diff options
913 files changed, 33855 insertions, 12119 deletions
diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index 986e44387dad..2ba45caabada 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -653,6 +653,9 @@ cpuidle.off=1 [CPU_IDLE] disable the cpuidle sub-system + cpufreq.off=1 [CPU_FREQ] + disable the cpufreq sub-system + cpu_init_udelay=N [X86] Delay for N microsec between assert and de-assert of APIC INIT to start processors. This delay occurs @@ -1183,6 +1186,12 @@ functions that can be changed at run time by the set_graph_notrace file in the debugfs tracing directory. + ftrace_graph_max_depth=<uint> + [FTRACE] Used with the function graph tracer. This is + the max depth it will trace into a function. This value + can be changed at run time by the max_graph_depth file + in the tracefs tracing directory. default: 0 (no limit) + gamecon.map[2|3]= [HW,JOY] Multisystem joystick and NES/SNES/PSX pad support via parallel port (up to 5 devices per port) diff --git a/Documentation/arm64/silicon-errata.txt b/Documentation/arm64/silicon-errata.txt index a71b8095dbd8..2f66683500b8 100644 --- a/Documentation/arm64/silicon-errata.txt +++ b/Documentation/arm64/silicon-errata.txt @@ -68,3 +68,4 @@ stable kernels. | | | | | | Qualcomm Tech. | Falkor v1 | E1003 | QCOM_FALKOR_ERRATUM_1003 | | Qualcomm Tech. | Falkor v1 | E1009 | QCOM_FALKOR_ERRATUM_1009 | +| Qualcomm Tech. | QDF2400 ITS | E0065 | QCOM_QDF2400_ERRATUM_0065 | diff --git a/Documentation/cgroup-v2.txt b/Documentation/cgroup-v2.txt index 3b8449f8ac7e..49d7c997fa1e 100644 --- a/Documentation/cgroup-v2.txt +++ b/Documentation/cgroup-v2.txt @@ -1142,16 +1142,17 @@ used by the kernel. pids.max - A read-write single value file which exists on non-root cgroups. The - default is "max". + A read-write single value file which exists on non-root + cgroups. The default is "max". - Hard limit of number of processes. + Hard limit of number of processes. pids.current - A read-only single value file which exists on all cgroups. + A read-only single value file which exists on all cgroups. - The number of processes currently in the cgroup and its descendants. + The number of processes currently in the cgroup and its + descendants. Organisational operations are not blocked by cgroup policies, so it is possible to have pids.current > pids.max. This can be done by either diff --git a/Documentation/dev-tools/kcov.rst b/Documentation/dev-tools/kcov.rst index 2c41b713841f..44886c91e112 100644 --- a/Documentation/dev-tools/kcov.rst +++ b/Documentation/dev-tools/kcov.rst @@ -10,7 +10,7 @@ Note that kcov does not aim to collect as much coverage as possible. It aims to collect more or less stable coverage that is function of syscall inputs. To achieve this goal it does not collect coverage in soft/hard interrupts and instrumentation of some inherently non-deterministic parts of kernel is -disbled (e.g. scheduler, locking). +disabled (e.g. scheduler, locking). Usage ----- diff --git a/Documentation/devicetree/bindings/net/brcm,bcmgenet.txt b/Documentation/devicetree/bindings/net/brcm,bcmgenet.txt index 10587bdadbbe..26c77d985faf 100644 --- a/Documentation/devicetree/bindings/net/brcm,bcmgenet.txt +++ b/Documentation/devicetree/bindings/net/brcm,bcmgenet.txt @@ -2,11 +2,14 @@ Required properties: - compatible: should contain one of "brcm,genet-v1", "brcm,genet-v2", - "brcm,genet-v3", "brcm,genet-v4". + "brcm,genet-v3", "brcm,genet-v4", "brcm,genet-v5". - reg: address and length of the register set for the device -- interrupts: must be two cells, the first cell is the general purpose - interrupt line, while the second cell is the interrupt for the ring - RX and TX queues operating in ring mode +- interrupts and/or interrupts-extended: must be two cells, the first cell + is the general purpose interrupt line, while the second cell is the + interrupt for the ring RX and TX queues operating in ring mode. An + optional third interrupt cell for Wake-on-LAN can be specified. + See Documentation/devicetree/bindings/interrupt-controller/interrupts.txt + for information on the property specifics. - phy-mode: see ethernet.txt file in the same directory - #address-cells: should be 1 - #size-cells: should be 1 @@ -29,15 +32,15 @@ Optional properties: Required child nodes: -- mdio bus node: this node should always be present regarless of the PHY +- mdio bus node: this node should always be present regardless of the PHY configuration of the GENET instance MDIO bus node required properties: - compatible: should contain one of "brcm,genet-mdio-v1", "brcm,genet-mdio-v2" - "brcm,genet-mdio-v3", "brcm,genet-mdio-v4", the version has to match the - parent node compatible property (e.g: brcm,genet-v4 pairs with - brcm,genet-mdio-v4) + "brcm,genet-mdio-v3", "brcm,genet-mdio-v4", "brcm,genet-mdio-v5", the version + has to match the parent node compatible property (e.g: brcm,genet-v4 pairs + with brcm,genet-mdio-v4) - reg: address and length relative to the parent node base register address - #address-cells: address cell for MDIO bus addressing, should be 1 - #size-cells: size of the cells for MDIO bus addressing, should be 0 diff --git a/Documentation/devicetree/bindings/net/brcm,unimac-mdio.txt b/Documentation/devicetree/bindings/net/brcm,unimac-mdio.txt index ab0bb4247d14..4648948f7c3b 100644 --- a/Documentation/devicetree/bindings/net/brcm,unimac-mdio.txt +++ b/Documentation/devicetree/bindings/net/brcm,unimac-mdio.txt @@ -2,8 +2,9 @@ Required properties: - compatible: should one from "brcm,genet-mdio-v1", "brcm,genet-mdio-v2", - "brcm,genet-mdio-v3", "brcm,genet-mdio-v4" or "brcm,unimac-mdio" -- reg: address and length of the regsiter set for the device, first one is the + "brcm,genet-mdio-v3", "brcm,genet-mdio-v4", "brcm,genet-mdio-v5" or + "brcm,unimac-mdio" +- reg: address and length of the register set for the device, first one is the base register, and the second one is optional and for indirect accesses to larger than 16-bits MDIO transactions - reg-names: name(s) of the register must be "mdio" and optional "mdio_indir_rw" diff --git a/Documentation/devicetree/bindings/net/marvell-pp2.txt b/Documentation/devicetree/bindings/net/marvell-pp2.txt index 4754364df4c6..6b4956beff8c 100644 --- a/Documentation/devicetree/bindings/net/marvell-pp2.txt +++ b/Documentation/devicetree/bindings/net/marvell-pp2.txt @@ -1,17 +1,28 @@ -* Marvell Armada 375 Ethernet Controller (PPv2) +* Marvell Armada 375 Ethernet Controller (PPv2.1) + Marvell Armada 7K/8K Ethernet Controller (PPv2.2) Required properties: -- compatible: should be "marvell,armada-375-pp2" +- compatible: should be one of: + "marvell,armada-375-pp2" + "marvell,armada-7k-pp2" - reg: addresses and length of the register sets for the device. - Must contain the following register sets: + For "marvell,armada-375-pp2", must contain the following register + sets: - common controller registers - LMS registers - In addition, at least one port register set is required. -- clocks: a pointer to the reference clocks for this device, consequently: - - main controller clock - - GOP clock -- clock-names: names of used clocks, must be "pp_clk" and "gop_clk". + - one register area per Ethernet port + For "marvell,armada-7k-pp2", must contain the following register + sets: + - packet processor registers + - networking interfaces registers + +- clocks: pointers to the reference clocks for this device, consequently: + - main controller clock (for both armada-375-pp2 and armada-7k-pp2) + - GOP clock (for both armada-375-pp2 and armada-7k-pp2) + - MG clock (only for armada-7k-pp2) +- clock-names: names of used clocks, must be "pp_clk", "gop_clk" and + "mg_clk" (the latter only for armada-7k-pp2). The ethernet ports are represented by subnodes. At least one port is required. @@ -19,8 +30,10 @@ required. Required properties (port): - interrupts: interrupt for the port -- port-id: should be '0' or '1' for ethernet ports, and '2' for the - loopback port +- port-id: ID of the port from the MAC point of view +- gop-port-id: only for marvell,armada-7k-pp2, ID of the port from the + GOP (Group Of Ports) point of view. This ID is used to index the + per-port registers in the second register area. - phy-mode: See ethernet.txt file in the same directory Optional properties (port): @@ -29,7 +42,7 @@ Optional properties (port): - phy: a phandle to a phy node defining the PHY address (as the reg property, a single integer). -Example: +Example for marvell,armada-375-pp2: ethernet@f0000 { compatible = "marvell,armada-375-pp2"; @@ -57,3 +70,30 @@ ethernet@f0000 { phy-mode = "gmii"; }; }; + +Example for marvell,armada-7k-pp2: + +cpm_ethernet: ethernet@0 { + compatible = "marvell,armada-7k-pp22"; + reg = <0x0 0x100000>, <0x129000 0xb000>; + clocks = <&cpm_syscon0 1 3>, <&cpm_syscon0 1 9>, <&cpm_syscon0 1 5>; + clock-names = "pp_clk", "gop_clk", "gp_clk"; + + eth0: eth0 { + interrupts = <GIC_SPI 37 IRQ_TYPE_LEVEL_HIGH>; + port-id = <0>; + gop-port-id = <0>; + }; + + eth1: eth1 { + interrupts = <GIC_SPI 38 IRQ_TYPE_LEVEL_HIGH>; + port-id = <1>; + gop-port-id = <2>; + }; + + eth2: eth2 { + interrupts = <GIC_SPI 39 IRQ_TYPE_LEVEL_HIGH>; + port-id = <2>; + gop-port-id = <3>; + }; +}; diff --git a/Documentation/devicetree/bindings/net/stmmac.txt b/Documentation/devicetree/bindings/net/stmmac.txt index d3bfc2b30fb5..a7b0e41cb264 100644 --- a/Documentation/devicetree/bindings/net/stmmac.txt +++ b/Documentation/devicetree/bindings/net/stmmac.txt @@ -28,9 +28,9 @@ Optional properties: clocks may be specified in derived bindings. - clock-names: One name for each entry in the clocks property, the first one should be "stmmaceth" and the second one should be "pclk". -- clk_ptp_ref: this is the PTP reference clock; in case of the PTP is - available this clock is used for programming the Timestamp Addend Register. - If not passed then the system clock will be used and this is fine on some +- ptp_ref: this is the PTP reference clock; in case of the PTP is available + this clock is used for programming the Timestamp Addend Register. If not + passed then the system clock will be used and this is fine on some platforms. - tx-fifo-depth: See ethernet.txt file in the same directory - rx-fifo-depth: See ethernet.txt file in the same directory @@ -72,7 +72,35 @@ Optional properties: - snps,mb: mixed-burst - snps,rb: rebuild INCRx Burst - mdio: with compatible = "snps,dwmac-mdio", create and register mdio bus. - +- Multiple RX Queues parameters: below the list of all the parameters to + configure the multiple RX queues: + - snps,rx-queues-to-use: number of RX queues to be used in the driver + - Choose one of these RX scheduling algorithms: + - snps,rx-sched-sp: Strict priority + - snps,rx-sched-wsp: Weighted Strict priority + - For each RX queue + - Choose one of these modes: + - snps,dcb-algorithm: Queue to be enabled as DCB + - snps,avb-algorithm: Queue to be enabled as AVB + - snps,map-to-dma-channel: Channel to map +- Multiple TX Queues parameters: below the list of all the parameters to + configure the multiple TX queues: + - snps,tx-queues-to-use: number of TX queues to be used in the driver + - Choose one of these TX scheduling algorithms: + - snps,tx-sched-wrr: Weighted Round Robin + - snps,tx-sched-wfq: Weighted Fair Queuing + - snps,tx-sched-dwrr: Deficit Weighted Round Robin + - snps,tx-sched-sp: Strict priority + - For each TX queue + - snps,weight: TX queue weight (if using a DCB weight algorithm) + - Choose one of these modes: + - snps,dcb-algorithm: TX queue will be working in DCB + - snps,avb-algorithm: TX queue will be working in AVB + - Configure Credit Base Shaper (if AVB Mode selected): + - snps,send_slope: enable Low Power Interface + - snps,idle_slope: unlock on WoL + - snps,high_credit: max write outstanding req. limit + - snps,low_credit: max read outstanding req. limit Examples: stmmac_axi_setup: stmmac-axi-config { @@ -81,6 +109,32 @@ Examples: snps,blen = <256 128 64 32 0 0 0>; }; + mtl_rx_setup: rx-queues-config { + snps,rx-queues-to-use = <1>; + snps,rx-sched-sp; + queue0 { + snps,dcb-algorithm; + snps,map-to-dma-channel = <0x0>; + }; + }; + + mtl_tx_setup: tx-queues-config { + snps,tx-queues-to-use = <2>; + snps,tx-sched-wrr; + queue0 { + snps,weight = <0x10>; + snps,dcb-algorithm; + }; + + queue1 { + snps,avb-algorithm; + snps,send_slope = <0x1000>; + snps,idle_slope = <0x1000>; + snps,high_credit = <0x3E800>; + snps,low_credit = <0xFFC18000>; + }; + }; + gmac0: ethernet@e0800000 { compatible = "st,spear600-gmac"; reg = <0xe0800000 0x8000>; @@ -104,4 +158,6 @@ Examples: phy1: ethernet-phy@0 { }; }; + snps,mtl-rx-config = <&mtl_rx_setup>; + snps,mtl-tx-config = <&mtl_tx_setup>; }; diff --git a/Documentation/devicetree/bindings/powerpc/4xx/emac.txt b/Documentation/devicetree/bindings/powerpc/4xx/emac.txt index 712baf6c3e24..44b842b6ca15 100644 --- a/Documentation/devicetree/bindings/powerpc/4xx/emac.txt +++ b/Documentation/devicetree/bindings/powerpc/4xx/emac.txt @@ -71,6 +71,9 @@ For Axon it can be absent, though my current driver doesn't handle phy-address yet so for now, keep 0x00ffffff in it. + - phy-handle : Used to describe configurations where a external PHY + is used. Please refer to: + Documentation/devicetree/bindings/net/ethernet.txt - rx-fifo-size-gige : 1 cell, Rx fifo size in bytes for 1000 Mb/sec operations (if absent the value is the same as rx-fifo-size). For Axon, either absent or 2048. @@ -81,8 +84,22 @@ offload, phandle of the TAH device node. - tah-channel : 1 cell, optional. If appropriate, channel used on the TAH engine. + - fixed-link : Fixed-link subnode describing a link to a non-MDIO + managed entity. See + Documentation/devicetree/bindings/net/fixed-link.txt + for details. + - mdio subnode : When the EMAC has a phy connected to its local + mdio, which us supported by the kernel's network + PHY library in drivers/net/phy, there must be device + tree subnode with the following required properties: + - #address-cells: Must be <1>. + - #size-cells: Must be <0>. - Example: + For PHY definitions: Please refer to + Documentation/devicetree/bindings/net/phy.txt and + Documentation/devicetree/bindings/net/ethernet.txt + + Examples: EMAC0: ethernet@40000800 { device_type = "network"; @@ -104,6 +121,48 @@ zmii-channel = <0>; }; + EMAC1: ethernet@ef600c00 { + device_type = "network"; + compatible = "ibm,emac-apm821xx", "ibm,emac4sync"; + interrupt-parent = <&EMAC1>; + interrupts = <0 1>; + #interrupt-cells = <1>; + #address-cells = <0>; + #size-cells = <0>; + interrupt-map = <0 &UIC2 0x10 IRQ_TYPE_LEVEL_HIGH /* Status */ + 1 &UIC2 0x14 IRQ_TYPE_LEVEL_HIGH /* Wake */>; + reg = <0xef600c00 0x000000c4>; + local-mac-address = [000000000000]; /* Filled in by U-Boot */ + mal-device = <&MAL0>; + mal-tx-channel = <0>; + mal-rx-channel = <0>; + cell-index = <0>; + max-frame-size = <9000>; + rx-fifo-size = <16384>; + tx-fifo-size = <2048>; + fifo-entry-size = <10>; + phy-mode = "rgmii"; + phy-handle = <&phy0>; + phy-map = <0x00000000>; + rgmii-device = <&RGMII0>; + rgmii-channel = <0>; + tah-device = <&TAH0>; + tah-channel = <0>; + has-inverted-stacr-oc; + has-new-stacr-staopc; + + mdio { + #address-cells = <1>; + #size-cells = <0>; + + phy0: ethernet-phy@0 { + compatible = "ethernet-phy-ieee802.3-c22"; + reg = <0>; + }; + }; + }; + + ii) McMAL node Required properties: @@ -145,4 +204,3 @@ - revision : as provided by the RGMII new version register if available. For Axon: 0x0000012a - diff --git a/Documentation/devicetree/bindings/regulator/ti-abb-regulator.txt b/Documentation/devicetree/bindings/regulator/ti-abb-regulator.txt index c3f6546ebac7..6a23ad9ac53a 100644 --- a/Documentation/devicetree/bindings/regulator/ti-abb-regulator.txt +++ b/Documentation/devicetree/bindings/regulator/ti-abb-regulator.txt @@ -45,7 +45,7 @@ Required Properties: Optional Properties: - reg-names: In addition to the required properties, the following are optional - "efuse-address" - Contains efuse base address used to pick up ABB info. - - "ldo-address" - Contains address of ABB LDO overide register address. + - "ldo-address" - Contains address of ABB LDO override register. "efuse-address" is required for this. - ti,ldovbb-vset-mask - Required if ldo-address is set, mask for LDO override register to provide override vset value. diff --git a/Documentation/devicetree/bindings/usb/usb251xb.txt b/Documentation/devicetree/bindings/usb/usb251xb.txt index 0c065f77658f..3957d4edaa74 100644 --- a/Documentation/devicetree/bindings/usb/usb251xb.txt +++ b/Documentation/devicetree/bindings/usb/usb251xb.txt @@ -7,18 +7,18 @@ Required properties : - compatible : Should be "microchip,usb251xb" or one of the specific types: "microchip,usb2512b", "microchip,usb2512bi", "microchip,usb2513b", "microchip,usb2513bi", "microchip,usb2514b", "microchip,usb2514bi" - - hub-reset-gpios : Should specify the gpio for hub reset + - reset-gpios : Should specify the gpio for hub reset + - reg : I2C address on the selected bus (default is <0x2C>) Optional properties : - - reg : I2C address on the selected bus (default is <0x2C>) - skip-config : Skip Hub configuration, but only send the USB-Attach command - - vendor-id : USB Vendor ID of the hub (16 bit, default is 0x0424) - - product-id : USB Product ID of the hub (16 bit, default depends on type) - - device-id : USB Device ID of the hub (16 bit, default is 0x0bb3) - - language-id : USB Language ID (16 bit, default is 0x0000) - - manufacturer : USB Manufacturer string (max 31 characters long) - - product : USB Product string (max 31 characters long) - - serial : USB Serial string (max 31 characters long) + - vendor-id : Set USB Vendor ID of the hub (16 bit, default is 0x0424) + - product-id : Set USB Product ID of the hub (16 bit, default depends on type) + - device-id : Set USB Device ID of the hub (16 bit, default is 0x0bb3) + - language-id : Set USB Language ID (16 bit, default is 0x0000) + - manufacturer : Set USB Manufacturer string (max 31 characters long) + - product : Set USB Product string (max 31 characters long) + - serial : Set USB Serial string (max 31 characters long) - {bus,self}-powered : selects between self- and bus-powered operation (default is self-powered) - disable-hi-speed : disable USB Hi-Speed support @@ -31,8 +31,10 @@ Optional properties : (default is individual) - dynamic-power-switching : enable auto-switching from self- to bus-powered operation if the local power source is removed or unavailable - - oc-delay-{100us,4ms,8ms,16ms} : set over current timer delay (default is 8ms) - - compound-device : indicated the hub is part of a compound device + - oc-delay-us : Delay time (in microseconds) for filtering the over-current + sense inputs. Valid values are 100, 4000, 8000 (default) and 16000. If + an invalid value is given, the default is used instead. + - compound-device : indicate the hub is part of a compound device - port-mapping-mode : enable port mapping mode - string-support : enable string descriptor support (required for manufacturer, product and serial string configuration) @@ -40,34 +42,15 @@ Optional properties : device connected. - sp-disabled-ports : Specifies the ports which will be self-power disabled - bp-disabled-ports : Specifies the ports which will be bus-power disabled - - max-sp-power : Specifies the maximum current the hub consumes from an - upstream port when operating as self-powered hub including the power - consumption of a permanently attached peripheral if the hub is - configured as a compound device. The value is given in mA in a 0 - 500 - range (default is 2). - - max-bp-power : Specifies the maximum current the hub consumes from an - upstream port when operating as bus-powered hub including the power - consumption of a permanently attached peripheral if the hub is - configured as a compound device. The value is given in mA in a 0 - 500 - range (default is 100). - - max-sp-current : Specifies the maximum current the hub consumes from an - upstream port when operating as self-powered hub EXCLUDING the power - consumption of a permanently attached peripheral if the hub is - configured as a compound device. The value is given in mA in a 0 - 500 - range (default is 2). - - max-bp-current : Specifies the maximum current the hub consumes from an - upstream port when operating as bus-powered hub EXCLUDING the power - consumption of a permanently attached peripheral if the hub is - configured as a compound device. The value is given in mA in a 0 - 500 - range (default is 100). - - power-on-time : Specifies the time it takes from the time the host initiates - the power-on sequence to a port until the port has adequate power. The - value is given in ms in a 0 - 510 range (default is 100ms). + - power-on-time-ms : Specifies the time it takes from the time the host + initiates the power-on sequence to a port until the port has adequate + power. The value is given in ms in a 0 - 510 range (default is 100ms). Examples: usb2512b@2c { compatible = "microchip,usb2512b"; - hub-reset-gpios = <&gpio1 4 GPIO_ACTIVE_LOW>; + reg = <0x2c>; + reset-gpios = <&gpio1 4 GPIO_ACTIVE_LOW>; }; usb2514b@2c { diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt index fc73eeb7b3b8..ed3d0791eb27 100644 --- a/Documentation/networking/ip-sysctl.txt +++ b/Documentation/networking/ip-sysctl.txt @@ -640,11 +640,6 @@ tcp_tso_win_divisor - INTEGER building larger TSO frames. Default: 3 -tcp_tw_recycle - BOOLEAN - Enable fast recycling TIME-WAIT sockets. Default value is 0. - It should not be changed without advice/request of technical - experts. - tcp_tw_reuse - BOOLEAN Allow to reuse TIME-WAIT sockets for new connections when it is safe from protocol viewpoint. Default value is 0. @@ -1006,7 +1001,8 @@ accept_redirects - BOOLEAN FALSE (router) forwarding - BOOLEAN - Enable IP forwarding on this interface. + Enable IP forwarding on this interface. This controls whether packets + received _on_ this interface can be forwarded. mc_forwarding - BOOLEAN Do multicast routing. The kernel needs to be compiled with CONFIG_MROUTE diff --git a/Documentation/networking/mpls-sysctl.txt b/Documentation/networking/mpls-sysctl.txt index 15d8d16934fd..2f24a1912a48 100644 --- a/Documentation/networking/mpls-sysctl.txt +++ b/Documentation/networking/mpls-sysctl.txt @@ -19,6 +19,25 @@ platform_labels - INTEGER Possible values: 0 - 1048575 Default: 0 +ip_ttl_propagate - BOOL + Control whether TTL is propagated from the IPv4/IPv6 header to + the MPLS header on imposing labels and propagated from the + MPLS header to the IPv4/IPv6 header on popping the last label. + + If disabled, the MPLS transport network will appear as a + single hop to transit traffic. + + 0 - disabled / RFC 3443 [Short] Pipe Model + 1 - enabled / RFC 3443 Uniform Model (default) + +default_ttl - BOOL + Default TTL value to use for MPLS packets where it cannot be + propagated from an IP header, either because one isn't present + or ip_ttl_propagate has been disabled. + + Possible values: 1 - 255 + Default: 255 + conf/<interface>/input - BOOL Control whether packets can be input on this interface. diff --git a/Documentation/trace/kprobetrace.txt b/Documentation/trace/kprobetrace.txt index e4991fb1eedc..41ef9d8efe95 100644 --- a/Documentation/trace/kprobetrace.txt +++ b/Documentation/trace/kprobetrace.txt @@ -12,7 +12,7 @@ kprobes can probe (this means, all functions body except for __kprobes functions). Unlike the Tracepoint based event, this can be added and removed dynamically, on the fly. -To enable this feature, build your kernel with CONFIG_KPROBE_EVENT=y. +To enable this feature, build your kernel with CONFIG_KPROBE_EVENTS=y. Similar to the events tracer, this doesn't need to be activated via current_tracer. Instead of that, add probe points via diff --git a/Documentation/trace/uprobetracer.txt b/Documentation/trace/uprobetracer.txt index fa7b680ee8a0..bf526a7c5559 100644 --- a/Documentation/trace/uprobetracer.txt +++ b/Documentation/trace/uprobetracer.txt @@ -7,7 +7,7 @@ Overview -------- Uprobe based trace events are similar to kprobe based trace events. -To enable this feature, build your kernel with CONFIG_UPROBE_EVENT=y. +To enable this feature, build your kernel with CONFIG_UPROBE_EVENTS=y. Similar to the kprobe-event tracer, this doesn't need to be activated via current_tracer. Instead of that, add probe points via diff --git a/Documentation/virtual/kvm/api.txt b/Documentation/virtual/kvm/api.txt index 069450938b79..3c248f772ae6 100644 --- a/Documentation/virtual/kvm/api.txt +++ b/Documentation/virtual/kvm/api.txt @@ -951,6 +951,10 @@ This ioctl allows the user to create or modify a guest physical memory slot. When changing an existing slot, it may be moved in the guest physical memory space, or its flags may be modified. It may not be resized. Slots may not overlap in guest physical address space. +Bits 0-15 of "slot" specifies the slot id and this value should be +less than the maximum number of user memory slots supported per VM. +The maximum allowed slots can be queried using KVM_CAP_NR_MEMSLOTS, +if this capability is supported by the architecture. If KVM_CAP_MULTI_ADDRESS_SPACE is available, bits 16-31 of "slot" specifies the address space which is being modified. They must be diff --git a/Documentation/vm/userfaultfd.txt b/Documentation/vm/userfaultfd.txt index 0e5543a920e5..bb2f945f87ab 100644 --- a/Documentation/vm/userfaultfd.txt +++ b/Documentation/vm/userfaultfd.txt @@ -172,10 +172,6 @@ the same read(2) protocol as for the page fault notifications. The manager has to explicitly enable these events by setting appropriate bits in uffdio_api.features passed to UFFDIO_API ioctl: -UFFD_FEATURE_EVENT_EXIT - enable notification about exit() of the -non-cooperative process. When the monitored process exits, the uffd -manager will get UFFD_EVENT_EXIT. - UFFD_FEATURE_EVENT_FORK - enable userfaultfd hooks for fork(). When this feature is enabled, the userfaultfd context of the parent process is duplicated into the newly created process. The manager receives diff --git a/MAINTAINERS b/MAINTAINERS index c265a5fe4848..632e76223cc5 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -896,12 +896,19 @@ F: arch/arm64/boot/dts/apm/ APPLIED MICRO (APM) X-GENE SOC ETHERNET DRIVER M: Iyappan Subramanian <[email protected]> M: Keyur Chudgar <[email protected]> +M: Quan Nguyen <[email protected]> S: Supported F: drivers/net/ethernet/apm/xgene/ F: drivers/net/phy/mdio-xgene.c F: Documentation/devicetree/bindings/net/apm-xgene-enet.txt F: Documentation/devicetree/bindings/net/apm-xgene-mdio.txt +APPLIED MICRO (APM) X-GENE SOC ETHERNET (V2) DRIVER +M: Iyappan Subramanian <[email protected]> +M: Keyur Chudgar <[email protected]> +S: Supported +F: drivers/net/ethernet/apm/xgene-v2/ + APPLIED MICRO (APM) X-GENE SOC PMU M: Tai Nguyen <[email protected]> S: Supported @@ -8307,7 +8314,6 @@ M: Richard Leitner <[email protected]> S: Maintained F: drivers/usb/misc/usb251xb.c -F: include/linux/platform_data/usb251xb.h F: Documentation/devicetree/bindings/usb/usb251xb.txt MICROSOFT SURFACE PRO 3 BUTTON DRIVER @@ -11062,6 +11068,12 @@ F: include/linux/dma/dw.h F: include/linux/platform_data/dma-dw.h F: drivers/dma/dw/ +SYNOPSYS DESIGNWARE ENTERPRISE ETHERNET DRIVER +M: Jie Deng <[email protected]> +S: Supported +F: drivers/net/ethernet/synopsys/ + SYNOPSYS DESIGNWARE I2C DRIVER M: Jarkko Nikula <[email protected]> R: Andy Shevchenko <[email protected]> @@ -1,7 +1,7 @@ VERSION = 4 -PATCHLEVEL = 10 +PATCHLEVEL = 11 SUBLEVEL = 0 -EXTRAVERSION = +EXTRAVERSION = -rc2 NAME = Fearless Coyote # *DOCUMENTATION* diff --git a/arch/arc/include/asm/hugepage.h b/arch/arc/include/asm/hugepage.h index 317ff773e1ca..b18fcb606908 100644 --- a/arch/arc/include/asm/hugepage.h +++ b/arch/arc/include/asm/hugepage.h @@ -11,6 +11,7 @@ #define _ASM_ARC_HUGEPAGE_H #include <linux/types.h> +#define __ARCH_USE_5LEVEL_HACK #include <asm-generic/pgtable-nopmd.h> static inline pte_t pmd_pte(pmd_t pmd) diff --git a/arch/arc/include/asm/pgtable.h b/arch/arc/include/asm/pgtable.h index e94ca72b974e..ee22d40afef4 100644 --- a/arch/arc/include/asm/pgtable.h +++ b/arch/arc/include/asm/pgtable.h @@ -37,6 +37,7 @@ #include <asm/page.h> #include <asm/mmu.h> +#define __ARCH_USE_5LEVEL_HACK #include <asm-generic/pgtable-nopmd.h> #include <linux/const.h> diff --git a/arch/arm/include/asm/kvm_arm.h b/arch/arm/include/asm/kvm_arm.h index e22089fb44dc..a3f0b3d50089 100644 --- a/arch/arm/include/asm/kvm_arm.h +++ b/arch/arm/include/asm/kvm_arm.h @@ -209,6 +209,7 @@ #define HSR_EC_IABT_HYP (0x21) #define HSR_EC_DABT (0x24) #define HSR_EC_DABT_HYP (0x25) +#define HSR_EC_MAX (0x3f) #define HSR_WFI_IS_WFE (_AC(1, UL) << 0) diff --git a/arch/arm/include/asm/kvm_host.h b/arch/arm/include/asm/kvm_host.h index cc495d799c67..31ee468ce667 100644 --- a/arch/arm/include/asm/kvm_host.h +++ b/arch/arm/include/asm/kvm_host.h @@ -30,7 +30,6 @@ #define __KVM_HAVE_ARCH_INTC_INITIALIZED #define KVM_USER_MEM_SLOTS 32 -#define KVM_PRIVATE_MEM_SLOTS 4 #define KVM_COALESCED_MMIO_PAGE_OFFSET 1 #define KVM_HAVE_ONE_REG #define KVM_HALT_POLL_NS_DEFAULT 500000 diff --git a/arch/arm/include/asm/pgtable.h b/arch/arm/include/asm/pgtable.h index a8d656d9aec7..1c462381c225 100644 --- a/arch/arm/include/asm/pgtable.h +++ b/arch/arm/include/asm/pgtable.h @@ -20,6 +20,7 @@ #else +#define __ARCH_USE_5LEVEL_HACK #include <asm-generic/pgtable-nopud.h> #include <asm/memory.h> #include <asm/pgtable-hwdef.h> diff --git a/arch/arm/kvm/arm.c b/arch/arm/kvm/arm.c index c9a2103faeb9..96dba7cd8be7 100644 --- a/arch/arm/kvm/arm.c +++ b/arch/arm/kvm/arm.c @@ -221,6 +221,9 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_MAX_VCPUS: r = KVM_MAX_VCPUS; break; + case KVM_CAP_NR_MEMSLOTS: + r = KVM_USER_MEM_SLOTS; + break; case KVM_CAP_MSI_DEVID: if (!kvm) r = -EINVAL; diff --git a/arch/arm/kvm/handle_exit.c b/arch/arm/kvm/handle_exit.c index 4e40d1955e35..96af65a30d78 100644 --- a/arch/arm/kvm/handle_exit.c +++ b/arch/arm/kvm/handle_exit.c @@ -79,7 +79,19 @@ static int kvm_handle_wfx(struct kvm_vcpu *vcpu, struct kvm_run *run) return 1; } +static int kvm_handle_unknown_ec(struct kvm_vcpu *vcpu, struct kvm_run *run) +{ + u32 hsr = kvm_vcpu_get_hsr(vcpu); + + kvm_pr_unimpl("Unknown exception class: hsr: %#08x\n", + hsr); + + kvm_inject_undefined(vcpu); + return 1; +} + static exit_handle_fn arm_exit_handlers[] = { + [0 ... HSR_EC_MAX] = kvm_handle_unknown_ec, [HSR_EC_WFI] = kvm_handle_wfx, [HSR_EC_CP15_32] = kvm_handle_cp15_32, [HSR_EC_CP15_64] = kvm_handle_cp15_64, @@ -98,13 +110,6 @@ static exit_handle_fn kvm_get_exit_handler(struct kvm_vcpu *vcpu) { u8 hsr_ec = kvm_vcpu_trap_get_class(vcpu); - if (hsr_ec >= ARRAY_SIZE(arm_exit_handlers) || - !arm_exit_handlers[hsr_ec]) { - kvm_err("Unknown exception class: hsr: %#08x\n", - (unsigned int)kvm_vcpu_get_hsr(vcpu)); - BUG(); - } - return arm_exit_handlers[hsr_ec]; } diff --git a/arch/arm/xen/mm.c b/arch/arm/xen/mm.c index ce18c91b50a1..f0325d96b97a 100644 --- a/arch/arm/xen/mm.c +++ b/arch/arm/xen/mm.c @@ -198,6 +198,8 @@ static const struct dma_map_ops xen_swiotlb_dma_ops = { .unmap_page = xen_swiotlb_unmap_page, .dma_supported = xen_swiotlb_dma_supported, .set_dma_mask = xen_swiotlb_set_dma_mask, + .mmap = xen_swiotlb_dma_mmap, + .get_sgtable = xen_swiotlb_get_sgtable, }; int __init xen_mm_init(void) diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index a39029b5414e..8c7c244247b6 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -508,6 +508,16 @@ config QCOM_FALKOR_ERRATUM_1009 If unsure, say Y. +config QCOM_QDF2400_ERRATUM_0065 + bool "QDF2400 E0065: Incorrect GITS_TYPER.ITT_Entry_size" + default y + help + On Qualcomm Datacenter Technologies QDF2400 SoC, ITS hardware reports + ITE size incorrectly. The GITS_TYPER.ITT_Entry_size field should have + been indicated as 16Bytes (0xf), not 8Bytes (0x7). + + If unsure, say Y. + endmenu diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h index f21fd3894370..e7705e7bb07b 100644 --- a/arch/arm64/include/asm/kvm_host.h +++ b/arch/arm64/include/asm/kvm_host.h @@ -30,8 +30,7 @@ #define __KVM_HAVE_ARCH_INTC_INITIALIZED -#define KVM_USER_MEM_SLOTS 32 -#define KVM_PRIVATE_MEM_SLOTS 4 +#define KVM_USER_MEM_SLOTS 512 #define KVM_COALESCED_MMIO_PAGE_OFFSET 1 #define KVM_HALT_POLL_NS_DEFAULT 500000 diff --git a/arch/arm64/include/asm/pgtable-types.h b/arch/arm64/include/asm/pgtable-types.h index 69b2fd41503c..345a072b5856 100644 --- a/arch/arm64/include/asm/pgtable-types.h +++ b/arch/arm64/include/asm/pgtable-types.h @@ -55,9 +55,13 @@ typedef struct { pteval_t pgprot; } pgprot_t; #define __pgprot(x) ((pgprot_t) { (x) } ) #if CONFIG_PGTABLE_LEVELS == 2 +#define __ARCH_USE_5LEVEL_HACK #include <asm-generic/pgtable-nopmd.h> #elif CONFIG_PGTABLE_LEVELS == 3 +#define __ARCH_USE_5LEVEL_HACK #include <asm-generic/pgtable-nopud.h> +#elif CONFIG_PGTABLE_LEVELS == 4 +#include <asm-generic/5level-fixup.h> #endif #endif /* __ASM_PGTABLE_TYPES_H */ diff --git a/arch/arm64/kvm/handle_exit.c b/arch/arm64/kvm/handle_exit.c index 1bfe30dfbfe7..fa1b18e364fc 100644 --- a/arch/arm64/kvm/handle_exit.c +++ b/arch/arm64/kvm/handle_exit.c @@ -135,7 +135,19 @@ static int kvm_handle_guest_debug(struct kvm_vcpu *vcpu, struct kvm_run *run) return ret; } +static int kvm_handle_unknown_ec(struct kvm_vcpu *vcpu, struct kvm_run *run) +{ + u32 hsr = kvm_vcpu_get_hsr(vcpu); + + kvm_pr_unimpl("Unknown exception class: hsr: %#08x -- %s\n", + hsr, esr_get_class_string(hsr)); + + kvm_inject_undefined(vcpu); + return 1; +} + static exit_handle_fn arm_exit_handlers[] = { + [0 ... ESR_ELx_EC_MAX] = kvm_handle_unknown_ec, [ESR_ELx_EC_WFx] = kvm_handle_wfx, [ESR_ELx_EC_CP15_32] = kvm_handle_cp15_32, [ESR_ELx_EC_CP15_64] = kvm_handle_cp15_64, @@ -162,13 +174,6 @@ static exit_handle_fn kvm_get_exit_handler(struct kvm_vcpu *vcpu) u32 hsr = kvm_vcpu_get_hsr(vcpu); u8 hsr_ec = ESR_ELx_EC(hsr); - if (hsr_ec >= ARRAY_SIZE(arm_exit_handlers) || - !arm_exit_handlers[hsr_ec]) { - kvm_err("Unknown exception class: hsr: %#08x -- %s\n", - hsr, esr_get_class_string(hsr)); - BUG(); - } - return arm_exit_handlers[hsr_ec]; } diff --git a/arch/arm64/kvm/hyp/tlb.c b/arch/arm64/kvm/hyp/tlb.c index e8e7ba2bc11f..9e1d2b75eecd 100644 --- a/arch/arm64/kvm/hyp/tlb.c +++ b/arch/arm64/kvm/hyp/tlb.c @@ -18,14 +18,62 @@ #include <asm/kvm_hyp.h> #include <asm/tlbflush.h> +static void __hyp_text __tlb_switch_to_guest_vhe(struct kvm *kvm) +{ + u64 val; + + /* + * With VHE enabled, we have HCR_EL2.{E2H,TGE} = {1,1}, and + * most TLB operations target EL2/EL0. In order to affect the + * guest TLBs (EL1/EL0), we need to change one of these two + * bits. Changing E2H is impossible (goodbye TTBR1_EL2), so + * let's flip TGE before executing the TLB operation. + */ + write_sysreg(kvm->arch.vttbr, vttbr_el2); + val = read_sysreg(hcr_el2); + val &= ~HCR_TGE; + write_sysreg(val, hcr_el2); + isb(); +} + +static void __hyp_text __tlb_switch_to_guest_nvhe(struct kvm *kvm) +{ + write_sysreg(kvm->arch.vttbr, vttbr_el2); + isb(); +} + +static hyp_alternate_select(__tlb_switch_to_guest, + __tlb_switch_to_guest_nvhe, + __tlb_switch_to_guest_vhe, + ARM64_HAS_VIRT_HOST_EXTN); + +static void __hyp_text __tlb_switch_to_host_vhe(struct kvm *kvm) +{ + /* + * We're done with the TLB operation, let's restore the host's + * view of HCR_EL2. + */ + write_sysreg(0, vttbr_el2); + write_sysreg(HCR_HOST_VHE_FLAGS, hcr_el2); +} + +static void __hyp_text __tlb_switch_to_host_nvhe(struct kvm *kvm) +{ + write_sysreg(0, vttbr_el2); +} + +static hyp_alternate_select(__tlb_switch_to_host, + __tlb_switch_to_host_nvhe, + __tlb_switch_to_host_vhe, + ARM64_HAS_VIRT_HOST_EXTN); + void __hyp_text __kvm_tlb_flush_vmid_ipa(struct kvm *kvm, phys_addr_t ipa) { dsb(ishst); /* Switch to requested VMID */ kvm = kern_hyp_va(kvm); - write_sysreg(kvm->arch.vttbr, vttbr_el2); - isb(); + __tlb_switch_to_guest()(kvm); /* * We could do so much better if we had the VA as well. @@ -46,7 +94,7 @@ void __hyp_text __kvm_tlb_flush_vmid_ipa(struct kvm *kvm, phys_addr_t ipa) dsb(ish); isb(); - write_sysreg(0, vttbr_el2); + __tlb_switch_to_host()(kvm); } void __hyp_text __kvm_tlb_flush_vmid(struct kvm *kvm) @@ -55,14 +103,13 @@ void __hyp_text __kvm_tlb_flush_vmid(struct kvm *kvm) /* Switch to requested VMID */ kvm = kern_hyp_va(kvm); - write_sysreg(kvm->arch.vttbr, vttbr_el2); - isb(); + __tlb_switch_to_guest()(kvm); __tlbi(vmalls12e1is); dsb(ish); isb(); - write_sysreg(0, vttbr_el2); + __tlb_switch_to_host()(kvm); } void __hyp_text __kvm_tlb_flush_local_vmid(struct kvm_vcpu *vcpu) @@ -70,14 +117,13 @@ void __hyp_text __kvm_tlb_flush_local_vmid(struct kvm_vcpu *vcpu) struct kvm *kvm = kern_hyp_va(kern_hyp_va(vcpu)->kvm); /* Switch to requested VMID */ - write_sysreg(kvm->arch.vttbr, vttbr_el2); - isb(); + __tlb_switch_to_guest()(kvm); __tlbi(vmalle1); dsb(nsh); isb(); - write_sysreg(0, vttbr_el2); + __tlb_switch_to_host()(kvm); } void __hyp_text __kvm_flush_vm_context(void) diff --git a/arch/avr32/include/asm/pgtable-2level.h b/arch/avr32/include/asm/pgtable-2level.h index 425dd567b5b9..d5b1c63993ec 100644 --- a/arch/avr32/include/asm/pgtable-2level.h +++ b/arch/avr32/include/asm/pgtable-2level.h @@ -8,6 +8,7 @@ #ifndef __ASM_AVR32_PGTABLE_2LEVEL_H #define __ASM_AVR32_PGTABLE_2LEVEL_H +#define __ARCH_USE_5LEVEL_HACK #include <asm-generic/pgtable-nopmd.h> /* diff --git a/arch/avr32/oprofile/backtrace.c b/arch/avr32/oprofile/backtrace.c index 75d9ad6f99cf..29cf2f191bfd 100644 --- a/arch/avr32/oprofile/backtrace.c +++ b/arch/avr32/oprofile/backtrace.c @@ -14,7 +14,7 @@ */ #include <linux/oprofile.h> -#include <linux/sched.h> +#include <linux/ptrace.h> #include <linux/uaccess.h> /* The first two words of each frame on the stack look like this if we have diff --git a/arch/cris/arch-v32/drivers/cryptocop.c b/arch/cris/arch-v32/drivers/cryptocop.c index ae6903d7fdbe..14970f11bbf2 100644 --- a/arch/cris/arch-v32/drivers/cryptocop.c +++ b/arch/cris/arch-v32/drivers/cryptocop.c @@ -2086,7 +2086,7 @@ static void cryptocop_job_queue_close(void) dma_in_cfg.en = regk_dma_no; REG_WR(dma, IN_DMA_INST, rw_cfg, dma_in_cfg); - /* Disble the cryptocop. */ + /* Disable the cryptocop. */ rw_cfg = REG_RD(strcop, regi_strcop, rw_cfg); rw_cfg.en = 0; REG_WR(strcop, regi_strcop, rw_cfg, rw_cfg); diff --git a/arch/cris/include/asm/pgtable.h b/arch/cris/include/asm/pgtable.h index 2a3210ba4c72..fa3a73004cc5 100644 --- a/arch/cris/include/asm/pgtable.h +++ b/arch/cris/include/asm/pgtable.h @@ -6,6 +6,7 @@ #define _CRIS_PGTABLE_H #include <asm/page.h> +#define __ARCH_USE_5LEVEL_HACK #include <asm-generic/pgtable-nopmd.h> #ifndef __ASSEMBLY__ diff --git a/arch/frv/include/asm/pgtable.h b/arch/frv/include/asm/pgtable.h index a0513d463a1f..ab6e7e961b54 100644 --- a/arch/frv/include/asm/pgtable.h +++ b/arch/frv/include/asm/pgtable.h @@ -16,6 +16,7 @@ #ifndef _ASM_PGTABLE_H #define _ASM_PGTABLE_H +#include <asm-generic/5level-fixup.h> #include <asm/mem-layout.h> #include <asm/setup.h> #include <asm/processor.h> diff --git a/arch/h8300/include/asm/pgtable.h b/arch/h8300/include/asm/pgtable.h index 8341db67821d..7d265d28ba5e 100644 --- a/arch/h8300/include/asm/pgtable.h +++ b/arch/h8300/include/asm/pgtable.h @@ -1,5 +1,6 @@ #ifndef _H8300_PGTABLE_H #define _H8300_PGTABLE_H +#define __ARCH_USE_5LEVEL_HACK #include <asm-generic/pgtable-nopud.h> #include <asm-generic/pgtable.h> #define pgtable_cache_init() do { } while (0) diff --git a/arch/h8300/kernel/ptrace_h.c b/arch/h8300/kernel/ptrace_h.c index fe3b5673baba..f5ff3b794c85 100644 --- a/arch/h8300/kernel/ptrace_h.c +++ b/arch/h8300/kernel/ptrace_h.c @@ -9,7 +9,7 @@ */ #include <linux/linkage.h> -#include <linux/sched.h> +#include <linux/sched/signal.h> #include <asm/ptrace.h> #define BREAKINST 0x5730 /* trapa #3 */ diff --git a/arch/hexagon/include/asm/pgtable.h b/arch/hexagon/include/asm/pgtable.h index 49eab8136ec3..24a9177fb897 100644 --- a/arch/hexagon/include/asm/pgtable.h +++ b/arch/hexagon/include/asm/pgtable.h @@ -26,6 +26,7 @@ */ #include <linux/swap.h> #include <asm/page.h> +#define __ARCH_USE_5LEVEL_HACK #include <asm-generic/pgtable-nopmd.h> /* A handy thing to have if one has the RAM. Declared in head.S */ diff --git a/arch/ia64/include/asm/pgtable.h b/arch/ia64/include/asm/pgtable.h index 384794e665fc..6cc22c8d8923 100644 --- a/arch/ia64/include/asm/pgtable.h +++ b/arch/ia64/include/asm/pgtable.h @@ -587,8 +587,10 @@ extern struct page *zero_page_memmap_ptr; #if CONFIG_PGTABLE_LEVELS == 3 +#define __ARCH_USE_5LEVEL_HACK #include <asm-generic/pgtable-nopud.h> #endif +#include <asm-generic/5level-fixup.h> #include <asm-generic/pgtable.h> #endif /* _ASM_IA64_PGTABLE_H */ diff --git a/arch/metag/include/asm/pgtable.h b/arch/metag/include/asm/pgtable.h index ffa3a3a2ecad..0c151e5af079 100644 --- a/arch/metag/include/asm/pgtable.h +++ b/arch/metag/include/asm/pgtable.h @@ -6,6 +6,7 @@ #define _METAG_PGTABLE_H #include <asm/pgtable-bits.h> +#define __ARCH_USE_5LEVEL_HACK #include <asm-generic/pgtable-nopmd.h> /* Invalid regions on Meta: 0x00000000-0x001FFFFF and 0xFFFF0000-0xFFFFFFFF */ diff --git a/arch/microblaze/include/asm/page.h b/arch/microblaze/include/asm/page.h index fd850879854d..d506bb0893f9 100644 --- a/arch/microblaze/include/asm/page.h +++ b/arch/microblaze/include/asm/page.h @@ -95,7 +95,8 @@ typedef struct { unsigned long pgd; } pgd_t; # else /* CONFIG_MMU */ typedef struct { unsigned long ste[64]; } pmd_t; typedef struct { pmd_t pue[1]; } pud_t; -typedef struct { pud_t pge[1]; } pgd_t; +typedef struct { pud_t p4e[1]; } p4d_t; +typedef struct { p4d_t pge[1]; } pgd_t; # endif /* CONFIG_MMU */ # define pte_val(x) ((x).pte) diff --git a/arch/mips/cavium-octeon/cpu.c b/arch/mips/cavium-octeon/cpu.c index a5b427909b5c..036d56cc4591 100644 --- a/arch/mips/cavium-octeon/cpu.c +++ b/arch/mips/cavium-octeon/cpu.c @@ -10,7 +10,9 @@ #include <linux/irqflags.h> #include <linux/notifier.h> #include <linux/prefetch.h> +#include <linux/ptrace.h> #include <linux/sched.h> +#include <linux/sched/task_stack.h> #include <asm/cop2.h> #include <asm/current.h> diff --git a/arch/mips/cavium-octeon/crypto/octeon-crypto.c b/arch/mips/cavium-octeon/crypto/octeon-crypto.c index 4d22365844af..cfb4a146cf17 100644 --- a/arch/mips/cavium-octeon/crypto/octeon-crypto.c +++ b/arch/mips/cavium-octeon/crypto/octeon-crypto.c @@ -9,6 +9,7 @@ #include <asm/cop2.h> #include <linux/export.h> #include <linux/interrupt.h> +#include <linux/sched/task_stack.h> #include "octeon-crypto.h" diff --git a/arch/mips/cavium-octeon/smp.c b/arch/mips/cavium-octeon/smp.c index 4b94b7fbafa3..3de786545ded 100644 --- a/arch/mips/cavium-octeon/smp.c +++ b/arch/mips/cavium-octeon/smp.c @@ -12,6 +12,7 @@ #include <linux/kernel_stat.h> #include <linux/sched.h> #include <linux/sched/hotplug.h> +#include <linux/sched/task_stack.h> #include <linux/init.h> #include <linux/export.h> diff --git a/arch/mips/include/asm/fpu.h b/arch/mips/include/asm/fpu.h index 321752bcbab6..f94455f964ec 100644 --- a/arch/mips/include/asm/fpu.h +++ b/arch/mips/include/asm/fpu.h @@ -12,6 +12,7 @@ #include <linux/sched.h> #include <linux/sched/task_stack.h> +#include <linux/ptrace.h> #include <linux/thread_info.h> #include <linux/bitops.h> diff --git a/arch/mips/include/asm/pgtable-32.h b/arch/mips/include/asm/pgtable-32.h index d21f3da7bdb6..6f94bed571c4 100644 --- a/arch/mips/include/asm/pgtable-32.h +++ b/arch/mips/include/asm/pgtable-32.h @@ -16,6 +16,7 @@ #include <asm/cachectl.h> #include <asm/fixmap.h> +#define __ARCH_USE_5LEVEL_HACK #include <asm-generic/pgtable-nopmd.h> extern int temp_tlb_entry; diff --git a/arch/mips/include/asm/pgtable-64.h b/arch/mips/include/asm/pgtable-64.h index 514cbc0a6a67..130a2a6c1531 100644 --- a/arch/mips/include/asm/pgtable-64.h +++ b/arch/mips/include/asm/pgtable-64.h @@ -17,6 +17,7 @@ #include <asm/cachectl.h> #include <asm/fixmap.h> +#define __ARCH_USE_5LEVEL_HACK #if defined(CONFIG_PAGE_SIZE_64KB) && !defined(CONFIG_MIPS_VA_BITS_48) #include <asm-generic/pgtable-nopmd.h> #else diff --git a/arch/mips/kernel/smp-bmips.c b/arch/mips/kernel/smp-bmips.c index 3daa2cae50b0..1b070a76fcdd 100644 --- a/arch/mips/kernel/smp-bmips.c +++ b/arch/mips/kernel/smp-bmips.c @@ -11,6 +11,7 @@ #include <linux/init.h> #include <linux/sched.h> #include <linux/sched/hotplug.h> +#include <linux/sched/task_stack.h> #include <linux/mm.h> #include <linux/delay.h> #include <linux/smp.h> diff --git a/arch/mips/kernel/smp-mt.c b/arch/mips/kernel/smp-mt.c index e077ea3e11fb..e398cbc3d776 100644 --- a/arch/mips/kernel/smp-mt.c +++ b/arch/mips/kernel/smp-mt.c @@ -23,6 +23,7 @@ #include <linux/interrupt.h> #include <linux/irqchip/mips-gic.h> #include <linux/compiler.h> +#include <linux/sched/task_stack.h> #include <linux/smp.h> #include <linux/atomic.h> diff --git a/arch/mips/loongson64/loongson-3/cop2-ex.c b/arch/mips/loongson64/loongson-3/cop2-ex.c index ea13764d0a03..621d6af5f6eb 100644 --- a/arch/mips/loongson64/loongson-3/cop2-ex.c +++ b/arch/mips/loongson64/loongson-3/cop2-ex.c @@ -13,6 +13,7 @@ #include <linux/init.h> #include <linux/sched.h> #include <linux/notifier.h> +#include <linux/ptrace.h> #include <asm/fpu.h> #include <asm/cop2.h> diff --git a/arch/mips/netlogic/common/smp.c b/arch/mips/netlogic/common/smp.c index 10d86d54880a..bddf1ef553a4 100644 --- a/arch/mips/netlogic/common/smp.c +++ b/arch/mips/netlogic/common/smp.c @@ -35,6 +35,7 @@ #include <linux/kernel.h> #include <linux/delay.h> #include <linux/init.h> +#include <linux/sched/task_stack.h> #include <linux/smp.h> #include <linux/irq.h> diff --git a/arch/mips/netlogic/xlp/cop2-ex.c b/arch/mips/netlogic/xlp/cop2-ex.c index 52bc5de42005..21e439b3db70 100644 --- a/arch/mips/netlogic/xlp/cop2-ex.c +++ b/arch/mips/netlogic/xlp/cop2-ex.c @@ -9,11 +9,14 @@ * Copyright (C) 2009 Wind River Systems, * written by Ralf Baechle <[email protected]> */ +#include <linux/capability.h> #include <linux/init.h> #include <linux/irqflags.h> #include <linux/notifier.h> #include <linux/prefetch.h> +#include <linux/ptrace.h> #include <linux/sched.h> +#include <linux/sched/task_stack.h> #include <asm/cop2.h> #include <asm/current.h> diff --git a/arch/mips/sgi-ip22/ip28-berr.c b/arch/mips/sgi-ip22/ip28-berr.c index 1f2a5bc4779e..75460e1e106b 100644 --- a/arch/mips/sgi-ip22/ip28-berr.c +++ b/arch/mips/sgi-ip22/ip28-berr.c @@ -9,6 +9,7 @@ #include <linux/kernel.h> #include <linux/sched.h> #include <linux/sched/debug.h> +#include <linux/sched/signal.h> #include <linux/seq_file.h> #include <asm/addrspace.h> diff --git a/arch/mips/sgi-ip27/ip27-berr.c b/arch/mips/sgi-ip27/ip27-berr.c index d12879eb2b1f..83efe03d5c60 100644 --- a/arch/mips/sgi-ip27/ip27-berr.c +++ b/arch/mips/sgi-ip27/ip27-berr.c @@ -12,7 +12,9 @@ #include <linux/signal.h> /* for SIGBUS */ #include <linux/sched.h> /* schow_regs(), force_sig() */ #include <linux/sched/debug.h> +#include <linux/sched/signal.h> +#include <asm/ptrace.h> #include <asm/sn/addrs.h> #include <asm/sn/arch.h> #include <asm/sn/sn0/hub.h> diff --git a/arch/mips/sgi-ip27/ip27-smp.c b/arch/mips/sgi-ip27/ip27-smp.c index f5ed45e8f442..4cd47d23d81a 100644 --- a/arch/mips/sgi-ip27/ip27-smp.c +++ b/arch/mips/sgi-ip27/ip27-smp.c @@ -8,10 +8,13 @@ */ #include <linux/init.h> #include <linux/sched.h> +#include <linux/sched/task_stack.h> #include <linux/topology.h> #include <linux/nodemask.h> + #include <asm/page.h> #include <asm/processor.h> +#include <asm/ptrace.h> #include <asm/sn/arch.h> #include <asm/sn/gda.h> #include <asm/sn/intr.h> diff --git a/arch/mips/sgi-ip32/ip32-berr.c b/arch/mips/sgi-ip32/ip32-berr.c index 57d8c7486fe6..c1f12a9cf305 100644 --- a/arch/mips/sgi-ip32/ip32-berr.c +++ b/arch/mips/sgi-ip32/ip32-berr.c @@ -11,6 +11,7 @@ #include <linux/kernel.h> #include <linux/sched.h> #include <linux/sched/debug.h> +#include <linux/sched/signal.h> #include <asm/traps.h> #include <linux/uaccess.h> #include <asm/addrspace.h> diff --git a/arch/mips/sgi-ip32/ip32-reset.c b/arch/mips/sgi-ip32/ip32-reset.c index 8bd415c8729f..b3b442def423 100644 --- a/arch/mips/sgi-ip32/ip32-reset.c +++ b/arch/mips/sgi-ip32/ip32-reset.c @@ -13,6 +13,7 @@ #include <linux/kernel.h> #include <linux/module.h> #include <linux/sched.h> +#include <linux/sched/signal.h> #include <linux/notifier.h> #include <linux/delay.h> #include <linux/rtc/ds1685.h> diff --git a/arch/mn10300/include/asm/page.h b/arch/mn10300/include/asm/page.h index 3810a6f740fd..dfe730a5ede0 100644 --- a/arch/mn10300/include/asm/page.h +++ b/arch/mn10300/include/asm/page.h @@ -57,6 +57,7 @@ typedef struct page *pgtable_t; #define __pgd(x) ((pgd_t) { (x) }) #define __pgprot(x) ((pgprot_t) { (x) }) +#define __ARCH_USE_5LEVEL_HACK #include <asm-generic/pgtable-nopmd.h> #endif /* !__ASSEMBLY__ */ diff --git a/arch/nios2/include/asm/pgtable.h b/arch/nios2/include/asm/pgtable.h index 298393c3cb42..db4f7d179220 100644 --- a/arch/nios2/include/asm/pgtable.h +++ b/arch/nios2/include/asm/pgtable.h @@ -22,6 +22,7 @@ #include <asm/tlbflush.h> #include <asm/pgtable-bits.h> +#define __ARCH_USE_5LEVEL_HACK #include <asm-generic/pgtable-nopmd.h> #define FIRST_USER_ADDRESS 0UL diff --git a/arch/openrisc/include/asm/pgtable.h b/arch/openrisc/include/asm/pgtable.h index 3567aa7be555..ff97374ca069 100644 --- a/arch/openrisc/include/asm/pgtable.h +++ b/arch/openrisc/include/asm/pgtable.h @@ -25,6 +25,7 @@ #ifndef __ASM_OPENRISC_PGTABLE_H #define __ASM_OPENRISC_PGTABLE_H +#define __ARCH_USE_5LEVEL_HACK #include <asm-generic/pgtable-nopmd.h> #ifndef __ASSEMBLY__ diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index 494091762bd7..97a8bc8a095c 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -80,93 +80,99 @@ config ARCH_HAS_DMA_SET_COHERENT_MASK config PPC bool default y - select BUILDTIME_EXTABLE_SORT + # + # Please keep this list sorted alphabetically. + # + select ARCH_HAS_DEVMEM_IS_ALLOWED + select ARCH_HAS_DMA_SET_COHERENT_MASK + select ARCH_HAS_ELF_RANDOMIZE + select ARCH_HAS_GCOV_PROFILE_ALL + select ARCH_HAS_SCALED_CPUTIME if VIRT_CPU_ACCOUNTING_NATIVE + select ARCH_HAS_SG_CHAIN + select ARCH_HAS_TICK_BROADCAST if GENERIC_CLOCKEVENTS_BROADCAST + select ARCH_HAS_UBSAN_SANITIZE_ALL + select ARCH_HAVE_NMI_SAFE_CMPXCHG select ARCH_MIGHT_HAVE_PC_PARPORT select ARCH_MIGHT_HAVE_PC_SERIO + select ARCH_SUPPORTS_ATOMIC_RMW + select ARCH_SUPPORTS_DEFERRED_STRUCT_PAGE_INIT + select ARCH_USE_BUILTIN_BSWAP + select ARCH_USE_CMPXCHG_LOCKREF if PPC64 + select ARCH_WANT_IPC_PARSE_VERSION select BINFMT_ELF - select ARCH_HAS_ELF_RANDOMIZE - select OF - select OF_EARLY_FLATTREE - select OF_RESERVED_MEM - select HAVE_FTRACE_MCOUNT_RECORD + select BUILDTIME_EXTABLE_SORT + select CLONE_BACKWARDS + select DCACHE_WORD_ACCESS if PPC64 && CPU_LITTLE_ENDIAN + select EDAC_ATOMIC_SCRUB + select EDAC_SUPPORT + select GENERIC_ATOMIC64 if PPC32 + select GENERIC_CLOCKEVENTS + select GENERIC_CLOCKEVENTS_BROADCAST if SMP + select GENERIC_CMOS_UPDATE + select GENERIC_CPU_AUTOPROBE + select GENERIC_IRQ_SHOW + select GENERIC_IRQ_SHOW_LEVEL + select GENERIC_SMP_IDLE_THREAD + select GENERIC_STRNCPY_FROM_USER + select GENERIC_STRNLEN_USER + select GENERIC_TIME_VSYSCALL_OLD + select HAVE_ARCH_AUDITSYSCALL + select HAVE_ARCH_HARDENED_USERCOPY + select HAVE_ARCH_JUMP_LABEL + select HAVE_ARCH_KGDB + select HAVE_ARCH_SECCOMP_FILTER + select HAVE_ARCH_TRACEHOOK + select HAVE_CBPF_JIT if !PPC64 + select HAVE_CONTEXT_TRACKING if PPC64 + select HAVE_DEBUG_KMEMLEAK + select HAVE_DEBUG_STACKOVERFLOW + select HAVE_DMA_API_DEBUG select HAVE_DYNAMIC_FTRACE - select HAVE_DYNAMIC_FTRACE_WITH_REGS if MPROFILE_KERNEL - select HAVE_FUNCTION_TRACER + select HAVE_DYNAMIC_FTRACE_WITH_REGS if MPROFILE_KERNEL + select HAVE_EBPF_JIT if PPC64 + select HAVE_EFFICIENT_UNALIGNED_ACCESS if !(CPU_LITTLE_ENDIAN && POWER7_CPU) + select HAVE_FTRACE_MCOUNT_RECORD select HAVE_FUNCTION_GRAPH_TRACER + select HAVE_FUNCTION_TRACER select HAVE_GCC_PLUGINS - select SYSCTL_EXCEPTION_TRACE - select VIRT_TO_BUS if !PPC64 + select HAVE_GENERIC_RCU_GUP + select HAVE_HW_BREAKPOINT if PERF_EVENTS && (PPC_BOOK3S || PPC_8xx) select HAVE_IDE select HAVE_IOREMAP_PROT - select HAVE_EFFICIENT_UNALIGNED_ACCESS if !(CPU_LITTLE_ENDIAN && POWER7_CPU) + select HAVE_IRQ_EXIT_ON_IRQ_STACK + select HAVE_KERNEL_GZIP select HAVE_KPROBES - select HAVE_OPTPROBES if PPC64 - select HAVE_ARCH_KGDB select HAVE_KRETPROBES - select HAVE_ARCH_TRACEHOOK + select HAVE_LIVEPATCH if HAVE_DYNAMIC_FTRACE_WITH_REGS select HAVE_MEMBLOCK select HAVE_MEMBLOCK_NODE_MAP - select HAVE_DMA_API_DEBUG + select HAVE_MOD_ARCH_SPECIFIC + select HAVE_NMI if PERF_EVENTS select HAVE_OPROFILE - select HAVE_DEBUG_KMEMLEAK - select ARCH_HAS_SG_CHAIN - select GENERIC_ATOMIC64 if PPC32 + select HAVE_OPTPROBES if PPC64 select HAVE_PERF_EVENTS + select HAVE_PERF_EVENTS_NMI if PPC64 select HAVE_PERF_REGS select HAVE_PERF_USER_STACK_DUMP + select HAVE_RCU_TABLE_FREE if SMP select HAVE_REGS_AND_STACK_ACCESS_API - select HAVE_HW_BREAKPOINT if PERF_EVENTS && (PPC_BOOK3S || PPC_8xx) - select ARCH_WANT_IPC_PARSE_VERSION - select SPARSE_IRQ + select HAVE_SYSCALL_TRACEPOINTS + select HAVE_VIRT_CPU_ACCOUNTING select IRQ_DOMAIN - select GENERIC_IRQ_SHOW - select GENERIC_IRQ_SHOW_LEVEL select IRQ_FORCED_THREADING - select HAVE_RCU_TABLE_FREE if SMP - select HAVE_SYSCALL_TRACEPOINTS - select HAVE_CBPF_JIT if !PPC64 - select HAVE_EBPF_JIT if PPC64 - select HAVE_ARCH_JUMP_LABEL - select ARCH_HAVE_NMI_SAFE_CMPXCHG - select ARCH_HAS_GCOV_PROFILE_ALL - select GENERIC_SMP_IDLE_THREAD - select GENERIC_CMOS_UPDATE - select GENERIC_TIME_VSYSCALL_OLD - select GENERIC_CLOCKEVENTS - select GENERIC_CLOCKEVENTS_BROADCAST if SMP - select ARCH_HAS_TICK_BROADCAST if GENERIC_CLOCKEVENTS_BROADCAST - select GENERIC_STRNCPY_FROM_USER - select GENERIC_STRNLEN_USER - select HAVE_MOD_ARCH_SPECIFIC select MODULES_USE_ELF_RELA - select CLONE_BACKWARDS - select ARCH_USE_BUILTIN_BSWAP - select OLD_SIGSUSPEND - select OLD_SIGACTION if PPC32 - select HAVE_DEBUG_STACKOVERFLOW - select HAVE_IRQ_EXIT_ON_IRQ_STACK - select ARCH_USE_CMPXCHG_LOCKREF if PPC64 - select HAVE_ARCH_AUDITSYSCALL - select ARCH_SUPPORTS_ATOMIC_RMW - select DCACHE_WORD_ACCESS if PPC64 && CPU_LITTLE_ENDIAN select NO_BOOTMEM - select HAVE_GENERIC_RCU_GUP - select HAVE_PERF_EVENTS_NMI if PPC64 - select HAVE_NMI if PERF_EVENTS - select EDAC_SUPPORT - select EDAC_ATOMIC_SCRUB - select ARCH_HAS_DMA_SET_COHERENT_MASK - select ARCH_HAS_DEVMEM_IS_ALLOWED - select HAVE_ARCH_SECCOMP_FILTER - select ARCH_HAS_UBSAN_SANITIZE_ALL - select ARCH_SUPPORTS_DEFERRED_STRUCT_PAGE_INIT - select HAVE_LIVEPATCH if HAVE_DYNAMIC_FTRACE_WITH_REGS - select GENERIC_CPU_AUTOPROBE - select HAVE_VIRT_CPU_ACCOUNTING - select ARCH_HAS_SCALED_CPUTIME if VIRT_CPU_ACCOUNTING_NATIVE - select HAVE_ARCH_HARDENED_USERCOPY - select HAVE_KERNEL_GZIP - select HAVE_CONTEXT_TRACKING if PPC64 + select OF + select OF_EARLY_FLATTREE + select OF_RESERVED_MEM + select OLD_SIGACTION if PPC32 + select OLD_SIGSUSPEND + select SPARSE_IRQ + select SYSCTL_EXCEPTION_TRACE + select VIRT_TO_BUS if !PPC64 + # + # Please keep this list sorted alphabetically. + # config GENERIC_CSUM def_bool n diff --git a/arch/powerpc/Makefile b/arch/powerpc/Makefile index 31286fa7873c..19b0d1a81959 100644 --- a/arch/powerpc/Makefile +++ b/arch/powerpc/Makefile @@ -72,8 +72,15 @@ GNUTARGET := powerpc MULTIPLEWORD := -mmultiple endif -cflags-$(CONFIG_CPU_BIG_ENDIAN) += $(call cc-option,-mbig-endian) +ifdef CONFIG_PPC64 +cflags-$(CONFIG_CPU_BIG_ENDIAN) += $(call cc-option,-mabi=elfv1) +cflags-$(CONFIG_CPU_BIG_ENDIAN) += $(call cc-option,-mcall-aixdesc) +aflags-$(CONFIG_CPU_BIG_ENDIAN) += $(call cc-option,-mabi=elfv1) +aflags-$(CONFIG_CPU_LITTLE_ENDIAN) += -mabi=elfv2 +endif + cflags-$(CONFIG_CPU_LITTLE_ENDIAN) += -mlittle-endian +cflags-$(CONFIG_CPU_BIG_ENDIAN) += $(call cc-option,-mbig-endian) ifneq ($(cc-name),clang) cflags-$(CONFIG_CPU_LITTLE_ENDIAN) += -mno-strict-align endif @@ -113,7 +120,9 @@ ifeq ($(CONFIG_CPU_LITTLE_ENDIAN),y) CFLAGS-$(CONFIG_PPC64) += $(call cc-option,-mabi=elfv2,$(call cc-option,-mcall-aixdesc)) AFLAGS-$(CONFIG_PPC64) += $(call cc-option,-mabi=elfv2) else +CFLAGS-$(CONFIG_PPC64) += $(call cc-option,-mabi=elfv1) CFLAGS-$(CONFIG_PPC64) += $(call cc-option,-mcall-aixdesc) +AFLAGS-$(CONFIG_PPC64) += $(call cc-option,-mabi=elfv1) endif CFLAGS-$(CONFIG_PPC64) += $(call cc-option,-mcmodel=medium,$(call cc-option,-mminimal-toc)) CFLAGS-$(CONFIG_PPC64) += $(call cc-option,-mno-pointers-to-nested-functions) diff --git a/arch/powerpc/boot/zImage.lds.S b/arch/powerpc/boot/zImage.lds.S index 861e72109df2..f080abfc2f83 100644 --- a/arch/powerpc/boot/zImage.lds.S +++ b/arch/powerpc/boot/zImage.lds.S @@ -68,6 +68,7 @@ SECTIONS } #ifdef CONFIG_PPC64_BOOT_WRAPPER + . = ALIGN(256); .got : { __toc_start = .; diff --git a/arch/powerpc/crypto/crc32c-vpmsum_glue.c b/arch/powerpc/crypto/crc32c-vpmsum_glue.c index 9fa046d56eba..411994551afc 100644 --- a/arch/powerpc/crypto/crc32c-vpmsum_glue.c +++ b/arch/powerpc/crypto/crc32c-vpmsum_glue.c @@ -52,7 +52,7 @@ static int crc32c_vpmsum_cra_init(struct crypto_tfm *tfm) { u32 *key = crypto_tfm_ctx(tfm); - *key = 0; + *key = ~0; return 0; } diff --git a/arch/powerpc/include/asm/bitops.h b/arch/powerpc/include/asm/bitops.h index 73eb794d6163..bc5fdfd22788 100644 --- a/arch/powerpc/include/asm/bitops.h +++ b/arch/powerpc/include/asm/bitops.h @@ -51,6 +51,10 @@ #define PPC_BIT(bit) (1UL << PPC_BITLSHIFT(bit)) #define PPC_BITMASK(bs, be) ((PPC_BIT(bs) - PPC_BIT(be)) | PPC_BIT(bs)) +/* Put a PPC bit into a "normal" bit position */ +#define PPC_BITEXTRACT(bits, ppc_bit, dst_bit) \ + ((((bits) >> PPC_BITLSHIFT(ppc_bit)) & 1) << (dst_bit)) + #include <asm/barrier.h> /* Macro for generating the ***_bits() functions */ diff --git a/arch/powerpc/include/asm/book3s/32/pgtable.h b/arch/powerpc/include/asm/book3s/32/pgtable.h index 012223638815..26ed228d4dc6 100644 --- a/arch/powerpc/include/asm/book3s/32/pgtable.h +++ b/arch/powerpc/include/asm/book3s/32/pgtable.h @@ -1,6 +1,7 @@ #ifndef _ASM_POWERPC_BOOK3S_32_PGTABLE_H #define _ASM_POWERPC_BOOK3S_32_PGTABLE_H +#define __ARCH_USE_5LEVEL_HACK #include <asm-generic/pgtable-nopmd.h> #include <asm/book3s/32/hash.h> diff --git a/arch/powerpc/include/asm/book3s/64/pgtable.h b/arch/powerpc/include/asm/book3s/64/pgtable.h index 1eeeb72c7015..8f4d41936e5a 100644 --- a/arch/powerpc/include/asm/book3s/64/pgtable.h +++ b/arch/powerpc/include/asm/book3s/64/pgtable.h @@ -1,9 +1,12 @@ #ifndef _ASM_POWERPC_BOOK3S_64_PGTABLE_H_ #define _ASM_POWERPC_BOOK3S_64_PGTABLE_H_ +#include <asm-generic/5level-fixup.h> + #ifndef __ASSEMBLY__ #include <linux/mmdebug.h> #endif + /* * Common bits between hash and Radix page table */ @@ -347,23 +350,58 @@ static inline int __ptep_test_and_clear_young(struct mm_struct *mm, __r; \ }) +static inline int __pte_write(pte_t pte) +{ + return !!(pte_raw(pte) & cpu_to_be64(_PAGE_WRITE)); +} + +#ifdef CONFIG_NUMA_BALANCING +#define pte_savedwrite pte_savedwrite +static inline bool pte_savedwrite(pte_t pte) +{ + /* + * Saved write ptes are prot none ptes that doesn't have + * privileged bit sit. We mark prot none as one which has + * present and pviliged bit set and RWX cleared. To mark + * protnone which used to have _PAGE_WRITE set we clear + * the privileged bit. + */ + return !(pte_raw(pte) & cpu_to_be64(_PAGE_RWX | _PAGE_PRIVILEGED)); +} +#else +#define pte_savedwrite pte_savedwrite +static inline bool pte_savedwrite(pte_t pte) +{ + return false; +} +#endif + +static inline int pte_write(pte_t pte) +{ + return __pte_write(pte) || pte_savedwrite(pte); +} + #define __HAVE_ARCH_PTEP_SET_WRPROTECT static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long addr, pte_t *ptep) { - if ((pte_raw(*ptep) & cpu_to_be64(_PAGE_WRITE)) == 0) - return; - - pte_update(mm, addr, ptep, _PAGE_WRITE, 0, 0); + if (__pte_write(*ptep)) + pte_update(mm, addr, ptep, _PAGE_WRITE, 0, 0); + else if (unlikely(pte_savedwrite(*ptep))) + pte_update(mm, addr, ptep, 0, _PAGE_PRIVILEGED, 0); } static inline void huge_ptep_set_wrprotect(struct mm_struct *mm, unsigned long addr, pte_t *ptep) { - if ((pte_raw(*ptep) & cpu_to_be64(_PAGE_WRITE)) == 0) - return; - - pte_update(mm, addr, ptep, _PAGE_WRITE, 0, 1); + /* + * We should not find protnone for hugetlb, but this complete the + * interface. + */ + if (__pte_write(*ptep)) + pte_update(mm, addr, ptep, _PAGE_WRITE, 0, 1); + else if (unlikely(pte_savedwrite(*ptep))) + pte_update(mm, addr, ptep, 0, _PAGE_PRIVILEGED, 1); } #define __HAVE_ARCH_PTEP_GET_AND_CLEAR @@ -397,11 +435,6 @@ static inline void pte_clear(struct mm_struct *mm, unsigned long addr, pte_update(mm, addr, ptep, ~0UL, 0, 0); } -static inline int pte_write(pte_t pte) -{ - return !!(pte_raw(pte) & cpu_to_be64(_PAGE_WRITE)); -} - static inline int pte_dirty(pte_t pte) { return !!(pte_raw(pte) & cpu_to_be64(_PAGE_DIRTY)); @@ -465,19 +498,12 @@ static inline pte_t pte_clear_savedwrite(pte_t pte) VM_BUG_ON(!pte_protnone(pte)); return __pte(pte_val(pte) | _PAGE_PRIVILEGED); } - -#define pte_savedwrite pte_savedwrite -static inline bool pte_savedwrite(pte_t pte) +#else +#define pte_clear_savedwrite pte_clear_savedwrite +static inline pte_t pte_clear_savedwrite(pte_t pte) { - /* - * Saved write ptes are prot none ptes that doesn't have - * privileged bit sit. We mark prot none as one which has - * present and pviliged bit set and RWX cleared. To mark - * protnone which used to have _PAGE_WRITE set we clear - * the privileged bit. - */ - VM_BUG_ON(!pte_protnone(pte)); - return !(pte_raw(pte) & cpu_to_be64(_PAGE_RWX | _PAGE_PRIVILEGED)); + VM_WARN_ON(1); + return __pte(pte_val(pte) & ~_PAGE_WRITE); } #endif /* CONFIG_NUMA_BALANCING */ @@ -506,6 +532,8 @@ static inline unsigned long pte_pfn(pte_t pte) /* Generic modifiers for PTE bits */ static inline pte_t pte_wrprotect(pte_t pte) { + if (unlikely(pte_savedwrite(pte))) + return pte_clear_savedwrite(pte); return __pte(pte_val(pte) & ~_PAGE_WRITE); } @@ -926,6 +954,7 @@ static inline int pmd_protnone(pmd_t pmd) #define __HAVE_ARCH_PMD_WRITE #define pmd_write(pmd) pte_write(pmd_pte(pmd)) +#define __pmd_write(pmd) __pte_write(pmd_pte(pmd)) #define pmd_savedwrite(pmd) pte_savedwrite(pmd_pte(pmd)) #ifdef CONFIG_TRANSPARENT_HUGEPAGE @@ -982,11 +1011,10 @@ static inline int __pmdp_test_and_clear_young(struct mm_struct *mm, static inline void pmdp_set_wrprotect(struct mm_struct *mm, unsigned long addr, pmd_t *pmdp) { - - if ((pmd_raw(*pmdp) & cpu_to_be64(_PAGE_WRITE)) == 0) - return; - - pmd_hugepage_update(mm, addr, pmdp, _PAGE_WRITE, 0); + if (__pmd_write((*pmdp))) + pmd_hugepage_update(mm, addr, pmdp, _PAGE_WRITE, 0); + else if (unlikely(pmd_savedwrite(*pmdp))) + pmd_hugepage_update(mm, addr, pmdp, 0, _PAGE_PRIVILEGED); } static inline int pmd_trans_huge(pmd_t pmd) diff --git a/arch/powerpc/include/asm/checksum.h b/arch/powerpc/include/asm/checksum.h index 4e63787dc3be..842124b199b5 100644 --- a/arch/powerpc/include/asm/checksum.h +++ b/arch/powerpc/include/asm/checksum.h @@ -112,7 +112,7 @@ static inline __wsum csum_add(__wsum csum, __wsum addend) #ifdef __powerpc64__ res += (__force u64)addend; - return (__force __wsum)((u32)res + (res >> 32)); + return (__force __wsum) from64to32(res); #else asm("addc %0,%0,%1;" "addze %0,%0;" diff --git a/arch/powerpc/include/asm/cpuidle.h b/arch/powerpc/include/asm/cpuidle.h index fd321eb423cb..155731557c9b 100644 --- a/arch/powerpc/include/asm/cpuidle.h +++ b/arch/powerpc/include/asm/cpuidle.h @@ -70,8 +70,8 @@ static inline void report_invalid_psscr_val(u64 psscr_val, int err) std r0,0(r1); \ ptesync; \ ld r0,0(r1); \ -1: cmpd cr0,r0,r0; \ - bne 1b; \ +236: cmpd cr0,r0,r0; \ + bne 236b; \ IDLE_INST; \ #define IDLE_STATE_ENTER_SEQ_NORET(IDLE_INST) \ diff --git a/arch/powerpc/include/asm/elf.h b/arch/powerpc/include/asm/elf.h index 93b9b84568e8..09bde6e34f5d 100644 --- a/arch/powerpc/include/asm/elf.h +++ b/arch/powerpc/include/asm/elf.h @@ -144,8 +144,8 @@ extern int arch_setup_additional_pages(struct linux_binprm *bprm, #define ARCH_DLINFO_CACHE_GEOMETRY \ NEW_AUX_ENT(AT_L1I_CACHESIZE, ppc64_caches.l1i.size); \ NEW_AUX_ENT(AT_L1I_CACHEGEOMETRY, get_cache_geometry(l1i)); \ - NEW_AUX_ENT(AT_L1D_CACHESIZE, ppc64_caches.l1i.size); \ - NEW_AUX_ENT(AT_L1D_CACHEGEOMETRY, get_cache_geometry(l1i)); \ + NEW_AUX_ENT(AT_L1D_CACHESIZE, ppc64_caches.l1d.size); \ + NEW_AUX_ENT(AT_L1D_CACHEGEOMETRY, get_cache_geometry(l1d)); \ NEW_AUX_ENT(AT_L2_CACHESIZE, ppc64_caches.l2.size); \ NEW_AUX_ENT(AT_L2_CACHEGEOMETRY, get_cache_geometry(l2)); \ NEW_AUX_ENT(AT_L3_CACHESIZE, ppc64_caches.l3.size); \ diff --git a/arch/powerpc/include/asm/mce.h b/arch/powerpc/include/asm/mce.h index f97d8cb6bdf6..ed62efe01e49 100644 --- a/arch/powerpc/include/asm/mce.h +++ b/arch/powerpc/include/asm/mce.h @@ -66,6 +66,55 @@ #define P8_DSISR_MC_SLB_ERRORS (P7_DSISR_MC_SLB_ERRORS | \ P8_DSISR_MC_ERAT_MULTIHIT_SEC) + +/* + * Machine Check bits on power9 + */ +#define P9_SRR1_MC_LOADSTORE(srr1) (((srr1) >> PPC_BITLSHIFT(42)) & 1) + +#define P9_SRR1_MC_IFETCH(srr1) ( \ + PPC_BITEXTRACT(srr1, 45, 0) | \ + PPC_BITEXTRACT(srr1, 44, 1) | \ + PPC_BITEXTRACT(srr1, 43, 2) | \ + PPC_BITEXTRACT(srr1, 36, 3) ) + +/* 0 is reserved */ +#define P9_SRR1_MC_IFETCH_UE 1 +#define P9_SRR1_MC_IFETCH_SLB_PARITY 2 +#define P9_SRR1_MC_IFETCH_SLB_MULTIHIT 3 +#define P9_SRR1_MC_IFETCH_ERAT_MULTIHIT 4 +#define P9_SRR1_MC_IFETCH_TLB_MULTIHIT 5 +#define P9_SRR1_MC_IFETCH_UE_TLB_RELOAD 6 +/* 7 is reserved */ +#define P9_SRR1_MC_IFETCH_LINK_TIMEOUT 8 +#define P9_SRR1_MC_IFETCH_LINK_TABLEWALK_TIMEOUT 9 +/* 10 ? */ +#define P9_SRR1_MC_IFETCH_RA 11 +#define P9_SRR1_MC_IFETCH_RA_TABLEWALK 12 +#define P9_SRR1_MC_IFETCH_RA_ASYNC_STORE 13 +#define P9_SRR1_MC_IFETCH_LINK_ASYNC_STORE_TIMEOUT 14 +#define P9_SRR1_MC_IFETCH_RA_TABLEWALK_FOREIGN 15 + +/* DSISR bits for machine check (On Power9) */ +#define P9_DSISR_MC_UE (PPC_BIT(48)) +#define P9_DSISR_MC_UE_TABLEWALK (PPC_BIT(49)) +#define P9_DSISR_MC_LINK_LOAD_TIMEOUT (PPC_BIT(50)) +#define P9_DSISR_MC_LINK_TABLEWALK_TIMEOUT (PPC_BIT(51)) +#define P9_DSISR_MC_ERAT_MULTIHIT (PPC_BIT(52)) +#define P9_DSISR_MC_TLB_MULTIHIT_MFTLB (PPC_BIT(53)) +#define P9_DSISR_MC_USER_TLBIE (PPC_BIT(54)) +#define P9_DSISR_MC_SLB_PARITY_MFSLB (PPC_BIT(55)) +#define P9_DSISR_MC_SLB_MULTIHIT_MFSLB (PPC_BIT(56)) +#define P9_DSISR_MC_RA_LOAD (PPC_BIT(57)) +#define P9_DSISR_MC_RA_TABLEWALK (PPC_BIT(58)) +#define P9_DSISR_MC_RA_TABLEWALK_FOREIGN (PPC_BIT(59)) +#define P9_DSISR_MC_RA_FOREIGN (PPC_BIT(60)) + +/* SLB error bits */ +#define P9_DSISR_MC_SLB_ERRORS (P9_DSISR_MC_ERAT_MULTIHIT | \ + P9_DSISR_MC_SLB_PARITY_MFSLB | \ + P9_DSISR_MC_SLB_MULTIHIT_MFSLB) + enum MCE_Version { MCE_V1 = 1, }; @@ -93,6 +142,9 @@ enum MCE_ErrorType { MCE_ERROR_TYPE_SLB = 2, MCE_ERROR_TYPE_ERAT = 3, MCE_ERROR_TYPE_TLB = 4, + MCE_ERROR_TYPE_USER = 5, + MCE_ERROR_TYPE_RA = 6, + MCE_ERROR_TYPE_LINK = 7, }; enum MCE_UeErrorType { @@ -121,6 +173,32 @@ enum MCE_TlbErrorType { MCE_TLB_ERROR_MULTIHIT = 2, }; +enum MCE_UserErrorType { + MCE_USER_ERROR_INDETERMINATE = 0, + MCE_USER_ERROR_TLBIE = 1, +}; + +enum MCE_RaErrorType { + MCE_RA_ERROR_INDETERMINATE = 0, + MCE_RA_ERROR_IFETCH = 1, + MCE_RA_ERROR_PAGE_TABLE_WALK_IFETCH = 2, + MCE_RA_ERROR_PAGE_TABLE_WALK_IFETCH_FOREIGN = 3, + MCE_RA_ERROR_LOAD = 4, + MCE_RA_ERROR_STORE = 5, + MCE_RA_ERROR_PAGE_TABLE_WALK_LOAD_STORE = 6, + MCE_RA_ERROR_PAGE_TABLE_WALK_LOAD_STORE_FOREIGN = 7, + MCE_RA_ERROR_LOAD_STORE_FOREIGN = 8, +}; + +enum MCE_LinkErrorType { + MCE_LINK_ERROR_INDETERMINATE = 0, + MCE_LINK_ERROR_IFETCH_TIMEOUT = 1, + MCE_LINK_ERROR_PAGE_TABLE_WALK_IFETCH_TIMEOUT = 2, + MCE_LINK_ERROR_LOAD_TIMEOUT = 3, + MCE_LINK_ERROR_STORE_TIMEOUT = 4, + MCE_LINK_ERROR_PAGE_TABLE_WALK_LOAD_STORE_TIMEOUT = 5, +}; + struct machine_check_event { enum MCE_Version version:8; /* 0x00 */ uint8_t in_use; /* 0x01 */ @@ -166,6 +244,30 @@ struct machine_check_event { uint64_t effective_address; uint8_t reserved_2[16]; } tlb_error; + + struct { + enum MCE_UserErrorType user_error_type:8; + uint8_t effective_address_provided; + uint8_t reserved_1[6]; + uint64_t effective_address; + uint8_t reserved_2[16]; + } user_error; + + struct { + enum MCE_RaErrorType ra_error_type:8; + uint8_t effective_address_provided; + uint8_t reserved_1[6]; + uint64_t effective_address; + uint8_t reserved_2[16]; + } ra_error; + + struct { + enum MCE_LinkErrorType link_error_type:8; + uint8_t effective_address_provided; + uint8_t reserved_1[6]; + uint64_t effective_address; + uint8_t reserved_2[16]; + } link_error; } u; }; @@ -176,8 +278,12 @@ struct mce_error_info { enum MCE_SlbErrorType slb_error_type:8; enum MCE_EratErrorType erat_error_type:8; enum MCE_TlbErrorType tlb_error_type:8; + enum MCE_UserErrorType user_error_type:8; + enum MCE_RaErrorType ra_error_type:8; + enum MCE_LinkErrorType link_error_type:8; } u; - uint8_t reserved[2]; + enum MCE_Severity severity:8; + enum MCE_Initiator initiator:8; }; #define MAX_MC_EVT 100 diff --git a/arch/powerpc/include/asm/nohash/32/pgtable.h b/arch/powerpc/include/asm/nohash/32/pgtable.h index ba9921bf202e..5134ade2e850 100644 --- a/arch/powerpc/include/asm/nohash/32/pgtable.h +++ b/arch/powerpc/include/asm/nohash/32/pgtable.h @@ -1,6 +1,7 @@ #ifndef _ASM_POWERPC_NOHASH_32_PGTABLE_H #define _ASM_POWERPC_NOHASH_32_PGTABLE_H +#define __ARCH_USE_5LEVEL_HACK #include <asm-generic/pgtable-nopmd.h> #ifndef __ASSEMBLY__ diff --git a/arch/powerpc/include/asm/nohash/64/pgtable-4k.h b/arch/powerpc/include/asm/nohash/64/pgtable-4k.h index d0db98793dd8..9f4de0a1035e 100644 --- a/arch/powerpc/include/asm/nohash/64/pgtable-4k.h +++ b/arch/powerpc/include/asm/nohash/64/pgtable-4k.h @@ -1,5 +1,8 @@ #ifndef _ASM_POWERPC_NOHASH_64_PGTABLE_4K_H #define _ASM_POWERPC_NOHASH_64_PGTABLE_4K_H + +#include <asm-generic/5level-fixup.h> + /* * Entries per page directory level. The PTE level must use a 64b record * for each page table entry. The PMD and PGD level use a 32b record for diff --git a/arch/powerpc/include/asm/nohash/64/pgtable-64k.h b/arch/powerpc/include/asm/nohash/64/pgtable-64k.h index 55b28ef3409a..1facb584dd29 100644 --- a/arch/powerpc/include/asm/nohash/64/pgtable-64k.h +++ b/arch/powerpc/include/asm/nohash/64/pgtable-64k.h @@ -1,6 +1,7 @@ #ifndef _ASM_POWERPC_NOHASH_64_PGTABLE_64K_H #define _ASM_POWERPC_NOHASH_64_PGTABLE_64K_H +#define __ARCH_USE_5LEVEL_HACK #include <asm-generic/pgtable-nopud.h> diff --git a/arch/powerpc/include/asm/nohash/pgtable.h b/arch/powerpc/include/asm/nohash/pgtable.h index 0cd8a3852763..e5805ad78e12 100644 --- a/arch/powerpc/include/asm/nohash/pgtable.h +++ b/arch/powerpc/include/asm/nohash/pgtable.h @@ -230,7 +230,7 @@ static inline int hugepd_ok(hugepd_t hpd) return ((hpd_val(hpd) & 0x4) != 0); #else /* We clear the top bit to indicate hugepd */ - return ((hpd_val(hpd) & PD_HUGE) == 0); + return (hpd_val(hpd) && (hpd_val(hpd) & PD_HUGE) == 0); #endif } diff --git a/arch/powerpc/include/asm/ppc-opcode.h b/arch/powerpc/include/asm/ppc-opcode.h index d99bd442aacb..e7d6d86563ee 100644 --- a/arch/powerpc/include/asm/ppc-opcode.h +++ b/arch/powerpc/include/asm/ppc-opcode.h @@ -284,6 +284,13 @@ #define PPC_INST_BRANCH_COND 0x40800000 #define PPC_INST_LBZCIX 0x7c0006aa #define PPC_INST_STBCIX 0x7c0007aa +#define PPC_INST_LWZX 0x7c00002e +#define PPC_INST_LFSX 0x7c00042e +#define PPC_INST_STFSX 0x7c00052e +#define PPC_INST_LFDX 0x7c0004ae +#define PPC_INST_STFDX 0x7c0005ae +#define PPC_INST_LVX 0x7c0000ce +#define PPC_INST_STVX 0x7c0001ce /* macros to insert fields into opcodes */ #define ___PPC_RA(a) (((a) & 0x1f) << 16) diff --git a/arch/powerpc/include/asm/prom.h b/arch/powerpc/include/asm/prom.h index 4a90634e8322..35c00d7a0cf8 100644 --- a/arch/powerpc/include/asm/prom.h +++ b/arch/powerpc/include/asm/prom.h @@ -160,12 +160,18 @@ struct of_drconf_cell { #define OV5_PFO_HW_ENCR 0x1120 /* PFO Encryption Accelerator */ #define OV5_SUB_PROCESSORS 0x1501 /* 1,2,or 4 Sub-Processors supported */ #define OV5_XIVE_EXPLOIT 0x1701 /* XIVE exploitation supported */ -#define OV5_MMU_RADIX_300 0x1880 /* ISA v3.00 radix MMU supported */ -#define OV5_MMU_HASH_300 0x1840 /* ISA v3.00 hash MMU supported */ -#define OV5_MMU_SEGM_RADIX 0x1820 /* radix mode (no segmentation) */ -#define OV5_MMU_PROC_TBL 0x1810 /* hcall selects SLB or proc table */ -#define OV5_MMU_SLB 0x1800 /* always use SLB */ -#define OV5_MMU_GTSE 0x1808 /* Guest translation shootdown */ +/* MMU Base Architecture */ +#define OV5_MMU_SUPPORT 0x18C0 /* MMU Mode Support Mask */ +#define OV5_MMU_HASH 0x1800 /* Hash MMU Only */ +#define OV5_MMU_RADIX 0x1840 /* Radix MMU Only */ +#define OV5_MMU_EITHER 0x1880 /* Hash or Radix Supported */ +#define OV5_MMU_DYNAMIC 0x18C0 /* Hash or Radix Can Switch Later */ +#define OV5_NMMU 0x1820 /* Nest MMU Available */ +/* Hash Table Extensions */ +#define OV5_HASH_SEG_TBL 0x1980 /* In Memory Segment Tables Available */ +#define OV5_HASH_GTSE 0x1940 /* Guest Translation Shoot Down Avail */ +/* Radix Table Extensions */ +#define OV5_RADIX_GTSE 0x1A40 /* Guest Translation Shoot Down Avail */ /* Option Vector 6: IBM PAPR hints */ #define OV6_LINUX 0x02 /* Linux is our OS */ diff --git a/arch/powerpc/kernel/cputable.c b/arch/powerpc/kernel/cputable.c index bb7a1890aeb7..e79b9daa873c 100644 --- a/arch/powerpc/kernel/cputable.c +++ b/arch/powerpc/kernel/cputable.c @@ -77,6 +77,7 @@ extern void __flush_tlb_power8(unsigned int action); extern void __flush_tlb_power9(unsigned int action); extern long __machine_check_early_realmode_p7(struct pt_regs *regs); extern long __machine_check_early_realmode_p8(struct pt_regs *regs); +extern long __machine_check_early_realmode_p9(struct pt_regs *regs); #endif /* CONFIG_PPC64 */ #if defined(CONFIG_E500) extern void __setup_cpu_e5500(unsigned long offset, struct cpu_spec* spec); @@ -540,6 +541,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_setup = __setup_cpu_power9, .cpu_restore = __restore_cpu_power9, .flush_tlb = __flush_tlb_power9, + .machine_check_early = __machine_check_early_realmode_p9, .platform = "power9", }, { /* Power9 */ @@ -559,6 +561,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_setup = __setup_cpu_power9, .cpu_restore = __restore_cpu_power9, .flush_tlb = __flush_tlb_power9, + .machine_check_early = __machine_check_early_realmode_p9, .platform = "power9", }, { /* Cell Broadband Engine */ diff --git a/arch/powerpc/kernel/idle_book3s.S b/arch/powerpc/kernel/idle_book3s.S index 5f61cc0349c0..995728736677 100644 --- a/arch/powerpc/kernel/idle_book3s.S +++ b/arch/powerpc/kernel/idle_book3s.S @@ -276,19 +276,21 @@ power_enter_stop: */ andis. r4,r3,PSSCR_EC_ESL_MASK_SHIFTED clrldi r3,r3,60 /* r3 = Bits[60:63] = Requested Level (RL) */ - bne 1f + bne .Lhandle_esl_ec_set IDLE_STATE_ENTER_SEQ(PPC_STOP) li r3,0 /* Since we didn't lose state, return 0 */ b pnv_wakeup_noloss + +.Lhandle_esl_ec_set: /* * Check if the requested state is a deep idle state. */ -1: LOAD_REG_ADDRBASE(r5,pnv_first_deep_stop_state) + LOAD_REG_ADDRBASE(r5,pnv_first_deep_stop_state) ld r4,ADDROFF(pnv_first_deep_stop_state)(r5) cmpd r3,r4 - bge 2f + bge .Lhandle_deep_stop IDLE_STATE_ENTER_SEQ_NORET(PPC_STOP) -2: +.Lhandle_deep_stop: /* * Entering deep idle state. * Clear thread bit in PACA_CORE_IDLE_STATE, save SPRs to diff --git a/arch/powerpc/kernel/mce.c b/arch/powerpc/kernel/mce.c index c6923ff45131..a1475e6aef3a 100644 --- a/arch/powerpc/kernel/mce.c +++ b/arch/powerpc/kernel/mce.c @@ -58,6 +58,15 @@ static void mce_set_error_info(struct machine_check_event *mce, case MCE_ERROR_TYPE_TLB: mce->u.tlb_error.tlb_error_type = mce_err->u.tlb_error_type; break; + case MCE_ERROR_TYPE_USER: + mce->u.user_error.user_error_type = mce_err->u.user_error_type; + break; + case MCE_ERROR_TYPE_RA: + mce->u.ra_error.ra_error_type = mce_err->u.ra_error_type; + break; + case MCE_ERROR_TYPE_LINK: + mce->u.link_error.link_error_type = mce_err->u.link_error_type; + break; case MCE_ERROR_TYPE_UNKNOWN: default: break; @@ -90,13 +99,14 @@ void save_mce_event(struct pt_regs *regs, long handled, mce->gpr3 = regs->gpr[3]; mce->in_use = 1; - mce->initiator = MCE_INITIATOR_CPU; /* Mark it recovered if we have handled it and MSR(RI=1). */ if (handled && (regs->msr & MSR_RI)) mce->disposition = MCE_DISPOSITION_RECOVERED; else mce->disposition = MCE_DISPOSITION_NOT_RECOVERED; - mce->severity = MCE_SEV_ERROR_SYNC; + + mce->initiator = mce_err->initiator; + mce->severity = mce_err->severity; /* * Populate the mce error_type and type-specific error_type. @@ -115,6 +125,15 @@ void save_mce_event(struct pt_regs *regs, long handled, } else if (mce->error_type == MCE_ERROR_TYPE_ERAT) { mce->u.erat_error.effective_address_provided = true; mce->u.erat_error.effective_address = addr; + } else if (mce->error_type == MCE_ERROR_TYPE_USER) { + mce->u.user_error.effective_address_provided = true; + mce->u.user_error.effective_address = addr; + } else if (mce->error_type == MCE_ERROR_TYPE_RA) { + mce->u.ra_error.effective_address_provided = true; + mce->u.ra_error.effective_address = addr; + } else if (mce->error_type == MCE_ERROR_TYPE_LINK) { + mce->u.link_error.effective_address_provided = true; + mce->u.link_error.effective_address = addr; } else if (mce->error_type == MCE_ERROR_TYPE_UE) { mce->u.ue_error.effective_address_provided = true; mce->u.ue_error.effective_address = addr; @@ -239,6 +258,29 @@ void machine_check_print_event_info(struct machine_check_event *evt) "Parity", "Multihit", }; + static const char *mc_user_types[] = { + "Indeterminate", + "tlbie(l) invalid", + }; + static const char *mc_ra_types[] = { + "Indeterminate", + "Instruction fetch (bad)", + "Page table walk ifetch (bad)", + "Page table walk ifetch (foreign)", + "Load (bad)", + "Store (bad)", + "Page table walk Load/Store (bad)", + "Page table walk Load/Store (foreign)", + "Load/Store (foreign)", + }; + static const char *mc_link_types[] = { + "Indeterminate", + "Instruction fetch (timeout)", + "Page table walk ifetch (timeout)", + "Load (timeout)", + "Store (timeout)", + "Page table walk Load/Store (timeout)", + }; /* Print things out */ if (evt->version != MCE_V1) { @@ -315,6 +357,36 @@ void machine_check_print_event_info(struct machine_check_event *evt) printk("%s Effective address: %016llx\n", level, evt->u.tlb_error.effective_address); break; + case MCE_ERROR_TYPE_USER: + subtype = evt->u.user_error.user_error_type < + ARRAY_SIZE(mc_user_types) ? + mc_user_types[evt->u.user_error.user_error_type] + : "Unknown"; + printk("%s Error type: User [%s]\n", level, subtype); + if (evt->u.user_error.effective_address_provided) + printk("%s Effective address: %016llx\n", + level, evt->u.user_error.effective_address); + break; + case MCE_ERROR_TYPE_RA: + subtype = evt->u.ra_error.ra_error_type < + ARRAY_SIZE(mc_ra_types) ? + mc_ra_types[evt->u.ra_error.ra_error_type] + : "Unknown"; + printk("%s Error type: Real address [%s]\n", level, subtype); + if (evt->u.ra_error.effective_address_provided) + printk("%s Effective address: %016llx\n", + level, evt->u.ra_error.effective_address); + break; + case MCE_ERROR_TYPE_LINK: + subtype = evt->u.link_error.link_error_type < + ARRAY_SIZE(mc_link_types) ? + mc_link_types[evt->u.link_error.link_error_type] + : "Unknown"; + printk("%s Error type: Link [%s]\n", level, subtype); + if (evt->u.link_error.effective_address_provided) + printk("%s Effective address: %016llx\n", + level, evt->u.link_error.effective_address); + break; default: case MCE_ERROR_TYPE_UNKNOWN: printk("%s Error type: Unknown\n", level); @@ -341,6 +413,18 @@ uint64_t get_mce_fault_addr(struct machine_check_event *evt) if (evt->u.tlb_error.effective_address_provided) return evt->u.tlb_error.effective_address; break; + case MCE_ERROR_TYPE_USER: + if (evt->u.user_error.effective_address_provided) + return evt->u.user_error.effective_address; + break; + case MCE_ERROR_TYPE_RA: + if (evt->u.ra_error.effective_address_provided) + return evt->u.ra_error.effective_address; + break; + case MCE_ERROR_TYPE_LINK: + if (evt->u.link_error.effective_address_provided) + return evt->u.link_error.effective_address; + break; default: case MCE_ERROR_TYPE_UNKNOWN: break; diff --git a/arch/powerpc/kernel/mce_power.c b/arch/powerpc/kernel/mce_power.c index 7353991c4ece..763d6f58caa8 100644 --- a/arch/powerpc/kernel/mce_power.c +++ b/arch/powerpc/kernel/mce_power.c @@ -116,6 +116,51 @@ static void flush_and_reload_slb(void) } #endif +static void flush_erat(void) +{ + asm volatile(PPC_INVALIDATE_ERAT : : :"memory"); +} + +#define MCE_FLUSH_SLB 1 +#define MCE_FLUSH_TLB 2 +#define MCE_FLUSH_ERAT 3 + +static int mce_flush(int what) +{ +#ifdef CONFIG_PPC_STD_MMU_64 + if (what == MCE_FLUSH_SLB) { + flush_and_reload_slb(); + return 1; + } +#endif + if (what == MCE_FLUSH_ERAT) { + flush_erat(); + return 1; + } + if (what == MCE_FLUSH_TLB) { + if (cur_cpu_spec && cur_cpu_spec->flush_tlb) { + cur_cpu_spec->flush_tlb(TLB_INVAL_SCOPE_GLOBAL); + return 1; + } + } + + return 0; +} + +static int mce_handle_flush_derrors(uint64_t dsisr, uint64_t slb, uint64_t tlb, uint64_t erat) +{ + if ((dsisr & slb) && mce_flush(MCE_FLUSH_SLB)) + dsisr &= ~slb; + if ((dsisr & erat) && mce_flush(MCE_FLUSH_ERAT)) + dsisr &= ~erat; + if ((dsisr & tlb) && mce_flush(MCE_FLUSH_TLB)) + dsisr &= ~tlb; + /* Any other errors we don't understand? */ + if (dsisr) + return 0; + return 1; +} + static long mce_handle_derror(uint64_t dsisr, uint64_t slb_error_bits) { long handled = 1; @@ -281,6 +326,9 @@ long __machine_check_early_realmode_p7(struct pt_regs *regs) long handled = 1; struct mce_error_info mce_error_info = { 0 }; + mce_error_info.severity = MCE_SEV_ERROR_SYNC; + mce_error_info.initiator = MCE_INITIATOR_CPU; + srr1 = regs->msr; nip = regs->nip; @@ -352,6 +400,9 @@ long __machine_check_early_realmode_p8(struct pt_regs *regs) long handled = 1; struct mce_error_info mce_error_info = { 0 }; + mce_error_info.severity = MCE_SEV_ERROR_SYNC; + mce_error_info.initiator = MCE_INITIATOR_CPU; + srr1 = regs->msr; nip = regs->nip; @@ -372,3 +423,189 @@ long __machine_check_early_realmode_p8(struct pt_regs *regs) save_mce_event(regs, handled, &mce_error_info, nip, addr); return handled; } + +static int mce_handle_derror_p9(struct pt_regs *regs) +{ + uint64_t dsisr = regs->dsisr; + + return mce_handle_flush_derrors(dsisr, + P9_DSISR_MC_SLB_PARITY_MFSLB | + P9_DSISR_MC_SLB_MULTIHIT_MFSLB, + + P9_DSISR_MC_TLB_MULTIHIT_MFTLB, + + P9_DSISR_MC_ERAT_MULTIHIT); +} + +static int mce_handle_ierror_p9(struct pt_regs *regs) +{ + uint64_t srr1 = regs->msr; + + switch (P9_SRR1_MC_IFETCH(srr1)) { + case P9_SRR1_MC_IFETCH_SLB_PARITY: + case P9_SRR1_MC_IFETCH_SLB_MULTIHIT: + return mce_flush(MCE_FLUSH_SLB); + case P9_SRR1_MC_IFETCH_TLB_MULTIHIT: + return mce_flush(MCE_FLUSH_TLB); + case P9_SRR1_MC_IFETCH_ERAT_MULTIHIT: + return mce_flush(MCE_FLUSH_ERAT); + default: + return 0; + } +} + +static void mce_get_derror_p9(struct pt_regs *regs, + struct mce_error_info *mce_err, uint64_t *addr) +{ + uint64_t dsisr = regs->dsisr; + + mce_err->severity = MCE_SEV_ERROR_SYNC; + mce_err->initiator = MCE_INITIATOR_CPU; + + if (dsisr & P9_DSISR_MC_USER_TLBIE) + *addr = regs->nip; + else + *addr = regs->dar; + + if (dsisr & P9_DSISR_MC_UE) { + mce_err->error_type = MCE_ERROR_TYPE_UE; + mce_err->u.ue_error_type = MCE_UE_ERROR_LOAD_STORE; + } else if (dsisr & P9_DSISR_MC_UE_TABLEWALK) { + mce_err->error_type = MCE_ERROR_TYPE_UE; + mce_err->u.ue_error_type = MCE_UE_ERROR_PAGE_TABLE_WALK_LOAD_STORE; + } else if (dsisr & P9_DSISR_MC_LINK_LOAD_TIMEOUT) { + mce_err->error_type = MCE_ERROR_TYPE_LINK; + mce_err->u.link_error_type = MCE_LINK_ERROR_LOAD_TIMEOUT; + } else if (dsisr & P9_DSISR_MC_LINK_TABLEWALK_TIMEOUT) { + mce_err->error_type = MCE_ERROR_TYPE_LINK; + mce_err->u.link_error_type = MCE_LINK_ERROR_PAGE_TABLE_WALK_LOAD_STORE_TIMEOUT; + } else if (dsisr & P9_DSISR_MC_ERAT_MULTIHIT) { + mce_err->error_type = MCE_ERROR_TYPE_ERAT; + mce_err->u.erat_error_type = MCE_ERAT_ERROR_MULTIHIT; + } else if (dsisr & P9_DSISR_MC_TLB_MULTIHIT_MFTLB) { + mce_err->error_type = MCE_ERROR_TYPE_TLB; + mce_err->u.tlb_error_type = MCE_TLB_ERROR_MULTIHIT; + } else if (dsisr & P9_DSISR_MC_USER_TLBIE) { + mce_err->error_type = MCE_ERROR_TYPE_USER; + mce_err->u.user_error_type = MCE_USER_ERROR_TLBIE; + } else if (dsisr & P9_DSISR_MC_SLB_PARITY_MFSLB) { + mce_err->error_type = MCE_ERROR_TYPE_SLB; + mce_err->u.slb_error_type = MCE_SLB_ERROR_PARITY; + } else if (dsisr & P9_DSISR_MC_SLB_MULTIHIT_MFSLB) { + mce_err->error_type = MCE_ERROR_TYPE_SLB; + mce_err->u.slb_error_type = MCE_SLB_ERROR_MULTIHIT; + } else if (dsisr & P9_DSISR_MC_RA_LOAD) { + mce_err->error_type = MCE_ERROR_TYPE_RA; + mce_err->u.ra_error_type = MCE_RA_ERROR_LOAD; + } else if (dsisr & P9_DSISR_MC_RA_TABLEWALK) { + mce_err->error_type = MCE_ERROR_TYPE_RA; + mce_err->u.ra_error_type = MCE_RA_ERROR_PAGE_TABLE_WALK_LOAD_STORE; + } else if (dsisr & P9_DSISR_MC_RA_TABLEWALK_FOREIGN) { + mce_err->error_type = MCE_ERROR_TYPE_RA; + mce_err->u.ra_error_type = MCE_RA_ERROR_PAGE_TABLE_WALK_LOAD_STORE_FOREIGN; + } else if (dsisr & P9_DSISR_MC_RA_FOREIGN) { + mce_err->error_type = MCE_ERROR_TYPE_RA; + mce_err->u.ra_error_type = MCE_RA_ERROR_LOAD_STORE_FOREIGN; + } +} + +static void mce_get_ierror_p9(struct pt_regs *regs, + struct mce_error_info *mce_err, uint64_t *addr) +{ + uint64_t srr1 = regs->msr; + + switch (P9_SRR1_MC_IFETCH(srr1)) { + case P9_SRR1_MC_IFETCH_RA_ASYNC_STORE: + case P9_SRR1_MC_IFETCH_LINK_ASYNC_STORE_TIMEOUT: + mce_err->severity = MCE_SEV_FATAL; + break; + default: + mce_err->severity = MCE_SEV_ERROR_SYNC; + break; + } + + mce_err->initiator = MCE_INITIATOR_CPU; + + *addr = regs->nip; + + switch (P9_SRR1_MC_IFETCH(srr1)) { + case P9_SRR1_MC_IFETCH_UE: + mce_err->error_type = MCE_ERROR_TYPE_UE; + mce_err->u.ue_error_type = MCE_UE_ERROR_IFETCH; + break; + case P9_SRR1_MC_IFETCH_SLB_PARITY: + mce_err->error_type = MCE_ERROR_TYPE_SLB; + mce_err->u.slb_error_type = MCE_SLB_ERROR_PARITY; + break; + case P9_SRR1_MC_IFETCH_SLB_MULTIHIT: + mce_err->error_type = MCE_ERROR_TYPE_SLB; + mce_err->u.slb_error_type = MCE_SLB_ERROR_MULTIHIT; + break; + case P9_SRR1_MC_IFETCH_ERAT_MULTIHIT: + mce_err->error_type = MCE_ERROR_TYPE_ERAT; + mce_err->u.erat_error_type = MCE_ERAT_ERROR_MULTIHIT; + break; + case P9_SRR1_MC_IFETCH_TLB_MULTIHIT: + mce_err->error_type = MCE_ERROR_TYPE_TLB; + mce_err->u.tlb_error_type = MCE_TLB_ERROR_MULTIHIT; + break; + case P9_SRR1_MC_IFETCH_UE_TLB_RELOAD: + mce_err->error_type = MCE_ERROR_TYPE_UE; + mce_err->u.ue_error_type = MCE_UE_ERROR_PAGE_TABLE_WALK_IFETCH; + break; + case P9_SRR1_MC_IFETCH_LINK_TIMEOUT: + mce_err->error_type = MCE_ERROR_TYPE_LINK; + mce_err->u.link_error_type = MCE_LINK_ERROR_IFETCH_TIMEOUT; + break; + case P9_SRR1_MC_IFETCH_LINK_TABLEWALK_TIMEOUT: + mce_err->error_type = MCE_ERROR_TYPE_LINK; + mce_err->u.link_error_type = MCE_LINK_ERROR_PAGE_TABLE_WALK_IFETCH_TIMEOUT; + break; + case P9_SRR1_MC_IFETCH_RA: + mce_err->error_type = MCE_ERROR_TYPE_RA; + mce_err->u.ra_error_type = MCE_RA_ERROR_IFETCH; + break; + case P9_SRR1_MC_IFETCH_RA_TABLEWALK: + mce_err->error_type = MCE_ERROR_TYPE_RA; + mce_err->u.ra_error_type = MCE_RA_ERROR_PAGE_TABLE_WALK_IFETCH; + break; + case P9_SRR1_MC_IFETCH_RA_ASYNC_STORE: + mce_err->error_type = MCE_ERROR_TYPE_RA; + mce_err->u.ra_error_type = MCE_RA_ERROR_STORE; + break; + case P9_SRR1_MC_IFETCH_LINK_ASYNC_STORE_TIMEOUT: + mce_err->error_type = MCE_ERROR_TYPE_LINK; + mce_err->u.link_error_type = MCE_LINK_ERROR_STORE_TIMEOUT; + break; + case P9_SRR1_MC_IFETCH_RA_TABLEWALK_FOREIGN: + mce_err->error_type = MCE_ERROR_TYPE_RA; + mce_err->u.ra_error_type = MCE_RA_ERROR_PAGE_TABLE_WALK_IFETCH_FOREIGN; + break; + default: + break; + } +} + +long __machine_check_early_realmode_p9(struct pt_regs *regs) +{ + uint64_t nip, addr; + long handled; + struct mce_error_info mce_error_info = { 0 }; + + nip = regs->nip; + + if (P9_SRR1_MC_LOADSTORE(regs->msr)) { + handled = mce_handle_derror_p9(regs); + mce_get_derror_p9(regs, &mce_error_info, &addr); + } else { + handled = mce_handle_ierror_p9(regs); + mce_get_ierror_p9(regs, &mce_error_info, &addr); + } + + /* Handle UE error. */ + if (mce_error_info.error_type == MCE_ERROR_TYPE_UE) + handled = mce_handle_ue_error(regs); + + save_mce_event(regs, handled, &mce_error_info, nip, addr); + return handled; +} diff --git a/arch/powerpc/kernel/prom_init.c b/arch/powerpc/kernel/prom_init.c index a3944540fe0d..1c1b44ec7642 100644 --- a/arch/powerpc/kernel/prom_init.c +++ b/arch/powerpc/kernel/prom_init.c @@ -168,6 +168,14 @@ static unsigned long __initdata prom_tce_alloc_start; static unsigned long __initdata prom_tce_alloc_end; #endif +static bool __initdata prom_radix_disable; + +struct platform_support { + bool hash_mmu; + bool radix_mmu; + bool radix_gtse; +}; + /* Platforms codes are now obsolete in the kernel. Now only used within this * file and ultimately gone too. Feel free to change them if you need, they * are not shared with anything outside of this file anymore @@ -626,6 +634,12 @@ static void __init early_cmdline_parse(void) prom_memory_limit = ALIGN(prom_memory_limit, 0x1000000); #endif } + + opt = strstr(prom_cmd_line, "disable_radix"); + if (opt) { + prom_debug("Radix disabled from cmdline\n"); + prom_radix_disable = true; + } } #if defined(CONFIG_PPC_PSERIES) || defined(CONFIG_PPC_POWERNV) @@ -695,6 +709,8 @@ struct option_vector5 { u8 byte22; u8 intarch; u8 mmu; + u8 hash_ext; + u8 radix_ext; } __packed; struct option_vector6 { @@ -850,8 +866,9 @@ struct ibm_arch_vec __cacheline_aligned ibm_architecture_vec = { .reserved3 = 0, .subprocessors = 1, .intarch = 0, - .mmu = OV5_FEAT(OV5_MMU_RADIX_300) | OV5_FEAT(OV5_MMU_HASH_300) | - OV5_FEAT(OV5_MMU_PROC_TBL) | OV5_FEAT(OV5_MMU_GTSE), + .mmu = 0, + .hash_ext = 0, + .radix_ext = 0, }, /* option vector 6: IBM PAPR hints */ @@ -990,6 +1007,92 @@ static int __init prom_count_smt_threads(void) } +static void __init prom_parse_mmu_model(u8 val, + struct platform_support *support) +{ + switch (val) { + case OV5_FEAT(OV5_MMU_DYNAMIC): + case OV5_FEAT(OV5_MMU_EITHER): /* Either Available */ + prom_debug("MMU - either supported\n"); + support->radix_mmu = !prom_radix_disable; + support->hash_mmu = true; + break; + case OV5_FEAT(OV5_MMU_RADIX): /* Only Radix */ + prom_debug("MMU - radix only\n"); + if (prom_radix_disable) { + /* + * If we __have__ to do radix, we're better off ignoring + * the command line rather than not booting. + */ + prom_printf("WARNING: Ignoring cmdline option disable_radix\n"); + } + support->radix_mmu = true; + break; + case OV5_FEAT(OV5_MMU_HASH): + prom_debug("MMU - hash only\n"); + support->hash_mmu = true; + break; + default: + prom_debug("Unknown mmu support option: 0x%x\n", val); + break; + } +} + +static void __init prom_parse_platform_support(u8 index, u8 val, + struct platform_support *support) +{ + switch (index) { + case OV5_INDX(OV5_MMU_SUPPORT): /* MMU Model */ + prom_parse_mmu_model(val & OV5_FEAT(OV5_MMU_SUPPORT), support); + break; + case OV5_INDX(OV5_RADIX_GTSE): /* Radix Extensions */ + if (val & OV5_FEAT(OV5_RADIX_GTSE)) { + prom_debug("Radix - GTSE supported\n"); + support->radix_gtse = true; + } + break; + } +} + +static void __init prom_check_platform_support(void) +{ + struct platform_support supported = { + .hash_mmu = false, + .radix_mmu = false, + .radix_gtse = false + }; + int prop_len = prom_getproplen(prom.chosen, + "ibm,arch-vec-5-platform-support"); + if (prop_len > 1) { + int i; + u8 vec[prop_len]; + prom_debug("Found ibm,arch-vec-5-platform-support, len: %d\n", + prop_len); + prom_getprop(prom.chosen, "ibm,arch-vec-5-platform-support", + &vec, sizeof(vec)); + for (i = 0; i < prop_len; i += 2) { + prom_debug("%d: index = 0x%x val = 0x%x\n", i / 2 + , vec[i] + , vec[i + 1]); + prom_parse_platform_support(vec[i], vec[i + 1], + &supported); + } + } + + if (supported.radix_mmu && supported.radix_gtse) { + /* Radix preferred - but we require GTSE for now */ + prom_debug("Asking for radix with GTSE\n"); + ibm_architecture_vec.vec5.mmu = OV5_FEAT(OV5_MMU_RADIX); + ibm_architecture_vec.vec5.radix_ext = OV5_FEAT(OV5_RADIX_GTSE); + } else if (supported.hash_mmu) { + /* Default to hash mmu (if we can) */ + prom_debug("Asking for hash\n"); + ibm_architecture_vec.vec5.mmu = OV5_FEAT(OV5_MMU_HASH); + } else { + /* We're probably on a legacy hypervisor */ + prom_debug("Assuming legacy hash support\n"); + } +} static void __init prom_send_capabilities(void) { @@ -997,6 +1100,9 @@ static void __init prom_send_capabilities(void) prom_arg_t ret; u32 cores; + /* Check ibm,arch-vec-5-platform-support and fixup vec5 if required */ + prom_check_platform_support(); + root = call_prom("open", 1, 1, ADDR("/")); if (root != 0) { /* We need to tell the FW about the number of cores we support. @@ -2993,6 +3099,11 @@ unsigned long __init prom_init(unsigned long r3, unsigned long r4, */ prom_check_initrd(r3, r4); + /* + * Do early parsing of command line + */ + early_cmdline_parse(); + #if defined(CONFIG_PPC_PSERIES) || defined(CONFIG_PPC_POWERNV) /* * On pSeries, inform the firmware about our capabilities @@ -3009,11 +3120,6 @@ unsigned long __init prom_init(unsigned long r3, unsigned long r4, copy_and_flush(0, kbase, 0x100, 0); /* - * Do early parsing of command line - */ - early_cmdline_parse(); - - /* * Initialize memory management within prom_init */ prom_init_mem(); diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c index adf2084f214b..9cfaa8b69b5f 100644 --- a/arch/powerpc/kernel/setup_64.c +++ b/arch/powerpc/kernel/setup_64.c @@ -408,7 +408,10 @@ static void init_cache_info(struct ppc_cache_info *info, u32 size, u32 lsize, info->line_size = lsize; info->block_size = bsize; info->log_block_size = __ilog2(bsize); - info->blocks_per_page = PAGE_SIZE / bsize; + if (bsize) + info->blocks_per_page = PAGE_SIZE / bsize; + else + info->blocks_per_page = 0; if (sets == 0) info->assoc = 0xffff; diff --git a/arch/powerpc/kvm/book3s_64_mmu_hv.c b/arch/powerpc/kvm/book3s_64_mmu_hv.c index f3158fb16de3..8c68145ba1bd 100644 --- a/arch/powerpc/kvm/book3s_64_mmu_hv.c +++ b/arch/powerpc/kvm/book3s_64_mmu_hv.c @@ -601,7 +601,7 @@ int kvmppc_book3s_hv_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu, hva, NULL, NULL); if (ptep) { pte = kvmppc_read_update_linux_pte(ptep, 1); - if (pte_write(pte)) + if (__pte_write(pte)) write_ok = 1; } local_irq_restore(flags); diff --git a/arch/powerpc/kvm/book3s_hv_rm_mmu.c b/arch/powerpc/kvm/book3s_hv_rm_mmu.c index 6fca970373ee..ce6f2121fffe 100644 --- a/arch/powerpc/kvm/book3s_hv_rm_mmu.c +++ b/arch/powerpc/kvm/book3s_hv_rm_mmu.c @@ -256,7 +256,7 @@ long kvmppc_do_h_enter(struct kvm *kvm, unsigned long flags, } pte = kvmppc_read_update_linux_pte(ptep, writing); if (pte_present(pte) && !pte_protnone(pte)) { - if (writing && !pte_write(pte)) + if (writing && !__pte_write(pte)) /* make the actual HPTE be read-only */ ptel = hpte_make_readonly(ptel); is_ci = pte_ci(pte); diff --git a/arch/powerpc/lib/Makefile b/arch/powerpc/lib/Makefile index 0e649d72fe8d..2b5e09020cfe 100644 --- a/arch/powerpc/lib/Makefile +++ b/arch/powerpc/lib/Makefile @@ -20,6 +20,7 @@ obj64-y += copypage_64.o copyuser_64.o usercopy_64.o mem_64.o hweight_64.o \ obj64-$(CONFIG_SMP) += locks.o obj64-$(CONFIG_ALTIVEC) += vmx-helper.o +obj64-$(CONFIG_KPROBES_SANITY_TEST) += test_emulate_step.o obj-y += checksum_$(BITS).o checksum_wrappers.o diff --git a/arch/powerpc/lib/sstep.c b/arch/powerpc/lib/sstep.c index 846dba2c6360..9c542ec70c5b 100644 --- a/arch/powerpc/lib/sstep.c +++ b/arch/powerpc/lib/sstep.c @@ -1799,8 +1799,6 @@ int __kprobes emulate_step(struct pt_regs *regs, unsigned int instr) goto instr_done; case LARX: - if (regs->msr & MSR_LE) - return 0; if (op.ea & (size - 1)) break; /* can't handle misaligned */ if (!address_ok(regs, op.ea, size)) @@ -1823,8 +1821,6 @@ int __kprobes emulate_step(struct pt_regs *regs, unsigned int instr) goto ldst_done; case STCX: - if (regs->msr & MSR_LE) - return 0; if (op.ea & (size - 1)) break; /* can't handle misaligned */ if (!address_ok(regs, op.ea, size)) @@ -1849,8 +1845,6 @@ int __kprobes emulate_step(struct pt_regs *regs, unsigned int instr) goto ldst_done; case LOAD: - if (regs->msr & MSR_LE) - return 0; err = read_mem(®s->gpr[op.reg], op.ea, size, regs); if (!err) { if (op.type & SIGNEXT) @@ -1862,8 +1856,6 @@ int __kprobes emulate_step(struct pt_regs *regs, unsigned int instr) #ifdef CONFIG_PPC_FPU case LOAD_FP: - if (regs->msr & MSR_LE) - return 0; if (size == 4) err = do_fp_load(op.reg, do_lfs, op.ea, size, regs); else @@ -1872,15 +1864,11 @@ int __kprobes emulate_step(struct pt_regs *regs, unsigned int instr) #endif #ifdef CONFIG_ALTIVEC case LOAD_VMX: - if (regs->msr & MSR_LE) - return 0; err = do_vec_load(op.reg, do_lvx, op.ea & ~0xfUL, regs); goto ldst_done; #endif #ifdef CONFIG_VSX case LOAD_VSX: - if (regs->msr & MSR_LE) - return 0; err = do_vsx_load(op.reg, do_lxvd2x, op.ea, regs); goto ldst_done; #endif @@ -1903,8 +1891,6 @@ int __kprobes emulate_step(struct pt_regs *regs, unsigned int instr) goto instr_done; case STORE: - if (regs->msr & MSR_LE) - return 0; if ((op.type & UPDATE) && size == sizeof(long) && op.reg == 1 && op.update_reg == 1 && !(regs->msr & MSR_PR) && @@ -1917,8 +1903,6 @@ int __kprobes emulate_step(struct pt_regs *regs, unsigned int instr) #ifdef CONFIG_PPC_FPU case STORE_FP: - if (regs->msr & MSR_LE) - return 0; if (size == 4) err = do_fp_store(op.reg, do_stfs, op.ea, size, regs); else @@ -1927,15 +1911,11 @@ int __kprobes emulate_step(struct pt_regs *regs, unsigned int instr) #endif #ifdef CONFIG_ALTIVEC case STORE_VMX: - if (regs->msr & MSR_LE) - return 0; err = do_vec_store(op.reg, do_stvx, op.ea & ~0xfUL, regs); goto ldst_done; #endif #ifdef CONFIG_VSX case STORE_VSX: - if (regs->msr & MSR_LE) - return 0; err = do_vsx_store(op.reg, do_stxvd2x, op.ea, regs); goto ldst_done; #endif diff --git a/arch/powerpc/lib/test_emulate_step.c b/arch/powerpc/lib/test_emulate_step.c new file mode 100644 index 000000000000..2534c1447554 --- /dev/null +++ b/arch/powerpc/lib/test_emulate_step.c @@ -0,0 +1,434 @@ +/* + * Simple sanity test for emulate_step load/store instructions. + * + * Copyright IBM Corp. 2016 + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + */ + +#define pr_fmt(fmt) "emulate_step_test: " fmt + +#include <linux/ptrace.h> +#include <asm/sstep.h> +#include <asm/ppc-opcode.h> + +#define IMM_L(i) ((uintptr_t)(i) & 0xffff) + +/* + * Defined with TEST_ prefix so it does not conflict with other + * definitions. + */ +#define TEST_LD(r, base, i) (PPC_INST_LD | ___PPC_RT(r) | \ + ___PPC_RA(base) | IMM_L(i)) +#define TEST_LWZ(r, base, i) (PPC_INST_LWZ | ___PPC_RT(r) | \ + ___PPC_RA(base) | IMM_L(i)) +#define TEST_LWZX(t, a, b) (PPC_INST_LWZX | ___PPC_RT(t) | \ + ___PPC_RA(a) | ___PPC_RB(b)) +#define TEST_STD(r, base, i) (PPC_INST_STD | ___PPC_RS(r) | \ + ___PPC_RA(base) | ((i) & 0xfffc)) +#define TEST_LDARX(t, a, b, eh) (PPC_INST_LDARX | ___PPC_RT(t) | \ + ___PPC_RA(a) | ___PPC_RB(b) | \ + __PPC_EH(eh)) +#define TEST_STDCX(s, a, b) (PPC_INST_STDCX | ___PPC_RS(s) | \ + ___PPC_RA(a) | ___PPC_RB(b)) +#define TEST_LFSX(t, a, b) (PPC_INST_LFSX | ___PPC_RT(t) | \ + ___PPC_RA(a) | ___PPC_RB(b)) +#define TEST_STFSX(s, a, b) (PPC_INST_STFSX | ___PPC_RS(s) | \ + ___PPC_RA(a) | ___PPC_RB(b)) +#define TEST_LFDX(t, a, b) (PPC_INST_LFDX | ___PPC_RT(t) | \ + ___PPC_RA(a) | ___PPC_RB(b)) +#define TEST_STFDX(s, a, b) (PPC_INST_STFDX | ___PPC_RS(s) | \ + ___PPC_RA(a) | ___PPC_RB(b)) +#define TEST_LVX(t, a, b) (PPC_INST_LVX | ___PPC_RT(t) | \ + ___PPC_RA(a) | ___PPC_RB(b)) +#define TEST_STVX(s, a, b) (PPC_INST_STVX | ___PPC_RS(s) | \ + ___PPC_RA(a) | ___PPC_RB(b)) +#define TEST_LXVD2X(s, a, b) (PPC_INST_LXVD2X | VSX_XX1((s), R##a, R##b)) +#define TEST_STXVD2X(s, a, b) (PPC_INST_STXVD2X | VSX_XX1((s), R##a, R##b)) + + +static void __init init_pt_regs(struct pt_regs *regs) +{ + static unsigned long msr; + static bool msr_cached; + + memset(regs, 0, sizeof(struct pt_regs)); + + if (likely(msr_cached)) { + regs->msr = msr; + return; + } + + asm volatile("mfmsr %0" : "=r"(regs->msr)); + + regs->msr |= MSR_FP; + regs->msr |= MSR_VEC; + regs->msr |= MSR_VSX; + + msr = regs->msr; + msr_cached = true; +} + +static void __init show_result(char *ins, char *result) +{ + pr_info("%-14s : %s\n", ins, result); +} + +static void __init test_ld(void) +{ + struct pt_regs regs; + unsigned long a = 0x23; + int stepped = -1; + + init_pt_regs(®s); + regs.gpr[3] = (unsigned long) &a; + + /* ld r5, 0(r3) */ + stepped = emulate_step(®s, TEST_LD(5, 3, 0)); + + if (stepped == 1 && regs.gpr[5] == a) + show_result("ld", "PASS"); + else + show_result("ld", "FAIL"); +} + +static void __init test_lwz(void) +{ + struct pt_regs regs; + unsigned int a = 0x4545; + int stepped = -1; + + init_pt_regs(®s); + regs.gpr[3] = (unsigned long) &a; + + /* lwz r5, 0(r3) */ + stepped = emulate_step(®s, TEST_LWZ(5, 3, 0)); + + if (stepped == 1 && regs.gpr[5] == a) + show_result("lwz", "PASS"); + else + show_result("lwz", "FAIL"); +} + +static void __init test_lwzx(void) +{ + struct pt_regs regs; + unsigned int a[3] = {0x0, 0x0, 0x1234}; + int stepped = -1; + + init_pt_regs(®s); + regs.gpr[3] = (unsigned long) a; + regs.gpr[4] = 8; + regs.gpr[5] = 0x8765; + + /* lwzx r5, r3, r4 */ + stepped = emulate_step(®s, TEST_LWZX(5, 3, 4)); + if (stepped == 1 && regs.gpr[5] == a[2]) + show_result("lwzx", "PASS"); + else + show_result("lwzx", "FAIL"); +} + +static void __init test_std(void) +{ + struct pt_regs regs; + unsigned long a = 0x1234; + int stepped = -1; + + init_pt_regs(®s); + regs.gpr[3] = (unsigned long) &a; + regs.gpr[5] = 0x5678; + + /* std r5, 0(r3) */ + stepped = emulate_step(®s, TEST_STD(5, 3, 0)); + if (stepped == 1 || regs.gpr[5] == a) + show_result("std", "PASS"); + else + show_result("std", "FAIL"); +} + +static void __init test_ldarx_stdcx(void) +{ + struct pt_regs regs; + unsigned long a = 0x1234; + int stepped = -1; + unsigned long cr0_eq = 0x1 << 29; /* eq bit of CR0 */ + + init_pt_regs(®s); + asm volatile("mfcr %0" : "=r"(regs.ccr)); + + + /*** ldarx ***/ + + regs.gpr[3] = (unsigned long) &a; + regs.gpr[4] = 0; + regs.gpr[5] = 0x5678; + + /* ldarx r5, r3, r4, 0 */ + stepped = emulate_step(®s, TEST_LDARX(5, 3, 4, 0)); + + /* + * Don't touch 'a' here. Touching 'a' can do Load/store + * of 'a' which result in failure of subsequent stdcx. + * Instead, use hardcoded value for comparison. + */ + if (stepped <= 0 || regs.gpr[5] != 0x1234) { + show_result("ldarx / stdcx.", "FAIL (ldarx)"); + return; + } + + + /*** stdcx. ***/ + + regs.gpr[5] = 0x9ABC; + + /* stdcx. r5, r3, r4 */ + stepped = emulate_step(®s, TEST_STDCX(5, 3, 4)); + + /* + * Two possible scenarios that indicates successful emulation + * of stdcx. : + * 1. Reservation is active and store is performed. In this + * case cr0.eq bit will be set to 1. + * 2. Reservation is not active and store is not performed. + * In this case cr0.eq bit will be set to 0. + */ + if (stepped == 1 && ((regs.gpr[5] == a && (regs.ccr & cr0_eq)) + || (regs.gpr[5] != a && !(regs.ccr & cr0_eq)))) + show_result("ldarx / stdcx.", "PASS"); + else + show_result("ldarx / stdcx.", "FAIL (stdcx.)"); +} + +#ifdef CONFIG_PPC_FPU +static void __init test_lfsx_stfsx(void) +{ + struct pt_regs regs; + union { + float a; + int b; + } c; + int cached_b; + int stepped = -1; + + init_pt_regs(®s); + + + /*** lfsx ***/ + + c.a = 123.45; + cached_b = c.b; + + regs.gpr[3] = (unsigned long) &c.a; + regs.gpr[4] = 0; + + /* lfsx frt10, r3, r4 */ + stepped = emulate_step(®s, TEST_LFSX(10, 3, 4)); + + if (stepped == 1) + show_result("lfsx", "PASS"); + else + show_result("lfsx", "FAIL"); + + + /*** stfsx ***/ + + c.a = 678.91; + + /* stfsx frs10, r3, r4 */ + stepped = emulate_step(®s, TEST_STFSX(10, 3, 4)); + + if (stepped == 1 && c.b == cached_b) + show_result("stfsx", "PASS"); + else + show_result("stfsx", "FAIL"); +} + +static void __init test_lfdx_stfdx(void) +{ + struct pt_regs regs; + union { + double a; + long b; + } c; + long cached_b; + int stepped = -1; + + init_pt_regs(®s); + + + /*** lfdx ***/ + + c.a = 123456.78; + cached_b = c.b; + + regs.gpr[3] = (unsigned long) &c.a; + regs.gpr[4] = 0; + + /* lfdx frt10, r3, r4 */ + stepped = emulate_step(®s, TEST_LFDX(10, 3, 4)); + + if (stepped == 1) + show_result("lfdx", "PASS"); + else + show_result("lfdx", "FAIL"); + + + /*** stfdx ***/ + + c.a = 987654.32; + + /* stfdx frs10, r3, r4 */ + stepped = emulate_step(®s, TEST_STFDX(10, 3, 4)); + + if (stepped == 1 && c.b == cached_b) + show_result("stfdx", "PASS"); + else + show_result("stfdx", "FAIL"); +} +#else +static void __init test_lfsx_stfsx(void) +{ + show_result("lfsx", "SKIP (CONFIG_PPC_FPU is not set)"); + show_result("stfsx", "SKIP (CONFIG_PPC_FPU is not set)"); +} + +static void __init test_lfdx_stfdx(void) +{ + show_result("lfdx", "SKIP (CONFIG_PPC_FPU is not set)"); + show_result("stfdx", "SKIP (CONFIG_PPC_FPU is not set)"); +} +#endif /* CONFIG_PPC_FPU */ + +#ifdef CONFIG_ALTIVEC +static void __init test_lvx_stvx(void) +{ + struct pt_regs regs; + union { + vector128 a; + u32 b[4]; + } c; + u32 cached_b[4]; + int stepped = -1; + + init_pt_regs(®s); + + + /*** lvx ***/ + + cached_b[0] = c.b[0] = 923745; + cached_b[1] = c.b[1] = 2139478; + cached_b[2] = c.b[2] = 9012; + cached_b[3] = c.b[3] = 982134; + + regs.gpr[3] = (unsigned long) &c.a; + regs.gpr[4] = 0; + + /* lvx vrt10, r3, r4 */ + stepped = emulate_step(®s, TEST_LVX(10, 3, 4)); + + if (stepped == 1) + show_result("lvx", "PASS"); + else + show_result("lvx", "FAIL"); + + + /*** stvx ***/ + + c.b[0] = 4987513; + c.b[1] = 84313948; + c.b[2] = 71; + c.b[3] = 498532; + + /* stvx vrs10, r3, r4 */ + stepped = emulate_step(®s, TEST_STVX(10, 3, 4)); + + if (stepped == 1 && cached_b[0] == c.b[0] && cached_b[1] == c.b[1] && + cached_b[2] == c.b[2] && cached_b[3] == c.b[3]) + show_result("stvx", "PASS"); + else + show_result("stvx", "FAIL"); +} +#else +static void __init test_lvx_stvx(void) +{ + show_result("lvx", "SKIP (CONFIG_ALTIVEC is not set)"); + show_result("stvx", "SKIP (CONFIG_ALTIVEC is not set)"); +} +#endif /* CONFIG_ALTIVEC */ + +#ifdef CONFIG_VSX +static void __init test_lxvd2x_stxvd2x(void) +{ + struct pt_regs regs; + union { + vector128 a; + u32 b[4]; + } c; + u32 cached_b[4]; + int stepped = -1; + + init_pt_regs(®s); + + + /*** lxvd2x ***/ + + cached_b[0] = c.b[0] = 18233; + cached_b[1] = c.b[1] = 34863571; + cached_b[2] = c.b[2] = 834; + cached_b[3] = c.b[3] = 6138911; + + regs.gpr[3] = (unsigned long) &c.a; + regs.gpr[4] = 0; + + /* lxvd2x vsr39, r3, r4 */ + stepped = emulate_step(®s, TEST_LXVD2X(39, 3, 4)); + + if (stepped == 1) + show_result("lxvd2x", "PASS"); + else + show_result("lxvd2x", "FAIL"); + + + /*** stxvd2x ***/ + + c.b[0] = 21379463; + c.b[1] = 87; + c.b[2] = 374234; + c.b[3] = 4; + + /* stxvd2x vsr39, r3, r4 */ + stepped = emulate_step(®s, TEST_STXVD2X(39, 3, 4)); + + if (stepped == 1 && cached_b[0] == c.b[0] && cached_b[1] == c.b[1] && + cached_b[2] == c.b[2] && cached_b[3] == c.b[3]) + show_result("stxvd2x", "PASS"); + else + show_result("stxvd2x", "FAIL"); +} +#else +static void __init test_lxvd2x_stxvd2x(void) +{ + show_result("lxvd2x", "SKIP (CONFIG_VSX is not set)"); + show_result("stxvd2x", "SKIP (CONFIG_VSX is not set)"); +} +#endif /* CONFIG_VSX */ + +static int __init test_emulate_step(void) +{ + test_ld(); + test_lwz(); + test_lwzx(); + test_std(); + test_ldarx_stdcx(); + test_lfsx_stfsx(); + test_lfdx_stfdx(); + test_lvx_stvx(); + test_lxvd2x_stxvd2x(); + + return 0; +} +late_initcall(test_emulate_step); diff --git a/arch/powerpc/mm/init_64.c b/arch/powerpc/mm/init_64.c index 6aa3b76aa0d6..9be992083d2a 100644 --- a/arch/powerpc/mm/init_64.c +++ b/arch/powerpc/mm/init_64.c @@ -356,18 +356,42 @@ static void early_check_vec5(void) unsigned long root, chosen; int size; const u8 *vec5; + u8 mmu_supported; root = of_get_flat_dt_root(); chosen = of_get_flat_dt_subnode_by_name(root, "chosen"); - if (chosen == -FDT_ERR_NOTFOUND) + if (chosen == -FDT_ERR_NOTFOUND) { + cur_cpu_spec->mmu_features &= ~MMU_FTR_TYPE_RADIX; return; + } vec5 = of_get_flat_dt_prop(chosen, "ibm,architecture-vec-5", &size); - if (!vec5) + if (!vec5) { + cur_cpu_spec->mmu_features &= ~MMU_FTR_TYPE_RADIX; return; - if (size <= OV5_INDX(OV5_MMU_RADIX_300) || - !(vec5[OV5_INDX(OV5_MMU_RADIX_300)] & OV5_FEAT(OV5_MMU_RADIX_300))) - /* Hypervisor doesn't support radix */ + } + if (size <= OV5_INDX(OV5_MMU_SUPPORT)) { cur_cpu_spec->mmu_features &= ~MMU_FTR_TYPE_RADIX; + return; + } + + /* Check for supported configuration */ + mmu_supported = vec5[OV5_INDX(OV5_MMU_SUPPORT)] & + OV5_FEAT(OV5_MMU_SUPPORT); + if (mmu_supported == OV5_FEAT(OV5_MMU_RADIX)) { + /* Hypervisor only supports radix - check enabled && GTSE */ + if (!early_radix_enabled()) { + pr_warn("WARNING: Ignoring cmdline option disable_radix\n"); + } + if (!(vec5[OV5_INDX(OV5_RADIX_GTSE)] & + OV5_FEAT(OV5_RADIX_GTSE))) { + pr_warn("WARNING: Hypervisor doesn't support RADIX with GTSE\n"); + } + /* Do radix anyway - the hypervisor said we had to */ + cur_cpu_spec->mmu_features |= MMU_FTR_TYPE_RADIX; + } else if (mmu_supported == OV5_FEAT(OV5_MMU_HASH)) { + /* Hypervisor only supports hash - disable radix */ + cur_cpu_spec->mmu_features &= ~MMU_FTR_TYPE_RADIX; + } } void __init mmu_early_init_devtree(void) @@ -383,7 +407,7 @@ void __init mmu_early_init_devtree(void) * even though the ibm,architecture-vec-5 property created by * skiboot doesn't have the necessary bits set. */ - if (early_radix_enabled() && !(mfmsr() & MSR_HV)) + if (!(mfmsr() & MSR_HV)) early_check_vec5(); if (early_radix_enabled()) diff --git a/arch/powerpc/mm/pgtable-radix.c b/arch/powerpc/mm/pgtable-radix.c index 2a590a98e652..c28165d8970b 100644 --- a/arch/powerpc/mm/pgtable-radix.c +++ b/arch/powerpc/mm/pgtable-radix.c @@ -186,6 +186,10 @@ static void __init radix_init_pgtable(void) */ register_process_table(__pa(process_tb), 0, PRTB_SIZE_SHIFT - 12); pr_info("Process table %p and radix root for kernel: %p\n", process_tb, init_mm.pgd); + asm volatile("ptesync" : : : "memory"); + asm volatile(PPC_TLBIE_5(%0,%1,2,1,1) : : + "r" (TLBIEL_INVAL_SET_LPID), "r" (0)); + asm volatile("eieio; tlbsync; ptesync" : : : "memory"); } static void __init radix_init_partition_table(void) diff --git a/arch/powerpc/perf/core-book3s.c b/arch/powerpc/perf/core-book3s.c index 595dd718ea87..2ff13249f87a 100644 --- a/arch/powerpc/perf/core-book3s.c +++ b/arch/powerpc/perf/core-book3s.c @@ -188,6 +188,8 @@ static inline void perf_get_data_addr(struct pt_regs *regs, u64 *addrp) sdsync = POWER7P_MMCRA_SDAR_VALID; else if (ppmu->flags & PPMU_ALT_SIPR) sdsync = POWER6_MMCRA_SDSYNC; + else if (ppmu->flags & PPMU_NO_SIAR) + sdsync = MMCRA_SAMPLE_ENABLE; else sdsync = MMCRA_SDSYNC; diff --git a/arch/powerpc/perf/isa207-common.c b/arch/powerpc/perf/isa207-common.c index e79fb5fb817d..cd951fd231c4 100644 --- a/arch/powerpc/perf/isa207-common.c +++ b/arch/powerpc/perf/isa207-common.c @@ -65,12 +65,41 @@ static bool is_event_valid(u64 event) return !(event & ~valid_mask); } -static u64 mmcra_sdar_mode(u64 event) +static inline bool is_event_marked(u64 event) { - if (cpu_has_feature(CPU_FTR_ARCH_300) && !cpu_has_feature(CPU_FTR_POWER9_DD1)) - return p9_SDAR_MODE(event) << MMCRA_SDAR_MODE_SHIFT; + if (event & EVENT_IS_MARKED) + return true; + + return false; +} - return MMCRA_SDAR_MODE_TLB; +static void mmcra_sdar_mode(u64 event, unsigned long *mmcra) +{ + /* + * MMCRA[SDAR_MODE] specifices how the SDAR should be updated in + * continous sampling mode. + * + * Incase of Power8: + * MMCRA[SDAR_MODE] will be programmed as "0b01" for continous sampling + * mode and will be un-changed when setting MMCRA[63] (Marked events). + * + * Incase of Power9: + * Marked event: MMCRA[SDAR_MODE] will be set to 0b00 ('No Updates'), + * or if group already have any marked events. + * Non-Marked events (for DD1): + * MMCRA[SDAR_MODE] will be set to 0b01 + * For rest + * MMCRA[SDAR_MODE] will be set from event code. + */ + if (cpu_has_feature(CPU_FTR_ARCH_300)) { + if (is_event_marked(event) || (*mmcra & MMCRA_SAMPLE_ENABLE)) + *mmcra &= MMCRA_SDAR_MODE_NO_UPDATES; + else if (!cpu_has_feature(CPU_FTR_POWER9_DD1)) + *mmcra |= p9_SDAR_MODE(event) << MMCRA_SDAR_MODE_SHIFT; + else if (cpu_has_feature(CPU_FTR_POWER9_DD1)) + *mmcra |= MMCRA_SDAR_MODE_TLB; + } else + *mmcra |= MMCRA_SDAR_MODE_TLB; } static u64 thresh_cmp_val(u64 value) @@ -180,7 +209,7 @@ int isa207_get_constraint(u64 event, unsigned long *maskp, unsigned long *valp) value |= CNST_L1_QUAL_VAL(cache); } - if (event & EVENT_IS_MARKED) { + if (is_event_marked(event)) { mask |= CNST_SAMPLE_MASK; value |= CNST_SAMPLE_VAL(event >> EVENT_SAMPLE_SHIFT); } @@ -276,7 +305,7 @@ int isa207_compute_mmcr(u64 event[], int n_ev, } /* In continuous sampling mode, update SDAR on TLB miss */ - mmcra |= mmcra_sdar_mode(event[i]); + mmcra_sdar_mode(event[i], &mmcra); if (event[i] & EVENT_IS_L1) { cache = event[i] >> EVENT_CACHE_SEL_SHIFT; @@ -285,7 +314,7 @@ int isa207_compute_mmcr(u64 event[], int n_ev, mmcr1 |= (cache & 1) << MMCR1_DC_QUAL_SHIFT; } - if (event[i] & EVENT_IS_MARKED) { + if (is_event_marked(event[i])) { mmcra |= MMCRA_SAMPLE_ENABLE; val = (event[i] >> EVENT_SAMPLE_SHIFT) & EVENT_SAMPLE_MASK; diff --git a/arch/powerpc/perf/isa207-common.h b/arch/powerpc/perf/isa207-common.h index cf9bd8990159..899210f14ee4 100644 --- a/arch/powerpc/perf/isa207-common.h +++ b/arch/powerpc/perf/isa207-common.h @@ -246,6 +246,7 @@ #define MMCRA_THR_CMP_SHIFT 32 #define MMCRA_SDAR_MODE_SHIFT 42 #define MMCRA_SDAR_MODE_TLB (1ull << MMCRA_SDAR_MODE_SHIFT) +#define MMCRA_SDAR_MODE_NO_UPDATES ~(0x3ull << MMCRA_SDAR_MODE_SHIFT) #define MMCRA_IFM_SHIFT 30 /* MMCR1 Threshold Compare bit constant for power9 */ diff --git a/arch/powerpc/platforms/powernv/opal-wrappers.S b/arch/powerpc/platforms/powernv/opal-wrappers.S index 6693f75e93d1..da8a0f7a035c 100644 --- a/arch/powerpc/platforms/powernv/opal-wrappers.S +++ b/arch/powerpc/platforms/powernv/opal-wrappers.S @@ -39,8 +39,8 @@ opal_tracepoint_refcount: BEGIN_FTR_SECTION; \ b 1f; \ END_FTR_SECTION(0, 1); \ - ld r12,opal_tracepoint_refcount@toc(r2); \ - cmpdi r12,0; \ + ld r11,opal_tracepoint_refcount@toc(r2); \ + cmpdi r11,0; \ bne- LABEL; \ 1: diff --git a/arch/powerpc/platforms/powernv/opal.c b/arch/powerpc/platforms/powernv/opal.c index 86d9fde93c17..e0f856bfbfe8 100644 --- a/arch/powerpc/platforms/powernv/opal.c +++ b/arch/powerpc/platforms/powernv/opal.c @@ -395,7 +395,6 @@ static int opal_recover_mce(struct pt_regs *regs, struct machine_check_event *evt) { int recovered = 0; - uint64_t ea = get_mce_fault_addr(evt); if (!(regs->msr & MSR_RI)) { /* If MSR_RI isn't set, we cannot recover */ @@ -404,26 +403,18 @@ static int opal_recover_mce(struct pt_regs *regs, } else if (evt->disposition == MCE_DISPOSITION_RECOVERED) { /* Platform corrected itself */ recovered = 1; - } else if (ea && !is_kernel_addr(ea)) { + } else if (evt->severity == MCE_SEV_FATAL) { + /* Fatal machine check */ + pr_err("Machine check interrupt is fatal\n"); + recovered = 0; + } else if ((evt->severity == MCE_SEV_ERROR_SYNC) && + (user_mode(regs) && !is_global_init(current))) { /* - * Faulting address is not in kernel text. We should be fine. - * We need to find which process uses this address. * For now, kill the task if we have received exception when * in userspace. * * TODO: Queue up this address for hwpoisioning later. */ - if (user_mode(regs) && !is_global_init(current)) { - _exception(SIGBUS, regs, BUS_MCEERR_AR, regs->nip); - recovered = 1; - } else - recovered = 0; - } else if (user_mode(regs) && !is_global_init(current) && - evt->severity == MCE_SEV_ERROR_SYNC) { - /* - * If we have received a synchronous error when in userspace - * kill the task. - */ _exception(SIGBUS, regs, BUS_MCEERR_AR, regs->nip); recovered = 1; } diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c index 6901a06da2f9..e36738291c32 100644 --- a/arch/powerpc/platforms/powernv/pci-ioda.c +++ b/arch/powerpc/platforms/powernv/pci-ioda.c @@ -1775,17 +1775,20 @@ static u64 pnv_pci_ioda_dma_get_required_mask(struct pci_dev *pdev) } static void pnv_ioda_setup_bus_dma(struct pnv_ioda_pe *pe, - struct pci_bus *bus) + struct pci_bus *bus, + bool add_to_group) { struct pci_dev *dev; list_for_each_entry(dev, &bus->devices, bus_list) { set_iommu_table_base(&dev->dev, pe->table_group.tables[0]); set_dma_offset(&dev->dev, pe->tce_bypass_base); - iommu_add_device(&dev->dev); + if (add_to_group) + iommu_add_device(&dev->dev); if ((pe->flags & PNV_IODA_PE_BUS_ALL) && dev->subordinate) - pnv_ioda_setup_bus_dma(pe, dev->subordinate); + pnv_ioda_setup_bus_dma(pe, dev->subordinate, + add_to_group); } } @@ -2191,7 +2194,7 @@ found: set_iommu_table_base(&pe->pdev->dev, tbl); iommu_add_device(&pe->pdev->dev); } else if (pe->flags & (PNV_IODA_PE_BUS | PNV_IODA_PE_BUS_ALL)) - pnv_ioda_setup_bus_dma(pe, pe->pbus); + pnv_ioda_setup_bus_dma(pe, pe->pbus, true); return; fail: @@ -2426,6 +2429,8 @@ static void pnv_ioda2_take_ownership(struct iommu_table_group *table_group) pnv_pci_ioda2_set_bypass(pe, false); pnv_pci_ioda2_unset_window(&pe->table_group, 0); + if (pe->pbus) + pnv_ioda_setup_bus_dma(pe, pe->pbus, false); pnv_ioda2_table_free(tbl); } @@ -2435,6 +2440,8 @@ static void pnv_ioda2_release_ownership(struct iommu_table_group *table_group) table_group); pnv_pci_ioda2_setup_default_config(pe); + if (pe->pbus) + pnv_ioda_setup_bus_dma(pe, pe->pbus, false); } static struct iommu_table_group_ops pnv_pci_ioda2_ops = { @@ -2624,6 +2631,9 @@ static long pnv_pci_ioda2_table_alloc_pages(int nid, __u64 bus_offset, level_shift = entries_shift + 3; level_shift = max_t(unsigned, level_shift, PAGE_SHIFT); + if ((level_shift - 3) * levels + page_shift >= 60) + return -EINVAL; + /* Allocate TCE table */ addr = pnv_pci_ioda2_table_do_alloc_pages(nid, level_shift, levels, tce_table_size, &offset, &total_allocated); @@ -2728,7 +2738,7 @@ static void pnv_pci_ioda2_setup_dma_pe(struct pnv_phb *phb, if (pe->flags & PNV_IODA_PE_DEV) iommu_add_device(&pe->pdev->dev); else if (pe->flags & (PNV_IODA_PE_BUS | PNV_IODA_PE_BUS_ALL)) - pnv_ioda_setup_bus_dma(pe, pe->pbus); + pnv_ioda_setup_bus_dma(pe, pe->pbus, true); } #ifdef CONFIG_PCI_MSI diff --git a/arch/powerpc/purgatory/trampoline.S b/arch/powerpc/purgatory/trampoline.S index f9760ccf4032..3696ea6c4826 100644 --- a/arch/powerpc/purgatory/trampoline.S +++ b/arch/powerpc/purgatory/trampoline.S @@ -116,13 +116,13 @@ dt_offset: .data .balign 8 -.globl sha256_digest -sha256_digest: +.globl purgatory_sha256_digest +purgatory_sha256_digest: .skip 32 - .size sha256_digest, . - sha256_digest + .size purgatory_sha256_digest, . - purgatory_sha256_digest .balign 8 -.globl sha_regions -sha_regions: +.globl purgatory_sha_regions +purgatory_sha_regions: .skip 8 * 2 * 16 - .size sha_regions, . - sha_regions + .size purgatory_sha_regions, . - purgatory_sha_regions diff --git a/arch/powerpc/sysdev/axonram.c b/arch/powerpc/sysdev/axonram.c index ada29eaed6e2..f523ac883150 100644 --- a/arch/powerpc/sysdev/axonram.c +++ b/arch/powerpc/sysdev/axonram.c @@ -274,7 +274,9 @@ failed: if (bank->disk->major > 0) unregister_blkdev(bank->disk->major, bank->disk->disk_name); - del_gendisk(bank->disk); + if (bank->disk->flags & GENHD_FL_UP) + del_gendisk(bank->disk); + put_disk(bank->disk); } device->dev.platform_data = NULL; if (bank->io_addr != 0) @@ -299,6 +301,7 @@ axon_ram_remove(struct platform_device *device) device_remove_file(&device->dev, &dev_attr_ecc); free_irq(bank->irq_id, device); del_gendisk(bank->disk); + put_disk(bank->disk); iounmap((void __iomem *) bank->io_addr); kfree(bank); diff --git a/arch/powerpc/sysdev/xics/icp-opal.c b/arch/powerpc/sysdev/xics/icp-opal.c index f9670eabfcfa..b53f80f0b4d8 100644 --- a/arch/powerpc/sysdev/xics/icp-opal.c +++ b/arch/powerpc/sysdev/xics/icp-opal.c @@ -91,6 +91,16 @@ static unsigned int icp_opal_get_irq(void) static void icp_opal_set_cpu_priority(unsigned char cppr) { + /* + * Here be dragons. The caller has asked to allow only IPI's and not + * external interrupts. But OPAL XIVE doesn't support that. So instead + * of allowing no interrupts allow all. That's still not right, but + * currently the only caller who does this is xics_migrate_irqs_away() + * and it works in that case. + */ + if (cppr >= DEFAULT_PRIORITY) + cppr = LOWEST_PRIORITY; + xics_set_base_cppr(cppr); opal_int_set_cppr(cppr); iosync(); diff --git a/arch/powerpc/sysdev/xics/xics-common.c b/arch/powerpc/sysdev/xics/xics-common.c index 69d858e51ac7..23efe4e42172 100644 --- a/arch/powerpc/sysdev/xics/xics-common.c +++ b/arch/powerpc/sysdev/xics/xics-common.c @@ -20,6 +20,7 @@ #include <linux/of.h> #include <linux/slab.h> #include <linux/spinlock.h> +#include <linux/delay.h> #include <asm/prom.h> #include <asm/io.h> @@ -198,9 +199,6 @@ void xics_migrate_irqs_away(void) /* Remove ourselves from the global interrupt queue */ xics_set_cpu_giq(xics_default_distrib_server, 0); - /* Allow IPIs again... */ - icp_ops->set_priority(DEFAULT_PRIORITY); - for_each_irq_desc(virq, desc) { struct irq_chip *chip; long server; @@ -255,6 +253,19 @@ void xics_migrate_irqs_away(void) unlock: raw_spin_unlock_irqrestore(&desc->lock, flags); } + + /* Allow "sufficient" time to drop any inflight IRQ's */ + mdelay(5); + + /* + * Allow IPIs again. This is done at the very end, after migrating all + * interrupts, the expectation is that we'll only get woken up by an IPI + * interrupt beyond this point, but leave externals masked just to be + * safe. If we're using icp-opal this may actually allow all + * interrupts anyway, but that should be OK. + */ + icp_ops->set_priority(DEFAULT_PRIORITY); + } #endif /* CONFIG_HOTPLUG_CPU */ diff --git a/arch/s390/configs/default_defconfig b/arch/s390/configs/default_defconfig index 143b1e00b818..4b176fe83da4 100644 --- a/arch/s390/configs/default_defconfig +++ b/arch/s390/configs/default_defconfig @@ -609,7 +609,7 @@ CONFIG_SCHED_TRACER=y CONFIG_FTRACE_SYSCALLS=y CONFIG_STACK_TRACER=y CONFIG_BLK_DEV_IO_TRACE=y -CONFIG_UPROBE_EVENT=y +CONFIG_UPROBE_EVENTS=y CONFIG_FUNCTION_PROFILER=y CONFIG_HIST_TRIGGERS=y CONFIG_TRACE_ENUM_MAP_FILE=y diff --git a/arch/s390/configs/gcov_defconfig b/arch/s390/configs/gcov_defconfig index f05d2d6e1087..0de46cc397f6 100644 --- a/arch/s390/configs/gcov_defconfig +++ b/arch/s390/configs/gcov_defconfig @@ -560,7 +560,7 @@ CONFIG_SCHED_TRACER=y CONFIG_FTRACE_SYSCALLS=y CONFIG_STACK_TRACER=y CONFIG_BLK_DEV_IO_TRACE=y -CONFIG_UPROBE_EVENT=y +CONFIG_UPROBE_EVENTS=y CONFIG_FUNCTION_PROFILER=y CONFIG_HIST_TRIGGERS=y CONFIG_TRACE_ENUM_MAP_FILE=y diff --git a/arch/s390/configs/performance_defconfig b/arch/s390/configs/performance_defconfig index 2358bf33c5ef..e167557b434c 100644 --- a/arch/s390/configs/performance_defconfig +++ b/arch/s390/configs/performance_defconfig @@ -558,7 +558,7 @@ CONFIG_SCHED_TRACER=y CONFIG_FTRACE_SYSCALLS=y CONFIG_STACK_TRACER=y CONFIG_BLK_DEV_IO_TRACE=y -CONFIG_UPROBE_EVENT=y +CONFIG_UPROBE_EVENTS=y CONFIG_FUNCTION_PROFILER=y CONFIG_HIST_TRIGGERS=y CONFIG_TRACE_ENUM_MAP_FILE=y diff --git a/arch/s390/crypto/paes_s390.c b/arch/s390/crypto/paes_s390.c index d69ea495c4d7..716b17238599 100644 --- a/arch/s390/crypto/paes_s390.c +++ b/arch/s390/crypto/paes_s390.c @@ -474,8 +474,11 @@ static int ctr_paes_crypt(struct blkcipher_desc *desc, unsigned long modifier, ret = blkcipher_walk_done(desc, walk, nbytes - n); } if (k < n) { - if (__ctr_paes_set_key(ctx) != 0) + if (__ctr_paes_set_key(ctx) != 0) { + if (locked) + spin_unlock(&ctrblk_lock); return blkcipher_walk_done(desc, walk, -EIO); + } } } if (locked) diff --git a/arch/s390/defconfig b/arch/s390/defconfig index 68bfd09f1b02..97189dbaf34b 100644 --- a/arch/s390/defconfig +++ b/arch/s390/defconfig @@ -179,7 +179,7 @@ CONFIG_FTRACE_SYSCALLS=y CONFIG_TRACER_SNAPSHOT_PER_CPU_SWAP=y CONFIG_STACK_TRACER=y CONFIG_BLK_DEV_IO_TRACE=y -CONFIG_UPROBE_EVENT=y +CONFIG_UPROBE_EVENTS=y CONFIG_FUNCTION_PROFILER=y CONFIG_TRACE_ENUM_MAP_FILE=y CONFIG_KPROBES_SANITY_TEST=y diff --git a/arch/s390/include/asm/cputime.h b/arch/s390/include/asm/cputime.h index d1c407ddf703..9072bf63a846 100644 --- a/arch/s390/include/asm/cputime.h +++ b/arch/s390/include/asm/cputime.h @@ -8,31 +8,27 @@ #define _S390_CPUTIME_H #include <linux/types.h> -#include <asm/div64.h> +#include <asm/timex.h> #define CPUTIME_PER_USEC 4096ULL #define CPUTIME_PER_SEC (CPUTIME_PER_USEC * USEC_PER_SEC) /* We want to use full resolution of the CPU timer: 2**-12 micro-seconds. */ -typedef unsigned long long __nocast cputime_t; -typedef unsigned long long __nocast cputime64_t; - #define cmpxchg_cputime(ptr, old, new) cmpxchg64(ptr, old, new) -static inline unsigned long __div(unsigned long long n, unsigned long base) -{ - return n / base; -} - /* - * Convert cputime to microseconds and back. + * Convert cputime to microseconds. */ -static inline unsigned int cputime_to_usecs(const cputime_t cputime) +static inline u64 cputime_to_usecs(const u64 cputime) { - return (__force unsigned long long) cputime >> 12; + return cputime >> 12; } +/* + * Convert cputime to nanoseconds. + */ +#define cputime_to_nsecs(cputime) tod_to_ns(cputime) u64 arch_cpu_idle_time(int cpu); diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h index 7ed1972b1920..93e37b12e882 100644 --- a/arch/s390/include/asm/pgtable.h +++ b/arch/s390/include/asm/pgtable.h @@ -24,6 +24,7 @@ * the S390 page table tree. */ #ifndef __ASSEMBLY__ +#include <asm-generic/5level-fixup.h> #include <linux/sched.h> #include <linux/mm_types.h> #include <linux/page-flags.h> diff --git a/arch/s390/include/asm/timex.h b/arch/s390/include/asm/timex.h index 354344dcc198..118535123f34 100644 --- a/arch/s390/include/asm/timex.h +++ b/arch/s390/include/asm/timex.h @@ -206,20 +206,16 @@ static inline unsigned long long get_tod_clock_monotonic(void) * ns = (todval * 125) >> 9; * * In order to avoid an overflow with the multiplication we can rewrite this. - * With a split todval == 2^32 * th + tl (th upper 32 bits, tl lower 32 bits) + * With a split todval == 2^9 * th + tl (th upper 55 bits, tl lower 9 bits) * we end up with * - * ns = ((2^32 * th + tl) * 125 ) >> 9; - * -> ns = (2^23 * th * 125) + ((tl * 125) >> 9); + * ns = ((2^9 * th + tl) * 125 ) >> 9; + * -> ns = (th * 125) + ((tl * 125) >> 9); * */ static inline unsigned long long tod_to_ns(unsigned long long todval) { - unsigned long long ns; - - ns = ((todval >> 32) << 23) * 125; - ns += ((todval & 0xffffffff) * 125) >> 9; - return ns; + return ((todval >> 9) * 125) + (((todval & 0x1ff) * 125) >> 9); } #endif diff --git a/arch/s390/include/uapi/asm/unistd.h b/arch/s390/include/uapi/asm/unistd.h index 4384bc797a54..152de9b796e1 100644 --- a/arch/s390/include/uapi/asm/unistd.h +++ b/arch/s390/include/uapi/asm/unistd.h @@ -313,7 +313,9 @@ #define __NR_copy_file_range 375 #define __NR_preadv2 376 #define __NR_pwritev2 377 -#define NR_syscalls 378 +/* Number 378 is reserved for guarded storage */ +#define __NR_statx 379 +#define NR_syscalls 380 /* * There are some system calls that are not present on 64 bit, some diff --git a/arch/s390/kernel/compat_wrapper.c b/arch/s390/kernel/compat_wrapper.c index ae2cda5eee5a..e89cc2e71db1 100644 --- a/arch/s390/kernel/compat_wrapper.c +++ b/arch/s390/kernel/compat_wrapper.c @@ -178,3 +178,4 @@ COMPAT_SYSCALL_WRAP3(getpeername, int, fd, struct sockaddr __user *, usockaddr, COMPAT_SYSCALL_WRAP6(sendto, int, fd, void __user *, buff, size_t, len, unsigned int, flags, struct sockaddr __user *, addr, int, addr_len); COMPAT_SYSCALL_WRAP3(mlock2, unsigned long, start, size_t, len, int, flags); COMPAT_SYSCALL_WRAP6(copy_file_range, int, fd_in, loff_t __user *, off_in, int, fd_out, loff_t __user *, off_out, size_t, len, unsigned int, flags); +COMPAT_SYSCALL_WRAP5(statx, int, dfd, const char __user *, path, unsigned, flags, unsigned, mask, struct statx __user *, buffer); diff --git a/arch/s390/kernel/entry.S b/arch/s390/kernel/entry.S index dff2152350a7..6a7d737d514c 100644 --- a/arch/s390/kernel/entry.S +++ b/arch/s390/kernel/entry.S @@ -490,7 +490,7 @@ ENTRY(pgm_check_handler) jnz .Lpgm_svcper # -> single stepped svc 1: CHECK_STACK STACK_SIZE,__LC_SAVE_AREA_SYNC aghi %r15,-(STACK_FRAME_OVERHEAD + __PT_SIZE) - j 3f + j 4f 2: UPDATE_VTIME %r14,%r15,__LC_SYNC_ENTER_TIMER lg %r15,__LC_KERNEL_STACK lgr %r14,%r12 @@ -499,8 +499,8 @@ ENTRY(pgm_check_handler) tm __LC_PGM_ILC+2,0x02 # check for transaction abort jz 3f mvc __THREAD_trap_tdb(256,%r14),0(%r13) -3: la %r11,STACK_FRAME_OVERHEAD(%r15) - stg %r10,__THREAD_last_break(%r14) +3: stg %r10,__THREAD_last_break(%r14) +4: la %r11,STACK_FRAME_OVERHEAD(%r15) stmg %r0,%r7,__PT_R0(%r11) mvc __PT_R8(64,%r11),__LC_SAVE_AREA_SYNC stmg %r8,%r9,__PT_PSW(%r11) @@ -509,14 +509,14 @@ ENTRY(pgm_check_handler) xc __PT_FLAGS(8,%r11),__PT_FLAGS(%r11) stg %r10,__PT_ARGS(%r11) tm __LC_PGM_ILC+3,0x80 # check for per exception - jz 4f + jz 5f tmhh %r8,0x0001 # kernel per event ? jz .Lpgm_kprobe oi __PT_FLAGS+7(%r11),_PIF_PER_TRAP mvc __THREAD_per_address(8,%r14),__LC_PER_ADDRESS mvc __THREAD_per_cause(2,%r14),__LC_PER_CODE mvc __THREAD_per_paid(1,%r14),__LC_PER_ACCESS_ID -4: REENABLE_IRQS +5: REENABLE_IRQS xc __SF_BACKCHAIN(8,%r15),__SF_BACKCHAIN(%r15) larl %r1,pgm_check_table llgh %r10,__PT_INT_CODE+2(%r11) diff --git a/arch/s390/kernel/ipl.c b/arch/s390/kernel/ipl.c index b67dafb7b7cf..e545ffe5155a 100644 --- a/arch/s390/kernel/ipl.c +++ b/arch/s390/kernel/ipl.c @@ -564,6 +564,8 @@ static struct kset *ipl_kset; static void __ipl_run(void *unused) { + if (MACHINE_IS_LPAR && ipl_info.type == IPL_TYPE_CCW) + diag308(DIAG308_LOAD_NORMAL_DUMP, NULL); diag308(DIAG308_LOAD_CLEAR, NULL); if (MACHINE_IS_VM) __cpcmd("IPL", NULL, 0, NULL); diff --git a/arch/s390/kernel/process.c b/arch/s390/kernel/process.c index 20cd339e11ae..f29e41c5e2ec 100644 --- a/arch/s390/kernel/process.c +++ b/arch/s390/kernel/process.c @@ -124,7 +124,10 @@ int copy_thread_tls(unsigned long clone_flags, unsigned long new_stackp, clear_tsk_thread_flag(p, TIF_SINGLE_STEP); /* Initialize per thread user and system timer values */ p->thread.user_timer = 0; + p->thread.guest_timer = 0; p->thread.system_timer = 0; + p->thread.hardirq_timer = 0; + p->thread.softirq_timer = 0; frame->sf.back_chain = 0; /* new return point is ret_from_fork */ diff --git a/arch/s390/kernel/syscalls.S b/arch/s390/kernel/syscalls.S index 9b59e6212d8f..2659b5cfeddb 100644 --- a/arch/s390/kernel/syscalls.S +++ b/arch/s390/kernel/syscalls.S @@ -386,3 +386,5 @@ SYSCALL(sys_mlock2,compat_sys_mlock2) SYSCALL(sys_copy_file_range,compat_sys_copy_file_range) /* 375 */ SYSCALL(sys_preadv2,compat_sys_preadv2) SYSCALL(sys_pwritev2,compat_sys_pwritev2) +NI_SYSCALL +SYSCALL(sys_statx,compat_sys_statx) diff --git a/arch/s390/kernel/vtime.c b/arch/s390/kernel/vtime.c index c14fc9029912..072d84ba42a3 100644 --- a/arch/s390/kernel/vtime.c +++ b/arch/s390/kernel/vtime.c @@ -111,7 +111,7 @@ static inline u64 scale_vtime(u64 vtime) } static void account_system_index_scaled(struct task_struct *p, - cputime_t cputime, cputime_t scaled, + u64 cputime, u64 scaled, enum cpu_usage_stat index) { p->stimescaled += cputime_to_nsecs(scaled); diff --git a/arch/s390/mm/pgtable.c b/arch/s390/mm/pgtable.c index b48dc5f1900b..463e5ef02304 100644 --- a/arch/s390/mm/pgtable.c +++ b/arch/s390/mm/pgtable.c @@ -608,12 +608,29 @@ void ptep_zap_key(struct mm_struct *mm, unsigned long addr, pte_t *ptep) bool test_and_clear_guest_dirty(struct mm_struct *mm, unsigned long addr) { spinlock_t *ptl; + pgd_t *pgd; + pud_t *pud; + pmd_t *pmd; pgste_t pgste; pte_t *ptep; pte_t pte; bool dirty; - ptep = get_locked_pte(mm, addr, &ptl); + pgd = pgd_offset(mm, addr); + pud = pud_alloc(mm, pgd, addr); + if (!pud) + return false; + pmd = pmd_alloc(mm, pud, addr); + if (!pmd) + return false; + /* We can't run guests backed by huge pages, but userspace can + * still set them up and then try to migrate them without any + * migration support. + */ + if (pmd_large(*pmd)) + return true; + + ptep = pte_alloc_map_lock(mm, pmd, addr, &ptl); if (unlikely(!ptep)) return false; diff --git a/arch/score/include/asm/pgtable.h b/arch/score/include/asm/pgtable.h index 0553e5cd5985..46ff8fd678a7 100644 --- a/arch/score/include/asm/pgtable.h +++ b/arch/score/include/asm/pgtable.h @@ -2,6 +2,7 @@ #define _ASM_SCORE_PGTABLE_H #include <linux/const.h> +#define __ARCH_USE_5LEVEL_HACK #include <asm-generic/pgtable-nopmd.h> #include <asm/fixmap.h> diff --git a/arch/score/kernel/traps.c b/arch/score/kernel/traps.c index e359ec675869..12daf45369b4 100644 --- a/arch/score/kernel/traps.c +++ b/arch/score/kernel/traps.c @@ -24,6 +24,7 @@ */ #include <linux/extable.h> +#include <linux/ptrace.h> #include <linux/sched/mm.h> #include <linux/sched/signal.h> #include <linux/sched/debug.h> diff --git a/arch/score/mm/extable.c b/arch/score/mm/extable.c index ec871355fc2d..6736a3ad6286 100644 --- a/arch/score/mm/extable.c +++ b/arch/score/mm/extable.c @@ -24,6 +24,8 @@ */ #include <linux/extable.h> +#include <linux/ptrace.h> +#include <asm/extable.h> int fixup_exception(struct pt_regs *regs) { diff --git a/arch/sh/boards/mach-cayman/setup.c b/arch/sh/boards/mach-cayman/setup.c index 340fd40b381d..9c292c27e0d7 100644 --- a/arch/sh/boards/mach-cayman/setup.c +++ b/arch/sh/boards/mach-cayman/setup.c @@ -128,7 +128,6 @@ static int __init smsc_superio_setup(void) SMSC_SUPERIO_WRITE_INDEXED(1, SMSC_PRIMARY_INT_INDEX); SMSC_SUPERIO_WRITE_INDEXED(12, SMSC_SECONDARY_INT_INDEX); -#ifdef CONFIG_IDE /* * Only IDE1 exists on the Cayman */ @@ -158,7 +157,6 @@ static int __init smsc_superio_setup(void) SMSC_SUPERIO_WRITE_INDEXED(0x01, 0xc5); /* GP45 = IDE1_IRQ */ SMSC_SUPERIO_WRITE_INDEXED(0x00, 0xc6); /* GP46 = nIOROP */ SMSC_SUPERIO_WRITE_INDEXED(0x00, 0xc7); /* GP47 = nIOWOP */ -#endif /* Exit the configuration state */ outb(SMSC_EXIT_CONFIG_KEY, SMSC_CONFIG_PORT_ADDR); diff --git a/arch/sh/include/asm/pgtable-2level.h b/arch/sh/include/asm/pgtable-2level.h index 19bd89db17e7..f75cf4387257 100644 --- a/arch/sh/include/asm/pgtable-2level.h +++ b/arch/sh/include/asm/pgtable-2level.h @@ -1,6 +1,7 @@ #ifndef __ASM_SH_PGTABLE_2LEVEL_H #define __ASM_SH_PGTABLE_2LEVEL_H +#define __ARCH_USE_5LEVEL_HACK #include <asm-generic/pgtable-nopmd.h> /* diff --git a/arch/sh/include/asm/pgtable-3level.h b/arch/sh/include/asm/pgtable-3level.h index 249a985d9648..9b1e776eca31 100644 --- a/arch/sh/include/asm/pgtable-3level.h +++ b/arch/sh/include/asm/pgtable-3level.h @@ -1,6 +1,7 @@ #ifndef __ASM_SH_PGTABLE_3LEVEL_H #define __ASM_SH_PGTABLE_3LEVEL_H +#define __ARCH_USE_5LEVEL_HACK #include <asm-generic/pgtable-nopud.h> /* diff --git a/arch/sparc/include/asm/pgtable_64.h b/arch/sparc/include/asm/pgtable_64.h index 56e49c8f770d..8a598528ec1f 100644 --- a/arch/sparc/include/asm/pgtable_64.h +++ b/arch/sparc/include/asm/pgtable_64.h @@ -12,6 +12,7 @@ * the SpitFire page tables. */ +#include <asm-generic/5level-fixup.h> #include <linux/compiler.h> #include <linux/const.h> #include <asm/types.h> diff --git a/arch/tile/include/asm/pgtable_32.h b/arch/tile/include/asm/pgtable_32.h index d26a42279036..5f8c615cb5e9 100644 --- a/arch/tile/include/asm/pgtable_32.h +++ b/arch/tile/include/asm/pgtable_32.h @@ -74,6 +74,7 @@ extern unsigned long VMALLOC_RESERVE /* = CONFIG_VMALLOC_RESERVE */; #define MAXMEM (_VMALLOC_START - PAGE_OFFSET) /* We have no pmd or pud since we are strictly a two-level page table */ +#define __ARCH_USE_5LEVEL_HACK #include <asm-generic/pgtable-nopmd.h> static inline int pud_huge_page(pud_t pud) { return 0; } diff --git a/arch/tile/include/asm/pgtable_64.h b/arch/tile/include/asm/pgtable_64.h index e96cec52f6d8..96fe58b45118 100644 --- a/arch/tile/include/asm/pgtable_64.h +++ b/arch/tile/include/asm/pgtable_64.h @@ -59,6 +59,7 @@ #ifndef __ASSEMBLY__ /* We have no pud since we are a three-level page table. */ +#define __ARCH_USE_5LEVEL_HACK #include <asm-generic/pgtable-nopud.h> /* diff --git a/arch/um/include/asm/pgtable-2level.h b/arch/um/include/asm/pgtable-2level.h index cfbe59752469..179c0ea87a0c 100644 --- a/arch/um/include/asm/pgtable-2level.h +++ b/arch/um/include/asm/pgtable-2level.h @@ -8,6 +8,7 @@ #ifndef __UM_PGTABLE_2LEVEL_H #define __UM_PGTABLE_2LEVEL_H +#define __ARCH_USE_5LEVEL_HACK #include <asm-generic/pgtable-nopmd.h> /* PGDIR_SHIFT determines what a third-level page table entry can map */ diff --git a/arch/um/include/asm/pgtable-3level.h b/arch/um/include/asm/pgtable-3level.h index bae8523a162f..c4d876dfb9ac 100644 --- a/arch/um/include/asm/pgtable-3level.h +++ b/arch/um/include/asm/pgtable-3level.h @@ -7,6 +7,7 @@ #ifndef __UM_PGTABLE_3LEVEL_H #define __UM_PGTABLE_3LEVEL_H +#define __ARCH_USE_5LEVEL_HACK #include <asm-generic/pgtable-nopud.h> /* PGDIR_SHIFT determines what a third-level page table entry can map */ diff --git a/arch/unicore32/include/asm/pgtable.h b/arch/unicore32/include/asm/pgtable.h index 818d0f5598e3..a4f2bef37e70 100644 --- a/arch/unicore32/include/asm/pgtable.h +++ b/arch/unicore32/include/asm/pgtable.h @@ -12,6 +12,7 @@ #ifndef __UNICORE_PGTABLE_H__ #define __UNICORE_PGTABLE_H__ +#define __ARCH_USE_5LEVEL_HACK #include <asm-generic/pgtable-nopmd.h> #include <asm/cpu-single.h> diff --git a/arch/x86/configs/x86_64_defconfig b/arch/x86/configs/x86_64_defconfig index 7ef4a099defc..6205d3b81e6d 100644 --- a/arch/x86/configs/x86_64_defconfig +++ b/arch/x86/configs/x86_64_defconfig @@ -176,6 +176,7 @@ CONFIG_E1000E=y CONFIG_SKY2=y CONFIG_FORCEDETH=y CONFIG_8139TOO=y +CONFIG_R8169=y CONFIG_FDDI=y CONFIG_INPUT_POLLDEV=y # CONFIG_INPUT_MOUSEDEV_PSAUX is not set diff --git a/arch/x86/events/amd/core.c b/arch/x86/events/amd/core.c index afb222b63cae..c84584bb9402 100644 --- a/arch/x86/events/amd/core.c +++ b/arch/x86/events/amd/core.c @@ -604,7 +604,7 @@ amd_get_event_constraints_f15h(struct cpu_hw_events *cpuc, int idx, return &amd_f15_PMC20; } case AMD_EVENT_NB: - /* moved to perf_event_amd_uncore.c */ + /* moved to uncore.c */ return &emptyconstraint; default: return &emptyconstraint; diff --git a/arch/x86/events/intel/cstate.c b/arch/x86/events/intel/cstate.c index aff4b5b69d40..238ae3248ba5 100644 --- a/arch/x86/events/intel/cstate.c +++ b/arch/x86/events/intel/cstate.c @@ -1,5 +1,5 @@ /* - * perf_event_intel_cstate.c: support cstate residency counters + * Support cstate residency counters * * Copyright (C) 2015, Intel Corp. * Author: Kan Liang ([email protected]) diff --git a/arch/x86/events/intel/rapl.c b/arch/x86/events/intel/rapl.c index 22054ca49026..9d05c7e67f60 100644 --- a/arch/x86/events/intel/rapl.c +++ b/arch/x86/events/intel/rapl.c @@ -1,5 +1,5 @@ /* - * perf_event_intel_rapl.c: support Intel RAPL energy consumption counters + * Support Intel RAPL energy consumption counters * Copyright (C) 2013 Google, Inc., Stephane Eranian * * Intel RAPL interface is specified in the IA-32 Manual Vol3b diff --git a/arch/x86/events/intel/uncore.h b/arch/x86/events/intel/uncore.h index ad986c1e29bc..df5989f27b1b 100644 --- a/arch/x86/events/intel/uncore.h +++ b/arch/x86/events/intel/uncore.h @@ -360,7 +360,7 @@ extern struct list_head pci2phy_map_head; extern struct pci_extra_dev *uncore_extra_pci_dev; extern struct event_constraint uncore_constraint_empty; -/* perf_event_intel_uncore_snb.c */ +/* uncore_snb.c */ int snb_uncore_pci_init(void); int ivb_uncore_pci_init(void); int hsw_uncore_pci_init(void); @@ -371,7 +371,7 @@ void nhm_uncore_cpu_init(void); void skl_uncore_cpu_init(void); int snb_pci2phy_map_init(int devid); -/* perf_event_intel_uncore_snbep.c */ +/* uncore_snbep.c */ int snbep_uncore_pci_init(void); void snbep_uncore_cpu_init(void); int ivbep_uncore_pci_init(void); @@ -385,5 +385,5 @@ void knl_uncore_cpu_init(void); int skx_uncore_pci_init(void); void skx_uncore_cpu_init(void); -/* perf_event_intel_uncore_nhmex.c */ +/* uncore_nhmex.c */ void nhmex_uncore_cpu_init(void); diff --git a/arch/x86/hyperv/hv_init.c b/arch/x86/hyperv/hv_init.c index db64baf0e500..8bef70e7f3cc 100644 --- a/arch/x86/hyperv/hv_init.c +++ b/arch/x86/hyperv/hv_init.c @@ -158,13 +158,13 @@ void hyperv_init(void) clocksource_register_hz(&hyperv_cs_tsc, NSEC_PER_SEC/100); return; } +register_msr_cs: #endif /* * For 32 bit guests just use the MSR based mechanism for reading * the partition counter. */ -register_msr_cs: hyperv_cs = &hyperv_cs_msr; if (ms_hyperv.features & HV_X64_MSR_TIME_REF_COUNT_AVAILABLE) clocksource_register_hz(&hyperv_cs_msr, NSEC_PER_SEC/100); diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index 4e7772387c6e..b04bb6dfed7f 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -289,7 +289,8 @@ #define X86_FEATURE_PKU (16*32+ 3) /* Protection Keys for Userspace */ #define X86_FEATURE_OSPKE (16*32+ 4) /* OS Protection Keys Enable */ #define X86_FEATURE_AVX512_VPOPCNTDQ (16*32+14) /* POPCNT for vectors of DW/QW */ -#define X86_FEATURE_RDPID (16*32+ 22) /* RDPID instruction */ +#define X86_FEATURE_LA57 (16*32+16) /* 5-level page tables */ +#define X86_FEATURE_RDPID (16*32+22) /* RDPID instruction */ /* AMD-defined CPU features, CPUID level 0x80000007 (ebx), word 17 */ #define X86_FEATURE_OVERFLOW_RECOV (17*32+0) /* MCA overflow recovery support */ diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h index 8b4de22d6429..62484333673d 100644 --- a/arch/x86/include/asm/pgtable_types.h +++ b/arch/x86/include/asm/pgtable_types.h @@ -273,6 +273,8 @@ static inline pgdval_t pgd_flags(pgd_t pgd) } #if CONFIG_PGTABLE_LEVELS > 3 +#include <asm-generic/5level-fixup.h> + typedef struct { pudval_t pud; } pud_t; static inline pud_t native_make_pud(pmdval_t val) @@ -285,6 +287,7 @@ static inline pudval_t native_pud_val(pud_t pud) return pud.pud; } #else +#define __ARCH_USE_5LEVEL_HACK #include <asm-generic/pgtable-nopud.h> static inline pudval_t native_pud_val(pud_t pud) @@ -306,6 +309,7 @@ static inline pmdval_t native_pmd_val(pmd_t pmd) return pmd.pmd; } #else +#define __ARCH_USE_5LEVEL_HACK #include <asm-generic/pgtable-nopmd.h> static inline pmdval_t native_pmd_val(pmd_t pmd) diff --git a/arch/x86/include/asm/pkeys.h b/arch/x86/include/asm/pkeys.h index 34684adb6899..b3b09b98896d 100644 --- a/arch/x86/include/asm/pkeys.h +++ b/arch/x86/include/asm/pkeys.h @@ -46,6 +46,15 @@ extern int __arch_set_user_pkey_access(struct task_struct *tsk, int pkey, static inline bool mm_pkey_is_allocated(struct mm_struct *mm, int pkey) { + /* + * "Allocated" pkeys are those that have been returned + * from pkey_alloc(). pkey 0 is special, and never + * returned from pkey_alloc(). + */ + if (pkey <= 0) + return false; + if (pkey >= arch_max_pkey()) + return false; return mm_pkey_allocation_map(mm) & (1U << pkey); } @@ -82,12 +91,6 @@ int mm_pkey_alloc(struct mm_struct *mm) static inline int mm_pkey_free(struct mm_struct *mm, int pkey) { - /* - * pkey 0 is special, always allocated and can never - * be freed. - */ - if (!pkey) - return -EINVAL; if (!mm_pkey_is_allocated(mm, pkey)) return -EINVAL; diff --git a/arch/x86/include/asm/purgatory.h b/arch/x86/include/asm/purgatory.h new file mode 100644 index 000000000000..d7da2729903d --- /dev/null +++ b/arch/x86/include/asm/purgatory.h @@ -0,0 +1,20 @@ +#ifndef _ASM_X86_PURGATORY_H +#define _ASM_X86_PURGATORY_H + +#ifndef __ASSEMBLY__ +#include <linux/purgatory.h> + +extern void purgatory(void); +/* + * These forward declarations serve two purposes: + * + * 1) Make sparse happy when checking arch/purgatory + * 2) Document that these are required to be global so the symbol + * lookup in kexec works + */ +extern unsigned long purgatory_backup_dest; +extern unsigned long purgatory_backup_src; +extern unsigned long purgatory_backup_sz; +#endif /* __ASSEMBLY__ */ + +#endif /* _ASM_PURGATORY_H */ diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h index 6fa85944af83..fc5abff9b7fd 100644 --- a/arch/x86/include/asm/tlbflush.h +++ b/arch/x86/include/asm/tlbflush.h @@ -188,7 +188,7 @@ static inline void __native_flush_tlb_single(unsigned long addr) static inline void __flush_tlb_all(void) { - if (static_cpu_has(X86_FEATURE_PGE)) + if (boot_cpu_has(X86_FEATURE_PGE)) __flush_tlb_global(); else __flush_tlb(); diff --git a/arch/x86/include/uapi/asm/bootparam.h b/arch/x86/include/uapi/asm/bootparam.h index 5138dacf8bb8..07244ea16765 100644 --- a/arch/x86/include/uapi/asm/bootparam.h +++ b/arch/x86/include/uapi/asm/bootparam.h @@ -58,7 +58,7 @@ struct setup_header { __u32 header; __u16 version; __u32 realmode_swtch; - __u16 start_sys; + __u16 start_sys_seg; __u16 kernel_version; __u8 type_of_loader; __u8 loadflags; diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index 4261b3282ad9..aee7deddabd0 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -1610,24 +1610,15 @@ static inline void try_to_enable_x2apic(int remap_mode) { } static inline void __x2apic_enable(void) { } #endif /* !CONFIG_X86_X2APIC */ -static int __init try_to_enable_IR(void) -{ -#ifdef CONFIG_X86_IO_APIC - if (!x2apic_enabled() && skip_ioapic_setup) { - pr_info("Not enabling interrupt remapping due to skipped IO-APIC setup\n"); - return -1; - } -#endif - return irq_remapping_enable(); -} - void __init enable_IR_x2apic(void) { unsigned long flags; int ret, ir_stat; - if (skip_ioapic_setup) + if (skip_ioapic_setup) { + pr_info("Not enabling interrupt remapping due to skipped IO-APIC setup\n"); return; + } ir_stat = irq_remapping_prepare(); if (ir_stat < 0 && !x2apic_supported()) @@ -1645,7 +1636,7 @@ void __init enable_IR_x2apic(void) /* If irq_remapping_prepare() succeeded, try to enable it */ if (ir_stat >= 0) - ir_stat = try_to_enable_IR(); + ir_stat = irq_remapping_enable(); /* ir_stat contains the remap mode or an error code */ try_to_enable_x2apic(ir_stat); @@ -2062,10 +2053,10 @@ static int allocate_logical_cpuid(int apicid) /* Allocate a new cpuid. */ if (nr_logical_cpuids >= nr_cpu_ids) { - WARN_ONCE(1, "Only %d processors supported." + WARN_ONCE(1, "APIC: NR_CPUS/possible_cpus limit of %i reached. " "Processor %d/0x%x and the rest are ignored.\n", - nr_cpu_ids - 1, nr_logical_cpuids, apicid); - return -1; + nr_cpu_ids, nr_logical_cpuids, apicid); + return -EINVAL; } cpuid_to_apicid[nr_logical_cpuids] = apicid; diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index 35a5d5dca2fa..c36140d788fe 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -556,10 +556,6 @@ static void early_init_amd(struct cpuinfo_x86 *c) if (c->x86_power & (1 << 8)) { set_cpu_cap(c, X86_FEATURE_CONSTANT_TSC); set_cpu_cap(c, X86_FEATURE_NONSTOP_TSC); - if (check_tsc_unstable()) - clear_sched_clock_stable(); - } else { - clear_sched_clock_stable(); } /* Bit 12 of 8000_0007 edx is accumulated power mechanism. */ diff --git a/arch/x86/kernel/cpu/centaur.c b/arch/x86/kernel/cpu/centaur.c index adc0ebd8bed0..43955ee6715b 100644 --- a/arch/x86/kernel/cpu/centaur.c +++ b/arch/x86/kernel/cpu/centaur.c @@ -105,8 +105,6 @@ static void early_init_centaur(struct cpuinfo_x86 *c) #ifdef CONFIG_X86_64 set_cpu_cap(c, X86_FEATURE_SYSENTER32); #endif - - clear_sched_clock_stable(); } static void init_centaur(struct cpuinfo_x86 *c) diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index b11b38c3b0bd..58094a1f9e9d 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -88,7 +88,6 @@ static void default_init(struct cpuinfo_x86 *c) strcpy(c->x86_model_id, "386"); } #endif - clear_sched_clock_stable(); } static const struct cpu_dev default_cpu = { @@ -1077,8 +1076,6 @@ static void identify_cpu(struct cpuinfo_x86 *c) */ if (this_cpu->c_init) this_cpu->c_init(c); - else - clear_sched_clock_stable(); /* Disable the PN if appropriate */ squash_the_stupid_serial_number(c); diff --git a/arch/x86/kernel/cpu/cyrix.c b/arch/x86/kernel/cpu/cyrix.c index 0a3bc19de017..a70fd61095f8 100644 --- a/arch/x86/kernel/cpu/cyrix.c +++ b/arch/x86/kernel/cpu/cyrix.c @@ -185,7 +185,6 @@ static void early_init_cyrix(struct cpuinfo_x86 *c) set_cpu_cap(c, X86_FEATURE_CYRIX_ARR); break; } - clear_sched_clock_stable(); } static void init_cyrix(struct cpuinfo_x86 *c) diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c index fe0a615a051b..063197771b8d 100644 --- a/arch/x86/kernel/cpu/intel.c +++ b/arch/x86/kernel/cpu/intel.c @@ -162,10 +162,6 @@ static void early_init_intel(struct cpuinfo_x86 *c) if (c->x86_power & (1 << 8)) { set_cpu_cap(c, X86_FEATURE_CONSTANT_TSC); set_cpu_cap(c, X86_FEATURE_NONSTOP_TSC); - if (check_tsc_unstable()) - clear_sched_clock_stable(); - } else { - clear_sched_clock_stable(); } /* Penwell and Cloverview have the TSC which doesn't sleep on S3 */ diff --git a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c index 0bbe0f3a039f..c05509d38b1f 100644 --- a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c +++ b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c @@ -28,7 +28,6 @@ #include <linux/sched/signal.h> #include <linux/sched/task.h> #include <linux/slab.h> -#include <linux/cpu.h> #include <linux/task_work.h> #include <uapi/linux/magic.h> diff --git a/arch/x86/kernel/cpu/transmeta.c b/arch/x86/kernel/cpu/transmeta.c index 8457b4978668..d77d07ab310b 100644 --- a/arch/x86/kernel/cpu/transmeta.c +++ b/arch/x86/kernel/cpu/transmeta.c @@ -16,8 +16,6 @@ static void early_init_transmeta(struct cpuinfo_x86 *c) if (xlvl >= 0x80860001) c->x86_capability[CPUID_8086_0001_EDX] = cpuid_edx(0x80860001); } - - clear_sched_clock_stable(); } static void init_transmeta(struct cpuinfo_x86 *c) diff --git a/arch/x86/kernel/cpu/vmware.c b/arch/x86/kernel/cpu/vmware.c index 891f4dad7b2c..22403a28caf5 100644 --- a/arch/x86/kernel/cpu/vmware.c +++ b/arch/x86/kernel/cpu/vmware.c @@ -30,7 +30,6 @@ #include <asm/hypervisor.h> #include <asm/timer.h> #include <asm/apic.h> -#include <asm/timer.h> #undef pr_fmt #define pr_fmt(fmt) "vmware: " fmt diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c index 8639bb2ae058..8f3d9cf26ff9 100644 --- a/arch/x86/kernel/ftrace.c +++ b/arch/x86/kernel/ftrace.c @@ -535,7 +535,7 @@ static void run_sync(void) { int enable_irqs = irqs_disabled(); - /* We may be called with interrupts disbled (on bootup). */ + /* We may be called with interrupts disabled (on bootup). */ if (enable_irqs) local_irq_enable(); on_each_cpu(do_sync_core, NULL, 1); diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c index dc6ba5bda9fc..89ff7af2de50 100644 --- a/arch/x86/kernel/hpet.c +++ b/arch/x86/kernel/hpet.c @@ -354,7 +354,7 @@ static int hpet_resume(struct clock_event_device *evt, int timer) irq_domain_deactivate_irq(irq_get_irq_data(hdev->irq)); irq_domain_activate_irq(irq_get_irq_data(hdev->irq)); - disable_irq(hdev->irq); + disable_hardirq(hdev->irq); irq_set_affinity(hdev->irq, cpumask_of(hdev->cpu)); enable_irq(hdev->irq); } diff --git a/arch/x86/kernel/kdebugfs.c b/arch/x86/kernel/kdebugfs.c index bdb83e431d89..38b64587b31b 100644 --- a/arch/x86/kernel/kdebugfs.c +++ b/arch/x86/kernel/kdebugfs.c @@ -167,7 +167,7 @@ static int __init boot_params_kdebugfs_init(void) struct dentry *dbp, *version, *data; int error = -ENOMEM; - dbp = debugfs_create_dir("boot_params", NULL); + dbp = debugfs_create_dir("boot_params", arch_debugfs_dir); if (!dbp) return -ENOMEM; diff --git a/arch/x86/kernel/kprobes/common.h b/arch/x86/kernel/kprobes/common.h index c6ee63f927ab..d688826e5736 100644 --- a/arch/x86/kernel/kprobes/common.h +++ b/arch/x86/kernel/kprobes/common.h @@ -67,7 +67,7 @@ #endif /* Ensure if the instruction can be boostable */ -extern int can_boost(kprobe_opcode_t *instruction); +extern int can_boost(kprobe_opcode_t *instruction, void *addr); /* Recover instruction if given address is probed */ extern unsigned long recover_probed_instruction(kprobe_opcode_t *buf, unsigned long addr); diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c index 6384eb754a58..993fa4fe4f68 100644 --- a/arch/x86/kernel/kprobes/core.c +++ b/arch/x86/kernel/kprobes/core.c @@ -167,12 +167,12 @@ NOKPROBE_SYMBOL(skip_prefixes); * Returns non-zero if opcode is boostable. * RIP relative instructions are adjusted at copying time in 64 bits mode */ -int can_boost(kprobe_opcode_t *opcodes) +int can_boost(kprobe_opcode_t *opcodes, void *addr) { kprobe_opcode_t opcode; kprobe_opcode_t *orig_opcodes = opcodes; - if (search_exception_tables((unsigned long)opcodes)) + if (search_exception_tables((unsigned long)addr)) return 0; /* Page fault may occur on this address. */ retry: @@ -417,7 +417,7 @@ static int arch_copy_kprobe(struct kprobe *p) * __copy_instruction can modify the displacement of the instruction, * but it doesn't affect boostable check. */ - if (can_boost(p->ainsn.insn)) + if (can_boost(p->ainsn.insn, p->addr)) p->ainsn.boostable = 0; else p->ainsn.boostable = -1; diff --git a/arch/x86/kernel/kprobes/opt.c b/arch/x86/kernel/kprobes/opt.c index 3d1bee9d6a72..3e7c6e5a08ff 100644 --- a/arch/x86/kernel/kprobes/opt.c +++ b/arch/x86/kernel/kprobes/opt.c @@ -178,7 +178,7 @@ static int copy_optimized_instructions(u8 *dest, u8 *src) while (len < RELATIVEJUMP_SIZE) { ret = __copy_instruction(dest + len, src + len); - if (!ret || !can_boost(dest + len)) + if (!ret || !can_boost(dest + len, src + len)) return -EINVAL; len += ret; } diff --git a/arch/x86/kernel/machine_kexec_64.c b/arch/x86/kernel/machine_kexec_64.c index 307b1f4543de..857cdbd02867 100644 --- a/arch/x86/kernel/machine_kexec_64.c +++ b/arch/x86/kernel/machine_kexec_64.c @@ -194,19 +194,22 @@ static int arch_update_purgatory(struct kimage *image) /* Setup copying of backup region */ if (image->type == KEXEC_TYPE_CRASH) { - ret = kexec_purgatory_get_set_symbol(image, "backup_dest", + ret = kexec_purgatory_get_set_symbol(image, + "purgatory_backup_dest", &image->arch.backup_load_addr, sizeof(image->arch.backup_load_addr), 0); if (ret) return ret; - ret = kexec_purgatory_get_set_symbol(image, "backup_src", + ret = kexec_purgatory_get_set_symbol(image, + "purgatory_backup_src", &image->arch.backup_src_start, sizeof(image->arch.backup_src_start), 0); if (ret) return ret; - ret = kexec_purgatory_get_set_symbol(image, "backup_sz", + ret = kexec_purgatory_get_set_symbol(image, + "purgatory_backup_sz", &image->arch.backup_src_sz, sizeof(image->arch.backup_src_sz), 0); if (ret) diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c index e244c19a2451..067f9813fd2c 100644 --- a/arch/x86/kernel/reboot.c +++ b/arch/x86/kernel/reboot.c @@ -223,6 +223,22 @@ static struct dmi_system_id __initdata reboot_dmi_table[] = { DMI_MATCH(DMI_BOARD_NAME, "P4S800"), }, }, + { /* Handle problems with rebooting on ASUS EeeBook X205TA */ + .callback = set_acpi_reboot, + .ident = "ASUS EeeBook X205TA", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."), + DMI_MATCH(DMI_PRODUCT_NAME, "X205TA"), + }, + }, + { /* Handle problems with rebooting on ASUS EeeBook X205TAW */ + .callback = set_acpi_reboot, + .ident = "ASUS EeeBook X205TAW", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."), + DMI_MATCH(DMI_PRODUCT_NAME, "X205TAW"), + }, + }, /* Certec */ { /* Handle problems with rebooting on Certec BPC600 */ diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c index 46bcda4cb1c2..4f7a9833d8e5 100644 --- a/arch/x86/kernel/tsc.c +++ b/arch/x86/kernel/tsc.c @@ -327,9 +327,16 @@ unsigned long long sched_clock(void) { return paravirt_sched_clock(); } + +static inline bool using_native_sched_clock(void) +{ + return pv_time_ops.sched_clock == native_sched_clock; +} #else unsigned long long sched_clock(void) __attribute__((alias("native_sched_clock"))); + +static inline bool using_native_sched_clock(void) { return true; } #endif int check_tsc_unstable(void) @@ -1112,8 +1119,10 @@ static void tsc_cs_mark_unstable(struct clocksource *cs) { if (tsc_unstable) return; + tsc_unstable = 1; - clear_sched_clock_stable(); + if (using_native_sched_clock()) + clear_sched_clock_stable(); disable_sched_clock_irqtime(); pr_info("Marking TSC unstable due to clocksource watchdog\n"); } @@ -1135,18 +1144,20 @@ static struct clocksource clocksource_tsc = { void mark_tsc_unstable(char *reason) { - if (!tsc_unstable) { - tsc_unstable = 1; + if (tsc_unstable) + return; + + tsc_unstable = 1; + if (using_native_sched_clock()) clear_sched_clock_stable(); - disable_sched_clock_irqtime(); - pr_info("Marking TSC unstable due to %s\n", reason); - /* Change only the rating, when not registered */ - if (clocksource_tsc.mult) - clocksource_mark_unstable(&clocksource_tsc); - else { - clocksource_tsc.flags |= CLOCK_SOURCE_UNSTABLE; - clocksource_tsc.rating = 0; - } + disable_sched_clock_irqtime(); + pr_info("Marking TSC unstable due to %s\n", reason); + /* Change only the rating, when not registered */ + if (clocksource_tsc.mult) { + clocksource_mark_unstable(&clocksource_tsc); + } else { + clocksource_tsc.flags |= CLOCK_SOURCE_UNSTABLE; + clocksource_tsc.rating = 0; } } diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 283aa8601833..98e82ee1e699 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -7258,9 +7258,8 @@ static int handle_vmoff(struct kvm_vcpu *vcpu) static int handle_vmclear(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); + u32 zero = 0; gpa_t vmptr; - struct vmcs12 *vmcs12; - struct page *page; if (!nested_vmx_check_permission(vcpu)) return 1; @@ -7271,22 +7270,9 @@ static int handle_vmclear(struct kvm_vcpu *vcpu) if (vmptr == vmx->nested.current_vmptr) nested_release_vmcs12(vmx); - page = nested_get_page(vcpu, vmptr); - if (page == NULL) { - /* - * For accurate processor emulation, VMCLEAR beyond available - * physical memory should do nothing at all. However, it is - * possible that a nested vmx bug, not a guest hypervisor bug, - * resulted in this case, so let's shut down before doing any - * more damage: - */ - kvm_make_request(KVM_REQ_TRIPLE_FAULT, vcpu); - return 1; - } - vmcs12 = kmap(page); - vmcs12->launch_state = 0; - kunmap(page); - nested_release_page(page); + kvm_vcpu_write_guest(vcpu, + vmptr + offsetof(struct vmcs12, launch_state), + &zero, sizeof(zero)); nested_free_vmcs02(vmx, vmptr); @@ -9694,10 +9680,8 @@ static inline bool nested_vmx_merge_msr_bitmap(struct kvm_vcpu *vcpu, return false; page = nested_get_page(vcpu, vmcs12->msr_bitmap); - if (!page) { - WARN_ON(1); + if (!page) return false; - } msr_bitmap_l1 = (unsigned long *)kmap(page); memset(msr_bitmap_l0, 0xff, PAGE_SIZE); @@ -11121,8 +11105,10 @@ static void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 exit_reason, */ static void vmx_leave_nested(struct kvm_vcpu *vcpu) { - if (is_guest_mode(vcpu)) + if (is_guest_mode(vcpu)) { + to_vmx(vcpu)->nested.nested_run_pending = 0; nested_vmx_vmexit(vcpu, -1, 0, 0); + } free_nested(to_vmx(vcpu)); } diff --git a/arch/x86/mm/gup.c b/arch/x86/mm/gup.c index 99c7805a9693..1f3b6ef105cd 100644 --- a/arch/x86/mm/gup.c +++ b/arch/x86/mm/gup.c @@ -106,32 +106,35 @@ static noinline int gup_pte_range(pmd_t pmd, unsigned long addr, unsigned long end, int write, struct page **pages, int *nr) { struct dev_pagemap *pgmap = NULL; - int nr_start = *nr; - pte_t *ptep; + int nr_start = *nr, ret = 0; + pte_t *ptep, *ptem; - ptep = pte_offset_map(&pmd, addr); + /* + * Keep the original mapped PTE value (ptem) around since we + * might increment ptep off the end of the page when finishing + * our loop iteration. + */ + ptem = ptep = pte_offset_map(&pmd, addr); do { pte_t pte = gup_get_pte(ptep); struct page *page; /* Similar to the PMD case, NUMA hinting must take slow path */ - if (pte_protnone(pte)) { - pte_unmap(ptep); - return 0; - } + if (pte_protnone(pte)) + break; + + if (!pte_allows_gup(pte_val(pte), write)) + break; if (pte_devmap(pte)) { pgmap = get_dev_pagemap(pte_pfn(pte), pgmap); if (unlikely(!pgmap)) { undo_dev_pagemap(nr, nr_start, pages); - pte_unmap(ptep); - return 0; + break; } - } else if (!pte_allows_gup(pte_val(pte), write) || - pte_special(pte)) { - pte_unmap(ptep); - return 0; - } + } else if (pte_special(pte)) + break; + VM_BUG_ON(!pfn_valid(pte_pfn(pte))); page = pte_page(pte); get_page(page); @@ -141,9 +144,11 @@ static noinline int gup_pte_range(pmd_t pmd, unsigned long addr, (*nr)++; } while (ptep++, addr += PAGE_SIZE, addr != end); - pte_unmap(ptep - 1); + if (addr == end) + ret = 1; + pte_unmap(ptem); - return 1; + return ret; } static inline void get_head_page_multiple(struct page *page, int nr) diff --git a/arch/x86/pci/common.c b/arch/x86/pci/common.c index 0cb52ae0a8f0..190e718694b1 100644 --- a/arch/x86/pci/common.c +++ b/arch/x86/pci/common.c @@ -735,6 +735,15 @@ void pcibios_disable_device (struct pci_dev *dev) pcibios_disable_irq(dev); } +#ifdef CONFIG_ACPI_HOTPLUG_IOAPIC +void pcibios_release_device(struct pci_dev *dev) +{ + if (atomic_dec_return(&dev->enable_cnt) >= 0) + pcibios_disable_device(dev); + +} +#endif + int pci_ext_cfg_avail(void) { if (raw_pci_ext_ops) diff --git a/arch/x86/pci/xen.c b/arch/x86/pci/xen.c index e1fb269c87af..292ab0364a89 100644 --- a/arch/x86/pci/xen.c +++ b/arch/x86/pci/xen.c @@ -234,23 +234,14 @@ static int xen_hvm_setup_msi_irqs(struct pci_dev *dev, int nvec, int type) return 1; for_each_pci_msi_entry(msidesc, dev) { - __pci_read_msi_msg(msidesc, &msg); - pirq = MSI_ADDR_EXT_DEST_ID(msg.address_hi) | - ((msg.address_lo >> MSI_ADDR_DEST_ID_SHIFT) & 0xff); - if (msg.data != XEN_PIRQ_MSI_DATA || - xen_irq_from_pirq(pirq) < 0) { - pirq = xen_allocate_pirq_msi(dev, msidesc); - if (pirq < 0) { - irq = -ENODEV; - goto error; - } - xen_msi_compose_msg(dev, pirq, &msg); - __pci_write_msi_msg(msidesc, &msg); - dev_dbg(&dev->dev, "xen: msi bound to pirq=%d\n", pirq); - } else { - dev_dbg(&dev->dev, - "xen: msi already bound to pirq=%d\n", pirq); + pirq = xen_allocate_pirq_msi(dev, msidesc); + if (pirq < 0) { + irq = -ENODEV; + goto error; } + xen_msi_compose_msg(dev, pirq, &msg); + __pci_write_msi_msg(msidesc, &msg); + dev_dbg(&dev->dev, "xen: msi bound to pirq=%d\n", pirq); irq = xen_bind_pirq_msi_to_irq(dev, msidesc, pirq, (type == PCI_CAP_ID_MSI) ? nvec : 1, (type == PCI_CAP_ID_MSIX) ? diff --git a/arch/x86/platform/uv/tlb_uv.c b/arch/x86/platform/uv/tlb_uv.c index 766d4d3529a1..f25982cdff90 100644 --- a/arch/x86/platform/uv/tlb_uv.c +++ b/arch/x86/platform/uv/tlb_uv.c @@ -1847,7 +1847,6 @@ static void pq_init(int node, int pnode) ops.write_payload_first(pnode, first); ops.write_payload_last(pnode, last); - ops.write_g_sw_ack(pnode, 0xffffUL); /* in effect, all msg_type's are set to MSG_NOOP */ memset(pqp, 0, sizeof(struct bau_pq_entry) * DEST_Q_SIZE); diff --git a/arch/x86/purgatory/purgatory.c b/arch/x86/purgatory/purgatory.c index 25e068ba3382..470edad96bb9 100644 --- a/arch/x86/purgatory/purgatory.c +++ b/arch/x86/purgatory/purgatory.c @@ -10,21 +10,19 @@ * Version 2. See the file COPYING for more details. */ +#include <linux/bug.h> +#include <asm/purgatory.h> + #include "sha256.h" #include "../boot/string.h" -struct sha_region { - unsigned long start; - unsigned long len; -}; - -unsigned long backup_dest = 0; -unsigned long backup_src = 0; -unsigned long backup_sz = 0; +unsigned long purgatory_backup_dest __section(.kexec-purgatory); +unsigned long purgatory_backup_src __section(.kexec-purgatory); +unsigned long purgatory_backup_sz __section(.kexec-purgatory); -u8 sha256_digest[SHA256_DIGEST_SIZE] = { 0 }; +u8 purgatory_sha256_digest[SHA256_DIGEST_SIZE] __section(.kexec-purgatory); -struct sha_region sha_regions[16] = {}; +struct kexec_sha_region purgatory_sha_regions[KEXEC_SEGMENT_MAX] __section(.kexec-purgatory); /* * On x86, second kernel requries first 640K of memory to boot. Copy @@ -33,26 +31,28 @@ struct sha_region sha_regions[16] = {}; */ static int copy_backup_region(void) { - if (backup_dest) - memcpy((void *)backup_dest, (void *)backup_src, backup_sz); - + if (purgatory_backup_dest) { + memcpy((void *)purgatory_backup_dest, + (void *)purgatory_backup_src, purgatory_backup_sz); + } return 0; } -int verify_sha256_digest(void) +static int verify_sha256_digest(void) { - struct sha_region *ptr, *end; + struct kexec_sha_region *ptr, *end; u8 digest[SHA256_DIGEST_SIZE]; struct sha256_state sctx; sha256_init(&sctx); - end = &sha_regions[sizeof(sha_regions)/sizeof(sha_regions[0])]; - for (ptr = sha_regions; ptr < end; ptr++) + end = purgatory_sha_regions + ARRAY_SIZE(purgatory_sha_regions); + + for (ptr = purgatory_sha_regions; ptr < end; ptr++) sha256_update(&sctx, (uint8_t *)(ptr->start), ptr->len); sha256_final(&sctx, digest); - if (memcmp(digest, sha256_digest, sizeof(digest))) + if (memcmp(digest, purgatory_sha256_digest, sizeof(digest))) return 1; return 0; diff --git a/arch/x86/purgatory/setup-x86_64.S b/arch/x86/purgatory/setup-x86_64.S index fe3c91ba1bd0..dfae9b9e60b5 100644 --- a/arch/x86/purgatory/setup-x86_64.S +++ b/arch/x86/purgatory/setup-x86_64.S @@ -9,6 +9,7 @@ * This source code is licensed under the GNU General Public License, * Version 2. See the file COPYING for more details. */ +#include <asm/purgatory.h> .text .globl purgatory_start diff --git a/arch/x86/purgatory/sha256.h b/arch/x86/purgatory/sha256.h index bd15a4127735..2867d9825a57 100644 --- a/arch/x86/purgatory/sha256.h +++ b/arch/x86/purgatory/sha256.h @@ -10,7 +10,6 @@ #ifndef SHA256_H #define SHA256_H - #include <linux/types.h> #include <crypto/sha.h> diff --git a/arch/xtensa/include/asm/pgtable.h b/arch/xtensa/include/asm/pgtable.h index 8aa0e0d9cbb2..30dd5b2e4ad5 100644 --- a/arch/xtensa/include/asm/pgtable.h +++ b/arch/xtensa/include/asm/pgtable.h @@ -11,6 +11,7 @@ #ifndef _XTENSA_PGTABLE_H #define _XTENSA_PGTABLE_H +#define __ARCH_USE_5LEVEL_HACK #include <asm-generic/pgtable-nopmd.h> #include <asm/page.h> #include <asm/kmem_layout.h> diff --git a/block/blk-core.c b/block/blk-core.c index 1086dac8724c..0eeb99ef654f 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -578,8 +578,6 @@ void blk_cleanup_queue(struct request_queue *q) q->queue_lock = &q->__queue_lock; spin_unlock_irq(lock); - put_disk_devt(q->disk_devt); - /* @q is and will stay empty, shutdown and put */ blk_put_queue(q); } @@ -2017,17 +2015,34 @@ blk_qc_t generic_make_request(struct bio *bio) struct request_queue *q = bdev_get_queue(bio->bi_bdev); if (likely(blk_queue_enter(q, false) == 0)) { + struct bio_list hold; + struct bio_list lower, same; + + /* Create a fresh bio_list for all subordinate requests */ + hold = bio_list_on_stack; + bio_list_init(&bio_list_on_stack); ret = q->make_request_fn(q, bio); blk_queue_exit(q); - bio = bio_list_pop(current->bio_list); + /* sort new bios into those for a lower level + * and those for the same level + */ + bio_list_init(&lower); + bio_list_init(&same); + while ((bio = bio_list_pop(&bio_list_on_stack)) != NULL) + if (q == bdev_get_queue(bio->bi_bdev)) + bio_list_add(&same, bio); + else + bio_list_add(&lower, bio); + /* now assemble so we handle the lowest level first */ + bio_list_merge(&bio_list_on_stack, &lower); + bio_list_merge(&bio_list_on_stack, &same); + bio_list_merge(&bio_list_on_stack, &hold); } else { - struct bio *bio_next = bio_list_pop(current->bio_list); - bio_io_error(bio); - bio = bio_next; } + bio = bio_list_pop(current->bio_list); } while (bio); current->bio_list = NULL; /* deactivate */ diff --git a/block/blk-mq-sysfs.c b/block/blk-mq-sysfs.c index 295e69670c39..d745ab81033a 100644 --- a/block/blk-mq-sysfs.c +++ b/block/blk-mq-sysfs.c @@ -17,6 +17,15 @@ static void blk_mq_sysfs_release(struct kobject *kobj) { } +static void blk_mq_hw_sysfs_release(struct kobject *kobj) +{ + struct blk_mq_hw_ctx *hctx = container_of(kobj, struct blk_mq_hw_ctx, + kobj); + free_cpumask_var(hctx->cpumask); + kfree(hctx->ctxs); + kfree(hctx); +} + struct blk_mq_ctx_sysfs_entry { struct attribute attr; ssize_t (*show)(struct blk_mq_ctx *, char *); @@ -200,7 +209,7 @@ static struct kobj_type blk_mq_ctx_ktype = { static struct kobj_type blk_mq_hw_ktype = { .sysfs_ops = &blk_mq_hw_sysfs_ops, .default_attrs = default_hw_ctx_attrs, - .release = blk_mq_sysfs_release, + .release = blk_mq_hw_sysfs_release, }; static void blk_mq_unregister_hctx(struct blk_mq_hw_ctx *hctx) @@ -242,24 +251,15 @@ static int blk_mq_register_hctx(struct blk_mq_hw_ctx *hctx) static void __blk_mq_unregister_dev(struct device *dev, struct request_queue *q) { struct blk_mq_hw_ctx *hctx; - struct blk_mq_ctx *ctx; - int i, j; + int i; - queue_for_each_hw_ctx(q, hctx, i) { + queue_for_each_hw_ctx(q, hctx, i) blk_mq_unregister_hctx(hctx); - hctx_for_each_ctx(hctx, ctx, j) - kobject_put(&ctx->kobj); - - kobject_put(&hctx->kobj); - } - blk_mq_debugfs_unregister_hctxs(q); kobject_uevent(&q->mq_kobj, KOBJ_REMOVE); kobject_del(&q->mq_kobj); - kobject_put(&q->mq_kobj); - kobject_put(&dev->kobj); q->mq_sysfs_init_done = false; @@ -277,7 +277,19 @@ void blk_mq_hctx_kobj_init(struct blk_mq_hw_ctx *hctx) kobject_init(&hctx->kobj, &blk_mq_hw_ktype); } -static void blk_mq_sysfs_init(struct request_queue *q) +void blk_mq_sysfs_deinit(struct request_queue *q) +{ + struct blk_mq_ctx *ctx; + int cpu; + + for_each_possible_cpu(cpu) { + ctx = per_cpu_ptr(q->queue_ctx, cpu); + kobject_put(&ctx->kobj); + } + kobject_put(&q->mq_kobj); +} + +void blk_mq_sysfs_init(struct request_queue *q) { struct blk_mq_ctx *ctx; int cpu; @@ -297,8 +309,6 @@ int blk_mq_register_dev(struct device *dev, struct request_queue *q) blk_mq_disable_hotplug(); - blk_mq_sysfs_init(q); - ret = kobject_add(&q->mq_kobj, kobject_get(&dev->kobj), "%s", "mq"); if (ret < 0) goto out; diff --git a/block/blk-mq.c b/block/blk-mq.c index b2fd175e84d7..159187a28d66 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -1955,16 +1955,6 @@ static void blk_mq_exit_hw_queues(struct request_queue *q, } } -static void blk_mq_free_hw_queues(struct request_queue *q, - struct blk_mq_tag_set *set) -{ - struct blk_mq_hw_ctx *hctx; - unsigned int i; - - queue_for_each_hw_ctx(q, hctx, i) - free_cpumask_var(hctx->cpumask); -} - static int blk_mq_init_hctx(struct request_queue *q, struct blk_mq_tag_set *set, struct blk_mq_hw_ctx *hctx, unsigned hctx_idx) @@ -2045,7 +2035,6 @@ static void blk_mq_init_cpu_queues(struct request_queue *q, struct blk_mq_ctx *__ctx = per_cpu_ptr(q->queue_ctx, i); struct blk_mq_hw_ctx *hctx; - memset(__ctx, 0, sizeof(*__ctx)); __ctx->cpu = i; spin_lock_init(&__ctx->lock); INIT_LIST_HEAD(&__ctx->rq_list); @@ -2257,15 +2246,19 @@ void blk_mq_release(struct request_queue *q) queue_for_each_hw_ctx(q, hctx, i) { if (!hctx) continue; - kfree(hctx->ctxs); - kfree(hctx); + kobject_put(&hctx->kobj); } q->mq_map = NULL; kfree(q->queue_hw_ctx); - /* ctx kobj stays in queue_ctx */ + /* + * release .mq_kobj and sw queue's kobject now because + * both share lifetime with request queue. + */ + blk_mq_sysfs_deinit(q); + free_percpu(q->queue_ctx); } @@ -2330,10 +2323,7 @@ static void blk_mq_realloc_hw_ctxs(struct blk_mq_tag_set *set, if (hctx->tags) blk_mq_free_map_and_requests(set, j); blk_mq_exit_hctx(q, set, hctx, j); - free_cpumask_var(hctx->cpumask); kobject_put(&hctx->kobj); - kfree(hctx->ctxs); - kfree(hctx); hctxs[j] = NULL; } @@ -2352,6 +2342,9 @@ struct request_queue *blk_mq_init_allocated_queue(struct blk_mq_tag_set *set, if (!q->queue_ctx) goto err_exit; + /* init q->mq_kobj and sw queues' kobjects */ + blk_mq_sysfs_init(q); + q->queue_hw_ctx = kzalloc_node(nr_cpu_ids * sizeof(*(q->queue_hw_ctx)), GFP_KERNEL, set->numa_node); if (!q->queue_hw_ctx) @@ -2442,7 +2435,6 @@ void blk_mq_free_queue(struct request_queue *q) 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); } /* Basically redo blk_mq_init_queue with queue frozen */ diff --git a/block/blk-mq.h b/block/blk-mq.h index 088ced003c13..b79f9a7d8cf6 100644 --- a/block/blk-mq.h +++ b/block/blk-mq.h @@ -77,6 +77,8 @@ static inline struct blk_mq_hw_ctx *blk_mq_map_queue(struct request_queue *q, /* * sysfs helpers */ +extern void blk_mq_sysfs_init(struct request_queue *q); +extern void blk_mq_sysfs_deinit(struct request_queue *q); extern int blk_mq_sysfs_register(struct request_queue *q); extern void blk_mq_sysfs_unregister(struct request_queue *q); extern void blk_mq_hctx_kobj_init(struct blk_mq_hw_ctx *hctx); diff --git a/block/genhd.c b/block/genhd.c index b26a5ea115d0..a9c516a8b37d 100644 --- a/block/genhd.c +++ b/block/genhd.c @@ -572,20 +572,6 @@ exit: disk_part_iter_exit(&piter); } -void put_disk_devt(struct disk_devt *disk_devt) -{ - if (disk_devt && atomic_dec_and_test(&disk_devt->count)) - disk_devt->release(disk_devt); -} -EXPORT_SYMBOL(put_disk_devt); - -void get_disk_devt(struct disk_devt *disk_devt) -{ - if (disk_devt) - atomic_inc(&disk_devt->count); -} -EXPORT_SYMBOL(get_disk_devt); - /** * device_add_disk - add partitioning information to kernel list * @parent: parent device for the disk @@ -626,13 +612,6 @@ void device_add_disk(struct device *parent, struct gendisk *disk) disk_alloc_events(disk); - /* - * Take a reference on the devt and assign it to queue since it - * must not be reallocated while the bdi is registered - */ - disk->queue->disk_devt = disk->disk_devt; - get_disk_devt(disk->disk_devt); - /* Register BDI before referencing it from bdev */ bdi = disk->queue->backing_dev_info; bdi_register_owner(bdi, disk_to_dev(disk)); @@ -681,12 +660,16 @@ void del_gendisk(struct gendisk *disk) disk->flags &= ~GENHD_FL_UP; sysfs_remove_link(&disk_to_dev(disk)->kobj, "bdi"); - /* - * Unregister bdi before releasing device numbers (as they can get - * reused and we'd get clashes in sysfs). - */ - bdi_unregister(disk->queue->backing_dev_info); - blk_unregister_queue(disk); + if (disk->queue) { + /* + * Unregister bdi before releasing device numbers (as they can + * get reused and we'd get clashes in sysfs). + */ + bdi_unregister(disk->queue->backing_dev_info); + blk_unregister_queue(disk); + } else { + WARN_ON(1); + } blk_unregister_region(disk_devt(disk), disk->minors); part_stat_set_all(&disk->part0, 0); diff --git a/block/sed-opal.c b/block/sed-opal.c index 1e18dca360fc..14035f826b5e 100644 --- a/block/sed-opal.c +++ b/block/sed-opal.c @@ -1023,7 +1023,6 @@ static int finalize_and_send(struct opal_dev *dev, cont_fn cont) static int gen_key(struct opal_dev *dev, void *data) { - const u8 *method; u8 uid[OPAL_UID_LENGTH]; int err = 0; @@ -1031,7 +1030,6 @@ static int gen_key(struct opal_dev *dev, void *data) set_comid(dev, dev->comid); memcpy(uid, dev->prev_data, min(sizeof(uid), dev->prev_d_len)); - method = opalmethod[OPAL_GENKEY]; kfree(dev->prev_data); dev->prev_data = NULL; @@ -1669,7 +1667,6 @@ static int add_user_to_lr(struct opal_dev *dev, void *data) static int lock_unlock_locking_range(struct opal_dev *dev, void *data) { u8 lr_buffer[OPAL_UID_LENGTH]; - const u8 *method; struct opal_lock_unlock *lkul = data; u8 read_locked = 1, write_locked = 1; int err = 0; @@ -1677,7 +1674,6 @@ static int lock_unlock_locking_range(struct opal_dev *dev, void *data) clear_opal_cmd(dev); set_comid(dev, dev->comid); - method = opalmethod[OPAL_SET]; if (build_locking_range(lr_buffer, sizeof(lr_buffer), lkul->session.opal_key.lr) < 0) return -ERANGE; @@ -1733,14 +1729,12 @@ static int lock_unlock_locking_range_sum(struct opal_dev *dev, void *data) { u8 lr_buffer[OPAL_UID_LENGTH]; u8 read_locked = 1, write_locked = 1; - const u8 *method; struct opal_lock_unlock *lkul = data; int ret; clear_opal_cmd(dev); set_comid(dev, dev->comid); - method = opalmethod[OPAL_SET]; if (build_locking_range(lr_buffer, sizeof(lr_buffer), lkul->session.opal_key.lr) < 0) return -ERANGE; @@ -2133,7 +2127,7 @@ static int opal_add_user_to_lr(struct opal_dev *dev, pr_err("Locking state was not RO or RW\n"); return -EINVAL; } - if (lk_unlk->session.who < OPAL_USER1 && + if (lk_unlk->session.who < OPAL_USER1 || lk_unlk->session.who > OPAL_USER9) { pr_err("Authority was not within the range of users: %d\n", lk_unlk->session.who); @@ -2316,7 +2310,7 @@ static int opal_activate_user(struct opal_dev *dev, int ret; /* We can't activate Admin1 it's active as manufactured */ - if (opal_session->who < OPAL_USER1 && + if (opal_session->who < OPAL_USER1 || opal_session->who > OPAL_USER9) { pr_err("Who was not a valid user: %d\n", opal_session->who); return -EINVAL; diff --git a/crypto/af_alg.c b/crypto/af_alg.c index f5e18c2a4852..690deca17c35 100644 --- a/crypto/af_alg.c +++ b/crypto/af_alg.c @@ -266,7 +266,7 @@ unlock: return err; } -int af_alg_accept(struct sock *sk, struct socket *newsock) +int af_alg_accept(struct sock *sk, struct socket *newsock, bool kern) { struct alg_sock *ask = alg_sk(sk); const struct af_alg_type *type; @@ -281,7 +281,7 @@ int af_alg_accept(struct sock *sk, struct socket *newsock) if (!type) goto unlock; - sk2 = sk_alloc(sock_net(sk), PF_ALG, GFP_KERNEL, &alg_proto, 0); + sk2 = sk_alloc(sock_net(sk), PF_ALG, GFP_KERNEL, &alg_proto, kern); err = -ENOMEM; if (!sk2) goto unlock; @@ -323,9 +323,10 @@ unlock: } EXPORT_SYMBOL_GPL(af_alg_accept); -static int alg_accept(struct socket *sock, struct socket *newsock, int flags) +static int alg_accept(struct socket *sock, struct socket *newsock, int flags, + bool kern) { - return af_alg_accept(sock->sk, newsock); + return af_alg_accept(sock->sk, newsock, kern); } static const struct proto_ops alg_proto_ops = { diff --git a/crypto/algif_hash.c b/crypto/algif_hash.c index 54fc90e8339c..5e92bd275ef3 100644 --- a/crypto/algif_hash.c +++ b/crypto/algif_hash.c @@ -239,7 +239,8 @@ unlock: return err ?: len; } -static int hash_accept(struct socket *sock, struct socket *newsock, int flags) +static int hash_accept(struct socket *sock, struct socket *newsock, int flags, + bool kern) { struct sock *sk = sock->sk; struct alg_sock *ask = alg_sk(sk); @@ -260,7 +261,7 @@ static int hash_accept(struct socket *sock, struct socket *newsock, int flags) if (err) return err; - err = af_alg_accept(ask->parent, newsock); + err = af_alg_accept(ask->parent, newsock, kern); if (err) return err; @@ -378,7 +379,7 @@ static int hash_recvmsg_nokey(struct socket *sock, struct msghdr *msg, } static int hash_accept_nokey(struct socket *sock, struct socket *newsock, - int flags) + int flags, bool kern) { int err; @@ -386,7 +387,7 @@ static int hash_accept_nokey(struct socket *sock, struct socket *newsock, if (err) return err; - return hash_accept(sock, newsock, flags); + return hash_accept(sock, newsock, flags, kern); } static struct proto_ops algif_hash_ops_nokey = { diff --git a/drivers/acpi/internal.h b/drivers/acpi/internal.h index 219b90bc0922..f15900132912 100644 --- a/drivers/acpi/internal.h +++ b/drivers/acpi/internal.h @@ -41,8 +41,10 @@ void acpi_gpe_apply_masked_gpes(void); void acpi_container_init(void); void acpi_memory_hotplug_init(void); #ifdef CONFIG_ACPI_HOTPLUG_IOAPIC +void pci_ioapic_remove(struct acpi_pci_root *root); int acpi_ioapic_remove(struct acpi_pci_root *root); #else +static inline void pci_ioapic_remove(struct acpi_pci_root *root) { return; } static inline int acpi_ioapic_remove(struct acpi_pci_root *root) { return 0; } #endif #ifdef CONFIG_ACPI_DOCK diff --git a/drivers/acpi/ioapic.c b/drivers/acpi/ioapic.c index 6d7ce6e12aaa..1120dfd625b8 100644 --- a/drivers/acpi/ioapic.c +++ b/drivers/acpi/ioapic.c @@ -206,24 +206,34 @@ int acpi_ioapic_add(acpi_handle root_handle) return ACPI_SUCCESS(status) && ACPI_SUCCESS(retval) ? 0 : -ENODEV; } -int acpi_ioapic_remove(struct acpi_pci_root *root) +void pci_ioapic_remove(struct acpi_pci_root *root) { - int retval = 0; struct acpi_pci_ioapic *ioapic, *tmp; mutex_lock(&ioapic_list_lock); list_for_each_entry_safe(ioapic, tmp, &ioapic_list, list) { if (root->device->handle != ioapic->root_handle) continue; - - if (acpi_unregister_ioapic(ioapic->handle, ioapic->gsi_base)) - retval = -EBUSY; - if (ioapic->pdev) { pci_release_region(ioapic->pdev, 0); pci_disable_device(ioapic->pdev); pci_dev_put(ioapic->pdev); } + } + mutex_unlock(&ioapic_list_lock); +} + +int acpi_ioapic_remove(struct acpi_pci_root *root) +{ + int retval = 0; + struct acpi_pci_ioapic *ioapic, *tmp; + + mutex_lock(&ioapic_list_lock); + list_for_each_entry_safe(ioapic, tmp, &ioapic_list, list) { + if (root->device->handle != ioapic->root_handle) + continue; + if (acpi_unregister_ioapic(ioapic->handle, ioapic->gsi_base)) + retval = -EBUSY; if (ioapic->res.flags && ioapic->res.parent) release_resource(&ioapic->res); list_del(&ioapic->list); diff --git a/drivers/acpi/pci_root.c b/drivers/acpi/pci_root.c index bf601d4df8cf..919be0aa2578 100644 --- a/drivers/acpi/pci_root.c +++ b/drivers/acpi/pci_root.c @@ -648,12 +648,12 @@ static void acpi_pci_root_remove(struct acpi_device *device) pci_stop_root_bus(root->bus); - WARN_ON(acpi_ioapic_remove(root)); - + pci_ioapic_remove(root); device_set_run_wake(root->bus->bridge, false); pci_acpi_remove_bus_pm_notifier(device); pci_remove_root_bus(root->bus); + WARN_ON(acpi_ioapic_remove(root)); dmar_device_remove(device->handle); diff --git a/drivers/ata/ahci_qoriq.c b/drivers/ata/ahci_qoriq.c index 85d833289f28..4c96f3ac4976 100644 --- a/drivers/ata/ahci_qoriq.c +++ b/drivers/ata/ahci_qoriq.c @@ -177,7 +177,8 @@ static int ahci_qoriq_phy_init(struct ahci_host_priv *hpriv) case AHCI_LS1043A: if (!qpriv->ecc_addr) return -EINVAL; - writel(ECC_DIS_ARMV8_CH2, qpriv->ecc_addr); + writel(readl(qpriv->ecc_addr) | ECC_DIS_ARMV8_CH2, + qpriv->ecc_addr); writel(AHCI_PORT_PHY_1_CFG, reg_base + PORT_PHY1); writel(AHCI_PORT_TRANS_CFG, reg_base + PORT_TRANS); if (qpriv->is_dmacoherent) @@ -194,7 +195,8 @@ static int ahci_qoriq_phy_init(struct ahci_host_priv *hpriv) case AHCI_LS1046A: if (!qpriv->ecc_addr) return -EINVAL; - writel(ECC_DIS_ARMV8_CH2, qpriv->ecc_addr); + writel(readl(qpriv->ecc_addr) | ECC_DIS_ARMV8_CH2, + qpriv->ecc_addr); writel(AHCI_PORT_PHY_1_CFG, reg_base + PORT_PHY1); writel(AHCI_PORT_TRANS_CFG, reg_base + PORT_TRANS); if (qpriv->is_dmacoherent) diff --git a/drivers/ata/libata-sff.c b/drivers/ata/libata-sff.c index 2bd92dca3e62..274d6d7193d7 100644 --- a/drivers/ata/libata-sff.c +++ b/drivers/ata/libata-sff.c @@ -1482,7 +1482,6 @@ unsigned int ata_sff_qc_issue(struct ata_queued_cmd *qc) break; default: - WARN_ON_ONCE(1); return AC_ERR_SYSTEM; } diff --git a/drivers/ata/libata-transport.c b/drivers/ata/libata-transport.c index 46698232e6bf..19e6e539a061 100644 --- a/drivers/ata/libata-transport.c +++ b/drivers/ata/libata-transport.c @@ -224,7 +224,6 @@ static DECLARE_TRANSPORT_CLASS(ata_port_class, static void ata_tport_release(struct device *dev) { - put_device(dev->parent); } /** @@ -284,7 +283,7 @@ int ata_tport_add(struct device *parent, device_initialize(dev); dev->type = &ata_port_type; - dev->parent = get_device(parent); + dev->parent = parent; dev->release = ata_tport_release; dev_set_name(dev, "ata%d", ap->print_id); transport_setup_device(dev); @@ -348,7 +347,6 @@ static DECLARE_TRANSPORT_CLASS(ata_link_class, static void ata_tlink_release(struct device *dev) { - put_device(dev->parent); } /** @@ -410,7 +408,7 @@ int ata_tlink_add(struct ata_link *link) int error; device_initialize(dev); - dev->parent = get_device(&ap->tdev); + dev->parent = &ap->tdev; dev->release = ata_tlink_release; if (ata_is_host_link(link)) dev_set_name(dev, "link%d", ap->print_id); @@ -589,7 +587,6 @@ static DECLARE_TRANSPORT_CLASS(ata_dev_class, static void ata_tdev_release(struct device *dev) { - put_device(dev->parent); } /** @@ -662,7 +659,7 @@ static int ata_tdev_add(struct ata_device *ata_dev) int error; device_initialize(dev); - dev->parent = get_device(&link->tdev); + dev->parent = &link->tdev; dev->release = ata_tdev_release; if (ata_is_host_link(link)) dev_set_name(dev, "dev%d.%d", ap->print_id,ata_dev->devno); diff --git a/drivers/atm/ambassador.c b/drivers/atm/ambassador.c index 4a610795b585..906705e5f776 100644 --- a/drivers/atm/ambassador.c +++ b/drivers/atm/ambassador.c @@ -2267,9 +2267,8 @@ static int amb_probe(struct pci_dev *pci_dev, dev->atm_dev->ci_range.vpi_bits = NUM_VPI_BITS; dev->atm_dev->ci_range.vci_bits = NUM_VCI_BITS; - init_timer(&dev->housekeeping); - dev->housekeeping.function = do_housekeeping; - dev->housekeeping.data = (unsigned long) dev; + setup_timer(&dev->housekeeping, do_housekeeping, + (unsigned long)dev); mod_timer(&dev->housekeeping, jiffies); // enable host interrupts diff --git a/drivers/block/paride/pcd.c b/drivers/block/paride/pcd.c index 10aed84244f5..939641d6e262 100644 --- a/drivers/block/paride/pcd.c +++ b/drivers/block/paride/pcd.c @@ -50,7 +50,7 @@ the slower the port i/o. In some cases, setting this to zero will speed up the device. (default -1) - major You may use this parameter to overide the + major You may use this parameter to override the default major number (46) that this driver will use. Be sure to change the device name as well. diff --git a/drivers/block/paride/pd.c b/drivers/block/paride/pd.c index 644ba0888bd4..9cfd2e06a649 100644 --- a/drivers/block/paride/pd.c +++ b/drivers/block/paride/pd.c @@ -61,7 +61,7 @@ first drive found. - major You may use this parameter to overide the + major You may use this parameter to override the default major number (45) that this driver will use. Be sure to change the device name as well. diff --git a/drivers/block/paride/pf.c b/drivers/block/paride/pf.c index ed93e8badf56..14c5d32f5d8b 100644 --- a/drivers/block/paride/pf.c +++ b/drivers/block/paride/pf.c @@ -59,7 +59,7 @@ the slower the port i/o. In some cases, setting this to zero will speed up the device. (default -1) - major You may use this parameter to overide the + major You may use this parameter to override the default major number (47) that this driver will use. Be sure to change the device name as well. diff --git a/drivers/block/paride/pg.c b/drivers/block/paride/pg.c index 5db955fe3a94..3b5882bfb736 100644 --- a/drivers/block/paride/pg.c +++ b/drivers/block/paride/pg.c @@ -84,7 +84,7 @@ the slower the port i/o. In some cases, setting this to zero will speed up the device. (default -1) - major You may use this parameter to overide the + major You may use this parameter to override the default major number (97) that this driver will use. Be sure to change the device name as well. diff --git a/drivers/block/paride/pt.c b/drivers/block/paride/pt.c index 61fc6824299a..e815312a00ad 100644 --- a/drivers/block/paride/pt.c +++ b/drivers/block/paride/pt.c @@ -61,7 +61,7 @@ the slower the port i/o. In some cases, setting this to zero will speed up the device. (default -1) - major You may use this parameter to overide the + major You may use this parameter to override the default major number (96) that this driver will use. Be sure to change the device name as well. diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c index 4d6807723798..517838b65964 100644 --- a/drivers/block/rbd.c +++ b/drivers/block/rbd.c @@ -120,10 +120,11 @@ static int atomic_dec_return_safe(atomic_t *v) /* Feature bits */ -#define RBD_FEATURE_LAYERING (1<<0) -#define RBD_FEATURE_STRIPINGV2 (1<<1) -#define RBD_FEATURE_EXCLUSIVE_LOCK (1<<2) -#define RBD_FEATURE_DATA_POOL (1<<7) +#define RBD_FEATURE_LAYERING (1ULL<<0) +#define RBD_FEATURE_STRIPINGV2 (1ULL<<1) +#define RBD_FEATURE_EXCLUSIVE_LOCK (1ULL<<2) +#define RBD_FEATURE_DATA_POOL (1ULL<<7) + #define RBD_FEATURES_ALL (RBD_FEATURE_LAYERING | \ RBD_FEATURE_STRIPINGV2 | \ RBD_FEATURE_EXCLUSIVE_LOCK | \ @@ -499,16 +500,23 @@ static bool rbd_is_lock_owner(struct rbd_device *rbd_dev) return is_lock_owner; } +static ssize_t rbd_supported_features_show(struct bus_type *bus, char *buf) +{ + return sprintf(buf, "0x%llx\n", RBD_FEATURES_SUPPORTED); +} + static BUS_ATTR(add, S_IWUSR, NULL, rbd_add); static BUS_ATTR(remove, S_IWUSR, NULL, rbd_remove); static BUS_ATTR(add_single_major, S_IWUSR, NULL, rbd_add_single_major); static BUS_ATTR(remove_single_major, S_IWUSR, NULL, rbd_remove_single_major); +static BUS_ATTR(supported_features, S_IRUGO, rbd_supported_features_show, NULL); static struct attribute *rbd_bus_attrs[] = { &bus_attr_add.attr, &bus_attr_remove.attr, &bus_attr_add_single_major.attr, &bus_attr_remove_single_major.attr, + &bus_attr_supported_features.attr, NULL, }; diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c index e27d89a36c34..dceb5edd1e54 100644 --- a/drivers/block/zram/zram_drv.c +++ b/drivers/block/zram/zram_drv.c @@ -1189,6 +1189,8 @@ static int zram_add(void) blk_queue_io_min(zram->disk->queue, PAGE_SIZE); blk_queue_io_opt(zram->disk->queue, PAGE_SIZE); zram->disk->queue->limits.discard_granularity = PAGE_SIZE; + zram->disk->queue->limits.max_sectors = SECTORS_PER_PAGE; + zram->disk->queue->limits.chunk_sectors = 0; blk_queue_max_discard_sectors(zram->disk->queue, UINT_MAX); /* * zram_bio_discard() will clear all logical blocks if logical block diff --git a/drivers/char/hw_random/omap-rng.c b/drivers/char/hw_random/omap-rng.c index 3ad86fdf954e..b1ad12552b56 100644 --- a/drivers/char/hw_random/omap-rng.c +++ b/drivers/char/hw_random/omap-rng.c @@ -397,9 +397,8 @@ static int of_get_omap_rng_device_details(struct omap_rng_dev *priv, irq, err); return err; } - omap_rng_write(priv, RNG_INTMASK_REG, RNG_SHUTDOWN_OFLO_MASK); - priv->clk = of_clk_get(pdev->dev.of_node, 0); + priv->clk = devm_clk_get(&pdev->dev, NULL); if (IS_ERR(priv->clk) && PTR_ERR(priv->clk) == -EPROBE_DEFER) return -EPROBE_DEFER; if (!IS_ERR(priv->clk)) { @@ -408,6 +407,19 @@ static int of_get_omap_rng_device_details(struct omap_rng_dev *priv, dev_err(&pdev->dev, "unable to enable the clk, " "err = %d\n", err); } + + /* + * On OMAP4, enabling the shutdown_oflo interrupt is + * done in the interrupt mask register. There is no + * such register on EIP76, and it's enabled by the + * same bit in the control register + */ + if (priv->pdata->regs[RNG_INTMASK_REG]) + omap_rng_write(priv, RNG_INTMASK_REG, + RNG_SHUTDOWN_OFLO_MASK); + else + omap_rng_write(priv, RNG_CONTROL_REG, + RNG_SHUTDOWN_OFLO_MASK); } return 0; } diff --git a/drivers/char/nwbutton.c b/drivers/char/nwbutton.c index a5b1eb276c0b..e6d0d271c58c 100644 --- a/drivers/char/nwbutton.c +++ b/drivers/char/nwbutton.c @@ -6,7 +6,7 @@ #include <linux/module.h> #include <linux/kernel.h> -#include <linux/sched.h> +#include <linux/sched/signal.h> #include <linux/interrupt.h> #include <linux/time.h> #include <linux/timer.h> diff --git a/drivers/char/random.c b/drivers/char/random.c index 1ef26403bcc8..0ab024918907 100644 --- a/drivers/char/random.c +++ b/drivers/char/random.c @@ -313,13 +313,6 @@ static int random_read_wakeup_bits = 64; static int random_write_wakeup_bits = 28 * OUTPUT_POOL_WORDS; /* - * The minimum number of seconds between urandom pool reseeding. We - * do this to limit the amount of entropy that can be drained from the - * input pool even if there are heavy demands on /dev/urandom. - */ -static int random_min_urandom_seed = 60; - -/* * Originally, we used a primitive polynomial of degree .poolwords * over GF(2). The taps for various sizes are defined below. They * were chosen to be evenly spaced except for the last tap, which is 1 @@ -409,7 +402,6 @@ static struct poolinfo { */ static DECLARE_WAIT_QUEUE_HEAD(random_read_wait); static DECLARE_WAIT_QUEUE_HEAD(random_write_wait); -static DECLARE_WAIT_QUEUE_HEAD(urandom_init_wait); static struct fasync_struct *fasync; static DEFINE_SPINLOCK(random_ready_list_lock); @@ -467,7 +459,6 @@ struct entropy_store { int entropy_count; int entropy_total; unsigned int initialized:1; - unsigned int limit:1; unsigned int last_data_init:1; __u8 last_data[EXTRACT_SIZE]; }; @@ -485,7 +476,6 @@ static __u32 blocking_pool_data[OUTPUT_POOL_WORDS] __latent_entropy; static struct entropy_store input_pool = { .poolinfo = &poolinfo_table[0], .name = "input", - .limit = 1, .lock = __SPIN_LOCK_UNLOCKED(input_pool.lock), .pool = input_pool_data }; @@ -493,7 +483,6 @@ static struct entropy_store input_pool = { static struct entropy_store blocking_pool = { .poolinfo = &poolinfo_table[1], .name = "blocking", - .limit = 1, .pull = &input_pool, .lock = __SPIN_LOCK_UNLOCKED(blocking_pool.lock), .pool = blocking_pool_data, @@ -855,13 +844,6 @@ static void crng_reseed(struct crng_state *crng, struct entropy_store *r) spin_unlock_irqrestore(&primary_crng.lock, flags); } -static inline void maybe_reseed_primary_crng(void) -{ - if (crng_init > 2 && - time_after(jiffies, primary_crng.init_time + CRNG_RESEED_INTERVAL)) - crng_reseed(&primary_crng, &input_pool); -} - static inline void crng_wait_ready(void) { wait_event_interruptible(crng_init_wait, crng_ready()); @@ -1220,15 +1202,6 @@ static void xfer_secondary_pool(struct entropy_store *r, size_t nbytes) r->entropy_count > r->poolinfo->poolfracbits) return; - if (r->limit == 0 && random_min_urandom_seed) { - unsigned long now = jiffies; - - if (time_before(now, - r->last_pulled + random_min_urandom_seed * HZ)) - return; - r->last_pulled = now; - } - _xfer_secondary_pool(r, nbytes); } @@ -1236,8 +1209,6 @@ static void _xfer_secondary_pool(struct entropy_store *r, size_t nbytes) { __u32 tmp[OUTPUT_POOL_WORDS]; - /* For /dev/random's pool, always leave two wakeups' worth */ - int rsvd_bytes = r->limit ? 0 : random_read_wakeup_bits / 4; int bytes = nbytes; /* pull at least as much as a wakeup */ @@ -1248,7 +1219,7 @@ static void _xfer_secondary_pool(struct entropy_store *r, size_t nbytes) trace_xfer_secondary_pool(r->name, bytes * 8, nbytes * 8, ENTROPY_BITS(r), ENTROPY_BITS(r->pull)); bytes = extract_entropy(r->pull, tmp, bytes, - random_read_wakeup_bits / 8, rsvd_bytes); + random_read_wakeup_bits / 8, 0); mix_pool_bytes(r, tmp, bytes); credit_entropy_bits(r, bytes*8); } @@ -1276,7 +1247,7 @@ static void push_to_pool(struct work_struct *work) static size_t account(struct entropy_store *r, size_t nbytes, int min, int reserved) { - int entropy_count, orig; + int entropy_count, orig, have_bytes; size_t ibytes, nfrac; BUG_ON(r->entropy_count > r->poolinfo->poolfracbits); @@ -1285,14 +1256,12 @@ static size_t account(struct entropy_store *r, size_t nbytes, int min, retry: entropy_count = orig = ACCESS_ONCE(r->entropy_count); ibytes = nbytes; - /* If limited, never pull more than available */ - if (r->limit) { - int have_bytes = entropy_count >> (ENTROPY_SHIFT + 3); + /* never pull more than available */ + have_bytes = entropy_count >> (ENTROPY_SHIFT + 3); - if ((have_bytes -= reserved) < 0) - have_bytes = 0; - ibytes = min_t(size_t, ibytes, have_bytes); - } + if ((have_bytes -= reserved) < 0) + have_bytes = 0; + ibytes = min_t(size_t, ibytes, have_bytes); if (ibytes < min) ibytes = 0; @@ -1912,6 +1881,7 @@ SYSCALL_DEFINE3(getrandom, char __user *, buf, size_t, count, static int min_read_thresh = 8, min_write_thresh; static int max_read_thresh = OUTPUT_POOL_WORDS * 32; static int max_write_thresh = INPUT_POOL_WORDS * 32; +static int random_min_urandom_seed = 60; static char sysctl_bootid[16]; /* @@ -2042,63 +2012,64 @@ struct ctl_table random_table[] = { }; #endif /* CONFIG_SYSCTL */ -static u32 random_int_secret[MD5_MESSAGE_BYTES / 4] ____cacheline_aligned; - -int random_int_secret_init(void) -{ - get_random_bytes(random_int_secret, sizeof(random_int_secret)); - return 0; -} - -static DEFINE_PER_CPU(__u32 [MD5_DIGEST_WORDS], get_random_int_hash) - __aligned(sizeof(unsigned long)); +struct batched_entropy { + union { + u64 entropy_u64[CHACHA20_BLOCK_SIZE / sizeof(u64)]; + u32 entropy_u32[CHACHA20_BLOCK_SIZE / sizeof(u32)]; + }; + unsigned int position; +}; /* - * Get a random word for internal kernel use only. Similar to urandom but - * with the goal of minimal entropy pool depletion. As a result, the random - * value is not cryptographically secure but for several uses the cost of - * depleting entropy is too high + * Get a random word for internal kernel use only. The quality of the random + * number is either as good as RDRAND or as good as /dev/urandom, with the + * goal of being quite fast and not depleting entropy. */ -unsigned int get_random_int(void) +static DEFINE_PER_CPU(struct batched_entropy, batched_entropy_u64); +u64 get_random_u64(void) { - __u32 *hash; - unsigned int ret; + u64 ret; + struct batched_entropy *batch; - if (arch_get_random_int(&ret)) +#if BITS_PER_LONG == 64 + if (arch_get_random_long((unsigned long *)&ret)) return ret; +#else + if (arch_get_random_long((unsigned long *)&ret) && + arch_get_random_long((unsigned long *)&ret + 1)) + return ret; +#endif - hash = get_cpu_var(get_random_int_hash); - - hash[0] += current->pid + jiffies + random_get_entropy(); - md5_transform(hash, random_int_secret); - ret = hash[0]; - put_cpu_var(get_random_int_hash); - + batch = &get_cpu_var(batched_entropy_u64); + if (batch->position % ARRAY_SIZE(batch->entropy_u64) == 0) { + extract_crng((u8 *)batch->entropy_u64); + batch->position = 0; + } + ret = batch->entropy_u64[batch->position++]; + put_cpu_var(batched_entropy_u64); return ret; } -EXPORT_SYMBOL(get_random_int); +EXPORT_SYMBOL(get_random_u64); -/* - * Same as get_random_int(), but returns unsigned long. - */ -unsigned long get_random_long(void) +static DEFINE_PER_CPU(struct batched_entropy, batched_entropy_u32); +u32 get_random_u32(void) { - __u32 *hash; - unsigned long ret; + u32 ret; + struct batched_entropy *batch; - if (arch_get_random_long(&ret)) + if (arch_get_random_int(&ret)) return ret; - hash = get_cpu_var(get_random_int_hash); - - hash[0] += current->pid + jiffies + random_get_entropy(); - md5_transform(hash, random_int_secret); - ret = *(unsigned long *)hash; - put_cpu_var(get_random_int_hash); - + batch = &get_cpu_var(batched_entropy_u32); + if (batch->position % ARRAY_SIZE(batch->entropy_u32) == 0) { + extract_crng((u8 *)batch->entropy_u32); + batch->position = 0; + } + ret = batch->entropy_u32[batch->position++]; + put_cpu_var(batched_entropy_u32); return ret; } -EXPORT_SYMBOL(get_random_long); +EXPORT_SYMBOL(get_random_u32); /** * randomize_page - Generate a random, page aligned address diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c index a47543281864..38b9fdf854a4 100644 --- a/drivers/cpufreq/cpufreq.c +++ b/drivers/cpufreq/cpufreq.c @@ -2532,4 +2532,5 @@ static int __init cpufreq_core_init(void) return 0; } +module_param(off, int, 0444); core_initcall(cpufreq_core_init); diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c index b1fbaa30ae04..3d37219a0dd7 100644 --- a/drivers/cpufreq/intel_pstate.c +++ b/drivers/cpufreq/intel_pstate.c @@ -377,6 +377,7 @@ static void intel_pstate_set_performance_limits(struct perf_limits *limits) intel_pstate_init_limits(limits); limits->min_perf_pct = 100; limits->min_perf = int_ext_tofp(1); + limits->min_sysfs_pct = 100; } static DEFINE_MUTEX(intel_pstate_driver_lock); @@ -968,11 +969,20 @@ static int intel_pstate_resume(struct cpufreq_policy *policy) } static void intel_pstate_update_policies(void) + __releases(&intel_pstate_limits_lock) + __acquires(&intel_pstate_limits_lock) { + struct perf_limits *saved_limits = limits; int cpu; + mutex_unlock(&intel_pstate_limits_lock); + for_each_possible_cpu(cpu) cpufreq_update_policy(cpu); + + mutex_lock(&intel_pstate_limits_lock); + + limits = saved_limits; } /************************** debugfs begin ************************/ @@ -1180,10 +1190,10 @@ static ssize_t store_no_turbo(struct kobject *a, struct attribute *b, limits->no_turbo = clamp_t(int, input, 0, 1); - mutex_unlock(&intel_pstate_limits_lock); - intel_pstate_update_policies(); + mutex_unlock(&intel_pstate_limits_lock); + mutex_unlock(&intel_pstate_driver_lock); return count; @@ -1217,10 +1227,10 @@ static ssize_t store_max_perf_pct(struct kobject *a, struct attribute *b, limits->max_perf_pct); limits->max_perf = div_ext_fp(limits->max_perf_pct, 100); - mutex_unlock(&intel_pstate_limits_lock); - intel_pstate_update_policies(); + mutex_unlock(&intel_pstate_limits_lock); + mutex_unlock(&intel_pstate_driver_lock); return count; @@ -1254,10 +1264,10 @@ static ssize_t store_min_perf_pct(struct kobject *a, struct attribute *b, limits->min_perf_pct); limits->min_perf = div_ext_fp(limits->min_perf_pct, 100); - mutex_unlock(&intel_pstate_limits_lock); - intel_pstate_update_policies(); + mutex_unlock(&intel_pstate_limits_lock); + mutex_unlock(&intel_pstate_driver_lock); return count; @@ -1874,13 +1884,11 @@ static int intel_pstate_prepare_request(struct cpudata *cpu, int pstate) intel_pstate_get_min_max(cpu, &min_perf, &max_perf); pstate = clamp_t(int, pstate, min_perf, max_perf); - trace_cpu_frequency(pstate * cpu->pstate.scaling, cpu->cpu); return pstate; } static void intel_pstate_update_pstate(struct cpudata *cpu, int pstate) { - pstate = intel_pstate_prepare_request(cpu, pstate); if (pstate == cpu->pstate.current_pstate) return; @@ -1900,6 +1908,8 @@ static inline void intel_pstate_adjust_busy_pstate(struct cpudata *cpu) update_turbo_state(); + target_pstate = intel_pstate_prepare_request(cpu, target_pstate); + trace_cpu_frequency(target_pstate * cpu->pstate.scaling, cpu->cpu); intel_pstate_update_pstate(cpu, target_pstate); sample = &cpu->sample; @@ -2132,16 +2142,11 @@ static int intel_pstate_set_policy(struct cpufreq_policy *policy) mutex_lock(&intel_pstate_limits_lock); if (policy->policy == CPUFREQ_POLICY_PERFORMANCE) { + pr_debug("set performance\n"); if (!perf_limits) { limits = &performance_limits; perf_limits = limits; } - if (policy->max >= policy->cpuinfo.max_freq && - !limits->no_turbo) { - pr_debug("set performance\n"); - intel_pstate_set_performance_limits(perf_limits); - goto out; - } } else { pr_debug("set powersave\n"); if (!perf_limits) { @@ -2152,7 +2157,7 @@ static int intel_pstate_set_policy(struct cpufreq_policy *policy) } intel_pstate_update_perf_limits(policy, perf_limits); - out: + if (cpu->policy == CPUFREQ_POLICY_PERFORMANCE) { /* * NOHZ_FULL CPUs need this as the governor callback may not @@ -2198,9 +2203,9 @@ static int intel_pstate_verify_policy(struct cpufreq_policy *policy) unsigned int max_freq, min_freq; max_freq = policy->cpuinfo.max_freq * - limits->max_sysfs_pct / 100; + perf_limits->max_sysfs_pct / 100; min_freq = policy->cpuinfo.max_freq * - limits->min_sysfs_pct / 100; + perf_limits->min_sysfs_pct / 100; cpufreq_verify_within_limits(policy, min_freq, max_freq); } @@ -2243,13 +2248,8 @@ static int __intel_pstate_cpu_init(struct cpufreq_policy *policy) cpu = all_cpu_data[policy->cpu]; - /* - * We need sane value in the cpu->perf_limits, so inherit from global - * perf_limits limits, which are seeded with values based on the - * CONFIG_CPU_FREQ_DEFAULT_GOV_*, during boot up. - */ if (per_cpu_limits) - memcpy(cpu->perf_limits, limits, sizeof(struct perf_limits)); + intel_pstate_init_limits(cpu->perf_limits); policy->min = cpu->pstate.min_pstate * cpu->pstate.scaling; policy->max = cpu->pstate.turbo_pstate * cpu->pstate.scaling; @@ -2301,7 +2301,6 @@ static struct cpufreq_driver intel_pstate = { static int intel_cpufreq_verify_policy(struct cpufreq_policy *policy) { struct cpudata *cpu = all_cpu_data[policy->cpu]; - struct perf_limits *perf_limits = limits; update_turbo_state(); policy->cpuinfo.max_freq = limits->turbo_disabled ? @@ -2309,15 +2308,6 @@ static int intel_cpufreq_verify_policy(struct cpufreq_policy *policy) cpufreq_verify_within_cpu_limits(policy); - if (per_cpu_limits) - perf_limits = cpu->perf_limits; - - mutex_lock(&intel_pstate_limits_lock); - - intel_pstate_update_perf_limits(policy, perf_limits); - - mutex_unlock(&intel_pstate_limits_lock); - return 0; } @@ -2370,6 +2360,7 @@ static int intel_cpufreq_target(struct cpufreq_policy *policy, wrmsrl_on_cpu(policy->cpu, MSR_IA32_PERF_CTL, pstate_funcs.get_val(cpu, target_pstate)); } + freqs.new = target_pstate * cpu->pstate.scaling; cpufreq_freq_transition_end(policy, &freqs, false); return 0; @@ -2383,8 +2374,9 @@ static unsigned int intel_cpufreq_fast_switch(struct cpufreq_policy *policy, target_freq = intel_cpufreq_turbo_update(cpu, policy, target_freq); target_pstate = DIV_ROUND_UP(target_freq, cpu->pstate.scaling); + target_pstate = intel_pstate_prepare_request(cpu, target_pstate); intel_pstate_update_pstate(cpu, target_pstate); - return target_freq; + return target_pstate * cpu->pstate.scaling; } static int intel_cpufreq_cpu_init(struct cpufreq_policy *policy) @@ -2437,8 +2429,11 @@ static int intel_pstate_register_driver(void) intel_pstate_init_limits(&powersave_limits); intel_pstate_set_performance_limits(&performance_limits); - limits = IS_ENABLED(CONFIG_CPU_FREQ_DEFAULT_GOV_PERFORMANCE) ? - &performance_limits : &powersave_limits; + if (IS_ENABLED(CONFIG_CPU_FREQ_DEFAULT_GOV_PERFORMANCE) && + intel_pstate_driver == &intel_pstate) + limits = &performance_limits; + else + limits = &powersave_limits; ret = cpufreq_register_driver(intel_pstate_driver); if (ret) { diff --git a/drivers/crypto/s5p-sss.c b/drivers/crypto/s5p-sss.c index dce1af0ce85c..1b9da3dc799b 100644 --- a/drivers/crypto/s5p-sss.c +++ b/drivers/crypto/s5p-sss.c @@ -270,7 +270,7 @@ static void s5p_sg_copy_buf(void *buf, struct scatterlist *sg, scatterwalk_done(&walk, out, 0); } -static void s5p_aes_complete(struct s5p_aes_dev *dev, int err) +static void s5p_sg_done(struct s5p_aes_dev *dev) { if (dev->sg_dst_cpy) { dev_dbg(dev->dev, @@ -281,8 +281,11 @@ static void s5p_aes_complete(struct s5p_aes_dev *dev, int err) } s5p_free_sg_cpy(dev, &dev->sg_src_cpy); s5p_free_sg_cpy(dev, &dev->sg_dst_cpy); +} - /* holding a lock outside */ +/* Calls the completion. Cannot be called with dev->lock hold. */ +static void s5p_aes_complete(struct s5p_aes_dev *dev, int err) +{ dev->req->base.complete(&dev->req->base, err); dev->busy = false; } @@ -368,51 +371,44 @@ exit: } /* - * Returns true if new transmitting (output) data is ready and its - * address+length have to be written to device (by calling - * s5p_set_dma_outdata()). False otherwise. + * Returns -ERRNO on error (mapping of new data failed). + * On success returns: + * - 0 if there is no more data, + * - 1 if new transmitting (output) data is ready and its address+length + * have to be written to device (by calling s5p_set_dma_outdata()). */ -static bool s5p_aes_tx(struct s5p_aes_dev *dev) +static int s5p_aes_tx(struct s5p_aes_dev *dev) { - int err = 0; - bool ret = false; + int ret = 0; s5p_unset_outdata(dev); if (!sg_is_last(dev->sg_dst)) { - err = s5p_set_outdata(dev, sg_next(dev->sg_dst)); - if (err) - s5p_aes_complete(dev, err); - else - ret = true; - } else { - s5p_aes_complete(dev, err); - - dev->busy = true; - tasklet_schedule(&dev->tasklet); + ret = s5p_set_outdata(dev, sg_next(dev->sg_dst)); + if (!ret) + ret = 1; } return ret; } /* - * Returns true if new receiving (input) data is ready and its - * address+length have to be written to device (by calling - * s5p_set_dma_indata()). False otherwise. + * Returns -ERRNO on error (mapping of new data failed). + * On success returns: + * - 0 if there is no more data, + * - 1 if new receiving (input) data is ready and its address+length + * have to be written to device (by calling s5p_set_dma_indata()). */ -static bool s5p_aes_rx(struct s5p_aes_dev *dev) +static int s5p_aes_rx(struct s5p_aes_dev *dev/*, bool *set_dma*/) { - int err; - bool ret = false; + int ret = 0; s5p_unset_indata(dev); if (!sg_is_last(dev->sg_src)) { - err = s5p_set_indata(dev, sg_next(dev->sg_src)); - if (err) - s5p_aes_complete(dev, err); - else - ret = true; + ret = s5p_set_indata(dev, sg_next(dev->sg_src)); + if (!ret) + ret = 1; } return ret; @@ -422,33 +418,73 @@ static irqreturn_t s5p_aes_interrupt(int irq, void *dev_id) { struct platform_device *pdev = dev_id; struct s5p_aes_dev *dev = platform_get_drvdata(pdev); - bool set_dma_tx = false; - bool set_dma_rx = false; + int err_dma_tx = 0; + int err_dma_rx = 0; + bool tx_end = false; unsigned long flags; uint32_t status; + int err; spin_lock_irqsave(&dev->lock, flags); + /* + * Handle rx or tx interrupt. If there is still data (scatterlist did not + * reach end), then map next scatterlist entry. + * In case of such mapping error, s5p_aes_complete() should be called. + * + * If there is no more data in tx scatter list, call s5p_aes_complete() + * and schedule new tasklet. + */ status = SSS_READ(dev, FCINTSTAT); if (status & SSS_FCINTSTAT_BRDMAINT) - set_dma_rx = s5p_aes_rx(dev); - if (status & SSS_FCINTSTAT_BTDMAINT) - set_dma_tx = s5p_aes_tx(dev); + err_dma_rx = s5p_aes_rx(dev); + + if (status & SSS_FCINTSTAT_BTDMAINT) { + if (sg_is_last(dev->sg_dst)) + tx_end = true; + err_dma_tx = s5p_aes_tx(dev); + } SSS_WRITE(dev, FCINTPEND, status); - /* - * Writing length of DMA block (either receiving or transmitting) - * will start the operation immediately, so this should be done - * at the end (even after clearing pending interrupts to not miss the - * interrupt). - */ - if (set_dma_tx) - s5p_set_dma_outdata(dev, dev->sg_dst); - if (set_dma_rx) - s5p_set_dma_indata(dev, dev->sg_src); + if (err_dma_rx < 0) { + err = err_dma_rx; + goto error; + } + if (err_dma_tx < 0) { + err = err_dma_tx; + goto error; + } + + if (tx_end) { + s5p_sg_done(dev); + + spin_unlock_irqrestore(&dev->lock, flags); + + s5p_aes_complete(dev, 0); + dev->busy = true; + tasklet_schedule(&dev->tasklet); + } else { + /* + * Writing length of DMA block (either receiving or + * transmitting) will start the operation immediately, so this + * should be done at the end (even after clearing pending + * interrupts to not miss the interrupt). + */ + if (err_dma_tx == 1) + s5p_set_dma_outdata(dev, dev->sg_dst); + if (err_dma_rx == 1) + s5p_set_dma_indata(dev, dev->sg_src); + spin_unlock_irqrestore(&dev->lock, flags); + } + + return IRQ_HANDLED; + +error: + s5p_sg_done(dev); spin_unlock_irqrestore(&dev->lock, flags); + s5p_aes_complete(dev, err); return IRQ_HANDLED; } @@ -597,8 +633,9 @@ outdata_error: s5p_unset_indata(dev); indata_error: - s5p_aes_complete(dev, err); + s5p_sg_done(dev); spin_unlock_irqrestore(&dev->lock, flags); + s5p_aes_complete(dev, err); } static void s5p_tasklet_cb(unsigned long data) @@ -805,8 +842,9 @@ static int s5p_aes_probe(struct platform_device *pdev) dev_warn(dev, "feed control interrupt is not available.\n"); goto err_irq; } - err = devm_request_irq(dev, pdata->irq_fc, s5p_aes_interrupt, - IRQF_SHARED, pdev->name, pdev); + err = devm_request_threaded_irq(dev, pdata->irq_fc, NULL, + s5p_aes_interrupt, IRQF_ONESHOT, + pdev->name, pdev); if (err < 0) { dev_warn(dev, "feed control interrupt is not available.\n"); goto err_irq; diff --git a/drivers/crypto/ux500/cryp/cryp.c b/drivers/crypto/ux500/cryp/cryp.c index 43a0c8a26ab0..00a16ab601cb 100644 --- a/drivers/crypto/ux500/cryp/cryp.c +++ b/drivers/crypto/ux500/cryp/cryp.c @@ -82,7 +82,7 @@ void cryp_activity(struct cryp_device_data *device_data, void cryp_flush_inoutfifo(struct cryp_device_data *device_data) { /* - * We always need to disble the hardware before trying to flush the + * We always need to disable the hardware before trying to flush the * FIFO. This is something that isn't written in the design * specification, but we have been informed by the hardware designers * that this must be done. diff --git a/drivers/firmware/efi/arm-runtime.c b/drivers/firmware/efi/arm-runtime.c index 349dc3e1e52e..974c5a31a005 100644 --- a/drivers/firmware/efi/arm-runtime.c +++ b/drivers/firmware/efi/arm-runtime.c @@ -65,6 +65,7 @@ static bool __init efi_virtmap_init(void) bool systab_found; efi_mm.pgd = pgd_alloc(&efi_mm); + mm_init_cpumask(&efi_mm); init_new_context(NULL, &efi_mm); systab_found = false; diff --git a/drivers/firmware/efi/libstub/secureboot.c b/drivers/firmware/efi/libstub/secureboot.c index 6def402bf569..5da36e56b36a 100644 --- a/drivers/firmware/efi/libstub/secureboot.c +++ b/drivers/firmware/efi/libstub/secureboot.c @@ -45,6 +45,8 @@ enum efi_secureboot_mode efi_get_secureboot(efi_system_table_t *sys_table_arg) size = sizeof(secboot); status = get_efi_var(efi_SecureBoot_name, &efi_variable_guid, NULL, &size, &secboot); + if (status == EFI_NOT_FOUND) + return efi_secureboot_mode_disabled; if (status != EFI_SUCCESS) goto out_efi_err; @@ -78,7 +80,5 @@ secure_boot_enabled: out_efi_err: pr_efi_err(sys_table_arg, "Could not determine UEFI Secure Boot status.\n"); - if (status == EFI_NOT_FOUND) - return efi_secureboot_mode_disabled; return efi_secureboot_mode_unknown; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index 6abb238b25c9..4120b351a8e5 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -2094,8 +2094,11 @@ int amdgpu_device_resume(struct drm_device *dev, bool resume, bool fbcon) } r = amdgpu_late_init(adev); - if (r) + if (r) { + if (fbcon) + console_unlock(); return r; + } /* pin cursors */ list_for_each_entry(crtc, &dev->mode_config.crtc_list, head) { diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c index 75fc376ba735..f7adbace428a 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c @@ -59,9 +59,10 @@ * - 3.7.0 - Add support for VCE clock list packet * - 3.8.0 - Add support raster config init in the kernel * - 3.9.0 - Add support for memory query info about VRAM and GTT. + * - 3.10.0 - Add support for new fences ioctl, new gem ioctl flags */ #define KMS_DRIVER_MAJOR 3 -#define KMS_DRIVER_MINOR 9 +#define KMS_DRIVER_MINOR 10 #define KMS_DRIVER_PATCHLEVEL 0 int amdgpu_vram_limit = 0; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c index 51d759463384..106cf83c2e6b 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c @@ -202,6 +202,27 @@ int amdgpu_gem_create_ioctl(struct drm_device *dev, void *data, bool kernel = false; int r; + /* reject invalid gem flags */ + if (args->in.domain_flags & ~(AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED | + AMDGPU_GEM_CREATE_NO_CPU_ACCESS | + AMDGPU_GEM_CREATE_CPU_GTT_USWC | + AMDGPU_GEM_CREATE_VRAM_CLEARED| + AMDGPU_GEM_CREATE_SHADOW | + AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS)) { + r = -EINVAL; + goto error_unlock; + } + /* reject invalid gem domains */ + if (args->in.domains & ~(AMDGPU_GEM_DOMAIN_CPU | + AMDGPU_GEM_DOMAIN_GTT | + AMDGPU_GEM_DOMAIN_VRAM | + AMDGPU_GEM_DOMAIN_GDS | + AMDGPU_GEM_DOMAIN_GWS | + AMDGPU_GEM_DOMAIN_OA)) { + r = -EINVAL; + goto error_unlock; + } + /* create a gem object to contain this object in */ if (args->in.domains & (AMDGPU_GEM_DOMAIN_GDS | AMDGPU_GEM_DOMAIN_GWS | AMDGPU_GEM_DOMAIN_OA)) { diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c index 31375bdde6f1..011800f621c6 100644 --- a/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c +++ b/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c @@ -788,7 +788,7 @@ static int sdma_v3_0_start(struct amdgpu_device *adev) } } - /* disble sdma engine before programing it */ + /* disable sdma engine before programing it */ sdma_v3_0_ctx_switch_enable(adev, false); sdma_v3_0_enable(adev, false); diff --git a/drivers/gpu/drm/drm_edid.c b/drivers/gpu/drm/drm_edid.c index c8baab9bee0d..ba58f1b11d1e 100644 --- a/drivers/gpu/drm/drm_edid.c +++ b/drivers/gpu/drm/drm_edid.c @@ -148,6 +148,9 @@ static const struct edid_quirk { /* Panel in Samsung NP700G7A-S01PL notebook reports 6bpc */ { "SEC", 0xd033, EDID_QUIRK_FORCE_8BPC }, + + /* Rotel RSX-1058 forwards sink's EDID but only does HDMI 1.1*/ + { "ETR", 13896, EDID_QUIRK_FORCE_8BPC }, }; /* diff --git a/drivers/gpu/drm/i915/gvt/cfg_space.c b/drivers/gpu/drm/i915/gvt/cfg_space.c index 4a6a2ed65732..b7d7721e72fa 100644 --- a/drivers/gpu/drm/i915/gvt/cfg_space.c +++ b/drivers/gpu/drm/i915/gvt/cfg_space.c @@ -41,6 +41,54 @@ enum { INTEL_GVT_PCI_BAR_MAX, }; +/* bitmap for writable bits (RW or RW1C bits, but cannot co-exist in one + * byte) byte by byte in standard pci configuration space. (not the full + * 256 bytes.) + */ +static const u8 pci_cfg_space_rw_bmp[PCI_INTERRUPT_LINE + 4] = { + [PCI_COMMAND] = 0xff, 0x07, + [PCI_STATUS] = 0x00, 0xf9, /* the only one RW1C byte */ + [PCI_CACHE_LINE_SIZE] = 0xff, + [PCI_BASE_ADDRESS_0 ... PCI_CARDBUS_CIS - 1] = 0xff, + [PCI_ROM_ADDRESS] = 0x01, 0xf8, 0xff, 0xff, + [PCI_INTERRUPT_LINE] = 0xff, +}; + +/** + * vgpu_pci_cfg_mem_write - write virtual cfg space memory + * + * Use this function to write virtual cfg space memory. + * For standard cfg space, only RW bits can be changed, + * and we emulates the RW1C behavior of PCI_STATUS register. + */ +static void vgpu_pci_cfg_mem_write(struct intel_vgpu *vgpu, unsigned int off, + u8 *src, unsigned int bytes) +{ + u8 *cfg_base = vgpu_cfg_space(vgpu); + u8 mask, new, old; + int i = 0; + + for (; i < bytes && (off + i < sizeof(pci_cfg_space_rw_bmp)); i++) { + mask = pci_cfg_space_rw_bmp[off + i]; + old = cfg_base[off + i]; + new = src[i] & mask; + + /** + * The PCI_STATUS high byte has RW1C bits, here + * emulates clear by writing 1 for these bits. + * Writing a 0b to RW1C bits has no effect. + */ + if (off + i == PCI_STATUS + 1) + new = (~new & old) & mask; + + cfg_base[off + i] = (old & ~mask) | new; + } + + /* For other configuration space directly copy as it is. */ + if (i < bytes) + memcpy(cfg_base + off + i, src + i, bytes - i); +} + /** * intel_vgpu_emulate_cfg_read - emulate vGPU configuration space read * @@ -123,7 +171,7 @@ static int emulate_pci_command_write(struct intel_vgpu *vgpu, u8 changed = old ^ new; int ret; - memcpy(vgpu_cfg_space(vgpu) + offset, p_data, bytes); + vgpu_pci_cfg_mem_write(vgpu, offset, p_data, bytes); if (!(changed & PCI_COMMAND_MEMORY)) return 0; @@ -237,6 +285,9 @@ int intel_vgpu_emulate_cfg_write(struct intel_vgpu *vgpu, unsigned int offset, { int ret; + if (vgpu->failsafe) + return 0; + if (WARN_ON(bytes > 4)) return -EINVAL; @@ -274,10 +325,10 @@ int intel_vgpu_emulate_cfg_write(struct intel_vgpu *vgpu, unsigned int offset, if (ret) return ret; - memcpy(vgpu_cfg_space(vgpu) + offset, p_data, bytes); + vgpu_pci_cfg_mem_write(vgpu, offset, p_data, bytes); break; default: - memcpy(vgpu_cfg_space(vgpu) + offset, p_data, bytes); + vgpu_pci_cfg_mem_write(vgpu, offset, p_data, bytes); break; } return 0; diff --git a/drivers/gpu/drm/i915/gvt/cmd_parser.c b/drivers/gpu/drm/i915/gvt/cmd_parser.c index b9c8e2407682..7ae6e2b241c8 100644 --- a/drivers/gpu/drm/i915/gvt/cmd_parser.c +++ b/drivers/gpu/drm/i915/gvt/cmd_parser.c @@ -668,7 +668,7 @@ static inline void print_opcode(u32 cmd, int ring_id) if (d_info == NULL) return; - gvt_err("opcode=0x%x %s sub_ops:", + gvt_dbg_cmd("opcode=0x%x %s sub_ops:", cmd >> (32 - d_info->op_len), d_info->name); for (i = 0; i < d_info->nr_sub_op; i++) @@ -693,23 +693,23 @@ static void parser_exec_state_dump(struct parser_exec_state *s) int cnt = 0; int i; - gvt_err(" vgpu%d RING%d: ring_start(%08lx) ring_end(%08lx)" + gvt_dbg_cmd(" vgpu%d RING%d: ring_start(%08lx) ring_end(%08lx)" " ring_head(%08lx) ring_tail(%08lx)\n", s->vgpu->id, s->ring_id, s->ring_start, s->ring_start + s->ring_size, s->ring_head, s->ring_tail); - gvt_err(" %s %s ip_gma(%08lx) ", + gvt_dbg_cmd(" %s %s ip_gma(%08lx) ", s->buf_type == RING_BUFFER_INSTRUCTION ? "RING_BUFFER" : "BATCH_BUFFER", s->buf_addr_type == GTT_BUFFER ? "GTT" : "PPGTT", s->ip_gma); if (s->ip_va == NULL) { - gvt_err(" ip_va(NULL)"); + gvt_dbg_cmd(" ip_va(NULL)"); return; } - gvt_err(" ip_va=%p: %08x %08x %08x %08x\n", + gvt_dbg_cmd(" ip_va=%p: %08x %08x %08x %08x\n", s->ip_va, cmd_val(s, 0), cmd_val(s, 1), cmd_val(s, 2), cmd_val(s, 3)); diff --git a/drivers/gpu/drm/i915/gvt/display.c b/drivers/gpu/drm/i915/gvt/display.c index 6d8fde880c39..5419ae6ec633 100644 --- a/drivers/gpu/drm/i915/gvt/display.c +++ b/drivers/gpu/drm/i915/gvt/display.c @@ -83,44 +83,80 @@ static int pipe_is_enabled(struct intel_vgpu *vgpu, int pipe) return 0; } +static unsigned char virtual_dp_monitor_edid[GVT_EDID_NUM][EDID_SIZE] = { + { +/* EDID with 1024x768 as its resolution */ + /*Header*/ + 0x00, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0x00, + /* Vendor & Product Identification */ + 0x22, 0xf0, 0x54, 0x29, 0x00, 0x00, 0x00, 0x00, 0x04, 0x17, + /* Version & Revision */ + 0x01, 0x04, + /* Basic Display Parameters & Features */ + 0xa5, 0x34, 0x20, 0x78, 0x23, + /* Color Characteristics */ + 0xfc, 0x81, 0xa4, 0x55, 0x4d, 0x9d, 0x25, 0x12, 0x50, 0x54, + /* Established Timings: maximum resolution is 1024x768 */ + 0x21, 0x08, 0x00, + /* Standard Timings. All invalid */ + 0x00, 0xc0, 0x00, 0xc0, 0x00, 0x40, 0x00, 0x80, 0x00, 0x00, + 0x00, 0x40, 0x00, 0x00, 0x00, 0x01, + /* 18 Byte Data Blocks 1: invalid */ + 0x00, 0x00, 0x80, 0xa0, 0x70, 0xb0, + 0x23, 0x40, 0x30, 0x20, 0x36, 0x00, 0x06, 0x44, 0x21, 0x00, 0x00, 0x1a, + /* 18 Byte Data Blocks 2: invalid */ + 0x00, 0x00, 0x00, 0xfd, 0x00, 0x18, 0x3c, 0x18, 0x50, 0x11, 0x00, 0x0a, + 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, + /* 18 Byte Data Blocks 3: invalid */ + 0x00, 0x00, 0x00, 0xfc, 0x00, 0x48, + 0x50, 0x20, 0x5a, 0x52, 0x32, 0x34, 0x34, 0x30, 0x77, 0x0a, 0x20, 0x20, + /* 18 Byte Data Blocks 4: invalid */ + 0x00, 0x00, 0x00, 0xff, 0x00, 0x43, 0x4e, 0x34, 0x33, 0x30, 0x34, 0x30, + 0x44, 0x58, 0x51, 0x0a, 0x20, 0x20, + /* Extension Block Count */ + 0x00, + /* Checksum */ + 0xef, + }, + { /* EDID with 1920x1200 as its resolution */ -static unsigned char virtual_dp_monitor_edid[] = { - /*Header*/ - 0x00, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0x00, - /* Vendor & Product Identification */ - 0x22, 0xf0, 0x54, 0x29, 0x00, 0x00, 0x00, 0x00, 0x04, 0x17, - /* Version & Revision */ - 0x01, 0x04, - /* Basic Display Parameters & Features */ - 0xa5, 0x34, 0x20, 0x78, 0x23, - /* Color Characteristics */ - 0xfc, 0x81, 0xa4, 0x55, 0x4d, 0x9d, 0x25, 0x12, 0x50, 0x54, - /* Established Timings: maximum resolution is 1024x768 */ - 0x21, 0x08, 0x00, - /* - * Standard Timings. - * below new resolutions can be supported: - * 1920x1080, 1280x720, 1280x960, 1280x1024, - * 1440x900, 1600x1200, 1680x1050 - */ - 0xd1, 0xc0, 0x81, 0xc0, 0x81, 0x40, 0x81, 0x80, 0x95, 0x00, - 0xa9, 0x40, 0xb3, 0x00, 0x01, 0x01, - /* 18 Byte Data Blocks 1: max resolution is 1920x1200 */ - 0x28, 0x3c, 0x80, 0xa0, 0x70, 0xb0, - 0x23, 0x40, 0x30, 0x20, 0x36, 0x00, 0x06, 0x44, 0x21, 0x00, 0x00, 0x1a, - /* 18 Byte Data Blocks 2: invalid */ - 0x00, 0x00, 0x00, 0xfd, 0x00, 0x18, 0x3c, 0x18, 0x50, 0x11, 0x00, 0x0a, - 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, - /* 18 Byte Data Blocks 3: invalid */ - 0x00, 0x00, 0x00, 0xfc, 0x00, 0x48, - 0x50, 0x20, 0x5a, 0x52, 0x32, 0x34, 0x34, 0x30, 0x77, 0x0a, 0x20, 0x20, - /* 18 Byte Data Blocks 4: invalid */ - 0x00, 0x00, 0x00, 0xff, 0x00, 0x43, 0x4e, 0x34, 0x33, 0x30, 0x34, 0x30, - 0x44, 0x58, 0x51, 0x0a, 0x20, 0x20, - /* Extension Block Count */ - 0x00, - /* Checksum */ - 0x45, + /*Header*/ + 0x00, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0x00, + /* Vendor & Product Identification */ + 0x22, 0xf0, 0x54, 0x29, 0x00, 0x00, 0x00, 0x00, 0x04, 0x17, + /* Version & Revision */ + 0x01, 0x04, + /* Basic Display Parameters & Features */ + 0xa5, 0x34, 0x20, 0x78, 0x23, + /* Color Characteristics */ + 0xfc, 0x81, 0xa4, 0x55, 0x4d, 0x9d, 0x25, 0x12, 0x50, 0x54, + /* Established Timings: maximum resolution is 1024x768 */ + 0x21, 0x08, 0x00, + /* + * Standard Timings. + * below new resolutions can be supported: + * 1920x1080, 1280x720, 1280x960, 1280x1024, + * 1440x900, 1600x1200, 1680x1050 + */ + 0xd1, 0xc0, 0x81, 0xc0, 0x81, 0x40, 0x81, 0x80, 0x95, 0x00, + 0xa9, 0x40, 0xb3, 0x00, 0x01, 0x01, + /* 18 Byte Data Blocks 1: max resolution is 1920x1200 */ + 0x28, 0x3c, 0x80, 0xa0, 0x70, 0xb0, + 0x23, 0x40, 0x30, 0x20, 0x36, 0x00, 0x06, 0x44, 0x21, 0x00, 0x00, 0x1a, + /* 18 Byte Data Blocks 2: invalid */ + 0x00, 0x00, 0x00, 0xfd, 0x00, 0x18, 0x3c, 0x18, 0x50, 0x11, 0x00, 0x0a, + 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, + /* 18 Byte Data Blocks 3: invalid */ + 0x00, 0x00, 0x00, 0xfc, 0x00, 0x48, + 0x50, 0x20, 0x5a, 0x52, 0x32, 0x34, 0x34, 0x30, 0x77, 0x0a, 0x20, 0x20, + /* 18 Byte Data Blocks 4: invalid */ + 0x00, 0x00, 0x00, 0xff, 0x00, 0x43, 0x4e, 0x34, 0x33, 0x30, 0x34, 0x30, + 0x44, 0x58, 0x51, 0x0a, 0x20, 0x20, + /* Extension Block Count */ + 0x00, + /* Checksum */ + 0x45, + }, }; #define DPCD_HEADER_SIZE 0xb @@ -140,14 +176,20 @@ static void emulate_monitor_status_change(struct intel_vgpu *vgpu) vgpu_vreg(vgpu, SDEISR) &= ~(SDE_PORTA_HOTPLUG_SPT | SDE_PORTE_HOTPLUG_SPT); - if (intel_vgpu_has_monitor_on_port(vgpu, PORT_B)) + if (intel_vgpu_has_monitor_on_port(vgpu, PORT_B)) { vgpu_vreg(vgpu, SDEISR) |= SDE_PORTB_HOTPLUG_CPT; + vgpu_vreg(vgpu, SFUSE_STRAP) |= SFUSE_STRAP_DDIB_DETECTED; + } - if (intel_vgpu_has_monitor_on_port(vgpu, PORT_C)) + if (intel_vgpu_has_monitor_on_port(vgpu, PORT_C)) { vgpu_vreg(vgpu, SDEISR) |= SDE_PORTC_HOTPLUG_CPT; + vgpu_vreg(vgpu, SFUSE_STRAP) |= SFUSE_STRAP_DDIC_DETECTED; + } - if (intel_vgpu_has_monitor_on_port(vgpu, PORT_D)) + if (intel_vgpu_has_monitor_on_port(vgpu, PORT_D)) { vgpu_vreg(vgpu, SDEISR) |= SDE_PORTD_HOTPLUG_CPT; + vgpu_vreg(vgpu, SFUSE_STRAP) |= SFUSE_STRAP_DDID_DETECTED; + } if (IS_SKYLAKE(dev_priv) && intel_vgpu_has_monitor_on_port(vgpu, PORT_E)) { @@ -160,6 +202,8 @@ static void emulate_monitor_status_change(struct intel_vgpu *vgpu) GEN8_PORT_DP_A_HOTPLUG; else vgpu_vreg(vgpu, SDEISR) |= SDE_PORTA_HOTPLUG_SPT; + + vgpu_vreg(vgpu, DDI_BUF_CTL(PORT_A)) |= DDI_INIT_DISPLAY_DETECTED; } } @@ -175,10 +219,13 @@ static void clean_virtual_dp_monitor(struct intel_vgpu *vgpu, int port_num) } static int setup_virtual_dp_monitor(struct intel_vgpu *vgpu, int port_num, - int type) + int type, unsigned int resolution) { struct intel_vgpu_port *port = intel_vgpu_port(vgpu, port_num); + if (WARN_ON(resolution >= GVT_EDID_NUM)) + return -EINVAL; + port->edid = kzalloc(sizeof(*(port->edid)), GFP_KERNEL); if (!port->edid) return -ENOMEM; @@ -189,7 +236,7 @@ static int setup_virtual_dp_monitor(struct intel_vgpu *vgpu, int port_num, return -ENOMEM; } - memcpy(port->edid->edid_block, virtual_dp_monitor_edid, + memcpy(port->edid->edid_block, virtual_dp_monitor_edid[resolution], EDID_SIZE); port->edid->data_valid = true; @@ -322,16 +369,18 @@ void intel_vgpu_clean_display(struct intel_vgpu *vgpu) * Zero on success, negative error code if failed. * */ -int intel_vgpu_init_display(struct intel_vgpu *vgpu) +int intel_vgpu_init_display(struct intel_vgpu *vgpu, u64 resolution) { struct drm_i915_private *dev_priv = vgpu->gvt->dev_priv; intel_vgpu_init_i2c_edid(vgpu); if (IS_SKYLAKE(dev_priv)) - return setup_virtual_dp_monitor(vgpu, PORT_D, GVT_DP_D); + return setup_virtual_dp_monitor(vgpu, PORT_D, GVT_DP_D, + resolution); else - return setup_virtual_dp_monitor(vgpu, PORT_B, GVT_DP_B); + return setup_virtual_dp_monitor(vgpu, PORT_B, GVT_DP_B, + resolution); } /** diff --git a/drivers/gpu/drm/i915/gvt/display.h b/drivers/gpu/drm/i915/gvt/display.h index 8b234ea961f6..d73de22102e2 100644 --- a/drivers/gpu/drm/i915/gvt/display.h +++ b/drivers/gpu/drm/i915/gvt/display.h @@ -154,10 +154,28 @@ struct intel_vgpu_port { int type; }; +enum intel_vgpu_edid { + GVT_EDID_1024_768, + GVT_EDID_1920_1200, + GVT_EDID_NUM, +}; + +static inline char *vgpu_edid_str(enum intel_vgpu_edid id) +{ + switch (id) { + case GVT_EDID_1024_768: + return "1024x768"; + case GVT_EDID_1920_1200: + return "1920x1200"; + default: + return ""; + } +} + void intel_gvt_emulate_vblank(struct intel_gvt *gvt); void intel_gvt_check_vblank_emulation(struct intel_gvt *gvt); -int intel_vgpu_init_display(struct intel_vgpu *vgpu); +int intel_vgpu_init_display(struct intel_vgpu *vgpu, u64 resolution); void intel_vgpu_reset_display(struct intel_vgpu *vgpu); void intel_vgpu_clean_display(struct intel_vgpu *vgpu); diff --git a/drivers/gpu/drm/i915/gvt/firmware.c b/drivers/gpu/drm/i915/gvt/firmware.c index 1cb29b2d7dc6..933a7c211a1c 100644 --- a/drivers/gpu/drm/i915/gvt/firmware.c +++ b/drivers/gpu/drm/i915/gvt/firmware.c @@ -80,7 +80,7 @@ static int expose_firmware_sysfs(struct intel_gvt *gvt) int ret; size = sizeof(*h) + info->mmio_size + info->cfg_space_size - 1; - firmware = vmalloc(size); + firmware = vzalloc(size); if (!firmware) return -ENOMEM; diff --git a/drivers/gpu/drm/i915/gvt/gtt.c b/drivers/gpu/drm/i915/gvt/gtt.c index 28c92346db0e..6a5ff23ded90 100644 --- a/drivers/gpu/drm/i915/gvt/gtt.c +++ b/drivers/gpu/drm/i915/gvt/gtt.c @@ -1825,11 +1825,8 @@ static int emulate_gtt_mmio_write(struct intel_vgpu *vgpu, unsigned int off, gma = g_gtt_index << GTT_PAGE_SHIFT; /* the VM may configure the whole GM space when ballooning is used */ - if (WARN_ONCE(!vgpu_gmadr_is_valid(vgpu, gma), - "vgpu%d: found oob ggtt write, offset %x\n", - vgpu->id, off)) { + if (!vgpu_gmadr_is_valid(vgpu, gma)) return 0; - } ggtt_get_guest_entry(ggtt_mm, &e, g_gtt_index); @@ -2015,6 +2012,22 @@ int intel_vgpu_init_gtt(struct intel_vgpu *vgpu) return create_scratch_page_tree(vgpu); } +static void intel_vgpu_free_mm(struct intel_vgpu *vgpu, int type) +{ + struct list_head *pos, *n; + struct intel_vgpu_mm *mm; + + list_for_each_safe(pos, n, &vgpu->gtt.mm_list_head) { + mm = container_of(pos, struct intel_vgpu_mm, list); + if (mm->type == type) { + vgpu->gvt->gtt.mm_free_page_table(mm); + list_del(&mm->list); + list_del(&mm->lru_list); + kfree(mm); + } + } +} + /** * intel_vgpu_clean_gtt - clean up per-vGPU graphics memory virulization * @vgpu: a vGPU @@ -2027,19 +2040,11 @@ int intel_vgpu_init_gtt(struct intel_vgpu *vgpu) */ void intel_vgpu_clean_gtt(struct intel_vgpu *vgpu) { - struct list_head *pos, *n; - struct intel_vgpu_mm *mm; - ppgtt_free_all_shadow_page(vgpu); release_scratch_page_tree(vgpu); - list_for_each_safe(pos, n, &vgpu->gtt.mm_list_head) { - mm = container_of(pos, struct intel_vgpu_mm, list); - vgpu->gvt->gtt.mm_free_page_table(mm); - list_del(&mm->list); - list_del(&mm->lru_list); - kfree(mm); - } + intel_vgpu_free_mm(vgpu, INTEL_GVT_MM_PPGTT); + intel_vgpu_free_mm(vgpu, INTEL_GVT_MM_GGTT); } static void clean_spt_oos(struct intel_gvt *gvt) @@ -2322,6 +2327,13 @@ void intel_vgpu_reset_gtt(struct intel_vgpu *vgpu, bool dmlr) int i; ppgtt_free_all_shadow_page(vgpu); + + /* Shadow pages are only created when there is no page + * table tracking data, so remove page tracking data after + * removing the shadow pages. + */ + intel_vgpu_free_mm(vgpu, INTEL_GVT_MM_PPGTT); + if (!dmlr) return; diff --git a/drivers/gpu/drm/i915/gvt/gvt.h b/drivers/gpu/drm/i915/gvt/gvt.h index e227caf5859e..23791920ced1 100644 --- a/drivers/gpu/drm/i915/gvt/gvt.h +++ b/drivers/gpu/drm/i915/gvt/gvt.h @@ -143,6 +143,8 @@ struct intel_vgpu { int id; unsigned long handle; /* vGPU handle used by hypervisor MPT modules */ bool active; + bool pv_notified; + bool failsafe; bool resetting; void *sched_data; @@ -203,18 +205,18 @@ struct intel_gvt_firmware { }; struct intel_gvt_opregion { - void __iomem *opregion_va; + void *opregion_va; u32 opregion_pa; }; #define NR_MAX_INTEL_VGPU_TYPES 20 struct intel_vgpu_type { char name[16]; - unsigned int max_instance; unsigned int avail_instance; unsigned int low_gm_size; unsigned int high_gm_size; unsigned int fence; + enum intel_vgpu_edid resolution; }; struct intel_gvt { @@ -317,6 +319,7 @@ struct intel_vgpu_creation_params { __u64 low_gm_sz; /* in MB */ __u64 high_gm_sz; /* in MB */ __u64 fence_sz; + __u64 resolution; __s32 primary; __u64 vgpu_id; }; @@ -449,6 +452,11 @@ struct intel_gvt_ops { }; +enum { + GVT_FAILSAFE_UNSUPPORTED_GUEST, + GVT_FAILSAFE_INSUFFICIENT_RESOURCE, +}; + #include "mpt.h" #endif diff --git a/drivers/gpu/drm/i915/gvt/handlers.c b/drivers/gpu/drm/i915/gvt/handlers.c index 1d450627ff65..8e43395c748a 100644 --- a/drivers/gpu/drm/i915/gvt/handlers.c +++ b/drivers/gpu/drm/i915/gvt/handlers.c @@ -121,6 +121,7 @@ static int new_mmio_info(struct intel_gvt *gvt, info->size = size; info->length = (i + 4) < end ? 4 : (end - i); info->addr_mask = addr_mask; + info->ro_mask = ro_mask; info->device = device; info->read = read ? read : intel_vgpu_default_mmio_read; info->write = write ? write : intel_vgpu_default_mmio_write; @@ -150,15 +151,44 @@ static int render_mmio_to_ring_id(struct intel_gvt *gvt, unsigned int reg) #define fence_num_to_offset(num) \ (num * 8 + i915_mmio_reg_offset(FENCE_REG_GEN6_LO(0))) + +static void enter_failsafe_mode(struct intel_vgpu *vgpu, int reason) +{ + switch (reason) { + case GVT_FAILSAFE_UNSUPPORTED_GUEST: + pr_err("Detected your guest driver doesn't support GVT-g.\n"); + break; + case GVT_FAILSAFE_INSUFFICIENT_RESOURCE: + pr_err("Graphics resource is not enough for the guest\n"); + default: + break; + } + pr_err("Now vgpu %d will enter failsafe mode.\n", vgpu->id); + vgpu->failsafe = true; +} + static int sanitize_fence_mmio_access(struct intel_vgpu *vgpu, unsigned int fence_num, void *p_data, unsigned int bytes) { if (fence_num >= vgpu_fence_sz(vgpu)) { - gvt_err("vgpu%d: found oob fence register access\n", - vgpu->id); - gvt_err("vgpu%d: total fence num %d access fence num %d\n", - vgpu->id, vgpu_fence_sz(vgpu), fence_num); + + /* When guest access oob fence regs without access + * pv_info first, we treat guest not supporting GVT, + * and we will let vgpu enter failsafe mode. + */ + if (!vgpu->pv_notified) + enter_failsafe_mode(vgpu, + GVT_FAILSAFE_UNSUPPORTED_GUEST); + + if (!vgpu->mmio.disable_warn_untrack) { + gvt_err("vgpu%d: found oob fence register access\n", + vgpu->id); + gvt_err("vgpu%d: total fence %d, access fence %d\n", + vgpu->id, vgpu_fence_sz(vgpu), + fence_num); + } memset(p_data, 0, bytes); + return -EINVAL; } return 0; } @@ -369,6 +399,74 @@ static int pipeconf_mmio_write(struct intel_vgpu *vgpu, unsigned int offset, return 0; } +/* ascendingly sorted */ +static i915_reg_t force_nonpriv_white_list[] = { + GEN9_CS_DEBUG_MODE1, //_MMIO(0x20ec) + GEN9_CTX_PREEMPT_REG,//_MMIO(0x2248) + GEN8_CS_CHICKEN1,//_MMIO(0x2580) + _MMIO(0x2690), + _MMIO(0x2694), + _MMIO(0x2698), + _MMIO(0x4de0), + _MMIO(0x4de4), + _MMIO(0x4dfc), + GEN7_COMMON_SLICE_CHICKEN1,//_MMIO(0x7010) + _MMIO(0x7014), + HDC_CHICKEN0,//_MMIO(0x7300) + GEN8_HDC_CHICKEN1,//_MMIO(0x7304) + _MMIO(0x7700), + _MMIO(0x7704), + _MMIO(0x7708), + _MMIO(0x770c), + _MMIO(0xb110), + GEN8_L3SQCREG4,//_MMIO(0xb118) + _MMIO(0xe100), + _MMIO(0xe18c), + _MMIO(0xe48c), + _MMIO(0xe5f4), +}; + +/* a simple bsearch */ +static inline bool in_whitelist(unsigned int reg) +{ + int left = 0, right = ARRAY_SIZE(force_nonpriv_white_list); + i915_reg_t *array = force_nonpriv_white_list; + + while (left < right) { + int mid = (left + right)/2; + + if (reg > array[mid].reg) + left = mid + 1; + else if (reg < array[mid].reg) + right = mid; + else + return true; + } + return false; +} + +static int force_nonpriv_write(struct intel_vgpu *vgpu, + unsigned int offset, void *p_data, unsigned int bytes) +{ + u32 reg_nonpriv = *(u32 *)p_data; + int ret = -EINVAL; + + if ((bytes != 4) || ((offset & (bytes - 1)) != 0)) { + gvt_err("vgpu(%d) Invalid FORCE_NONPRIV offset %x(%dB)\n", + vgpu->id, offset, bytes); + return ret; + } + + if (in_whitelist(reg_nonpriv)) { + ret = intel_vgpu_default_mmio_write(vgpu, offset, p_data, + bytes); + } else { + gvt_err("vgpu(%d) Invalid FORCE_NONPRIV write %x\n", + vgpu->id, reg_nonpriv); + } + return ret; +} + static int ddi_buf_ctl_mmio_write(struct intel_vgpu *vgpu, unsigned int offset, void *p_data, unsigned int bytes) { @@ -1001,6 +1099,7 @@ static int pvinfo_mmio_read(struct intel_vgpu *vgpu, unsigned int offset, if (invalid_read) gvt_err("invalid pvinfo read: [%x:%x] = %x\n", offset, bytes, *(u32 *)p_data); + vgpu->pv_notified = true; return 0; } @@ -1039,7 +1138,7 @@ static int send_display_ready_uevent(struct intel_vgpu *vgpu, int ready) char vmid_str[20]; char display_ready_str[20]; - snprintf(display_ready_str, 20, "GVT_DISPLAY_READY=%d\n", ready); + snprintf(display_ready_str, 20, "GVT_DISPLAY_READY=%d", ready); env[0] = display_ready_str; snprintf(vmid_str, 20, "VMID=%d", vgpu->id); @@ -1078,6 +1177,9 @@ static int pvinfo_mmio_write(struct intel_vgpu *vgpu, unsigned int offset, case _vgtif_reg(execlist_context_descriptor_lo): case _vgtif_reg(execlist_context_descriptor_hi): break; + case _vgtif_reg(rsv5[0])..._vgtif_reg(rsv5[3]): + enter_failsafe_mode(vgpu, GVT_FAILSAFE_INSUFFICIENT_RESOURCE); + break; default: gvt_err("invalid pvinfo write offset %x bytes %x data %x\n", offset, bytes, data); @@ -1203,26 +1305,37 @@ static int mailbox_write(struct intel_vgpu *vgpu, unsigned int offset, u32 *data0 = &vgpu_vreg(vgpu, GEN6_PCODE_DATA); switch (cmd) { - case 0x6: - /** - * "Read memory latency" command on gen9. - * Below memory latency values are read - * from skylake platform. - */ - if (!*data0) - *data0 = 0x1e1a1100; - else - *data0 = 0x61514b3d; + case GEN9_PCODE_READ_MEM_LATENCY: + if (IS_SKYLAKE(vgpu->gvt->dev_priv)) { + /** + * "Read memory latency" command on gen9. + * Below memory latency values are read + * from skylake platform. + */ + if (!*data0) + *data0 = 0x1e1a1100; + else + *data0 = 0x61514b3d; + } + break; + case SKL_PCODE_CDCLK_CONTROL: + if (IS_SKYLAKE(vgpu->gvt->dev_priv)) + *data0 = SKL_CDCLK_READY_FOR_CHANGE; break; - case 0x5: + case GEN6_PCODE_READ_RC6VIDS: *data0 |= 0x1; break; } gvt_dbg_core("VM(%d) write %x to mailbox, return data0 %x\n", vgpu->id, value, *data0); - - value &= ~(1 << 31); + /** + * PCODE_READY clear means ready for pcode read/write, + * PCODE_ERROR_MASK clear means no error happened. In GVT-g we + * always emulate as pcode read/write success and ready for access + * anytime, since we don't touch real physical registers here. + */ + value &= ~(GEN6_PCODE_READY | GEN6_PCODE_ERROR_MASK); return intel_vgpu_default_mmio_write(vgpu, offset, &value, bytes); } @@ -1318,6 +1431,17 @@ static int ring_mode_mmio_write(struct intel_vgpu *vgpu, unsigned int offset, bool enable_execlist; write_vreg(vgpu, offset, p_data, bytes); + + /* when PPGTT mode enabled, we will check if guest has called + * pvinfo, if not, we will treat this guest as non-gvtg-aware + * guest, and stop emulating its cfg space, mmio, gtt, etc. + */ + if (((data & _MASKED_BIT_ENABLE(GFX_PPGTT_ENABLE)) || + (data & _MASKED_BIT_ENABLE(GFX_RUN_LIST_ENABLE))) + && !vgpu->pv_notified) { + enter_failsafe_mode(vgpu, GVT_FAILSAFE_UNSUPPORTED_GUEST); + return 0; + } if ((data & _MASKED_BIT_ENABLE(GFX_RUN_LIST_ENABLE)) || (data & _MASKED_BIT_DISABLE(GFX_RUN_LIST_ENABLE))) { enable_execlist = !!(data & GFX_RUN_LIST_ENABLE); @@ -1400,6 +1524,9 @@ static int ring_reset_ctl_write(struct intel_vgpu *vgpu, #define MMIO_GM(reg, d, r, w) \ MMIO_F(reg, 4, F_GMADR, 0xFFFFF000, 0, d, r, w) +#define MMIO_GM_RDR(reg, d, r, w) \ + MMIO_F(reg, 4, F_GMADR | F_CMD_ACCESS, 0xFFFFF000, 0, d, r, w) + #define MMIO_RO(reg, d, f, rm, r, w) \ MMIO_F(reg, 4, F_RO | f, 0, rm, d, r, w) @@ -1419,6 +1546,9 @@ static int ring_reset_ctl_write(struct intel_vgpu *vgpu, #define MMIO_RING_GM(prefix, d, r, w) \ MMIO_RING_F(prefix, 4, F_GMADR, 0xFFFF0000, 0, d, r, w) +#define MMIO_RING_GM_RDR(prefix, d, r, w) \ + MMIO_RING_F(prefix, 4, F_GMADR | F_CMD_ACCESS, 0xFFFF0000, 0, d, r, w) + #define MMIO_RING_RO(prefix, d, f, rm, r, w) \ MMIO_RING_F(prefix, 4, F_RO | f, 0, rm, d, r, w) @@ -1427,73 +1557,81 @@ static int init_generic_mmio_info(struct intel_gvt *gvt) struct drm_i915_private *dev_priv = gvt->dev_priv; int ret; - MMIO_RING_DFH(RING_IMR, D_ALL, 0, NULL, intel_vgpu_reg_imr_handler); + MMIO_RING_DFH(RING_IMR, D_ALL, F_CMD_ACCESS, NULL, + intel_vgpu_reg_imr_handler); MMIO_DFH(SDEIMR, D_ALL, 0, NULL, intel_vgpu_reg_imr_handler); MMIO_DFH(SDEIER, D_ALL, 0, NULL, intel_vgpu_reg_ier_handler); MMIO_DFH(SDEIIR, D_ALL, 0, NULL, intel_vgpu_reg_iir_handler); MMIO_D(SDEISR, D_ALL); - MMIO_RING_D(RING_HWSTAM, D_ALL); + MMIO_RING_DFH(RING_HWSTAM, D_ALL, F_CMD_ACCESS, NULL, NULL); - MMIO_GM(RENDER_HWS_PGA_GEN7, D_ALL, NULL, NULL); - MMIO_GM(BSD_HWS_PGA_GEN7, D_ALL, NULL, NULL); - MMIO_GM(BLT_HWS_PGA_GEN7, D_ALL, NULL, NULL); - MMIO_GM(VEBOX_HWS_PGA_GEN7, D_ALL, NULL, NULL); + MMIO_GM_RDR(RENDER_HWS_PGA_GEN7, D_ALL, NULL, NULL); + MMIO_GM_RDR(BSD_HWS_PGA_GEN7, D_ALL, NULL, NULL); + MMIO_GM_RDR(BLT_HWS_PGA_GEN7, D_ALL, NULL, NULL); + MMIO_GM_RDR(VEBOX_HWS_PGA_GEN7, D_ALL, NULL, NULL); #define RING_REG(base) (base + 0x28) - MMIO_RING_D(RING_REG, D_ALL); + MMIO_RING_DFH(RING_REG, D_ALL, F_CMD_ACCESS, NULL, NULL); #undef RING_REG #define RING_REG(base) (base + 0x134) - MMIO_RING_D(RING_REG, D_ALL); + MMIO_RING_DFH(RING_REG, D_ALL, F_CMD_ACCESS, NULL, NULL); #undef RING_REG - MMIO_GM(0x2148, D_ALL, NULL, NULL); - MMIO_GM(CCID, D_ALL, NULL, NULL); - MMIO_GM(0x12198, D_ALL, NULL, NULL); + MMIO_GM_RDR(0x2148, D_ALL, NULL, NULL); + MMIO_GM_RDR(CCID, D_ALL, NULL, NULL); + MMIO_GM_RDR(0x12198, D_ALL, NULL, NULL); MMIO_D(GEN7_CXT_SIZE, D_ALL); - MMIO_RING_D(RING_TAIL, D_ALL); - MMIO_RING_D(RING_HEAD, D_ALL); - MMIO_RING_D(RING_CTL, D_ALL); - MMIO_RING_D(RING_ACTHD, D_ALL); - MMIO_RING_GM(RING_START, D_ALL, NULL, NULL); + MMIO_RING_DFH(RING_TAIL, D_ALL, F_CMD_ACCESS, NULL, NULL); + MMIO_RING_DFH(RING_HEAD, D_ALL, F_CMD_ACCESS, NULL, NULL); + MMIO_RING_DFH(RING_CTL, D_ALL, F_CMD_ACCESS, NULL, NULL); + MMIO_RING_DFH(RING_ACTHD, D_ALL, F_CMD_ACCESS, NULL, NULL); + MMIO_RING_GM_RDR(RING_START, D_ALL, NULL, NULL); /* RING MODE */ #define RING_REG(base) (base + 0x29c) - MMIO_RING_DFH(RING_REG, D_ALL, F_MODE_MASK, NULL, ring_mode_mmio_write); + MMIO_RING_DFH(RING_REG, D_ALL, F_MODE_MASK | F_CMD_ACCESS, NULL, + ring_mode_mmio_write); #undef RING_REG - MMIO_RING_DFH(RING_MI_MODE, D_ALL, F_MODE_MASK, NULL, NULL); - MMIO_RING_DFH(RING_INSTPM, D_ALL, F_MODE_MASK, NULL, NULL); + MMIO_RING_DFH(RING_MI_MODE, D_ALL, F_MODE_MASK | F_CMD_ACCESS, + NULL, NULL); + MMIO_RING_DFH(RING_INSTPM, D_ALL, F_MODE_MASK | F_CMD_ACCESS, + NULL, NULL); MMIO_RING_DFH(RING_TIMESTAMP, D_ALL, F_CMD_ACCESS, ring_timestamp_mmio_read, NULL); MMIO_RING_DFH(RING_TIMESTAMP_UDW, D_ALL, F_CMD_ACCESS, ring_timestamp_mmio_read, NULL); - MMIO_DFH(GEN7_GT_MODE, D_ALL, F_MODE_MASK, NULL, NULL); - MMIO_DFH(CACHE_MODE_0_GEN7, D_ALL, F_MODE_MASK, NULL, NULL); + MMIO_DFH(GEN7_GT_MODE, D_ALL, F_MODE_MASK | F_CMD_ACCESS, NULL, NULL); + MMIO_DFH(CACHE_MODE_0_GEN7, D_ALL, F_MODE_MASK | F_CMD_ACCESS, + NULL, NULL); MMIO_DFH(CACHE_MODE_1, D_ALL, F_MODE_MASK | F_CMD_ACCESS, NULL, NULL); - - MMIO_DFH(0x20dc, D_ALL, F_MODE_MASK, NULL, NULL); - MMIO_DFH(_3D_CHICKEN3, D_ALL, F_MODE_MASK, NULL, NULL); - MMIO_DFH(0x2088, D_ALL, F_MODE_MASK, NULL, NULL); - MMIO_DFH(0x20e4, D_ALL, F_MODE_MASK, NULL, NULL); - MMIO_DFH(0x2470, D_ALL, F_MODE_MASK, NULL, NULL); - MMIO_D(GAM_ECOCHK, D_ALL); - MMIO_DFH(GEN7_COMMON_SLICE_CHICKEN1, D_ALL, F_MODE_MASK, NULL, NULL); + MMIO_DFH(CACHE_MODE_0, D_ALL, F_MODE_MASK | F_CMD_ACCESS, NULL, NULL); + MMIO_DFH(0x2124, D_ALL, F_MODE_MASK | F_CMD_ACCESS, NULL, NULL); + + MMIO_DFH(0x20dc, D_ALL, F_MODE_MASK | F_CMD_ACCESS, NULL, NULL); + MMIO_DFH(_3D_CHICKEN3, D_ALL, F_MODE_MASK | F_CMD_ACCESS, NULL, NULL); + MMIO_DFH(0x2088, D_ALL, F_MODE_MASK | F_CMD_ACCESS, NULL, NULL); + MMIO_DFH(0x20e4, D_ALL, F_MODE_MASK | F_CMD_ACCESS, NULL, NULL); + MMIO_DFH(0x2470, D_ALL, F_MODE_MASK | F_CMD_ACCESS, NULL, NULL); + MMIO_DFH(GAM_ECOCHK, D_ALL, F_CMD_ACCESS, NULL, NULL); + MMIO_DFH(GEN7_COMMON_SLICE_CHICKEN1, D_ALL, F_MODE_MASK | F_CMD_ACCESS, + NULL, NULL); MMIO_DFH(COMMON_SLICE_CHICKEN2, D_ALL, F_MODE_MASK | F_CMD_ACCESS, NULL, NULL); - MMIO_D(0x9030, D_ALL); - MMIO_D(0x20a0, D_ALL); - MMIO_D(0x2420, D_ALL); - MMIO_D(0x2430, D_ALL); - MMIO_D(0x2434, D_ALL); - MMIO_D(0x2438, D_ALL); - MMIO_D(0x243c, D_ALL); - MMIO_DFH(0x7018, D_ALL, F_MODE_MASK, NULL, NULL); + MMIO_DFH(0x9030, D_ALL, F_CMD_ACCESS, NULL, NULL); + MMIO_DFH(0x20a0, D_ALL, F_CMD_ACCESS, NULL, NULL); + MMIO_DFH(0x2420, D_ALL, F_CMD_ACCESS, NULL, NULL); + MMIO_DFH(0x2430, D_ALL, F_CMD_ACCESS, NULL, NULL); + MMIO_DFH(0x2434, D_ALL, F_CMD_ACCESS, NULL, NULL); + MMIO_DFH(0x2438, D_ALL, F_CMD_ACCESS, NULL, NULL); + MMIO_DFH(0x243c, D_ALL, F_CMD_ACCESS, NULL, NULL); + MMIO_DFH(0x7018, D_ALL, F_MODE_MASK | F_CMD_ACCESS, NULL, NULL); MMIO_DFH(HALF_SLICE_CHICKEN3, D_ALL, F_MODE_MASK | F_CMD_ACCESS, NULL, NULL); - MMIO_DFH(0xe100, D_ALL, F_MODE_MASK, NULL, NULL); + MMIO_DFH(GEN7_HALF_SLICE_CHICKEN1, D_ALL, F_MODE_MASK | F_CMD_ACCESS, NULL, NULL); /* display */ MMIO_F(0x60220, 0x20, 0, 0, 0, D_ALL, NULL, NULL); @@ -2022,8 +2160,8 @@ static int init_generic_mmio_info(struct intel_gvt *gvt) MMIO_D(FORCEWAKE_ACK, D_ALL); MMIO_D(GEN6_GT_CORE_STATUS, D_ALL); MMIO_D(GEN6_GT_THREAD_STATUS_REG, D_ALL); - MMIO_D(GTFIFODBG, D_ALL); - MMIO_D(GTFIFOCTL, D_ALL); + MMIO_DFH(GTFIFODBG, D_ALL, F_CMD_ACCESS, NULL, NULL); + MMIO_DFH(GTFIFOCTL, D_ALL, F_CMD_ACCESS, NULL, NULL); MMIO_DH(FORCEWAKE_MT, D_PRE_SKL, NULL, mul_force_wake_write); MMIO_DH(FORCEWAKE_ACK_HSW, D_HSW | D_BDW, NULL, NULL); MMIO_D(ECOBUS, D_ALL); @@ -2080,7 +2218,7 @@ static int init_generic_mmio_info(struct intel_gvt *gvt) MMIO_F(0x4f000, 0x90, 0, 0, 0, D_ALL, NULL, NULL); - MMIO_D(GEN6_PCODE_MAILBOX, D_PRE_SKL); + MMIO_D(GEN6_PCODE_MAILBOX, D_PRE_BDW); MMIO_D(GEN6_PCODE_DATA, D_ALL); MMIO_D(0x13812c, D_ALL); MMIO_DH(GEN7_ERR_INT, D_ALL, NULL, NULL); @@ -2159,36 +2297,35 @@ static int init_generic_mmio_info(struct intel_gvt *gvt) MMIO_D(0x1a054, D_ALL); MMIO_D(0x44070, D_ALL); - - MMIO_D(0x215c, D_HSW_PLUS); + MMIO_DFH(0x215c, D_HSW_PLUS, F_CMD_ACCESS, NULL, NULL); MMIO_DFH(0x2178, D_ALL, F_CMD_ACCESS, NULL, NULL); MMIO_DFH(0x217c, D_ALL, F_CMD_ACCESS, NULL, NULL); MMIO_DFH(0x12178, D_ALL, F_CMD_ACCESS, NULL, NULL); MMIO_DFH(0x1217c, D_ALL, F_CMD_ACCESS, NULL, NULL); - MMIO_F(0x2290, 8, 0, 0, 0, D_HSW_PLUS, NULL, NULL); - MMIO_D(GEN7_OACONTROL, D_HSW); + MMIO_F(0x2290, 8, F_CMD_ACCESS, 0, 0, D_HSW_PLUS, NULL, NULL); + MMIO_DFH(GEN7_OACONTROL, D_HSW, F_CMD_ACCESS, NULL, NULL); MMIO_D(0x2b00, D_BDW_PLUS); MMIO_D(0x2360, D_BDW_PLUS); - MMIO_F(0x5200, 32, 0, 0, 0, D_ALL, NULL, NULL); - MMIO_F(0x5240, 32, 0, 0, 0, D_ALL, NULL, NULL); - MMIO_F(0x5280, 16, 0, 0, 0, D_ALL, NULL, NULL); + MMIO_F(0x5200, 32, F_CMD_ACCESS, 0, 0, D_ALL, NULL, NULL); + MMIO_F(0x5240, 32, F_CMD_ACCESS, 0, 0, D_ALL, NULL, NULL); + MMIO_F(0x5280, 16, F_CMD_ACCESS, 0, 0, D_ALL, NULL, NULL); MMIO_DFH(0x1c17c, D_BDW_PLUS, F_CMD_ACCESS, NULL, NULL); MMIO_DFH(0x1c178, D_BDW_PLUS, F_CMD_ACCESS, NULL, NULL); - MMIO_D(BCS_SWCTRL, D_ALL); - - MMIO_F(HS_INVOCATION_COUNT, 8, 0, 0, 0, D_ALL, NULL, NULL); - MMIO_F(DS_INVOCATION_COUNT, 8, 0, 0, 0, D_ALL, NULL, NULL); - MMIO_F(IA_VERTICES_COUNT, 8, 0, 0, 0, D_ALL, NULL, NULL); - MMIO_F(IA_PRIMITIVES_COUNT, 8, 0, 0, 0, D_ALL, NULL, NULL); - MMIO_F(VS_INVOCATION_COUNT, 8, 0, 0, 0, D_ALL, NULL, NULL); - MMIO_F(GS_INVOCATION_COUNT, 8, 0, 0, 0, D_ALL, NULL, NULL); - MMIO_F(GS_PRIMITIVES_COUNT, 8, 0, 0, 0, D_ALL, NULL, NULL); - MMIO_F(CL_INVOCATION_COUNT, 8, 0, 0, 0, D_ALL, NULL, NULL); - MMIO_F(CL_PRIMITIVES_COUNT, 8, 0, 0, 0, D_ALL, NULL, NULL); - MMIO_F(PS_INVOCATION_COUNT, 8, 0, 0, 0, D_ALL, NULL, NULL); - MMIO_F(PS_DEPTH_COUNT, 8, 0, 0, 0, D_ALL, NULL, NULL); + MMIO_DFH(BCS_SWCTRL, D_ALL, F_CMD_ACCESS, NULL, NULL); + + MMIO_F(HS_INVOCATION_COUNT, 8, F_CMD_ACCESS, 0, 0, D_ALL, NULL, NULL); + MMIO_F(DS_INVOCATION_COUNT, 8, F_CMD_ACCESS, 0, 0, D_ALL, NULL, NULL); + MMIO_F(IA_VERTICES_COUNT, 8, F_CMD_ACCESS, 0, 0, D_ALL, NULL, NULL); + MMIO_F(IA_PRIMITIVES_COUNT, 8, F_CMD_ACCESS, 0, 0, D_ALL, NULL, NULL); + MMIO_F(VS_INVOCATION_COUNT, 8, F_CMD_ACCESS, 0, 0, D_ALL, NULL, NULL); + MMIO_F(GS_INVOCATION_COUNT, 8, F_CMD_ACCESS, 0, 0, D_ALL, NULL, NULL); + MMIO_F(GS_PRIMITIVES_COUNT, 8, F_CMD_ACCESS, 0, 0, D_ALL, NULL, NULL); + MMIO_F(CL_INVOCATION_COUNT, 8, F_CMD_ACCESS, 0, 0, D_ALL, NULL, NULL); + MMIO_F(CL_PRIMITIVES_COUNT, 8, F_CMD_ACCESS, 0, 0, D_ALL, NULL, NULL); + MMIO_F(PS_INVOCATION_COUNT, 8, F_CMD_ACCESS, 0, 0, D_ALL, NULL, NULL); + MMIO_F(PS_DEPTH_COUNT, 8, F_CMD_ACCESS, 0, 0, D_ALL, NULL, NULL); MMIO_DH(0x4260, D_BDW_PLUS, NULL, gvt_reg_tlb_control_handler); MMIO_DH(0x4264, D_BDW_PLUS, NULL, gvt_reg_tlb_control_handler); MMIO_DH(0x4268, D_BDW_PLUS, NULL, gvt_reg_tlb_control_handler); @@ -2196,6 +2333,17 @@ static int init_generic_mmio_info(struct intel_gvt *gvt) MMIO_DH(0x4270, D_BDW_PLUS, NULL, gvt_reg_tlb_control_handler); MMIO_DFH(0x4094, D_BDW_PLUS, F_CMD_ACCESS, NULL, NULL); + MMIO_DFH(ARB_MODE, D_ALL, F_MODE_MASK | F_CMD_ACCESS, NULL, NULL); + MMIO_RING_GM_RDR(RING_BBADDR, D_ALL, NULL, NULL); + MMIO_DFH(0x2220, D_ALL, F_CMD_ACCESS, NULL, NULL); + MMIO_DFH(0x12220, D_ALL, F_CMD_ACCESS, NULL, NULL); + MMIO_DFH(0x22220, D_ALL, F_CMD_ACCESS, NULL, NULL); + MMIO_RING_DFH(RING_SYNC_1, D_ALL, F_CMD_ACCESS, NULL, NULL); + MMIO_RING_DFH(RING_SYNC_0, D_ALL, F_CMD_ACCESS, NULL, NULL); + MMIO_DFH(0x22178, D_BDW_PLUS, F_CMD_ACCESS, NULL, NULL); + MMIO_DFH(0x1a178, D_BDW_PLUS, F_CMD_ACCESS, NULL, NULL); + MMIO_DFH(0x1a17c, D_BDW_PLUS, F_CMD_ACCESS, NULL, NULL); + MMIO_DFH(0x2217c, D_BDW_PLUS, F_CMD_ACCESS, NULL, NULL); return 0; } @@ -2204,7 +2352,7 @@ static int init_broadwell_mmio_info(struct intel_gvt *gvt) struct drm_i915_private *dev_priv = gvt->dev_priv; int ret; - MMIO_DH(RING_IMR(GEN8_BSD2_RING_BASE), D_BDW_PLUS, NULL, + MMIO_DFH(RING_IMR(GEN8_BSD2_RING_BASE), D_BDW_PLUS, F_CMD_ACCESS, NULL, intel_vgpu_reg_imr_handler); MMIO_DH(GEN8_GT_IMR(0), D_BDW_PLUS, NULL, intel_vgpu_reg_imr_handler); @@ -2269,24 +2417,31 @@ static int init_broadwell_mmio_info(struct intel_gvt *gvt) MMIO_DH(GEN8_MASTER_IRQ, D_BDW_PLUS, NULL, intel_vgpu_reg_master_irq_handler); - MMIO_D(RING_HWSTAM(GEN8_BSD2_RING_BASE), D_BDW_PLUS); - MMIO_D(0x1c134, D_BDW_PLUS); - - MMIO_D(RING_TAIL(GEN8_BSD2_RING_BASE), D_BDW_PLUS); - MMIO_D(RING_HEAD(GEN8_BSD2_RING_BASE), D_BDW_PLUS); - MMIO_GM(RING_START(GEN8_BSD2_RING_BASE), D_BDW_PLUS, NULL, NULL); - MMIO_D(RING_CTL(GEN8_BSD2_RING_BASE), D_BDW_PLUS); - MMIO_D(RING_ACTHD(GEN8_BSD2_RING_BASE), D_BDW_PLUS); - MMIO_D(RING_ACTHD_UDW(GEN8_BSD2_RING_BASE), D_BDW_PLUS); - MMIO_DFH(0x1c29c, D_BDW_PLUS, F_MODE_MASK, NULL, ring_mode_mmio_write); - MMIO_DFH(RING_MI_MODE(GEN8_BSD2_RING_BASE), D_BDW_PLUS, F_MODE_MASK, - NULL, NULL); - MMIO_DFH(RING_INSTPM(GEN8_BSD2_RING_BASE), D_BDW_PLUS, F_MODE_MASK, - NULL, NULL); + MMIO_DFH(RING_HWSTAM(GEN8_BSD2_RING_BASE), D_BDW_PLUS, + F_CMD_ACCESS, NULL, NULL); + MMIO_DFH(0x1c134, D_BDW_PLUS, F_CMD_ACCESS, NULL, NULL); + + MMIO_DFH(RING_TAIL(GEN8_BSD2_RING_BASE), D_BDW_PLUS, F_CMD_ACCESS, + NULL, NULL); + MMIO_DFH(RING_HEAD(GEN8_BSD2_RING_BASE), D_BDW_PLUS, + F_CMD_ACCESS, NULL, NULL); + MMIO_GM_RDR(RING_START(GEN8_BSD2_RING_BASE), D_BDW_PLUS, NULL, NULL); + MMIO_DFH(RING_CTL(GEN8_BSD2_RING_BASE), D_BDW_PLUS, F_CMD_ACCESS, + NULL, NULL); + MMIO_DFH(RING_ACTHD(GEN8_BSD2_RING_BASE), D_BDW_PLUS, + F_CMD_ACCESS, NULL, NULL); + MMIO_DFH(RING_ACTHD_UDW(GEN8_BSD2_RING_BASE), D_BDW_PLUS, + F_CMD_ACCESS, NULL, NULL); + MMIO_DFH(0x1c29c, D_BDW_PLUS, F_MODE_MASK | F_CMD_ACCESS, NULL, + ring_mode_mmio_write); + MMIO_DFH(RING_MI_MODE(GEN8_BSD2_RING_BASE), D_BDW_PLUS, + F_MODE_MASK | F_CMD_ACCESS, NULL, NULL); + MMIO_DFH(RING_INSTPM(GEN8_BSD2_RING_BASE), D_BDW_PLUS, + F_MODE_MASK | F_CMD_ACCESS, NULL, NULL); MMIO_DFH(RING_TIMESTAMP(GEN8_BSD2_RING_BASE), D_BDW_PLUS, F_CMD_ACCESS, ring_timestamp_mmio_read, NULL); - MMIO_RING_D(RING_ACTHD_UDW, D_BDW_PLUS); + MMIO_RING_DFH(RING_ACTHD_UDW, D_BDW_PLUS, F_CMD_ACCESS, NULL, NULL); #define RING_REG(base) (base + 0xd0) MMIO_RING_F(RING_REG, 4, F_RO, 0, @@ -2303,13 +2458,16 @@ static int init_broadwell_mmio_info(struct intel_gvt *gvt) #undef RING_REG #define RING_REG(base) (base + 0x234) - MMIO_RING_F(RING_REG, 8, F_RO, 0, ~0, D_BDW_PLUS, NULL, NULL); - MMIO_F(RING_REG(GEN8_BSD2_RING_BASE), 4, F_RO, 0, ~0LL, D_BDW_PLUS, NULL, NULL); + MMIO_RING_F(RING_REG, 8, F_RO | F_CMD_ACCESS, 0, ~0, D_BDW_PLUS, + NULL, NULL); + MMIO_F(RING_REG(GEN8_BSD2_RING_BASE), 4, F_RO | F_CMD_ACCESS, 0, + ~0LL, D_BDW_PLUS, NULL, NULL); #undef RING_REG #define RING_REG(base) (base + 0x244) - MMIO_RING_D(RING_REG, D_BDW_PLUS); - MMIO_D(RING_REG(GEN8_BSD2_RING_BASE), D_BDW_PLUS); + MMIO_RING_DFH(RING_REG, D_BDW_PLUS, F_CMD_ACCESS, NULL, NULL); + MMIO_DFH(RING_REG(GEN8_BSD2_RING_BASE), D_BDW_PLUS, F_CMD_ACCESS, + NULL, NULL); #undef RING_REG #define RING_REG(base) (base + 0x370) @@ -2331,6 +2489,8 @@ static int init_broadwell_mmio_info(struct intel_gvt *gvt) MMIO_D(GEN7_MISCCPCTL, D_BDW_PLUS); MMIO_D(0x1c054, D_BDW_PLUS); + MMIO_DH(GEN6_PCODE_MAILBOX, D_BDW_PLUS, NULL, mailbox_write); + MMIO_D(GEN8_PRIVATE_PAT_LO, D_BDW_PLUS); MMIO_D(GEN8_PRIVATE_PAT_HI, D_BDW_PLUS); @@ -2341,14 +2501,14 @@ static int init_broadwell_mmio_info(struct intel_gvt *gvt) MMIO_F(RING_REG(GEN8_BSD2_RING_BASE), 32, 0, 0, 0, D_BDW_PLUS, NULL, NULL); #undef RING_REG - MMIO_RING_GM(RING_HWS_PGA, D_BDW_PLUS, NULL, NULL); - MMIO_GM(0x1c080, D_BDW_PLUS, NULL, NULL); + MMIO_RING_GM_RDR(RING_HWS_PGA, D_BDW_PLUS, NULL, NULL); + MMIO_GM_RDR(RING_HWS_PGA(GEN8_BSD2_RING_BASE), D_BDW_PLUS, NULL, NULL); MMIO_DFH(HDC_CHICKEN0, D_BDW_PLUS, F_MODE_MASK | F_CMD_ACCESS, NULL, NULL); - MMIO_D(CHICKEN_PIPESL_1(PIPE_A), D_BDW); - MMIO_D(CHICKEN_PIPESL_1(PIPE_B), D_BDW); - MMIO_D(CHICKEN_PIPESL_1(PIPE_C), D_BDW); + MMIO_D(CHICKEN_PIPESL_1(PIPE_A), D_BDW_PLUS); + MMIO_D(CHICKEN_PIPESL_1(PIPE_B), D_BDW_PLUS); + MMIO_D(CHICKEN_PIPESL_1(PIPE_C), D_BDW_PLUS); MMIO_D(WM_MISC, D_BDW); MMIO_D(BDW_EDP_PSR_BASE, D_BDW); @@ -2362,27 +2522,31 @@ static int init_broadwell_mmio_info(struct intel_gvt *gvt) MMIO_D(GEN8_EU_DISABLE1, D_BDW_PLUS); MMIO_D(GEN8_EU_DISABLE2, D_BDW_PLUS); - MMIO_D(0xfdc, D_BDW); - MMIO_DFH(GEN8_ROW_CHICKEN, D_BDW_PLUS, F_CMD_ACCESS, NULL, NULL); - MMIO_D(GEN7_ROW_CHICKEN2, D_BDW_PLUS); - MMIO_D(GEN8_UCGCTL6, D_BDW_PLUS); + MMIO_D(0xfdc, D_BDW_PLUS); + MMIO_DFH(GEN8_ROW_CHICKEN, D_BDW_PLUS, F_MODE_MASK | F_CMD_ACCESS, + NULL, NULL); + MMIO_DFH(GEN7_ROW_CHICKEN2, D_BDW_PLUS, F_MODE_MASK | F_CMD_ACCESS, + NULL, NULL); + MMIO_DFH(GEN8_UCGCTL6, D_BDW_PLUS, F_CMD_ACCESS, NULL, NULL); - MMIO_D(0xb1f0, D_BDW); - MMIO_D(0xb1c0, D_BDW); + MMIO_DFH(0xb1f0, D_BDW, F_CMD_ACCESS, NULL, NULL); + MMIO_DFH(0xb1c0, D_BDW, F_CMD_ACCESS, NULL, NULL); MMIO_DFH(GEN8_L3SQCREG4, D_BDW_PLUS, F_CMD_ACCESS, NULL, NULL); - MMIO_D(0xb100, D_BDW); - MMIO_D(0xb10c, D_BDW); + MMIO_DFH(0xb100, D_BDW, F_CMD_ACCESS, NULL, NULL); + MMIO_DFH(0xb10c, D_BDW, F_CMD_ACCESS, NULL, NULL); MMIO_D(0xb110, D_BDW); - MMIO_DFH(0x24d0, D_BDW_PLUS, F_CMD_ACCESS, NULL, NULL); - MMIO_DFH(0x24d4, D_BDW_PLUS, F_CMD_ACCESS, NULL, NULL); - MMIO_DFH(0x24d8, D_BDW_PLUS, F_CMD_ACCESS, NULL, NULL); - MMIO_DFH(0x24dc, D_BDW_PLUS, F_CMD_ACCESS, NULL, NULL); + MMIO_F(0x24d0, 48, F_CMD_ACCESS, 0, 0, D_BDW_PLUS, + NULL, force_nonpriv_write); + + MMIO_D(0x22040, D_BDW_PLUS); + MMIO_D(0x44484, D_BDW_PLUS); + MMIO_D(0x4448c, D_BDW_PLUS); - MMIO_D(0x83a4, D_BDW); + MMIO_DFH(0x83a4, D_BDW, F_CMD_ACCESS, NULL, NULL); MMIO_D(GEN8_L3_LRA_1_GPGPU, D_BDW_PLUS); - MMIO_D(0x8430, D_BDW); + MMIO_DFH(0x8430, D_BDW, F_CMD_ACCESS, NULL, NULL); MMIO_D(0x110000, D_BDW_PLUS); @@ -2394,10 +2558,19 @@ static int init_broadwell_mmio_info(struct intel_gvt *gvt) MMIO_DFH(0xe194, D_BDW_PLUS, F_MODE_MASK | F_CMD_ACCESS, NULL, NULL); MMIO_DFH(0xe188, D_BDW_PLUS, F_MODE_MASK | F_CMD_ACCESS, NULL, NULL); MMIO_DFH(HALF_SLICE_CHICKEN2, D_BDW_PLUS, F_MODE_MASK | F_CMD_ACCESS, NULL, NULL); - MMIO_DFH(0x2580, D_BDW_PLUS, F_MODE_MASK, NULL, NULL); - - MMIO_D(0x2248, D_BDW); - + MMIO_DFH(0x2580, D_BDW_PLUS, F_MODE_MASK | F_CMD_ACCESS, NULL, NULL); + + MMIO_DFH(0x2248, D_BDW, F_CMD_ACCESS, NULL, NULL); + + MMIO_DFH(0xe220, D_BDW_PLUS, F_CMD_ACCESS, NULL, NULL); + MMIO_DFH(0xe230, D_BDW_PLUS, F_CMD_ACCESS, NULL, NULL); + MMIO_DFH(0xe240, D_BDW_PLUS, F_CMD_ACCESS, NULL, NULL); + MMIO_DFH(0xe260, D_BDW_PLUS, F_CMD_ACCESS, NULL, NULL); + MMIO_DFH(0xe270, D_BDW_PLUS, F_CMD_ACCESS, NULL, NULL); + MMIO_DFH(0xe280, D_BDW_PLUS, F_CMD_ACCESS, NULL, NULL); + MMIO_DFH(0xe2a0, D_BDW_PLUS, F_CMD_ACCESS, NULL, NULL); + MMIO_DFH(0xe2b0, D_BDW_PLUS, F_CMD_ACCESS, NULL, NULL); + MMIO_DFH(0xe2c0, D_BDW_PLUS, F_CMD_ACCESS, NULL, NULL); return 0; } @@ -2420,7 +2593,6 @@ static int init_skl_mmio_info(struct intel_gvt *gvt) MMIO_D(HSW_PWR_WELL_BIOS, D_SKL); MMIO_DH(HSW_PWR_WELL_DRIVER, D_SKL, NULL, skl_power_well_ctl_write); - MMIO_DH(GEN6_PCODE_MAILBOX, D_SKL, NULL, mailbox_write); MMIO_D(0xa210, D_SKL_PLUS); MMIO_D(GEN9_MEDIA_PG_IDLE_HYSTERESIS, D_SKL_PLUS); MMIO_D(GEN9_RENDER_PG_IDLE_HYSTERESIS, D_SKL_PLUS); @@ -2578,16 +2750,16 @@ static int init_skl_mmio_info(struct intel_gvt *gvt) MMIO_F(0xb020, 0x80, F_CMD_ACCESS, 0, 0, D_SKL, NULL, NULL); MMIO_D(0xd08, D_SKL); - MMIO_D(0x20e0, D_SKL); - MMIO_D(0x20ec, D_SKL); + MMIO_DFH(0x20e0, D_SKL, F_MODE_MASK, NULL, NULL); + MMIO_DFH(0x20ec, D_SKL, F_MODE_MASK | F_CMD_ACCESS, NULL, NULL); /* TRTT */ - MMIO_D(0x4de0, D_SKL); - MMIO_D(0x4de4, D_SKL); - MMIO_D(0x4de8, D_SKL); - MMIO_D(0x4dec, D_SKL); - MMIO_D(0x4df0, D_SKL); - MMIO_DH(0x4df4, D_SKL, NULL, gen9_trtte_write); + MMIO_DFH(0x4de0, D_SKL, F_CMD_ACCESS, NULL, NULL); + MMIO_DFH(0x4de4, D_SKL, F_CMD_ACCESS, NULL, NULL); + MMIO_DFH(0x4de8, D_SKL, F_CMD_ACCESS, NULL, NULL); + MMIO_DFH(0x4dec, D_SKL, F_CMD_ACCESS, NULL, NULL); + MMIO_DFH(0x4df0, D_SKL, F_CMD_ACCESS, NULL, NULL); + MMIO_DFH(0x4df4, D_SKL, F_CMD_ACCESS, NULL, gen9_trtte_write); MMIO_DH(0x4dfc, D_SKL, NULL, gen9_trtt_chicken_write); MMIO_D(0x45008, D_SKL); @@ -2611,7 +2783,7 @@ static int init_skl_mmio_info(struct intel_gvt *gvt) MMIO_D(0x65f08, D_SKL); MMIO_D(0x320f0, D_SKL); - MMIO_D(_REG_VCS2_EXCC, D_SKL); + MMIO_DFH(_REG_VCS2_EXCC, D_SKL, F_CMD_ACCESS, NULL, NULL); MMIO_D(0x70034, D_SKL); MMIO_D(0x71034, D_SKL); MMIO_D(0x72034, D_SKL); @@ -2624,6 +2796,9 @@ static int init_skl_mmio_info(struct intel_gvt *gvt) MMIO_D(_PLANE_KEYMSK_1(PIPE_C), D_SKL); MMIO_D(0x44500, D_SKL); + MMIO_DFH(GEN9_CSFE_CHICKEN1_RCS, D_SKL_PLUS, F_CMD_ACCESS, NULL, NULL); + MMIO_DFH(GEN8_HDC_CHICKEN1, D_SKL, F_MODE_MASK | F_CMD_ACCESS, + NULL, NULL); return 0; } diff --git a/drivers/gpu/drm/i915/gvt/kvmgt.c b/drivers/gpu/drm/i915/gvt/kvmgt.c index 0f7f5d97f582..84d801638ede 100644 --- a/drivers/gpu/drm/i915/gvt/kvmgt.c +++ b/drivers/gpu/drm/i915/gvt/kvmgt.c @@ -96,10 +96,10 @@ static int gvt_dma_map_iova(struct intel_vgpu *vgpu, kvm_pfn_t pfn, struct device *dev = &vgpu->gvt->dev_priv->drm.pdev->dev; dma_addr_t daddr; - page = pfn_to_page(pfn); - if (is_error_page(page)) + if (unlikely(!pfn_valid(pfn))) return -EFAULT; + page = pfn_to_page(pfn); daddr = dma_map_page(dev, page, 0, PAGE_SIZE, PCI_DMA_BIDIRECTIONAL); if (dma_mapping_error(dev, daddr)) @@ -295,10 +295,10 @@ static ssize_t description_show(struct kobject *kobj, struct device *dev, return 0; return sprintf(buf, "low_gm_size: %dMB\nhigh_gm_size: %dMB\n" - "fence: %d\n", - BYTES_TO_MB(type->low_gm_size), - BYTES_TO_MB(type->high_gm_size), - type->fence); + "fence: %d\nresolution: %s\n", + BYTES_TO_MB(type->low_gm_size), + BYTES_TO_MB(type->high_gm_size), + type->fence, vgpu_edid_str(type->resolution)); } static MDEV_TYPE_ATTR_RO(available_instances); diff --git a/drivers/gpu/drm/i915/gvt/mmio.c b/drivers/gpu/drm/i915/gvt/mmio.c index 4df078bc5d04..60b698cb8365 100644 --- a/drivers/gpu/drm/i915/gvt/mmio.c +++ b/drivers/gpu/drm/i915/gvt/mmio.c @@ -57,6 +57,58 @@ int intel_vgpu_gpa_to_mmio_offset(struct intel_vgpu *vgpu, u64 gpa) (reg >= gvt->device_info.gtt_start_offset \ && reg < gvt->device_info.gtt_start_offset + gvt_ggtt_sz(gvt)) +static void failsafe_emulate_mmio_rw(struct intel_vgpu *vgpu, uint64_t pa, + void *p_data, unsigned int bytes, bool read) +{ + struct intel_gvt *gvt = NULL; + void *pt = NULL; + unsigned int offset = 0; + + if (!vgpu || !p_data) + return; + + gvt = vgpu->gvt; + mutex_lock(&gvt->lock); + offset = intel_vgpu_gpa_to_mmio_offset(vgpu, pa); + if (reg_is_mmio(gvt, offset)) { + if (read) + intel_vgpu_default_mmio_read(vgpu, offset, p_data, + bytes); + else + intel_vgpu_default_mmio_write(vgpu, offset, p_data, + bytes); + } else if (reg_is_gtt(gvt, offset) && + vgpu->gtt.ggtt_mm->virtual_page_table) { + offset -= gvt->device_info.gtt_start_offset; + pt = vgpu->gtt.ggtt_mm->virtual_page_table + offset; + if (read) + memcpy(p_data, pt, bytes); + else + memcpy(pt, p_data, bytes); + + } else if (atomic_read(&vgpu->gtt.n_write_protected_guest_page)) { + struct intel_vgpu_guest_page *gp; + + /* Since we enter the failsafe mode early during guest boot, + * guest may not have chance to set up its ppgtt table, so + * there should not be any wp pages for guest. Keep the wp + * related code here in case we need to handle it in furture. + */ + gp = intel_vgpu_find_guest_page(vgpu, pa >> PAGE_SHIFT); + if (gp) { + /* remove write protection to prevent furture traps */ + intel_vgpu_clean_guest_page(vgpu, gp); + if (read) + intel_gvt_hypervisor_read_gpa(vgpu, pa, + p_data, bytes); + else + intel_gvt_hypervisor_write_gpa(vgpu, pa, + p_data, bytes); + } + } + mutex_unlock(&gvt->lock); +} + /** * intel_vgpu_emulate_mmio_read - emulate MMIO read * @vgpu: a vGPU @@ -75,6 +127,11 @@ int intel_vgpu_emulate_mmio_read(struct intel_vgpu *vgpu, uint64_t pa, unsigned int offset = 0; int ret = -EINVAL; + + if (vgpu->failsafe) { + failsafe_emulate_mmio_rw(vgpu, pa, p_data, bytes, true); + return 0; + } mutex_lock(&gvt->lock); if (atomic_read(&vgpu->gtt.n_write_protected_guest_page)) { @@ -188,6 +245,11 @@ int intel_vgpu_emulate_mmio_write(struct intel_vgpu *vgpu, uint64_t pa, u32 old_vreg = 0, old_sreg = 0; int ret = -EINVAL; + if (vgpu->failsafe) { + failsafe_emulate_mmio_rw(vgpu, pa, p_data, bytes, false); + return 0; + } + mutex_lock(&gvt->lock); if (atomic_read(&vgpu->gtt.n_write_protected_guest_page)) { @@ -236,7 +298,7 @@ int intel_vgpu_emulate_mmio_write(struct intel_vgpu *vgpu, uint64_t pa, mmio = intel_gvt_find_mmio_info(gvt, rounddown(offset, 4)); if (!mmio && !vgpu->mmio.disable_warn_untrack) - gvt_err("vgpu%d: write untracked MMIO %x len %d val %x\n", + gvt_dbg_mmio("vgpu%d: write untracked MMIO %x len %d val %x\n", vgpu->id, offset, bytes, *(u32 *)p_data); if (!intel_gvt_mmio_is_unalign(gvt, offset)) { @@ -322,6 +384,8 @@ void intel_vgpu_reset_mmio(struct intel_vgpu *vgpu) /* set the bit 0:2(Core C-State ) to C0 */ vgpu_vreg(vgpu, GEN6_GT_CORE_STATUS) = 0; + + vgpu->mmio.disable_warn_untrack = false; } /** diff --git a/drivers/gpu/drm/i915/gvt/opregion.c b/drivers/gpu/drm/i915/gvt/opregion.c index d9fb41ab7119..5d1caf9daba9 100644 --- a/drivers/gpu/drm/i915/gvt/opregion.c +++ b/drivers/gpu/drm/i915/gvt/opregion.c @@ -27,7 +27,6 @@ static int init_vgpu_opregion(struct intel_vgpu *vgpu, u32 gpa) { - void __iomem *host_va = vgpu->gvt->opregion.opregion_va; u8 *buf; int i; @@ -43,8 +42,8 @@ static int init_vgpu_opregion(struct intel_vgpu *vgpu, u32 gpa) if (!vgpu_opregion(vgpu)->va) return -ENOMEM; - memcpy_fromio(vgpu_opregion(vgpu)->va, host_va, - INTEL_GVT_OPREGION_SIZE); + memcpy(vgpu_opregion(vgpu)->va, vgpu->gvt->opregion.opregion_va, + INTEL_GVT_OPREGION_SIZE); for (i = 0; i < INTEL_GVT_OPREGION_PAGES; i++) vgpu_opregion(vgpu)->gfn[i] = (gpa >> PAGE_SHIFT) + i; diff --git a/drivers/gpu/drm/i915/gvt/render.c b/drivers/gpu/drm/i915/gvt/render.c index 2b3a642284b6..73f052a4f424 100644 --- a/drivers/gpu/drm/i915/gvt/render.c +++ b/drivers/gpu/drm/i915/gvt/render.c @@ -53,6 +53,14 @@ static struct render_mmio gen8_render_mmio_list[] = { {RCS, _MMIO(0x24d4), 0, false}, {RCS, _MMIO(0x24d8), 0, false}, {RCS, _MMIO(0x24dc), 0, false}, + {RCS, _MMIO(0x24e0), 0, false}, + {RCS, _MMIO(0x24e4), 0, false}, + {RCS, _MMIO(0x24e8), 0, false}, + {RCS, _MMIO(0x24ec), 0, false}, + {RCS, _MMIO(0x24f0), 0, false}, + {RCS, _MMIO(0x24f4), 0, false}, + {RCS, _MMIO(0x24f8), 0, false}, + {RCS, _MMIO(0x24fc), 0, false}, {RCS, _MMIO(0x7004), 0xffff, true}, {RCS, _MMIO(0x7008), 0xffff, true}, {RCS, _MMIO(0x7000), 0xffff, true}, @@ -76,6 +84,14 @@ static struct render_mmio gen9_render_mmio_list[] = { {RCS, _MMIO(0x24d4), 0, false}, {RCS, _MMIO(0x24d8), 0, false}, {RCS, _MMIO(0x24dc), 0, false}, + {RCS, _MMIO(0x24e0), 0, false}, + {RCS, _MMIO(0x24e4), 0, false}, + {RCS, _MMIO(0x24e8), 0, false}, + {RCS, _MMIO(0x24ec), 0, false}, + {RCS, _MMIO(0x24f0), 0, false}, + {RCS, _MMIO(0x24f4), 0, false}, + {RCS, _MMIO(0x24f8), 0, false}, + {RCS, _MMIO(0x24fc), 0, false}, {RCS, _MMIO(0x7004), 0xffff, true}, {RCS, _MMIO(0x7008), 0xffff, true}, {RCS, _MMIO(0x7000), 0xffff, true}, diff --git a/drivers/gpu/drm/i915/gvt/scheduler.c b/drivers/gpu/drm/i915/gvt/scheduler.c index d6b6d0efdd1a..d3a56c949025 100644 --- a/drivers/gpu/drm/i915/gvt/scheduler.c +++ b/drivers/gpu/drm/i915/gvt/scheduler.c @@ -139,6 +139,9 @@ static int shadow_context_status_change(struct notifier_block *nb, struct intel_vgpu_workload *workload = scheduler->current_workload[req->engine->id]; + if (unlikely(!workload)) + return NOTIFY_OK; + switch (action) { case INTEL_CONTEXT_SCHEDULE_IN: intel_gvt_load_render_mmio(workload->vgpu, @@ -148,6 +151,15 @@ static int shadow_context_status_change(struct notifier_block *nb, case INTEL_CONTEXT_SCHEDULE_OUT: intel_gvt_restore_render_mmio(workload->vgpu, workload->ring_id); + /* If the status is -EINPROGRESS means this workload + * doesn't meet any issue during dispatching so when + * get the SCHEDULE_OUT set the status to be zero for + * good. If the status is NOT -EINPROGRESS means there + * is something wrong happened during dispatching and + * the status should not be set to zero + */ + if (workload->status == -EINPROGRESS) + workload->status = 0; atomic_set(&workload->shadow_ctx_active, 0); break; default: @@ -359,15 +371,23 @@ static void complete_current_workload(struct intel_gvt *gvt, int ring_id) workload = scheduler->current_workload[ring_id]; vgpu = workload->vgpu; - if (!workload->status && !vgpu->resetting) { + /* For the workload w/ request, needs to wait for the context + * switch to make sure request is completed. + * For the workload w/o request, directly complete the workload. + */ + if (workload->req) { wait_event(workload->shadow_ctx_status_wq, !atomic_read(&workload->shadow_ctx_active)); - update_guest_context(workload); + i915_gem_request_put(fetch_and_zero(&workload->req)); + + if (!workload->status && !vgpu->resetting) { + update_guest_context(workload); - for_each_set_bit(event, workload->pending_events, - INTEL_GVT_EVENT_MAX) - intel_vgpu_trigger_virtual_event(vgpu, event); + for_each_set_bit(event, workload->pending_events, + INTEL_GVT_EVENT_MAX) + intel_vgpu_trigger_virtual_event(vgpu, event); + } } gvt_dbg_sched("ring id %d complete workload %p status %d\n", @@ -397,7 +417,6 @@ static int workload_thread(void *priv) int ring_id = p->ring_id; struct intel_gvt_workload_scheduler *scheduler = &gvt->scheduler; struct intel_vgpu_workload *workload = NULL; - long lret; int ret; bool need_force_wake = IS_SKYLAKE(gvt->dev_priv); DEFINE_WAIT_FUNC(wait, woken_wake_function); @@ -446,23 +465,24 @@ static int workload_thread(void *priv) gvt_dbg_sched("ring id %d wait workload %p\n", workload->ring_id, workload); - - lret = i915_wait_request(workload->req, +retry: + i915_wait_request(workload->req, 0, MAX_SCHEDULE_TIMEOUT); - if (lret < 0) { - workload->status = lret; - gvt_err("fail to wait workload, skip\n"); - } else { - workload->status = 0; + /* I915 has replay mechanism and a request will be replayed + * if there is i915 reset. So the seqno will be updated anyway. + * If the seqno is not updated yet after waiting, which means + * the replay may still be in progress and we can wait again. + */ + if (!i915_gem_request_completed(workload->req)) { + gvt_dbg_sched("workload %p not completed, wait again\n", + workload); + goto retry; } complete: gvt_dbg_sched("will complete workload %p, status: %d\n", workload, workload->status); - if (workload->req) - i915_gem_request_put(fetch_and_zero(&workload->req)); - complete_current_workload(gvt, ring_id); if (need_force_wake) diff --git a/drivers/gpu/drm/i915/gvt/vgpu.c b/drivers/gpu/drm/i915/gvt/vgpu.c index 95a97aa0051e..41cfa5ccae84 100644 --- a/drivers/gpu/drm/i915/gvt/vgpu.c +++ b/drivers/gpu/drm/i915/gvt/vgpu.c @@ -64,6 +64,20 @@ void populate_pvinfo_page(struct intel_vgpu *vgpu) WARN_ON(sizeof(struct vgt_if) != VGT_PVINFO_SIZE); } +static struct { + unsigned int low_mm; + unsigned int high_mm; + unsigned int fence; + enum intel_vgpu_edid edid; + char *name; +} vgpu_types[] = { +/* Fixed vGPU type table */ + { MB_TO_BYTES(64), MB_TO_BYTES(512), 4, GVT_EDID_1024_768, "8" }, + { MB_TO_BYTES(128), MB_TO_BYTES(512), 4, GVT_EDID_1920_1200, "4" }, + { MB_TO_BYTES(256), MB_TO_BYTES(1024), 4, GVT_EDID_1920_1200, "2" }, + { MB_TO_BYTES(512), MB_TO_BYTES(2048), 4, GVT_EDID_1920_1200, "1" }, +}; + /** * intel_gvt_init_vgpu_types - initialize vGPU type list * @gvt : GVT device @@ -78,9 +92,8 @@ int intel_gvt_init_vgpu_types(struct intel_gvt *gvt) unsigned int min_low; /* vGPU type name is defined as GVTg_Vx_y which contains - * physical GPU generation type and 'y' means maximum vGPU - * instances user can create on one physical GPU for this - * type. + * physical GPU generation type (e.g V4 as BDW server, V5 as + * SKL server). * * Depend on physical SKU resource, might see vGPU types like * GVTg_V4_8, GVTg_V4_4, GVTg_V4_2, etc. We can create @@ -92,7 +105,7 @@ int intel_gvt_init_vgpu_types(struct intel_gvt *gvt) */ low_avail = gvt_aperture_sz(gvt) - HOST_LOW_GM_SIZE; high_avail = gvt_hidden_sz(gvt) - HOST_HIGH_GM_SIZE; - num_types = 4; + num_types = sizeof(vgpu_types) / sizeof(vgpu_types[0]); gvt->types = kzalloc(num_types * sizeof(struct intel_vgpu_type), GFP_KERNEL); @@ -101,28 +114,29 @@ int intel_gvt_init_vgpu_types(struct intel_gvt *gvt) min_low = MB_TO_BYTES(32); for (i = 0; i < num_types; ++i) { - if (low_avail / min_low == 0) + if (low_avail / vgpu_types[i].low_mm == 0) break; - gvt->types[i].low_gm_size = min_low; - gvt->types[i].high_gm_size = max((min_low<<3), MB_TO_BYTES(384U)); - gvt->types[i].fence = 4; - gvt->types[i].max_instance = min(low_avail / min_low, - high_avail / gvt->types[i].high_gm_size); - gvt->types[i].avail_instance = gvt->types[i].max_instance; + + gvt->types[i].low_gm_size = vgpu_types[i].low_mm; + gvt->types[i].high_gm_size = vgpu_types[i].high_mm; + gvt->types[i].fence = vgpu_types[i].fence; + gvt->types[i].resolution = vgpu_types[i].edid; + gvt->types[i].avail_instance = min(low_avail / vgpu_types[i].low_mm, + high_avail / vgpu_types[i].high_mm); if (IS_GEN8(gvt->dev_priv)) - sprintf(gvt->types[i].name, "GVTg_V4_%u", - gvt->types[i].max_instance); + sprintf(gvt->types[i].name, "GVTg_V4_%s", + vgpu_types[i].name); else if (IS_GEN9(gvt->dev_priv)) - sprintf(gvt->types[i].name, "GVTg_V5_%u", - gvt->types[i].max_instance); + sprintf(gvt->types[i].name, "GVTg_V5_%s", + vgpu_types[i].name); - min_low <<= 1; - gvt_dbg_core("type[%d]: %s max %u avail %u low %u high %u fence %u\n", - i, gvt->types[i].name, gvt->types[i].max_instance, + gvt_dbg_core("type[%d]: %s avail %u low %u high %u fence %u res %s\n", + i, gvt->types[i].name, gvt->types[i].avail_instance, gvt->types[i].low_gm_size, - gvt->types[i].high_gm_size, gvt->types[i].fence); + gvt->types[i].high_gm_size, gvt->types[i].fence, + vgpu_edid_str(gvt->types[i].resolution)); } gvt->num_types = i; @@ -138,7 +152,7 @@ static void intel_gvt_update_vgpu_types(struct intel_gvt *gvt) { int i; unsigned int low_gm_avail, high_gm_avail, fence_avail; - unsigned int low_gm_min, high_gm_min, fence_min, total_min; + unsigned int low_gm_min, high_gm_min, fence_min; /* Need to depend on maxium hw resource size but keep on * static config for now. @@ -154,12 +168,11 @@ static void intel_gvt_update_vgpu_types(struct intel_gvt *gvt) low_gm_min = low_gm_avail / gvt->types[i].low_gm_size; high_gm_min = high_gm_avail / gvt->types[i].high_gm_size; fence_min = fence_avail / gvt->types[i].fence; - total_min = min(min(low_gm_min, high_gm_min), fence_min); - gvt->types[i].avail_instance = min(gvt->types[i].max_instance, - total_min); + gvt->types[i].avail_instance = min(min(low_gm_min, high_gm_min), + fence_min); - gvt_dbg_core("update type[%d]: %s max %u avail %u low %u high %u fence %u\n", - i, gvt->types[i].name, gvt->types[i].max_instance, + gvt_dbg_core("update type[%d]: %s avail %u low %u high %u fence %u\n", + i, gvt->types[i].name, gvt->types[i].avail_instance, gvt->types[i].low_gm_size, gvt->types[i].high_gm_size, gvt->types[i].fence); } @@ -248,7 +261,7 @@ static struct intel_vgpu *__intel_gvt_create_vgpu(struct intel_gvt *gvt, if (ret) goto out_detach_hypervisor_vgpu; - ret = intel_vgpu_init_display(vgpu); + ret = intel_vgpu_init_display(vgpu, param->resolution); if (ret) goto out_clean_gtt; @@ -312,6 +325,7 @@ struct intel_vgpu *intel_gvt_create_vgpu(struct intel_gvt *gvt, param.low_gm_sz = type->low_gm_size; param.high_gm_sz = type->high_gm_size; param.fence_sz = type->fence; + param.resolution = type->resolution; /* XXX current param based on MB */ param.low_gm_sz = BYTES_TO_MB(param.low_gm_sz); @@ -387,8 +401,12 @@ void intel_gvt_reset_vgpu_locked(struct intel_vgpu *vgpu, bool dmlr, populate_pvinfo_page(vgpu); intel_vgpu_reset_display(vgpu); - if (dmlr) + if (dmlr) { intel_vgpu_reset_cfg_space(vgpu); + /* only reset the failsafe mode when dmlr reset */ + vgpu->failsafe = false; + vgpu->pv_notified = false; + } } vgpu->resetting = false; diff --git a/drivers/gpu/drm/mxsfb/mxsfb_crtc.c b/drivers/gpu/drm/mxsfb/mxsfb_crtc.c index e10a4eda4078..1144e0c9e894 100644 --- a/drivers/gpu/drm/mxsfb/mxsfb_crtc.c +++ b/drivers/gpu/drm/mxsfb/mxsfb_crtc.c @@ -65,13 +65,11 @@ static int mxsfb_set_pixel_fmt(struct mxsfb_drm_private *mxsfb) switch (format) { case DRM_FORMAT_RGB565: dev_dbg(drm->dev, "Setting up RGB565 mode\n"); - ctrl |= CTRL_SET_BUS_WIDTH(STMLCDIF_16BIT); ctrl |= CTRL_SET_WORD_LENGTH(0); ctrl1 |= CTRL1_SET_BYTE_PACKAGING(0xf); break; case DRM_FORMAT_XRGB8888: dev_dbg(drm->dev, "Setting up XRGB8888 mode\n"); - ctrl |= CTRL_SET_BUS_WIDTH(STMLCDIF_24BIT); ctrl |= CTRL_SET_WORD_LENGTH(3); /* Do not use packed pixels = one pixel per word instead. */ ctrl1 |= CTRL1_SET_BYTE_PACKAGING(0x7); @@ -87,6 +85,36 @@ static int mxsfb_set_pixel_fmt(struct mxsfb_drm_private *mxsfb) return 0; } +static void mxsfb_set_bus_fmt(struct mxsfb_drm_private *mxsfb) +{ + struct drm_crtc *crtc = &mxsfb->pipe.crtc; + struct drm_device *drm = crtc->dev; + u32 bus_format = MEDIA_BUS_FMT_RGB888_1X24; + u32 reg; + + reg = readl(mxsfb->base + LCDC_CTRL); + + if (mxsfb->connector.display_info.num_bus_formats) + bus_format = mxsfb->connector.display_info.bus_formats[0]; + + reg &= ~CTRL_BUS_WIDTH_MASK; + switch (bus_format) { + case MEDIA_BUS_FMT_RGB565_1X16: + reg |= CTRL_SET_BUS_WIDTH(STMLCDIF_16BIT); + break; + case MEDIA_BUS_FMT_RGB666_1X18: + reg |= CTRL_SET_BUS_WIDTH(STMLCDIF_18BIT); + break; + case MEDIA_BUS_FMT_RGB888_1X24: + reg |= CTRL_SET_BUS_WIDTH(STMLCDIF_24BIT); + break; + default: + dev_err(drm->dev, "Unknown media bus format %d\n", bus_format); + break; + } + writel(reg, mxsfb->base + LCDC_CTRL); +} + static void mxsfb_enable_controller(struct mxsfb_drm_private *mxsfb) { u32 reg; @@ -168,13 +196,22 @@ static void mxsfb_crtc_mode_set_nofb(struct mxsfb_drm_private *mxsfb) vdctrl0 |= VDCTRL0_HSYNC_ACT_HIGH; if (m->flags & DRM_MODE_FLAG_PVSYNC) vdctrl0 |= VDCTRL0_VSYNC_ACT_HIGH; - if (bus_flags & DRM_BUS_FLAG_DE_HIGH) + /* Make sure Data Enable is high active by default */ + if (!(bus_flags & DRM_BUS_FLAG_DE_LOW)) vdctrl0 |= VDCTRL0_ENABLE_ACT_HIGH; - if (bus_flags & DRM_BUS_FLAG_PIXDATA_NEGEDGE) + /* + * DRM_BUS_FLAG_PIXDATA_ defines are controller centric, + * controllers VDCTRL0_DOTCLK is display centric. + * Drive on positive edge -> display samples on falling edge + * DRM_BUS_FLAG_PIXDATA_POSEDGE -> VDCTRL0_DOTCLK_ACT_FALLING + */ + if (bus_flags & DRM_BUS_FLAG_PIXDATA_POSEDGE) vdctrl0 |= VDCTRL0_DOTCLK_ACT_FALLING; writel(vdctrl0, mxsfb->base + LCDC_VDCTRL0); + mxsfb_set_bus_fmt(mxsfb); + /* Frame length in lines. */ writel(m->crtc_vtotal, mxsfb->base + LCDC_VDCTRL1); @@ -184,8 +221,8 @@ static void mxsfb_crtc_mode_set_nofb(struct mxsfb_drm_private *mxsfb) VDCTRL2_SET_HSYNC_PERIOD(m->crtc_htotal), mxsfb->base + LCDC_VDCTRL2); - writel(SET_HOR_WAIT_CNT(m->crtc_hblank_end - m->crtc_hsync_end) | - SET_VERT_WAIT_CNT(m->crtc_vblank_end - m->crtc_vsync_end), + writel(SET_HOR_WAIT_CNT(m->crtc_htotal - m->crtc_hsync_start) | + SET_VERT_WAIT_CNT(m->crtc_vtotal - m->crtc_vsync_start), mxsfb->base + LCDC_VDCTRL3); writel(SET_DOTCLK_H_VALID_DATA_CNT(m->hdisplay), diff --git a/drivers/gpu/drm/mxsfb/mxsfb_drv.c b/drivers/gpu/drm/mxsfb/mxsfb_drv.c index cdfbe0284635..ff6d6a6f842e 100644 --- a/drivers/gpu/drm/mxsfb/mxsfb_drv.c +++ b/drivers/gpu/drm/mxsfb/mxsfb_drv.c @@ -102,14 +102,18 @@ static void mxsfb_pipe_enable(struct drm_simple_display_pipe *pipe, { struct mxsfb_drm_private *mxsfb = drm_pipe_to_mxsfb_drm_private(pipe); + drm_panel_prepare(mxsfb->panel); mxsfb_crtc_enable(mxsfb); + drm_panel_enable(mxsfb->panel); } static void mxsfb_pipe_disable(struct drm_simple_display_pipe *pipe) { struct mxsfb_drm_private *mxsfb = drm_pipe_to_mxsfb_drm_private(pipe); + drm_panel_disable(mxsfb->panel); mxsfb_crtc_disable(mxsfb); + drm_panel_unprepare(mxsfb->panel); } static void mxsfb_pipe_update(struct drm_simple_display_pipe *pipe, diff --git a/drivers/gpu/drm/mxsfb/mxsfb_out.c b/drivers/gpu/drm/mxsfb/mxsfb_out.c index fa8d17399407..b8e81422d4e2 100644 --- a/drivers/gpu/drm/mxsfb/mxsfb_out.c +++ b/drivers/gpu/drm/mxsfb/mxsfb_out.c @@ -112,6 +112,7 @@ static int mxsfb_attach_endpoint(struct drm_device *drm, int mxsfb_create_output(struct drm_device *drm) { + struct mxsfb_drm_private *mxsfb = drm->dev_private; struct device_node *ep_np = NULL; struct of_endpoint ep; int ret; @@ -127,5 +128,8 @@ int mxsfb_create_output(struct drm_device *drm) } } + if (!mxsfb->panel) + return -EPROBE_DEFER; + return 0; } diff --git a/drivers/gpu/drm/mxsfb/mxsfb_regs.h b/drivers/gpu/drm/mxsfb/mxsfb_regs.h index 31d62cd0d3d7..66a6ba9ec533 100644 --- a/drivers/gpu/drm/mxsfb/mxsfb_regs.h +++ b/drivers/gpu/drm/mxsfb/mxsfb_regs.h @@ -44,6 +44,7 @@ #define CTRL_DATA_SELECT (1 << 16) #define CTRL_SET_BUS_WIDTH(x) (((x) & 0x3) << 10) #define CTRL_GET_BUS_WIDTH(x) (((x) >> 10) & 0x3) +#define CTRL_BUS_WIDTH_MASK (0x3 << 10) #define CTRL_SET_WORD_LENGTH(x) (((x) & 0x3) << 8) #define CTRL_GET_WORD_LENGTH(x) (((x) >> 8) & 0x3) #define CTRL_MASTER (1 << 5) diff --git a/drivers/gpu/drm/rcar-du/rcar_du_vsp.c b/drivers/gpu/drm/rcar-du/rcar_du_vsp.c index b5bfbe50bd87..b0ff304ce3dc 100644 --- a/drivers/gpu/drm/rcar-du/rcar_du_vsp.c +++ b/drivers/gpu/drm/rcar-du/rcar_du_vsp.c @@ -32,6 +32,10 @@ void rcar_du_vsp_enable(struct rcar_du_crtc *crtc) { const struct drm_display_mode *mode = &crtc->crtc.state->adjusted_mode; struct rcar_du_device *rcdu = crtc->group->dev; + struct vsp1_du_lif_config cfg = { + .width = mode->hdisplay, + .height = mode->vdisplay, + }; struct rcar_du_plane_state state = { .state = { .crtc = &crtc->crtc, @@ -66,12 +70,12 @@ void rcar_du_vsp_enable(struct rcar_du_crtc *crtc) */ crtc->group->need_restart = true; - vsp1_du_setup_lif(crtc->vsp->vsp, mode->hdisplay, mode->vdisplay); + vsp1_du_setup_lif(crtc->vsp->vsp, &cfg); } void rcar_du_vsp_disable(struct rcar_du_crtc *crtc) { - vsp1_du_setup_lif(crtc->vsp->vsp, 0, 0); + vsp1_du_setup_lif(crtc->vsp->vsp, NULL); } void rcar_du_vsp_atomic_begin(struct rcar_du_crtc *crtc) diff --git a/drivers/hv/channel.c b/drivers/hv/channel.c index 81a80c82f1bd..bd0d1988feb2 100644 --- a/drivers/hv/channel.c +++ b/drivers/hv/channel.c @@ -543,7 +543,7 @@ static int vmbus_close_internal(struct vmbus_channel *channel) /* * In case a device driver's probe() fails (e.g., * util_probe() -> vmbus_open() returns -ENOMEM) and the device is - * rescinded later (e.g., we dynamically disble an Integrated Service + * rescinded later (e.g., we dynamically disable an Integrated Service * in Hyper-V Manager), the driver's remove() invokes vmbus_close(): * here we should skip most of the below cleanup work. */ diff --git a/drivers/hv/ring_buffer.c b/drivers/hv/ring_buffer.c index 87799e81af97..c3f1a9e33cef 100644 --- a/drivers/hv/ring_buffer.c +++ b/drivers/hv/ring_buffer.c @@ -32,6 +32,8 @@ #include "hyperv_vmbus.h" +#define VMBUS_PKT_TRAILER 8 + /* * When we write to the ring buffer, check if the host needs to * be signaled. Here is the details of this protocol: @@ -336,6 +338,12 @@ int hv_ringbuffer_write(struct vmbus_channel *channel, return 0; } +static inline void +init_cached_read_index(struct hv_ring_buffer_info *rbi) +{ + rbi->cached_read_index = rbi->ring_buffer->read_index; +} + int hv_ringbuffer_read(struct vmbus_channel *channel, void *buffer, u32 buflen, u32 *buffer_actual_len, u64 *requestid, bool raw) @@ -366,7 +374,8 @@ int hv_ringbuffer_read(struct vmbus_channel *channel, return ret; } - init_cached_read_index(channel); + init_cached_read_index(inring_info); + next_read_location = hv_get_next_read_location(inring_info); next_read_location = hv_copyfrom_ringbuffer(inring_info, &desc, sizeof(desc), @@ -410,3 +419,86 @@ int hv_ringbuffer_read(struct vmbus_channel *channel, return ret; } + +/* + * Determine number of bytes available in ring buffer after + * the current iterator (priv_read_index) location. + * + * This is similar to hv_get_bytes_to_read but with private + * read index instead. + */ +static u32 hv_pkt_iter_avail(const struct hv_ring_buffer_info *rbi) +{ + u32 priv_read_loc = rbi->priv_read_index; + u32 write_loc = READ_ONCE(rbi->ring_buffer->write_index); + + if (write_loc >= priv_read_loc) + return write_loc - priv_read_loc; + else + return (rbi->ring_datasize - priv_read_loc) + write_loc; +} + +/* + * Get first vmbus packet from ring buffer after read_index + * + * If ring buffer is empty, returns NULL and no other action needed. + */ +struct vmpacket_descriptor *hv_pkt_iter_first(struct vmbus_channel *channel) +{ + struct hv_ring_buffer_info *rbi = &channel->inbound; + + /* set state for later hv_signal_on_read() */ + init_cached_read_index(rbi); + + if (hv_pkt_iter_avail(rbi) < sizeof(struct vmpacket_descriptor)) + return NULL; + + return hv_get_ring_buffer(rbi) + rbi->priv_read_index; +} +EXPORT_SYMBOL_GPL(hv_pkt_iter_first); + +/* + * Get next vmbus packet from ring buffer. + * + * Advances the current location (priv_read_index) and checks for more + * data. If the end of the ring buffer is reached, then return NULL. + */ +struct vmpacket_descriptor * +__hv_pkt_iter_next(struct vmbus_channel *channel, + const struct vmpacket_descriptor *desc) +{ + struct hv_ring_buffer_info *rbi = &channel->inbound; + u32 packetlen = desc->len8 << 3; + u32 dsize = rbi->ring_datasize; + + /* bump offset to next potential packet */ + rbi->priv_read_index += packetlen + VMBUS_PKT_TRAILER; + if (rbi->priv_read_index >= dsize) + rbi->priv_read_index -= dsize; + + /* more data? */ + if (hv_pkt_iter_avail(rbi) < sizeof(struct vmpacket_descriptor)) + return NULL; + else + return hv_get_ring_buffer(rbi) + rbi->priv_read_index; +} +EXPORT_SYMBOL_GPL(__hv_pkt_iter_next); + +/* + * Update host ring buffer after iterating over packets. + */ +void hv_pkt_iter_close(struct vmbus_channel *channel) +{ + struct hv_ring_buffer_info *rbi = &channel->inbound; + + /* + * Make sure all reads are done before we update the read index since + * the writer may start writing to the read area once the read index + * is updated. + */ + virt_rmb(); + rbi->ring_buffer->read_index = rbi->priv_read_index; + + hv_signal_on_read(channel); +} +EXPORT_SYMBOL_GPL(hv_pkt_iter_close); diff --git a/drivers/i2c/busses/i2c-brcmstb.c b/drivers/i2c/busses/i2c-brcmstb.c index 0652281662a8..78792b4d6437 100644 --- a/drivers/i2c/busses/i2c-brcmstb.c +++ b/drivers/i2c/busses/i2c-brcmstb.c @@ -465,6 +465,7 @@ static int brcmstb_i2c_xfer(struct i2c_adapter *adapter, u8 *tmp_buf; int len = 0; int xfersz = brcmstb_i2c_get_xfersz(dev); + u32 cond, cond_per_msg; if (dev->is_suspended) return -EBUSY; @@ -481,10 +482,11 @@ static int brcmstb_i2c_xfer(struct i2c_adapter *adapter, pmsg->buf ? pmsg->buf[0] : '0', pmsg->len); if (i < (num - 1) && (msgs[i + 1].flags & I2C_M_NOSTART)) - brcmstb_set_i2c_start_stop(dev, ~(COND_START_STOP)); + cond = ~COND_START_STOP; else - brcmstb_set_i2c_start_stop(dev, - COND_RESTART | COND_NOSTOP); + cond = COND_RESTART | COND_NOSTOP; + + brcmstb_set_i2c_start_stop(dev, cond); /* Send slave address */ if (!(pmsg->flags & I2C_M_NOSTART)) { @@ -497,13 +499,24 @@ static int brcmstb_i2c_xfer(struct i2c_adapter *adapter, } } + cond_per_msg = cond; + /* Perform data transfer */ while (len) { bytes_to_xfer = min(len, xfersz); - if (len <= xfersz && i == (num - 1)) - brcmstb_set_i2c_start_stop(dev, - ~(COND_START_STOP)); + if (len <= xfersz) { + if (i == (num - 1)) + cond_per_msg = cond_per_msg & + ~(COND_RESTART | COND_NOSTOP); + else + cond_per_msg = cond; + } else { + cond_per_msg = (cond_per_msg & ~COND_RESTART) | + COND_NOSTOP; + } + + brcmstb_set_i2c_start_stop(dev, cond_per_msg); rc = brcmstb_i2c_xfer_bsc_data(dev, tmp_buf, bytes_to_xfer, pmsg); @@ -512,6 +525,8 @@ static int brcmstb_i2c_xfer(struct i2c_adapter *adapter, len -= bytes_to_xfer; tmp_buf += bytes_to_xfer; + + cond_per_msg = COND_NOSTART | COND_NOSTOP; } } diff --git a/drivers/i2c/busses/i2c-designware-core.h b/drivers/i2c/busses/i2c-designware-core.h index c1db3a5a340f..d9aaf1790e0e 100644 --- a/drivers/i2c/busses/i2c-designware-core.h +++ b/drivers/i2c/busses/i2c-designware-core.h @@ -88,6 +88,7 @@ struct dw_i2c_dev { void __iomem *base; struct completion cmd_complete; struct clk *clk; + struct reset_control *rst; u32 (*get_clk_rate_khz) (struct dw_i2c_dev *dev); struct dw_pci_controller *controller; int cmd_err; diff --git a/drivers/i2c/busses/i2c-designware-platdrv.c b/drivers/i2c/busses/i2c-designware-platdrv.c index 6ce431323125..79c4b4ea0539 100644 --- a/drivers/i2c/busses/i2c-designware-platdrv.c +++ b/drivers/i2c/busses/i2c-designware-platdrv.c @@ -38,6 +38,7 @@ #include <linux/pm_runtime.h> #include <linux/property.h> #include <linux/io.h> +#include <linux/reset.h> #include <linux/slab.h> #include <linux/acpi.h> #include <linux/platform_data/i2c-designware.h> @@ -199,6 +200,14 @@ static int dw_i2c_plat_probe(struct platform_device *pdev) dev->irq = irq; platform_set_drvdata(pdev, dev); + dev->rst = devm_reset_control_get_optional_exclusive(&pdev->dev, NULL); + if (IS_ERR(dev->rst)) { + if (PTR_ERR(dev->rst) == -EPROBE_DEFER) + return -EPROBE_DEFER; + } else { + reset_control_deassert(dev->rst); + } + if (pdata) { dev->clk_freq = pdata->i2c_scl_freq; } else { @@ -235,12 +244,13 @@ static int dw_i2c_plat_probe(struct platform_device *pdev) && dev->clk_freq != 1000000 && dev->clk_freq != 3400000) { dev_err(&pdev->dev, "Only 100kHz, 400kHz, 1MHz and 3.4MHz supported"); - return -EINVAL; + r = -EINVAL; + goto exit_reset; } r = i2c_dw_eval_lock_support(dev); if (r) - return r; + goto exit_reset; dev->functionality = I2C_FUNC_10BIT_ADDR | DW_IC_DEFAULT_FUNCTIONALITY; @@ -286,10 +296,18 @@ static int dw_i2c_plat_probe(struct platform_device *pdev) } r = i2c_dw_probe(dev); - if (r && !dev->pm_runtime_disabled) - pm_runtime_disable(&pdev->dev); + if (r) + goto exit_probe; return r; + +exit_probe: + if (!dev->pm_runtime_disabled) + pm_runtime_disable(&pdev->dev); +exit_reset: + if (!IS_ERR_OR_NULL(dev->rst)) + reset_control_assert(dev->rst); + return r; } static int dw_i2c_plat_remove(struct platform_device *pdev) @@ -306,6 +324,8 @@ static int dw_i2c_plat_remove(struct platform_device *pdev) pm_runtime_put_sync(&pdev->dev); if (!dev->pm_runtime_disabled) pm_runtime_disable(&pdev->dev); + if (!IS_ERR_OR_NULL(dev->rst)) + reset_control_assert(dev->rst); return 0; } diff --git a/drivers/i2c/busses/i2c-exynos5.c b/drivers/i2c/busses/i2c-exynos5.c index cbd93ce0661f..736a82472101 100644 --- a/drivers/i2c/busses/i2c-exynos5.c +++ b/drivers/i2c/busses/i2c-exynos5.c @@ -457,7 +457,6 @@ static irqreturn_t exynos5_i2c_irq(int irqno, void *dev_id) int_status = readl(i2c->regs + HSI2C_INT_STATUS); writel(int_status, i2c->regs + HSI2C_INT_STATUS); - trans_status = readl(i2c->regs + HSI2C_TRANS_STATUS); /* handle interrupt related to the transfer status */ if (i2c->variant->hw == HSI2C_EXYNOS7) { @@ -482,11 +481,13 @@ static irqreturn_t exynos5_i2c_irq(int irqno, void *dev_id) goto stop; } + trans_status = readl(i2c->regs + HSI2C_TRANS_STATUS); if ((trans_status & HSI2C_MASTER_ST_MASK) == HSI2C_MASTER_ST_LOSE) { i2c->state = -EAGAIN; goto stop; } } else if (int_status & HSI2C_INT_I2C) { + trans_status = readl(i2c->regs + HSI2C_TRANS_STATUS); if (trans_status & HSI2C_NO_DEV_ACK) { dev_dbg(i2c->dev, "No ACK from device\n"); i2c->state = -ENXIO; diff --git a/drivers/i2c/busses/i2c-meson.c b/drivers/i2c/busses/i2c-meson.c index 2aa61bbbd307..73b97c71a484 100644 --- a/drivers/i2c/busses/i2c-meson.c +++ b/drivers/i2c/busses/i2c-meson.c @@ -175,7 +175,7 @@ static void meson_i2c_put_data(struct meson_i2c *i2c, char *buf, int len) wdata1 |= *buf++ << ((i - 4) * 8); writel(wdata0, i2c->regs + REG_TOK_WDATA0); - writel(wdata0, i2c->regs + REG_TOK_WDATA1); + writel(wdata1, i2c->regs + REG_TOK_WDATA1); dev_dbg(i2c->dev, "%s: data %08x %08x len %d\n", __func__, wdata0, wdata1, len); diff --git a/drivers/i2c/busses/i2c-mt65xx.c b/drivers/i2c/busses/i2c-mt65xx.c index 4a7d9bc2142b..45d61714c81b 100644 --- a/drivers/i2c/busses/i2c-mt65xx.c +++ b/drivers/i2c/busses/i2c-mt65xx.c @@ -172,14 +172,6 @@ static const struct i2c_adapter_quirks mt6577_i2c_quirks = { .max_comb_2nd_msg_len = 31, }; -static const struct i2c_adapter_quirks mt8173_i2c_quirks = { - .max_num_msgs = 65535, - .max_write_len = 65535, - .max_read_len = 65535, - .max_comb_1st_msg_len = 65535, - .max_comb_2nd_msg_len = 65535, -}; - static const struct mtk_i2c_compatible mt6577_compat = { .quirks = &mt6577_i2c_quirks, .pmic_i2c = 0, @@ -199,7 +191,6 @@ static const struct mtk_i2c_compatible mt6589_compat = { }; static const struct mtk_i2c_compatible mt8173_compat = { - .quirks = &mt8173_i2c_quirks, .pmic_i2c = 0, .dcm = 1, .auto_restart = 1, diff --git a/drivers/i2c/busses/i2c-riic.c b/drivers/i2c/busses/i2c-riic.c index 8f11d347b3ec..c811af4c8d81 100644 --- a/drivers/i2c/busses/i2c-riic.c +++ b/drivers/i2c/busses/i2c-riic.c @@ -218,8 +218,12 @@ static irqreturn_t riic_tend_isr(int irq, void *data) } if (riic->is_last || riic->err) { - riic_clear_set_bit(riic, 0, ICIER_SPIE, RIIC_ICIER); + riic_clear_set_bit(riic, ICIER_TEIE, ICIER_SPIE, RIIC_ICIER); writeb(ICCR2_SP, riic->base + RIIC_ICCR2); + } else { + /* Transfer is complete, but do not send STOP */ + riic_clear_set_bit(riic, ICIER_TEIE, 0, RIIC_ICIER); + complete(&riic->msg_done); } return IRQ_HANDLED; diff --git a/drivers/i2c/i2c-mux.c b/drivers/i2c/i2c-mux.c index 83768e85a919..2178266bca79 100644 --- a/drivers/i2c/i2c-mux.c +++ b/drivers/i2c/i2c-mux.c @@ -429,6 +429,7 @@ void i2c_mux_del_adapters(struct i2c_mux_core *muxc) while (muxc->num_adapters) { struct i2c_adapter *adap = muxc->adapter[--muxc->num_adapters]; struct i2c_mux_priv *priv = adap->algo_data; + struct device_node *np = adap->dev.of_node; muxc->adapter[muxc->num_adapters] = NULL; @@ -438,6 +439,7 @@ void i2c_mux_del_adapters(struct i2c_mux_core *muxc) sysfs_remove_link(&priv->adap.dev.kobj, "mux_device"); i2c_del_adapter(adap); + of_node_put(np); kfree(priv); } } diff --git a/drivers/infiniband/hw/qedr/main.c b/drivers/infiniband/hw/qedr/main.c index b9b47e5cc8b3..ced0461d6e9f 100644 --- a/drivers/infiniband/hw/qedr/main.c +++ b/drivers/infiniband/hw/qedr/main.c @@ -587,9 +587,8 @@ void qedr_affiliated_event(void *context, u8 e_code, void *fw_handle) #define EVENT_TYPE_CQ 1 #define EVENT_TYPE_QP 2 struct qedr_dev *dev = (struct qedr_dev *)context; - union event_ring_data *data = fw_handle; - u64 roce_handle64 = ((u64)data->roce_handle.hi << 32) + - data->roce_handle.lo; + struct regpair *async_handle = (struct regpair *)fw_handle; + u64 roce_handle64 = ((u64) async_handle->hi << 32) + async_handle->lo; u8 event_type = EVENT_TYPE_NOT_DEFINED; struct ib_event event; struct ib_cq *ibcq; diff --git a/drivers/infiniband/hw/qedr/qedr.h b/drivers/infiniband/hw/qedr/qedr.h index bb32e4792ec9..5cb9195513bd 100644 --- a/drivers/infiniband/hw/qedr/qedr.h +++ b/drivers/infiniband/hw/qedr/qedr.h @@ -38,7 +38,8 @@ #include <linux/qed/qed_chain.h> #include <linux/qed/qed_roce_if.h> #include <linux/qed/qede_roce.h> -#include "qedr_hsi.h" +#include <linux/qed/roce_common.h> +#include "qedr_hsi_rdma.h" #define QEDR_MODULE_VERSION "8.10.10.0" #define QEDR_NODE_DESC "QLogic 579xx RoCE HCA" diff --git a/drivers/infiniband/hw/qedr/qedr_cm.c b/drivers/infiniband/hw/qedr/qedr_cm.c index 699632893dd9..a6280ce3e2a5 100644 --- a/drivers/infiniband/hw/qedr/qedr_cm.c +++ b/drivers/infiniband/hw/qedr/qedr_cm.c @@ -43,14 +43,11 @@ #include <rdma/ib_addr.h> #include <rdma/ib_cache.h> -#include "qedr_hsi.h" #include <linux/qed/qed_if.h> #include <linux/qed/qed_roce_if.h> #include "qedr.h" -#include "qedr_hsi.h" #include "verbs.h" #include <rdma/qedr-abi.h> -#include "qedr_hsi.h" #include "qedr_cm.h" void qedr_inc_sw_gsi_cons(struct qedr_qp_hwq_info *info) diff --git a/drivers/infiniband/hw/qedr/qedr_hsi.h b/drivers/infiniband/hw/qedr/qedr_hsi.h deleted file mode 100644 index 66d27521373f..000000000000 --- a/drivers/infiniband/hw/qedr/qedr_hsi.h +++ /dev/null @@ -1,56 +0,0 @@ -/* QLogic qedr NIC Driver - * Copyright (c) 2015-2016 QLogic Corporation - * - * This software is available to you under a choice of one of two - * licenses. You may choose to be licensed under the terms of the GNU - * General Public License (GPL) Version 2, available from the file - * COPYING in the main directory of this source tree, or the - * OpenIB.org BSD license below: - * - * Redistribution and use in source and binary forms, with or - * without modification, are permitted provided that the following - * conditions are met: - * - * - Redistributions of source code must retain the above - * copyright notice, this list of conditions and the following - * disclaimer. - * - * - Redistributions in binary form must reproduce the above - * copyright notice, this list of conditions and the following - * disclaimer in the documentation and /or other materials - * provided with the distribution. - * - * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, - * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF - * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND - * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS - * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN - * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN - * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE - * SOFTWARE. - */ -#ifndef __QED_HSI_ROCE__ -#define __QED_HSI_ROCE__ - -#include <linux/qed/common_hsi.h> -#include <linux/qed/roce_common.h> -#include "qedr_hsi_rdma.h" - -/* Affiliated asynchronous events / errors enumeration */ -enum roce_async_events_type { - ROCE_ASYNC_EVENT_NONE = 0, - ROCE_ASYNC_EVENT_COMM_EST = 1, - ROCE_ASYNC_EVENT_SQ_DRAINED, - ROCE_ASYNC_EVENT_SRQ_LIMIT, - ROCE_ASYNC_EVENT_LAST_WQE_REACHED, - ROCE_ASYNC_EVENT_CQ_ERR, - ROCE_ASYNC_EVENT_LOCAL_INVALID_REQUEST_ERR, - ROCE_ASYNC_EVENT_LOCAL_CATASTROPHIC_ERR, - ROCE_ASYNC_EVENT_LOCAL_ACCESS_ERR, - ROCE_ASYNC_EVENT_QP_CATASTROPHIC_ERR, - ROCE_ASYNC_EVENT_CQ_OVERFLOW_ERR, - ROCE_ASYNC_EVENT_SRQ_EMPTY, - MAX_ROCE_ASYNC_EVENTS_TYPE -}; - -#endif /* __QED_HSI_ROCE__ */ diff --git a/drivers/infiniband/hw/qedr/verbs.c b/drivers/infiniband/hw/qedr/verbs.c index 6b3bb32803bd..2091902848e6 100644 --- a/drivers/infiniband/hw/qedr/verbs.c +++ b/drivers/infiniband/hw/qedr/verbs.c @@ -43,7 +43,8 @@ #include <rdma/ib_addr.h> #include <rdma/ib_cache.h> -#include "qedr_hsi.h" +#include <linux/qed/common_hsi.h> +#include "qedr_hsi_rdma.h" #include <linux/qed/qed_if.h> #include "qedr.h" #include "verbs.h" diff --git a/drivers/irqchip/irq-crossbar.c b/drivers/irqchip/irq-crossbar.c index 1eef56a89b1f..f96601268f71 100644 --- a/drivers/irqchip/irq-crossbar.c +++ b/drivers/irqchip/irq-crossbar.c @@ -198,7 +198,8 @@ static const struct irq_domain_ops crossbar_domain_ops = { static int __init crossbar_of_init(struct device_node *node) { - int i, size, max = 0, reserved = 0, entry; + u32 max = 0, entry, reg_size; + int i, size, reserved = 0; const __be32 *irqsr; int ret = -ENOMEM; @@ -275,9 +276,9 @@ static int __init crossbar_of_init(struct device_node *node) if (!cb->register_offsets) goto err_irq_map; - of_property_read_u32(node, "ti,reg-size", &size); + of_property_read_u32(node, "ti,reg-size", ®_size); - switch (size) { + switch (reg_size) { case 1: cb->write = crossbar_writeb; break; @@ -303,7 +304,7 @@ static int __init crossbar_of_init(struct device_node *node) continue; cb->register_offsets[i] = reserved; - reserved += size; + reserved += reg_size; } of_property_read_u32(node, "ti,irqs-safe-map", &cb->safe_map); diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c index 23201004fd7a..f77f840d2b5f 100644 --- a/drivers/irqchip/irq-gic-v3-its.c +++ b/drivers/irqchip/irq-gic-v3-its.c @@ -1601,6 +1601,14 @@ static void __maybe_unused its_enable_quirk_cavium_23144(void *data) its->flags |= ITS_FLAGS_WORKAROUND_CAVIUM_23144; } +static void __maybe_unused its_enable_quirk_qdf2400_e0065(void *data) +{ + struct its_node *its = data; + + /* On QDF2400, the size of the ITE is 16Bytes */ + its->ite_size = 16; +} + static const struct gic_quirk its_quirks[] = { #ifdef CONFIG_CAVIUM_ERRATUM_22375 { @@ -1618,6 +1626,14 @@ static const struct gic_quirk its_quirks[] = { .init = its_enable_quirk_cavium_23144, }, #endif +#ifdef CONFIG_QCOM_QDF2400_ERRATUM_0065 + { + .desc = "ITS: QDF2400 erratum 0065", + .iidr = 0x00001070, /* QDF2400 ITS rev 1.x */ + .mask = 0xffffffff, + .init = its_enable_quirk_qdf2400_e0065, + }, +#endif { } }; diff --git a/drivers/isdn/gigaset/bas-gigaset.c b/drivers/isdn/gigaset/bas-gigaset.c index 11e13c56126f..2da3ff650e1d 100644 --- a/drivers/isdn/gigaset/bas-gigaset.c +++ b/drivers/isdn/gigaset/bas-gigaset.c @@ -2317,6 +2317,9 @@ static int gigaset_probe(struct usb_interface *interface, return -ENODEV; } + if (hostif->desc.bNumEndpoints < 1) + return -ENODEV; + dev_info(&udev->dev, "%s: Device matched (Vendor: 0x%x, Product: 0x%x)\n", __func__, le16_to_cpu(udev->descriptor.idVendor), diff --git a/drivers/isdn/hardware/mISDN/Kconfig b/drivers/isdn/hardware/mISDN/Kconfig index 09df54fc1fef..fda912b0833f 100644 --- a/drivers/isdn/hardware/mISDN/Kconfig +++ b/drivers/isdn/hardware/mISDN/Kconfig @@ -13,7 +13,7 @@ config MISDN_HFCPCI config MISDN_HFCMULTI tristate "Support for HFC multiport cards (HFC-4S/8S/E1)" - depends on PCI || 8xx + depends on PCI || CPM1 depends on MISDN help Enable support for cards with Cologne Chip AG's HFC multiport @@ -27,8 +27,8 @@ config MISDN_HFCMULTI_8xx bool "Support for XHFC embedded board in HFC multiport driver" depends on MISDN depends on MISDN_HFCMULTI - depends on 8xx - default 8xx + depends on CPM1 + default CPM1 help Enable support for the XHFC embedded solution from Speech Design. diff --git a/drivers/isdn/hardware/mISDN/hfc_multi_8xx.h b/drivers/isdn/hardware/mISDN/hfc_multi_8xx.h index 0eafe9f04fca..8a254747768e 100644 --- a/drivers/isdn/hardware/mISDN/hfc_multi_8xx.h +++ b/drivers/isdn/hardware/mISDN/hfc_multi_8xx.h @@ -6,7 +6,7 @@ * */ -#include <asm/8xx_immap.h> +#include <asm/cpm1.h> /* Change this to the value used by your board */ #ifndef IMAP_ADDR diff --git a/drivers/isdn/hisax/st5481_b.c b/drivers/isdn/hisax/st5481_b.c index 409849165838..f64a36007800 100644 --- a/drivers/isdn/hisax/st5481_b.c +++ b/drivers/isdn/hisax/st5481_b.c @@ -239,7 +239,7 @@ static void st5481B_mode(struct st5481_bcs *bcs, int mode) } } } else { - // Disble B channel interrupts + // Disable B channel interrupts st5481_usb_device_ctrl_msg(adapter, FFMSK_B1+(bcs->channel * 2), 0, NULL, NULL); // Disable B channel FIFOs diff --git a/drivers/macintosh/macio_asic.c b/drivers/macintosh/macio_asic.c index 3f041b187033..f757cef293f8 100644 --- a/drivers/macintosh/macio_asic.c +++ b/drivers/macintosh/macio_asic.c @@ -392,6 +392,7 @@ static struct macio_dev * macio_add_one_device(struct macio_chip *chip, * To get all the fields, copy all archdata */ dev->ofdev.dev.archdata = chip->lbus.pdev->dev.archdata; + dev->ofdev.dev.dma_ops = chip->lbus.pdev->dev.dma_ops; #endif /* CONFIG_PCI */ #ifdef DEBUG diff --git a/drivers/md/bcache/util.h b/drivers/md/bcache/util.h index a126919ed102..5d13930f0f22 100644 --- a/drivers/md/bcache/util.h +++ b/drivers/md/bcache/util.h @@ -4,7 +4,6 @@ #include <linux/blkdev.h> #include <linux/errno.h> -#include <linux/blkdev.h> #include <linux/kernel.h> #include <linux/sched/clock.h> #include <linux/llist.h> diff --git a/drivers/media/dvb-frontends/drx39xyj/drx_driver.h b/drivers/media/dvb-frontends/drx39xyj/drx_driver.h index 7a681d8202c7..4442e478db72 100644 --- a/drivers/media/dvb-frontends/drx39xyj/drx_driver.h +++ b/drivers/media/dvb-frontends/drx39xyj/drx_driver.h @@ -256,8 +256,7 @@ int drxbsp_tuner_default_i2c_write_read(struct tuner_instance *tuner, * * The actual DAP implementation may be restricted to only one of the modes. * A compiler warning or error will be generated if the DAP implementation -* overides or cannot handle the mode defined below. -* +* overrides or cannot handle the mode defined below. */ #ifndef DRXDAP_SINGLE_MASTER #define DRXDAP_SINGLE_MASTER 1 @@ -272,7 +271,7 @@ int drxbsp_tuner_default_i2c_write_read(struct tuner_instance *tuner, * * This maximum size may be restricted by the actual DAP implementation. * A compiler warning or error will be generated if the DAP implementation -* overides or cannot handle the chunksize defined below. +* overrides or cannot handle the chunksize defined below. * * Beware that the DAP uses DRXDAP_MAX_WCHUNKSIZE to create a temporary data * buffer. Do not undefine or choose too large, unless your system is able to @@ -292,8 +291,7 @@ int drxbsp_tuner_default_i2c_write_read(struct tuner_instance *tuner, * * This maximum size may be restricted by the actual DAP implementation. * A compiler warning or error will be generated if the DAP implementation -* overides or cannot handle the chunksize defined below. -* +* overrides or cannot handle the chunksize defined below. */ #ifndef DRXDAP_MAX_RCHUNKSIZE #define DRXDAP_MAX_RCHUNKSIZE 60 diff --git a/drivers/media/platform/vsp1/vsp1_drm.c b/drivers/media/platform/vsp1/vsp1_drm.c index b4b583f7137a..b4c0f10fc3b0 100644 --- a/drivers/media/platform/vsp1/vsp1_drm.c +++ b/drivers/media/platform/vsp1/vsp1_drm.c @@ -54,12 +54,11 @@ EXPORT_SYMBOL_GPL(vsp1_du_init); /** * vsp1_du_setup_lif - Setup the output part of the VSP pipeline * @dev: the VSP device - * @width: output frame width in pixels - * @height: output frame height in pixels + * @cfg: the LIF configuration * - * Configure the output part of VSP DRM pipeline for the given frame @width and - * @height. This sets up formats on the BRU source pad, the WPF0 sink and source - * pads, and the LIF sink pad. + * Configure the output part of VSP DRM pipeline for the given frame @cfg.width + * and @cfg.height. This sets up formats on the BRU source pad, the WPF0 sink + * and source pads, and the LIF sink pad. * * As the media bus code on the BRU source pad is conditioned by the * configuration of the BRU sink 0 pad, we also set up the formats on all BRU @@ -69,8 +68,7 @@ EXPORT_SYMBOL_GPL(vsp1_du_init); * * Return 0 on success or a negative error code on failure. */ -int vsp1_du_setup_lif(struct device *dev, unsigned int width, - unsigned int height) +int vsp1_du_setup_lif(struct device *dev, const struct vsp1_du_lif_config *cfg) { struct vsp1_device *vsp1 = dev_get_drvdata(dev); struct vsp1_pipeline *pipe = &vsp1->drm->pipe; @@ -79,11 +77,8 @@ int vsp1_du_setup_lif(struct device *dev, unsigned int width, unsigned int i; int ret; - dev_dbg(vsp1->dev, "%s: configuring LIF with format %ux%u\n", - __func__, width, height); - - if (width == 0 || height == 0) { - /* Zero width or height means the CRTC is being disabled, stop + if (!cfg) { + /* NULL configuration means the CRTC is being disabled, stop * the pipeline and turn the light off. */ ret = vsp1_pipeline_stop(pipe); @@ -108,6 +103,9 @@ int vsp1_du_setup_lif(struct device *dev, unsigned int width, return 0; } + dev_dbg(vsp1->dev, "%s: configuring LIF with format %ux%u\n", + __func__, cfg->width, cfg->height); + /* Configure the format at the BRU sinks and propagate it through the * pipeline. */ @@ -117,8 +115,8 @@ int vsp1_du_setup_lif(struct device *dev, unsigned int width, for (i = 0; i < bru->entity.source_pad; ++i) { format.pad = i; - format.format.width = width; - format.format.height = height; + format.format.width = cfg->width; + format.format.height = cfg->height; format.format.code = MEDIA_BUS_FMT_ARGB8888_1X32; format.format.field = V4L2_FIELD_NONE; @@ -133,8 +131,8 @@ int vsp1_du_setup_lif(struct device *dev, unsigned int width, } format.pad = bru->entity.source_pad; - format.format.width = width; - format.format.height = height; + format.format.width = cfg->width; + format.format.height = cfg->height; format.format.code = MEDIA_BUS_FMT_ARGB8888_1X32; format.format.field = V4L2_FIELD_NONE; @@ -180,7 +178,8 @@ int vsp1_du_setup_lif(struct device *dev, unsigned int width, /* Verify that the format at the output of the pipeline matches the * requested frame size and media bus code. */ - if (format.format.width != width || format.format.height != height || + if (format.format.width != cfg->width || + format.format.height != cfg->height || format.format.code != MEDIA_BUS_FMT_ARGB8888_1X32) { dev_dbg(vsp1->dev, "%s: format mismatch\n", __func__); return -EPIPE; diff --git a/drivers/media/rc/lirc_dev.c b/drivers/media/rc/lirc_dev.c index 393dccaabdd0..1688893a65bb 100644 --- a/drivers/media/rc/lirc_dev.c +++ b/drivers/media/rc/lirc_dev.c @@ -436,6 +436,8 @@ int lirc_dev_fop_open(struct inode *inode, struct file *file) return -ERESTARTSYS; ir = irctls[iminor(inode)]; + mutex_unlock(&lirc_dev_lock); + if (!ir) { retval = -ENODEV; goto error; @@ -476,8 +478,6 @@ int lirc_dev_fop_open(struct inode *inode, struct file *file) } error: - mutex_unlock(&lirc_dev_lock); - nonseekable_open(inode, file); return retval; diff --git a/drivers/media/rc/nuvoton-cir.c b/drivers/media/rc/nuvoton-cir.c index b109f8246b96..ec4b25bd2ec2 100644 --- a/drivers/media/rc/nuvoton-cir.c +++ b/drivers/media/rc/nuvoton-cir.c @@ -176,12 +176,13 @@ static void nvt_write_wakeup_codes(struct rc_dev *dev, { u8 tolerance, config; struct nvt_dev *nvt = dev->priv; + unsigned long flags; int i; /* hardcode the tolerance to 10% */ tolerance = DIV_ROUND_UP(count, 10); - spin_lock(&nvt->lock); + spin_lock_irqsave(&nvt->lock, flags); nvt_clear_cir_wake_fifo(nvt); nvt_cir_wake_reg_write(nvt, count, CIR_WAKE_FIFO_CMP_DEEP); @@ -203,7 +204,7 @@ static void nvt_write_wakeup_codes(struct rc_dev *dev, nvt_cir_wake_reg_write(nvt, config, CIR_WAKE_IRCON); - spin_unlock(&nvt->lock); + spin_unlock_irqrestore(&nvt->lock, flags); } static ssize_t wakeup_data_show(struct device *dev, diff --git a/drivers/media/rc/rc-main.c b/drivers/media/rc/rc-main.c index 2424946740e6..d84533699668 100644 --- a/drivers/media/rc/rc-main.c +++ b/drivers/media/rc/rc-main.c @@ -1663,6 +1663,7 @@ static int rc_setup_rx_device(struct rc_dev *dev) { int rc; struct rc_map *rc_map; + u64 rc_type; if (!dev->map_name) return -EINVAL; @@ -1677,15 +1678,18 @@ static int rc_setup_rx_device(struct rc_dev *dev) if (rc) return rc; - if (dev->change_protocol) { - u64 rc_type = (1ll << rc_map->rc_type); + rc_type = BIT_ULL(rc_map->rc_type); + if (dev->change_protocol) { rc = dev->change_protocol(dev, &rc_type); if (rc < 0) goto out_table; dev->enabled_protocols = rc_type; } + if (dev->driver_type == RC_DRIVER_IR_RAW) + ir_raw_load_modules(&rc_type); + set_bit(EV_KEY, dev->input_dev->evbit); set_bit(EV_REP, dev->input_dev->evbit); set_bit(EV_MSC, dev->input_dev->evbit); @@ -1777,12 +1781,6 @@ int rc_register_device(struct rc_dev *dev) dev->input_name ?: "Unspecified device", path ?: "N/A"); kfree(path); - if (dev->driver_type != RC_DRIVER_IR_RAW_TX) { - rc = rc_setup_rx_device(dev); - if (rc) - goto out_dev; - } - if (dev->driver_type == RC_DRIVER_IR_RAW || dev->driver_type == RC_DRIVER_IR_RAW_TX) { if (!raw_init) { @@ -1791,7 +1789,13 @@ int rc_register_device(struct rc_dev *dev) } rc = ir_raw_event_register(dev); if (rc < 0) - goto out_rx; + goto out_dev; + } + + if (dev->driver_type != RC_DRIVER_IR_RAW_TX) { + rc = rc_setup_rx_device(dev); + if (rc) + goto out_raw; } /* Allow the RC sysfs nodes to be accessible */ @@ -1803,8 +1807,8 @@ int rc_register_device(struct rc_dev *dev) return 0; -out_rx: - rc_free_rx_device(dev); +out_raw: + ir_raw_event_unregister(dev); out_dev: device_del(&dev->dev); out_unlock: diff --git a/drivers/media/rc/serial_ir.c b/drivers/media/rc/serial_ir.c index 923fb2299553..41b54e40176c 100644 --- a/drivers/media/rc/serial_ir.c +++ b/drivers/media/rc/serial_ir.c @@ -487,10 +487,69 @@ static void serial_ir_timeout(unsigned long arg) ir_raw_event_handle(serial_ir.rcdev); } +/* Needed by serial_ir_probe() */ +static int serial_ir_tx(struct rc_dev *dev, unsigned int *txbuf, + unsigned int count); +static int serial_ir_tx_duty_cycle(struct rc_dev *dev, u32 cycle); +static int serial_ir_tx_carrier(struct rc_dev *dev, u32 carrier); +static int serial_ir_open(struct rc_dev *rcdev); +static void serial_ir_close(struct rc_dev *rcdev); + static int serial_ir_probe(struct platform_device *dev) { + struct rc_dev *rcdev; int i, nlow, nhigh, result; + rcdev = devm_rc_allocate_device(&dev->dev, RC_DRIVER_IR_RAW); + if (!rcdev) + return -ENOMEM; + + if (hardware[type].send_pulse && hardware[type].send_space) + rcdev->tx_ir = serial_ir_tx; + if (hardware[type].set_send_carrier) + rcdev->s_tx_carrier = serial_ir_tx_carrier; + if (hardware[type].set_duty_cycle) + rcdev->s_tx_duty_cycle = serial_ir_tx_duty_cycle; + + switch (type) { + case IR_HOMEBREW: + rcdev->input_name = "Serial IR type home-brew"; + break; + case IR_IRDEO: + rcdev->input_name = "Serial IR type IRdeo"; + break; + case IR_IRDEO_REMOTE: + rcdev->input_name = "Serial IR type IRdeo remote"; + break; + case IR_ANIMAX: + rcdev->input_name = "Serial IR type AnimaX"; + break; + case IR_IGOR: + rcdev->input_name = "Serial IR type IgorPlug"; + break; + } + + rcdev->input_phys = KBUILD_MODNAME "/input0"; + rcdev->input_id.bustype = BUS_HOST; + rcdev->input_id.vendor = 0x0001; + rcdev->input_id.product = 0x0001; + rcdev->input_id.version = 0x0100; + rcdev->open = serial_ir_open; + rcdev->close = serial_ir_close; + rcdev->dev.parent = &serial_ir.pdev->dev; + rcdev->allowed_protocols = RC_BIT_ALL_IR_DECODER; + rcdev->driver_name = KBUILD_MODNAME; + rcdev->map_name = RC_MAP_RC6_MCE; + rcdev->min_timeout = 1; + rcdev->timeout = IR_DEFAULT_TIMEOUT; + rcdev->max_timeout = 10 * IR_DEFAULT_TIMEOUT; + rcdev->rx_resolution = 250000; + + serial_ir.rcdev = rcdev; + + setup_timer(&serial_ir.timeout_timer, serial_ir_timeout, + (unsigned long)&serial_ir); + result = devm_request_irq(&dev->dev, irq, serial_ir_irq_handler, share_irq ? IRQF_SHARED : 0, KBUILD_MODNAME, &hardware); @@ -516,9 +575,6 @@ static int serial_ir_probe(struct platform_device *dev) return -EBUSY; } - setup_timer(&serial_ir.timeout_timer, serial_ir_timeout, - (unsigned long)&serial_ir); - result = hardware_init_port(); if (result < 0) return result; @@ -552,7 +608,8 @@ static int serial_ir_probe(struct platform_device *dev) sense ? "low" : "high"); dev_dbg(&dev->dev, "Interrupt %d, port %04x obtained\n", irq, io); - return 0; + + return devm_rc_register_device(&dev->dev, rcdev); } static int serial_ir_open(struct rc_dev *rcdev) @@ -723,7 +780,6 @@ static void serial_ir_exit(void) static int __init serial_ir_init_module(void) { - struct rc_dev *rcdev; int result; switch (type) { @@ -754,63 +810,9 @@ static int __init serial_ir_init_module(void) sense = !!sense; result = serial_ir_init(); - if (result) - return result; - - rcdev = devm_rc_allocate_device(&serial_ir.pdev->dev, RC_DRIVER_IR_RAW); - if (!rcdev) { - result = -ENOMEM; - goto serial_cleanup; - } - - if (hardware[type].send_pulse && hardware[type].send_space) - rcdev->tx_ir = serial_ir_tx; - if (hardware[type].set_send_carrier) - rcdev->s_tx_carrier = serial_ir_tx_carrier; - if (hardware[type].set_duty_cycle) - rcdev->s_tx_duty_cycle = serial_ir_tx_duty_cycle; - - switch (type) { - case IR_HOMEBREW: - rcdev->input_name = "Serial IR type home-brew"; - break; - case IR_IRDEO: - rcdev->input_name = "Serial IR type IRdeo"; - break; - case IR_IRDEO_REMOTE: - rcdev->input_name = "Serial IR type IRdeo remote"; - break; - case IR_ANIMAX: - rcdev->input_name = "Serial IR type AnimaX"; - break; - case IR_IGOR: - rcdev->input_name = "Serial IR type IgorPlug"; - break; - } - - rcdev->input_phys = KBUILD_MODNAME "/input0"; - rcdev->input_id.bustype = BUS_HOST; - rcdev->input_id.vendor = 0x0001; - rcdev->input_id.product = 0x0001; - rcdev->input_id.version = 0x0100; - rcdev->open = serial_ir_open; - rcdev->close = serial_ir_close; - rcdev->dev.parent = &serial_ir.pdev->dev; - rcdev->allowed_protocols = RC_BIT_ALL_IR_DECODER; - rcdev->driver_name = KBUILD_MODNAME; - rcdev->map_name = RC_MAP_RC6_MCE; - rcdev->min_timeout = 1; - rcdev->timeout = IR_DEFAULT_TIMEOUT; - rcdev->max_timeout = 10 * IR_DEFAULT_TIMEOUT; - rcdev->rx_resolution = 250000; - - serial_ir.rcdev = rcdev; - - result = rc_register_device(rcdev); - if (!result) return 0; -serial_cleanup: + serial_ir_exit(); return result; } @@ -818,7 +820,6 @@ serial_cleanup: static void __exit serial_ir_exit_module(void) { del_timer_sync(&serial_ir.timeout_timer); - rc_unregister_device(serial_ir.rcdev); serial_ir_exit(); } diff --git a/drivers/media/usb/dvb-usb/dw2102.c b/drivers/media/usb/dvb-usb/dw2102.c index 6ca502d834b4..4f42d57f81d9 100644 --- a/drivers/media/usb/dvb-usb/dw2102.c +++ b/drivers/media/usb/dvb-usb/dw2102.c @@ -68,6 +68,7 @@ struct dw2102_state { u8 initialized; u8 last_lock; + u8 data[MAX_XFER_SIZE + 4]; struct i2c_client *i2c_client_demod; struct i2c_client *i2c_client_tuner; @@ -661,62 +662,72 @@ static int su3000_i2c_transfer(struct i2c_adapter *adap, struct i2c_msg msg[], int num) { struct dvb_usb_device *d = i2c_get_adapdata(adap); - u8 obuf[0x40], ibuf[0x40]; + struct dw2102_state *state; if (!d) return -ENODEV; + + state = d->priv; + if (mutex_lock_interruptible(&d->i2c_mutex) < 0) return -EAGAIN; + if (mutex_lock_interruptible(&d->data_mutex) < 0) { + mutex_unlock(&d->i2c_mutex); + return -EAGAIN; + } switch (num) { case 1: switch (msg[0].addr) { case SU3000_STREAM_CTRL: - obuf[0] = msg[0].buf[0] + 0x36; - obuf[1] = 3; - obuf[2] = 0; - if (dvb_usb_generic_rw(d, obuf, 3, ibuf, 0, 0) < 0) + state->data[0] = msg[0].buf[0] + 0x36; + state->data[1] = 3; + state->data[2] = 0; + if (dvb_usb_generic_rw(d, state->data, 3, + state->data, 0, 0) < 0) err("i2c transfer failed."); break; case DW2102_RC_QUERY: - obuf[0] = 0x10; - if (dvb_usb_generic_rw(d, obuf, 1, ibuf, 2, 0) < 0) + state->data[0] = 0x10; + if (dvb_usb_generic_rw(d, state->data, 1, + state->data, 2, 0) < 0) err("i2c transfer failed."); - msg[0].buf[1] = ibuf[0]; - msg[0].buf[0] = ibuf[1]; + msg[0].buf[1] = state->data[0]; + msg[0].buf[0] = state->data[1]; break; default: /* always i2c write*/ - obuf[0] = 0x08; - obuf[1] = msg[0].addr; - obuf[2] = msg[0].len; + state->data[0] = 0x08; + state->data[1] = msg[0].addr; + state->data[2] = msg[0].len; - memcpy(&obuf[3], msg[0].buf, msg[0].len); + memcpy(&state->data[3], msg[0].buf, msg[0].len); - if (dvb_usb_generic_rw(d, obuf, msg[0].len + 3, - ibuf, 1, 0) < 0) + if (dvb_usb_generic_rw(d, state->data, msg[0].len + 3, + state->data, 1, 0) < 0) err("i2c transfer failed."); } break; case 2: /* always i2c read */ - obuf[0] = 0x09; - obuf[1] = msg[0].len; - obuf[2] = msg[1].len; - obuf[3] = msg[0].addr; - memcpy(&obuf[4], msg[0].buf, msg[0].len); - - if (dvb_usb_generic_rw(d, obuf, msg[0].len + 4, - ibuf, msg[1].len + 1, 0) < 0) + state->data[0] = 0x09; + state->data[1] = msg[0].len; + state->data[2] = msg[1].len; + state->data[3] = msg[0].addr; + memcpy(&state->data[4], msg[0].buf, msg[0].len); + + if (dvb_usb_generic_rw(d, state->data, msg[0].len + 4, + state->data, msg[1].len + 1, 0) < 0) err("i2c transfer failed."); - memcpy(msg[1].buf, &ibuf[1], msg[1].len); + memcpy(msg[1].buf, &state->data[1], msg[1].len); break; default: warn("more than 2 i2c messages at a time is not handled yet."); break; } + mutex_unlock(&d->data_mutex); mutex_unlock(&d->i2c_mutex); return num; } @@ -844,17 +855,23 @@ static int su3000_streaming_ctrl(struct dvb_usb_adapter *adap, int onoff) static int su3000_power_ctrl(struct dvb_usb_device *d, int i) { struct dw2102_state *state = (struct dw2102_state *)d->priv; - u8 obuf[] = {0xde, 0}; + int ret = 0; info("%s: %d, initialized %d", __func__, i, state->initialized); if (i && !state->initialized) { + mutex_lock(&d->data_mutex); + + state->data[0] = 0xde; + state->data[1] = 0; + state->initialized = 1; /* reset board */ - return dvb_usb_generic_rw(d, obuf, 2, NULL, 0, 0); + ret = dvb_usb_generic_rw(d, state->data, 2, NULL, 0, 0); + mutex_unlock(&d->data_mutex); } - return 0; + return ret; } static int su3000_read_mac_address(struct dvb_usb_device *d, u8 mac[6]) @@ -1309,49 +1326,57 @@ static int prof_7500_frontend_attach(struct dvb_usb_adapter *d) return 0; } -static int su3000_frontend_attach(struct dvb_usb_adapter *d) +static int su3000_frontend_attach(struct dvb_usb_adapter *adap) { - u8 obuf[3] = { 0xe, 0x80, 0 }; - u8 ibuf[] = { 0 }; + struct dvb_usb_device *d = adap->dev; + struct dw2102_state *state = d->priv; + + mutex_lock(&d->data_mutex); + + state->data[0] = 0xe; + state->data[1] = 0x80; + state->data[2] = 0; - if (dvb_usb_generic_rw(d->dev, obuf, 3, ibuf, 1, 0) < 0) + if (dvb_usb_generic_rw(d, state->data, 3, state->data, 1, 0) < 0) err("command 0x0e transfer failed."); - obuf[0] = 0xe; - obuf[1] = 0x02; - obuf[2] = 1; + state->data[0] = 0xe; + state->data[1] = 0x02; + state->data[2] = 1; - if (dvb_usb_generic_rw(d->dev, obuf, 3, ibuf, 1, 0) < 0) + if (dvb_usb_generic_rw(d, state->data, 3, state->data, 1, 0) < 0) err("command 0x0e transfer failed."); msleep(300); - obuf[0] = 0xe; - obuf[1] = 0x83; - obuf[2] = 0; + state->data[0] = 0xe; + state->data[1] = 0x83; + state->data[2] = 0; - if (dvb_usb_generic_rw(d->dev, obuf, 3, ibuf, 1, 0) < 0) + if (dvb_usb_generic_rw(d, state->data, 3, state->data, 1, 0) < 0) err("command 0x0e transfer failed."); - obuf[0] = 0xe; - obuf[1] = 0x83; - obuf[2] = 1; + state->data[0] = 0xe; + state->data[1] = 0x83; + state->data[2] = 1; - if (dvb_usb_generic_rw(d->dev, obuf, 3, ibuf, 1, 0) < 0) + if (dvb_usb_generic_rw(d, state->data, 3, state->data, 1, 0) < 0) err("command 0x0e transfer failed."); - obuf[0] = 0x51; + state->data[0] = 0x51; - if (dvb_usb_generic_rw(d->dev, obuf, 1, ibuf, 1, 0) < 0) + if (dvb_usb_generic_rw(d, state->data, 1, state->data, 1, 0) < 0) err("command 0x51 transfer failed."); - d->fe_adap[0].fe = dvb_attach(ds3000_attach, &su3000_ds3000_config, - &d->dev->i2c_adap); - if (d->fe_adap[0].fe == NULL) + mutex_unlock(&d->data_mutex); + + adap->fe_adap[0].fe = dvb_attach(ds3000_attach, &su3000_ds3000_config, + &d->i2c_adap); + if (adap->fe_adap[0].fe == NULL) return -EIO; - if (dvb_attach(ts2020_attach, d->fe_adap[0].fe, + if (dvb_attach(ts2020_attach, adap->fe_adap[0].fe, &dw2104_ts2020_config, - &d->dev->i2c_adap)) { + &d->i2c_adap)) { info("Attached DS3000/TS2020!"); return 0; } @@ -1360,47 +1385,55 @@ static int su3000_frontend_attach(struct dvb_usb_adapter *d) return -EIO; } -static int t220_frontend_attach(struct dvb_usb_adapter *d) +static int t220_frontend_attach(struct dvb_usb_adapter *adap) { - u8 obuf[3] = { 0xe, 0x87, 0 }; - u8 ibuf[] = { 0 }; + struct dvb_usb_device *d = adap->dev; + struct dw2102_state *state = d->priv; + + mutex_lock(&d->data_mutex); - if (dvb_usb_generic_rw(d->dev, obuf, 3, ibuf, 1, 0) < 0) + state->data[0] = 0xe; + state->data[1] = 0x87; + state->data[2] = 0x0; + + if (dvb_usb_generic_rw(d, state->data, 3, state->data, 1, 0) < 0) err("command 0x0e transfer failed."); - obuf[0] = 0xe; - obuf[1] = 0x86; - obuf[2] = 1; + state->data[0] = 0xe; + state->data[1] = 0x86; + state->data[2] = 1; - if (dvb_usb_generic_rw(d->dev, obuf, 3, ibuf, 1, 0) < 0) + if (dvb_usb_generic_rw(d, state->data, 3, state->data, 1, 0) < 0) err("command 0x0e transfer failed."); - obuf[0] = 0xe; - obuf[1] = 0x80; - obuf[2] = 0; + state->data[0] = 0xe; + state->data[1] = 0x80; + state->data[2] = 0; - if (dvb_usb_generic_rw(d->dev, obuf, 3, ibuf, 1, 0) < 0) + if (dvb_usb_generic_rw(d, state->data, 3, state->data, 1, 0) < 0) err("command 0x0e transfer failed."); msleep(50); - obuf[0] = 0xe; - obuf[1] = 0x80; - obuf[2] = 1; + state->data[0] = 0xe; + state->data[1] = 0x80; + state->data[2] = 1; - if (dvb_usb_generic_rw(d->dev, obuf, 3, ibuf, 1, 0) < 0) + if (dvb_usb_generic_rw(d, state->data, 3, state->data, 1, 0) < 0) err("command 0x0e transfer failed."); - obuf[0] = 0x51; + state->data[0] = 0x51; - if (dvb_usb_generic_rw(d->dev, obuf, 1, ibuf, 1, 0) < 0) + if (dvb_usb_generic_rw(d, state->data, 1, state->data, 1, 0) < 0) err("command 0x51 transfer failed."); - d->fe_adap[0].fe = dvb_attach(cxd2820r_attach, &cxd2820r_config, - &d->dev->i2c_adap, NULL); - if (d->fe_adap[0].fe != NULL) { - if (dvb_attach(tda18271_attach, d->fe_adap[0].fe, 0x60, - &d->dev->i2c_adap, &tda18271_config)) { + mutex_unlock(&d->data_mutex); + + adap->fe_adap[0].fe = dvb_attach(cxd2820r_attach, &cxd2820r_config, + &d->i2c_adap, NULL); + if (adap->fe_adap[0].fe != NULL) { + if (dvb_attach(tda18271_attach, adap->fe_adap[0].fe, 0x60, + &d->i2c_adap, &tda18271_config)) { info("Attached TDA18271HD/CXD2820R!"); return 0; } @@ -1410,23 +1443,30 @@ static int t220_frontend_attach(struct dvb_usb_adapter *d) return -EIO; } -static int m88rs2000_frontend_attach(struct dvb_usb_adapter *d) +static int m88rs2000_frontend_attach(struct dvb_usb_adapter *adap) { - u8 obuf[] = { 0x51 }; - u8 ibuf[] = { 0 }; + struct dvb_usb_device *d = adap->dev; + struct dw2102_state *state = d->priv; + + mutex_lock(&d->data_mutex); - if (dvb_usb_generic_rw(d->dev, obuf, 1, ibuf, 1, 0) < 0) + state->data[0] = 0x51; + + if (dvb_usb_generic_rw(d, state->data, 1, state->data, 1, 0) < 0) err("command 0x51 transfer failed."); - d->fe_adap[0].fe = dvb_attach(m88rs2000_attach, &s421_m88rs2000_config, - &d->dev->i2c_adap); + mutex_unlock(&d->data_mutex); - if (d->fe_adap[0].fe == NULL) + adap->fe_adap[0].fe = dvb_attach(m88rs2000_attach, + &s421_m88rs2000_config, + &d->i2c_adap); + + if (adap->fe_adap[0].fe == NULL) return -EIO; - if (dvb_attach(ts2020_attach, d->fe_adap[0].fe, + if (dvb_attach(ts2020_attach, adap->fe_adap[0].fe, &dw2104_ts2020_config, - &d->dev->i2c_adap)) { + &d->i2c_adap)) { info("Attached RS2000/TS2020!"); return 0; } @@ -1439,44 +1479,50 @@ static int tt_s2_4600_frontend_attach(struct dvb_usb_adapter *adap) { struct dvb_usb_device *d = adap->dev; struct dw2102_state *state = d->priv; - u8 obuf[3] = { 0xe, 0x80, 0 }; - u8 ibuf[] = { 0 }; struct i2c_adapter *i2c_adapter; struct i2c_client *client; struct i2c_board_info board_info; struct m88ds3103_platform_data m88ds3103_pdata = {}; struct ts2020_config ts2020_config = {}; - if (dvb_usb_generic_rw(d, obuf, 3, ibuf, 1, 0) < 0) + mutex_lock(&d->data_mutex); + + state->data[0] = 0xe; + state->data[1] = 0x80; + state->data[2] = 0x0; + + if (dvb_usb_generic_rw(d, state->data, 3, state->data, 1, 0) < 0) err("command 0x0e transfer failed."); - obuf[0] = 0xe; - obuf[1] = 0x02; - obuf[2] = 1; + state->data[0] = 0xe; + state->data[1] = 0x02; + state->data[2] = 1; - if (dvb_usb_generic_rw(d, obuf, 3, ibuf, 1, 0) < 0) + if (dvb_usb_generic_rw(d, state->data, 3, state->data, 1, 0) < 0) err("command 0x0e transfer failed."); msleep(300); - obuf[0] = 0xe; - obuf[1] = 0x83; - obuf[2] = 0; + state->data[0] = 0xe; + state->data[1] = 0x83; + state->data[2] = 0; - if (dvb_usb_generic_rw(d, obuf, 3, ibuf, 1, 0) < 0) + if (dvb_usb_generic_rw(d, state->data, 3, state->data, 1, 0) < 0) err("command 0x0e transfer failed."); - obuf[0] = 0xe; - obuf[1] = 0x83; - obuf[2] = 1; + state->data[0] = 0xe; + state->data[1] = 0x83; + state->data[2] = 1; - if (dvb_usb_generic_rw(d, obuf, 3, ibuf, 1, 0) < 0) + if (dvb_usb_generic_rw(d, state->data, 3, state->data, 1, 0) < 0) err("command 0x0e transfer failed."); - obuf[0] = 0x51; + state->data[0] = 0x51; - if (dvb_usb_generic_rw(d, obuf, 1, ibuf, 1, 0) < 0) + if (dvb_usb_generic_rw(d, state->data, 1, state->data, 1, 0) < 0) err("command 0x51 transfer failed."); + mutex_unlock(&d->data_mutex); + /* attach demod */ m88ds3103_pdata.clk = 27000000; m88ds3103_pdata.i2c_wr_max = 33; diff --git a/drivers/misc/sgi-gru/grufault.c b/drivers/misc/sgi-gru/grufault.c index 6fb773dbcd0c..93be82fc338a 100644 --- a/drivers/misc/sgi-gru/grufault.c +++ b/drivers/misc/sgi-gru/grufault.c @@ -219,15 +219,20 @@ static int atomic_pte_lookup(struct vm_area_struct *vma, unsigned long vaddr, int write, unsigned long *paddr, int *pageshift) { pgd_t *pgdp; - pmd_t *pmdp; + p4d_t *p4dp; pud_t *pudp; + pmd_t *pmdp; pte_t pte; pgdp = pgd_offset(vma->vm_mm, vaddr); if (unlikely(pgd_none(*pgdp))) goto err; - pudp = pud_offset(pgdp, vaddr); + p4dp = p4d_offset(pgdp, vaddr); + if (unlikely(p4d_none(*p4dp))) + goto err; + + pudp = pud_offset(p4dp, vaddr); if (unlikely(pud_none(*pudp))) goto err; diff --git a/drivers/mtd/spi-nor/spi-nor.c b/drivers/mtd/spi-nor/spi-nor.c index 1ae872bfc3ba..747645c74134 100644 --- a/drivers/mtd/spi-nor/spi-nor.c +++ b/drivers/mtd/spi-nor/spi-nor.c @@ -186,7 +186,7 @@ static inline int write_enable(struct spi_nor *nor) } /* - * Send write disble instruction to the chip. + * Send write disable instruction to the chip. */ static inline int write_disable(struct spi_nor *nor) { diff --git a/drivers/net/bonding/bond_3ad.c b/drivers/net/bonding/bond_3ad.c index edc70ffad660..508713b4e533 100644 --- a/drivers/net/bonding/bond_3ad.c +++ b/drivers/net/bonding/bond_3ad.c @@ -92,6 +92,7 @@ enum ad_link_speed_type { AD_LINK_SPEED_2500MBPS, AD_LINK_SPEED_10000MBPS, AD_LINK_SPEED_20000MBPS, + AD_LINK_SPEED_25000MBPS, AD_LINK_SPEED_40000MBPS, AD_LINK_SPEED_56000MBPS, AD_LINK_SPEED_100000MBPS, @@ -260,6 +261,7 @@ static inline int __check_agg_selection_timer(struct port *port) * %AD_LINK_SPEED_2500MBPS, * %AD_LINK_SPEED_10000MBPS * %AD_LINK_SPEED_20000MBPS + * %AD_LINK_SPEED_25000MBPS * %AD_LINK_SPEED_40000MBPS * %AD_LINK_SPEED_56000MBPS * %AD_LINK_SPEED_100000MBPS @@ -302,6 +304,10 @@ static u16 __get_link_speed(struct port *port) speed = AD_LINK_SPEED_20000MBPS; break; + case SPEED_25000: + speed = AD_LINK_SPEED_25000MBPS; + break; + case SPEED_40000: speed = AD_LINK_SPEED_40000MBPS; break; @@ -707,6 +713,9 @@ static u32 __get_agg_bandwidth(struct aggregator *aggregator) case AD_LINK_SPEED_20000MBPS: bandwidth = nports * 20000; break; + case AD_LINK_SPEED_25000MBPS: + bandwidth = nports * 25000; + break; case AD_LINK_SPEED_40000MBPS: bandwidth = nports * 40000; break; @@ -1052,8 +1061,7 @@ static void ad_rx_machine(struct lacpdu *lacpdu, struct port *port) port->sm_rx_state = AD_RX_INITIALIZE; port->sm_vars |= AD_PORT_CHURNED; /* check if port is not enabled */ - } else if (!(port->sm_vars & AD_PORT_BEGIN) - && !port->is_enabled && !(port->sm_vars & AD_PORT_MOVED)) + } else if (!(port->sm_vars & AD_PORT_BEGIN) && !port->is_enabled) port->sm_rx_state = AD_RX_PORT_DISABLED; /* check if new lacpdu arrived */ else if (lacpdu && ((port->sm_rx_state == AD_RX_EXPIRED) || @@ -1081,11 +1089,8 @@ static void ad_rx_machine(struct lacpdu *lacpdu, struct port *port) /* if no lacpdu arrived and no timer is on */ switch (port->sm_rx_state) { case AD_RX_PORT_DISABLED: - if (port->sm_vars & AD_PORT_MOVED) - port->sm_rx_state = AD_RX_INITIALIZE; - else if (port->is_enabled - && (port->sm_vars - & AD_PORT_LACP_ENABLED)) + if (port->is_enabled && + (port->sm_vars & AD_PORT_LACP_ENABLED)) port->sm_rx_state = AD_RX_EXPIRED; else if (port->is_enabled && ((port->sm_vars @@ -1115,7 +1120,6 @@ static void ad_rx_machine(struct lacpdu *lacpdu, struct port *port) port->sm_vars &= ~AD_PORT_SELECTED; __record_default(port); port->actor_oper_port_state &= ~AD_STATE_EXPIRED; - port->sm_vars &= ~AD_PORT_MOVED; port->sm_rx_state = AD_RX_PORT_DISABLED; /* Fall Through */ diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 8a4ba8b88e52..ba934020dfaa 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -201,12 +201,6 @@ atomic_t netpoll_block_tx = ATOMIC_INIT(0); unsigned int bond_net_id __read_mostly; -static __be32 arp_target[BOND_MAX_ARP_TARGETS]; -static int arp_ip_count; -static int bond_mode = BOND_MODE_ROUNDROBIN; -static int xmit_hashtype = BOND_XMIT_POLICY_LAYER2; -static int lacp_fast; - /*-------------------------- Forward declarations ---------------------------*/ static int bond_init(struct net_device *bond_dev); @@ -2575,10 +2569,8 @@ static bool bond_time_in_interval(struct bonding *bond, unsigned long last_act, * arp is transmitted to generate traffic. see activebackup_arp_monitor for * arp monitoring in active backup mode. */ -static void bond_loadbalance_arp_mon(struct work_struct *work) +static void bond_loadbalance_arp_mon(struct bonding *bond) { - struct bonding *bond = container_of(work, struct bonding, - arp_work.work); struct slave *slave, *oldcurrent; struct list_head *iter; int do_failover = 0, slave_state_changed = 0; @@ -2916,10 +2908,8 @@ check_state: return should_notify_rtnl; } -static void bond_activebackup_arp_mon(struct work_struct *work) +static void bond_activebackup_arp_mon(struct bonding *bond) { - struct bonding *bond = container_of(work, struct bonding, - arp_work.work); bool should_notify_peers = false; bool should_notify_rtnl = false; int delta_in_ticks; @@ -2972,6 +2962,17 @@ re_arm: } } +static void bond_arp_monitor(struct work_struct *work) +{ + struct bonding *bond = container_of(work, struct bonding, + arp_work.work); + + if (BOND_MODE(bond) == BOND_MODE_ACTIVEBACKUP) + bond_activebackup_arp_mon(bond); + else + bond_loadbalance_arp_mon(bond); +} + /*-------------------------- netdev event handling --------------------------*/ /* Change device name */ @@ -3228,10 +3229,7 @@ static void bond_work_init_all(struct bonding *bond) bond_resend_igmp_join_requests_delayed); INIT_DELAYED_WORK(&bond->alb_work, bond_alb_monitor); INIT_DELAYED_WORK(&bond->mii_work, bond_mii_monitor); - if (BOND_MODE(bond) == BOND_MODE_ACTIVEBACKUP) - INIT_DELAYED_WORK(&bond->arp_work, bond_activebackup_arp_mon); - else - INIT_DELAYED_WORK(&bond->arp_work, bond_loadbalance_arp_mon); + INIT_DELAYED_WORK(&bond->arp_work, bond_arp_monitor); INIT_DELAYED_WORK(&bond->ad_work, bond_3ad_state_machine_handler); INIT_DELAYED_WORK(&bond->slave_arr_work, bond_slave_arr_handler); } @@ -3266,8 +3264,6 @@ static int bond_open(struct net_device *bond_dev) } } - bond_work_init_all(bond); - if (bond_is_lb(bond)) { /* bond_alb_initialize must be called before the timer * is started. @@ -4252,6 +4248,12 @@ static int bond_check_params(struct bond_params *params) int arp_all_targets_value; u16 ad_actor_sys_prio = 0; u16 ad_user_port_key = 0; + __be32 arp_target[BOND_MAX_ARP_TARGETS]; + int arp_ip_count; + int bond_mode = BOND_MODE_ROUNDROBIN; + int xmit_hashtype = BOND_XMIT_POLICY_LAYER2; + int lacp_fast = 0; + int tlb_dynamic_lb = 0; /* Convert string parameters. */ if (mode) { @@ -4564,6 +4566,17 @@ static int bond_check_params(struct bond_params *params) } ad_user_port_key = valptr->value; + if (bond_mode == BOND_MODE_TLB) { + bond_opt_initstr(&newval, "default"); + valptr = bond_opt_parse(bond_opt_get(BOND_OPT_TLB_DYNAMIC_LB), + &newval); + if (!valptr) { + pr_err("Error: No tlb_dynamic_lb default value"); + return -EINVAL; + } + tlb_dynamic_lb = valptr->value; + } + if (lp_interval == 0) { pr_warn("Warning: ip_interval must be between 1 and %d, so it was reset to %d\n", INT_MAX, BOND_ALB_DEFAULT_LP_INTERVAL); @@ -4591,7 +4604,7 @@ static int bond_check_params(struct bond_params *params) params->min_links = min_links; params->lp_interval = lp_interval; params->packets_per_slave = packets_per_slave; - params->tlb_dynamic_lb = 1; /* Default value */ + params->tlb_dynamic_lb = tlb_dynamic_lb; params->ad_actor_sys_prio = ad_actor_sys_prio; eth_zero_addr(params->ad_actor_system); params->ad_user_port_key = ad_user_port_key; @@ -4687,6 +4700,8 @@ int bond_create(struct net *net, const char *name) netif_carrier_off(bond_dev); + bond_work_init_all(bond); + rtnl_unlock(); if (res < 0) bond_destructor(bond_dev); diff --git a/drivers/net/dsa/mv88e6xxx/Makefile b/drivers/net/dsa/mv88e6xxx/Makefile index c36be318de1a..31d37a90cec7 100644 --- a/drivers/net/dsa/mv88e6xxx/Makefile +++ b/drivers/net/dsa/mv88e6xxx/Makefile @@ -1,5 +1,6 @@ obj-$(CONFIG_NET_DSA_MV88E6XXX) += mv88e6xxx.o mv88e6xxx-objs := chip.o mv88e6xxx-objs += global1.o +mv88e6xxx-objs += global1_atu.o mv88e6xxx-$(CONFIG_NET_DSA_MV88E6XXX_GLOBAL2) += global2.o mv88e6xxx-objs += port.o diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c index 03dc886ed3d6..2bca297d9296 100644 --- a/drivers/net/dsa/mv88e6xxx/chip.c +++ b/drivers/net/dsa/mv88e6xxx/chip.c @@ -687,11 +687,6 @@ static bool mv88e6xxx_6165_family(struct mv88e6xxx_chip *chip) return chip->info->family == MV88E6XXX_FAMILY_6165; } -static bool mv88e6xxx_6320_family(struct mv88e6xxx_chip *chip) -{ - return chip->info->family == MV88E6XXX_FAMILY_6320; -} - static bool mv88e6xxx_6341_family(struct mv88e6xxx_chip *chip) { return chip->info->family == MV88E6XXX_FAMILY_6341; @@ -1066,11 +1061,6 @@ static void mv88e6xxx_get_regs(struct dsa_switch *ds, int port, mutex_unlock(&chip->reg_lock); } -static int _mv88e6xxx_atu_wait(struct mv88e6xxx_chip *chip) -{ - return mv88e6xxx_g1_wait(chip, GLOBAL_ATU_OP, GLOBAL_ATU_OP_BUSY); -} - static int mv88e6xxx_get_eee(struct dsa_switch *ds, int port, struct ethtool_eee *e) { @@ -1130,122 +1120,6 @@ out: return err; } -static int _mv88e6xxx_atu_cmd(struct mv88e6xxx_chip *chip, u16 fid, u16 cmd) -{ - u16 val; - int err; - - if (mv88e6xxx_has(chip, MV88E6XXX_FLAG_G1_ATU_FID)) { - err = mv88e6xxx_g1_write(chip, GLOBAL_ATU_FID, fid); - if (err) - return err; - } else if (mv88e6xxx_num_databases(chip) == 256) { - /* ATU DBNum[7:4] are located in ATU Control 15:12 */ - err = mv88e6xxx_g1_read(chip, GLOBAL_ATU_CONTROL, &val); - if (err) - return err; - - err = mv88e6xxx_g1_write(chip, GLOBAL_ATU_CONTROL, - (val & 0xfff) | ((fid << 8) & 0xf000)); - if (err) - return err; - - /* ATU DBNum[3:0] are located in ATU Operation 3:0 */ - cmd |= fid & 0xf; - } - - err = mv88e6xxx_g1_write(chip, GLOBAL_ATU_OP, cmd); - if (err) - return err; - - return _mv88e6xxx_atu_wait(chip); -} - -static int _mv88e6xxx_atu_data_write(struct mv88e6xxx_chip *chip, - struct mv88e6xxx_atu_entry *entry) -{ - u16 data = entry->state & GLOBAL_ATU_DATA_STATE_MASK; - - if (entry->state != GLOBAL_ATU_DATA_STATE_UNUSED) { - unsigned int mask, shift; - - if (entry->trunk) { - data |= GLOBAL_ATU_DATA_TRUNK; - mask = GLOBAL_ATU_DATA_TRUNK_ID_MASK; - shift = GLOBAL_ATU_DATA_TRUNK_ID_SHIFT; - } else { - mask = GLOBAL_ATU_DATA_PORT_VECTOR_MASK; - shift = GLOBAL_ATU_DATA_PORT_VECTOR_SHIFT; - } - - data |= (entry->portv_trunkid << shift) & mask; - } - - return mv88e6xxx_g1_write(chip, GLOBAL_ATU_DATA, data); -} - -static int _mv88e6xxx_atu_flush_move(struct mv88e6xxx_chip *chip, - struct mv88e6xxx_atu_entry *entry, - bool static_too) -{ - int op; - int err; - - err = _mv88e6xxx_atu_wait(chip); - if (err) - return err; - - err = _mv88e6xxx_atu_data_write(chip, entry); - if (err) - return err; - - if (entry->fid) { - op = static_too ? GLOBAL_ATU_OP_FLUSH_MOVE_ALL_DB : - GLOBAL_ATU_OP_FLUSH_MOVE_NON_STATIC_DB; - } else { - op = static_too ? GLOBAL_ATU_OP_FLUSH_MOVE_ALL : - GLOBAL_ATU_OP_FLUSH_MOVE_NON_STATIC; - } - - return _mv88e6xxx_atu_cmd(chip, entry->fid, op); -} - -static int _mv88e6xxx_atu_flush(struct mv88e6xxx_chip *chip, - u16 fid, bool static_too) -{ - struct mv88e6xxx_atu_entry entry = { - .fid = fid, - .state = 0, /* EntryState bits must be 0 */ - }; - - return _mv88e6xxx_atu_flush_move(chip, &entry, static_too); -} - -static int _mv88e6xxx_atu_move(struct mv88e6xxx_chip *chip, u16 fid, - int from_port, int to_port, bool static_too) -{ - struct mv88e6xxx_atu_entry entry = { - .trunk = false, - .fid = fid, - }; - - /* EntryState bits must be 0xF */ - entry.state = GLOBAL_ATU_DATA_STATE_MASK; - - /* ToPort and FromPort are respectively in PortVec bits 7:4 and 3:0 */ - entry.portv_trunkid = (to_port & 0x0f) << 4; - entry.portv_trunkid |= from_port & 0x0f; - - return _mv88e6xxx_atu_flush_move(chip, &entry, static_too); -} - -static int _mv88e6xxx_atu_remove(struct mv88e6xxx_chip *chip, u16 fid, - int port, bool static_too) -{ - /* Destination port 0xF means remove the entries */ - return _mv88e6xxx_atu_move(chip, fid, port, 0x0f, static_too); -} - static int _mv88e6xxx_port_based_vlan_map(struct mv88e6xxx_chip *chip, int port) { struct dsa_switch *ds = chip->ds; @@ -1306,13 +1180,28 @@ static void mv88e6xxx_port_stp_state_set(struct dsa_switch *ds, int port, netdev_err(ds->ports[port].netdev, "failed to update state\n"); } +static int mv88e6xxx_atu_setup(struct mv88e6xxx_chip *chip) +{ + int err; + + err = mv88e6xxx_g1_atu_flush(chip, 0, true); + if (err) + return err; + + err = mv88e6xxx_g1_atu_set_learn2all(chip, true); + if (err) + return err; + + return mv88e6xxx_g1_atu_set_age_time(chip, 300000); +} + static void mv88e6xxx_port_fast_age(struct dsa_switch *ds, int port) { struct mv88e6xxx_chip *chip = ds->priv; int err; mutex_lock(&chip->reg_lock); - err = _mv88e6xxx_atu_remove(chip, 0, port, false); + err = mv88e6xxx_g1_atu_remove(chip, 0, port, false); mutex_unlock(&chip->reg_lock); if (err) @@ -1662,7 +1551,7 @@ loadpurge: return _mv88e6xxx_vtu_cmd(chip, GLOBAL_VTU_OP_STU_LOAD_PURGE); } -static int _mv88e6xxx_fid_new(struct mv88e6xxx_chip *chip, u16 *fid) +static int mv88e6xxx_atu_new(struct mv88e6xxx_chip *chip, u16 *fid) { DECLARE_BITMAP(fid_bitmap, MV88E6XXX_N_FID); struct mv88e6xxx_vtu_entry vlan; @@ -1703,7 +1592,7 @@ static int _mv88e6xxx_fid_new(struct mv88e6xxx_chip *chip, u16 *fid) return -ENOSPC; /* Clear the database */ - return _mv88e6xxx_atu_flush(chip, *fid, true); + return mv88e6xxx_g1_atu_flush(chip, *fid, true); } static int _mv88e6xxx_vtu_new(struct mv88e6xxx_chip *chip, u16 vid, @@ -1716,7 +1605,7 @@ static int _mv88e6xxx_vtu_new(struct mv88e6xxx_chip *chip, u16 vid, }; int i, err; - err = _mv88e6xxx_fid_new(chip, &vlan.fid); + err = mv88e6xxx_atu_new(chip, &vlan.fid); if (err) return err; @@ -1964,7 +1853,7 @@ static int _mv88e6xxx_port_vlan_del(struct mv88e6xxx_chip *chip, if (err) return err; - return _mv88e6xxx_atu_remove(chip, vlan.fid, port, false); + return mv88e6xxx_g1_atu_remove(chip, vlan.fid, port, false); } static int mv88e6xxx_port_vlan_del(struct dsa_switch *ds, int port, @@ -2001,96 +1890,6 @@ unlock: return err; } -static int _mv88e6xxx_atu_mac_write(struct mv88e6xxx_chip *chip, - const unsigned char *addr) -{ - int i, err; - - for (i = 0; i < 3; i++) { - err = mv88e6xxx_g1_write(chip, GLOBAL_ATU_MAC_01 + i, - (addr[i * 2] << 8) | addr[i * 2 + 1]); - if (err) - return err; - } - - return 0; -} - -static int _mv88e6xxx_atu_mac_read(struct mv88e6xxx_chip *chip, - unsigned char *addr) -{ - u16 val; - int i, err; - - for (i = 0; i < 3; i++) { - err = mv88e6xxx_g1_read(chip, GLOBAL_ATU_MAC_01 + i, &val); - if (err) - return err; - - addr[i * 2] = val >> 8; - addr[i * 2 + 1] = val & 0xff; - } - - return 0; -} - -static int _mv88e6xxx_atu_load(struct mv88e6xxx_chip *chip, - struct mv88e6xxx_atu_entry *entry) -{ - int ret; - - ret = _mv88e6xxx_atu_wait(chip); - if (ret < 0) - return ret; - - ret = _mv88e6xxx_atu_mac_write(chip, entry->mac); - if (ret < 0) - return ret; - - ret = _mv88e6xxx_atu_data_write(chip, entry); - if (ret < 0) - return ret; - - return _mv88e6xxx_atu_cmd(chip, entry->fid, GLOBAL_ATU_OP_LOAD_DB); -} - -static int _mv88e6xxx_atu_getnext(struct mv88e6xxx_chip *chip, u16 fid, - struct mv88e6xxx_atu_entry *entry); - -static int mv88e6xxx_atu_get(struct mv88e6xxx_chip *chip, int fid, - const u8 *addr, struct mv88e6xxx_atu_entry *entry) -{ - struct mv88e6xxx_atu_entry next; - int err; - - memcpy(next.mac, addr, ETH_ALEN); - eth_addr_dec(next.mac); - - err = _mv88e6xxx_atu_mac_write(chip, next.mac); - if (err) - return err; - - do { - err = _mv88e6xxx_atu_getnext(chip, fid, &next); - if (err) - return err; - - if (next.state == GLOBAL_ATU_DATA_STATE_UNUSED) - break; - - if (ether_addr_equal(next.mac, addr)) { - *entry = next; - return 0; - } - } while (ether_addr_greater(addr, next.mac)); - - memset(entry, 0, sizeof(*entry)); - entry->fid = fid; - ether_addr_copy(entry->mac, addr); - - return 0; -} - static int mv88e6xxx_port_db_load_purge(struct mv88e6xxx_chip *chip, int port, const unsigned char *addr, u16 vid, u8 state) @@ -2107,21 +1906,32 @@ static int mv88e6xxx_port_db_load_purge(struct mv88e6xxx_chip *chip, int port, if (err) return err; - err = mv88e6xxx_atu_get(chip, vlan.fid, addr, &entry); + entry.state = GLOBAL_ATU_DATA_STATE_UNUSED; + ether_addr_copy(entry.mac, addr); + eth_addr_dec(entry.mac); + + err = mv88e6xxx_g1_atu_getnext(chip, vlan.fid, &entry); if (err) return err; + /* Initialize a fresh ATU entry if it isn't found */ + if (entry.state == GLOBAL_ATU_DATA_STATE_UNUSED || + !ether_addr_equal(entry.mac, addr)) { + memset(&entry, 0, sizeof(entry)); + ether_addr_copy(entry.mac, addr); + } + /* Purge the ATU entry only if no port is using it anymore */ if (state == GLOBAL_ATU_DATA_STATE_UNUSED) { - entry.portv_trunkid &= ~BIT(port); - if (!entry.portv_trunkid) + entry.portvec &= ~BIT(port); + if (!entry.portvec) entry.state = GLOBAL_ATU_DATA_STATE_UNUSED; } else { - entry.portv_trunkid |= BIT(port); + entry.portvec |= BIT(port); entry.state = state; } - return _mv88e6xxx_atu_load(chip, &entry); + return mv88e6xxx_g1_atu_loadpurge(chip, vlan.fid, &entry); } static int mv88e6xxx_port_fdb_prepare(struct dsa_switch *ds, int port, @@ -2161,75 +1971,26 @@ static int mv88e6xxx_port_fdb_del(struct dsa_switch *ds, int port, return err; } -static int _mv88e6xxx_atu_getnext(struct mv88e6xxx_chip *chip, u16 fid, - struct mv88e6xxx_atu_entry *entry) -{ - struct mv88e6xxx_atu_entry next = { 0 }; - u16 val; - int err; - - next.fid = fid; - - err = _mv88e6xxx_atu_wait(chip); - if (err) - return err; - - err = _mv88e6xxx_atu_cmd(chip, fid, GLOBAL_ATU_OP_GET_NEXT_DB); - if (err) - return err; - - err = _mv88e6xxx_atu_mac_read(chip, next.mac); - if (err) - return err; - - err = mv88e6xxx_g1_read(chip, GLOBAL_ATU_DATA, &val); - if (err) - return err; - - next.state = val & GLOBAL_ATU_DATA_STATE_MASK; - if (next.state != GLOBAL_ATU_DATA_STATE_UNUSED) { - unsigned int mask, shift; - - if (val & GLOBAL_ATU_DATA_TRUNK) { - next.trunk = true; - mask = GLOBAL_ATU_DATA_TRUNK_ID_MASK; - shift = GLOBAL_ATU_DATA_TRUNK_ID_SHIFT; - } else { - next.trunk = false; - mask = GLOBAL_ATU_DATA_PORT_VECTOR_MASK; - shift = GLOBAL_ATU_DATA_PORT_VECTOR_SHIFT; - } - - next.portv_trunkid = (val & mask) >> shift; - } - - *entry = next; - return 0; -} - static int mv88e6xxx_port_db_dump_fid(struct mv88e6xxx_chip *chip, u16 fid, u16 vid, int port, struct switchdev_obj *obj, int (*cb)(struct switchdev_obj *obj)) { - struct mv88e6xxx_atu_entry addr = { - .mac = { 0xff, 0xff, 0xff, 0xff, 0xff, 0xff }, - }; + struct mv88e6xxx_atu_entry addr; int err; - err = _mv88e6xxx_atu_mac_write(chip, addr.mac); - if (err) - return err; + addr.state = GLOBAL_ATU_DATA_STATE_UNUSED; + eth_broadcast_addr(addr.mac); do { - err = _mv88e6xxx_atu_getnext(chip, fid, &addr); + err = mv88e6xxx_g1_atu_getnext(chip, fid, &addr); if (err) return err; if (addr.state == GLOBAL_ATU_DATA_STATE_UNUSED) break; - if (addr.trunk || (addr.portv_trunkid & BIT(port)) == 0) + if (addr.trunk || (addr.portvec & BIT(port)) == 0) continue; if (obj->id == SWITCHDEV_OBJ_ID_PORT_FDB) { @@ -2433,70 +2194,85 @@ static int mv88e6xxx_serdes_power_on(struct mv88e6xxx_chip *chip) return err; } -static int mv88e6xxx_setup_port_dsa(struct mv88e6xxx_chip *chip, int port, - int upstream_port) +static int mv88e6xxx_set_port_mode(struct mv88e6xxx_chip *chip, int port, + enum mv88e6xxx_frame_mode frame, u16 egress, + u16 etype) { int err; - err = chip->info->ops->port_set_frame_mode( - chip, port, MV88E6XXX_FRAME_MODE_DSA); + if (!chip->info->ops->port_set_frame_mode) + return -EOPNOTSUPP; + + err = mv88e6xxx_port_set_egress_mode(chip, port, egress); + if (err) + return err; + + err = chip->info->ops->port_set_frame_mode(chip, port, frame); if (err) return err; - return chip->info->ops->port_set_egress_unknowns( - chip, port, port == upstream_port); + if (chip->info->ops->port_set_ether_type) + return chip->info->ops->port_set_ether_type(chip, port, etype); + + return 0; } -static int mv88e6xxx_setup_port_cpu(struct mv88e6xxx_chip *chip, int port) +static int mv88e6xxx_set_port_mode_normal(struct mv88e6xxx_chip *chip, int port) { - int err; + return mv88e6xxx_set_port_mode(chip, port, MV88E6XXX_FRAME_MODE_NORMAL, + PORT_CONTROL_EGRESS_UNMODIFIED, + PORT_ETH_TYPE_DEFAULT); +} - switch (chip->info->tag_protocol) { - case DSA_TAG_PROTO_EDSA: - err = chip->info->ops->port_set_frame_mode( - chip, port, MV88E6XXX_FRAME_MODE_ETHERTYPE); - if (err) - return err; +static int mv88e6xxx_set_port_mode_dsa(struct mv88e6xxx_chip *chip, int port) +{ + return mv88e6xxx_set_port_mode(chip, port, MV88E6XXX_FRAME_MODE_DSA, + PORT_CONTROL_EGRESS_UNMODIFIED, + PORT_ETH_TYPE_DEFAULT); +} - err = mv88e6xxx_port_set_egress_mode( - chip, port, PORT_CONTROL_EGRESS_ADD_TAG); - if (err) - return err; +static int mv88e6xxx_set_port_mode_edsa(struct mv88e6xxx_chip *chip, int port) +{ + return mv88e6xxx_set_port_mode(chip, port, + MV88E6XXX_FRAME_MODE_ETHERTYPE, + PORT_CONTROL_EGRESS_ADD_TAG, ETH_P_EDSA); +} - if (chip->info->ops->port_set_ether_type) - err = chip->info->ops->port_set_ether_type( - chip, port, ETH_P_EDSA); - break; +static int mv88e6xxx_setup_port_mode(struct mv88e6xxx_chip *chip, int port) +{ + if (dsa_is_dsa_port(chip->ds, port)) + return mv88e6xxx_set_port_mode_dsa(chip, port); - case DSA_TAG_PROTO_DSA: - err = chip->info->ops->port_set_frame_mode( - chip, port, MV88E6XXX_FRAME_MODE_DSA); - if (err) - return err; + if (dsa_is_normal_port(chip->ds, port)) + return mv88e6xxx_set_port_mode_normal(chip, port); - err = mv88e6xxx_port_set_egress_mode( - chip, port, PORT_CONTROL_EGRESS_UNMODIFIED); - break; - default: - err = -EINVAL; - } + /* Setup CPU port mode depending on its supported tag format */ + if (chip->info->tag_protocol == DSA_TAG_PROTO_DSA) + return mv88e6xxx_set_port_mode_dsa(chip, port); - if (err) - return err; + if (chip->info->tag_protocol == DSA_TAG_PROTO_EDSA) + return mv88e6xxx_set_port_mode_edsa(chip, port); - return chip->info->ops->port_set_egress_unknowns(chip, port, true); + return -EINVAL; } -static int mv88e6xxx_setup_port_normal(struct mv88e6xxx_chip *chip, int port) +static int mv88e6xxx_setup_message_port(struct mv88e6xxx_chip *chip, int port) { - int err; + bool message = dsa_is_dsa_port(chip->ds, port); - err = chip->info->ops->port_set_frame_mode( - chip, port, MV88E6XXX_FRAME_MODE_NORMAL); - if (err) - return err; + return mv88e6xxx_port_set_message_port(chip, port, message); +} - return chip->info->ops->port_set_egress_unknowns(chip, port, false); +static int mv88e6xxx_setup_egress_floods(struct mv88e6xxx_chip *chip, int port) +{ + bool flood = port == dsa_upstream_port(chip->ds); + + /* Upstream ports flood frames with unknown unicast or multicast DA */ + if (chip->info->ops->port_set_egress_floods) + return chip->info->ops->port_set_egress_floods(chip, port, + flood, flood); + + return 0; } static int mv88e6xxx_setup_port(struct mv88e6xxx_chip *chip, int port) @@ -2541,14 +2317,11 @@ static int mv88e6xxx_setup_port(struct mv88e6xxx_chip *chip, int port) if (err) return err; - if (dsa_is_cpu_port(ds, port)) { - err = mv88e6xxx_setup_port_cpu(chip, port); - } else if (dsa_is_dsa_port(ds, port)) { - err = mv88e6xxx_setup_port_dsa(chip, port, - dsa_upstream_port(ds)); - } else { - err = mv88e6xxx_setup_port_normal(chip, port); - } + err = mv88e6xxx_setup_port_mode(chip, port); + if (err) + return err; + + err = mv88e6xxx_setup_egress_floods(chip, port); if (err) return err; @@ -2623,20 +2396,14 @@ static int mv88e6xxx_setup_port(struct mv88e6xxx_chip *chip, int port) return err; } - if (mv88e6xxx_6352_family(chip) || mv88e6xxx_6351_family(chip) || - mv88e6xxx_6165_family(chip) || mv88e6xxx_6097_family(chip) || - mv88e6xxx_6320_family(chip) || mv88e6xxx_6341_family(chip)) { - /* Port ATU control: disable limiting the number of - * address database entries that this port is allowed - * to use. - */ - err = mv88e6xxx_port_write(chip, port, PORT_ATU_CONTROL, - 0x0000); - /* Priority Override: disable DA, SA and VTU priority - * override. - */ - err = mv88e6xxx_port_write(chip, port, PORT_PRI_OVERRIDE, - 0x0000); + if (chip->info->ops->port_disable_learn_limit) { + err = chip->info->ops->port_disable_learn_limit(chip, port); + if (err) + return err; + } + + if (chip->info->ops->port_disable_pri_override) { + err = chip->info->ops->port_disable_pri_override(chip, port); if (err) return err; } @@ -2653,10 +2420,7 @@ static int mv88e6xxx_setup_port(struct mv88e6xxx_chip *chip, int port) return err; } - /* Port Control 1: disable trunking, disable sending - * learning messages to this port. - */ - err = mv88e6xxx_port_write(chip, port, PORT_CONTROL_1, 0x0000); + err = mv88e6xxx_setup_message_port(chip, port); if (err) return err; @@ -2697,33 +2461,6 @@ static int mv88e6xxx_g1_set_switch_mac(struct mv88e6xxx_chip *chip, u8 *addr) return 0; } -static int mv88e6xxx_g1_set_age_time(struct mv88e6xxx_chip *chip, - unsigned int msecs) -{ - const unsigned int coeff = chip->info->age_time_coeff; - const unsigned int min = 0x01 * coeff; - const unsigned int max = 0xff * coeff; - u8 age_time; - u16 val; - int err; - - if (msecs < min || msecs > max) - return -ERANGE; - - /* Round to nearest multiple of coeff */ - age_time = (msecs + coeff / 2) / coeff; - - err = mv88e6xxx_g1_read(chip, GLOBAL_ATU_CONTROL, &val); - if (err) - return err; - - /* AgeTime is 11:4 bits */ - val &= ~0xff0; - val |= age_time << 4; - - return mv88e6xxx_g1_write(chip, GLOBAL_ATU_CONTROL, val); -} - static int mv88e6xxx_set_ageing_time(struct dsa_switch *ds, unsigned int ageing_time) { @@ -2731,7 +2468,7 @@ static int mv88e6xxx_set_ageing_time(struct dsa_switch *ds, int err; mutex_lock(&chip->reg_lock); - err = mv88e6xxx_g1_set_age_time(chip, ageing_time); + err = mv88e6xxx_g1_atu_set_age_time(chip, ageing_time); mutex_unlock(&chip->reg_lock); return err; @@ -2774,24 +2511,6 @@ static int mv88e6xxx_g1_setup(struct mv88e6xxx_chip *chip) if (err < 0) return err; - /* Set the default address aging time to 5 minutes, and - * enable address learn messages to be sent to all message - * ports. - */ - err = mv88e6xxx_g1_write(chip, GLOBAL_ATU_CONTROL, - GLOBAL_ATU_CONTROL_LEARN2ALL); - if (err) - return err; - - err = mv88e6xxx_g1_set_age_time(chip, 300000); - if (err) - return err; - - /* Clear all ATU entries */ - err = _mv88e6xxx_atu_flush(chip, 0, true); - if (err) - return err; - /* Configure the IP ToS mapping registers. */ err = mv88e6xxx_g1_write(chip, GLOBAL_IP_PRI_0, 0x0000); if (err) @@ -2872,6 +2591,10 @@ static int mv88e6xxx_setup(struct dsa_switch *ds) goto unlock; } + err = mv88e6xxx_atu_setup(chip); + if (err) + goto unlock; + /* Some generations have the configuration of sending reserved * management frames to the CPU in global2, others in * global1. Hence it does not fit the two setup functions @@ -3101,10 +2824,12 @@ static const struct mv88e6xxx_ops mv88e6085_ops = { .port_set_speed = mv88e6185_port_set_speed, .port_tag_remap = mv88e6095_port_tag_remap, .port_set_frame_mode = mv88e6351_port_set_frame_mode, - .port_set_egress_unknowns = mv88e6351_port_set_egress_unknowns, + .port_set_egress_floods = mv88e6352_port_set_egress_floods, .port_set_ether_type = mv88e6351_port_set_ether_type, .port_egress_rate_limiting = mv88e6097_port_egress_rate_limiting, .port_pause_config = mv88e6097_port_pause_config, + .port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit, + .port_disable_pri_override = mv88e6xxx_port_disable_pri_override, .stats_snapshot = mv88e6xxx_g1_stats_snapshot, .stats_get_sset_count = mv88e6095_stats_get_sset_count, .stats_get_strings = mv88e6095_stats_get_strings, @@ -3127,7 +2852,7 @@ static const struct mv88e6xxx_ops mv88e6095_ops = { .port_set_duplex = mv88e6xxx_port_set_duplex, .port_set_speed = mv88e6185_port_set_speed, .port_set_frame_mode = mv88e6085_port_set_frame_mode, - .port_set_egress_unknowns = mv88e6095_port_set_egress_unknowns, + .port_set_egress_floods = mv88e6185_port_set_egress_floods, .port_set_upstream_port = mv88e6095_port_set_upstream_port, .stats_snapshot = mv88e6xxx_g1_stats_snapshot, .stats_get_sset_count = mv88e6095_stats_get_sset_count, @@ -3149,11 +2874,13 @@ static const struct mv88e6xxx_ops mv88e6097_ops = { .port_set_speed = mv88e6185_port_set_speed, .port_tag_remap = mv88e6095_port_tag_remap, .port_set_frame_mode = mv88e6351_port_set_frame_mode, - .port_set_egress_unknowns = mv88e6351_port_set_egress_unknowns, + .port_set_egress_floods = mv88e6352_port_set_egress_floods, .port_set_ether_type = mv88e6351_port_set_ether_type, .port_jumbo_config = mv88e6165_port_jumbo_config, .port_egress_rate_limiting = mv88e6095_port_egress_rate_limiting, .port_pause_config = mv88e6097_port_pause_config, + .port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit, + .port_disable_pri_override = mv88e6xxx_port_disable_pri_override, .stats_snapshot = mv88e6xxx_g1_stats_snapshot, .stats_get_sset_count = mv88e6095_stats_get_sset_count, .stats_get_strings = mv88e6095_stats_get_strings, @@ -3174,7 +2901,9 @@ static const struct mv88e6xxx_ops mv88e6123_ops = { .port_set_duplex = mv88e6xxx_port_set_duplex, .port_set_speed = mv88e6185_port_set_speed, .port_set_frame_mode = mv88e6085_port_set_frame_mode, - .port_set_egress_unknowns = mv88e6085_port_set_egress_unknowns, + .port_set_egress_floods = mv88e6352_port_set_egress_floods, + .port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit, + .port_disable_pri_override = mv88e6xxx_port_disable_pri_override, .stats_snapshot = mv88e6xxx_g1_stats_snapshot, .stats_get_sset_count = mv88e6095_stats_get_sset_count, .stats_get_strings = mv88e6095_stats_get_strings, @@ -3196,7 +2925,7 @@ static const struct mv88e6xxx_ops mv88e6131_ops = { .port_set_speed = mv88e6185_port_set_speed, .port_tag_remap = mv88e6095_port_tag_remap, .port_set_frame_mode = mv88e6351_port_set_frame_mode, - .port_set_egress_unknowns = mv88e6095_port_set_egress_unknowns, + .port_set_egress_floods = mv88e6185_port_set_egress_floods, .port_set_ether_type = mv88e6351_port_set_ether_type, .port_set_upstream_port = mv88e6095_port_set_upstream_port, .port_jumbo_config = mv88e6165_port_jumbo_config, @@ -3225,11 +2954,13 @@ static const struct mv88e6xxx_ops mv88e6161_ops = { .port_set_speed = mv88e6185_port_set_speed, .port_tag_remap = mv88e6095_port_tag_remap, .port_set_frame_mode = mv88e6351_port_set_frame_mode, - .port_set_egress_unknowns = mv88e6351_port_set_egress_unknowns, + .port_set_egress_floods = mv88e6352_port_set_egress_floods, .port_set_ether_type = mv88e6351_port_set_ether_type, .port_jumbo_config = mv88e6165_port_jumbo_config, .port_egress_rate_limiting = mv88e6097_port_egress_rate_limiting, .port_pause_config = mv88e6097_port_pause_config, + .port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit, + .port_disable_pri_override = mv88e6xxx_port_disable_pri_override, .stats_snapshot = mv88e6xxx_g1_stats_snapshot, .stats_get_sset_count = mv88e6095_stats_get_sset_count, .stats_get_strings = mv88e6095_stats_get_strings, @@ -3249,6 +2980,8 @@ static const struct mv88e6xxx_ops mv88e6165_ops = { .port_set_link = mv88e6xxx_port_set_link, .port_set_duplex = mv88e6xxx_port_set_duplex, .port_set_speed = mv88e6185_port_set_speed, + .port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit, + .port_disable_pri_override = mv88e6xxx_port_disable_pri_override, .stats_snapshot = mv88e6xxx_g1_stats_snapshot, .stats_get_sset_count = mv88e6095_stats_get_sset_count, .stats_get_strings = mv88e6095_stats_get_strings, @@ -3271,11 +3004,13 @@ static const struct mv88e6xxx_ops mv88e6171_ops = { .port_set_speed = mv88e6185_port_set_speed, .port_tag_remap = mv88e6095_port_tag_remap, .port_set_frame_mode = mv88e6351_port_set_frame_mode, - .port_set_egress_unknowns = mv88e6351_port_set_egress_unknowns, + .port_set_egress_floods = mv88e6352_port_set_egress_floods, .port_set_ether_type = mv88e6351_port_set_ether_type, .port_jumbo_config = mv88e6165_port_jumbo_config, .port_egress_rate_limiting = mv88e6097_port_egress_rate_limiting, .port_pause_config = mv88e6097_port_pause_config, + .port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit, + .port_disable_pri_override = mv88e6xxx_port_disable_pri_override, .stats_snapshot = mv88e6320_g1_stats_snapshot, .stats_get_sset_count = mv88e6095_stats_get_sset_count, .stats_get_strings = mv88e6095_stats_get_strings, @@ -3300,11 +3035,13 @@ static const struct mv88e6xxx_ops mv88e6172_ops = { .port_set_speed = mv88e6352_port_set_speed, .port_tag_remap = mv88e6095_port_tag_remap, .port_set_frame_mode = mv88e6351_port_set_frame_mode, - .port_set_egress_unknowns = mv88e6351_port_set_egress_unknowns, + .port_set_egress_floods = mv88e6352_port_set_egress_floods, .port_set_ether_type = mv88e6351_port_set_ether_type, .port_jumbo_config = mv88e6165_port_jumbo_config, .port_egress_rate_limiting = mv88e6097_port_egress_rate_limiting, .port_pause_config = mv88e6097_port_pause_config, + .port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit, + .port_disable_pri_override = mv88e6xxx_port_disable_pri_override, .stats_snapshot = mv88e6320_g1_stats_snapshot, .stats_get_sset_count = mv88e6095_stats_get_sset_count, .stats_get_strings = mv88e6095_stats_get_strings, @@ -3327,11 +3064,13 @@ static const struct mv88e6xxx_ops mv88e6175_ops = { .port_set_speed = mv88e6185_port_set_speed, .port_tag_remap = mv88e6095_port_tag_remap, .port_set_frame_mode = mv88e6351_port_set_frame_mode, - .port_set_egress_unknowns = mv88e6351_port_set_egress_unknowns, + .port_set_egress_floods = mv88e6352_port_set_egress_floods, .port_set_ether_type = mv88e6351_port_set_ether_type, .port_jumbo_config = mv88e6165_port_jumbo_config, .port_egress_rate_limiting = mv88e6097_port_egress_rate_limiting, .port_pause_config = mv88e6097_port_pause_config, + .port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit, + .port_disable_pri_override = mv88e6xxx_port_disable_pri_override, .stats_snapshot = mv88e6320_g1_stats_snapshot, .stats_get_sset_count = mv88e6095_stats_get_sset_count, .stats_get_strings = mv88e6095_stats_get_strings, @@ -3356,11 +3095,13 @@ static const struct mv88e6xxx_ops mv88e6176_ops = { .port_set_speed = mv88e6352_port_set_speed, .port_tag_remap = mv88e6095_port_tag_remap, .port_set_frame_mode = mv88e6351_port_set_frame_mode, - .port_set_egress_unknowns = mv88e6351_port_set_egress_unknowns, + .port_set_egress_floods = mv88e6352_port_set_egress_floods, .port_set_ether_type = mv88e6351_port_set_ether_type, .port_jumbo_config = mv88e6165_port_jumbo_config, .port_egress_rate_limiting = mv88e6097_port_egress_rate_limiting, .port_pause_config = mv88e6097_port_pause_config, + .port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit, + .port_disable_pri_override = mv88e6xxx_port_disable_pri_override, .stats_snapshot = mv88e6320_g1_stats_snapshot, .stats_get_sset_count = mv88e6095_stats_get_sset_count, .stats_get_strings = mv88e6095_stats_get_strings, @@ -3381,7 +3122,7 @@ static const struct mv88e6xxx_ops mv88e6185_ops = { .port_set_duplex = mv88e6xxx_port_set_duplex, .port_set_speed = mv88e6185_port_set_speed, .port_set_frame_mode = mv88e6085_port_set_frame_mode, - .port_set_egress_unknowns = mv88e6095_port_set_egress_unknowns, + .port_set_egress_floods = mv88e6185_port_set_egress_floods, .port_egress_rate_limiting = mv88e6095_port_egress_rate_limiting, .port_set_upstream_port = mv88e6095_port_set_upstream_port, .stats_snapshot = mv88e6xxx_g1_stats_snapshot, @@ -3410,9 +3151,11 @@ static const struct mv88e6xxx_ops mv88e6190_ops = { .port_set_speed = mv88e6390_port_set_speed, .port_tag_remap = mv88e6390_port_tag_remap, .port_set_frame_mode = mv88e6351_port_set_frame_mode, - .port_set_egress_unknowns = mv88e6351_port_set_egress_unknowns, + .port_set_egress_floods = mv88e6352_port_set_egress_floods, .port_set_ether_type = mv88e6351_port_set_ether_type, .port_pause_config = mv88e6390_port_pause_config, + .port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit, + .port_disable_pri_override = mv88e6xxx_port_disable_pri_override, .stats_snapshot = mv88e6390_g1_stats_snapshot, .stats_set_histogram = mv88e6390_g1_stats_set_histogram, .stats_get_sset_count = mv88e6320_stats_get_sset_count, @@ -3438,9 +3181,11 @@ static const struct mv88e6xxx_ops mv88e6190x_ops = { .port_set_speed = mv88e6390x_port_set_speed, .port_tag_remap = mv88e6390_port_tag_remap, .port_set_frame_mode = mv88e6351_port_set_frame_mode, - .port_set_egress_unknowns = mv88e6351_port_set_egress_unknowns, + .port_set_egress_floods = mv88e6352_port_set_egress_floods, .port_set_ether_type = mv88e6351_port_set_ether_type, .port_pause_config = mv88e6390_port_pause_config, + .port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit, + .port_disable_pri_override = mv88e6xxx_port_disable_pri_override, .stats_snapshot = mv88e6390_g1_stats_snapshot, .stats_set_histogram = mv88e6390_g1_stats_set_histogram, .stats_get_sset_count = mv88e6320_stats_get_sset_count, @@ -3466,9 +3211,11 @@ static const struct mv88e6xxx_ops mv88e6191_ops = { .port_set_speed = mv88e6390_port_set_speed, .port_tag_remap = mv88e6390_port_tag_remap, .port_set_frame_mode = mv88e6351_port_set_frame_mode, - .port_set_egress_unknowns = mv88e6351_port_set_egress_unknowns, + .port_set_egress_floods = mv88e6352_port_set_egress_floods, .port_set_ether_type = mv88e6351_port_set_ether_type, .port_pause_config = mv88e6390_port_pause_config, + .port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit, + .port_disable_pri_override = mv88e6xxx_port_disable_pri_override, .stats_snapshot = mv88e6390_g1_stats_snapshot, .stats_set_histogram = mv88e6390_g1_stats_set_histogram, .stats_get_sset_count = mv88e6320_stats_get_sset_count, @@ -3494,11 +3241,13 @@ static const struct mv88e6xxx_ops mv88e6240_ops = { .port_set_speed = mv88e6352_port_set_speed, .port_tag_remap = mv88e6095_port_tag_remap, .port_set_frame_mode = mv88e6351_port_set_frame_mode, - .port_set_egress_unknowns = mv88e6351_port_set_egress_unknowns, + .port_set_egress_floods = mv88e6352_port_set_egress_floods, .port_set_ether_type = mv88e6351_port_set_ether_type, .port_jumbo_config = mv88e6165_port_jumbo_config, .port_egress_rate_limiting = mv88e6097_port_egress_rate_limiting, .port_pause_config = mv88e6097_port_pause_config, + .port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit, + .port_disable_pri_override = mv88e6xxx_port_disable_pri_override, .stats_snapshot = mv88e6320_g1_stats_snapshot, .stats_get_sset_count = mv88e6095_stats_get_sset_count, .stats_get_strings = mv88e6095_stats_get_strings, @@ -3523,10 +3272,12 @@ static const struct mv88e6xxx_ops mv88e6290_ops = { .port_set_speed = mv88e6390_port_set_speed, .port_tag_remap = mv88e6390_port_tag_remap, .port_set_frame_mode = mv88e6351_port_set_frame_mode, - .port_set_egress_unknowns = mv88e6351_port_set_egress_unknowns, + .port_set_egress_floods = mv88e6352_port_set_egress_floods, .port_set_ether_type = mv88e6351_port_set_ether_type, .port_pause_config = mv88e6390_port_pause_config, .port_set_cmode = mv88e6390x_port_set_cmode, + .port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit, + .port_disable_pri_override = mv88e6xxx_port_disable_pri_override, .stats_snapshot = mv88e6390_g1_stats_snapshot, .stats_set_histogram = mv88e6390_g1_stats_set_histogram, .stats_get_sset_count = mv88e6320_stats_get_sset_count, @@ -3551,11 +3302,13 @@ static const struct mv88e6xxx_ops mv88e6320_ops = { .port_set_speed = mv88e6185_port_set_speed, .port_tag_remap = mv88e6095_port_tag_remap, .port_set_frame_mode = mv88e6351_port_set_frame_mode, - .port_set_egress_unknowns = mv88e6351_port_set_egress_unknowns, + .port_set_egress_floods = mv88e6352_port_set_egress_floods, .port_set_ether_type = mv88e6351_port_set_ether_type, .port_jumbo_config = mv88e6165_port_jumbo_config, .port_egress_rate_limiting = mv88e6097_port_egress_rate_limiting, .port_pause_config = mv88e6097_port_pause_config, + .port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit, + .port_disable_pri_override = mv88e6xxx_port_disable_pri_override, .stats_snapshot = mv88e6320_g1_stats_snapshot, .stats_get_sset_count = mv88e6320_stats_get_sset_count, .stats_get_strings = mv88e6320_stats_get_strings, @@ -3578,11 +3331,13 @@ static const struct mv88e6xxx_ops mv88e6321_ops = { .port_set_speed = mv88e6185_port_set_speed, .port_tag_remap = mv88e6095_port_tag_remap, .port_set_frame_mode = mv88e6351_port_set_frame_mode, - .port_set_egress_unknowns = mv88e6351_port_set_egress_unknowns, + .port_set_egress_floods = mv88e6352_port_set_egress_floods, .port_set_ether_type = mv88e6351_port_set_ether_type, .port_jumbo_config = mv88e6165_port_jumbo_config, .port_egress_rate_limiting = mv88e6097_port_egress_rate_limiting, .port_pause_config = mv88e6097_port_pause_config, + .port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit, + .port_disable_pri_override = mv88e6xxx_port_disable_pri_override, .stats_snapshot = mv88e6320_g1_stats_snapshot, .stats_get_sset_count = mv88e6320_stats_get_sset_count, .stats_get_strings = mv88e6320_stats_get_strings, @@ -3603,11 +3358,13 @@ static const struct mv88e6xxx_ops mv88e6350_ops = { .port_set_speed = mv88e6185_port_set_speed, .port_tag_remap = mv88e6095_port_tag_remap, .port_set_frame_mode = mv88e6351_port_set_frame_mode, - .port_set_egress_unknowns = mv88e6351_port_set_egress_unknowns, + .port_set_egress_floods = mv88e6352_port_set_egress_floods, .port_set_ether_type = mv88e6351_port_set_ether_type, .port_jumbo_config = mv88e6165_port_jumbo_config, .port_egress_rate_limiting = mv88e6097_port_egress_rate_limiting, .port_pause_config = mv88e6097_port_pause_config, + .port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit, + .port_disable_pri_override = mv88e6xxx_port_disable_pri_override, .stats_snapshot = mv88e6320_g1_stats_snapshot, .stats_get_sset_count = mv88e6095_stats_get_sset_count, .stats_get_strings = mv88e6095_stats_get_strings, @@ -3630,11 +3387,13 @@ static const struct mv88e6xxx_ops mv88e6351_ops = { .port_set_speed = mv88e6185_port_set_speed, .port_tag_remap = mv88e6095_port_tag_remap, .port_set_frame_mode = mv88e6351_port_set_frame_mode, - .port_set_egress_unknowns = mv88e6351_port_set_egress_unknowns, + .port_set_egress_floods = mv88e6352_port_set_egress_floods, .port_set_ether_type = mv88e6351_port_set_ether_type, .port_jumbo_config = mv88e6165_port_jumbo_config, .port_egress_rate_limiting = mv88e6097_port_egress_rate_limiting, .port_pause_config = mv88e6097_port_pause_config, + .port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit, + .port_disable_pri_override = mv88e6xxx_port_disable_pri_override, .stats_snapshot = mv88e6320_g1_stats_snapshot, .stats_get_sset_count = mv88e6095_stats_get_sset_count, .stats_get_strings = mv88e6095_stats_get_strings, @@ -3659,11 +3418,13 @@ static const struct mv88e6xxx_ops mv88e6352_ops = { .port_set_speed = mv88e6352_port_set_speed, .port_tag_remap = mv88e6095_port_tag_remap, .port_set_frame_mode = mv88e6351_port_set_frame_mode, - .port_set_egress_unknowns = mv88e6351_port_set_egress_unknowns, + .port_set_egress_floods = mv88e6352_port_set_egress_floods, .port_set_ether_type = mv88e6351_port_set_ether_type, .port_jumbo_config = mv88e6165_port_jumbo_config, .port_egress_rate_limiting = mv88e6097_port_egress_rate_limiting, .port_pause_config = mv88e6097_port_pause_config, + .port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit, + .port_disable_pri_override = mv88e6xxx_port_disable_pri_override, .stats_snapshot = mv88e6320_g1_stats_snapshot, .stats_get_sset_count = mv88e6095_stats_get_sset_count, .stats_get_strings = mv88e6095_stats_get_strings, @@ -3688,11 +3449,13 @@ static const struct mv88e6xxx_ops mv88e6141_ops = { .port_set_speed = mv88e6390_port_set_speed, .port_tag_remap = mv88e6095_port_tag_remap, .port_set_frame_mode = mv88e6351_port_set_frame_mode, - .port_set_egress_unknowns = mv88e6351_port_set_egress_unknowns, + .port_set_egress_floods = mv88e6352_port_set_egress_floods, .port_set_ether_type = mv88e6351_port_set_ether_type, .port_jumbo_config = mv88e6165_port_jumbo_config, .port_egress_rate_limiting = mv88e6097_port_egress_rate_limiting, .port_pause_config = mv88e6097_port_pause_config, + .port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit, + .port_disable_pri_override = mv88e6xxx_port_disable_pri_override, .stats_snapshot = mv88e6390_g1_stats_snapshot, .stats_get_sset_count = mv88e6320_stats_get_sset_count, .stats_get_strings = mv88e6320_stats_get_strings, @@ -3717,11 +3480,13 @@ static const struct mv88e6xxx_ops mv88e6341_ops = { .port_set_speed = mv88e6390_port_set_speed, .port_tag_remap = mv88e6095_port_tag_remap, .port_set_frame_mode = mv88e6351_port_set_frame_mode, - .port_set_egress_unknowns = mv88e6351_port_set_egress_unknowns, + .port_set_egress_floods = mv88e6352_port_set_egress_floods, .port_set_ether_type = mv88e6351_port_set_ether_type, .port_jumbo_config = mv88e6165_port_jumbo_config, .port_egress_rate_limiting = mv88e6097_port_egress_rate_limiting, .port_pause_config = mv88e6097_port_pause_config, + .port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit, + .port_disable_pri_override = mv88e6xxx_port_disable_pri_override, .stats_snapshot = mv88e6390_g1_stats_snapshot, .stats_get_sset_count = mv88e6320_stats_get_sset_count, .stats_get_strings = mv88e6320_stats_get_strings, @@ -3746,12 +3511,14 @@ static const struct mv88e6xxx_ops mv88e6390_ops = { .port_set_speed = mv88e6390_port_set_speed, .port_tag_remap = mv88e6390_port_tag_remap, .port_set_frame_mode = mv88e6351_port_set_frame_mode, - .port_set_egress_unknowns = mv88e6351_port_set_egress_unknowns, + .port_set_egress_floods = mv88e6352_port_set_egress_floods, .port_set_ether_type = mv88e6351_port_set_ether_type, .port_jumbo_config = mv88e6165_port_jumbo_config, .port_egress_rate_limiting = mv88e6097_port_egress_rate_limiting, .port_pause_config = mv88e6390_port_pause_config, .port_set_cmode = mv88e6390x_port_set_cmode, + .port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit, + .port_disable_pri_override = mv88e6xxx_port_disable_pri_override, .stats_snapshot = mv88e6390_g1_stats_snapshot, .stats_set_histogram = mv88e6390_g1_stats_set_histogram, .stats_get_sset_count = mv88e6320_stats_get_sset_count, @@ -3777,11 +3544,13 @@ static const struct mv88e6xxx_ops mv88e6390x_ops = { .port_set_speed = mv88e6390x_port_set_speed, .port_tag_remap = mv88e6390_port_tag_remap, .port_set_frame_mode = mv88e6351_port_set_frame_mode, - .port_set_egress_unknowns = mv88e6351_port_set_egress_unknowns, + .port_set_egress_floods = mv88e6352_port_set_egress_floods, .port_set_ether_type = mv88e6351_port_set_ether_type, .port_jumbo_config = mv88e6165_port_jumbo_config, .port_egress_rate_limiting = mv88e6097_port_egress_rate_limiting, .port_pause_config = mv88e6390_port_pause_config, + .port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit, + .port_disable_pri_override = mv88e6xxx_port_disable_pri_override, .stats_snapshot = mv88e6390_g1_stats_snapshot, .stats_set_histogram = mv88e6390_g1_stats_set_histogram, .stats_get_sset_count = mv88e6320_stats_get_sset_count, @@ -3807,9 +3576,11 @@ static const struct mv88e6xxx_ops mv88e6391_ops = { .port_set_speed = mv88e6390_port_set_speed, .port_tag_remap = mv88e6390_port_tag_remap, .port_set_frame_mode = mv88e6351_port_set_frame_mode, - .port_set_egress_unknowns = mv88e6351_port_set_egress_unknowns, + .port_set_egress_floods = mv88e6352_port_set_egress_floods, .port_set_ether_type = mv88e6351_port_set_ether_type, .port_pause_config = mv88e6390_port_pause_config, + .port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit, + .port_disable_pri_override = mv88e6xxx_port_disable_pri_override, .stats_snapshot = mv88e6390_g1_stats_snapshot, .stats_set_histogram = mv88e6390_g1_stats_set_histogram, .stats_get_sset_count = mv88e6320_stats_get_sset_count, @@ -3822,22 +3593,6 @@ static const struct mv88e6xxx_ops mv88e6391_ops = { .reset = mv88e6352_g1_reset, }; -static int mv88e6xxx_verify_madatory_ops(struct mv88e6xxx_chip *chip, - const struct mv88e6xxx_ops *ops) -{ - if (!ops->port_set_frame_mode) { - dev_err(chip->dev, "Missing port_set_frame_mode"); - return -EINVAL; - } - - if (!ops->port_set_egress_unknowns) { - dev_err(chip->dev, "Missing port_set_egress_mode"); - return -EINVAL; - } - - return 0; -} - static const struct mv88e6xxx_info mv88e6xxx_table[] = { [MV88E6085] = { .prod_num = PORT_SWITCH_ID_PROD_NUM_6085, @@ -3849,6 +3604,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = { .global1_addr = 0x1b, .age_time_coeff = 15000, .g1_irqs = 8, + .atu_move_port_mask = 0xf, .tag_protocol = DSA_TAG_PROTO_DSA, .flags = MV88E6XXX_FLAGS_FAMILY_6097, .ops = &mv88e6085_ops, @@ -3864,6 +3620,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = { .global1_addr = 0x1b, .age_time_coeff = 15000, .g1_irqs = 8, + .atu_move_port_mask = 0xf, .tag_protocol = DSA_TAG_PROTO_DSA, .flags = MV88E6XXX_FLAGS_FAMILY_6095, .ops = &mv88e6095_ops, @@ -3879,6 +3636,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = { .global1_addr = 0x1b, .age_time_coeff = 15000, .g1_irqs = 8, + .atu_move_port_mask = 0xf, .tag_protocol = DSA_TAG_PROTO_EDSA, .flags = MV88E6XXX_FLAGS_FAMILY_6097, .ops = &mv88e6097_ops, @@ -3894,6 +3652,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = { .global1_addr = 0x1b, .age_time_coeff = 15000, .g1_irqs = 9, + .atu_move_port_mask = 0xf, .tag_protocol = DSA_TAG_PROTO_DSA, .flags = MV88E6XXX_FLAGS_FAMILY_6165, .ops = &mv88e6123_ops, @@ -3909,6 +3668,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = { .global1_addr = 0x1b, .age_time_coeff = 15000, .g1_irqs = 9, + .atu_move_port_mask = 0xf, .tag_protocol = DSA_TAG_PROTO_DSA, .flags = MV88E6XXX_FLAGS_FAMILY_6185, .ops = &mv88e6131_ops, @@ -3924,6 +3684,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = { .global1_addr = 0x1b, .age_time_coeff = 15000, .g1_irqs = 9, + .atu_move_port_mask = 0xf, .tag_protocol = DSA_TAG_PROTO_DSA, .flags = MV88E6XXX_FLAGS_FAMILY_6165, .ops = &mv88e6161_ops, @@ -3939,6 +3700,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = { .global1_addr = 0x1b, .age_time_coeff = 15000, .g1_irqs = 9, + .atu_move_port_mask = 0xf, .tag_protocol = DSA_TAG_PROTO_DSA, .flags = MV88E6XXX_FLAGS_FAMILY_6165, .ops = &mv88e6165_ops, @@ -3954,6 +3716,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = { .global1_addr = 0x1b, .age_time_coeff = 15000, .g1_irqs = 9, + .atu_move_port_mask = 0xf, .tag_protocol = DSA_TAG_PROTO_EDSA, .flags = MV88E6XXX_FLAGS_FAMILY_6351, .ops = &mv88e6171_ops, @@ -3969,6 +3732,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = { .global1_addr = 0x1b, .age_time_coeff = 15000, .g1_irqs = 9, + .atu_move_port_mask = 0xf, .tag_protocol = DSA_TAG_PROTO_EDSA, .flags = MV88E6XXX_FLAGS_FAMILY_6352, .ops = &mv88e6172_ops, @@ -3984,6 +3748,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = { .global1_addr = 0x1b, .age_time_coeff = 15000, .g1_irqs = 9, + .atu_move_port_mask = 0xf, .tag_protocol = DSA_TAG_PROTO_EDSA, .flags = MV88E6XXX_FLAGS_FAMILY_6351, .ops = &mv88e6175_ops, @@ -3999,6 +3764,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = { .global1_addr = 0x1b, .age_time_coeff = 15000, .g1_irqs = 9, + .atu_move_port_mask = 0xf, .tag_protocol = DSA_TAG_PROTO_EDSA, .flags = MV88E6XXX_FLAGS_FAMILY_6352, .ops = &mv88e6176_ops, @@ -4014,6 +3780,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = { .global1_addr = 0x1b, .age_time_coeff = 15000, .g1_irqs = 8, + .atu_move_port_mask = 0xf, .tag_protocol = DSA_TAG_PROTO_EDSA, .flags = MV88E6XXX_FLAGS_FAMILY_6185, .ops = &mv88e6185_ops, @@ -4030,6 +3797,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = { .tag_protocol = DSA_TAG_PROTO_DSA, .age_time_coeff = 3750, .g1_irqs = 9, + .atu_move_port_mask = 0x1f, .flags = MV88E6XXX_FLAGS_FAMILY_6390, .ops = &mv88e6190_ops, }, @@ -4044,6 +3812,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = { .global1_addr = 0x1b, .age_time_coeff = 3750, .g1_irqs = 9, + .atu_move_port_mask = 0x1f, .tag_protocol = DSA_TAG_PROTO_DSA, .flags = MV88E6XXX_FLAGS_FAMILY_6390, .ops = &mv88e6190x_ops, @@ -4059,6 +3828,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = { .global1_addr = 0x1b, .age_time_coeff = 3750, .g1_irqs = 9, + .atu_move_port_mask = 0x1f, .tag_protocol = DSA_TAG_PROTO_DSA, .flags = MV88E6XXX_FLAGS_FAMILY_6390, .ops = &mv88e6391_ops, @@ -4074,6 +3844,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = { .global1_addr = 0x1b, .age_time_coeff = 15000, .g1_irqs = 9, + .atu_move_port_mask = 0xf, .tag_protocol = DSA_TAG_PROTO_EDSA, .flags = MV88E6XXX_FLAGS_FAMILY_6352, .ops = &mv88e6240_ops, @@ -4089,6 +3860,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = { .global1_addr = 0x1b, .age_time_coeff = 3750, .g1_irqs = 9, + .atu_move_port_mask = 0x1f, .tag_protocol = DSA_TAG_PROTO_DSA, .flags = MV88E6XXX_FLAGS_FAMILY_6390, .ops = &mv88e6290_ops, @@ -4104,6 +3876,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = { .global1_addr = 0x1b, .age_time_coeff = 15000, .g1_irqs = 8, + .atu_move_port_mask = 0xf, .tag_protocol = DSA_TAG_PROTO_EDSA, .flags = MV88E6XXX_FLAGS_FAMILY_6320, .ops = &mv88e6320_ops, @@ -4119,6 +3892,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = { .global1_addr = 0x1b, .age_time_coeff = 15000, .g1_irqs = 8, + .atu_move_port_mask = 0xf, .tag_protocol = DSA_TAG_PROTO_EDSA, .flags = MV88E6XXX_FLAGS_FAMILY_6320, .ops = &mv88e6321_ops, @@ -4133,6 +3907,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = { .port_base_addr = 0x10, .global1_addr = 0x1b, .age_time_coeff = 3750, + .atu_move_port_mask = 0x1f, .tag_protocol = DSA_TAG_PROTO_EDSA, .flags = MV88E6XXX_FLAGS_FAMILY_6341, .ops = &mv88e6141_ops, @@ -4147,6 +3922,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = { .port_base_addr = 0x10, .global1_addr = 0x1b, .age_time_coeff = 3750, + .atu_move_port_mask = 0x1f, .tag_protocol = DSA_TAG_PROTO_EDSA, .flags = MV88E6XXX_FLAGS_FAMILY_6341, .ops = &mv88e6341_ops, @@ -4162,6 +3938,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = { .global1_addr = 0x1b, .age_time_coeff = 15000, .g1_irqs = 9, + .atu_move_port_mask = 0xf, .tag_protocol = DSA_TAG_PROTO_EDSA, .flags = MV88E6XXX_FLAGS_FAMILY_6351, .ops = &mv88e6350_ops, @@ -4177,6 +3954,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = { .global1_addr = 0x1b, .age_time_coeff = 15000, .g1_irqs = 9, + .atu_move_port_mask = 0xf, .tag_protocol = DSA_TAG_PROTO_EDSA, .flags = MV88E6XXX_FLAGS_FAMILY_6351, .ops = &mv88e6351_ops, @@ -4192,6 +3970,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = { .global1_addr = 0x1b, .age_time_coeff = 15000, .g1_irqs = 9, + .atu_move_port_mask = 0xf, .tag_protocol = DSA_TAG_PROTO_EDSA, .flags = MV88E6XXX_FLAGS_FAMILY_6352, .ops = &mv88e6352_ops, @@ -4206,6 +3985,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = { .global1_addr = 0x1b, .age_time_coeff = 3750, .g1_irqs = 9, + .atu_move_port_mask = 0x1f, .tag_protocol = DSA_TAG_PROTO_DSA, .flags = MV88E6XXX_FLAGS_FAMILY_6390, .ops = &mv88e6390_ops, @@ -4220,6 +4000,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = { .global1_addr = 0x1b, .age_time_coeff = 3750, .g1_irqs = 9, + .atu_move_port_mask = 0x1f, .tag_protocol = DSA_TAG_PROTO_DSA, .flags = MV88E6XXX_FLAGS_FAMILY_6390, .ops = &mv88e6390x_ops, @@ -4472,6 +4253,8 @@ static int mv88e6xxx_register_switch(struct mv88e6xxx_chip *chip) ds->priv = chip; ds->ops = &mv88e6xxx_switch_ops; + ds->ageing_time_min = chip->info->age_time_coeff; + ds->ageing_time_max = chip->info->age_time_coeff * U8_MAX; dev_set_drvdata(dev, ds); @@ -4502,10 +4285,6 @@ static int mv88e6xxx_probe(struct mdio_device *mdiodev) chip->info = compat_info; - err = mv88e6xxx_verify_madatory_ops(chip, chip->info->ops); - if (err) - return err; - err = mv88e6xxx_smi_init(chip, mdiodev->bus, mdiodev->addr); if (err) return err; diff --git a/drivers/net/dsa/mv88e6xxx/global1.h b/drivers/net/dsa/mv88e6xxx/global1.h index 1aec7382c02d..eece7418e67d 100644 --- a/drivers/net/dsa/mv88e6xxx/global1.h +++ b/drivers/net/dsa/mv88e6xxx/global1.h @@ -38,4 +38,15 @@ int mv88e6095_g1_set_cpu_port(struct mv88e6xxx_chip *chip, int port); int mv88e6390_g1_set_cpu_port(struct mv88e6xxx_chip *chip, int port); int mv88e6390_g1_mgmt_rsvd2cpu(struct mv88e6xxx_chip *chip); +int mv88e6xxx_g1_atu_set_learn2all(struct mv88e6xxx_chip *chip, bool learn2all); +int mv88e6xxx_g1_atu_set_age_time(struct mv88e6xxx_chip *chip, + unsigned int msecs); +int mv88e6xxx_g1_atu_getnext(struct mv88e6xxx_chip *chip, u16 fid, + struct mv88e6xxx_atu_entry *entry); +int mv88e6xxx_g1_atu_loadpurge(struct mv88e6xxx_chip *chip, u16 fid, + struct mv88e6xxx_atu_entry *entry); +int mv88e6xxx_g1_atu_flush(struct mv88e6xxx_chip *chip, u16 fid, bool all); +int mv88e6xxx_g1_atu_remove(struct mv88e6xxx_chip *chip, u16 fid, int port, + bool all); + #endif /* _MV88E6XXX_GLOBAL1_H */ diff --git a/drivers/net/dsa/mv88e6xxx/global1_atu.c b/drivers/net/dsa/mv88e6xxx/global1_atu.c new file mode 100644 index 000000000000..120b7f41a735 --- /dev/null +++ b/drivers/net/dsa/mv88e6xxx/global1_atu.c @@ -0,0 +1,300 @@ +/* + * Marvell 88E6xxx Address Translation Unit (ATU) support + * + * Copyright (c) 2008 Marvell Semiconductor + * Copyright (c) 2017 Savoir-faire Linux, Inc. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + */ + +#include "mv88e6xxx.h" +#include "global1.h" + +/* Offset 0x01: ATU FID Register */ + +static int mv88e6xxx_g1_atu_fid_write(struct mv88e6xxx_chip *chip, u16 fid) +{ + return mv88e6xxx_g1_write(chip, GLOBAL_ATU_FID, fid & 0xfff); +} + +/* Offset 0x0A: ATU Control Register */ + +int mv88e6xxx_g1_atu_set_learn2all(struct mv88e6xxx_chip *chip, bool learn2all) +{ + u16 val; + int err; + + err = mv88e6xxx_g1_read(chip, GLOBAL_ATU_CONTROL, &val); + if (err) + return err; + + if (learn2all) + val |= GLOBAL_ATU_CONTROL_LEARN2ALL; + else + val &= ~GLOBAL_ATU_CONTROL_LEARN2ALL; + + return mv88e6xxx_g1_write(chip, GLOBAL_ATU_CONTROL, val); +} + +int mv88e6xxx_g1_atu_set_age_time(struct mv88e6xxx_chip *chip, + unsigned int msecs) +{ + const unsigned int coeff = chip->info->age_time_coeff; + const unsigned int min = 0x01 * coeff; + const unsigned int max = 0xff * coeff; + u8 age_time; + u16 val; + int err; + + if (msecs < min || msecs > max) + return -ERANGE; + + /* Round to nearest multiple of coeff */ + age_time = (msecs + coeff / 2) / coeff; + + err = mv88e6xxx_g1_read(chip, GLOBAL_ATU_CONTROL, &val); + if (err) + return err; + + /* AgeTime is 11:4 bits */ + val &= ~0xff0; + val |= age_time << 4; + + return mv88e6xxx_g1_write(chip, GLOBAL_ATU_CONTROL, val); +} + +/* Offset 0x0B: ATU Operation Register */ + +static int mv88e6xxx_g1_atu_op_wait(struct mv88e6xxx_chip *chip) +{ + return mv88e6xxx_g1_wait(chip, GLOBAL_ATU_OP, GLOBAL_ATU_OP_BUSY); +} + +static int mv88e6xxx_g1_atu_op(struct mv88e6xxx_chip *chip, u16 fid, u16 op) +{ + u16 val; + int err; + + /* FID bits are dispatched all around gradually as more are supported */ + if (mv88e6xxx_num_databases(chip) > 256) { + err = mv88e6xxx_g1_atu_fid_write(chip, fid); + if (err) + return err; + } else { + if (mv88e6xxx_num_databases(chip) > 16) { + /* ATU DBNum[7:4] are located in ATU Control 15:12 */ + err = mv88e6xxx_g1_read(chip, GLOBAL_ATU_CONTROL, &val); + if (err) + return err; + + val = (val & 0x0fff) | ((fid << 8) & 0xf000); + err = mv88e6xxx_g1_write(chip, GLOBAL_ATU_CONTROL, val); + if (err) + return err; + } + + /* ATU DBNum[3:0] are located in ATU Operation 3:0 */ + op |= fid & 0xf; + } + + err = mv88e6xxx_g1_write(chip, GLOBAL_ATU_OP, op); + if (err) + return err; + + return mv88e6xxx_g1_atu_op_wait(chip); +} + +/* Offset 0x0C: ATU Data Register */ + +static int mv88e6xxx_g1_atu_data_read(struct mv88e6xxx_chip *chip, + struct mv88e6xxx_atu_entry *entry) +{ + u16 val; + int err; + + err = mv88e6xxx_g1_read(chip, GLOBAL_ATU_DATA, &val); + if (err) + return err; + + entry->state = val & 0xf; + if (entry->state != GLOBAL_ATU_DATA_STATE_UNUSED) { + if (val & GLOBAL_ATU_DATA_TRUNK) + entry->trunk = true; + + entry->portvec = (val >> 4) & mv88e6xxx_port_mask(chip); + } + + return 0; +} + +static int mv88e6xxx_g1_atu_data_write(struct mv88e6xxx_chip *chip, + struct mv88e6xxx_atu_entry *entry) +{ + u16 data = entry->state & 0xf; + + if (entry->state != GLOBAL_ATU_DATA_STATE_UNUSED) { + if (entry->trunk) + data |= GLOBAL_ATU_DATA_TRUNK; + + data |= (entry->portvec & mv88e6xxx_port_mask(chip)) << 4; + } + + return mv88e6xxx_g1_write(chip, GLOBAL_ATU_DATA, data); +} + +/* Offset 0x0D: ATU MAC Address Register Bytes 0 & 1 + * Offset 0x0E: ATU MAC Address Register Bytes 2 & 3 + * Offset 0x0F: ATU MAC Address Register Bytes 4 & 5 + */ + +static int mv88e6xxx_g1_atu_mac_read(struct mv88e6xxx_chip *chip, + struct mv88e6xxx_atu_entry *entry) +{ + u16 val; + int i, err; + + for (i = 0; i < 3; i++) { + err = mv88e6xxx_g1_read(chip, GLOBAL_ATU_MAC_01 + i, &val); + if (err) + return err; + + entry->mac[i * 2] = val >> 8; + entry->mac[i * 2 + 1] = val & 0xff; + } + + return 0; +} + +static int mv88e6xxx_g1_atu_mac_write(struct mv88e6xxx_chip *chip, + struct mv88e6xxx_atu_entry *entry) +{ + u16 val; + int i, err; + + for (i = 0; i < 3; i++) { + val = (entry->mac[i * 2] << 8) | entry->mac[i * 2 + 1]; + err = mv88e6xxx_g1_write(chip, GLOBAL_ATU_MAC_01 + i, val); + if (err) + return err; + } + + return 0; +} + +/* Address Translation Unit operations */ + +int mv88e6xxx_g1_atu_getnext(struct mv88e6xxx_chip *chip, u16 fid, + struct mv88e6xxx_atu_entry *entry) +{ + int err; + + err = mv88e6xxx_g1_atu_op_wait(chip); + if (err) + return err; + + /* Write the MAC address to iterate from only once */ + if (entry->state == GLOBAL_ATU_DATA_STATE_UNUSED) { + err = mv88e6xxx_g1_atu_mac_write(chip, entry); + if (err) + return err; + } + + err = mv88e6xxx_g1_atu_op(chip, fid, GLOBAL_ATU_OP_GET_NEXT_DB); + if (err) + return err; + + err = mv88e6xxx_g1_atu_data_read(chip, entry); + if (err) + return err; + + return mv88e6xxx_g1_atu_mac_read(chip, entry); +} + +int mv88e6xxx_g1_atu_loadpurge(struct mv88e6xxx_chip *chip, u16 fid, + struct mv88e6xxx_atu_entry *entry) +{ + int err; + + err = mv88e6xxx_g1_atu_op_wait(chip); + if (err) + return err; + + err = mv88e6xxx_g1_atu_mac_write(chip, entry); + if (err) + return err; + + err = mv88e6xxx_g1_atu_data_write(chip, entry); + if (err) + return err; + + return mv88e6xxx_g1_atu_op(chip, fid, GLOBAL_ATU_OP_LOAD_DB); +} + +static int mv88e6xxx_g1_atu_flushmove(struct mv88e6xxx_chip *chip, u16 fid, + struct mv88e6xxx_atu_entry *entry, + bool all) +{ + u16 op; + int err; + + err = mv88e6xxx_g1_atu_op_wait(chip); + if (err) + return err; + + err = mv88e6xxx_g1_atu_data_write(chip, entry); + if (err) + return err; + + /* Flush/Move all or non-static entries from all or a given database */ + if (all && fid) + op = GLOBAL_ATU_OP_FLUSH_MOVE_ALL_DB; + else if (fid) + op = GLOBAL_ATU_OP_FLUSH_MOVE_NON_STATIC_DB; + else if (all) + op = GLOBAL_ATU_OP_FLUSH_MOVE_ALL; + else + op = GLOBAL_ATU_OP_FLUSH_MOVE_NON_STATIC; + + return mv88e6xxx_g1_atu_op(chip, fid, op); +} + +int mv88e6xxx_g1_atu_flush(struct mv88e6xxx_chip *chip, u16 fid, bool all) +{ + struct mv88e6xxx_atu_entry entry = { + .state = 0, /* Null EntryState means Flush */ + }; + + return mv88e6xxx_g1_atu_flushmove(chip, fid, &entry, all); +} + +static int mv88e6xxx_g1_atu_move(struct mv88e6xxx_chip *chip, u16 fid, + int from_port, int to_port, bool all) +{ + struct mv88e6xxx_atu_entry entry = { 0 }; + unsigned long mask; + int shift; + + if (!chip->info->atu_move_port_mask) + return -EOPNOTSUPP; + + mask = chip->info->atu_move_port_mask; + shift = bitmap_weight(&mask, 16); + + entry.state = 0xf, /* Full EntryState means Move */ + entry.portvec = from_port & mask; + entry.portvec |= (to_port & mask) << shift; + + return mv88e6xxx_g1_atu_flushmove(chip, fid, &entry, all); +} + +int mv88e6xxx_g1_atu_remove(struct mv88e6xxx_chip *chip, u16 fid, int port, + bool all) +{ + int from_port = port; + int to_port = chip->info->atu_move_port_mask; + + return mv88e6xxx_g1_atu_move(chip, fid, from_port, to_port, all); +} diff --git a/drivers/net/dsa/mv88e6xxx/mv88e6xxx.h b/drivers/net/dsa/mv88e6xxx/mv88e6xxx.h index 6033f2f6260a..75be2c339a49 100644 --- a/drivers/net/dsa/mv88e6xxx/mv88e6xxx.h +++ b/drivers/net/dsa/mv88e6xxx/mv88e6xxx.h @@ -132,18 +132,19 @@ #define PORT_CONTROL_TAG_IF_BOTH BIT(6) #define PORT_CONTROL_USE_IP BIT(5) #define PORT_CONTROL_USE_TAG BIT(4) -#define PORT_CONTROL_FORWARD_UNKNOWN_MC BIT(3) #define PORT_CONTROL_FORWARD_UNKNOWN BIT(2) -#define PORT_CONTROL_NOT_EGRESS_UNKNOWN_DA (0x0 << 2) -#define PORT_CONTROL_NOT_EGRESS_UNKNOWN_MULTICAST_DA (0x1 << 2) -#define PORT_CONTROL_NOT_EGRESS_UNKNOWN_UNITCAST_DA (0x2 << 2) -#define PORT_CONTROL_EGRESS_ALL_UNKNOWN_DA (0x3 << 2) +#define PORT_CONTROL_EGRESS_FLOODS_MASK (0x3 << 2) +#define PORT_CONTROL_EGRESS_FLOODS_NO_UNKNOWN_DA (0x0 << 2) +#define PORT_CONTROL_EGRESS_FLOODS_NO_UNKNOWN_MC_DA (0x1 << 2) +#define PORT_CONTROL_EGRESS_FLOODS_NO_UNKNOWN_UC_DA (0x2 << 2) +#define PORT_CONTROL_EGRESS_FLOODS_ALL_UNKNOWN_DA (0x3 << 2) #define PORT_CONTROL_STATE_MASK 0x03 #define PORT_CONTROL_STATE_DISABLED 0x00 #define PORT_CONTROL_STATE_BLOCKING 0x01 #define PORT_CONTROL_STATE_LEARNING 0x02 #define PORT_CONTROL_STATE_FORWARDING 0x03 #define PORT_CONTROL_1 0x05 +#define PORT_CONTROL_1_MESSAGE_PORT BIT(15) #define PORT_CONTROL_1_FID_11_4_MASK (0xff << 0) #define PORT_BASE_VLAN 0x06 #define PORT_BASE_VLAN_FID_3_0_MASK (0xf << 12) @@ -166,7 +167,6 @@ #define PORT_CONTROL_2_DISCARD_UNTAGGED BIT(8) #define PORT_CONTROL_2_MAP_DA BIT(7) #define PORT_CONTROL_2_DEFAULT_FORWARD BIT(6) -#define PORT_CONTROL_2_FORWARD_UNKNOWN BIT(6) #define PORT_CONTROL_2_EGRESS_MONITOR BIT(5) #define PORT_CONTROL_2_INGRESS_MONITOR BIT(4) #define PORT_CONTROL_2_UPSTREAM_MASK 0x0f @@ -181,6 +181,7 @@ #define PORT_ATU_CONTROL 0x0c #define PORT_PRI_OVERRIDE 0x0d #define PORT_ETH_TYPE 0x0f +#define PORT_ETH_TYPE_DEFAULT 0x9100 #define PORT_IN_DISCARD_LO 0x10 #define PORT_IN_DISCARD_HI 0x11 #define PORT_IN_FILTERED 0x12 @@ -551,7 +552,6 @@ enum mv88e6xxx_cap { #define MV88E6XXX_FLAG_SERDES BIT_ULL(MV88E6XXX_CAP_SERDES) -#define MV88E6XXX_FLAG_G1_ATU_FID BIT_ULL(MV88E6XXX_CAP_G1_ATU_FID) #define MV88E6XXX_FLAG_G1_VTU_FID BIT_ULL(MV88E6XXX_CAP_G1_VTU_FID) #define MV88E6XXX_FLAG_GLOBAL2 BIT_ULL(MV88E6XXX_CAP_GLOBAL2) @@ -594,8 +594,7 @@ enum mv88e6xxx_cap { MV88E6XXX_FLAGS_MULTI_CHIP) #define MV88E6XXX_FLAGS_FAMILY_6097 \ - (MV88E6XXX_FLAG_G1_ATU_FID | \ - MV88E6XXX_FLAG_G1_VTU_FID | \ + (MV88E6XXX_FLAG_G1_VTU_FID | \ MV88E6XXX_FLAG_GLOBAL2 | \ MV88E6XXX_FLAG_G2_INT | \ MV88E6XXX_FLAG_G2_MGMT_EN_2X | \ @@ -608,8 +607,7 @@ enum mv88e6xxx_cap { MV88E6XXX_FLAGS_PVT) #define MV88E6XXX_FLAGS_FAMILY_6165 \ - (MV88E6XXX_FLAG_G1_ATU_FID | \ - MV88E6XXX_FLAG_G1_VTU_FID | \ + (MV88E6XXX_FLAG_G1_VTU_FID | \ MV88E6XXX_FLAG_GLOBAL2 | \ MV88E6XXX_FLAG_G2_INT | \ MV88E6XXX_FLAG_G2_MGMT_EN_2X | \ @@ -641,7 +639,6 @@ enum mv88e6xxx_cap { #define MV88E6XXX_FLAGS_FAMILY_6341 \ (MV88E6XXX_FLAG_EEE | \ - MV88E6XXX_FLAG_G1_ATU_FID | \ MV88E6XXX_FLAG_G1_VTU_FID | \ MV88E6XXX_FLAG_GLOBAL2 | \ MV88E6XXX_FLAG_G2_INT | \ @@ -654,8 +651,7 @@ enum mv88e6xxx_cap { MV88E6XXX_FLAGS_SERDES) #define MV88E6XXX_FLAGS_FAMILY_6351 \ - (MV88E6XXX_FLAG_G1_ATU_FID | \ - MV88E6XXX_FLAG_G1_VTU_FID | \ + (MV88E6XXX_FLAG_G1_VTU_FID | \ MV88E6XXX_FLAG_GLOBAL2 | \ MV88E6XXX_FLAG_G2_INT | \ MV88E6XXX_FLAG_G2_MGMT_EN_2X | \ @@ -669,7 +665,6 @@ enum mv88e6xxx_cap { #define MV88E6XXX_FLAGS_FAMILY_6352 \ (MV88E6XXX_FLAG_EEE | \ - MV88E6XXX_FLAG_G1_ATU_FID | \ MV88E6XXX_FLAG_G1_VTU_FID | \ MV88E6XXX_FLAG_GLOBAL2 | \ MV88E6XXX_FLAG_G2_INT | \ @@ -707,14 +702,18 @@ struct mv88e6xxx_info { unsigned int g1_irqs; enum dsa_tag_protocol tag_protocol; unsigned long long flags; + + /* Mask for FromPort and ToPort value of PortVec used in ATU Move + * operation. 0 means that the ATU Move operation is not supported. + */ + u8 atu_move_port_mask; const struct mv88e6xxx_ops *ops; }; struct mv88e6xxx_atu_entry { - u16 fid; u8 state; bool trunk; - u16 portv_trunkid; + u16 portvec; u8 mac[ETH_ALEN]; }; @@ -864,14 +863,16 @@ struct mv88e6xxx_ops { int (*port_set_frame_mode)(struct mv88e6xxx_chip *chip, int port, enum mv88e6xxx_frame_mode mode); - int (*port_set_egress_unknowns)(struct mv88e6xxx_chip *chip, int port, - bool on); + int (*port_set_egress_floods)(struct mv88e6xxx_chip *chip, int port, + bool unicast, bool multicast); int (*port_set_ether_type)(struct mv88e6xxx_chip *chip, int port, u16 etype); int (*port_jumbo_config)(struct mv88e6xxx_chip *chip, int port); int (*port_egress_rate_limiting)(struct mv88e6xxx_chip *chip, int port); int (*port_pause_config)(struct mv88e6xxx_chip *chip, int port); + int (*port_disable_learn_limit)(struct mv88e6xxx_chip *chip, int port); + int (*port_disable_pri_override)(struct mv88e6xxx_chip *chip, int port); /* CMODE control what PHY mode the MAC will use, eg. SGMII, RGMII, etc. * Some chips allow this to be configured on specific ports. @@ -944,6 +945,11 @@ static inline unsigned int mv88e6xxx_num_ports(struct mv88e6xxx_chip *chip) return chip->info->num_ports; } +static inline u16 mv88e6xxx_port_mask(struct mv88e6xxx_chip *chip) +{ + return GENMASK(mv88e6xxx_num_ports(chip) - 1, 0); +} + int mv88e6xxx_read(struct mv88e6xxx_chip *chip, int addr, int reg, u16 *val); int mv88e6xxx_write(struct mv88e6xxx_chip *chip, int addr, int reg, u16 val); int mv88e6xxx_update(struct mv88e6xxx_chip *chip, int addr, int reg, diff --git a/drivers/net/dsa/mv88e6xxx/port.c b/drivers/net/dsa/mv88e6xxx/port.c index 8875784c4718..d4868bb50ed5 100644 --- a/drivers/net/dsa/mv88e6xxx/port.c +++ b/drivers/net/dsa/mv88e6xxx/port.c @@ -497,8 +497,8 @@ int mv88e6351_port_set_frame_mode(struct mv88e6xxx_chip *chip, int port, return mv88e6xxx_port_write(chip, port, PORT_CONTROL, reg); } -int mv88e6085_port_set_egress_unknowns(struct mv88e6xxx_chip *chip, int port, - bool on) +static int mv88e6185_port_set_forward_unknown(struct mv88e6xxx_chip *chip, + int port, bool unicast) { int err; u16 reg; @@ -507,7 +507,7 @@ int mv88e6085_port_set_egress_unknowns(struct mv88e6xxx_chip *chip, int port, if (err) return err; - if (on) + if (unicast) reg |= PORT_CONTROL_FORWARD_UNKNOWN; else reg &= ~PORT_CONTROL_FORWARD_UNKNOWN; @@ -515,8 +515,8 @@ int mv88e6085_port_set_egress_unknowns(struct mv88e6xxx_chip *chip, int port, return mv88e6xxx_port_write(chip, port, PORT_CONTROL, reg); } -int mv88e6351_port_set_egress_unknowns(struct mv88e6xxx_chip *chip, int port, - bool on) +int mv88e6352_port_set_egress_floods(struct mv88e6xxx_chip *chip, int port, + bool unicast, bool multicast) { int err; u16 reg; @@ -525,21 +525,45 @@ int mv88e6351_port_set_egress_unknowns(struct mv88e6xxx_chip *chip, int port, if (err) return err; - if (on) - reg |= PORT_CONTROL_EGRESS_ALL_UNKNOWN_DA; + reg &= ~PORT_CONTROL_EGRESS_FLOODS_MASK; + + if (unicast && multicast) + reg |= PORT_CONTROL_EGRESS_FLOODS_ALL_UNKNOWN_DA; + else if (unicast) + reg |= PORT_CONTROL_EGRESS_FLOODS_NO_UNKNOWN_MC_DA; + else if (multicast) + reg |= PORT_CONTROL_EGRESS_FLOODS_NO_UNKNOWN_UC_DA; else - reg &= ~PORT_CONTROL_EGRESS_ALL_UNKNOWN_DA; + reg |= PORT_CONTROL_EGRESS_FLOODS_NO_UNKNOWN_DA; return mv88e6xxx_port_write(chip, port, PORT_CONTROL, reg); } /* Offset 0x05: Port Control 1 */ +int mv88e6xxx_port_set_message_port(struct mv88e6xxx_chip *chip, int port, + bool message_port) +{ + u16 val; + int err; + + err = mv88e6xxx_port_read(chip, port, PORT_CONTROL_1, &val); + if (err) + return err; + + if (message_port) + val |= PORT_CONTROL_1_MESSAGE_PORT; + else + val &= ~PORT_CONTROL_1_MESSAGE_PORT; + + return mv88e6xxx_port_write(chip, port, PORT_CONTROL_1, val); +} + /* Offset 0x06: Port Based VLAN Map */ int mv88e6xxx_port_set_vlan_map(struct mv88e6xxx_chip *chip, int port, u16 map) { - const u16 mask = GENMASK(mv88e6xxx_num_ports(chip) - 1, 0); + const u16 mask = mv88e6xxx_port_mask(chip); u16 reg; int err; @@ -672,8 +696,8 @@ static const char * const mv88e6xxx_port_8021q_mode_names[] = { [PORT_CONTROL_2_8021Q_SECURE] = "Secure", }; -int mv88e6095_port_set_egress_unknowns(struct mv88e6xxx_chip *chip, int port, - bool on) +static int mv88e6185_port_set_default_forward(struct mv88e6xxx_chip *chip, + int port, bool multicast) { int err; u16 reg; @@ -682,14 +706,26 @@ int mv88e6095_port_set_egress_unknowns(struct mv88e6xxx_chip *chip, int port, if (err) return err; - if (on) - reg |= PORT_CONTROL_2_FORWARD_UNKNOWN; + if (multicast) + reg |= PORT_CONTROL_2_DEFAULT_FORWARD; else - reg &= ~PORT_CONTROL_2_FORWARD_UNKNOWN; + reg &= ~PORT_CONTROL_2_DEFAULT_FORWARD; return mv88e6xxx_port_write(chip, port, PORT_CONTROL_2, reg); } +int mv88e6185_port_set_egress_floods(struct mv88e6xxx_chip *chip, int port, + bool unicast, bool multicast) +{ + int err; + + err = mv88e6185_port_set_forward_unknown(chip, port, unicast); + if (err) + return err; + + return mv88e6185_port_set_default_forward(chip, port, multicast); +} + int mv88e6095_port_set_upstream_port(struct mv88e6xxx_chip *chip, int port, int upstream_port) { @@ -769,6 +805,20 @@ int mv88e6097_port_egress_rate_limiting(struct mv88e6xxx_chip *chip, int port) return mv88e6xxx_port_write(chip, port, PORT_RATE_CONTROL, 0x0001); } +/* Offset 0x0C: Port ATU Control */ + +int mv88e6xxx_port_disable_learn_limit(struct mv88e6xxx_chip *chip, int port) +{ + return mv88e6xxx_port_write(chip, port, PORT_ATU_CONTROL, 0); +} + +/* Offset 0x0D: (Priority) Override Register */ + +int mv88e6xxx_port_disable_pri_override(struct mv88e6xxx_chip *chip, int port) +{ + return mv88e6xxx_port_write(chip, port, PORT_PRI_OVERRIDE, 0); +} + /* Offset 0x0f: Port Ether type */ int mv88e6351_port_set_ether_type(struct mv88e6xxx_chip *chip, int port, diff --git a/drivers/net/dsa/mv88e6xxx/port.h b/drivers/net/dsa/mv88e6xxx/port.h index c83cbb3f4491..c2425ddab287 100644 --- a/drivers/net/dsa/mv88e6xxx/port.h +++ b/drivers/net/dsa/mv88e6xxx/port.h @@ -56,14 +56,14 @@ int mv88e6085_port_set_frame_mode(struct mv88e6xxx_chip *chip, int port, enum mv88e6xxx_frame_mode mode); int mv88e6351_port_set_frame_mode(struct mv88e6xxx_chip *chip, int port, enum mv88e6xxx_frame_mode mode); -int mv88e6085_port_set_egress_unknowns(struct mv88e6xxx_chip *chip, int port, - bool on); -int mv88e6095_port_set_egress_unknowns(struct mv88e6xxx_chip *chip, int port, - bool on); -int mv88e6351_port_set_egress_unknowns(struct mv88e6xxx_chip *chip, int port, - bool on); +int mv88e6185_port_set_egress_floods(struct mv88e6xxx_chip *chip, int port, + bool unicast, bool multicast); +int mv88e6352_port_set_egress_floods(struct mv88e6xxx_chip *chip, int port, + bool unicast, bool multicast); int mv88e6351_port_set_ether_type(struct mv88e6xxx_chip *chip, int port, u16 etype); +int mv88e6xxx_port_set_message_port(struct mv88e6xxx_chip *chip, int port, + bool message_port); int mv88e6165_port_jumbo_config(struct mv88e6xxx_chip *chip, int port); int mv88e6095_port_egress_rate_limiting(struct mv88e6xxx_chip *chip, int port); int mv88e6097_port_egress_rate_limiting(struct mv88e6xxx_chip *chip, int port); @@ -75,4 +75,8 @@ int mv88e6xxx_port_get_cmode(struct mv88e6xxx_chip *chip, int port, u8 *cmode); int mv88e6xxx_port_set_map_da(struct mv88e6xxx_chip *chip, int port); int mv88e6095_port_set_upstream_port(struct mv88e6xxx_chip *chip, int port, int upstream_port); + +int mv88e6xxx_port_disable_learn_limit(struct mv88e6xxx_chip *chip, int port); +int mv88e6xxx_port_disable_pri_override(struct mv88e6xxx_chip *chip, int port); + #endif /* _MV88E6XXX_PORT_H */ diff --git a/drivers/net/ethernet/Kconfig b/drivers/net/ethernet/Kconfig index 8c08f9deef92..edae15ac0e98 100644 --- a/drivers/net/ethernet/Kconfig +++ b/drivers/net/ethernet/Kconfig @@ -180,5 +180,6 @@ source "drivers/net/ethernet/via/Kconfig" source "drivers/net/ethernet/wiznet/Kconfig" source "drivers/net/ethernet/xilinx/Kconfig" source "drivers/net/ethernet/xircom/Kconfig" +source "drivers/net/ethernet/synopsys/Kconfig" endif # ETHERNET diff --git a/drivers/net/ethernet/Makefile b/drivers/net/ethernet/Makefile index 26dce5bf2c18..bf7f4502cabc 100644 --- a/drivers/net/ethernet/Makefile +++ b/drivers/net/ethernet/Makefile @@ -91,3 +91,4 @@ obj-$(CONFIG_NET_VENDOR_VIA) += via/ obj-$(CONFIG_NET_VENDOR_WIZNET) += wiznet/ obj-$(CONFIG_NET_VENDOR_XILINX) += xilinx/ obj-$(CONFIG_NET_VENDOR_XIRCOM) += xircom/ +obj-$(CONFIG_NET_VENDOR_SYNOPSYS) += synopsys/ diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c index 248f60d171a5..7ec2c9717cf1 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c +++ b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c @@ -1854,7 +1854,8 @@ static int xgbe_setup_tc(struct net_device *netdev, u32 handle, __be16 proto, if (tc_to_netdev->type != TC_SETUP_MQPRIO) return -EINVAL; - tc = tc_to_netdev->tc; + tc_to_netdev->mqprio->hw = TC_MQPRIO_HW_OFFLOAD_TCS; + tc = tc_to_netdev->mqprio->num_tc; if (tc > pdata->hw_feat.tc_cnt) return -EINVAL; @@ -2272,10 +2273,7 @@ static int xgbe_one_poll(struct napi_struct *napi, int budget) processed = xgbe_rx_poll(channel, budget); /* If we processed everything, we are done */ - if (processed < budget) { - /* Turn off polling */ - napi_complete_done(napi, processed); - + if ((processed < budget) && napi_complete_done(napi, processed)) { /* Enable Tx and Rx interrupts */ if (pdata->channel_irq_mode) xgbe_enable_rx_tx_int(pdata, channel); @@ -2317,10 +2315,7 @@ static int xgbe_all_poll(struct napi_struct *napi, int budget) } while ((processed < budget) && (processed != last_processed)); /* If we processed everything, we are done */ - if (processed < budget) { - /* Turn off polling */ - napi_complete_done(napi, processed); - + if ((processed < budget) && napi_complete_done(napi, processed)) { /* Enable Tx and Rx interrupts */ xgbe_enable_rx_tx_ints(pdata); } diff --git a/drivers/net/ethernet/apm/Kconfig b/drivers/net/ethernet/apm/Kconfig index ec63d706d464..59efe5b145dd 100644 --- a/drivers/net/ethernet/apm/Kconfig +++ b/drivers/net/ethernet/apm/Kconfig @@ -1 +1,2 @@ source "drivers/net/ethernet/apm/xgene/Kconfig" +source "drivers/net/ethernet/apm/xgene-v2/Kconfig" diff --git a/drivers/net/ethernet/apm/Makefile b/drivers/net/ethernet/apm/Makefile index 65ce32ad1b2c..946b2a4c882d 100644 --- a/drivers/net/ethernet/apm/Makefile +++ b/drivers/net/ethernet/apm/Makefile @@ -3,3 +3,4 @@ # obj-$(CONFIG_NET_XGENE) += xgene/ +obj-$(CONFIG_NET_XGENE_V2) += xgene-v2/ diff --git a/drivers/net/ethernet/apm/xgene-v2/Kconfig b/drivers/net/ethernet/apm/xgene-v2/Kconfig new file mode 100644 index 000000000000..1205861b6318 --- /dev/null +++ b/drivers/net/ethernet/apm/xgene-v2/Kconfig @@ -0,0 +1,11 @@ +config NET_XGENE_V2 + tristate "APM X-Gene SoC Ethernet-v2 Driver" + depends on HAS_DMA + depends on ARCH_XGENE || COMPILE_TEST + help + This is the Ethernet driver for the on-chip ethernet interface + which uses a linked list of DMA descriptor architecture (v2) for + APM X-Gene SoCs. + + To compile this driver as a module, choose M here. This module will + be called xgene-enet-v2. diff --git a/drivers/net/ethernet/apm/xgene-v2/Makefile b/drivers/net/ethernet/apm/xgene-v2/Makefile new file mode 100644 index 000000000000..735309c0b8b1 --- /dev/null +++ b/drivers/net/ethernet/apm/xgene-v2/Makefile @@ -0,0 +1,6 @@ +# +# Makefile for APM X-Gene Ethernet v2 driver +# + +xgene-enet-v2-objs := main.o mac.o enet.o ring.o +obj-$(CONFIG_NET_XGENE_V2) += xgene-enet-v2.o diff --git a/drivers/net/ethernet/apm/xgene-v2/enet.c b/drivers/net/ethernet/apm/xgene-v2/enet.c new file mode 100644 index 000000000000..b49edeeb6275 --- /dev/null +++ b/drivers/net/ethernet/apm/xgene-v2/enet.c @@ -0,0 +1,71 @@ +/* + * Applied Micro X-Gene SoC Ethernet v2 Driver + * + * Copyright (c) 2017, Applied Micro Circuits Corporation + * Author(s): Iyappan Subramanian <[email protected]> + * Keyur Chudgar <[email protected]> + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the + * Free Software Foundation; either version 2 of the License, or (at your + * option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +#include "main.h" + +void xge_wr_csr(struct xge_pdata *pdata, u32 offset, u32 val) +{ + void __iomem *addr = pdata->resources.base_addr + offset; + + iowrite32(val, addr); +} + +u32 xge_rd_csr(struct xge_pdata *pdata, u32 offset) +{ + void __iomem *addr = pdata->resources.base_addr + offset; + + return ioread32(addr); +} + +int xge_port_reset(struct net_device *ndev) +{ + struct xge_pdata *pdata = netdev_priv(ndev); + + xge_wr_csr(pdata, ENET_SRST, 0x3); + xge_wr_csr(pdata, ENET_SRST, 0x2); + xge_wr_csr(pdata, ENET_SRST, 0x0); + + xge_wr_csr(pdata, ENET_SHIM, DEVM_ARAUX_COH | DEVM_AWAUX_COH); + + return 0; +} + +static void xge_traffic_resume(struct net_device *ndev) +{ + struct xge_pdata *pdata = netdev_priv(ndev); + + xge_wr_csr(pdata, CFG_FORCE_LINK_STATUS_EN, 1); + xge_wr_csr(pdata, FORCE_LINK_STATUS, 1); + + xge_wr_csr(pdata, CFG_LINK_AGGR_RESUME, 1); + xge_wr_csr(pdata, RX_DV_GATE_REG, 1); +} + +int xge_port_init(struct net_device *ndev) +{ + struct xge_pdata *pdata = netdev_priv(ndev); + + pdata->phy_speed = SPEED_1000; + xge_mac_init(pdata); + xge_traffic_resume(ndev); + + return 0; +} diff --git a/drivers/net/ethernet/apm/xgene-v2/enet.h b/drivers/net/ethernet/apm/xgene-v2/enet.h new file mode 100644 index 000000000000..40371cfcfce4 --- /dev/null +++ b/drivers/net/ethernet/apm/xgene-v2/enet.h @@ -0,0 +1,43 @@ +/* + * Applied Micro X-Gene SoC Ethernet v2 Driver + * + * Copyright (c) 2017, Applied Micro Circuits Corporation + * Author(s): Iyappan Subramanian <[email protected]> + * Keyur Chudgar <[email protected]> + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the + * Free Software Foundation; either version 2 of the License, or (at your + * option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +#ifndef __XGENE_ENET_V2_ENET_H__ +#define __XGENE_ENET_V2_ENET_H__ + +#define ENET_CLKEN 0xc008 +#define ENET_SRST 0xc000 +#define ENET_SHIM 0xc010 +#define CFG_MEM_RAM_SHUTDOWN 0xd070 +#define BLOCK_MEM_RDY 0xd074 + +#define DEVM_ARAUX_COH BIT(19) +#define DEVM_AWAUX_COH BIT(3) + +#define CFG_FORCE_LINK_STATUS_EN 0x229c +#define FORCE_LINK_STATUS 0x22a0 +#define CFG_LINK_AGGR_RESUME 0x27c8 +#define RX_DV_GATE_REG 0x2dfc + +void xge_wr_csr(struct xge_pdata *pdata, u32 offset, u32 val); +u32 xge_rd_csr(struct xge_pdata *pdata, u32 offset); +int xge_port_reset(struct net_device *ndev); + +#endif /* __XGENE_ENET_V2_ENET__H__ */ diff --git a/drivers/net/ethernet/apm/xgene-v2/mac.c b/drivers/net/ethernet/apm/xgene-v2/mac.c new file mode 100644 index 000000000000..c3189de3df55 --- /dev/null +++ b/drivers/net/ethernet/apm/xgene-v2/mac.c @@ -0,0 +1,116 @@ +/* + * Applied Micro X-Gene SoC Ethernet v2 Driver + * + * Copyright (c) 2017, Applied Micro Circuits Corporation + * Author(s): Iyappan Subramanian <[email protected]> + * Keyur Chudgar <[email protected]> + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the + * Free Software Foundation; either version 2 of the License, or (at your + * option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +#include "main.h" + +void xge_mac_reset(struct xge_pdata *pdata) +{ + xge_wr_csr(pdata, MAC_CONFIG_1, SOFT_RESET); + xge_wr_csr(pdata, MAC_CONFIG_1, 0); +} + +static void xge_mac_set_speed(struct xge_pdata *pdata) +{ + u32 icm0, icm2, ecm0, mc2; + u32 intf_ctrl, rgmii; + + icm0 = xge_rd_csr(pdata, ICM_CONFIG0_REG_0); + icm2 = xge_rd_csr(pdata, ICM_CONFIG2_REG_0); + ecm0 = xge_rd_csr(pdata, ECM_CONFIG0_REG_0); + rgmii = xge_rd_csr(pdata, RGMII_REG_0); + mc2 = xge_rd_csr(pdata, MAC_CONFIG_2); + intf_ctrl = xge_rd_csr(pdata, INTERFACE_CONTROL); + icm2 |= CFG_WAITASYNCRD_EN; + + switch (pdata->phy_speed) { + case SPEED_10: + SET_REG_BITS(&mc2, INTF_MODE, 1); + SET_REG_BITS(&intf_ctrl, HD_MODE, 0); + SET_REG_BITS(&icm0, CFG_MACMODE, 0); + SET_REG_BITS(&icm2, CFG_WAITASYNCRD, 500); + SET_REG_BIT(&rgmii, CFG_SPEED_125, 0); + break; + case SPEED_100: + SET_REG_BITS(&mc2, INTF_MODE, 1); + SET_REG_BITS(&intf_ctrl, HD_MODE, 1); + SET_REG_BITS(&icm0, CFG_MACMODE, 1); + SET_REG_BITS(&icm2, CFG_WAITASYNCRD, 80); + SET_REG_BIT(&rgmii, CFG_SPEED_125, 0); + break; + default: + SET_REG_BITS(&mc2, INTF_MODE, 2); + SET_REG_BITS(&intf_ctrl, HD_MODE, 2); + SET_REG_BITS(&icm0, CFG_MACMODE, 2); + SET_REG_BITS(&icm2, CFG_WAITASYNCRD, 16); + SET_REG_BIT(&rgmii, CFG_SPEED_125, 1); + break; + } + + mc2 |= FULL_DUPLEX | CRC_EN | PAD_CRC; + SET_REG_BITS(&ecm0, CFG_WFIFOFULLTHR, 0x32); + + xge_wr_csr(pdata, MAC_CONFIG_2, mc2); + xge_wr_csr(pdata, INTERFACE_CONTROL, intf_ctrl); + xge_wr_csr(pdata, RGMII_REG_0, rgmii); + xge_wr_csr(pdata, ICM_CONFIG0_REG_0, icm0); + xge_wr_csr(pdata, ICM_CONFIG2_REG_0, icm2); + xge_wr_csr(pdata, ECM_CONFIG0_REG_0, ecm0); +} + +void xge_mac_set_station_addr(struct xge_pdata *pdata) +{ + u8 *dev_addr = pdata->ndev->dev_addr; + u32 addr0, addr1; + + addr0 = (dev_addr[3] << 24) | (dev_addr[2] << 16) | + (dev_addr[1] << 8) | dev_addr[0]; + addr1 = (dev_addr[5] << 24) | (dev_addr[4] << 16); + + xge_wr_csr(pdata, STATION_ADDR0, addr0); + xge_wr_csr(pdata, STATION_ADDR1, addr1); +} + +void xge_mac_init(struct xge_pdata *pdata) +{ + xge_mac_reset(pdata); + xge_mac_set_speed(pdata); + xge_mac_set_station_addr(pdata); +} + +void xge_mac_enable(struct xge_pdata *pdata) +{ + u32 data; + + data = xge_rd_csr(pdata, MAC_CONFIG_1); + data |= TX_EN | RX_EN; + xge_wr_csr(pdata, MAC_CONFIG_1, data); + + data = xge_rd_csr(pdata, MAC_CONFIG_1); +} + +void xge_mac_disable(struct xge_pdata *pdata) +{ + u32 data; + + data = xge_rd_csr(pdata, MAC_CONFIG_1); + data &= ~(TX_EN | RX_EN); + xge_wr_csr(pdata, MAC_CONFIG_1, data); +} diff --git a/drivers/net/ethernet/apm/xgene-v2/mac.h b/drivers/net/ethernet/apm/xgene-v2/mac.h new file mode 100644 index 000000000000..0fce6ae15ce0 --- /dev/null +++ b/drivers/net/ethernet/apm/xgene-v2/mac.h @@ -0,0 +1,110 @@ +/* + * Applied Micro X-Gene SoC Ethernet v2 Driver + * + * Copyright (c) 2017, Applied Micro Circuits Corporation + * Author(s): Iyappan Subramanian <[email protected]> + * Keyur Chudgar <[email protected]> + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the + * Free Software Foundation; either version 2 of the License, or (at your + * option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +#ifndef __XGENE_ENET_V2_MAC_H__ +#define __XGENE_ENET_V2_MAC_H__ + +/* Register offsets */ +#define MAC_CONFIG_1 0xa000 +#define MAC_CONFIG_2 0xa004 +#define MII_MGMT_CONFIG 0xa020 +#define MII_MGMT_COMMAND 0xa024 +#define MII_MGMT_ADDRESS 0xa028 +#define MII_MGMT_CONTROL 0xa02c +#define MII_MGMT_STATUS 0xa030 +#define MII_MGMT_INDICATORS 0xa034 +#define INTERFACE_CONTROL 0xa038 +#define STATION_ADDR0 0xa040 +#define STATION_ADDR1 0xa044 +#define RBYT 0xa09c +#define RPKT 0xa0a0 +#define RFCS 0xa0a4 + +#define RGMII_REG_0 0x27e0 +#define ICM_CONFIG0_REG_0 0x2c00 +#define ICM_CONFIG2_REG_0 0x2c08 +#define ECM_CONFIG0_REG_0 0x2d00 + +/* Register fields */ +#define SOFT_RESET BIT(31) +#define TX_EN BIT(0) +#define RX_EN BIT(2) +#define PAD_CRC BIT(2) +#define CRC_EN BIT(1) +#define FULL_DUPLEX BIT(0) + +#define INTF_MODE_POS 8 +#define INTF_MODE_LEN 2 +#define HD_MODE_POS 25 +#define HD_MODE_LEN 2 +#define CFG_MACMODE_POS 18 +#define CFG_MACMODE_LEN 2 +#define CFG_WAITASYNCRD_POS 0 +#define CFG_WAITASYNCRD_LEN 16 +#define CFG_SPEED_125_POS 24 +#define CFG_WFIFOFULLTHR_POS 0 +#define CFG_WFIFOFULLTHR_LEN 7 +#define MGMT_CLOCK_SEL_POS 0 +#define MGMT_CLOCK_SEL_LEN 3 +#define PHY_ADDR_POS 8 +#define PHY_ADDR_LEN 5 +#define REG_ADDR_POS 0 +#define REG_ADDR_LEN 5 +#define MII_MGMT_BUSY BIT(0) +#define MII_READ_CYCLE BIT(0) +#define CFG_WAITASYNCRD_EN BIT(16) + +static inline void xgene_set_reg_bits(u32 *var, int pos, int len, u32 val) +{ + u32 mask = GENMASK(pos + len, pos); + + *var &= ~mask; + *var |= ((val << pos) & mask); +} + +static inline u32 xgene_get_reg_bits(u32 var, int pos, int len) +{ + u32 mask = GENMASK(pos + len, pos); + + return (var & mask) >> pos; +} + +#define SET_REG_BITS(var, field, val) \ + xgene_set_reg_bits(var, field ## _POS, field ## _LEN, val) + +#define SET_REG_BIT(var, field, val) \ + xgene_set_reg_bits(var, field ## _POS, 1, val) + +#define GET_REG_BITS(var, field) \ + xgene_get_reg_bits(var, field ## _POS, field ## _LEN) + +#define GET_REG_BIT(var, field) ((var) & (field)) + +struct xge_pdata; + +void xge_mac_reset(struct xge_pdata *pdata); +void xge_mac_enable(struct xge_pdata *pdata); +void xge_mac_disable(struct xge_pdata *pdata); +void xge_mac_init(struct xge_pdata *pdata); +int xge_port_init(struct net_device *ndev); +void xge_mac_set_station_addr(struct xge_pdata *pdata); + +#endif /* __XGENE_ENET_V2_MAC_H__ */ diff --git a/drivers/net/ethernet/apm/xgene-v2/main.c b/drivers/net/ethernet/apm/xgene-v2/main.c new file mode 100644 index 000000000000..ae76977d10b4 --- /dev/null +++ b/drivers/net/ethernet/apm/xgene-v2/main.c @@ -0,0 +1,756 @@ +/* + * Applied Micro X-Gene SoC Ethernet v2 Driver + * + * Copyright (c) 2017, Applied Micro Circuits Corporation + * Author(s): Iyappan Subramanian <[email protected]> + * Keyur Chudgar <[email protected]> + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the + * Free Software Foundation; either version 2 of the License, or (at your + * option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +#include "main.h" + +static const struct acpi_device_id xge_acpi_match[]; + +static int xge_get_resources(struct xge_pdata *pdata) +{ + struct platform_device *pdev; + struct net_device *ndev; + int phy_mode, ret = 0; + struct resource *res; + struct device *dev; + + pdev = pdata->pdev; + dev = &pdev->dev; + ndev = pdata->ndev; + + res = platform_get_resource(pdev, IORESOURCE_MEM, 0); + if (!res) { + dev_err(dev, "Resource enet_csr not defined\n"); + return -ENODEV; + } + + pdata->resources.base_addr = devm_ioremap(dev, res->start, + resource_size(res)); + if (!pdata->resources.base_addr) { + dev_err(dev, "Unable to retrieve ENET Port CSR region\n"); + return -ENOMEM; + } + + if (!device_get_mac_address(dev, ndev->dev_addr, ETH_ALEN)) + eth_hw_addr_random(ndev); + + memcpy(ndev->perm_addr, ndev->dev_addr, ndev->addr_len); + + phy_mode = device_get_phy_mode(dev); + if (phy_mode < 0) { + dev_err(dev, "Unable to get phy-connection-type\n"); + return phy_mode; + } + pdata->resources.phy_mode = phy_mode; + + if (pdata->resources.phy_mode != PHY_INTERFACE_MODE_RGMII) { + dev_err(dev, "Incorrect phy-connection-type specified\n"); + return -ENODEV; + } + + ret = platform_get_irq(pdev, 0); + if (ret <= 0) { + dev_err(dev, "Unable to get ENET IRQ\n"); + ret = ret ? : -ENXIO; + return ret; + } + pdata->resources.irq = ret; + + return 0; +} + +static int xge_refill_buffers(struct net_device *ndev, u32 nbuf) +{ + struct xge_pdata *pdata = netdev_priv(ndev); + struct xge_desc_ring *ring = pdata->rx_ring; + const u8 slots = XGENE_ENET_NUM_DESC - 1; + struct device *dev = &pdata->pdev->dev; + struct xge_raw_desc *raw_desc; + u64 addr_lo, addr_hi; + u8 tail = ring->tail; + struct sk_buff *skb; + dma_addr_t dma_addr; + u16 len; + int i; + + for (i = 0; i < nbuf; i++) { + raw_desc = &ring->raw_desc[tail]; + + len = XGENE_ENET_STD_MTU; + skb = netdev_alloc_skb(ndev, len); + if (unlikely(!skb)) + return -ENOMEM; + + dma_addr = dma_map_single(dev, skb->data, len, DMA_FROM_DEVICE); + if (dma_mapping_error(dev, dma_addr)) { + netdev_err(ndev, "DMA mapping error\n"); + dev_kfree_skb_any(skb); + return -EINVAL; + } + + ring->pkt_info[tail].skb = skb; + ring->pkt_info[tail].dma_addr = dma_addr; + + addr_hi = GET_BITS(NEXT_DESC_ADDRH, le64_to_cpu(raw_desc->m1)); + addr_lo = GET_BITS(NEXT_DESC_ADDRL, le64_to_cpu(raw_desc->m1)); + raw_desc->m1 = cpu_to_le64(SET_BITS(NEXT_DESC_ADDRL, addr_lo) | + SET_BITS(NEXT_DESC_ADDRH, addr_hi) | + SET_BITS(PKT_ADDRH, + upper_32_bits(dma_addr))); + + dma_wmb(); + raw_desc->m0 = cpu_to_le64(SET_BITS(PKT_ADDRL, dma_addr) | + SET_BITS(E, 1)); + tail = (tail + 1) & slots; + } + + ring->tail = tail; + + return 0; +} + +static int xge_init_hw(struct net_device *ndev) +{ + struct xge_pdata *pdata = netdev_priv(ndev); + int ret; + + ret = xge_port_reset(ndev); + if (ret) + return ret; + + xge_port_init(ndev); + pdata->nbufs = NUM_BUFS; + + return 0; +} + +static irqreturn_t xge_irq(const int irq, void *data) +{ + struct xge_pdata *pdata = data; + + if (napi_schedule_prep(&pdata->napi)) { + xge_intr_disable(pdata); + __napi_schedule(&pdata->napi); + } + + return IRQ_HANDLED; +} + +static int xge_request_irq(struct net_device *ndev) +{ + struct xge_pdata *pdata = netdev_priv(ndev); + struct device *dev = &pdata->pdev->dev; + int ret; + + snprintf(pdata->irq_name, IRQ_ID_SIZE, "%s", ndev->name); + + ret = devm_request_irq(dev, pdata->resources.irq, xge_irq, + 0, pdata->irq_name, pdata); + if (ret) + netdev_err(ndev, "Failed to request irq %s\n", pdata->irq_name); + + return ret; +} + +static void xge_free_irq(struct net_device *ndev) +{ + struct xge_pdata *pdata = netdev_priv(ndev); + struct device *dev = &pdata->pdev->dev; + + devm_free_irq(dev, pdata->resources.irq, pdata); +} + +static bool is_tx_slot_available(struct xge_raw_desc *raw_desc) +{ + if (GET_BITS(E, le64_to_cpu(raw_desc->m0)) && + (GET_BITS(PKT_SIZE, le64_to_cpu(raw_desc->m0)) == SLOT_EMPTY)) + return true; + + return false; +} + +static netdev_tx_t xge_start_xmit(struct sk_buff *skb, struct net_device *ndev) +{ + struct xge_pdata *pdata = netdev_priv(ndev); + struct device *dev = &pdata->pdev->dev; + struct xge_desc_ring *tx_ring; + struct xge_raw_desc *raw_desc; + static dma_addr_t dma_addr; + u64 addr_lo, addr_hi; + void *pkt_buf; + u8 tail; + u16 len; + + tx_ring = pdata->tx_ring; + tail = tx_ring->tail; + len = skb_headlen(skb); + raw_desc = &tx_ring->raw_desc[tail]; + + if (!is_tx_slot_available(raw_desc)) { + netif_stop_queue(ndev); + return NETDEV_TX_BUSY; + } + + /* Packet buffers should be 64B aligned */ + pkt_buf = dma_zalloc_coherent(dev, XGENE_ENET_STD_MTU, &dma_addr, + GFP_ATOMIC); + if (unlikely(!pkt_buf)) { + dev_kfree_skb_any(skb); + return NETDEV_TX_OK; + } + memcpy(pkt_buf, skb->data, len); + + addr_hi = GET_BITS(NEXT_DESC_ADDRH, le64_to_cpu(raw_desc->m1)); + addr_lo = GET_BITS(NEXT_DESC_ADDRL, le64_to_cpu(raw_desc->m1)); + raw_desc->m1 = cpu_to_le64(SET_BITS(NEXT_DESC_ADDRL, addr_lo) | + SET_BITS(NEXT_DESC_ADDRH, addr_hi) | + SET_BITS(PKT_ADDRH, + upper_32_bits(dma_addr))); + + tx_ring->pkt_info[tail].skb = skb; + tx_ring->pkt_info[tail].dma_addr = dma_addr; + tx_ring->pkt_info[tail].pkt_buf = pkt_buf; + + dma_wmb(); + + raw_desc->m0 = cpu_to_le64(SET_BITS(PKT_ADDRL, dma_addr) | + SET_BITS(PKT_SIZE, len) | + SET_BITS(E, 0)); + skb_tx_timestamp(skb); + xge_wr_csr(pdata, DMATXCTRL, 1); + + tx_ring->tail = (tail + 1) & (XGENE_ENET_NUM_DESC - 1); + + return NETDEV_TX_OK; +} + +static bool is_tx_hw_done(struct xge_raw_desc *raw_desc) +{ + if (GET_BITS(E, le64_to_cpu(raw_desc->m0)) && + !GET_BITS(PKT_SIZE, le64_to_cpu(raw_desc->m0))) + return true; + + return false; +} + +static void xge_txc_poll(struct net_device *ndev) +{ + struct xge_pdata *pdata = netdev_priv(ndev); + struct device *dev = &pdata->pdev->dev; + struct xge_desc_ring *tx_ring; + struct xge_raw_desc *raw_desc; + dma_addr_t dma_addr; + struct sk_buff *skb; + void *pkt_buf; + u32 data; + u8 head; + + tx_ring = pdata->tx_ring; + head = tx_ring->head; + + data = xge_rd_csr(pdata, DMATXSTATUS); + if (!GET_BITS(TXPKTCOUNT, data)) + return; + + while (1) { + raw_desc = &tx_ring->raw_desc[head]; + + if (!is_tx_hw_done(raw_desc)) + break; + + dma_rmb(); + + skb = tx_ring->pkt_info[head].skb; + dma_addr = tx_ring->pkt_info[head].dma_addr; + pkt_buf = tx_ring->pkt_info[head].pkt_buf; + pdata->stats.tx_packets++; + pdata->stats.tx_bytes += skb->len; + dma_free_coherent(dev, XGENE_ENET_STD_MTU, pkt_buf, dma_addr); + dev_kfree_skb_any(skb); + + /* clear pktstart address and pktsize */ + raw_desc->m0 = cpu_to_le64(SET_BITS(E, 1) | + SET_BITS(PKT_SIZE, SLOT_EMPTY)); + xge_wr_csr(pdata, DMATXSTATUS, 1); + + head = (head + 1) & (XGENE_ENET_NUM_DESC - 1); + } + + if (netif_queue_stopped(ndev)) + netif_wake_queue(ndev); + + tx_ring->head = head; +} + +static int xge_rx_poll(struct net_device *ndev, unsigned int budget) +{ + struct xge_pdata *pdata = netdev_priv(ndev); + struct device *dev = &pdata->pdev->dev; + struct xge_desc_ring *rx_ring; + struct xge_raw_desc *raw_desc; + struct sk_buff *skb; + dma_addr_t dma_addr; + int processed = 0; + u8 head, rx_error; + int i, ret; + u32 data; + u16 len; + + rx_ring = pdata->rx_ring; + head = rx_ring->head; + + data = xge_rd_csr(pdata, DMARXSTATUS); + if (!GET_BITS(RXPKTCOUNT, data)) + return 0; + + for (i = 0; i < budget; i++) { + raw_desc = &rx_ring->raw_desc[head]; + + if (GET_BITS(E, le64_to_cpu(raw_desc->m0))) + break; + + dma_rmb(); + + skb = rx_ring->pkt_info[head].skb; + rx_ring->pkt_info[head].skb = NULL; + dma_addr = rx_ring->pkt_info[head].dma_addr; + len = GET_BITS(PKT_SIZE, le64_to_cpu(raw_desc->m0)); + dma_unmap_single(dev, dma_addr, XGENE_ENET_STD_MTU, + DMA_FROM_DEVICE); + + rx_error = GET_BITS(D, le64_to_cpu(raw_desc->m2)); + if (unlikely(rx_error)) { + pdata->stats.rx_errors++; + dev_kfree_skb_any(skb); + goto out; + } + + skb_put(skb, len); + skb->protocol = eth_type_trans(skb, ndev); + + pdata->stats.rx_packets++; + pdata->stats.rx_bytes += len; + napi_gro_receive(&pdata->napi, skb); +out: + ret = xge_refill_buffers(ndev, 1); + xge_wr_csr(pdata, DMARXSTATUS, 1); + xge_wr_csr(pdata, DMARXCTRL, 1); + + if (ret) + break; + + head = (head + 1) & (XGENE_ENET_NUM_DESC - 1); + processed++; + } + + rx_ring->head = head; + + return processed; +} + +static void xge_delete_desc_ring(struct net_device *ndev, + struct xge_desc_ring *ring) +{ + struct xge_pdata *pdata = netdev_priv(ndev); + struct device *dev = &pdata->pdev->dev; + u16 size; + + if (!ring) + return; + + size = XGENE_ENET_DESC_SIZE * XGENE_ENET_NUM_DESC; + if (ring->desc_addr) + dma_free_coherent(dev, size, ring->desc_addr, ring->dma_addr); + + kfree(ring->pkt_info); + kfree(ring); +} + +static void xge_free_buffers(struct net_device *ndev) +{ + struct xge_pdata *pdata = netdev_priv(ndev); + struct xge_desc_ring *ring = pdata->rx_ring; + struct device *dev = &pdata->pdev->dev; + struct sk_buff *skb; + dma_addr_t dma_addr; + int i; + + for (i = 0; i < XGENE_ENET_NUM_DESC; i++) { + skb = ring->pkt_info[i].skb; + dma_addr = ring->pkt_info[i].dma_addr; + + if (!skb) + continue; + + dma_unmap_single(dev, dma_addr, XGENE_ENET_STD_MTU, + DMA_FROM_DEVICE); + dev_kfree_skb_any(skb); + } +} + +static void xge_delete_desc_rings(struct net_device *ndev) +{ + struct xge_pdata *pdata = netdev_priv(ndev); + + xge_txc_poll(ndev); + xge_delete_desc_ring(ndev, pdata->tx_ring); + + xge_rx_poll(ndev, 64); + xge_free_buffers(ndev); + xge_delete_desc_ring(ndev, pdata->rx_ring); +} + +static struct xge_desc_ring *xge_create_desc_ring(struct net_device *ndev) +{ + struct xge_pdata *pdata = netdev_priv(ndev); + struct device *dev = &pdata->pdev->dev; + struct xge_desc_ring *ring; + u16 size; + + ring = kzalloc(sizeof(struct xge_desc_ring), GFP_KERNEL); + if (!ring) + return NULL; + + ring->ndev = ndev; + + size = XGENE_ENET_DESC_SIZE * XGENE_ENET_NUM_DESC; + ring->desc_addr = dma_zalloc_coherent(dev, size, &ring->dma_addr, + GFP_KERNEL); + if (!ring->desc_addr) + goto err; + + ring->pkt_info = kcalloc(XGENE_ENET_NUM_DESC, sizeof(struct pkt_info), + GFP_KERNEL); + if (!ring->pkt_info) + goto err; + + xge_setup_desc(ring); + + return ring; + +err: + xge_delete_desc_ring(ndev, ring); + + return NULL; +} + +static int xge_create_desc_rings(struct net_device *ndev) +{ + struct xge_pdata *pdata = netdev_priv(ndev); + struct xge_desc_ring *ring; + int ret; + + /* create tx ring */ + ring = xge_create_desc_ring(ndev); + if (!ring) + goto err; + + pdata->tx_ring = ring; + xge_update_tx_desc_addr(pdata); + + /* create rx ring */ + ring = xge_create_desc_ring(ndev); + if (!ring) + goto err; + + pdata->rx_ring = ring; + xge_update_rx_desc_addr(pdata); + + ret = xge_refill_buffers(ndev, XGENE_ENET_NUM_DESC); + if (ret) + goto err; + + return 0; +err: + xge_delete_desc_rings(ndev); + + return -ENOMEM; +} + +static int xge_open(struct net_device *ndev) +{ + struct xge_pdata *pdata = netdev_priv(ndev); + int ret; + + ret = xge_create_desc_rings(ndev); + if (ret) + return ret; + + napi_enable(&pdata->napi); + ret = xge_request_irq(ndev); + if (ret) + return ret; + + xge_intr_enable(pdata); + xge_wr_csr(pdata, DMARXCTRL, 1); + xge_mac_enable(pdata); + netif_start_queue(ndev); + netif_carrier_on(ndev); + + return 0; +} + +static int xge_close(struct net_device *ndev) +{ + struct xge_pdata *pdata = netdev_priv(ndev); + + netif_carrier_off(ndev); + netif_stop_queue(ndev); + xge_mac_disable(pdata); + + xge_intr_disable(pdata); + xge_free_irq(ndev); + napi_disable(&pdata->napi); + xge_delete_desc_rings(ndev); + + return 0; +} + +static int xge_napi(struct napi_struct *napi, const int budget) +{ + struct net_device *ndev = napi->dev; + struct xge_pdata *pdata; + int processed; + + pdata = netdev_priv(ndev); + + xge_txc_poll(ndev); + processed = xge_rx_poll(ndev, budget); + + if (processed < budget) { + napi_complete_done(napi, processed); + xge_intr_enable(pdata); + } + + return processed; +} + +static int xge_set_mac_addr(struct net_device *ndev, void *addr) +{ + struct xge_pdata *pdata = netdev_priv(ndev); + int ret; + + ret = eth_mac_addr(ndev, addr); + if (ret) + return ret; + + xge_mac_set_station_addr(pdata); + + return 0; +} + +static bool is_tx_pending(struct xge_raw_desc *raw_desc) +{ + if (!GET_BITS(E, le64_to_cpu(raw_desc->m0))) + return true; + + return false; +} + +static void xge_free_pending_skb(struct net_device *ndev) +{ + struct xge_pdata *pdata = netdev_priv(ndev); + struct device *dev = &pdata->pdev->dev; + struct xge_desc_ring *tx_ring; + struct xge_raw_desc *raw_desc; + dma_addr_t dma_addr; + struct sk_buff *skb; + void *pkt_buf; + int i; + + tx_ring = pdata->tx_ring; + + for (i = 0; i < XGENE_ENET_NUM_DESC; i++) { + raw_desc = &tx_ring->raw_desc[i]; + + if (!is_tx_pending(raw_desc)) + continue; + + skb = tx_ring->pkt_info[i].skb; + dma_addr = tx_ring->pkt_info[i].dma_addr; + pkt_buf = tx_ring->pkt_info[i].pkt_buf; + dma_free_coherent(dev, XGENE_ENET_STD_MTU, pkt_buf, dma_addr); + dev_kfree_skb_any(skb); + } +} + +static void xge_timeout(struct net_device *ndev) +{ + struct xge_pdata *pdata = netdev_priv(ndev); + + rtnl_lock(); + + if (netif_running(ndev)) { + netif_carrier_off(ndev); + netif_stop_queue(ndev); + xge_intr_disable(pdata); + napi_disable(&pdata->napi); + + xge_wr_csr(pdata, DMATXCTRL, 0); + xge_txc_poll(ndev); + xge_free_pending_skb(ndev); + xge_wr_csr(pdata, DMATXSTATUS, ~0U); + + xge_setup_desc(pdata->tx_ring); + xge_update_tx_desc_addr(pdata); + xge_mac_init(pdata); + + napi_enable(&pdata->napi); + xge_intr_enable(pdata); + xge_mac_enable(pdata); + netif_start_queue(ndev); + netif_carrier_on(ndev); + } + + rtnl_unlock(); +} + +static void xge_get_stats64(struct net_device *ndev, + struct rtnl_link_stats64 *storage) +{ + struct xge_pdata *pdata = netdev_priv(ndev); + struct xge_stats *stats = &pdata->stats; + + storage->tx_packets += stats->tx_packets; + storage->tx_bytes += stats->tx_bytes; + + storage->rx_packets += stats->rx_packets; + storage->rx_bytes += stats->rx_bytes; + storage->rx_errors += stats->rx_errors; +} + +static const struct net_device_ops xgene_ndev_ops = { + .ndo_open = xge_open, + .ndo_stop = xge_close, + .ndo_start_xmit = xge_start_xmit, + .ndo_set_mac_address = xge_set_mac_addr, + .ndo_tx_timeout = xge_timeout, + .ndo_get_stats64 = xge_get_stats64, +}; + +static int xge_probe(struct platform_device *pdev) +{ + struct device *dev = &pdev->dev; + struct net_device *ndev; + struct xge_pdata *pdata; + int ret; + + ndev = alloc_etherdev(sizeof(struct xge_pdata)); + if (!ndev) + return -ENOMEM; + + pdata = netdev_priv(ndev); + + pdata->pdev = pdev; + pdata->ndev = ndev; + SET_NETDEV_DEV(ndev, dev); + platform_set_drvdata(pdev, pdata); + ndev->netdev_ops = &xgene_ndev_ops; + + ndev->features |= NETIF_F_GSO | + NETIF_F_GRO; + + ret = xge_get_resources(pdata); + if (ret) + goto err; + + ndev->hw_features = ndev->features; + + ret = dma_coerce_mask_and_coherent(dev, DMA_BIT_MASK(64)); + if (ret) { + netdev_err(ndev, "No usable DMA configuration\n"); + goto err; + } + + ret = xge_init_hw(ndev); + if (ret) + goto err; + + netif_napi_add(ndev, &pdata->napi, xge_napi, NAPI_POLL_WEIGHT); + + netif_carrier_off(ndev); + ret = register_netdev(ndev); + if (ret) { + netdev_err(ndev, "Failed to register netdev\n"); + goto err; + } + + return 0; + +err: + free_netdev(ndev); + + return ret; +} + +static int xge_remove(struct platform_device *pdev) +{ + struct xge_pdata *pdata; + struct net_device *ndev; + + pdata = platform_get_drvdata(pdev); + ndev = pdata->ndev; + + rtnl_lock(); + if (netif_running(ndev)) + dev_close(ndev); + rtnl_unlock(); + + unregister_netdev(ndev); + free_netdev(ndev); + + return 0; +} + +static void xge_shutdown(struct platform_device *pdev) +{ + struct xge_pdata *pdata; + + pdata = platform_get_drvdata(pdev); + if (!pdata) + return; + + if (!pdata->ndev) + return; + + xge_remove(pdev); +} + +static const struct acpi_device_id xge_acpi_match[] = { + { "APMC0D80" }, + { } +}; +MODULE_DEVICE_TABLE(acpi, xge_acpi_match); + +static struct platform_driver xge_driver = { + .driver = { + .name = "xgene-enet-v2", + .acpi_match_table = ACPI_PTR(xge_acpi_match), + }, + .probe = xge_probe, + .remove = xge_remove, + .shutdown = xge_shutdown, +}; +module_platform_driver(xge_driver); + +MODULE_DESCRIPTION("APM X-Gene SoC Ethernet v2 driver"); +MODULE_AUTHOR("Iyappan Subramanian <[email protected]>"); +MODULE_VERSION(XGENE_ENET_V2_VERSION); +MODULE_LICENSE("GPL"); diff --git a/drivers/net/ethernet/apm/xgene-v2/main.h b/drivers/net/ethernet/apm/xgene-v2/main.h new file mode 100644 index 000000000000..ada7b0e82586 --- /dev/null +++ b/drivers/net/ethernet/apm/xgene-v2/main.h @@ -0,0 +1,75 @@ +/* + * Applied Micro X-Gene SoC Ethernet v2 Driver + * + * Copyright (c) 2017, Applied Micro Circuits Corporation + * Author(s): Iyappan Subramanian <[email protected]> + * Keyur Chudgar <[email protected]> + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the + * Free Software Foundation; either version 2 of the License, or (at your + * option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +#ifndef __XGENE_ENET_V2_MAIN_H__ +#define __XGENE_ENET_V2_MAIN_H__ + +#include <linux/acpi.h> +#include <linux/clk.h> +#include <linux/efi.h> +#include <linux/if_vlan.h> +#include <linux/irq.h> +#include <linux/io.h> +#include <linux/module.h> +#include <linux/of_platform.h> +#include <linux/of_net.h> +#include <linux/of_mdio.h> +#include <linux/prefetch.h> +#include <linux/phy.h> +#include <net/ip.h> +#include "mac.h" +#include "enet.h" +#include "ring.h" + +#define XGENE_ENET_V2_VERSION "v1.0" +#define XGENE_ENET_STD_MTU 1536 +#define XGENE_ENET_MIN_FRAME 60 +#define IRQ_ID_SIZE 16 + +struct xge_resource { + void __iomem *base_addr; + int phy_mode; + u32 irq; +}; + +struct xge_stats { + u64 tx_packets; + u64 tx_bytes; + u64 rx_packets; + u64 rx_bytes; + u64 rx_errors; +}; + +/* ethernet private data */ +struct xge_pdata { + struct xge_resource resources; + struct xge_desc_ring *tx_ring; + struct xge_desc_ring *rx_ring; + struct platform_device *pdev; + char irq_name[IRQ_ID_SIZE]; + struct net_device *ndev; + struct napi_struct napi; + struct xge_stats stats; + int phy_speed; + u8 nbufs; +}; + +#endif /* __XGENE_ENET_V2_MAIN_H__ */ diff --git a/drivers/net/ethernet/apm/xgene-v2/ring.c b/drivers/net/ethernet/apm/xgene-v2/ring.c new file mode 100644 index 000000000000..38810828f8f0 --- /dev/null +++ b/drivers/net/ethernet/apm/xgene-v2/ring.c @@ -0,0 +1,81 @@ +/* + * Applied Micro X-Gene SoC Ethernet v2 Driver + * + * Copyright (c) 2017, Applied Micro Circuits Corporation + * Author(s): Iyappan Subramanian <[email protected]> + * Keyur Chudgar <[email protected]> + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the + * Free Software Foundation; either version 2 of the License, or (at your + * option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +#include "main.h" + +/* create circular linked list of descriptors */ +void xge_setup_desc(struct xge_desc_ring *ring) +{ + struct xge_raw_desc *raw_desc; + dma_addr_t dma_h, next_dma; + u16 offset; + int i; + + for (i = 0; i < XGENE_ENET_NUM_DESC; i++) { + raw_desc = &ring->raw_desc[i]; + + offset = (i + 1) & (XGENE_ENET_NUM_DESC - 1); + next_dma = ring->dma_addr + (offset * XGENE_ENET_DESC_SIZE); + + raw_desc->m0 = cpu_to_le64(SET_BITS(E, 1) | + SET_BITS(PKT_SIZE, SLOT_EMPTY)); + dma_h = upper_32_bits(next_dma); + raw_desc->m1 = cpu_to_le64(SET_BITS(NEXT_DESC_ADDRL, next_dma) | + SET_BITS(NEXT_DESC_ADDRH, dma_h)); + } +} + +void xge_update_tx_desc_addr(struct xge_pdata *pdata) +{ + struct xge_desc_ring *ring = pdata->tx_ring; + dma_addr_t dma_addr = ring->dma_addr; + + xge_wr_csr(pdata, DMATXDESCL, dma_addr); + xge_wr_csr(pdata, DMATXDESCH, upper_32_bits(dma_addr)); + + ring->head = 0; + ring->tail = 0; +} + +void xge_update_rx_desc_addr(struct xge_pdata *pdata) +{ + struct xge_desc_ring *ring = pdata->rx_ring; + dma_addr_t dma_addr = ring->dma_addr; + + xge_wr_csr(pdata, DMARXDESCL, dma_addr); + xge_wr_csr(pdata, DMARXDESCH, upper_32_bits(dma_addr)); + + ring->head = 0; + ring->tail = 0; +} + +void xge_intr_enable(struct xge_pdata *pdata) +{ + u32 data; + + data = RX_PKT_RCVD | TX_PKT_SENT; + xge_wr_csr(pdata, DMAINTRMASK, data); +} + +void xge_intr_disable(struct xge_pdata *pdata) +{ + xge_wr_csr(pdata, DMAINTRMASK, 0); +} diff --git a/drivers/net/ethernet/apm/xgene-v2/ring.h b/drivers/net/ethernet/apm/xgene-v2/ring.h new file mode 100644 index 000000000000..abc8c9a84954 --- /dev/null +++ b/drivers/net/ethernet/apm/xgene-v2/ring.h @@ -0,0 +1,119 @@ +/* + * Applied Micro X-Gene SoC Ethernet v2 Driver + * + * Copyright (c) 2017, Applied Micro Circuits Corporation + * Author(s): Iyappan Subramanian <[email protected]> + * Keyur Chudgar <[email protected]> + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the + * Free Software Foundation; either version 2 of the License, or (at your + * option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +#ifndef __XGENE_ENET_V2_RING_H__ +#define __XGENE_ENET_V2_RING_H__ + +#define XGENE_ENET_DESC_SIZE 64 +#define XGENE_ENET_NUM_DESC 256 +#define NUM_BUFS 8 +#define SLOT_EMPTY 0xfff + +#define DMATXCTRL 0xa180 +#define DMATXDESCL 0xa184 +#define DMATXDESCH 0xa1a0 +#define DMATXSTATUS 0xa188 +#define DMARXCTRL 0xa18c +#define DMARXDESCL 0xa190 +#define DMARXDESCH 0xa1a4 +#define DMARXSTATUS 0xa194 +#define DMAINTRMASK 0xa198 +#define DMAINTERRUPT 0xa19c + +#define D_POS 62 +#define D_LEN 2 +#define E_POS 63 +#define E_LEN 1 +#define PKT_ADDRL_POS 0 +#define PKT_ADDRL_LEN 32 +#define PKT_ADDRH_POS 32 +#define PKT_ADDRH_LEN 10 +#define PKT_SIZE_POS 32 +#define PKT_SIZE_LEN 12 +#define NEXT_DESC_ADDRL_POS 0 +#define NEXT_DESC_ADDRL_LEN 32 +#define NEXT_DESC_ADDRH_POS 48 +#define NEXT_DESC_ADDRH_LEN 10 + +#define TXPKTCOUNT_POS 16 +#define TXPKTCOUNT_LEN 8 +#define RXPKTCOUNT_POS 16 +#define RXPKTCOUNT_LEN 8 + +#define TX_PKT_SENT BIT(0) +#define TX_BUS_ERROR BIT(3) +#define RX_PKT_RCVD BIT(4) +#define RX_BUS_ERROR BIT(7) +#define RXSTATUS_RXPKTRCVD BIT(0) + +struct xge_raw_desc { + __le64 m0; + __le64 m1; + __le64 m2; + __le64 m3; + __le64 m4; + __le64 m5; + __le64 m6; + __le64 m7; +}; + +struct pkt_info { + struct sk_buff *skb; + dma_addr_t dma_addr; + void *pkt_buf; +}; + +/* software context of a descriptor ring */ +struct xge_desc_ring { + struct net_device *ndev; + dma_addr_t dma_addr; + u8 head; + u8 tail; + union { + void *desc_addr; + struct xge_raw_desc *raw_desc; + }; + struct pkt_info (*pkt_info); +}; + +static inline u64 xge_set_desc_bits(int pos, int len, u64 val) +{ + return (val & ((1ULL << len) - 1)) << pos; +} + +static inline u64 xge_get_desc_bits(int pos, int len, u64 src) +{ + return (src >> pos) & ((1ULL << len) - 1); +} + +#define SET_BITS(field, val) \ + xge_set_desc_bits(field ## _POS, field ## _LEN, val) + +#define GET_BITS(field, src) \ + xge_get_desc_bits(field ## _POS, field ## _LEN, src) + +void xge_setup_desc(struct xge_desc_ring *ring); +void xge_update_tx_desc_addr(struct xge_pdata *pdata); +void xge_update_rx_desc_addr(struct xge_pdata *pdata); +void xge_intr_enable(struct xge_pdata *pdata); +void xge_intr_disable(struct xge_pdata *pdata); + +#endif /* __XGENE_ENET_V2_RING_H__ */ diff --git a/drivers/net/ethernet/apm/xgene/xgene_enet_hw.c b/drivers/net/ethernet/apm/xgene/xgene_enet_hw.c index 06e681697c17..2a835e07adfb 100644 --- a/drivers/net/ethernet/apm/xgene/xgene_enet_hw.c +++ b/drivers/net/ethernet/apm/xgene/xgene_enet_hw.c @@ -494,7 +494,7 @@ static void xgene_gmac_set_speed(struct xgene_enet_pdata *pdata) break; } - mc2 |= FULL_DUPLEX2 | PAD_CRC; + mc2 |= FULL_DUPLEX2 | PAD_CRC | LENGTH_CHK; xgene_enet_wr_mcx_mac(pdata, MAC_CONFIG_2_ADDR, mc2); xgene_enet_wr_mcx_mac(pdata, INTERFACE_CONTROL_ADDR, intf_ctl); xgene_enet_wr_csr(pdata, RGMII_REG_0_ADDR, rgmii); @@ -623,6 +623,7 @@ static void xgene_enet_cle_bypass(struct xgene_enet_pdata *pdata, xgene_enet_rd_csr(pdata, CLE_BYPASS_REG0_0_ADDR, &cb); cb |= CFG_CLE_BYPASS_EN0; CFG_CLE_IP_PROTOCOL0_SET(&cb, 3); + CFG_CLE_IP_HDR_LEN_SET(&cb, 0); xgene_enet_wr_csr(pdata, CLE_BYPASS_REG0_0_ADDR, cb); xgene_enet_rd_csr(pdata, CLE_BYPASS_REG1_0_ADDR, &cb); diff --git a/drivers/net/ethernet/apm/xgene/xgene_enet_hw.h b/drivers/net/ethernet/apm/xgene/xgene_enet_hw.h index 5f83037bb96b..d250bfe94d24 100644 --- a/drivers/net/ethernet/apm/xgene/xgene_enet_hw.h +++ b/drivers/net/ethernet/apm/xgene/xgene_enet_hw.h @@ -163,6 +163,7 @@ enum xgene_enet_rm { #define CFG_RXCLK_MUXSEL0_SET(dst, val) xgene_set_bits(dst, val, 26, 3) #define CFG_CLE_IP_PROTOCOL0_SET(dst, val) xgene_set_bits(dst, val, 16, 2) +#define CFG_CLE_IP_HDR_LEN_SET(dst, val) xgene_set_bits(dst, val, 8, 5) #define CFG_CLE_DSTQID0_SET(dst, val) xgene_set_bits(dst, val, 0, 12) #define CFG_CLE_FPSEL0_SET(dst, val) xgene_set_bits(dst, val, 16, 4) #define CFG_CLE_NXTFPSEL0_SET(dst, val) xgene_set_bits(dst, val, 20, 4) @@ -215,6 +216,7 @@ enum xgene_enet_rm { #define ENET_GHD_MODE BIT(26) #define FULL_DUPLEX2 BIT(0) #define PAD_CRC BIT(2) +#define LENGTH_CHK BIT(4) #define SCAN_AUTO_INCR BIT(5) #define TBYT_ADDR 0x38 #define TPKT_ADDR 0x39 diff --git a/drivers/net/ethernet/apm/xgene/xgene_enet_main.c b/drivers/net/ethernet/apm/xgene/xgene_enet_main.c index b3568c453b14..5f37ed3506d5 100644 --- a/drivers/net/ethernet/apm/xgene/xgene_enet_main.c +++ b/drivers/net/ethernet/apm/xgene/xgene_enet_main.c @@ -601,14 +601,24 @@ static netdev_tx_t xgene_enet_start_xmit(struct sk_buff *skb, return NETDEV_TX_OK; } -static void xgene_enet_skip_csum(struct sk_buff *skb) +static void xgene_enet_rx_csum(struct sk_buff *skb) { + struct net_device *ndev = skb->dev; struct iphdr *iph = ip_hdr(skb); - if (!ip_is_fragment(iph) || - (iph->protocol != IPPROTO_TCP && iph->protocol != IPPROTO_UDP)) { - skb->ip_summed = CHECKSUM_UNNECESSARY; - } + if (!(ndev->features & NETIF_F_RXCSUM)) + return; + + if (skb->protocol != htons(ETH_P_IP)) + return; + + if (ip_is_fragment(iph)) + return; + + if (iph->protocol != IPPROTO_TCP && iph->protocol != IPPROTO_UDP) + return; + + skb->ip_summed = CHECKSUM_UNNECESSARY; } static void xgene_enet_free_pagepool(struct xgene_enet_desc_ring *buf_pool, @@ -648,12 +658,24 @@ static void xgene_enet_free_pagepool(struct xgene_enet_desc_ring *buf_pool, buf_pool->head = head; } +/* Errata 10GE_8 and ENET_11 - allow packet with length <=64B */ +static bool xgene_enet_errata_10GE_8(struct sk_buff *skb, u32 len, u8 status) +{ + if (status == INGRESS_PKT_LEN && len == ETHER_MIN_PACKET) { + if (ntohs(eth_hdr(skb)->h_proto) < 46) + return true; + } + + return false; +} + static int xgene_enet_rx_frame(struct xgene_enet_desc_ring *rx_ring, struct xgene_enet_raw_desc *raw_desc, struct xgene_enet_raw_desc *exp_desc) { struct xgene_enet_desc_ring *buf_pool, *page_pool; u32 datalen, frag_size, skb_index; + struct xgene_enet_pdata *pdata; struct net_device *ndev; dma_addr_t dma_addr; struct sk_buff *skb; @@ -666,6 +688,7 @@ static int xgene_enet_rx_frame(struct xgene_enet_desc_ring *rx_ring, bool nv; ndev = rx_ring->ndev; + pdata = netdev_priv(ndev); dev = ndev_to_dev(rx_ring->ndev); buf_pool = rx_ring->buf_pool; page_pool = rx_ring->page_pool; @@ -676,30 +699,29 @@ static int xgene_enet_rx_frame(struct xgene_enet_desc_ring *rx_ring, skb = buf_pool->rx_skb[skb_index]; buf_pool->rx_skb[skb_index] = NULL; + datalen = xgene_enet_get_data_len(le64_to_cpu(raw_desc->m1)); + skb_put(skb, datalen); + prefetch(skb->data - NET_IP_ALIGN); + skb->protocol = eth_type_trans(skb, ndev); + /* checking for error */ - status = (GET_VAL(ELERR, le64_to_cpu(raw_desc->m0)) << LERR_LEN) || + status = (GET_VAL(ELERR, le64_to_cpu(raw_desc->m0)) << LERR_LEN) | GET_VAL(LERR, le64_to_cpu(raw_desc->m0)); - if (unlikely(status > 2)) { - dev_kfree_skb_any(skb); - xgene_enet_free_pagepool(page_pool, raw_desc, exp_desc); - xgene_enet_parse_error(rx_ring, netdev_priv(rx_ring->ndev), - status); - ret = -EIO; - goto out; + if (unlikely(status)) { + if (!xgene_enet_errata_10GE_8(skb, datalen, status)) { + dev_kfree_skb_any(skb); + xgene_enet_free_pagepool(page_pool, raw_desc, exp_desc); + xgene_enet_parse_error(rx_ring, pdata, status); + goto out; + } } - /* strip off CRC as HW isn't doing this */ - datalen = xgene_enet_get_data_len(le64_to_cpu(raw_desc->m1)); - nv = GET_VAL(NV, le64_to_cpu(raw_desc->m0)); - if (!nv) + if (!nv) { + /* strip off CRC as HW isn't doing this */ datalen -= 4; - - skb_put(skb, datalen); - prefetch(skb->data - NET_IP_ALIGN); - - if (!nv) goto skip_jumbo; + } slots = page_pool->slots - 1; head = page_pool->head; @@ -728,11 +750,7 @@ static int xgene_enet_rx_frame(struct xgene_enet_desc_ring *rx_ring, skip_jumbo: skb_checksum_none_assert(skb); - skb->protocol = eth_type_trans(skb, ndev); - if (likely((ndev->features & NETIF_F_IP_CSUM) && - skb->protocol == htons(ETH_P_IP))) { - xgene_enet_skip_csum(skb); - } + xgene_enet_rx_csum(skb); rx_ring->rx_packets++; rx_ring->rx_bytes += datalen; @@ -2039,7 +2057,7 @@ static int xgene_enet_probe(struct platform_device *pdev) xgene_enet_setup_ops(pdata); if (pdata->phy_mode == PHY_INTERFACE_MODE_XGMII) { - ndev->features |= NETIF_F_TSO; + ndev->features |= NETIF_F_TSO | NETIF_F_RXCSUM; spin_lock_init(&pdata->mss_lock); } ndev->hw_features = ndev->features; diff --git a/drivers/net/ethernet/apm/xgene/xgene_enet_main.h b/drivers/net/ethernet/apm/xgene/xgene_enet_main.h index 52571741da9f..0d4be2425ebc 100644 --- a/drivers/net/ethernet/apm/xgene/xgene_enet_main.h +++ b/drivers/net/ethernet/apm/xgene/xgene_enet_main.h @@ -41,6 +41,7 @@ #include "../../../phy/mdio-xgene.h" #define XGENE_DRV_VERSION "v1.0" +#define ETHER_MIN_PACKET 64 #define XGENE_ENET_STD_MTU 1536 #define XGENE_ENET_MAX_MTU 9600 #define SKB_BUFFER_SIZE (XGENE_ENET_STD_MTU - NET_IP_ALIGN) diff --git a/drivers/net/ethernet/apm/xgene/xgene_enet_xgmac.c b/drivers/net/ethernet/apm/xgene/xgene_enet_xgmac.c index ece19e6d68e3..423240c97d39 100644 --- a/drivers/net/ethernet/apm/xgene/xgene_enet_xgmac.c +++ b/drivers/net/ethernet/apm/xgene/xgene_enet_xgmac.c @@ -341,8 +341,15 @@ static void xgene_xgmac_init(struct xgene_enet_pdata *pdata) xgene_enet_rd_csr(pdata, XG_RSIF_CONFIG_REG_ADDR, &data); data |= CFG_RSIF_FPBUFF_TIMEOUT_EN; + /* Errata 10GE_1 - FIFO threshold default value incorrect */ + RSIF_CLE_BUFF_THRESH_SET(&data, XG_RSIF_CLE_BUFF_THRESH); xgene_enet_wr_csr(pdata, XG_RSIF_CONFIG_REG_ADDR, data); + /* Errata 10GE_1 - FIFO threshold default value incorrect */ + xgene_enet_rd_csr(pdata, XG_RSIF_CONFIG1_REG_ADDR, &data); + RSIF_PLC_CLE_BUFF_THRESH_SET(&data, XG_RSIF_PLC_CLE_BUFF_THRESH); + xgene_enet_wr_csr(pdata, XG_RSIF_CONFIG1_REG_ADDR, data); + xgene_enet_rd_csr(pdata, XG_ENET_SPARE_CFG_REG_ADDR, &data); data |= BIT(12); xgene_enet_wr_csr(pdata, XG_ENET_SPARE_CFG_REG_ADDR, data); diff --git a/drivers/net/ethernet/apm/xgene/xgene_enet_xgmac.h b/drivers/net/ethernet/apm/xgene/xgene_enet_xgmac.h index 03b847ad8937..e644a429ebf4 100644 --- a/drivers/net/ethernet/apm/xgene/xgene_enet_xgmac.h +++ b/drivers/net/ethernet/apm/xgene/xgene_enet_xgmac.h @@ -65,6 +65,11 @@ #define XG_DEF_PAUSE_THRES 0x390 #define XG_DEF_PAUSE_OFF_THRES 0x2c0 #define XG_RSIF_CONFIG_REG_ADDR 0x00a0 +#define XG_RSIF_CLE_BUFF_THRESH 0x3 +#define RSIF_CLE_BUFF_THRESH_SET(dst, val) xgene_set_bits(dst, val, 0, 3) +#define XG_RSIF_CONFIG1_REG_ADDR 0x00b8 +#define XG_RSIF_PLC_CLE_BUFF_THRESH 0x1 +#define RSIF_PLC_CLE_BUFF_THRESH_SET(dst, val) xgene_set_bits(dst, val, 0, 2) #define XCLE_BYPASS_REG0_ADDR 0x0160 #define XCLE_BYPASS_REG1_ADDR 0x0164 #define XG_CFG_BYPASS_ADDR 0x0204 diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c b/drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c index 581de71a958a..4c6c882c6a1c 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c +++ b/drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c @@ -213,9 +213,9 @@ void aq_pci_func_free_irqs(struct aq_pci_func_s *self) if (!((1U << i) & self->msix_entry_mask)) continue; - free_irq(pci_irq_vector(pdev, i), self->aq_vec[i]); if (pdev->msix_enabled) irq_set_affinity_hint(pci_irq_vector(pdev, i), NULL); + free_irq(pci_irq_vector(pdev, i), self->aq_vec[i]); self->msix_entry_mask &= ~(1U << i); } } diff --git a/drivers/net/ethernet/broadcom/Kconfig b/drivers/net/ethernet/broadcom/Kconfig index 940fb24bba21..96413808c726 100644 --- a/drivers/net/ethernet/broadcom/Kconfig +++ b/drivers/net/ethernet/broadcom/Kconfig @@ -109,7 +109,6 @@ config TIGON3 tristate "Broadcom Tigon3 support" depends on PCI select PHYLIB - select HWMON imply PTP_1588_CLOCK ---help--- This driver supports Broadcom Tigon3 based gigabit Ethernet cards. @@ -117,6 +116,13 @@ config TIGON3 To compile this driver as a module, choose M here: the module will be called tg3. This is recommended. +config TIGON3_HWMON + bool "Broadcom Tigon3 HWMON support" + default y + depends on TIGON3 && HWMON && !(TIGON3=y && HWMON=m) + ---help--- + Say Y if you want to expose the thermal sensor on Tigon3 devices. + config BNX2X tristate "Broadcom NetXtremeII 10Gb support" depends on PCI diff --git a/drivers/net/ethernet/broadcom/bgmac-bcma.c b/drivers/net/ethernet/broadcom/bgmac-bcma.c index d59cfcc4c4d5..6322594ab260 100644 --- a/drivers/net/ethernet/broadcom/bgmac-bcma.c +++ b/drivers/net/ethernet/broadcom/bgmac-bcma.c @@ -11,6 +11,7 @@ #include <linux/bcma/bcma.h> #include <linux/brcmphy.h> #include <linux/etherdevice.h> +#include <linux/of_net.h> #include "bgmac.h" static inline bool bgmac_is_bcm4707_family(struct bcma_device *core) @@ -114,7 +115,7 @@ static int bgmac_probe(struct bcma_device *core) struct ssb_sprom *sprom = &core->bus->sprom; struct mii_bus *mii_bus; struct bgmac *bgmac; - u8 *mac; + const u8 *mac = NULL; int err; bgmac = bgmac_alloc(&core->dev); @@ -127,21 +128,27 @@ static int bgmac_probe(struct bcma_device *core) bcma_set_drvdata(core, bgmac); - switch (core->core_unit) { - case 0: - mac = sprom->et0mac; - break; - case 1: - mac = sprom->et1mac; - break; - case 2: - mac = sprom->et2mac; - break; - default: - dev_err(bgmac->dev, "Unsupported core_unit %d\n", - core->core_unit); - err = -ENOTSUPP; - goto err; + if (bgmac->dev->of_node) + mac = of_get_mac_address(bgmac->dev->of_node); + + /* If no MAC address assigned via device tree, check SPROM */ + if (!mac) { + switch (core->core_unit) { + case 0: + mac = sprom->et0mac; + break; + case 1: + mac = sprom->et1mac; + break; + case 2: + mac = sprom->et2mac; + break; + default: + dev_err(bgmac->dev, "Unsupported core_unit %d\n", + core->core_unit); + err = -ENOTSUPP; + goto err; + } } ether_addr_copy(bgmac->net_dev->dev_addr, mac); @@ -192,36 +199,50 @@ static int bgmac_probe(struct bcma_device *core) goto err1; } - bgmac->has_robosw = !!(core->bus->sprom.boardflags_lo & - BGMAC_BFL_ENETROBO); + bgmac->has_robosw = !!(sprom->boardflags_lo & BGMAC_BFL_ENETROBO); if (bgmac->has_robosw) dev_warn(bgmac->dev, "Support for Roboswitch not implemented\n"); - if (core->bus->sprom.boardflags_lo & BGMAC_BFL_ENETADM) + if (sprom->boardflags_lo & BGMAC_BFL_ENETADM) dev_warn(bgmac->dev, "Support for ADMtek ethernet switch not implemented\n"); /* Feature Flags */ - switch (core->bus->chipinfo.id) { + switch (ci->id) { + /* BCM 471X/535X family */ + case BCMA_CHIP_ID_BCM4716: + bgmac->feature_flags |= BGMAC_FEAT_CLKCTLST; + /* fallthrough */ + case BCMA_CHIP_ID_BCM47162: + bgmac->feature_flags |= BGMAC_FEAT_FLW_CTRL2; + bgmac->feature_flags |= BGMAC_FEAT_SET_RXQ_CLK; + break; case BCMA_CHIP_ID_BCM5357: + case BCMA_CHIP_ID_BCM53572: bgmac->feature_flags |= BGMAC_FEAT_SET_RXQ_CLK; bgmac->feature_flags |= BGMAC_FEAT_CLKCTLST; bgmac->feature_flags |= BGMAC_FEAT_FLW_CTRL1; bgmac->feature_flags |= BGMAC_FEAT_SW_TYPE_PHY; - if (core->bus->chipinfo.pkg == BCMA_PKG_ID_BCM47186) { - bgmac->feature_flags |= BGMAC_FEAT_IOST_ATTACHED; + if (ci->pkg == BCMA_PKG_ID_BCM47188 || + ci->pkg == BCMA_PKG_ID_BCM47186) { bgmac->feature_flags |= BGMAC_FEAT_SW_TYPE_RGMII; + bgmac->feature_flags |= BGMAC_FEAT_IOST_ATTACHED; } - if (core->bus->chipinfo.pkg == BCMA_PKG_ID_BCM5358) + if (ci->pkg == BCMA_PKG_ID_BCM5358) bgmac->feature_flags |= BGMAC_FEAT_SW_TYPE_EPHYRMII; break; - case BCMA_CHIP_ID_BCM53572: - bgmac->feature_flags |= BGMAC_FEAT_SET_RXQ_CLK; + case BCMA_CHIP_ID_BCM53573: bgmac->feature_flags |= BGMAC_FEAT_CLKCTLST; - bgmac->feature_flags |= BGMAC_FEAT_FLW_CTRL1; - bgmac->feature_flags |= BGMAC_FEAT_SW_TYPE_PHY; - if (core->bus->chipinfo.pkg == BCMA_PKG_ID_BCM47188) { - bgmac->feature_flags |= BGMAC_FEAT_SW_TYPE_RGMII; + bgmac->feature_flags |= BGMAC_FEAT_SET_RXQ_CLK; + if (ci->pkg == BCMA_PKG_ID_BCM47189) bgmac->feature_flags |= BGMAC_FEAT_IOST_ATTACHED; + if (core->core_unit == 0) { + bgmac->feature_flags |= BGMAC_FEAT_CC4_IF_SW_TYPE; + if (ci->pkg == BCMA_PKG_ID_BCM47189) + bgmac->feature_flags |= + BGMAC_FEAT_CC4_IF_SW_TYPE_RGMII; + } else if (core->core_unit == 1) { + bgmac->feature_flags |= BGMAC_FEAT_IRQ_ID_OOB_6; + bgmac->feature_flags |= BGMAC_FEAT_CC7_IF_TYPE_RGMII; } break; case BCMA_CHIP_ID_BCM4749: @@ -229,18 +250,11 @@ static int bgmac_probe(struct bcma_device *core) bgmac->feature_flags |= BGMAC_FEAT_CLKCTLST; bgmac->feature_flags |= BGMAC_FEAT_FLW_CTRL1; bgmac->feature_flags |= BGMAC_FEAT_SW_TYPE_PHY; - if (core->bus->chipinfo.pkg == 10) { + if (ci->pkg == 10) { bgmac->feature_flags |= BGMAC_FEAT_SW_TYPE_RGMII; bgmac->feature_flags |= BGMAC_FEAT_IOST_ATTACHED; } break; - case BCMA_CHIP_ID_BCM4716: - bgmac->feature_flags |= BGMAC_FEAT_CLKCTLST; - /* fallthrough */ - case BCMA_CHIP_ID_BCM47162: - bgmac->feature_flags |= BGMAC_FEAT_FLW_CTRL2; - bgmac->feature_flags |= BGMAC_FEAT_SET_RXQ_CLK; - break; /* bcm4707_family */ case BCMA_CHIP_ID_BCM4707: case BCMA_CHIP_ID_BCM47094: @@ -249,21 +263,6 @@ static int bgmac_probe(struct bcma_device *core) bgmac->feature_flags |= BGMAC_FEAT_NO_RESET; bgmac->feature_flags |= BGMAC_FEAT_FORCE_SPEED_2500; break; - case BCMA_CHIP_ID_BCM53573: - bgmac->feature_flags |= BGMAC_FEAT_CLKCTLST; - bgmac->feature_flags |= BGMAC_FEAT_SET_RXQ_CLK; - if (ci->pkg == BCMA_PKG_ID_BCM47189) - bgmac->feature_flags |= BGMAC_FEAT_IOST_ATTACHED; - if (core->core_unit == 0) { - bgmac->feature_flags |= BGMAC_FEAT_CC4_IF_SW_TYPE; - if (ci->pkg == BCMA_PKG_ID_BCM47189) - bgmac->feature_flags |= - BGMAC_FEAT_CC4_IF_SW_TYPE_RGMII; - } else if (core->core_unit == 1) { - bgmac->feature_flags |= BGMAC_FEAT_IRQ_ID_OOB_6; - bgmac->feature_flags |= BGMAC_FEAT_CC7_IF_TYPE_RGMII; - } - break; default: bgmac->feature_flags |= BGMAC_FEAT_CLKCTLST; bgmac->feature_flags |= BGMAC_FEAT_SET_RXQ_CLK; diff --git a/drivers/net/ethernet/broadcom/bgmac-platform.c b/drivers/net/ethernet/broadcom/bgmac-platform.c index da1b8b225eb9..73aca97a96bc 100644 --- a/drivers/net/ethernet/broadcom/bgmac-platform.c +++ b/drivers/net/ethernet/broadcom/bgmac-platform.c @@ -21,8 +21,12 @@ #include <linux/of_net.h> #include "bgmac.h" +#define NICPM_PADRING_CFG 0x00000004 #define NICPM_IOMUX_CTRL 0x00000008 +#define NICPM_PADRING_CFG_INIT_VAL 0x74000000 +#define NICPM_IOMUX_CTRL_INIT_VAL_AX 0x21880000 + #define NICPM_IOMUX_CTRL_INIT_VAL 0x3196e000 #define NICPM_IOMUX_CTRL_SPD_SHIFT 10 #define NICPM_IOMUX_CTRL_SPD_10M 0 @@ -113,6 +117,10 @@ static void bgmac_nicpm_speed_set(struct net_device *net_dev) if (!bgmac->plat.nicpm_base) return; + /* SET RGMII IO CONFIG */ + writel(NICPM_PADRING_CFG_INIT_VAL, + bgmac->plat.nicpm_base + NICPM_PADRING_CFG); + val = NICPM_IOMUX_CTRL_INIT_VAL; switch (bgmac->net_dev->phydev->speed) { default: @@ -244,6 +252,31 @@ static int bgmac_remove(struct platform_device *pdev) return 0; } +#ifdef CONFIG_PM +static int bgmac_suspend(struct device *dev) +{ + struct bgmac *bgmac = dev_get_drvdata(dev); + + return bgmac_enet_suspend(bgmac); +} + +static int bgmac_resume(struct device *dev) +{ + struct bgmac *bgmac = dev_get_drvdata(dev); + + return bgmac_enet_resume(bgmac); +} + +static const struct dev_pm_ops bgmac_pm_ops = { + .suspend = bgmac_suspend, + .resume = bgmac_resume +}; + +#define BGMAC_PM_OPS (&bgmac_pm_ops) +#else +#define BGMAC_PM_OPS NULL +#endif /* CONFIG_PM */ + static const struct of_device_id bgmac_of_enet_match[] = { {.compatible = "brcm,amac",}, {.compatible = "brcm,nsp-amac",}, @@ -257,6 +290,7 @@ static struct platform_driver bgmac_enet_driver = { .driver = { .name = "bgmac-enet", .of_match_table = bgmac_of_enet_match, + .pm = BGMAC_PM_OPS }, .probe = bgmac_probe, .remove = bgmac_remove, diff --git a/drivers/net/ethernet/broadcom/bgmac.c b/drivers/net/ethernet/broadcom/bgmac.c index fd66fca00e01..e1a24ee6ab8b 100644 --- a/drivers/net/ethernet/broadcom/bgmac.c +++ b/drivers/net/ethernet/broadcom/bgmac.c @@ -1480,6 +1480,7 @@ int bgmac_enet_probe(struct bgmac *bgmac) net_dev->irq = bgmac->irq; SET_NETDEV_DEV(net_dev, bgmac->dev); + dev_set_drvdata(bgmac->dev, bgmac); if (!is_valid_ether_addr(net_dev->dev_addr)) { dev_err(bgmac->dev, "Invalid MAC addr: %pM\n", @@ -1552,5 +1553,55 @@ void bgmac_enet_remove(struct bgmac *bgmac) } EXPORT_SYMBOL_GPL(bgmac_enet_remove); +int bgmac_enet_suspend(struct bgmac *bgmac) +{ + if (!netif_running(bgmac->net_dev)) + return 0; + + phy_stop(bgmac->net_dev->phydev); + + netif_stop_queue(bgmac->net_dev); + + napi_disable(&bgmac->napi); + + netif_tx_lock(bgmac->net_dev); + netif_device_detach(bgmac->net_dev); + netif_tx_unlock(bgmac->net_dev); + + bgmac_chip_intrs_off(bgmac); + bgmac_chip_reset(bgmac); + bgmac_dma_cleanup(bgmac); + + return 0; +} +EXPORT_SYMBOL_GPL(bgmac_enet_suspend); + +int bgmac_enet_resume(struct bgmac *bgmac) +{ + int rc; + + if (!netif_running(bgmac->net_dev)) + return 0; + + rc = bgmac_dma_init(bgmac); + if (rc) + return rc; + + bgmac_chip_init(bgmac); + + napi_enable(&bgmac->napi); + + netif_tx_lock(bgmac->net_dev); + netif_device_attach(bgmac->net_dev); + netif_tx_unlock(bgmac->net_dev); + + netif_start_queue(bgmac->net_dev); + + phy_start(bgmac->net_dev->phydev); + + return 0; +} +EXPORT_SYMBOL_GPL(bgmac_enet_resume); + MODULE_AUTHOR("Rafał Miłecki"); MODULE_LICENSE("GPL"); diff --git a/drivers/net/ethernet/broadcom/bgmac.h b/drivers/net/ethernet/broadcom/bgmac.h index 6d1c6ff1ed96..c1818766c501 100644 --- a/drivers/net/ethernet/broadcom/bgmac.h +++ b/drivers/net/ethernet/broadcom/bgmac.h @@ -402,7 +402,7 @@ #define BGMAC_WEIGHT 64 -#define ETHER_MAX_LEN 1518 +#define ETHER_MAX_LEN (ETH_FRAME_LEN + ETH_FCS_LEN) /* Feature Flags */ #define BGMAC_FEAT_TX_MASK_SETUP BIT(0) @@ -537,6 +537,8 @@ int bgmac_enet_probe(struct bgmac *bgmac); void bgmac_enet_remove(struct bgmac *bgmac); void bgmac_adjust_link(struct net_device *net_dev); int bgmac_phy_connect_direct(struct bgmac *bgmac); +int bgmac_enet_suspend(struct bgmac *bgmac); +int bgmac_enet_resume(struct bgmac *bgmac); struct mii_bus *bcma_mdio_mii_register(struct bgmac *bgmac); void bcma_mdio_mii_unregister(struct mii_bus *mii_bus); diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c index 9e8c06130c09..ad3e0631877e 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c @@ -4277,7 +4277,10 @@ int __bnx2x_setup_tc(struct net_device *dev, u32 handle, __be16 proto, { if (tc->type != TC_SETUP_MQPRIO) return -EINVAL; - return bnx2x_setup_tc(dev, tc->tc); + + tc->mqprio->hw = TC_MQPRIO_HW_OFFLOAD_TCS; + + return bnx2x_setup_tc(dev, tc->mqprio->num_tc); } /* called with rtnl_lock */ diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c index d8d06fdfc42b..ac76fc251d26 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c @@ -13292,17 +13292,15 @@ static int bnx2x_init_dev(struct bnx2x *bp, struct pci_dev *pdev, dev->vlan_features = NETIF_F_SG | NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM | NETIF_F_TSO | NETIF_F_TSO_ECN | NETIF_F_TSO6 | NETIF_F_HIGHDMA; - /* VF with OLD Hypervisor or old PF do not support filtering */ if (IS_PF(bp)) { if (chip_is_e1x) bp->accept_any_vlan = true; else dev->hw_features |= NETIF_F_HW_VLAN_CTAG_FILTER; -#ifdef CONFIG_BNX2X_SRIOV - } else if (bp->acquire_resp.pfdev_info.pf_cap & PFVF_CAP_VLAN_FILTER) { - dev->hw_features |= NETIF_F_HW_VLAN_CTAG_FILTER; -#endif } + /* For VF we'll know whether to enable VLAN filtering after + * getting a response to CHANNEL_TLV_ACQUIRE from PF. + */ dev->features |= dev->hw_features | NETIF_F_HW_VLAN_CTAG_RX; dev->features |= NETIF_F_HIGHDMA; @@ -13738,7 +13736,7 @@ static int bnx2x_ptp_adjfreq(struct ptp_clock_info *ptp, s32 ppb) if (!netif_running(bp->dev)) { DP(BNX2X_MSG_PTP, "PTP adjfreq called while the interface is down\n"); - return -EFAULT; + return -ENETDOWN; } if (ppb < 0) { @@ -13797,6 +13795,12 @@ static int bnx2x_ptp_adjtime(struct ptp_clock_info *ptp, s64 delta) { struct bnx2x *bp = container_of(ptp, struct bnx2x, ptp_clock_info); + if (!netif_running(bp->dev)) { + DP(BNX2X_MSG_PTP, + "PTP adjtime called while the interface is down\n"); + return -ENETDOWN; + } + DP(BNX2X_MSG_PTP, "PTP adjtime called, delta = %llx\n", delta); timecounter_adjtime(&bp->timecounter, delta); @@ -13809,6 +13813,12 @@ static int bnx2x_ptp_gettime(struct ptp_clock_info *ptp, struct timespec64 *ts) struct bnx2x *bp = container_of(ptp, struct bnx2x, ptp_clock_info); u64 ns; + if (!netif_running(bp->dev)) { + DP(BNX2X_MSG_PTP, + "PTP gettime called while the interface is down\n"); + return -ENETDOWN; + } + ns = timecounter_read(&bp->timecounter); DP(BNX2X_MSG_PTP, "PTP gettime called, ns = %llu\n", ns); @@ -13824,6 +13834,12 @@ static int bnx2x_ptp_settime(struct ptp_clock_info *ptp, struct bnx2x *bp = container_of(ptp, struct bnx2x, ptp_clock_info); u64 ns; + if (!netif_running(bp->dev)) { + DP(BNX2X_MSG_PTP, + "PTP settime called while the interface is down\n"); + return -ENETDOWN; + } + ns = timespec64_to_ns(ts); DP(BNX2X_MSG_PTP, "PTP settime called, ns = %llu\n", ns); @@ -13991,6 +14007,14 @@ static int bnx2x_init_one(struct pci_dev *pdev, rc = bnx2x_vfpf_acquire(bp, tx_count, rx_count); if (rc) goto init_one_freemem; + +#ifdef CONFIG_BNX2X_SRIOV + /* VF with OLD Hypervisor or old PF do not support filtering */ + if (bp->acquire_resp.pfdev_info.pf_cap & PFVF_CAP_VLAN_FILTER) { + dev->hw_features |= NETIF_F_HW_VLAN_CTAG_FILTER; + dev->features |= NETIF_F_HW_VLAN_CTAG_FILTER; + } +#endif } /* Enable SRIOV if capability found in configuration space */ diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c index 6fad22adbbb9..bdfd53b46bc5 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c @@ -434,7 +434,9 @@ static int bnx2x_vf_mac_vlan_config(struct bnx2x *bp, /* Add/Remove the filter */ rc = bnx2x_config_vlan_mac(bp, &ramrod); - if (rc && rc != -EEXIST) { + if (rc == -EEXIST) + return 0; + if (rc) { BNX2X_ERR("Failed to %s %s\n", filter->add ? "add" : "delete", (filter->type == BNX2X_VF_FILTER_VLAN_MAC) ? @@ -444,6 +446,8 @@ static int bnx2x_vf_mac_vlan_config(struct bnx2x *bp, return rc; } + filter->applied = true; + return 0; } @@ -469,8 +473,10 @@ int bnx2x_vf_mac_vlan_config_list(struct bnx2x *bp, struct bnx2x_virtf *vf, /* Rollback if needed */ if (i != filters->count) { BNX2X_ERR("Managed only %d/%d filters - rolling back\n", - i, filters->count + 1); + i, filters->count); while (--i >= 0) { + if (!filters->filters[i].applied) + continue; filters->filters[i].add = !filters->filters[i].add; bnx2x_vf_mac_vlan_config(bp, vf, qid, &filters->filters[i], @@ -1899,7 +1905,8 @@ void bnx2x_iov_adjust_stats_req(struct bnx2x *bp) continue; } - DP(BNX2X_MSG_IOV, "add addresses for vf %d\n", vf->abs_vfid); + DP_AND((BNX2X_MSG_IOV | BNX2X_MSG_STATS), + "add addresses for vf %d\n", vf->abs_vfid); for_each_vfq(vf, j) { struct bnx2x_vf_queue *rxq = vfq_get(vf, j); @@ -1920,11 +1927,12 @@ void bnx2x_iov_adjust_stats_req(struct bnx2x *bp) cpu_to_le32(U64_HI(q_stats_addr)); cur_query_entry->address.lo = cpu_to_le32(U64_LO(q_stats_addr)); - DP(BNX2X_MSG_IOV, - "added address %x %x for vf %d queue %d client %d\n", - cur_query_entry->address.hi, - cur_query_entry->address.lo, cur_query_entry->funcID, - j, cur_query_entry->index); + DP_AND((BNX2X_MSG_IOV | BNX2X_MSG_STATS), + "added address %x %x for vf %d queue %d client %d\n", + cur_query_entry->address.hi, + cur_query_entry->address.lo, + cur_query_entry->funcID, + j, cur_query_entry->index); cur_query_entry++; cur_data_offset += sizeof(struct per_queue_stats); stats_count++; diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.h index 7a6d406f4c11..888d0b6632e8 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.h +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.h @@ -114,6 +114,7 @@ struct bnx2x_vf_mac_vlan_filter { (BNX2X_VF_FILTER_MAC | BNX2X_VF_FILTER_VLAN) /*shortcut*/ bool add; + bool applied; u8 *mac; u16 vid; }; diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c index bfae300cf25f..76a4668c50fe 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c @@ -868,7 +868,7 @@ int bnx2x_vfpf_set_mcast(struct net_device *dev) struct bnx2x *bp = netdev_priv(dev); struct vfpf_set_q_filters_tlv *req = &bp->vf2pf_mbox->req.set_q_filters; struct pfvf_general_resp_tlv *resp = &bp->vf2pf_mbox->resp.general_resp; - int rc, i = 0; + int rc = 0, i = 0; struct netdev_hw_addr *ha; if (bp->state != BNX2X_STATE_OPEN) { @@ -883,6 +883,15 @@ int bnx2x_vfpf_set_mcast(struct net_device *dev) /* Get Rx mode requested */ DP(NETIF_MSG_IFUP, "dev->flags = %x\n", dev->flags); + /* We support PFVF_MAX_MULTICAST_PER_VF mcast addresses tops */ + if (netdev_mc_count(dev) > PFVF_MAX_MULTICAST_PER_VF) { + DP(NETIF_MSG_IFUP, + "VF supports not more than %d multicast MAC addresses\n", + PFVF_MAX_MULTICAST_PER_VF); + rc = -EINVAL; + goto out; + } + netdev_for_each_mc_addr(ha, dev) { DP(NETIF_MSG_IFUP, "Adding mcast MAC: %pM\n", bnx2x_mc_addr(ha)); @@ -890,16 +899,6 @@ int bnx2x_vfpf_set_mcast(struct net_device *dev) i++; } - /* We support four PFVF_MAX_MULTICAST_PER_VF mcast - * addresses tops - */ - if (i >= PFVF_MAX_MULTICAST_PER_VF) { - DP(NETIF_MSG_IFUP, - "VF supports not more than %d multicast MAC addresses\n", - PFVF_MAX_MULTICAST_PER_VF); - return -EINVAL; - } - req->n_multicast = i; req->flags |= VFPF_SET_Q_FILTERS_MULTICAST_CHANGED; req->vf_qid = 0; @@ -924,7 +923,7 @@ int bnx2x_vfpf_set_mcast(struct net_device *dev) out: bnx2x_vfpf_finalize(bp, &req->first_tlv); - return 0; + return rc; } /* request pf to add a vlan for the vf */ @@ -1778,6 +1777,23 @@ static int bnx2x_vf_mbx_qfilters(struct bnx2x *bp, struct bnx2x_virtf *vf) goto op_err; } + /* build vlan list */ + fl = NULL; + + rc = bnx2x_vf_mbx_macvlan_list(bp, vf, msg, &fl, + VFPF_VLAN_FILTER); + if (rc) + goto op_err; + + if (fl) { + /* set vlan list */ + rc = bnx2x_vf_mac_vlan_config_list(bp, vf, fl, + msg->vf_qid, + false); + if (rc) + goto op_err; + } + } if (msg->flags & VFPF_SET_Q_FILTERS_RX_MASK_CHANGED) { diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index 235733e91c79..174ec8f84637 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -4465,6 +4465,10 @@ static int bnxt_hwrm_func_qcfg(struct bnxt *bp) vf->vlan = le16_to_cpu(resp->vlan) & VLAN_VID_MASK; } #endif + if (BNXT_PF(bp) && (le16_to_cpu(resp->flags) & + FUNC_QCFG_RESP_FLAGS_FW_DCBX_AGENT_ENABLED)) + bp->flags |= BNXT_FLAG_FW_LLDP_AGENT; + switch (resp->port_partition_type) { case FUNC_QCFG_RESP_PORT_PARTITION_TYPE_NPAR1_0: case FUNC_QCFG_RESP_PORT_PARTITION_TYPE_NPAR1_5: @@ -5507,8 +5511,9 @@ static int bnxt_hwrm_phy_qcaps(struct bnxt *bp) bp->lpi_tmr_hi = le32_to_cpu(resp->valid_tx_lpi_timer_high) & PORT_PHY_QCAPS_RESP_TX_LPI_TIMER_HIGH_MASK; } - link_info->support_auto_speeds = - le16_to_cpu(resp->supported_speeds_auto_mode); + if (resp->supported_speeds_auto_mode) + link_info->support_auto_speeds = + le16_to_cpu(resp->supported_speeds_auto_mode); hwrm_phy_qcaps_exit: mutex_unlock(&bp->hwrm_cmd_lock); @@ -6495,8 +6500,14 @@ static void bnxt_reset_task(struct bnxt *bp, bool silent) if (!silent) bnxt_dbg_dump_states(bp); if (netif_running(bp->dev)) { + int rc; + + if (!silent) + bnxt_ulp_stop(bp); bnxt_close_nic(bp, false, false); - bnxt_open_nic(bp, false, false); + rc = bnxt_open_nic(bp, false, false); + if (!silent && !rc) + bnxt_ulp_start(bp); } } @@ -6894,7 +6905,9 @@ static int bnxt_setup_tc(struct net_device *dev, u32 handle, __be16 proto, if (ntc->type != TC_SETUP_MQPRIO) return -EINVAL; - return bnxt_setup_mq_tc(dev, ntc->tc); + ntc->mqprio->hw = TC_MQPRIO_HW_OFFLOAD_TCS; + + return bnxt_setup_mq_tc(dev, ntc->mqprio->num_tc); } #ifdef CONFIG_RFS_ACCEL @@ -7444,6 +7457,10 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) if (rc) goto init_err_pci_clean; + rc = bnxt_hwrm_func_reset(bp); + if (rc) + goto init_err_pci_clean; + bnxt_hwrm_fw_set_time(bp); dev->hw_features = NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM | NETIF_F_SG | @@ -7554,10 +7571,6 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) if (rc) goto init_err_pci_clean; - rc = bnxt_hwrm_func_reset(bp); - if (rc) - goto init_err_pci_clean; - rc = bnxt_init_int_mode(bp); if (rc) goto init_err_pci_clean; diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h index faf26a2f726b..c7a5b84a5cb2 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h @@ -993,6 +993,7 @@ struct bnxt { BNXT_FLAG_ROCEV2_CAP) #define BNXT_FLAG_NO_AGG_RINGS 0x20000 #define BNXT_FLAG_RX_PAGE_MODE 0x40000 + #define BNXT_FLAG_FW_LLDP_AGENT 0x80000 #define BNXT_FLAG_CHIP_NITRO_A0 0x1000000 #define BNXT_FLAG_ALL_CONFIG_FEATS (BNXT_FLAG_TPA | \ diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.c index fdf2d8caf7bf..03532061d211 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.c @@ -474,7 +474,7 @@ void bnxt_dcb_init(struct bnxt *bp) return; bp->dcbx_cap = DCB_CAP_DCBX_VER_IEEE; - if (BNXT_PF(bp)) + if (BNXT_PF(bp) && !(bp->flags & BNXT_FLAG_FW_LLDP_AGENT)) bp->dcbx_cap |= DCB_CAP_DCBX_HOST; else bp->dcbx_cap |= DCB_CAP_DCBX_LLD_MANAGED; diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c index f92896835d2a..44f9c0a1f85d 100644 --- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c +++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c @@ -1,7 +1,7 @@ /* * Broadcom GENET (Gigabit Ethernet) controller driver * - * Copyright (c) 2014 Broadcom Corporation + * Copyright (c) 2014-2017 Broadcom * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License version 2 as @@ -450,6 +450,22 @@ static inline void bcmgenet_rdma_ring_writel(struct bcmgenet_priv *priv, genet_dma_ring_regs[r]); } +static int bcmgenet_begin(struct net_device *dev) +{ + struct bcmgenet_priv *priv = netdev_priv(dev); + + /* Turn on the clock */ + return clk_prepare_enable(priv->clk); +} + +static void bcmgenet_complete(struct net_device *dev) +{ + struct bcmgenet_priv *priv = netdev_priv(dev); + + /* Turn off the clock */ + clk_disable_unprepare(priv->clk); +} + static int bcmgenet_get_link_ksettings(struct net_device *dev, struct ethtool_link_ksettings *cmd) { @@ -605,7 +621,7 @@ static int bcmgenet_set_coalesce(struct net_device *dev, /* GENET TDMA hardware does not support a configurable timeout, but will * always generate an interrupt either after MBDONE packets have been - * transmitted, or when the ring is emtpy. + * transmitted, or when the ring is empty. */ if (ec->tx_coalesce_usecs || ec->tx_coalesce_usecs_high || ec->tx_coalesce_usecs_irq || ec->tx_coalesce_usecs_low) @@ -778,8 +794,9 @@ static const struct bcmgenet_stats bcmgenet_gstrings_stats[] = { STAT_GENET_RUNT("rx_runt_bytes", mib.rx_runt_bytes), /* Misc UniMAC counters */ STAT_GENET_MISC("rbuf_ovflow_cnt", mib.rbuf_ovflow_cnt, - UMAC_RBUF_OVFL_CNT), - STAT_GENET_MISC("rbuf_err_cnt", mib.rbuf_err_cnt, UMAC_RBUF_ERR_CNT), + UMAC_RBUF_OVFL_CNT_V1), + STAT_GENET_MISC("rbuf_err_cnt", mib.rbuf_err_cnt, + UMAC_RBUF_ERR_CNT_V1), STAT_GENET_MISC("mdf_err_cnt", mib.mdf_err_cnt, UMAC_MDF_ERR_CNT), STAT_GENET_SOFT_MIB("alloc_rx_buff_failed", mib.alloc_rx_buff_failed), STAT_GENET_SOFT_MIB("rx_dma_failed", mib.rx_dma_failed), @@ -821,6 +838,45 @@ static void bcmgenet_get_strings(struct net_device *dev, u32 stringset, } } +static u32 bcmgenet_update_stat_misc(struct bcmgenet_priv *priv, u16 offset) +{ + u16 new_offset; + u32 val; + + switch (offset) { + case UMAC_RBUF_OVFL_CNT_V1: + if (GENET_IS_V2(priv)) + new_offset = RBUF_OVFL_CNT_V2; + else + new_offset = RBUF_OVFL_CNT_V3PLUS; + + val = bcmgenet_rbuf_readl(priv, new_offset); + /* clear if overflowed */ + if (val == ~0) + bcmgenet_rbuf_writel(priv, 0, new_offset); + break; + case UMAC_RBUF_ERR_CNT_V1: + if (GENET_IS_V2(priv)) + new_offset = RBUF_ERR_CNT_V2; + else + new_offset = RBUF_ERR_CNT_V3PLUS; + + val = bcmgenet_rbuf_readl(priv, new_offset); + /* clear if overflowed */ + if (val == ~0) + bcmgenet_rbuf_writel(priv, 0, new_offset); + break; + default: + val = bcmgenet_umac_readl(priv, offset); + /* clear if overflowed */ + if (val == ~0) + bcmgenet_umac_writel(priv, 0, offset); + break; + } + + return val; +} + static void bcmgenet_update_mib_counters(struct bcmgenet_priv *priv) { int i, j = 0; @@ -836,19 +892,28 @@ static void bcmgenet_update_mib_counters(struct bcmgenet_priv *priv) case BCMGENET_STAT_NETDEV: case BCMGENET_STAT_SOFT: continue; - case BCMGENET_STAT_MIB_RX: - case BCMGENET_STAT_MIB_TX: case BCMGENET_STAT_RUNT: - if (s->type != BCMGENET_STAT_MIB_RX) - offset = BCMGENET_STAT_OFFSET; + offset += BCMGENET_STAT_OFFSET; + /* fall through */ + case BCMGENET_STAT_MIB_TX: + offset += BCMGENET_STAT_OFFSET; + /* fall through */ + case BCMGENET_STAT_MIB_RX: val = bcmgenet_umac_readl(priv, UMAC_MIB_START + j + offset); + offset = 0; /* Reset Offset */ break; case BCMGENET_STAT_MISC: - val = bcmgenet_umac_readl(priv, s->reg_offset); - /* clear if overflowed */ - if (val == ~0) - bcmgenet_umac_writel(priv, 0, s->reg_offset); + if (GENET_IS_V1(priv)) { + val = bcmgenet_umac_readl(priv, s->reg_offset); + /* clear if overflowed */ + if (val == ~0) + bcmgenet_umac_writel(priv, 0, + s->reg_offset); + } else { + val = bcmgenet_update_stat_misc(priv, + s->reg_offset); + } break; } @@ -973,6 +1038,8 @@ static int bcmgenet_set_eee(struct net_device *dev, struct ethtool_eee *e) /* standard ethtool support functions. */ static const struct ethtool_ops bcmgenet_ethtool_ops = { + .begin = bcmgenet_begin, + .complete = bcmgenet_complete, .get_strings = bcmgenet_get_strings, .get_sset_count = bcmgenet_get_sset_count, .get_ethtool_stats = bcmgenet_get_ethtool_stats, @@ -1011,8 +1078,17 @@ static int bcmgenet_power_down(struct bcmgenet_priv *priv, /* Power down LED */ if (priv->hw_params->flags & GENET_HAS_EXT) { reg = bcmgenet_ext_readl(priv, EXT_EXT_PWR_MGMT); - reg |= (EXT_PWR_DOWN_PHY | - EXT_PWR_DOWN_DLL | EXT_PWR_DOWN_BIAS); + if (GENET_IS_V5(priv)) + reg |= EXT_PWR_DOWN_PHY_EN | + EXT_PWR_DOWN_PHY_RD | + EXT_PWR_DOWN_PHY_SD | + EXT_PWR_DOWN_PHY_RX | + EXT_PWR_DOWN_PHY_TX | + EXT_IDDQ_GLBL_PWR; + else + reg |= EXT_PWR_DOWN_PHY; + + reg |= (EXT_PWR_DOWN_DLL | EXT_PWR_DOWN_BIAS); bcmgenet_ext_writel(priv, reg, EXT_EXT_PWR_MGMT); bcmgenet_phy_power_set(priv->dev, false); @@ -1037,12 +1113,34 @@ static void bcmgenet_power_up(struct bcmgenet_priv *priv, switch (mode) { case GENET_POWER_PASSIVE: - reg &= ~(EXT_PWR_DOWN_DLL | EXT_PWR_DOWN_PHY | - EXT_PWR_DOWN_BIAS); - /* fallthrough */ + reg &= ~(EXT_PWR_DOWN_DLL | EXT_PWR_DOWN_BIAS); + if (GENET_IS_V5(priv)) { + reg &= ~(EXT_PWR_DOWN_PHY_EN | + EXT_PWR_DOWN_PHY_RD | + EXT_PWR_DOWN_PHY_SD | + EXT_PWR_DOWN_PHY_RX | + EXT_PWR_DOWN_PHY_TX | + EXT_IDDQ_GLBL_PWR); + reg |= EXT_PHY_RESET; + bcmgenet_ext_writel(priv, reg, EXT_EXT_PWR_MGMT); + mdelay(1); + + reg &= ~EXT_PHY_RESET; + } else { + reg &= ~EXT_PWR_DOWN_PHY; + reg |= EXT_PWR_DN_EN_LD; + } + bcmgenet_ext_writel(priv, reg, EXT_EXT_PWR_MGMT); + bcmgenet_phy_power_set(priv->dev, true); + bcmgenet_mii_reset(priv->dev); + break; + case GENET_POWER_CABLE_SENSE: /* enable APD */ - reg |= EXT_PWR_DN_EN_LD; + if (!GENET_IS_V5(priv)) { + reg |= EXT_PWR_DN_EN_LD; + bcmgenet_ext_writel(priv, reg, EXT_EXT_PWR_MGMT); + } break; case GENET_POWER_WOL_MAGIC: bcmgenet_wol_power_up_cfg(priv, mode); @@ -1050,39 +1148,20 @@ static void bcmgenet_power_up(struct bcmgenet_priv *priv, default: break; } - - bcmgenet_ext_writel(priv, reg, EXT_EXT_PWR_MGMT); - if (mode == GENET_POWER_PASSIVE) { - bcmgenet_phy_power_set(priv->dev, true); - bcmgenet_mii_reset(priv->dev); - } } /* ioctl handle special commands that are not present in ethtool. */ static int bcmgenet_ioctl(struct net_device *dev, struct ifreq *rq, int cmd) { struct bcmgenet_priv *priv = netdev_priv(dev); - int val = 0; if (!netif_running(dev)) return -EINVAL; - switch (cmd) { - case SIOCGMIIPHY: - case SIOCGMIIREG: - case SIOCSMIIREG: - if (!priv->phydev) - val = -ENODEV; - else - val = phy_mii_ioctl(priv->phydev, rq, cmd); - break; - - default: - val = -EINVAL; - break; - } + if (!priv->phydev) + return -ENODEV; - return val; + return phy_mii_ioctl(priv->phydev, rq, cmd); } static struct enet_cb *bcmgenet_get_txcb(struct bcmgenet_priv *priv, @@ -1167,21 +1246,24 @@ static unsigned int __bcmgenet_tx_reclaim(struct net_device *dev, struct bcmgenet_priv *priv = netdev_priv(dev); struct device *kdev = &priv->pdev->dev; struct enet_cb *tx_cb_ptr; - struct netdev_queue *txq; unsigned int pkts_compl = 0; unsigned int bytes_compl = 0; unsigned int c_index; unsigned int txbds_ready; unsigned int txbds_processed = 0; - /* Compute how many buffers are transmitted since last xmit call */ - c_index = bcmgenet_tdma_ring_readl(priv, ring->index, TDMA_CONS_INDEX); - c_index &= DMA_C_INDEX_MASK; - - if (likely(c_index >= ring->c_index)) - txbds_ready = c_index - ring->c_index; + /* Clear status before servicing to reduce spurious interrupts */ + if (ring->index == DESC_INDEX) + bcmgenet_intrl2_0_writel(priv, UMAC_IRQ_TXDMA_DONE, + INTRL2_CPU_CLEAR); else - txbds_ready = (DMA_C_INDEX_MASK + 1) - ring->c_index + c_index; + bcmgenet_intrl2_1_writel(priv, (1 << ring->index), + INTRL2_CPU_CLEAR); + + /* Compute how many buffers are transmitted since last xmit call */ + c_index = bcmgenet_tdma_ring_readl(priv, ring->index, TDMA_CONS_INDEX) + & DMA_C_INDEX_MASK; + txbds_ready = (c_index - ring->c_index) & DMA_C_INDEX_MASK; netif_dbg(priv, tx_done, dev, "%s ring=%d old_c_index=%u c_index=%u txbds_ready=%u\n", @@ -1214,20 +1296,15 @@ static unsigned int __bcmgenet_tx_reclaim(struct net_device *dev, } ring->free_bds += txbds_processed; - ring->c_index = (ring->c_index + txbds_processed) & DMA_C_INDEX_MASK; + ring->c_index = c_index; dev->stats.tx_packets += pkts_compl; dev->stats.tx_bytes += bytes_compl; - txq = netdev_get_tx_queue(dev, ring->queue); - netdev_tx_completed_queue(txq, pkts_compl, bytes_compl); + netdev_tx_completed_queue(netdev_get_tx_queue(dev, ring->queue), + pkts_compl, bytes_compl); - if (ring->free_bds > (MAX_SKB_FRAGS + 1)) { - if (netif_tx_queue_stopped(txq)) - netif_tx_wake_queue(txq); - } - - return pkts_compl; + return txbds_processed; } static unsigned int bcmgenet_tx_reclaim(struct net_device *dev, @@ -1248,8 +1325,16 @@ static int bcmgenet_tx_poll(struct napi_struct *napi, int budget) struct bcmgenet_tx_ring *ring = container_of(napi, struct bcmgenet_tx_ring, napi); unsigned int work_done = 0; + struct netdev_queue *txq; + unsigned long flags; - work_done = bcmgenet_tx_reclaim(ring->priv->dev, ring); + spin_lock_irqsave(&ring->lock, flags); + work_done = __bcmgenet_tx_reclaim(ring->priv->dev, ring); + if (ring->free_bds > (MAX_SKB_FRAGS + 1)) { + txq = netdev_get_tx_queue(ring->priv->dev, ring->queue); + netif_tx_wake_queue(txq); + } + spin_unlock_irqrestore(&ring->lock, flags); if (work_done == 0) { napi_complete(napi); @@ -1588,10 +1673,21 @@ static unsigned int bcmgenet_desc_rx(struct bcmgenet_rx_ring *ring, unsigned long dma_flag; int len; unsigned int rxpktprocessed = 0, rxpkttoprocess; - unsigned int p_index; + unsigned int p_index, mask; unsigned int discards; unsigned int chksum_ok = 0; + /* Clear status before servicing to reduce spurious interrupts */ + if (ring->index == DESC_INDEX) { + bcmgenet_intrl2_0_writel(priv, UMAC_IRQ_RXDMA_DONE, + INTRL2_CPU_CLEAR); + } else { + mask = 1 << (UMAC_IRQ1_RX_INTR_SHIFT + ring->index); + bcmgenet_intrl2_1_writel(priv, + mask, + INTRL2_CPU_CLEAR); + } + p_index = bcmgenet_rdma_ring_readl(priv, ring->index, RDMA_PROD_INDEX); discards = (p_index >> DMA_P_INDEX_DISCARD_CNT_SHIFT) & @@ -1611,12 +1707,7 @@ static unsigned int bcmgenet_desc_rx(struct bcmgenet_rx_ring *ring, } p_index &= DMA_P_INDEX_MASK; - - if (likely(p_index >= ring->c_index)) - rxpkttoprocess = p_index - ring->c_index; - else - rxpkttoprocess = (DMA_C_INDEX_MASK + 1) - ring->c_index + - p_index; + rxpkttoprocess = (p_index - ring->c_index) & DMA_C_INDEX_MASK; netif_dbg(priv, rx_status, dev, "RDMA: rxpkttoprocess=%d\n", rxpkttoprocess); @@ -1843,10 +1934,8 @@ static void bcmgenet_intr_disable(struct bcmgenet_priv *priv) /* Mask all interrupts.*/ bcmgenet_intrl2_0_writel(priv, 0xFFFFFFFF, INTRL2_CPU_MASK_SET); bcmgenet_intrl2_0_writel(priv, 0xFFFFFFFF, INTRL2_CPU_CLEAR); - bcmgenet_intrl2_0_writel(priv, 0, INTRL2_CPU_MASK_CLEAR); bcmgenet_intrl2_1_writel(priv, 0xFFFFFFFF, INTRL2_CPU_MASK_SET); bcmgenet_intrl2_1_writel(priv, 0xFFFFFFFF, INTRL2_CPU_CLEAR); - bcmgenet_intrl2_1_writel(priv, 0, INTRL2_CPU_MASK_CLEAR); } static void bcmgenet_link_intr_enable(struct bcmgenet_priv *priv) @@ -1873,8 +1962,6 @@ static int init_umac(struct bcmgenet_priv *priv) int ret; u32 reg; u32 int0_enable = 0; - u32 int1_enable = 0; - int i; dev_dbg(&priv->pdev->dev, "bcmgenet: init_umac\n"); @@ -1901,12 +1988,6 @@ static int init_umac(struct bcmgenet_priv *priv) bcmgenet_intr_disable(priv); - /* Enable Rx default queue 16 interrupts */ - int0_enable |= UMAC_IRQ_RXDMA_DONE; - - /* Enable Tx default queue 16 interrupts */ - int0_enable |= UMAC_IRQ_TXDMA_DONE; - /* Configure backpressure vectors for MoCA */ if (priv->phy_interface == PHY_INTERFACE_MODE_MOCA) { reg = bcmgenet_bp_mc_get(priv); @@ -1924,18 +2005,8 @@ static int init_umac(struct bcmgenet_priv *priv) if (priv->hw_params->flags & GENET_HAS_MDIO_INTR) int0_enable |= (UMAC_IRQ_MDIO_DONE | UMAC_IRQ_MDIO_ERROR); - /* Enable Rx priority queue interrupts */ - for (i = 0; i < priv->hw_params->rx_queues; ++i) - int1_enable |= (1 << (UMAC_IRQ1_RX_INTR_SHIFT + i)); - - /* Enable Tx priority queue interrupts */ - for (i = 0; i < priv->hw_params->tx_queues; ++i) - int1_enable |= (1 << i); - bcmgenet_intrl2_0_writel(priv, int0_enable, INTRL2_CPU_MASK_CLEAR); - bcmgenet_intrl2_1_writel(priv, int1_enable, INTRL2_CPU_MASK_CLEAR); - /* Enable rx/tx engine.*/ dev_dbg(kdev, "done init umac\n"); return 0; @@ -2067,22 +2138,33 @@ static void bcmgenet_init_tx_napi(struct bcmgenet_priv *priv) static void bcmgenet_enable_tx_napi(struct bcmgenet_priv *priv) { unsigned int i; + u32 int0_enable = UMAC_IRQ_TXDMA_DONE; + u32 int1_enable = 0; struct bcmgenet_tx_ring *ring; for (i = 0; i < priv->hw_params->tx_queues; ++i) { ring = &priv->tx_rings[i]; napi_enable(&ring->napi); + int1_enable |= (1 << i); } ring = &priv->tx_rings[DESC_INDEX]; napi_enable(&ring->napi); + + bcmgenet_intrl2_0_writel(priv, int0_enable, INTRL2_CPU_MASK_CLEAR); + bcmgenet_intrl2_1_writel(priv, int1_enable, INTRL2_CPU_MASK_CLEAR); } static void bcmgenet_disable_tx_napi(struct bcmgenet_priv *priv) { unsigned int i; + u32 int0_disable = UMAC_IRQ_TXDMA_DONE; + u32 int1_disable = 0xffff; struct bcmgenet_tx_ring *ring; + bcmgenet_intrl2_0_writel(priv, int0_disable, INTRL2_CPU_MASK_SET); + bcmgenet_intrl2_1_writel(priv, int1_disable, INTRL2_CPU_MASK_SET); + for (i = 0; i < priv->hw_params->tx_queues; ++i) { ring = &priv->tx_rings[i]; napi_disable(&ring->napi); @@ -2195,22 +2277,33 @@ static void bcmgenet_init_rx_napi(struct bcmgenet_priv *priv) static void bcmgenet_enable_rx_napi(struct bcmgenet_priv *priv) { unsigned int i; + u32 int0_enable = UMAC_IRQ_RXDMA_DONE; + u32 int1_enable = 0; struct bcmgenet_rx_ring *ring; for (i = 0; i < priv->hw_params->rx_queues; ++i) { ring = &priv->rx_rings[i]; napi_enable(&ring->napi); + int1_enable |= (1 << (UMAC_IRQ1_RX_INTR_SHIFT + i)); } ring = &priv->rx_rings[DESC_INDEX]; napi_enable(&ring->napi); + + bcmgenet_intrl2_0_writel(priv, int0_enable, INTRL2_CPU_MASK_CLEAR); + bcmgenet_intrl2_1_writel(priv, int1_enable, INTRL2_CPU_MASK_CLEAR); } static void bcmgenet_disable_rx_napi(struct bcmgenet_priv *priv) { unsigned int i; + u32 int0_disable = UMAC_IRQ_RXDMA_DONE; + u32 int1_disable = 0xffff << UMAC_IRQ1_RX_INTR_SHIFT; struct bcmgenet_rx_ring *ring; + bcmgenet_intrl2_0_writel(priv, int0_disable, INTRL2_CPU_MASK_SET); + bcmgenet_intrl2_1_writel(priv, int1_disable, INTRL2_CPU_MASK_SET); + for (i = 0; i < priv->hw_params->rx_queues; ++i) { ring = &priv->rx_rings[i]; napi_disable(&ring->napi); @@ -2457,24 +2550,28 @@ static int bcmgenet_init_dma(struct bcmgenet_priv *priv) /* Interrupt bottom half */ static void bcmgenet_irq_task(struct work_struct *work) { + unsigned long flags; + unsigned int status; struct bcmgenet_priv *priv = container_of( work, struct bcmgenet_priv, bcmgenet_irq_work); netif_dbg(priv, intr, priv->dev, "%s\n", __func__); - if (priv->irq0_stat & UMAC_IRQ_MPD_R) { - priv->irq0_stat &= ~UMAC_IRQ_MPD_R; + spin_lock_irqsave(&priv->lock, flags); + status = priv->irq0_stat; + priv->irq0_stat = 0; + spin_unlock_irqrestore(&priv->lock, flags); + + if (status & UMAC_IRQ_MPD_R) { netif_dbg(priv, wol, priv->dev, "magic packet detected, waking up\n"); bcmgenet_power_up(priv, GENET_POWER_WOL_MAGIC); } /* Link UP/DOWN event */ - if (priv->irq0_stat & UMAC_IRQ_LINK_EVENT) { + if (status & UMAC_IRQ_LINK_EVENT) phy_mac_interrupt(priv->phydev, - !!(priv->irq0_stat & UMAC_IRQ_LINK_UP)); - priv->irq0_stat &= ~UMAC_IRQ_LINK_EVENT; - } + !!(status & UMAC_IRQ_LINK_UP)); } /* bcmgenet_isr1: handle Rx and Tx priority queues */ @@ -2483,22 +2580,21 @@ static irqreturn_t bcmgenet_isr1(int irq, void *dev_id) struct bcmgenet_priv *priv = dev_id; struct bcmgenet_rx_ring *rx_ring; struct bcmgenet_tx_ring *tx_ring; - unsigned int index; + unsigned int index, status; - /* Save irq status for bottom-half processing. */ - priv->irq1_stat = - bcmgenet_intrl2_1_readl(priv, INTRL2_CPU_STAT) & + /* Read irq status */ + status = bcmgenet_intrl2_1_readl(priv, INTRL2_CPU_STAT) & ~bcmgenet_intrl2_1_readl(priv, INTRL2_CPU_MASK_STATUS); /* clear interrupts */ - bcmgenet_intrl2_1_writel(priv, priv->irq1_stat, INTRL2_CPU_CLEAR); + bcmgenet_intrl2_1_writel(priv, status, INTRL2_CPU_CLEAR); netif_dbg(priv, intr, priv->dev, - "%s: IRQ=0x%x\n", __func__, priv->irq1_stat); + "%s: IRQ=0x%x\n", __func__, status); /* Check Rx priority queue interrupts */ for (index = 0; index < priv->hw_params->rx_queues; index++) { - if (!(priv->irq1_stat & BIT(UMAC_IRQ1_RX_INTR_SHIFT + index))) + if (!(status & BIT(UMAC_IRQ1_RX_INTR_SHIFT + index))) continue; rx_ring = &priv->rx_rings[index]; @@ -2511,7 +2607,7 @@ static irqreturn_t bcmgenet_isr1(int irq, void *dev_id) /* Check Tx priority queue interrupts */ for (index = 0; index < priv->hw_params->tx_queues; index++) { - if (!(priv->irq1_stat & BIT(index))) + if (!(status & BIT(index))) continue; tx_ring = &priv->tx_rings[index]; @@ -2531,19 +2627,20 @@ static irqreturn_t bcmgenet_isr0(int irq, void *dev_id) struct bcmgenet_priv *priv = dev_id; struct bcmgenet_rx_ring *rx_ring; struct bcmgenet_tx_ring *tx_ring; + unsigned int status; + unsigned long flags; - /* Save irq status for bottom-half processing. */ - priv->irq0_stat = - bcmgenet_intrl2_0_readl(priv, INTRL2_CPU_STAT) & + /* Read irq status */ + status = bcmgenet_intrl2_0_readl(priv, INTRL2_CPU_STAT) & ~bcmgenet_intrl2_0_readl(priv, INTRL2_CPU_MASK_STATUS); /* clear interrupts */ - bcmgenet_intrl2_0_writel(priv, priv->irq0_stat, INTRL2_CPU_CLEAR); + bcmgenet_intrl2_0_writel(priv, status, INTRL2_CPU_CLEAR); netif_dbg(priv, intr, priv->dev, - "IRQ=0x%x\n", priv->irq0_stat); + "IRQ=0x%x\n", status); - if (priv->irq0_stat & UMAC_IRQ_RXDMA_DONE) { + if (status & UMAC_IRQ_RXDMA_DONE) { rx_ring = &priv->rx_rings[DESC_INDEX]; if (likely(napi_schedule_prep(&rx_ring->napi))) { @@ -2552,7 +2649,7 @@ static irqreturn_t bcmgenet_isr0(int irq, void *dev_id) } } - if (priv->irq0_stat & UMAC_IRQ_TXDMA_DONE) { + if (status & UMAC_IRQ_TXDMA_DONE) { tx_ring = &priv->tx_rings[DESC_INDEX]; if (likely(napi_schedule_prep(&tx_ring->napi))) { @@ -2565,18 +2662,28 @@ static irqreturn_t bcmgenet_isr0(int irq, void *dev_id) UMAC_IRQ_PHY_DET_F | UMAC_IRQ_LINK_EVENT | UMAC_IRQ_HFB_SM | - UMAC_IRQ_HFB_MM | - UMAC_IRQ_MPD_R)) { + UMAC_IRQ_HFB_MM)) { /* all other interested interrupts handled in bottom half */ schedule_work(&priv->bcmgenet_irq_work); } if ((priv->hw_params->flags & GENET_HAS_MDIO_INTR) && - priv->irq0_stat & (UMAC_IRQ_MDIO_DONE | UMAC_IRQ_MDIO_ERROR)) { - priv->irq0_stat &= ~(UMAC_IRQ_MDIO_DONE | UMAC_IRQ_MDIO_ERROR); + status & (UMAC_IRQ_MDIO_DONE | UMAC_IRQ_MDIO_ERROR)) { wake_up(&priv->wq); } + /* all other interested interrupts handled in bottom half */ + status &= (UMAC_IRQ_LINK_EVENT | + UMAC_IRQ_MPD_R); + if (status) { + /* Save irq status for bottom-half processing. */ + spin_lock_irqsave(&priv->lock, flags); + priv->irq0_stat |= status; + spin_unlock_irqrestore(&priv->lock, flags); + + schedule_work(&priv->bcmgenet_irq_work); + } + return IRQ_HANDLED; } @@ -2801,6 +2908,8 @@ err_irq0: err_fini_dma: bcmgenet_fini_dma(priv); err_clk_disable: + if (priv->internal_phy) + bcmgenet_power_down(priv, GENET_POWER_PASSIVE); clk_disable_unprepare(priv->clk); return ret; } @@ -2845,7 +2954,7 @@ static int bcmgenet_close(struct net_device *dev) if (ret) return ret; - /* Disable MAC transmit. TX DMA disabled have to done before this */ + /* Disable MAC transmit. TX DMA disabled must be done before this */ umac_enable_set(priv, CMD_TX_EN, false); /* tx reclaim */ @@ -3110,6 +3219,25 @@ static struct bcmgenet_hw_params bcmgenet_hw_params[] = { .flags = GENET_HAS_40BITS | GENET_HAS_EXT | GENET_HAS_MDIO_INTR | GENET_HAS_MOCA_LINK_DET, }, + [GENET_V5] = { + .tx_queues = 4, + .tx_bds_per_q = 32, + .rx_queues = 0, + .rx_bds_per_q = 0, + .bp_in_en_shift = 17, + .bp_in_mask = 0x1ffff, + .hfb_filter_cnt = 48, + .hfb_filter_size = 128, + .qtag_mask = 0x3F, + .tbuf_offset = 0x0600, + .hfb_offset = 0x8000, + .hfb_reg_offset = 0xfc00, + .rdma_offset = 0x2000, + .tdma_offset = 0x4000, + .words_per_bd = 3, + .flags = GENET_HAS_40BITS | GENET_HAS_EXT | + GENET_HAS_MDIO_INTR | GENET_HAS_MOCA_LINK_DET, + }, }; /* Infer hardware parameters from the detected GENET version */ @@ -3120,26 +3248,22 @@ static void bcmgenet_set_hw_params(struct bcmgenet_priv *priv) u8 major; u16 gphy_rev; - if (GENET_IS_V4(priv)) { + if (GENET_IS_V5(priv) || GENET_IS_V4(priv)) { bcmgenet_dma_regs = bcmgenet_dma_regs_v3plus; genet_dma_ring_regs = genet_dma_ring_regs_v4; priv->dma_rx_chk_bit = DMA_RX_CHK_V3PLUS; - priv->version = GENET_V4; } else if (GENET_IS_V3(priv)) { bcmgenet_dma_regs = bcmgenet_dma_regs_v3plus; genet_dma_ring_regs = genet_dma_ring_regs_v123; priv->dma_rx_chk_bit = DMA_RX_CHK_V3PLUS; - priv->version = GENET_V3; } else if (GENET_IS_V2(priv)) { bcmgenet_dma_regs = bcmgenet_dma_regs_v2; genet_dma_ring_regs = genet_dma_ring_regs_v123; priv->dma_rx_chk_bit = DMA_RX_CHK_V12; - priv->version = GENET_V2; } else if (GENET_IS_V1(priv)) { bcmgenet_dma_regs = bcmgenet_dma_regs_v1; genet_dma_ring_regs = genet_dma_ring_regs_v123; priv->dma_rx_chk_bit = DMA_RX_CHK_V12; - priv->version = GENET_V1; } /* enum genet_version starts at 1 */ @@ -3149,7 +3273,9 @@ static void bcmgenet_set_hw_params(struct bcmgenet_priv *priv) /* Read GENET HW version */ reg = bcmgenet_sys_readl(priv, SYS_REV_CTRL); major = (reg >> 24 & 0x0f); - if (major == 5) + if (major == 6) + major = 5; + else if (major == 5) major = 4; else if (major == 0) major = 1; @@ -3177,18 +3303,24 @@ static void bcmgenet_set_hw_params(struct bcmgenet_priv *priv) */ gphy_rev = reg & 0xffff; + if (GENET_IS_V5(priv)) { + /* The EPHY revision should come from the MDIO registers of + * the PHY not from GENET. + */ + if (gphy_rev != 0) { + pr_warn("GENET is reporting EPHY revision: 0x%04x\n", + gphy_rev); + } + /* This is reserved so should require special treatment */ + } else if (gphy_rev == 0 || gphy_rev == 0x01ff) { + pr_warn("Invalid GPHY revision detected: 0x%04x\n", gphy_rev); + return; /* This is the good old scheme, just GPHY major, no minor nor patch */ - if ((gphy_rev & 0xf0) != 0) + } else if ((gphy_rev & 0xf0) != 0) { priv->gphy_rev = gphy_rev << 8; - /* This is the new scheme, GPHY major rolls over with 0x10 = rev G0 */ - else if ((gphy_rev & 0xff00) != 0) + } else if ((gphy_rev & 0xff00) != 0) { priv->gphy_rev = gphy_rev; - - /* This is reserved so should require special treatment */ - else if (gphy_rev == 0 || gphy_rev == 0x01ff) { - pr_warn("Invalid GPHY revision detected: 0x%04x\n", gphy_rev); - return; } #ifdef CONFIG_PHYS_ADDR_T_64BIT @@ -3219,6 +3351,7 @@ static const struct of_device_id bcmgenet_match[] = { { .compatible = "brcm,genet-v2", .data = (void *)GENET_V2 }, { .compatible = "brcm,genet-v3", .data = (void *)GENET_V3 }, { .compatible = "brcm,genet-v4", .data = (void *)GENET_V4 }, + { .compatible = "brcm,genet-v5", .data = (void *)GENET_V5 }, { }, }; MODULE_DEVICE_TABLE(of, bcmgenet_match); @@ -3233,6 +3366,7 @@ static int bcmgenet_probe(struct platform_device *pdev) const void *macaddr; struct resource *r; int err = -EIO; + const char *phy_mode_str; /* Up to GENET_MAX_MQ_CNT + 1 TX queues and RX queues */ dev = alloc_etherdev_mqs(sizeof(*priv), GENET_MAX_MQ_CNT + 1, @@ -3276,6 +3410,8 @@ static int bcmgenet_probe(struct platform_device *pdev) goto err; } + spin_lock_init(&priv->lock); + SET_NETDEV_DEV(dev, &pdev->dev); dev_set_drvdata(&pdev->dev, dev); ether_addr_copy(dev->dev_addr, macaddr); @@ -3338,6 +3474,13 @@ static int bcmgenet_probe(struct platform_device *pdev) priv->clk_eee = NULL; } + /* If this is an internal GPHY, power it on now, before UniMAC is + * brought out of reset as absolutely no UniMAC activity is allowed + */ + if (dn && !of_property_read_string(dn, "phy-mode", &phy_mode_str) && + !strcasecmp(phy_mode_str, "internal")) + bcmgenet_power_up(priv, GENET_POWER_PASSIVE); + err = reset_umac(priv); if (err) goto err_clk_disable; @@ -3406,7 +3549,7 @@ static int bcmgenet_suspend(struct device *d) if (ret) return ret; - /* Disable MAC transmit. TX DMA disabled have to done before this */ + /* Disable MAC transmit. TX DMA disabled must be done before this */ umac_enable_set(priv, CMD_TX_EN, false); /* tx reclaim */ @@ -3502,6 +3645,8 @@ static int bcmgenet_resume(struct device *d) return 0; out_clk_disable: + if (priv->internal_phy) + bcmgenet_power_down(priv, GENET_POWER_PASSIVE); clk_disable_unprepare(priv->clk); return ret; } diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.h b/drivers/net/ethernet/broadcom/genet/bcmgenet.h index 1e2dc34d331a..5692c0582434 100644 --- a/drivers/net/ethernet/broadcom/genet/bcmgenet.h +++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.h @@ -1,5 +1,5 @@ /* - * Copyright (c) 2014 Broadcom Corporation + * Copyright (c) 2014-2017 Broadcom * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License version 2 as @@ -214,7 +214,9 @@ struct bcmgenet_mib_counters { #define MDIO_REG_SHIFT 16 #define MDIO_REG_MASK 0x1F -#define UMAC_RBUF_OVFL_CNT 0x61C +#define UMAC_RBUF_OVFL_CNT_V1 0x61C +#define RBUF_OVFL_CNT_V2 0x80 +#define RBUF_OVFL_CNT_V3PLUS 0x94 #define UMAC_MPD_CTRL 0x620 #define MPD_EN (1 << 0) @@ -224,7 +226,9 @@ struct bcmgenet_mib_counters { #define UMAC_MPD_PW_MS 0x624 #define UMAC_MPD_PW_LS 0x628 -#define UMAC_RBUF_ERR_CNT 0x634 +#define UMAC_RBUF_ERR_CNT_V1 0x634 +#define RBUF_ERR_CNT_V2 0x84 +#define RBUF_ERR_CNT_V3PLUS 0x98 #define UMAC_MDF_ERR_CNT 0x638 #define UMAC_MDF_CTRL 0x650 #define UMAC_MDF_ADDR 0x654 @@ -351,8 +355,14 @@ struct bcmgenet_mib_counters { #define EXT_PWR_DN_EN_LD (1 << 3) #define EXT_ENERGY_DET (1 << 4) #define EXT_IDDQ_FROM_PHY (1 << 5) +#define EXT_IDDQ_GLBL_PWR (1 << 7) #define EXT_PHY_RESET (1 << 8) #define EXT_ENERGY_DET_MASK (1 << 12) +#define EXT_PWR_DOWN_PHY_TX (1 << 16) +#define EXT_PWR_DOWN_PHY_RX (1 << 17) +#define EXT_PWR_DOWN_PHY_SD (1 << 18) +#define EXT_PWR_DOWN_PHY_RD (1 << 19) +#define EXT_PWR_DOWN_PHY_EN (1 << 20) #define EXT_RGMII_OOB_CTRL 0x0C #define RGMII_LINK (1 << 4) @@ -495,13 +505,15 @@ enum bcmgenet_version { GENET_V1 = 1, GENET_V2, GENET_V3, - GENET_V4 + GENET_V4, + GENET_V5 }; #define GENET_IS_V1(p) ((p)->version == GENET_V1) #define GENET_IS_V2(p) ((p)->version == GENET_V2) #define GENET_IS_V3(p) ((p)->version == GENET_V3) #define GENET_IS_V4(p) ((p)->version == GENET_V4) +#define GENET_IS_V5(p) ((p)->version == GENET_V5) /* Hardware flags */ #define GENET_HAS_40BITS (1 << 0) @@ -619,11 +631,13 @@ struct bcmgenet_priv { struct work_struct bcmgenet_irq_work; int irq0; int irq1; - unsigned int irq0_stat; - unsigned int irq1_stat; int wol_irq; bool wol_irq_disabled; + /* shared status */ + spinlock_t lock; + unsigned int irq0_stat; + /* HW descriptors/checksum variables */ bool desc_64b_en; bool desc_rxchk_en; diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet_wol.c b/drivers/net/ethernet/broadcom/genet/bcmgenet_wol.c index b97122926d3a..2fbd027f0148 100644 --- a/drivers/net/ethernet/broadcom/genet/bcmgenet_wol.c +++ b/drivers/net/ethernet/broadcom/genet/bcmgenet_wol.c @@ -1,7 +1,7 @@ /* * Broadcom GENET (Gigabit Ethernet) Wake-on-LAN support * - * Copyright (c) 2014 Broadcom Corporation + * Copyright (c) 2014-2017 Broadcom * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License version 2 as @@ -127,7 +127,6 @@ int bcmgenet_wol_power_down_cfg(struct bcmgenet_priv *priv, enum bcmgenet_power_mode mode) { struct net_device *dev = priv->dev; - u32 cpu_mask_clear; int retries = 0; u32 reg; @@ -173,18 +172,12 @@ int bcmgenet_wol_power_down_cfg(struct bcmgenet_priv *priv, bcmgenet_ext_writel(priv, reg, EXT_EXT_PWR_MGMT); } - /* Enable the MPD interrupt */ - cpu_mask_clear = UMAC_IRQ_MPD_R; - - bcmgenet_intrl2_0_writel(priv, cpu_mask_clear, INTRL2_CPU_MASK_CLEAR); - return 0; } void bcmgenet_wol_power_up_cfg(struct bcmgenet_priv *priv, enum bcmgenet_power_mode mode) { - u32 cpu_mask_set; u32 reg; if (mode != GENET_POWER_WOL_MAGIC) { @@ -201,10 +194,4 @@ void bcmgenet_wol_power_up_cfg(struct bcmgenet_priv *priv, reg &= ~CMD_CRC_FWD; bcmgenet_umac_writel(priv, reg, UMAC_CMD); priv->crc_fwd_en = 0; - - /* Stop monitoring magic packet IRQ */ - cpu_mask_set = UMAC_IRQ_MPD_R; - - /* Stop monitoring magic packet IRQ */ - bcmgenet_intrl2_0_writel(priv, cpu_mask_set, INTRL2_CPU_MASK_SET); } diff --git a/drivers/net/ethernet/broadcom/genet/bcmmii.c b/drivers/net/ethernet/broadcom/genet/bcmmii.c index e87607621e62..8df47c90cfc5 100644 --- a/drivers/net/ethernet/broadcom/genet/bcmmii.c +++ b/drivers/net/ethernet/broadcom/genet/bcmmii.c @@ -1,7 +1,7 @@ /* * Broadcom GENET MDIO routines * - * Copyright (c) 2014 Broadcom Corporation + * Copyright (c) 2014-2017 Broadcom * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License version 2 as @@ -195,29 +195,31 @@ void bcmgenet_phy_power_set(struct net_device *dev, bool enable) u32 reg = 0; /* EXT_GPHY_CTRL is only valid for GENETv4 and onward */ - if (!GENET_IS_V4(priv)) - return; - - reg = bcmgenet_ext_readl(priv, EXT_GPHY_CTRL); - if (enable) { - reg &= ~EXT_CK25_DIS; - bcmgenet_ext_writel(priv, reg, EXT_GPHY_CTRL); - mdelay(1); - - reg &= ~(EXT_CFG_IDDQ_BIAS | EXT_CFG_PWR_DOWN); - reg |= EXT_GPHY_RESET; + if (GENET_IS_V4(priv)) { + reg = bcmgenet_ext_readl(priv, EXT_GPHY_CTRL); + if (enable) { + reg &= ~EXT_CK25_DIS; + bcmgenet_ext_writel(priv, reg, EXT_GPHY_CTRL); + mdelay(1); + + reg &= ~(EXT_CFG_IDDQ_BIAS | EXT_CFG_PWR_DOWN); + reg |= EXT_GPHY_RESET; + bcmgenet_ext_writel(priv, reg, EXT_GPHY_CTRL); + mdelay(1); + + reg &= ~EXT_GPHY_RESET; + } else { + reg |= EXT_CFG_IDDQ_BIAS | EXT_CFG_PWR_DOWN | + EXT_GPHY_RESET; + bcmgenet_ext_writel(priv, reg, EXT_GPHY_CTRL); + mdelay(1); + reg |= EXT_CK25_DIS; + } bcmgenet_ext_writel(priv, reg, EXT_GPHY_CTRL); - mdelay(1); - - reg &= ~EXT_GPHY_RESET; + udelay(60); } else { - reg |= EXT_CFG_IDDQ_BIAS | EXT_CFG_PWR_DOWN | EXT_GPHY_RESET; - bcmgenet_ext_writel(priv, reg, EXT_GPHY_CTRL); mdelay(1); - reg |= EXT_CK25_DIS; } - bcmgenet_ext_writel(priv, reg, EXT_GPHY_CTRL); - udelay(60); } static void bcmgenet_internal_phy_setup(struct net_device *dev) @@ -227,10 +229,12 @@ static void bcmgenet_internal_phy_setup(struct net_device *dev) /* Power up PHY */ bcmgenet_phy_power_set(dev, true); - /* enable APD */ - reg = bcmgenet_ext_readl(priv, EXT_EXT_PWR_MGMT); - reg |= EXT_PWR_DN_EN_LD; - bcmgenet_ext_writel(priv, reg, EXT_EXT_PWR_MGMT); + if (!GENET_IS_V5(priv)) { + /* enable APD */ + reg = bcmgenet_ext_readl(priv, EXT_EXT_PWR_MGMT); + reg |= EXT_PWR_DN_EN_LD; + bcmgenet_ext_writel(priv, reg, EXT_EXT_PWR_MGMT); + } bcmgenet_mii_reset(dev); } @@ -238,10 +242,12 @@ static void bcmgenet_moca_phy_setup(struct bcmgenet_priv *priv) { u32 reg; - /* Speed settings are set in bcmgenet_mii_setup() */ - reg = bcmgenet_sys_readl(priv, SYS_PORT_CTRL); - reg |= LED_ACT_SOURCE_MAC; - bcmgenet_sys_writel(priv, reg, SYS_PORT_CTRL); + if (!GENET_IS_V5(priv)) { + /* Speed settings are set in bcmgenet_mii_setup() */ + reg = bcmgenet_sys_readl(priv, SYS_PORT_CTRL); + reg |= LED_ACT_SOURCE_MAC; + bcmgenet_sys_writel(priv, reg, SYS_PORT_CTRL); + } if (priv->hw_params->flags & GENET_HAS_MOCA_LINK_DET) fixed_phy_set_link_update(priv->phydev, diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c index 30d1eb9ebec9..f395b951f5e7 100644 --- a/drivers/net/ethernet/broadcom/tg3.c +++ b/drivers/net/ethernet/broadcom/tg3.c @@ -825,6 +825,7 @@ static int tg3_ape_event_lock(struct tg3 *tp, u32 timeout_us) return timeout_us ? 0 : -EBUSY; } +#ifdef CONFIG_TIGON3_HWMON static int tg3_ape_wait_for_event(struct tg3 *tp, u32 timeout_us) { u32 i, apedata; @@ -904,6 +905,7 @@ static int tg3_ape_scratchpad_read(struct tg3 *tp, u32 *data, u32 base_off, return 0; } +#endif static int tg3_ape_send_event(struct tg3 *tp, u32 event) { @@ -10744,6 +10746,7 @@ static int tg3_init_hw(struct tg3 *tp, bool reset_phy) return tg3_reset_hw(tp, reset_phy); } +#ifdef CONFIG_TIGON3_HWMON static void tg3_sd_scan_scratchpad(struct tg3 *tp, struct tg3_ocir *ocir) { int i; @@ -10826,6 +10829,10 @@ static void tg3_hwmon_open(struct tg3 *tp) dev_err(&pdev->dev, "Cannot register hwmon device, aborting\n"); } } +#else +static inline void tg3_hwmon_close(struct tg3 *tp) { } +static inline void tg3_hwmon_open(struct tg3 *tp) { } +#endif /* CONFIG_TIGON3_HWMON */ #define TG3_STAT_ADD32(PSTAT, REG) \ diff --git a/drivers/net/ethernet/cavium/liquidio/lio_ethtool.c b/drivers/net/ethernet/cavium/liquidio/lio_ethtool.c index 50384cede8be..6eef3b999130 100644 --- a/drivers/net/ethernet/cavium/liquidio/lio_ethtool.c +++ b/drivers/net/ethernet/cavium/liquidio/lio_ethtool.c @@ -213,17 +213,23 @@ static int lio_get_link_ksettings(struct net_device *netdev, struct lio *lio = GET_LIO(netdev); struct octeon_device *oct = lio->oct_dev; struct oct_link_info *linfo; - u32 supported, advertising; + u32 supported = 0, advertising = 0; linfo = &lio->linfo; if (linfo->link.s.if_mode == INTERFACE_MODE_XAUI || linfo->link.s.if_mode == INTERFACE_MODE_RXAUI || + linfo->link.s.if_mode == INTERFACE_MODE_XLAUI || linfo->link.s.if_mode == INTERFACE_MODE_XFI) { ecmd->base.port = PORT_FIBRE; - supported = (SUPPORTED_10000baseT_Full | SUPPORTED_FIBRE | - SUPPORTED_Pause); - advertising = (ADVERTISED_10000baseT_Full | ADVERTISED_Pause); + + if (linfo->link.s.speed == SPEED_10000) { + supported = SUPPORTED_10000baseT_Full; + advertising = ADVERTISED_10000baseT_Full; + } + + supported |= SUPPORTED_FIBRE | SUPPORTED_Pause; + advertising |= ADVERTISED_Pause; ethtool_convert_legacy_u32_to_link_mode( ecmd->link_modes.supported, supported); ethtool_convert_legacy_u32_to_link_mode( diff --git a/drivers/net/ethernet/cavium/liquidio/lio_main.c b/drivers/net/ethernet/cavium/liquidio/lio_main.c index be9c0e3f5ade..761061b96948 100644 --- a/drivers/net/ethernet/cavium/liquidio/lio_main.c +++ b/drivers/net/ethernet/cavium/liquidio/lio_main.c @@ -152,7 +152,7 @@ struct octnic_gather { */ struct octeon_sg_entry *sg; - u64 sg_dma_ptr; + dma_addr_t sg_dma_ptr; }; struct handshake { @@ -734,6 +734,9 @@ static void delete_glists(struct lio *lio) struct octnic_gather *g; int i; + kfree(lio->glist_lock); + lio->glist_lock = NULL; + if (!lio->glist) return; @@ -741,23 +744,26 @@ static void delete_glists(struct lio *lio) do { g = (struct octnic_gather *) list_delete_head(&lio->glist[i]); - if (g) { - if (g->sg) { - dma_unmap_single(&lio->oct_dev-> - pci_dev->dev, - g->sg_dma_ptr, - g->sg_size, - DMA_TO_DEVICE); - kfree((void *)((unsigned long)g->sg - - g->adjust)); - } + if (g) kfree(g); - } } while (g); + + if (lio->glists_virt_base && lio->glists_virt_base[i]) { + lio_dma_free(lio->oct_dev, + lio->glist_entry_size * lio->tx_qsize, + lio->glists_virt_base[i], + lio->glists_dma_base[i]); + } } - kfree((void *)lio->glist); - kfree((void *)lio->glist_lock); + kfree(lio->glists_virt_base); + lio->glists_virt_base = NULL; + + kfree(lio->glists_dma_base); + lio->glists_dma_base = NULL; + + kfree(lio->glist); + lio->glist = NULL; } /** @@ -772,22 +778,49 @@ static int setup_glists(struct octeon_device *oct, struct lio *lio, int num_iqs) lio->glist_lock = kcalloc(num_iqs, sizeof(*lio->glist_lock), GFP_KERNEL); if (!lio->glist_lock) - return 1; + return -ENOMEM; lio->glist = kcalloc(num_iqs, sizeof(*lio->glist), GFP_KERNEL); if (!lio->glist) { - kfree((void *)lio->glist_lock); - return 1; + kfree(lio->glist_lock); + lio->glist_lock = NULL; + return -ENOMEM; + } + + lio->glist_entry_size = + ROUNDUP8((ROUNDUP4(OCTNIC_MAX_SG) >> 2) * OCT_SG_ENTRY_SIZE); + + /* allocate memory to store virtual and dma base address of + * per glist consistent memory + */ + lio->glists_virt_base = kcalloc(num_iqs, sizeof(*lio->glists_virt_base), + GFP_KERNEL); + lio->glists_dma_base = kcalloc(num_iqs, sizeof(*lio->glists_dma_base), + GFP_KERNEL); + + if (!lio->glists_virt_base || !lio->glists_dma_base) { + delete_glists(lio); + return -ENOMEM; } for (i = 0; i < num_iqs; i++) { - int numa_node = cpu_to_node(i % num_online_cpus()); + int numa_node = dev_to_node(&oct->pci_dev->dev); spin_lock_init(&lio->glist_lock[i]); INIT_LIST_HEAD(&lio->glist[i]); + lio->glists_virt_base[i] = + lio_dma_alloc(oct, + lio->glist_entry_size * lio->tx_qsize, + &lio->glists_dma_base[i]); + + if (!lio->glists_virt_base[i]) { + delete_glists(lio); + return -ENOMEM; + } + for (j = 0; j < lio->tx_qsize; j++) { g = kzalloc_node(sizeof(*g), GFP_KERNEL, numa_node); @@ -796,43 +829,18 @@ static int setup_glists(struct octeon_device *oct, struct lio *lio, int num_iqs) if (!g) break; - g->sg_size = ((ROUNDUP4(OCTNIC_MAX_SG) >> 2) * - OCT_SG_ENTRY_SIZE); + g->sg = lio->glists_virt_base[i] + + (j * lio->glist_entry_size); - g->sg = kmalloc_node(g->sg_size + 8, - GFP_KERNEL, numa_node); - if (!g->sg) - g->sg = kmalloc(g->sg_size + 8, GFP_KERNEL); - if (!g->sg) { - kfree(g); - break; - } - - /* The gather component should be aligned on 64-bit - * boundary - */ - if (((unsigned long)g->sg) & 7) { - g->adjust = 8 - (((unsigned long)g->sg) & 7); - g->sg = (struct octeon_sg_entry *) - ((unsigned long)g->sg + g->adjust); - } - g->sg_dma_ptr = dma_map_single(&oct->pci_dev->dev, - g->sg, g->sg_size, - DMA_TO_DEVICE); - if (dma_mapping_error(&oct->pci_dev->dev, - g->sg_dma_ptr)) { - kfree((void *)((unsigned long)g->sg - - g->adjust)); - kfree(g); - break; - } + g->sg_dma_ptr = lio->glists_dma_base[i] + + (j * lio->glist_entry_size); list_add_tail(&g->list, &lio->glist[i]); } if (j != lio->tx_qsize) { delete_glists(lio); - return 1; + return -ENOMEM; } } @@ -1076,16 +1084,35 @@ static int octeon_setup_interrupt(struct octeon_device *oct) int i; int num_ioq_vectors; int num_alloc_ioq_vectors; + char *queue_irq_names = NULL; + char *aux_irq_name = NULL; if (OCTEON_CN23XX_PF(oct) && oct->msix_on) { oct->num_msix_irqs = oct->sriov_info.num_pf_rings; /* one non ioq interrupt for handling sli_mac_pf_int_sum */ oct->num_msix_irqs += 1; + /* allocate storage for the names assigned to each irq */ + oct->irq_name_storage = + kcalloc((MAX_IOQ_INTERRUPTS_PER_PF + 1), INTRNAMSIZ, + GFP_KERNEL); + if (!oct->irq_name_storage) { + dev_err(&oct->pci_dev->dev, "Irq name storage alloc failed...\n"); + return -ENOMEM; + } + + queue_irq_names = oct->irq_name_storage; + aux_irq_name = &queue_irq_names + [IRQ_NAME_OFF(MAX_IOQ_INTERRUPTS_PER_PF)]; + oct->msix_entries = kcalloc( oct->num_msix_irqs, sizeof(struct msix_entry), GFP_KERNEL); - if (!oct->msix_entries) - return 1; + if (!oct->msix_entries) { + dev_err(&oct->pci_dev->dev, "Memory Alloc failed...\n"); + kfree(oct->irq_name_storage); + oct->irq_name_storage = NULL; + return -ENOMEM; + } msix_entries = (struct msix_entry *)oct->msix_entries; /*Assumption is that pf msix vectors start from pf srn to pf to @@ -1103,7 +1130,9 @@ static int octeon_setup_interrupt(struct octeon_device *oct) dev_err(&oct->pci_dev->dev, "unable to Allocate MSI-X interrupts\n"); kfree(oct->msix_entries); oct->msix_entries = NULL; - return 1; + kfree(oct->irq_name_storage); + oct->irq_name_storage = NULL; + return num_alloc_ioq_vectors; } dev_dbg(&oct->pci_dev->dev, "OCTEON: Enough MSI-X interrupts are allocated...\n"); @@ -1111,9 +1140,12 @@ static int octeon_setup_interrupt(struct octeon_device *oct) /** For PF, there is one non-ioq interrupt handler */ num_ioq_vectors -= 1; + + snprintf(aux_irq_name, INTRNAMSIZ, + "LiquidIO%u-pf%u-aux", oct->octeon_id, oct->pf_num); irqret = request_irq(msix_entries[num_ioq_vectors].vector, - liquidio_legacy_intr_handler, 0, "octeon", - oct); + liquidio_legacy_intr_handler, 0, + aux_irq_name, oct); if (irqret) { dev_err(&oct->pci_dev->dev, "OCTEON: Request_irq failed for MSIX interrupt Error: %d\n", @@ -1121,13 +1153,20 @@ static int octeon_setup_interrupt(struct octeon_device *oct) pci_disable_msix(oct->pci_dev); kfree(oct->msix_entries); oct->msix_entries = NULL; - return 1; + kfree(oct->irq_name_storage); + oct->irq_name_storage = NULL; + return irqret; } for (i = 0; i < num_ioq_vectors; i++) { + snprintf(&queue_irq_names[IRQ_NAME_OFF(i)], INTRNAMSIZ, + "LiquidIO%u-pf%u-rxtx-%u", + oct->octeon_id, oct->pf_num, i); + irqret = request_irq(msix_entries[i].vector, liquidio_msix_intr_handler, 0, - "octeon", &oct->ioq_vector[i]); + &queue_irq_names[IRQ_NAME_OFF(i)], + &oct->ioq_vector[i]); if (irqret) { dev_err(&oct->pci_dev->dev, "OCTEON: Request_irq failed for MSIX interrupt Error: %d\n", @@ -1147,7 +1186,9 @@ static int octeon_setup_interrupt(struct octeon_device *oct) pci_disable_msix(oct->pci_dev); kfree(oct->msix_entries); oct->msix_entries = NULL; - return 1; + kfree(oct->irq_name_storage); + oct->irq_name_storage = NULL; + return irqret; } oct->ioq_vector[i].vector = msix_entries[i].vector; /* assign the cpu mask for this msix interrupt vector */ @@ -1165,15 +1206,29 @@ static int octeon_setup_interrupt(struct octeon_device *oct) else oct->flags |= LIO_FLAG_MSI_ENABLED; + /* allocate storage for the names assigned to the irq */ + oct->irq_name_storage = kcalloc(1, INTRNAMSIZ, GFP_KERNEL); + if (!oct->irq_name_storage) + return -ENOMEM; + + queue_irq_names = oct->irq_name_storage; + + snprintf(&queue_irq_names[IRQ_NAME_OFF(0)], INTRNAMSIZ, + "LiquidIO%u-pf%u-rxtx-%u", + oct->octeon_id, oct->pf_num, 0); + irqret = request_irq(oct->pci_dev->irq, - liquidio_legacy_intr_handler, IRQF_SHARED, - "octeon", oct); + liquidio_legacy_intr_handler, + IRQF_SHARED, + &queue_irq_names[IRQ_NAME_OFF(0)], oct); if (irqret) { if (oct->flags & LIO_FLAG_MSI_ENABLED) pci_disable_msi(oct->pci_dev); dev_err(&oct->pci_dev->dev, "Request IRQ failed with code: %d\n", irqret); - return 1; + kfree(oct->irq_name_storage); + oct->irq_name_storage = NULL; + return irqret; } } return 0; @@ -1441,6 +1496,9 @@ static void octeon_destroy_resources(struct octeon_device *oct) pci_disable_msi(oct->pci_dev); } + kfree(oct->irq_name_storage); + oct->irq_name_storage = NULL; + /* fallthrough */ case OCT_DEV_MSIX_ALLOC_VECTOR_DONE: if (OCTEON_CN23XX_PF(oct)) @@ -1885,9 +1943,6 @@ static void free_netsgbuf(void *buf) i++; } - dma_sync_single_for_cpu(&lio->oct_dev->pci_dev->dev, - g->sg_dma_ptr, g->sg_size, DMA_TO_DEVICE); - iq = skb_iq(lio, skb); spin_lock(&lio->glist_lock[iq]); list_add_tail(&g->list, &lio->glist[iq]); @@ -1933,9 +1988,6 @@ static void free_netsgbuf_with_resp(void *buf) i++; } - dma_sync_single_for_cpu(&lio->oct_dev->pci_dev->dev, - g->sg_dma_ptr, g->sg_size, DMA_TO_DEVICE); - iq = skb_iq(lio, skb); spin_lock(&lio->glist_lock[iq]); @@ -2553,6 +2605,15 @@ static inline int setup_io_queues(struct octeon_device *octeon_dev, __func__); return 1; } + + if (octeon_dev->ioq_vector) { + struct octeon_ioq_vector *ioq_vector; + + ioq_vector = &octeon_dev->ioq_vector[q]; + netif_set_xps_queue(netdev, + &ioq_vector->affinity_mask, + ioq_vector->iq_index); + } } return 0; @@ -3273,8 +3334,6 @@ static int liquidio_xmit(struct sk_buff *skb, struct net_device *netdev) i++; } - dma_sync_single_for_device(&oct->pci_dev->dev, g->sg_dma_ptr, - g->sg_size, DMA_TO_DEVICE); dptr = g->sg_dma_ptr; if (OCTEON_CN23XX_PF(oct)) diff --git a/drivers/net/ethernet/cavium/liquidio/lio_vf_main.c b/drivers/net/ethernet/cavium/liquidio/lio_vf_main.c index 9d5e03502c76..5ec5c24cee5d 100644 --- a/drivers/net/ethernet/cavium/liquidio/lio_vf_main.c +++ b/drivers/net/ethernet/cavium/liquidio/lio_vf_main.c @@ -108,6 +108,8 @@ struct octnic_gather { * received from the IP layer. */ struct octeon_sg_entry *sg; + + dma_addr_t sg_dma_ptr; }; struct octeon_device_priv { @@ -490,6 +492,9 @@ static void delete_glists(struct lio *lio) struct octnic_gather *g; int i; + kfree(lio->glist_lock); + lio->glist_lock = NULL; + if (!lio->glist) return; @@ -497,17 +502,26 @@ static void delete_glists(struct lio *lio) do { g = (struct octnic_gather *) list_delete_head(&lio->glist[i]); - if (g) { - if (g->sg) - kfree((void *)((unsigned long)g->sg - - g->adjust)); + if (g) kfree(g); - } } while (g); + + if (lio->glists_virt_base && lio->glists_virt_base[i]) { + lio_dma_free(lio->oct_dev, + lio->glist_entry_size * lio->tx_qsize, + lio->glists_virt_base[i], + lio->glists_dma_base[i]); + } } + kfree(lio->glists_virt_base); + lio->glists_virt_base = NULL; + + kfree(lio->glists_dma_base); + lio->glists_dma_base = NULL; + kfree(lio->glist); - kfree(lio->glist_lock); + lio->glist = NULL; } /** @@ -522,13 +536,30 @@ static int setup_glists(struct lio *lio, int num_iqs) lio->glist_lock = kzalloc(sizeof(*lio->glist_lock) * num_iqs, GFP_KERNEL); if (!lio->glist_lock) - return 1; + return -ENOMEM; lio->glist = kzalloc(sizeof(*lio->glist) * num_iqs, GFP_KERNEL); if (!lio->glist) { kfree(lio->glist_lock); - return 1; + lio->glist_lock = NULL; + return -ENOMEM; + } + + lio->glist_entry_size = + ROUNDUP8((ROUNDUP4(OCTNIC_MAX_SG) >> 2) * OCT_SG_ENTRY_SIZE); + + /* allocate memory to store virtual and dma base address of + * per glist consistent memory + */ + lio->glists_virt_base = kcalloc(num_iqs, sizeof(*lio->glists_virt_base), + GFP_KERNEL); + lio->glists_dma_base = kcalloc(num_iqs, sizeof(*lio->glists_dma_base), + GFP_KERNEL); + + if (!lio->glists_virt_base || !lio->glists_dma_base) { + delete_glists(lio); + return -ENOMEM; } for (i = 0; i < num_iqs; i++) { @@ -536,34 +567,33 @@ static int setup_glists(struct lio *lio, int num_iqs) INIT_LIST_HEAD(&lio->glist[i]); + lio->glists_virt_base[i] = + lio_dma_alloc(lio->oct_dev, + lio->glist_entry_size * lio->tx_qsize, + &lio->glists_dma_base[i]); + + if (!lio->glists_virt_base[i]) { + delete_glists(lio); + return -ENOMEM; + } + for (j = 0; j < lio->tx_qsize; j++) { g = kzalloc(sizeof(*g), GFP_KERNEL); if (!g) break; - g->sg_size = ((ROUNDUP4(OCTNIC_MAX_SG) >> 2) * - OCT_SG_ENTRY_SIZE); + g->sg = lio->glists_virt_base[i] + + (j * lio->glist_entry_size); - g->sg = kmalloc(g->sg_size + 8, GFP_KERNEL); - if (!g->sg) { - kfree(g); - break; - } + g->sg_dma_ptr = lio->glists_dma_base[i] + + (j * lio->glist_entry_size); - /* The gather component should be aligned on 64-bit - * boundary - */ - if (((unsigned long)g->sg) & 7) { - g->adjust = 8 - (((unsigned long)g->sg) & 7); - g->sg = (struct octeon_sg_entry *) - ((unsigned long)g->sg + g->adjust); - } list_add_tail(&g->list, &lio->glist[i]); } if (j != lio->tx_qsize) { delete_glists(lio); - return 1; + return -ENOMEM; } } @@ -750,6 +780,7 @@ liquidio_msix_intr_handler(int irq __attribute__((unused)), void *dev) static int octeon_setup_interrupt(struct octeon_device *oct) { struct msix_entry *msix_entries; + char *queue_irq_names = NULL; int num_alloc_ioq_vectors; int num_ioq_vectors; int irqret; @@ -758,10 +789,25 @@ static int octeon_setup_interrupt(struct octeon_device *oct) if (oct->msix_on) { oct->num_msix_irqs = oct->sriov_info.rings_per_vf; + /* allocate storage for the names assigned to each irq */ + oct->irq_name_storage = + kcalloc(MAX_IOQ_INTERRUPTS_PER_VF, INTRNAMSIZ, + GFP_KERNEL); + if (!oct->irq_name_storage) { + dev_err(&oct->pci_dev->dev, "Irq name storage alloc failed...\n"); + return -ENOMEM; + } + + queue_irq_names = oct->irq_name_storage; + oct->msix_entries = kcalloc( oct->num_msix_irqs, sizeof(struct msix_entry), GFP_KERNEL); - if (!oct->msix_entries) - return 1; + if (!oct->msix_entries) { + dev_err(&oct->pci_dev->dev, "Memory Alloc failed...\n"); + kfree(oct->irq_name_storage); + oct->irq_name_storage = NULL; + return -ENOMEM; + } msix_entries = (struct msix_entry *)oct->msix_entries; @@ -775,16 +821,23 @@ static int octeon_setup_interrupt(struct octeon_device *oct) dev_err(&oct->pci_dev->dev, "unable to Allocate MSI-X interrupts\n"); kfree(oct->msix_entries); oct->msix_entries = NULL; - return 1; + kfree(oct->irq_name_storage); + oct->irq_name_storage = NULL; + return num_alloc_ioq_vectors; } dev_dbg(&oct->pci_dev->dev, "OCTEON: Enough MSI-X interrupts are allocated...\n"); num_ioq_vectors = oct->num_msix_irqs; for (i = 0; i < num_ioq_vectors; i++) { + snprintf(&queue_irq_names[IRQ_NAME_OFF(i)], INTRNAMSIZ, + "LiquidIO%u-vf%u-rxtx-%u", + oct->octeon_id, oct->vf_num, i); + irqret = request_irq(msix_entries[i].vector, liquidio_msix_intr_handler, 0, - "octeon", &oct->ioq_vector[i]); + &queue_irq_names[IRQ_NAME_OFF(i)], + &oct->ioq_vector[i]); if (irqret) { dev_err(&oct->pci_dev->dev, "OCTEON: Request_irq failed for MSIX interrupt Error: %d\n", @@ -800,7 +853,9 @@ static int octeon_setup_interrupt(struct octeon_device *oct) pci_disable_msix(oct->pci_dev); kfree(oct->msix_entries); oct->msix_entries = NULL; - return 1; + kfree(oct->irq_name_storage); + oct->irq_name_storage = NULL; + return irqret; } oct->ioq_vector[i].vector = msix_entries[i].vector; /* assign the cpu mask for this msix interrupt vector */ @@ -945,6 +1000,8 @@ static void octeon_destroy_resources(struct octeon_device *oct) pci_disable_msix(oct->pci_dev); kfree(oct->msix_entries); oct->msix_entries = NULL; + kfree(oct->irq_name_storage); + oct->irq_name_storage = NULL; } /* Soft reset the octeon device before exiting */ if (oct->pci_dev->reset_fn) @@ -1324,10 +1381,6 @@ static void free_netsgbuf(void *buf) i++; } - dma_unmap_single(&lio->oct_dev->pci_dev->dev, - finfo->dptr, g->sg_size, - DMA_TO_DEVICE); - iq = skb_iq(lio, skb); spin_lock(&lio->glist_lock[iq]); @@ -1374,10 +1427,6 @@ static void free_netsgbuf_with_resp(void *buf) i++; } - dma_unmap_single(&lio->oct_dev->pci_dev->dev, - finfo->dptr, g->sg_size, - DMA_TO_DEVICE); - iq = skb_iq(lio, skb); spin_lock(&lio->glist_lock[iq]); @@ -2382,23 +2431,7 @@ static int liquidio_xmit(struct sk_buff *skb, struct net_device *netdev) i++; } - dptr = dma_map_single(&oct->pci_dev->dev, - g->sg, g->sg_size, - DMA_TO_DEVICE); - if (dma_mapping_error(&oct->pci_dev->dev, dptr)) { - dev_err(&oct->pci_dev->dev, "%s DMA mapping error 4\n", - __func__); - dma_unmap_single(&oct->pci_dev->dev, g->sg[0].ptr[0], - skb->len - skb->data_len, - DMA_TO_DEVICE); - for (j = 1; j <= frags; j++) { - frag = &skb_shinfo(skb)->frags[j - 1]; - dma_unmap_page(&oct->pci_dev->dev, - g->sg[j >> 2].ptr[j & 3], - frag->size, DMA_TO_DEVICE); - } - return NETDEV_TX_BUSY; - } + dptr = g->sg_dma_ptr; ndata.cmd.cmd3.dptr = dptr; finfo->dptr = dptr; diff --git a/drivers/net/ethernet/cavium/liquidio/liquidio_common.h b/drivers/net/ethernet/cavium/liquidio/liquidio_common.h index 294c6f3c6b48..4a07c0ac9fab 100644 --- a/drivers/net/ethernet/cavium/liquidio/liquidio_common.h +++ b/drivers/net/ethernet/cavium/liquidio/liquidio_common.h @@ -100,6 +100,11 @@ enum octeon_tag_type { #define BYTES_PER_DHLEN_UNIT 8 #define MAX_REG_CNT 2000000U +#define INTRNAMSIZ 32 +#define IRQ_NAME_OFF(i) ((i) * INTRNAMSIZ) +#define MAX_IOQ_INTERRUPTS_PER_PF (64 * 2) +#define MAX_IOQ_INTERRUPTS_PER_VF (8 * 2) + static inline u32 incr_index(u32 index, u32 count, u32 max) { diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_config.h b/drivers/net/ethernet/cavium/liquidio/octeon_config.h index b3dc2e9651a8..d29ebc531151 100644 --- a/drivers/net/ethernet/cavium/liquidio/octeon_config.h +++ b/drivers/net/ethernet/cavium/liquidio/octeon_config.h @@ -71,17 +71,17 @@ #define CN23XX_MAX_RINGS_PER_VF 8 #define CN23XX_MAX_INPUT_QUEUES CN23XX_MAX_RINGS_PER_PF -#define CN23XX_MAX_IQ_DESCRIPTORS 2048 +#define CN23XX_MAX_IQ_DESCRIPTORS 512 #define CN23XX_DB_MIN 1 #define CN23XX_DB_MAX 8 #define CN23XX_DB_TIMEOUT 1 #define CN23XX_MAX_OUTPUT_QUEUES CN23XX_MAX_RINGS_PER_PF -#define CN23XX_MAX_OQ_DESCRIPTORS 2048 +#define CN23XX_MAX_OQ_DESCRIPTORS 512 #define CN23XX_OQ_BUF_SIZE 1536 #define CN23XX_OQ_PKTSPER_INTR 128 /*#define CAVIUM_ONLY_CN23XX_RX_PERF*/ -#define CN23XX_OQ_REFIL_THRESHOLD 128 +#define CN23XX_OQ_REFIL_THRESHOLD 16 #define CN23XX_OQ_INTR_PKT 64 #define CN23XX_OQ_INTR_TIME 100 diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_device.c b/drivers/net/ethernet/cavium/liquidio/octeon_device.c index 9675ffbf25e6..e21b477d0159 100644 --- a/drivers/net/ethernet/cavium/liquidio/octeon_device.c +++ b/drivers/net/ethernet/cavium/liquidio/octeon_device.c @@ -793,7 +793,7 @@ int octeon_setup_instr_queues(struct octeon_device *oct) u32 num_descs = 0; u32 iq_no = 0; union oct_txpciq txpciq; - int numa_node = cpu_to_node(iq_no % num_online_cpus()); + int numa_node = dev_to_node(&oct->pci_dev->dev); if (OCTEON_CN6XXX(oct)) num_descs = @@ -837,7 +837,7 @@ int octeon_setup_output_queues(struct octeon_device *oct) u32 num_descs = 0; u32 desc_size = 0; u32 oq_no = 0; - int numa_node = cpu_to_node(oq_no % num_online_cpus()); + int numa_node = dev_to_node(&oct->pci_dev->dev); if (OCTEON_CN6XXX(oct)) { num_descs = diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_device.h b/drivers/net/ethernet/cavium/liquidio/octeon_device.h index c301a3852482..8c5d33e53cfa 100644 --- a/drivers/net/ethernet/cavium/liquidio/octeon_device.h +++ b/drivers/net/ethernet/cavium/liquidio/octeon_device.h @@ -517,6 +517,9 @@ struct octeon_device { void *msix_entries; + /* when requesting IRQs, the names are stored here */ + void *irq_name_storage; + struct octeon_sriov_info sriov_info; struct octeon_pf_vf_hs_word pfvf_hsword; diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_droq.c b/drivers/net/ethernet/cavium/liquidio/octeon_droq.c index 0be87d119a97..00970597ada8 100644 --- a/drivers/net/ethernet/cavium/liquidio/octeon_droq.c +++ b/drivers/net/ethernet/cavium/liquidio/octeon_droq.c @@ -155,11 +155,6 @@ octeon_droq_destroy_ring_buffers(struct octeon_device *oct, recv_buffer_destroy(droq->recv_buf_list[i].buffer, pg_info); - if (droq->desc_ring && droq->desc_ring[i].info_ptr) - lio_unmap_ring_info(oct->pci_dev, - (u64)droq-> - desc_ring[i].info_ptr, - OCT_DROQ_INFO_SIZE); droq->recv_buf_list[i].buffer = NULL; } @@ -211,10 +206,7 @@ int octeon_delete_droq(struct octeon_device *oct, u32 q_no) vfree(droq->recv_buf_list); if (droq->info_base_addr) - cnnic_free_aligned_dma(oct->pci_dev, droq->info_list, - droq->info_alloc_size, - droq->info_base_addr, - droq->info_list_dma); + lio_free_info_buffer(oct, droq); if (droq->desc_ring) lio_dma_free(oct, (droq->max_count * OCT_DROQ_DESC_SIZE), @@ -234,8 +226,7 @@ int octeon_init_droq(struct octeon_device *oct, struct octeon_droq *droq; u32 desc_ring_size = 0, c_num_descs = 0, c_buf_size = 0; u32 c_pkts_per_intr = 0, c_refill_threshold = 0; - int orig_node = dev_to_node(&oct->pci_dev->dev); - int numa_node = cpu_to_node(q_no % num_online_cpus()); + int numa_node = dev_to_node(&oct->pci_dev->dev); dev_dbg(&oct->pci_dev->dev, "%s[%d]\n", __func__, q_no); @@ -275,13 +266,8 @@ int octeon_init_droq(struct octeon_device *oct, droq->buffer_size = c_buf_size; desc_ring_size = droq->max_count * OCT_DROQ_DESC_SIZE; - set_dev_node(&oct->pci_dev->dev, numa_node); droq->desc_ring = lio_dma_alloc(oct, desc_ring_size, (dma_addr_t *)&droq->desc_ring_dma); - set_dev_node(&oct->pci_dev->dev, orig_node); - if (!droq->desc_ring) - droq->desc_ring = lio_dma_alloc(oct, desc_ring_size, - (dma_addr_t *)&droq->desc_ring_dma); if (!droq->desc_ring) { dev_err(&oct->pci_dev->dev, @@ -294,12 +280,7 @@ int octeon_init_droq(struct octeon_device *oct, dev_dbg(&oct->pci_dev->dev, "droq[%d]: num_desc: %d\n", q_no, droq->max_count); - droq->info_list = - cnnic_numa_alloc_aligned_dma((droq->max_count * - OCT_DROQ_INFO_SIZE), - &droq->info_alloc_size, - &droq->info_base_addr, - numa_node); + droq->info_list = lio_alloc_info_buffer(oct, droq); if (!droq->info_list) { dev_err(&oct->pci_dev->dev, "Cannot allocate memory for info list.\n"); lio_dma_free(oct, (droq->max_count * OCT_DROQ_DESC_SIZE), @@ -983,7 +964,7 @@ int octeon_create_droq(struct octeon_device *oct, u32 desc_size, void *app_ctx) { struct octeon_droq *droq; - int numa_node = cpu_to_node(q_no % num_online_cpus()); + int numa_node = dev_to_node(&oct->pci_dev->dev); if (oct->droq[q_no]) { dev_dbg(&oct->pci_dev->dev, "Droq already in use. Cannot create droq %d again\n", diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_droq.h b/drivers/net/ethernet/cavium/liquidio/octeon_droq.h index e62074090681..6982c0af5ecc 100644 --- a/drivers/net/ethernet/cavium/liquidio/octeon_droq.h +++ b/drivers/net/ethernet/cavium/liquidio/octeon_droq.h @@ -325,10 +325,10 @@ struct octeon_droq { size_t desc_ring_dma; /** Info ptr list are allocated at this virtual address. */ - size_t info_base_addr; + void *info_base_addr; /** DMA mapped address of the info list */ - size_t info_list_dma; + dma_addr_t info_list_dma; /** Allocated size of info list. */ u32 info_alloc_size; diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_iq.h b/drivers/net/ethernet/cavium/liquidio/octeon_iq.h index 4608a5af35a3..5063a12613e5 100644 --- a/drivers/net/ethernet/cavium/liquidio/octeon_iq.h +++ b/drivers/net/ethernet/cavium/liquidio/octeon_iq.h @@ -152,7 +152,7 @@ struct octeon_instr_queue { struct oct_iq_stats stats; /** DMA mapped base address of the input descriptor ring. */ - u64 base_addr_dma; + dma_addr_t base_addr_dma; /** Application context */ void *app_ctx; diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_main.h b/drivers/net/ethernet/cavium/liquidio/octeon_main.h index aa36e9ae7676..bed9ef17bc26 100644 --- a/drivers/net/ethernet/cavium/liquidio/octeon_main.h +++ b/drivers/net/ethernet/cavium/liquidio/octeon_main.h @@ -140,48 +140,6 @@ err_release_region: return 1; } -static inline void * -cnnic_numa_alloc_aligned_dma(u32 size, - u32 *alloc_size, - size_t *orig_ptr, - int numa_node) -{ - int retries = 0; - void *ptr = NULL; - -#define OCTEON_MAX_ALLOC_RETRIES 1 - do { - struct page *page = NULL; - - page = alloc_pages_node(numa_node, - GFP_KERNEL, - get_order(size)); - if (!page) - page = alloc_pages(GFP_KERNEL, - get_order(size)); - ptr = (void *)page_address(page); - if ((unsigned long)ptr & 0x07) { - __free_pages(page, get_order(size)); - ptr = NULL; - /* Increment the size required if the first - * attempt failed. - */ - if (!retries) - size += 7; - } - retries++; - } while ((retries <= OCTEON_MAX_ALLOC_RETRIES) && !ptr); - - *alloc_size = size; - *orig_ptr = (unsigned long)ptr; - if ((unsigned long)ptr & 0x07) - ptr = (void *)(((unsigned long)ptr + 7) & ~(7UL)); - return ptr; -} - -#define cnnic_free_aligned_dma(pci_dev, ptr, size, orig_ptr, dma_addr) \ - free_pages(orig_ptr, get_order(size)) - static inline int sleep_cond(wait_queue_head_t *wait_queue, int *condition) { diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_network.h b/drivers/net/ethernet/cavium/liquidio/octeon_network.h index 6bb89419006e..eef2a1e8a7e3 100644 --- a/drivers/net/ethernet/cavium/liquidio/octeon_network.h +++ b/drivers/net/ethernet/cavium/liquidio/octeon_network.h @@ -62,6 +62,9 @@ struct lio { /** Array of gather component linked lists */ struct list_head *glist; + void **glists_virt_base; + dma_addr_t *glists_dma_base; + u32 glist_entry_size; /** Pointer to the NIC properties for the Octeon device this network * interface is associated with. @@ -344,6 +347,29 @@ static inline void tx_buffer_free(void *buffer) #define lio_dma_free(oct, size, virt_addr, dma_addr) \ dma_free_coherent(&(oct)->pci_dev->dev, size, virt_addr, dma_addr) +static inline void * +lio_alloc_info_buffer(struct octeon_device *oct, + struct octeon_droq *droq) +{ + void *virt_ptr; + + virt_ptr = lio_dma_alloc(oct, (droq->max_count * OCT_DROQ_INFO_SIZE), + &droq->info_list_dma); + if (virt_ptr) { + droq->info_alloc_size = droq->max_count * OCT_DROQ_INFO_SIZE; + droq->info_base_addr = virt_ptr; + } + + return virt_ptr; +} + +static inline void lio_free_info_buffer(struct octeon_device *oct, + struct octeon_droq *droq) +{ + lio_dma_free(oct, droq->info_alloc_size, droq->info_base_addr, + droq->info_list_dma); +} + static inline void *get_rbd(struct sk_buff *skb) { @@ -359,22 +385,7 @@ void *get_rbd(struct sk_buff *skb) static inline u64 lio_map_ring_info(struct octeon_droq *droq, u32 i) { - dma_addr_t dma_addr; - struct octeon_device *oct = droq->oct_dev; - - dma_addr = dma_map_single(&oct->pci_dev->dev, &droq->info_list[i], - OCT_DROQ_INFO_SIZE, DMA_FROM_DEVICE); - - WARN_ON(dma_mapping_error(&oct->pci_dev->dev, dma_addr)); - - return (u64)dma_addr; -} - -static inline void -lio_unmap_ring_info(struct pci_dev *pci_dev, - u64 info_ptr, u32 size) -{ - dma_unmap_single(&pci_dev->dev, info_ptr, size, DMA_FROM_DEVICE); + return droq->info_list_dma + (i * sizeof(struct octeon_droq_info)); } static inline u64 diff --git a/drivers/net/ethernet/cavium/liquidio/request_manager.c b/drivers/net/ethernet/cavium/liquidio/request_manager.c index 707bc15adec6..261f448f9de2 100644 --- a/drivers/net/ethernet/cavium/liquidio/request_manager.c +++ b/drivers/net/ethernet/cavium/liquidio/request_manager.c @@ -62,8 +62,7 @@ int octeon_init_instr_queue(struct octeon_device *oct, u32 iq_no = (u32)txpciq.s.q_no; u32 q_size; struct cavium_wq *db_wq; - int orig_node = dev_to_node(&oct->pci_dev->dev); - int numa_node = cpu_to_node(iq_no % num_online_cpus()); + int numa_node = dev_to_node(&oct->pci_dev->dev); if (OCTEON_CN6XXX(oct)) conf = &(CFG_GET_IQ_CFG(CHIP_CONF(oct, cn6xxx))); @@ -91,13 +90,7 @@ int octeon_init_instr_queue(struct octeon_device *oct, iq->oct_dev = oct; - set_dev_node(&oct->pci_dev->dev, numa_node); - iq->base_addr = lio_dma_alloc(oct, q_size, - (dma_addr_t *)&iq->base_addr_dma); - set_dev_node(&oct->pci_dev->dev, orig_node); - if (!iq->base_addr) - iq->base_addr = lio_dma_alloc(oct, q_size, - (dma_addr_t *)&iq->base_addr_dma); + iq->base_addr = lio_dma_alloc(oct, q_size, &iq->base_addr_dma); if (!iq->base_addr) { dev_err(&oct->pci_dev->dev, "Cannot allocate memory for instr queue %d\n", iq_no); @@ -211,7 +204,7 @@ int octeon_setup_iq(struct octeon_device *oct, void *app_ctx) { u32 iq_no = (u32)txpciq.s.q_no; - int numa_node = cpu_to_node(iq_no % num_online_cpus()); + int numa_node = dev_to_node(&oct->pci_dev->dev); if (oct->instr_queue[iq_no]) { dev_dbg(&oct->pci_dev->dev, "IQ is in use. Cannot create the IQ: %d again\n", diff --git a/drivers/net/ethernet/cavium/liquidio/response_manager.c b/drivers/net/ethernet/cavium/liquidio/response_manager.c index 2fbaae96b505..1d987d7cd7bd 100644 --- a/drivers/net/ethernet/cavium/liquidio/response_manager.c +++ b/drivers/net/ethernet/cavium/liquidio/response_manager.c @@ -69,41 +69,35 @@ int lio_process_ordered_list(struct octeon_device *octeon_dev, int resp_to_process = MAX_ORD_REQS_TO_PROCESS; u32 status; u64 status64; - struct octeon_instr_rdp *rdp; - u64 rptr; ordered_sc_list = &octeon_dev->response_list[OCTEON_ORDERED_SC_LIST]; do { spin_lock_bh(&ordered_sc_list->lock); - if (ordered_sc_list->head.next == &ordered_sc_list->head) { + if (list_empty(&ordered_sc_list->head)) { spin_unlock_bh(&ordered_sc_list->lock); return 1; } - sc = (struct octeon_soft_command *)ordered_sc_list-> - head.next; - if (OCTEON_CN23XX_PF(octeon_dev) || - OCTEON_CN23XX_VF(octeon_dev)) { - rdp = (struct octeon_instr_rdp *)&sc->cmd.cmd3.rdp; - rptr = sc->cmd.cmd3.rptr; - } else { - rdp = (struct octeon_instr_rdp *)&sc->cmd.cmd2.rdp; - rptr = sc->cmd.cmd2.rptr; - } + sc = list_first_entry(&ordered_sc_list->head, + struct octeon_soft_command, node); status = OCTEON_REQUEST_PENDING; /* check if octeon has finished DMA'ing a response * to where rptr is pointing to */ - dma_sync_single_for_cpu(&octeon_dev->pci_dev->dev, - rptr, rdp->rlen, - DMA_FROM_DEVICE); status64 = *sc->status_word; if (status64 != COMPLETION_WORD_INIT) { + /* This logic ensures that all 64b have been written. + * 1. check byte 0 for non-FF + * 2. if non-FF, then swap result from BE to host order + * 3. check byte 7 (swapped to 0) for non-FF + * 4. if non-FF, use the low 32-bit status code + * 5. if either byte 0 or byte 7 is FF, don't use status + */ if ((status64 & 0xff) != 0xff) { octeon_swap_8B_data(&status64, 1); if (((status64 & 0xff) != 0xff)) { diff --git a/drivers/net/ethernet/cavium/thunder/nic.h b/drivers/net/ethernet/cavium/thunder/nic.h index e739c7153562..2269ff562d95 100644 --- a/drivers/net/ethernet/cavium/thunder/nic.h +++ b/drivers/net/ethernet/cavium/thunder/nic.h @@ -269,6 +269,7 @@ struct nicvf { #define MAX_QUEUES_PER_QSET 8 struct queue_set *qs; struct nicvf_cq_poll *napi[8]; + void *iommu_domain; u8 vf_id; u8 sqs_id; bool sqs_mode; diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_main.c b/drivers/net/ethernet/cavium/thunder/nicvf_main.c index 6feaa24bcfd4..24017588f531 100644 --- a/drivers/net/ethernet/cavium/thunder/nicvf_main.c +++ b/drivers/net/ethernet/cavium/thunder/nicvf_main.c @@ -16,6 +16,7 @@ #include <linux/log2.h> #include <linux/prefetch.h> #include <linux/irq.h> +#include <linux/iommu.h> #include "nic_reg.h" #include "nic.h" @@ -525,7 +526,12 @@ static void nicvf_snd_pkt_handler(struct net_device *netdev, /* Get actual TSO descriptors and free them */ tso_sqe = (struct sq_hdr_subdesc *)GET_SQ_DESC(sq, hdr->rsvd2); + nicvf_unmap_sndq_buffers(nic, sq, hdr->rsvd2, + tso_sqe->subdesc_cnt); nicvf_put_sq_desc(sq, tso_sqe->subdesc_cnt + 1); + } else { + nicvf_unmap_sndq_buffers(nic, sq, cqe_tx->sqe_ptr, + hdr->subdesc_cnt); } nicvf_put_sq_desc(sq, hdr->subdesc_cnt + 1); prefetch(skb); @@ -576,6 +582,7 @@ static void nicvf_rcv_pkt_handler(struct net_device *netdev, { struct sk_buff *skb; struct nicvf *nic = netdev_priv(netdev); + struct nicvf *snic = nic; int err = 0; int rq_idx; @@ -592,7 +599,7 @@ static void nicvf_rcv_pkt_handler(struct net_device *netdev, if (err && !cqe_rx->rb_cnt) return; - skb = nicvf_get_rcv_skb(nic, cqe_rx); + skb = nicvf_get_rcv_skb(snic, cqe_rx); if (!skb) { netdev_dbg(nic->netdev, "Packet not received\n"); return; @@ -1643,6 +1650,9 @@ static int nicvf_probe(struct pci_dev *pdev, const struct pci_device_id *ent) if (!pass1_silicon(nic->pdev)) nic->hw_tso = true; + /* Get iommu domain for iova to physical addr conversion */ + nic->iommu_domain = iommu_get_domain_for_dev(dev); + pci_read_config_word(nic->pdev, PCI_SUBSYSTEM_ID, &sdevid); if (sdevid == 0xA134) nic->t88 = true; diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_queues.c b/drivers/net/ethernet/cavium/thunder/nicvf_queues.c index ac0390be3b12..f13289f0d238 100644 --- a/drivers/net/ethernet/cavium/thunder/nicvf_queues.c +++ b/drivers/net/ethernet/cavium/thunder/nicvf_queues.c @@ -10,6 +10,7 @@ #include <linux/netdevice.h> #include <linux/ip.h> #include <linux/etherdevice.h> +#include <linux/iommu.h> #include <net/ip.h> #include <net/tso.h> @@ -18,6 +19,16 @@ #include "q_struct.h" #include "nicvf_queues.h" +#define NICVF_PAGE_ORDER ((PAGE_SIZE <= 4096) ? PAGE_ALLOC_COSTLY_ORDER : 0) + +static inline u64 nicvf_iova_to_phys(struct nicvf *nic, dma_addr_t dma_addr) +{ + /* Translation is installed only when IOMMU is present */ + if (nic->iommu_domain) + return iommu_iova_to_phys(nic->iommu_domain, dma_addr); + return dma_addr; +} + static void nicvf_get_page(struct nicvf *nic) { if (!nic->rb_pageref || !nic->rb_page) @@ -87,7 +98,7 @@ static void nicvf_free_q_desc_mem(struct nicvf *nic, struct q_desc_mem *dmem) static inline int nicvf_alloc_rcv_buffer(struct nicvf *nic, gfp_t gfp, u32 buf_len, u64 **rbuf) { - int order = (PAGE_SIZE <= 4096) ? PAGE_ALLOC_COSTLY_ORDER : 0; + int order = NICVF_PAGE_ORDER; /* Check if request can be accomodated in previous allocated page */ if (nic->rb_page && @@ -97,22 +108,27 @@ static inline int nicvf_alloc_rcv_buffer(struct nicvf *nic, gfp_t gfp, } nicvf_get_page(nic); - nic->rb_page = NULL; /* Allocate a new page */ + nic->rb_page = alloc_pages(gfp | __GFP_COMP | __GFP_NOWARN, + order); if (!nic->rb_page) { - nic->rb_page = alloc_pages(gfp | __GFP_COMP | __GFP_NOWARN, - order); - if (!nic->rb_page) { - this_cpu_inc(nic->pnicvf->drv_stats-> - rcv_buffer_alloc_failures); - return -ENOMEM; - } - nic->rb_page_offset = 0; + this_cpu_inc(nic->pnicvf->drv_stats->rcv_buffer_alloc_failures); + return -ENOMEM; } - + nic->rb_page_offset = 0; ret: - *rbuf = (u64 *)((u64)page_address(nic->rb_page) + nic->rb_page_offset); + /* HW will ensure data coherency, CPU sync not required */ + *rbuf = (u64 *)((u64)dma_map_page_attrs(&nic->pdev->dev, nic->rb_page, + nic->rb_page_offset, buf_len, + DMA_FROM_DEVICE, + DMA_ATTR_SKIP_CPU_SYNC)); + if (dma_mapping_error(&nic->pdev->dev, (dma_addr_t)*rbuf)) { + if (!nic->rb_page_offset) + __free_pages(nic->rb_page, order); + nic->rb_page = NULL; + return -ENOMEM; + } nic->rb_page_offset += buf_len; return 0; @@ -158,16 +174,21 @@ static int nicvf_init_rbdr(struct nicvf *nic, struct rbdr *rbdr, rbdr->dma_size = buf_size; rbdr->enable = true; rbdr->thresh = RBDR_THRESH; + rbdr->head = 0; + rbdr->tail = 0; nic->rb_page = NULL; for (idx = 0; idx < ring_len; idx++) { err = nicvf_alloc_rcv_buffer(nic, GFP_KERNEL, RCV_FRAG_LEN, &rbuf); - if (err) + if (err) { + /* To free already allocated and mapped ones */ + rbdr->tail = idx - 1; return err; + } desc = GET_RBDR_DESC(rbdr, idx); - desc->buf_addr = virt_to_phys(rbuf) >> NICVF_RCV_BUF_ALIGN; + desc->buf_addr = (u64)rbuf >> NICVF_RCV_BUF_ALIGN; } nicvf_get_page(nic); @@ -179,7 +200,7 @@ static int nicvf_init_rbdr(struct nicvf *nic, struct rbdr *rbdr, static void nicvf_free_rbdr(struct nicvf *nic, struct rbdr *rbdr) { int head, tail; - u64 buf_addr; + u64 buf_addr, phys_addr; struct rbdr_entry_t *desc; if (!rbdr) @@ -192,18 +213,26 @@ static void nicvf_free_rbdr(struct nicvf *nic, struct rbdr *rbdr) head = rbdr->head; tail = rbdr->tail; - /* Free SKBs */ + /* Release page references */ while (head != tail) { desc = GET_RBDR_DESC(rbdr, head); - buf_addr = desc->buf_addr << NICVF_RCV_BUF_ALIGN; - put_page(virt_to_page(phys_to_virt(buf_addr))); + buf_addr = ((u64)desc->buf_addr) << NICVF_RCV_BUF_ALIGN; + phys_addr = nicvf_iova_to_phys(nic, buf_addr); + dma_unmap_page_attrs(&nic->pdev->dev, buf_addr, RCV_FRAG_LEN, + DMA_FROM_DEVICE, DMA_ATTR_SKIP_CPU_SYNC); + if (phys_addr) + put_page(virt_to_page(phys_to_virt(phys_addr))); head++; head &= (rbdr->dmem.q_len - 1); } - /* Free SKB of tail desc */ + /* Release buffer of tail desc */ desc = GET_RBDR_DESC(rbdr, tail); - buf_addr = desc->buf_addr << NICVF_RCV_BUF_ALIGN; - put_page(virt_to_page(phys_to_virt(buf_addr))); + buf_addr = ((u64)desc->buf_addr) << NICVF_RCV_BUF_ALIGN; + phys_addr = nicvf_iova_to_phys(nic, buf_addr); + dma_unmap_page_attrs(&nic->pdev->dev, buf_addr, RCV_FRAG_LEN, + DMA_FROM_DEVICE, DMA_ATTR_SKIP_CPU_SYNC); + if (phys_addr) + put_page(virt_to_page(phys_to_virt(phys_addr))); /* Free RBDR ring */ nicvf_free_q_desc_mem(nic, &rbdr->dmem); @@ -250,7 +279,7 @@ refill: break; desc = GET_RBDR_DESC(rbdr, tail); - desc->buf_addr = virt_to_phys(rbuf) >> NICVF_RCV_BUF_ALIGN; + desc->buf_addr = (u64)rbuf >> NICVF_RCV_BUF_ALIGN; refill_rb_cnt--; new_rb++; } @@ -361,9 +390,29 @@ static int nicvf_init_snd_queue(struct nicvf *nic, return 0; } +void nicvf_unmap_sndq_buffers(struct nicvf *nic, struct snd_queue *sq, + int hdr_sqe, u8 subdesc_cnt) +{ + u8 idx; + struct sq_gather_subdesc *gather; + + /* Unmap DMA mapped skb data buffers */ + for (idx = 0; idx < subdesc_cnt; idx++) { + hdr_sqe++; + hdr_sqe &= (sq->dmem.q_len - 1); + gather = (struct sq_gather_subdesc *)GET_SQ_DESC(sq, hdr_sqe); + /* HW will ensure data coherency, CPU sync not required */ + dma_unmap_page_attrs(&nic->pdev->dev, gather->addr, + gather->size, DMA_TO_DEVICE, + DMA_ATTR_SKIP_CPU_SYNC); + } +} + static void nicvf_free_snd_queue(struct nicvf *nic, struct snd_queue *sq) { struct sk_buff *skb; + struct sq_hdr_subdesc *hdr; + struct sq_hdr_subdesc *tso_sqe; if (!sq) return; @@ -379,8 +428,22 @@ static void nicvf_free_snd_queue(struct nicvf *nic, struct snd_queue *sq) smp_rmb(); while (sq->head != sq->tail) { skb = (struct sk_buff *)sq->skbuff[sq->head]; - if (skb) - dev_kfree_skb_any(skb); + if (!skb) + goto next; + hdr = (struct sq_hdr_subdesc *)GET_SQ_DESC(sq, sq->head); + /* Check for dummy descriptor used for HW TSO offload on 88xx */ + if (hdr->dont_send) { + /* Get actual TSO descriptors and unmap them */ + tso_sqe = + (struct sq_hdr_subdesc *)GET_SQ_DESC(sq, hdr->rsvd2); + nicvf_unmap_sndq_buffers(nic, sq, hdr->rsvd2, + tso_sqe->subdesc_cnt); + } else { + nicvf_unmap_sndq_buffers(nic, sq, sq->head, + hdr->subdesc_cnt); + } + dev_kfree_skb_any(skb); +next: sq->head++; sq->head &= (sq->dmem.q_len - 1); } @@ -559,9 +622,11 @@ static void nicvf_rcv_queue_config(struct nicvf *nic, struct queue_set *qs, nicvf_send_msg_to_pf(nic, &mbx); if (!nic->sqs_mode && (qidx == 0)) { - /* Enable checking L3/L4 length and TCP/UDP checksums */ + /* Enable checking L3/L4 length and TCP/UDP checksums + * Also allow IPv6 pkts with zero UDP checksum. + */ nicvf_queue_reg_write(nic, NIC_QSET_RQ_GEN_CFG, 0, - (BIT(24) | BIT(23) | BIT(21))); + (BIT(24) | BIT(23) | BIT(21) | BIT(20))); nicvf_config_vlan_stripping(nic, nic->netdev->features); } @@ -882,6 +947,14 @@ static inline int nicvf_get_sq_desc(struct snd_queue *sq, int desc_cnt) return qentry; } +/* Rollback to previous tail pointer when descriptors not used */ +static inline void nicvf_rollback_sq_desc(struct snd_queue *sq, + int qentry, int desc_cnt) +{ + sq->tail = qentry; + atomic_add(desc_cnt, &sq->free_cnt); +} + /* Free descriptor back to SQ for future use */ void nicvf_put_sq_desc(struct snd_queue *sq, int desc_cnt) { @@ -1207,8 +1280,9 @@ int nicvf_sq_append_skb(struct nicvf *nic, struct snd_queue *sq, struct sk_buff *skb, u8 sq_num) { int i, size; - int subdesc_cnt, tso_sqe = 0; + int subdesc_cnt, hdr_sqe = 0; int qentry; + u64 dma_addr; subdesc_cnt = nicvf_sq_subdesc_required(nic, skb); if (subdesc_cnt > atomic_read(&sq->free_cnt)) @@ -1223,12 +1297,21 @@ int nicvf_sq_append_skb(struct nicvf *nic, struct snd_queue *sq, /* Add SQ header subdesc */ nicvf_sq_add_hdr_subdesc(nic, sq, qentry, subdesc_cnt - 1, skb, skb->len); - tso_sqe = qentry; + hdr_sqe = qentry; /* Add SQ gather subdescs */ qentry = nicvf_get_nxt_sqentry(sq, qentry); size = skb_is_nonlinear(skb) ? skb_headlen(skb) : skb->len; - nicvf_sq_add_gather_subdesc(sq, qentry, size, virt_to_phys(skb->data)); + /* HW will ensure data coherency, CPU sync not required */ + dma_addr = dma_map_page_attrs(&nic->pdev->dev, virt_to_page(skb->data), + offset_in_page(skb->data), size, + DMA_TO_DEVICE, DMA_ATTR_SKIP_CPU_SYNC); + if (dma_mapping_error(&nic->pdev->dev, dma_addr)) { + nicvf_rollback_sq_desc(sq, qentry, subdesc_cnt); + return 0; + } + + nicvf_sq_add_gather_subdesc(sq, qentry, size, dma_addr); /* Check for scattered buffer */ if (!skb_is_nonlinear(skb)) @@ -1241,15 +1324,26 @@ int nicvf_sq_append_skb(struct nicvf *nic, struct snd_queue *sq, qentry = nicvf_get_nxt_sqentry(sq, qentry); size = skb_frag_size(frag); - nicvf_sq_add_gather_subdesc(sq, qentry, size, - virt_to_phys( - skb_frag_address(frag))); + dma_addr = dma_map_page_attrs(&nic->pdev->dev, + skb_frag_page(frag), + frag->page_offset, size, + DMA_TO_DEVICE, + DMA_ATTR_SKIP_CPU_SYNC); + if (dma_mapping_error(&nic->pdev->dev, dma_addr)) { + /* Free entire chain of mapped buffers + * here 'i' = frags mapped + above mapped skb->data + */ + nicvf_unmap_sndq_buffers(nic, sq, hdr_sqe, i); + nicvf_rollback_sq_desc(sq, qentry, subdesc_cnt); + return 0; + } + nicvf_sq_add_gather_subdesc(sq, qentry, size, dma_addr); } doorbell: if (nic->t88 && skb_shinfo(skb)->gso_size) { qentry = nicvf_get_nxt_sqentry(sq, qentry); - nicvf_sq_add_cqe_subdesc(sq, qentry, tso_sqe, skb); + nicvf_sq_add_cqe_subdesc(sq, qentry, hdr_sqe, skb); } nicvf_sq_doorbell(nic, skb, sq_num, subdesc_cnt); @@ -1282,6 +1376,7 @@ struct sk_buff *nicvf_get_rcv_skb(struct nicvf *nic, struct cqe_rx_t *cqe_rx) int offset; u16 *rb_lens = NULL; u64 *rb_ptrs = NULL; + u64 phys_addr; rb_lens = (void *)cqe_rx + (3 * sizeof(u64)); /* Except 88xx pass1 on all other chips CQE_RX2_S is added to @@ -1296,15 +1391,23 @@ struct sk_buff *nicvf_get_rcv_skb(struct nicvf *nic, struct cqe_rx_t *cqe_rx) else rb_ptrs = (void *)cqe_rx + (7 * sizeof(u64)); - netdev_dbg(nic->netdev, "%s rb_cnt %d rb0_ptr %llx rb0_sz %d\n", - __func__, cqe_rx->rb_cnt, cqe_rx->rb0_ptr, cqe_rx->rb0_sz); - for (frag = 0; frag < cqe_rx->rb_cnt; frag++) { payload_len = rb_lens[frag_num(frag)]; + phys_addr = nicvf_iova_to_phys(nic, *rb_ptrs); + if (!phys_addr) { + if (skb) + dev_kfree_skb_any(skb); + return NULL; + } + if (!frag) { /* First fragment */ + dma_unmap_page_attrs(&nic->pdev->dev, + *rb_ptrs - cqe_rx->align_pad, + RCV_FRAG_LEN, DMA_FROM_DEVICE, + DMA_ATTR_SKIP_CPU_SYNC); skb = nicvf_rb_ptr_to_skb(nic, - *rb_ptrs - cqe_rx->align_pad, + phys_addr - cqe_rx->align_pad, payload_len); if (!skb) return NULL; @@ -1312,8 +1415,11 @@ struct sk_buff *nicvf_get_rcv_skb(struct nicvf *nic, struct cqe_rx_t *cqe_rx) skb_put(skb, payload_len); } else { /* Add fragments */ - page = virt_to_page(phys_to_virt(*rb_ptrs)); - offset = phys_to_virt(*rb_ptrs) - page_address(page); + dma_unmap_page_attrs(&nic->pdev->dev, *rb_ptrs, + RCV_FRAG_LEN, DMA_FROM_DEVICE, + DMA_ATTR_SKIP_CPU_SYNC); + page = virt_to_page(phys_to_virt(phys_addr)); + offset = phys_to_virt(phys_addr) - page_address(page); skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, page, offset, payload_len, RCV_FRAG_LEN); } diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_queues.h b/drivers/net/ethernet/cavium/thunder/nicvf_queues.h index 5cb84da99a2d..10cb4b84625b 100644 --- a/drivers/net/ethernet/cavium/thunder/nicvf_queues.h +++ b/drivers/net/ethernet/cavium/thunder/nicvf_queues.h @@ -87,7 +87,7 @@ #define RCV_BUF_COUNT (1ULL << (RBDR_SIZE + 13)) #define MAX_RCV_BUF_COUNT (1ULL << (RBDR_SIZE6 + 13)) #define RBDR_THRESH (RCV_BUF_COUNT / 2) -#define DMA_BUFFER_LEN 2048 /* In multiples of 128bytes */ +#define DMA_BUFFER_LEN 1536 /* In multiples of 128bytes */ #define RCV_FRAG_LEN (SKB_DATA_ALIGN(DMA_BUFFER_LEN + NET_SKB_PAD) + \ SKB_DATA_ALIGN(sizeof(struct skb_shared_info))) @@ -301,6 +301,8 @@ struct queue_set { #define CQ_ERR_MASK (CQ_WR_FULL | CQ_WR_DISABLE | CQ_WR_FAULT) +void nicvf_unmap_sndq_buffers(struct nicvf *nic, struct snd_queue *sq, + int hdr_sqe, u8 subdesc_cnt); void nicvf_config_vlan_stripping(struct nicvf *nic, netdev_features_t features); int nicvf_set_qset_resources(struct nicvf *nic); diff --git a/drivers/net/ethernet/cavium/thunder/thunder_bgx.c b/drivers/net/ethernet/cavium/thunder/thunder_bgx.c index 4c8e8cf730bb..64a1095e4d14 100644 --- a/drivers/net/ethernet/cavium/thunder/thunder_bgx.c +++ b/drivers/net/ethernet/cavium/thunder/thunder_bgx.c @@ -123,14 +123,44 @@ static int bgx_poll_reg(struct bgx *bgx, u8 lmac, u64 reg, u64 mask, bool zero) return 1; } +static int max_bgx_per_node; +static void set_max_bgx_per_node(struct pci_dev *pdev) +{ + u16 sdevid; + + if (max_bgx_per_node) + return; + + pci_read_config_word(pdev, PCI_SUBSYSTEM_ID, &sdevid); + switch (sdevid) { + case PCI_SUBSYS_DEVID_81XX_BGX: + max_bgx_per_node = MAX_BGX_PER_CN81XX; + break; + case PCI_SUBSYS_DEVID_83XX_BGX: + max_bgx_per_node = MAX_BGX_PER_CN83XX; + break; + case PCI_SUBSYS_DEVID_88XX_BGX: + default: + max_bgx_per_node = MAX_BGX_PER_CN88XX; + break; + } +} + +static struct bgx *get_bgx(int node, int bgx_idx) +{ + int idx = (node * max_bgx_per_node) + bgx_idx; + + return bgx_vnic[idx]; +} + /* Return number of BGX present in HW */ unsigned bgx_get_map(int node) { int i; unsigned map = 0; - for (i = 0; i < MAX_BGX_PER_NODE; i++) { - if (bgx_vnic[(node * MAX_BGX_PER_NODE) + i]) + for (i = 0; i < max_bgx_per_node; i++) { + if (bgx_vnic[(node * max_bgx_per_node) + i]) map |= (1 << i); } @@ -143,7 +173,7 @@ int bgx_get_lmac_count(int node, int bgx_idx) { struct bgx *bgx; - bgx = bgx_vnic[(node * MAX_BGX_PER_NODE) + bgx_idx]; + bgx = get_bgx(node, bgx_idx); if (bgx) return bgx->lmac_count; @@ -158,7 +188,7 @@ void bgx_get_lmac_link_state(int node, int bgx_idx, int lmacid, void *status) struct bgx *bgx; struct lmac *lmac; - bgx = bgx_vnic[(node * MAX_BGX_PER_NODE) + bgx_idx]; + bgx = get_bgx(node, bgx_idx); if (!bgx) return; @@ -172,7 +202,7 @@ EXPORT_SYMBOL(bgx_get_lmac_link_state); const u8 *bgx_get_lmac_mac(int node, int bgx_idx, int lmacid) { - struct bgx *bgx = bgx_vnic[(node * MAX_BGX_PER_NODE) + bgx_idx]; + struct bgx *bgx = get_bgx(node, bgx_idx); if (bgx) return bgx->lmac[lmacid].mac; @@ -183,7 +213,7 @@ EXPORT_SYMBOL(bgx_get_lmac_mac); void bgx_set_lmac_mac(int node, int bgx_idx, int lmacid, const u8 *mac) { - struct bgx *bgx = bgx_vnic[(node * MAX_BGX_PER_NODE) + bgx_idx]; + struct bgx *bgx = get_bgx(node, bgx_idx); if (!bgx) return; @@ -194,7 +224,7 @@ EXPORT_SYMBOL(bgx_set_lmac_mac); void bgx_lmac_rx_tx_enable(int node, int bgx_idx, int lmacid, bool enable) { - struct bgx *bgx = bgx_vnic[(node * MAX_BGX_PER_NODE) + bgx_idx]; + struct bgx *bgx = get_bgx(node, bgx_idx); struct lmac *lmac; u64 cfg; @@ -217,7 +247,7 @@ EXPORT_SYMBOL(bgx_lmac_rx_tx_enable); void bgx_lmac_get_pfc(int node, int bgx_idx, int lmacid, void *pause) { struct pfc *pfc = (struct pfc *)pause; - struct bgx *bgx = bgx_vnic[(node * MAX_BGX_PER_CN88XX) + bgx_idx]; + struct bgx *bgx = get_bgx(node, bgx_idx); struct lmac *lmac; u64 cfg; @@ -237,7 +267,7 @@ EXPORT_SYMBOL(bgx_lmac_get_pfc); void bgx_lmac_set_pfc(int node, int bgx_idx, int lmacid, void *pause) { struct pfc *pfc = (struct pfc *)pause; - struct bgx *bgx = bgx_vnic[(node * MAX_BGX_PER_CN88XX) + bgx_idx]; + struct bgx *bgx = get_bgx(node, bgx_idx); struct lmac *lmac; u64 cfg; @@ -369,7 +399,7 @@ u64 bgx_get_rx_stats(int node, int bgx_idx, int lmac, int idx) { struct bgx *bgx; - bgx = bgx_vnic[(node * MAX_BGX_PER_NODE) + bgx_idx]; + bgx = get_bgx(node, bgx_idx); if (!bgx) return 0; @@ -383,7 +413,7 @@ u64 bgx_get_tx_stats(int node, int bgx_idx, int lmac, int idx) { struct bgx *bgx; - bgx = bgx_vnic[(node * MAX_BGX_PER_NODE) + bgx_idx]; + bgx = get_bgx(node, bgx_idx); if (!bgx) return 0; @@ -411,7 +441,7 @@ void bgx_lmac_internal_loopback(int node, int bgx_idx, struct lmac *lmac; u64 cfg; - bgx = bgx_vnic[(node * MAX_BGX_PER_NODE) + bgx_idx]; + bgx = get_bgx(node, bgx_idx); if (!bgx) return; @@ -1011,12 +1041,6 @@ static void bgx_print_qlm_mode(struct bgx *bgx, u8 lmacid) dev_info(dev, "%s: 40G_KR4\n", (char *)str); break; case BGX_MODE_QSGMII: - if ((lmacid == 0) && - (bgx_get_lane2sds_cfg(bgx, lmac) != lmacid)) - return; - if ((lmacid == 2) && - (bgx_get_lane2sds_cfg(bgx, lmac) == lmacid)) - return; dev_info(dev, "%s: QSGMII\n", (char *)str); break; case BGX_MODE_RGMII: @@ -1334,11 +1358,13 @@ static int bgx_probe(struct pci_dev *pdev, const struct pci_device_id *ent) goto err_release_regions; } + set_max_bgx_per_node(pdev); + pci_read_config_word(pdev, PCI_DEVICE_ID, &sdevid); if (sdevid != PCI_DEVICE_ID_THUNDER_RGX) { bgx->bgx_id = (pci_resource_start(pdev, PCI_CFG_REG_BAR_NUM) >> 24) & BGX_ID_MASK; - bgx->bgx_id += nic_get_node_id(pdev) * MAX_BGX_PER_NODE; + bgx->bgx_id += nic_get_node_id(pdev) * max_bgx_per_node; bgx->max_lmac = MAX_LMAC_PER_BGX; bgx_vnic[bgx->bgx_id] = bgx; } else { diff --git a/drivers/net/ethernet/cavium/thunder/thunder_bgx.h b/drivers/net/ethernet/cavium/thunder/thunder_bgx.h index a60f189429bb..c5080f2cead5 100644 --- a/drivers/net/ethernet/cavium/thunder/thunder_bgx.h +++ b/drivers/net/ethernet/cavium/thunder/thunder_bgx.h @@ -22,7 +22,6 @@ #define MAX_BGX_PER_CN88XX 2 #define MAX_BGX_PER_CN81XX 3 /* 2 BGXs + 1 RGX */ #define MAX_BGX_PER_CN83XX 4 -#define MAX_BGX_PER_NODE 4 #define MAX_LMAC_PER_BGX 4 #define MAX_BGX_CHANS_PER_LMAC 16 #define MAX_DMAC_PER_LMAC 8 diff --git a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c index e2ca107f9d94..d4bb8bf86a45 100644 --- a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c +++ b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c @@ -137,6 +137,13 @@ MODULE_PARM_DESC(tx_timeout, "The Tx timeout in ms"); /* L4 Type field: TCP */ #define FM_L4_PARSE_RESULT_TCP 0x20 +/* FD status field indicating whether the FM Parser has attempted to validate + * the L4 csum of the frame. + * Note that having this bit set doesn't necessarily imply that the checksum + * is valid. One would have to check the parse results to find that out. + */ +#define FM_FD_STAT_L4CV 0x00000004 + #define DPAA_SGT_MAX_ENTRIES 16 /* maximum number of entries in SG Table */ #define DPAA_BUFF_RELEASE_MAX 8 /* maximum number of buffers released at once */ @@ -235,6 +242,7 @@ static int dpaa_netdev_init(struct net_device *net_dev, * For conformity, we'll still declare GSO explicitly. */ net_dev->features |= NETIF_F_GSO; + net_dev->features |= NETIF_F_RXCSUM; net_dev->priv_flags |= IFF_LIVE_ADDR_CHANGE; /* we do not want shared skbs on TX */ @@ -334,6 +342,45 @@ static void dpaa_get_stats64(struct net_device *net_dev, } } +static int dpaa_setup_tc(struct net_device *net_dev, u32 handle, __be16 proto, + struct tc_to_netdev *tc) +{ + struct dpaa_priv *priv = netdev_priv(net_dev); + u8 num_tc; + int i; + + if (tc->type != TC_SETUP_MQPRIO) + return -EINVAL; + + tc->mqprio->hw = TC_MQPRIO_HW_OFFLOAD_TCS; + num_tc = tc->mqprio->num_tc; + + if (num_tc == priv->num_tc) + return 0; + + if (!num_tc) { + netdev_reset_tc(net_dev); + goto out; + } + + if (num_tc > DPAA_TC_NUM) { + netdev_err(net_dev, "Too many traffic classes: max %d supported.\n", + DPAA_TC_NUM); + return -EINVAL; + } + + netdev_set_num_tc(net_dev, num_tc); + + for (i = 0; i < num_tc; i++) + netdev_set_tc_queue(net_dev, i, DPAA_TC_TXQ_NUM, + i * DPAA_TC_TXQ_NUM); + +out: + priv->num_tc = num_tc ? : 1; + netif_set_real_num_tx_queues(net_dev, priv->num_tc * DPAA_TC_TXQ_NUM); + return 0; +} + static struct mac_device *dpaa_mac_dev_get(struct platform_device *pdev) { struct platform_device *of_dev; @@ -557,16 +604,18 @@ static void dpaa_bps_free(struct dpaa_priv *priv) /* Use multiple WQs for FQ assignment: * - Tx Confirmation queues go to WQ1. - * - Rx Error and Tx Error queues go to WQ2 (giving them a better chance - * to be scheduled, in case there are many more FQs in WQ3). - * - Rx Default and Tx queues go to WQ3 (no differentiation between - * Rx and Tx traffic). + * - Rx Error and Tx Error queues go to WQ5 (giving them a better chance + * to be scheduled, in case there are many more FQs in WQ6). + * - Rx Default goes to WQ6. + * - Tx queues go to different WQs depending on their priority. Equal + * chunks of NR_CPUS queues go to WQ6 (lowest priority), WQ2, WQ1 and + * WQ0 (highest priority). * This ensures that Tx-confirmed buffers are timely released. In particular, * it avoids congestion on the Tx Confirm FQs, which can pile up PFDRs if they * are greatly outnumbered by other FQs in the system, while * dequeue scheduling is round-robin. */ -static inline void dpaa_assign_wq(struct dpaa_fq *fq) +static inline void dpaa_assign_wq(struct dpaa_fq *fq, int idx) { switch (fq->fq_type) { case FQ_TYPE_TX_CONFIRM: @@ -575,11 +624,33 @@ static inline void dpaa_assign_wq(struct dpaa_fq *fq) break; case FQ_TYPE_RX_ERROR: case FQ_TYPE_TX_ERROR: - fq->wq = 2; + fq->wq = 5; break; case FQ_TYPE_RX_DEFAULT: + fq->wq = 6; + break; case FQ_TYPE_TX: - fq->wq = 3; + switch (idx / DPAA_TC_TXQ_NUM) { + case 0: + /* Low priority (best effort) */ + fq->wq = 6; + break; + case 1: + /* Medium priority */ + fq->wq = 2; + break; + case 2: + /* High priority */ + fq->wq = 1; + break; + case 3: + /* Very high priority */ + fq->wq = 0; + break; + default: + WARN(1, "Too many TX FQs: more than %d!\n", + DPAA_ETH_TXQ_NUM); + } break; default: WARN(1, "Invalid FQ type %d for FQID %d!\n", @@ -607,7 +678,7 @@ static struct dpaa_fq *dpaa_fq_alloc(struct device *dev, } for (i = 0; i < count; i++) - dpaa_assign_wq(dpaa_fq + i); + dpaa_assign_wq(dpaa_fq + i, i); return dpaa_fq; } @@ -985,7 +1056,8 @@ static int dpaa_fq_init(struct dpaa_fq *dpaa_fq, bool td_enable) /* Initialization common to all ingress queues */ if (dpaa_fq->flags & QMAN_FQ_FLAG_NO_ENQUEUE) { initfq.we_mask |= cpu_to_be16(QM_INITFQ_WE_CONTEXTA); - initfq.fqd.fq_ctrl |= cpu_to_be16(QM_FQCTRL_HOLDACTIVE); + initfq.fqd.fq_ctrl |= cpu_to_be16(QM_FQCTRL_HOLDACTIVE | + QM_FQCTRL_CTXASTASHING); initfq.fqd.context_a.stashing.exclusive = QM_STASHING_EXCL_DATA | QM_STASHING_EXCL_CTX | QM_STASHING_EXCL_ANNOTATION; @@ -1055,9 +1127,9 @@ static int dpaa_fq_free(struct device *dev, struct list_head *list) return err; } -static void dpaa_eth_init_tx_port(struct fman_port *port, struct dpaa_fq *errq, - struct dpaa_fq *defq, - struct dpaa_buffer_layout *buf_layout) +static int dpaa_eth_init_tx_port(struct fman_port *port, struct dpaa_fq *errq, + struct dpaa_fq *defq, + struct dpaa_buffer_layout *buf_layout) { struct fman_buffer_prefix_content buf_prefix_content; struct fman_port_params params; @@ -1076,23 +1148,29 @@ static void dpaa_eth_init_tx_port(struct fman_port *port, struct dpaa_fq *errq, params.specific_params.non_rx_params.dflt_fqid = defq->fqid; err = fman_port_config(port, ¶ms); - if (err) + if (err) { pr_err("%s: fman_port_config failed\n", __func__); + return err; + } err = fman_port_cfg_buf_prefix_content(port, &buf_prefix_content); - if (err) + if (err) { pr_err("%s: fman_port_cfg_buf_prefix_content failed\n", __func__); + return err; + } err = fman_port_init(port); if (err) pr_err("%s: fm_port_init failed\n", __func__); + + return err; } -static void dpaa_eth_init_rx_port(struct fman_port *port, struct dpaa_bp **bps, - size_t count, struct dpaa_fq *errq, - struct dpaa_fq *defq, - struct dpaa_buffer_layout *buf_layout) +static int dpaa_eth_init_rx_port(struct fman_port *port, struct dpaa_bp **bps, + size_t count, struct dpaa_fq *errq, + struct dpaa_fq *defq, + struct dpaa_buffer_layout *buf_layout) { struct fman_buffer_prefix_content buf_prefix_content; struct fman_port_rx_params *rx_p; @@ -1120,32 +1198,44 @@ static void dpaa_eth_init_rx_port(struct fman_port *port, struct dpaa_bp **bps, } err = fman_port_config(port, ¶ms); - if (err) + if (err) { pr_err("%s: fman_port_config failed\n", __func__); + return err; + } err = fman_port_cfg_buf_prefix_content(port, &buf_prefix_content); - if (err) + if (err) { pr_err("%s: fman_port_cfg_buf_prefix_content failed\n", __func__); + return err; + } err = fman_port_init(port); if (err) pr_err("%s: fm_port_init failed\n", __func__); + + return err; } -static void dpaa_eth_init_ports(struct mac_device *mac_dev, - struct dpaa_bp **bps, size_t count, - struct fm_port_fqs *port_fqs, - struct dpaa_buffer_layout *buf_layout, - struct device *dev) +static int dpaa_eth_init_ports(struct mac_device *mac_dev, + struct dpaa_bp **bps, size_t count, + struct fm_port_fqs *port_fqs, + struct dpaa_buffer_layout *buf_layout, + struct device *dev) { struct fman_port *rxport = mac_dev->port[RX]; struct fman_port *txport = mac_dev->port[TX]; + int err; + + err = dpaa_eth_init_tx_port(txport, port_fqs->tx_errq, + port_fqs->tx_defq, &buf_layout[TX]); + if (err) + return err; + + err = dpaa_eth_init_rx_port(rxport, bps, count, port_fqs->rx_errq, + port_fqs->rx_defq, &buf_layout[RX]); - dpaa_eth_init_tx_port(txport, port_fqs->tx_errq, - port_fqs->tx_defq, &buf_layout[TX]); - dpaa_eth_init_rx_port(rxport, bps, count, port_fqs->rx_errq, - port_fqs->rx_defq, &buf_layout[RX]); + return err; } static int dpaa_bman_release(const struct dpaa_bp *dpaa_bp, @@ -1526,6 +1616,23 @@ static struct sk_buff *dpaa_cleanup_tx_fd(const struct dpaa_priv *priv, return skb; } +static u8 rx_csum_offload(const struct dpaa_priv *priv, const struct qm_fd *fd) +{ + /* The parser has run and performed L4 checksum validation. + * We know there were no parser errors (and implicitly no + * L4 csum error), otherwise we wouldn't be here. + */ + if ((priv->net_dev->features & NETIF_F_RXCSUM) && + (be32_to_cpu(fd->status) & FM_FD_STAT_L4CV)) + return CHECKSUM_UNNECESSARY; + + /* We're here because either the parser didn't run or the L4 checksum + * was not verified. This may include the case of a UDP frame with + * checksum zero or an L4 proto other than TCP/UDP + */ + return CHECKSUM_NONE; +} + /* Build a linear skb around the received buffer. * We are guaranteed there is enough room at the end of the data buffer to * accommodate the shared info area of the skb. @@ -1556,7 +1663,7 @@ static struct sk_buff *contig_fd_to_skb(const struct dpaa_priv *priv, skb_reserve(skb, fd_off); skb_put(skb, qm_fd_get_length(fd)); - skb->ip_summed = CHECKSUM_NONE; + skb->ip_summed = rx_csum_offload(priv, fd); return skb; @@ -1616,7 +1723,7 @@ static struct sk_buff *sg_fd_to_skb(const struct dpaa_priv *priv, if (WARN_ON(unlikely(!skb))) goto free_buffers; - skb->ip_summed = CHECKSUM_NONE; + skb->ip_summed = rx_csum_offload(priv, fd); /* Make sure forwarded skbs will have enough space * on Tx, if extra headers are added. @@ -2093,7 +2200,7 @@ static enum qman_cb_dqrr_result rx_default_dqrr(struct qman_portal *portal, dma_addr_t addr = qm_fd_addr(fd); enum qm_fd_format fd_format; struct net_device *net_dev; - u32 fd_status = fd->status; + u32 fd_status; struct dpaa_bp *dpaa_bp; struct dpaa_priv *priv; unsigned int skb_len; @@ -2350,6 +2457,7 @@ static const struct net_device_ops dpaa_ops = { .ndo_validate_addr = eth_validate_addr, .ndo_set_rx_mode = dpaa_set_rx_mode, .ndo_do_ioctl = dpaa_ioctl, + .ndo_setup_tc = dpaa_setup_tc, }; static int dpaa_napi_add(struct net_device *net_dev) @@ -2624,8 +2732,10 @@ static int dpaa_eth_probe(struct platform_device *pdev) priv->rx_headroom = dpaa_get_headroom(&priv->buf_layout[RX]); /* All real interfaces need their ports initialized */ - dpaa_eth_init_ports(mac_dev, dpaa_bps, DPAA_BPS_NUM, &port_fqs, - &priv->buf_layout[0], dev); + err = dpaa_eth_init_ports(mac_dev, dpaa_bps, DPAA_BPS_NUM, &port_fqs, + &priv->buf_layout[0], dev); + if (err) + goto init_ports_failed; priv->percpu_priv = devm_alloc_percpu(dev, *priv->percpu_priv); if (!priv->percpu_priv) { @@ -2638,6 +2748,9 @@ static int dpaa_eth_probe(struct platform_device *pdev) memset(percpu_priv, 0, sizeof(*percpu_priv)); } + priv->num_tc = 1; + netif_set_real_num_tx_queues(net_dev, priv->num_tc * DPAA_TC_TXQ_NUM); + /* Initialize NAPI */ err = dpaa_napi_add(net_dev); if (err < 0) @@ -2658,6 +2771,7 @@ netdev_init_failed: napi_add_failed: dpaa_napi_del(net_dev); alloc_percpu_failed: +init_ports_failed: dpaa_fq_free(dev, &priv->dpaa_fq_list); fq_alloc_failed: qman_delete_cgr_safe(&priv->ingress_cgr); diff --git a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.h b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.h index 1f9aebf3f3c5..9941a7866ebe 100644 --- a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.h +++ b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.h @@ -39,7 +39,12 @@ #include "mac.h" #include "dpaa_eth_trace.h" -#define DPAA_ETH_TXQ_NUM NR_CPUS +/* Number of prioritised traffic classes */ +#define DPAA_TC_NUM 4 +/* Number of Tx queues per traffic class */ +#define DPAA_TC_TXQ_NUM NR_CPUS +/* Total number of Tx queues */ +#define DPAA_ETH_TXQ_NUM (DPAA_TC_NUM * DPAA_TC_TXQ_NUM) #define DPAA_BPS_NUM 3 /* number of bpools per interface */ @@ -152,6 +157,7 @@ struct dpaa_priv { u16 channel; struct list_head dpaa_fq_list; + u8 num_tc; u32 msg_enable; /* net_device message level */ struct { diff --git a/drivers/net/ethernet/freescale/fman/fman.c b/drivers/net/ethernet/freescale/fman/fman.c index f60845f0c6ca..4aefe2438969 100644 --- a/drivers/net/ethernet/freescale/fman/fman.c +++ b/drivers/net/ethernet/freescale/fman/fman.c @@ -59,6 +59,7 @@ #define DMA_OFFSET 0x000C2000 #define FPM_OFFSET 0x000C3000 #define IMEM_OFFSET 0x000C4000 +#define HWP_OFFSET 0x000C7000 #define CGP_OFFSET 0x000DB000 /* Exceptions bit map */ @@ -218,6 +219,9 @@ #define QMI_GS_HALT_NOT_BUSY 0x00000002 +/* HWP defines */ +#define HWP_RPIMAC_PEN 0x00000001 + /* IRAM defines */ #define IRAM_IADD_AIE 0x80000000 #define IRAM_READY 0x80000000 @@ -475,6 +479,12 @@ struct fman_dma_regs { u32 res00e0[0x400 - 56]; }; +struct fman_hwp_regs { + u32 res0000[0x844 / 4]; /* 0x000..0x843 */ + u32 fmprrpimac; /* FM Parser Internal memory access control */ + u32 res[(0x1000 - 0x848) / 4]; /* 0x848..0xFFF */ +}; + /* Structure that holds current FMan state. * Used for saving run time information. */ @@ -606,6 +616,7 @@ struct fman { struct fman_bmi_regs __iomem *bmi_regs; struct fman_qmi_regs __iomem *qmi_regs; struct fman_dma_regs __iomem *dma_regs; + struct fman_hwp_regs __iomem *hwp_regs; fman_exceptions_cb *exception_cb; fman_bus_error_cb *bus_error_cb; /* Spinlock for FMan use */ @@ -999,6 +1010,12 @@ static void qmi_init(struct fman_qmi_regs __iomem *qmi_rg, iowrite32be(tmp_reg, &qmi_rg->fmqm_ien); } +static void hwp_init(struct fman_hwp_regs __iomem *hwp_rg) +{ + /* enable HW Parser */ + iowrite32be(HWP_RPIMAC_PEN, &hwp_rg->fmprrpimac); +} + static int enable(struct fman *fman, struct fman_cfg *cfg) { u32 cfg_reg = 0; @@ -1195,7 +1212,7 @@ static int fill_soc_specific_params(struct fman_state_struct *state) state->max_num_of_open_dmas = 32; state->fm_port_num_of_cg = 256; state->num_of_rx_ports = 6; - state->total_fifo_size = 122 * 1024; + state->total_fifo_size = 136 * 1024; break; case 2: @@ -1793,6 +1810,7 @@ static int fman_config(struct fman *fman) fman->bmi_regs = base_addr + BMI_OFFSET; fman->qmi_regs = base_addr + QMI_OFFSET; fman->dma_regs = base_addr + DMA_OFFSET; + fman->hwp_regs = base_addr + HWP_OFFSET; fman->base_addr = base_addr; spin_lock_init(&fman->spinlock); @@ -2062,6 +2080,9 @@ static int fman_init(struct fman *fman) /* Init QMI Registers */ qmi_init(fman->qmi_regs, fman->cfg); + /* Init HW Parser */ + hwp_init(fman->hwp_regs); + err = enable(fman, cfg); if (err != 0) return err; diff --git a/drivers/net/ethernet/freescale/fman/fman.h b/drivers/net/ethernet/freescale/fman/fman.h index 57aae8d17d77..f53e1473dbcc 100644 --- a/drivers/net/ethernet/freescale/fman/fman.h +++ b/drivers/net/ethernet/freescale/fman/fman.h @@ -134,14 +134,14 @@ enum fman_exceptions { struct fman_prs_result { u8 lpid; /* Logical port id */ u8 shimr; /* Shim header result */ - u16 l2r; /* Layer 2 result */ - u16 l3r; /* Layer 3 result */ + __be16 l2r; /* Layer 2 result */ + __be16 l3r; /* Layer 3 result */ u8 l4r; /* Layer 4 result */ u8 cplan; /* Classification plan id */ - u16 nxthdr; /* Next Header */ - u16 cksum; /* Running-sum */ + __be16 nxthdr; /* Next Header */ + __be16 cksum; /* Running-sum */ /* Flags&fragment-offset field of the last IP-header */ - u16 flags_frag_off; + __be16 flags_frag_off; /* Routing type field of a IPV6 routing extension header */ u8 route_type; /* Routing Extension Header Present; last bit is IP valid */ diff --git a/drivers/net/ethernet/freescale/fman/fman_port.c b/drivers/net/ethernet/freescale/fman/fman_port.c index 9f3bb50a2365..57bf44fa16a1 100644 --- a/drivers/net/ethernet/freescale/fman/fman_port.c +++ b/drivers/net/ethernet/freescale/fman/fman_port.c @@ -62,6 +62,7 @@ #define BMI_PORT_REGS_OFFSET 0 #define QMI_PORT_REGS_OFFSET 0x400 +#define HWP_PORT_REGS_OFFSET 0x800 /* Default values */ #define DFLT_PORT_BUFFER_PREFIX_CONTEXT_DATA_ALIGN \ @@ -182,7 +183,7 @@ #define NIA_ENG_BMI 0x00500000 #define NIA_ENG_QMI_ENQ 0x00540000 #define NIA_ENG_QMI_DEQ 0x00580000 - +#define NIA_ENG_HWP 0x00440000 #define NIA_BMI_AC_ENQ_FRAME 0x00000002 #define NIA_BMI_AC_TX_RELEASE 0x000002C0 #define NIA_BMI_AC_RELEASE 0x000000C0 @@ -317,6 +318,19 @@ struct fman_port_qmi_regs { u32 fmqm_pndcc; /* PortID n Dequeue Confirm Counter */ }; +#define HWP_HXS_COUNT 16 +#define HWP_HXS_PHE_REPORT 0x00000800 +#define HWP_HXS_PCAC_PSTAT 0x00000100 +#define HWP_HXS_PCAC_PSTOP 0x00000001 +struct fman_port_hwp_regs { + struct { + u32 ssa; /* Soft Sequence Attachment */ + u32 lcv; /* Line-up Enable Confirmation Mask */ + } pmda[HWP_HXS_COUNT]; /* Parse Memory Direct Access Registers */ + u32 reserved080[(0x3f8 - 0x080) / 4]; /* (0x080-0x3f7) */ + u32 fmpr_pcac; /* Configuration Access Control */ +}; + /* QMI dequeue prefetch modes */ enum fman_port_deq_prefetch { FMAN_PORT_DEQ_NO_PREFETCH, /* No prefetch mode */ @@ -436,6 +450,7 @@ struct fman_port { union fman_port_bmi_regs __iomem *bmi_regs; struct fman_port_qmi_regs __iomem *qmi_regs; + struct fman_port_hwp_regs __iomem *hwp_regs; struct fman_sp_buffer_offsets buffer_offsets; @@ -521,9 +536,12 @@ static int init_bmi_rx(struct fman_port *port) /* NIA */ tmp = (u32)cfg->rx_fd_bits << BMI_NEXT_ENG_FD_BITS_SHIFT; - tmp |= NIA_ENG_BMI | NIA_BMI_AC_ENQ_FRAME; + tmp |= NIA_ENG_HWP; iowrite32be(tmp, ®s->fmbm_rfne); + /* Parser Next Engine NIA */ + iowrite32be(NIA_ENG_BMI | NIA_BMI_AC_ENQ_FRAME, ®s->fmbm_rfpne); + /* Enqueue NIA */ iowrite32be(NIA_ENG_QMI_ENQ | NIA_ORDER_RESTOR, ®s->fmbm_rfene); @@ -665,6 +683,50 @@ static int init_qmi(struct fman_port *port) return 0; } +static void stop_port_hwp(struct fman_port *port) +{ + struct fman_port_hwp_regs __iomem *regs = port->hwp_regs; + int cnt = 100; + + iowrite32be(HWP_HXS_PCAC_PSTOP, ®s->fmpr_pcac); + + while (cnt-- > 0 && + (ioread32be(®s->fmpr_pcac) & HWP_HXS_PCAC_PSTAT)) + udelay(10); + if (!cnt) + pr_err("Timeout stopping HW Parser\n"); +} + +static void start_port_hwp(struct fman_port *port) +{ + struct fman_port_hwp_regs __iomem *regs = port->hwp_regs; + int cnt = 100; + + iowrite32be(0, ®s->fmpr_pcac); + + while (cnt-- > 0 && + !(ioread32be(®s->fmpr_pcac) & HWP_HXS_PCAC_PSTAT)) + udelay(10); + if (!cnt) + pr_err("Timeout starting HW Parser\n"); +} + +static void init_hwp(struct fman_port *port) +{ + struct fman_port_hwp_regs __iomem *regs = port->hwp_regs; + int i; + + stop_port_hwp(port); + + for (i = 0; i < HWP_HXS_COUNT; i++) { + /* enable HXS error reporting into FD[STATUS] PHE */ + iowrite32be(0x00000000, ®s->pmda[i].ssa); + iowrite32be(0xffffffff, ®s->pmda[i].lcv); + } + + start_port_hwp(port); +} + static int init(struct fman_port *port) { int err; @@ -673,6 +735,8 @@ static int init(struct fman_port *port) switch (port->port_type) { case FMAN_PORT_TYPE_RX: err = init_bmi_rx(port); + if (!err) + init_hwp(port); break; case FMAN_PORT_TYPE_TX: err = init_bmi_tx(port); @@ -686,7 +750,8 @@ static int init(struct fman_port *port) /* Init QMI registers */ err = init_qmi(port); - return err; + if (err) + return err; return 0; } @@ -1247,7 +1312,7 @@ int fman_port_config(struct fman_port *port, struct fman_port_params *params) /* Allocate the FM driver's parameters structure */ port->cfg = kzalloc(sizeof(*port->cfg), GFP_KERNEL); if (!port->cfg) - goto err_params; + return -EINVAL; /* Initialize FM port parameters which will be kept by the driver */ port->port_type = port->dts_params.type; @@ -1276,6 +1341,7 @@ int fman_port_config(struct fman_port *port, struct fman_port_params *params) /* set memory map pointers */ port->bmi_regs = base_addr + BMI_PORT_REGS_OFFSET; port->qmi_regs = base_addr + QMI_PORT_REGS_OFFSET; + port->hwp_regs = base_addr + HWP_PORT_REGS_OFFSET; port->max_frame_length = DFLT_PORT_MAX_FRAME_LENGTH; /* resource distribution. */ @@ -1327,8 +1393,6 @@ int fman_port_config(struct fman_port *port, struct fman_port_params *params) err_port_cfg: kfree(port->cfg); -err_params: - kfree(port); return -EINVAL; } EXPORT_SYMBOL(fman_port_config); diff --git a/drivers/net/ethernet/freescale/fs_enet/mac-fec.c b/drivers/net/ethernet/freescale/fs_enet/mac-fec.c index db9c0bcf54cd..1fc27c97e3b2 100644 --- a/drivers/net/ethernet/freescale/fs_enet/mac-fec.c +++ b/drivers/net/ethernet/freescale/fs_enet/mac-fec.c @@ -38,12 +38,6 @@ #include <asm/irq.h> #include <linux/uaccess.h> -#ifdef CONFIG_8xx -#include <asm/8xx_immap.h> -#include <asm/pgtable.h> -#include <asm/cpm1.h> -#endif - #include "fs_enet.h" #include "fec.h" diff --git a/drivers/net/ethernet/freescale/fs_enet/mac-scc.c b/drivers/net/ethernet/freescale/fs_enet/mac-scc.c index 96d44cf44fe0..64300ac13e02 100644 --- a/drivers/net/ethernet/freescale/fs_enet/mac-scc.c +++ b/drivers/net/ethernet/freescale/fs_enet/mac-scc.c @@ -37,12 +37,6 @@ #include <asm/irq.h> #include <linux/uaccess.h> -#ifdef CONFIG_8xx -#include <asm/8xx_immap.h> -#include <asm/pgtable.h> -#include <asm/cpm1.h> -#endif - #include "fs_enet.h" /*************************************************/ diff --git a/drivers/net/ethernet/ibm/emac/core.c b/drivers/net/ethernet/ibm/emac/core.c index 275c2e2349ad..c44036d5761a 100644 --- a/drivers/net/ethernet/ibm/emac/core.c +++ b/drivers/net/ethernet/ibm/emac/core.c @@ -2589,8 +2589,6 @@ static int emac_dt_mdio_probe(struct emac_instance *dev) static int emac_dt_phy_connect(struct emac_instance *dev, struct device_node *phy_handle) { - int res; - dev->phy.def = devm_kzalloc(&dev->ofdev->dev, sizeof(*dev->phy.def), GFP_KERNEL); if (!dev->phy.def) @@ -2617,7 +2615,7 @@ static int emac_dt_phy_probe(struct emac_instance *dev) { struct device_node *np = dev->ofdev->dev.of_node; struct device_node *phy_handle; - int res = 0; + int res = 1; phy_handle = of_parse_phandle(np, "phy-handle", 0); @@ -2714,13 +2712,24 @@ static int emac_init_phy(struct emac_instance *dev) if (emac_has_feature(dev, EMAC_FTR_HAS_RGMII)) { int res = emac_dt_phy_probe(dev); - mutex_unlock(&emac_phy_map_lock); - if (!res) + switch (res) { + case 1: + /* No phy-handle property configured. + * Continue with the existing phy probe + * and setup code. + */ + break; + + case 0: + mutex_unlock(&emac_phy_map_lock); goto init_phy; - dev_err(&dev->ofdev->dev, "failed to attach dt phy (%d).\n", - res); - return res; + default: + mutex_unlock(&emac_phy_map_lock); + dev_err(&dev->ofdev->dev, "failed to attach dt phy (%d).\n", + res); + return res; + } } if (dev->phy_address != 0xffffffff) diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c index 9198e6bd5160..5f11b4dc95d2 100644 --- a/drivers/net/ethernet/ibm/ibmvnic.c +++ b/drivers/net/ethernet/ibm/ibmvnic.c @@ -404,7 +404,7 @@ static int ibmvnic_open(struct net_device *netdev) send_map_query(adapter); for (i = 0; i < rxadd_subcrqs; i++) { init_rx_pool(adapter, &adapter->rx_pool[i], - IBMVNIC_BUFFS_PER_POOL, i, + adapter->req_rx_add_entries_per_subcrq, i, be64_to_cpu(size_array[i]), 1); if (alloc_rx_pool(adapter, &adapter->rx_pool[i])) { dev_err(dev, "Couldn't alloc rx pool\n"); @@ -419,23 +419,23 @@ static int ibmvnic_open(struct net_device *netdev) for (i = 0; i < tx_subcrqs; i++) { tx_pool = &adapter->tx_pool[i]; tx_pool->tx_buff = - kcalloc(adapter->max_tx_entries_per_subcrq, + kcalloc(adapter->req_tx_entries_per_subcrq, sizeof(struct ibmvnic_tx_buff), GFP_KERNEL); if (!tx_pool->tx_buff) goto tx_pool_alloc_failed; if (alloc_long_term_buff(adapter, &tx_pool->long_term_buff, - adapter->max_tx_entries_per_subcrq * + adapter->req_tx_entries_per_subcrq * adapter->req_mtu)) goto tx_ltb_alloc_failed; tx_pool->free_map = - kcalloc(adapter->max_tx_entries_per_subcrq, + kcalloc(adapter->req_tx_entries_per_subcrq, sizeof(int), GFP_KERNEL); if (!tx_pool->free_map) goto tx_fm_alloc_failed; - for (j = 0; j < adapter->max_tx_entries_per_subcrq; j++) + for (j = 0; j < adapter->req_tx_entries_per_subcrq; j++) tx_pool->free_map[j] = j; tx_pool->consumer_index = 0; @@ -705,6 +705,7 @@ static int ibmvnic_xmit(struct sk_buff *skb, struct net_device *netdev) u8 *hdrs = (u8 *)&adapter->tx_rx_desc_req; struct device *dev = &adapter->vdev->dev; struct ibmvnic_tx_buff *tx_buff = NULL; + struct ibmvnic_sub_crq_queue *tx_scrq; struct ibmvnic_tx_pool *tx_pool; unsigned int tx_send_failed = 0; unsigned int tx_map_failed = 0; @@ -724,6 +725,7 @@ static int ibmvnic_xmit(struct sk_buff *skb, struct net_device *netdev) int ret = 0; tx_pool = &adapter->tx_pool[queue_num]; + tx_scrq = adapter->tx_scrq[queue_num]; txq = netdev_get_tx_queue(netdev, skb_get_queue_mapping(skb)); handle_array = (u64 *)((u8 *)(adapter->login_rsp_buf) + be32_to_cpu(adapter->login_rsp_buf-> @@ -744,7 +746,7 @@ static int ibmvnic_xmit(struct sk_buff *skb, struct net_device *netdev) tx_pool->consumer_index = (tx_pool->consumer_index + 1) % - adapter->max_tx_entries_per_subcrq; + adapter->req_tx_entries_per_subcrq; tx_buff = &tx_pool->tx_buff[index]; tx_buff->skb = skb; @@ -817,7 +819,7 @@ static int ibmvnic_xmit(struct sk_buff *skb, struct net_device *netdev) if (tx_pool->consumer_index == 0) tx_pool->consumer_index = - adapter->max_tx_entries_per_subcrq - 1; + adapter->req_tx_entries_per_subcrq - 1; else tx_pool->consumer_index--; @@ -826,6 +828,14 @@ static int ibmvnic_xmit(struct sk_buff *skb, struct net_device *netdev) ret = NETDEV_TX_BUSY; goto out; } + + atomic_inc(&tx_scrq->used); + + if (atomic_read(&tx_scrq->used) >= adapter->req_tx_entries_per_subcrq) { + netdev_info(netdev, "Stopping queue %d\n", queue_num); + netif_stop_subqueue(netdev, queue_num); + } + tx_packets++; tx_bytes += skb->len; txq->trans_start = jiffies; @@ -1213,6 +1223,7 @@ static struct ibmvnic_sub_crq_queue *init_sub_crq_queue(struct ibmvnic_adapter scrq->adapter = adapter; scrq->size = 4 * PAGE_SIZE / sizeof(*scrq->msgs); scrq->cur = 0; + atomic_set(&scrq->used, 0); scrq->rx_skb_top = NULL; spin_lock_init(&scrq->lock); @@ -1355,14 +1366,28 @@ restart_loop: DMA_TO_DEVICE); } - if (txbuff->last_frag) + if (txbuff->last_frag) { + atomic_dec(&scrq->used); + + if (atomic_read(&scrq->used) <= + (adapter->req_tx_entries_per_subcrq / 2) && + netif_subqueue_stopped(adapter->netdev, + txbuff->skb)) { + netif_wake_subqueue(adapter->netdev, + scrq->pool_index); + netdev_dbg(adapter->netdev, + "Started queue %d\n", + scrq->pool_index); + } + dev_kfree_skb_any(txbuff->skb); + } adapter->tx_pool[pool].free_map[adapter->tx_pool[pool]. producer_index] = index; adapter->tx_pool[pool].producer_index = (adapter->tx_pool[pool].producer_index + 1) % - adapter->max_tx_entries_per_subcrq; + adapter->req_tx_entries_per_subcrq; } /* remove tx_comp scrq*/ next->tx_comp.first = 0; diff --git a/drivers/net/ethernet/ibm/ibmvnic.h b/drivers/net/ethernet/ibm/ibmvnic.h index 422824f1f42a..1993b42666f7 100644 --- a/drivers/net/ethernet/ibm/ibmvnic.h +++ b/drivers/net/ethernet/ibm/ibmvnic.h @@ -863,6 +863,7 @@ struct ibmvnic_sub_crq_queue { spinlock_t lock; struct sk_buff *rx_skb_top; struct ibmvnic_adapter *adapter; + atomic_t used; }; struct ibmvnic_long_term_buff { diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_netdev.c b/drivers/net/ethernet/intel/fm10k/fm10k_netdev.c index 01db688cf539..72481670478c 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_netdev.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_netdev.c @@ -1226,7 +1226,9 @@ static int __fm10k_setup_tc(struct net_device *dev, u32 handle, __be16 proto, if (tc->type != TC_SETUP_MQPRIO) return -EINVAL; - return fm10k_setup_tc(dev, tc->tc); + tc->mqprio->hw = TC_MQPRIO_HW_OFFLOAD_TCS; + + return fm10k_setup_tc(dev, tc->mqprio->num_tc); } static void fm10k_assign_l2_accel(struct fm10k_intfc *interface, diff --git a/drivers/net/ethernet/intel/i40e/i40e.h b/drivers/net/ethernet/intel/i40e/i40e.h index 82d8040fa418..a5cf5d11d0e7 100644 --- a/drivers/net/ethernet/intel/i40e/i40e.h +++ b/drivers/net/ethernet/intel/i40e/i40e.h @@ -348,16 +348,23 @@ struct i40e_pf { #define I40E_FLAG_TRUE_PROMISC_SUPPORT BIT_ULL(51) #define I40E_FLAG_HAVE_CRT_RETIMER BIT_ULL(52) #define I40E_FLAG_PTP_L4_CAPABLE BIT_ULL(53) -#define I40E_FLAG_WOL_MC_MAGIC_PKT_WAKE BIT_ULL(54) +#define I40E_FLAG_CLIENT_RESET BIT_ULL(54) #define I40E_FLAG_TEMP_LINK_POLLING BIT_ULL(55) +#define I40E_FLAG_CLIENT_L2_CHANGE BIT_ULL(56) +#define I40E_FLAG_WOL_MC_MAGIC_PKT_WAKE BIT_ULL(57) - /* tracks features that get auto disabled by errors */ - u64 auto_disable_flags; + /* Tracks features that are disabled due to hw limitations. + * If a bit is set here, it means that the corresponding + * bit in the 'flags' field is cleared i.e that feature + * is disabled + */ + u64 hw_disabled_flags; #ifdef I40E_FCOE struct i40e_fcoe fcoe; #endif /* I40E_FCOE */ + struct i40e_client_instance *cinst; bool stat_offsets_loaded; struct i40e_hw_port_stats stats; struct i40e_hw_port_stats stats_offsets; @@ -813,8 +820,7 @@ void i40e_notify_client_of_l2_param_changes(struct i40e_vsi *vsi); void i40e_notify_client_of_netdev_close(struct i40e_vsi *vsi, bool reset); void i40e_notify_client_of_vf_enable(struct i40e_pf *pf, u32 num_vfs); void i40e_notify_client_of_vf_reset(struct i40e_pf *pf, u32 vf_id); -int i40e_vf_client_capable(struct i40e_pf *pf, u32 vf_id, - enum i40e_client_type type); +int i40e_vf_client_capable(struct i40e_pf *pf, u32 vf_id); /** * i40e_irq_dynamic_enable - Enable default interrupt generation settings * @vsi: pointer to a vsi diff --git a/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h b/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h index 451f48b7540a..251074c677c4 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h +++ b/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h @@ -132,6 +132,10 @@ enum i40e_admin_queue_opc { i40e_aqc_opc_list_func_capabilities = 0x000A, i40e_aqc_opc_list_dev_capabilities = 0x000B, + /* Proxy commands */ + i40e_aqc_opc_set_proxy_config = 0x0104, + i40e_aqc_opc_set_ns_proxy_table_entry = 0x0105, + /* LAA */ i40e_aqc_opc_mac_address_read = 0x0107, i40e_aqc_opc_mac_address_write = 0x0108, @@ -139,6 +143,10 @@ enum i40e_admin_queue_opc { /* PXE */ i40e_aqc_opc_clear_pxe_mode = 0x0110, + /* WoL commands */ + i40e_aqc_opc_set_wol_filter = 0x0120, + i40e_aqc_opc_get_wake_reason = 0x0121, + /* internal switch commands */ i40e_aqc_opc_get_switch_config = 0x0200, i40e_aqc_opc_add_statistics = 0x0201, @@ -177,6 +185,7 @@ enum i40e_admin_queue_opc { i40e_aqc_opc_remove_control_packet_filter = 0x025B, i40e_aqc_opc_add_cloud_filters = 0x025C, i40e_aqc_opc_remove_cloud_filters = 0x025D, + i40e_aqc_opc_clear_wol_switch_filters = 0x025E, i40e_aqc_opc_add_mirror_rule = 0x0260, i40e_aqc_opc_delete_mirror_rule = 0x0261, @@ -563,6 +572,56 @@ struct i40e_aqc_clear_pxe { I40E_CHECK_CMD_LENGTH(i40e_aqc_clear_pxe); +/* Set WoL Filter (0x0120) */ + +struct i40e_aqc_set_wol_filter { + __le16 filter_index; +#define I40E_AQC_MAX_NUM_WOL_FILTERS 8 +#define I40E_AQC_SET_WOL_FILTER_TYPE_MAGIC_SHIFT 15 +#define I40E_AQC_SET_WOL_FILTER_TYPE_MAGIC_MASK (0x1 << \ + I40E_AQC_SET_WOL_FILTER_TYPE_MAGIC_SHIFT) + +#define I40E_AQC_SET_WOL_FILTER_INDEX_SHIFT 0 +#define I40E_AQC_SET_WOL_FILTER_INDEX_MASK (0x7 << \ + I40E_AQC_SET_WOL_FILTER_INDEX_SHIFT) + __le16 cmd_flags; +#define I40E_AQC_SET_WOL_FILTER 0x8000 +#define I40E_AQC_SET_WOL_FILTER_NO_TCO_WOL 0x4000 +#define I40E_AQC_SET_WOL_FILTER_ACTION_CLEAR 0 +#define I40E_AQC_SET_WOL_FILTER_ACTION_SET 1 + __le16 valid_flags; +#define I40E_AQC_SET_WOL_FILTER_ACTION_VALID 0x8000 +#define I40E_AQC_SET_WOL_FILTER_NO_TCO_ACTION_VALID 0x4000 + u8 reserved[2]; + __le32 address_high; + __le32 address_low; +}; + +I40E_CHECK_CMD_LENGTH(i40e_aqc_set_wol_filter); + +struct i40e_aqc_set_wol_filter_data { + u8 filter[128]; + u8 mask[16]; +}; + +I40E_CHECK_STRUCT_LEN(0x90, i40e_aqc_set_wol_filter_data); + +/* Get Wake Reason (0x0121) */ + +struct i40e_aqc_get_wake_reason_completion { + u8 reserved_1[2]; + __le16 wake_reason; +#define I40E_AQC_GET_WAKE_UP_REASON_WOL_REASON_MATCHED_INDEX_SHIFT 0 +#define I40E_AQC_GET_WAKE_UP_REASON_WOL_REASON_MATCHED_INDEX_MASK (0xFF << \ + I40E_AQC_GET_WAKE_UP_REASON_WOL_REASON_MATCHED_INDEX_SHIFT) +#define I40E_AQC_GET_WAKE_UP_REASON_WOL_REASON_RESERVED_SHIFT 8 +#define I40E_AQC_GET_WAKE_UP_REASON_WOL_REASON_RESERVED_MASK (0xFF << \ + I40E_AQC_GET_WAKE_UP_REASON_WOL_REASON_RESERVED_SHIFT) + u8 reserved_2[12]; +}; + +I40E_CHECK_CMD_LENGTH(i40e_aqc_get_wake_reason_completion); + /* Switch configuration commands (0x02xx) */ /* Used by many indirect commands that only pass an seid and a buffer in the @@ -645,6 +704,8 @@ struct i40e_aqc_set_port_parameters { #define I40E_AQ_SET_P_PARAMS_PAD_SHORT_PACKETS 2 /* must set! */ #define I40E_AQ_SET_P_PARAMS_DOUBLE_VLAN_ENA 4 __le16 bad_frame_vsi; +#define I40E_AQ_SET_P_PARAMS_BFRAME_SEID_SHIFT 0x0 +#define I40E_AQ_SET_P_PARAMS_BFRAME_SEID_MASK 0x3FF __le16 default_seid; /* reserved for command */ u8 reserved[10]; }; @@ -696,6 +757,7 @@ I40E_CHECK_STRUCT_LEN(0x10, i40e_aqc_switch_resource_alloc_element_resp); /* Set Switch Configuration (direct 0x0205) */ struct i40e_aqc_set_switch_config { __le16 flags; +/* flags used for both fields below */ #define I40E_AQ_SET_SWITCH_CFG_PROMISC 0x0001 #define I40E_AQ_SET_SWITCH_CFG_L2_FILTER 0x0002 __le16 valid_flags; @@ -1844,11 +1906,12 @@ struct i40e_aqc_get_link_status { #define I40E_AQ_CONFIG_FEC_RS_ENA 0x02 #define I40E_AQ_CONFIG_CRC_ENA 0x04 #define I40E_AQ_CONFIG_PACING_MASK 0x78 - u8 external_power_ability; + u8 power_desc; #define I40E_AQ_LINK_POWER_CLASS_1 0x00 #define I40E_AQ_LINK_POWER_CLASS_2 0x01 #define I40E_AQ_LINK_POWER_CLASS_3 0x02 #define I40E_AQ_LINK_POWER_CLASS_4 0x03 +#define I40E_AQ_PWR_CLASS_MASK 0x03 u8 reserved[4]; }; diff --git a/drivers/net/ethernet/intel/i40e/i40e_client.c b/drivers/net/ethernet/intel/i40e/i40e_client.c index d570219efd9f..a9f0d22a7cf4 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_client.c +++ b/drivers/net/ethernet/intel/i40e/i40e_client.c @@ -32,16 +32,10 @@ #include "i40e_client.h" static const char i40e_client_interface_version_str[] = I40E_CLIENT_VERSION_STR; - +static struct i40e_client *registered_client; static LIST_HEAD(i40e_devices); static DEFINE_MUTEX(i40e_device_mutex); -static LIST_HEAD(i40e_clients); -static DEFINE_MUTEX(i40e_client_mutex); - -static LIST_HEAD(i40e_client_instances); -static DEFINE_MUTEX(i40e_client_instance_mutex); - static int i40e_client_virtchnl_send(struct i40e_info *ldev, struct i40e_client *client, u32 vf_id, u8 *msg, u16 len); @@ -67,28 +61,6 @@ static struct i40e_ops i40e_lan_ops = { }; /** - * i40e_client_type_to_vsi_type - convert client type to vsi type - * @client_type: the i40e_client type - * - * returns the related vsi type value - **/ -static -enum i40e_vsi_type i40e_client_type_to_vsi_type(enum i40e_client_type type) -{ - switch (type) { - case I40E_CLIENT_IWARP: - return I40E_VSI_IWARP; - - case I40E_CLIENT_VMDQ2: - return I40E_VSI_VMDQ2; - - default: - pr_err("i40e: Client type unknown\n"); - return I40E_VSI_TYPE_UNKNOWN; - } -} - -/** * i40e_client_get_params - Get the params that can change at runtime * @vsi: the VSI with the message * @param: clinet param struct @@ -134,31 +106,22 @@ int i40e_client_get_params(struct i40e_vsi *vsi, struct i40e_params *params) void i40e_notify_client_of_vf_msg(struct i40e_vsi *vsi, u32 vf_id, u8 *msg, u16 len) { - struct i40e_client_instance *cdev; + struct i40e_pf *pf = vsi->back; + struct i40e_client_instance *cdev = pf->cinst; - if (!vsi) + if (!cdev || !cdev->client) + return; + if (!cdev->client->ops || !cdev->client->ops->virtchnl_receive) { + dev_dbg(&pf->pdev->dev, + "Cannot locate client instance virtual channel receive routine\n"); + return; + } + if (!test_bit(__I40E_CLIENT_INSTANCE_OPENED, &cdev->state)) { + dev_dbg(&pf->pdev->dev, "Client is not open, abort virtchnl_receive\n"); return; - mutex_lock(&i40e_client_instance_mutex); - list_for_each_entry(cdev, &i40e_client_instances, list) { - if (cdev->lan_info.pf == vsi->back) { - if (!cdev->client || - !cdev->client->ops || - !cdev->client->ops->virtchnl_receive) { - dev_dbg(&vsi->back->pdev->dev, - "Cannot locate client instance virtual channel receive routine\n"); - continue; - } - if (!test_bit(__I40E_CLIENT_INSTANCE_OPENED, - &cdev->state)) { - dev_dbg(&vsi->back->pdev->dev, "Client is not open, abort virtchnl_receive\n"); - continue; - } - cdev->client->ops->virtchnl_receive(&cdev->lan_info, - cdev->client, - vf_id, msg, len); - } } - mutex_unlock(&i40e_client_instance_mutex); + cdev->client->ops->virtchnl_receive(&cdev->lan_info, cdev->client, + vf_id, msg, len); } /** @@ -169,39 +132,28 @@ i40e_notify_client_of_vf_msg(struct i40e_vsi *vsi, u32 vf_id, u8 *msg, u16 len) **/ void i40e_notify_client_of_l2_param_changes(struct i40e_vsi *vsi) { - struct i40e_client_instance *cdev; + struct i40e_pf *pf = vsi->back; + struct i40e_client_instance *cdev = pf->cinst; struct i40e_params params; - if (!vsi) + if (!cdev || !cdev->client) + return; + if (!cdev->client->ops || !cdev->client->ops->l2_param_change) { + dev_dbg(&vsi->back->pdev->dev, + "Cannot locate client instance l2_param_change routine\n"); + return; + } + if (!test_bit(__I40E_CLIENT_INSTANCE_OPENED, &cdev->state)) { + dev_dbg(&vsi->back->pdev->dev, "Client is not open, abort l2 param change\n"); return; - mutex_lock(&i40e_client_instance_mutex); - list_for_each_entry(cdev, &i40e_client_instances, list) { - if (cdev->lan_info.pf == vsi->back) { - if (!cdev->client || - !cdev->client->ops || - !cdev->client->ops->l2_param_change) { - dev_dbg(&vsi->back->pdev->dev, - "Cannot locate client instance l2_param_change routine\n"); - continue; - } - memset(¶ms, 0, sizeof(params)); - i40e_client_get_params(vsi, ¶ms); - if (!test_bit(__I40E_CLIENT_INSTANCE_OPENED, - &cdev->state)) { - dev_dbg(&vsi->back->pdev->dev, "Client is not open, abort l2 param change\n"); - continue; - } - cdev->lan_info.params = params; - cdev->client->ops->l2_param_change(&cdev->lan_info, - cdev->client, - ¶ms); - } } - mutex_unlock(&i40e_client_instance_mutex); + memcpy(&cdev->lan_info.params, ¶ms, sizeof(struct i40e_params)); + cdev->client->ops->l2_param_change(&cdev->lan_info, cdev->client, + ¶ms); } /** - * i40e_client_release_qvlist + * i40e_client_release_qvlist - release MSI-X vector mapping for client * @ldev: pointer to L2 context. * **/ @@ -237,26 +189,19 @@ static void i40e_client_release_qvlist(struct i40e_info *ldev) **/ void i40e_notify_client_of_netdev_close(struct i40e_vsi *vsi, bool reset) { - struct i40e_client_instance *cdev; + struct i40e_pf *pf = vsi->back; + struct i40e_client_instance *cdev = pf->cinst; - if (!vsi) + if (!cdev || !cdev->client) + return; + if (!cdev->client->ops || !cdev->client->ops->close) { + dev_dbg(&vsi->back->pdev->dev, + "Cannot locate client instance close routine\n"); return; - mutex_lock(&i40e_client_instance_mutex); - list_for_each_entry(cdev, &i40e_client_instances, list) { - if (cdev->lan_info.netdev == vsi->netdev) { - if (!cdev->client || - !cdev->client->ops || !cdev->client->ops->close) { - dev_dbg(&vsi->back->pdev->dev, - "Cannot locate client instance close routine\n"); - continue; - } - cdev->client->ops->close(&cdev->lan_info, cdev->client, - reset); - clear_bit(__I40E_CLIENT_INSTANCE_OPENED, &cdev->state); - i40e_client_release_qvlist(&cdev->lan_info); - } } - mutex_unlock(&i40e_client_instance_mutex); + cdev->client->ops->close(&cdev->lan_info, cdev->client, reset); + clear_bit(__I40E_CLIENT_INSTANCE_OPENED, &cdev->state); + i40e_client_release_qvlist(&cdev->lan_info); } /** @@ -268,30 +213,20 @@ void i40e_notify_client_of_netdev_close(struct i40e_vsi *vsi, bool reset) **/ void i40e_notify_client_of_vf_reset(struct i40e_pf *pf, u32 vf_id) { - struct i40e_client_instance *cdev; + struct i40e_client_instance *cdev = pf->cinst; - if (!pf) + if (!cdev || !cdev->client) + return; + if (!cdev->client->ops || !cdev->client->ops->vf_reset) { + dev_dbg(&pf->pdev->dev, + "Cannot locate client instance VF reset routine\n"); + return; + } + if (!test_bit(__I40E_CLIENT_INSTANCE_OPENED, &cdev->state)) { + dev_dbg(&pf->pdev->dev, "Client is not open, abort vf-reset\n"); return; - mutex_lock(&i40e_client_instance_mutex); - list_for_each_entry(cdev, &i40e_client_instances, list) { - if (cdev->lan_info.pf == pf) { - if (!cdev->client || - !cdev->client->ops || - !cdev->client->ops->vf_reset) { - dev_dbg(&pf->pdev->dev, - "Cannot locate client instance VF reset routine\n"); - continue; - } - if (!test_bit(__I40E_CLIENT_INSTANCE_OPENED, - &cdev->state)) { - dev_dbg(&pf->pdev->dev, "Client is not open, abort vf-reset\n"); - continue; - } - cdev->client->ops->vf_reset(&cdev->lan_info, - cdev->client, vf_id); - } } - mutex_unlock(&i40e_client_instance_mutex); + cdev->client->ops->vf_reset(&cdev->lan_info, cdev->client, vf_id); } /** @@ -303,30 +238,21 @@ void i40e_notify_client_of_vf_reset(struct i40e_pf *pf, u32 vf_id) **/ void i40e_notify_client_of_vf_enable(struct i40e_pf *pf, u32 num_vfs) { - struct i40e_client_instance *cdev; + struct i40e_client_instance *cdev = pf->cinst; - if (!pf) + if (!cdev || !cdev->client) + return; + if (!cdev->client->ops || !cdev->client->ops->vf_enable) { + dev_dbg(&pf->pdev->dev, + "Cannot locate client instance VF enable routine\n"); + return; + } + if (!test_bit(__I40E_CLIENT_INSTANCE_OPENED, + &cdev->state)) { + dev_dbg(&pf->pdev->dev, "Client is not open, abort vf-enable\n"); return; - mutex_lock(&i40e_client_instance_mutex); - list_for_each_entry(cdev, &i40e_client_instances, list) { - if (cdev->lan_info.pf == pf) { - if (!cdev->client || - !cdev->client->ops || - !cdev->client->ops->vf_enable) { - dev_dbg(&pf->pdev->dev, - "Cannot locate client instance VF enable routine\n"); - continue; - } - if (!test_bit(__I40E_CLIENT_INSTANCE_OPENED, - &cdev->state)) { - dev_dbg(&pf->pdev->dev, "Client is not open, abort vf-enable\n"); - continue; - } - cdev->client->ops->vf_enable(&cdev->lan_info, - cdev->client, num_vfs); - } } - mutex_unlock(&i40e_client_instance_mutex); + cdev->client->ops->vf_enable(&cdev->lan_info, cdev->client, num_vfs); } /** @@ -337,37 +263,25 @@ void i40e_notify_client_of_vf_enable(struct i40e_pf *pf, u32 num_vfs) * If there is a client of the specified type attached to this PF, call * its vf_capable routine **/ -int i40e_vf_client_capable(struct i40e_pf *pf, u32 vf_id, - enum i40e_client_type type) +int i40e_vf_client_capable(struct i40e_pf *pf, u32 vf_id) { - struct i40e_client_instance *cdev; + struct i40e_client_instance *cdev = pf->cinst; int capable = false; - if (!pf) - return false; - mutex_lock(&i40e_client_instance_mutex); - list_for_each_entry(cdev, &i40e_client_instances, list) { - if (cdev->lan_info.pf == pf) { - if (!cdev->client || - !cdev->client->ops || - !cdev->client->ops->vf_capable || - !(cdev->client->type == type)) { - dev_dbg(&pf->pdev->dev, - "Cannot locate client instance VF capability routine\n"); - continue; - } - if (!test_bit(__I40E_CLIENT_INSTANCE_OPENED, - &cdev->state)) { - dev_dbg(&pf->pdev->dev, "Client is not open, abort vf-capable\n"); - continue; - } - capable = cdev->client->ops->vf_capable(&cdev->lan_info, - cdev->client, - vf_id); - break; - } + if (!cdev || !cdev->client) + goto out; + if (!cdev->client->ops || !cdev->client->ops->vf_capable) { + dev_info(&pf->pdev->dev, + "Cannot locate client instance VF capability routine\n"); + goto out; } - mutex_unlock(&i40e_client_instance_mutex); + if (!test_bit(__I40E_CLIENT_INSTANCE_OPENED, &cdev->state)) + goto out; + + capable = cdev->client->ops->vf_capable(&cdev->lan_info, + cdev->client, + vf_id); +out: return capable; } @@ -377,27 +291,19 @@ int i40e_vf_client_capable(struct i40e_pf *pf, u32 vf_id, * @client: pointer to a client struct in the client list. * @existing: if there was already an existing instance * - * Returns cdev ptr on success or if already exists, NULL on failure **/ -static -struct i40e_client_instance *i40e_client_add_instance(struct i40e_pf *pf, - struct i40e_client *client, - bool *existing) +static void i40e_client_add_instance(struct i40e_pf *pf) { - struct i40e_client_instance *cdev; + struct i40e_client_instance *cdev = NULL; struct netdev_hw_addr *mac = NULL; struct i40e_vsi *vsi = pf->vsi[pf->lan_vsi]; - mutex_lock(&i40e_client_instance_mutex); - list_for_each_entry(cdev, &i40e_client_instances, list) { - if ((cdev->lan_info.pf == pf) && (cdev->client == client)) { - *existing = true; - goto out; - } - } + if (!registered_client || pf->cinst) + return; + cdev = kzalloc(sizeof(*cdev), GFP_KERNEL); if (!cdev) - goto out; + return; cdev->lan_info.pf = (void *)pf; cdev->lan_info.netdev = vsi->netdev; @@ -417,7 +323,7 @@ struct i40e_client_instance *i40e_client_add_instance(struct i40e_pf *pf, if (i40e_client_get_params(vsi, &cdev->lan_info.params)) { kfree(cdev); cdev = NULL; - goto out; + return; } cdev->lan_info.msix_count = pf->num_iwarp_msix; @@ -430,41 +336,20 @@ struct i40e_client_instance *i40e_client_add_instance(struct i40e_pf *pf, else dev_err(&pf->pdev->dev, "MAC address list is empty!\n"); - cdev->client = client; - INIT_LIST_HEAD(&cdev->list); - list_add(&cdev->list, &i40e_client_instances); -out: - mutex_unlock(&i40e_client_instance_mutex); - return cdev; + cdev->client = registered_client; + pf->cinst = cdev; } /** * i40e_client_del_instance - removes a client instance from the list * @pf: pointer to the board struct * - * Returns 0 on success or non-0 on error **/ static -int i40e_client_del_instance(struct i40e_pf *pf, struct i40e_client *client) +void i40e_client_del_instance(struct i40e_pf *pf) { - struct i40e_client_instance *cdev, *tmp; - int ret = -ENODEV; - - mutex_lock(&i40e_client_instance_mutex); - list_for_each_entry_safe(cdev, tmp, &i40e_client_instances, list) { - if ((cdev->lan_info.pf != pf) || (cdev->client != client)) - continue; - - dev_info(&pf->pdev->dev, "Deleted instance of Client %s, of dev %d bus=0x%02x func=0x%02x)\n", - client->name, pf->hw.pf_id, - pf->hw.bus.device, pf->hw.bus.func); - list_del(&cdev->list); - kfree(cdev); - ret = 0; - break; - } - mutex_unlock(&i40e_client_instance_mutex); - return ret; + kfree(pf->cinst); + pf->cinst = NULL; } /** @@ -473,67 +358,50 @@ int i40e_client_del_instance(struct i40e_pf *pf, struct i40e_client *client) **/ void i40e_client_subtask(struct i40e_pf *pf) { + struct i40e_client *client = registered_client; struct i40e_client_instance *cdev; - struct i40e_client *client; - bool existing = false; + struct i40e_vsi *vsi = pf->vsi[pf->lan_vsi]; int ret = 0; if (!(pf->flags & I40E_FLAG_SERVICE_CLIENT_REQUESTED)) return; pf->flags &= ~I40E_FLAG_SERVICE_CLIENT_REQUESTED; + cdev = pf->cinst; /* If we're down or resetting, just bail */ if (test_bit(__I40E_DOWN, &pf->state) || test_bit(__I40E_CONFIG_BUSY, &pf->state)) return; - /* Check client state and instantiate client if client registered */ - mutex_lock(&i40e_client_mutex); - list_for_each_entry(client, &i40e_clients, list) { - /* first check client is registered */ - if (!test_bit(__I40E_CLIENT_REGISTERED, &client->state)) - continue; - - /* Do we also need the LAN VSI to be up, to create instance */ - if (!(client->flags & I40E_CLIENT_FLAGS_LAUNCH_ON_PROBE)) { - /* check if L2 VSI is up, if not we are not ready */ - if (test_bit(__I40E_DOWN, &pf->vsi[pf->lan_vsi]->state)) - continue; - } else { - dev_warn(&pf->pdev->dev, "This client %s is being instantiated at probe\n", - client->name); - } - - /* Add the client instance to the instance list */ - cdev = i40e_client_add_instance(pf, client, &existing); - if (!cdev) - continue; - - if (!existing) { - dev_info(&pf->pdev->dev, "Added instance of Client %s to PF%d bus=0x%02x dev=0x%02x func=0x%02x\n", - client->name, pf->hw.pf_id, - pf->hw.bus.bus_id, pf->hw.bus.device, - pf->hw.bus.func); - } + if (!client || !cdev) + return; - mutex_lock(&i40e_client_instance_mutex); - if (!test_bit(__I40E_CLIENT_INSTANCE_OPENED, - &cdev->state)) { - /* Send an Open request to the client */ - if (client->ops && client->ops->open) - ret = client->ops->open(&cdev->lan_info, - client); - if (!ret) { - set_bit(__I40E_CLIENT_INSTANCE_OPENED, - &cdev->state); - } else { - /* remove client instance */ - i40e_client_del_instance(pf, client); + /* Here we handle client opens. If the client is down, but + * the netdev is up, then open the client. + */ + if (!test_bit(__I40E_CLIENT_INSTANCE_OPENED, &cdev->state)) { + if (!test_bit(__I40E_DOWN, &vsi->state) && + client->ops && client->ops->open) { + set_bit(__I40E_CLIENT_INSTANCE_OPENED, &cdev->state); + ret = client->ops->open(&cdev->lan_info, client); + if (ret) { + /* Remove failed client instance */ + clear_bit(__I40E_CLIENT_INSTANCE_OPENED, + &cdev->state); + i40e_client_del_instance(pf); } } - mutex_unlock(&i40e_client_instance_mutex); + } else { + /* Likewise for client close. If the client is up, but the netdev + * is down, then close the client. + */ + if (test_bit(__I40E_DOWN, &vsi->state) && + client->ops && client->ops->close) { + clear_bit(__I40E_CLIENT_INSTANCE_OPENED, &cdev->state); + client->ops->close(&cdev->lan_info, client, false); + i40e_client_release_qvlist(&cdev->lan_info); + } } - mutex_unlock(&i40e_client_mutex); } /** @@ -601,7 +469,6 @@ int i40e_lan_del_device(struct i40e_pf *pf) break; } } - mutex_unlock(&i40e_device_mutex); return ret; } @@ -610,22 +477,24 @@ int i40e_lan_del_device(struct i40e_pf *pf) * i40e_client_release - release client specific resources * @client: pointer to the registered client * - * Return 0 on success or < 0 on error **/ -static int i40e_client_release(struct i40e_client *client) +static void i40e_client_release(struct i40e_client *client) { - struct i40e_client_instance *cdev, *tmp; + struct i40e_client_instance *cdev; + struct i40e_device *ldev; struct i40e_pf *pf; - int ret = 0; - LIST_HEAD(cdevs_tmp); - - mutex_lock(&i40e_client_instance_mutex); - list_for_each_entry_safe(cdev, tmp, &i40e_client_instances, list) { - if (strncmp(cdev->client->name, client->name, - I40E_CLIENT_STR_LENGTH)) + mutex_lock(&i40e_device_mutex); + list_for_each_entry(ldev, &i40e_devices, list) { + pf = ldev->pf; + cdev = pf->cinst; + if (!cdev) continue; - pf = (struct i40e_pf *)cdev->lan_info.pf; + + while (test_and_set_bit(__I40E_SERVICE_SCHED, + &pf->state)) + usleep_range(500, 1000); + if (test_bit(__I40E_CLIENT_INSTANCE_OPENED, &cdev->state)) { if (client->ops && client->ops->close) client->ops->close(&cdev->lan_info, client, @@ -637,18 +506,13 @@ static int i40e_client_release(struct i40e_client *client) "Client %s instance for PF id %d closed\n", client->name, pf->hw.pf_id); } - /* delete the client instance from the list */ - list_move(&cdev->list, &cdevs_tmp); + /* delete the client instance */ + i40e_client_del_instance(pf); dev_info(&pf->pdev->dev, "Deleted client instance of Client %s\n", client->name); + clear_bit(__I40E_SERVICE_SCHED, &pf->state); } - mutex_unlock(&i40e_client_instance_mutex); - - /* free the client device and release its vsi */ - list_for_each_entry_safe(cdev, tmp, &cdevs_tmp, list) { - kfree(cdev); - } - return ret; + mutex_unlock(&i40e_device_mutex); } /** @@ -664,6 +528,7 @@ static void i40e_client_prepare(struct i40e_client *client) mutex_lock(&i40e_device_mutex); list_for_each_entry(ldev, &i40e_devices, list) { pf = ldev->pf; + i40e_client_add_instance(pf); /* Start the client subtask */ pf->flags |= I40E_FLAG_SERVICE_CLIENT_REQUESTED; i40e_service_event_schedule(pf); @@ -792,8 +657,8 @@ static void i40e_client_request_reset(struct i40e_info *ldev, break; default: dev_warn(&pf->pdev->dev, - "Client %s instance for PF id %d request an unsupported reset: %d.\n", - client->name, pf->hw.pf_id, reset_level); + "Client for PF id %d requested an unsupported reset: %d.\n", + pf->hw.pf_id, reset_level); break; } @@ -852,8 +717,8 @@ static int i40e_client_update_vsi_ctxt(struct i40e_info *ldev, } else { update = false; dev_warn(&pf->pdev->dev, - "Client %s instance for PF id %d request an unsupported Config: %x.\n", - client->name, pf->hw.pf_id, flag); + "Client for PF id %d request an unsupported Config: %x.\n", + pf->hw.pf_id, flag); } if (update) { @@ -878,7 +743,6 @@ static int i40e_client_update_vsi_ctxt(struct i40e_info *ldev, int i40e_register_client(struct i40e_client *client) { int ret = 0; - enum i40e_vsi_type vsi_type; if (!client) { ret = -EIO; @@ -891,11 +755,9 @@ int i40e_register_client(struct i40e_client *client) goto out; } - mutex_lock(&i40e_client_mutex); - if (i40e_client_is_registered(client)) { + if (registered_client) { pr_info("i40e: Client %s has already been registered!\n", client->name); - mutex_unlock(&i40e_client_mutex); ret = -EEXIST; goto out; } @@ -908,22 +770,11 @@ int i40e_register_client(struct i40e_client *client) client->version.major, client->version.minor, client->version.build, i40e_client_interface_version_str); - mutex_unlock(&i40e_client_mutex); ret = -EIO; goto out; } - vsi_type = i40e_client_type_to_vsi_type(client->type); - if (vsi_type == I40E_VSI_TYPE_UNKNOWN) { - pr_info("i40e: Failed to register client %s due to unknown client type %d\n", - client->name, client->type); - mutex_unlock(&i40e_client_mutex); - ret = -EIO; - goto out; - } - list_add(&client->list, &i40e_clients); - set_bit(__I40E_CLIENT_REGISTERED, &client->state); - mutex_unlock(&i40e_client_mutex); + registered_client = client; i40e_client_prepare(client); @@ -943,29 +794,21 @@ int i40e_unregister_client(struct i40e_client *client) { int ret = 0; - /* When a unregister request comes through we would have to send - * a close for each of the client instances that were opened. - * client_release function is called to handle this. - */ - mutex_lock(&i40e_client_mutex); - if (!client || i40e_client_release(client)) { - ret = -EIO; - goto out; - } - - /* TODO: check if device is in reset, or if that matters? */ - if (!i40e_client_is_registered(client)) { + if (registered_client != client) { pr_info("i40e: Client %s has not been registered\n", client->name); ret = -ENODEV; goto out; } - clear_bit(__I40E_CLIENT_REGISTERED, &client->state); - list_del(&client->list); - pr_info("i40e: Unregistered client %s with return code %d\n", - client->name, ret); + registered_client = NULL; + /* When a unregister request comes through we would have to send + * a close for each of the client instances that were opened. + * client_release function is called to handle this. + */ + i40e_client_release(client); + + pr_info("i40e: Unregistered client %s\n", client->name); out: - mutex_unlock(&i40e_client_mutex); return ret; } EXPORT_SYMBOL(i40e_unregister_client); diff --git a/drivers/net/ethernet/intel/i40e/i40e_client.h b/drivers/net/ethernet/intel/i40e/i40e_client.h index 528bd79b05fe..15b21a5315b5 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_client.h +++ b/drivers/net/ethernet/intel/i40e/i40e_client.h @@ -57,11 +57,6 @@ enum i40e_client_instance_state { __I40E_CLIENT_INSTANCE_OPENED, }; -enum i40e_client_type { - I40E_CLIENT_IWARP, - I40E_CLIENT_VMDQ2 -}; - struct i40e_ops; struct i40e_client; @@ -214,7 +209,8 @@ struct i40e_client { u32 flags; #define I40E_CLIENT_FLAGS_LAUNCH_ON_PROBE BIT(0) #define I40E_TX_FLAGS_NOTIFY_OTHER_EVENTS BIT(2) - enum i40e_client_type type; + u8 type; +#define I40E_CLIENT_IWARP 0 const struct i40e_client_ops *ops; /* client ops provided by the client */ }; diff --git a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c index a22e26200bcc..a933c6c2aff8 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c +++ b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c @@ -1165,6 +1165,11 @@ static int i40e_get_eeprom_len(struct net_device *netdev) struct i40e_hw *hw = &np->vsi->back->hw; u32 val; +#define X722_EEPROM_SCOPE_LIMIT 0x5B9FFF + if (hw->mac.type == I40E_MAC_X722) { + val = X722_EEPROM_SCOPE_LIMIT + 1; + return val; + } val = (rd32(hw, I40E_GLPCI_LBARCTRL) & I40E_GLPCI_LBARCTRL_FL_SIZE_MASK) >> I40E_GLPCI_LBARCTRL_FL_SIZE_SHIFT; @@ -2712,7 +2717,7 @@ static int i40e_add_fdir_ethtool(struct i40e_vsi *vsi, if (!(pf->flags & I40E_FLAG_FD_SB_ENABLED)) return -EOPNOTSUPP; - if (pf->auto_disable_flags & I40E_FLAG_FD_SB_ENABLED) + if (pf->hw_disabled_flags & I40E_FLAG_FD_SB_ENABLED) return -ENOSPC; if (test_bit(__I40E_RESET_RECOVERY_PENDING, &pf->state) || @@ -3054,7 +3059,7 @@ static u32 i40e_get_priv_flags(struct net_device *dev) I40E_PRIV_FLAGS_FD_ATR : 0; ret_flags |= pf->flags & I40E_FLAG_VEB_STATS_ENABLED ? I40E_PRIV_FLAGS_VEB_STATS : 0; - ret_flags |= pf->auto_disable_flags & I40E_FLAG_HW_ATR_EVICT_CAPABLE ? + ret_flags |= pf->hw_disabled_flags & I40E_FLAG_HW_ATR_EVICT_CAPABLE ? 0 : I40E_PRIV_FLAGS_HW_ATR_EVICT; if (pf->hw.pf_id == 0) { ret_flags |= pf->flags & I40E_FLAG_TRUE_PROMISC_SUPPORT ? @@ -3094,7 +3099,7 @@ static int i40e_set_priv_flags(struct net_device *dev, u32 flags) pf->flags |= I40E_FLAG_FD_ATR_ENABLED; } else { pf->flags &= ~I40E_FLAG_FD_ATR_ENABLED; - pf->auto_disable_flags |= I40E_FLAG_FD_ATR_ENABLED; + pf->hw_disabled_flags |= I40E_FLAG_FD_ATR_ENABLED; /* flush current ATR settings */ set_bit(__I40E_FD_FLUSH_REQUESTED, &pf->state); @@ -3139,9 +3144,9 @@ static int i40e_set_priv_flags(struct net_device *dev, u32 flags) if ((flags & I40E_PRIV_FLAGS_HW_ATR_EVICT) && (pf->flags & I40E_FLAG_HW_ATR_EVICT_CAPABLE)) - pf->auto_disable_flags &= ~I40E_FLAG_HW_ATR_EVICT_CAPABLE; + pf->hw_disabled_flags &= ~I40E_FLAG_HW_ATR_EVICT_CAPABLE; else - pf->auto_disable_flags |= I40E_FLAG_HW_ATR_EVICT_CAPABLE; + pf->hw_disabled_flags |= I40E_FLAG_HW_ATR_EVICT_CAPABLE; /* if needed, issue reset to cause things to take effect */ if (reset_required) diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index e8a8351c8ea9..9df0d86812e7 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -39,9 +39,9 @@ static const char i40e_driver_string[] = #define DRV_KERN "-k" -#define DRV_VERSION_MAJOR 1 -#define DRV_VERSION_MINOR 6 -#define DRV_VERSION_BUILD 27 +#define DRV_VERSION_MAJOR 2 +#define DRV_VERSION_MINOR 1 +#define DRV_VERSION_BUILD 7 #define DRV_VERSION __stringify(DRV_VERSION_MAJOR) "." \ __stringify(DRV_VERSION_MINOR) "." \ __stringify(DRV_VERSION_BUILD) DRV_KERN @@ -1101,13 +1101,13 @@ static void i40e_update_pf_stats(struct i40e_pf *pf) &osd->rx_lpi_count, &nsd->rx_lpi_count); if (pf->flags & I40E_FLAG_FD_SB_ENABLED && - !(pf->auto_disable_flags & I40E_FLAG_FD_SB_ENABLED)) + !(pf->hw_disabled_flags & I40E_FLAG_FD_SB_ENABLED)) nsd->fd_sb_status = true; else nsd->fd_sb_status = false; if (pf->flags & I40E_FLAG_FD_ATR_ENABLED && - !(pf->auto_disable_flags & I40E_FLAG_FD_ATR_ENABLED)) + !(pf->hw_disabled_flags & I40E_FLAG_FD_ATR_ENABLED)) nsd->fd_atr_status = true; else nsd->fd_atr_status = false; @@ -2487,13 +2487,15 @@ static int i40e_change_mtu(struct net_device *netdev, int new_mtu) { struct i40e_netdev_priv *np = netdev_priv(netdev); struct i40e_vsi *vsi = np->vsi; + struct i40e_pf *pf = vsi->back; netdev_info(netdev, "changing MTU from %d to %d\n", netdev->mtu, new_mtu); netdev->mtu = new_mtu; if (netif_running(netdev)) i40e_vsi_reinit_locked(vsi); - i40e_notify_client_of_l2_param_changes(vsi); + pf->flags |= (I40E_FLAG_SERVICE_CLIENT_REQUESTED | + I40E_FLAG_CLIENT_L2_CHANGE); return 0; } @@ -4463,17 +4465,16 @@ static void i40e_napi_disable_all(struct i40e_vsi *vsi) **/ static void i40e_vsi_close(struct i40e_vsi *vsi) { - bool reset = false; - + struct i40e_pf *pf = vsi->back; if (!test_and_set_bit(__I40E_DOWN, &vsi->state)) i40e_down(vsi); i40e_vsi_free_irq(vsi); i40e_vsi_free_tx_resources(vsi); i40e_vsi_free_rx_resources(vsi); vsi->current_netdev_flags = 0; - if (test_bit(__I40E_RESET_RECOVERY_PENDING, &vsi->back->state)) - reset = true; - i40e_notify_client_of_netdev_close(vsi, reset); + pf->flags |= I40E_FLAG_SERVICE_CLIENT_REQUESTED; + if (test_bit(__I40E_RESET_RECOVERY_PENDING, &pf->state)) + pf->flags |= I40E_FLAG_CLIENT_RESET; } /** @@ -5466,7 +5467,7 @@ static int i40e_up_complete(struct i40e_vsi *vsi) /* reset fd counters */ pf->fd_add_err = pf->fd_atr_cnt = 0; if (pf->fd_tcp_rule > 0) { - pf->auto_disable_flags |= I40E_FLAG_FD_ATR_ENABLED; + pf->hw_disabled_flags |= I40E_FLAG_FD_ATR_ENABLED; if (I40E_DEBUG_FD & pf->hw.debug_mask) dev_info(&pf->pdev->dev, "Forcing ATR off, sideband rules for TCP/IPv4 exist\n"); pf->fd_tcp_rule = 0; @@ -5542,8 +5543,6 @@ void i40e_down(struct i40e_vsi *vsi) i40e_clean_rx_ring(vsi->rx_rings[i]); } - i40e_notify_client_of_netdev_close(vsi, false); - } /** @@ -5612,9 +5611,12 @@ static int __i40e_setup_tc(struct net_device *netdev, u32 handle, __be16 proto, struct tc_to_netdev *tc) #endif { - if (handle != TC_H_ROOT || tc->type != TC_SETUP_MQPRIO) + if (tc->type != TC_SETUP_MQPRIO) return -EINVAL; - return i40e_setup_tc(netdev, tc->tc); + + tc->mqprio->hw = TC_MQPRIO_HW_OFFLOAD_TCS; + + return i40e_setup_tc(netdev, tc->mqprio->num_tc); } /** @@ -6021,8 +6023,8 @@ static int i40e_handle_lldp_event(struct i40e_pf *pf, i40e_service_event_schedule(pf); } else { i40e_pf_unquiesce_all_vsi(pf); - /* Notify the client for the DCB changes */ - i40e_notify_client_of_l2_param_changes(pf->vsi[pf->lan_vsi]); + pf->flags |= (I40E_FLAG_SERVICE_CLIENT_REQUESTED | + I40E_FLAG_CLIENT_L2_CHANGE); } exit: @@ -6144,8 +6146,8 @@ void i40e_fdir_check_and_reenable(struct i40e_pf *pf) (pf->fd_add_err == 0) || (i40e_get_current_atr_cnt(pf) < pf->fd_atr_cnt)) { if ((pf->flags & I40E_FLAG_FD_SB_ENABLED) && - (pf->auto_disable_flags & I40E_FLAG_FD_SB_ENABLED)) { - pf->auto_disable_flags &= ~I40E_FLAG_FD_SB_ENABLED; + (pf->hw_disabled_flags & I40E_FLAG_FD_SB_ENABLED)) { + pf->hw_disabled_flags &= ~I40E_FLAG_FD_SB_ENABLED; if (I40E_DEBUG_FD & pf->hw.debug_mask) dev_info(&pf->pdev->dev, "FD Sideband/ntuple is being enabled since we have space in the table now\n"); } @@ -6156,9 +6158,9 @@ void i40e_fdir_check_and_reenable(struct i40e_pf *pf) */ if (fcnt_prog < (fcnt_avail - I40E_FDIR_BUFFER_HEAD_ROOM * 2)) { if ((pf->flags & I40E_FLAG_FD_ATR_ENABLED) && - (pf->auto_disable_flags & I40E_FLAG_FD_ATR_ENABLED) && + (pf->hw_disabled_flags & I40E_FLAG_FD_ATR_ENABLED) && (pf->fd_tcp_rule == 0)) { - pf->auto_disable_flags &= ~I40E_FLAG_FD_ATR_ENABLED; + pf->hw_disabled_flags &= ~I40E_FLAG_FD_ATR_ENABLED; if (I40E_DEBUG_FD & pf->hw.debug_mask) dev_info(&pf->pdev->dev, "ATR is being enabled since we have space in the table and there are no conflicting ntuple rules\n"); } @@ -6210,7 +6212,7 @@ static void i40e_fdir_flush_and_replay(struct i40e_pf *pf) } pf->fd_flush_timestamp = jiffies; - pf->auto_disable_flags |= I40E_FLAG_FD_ATR_ENABLED; + pf->hw_disabled_flags |= I40E_FLAG_FD_ATR_ENABLED; /* flush all filters */ wr32(&pf->hw, I40E_PFQF_CTL_1, I40E_PFQF_CTL_1_CLEARFDTABLE_MASK); @@ -6230,7 +6232,7 @@ static void i40e_fdir_flush_and_replay(struct i40e_pf *pf) /* replay sideband filters */ i40e_fdir_filter_restore(pf->vsi[pf->lan_vsi]); if (!disable_atr) - pf->auto_disable_flags &= ~I40E_FLAG_FD_ATR_ENABLED; + pf->hw_disabled_flags &= ~I40E_FLAG_FD_ATR_ENABLED; clear_bit(__I40E_FD_FLUSH_REQUESTED, &pf->state); if (I40E_DEBUG_FD & pf->hw.debug_mask) dev_info(&pf->pdev->dev, "FD Filter table flushed and FD-SB replayed.\n"); @@ -7411,7 +7413,18 @@ static void i40e_service_task(struct work_struct *work) i40e_vc_process_vflr_event(pf); i40e_watchdog_subtask(pf); i40e_fdir_reinit_subtask(pf); - i40e_client_subtask(pf); + if (pf->flags & I40E_FLAG_CLIENT_RESET) { + /* Client subtask will reopen next time through. */ + i40e_notify_client_of_netdev_close(pf->vsi[pf->lan_vsi], true); + pf->flags &= ~I40E_FLAG_CLIENT_RESET; + } else { + i40e_client_subtask(pf); + if (pf->flags & I40E_FLAG_CLIENT_L2_CHANGE) { + i40e_notify_client_of_l2_param_changes( + pf->vsi[pf->lan_vsi]); + pf->flags &= ~I40E_FLAG_CLIENT_L2_CHANGE; + } + } i40e_sync_filters_subtask(pf); i40e_sync_udp_filters_subtask(pf); i40e_clean_adminq_subtask(pf); @@ -7809,6 +7822,7 @@ static int i40e_reserve_msix_vectors(struct i40e_pf *pf, int vectors) static int i40e_init_msix(struct i40e_pf *pf) { struct i40e_hw *hw = &pf->hw; + int cpus, extra_vectors; int vectors_left; int v_budget, i; int v_actual; @@ -7844,10 +7858,16 @@ static int i40e_init_msix(struct i40e_pf *pf) vectors_left--; } - /* reserve vectors for the main PF traffic queues */ - pf->num_lan_msix = min_t(int, num_online_cpus(), vectors_left); + /* reserve some vectors for the main PF traffic queues. Initially we + * only reserve at most 50% of the available vectors, in the case that + * the number of online CPUs is large. This ensures that we can enable + * extra features as well. Once we've enabled the other features, we + * will use any remaining vectors to reach as close as we can to the + * number of online CPUs. + */ + cpus = num_online_cpus(); + pf->num_lan_msix = min_t(int, cpus, vectors_left / 2); vectors_left -= pf->num_lan_msix; - v_budget += pf->num_lan_msix; /* reserve one vector for sideband flow director */ if (pf->flags & I40E_FLAG_FD_SB_ENABLED) { @@ -7910,6 +7930,23 @@ static int i40e_init_msix(struct i40e_pf *pf) } } + /* On systems with a large number of SMP cores, we previously limited + * the number of vectors for num_lan_msix to be at most 50% of the + * available vectors, to allow for other features. Now, we add back + * the remaining vectors. However, we ensure that the total + * num_lan_msix will not exceed num_online_cpus(). To do this, we + * calculate the number of vectors we can add without going over the + * cap of CPUs. For systems with a small number of CPUs this will be + * zero. + */ + extra_vectors = min_t(int, cpus - pf->num_lan_msix, vectors_left); + pf->num_lan_msix += extra_vectors; + vectors_left -= extra_vectors; + + WARN(vectors_left < 0, + "Calculation of remaining vectors underflowed. This is an accounting bug when determining total MSI-X vectors.\n"); + + v_budget += pf->num_lan_msix; pf->msix_entries = kcalloc(v_budget, sizeof(struct msix_entry), GFP_KERNEL); if (!pf->msix_entries) @@ -8360,13 +8397,10 @@ static int i40e_config_rss_reg(struct i40e_vsi *vsi, const u8 *seed, if (vsi->type == I40E_VSI_MAIN) { for (i = 0; i <= I40E_PFQF_HKEY_MAX_INDEX; i++) - i40e_write_rx_ctl(hw, I40E_PFQF_HKEY(i), - seed_dw[i]); + wr32(hw, I40E_PFQF_HKEY(i), seed_dw[i]); } else if (vsi->type == I40E_VSI_SRIOV) { for (i = 0; i <= I40E_VFQF_HKEY1_MAX_INDEX; i++) - i40e_write_rx_ctl(hw, - I40E_VFQF_HKEY1(i, vf_id), - seed_dw[i]); + wr32(hw, I40E_VFQF_HKEY1(i, vf_id), seed_dw[i]); } else { dev_err(&pf->pdev->dev, "Cannot set RSS seed - invalid VSI type\n"); } @@ -8384,9 +8418,7 @@ static int i40e_config_rss_reg(struct i40e_vsi *vsi, const u8 *seed, if (lut_size != I40E_VF_HLUT_ARRAY_SIZE) return -EINVAL; for (i = 0; i <= I40E_VFQF_HLUT_MAX_INDEX; i++) - i40e_write_rx_ctl(hw, - I40E_VFQF_HLUT1(i, vf_id), - lut_dw[i]); + wr32(hw, I40E_VFQF_HLUT1(i, vf_id), lut_dw[i]); } else { dev_err(&pf->pdev->dev, "Cannot set RSS LUT - invalid VSI type\n"); } @@ -8843,9 +8875,9 @@ static int i40e_sw_init(struct i40e_pf *pf) (pf->hw.aq.api_min_ver > 4))) { /* Supported in FW API version higher than 1.4 */ pf->flags |= I40E_FLAG_GENEVE_OFFLOAD_CAPABLE; - pf->auto_disable_flags = I40E_FLAG_HW_ATR_EVICT_CAPABLE; + pf->hw_disabled_flags = I40E_FLAG_HW_ATR_EVICT_CAPABLE; } else { - pf->auto_disable_flags = I40E_FLAG_HW_ATR_EVICT_CAPABLE; + pf->hw_disabled_flags = I40E_FLAG_HW_ATR_EVICT_CAPABLE; } pf->eeprom_version = 0xDEAD; @@ -8906,14 +8938,14 @@ bool i40e_set_ntuple(struct i40e_pf *pf, netdev_features_t features) i40e_fdir_filter_exit(pf); } pf->flags &= ~I40E_FLAG_FD_SB_ENABLED; - pf->auto_disable_flags &= ~I40E_FLAG_FD_SB_ENABLED; + pf->hw_disabled_flags &= ~I40E_FLAG_FD_SB_ENABLED; /* reset fd counters */ pf->fd_add_err = pf->fd_atr_cnt = pf->fd_tcp_rule = 0; pf->fdir_pf_active_filters = 0; /* if ATR was auto disabled it can be re-enabled. */ if ((pf->flags & I40E_FLAG_FD_ATR_ENABLED) && - (pf->auto_disable_flags & I40E_FLAG_FD_ATR_ENABLED)) { - pf->auto_disable_flags &= ~I40E_FLAG_FD_ATR_ENABLED; + (pf->hw_disabled_flags & I40E_FLAG_FD_ATR_ENABLED)) { + pf->hw_disabled_flags &= ~I40E_FLAG_FD_ATR_ENABLED; if (I40E_DEBUG_FD & pf->hw.debug_mask) dev_info(&pf->pdev->dev, "ATR re-enabled.\n"); } @@ -9432,10 +9464,10 @@ static int i40e_config_netdev(struct i40e_vsi *vsi) if (vsi->type == I40E_VSI_MAIN) { SET_NETDEV_DEV(netdev, &pf->pdev->dev); ether_addr_copy(mac_addr, hw->mac.perm_addr); - /* The following steps are necessary to prevent reception - * of tagged packets - some older NVM configurations load a - * default a MAC-VLAN filter that accepts any tagged packet - * which must be replaced by a normal filter. + /* The following steps are necessary to properly keep track of + * MAC-VLAN filters loaded into firmware - first we remove + * filter that is automatically generated by firmware and then + * add new filter both to the driver hash table and firmware. */ i40e_rm_default_mac_filter(vsi, mac_addr); spin_lock_bh(&vsi->mac_filter_hash_lock); diff --git a/drivers/net/ethernet/intel/i40e/i40e_nvm.c b/drivers/net/ethernet/intel/i40e/i40e_nvm.c index 38ee18f11124..800bd55d0159 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_nvm.c +++ b/drivers/net/ethernet/intel/i40e/i40e_nvm.c @@ -292,14 +292,14 @@ i40e_status i40e_read_nvm_word(struct i40e_hw *hw, u16 offset, { 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_acquire_nvm(hw, I40E_RESOURCE_READ); + if (!ret_code) { + if (hw->flags & I40E_HW_FLAG_AQ_SRCTL_ACCESS_ENABLE) { 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); } - } else { - ret_code = i40e_read_nvm_word_srctl(hw, offset, data); + i40e_release_nvm(hw); } return ret_code; } diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c index 97d46058d71d..6eb5dc4168f3 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c +++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c @@ -291,7 +291,7 @@ static int i40e_add_del_fdir_tcpv4(struct i40e_vsi *vsi, if ((pf->flags & I40E_FLAG_FD_ATR_ENABLED) && I40E_DEBUG_FD & pf->hw.debug_mask) dev_info(&pf->pdev->dev, "Forcing ATR off, sideband rules for TCP/IPv4 flow being applied\n"); - pf->auto_disable_flags |= I40E_FLAG_FD_ATR_ENABLED; + pf->hw_disabled_flags |= I40E_FLAG_FD_ATR_ENABLED; } else { pf->fd_tcp_rule = (pf->fd_tcp_rule > 0) ? (pf->fd_tcp_rule - 1) : 0; @@ -299,7 +299,7 @@ static int i40e_add_del_fdir_tcpv4(struct i40e_vsi *vsi, if ((pf->flags & I40E_FLAG_FD_ATR_ENABLED) && I40E_DEBUG_FD & pf->hw.debug_mask) dev_info(&pf->pdev->dev, "ATR re-enabled due to no sideband TCP/IPv4 rules\n"); - pf->auto_disable_flags &= ~I40E_FLAG_FD_ATR_ENABLED; + pf->hw_disabled_flags &= ~I40E_FLAG_FD_ATR_ENABLED; } } @@ -484,8 +484,8 @@ static void i40e_fd_handle_status(struct i40e_ring *rx_ring, pf->fd_atr_cnt = i40e_get_current_atr_cnt(pf); if ((rx_desc->wb.qword0.hi_dword.fd_id == 0) && - (pf->auto_disable_flags & I40E_FLAG_FD_SB_ENABLED)) { - pf->auto_disable_flags |= I40E_FLAG_FD_ATR_ENABLED; + (pf->hw_disabled_flags & I40E_FLAG_FD_SB_ENABLED)) { + pf->hw_disabled_flags |= I40E_FLAG_FD_ATR_ENABLED; set_bit(__I40E_FD_FLUSH_REQUESTED, &pf->state); } @@ -498,11 +498,11 @@ static void i40e_fd_handle_status(struct i40e_ring *rx_ring, */ if (fcnt_prog >= (fcnt_avail - I40E_FDIR_BUFFER_FULL_MARGIN)) { if ((pf->flags & I40E_FLAG_FD_SB_ENABLED) && - !(pf->auto_disable_flags & + !(pf->hw_disabled_flags & I40E_FLAG_FD_SB_ENABLED)) { if (I40E_DEBUG_FD & pf->hw.debug_mask) dev_warn(&pdev->dev, "FD filter space full, new ntuple rules will not be added\n"); - pf->auto_disable_flags |= + pf->hw_disabled_flags |= I40E_FLAG_FD_SB_ENABLED; } } @@ -1010,7 +1010,6 @@ err: **/ void i40e_clean_rx_ring(struct i40e_ring *rx_ring) { - struct device *dev = rx_ring->dev; unsigned long bi_size; u16 i; @@ -1030,7 +1029,20 @@ void i40e_clean_rx_ring(struct i40e_ring *rx_ring) if (!rx_bi->page) continue; - dma_unmap_page(dev, rx_bi->dma, PAGE_SIZE, DMA_FROM_DEVICE); + /* Invalidate cache lines that may have been written to by + * device so that we avoid corrupting memory. + */ + dma_sync_single_range_for_cpu(rx_ring->dev, + rx_bi->dma, + rx_bi->page_offset, + I40E_RXBUFFER_2048, + DMA_FROM_DEVICE); + + /* free resources associated with mapping */ + dma_unmap_page_attrs(rx_ring->dev, rx_bi->dma, + PAGE_SIZE, + DMA_FROM_DEVICE, + I40E_RX_DMA_ATTR); __free_pages(rx_bi->page, 0); rx_bi->page = NULL; @@ -1159,7 +1171,10 @@ static bool i40e_alloc_mapped_page(struct i40e_ring *rx_ring, } /* map page for use */ - dma = dma_map_page(rx_ring->dev, page, 0, PAGE_SIZE, DMA_FROM_DEVICE); + dma = dma_map_page_attrs(rx_ring->dev, page, 0, + PAGE_SIZE, + DMA_FROM_DEVICE, + I40E_RX_DMA_ATTR); /* if mapping failed free memory back to system since * there isn't much point in holding memory we can't use @@ -1219,6 +1234,12 @@ bool i40e_alloc_rx_buffers(struct i40e_ring *rx_ring, u16 cleaned_count) if (!i40e_alloc_mapped_page(rx_ring, bi)) goto no_buffers; + /* sync the buffer for use by the device */ + dma_sync_single_range_for_device(rx_ring->dev, bi->dma, + bi->page_offset, + I40E_RXBUFFER_2048, + DMA_FROM_DEVICE); + /* Refresh the desc even if buffer_addrs didn't change * because each write-back erases this info. */ @@ -1685,8 +1706,8 @@ struct sk_buff *i40e_fetch_rx_buffer(struct i40e_ring *rx_ring, rx_ring->rx_stats.page_reuse_count++; } else { /* we are not reusing the buffer so unmap it */ - dma_unmap_page(rx_ring->dev, rx_buffer->dma, PAGE_SIZE, - DMA_FROM_DEVICE); + dma_unmap_page_attrs(rx_ring->dev, rx_buffer->dma, PAGE_SIZE, + DMA_FROM_DEVICE, I40E_RX_DMA_ATTR); } /* clear contents of buffer_info */ @@ -2079,7 +2100,7 @@ static void i40e_atr(struct i40e_ring *tx_ring, struct sk_buff *skb, if (!(pf->flags & I40E_FLAG_FD_ATR_ENABLED)) return; - if ((pf->auto_disable_flags & I40E_FLAG_FD_ATR_ENABLED)) + if ((pf->hw_disabled_flags & I40E_FLAG_FD_ATR_ENABLED)) return; /* if sampling is disabled do nothing */ @@ -2113,10 +2134,10 @@ static void i40e_atr(struct i40e_ring *tx_ring, struct sk_buff *skb, th = (struct tcphdr *)(hdr.network + hlen); /* Due to lack of space, no more new filters can be programmed */ - if (th->syn && (pf->auto_disable_flags & I40E_FLAG_FD_ATR_ENABLED)) + if (th->syn && (pf->hw_disabled_flags & I40E_FLAG_FD_ATR_ENABLED)) return; if ((pf->flags & I40E_FLAG_HW_ATR_EVICT_CAPABLE) && - (!(pf->auto_disable_flags & I40E_FLAG_HW_ATR_EVICT_CAPABLE))) { + (!(pf->hw_disabled_flags & I40E_FLAG_HW_ATR_EVICT_CAPABLE))) { /* HW ATR eviction will take care of removing filters on FIN * and RST packets. */ @@ -2179,7 +2200,7 @@ static void i40e_atr(struct i40e_ring *tx_ring, struct sk_buff *skb, I40E_TXD_FLTR_QW1_CNTINDEX_MASK; if ((pf->flags & I40E_FLAG_HW_ATR_EVICT_CAPABLE) && - (!(pf->auto_disable_flags & I40E_FLAG_HW_ATR_EVICT_CAPABLE))) + (!(pf->hw_disabled_flags & I40E_FLAG_HW_ATR_EVICT_CAPABLE))) dtype_cmd |= I40E_TXD_FLTR_QW1_ATR_MASK; fdir_desc->qindex_flex_ptype_vsi = cpu_to_le32(flex_ptype); diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.h b/drivers/net/ethernet/intel/i40e/i40e_txrx.h index f80979025c01..49c7b2089d8e 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_txrx.h +++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.h @@ -133,6 +133,9 @@ enum i40e_dyn_idx_t { #define I40E_RX_HDR_SIZE I40E_RXBUFFER_256 #define i40e_rx_desc i40e_32byte_rx_desc +#define I40E_RX_DMA_ATTR \ + (DMA_ATTR_SKIP_CPU_SYNC | DMA_ATTR_WEAK_ORDERING) + /** * i40e_test_staterr - tests bits in Rx descriptor status and error fields * @rx_desc: pointer to receive descriptor (in le64 format) diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c index 78460c52b7c4..cfe8b78dac0e 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c +++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c @@ -702,10 +702,8 @@ static int i40e_alloc_vsi_res(struct i40e_vf *vf, enum i40e_vsi_type type) dev_info(&pf->pdev->dev, "Could not allocate VF broadcast filter\n"); spin_unlock_bh(&vsi->mac_filter_hash_lock); - i40e_write_rx_ctl(&pf->hw, I40E_VFQF_HENA1(0, vf->vf_id), - (u32)hena); - i40e_write_rx_ctl(&pf->hw, I40E_VFQF_HENA1(1, vf->vf_id), - (u32)(hena >> 32)); + wr32(&pf->hw, I40E_VFQF_HENA1(0, vf->vf_id), (u32)hena); + wr32(&pf->hw, I40E_VFQF_HENA1(1, vf->vf_id), (u32)(hena >> 32)); } /* program mac filter */ @@ -1359,7 +1357,7 @@ static int i40e_vc_get_vf_resources_msg(struct i40e_vf *vf, u8 *msg) if (!vsi->info.pvid) vfres->vf_offload_flags |= I40E_VIRTCHNL_VF_OFFLOAD_VLAN; - if (i40e_vf_client_capable(pf, vf->vf_id, I40E_CLIENT_IWARP) && + if (i40e_vf_client_capable(pf, vf->vf_id) && (vf->driver_caps & I40E_VIRTCHNL_VF_OFFLOAD_IWARP)) { vfres->vf_offload_flags |= I40E_VIRTCHNL_VF_OFFLOAD_IWARP; set_bit(I40E_VF_STAT_IWARPENA, &vf->vf_states); @@ -1853,7 +1851,7 @@ error_param: } /* If the VF is not trusted restrict the number of MAC/VLAN it can program */ -#define I40E_VC_MAX_MAC_ADDR_PER_VF 8 +#define I40E_VC_MAX_MAC_ADDR_PER_VF 12 #define I40E_VC_MAX_VLAN_PER_VF 8 /** diff --git a/drivers/net/ethernet/intel/i40evf/Makefile b/drivers/net/ethernet/intel/i40evf/Makefile index 3a423836a565..827c7a6ed0ba 100644 --- a/drivers/net/ethernet/intel/i40evf/Makefile +++ b/drivers/net/ethernet/intel/i40evf/Makefile @@ -32,5 +32,5 @@ obj-$(CONFIG_I40EVF) += i40evf.o i40evf-objs := i40evf_main.o i40evf_ethtool.o i40evf_virtchnl.o \ - i40e_txrx.o i40e_common.o i40e_adminq.o + i40e_txrx.o i40e_common.o i40e_adminq.o i40evf_client.o diff --git a/drivers/net/ethernet/intel/i40evf/i40e_adminq_cmd.h b/drivers/net/ethernet/intel/i40evf/i40e_adminq_cmd.h index eeb9864bc5b1..c28cb8f27243 100644 --- a/drivers/net/ethernet/intel/i40evf/i40e_adminq_cmd.h +++ b/drivers/net/ethernet/intel/i40evf/i40e_adminq_cmd.h @@ -132,6 +132,10 @@ enum i40e_admin_queue_opc { i40e_aqc_opc_list_func_capabilities = 0x000A, i40e_aqc_opc_list_dev_capabilities = 0x000B, + /* Proxy commands */ + i40e_aqc_opc_set_proxy_config = 0x0104, + i40e_aqc_opc_set_ns_proxy_table_entry = 0x0105, + /* LAA */ i40e_aqc_opc_mac_address_read = 0x0107, i40e_aqc_opc_mac_address_write = 0x0108, @@ -139,6 +143,10 @@ enum i40e_admin_queue_opc { /* PXE */ i40e_aqc_opc_clear_pxe_mode = 0x0110, + /* WoL commands */ + i40e_aqc_opc_set_wol_filter = 0x0120, + i40e_aqc_opc_get_wake_reason = 0x0121, + /* internal switch commands */ i40e_aqc_opc_get_switch_config = 0x0200, i40e_aqc_opc_add_statistics = 0x0201, @@ -177,6 +185,7 @@ enum i40e_admin_queue_opc { i40e_aqc_opc_remove_control_packet_filter = 0x025B, i40e_aqc_opc_add_cloud_filters = 0x025C, i40e_aqc_opc_remove_cloud_filters = 0x025D, + i40e_aqc_opc_clear_wol_switch_filters = 0x025E, i40e_aqc_opc_add_mirror_rule = 0x0260, i40e_aqc_opc_delete_mirror_rule = 0x0261, @@ -558,6 +567,56 @@ struct i40e_aqc_clear_pxe { I40E_CHECK_CMD_LENGTH(i40e_aqc_clear_pxe); +/* Set WoL Filter (0x0120) */ + +struct i40e_aqc_set_wol_filter { + __le16 filter_index; +#define I40E_AQC_MAX_NUM_WOL_FILTERS 8 +#define I40E_AQC_SET_WOL_FILTER_TYPE_MAGIC_SHIFT 15 +#define I40E_AQC_SET_WOL_FILTER_TYPE_MAGIC_MASK (0x1 << \ + I40E_AQC_SET_WOL_FILTER_TYPE_MAGIC_SHIFT) + +#define I40E_AQC_SET_WOL_FILTER_INDEX_SHIFT 0 +#define I40E_AQC_SET_WOL_FILTER_INDEX_MASK (0x7 << \ + I40E_AQC_SET_WOL_FILTER_INDEX_SHIFT) + __le16 cmd_flags; +#define I40E_AQC_SET_WOL_FILTER 0x8000 +#define I40E_AQC_SET_WOL_FILTER_NO_TCO_WOL 0x4000 +#define I40E_AQC_SET_WOL_FILTER_ACTION_CLEAR 0 +#define I40E_AQC_SET_WOL_FILTER_ACTION_SET 1 + __le16 valid_flags; +#define I40E_AQC_SET_WOL_FILTER_ACTION_VALID 0x8000 +#define I40E_AQC_SET_WOL_FILTER_NO_TCO_ACTION_VALID 0x4000 + u8 reserved[2]; + __le32 address_high; + __le32 address_low; +}; + +I40E_CHECK_CMD_LENGTH(i40e_aqc_set_wol_filter); + +struct i40e_aqc_set_wol_filter_data { + u8 filter[128]; + u8 mask[16]; +}; + +I40E_CHECK_STRUCT_LEN(0x90, i40e_aqc_set_wol_filter_data); + +/* Get Wake Reason (0x0121) */ + +struct i40e_aqc_get_wake_reason_completion { + u8 reserved_1[2]; + __le16 wake_reason; +#define I40E_AQC_GET_WAKE_UP_REASON_WOL_REASON_MATCHED_INDEX_SHIFT 0 +#define I40E_AQC_GET_WAKE_UP_REASON_WOL_REASON_MATCHED_INDEX_MASK (0xFF << \ + I40E_AQC_GET_WAKE_UP_REASON_WOL_REASON_MATCHED_INDEX_SHIFT) +#define I40E_AQC_GET_WAKE_UP_REASON_WOL_REASON_RESERVED_SHIFT 8 +#define I40E_AQC_GET_WAKE_UP_REASON_WOL_REASON_RESERVED_MASK (0xFF << \ + I40E_AQC_GET_WAKE_UP_REASON_WOL_REASON_RESERVED_SHIFT) + u8 reserved_2[12]; +}; + +I40E_CHECK_CMD_LENGTH(i40e_aqc_get_wake_reason_completion); + /* Switch configuration commands (0x02xx) */ /* Used by many indirect commands that only pass an seid and a buffer in the @@ -640,6 +699,8 @@ struct i40e_aqc_set_port_parameters { #define I40E_AQ_SET_P_PARAMS_PAD_SHORT_PACKETS 2 /* must set! */ #define I40E_AQ_SET_P_PARAMS_DOUBLE_VLAN_ENA 4 __le16 bad_frame_vsi; +#define I40E_AQ_SET_P_PARAMS_BFRAME_SEID_SHIFT 0x0 +#define I40E_AQ_SET_P_PARAMS_BFRAME_SEID_MASK 0x3FF __le16 default_seid; /* reserved for command */ u8 reserved[10]; }; @@ -691,6 +752,7 @@ I40E_CHECK_STRUCT_LEN(0x10, i40e_aqc_switch_resource_alloc_element_resp); /* Set Switch Configuration (direct 0x0205) */ struct i40e_aqc_set_switch_config { __le16 flags; +/* flags used for both fields below */ #define I40E_AQ_SET_SWITCH_CFG_PROMISC 0x0001 #define I40E_AQ_SET_SWITCH_CFG_L2_FILTER 0x0002 __le16 valid_flags; @@ -1839,11 +1901,12 @@ struct i40e_aqc_get_link_status { #define I40E_AQ_CONFIG_FEC_RS_ENA 0x02 #define I40E_AQ_CONFIG_CRC_ENA 0x04 #define I40E_AQ_CONFIG_PACING_MASK 0x78 - u8 external_power_ability; + u8 power_desc; #define I40E_AQ_LINK_POWER_CLASS_1 0x00 #define I40E_AQ_LINK_POWER_CLASS_2 0x01 #define I40E_AQ_LINK_POWER_CLASS_3 0x02 #define I40E_AQ_LINK_POWER_CLASS_4 0x03 +#define I40E_AQ_PWR_CLASS_MASK 0x03 u8 reserved[4]; }; diff --git a/drivers/net/ethernet/intel/i40evf/i40e_txrx.c b/drivers/net/ethernet/intel/i40evf/i40e_txrx.c index c91fcf43ccbc..d7790c08e523 100644 --- a/drivers/net/ethernet/intel/i40evf/i40e_txrx.c +++ b/drivers/net/ethernet/intel/i40evf/i40e_txrx.c @@ -493,7 +493,6 @@ err: **/ void i40evf_clean_rx_ring(struct i40e_ring *rx_ring) { - struct device *dev = rx_ring->dev; unsigned long bi_size; u16 i; @@ -513,7 +512,20 @@ void i40evf_clean_rx_ring(struct i40e_ring *rx_ring) if (!rx_bi->page) continue; - dma_unmap_page(dev, rx_bi->dma, PAGE_SIZE, DMA_FROM_DEVICE); + /* Invalidate cache lines that may have been written to by + * device so that we avoid corrupting memory. + */ + dma_sync_single_range_for_cpu(rx_ring->dev, + rx_bi->dma, + rx_bi->page_offset, + I40E_RXBUFFER_2048, + DMA_FROM_DEVICE); + + /* free resources associated with mapping */ + dma_unmap_page_attrs(rx_ring->dev, rx_bi->dma, + PAGE_SIZE, + DMA_FROM_DEVICE, + I40E_RX_DMA_ATTR); __free_pages(rx_bi->page, 0); rx_bi->page = NULL; @@ -642,7 +654,10 @@ static bool i40e_alloc_mapped_page(struct i40e_ring *rx_ring, } /* map page for use */ - dma = dma_map_page(rx_ring->dev, page, 0, PAGE_SIZE, DMA_FROM_DEVICE); + dma = dma_map_page_attrs(rx_ring->dev, page, 0, + PAGE_SIZE, + DMA_FROM_DEVICE, + I40E_RX_DMA_ATTR); /* if mapping failed free memory back to system since * there isn't much point in holding memory we can't use @@ -702,6 +717,12 @@ bool i40evf_alloc_rx_buffers(struct i40e_ring *rx_ring, u16 cleaned_count) if (!i40e_alloc_mapped_page(rx_ring, bi)) goto no_buffers; + /* sync the buffer for use by the device */ + dma_sync_single_range_for_device(rx_ring->dev, bi->dma, + bi->page_offset, + I40E_RXBUFFER_2048, + DMA_FROM_DEVICE); + /* Refresh the desc even if buffer_addrs didn't change * because each write-back erases this info. */ @@ -1158,8 +1179,8 @@ struct sk_buff *i40evf_fetch_rx_buffer(struct i40e_ring *rx_ring, rx_ring->rx_stats.page_reuse_count++; } else { /* we are not reusing the buffer so unmap it */ - dma_unmap_page(rx_ring->dev, rx_buffer->dma, PAGE_SIZE, - DMA_FROM_DEVICE); + dma_unmap_page_attrs(rx_ring->dev, rx_buffer->dma, PAGE_SIZE, + DMA_FROM_DEVICE, I40E_RX_DMA_ATTR); } /* clear contents of buffer_info */ diff --git a/drivers/net/ethernet/intel/i40evf/i40e_txrx.h b/drivers/net/ethernet/intel/i40evf/i40e_txrx.h index 8274ba68bd32..013512124e6a 100644 --- a/drivers/net/ethernet/intel/i40evf/i40e_txrx.h +++ b/drivers/net/ethernet/intel/i40evf/i40e_txrx.h @@ -120,6 +120,9 @@ enum i40e_dyn_idx_t { #define I40E_RX_HDR_SIZE I40E_RXBUFFER_256 #define i40e_rx_desc i40e_32byte_rx_desc +#define I40E_RX_DMA_ATTR \ + (DMA_ATTR_SKIP_CPU_SYNC | DMA_ATTR_WEAK_ORDERING) + /** * i40e_test_staterr - tests bits in Rx descriptor status and error fields * @rx_desc: pointer to receive descriptor (in le64 format) diff --git a/drivers/net/ethernet/intel/i40evf/i40e_virtchnl.h b/drivers/net/ethernet/intel/i40evf/i40e_virtchnl.h index d38a2b2aea2b..f431fbc4a3e7 100644 --- a/drivers/net/ethernet/intel/i40evf/i40e_virtchnl.h +++ b/drivers/net/ethernet/intel/i40evf/i40e_virtchnl.h @@ -81,7 +81,9 @@ enum i40e_virtchnl_ops { I40E_VIRTCHNL_OP_GET_STATS = 15, I40E_VIRTCHNL_OP_FCOE = 16, I40E_VIRTCHNL_OP_EVENT = 17, /* must ALWAYS be 17 */ + I40E_VIRTCHNL_OP_IWARP = 20, I40E_VIRTCHNL_OP_CONFIG_IWARP_IRQ_MAP = 21, + I40E_VIRTCHNL_OP_RELEASE_IWARP_IRQ_MAP = 22, I40E_VIRTCHNL_OP_CONFIG_RSS_KEY = 23, I40E_VIRTCHNL_OP_CONFIG_RSS_LUT = 24, I40E_VIRTCHNL_OP_GET_RSS_HENA_CAPS = 25, @@ -393,6 +395,37 @@ struct i40e_virtchnl_pf_event { int severity; }; +/* I40E_VIRTCHNL_OP_CONFIG_IWARP_IRQ_MAP + * VF uses this message to request PF to map IWARP vectors to IWARP queues. + * The request for this originates from the VF IWARP driver through + * a client interface between VF LAN and VF IWARP driver. + * A vector could have an AEQ and CEQ attached to it although + * there is a single AEQ per VF IWARP instance in which case + * most vectors will have an INVALID_IDX for aeq and valid idx for ceq. + * There will never be a case where there will be multiple CEQs attached + * to a single vector. + * PF configures interrupt mapping and returns status. + */ + +/* HW does not define a type value for AEQ; only for RX/TX and CEQ. + * In order for us to keep the interface simple, SW will define a + * unique type value for AEQ. + */ +#define I40E_QUEUE_TYPE_PE_AEQ 0x80 +#define I40E_QUEUE_INVALID_IDX 0xFFFF + +struct i40e_virtchnl_iwarp_qv_info { + u32 v_idx; /* msix_vector */ + u16 ceq_idx; + u16 aeq_idx; + u8 itr_idx; +}; + +struct i40e_virtchnl_iwarp_qvlist_info { + u32 num_vectors; + struct i40e_virtchnl_iwarp_qv_info qv_info[1]; +}; + /* VF reset states - these are written into the RSTAT register: * I40E_VFGEN_RSTAT1 on the PF * I40E_VFGEN_RSTAT on the VF diff --git a/drivers/net/ethernet/intel/i40evf/i40evf.h b/drivers/net/ethernet/intel/i40evf/i40evf.h index 00c42d803276..b2b48511f457 100644 --- a/drivers/net/ethernet/intel/i40evf/i40evf.h +++ b/drivers/net/ethernet/intel/i40evf/i40evf.h @@ -60,6 +60,7 @@ struct i40e_vsi { int base_vector; u16 work_limit; u16 qs_handle; + void *priv; /* client driver data reference. */ }; /* How many Rx Buffers do we bundle into one write to the hardware ? */ @@ -169,6 +170,7 @@ enum i40evf_state_t { enum i40evf_critical_section_t { __I40EVF_IN_CRITICAL_TASK, /* cannot be interrupted */ + __I40EVF_IN_CLIENT_TASK, }; /* make common code happy */ #define __I40E_DOWN __I40EVF_DOWN @@ -178,6 +180,7 @@ struct i40evf_adapter { struct timer_list watchdog_timer; struct work_struct reset_task; struct work_struct adminq_task; + struct delayed_work client_task; struct delayed_work init_task; struct i40e_q_vector *q_vectors; struct list_head vlan_filter_list; @@ -195,7 +198,10 @@ struct i40evf_adapter { u64 hw_csum_rx_error; u32 rx_desc_count; int num_msix_vectors; + int num_iwarp_msix; + int iwarp_base_vector; u32 client_pending; + struct i40e_client_instance *cinst; struct msix_entry *msix_entries; u32 flags; @@ -211,8 +217,11 @@ struct i40evf_adapter { #define I40EVF_FLAG_OUTER_UDP_CSUM_CAPABLE BIT(12) #define I40EVF_FLAG_ADDR_SET_BY_PF BIT(13) #define I40EVF_FLAG_SERVICE_CLIENT_REQUESTED BIT(14) -#define I40EVF_FLAG_PROMISC_ON BIT(15) -#define I40EVF_FLAG_ALLMULTI_ON BIT(16) +#define I40EVF_FLAG_CLIENT_NEEDS_OPEN BIT(15) +#define I40EVF_FLAG_CLIENT_NEEDS_CLOSE BIT(16) +#define I40EVF_FLAG_CLIENT_NEEDS_L2_PARAMS BIT(17) +#define I40EVF_FLAG_PROMISC_ON BIT(18) +#define I40EVF_FLAG_ALLMULTI_ON BIT(19) /* duplicates for common code */ #define I40E_FLAG_FDIR_ATR_ENABLED 0 #define I40E_FLAG_DCB_ENABLED 0 @@ -258,10 +267,11 @@ struct i40evf_adapter { bool link_up; enum i40e_aq_link_speed link_speed; enum i40e_virtchnl_ops current_op; -#define CLIENT_ENABLED(_a) ((_a)->vf_res ? \ +#define CLIENT_ALLOWED(_a) ((_a)->vf_res ? \ (_a)->vf_res->vf_offload_flags & \ I40E_VIRTCHNL_VF_OFFLOAD_IWARP : \ 0) +#define CLIENT_ENABLED(_a) ((_a)->cinst) /* RSS by the PF should be preferred over RSS via other methods. */ #define RSS_PF(_a) ((_a)->vf_res->vf_offload_flags & \ I40E_VIRTCHNL_VF_OFFLOAD_RSS_PF) @@ -292,6 +302,12 @@ struct i40evf_adapter { /* Ethtool Private Flags */ +/* lan device */ +struct i40e_device { + struct list_head list; + struct i40evf_adapter *vf; +}; + /* needed by i40evf_ethtool.c */ extern char i40evf_driver_name[]; extern const char i40evf_driver_version[]; @@ -337,4 +353,11 @@ void i40evf_virtchnl_completion(struct i40evf_adapter *adapter, enum i40e_virtchnl_ops v_opcode, i40e_status v_retval, u8 *msg, u16 msglen); int i40evf_config_rss(struct i40evf_adapter *adapter); +int i40evf_lan_add_device(struct i40evf_adapter *adapter); +int i40evf_lan_del_device(struct i40evf_adapter *adapter); +void i40evf_client_subtask(struct i40evf_adapter *adapter); +void i40evf_notify_client_message(struct i40e_vsi *vsi, u8 *msg, u16 len); +void i40evf_notify_client_l2_params(struct i40e_vsi *vsi); +void i40evf_notify_client_open(struct i40e_vsi *vsi); +void i40evf_notify_client_close(struct i40e_vsi *vsi, bool reset); #endif /* _I40EVF_H_ */ diff --git a/drivers/net/ethernet/intel/i40evf/i40evf_client.c b/drivers/net/ethernet/intel/i40evf/i40evf_client.c new file mode 100644 index 000000000000..5b43e5b6e2eb --- /dev/null +++ b/drivers/net/ethernet/intel/i40evf/i40evf_client.c @@ -0,0 +1,563 @@ +#include <linux/list.h> +#include <linux/errno.h> + +#include "i40evf.h" +#include "i40e_prototype.h" +#include "i40evf_client.h" + +static +const char i40evf_client_interface_version_str[] = I40EVF_CLIENT_VERSION_STR; +static struct i40e_client *vf_registered_client; +static LIST_HEAD(i40evf_devices); +static DEFINE_MUTEX(i40evf_device_mutex); + +static u32 i40evf_client_virtchnl_send(struct i40e_info *ldev, + struct i40e_client *client, + u8 *msg, u16 len); + +static int i40evf_client_setup_qvlist(struct i40e_info *ldev, + struct i40e_client *client, + struct i40e_qvlist_info *qvlist_info); + +static struct i40e_ops i40evf_lan_ops = { + .virtchnl_send = i40evf_client_virtchnl_send, + .setup_qvlist = i40evf_client_setup_qvlist, +}; + +/** + * i40evf_notify_client_message - call the client message receive callback + * @vsi: the VSI associated with this client + * @msg: message buffer + * @len: length of message + * + * If there is a client to this VSI, call the client + **/ +void i40evf_notify_client_message(struct i40e_vsi *vsi, u8 *msg, u16 len) +{ + struct i40evf_adapter *adapter = vsi->back; + struct i40e_client_instance *cinst = adapter->cinst; + + if (!vsi) + return; + + if (!cinst || !cinst->client || !cinst->client->ops || + !cinst->client->ops->virtchnl_receive) { + dev_dbg(&vsi->back->pdev->dev, + "Cannot locate client instance virtchnl_receive function\n"); + return; + } + cinst->client->ops->virtchnl_receive(&cinst->lan_info, cinst->client, + msg, len); +} + +/** + * i40evf_notify_client_l2_params - call the client notify callback + * @vsi: the VSI with l2 param changes + * + * If there is a client to this VSI, call the client + **/ +void i40evf_notify_client_l2_params(struct i40e_vsi *vsi) +{ + struct i40evf_adapter *adapter = vsi->back; + struct i40e_client_instance *cinst = adapter->cinst; + struct i40e_params params; + + if (!vsi) + return; + memset(¶ms, 0, sizeof(params)); + params.mtu = vsi->netdev->mtu; + params.link_up = vsi->back->link_up; + params.qos.prio_qos[0].qs_handle = vsi->qs_handle; + + if (!cinst || !cinst->client || !cinst->client->ops || + !cinst->client->ops->l2_param_change) { + dev_dbg(&vsi->back->pdev->dev, + "Cannot locate client instance l2_param_change function\n"); + return; + } + cinst->client->ops->l2_param_change(&cinst->lan_info, cinst->client, + ¶ms); +} + +/** + * i40evf_notify_client_open - call the client open callback + * @vsi: the VSI with netdev opened + * + * If there is a client to this netdev, call the client with open + **/ +void i40evf_notify_client_open(struct i40e_vsi *vsi) +{ + struct i40evf_adapter *adapter = vsi->back; + struct i40e_client_instance *cinst = adapter->cinst; + int ret; + + if (!cinst || !cinst->client || !cinst->client->ops || + !cinst->client->ops->open) { + dev_dbg(&vsi->back->pdev->dev, + "Cannot locate client instance open function\n"); + return; + } + if (!(test_bit(__I40E_CLIENT_INSTANCE_OPENED, &cinst->state))) { + ret = cinst->client->ops->open(&cinst->lan_info, cinst->client); + if (!ret) + set_bit(__I40E_CLIENT_INSTANCE_OPENED, &cinst->state); + } +} + +/** + * i40evf_client_release_qvlist - send a message to the PF to release iwarp qv map + * @ldev: pointer to L2 context. + * + * Return 0 on success or < 0 on error + **/ +static int i40evf_client_release_qvlist(struct i40e_info *ldev) +{ + struct i40evf_adapter *adapter = ldev->vf; + i40e_status err; + + if (adapter->aq_required) + return -EAGAIN; + + err = i40e_aq_send_msg_to_pf(&adapter->hw, + I40E_VIRTCHNL_OP_RELEASE_IWARP_IRQ_MAP, + I40E_SUCCESS, NULL, 0, NULL); + + if (err) + dev_err(&adapter->pdev->dev, + "Unable to send iWarp vector release message to PF, error %d, aq status %d\n", + err, adapter->hw.aq.asq_last_status); + + return err; +} + +/** + * i40evf_notify_client_close - call the client close callback + * @vsi: the VSI with netdev closed + * @reset: true when close called due to reset pending + * + * If there is a client to this netdev, call the client with close + **/ +void i40evf_notify_client_close(struct i40e_vsi *vsi, bool reset) +{ + struct i40evf_adapter *adapter = vsi->back; + struct i40e_client_instance *cinst = adapter->cinst; + + if (!cinst || !cinst->client || !cinst->client->ops || + !cinst->client->ops->close) { + dev_dbg(&vsi->back->pdev->dev, + "Cannot locate client instance close function\n"); + return; + } + cinst->client->ops->close(&cinst->lan_info, cinst->client, reset); + i40evf_client_release_qvlist(&cinst->lan_info); + clear_bit(__I40E_CLIENT_INSTANCE_OPENED, &cinst->state); +} + +/** + * i40evf_client_add_instance - add a client instance to the instance list + * @adapter: pointer to the board struct + * @client: pointer to a client struct in the client list. + * + * Returns cinst ptr on success, NULL on failure + **/ +static struct i40e_client_instance * +i40evf_client_add_instance(struct i40evf_adapter *adapter) +{ + struct i40e_client_instance *cinst = NULL; + struct netdev_hw_addr *mac = NULL; + struct i40e_vsi *vsi = &adapter->vsi; + int i; + + if (!vf_registered_client) + goto out; + + if (adapter->cinst) { + cinst = adapter->cinst; + goto out; + } + + cinst = kzalloc(sizeof(*cinst), GFP_KERNEL); + if (!cinst) + goto out; + + cinst->lan_info.vf = (void *)adapter; + cinst->lan_info.netdev = vsi->netdev; + cinst->lan_info.pcidev = adapter->pdev; + cinst->lan_info.fid = 0; + cinst->lan_info.ftype = I40E_CLIENT_FTYPE_VF; + cinst->lan_info.hw_addr = adapter->hw.hw_addr; + cinst->lan_info.ops = &i40evf_lan_ops; + cinst->lan_info.version.major = I40EVF_CLIENT_VERSION_MAJOR; + cinst->lan_info.version.minor = I40EVF_CLIENT_VERSION_MINOR; + cinst->lan_info.version.build = I40EVF_CLIENT_VERSION_BUILD; + set_bit(__I40E_CLIENT_INSTANCE_NONE, &cinst->state); + + cinst->lan_info.msix_count = adapter->num_iwarp_msix; + cinst->lan_info.msix_entries = + &adapter->msix_entries[adapter->iwarp_base_vector]; + + for (i = 0; i < I40E_MAX_USER_PRIORITY; i++) { + cinst->lan_info.params.qos.prio_qos[i].tc = 0; + cinst->lan_info.params.qos.prio_qos[i].qs_handle = + vsi->qs_handle; + } + + mac = list_first_entry(&cinst->lan_info.netdev->dev_addrs.list, + struct netdev_hw_addr, list); + if (mac) + ether_addr_copy(cinst->lan_info.lanmac, mac->addr); + else + dev_err(&adapter->pdev->dev, "MAC address list is empty!\n"); + + cinst->client = vf_registered_client; + adapter->cinst = cinst; +out: + return cinst; +} + +/** + * i40evf_client_del_instance - removes a client instance from the list + * @adapter: pointer to the board struct + * @client: pointer to the client struct + * + **/ +static +void i40evf_client_del_instance(struct i40evf_adapter *adapter) +{ + kfree(adapter->cinst); + adapter->cinst = NULL; +} + +/** + * i40evf_client_subtask - client maintenance work + * @adapter: board private structure + **/ +void i40evf_client_subtask(struct i40evf_adapter *adapter) +{ + struct i40e_client *client = vf_registered_client; + struct i40e_client_instance *cinst; + int ret = 0; + + if (adapter->state < __I40EVF_DOWN) + return; + + /* first check client is registered */ + if (!client) + return; + + /* Add the client instance to the instance list */ + cinst = i40evf_client_add_instance(adapter); + if (!cinst) + return; + + dev_info(&adapter->pdev->dev, "Added instance of Client %s\n", + client->name); + + if (!test_bit(__I40E_CLIENT_INSTANCE_OPENED, &cinst->state)) { + /* Send an Open request to the client */ + + if (client->ops && client->ops->open) + ret = client->ops->open(&cinst->lan_info, client); + if (!ret) + set_bit(__I40E_CLIENT_INSTANCE_OPENED, + &cinst->state); + else + /* remove client instance */ + i40evf_client_del_instance(adapter); + } +} + +/** + * i40evf_lan_add_device - add a lan device struct to the list of lan devices + * @adapter: pointer to the board struct + * + * Returns 0 on success or none 0 on error + **/ +int i40evf_lan_add_device(struct i40evf_adapter *adapter) +{ + struct i40e_device *ldev; + int ret = 0; + + mutex_lock(&i40evf_device_mutex); + list_for_each_entry(ldev, &i40evf_devices, list) { + if (ldev->vf == adapter) { + ret = -EEXIST; + goto out; + } + } + ldev = kzalloc(sizeof(*ldev), GFP_KERNEL); + if (!ldev) { + ret = -ENOMEM; + goto out; + } + ldev->vf = adapter; + INIT_LIST_HEAD(&ldev->list); + list_add(&ldev->list, &i40evf_devices); + dev_info(&adapter->pdev->dev, "Added LAN device bus=0x%02x dev=0x%02x func=0x%02x\n", + adapter->hw.bus.bus_id, adapter->hw.bus.device, + adapter->hw.bus.func); + + /* Since in some cases register may have happened before a device gets + * added, we can schedule a subtask to go initiate the clients. + */ + adapter->flags |= I40EVF_FLAG_SERVICE_CLIENT_REQUESTED; + +out: + mutex_unlock(&i40evf_device_mutex); + return ret; +} + +/** + * i40evf_lan_del_device - removes a lan device from the device list + * @adapter: pointer to the board struct + * + * Returns 0 on success or non-0 on error + **/ +int i40evf_lan_del_device(struct i40evf_adapter *adapter) +{ + struct i40e_device *ldev, *tmp; + int ret = -ENODEV; + + mutex_lock(&i40evf_device_mutex); + list_for_each_entry_safe(ldev, tmp, &i40evf_devices, list) { + if (ldev->vf == adapter) { + dev_info(&adapter->pdev->dev, + "Deleted LAN device bus=0x%02x dev=0x%02x func=0x%02x\n", + adapter->hw.bus.bus_id, adapter->hw.bus.device, + adapter->hw.bus.func); + list_del(&ldev->list); + kfree(ldev); + ret = 0; + break; + } + } + + mutex_unlock(&i40evf_device_mutex); + return ret; +} + +/** + * i40evf_client_release - release client specific resources + * @client: pointer to the registered client + * + **/ +static void i40evf_client_release(struct i40e_client *client) +{ + struct i40e_client_instance *cinst; + struct i40e_device *ldev; + struct i40evf_adapter *adapter; + + mutex_lock(&i40evf_device_mutex); + list_for_each_entry(ldev, &i40evf_devices, list) { + adapter = ldev->vf; + cinst = adapter->cinst; + if (!cinst) + continue; + if (test_bit(__I40E_CLIENT_INSTANCE_OPENED, &cinst->state)) { + if (client->ops && client->ops->close) + client->ops->close(&cinst->lan_info, client, + false); + i40evf_client_release_qvlist(&cinst->lan_info); + clear_bit(__I40E_CLIENT_INSTANCE_OPENED, &cinst->state); + + dev_warn(&adapter->pdev->dev, + "Client %s instance closed\n", client->name); + } + /* delete the client instance */ + i40evf_client_del_instance(adapter); + dev_info(&adapter->pdev->dev, "Deleted client instance of Client %s\n", + client->name); + } + mutex_unlock(&i40evf_device_mutex); +} + +/** + * i40evf_client_prepare - prepare client specific resources + * @client: pointer to the registered client + * + **/ +static void i40evf_client_prepare(struct i40e_client *client) +{ + struct i40e_device *ldev; + struct i40evf_adapter *adapter; + + mutex_lock(&i40evf_device_mutex); + list_for_each_entry(ldev, &i40evf_devices, list) { + adapter = ldev->vf; + /* Signal the watchdog to service the client */ + adapter->flags |= I40EVF_FLAG_SERVICE_CLIENT_REQUESTED; + } + mutex_unlock(&i40evf_device_mutex); +} + +/** + * i40evf_client_virtchnl_send - send a message to the PF instance + * @ldev: pointer to L2 context. + * @client: Client pointer. + * @msg: pointer to message buffer + * @len: message length + * + * Return 0 on success or < 0 on error + **/ +static u32 i40evf_client_virtchnl_send(struct i40e_info *ldev, + struct i40e_client *client, + u8 *msg, u16 len) +{ + struct i40evf_adapter *adapter = ldev->vf; + i40e_status err; + + if (adapter->aq_required) + return -EAGAIN; + + err = i40e_aq_send_msg_to_pf(&adapter->hw, I40E_VIRTCHNL_OP_IWARP, + I40E_SUCCESS, msg, len, NULL); + if (err) + dev_err(&adapter->pdev->dev, "Unable to send iWarp message to PF, error %d, aq status %d\n", + err, adapter->hw.aq.asq_last_status); + + return err; +} + +/** + * i40evf_client_setup_qvlist - send a message to the PF to setup iwarp qv map + * @ldev: pointer to L2 context. + * @client: Client pointer. + * @qv_info: queue and vector list + * + * Return 0 on success or < 0 on error + **/ +static int i40evf_client_setup_qvlist(struct i40e_info *ldev, + struct i40e_client *client, + struct i40e_qvlist_info *qvlist_info) +{ + struct i40e_virtchnl_iwarp_qvlist_info *v_qvlist_info; + struct i40evf_adapter *adapter = ldev->vf; + struct i40e_qv_info *qv_info; + i40e_status err; + u32 v_idx, i; + u32 msg_size; + + if (adapter->aq_required) + return -EAGAIN; + + /* A quick check on whether the vectors belong to the client */ + for (i = 0; i < qvlist_info->num_vectors; i++) { + qv_info = &qvlist_info->qv_info[i]; + if (!qv_info) + continue; + v_idx = qv_info->v_idx; + if ((v_idx >= + (adapter->iwarp_base_vector + adapter->num_iwarp_msix)) || + (v_idx < adapter->iwarp_base_vector)) + return -EINVAL; + } + + v_qvlist_info = (struct i40e_virtchnl_iwarp_qvlist_info *)qvlist_info; + msg_size = sizeof(struct i40e_virtchnl_iwarp_qvlist_info) + + (sizeof(struct i40e_virtchnl_iwarp_qv_info) * + (v_qvlist_info->num_vectors - 1)); + + adapter->client_pending |= BIT(I40E_VIRTCHNL_OP_CONFIG_IWARP_IRQ_MAP); + err = i40e_aq_send_msg_to_pf(&adapter->hw, + I40E_VIRTCHNL_OP_CONFIG_IWARP_IRQ_MAP, + I40E_SUCCESS, (u8 *)v_qvlist_info, msg_size, NULL); + + if (err) { + dev_err(&adapter->pdev->dev, + "Unable to send iWarp vector config message to PF, error %d, aq status %d\n", + err, adapter->hw.aq.asq_last_status); + goto out; + } + + err = -EBUSY; + for (i = 0; i < 5; i++) { + msleep(100); + if (!(adapter->client_pending & + BIT(I40E_VIRTCHNL_OP_CONFIG_IWARP_IRQ_MAP))) { + err = 0; + break; + } + } +out: + return err; +} + +/** + * i40evf_register_client - Register a i40e client driver with the L2 driver + * @client: pointer to the i40e_client struct + * + * Returns 0 on success or non-0 on error + **/ +int i40evf_register_client(struct i40e_client *client) +{ + int ret = 0; + + if (!client) { + ret = -EIO; + goto out; + } + + if (strlen(client->name) == 0) { + pr_info("i40evf: Failed to register client with no name\n"); + ret = -EIO; + goto out; + } + + if (vf_registered_client) { + pr_info("i40evf: Client %s has already been registered!\n", + client->name); + ret = -EEXIST; + goto out; + } + + if ((client->version.major != I40EVF_CLIENT_VERSION_MAJOR) || + (client->version.minor != I40EVF_CLIENT_VERSION_MINOR)) { + pr_info("i40evf: Failed to register client %s due to mismatched client interface version\n", + client->name); + pr_info("Client is using version: %02d.%02d.%02d while LAN driver supports %s\n", + client->version.major, client->version.minor, + client->version.build, + i40evf_client_interface_version_str); + ret = -EIO; + goto out; + } + + vf_registered_client = client; + + i40evf_client_prepare(client); + + pr_info("i40evf: Registered client %s with return code %d\n", + client->name, ret); +out: + return ret; +} +EXPORT_SYMBOL(i40evf_register_client); + +/** + * i40evf_unregister_client - Unregister a i40e client driver with the L2 driver + * @client: pointer to the i40e_client struct + * + * Returns 0 on success or non-0 on error + **/ +int i40evf_unregister_client(struct i40e_client *client) +{ + int ret = 0; + + /* When a unregister request comes through we would have to send + * a close for each of the client instances that were opened. + * client_release function is called to handle this. + */ + i40evf_client_release(client); + + if (vf_registered_client != client) { + pr_info("i40evf: Client %s has not been registered\n", + client->name); + ret = -ENODEV; + goto out; + } + vf_registered_client = NULL; + pr_info("i40evf: Unregistered client %s\n", client->name); +out: + return ret; +} +EXPORT_SYMBOL(i40evf_unregister_client); diff --git a/drivers/net/ethernet/intel/i40evf/i40evf_client.h b/drivers/net/ethernet/intel/i40evf/i40evf_client.h new file mode 100644 index 000000000000..7d283c7506a5 --- /dev/null +++ b/drivers/net/ethernet/intel/i40evf/i40evf_client.h @@ -0,0 +1,166 @@ +#ifndef _I40E_CLIENT_H_ +#define _I40E_CLIENT_H_ + +#define I40EVF_CLIENT_STR_LENGTH 10 + +/* Client interface version should be updated anytime there is a change in the + * existing APIs or data structures. + */ +#define I40EVF_CLIENT_VERSION_MAJOR 0 +#define I40EVF_CLIENT_VERSION_MINOR 01 +#define I40EVF_CLIENT_VERSION_BUILD 00 +#define I40EVF_CLIENT_VERSION_STR \ + __stringify(I40EVF_CLIENT_VERSION_MAJOR) "." \ + __stringify(I40EVF_CLIENT_VERSION_MINOR) "." \ + __stringify(I40EVF_CLIENT_VERSION_BUILD) + +struct i40e_client_version { + u8 major; + u8 minor; + u8 build; + u8 rsvd; +}; + +enum i40e_client_state { + __I40E_CLIENT_NULL, + __I40E_CLIENT_REGISTERED +}; + +enum i40e_client_instance_state { + __I40E_CLIENT_INSTANCE_NONE, + __I40E_CLIENT_INSTANCE_OPENED, +}; + +struct i40e_ops; +struct i40e_client; + +/* HW does not define a type value for AEQ; only for RX/TX and CEQ. + * In order for us to keep the interface simple, SW will define a + * unique type value for AEQ. + */ +#define I40E_QUEUE_TYPE_PE_AEQ 0x80 +#define I40E_QUEUE_INVALID_IDX 0xFFFF + +struct i40e_qv_info { + u32 v_idx; /* msix_vector */ + u16 ceq_idx; + u16 aeq_idx; + u8 itr_idx; +}; + +struct i40e_qvlist_info { + u32 num_vectors; + struct i40e_qv_info qv_info[1]; +}; + +#define I40E_CLIENT_MSIX_ALL 0xFFFFFFFF + +/* set of LAN parameters useful for clients managed by LAN */ + +/* Struct to hold per priority info */ +struct i40e_prio_qos_params { + u16 qs_handle; /* qs handle for prio */ + u8 tc; /* TC mapped to prio */ + u8 reserved; +}; + +#define I40E_CLIENT_MAX_USER_PRIORITY 8 +/* Struct to hold Client QoS */ +struct i40e_qos_params { + struct i40e_prio_qos_params prio_qos[I40E_CLIENT_MAX_USER_PRIORITY]; +}; + +struct i40e_params { + struct i40e_qos_params qos; + u16 mtu; + u16 link_up; /* boolean */ +}; + +/* Structure to hold LAN device info for a client device */ +struct i40e_info { + struct i40e_client_version version; + u8 lanmac[6]; + struct net_device *netdev; + struct pci_dev *pcidev; + u8 __iomem *hw_addr; + u8 fid; /* function id, PF id or VF id */ +#define I40E_CLIENT_FTYPE_PF 0 +#define I40E_CLIENT_FTYPE_VF 1 + u8 ftype; /* function type, PF or VF */ + void *vf; /* cast to i40evf_adapter */ + + /* All L2 params that could change during the life span of the device + * and needs to be communicated to the client when they change + */ + struct i40e_params params; + struct i40e_ops *ops; + + u16 msix_count; /* number of msix vectors*/ + /* Array down below will be dynamically allocated based on msix_count */ + struct msix_entry *msix_entries; + u16 itr_index; /* Which ITR index the PE driver is suppose to use */ +}; + +struct i40e_ops { + /* setup_q_vector_list enables queues with a particular vector */ + int (*setup_qvlist)(struct i40e_info *ldev, struct i40e_client *client, + struct i40e_qvlist_info *qv_info); + + u32 (*virtchnl_send)(struct i40e_info *ldev, struct i40e_client *client, + u8 *msg, u16 len); + + /* If the PE Engine is unresponsive, RDMA driver can request a reset.*/ + void (*request_reset)(struct i40e_info *ldev, + struct i40e_client *client); +}; + +struct i40e_client_ops { + /* Should be called from register_client() or whenever the driver is + * ready to create a specific client instance. + */ + int (*open)(struct i40e_info *ldev, struct i40e_client *client); + + /* Should be closed when netdev is unavailable or when unregister + * call comes in. If the close happens due to a reset, set the reset + * bit to true. + */ + void (*close)(struct i40e_info *ldev, struct i40e_client *client, + bool reset); + + /* called when some l2 managed parameters changes - mss */ + void (*l2_param_change)(struct i40e_info *ldev, + struct i40e_client *client, + struct i40e_params *params); + + /* called when a message is received from the PF */ + int (*virtchnl_receive)(struct i40e_info *ldev, + struct i40e_client *client, + u8 *msg, u16 len); +}; + +/* Client device */ +struct i40e_client_instance { + struct list_head list; + struct i40e_info lan_info; + struct i40e_client *client; + unsigned long state; +}; + +struct i40e_client { + struct list_head list; /* list of registered clients */ + char name[I40EVF_CLIENT_STR_LENGTH]; + struct i40e_client_version version; + unsigned long state; /* client state */ + atomic_t ref_cnt; /* Count of all the client devices of this kind */ + u32 flags; +#define I40E_CLIENT_FLAGS_LAUNCH_ON_PROBE BIT(0) +#define I40E_TX_FLAGS_NOTIFY_OTHER_EVENTS BIT(2) + u8 type; +#define I40E_CLIENT_IWARP 0 + struct i40e_client_ops *ops; /* client ops provided by the client */ +}; + +/* used by clients */ +int i40evf_register_client(struct i40e_client *client); +int i40evf_unregister_client(struct i40e_client *client); +#endif /* _I40E_CLIENT_H_ */ diff --git a/drivers/net/ethernet/intel/i40evf/i40evf_main.c b/drivers/net/ethernet/intel/i40evf/i40evf_main.c index f35dcaac5bb7..6d666bde9df5 100644 --- a/drivers/net/ethernet/intel/i40evf/i40evf_main.c +++ b/drivers/net/ethernet/intel/i40evf/i40evf_main.c @@ -26,6 +26,7 @@ #include "i40evf.h" #include "i40e_prototype.h" +#include "i40evf_client.h" static int i40evf_setup_all_tx_resources(struct i40evf_adapter *adapter); static int i40evf_setup_all_rx_resources(struct i40evf_adapter *adapter); static int i40evf_close(struct net_device *netdev); @@ -36,9 +37,9 @@ static const char i40evf_driver_string[] = #define DRV_KERN "-k" -#define DRV_VERSION_MAJOR 1 -#define DRV_VERSION_MINOR 6 -#define DRV_VERSION_BUILD 27 +#define DRV_VERSION_MAJOR 2 +#define DRV_VERSION_MINOR 1 +#define DRV_VERSION_BUILD 7 #define DRV_VERSION __stringify(DRV_VERSION_MAJOR) "." \ __stringify(DRV_VERSION_MINOR) "." \ __stringify(DRV_VERSION_BUILD) \ @@ -1058,6 +1059,8 @@ static void i40evf_up_complete(struct i40evf_adapter *adapter) i40evf_napi_enable_all(adapter); adapter->aq_required |= I40EVF_FLAG_AQ_ENABLE_QUEUES; + if (CLIENT_ENABLED(adapter)) + adapter->flags |= I40EVF_FLAG_CLIENT_NEEDS_OPEN; mod_timer_pending(&adapter->watchdog_timer, jiffies + 1); } @@ -1685,6 +1688,7 @@ static void i40evf_watchdog_task(struct work_struct *work) i40evf_set_promiscuous(adapter, 0); goto watchdog_done; } + schedule_delayed_work(&adapter->client_task, msecs_to_jiffies(5)); if (adapter->state == __I40EVF_RUNNING) i40evf_request_stats(adapter); @@ -1773,10 +1777,17 @@ static void i40evf_reset_task(struct work_struct *work) u32 reg_val; int i = 0, err; - while (test_and_set_bit(__I40EVF_IN_CRITICAL_TASK, + while (test_and_set_bit(__I40EVF_IN_CLIENT_TASK, &adapter->crit_section)) usleep_range(500, 1000); - + if (CLIENT_ENABLED(adapter)) { + adapter->flags &= ~(I40EVF_FLAG_CLIENT_NEEDS_OPEN | + I40EVF_FLAG_CLIENT_NEEDS_CLOSE | + I40EVF_FLAG_CLIENT_NEEDS_L2_PARAMS | + I40EVF_FLAG_SERVICE_CLIENT_REQUESTED); + cancel_delayed_work_sync(&adapter->client_task); + i40evf_notify_client_close(&adapter->vsi, true); + } i40evf_misc_irq_disable(adapter); if (adapter->flags & I40EVF_FLAG_RESET_NEEDED) { adapter->flags &= ~I40EVF_FLAG_RESET_NEEDED; @@ -1819,6 +1830,7 @@ static void i40evf_reset_task(struct work_struct *work) dev_err(&adapter->pdev->dev, "Reset never finished (%x)\n", reg_val); i40evf_disable_vf(adapter); + clear_bit(__I40EVF_IN_CLIENT_TASK, &adapter->crit_section); return; /* Do not attempt to reinit. It's dead, Jim. */ } @@ -1861,9 +1873,8 @@ continue_reset: } adapter->aq_required |= I40EVF_FLAG_AQ_ADD_MAC_FILTER; adapter->aq_required |= I40EVF_FLAG_AQ_ADD_VLAN_FILTER; - /* Open RDMA Client again */ - adapter->aq_required |= I40EVF_FLAG_SERVICE_CLIENT_REQUESTED; clear_bit(__I40EVF_IN_CRITICAL_TASK, &adapter->crit_section); + clear_bit(__I40EVF_IN_CLIENT_TASK, &adapter->crit_section); i40evf_misc_irq_enable(adapter); mod_timer(&adapter->watchdog_timer, jiffies + 2); @@ -1980,6 +1991,48 @@ out: } /** + * i40evf_client_task - worker thread to perform client work + * @work: pointer to work_struct containing our data + * + * This task handles client interactions. Because client calls can be + * reentrant, we can't handle them in the watchdog. + **/ +static void i40evf_client_task(struct work_struct *work) +{ + struct i40evf_adapter *adapter = + container_of(work, struct i40evf_adapter, client_task.work); + + /* If we can't get the client bit, just give up. We'll be rescheduled + * later. + */ + + if (test_and_set_bit(__I40EVF_IN_CLIENT_TASK, &adapter->crit_section)) + return; + + if (adapter->flags & I40EVF_FLAG_SERVICE_CLIENT_REQUESTED) { + i40evf_client_subtask(adapter); + adapter->flags &= ~I40EVF_FLAG_SERVICE_CLIENT_REQUESTED; + goto out; + } + if (adapter->flags & I40EVF_FLAG_CLIENT_NEEDS_CLOSE) { + i40evf_notify_client_close(&adapter->vsi, false); + adapter->flags &= ~I40EVF_FLAG_CLIENT_NEEDS_CLOSE; + goto out; + } + if (adapter->flags & I40EVF_FLAG_CLIENT_NEEDS_OPEN) { + i40evf_notify_client_open(&adapter->vsi); + adapter->flags &= ~I40EVF_FLAG_CLIENT_NEEDS_OPEN; + goto out; + } + if (adapter->flags & I40EVF_FLAG_CLIENT_NEEDS_L2_PARAMS) { + i40evf_notify_client_l2_params(&adapter->vsi); + adapter->flags &= ~I40EVF_FLAG_CLIENT_NEEDS_L2_PARAMS; + } +out: + clear_bit(__I40EVF_IN_CLIENT_TASK, &adapter->crit_section); +} + +/** * i40evf_free_all_tx_resources - Free Tx Resources for All Queues * @adapter: board private structure * @@ -2148,6 +2201,8 @@ static int i40evf_close(struct net_device *netdev) set_bit(__I40E_DOWN, &adapter->vsi.state); + if (CLIENT_ENABLED(adapter)) + adapter->flags |= I40EVF_FLAG_CLIENT_NEEDS_CLOSE; i40evf_down(adapter); adapter->state = __I40EVF_DOWN_PENDING; @@ -2188,6 +2243,10 @@ static int i40evf_change_mtu(struct net_device *netdev, int new_mtu) struct i40evf_adapter *adapter = netdev_priv(netdev); netdev->mtu = new_mtu; + if (CLIENT_ENABLED(adapter)) { + i40evf_notify_client_l2_params(&adapter->vsi); + adapter->flags |= I40EVF_FLAG_SERVICE_CLIENT_REQUESTED; + } adapter->flags |= I40EVF_FLAG_RESET_NEEDED; schedule_work(&adapter->reset_task); @@ -2581,6 +2640,12 @@ static void i40evf_init_task(struct work_struct *work) adapter->netdev_registered = true; netif_tx_stop_all_queues(netdev); + if (CLIENT_ALLOWED(adapter)) { + err = i40evf_lan_add_device(adapter); + if (err) + dev_info(&pdev->dev, "Failed to add VF to client API service list: %d\n", + err); + } dev_info(&pdev->dev, "MAC address: %pM\n", adapter->hw.mac.addr); if (netdev->features & NETIF_F_GRO) @@ -2745,6 +2810,7 @@ static int i40evf_probe(struct pci_dev *pdev, const struct pci_device_id *ent) INIT_WORK(&adapter->reset_task, i40evf_reset_task); INIT_WORK(&adapter->adminq_task, i40evf_adminq_task); INIT_WORK(&adapter->watchdog_task, i40evf_watchdog_task); + INIT_DELAYED_WORK(&adapter->client_task, i40evf_client_task); INIT_DELAYED_WORK(&adapter->init_task, i40evf_init_task); schedule_delayed_work(&adapter->init_task, msecs_to_jiffies(5 * (pdev->devfn & 0x07))); @@ -2857,14 +2923,21 @@ static void i40evf_remove(struct pci_dev *pdev) struct i40evf_adapter *adapter = netdev_priv(netdev); struct i40evf_mac_filter *f, *ftmp; struct i40e_hw *hw = &adapter->hw; + int err; cancel_delayed_work_sync(&adapter->init_task); cancel_work_sync(&adapter->reset_task); - + cancel_delayed_work_sync(&adapter->client_task); if (adapter->netdev_registered) { unregister_netdev(netdev); adapter->netdev_registered = false; } + if (CLIENT_ALLOWED(adapter)) { + err = i40evf_lan_del_device(adapter); + if (err) + dev_warn(&pdev->dev, "Failed to delete client device: %d\n", + err); + } /* Shut down all the garbage mashers on the detention level */ adapter->state = __I40EVF_REMOVE; diff --git a/drivers/net/ethernet/intel/i40evf/i40evf_virtchnl.c b/drivers/net/ethernet/intel/i40evf/i40evf_virtchnl.c index bee58af390e1..a2a7354426a3 100644 --- a/drivers/net/ethernet/intel/i40evf/i40evf_virtchnl.c +++ b/drivers/net/ethernet/intel/i40evf/i40evf_virtchnl.c @@ -26,6 +26,7 @@ #include "i40evf.h" #include "i40e_prototype.h" +#include "i40evf_client.h" /* busy wait delay in msec */ #define I40EVF_BUSY_WAIT_DELAY 10 @@ -999,6 +1000,16 @@ void i40evf_virtchnl_completion(struct i40evf_adapter *adapter, if (v_opcode != adapter->current_op) return; break; + case I40E_VIRTCHNL_OP_IWARP: + /* Gobble zero-length replies from the PF. They indicate that + * a previous message was received OK, and the client doesn't + * care about that. + */ + if (msglen && CLIENT_ENABLED(adapter)) + i40evf_notify_client_message(&adapter->vsi, + msg, msglen); + break; + case I40E_VIRTCHNL_OP_CONFIG_IWARP_IRQ_MAP: adapter->client_pending &= ~(BIT(I40E_VIRTCHNL_OP_CONFIG_IWARP_IRQ_MAP)); @@ -1014,7 +1025,7 @@ void i40evf_virtchnl_completion(struct i40evf_adapter *adapter, } break; default: - if (v_opcode != adapter->current_op) + if (adapter->current_op && (v_opcode != adapter->current_op)) dev_warn(&adapter->pdev->dev, "Expected response %d from PF, received %d\n", adapter->current_op, v_opcode); break; diff --git a/drivers/net/ethernet/intel/igb/igb.h b/drivers/net/ethernet/intel/igb/igb.h index acbc3abe2ddd..dc6e2980718f 100644 --- a/drivers/net/ethernet/intel/igb/igb.h +++ b/drivers/net/ethernet/intel/igb/igb.h @@ -142,12 +142,24 @@ struct vf_data_storage { /* Supported Rx Buffer Sizes */ #define IGB_RXBUFFER_256 256 #define IGB_RXBUFFER_2048 2048 +#define IGB_RXBUFFER_3072 3072 #define IGB_RX_HDR_LEN IGB_RXBUFFER_256 -#define IGB_RX_BUFSZ IGB_RXBUFFER_2048 +#define IGB_TS_HDR_LEN 16 + +#define IGB_SKB_PAD (NET_SKB_PAD + NET_IP_ALIGN) +#if (PAGE_SIZE < 8192) +#define IGB_MAX_FRAME_BUILD_SKB \ + (SKB_WITH_OVERHEAD(IGB_RXBUFFER_2048) - IGB_SKB_PAD - IGB_TS_HDR_LEN) +#else +#define IGB_MAX_FRAME_BUILD_SKB (IGB_RXBUFFER_2048 - IGB_TS_HDR_LEN) +#endif /* How many Rx Buffers do we bundle into one write to the hardware ? */ #define IGB_RX_BUFFER_WRITE 16 /* Must be power of 2 */ +#define IGB_RX_DMA_ATTR \ + (DMA_ATTR_SKIP_CPU_SYNC | DMA_ATTR_WEAK_ORDERING) + #define AUTO_ALL_MODES 0 #define IGB_EEPROM_APME 0x0400 @@ -301,12 +313,51 @@ struct igb_q_vector { }; enum e1000_ring_flags_t { + IGB_RING_FLAG_RX_3K_BUFFER, + IGB_RING_FLAG_RX_BUILD_SKB_ENABLED, IGB_RING_FLAG_RX_SCTP_CSUM, IGB_RING_FLAG_RX_LB_VLAN_BSWAP, IGB_RING_FLAG_TX_CTX_IDX, IGB_RING_FLAG_TX_DETECT_HANG }; +#define ring_uses_large_buffer(ring) \ + test_bit(IGB_RING_FLAG_RX_3K_BUFFER, &(ring)->flags) +#define set_ring_uses_large_buffer(ring) \ + set_bit(IGB_RING_FLAG_RX_3K_BUFFER, &(ring)->flags) +#define clear_ring_uses_large_buffer(ring) \ + clear_bit(IGB_RING_FLAG_RX_3K_BUFFER, &(ring)->flags) + +#define ring_uses_build_skb(ring) \ + test_bit(IGB_RING_FLAG_RX_BUILD_SKB_ENABLED, &(ring)->flags) +#define set_ring_build_skb_enabled(ring) \ + set_bit(IGB_RING_FLAG_RX_BUILD_SKB_ENABLED, &(ring)->flags) +#define clear_ring_build_skb_enabled(ring) \ + clear_bit(IGB_RING_FLAG_RX_BUILD_SKB_ENABLED, &(ring)->flags) + +static inline unsigned int igb_rx_bufsz(struct igb_ring *ring) +{ +#if (PAGE_SIZE < 8192) + if (ring_uses_large_buffer(ring)) + return IGB_RXBUFFER_3072; + + if (ring_uses_build_skb(ring)) + return IGB_MAX_FRAME_BUILD_SKB + IGB_TS_HDR_LEN; +#endif + return IGB_RXBUFFER_2048; +} + +static inline unsigned int igb_rx_pg_order(struct igb_ring *ring) +{ +#if (PAGE_SIZE < 8192) + if (ring_uses_large_buffer(ring)) + return 1; +#endif + return 0; +} + +#define igb_rx_pg_size(_ring) (PAGE_SIZE << igb_rx_pg_order(_ring)) + #define IGB_TXD_DCMD (E1000_ADVTXD_DCMD_EOP | E1000_ADVTXD_DCMD_RS) #define IGB_RX_DESC(R, i) \ @@ -545,6 +596,7 @@ struct igb_adapter { #define IGB_FLAG_HAS_MSIX BIT(13) #define IGB_FLAG_EEE BIT(14) #define IGB_FLAG_VLAN_PROMISC BIT(15) +#define IGB_FLAG_RX_LEGACY BIT(16) /* Media Auto Sense */ #define IGB_MAS_ENABLE_0 0X0001 @@ -558,7 +610,6 @@ struct igb_adapter { #define IGB_DMCTLX_DCFLUSH_DIS 0x80000000 /* Disable DMA Coal Flush */ #define IGB_82576_TSYNC_SHIFT 19 -#define IGB_TS_HDR_LEN 16 enum e1000_state_t { __IGB_TESTING, __IGB_RESETTING, @@ -591,7 +642,6 @@ void igb_configure_rx_ring(struct igb_adapter *, struct igb_ring *); void igb_setup_tctl(struct igb_adapter *); void igb_setup_rctl(struct igb_adapter *); netdev_tx_t igb_xmit_frame_ring(struct sk_buff *, struct igb_ring *); -void igb_unmap_and_free_tx_resource(struct igb_ring *, struct igb_tx_buffer *); void igb_alloc_rx_buffers(struct igb_ring *, u16); void igb_update_stats(struct igb_adapter *, struct rtnl_link_stats64 *); bool igb_has_link(struct igb_adapter *adapter); @@ -604,7 +654,7 @@ void igb_ptp_reset(struct igb_adapter *adapter); void igb_ptp_suspend(struct igb_adapter *adapter); void igb_ptp_rx_hang(struct igb_adapter *adapter); void igb_ptp_rx_rgtstamp(struct igb_q_vector *q_vector, struct sk_buff *skb); -void igb_ptp_rx_pktstamp(struct igb_q_vector *q_vector, unsigned char *va, +void igb_ptp_rx_pktstamp(struct igb_q_vector *q_vector, void *va, struct sk_buff *skb); int igb_ptp_set_ts_config(struct net_device *netdev, struct ifreq *ifr); int igb_ptp_get_ts_config(struct net_device *netdev, struct ifreq *ifr); diff --git a/drivers/net/ethernet/intel/igb/igb_ethtool.c b/drivers/net/ethernet/intel/igb/igb_ethtool.c index 737b664d004c..797b9daba224 100644 --- a/drivers/net/ethernet/intel/igb/igb_ethtool.c +++ b/drivers/net/ethernet/intel/igb/igb_ethtool.c @@ -144,6 +144,13 @@ static const char igb_gstrings_test[][ETH_GSTRING_LEN] = { }; #define IGB_TEST_LEN (sizeof(igb_gstrings_test) / ETH_GSTRING_LEN) +static const char igb_priv_flags_strings[][ETH_GSTRING_LEN] = { +#define IGB_PRIV_FLAGS_LEGACY_RX BIT(0) + "legacy-rx", +}; + +#define IGB_PRIV_FLAGS_STR_LEN ARRAY_SIZE(igb_priv_flags_strings) + static int igb_get_settings(struct net_device *netdev, struct ethtool_cmd *ecmd) { struct igb_adapter *adapter = netdev_priv(netdev); @@ -852,6 +859,8 @@ 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_priv_flags = IGB_PRIV_FLAGS_STR_LEN; } static void igb_get_ringparam(struct net_device *netdev, @@ -1811,14 +1820,14 @@ static int igb_clean_test_rings(struct igb_ring *rx_ring, tx_ntc = tx_ring->next_to_clean; rx_desc = IGB_RX_DESC(rx_ring, rx_ntc); - while (igb_test_staterr(rx_desc, E1000_RXD_STAT_DD)) { + while (rx_desc->wb.upper.length) { /* check Rx buffer */ rx_buffer_info = &rx_ring->rx_buffer_info[rx_ntc]; /* sync Rx buffer for CPU read */ dma_sync_single_for_cpu(rx_ring->dev, rx_buffer_info->dma, - IGB_RX_BUFSZ, + size, DMA_FROM_DEVICE); /* verify contents of skb */ @@ -1828,12 +1837,21 @@ static int igb_clean_test_rings(struct igb_ring *rx_ring, /* sync Rx buffer for device write */ dma_sync_single_for_device(rx_ring->dev, rx_buffer_info->dma, - IGB_RX_BUFSZ, + size, DMA_FROM_DEVICE); /* unmap buffer on Tx side */ tx_buffer_info = &tx_ring->tx_buffer_info[tx_ntc]; - igb_unmap_and_free_tx_resource(tx_ring, tx_buffer_info); + + /* Free all the Tx ring sk_buffs */ + dev_kfree_skb_any(tx_buffer_info->skb); + + /* unmap skb header data */ + dma_unmap_single(tx_ring->dev, + dma_unmap_addr(tx_buffer_info, dma), + dma_unmap_len(tx_buffer_info, len), + DMA_TO_DEVICE); + dma_unmap_len_set(tx_buffer_info, len, 0); /* increment Rx/Tx next to clean counters */ rx_ntc++; @@ -2271,6 +2289,8 @@ static int igb_get_sset_count(struct net_device *netdev, int sset) return IGB_STATS_LEN; case ETH_SS_TEST: return IGB_TEST_LEN; + case ETH_SS_PRIV_FLAGS: + return IGB_PRIV_FLAGS_STR_LEN; default: return -ENOTSUPP; } @@ -2376,6 +2396,10 @@ static void igb_get_strings(struct net_device *netdev, u32 stringset, u8 *data) } /* BUG_ON(p - data != IGB_STATS_LEN * ETH_GSTRING_LEN); */ break; + case ETH_SS_PRIV_FLAGS: + memcpy(data, igb_priv_flags_strings, + IGB_PRIV_FLAGS_STR_LEN * ETH_GSTRING_LEN); + break; } } @@ -3388,6 +3412,37 @@ static int igb_set_channels(struct net_device *netdev, return 0; } +static u32 igb_get_priv_flags(struct net_device *netdev) +{ + struct igb_adapter *adapter = netdev_priv(netdev); + u32 priv_flags = 0; + + if (adapter->flags & IGB_FLAG_RX_LEGACY) + priv_flags |= IGB_PRIV_FLAGS_LEGACY_RX; + + return priv_flags; +} + +static int igb_set_priv_flags(struct net_device *netdev, u32 priv_flags) +{ + struct igb_adapter *adapter = netdev_priv(netdev); + unsigned int flags = adapter->flags; + + flags &= ~IGB_FLAG_RX_LEGACY; + if (priv_flags & IGB_PRIV_FLAGS_LEGACY_RX) + flags |= IGB_FLAG_RX_LEGACY; + + if (flags != adapter->flags) { + adapter->flags = flags; + + /* reset interface to repopulate queues */ + if (netif_running(netdev)) + igb_reinit_locked(adapter); + } + + return 0; +} + static const struct ethtool_ops igb_ethtool_ops = { .get_settings = igb_get_settings, .set_settings = igb_set_settings, @@ -3426,6 +3481,8 @@ static const struct ethtool_ops igb_ethtool_ops = { .set_rxfh = igb_set_rxfh, .get_channels = igb_get_channels, .set_channels = igb_set_channels, + .get_priv_flags = igb_get_priv_flags, + .set_priv_flags = igb_set_priv_flags, .begin = igb_ethtool_begin, .complete = igb_ethtool_complete, }; diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c index be456bae8169..26a821fcd220 100644 --- a/drivers/net/ethernet/intel/igb/igb_main.c +++ b/drivers/net/ethernet/intel/igb/igb_main.c @@ -554,7 +554,7 @@ rx_ring_summary: 16, 1, page_address(buffer_info->page) + buffer_info->page_offset, - IGB_RX_BUFSZ, true); + igb_rx_bufsz(rx_ring), true); } } } @@ -3293,7 +3293,7 @@ int igb_setup_tx_resources(struct igb_ring *tx_ring) size = sizeof(struct igb_tx_buffer) * tx_ring->count; - tx_ring->tx_buffer_info = vzalloc(size); + tx_ring->tx_buffer_info = vmalloc(size); if (!tx_ring->tx_buffer_info) goto err; @@ -3404,6 +3404,10 @@ void igb_configure_tx_ring(struct igb_adapter *adapter, txdctl |= IGB_TX_HTHRESH << 8; txdctl |= IGB_TX_WTHRESH << 16; + /* reinitialize tx_buffer_info */ + memset(ring->tx_buffer_info, 0, + sizeof(struct igb_tx_buffer) * ring->count); + txdctl |= E1000_TXDCTL_QUEUE_ENABLE; wr32(E1000_TXDCTL(reg_idx), txdctl); } @@ -3435,7 +3439,7 @@ int igb_setup_rx_resources(struct igb_ring *rx_ring) size = sizeof(struct igb_rx_buffer) * rx_ring->count; - rx_ring->rx_buffer_info = vzalloc(size); + rx_ring->rx_buffer_info = vmalloc(size); if (!rx_ring->rx_buffer_info) goto err; @@ -3720,6 +3724,7 @@ void igb_configure_rx_ring(struct igb_adapter *adapter, struct igb_ring *ring) { struct e1000_hw *hw = &adapter->hw; + union e1000_adv_rx_desc *rx_desc; u64 rdba = ring->dma; int reg_idx = ring->reg_idx; u32 srrctl = 0, rxdctl = 0; @@ -3741,7 +3746,10 @@ void igb_configure_rx_ring(struct igb_adapter *adapter, /* set descriptor configuration */ srrctl = IGB_RX_HDR_LEN << E1000_SRRCTL_BSIZEHDRSIZE_SHIFT; - srrctl |= IGB_RX_BUFSZ >> E1000_SRRCTL_BSIZEPKT_SHIFT; + if (ring_uses_large_buffer(ring)) + srrctl |= IGB_RXBUFFER_3072 >> E1000_SRRCTL_BSIZEPKT_SHIFT; + else + srrctl |= IGB_RXBUFFER_2048 >> E1000_SRRCTL_BSIZEPKT_SHIFT; srrctl |= E1000_SRRCTL_DESCTYPE_ADV_ONEBUF; if (hw->mac.type >= e1000_82580) srrctl |= E1000_SRRCTL_TIMESTAMP; @@ -3758,11 +3766,39 @@ void igb_configure_rx_ring(struct igb_adapter *adapter, rxdctl |= IGB_RX_HTHRESH << 8; rxdctl |= IGB_RX_WTHRESH << 16; + /* initialize rx_buffer_info */ + memset(ring->rx_buffer_info, 0, + sizeof(struct igb_rx_buffer) * ring->count); + + /* initialize Rx descriptor 0 */ + rx_desc = IGB_RX_DESC(ring, 0); + rx_desc->wb.upper.length = 0; + /* enable receive descriptor fetching */ rxdctl |= E1000_RXDCTL_QUEUE_ENABLE; wr32(E1000_RXDCTL(reg_idx), rxdctl); } +static void igb_set_rx_buffer_len(struct igb_adapter *adapter, + struct igb_ring *rx_ring) +{ + /* set build_skb and buffer size flags */ + clear_ring_build_skb_enabled(rx_ring); + clear_ring_uses_large_buffer(rx_ring); + + if (adapter->flags & IGB_FLAG_RX_LEGACY) + return; + + set_ring_build_skb_enabled(rx_ring); + +#if (PAGE_SIZE < 8192) + if (adapter->max_frame_size <= IGB_MAX_FRAME_BUILD_SKB) + return; + + set_ring_uses_large_buffer(rx_ring); +#endif +} + /** * igb_configure_rx - Configure receive Unit after Reset * @adapter: board private structure @@ -3780,8 +3816,12 @@ static void igb_configure_rx(struct igb_adapter *adapter) /* Setup the HW Rx Head and Tail Descriptor Pointers and * the Base and Length of the Rx Descriptor Ring */ - for (i = 0; i < adapter->num_rx_queues; i++) - igb_configure_rx_ring(adapter, adapter->rx_ring[i]); + for (i = 0; i < adapter->num_rx_queues; i++) { + struct igb_ring *rx_ring = adapter->rx_ring[i]; + + igb_set_rx_buffer_len(adapter, rx_ring); + igb_configure_rx_ring(adapter, rx_ring); + } } /** @@ -3822,55 +3862,63 @@ static void igb_free_all_tx_resources(struct igb_adapter *adapter) igb_free_tx_resources(adapter->tx_ring[i]); } -void igb_unmap_and_free_tx_resource(struct igb_ring *ring, - struct igb_tx_buffer *tx_buffer) -{ - if (tx_buffer->skb) { - dev_kfree_skb_any(tx_buffer->skb); - if (dma_unmap_len(tx_buffer, len)) - dma_unmap_single(ring->dev, - dma_unmap_addr(tx_buffer, dma), - dma_unmap_len(tx_buffer, len), - DMA_TO_DEVICE); - } else if (dma_unmap_len(tx_buffer, len)) { - dma_unmap_page(ring->dev, - dma_unmap_addr(tx_buffer, dma), - dma_unmap_len(tx_buffer, len), - DMA_TO_DEVICE); - } - tx_buffer->next_to_watch = NULL; - tx_buffer->skb = NULL; - dma_unmap_len_set(tx_buffer, len, 0); - /* buffer_info must be completely set up in the transmit path */ -} - /** * igb_clean_tx_ring - Free Tx Buffers * @tx_ring: ring to be cleaned **/ static void igb_clean_tx_ring(struct igb_ring *tx_ring) { - struct igb_tx_buffer *buffer_info; - unsigned long size; - u16 i; + u16 i = tx_ring->next_to_clean; + struct igb_tx_buffer *tx_buffer = &tx_ring->tx_buffer_info[i]; - if (!tx_ring->tx_buffer_info) - return; - /* Free all the Tx ring sk_buffs */ + while (i != tx_ring->next_to_use) { + union e1000_adv_tx_desc *eop_desc, *tx_desc; - for (i = 0; i < tx_ring->count; i++) { - buffer_info = &tx_ring->tx_buffer_info[i]; - igb_unmap_and_free_tx_resource(tx_ring, buffer_info); - } + /* Free all the Tx ring sk_buffs */ + dev_kfree_skb_any(tx_buffer->skb); - netdev_tx_reset_queue(txring_txq(tx_ring)); + /* unmap skb header data */ + dma_unmap_single(tx_ring->dev, + dma_unmap_addr(tx_buffer, dma), + dma_unmap_len(tx_buffer, len), + DMA_TO_DEVICE); - size = sizeof(struct igb_tx_buffer) * tx_ring->count; - memset(tx_ring->tx_buffer_info, 0, size); + /* check for eop_desc to determine the end of the packet */ + eop_desc = tx_buffer->next_to_watch; + tx_desc = IGB_TX_DESC(tx_ring, i); + + /* unmap remaining buffers */ + while (tx_desc != eop_desc) { + tx_buffer++; + tx_desc++; + i++; + if (unlikely(i == tx_ring->count)) { + i = 0; + tx_buffer = tx_ring->tx_buffer_info; + tx_desc = IGB_TX_DESC(tx_ring, 0); + } + + /* unmap any remaining paged data */ + if (dma_unmap_len(tx_buffer, len)) + dma_unmap_page(tx_ring->dev, + dma_unmap_addr(tx_buffer, dma), + dma_unmap_len(tx_buffer, len), + DMA_TO_DEVICE); + } - /* Zero out the descriptor ring */ - memset(tx_ring->desc, 0, tx_ring->size); + /* move us one more past the eop_desc for start of next pkt */ + tx_buffer++; + i++; + if (unlikely(i == tx_ring->count)) { + i = 0; + tx_buffer = tx_ring->tx_buffer_info; + } + } + /* reset BQL for queue */ + netdev_tx_reset_queue(txring_txq(tx_ring)); + + /* reset next_to_use and next_to_clean */ tx_ring->next_to_use = 0; tx_ring->next_to_clean = 0; } @@ -3932,50 +3980,39 @@ static void igb_free_all_rx_resources(struct igb_adapter *adapter) **/ static void igb_clean_rx_ring(struct igb_ring *rx_ring) { - unsigned long size; - u16 i; + u16 i = rx_ring->next_to_clean; if (rx_ring->skb) dev_kfree_skb(rx_ring->skb); rx_ring->skb = NULL; - if (!rx_ring->rx_buffer_info) - return; - /* Free all the Rx ring sk_buffs */ - for (i = 0; i < rx_ring->count; i++) { + while (i != rx_ring->next_to_alloc) { struct igb_rx_buffer *buffer_info = &rx_ring->rx_buffer_info[i]; - if (!buffer_info->page) - continue; - /* Invalidate cache lines that may have been written to by * device so that we avoid corrupting memory. */ dma_sync_single_range_for_cpu(rx_ring->dev, buffer_info->dma, buffer_info->page_offset, - IGB_RX_BUFSZ, + igb_rx_bufsz(rx_ring), DMA_FROM_DEVICE); /* free resources associated with mapping */ dma_unmap_page_attrs(rx_ring->dev, buffer_info->dma, - PAGE_SIZE, + igb_rx_pg_size(rx_ring), DMA_FROM_DEVICE, - DMA_ATTR_SKIP_CPU_SYNC); + IGB_RX_DMA_ATTR); __page_frag_cache_drain(buffer_info->page, buffer_info->pagecnt_bias); - buffer_info->page = NULL; + i++; + if (i == rx_ring->count) + i = 0; } - size = sizeof(struct igb_rx_buffer) * rx_ring->count; - memset(rx_ring->rx_buffer_info, 0, size); - - /* Zero out the descriptor ring */ - memset(rx_ring->desc, 0, rx_ring->size); - rx_ring->next_to_alloc = 0; rx_ring->next_to_clean = 0; rx_ring->next_to_use = 0; @@ -4240,7 +4277,7 @@ static void igb_set_rx_mode(struct net_device *netdev) struct igb_adapter *adapter = netdev_priv(netdev); struct e1000_hw *hw = &adapter->hw; unsigned int vfn = adapter->vfs_allocated_count; - u32 rctl = 0, vmolr = 0; + u32 rctl = 0, vmolr = 0, rlpml = MAX_JUMBO_FRAME_SIZE; int count; /* Check for Promiscuous and All Multicast modes */ @@ -4298,6 +4335,14 @@ static void igb_set_rx_mode(struct net_device *netdev) E1000_RCTL_VFE); wr32(E1000_RCTL, rctl); +#if (PAGE_SIZE < 8192) + if (!adapter->vfs_allocated_count) { + if (adapter->max_frame_size <= IGB_MAX_FRAME_BUILD_SKB) + rlpml = IGB_MAX_FRAME_BUILD_SKB; + } +#endif + wr32(E1000_RLPML, rlpml); + /* In order to support SR-IOV and eventually VMDq it is necessary to set * the VMOLR to enable the appropriate modes. Without this workaround * we will have issues with VLAN tag stripping not being done for frames @@ -4312,12 +4357,17 @@ static void igb_set_rx_mode(struct net_device *netdev) vmolr |= rd32(E1000_VMOLR(vfn)) & ~(E1000_VMOLR_ROPE | E1000_VMOLR_MPME | E1000_VMOLR_ROMPE); - /* enable Rx jumbo frames, no need for restriction */ + /* enable Rx jumbo frames, restrict as needed to support build_skb */ vmolr &= ~E1000_VMOLR_RLPML_MASK; - vmolr |= MAX_JUMBO_FRAME_SIZE | E1000_VMOLR_LPE; +#if (PAGE_SIZE < 8192) + if (adapter->max_frame_size <= IGB_MAX_FRAME_BUILD_SKB) + vmolr |= IGB_MAX_FRAME_BUILD_SKB; + else +#endif + vmolr |= MAX_JUMBO_FRAME_SIZE; + vmolr |= E1000_VMOLR_LPE; wr32(E1000_VMOLR(vfn), vmolr); - wr32(E1000_RLPML, MAX_JUMBO_FRAME_SIZE); igb_restore_vf_multicasts(adapter); } @@ -5256,18 +5306,32 @@ static void igb_tx_map(struct igb_ring *tx_ring, dma_error: dev_err(tx_ring->dev, "TX DMA map failed\n"); + tx_buffer = &tx_ring->tx_buffer_info[i]; /* clear dma mappings for failed tx_buffer_info map */ - for (;;) { + while (tx_buffer != first) { + if (dma_unmap_len(tx_buffer, len)) + dma_unmap_page(tx_ring->dev, + dma_unmap_addr(tx_buffer, dma), + dma_unmap_len(tx_buffer, len), + DMA_TO_DEVICE); + dma_unmap_len_set(tx_buffer, len, 0); + + if (i--) + i += tx_ring->count; tx_buffer = &tx_ring->tx_buffer_info[i]; - igb_unmap_and_free_tx_resource(tx_ring, tx_buffer); - if (tx_buffer == first) - break; - if (i == 0) - i = tx_ring->count; - i--; } + if (dma_unmap_len(tx_buffer, len)) + dma_unmap_single(tx_ring->dev, + dma_unmap_addr(tx_buffer, dma), + dma_unmap_len(tx_buffer, len), + DMA_TO_DEVICE); + dma_unmap_len_set(tx_buffer, len, 0); + + dev_kfree_skb_any(tx_buffer->skb); + tx_buffer->skb = NULL; + tx_ring->next_to_use = i; } @@ -5339,7 +5403,8 @@ netdev_tx_t igb_xmit_frame_ring(struct sk_buff *skb, return NETDEV_TX_OK; out_drop: - igb_unmap_and_free_tx_resource(tx_ring, first); + dev_kfree_skb_any(first->skb); + first->skb = NULL; return NETDEV_TX_OK; } @@ -6686,7 +6751,6 @@ static bool igb_clean_tx_irq(struct igb_q_vector *q_vector, int napi_budget) DMA_TO_DEVICE); /* clear tx_buffer data */ - tx_buffer->skb = NULL; dma_unmap_len_set(tx_buffer, len, 0); /* clear last DMA location and unmap remaining buffers */ @@ -6822,8 +6886,14 @@ static void igb_reuse_rx_page(struct igb_ring *rx_ring, nta++; rx_ring->next_to_alloc = (nta < rx_ring->count) ? nta : 0; - /* transfer page from old buffer to new buffer */ - *new_buff = *old_buff; + /* Transfer page from old buffer to new buffer. + * Move each member individually to avoid possible store + * forwarding stalls. + */ + new_buff->dma = old_buff->dma; + new_buff->page = old_buff->page; + new_buff->page_offset = old_buff->page_offset; + new_buff->pagecnt_bias = old_buff->pagecnt_bias; } static inline bool igb_page_is_reserved(struct page *page) @@ -6831,11 +6901,10 @@ static inline bool igb_page_is_reserved(struct page *page) return (page_to_nid(page) != numa_mem_id()) || page_is_pfmemalloc(page); } -static bool igb_can_reuse_rx_page(struct igb_rx_buffer *rx_buffer, - struct page *page, - unsigned int truesize) +static bool igb_can_reuse_rx_page(struct igb_rx_buffer *rx_buffer) { - unsigned int pagecnt_bias = rx_buffer->pagecnt_bias--; + unsigned int pagecnt_bias = rx_buffer->pagecnt_bias; + struct page *page = rx_buffer->page; /* avoid re-using remote pages */ if (unlikely(igb_page_is_reserved(page))) @@ -6843,16 +6912,13 @@ static bool igb_can_reuse_rx_page(struct igb_rx_buffer *rx_buffer, #if (PAGE_SIZE < 8192) /* if we are only owner of page we can reuse it */ - if (unlikely(page_ref_count(page) != pagecnt_bias)) + if (unlikely((page_ref_count(page) - pagecnt_bias) > 1)) return false; - - /* flip page offset to other buffer */ - rx_buffer->page_offset ^= IGB_RX_BUFSZ; #else - /* move offset up to the next cache line */ - rx_buffer->page_offset += truesize; +#define IGB_LAST_OFFSET \ + (SKB_WITH_OVERHEAD(PAGE_SIZE) - IGB_RXBUFFER_2048) - if (rx_buffer->page_offset > (PAGE_SIZE - IGB_RX_BUFSZ)) + if (rx_buffer->page_offset > IGB_LAST_OFFSET) return false; #endif @@ -6860,7 +6926,7 @@ static bool igb_can_reuse_rx_page(struct igb_rx_buffer *rx_buffer, * the pagecnt_bias and page count so that we fully restock the * number of references the driver holds. */ - if (unlikely(pagecnt_bias == 1)) { + if (unlikely(!pagecnt_bias)) { page_ref_add(page, USHRT_MAX); rx_buffer->pagecnt_bias = USHRT_MAX; } @@ -6872,34 +6938,56 @@ static bool igb_can_reuse_rx_page(struct igb_rx_buffer *rx_buffer, * igb_add_rx_frag - Add contents of Rx buffer to sk_buff * @rx_ring: rx descriptor ring to transact packets on * @rx_buffer: buffer containing page to add - * @rx_desc: descriptor containing length of buffer written by hardware * @skb: sk_buff to place the data into + * @size: size of buffer to be added * * This function will add the data contained in rx_buffer->page to the skb. - * This is done either through a direct copy if the data in the buffer is - * less than the skb header size, otherwise it will just attach the page as - * a frag to the skb. - * - * The function will then update the page offset if necessary and return - * true if the buffer can be reused by the adapter. **/ -static bool igb_add_rx_frag(struct igb_ring *rx_ring, +static void igb_add_rx_frag(struct igb_ring *rx_ring, struct igb_rx_buffer *rx_buffer, - unsigned int size, - union e1000_adv_rx_desc *rx_desc, - struct sk_buff *skb) + struct sk_buff *skb, + unsigned int size) { - struct page *page = rx_buffer->page; - unsigned char *va = page_address(page) + rx_buffer->page_offset; #if (PAGE_SIZE < 8192) - unsigned int truesize = IGB_RX_BUFSZ; + unsigned int truesize = igb_rx_pg_size(rx_ring) / 2; +#else + unsigned int truesize = ring_uses_build_skb(rx_ring) ? + SKB_DATA_ALIGN(IGB_SKB_PAD + size) : + SKB_DATA_ALIGN(size); +#endif + skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, rx_buffer->page, + rx_buffer->page_offset, size, truesize); +#if (PAGE_SIZE < 8192) + rx_buffer->page_offset ^= truesize; +#else + rx_buffer->page_offset += truesize; +#endif +} + +static struct sk_buff *igb_construct_skb(struct igb_ring *rx_ring, + struct igb_rx_buffer *rx_buffer, + union e1000_adv_rx_desc *rx_desc, + unsigned int size) +{ + void *va = page_address(rx_buffer->page) + rx_buffer->page_offset; +#if (PAGE_SIZE < 8192) + unsigned int truesize = igb_rx_pg_size(rx_ring) / 2; #else unsigned int truesize = SKB_DATA_ALIGN(size); #endif - unsigned int pull_len; + unsigned int headlen; + struct sk_buff *skb; - if (unlikely(skb_is_nonlinear(skb))) - goto add_tail_frag; + /* prefetch first cache line of first page */ + prefetch(va); +#if L1_CACHE_BYTES < 128 + prefetch(va + L1_CACHE_BYTES); +#endif + + /* allocate a skb to store the frags */ + skb = napi_alloc_skb(&rx_ring->q_vector->napi, IGB_RX_HDR_LEN); + if (unlikely(!skb)) + return NULL; if (unlikely(igb_test_staterr(rx_desc, E1000_RXDADV_STAT_TSIP))) { igb_ptp_rx_pktstamp(rx_ring->q_vector, va, skb); @@ -6907,95 +6995,73 @@ static bool igb_add_rx_frag(struct igb_ring *rx_ring, size -= IGB_TS_HDR_LEN; } - if (likely(size <= IGB_RX_HDR_LEN)) { - memcpy(__skb_put(skb, size), va, ALIGN(size, sizeof(long))); - - /* page is not reserved, we can reuse buffer as-is */ - if (likely(!igb_page_is_reserved(page))) - return true; - - /* this page cannot be reused so discard it */ - return false; - } - - /* we need the header to contain the greater of either ETH_HLEN or - * 60 bytes if the skb->len is less than 60 for skb_pad. - */ - pull_len = eth_get_headlen(va, IGB_RX_HDR_LEN); + /* Determine available headroom for copy */ + headlen = size; + if (headlen > IGB_RX_HDR_LEN) + headlen = eth_get_headlen(va, IGB_RX_HDR_LEN); /* align pull length to size of long to optimize memcpy performance */ - memcpy(__skb_put(skb, pull_len), va, ALIGN(pull_len, sizeof(long))); + memcpy(__skb_put(skb, headlen), va, ALIGN(headlen, sizeof(long))); /* update all of the pointers */ - va += pull_len; - size -= pull_len; - -add_tail_frag: - skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, page, - (unsigned long)va & ~PAGE_MASK, size, truesize); + size -= headlen; + if (size) { + skb_add_rx_frag(skb, 0, rx_buffer->page, + (va + headlen) - page_address(rx_buffer->page), + size, truesize); +#if (PAGE_SIZE < 8192) + rx_buffer->page_offset ^= truesize; +#else + rx_buffer->page_offset += truesize; +#endif + } else { + rx_buffer->pagecnt_bias++; + } - return igb_can_reuse_rx_page(rx_buffer, page, truesize); + return skb; } -static struct sk_buff *igb_fetch_rx_buffer(struct igb_ring *rx_ring, - union e1000_adv_rx_desc *rx_desc, - struct sk_buff *skb) +static struct sk_buff *igb_build_skb(struct igb_ring *rx_ring, + struct igb_rx_buffer *rx_buffer, + union e1000_adv_rx_desc *rx_desc, + unsigned int size) { - unsigned int size = le16_to_cpu(rx_desc->wb.upper.length); - struct igb_rx_buffer *rx_buffer; - struct page *page; - - rx_buffer = &rx_ring->rx_buffer_info[rx_ring->next_to_clean]; - page = rx_buffer->page; - prefetchw(page); - - /* we are reusing so sync this buffer for CPU use */ - dma_sync_single_range_for_cpu(rx_ring->dev, - rx_buffer->dma, - rx_buffer->page_offset, - size, - DMA_FROM_DEVICE); - - if (likely(!skb)) { - void *page_addr = page_address(page) + - rx_buffer->page_offset; + void *va = page_address(rx_buffer->page) + rx_buffer->page_offset; +#if (PAGE_SIZE < 8192) + unsigned int truesize = igb_rx_pg_size(rx_ring) / 2; +#else + unsigned int truesize = SKB_DATA_ALIGN(sizeof(struct skb_shared_info)) + + SKB_DATA_ALIGN(IGB_SKB_PAD + size); +#endif + struct sk_buff *skb; - /* prefetch first cache line of first page */ - prefetch(page_addr); + /* prefetch first cache line of first page */ + prefetch(va); #if L1_CACHE_BYTES < 128 - prefetch(page_addr + L1_CACHE_BYTES); + prefetch(va + L1_CACHE_BYTES); #endif - /* allocate a skb to store the frags */ - skb = napi_alloc_skb(&rx_ring->q_vector->napi, IGB_RX_HDR_LEN); - if (unlikely(!skb)) { - rx_ring->rx_stats.alloc_failed++; - return NULL; - } + /* build an skb around the page buffer */ + skb = build_skb(va - IGB_SKB_PAD, truesize); + if (unlikely(!skb)) + return NULL; - /* we will be copying header into skb->data in - * pskb_may_pull so it is in our interest to prefetch - * it now to avoid a possible cache miss - */ - prefetchw(skb->data); - } + /* update pointers within the skb to store the data */ + skb_reserve(skb, IGB_SKB_PAD); + __skb_put(skb, size); - /* pull page into skb */ - if (igb_add_rx_frag(rx_ring, rx_buffer, size, rx_desc, skb)) { - /* hand second half of page back to the ring */ - igb_reuse_rx_page(rx_ring, rx_buffer); - } else { - /* We are not reusing the buffer so unmap it and free - * any references we are holding to it - */ - dma_unmap_page_attrs(rx_ring->dev, rx_buffer->dma, - PAGE_SIZE, DMA_FROM_DEVICE, - DMA_ATTR_SKIP_CPU_SYNC); - __page_frag_cache_drain(page, rx_buffer->pagecnt_bias); + /* pull timestamp out of packet data */ + if (igb_test_staterr(rx_desc, E1000_RXDADV_STAT_TSIP)) { + igb_ptp_rx_pktstamp(rx_ring->q_vector, skb->data, skb); + __skb_pull(skb, IGB_TS_HDR_LEN); } - /* clear contents of rx_buffer */ - rx_buffer->page = NULL; + /* update buffer offset */ +#if (PAGE_SIZE < 8192) + rx_buffer->page_offset ^= truesize; +#else + rx_buffer->page_offset += truesize; +#endif return skb; } @@ -7154,6 +7220,47 @@ static void igb_process_skb_fields(struct igb_ring *rx_ring, skb->protocol = eth_type_trans(skb, rx_ring->netdev); } +static struct igb_rx_buffer *igb_get_rx_buffer(struct igb_ring *rx_ring, + const unsigned int size) +{ + struct igb_rx_buffer *rx_buffer; + + rx_buffer = &rx_ring->rx_buffer_info[rx_ring->next_to_clean]; + prefetchw(rx_buffer->page); + + /* we are reusing so sync this buffer for CPU use */ + dma_sync_single_range_for_cpu(rx_ring->dev, + rx_buffer->dma, + rx_buffer->page_offset, + size, + DMA_FROM_DEVICE); + + rx_buffer->pagecnt_bias--; + + return rx_buffer; +} + +static void igb_put_rx_buffer(struct igb_ring *rx_ring, + struct igb_rx_buffer *rx_buffer) +{ + if (igb_can_reuse_rx_page(rx_buffer)) { + /* hand second half of page back to the ring */ + igb_reuse_rx_page(rx_ring, rx_buffer); + } else { + /* We are not reusing the buffer so unmap it and free + * any references we are holding to it + */ + dma_unmap_page_attrs(rx_ring->dev, rx_buffer->dma, + igb_rx_pg_size(rx_ring), DMA_FROM_DEVICE, + IGB_RX_DMA_ATTR); + __page_frag_cache_drain(rx_buffer->page, + rx_buffer->pagecnt_bias); + } + + /* clear contents of rx_buffer */ + rx_buffer->page = NULL; +} + static int igb_clean_rx_irq(struct igb_q_vector *q_vector, const int budget) { struct igb_ring *rx_ring = q_vector->rx.ring; @@ -7163,6 +7270,8 @@ static int igb_clean_rx_irq(struct igb_q_vector *q_vector, const int budget) while (likely(total_packets < budget)) { union e1000_adv_rx_desc *rx_desc; + struct igb_rx_buffer *rx_buffer; + unsigned int size; /* return some buffers to hardware, one at a time is too slow */ if (cleaned_count >= IGB_RX_BUFFER_WRITE) { @@ -7171,8 +7280,8 @@ static int igb_clean_rx_irq(struct igb_q_vector *q_vector, const int budget) } rx_desc = IGB_RX_DESC(rx_ring, rx_ring->next_to_clean); - - if (!rx_desc->wb.upper.status_error) + size = le16_to_cpu(rx_desc->wb.upper.length); + if (!size) break; /* This memory barrier is needed to keep us from reading @@ -7181,13 +7290,25 @@ static int igb_clean_rx_irq(struct igb_q_vector *q_vector, const int budget) */ dma_rmb(); + rx_buffer = igb_get_rx_buffer(rx_ring, size); + /* retrieve a buffer from the ring */ - skb = igb_fetch_rx_buffer(rx_ring, rx_desc, skb); + if (skb) + igb_add_rx_frag(rx_ring, rx_buffer, skb, size); + else if (ring_uses_build_skb(rx_ring)) + skb = igb_build_skb(rx_ring, rx_buffer, rx_desc, size); + else + skb = igb_construct_skb(rx_ring, rx_buffer, + rx_desc, size); /* exit if we failed to retrieve a buffer */ - if (!skb) + if (!skb) { + rx_ring->rx_stats.alloc_failed++; + rx_buffer->pagecnt_bias++; break; + } + igb_put_rx_buffer(rx_ring, rx_buffer); cleaned_count++; /* fetch next buffer in frame if non-eop */ @@ -7231,6 +7352,11 @@ static int igb_clean_rx_irq(struct igb_q_vector *q_vector, const int budget) return total_packets; } +static inline unsigned int igb_rx_offset(struct igb_ring *rx_ring) +{ + return ring_uses_build_skb(rx_ring) ? IGB_SKB_PAD : 0; +} + static bool igb_alloc_mapped_page(struct igb_ring *rx_ring, struct igb_rx_buffer *bi) { @@ -7242,21 +7368,23 @@ static bool igb_alloc_mapped_page(struct igb_ring *rx_ring, return true; /* alloc new page for storage */ - page = dev_alloc_page(); + page = dev_alloc_pages(igb_rx_pg_order(rx_ring)); if (unlikely(!page)) { rx_ring->rx_stats.alloc_failed++; return false; } /* map page for use */ - dma = dma_map_page_attrs(rx_ring->dev, page, 0, PAGE_SIZE, - DMA_FROM_DEVICE, DMA_ATTR_SKIP_CPU_SYNC); + dma = dma_map_page_attrs(rx_ring->dev, page, 0, + igb_rx_pg_size(rx_ring), + DMA_FROM_DEVICE, + IGB_RX_DMA_ATTR); /* if mapping failed free memory back to system since * there isn't much point in holding memory we can't use */ if (dma_mapping_error(rx_ring->dev, dma)) { - __free_page(page); + __free_pages(page, igb_rx_pg_order(rx_ring)); rx_ring->rx_stats.alloc_failed++; return false; @@ -7264,7 +7392,7 @@ static bool igb_alloc_mapped_page(struct igb_ring *rx_ring, bi->dma = dma; bi->page = page; - bi->page_offset = 0; + bi->page_offset = igb_rx_offset(rx_ring); bi->pagecnt_bias = 1; return true; @@ -7279,6 +7407,7 @@ void igb_alloc_rx_buffers(struct igb_ring *rx_ring, u16 cleaned_count) union e1000_adv_rx_desc *rx_desc; struct igb_rx_buffer *bi; u16 i = rx_ring->next_to_use; + u16 bufsz; /* nothing to do */ if (!cleaned_count) @@ -7288,14 +7417,15 @@ void igb_alloc_rx_buffers(struct igb_ring *rx_ring, u16 cleaned_count) bi = &rx_ring->rx_buffer_info[i]; i -= rx_ring->count; + bufsz = igb_rx_bufsz(rx_ring); + do { if (!igb_alloc_mapped_page(rx_ring, bi)) break; /* sync the buffer for use by the device */ dma_sync_single_range_for_device(rx_ring->dev, bi->dma, - bi->page_offset, - IGB_RX_BUFSZ, + bi->page_offset, bufsz, DMA_FROM_DEVICE); /* Refresh the desc even if buffer_addrs didn't change @@ -7312,8 +7442,8 @@ void igb_alloc_rx_buffers(struct igb_ring *rx_ring, u16 cleaned_count) i -= rx_ring->count; } - /* clear the status bits for the next_to_use descriptor */ - rx_desc->wb.upper.status_error = 0; + /* clear the length for the next_to_use descriptor */ + rx_desc->wb.upper.length = 0; cleaned_count--; } while (cleaned_count); diff --git a/drivers/net/ethernet/intel/igb/igb_ptp.c b/drivers/net/ethernet/intel/igb/igb_ptp.c index c4477552ce9e..7a3fd4d74592 100644 --- a/drivers/net/ethernet/intel/igb/igb_ptp.c +++ b/drivers/net/ethernet/intel/igb/igb_ptp.c @@ -764,8 +764,7 @@ static void igb_ptp_tx_hwtstamp(struct igb_adapter *adapter) * incoming frame. The value is stored in little endian format starting on * byte 8. **/ -void igb_ptp_rx_pktstamp(struct igb_q_vector *q_vector, - unsigned char *va, +void igb_ptp_rx_pktstamp(struct igb_q_vector *q_vector, void *va, struct sk_buff *skb) { __le64 *regval = (__le64 *)va; diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c index 90fa5bf23d1b..0da0752fedef 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c @@ -186,60 +186,62 @@ static u32 ixgbe_get_supported_10gtypes(struct ixgbe_hw *hw) } } -static int ixgbe_get_settings(struct net_device *netdev, - struct ethtool_cmd *ecmd) +static int ixgbe_get_link_ksettings(struct net_device *netdev, + struct ethtool_link_ksettings *cmd) { struct ixgbe_adapter *adapter = netdev_priv(netdev); struct ixgbe_hw *hw = &adapter->hw; ixgbe_link_speed supported_link; bool autoneg = false; + u32 supported, advertising; + + ethtool_convert_link_mode_to_legacy_u32(&supported, + cmd->link_modes.supported); hw->mac.ops.get_link_capabilities(hw, &supported_link, &autoneg); /* set the supported link speeds */ if (supported_link & IXGBE_LINK_SPEED_10GB_FULL) - ecmd->supported |= ixgbe_get_supported_10gtypes(hw); + supported |= ixgbe_get_supported_10gtypes(hw); if (supported_link & IXGBE_LINK_SPEED_1GB_FULL) - ecmd->supported |= (ixgbe_isbackplane(hw->phy.media_type)) ? + supported |= (ixgbe_isbackplane(hw->phy.media_type)) ? SUPPORTED_1000baseKX_Full : SUPPORTED_1000baseT_Full; if (supported_link & IXGBE_LINK_SPEED_100_FULL) - ecmd->supported |= SUPPORTED_100baseT_Full; + supported |= SUPPORTED_100baseT_Full; if (supported_link & IXGBE_LINK_SPEED_10_FULL) - ecmd->supported |= SUPPORTED_10baseT_Full; + supported |= SUPPORTED_10baseT_Full; /* default advertised speed if phy.autoneg_advertised isn't set */ - ecmd->advertising = ecmd->supported; + advertising = supported; /* set the advertised speeds */ if (hw->phy.autoneg_advertised) { - ecmd->advertising = 0; + advertising = 0; if (hw->phy.autoneg_advertised & IXGBE_LINK_SPEED_10_FULL) - ecmd->advertising |= ADVERTISED_10baseT_Full; + advertising |= ADVERTISED_10baseT_Full; if (hw->phy.autoneg_advertised & IXGBE_LINK_SPEED_100_FULL) - ecmd->advertising |= ADVERTISED_100baseT_Full; + advertising |= ADVERTISED_100baseT_Full; if (hw->phy.autoneg_advertised & IXGBE_LINK_SPEED_10GB_FULL) - ecmd->advertising |= ecmd->supported & ADVRTSD_MSK_10G; + advertising |= supported & ADVRTSD_MSK_10G; if (hw->phy.autoneg_advertised & IXGBE_LINK_SPEED_1GB_FULL) { - if (ecmd->supported & SUPPORTED_1000baseKX_Full) - ecmd->advertising |= ADVERTISED_1000baseKX_Full; + if (supported & SUPPORTED_1000baseKX_Full) + advertising |= ADVERTISED_1000baseKX_Full; else - ecmd->advertising |= ADVERTISED_1000baseT_Full; + advertising |= ADVERTISED_1000baseT_Full; } } else { if (hw->phy.multispeed_fiber && !autoneg) { if (supported_link & IXGBE_LINK_SPEED_10GB_FULL) - ecmd->advertising = ADVERTISED_10000baseT_Full; + advertising = ADVERTISED_10000baseT_Full; } } if (autoneg) { - ecmd->supported |= SUPPORTED_Autoneg; - ecmd->advertising |= ADVERTISED_Autoneg; - ecmd->autoneg = AUTONEG_ENABLE; + supported |= SUPPORTED_Autoneg; + advertising |= ADVERTISED_Autoneg; + cmd->base.autoneg = AUTONEG_ENABLE; } else - ecmd->autoneg = AUTONEG_DISABLE; - - ecmd->transceiver = XCVR_EXTERNAL; + cmd->base.autoneg = AUTONEG_DISABLE; /* Determine the remaining settings based on the PHY type. */ switch (adapter->hw.phy.type) { @@ -248,14 +250,14 @@ static int ixgbe_get_settings(struct net_device *netdev, case ixgbe_phy_x550em_ext_t: case ixgbe_phy_fw: case ixgbe_phy_cu_unknown: - ecmd->supported |= SUPPORTED_TP; - ecmd->advertising |= ADVERTISED_TP; - ecmd->port = PORT_TP; + supported |= SUPPORTED_TP; + advertising |= ADVERTISED_TP; + cmd->base.port = PORT_TP; break; case ixgbe_phy_qt: - ecmd->supported |= SUPPORTED_FIBRE; - ecmd->advertising |= ADVERTISED_FIBRE; - ecmd->port = PORT_FIBRE; + supported |= SUPPORTED_FIBRE; + advertising |= ADVERTISED_FIBRE; + cmd->base.port = PORT_FIBRE; break; case ixgbe_phy_nl: case ixgbe_phy_sfp_passive_tyco: @@ -273,9 +275,9 @@ static int ixgbe_get_settings(struct net_device *netdev, case ixgbe_sfp_type_da_cu: case ixgbe_sfp_type_da_cu_core0: case ixgbe_sfp_type_da_cu_core1: - ecmd->supported |= SUPPORTED_FIBRE; - ecmd->advertising |= ADVERTISED_FIBRE; - ecmd->port = PORT_DA; + supported |= SUPPORTED_FIBRE; + advertising |= ADVERTISED_FIBRE; + cmd->base.port = PORT_DA; break; case ixgbe_sfp_type_sr: case ixgbe_sfp_type_lr: @@ -285,102 +287,113 @@ static int ixgbe_get_settings(struct net_device *netdev, case ixgbe_sfp_type_1g_sx_core1: case ixgbe_sfp_type_1g_lx_core0: case ixgbe_sfp_type_1g_lx_core1: - ecmd->supported |= SUPPORTED_FIBRE; - ecmd->advertising |= ADVERTISED_FIBRE; - ecmd->port = PORT_FIBRE; + supported |= SUPPORTED_FIBRE; + advertising |= ADVERTISED_FIBRE; + cmd->base.port = PORT_FIBRE; break; case ixgbe_sfp_type_not_present: - ecmd->supported |= SUPPORTED_FIBRE; - ecmd->advertising |= ADVERTISED_FIBRE; - ecmd->port = PORT_NONE; + supported |= SUPPORTED_FIBRE; + advertising |= ADVERTISED_FIBRE; + cmd->base.port = PORT_NONE; break; case ixgbe_sfp_type_1g_cu_core0: case ixgbe_sfp_type_1g_cu_core1: - ecmd->supported |= SUPPORTED_TP; - ecmd->advertising |= ADVERTISED_TP; - ecmd->port = PORT_TP; + supported |= SUPPORTED_TP; + advertising |= ADVERTISED_TP; + cmd->base.port = PORT_TP; break; case ixgbe_sfp_type_unknown: default: - ecmd->supported |= SUPPORTED_FIBRE; - ecmd->advertising |= ADVERTISED_FIBRE; - ecmd->port = PORT_OTHER; + supported |= SUPPORTED_FIBRE; + advertising |= ADVERTISED_FIBRE; + cmd->base.port = PORT_OTHER; break; } break; case ixgbe_phy_xaui: - ecmd->supported |= SUPPORTED_FIBRE; - ecmd->advertising |= ADVERTISED_FIBRE; - ecmd->port = PORT_NONE; + supported |= SUPPORTED_FIBRE; + advertising |= ADVERTISED_FIBRE; + cmd->base.port = PORT_NONE; break; case ixgbe_phy_unknown: case ixgbe_phy_generic: case ixgbe_phy_sfp_unsupported: default: - ecmd->supported |= SUPPORTED_FIBRE; - ecmd->advertising |= ADVERTISED_FIBRE; - ecmd->port = PORT_OTHER; + supported |= SUPPORTED_FIBRE; + advertising |= ADVERTISED_FIBRE; + cmd->base.port = PORT_OTHER; break; } /* Indicate pause support */ - ecmd->supported |= SUPPORTED_Pause; + supported |= SUPPORTED_Pause; switch (hw->fc.requested_mode) { case ixgbe_fc_full: - ecmd->advertising |= ADVERTISED_Pause; + advertising |= ADVERTISED_Pause; break; case ixgbe_fc_rx_pause: - ecmd->advertising |= ADVERTISED_Pause | + advertising |= ADVERTISED_Pause | ADVERTISED_Asym_Pause; break; case ixgbe_fc_tx_pause: - ecmd->advertising |= ADVERTISED_Asym_Pause; + advertising |= ADVERTISED_Asym_Pause; break; default: - ecmd->advertising &= ~(ADVERTISED_Pause | + advertising &= ~(ADVERTISED_Pause | ADVERTISED_Asym_Pause); } if (netif_carrier_ok(netdev)) { switch (adapter->link_speed) { case IXGBE_LINK_SPEED_10GB_FULL: - ethtool_cmd_speed_set(ecmd, SPEED_10000); + cmd->base.speed = SPEED_10000; break; case IXGBE_LINK_SPEED_5GB_FULL: - ethtool_cmd_speed_set(ecmd, SPEED_5000); + cmd->base.speed = SPEED_5000; break; case IXGBE_LINK_SPEED_2_5GB_FULL: - ethtool_cmd_speed_set(ecmd, SPEED_2500); + cmd->base.speed = SPEED_2500; break; case IXGBE_LINK_SPEED_1GB_FULL: - ethtool_cmd_speed_set(ecmd, SPEED_1000); + cmd->base.speed = SPEED_1000; break; case IXGBE_LINK_SPEED_100_FULL: - ethtool_cmd_speed_set(ecmd, SPEED_100); + cmd->base.speed = SPEED_100; break; case IXGBE_LINK_SPEED_10_FULL: - ethtool_cmd_speed_set(ecmd, SPEED_10); + cmd->base.speed = SPEED_10; break; default: break; } - ecmd->duplex = DUPLEX_FULL; + cmd->base.duplex = DUPLEX_FULL; } else { - ethtool_cmd_speed_set(ecmd, SPEED_UNKNOWN); - ecmd->duplex = DUPLEX_UNKNOWN; + cmd->base.speed = SPEED_UNKNOWN; + cmd->base.duplex = DUPLEX_UNKNOWN; } + ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.supported, + supported); + ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.advertising, + advertising); + return 0; } -static int ixgbe_set_settings(struct net_device *netdev, - struct ethtool_cmd *ecmd) +static int ixgbe_set_link_ksettings(struct net_device *netdev, + const struct ethtool_link_ksettings *cmd) { struct ixgbe_adapter *adapter = netdev_priv(netdev); struct ixgbe_hw *hw = &adapter->hw; u32 advertised, old; s32 err = 0; + u32 supported, advertising; + + ethtool_convert_link_mode_to_legacy_u32(&supported, + cmd->link_modes.supported); + ethtool_convert_link_mode_to_legacy_u32(&advertising, + cmd->link_modes.advertising); if ((hw->phy.media_type == ixgbe_media_type_copper) || (hw->phy.multispeed_fiber)) { @@ -388,12 +401,12 @@ static int ixgbe_set_settings(struct net_device *netdev, * this function does not support duplex forcing, but can * limit the advertising of the adapter to the specified speed */ - if (ecmd->advertising & ~ecmd->supported) + if (advertising & ~supported) return -EINVAL; /* only allow one speed at a time if no autoneg */ - if (!ecmd->autoneg && hw->phy.multispeed_fiber) { - if (ecmd->advertising == + if (!cmd->base.autoneg && hw->phy.multispeed_fiber) { + if (advertising == (ADVERTISED_10000baseT_Full | ADVERTISED_1000baseT_Full)) return -EINVAL; @@ -401,16 +414,16 @@ static int ixgbe_set_settings(struct net_device *netdev, old = hw->phy.autoneg_advertised; advertised = 0; - if (ecmd->advertising & ADVERTISED_10000baseT_Full) + if (advertising & ADVERTISED_10000baseT_Full) advertised |= IXGBE_LINK_SPEED_10GB_FULL; - if (ecmd->advertising & ADVERTISED_1000baseT_Full) + if (advertising & ADVERTISED_1000baseT_Full) advertised |= IXGBE_LINK_SPEED_1GB_FULL; - if (ecmd->advertising & ADVERTISED_100baseT_Full) + if (advertising & ADVERTISED_100baseT_Full) advertised |= IXGBE_LINK_SPEED_100_FULL; - if (ecmd->advertising & ADVERTISED_10baseT_Full) + if (advertising & ADVERTISED_10baseT_Full) advertised |= IXGBE_LINK_SPEED_10_FULL; if (old == advertised) @@ -428,10 +441,11 @@ static int ixgbe_set_settings(struct net_device *netdev, clear_bit(__IXGBE_IN_SFP_INIT, &adapter->state); } else { /* in this case we currently only support 10Gb/FULL */ - u32 speed = ethtool_cmd_speed(ecmd); - if ((ecmd->autoneg == AUTONEG_ENABLE) || - (ecmd->advertising != ADVERTISED_10000baseT_Full) || - (speed + ecmd->duplex != SPEED_10000 + DUPLEX_FULL)) + u32 speed = cmd->base.speed; + + if ((cmd->base.autoneg == AUTONEG_ENABLE) || + (advertising != ADVERTISED_10000baseT_Full) || + (speed + cmd->base.duplex != SPEED_10000 + DUPLEX_FULL)) return -EINVAL; } @@ -3402,8 +3416,6 @@ static int ixgbe_set_priv_flags(struct net_device *netdev, u32 priv_flags) } static const struct ethtool_ops ixgbe_ethtool_ops = { - .get_settings = ixgbe_get_settings, - .set_settings = ixgbe_set_settings, .get_drvinfo = ixgbe_get_drvinfo, .get_regs_len = ixgbe_get_regs_len, .get_regs = ixgbe_get_regs, @@ -3442,6 +3454,8 @@ static const struct ethtool_ops ixgbe_ethtool_ops = { .get_ts_info = ixgbe_get_ts_info, .get_module_info = ixgbe_get_module_info, .get_module_eeprom = ixgbe_get_module_eeprom, + .get_link_ksettings = ixgbe_get_link_ksettings, + .set_link_ksettings = ixgbe_set_link_ksettings, }; void ixgbe_set_ethtool_ops(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 a7a430a7be2c..852a2e7e25ed 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -2122,7 +2122,7 @@ static struct sk_buff *ixgbe_build_skb(struct ixgbe_ring *rx_ring, prefetch(va + L1_CACHE_BYTES); #endif - /* build an skb to around the page buffer */ + /* build an skb around the page buffer */ skb = build_skb(va - IXGBE_SKB_PAD, truesize); if (unlikely(!skb)) return NULL; @@ -8948,7 +8948,9 @@ static int __ixgbe_setup_tc(struct net_device *dev, u32 handle, __be16 proto, if (tc->type != TC_SETUP_MQPRIO) return -EINVAL; - return ixgbe_setup_tc(dev, tc->tc); + tc->mqprio->hw = TC_MQPRIO_HW_OFFLOAD_TCS; + + return ixgbe_setup_tc(dev, tc->mqprio->num_tc); } #ifdef CONFIG_PCI_IOV diff --git a/drivers/net/ethernet/marvell/Kconfig b/drivers/net/ethernet/marvell/Kconfig index d2555e8b947e..da6fb825afea 100644 --- a/drivers/net/ethernet/marvell/Kconfig +++ b/drivers/net/ethernet/marvell/Kconfig @@ -82,13 +82,13 @@ config MVNETA_BM that all dependencies are met. config MVPP2 - tristate "Marvell Armada 375 network interface support" + tristate "Marvell Armada 375/7K/8K network interface support" depends on ARCH_MVEBU || COMPILE_TEST depends on HAS_DMA select MVMDIO ---help--- This driver supports the network interface units in the - Marvell ARMADA 375 SoC. + Marvell ARMADA 375, 7K and 8K SoCs. config PXA168_ETH tristate "Marvell pxa168 ethernet support" diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c index 61dd4462411c..aebbc5399a06 100644 --- a/drivers/net/ethernet/marvell/mvneta.c +++ b/drivers/net/ethernet/marvell/mvneta.c @@ -431,6 +431,7 @@ struct mvneta_port { /* Flags for special SoC configurations */ bool neta_armada3700; u16 rx_offset_correction; + const struct mbus_dram_target_info *dram_target_info; }; /* The mvneta_tx_desc and mvneta_rx_desc structures describe the @@ -4118,7 +4119,6 @@ static int mvneta_port_power_up(struct mvneta_port *pp, int phy_mode) /* Device initialization routine */ static int mvneta_probe(struct platform_device *pdev) { - const struct mbus_dram_target_info *dram_target_info; struct resource *res; struct device_node *dn = pdev->dev.of_node; struct device_node *phy_node; @@ -4267,13 +4267,13 @@ static int mvneta_probe(struct platform_device *pdev) pp->tx_csum_limit = tx_csum_limit; - dram_target_info = mv_mbus_dram_info(); + pp->dram_target_info = mv_mbus_dram_info(); /* Armada3700 requires setting default configuration of Mbus * windows, however without using filled mbus_dram_target_info * structure. */ - if (dram_target_info || pp->neta_armada3700) - mvneta_conf_mbus_windows(pp, dram_target_info); + if (pp->dram_target_info || pp->neta_armada3700) + mvneta_conf_mbus_windows(pp, pp->dram_target_info); pp->tx_ring_size = MVNETA_MAX_TXD; pp->rx_ring_size = MVNETA_MAX_RXD; @@ -4405,6 +4405,58 @@ static int mvneta_remove(struct platform_device *pdev) return 0; } +#ifdef CONFIG_PM_SLEEP +static int mvneta_suspend(struct device *device) +{ + struct net_device *dev = dev_get_drvdata(device); + struct mvneta_port *pp = netdev_priv(dev); + + if (netif_running(dev)) + mvneta_stop(dev); + netif_device_detach(dev); + clk_disable_unprepare(pp->clk_bus); + clk_disable_unprepare(pp->clk); + return 0; +} + +static int mvneta_resume(struct device *device) +{ + struct platform_device *pdev = to_platform_device(device); + struct net_device *dev = dev_get_drvdata(device); + struct mvneta_port *pp = netdev_priv(dev); + int err; + + clk_prepare_enable(pp->clk); + if (!IS_ERR(pp->clk_bus)) + clk_prepare_enable(pp->clk_bus); + if (pp->dram_target_info || pp->neta_armada3700) + mvneta_conf_mbus_windows(pp, pp->dram_target_info); + if (pp->bm_priv) { + err = mvneta_bm_port_init(pdev, pp); + if (err < 0) { + dev_info(&pdev->dev, "use SW buffer management\n"); + pp->bm_priv = NULL; + } + } + mvneta_defaults_set(pp); + err = mvneta_port_power_up(pp, pp->phy_interface); + if (err < 0) { + dev_err(device, "can't power up port\n"); + return err; + } + + if (pp->use_inband_status) + mvneta_fixed_link_update(pp, dev->phydev); + + netif_device_attach(dev); + if (netif_running(dev)) + mvneta_open(dev); + return 0; +} +#endif + +static SIMPLE_DEV_PM_OPS(mvneta_pm_ops, mvneta_suspend, mvneta_resume); + static const struct of_device_id mvneta_match[] = { { .compatible = "marvell,armada-370-neta" }, { .compatible = "marvell,armada-xp-neta" }, @@ -4419,6 +4471,7 @@ static struct platform_driver mvneta_driver = { .driver = { .name = MVNETA_DRIVER_NAME, .of_match_table = mvneta_match, + .pm = &mvneta_pm_ops, }, }; diff --git a/drivers/net/ethernet/marvell/mvpp2.c b/drivers/net/ethernet/marvell/mvpp2.c index d00421b9ffea..af5bfa13d976 100644 --- a/drivers/net/ethernet/marvell/mvpp2.c +++ b/drivers/net/ethernet/marvell/mvpp2.c @@ -25,6 +25,7 @@ #include <linux/of_mdio.h> #include <linux/of_net.h> #include <linux/of_address.h> +#include <linux/of_device.h> #include <linux/phy.h> #include <linux/clk.h> #include <linux/hrtimer.h> @@ -49,9 +50,11 @@ #define MVPP2_SNOOP_PKT_SIZE_MASK 0x1ff #define MVPP2_SNOOP_BUF_HDR_MASK BIT(9) #define MVPP2_RXQ_POOL_SHORT_OFFS 20 -#define MVPP2_RXQ_POOL_SHORT_MASK 0x700000 +#define MVPP21_RXQ_POOL_SHORT_MASK 0x700000 +#define MVPP22_RXQ_POOL_SHORT_MASK 0xf00000 #define MVPP2_RXQ_POOL_LONG_OFFS 24 -#define MVPP2_RXQ_POOL_LONG_MASK 0x7000000 +#define MVPP21_RXQ_POOL_LONG_MASK 0x7000000 +#define MVPP22_RXQ_POOL_LONG_MASK 0xf000000 #define MVPP2_RXQ_PACKET_OFFSET_OFFS 28 #define MVPP2_RXQ_PACKET_OFFSET_MASK 0x70000000 #define MVPP2_RXQ_DISABLE_MASK BIT(31) @@ -99,6 +102,7 @@ /* Descriptor Manager Top Registers */ #define MVPP2_RXQ_NUM_REG 0x2040 #define MVPP2_RXQ_DESC_ADDR_REG 0x2044 +#define MVPP22_DESC_ADDR_OFFS 8 #define MVPP2_RXQ_DESC_SIZE_REG 0x2048 #define MVPP2_RXQ_DESC_SIZE_MASK 0x3ff0 #define MVPP2_RXQ_STATUS_UPDATE_REG(rxq) (0x3000 + 4 * (rxq)) @@ -117,9 +121,6 @@ #define MVPP2_TXQ_DESC_SIZE_REG 0x2088 #define MVPP2_TXQ_DESC_SIZE_MASK 0x3ff0 #define MVPP2_AGGR_TXQ_UPDATE_REG 0x2090 -#define MVPP2_TXQ_THRESH_REG 0x2094 -#define MVPP2_TRANSMITTED_THRESH_OFFSET 16 -#define MVPP2_TRANSMITTED_THRESH_MASK 0x3fff0000 #define MVPP2_TXQ_INDEX_REG 0x2098 #define MVPP2_TXQ_PREF_BUF_REG 0x209c #define MVPP2_PREF_BUF_PTR(desc) ((desc) & 0xfff) @@ -140,6 +141,7 @@ #define MVPP2_TXQ_RSVD_CLR_REG 0x20b8 #define MVPP2_TXQ_RSVD_CLR_OFFSET 16 #define MVPP2_AGGR_TXQ_DESC_ADDR_REG(cpu) (0x2100 + 4 * (cpu)) +#define MVPP22_AGGR_TXQ_DESC_ADDR_OFFS 8 #define MVPP2_AGGR_TXQ_DESC_SIZE_REG(cpu) (0x2140 + 4 * (cpu)) #define MVPP2_AGGR_TXQ_DESC_SIZE_MASK 0x3ff0 #define MVPP2_AGGR_TXQ_STATUS_REG(cpu) (0x2180 + 4 * (cpu)) @@ -152,10 +154,52 @@ #define MVPP2_WIN_REMAP(w) (0x4040 + ((w) << 2)) #define MVPP2_BASE_ADDR_ENABLE 0x4060 +/* AXI Bridge Registers */ +#define MVPP22_AXI_BM_WR_ATTR_REG 0x4100 +#define MVPP22_AXI_BM_RD_ATTR_REG 0x4104 +#define MVPP22_AXI_AGGRQ_DESCR_RD_ATTR_REG 0x4110 +#define MVPP22_AXI_TXQ_DESCR_WR_ATTR_REG 0x4114 +#define MVPP22_AXI_TXQ_DESCR_RD_ATTR_REG 0x4118 +#define MVPP22_AXI_RXQ_DESCR_WR_ATTR_REG 0x411c +#define MVPP22_AXI_RX_DATA_WR_ATTR_REG 0x4120 +#define MVPP22_AXI_TX_DATA_RD_ATTR_REG 0x4130 +#define MVPP22_AXI_RD_NORMAL_CODE_REG 0x4150 +#define MVPP22_AXI_RD_SNOOP_CODE_REG 0x4154 +#define MVPP22_AXI_WR_NORMAL_CODE_REG 0x4160 +#define MVPP22_AXI_WR_SNOOP_CODE_REG 0x4164 + +/* Values for AXI Bridge registers */ +#define MVPP22_AXI_ATTR_CACHE_OFFS 0 +#define MVPP22_AXI_ATTR_DOMAIN_OFFS 12 + +#define MVPP22_AXI_CODE_CACHE_OFFS 0 +#define MVPP22_AXI_CODE_DOMAIN_OFFS 4 + +#define MVPP22_AXI_CODE_CACHE_NON_CACHE 0x3 +#define MVPP22_AXI_CODE_CACHE_WR_CACHE 0x7 +#define MVPP22_AXI_CODE_CACHE_RD_CACHE 0xb + +#define MVPP22_AXI_CODE_DOMAIN_OUTER_DOM 2 +#define MVPP22_AXI_CODE_DOMAIN_SYSTEM 3 + /* Interrupt Cause and Mask registers */ #define MVPP2_ISR_RX_THRESHOLD_REG(rxq) (0x5200 + 4 * (rxq)) #define MVPP2_MAX_ISR_RX_THRESHOLD 0xfffff0 -#define MVPP2_ISR_RXQ_GROUP_REG(rxq) (0x5400 + 4 * (rxq)) +#define MVPP21_ISR_RXQ_GROUP_REG(rxq) (0x5400 + 4 * (rxq)) + +#define MVPP22_ISR_RXQ_GROUP_INDEX_REG 0x5400 +#define MVPP22_ISR_RXQ_GROUP_INDEX_SUBGROUP_MASK 0xf +#define MVPP22_ISR_RXQ_GROUP_INDEX_GROUP_MASK 0x380 +#define MVPP22_ISR_RXQ_GROUP_INDEX_GROUP_OFFSET 7 + +#define MVPP22_ISR_RXQ_GROUP_INDEX_SUBGROUP_MASK 0xf +#define MVPP22_ISR_RXQ_GROUP_INDEX_GROUP_MASK 0x380 + +#define MVPP22_ISR_RXQ_SUB_GROUP_CONFIG_REG 0x5404 +#define MVPP22_ISR_RXQ_SUB_GROUP_STARTQ_MASK 0x1f +#define MVPP22_ISR_RXQ_SUB_GROUP_SIZE_MASK 0xf00 +#define MVPP22_ISR_RXQ_SUB_GROUP_SIZE_OFFSET 8 + #define MVPP2_ISR_ENABLE_REG(port) (0x5420 + 4 * (port)) #define MVPP2_ISR_ENABLE_INTERRUPT(mask) ((mask) & 0xffff) #define MVPP2_ISR_DISABLE_INTERRUPT(mask) (((mask) << 16) & 0xffff0000) @@ -210,14 +254,19 @@ #define MVPP2_BM_PHY_ALLOC_REG(pool) (0x6400 + ((pool) * 4)) #define MVPP2_BM_PHY_ALLOC_GRNTD_MASK BIT(0) #define MVPP2_BM_VIRT_ALLOC_REG 0x6440 +#define MVPP22_BM_ADDR_HIGH_ALLOC 0x6444 +#define MVPP22_BM_ADDR_HIGH_PHYS_MASK 0xff +#define MVPP22_BM_ADDR_HIGH_VIRT_MASK 0xff00 +#define MVPP22_BM_ADDR_HIGH_VIRT_SHIFT 8 #define MVPP2_BM_PHY_RLS_REG(pool) (0x6480 + ((pool) * 4)) #define MVPP2_BM_PHY_RLS_MC_BUFF_MASK BIT(0) #define MVPP2_BM_PHY_RLS_PRIO_EN_MASK BIT(1) #define MVPP2_BM_PHY_RLS_GRNTD_MASK BIT(2) #define MVPP2_BM_VIRT_RLS_REG 0x64c0 -#define MVPP2_BM_MC_RLS_REG 0x64c4 -#define MVPP2_BM_MC_ID_MASK 0xfff -#define MVPP2_BM_FORCE_RELEASE_MASK BIT(12) +#define MVPP22_BM_ADDR_HIGH_RLS_REG 0x64c4 +#define MVPP22_BM_ADDR_HIGH_PHYS_RLS_MASK 0xff +#define MVPP22_BM_ADDR_HIGH_VIRT_RLS_MASK 0xff00 +#define MVPP22_BM_ADDR_HIGH_VIRT_RLS_SHIFT 8 /* TX Scheduler registers */ #define MVPP2_TXP_SCHED_PORT_INDEX_REG 0x8000 @@ -287,6 +336,24 @@ #define MVPP2_GMAC_TX_FIFO_MIN_TH_ALL_MASK 0x1fc0 #define MVPP2_GMAC_TX_FIFO_MIN_TH_MASK(v) (((v) << 6) & \ MVPP2_GMAC_TX_FIFO_MIN_TH_ALL_MASK) +#define MVPP22_GMAC_CTRL_4_REG 0x90 +#define MVPP22_CTRL4_EXT_PIN_GMII_SEL BIT(0) +#define MVPP22_CTRL4_DP_CLK_SEL BIT(5) +#define MVPP22_CTRL4_SYNC_BYPASS BIT(6) +#define MVPP22_CTRL4_QSGMII_BYPASS_ACTIVE BIT(7) + +/* Per-port XGMAC registers. PPv2.2 only, only for GOP port 0, + * relative to port->base. + */ +#define MVPP22_XLG_CTRL3_REG 0x11c +#define MVPP22_XLG_CTRL3_MACMODESELECT_MASK (7 << 13) +#define MVPP22_XLG_CTRL3_MACMODESELECT_GMAC (0 << 13) + +/* SMI registers. PPv2.2 only, relative to priv->iface_base. */ +#define MVPP22_SMI_MISC_CFG_REG 0x1204 +#define MVPP22_SMI_POLLING_EN BIT(10) + +#define MVPP22_GMAC_BASE(port) (0x7000 + (port) * 0x1000 + 0xe00) #define MVPP2_CAUSE_TXQ_SENT_DESC_ALL_MASK 0xff @@ -335,15 +402,9 @@ /* Maximum number of TXQs used by single port */ #define MVPP2_MAX_TXQ 8 -/* Maximum number of RXQs used by single port */ -#define MVPP2_MAX_RXQ 8 - /* Dfault number of RXQs in use */ #define MVPP2_DEFAULT_RXQ 4 -/* Total number of RXQs available to all ports */ -#define MVPP2_RXQ_TOTAL_NUM (MVPP2_MAX_PORTS * MVPP2_MAX_RXQ) - /* Max number of Rx descriptors */ #define MVPP2_MAX_RXD 128 @@ -615,6 +676,11 @@ enum mvpp2_prs_l3_cast { */ #define MVPP2_BM_SHORT_PKT_SIZE MVPP2_RX_MAX_PKT_SIZE(512) +#define MVPP21_ADDR_SPACE_SZ 0 +#define MVPP22_ADDR_SPACE_SZ SZ_64K + +#define MVPP2_MAX_CPUS 4 + enum mvpp2_bm_type { MVPP2_BM_FREE, MVPP2_BM_SWF_LONG, @@ -626,12 +692,19 @@ enum mvpp2_bm_type { /* Shared Packet Processor resources */ struct mvpp2 { /* Shared registers' base addresses */ - void __iomem *base; void __iomem *lms_base; + void __iomem *iface_base; + + /* On PPv2.2, each CPU can access the base register through a + * separate address space, each 64 KB apart from each + * other. + */ + void __iomem *cpu_base[MVPP2_MAX_CPUS]; /* Common clocks */ struct clk *pp_clk; struct clk *gop_clk; + struct clk *mg_clk; /* List of pointers to port structures */ struct mvpp2_port **port_list; @@ -649,6 +722,12 @@ struct mvpp2 { /* Tclk value */ u32 tclk; + + /* HW version */ + enum { MVPP21, MVPP22 } hw_version; + + /* Maximum number of RXQs per port */ + unsigned int max_port_rxqs; }; struct mvpp2_pcpu_stats { @@ -670,6 +749,11 @@ struct mvpp2_port_pcpu { struct mvpp2_port { u8 id; + /* Index of the port from the "group of ports" complex point + * of view + */ + int gop_id; + int irq; struct mvpp2 *priv; @@ -741,22 +825,24 @@ struct mvpp2_port { #define MVPP2_RXD_L3_IP6 BIT(30) #define MVPP2_RXD_BUF_HDR BIT(31) -struct mvpp2_tx_desc { +/* HW TX descriptor for PPv2.1 */ +struct mvpp21_tx_desc { u32 command; /* Options used by HW for packet transmitting.*/ u8 packet_offset; /* the offset from the buffer beginning */ u8 phys_txq; /* destination queue ID */ u16 data_size; /* data size of transmitted packet in bytes */ - u32 buf_phys_addr; /* physical addr of transmitted buffer */ + u32 buf_dma_addr; /* physical addr of transmitted buffer */ u32 buf_cookie; /* cookie for access to TX buffer in tx path */ u32 reserved1[3]; /* hw_cmd (for future use, BM, PON, PNC) */ u32 reserved2; /* reserved (for future use) */ }; -struct mvpp2_rx_desc { +/* HW RX descriptor for PPv2.1 */ +struct mvpp21_rx_desc { u32 status; /* info about received packet */ u16 reserved1; /* parser_info (for future use, PnC) */ u16 data_size; /* size of received packet in bytes */ - u32 buf_phys_addr; /* physical address of the buffer */ + u32 buf_dma_addr; /* physical address of the buffer */ u32 buf_cookie; /* cookie for access to RX buffer in rx path */ u16 reserved2; /* gem_port_id (for future use, PON) */ u16 reserved3; /* csum_l4 (for future use, PnC) */ @@ -767,12 +853,51 @@ struct mvpp2_rx_desc { u32 reserved8; }; +/* HW TX descriptor for PPv2.2 */ +struct mvpp22_tx_desc { + u32 command; + u8 packet_offset; + u8 phys_txq; + u16 data_size; + u64 reserved1; + u64 buf_dma_addr_ptp; + u64 buf_cookie_misc; +}; + +/* HW RX descriptor for PPv2.2 */ +struct mvpp22_rx_desc { + u32 status; + u16 reserved1; + u16 data_size; + u32 reserved2; + u32 reserved3; + u64 buf_dma_addr_key_hash; + u64 buf_cookie_misc; +}; + +/* Opaque type used by the driver to manipulate the HW TX and RX + * descriptors + */ +struct mvpp2_tx_desc { + union { + struct mvpp21_tx_desc pp21; + struct mvpp22_tx_desc pp22; + }; +}; + +struct mvpp2_rx_desc { + union { + struct mvpp21_rx_desc pp21; + struct mvpp22_rx_desc pp22; + }; +}; + struct mvpp2_txq_pcpu_buf { /* Transmitted SKB */ struct sk_buff *skb; /* Physical address of transmitted buffer */ - dma_addr_t phys; + dma_addr_t dma; /* Size transmitted */ size_t size; @@ -825,7 +950,7 @@ struct mvpp2_tx_queue { struct mvpp2_tx_desc *descs; /* DMA address of the Tx DMA descriptors array */ - dma_addr_t descs_phys; + dma_addr_t descs_dma; /* Index of the last Tx DMA descriptor */ int last_desc; @@ -848,7 +973,7 @@ struct mvpp2_rx_queue { struct mvpp2_rx_desc *descs; /* DMA address of the RX DMA descriptors array */ - dma_addr_t descs_phys; + dma_addr_t descs_dma; /* Index of the last RX DMA descriptor */ int last_desc; @@ -912,6 +1037,8 @@ struct mvpp2_bm_pool { /* Buffer Pointers Pool External (BPPE) size */ int size; + /* BPPE size in bytes */ + int size_bytes; /* Number of buffers for this pool */ int buf_num; /* Pool buffer size */ @@ -922,29 +1049,13 @@ struct mvpp2_bm_pool { /* BPPE virtual base address */ u32 *virt_addr; - /* BPPE physical base address */ - dma_addr_t phys_addr; + /* BPPE DMA base address */ + dma_addr_t dma_addr; /* Ports using BM pool */ u32 port_map; }; -struct mvpp2_buff_hdr { - u32 next_buff_phys_addr; - u32 next_buff_virt_addr; - u16 byte_count; - u16 info; - u8 reserved1; /* bm_qset (for future use, BM) */ -}; - -/* Buffer header info bits */ -#define MVPP2_B_HDR_INFO_MC_ID_MASK 0xfff -#define MVPP2_B_HDR_INFO_MC_ID(info) ((info) & MVPP2_B_HDR_INFO_MC_ID_MASK) -#define MVPP2_B_HDR_INFO_LAST_OFFS 12 -#define MVPP2_B_HDR_INFO_LAST_MASK BIT(12) -#define MVPP2_B_HDR_INFO_IS_LAST(info) \ - ((info & MVPP2_B_HDR_INFO_LAST_MASK) >> MVPP2_B_HDR_INFO_LAST_OFFS) - /* Static declaractions */ /* Number of RXQs used by single port */ @@ -959,12 +1070,177 @@ static int txq_number = MVPP2_MAX_TXQ; static void mvpp2_write(struct mvpp2 *priv, u32 offset, u32 data) { - writel(data, priv->base + offset); + writel(data, priv->cpu_base[0] + offset); } static u32 mvpp2_read(struct mvpp2 *priv, u32 offset) { - return readl(priv->base + offset); + return readl(priv->cpu_base[0] + offset); +} + +/* These accessors should be used to access: + * + * - per-CPU registers, where each CPU has its own copy of the + * register. + * + * MVPP2_BM_VIRT_ALLOC_REG + * MVPP2_BM_ADDR_HIGH_ALLOC + * MVPP22_BM_ADDR_HIGH_RLS_REG + * MVPP2_BM_VIRT_RLS_REG + * MVPP2_ISR_RX_TX_CAUSE_REG + * MVPP2_ISR_RX_TX_MASK_REG + * MVPP2_TXQ_NUM_REG + * MVPP2_AGGR_TXQ_UPDATE_REG + * MVPP2_TXQ_RSVD_REQ_REG + * MVPP2_TXQ_RSVD_RSLT_REG + * MVPP2_TXQ_SENT_REG + * MVPP2_RXQ_NUM_REG + * + * - global registers that must be accessed through a specific CPU + * window, because they are related to an access to a per-CPU + * register + * + * MVPP2_BM_PHY_ALLOC_REG (related to MVPP2_BM_VIRT_ALLOC_REG) + * MVPP2_BM_PHY_RLS_REG (related to MVPP2_BM_VIRT_RLS_REG) + * MVPP2_RXQ_THRESH_REG (related to MVPP2_RXQ_NUM_REG) + * MVPP2_RXQ_DESC_ADDR_REG (related to MVPP2_RXQ_NUM_REG) + * MVPP2_RXQ_DESC_SIZE_REG (related to MVPP2_RXQ_NUM_REG) + * MVPP2_RXQ_INDEX_REG (related to MVPP2_RXQ_NUM_REG) + * MVPP2_TXQ_PENDING_REG (related to MVPP2_TXQ_NUM_REG) + * MVPP2_TXQ_DESC_ADDR_REG (related to MVPP2_TXQ_NUM_REG) + * MVPP2_TXQ_DESC_SIZE_REG (related to MVPP2_TXQ_NUM_REG) + * MVPP2_TXQ_INDEX_REG (related to MVPP2_TXQ_NUM_REG) + * MVPP2_TXQ_PENDING_REG (related to MVPP2_TXQ_NUM_REG) + * MVPP2_TXQ_PREF_BUF_REG (related to MVPP2_TXQ_NUM_REG) + * MVPP2_TXQ_PREF_BUF_REG (related to MVPP2_TXQ_NUM_REG) + */ +static void mvpp2_percpu_write(struct mvpp2 *priv, int cpu, + u32 offset, u32 data) +{ + writel(data, priv->cpu_base[cpu] + offset); +} + +static u32 mvpp2_percpu_read(struct mvpp2 *priv, int cpu, + u32 offset) +{ + return readl(priv->cpu_base[cpu] + offset); +} + +static dma_addr_t mvpp2_txdesc_dma_addr_get(struct mvpp2_port *port, + struct mvpp2_tx_desc *tx_desc) +{ + if (port->priv->hw_version == MVPP21) + return tx_desc->pp21.buf_dma_addr; + else + return tx_desc->pp22.buf_dma_addr_ptp & GENMASK_ULL(40, 0); +} + +static void mvpp2_txdesc_dma_addr_set(struct mvpp2_port *port, + struct mvpp2_tx_desc *tx_desc, + dma_addr_t dma_addr) +{ + if (port->priv->hw_version == MVPP21) { + tx_desc->pp21.buf_dma_addr = dma_addr; + } else { + u64 val = (u64)dma_addr; + + tx_desc->pp22.buf_dma_addr_ptp &= ~GENMASK_ULL(40, 0); + tx_desc->pp22.buf_dma_addr_ptp |= val; + } +} + +static size_t mvpp2_txdesc_size_get(struct mvpp2_port *port, + struct mvpp2_tx_desc *tx_desc) +{ + if (port->priv->hw_version == MVPP21) + return tx_desc->pp21.data_size; + else + return tx_desc->pp22.data_size; +} + +static void mvpp2_txdesc_size_set(struct mvpp2_port *port, + struct mvpp2_tx_desc *tx_desc, + size_t size) +{ + if (port->priv->hw_version == MVPP21) + tx_desc->pp21.data_size = size; + else + tx_desc->pp22.data_size = size; +} + +static void mvpp2_txdesc_txq_set(struct mvpp2_port *port, + struct mvpp2_tx_desc *tx_desc, + unsigned int txq) +{ + if (port->priv->hw_version == MVPP21) + tx_desc->pp21.phys_txq = txq; + else + tx_desc->pp22.phys_txq = txq; +} + +static void mvpp2_txdesc_cmd_set(struct mvpp2_port *port, + struct mvpp2_tx_desc *tx_desc, + unsigned int command) +{ + if (port->priv->hw_version == MVPP21) + tx_desc->pp21.command = command; + else + tx_desc->pp22.command = command; +} + +static void mvpp2_txdesc_offset_set(struct mvpp2_port *port, + struct mvpp2_tx_desc *tx_desc, + unsigned int offset) +{ + if (port->priv->hw_version == MVPP21) + tx_desc->pp21.packet_offset = offset; + else + tx_desc->pp22.packet_offset = offset; +} + +static unsigned int mvpp2_txdesc_offset_get(struct mvpp2_port *port, + struct mvpp2_tx_desc *tx_desc) +{ + if (port->priv->hw_version == MVPP21) + return tx_desc->pp21.packet_offset; + else + return tx_desc->pp22.packet_offset; +} + +static dma_addr_t mvpp2_rxdesc_dma_addr_get(struct mvpp2_port *port, + struct mvpp2_rx_desc *rx_desc) +{ + if (port->priv->hw_version == MVPP21) + return rx_desc->pp21.buf_dma_addr; + else + return rx_desc->pp22.buf_dma_addr_key_hash & GENMASK_ULL(40, 0); +} + +static unsigned long mvpp2_rxdesc_cookie_get(struct mvpp2_port *port, + struct mvpp2_rx_desc *rx_desc) +{ + if (port->priv->hw_version == MVPP21) + return rx_desc->pp21.buf_cookie; + else + return rx_desc->pp22.buf_cookie_misc & GENMASK_ULL(40, 0); +} + +static size_t mvpp2_rxdesc_size_get(struct mvpp2_port *port, + struct mvpp2_rx_desc *rx_desc) +{ + if (port->priv->hw_version == MVPP21) + return rx_desc->pp21.data_size; + else + return rx_desc->pp22.data_size; +} + +static u32 mvpp2_rxdesc_status_get(struct mvpp2_port *port, + struct mvpp2_rx_desc *rx_desc) +{ + if (port->priv->hw_version == MVPP21) + return rx_desc->pp21.status; + else + return rx_desc->pp22.status; } static void mvpp2_txq_inc_get(struct mvpp2_txq_pcpu *txq_pcpu) @@ -974,15 +1250,17 @@ static void mvpp2_txq_inc_get(struct mvpp2_txq_pcpu *txq_pcpu) txq_pcpu->txq_get_index = 0; } -static void mvpp2_txq_inc_put(struct mvpp2_txq_pcpu *txq_pcpu, +static void mvpp2_txq_inc_put(struct mvpp2_port *port, + struct mvpp2_txq_pcpu *txq_pcpu, struct sk_buff *skb, struct mvpp2_tx_desc *tx_desc) { struct mvpp2_txq_pcpu_buf *tx_buf = txq_pcpu->buffs + txq_pcpu->txq_put_index; tx_buf->skb = skb; - tx_buf->size = tx_desc->data_size; - tx_buf->phys = tx_desc->buf_phys_addr + tx_desc->packet_offset; + tx_buf->size = mvpp2_txdesc_size_get(port, tx_desc); + tx_buf->dma = mvpp2_txdesc_dma_addr_get(port, tx_desc) + + mvpp2_txdesc_offset_get(port, tx_desc); txq_pcpu->txq_put_index++; if (txq_pcpu->txq_put_index == txq_pcpu->size) txq_pcpu->txq_put_index = 0; @@ -3378,27 +3656,39 @@ static int mvpp2_bm_pool_create(struct platform_device *pdev, struct mvpp2 *priv, struct mvpp2_bm_pool *bm_pool, int size) { - int size_bytes; u32 val; - size_bytes = sizeof(u32) * size; - bm_pool->virt_addr = dma_alloc_coherent(&pdev->dev, size_bytes, - &bm_pool->phys_addr, + /* Number of buffer pointers must be a multiple of 16, as per + * hardware constraints + */ + if (!IS_ALIGNED(size, 16)) + return -EINVAL; + + /* PPv2.1 needs 8 bytes per buffer pointer, PPv2.2 needs 16 + * bytes per buffer pointer + */ + if (priv->hw_version == MVPP21) + bm_pool->size_bytes = 2 * sizeof(u32) * size; + else + bm_pool->size_bytes = 2 * sizeof(u64) * size; + + bm_pool->virt_addr = dma_alloc_coherent(&pdev->dev, bm_pool->size_bytes, + &bm_pool->dma_addr, GFP_KERNEL); if (!bm_pool->virt_addr) return -ENOMEM; if (!IS_ALIGNED((unsigned long)bm_pool->virt_addr, MVPP2_BM_POOL_PTR_ALIGN)) { - dma_free_coherent(&pdev->dev, size_bytes, bm_pool->virt_addr, - bm_pool->phys_addr); + dma_free_coherent(&pdev->dev, bm_pool->size_bytes, + bm_pool->virt_addr, bm_pool->dma_addr); dev_err(&pdev->dev, "BM pool %d is not %d bytes aligned\n", bm_pool->id, MVPP2_BM_POOL_PTR_ALIGN); return -ENOMEM; } mvpp2_write(priv, MVPP2_BM_POOL_BASE_REG(bm_pool->id), - bm_pool->phys_addr); + lower_32_bits(bm_pool->dma_addr)); mvpp2_write(priv, MVPP2_BM_POOL_SIZE_REG(bm_pool->id), size); val = mvpp2_read(priv, MVPP2_BM_POOL_CTRL_REG(bm_pool->id)); @@ -3426,6 +3716,34 @@ static void mvpp2_bm_pool_bufsize_set(struct mvpp2 *priv, mvpp2_write(priv, MVPP2_POOL_BUF_SIZE_REG(bm_pool->id), val); } +static void mvpp2_bm_bufs_get_addrs(struct device *dev, struct mvpp2 *priv, + struct mvpp2_bm_pool *bm_pool, + dma_addr_t *dma_addr, + phys_addr_t *phys_addr) +{ + int cpu = smp_processor_id(); + + *dma_addr = mvpp2_percpu_read(priv, cpu, + MVPP2_BM_PHY_ALLOC_REG(bm_pool->id)); + *phys_addr = mvpp2_percpu_read(priv, cpu, MVPP2_BM_VIRT_ALLOC_REG); + + if (priv->hw_version == MVPP22) { + u32 val; + u32 dma_addr_highbits, phys_addr_highbits; + + val = mvpp2_percpu_read(priv, cpu, MVPP22_BM_ADDR_HIGH_ALLOC); + dma_addr_highbits = (val & MVPP22_BM_ADDR_HIGH_PHYS_MASK); + phys_addr_highbits = (val & MVPP22_BM_ADDR_HIGH_VIRT_MASK) >> + MVPP22_BM_ADDR_HIGH_VIRT_SHIFT; + + if (sizeof(dma_addr_t) == 8) + *dma_addr |= (u64)dma_addr_highbits << 32; + + if (sizeof(phys_addr_t) == 8) + *phys_addr |= (u64)phys_addr_highbits << 32; + } +} + /* Free all buffers from the pool */ static void mvpp2_bm_bufs_free(struct device *dev, struct mvpp2 *priv, struct mvpp2_bm_pool *bm_pool) @@ -3433,21 +3751,21 @@ static void mvpp2_bm_bufs_free(struct device *dev, struct mvpp2 *priv, int i; for (i = 0; i < bm_pool->buf_num; i++) { - dma_addr_t buf_phys_addr; - unsigned long vaddr; + dma_addr_t buf_dma_addr; + phys_addr_t buf_phys_addr; + void *data; - /* Get buffer virtual address (indirect access) */ - buf_phys_addr = mvpp2_read(priv, - MVPP2_BM_PHY_ALLOC_REG(bm_pool->id)); - vaddr = mvpp2_read(priv, MVPP2_BM_VIRT_ALLOC_REG); + mvpp2_bm_bufs_get_addrs(dev, priv, bm_pool, + &buf_dma_addr, &buf_phys_addr); - dma_unmap_single(dev, buf_phys_addr, + dma_unmap_single(dev, buf_dma_addr, bm_pool->buf_size, DMA_FROM_DEVICE); - if (!vaddr) + data = (void *)phys_to_virt(buf_phys_addr); + if (!data) break; - mvpp2_frag_free(bm_pool, (void *)vaddr); + mvpp2_frag_free(bm_pool, data); } /* Update BM driver with number of buffers removed from pool */ @@ -3471,9 +3789,9 @@ static int mvpp2_bm_pool_destroy(struct platform_device *pdev, val |= MVPP2_BM_STOP_MASK; mvpp2_write(priv, MVPP2_BM_POOL_CTRL_REG(bm_pool->id), val); - dma_free_coherent(&pdev->dev, sizeof(u32) * bm_pool->size, + dma_free_coherent(&pdev->dev, bm_pool->size_bytes, bm_pool->virt_addr, - bm_pool->phys_addr); + bm_pool->dma_addr); return 0; } @@ -3529,17 +3847,20 @@ static int mvpp2_bm_init(struct platform_device *pdev, struct mvpp2 *priv) static void mvpp2_rxq_long_pool_set(struct mvpp2_port *port, int lrxq, int long_pool) { - u32 val; + u32 val, mask; int prxq; /* Get queue physical ID */ prxq = port->rxqs[lrxq]->id; - val = mvpp2_read(port->priv, MVPP2_RXQ_CONFIG_REG(prxq)); - val &= ~MVPP2_RXQ_POOL_LONG_MASK; - val |= ((long_pool << MVPP2_RXQ_POOL_LONG_OFFS) & - MVPP2_RXQ_POOL_LONG_MASK); + if (port->priv->hw_version == MVPP21) + mask = MVPP21_RXQ_POOL_LONG_MASK; + else + mask = MVPP22_RXQ_POOL_LONG_MASK; + val = mvpp2_read(port->priv, MVPP2_RXQ_CONFIG_REG(prxq)); + val &= ~mask; + val |= (long_pool << MVPP2_RXQ_POOL_LONG_OFFS) & mask; mvpp2_write(port->priv, MVPP2_RXQ_CONFIG_REG(prxq), val); } @@ -3547,40 +3868,45 @@ static void mvpp2_rxq_long_pool_set(struct mvpp2_port *port, static void mvpp2_rxq_short_pool_set(struct mvpp2_port *port, int lrxq, int short_pool) { - u32 val; + u32 val, mask; int prxq; /* Get queue physical ID */ prxq = port->rxqs[lrxq]->id; - val = mvpp2_read(port->priv, MVPP2_RXQ_CONFIG_REG(prxq)); - val &= ~MVPP2_RXQ_POOL_SHORT_MASK; - val |= ((short_pool << MVPP2_RXQ_POOL_SHORT_OFFS) & - MVPP2_RXQ_POOL_SHORT_MASK); + if (port->priv->hw_version == MVPP21) + mask = MVPP21_RXQ_POOL_SHORT_MASK; + else + mask = MVPP22_RXQ_POOL_SHORT_MASK; + val = mvpp2_read(port->priv, MVPP2_RXQ_CONFIG_REG(prxq)); + val &= ~mask; + val |= (short_pool << MVPP2_RXQ_POOL_SHORT_OFFS) & mask; mvpp2_write(port->priv, MVPP2_RXQ_CONFIG_REG(prxq), val); } static void *mvpp2_buf_alloc(struct mvpp2_port *port, struct mvpp2_bm_pool *bm_pool, - dma_addr_t *buf_phys_addr, + dma_addr_t *buf_dma_addr, + phys_addr_t *buf_phys_addr, gfp_t gfp_mask) { - dma_addr_t phys_addr; + dma_addr_t dma_addr; void *data; data = mvpp2_frag_alloc(bm_pool); if (!data) return NULL; - phys_addr = dma_map_single(port->dev->dev.parent, data, - MVPP2_RX_BUF_SIZE(bm_pool->pkt_size), - DMA_FROM_DEVICE); - if (unlikely(dma_mapping_error(port->dev->dev.parent, phys_addr))) { + dma_addr = dma_map_single(port->dev->dev.parent, data, + MVPP2_RX_BUF_SIZE(bm_pool->pkt_size), + DMA_FROM_DEVICE); + if (unlikely(dma_mapping_error(port->dev->dev.parent, dma_addr))) { mvpp2_frag_free(bm_pool, data); return NULL; } - *buf_phys_addr = phys_addr; + *buf_dma_addr = dma_addr; + *buf_phys_addr = virt_to_phys(data); return data; } @@ -3604,37 +3930,46 @@ static inline int mvpp2_bm_cookie_pool_get(unsigned long cookie) /* Release buffer to BM */ static inline void mvpp2_bm_pool_put(struct mvpp2_port *port, int pool, - dma_addr_t buf_phys_addr, - unsigned long buf_virt_addr) + dma_addr_t buf_dma_addr, + phys_addr_t buf_phys_addr) { - mvpp2_write(port->priv, MVPP2_BM_VIRT_RLS_REG, buf_virt_addr); - mvpp2_write(port->priv, MVPP2_BM_PHY_RLS_REG(pool), buf_phys_addr); -} + int cpu = smp_processor_id(); -/* Release multicast buffer */ -static void mvpp2_bm_pool_mc_put(struct mvpp2_port *port, int pool, - dma_addr_t buf_phys_addr, - unsigned long buf_virt_addr, - int mc_id) -{ - u32 val = 0; + if (port->priv->hw_version == MVPP22) { + u32 val = 0; + + if (sizeof(dma_addr_t) == 8) + val |= upper_32_bits(buf_dma_addr) & + MVPP22_BM_ADDR_HIGH_PHYS_RLS_MASK; + + if (sizeof(phys_addr_t) == 8) + val |= (upper_32_bits(buf_phys_addr) + << MVPP22_BM_ADDR_HIGH_VIRT_RLS_SHIFT) & + MVPP22_BM_ADDR_HIGH_VIRT_RLS_MASK; - val |= (mc_id & MVPP2_BM_MC_ID_MASK); - mvpp2_write(port->priv, MVPP2_BM_MC_RLS_REG, val); + mvpp2_percpu_write(port->priv, cpu, + MVPP22_BM_ADDR_HIGH_RLS_REG, val); + } - mvpp2_bm_pool_put(port, pool, - buf_phys_addr | MVPP2_BM_PHY_RLS_MC_BUFF_MASK, - buf_virt_addr); + /* MVPP2_BM_VIRT_RLS_REG is not interpreted by HW, and simply + * returned in the "cookie" field of the RX + * descriptor. Instead of storing the virtual address, we + * store the physical address + */ + mvpp2_percpu_write(port->priv, cpu, + MVPP2_BM_VIRT_RLS_REG, buf_phys_addr); + mvpp2_percpu_write(port->priv, cpu, + MVPP2_BM_PHY_RLS_REG(pool), buf_dma_addr); } /* Refill BM pool */ static void mvpp2_pool_refill(struct mvpp2_port *port, u32 bm, - dma_addr_t phys_addr, - unsigned long cookie) + dma_addr_t dma_addr, + phys_addr_t phys_addr) { int pool = mvpp2_bm_cookie_pool_get(bm); - mvpp2_bm_pool_put(port, pool, phys_addr, cookie); + mvpp2_bm_pool_put(port, pool, dma_addr, phys_addr); } /* Allocate buffers for the pool */ @@ -3642,7 +3977,8 @@ static int mvpp2_bm_bufs_add(struct mvpp2_port *port, struct mvpp2_bm_pool *bm_pool, int buf_num) { int i, buf_size, total_size; - dma_addr_t phys_addr; + dma_addr_t dma_addr; + phys_addr_t phys_addr; void *buf; buf_size = MVPP2_RX_BUF_SIZE(bm_pool->pkt_size); @@ -3657,12 +3993,13 @@ static int mvpp2_bm_bufs_add(struct mvpp2_port *port, } for (i = 0; i < buf_num; i++) { - buf = mvpp2_buf_alloc(port, bm_pool, &phys_addr, GFP_KERNEL); + buf = mvpp2_buf_alloc(port, bm_pool, &dma_addr, + &phys_addr, GFP_KERNEL); if (!buf) break; - mvpp2_bm_pool_put(port, bm_pool->id, phys_addr, - (unsigned long)buf); + mvpp2_bm_pool_put(port, bm_pool->id, dma_addr, + phys_addr); } /* Update BM driver with number of buffers added to pool */ @@ -3830,7 +4167,8 @@ static void mvpp2_interrupts_mask(void *arg) { struct mvpp2_port *port = arg; - mvpp2_write(port->priv, MVPP2_ISR_RX_TX_MASK_REG(port->id), 0); + mvpp2_percpu_write(port->priv, smp_processor_id(), + MVPP2_ISR_RX_TX_MASK_REG(port->id), 0); } /* Unmask the current CPU's Rx/Tx interrupts */ @@ -3838,17 +4176,46 @@ static void mvpp2_interrupts_unmask(void *arg) { struct mvpp2_port *port = arg; - mvpp2_write(port->priv, MVPP2_ISR_RX_TX_MASK_REG(port->id), - (MVPP2_CAUSE_MISC_SUM_MASK | - MVPP2_CAUSE_RXQ_OCCUP_DESC_ALL_MASK)); + mvpp2_percpu_write(port->priv, smp_processor_id(), + MVPP2_ISR_RX_TX_MASK_REG(port->id), + (MVPP2_CAUSE_MISC_SUM_MASK | + MVPP2_CAUSE_RXQ_OCCUP_DESC_ALL_MASK)); } /* Port configuration routines */ +static void mvpp22_port_mii_set(struct mvpp2_port *port) +{ + u32 val; + + return; + + /* Only GOP port 0 has an XLG MAC */ + if (port->gop_id == 0) { + val = readl(port->base + MVPP22_XLG_CTRL3_REG); + val &= ~MVPP22_XLG_CTRL3_MACMODESELECT_MASK; + val |= MVPP22_XLG_CTRL3_MACMODESELECT_GMAC; + writel(val, port->base + MVPP22_XLG_CTRL3_REG); + } + + val = readl(port->base + MVPP22_GMAC_CTRL_4_REG); + if (port->phy_interface == PHY_INTERFACE_MODE_RGMII) + val |= MVPP22_CTRL4_EXT_PIN_GMII_SEL; + else + val &= ~MVPP22_CTRL4_EXT_PIN_GMII_SEL; + val &= ~MVPP22_CTRL4_DP_CLK_SEL; + val |= MVPP22_CTRL4_SYNC_BYPASS; + val |= MVPP22_CTRL4_QSGMII_BYPASS_ACTIVE; + writel(val, port->base + MVPP22_GMAC_CTRL_4_REG); +} + static void mvpp2_port_mii_set(struct mvpp2_port *port) { u32 val; + if (port->priv->hw_version == MVPP22) + mvpp22_port_mii_set(port); + val = readl(port->base + MVPP2_GMAC_CTRL_2_REG); switch (port->phy_interface) { @@ -3952,16 +4319,18 @@ static void mvpp2_defaults_set(struct mvpp2_port *port) { int tx_port_num, val, queue, ptxq, lrxq; - /* Configure port to loopback if needed */ - if (port->flags & MVPP2_F_LOOPBACK) - mvpp2_port_loopback_set(port); + if (port->priv->hw_version == MVPP21) { + /* Configure port to loopback if needed */ + if (port->flags & MVPP2_F_LOOPBACK) + mvpp2_port_loopback_set(port); - /* Update TX FIFO MIN Threshold */ - val = readl(port->base + MVPP2_GMAC_PORT_FIFO_CFG_1_REG); - val &= ~MVPP2_GMAC_TX_FIFO_MIN_TH_ALL_MASK; - /* Min. TX threshold must be less than minimal packet length */ - val |= MVPP2_GMAC_TX_FIFO_MIN_TH_MASK(64 - 4 - 2); - writel(val, port->base + MVPP2_GMAC_PORT_FIFO_CFG_1_REG); + /* Update TX FIFO MIN Threshold */ + val = readl(port->base + MVPP2_GMAC_PORT_FIFO_CFG_1_REG); + val &= ~MVPP2_GMAC_TX_FIFO_MIN_TH_ALL_MASK; + /* Min. TX threshold must be less than minimal packet length */ + val |= MVPP2_GMAC_TX_FIFO_MIN_TH_MASK(64 - 4 - 2); + writel(val, port->base + MVPP2_GMAC_PORT_FIFO_CFG_1_REG); + } /* Disable Legacy WRR, Disable EJP, Release from reset */ tx_port_num = mvpp2_egress_port(port); @@ -4149,11 +4518,15 @@ static void mvpp2_rxq_offset_set(struct mvpp2_port *port, } /* Obtain BM cookie information from descriptor */ -static u32 mvpp2_bm_cookie_build(struct mvpp2_rx_desc *rx_desc) +static u32 mvpp2_bm_cookie_build(struct mvpp2_port *port, + struct mvpp2_rx_desc *rx_desc) { - int pool = (rx_desc->status & MVPP2_RXD_BM_POOL_ID_MASK) >> - MVPP2_RXD_BM_POOL_ID_OFFS; int cpu = smp_processor_id(); + int pool; + + pool = (mvpp2_rxdesc_status_get(port, rx_desc) & + MVPP2_RXD_BM_POOL_ID_MASK) >> + MVPP2_RXD_BM_POOL_ID_OFFS; return ((pool & 0xFF) << MVPP2_BM_COOKIE_POOL_OFFS) | ((cpu & 0xFF) << MVPP2_BM_COOKIE_CPU_OFFS); @@ -4161,18 +4534,6 @@ static u32 mvpp2_bm_cookie_build(struct mvpp2_rx_desc *rx_desc) /* Tx descriptors helper methods */ -/* Get number of Tx descriptors waiting to be transmitted by HW */ -static int mvpp2_txq_pend_desc_num_get(struct mvpp2_port *port, - struct mvpp2_tx_queue *txq) -{ - u32 val; - - mvpp2_write(port->priv, MVPP2_TXQ_NUM_REG, txq->id); - val = mvpp2_read(port->priv, MVPP2_TXQ_PENDING_REG); - - return val & MVPP2_TXQ_PENDING_MASK; -} - /* Get pointer to next Tx descriptor to be processed (send) by HW */ static struct mvpp2_tx_desc * mvpp2_txq_next_desc_get(struct mvpp2_tx_queue *txq) @@ -4187,7 +4548,8 @@ mvpp2_txq_next_desc_get(struct mvpp2_tx_queue *txq) static void mvpp2_aggr_txq_pend_desc_add(struct mvpp2_port *port, int pending) { /* aggregated access - relevant TXQ number is written in TX desc */ - mvpp2_write(port->priv, MVPP2_AGGR_TXQ_UPDATE_REG, pending); + mvpp2_percpu_write(port->priv, smp_processor_id(), + MVPP2_AGGR_TXQ_UPDATE_REG, pending); } @@ -4216,11 +4578,12 @@ static int mvpp2_txq_alloc_reserved_desc(struct mvpp2 *priv, struct mvpp2_tx_queue *txq, int num) { u32 val; + int cpu = smp_processor_id(); val = (txq->id << MVPP2_TXQ_RSVD_REQ_Q_OFFSET) | num; - mvpp2_write(priv, MVPP2_TXQ_RSVD_REQ_REG, val); + mvpp2_percpu_write(priv, cpu, MVPP2_TXQ_RSVD_REQ_REG, val); - val = mvpp2_read(priv, MVPP2_TXQ_RSVD_RSLT_REG); + val = mvpp2_percpu_read(priv, cpu, MVPP2_TXQ_RSVD_RSLT_REG); return val & MVPP2_TXQ_RSVD_RSLT_MASK; } @@ -4321,7 +4684,8 @@ static inline int mvpp2_txq_sent_desc_proc(struct mvpp2_port *port, u32 val; /* Reading status reg resets transmitted descriptor counter */ - val = mvpp2_read(port->priv, MVPP2_TXQ_SENT_REG(txq->id)); + val = mvpp2_percpu_read(port->priv, smp_processor_id(), + MVPP2_TXQ_SENT_REG(txq->id)); return (val & MVPP2_TRANSMITTED_COUNT_MASK) >> MVPP2_TRANSMITTED_COUNT_OFFSET; @@ -4335,7 +4699,8 @@ static void mvpp2_txq_sent_counter_clear(void *arg) for (queue = 0; queue < txq_number; queue++) { int id = port->txqs[queue]->id; - mvpp2_read(port->priv, MVPP2_TXQ_SENT_REG(id)); + mvpp2_percpu_read(port->priv, smp_processor_id(), + MVPP2_TXQ_SENT_REG(id)); } } @@ -4394,12 +4759,14 @@ static void mvpp2_txp_max_tx_size_set(struct mvpp2_port *port) static void mvpp2_rx_pkts_coal_set(struct mvpp2_port *port, struct mvpp2_rx_queue *rxq) { + int cpu = smp_processor_id(); + if (rxq->pkts_coal > MVPP2_OCCUPIED_THRESH_MASK) rxq->pkts_coal = MVPP2_OCCUPIED_THRESH_MASK; - mvpp2_write(port->priv, MVPP2_RXQ_NUM_REG, rxq->id); - mvpp2_write(port->priv, MVPP2_RXQ_THRESH_REG, - rxq->pkts_coal); + mvpp2_percpu_write(port->priv, cpu, MVPP2_RXQ_NUM_REG, rxq->id); + mvpp2_percpu_write(port->priv, cpu, MVPP2_RXQ_THRESH_REG, + rxq->pkts_coal); } static u32 mvpp2_usec_to_cycles(u32 usec, unsigned long clk_hz) @@ -4449,7 +4816,7 @@ static void mvpp2_txq_bufs_free(struct mvpp2_port *port, struct mvpp2_txq_pcpu_buf *tx_buf = txq_pcpu->buffs + txq_pcpu->txq_get_index; - dma_unmap_single(port->dev->dev.parent, tx_buf->phys, + dma_unmap_single(port->dev->dev.parent, tx_buf->dma, tx_buf->size, DMA_TO_DEVICE); if (tx_buf->skb) dev_kfree_skb_any(tx_buf->skb); @@ -4527,10 +4894,12 @@ static int mvpp2_aggr_txq_init(struct platform_device *pdev, int desc_num, int cpu, struct mvpp2 *priv) { + u32 txq_dma; + /* Allocate memory for TX descriptors */ aggr_txq->descs = dma_alloc_coherent(&pdev->dev, desc_num * MVPP2_DESC_ALIGNED_SIZE, - &aggr_txq->descs_phys, GFP_KERNEL); + &aggr_txq->descs_dma, GFP_KERNEL); if (!aggr_txq->descs) return -ENOMEM; @@ -4540,10 +4909,16 @@ static int mvpp2_aggr_txq_init(struct platform_device *pdev, aggr_txq->next_desc_to_proc = mvpp2_read(priv, MVPP2_AGGR_TXQ_INDEX_REG(cpu)); - /* Set Tx descriptors queue starting address */ - /* indirect access */ - mvpp2_write(priv, MVPP2_AGGR_TXQ_DESC_ADDR_REG(cpu), - aggr_txq->descs_phys); + /* Set Tx descriptors queue starting address indirect + * access + */ + if (priv->hw_version == MVPP21) + txq_dma = aggr_txq->descs_dma; + else + txq_dma = aggr_txq->descs_dma >> + MVPP22_AGGR_TXQ_DESC_ADDR_OFFS; + + mvpp2_write(priv, MVPP2_AGGR_TXQ_DESC_ADDR_REG(cpu), txq_dma); mvpp2_write(priv, MVPP2_AGGR_TXQ_DESC_SIZE_REG(cpu), desc_num); return 0; @@ -4554,12 +4929,15 @@ static int mvpp2_rxq_init(struct mvpp2_port *port, struct mvpp2_rx_queue *rxq) { + u32 rxq_dma; + int cpu; + rxq->size = port->rx_ring_size; /* Allocate memory for RX descriptors */ rxq->descs = dma_alloc_coherent(port->dev->dev.parent, rxq->size * MVPP2_DESC_ALIGNED_SIZE, - &rxq->descs_phys, GFP_KERNEL); + &rxq->descs_dma, GFP_KERNEL); if (!rxq->descs) return -ENOMEM; @@ -4569,10 +4947,15 @@ static int mvpp2_rxq_init(struct mvpp2_port *port, mvpp2_write(port->priv, MVPP2_RXQ_STATUS_REG(rxq->id), 0); /* Set Rx descriptors queue starting address - indirect access */ - mvpp2_write(port->priv, MVPP2_RXQ_NUM_REG, rxq->id); - mvpp2_write(port->priv, MVPP2_RXQ_DESC_ADDR_REG, rxq->descs_phys); - mvpp2_write(port->priv, MVPP2_RXQ_DESC_SIZE_REG, rxq->size); - mvpp2_write(port->priv, MVPP2_RXQ_INDEX_REG, 0); + cpu = smp_processor_id(); + mvpp2_percpu_write(port->priv, cpu, MVPP2_RXQ_NUM_REG, rxq->id); + if (port->priv->hw_version == MVPP21) + rxq_dma = rxq->descs_dma; + else + rxq_dma = rxq->descs_dma >> MVPP22_DESC_ADDR_OFFS; + mvpp2_percpu_write(port->priv, cpu, MVPP2_RXQ_DESC_ADDR_REG, rxq_dma); + mvpp2_percpu_write(port->priv, cpu, MVPP2_RXQ_DESC_SIZE_REG, rxq->size); + mvpp2_percpu_write(port->priv, cpu, MVPP2_RXQ_INDEX_REG, 0); /* Set Offset */ mvpp2_rxq_offset_set(port, rxq->id, NET_SKB_PAD); @@ -4599,10 +4982,11 @@ static void mvpp2_rxq_drop_pkts(struct mvpp2_port *port, for (i = 0; i < rx_received; i++) { struct mvpp2_rx_desc *rx_desc = mvpp2_rxq_next_desc_get(rxq); - u32 bm = mvpp2_bm_cookie_build(rx_desc); + u32 bm = mvpp2_bm_cookie_build(port, rx_desc); - mvpp2_pool_refill(port, bm, rx_desc->buf_phys_addr, - rx_desc->buf_cookie); + mvpp2_pool_refill(port, bm, + mvpp2_rxdesc_dma_addr_get(port, rx_desc), + mvpp2_rxdesc_cookie_get(port, rx_desc)); } mvpp2_rxq_status_update(port, rxq->id, rx_received, rx_received); } @@ -4611,26 +4995,29 @@ static void mvpp2_rxq_drop_pkts(struct mvpp2_port *port, static void mvpp2_rxq_deinit(struct mvpp2_port *port, struct mvpp2_rx_queue *rxq) { + int cpu; + mvpp2_rxq_drop_pkts(port, rxq); if (rxq->descs) dma_free_coherent(port->dev->dev.parent, rxq->size * MVPP2_DESC_ALIGNED_SIZE, rxq->descs, - rxq->descs_phys); + rxq->descs_dma); rxq->descs = NULL; rxq->last_desc = 0; rxq->next_desc_to_proc = 0; - rxq->descs_phys = 0; + rxq->descs_dma = 0; /* Clear Rx descriptors queue starting address and size; * free descriptor number */ mvpp2_write(port->priv, MVPP2_RXQ_STATUS_REG(rxq->id), 0); - mvpp2_write(port->priv, MVPP2_RXQ_NUM_REG, rxq->id); - mvpp2_write(port->priv, MVPP2_RXQ_DESC_ADDR_REG, 0); - mvpp2_write(port->priv, MVPP2_RXQ_DESC_SIZE_REG, 0); + cpu = smp_processor_id(); + mvpp2_percpu_write(port->priv, cpu, MVPP2_RXQ_NUM_REG, rxq->id); + mvpp2_percpu_write(port->priv, cpu, MVPP2_RXQ_DESC_ADDR_REG, 0); + mvpp2_percpu_write(port->priv, cpu, MVPP2_RXQ_DESC_SIZE_REG, 0); } /* Create and initialize a Tx queue */ @@ -4646,23 +5033,25 @@ static int mvpp2_txq_init(struct mvpp2_port *port, /* Allocate memory for Tx descriptors */ txq->descs = dma_alloc_coherent(port->dev->dev.parent, txq->size * MVPP2_DESC_ALIGNED_SIZE, - &txq->descs_phys, GFP_KERNEL); + &txq->descs_dma, GFP_KERNEL); if (!txq->descs) return -ENOMEM; txq->last_desc = txq->size - 1; /* Set Tx descriptors queue starting address - indirect access */ - mvpp2_write(port->priv, MVPP2_TXQ_NUM_REG, txq->id); - mvpp2_write(port->priv, MVPP2_TXQ_DESC_ADDR_REG, txq->descs_phys); - mvpp2_write(port->priv, MVPP2_TXQ_DESC_SIZE_REG, txq->size & - MVPP2_TXQ_DESC_SIZE_MASK); - mvpp2_write(port->priv, MVPP2_TXQ_INDEX_REG, 0); - mvpp2_write(port->priv, MVPP2_TXQ_RSVD_CLR_REG, - txq->id << MVPP2_TXQ_RSVD_CLR_OFFSET); - val = mvpp2_read(port->priv, MVPP2_TXQ_PENDING_REG); + cpu = smp_processor_id(); + mvpp2_percpu_write(port->priv, cpu, MVPP2_TXQ_NUM_REG, txq->id); + mvpp2_percpu_write(port->priv, cpu, MVPP2_TXQ_DESC_ADDR_REG, + txq->descs_dma); + mvpp2_percpu_write(port->priv, cpu, MVPP2_TXQ_DESC_SIZE_REG, + txq->size & MVPP2_TXQ_DESC_SIZE_MASK); + mvpp2_percpu_write(port->priv, cpu, MVPP2_TXQ_INDEX_REG, 0); + mvpp2_percpu_write(port->priv, cpu, MVPP2_TXQ_RSVD_CLR_REG, + txq->id << MVPP2_TXQ_RSVD_CLR_OFFSET); + val = mvpp2_percpu_read(port->priv, cpu, MVPP2_TXQ_PENDING_REG); val &= ~MVPP2_TXQ_PENDING_MASK; - mvpp2_write(port->priv, MVPP2_TXQ_PENDING_REG, val); + mvpp2_percpu_write(port->priv, cpu, MVPP2_TXQ_PENDING_REG, val); /* Calculate base address in prefetch buffer. We reserve 16 descriptors * for each existing TXQ. @@ -4673,9 +5062,9 @@ static int mvpp2_txq_init(struct mvpp2_port *port, desc = (port->id * MVPP2_MAX_TXQ * desc_per_txq) + (txq->log_id * desc_per_txq); - mvpp2_write(port->priv, MVPP2_TXQ_PREF_BUF_REG, - MVPP2_PREF_BUF_PTR(desc) | MVPP2_PREF_BUF_SIZE_16 | - MVPP2_PREF_BUF_THRESH(desc_per_txq/2)); + mvpp2_percpu_write(port->priv, cpu, MVPP2_TXQ_PREF_BUF_REG, + MVPP2_PREF_BUF_PTR(desc) | MVPP2_PREF_BUF_SIZE_16 | + MVPP2_PREF_BUF_THRESH(desc_per_txq / 2)); /* WRR / EJP configuration - indirect access */ tx_port_num = mvpp2_egress_port(port); @@ -4716,7 +5105,7 @@ error: dma_free_coherent(port->dev->dev.parent, txq->size * MVPP2_DESC_ALIGNED_SIZE, - txq->descs, txq->descs_phys); + txq->descs, txq->descs_dma); return -ENOMEM; } @@ -4736,20 +5125,21 @@ static void mvpp2_txq_deinit(struct mvpp2_port *port, if (txq->descs) dma_free_coherent(port->dev->dev.parent, txq->size * MVPP2_DESC_ALIGNED_SIZE, - txq->descs, txq->descs_phys); + txq->descs, txq->descs_dma); txq->descs = NULL; txq->last_desc = 0; txq->next_desc_to_proc = 0; - txq->descs_phys = 0; + txq->descs_dma = 0; /* Set minimum bandwidth for disabled TXQs */ mvpp2_write(port->priv, MVPP2_TXQ_SCHED_TOKEN_CNTR_REG(txq->id), 0); /* Set Tx descriptors queue starting address and size */ - mvpp2_write(port->priv, MVPP2_TXQ_NUM_REG, txq->id); - mvpp2_write(port->priv, MVPP2_TXQ_DESC_ADDR_REG, 0); - mvpp2_write(port->priv, MVPP2_TXQ_DESC_SIZE_REG, 0); + cpu = smp_processor_id(); + mvpp2_percpu_write(port->priv, cpu, MVPP2_TXQ_NUM_REG, txq->id); + mvpp2_percpu_write(port->priv, cpu, MVPP2_TXQ_DESC_ADDR_REG, 0); + mvpp2_percpu_write(port->priv, cpu, MVPP2_TXQ_DESC_SIZE_REG, 0); } /* Cleanup Tx ports */ @@ -4759,10 +5149,11 @@ static void mvpp2_txq_clean(struct mvpp2_port *port, struct mvpp2_tx_queue *txq) int delay, pending, cpu; u32 val; - mvpp2_write(port->priv, MVPP2_TXQ_NUM_REG, txq->id); - val = mvpp2_read(port->priv, MVPP2_TXQ_PREF_BUF_REG); + cpu = smp_processor_id(); + mvpp2_percpu_write(port->priv, cpu, MVPP2_TXQ_NUM_REG, txq->id); + val = mvpp2_percpu_read(port->priv, cpu, MVPP2_TXQ_PREF_BUF_REG); val |= MVPP2_TXQ_DRAIN_EN_MASK; - mvpp2_write(port->priv, MVPP2_TXQ_PREF_BUF_REG, val); + mvpp2_percpu_write(port->priv, cpu, MVPP2_TXQ_PREF_BUF_REG, val); /* The napi queue has been stopped so wait for all packets * to be transmitted. @@ -4778,11 +5169,13 @@ static void mvpp2_txq_clean(struct mvpp2_port *port, struct mvpp2_tx_queue *txq) mdelay(1); delay++; - pending = mvpp2_txq_pend_desc_num_get(port, txq); + pending = mvpp2_percpu_read(port->priv, cpu, + MVPP2_TXQ_PENDING_REG); + pending &= MVPP2_TXQ_PENDING_MASK; } while (pending); val &= ~MVPP2_TXQ_DRAIN_EN_MASK; - mvpp2_write(port->priv, MVPP2_TXQ_PREF_BUF_REG, val); + mvpp2_percpu_write(port->priv, cpu, MVPP2_TXQ_PREF_BUF_REG, val); for_each_present_cpu(cpu) { txq_pcpu = per_cpu_ptr(txq->pcpu, cpu); @@ -4991,20 +5384,21 @@ static enum hrtimer_restart mvpp2_hr_timer_cb(struct hrtimer *timer) static void mvpp2_rx_error(struct mvpp2_port *port, struct mvpp2_rx_desc *rx_desc) { - u32 status = rx_desc->status; + u32 status = mvpp2_rxdesc_status_get(port, rx_desc); + size_t sz = mvpp2_rxdesc_size_get(port, rx_desc); switch (status & MVPP2_RXD_ERR_CODE_MASK) { case MVPP2_RXD_ERR_CRC: - netdev_err(port->dev, "bad rx status %08x (crc error), size=%d\n", - status, rx_desc->data_size); + netdev_err(port->dev, "bad rx status %08x (crc error), size=%zu\n", + status, sz); break; case MVPP2_RXD_ERR_OVERRUN: - netdev_err(port->dev, "bad rx status %08x (overrun error), size=%d\n", - status, rx_desc->data_size); + netdev_err(port->dev, "bad rx status %08x (overrun error), size=%zu\n", + status, sz); break; case MVPP2_RXD_ERR_RESOURCE: - netdev_err(port->dev, "bad rx status %08x (resource error), size=%d\n", - status, rx_desc->data_size); + netdev_err(port->dev, "bad rx status %08x (resource error), size=%zu\n", + status, sz); break; } } @@ -5031,15 +5425,17 @@ static void mvpp2_rx_csum(struct mvpp2_port *port, u32 status, static int mvpp2_rx_refill(struct mvpp2_port *port, struct mvpp2_bm_pool *bm_pool, u32 bm) { - dma_addr_t phys_addr; + dma_addr_t dma_addr; + phys_addr_t phys_addr; void *buf; /* No recycle or too many buffers are in use, so allocate a new skb */ - buf = mvpp2_buf_alloc(port, bm_pool, &phys_addr, GFP_ATOMIC); + buf = mvpp2_buf_alloc(port, bm_pool, &dma_addr, &phys_addr, + GFP_ATOMIC); if (!buf) return -ENOMEM; - mvpp2_pool_refill(port, bm, phys_addr, (unsigned long)buf); + mvpp2_pool_refill(port, bm, dma_addr, phys_addr); return 0; } @@ -5075,43 +5471,6 @@ static u32 mvpp2_skb_tx_csum(struct mvpp2_port *port, struct sk_buff *skb) return MVPP2_TXD_L4_CSUM_NOT | MVPP2_TXD_IP_CSUM_DISABLE; } -static void mvpp2_buff_hdr_rx(struct mvpp2_port *port, - struct mvpp2_rx_desc *rx_desc) -{ - struct mvpp2_buff_hdr *buff_hdr; - struct sk_buff *skb; - u32 rx_status = rx_desc->status; - dma_addr_t buff_phys_addr; - unsigned long buff_virt_addr; - dma_addr_t buff_phys_addr_next; - unsigned long buff_virt_addr_next; - int mc_id; - int pool_id; - - pool_id = (rx_status & MVPP2_RXD_BM_POOL_ID_MASK) >> - MVPP2_RXD_BM_POOL_ID_OFFS; - buff_phys_addr = rx_desc->buf_phys_addr; - buff_virt_addr = rx_desc->buf_cookie; - - do { - skb = (struct sk_buff *)buff_virt_addr; - buff_hdr = (struct mvpp2_buff_hdr *)skb->head; - - mc_id = MVPP2_B_HDR_INFO_MC_ID(buff_hdr->info); - - buff_phys_addr_next = buff_hdr->next_buff_phys_addr; - buff_virt_addr_next = buff_hdr->next_buff_virt_addr; - - /* Release buffer */ - mvpp2_bm_pool_mc_put(port, pool_id, buff_phys_addr, - buff_virt_addr, mc_id); - - buff_phys_addr = buff_phys_addr_next; - buff_virt_addr = buff_virt_addr_next; - - } while (!MVPP2_B_HDR_INFO_IS_LAST(buff_hdr->info)); -} - /* Main rx processing */ static int mvpp2_rx(struct mvpp2_port *port, int rx_todo, struct mvpp2_rx_queue *rxq) @@ -5132,25 +5491,23 @@ static int mvpp2_rx(struct mvpp2_port *port, int rx_todo, struct mvpp2_bm_pool *bm_pool; struct sk_buff *skb; unsigned int frag_size; - dma_addr_t phys_addr; + dma_addr_t dma_addr; + phys_addr_t phys_addr; u32 bm, rx_status; int pool, rx_bytes, err; void *data; rx_done++; - rx_status = rx_desc->status; - rx_bytes = rx_desc->data_size - MVPP2_MH_SIZE; - phys_addr = rx_desc->buf_phys_addr; - data = (void *)(uintptr_t)rx_desc->buf_cookie; - - bm = mvpp2_bm_cookie_build(rx_desc); + rx_status = mvpp2_rxdesc_status_get(port, rx_desc); + rx_bytes = mvpp2_rxdesc_size_get(port, rx_desc); + rx_bytes -= MVPP2_MH_SIZE; + dma_addr = mvpp2_rxdesc_dma_addr_get(port, rx_desc); + phys_addr = mvpp2_rxdesc_cookie_get(port, rx_desc); + data = (void *)phys_to_virt(phys_addr); + + bm = mvpp2_bm_cookie_build(port, rx_desc); pool = mvpp2_bm_cookie_pool_get(bm); bm_pool = &port->priv->bm_pools[pool]; - /* Check if buffer header is used */ - if (rx_status & MVPP2_RXD_BUF_HDR) { - mvpp2_buff_hdr_rx(port, rx_desc); - continue; - } /* In case of an error, release the requested buffer pointer * to the Buffer Manager. This request process is controlled @@ -5162,9 +5519,7 @@ static int mvpp2_rx(struct mvpp2_port *port, int rx_todo, dev->stats.rx_errors++; mvpp2_rx_error(port, rx_desc); /* Return the buffer to the pool */ - - mvpp2_pool_refill(port, bm, rx_desc->buf_phys_addr, - rx_desc->buf_cookie); + mvpp2_pool_refill(port, bm, dma_addr, phys_addr); continue; } @@ -5185,7 +5540,7 @@ static int mvpp2_rx(struct mvpp2_port *port, int rx_todo, goto err_drop_frame; } - dma_unmap_single(dev->dev.parent, phys_addr, + dma_unmap_single(dev->dev.parent, dma_addr, bm_pool->buf_size, DMA_FROM_DEVICE); rcvd_pkts++; @@ -5216,11 +5571,15 @@ static int mvpp2_rx(struct mvpp2_port *port, int rx_todo, } static inline void -tx_desc_unmap_put(struct device *dev, struct mvpp2_tx_queue *txq, +tx_desc_unmap_put(struct mvpp2_port *port, struct mvpp2_tx_queue *txq, struct mvpp2_tx_desc *desc) { - dma_unmap_single(dev, desc->buf_phys_addr, - desc->data_size, DMA_TO_DEVICE); + dma_addr_t buf_dma_addr = + mvpp2_txdesc_dma_addr_get(port, desc); + size_t buf_sz = + mvpp2_txdesc_size_get(port, desc); + dma_unmap_single(port->dev->dev.parent, buf_dma_addr, + buf_sz, DMA_TO_DEVICE); mvpp2_txq_desc_put(txq); } @@ -5232,35 +5591,38 @@ static int mvpp2_tx_frag_process(struct mvpp2_port *port, struct sk_buff *skb, struct mvpp2_txq_pcpu *txq_pcpu = this_cpu_ptr(txq->pcpu); struct mvpp2_tx_desc *tx_desc; int i; - dma_addr_t buf_phys_addr; + dma_addr_t buf_dma_addr; for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; void *addr = page_address(frag->page.p) + frag->page_offset; tx_desc = mvpp2_txq_next_desc_get(aggr_txq); - tx_desc->phys_txq = txq->id; - tx_desc->data_size = frag->size; + mvpp2_txdesc_txq_set(port, tx_desc, txq->id); + mvpp2_txdesc_size_set(port, tx_desc, frag->size); - buf_phys_addr = dma_map_single(port->dev->dev.parent, addr, - tx_desc->data_size, + buf_dma_addr = dma_map_single(port->dev->dev.parent, addr, + frag->size, DMA_TO_DEVICE); - if (dma_mapping_error(port->dev->dev.parent, buf_phys_addr)) { + if (dma_mapping_error(port->dev->dev.parent, buf_dma_addr)) { mvpp2_txq_desc_put(txq); goto error; } - tx_desc->packet_offset = buf_phys_addr & MVPP2_TX_DESC_ALIGN; - tx_desc->buf_phys_addr = buf_phys_addr & (~MVPP2_TX_DESC_ALIGN); + mvpp2_txdesc_offset_set(port, tx_desc, + buf_dma_addr & MVPP2_TX_DESC_ALIGN); + mvpp2_txdesc_dma_addr_set(port, tx_desc, + buf_dma_addr & ~MVPP2_TX_DESC_ALIGN); if (i == (skb_shinfo(skb)->nr_frags - 1)) { /* Last descriptor */ - tx_desc->command = MVPP2_TXD_L_DESC; - mvpp2_txq_inc_put(txq_pcpu, skb, tx_desc); + mvpp2_txdesc_cmd_set(port, tx_desc, + MVPP2_TXD_L_DESC); + mvpp2_txq_inc_put(port, txq_pcpu, skb, tx_desc); } else { /* Descriptor in the middle: Not First, Not Last */ - tx_desc->command = 0; - mvpp2_txq_inc_put(txq_pcpu, NULL, tx_desc); + mvpp2_txdesc_cmd_set(port, tx_desc, 0); + mvpp2_txq_inc_put(port, txq_pcpu, NULL, tx_desc); } } @@ -5272,7 +5634,7 @@ error: */ for (i = i - 1; i >= 0; i--) { tx_desc = txq->descs + i; - tx_desc_unmap_put(port->dev->dev.parent, txq, tx_desc); + tx_desc_unmap_put(port, txq, tx_desc); } return -ENOMEM; @@ -5285,7 +5647,7 @@ static int mvpp2_tx(struct sk_buff *skb, struct net_device *dev) struct mvpp2_tx_queue *txq, *aggr_txq; struct mvpp2_txq_pcpu *txq_pcpu; struct mvpp2_tx_desc *tx_desc; - dma_addr_t buf_phys_addr; + dma_addr_t buf_dma_addr; int frags = 0; u16 txq_id; u32 tx_cmd; @@ -5307,35 +5669,38 @@ static int mvpp2_tx(struct sk_buff *skb, struct net_device *dev) /* Get a descriptor for the first part of the packet */ tx_desc = mvpp2_txq_next_desc_get(aggr_txq); - tx_desc->phys_txq = txq->id; - tx_desc->data_size = skb_headlen(skb); + mvpp2_txdesc_txq_set(port, tx_desc, txq->id); + mvpp2_txdesc_size_set(port, tx_desc, skb_headlen(skb)); - buf_phys_addr = dma_map_single(dev->dev.parent, skb->data, - tx_desc->data_size, DMA_TO_DEVICE); - if (unlikely(dma_mapping_error(dev->dev.parent, buf_phys_addr))) { + buf_dma_addr = dma_map_single(dev->dev.parent, skb->data, + skb_headlen(skb), DMA_TO_DEVICE); + if (unlikely(dma_mapping_error(dev->dev.parent, buf_dma_addr))) { mvpp2_txq_desc_put(txq); frags = 0; goto out; } - tx_desc->packet_offset = buf_phys_addr & MVPP2_TX_DESC_ALIGN; - tx_desc->buf_phys_addr = buf_phys_addr & ~MVPP2_TX_DESC_ALIGN; + + mvpp2_txdesc_offset_set(port, tx_desc, + buf_dma_addr & MVPP2_TX_DESC_ALIGN); + mvpp2_txdesc_dma_addr_set(port, tx_desc, + buf_dma_addr & ~MVPP2_TX_DESC_ALIGN); tx_cmd = mvpp2_skb_tx_csum(port, skb); if (frags == 1) { /* First and Last descriptor */ tx_cmd |= MVPP2_TXD_F_DESC | MVPP2_TXD_L_DESC; - tx_desc->command = tx_cmd; - mvpp2_txq_inc_put(txq_pcpu, skb, tx_desc); + mvpp2_txdesc_cmd_set(port, tx_desc, tx_cmd); + mvpp2_txq_inc_put(port, txq_pcpu, skb, tx_desc); } else { /* First but not Last */ tx_cmd |= MVPP2_TXD_F_DESC | MVPP2_TXD_PADDING_DISABLE; - tx_desc->command = tx_cmd; - mvpp2_txq_inc_put(txq_pcpu, NULL, tx_desc); + mvpp2_txdesc_cmd_set(port, tx_desc, tx_cmd); + mvpp2_txq_inc_put(port, txq_pcpu, NULL, tx_desc); /* Continue with other skb fragments */ if (mvpp2_tx_frag_process(port, skb, aggr_txq, txq)) { - tx_desc_unmap_put(port->dev->dev.parent, txq, tx_desc); + tx_desc_unmap_put(port, txq, tx_desc); frags = 0; goto out; } @@ -5396,6 +5761,7 @@ static int mvpp2_poll(struct napi_struct *napi, int budget) u32 cause_rx_tx, cause_rx, cause_misc; int rx_done = 0; struct mvpp2_port *port = netdev_priv(napi->dev); + int cpu = smp_processor_id(); /* Rx/Tx cause register * @@ -5407,8 +5773,8 @@ static int mvpp2_poll(struct napi_struct *napi, int budget) * * Each CPU has its own Rx/Tx cause register */ - cause_rx_tx = mvpp2_read(port->priv, - MVPP2_ISR_RX_TX_CAUSE_REG(port->id)); + cause_rx_tx = mvpp2_percpu_read(port->priv, cpu, + MVPP2_ISR_RX_TX_CAUSE_REG(port->id)); cause_rx_tx &= ~MVPP2_CAUSE_TXQ_OCCUP_DESC_ALL_MASK; cause_misc = cause_rx_tx & MVPP2_CAUSE_MISC_SUM_MASK; @@ -5417,8 +5783,9 @@ static int mvpp2_poll(struct napi_struct *napi, int budget) /* Clear the cause register */ mvpp2_write(port->priv, MVPP2_ISR_MISC_CAUSE_REG, 0); - mvpp2_write(port->priv, MVPP2_ISR_RX_TX_CAUSE_REG(port->id), - cause_rx_tx & ~MVPP2_CAUSE_MISC_SUM_MASK); + mvpp2_percpu_write(port->priv, cpu, + MVPP2_ISR_RX_TX_CAUSE_REG(port->id), + cause_rx_tx & ~MVPP2_CAUSE_MISC_SUM_MASK); } cause_rx = cause_rx_tx & MVPP2_CAUSE_RXQ_OCCUP_DESC_ALL_MASK; @@ -5530,7 +5897,7 @@ static int mvpp2_check_ringparam_valid(struct net_device *dev, return 0; } -static void mvpp2_get_mac_address(struct mvpp2_port *port, unsigned char *addr) +static void mvpp21_get_mac_address(struct mvpp2_port *port, unsigned char *addr) { u32 mac_addr_l, mac_addr_m, mac_addr_h; @@ -5975,16 +6342,6 @@ static const struct ethtool_ops mvpp2_eth_tool_ops = { .set_link_ksettings = phy_ethtool_set_link_ksettings, }; -/* Driver initialization */ - -static void mvpp2_port_power_up(struct mvpp2_port *port) -{ - mvpp2_port_mii_set(port); - mvpp2_port_periodic_xon_disable(port); - mvpp2_port_fc_adv_enable(port); - mvpp2_port_reset(port); -} - /* Initialize port HW */ static int mvpp2_port_init(struct mvpp2_port *port) { @@ -5993,7 +6350,8 @@ static int mvpp2_port_init(struct mvpp2_port *port) struct mvpp2_txq_pcpu *txq_pcpu; int queue, cpu, err; - if (port->first_rxq + rxq_number > MVPP2_RXQ_TOTAL_NUM) + if (port->first_rxq + rxq_number > + MVPP2_MAX_PORTS * priv->max_port_rxqs) return -EINVAL; /* Disable port */ @@ -6061,7 +6419,18 @@ static int mvpp2_port_init(struct mvpp2_port *port) } /* Configure Rx queue group interrupt for this port */ - mvpp2_write(priv, MVPP2_ISR_RXQ_GROUP_REG(port->id), rxq_number); + if (priv->hw_version == MVPP21) { + mvpp2_write(priv, MVPP21_ISR_RXQ_GROUP_REG(port->id), + rxq_number); + } else { + u32 val; + + val = (port->id << MVPP22_ISR_RXQ_GROUP_INDEX_GROUP_OFFSET); + mvpp2_write(priv, MVPP22_ISR_RXQ_GROUP_INDEX_REG, val); + + val = (rxq_number << MVPP22_ISR_RXQ_SUB_GROUP_SIZE_OFFSET); + mvpp2_write(priv, MVPP22_ISR_RXQ_SUB_GROUP_CONFIG_REG, val); + } /* Create Rx descriptor rings */ for (queue = 0; queue < rxq_number; queue++) { @@ -6103,8 +6472,7 @@ err_free_percpu: /* Ports initialization */ static int mvpp2_port_probe(struct platform_device *pdev, struct device_node *port_node, - struct mvpp2 *priv, - int *next_first_rxq) + struct mvpp2 *priv) { struct device_node *phy_node; struct mvpp2_port *port; @@ -6117,7 +6485,6 @@ static int mvpp2_port_probe(struct platform_device *pdev, u32 id; int features; int phy_mode; - int priv_common_regs_num = 2; int err, i, cpu; dev = alloc_etherdev_mqs(sizeof(struct mvpp2_port), txq_number, @@ -6163,16 +6530,30 @@ static int mvpp2_port_probe(struct platform_device *pdev, port->priv = priv; port->id = id; - port->first_rxq = *next_first_rxq; + if (priv->hw_version == MVPP21) + port->first_rxq = port->id * rxq_number; + else + port->first_rxq = port->id * priv->max_port_rxqs; + port->phy_node = phy_node; port->phy_interface = phy_mode; - res = platform_get_resource(pdev, IORESOURCE_MEM, - priv_common_regs_num + id); - port->base = devm_ioremap_resource(&pdev->dev, res); - if (IS_ERR(port->base)) { - err = PTR_ERR(port->base); - goto err_free_irq; + if (priv->hw_version == MVPP21) { + res = platform_get_resource(pdev, IORESOURCE_MEM, 2 + id); + port->base = devm_ioremap_resource(&pdev->dev, res); + if (IS_ERR(port->base)) { + err = PTR_ERR(port->base); + goto err_free_irq; + } + } else { + if (of_property_read_u32(port_node, "gop-port-id", + &port->gop_id)) { + err = -EINVAL; + dev_err(&pdev->dev, "missing gop-port-id value\n"); + goto err_free_irq; + } + + port->base = priv->iface_base + MVPP22_GMAC_BASE(port->gop_id); } /* Alloc per-cpu stats */ @@ -6187,7 +6568,8 @@ static int mvpp2_port_probe(struct platform_device *pdev, mac_from = "device tree"; ether_addr_copy(dev->dev_addr, dt_mac_addr); } else { - mvpp2_get_mac_address(port, hw_mac_addr); + if (priv->hw_version == MVPP21) + mvpp21_get_mac_address(port, hw_mac_addr); if (is_valid_ether_addr(hw_mac_addr)) { mac_from = "hardware"; ether_addr_copy(dev->dev_addr, hw_mac_addr); @@ -6207,7 +6589,14 @@ static int mvpp2_port_probe(struct platform_device *pdev, dev_err(&pdev->dev, "failed to init port %d\n", id); goto err_free_stats; } - mvpp2_port_power_up(port); + + mvpp2_port_mii_set(port); + mvpp2_port_periodic_xon_disable(port); + + if (priv->hw_version == MVPP21) + mvpp2_port_fc_adv_enable(port); + + mvpp2_port_reset(port); port->pcpu = alloc_percpu(struct mvpp2_port_pcpu); if (!port->pcpu) { @@ -6245,8 +6634,6 @@ static int mvpp2_port_probe(struct platform_device *pdev, } netdev_info(dev, "Using %s mac address %pM\n", mac_from, dev->dev_addr); - /* Increment the first Rx queue number to be used by the next port */ - *next_first_rxq += rxq_number; priv->port_list[id] = port; return 0; @@ -6330,6 +6717,60 @@ static void mvpp2_rx_fifo_init(struct mvpp2 *priv) mvpp2_write(priv, MVPP2_RX_FIFO_INIT_REG, 0x1); } +static void mvpp2_axi_init(struct mvpp2 *priv) +{ + u32 val, rdval, wrval; + + mvpp2_write(priv, MVPP22_BM_ADDR_HIGH_RLS_REG, 0x0); + + /* AXI Bridge Configuration */ + + rdval = MVPP22_AXI_CODE_CACHE_RD_CACHE + << MVPP22_AXI_ATTR_CACHE_OFFS; + rdval |= MVPP22_AXI_CODE_DOMAIN_OUTER_DOM + << MVPP22_AXI_ATTR_DOMAIN_OFFS; + + wrval = MVPP22_AXI_CODE_CACHE_WR_CACHE + << MVPP22_AXI_ATTR_CACHE_OFFS; + wrval |= MVPP22_AXI_CODE_DOMAIN_OUTER_DOM + << MVPP22_AXI_ATTR_DOMAIN_OFFS; + + /* BM */ + mvpp2_write(priv, MVPP22_AXI_BM_WR_ATTR_REG, wrval); + mvpp2_write(priv, MVPP22_AXI_BM_RD_ATTR_REG, rdval); + + /* Descriptors */ + mvpp2_write(priv, MVPP22_AXI_AGGRQ_DESCR_RD_ATTR_REG, rdval); + mvpp2_write(priv, MVPP22_AXI_TXQ_DESCR_WR_ATTR_REG, wrval); + mvpp2_write(priv, MVPP22_AXI_TXQ_DESCR_RD_ATTR_REG, rdval); + mvpp2_write(priv, MVPP22_AXI_RXQ_DESCR_WR_ATTR_REG, wrval); + + /* Buffer Data */ + mvpp2_write(priv, MVPP22_AXI_TX_DATA_RD_ATTR_REG, rdval); + mvpp2_write(priv, MVPP22_AXI_RX_DATA_WR_ATTR_REG, wrval); + + val = MVPP22_AXI_CODE_CACHE_NON_CACHE + << MVPP22_AXI_CODE_CACHE_OFFS; + val |= MVPP22_AXI_CODE_DOMAIN_SYSTEM + << MVPP22_AXI_CODE_DOMAIN_OFFS; + mvpp2_write(priv, MVPP22_AXI_RD_NORMAL_CODE_REG, val); + mvpp2_write(priv, MVPP22_AXI_WR_NORMAL_CODE_REG, val); + + val = MVPP22_AXI_CODE_CACHE_RD_CACHE + << MVPP22_AXI_CODE_CACHE_OFFS; + val |= MVPP22_AXI_CODE_DOMAIN_OUTER_DOM + << MVPP22_AXI_CODE_DOMAIN_OFFS; + + mvpp2_write(priv, MVPP22_AXI_RD_SNOOP_CODE_REG, val); + + val = MVPP22_AXI_CODE_CACHE_WR_CACHE + << MVPP22_AXI_CODE_CACHE_OFFS; + val |= MVPP22_AXI_CODE_DOMAIN_OUTER_DOM + << MVPP22_AXI_CODE_DOMAIN_OFFS; + + mvpp2_write(priv, MVPP22_AXI_WR_SNOOP_CODE_REG, val); +} + /* Initialize network controller common part HW */ static int mvpp2_init(struct platform_device *pdev, struct mvpp2 *priv) { @@ -6338,7 +6779,7 @@ static int mvpp2_init(struct platform_device *pdev, struct mvpp2 *priv) u32 val; /* Checks for hardware constraints */ - if (rxq_number % 4 || (rxq_number > MVPP2_MAX_RXQ) || + if (rxq_number % 4 || (rxq_number > priv->max_port_rxqs) || (txq_number > MVPP2_MAX_TXQ)) { dev_err(&pdev->dev, "invalid queue size parameter\n"); return -EINVAL; @@ -6349,10 +6790,19 @@ static int mvpp2_init(struct platform_device *pdev, struct mvpp2 *priv) if (dram_target_info) mvpp2_conf_mbus_windows(dram_target_info, priv); + if (priv->hw_version == MVPP22) + mvpp2_axi_init(priv); + /* Disable HW PHY polling */ - val = readl(priv->lms_base + MVPP2_PHY_AN_CFG0_REG); - val |= MVPP2_PHY_AN_STOP_SMI0_MASK; - writel(val, priv->lms_base + MVPP2_PHY_AN_CFG0_REG); + if (priv->hw_version == MVPP21) { + val = readl(priv->lms_base + MVPP2_PHY_AN_CFG0_REG); + val |= MVPP2_PHY_AN_STOP_SMI0_MASK; + writel(val, priv->lms_base + MVPP2_PHY_AN_CFG0_REG); + } else { + val = readl(priv->iface_base + MVPP22_SMI_MISC_CFG_REG); + val &= ~MVPP22_SMI_POLLING_EN; + writel(val, priv->iface_base + MVPP22_SMI_MISC_CFG_REG); + } /* Allocate and initialize aggregated TXQs */ priv->aggr_txqs = devm_kcalloc(&pdev->dev, num_present_cpus(), @@ -6374,11 +6824,25 @@ static int mvpp2_init(struct platform_device *pdev, struct mvpp2 *priv) mvpp2_rx_fifo_init(priv); /* Reset Rx queue group interrupt configuration */ - for (i = 0; i < MVPP2_MAX_PORTS; i++) - mvpp2_write(priv, MVPP2_ISR_RXQ_GROUP_REG(i), rxq_number); + for (i = 0; i < MVPP2_MAX_PORTS; i++) { + if (priv->hw_version == MVPP21) { + mvpp2_write(priv, MVPP21_ISR_RXQ_GROUP_REG(i), + rxq_number); + continue; + } else { + u32 val; + + val = (i << MVPP22_ISR_RXQ_GROUP_INDEX_GROUP_OFFSET); + mvpp2_write(priv, MVPP22_ISR_RXQ_GROUP_INDEX_REG, val); - writel(MVPP2_EXT_GLOBAL_CTRL_DEFAULT, - priv->lms_base + MVPP2_MNG_EXTENDED_GLOBAL_CTRL_REG); + val = (rxq_number << MVPP22_ISR_RXQ_SUB_GROUP_SIZE_OFFSET); + mvpp2_write(priv, MVPP22_ISR_RXQ_SUB_GROUP_CONFIG_REG, val); + } + } + + if (priv->hw_version == MVPP21) + writel(MVPP2_EXT_GLOBAL_CTRL_DEFAULT, + priv->lms_base + MVPP2_MNG_EXTENDED_GLOBAL_CTRL_REG); /* Allow cache snoop when transmiting packets */ mvpp2_write(priv, MVPP2_TX_SNOOP_REG, 0x1); @@ -6405,22 +6869,46 @@ static int mvpp2_probe(struct platform_device *pdev) struct device_node *port_node; struct mvpp2 *priv; struct resource *res; - int port_count, first_rxq; + void __iomem *base; + int port_count, cpu; int err; priv = devm_kzalloc(&pdev->dev, sizeof(struct mvpp2), GFP_KERNEL); if (!priv) return -ENOMEM; + priv->hw_version = + (unsigned long)of_device_get_match_data(&pdev->dev); + res = platform_get_resource(pdev, IORESOURCE_MEM, 0); - priv->base = devm_ioremap_resource(&pdev->dev, res); - if (IS_ERR(priv->base)) - return PTR_ERR(priv->base); + base = devm_ioremap_resource(&pdev->dev, res); + if (IS_ERR(base)) + return PTR_ERR(base); + + if (priv->hw_version == MVPP21) { + res = platform_get_resource(pdev, IORESOURCE_MEM, 1); + priv->lms_base = devm_ioremap_resource(&pdev->dev, res); + if (IS_ERR(priv->lms_base)) + return PTR_ERR(priv->lms_base); + } else { + res = platform_get_resource(pdev, IORESOURCE_MEM, 1); + priv->iface_base = devm_ioremap_resource(&pdev->dev, res); + if (IS_ERR(priv->iface_base)) + return PTR_ERR(priv->iface_base); + } + + for_each_present_cpu(cpu) { + u32 addr_space_sz; + + addr_space_sz = (priv->hw_version == MVPP21 ? + MVPP21_ADDR_SPACE_SZ : MVPP22_ADDR_SPACE_SZ); + priv->cpu_base[cpu] = base + cpu * addr_space_sz; + } - res = platform_get_resource(pdev, IORESOURCE_MEM, 1); - priv->lms_base = devm_ioremap_resource(&pdev->dev, res); - if (IS_ERR(priv->lms_base)) - return PTR_ERR(priv->lms_base); + if (priv->hw_version == MVPP21) + priv->max_port_rxqs = 8; + else + priv->max_port_rxqs = 32; priv->pp_clk = devm_clk_get(&pdev->dev, "pp_clk"); if (IS_ERR(priv->pp_clk)) @@ -6438,21 +6926,47 @@ static int mvpp2_probe(struct platform_device *pdev) if (err < 0) goto err_pp_clk; + if (priv->hw_version == MVPP22) { + priv->mg_clk = devm_clk_get(&pdev->dev, "mg_clk"); + if (IS_ERR(priv->mg_clk)) { + err = PTR_ERR(priv->mg_clk); + goto err_gop_clk; + } + + err = clk_prepare_enable(priv->mg_clk); + if (err < 0) + goto err_gop_clk; + } + /* Get system's tclk rate */ priv->tclk = clk_get_rate(priv->pp_clk); + if (priv->hw_version == MVPP22) { + err = dma_set_mask(&pdev->dev, DMA_BIT_MASK(40)); + if (err) + goto err_mg_clk; + /* Sadly, the BM pools all share the same register to + * store the high 32 bits of their address. So they + * must all have the same high 32 bits, which forces + * us to restrict coherent memory to DMA_BIT_MASK(32). + */ + err = dma_set_coherent_mask(&pdev->dev, DMA_BIT_MASK(32)); + if (err) + goto err_mg_clk; + } + /* Initialize network controller */ err = mvpp2_init(pdev, priv); if (err < 0) { dev_err(&pdev->dev, "failed to initialize controller\n"); - goto err_gop_clk; + goto err_mg_clk; } port_count = of_get_available_child_count(dn); if (port_count == 0) { dev_err(&pdev->dev, "no ports enabled\n"); err = -ENODEV; - goto err_gop_clk; + goto err_mg_clk; } priv->port_list = devm_kcalloc(&pdev->dev, port_count, @@ -6460,20 +6974,22 @@ static int mvpp2_probe(struct platform_device *pdev) GFP_KERNEL); if (!priv->port_list) { err = -ENOMEM; - goto err_gop_clk; + goto err_mg_clk; } /* Initialize ports */ - first_rxq = 0; for_each_available_child_of_node(dn, port_node) { - err = mvpp2_port_probe(pdev, port_node, priv, &first_rxq); + err = mvpp2_port_probe(pdev, port_node, priv); if (err < 0) - goto err_gop_clk; + goto err_mg_clk; } platform_set_drvdata(pdev, priv); return 0; +err_mg_clk: + if (priv->hw_version == MVPP22) + clk_disable_unprepare(priv->mg_clk); err_gop_clk: clk_disable_unprepare(priv->gop_clk); err_pp_clk: @@ -6506,9 +7022,10 @@ static int mvpp2_remove(struct platform_device *pdev) dma_free_coherent(&pdev->dev, MVPP2_AGGR_TXQ_SIZE * MVPP2_DESC_ALIGNED_SIZE, aggr_txq->descs, - aggr_txq->descs_phys); + aggr_txq->descs_dma); } + clk_disable_unprepare(priv->mg_clk); clk_disable_unprepare(priv->pp_clk); clk_disable_unprepare(priv->gop_clk); @@ -6516,7 +7033,14 @@ static int mvpp2_remove(struct platform_device *pdev) } static const struct of_device_id mvpp2_match[] = { - { .compatible = "marvell,armada-375-pp2" }, + { + .compatible = "marvell,armada-375-pp2", + .data = (void *)MVPP21, + }, + { + .compatible = "marvell,armada-7k-pp22", + .data = (void *)MVPP22, + }, { } }; MODULE_DEVICE_TABLE(of, mvpp2_match); diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.c b/drivers/net/ethernet/mediatek/mtk_eth_soc.c index 9e757684816d..bf6317eca2f6 100644 --- a/drivers/net/ethernet/mediatek/mtk_eth_soc.c +++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.c @@ -1908,10 +1908,9 @@ static int __init mtk_init(struct net_device *dev) /* If the mac address is invalid, use random mac address */ if (!is_valid_ether_addr(dev->dev_addr)) { - random_ether_addr(dev->dev_addr); + eth_hw_addr_random(dev); dev_err(eth->dev, "generated random MAC address %pM\n", dev->dev_addr); - dev->addr_assign_type = NET_ADDR_RANDOM; } return mtk_phy_connect(dev); diff --git a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c index c4d714fcc7da..ffbcb27c05e5 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c @@ -117,7 +117,7 @@ static const char main_strings[][ETH_GSTRING_LEN] = { /* port statistics */ "tso_packets", "xmit_more", - "queue_stopped", "wake_queue", "tx_timeout", "rx_alloc_failed", + "queue_stopped", "wake_queue", "tx_timeout", "rx_alloc_pages", "rx_csum_good", "rx_csum_none", "rx_csum_complete", "tx_chksum_offload", /* pf statistics */ diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c index 61420473fe5f..94fab20ef146 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c @@ -92,7 +92,9 @@ static int __mlx4_en_setup_tc(struct net_device *dev, u32 handle, __be16 proto, if (tc->type != TC_SETUP_MQPRIO) return -EINVAL; - return mlx4_en_setup_tc(dev, tc->tc); + tc->mqprio->hw = TC_MQPRIO_HW_OFFLOAD_TCS; + + return mlx4_en_setup_tc(dev, tc->mqprio->num_tc); } #ifdef CONFIG_RFS_ACCEL diff --git a/drivers/net/ethernet/mellanox/mlx4/en_port.c b/drivers/net/ethernet/mellanox/mlx4/en_port.c index 9166d90e7328..e0eb695318e6 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_port.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_port.c @@ -213,6 +213,7 @@ int mlx4_en_DUMP_ETH_STATS(struct mlx4_en_dev *mdev, u8 port, u8 reset) priv->port_stats.rx_chksum_good = 0; priv->port_stats.rx_chksum_none = 0; priv->port_stats.rx_chksum_complete = 0; + priv->port_stats.rx_alloc_pages = 0; priv->xdp_stats.rx_xdp_drop = 0; priv->xdp_stats.rx_xdp_tx = 0; priv->xdp_stats.rx_xdp_tx_full = 0; @@ -223,6 +224,7 @@ int mlx4_en_DUMP_ETH_STATS(struct mlx4_en_dev *mdev, u8 port, u8 reset) priv->port_stats.rx_chksum_good += READ_ONCE(ring->csum_ok); priv->port_stats.rx_chksum_none += READ_ONCE(ring->csum_none); priv->port_stats.rx_chksum_complete += READ_ONCE(ring->csum_complete); + priv->port_stats.rx_alloc_pages += READ_ONCE(ring->rx_alloc_pages); priv->xdp_stats.rx_xdp_drop += READ_ONCE(ring->xdp_drop); priv->xdp_stats.rx_xdp_tx += READ_ONCE(ring->xdp_tx); priv->xdp_stats.rx_xdp_tx_full += READ_ONCE(ring->xdp_tx_full); diff --git a/drivers/net/ethernet/mellanox/mlx4/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c index 867292880c07..aa074e57ce06 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_rx.c @@ -50,173 +50,62 @@ #include "mlx4_en.h" -static int mlx4_alloc_pages(struct mlx4_en_priv *priv, - struct mlx4_en_rx_alloc *page_alloc, - const struct mlx4_en_frag_info *frag_info, - gfp_t _gfp) +static int mlx4_alloc_page(struct mlx4_en_priv *priv, + struct mlx4_en_rx_alloc *frag, + gfp_t gfp) { - int order; struct page *page; dma_addr_t dma; - for (order = frag_info->order; ;) { - gfp_t gfp = _gfp; - - if (order) - gfp |= __GFP_COMP | __GFP_NOWARN | __GFP_NOMEMALLOC; - page = alloc_pages(gfp, order); - if (likely(page)) - break; - if (--order < 0 || - ((PAGE_SIZE << order) < frag_info->frag_size)) - return -ENOMEM; - } - dma = dma_map_page(priv->ddev, page, 0, PAGE_SIZE << order, - frag_info->dma_dir); + page = alloc_page(gfp); + if (unlikely(!page)) + return -ENOMEM; + dma = dma_map_page(priv->ddev, page, 0, PAGE_SIZE, priv->dma_dir); if (unlikely(dma_mapping_error(priv->ddev, dma))) { - put_page(page); + __free_page(page); return -ENOMEM; } - page_alloc->page_size = PAGE_SIZE << order; - page_alloc->page = page; - page_alloc->dma = dma; - page_alloc->page_offset = 0; - /* Not doing get_page() for each frag is a big win - * on asymetric workloads. Note we can not use atomic_set(). - */ - page_ref_add(page, page_alloc->page_size / frag_info->frag_stride - 1); + frag->page = page; + frag->dma = dma; + frag->page_offset = priv->rx_headroom; return 0; } static int mlx4_en_alloc_frags(struct mlx4_en_priv *priv, + struct mlx4_en_rx_ring *ring, struct mlx4_en_rx_desc *rx_desc, struct mlx4_en_rx_alloc *frags, - struct mlx4_en_rx_alloc *ring_alloc, gfp_t gfp) { - struct mlx4_en_rx_alloc page_alloc[MLX4_EN_MAX_RX_FRAGS]; - const struct mlx4_en_frag_info *frag_info; - struct page *page; int i; - for (i = 0; i < priv->num_frags; i++) { - frag_info = &priv->frag_info[i]; - page_alloc[i] = ring_alloc[i]; - page_alloc[i].page_offset += frag_info->frag_stride; - - if (page_alloc[i].page_offset + frag_info->frag_stride <= - ring_alloc[i].page_size) - continue; - - if (unlikely(mlx4_alloc_pages(priv, &page_alloc[i], - frag_info, gfp))) - goto out; - } - - for (i = 0; i < priv->num_frags; i++) { - frags[i] = ring_alloc[i]; - frags[i].page_offset += priv->frag_info[i].rx_headroom; - rx_desc->data[i].addr = cpu_to_be64(frags[i].dma + - frags[i].page_offset); - ring_alloc[i] = page_alloc[i]; - } - - return 0; - -out: - while (i--) { - if (page_alloc[i].page != ring_alloc[i].page) { - dma_unmap_page(priv->ddev, page_alloc[i].dma, - page_alloc[i].page_size, - priv->frag_info[i].dma_dir); - page = page_alloc[i].page; - /* Revert changes done by mlx4_alloc_pages */ - page_ref_sub(page, page_alloc[i].page_size / - priv->frag_info[i].frag_stride - 1); - put_page(page); + for (i = 0; i < priv->num_frags; i++, frags++) { + if (!frags->page) { + if (mlx4_alloc_page(priv, frags, gfp)) + return -ENOMEM; + ring->rx_alloc_pages++; } - } - return -ENOMEM; -} - -static void mlx4_en_free_frag(struct mlx4_en_priv *priv, - struct mlx4_en_rx_alloc *frags, - int i) -{ - const struct mlx4_en_frag_info *frag_info = &priv->frag_info[i]; - u32 next_frag_end = frags[i].page_offset + 2 * frag_info->frag_stride; - - - if (next_frag_end > frags[i].page_size) - dma_unmap_page(priv->ddev, frags[i].dma, frags[i].page_size, - frag_info->dma_dir); - - if (frags[i].page) - put_page(frags[i].page); -} - -static int mlx4_en_init_allocator(struct mlx4_en_priv *priv, - struct mlx4_en_rx_ring *ring) -{ - int i; - struct mlx4_en_rx_alloc *page_alloc; - - for (i = 0; i < priv->num_frags; i++) { - const struct mlx4_en_frag_info *frag_info = &priv->frag_info[i]; - - if (mlx4_alloc_pages(priv, &ring->page_alloc[i], - frag_info, GFP_KERNEL | __GFP_COLD)) - goto out; - - en_dbg(DRV, priv, " frag %d allocator: - size:%d frags:%d\n", - i, ring->page_alloc[i].page_size, - page_ref_count(ring->page_alloc[i].page)); + rx_desc->data[i].addr = cpu_to_be64(frags->dma + + frags->page_offset); } return 0; - -out: - while (i--) { - struct page *page; - - page_alloc = &ring->page_alloc[i]; - dma_unmap_page(priv->ddev, page_alloc->dma, - page_alloc->page_size, - priv->frag_info[i].dma_dir); - page = page_alloc->page; - /* Revert changes done by mlx4_alloc_pages */ - page_ref_sub(page, page_alloc->page_size / - priv->frag_info[i].frag_stride - 1); - put_page(page); - page_alloc->page = NULL; - } - return -ENOMEM; } -static void mlx4_en_destroy_allocator(struct mlx4_en_priv *priv, - struct mlx4_en_rx_ring *ring) +static void mlx4_en_free_frag(const struct mlx4_en_priv *priv, + struct mlx4_en_rx_alloc *frag) { - struct mlx4_en_rx_alloc *page_alloc; - int i; - - for (i = 0; i < priv->num_frags; i++) { - const struct mlx4_en_frag_info *frag_info = &priv->frag_info[i]; - - page_alloc = &ring->page_alloc[i]; - en_dbg(DRV, priv, "Freeing allocator:%d count:%d\n", - i, page_count(page_alloc->page)); - - dma_unmap_page(priv->ddev, page_alloc->dma, - page_alloc->page_size, frag_info->dma_dir); - while (page_alloc->page_offset + frag_info->frag_stride < - page_alloc->page_size) { - put_page(page_alloc->page); - page_alloc->page_offset += frag_info->frag_stride; - } - page_alloc->page = NULL; + if (frag->page) { + dma_unmap_page(priv->ddev, frag->dma, + PAGE_SIZE, priv->dma_dir); + __free_page(frag->page); } + /* We need to clear all fields, otherwise a change of priv->log_rx_info + * could lead to see garbage later in frag->page. + */ + memset(frag, 0, sizeof(*frag)); } -static void mlx4_en_init_rx_desc(struct mlx4_en_priv *priv, +static void mlx4_en_init_rx_desc(const struct mlx4_en_priv *priv, struct mlx4_en_rx_ring *ring, int index) { struct mlx4_en_rx_desc *rx_desc = ring->buf + ring->stride * index; @@ -248,18 +137,23 @@ static int mlx4_en_prepare_rx_desc(struct mlx4_en_priv *priv, struct mlx4_en_rx_desc *rx_desc = ring->buf + (index * ring->stride); struct mlx4_en_rx_alloc *frags = ring->rx_info + (index << priv->log_rx_info); - if (ring->page_cache.index > 0) { - frags[0] = ring->page_cache.buf[--ring->page_cache.index]; - rx_desc->data[0].addr = cpu_to_be64(frags[0].dma + - frags[0].page_offset); + /* XDP uses a single page per frame */ + if (!frags->page) { + ring->page_cache.index--; + frags->page = ring->page_cache.buf[ring->page_cache.index].page; + frags->dma = ring->page_cache.buf[ring->page_cache.index].dma; + } + frags->page_offset = XDP_PACKET_HEADROOM; + rx_desc->data[0].addr = cpu_to_be64(frags->dma + + XDP_PACKET_HEADROOM); return 0; } - return mlx4_en_alloc_frags(priv, rx_desc, frags, ring->page_alloc, gfp); + return mlx4_en_alloc_frags(priv, ring, rx_desc, frags, gfp); } -static inline bool mlx4_en_is_ring_empty(struct mlx4_en_rx_ring *ring) +static bool mlx4_en_is_ring_empty(const struct mlx4_en_rx_ring *ring) { return ring->prod == ring->cons; } @@ -269,7 +163,8 @@ static inline void mlx4_en_update_rx_prod_db(struct mlx4_en_rx_ring *ring) *ring->wqres.db.db = cpu_to_be32(ring->prod & 0xffff); } -static void mlx4_en_free_rx_desc(struct mlx4_en_priv *priv, +/* slow path */ +static void mlx4_en_free_rx_desc(const struct mlx4_en_priv *priv, struct mlx4_en_rx_ring *ring, int index) { @@ -279,7 +174,7 @@ static void mlx4_en_free_rx_desc(struct mlx4_en_priv *priv, frags = ring->rx_info + (index << priv->log_rx_info); for (nr = 0; nr < priv->num_frags; nr++) { en_dbg(DRV, priv, "Freeing fragment:%d\n", nr); - mlx4_en_free_frag(priv, frags, nr); + mlx4_en_free_frag(priv, frags + nr); } } @@ -335,12 +230,12 @@ static void mlx4_en_free_rx_buf(struct mlx4_en_priv *priv, ring->cons, ring->prod); /* Unmap and free Rx buffers */ - while (!mlx4_en_is_ring_empty(ring)) { - index = ring->cons & ring->size_mask; + for (index = 0; index < ring->size; index++) { en_dbg(DRV, priv, "Processing descriptor:%d\n", index); mlx4_en_free_rx_desc(priv, ring, index); - ++ring->cons; } + ring->cons = 0; + ring->prod = 0; } void mlx4_en_set_num_rx_rings(struct mlx4_en_dev *mdev) @@ -392,9 +287,9 @@ int mlx4_en_create_rx_ring(struct mlx4_en_priv *priv, tmp = size * roundup_pow_of_two(MLX4_EN_MAX_RX_FRAGS * sizeof(struct mlx4_en_rx_alloc)); - ring->rx_info = vmalloc_node(tmp, node); + ring->rx_info = vzalloc_node(tmp, node); if (!ring->rx_info) { - ring->rx_info = vmalloc(tmp); + ring->rx_info = vzalloc(tmp); if (!ring->rx_info) { err = -ENOMEM; goto err_ring; @@ -464,16 +359,6 @@ int mlx4_en_activate_rx_rings(struct mlx4_en_priv *priv) /* Initialize all descriptors */ for (i = 0; i < ring->size; i++) mlx4_en_init_rx_desc(priv, ring, i); - - /* Initialize page allocators */ - err = mlx4_en_init_allocator(priv, ring); - if (err) { - en_err(priv, "Failed initializing ring allocator\n"); - if (ring->stride <= TXBB_SIZE) - ring->buf -= TXBB_SIZE; - ring_ind--; - goto err_allocator; - } } err = mlx4_en_fill_rx_buffers(priv); if (err) @@ -493,11 +378,9 @@ err_buffers: mlx4_en_free_rx_buf(priv, priv->rx_ring[ring_ind]); ring_ind = priv->rx_ring_num - 1; -err_allocator: while (ring_ind >= 0) { if (priv->rx_ring[ring_ind]->stride <= TXBB_SIZE) priv->rx_ring[ring_ind]->buf -= TXBB_SIZE; - mlx4_en_destroy_allocator(priv, priv->rx_ring[ring_ind]); ring_ind--; } return err; @@ -537,7 +420,9 @@ bool mlx4_en_rx_recycle(struct mlx4_en_rx_ring *ring, if (cache->index >= MLX4_EN_CACHE_SIZE) return false; - cache->buf[cache->index++] = *frame; + cache->buf[cache->index].page = frame->page; + cache->buf[cache->index].dma = frame->dma; + cache->index++; return true; } @@ -567,136 +452,91 @@ void mlx4_en_deactivate_rx_ring(struct mlx4_en_priv *priv, int i; for (i = 0; i < ring->page_cache.index; i++) { - struct mlx4_en_rx_alloc *frame = &ring->page_cache.buf[i]; - - dma_unmap_page(priv->ddev, frame->dma, frame->page_size, - priv->frag_info[0].dma_dir); - put_page(frame->page); + dma_unmap_page(priv->ddev, ring->page_cache.buf[i].dma, + PAGE_SIZE, priv->dma_dir); + put_page(ring->page_cache.buf[i].page); } ring->page_cache.index = 0; mlx4_en_free_rx_buf(priv, ring); if (ring->stride <= TXBB_SIZE) ring->buf -= TXBB_SIZE; - mlx4_en_destroy_allocator(priv, ring); } static int mlx4_en_complete_rx_desc(struct mlx4_en_priv *priv, - struct mlx4_en_rx_desc *rx_desc, struct mlx4_en_rx_alloc *frags, struct sk_buff *skb, int length) { - struct skb_frag_struct *skb_frags_rx = skb_shinfo(skb)->frags; - struct mlx4_en_frag_info *frag_info; - int nr; + const struct mlx4_en_frag_info *frag_info = priv->frag_info; + unsigned int truesize = 0; + int nr, frag_size; + struct page *page; dma_addr_t dma; + bool release; /* Collect used fragments while replacing them in the HW descriptors */ - for (nr = 0; nr < priv->num_frags; nr++) { - frag_info = &priv->frag_info[nr]; - if (length <= frag_info->frag_prefix_size) - break; - if (unlikely(!frags[nr].page)) + for (nr = 0;; frags++) { + frag_size = min_t(int, length, frag_info->frag_size); + + page = frags->page; + if (unlikely(!page)) goto fail; - dma = be64_to_cpu(rx_desc->data[nr].addr); - dma_sync_single_for_cpu(priv->ddev, dma, frag_info->frag_size, - DMA_FROM_DEVICE); + dma = frags->dma; + dma_sync_single_range_for_cpu(priv->ddev, dma, frags->page_offset, + frag_size, priv->dma_dir); + + __skb_fill_page_desc(skb, nr, page, frags->page_offset, + frag_size); - __skb_fill_page_desc(skb, nr, frags[nr].page, - frags[nr].page_offset, - frag_info->frag_size); + truesize += frag_info->frag_stride; + if (frag_info->frag_stride == PAGE_SIZE / 2) { + frags->page_offset ^= PAGE_SIZE / 2; + release = page_count(page) != 1 || + page_is_pfmemalloc(page) || + page_to_nid(page) != numa_mem_id(); + } else { + u32 sz_align = ALIGN(frag_size, SMP_CACHE_BYTES); - skb->truesize += frag_info->frag_stride; - frags[nr].page = NULL; + frags->page_offset += sz_align; + release = frags->page_offset + frag_info->frag_size > PAGE_SIZE; + } + if (release) { + dma_unmap_page(priv->ddev, dma, PAGE_SIZE, priv->dma_dir); + frags->page = NULL; + } else { + page_ref_inc(page); + } + + nr++; + length -= frag_size; + if (!length) + break; + frag_info++; } - /* Adjust size of last fragment to match actual length */ - if (nr > 0) - skb_frag_size_set(&skb_frags_rx[nr - 1], - length - priv->frag_info[nr - 1].frag_prefix_size); + skb->truesize += truesize; return nr; fail: while (nr > 0) { nr--; - __skb_frag_unref(&skb_frags_rx[nr]); + __skb_frag_unref(skb_shinfo(skb)->frags + nr); } return 0; } - -static struct sk_buff *mlx4_en_rx_skb(struct mlx4_en_priv *priv, - struct mlx4_en_rx_desc *rx_desc, - struct mlx4_en_rx_alloc *frags, - unsigned int length) -{ - struct sk_buff *skb; - void *va; - int used_frags; - dma_addr_t dma; - - skb = netdev_alloc_skb(priv->dev, SMALL_PACKET_SIZE + NET_IP_ALIGN); - if (unlikely(!skb)) { - en_dbg(RX_ERR, priv, "Failed allocating skb\n"); - return NULL; - } - skb_reserve(skb, NET_IP_ALIGN); - skb->len = length; - - /* Get pointer to first fragment so we could copy the headers into the - * (linear part of the) skb */ - va = page_address(frags[0].page) + frags[0].page_offset; - - if (length <= SMALL_PACKET_SIZE) { - /* We are copying all relevant data to the skb - temporarily - * sync buffers for the copy */ - dma = be64_to_cpu(rx_desc->data[0].addr); - dma_sync_single_for_cpu(priv->ddev, dma, length, - DMA_FROM_DEVICE); - skb_copy_to_linear_data(skb, va, length); - skb->tail += length; - } else { - unsigned int pull_len; - - /* Move relevant fragments to skb */ - used_frags = mlx4_en_complete_rx_desc(priv, rx_desc, frags, - skb, length); - if (unlikely(!used_frags)) { - kfree_skb(skb); - return NULL; - } - skb_shinfo(skb)->nr_frags = used_frags; - - pull_len = eth_get_headlen(va, SMALL_PACKET_SIZE); - /* Copy headers into the skb linear buffer */ - memcpy(skb->data, va, pull_len); - skb->tail += pull_len; - - /* Skip headers in first fragment */ - skb_shinfo(skb)->frags[0].page_offset += pull_len; - - /* Adjust size of first fragment */ - skb_frag_size_sub(&skb_shinfo(skb)->frags[0], pull_len); - skb->data_len = length - pull_len; - } - return skb; -} - -static void validate_loopback(struct mlx4_en_priv *priv, struct sk_buff *skb) +static void validate_loopback(struct mlx4_en_priv *priv, void *va) { + const unsigned char *data = va + ETH_HLEN; int i; - int offset = ETH_HLEN; - for (i = 0; i < MLX4_LOOPBACK_TEST_PAYLOAD; i++, offset++) { - if (*(skb->data + offset) != (unsigned char) (i & 0xff)) - goto out_loopback; + for (i = 0; i < MLX4_LOOPBACK_TEST_PAYLOAD; i++) { + if (data[i] != (unsigned char)i) + return; } /* Loopback found */ priv->loopback_ok = 1; - -out_loopback: - dev_kfree_skb_any(skb); } static bool mlx4_en_refill_rx_buffers(struct mlx4_en_priv *priv, @@ -801,7 +641,6 @@ int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int bud struct mlx4_cqe *cqe; struct mlx4_en_rx_ring *ring = priv->rx_ring[cq->ring]; struct mlx4_en_rx_alloc *frags; - struct mlx4_en_rx_desc *rx_desc; struct bpf_prog *xdp_prog; int doorbell_pending; struct sk_buff *skb; @@ -834,10 +673,10 @@ int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int bud /* Process all completed CQEs */ while (XNOR(cqe->owner_sr_opcode & MLX4_CQE_OWNER_MASK, cq->mcq.cons_index & cq->size)) { + void *va; frags = ring->rx_info + (index << priv->log_rx_info); - rx_desc = ring->buf + (index << ring->log_stride); - + va = page_address(frags[0].page) + frags[0].page_offset; /* * make sure we read the CQE after we read the ownership bit */ @@ -860,16 +699,14 @@ int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int bud * and not performing the selftest or flb disabled */ if (priv->flags & MLX4_EN_FLAG_RX_FILTER_NEEDED) { - struct ethhdr *ethh; + const struct ethhdr *ethh = va; dma_addr_t dma; /* Get pointer to first fragment since we haven't * skb yet and cast it to ethhdr struct */ - dma = be64_to_cpu(rx_desc->data[0].addr); + dma = frags[0].dma + frags[0].page_offset; dma_sync_single_for_cpu(priv->ddev, dma, sizeof(*ethh), DMA_FROM_DEVICE); - ethh = (struct ethhdr *)(page_address(frags[0].page) + - frags[0].page_offset); if (is_multicast_ether_addr(ethh->h_dest)) { struct mlx4_mac_entry *entry; @@ -887,13 +724,16 @@ int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int bud } } + if (unlikely(priv->validate_loopback)) { + validate_loopback(priv, va); + goto next; + } + /* * Packet is OK - process it. */ length = be32_to_cpu(cqe->byte_cnt); length -= ring->fcs_del; - l2_tunnel = (dev->hw_enc_features & NETIF_F_RXCSUM) && - (cqe->vlan_my_qpn & cpu_to_be32(MLX4_CQE_L2_TUNNEL)); /* A bpf program gets first chance to drop the packet. It may * read bytes but not past the end of the frag. @@ -904,13 +744,13 @@ int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int bud void *orig_data; u32 act; - dma = be64_to_cpu(rx_desc->data[0].addr); + dma = frags[0].dma + frags[0].page_offset; dma_sync_single_for_cpu(priv->ddev, dma, priv->frag_info[0].frag_size, DMA_FROM_DEVICE); - xdp.data_hard_start = page_address(frags[0].page); - xdp.data = xdp.data_hard_start + frags[0].page_offset; + xdp.data_hard_start = va - frags[0].page_offset; + xdp.data = va; xdp.data_end = xdp.data + length; orig_data = xdp.data; @@ -920,6 +760,7 @@ int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int bud length = xdp.data_end - xdp.data; frags[0].page_offset = xdp.data - xdp.data_hard_start; + va = xdp.data; } switch (act) { @@ -928,8 +769,10 @@ int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int bud case XDP_TX: if (likely(!mlx4_en_xmit_frame(ring, frags, dev, length, cq->ring, - &doorbell_pending))) - goto consumed; + &doorbell_pending))) { + frags[0].page = NULL; + goto next; + } trace_xdp_exception(dev, xdp_prog, act); goto xdp_drop_no_cnt; /* Drop on xmit failure */ default: @@ -939,8 +782,6 @@ int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int bud case XDP_DROP: ring->xdp_drop++; xdp_drop_no_cnt: - if (likely(mlx4_en_rx_recycle(ring, frags))) - goto consumed; goto next; } } @@ -948,129 +789,51 @@ xdp_drop_no_cnt: ring->bytes += length; ring->packets++; + skb = napi_get_frags(&cq->napi); + if (!skb) + goto next; + + if (unlikely(ring->hwtstamp_rx_filter == HWTSTAMP_FILTER_ALL)) { + timestamp = mlx4_en_get_cqe_ts(cqe); + mlx4_en_fill_hwtstamps(mdev, skb_hwtstamps(skb), + timestamp); + } + skb_record_rx_queue(skb, cq->ring); + if (likely(dev->features & NETIF_F_RXCSUM)) { if (cqe->status & cpu_to_be16(MLX4_CQE_STATUS_TCP | MLX4_CQE_STATUS_UDP)) { if ((cqe->status & cpu_to_be16(MLX4_CQE_STATUS_IPOK)) && cqe->checksum == cpu_to_be16(0xffff)) { ip_summed = CHECKSUM_UNNECESSARY; + l2_tunnel = (dev->hw_enc_features & NETIF_F_RXCSUM) && + (cqe->vlan_my_qpn & cpu_to_be32(MLX4_CQE_L2_TUNNEL)); + if (l2_tunnel) + skb->csum_level = 1; ring->csum_ok++; } else { - ip_summed = CHECKSUM_NONE; - ring->csum_none++; + goto csum_none; } } else { if (priv->flags & MLX4_EN_FLAG_RX_CSUM_NON_TCP_UDP && (cqe->status & cpu_to_be16(MLX4_CQE_STATUS_IPV4 | MLX4_CQE_STATUS_IPV6))) { - ip_summed = CHECKSUM_COMPLETE; - ring->csum_complete++; + if (check_csum(cqe, skb, va, dev->features)) { + goto csum_none; + } else { + ip_summed = CHECKSUM_COMPLETE; + ring->csum_complete++; + } } else { - ip_summed = CHECKSUM_NONE; - ring->csum_none++; + goto csum_none; } } } else { +csum_none: ip_summed = CHECKSUM_NONE; ring->csum_none++; } - - /* This packet is eligible for GRO if it is: - * - DIX Ethernet (type interpretation) - * - TCP/IP (v4) - * - without IP options - * - not an IP fragment - */ - if (dev->features & NETIF_F_GRO) { - struct sk_buff *gro_skb = napi_get_frags(&cq->napi); - if (!gro_skb) - goto next; - - nr = mlx4_en_complete_rx_desc(priv, - rx_desc, frags, gro_skb, - length); - if (!nr) - goto next; - - if (ip_summed == CHECKSUM_COMPLETE) { - void *va = skb_frag_address(skb_shinfo(gro_skb)->frags); - if (check_csum(cqe, gro_skb, va, - dev->features)) { - ip_summed = CHECKSUM_NONE; - ring->csum_none++; - ring->csum_complete--; - } - } - - skb_shinfo(gro_skb)->nr_frags = nr; - gro_skb->len = length; - gro_skb->data_len = length; - gro_skb->ip_summed = ip_summed; - - if (l2_tunnel && ip_summed == CHECKSUM_UNNECESSARY) - gro_skb->csum_level = 1; - - if ((cqe->vlan_my_qpn & - cpu_to_be32(MLX4_CQE_CVLAN_PRESENT_MASK)) && - (dev->features & NETIF_F_HW_VLAN_CTAG_RX)) { - u16 vid = be16_to_cpu(cqe->sl_vid); - - __vlan_hwaccel_put_tag(gro_skb, htons(ETH_P_8021Q), vid); - } else if ((be32_to_cpu(cqe->vlan_my_qpn) & - MLX4_CQE_SVLAN_PRESENT_MASK) && - (dev->features & NETIF_F_HW_VLAN_STAG_RX)) { - __vlan_hwaccel_put_tag(gro_skb, - htons(ETH_P_8021AD), - be16_to_cpu(cqe->sl_vid)); - } - - if (dev->features & NETIF_F_RXHASH) - skb_set_hash(gro_skb, - be32_to_cpu(cqe->immed_rss_invalid), - (ip_summed == CHECKSUM_UNNECESSARY) ? - PKT_HASH_TYPE_L4 : - PKT_HASH_TYPE_L3); - - skb_record_rx_queue(gro_skb, cq->ring); - - if (ring->hwtstamp_rx_filter == HWTSTAMP_FILTER_ALL) { - timestamp = mlx4_en_get_cqe_ts(cqe); - mlx4_en_fill_hwtstamps(mdev, - skb_hwtstamps(gro_skb), - timestamp); - } - - napi_gro_frags(&cq->napi); - goto next; - } - - /* GRO not possible, complete processing here */ - skb = mlx4_en_rx_skb(priv, rx_desc, frags, length); - if (unlikely(!skb)) { - ring->dropped++; - goto next; - } - - if (unlikely(priv->validate_loopback)) { - validate_loopback(priv, skb); - goto next; - } - - if (ip_summed == CHECKSUM_COMPLETE) { - if (check_csum(cqe, skb, skb->data, dev->features)) { - ip_summed = CHECKSUM_NONE; - ring->csum_complete--; - ring->csum_none++; - } - } - skb->ip_summed = ip_summed; - skb->protocol = eth_type_trans(skb, dev); - skb_record_rx_queue(skb, cq->ring); - - if (l2_tunnel && ip_summed == CHECKSUM_UNNECESSARY) - skb->csum_level = 1; - if (dev->features & NETIF_F_RXHASH) skb_set_hash(skb, be32_to_cpu(cqe->immed_rss_invalid), @@ -1078,36 +841,36 @@ xdp_drop_no_cnt: PKT_HASH_TYPE_L4 : PKT_HASH_TYPE_L3); - if ((be32_to_cpu(cqe->vlan_my_qpn) & - MLX4_CQE_CVLAN_PRESENT_MASK) && + + if ((cqe->vlan_my_qpn & + cpu_to_be32(MLX4_CQE_CVLAN_PRESENT_MASK)) && (dev->features & NETIF_F_HW_VLAN_CTAG_RX)) - __vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), be16_to_cpu(cqe->sl_vid)); - else if ((be32_to_cpu(cqe->vlan_my_qpn) & - MLX4_CQE_SVLAN_PRESENT_MASK) && + __vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), + be16_to_cpu(cqe->sl_vid)); + else if ((cqe->vlan_my_qpn & + cpu_to_be32(MLX4_CQE_SVLAN_PRESENT_MASK)) && (dev->features & NETIF_F_HW_VLAN_STAG_RX)) __vlan_hwaccel_put_tag(skb, htons(ETH_P_8021AD), be16_to_cpu(cqe->sl_vid)); - if (ring->hwtstamp_rx_filter == HWTSTAMP_FILTER_ALL) { - timestamp = mlx4_en_get_cqe_ts(cqe); - mlx4_en_fill_hwtstamps(mdev, skb_hwtstamps(skb), - timestamp); + nr = mlx4_en_complete_rx_desc(priv, frags, skb, length); + if (likely(nr)) { + skb_shinfo(skb)->nr_frags = nr; + skb->len = length; + skb->data_len = length; + napi_gro_frags(&cq->napi); + } else { + skb->vlan_tci = 0; + skb_clear_hash(skb); } - - napi_gro_receive(&cq->napi, skb); next: - for (nr = 0; nr < priv->num_frags; nr++) - mlx4_en_free_frag(priv, frags, nr); - -consumed: ++cq->mcq.cons_index; index = (cq->mcq.cons_index) & ring->size_mask; cqe = mlx4_en_get_cqe(cq->buf, index, priv->cqe_size) + factor; if (++polled == budget) - goto out; + break; } -out: rcu_read_unlock(); if (polled) { @@ -1178,13 +941,6 @@ int mlx4_en_poll_rx_cq(struct napi_struct *napi, int budget) return done; } -static const int frag_sizes[] = { - FRAG_SZ0, - FRAG_SZ1, - FRAG_SZ2, - FRAG_SZ3 -}; - void mlx4_en_calc_rx_buf(struct net_device *dev) { struct mlx4_en_priv *priv = netdev_priv(dev); @@ -1195,33 +951,43 @@ void mlx4_en_calc_rx_buf(struct net_device *dev) * This only works when num_frags == 1. */ if (priv->tx_ring_num[TX_XDP]) { - priv->frag_info[0].order = 0; priv->frag_info[0].frag_size = eff_mtu; - priv->frag_info[0].frag_prefix_size = 0; /* This will gain efficient xdp frame recycling at the * expense of more costly truesize accounting */ priv->frag_info[0].frag_stride = PAGE_SIZE; - priv->frag_info[0].dma_dir = PCI_DMA_BIDIRECTIONAL; - priv->frag_info[0].rx_headroom = XDP_PACKET_HEADROOM; + priv->dma_dir = PCI_DMA_BIDIRECTIONAL; + priv->rx_headroom = XDP_PACKET_HEADROOM; i = 1; } else { - int buf_size = 0; + int frag_size_max = 2048, buf_size = 0; + + /* should not happen, right ? */ + if (eff_mtu > PAGE_SIZE + (MLX4_EN_MAX_RX_FRAGS - 1) * 2048) + frag_size_max = PAGE_SIZE; while (buf_size < eff_mtu) { - priv->frag_info[i].order = MLX4_EN_ALLOC_PREFER_ORDER; - priv->frag_info[i].frag_size = - (eff_mtu > buf_size + frag_sizes[i]) ? - frag_sizes[i] : eff_mtu - buf_size; - priv->frag_info[i].frag_prefix_size = buf_size; - priv->frag_info[i].frag_stride = - ALIGN(priv->frag_info[i].frag_size, - SMP_CACHE_BYTES); - priv->frag_info[i].dma_dir = PCI_DMA_FROMDEVICE; - priv->frag_info[i].rx_headroom = 0; - buf_size += priv->frag_info[i].frag_size; + int frag_stride, frag_size = eff_mtu - buf_size; + int pad, nb; + + if (i < MLX4_EN_MAX_RX_FRAGS - 1) + frag_size = min(frag_size, frag_size_max); + + priv->frag_info[i].frag_size = frag_size; + frag_stride = ALIGN(frag_size, SMP_CACHE_BYTES); + /* We can only pack 2 1536-bytes frames in on 4K page + * Therefore, each frame would consume more bytes (truesize) + */ + nb = PAGE_SIZE / frag_stride; + pad = (PAGE_SIZE - nb * frag_stride) / nb; + pad &= ~(SMP_CACHE_BYTES - 1); + priv->frag_info[i].frag_stride = frag_stride + pad; + + buf_size += frag_size; i++; } + priv->dma_dir = PCI_DMA_FROMDEVICE; + priv->rx_headroom = 0; } priv->num_frags = i; @@ -1232,10 +998,9 @@ void mlx4_en_calc_rx_buf(struct net_device *dev) eff_mtu, priv->num_frags); for (i = 0; i < priv->num_frags; i++) { en_err(priv, - " frag:%d - size:%d prefix:%d stride:%d\n", + " frag:%d - size:%d stride:%d\n", i, priv->frag_info[i].frag_size, - priv->frag_info[i].frag_prefix_size, priv->frag_info[i].frag_stride); } } diff --git a/drivers/net/ethernet/mellanox/mlx4/en_selftest.c b/drivers/net/ethernet/mellanox/mlx4/en_selftest.c index 95290e1fc9fe..17112faafbcc 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_selftest.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_selftest.c @@ -81,14 +81,11 @@ static int mlx4_en_test_loopback(struct mlx4_en_priv *priv) { u32 loopback_ok = 0; int i; - bool gro_enabled; priv->loopback_ok = 0; priv->validate_loopback = 1; - gro_enabled = priv->dev->features & NETIF_F_GRO; mlx4_en_update_loopback_state(priv->dev, priv->dev->features); - priv->dev->features &= ~NETIF_F_GRO; /* xmit */ if (mlx4_en_test_loopback_xmit(priv)) { @@ -111,9 +108,6 @@ mlx4_en_test_loopback_exit: priv->validate_loopback = 0; - if (gro_enabled) - priv->dev->features |= NETIF_F_GRO; - mlx4_en_update_loopback_state(priv->dev, priv->dev->features); return !loopback_ok; } diff --git a/drivers/net/ethernet/mellanox/mlx4/en_tx.c b/drivers/net/ethernet/mellanox/mlx4/en_tx.c index 3ed42199d3f1..e0c5ffb3e3a6 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_tx.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_tx.c @@ -354,13 +354,11 @@ u32 mlx4_en_recycle_tx_desc(struct mlx4_en_priv *priv, struct mlx4_en_rx_alloc frame = { .page = tx_info->page, .dma = tx_info->map0_dma, - .page_offset = XDP_PACKET_HEADROOM, - .page_size = PAGE_SIZE, }; if (!mlx4_en_rx_recycle(ring->recycle_ring, &frame)) { dma_unmap_page(priv->ddev, tx_info->map0_dma, - PAGE_SIZE, priv->frag_info[0].dma_dir); + PAGE_SIZE, priv->dma_dir); put_page(tx_info->page); } diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h index 3629ce11a68b..39f401aa3047 100644 --- a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h +++ b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h @@ -102,17 +102,6 @@ /* Use the maximum between 16384 and a single page */ #define MLX4_EN_ALLOC_SIZE PAGE_ALIGN(16384) -#define MLX4_EN_ALLOC_PREFER_ORDER min_t(int, get_order(32768), \ - PAGE_ALLOC_COSTLY_ORDER) - -/* Receive fragment sizes; we use at most 3 fragments (for 9600 byte MTU - * and 4K allocations) */ -enum { - FRAG_SZ0 = 1536 - NET_IP_ALIGN, - FRAG_SZ1 = 4096, - FRAG_SZ2 = 4096, - FRAG_SZ3 = MLX4_EN_ALLOC_SIZE -}; #define MLX4_EN_MAX_RX_FRAGS 4 /* Maximum ring sizes */ @@ -264,13 +253,16 @@ struct mlx4_en_rx_alloc { struct page *page; dma_addr_t dma; u32 page_offset; - u32 page_size; }; #define MLX4_EN_CACHE_SIZE (2 * NAPI_POLL_WEIGHT) + struct mlx4_en_page_cache { u32 index; - struct mlx4_en_rx_alloc buf[MLX4_EN_CACHE_SIZE]; + struct { + struct page *page; + dma_addr_t dma; + } buf[MLX4_EN_CACHE_SIZE]; }; struct mlx4_en_priv; @@ -335,7 +327,6 @@ struct mlx4_en_rx_desc { struct mlx4_en_rx_ring { struct mlx4_hwq_resources wqres; - struct mlx4_en_rx_alloc page_alloc[MLX4_EN_MAX_RX_FRAGS]; u32 size ; /* number of Rx descs*/ u32 actual_size; u32 size_mask; @@ -355,6 +346,7 @@ struct mlx4_en_rx_ring { unsigned long csum_ok; unsigned long csum_none; unsigned long csum_complete; + unsigned long rx_alloc_pages; unsigned long xdp_drop; unsigned long xdp_tx; unsigned long xdp_tx_full; @@ -472,11 +464,7 @@ struct mlx4_en_mc_list { struct mlx4_en_frag_info { u16 frag_size; - u16 frag_prefix_size; u32 frag_stride; - enum dma_data_direction dma_dir; - u16 order; - u16 rx_headroom; }; #ifdef CONFIG_MLX4_EN_DCB @@ -584,8 +572,10 @@ struct mlx4_en_priv { u32 rx_ring_num; u32 rx_skb_size; struct mlx4_en_frag_info frag_info[MLX4_EN_MAX_RX_FRAGS]; - u16 num_frags; - u16 log_rx_info; + u8 num_frags; + u8 log_rx_info; + u8 dma_dir; + u16 rx_headroom; struct mlx4_en_tx_ring **tx_ring[MLX4_EN_NUM_TX_TYPES]; struct mlx4_en_rx_ring *rx_ring[MAX_RX_RINGS]; diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4_stats.h b/drivers/net/ethernet/mellanox/mlx4/mlx4_stats.h index 48641cb0367f..926f3c3f3665 100644 --- a/drivers/net/ethernet/mellanox/mlx4/mlx4_stats.h +++ b/drivers/net/ethernet/mellanox/mlx4/mlx4_stats.h @@ -37,7 +37,7 @@ struct mlx4_en_port_stats { unsigned long queue_stopped; unsigned long wake_queue; unsigned long tx_timeout; - unsigned long rx_alloc_failed; + unsigned long rx_alloc_pages; unsigned long rx_chksum_good; unsigned long rx_chksum_none; unsigned long rx_chksum_complete; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Kconfig b/drivers/net/ethernet/mellanox/mlx5/core/Kconfig index ddb4ca4ff930..117170014e88 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/Kconfig +++ b/drivers/net/ethernet/mellanox/mlx5/core/Kconfig @@ -14,6 +14,7 @@ config MLX5_CORE config MLX5_CORE_EN bool "Mellanox Technologies ConnectX-4 Ethernet support" depends on NETDEVICES && ETHERNET && PCI && MLX5_CORE + depends on IPV6=y || IPV6=n || MLX5_CORE=m imply PTP_1588_CLOCK default n ---help--- diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c b/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c index 0523ed47f597..8fa23f6a1f67 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c @@ -302,6 +302,9 @@ static u8 mlx5e_dcbnl_setdcbx(struct net_device *dev, u8 mode) struct mlx5e_priv *priv = netdev_priv(dev); struct mlx5e_dcbx *dcbx = &priv->dcbx; + if (mode & DCB_CAP_DCBX_LLD_MANAGED) + return 1; + if ((!mode) && MLX5_CAP_GEN(priv->mdev, dcbx)) { if (dcbx->mode == MLX5E_DCBX_PARAM_VER_OPER_AUTO) return 0; @@ -315,13 +318,10 @@ static u8 mlx5e_dcbnl_setdcbx(struct net_device *dev, u8 mode) return 1; } - if (mlx5e_dcbnl_switch_to_host_mode(netdev_priv(dev))) + if (!(mode & DCB_CAP_DCBX_HOST)) return 1; - if ((mode & DCB_CAP_DCBX_LLD_MANAGED) || - !(mode & DCB_CAP_DCBX_VER_CEE) || - !(mode & DCB_CAP_DCBX_VER_IEEE) || - !(mode & DCB_CAP_DCBX_HOST)) + if (mlx5e_dcbnl_switch_to_host_mode(netdev_priv(dev))) return 1; return 0; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index 8ef64c4db2c2..f96a73ea8e0b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -2737,7 +2737,9 @@ mqprio: if (tc->type != TC_SETUP_MQPRIO) return -EINVAL; - return mlx5e_setup_tc(dev, tc->tc); + tc->mqprio->hw = TC_MQPRIO_HW_OFFLOAD_TCS; + + return mlx5e_setup_tc(dev, tc->mqprio->num_tc); } static void diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_selftest.c b/drivers/net/ethernet/mellanox/mlx5/core/en_selftest.c index 31e3cb7ee5fe..5621dcfda4f1 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_selftest.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_selftest.c @@ -204,9 +204,6 @@ mlx5e_test_loopback_validate(struct sk_buff *skb, struct iphdr *iph; /* We are only going to peek, no need to clone the SKB */ - if (skb->protocol != htons(ETH_P_IP)) - goto out; - if (MLX5E_TEST_PKT_SIZE - ETH_HLEN > skb_headlen(skb)) goto out; @@ -249,7 +246,7 @@ static int mlx5e_test_loopback_setup(struct mlx5e_priv *priv, lbtp->loopback_ok = false; init_completion(&lbtp->comp); - lbtp->pt.type = htons(ETH_P_ALL); + lbtp->pt.type = htons(ETH_P_IP); lbtp->pt.func = mlx5e_test_loopback_validate; lbtp->pt.dev = priv->netdev; lbtp->pt.af_packet_priv = lbtp; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index 44406a5ec15d..79481f4cf264 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -48,9 +48,14 @@ #include "eswitch.h" #include "vxlan.h" +enum { + MLX5E_TC_FLOW_ESWITCH = BIT(0), +}; + struct mlx5e_tc_flow { struct rhash_head node; u64 cookie; + u8 flags; struct mlx5_flow_handle *rule; struct list_head encap; /* flows sharing the same encap */ struct mlx5_esw_flow_attr *attr; @@ -177,7 +182,7 @@ static void mlx5e_tc_del_flow(struct mlx5e_priv *priv, mlx5_fc_destroy(priv->mdev, counter); } - if (esw && esw->mode == SRIOV_OFFLOADS) { + if (flow->flags & MLX5E_TC_FLOW_ESWITCH) { mlx5_eswitch_del_vlan_action(esw, flow->attr); if (flow->attr->action & MLX5_FLOW_CONTEXT_ACTION_ENCAP) mlx5e_detach_encap(priv, flow); @@ -598,6 +603,7 @@ static int __parse_cls_flower(struct mlx5e_priv *priv, } static int parse_cls_flower(struct mlx5e_priv *priv, + struct mlx5e_tc_flow *flow, struct mlx5_flow_spec *spec, struct tc_cls_flower_offload *f) { @@ -609,7 +615,7 @@ static int parse_cls_flower(struct mlx5e_priv *priv, err = __parse_cls_flower(priv, spec, f, &min_inline); - if (!err && esw->mode == SRIOV_OFFLOADS && + if (!err && (flow->flags & MLX5E_TC_FLOW_ESWITCH) && rep->vport != FDB_UPLINK_VPORT) { if (min_inline > esw->offloads.inline_mode) { netdev_warn(priv->netdev, @@ -1132,23 +1138,19 @@ int mlx5e_configure_flower(struct mlx5e_priv *priv, __be16 protocol, struct tc_cls_flower_offload *f) { struct mlx5e_tc_table *tc = &priv->fs.tc; - int err = 0; - bool fdb_flow = false; + int err, attr_size = 0; u32 flow_tag, action; struct mlx5e_tc_flow *flow; struct mlx5_flow_spec *spec; struct mlx5_eswitch *esw = priv->mdev->priv.eswitch; + u8 flow_flags = 0; - if (esw && esw->mode == SRIOV_OFFLOADS) - fdb_flow = true; - - if (fdb_flow) - flow = kzalloc(sizeof(*flow) + - sizeof(struct mlx5_esw_flow_attr), - GFP_KERNEL); - else - flow = kzalloc(sizeof(*flow), GFP_KERNEL); + if (esw && esw->mode == SRIOV_OFFLOADS) { + flow_flags = MLX5E_TC_FLOW_ESWITCH; + attr_size = sizeof(struct mlx5_esw_flow_attr); + } + flow = kzalloc(sizeof(*flow) + attr_size, GFP_KERNEL); spec = mlx5_vzalloc(sizeof(*spec)); if (!spec || !flow) { err = -ENOMEM; @@ -1156,12 +1158,13 @@ int mlx5e_configure_flower(struct mlx5e_priv *priv, __be16 protocol, } flow->cookie = f->cookie; + flow->flags = flow_flags; - err = parse_cls_flower(priv, spec, f); + err = parse_cls_flower(priv, flow, spec, f); if (err < 0) goto err_free; - if (fdb_flow) { + if (flow->flags & MLX5E_TC_FLOW_ESWITCH) { flow->attr = (struct mlx5_esw_flow_attr *)(flow + 1); err = parse_tc_fdb_actions(priv, f->exts, flow); if (err < 0) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c index 2478516a61e2..ded27bb9a3b6 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c @@ -1136,7 +1136,7 @@ static struct mlx5_flow_group *create_autogroup(struct mlx5_flow_table *ft, u32 *match_criteria) { int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in); - struct list_head *prev = ft->node.children.prev; + struct list_head *prev = &ft->node.children; unsigned int candidate_index = 0; struct mlx5_flow_group *fg; void *match_criteria_addr; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index c4242a4e8130..e2bd600d19de 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -1352,6 +1352,7 @@ static int init_one(struct pci_dev *pdev, if (err) goto clean_load; + pci_save_state(pdev); return 0; clean_load: @@ -1407,9 +1408,8 @@ static pci_ers_result_t mlx5_pci_err_detected(struct pci_dev *pdev, mlx5_enter_error_state(dev); mlx5_unload_one(dev, priv, false); - /* In case of kernel call save the pci state and drain the health wq */ + /* In case of kernel call drain the health wq */ if (state) { - pci_save_state(pdev); mlx5_drain_health_wq(dev); mlx5_pci_disable_device(dev); } @@ -1461,6 +1461,7 @@ static pci_ers_result_t mlx5_pci_slot_reset(struct pci_dev *pdev) pci_set_master(pdev); pci_restore_state(pdev); + pci_save_state(pdev); if (wait_vital(pdev)) { dev_err(&pdev->dev, "%s: wait_vital timed out\n", __func__); diff --git a/drivers/net/ethernet/mellanox/mlxsw/Makefile b/drivers/net/ethernet/mellanox/mlxsw/Makefile index 6b6c30deee83..95fcacf9c8be 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/Makefile +++ b/drivers/net/ethernet/mellanox/mlxsw/Makefile @@ -15,7 +15,8 @@ obj-$(CONFIG_MLXSW_SPECTRUM) += mlxsw_spectrum.o mlxsw_spectrum-objs := spectrum.o spectrum_buffers.o \ spectrum_switchdev.o spectrum_router.o \ spectrum_kvdl.o spectrum_acl_tcam.o \ - spectrum_acl.o spectrum_flower.o + spectrum_acl.o spectrum_flower.o \ + spectrum_cnt.o mlxsw_spectrum-$(CONFIG_MLXSW_SPECTRUM_DCB) += spectrum_dcb.o obj-$(CONFIG_MLXSW_MINIMAL) += mlxsw_minimal.o mlxsw_minimal-objs := minimal.o diff --git a/drivers/net/ethernet/mellanox/mlxsw/cmd.h b/drivers/net/ethernet/mellanox/mlxsw/cmd.h index a1b48421648a..479511cf79bc 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/cmd.h +++ b/drivers/net/ethernet/mellanox/mlxsw/cmd.h @@ -1043,13 +1043,6 @@ MLXSW_ITEM32(cmd_mbox, sw2hw_cq, cv, 0x00, 28, 4); */ MLXSW_ITEM32(cmd_mbox, sw2hw_cq, c_eqn, 0x00, 24, 1); -/* cmd_mbox_sw2hw_cq_oi - * When set, overrun ignore is enabled. When set, updates of - * CQ consumer counter (poll for completion) or Request completion - * notifications (Arm CQ) DoorBells should not be rung on that CQ. - */ -MLXSW_ITEM32(cmd_mbox, sw2hw_cq, oi, 0x00, 12, 1); - /* cmd_mbox_sw2hw_cq_st * Event delivery state machine * 0x0 - FIRED @@ -1132,11 +1125,6 @@ static inline int mlxsw_cmd_sw2hw_eq(struct mlxsw_core *mlxsw_core, */ MLXSW_ITEM32(cmd_mbox, sw2hw_eq, int_msix, 0x00, 24, 1); -/* cmd_mbox_sw2hw_eq_oi - * When set, overrun ignore is enabled. - */ -MLXSW_ITEM32(cmd_mbox, sw2hw_eq, oi, 0x00, 12, 1); - /* cmd_mbox_sw2hw_eq_st * Event delivery state machine * 0x0 - FIRED diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.c b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.c index 5f337715a4da..a984c361926c 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.c +++ b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.c @@ -567,6 +567,89 @@ static char *mlxsw_afa_block_append_action(struct mlxsw_afa_block *block, return oneact + MLXSW_AFA_PAYLOAD_OFFSET; } +/* VLAN Action + * ----------- + * VLAN action is used for manipulating VLANs. It can be used to implement QinQ, + * VLAN translation, change of PCP bits of the VLAN tag, push, pop as swap VLANs + * and more. + */ + +#define MLXSW_AFA_VLAN_CODE 0x02 +#define MLXSW_AFA_VLAN_SIZE 1 + +enum mlxsw_afa_vlan_vlan_tag_cmd { + MLXSW_AFA_VLAN_VLAN_TAG_CMD_NOP, + MLXSW_AFA_VLAN_VLAN_TAG_CMD_PUSH_TAG, + MLXSW_AFA_VLAN_VLAN_TAG_CMD_POP_TAG, +}; + +enum mlxsw_afa_vlan_cmd { + MLXSW_AFA_VLAN_CMD_NOP, + MLXSW_AFA_VLAN_CMD_SET_OUTER, + MLXSW_AFA_VLAN_CMD_SET_INNER, + MLXSW_AFA_VLAN_CMD_COPY_OUTER_TO_INNER, + MLXSW_AFA_VLAN_CMD_COPY_INNER_TO_OUTER, + MLXSW_AFA_VLAN_CMD_SWAP, +}; + +/* afa_vlan_vlan_tag_cmd + * Tag command: push, pop, nop VLAN header. + */ +MLXSW_ITEM32(afa, vlan, vlan_tag_cmd, 0x00, 29, 3); + +/* afa_vlan_vid_cmd */ +MLXSW_ITEM32(afa, vlan, vid_cmd, 0x04, 29, 3); + +/* afa_vlan_vid */ +MLXSW_ITEM32(afa, vlan, vid, 0x04, 0, 12); + +/* afa_vlan_ethertype_cmd */ +MLXSW_ITEM32(afa, vlan, ethertype_cmd, 0x08, 29, 3); + +/* afa_vlan_ethertype + * Index to EtherTypes in Switch VLAN EtherType Register (SVER). + */ +MLXSW_ITEM32(afa, vlan, ethertype, 0x08, 24, 3); + +/* afa_vlan_pcp_cmd */ +MLXSW_ITEM32(afa, vlan, pcp_cmd, 0x08, 13, 3); + +/* afa_vlan_pcp */ +MLXSW_ITEM32(afa, vlan, pcp, 0x08, 8, 3); + +static inline void +mlxsw_afa_vlan_pack(char *payload, + enum mlxsw_afa_vlan_vlan_tag_cmd vlan_tag_cmd, + enum mlxsw_afa_vlan_cmd vid_cmd, u16 vid, + enum mlxsw_afa_vlan_cmd pcp_cmd, u8 pcp, + enum mlxsw_afa_vlan_cmd ethertype_cmd, u8 ethertype) +{ + mlxsw_afa_vlan_vlan_tag_cmd_set(payload, vlan_tag_cmd); + mlxsw_afa_vlan_vid_cmd_set(payload, vid_cmd); + mlxsw_afa_vlan_vid_set(payload, vid); + mlxsw_afa_vlan_pcp_cmd_set(payload, pcp_cmd); + mlxsw_afa_vlan_pcp_set(payload, pcp); + mlxsw_afa_vlan_ethertype_cmd_set(payload, ethertype_cmd); + mlxsw_afa_vlan_ethertype_set(payload, ethertype); +} + +int mlxsw_afa_block_append_vlan_modify(struct mlxsw_afa_block *block, + u16 vid, u8 pcp, u8 et) +{ + char *act = mlxsw_afa_block_append_action(block, + MLXSW_AFA_VLAN_CODE, + MLXSW_AFA_VLAN_SIZE); + + if (!act) + return -ENOBUFS; + mlxsw_afa_vlan_pack(act, MLXSW_AFA_VLAN_VLAN_TAG_CMD_NOP, + MLXSW_AFA_VLAN_CMD_SET_OUTER, vid, + MLXSW_AFA_VLAN_CMD_SET_OUTER, pcp, + MLXSW_AFA_VLAN_CMD_SET_OUTER, et); + return 0; +} +EXPORT_SYMBOL(mlxsw_afa_block_append_vlan_modify); + /* Trap / Discard Action * --------------------- * The Trap / Discard action enables trapping / mirroring packets to the CPU @@ -677,3 +760,54 @@ err_append_action: return err; } EXPORT_SYMBOL(mlxsw_afa_block_append_fwd); + +/* Policing and Counting Action + * ---------------------------- + * Policing and Counting action is used for binding policer and counter + * to ACL rules. + */ + +#define MLXSW_AFA_POLCNT_CODE 0x08 +#define MLXSW_AFA_POLCNT_SIZE 1 + +enum mlxsw_afa_polcnt_counter_set_type { + /* No count */ + MLXSW_AFA_POLCNT_COUNTER_SET_TYPE_NO_COUNT = 0x00, + /* Count packets and bytes */ + MLXSW_AFA_POLCNT_COUNTER_SET_TYPE_PACKETS_BYTES = 0x03, + /* Count only packets */ + MLXSW_AFA_POLCNT_COUNTER_SET_TYPE_PACKETS = 0x05, +}; + +/* afa_polcnt_counter_set_type + * Counter set type for flow counters. + */ +MLXSW_ITEM32(afa, polcnt, counter_set_type, 0x04, 24, 8); + +/* afa_polcnt_counter_index + * Counter index for flow counters. + */ +MLXSW_ITEM32(afa, polcnt, counter_index, 0x04, 0, 24); + +static inline void +mlxsw_afa_polcnt_pack(char *payload, + enum mlxsw_afa_polcnt_counter_set_type set_type, + u32 counter_index) +{ + mlxsw_afa_polcnt_counter_set_type_set(payload, set_type); + mlxsw_afa_polcnt_counter_index_set(payload, counter_index); +} + +int mlxsw_afa_block_append_counter(struct mlxsw_afa_block *block, + u32 counter_index) +{ + char *act = mlxsw_afa_block_append_action(block, + MLXSW_AFA_POLCNT_CODE, + MLXSW_AFA_POLCNT_SIZE); + if (!act) + return -ENOBUFS; + mlxsw_afa_polcnt_pack(act, MLXSW_AFA_POLCNT_COUNTER_SET_TYPE_PACKETS_BYTES, + counter_index); + return 0; +} +EXPORT_SYMBOL(mlxsw_afa_block_append_counter); diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.h b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.h index 43f78dcfe394..a03362c1ef32 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.h +++ b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.h @@ -62,5 +62,9 @@ void mlxsw_afa_block_jump(struct mlxsw_afa_block *block, u16 group_id); int mlxsw_afa_block_append_drop(struct mlxsw_afa_block *block); int mlxsw_afa_block_append_fwd(struct mlxsw_afa_block *block, u8 local_port, bool in_port); +int mlxsw_afa_block_append_vlan_modify(struct mlxsw_afa_block *block, + u16 vid, u8 pcp, u8 et); +int mlxsw_afa_block_append_counter(struct mlxsw_afa_block *block, + u32 counter_index); #endif diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_keys.h b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_keys.h index e4fcba7c2af2..c75e9141e3ec 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_keys.h +++ b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_keys.h @@ -54,6 +54,8 @@ enum mlxsw_afk_element { MLXSW_AFK_ELEMENT_DST_IP6_LO, MLXSW_AFK_ELEMENT_DST_L4_PORT, MLXSW_AFK_ELEMENT_SRC_L4_PORT, + MLXSW_AFK_ELEMENT_VID, + MLXSW_AFK_ELEMENT_PCP, MLXSW_AFK_ELEMENT_MAX, }; @@ -88,7 +90,7 @@ struct mlxsw_afk_element_info { MLXSW_AFK_ELEMENT_INFO(MLXSW_AFK_ELEMENT_TYPE_BUF, \ _element, _offset, 0, _size) -/* For the purpose of the driver, define a internal storage scratchpad +/* For the purpose of the driver, define an internal storage scratchpad * that will be used to store key/mask values. For each defined element type * define an internal storage geometry. */ @@ -98,6 +100,8 @@ static const struct mlxsw_afk_element_info mlxsw_afk_element_infos[] = { MLXSW_AFK_ELEMENT_INFO_BUF(SMAC, 0x0A, 6), MLXSW_AFK_ELEMENT_INFO_U32(ETHERTYPE, 0x00, 0, 16), MLXSW_AFK_ELEMENT_INFO_U32(IP_PROTO, 0x10, 0, 8), + MLXSW_AFK_ELEMENT_INFO_U32(VID, 0x10, 8, 12), + MLXSW_AFK_ELEMENT_INFO_U32(PCP, 0x10, 20, 3), MLXSW_AFK_ELEMENT_INFO_U32(SRC_IP4, 0x18, 0, 32), MLXSW_AFK_ELEMENT_INFO_U32(DST_IP4, 0x1C, 0, 32), MLXSW_AFK_ELEMENT_INFO_BUF(SRC_IP6_HI, 0x18, 8), diff --git a/drivers/net/ethernet/mellanox/mlxsw/pci.c b/drivers/net/ethernet/mellanox/mlxsw/pci.c index a223c85dfde0..ffeb746fe2f4 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/pci.c +++ b/drivers/net/ethernet/mellanox/mlxsw/pci.c @@ -580,7 +580,6 @@ static int mlxsw_pci_cq_init(struct mlxsw_pci *mlxsw_pci, char *mbox, mlxsw_cmd_mbox_sw2hw_cq_cv_set(mbox, 0); /* CQE ver 0 */ mlxsw_cmd_mbox_sw2hw_cq_c_eqn_set(mbox, MLXSW_PCI_EQ_COMP_NUM); - mlxsw_cmd_mbox_sw2hw_cq_oi_set(mbox, 0); mlxsw_cmd_mbox_sw2hw_cq_st_set(mbox, 0); mlxsw_cmd_mbox_sw2hw_cq_log_cq_size_set(mbox, ilog2(q->count)); for (i = 0; i < MLXSW_PCI_AQ_PAGES; i++) { @@ -755,7 +754,6 @@ static int mlxsw_pci_eq_init(struct mlxsw_pci *mlxsw_pci, char *mbox, } mlxsw_cmd_mbox_sw2hw_eq_int_msix_set(mbox, 1); /* MSI-X used */ - mlxsw_cmd_mbox_sw2hw_eq_oi_set(mbox, 0); mlxsw_cmd_mbox_sw2hw_eq_st_set(mbox, 1); /* armed */ mlxsw_cmd_mbox_sw2hw_eq_log_eq_size_set(mbox, ilog2(q->count)); for (i = 0; i < MLXSW_PCI_AQ_PAGES; i++) { diff --git a/drivers/net/ethernet/mellanox/mlxsw/reg.h b/drivers/net/ethernet/mellanox/mlxsw/reg.h index 0899e2d310e2..e7a652c43b5c 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/reg.h +++ b/drivers/net/ethernet/mellanox/mlxsw/reg.h @@ -769,7 +769,7 @@ static inline void mlxsw_reg_spvid_pack(char *payload, u8 local_port, u16 pvid) #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_REC_MAX_COUNT 255 #define MLXSW_REG_SPVM_LEN (MLXSW_REG_SPVM_BASE_LEN + \ MLXSW_REG_SPVM_REC_LEN * MLXSW_REG_SPVM_REC_MAX_COUNT) @@ -1702,7 +1702,7 @@ static inline void mlxsw_reg_sfmr_pack(char *payload, #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_REC_MAX_COUNT 255 #define MLXSW_REG_SPVMLR_LEN (MLXSW_REG_SPVMLR_BASE_LEN + \ MLXSW_REG_SPVMLR_REC_LEN * \ MLXSW_REG_SPVMLR_REC_MAX_COUNT) @@ -4141,7 +4141,8 @@ static inline void mlxsw_reg_ritr_sp_if_pack(char *payload, bool lag, static inline void mlxsw_reg_ritr_pack(char *payload, bool enable, enum mlxsw_reg_ritr_if_type type, - u16 rif, u16 mtu, const char *mac) + u16 rif, u16 vr_id, u16 mtu, + const char *mac) { bool op = enable ? MLXSW_REG_RITR_RIF_CREATE : MLXSW_REG_RITR_RIF_DEL; @@ -4153,6 +4154,7 @@ static inline void mlxsw_reg_ritr_pack(char *payload, bool enable, mlxsw_reg_ritr_rif_set(payload, rif); mlxsw_reg_ritr_ipv4_fe_set(payload, 1); mlxsw_reg_ritr_lb_en_set(payload, 1); + mlxsw_reg_ritr_virtual_router_set(payload, vr_id); mlxsw_reg_ritr_mtu_set(payload, mtu); mlxsw_reg_ritr_if_mac_memcpy_to(payload, mac); } @@ -5504,6 +5506,70 @@ static inline void mlxsw_reg_mpsc_pack(char *payload, u8 local_port, bool e, mlxsw_reg_mpsc_rate_set(payload, rate); } +/* MGPC - Monitoring General Purpose Counter Set Register + * The MGPC register retrieves and sets the General Purpose Counter Set. + */ +#define MLXSW_REG_MGPC_ID 0x9081 +#define MLXSW_REG_MGPC_LEN 0x18 + +MLXSW_REG_DEFINE(mgpc, MLXSW_REG_MGPC_ID, MLXSW_REG_MGPC_LEN); + +enum mlxsw_reg_mgpc_counter_set_type { + /* No count */ + MLXSW_REG_MGPC_COUNTER_SET_TYPE_NO_COUT = 0x00, + /* Count packets and bytes */ + MLXSW_REG_MGPC_COUNTER_SET_TYPE_PACKETS_BYTES = 0x03, + /* Count only packets */ + MLXSW_REG_MGPC_COUNTER_SET_TYPE_PACKETS = 0x05, +}; + +/* reg_mgpc_counter_set_type + * Counter set type. + * Access: OP + */ +MLXSW_ITEM32(reg, mgpc, counter_set_type, 0x00, 24, 8); + +/* reg_mgpc_counter_index + * Counter index. + * Access: Index + */ +MLXSW_ITEM32(reg, mgpc, counter_index, 0x00, 0, 24); + +enum mlxsw_reg_mgpc_opcode { + /* Nop */ + MLXSW_REG_MGPC_OPCODE_NOP = 0x00, + /* Clear counters */ + MLXSW_REG_MGPC_OPCODE_CLEAR = 0x08, +}; + +/* reg_mgpc_opcode + * Opcode. + * Access: OP + */ +MLXSW_ITEM32(reg, mgpc, opcode, 0x04, 28, 4); + +/* reg_mgpc_byte_counter + * Byte counter value. + * Access: RW + */ +MLXSW_ITEM64(reg, mgpc, byte_counter, 0x08, 0, 64); + +/* reg_mgpc_packet_counter + * Packet counter value. + * Access: RW + */ +MLXSW_ITEM64(reg, mgpc, packet_counter, 0x10, 0, 64); + +static inline void mlxsw_reg_mgpc_pack(char *payload, u32 counter_index, + enum mlxsw_reg_mgpc_opcode opcode, + enum mlxsw_reg_mgpc_counter_set_type set_type) +{ + MLXSW_REG_ZERO(mgpc, payload); + mlxsw_reg_mgpc_counter_index_set(payload, counter_index); + mlxsw_reg_mgpc_counter_set_type_set(payload, set_type); + mlxsw_reg_mgpc_opcode_set(payload, opcode); +} + /* SBPR - Shared Buffer Pools Register * ----------------------------------- * The SBPR configures and retrieves the shared buffer pools and configuration. @@ -5977,6 +6043,7 @@ static const struct mlxsw_reg_info *mlxsw_reg_infos[] = { MLXSW_REG(mpar), MLXSW_REG(mlcr), MLXSW_REG(mpsc), + MLXSW_REG(mgpc), MLXSW_REG(sbpr), MLXSW_REG(sbcm), MLXSW_REG(sbpm), diff --git a/drivers/net/ethernet/mellanox/mlxsw/resources.h b/drivers/net/ethernet/mellanox/mlxsw/resources.h index bce8c2e00630..905a8e269f87 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/resources.h +++ b/drivers/net/ethernet/mellanox/mlxsw/resources.h @@ -43,7 +43,9 @@ enum mlxsw_res_id { MLXSW_RES_ID_KVD_SINGLE_MIN_SIZE, MLXSW_RES_ID_KVD_DOUBLE_MIN_SIZE, MLXSW_RES_ID_MAX_TRAP_GROUPS, + MLXSW_RES_ID_COUNTER_POOL_SIZE, MLXSW_RES_ID_MAX_SPAN, + MLXSW_RES_ID_COUNTER_SIZE_PACKETS_BYTES, MLXSW_RES_ID_MAX_SYSTEM_PORT, MLXSW_RES_ID_MAX_LAG, MLXSW_RES_ID_MAX_LAG_MEMBERS, @@ -75,7 +77,9 @@ static u16 mlxsw_res_ids[] = { [MLXSW_RES_ID_KVD_SINGLE_MIN_SIZE] = 0x1002, [MLXSW_RES_ID_KVD_DOUBLE_MIN_SIZE] = 0x1003, [MLXSW_RES_ID_MAX_TRAP_GROUPS] = 0x2201, + [MLXSW_RES_ID_COUNTER_POOL_SIZE] = 0x2410, [MLXSW_RES_ID_MAX_SPAN] = 0x2420, + [MLXSW_RES_ID_COUNTER_SIZE_PACKETS_BYTES] = 0x2443, [MLXSW_RES_ID_MAX_SYSTEM_PORT] = 0x2502, [MLXSW_RES_ID_MAX_LAG] = 0x2520, [MLXSW_RES_ID_MAX_LAG_MEMBERS] = 0x2521, diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c index 16484f24b7db..28019f8b70f7 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c @@ -66,6 +66,7 @@ #include "port.h" #include "trap.h" #include "txheader.h" +#include "spectrum_cnt.h" static const char mlxsw_sp_driver_name[] = "mlxsw_spectrum"; static const char mlxsw_sp_driver_version[] = "1.0"; @@ -138,6 +139,60 @@ MLXSW_ITEM32(tx, hdr, fid, 0x08, 0, 16); */ MLXSW_ITEM32(tx, hdr, type, 0x0C, 0, 4); +int mlxsw_sp_flow_counter_get(struct mlxsw_sp *mlxsw_sp, + unsigned int counter_index, u64 *packets, + u64 *bytes) +{ + char mgpc_pl[MLXSW_REG_MGPC_LEN]; + int err; + + mlxsw_reg_mgpc_pack(mgpc_pl, counter_index, MLXSW_REG_MGPC_OPCODE_NOP, + MLXSW_REG_MGPC_COUNTER_SET_TYPE_PACKETS_BYTES); + err = mlxsw_reg_query(mlxsw_sp->core, MLXSW_REG(mgpc), mgpc_pl); + if (err) + return err; + *packets = mlxsw_reg_mgpc_packet_counter_get(mgpc_pl); + *bytes = mlxsw_reg_mgpc_byte_counter_get(mgpc_pl); + return 0; +} + +static int mlxsw_sp_flow_counter_clear(struct mlxsw_sp *mlxsw_sp, + unsigned int counter_index) +{ + char mgpc_pl[MLXSW_REG_MGPC_LEN]; + + mlxsw_reg_mgpc_pack(mgpc_pl, counter_index, MLXSW_REG_MGPC_OPCODE_CLEAR, + MLXSW_REG_MGPC_COUNTER_SET_TYPE_PACKETS_BYTES); + return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(mgpc), mgpc_pl); +} + +int mlxsw_sp_flow_counter_alloc(struct mlxsw_sp *mlxsw_sp, + unsigned int *p_counter_index) +{ + int err; + + err = mlxsw_sp_counter_alloc(mlxsw_sp, MLXSW_SP_COUNTER_SUB_POOL_FLOW, + p_counter_index); + if (err) + return err; + err = mlxsw_sp_flow_counter_clear(mlxsw_sp, *p_counter_index); + if (err) + goto err_counter_clear; + return 0; + +err_counter_clear: + mlxsw_sp_counter_free(mlxsw_sp, MLXSW_SP_COUNTER_SUB_POOL_FLOW, + *p_counter_index); + return err; +} + +void mlxsw_sp_flow_counter_free(struct mlxsw_sp *mlxsw_sp, + unsigned int counter_index) +{ + mlxsw_sp_counter_free(mlxsw_sp, MLXSW_SP_COUNTER_SUB_POOL_FLOW, + counter_index); +} + static void mlxsw_sp_txhdr_construct(struct sk_buff *skb, const struct mlxsw_tx_info *tx_info) { @@ -1379,6 +1434,9 @@ static int mlxsw_sp_setup_tc(struct net_device *dev, u32 handle, mlxsw_sp_flower_destroy(mlxsw_sp_port, ingress, tc->cls_flower); return 0; + case TC_CLSFLOWER_STATS: + return mlxsw_sp_flower_stats(mlxsw_sp_port, ingress, + tc->cls_flower); default: return -EOPNOTSUPP; } @@ -3224,6 +3282,12 @@ static int mlxsw_sp_init(struct mlxsw_core *mlxsw_core, goto err_acl_init; } + err = mlxsw_sp_counter_pool_init(mlxsw_sp); + if (err) { + dev_err(mlxsw_sp->bus_info->dev, "Failed to init counter pool\n"); + goto err_counter_pool_init; + } + err = mlxsw_sp_ports_create(mlxsw_sp); if (err) { dev_err(mlxsw_sp->bus_info->dev, "Failed to create ports\n"); @@ -3233,6 +3297,8 @@ static int mlxsw_sp_init(struct mlxsw_core *mlxsw_core, return 0; err_ports_create: + mlxsw_sp_counter_pool_fini(mlxsw_sp); +err_counter_pool_init: mlxsw_sp_acl_fini(mlxsw_sp); err_acl_init: mlxsw_sp_span_fini(mlxsw_sp); @@ -3255,6 +3321,7 @@ static void mlxsw_sp_fini(struct mlxsw_core *mlxsw_core) struct mlxsw_sp *mlxsw_sp = mlxsw_core_driver_priv(mlxsw_core); mlxsw_sp_ports_remove(mlxsw_sp); + mlxsw_sp_counter_pool_fini(mlxsw_sp); mlxsw_sp_acl_fini(mlxsw_sp); mlxsw_sp_span_fini(mlxsw_sp); mlxsw_sp_router_fini(mlxsw_sp); @@ -3326,13 +3393,13 @@ bool mlxsw_sp_port_dev_check(const struct net_device *dev) return dev->netdev_ops == &mlxsw_sp_port_netdev_ops; } -static int mlxsw_lower_dev_walk(struct net_device *lower_dev, void *data) +static int mlxsw_sp_lower_dev_walk(struct net_device *lower_dev, void *data) { - struct mlxsw_sp_port **port = data; + struct mlxsw_sp_port **p_mlxsw_sp_port = data; int ret = 0; if (mlxsw_sp_port_dev_check(lower_dev)) { - *port = netdev_priv(lower_dev); + *p_mlxsw_sp_port = netdev_priv(lower_dev); ret = 1; } @@ -3341,18 +3408,18 @@ static int mlxsw_lower_dev_walk(struct net_device *lower_dev, void *data) static struct mlxsw_sp_port *mlxsw_sp_port_dev_lower_find(struct net_device *dev) { - struct mlxsw_sp_port *port; + struct mlxsw_sp_port *mlxsw_sp_port; if (mlxsw_sp_port_dev_check(dev)) return netdev_priv(dev); - port = NULL; - netdev_walk_all_lower_dev(dev, mlxsw_lower_dev_walk, &port); + mlxsw_sp_port = NULL; + netdev_walk_all_lower_dev(dev, mlxsw_sp_lower_dev_walk, &mlxsw_sp_port); - return port; + return mlxsw_sp_port; } -static struct mlxsw_sp *mlxsw_sp_lower_get(struct net_device *dev) +struct mlxsw_sp *mlxsw_sp_lower_get(struct net_device *dev) { struct mlxsw_sp_port *mlxsw_sp_port; @@ -3362,15 +3429,16 @@ static struct mlxsw_sp *mlxsw_sp_lower_get(struct net_device *dev) static struct mlxsw_sp_port *mlxsw_sp_port_dev_lower_find_rcu(struct net_device *dev) { - struct mlxsw_sp_port *port; + struct mlxsw_sp_port *mlxsw_sp_port; if (mlxsw_sp_port_dev_check(dev)) return netdev_priv(dev); - port = NULL; - netdev_walk_all_lower_dev_rcu(dev, mlxsw_lower_dev_walk, &port); + mlxsw_sp_port = NULL; + netdev_walk_all_lower_dev_rcu(dev, mlxsw_sp_lower_dev_walk, + &mlxsw_sp_port); - return port; + return mlxsw_sp_port; } struct mlxsw_sp_port *mlxsw_sp_port_lower_dev_hold(struct net_device *dev) @@ -3390,546 +3458,6 @@ void mlxsw_sp_port_dev_put(struct mlxsw_sp_port *mlxsw_sp_port) dev_put(mlxsw_sp_port->dev); } -static bool mlxsw_sp_rif_should_config(struct mlxsw_sp_rif *r, - unsigned long event) -{ - switch (event) { - case NETDEV_UP: - if (!r) - return true; - r->ref_count++; - return false; - case NETDEV_DOWN: - if (r && --r->ref_count == 0) - return true; - /* It is possible we already removed the RIF ourselves - * if it was assigned to a netdev that is now a bridge - * or LAG slave. - */ - return false; - } - - return false; -} - -static int mlxsw_sp_avail_rif_get(struct mlxsw_sp *mlxsw_sp) -{ - int i; - - for (i = 0; i < MLXSW_CORE_RES_GET(mlxsw_sp->core, MAX_RIFS); i++) - if (!mlxsw_sp->rifs[i]) - return i; - - return MLXSW_SP_INVALID_RIF; -} - -static void mlxsw_sp_vport_rif_sp_attr_get(struct mlxsw_sp_port *mlxsw_sp_vport, - bool *p_lagged, u16 *p_system_port) -{ - u8 local_port = mlxsw_sp_vport->local_port; - - *p_lagged = mlxsw_sp_vport->lagged; - *p_system_port = *p_lagged ? mlxsw_sp_vport->lag_id : local_port; -} - -static int mlxsw_sp_vport_rif_sp_op(struct mlxsw_sp_port *mlxsw_sp_vport, - struct net_device *l3_dev, u16 rif, - bool create) -{ - struct mlxsw_sp *mlxsw_sp = mlxsw_sp_vport->mlxsw_sp; - bool lagged = mlxsw_sp_vport->lagged; - char ritr_pl[MLXSW_REG_RITR_LEN]; - u16 system_port; - - mlxsw_reg_ritr_pack(ritr_pl, create, MLXSW_REG_RITR_SP_IF, rif, - l3_dev->mtu, l3_dev->dev_addr); - - mlxsw_sp_vport_rif_sp_attr_get(mlxsw_sp_vport, &lagged, &system_port); - mlxsw_reg_ritr_sp_if_pack(ritr_pl, lagged, system_port, - mlxsw_sp_vport_vid_get(mlxsw_sp_vport)); - - return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ritr), ritr_pl); -} - -static void mlxsw_sp_vport_rif_sp_leave(struct mlxsw_sp_port *mlxsw_sp_vport); - -static struct mlxsw_sp_fid * -mlxsw_sp_rfid_alloc(u16 fid, struct net_device *l3_dev) -{ - struct mlxsw_sp_fid *f; - - f = kzalloc(sizeof(*f), GFP_KERNEL); - if (!f) - return NULL; - - f->leave = mlxsw_sp_vport_rif_sp_leave; - f->ref_count = 0; - f->dev = l3_dev; - f->fid = fid; - - return f; -} - -static struct mlxsw_sp_rif * -mlxsw_sp_rif_alloc(u16 rif, struct net_device *l3_dev, struct mlxsw_sp_fid *f) -{ - struct mlxsw_sp_rif *r; - - r = kzalloc(sizeof(*r), GFP_KERNEL); - if (!r) - return NULL; - - INIT_LIST_HEAD(&r->nexthop_list); - INIT_LIST_HEAD(&r->neigh_list); - ether_addr_copy(r->addr, l3_dev->dev_addr); - r->mtu = l3_dev->mtu; - r->ref_count = 1; - r->dev = l3_dev; - r->rif = rif; - r->f = f; - - return r; -} - -static struct mlxsw_sp_rif * -mlxsw_sp_vport_rif_sp_create(struct mlxsw_sp_port *mlxsw_sp_vport, - struct net_device *l3_dev) -{ - struct mlxsw_sp *mlxsw_sp = mlxsw_sp_vport->mlxsw_sp; - struct mlxsw_sp_fid *f; - struct mlxsw_sp_rif *r; - u16 fid, rif; - int err; - - rif = mlxsw_sp_avail_rif_get(mlxsw_sp); - if (rif == MLXSW_SP_INVALID_RIF) - return ERR_PTR(-ERANGE); - - err = mlxsw_sp_vport_rif_sp_op(mlxsw_sp_vport, l3_dev, rif, true); - if (err) - return ERR_PTR(err); - - fid = mlxsw_sp_rif_sp_to_fid(rif); - err = mlxsw_sp_rif_fdb_op(mlxsw_sp, l3_dev->dev_addr, fid, true); - if (err) - goto err_rif_fdb_op; - - f = mlxsw_sp_rfid_alloc(fid, l3_dev); - if (!f) { - err = -ENOMEM; - goto err_rfid_alloc; - } - - r = mlxsw_sp_rif_alloc(rif, l3_dev, f); - if (!r) { - err = -ENOMEM; - goto err_rif_alloc; - } - - f->r = r; - mlxsw_sp->rifs[rif] = r; - - return r; - -err_rif_alloc: - kfree(f); -err_rfid_alloc: - mlxsw_sp_rif_fdb_op(mlxsw_sp, l3_dev->dev_addr, fid, false); -err_rif_fdb_op: - mlxsw_sp_vport_rif_sp_op(mlxsw_sp_vport, l3_dev, rif, false); - return ERR_PTR(err); -} - -static void mlxsw_sp_vport_rif_sp_destroy(struct mlxsw_sp_port *mlxsw_sp_vport, - struct mlxsw_sp_rif *r) -{ - struct mlxsw_sp *mlxsw_sp = mlxsw_sp_vport->mlxsw_sp; - struct net_device *l3_dev = r->dev; - struct mlxsw_sp_fid *f = r->f; - u16 fid = f->fid; - u16 rif = r->rif; - - mlxsw_sp_router_rif_gone_sync(mlxsw_sp, r); - - mlxsw_sp->rifs[rif] = NULL; - f->r = NULL; - - kfree(r); - - kfree(f); - - mlxsw_sp_rif_fdb_op(mlxsw_sp, l3_dev->dev_addr, fid, false); - - mlxsw_sp_vport_rif_sp_op(mlxsw_sp_vport, l3_dev, rif, false); -} - -static int mlxsw_sp_vport_rif_sp_join(struct mlxsw_sp_port *mlxsw_sp_vport, - struct net_device *l3_dev) -{ - struct mlxsw_sp *mlxsw_sp = mlxsw_sp_vport->mlxsw_sp; - struct mlxsw_sp_rif *r; - - r = mlxsw_sp_rif_find_by_dev(mlxsw_sp, l3_dev); - if (!r) { - r = mlxsw_sp_vport_rif_sp_create(mlxsw_sp_vport, l3_dev); - if (IS_ERR(r)) - return PTR_ERR(r); - } - - mlxsw_sp_vport_fid_set(mlxsw_sp_vport, r->f); - r->f->ref_count++; - - netdev_dbg(mlxsw_sp_vport->dev, "Joined FID=%d\n", r->f->fid); - - return 0; -} - -static void mlxsw_sp_vport_rif_sp_leave(struct mlxsw_sp_port *mlxsw_sp_vport) -{ - struct mlxsw_sp_fid *f = mlxsw_sp_vport_fid_get(mlxsw_sp_vport); - - netdev_dbg(mlxsw_sp_vport->dev, "Left FID=%d\n", f->fid); - - mlxsw_sp_vport_fid_set(mlxsw_sp_vport, NULL); - if (--f->ref_count == 0) - mlxsw_sp_vport_rif_sp_destroy(mlxsw_sp_vport, f->r); -} - -static int mlxsw_sp_inetaddr_vport_event(struct net_device *l3_dev, - struct net_device *port_dev, - unsigned long event, u16 vid) -{ - struct mlxsw_sp_port *mlxsw_sp_port = netdev_priv(port_dev); - struct mlxsw_sp_port *mlxsw_sp_vport; - - mlxsw_sp_vport = mlxsw_sp_port_vport_find(mlxsw_sp_port, vid); - if (WARN_ON(!mlxsw_sp_vport)) - return -EINVAL; - - switch (event) { - case NETDEV_UP: - return mlxsw_sp_vport_rif_sp_join(mlxsw_sp_vport, l3_dev); - case NETDEV_DOWN: - mlxsw_sp_vport_rif_sp_leave(mlxsw_sp_vport); - break; - } - - return 0; -} - -static int mlxsw_sp_inetaddr_port_event(struct net_device *port_dev, - unsigned long event) -{ - if (netif_is_bridge_port(port_dev) || netif_is_lag_port(port_dev)) - return 0; - - return mlxsw_sp_inetaddr_vport_event(port_dev, port_dev, event, 1); -} - -static int __mlxsw_sp_inetaddr_lag_event(struct net_device *l3_dev, - struct net_device *lag_dev, - unsigned long event, u16 vid) -{ - struct net_device *port_dev; - struct list_head *iter; - int err; - - netdev_for_each_lower_dev(lag_dev, port_dev, iter) { - if (mlxsw_sp_port_dev_check(port_dev)) { - err = mlxsw_sp_inetaddr_vport_event(l3_dev, port_dev, - event, vid); - if (err) - return err; - } - } - - return 0; -} - -static int mlxsw_sp_inetaddr_lag_event(struct net_device *lag_dev, - unsigned long event) -{ - if (netif_is_bridge_port(lag_dev)) - return 0; - - return __mlxsw_sp_inetaddr_lag_event(lag_dev, lag_dev, event, 1); -} - -static struct mlxsw_sp_fid *mlxsw_sp_bridge_fid_get(struct mlxsw_sp *mlxsw_sp, - struct net_device *l3_dev) -{ - u16 fid; - - if (is_vlan_dev(l3_dev)) - fid = vlan_dev_vlan_id(l3_dev); - else if (mlxsw_sp->master_bridge.dev == l3_dev) - fid = 1; - else - return mlxsw_sp_vfid_find(mlxsw_sp, l3_dev); - - return mlxsw_sp_fid_find(mlxsw_sp, fid); -} - -static enum mlxsw_flood_table_type mlxsw_sp_flood_table_type_get(u16 fid) -{ - return mlxsw_sp_fid_is_vfid(fid) ? MLXSW_REG_SFGC_TABLE_TYPE_FID : - MLXSW_REG_SFGC_TABLE_TYPE_FID_OFFEST; -} - -static u16 mlxsw_sp_flood_table_index_get(u16 fid) -{ - return mlxsw_sp_fid_is_vfid(fid) ? mlxsw_sp_fid_to_vfid(fid) : fid; -} - -static int mlxsw_sp_router_port_flood_set(struct mlxsw_sp *mlxsw_sp, u16 fid, - bool set) -{ - enum mlxsw_flood_table_type table_type; - char *sftr_pl; - u16 index; - int err; - - sftr_pl = kmalloc(MLXSW_REG_SFTR_LEN, GFP_KERNEL); - if (!sftr_pl) - return -ENOMEM; - - table_type = mlxsw_sp_flood_table_type_get(fid); - index = mlxsw_sp_flood_table_index_get(fid); - mlxsw_reg_sftr_pack(sftr_pl, MLXSW_SP_FLOOD_TABLE_BC, index, table_type, - 1, MLXSW_PORT_ROUTER_PORT, set); - err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(sftr), sftr_pl); - - kfree(sftr_pl); - return err; -} - -static enum mlxsw_reg_ritr_if_type mlxsw_sp_rif_type_get(u16 fid) -{ - if (mlxsw_sp_fid_is_vfid(fid)) - return MLXSW_REG_RITR_FID_IF; - else - return MLXSW_REG_RITR_VLAN_IF; -} - -static int mlxsw_sp_rif_bridge_op(struct mlxsw_sp *mlxsw_sp, - struct net_device *l3_dev, - u16 fid, u16 rif, - bool create) -{ - enum mlxsw_reg_ritr_if_type rif_type; - char ritr_pl[MLXSW_REG_RITR_LEN]; - - rif_type = mlxsw_sp_rif_type_get(fid); - mlxsw_reg_ritr_pack(ritr_pl, create, rif_type, rif, l3_dev->mtu, - l3_dev->dev_addr); - mlxsw_reg_ritr_fid_set(ritr_pl, rif_type, fid); - - return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ritr), ritr_pl); -} - -static int mlxsw_sp_rif_bridge_create(struct mlxsw_sp *mlxsw_sp, - struct net_device *l3_dev, - struct mlxsw_sp_fid *f) -{ - struct mlxsw_sp_rif *r; - u16 rif; - int err; - - rif = mlxsw_sp_avail_rif_get(mlxsw_sp); - if (rif == MLXSW_SP_INVALID_RIF) - return -ERANGE; - - err = mlxsw_sp_router_port_flood_set(mlxsw_sp, f->fid, true); - if (err) - return err; - - err = mlxsw_sp_rif_bridge_op(mlxsw_sp, l3_dev, f->fid, rif, true); - if (err) - goto err_rif_bridge_op; - - err = mlxsw_sp_rif_fdb_op(mlxsw_sp, l3_dev->dev_addr, f->fid, true); - if (err) - goto err_rif_fdb_op; - - r = mlxsw_sp_rif_alloc(rif, l3_dev, f); - if (!r) { - err = -ENOMEM; - goto err_rif_alloc; - } - - f->r = r; - mlxsw_sp->rifs[rif] = r; - - netdev_dbg(l3_dev, "RIF=%d created\n", rif); - - return 0; - -err_rif_alloc: - mlxsw_sp_rif_fdb_op(mlxsw_sp, l3_dev->dev_addr, f->fid, false); -err_rif_fdb_op: - mlxsw_sp_rif_bridge_op(mlxsw_sp, l3_dev, f->fid, rif, false); -err_rif_bridge_op: - mlxsw_sp_router_port_flood_set(mlxsw_sp, f->fid, false); - return err; -} - -void mlxsw_sp_rif_bridge_destroy(struct mlxsw_sp *mlxsw_sp, - struct mlxsw_sp_rif *r) -{ - struct net_device *l3_dev = r->dev; - struct mlxsw_sp_fid *f = r->f; - u16 rif = r->rif; - - mlxsw_sp_router_rif_gone_sync(mlxsw_sp, r); - - mlxsw_sp->rifs[rif] = NULL; - f->r = NULL; - - kfree(r); - - mlxsw_sp_rif_fdb_op(mlxsw_sp, l3_dev->dev_addr, f->fid, false); - - mlxsw_sp_rif_bridge_op(mlxsw_sp, l3_dev, f->fid, rif, false); - - mlxsw_sp_router_port_flood_set(mlxsw_sp, f->fid, false); - - netdev_dbg(l3_dev, "RIF=%d destroyed\n", rif); -} - -static int mlxsw_sp_inetaddr_bridge_event(struct net_device *l3_dev, - struct net_device *br_dev, - unsigned long event) -{ - struct mlxsw_sp *mlxsw_sp = mlxsw_sp_lower_get(l3_dev); - struct mlxsw_sp_fid *f; - - /* FID can either be an actual FID if the L3 device is the - * VLAN-aware bridge or a VLAN device on top. Otherwise, the - * L3 device is a VLAN-unaware bridge and we get a vFID. - */ - f = mlxsw_sp_bridge_fid_get(mlxsw_sp, l3_dev); - if (WARN_ON(!f)) - return -EINVAL; - - switch (event) { - case NETDEV_UP: - return mlxsw_sp_rif_bridge_create(mlxsw_sp, l3_dev, f); - case NETDEV_DOWN: - mlxsw_sp_rif_bridge_destroy(mlxsw_sp, f->r); - break; - } - - return 0; -} - -static int mlxsw_sp_inetaddr_vlan_event(struct net_device *vlan_dev, - unsigned long event) -{ - struct net_device *real_dev = vlan_dev_real_dev(vlan_dev); - struct mlxsw_sp *mlxsw_sp = mlxsw_sp_lower_get(vlan_dev); - u16 vid = vlan_dev_vlan_id(vlan_dev); - - if (mlxsw_sp_port_dev_check(real_dev)) - return mlxsw_sp_inetaddr_vport_event(vlan_dev, real_dev, event, - vid); - else if (netif_is_lag_master(real_dev)) - return __mlxsw_sp_inetaddr_lag_event(vlan_dev, real_dev, event, - vid); - else if (netif_is_bridge_master(real_dev) && - mlxsw_sp->master_bridge.dev == real_dev) - return mlxsw_sp_inetaddr_bridge_event(vlan_dev, real_dev, - event); - - return 0; -} - -static int mlxsw_sp_inetaddr_event(struct notifier_block *unused, - unsigned long event, void *ptr) -{ - struct in_ifaddr *ifa = (struct in_ifaddr *) ptr; - struct net_device *dev = ifa->ifa_dev->dev; - struct mlxsw_sp *mlxsw_sp; - struct mlxsw_sp_rif *r; - int err = 0; - - mlxsw_sp = mlxsw_sp_lower_get(dev); - if (!mlxsw_sp) - goto out; - - r = mlxsw_sp_rif_find_by_dev(mlxsw_sp, dev); - if (!mlxsw_sp_rif_should_config(r, event)) - goto out; - - if (mlxsw_sp_port_dev_check(dev)) - err = mlxsw_sp_inetaddr_port_event(dev, event); - else if (netif_is_lag_master(dev)) - err = mlxsw_sp_inetaddr_lag_event(dev, event); - else if (netif_is_bridge_master(dev)) - err = mlxsw_sp_inetaddr_bridge_event(dev, dev, event); - else if (is_vlan_dev(dev)) - err = mlxsw_sp_inetaddr_vlan_event(dev, event); - -out: - return notifier_from_errno(err); -} - -static int mlxsw_sp_rif_edit(struct mlxsw_sp *mlxsw_sp, u16 rif, - const char *mac, int mtu) -{ - char ritr_pl[MLXSW_REG_RITR_LEN]; - int err; - - mlxsw_reg_ritr_rif_pack(ritr_pl, rif); - err = mlxsw_reg_query(mlxsw_sp->core, MLXSW_REG(ritr), ritr_pl); - if (err) - return err; - - mlxsw_reg_ritr_mtu_set(ritr_pl, mtu); - mlxsw_reg_ritr_if_mac_memcpy_to(ritr_pl, mac); - mlxsw_reg_ritr_op_set(ritr_pl, MLXSW_REG_RITR_RIF_CREATE); - return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ritr), ritr_pl); -} - -static int mlxsw_sp_netdevice_router_port_event(struct net_device *dev) -{ - struct mlxsw_sp *mlxsw_sp; - struct mlxsw_sp_rif *r; - int err; - - mlxsw_sp = mlxsw_sp_lower_get(dev); - if (!mlxsw_sp) - return 0; - - r = mlxsw_sp_rif_find_by_dev(mlxsw_sp, dev); - if (!r) - return 0; - - err = mlxsw_sp_rif_fdb_op(mlxsw_sp, r->addr, r->f->fid, false); - if (err) - return err; - - err = mlxsw_sp_rif_edit(mlxsw_sp, r->rif, dev->dev_addr, dev->mtu); - if (err) - goto err_rif_edit; - - err = mlxsw_sp_rif_fdb_op(mlxsw_sp, dev->dev_addr, r->f->fid, true); - if (err) - goto err_rif_fdb_op; - - ether_addr_copy(r->addr, dev->dev_addr); - r->mtu = dev->mtu; - - netdev_dbg(dev, "Updated RIF=%d\n", r->rif); - - return 0; - -err_rif_fdb_op: - mlxsw_sp_rif_edit(mlxsw_sp, r->rif, r->addr, r->mtu); -err_rif_edit: - mlxsw_sp_rif_fdb_op(mlxsw_sp, r->addr, r->f->fid, true); - return err; -} - static bool mlxsw_sp_lag_port_fid_member(struct mlxsw_sp_port *lag_port, u16 fid) { @@ -4220,7 +3748,7 @@ static int mlxsw_sp_port_lag_index_get(struct mlxsw_sp *mlxsw_sp, static void mlxsw_sp_port_pvid_vport_lag_join(struct mlxsw_sp_port *mlxsw_sp_port, - u16 lag_id) + struct net_device *lag_dev, u16 lag_id) { struct mlxsw_sp_port *mlxsw_sp_vport; struct mlxsw_sp_fid *f; @@ -4238,6 +3766,7 @@ mlxsw_sp_port_pvid_vport_lag_join(struct mlxsw_sp_port *mlxsw_sp_port, mlxsw_sp_vport->lag_id = lag_id; mlxsw_sp_vport->lagged = 1; + mlxsw_sp_vport->dev = lag_dev; } static void @@ -4254,6 +3783,7 @@ mlxsw_sp_port_pvid_vport_lag_leave(struct mlxsw_sp_port *mlxsw_sp_port) if (f) f->leave(mlxsw_sp_vport); + mlxsw_sp_vport->dev = mlxsw_sp_port->dev; mlxsw_sp_vport->lagged = 0; } @@ -4293,7 +3823,7 @@ static int mlxsw_sp_port_lag_join(struct mlxsw_sp_port *mlxsw_sp_port, mlxsw_sp_port->lagged = 1; lag->ref_count++; - mlxsw_sp_port_pvid_vport_lag_join(mlxsw_sp_port, lag_id); + mlxsw_sp_port_pvid_vport_lag_join(mlxsw_sp_port, lag_dev, lag_id); return 0; @@ -4421,7 +3951,8 @@ static int mlxsw_sp_netdevice_port_upper_event(struct net_device *dev, upper_dev = info->upper_dev; if (!is_vlan_dev(upper_dev) && !netif_is_lag_master(upper_dev) && - !netif_is_bridge_master(upper_dev)) + !netif_is_bridge_master(upper_dev) && + !netif_is_l3_master(upper_dev)) return -EINVAL; if (!info->linking) break; @@ -4461,6 +3992,11 @@ static int mlxsw_sp_netdevice_port_upper_event(struct net_device *dev, else mlxsw_sp_port_lag_leave(mlxsw_sp_port, upper_dev); + } else if (netif_is_l3_master(upper_dev)) { + if (info->linking) + err = mlxsw_sp_port_vrf_join(mlxsw_sp_port); + else + mlxsw_sp_port_vrf_leave(mlxsw_sp_port); } else { err = -EINVAL; WARN_ON(1); @@ -4564,33 +4100,46 @@ static int mlxsw_sp_netdevice_bridge_event(struct net_device *br_dev, struct netdev_notifier_changeupper_info *info; struct net_device *upper_dev; struct mlxsw_sp *mlxsw_sp; - int err; + int err = 0; mlxsw_sp = mlxsw_sp_lower_get(br_dev); if (!mlxsw_sp) return 0; - if (br_dev != mlxsw_sp->master_bridge.dev) - return 0; info = ptr; switch (event) { + case NETDEV_PRECHANGEUPPER: + upper_dev = info->upper_dev; + if (!is_vlan_dev(upper_dev) && !netif_is_l3_master(upper_dev)) + return -EINVAL; + if (is_vlan_dev(upper_dev) && + br_dev != mlxsw_sp->master_bridge.dev) + return -EINVAL; + break; case NETDEV_CHANGEUPPER: upper_dev = info->upper_dev; - if (!is_vlan_dev(upper_dev)) - break; - if (info->linking) { - err = mlxsw_sp_master_bridge_vlan_link(mlxsw_sp, - upper_dev); - if (err) - return err; + if (is_vlan_dev(upper_dev)) { + if (info->linking) + err = mlxsw_sp_master_bridge_vlan_link(mlxsw_sp, + upper_dev); + else + mlxsw_sp_master_bridge_vlan_unlink(mlxsw_sp, + upper_dev); + } else if (netif_is_l3_master(upper_dev)) { + if (info->linking) + err = mlxsw_sp_bridge_vrf_join(mlxsw_sp, + br_dev); + else + mlxsw_sp_bridge_vrf_leave(mlxsw_sp, br_dev); } else { - mlxsw_sp_master_bridge_vlan_unlink(mlxsw_sp, upper_dev); + err = -EINVAL; + WARN_ON(1); } break; } - return 0; + return err; } static u16 mlxsw_sp_avail_vfid_get(const struct mlxsw_sp *mlxsw_sp) @@ -4810,33 +4359,43 @@ static int mlxsw_sp_netdevice_vport_event(struct net_device *dev, int err = 0; mlxsw_sp_vport = mlxsw_sp_port_vport_find(mlxsw_sp_port, vid); + if (!mlxsw_sp_vport) + return 0; switch (event) { case NETDEV_PRECHANGEUPPER: upper_dev = info->upper_dev; - if (!netif_is_bridge_master(upper_dev)) + if (!netif_is_bridge_master(upper_dev) && + !netif_is_l3_master(upper_dev)) return -EINVAL; if (!info->linking) break; /* We can't have multiple VLAN interfaces configured on * the same port and being members in the same bridge. */ - if (!mlxsw_sp_port_master_bridge_check(mlxsw_sp_port, + if (netif_is_bridge_master(upper_dev) && + !mlxsw_sp_port_master_bridge_check(mlxsw_sp_port, upper_dev)) return -EINVAL; break; case NETDEV_CHANGEUPPER: upper_dev = info->upper_dev; - if (info->linking) { - if (WARN_ON(!mlxsw_sp_vport)) - return -EINVAL; - err = mlxsw_sp_vport_bridge_join(mlxsw_sp_vport, - upper_dev); + if (netif_is_bridge_master(upper_dev)) { + if (info->linking) + err = mlxsw_sp_vport_bridge_join(mlxsw_sp_vport, + upper_dev); + else + mlxsw_sp_vport_bridge_leave(mlxsw_sp_vport); + } else if (netif_is_l3_master(upper_dev)) { + if (info->linking) + err = mlxsw_sp_vport_vrf_join(mlxsw_sp_vport); + else + mlxsw_sp_vport_vrf_leave(mlxsw_sp_vport); } else { - if (!mlxsw_sp_vport) - return 0; - mlxsw_sp_vport_bridge_leave(mlxsw_sp_vport); + err = -EINVAL; + WARN_ON(1); } + break; } return err; @@ -4862,6 +4421,47 @@ static int mlxsw_sp_netdevice_lag_vport_event(struct net_device *lag_dev, return 0; } +static int mlxsw_sp_netdevice_bridge_vlan_event(struct net_device *vlan_dev, + unsigned long event, void *ptr) +{ + struct netdev_notifier_changeupper_info *info; + struct mlxsw_sp *mlxsw_sp; + int err = 0; + + mlxsw_sp = mlxsw_sp_lower_get(vlan_dev); + if (!mlxsw_sp) + return 0; + + info = ptr; + + switch (event) { + case NETDEV_PRECHANGEUPPER: + /* VLAN devices are only allowed on top of the + * VLAN-aware bridge. + */ + if (WARN_ON(vlan_dev_real_dev(vlan_dev) != + mlxsw_sp->master_bridge.dev)) + return -EINVAL; + if (!netif_is_l3_master(info->upper_dev)) + return -EINVAL; + break; + case NETDEV_CHANGEUPPER: + if (netif_is_l3_master(info->upper_dev)) { + if (info->linking) + err = mlxsw_sp_bridge_vrf_join(mlxsw_sp, + vlan_dev); + else + mlxsw_sp_bridge_vrf_leave(mlxsw_sp, vlan_dev); + } else { + err = -EINVAL; + WARN_ON(1); + } + break; + } + + return err; +} + static int mlxsw_sp_netdevice_vlan_event(struct net_device *vlan_dev, unsigned long event, void *ptr) { @@ -4874,6 +4474,9 @@ static int mlxsw_sp_netdevice_vlan_event(struct net_device *vlan_dev, else if (netif_is_lag_master(real_dev)) return mlxsw_sp_netdevice_lag_vport_event(real_dev, event, ptr, vid); + else if (netif_is_bridge_master(real_dev)) + return mlxsw_sp_netdevice_bridge_vlan_event(vlan_dev, event, + ptr); return 0; } diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h index 13ec85e7c392..0e223f6983c5 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h @@ -58,7 +58,6 @@ #define MLXSW_SP_VFID_MAX 1024 /* Bridged VLAN interfaces */ #define MLXSW_SP_RFID_BASE 15360 -#define MLXSW_SP_INVALID_RIF 0xffff #define MLXSW_SP_MID_MAX 7000 @@ -92,6 +91,7 @@ static inline u16 mlxsw_sp_pfc_delay_get(int mtu, u16 delay) } struct mlxsw_sp_port; +struct mlxsw_sp_rif; struct mlxsw_sp_upper { struct net_device *dev; @@ -107,17 +107,6 @@ struct mlxsw_sp_fid { u16 fid; }; -struct mlxsw_sp_rif { - struct list_head nexthop_list; - struct list_head neigh_list; - struct net_device *dev; - unsigned int ref_count; - struct mlxsw_sp_fid *f; - unsigned char addr[ETH_ALEN]; - int mtu; - u16 rif; -}; - struct mlxsw_sp_mid { struct list_head list; unsigned char addr[ETH_ALEN]; @@ -141,16 +130,6 @@ static inline bool mlxsw_sp_fid_is_vfid(u16 fid) return fid >= MLXSW_SP_VFID_BASE && fid < MLXSW_SP_RFID_BASE; } -static inline bool mlxsw_sp_fid_is_rfid(u16 fid) -{ - return fid >= MLXSW_SP_RFID_BASE; -} - -static inline u16 mlxsw_sp_rif_sp_to_fid(u16 rif) -{ - return MLXSW_SP_RFID_BASE + rif; -} - struct mlxsw_sp_sb_pr { enum mlxsw_reg_sbpr_mode mode; u32 size; @@ -207,11 +186,9 @@ struct mlxsw_sp_fib; struct mlxsw_sp_vr { u16 id; /* virtual router ID */ - bool used; - enum mlxsw_sp_l3proto proto; u32 tb_id; /* kernel fib table id */ - struct mlxsw_sp_lpm_tree *lpm_tree; - struct mlxsw_sp_fib *fib; + unsigned int rif_count; + struct mlxsw_sp_fib *fib4; }; enum mlxsw_sp_span_type { @@ -269,6 +246,7 @@ struct mlxsw_sp_router { }; struct mlxsw_sp_acl; +struct mlxsw_sp_counter_pool; struct mlxsw_sp { struct { @@ -304,6 +282,7 @@ struct mlxsw_sp { DECLARE_BITMAP(usage, MLXSW_SP_KVD_LINEAR_SIZE); } kvdl; + struct mlxsw_sp_counter_pool *counter_pool; struct { struct mlxsw_sp_span_entry *entries; int entries_count; @@ -386,6 +365,7 @@ struct mlxsw_sp_port { }; bool mlxsw_sp_port_dev_check(const struct net_device *dev); +struct mlxsw_sp *mlxsw_sp_lower_get(struct net_device *dev); struct mlxsw_sp_port *mlxsw_sp_port_lower_dev_hold(struct net_device *dev); void mlxsw_sp_port_dev_put(struct mlxsw_sp_port *mlxsw_sp_port); @@ -497,19 +477,6 @@ mlxsw_sp_vfid_find(const struct mlxsw_sp *mlxsw_sp, return NULL; } -static inline struct mlxsw_sp_rif * -mlxsw_sp_rif_find_by_dev(const struct mlxsw_sp *mlxsw_sp, - const struct net_device *dev) -{ - int i; - - for (i = 0; i < MLXSW_CORE_RES_GET(mlxsw_sp->core, MAX_RIFS); i++) - if (mlxsw_sp->rifs[i] && mlxsw_sp->rifs[i]->dev == dev) - return mlxsw_sp->rifs[i]; - - return NULL; -} - enum mlxsw_sp_flood_table { MLXSW_SP_FLOOD_TABLE_UC, MLXSW_SP_FLOOD_TABLE_BC, @@ -570,8 +537,6 @@ int mlxsw_sp_rif_fdb_op(struct mlxsw_sp *mlxsw_sp, const char *mac, u16 fid, bool adding); struct mlxsw_sp_fid *mlxsw_sp_fid_create(struct mlxsw_sp *mlxsw_sp, u16 fid); void mlxsw_sp_fid_destroy(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_fid *f); -void mlxsw_sp_rif_bridge_destroy(struct mlxsw_sp *mlxsw_sp, - struct mlxsw_sp_rif *r); int mlxsw_sp_port_ets_set(struct mlxsw_sp_port *mlxsw_sp_port, enum mlxsw_reg_qeec_hr hr, u8 index, u8 next_index, bool dwrr, u8 dwrr_weight); @@ -608,8 +573,19 @@ int mlxsw_sp_router_init(struct mlxsw_sp *mlxsw_sp); void mlxsw_sp_router_fini(struct mlxsw_sp *mlxsw_sp); int mlxsw_sp_router_netevent_event(struct notifier_block *unused, unsigned long event, void *ptr); -void mlxsw_sp_router_rif_gone_sync(struct mlxsw_sp *mlxsw_sp, - struct mlxsw_sp_rif *r); +int mlxsw_sp_netdevice_router_port_event(struct net_device *dev); +int mlxsw_sp_inetaddr_event(struct notifier_block *unused, + unsigned long event, void *ptr); +void mlxsw_sp_rif_bridge_destroy(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_rif *r); +int mlxsw_sp_vport_vrf_join(struct mlxsw_sp_port *mlxsw_sp_vport); +void mlxsw_sp_vport_vrf_leave(struct mlxsw_sp_port *mlxsw_sp_vport); +int mlxsw_sp_port_vrf_join(struct mlxsw_sp_port *mlxsw_sp_port); +void mlxsw_sp_port_vrf_leave(struct mlxsw_sp_port *mlxsw_sp_port); +int mlxsw_sp_bridge_vrf_join(struct mlxsw_sp *mlxsw_sp, + struct net_device *l3_dev); +void mlxsw_sp_bridge_vrf_leave(struct mlxsw_sp *mlxsw_sp, + struct net_device *l3_dev); int mlxsw_sp_kvdl_alloc(struct mlxsw_sp *mlxsw_sp, unsigned int entry_count); void mlxsw_sp_kvdl_free(struct mlxsw_sp *mlxsw_sp, int entry_index); @@ -620,6 +596,8 @@ struct mlxsw_sp_acl_rule_info { unsigned int priority; struct mlxsw_afk_element_values values; struct mlxsw_afa_block *act_block; + unsigned int counter_index; + bool counter_valid; }; enum mlxsw_sp_acl_profile { @@ -639,6 +617,8 @@ struct mlxsw_sp_acl_profile_ops { void *ruleset_priv, void *rule_priv, struct mlxsw_sp_acl_rule_info *rulei); void (*rule_del)(struct mlxsw_sp *mlxsw_sp, void *rule_priv); + int (*rule_activity_get)(struct mlxsw_sp *mlxsw_sp, void *rule_priv, + bool *activity); }; struct mlxsw_sp_acl_ops { @@ -679,6 +659,11 @@ int mlxsw_sp_acl_rulei_act_drop(struct mlxsw_sp_acl_rule_info *rulei); int mlxsw_sp_acl_rulei_act_fwd(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_acl_rule_info *rulei, struct net_device *out_dev); +int mlxsw_sp_acl_rulei_act_vlan(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_acl_rule_info *rulei, + u32 action, u16 vid, u16 proto, u8 prio); +int mlxsw_sp_acl_rulei_act_count(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_acl_rule_info *rulei); struct mlxsw_sp_acl_rule; @@ -698,6 +683,9 @@ mlxsw_sp_acl_rule_lookup(struct mlxsw_sp *mlxsw_sp, unsigned long cookie); struct mlxsw_sp_acl_rule_info * mlxsw_sp_acl_rule_rulei(struct mlxsw_sp_acl_rule *rule); +int mlxsw_sp_acl_rule_get_stats(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_acl_rule *rule, + u64 *packets, u64 *bytes, u64 *last_use); int mlxsw_sp_acl_init(struct mlxsw_sp *mlxsw_sp); void mlxsw_sp_acl_fini(struct mlxsw_sp *mlxsw_sp); @@ -708,5 +696,14 @@ int mlxsw_sp_flower_replace(struct mlxsw_sp_port *mlxsw_sp_port, bool ingress, __be16 protocol, struct tc_cls_flower_offload *f); void mlxsw_sp_flower_destroy(struct mlxsw_sp_port *mlxsw_sp_port, bool ingress, struct tc_cls_flower_offload *f); +int mlxsw_sp_flower_stats(struct mlxsw_sp_port *mlxsw_sp_port, bool ingress, + struct tc_cls_flower_offload *f); +int mlxsw_sp_flow_counter_get(struct mlxsw_sp *mlxsw_sp, + unsigned int counter_index, u64 *packets, + u64 *bytes); +int mlxsw_sp_flow_counter_alloc(struct mlxsw_sp *mlxsw_sp, + unsigned int *p_counter_index); +void mlxsw_sp_flow_counter_free(struct mlxsw_sp *mlxsw_sp, + unsigned int counter_index); #endif diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c index 8a18b3aa70dc..4d6920d45026 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c @@ -39,6 +39,7 @@ #include <linux/string.h> #include <linux/rhashtable.h> #include <linux/netdevice.h> +#include <net/tc_act/tc_vlan.h> #include "reg.h" #include "core.h" @@ -49,10 +50,17 @@ #include "spectrum_acl_flex_keys.h" struct mlxsw_sp_acl { + struct mlxsw_sp *mlxsw_sp; struct mlxsw_afk *afk; struct mlxsw_afa *afa; const struct mlxsw_sp_acl_ops *ops; struct rhashtable ruleset_ht; + struct list_head rules; + struct { + struct delayed_work dw; + unsigned long interval; /* ms */ +#define MLXSW_SP_ACL_RULE_ACTIVITY_UPDATE_PERIOD_MS 1000 + } rule_activity_update; unsigned long priv[0]; /* priv has to be always the last item */ }; @@ -79,9 +87,13 @@ struct mlxsw_sp_acl_ruleset { struct mlxsw_sp_acl_rule { struct rhash_head ht_node; /* Member of rule HT */ + struct list_head list; unsigned long cookie; /* HT key */ struct mlxsw_sp_acl_ruleset *ruleset; struct mlxsw_sp_acl_rule_info *rulei; + u64 last_used; + u64 last_packets; + u64 last_bytes; unsigned long priv[0]; /* priv has to be always the last item */ }; @@ -237,6 +249,27 @@ void mlxsw_sp_acl_ruleset_put(struct mlxsw_sp *mlxsw_sp, mlxsw_sp_acl_ruleset_ref_dec(mlxsw_sp, ruleset); } +static int +mlxsw_sp_acl_rulei_counter_alloc(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_acl_rule_info *rulei) +{ + int err; + + err = mlxsw_sp_flow_counter_alloc(mlxsw_sp, &rulei->counter_index); + if (err) + return err; + rulei->counter_valid = true; + return 0; +} + +static void +mlxsw_sp_acl_rulei_counter_free(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_acl_rule_info *rulei) +{ + rulei->counter_valid = false; + mlxsw_sp_flow_counter_free(mlxsw_sp, rulei->counter_index); +} + struct mlxsw_sp_acl_rule_info * mlxsw_sp_acl_rulei_create(struct mlxsw_sp_acl *acl) { @@ -335,6 +368,41 @@ int mlxsw_sp_acl_rulei_act_fwd(struct mlxsw_sp *mlxsw_sp, local_port, in_port); } +int mlxsw_sp_acl_rulei_act_vlan(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_acl_rule_info *rulei, + u32 action, u16 vid, u16 proto, u8 prio) +{ + u8 ethertype; + + if (action == TCA_VLAN_ACT_MODIFY) { + switch (proto) { + case ETH_P_8021Q: + ethertype = 0; + break; + case ETH_P_8021AD: + ethertype = 1; + break; + default: + dev_err(mlxsw_sp->bus_info->dev, "Unsupported VLAN protocol %#04x\n", + proto); + return -EINVAL; + } + + return mlxsw_afa_block_append_vlan_modify(rulei->act_block, + vid, prio, ethertype); + } else { + dev_err(mlxsw_sp->bus_info->dev, "Unsupported VLAN action\n"); + return -EINVAL; + } +} + +int mlxsw_sp_acl_rulei_act_count(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_acl_rule_info *rulei) +{ + return mlxsw_afa_block_append_counter(rulei->act_block, + rulei->counter_index); +} + struct mlxsw_sp_acl_rule * mlxsw_sp_acl_rule_create(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_acl_ruleset *ruleset, @@ -358,8 +426,14 @@ mlxsw_sp_acl_rule_create(struct mlxsw_sp *mlxsw_sp, err = PTR_ERR(rule->rulei); goto err_rulei_create; } + + err = mlxsw_sp_acl_rulei_counter_alloc(mlxsw_sp, rule->rulei); + if (err) + goto err_counter_alloc; return rule; +err_counter_alloc: + mlxsw_sp_acl_rulei_destroy(rule->rulei); err_rulei_create: kfree(rule); err_alloc: @@ -372,6 +446,7 @@ void mlxsw_sp_acl_rule_destroy(struct mlxsw_sp *mlxsw_sp, { struct mlxsw_sp_acl_ruleset *ruleset = rule->ruleset; + mlxsw_sp_acl_rulei_counter_free(mlxsw_sp, rule->rulei); mlxsw_sp_acl_rulei_destroy(rule->rulei); kfree(rule); mlxsw_sp_acl_ruleset_ref_dec(mlxsw_sp, ruleset); @@ -393,6 +468,7 @@ int mlxsw_sp_acl_rule_add(struct mlxsw_sp *mlxsw_sp, if (err) goto err_rhashtable_insert; + list_add_tail(&rule->list, &mlxsw_sp->acl->rules); return 0; err_rhashtable_insert: @@ -406,6 +482,7 @@ void mlxsw_sp_acl_rule_del(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_acl_ruleset *ruleset = rule->ruleset; const struct mlxsw_sp_acl_profile_ops *ops = ruleset->ht_key.ops; + list_del(&rule->list); rhashtable_remove_fast(&ruleset->rule_ht, &rule->ht_node, mlxsw_sp_acl_rule_ht_params); ops->rule_del(mlxsw_sp, rule->priv); @@ -426,6 +503,90 @@ mlxsw_sp_acl_rule_rulei(struct mlxsw_sp_acl_rule *rule) return rule->rulei; } +static int mlxsw_sp_acl_rule_activity_update(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_acl_rule *rule) +{ + struct mlxsw_sp_acl_ruleset *ruleset = rule->ruleset; + const struct mlxsw_sp_acl_profile_ops *ops = ruleset->ht_key.ops; + bool active; + int err; + + err = ops->rule_activity_get(mlxsw_sp, rule->priv, &active); + if (err) + return err; + if (active) + rule->last_used = jiffies; + return 0; +} + +static int mlxsw_sp_acl_rules_activity_update(struct mlxsw_sp_acl *acl) +{ + struct mlxsw_sp_acl_rule *rule; + int err; + + /* Protect internal structures from changes */ + rtnl_lock(); + list_for_each_entry(rule, &acl->rules, list) { + err = mlxsw_sp_acl_rule_activity_update(acl->mlxsw_sp, + rule); + if (err) + goto err_rule_update; + } + rtnl_unlock(); + return 0; + +err_rule_update: + rtnl_unlock(); + return err; +} + +static void mlxsw_sp_acl_rule_activity_work_schedule(struct mlxsw_sp_acl *acl) +{ + unsigned long interval = acl->rule_activity_update.interval; + + mlxsw_core_schedule_dw(&acl->rule_activity_update.dw, + msecs_to_jiffies(interval)); +} + +static void mlxsw_sp_acl_rul_activity_update_work(struct work_struct *work) +{ + struct mlxsw_sp_acl *acl = container_of(work, struct mlxsw_sp_acl, + rule_activity_update.dw.work); + int err; + + err = mlxsw_sp_acl_rules_activity_update(acl); + if (err) + dev_err(acl->mlxsw_sp->bus_info->dev, "Could not update acl activity"); + + mlxsw_sp_acl_rule_activity_work_schedule(acl); +} + +int mlxsw_sp_acl_rule_get_stats(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_acl_rule *rule, + u64 *packets, u64 *bytes, u64 *last_use) + +{ + struct mlxsw_sp_acl_rule_info *rulei; + u64 current_packets; + u64 current_bytes; + int err; + + rulei = mlxsw_sp_acl_rule_rulei(rule); + err = mlxsw_sp_flow_counter_get(mlxsw_sp, rulei->counter_index, + ¤t_packets, ¤t_bytes); + if (err) + return err; + + *packets = current_packets - rule->last_packets; + *bytes = current_bytes - rule->last_bytes; + *last_use = rule->last_used; + + rule->last_bytes = current_bytes; + rule->last_packets = current_packets; + + return 0; +} + #define MLXSW_SP_KDVL_ACT_EXT_SIZE 1 static int mlxsw_sp_act_kvdl_set_add(void *priv, u32 *p_kvdl_index, @@ -518,7 +679,7 @@ int mlxsw_sp_acl_init(struct mlxsw_sp *mlxsw_sp) if (!acl) return -ENOMEM; mlxsw_sp->acl = acl; - + acl->mlxsw_sp = mlxsw_sp; acl->afk = mlxsw_afk_create(MLXSW_CORE_RES_GET(mlxsw_sp->core, ACL_FLEX_KEYS), mlxsw_sp_afk_blocks, @@ -541,11 +702,18 @@ int mlxsw_sp_acl_init(struct mlxsw_sp *mlxsw_sp) if (err) goto err_rhashtable_init; + INIT_LIST_HEAD(&acl->rules); err = acl_ops->init(mlxsw_sp, acl->priv); if (err) goto err_acl_ops_init; acl->ops = acl_ops; + + /* Create the delayed work for the rule activity_update */ + INIT_DELAYED_WORK(&acl->rule_activity_update.dw, + mlxsw_sp_acl_rul_activity_update_work); + acl->rule_activity_update.interval = MLXSW_SP_ACL_RULE_ACTIVITY_UPDATE_PERIOD_MS; + mlxsw_core_schedule_dw(&acl->rule_activity_update.dw, 0); return 0; err_acl_ops_init: @@ -564,7 +732,9 @@ void mlxsw_sp_acl_fini(struct mlxsw_sp *mlxsw_sp) struct mlxsw_sp_acl *acl = mlxsw_sp->acl; const struct mlxsw_sp_acl_ops *acl_ops = acl->ops; + cancel_delayed_work_sync(&mlxsw_sp->acl->rule_activity_update.dw); acl_ops->fini(mlxsw_sp, acl->priv); + WARN_ON(!list_empty(&acl->rules)); rhashtable_destroy(&acl->ruleset_ht); mlxsw_afa_destroy(acl->afa); mlxsw_afk_destroy(acl->afk); diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_keys.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_keys.h index 82b81cf7f4a7..af7b7bad48df 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_keys.h +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_keys.h @@ -39,11 +39,15 @@ static struct mlxsw_afk_element_inst mlxsw_sp_afk_element_info_l2_dmac[] = { MLXSW_AFK_ELEMENT_INST_BUF(DMAC, 0x00, 6), + MLXSW_AFK_ELEMENT_INST_U32(PCP, 0x08, 13, 3), + MLXSW_AFK_ELEMENT_INST_U32(VID, 0x08, 0, 12), MLXSW_AFK_ELEMENT_INST_U32(SRC_SYS_PORT, 0x0C, 0, 16), }; static struct mlxsw_afk_element_inst mlxsw_sp_afk_element_info_l2_smac[] = { MLXSW_AFK_ELEMENT_INST_BUF(SMAC, 0x00, 6), + MLXSW_AFK_ELEMENT_INST_U32(PCP, 0x08, 13, 3), + MLXSW_AFK_ELEMENT_INST_U32(VID, 0x08, 0, 12), MLXSW_AFK_ELEMENT_INST_U32(SRC_SYS_PORT, 0x0C, 0, 16), }; @@ -65,6 +69,8 @@ static struct mlxsw_afk_element_inst mlxsw_sp_afk_element_info_ipv4_dip[] = { }; static struct mlxsw_afk_element_inst mlxsw_sp_afk_element_info_ipv4_ex[] = { + MLXSW_AFK_ELEMENT_INST_U32(VID, 0x00, 0, 12), + MLXSW_AFK_ELEMENT_INST_U32(PCP, 0x08, 29, 3), MLXSW_AFK_ELEMENT_INST_U32(SRC_L4_PORT, 0x08, 0, 16), MLXSW_AFK_ELEMENT_INST_U32(DST_L4_PORT, 0x0C, 0, 16), }; diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c index 7382832215fa..3a24289979d9 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c @@ -561,6 +561,24 @@ mlxsw_sp_acl_tcam_region_entry_remove(struct mlxsw_sp *mlxsw_sp, mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ptce2), ptce2_pl); } +static int +mlxsw_sp_acl_tcam_region_entry_activity_get(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_acl_tcam_region *region, + unsigned int offset, + bool *activity) +{ + char ptce2_pl[MLXSW_REG_PTCE2_LEN]; + int err; + + mlxsw_reg_ptce2_pack(ptce2_pl, true, MLXSW_REG_PTCE2_OP_QUERY_CLEAR_ON_READ, + region->tcam_region_info, offset); + err = mlxsw_reg_query(mlxsw_sp->core, MLXSW_REG(ptce2), ptce2_pl); + if (err) + return err; + *activity = mlxsw_reg_ptce2_a_get(ptce2_pl); + return 0; +} + #define MLXSW_SP_ACL_TCAM_CATCHALL_PRIO (~0U) static int @@ -940,6 +958,19 @@ static void mlxsw_sp_acl_tcam_entry_del(struct mlxsw_sp *mlxsw_sp, mlxsw_sp_acl_tcam_chunk_put(mlxsw_sp, chunk); } +static int +mlxsw_sp_acl_tcam_entry_activity_get(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_acl_tcam_entry *entry, + bool *activity) +{ + struct mlxsw_sp_acl_tcam_chunk *chunk = entry->chunk; + struct mlxsw_sp_acl_tcam_region *region = chunk->region; + + return mlxsw_sp_acl_tcam_region_entry_activity_get(mlxsw_sp, region, + entry->parman_item.index, + activity); +} + static const enum mlxsw_afk_element mlxsw_sp_acl_tcam_pattern_ipv4[] = { MLXSW_AFK_ELEMENT_SRC_SYS_PORT, MLXSW_AFK_ELEMENT_DMAC, @@ -950,6 +981,8 @@ static const enum mlxsw_afk_element mlxsw_sp_acl_tcam_pattern_ipv4[] = { MLXSW_AFK_ELEMENT_DST_IP4, MLXSW_AFK_ELEMENT_DST_L4_PORT, MLXSW_AFK_ELEMENT_SRC_L4_PORT, + MLXSW_AFK_ELEMENT_VID, + MLXSW_AFK_ELEMENT_PCP, }; static const enum mlxsw_afk_element mlxsw_sp_acl_tcam_pattern_ipv6[] = { @@ -1046,6 +1079,16 @@ mlxsw_sp_acl_tcam_flower_rule_del(struct mlxsw_sp *mlxsw_sp, void *rule_priv) mlxsw_sp_acl_tcam_entry_del(mlxsw_sp, &rule->entry); } +static int +mlxsw_sp_acl_tcam_flower_rule_activity_get(struct mlxsw_sp *mlxsw_sp, + void *rule_priv, bool *activity) +{ + struct mlxsw_sp_acl_tcam_flower_rule *rule = rule_priv; + + return mlxsw_sp_acl_tcam_entry_activity_get(mlxsw_sp, &rule->entry, + activity); +} + static const struct mlxsw_sp_acl_profile_ops mlxsw_sp_acl_tcam_flower_ops = { .ruleset_priv_size = sizeof(struct mlxsw_sp_acl_tcam_flower_ruleset), .ruleset_add = mlxsw_sp_acl_tcam_flower_ruleset_add, @@ -1055,6 +1098,7 @@ static const struct mlxsw_sp_acl_profile_ops mlxsw_sp_acl_tcam_flower_ops = { .rule_priv_size = sizeof(struct mlxsw_sp_acl_tcam_flower_rule), .rule_add = mlxsw_sp_acl_tcam_flower_rule_add, .rule_del = mlxsw_sp_acl_tcam_flower_rule_del, + .rule_activity_get = mlxsw_sp_acl_tcam_flower_rule_activity_get, }; static const struct mlxsw_sp_acl_profile_ops * diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_cnt.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_cnt.c new file mode 100644 index 000000000000..1631e01908c0 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_cnt.c @@ -0,0 +1,198 @@ +/* + * drivers/net/ethernet/mellanox/mlxsw/spectrum_cnt.c + * Copyright (c) 2017 Mellanox Technologies. All rights reserved. + * Copyright (c) 2017 Arkadi Sharshevsky <[email protected]> + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions are met: + * + * 1. Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * 2. Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * 3. Neither the names of the copyright holders nor the names of its + * contributors may be used to endorse or promote products derived from + * this software without specific prior written permission. + * + * Alternatively, this software may be distributed under the terms of the + * GNU General Public License ("GPL") version 2 as published by the Free + * Software Foundation. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" + * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE + * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE + * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE + * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR + * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF + * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS + * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN + * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) + * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE + * POSSIBILITY OF SUCH DAMAGE. + */ + +#include <linux/kernel.h> +#include <linux/bitops.h> + +#include "spectrum_cnt.h" + +#define MLXSW_SP_COUNTER_POOL_BANK_SIZE 4096 + +struct mlxsw_sp_counter_sub_pool { + unsigned int base_index; + unsigned int size; + unsigned int entry_size; + unsigned int bank_count; +}; + +struct mlxsw_sp_counter_pool { + unsigned int pool_size; + unsigned long *usage; /* Usage bitmap */ + struct mlxsw_sp_counter_sub_pool *sub_pools; +}; + +static struct mlxsw_sp_counter_sub_pool mlxsw_sp_counter_sub_pools[] = { + [MLXSW_SP_COUNTER_SUB_POOL_FLOW] = { + .bank_count = 6, + }, +}; + +static int mlxsw_sp_counter_pool_validate(struct mlxsw_sp *mlxsw_sp) +{ + unsigned int total_bank_config = 0; + unsigned int pool_size; + int i; + + pool_size = MLXSW_CORE_RES_GET(mlxsw_sp->core, COUNTER_POOL_SIZE); + /* Check config is valid, no bank over subscription */ + for (i = 0; i < ARRAY_SIZE(mlxsw_sp_counter_sub_pools); i++) + total_bank_config += mlxsw_sp_counter_sub_pools[i].bank_count; + if (total_bank_config > pool_size / MLXSW_SP_COUNTER_POOL_BANK_SIZE + 1) + return -EINVAL; + return 0; +} + +static int mlxsw_sp_counter_sub_pools_prepare(struct mlxsw_sp *mlxsw_sp) +{ + struct mlxsw_sp_counter_sub_pool *sub_pool; + + /* Prepare generic flow pool*/ + sub_pool = &mlxsw_sp_counter_sub_pools[MLXSW_SP_COUNTER_SUB_POOL_FLOW]; + if (!MLXSW_CORE_RES_VALID(mlxsw_sp->core, COUNTER_SIZE_PACKETS_BYTES)) + return -EIO; + sub_pool->entry_size = MLXSW_CORE_RES_GET(mlxsw_sp->core, + COUNTER_SIZE_PACKETS_BYTES); + return 0; +} + +int mlxsw_sp_counter_pool_init(struct mlxsw_sp *mlxsw_sp) +{ + struct mlxsw_sp_counter_sub_pool *sub_pool; + struct mlxsw_sp_counter_pool *pool; + unsigned int base_index; + unsigned int map_size; + int i; + int err; + + if (!MLXSW_CORE_RES_VALID(mlxsw_sp->core, COUNTER_POOL_SIZE)) + return -EIO; + + err = mlxsw_sp_counter_pool_validate(mlxsw_sp); + if (err) + return err; + + err = mlxsw_sp_counter_sub_pools_prepare(mlxsw_sp); + if (err) + return err; + + pool = kzalloc(sizeof(*pool), GFP_KERNEL); + if (!pool) + return -ENOMEM; + + pool->pool_size = MLXSW_CORE_RES_GET(mlxsw_sp->core, COUNTER_POOL_SIZE); + map_size = BITS_TO_LONGS(pool->pool_size) * sizeof(unsigned long); + + pool->usage = kzalloc(map_size, GFP_KERNEL); + if (!pool->usage) { + err = -ENOMEM; + goto err_usage_alloc; + } + + pool->sub_pools = mlxsw_sp_counter_sub_pools; + /* Allocation is based on bank count which should be + * specified for each sub pool statically. + */ + base_index = 0; + for (i = 0; i < ARRAY_SIZE(mlxsw_sp_counter_sub_pools); i++) { + sub_pool = &pool->sub_pools[i]; + sub_pool->size = sub_pool->bank_count * + MLXSW_SP_COUNTER_POOL_BANK_SIZE; + sub_pool->base_index = base_index; + base_index += sub_pool->size; + /* The last bank can't be fully used */ + if (sub_pool->base_index + sub_pool->size > pool->pool_size) + sub_pool->size = pool->pool_size - sub_pool->base_index; + } + + mlxsw_sp->counter_pool = pool; + return 0; + +err_usage_alloc: + kfree(pool); + return err; +} + +void mlxsw_sp_counter_pool_fini(struct mlxsw_sp *mlxsw_sp) +{ + struct mlxsw_sp_counter_pool *pool = mlxsw_sp->counter_pool; + + WARN_ON(find_first_bit(pool->usage, pool->pool_size) != + pool->pool_size); + kfree(pool->usage); + kfree(pool); +} + +int mlxsw_sp_counter_alloc(struct mlxsw_sp *mlxsw_sp, + enum mlxsw_sp_counter_sub_pool_id sub_pool_id, + unsigned int *p_counter_index) +{ + struct mlxsw_sp_counter_pool *pool = mlxsw_sp->counter_pool; + struct mlxsw_sp_counter_sub_pool *sub_pool; + unsigned int entry_index; + unsigned int stop_index; + int i; + + sub_pool = &mlxsw_sp_counter_sub_pools[sub_pool_id]; + stop_index = sub_pool->base_index + sub_pool->size; + entry_index = sub_pool->base_index; + + entry_index = find_next_zero_bit(pool->usage, stop_index, entry_index); + if (entry_index == stop_index) + return -ENOBUFS; + /* The sub-pools can contain non-integer number of entries + * so we must check for overflow + */ + if (entry_index + sub_pool->entry_size > stop_index) + return -ENOBUFS; + for (i = 0; i < sub_pool->entry_size; i++) + __set_bit(entry_index + i, pool->usage); + + *p_counter_index = entry_index; + return 0; +} + +void mlxsw_sp_counter_free(struct mlxsw_sp *mlxsw_sp, + enum mlxsw_sp_counter_sub_pool_id sub_pool_id, + unsigned int counter_index) +{ + struct mlxsw_sp_counter_pool *pool = mlxsw_sp->counter_pool; + struct mlxsw_sp_counter_sub_pool *sub_pool; + int i; + + if (WARN_ON(counter_index >= pool->pool_size)) + return; + sub_pool = &mlxsw_sp_counter_sub_pools[sub_pool_id]; + for (i = 0; i < sub_pool->entry_size; i++) + __clear_bit(counter_index + i, pool->usage); +} diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_cnt.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum_cnt.h new file mode 100644 index 000000000000..031bc4abbe2d --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_cnt.h @@ -0,0 +1,53 @@ +/* + * drivers/net/ethernet/mellanox/mlxsw/spectrum_cnt.h + * Copyright (c) 2017 Mellanox Technologies. All rights reserved. + * Copyright (c) 2017 Arkadi Sharshevsky <[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_CNT_H +#define _MLXSW_SPECTRUM_CNT_H + +#include "spectrum.h" + +enum mlxsw_sp_counter_sub_pool_id { + MLXSW_SP_COUNTER_SUB_POOL_FLOW, +}; + +int mlxsw_sp_counter_alloc(struct mlxsw_sp *mlxsw_sp, + enum mlxsw_sp_counter_sub_pool_id sub_pool_id, + unsigned int *p_counter_index); +void mlxsw_sp_counter_free(struct mlxsw_sp *mlxsw_sp, + enum mlxsw_sp_counter_sub_pool_id sub_pool_id, + unsigned int counter_index); +int mlxsw_sp_counter_pool_init(struct mlxsw_sp *mlxsw_sp); +void mlxsw_sp_counter_pool_fini(struct mlxsw_sp *mlxsw_sp); + +#endif diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c index 22ab42925377..e724c6266247 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c @@ -39,6 +39,7 @@ #include <net/pkt_cls.h> #include <net/tc_act/tc_gact.h> #include <net/tc_act/tc_mirred.h> +#include <net/tc_act/tc_vlan.h> #include "spectrum.h" #include "core_acl_flex_keys.h" @@ -55,6 +56,11 @@ static int mlxsw_sp_flower_parse_actions(struct mlxsw_sp *mlxsw_sp, if (tc_no_actions(exts)) return 0; + /* Count action is inserted first */ + err = mlxsw_sp_acl_rulei_act_count(mlxsw_sp, rulei); + if (err) + return err; + tcf_exts_to_list(exts, &actions); list_for_each_entry(a, &actions, list) { if (is_tcf_gact_shot(a)) { @@ -73,6 +79,15 @@ static int mlxsw_sp_flower_parse_actions(struct mlxsw_sp *mlxsw_sp, out_dev); if (err) return err; + } else if (is_tcf_vlan(a)) { + u16 proto = be16_to_cpu(tcf_vlan_push_proto(a)); + u32 action = tcf_vlan_action(a); + u8 prio = tcf_vlan_push_prio(a); + u16 vid = tcf_vlan_push_vid(a); + + return mlxsw_sp_acl_rulei_act_vlan(mlxsw_sp, rulei, + action, vid, + proto, prio); } else { dev_err(mlxsw_sp->bus_info->dev, "Unsupported action\n"); return -EOPNOTSUPP; @@ -173,7 +188,8 @@ static int mlxsw_sp_flower_parse(struct mlxsw_sp *mlxsw_sp, BIT(FLOW_DISSECTOR_KEY_ETH_ADDRS) | BIT(FLOW_DISSECTOR_KEY_IPV4_ADDRS) | BIT(FLOW_DISSECTOR_KEY_IPV6_ADDRS) | - BIT(FLOW_DISSECTOR_KEY_PORTS))) { + BIT(FLOW_DISSECTOR_KEY_PORTS) | + BIT(FLOW_DISSECTOR_KEY_VLAN))) { dev_err(mlxsw_sp->bus_info->dev, "Unsupported key\n"); return -EOPNOTSUPP; } @@ -234,6 +250,27 @@ static int mlxsw_sp_flower_parse(struct mlxsw_sp *mlxsw_sp, sizeof(key->src)); } + if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_VLAN)) { + struct flow_dissector_key_vlan *key = + skb_flow_dissector_target(f->dissector, + FLOW_DISSECTOR_KEY_VLAN, + f->key); + struct flow_dissector_key_vlan *mask = + skb_flow_dissector_target(f->dissector, + FLOW_DISSECTOR_KEY_VLAN, + f->mask); + if (mask->vlan_id != 0) + mlxsw_sp_acl_rulei_keymask_u32(rulei, + MLXSW_AFK_ELEMENT_VID, + key->vlan_id, + mask->vlan_id); + if (mask->vlan_priority != 0) + mlxsw_sp_acl_rulei_keymask_u32(rulei, + MLXSW_AFK_ELEMENT_PCP, + key->vlan_priority, + mask->vlan_priority); + } + if (addr_type == FLOW_DISSECTOR_KEY_IPV4_ADDRS) mlxsw_sp_flower_parse_ipv4(rulei, f); @@ -303,14 +340,58 @@ void mlxsw_sp_flower_destroy(struct mlxsw_sp_port *mlxsw_sp_port, bool ingress, ruleset = mlxsw_sp_acl_ruleset_get(mlxsw_sp, mlxsw_sp_port->dev, ingress, MLXSW_SP_ACL_PROFILE_FLOWER); - if (WARN_ON(IS_ERR(ruleset))) + if (IS_ERR(ruleset)) return; rule = mlxsw_sp_acl_rule_lookup(mlxsw_sp, ruleset, f->cookie); - if (!WARN_ON(!rule)) { + if (rule) { mlxsw_sp_acl_rule_del(mlxsw_sp, rule); mlxsw_sp_acl_rule_destroy(mlxsw_sp, rule); } mlxsw_sp_acl_ruleset_put(mlxsw_sp, ruleset); } + +int mlxsw_sp_flower_stats(struct mlxsw_sp_port *mlxsw_sp_port, bool ingress, + struct tc_cls_flower_offload *f) +{ + struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp; + struct mlxsw_sp_acl_ruleset *ruleset; + struct mlxsw_sp_acl_rule *rule; + struct tc_action *a; + LIST_HEAD(actions); + u64 packets; + u64 lastuse; + u64 bytes; + int err; + + ruleset = mlxsw_sp_acl_ruleset_get(mlxsw_sp, mlxsw_sp_port->dev, + ingress, + MLXSW_SP_ACL_PROFILE_FLOWER); + if (WARN_ON(IS_ERR(ruleset))) + return -EINVAL; + + rule = mlxsw_sp_acl_rule_lookup(mlxsw_sp, ruleset, f->cookie); + if (!rule) + return -EINVAL; + + err = mlxsw_sp_acl_rule_get_stats(mlxsw_sp, rule, &bytes, &packets, + &lastuse); + if (err) + goto err_rule_get_stats; + + preempt_disable(); + + tcf_exts_to_list(f->exts, &actions); + list_for_each_entry(a, &actions, list) + tcf_action_stats_update(a, bytes, packets, lastuse); + + preempt_enable(); + + mlxsw_sp_acl_ruleset_put(mlxsw_sp, ruleset); + return 0; + +err_rule_get_stats: + mlxsw_sp_acl_ruleset_put(mlxsw_sp, ruleset); + return err; +} diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c index bd8de6b9be71..488bc1fd7868 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c @@ -41,15 +41,33 @@ #include <linux/in6.h> #include <linux/notifier.h> #include <linux/inetdevice.h> +#include <linux/netdevice.h> #include <net/netevent.h> #include <net/neighbour.h> #include <net/arp.h> #include <net/ip_fib.h> +#include <net/fib_rules.h> +#include <net/l3mdev.h> #include "spectrum.h" #include "core.h" #include "reg.h" +struct mlxsw_sp_rif { + struct list_head nexthop_list; + struct list_head neigh_list; + struct net_device *dev; + struct mlxsw_sp_fid *f; + unsigned char addr[ETH_ALEN]; + int mtu; + u16 rif; + u16 vr_id; +}; + +static struct mlxsw_sp_rif * +mlxsw_sp_rif_find_by_dev(const struct mlxsw_sp *mlxsw_sp, + const struct net_device *dev); + #define mlxsw_sp_prefix_usage_for_each(prefix, prefix_usage) \ for_each_set_bit(prefix, (prefix_usage)->b, MLXSW_SP_PREFIX_COUNT) @@ -89,12 +107,6 @@ mlxsw_sp_prefix_usage_cpy(struct mlxsw_sp_prefix_usage *prefix_usage1, } static void -mlxsw_sp_prefix_usage_zero(struct mlxsw_sp_prefix_usage *prefix_usage) -{ - memset(prefix_usage, 0, sizeof(*prefix_usage)); -} - -static void mlxsw_sp_prefix_usage_set(struct mlxsw_sp_prefix_usage *prefix_usage, unsigned char prefix_len) { @@ -125,7 +137,7 @@ struct mlxsw_sp_fib_node { struct list_head entry_list; struct list_head list; struct rhash_head ht_node; - struct mlxsw_sp_vr *vr; + struct mlxsw_sp_fib *fib; struct mlxsw_sp_fib_key key; }; @@ -149,13 +161,17 @@ struct mlxsw_sp_fib_entry { struct mlxsw_sp_fib { struct rhashtable ht; struct list_head node_list; + struct mlxsw_sp_vr *vr; + struct mlxsw_sp_lpm_tree *lpm_tree; unsigned long prefix_ref_count[MLXSW_SP_PREFIX_COUNT]; struct mlxsw_sp_prefix_usage prefix_usage; + enum mlxsw_sp_l3proto proto; }; static const struct rhashtable_params mlxsw_sp_fib_ht_params; -static struct mlxsw_sp_fib *mlxsw_sp_fib_create(void) +static struct mlxsw_sp_fib *mlxsw_sp_fib_create(struct mlxsw_sp_vr *vr, + enum mlxsw_sp_l3proto proto) { struct mlxsw_sp_fib *fib; int err; @@ -167,6 +183,8 @@ static struct mlxsw_sp_fib *mlxsw_sp_fib_create(void) if (err) goto err_rhashtable_init; INIT_LIST_HEAD(&fib->node_list); + fib->proto = proto; + fib->vr = vr; return fib; err_rhashtable_init: @@ -177,24 +195,21 @@ err_rhashtable_init: static void mlxsw_sp_fib_destroy(struct mlxsw_sp_fib *fib) { WARN_ON(!list_empty(&fib->node_list)); + WARN_ON(fib->lpm_tree); rhashtable_destroy(&fib->ht); kfree(fib); } static struct mlxsw_sp_lpm_tree * -mlxsw_sp_lpm_tree_find_unused(struct mlxsw_sp *mlxsw_sp, bool one_reserved) +mlxsw_sp_lpm_tree_find_unused(struct mlxsw_sp *mlxsw_sp) { static struct mlxsw_sp_lpm_tree *lpm_tree; int i; for (i = 0; i < MLXSW_SP_LPM_TREE_COUNT; i++) { lpm_tree = &mlxsw_sp->router.lpm_trees[i]; - if (lpm_tree->ref_count == 0) { - if (one_reserved) - one_reserved = false; - else - return lpm_tree; - } + if (lpm_tree->ref_count == 0) + return lpm_tree; } return NULL; } @@ -248,12 +263,12 @@ mlxsw_sp_lpm_tree_left_struct_set(struct mlxsw_sp *mlxsw_sp, static struct mlxsw_sp_lpm_tree * mlxsw_sp_lpm_tree_create(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_prefix_usage *prefix_usage, - enum mlxsw_sp_l3proto proto, bool one_reserved) + enum mlxsw_sp_l3proto proto) { struct mlxsw_sp_lpm_tree *lpm_tree; int err; - lpm_tree = mlxsw_sp_lpm_tree_find_unused(mlxsw_sp, one_reserved); + lpm_tree = mlxsw_sp_lpm_tree_find_unused(mlxsw_sp); if (!lpm_tree) return ERR_PTR(-EBUSY); lpm_tree->proto = proto; @@ -283,7 +298,7 @@ static int mlxsw_sp_lpm_tree_destroy(struct mlxsw_sp *mlxsw_sp, static struct mlxsw_sp_lpm_tree * mlxsw_sp_lpm_tree_get(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_prefix_usage *prefix_usage, - enum mlxsw_sp_l3proto proto, bool one_reserved) + enum mlxsw_sp_l3proto proto) { struct mlxsw_sp_lpm_tree *lpm_tree; int i; @@ -297,7 +312,7 @@ mlxsw_sp_lpm_tree_get(struct mlxsw_sp *mlxsw_sp, goto inc_ref_count; } lpm_tree = mlxsw_sp_lpm_tree_create(mlxsw_sp, prefix_usage, - proto, one_reserved); + proto); if (IS_ERR(lpm_tree)) return lpm_tree; @@ -325,6 +340,11 @@ static void mlxsw_sp_lpm_init(struct mlxsw_sp *mlxsw_sp) } } +static bool mlxsw_sp_vr_is_used(const struct mlxsw_sp_vr *vr) +{ + return !!vr->fib4; +} + static struct mlxsw_sp_vr *mlxsw_sp_vr_find_unused(struct mlxsw_sp *mlxsw_sp) { struct mlxsw_sp_vr *vr; @@ -332,31 +352,31 @@ static struct mlxsw_sp_vr *mlxsw_sp_vr_find_unused(struct mlxsw_sp *mlxsw_sp) for (i = 0; i < MLXSW_CORE_RES_GET(mlxsw_sp->core, MAX_VRS); i++) { vr = &mlxsw_sp->router.vrs[i]; - if (!vr->used) + if (!mlxsw_sp_vr_is_used(vr)) return vr; } return NULL; } static int mlxsw_sp_vr_lpm_tree_bind(struct mlxsw_sp *mlxsw_sp, - struct mlxsw_sp_vr *vr) + const struct mlxsw_sp_fib *fib) { char raltb_pl[MLXSW_REG_RALTB_LEN]; - mlxsw_reg_raltb_pack(raltb_pl, vr->id, - (enum mlxsw_reg_ralxx_protocol) vr->proto, - vr->lpm_tree->id); + mlxsw_reg_raltb_pack(raltb_pl, fib->vr->id, + (enum mlxsw_reg_ralxx_protocol) fib->proto, + fib->lpm_tree->id); return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(raltb), raltb_pl); } static int mlxsw_sp_vr_lpm_tree_unbind(struct mlxsw_sp *mlxsw_sp, - struct mlxsw_sp_vr *vr) + const struct mlxsw_sp_fib *fib) { char raltb_pl[MLXSW_REG_RALTB_LEN]; /* Bind to tree 0 which is default */ - mlxsw_reg_raltb_pack(raltb_pl, vr->id, - (enum mlxsw_reg_ralxx_protocol) vr->proto, 0); + mlxsw_reg_raltb_pack(raltb_pl, fib->vr->id, + (enum mlxsw_reg_ralxx_protocol) fib->proto, 0); return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(raltb), raltb_pl); } @@ -369,8 +389,7 @@ static u32 mlxsw_sp_fix_tb_id(u32 tb_id) } static struct mlxsw_sp_vr *mlxsw_sp_vr_find(struct mlxsw_sp *mlxsw_sp, - u32 tb_id, - enum mlxsw_sp_l3proto proto) + u32 tb_id) { struct mlxsw_sp_vr *vr; int i; @@ -379,69 +398,50 @@ static struct mlxsw_sp_vr *mlxsw_sp_vr_find(struct mlxsw_sp *mlxsw_sp, for (i = 0; i < MLXSW_CORE_RES_GET(mlxsw_sp->core, MAX_VRS); i++) { vr = &mlxsw_sp->router.vrs[i]; - if (vr->used && vr->proto == proto && vr->tb_id == tb_id) + if (mlxsw_sp_vr_is_used(vr) && vr->tb_id == tb_id) return vr; } return NULL; } +static struct mlxsw_sp_fib *mlxsw_sp_vr_fib(const struct mlxsw_sp_vr *vr, + enum mlxsw_sp_l3proto proto) +{ + switch (proto) { + case MLXSW_SP_L3_PROTO_IPV4: + return vr->fib4; + case MLXSW_SP_L3_PROTO_IPV6: + BUG_ON(1); + } + return NULL; +} + static struct mlxsw_sp_vr *mlxsw_sp_vr_create(struct mlxsw_sp *mlxsw_sp, - unsigned char prefix_len, - u32 tb_id, - enum mlxsw_sp_l3proto proto) + u32 tb_id) { - struct mlxsw_sp_prefix_usage req_prefix_usage; - struct mlxsw_sp_lpm_tree *lpm_tree; struct mlxsw_sp_vr *vr; - int err; vr = mlxsw_sp_vr_find_unused(mlxsw_sp); if (!vr) return ERR_PTR(-EBUSY); - vr->fib = mlxsw_sp_fib_create(); - if (IS_ERR(vr->fib)) - return ERR_CAST(vr->fib); - - vr->proto = proto; + vr->fib4 = mlxsw_sp_fib_create(vr, MLXSW_SP_L3_PROTO_IPV4); + if (IS_ERR(vr->fib4)) + return ERR_CAST(vr->fib4); vr->tb_id = tb_id; - mlxsw_sp_prefix_usage_zero(&req_prefix_usage); - mlxsw_sp_prefix_usage_set(&req_prefix_usage, prefix_len); - lpm_tree = mlxsw_sp_lpm_tree_get(mlxsw_sp, &req_prefix_usage, - proto, true); - if (IS_ERR(lpm_tree)) { - err = PTR_ERR(lpm_tree); - goto err_tree_get; - } - vr->lpm_tree = lpm_tree; - err = mlxsw_sp_vr_lpm_tree_bind(mlxsw_sp, vr); - if (err) - goto err_tree_bind; - - vr->used = true; return vr; - -err_tree_bind: - mlxsw_sp_lpm_tree_put(mlxsw_sp, vr->lpm_tree); -err_tree_get: - mlxsw_sp_fib_destroy(vr->fib); - - return ERR_PTR(err); } -static void mlxsw_sp_vr_destroy(struct mlxsw_sp *mlxsw_sp, - struct mlxsw_sp_vr *vr) +static void mlxsw_sp_vr_destroy(struct mlxsw_sp_vr *vr) { - mlxsw_sp_vr_lpm_tree_unbind(mlxsw_sp, vr); - mlxsw_sp_lpm_tree_put(mlxsw_sp, vr->lpm_tree); - mlxsw_sp_fib_destroy(vr->fib); - vr->used = false; + mlxsw_sp_fib_destroy(vr->fib4); + vr->fib4 = NULL; } static int -mlxsw_sp_vr_lpm_tree_check(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_vr *vr, +mlxsw_sp_vr_lpm_tree_check(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_fib *fib, struct mlxsw_sp_prefix_usage *req_prefix_usage) { - struct mlxsw_sp_lpm_tree *lpm_tree = vr->lpm_tree; + struct mlxsw_sp_lpm_tree *lpm_tree = fib->lpm_tree; struct mlxsw_sp_lpm_tree *new_tree; int err; @@ -449,7 +449,7 @@ mlxsw_sp_vr_lpm_tree_check(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_vr *vr, return 0; new_tree = mlxsw_sp_lpm_tree_get(mlxsw_sp, req_prefix_usage, - vr->proto, false); + fib->proto); if (IS_ERR(new_tree)) { /* We failed to get a tree according to the required * prefix usage. However, the current tree might be still good @@ -463,8 +463,8 @@ mlxsw_sp_vr_lpm_tree_check(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_vr *vr, } /* Prevent packet loss by overwriting existing binding */ - vr->lpm_tree = new_tree; - err = mlxsw_sp_vr_lpm_tree_bind(mlxsw_sp, vr); + fib->lpm_tree = new_tree; + err = mlxsw_sp_vr_lpm_tree_bind(mlxsw_sp, fib); if (err) goto err_tree_bind; mlxsw_sp_lpm_tree_put(mlxsw_sp, lpm_tree); @@ -472,53 +472,26 @@ mlxsw_sp_vr_lpm_tree_check(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_vr *vr, return 0; err_tree_bind: - vr->lpm_tree = lpm_tree; + fib->lpm_tree = lpm_tree; mlxsw_sp_lpm_tree_put(mlxsw_sp, new_tree); return err; } -static struct mlxsw_sp_vr *mlxsw_sp_vr_get(struct mlxsw_sp *mlxsw_sp, - unsigned char prefix_len, - u32 tb_id, - enum mlxsw_sp_l3proto proto) +static struct mlxsw_sp_vr *mlxsw_sp_vr_get(struct mlxsw_sp *mlxsw_sp, u32 tb_id) { struct mlxsw_sp_vr *vr; - int err; tb_id = mlxsw_sp_fix_tb_id(tb_id); - vr = mlxsw_sp_vr_find(mlxsw_sp, tb_id, proto); - if (!vr) { - vr = mlxsw_sp_vr_create(mlxsw_sp, prefix_len, tb_id, proto); - if (IS_ERR(vr)) - return vr; - } else { - struct mlxsw_sp_prefix_usage req_prefix_usage; - - mlxsw_sp_prefix_usage_cpy(&req_prefix_usage, - &vr->fib->prefix_usage); - mlxsw_sp_prefix_usage_set(&req_prefix_usage, prefix_len); - /* Need to replace LPM tree in case new prefix is required. */ - err = mlxsw_sp_vr_lpm_tree_check(mlxsw_sp, vr, - &req_prefix_usage); - if (err) - return ERR_PTR(err); - } + vr = mlxsw_sp_vr_find(mlxsw_sp, tb_id); + if (!vr) + vr = mlxsw_sp_vr_create(mlxsw_sp, tb_id); return vr; } -static void mlxsw_sp_vr_put(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_vr *vr) +static void mlxsw_sp_vr_put(struct mlxsw_sp_vr *vr) { - /* Destroy virtual router entity in case the associated FIB is empty - * and allow it to be used for other tables in future. Otherwise, - * check if some prefix usage did not disappear and change tree if - * that is the case. Note that in case new, smaller tree cannot be - * allocated, the original one will be kept being used. - */ - if (mlxsw_sp_prefix_usage_none(&vr->fib->prefix_usage)) - mlxsw_sp_vr_destroy(mlxsw_sp, vr); - else - mlxsw_sp_vr_lpm_tree_check(mlxsw_sp, vr, - &vr->fib->prefix_usage); + if (!vr->rif_count && list_empty(&vr->fib4->node_list)) + mlxsw_sp_vr_destroy(vr); } static int mlxsw_sp_vrs_init(struct mlxsw_sp *mlxsw_sp) @@ -1171,7 +1144,7 @@ mlxsw_sp_nexthop_lookup(struct mlxsw_sp *mlxsw_sp, } static int mlxsw_sp_adj_index_mass_update_vr(struct mlxsw_sp *mlxsw_sp, - struct mlxsw_sp_vr *vr, + const struct mlxsw_sp_fib *fib, u32 adj_index, u16 ecmp_size, u32 new_adj_index, u16 new_ecmp_size) @@ -1179,8 +1152,8 @@ static int mlxsw_sp_adj_index_mass_update_vr(struct mlxsw_sp *mlxsw_sp, char raleu_pl[MLXSW_REG_RALEU_LEN]; mlxsw_reg_raleu_pack(raleu_pl, - (enum mlxsw_reg_ralxx_protocol) vr->proto, vr->id, - adj_index, ecmp_size, new_adj_index, + (enum mlxsw_reg_ralxx_protocol) fib->proto, + fib->vr->id, adj_index, ecmp_size, new_adj_index, new_ecmp_size); return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(raleu), raleu_pl); } @@ -1190,14 +1163,14 @@ static int mlxsw_sp_adj_index_mass_update(struct mlxsw_sp *mlxsw_sp, u32 old_adj_index, u16 old_ecmp_size) { struct mlxsw_sp_fib_entry *fib_entry; - struct mlxsw_sp_vr *vr = NULL; + struct mlxsw_sp_fib *fib = NULL; int err; list_for_each_entry(fib_entry, &nh_grp->fib_list, nexthop_group_node) { - if (vr == fib_entry->fib_node->vr) + if (fib == fib_entry->fib_node->fib) continue; - vr = fib_entry->fib_node->vr; - err = mlxsw_sp_adj_index_mass_update_vr(mlxsw_sp, vr, + fib = fib_entry->fib_node->fib; + err = mlxsw_sp_adj_index_mass_update_vr(mlxsw_sp, fib, old_adj_index, old_ecmp_size, nh_grp->adj_index, @@ -1514,6 +1487,9 @@ static int mlxsw_sp_nexthop_init(struct mlxsw_sp *mlxsw_sp, if (err) return err; + if (!dev) + return 0; + in_dev = __in_dev_get_rtnl(dev); if (in_dev && IN_DEV_IGNORE_ROUTES_WITH_LINKDOWN(in_dev) && fib_nh->nh_flags & RTNH_F_LINKDOWN) @@ -1699,7 +1675,7 @@ static void mlxsw_sp_fib_entry_offload_set(struct mlxsw_sp_fib_entry *fib_entry) { fib_entry->offloaded = true; - switch (fib_entry->fib_node->vr->proto) { + switch (fib_entry->fib_node->fib->proto) { case MLXSW_SP_L3_PROTO_IPV4: fib_info_offload_inc(fib_entry->nh_group->key.fi); break; @@ -1711,7 +1687,7 @@ static void mlxsw_sp_fib_entry_offload_set(struct mlxsw_sp_fib_entry *fib_entry) static void mlxsw_sp_fib_entry_offload_unset(struct mlxsw_sp_fib_entry *fib_entry) { - switch (fib_entry->fib_node->vr->proto) { + switch (fib_entry->fib_node->fib->proto) { case MLXSW_SP_L3_PROTO_IPV4: fib_info_offload_dec(fib_entry->nh_group->key.fi); break; @@ -1751,8 +1727,8 @@ static int mlxsw_sp_fib_entry_op4_remote(struct mlxsw_sp *mlxsw_sp, enum mlxsw_reg_ralue_op op) { char ralue_pl[MLXSW_REG_RALUE_LEN]; + struct mlxsw_sp_fib *fib = fib_entry->fib_node->fib; u32 *p_dip = (u32 *) fib_entry->fib_node->key.addr; - struct mlxsw_sp_vr *vr = fib_entry->fib_node->vr; enum mlxsw_reg_ralue_trap_action trap_action; u16 trap_id = 0; u32 adjacency_index = 0; @@ -1772,8 +1748,8 @@ static int mlxsw_sp_fib_entry_op4_remote(struct mlxsw_sp *mlxsw_sp, } mlxsw_reg_ralue_pack4(ralue_pl, - (enum mlxsw_reg_ralxx_protocol) vr->proto, op, - vr->id, fib_entry->fib_node->key.prefix_len, + (enum mlxsw_reg_ralxx_protocol) fib->proto, op, + fib->vr->id, fib_entry->fib_node->key.prefix_len, *p_dip); mlxsw_reg_ralue_act_remote_pack(ralue_pl, trap_action, trap_id, adjacency_index, ecmp_size); @@ -1785,10 +1761,10 @@ static int mlxsw_sp_fib_entry_op4_local(struct mlxsw_sp *mlxsw_sp, enum mlxsw_reg_ralue_op op) { struct mlxsw_sp_rif *r = fib_entry->nh_group->nh_rif; + struct mlxsw_sp_fib *fib = fib_entry->fib_node->fib; enum mlxsw_reg_ralue_trap_action trap_action; char ralue_pl[MLXSW_REG_RALUE_LEN]; u32 *p_dip = (u32 *) fib_entry->fib_node->key.addr; - struct mlxsw_sp_vr *vr = fib_entry->fib_node->vr; u16 trap_id = 0; u16 rif = 0; @@ -1801,8 +1777,8 @@ static int mlxsw_sp_fib_entry_op4_local(struct mlxsw_sp *mlxsw_sp, } mlxsw_reg_ralue_pack4(ralue_pl, - (enum mlxsw_reg_ralxx_protocol) vr->proto, op, - vr->id, fib_entry->fib_node->key.prefix_len, + (enum mlxsw_reg_ralxx_protocol) fib->proto, op, + fib->vr->id, fib_entry->fib_node->key.prefix_len, *p_dip); mlxsw_reg_ralue_act_local_pack(ralue_pl, trap_action, trap_id, rif); return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ralue), ralue_pl); @@ -1812,13 +1788,13 @@ static int mlxsw_sp_fib_entry_op4_trap(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_fib_entry *fib_entry, enum mlxsw_reg_ralue_op op) { + struct mlxsw_sp_fib *fib = fib_entry->fib_node->fib; char ralue_pl[MLXSW_REG_RALUE_LEN]; u32 *p_dip = (u32 *) fib_entry->fib_node->key.addr; - struct mlxsw_sp_vr *vr = fib_entry->fib_node->vr; mlxsw_reg_ralue_pack4(ralue_pl, - (enum mlxsw_reg_ralxx_protocol) vr->proto, op, - vr->id, fib_entry->fib_node->key.prefix_len, + (enum mlxsw_reg_ralxx_protocol) fib->proto, op, + fib->vr->id, fib_entry->fib_node->key.prefix_len, *p_dip); mlxsw_reg_ralue_act_ip2me_pack(ralue_pl); return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ralue), ralue_pl); @@ -1845,7 +1821,7 @@ static int mlxsw_sp_fib_entry_op(struct mlxsw_sp *mlxsw_sp, { int err = -EINVAL; - switch (fib_entry->fib_node->vr->proto) { + switch (fib_entry->fib_node->fib->proto) { case MLXSW_SP_L3_PROTO_IPV4: err = mlxsw_sp_fib_entry_op4(mlxsw_sp, fib_entry, op); break; @@ -1877,17 +1853,29 @@ mlxsw_sp_fib4_entry_type_set(struct mlxsw_sp *mlxsw_sp, { struct fib_info *fi = fen_info->fi; - if (fen_info->type == RTN_LOCAL || fen_info->type == RTN_BROADCAST) { + switch (fen_info->type) { + case RTN_BROADCAST: /* fall through */ + case RTN_LOCAL: fib_entry->type = MLXSW_SP_FIB_ENTRY_TYPE_TRAP; return 0; - } - if (fen_info->type != RTN_UNICAST) - return -EINVAL; - if (fi->fib_nh->nh_scope != RT_SCOPE_LINK) + case RTN_UNREACHABLE: /* fall through */ + case RTN_BLACKHOLE: /* fall through */ + case RTN_PROHIBIT: + /* Packets hitting these routes need to be trapped, but + * can do so with a lower priority than packets directed + * at the host, so use action type local instead of trap. + */ fib_entry->type = MLXSW_SP_FIB_ENTRY_TYPE_LOCAL; - else - fib_entry->type = MLXSW_SP_FIB_ENTRY_TYPE_REMOTE; - return 0; + return 0; + case RTN_UNICAST: + if (fi->fib_nh->nh_scope != RT_SCOPE_LINK) + fib_entry->type = MLXSW_SP_FIB_ENTRY_TYPE_LOCAL; + else + fib_entry->type = MLXSW_SP_FIB_ENTRY_TYPE_REMOTE; + return 0; + default: + return -EINVAL; + } } static struct mlxsw_sp_fib_entry * @@ -1996,7 +1984,7 @@ mlxsw_sp_fib_node_lookup(struct mlxsw_sp_fib *fib, const void *addr, } static struct mlxsw_sp_fib_node * -mlxsw_sp_fib_node_create(struct mlxsw_sp_vr *vr, const void *addr, +mlxsw_sp_fib_node_create(struct mlxsw_sp_fib *fib, const void *addr, size_t addr_len, unsigned char prefix_len) { struct mlxsw_sp_fib_node *fib_node; @@ -2006,18 +1994,15 @@ mlxsw_sp_fib_node_create(struct mlxsw_sp_vr *vr, const void *addr, return NULL; INIT_LIST_HEAD(&fib_node->entry_list); - list_add(&fib_node->list, &vr->fib->node_list); + list_add(&fib_node->list, &fib->node_list); memcpy(fib_node->key.addr, addr, addr_len); fib_node->key.prefix_len = prefix_len; - mlxsw_sp_fib_node_insert(vr->fib, fib_node); - fib_node->vr = vr; return fib_node; } static void mlxsw_sp_fib_node_destroy(struct mlxsw_sp_fib_node *fib_node) { - mlxsw_sp_fib_node_remove(fib_node->vr->fib, fib_node); list_del(&fib_node->list); WARN_ON(!list_empty(&fib_node->entry_list)); kfree(fib_node); @@ -2034,7 +2019,7 @@ mlxsw_sp_fib_node_entry_is_first(const struct mlxsw_sp_fib_node *fib_node, static void mlxsw_sp_fib_node_prefix_inc(struct mlxsw_sp_fib_node *fib_node) { unsigned char prefix_len = fib_node->key.prefix_len; - struct mlxsw_sp_fib *fib = fib_node->vr->fib; + struct mlxsw_sp_fib *fib = fib_node->fib; if (fib->prefix_ref_count[prefix_len]++ == 0) mlxsw_sp_prefix_usage_set(&fib->prefix_usage, prefix_len); @@ -2043,32 +2028,98 @@ static void mlxsw_sp_fib_node_prefix_inc(struct mlxsw_sp_fib_node *fib_node) static void mlxsw_sp_fib_node_prefix_dec(struct mlxsw_sp_fib_node *fib_node) { unsigned char prefix_len = fib_node->key.prefix_len; - struct mlxsw_sp_fib *fib = fib_node->vr->fib; + struct mlxsw_sp_fib *fib = fib_node->fib; if (--fib->prefix_ref_count[prefix_len] == 0) mlxsw_sp_prefix_usage_clear(&fib->prefix_usage, prefix_len); } +static int mlxsw_sp_fib_node_init(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_fib_node *fib_node, + struct mlxsw_sp_fib *fib) +{ + struct mlxsw_sp_prefix_usage req_prefix_usage; + struct mlxsw_sp_lpm_tree *lpm_tree; + int err; + + err = mlxsw_sp_fib_node_insert(fib, fib_node); + if (err) + return err; + fib_node->fib = fib; + + mlxsw_sp_prefix_usage_cpy(&req_prefix_usage, &fib->prefix_usage); + mlxsw_sp_prefix_usage_set(&req_prefix_usage, fib_node->key.prefix_len); + + if (!mlxsw_sp_prefix_usage_none(&fib->prefix_usage)) { + err = mlxsw_sp_vr_lpm_tree_check(mlxsw_sp, fib, + &req_prefix_usage); + if (err) + goto err_tree_check; + } else { + lpm_tree = mlxsw_sp_lpm_tree_get(mlxsw_sp, &req_prefix_usage, + fib->proto); + if (IS_ERR(lpm_tree)) + return PTR_ERR(lpm_tree); + fib->lpm_tree = lpm_tree; + err = mlxsw_sp_vr_lpm_tree_bind(mlxsw_sp, fib); + if (err) + goto err_tree_bind; + } + + mlxsw_sp_fib_node_prefix_inc(fib_node); + + return 0; + +err_tree_bind: + fib->lpm_tree = NULL; + mlxsw_sp_lpm_tree_put(mlxsw_sp, lpm_tree); +err_tree_check: + fib_node->fib = NULL; + mlxsw_sp_fib_node_remove(fib, fib_node); + return err; +} + +static void mlxsw_sp_fib_node_fini(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_fib_node *fib_node) +{ + struct mlxsw_sp_lpm_tree *lpm_tree = fib_node->fib->lpm_tree; + struct mlxsw_sp_fib *fib = fib_node->fib; + + mlxsw_sp_fib_node_prefix_dec(fib_node); + + if (mlxsw_sp_prefix_usage_none(&fib->prefix_usage)) { + mlxsw_sp_vr_lpm_tree_unbind(mlxsw_sp, fib); + fib->lpm_tree = NULL; + mlxsw_sp_lpm_tree_put(mlxsw_sp, lpm_tree); + } else { + mlxsw_sp_vr_lpm_tree_check(mlxsw_sp, fib, &fib->prefix_usage); + } + + fib_node->fib = NULL; + mlxsw_sp_fib_node_remove(fib, fib_node); +} + static struct mlxsw_sp_fib_node * mlxsw_sp_fib4_node_get(struct mlxsw_sp *mlxsw_sp, const struct fib_entry_notifier_info *fen_info) { struct mlxsw_sp_fib_node *fib_node; + struct mlxsw_sp_fib *fib; struct mlxsw_sp_vr *vr; int err; - vr = mlxsw_sp_vr_get(mlxsw_sp, fen_info->dst_len, fen_info->tb_id, - MLXSW_SP_L3_PROTO_IPV4); + vr = mlxsw_sp_vr_get(mlxsw_sp, fen_info->tb_id); if (IS_ERR(vr)) return ERR_CAST(vr); + fib = mlxsw_sp_vr_fib(vr, MLXSW_SP_L3_PROTO_IPV4); - fib_node = mlxsw_sp_fib_node_lookup(vr->fib, &fen_info->dst, + fib_node = mlxsw_sp_fib_node_lookup(fib, &fen_info->dst, sizeof(fen_info->dst), fen_info->dst_len); if (fib_node) return fib_node; - fib_node = mlxsw_sp_fib_node_create(vr, &fen_info->dst, + fib_node = mlxsw_sp_fib_node_create(fib, &fen_info->dst, sizeof(fen_info->dst), fen_info->dst_len); if (!fib_node) { @@ -2076,22 +2127,29 @@ mlxsw_sp_fib4_node_get(struct mlxsw_sp *mlxsw_sp, goto err_fib_node_create; } + err = mlxsw_sp_fib_node_init(mlxsw_sp, fib_node, fib); + if (err) + goto err_fib_node_init; + return fib_node; +err_fib_node_init: + mlxsw_sp_fib_node_destroy(fib_node); err_fib_node_create: - mlxsw_sp_vr_put(mlxsw_sp, vr); + mlxsw_sp_vr_put(vr); return ERR_PTR(err); } static void mlxsw_sp_fib4_node_put(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_fib_node *fib_node) { - struct mlxsw_sp_vr *vr = fib_node->vr; + struct mlxsw_sp_vr *vr = fib_node->fib->vr; if (!list_empty(&fib_node->entry_list)) return; + mlxsw_sp_fib_node_fini(mlxsw_sp, fib_node); mlxsw_sp_fib_node_destroy(fib_node); - mlxsw_sp_vr_put(mlxsw_sp, vr); + mlxsw_sp_vr_put(vr); } static struct mlxsw_sp_fib_entry * @@ -2236,8 +2294,6 @@ static int mlxsw_sp_fib4_node_entry_link(struct mlxsw_sp *mlxsw_sp, if (err) goto err_fib4_node_entry_add; - mlxsw_sp_fib_node_prefix_inc(fib_node); - return 0; err_fib4_node_entry_add: @@ -2251,7 +2307,6 @@ mlxsw_sp_fib4_node_entry_unlink(struct mlxsw_sp *mlxsw_sp, { struct mlxsw_sp_fib_node *fib_node = fib_entry->fib_node; - mlxsw_sp_fib_node_prefix_dec(fib_node); mlxsw_sp_fib4_node_entry_del(mlxsw_sp, fib_node, fib_entry); mlxsw_sp_fib4_node_list_remove(fib_entry); } @@ -2340,9 +2395,7 @@ static int mlxsw_sp_router_set_abort_trap(struct mlxsw_sp *mlxsw_sp) { char ralta_pl[MLXSW_REG_RALTA_LEN]; char ralst_pl[MLXSW_REG_RALST_LEN]; - char raltb_pl[MLXSW_REG_RALTB_LEN]; - char ralue_pl[MLXSW_REG_RALUE_LEN]; - int err; + int i, err; mlxsw_reg_ralta_pack(ralta_pl, true, MLXSW_REG_RALXX_PROTOCOL_IPV4, MLXSW_SP_LPM_TREE_MIN); @@ -2355,16 +2408,33 @@ static int mlxsw_sp_router_set_abort_trap(struct mlxsw_sp *mlxsw_sp) if (err) return err; - mlxsw_reg_raltb_pack(raltb_pl, 0, MLXSW_REG_RALXX_PROTOCOL_IPV4, - MLXSW_SP_LPM_TREE_MIN); - err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(raltb), raltb_pl); - if (err) - return err; + for (i = 0; i < MLXSW_CORE_RES_GET(mlxsw_sp->core, MAX_VRS); i++) { + struct mlxsw_sp_vr *vr = &mlxsw_sp->router.vrs[i]; + char raltb_pl[MLXSW_REG_RALTB_LEN]; + char ralue_pl[MLXSW_REG_RALUE_LEN]; - mlxsw_reg_ralue_pack4(ralue_pl, MLXSW_SP_L3_PROTO_IPV4, - MLXSW_REG_RALUE_OP_WRITE_WRITE, 0, 0, 0); - mlxsw_reg_ralue_act_ip2me_pack(ralue_pl); - return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ralue), ralue_pl); + if (!mlxsw_sp_vr_is_used(vr)) + continue; + + mlxsw_reg_raltb_pack(raltb_pl, vr->id, + MLXSW_REG_RALXX_PROTOCOL_IPV4, + MLXSW_SP_LPM_TREE_MIN); + err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(raltb), + raltb_pl); + if (err) + return err; + + mlxsw_reg_ralue_pack4(ralue_pl, MLXSW_SP_L3_PROTO_IPV4, + MLXSW_REG_RALUE_OP_WRITE_WRITE, vr->id, 0, + 0); + mlxsw_reg_ralue_act_ip2me_pack(ralue_pl); + err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ralue), + ralue_pl); + if (err) + return err; + } + + return 0; } static void mlxsw_sp_fib4_node_flush(struct mlxsw_sp *mlxsw_sp, @@ -2390,7 +2460,7 @@ static void mlxsw_sp_fib4_node_flush(struct mlxsw_sp *mlxsw_sp, static void mlxsw_sp_fib_node_flush(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_fib_node *fib_node) { - switch (fib_node->vr->proto) { + switch (fib_node->fib->proto) { case MLXSW_SP_L3_PROTO_IPV4: mlxsw_sp_fib4_node_flush(mlxsw_sp, fib_node); break; @@ -2400,26 +2470,32 @@ static void mlxsw_sp_fib_node_flush(struct mlxsw_sp *mlxsw_sp, } } -static void mlxsw_sp_router_fib_flush(struct mlxsw_sp *mlxsw_sp) +static void mlxsw_sp_vr_fib_flush(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_vr *vr, + enum mlxsw_sp_l3proto proto) { + struct mlxsw_sp_fib *fib = mlxsw_sp_vr_fib(vr, proto); struct mlxsw_sp_fib_node *fib_node, *tmp; - struct mlxsw_sp_vr *vr; + + list_for_each_entry_safe(fib_node, tmp, &fib->node_list, list) { + bool do_break = &tmp->list == &fib->node_list; + + mlxsw_sp_fib_node_flush(mlxsw_sp, fib_node); + if (do_break) + break; + } +} + +static void mlxsw_sp_router_fib_flush(struct mlxsw_sp *mlxsw_sp) +{ int i; for (i = 0; i < MLXSW_CORE_RES_GET(mlxsw_sp->core, MAX_VRS); i++) { - vr = &mlxsw_sp->router.vrs[i]; + struct mlxsw_sp_vr *vr = &mlxsw_sp->router.vrs[i]; - if (!vr->used) + if (!mlxsw_sp_vr_is_used(vr)) continue; - - list_for_each_entry_safe(fib_node, tmp, &vr->fib->node_list, - list) { - bool do_break = &tmp->list == &vr->fib->node_list; - - mlxsw_sp_fib_node_flush(mlxsw_sp, fib_node); - if (do_break) - break; - } + mlxsw_sp_vr_fib_flush(mlxsw_sp, vr, MLXSW_SP_L3_PROTO_IPV4); } } @@ -2437,74 +2513,11 @@ static void mlxsw_sp_router_fib4_abort(struct mlxsw_sp *mlxsw_sp) dev_warn(mlxsw_sp->bus_info->dev, "Failed to set abort trap.\n"); } -static int mlxsw_sp_router_rif_disable(struct mlxsw_sp *mlxsw_sp, u16 rif) -{ - char ritr_pl[MLXSW_REG_RITR_LEN]; - int err; - - mlxsw_reg_ritr_rif_pack(ritr_pl, rif); - err = mlxsw_reg_query(mlxsw_sp->core, MLXSW_REG(ritr), ritr_pl); - if (WARN_ON_ONCE(err)) - return err; - - mlxsw_reg_ritr_enable_set(ritr_pl, false); - return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ritr), ritr_pl); -} - -void mlxsw_sp_router_rif_gone_sync(struct mlxsw_sp *mlxsw_sp, - struct mlxsw_sp_rif *r) -{ - mlxsw_sp_router_rif_disable(mlxsw_sp, r->rif); - mlxsw_sp_nexthop_rif_gone_sync(mlxsw_sp, r); - mlxsw_sp_neigh_rif_gone_sync(mlxsw_sp, r); -} - -static int __mlxsw_sp_router_init(struct mlxsw_sp *mlxsw_sp) -{ - char rgcr_pl[MLXSW_REG_RGCR_LEN]; - u64 max_rifs; - int err; - - if (!MLXSW_CORE_RES_VALID(mlxsw_sp->core, MAX_RIFS)) - return -EIO; - - max_rifs = MLXSW_CORE_RES_GET(mlxsw_sp->core, MAX_RIFS); - mlxsw_sp->rifs = kcalloc(max_rifs, sizeof(struct mlxsw_sp_rif *), - GFP_KERNEL); - if (!mlxsw_sp->rifs) - return -ENOMEM; - - mlxsw_reg_rgcr_pack(rgcr_pl, true); - mlxsw_reg_rgcr_max_router_interfaces_set(rgcr_pl, max_rifs); - err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(rgcr), rgcr_pl); - if (err) - goto err_rgcr_fail; - - return 0; - -err_rgcr_fail: - kfree(mlxsw_sp->rifs); - return err; -} - -static void __mlxsw_sp_router_fini(struct mlxsw_sp *mlxsw_sp) -{ - char rgcr_pl[MLXSW_REG_RGCR_LEN]; - int i; - - mlxsw_reg_rgcr_pack(rgcr_pl, false); - mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(rgcr), rgcr_pl); - - for (i = 0; i < MLXSW_CORE_RES_GET(mlxsw_sp->core, MAX_RIFS); i++) - WARN_ON_ONCE(mlxsw_sp->rifs[i]); - - kfree(mlxsw_sp->rifs); -} - struct mlxsw_sp_fib_event_work { struct work_struct work; union { struct fib_entry_notifier_info fen_info; + struct fib_rule_notifier_info fr_info; struct fib_nh_notifier_info fnh_info; }; struct mlxsw_sp *mlxsw_sp; @@ -2516,6 +2529,7 @@ static void mlxsw_sp_router_fib_event_work(struct work_struct *work) struct mlxsw_sp_fib_event_work *fib_work = container_of(work, struct mlxsw_sp_fib_event_work, work); struct mlxsw_sp *mlxsw_sp = fib_work->mlxsw_sp; + struct fib_rule *rule; bool replace, append; int err; @@ -2539,7 +2553,10 @@ static void mlxsw_sp_router_fib_event_work(struct work_struct *work) break; case FIB_EVENT_RULE_ADD: /* fall through */ case FIB_EVENT_RULE_DEL: - mlxsw_sp_router_fib4_abort(mlxsw_sp); + rule = fib_work->fr_info.rule; + if (!fib4_rule_default(rule) && !rule->l3mdev) + mlxsw_sp_router_fib4_abort(mlxsw_sp); + fib_rule_put(rule); break; case FIB_EVENT_NH_ADD: /* fall through */ case FIB_EVENT_NH_DEL: @@ -2582,6 +2599,11 @@ static int mlxsw_sp_router_fib_event(struct notifier_block *nb, */ fib_info_hold(fib_work->fen_info.fi); break; + case FIB_EVENT_RULE_ADD: /* fall through */ + case FIB_EVENT_RULE_DEL: + memcpy(&fib_work->fr_info, ptr, sizeof(fib_work->fr_info)); + fib_rule_get(fib_work->fr_info.rule); + break; case FIB_EVENT_NH_ADD: /* fall through */ case FIB_EVENT_NH_DEL: memcpy(&fib_work->fnh_info, ptr, sizeof(fib_work->fnh_info)); @@ -2594,6 +2616,683 @@ static int mlxsw_sp_router_fib_event(struct notifier_block *nb, return NOTIFY_DONE; } +static struct mlxsw_sp_rif * +mlxsw_sp_rif_find_by_dev(const struct mlxsw_sp *mlxsw_sp, + const struct net_device *dev) +{ + int i; + + for (i = 0; i < MLXSW_CORE_RES_GET(mlxsw_sp->core, MAX_RIFS); i++) + if (mlxsw_sp->rifs[i] && mlxsw_sp->rifs[i]->dev == dev) + return mlxsw_sp->rifs[i]; + + return NULL; +} + +static int mlxsw_sp_router_rif_disable(struct mlxsw_sp *mlxsw_sp, u16 rif) +{ + char ritr_pl[MLXSW_REG_RITR_LEN]; + int err; + + mlxsw_reg_ritr_rif_pack(ritr_pl, rif); + err = mlxsw_reg_query(mlxsw_sp->core, MLXSW_REG(ritr), ritr_pl); + if (WARN_ON_ONCE(err)) + return err; + + mlxsw_reg_ritr_enable_set(ritr_pl, false); + return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ritr), ritr_pl); +} + +static void mlxsw_sp_router_rif_gone_sync(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_rif *r) +{ + mlxsw_sp_router_rif_disable(mlxsw_sp, r->rif); + mlxsw_sp_nexthop_rif_gone_sync(mlxsw_sp, r); + mlxsw_sp_neigh_rif_gone_sync(mlxsw_sp, r); +} + +static bool mlxsw_sp_rif_should_config(struct mlxsw_sp_rif *r, + const struct in_device *in_dev, + unsigned long event) +{ + switch (event) { + case NETDEV_UP: + if (!r) + return true; + return false; + case NETDEV_DOWN: + if (r && !in_dev->ifa_list && !netif_is_l3_slave(r->dev)) + return true; + /* It is possible we already removed the RIF ourselves + * if it was assigned to a netdev that is now a bridge + * or LAG slave. + */ + return false; + } + + return false; +} + +#define MLXSW_SP_INVALID_RIF 0xffff +static int mlxsw_sp_avail_rif_get(struct mlxsw_sp *mlxsw_sp) +{ + int i; + + for (i = 0; i < MLXSW_CORE_RES_GET(mlxsw_sp->core, MAX_RIFS); i++) + if (!mlxsw_sp->rifs[i]) + return i; + + return MLXSW_SP_INVALID_RIF; +} + +static void mlxsw_sp_vport_rif_sp_attr_get(struct mlxsw_sp_port *mlxsw_sp_vport, + bool *p_lagged, u16 *p_system_port) +{ + u8 local_port = mlxsw_sp_vport->local_port; + + *p_lagged = mlxsw_sp_vport->lagged; + *p_system_port = *p_lagged ? mlxsw_sp_vport->lag_id : local_port; +} + +static int mlxsw_sp_vport_rif_sp_op(struct mlxsw_sp_port *mlxsw_sp_vport, + u16 vr_id, struct net_device *l3_dev, + u16 rif, bool create) +{ + struct mlxsw_sp *mlxsw_sp = mlxsw_sp_vport->mlxsw_sp; + bool lagged = mlxsw_sp_vport->lagged; + char ritr_pl[MLXSW_REG_RITR_LEN]; + u16 system_port; + + mlxsw_reg_ritr_pack(ritr_pl, create, MLXSW_REG_RITR_SP_IF, rif, vr_id, + l3_dev->mtu, l3_dev->dev_addr); + + mlxsw_sp_vport_rif_sp_attr_get(mlxsw_sp_vport, &lagged, &system_port); + mlxsw_reg_ritr_sp_if_pack(ritr_pl, lagged, system_port, + mlxsw_sp_vport_vid_get(mlxsw_sp_vport)); + + return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ritr), ritr_pl); +} + +static void mlxsw_sp_vport_rif_sp_leave(struct mlxsw_sp_port *mlxsw_sp_vport); + +static u16 mlxsw_sp_rif_sp_to_fid(u16 rif) +{ + return MLXSW_SP_RFID_BASE + rif; +} + +static struct mlxsw_sp_fid * +mlxsw_sp_rfid_alloc(u16 fid, struct net_device *l3_dev) +{ + struct mlxsw_sp_fid *f; + + f = kzalloc(sizeof(*f), GFP_KERNEL); + if (!f) + return NULL; + + f->leave = mlxsw_sp_vport_rif_sp_leave; + f->ref_count = 0; + f->dev = l3_dev; + f->fid = fid; + + return f; +} + +static struct mlxsw_sp_rif * +mlxsw_sp_rif_alloc(u16 rif, u16 vr_id, struct net_device *l3_dev, + struct mlxsw_sp_fid *f) +{ + struct mlxsw_sp_rif *r; + + r = kzalloc(sizeof(*r), GFP_KERNEL); + if (!r) + return NULL; + + INIT_LIST_HEAD(&r->nexthop_list); + INIT_LIST_HEAD(&r->neigh_list); + ether_addr_copy(r->addr, l3_dev->dev_addr); + r->mtu = l3_dev->mtu; + r->vr_id = vr_id; + r->dev = l3_dev; + r->rif = rif; + r->f = f; + + return r; +} + +static struct mlxsw_sp_rif * +mlxsw_sp_vport_rif_sp_create(struct mlxsw_sp_port *mlxsw_sp_vport, + struct net_device *l3_dev) +{ + struct mlxsw_sp *mlxsw_sp = mlxsw_sp_vport->mlxsw_sp; + u32 tb_id = l3mdev_fib_table(l3_dev); + struct mlxsw_sp_vr *vr; + struct mlxsw_sp_fid *f; + struct mlxsw_sp_rif *r; + u16 fid, rif; + int err; + + rif = mlxsw_sp_avail_rif_get(mlxsw_sp); + if (rif == MLXSW_SP_INVALID_RIF) + return ERR_PTR(-ERANGE); + + vr = mlxsw_sp_vr_get(mlxsw_sp, tb_id ? : RT_TABLE_MAIN); + if (IS_ERR(vr)) + return ERR_CAST(vr); + + err = mlxsw_sp_vport_rif_sp_op(mlxsw_sp_vport, vr->id, l3_dev, rif, + true); + if (err) + goto err_vport_rif_sp_op; + + fid = mlxsw_sp_rif_sp_to_fid(rif); + err = mlxsw_sp_rif_fdb_op(mlxsw_sp, l3_dev->dev_addr, fid, true); + if (err) + goto err_rif_fdb_op; + + f = mlxsw_sp_rfid_alloc(fid, l3_dev); + if (!f) { + err = -ENOMEM; + goto err_rfid_alloc; + } + + r = mlxsw_sp_rif_alloc(rif, vr->id, l3_dev, f); + if (!r) { + err = -ENOMEM; + goto err_rif_alloc; + } + + f->r = r; + mlxsw_sp->rifs[rif] = r; + vr->rif_count++; + + return r; + +err_rif_alloc: + kfree(f); +err_rfid_alloc: + mlxsw_sp_rif_fdb_op(mlxsw_sp, l3_dev->dev_addr, fid, false); +err_rif_fdb_op: + mlxsw_sp_vport_rif_sp_op(mlxsw_sp_vport, vr->id, l3_dev, rif, false); +err_vport_rif_sp_op: + mlxsw_sp_vr_put(vr); + return ERR_PTR(err); +} + +static void mlxsw_sp_vport_rif_sp_destroy(struct mlxsw_sp_port *mlxsw_sp_vport, + struct mlxsw_sp_rif *r) +{ + struct mlxsw_sp *mlxsw_sp = mlxsw_sp_vport->mlxsw_sp; + struct mlxsw_sp_vr *vr = &mlxsw_sp->router.vrs[r->vr_id]; + struct net_device *l3_dev = r->dev; + struct mlxsw_sp_fid *f = r->f; + u16 fid = f->fid; + u16 rif = r->rif; + + mlxsw_sp_router_rif_gone_sync(mlxsw_sp, r); + + vr->rif_count--; + mlxsw_sp->rifs[rif] = NULL; + f->r = NULL; + + kfree(r); + + kfree(f); + + mlxsw_sp_rif_fdb_op(mlxsw_sp, l3_dev->dev_addr, fid, false); + + mlxsw_sp_vport_rif_sp_op(mlxsw_sp_vport, vr->id, l3_dev, rif, false); + + mlxsw_sp_vr_put(vr); +} + +static int mlxsw_sp_vport_rif_sp_join(struct mlxsw_sp_port *mlxsw_sp_vport, + struct net_device *l3_dev) +{ + struct mlxsw_sp *mlxsw_sp = mlxsw_sp_vport->mlxsw_sp; + struct mlxsw_sp_rif *r; + + r = mlxsw_sp_rif_find_by_dev(mlxsw_sp, l3_dev); + if (!r) { + r = mlxsw_sp_vport_rif_sp_create(mlxsw_sp_vport, l3_dev); + if (IS_ERR(r)) + return PTR_ERR(r); + } + + mlxsw_sp_vport_fid_set(mlxsw_sp_vport, r->f); + r->f->ref_count++; + + netdev_dbg(mlxsw_sp_vport->dev, "Joined FID=%d\n", r->f->fid); + + return 0; +} + +static void mlxsw_sp_vport_rif_sp_leave(struct mlxsw_sp_port *mlxsw_sp_vport) +{ + struct mlxsw_sp_fid *f = mlxsw_sp_vport_fid_get(mlxsw_sp_vport); + + netdev_dbg(mlxsw_sp_vport->dev, "Left FID=%d\n", f->fid); + + mlxsw_sp_vport_fid_set(mlxsw_sp_vport, NULL); + if (--f->ref_count == 0) + mlxsw_sp_vport_rif_sp_destroy(mlxsw_sp_vport, f->r); +} + +static int mlxsw_sp_inetaddr_vport_event(struct net_device *l3_dev, + struct net_device *port_dev, + unsigned long event, u16 vid) +{ + struct mlxsw_sp_port *mlxsw_sp_port = netdev_priv(port_dev); + struct mlxsw_sp_port *mlxsw_sp_vport; + + mlxsw_sp_vport = mlxsw_sp_port_vport_find(mlxsw_sp_port, vid); + if (WARN_ON(!mlxsw_sp_vport)) + return -EINVAL; + + switch (event) { + case NETDEV_UP: + return mlxsw_sp_vport_rif_sp_join(mlxsw_sp_vport, l3_dev); + case NETDEV_DOWN: + mlxsw_sp_vport_rif_sp_leave(mlxsw_sp_vport); + break; + } + + return 0; +} + +static int mlxsw_sp_inetaddr_port_event(struct net_device *port_dev, + unsigned long event) +{ + if (netif_is_bridge_port(port_dev) || netif_is_lag_port(port_dev)) + return 0; + + return mlxsw_sp_inetaddr_vport_event(port_dev, port_dev, event, 1); +} + +static int __mlxsw_sp_inetaddr_lag_event(struct net_device *l3_dev, + struct net_device *lag_dev, + unsigned long event, u16 vid) +{ + struct net_device *port_dev; + struct list_head *iter; + int err; + + netdev_for_each_lower_dev(lag_dev, port_dev, iter) { + if (mlxsw_sp_port_dev_check(port_dev)) { + err = mlxsw_sp_inetaddr_vport_event(l3_dev, port_dev, + event, vid); + if (err) + return err; + } + } + + return 0; +} + +static int mlxsw_sp_inetaddr_lag_event(struct net_device *lag_dev, + unsigned long event) +{ + if (netif_is_bridge_port(lag_dev)) + return 0; + + return __mlxsw_sp_inetaddr_lag_event(lag_dev, lag_dev, event, 1); +} + +static struct mlxsw_sp_fid *mlxsw_sp_bridge_fid_get(struct mlxsw_sp *mlxsw_sp, + struct net_device *l3_dev) +{ + u16 fid; + + if (is_vlan_dev(l3_dev)) + fid = vlan_dev_vlan_id(l3_dev); + else if (mlxsw_sp->master_bridge.dev == l3_dev) + fid = 1; + else + return mlxsw_sp_vfid_find(mlxsw_sp, l3_dev); + + return mlxsw_sp_fid_find(mlxsw_sp, fid); +} + +static enum mlxsw_flood_table_type mlxsw_sp_flood_table_type_get(u16 fid) +{ + return mlxsw_sp_fid_is_vfid(fid) ? MLXSW_REG_SFGC_TABLE_TYPE_FID : + MLXSW_REG_SFGC_TABLE_TYPE_FID_OFFEST; +} + +static u16 mlxsw_sp_flood_table_index_get(u16 fid) +{ + return mlxsw_sp_fid_is_vfid(fid) ? mlxsw_sp_fid_to_vfid(fid) : fid; +} + +static int mlxsw_sp_router_port_flood_set(struct mlxsw_sp *mlxsw_sp, u16 fid, + bool set) +{ + enum mlxsw_flood_table_type table_type; + char *sftr_pl; + u16 index; + int err; + + sftr_pl = kmalloc(MLXSW_REG_SFTR_LEN, GFP_KERNEL); + if (!sftr_pl) + return -ENOMEM; + + table_type = mlxsw_sp_flood_table_type_get(fid); + index = mlxsw_sp_flood_table_index_get(fid); + mlxsw_reg_sftr_pack(sftr_pl, MLXSW_SP_FLOOD_TABLE_BC, index, table_type, + 1, MLXSW_PORT_ROUTER_PORT, set); + err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(sftr), sftr_pl); + + kfree(sftr_pl); + return err; +} + +static enum mlxsw_reg_ritr_if_type mlxsw_sp_rif_type_get(u16 fid) +{ + if (mlxsw_sp_fid_is_vfid(fid)) + return MLXSW_REG_RITR_FID_IF; + else + return MLXSW_REG_RITR_VLAN_IF; +} + +static int mlxsw_sp_rif_bridge_op(struct mlxsw_sp *mlxsw_sp, u16 vr_id, + struct net_device *l3_dev, + u16 fid, u16 rif, + bool create) +{ + enum mlxsw_reg_ritr_if_type rif_type; + char ritr_pl[MLXSW_REG_RITR_LEN]; + + rif_type = mlxsw_sp_rif_type_get(fid); + mlxsw_reg_ritr_pack(ritr_pl, create, rif_type, rif, vr_id, l3_dev->mtu, + l3_dev->dev_addr); + mlxsw_reg_ritr_fid_set(ritr_pl, rif_type, fid); + + return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ritr), ritr_pl); +} + +static int mlxsw_sp_rif_bridge_create(struct mlxsw_sp *mlxsw_sp, + struct net_device *l3_dev, + struct mlxsw_sp_fid *f) +{ + u32 tb_id = l3mdev_fib_table(l3_dev); + struct mlxsw_sp_vr *vr; + struct mlxsw_sp_rif *r; + u16 rif; + int err; + + rif = mlxsw_sp_avail_rif_get(mlxsw_sp); + if (rif == MLXSW_SP_INVALID_RIF) + return -ERANGE; + + vr = mlxsw_sp_vr_get(mlxsw_sp, tb_id ? : RT_TABLE_MAIN); + if (IS_ERR(vr)) + return PTR_ERR(vr); + + err = mlxsw_sp_router_port_flood_set(mlxsw_sp, f->fid, true); + if (err) + goto err_port_flood_set; + + err = mlxsw_sp_rif_bridge_op(mlxsw_sp, vr->id, l3_dev, f->fid, rif, + true); + if (err) + goto err_rif_bridge_op; + + err = mlxsw_sp_rif_fdb_op(mlxsw_sp, l3_dev->dev_addr, f->fid, true); + if (err) + goto err_rif_fdb_op; + + r = mlxsw_sp_rif_alloc(rif, vr->id, l3_dev, f); + if (!r) { + err = -ENOMEM; + goto err_rif_alloc; + } + + f->r = r; + mlxsw_sp->rifs[rif] = r; + vr->rif_count++; + + netdev_dbg(l3_dev, "RIF=%d created\n", rif); + + return 0; + +err_rif_alloc: + mlxsw_sp_rif_fdb_op(mlxsw_sp, l3_dev->dev_addr, f->fid, false); +err_rif_fdb_op: + mlxsw_sp_rif_bridge_op(mlxsw_sp, vr->id, l3_dev, f->fid, rif, false); +err_rif_bridge_op: + mlxsw_sp_router_port_flood_set(mlxsw_sp, f->fid, false); +err_port_flood_set: + mlxsw_sp_vr_put(vr); + return err; +} + +void mlxsw_sp_rif_bridge_destroy(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_rif *r) +{ + struct mlxsw_sp_vr *vr = &mlxsw_sp->router.vrs[r->vr_id]; + struct net_device *l3_dev = r->dev; + struct mlxsw_sp_fid *f = r->f; + u16 rif = r->rif; + + mlxsw_sp_router_rif_gone_sync(mlxsw_sp, r); + + vr->rif_count--; + mlxsw_sp->rifs[rif] = NULL; + f->r = NULL; + + kfree(r); + + mlxsw_sp_rif_fdb_op(mlxsw_sp, l3_dev->dev_addr, f->fid, false); + + mlxsw_sp_rif_bridge_op(mlxsw_sp, vr->id, l3_dev, f->fid, rif, false); + + mlxsw_sp_router_port_flood_set(mlxsw_sp, f->fid, false); + + mlxsw_sp_vr_put(vr); + + netdev_dbg(l3_dev, "RIF=%d destroyed\n", rif); +} + +static int mlxsw_sp_inetaddr_bridge_event(struct net_device *l3_dev, + struct net_device *br_dev, + unsigned long event) +{ + struct mlxsw_sp *mlxsw_sp = mlxsw_sp_lower_get(l3_dev); + struct mlxsw_sp_fid *f; + + /* FID can either be an actual FID if the L3 device is the + * VLAN-aware bridge or a VLAN device on top. Otherwise, the + * L3 device is a VLAN-unaware bridge and we get a vFID. + */ + f = mlxsw_sp_bridge_fid_get(mlxsw_sp, l3_dev); + if (WARN_ON(!f)) + return -EINVAL; + + switch (event) { + case NETDEV_UP: + return mlxsw_sp_rif_bridge_create(mlxsw_sp, l3_dev, f); + case NETDEV_DOWN: + mlxsw_sp_rif_bridge_destroy(mlxsw_sp, f->r); + break; + } + + return 0; +} + +static int mlxsw_sp_inetaddr_vlan_event(struct net_device *vlan_dev, + unsigned long event) +{ + struct net_device *real_dev = vlan_dev_real_dev(vlan_dev); + struct mlxsw_sp *mlxsw_sp = mlxsw_sp_lower_get(vlan_dev); + u16 vid = vlan_dev_vlan_id(vlan_dev); + + if (mlxsw_sp_port_dev_check(real_dev)) + return mlxsw_sp_inetaddr_vport_event(vlan_dev, real_dev, event, + vid); + else if (netif_is_lag_master(real_dev)) + return __mlxsw_sp_inetaddr_lag_event(vlan_dev, real_dev, event, + vid); + else if (netif_is_bridge_master(real_dev) && + mlxsw_sp->master_bridge.dev == real_dev) + return mlxsw_sp_inetaddr_bridge_event(vlan_dev, real_dev, + event); + + return 0; +} + +int mlxsw_sp_inetaddr_event(struct notifier_block *unused, + unsigned long event, void *ptr) +{ + struct in_ifaddr *ifa = (struct in_ifaddr *) ptr; + struct net_device *dev = ifa->ifa_dev->dev; + struct mlxsw_sp *mlxsw_sp; + struct mlxsw_sp_rif *r; + int err = 0; + + mlxsw_sp = mlxsw_sp_lower_get(dev); + if (!mlxsw_sp) + goto out; + + r = mlxsw_sp_rif_find_by_dev(mlxsw_sp, dev); + if (!mlxsw_sp_rif_should_config(r, ifa->ifa_dev, event)) + goto out; + + if (mlxsw_sp_port_dev_check(dev)) + err = mlxsw_sp_inetaddr_port_event(dev, event); + else if (netif_is_lag_master(dev)) + err = mlxsw_sp_inetaddr_lag_event(dev, event); + else if (netif_is_bridge_master(dev)) + err = mlxsw_sp_inetaddr_bridge_event(dev, dev, event); + else if (is_vlan_dev(dev)) + err = mlxsw_sp_inetaddr_vlan_event(dev, event); + +out: + return notifier_from_errno(err); +} + +static int mlxsw_sp_rif_edit(struct mlxsw_sp *mlxsw_sp, u16 rif, + const char *mac, int mtu) +{ + char ritr_pl[MLXSW_REG_RITR_LEN]; + int err; + + mlxsw_reg_ritr_rif_pack(ritr_pl, rif); + err = mlxsw_reg_query(mlxsw_sp->core, MLXSW_REG(ritr), ritr_pl); + if (err) + return err; + + mlxsw_reg_ritr_mtu_set(ritr_pl, mtu); + mlxsw_reg_ritr_if_mac_memcpy_to(ritr_pl, mac); + mlxsw_reg_ritr_op_set(ritr_pl, MLXSW_REG_RITR_RIF_CREATE); + return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ritr), ritr_pl); +} + +int mlxsw_sp_netdevice_router_port_event(struct net_device *dev) +{ + struct mlxsw_sp *mlxsw_sp; + struct mlxsw_sp_rif *r; + int err; + + mlxsw_sp = mlxsw_sp_lower_get(dev); + if (!mlxsw_sp) + return 0; + + r = mlxsw_sp_rif_find_by_dev(mlxsw_sp, dev); + if (!r) + return 0; + + err = mlxsw_sp_rif_fdb_op(mlxsw_sp, r->addr, r->f->fid, false); + if (err) + return err; + + err = mlxsw_sp_rif_edit(mlxsw_sp, r->rif, dev->dev_addr, dev->mtu); + if (err) + goto err_rif_edit; + + err = mlxsw_sp_rif_fdb_op(mlxsw_sp, dev->dev_addr, r->f->fid, true); + if (err) + goto err_rif_fdb_op; + + ether_addr_copy(r->addr, dev->dev_addr); + r->mtu = dev->mtu; + + netdev_dbg(dev, "Updated RIF=%d\n", r->rif); + + return 0; + +err_rif_fdb_op: + mlxsw_sp_rif_edit(mlxsw_sp, r->rif, r->addr, r->mtu); +err_rif_edit: + mlxsw_sp_rif_fdb_op(mlxsw_sp, r->addr, r->f->fid, true); + return err; +} + +int mlxsw_sp_vport_vrf_join(struct mlxsw_sp_port *mlxsw_sp_vport) +{ + struct mlxsw_sp_fid *f = mlxsw_sp_vport_fid_get(mlxsw_sp_vport); + struct net_device *dev = mlxsw_sp_vport->dev; + + /* In case vPort already has a RIF, then we need to drop it. + * A new one will be created using the VRF's VR. + */ + if (f && f->r) + mlxsw_sp_vport_rif_sp_leave(mlxsw_sp_vport); + + return mlxsw_sp_vport_rif_sp_join(mlxsw_sp_vport, dev); +} + +void mlxsw_sp_vport_vrf_leave(struct mlxsw_sp_port *mlxsw_sp_vport) +{ + mlxsw_sp_vport_rif_sp_leave(mlxsw_sp_vport); +} + +int mlxsw_sp_port_vrf_join(struct mlxsw_sp_port *mlxsw_sp_port) +{ + struct mlxsw_sp_port *mlxsw_sp_vport; + + mlxsw_sp_vport = mlxsw_sp_port_vport_find(mlxsw_sp_port, 1); + if (WARN_ON(!mlxsw_sp_vport)) + return -EINVAL; + + return mlxsw_sp_vport_vrf_join(mlxsw_sp_vport); +} + +void mlxsw_sp_port_vrf_leave(struct mlxsw_sp_port *mlxsw_sp_port) +{ + struct mlxsw_sp_port *mlxsw_sp_vport; + + mlxsw_sp_vport = mlxsw_sp_port_vport_find(mlxsw_sp_port, 1); + if (WARN_ON(!mlxsw_sp_vport)) + return; + + mlxsw_sp_vport_vrf_leave(mlxsw_sp_vport); +} + +int mlxsw_sp_bridge_vrf_join(struct mlxsw_sp *mlxsw_sp, + struct net_device *l3_dev) +{ + struct mlxsw_sp_fid *f; + + f = mlxsw_sp_bridge_fid_get(mlxsw_sp, l3_dev); + if (WARN_ON(!f)) + return -EINVAL; + + if (f->r) + mlxsw_sp_rif_bridge_destroy(mlxsw_sp, f->r); + + return mlxsw_sp_rif_bridge_create(mlxsw_sp, l3_dev, f); +} + +void mlxsw_sp_bridge_vrf_leave(struct mlxsw_sp *mlxsw_sp, + struct net_device *l3_dev) +{ + struct mlxsw_sp_fid *f; + + f = mlxsw_sp_bridge_fid_get(mlxsw_sp, l3_dev); + if (WARN_ON(!f)) + return; + mlxsw_sp_rif_bridge_destroy(mlxsw_sp, f->r); +} + static void mlxsw_sp_router_fib_dump_flush(struct notifier_block *nb) { struct mlxsw_sp *mlxsw_sp = container_of(nb, struct mlxsw_sp, fib_nb); @@ -2606,6 +3305,48 @@ static void mlxsw_sp_router_fib_dump_flush(struct notifier_block *nb) mlxsw_sp_router_fib_flush(mlxsw_sp); } +static int __mlxsw_sp_router_init(struct mlxsw_sp *mlxsw_sp) +{ + char rgcr_pl[MLXSW_REG_RGCR_LEN]; + u64 max_rifs; + int err; + + if (!MLXSW_CORE_RES_VALID(mlxsw_sp->core, MAX_RIFS)) + return -EIO; + + max_rifs = MLXSW_CORE_RES_GET(mlxsw_sp->core, MAX_RIFS); + mlxsw_sp->rifs = kcalloc(max_rifs, sizeof(struct mlxsw_sp_rif *), + GFP_KERNEL); + if (!mlxsw_sp->rifs) + return -ENOMEM; + + mlxsw_reg_rgcr_pack(rgcr_pl, true); + mlxsw_reg_rgcr_max_router_interfaces_set(rgcr_pl, max_rifs); + err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(rgcr), rgcr_pl); + if (err) + goto err_rgcr_fail; + + return 0; + +err_rgcr_fail: + kfree(mlxsw_sp->rifs); + return err; +} + +static void __mlxsw_sp_router_fini(struct mlxsw_sp *mlxsw_sp) +{ + char rgcr_pl[MLXSW_REG_RGCR_LEN]; + int i; + + mlxsw_reg_rgcr_pack(rgcr_pl, false); + mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(rgcr), rgcr_pl); + + for (i = 0; i < MLXSW_CORE_RES_GET(mlxsw_sp->core, MAX_RIFS); i++) + WARN_ON_ONCE(mlxsw_sp->rifs[i]); + + kfree(mlxsw_sp->rifs); +} + int mlxsw_sp_router_init(struct mlxsw_sp *mlxsw_sp) { int err; diff --git a/drivers/net/ethernet/micrel/ks8851.c b/drivers/net/ethernet/micrel/ks8851.c index 279ee4612981..20358f87de57 100644 --- a/drivers/net/ethernet/micrel/ks8851.c +++ b/drivers/net/ethernet/micrel/ks8851.c @@ -212,25 +212,6 @@ static void ks8851_wrreg8(struct ks8851_net *ks, unsigned reg, unsigned val) } /** - * ks8851_rx_1msg - select whether to use one or two messages for spi read - * @ks: The device structure - * - * Return whether to generate a single message with a tx and rx buffer - * supplied to spi_sync(), or alternatively send the tx and rx buffers - * as separate messages. - * - * Depending on the hardware in use, a single message may be more efficient - * on interrupts or work done by the driver. - * - * This currently always returns true until we add some per-device data passed - * from the platform code to specify which mode is better. - */ -static inline bool ks8851_rx_1msg(struct ks8851_net *ks) -{ - return true; -} - -/** * ks8851_rdreg - issue read register command and return the data * @ks: The device state * @op: The register address and byte enables in message format. @@ -251,14 +232,7 @@ static void ks8851_rdreg(struct ks8851_net *ks, unsigned op, txb[0] = cpu_to_le16(op | KS_SPIOP_RD); - if (ks8851_rx_1msg(ks)) { - msg = &ks->spi_msg1; - xfer = &ks->spi_xfer1; - - xfer->tx_buf = txb; - xfer->rx_buf = trx; - xfer->len = rxl + 2; - } else { + if (ks->spidev->master->flags & SPI_MASTER_HALF_DUPLEX) { msg = &ks->spi_msg2; xfer = ks->spi_xfer2; @@ -270,15 +244,22 @@ static void ks8851_rdreg(struct ks8851_net *ks, unsigned op, xfer->tx_buf = NULL; xfer->rx_buf = trx; xfer->len = rxl; + } else { + msg = &ks->spi_msg1; + xfer = &ks->spi_xfer1; + + xfer->tx_buf = txb; + xfer->rx_buf = trx; + xfer->len = rxl + 2; } ret = spi_sync(ks->spidev, msg); if (ret < 0) netdev_err(ks->netdev, "read: spi_sync() failed\n"); - else if (ks8851_rx_1msg(ks)) - memcpy(rxb, trx + 2, rxl); - else + else if (ks->spidev->master->flags & SPI_MASTER_HALF_DUPLEX) memcpy(rxb, trx, rxl); + else + memcpy(rxb, trx + 2, rxl); } /** diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net.h b/drivers/net/ethernet/netronome/nfp/nfp_net.h index e614a376b595..4d45f4573b57 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net.h +++ b/drivers/net/ethernet/netronome/nfp/nfp_net.h @@ -50,14 +50,14 @@ #include "nfp_net_ctrl.h" -#define nn_err(nn, fmt, args...) netdev_err((nn)->netdev, fmt, ## args) -#define nn_warn(nn, fmt, args...) netdev_warn((nn)->netdev, fmt, ## args) -#define nn_info(nn, fmt, args...) netdev_info((nn)->netdev, fmt, ## args) -#define nn_dbg(nn, fmt, args...) netdev_dbg((nn)->netdev, fmt, ## args) -#define nn_warn_ratelimit(nn, fmt, args...) \ +#define nn_err(nn, fmt, args...) netdev_err((nn)->dp.netdev, fmt, ## args) +#define nn_warn(nn, fmt, args...) netdev_warn((nn)->dp.netdev, fmt, ## args) +#define nn_info(nn, fmt, args...) netdev_info((nn)->dp.netdev, fmt, ## args) +#define nn_dbg(nn, fmt, args...) netdev_dbg((nn)->dp.netdev, fmt, ## args) +#define nn_dp_warn(dp, fmt, args...) \ do { \ if (unlikely(net_ratelimit())) \ - netdev_warn((nn)->netdev, fmt, ## args); \ + netdev_warn((dp)->netdev, fmt, ## args); \ } while (0) /* Max time to wait for NFP to respond on updates (in seconds) */ @@ -112,6 +112,7 @@ /* Forward declarations */ struct nfp_cpp; +struct nfp_eth_table_port; struct nfp_net; struct nfp_net_r_vector; @@ -315,8 +316,6 @@ struct nfp_net_rx_buf { * @rxds: Virtual address of FL/RX ring in host memory * @dma: DMA address of the FL/RX ring * @size: Size, in bytes, of the FL/RX ring (needed to free) - * @bufsz: Buffer allocation size for convenience of management routines - * (NOTE: this is in second cache line, do not use on fast path!) */ struct nfp_net_rx_ring { struct nfp_net_r_vector *r_vec; @@ -338,7 +337,6 @@ struct nfp_net_rx_ring { dma_addr_t dma; unsigned int size; - unsigned int bufsz; } ____cacheline_aligned; /** @@ -433,19 +431,76 @@ struct nfp_stat_pair { }; /** - * struct nfp_net - NFP network device structure - * @pdev: Backpointer to PCI device - * @netdev: Backpointer to net_device structure - * @is_vf: Is the driver attached to a VF? + * struct nfp_net_dp - NFP network device datapath data structure + * @dev: Backpointer to struct device + * @netdev: Backpointer to net_device structure + * @is_vf: Is the driver attached to a VF? * @bpf_offload_skip_sw: Offloaded BPF program will not be rerun by cls_bpf * @bpf_offload_xdp: Offloaded BPF program is XDP - * @ctrl: Local copy of the control register/word. - * @fl_bufsz: Currently configured size of the freelist buffers + * @chained_metadata_format: Firemware will use new metadata format + * @rx_dma_dir: Mapping direction for RX buffers + * @rx_dma_off: Offset at which DMA packets (for XDP headroom) * @rx_offset: Offset in the RX buffers where packet data starts + * @ctrl: Local copy of the control register/word. + * @fl_bufsz: Currently configured size of the freelist buffers * @xdp_prog: Installed XDP program - * @fw_ver: Firmware version + * @tx_rings: Array of pre-allocated TX ring structures + * @rx_rings: Array of pre-allocated RX ring structures + * @ctrl_bar: Pointer to mapped control BAR + * + * @txd_cnt: Size of the TX ring in number of descriptors + * @rxd_cnt: Size of the RX ring in number of descriptors + * @num_r_vecs: Number of used ring vectors + * @num_tx_rings: Currently configured number of TX rings + * @num_stack_tx_rings: Number of TX rings used by the stack (not XDP) + * @num_rx_rings: Currently configured number of RX rings + * @mtu: Device MTU + */ +struct nfp_net_dp { + struct device *dev; + struct net_device *netdev; + + u8 is_vf:1; + u8 bpf_offload_skip_sw:1; + u8 bpf_offload_xdp:1; + u8 chained_metadata_format:1; + + u8 rx_dma_dir; + u8 rx_dma_off; + + u8 rx_offset; + + u32 ctrl; + u32 fl_bufsz; + + struct bpf_prog *xdp_prog; + + struct nfp_net_tx_ring *tx_rings; + struct nfp_net_rx_ring *rx_rings; + + u8 __iomem *ctrl_bar; + + /* Cold data follows */ + + unsigned int txd_cnt; + unsigned int rxd_cnt; + + unsigned int num_r_vecs; + + unsigned int num_tx_rings; + unsigned int num_stack_tx_rings; + unsigned int num_rx_rings; + + unsigned int mtu; +}; + +/** + * struct nfp_net - NFP network device structure + * @dp: Datapath structure + * @fw_ver: Firmware version * @cap: Capabilities advertised by the Firmware * @max_mtu: Maximum support MTU advertised by the Firmware + * @rss_hfunc: RSS selected hash function * @rss_cfg: RSS configuration * @rss_key: RSS secret key * @rss_itbl: RSS indirection table @@ -454,17 +509,9 @@ struct nfp_stat_pair { * @rx_filter_change: Jiffies when statistics last changed * @rx_filter_stats_timer: Timer for polling filter offload statistics * @rx_filter_lock: Lock protecting timer state changes (teardown) + * @max_r_vecs: Number of allocated interrupt vectors for RX/TX * @max_tx_rings: Maximum number of TX rings supported by the Firmware * @max_rx_rings: Maximum number of RX rings supported by the Firmware - * @num_tx_rings: Currently configured number of TX rings - * @num_stack_tx_rings: Number of TX rings used by the stack (not XDP) - * @num_rx_rings: Currently configured number of RX rings - * @txd_cnt: Size of the TX ring in number of descriptors - * @rxd_cnt: Size of the RX ring in number of descriptors - * @tx_rings: Array of pre-allocated TX ring structures - * @rx_rings: Array of pre-allocated RX ring structures - * @max_r_vecs: Number of allocated interrupt vectors for RX/TX - * @num_r_vecs: Number of used ring vectors * @r_vecs: Pre-allocated array of ring vectors * @irq_entries: Pre-allocated array of MSI-X entries * @lsc_handler: Handler for Link State Change interrupt @@ -488,36 +535,24 @@ struct nfp_stat_pair { * @vxlan_ports: VXLAN ports for RX inner csum offload communicated to HW * @vxlan_usecnt: IPv4/IPv6 VXLAN port use counts * @qcp_cfg: Pointer to QCP queue used for configuration notification - * @ctrl_bar: Pointer to mapped control BAR * @tx_bar: Pointer to mapped TX queues * @rx_bar: Pointer to mapped FL/RX queues * @debugfs_dir: Device directory in debugfs * @ethtool_dump_flag: Ethtool dump flag * @port_list: Entry on device port list + * @pdev: Backpointer to PCI device * @cpp: CPP device handle if available + * @eth_port: Translated ETH Table port entry */ struct nfp_net { - struct pci_dev *pdev; - struct net_device *netdev; - - unsigned is_vf:1; - unsigned bpf_offload_skip_sw:1; - unsigned bpf_offload_xdp:1; - - u32 ctrl; - u32 fl_bufsz; - - u32 rx_offset; - - struct bpf_prog *xdp_prog; - - struct nfp_net_tx_ring *tx_rings; - struct nfp_net_rx_ring *rx_rings; + struct nfp_net_dp dp; struct nfp_net_fw_version fw_ver; + u32 cap; u32 max_mtu; + u8 rss_hfunc; u32 rss_cfg; u8 rss_key[NFP_NET_CFG_RSS_KEY_SZ]; u8 rss_itbl[NFP_NET_CFG_RSS_ITBL_SZ]; @@ -530,18 +565,10 @@ struct nfp_net { unsigned int max_tx_rings; unsigned int max_rx_rings; - unsigned int num_tx_rings; - unsigned int num_stack_tx_rings; - unsigned int num_rx_rings; - int stride_tx; int stride_rx; - int txd_cnt; - int rxd_cnt; - unsigned int max_r_vecs; - unsigned int num_r_vecs; struct nfp_net_r_vector r_vecs[NFP_NET_MAX_R_VECS]; struct msix_entry irq_entries[NFP_NET_MAX_IRQS]; @@ -575,7 +602,6 @@ struct nfp_net { u8 __iomem *qcp_cfg; - u8 __iomem *ctrl_bar; u8 __iomem *tx_bar; u8 __iomem *rx_bar; @@ -584,14 +610,10 @@ struct nfp_net { struct list_head port_list; + struct pci_dev *pdev; struct nfp_cpp *cpp; -}; -struct nfp_net_ring_set { - unsigned int n_rings; - unsigned int mtu; - unsigned int dcnt; - void *rings; + struct nfp_eth_table_port *eth_port; }; /* Functions to read/write from/to a BAR @@ -599,42 +621,42 @@ struct nfp_net_ring_set { */ static inline u16 nn_readb(struct nfp_net *nn, int off) { - return readb(nn->ctrl_bar + off); + return readb(nn->dp.ctrl_bar + off); } static inline void nn_writeb(struct nfp_net *nn, int off, u8 val) { - writeb(val, nn->ctrl_bar + off); + writeb(val, nn->dp.ctrl_bar + off); } static inline u16 nn_readw(struct nfp_net *nn, int off) { - return readw(nn->ctrl_bar + off); + return readw(nn->dp.ctrl_bar + off); } static inline void nn_writew(struct nfp_net *nn, int off, u16 val) { - writew(val, nn->ctrl_bar + off); + writew(val, nn->dp.ctrl_bar + off); } static inline u32 nn_readl(struct nfp_net *nn, int off) { - return readl(nn->ctrl_bar + off); + return readl(nn->dp.ctrl_bar + off); } static inline void nn_writel(struct nfp_net *nn, int off, u32 val) { - writel(val, nn->ctrl_bar + off); + writel(val, nn->dp.ctrl_bar + off); } static inline u64 nn_readq(struct nfp_net *nn, int off) { - return readq(nn->ctrl_bar + off); + return readq(nn->dp.ctrl_bar + off); } static inline void nn_writeq(struct nfp_net *nn, int off, u64 val) { - writeq(val, nn->ctrl_bar + off); + writeq(val, nn->dp.ctrl_bar + off); } /* Flush posted PCI writes by reading something without side effects */ @@ -776,6 +798,7 @@ void nfp_net_netdev_clean(struct net_device *netdev); void nfp_net_set_ethtool_ops(struct net_device *netdev); void nfp_net_info(struct nfp_net *nn); int nfp_net_reconfig(struct nfp_net *nn, u32 update); +unsigned int nfp_net_rss_key_sz(struct nfp_net *nn); void nfp_net_rss_write_itbl(struct nfp_net *nn); void nfp_net_rss_write_key(struct nfp_net *nn); void nfp_net_coalesce_write_cfg(struct nfp_net *nn); @@ -787,9 +810,9 @@ void nfp_net_irqs_disable(struct pci_dev *pdev); void nfp_net_irqs_assign(struct nfp_net *nn, struct msix_entry *irq_entries, unsigned int n); -int -nfp_net_ring_reconfig(struct nfp_net *nn, struct bpf_prog **xdp_prog, - struct nfp_net_ring_set *rx, struct nfp_net_ring_set *tx); + +struct nfp_net_dp *nfp_net_clone_dp(struct nfp_net *nn); +int nfp_net_ring_reconfig(struct nfp_net *nn, struct nfp_net_dp *new); #ifdef CONFIG_NFP_DEBUG void nfp_net_debugfs_create(void); diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c index 9179a99563af..f134f1808b9a 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c @@ -41,6 +41,7 @@ * Chris Telfer <[email protected]> */ +#include <linux/bitfield.h> #include <linux/bpf.h> #include <linux/bpf_trace.h> #include <linux/module.h> @@ -66,6 +67,7 @@ #include <net/pkt_cls.h> #include <net/vxlan.h> +#include "nfpcore/nfp_nsp_eth.h" #include "nfp_net_ctrl.h" #include "nfp_net.h" @@ -83,20 +85,18 @@ void nfp_net_get_fw_version(struct nfp_net_fw_version *fw_ver, put_unaligned_le32(reg, fw_ver); } -static dma_addr_t -nfp_net_dma_map_rx(struct nfp_net *nn, void *frag, unsigned int bufsz, - int direction) +static dma_addr_t nfp_net_dma_map_rx(struct nfp_net_dp *dp, void *frag) { - return dma_map_single(&nn->pdev->dev, frag + NFP_NET_RX_BUF_HEADROOM, - bufsz - NFP_NET_RX_BUF_NON_DATA, direction); + return dma_map_single(dp->dev, frag + NFP_NET_RX_BUF_HEADROOM, + dp->fl_bufsz - NFP_NET_RX_BUF_NON_DATA, + dp->rx_dma_dir); } -static void -nfp_net_dma_unmap_rx(struct nfp_net *nn, dma_addr_t dma_addr, - unsigned int bufsz, int direction) +static void nfp_net_dma_unmap_rx(struct nfp_net_dp *dp, dma_addr_t dma_addr) { - dma_unmap_single(&nn->pdev->dev, dma_addr, - bufsz - NFP_NET_RX_BUF_NON_DATA, direction); + dma_unmap_single(dp->dev, dma_addr, + dp->fl_bufsz - NFP_NET_RX_BUF_NON_DATA, + dp->rx_dma_dir); } /* Firmware reconfig @@ -327,19 +327,22 @@ void nfp_net_irqs_assign(struct nfp_net *nn, struct msix_entry *irq_entries, unsigned int n) { + struct nfp_net_dp *dp = &nn->dp; + nn->max_r_vecs = n - NFP_NET_NON_Q_VECTORS; - nn->num_r_vecs = nn->max_r_vecs; + dp->num_r_vecs = nn->max_r_vecs; memcpy(nn->irq_entries, irq_entries, sizeof(*irq_entries) * n); - if (nn->num_rx_rings > nn->num_r_vecs || - nn->num_tx_rings > nn->num_r_vecs) + if (dp->num_rx_rings > dp->num_r_vecs || + dp->num_tx_rings > dp->num_r_vecs) nn_warn(nn, "More rings (%d,%d) than vectors (%d).\n", - nn->num_rx_rings, nn->num_tx_rings, nn->num_r_vecs); + dp->num_rx_rings, dp->num_tx_rings, + dp->num_r_vecs); - nn->num_rx_rings = min(nn->num_r_vecs, nn->num_rx_rings); - nn->num_tx_rings = min(nn->num_r_vecs, nn->num_tx_rings); - nn->num_stack_tx_rings = nn->num_tx_rings; + dp->num_rx_rings = min(dp->num_r_vecs, dp->num_rx_rings); + dp->num_tx_rings = min(dp->num_r_vecs, dp->num_tx_rings); + dp->num_stack_tx_rings = dp->num_tx_rings; } /** @@ -394,11 +397,11 @@ static void nfp_net_read_link_status(struct nfp_net *nn) nn->link_up = link_up; if (nn->link_up) { - netif_carrier_on(nn->netdev); - netdev_info(nn->netdev, "NIC Link is Up\n"); + netif_carrier_on(nn->dp.netdev); + netdev_info(nn->dp.netdev, "NIC Link is Up\n"); } else { - netif_carrier_off(nn->netdev); - netdev_info(nn->netdev, "NIC Link is Down\n"); + netif_carrier_off(nn->dp.netdev); + netdev_info(nn->dp.netdev, "NIC Link is Down\n"); } out: spin_unlock_irqrestore(&nn->link_status_lock, flags); @@ -530,7 +533,7 @@ nfp_net_aux_irq_request(struct nfp_net *nn, u32 ctrl_offset, entry = &nn->irq_entries[vector_idx]; - snprintf(name, name_sz, format, netdev_name(nn->netdev)); + snprintf(name, name_sz, format, netdev_name(nn->dp.netdev)); err = request_irq(entry->vector, handler, 0, name, nn); if (err) { nn_err(nn, "Failed to request IRQ %d (err=%d).\n", @@ -617,7 +620,6 @@ static void nfp_net_tx_ring_stop(struct netdev_queue *nd_q, /** * nfp_net_tx_tso() - Set up Tx descriptor for LSO - * @nn: NFP Net device * @r_vec: per-ring structure * @txbuf: Pointer to driver soft TX descriptor * @txd: Pointer to HW TX descriptor @@ -626,7 +628,7 @@ static void nfp_net_tx_ring_stop(struct netdev_queue *nd_q, * Set up Tx descriptor for LSO, do nothing for non-LSO skbs. * Return error on packet header greater than maximum supported LSO header size. */ -static void nfp_net_tx_tso(struct nfp_net *nn, struct nfp_net_r_vector *r_vec, +static void nfp_net_tx_tso(struct nfp_net_r_vector *r_vec, struct nfp_net_tx_buf *txbuf, struct nfp_net_tx_desc *txd, struct sk_buff *skb) { @@ -657,7 +659,7 @@ static void nfp_net_tx_tso(struct nfp_net *nn, struct nfp_net_r_vector *r_vec, /** * nfp_net_tx_csum() - Set TX CSUM offload flags in TX descriptor - * @nn: NFP Net device + * @dp: NFP Net data path struct * @r_vec: per-ring structure * @txbuf: Pointer to driver soft TX descriptor * @txd: Pointer to TX descriptor @@ -666,7 +668,8 @@ static void nfp_net_tx_tso(struct nfp_net *nn, struct nfp_net_r_vector *r_vec, * This function sets the TX checksum flags in the TX descriptor based * on the configuration and the protocol of the packet to be transmitted. */ -static void nfp_net_tx_csum(struct nfp_net *nn, struct nfp_net_r_vector *r_vec, +static void nfp_net_tx_csum(struct nfp_net_dp *dp, + struct nfp_net_r_vector *r_vec, struct nfp_net_tx_buf *txbuf, struct nfp_net_tx_desc *txd, struct sk_buff *skb) { @@ -674,7 +677,7 @@ static void nfp_net_tx_csum(struct nfp_net *nn, struct nfp_net_r_vector *r_vec, struct iphdr *iph; u8 l4_hdr; - if (!(nn->ctrl & NFP_NET_CFG_CTRL_TXCSUM)) + if (!(dp->ctrl & NFP_NET_CFG_CTRL_TXCSUM)) return; if (skb->ip_summed != CHECKSUM_PARTIAL) @@ -693,8 +696,7 @@ static void nfp_net_tx_csum(struct nfp_net *nn, struct nfp_net_r_vector *r_vec, } else if (ipv6h->version == 6) { l4_hdr = ipv6h->nexthdr; } else { - nn_warn_ratelimit(nn, "partial checksum but ipv=%x!\n", - iph->version); + nn_dp_warn(dp, "partial checksum but ipv=%x!\n", iph->version); return; } @@ -706,8 +708,7 @@ static void nfp_net_tx_csum(struct nfp_net *nn, struct nfp_net_r_vector *r_vec, txd->flags |= PCIE_DESC_TX_UDP_CSUM; break; default: - nn_warn_ratelimit(nn, "partial checksum but l4 proto=%x!\n", - l4_hdr); + nn_dp_warn(dp, "partial checksum but l4 proto=%x!\n", l4_hdr); return; } @@ -737,27 +738,29 @@ static int nfp_net_tx(struct sk_buff *skb, struct net_device *netdev) { struct nfp_net *nn = netdev_priv(netdev); const struct skb_frag_struct *frag; - struct nfp_net_r_vector *r_vec; struct nfp_net_tx_desc *txd, txdg; - struct nfp_net_tx_buf *txbuf; struct nfp_net_tx_ring *tx_ring; + struct nfp_net_r_vector *r_vec; + struct nfp_net_tx_buf *txbuf; struct netdev_queue *nd_q; + struct nfp_net_dp *dp; dma_addr_t dma_addr; unsigned int fsize; int f, nr_frags; int wr_idx; u16 qidx; + dp = &nn->dp; qidx = skb_get_queue_mapping(skb); - tx_ring = &nn->tx_rings[qidx]; + tx_ring = &dp->tx_rings[qidx]; r_vec = tx_ring->r_vec; - nd_q = netdev_get_tx_queue(nn->netdev, qidx); + nd_q = netdev_get_tx_queue(dp->netdev, qidx); nr_frags = skb_shinfo(skb)->nr_frags; if (unlikely(nfp_net_tx_full(tx_ring, nr_frags + 1))) { - nn_warn_ratelimit(nn, "TX ring %d busy. wrp=%u rdp=%u\n", - qidx, tx_ring->wr_p, tx_ring->rd_p); + nn_dp_warn(dp, "TX ring %d busy. wrp=%u rdp=%u\n", + qidx, tx_ring->wr_p, tx_ring->rd_p); netif_tx_stop_queue(nd_q); u64_stats_update_begin(&r_vec->tx_sync); r_vec->tx_busy++; @@ -766,9 +769,9 @@ static int nfp_net_tx(struct sk_buff *skb, struct net_device *netdev) } /* Start with the head skbuf */ - dma_addr = dma_map_single(&nn->pdev->dev, skb->data, skb_headlen(skb), + dma_addr = dma_map_single(dp->dev, skb->data, skb_headlen(skb), DMA_TO_DEVICE); - if (dma_mapping_error(&nn->pdev->dev, dma_addr)) + if (dma_mapping_error(dp->dev, dma_addr)) goto err_free; wr_idx = tx_ring->wr_p & (tx_ring->cnt - 1); @@ -792,11 +795,11 @@ static int nfp_net_tx(struct sk_buff *skb, struct net_device *netdev) txd->mss = 0; txd->l4_offset = 0; - nfp_net_tx_tso(nn, r_vec, txbuf, txd, skb); + nfp_net_tx_tso(r_vec, txbuf, txd, skb); - nfp_net_tx_csum(nn, r_vec, txbuf, txd, skb); + nfp_net_tx_csum(dp, r_vec, txbuf, txd, skb); - if (skb_vlan_tag_present(skb) && nn->ctrl & NFP_NET_CFG_CTRL_TXVLAN) { + if (skb_vlan_tag_present(skb) && dp->ctrl & NFP_NET_CFG_CTRL_TXVLAN) { txd->flags |= PCIE_DESC_TX_VLAN; txd->vlan = cpu_to_le16(skb_vlan_tag_get(skb)); } @@ -810,9 +813,9 @@ static int nfp_net_tx(struct sk_buff *skb, struct net_device *netdev) frag = &skb_shinfo(skb)->frags[f]; fsize = skb_frag_size(frag); - dma_addr = skb_frag_dma_map(&nn->pdev->dev, frag, 0, + dma_addr = skb_frag_dma_map(dp->dev, frag, 0, fsize, DMA_TO_DEVICE); - if (dma_mapping_error(&nn->pdev->dev, dma_addr)) + if (dma_mapping_error(dp->dev, dma_addr)) goto err_unmap; wr_idx = (wr_idx + 1) & (tx_ring->cnt - 1); @@ -851,8 +854,7 @@ err_unmap: --f; while (f >= 0) { frag = &skb_shinfo(skb)->frags[f]; - dma_unmap_page(&nn->pdev->dev, - tx_ring->txbufs[wr_idx].dma_addr, + dma_unmap_page(dp->dev, tx_ring->txbufs[wr_idx].dma_addr, skb_frag_size(frag), DMA_TO_DEVICE); tx_ring->txbufs[wr_idx].skb = NULL; tx_ring->txbufs[wr_idx].dma_addr = 0; @@ -861,13 +863,13 @@ err_unmap: if (wr_idx < 0) wr_idx += tx_ring->cnt; } - dma_unmap_single(&nn->pdev->dev, tx_ring->txbufs[wr_idx].dma_addr, + dma_unmap_single(dp->dev, tx_ring->txbufs[wr_idx].dma_addr, skb_headlen(skb), DMA_TO_DEVICE); tx_ring->txbufs[wr_idx].skb = NULL; tx_ring->txbufs[wr_idx].dma_addr = 0; tx_ring->txbufs[wr_idx].fidx = -2; err_free: - nn_warn_ratelimit(nn, "Failed to map DMA TX buffer\n"); + nn_dp_warn(dp, "Failed to map DMA TX buffer\n"); u64_stats_update_begin(&r_vec->tx_sync); r_vec->tx_errors++; u64_stats_update_end(&r_vec->tx_sync); @@ -884,7 +886,7 @@ err_free: static void nfp_net_tx_complete(struct nfp_net_tx_ring *tx_ring) { struct nfp_net_r_vector *r_vec = tx_ring->r_vec; - struct nfp_net *nn = r_vec->nfp_net; + struct nfp_net_dp *dp = &r_vec->nfp_net->dp; const struct skb_frag_struct *frag; struct netdev_queue *nd_q; u32 done_pkts = 0, done_bytes = 0; @@ -918,8 +920,7 @@ static void nfp_net_tx_complete(struct nfp_net_tx_ring *tx_ring) if (fidx == -1) { /* unmap head */ - dma_unmap_single(&nn->pdev->dev, - tx_ring->txbufs[idx].dma_addr, + dma_unmap_single(dp->dev, tx_ring->txbufs[idx].dma_addr, skb_headlen(skb), DMA_TO_DEVICE); done_pkts += tx_ring->txbufs[idx].pkt_cnt; @@ -927,8 +928,7 @@ static void nfp_net_tx_complete(struct nfp_net_tx_ring *tx_ring) } else { /* unmap fragment */ frag = &skb_shinfo(skb)->frags[fidx]; - dma_unmap_page(&nn->pdev->dev, - tx_ring->txbufs[idx].dma_addr, + dma_unmap_page(dp->dev, tx_ring->txbufs[idx].dma_addr, skb_frag_size(frag), DMA_TO_DEVICE); } @@ -948,7 +948,7 @@ static void nfp_net_tx_complete(struct nfp_net_tx_ring *tx_ring) r_vec->tx_pkts += done_pkts; u64_stats_update_end(&r_vec->tx_sync); - nd_q = netdev_get_tx_queue(nn->netdev, tx_ring->idx); + nd_q = netdev_get_tx_queue(dp->netdev, tx_ring->idx); netdev_tx_completed_queue(nd_q, done_pkts, done_bytes); if (nfp_net_tx_ring_should_wake(tx_ring)) { /* Make sure TX thread will see updated tx_ring->rd_p */ @@ -966,7 +966,7 @@ static void nfp_net_tx_complete(struct nfp_net_tx_ring *tx_ring) static void nfp_net_xdp_complete(struct nfp_net_tx_ring *tx_ring) { struct nfp_net_r_vector *r_vec = tx_ring->r_vec; - struct nfp_net *nn = r_vec->nfp_net; + struct nfp_net_dp *dp = &r_vec->nfp_net->dp; u32 done_pkts = 0, done_bytes = 0; int idx, todo; u32 qcp_rd_p; @@ -989,8 +989,7 @@ static void nfp_net_xdp_complete(struct nfp_net_tx_ring *tx_ring) if (!tx_ring->txbufs[idx].frag) continue; - nfp_net_dma_unmap_rx(nn, tx_ring->txbufs[idx].dma_addr, - nn->fl_bufsz, DMA_BIDIRECTIONAL); + nfp_net_dma_unmap_rx(dp, tx_ring->txbufs[idx].dma_addr); __free_page(virt_to_page(tx_ring->txbufs[idx].frag)); done_pkts++; @@ -1015,17 +1014,16 @@ static void nfp_net_xdp_complete(struct nfp_net_tx_ring *tx_ring) /** * nfp_net_tx_ring_reset() - Free any untransmitted buffers and reset pointers - * @nn: NFP Net device + * @dp: NFP Net data path struct * @tx_ring: TX ring structure * * Assumes that the device is stopped */ static void -nfp_net_tx_ring_reset(struct nfp_net *nn, struct nfp_net_tx_ring *tx_ring) +nfp_net_tx_ring_reset(struct nfp_net_dp *dp, struct nfp_net_tx_ring *tx_ring) { struct nfp_net_r_vector *r_vec = tx_ring->r_vec; const struct skb_frag_struct *frag; - struct pci_dev *pdev = nn->pdev; struct netdev_queue *nd_q; while (tx_ring->rd_p != tx_ring->wr_p) { @@ -1036,8 +1034,7 @@ nfp_net_tx_ring_reset(struct nfp_net *nn, struct nfp_net_tx_ring *tx_ring) tx_buf = &tx_ring->txbufs[idx]; if (tx_ring == r_vec->xdp_ring) { - nfp_net_dma_unmap_rx(nn, tx_buf->dma_addr, - nn->fl_bufsz, DMA_BIDIRECTIONAL); + nfp_net_dma_unmap_rx(dp, tx_buf->dma_addr); __free_page(virt_to_page(tx_ring->txbufs[idx].frag)); } else { struct sk_buff *skb = tx_ring->txbufs[idx].skb; @@ -1045,13 +1042,13 @@ nfp_net_tx_ring_reset(struct nfp_net *nn, struct nfp_net_tx_ring *tx_ring) if (tx_buf->fidx == -1) { /* unmap head */ - dma_unmap_single(&pdev->dev, tx_buf->dma_addr, + dma_unmap_single(dp->dev, tx_buf->dma_addr, skb_headlen(skb), DMA_TO_DEVICE); } else { /* unmap fragment */ frag = &skb_shinfo(skb)->frags[tx_buf->fidx]; - dma_unmap_page(&pdev->dev, tx_buf->dma_addr, + dma_unmap_page(dp->dev, tx_buf->dma_addr, skb_frag_size(frag), DMA_TO_DEVICE); } @@ -1078,7 +1075,7 @@ nfp_net_tx_ring_reset(struct nfp_net *nn, struct nfp_net_tx_ring *tx_ring) if (tx_ring == r_vec->xdp_ring) return; - nd_q = netdev_get_tx_queue(nn->netdev, tx_ring->idx); + nd_q = netdev_get_tx_queue(dp->netdev, tx_ring->idx); netdev_tx_reset_queue(nd_q); } @@ -1087,7 +1084,7 @@ static void nfp_net_tx_timeout(struct net_device *netdev) struct nfp_net *nn = netdev_priv(netdev); int i; - for (i = 0; i < nn->netdev->real_num_tx_queues; i++) { + for (i = 0; i < nn->dp.netdev->real_num_tx_queues; i++) { if (!netif_tx_queue_stopped(netdev_get_tx_queue(netdev, i))) continue; nn_warn(nn, "TX timeout on ring: %d\n", i); @@ -1098,16 +1095,17 @@ static void nfp_net_tx_timeout(struct net_device *netdev) /* Receive processing */ static unsigned int -nfp_net_calc_fl_bufsz(struct nfp_net *nn, unsigned int mtu) +nfp_net_calc_fl_bufsz(struct nfp_net_dp *dp) { unsigned int fl_bufsz; fl_bufsz = NFP_NET_RX_BUF_HEADROOM; - if (nn->rx_offset == NFP_NET_CFG_RX_OFFSET_DYNAMIC) + fl_bufsz += dp->rx_dma_off; + if (dp->rx_offset == NFP_NET_CFG_RX_OFFSET_DYNAMIC) fl_bufsz += NFP_NET_MAX_PREPEND; else - fl_bufsz += nn->rx_offset; - fl_bufsz += ETH_HLEN + VLAN_HLEN * 2 + mtu; + fl_bufsz += dp->rx_offset; + fl_bufsz += ETH_HLEN + VLAN_HLEN * 2 + dp->mtu; fl_bufsz = SKB_DATA_ALIGN(fl_bufsz); fl_bufsz += SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); @@ -1126,62 +1124,56 @@ nfp_net_free_frag(void *frag, bool xdp) /** * nfp_net_rx_alloc_one() - Allocate and map page frag for RX + * @dp: NFP Net data path struct * @rx_ring: RX ring structure of the skb * @dma_addr: Pointer to storage for DMA address (output param) - * @fl_bufsz: size of freelist buffers - * @xdp: Whether XDP is enabled * * This function will allcate a new page frag, map it for DMA. * * Return: allocated page frag or NULL on failure. */ static void * -nfp_net_rx_alloc_one(struct nfp_net_rx_ring *rx_ring, dma_addr_t *dma_addr, - unsigned int fl_bufsz, bool xdp) +nfp_net_rx_alloc_one(struct nfp_net_dp *dp, struct nfp_net_rx_ring *rx_ring, + dma_addr_t *dma_addr) { - struct nfp_net *nn = rx_ring->r_vec->nfp_net; - int direction; void *frag; - if (!xdp) - frag = netdev_alloc_frag(fl_bufsz); + if (!dp->xdp_prog) + frag = netdev_alloc_frag(dp->fl_bufsz); else frag = page_address(alloc_page(GFP_KERNEL | __GFP_COLD)); if (!frag) { - nn_warn_ratelimit(nn, "Failed to alloc receive page frag\n"); + nn_dp_warn(dp, "Failed to alloc receive page frag\n"); return NULL; } - direction = xdp ? DMA_BIDIRECTIONAL : DMA_FROM_DEVICE; - - *dma_addr = nfp_net_dma_map_rx(nn, frag, fl_bufsz, direction); - if (dma_mapping_error(&nn->pdev->dev, *dma_addr)) { - nfp_net_free_frag(frag, xdp); - nn_warn_ratelimit(nn, "Failed to map DMA RX buffer\n"); + *dma_addr = nfp_net_dma_map_rx(dp, frag); + if (dma_mapping_error(dp->dev, *dma_addr)) { + nfp_net_free_frag(frag, dp->xdp_prog); + nn_dp_warn(dp, "Failed to map DMA RX buffer\n"); return NULL; } return frag; } -static void * -nfp_net_napi_alloc_one(struct nfp_net *nn, int direction, dma_addr_t *dma_addr) +static void *nfp_net_napi_alloc_one(struct nfp_net_dp *dp, dma_addr_t *dma_addr) { void *frag; - if (!nn->xdp_prog) - frag = napi_alloc_frag(nn->fl_bufsz); + if (!dp->xdp_prog) + frag = napi_alloc_frag(dp->fl_bufsz); else frag = page_address(alloc_page(GFP_ATOMIC | __GFP_COLD)); if (!frag) { - nn_warn_ratelimit(nn, "Failed to alloc receive page frag\n"); + nn_dp_warn(dp, "Failed to alloc receive page frag\n"); return NULL; } - *dma_addr = nfp_net_dma_map_rx(nn, frag, nn->fl_bufsz, direction); - if (dma_mapping_error(&nn->pdev->dev, *dma_addr)) { - nfp_net_free_frag(frag, nn->xdp_prog); - nn_warn_ratelimit(nn, "Failed to map DMA RX buffer\n"); + *dma_addr = nfp_net_dma_map_rx(dp, frag); + if (dma_mapping_error(dp->dev, *dma_addr)) { + nfp_net_free_frag(frag, dp->xdp_prog); + nn_dp_warn(dp, "Failed to map DMA RX buffer\n"); return NULL; } @@ -1190,11 +1182,13 @@ nfp_net_napi_alloc_one(struct nfp_net *nn, int direction, dma_addr_t *dma_addr) /** * nfp_net_rx_give_one() - Put mapped skb on the software and hardware rings + * @dp: NFP Net data path struct * @rx_ring: RX ring structure * @frag: page fragment buffer * @dma_addr: DMA address of skb mapping */ -static void nfp_net_rx_give_one(struct nfp_net_rx_ring *rx_ring, +static void nfp_net_rx_give_one(const struct nfp_net_dp *dp, + struct nfp_net_rx_ring *rx_ring, void *frag, dma_addr_t dma_addr) { unsigned int wr_idx; @@ -1208,7 +1202,8 @@ static void nfp_net_rx_give_one(struct nfp_net_rx_ring *rx_ring, /* Fill freelist descriptor */ rx_ring->rxds[wr_idx].fld.reserved = 0; rx_ring->rxds[wr_idx].fld.meta_len_dd = 0; - nfp_desc_set_dma_addr(&rx_ring->rxds[wr_idx].fld, dma_addr); + nfp_desc_set_dma_addr(&rx_ring->rxds[wr_idx].fld, + dma_addr + dp->rx_dma_off); rx_ring->wr_p++; rx_ring->wr_ptr_add++; @@ -1249,19 +1244,17 @@ static void nfp_net_rx_ring_reset(struct nfp_net_rx_ring *rx_ring) /** * nfp_net_rx_ring_bufs_free() - Free any buffers currently on the RX ring - * @nn: NFP Net device + * @dp: NFP Net data path struct * @rx_ring: RX ring to remove buffers from - * @xdp: Whether XDP is enabled * * Assumes that the device is stopped and buffers are in [0, ring->cnt - 1) * entries. After device is disabled nfp_net_rx_ring_reset() must be called * to restore required ring geometry. */ static void -nfp_net_rx_ring_bufs_free(struct nfp_net *nn, struct nfp_net_rx_ring *rx_ring, - bool xdp) +nfp_net_rx_ring_bufs_free(struct nfp_net_dp *dp, + struct nfp_net_rx_ring *rx_ring) { - int direction = xdp ? DMA_BIDIRECTIONAL : DMA_FROM_DEVICE; unsigned int i; for (i = 0; i < rx_ring->cnt - 1; i++) { @@ -1272,9 +1265,8 @@ nfp_net_rx_ring_bufs_free(struct nfp_net *nn, struct nfp_net_rx_ring *rx_ring, if (!rx_ring->rxbufs[i].frag) continue; - nfp_net_dma_unmap_rx(nn, rx_ring->rxbufs[i].dma_addr, - rx_ring->bufsz, direction); - nfp_net_free_frag(rx_ring->rxbufs[i].frag, xdp); + nfp_net_dma_unmap_rx(dp, rx_ring->rxbufs[i].dma_addr); + nfp_net_free_frag(rx_ring->rxbufs[i].frag, dp->xdp_prog); rx_ring->rxbufs[i].dma_addr = 0; rx_ring->rxbufs[i].frag = NULL; } @@ -1282,13 +1274,12 @@ nfp_net_rx_ring_bufs_free(struct nfp_net *nn, struct nfp_net_rx_ring *rx_ring, /** * nfp_net_rx_ring_bufs_alloc() - Fill RX ring with buffers (don't give to FW) - * @nn: NFP Net device + * @dp: NFP Net data path struct * @rx_ring: RX ring to remove buffers from - * @xdp: Whether XDP is enabled */ static int -nfp_net_rx_ring_bufs_alloc(struct nfp_net *nn, struct nfp_net_rx_ring *rx_ring, - bool xdp) +nfp_net_rx_ring_bufs_alloc(struct nfp_net_dp *dp, + struct nfp_net_rx_ring *rx_ring) { struct nfp_net_rx_buf *rxbufs; unsigned int i; @@ -1297,10 +1288,9 @@ nfp_net_rx_ring_bufs_alloc(struct nfp_net *nn, struct nfp_net_rx_ring *rx_ring, for (i = 0; i < rx_ring->cnt - 1; i++) { rxbufs[i].frag = - nfp_net_rx_alloc_one(rx_ring, &rxbufs[i].dma_addr, - rx_ring->bufsz, xdp); + nfp_net_rx_alloc_one(dp, rx_ring, &rxbufs[i].dma_addr); if (!rxbufs[i].frag) { - nfp_net_rx_ring_bufs_free(nn, rx_ring, xdp); + nfp_net_rx_ring_bufs_free(dp, rx_ring); return -ENOMEM; } } @@ -1310,14 +1300,17 @@ nfp_net_rx_ring_bufs_alloc(struct nfp_net *nn, struct nfp_net_rx_ring *rx_ring, /** * nfp_net_rx_ring_fill_freelist() - Give buffers from the ring to FW + * @dp: NFP Net data path struct * @rx_ring: RX ring to fill */ -static void nfp_net_rx_ring_fill_freelist(struct nfp_net_rx_ring *rx_ring) +static void +nfp_net_rx_ring_fill_freelist(struct nfp_net_dp *dp, + struct nfp_net_rx_ring *rx_ring) { unsigned int i; for (i = 0; i < rx_ring->cnt - 1; i++) - nfp_net_rx_give_one(rx_ring, rx_ring->rxbufs[i].frag, + nfp_net_rx_give_one(dp, rx_ring, rx_ring->rxbufs[i].frag, rx_ring->rxbufs[i].dma_addr); } @@ -1337,17 +1330,18 @@ static int nfp_net_rx_csum_has_errors(u16 flags) /** * nfp_net_rx_csum() - set SKB checksum field based on RX descriptor flags - * @nn: NFP Net device + * @dp: NFP Net data path struct * @r_vec: per-ring structure * @rxd: Pointer to RX descriptor * @skb: Pointer to SKB */ -static void nfp_net_rx_csum(struct nfp_net *nn, struct nfp_net_r_vector *r_vec, +static void nfp_net_rx_csum(struct nfp_net_dp *dp, + struct nfp_net_r_vector *r_vec, struct nfp_net_rx_desc *rxd, struct sk_buff *skb) { skb_checksum_none_assert(skb); - if (!(nn->netdev->features & NETIF_F_RXCSUM)) + if (!(dp->netdev->features & NETIF_F_RXCSUM)) return; if (nfp_net_rx_csum_has_errors(le16_to_cpu(rxd->rxd.flags))) { @@ -1398,24 +1392,21 @@ static void nfp_net_set_hash(struct net_device *netdev, struct sk_buff *skb, static void nfp_net_set_hash_desc(struct net_device *netdev, struct sk_buff *skb, - struct nfp_net_rx_desc *rxd) + void *data, struct nfp_net_rx_desc *rxd) { - struct nfp_net_rx_hash *rx_hash; + struct nfp_net_rx_hash *rx_hash = data; if (!(rxd->rxd.flags & PCIE_DESC_RX_RSS)) return; - rx_hash = (struct nfp_net_rx_hash *)(skb->data - sizeof(*rx_hash)); - nfp_net_set_hash(netdev, skb, get_unaligned_be32(&rx_hash->hash_type), &rx_hash->hash); } static void * nfp_net_parse_meta(struct net_device *netdev, struct sk_buff *skb, - int meta_len) + void *data, int meta_len) { - u8 *data = skb->data - meta_len; u32 meta_info; meta_info = get_unaligned_be32(data); @@ -1445,8 +1436,9 @@ nfp_net_parse_meta(struct net_device *netdev, struct sk_buff *skb, } static void -nfp_net_rx_drop(struct nfp_net_r_vector *r_vec, struct nfp_net_rx_ring *rx_ring, - struct nfp_net_rx_buf *rxbuf, struct sk_buff *skb) +nfp_net_rx_drop(const struct nfp_net_dp *dp, struct nfp_net_r_vector *r_vec, + struct nfp_net_rx_ring *rx_ring, struct nfp_net_rx_buf *rxbuf, + struct sk_buff *skb) { u64_stats_update_begin(&r_vec->rx_sync); r_vec->rx_drops++; @@ -1458,15 +1450,15 @@ nfp_net_rx_drop(struct nfp_net_r_vector *r_vec, struct nfp_net_rx_ring *rx_ring, if (skb && rxbuf && skb->head == rxbuf->frag) page_ref_inc(virt_to_head_page(rxbuf->frag)); if (rxbuf) - nfp_net_rx_give_one(rx_ring, rxbuf->frag, rxbuf->dma_addr); + nfp_net_rx_give_one(dp, rx_ring, rxbuf->frag, rxbuf->dma_addr); if (skb) dev_kfree_skb_any(skb); } static bool -nfp_net_tx_xdp_buf(struct nfp_net *nn, struct nfp_net_rx_ring *rx_ring, +nfp_net_tx_xdp_buf(struct nfp_net_dp *dp, struct nfp_net_rx_ring *rx_ring, struct nfp_net_tx_ring *tx_ring, - struct nfp_net_rx_buf *rxbuf, unsigned int pkt_off, + struct nfp_net_rx_buf *rxbuf, unsigned int dma_off, unsigned int pkt_len) { struct nfp_net_tx_buf *txbuf; @@ -1476,16 +1468,16 @@ nfp_net_tx_xdp_buf(struct nfp_net *nn, struct nfp_net_rx_ring *rx_ring, int wr_idx; if (unlikely(nfp_net_tx_full(tx_ring, 1))) { - nfp_net_rx_drop(rx_ring->r_vec, rx_ring, rxbuf, NULL); + nfp_net_rx_drop(dp, rx_ring->r_vec, rx_ring, rxbuf, NULL); return false; } - new_frag = nfp_net_napi_alloc_one(nn, DMA_BIDIRECTIONAL, &new_dma_addr); + new_frag = nfp_net_napi_alloc_one(dp, &new_dma_addr); if (unlikely(!new_frag)) { - nfp_net_rx_drop(rx_ring->r_vec, rx_ring, rxbuf, NULL); + nfp_net_rx_drop(dp, rx_ring->r_vec, rx_ring, rxbuf, NULL); return false; } - nfp_net_rx_give_one(rx_ring, new_frag, new_dma_addr); + nfp_net_rx_give_one(dp, rx_ring, new_frag, new_dma_addr); wr_idx = tx_ring->wr_p & (tx_ring->cnt - 1); @@ -1497,14 +1489,14 @@ nfp_net_tx_xdp_buf(struct nfp_net *nn, struct nfp_net_rx_ring *rx_ring, txbuf->pkt_cnt = 1; txbuf->real_len = pkt_len; - dma_sync_single_for_device(&nn->pdev->dev, rxbuf->dma_addr + pkt_off, + dma_sync_single_for_device(dp->dev, rxbuf->dma_addr + dma_off, pkt_len, DMA_BIDIRECTIONAL); /* Build TX descriptor */ txd = &tx_ring->txds[wr_idx]; txd->offset_eop = PCIE_DESC_TX_EOP; txd->dma_len = cpu_to_le16(pkt_len); - nfp_desc_set_dma_addr(txd, rxbuf->dma_addr + pkt_off); + nfp_desc_set_dma_addr(txd, rxbuf->dma_addr + dma_off); txd->data_len = cpu_to_le16(pkt_len); txd->flags = 0; @@ -1516,14 +1508,24 @@ nfp_net_tx_xdp_buf(struct nfp_net *nn, struct nfp_net_rx_ring *rx_ring, return true; } -static int nfp_net_run_xdp(struct bpf_prog *prog, void *data, unsigned int len) +static int nfp_net_run_xdp(struct bpf_prog *prog, void *data, void *hard_start, + unsigned int *off, unsigned int *len) { struct xdp_buff xdp; + void *orig_data; + int ret; + + xdp.data_hard_start = hard_start; + xdp.data = data + *off; + xdp.data_end = data + *off + *len; - xdp.data = data; - xdp.data_end = data + len; + orig_data = xdp.data; + ret = bpf_prog_run_xdp(prog, &xdp); - return bpf_prog_run_xdp(prog, &xdp); + *len -= xdp.data - orig_data; + *off += xdp.data - orig_data; + + return ret; } /** @@ -1540,27 +1542,27 @@ static int nfp_net_run_xdp(struct bpf_prog *prog, void *data, unsigned int len) static int nfp_net_rx(struct nfp_net_rx_ring *rx_ring, int budget) { struct nfp_net_r_vector *r_vec = rx_ring->r_vec; - struct nfp_net *nn = r_vec->nfp_net; + struct nfp_net_dp *dp = &r_vec->nfp_net->dp; struct nfp_net_tx_ring *tx_ring; struct bpf_prog *xdp_prog; unsigned int true_bufsz; struct sk_buff *skb; int pkts_polled = 0; - int rx_dma_map_dir; int idx; rcu_read_lock(); - xdp_prog = READ_ONCE(nn->xdp_prog); - rx_dma_map_dir = xdp_prog ? DMA_BIDIRECTIONAL : DMA_FROM_DEVICE; - true_bufsz = xdp_prog ? PAGE_SIZE : nn->fl_bufsz; + xdp_prog = READ_ONCE(dp->xdp_prog); + true_bufsz = xdp_prog ? PAGE_SIZE : dp->fl_bufsz; tx_ring = r_vec->xdp_ring; while (pkts_polled < budget) { - unsigned int meta_len, data_len, data_off, pkt_len, pkt_off; + unsigned int meta_len, data_len, data_off, pkt_len; + u8 meta_prepend[NFP_NET_MAX_PREPEND]; struct nfp_net_rx_buf *rxbuf; struct nfp_net_rx_desc *rxd; dma_addr_t new_dma_addr; void *new_frag; + u8 *meta; idx = rx_ring->rd_p & (rx_ring->cnt - 1); @@ -1593,11 +1595,11 @@ static int nfp_net_rx(struct nfp_net_rx_ring *rx_ring, int budget) data_len = le16_to_cpu(rxd->rxd.data_len); pkt_len = data_len - meta_len; - if (nn->rx_offset == NFP_NET_CFG_RX_OFFSET_DYNAMIC) - pkt_off = meta_len; + if (dp->rx_offset == NFP_NET_CFG_RX_OFFSET_DYNAMIC) + data_off = NFP_NET_RX_BUF_HEADROOM + meta_len; else - pkt_off = nn->rx_offset; - data_off = NFP_NET_RX_BUF_HEADROOM + pkt_off; + data_off = NFP_NET_RX_BUF_HEADROOM + dp->rx_offset; + data_off += dp->rx_dma_off; /* Stats update */ u64_stats_update_begin(&r_vec->rx_sync); @@ -1605,30 +1607,55 @@ static int nfp_net_rx(struct nfp_net_rx_ring *rx_ring, int budget) r_vec->rx_bytes += pkt_len; u64_stats_update_end(&r_vec->rx_sync); + /* Pointer to start of metadata */ + meta = rxbuf->frag + data_off - meta_len; + + if (unlikely(meta_len > NFP_NET_MAX_PREPEND || + (dp->rx_offset && meta_len > dp->rx_offset))) { + nn_dp_warn(dp, "oversized RX packet metadata %u\n", + meta_len); + nfp_net_rx_drop(dp, r_vec, rx_ring, rxbuf, NULL); + continue; + } + if (xdp_prog && !(rxd->rxd.flags & PCIE_DESC_RX_BPF && - nn->bpf_offload_xdp)) { + dp->bpf_offload_xdp)) { + unsigned int dma_off; + void *hard_start; int act; - dma_sync_single_for_cpu(&nn->pdev->dev, - rxbuf->dma_addr + pkt_off, - pkt_len, DMA_BIDIRECTIONAL); - act = nfp_net_run_xdp(xdp_prog, rxbuf->frag + data_off, - pkt_len); + hard_start = rxbuf->frag + NFP_NET_RX_BUF_HEADROOM; + dma_off = data_off - NFP_NET_RX_BUF_HEADROOM; + dma_sync_single_for_cpu(dp->dev, rxbuf->dma_addr, + dma_off + pkt_len, + DMA_BIDIRECTIONAL); + + /* Move prepend out of the way */ + if (xdp_prog->xdp_adjust_head) { + memcpy(meta_prepend, meta, meta_len); + meta = meta_prepend; + } + + act = nfp_net_run_xdp(xdp_prog, rxbuf->frag, hard_start, + &data_off, &pkt_len); switch (act) { case XDP_PASS: break; case XDP_TX: - if (unlikely(!nfp_net_tx_xdp_buf(nn, rx_ring, + dma_off = data_off - NFP_NET_RX_BUF_HEADROOM; + if (unlikely(!nfp_net_tx_xdp_buf(dp, rx_ring, tx_ring, rxbuf, - pkt_off, pkt_len))) - trace_xdp_exception(nn->netdev, xdp_prog, act); + dma_off, + pkt_len))) + trace_xdp_exception(dp->netdev, + xdp_prog, act); continue; default: bpf_warn_invalid_xdp_action(act); case XDP_ABORTED: - trace_xdp_exception(nn->netdev, xdp_prog, act); + trace_xdp_exception(dp->netdev, xdp_prog, act); case XDP_DROP: - nfp_net_rx_give_one(rx_ring, rxbuf->frag, + nfp_net_rx_give_one(dp, rx_ring, rxbuf->frag, rxbuf->dma_addr); continue; } @@ -1636,41 +1663,40 @@ static int nfp_net_rx(struct nfp_net_rx_ring *rx_ring, int budget) skb = build_skb(rxbuf->frag, true_bufsz); if (unlikely(!skb)) { - nfp_net_rx_drop(r_vec, rx_ring, rxbuf, NULL); + nfp_net_rx_drop(dp, r_vec, rx_ring, rxbuf, NULL); continue; } - new_frag = nfp_net_napi_alloc_one(nn, rx_dma_map_dir, - &new_dma_addr); + new_frag = nfp_net_napi_alloc_one(dp, &new_dma_addr); if (unlikely(!new_frag)) { - nfp_net_rx_drop(r_vec, rx_ring, rxbuf, skb); + nfp_net_rx_drop(dp, r_vec, rx_ring, rxbuf, skb); continue; } - nfp_net_dma_unmap_rx(nn, rxbuf->dma_addr, nn->fl_bufsz, - rx_dma_map_dir); + nfp_net_dma_unmap_rx(dp, rxbuf->dma_addr); - nfp_net_rx_give_one(rx_ring, new_frag, new_dma_addr); + nfp_net_rx_give_one(dp, rx_ring, new_frag, new_dma_addr); skb_reserve(skb, data_off); skb_put(skb, pkt_len); - if (nn->fw_ver.major <= 3) { - nfp_net_set_hash_desc(nn->netdev, skb, rxd); + if (!dp->chained_metadata_format) { + nfp_net_set_hash_desc(dp->netdev, skb, meta, rxd); } else if (meta_len) { void *end; - end = nfp_net_parse_meta(nn->netdev, skb, meta_len); - if (unlikely(end != skb->data)) { - nn_warn_ratelimit(nn, "invalid RX packet metadata\n"); - nfp_net_rx_drop(r_vec, rx_ring, NULL, skb); + end = nfp_net_parse_meta(dp->netdev, skb, meta, + meta_len); + if (unlikely(end != meta + meta_len)) { + nn_dp_warn(dp, "invalid RX packet metadata\n"); + nfp_net_rx_drop(dp, r_vec, rx_ring, NULL, skb); continue; } } skb_record_rx_queue(skb, rx_ring->idx); - skb->protocol = eth_type_trans(skb, nn->netdev); + skb->protocol = eth_type_trans(skb, dp->netdev); - nfp_net_rx_csum(nn, r_vec, rxd, skb); + nfp_net_rx_csum(dp, r_vec, rxd, skb); if (rxd->rxd.flags & PCIE_DESC_RX_VLAN) __vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), @@ -1707,10 +1733,9 @@ static int nfp_net_poll(struct napi_struct *napi, int budget) nfp_net_xdp_complete(r_vec->xdp_ring); } - if (pkts_polled < budget) { - napi_complete_done(napi, pkts_polled); - nfp_net_irq_unmask(r_vec->nfp_net, r_vec->irq_entry); - } + if (pkts_polled < budget) + if (napi_complete_done(napi, pkts_polled)) + nfp_net_irq_unmask(r_vec->nfp_net, r_vec->irq_entry); return pkts_polled; } @@ -1725,13 +1750,12 @@ static int nfp_net_poll(struct napi_struct *napi, int budget) static void nfp_net_tx_ring_free(struct nfp_net_tx_ring *tx_ring) { struct nfp_net_r_vector *r_vec = tx_ring->r_vec; - struct nfp_net *nn = r_vec->nfp_net; - struct pci_dev *pdev = nn->pdev; + struct nfp_net_dp *dp = &r_vec->nfp_net->dp; kfree(tx_ring->txbufs); if (tx_ring->txds) - dma_free_coherent(&pdev->dev, tx_ring->size, + dma_free_coherent(dp->dev, tx_ring->size, tx_ring->txds, tx_ring->dma); tx_ring->cnt = 0; @@ -1743,24 +1767,23 @@ static void nfp_net_tx_ring_free(struct nfp_net_tx_ring *tx_ring) /** * nfp_net_tx_ring_alloc() - Allocate resource for a TX ring + * @dp: NFP Net data path struct * @tx_ring: TX Ring structure to allocate - * @cnt: Ring buffer count * @is_xdp: True if ring will be used for XDP * * Return: 0 on success, negative errno otherwise. */ static int -nfp_net_tx_ring_alloc(struct nfp_net_tx_ring *tx_ring, u32 cnt, bool is_xdp) +nfp_net_tx_ring_alloc(struct nfp_net_dp *dp, struct nfp_net_tx_ring *tx_ring, + bool is_xdp) { struct nfp_net_r_vector *r_vec = tx_ring->r_vec; - struct nfp_net *nn = r_vec->nfp_net; - struct pci_dev *pdev = nn->pdev; int sz; - tx_ring->cnt = cnt; + tx_ring->cnt = dp->txd_cnt; tx_ring->size = sizeof(*tx_ring->txds) * tx_ring->cnt; - tx_ring->txds = dma_zalloc_coherent(&pdev->dev, tx_ring->size, + tx_ring->txds = dma_zalloc_coherent(dp->dev, tx_ring->size, &tx_ring->dma, GFP_KERNEL); if (!tx_ring->txds) goto err_alloc; @@ -1771,14 +1794,9 @@ nfp_net_tx_ring_alloc(struct nfp_net_tx_ring *tx_ring, u32 cnt, bool is_xdp) goto err_alloc; if (!is_xdp) - netif_set_xps_queue(nn->netdev, &r_vec->affinity_mask, + netif_set_xps_queue(dp->netdev, &r_vec->affinity_mask, tx_ring->idx); - nn_dbg(nn, "TxQ%02d: QCidx=%02d cnt=%d dma=%#llx host=%p %s\n", - tx_ring->idx, tx_ring->qcidx, - tx_ring->cnt, (unsigned long long)tx_ring->dma, tx_ring->txds, - is_xdp ? "XDP" : ""); - return 0; err_alloc: @@ -1786,62 +1804,45 @@ err_alloc: return -ENOMEM; } -static struct nfp_net_tx_ring * -nfp_net_tx_ring_set_prepare(struct nfp_net *nn, struct nfp_net_ring_set *s, - unsigned int num_stack_tx_rings) +static int nfp_net_tx_rings_prepare(struct nfp_net *nn, struct nfp_net_dp *dp) { - struct nfp_net_tx_ring *rings; unsigned int r; - rings = kcalloc(s->n_rings, sizeof(*rings), GFP_KERNEL); - if (!rings) - return NULL; + dp->tx_rings = kcalloc(dp->num_tx_rings, sizeof(*dp->tx_rings), + GFP_KERNEL); + if (!dp->tx_rings) + return -ENOMEM; - for (r = 0; r < s->n_rings; r++) { + for (r = 0; r < dp->num_tx_rings; r++) { int bias = 0; - if (r >= num_stack_tx_rings) - bias = num_stack_tx_rings; + if (r >= dp->num_stack_tx_rings) + bias = dp->num_stack_tx_rings; - nfp_net_tx_ring_init(&rings[r], &nn->r_vecs[r - bias], r); + nfp_net_tx_ring_init(&dp->tx_rings[r], &nn->r_vecs[r - bias], + r); - if (nfp_net_tx_ring_alloc(&rings[r], s->dcnt, bias)) + if (nfp_net_tx_ring_alloc(dp, &dp->tx_rings[r], bias)) goto err_free_prev; } - return s->rings = rings; + return 0; err_free_prev: while (r--) - nfp_net_tx_ring_free(&rings[r]); - kfree(rings); - return NULL; -} - -static void -nfp_net_tx_ring_set_swap(struct nfp_net *nn, struct nfp_net_ring_set *s) -{ - struct nfp_net_ring_set new = *s; - - s->dcnt = nn->txd_cnt; - s->rings = nn->tx_rings; - s->n_rings = nn->num_tx_rings; - - nn->txd_cnt = new.dcnt; - nn->tx_rings = new.rings; - nn->num_tx_rings = new.n_rings; + nfp_net_tx_ring_free(&dp->tx_rings[r]); + kfree(dp->tx_rings); + return -ENOMEM; } -static void -nfp_net_tx_ring_set_free(struct nfp_net *nn, struct nfp_net_ring_set *s) +static void nfp_net_tx_rings_free(struct nfp_net_dp *dp) { - struct nfp_net_tx_ring *rings = s->rings; unsigned int r; - for (r = 0; r < s->n_rings; r++) - nfp_net_tx_ring_free(&rings[r]); + for (r = 0; r < dp->num_tx_rings; r++) + nfp_net_tx_ring_free(&dp->tx_rings[r]); - kfree(rings); + kfree(dp->tx_rings); } /** @@ -1851,13 +1852,12 @@ nfp_net_tx_ring_set_free(struct nfp_net *nn, struct nfp_net_ring_set *s) static void nfp_net_rx_ring_free(struct nfp_net_rx_ring *rx_ring) { struct nfp_net_r_vector *r_vec = rx_ring->r_vec; - struct nfp_net *nn = r_vec->nfp_net; - struct pci_dev *pdev = nn->pdev; + struct nfp_net_dp *dp = &r_vec->nfp_net->dp; kfree(rx_ring->rxbufs); if (rx_ring->rxds) - dma_free_coherent(&pdev->dev, rx_ring->size, + dma_free_coherent(dp->dev, rx_ring->size, rx_ring->rxds, rx_ring->dma); rx_ring->cnt = 0; @@ -1869,26 +1869,19 @@ static void nfp_net_rx_ring_free(struct nfp_net_rx_ring *rx_ring) /** * nfp_net_rx_ring_alloc() - Allocate resource for a RX ring + * @dp: NFP Net data path struct * @rx_ring: RX ring to allocate - * @fl_bufsz: Size of buffers to allocate - * @cnt: Ring buffer count * * Return: 0 on success, negative errno otherwise. */ static int -nfp_net_rx_ring_alloc(struct nfp_net_rx_ring *rx_ring, unsigned int fl_bufsz, - u32 cnt) +nfp_net_rx_ring_alloc(struct nfp_net_dp *dp, struct nfp_net_rx_ring *rx_ring) { - struct nfp_net_r_vector *r_vec = rx_ring->r_vec; - struct nfp_net *nn = r_vec->nfp_net; - struct pci_dev *pdev = nn->pdev; int sz; - rx_ring->cnt = cnt; - rx_ring->bufsz = fl_bufsz; - + rx_ring->cnt = dp->rxd_cnt; rx_ring->size = sizeof(*rx_ring->rxds) * rx_ring->cnt; - rx_ring->rxds = dma_zalloc_coherent(&pdev->dev, rx_ring->size, + rx_ring->rxds = dma_zalloc_coherent(dp->dev, rx_ring->size, &rx_ring->dma, GFP_KERNEL); if (!rx_ring->rxds) goto err_alloc; @@ -1898,10 +1891,6 @@ nfp_net_rx_ring_alloc(struct nfp_net_rx_ring *rx_ring, unsigned int fl_bufsz, if (!rx_ring->rxbufs) goto err_alloc; - nn_dbg(nn, "RxQ%02d: FlQCidx=%02d RxQCidx=%02d cnt=%d dma=%#llx host=%p\n", - rx_ring->idx, rx_ring->fl_qcidx, rx_ring->rx_qcidx, - rx_ring->cnt, (unsigned long long)rx_ring->dma, rx_ring->rxds); - return 0; err_alloc: @@ -1909,82 +1898,59 @@ err_alloc: return -ENOMEM; } -static struct nfp_net_rx_ring * -nfp_net_rx_ring_set_prepare(struct nfp_net *nn, struct nfp_net_ring_set *s, - bool xdp) +static int nfp_net_rx_rings_prepare(struct nfp_net *nn, struct nfp_net_dp *dp) { - unsigned int fl_bufsz = nfp_net_calc_fl_bufsz(nn, s->mtu); - struct nfp_net_rx_ring *rings; unsigned int r; - rings = kcalloc(s->n_rings, sizeof(*rings), GFP_KERNEL); - if (!rings) - return NULL; + dp->rx_rings = kcalloc(dp->num_rx_rings, sizeof(*dp->rx_rings), + GFP_KERNEL); + if (!dp->rx_rings) + return -ENOMEM; - for (r = 0; r < s->n_rings; r++) { - nfp_net_rx_ring_init(&rings[r], &nn->r_vecs[r], r); + for (r = 0; r < dp->num_rx_rings; r++) { + nfp_net_rx_ring_init(&dp->rx_rings[r], &nn->r_vecs[r], r); - if (nfp_net_rx_ring_alloc(&rings[r], fl_bufsz, s->dcnt)) + if (nfp_net_rx_ring_alloc(dp, &dp->rx_rings[r])) goto err_free_prev; - if (nfp_net_rx_ring_bufs_alloc(nn, &rings[r], xdp)) + if (nfp_net_rx_ring_bufs_alloc(dp, &dp->rx_rings[r])) goto err_free_ring; } - return s->rings = rings; + return 0; err_free_prev: while (r--) { - nfp_net_rx_ring_bufs_free(nn, &rings[r], xdp); + nfp_net_rx_ring_bufs_free(dp, &dp->rx_rings[r]); err_free_ring: - nfp_net_rx_ring_free(&rings[r]); + nfp_net_rx_ring_free(&dp->rx_rings[r]); } - kfree(rings); - return NULL; -} - -static void -nfp_net_rx_ring_set_swap(struct nfp_net *nn, struct nfp_net_ring_set *s) -{ - struct nfp_net_ring_set new = *s; - - s->mtu = nn->netdev->mtu; - s->dcnt = nn->rxd_cnt; - s->rings = nn->rx_rings; - s->n_rings = nn->num_rx_rings; - - nn->netdev->mtu = new.mtu; - nn->fl_bufsz = nfp_net_calc_fl_bufsz(nn, new.mtu); - nn->rxd_cnt = new.dcnt; - nn->rx_rings = new.rings; - nn->num_rx_rings = new.n_rings; + kfree(dp->rx_rings); + return -ENOMEM; } -static void -nfp_net_rx_ring_set_free(struct nfp_net *nn, struct nfp_net_ring_set *s, - bool xdp) +static void nfp_net_rx_rings_free(struct nfp_net_dp *dp) { - struct nfp_net_rx_ring *rings = s->rings; unsigned int r; - for (r = 0; r < s->n_rings; r++) { - nfp_net_rx_ring_bufs_free(nn, &rings[r], xdp); - nfp_net_rx_ring_free(&rings[r]); + for (r = 0; r < dp->num_rx_rings; r++) { + nfp_net_rx_ring_bufs_free(dp, &dp->rx_rings[r]); + nfp_net_rx_ring_free(&dp->rx_rings[r]); } - kfree(rings); + kfree(dp->rx_rings); } static void -nfp_net_vector_assign_rings(struct nfp_net *nn, struct nfp_net_r_vector *r_vec, - int idx) +nfp_net_vector_assign_rings(struct nfp_net_dp *dp, + struct nfp_net_r_vector *r_vec, int idx) { - r_vec->rx_ring = idx < nn->num_rx_rings ? &nn->rx_rings[idx] : NULL; + r_vec->rx_ring = idx < dp->num_rx_rings ? &dp->rx_rings[idx] : NULL; r_vec->tx_ring = - idx < nn->num_stack_tx_rings ? &nn->tx_rings[idx] : NULL; + idx < dp->num_stack_tx_rings ? &dp->tx_rings[idx] : NULL; - r_vec->xdp_ring = idx < nn->num_tx_rings - nn->num_stack_tx_rings ? - &nn->tx_rings[nn->num_stack_tx_rings + idx] : NULL; + r_vec->xdp_ring = idx < dp->num_tx_rings - dp->num_stack_tx_rings ? + &dp->tx_rings[dp->num_stack_tx_rings + idx] : NULL; } static int @@ -1994,11 +1960,11 @@ nfp_net_prepare_vector(struct nfp_net *nn, struct nfp_net_r_vector *r_vec, int err; /* Setup NAPI */ - netif_napi_add(nn->netdev, &r_vec->napi, + netif_napi_add(nn->dp.netdev, &r_vec->napi, nfp_net_poll, NAPI_POLL_WEIGHT); snprintf(r_vec->name, sizeof(r_vec->name), - "%s-rxtx-%d", nn->netdev->name, idx); + "%s-rxtx-%d", nn->dp.netdev->name, idx); err = request_irq(r_vec->irq_vector, r_vec->handler, 0, r_vec->name, r_vec); if (err) { @@ -2045,7 +2011,7 @@ void nfp_net_rss_write_key(struct nfp_net *nn) { int i; - for (i = 0; i < NFP_NET_CFG_RSS_KEY_SZ; i += 4) + for (i = 0; i < nfp_net_rss_key_sz(nn); i += 4) nn_writel(nn, NFP_NET_CFG_RSS_KEY + i, get_unaligned_le32(nn->rss_key + i)); } @@ -2069,13 +2035,13 @@ void nfp_net_coalesce_write_cfg(struct nfp_net *nn) /* copy RX interrupt coalesce parameters */ value = (nn->rx_coalesce_max_frames << 16) | (factor * nn->rx_coalesce_usecs); - for (i = 0; i < nn->num_rx_rings; i++) + for (i = 0; i < nn->dp.num_rx_rings; i++) nn_writel(nn, NFP_NET_CFG_RXR_IRQ_MOD(i), value); /* copy TX interrupt coalesce parameters */ value = (nn->tx_coalesce_max_frames << 16) | (factor * nn->tx_coalesce_usecs); - for (i = 0; i < nn->num_tx_rings; i++) + for (i = 0; i < nn->dp.num_tx_rings; i++) nn_writel(nn, NFP_NET_CFG_TXR_IRQ_MOD(i), value); } @@ -2090,9 +2056,9 @@ void nfp_net_coalesce_write_cfg(struct nfp_net *nn) static void nfp_net_write_mac_addr(struct nfp_net *nn) { nn_writel(nn, NFP_NET_CFG_MACADDR + 0, - get_unaligned_be32(nn->netdev->dev_addr)); + get_unaligned_be32(nn->dp.netdev->dev_addr)); nn_writew(nn, NFP_NET_CFG_MACADDR + 6, - get_unaligned_be16(nn->netdev->dev_addr + 4)); + get_unaligned_be16(nn->dp.netdev->dev_addr + 4)); } static void nfp_net_vec_clear_ring_data(struct nfp_net *nn, unsigned int idx) @@ -2116,7 +2082,7 @@ static void nfp_net_clear_config_and_disable(struct nfp_net *nn) unsigned int r; int err; - new_ctrl = nn->ctrl; + new_ctrl = nn->dp.ctrl; new_ctrl &= ~NFP_NET_CFG_CTRL_ENABLE; update = NFP_NET_CFG_UPDATE_GEN; update |= NFP_NET_CFG_UPDATE_MSIX; @@ -2133,14 +2099,14 @@ static void nfp_net_clear_config_and_disable(struct nfp_net *nn) if (err) nn_err(nn, "Could not disable device: %d\n", err); - for (r = 0; r < nn->num_rx_rings; r++) - nfp_net_rx_ring_reset(&nn->rx_rings[r]); - for (r = 0; r < nn->num_tx_rings; r++) - nfp_net_tx_ring_reset(nn, &nn->tx_rings[r]); - for (r = 0; r < nn->num_r_vecs; r++) + for (r = 0; r < nn->dp.num_rx_rings; r++) + nfp_net_rx_ring_reset(&nn->dp.rx_rings[r]); + for (r = 0; r < nn->dp.num_tx_rings; r++) + nfp_net_tx_ring_reset(&nn->dp, &nn->dp.tx_rings[r]); + for (r = 0; r < nn->dp.num_r_vecs; r++) nfp_net_vec_clear_ring_data(nn, r); - nn->ctrl = new_ctrl; + nn->dp.ctrl = new_ctrl; } static void @@ -2168,7 +2134,7 @@ static int __nfp_net_set_config_and_enable(struct nfp_net *nn) unsigned int r; int err; - new_ctrl = nn->ctrl; + new_ctrl = nn->dp.ctrl; if (nn->cap & NFP_NET_CFG_CTRL_RSS) { nfp_net_rss_write_key(nn); @@ -2184,22 +2150,22 @@ static int __nfp_net_set_config_and_enable(struct nfp_net *nn) update |= NFP_NET_CFG_UPDATE_IRQMOD; } - for (r = 0; r < nn->num_tx_rings; r++) - nfp_net_tx_ring_hw_cfg_write(nn, &nn->tx_rings[r], r); - for (r = 0; r < nn->num_rx_rings; r++) - nfp_net_rx_ring_hw_cfg_write(nn, &nn->rx_rings[r], r); + for (r = 0; r < nn->dp.num_tx_rings; r++) + nfp_net_tx_ring_hw_cfg_write(nn, &nn->dp.tx_rings[r], r); + for (r = 0; r < nn->dp.num_rx_rings; r++) + nfp_net_rx_ring_hw_cfg_write(nn, &nn->dp.rx_rings[r], r); - nn_writeq(nn, NFP_NET_CFG_TXRS_ENABLE, nn->num_tx_rings == 64 ? - 0xffffffffffffffffULL : ((u64)1 << nn->num_tx_rings) - 1); + nn_writeq(nn, NFP_NET_CFG_TXRS_ENABLE, nn->dp.num_tx_rings == 64 ? + 0xffffffffffffffffULL : ((u64)1 << nn->dp.num_tx_rings) - 1); - nn_writeq(nn, NFP_NET_CFG_RXRS_ENABLE, nn->num_rx_rings == 64 ? - 0xffffffffffffffffULL : ((u64)1 << nn->num_rx_rings) - 1); + nn_writeq(nn, NFP_NET_CFG_RXRS_ENABLE, nn->dp.num_rx_rings == 64 ? + 0xffffffffffffffffULL : ((u64)1 << nn->dp.num_rx_rings) - 1); nfp_net_write_mac_addr(nn); - nn_writel(nn, NFP_NET_CFG_MTU, nn->netdev->mtu); + nn_writel(nn, NFP_NET_CFG_MTU, nn->dp.netdev->mtu); nn_writel(nn, NFP_NET_CFG_FLBUFSZ, - nn->fl_bufsz - NFP_NET_RX_BUF_NON_DATA); + nn->dp.fl_bufsz - NFP_NET_RX_BUF_NON_DATA); /* Enable device */ new_ctrl |= NFP_NET_CFG_CTRL_ENABLE; @@ -2212,18 +2178,18 @@ static int __nfp_net_set_config_and_enable(struct nfp_net *nn) nn_writel(nn, NFP_NET_CFG_CTRL, new_ctrl); err = nfp_net_reconfig(nn, update); - nn->ctrl = new_ctrl; + nn->dp.ctrl = new_ctrl; - for (r = 0; r < nn->num_rx_rings; r++) - nfp_net_rx_ring_fill_freelist(&nn->rx_rings[r]); + for (r = 0; r < nn->dp.num_rx_rings; r++) + nfp_net_rx_ring_fill_freelist(&nn->dp, &nn->dp.rx_rings[r]); /* Since reconfiguration requests while NFP is down are ignored we * have to wipe the entire VXLAN configuration and reinitialize it. */ - if (nn->ctrl & NFP_NET_CFG_CTRL_VXLAN) { + if (nn->dp.ctrl & NFP_NET_CFG_CTRL_VXLAN) { memset(&nn->vxlan_ports, 0, sizeof(nn->vxlan_ports)); memset(&nn->vxlan_usecnt, 0, sizeof(nn->vxlan_usecnt)); - udp_tunnel_get_rx_info(nn->netdev); + udp_tunnel_get_rx_info(nn->dp.netdev); } return err; @@ -2252,12 +2218,12 @@ static void nfp_net_open_stack(struct nfp_net *nn) { unsigned int r; - for (r = 0; r < nn->num_r_vecs; r++) { + for (r = 0; r < nn->dp.num_r_vecs; r++) { napi_enable(&nn->r_vecs[r].napi); enable_irq(nn->r_vecs[r].irq_vector); } - netif_tx_wake_all_queues(nn->netdev); + netif_tx_wake_all_queues(nn->dp.netdev); enable_irq(nn->irq_entries[NFP_NET_IRQ_LSC_IDX].vector); nfp_net_read_link_status(nn); @@ -2266,19 +2232,10 @@ static void nfp_net_open_stack(struct nfp_net *nn) static int nfp_net_netdev_open(struct net_device *netdev) { struct nfp_net *nn = netdev_priv(netdev); - struct nfp_net_ring_set rx = { - .n_rings = nn->num_rx_rings, - .mtu = nn->netdev->mtu, - .dcnt = nn->rxd_cnt, - }; - struct nfp_net_ring_set tx = { - .n_rings = nn->num_tx_rings, - .dcnt = nn->txd_cnt, - }; int err, r; - if (nn->ctrl & NFP_NET_CFG_CTRL_ENABLE) { - nn_err(nn, "Dev is already enabled: 0x%08x\n", nn->ctrl); + if (nn->dp.ctrl & NFP_NET_CFG_CTRL_ENABLE) { + nn_err(nn, "Dev is already enabled: 0x%08x\n", nn->dp.ctrl); return -EBUSY; } @@ -2299,33 +2256,28 @@ static int nfp_net_netdev_open(struct net_device *netdev) goto err_free_exn; disable_irq(nn->irq_entries[NFP_NET_IRQ_LSC_IDX].vector); - for (r = 0; r < nn->num_r_vecs; r++) { + for (r = 0; r < nn->dp.num_r_vecs; r++) { err = nfp_net_prepare_vector(nn, &nn->r_vecs[r], r); if (err) goto err_cleanup_vec_p; } - nn->rx_rings = nfp_net_rx_ring_set_prepare(nn, &rx, nn->xdp_prog); - if (!nn->rx_rings) { - err = -ENOMEM; + err = nfp_net_rx_rings_prepare(nn, &nn->dp); + if (err) goto err_cleanup_vec; - } - nn->tx_rings = nfp_net_tx_ring_set_prepare(nn, &tx, - nn->num_stack_tx_rings); - if (!nn->tx_rings) { - err = -ENOMEM; + err = nfp_net_tx_rings_prepare(nn, &nn->dp); + if (err) goto err_free_rx_rings; - } for (r = 0; r < nn->max_r_vecs; r++) - nfp_net_vector_assign_rings(nn, &nn->r_vecs[r], r); + nfp_net_vector_assign_rings(&nn->dp, &nn->r_vecs[r], r); - err = netif_set_real_num_tx_queues(netdev, nn->num_stack_tx_rings); + err = netif_set_real_num_tx_queues(netdev, nn->dp.num_stack_tx_rings); if (err) goto err_free_rings; - err = netif_set_real_num_rx_queues(netdev, nn->num_rx_rings); + err = netif_set_real_num_rx_queues(netdev, nn->dp.num_rx_rings); if (err) goto err_free_rings; @@ -2351,11 +2303,11 @@ static int nfp_net_netdev_open(struct net_device *netdev) return 0; err_free_rings: - nfp_net_tx_ring_set_free(nn, &tx); + nfp_net_tx_rings_free(&nn->dp); err_free_rx_rings: - nfp_net_rx_ring_set_free(nn, &rx, nn->xdp_prog); + nfp_net_rx_rings_free(&nn->dp); err_cleanup_vec: - r = nn->num_r_vecs; + r = nn->dp.num_r_vecs; err_cleanup_vec_p: while (r--) nfp_net_cleanup_vector(nn, &nn->r_vecs[r]); @@ -2374,15 +2326,15 @@ static void nfp_net_close_stack(struct nfp_net *nn) unsigned int r; disable_irq(nn->irq_entries[NFP_NET_IRQ_LSC_IDX].vector); - netif_carrier_off(nn->netdev); + netif_carrier_off(nn->dp.netdev); nn->link_up = false; - for (r = 0; r < nn->num_r_vecs; r++) { + for (r = 0; r < nn->dp.num_r_vecs; r++) { disable_irq(nn->r_vecs[r].irq_vector); napi_disable(&nn->r_vecs[r].napi); } - netif_tx_disable(nn->netdev); + netif_tx_disable(nn->dp.netdev); } /** @@ -2393,17 +2345,17 @@ static void nfp_net_close_free_all(struct nfp_net *nn) { unsigned int r; - for (r = 0; r < nn->num_rx_rings; r++) { - nfp_net_rx_ring_bufs_free(nn, &nn->rx_rings[r], nn->xdp_prog); - nfp_net_rx_ring_free(&nn->rx_rings[r]); + for (r = 0; r < nn->dp.num_rx_rings; r++) { + nfp_net_rx_ring_bufs_free(&nn->dp, &nn->dp.rx_rings[r]); + nfp_net_rx_ring_free(&nn->dp.rx_rings[r]); } - for (r = 0; r < nn->num_tx_rings; r++) - nfp_net_tx_ring_free(&nn->tx_rings[r]); - for (r = 0; r < nn->num_r_vecs; r++) + for (r = 0; r < nn->dp.num_tx_rings; r++) + nfp_net_tx_ring_free(&nn->dp.tx_rings[r]); + for (r = 0; r < nn->dp.num_r_vecs; r++) nfp_net_cleanup_vector(nn, &nn->r_vecs[r]); - kfree(nn->rx_rings); - kfree(nn->tx_rings); + kfree(nn->dp.rx_rings); + kfree(nn->dp.tx_rings); nfp_net_aux_irq_free(nn, NFP_NET_CFG_LSC, NFP_NET_IRQ_LSC_IDX); nfp_net_aux_irq_free(nn, NFP_NET_CFG_EXN, NFP_NET_IRQ_EXN_IDX); @@ -2417,8 +2369,8 @@ static int nfp_net_netdev_close(struct net_device *netdev) { struct nfp_net *nn = netdev_priv(netdev); - if (!(nn->ctrl & NFP_NET_CFG_CTRL_ENABLE)) { - nn_err(nn, "Dev is not up: 0x%08x\n", nn->ctrl); + if (!(nn->dp.ctrl & NFP_NET_CFG_CTRL_ENABLE)) { + nn_err(nn, "Dev is not up: 0x%08x\n", nn->dp.ctrl); return 0; } @@ -2443,7 +2395,7 @@ static void nfp_net_set_rx_mode(struct net_device *netdev) struct nfp_net *nn = netdev_priv(netdev); u32 new_ctrl; - new_ctrl = nn->ctrl; + new_ctrl = nn->dp.ctrl; if (netdev->flags & IFF_PROMISC) { if (nn->cap & NFP_NET_CFG_CTRL_PROMISC) @@ -2454,13 +2406,13 @@ static void nfp_net_set_rx_mode(struct net_device *netdev) new_ctrl &= ~NFP_NET_CFG_CTRL_PROMISC; } - if (new_ctrl == nn->ctrl) + if (new_ctrl == nn->dp.ctrl) return; nn_writel(nn, NFP_NET_CFG_CTRL, new_ctrl); nfp_net_reconfig_post(nn, NFP_NET_CFG_UPDATE_GEN); - nn->ctrl = new_ctrl; + nn->dp.ctrl = new_ctrl; } static void nfp_net_rss_init_itbl(struct nfp_net *nn) @@ -2469,42 +2421,39 @@ static void nfp_net_rss_init_itbl(struct nfp_net *nn) for (i = 0; i < sizeof(nn->rss_itbl); i++) nn->rss_itbl[i] = - ethtool_rxfh_indir_default(i, nn->num_rx_rings); + ethtool_rxfh_indir_default(i, nn->dp.num_rx_rings); } -static int -nfp_net_ring_swap_enable(struct nfp_net *nn, unsigned int *num_vecs, - unsigned int *stack_tx_rings, - struct bpf_prog **xdp_prog, - struct nfp_net_ring_set *rx, - struct nfp_net_ring_set *tx) +static void nfp_net_dp_swap(struct nfp_net *nn, struct nfp_net_dp *dp) +{ + struct nfp_net_dp new_dp = *dp; + + *dp = nn->dp; + nn->dp = new_dp; + + nn->dp.netdev->mtu = new_dp.mtu; + + if (!netif_is_rxfh_configured(nn->dp.netdev)) + nfp_net_rss_init_itbl(nn); +} + +static int nfp_net_dp_swap_enable(struct nfp_net *nn, struct nfp_net_dp *dp) { unsigned int r; int err; - if (rx) - nfp_net_rx_ring_set_swap(nn, rx); - if (tx) - nfp_net_tx_ring_set_swap(nn, tx); - - swap(*num_vecs, nn->num_r_vecs); - swap(*stack_tx_rings, nn->num_stack_tx_rings); - *xdp_prog = xchg(&nn->xdp_prog, *xdp_prog); + nfp_net_dp_swap(nn, dp); for (r = 0; r < nn->max_r_vecs; r++) - nfp_net_vector_assign_rings(nn, &nn->r_vecs[r], r); + nfp_net_vector_assign_rings(&nn->dp, &nn->r_vecs[r], r); - if (!netif_is_rxfh_configured(nn->netdev)) - nfp_net_rss_init_itbl(nn); - - err = netif_set_real_num_rx_queues(nn->netdev, - nn->num_rx_rings); + err = netif_set_real_num_rx_queues(nn->dp.netdev, nn->dp.num_rx_rings); if (err) return err; - if (nn->netdev->real_num_tx_queues != nn->num_stack_tx_rings) { - err = netif_set_real_num_tx_queues(nn->netdev, - nn->num_stack_tx_rings); + if (nn->dp.netdev->real_num_tx_queues != nn->dp.num_stack_tx_rings) { + err = netif_set_real_num_tx_queues(nn->dp.netdev, + nn->dp.num_stack_tx_rings); if (err) return err; } @@ -2512,18 +2461,36 @@ nfp_net_ring_swap_enable(struct nfp_net *nn, unsigned int *num_vecs, return __nfp_net_set_config_and_enable(nn); } -static int -nfp_net_check_config(struct nfp_net *nn, struct bpf_prog *xdp_prog, - struct nfp_net_ring_set *rx, struct nfp_net_ring_set *tx) +struct nfp_net_dp *nfp_net_clone_dp(struct nfp_net *nn) +{ + struct nfp_net_dp *new; + + new = kmalloc(sizeof(*new), GFP_KERNEL); + if (!new) + return NULL; + + *new = nn->dp; + + /* Clear things which need to be recomputed */ + new->fl_bufsz = 0; + new->tx_rings = NULL; + new->rx_rings = NULL; + new->num_r_vecs = 0; + new->num_stack_tx_rings = 0; + + return new; +} + +static int nfp_net_check_config(struct nfp_net *nn, struct nfp_net_dp *dp) { /* XDP-enabled tests */ - if (!xdp_prog) + if (!dp->xdp_prog) return 0; - if (rx && nfp_net_calc_fl_bufsz(nn, rx->mtu) > PAGE_SIZE) { + if (dp->fl_bufsz > PAGE_SIZE) { nn_warn(nn, "MTU too large w/ XDP enabled\n"); return -EINVAL; } - if (tx && tx->n_rings > nn->max_tx_rings) { + if (dp->num_tx_rings > nn->max_tx_rings) { nn_warn(nn, "Insufficient number of TX rings w/ XDP enabled\n"); return -EINVAL; } @@ -2531,119 +2498,94 @@ nfp_net_check_config(struct nfp_net *nn, struct bpf_prog *xdp_prog, return 0; } -static void -nfp_net_ring_reconfig_down(struct nfp_net *nn, struct bpf_prog **xdp_prog, - struct nfp_net_ring_set *rx, - struct nfp_net_ring_set *tx, - unsigned int stack_tx_rings, unsigned int num_vecs) -{ - nn->netdev->mtu = rx ? rx->mtu : nn->netdev->mtu; - nn->fl_bufsz = nfp_net_calc_fl_bufsz(nn, nn->netdev->mtu); - nn->rxd_cnt = rx ? rx->dcnt : nn->rxd_cnt; - nn->txd_cnt = tx ? tx->dcnt : nn->txd_cnt; - nn->num_rx_rings = rx ? rx->n_rings : nn->num_rx_rings; - nn->num_tx_rings = tx ? tx->n_rings : nn->num_tx_rings; - nn->num_stack_tx_rings = stack_tx_rings; - nn->num_r_vecs = num_vecs; - *xdp_prog = xchg(&nn->xdp_prog, *xdp_prog); - - if (!netif_is_rxfh_configured(nn->netdev)) - nfp_net_rss_init_itbl(nn); -} - -int -nfp_net_ring_reconfig(struct nfp_net *nn, struct bpf_prog **xdp_prog, - struct nfp_net_ring_set *rx, struct nfp_net_ring_set *tx) +int nfp_net_ring_reconfig(struct nfp_net *nn, struct nfp_net_dp *dp) { - unsigned int stack_tx_rings, num_vecs, r; - int err; + int r, err; + + dp->fl_bufsz = nfp_net_calc_fl_bufsz(dp); - stack_tx_rings = tx ? tx->n_rings : nn->num_tx_rings; - if (*xdp_prog) - stack_tx_rings -= rx ? rx->n_rings : nn->num_rx_rings; + dp->num_stack_tx_rings = dp->num_tx_rings; + if (dp->xdp_prog) + dp->num_stack_tx_rings -= dp->num_rx_rings; - num_vecs = max(rx ? rx->n_rings : nn->num_rx_rings, stack_tx_rings); + dp->num_r_vecs = max(dp->num_rx_rings, dp->num_stack_tx_rings); - err = nfp_net_check_config(nn, *xdp_prog, rx, tx); + err = nfp_net_check_config(nn, dp); if (err) - return err; + goto exit_free_dp; - if (!netif_running(nn->netdev)) { - nfp_net_ring_reconfig_down(nn, xdp_prog, rx, tx, - stack_tx_rings, num_vecs); - return 0; + if (!netif_running(dp->netdev)) { + nfp_net_dp_swap(nn, dp); + err = 0; + goto exit_free_dp; } /* Prepare new rings */ - for (r = nn->num_r_vecs; r < num_vecs; r++) { + for (r = nn->dp.num_r_vecs; r < dp->num_r_vecs; r++) { err = nfp_net_prepare_vector(nn, &nn->r_vecs[r], r); if (err) { - num_vecs = r; + dp->num_r_vecs = r; goto err_cleanup_vecs; } } - if (rx) { - if (!nfp_net_rx_ring_set_prepare(nn, rx, *xdp_prog)) { - err = -ENOMEM; - goto err_cleanup_vecs; - } - } - if (tx) { - if (!nfp_net_tx_ring_set_prepare(nn, tx, stack_tx_rings)) { - err = -ENOMEM; - goto err_free_rx; - } - } + + err = nfp_net_rx_rings_prepare(nn, dp); + if (err) + goto err_cleanup_vecs; + + err = nfp_net_tx_rings_prepare(nn, dp); + if (err) + goto err_free_rx; /* Stop device, swap in new rings, try to start the firmware */ nfp_net_close_stack(nn); nfp_net_clear_config_and_disable(nn); - err = nfp_net_ring_swap_enable(nn, &num_vecs, &stack_tx_rings, - xdp_prog, rx, tx); + err = nfp_net_dp_swap_enable(nn, dp); if (err) { int err2; nfp_net_clear_config_and_disable(nn); /* Try with old configuration and old rings */ - err2 = nfp_net_ring_swap_enable(nn, &num_vecs, &stack_tx_rings, - xdp_prog, rx, tx); + err2 = nfp_net_dp_swap_enable(nn, dp); if (err2) nn_err(nn, "Can't restore ring config - FW communication failed (%d,%d)\n", err, err2); } - for (r = num_vecs - 1; r >= nn->num_r_vecs; r--) + for (r = dp->num_r_vecs - 1; r >= nn->dp.num_r_vecs; r--) nfp_net_cleanup_vector(nn, &nn->r_vecs[r]); - if (rx) - nfp_net_rx_ring_set_free(nn, rx, *xdp_prog); - if (tx) - nfp_net_tx_ring_set_free(nn, tx); + nfp_net_rx_rings_free(dp); + nfp_net_tx_rings_free(dp); nfp_net_open_stack(nn); +exit_free_dp: + kfree(dp); return err; err_free_rx: - if (rx) - nfp_net_rx_ring_set_free(nn, rx, *xdp_prog); + nfp_net_rx_rings_free(dp); err_cleanup_vecs: - for (r = num_vecs - 1; r >= nn->num_r_vecs; r--) + for (r = dp->num_r_vecs - 1; r >= nn->dp.num_r_vecs; r--) nfp_net_cleanup_vector(nn, &nn->r_vecs[r]); + kfree(dp); return err; } static int nfp_net_change_mtu(struct net_device *netdev, int new_mtu) { struct nfp_net *nn = netdev_priv(netdev); - struct nfp_net_ring_set rx = { - .n_rings = nn->num_rx_rings, - .mtu = new_mtu, - .dcnt = nn->rxd_cnt, - }; + struct nfp_net_dp *dp; + + dp = nfp_net_clone_dp(nn); + if (!dp) + return -ENOMEM; - return nfp_net_ring_reconfig(nn, &nn->xdp_prog, &rx, NULL); + dp->mtu = new_mtu; + + return nfp_net_ring_reconfig(nn, dp); } static void nfp_net_stat64(struct net_device *netdev, @@ -2652,7 +2594,7 @@ static void nfp_net_stat64(struct net_device *netdev, struct nfp_net *nn = netdev_priv(netdev); int r; - for (r = 0; r < nn->num_r_vecs; r++) { + for (r = 0; r < nn->dp.num_r_vecs; r++) { struct nfp_net_r_vector *r_vec = &nn->r_vecs[r]; u64 data[3]; unsigned int start; @@ -2699,7 +2641,7 @@ nfp_net_setup_tc(struct net_device *netdev, u32 handle, __be16 proto, return -ENOTSUPP; if (tc->type == TC_SETUP_CLSBPF && nfp_net_ebpf_capable(nn)) { - if (!nn->bpf_offload_xdp) + if (!nn->dp.bpf_offload_xdp) return nfp_net_bpf_offload(nn, tc->cls_bpf); else return -EBUSY; @@ -2718,7 +2660,7 @@ static int nfp_net_set_features(struct net_device *netdev, /* Assume this is not called with features we have not advertised */ - new_ctrl = nn->ctrl; + new_ctrl = nn->dp.ctrl; if (changed & NETIF_F_RXCSUM) { if (features & NETIF_F_RXCSUM) @@ -2762,7 +2704,7 @@ static int nfp_net_set_features(struct net_device *netdev, new_ctrl &= ~NFP_NET_CFG_CTRL_GATHER; } - if (changed & NETIF_F_HW_TC && nn->ctrl & NFP_NET_CFG_CTRL_BPF) { + if (changed & NETIF_F_HW_TC && nn->dp.ctrl & NFP_NET_CFG_CTRL_BPF) { nn_err(nn, "Cannot disable HW TC offload while in use\n"); return -EBUSY; } @@ -2770,16 +2712,16 @@ static int nfp_net_set_features(struct net_device *netdev, nn_dbg(nn, "Feature change 0x%llx -> 0x%llx (changed=0x%llx)\n", netdev->features, features, changed); - if (new_ctrl == nn->ctrl) + if (new_ctrl == nn->dp.ctrl) return 0; - nn_dbg(nn, "NIC ctrl: 0x%x -> 0x%x\n", nn->ctrl, new_ctrl); + nn_dbg(nn, "NIC ctrl: 0x%x -> 0x%x\n", nn->dp.ctrl, new_ctrl); nn_writel(nn, NFP_NET_CFG_CTRL, new_ctrl); err = nfp_net_reconfig(nn, NFP_NET_CFG_UPDATE_GEN); if (err) return err; - nn->ctrl = new_ctrl; + nn->dp.ctrl = new_ctrl; return 0; } @@ -2830,6 +2772,26 @@ nfp_net_features_check(struct sk_buff *skb, struct net_device *dev, return features; } +static int +nfp_net_get_phys_port_name(struct net_device *netdev, char *name, size_t len) +{ + struct nfp_net *nn = netdev_priv(netdev); + int err; + + if (!nn->eth_port) + return -EOPNOTSUPP; + + if (!nn->eth_port->is_split) + err = snprintf(name, len, "p%d", nn->eth_port->label_port); + else + err = snprintf(name, len, "p%ds%d", nn->eth_port->label_port, + nn->eth_port->label_subport); + if (err >= len) + return -EINVAL; + + return 0; +} + /** * nfp_net_set_vxlan_port() - set vxlan port in SW and reconfigure HW * @nn: NFP Net device to reconfigure @@ -2842,7 +2804,7 @@ static void nfp_net_set_vxlan_port(struct nfp_net *nn, int idx, __be16 port) nn->vxlan_ports[idx] = port; - if (!(nn->ctrl & NFP_NET_CFG_CTRL_VXLAN)) + if (!(nn->dp.ctrl & NFP_NET_CFG_CTRL_VXLAN)) return; BUILD_BUG_ON(NFP_NET_N_VXLAN_PORTS & 1); @@ -2921,8 +2883,8 @@ static int nfp_net_xdp_offload(struct nfp_net *nn, struct bpf_prog *prog) if (!nfp_net_ebpf_capable(nn)) return -EINVAL; - if (nn->ctrl & NFP_NET_CFG_CTRL_BPF) { - if (!nn->bpf_offload_xdp) + if (nn->dp.ctrl & NFP_NET_CFG_CTRL_BPF) { + if (!nn->dp.bpf_offload_xdp) return prog ? -EBUSY : 0; cmd.command = prog ? TC_CLSBPF_REPLACE : TC_CLSBPF_DESTROY; } else { @@ -2935,48 +2897,47 @@ static int nfp_net_xdp_offload(struct nfp_net *nn, struct bpf_prog *prog) /* Stop offload if replace not possible */ if (ret && cmd.command == TC_CLSBPF_REPLACE) nfp_net_xdp_offload(nn, NULL); - nn->bpf_offload_xdp = prog && !ret; + nn->dp.bpf_offload_xdp = prog && !ret; return ret; } static int nfp_net_xdp_setup(struct nfp_net *nn, struct bpf_prog *prog) { - struct nfp_net_ring_set rx = { - .n_rings = nn->num_rx_rings, - .mtu = nn->netdev->mtu, - .dcnt = nn->rxd_cnt, - }; - struct nfp_net_ring_set tx = { - .n_rings = nn->num_tx_rings, - .dcnt = nn->txd_cnt, - }; + struct bpf_prog *old_prog = nn->dp.xdp_prog; + struct nfp_net_dp *dp; int err; - if (prog && prog->xdp_adjust_head) { - nn_err(nn, "Does not support bpf_xdp_adjust_head()\n"); - return -EOPNOTSUPP; - } - if (!prog && !nn->xdp_prog) + if (!prog && !nn->dp.xdp_prog) return 0; - if (prog && nn->xdp_prog) { - prog = xchg(&nn->xdp_prog, prog); + if (prog && nn->dp.xdp_prog) { + prog = xchg(&nn->dp.xdp_prog, prog); bpf_prog_put(prog); - nfp_net_xdp_offload(nn, nn->xdp_prog); + nfp_net_xdp_offload(nn, nn->dp.xdp_prog); return 0; } - tx.n_rings += prog ? nn->num_rx_rings : -nn->num_rx_rings; + dp = nfp_net_clone_dp(nn); + if (!dp) + return -ENOMEM; + + dp->xdp_prog = prog; + dp->num_tx_rings += prog ? nn->dp.num_rx_rings : -nn->dp.num_rx_rings; + dp->rx_dma_dir = prog ? DMA_BIDIRECTIONAL : DMA_FROM_DEVICE; + if (prog) + dp->rx_dma_off = XDP_PACKET_HEADROOM - + (nn->dp.rx_offset ?: NFP_NET_MAX_PREPEND); + else + dp->rx_dma_off = 0; /* We need RX reconfig to remap the buffers (BIDIR vs FROM_DEV) */ - err = nfp_net_ring_reconfig(nn, &prog, &rx, &tx); + err = nfp_net_ring_reconfig(nn, dp); if (err) return err; - /* @prog got swapped and is now the old one */ - if (prog) - bpf_prog_put(prog); + if (old_prog) + bpf_prog_put(old_prog); - nfp_net_xdp_offload(nn, nn->xdp_prog); + nfp_net_xdp_offload(nn, nn->dp.xdp_prog); return 0; } @@ -2989,7 +2950,7 @@ static int nfp_net_xdp(struct net_device *netdev, struct netdev_xdp *xdp) case XDP_SETUP_PROG: return nfp_net_xdp_setup(nn, xdp->prog); case XDP_QUERY_PROG: - xdp->prog_attached = !!nn->xdp_prog; + xdp->prog_attached = !!nn->dp.xdp_prog; return 0; default: return -EINVAL; @@ -3008,6 +2969,7 @@ static const struct net_device_ops nfp_net_netdev_ops = { .ndo_set_mac_address = eth_mac_addr, .ndo_set_features = nfp_net_set_features, .ndo_features_check = nfp_net_features_check, + .ndo_get_phys_port_name = nfp_net_get_phys_port_name, .ndo_udp_tunnel_add = nfp_net_add_vxlan_port, .ndo_udp_tunnel_del = nfp_net_del_vxlan_port, .ndo_xdp = nfp_net_xdp, @@ -3020,9 +2982,9 @@ static const struct net_device_ops nfp_net_netdev_ops = { void nfp_net_info(struct nfp_net *nn) { nn_info(nn, "Netronome NFP-6xxx %sNetdev: TxQs=%d/%d RxQs=%d/%d\n", - nn->is_vf ? "VF " : "", - nn->num_tx_rings, nn->max_tx_rings, - nn->num_rx_rings, nn->max_rx_rings); + nn->dp.is_vf ? "VF " : "", + nn->dp.num_tx_rings, nn->max_tx_rings, + nn->dp.num_rx_rings, nn->max_rx_rings); nn_info(nn, "VER: %d.%d.%d.%d, Maximum supported MTU: %d\n", nn->fw_ver.resv, nn->fw_ver.class, nn->fw_ver.major, nn->fw_ver.minor, @@ -3074,21 +3036,24 @@ struct nfp_net *nfp_net_netdev_alloc(struct pci_dev *pdev, SET_NETDEV_DEV(netdev, &pdev->dev); nn = netdev_priv(netdev); - nn->netdev = netdev; + nn->dp.netdev = netdev; + nn->dp.dev = &pdev->dev; nn->pdev = pdev; nn->max_tx_rings = max_tx_rings; nn->max_rx_rings = max_rx_rings; - nn->num_tx_rings = min_t(unsigned int, max_tx_rings, num_online_cpus()); - nn->num_rx_rings = min_t(unsigned int, max_rx_rings, + nn->dp.num_tx_rings = min_t(unsigned int, + max_tx_rings, num_online_cpus()); + nn->dp.num_rx_rings = min_t(unsigned int, max_rx_rings, netif_get_num_default_rss_queues()); - nn->num_r_vecs = max(nn->num_tx_rings, nn->num_rx_rings); - nn->num_r_vecs = min_t(unsigned int, nn->num_r_vecs, num_online_cpus()); + nn->dp.num_r_vecs = max(nn->dp.num_tx_rings, nn->dp.num_rx_rings); + nn->dp.num_r_vecs = min_t(unsigned int, + nn->dp.num_r_vecs, num_online_cpus()); - nn->txd_cnt = NFP_NET_TX_DESCS_DEFAULT; - nn->rxd_cnt = NFP_NET_RX_DESCS_DEFAULT; + nn->dp.txd_cnt = NFP_NET_TX_DESCS_DEFAULT; + nn->dp.rxd_cnt = NFP_NET_RX_DESCS_DEFAULT; spin_lock_init(&nn->reconfig_lock); spin_lock_init(&nn->rx_filter_lock); @@ -3108,7 +3073,28 @@ struct nfp_net *nfp_net_netdev_alloc(struct pci_dev *pdev, */ void nfp_net_netdev_free(struct nfp_net *nn) { - free_netdev(nn->netdev); + free_netdev(nn->dp.netdev); +} + +/** + * nfp_net_rss_key_sz() - Get current size of the RSS key + * @nn: NFP Net device instance + * + * Return: size of the RSS key for currently selected hash function. + */ +unsigned int nfp_net_rss_key_sz(struct nfp_net *nn) +{ + switch (nn->rss_hfunc) { + case ETH_RSS_HASH_TOP: + return NFP_NET_CFG_RSS_KEY_SZ; + case ETH_RSS_HASH_XOR: + return 0; + case ETH_RSS_HASH_CRC32: + return 4; + } + + nn_warn(nn, "Unknown hash function: %u\n", nn->rss_hfunc); + return 0; } /** @@ -3117,14 +3103,32 @@ void nfp_net_netdev_free(struct nfp_net *nn) */ static void nfp_net_rss_init(struct nfp_net *nn) { - netdev_rss_key_fill(nn->rss_key, NFP_NET_CFG_RSS_KEY_SZ); + unsigned long func_bit, rss_cap_hfunc; + u32 reg; + + /* Read the RSS function capability and select first supported func */ + reg = nn_readl(nn, NFP_NET_CFG_RSS_CAP); + rss_cap_hfunc = FIELD_GET(NFP_NET_CFG_RSS_CAP_HFUNC, reg); + if (!rss_cap_hfunc) + rss_cap_hfunc = FIELD_GET(NFP_NET_CFG_RSS_CAP_HFUNC, + NFP_NET_CFG_RSS_TOEPLITZ); + + func_bit = find_first_bit(&rss_cap_hfunc, NFP_NET_CFG_RSS_HFUNCS); + if (func_bit == NFP_NET_CFG_RSS_HFUNCS) { + dev_warn(nn->dp.dev, + "Bad RSS config, defaulting to Toeplitz hash\n"); + func_bit = ETH_RSS_HASH_TOP_BIT; + } + nn->rss_hfunc = 1 << func_bit; + + netdev_rss_key_fill(nn->rss_key, nfp_net_rss_key_sz(nn)); nfp_net_rss_init_itbl(nn); /* Enable IPv4/IPv6 TCP by default */ nn->rss_cfg = NFP_NET_CFG_RSS_IPV4_TCP | NFP_NET_CFG_RSS_IPV6_TCP | - NFP_NET_CFG_RSS_TOEPLITZ | + FIELD_PREP(NFP_NET_CFG_RSS_HFUNC, nn->rss_hfunc) | NFP_NET_CFG_RSS_MASK; } @@ -3151,6 +3155,17 @@ int nfp_net_netdev_init(struct net_device *netdev) struct nfp_net *nn = netdev_priv(netdev); int err; + /* XDP calls for 256 byte packet headroom which wouldn't fit in a u8. + * We, however, reuse the metadata prepend space for XDP buffers which + * is at least 1 byte long and as long as XDP headroom doesn't increase + * above 256 the *extra* XDP headroom will fit on 8 bits. + */ + BUILD_BUG_ON(XDP_PACKET_HEADROOM > 256); + + nn->dp.chained_metadata_format = nn->fw_ver.major > 3; + + nn->dp.rx_dma_dir = DMA_FROM_DEVICE; + /* Get some of the read-only fields from the BAR */ nn->cap = nn_readl(nn, NFP_NET_CFG_CAP); nn->max_mtu = nn_readl(nn, NFP_NET_CFG_MAX_MTU); @@ -3158,17 +3173,26 @@ int nfp_net_netdev_init(struct net_device *netdev) nfp_net_write_mac_addr(nn); /* Determine RX packet/metadata boundary offset */ - if (nn->fw_ver.major >= 2) - nn->rx_offset = nn_readl(nn, NFP_NET_CFG_RX_OFFSET); - else - nn->rx_offset = NFP_NET_RX_OFFSET; + if (nn->fw_ver.major >= 2) { + u32 reg; + + reg = nn_readl(nn, NFP_NET_CFG_RX_OFFSET); + if (reg > NFP_NET_MAX_PREPEND) { + nn_err(nn, "Invalid rx offset: %d\n", reg); + return -EINVAL; + } + nn->dp.rx_offset = reg; + } else { + nn->dp.rx_offset = NFP_NET_RX_OFFSET; + } /* Set default MTU and Freelist buffer size */ if (nn->max_mtu < NFP_NET_DEFAULT_MTU) netdev->mtu = nn->max_mtu; else netdev->mtu = NFP_NET_DEFAULT_MTU; - nn->fl_bufsz = nfp_net_calc_fl_bufsz(nn, netdev->mtu); + nn->dp.mtu = netdev->mtu; + nn->dp.fl_bufsz = nfp_net_calc_fl_bufsz(&nn->dp); /* Advertise/enable offloads based on capabilities * @@ -3179,31 +3203,31 @@ int nfp_net_netdev_init(struct net_device *netdev) netdev->hw_features = NETIF_F_HIGHDMA; if (nn->cap & NFP_NET_CFG_CTRL_RXCSUM) { netdev->hw_features |= NETIF_F_RXCSUM; - nn->ctrl |= NFP_NET_CFG_CTRL_RXCSUM; + nn->dp.ctrl |= NFP_NET_CFG_CTRL_RXCSUM; } if (nn->cap & NFP_NET_CFG_CTRL_TXCSUM) { netdev->hw_features |= NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM; - nn->ctrl |= NFP_NET_CFG_CTRL_TXCSUM; + nn->dp.ctrl |= NFP_NET_CFG_CTRL_TXCSUM; } if (nn->cap & NFP_NET_CFG_CTRL_GATHER) { netdev->hw_features |= NETIF_F_SG; - nn->ctrl |= NFP_NET_CFG_CTRL_GATHER; + nn->dp.ctrl |= NFP_NET_CFG_CTRL_GATHER; } if ((nn->cap & NFP_NET_CFG_CTRL_LSO) && nn->fw_ver.major > 2) { netdev->hw_features |= NETIF_F_TSO | NETIF_F_TSO6; - nn->ctrl |= NFP_NET_CFG_CTRL_LSO; + nn->dp.ctrl |= NFP_NET_CFG_CTRL_LSO; } if (nn->cap & NFP_NET_CFG_CTRL_RSS) { netdev->hw_features |= NETIF_F_RXHASH; nfp_net_rss_init(nn); - nn->ctrl |= NFP_NET_CFG_CTRL_RSS; + nn->dp.ctrl |= NFP_NET_CFG_CTRL_RSS; } if (nn->cap & NFP_NET_CFG_CTRL_VXLAN && nn->cap & NFP_NET_CFG_CTRL_NVGRE) { if (nn->cap & NFP_NET_CFG_CTRL_LSO) netdev->hw_features |= NETIF_F_GSO_GRE | NETIF_F_GSO_UDP_TUNNEL; - nn->ctrl |= NFP_NET_CFG_CTRL_VXLAN | NFP_NET_CFG_CTRL_NVGRE; + nn->dp.ctrl |= NFP_NET_CFG_CTRL_VXLAN | NFP_NET_CFG_CTRL_NVGRE; netdev->hw_enc_features = netdev->hw_features; } @@ -3212,11 +3236,11 @@ int nfp_net_netdev_init(struct net_device *netdev) if (nn->cap & NFP_NET_CFG_CTRL_RXVLAN) { netdev->hw_features |= NETIF_F_HW_VLAN_CTAG_RX; - nn->ctrl |= NFP_NET_CFG_CTRL_RXVLAN; + nn->dp.ctrl |= NFP_NET_CFG_CTRL_RXVLAN; } if (nn->cap & NFP_NET_CFG_CTRL_TXVLAN) { netdev->hw_features |= NETIF_F_HW_VLAN_CTAG_TX; - nn->ctrl |= NFP_NET_CFG_CTRL_TXVLAN; + nn->dp.ctrl |= NFP_NET_CFG_CTRL_TXVLAN; } netdev->features = netdev->hw_features; @@ -3229,14 +3253,14 @@ int nfp_net_netdev_init(struct net_device *netdev) /* Allow L2 Broadcast and Multicast through by default, if supported */ if (nn->cap & NFP_NET_CFG_CTRL_L2BC) - nn->ctrl |= NFP_NET_CFG_CTRL_L2BC; + nn->dp.ctrl |= NFP_NET_CFG_CTRL_L2BC; if (nn->cap & NFP_NET_CFG_CTRL_L2MC) - nn->ctrl |= NFP_NET_CFG_CTRL_L2MC; + nn->dp.ctrl |= NFP_NET_CFG_CTRL_L2MC; /* Allow IRQ moderation, if supported */ if (nn->cap & NFP_NET_CFG_CTRL_IRQMOD) { nfp_net_irqmod_init(nn); - nn->ctrl |= NFP_NET_CFG_CTRL_IRQMOD; + nn->dp.ctrl |= NFP_NET_CFG_CTRL_IRQMOD; } /* Stash the re-configuration queue away. First odd queue in TX Bar */ @@ -3275,9 +3299,9 @@ void nfp_net_netdev_clean(struct net_device *netdev) { struct nfp_net *nn = netdev_priv(netdev); - if (nn->xdp_prog) - bpf_prog_put(nn->xdp_prog); - if (nn->bpf_offload_xdp) + if (nn->dp.xdp_prog) + bpf_prog_put(nn->dp.xdp_prog); + if (nn->dp.bpf_offload_xdp) nfp_net_xdp_offload(nn, NULL); - unregister_netdev(nn->netdev); + unregister_netdev(nn->dp.netdev); } diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_ctrl.h b/drivers/net/ethernet/netronome/nfp/nfp_net_ctrl.h index 385ba355c965..71d86171b4ee 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net_ctrl.h +++ b/drivers/net/ethernet/netronome/nfp/nfp_net_ctrl.h @@ -1,5 +1,5 @@ /* - * Copyright (C) 2015 Netronome Systems, Inc. + * Copyright (C) 2015-2017 Netronome Systems, Inc. * * This software is dual licensed under the GNU General License Version 2, * June 1991 as shown in the file COPYING in the top-level directory of this @@ -192,6 +192,14 @@ #define NFP_NET_CFG_RX_OFFSET_DYNAMIC 0 /* Prepend mode */ /** + * RSS capabilities + * @NFP_NET_CFG_RSS_CAP_HFUNC: supported hash functions (same bits as + * @NFP_NET_CFG_RSS_HFUNC) + */ +#define NFP_NET_CFG_RSS_CAP 0x0054 +#define NFP_NET_CFG_RSS_CAP_HFUNC 0xff000000 + +/** * VXLAN/UDP encap configuration * @NFP_NET_CFG_VXLAN_PORT: Base address of table of tunnels' UDP dst ports * @NFP_NET_CFG_VXLAN_SZ: Size of the UDP port table in bytes @@ -249,7 +257,11 @@ #define NFP_NET_CFG_RSS_IPV4_UDP (1 << 11) /* RSS for IPv4/UDP */ #define NFP_NET_CFG_RSS_IPV6_TCP (1 << 12) /* RSS for IPv6/TCP */ #define NFP_NET_CFG_RSS_IPV6_UDP (1 << 13) /* RSS for IPv6/UDP */ +#define NFP_NET_CFG_RSS_HFUNC 0xff000000 #define NFP_NET_CFG_RSS_TOEPLITZ (1 << 24) /* Use Toeplitz hash */ +#define NFP_NET_CFG_RSS_XOR (1 << 25) /* Use XOR as hash */ +#define NFP_NET_CFG_RSS_CRC32 (1 << 26) /* Use CRC32 as hash */ +#define NFP_NET_CFG_RSS_HFUNCS 3 #define NFP_NET_CFG_RSS_KEY (NFP_NET_CFG_RSS_BASE + 0x4) #define NFP_NET_CFG_RSS_KEY_SZ 0x28 #define NFP_NET_CFG_RSS_ITBL (NFP_NET_CFG_RSS_BASE + 0x4 + \ diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_debugfs.c b/drivers/net/ethernet/netronome/nfp/nfp_net_debugfs.c index 6e9372a18375..74125584260b 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net_debugfs.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_net_debugfs.c @@ -54,7 +54,7 @@ static int nfp_net_debugfs_rx_q_read(struct seq_file *file, void *data) goto out; nn = r_vec->nfp_net; rx_ring = r_vec->rx_ring; - if (!netif_running(nn->netdev)) + if (!netif_running(nn->dp.netdev)) goto out; rxd_cnt = rx_ring->cnt; @@ -64,8 +64,10 @@ static int nfp_net_debugfs_rx_q_read(struct seq_file *file, void *data) rx_rd_p = nfp_qcp_rd_ptr_read(rx_ring->qcp_rx); rx_wr_p = nfp_qcp_wr_ptr_read(rx_ring->qcp_rx); - seq_printf(file, "RX[%02d]: H_RD=%d H_WR=%d FL_RD=%d FL_WR=%d RX_RD=%d RX_WR=%d\n", - rx_ring->idx, rx_ring->rd_p, rx_ring->wr_p, + seq_printf(file, "RX[%02d,%02d,%02d]: cnt=%d dma=%pad host=%p H_RD=%d H_WR=%d FL_RD=%d FL_WR=%d RX_RD=%d RX_WR=%d\n", + rx_ring->idx, rx_ring->fl_qcidx, rx_ring->rx_qcidx, + rx_ring->cnt, &rx_ring->dma, rx_ring->rxds, + rx_ring->rd_p, rx_ring->wr_p, fl_rd_p, fl_wr_p, rx_rd_p, rx_wr_p); for (i = 0; i < rxd_cnt; i++) { @@ -143,7 +145,7 @@ static int nfp_net_debugfs_tx_q_read(struct seq_file *file, void *data) if (!r_vec->nfp_net || !tx_ring) goto out; nn = r_vec->nfp_net; - if (!netif_running(nn->netdev)) + if (!netif_running(nn->dp.netdev)) goto out; txd_cnt = tx_ring->cnt; @@ -151,8 +153,11 @@ static int nfp_net_debugfs_tx_q_read(struct seq_file *file, void *data) d_rd_p = nfp_qcp_rd_ptr_read(tx_ring->qcp_q); d_wr_p = nfp_qcp_wr_ptr_read(tx_ring->qcp_q); - seq_printf(file, "TX[%02d]: H_RD=%d H_WR=%d D_RD=%d D_WR=%d\n", - tx_ring->idx, tx_ring->rd_p, tx_ring->wr_p, d_rd_p, d_wr_p); + seq_printf(file, "TX[%02d,%02d%s]: cnt=%d dma=%pad host=%p H_RD=%d H_WR=%d D_RD=%d D_WR=%d\n", + tx_ring->idx, tx_ring->qcidx, + tx_ring == r_vec->tx_ring ? "" : "xdp", + tx_ring->cnt, &tx_ring->dma, tx_ring->txds, + tx_ring->rd_p, tx_ring->wr_p, d_rd_p, d_wr_p); for (i = 0; i < txd_cnt; i++) { txd = &tx_ring->txds[i]; diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c b/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c index 2649f7523c81..ed22a813e579 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c @@ -40,6 +40,7 @@ * Brad Petrus <[email protected]> */ +#include <linux/bitfield.h> #include <linux/kernel.h> #include <linux/netdevice.h> #include <linux/etherdevice.h> @@ -126,9 +127,9 @@ static const struct _nfp_net_et_stats nfp_net_et_stats[] = { }; #define NN_ET_GLOBAL_STATS_LEN ARRAY_SIZE(nfp_net_et_stats) -#define NN_ET_RVEC_STATS_LEN (nn->num_r_vecs * 3) +#define NN_ET_RVEC_STATS_LEN (nn->dp.num_r_vecs * 3) #define NN_ET_RVEC_GATHER_STATS 7 -#define NN_ET_QUEUE_STATS_LEN ((nn->num_tx_rings + nn->num_rx_rings) * 2) +#define NN_ET_QUEUE_STATS_LEN ((nn->dp.num_tx_rings + nn->dp.num_rx_rings) * 2) #define NN_ET_STATS_LEN (NN_ET_GLOBAL_STATS_LEN + NN_ET_RVEC_GATHER_STATS + \ NN_ET_RVEC_STATS_LEN + NN_ET_QUEUE_STATS_LEN) @@ -179,30 +180,22 @@ static void nfp_net_get_ringparam(struct net_device *netdev, ring->rx_max_pending = NFP_NET_MAX_RX_DESCS; ring->tx_max_pending = NFP_NET_MAX_TX_DESCS; - ring->rx_pending = nn->rxd_cnt; - ring->tx_pending = nn->txd_cnt; + ring->rx_pending = nn->dp.rxd_cnt; + ring->tx_pending = nn->dp.txd_cnt; } static int nfp_net_set_ring_size(struct nfp_net *nn, u32 rxd_cnt, u32 txd_cnt) { - struct nfp_net_ring_set *reconfig_rx = NULL, *reconfig_tx = NULL; - struct nfp_net_ring_set rx = { - .n_rings = nn->num_rx_rings, - .mtu = nn->netdev->mtu, - .dcnt = rxd_cnt, - }; - struct nfp_net_ring_set tx = { - .n_rings = nn->num_tx_rings, - .dcnt = txd_cnt, - }; + struct nfp_net_dp *dp; + + dp = nfp_net_clone_dp(nn); + if (!dp) + return -ENOMEM; - if (nn->rxd_cnt != rxd_cnt) - reconfig_rx = ℞ - if (nn->txd_cnt != txd_cnt) - reconfig_tx = &tx; + dp->rxd_cnt = rxd_cnt; + dp->txd_cnt = txd_cnt; - return nfp_net_ring_reconfig(nn, &nn->xdp_prog, - reconfig_rx, reconfig_tx); + return nfp_net_ring_reconfig(nn, dp); } static int nfp_net_set_ringparam(struct net_device *netdev, @@ -223,11 +216,11 @@ static int nfp_net_set_ringparam(struct net_device *netdev, txd_cnt < NFP_NET_MIN_TX_DESCS || txd_cnt > NFP_NET_MAX_TX_DESCS) return -EINVAL; - if (nn->rxd_cnt == rxd_cnt && nn->txd_cnt == txd_cnt) + if (nn->dp.rxd_cnt == rxd_cnt && nn->dp.txd_cnt == txd_cnt) return 0; nn_dbg(nn, "Change ring size: RxQ %u->%u, TxQ %u->%u\n", - nn->rxd_cnt, rxd_cnt, nn->txd_cnt, txd_cnt); + nn->dp.rxd_cnt, rxd_cnt, nn->dp.txd_cnt, txd_cnt); return nfp_net_set_ring_size(nn, rxd_cnt, txd_cnt); } @@ -245,7 +238,7 @@ static void nfp_net_get_strings(struct net_device *netdev, memcpy(p, nfp_net_et_stats[i].name, ETH_GSTRING_LEN); p += ETH_GSTRING_LEN; } - for (i = 0; i < nn->num_r_vecs; i++) { + for (i = 0; i < nn->dp.num_r_vecs; i++) { sprintf(p, "rvec_%u_rx_pkts", i); p += ETH_GSTRING_LEN; sprintf(p, "rvec_%u_tx_pkts", i); @@ -267,13 +260,13 @@ static void nfp_net_get_strings(struct net_device *netdev, p += ETH_GSTRING_LEN; strncpy(p, "tx_lso", ETH_GSTRING_LEN); p += ETH_GSTRING_LEN; - for (i = 0; i < nn->num_tx_rings; i++) { + for (i = 0; i < nn->dp.num_tx_rings; i++) { sprintf(p, "txq_%u_pkts", i); p += ETH_GSTRING_LEN; sprintf(p, "txq_%u_bytes", i); p += ETH_GSTRING_LEN; } - for (i = 0; i < nn->num_rx_rings; i++) { + for (i = 0; i < nn->dp.num_rx_rings; i++) { sprintf(p, "rxq_%u_pkts", i); p += ETH_GSTRING_LEN; sprintf(p, "rxq_%u_bytes", i); @@ -306,12 +299,12 @@ static void nfp_net_get_stats(struct net_device *netdev, break; case NFP_NET_DEV_ET_STATS: - io_p = nn->ctrl_bar + nfp_net_et_stats[i].off; + io_p = nn->dp.ctrl_bar + nfp_net_et_stats[i].off; data[i] = readq(io_p); break; } } - for (j = 0; j < nn->num_r_vecs; j++) { + for (j = 0; j < nn->dp.num_r_vecs; j++) { unsigned int start; do { @@ -337,16 +330,16 @@ static void nfp_net_get_stats(struct net_device *netdev, } for (j = 0; j < NN_ET_RVEC_GATHER_STATS; j++) data[i++] = gathered_stats[j]; - for (j = 0; j < nn->num_tx_rings; j++) { - io_p = nn->ctrl_bar + NFP_NET_CFG_TXR_STATS(j); + for (j = 0; j < nn->dp.num_tx_rings; j++) { + io_p = nn->dp.ctrl_bar + NFP_NET_CFG_TXR_STATS(j); data[i++] = readq(io_p); - io_p = nn->ctrl_bar + NFP_NET_CFG_TXR_STATS(j) + 8; + io_p = nn->dp.ctrl_bar + NFP_NET_CFG_TXR_STATS(j) + 8; data[i++] = readq(io_p); } - for (j = 0; j < nn->num_rx_rings; j++) { - io_p = nn->ctrl_bar + NFP_NET_CFG_RXR_STATS(j); + for (j = 0; j < nn->dp.num_rx_rings; j++) { + io_p = nn->dp.ctrl_bar + NFP_NET_CFG_RXR_STATS(j); data[i++] = readq(io_p); - io_p = nn->ctrl_bar + NFP_NET_CFG_RXR_STATS(j) + 8; + io_p = nn->dp.ctrl_bar + NFP_NET_CFG_RXR_STATS(j) + 8; data[i++] = readq(io_p); } } @@ -410,7 +403,7 @@ static int nfp_net_get_rxnfc(struct net_device *netdev, switch (cmd->cmd) { case ETHTOOL_GRXRINGS: - cmd->data = nn->num_rx_rings; + cmd->data = nn->dp.num_rx_rings; return 0; case ETHTOOL_GRXFH: return nfp_net_get_rss_hash_opts(nn, cmd); @@ -454,13 +447,13 @@ static int nfp_net_set_rss_hash_opt(struct nfp_net *nn, return -EINVAL; } - new_rss_cfg |= NFP_NET_CFG_RSS_TOEPLITZ; + new_rss_cfg |= FIELD_PREP(NFP_NET_CFG_RSS_HFUNC, nn->rss_hfunc); new_rss_cfg |= NFP_NET_CFG_RSS_MASK; if (new_rss_cfg == nn->rss_cfg) return 0; - writel(new_rss_cfg, nn->ctrl_bar + NFP_NET_CFG_RSS_CTRL); + writel(new_rss_cfg, nn->dp.ctrl_bar + NFP_NET_CFG_RSS_CTRL); err = nfp_net_reconfig(nn, NFP_NET_CFG_UPDATE_RSS); if (err) return err; @@ -496,7 +489,12 @@ static u32 nfp_net_get_rxfh_indir_size(struct net_device *netdev) static u32 nfp_net_get_rxfh_key_size(struct net_device *netdev) { - return NFP_NET_CFG_RSS_KEY_SZ; + struct nfp_net *nn = netdev_priv(netdev); + + if (!(nn->cap & NFP_NET_CFG_CTRL_RSS)) + return -EOPNOTSUPP; + + return nfp_net_rss_key_sz(nn); } static int nfp_net_get_rxfh(struct net_device *netdev, u32 *indir, u8 *key, @@ -512,9 +510,12 @@ static int nfp_net_get_rxfh(struct net_device *netdev, u32 *indir, u8 *key, for (i = 0; i < ARRAY_SIZE(nn->rss_itbl); i++) indir[i] = nn->rss_itbl[i]; if (key) - memcpy(key, nn->rss_key, NFP_NET_CFG_RSS_KEY_SZ); - if (hfunc) - *hfunc = ETH_RSS_HASH_TOP; + memcpy(key, nn->rss_key, nfp_net_rss_key_sz(nn)); + if (hfunc) { + *hfunc = nn->rss_hfunc; + if (*hfunc >= 1 << ETH_RSS_HASH_FUNCS_COUNT) + *hfunc = ETH_RSS_HASH_UNKNOWN; + } return 0; } @@ -527,14 +528,14 @@ static int nfp_net_set_rxfh(struct net_device *netdev, int i; if (!(nn->cap & NFP_NET_CFG_CTRL_RSS) || - !(hfunc == ETH_RSS_HASH_NO_CHANGE || hfunc == ETH_RSS_HASH_TOP)) + !(hfunc == ETH_RSS_HASH_NO_CHANGE || hfunc == nn->rss_hfunc)) return -EOPNOTSUPP; if (!key && !indir) return 0; if (key) { - memcpy(nn->rss_key, key, NFP_NET_CFG_RSS_KEY_SZ); + memcpy(nn->rss_key, key, nfp_net_rss_key_sz(nn)); nfp_net_rss_write_key(nn); } if (indir) { @@ -564,7 +565,7 @@ static void nfp_net_get_regs(struct net_device *netdev, regs->version = nn_readl(nn, NFP_NET_CFG_VERSION); for (i = 0; i < NFP_NET_CFG_BAR_SZ / sizeof(u32); i++) - regs_buf[i] = readl(nn->ctrl_bar + (i * sizeof(u32))); + regs_buf[i] = readl(nn->dp.ctrl_bar + (i * sizeof(u32))); } static int nfp_net_get_coalesce(struct net_device *netdev, @@ -736,16 +737,16 @@ static void nfp_net_get_channels(struct net_device *netdev, struct nfp_net *nn = netdev_priv(netdev); unsigned int num_tx_rings; - num_tx_rings = nn->num_tx_rings; - if (nn->xdp_prog) - num_tx_rings -= nn->num_rx_rings; + num_tx_rings = nn->dp.num_tx_rings; + if (nn->dp.xdp_prog) + num_tx_rings -= nn->dp.num_rx_rings; channel->max_rx = min(nn->max_rx_rings, nn->max_r_vecs); channel->max_tx = min(nn->max_tx_rings, nn->max_r_vecs); channel->max_combined = min(channel->max_rx, channel->max_tx); channel->max_other = NFP_NET_NON_Q_VECTORS; - channel->combined_count = min(nn->num_rx_rings, num_tx_rings); - channel->rx_count = nn->num_rx_rings - channel->combined_count; + channel->combined_count = min(nn->dp.num_rx_rings, num_tx_rings); + channel->rx_count = nn->dp.num_rx_rings - channel->combined_count; channel->tx_count = num_tx_rings - channel->combined_count; channel->other_count = NFP_NET_NON_Q_VECTORS; } @@ -753,29 +754,19 @@ static void nfp_net_get_channels(struct net_device *netdev, static int nfp_net_set_num_rings(struct nfp_net *nn, unsigned int total_rx, unsigned int total_tx) { - struct nfp_net_ring_set *reconfig_rx = NULL, *reconfig_tx = NULL; - struct nfp_net_ring_set rx = { - .n_rings = total_rx, - .mtu = nn->netdev->mtu, - .dcnt = nn->rxd_cnt, - }; - struct nfp_net_ring_set tx = { - .n_rings = total_tx, - .dcnt = nn->txd_cnt, - }; + struct nfp_net_dp *dp; - if (nn->num_rx_rings != total_rx) - reconfig_rx = ℞ - if (nn->num_stack_tx_rings != total_tx || - (nn->xdp_prog && reconfig_rx)) - reconfig_tx = &tx; + dp = nfp_net_clone_dp(nn); + if (!dp) + return -ENOMEM; - /* nfp_net_check_config() will catch tx.n_rings > nn->max_tx_rings */ - if (nn->xdp_prog) - tx.n_rings += total_rx; + dp->num_rx_rings = total_rx; + dp->num_tx_rings = total_tx; + /* nfp_net_check_config() will catch num_tx_rings > nn->max_tx_rings */ + if (dp->xdp_prog) + dp->num_tx_rings += total_rx; - return nfp_net_ring_reconfig(nn, &nn->xdp_prog, - reconfig_rx, reconfig_tx); + return nfp_net_ring_reconfig(nn, dp); } static int nfp_net_set_channels(struct net_device *netdev, diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_main.c b/drivers/net/ethernet/netronome/nfp/nfp_net_main.c index 3afcdc11480c..2025cb7c6d90 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net_main.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_net_main.c @@ -130,7 +130,7 @@ err_area: } static void -nfp_net_get_mac_addr_hwinfo(struct nfp_net *nn, struct nfp_cpp *cpp, +nfp_net_get_mac_addr_hwinfo(struct nfp_net_dp *dp, struct nfp_cpp *cpp, unsigned int id) { u8 mac_addr[ETH_ALEN]; @@ -141,23 +141,22 @@ nfp_net_get_mac_addr_hwinfo(struct nfp_net *nn, struct nfp_cpp *cpp, mac_str = nfp_hwinfo_lookup(cpp, name); if (!mac_str) { - dev_warn(&nn->pdev->dev, - "Can't lookup MAC address. Generate\n"); - eth_hw_addr_random(nn->netdev); + dev_warn(dp->dev, "Can't lookup MAC address. Generate\n"); + eth_hw_addr_random(dp->netdev); return; } if (sscanf(mac_str, "%02hhx:%02hhx:%02hhx:%02hhx:%02hhx:%02hhx", &mac_addr[0], &mac_addr[1], &mac_addr[2], &mac_addr[3], &mac_addr[4], &mac_addr[5]) != 6) { - dev_warn(&nn->pdev->dev, + dev_warn(dp->dev, "Can't parse MAC address (%s). Generate.\n", mac_str); - eth_hw_addr_random(nn->netdev); + eth_hw_addr_random(dp->netdev); return; } - ether_addr_copy(nn->netdev->dev_addr, mac_addr); - ether_addr_copy(nn->netdev->perm_addr, mac_addr); + ether_addr_copy(dp->netdev->dev_addr, mac_addr); + ether_addr_copy(dp->netdev->perm_addr, mac_addr); } /** @@ -178,12 +177,14 @@ nfp_net_get_mac_addr(struct nfp_net *nn, struct nfp_pf *pf, unsigned int id) if (pf->eth_tbl->ports[i].eth_index == id) { const u8 *mac_addr = pf->eth_tbl->ports[i].mac_addr; - ether_addr_copy(nn->netdev->dev_addr, mac_addr); - ether_addr_copy(nn->netdev->perm_addr, mac_addr); + nn->eth_port = &pf->eth_tbl->ports[i]; + + ether_addr_copy(nn->dp.netdev->dev_addr, mac_addr); + ether_addr_copy(nn->dp.netdev->perm_addr, mac_addr); return; } - nfp_net_get_mac_addr_hwinfo(nn, pf->cpp, id); + nfp_net_get_mac_addr_hwinfo(&nn->dp, pf->cpp, id); } static unsigned int nfp_net_pf_get_num_ports(struct nfp_pf *pf) @@ -305,10 +306,10 @@ nfp_net_pf_alloc_port_netdev(struct nfp_pf *pf, void __iomem *ctrl_bar, nn->cpp = pf->cpp; nn->fw_ver = *fw_ver; - nn->ctrl_bar = ctrl_bar; + nn->dp.ctrl_bar = ctrl_bar; nn->tx_bar = tx_bar; nn->rx_bar = rx_bar; - nn->is_vf = 0; + nn->dp.is_vf = 0; nn->stride_rx = stride; nn->stride_tx = stride; @@ -330,7 +331,7 @@ nfp_net_pf_init_port_netdev(struct nfp_pf *pf, struct nfp_net *nn, */ nn->me_freq_mhz = 1200; - err = nfp_net_netdev_init(nn->netdev); + err = nfp_net_netdev_init(nn->dp.netdev); if (err) return err; @@ -399,7 +400,7 @@ nfp_net_pf_spawn_netdevs(struct nfp_pf *pf, /* Get MSI-X vectors */ wanted_irqs = 0; list_for_each_entry(nn, &pf->ports, port_list) - wanted_irqs += NFP_NET_NON_Q_VECTORS + nn->num_r_vecs; + wanted_irqs += NFP_NET_NON_Q_VECTORS + nn->dp.num_r_vecs; pf->irq_entries = kcalloc(wanted_irqs, sizeof(*pf->irq_entries), GFP_KERNEL); if (!pf->irq_entries) { @@ -444,7 +445,7 @@ nfp_net_pf_spawn_netdevs(struct nfp_pf *pf, err_prev_deinit: list_for_each_entry_continue_reverse(nn, &pf->ports, port_list) { nfp_net_debugfs_dir_clean(&nn->debugfs_dir); - nfp_net_netdev_clean(nn->netdev); + nfp_net_netdev_clean(nn->dp.netdev); } nfp_net_irqs_disable(pf->pdev); err_vec_free: @@ -570,7 +571,7 @@ void nfp_net_pci_remove(struct nfp_pf *pf) list_for_each_entry(nn, &pf->ports, port_list) { nfp_net_debugfs_dir_clean(&nn->debugfs_dir); - nfp_net_netdev_clean(nn->netdev); + nfp_net_netdev_clean(nn->dp.netdev); } nfp_net_pf_free_netdevs(pf); diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_offload.c b/drivers/net/ethernet/netronome/nfp/nfp_net_offload.c index 18a851eb3508..b5b6f69d1e0f 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net_offload.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_net_offload.c @@ -58,7 +58,7 @@ void nfp_net_filter_stats_timer(unsigned long data) spin_lock_bh(&nn->rx_filter_lock); - if (nn->ctrl & NFP_NET_CFG_CTRL_BPF) + if (nn->dp.ctrl & NFP_NET_CFG_CTRL_BPF) mod_timer(&nn->rx_filter_stats_timer, jiffies + NFP_NET_STAT_POLL_IVL); @@ -132,7 +132,7 @@ nfp_net_bpf_get_act(struct nfp_net *nn, struct tc_cls_bpf_offload *cls_bpf) return NN_ACT_TC_DROP; if (is_tcf_mirred_egress_redirect(a) && - tcf_mirred_ifindex(a) == nn->netdev->ifindex) + tcf_mirred_ifindex(a) == nn->dp.netdev->ifindex) return NN_ACT_TC_REDIR; } @@ -160,7 +160,7 @@ nfp_net_bpf_offload_prepare(struct nfp_net *nn, act = ret; max_mtu = nn_readb(nn, NFP_NET_CFG_BPF_INL_MTU) * 64 - 32; - if (max_mtu < nn->netdev->mtu) { + if (max_mtu < nn->dp.netdev->mtu) { nn_info(nn, "BPF offload not supported with MTU larger than HW packet split boundary\n"); return -ENOTSUPP; } @@ -168,8 +168,7 @@ nfp_net_bpf_offload_prepare(struct nfp_net *nn, start_off = nn_readw(nn, NFP_NET_CFG_BPF_START); done_off = nn_readw(nn, NFP_NET_CFG_BPF_DONE); - *code = dma_zalloc_coherent(&nn->pdev->dev, code_sz, dma_addr, - GFP_KERNEL); + *code = dma_zalloc_coherent(nn->dp.dev, code_sz, dma_addr, GFP_KERNEL); if (!*code) return -ENOMEM; @@ -181,7 +180,7 @@ nfp_net_bpf_offload_prepare(struct nfp_net *nn, return 0; out: - dma_free_coherent(&nn->pdev->dev, code_sz, *code, *dma_addr); + dma_free_coherent(nn->dp.dev, code_sz, *code, *dma_addr); return ret; } @@ -194,7 +193,7 @@ nfp_net_bpf_load_and_start(struct nfp_net *nn, u32 tc_flags, u64 bpf_addr = dma_addr; int err; - nn->bpf_offload_skip_sw = !!(tc_flags & TCA_CLS_FLAGS_SKIP_SW); + nn->dp.bpf_offload_skip_sw = !!(tc_flags & TCA_CLS_FLAGS_SKIP_SW); if (dense_mode) bpf_addr |= NFP_NET_CFG_BPF_CFG_8CTX; @@ -208,13 +207,13 @@ nfp_net_bpf_load_and_start(struct nfp_net *nn, u32 tc_flags, nn_err(nn, "FW command error while loading BPF: %d\n", err); /* Enable passing packets through BPF function */ - nn->ctrl |= NFP_NET_CFG_CTRL_BPF; - nn_writel(nn, NFP_NET_CFG_CTRL, nn->ctrl); + nn->dp.ctrl |= NFP_NET_CFG_CTRL_BPF; + nn_writel(nn, NFP_NET_CFG_CTRL, nn->dp.ctrl); err = nfp_net_reconfig(nn, NFP_NET_CFG_UPDATE_GEN); if (err) nn_err(nn, "FW command error while enabling BPF: %d\n", err); - dma_free_coherent(&nn->pdev->dev, code_sz, code, dma_addr); + dma_free_coherent(nn->dp.dev, code_sz, code, dma_addr); nfp_net_bpf_stats_reset(nn); mod_timer(&nn->rx_filter_stats_timer, jiffies + NFP_NET_STAT_POLL_IVL); @@ -222,16 +221,16 @@ nfp_net_bpf_load_and_start(struct nfp_net *nn, u32 tc_flags, static int nfp_net_bpf_stop(struct nfp_net *nn) { - if (!(nn->ctrl & NFP_NET_CFG_CTRL_BPF)) + if (!(nn->dp.ctrl & NFP_NET_CFG_CTRL_BPF)) return 0; spin_lock_bh(&nn->rx_filter_lock); - nn->ctrl &= ~NFP_NET_CFG_CTRL_BPF; + nn->dp.ctrl &= ~NFP_NET_CFG_CTRL_BPF; spin_unlock_bh(&nn->rx_filter_lock); - nn_writel(nn, NFP_NET_CFG_CTRL, nn->ctrl); + nn_writel(nn, NFP_NET_CFG_CTRL, nn->dp.ctrl); del_timer_sync(&nn->rx_filter_stats_timer); - nn->bpf_offload_skip_sw = 0; + nn->dp.bpf_offload_skip_sw = 0; return nfp_net_reconfig(nn, NFP_NET_CFG_UPDATE_GEN); } @@ -255,7 +254,7 @@ int nfp_net_bpf_offload(struct nfp_net *nn, struct tc_cls_bpf_offload *cls_bpf) * frames which didn't have BPF applied in the hardware should * be fine if software fallback is available, though. */ - if (nn->bpf_offload_skip_sw) + if (nn->dp.bpf_offload_skip_sw) return -EBUSY; err = nfp_net_bpf_offload_prepare(nn, cls_bpf, &res, &code, @@ -270,7 +269,7 @@ int nfp_net_bpf_offload(struct nfp_net *nn, struct tc_cls_bpf_offload *cls_bpf) return 0; case TC_CLSBPF_ADD: - if (nn->ctrl & NFP_NET_CFG_CTRL_BPF) + if (nn->dp.ctrl & NFP_NET_CFG_CTRL_BPF) return -EBUSY; err = nfp_net_bpf_offload_prepare(nn, cls_bpf, &res, &code, diff --git a/drivers/net/ethernet/netronome/nfp/nfp_netvf_main.c b/drivers/net/ethernet/netronome/nfp/nfp_netvf_main.c index 39407f7cc586..86e61be6f35c 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_netvf_main.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_netvf_main.c @@ -84,12 +84,12 @@ static void nfp_netvf_get_mac_addr(struct nfp_net *nn) put_unaligned_be16(nn_readw(nn, NFP_NET_CFG_MACADDR + 6), &mac_addr[4]); if (!is_valid_ether_addr(mac_addr)) { - eth_hw_addr_random(nn->netdev); + eth_hw_addr_random(nn->dp.netdev); return; } - ether_addr_copy(nn->netdev->dev_addr, mac_addr); - ether_addr_copy(nn->netdev->perm_addr, mac_addr); + ether_addr_copy(nn->dp.netdev->dev_addr, mac_addr); + ether_addr_copy(nn->dp.netdev->perm_addr, mac_addr); } static int nfp_netvf_pci_probe(struct pci_dev *pdev, @@ -210,8 +210,8 @@ static int nfp_netvf_pci_probe(struct pci_dev *pdev, vf->nn = nn; nn->fw_ver = fw_ver; - nn->ctrl_bar = ctrl_bar; - nn->is_vf = 1; + nn->dp.ctrl_bar = ctrl_bar; + nn->dp.is_vf = 1; nn->stride_tx = stride; nn->stride_rx = stride; @@ -268,7 +268,8 @@ static int nfp_netvf_pci_probe(struct pci_dev *pdev, num_irqs = nfp_net_irqs_alloc(pdev, vf->irq_entries, NFP_NET_MIN_PORT_IRQS, - NFP_NET_NON_Q_VECTORS + nn->num_r_vecs); + NFP_NET_NON_Q_VECTORS + + nn->dp.num_r_vecs); if (!num_irqs) { nn_warn(nn, "Unable to allocate MSI-X Vectors. Exiting\n"); err = -EIO; @@ -282,7 +283,7 @@ static int nfp_netvf_pci_probe(struct pci_dev *pdev, */ nn->me_freq_mhz = 1200; - err = nfp_net_netdev_init(nn->netdev); + err = nfp_net_netdev_init(nn->dp.netdev); if (err) goto err_irqs_disable; @@ -327,7 +328,7 @@ static void nfp_netvf_pci_remove(struct pci_dev *pdev) nfp_net_debugfs_dir_clean(&nn->debugfs_dir); nfp_net_debugfs_dir_clean(&vf->ddir); - nfp_net_netdev_clean(nn->netdev); + nfp_net_netdev_clean(nn->dp.netdev); nfp_net_irqs_disable(pdev); @@ -337,7 +338,7 @@ static void nfp_netvf_pci_remove(struct pci_dev *pdev) } else { iounmap(vf->q_bar); } - iounmap(nn->ctrl_bar); + iounmap(nn->dp.ctrl_bar); nfp_net_netdev_free(nn); diff --git a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp_eth.c b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp_eth.c index 1ece1f8ae4b3..38bd80077e33 100644 --- a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp_eth.c +++ b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp_eth.c @@ -134,9 +134,32 @@ nfp_eth_port_translate(const struct eth_table_entry *src, unsigned int index, nfp_eth_copy_mac_reverse(dst->mac_addr, src->mac_addr); - snprintf(dst->label, sizeof(dst->label) - 1, "%llu.%llu", - FIELD_GET(NSP_ETH_PORT_PHYLABEL, port), - FIELD_GET(NSP_ETH_PORT_LABEL, port)); + dst->label_port = FIELD_GET(NSP_ETH_PORT_PHYLABEL, port); + dst->label_subport = FIELD_GET(NSP_ETH_PORT_LABEL, port); +} + +static void +nfp_eth_mark_split_ports(struct nfp_cpp *cpp, struct nfp_eth_table *table) +{ + unsigned int i, j; + + for (i = 0; i < table->count; i++) + for (j = 0; j < table->count; j++) { + if (i == j) + continue; + if (table->ports[i].label_port != + table->ports[j].label_port) + continue; + if (table->ports[i].label_subport == + table->ports[j].label_subport) + nfp_warn(cpp, + "Port %d subport %d is a duplicate\n", + table->ports[i].label_port, + table->ports[i].label_subport); + + table->ports[i].is_split = true; + break; + } } /** @@ -168,8 +191,7 @@ __nfp_eth_read_ports(struct nfp_cpp *cpp, struct nfp_nsp *nsp) { struct eth_table_entry *entries; struct nfp_eth_table *table; - unsigned int cnt; - int i, j, ret; + int i, j, ret, cnt = 0; entries = kzalloc(NSP_ETH_TABLE_SIZE, GFP_KERNEL); if (!entries) @@ -178,24 +200,27 @@ __nfp_eth_read_ports(struct nfp_cpp *cpp, struct nfp_nsp *nsp) ret = nfp_nsp_read_eth_table(nsp, entries, NSP_ETH_TABLE_SIZE); if (ret < 0) { nfp_err(cpp, "reading port table failed %d\n", ret); - kfree(entries); - return NULL; + goto err; } - /* Some versions of flash will give us 0 instead of port count */ - cnt = ret; - if (!cnt) { - for (i = 0; i < NSP_ETH_MAX_COUNT; i++) - if (entries[i].port & NSP_ETH_PORT_LANES_MASK) - cnt++; + for (i = 0; i < NSP_ETH_MAX_COUNT; i++) + if (entries[i].port & NSP_ETH_PORT_LANES_MASK) + cnt++; + + /* Some versions of flash will give us 0 instead of port count. + * For those that give a port count, verify it against the value + * calculated above. + */ + if (ret && ret != cnt) { + nfp_err(cpp, "table entry count reported (%d) does not match entries present (%d)\n", + ret, cnt); + goto err; } table = kzalloc(sizeof(*table) + sizeof(struct nfp_eth_table_port) * cnt, GFP_KERNEL); - if (!table) { - kfree(entries); - return NULL; - } + if (!table) + goto err; table->count = cnt; for (i = 0, j = 0; i < NSP_ETH_MAX_COUNT; i++) @@ -203,9 +228,15 @@ __nfp_eth_read_ports(struct nfp_cpp *cpp, struct nfp_nsp *nsp) nfp_eth_port_translate(&entries[i], i, &table->ports[j++]); + nfp_eth_mark_split_ports(cpp, table); + kfree(entries); return table; + +err: + kfree(entries); + return NULL; } /** diff --git a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp_eth.h b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp_eth.h index edf703d319c8..325e841ca90a 100644 --- a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp_eth.h +++ b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp_eth.h @@ -49,10 +49,13 @@ * @lanes: number of channels * @speed: interface speed (in Mbps) * @mac_addr: interface MAC address - * @label: interface id string + * @label_port: port id + * @label_subport: id of interface within port (for split ports) * @enabled: is enabled? * @tx_enabled: is TX enabled? * @rx_enabled: is RX enabled? + * + * @is_split: is interface part of a split port */ struct nfp_eth_table { unsigned int count; @@ -65,14 +68,22 @@ struct nfp_eth_table { unsigned int speed; u8 mac_addr[ETH_ALEN]; - char label[8]; + + u8 label_port; + u8 label_subport; bool enabled; bool tx_enabled; bool rx_enabled; + + /* Computed fields */ + bool is_split; } ports[0]; }; +struct nfp_cpp; +struct nfp_nsp; + struct nfp_eth_table *nfp_eth_read_ports(struct nfp_cpp *cpp); struct nfp_eth_table * __nfp_eth_read_ports(struct nfp_cpp *cpp, struct nfp_nsp *nsp); diff --git a/drivers/net/ethernet/qlogic/netxen/netxen_nic_init.c b/drivers/net/ethernet/qlogic/netxen/netxen_nic_init.c index 7b43a3b4abdc..3dd973475125 100644 --- a/drivers/net/ethernet/qlogic/netxen/netxen_nic_init.c +++ b/drivers/net/ethernet/qlogic/netxen/netxen_nic_init.c @@ -1375,13 +1375,8 @@ netxen_receive_peg_ready(struct netxen_adapter *adapter) } while (--retries); - if (!retries) { - printk(KERN_ERR "Receive Peg initialization not " - "complete, state: 0x%x.\n", val); - return -EIO; - } - - return 0; + pr_err("Receive Peg initialization not complete, state: 0x%x.\n", val); + return -EIO; } int netxen_init_firmware(struct netxen_adapter *adapter) diff --git a/drivers/net/ethernet/qlogic/qed/qed.h b/drivers/net/ethernet/qlogic/qed/qed.h index 00c17fa6545b..ca30a27df035 100644 --- a/drivers/net/ethernet/qlogic/qed/qed.h +++ b/drivers/net/ethernet/qlogic/qed/qed.h @@ -51,7 +51,7 @@ #include "qed_hsi.h" extern const struct qed_common_ops qed_common_ops_pass; -#define DRV_MODULE_VERSION "8.10.10.20" +#define DRV_MODULE_VERSION "8.10.10.21" #define MAX_HWFNS_PER_DEVICE (4) #define NAME_SIZE 16 @@ -219,7 +219,9 @@ enum QED_PORT_MODE { QED_PORT_MODE_DE_4X20G, QED_PORT_MODE_DE_1X40G, QED_PORT_MODE_DE_2X25G, - QED_PORT_MODE_DE_1X25G + QED_PORT_MODE_DE_1X25G, + QED_PORT_MODE_DE_4X25G, + QED_PORT_MODE_DE_2X10G, }; enum qed_dev_cap { @@ -364,7 +366,8 @@ struct qed_hwfn { #define IS_LEAD_HWFN(edev) (!((edev)->my_id)) u8 rel_pf_id; /* Relative to engine*/ u8 abs_pf_id; -#define QED_PATH_ID(_p_hwfn) ((_p_hwfn)->abs_pf_id & 1) +#define QED_PATH_ID(_p_hwfn) \ + (QED_IS_K2((_p_hwfn)->cdev) ? 0 : ((_p_hwfn)->abs_pf_id & 1)) u8 port_id; bool b_active; @@ -523,9 +526,7 @@ struct qed_dev { u8 dp_level; char name[NAME_SIZE]; - u8 type; -#define QED_DEV_TYPE_BB (0 << 0) -#define QED_DEV_TYPE_AH BIT(0) + enum qed_dev_type type; /* Translate type/revision combo into the proper conditions */ #define QED_IS_BB(dev) ((dev)->type == QED_DEV_TYPE_BB) #define QED_IS_BB_A0(dev) (QED_IS_BB(dev) && \ @@ -540,6 +541,9 @@ struct qed_dev { u16 vendor_id; u16 device_id; +#define QED_DEV_ID_MASK 0xff00 +#define QED_DEV_ID_MASK_BB 0x1600 +#define QED_DEV_ID_MASK_AH 0x8000 u16 chip_num; #define CHIP_NUM_MASK 0xffff @@ -654,10 +658,16 @@ struct qed_dev { u32 rdma_max_srq_sge; }; -#define NUM_OF_VFS(dev) MAX_NUM_VFS_BB -#define NUM_OF_L2_QUEUES(dev) MAX_NUM_L2_QUEUES_BB -#define NUM_OF_SBS(dev) MAX_SB_PER_PATH_BB -#define NUM_OF_ENG_PFS(dev) MAX_NUM_PFS_BB +#define NUM_OF_VFS(dev) (QED_IS_BB(dev) ? MAX_NUM_VFS_BB \ + : MAX_NUM_VFS_K2) +#define NUM_OF_L2_QUEUES(dev) (QED_IS_BB(dev) ? MAX_NUM_L2_QUEUES_BB \ + : MAX_NUM_L2_QUEUES_K2) +#define NUM_OF_PORTS(dev) (QED_IS_BB(dev) ? MAX_NUM_PORTS_BB \ + : MAX_NUM_PORTS_K2) +#define NUM_OF_SBS(dev) (QED_IS_BB(dev) ? MAX_SB_PER_PATH_BB \ + : MAX_SB_PER_PATH_K2) +#define NUM_OF_ENG_PFS(dev) (QED_IS_BB(dev) ? MAX_NUM_PFS_BB \ + : MAX_NUM_PFS_K2) /** * @brief qed_concrete_to_sw_fid - get the sw function id from @@ -694,6 +704,7 @@ void qed_configure_vp_wfq_on_link_change(struct qed_dev *cdev, void qed_clean_wfq_db(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt); #define QED_LEADING_HWFN(dev) (&dev->hwfns[0]) +int qed_device_num_engines(struct qed_dev *cdev); /* Other Linux specific common definitions */ #define DP_NAME(cdev) ((cdev)->name) diff --git a/drivers/net/ethernet/qlogic/qed/qed_cxt.c b/drivers/net/ethernet/qlogic/qed/qed_cxt.c index d42d03df751a..9ff62cc5723d 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_cxt.c +++ b/drivers/net/ethernet/qlogic/qed/qed_cxt.c @@ -71,8 +71,7 @@ #define TM_ALIGN BIT(TM_SHIFT) #define TM_ELEM_SIZE 4 -/* For RoCE we configure to 64K to cover for RoCE max tasks 256K purpose. */ -#define ILT_DEFAULT_HW_P_SIZE (IS_ENABLED(CONFIG_QED_RDMA) ? 4 : 3) +#define ILT_DEFAULT_HW_P_SIZE 4 #define ILT_PAGE_IN_BYTES(hw_p_size) (1U << ((hw_p_size) + 12)) #define ILT_CFG_REG(cli, reg) PSWRQ2_REG_ ## cli ## _ ## reg ## _RT_OFFSET @@ -422,8 +421,9 @@ static void qed_cxt_set_proto_cid_count(struct qed_hwfn *p_hwfn, u32 page_sz = p_mgr->clients[ILT_CLI_CDUC].p_size.val; u32 cxt_size = CONN_CXT_SIZE(p_hwfn); u32 elems_per_page = ILT_PAGE_IN_BYTES(page_sz) / cxt_size; + u32 align = elems_per_page * DQ_RANGE_ALIGN; - p_conn->cid_count = roundup(p_conn->cid_count, elems_per_page); + p_conn->cid_count = roundup(p_conn->cid_count, align); } } @@ -1126,7 +1126,7 @@ int qed_cxt_mngr_alloc(struct qed_hwfn *p_hwfn) clients[ILT_CLI_TSDM].first.reg = ILT_CFG_REG(TSDM, FIRST_ILT); clients[ILT_CLI_TSDM].last.reg = ILT_CFG_REG(TSDM, LAST_ILT); clients[ILT_CLI_TSDM].p_size.reg = ILT_CFG_REG(TSDM, P_SIZE); - /* default ILT page size for all clients is 32K */ + /* default ILT page size for all clients is 64K */ for (i = 0; i < ILT_CLI_MAX; i++) p_mngr->clients[i].p_size.val = ILT_DEFAULT_HW_P_SIZE; diff --git a/drivers/net/ethernet/qlogic/qed/qed_debug.c b/drivers/net/ethernet/qlogic/qed/qed_debug.c index 68f19ca57f96..483241b4b05d 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_debug.c +++ b/drivers/net/ethernet/qlogic/qed/qed_debug.c @@ -17,7 +17,6 @@ /* Chip IDs enum */ enum chip_ids { - CHIP_RESERVED, CHIP_BB_B0, CHIP_K2, MAX_CHIP_IDS @@ -40,6 +39,7 @@ enum mem_groups { MEM_GROUP_BTB_RAM, MEM_GROUP_RDIF_CTX, MEM_GROUP_TDIF_CTX, + MEM_GROUP_CFC_MEM, MEM_GROUP_CONN_CFC_MEM, MEM_GROUP_TASK_CFC_MEM, MEM_GROUP_CAU_PI, @@ -72,6 +72,7 @@ static const char * const s_mem_group_names[] = { "BTB_RAM", "RDIF_CTX", "TDIF_CTX", + "CFC_MEM", "CONN_CFC_MEM", "TASK_CFC_MEM", "CAU_PI", @@ -185,13 +186,16 @@ struct dbg_array { u32 size_in_dwords; }; +struct chip_platform_defs { + u8 num_ports; + u8 num_pfs; + u8 num_vfs; +}; + /* Chip constant definitions */ struct chip_defs { const char *name; - struct { - u8 num_ports; - u8 num_pfs; - } per_platform[MAX_PLATFORM_IDS]; + struct chip_platform_defs per_platform[MAX_PLATFORM_IDS]; }; /* Platform constant definitions */ @@ -405,22 +409,23 @@ struct phy_defs { /***************************** Constant Arrays *******************************/ /* Debug arrays */ -static struct dbg_array s_dbg_arrays[MAX_BIN_DBG_BUFFER_TYPE] = { {NULL} }; +static struct dbg_array s_dbg_arrays[MAX_BIN_DBG_BUFFER_TYPE] = { {0} }; /* Chip constant definitions array */ static struct chip_defs s_chip_defs[MAX_CHIP_IDS] = { - { "reserved", { {0, 0}, {0, 0}, {0, 0}, {0, 0} } }, { "bb_b0", - { {MAX_NUM_PORTS_BB, MAX_NUM_PFS_BB}, {0, 0}, {0, 0}, {0, 0} } }, - { "k2", { {MAX_NUM_PORTS_K2, MAX_NUM_PFS_K2}, {0, 0}, {0, 0}, {0, 0} } } + { {MAX_NUM_PORTS_BB, MAX_NUM_PFS_BB, MAX_NUM_VFS_BB}, {0, 0, 0}, + {0, 0, 0}, {0, 0, 0} } }, + { "k2", + { {MAX_NUM_PORTS_K2, MAX_NUM_PFS_K2, MAX_NUM_VFS_K2}, {0, 0, 0}, + {0, 0, 0}, {0, 0, 0} } } }; /* Storm constant definitions array */ static struct storm_defs s_storm_defs[] = { /* Tstorm */ {'T', BLOCK_TSEM, - {DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCT, - DBG_BUS_CLIENT_RBCT}, true, + {DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCT}, true, TSEM_REG_FAST_MEMORY, TSEM_REG_DBG_FRAME_MODE, TSEM_REG_SLOW_DBG_ACTIVE, TSEM_REG_SLOW_DBG_MODE, TSEM_REG_DBG_MODE1_CFG, @@ -432,8 +437,7 @@ static struct storm_defs s_storm_defs[] = { 4, TCM_REG_SM_TASK_CTX}, /* Mstorm */ {'M', BLOCK_MSEM, - {DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCT, - DBG_BUS_CLIENT_RBCM}, false, + {DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCM}, false, MSEM_REG_FAST_MEMORY, MSEM_REG_DBG_FRAME_MODE, MSEM_REG_SLOW_DBG_ACTIVE, MSEM_REG_SLOW_DBG_MODE, MSEM_REG_DBG_MODE1_CFG, @@ -445,8 +449,7 @@ static struct storm_defs s_storm_defs[] = { 7, MCM_REG_SM_TASK_CTX}, /* Ustorm */ {'U', BLOCK_USEM, - {DBG_BUS_CLIENT_RBCU, DBG_BUS_CLIENT_RBCU, - DBG_BUS_CLIENT_RBCU}, false, + {DBG_BUS_CLIENT_RBCU, DBG_BUS_CLIENT_RBCU}, false, USEM_REG_FAST_MEMORY, USEM_REG_DBG_FRAME_MODE, USEM_REG_SLOW_DBG_ACTIVE, USEM_REG_SLOW_DBG_MODE, USEM_REG_DBG_MODE1_CFG, @@ -458,8 +461,7 @@ static struct storm_defs s_storm_defs[] = { 3, UCM_REG_SM_TASK_CTX}, /* Xstorm */ {'X', BLOCK_XSEM, - {DBG_BUS_CLIENT_RBCX, DBG_BUS_CLIENT_RBCX, - DBG_BUS_CLIENT_RBCX}, false, + {DBG_BUS_CLIENT_RBCX, DBG_BUS_CLIENT_RBCX}, false, XSEM_REG_FAST_MEMORY, XSEM_REG_DBG_FRAME_MODE, XSEM_REG_SLOW_DBG_ACTIVE, XSEM_REG_SLOW_DBG_MODE, XSEM_REG_DBG_MODE1_CFG, @@ -471,8 +473,7 @@ static struct storm_defs s_storm_defs[] = { 0, 0}, /* Ystorm */ {'Y', BLOCK_YSEM, - {DBG_BUS_CLIENT_RBCX, DBG_BUS_CLIENT_RBCX, - DBG_BUS_CLIENT_RBCY}, false, + {DBG_BUS_CLIENT_RBCX, DBG_BUS_CLIENT_RBCY}, false, YSEM_REG_FAST_MEMORY, YSEM_REG_DBG_FRAME_MODE, YSEM_REG_SLOW_DBG_ACTIVE, YSEM_REG_SLOW_DBG_MODE, YSEM_REG_DBG_MODE1_CFG, @@ -484,8 +485,7 @@ static struct storm_defs s_storm_defs[] = { 12, YCM_REG_SM_TASK_CTX}, /* Pstorm */ {'P', BLOCK_PSEM, - {DBG_BUS_CLIENT_RBCS, DBG_BUS_CLIENT_RBCS, - DBG_BUS_CLIENT_RBCS}, true, + {DBG_BUS_CLIENT_RBCS, DBG_BUS_CLIENT_RBCS}, true, PSEM_REG_FAST_MEMORY, PSEM_REG_DBG_FRAME_MODE, PSEM_REG_SLOW_DBG_ACTIVE, PSEM_REG_SLOW_DBG_MODE, PSEM_REG_DBG_MODE1_CFG, @@ -499,8 +499,9 @@ static struct storm_defs s_storm_defs[] = { /* Block definitions array */ static struct block_defs block_grc_defs = { - "grc", {true, true, true}, false, 0, - {DBG_BUS_CLIENT_RBCN, DBG_BUS_CLIENT_RBCN, DBG_BUS_CLIENT_RBCN}, + "grc", + {true, true}, false, 0, + {DBG_BUS_CLIENT_RBCN, DBG_BUS_CLIENT_RBCN}, GRC_REG_DBG_SELECT, GRC_REG_DBG_DWORD_ENABLE, GRC_REG_DBG_SHIFT, GRC_REG_DBG_FORCE_VALID, GRC_REG_DBG_FORCE_FRAME, @@ -508,29 +509,30 @@ static struct block_defs block_grc_defs = { }; static struct block_defs block_miscs_defs = { - "miscs", {false, false, false}, false, 0, - {MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS}, + "miscs", {false, false}, false, 0, + {MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS}, 0, 0, 0, 0, 0, false, false, MAX_DBG_RESET_REGS, 0 }; static struct block_defs block_misc_defs = { - "misc", {false, false, false}, false, 0, - {MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS}, + "misc", {false, false}, false, 0, + {MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS}, 0, 0, 0, 0, 0, false, false, MAX_DBG_RESET_REGS, 0 }; static struct block_defs block_dbu_defs = { - "dbu", {false, false, false}, false, 0, - {MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS}, + "dbu", {false, false}, false, 0, + {MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS}, 0, 0, 0, 0, 0, false, false, MAX_DBG_RESET_REGS, 0 }; static struct block_defs block_pglue_b_defs = { - "pglue_b", {true, true, true}, false, 0, - {DBG_BUS_CLIENT_RBCH, DBG_BUS_CLIENT_RBCH, DBG_BUS_CLIENT_RBCH}, + "pglue_b", + {true, true}, false, 0, + {DBG_BUS_CLIENT_RBCH, DBG_BUS_CLIENT_RBCH}, PGLUE_B_REG_DBG_SELECT, PGLUE_B_REG_DBG_DWORD_ENABLE, PGLUE_B_REG_DBG_SHIFT, PGLUE_B_REG_DBG_FORCE_VALID, PGLUE_B_REG_DBG_FORCE_FRAME, @@ -538,8 +540,9 @@ static struct block_defs block_pglue_b_defs = { }; static struct block_defs block_cnig_defs = { - "cnig", {false, false, true}, false, 0, - {MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS, DBG_BUS_CLIENT_RBCW}, + "cnig", + {false, true}, false, 0, + {MAX_DBG_BUS_CLIENTS, DBG_BUS_CLIENT_RBCW}, CNIG_REG_DBG_SELECT_K2, CNIG_REG_DBG_DWORD_ENABLE_K2, CNIG_REG_DBG_SHIFT_K2, CNIG_REG_DBG_FORCE_VALID_K2, CNIG_REG_DBG_FORCE_FRAME_K2, @@ -547,15 +550,16 @@ static struct block_defs block_cnig_defs = { }; static struct block_defs block_cpmu_defs = { - "cpmu", {false, false, false}, false, 0, - {MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS}, + "cpmu", {false, false}, false, 0, + {MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS}, 0, 0, 0, 0, 0, true, false, DBG_RESET_REG_MISCS_PL_HV, 8 }; static struct block_defs block_ncsi_defs = { - "ncsi", {true, true, true}, false, 0, - {DBG_BUS_CLIENT_RBCZ, DBG_BUS_CLIENT_RBCZ, DBG_BUS_CLIENT_RBCZ}, + "ncsi", + {true, true}, false, 0, + {DBG_BUS_CLIENT_RBCZ, DBG_BUS_CLIENT_RBCZ}, NCSI_REG_DBG_SELECT, NCSI_REG_DBG_DWORD_ENABLE, NCSI_REG_DBG_SHIFT, NCSI_REG_DBG_FORCE_VALID, NCSI_REG_DBG_FORCE_FRAME, @@ -563,15 +567,16 @@ static struct block_defs block_ncsi_defs = { }; static struct block_defs block_opte_defs = { - "opte", {false, false, false}, false, 0, - {MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS}, + "opte", {false, false}, false, 0, + {MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS}, 0, 0, 0, 0, 0, true, false, DBG_RESET_REG_MISCS_PL_HV, 4 }; static struct block_defs block_bmb_defs = { - "bmb", {true, true, true}, false, 0, - {DBG_BUS_CLIENT_RBCZ, DBG_BUS_CLIENT_RBCZ, DBG_BUS_CLIENT_RBCB}, + "bmb", + {true, true}, false, 0, + {DBG_BUS_CLIENT_RBCZ, DBG_BUS_CLIENT_RBCB}, BMB_REG_DBG_SELECT, BMB_REG_DBG_DWORD_ENABLE, BMB_REG_DBG_SHIFT, BMB_REG_DBG_FORCE_VALID, BMB_REG_DBG_FORCE_FRAME, @@ -579,8 +584,9 @@ static struct block_defs block_bmb_defs = { }; static struct block_defs block_pcie_defs = { - "pcie", {false, false, true}, false, 0, - {MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS, DBG_BUS_CLIENT_RBCH}, + "pcie", + {false, true}, false, 0, + {MAX_DBG_BUS_CLIENTS, DBG_BUS_CLIENT_RBCH}, PCIE_REG_DBG_COMMON_SELECT, PCIE_REG_DBG_COMMON_DWORD_ENABLE, PCIE_REG_DBG_COMMON_SHIFT, PCIE_REG_DBG_COMMON_FORCE_VALID, PCIE_REG_DBG_COMMON_FORCE_FRAME, @@ -588,15 +594,16 @@ static struct block_defs block_pcie_defs = { }; static struct block_defs block_mcp_defs = { - "mcp", {false, false, false}, false, 0, - {MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS}, + "mcp", {false, false}, false, 0, + {MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS}, 0, 0, 0, 0, 0, false, false, MAX_DBG_RESET_REGS, 0 }; static struct block_defs block_mcp2_defs = { - "mcp2", {true, true, true}, false, 0, - {DBG_BUS_CLIENT_RBCZ, DBG_BUS_CLIENT_RBCZ, DBG_BUS_CLIENT_RBCZ}, + "mcp2", + {true, true}, false, 0, + {DBG_BUS_CLIENT_RBCZ, DBG_BUS_CLIENT_RBCZ}, MCP2_REG_DBG_SELECT, MCP2_REG_DBG_DWORD_ENABLE, MCP2_REG_DBG_SHIFT, MCP2_REG_DBG_FORCE_VALID, MCP2_REG_DBG_FORCE_FRAME, @@ -604,8 +611,9 @@ static struct block_defs block_mcp2_defs = { }; static struct block_defs block_pswhst_defs = { - "pswhst", {true, true, true}, false, 0, - {DBG_BUS_CLIENT_RBCP, DBG_BUS_CLIENT_RBCP, DBG_BUS_CLIENT_RBCP}, + "pswhst", + {true, true}, false, 0, + {DBG_BUS_CLIENT_RBCP, DBG_BUS_CLIENT_RBCP}, PSWHST_REG_DBG_SELECT, PSWHST_REG_DBG_DWORD_ENABLE, PSWHST_REG_DBG_SHIFT, PSWHST_REG_DBG_FORCE_VALID, PSWHST_REG_DBG_FORCE_FRAME, @@ -613,8 +621,9 @@ static struct block_defs block_pswhst_defs = { }; static struct block_defs block_pswhst2_defs = { - "pswhst2", {true, true, true}, false, 0, - {DBG_BUS_CLIENT_RBCP, DBG_BUS_CLIENT_RBCP, DBG_BUS_CLIENT_RBCP}, + "pswhst2", + {true, true}, false, 0, + {DBG_BUS_CLIENT_RBCP, DBG_BUS_CLIENT_RBCP}, PSWHST2_REG_DBG_SELECT, PSWHST2_REG_DBG_DWORD_ENABLE, PSWHST2_REG_DBG_SHIFT, PSWHST2_REG_DBG_FORCE_VALID, PSWHST2_REG_DBG_FORCE_FRAME, @@ -622,8 +631,9 @@ static struct block_defs block_pswhst2_defs = { }; static struct block_defs block_pswrd_defs = { - "pswrd", {true, true, true}, false, 0, - {DBG_BUS_CLIENT_RBCP, DBG_BUS_CLIENT_RBCP, DBG_BUS_CLIENT_RBCP}, + "pswrd", + {true, true}, false, 0, + {DBG_BUS_CLIENT_RBCP, DBG_BUS_CLIENT_RBCP}, PSWRD_REG_DBG_SELECT, PSWRD_REG_DBG_DWORD_ENABLE, PSWRD_REG_DBG_SHIFT, PSWRD_REG_DBG_FORCE_VALID, PSWRD_REG_DBG_FORCE_FRAME, @@ -631,8 +641,9 @@ static struct block_defs block_pswrd_defs = { }; static struct block_defs block_pswrd2_defs = { - "pswrd2", {true, true, true}, false, 0, - {DBG_BUS_CLIENT_RBCP, DBG_BUS_CLIENT_RBCP, DBG_BUS_CLIENT_RBCP}, + "pswrd2", + {true, true}, false, 0, + {DBG_BUS_CLIENT_RBCP, DBG_BUS_CLIENT_RBCP}, PSWRD2_REG_DBG_SELECT, PSWRD2_REG_DBG_DWORD_ENABLE, PSWRD2_REG_DBG_SHIFT, PSWRD2_REG_DBG_FORCE_VALID, PSWRD2_REG_DBG_FORCE_FRAME, @@ -640,8 +651,9 @@ static struct block_defs block_pswrd2_defs = { }; static struct block_defs block_pswwr_defs = { - "pswwr", {true, true, true}, false, 0, - {DBG_BUS_CLIENT_RBCP, DBG_BUS_CLIENT_RBCP, DBG_BUS_CLIENT_RBCP}, + "pswwr", + {true, true}, false, 0, + {DBG_BUS_CLIENT_RBCP, DBG_BUS_CLIENT_RBCP}, PSWWR_REG_DBG_SELECT, PSWWR_REG_DBG_DWORD_ENABLE, PSWWR_REG_DBG_SHIFT, PSWWR_REG_DBG_FORCE_VALID, PSWWR_REG_DBG_FORCE_FRAME, @@ -649,15 +661,16 @@ static struct block_defs block_pswwr_defs = { }; static struct block_defs block_pswwr2_defs = { - "pswwr2", {false, false, false}, false, 0, - {MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS}, + "pswwr2", {false, false}, false, 0, + {MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS}, 0, 0, 0, 0, 0, true, false, DBG_RESET_REG_MISC_PL_HV, 3 }; static struct block_defs block_pswrq_defs = { - "pswrq", {true, true, true}, false, 0, - {DBG_BUS_CLIENT_RBCP, DBG_BUS_CLIENT_RBCP, DBG_BUS_CLIENT_RBCP}, + "pswrq", + {true, true}, false, 0, + {DBG_BUS_CLIENT_RBCP, DBG_BUS_CLIENT_RBCP}, PSWRQ_REG_DBG_SELECT, PSWRQ_REG_DBG_DWORD_ENABLE, PSWRQ_REG_DBG_SHIFT, PSWRQ_REG_DBG_FORCE_VALID, PSWRQ_REG_DBG_FORCE_FRAME, @@ -665,8 +678,9 @@ static struct block_defs block_pswrq_defs = { }; static struct block_defs block_pswrq2_defs = { - "pswrq2", {true, true, true}, false, 0, - {DBG_BUS_CLIENT_RBCP, DBG_BUS_CLIENT_RBCP, DBG_BUS_CLIENT_RBCP}, + "pswrq2", + {true, true}, false, 0, + {DBG_BUS_CLIENT_RBCP, DBG_BUS_CLIENT_RBCP}, PSWRQ2_REG_DBG_SELECT, PSWRQ2_REG_DBG_DWORD_ENABLE, PSWRQ2_REG_DBG_SHIFT, PSWRQ2_REG_DBG_FORCE_VALID, PSWRQ2_REG_DBG_FORCE_FRAME, @@ -674,8 +688,9 @@ static struct block_defs block_pswrq2_defs = { }; static struct block_defs block_pglcs_defs = { - "pglcs", {false, false, true}, false, 0, - {MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS, DBG_BUS_CLIENT_RBCH}, + "pglcs", + {false, true}, false, 0, + {MAX_DBG_BUS_CLIENTS, DBG_BUS_CLIENT_RBCH}, PGLCS_REG_DBG_SELECT, PGLCS_REG_DBG_DWORD_ENABLE, PGLCS_REG_DBG_SHIFT, PGLCS_REG_DBG_FORCE_VALID, PGLCS_REG_DBG_FORCE_FRAME, @@ -683,8 +698,9 @@ static struct block_defs block_pglcs_defs = { }; static struct block_defs block_ptu_defs = { - "ptu", {true, true, true}, false, 0, - {DBG_BUS_CLIENT_RBCP, DBG_BUS_CLIENT_RBCP, DBG_BUS_CLIENT_RBCP}, + "ptu", + {true, true}, false, 0, + {DBG_BUS_CLIENT_RBCP, DBG_BUS_CLIENT_RBCP}, PTU_REG_DBG_SELECT, PTU_REG_DBG_DWORD_ENABLE, PTU_REG_DBG_SHIFT, PTU_REG_DBG_FORCE_VALID, PTU_REG_DBG_FORCE_FRAME, @@ -692,8 +708,9 @@ static struct block_defs block_ptu_defs = { }; static struct block_defs block_dmae_defs = { - "dmae", {true, true, true}, false, 0, - {DBG_BUS_CLIENT_RBCP, DBG_BUS_CLIENT_RBCP, DBG_BUS_CLIENT_RBCP}, + "dmae", + {true, true}, false, 0, + {DBG_BUS_CLIENT_RBCP, DBG_BUS_CLIENT_RBCP}, DMAE_REG_DBG_SELECT, DMAE_REG_DBG_DWORD_ENABLE, DMAE_REG_DBG_SHIFT, DMAE_REG_DBG_FORCE_VALID, DMAE_REG_DBG_FORCE_FRAME, @@ -701,8 +718,9 @@ static struct block_defs block_dmae_defs = { }; static struct block_defs block_tcm_defs = { - "tcm", {true, true, true}, true, DBG_TSTORM_ID, - {DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCT}, + "tcm", + {true, true}, true, DBG_TSTORM_ID, + {DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCT}, TCM_REG_DBG_SELECT, TCM_REG_DBG_DWORD_ENABLE, TCM_REG_DBG_SHIFT, TCM_REG_DBG_FORCE_VALID, TCM_REG_DBG_FORCE_FRAME, @@ -710,8 +728,9 @@ static struct block_defs block_tcm_defs = { }; static struct block_defs block_mcm_defs = { - "mcm", {true, true, true}, true, DBG_MSTORM_ID, - {DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCM}, + "mcm", + {true, true}, true, DBG_MSTORM_ID, + {DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCM}, MCM_REG_DBG_SELECT, MCM_REG_DBG_DWORD_ENABLE, MCM_REG_DBG_SHIFT, MCM_REG_DBG_FORCE_VALID, MCM_REG_DBG_FORCE_FRAME, @@ -719,8 +738,9 @@ static struct block_defs block_mcm_defs = { }; static struct block_defs block_ucm_defs = { - "ucm", {true, true, true}, true, DBG_USTORM_ID, - {DBG_BUS_CLIENT_RBCU, DBG_BUS_CLIENT_RBCU, DBG_BUS_CLIENT_RBCU}, + "ucm", + {true, true}, true, DBG_USTORM_ID, + {DBG_BUS_CLIENT_RBCU, DBG_BUS_CLIENT_RBCU}, UCM_REG_DBG_SELECT, UCM_REG_DBG_DWORD_ENABLE, UCM_REG_DBG_SHIFT, UCM_REG_DBG_FORCE_VALID, UCM_REG_DBG_FORCE_FRAME, @@ -728,8 +748,9 @@ static struct block_defs block_ucm_defs = { }; static struct block_defs block_xcm_defs = { - "xcm", {true, true, true}, true, DBG_XSTORM_ID, - {DBG_BUS_CLIENT_RBCX, DBG_BUS_CLIENT_RBCX, DBG_BUS_CLIENT_RBCX}, + "xcm", + {true, true}, true, DBG_XSTORM_ID, + {DBG_BUS_CLIENT_RBCX, DBG_BUS_CLIENT_RBCX}, XCM_REG_DBG_SELECT, XCM_REG_DBG_DWORD_ENABLE, XCM_REG_DBG_SHIFT, XCM_REG_DBG_FORCE_VALID, XCM_REG_DBG_FORCE_FRAME, @@ -737,8 +758,9 @@ static struct block_defs block_xcm_defs = { }; static struct block_defs block_ycm_defs = { - "ycm", {true, true, true}, true, DBG_YSTORM_ID, - {DBG_BUS_CLIENT_RBCX, DBG_BUS_CLIENT_RBCX, DBG_BUS_CLIENT_RBCY}, + "ycm", + {true, true}, true, DBG_YSTORM_ID, + {DBG_BUS_CLIENT_RBCX, DBG_BUS_CLIENT_RBCY}, YCM_REG_DBG_SELECT, YCM_REG_DBG_DWORD_ENABLE, YCM_REG_DBG_SHIFT, YCM_REG_DBG_FORCE_VALID, YCM_REG_DBG_FORCE_FRAME, @@ -746,8 +768,9 @@ static struct block_defs block_ycm_defs = { }; static struct block_defs block_pcm_defs = { - "pcm", {true, true, true}, true, DBG_PSTORM_ID, - {DBG_BUS_CLIENT_RBCS, DBG_BUS_CLIENT_RBCS, DBG_BUS_CLIENT_RBCS}, + "pcm", + {true, true}, true, DBG_PSTORM_ID, + {DBG_BUS_CLIENT_RBCS, DBG_BUS_CLIENT_RBCS}, PCM_REG_DBG_SELECT, PCM_REG_DBG_DWORD_ENABLE, PCM_REG_DBG_SHIFT, PCM_REG_DBG_FORCE_VALID, PCM_REG_DBG_FORCE_FRAME, @@ -755,8 +778,9 @@ static struct block_defs block_pcm_defs = { }; static struct block_defs block_qm_defs = { - "qm", {true, true, true}, false, 0, - {DBG_BUS_CLIENT_RBCP, DBG_BUS_CLIENT_RBCP, DBG_BUS_CLIENT_RBCQ}, + "qm", + {true, true}, false, 0, + {DBG_BUS_CLIENT_RBCP, DBG_BUS_CLIENT_RBCQ}, QM_REG_DBG_SELECT, QM_REG_DBG_DWORD_ENABLE, QM_REG_DBG_SHIFT, QM_REG_DBG_FORCE_VALID, QM_REG_DBG_FORCE_FRAME, @@ -764,8 +788,9 @@ static struct block_defs block_qm_defs = { }; static struct block_defs block_tm_defs = { - "tm", {true, true, true}, false, 0, - {DBG_BUS_CLIENT_RBCS, DBG_BUS_CLIENT_RBCS, DBG_BUS_CLIENT_RBCS}, + "tm", + {true, true}, false, 0, + {DBG_BUS_CLIENT_RBCS, DBG_BUS_CLIENT_RBCS}, TM_REG_DBG_SELECT, TM_REG_DBG_DWORD_ENABLE, TM_REG_DBG_SHIFT, TM_REG_DBG_FORCE_VALID, TM_REG_DBG_FORCE_FRAME, @@ -773,8 +798,9 @@ static struct block_defs block_tm_defs = { }; static struct block_defs block_dorq_defs = { - "dorq", {true, true, true}, false, 0, - {DBG_BUS_CLIENT_RBCX, DBG_BUS_CLIENT_RBCX, DBG_BUS_CLIENT_RBCY}, + "dorq", + {true, true}, false, 0, + {DBG_BUS_CLIENT_RBCX, DBG_BUS_CLIENT_RBCY}, DORQ_REG_DBG_SELECT, DORQ_REG_DBG_DWORD_ENABLE, DORQ_REG_DBG_SHIFT, DORQ_REG_DBG_FORCE_VALID, DORQ_REG_DBG_FORCE_FRAME, @@ -782,8 +808,9 @@ static struct block_defs block_dorq_defs = { }; static struct block_defs block_brb_defs = { - "brb", {true, true, true}, false, 0, - {DBG_BUS_CLIENT_RBCR, DBG_BUS_CLIENT_RBCR, DBG_BUS_CLIENT_RBCR}, + "brb", + {true, true}, false, 0, + {DBG_BUS_CLIENT_RBCR, DBG_BUS_CLIENT_RBCR}, BRB_REG_DBG_SELECT, BRB_REG_DBG_DWORD_ENABLE, BRB_REG_DBG_SHIFT, BRB_REG_DBG_FORCE_VALID, BRB_REG_DBG_FORCE_FRAME, @@ -791,8 +818,9 @@ static struct block_defs block_brb_defs = { }; static struct block_defs block_src_defs = { - "src", {true, true, true}, false, 0, - {DBG_BUS_CLIENT_RBCF, DBG_BUS_CLIENT_RBCF, DBG_BUS_CLIENT_RBCF}, + "src", + {true, true}, false, 0, + {DBG_BUS_CLIENT_RBCF, DBG_BUS_CLIENT_RBCF}, SRC_REG_DBG_SELECT, SRC_REG_DBG_DWORD_ENABLE, SRC_REG_DBG_SHIFT, SRC_REG_DBG_FORCE_VALID, SRC_REG_DBG_FORCE_FRAME, @@ -800,8 +828,9 @@ static struct block_defs block_src_defs = { }; static struct block_defs block_prs_defs = { - "prs", {true, true, true}, false, 0, - {DBG_BUS_CLIENT_RBCR, DBG_BUS_CLIENT_RBCR, DBG_BUS_CLIENT_RBCR}, + "prs", + {true, true}, false, 0, + {DBG_BUS_CLIENT_RBCR, DBG_BUS_CLIENT_RBCR}, PRS_REG_DBG_SELECT, PRS_REG_DBG_DWORD_ENABLE, PRS_REG_DBG_SHIFT, PRS_REG_DBG_FORCE_VALID, PRS_REG_DBG_FORCE_FRAME, @@ -809,8 +838,9 @@ static struct block_defs block_prs_defs = { }; static struct block_defs block_tsdm_defs = { - "tsdm", {true, true, true}, true, DBG_TSTORM_ID, - {DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCT}, + "tsdm", + {true, true}, true, DBG_TSTORM_ID, + {DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCT}, TSDM_REG_DBG_SELECT, TSDM_REG_DBG_DWORD_ENABLE, TSDM_REG_DBG_SHIFT, TSDM_REG_DBG_FORCE_VALID, TSDM_REG_DBG_FORCE_FRAME, @@ -818,8 +848,9 @@ static struct block_defs block_tsdm_defs = { }; static struct block_defs block_msdm_defs = { - "msdm", {true, true, true}, true, DBG_MSTORM_ID, - {DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCM}, + "msdm", + {true, true}, true, DBG_MSTORM_ID, + {DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCM}, MSDM_REG_DBG_SELECT, MSDM_REG_DBG_DWORD_ENABLE, MSDM_REG_DBG_SHIFT, MSDM_REG_DBG_FORCE_VALID, MSDM_REG_DBG_FORCE_FRAME, @@ -827,8 +858,9 @@ static struct block_defs block_msdm_defs = { }; static struct block_defs block_usdm_defs = { - "usdm", {true, true, true}, true, DBG_USTORM_ID, - {DBG_BUS_CLIENT_RBCU, DBG_BUS_CLIENT_RBCU, DBG_BUS_CLIENT_RBCU}, + "usdm", + {true, true}, true, DBG_USTORM_ID, + {DBG_BUS_CLIENT_RBCU, DBG_BUS_CLIENT_RBCU}, USDM_REG_DBG_SELECT, USDM_REG_DBG_DWORD_ENABLE, USDM_REG_DBG_SHIFT, USDM_REG_DBG_FORCE_VALID, USDM_REG_DBG_FORCE_FRAME, @@ -836,8 +868,9 @@ static struct block_defs block_usdm_defs = { }; static struct block_defs block_xsdm_defs = { - "xsdm", {true, true, true}, true, DBG_XSTORM_ID, - {DBG_BUS_CLIENT_RBCX, DBG_BUS_CLIENT_RBCX, DBG_BUS_CLIENT_RBCX}, + "xsdm", + {true, true}, true, DBG_XSTORM_ID, + {DBG_BUS_CLIENT_RBCX, DBG_BUS_CLIENT_RBCX}, XSDM_REG_DBG_SELECT, XSDM_REG_DBG_DWORD_ENABLE, XSDM_REG_DBG_SHIFT, XSDM_REG_DBG_FORCE_VALID, XSDM_REG_DBG_FORCE_FRAME, @@ -845,8 +878,9 @@ static struct block_defs block_xsdm_defs = { }; static struct block_defs block_ysdm_defs = { - "ysdm", {true, true, true}, true, DBG_YSTORM_ID, - {DBG_BUS_CLIENT_RBCX, DBG_BUS_CLIENT_RBCX, DBG_BUS_CLIENT_RBCY}, + "ysdm", + {true, true}, true, DBG_YSTORM_ID, + {DBG_BUS_CLIENT_RBCX, DBG_BUS_CLIENT_RBCY}, YSDM_REG_DBG_SELECT, YSDM_REG_DBG_DWORD_ENABLE, YSDM_REG_DBG_SHIFT, YSDM_REG_DBG_FORCE_VALID, YSDM_REG_DBG_FORCE_FRAME, @@ -854,8 +888,9 @@ static struct block_defs block_ysdm_defs = { }; static struct block_defs block_psdm_defs = { - "psdm", {true, true, true}, true, DBG_PSTORM_ID, - {DBG_BUS_CLIENT_RBCS, DBG_BUS_CLIENT_RBCS, DBG_BUS_CLIENT_RBCS}, + "psdm", + {true, true}, true, DBG_PSTORM_ID, + {DBG_BUS_CLIENT_RBCS, DBG_BUS_CLIENT_RBCS}, PSDM_REG_DBG_SELECT, PSDM_REG_DBG_DWORD_ENABLE, PSDM_REG_DBG_SHIFT, PSDM_REG_DBG_FORCE_VALID, PSDM_REG_DBG_FORCE_FRAME, @@ -863,8 +898,9 @@ static struct block_defs block_psdm_defs = { }; static struct block_defs block_tsem_defs = { - "tsem", {true, true, true}, true, DBG_TSTORM_ID, - {DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCT}, + "tsem", + {true, true}, true, DBG_TSTORM_ID, + {DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCT}, TSEM_REG_DBG_SELECT, TSEM_REG_DBG_DWORD_ENABLE, TSEM_REG_DBG_SHIFT, TSEM_REG_DBG_FORCE_VALID, TSEM_REG_DBG_FORCE_FRAME, @@ -872,8 +908,9 @@ static struct block_defs block_tsem_defs = { }; static struct block_defs block_msem_defs = { - "msem", {true, true, true}, true, DBG_MSTORM_ID, - {DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCM}, + "msem", + {true, true}, true, DBG_MSTORM_ID, + {DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCM}, MSEM_REG_DBG_SELECT, MSEM_REG_DBG_DWORD_ENABLE, MSEM_REG_DBG_SHIFT, MSEM_REG_DBG_FORCE_VALID, MSEM_REG_DBG_FORCE_FRAME, @@ -881,8 +918,9 @@ static struct block_defs block_msem_defs = { }; static struct block_defs block_usem_defs = { - "usem", {true, true, true}, true, DBG_USTORM_ID, - {DBG_BUS_CLIENT_RBCU, DBG_BUS_CLIENT_RBCU, DBG_BUS_CLIENT_RBCU}, + "usem", + {true, true}, true, DBG_USTORM_ID, + {DBG_BUS_CLIENT_RBCU, DBG_BUS_CLIENT_RBCU}, USEM_REG_DBG_SELECT, USEM_REG_DBG_DWORD_ENABLE, USEM_REG_DBG_SHIFT, USEM_REG_DBG_FORCE_VALID, USEM_REG_DBG_FORCE_FRAME, @@ -890,8 +928,9 @@ static struct block_defs block_usem_defs = { }; static struct block_defs block_xsem_defs = { - "xsem", {true, true, true}, true, DBG_XSTORM_ID, - {DBG_BUS_CLIENT_RBCX, DBG_BUS_CLIENT_RBCX, DBG_BUS_CLIENT_RBCX}, + "xsem", + {true, true}, true, DBG_XSTORM_ID, + {DBG_BUS_CLIENT_RBCX, DBG_BUS_CLIENT_RBCX}, XSEM_REG_DBG_SELECT, XSEM_REG_DBG_DWORD_ENABLE, XSEM_REG_DBG_SHIFT, XSEM_REG_DBG_FORCE_VALID, XSEM_REG_DBG_FORCE_FRAME, @@ -899,8 +938,9 @@ static struct block_defs block_xsem_defs = { }; static struct block_defs block_ysem_defs = { - "ysem", {true, true, true}, true, DBG_YSTORM_ID, - {DBG_BUS_CLIENT_RBCX, DBG_BUS_CLIENT_RBCX, DBG_BUS_CLIENT_RBCY}, + "ysem", + {true, true}, true, DBG_YSTORM_ID, + {DBG_BUS_CLIENT_RBCX, DBG_BUS_CLIENT_RBCY}, YSEM_REG_DBG_SELECT, YSEM_REG_DBG_DWORD_ENABLE, YSEM_REG_DBG_SHIFT, YSEM_REG_DBG_FORCE_VALID, YSEM_REG_DBG_FORCE_FRAME, @@ -908,8 +948,9 @@ static struct block_defs block_ysem_defs = { }; static struct block_defs block_psem_defs = { - "psem", {true, true, true}, true, DBG_PSTORM_ID, - {DBG_BUS_CLIENT_RBCS, DBG_BUS_CLIENT_RBCS, DBG_BUS_CLIENT_RBCS}, + "psem", + {true, true}, true, DBG_PSTORM_ID, + {DBG_BUS_CLIENT_RBCS, DBG_BUS_CLIENT_RBCS}, PSEM_REG_DBG_SELECT, PSEM_REG_DBG_DWORD_ENABLE, PSEM_REG_DBG_SHIFT, PSEM_REG_DBG_FORCE_VALID, PSEM_REG_DBG_FORCE_FRAME, @@ -917,8 +958,9 @@ static struct block_defs block_psem_defs = { }; static struct block_defs block_rss_defs = { - "rss", {true, true, true}, false, 0, - {DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCT}, + "rss", + {true, true}, false, 0, + {DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCT}, RSS_REG_DBG_SELECT, RSS_REG_DBG_DWORD_ENABLE, RSS_REG_DBG_SHIFT, RSS_REG_DBG_FORCE_VALID, RSS_REG_DBG_FORCE_FRAME, @@ -926,8 +968,9 @@ static struct block_defs block_rss_defs = { }; static struct block_defs block_tmld_defs = { - "tmld", {true, true, true}, false, 0, - {DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCM}, + "tmld", + {true, true}, false, 0, + {DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCM}, TMLD_REG_DBG_SELECT, TMLD_REG_DBG_DWORD_ENABLE, TMLD_REG_DBG_SHIFT, TMLD_REG_DBG_FORCE_VALID, TMLD_REG_DBG_FORCE_FRAME, @@ -935,8 +978,9 @@ static struct block_defs block_tmld_defs = { }; static struct block_defs block_muld_defs = { - "muld", {true, true, true}, false, 0, - {DBG_BUS_CLIENT_RBCU, DBG_BUS_CLIENT_RBCU, DBG_BUS_CLIENT_RBCU}, + "muld", + {true, true}, false, 0, + {DBG_BUS_CLIENT_RBCU, DBG_BUS_CLIENT_RBCU}, MULD_REG_DBG_SELECT, MULD_REG_DBG_DWORD_ENABLE, MULD_REG_DBG_SHIFT, MULD_REG_DBG_FORCE_VALID, MULD_REG_DBG_FORCE_FRAME, @@ -944,8 +988,9 @@ static struct block_defs block_muld_defs = { }; static struct block_defs block_yuld_defs = { - "yuld", {true, true, true}, false, 0, - {DBG_BUS_CLIENT_RBCU, DBG_BUS_CLIENT_RBCU, DBG_BUS_CLIENT_RBCU}, + "yuld", + {true, true}, false, 0, + {DBG_BUS_CLIENT_RBCU, DBG_BUS_CLIENT_RBCU}, YULD_REG_DBG_SELECT, YULD_REG_DBG_DWORD_ENABLE, YULD_REG_DBG_SHIFT, YULD_REG_DBG_FORCE_VALID, YULD_REG_DBG_FORCE_FRAME, @@ -953,8 +998,9 @@ static struct block_defs block_yuld_defs = { }; static struct block_defs block_xyld_defs = { - "xyld", {true, true, true}, false, 0, - {DBG_BUS_CLIENT_RBCX, DBG_BUS_CLIENT_RBCX, DBG_BUS_CLIENT_RBCX}, + "xyld", + {true, true}, false, 0, + {DBG_BUS_CLIENT_RBCX, DBG_BUS_CLIENT_RBCX}, XYLD_REG_DBG_SELECT, XYLD_REG_DBG_DWORD_ENABLE, XYLD_REG_DBG_SHIFT, XYLD_REG_DBG_FORCE_VALID, XYLD_REG_DBG_FORCE_FRAME, @@ -962,8 +1008,9 @@ static struct block_defs block_xyld_defs = { }; static struct block_defs block_prm_defs = { - "prm", {true, true, true}, false, 0, - {DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCM}, + "prm", + {true, true}, false, 0, + {DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCM}, PRM_REG_DBG_SELECT, PRM_REG_DBG_DWORD_ENABLE, PRM_REG_DBG_SHIFT, PRM_REG_DBG_FORCE_VALID, PRM_REG_DBG_FORCE_FRAME, @@ -971,8 +1018,9 @@ static struct block_defs block_prm_defs = { }; static struct block_defs block_pbf_pb1_defs = { - "pbf_pb1", {true, true, true}, false, 0, - {DBG_BUS_CLIENT_RBCS, DBG_BUS_CLIENT_RBCS, DBG_BUS_CLIENT_RBCV}, + "pbf_pb1", + {true, true}, false, 0, + {DBG_BUS_CLIENT_RBCS, DBG_BUS_CLIENT_RBCV}, PBF_PB1_REG_DBG_SELECT, PBF_PB1_REG_DBG_DWORD_ENABLE, PBF_PB1_REG_DBG_SHIFT, PBF_PB1_REG_DBG_FORCE_VALID, PBF_PB1_REG_DBG_FORCE_FRAME, @@ -981,8 +1029,9 @@ static struct block_defs block_pbf_pb1_defs = { }; static struct block_defs block_pbf_pb2_defs = { - "pbf_pb2", {true, true, true}, false, 0, - {DBG_BUS_CLIENT_RBCS, DBG_BUS_CLIENT_RBCS, DBG_BUS_CLIENT_RBCV}, + "pbf_pb2", + {true, true}, false, 0, + {DBG_BUS_CLIENT_RBCS, DBG_BUS_CLIENT_RBCV}, PBF_PB2_REG_DBG_SELECT, PBF_PB2_REG_DBG_DWORD_ENABLE, PBF_PB2_REG_DBG_SHIFT, PBF_PB2_REG_DBG_FORCE_VALID, PBF_PB2_REG_DBG_FORCE_FRAME, @@ -991,8 +1040,9 @@ static struct block_defs block_pbf_pb2_defs = { }; static struct block_defs block_rpb_defs = { - "rpb", {true, true, true}, false, 0, - {DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCM}, + "rpb", + {true, true}, false, 0, + {DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCM}, RPB_REG_DBG_SELECT, RPB_REG_DBG_DWORD_ENABLE, RPB_REG_DBG_SHIFT, RPB_REG_DBG_FORCE_VALID, RPB_REG_DBG_FORCE_FRAME, @@ -1000,8 +1050,9 @@ static struct block_defs block_rpb_defs = { }; static struct block_defs block_btb_defs = { - "btb", {true, true, true}, false, 0, - {DBG_BUS_CLIENT_RBCR, DBG_BUS_CLIENT_RBCR, DBG_BUS_CLIENT_RBCV}, + "btb", + {true, true}, false, 0, + {DBG_BUS_CLIENT_RBCR, DBG_BUS_CLIENT_RBCV}, BTB_REG_DBG_SELECT, BTB_REG_DBG_DWORD_ENABLE, BTB_REG_DBG_SHIFT, BTB_REG_DBG_FORCE_VALID, BTB_REG_DBG_FORCE_FRAME, @@ -1009,8 +1060,9 @@ static struct block_defs block_btb_defs = { }; static struct block_defs block_pbf_defs = { - "pbf", {true, true, true}, false, 0, - {DBG_BUS_CLIENT_RBCS, DBG_BUS_CLIENT_RBCS, DBG_BUS_CLIENT_RBCV}, + "pbf", + {true, true}, false, 0, + {DBG_BUS_CLIENT_RBCS, DBG_BUS_CLIENT_RBCV}, PBF_REG_DBG_SELECT, PBF_REG_DBG_DWORD_ENABLE, PBF_REG_DBG_SHIFT, PBF_REG_DBG_FORCE_VALID, PBF_REG_DBG_FORCE_FRAME, @@ -1018,8 +1070,9 @@ static struct block_defs block_pbf_defs = { }; static struct block_defs block_rdif_defs = { - "rdif", {true, true, true}, false, 0, - {DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCM}, + "rdif", + {true, true}, false, 0, + {DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCM}, RDIF_REG_DBG_SELECT, RDIF_REG_DBG_DWORD_ENABLE, RDIF_REG_DBG_SHIFT, RDIF_REG_DBG_FORCE_VALID, RDIF_REG_DBG_FORCE_FRAME, @@ -1027,8 +1080,9 @@ static struct block_defs block_rdif_defs = { }; static struct block_defs block_tdif_defs = { - "tdif", {true, true, true}, false, 0, - {DBG_BUS_CLIENT_RBCS, DBG_BUS_CLIENT_RBCS, DBG_BUS_CLIENT_RBCS}, + "tdif", + {true, true}, false, 0, + {DBG_BUS_CLIENT_RBCS, DBG_BUS_CLIENT_RBCS}, TDIF_REG_DBG_SELECT, TDIF_REG_DBG_DWORD_ENABLE, TDIF_REG_DBG_SHIFT, TDIF_REG_DBG_FORCE_VALID, TDIF_REG_DBG_FORCE_FRAME, @@ -1036,8 +1090,9 @@ static struct block_defs block_tdif_defs = { }; static struct block_defs block_cdu_defs = { - "cdu", {true, true, true}, false, 0, - {DBG_BUS_CLIENT_RBCF, DBG_BUS_CLIENT_RBCF, DBG_BUS_CLIENT_RBCF}, + "cdu", + {true, true}, false, 0, + {DBG_BUS_CLIENT_RBCF, DBG_BUS_CLIENT_RBCF}, CDU_REG_DBG_SELECT, CDU_REG_DBG_DWORD_ENABLE, CDU_REG_DBG_SHIFT, CDU_REG_DBG_FORCE_VALID, CDU_REG_DBG_FORCE_FRAME, @@ -1045,8 +1100,9 @@ static struct block_defs block_cdu_defs = { }; static struct block_defs block_ccfc_defs = { - "ccfc", {true, true, true}, false, 0, - {DBG_BUS_CLIENT_RBCF, DBG_BUS_CLIENT_RBCF, DBG_BUS_CLIENT_RBCF}, + "ccfc", + {true, true}, false, 0, + {DBG_BUS_CLIENT_RBCF, DBG_BUS_CLIENT_RBCF}, CCFC_REG_DBG_SELECT, CCFC_REG_DBG_DWORD_ENABLE, CCFC_REG_DBG_SHIFT, CCFC_REG_DBG_FORCE_VALID, CCFC_REG_DBG_FORCE_FRAME, @@ -1054,8 +1110,9 @@ static struct block_defs block_ccfc_defs = { }; static struct block_defs block_tcfc_defs = { - "tcfc", {true, true, true}, false, 0, - {DBG_BUS_CLIENT_RBCF, DBG_BUS_CLIENT_RBCF, DBG_BUS_CLIENT_RBCF}, + "tcfc", + {true, true}, false, 0, + {DBG_BUS_CLIENT_RBCF, DBG_BUS_CLIENT_RBCF}, TCFC_REG_DBG_SELECT, TCFC_REG_DBG_DWORD_ENABLE, TCFC_REG_DBG_SHIFT, TCFC_REG_DBG_FORCE_VALID, TCFC_REG_DBG_FORCE_FRAME, @@ -1063,8 +1120,9 @@ static struct block_defs block_tcfc_defs = { }; static struct block_defs block_igu_defs = { - "igu", {true, true, true}, false, 0, - {DBG_BUS_CLIENT_RBCP, DBG_BUS_CLIENT_RBCP, DBG_BUS_CLIENT_RBCP}, + "igu", + {true, true}, false, 0, + {DBG_BUS_CLIENT_RBCP, DBG_BUS_CLIENT_RBCP}, IGU_REG_DBG_SELECT, IGU_REG_DBG_DWORD_ENABLE, IGU_REG_DBG_SHIFT, IGU_REG_DBG_FORCE_VALID, IGU_REG_DBG_FORCE_FRAME, @@ -1072,8 +1130,9 @@ static struct block_defs block_igu_defs = { }; static struct block_defs block_cau_defs = { - "cau", {true, true, true}, false, 0, - {DBG_BUS_CLIENT_RBCP, DBG_BUS_CLIENT_RBCP, DBG_BUS_CLIENT_RBCP}, + "cau", + {true, true}, false, 0, + {DBG_BUS_CLIENT_RBCP, DBG_BUS_CLIENT_RBCP}, CAU_REG_DBG_SELECT, CAU_REG_DBG_DWORD_ENABLE, CAU_REG_DBG_SHIFT, CAU_REG_DBG_FORCE_VALID, CAU_REG_DBG_FORCE_FRAME, @@ -1081,8 +1140,9 @@ static struct block_defs block_cau_defs = { }; static struct block_defs block_umac_defs = { - "umac", {false, false, true}, false, 0, - {MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS, DBG_BUS_CLIENT_RBCZ}, + "umac", + {false, true}, false, 0, + {MAX_DBG_BUS_CLIENTS, DBG_BUS_CLIENT_RBCZ}, UMAC_REG_DBG_SELECT, UMAC_REG_DBG_DWORD_ENABLE, UMAC_REG_DBG_SHIFT, UMAC_REG_DBG_FORCE_VALID, UMAC_REG_DBG_FORCE_FRAME, @@ -1090,22 +1150,23 @@ static struct block_defs block_umac_defs = { }; static struct block_defs block_xmac_defs = { - "xmac", {false, false, false}, false, 0, - {MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS}, + "xmac", {false, false}, false, 0, + {MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS}, 0, 0, 0, 0, 0, false, false, MAX_DBG_RESET_REGS, 0 }; static struct block_defs block_dbg_defs = { - "dbg", {false, false, false}, false, 0, - {MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS}, + "dbg", {false, false}, false, 0, + {MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS}, 0, 0, 0, 0, 0, true, true, DBG_RESET_REG_MISC_PL_PDA_VAUX, 3 }; static struct block_defs block_nig_defs = { - "nig", {true, true, true}, false, 0, - {DBG_BUS_CLIENT_RBCN, DBG_BUS_CLIENT_RBCN, DBG_BUS_CLIENT_RBCN}, + "nig", + {true, true}, false, 0, + {DBG_BUS_CLIENT_RBCN, DBG_BUS_CLIENT_RBCN}, NIG_REG_DBG_SELECT, NIG_REG_DBG_DWORD_ENABLE, NIG_REG_DBG_SHIFT, NIG_REG_DBG_FORCE_VALID, NIG_REG_DBG_FORCE_FRAME, @@ -1113,8 +1174,9 @@ static struct block_defs block_nig_defs = { }; static struct block_defs block_wol_defs = { - "wol", {false, false, true}, false, 0, - {MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS, DBG_BUS_CLIENT_RBCZ}, + "wol", + {false, true}, false, 0, + {MAX_DBG_BUS_CLIENTS, DBG_BUS_CLIENT_RBCZ}, WOL_REG_DBG_SELECT, WOL_REG_DBG_DWORD_ENABLE, WOL_REG_DBG_SHIFT, WOL_REG_DBG_FORCE_VALID, WOL_REG_DBG_FORCE_FRAME, @@ -1122,8 +1184,9 @@ static struct block_defs block_wol_defs = { }; static struct block_defs block_bmbn_defs = { - "bmbn", {false, false, true}, false, 0, - {MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS, DBG_BUS_CLIENT_RBCB}, + "bmbn", + {false, true}, false, 0, + {MAX_DBG_BUS_CLIENTS, DBG_BUS_CLIENT_RBCB}, BMBN_REG_DBG_SELECT, BMBN_REG_DBG_DWORD_ENABLE, BMBN_REG_DBG_SHIFT, BMBN_REG_DBG_FORCE_VALID, BMBN_REG_DBG_FORCE_FRAME, @@ -1131,15 +1194,16 @@ static struct block_defs block_bmbn_defs = { }; static struct block_defs block_ipc_defs = { - "ipc", {false, false, false}, false, 0, - {MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS}, + "ipc", {false, false}, false, 0, + {MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS}, 0, 0, 0, 0, 0, true, false, DBG_RESET_REG_MISCS_PL_UA, 8 }; static struct block_defs block_nwm_defs = { - "nwm", {false, false, true}, false, 0, - {MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS, DBG_BUS_CLIENT_RBCW}, + "nwm", + {false, true}, false, 0, + {MAX_DBG_BUS_CLIENTS, DBG_BUS_CLIENT_RBCW}, NWM_REG_DBG_SELECT, NWM_REG_DBG_DWORD_ENABLE, NWM_REG_DBG_SHIFT, NWM_REG_DBG_FORCE_VALID, NWM_REG_DBG_FORCE_FRAME, @@ -1147,22 +1211,29 @@ static struct block_defs block_nwm_defs = { }; static struct block_defs block_nws_defs = { - "nws", {false, false, false}, false, 0, - {MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS}, - 0, 0, 0, 0, 0, + "nws", + {false, true}, false, 0, + {MAX_DBG_BUS_CLIENTS, DBG_BUS_CLIENT_RBCW}, + NWS_REG_DBG_SELECT, NWS_REG_DBG_DWORD_ENABLE, + NWS_REG_DBG_SHIFT, NWS_REG_DBG_FORCE_VALID, + NWS_REG_DBG_FORCE_FRAME, true, false, DBG_RESET_REG_MISCS_PL_HV, 12 }; static struct block_defs block_ms_defs = { - "ms", {false, false, false}, false, 0, - {MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS}, - 0, 0, 0, 0, 0, + "ms", + {false, true}, false, 0, + {MAX_DBG_BUS_CLIENTS, DBG_BUS_CLIENT_RBCZ}, + MS_REG_DBG_SELECT, MS_REG_DBG_DWORD_ENABLE, + MS_REG_DBG_SHIFT, MS_REG_DBG_FORCE_VALID, + MS_REG_DBG_FORCE_FRAME, true, false, DBG_RESET_REG_MISCS_PL_HV, 13 }; static struct block_defs block_phy_pcie_defs = { - "phy_pcie", {false, false, true}, false, 0, - {MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS, DBG_BUS_CLIENT_RBCH}, + "phy_pcie", + {false, true}, false, 0, + {MAX_DBG_BUS_CLIENTS, DBG_BUS_CLIENT_RBCH}, PCIE_REG_DBG_COMMON_SELECT, PCIE_REG_DBG_COMMON_DWORD_ENABLE, PCIE_REG_DBG_COMMON_SHIFT, PCIE_REG_DBG_COMMON_FORCE_VALID, PCIE_REG_DBG_COMMON_FORCE_FRAME, @@ -1170,22 +1241,57 @@ static struct block_defs block_phy_pcie_defs = { }; static struct block_defs block_led_defs = { - "led", {false, false, false}, false, 0, - {MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS}, + "led", {false, false}, false, 0, + {MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS}, + 0, 0, 0, 0, 0, + true, false, DBG_RESET_REG_MISCS_PL_HV, 14 +}; + +static struct block_defs block_avs_wrap_defs = { + "avs_wrap", {false, false}, false, 0, + {MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS}, + 0, 0, 0, 0, 0, + true, false, DBG_RESET_REG_MISCS_PL_UA, 11 +}; + +static struct block_defs block_rgfs_defs = { + "rgfs", {false, false}, false, 0, + {MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS}, 0, 0, 0, 0, 0, - true, true, DBG_RESET_REG_MISCS_PL_HV, 14 + false, false, MAX_DBG_RESET_REGS, 0 +}; + +static struct block_defs block_tgfs_defs = { + "tgfs", {false, false}, false, 0, + {MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS}, + 0, 0, 0, 0, 0, + false, false, MAX_DBG_RESET_REGS, 0 +}; + +static struct block_defs block_ptld_defs = { + "ptld", {false, false}, false, 0, + {MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS}, + 0, 0, 0, 0, 0, + false, false, MAX_DBG_RESET_REGS, 0 +}; + +static struct block_defs block_ypld_defs = { + "ypld", {false, false}, false, 0, + {MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS}, + 0, 0, 0, 0, 0, + false, false, MAX_DBG_RESET_REGS, 0 }; static struct block_defs block_misc_aeu_defs = { - "misc_aeu", {false, false, false}, false, 0, - {MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS}, + "misc_aeu", {false, false}, false, 0, + {MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS}, 0, 0, 0, 0, 0, false, false, MAX_DBG_RESET_REGS, 0 }; static struct block_defs block_bar0_map_defs = { - "bar0_map", {false, false, false}, false, 0, - {MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS}, + "bar0_map", {false, false}, false, 0, + {MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS}, 0, 0, 0, 0, 0, false, false, MAX_DBG_RESET_REGS, 0 }; @@ -1269,6 +1375,11 @@ static struct block_defs *s_block_defs[MAX_BLOCK_ID] = { &block_ms_defs, &block_phy_pcie_defs, &block_led_defs, + &block_avs_wrap_defs, + &block_rgfs_defs, + &block_tgfs_defs, + &block_ptld_defs, + &block_ypld_defs, &block_misc_aeu_defs, &block_bar0_map_defs, }; @@ -1281,65 +1392,67 @@ static struct platform_defs s_platform_defs[] = { }; static struct grc_param_defs s_grc_param_defs[] = { - {{1, 1, 1}, 0, 1, false, 1, 1}, /* DBG_GRC_PARAM_DUMP_TSTORM */ - {{1, 1, 1}, 0, 1, false, 1, 1}, /* DBG_GRC_PARAM_DUMP_MSTORM */ - {{1, 1, 1}, 0, 1, false, 1, 1}, /* DBG_GRC_PARAM_DUMP_USTORM */ - {{1, 1, 1}, 0, 1, false, 1, 1}, /* DBG_GRC_PARAM_DUMP_XSTORM */ - {{1, 1, 1}, 0, 1, false, 1, 1}, /* DBG_GRC_PARAM_DUMP_YSTORM */ - {{1, 1, 1}, 0, 1, false, 1, 1}, /* DBG_GRC_PARAM_DUMP_PSTORM */ - {{1, 1, 1}, 0, 1, false, 0, 1}, /* DBG_GRC_PARAM_DUMP_REGS */ - {{1, 1, 1}, 0, 1, false, 0, 1}, /* DBG_GRC_PARAM_DUMP_RAM */ - {{1, 1, 1}, 0, 1, false, 0, 1}, /* DBG_GRC_PARAM_DUMP_PBUF */ - {{0, 0, 0}, 0, 1, false, 0, 1}, /* DBG_GRC_PARAM_DUMP_IOR */ - {{0, 0, 0}, 0, 1, false, 0, 1}, /* DBG_GRC_PARAM_DUMP_VFC */ - {{1, 1, 1}, 0, 1, false, 0, 1}, /* DBG_GRC_PARAM_DUMP_CM_CTX */ - {{1, 1, 1}, 0, 1, false, 0, 1}, /* DBG_GRC_PARAM_DUMP_ILT */ - {{1, 1, 1}, 0, 1, false, 0, 1}, /* DBG_GRC_PARAM_DUMP_RSS */ - {{1, 1, 1}, 0, 1, false, 0, 1}, /* DBG_GRC_PARAM_DUMP_CAU */ - {{1, 1, 1}, 0, 1, false, 0, 1}, /* DBG_GRC_PARAM_DUMP_QM */ - {{1, 1, 1}, 0, 1, false, 0, 1}, /* DBG_GRC_PARAM_DUMP_MCP */ - {{1, 1, 1}, 0, 1, false, 0, 1}, /* DBG_GRC_PARAM_RESERVED */ - {{1, 1, 1}, 0, 1, false, 0, 1}, /* DBG_GRC_PARAM_DUMP_CFC */ - {{1, 1, 1}, 0, 1, false, 0, 1}, /* DBG_GRC_PARAM_DUMP_IGU */ - {{0, 0, 0}, 0, 1, false, 0, 1}, /* DBG_GRC_PARAM_DUMP_BRB */ - {{0, 0, 0}, 0, 1, false, 0, 1}, /* DBG_GRC_PARAM_DUMP_BTB */ - {{0, 0, 0}, 0, 1, false, 0, 1}, /* DBG_GRC_PARAM_DUMP_BMB */ - {{1, 1, 1}, 0, 1, false, 0, 1}, /* DBG_GRC_PARAM_DUMP_NIG */ - {{1, 1, 1}, 0, 1, false, 0, 1}, /* DBG_GRC_PARAM_DUMP_MULD */ - {{1, 1, 1}, 0, 1, false, 0, 1}, /* DBG_GRC_PARAM_DUMP_PRS */ - {{1, 1, 1}, 0, 1, false, 0, 1}, /* DBG_GRC_PARAM_DUMP_DMAE */ - {{1, 1, 1}, 0, 1, false, 0, 1}, /* DBG_GRC_PARAM_DUMP_TM */ - {{1, 1, 1}, 0, 1, false, 0, 1}, /* DBG_GRC_PARAM_DUMP_SDM */ - {{1, 1, 1}, 0, 1, false, 0, 1}, /* DBG_GRC_PARAM_DUMP_DIF */ - {{1, 1, 1}, 0, 1, false, 0, 1}, /* DBG_GRC_PARAM_DUMP_STATIC */ - {{0, 0, 0}, 0, 1, false, 0, 0}, /* DBG_GRC_PARAM_UNSTALL */ - {{MAX_LCIDS, MAX_LCIDS, MAX_LCIDS}, 1, MAX_LCIDS, false, MAX_LCIDS, + {{1, 1}, 0, 1, false, 1, 1}, /* DBG_GRC_PARAM_DUMP_TSTORM */ + {{1, 1}, 0, 1, false, 1, 1}, /* DBG_GRC_PARAM_DUMP_MSTORM */ + {{1, 1}, 0, 1, false, 1, 1}, /* DBG_GRC_PARAM_DUMP_USTORM */ + {{1, 1}, 0, 1, false, 1, 1}, /* DBG_GRC_PARAM_DUMP_XSTORM */ + {{1, 1}, 0, 1, false, 1, 1}, /* DBG_GRC_PARAM_DUMP_YSTORM */ + {{1, 1}, 0, 1, false, 1, 1}, /* DBG_GRC_PARAM_DUMP_PSTORM */ + {{1, 1}, 0, 1, false, 0, 1}, /* DBG_GRC_PARAM_DUMP_REGS */ + {{1, 1}, 0, 1, false, 0, 1}, /* DBG_GRC_PARAM_DUMP_RAM */ + {{1, 1}, 0, 1, false, 0, 1}, /* DBG_GRC_PARAM_DUMP_PBUF */ + {{0, 0}, 0, 1, false, 0, 1}, /* DBG_GRC_PARAM_DUMP_IOR */ + {{0, 0}, 0, 1, false, 0, 1}, /* DBG_GRC_PARAM_DUMP_VFC */ + {{1, 1}, 0, 1, false, 0, 1}, /* DBG_GRC_PARAM_DUMP_CM_CTX */ + {{1, 1}, 0, 1, false, 0, 1}, /* DBG_GRC_PARAM_DUMP_ILT */ + {{1, 1}, 0, 1, false, 0, 1}, /* DBG_GRC_PARAM_DUMP_RSS */ + {{1, 1}, 0, 1, false, 0, 1}, /* DBG_GRC_PARAM_DUMP_CAU */ + {{1, 1}, 0, 1, false, 0, 1}, /* DBG_GRC_PARAM_DUMP_QM */ + {{1, 1}, 0, 1, false, 0, 1}, /* DBG_GRC_PARAM_DUMP_MCP */ + {{1, 1}, 0, 1, false, 0, 1}, /* DBG_GRC_PARAM_RESERVED */ + {{1, 1}, 0, 1, false, 0, 1}, /* DBG_GRC_PARAM_DUMP_CFC */ + {{1, 1}, 0, 1, false, 0, 1}, /* DBG_GRC_PARAM_DUMP_IGU */ + {{0, 0}, 0, 1, false, 0, 1}, /* DBG_GRC_PARAM_DUMP_BRB */ + {{0, 0}, 0, 1, false, 0, 1}, /* DBG_GRC_PARAM_DUMP_BTB */ + {{0, 0}, 0, 1, false, 0, 1}, /* DBG_GRC_PARAM_DUMP_BMB */ + {{1, 1}, 0, 1, false, 0, 1}, /* DBG_GRC_PARAM_DUMP_NIG */ + {{1, 1}, 0, 1, false, 0, 1}, /* DBG_GRC_PARAM_DUMP_MULD */ + {{1, 1}, 0, 1, false, 0, 1}, /* DBG_GRC_PARAM_DUMP_PRS */ + {{1, 1}, 0, 1, false, 0, 1}, /* DBG_GRC_PARAM_DUMP_DMAE */ + {{1, 1}, 0, 1, false, 0, 1}, /* DBG_GRC_PARAM_DUMP_TM */ + {{1, 1}, 0, 1, false, 0, 1}, /* DBG_GRC_PARAM_DUMP_SDM */ + {{1, 1}, 0, 1, false, 0, 1}, /* DBG_GRC_PARAM_DUMP_DIF */ + {{1, 1}, 0, 1, false, 0, 1}, /* DBG_GRC_PARAM_DUMP_STATIC */ + {{0, 0}, 0, 1, false, 0, 0}, /* DBG_GRC_PARAM_UNSTALL */ + {{MAX_LCIDS, MAX_LCIDS}, 1, MAX_LCIDS, false, MAX_LCIDS, MAX_LCIDS}, /* DBG_GRC_PARAM_NUM_LCIDS */ - {{MAX_LTIDS, MAX_LTIDS, MAX_LTIDS}, 1, MAX_LTIDS, false, MAX_LTIDS, + {{MAX_LTIDS, MAX_LTIDS}, 1, MAX_LTIDS, false, MAX_LTIDS, MAX_LTIDS}, /* DBG_GRC_PARAM_NUM_LTIDS */ - {{0, 0, 0}, 0, 1, true, 0, 0}, /* DBG_GRC_PARAM_EXCLUDE_ALL */ - {{0, 0, 0}, 0, 1, true, 0, 0}, /* DBG_GRC_PARAM_CRASH */ - {{0, 0, 0}, 0, 1, false, 1, 0}, /* DBG_GRC_PARAM_PARITY_SAFE */ - {{1, 1, 1}, 0, 1, false, 0, 1}, /* DBG_GRC_PARAM_DUMP_CM */ - {{1, 1, 1}, 0, 1, false, 0, 1} /* DBG_GRC_PARAM_DUMP_PHY */ + {{0, 0}, 0, 1, true, 0, 0}, /* DBG_GRC_PARAM_EXCLUDE_ALL */ + {{0, 0}, 0, 1, true, 0, 0}, /* DBG_GRC_PARAM_CRASH */ + {{0, 0}, 0, 1, false, 1, 0}, /* DBG_GRC_PARAM_PARITY_SAFE */ + {{1, 1}, 0, 1, false, 0, 1}, /* DBG_GRC_PARAM_DUMP_CM */ + {{1, 1}, 0, 1, false, 0, 1}, /* DBG_GRC_PARAM_DUMP_PHY */ + {{0, 0}, 0, 1, false, 0, 0}, /* DBG_GRC_PARAM_NO_MCP */ + {{0, 0}, 0, 1, false, 0, 0} /* DBG_GRC_PARAM_NO_FW_VER */ }; static struct rss_mem_defs s_rss_mem_defs[] = { { "rss_mem_cid", "rss_cid", 0, - {256, 256, 320}, - {32, 32, 32} }, + {256, 320}, + {32, 32} }, { "rss_mem_key_msb", "rss_key", 1024, - {128, 128, 208}, - {256, 256, 256} }, + {128, 208}, + {256, 256} }, { "rss_mem_key_lsb", "rss_key", 2048, - {128, 128, 208}, - {64, 64, 64} }, + {128, 208}, + {64, 64} }, { "rss_mem_info", "rss_info", 3072, - {128, 128, 208}, - {16, 16, 16} }, + {128, 208}, + {16, 16} }, { "rss_mem_ind", "rss_ind", 4096, - {(128 * 128), (128 * 128), (128 * 208)}, - {16, 16, 16} } + {(128 * 128), (128 * 208)}, + {16, 16} } }; static struct vfc_ram_defs s_vfc_ram_defs[] = { @@ -1352,32 +1465,32 @@ static struct vfc_ram_defs s_vfc_ram_defs[] = { static struct big_ram_defs s_big_ram_defs[] = { { "BRB", MEM_GROUP_BRB_MEM, MEM_GROUP_BRB_RAM, DBG_GRC_PARAM_DUMP_BRB, BRB_REG_BIG_RAM_ADDRESS, BRB_REG_BIG_RAM_DATA, - {4800, 4800, 5632} }, + {4800, 5632} }, { "BTB", MEM_GROUP_BTB_MEM, MEM_GROUP_BTB_RAM, DBG_GRC_PARAM_DUMP_BTB, BTB_REG_BIG_RAM_ADDRESS, BTB_REG_BIG_RAM_DATA, - {2880, 2880, 3680} }, + {2880, 3680} }, { "BMB", MEM_GROUP_BMB_MEM, MEM_GROUP_BMB_RAM, DBG_GRC_PARAM_DUMP_BMB, BMB_REG_BIG_RAM_ADDRESS, BMB_REG_BIG_RAM_DATA, - {1152, 1152, 1152} } + {1152, 1152} } }; static struct reset_reg_defs s_reset_regs_defs[] = { { MISCS_REG_RESET_PL_UA, 0x0, - {true, true, true} }, /* DBG_RESET_REG_MISCS_PL_UA */ + {true, true} }, /* DBG_RESET_REG_MISCS_PL_UA */ { MISCS_REG_RESET_PL_HV, 0x0, - {true, true, true} }, /* DBG_RESET_REG_MISCS_PL_HV */ + {true, true} }, /* DBG_RESET_REG_MISCS_PL_HV */ { MISCS_REG_RESET_PL_HV_2, 0x0, - {false, false, true} }, /* DBG_RESET_REG_MISCS_PL_HV_2 */ + {false, true} }, /* DBG_RESET_REG_MISCS_PL_HV_2 */ { MISC_REG_RESET_PL_UA, 0x0, - {true, true, true} }, /* DBG_RESET_REG_MISC_PL_UA */ + {true, true} }, /* DBG_RESET_REG_MISC_PL_UA */ { MISC_REG_RESET_PL_HV, 0x0, - {true, true, true} }, /* DBG_RESET_REG_MISC_PL_HV */ + {true, true} }, /* DBG_RESET_REG_MISC_PL_HV */ { MISC_REG_RESET_PL_PDA_VMAIN_1, 0x4404040, - {true, true, true} }, /* DBG_RESET_REG_MISC_PL_PDA_VMAIN_1 */ + {true, true} }, /* DBG_RESET_REG_MISC_PL_PDA_VMAIN_1 */ { MISC_REG_RESET_PL_PDA_VMAIN_2, 0x7c00007, - {true, true, true} }, /* DBG_RESET_REG_MISC_PL_PDA_VMAIN_2 */ + {true, true} }, /* DBG_RESET_REG_MISC_PL_PDA_VMAIN_2 */ { MISC_REG_RESET_PL_PDA_VAUX, 0x2, - {true, true, true} }, /* DBG_RESET_REG_MISC_PL_PDA_VAUX */ + {true, true} }, /* DBG_RESET_REG_MISC_PL_PDA_VAUX */ }; static struct phy_defs s_phy_defs[] = { @@ -1410,6 +1523,26 @@ static u32 qed_read_unaligned_dword(u8 *buf) return dword; } +/* Returns the value of the specified GRC param */ +static u32 qed_grc_get_param(struct qed_hwfn *p_hwfn, + enum dbg_grc_params grc_param) +{ + struct dbg_tools_data *dev_data = &p_hwfn->dbg_info; + + return dev_data->grc.param_val[grc_param]; +} + +/* Initializes the GRC parameters */ +static void qed_dbg_grc_init_params(struct qed_hwfn *p_hwfn) +{ + struct dbg_tools_data *dev_data = &p_hwfn->dbg_info; + + if (!dev_data->grc.params_initialized) { + qed_dbg_grc_set_params_default(p_hwfn); + dev_data->grc.params_initialized = 1; + } +} + /* Initializes debug data for the specified device */ static enum dbg_status qed_dbg_dev_init(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt) @@ -1424,13 +1557,17 @@ static enum dbg_status qed_dbg_dev_init(struct qed_hwfn *p_hwfn, dev_data->mode_enable[MODE_K2] = 1; } else if (QED_IS_BB_B0(p_hwfn->cdev)) { dev_data->chip_id = CHIP_BB_B0; - dev_data->mode_enable[MODE_BB_B0] = 1; + dev_data->mode_enable[MODE_BB] = 1; } else { return DBG_STATUS_UNKNOWN_CHIP; } dev_data->platform_id = PLATFORM_ASIC; dev_data->mode_enable[MODE_ASIC] = 1; + + /* Initializes the GRC parameters */ + qed_dbg_grc_init_params(p_hwfn); + dev_data->initialized = true; return DBG_STATUS_OK; } @@ -1561,7 +1698,7 @@ static u32 qed_dump_fw_ver_param(struct qed_hwfn *p_hwfn, int printed_chars; u32 offset = 0; - if (dump) { + if (dump && !qed_grc_get_param(p_hwfn, DBG_GRC_PARAM_NO_FW_VER)) { /* Read FW image/version from PRAM in a non-reset SEMI */ bool found = false; u8 storm_id; @@ -1622,7 +1759,7 @@ static u32 qed_dump_mfw_ver_param(struct qed_hwfn *p_hwfn, { char mfw_ver_str[16] = EMPTY_FW_VERSION_STR; - if (dump) { + if (dump && !qed_grc_get_param(p_hwfn, DBG_GRC_PARAM_NO_FW_VER)) { u32 global_section_offsize, global_section_addr, mfw_ver; u32 public_data_addr, global_section_offsize_addr; int printed_chars; @@ -1683,15 +1820,13 @@ static u32 qed_dump_common_global_params(struct qed_hwfn *p_hwfn, bool dump, u8 num_specific_global_params) { + u8 num_params = NUM_COMMON_GLOBAL_PARAMS + num_specific_global_params; struct dbg_tools_data *dev_data = &p_hwfn->dbg_info; u32 offset = 0; /* Find platform string and dump global params section header */ offset += qed_dump_section_hdr(dump_buf + offset, - dump, - "global_params", - NUM_COMMON_GLOBAL_PARAMS + - num_specific_global_params); + dump, "global_params", num_params); /* Store params */ offset += qed_dump_fw_ver_param(p_hwfn, p_ptt, dump_buf + offset, dump); @@ -1815,37 +1950,6 @@ static bool qed_is_mode_match(struct qed_hwfn *p_hwfn, u16 *modes_buf_offset) } } -/* Returns the value of the specified GRC param */ -static u32 qed_grc_get_param(struct qed_hwfn *p_hwfn, - enum dbg_grc_params grc_param) -{ - struct dbg_tools_data *dev_data = &p_hwfn->dbg_info; - - return dev_data->grc.param_val[grc_param]; -} - -/* Clear all GRC params */ -static void qed_dbg_grc_clear_params(struct qed_hwfn *p_hwfn) -{ - struct dbg_tools_data *dev_data = &p_hwfn->dbg_info; - u32 i; - - for (i = 0; i < MAX_DBG_GRC_PARAMS; i++) - dev_data->grc.param_set_by_user[i] = 0; -} - -/* Assign default GRC param values */ -static void qed_dbg_grc_set_params_default(struct qed_hwfn *p_hwfn) -{ - struct dbg_tools_data *dev_data = &p_hwfn->dbg_info; - u32 i; - - for (i = 0; i < MAX_DBG_GRC_PARAMS; i++) - if (!dev_data->grc.param_set_by_user[i]) - dev_data->grc.param_val[i] = - s_grc_param_defs[i].default_val[dev_data->chip_id]; -} - /* Returns true if the specified entity (indicated by GRC param) should be * included in the dump, false otherwise. */ @@ -1971,7 +2075,7 @@ static void qed_grc_unreset_blocks(struct qed_hwfn *p_hwfn, } } -/* Returns the attention name offsets of the specified block */ +/* Returns the attention block data of the specified block */ static const struct dbg_attn_block_type_data * qed_get_block_attn_data(enum block_id block_id, enum dbg_attn_type attn_type) { @@ -2040,7 +2144,7 @@ static void qed_grc_clear_all_prty(struct qed_hwfn *p_hwfn, * The following parameters are dumped: * - 'count' = num_dumped_entries * - 'split' = split_type - * - 'id'i = split_id (dumped only if split_id >= 0) + * - 'id' = split_id (dumped only if split_id >= 0) * - 'param_name' = param_val (user param, dumped only if param_name != NULL and * param_val != NULL) */ @@ -2069,21 +2173,81 @@ static u32 qed_grc_dump_regs_hdr(u32 *dump_buf, return offset; } -/* Dumps GRC register/memory. Returns the dumped size in dwords. */ +/* Dumps the GRC registers in the specified address range. + * Returns the dumped size in dwords. + */ +static u32 qed_grc_dump_addr_range(struct qed_hwfn *p_hwfn, + struct qed_ptt *p_ptt, u32 *dump_buf, + bool dump, u32 addr, u32 len) +{ + u32 byte_addr = DWORDS_TO_BYTES(addr), offset = 0, i; + + if (dump) + for (i = 0; i < len; i++, byte_addr += BYTES_IN_DWORD, offset++) + *(dump_buf + offset) = qed_rd(p_hwfn, p_ptt, byte_addr); + else + offset += len; + return offset; +} + +/* Dumps GRC registers sequence header. Returns the dumped size in dwords. */ +static u32 qed_grc_dump_reg_entry_hdr(u32 *dump_buf, bool dump, u32 addr, + u32 len) +{ + if (dump) + *dump_buf = addr | (len << REG_DUMP_LEN_SHIFT); + return 1; +} + +/* Dumps GRC registers sequence. Returns the dumped size in dwords. */ static u32 qed_grc_dump_reg_entry(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, u32 *dump_buf, bool dump, u32 addr, u32 len) { - u32 offset = 0, i; + u32 offset = 0; + + offset += qed_grc_dump_reg_entry_hdr(dump_buf, dump, addr, len); + offset += qed_grc_dump_addr_range(p_hwfn, + p_ptt, + dump_buf + offset, dump, addr, len); + return offset; +} + +/* Dumps GRC registers sequence with skip cycle. + * Returns the dumped size in dwords. + */ +static u32 qed_grc_dump_reg_entry_skip(struct qed_hwfn *p_hwfn, + struct qed_ptt *p_ptt, u32 *dump_buf, + bool dump, u32 addr, u32 total_len, + u32 read_len, u32 skip_len) +{ + u32 offset = 0, reg_offset = 0; + offset += qed_grc_dump_reg_entry_hdr(dump_buf, dump, addr, total_len); if (dump) { - *(dump_buf + offset++) = addr | (len << REG_DUMP_LEN_SHIFT); - for (i = 0; i < len; i++, addr++, offset++) - *(dump_buf + offset) = qed_rd(p_hwfn, - p_ptt, - DWORDS_TO_BYTES(addr)); + while (reg_offset < total_len) { + u32 curr_len = min_t(u32, + read_len, + total_len - reg_offset); + offset += qed_grc_dump_addr_range(p_hwfn, + p_ptt, + dump_buf + offset, + dump, addr, curr_len); + reg_offset += curr_len; + addr += curr_len; + if (reg_offset < total_len) { + curr_len = min_t(u32, + skip_len, + total_len - skip_len); + memset(dump_buf + offset, 0, + DWORDS_TO_BYTES(curr_len)); + offset += curr_len; + reg_offset += curr_len; + addr += curr_len; + } + } } else { - offset += len + 1; + offset += total_len; } return offset; @@ -2124,14 +2288,17 @@ static u32 qed_grc_dump_regs_entries(struct qed_hwfn *p_hwfn, const struct dbg_dump_reg *reg = (const struct dbg_dump_reg *) &input_regs_arr.ptr[input_offset]; + u32 addr, len; + addr = GET_FIELD(reg->data, + DBG_DUMP_REG_ADDRESS); + len = GET_FIELD(reg->data, DBG_DUMP_REG_LENGTH); offset += - qed_grc_dump_reg_entry(p_hwfn, p_ptt, - dump_buf + offset, dump, - GET_FIELD(reg->data, - DBG_DUMP_REG_ADDRESS), - GET_FIELD(reg->data, - DBG_DUMP_REG_LENGTH)); + qed_grc_dump_reg_entry(p_hwfn, p_ptt, + dump_buf + offset, + dump, + addr, + len); (*num_dumped_reg_entries)++; } } else { @@ -2194,8 +2361,14 @@ static u32 qed_grc_dump_registers(struct qed_hwfn *p_hwfn, const char *param_name, const char *param_val) { struct dbg_tools_data *dev_data = &p_hwfn->dbg_info; + struct chip_platform_defs *p_platform_defs; u32 offset = 0, input_offset = 0; - u8 port_id, pf_id; + struct chip_defs *p_chip_defs; + u8 port_id, pf_id, vf_id; + u16 fid; + + p_chip_defs = &s_chip_defs[dev_data->chip_id]; + p_platform_defs = &p_chip_defs->per_platform[dev_data->platform_id]; if (dump) DP_VERBOSE(p_hwfn, QED_MSG_DEBUG, "Dumping registers...\n"); @@ -2214,7 +2387,6 @@ static u32 qed_grc_dump_registers(struct qed_hwfn *p_hwfn, switch (split_type_id) { case SPLIT_TYPE_NONE: - case SPLIT_TYPE_VF: offset += qed_grc_dump_split_data(p_hwfn, p_ptt, curr_input_regs_arr, @@ -2227,10 +2399,7 @@ static u32 qed_grc_dump_registers(struct qed_hwfn *p_hwfn, param_val); break; case SPLIT_TYPE_PORT: - for (port_id = 0; - port_id < - s_chip_defs[dev_data->chip_id]. - per_platform[dev_data->platform_id].num_ports; + for (port_id = 0; port_id < p_platform_defs->num_ports; port_id++) { if (dump) qed_port_pretend(p_hwfn, p_ptt, @@ -2247,20 +2416,48 @@ static u32 qed_grc_dump_registers(struct qed_hwfn *p_hwfn, break; case SPLIT_TYPE_PF: case SPLIT_TYPE_PORT_PF: - for (pf_id = 0; - pf_id < - s_chip_defs[dev_data->chip_id]. - per_platform[dev_data->platform_id].num_pfs; + for (pf_id = 0; pf_id < p_platform_defs->num_pfs; pf_id++) { - if (dump) - qed_fid_pretend(p_hwfn, p_ptt, pf_id); - offset += qed_grc_dump_split_data(p_hwfn, - p_ptt, - curr_input_regs_arr, - dump_buf + offset, - dump, block_enable, - "pf", pf_id, param_name, - param_val); + u8 pfid_shift = + PXP_PRETEND_CONCRETE_FID_PFID_SHIFT; + + if (dump) { + fid = pf_id << pfid_shift; + qed_fid_pretend(p_hwfn, p_ptt, fid); + } + + offset += + qed_grc_dump_split_data(p_hwfn, p_ptt, + curr_input_regs_arr, + dump_buf + offset, + dump, block_enable, + "pf", pf_id, + param_name, + param_val); + } + break; + case SPLIT_TYPE_VF: + for (vf_id = 0; vf_id < p_platform_defs->num_vfs; + vf_id++) { + u8 vfvalid_shift = + PXP_PRETEND_CONCRETE_FID_VFVALID_SHIFT; + u8 vfid_shift = + PXP_PRETEND_CONCRETE_FID_VFID_SHIFT; + + if (dump) { + fid = BIT(vfvalid_shift) | + (vf_id << vfid_shift); + qed_fid_pretend(p_hwfn, p_ptt, fid); + } + + offset += + qed_grc_dump_split_data(p_hwfn, p_ptt, + curr_input_regs_arr, + dump_buf + offset, + dump, block_enable, + "vf", vf_id, + param_name, + param_val); } break; default: @@ -2271,8 +2468,11 @@ static u32 qed_grc_dump_registers(struct qed_hwfn *p_hwfn, } /* Pretend to original PF */ - if (dump) - qed_fid_pretend(p_hwfn, p_ptt, p_hwfn->rel_pf_id); + if (dump) { + fid = p_hwfn->rel_pf_id << PXP_PRETEND_CONCRETE_FID_PFID_SHIFT; + qed_fid_pretend(p_hwfn, p_ptt, fid); + } + return offset; } @@ -2291,13 +2491,14 @@ static u32 qed_grc_dump_reset_regs(struct qed_hwfn *p_hwfn, /* Write reset registers */ for (i = 0; i < MAX_DBG_RESET_REGS; i++) { if (s_reset_regs_defs[i].exists[dev_data->chip_id]) { + u32 addr = BYTES_TO_DWORDS(s_reset_regs_defs[i].addr); + offset += qed_grc_dump_reg_entry(p_hwfn, p_ptt, dump_buf + offset, dump, - BYTES_TO_DWORDS - (s_reset_regs_defs - [i].addr), 1); + addr, + 1); num_regs++; } } @@ -2339,6 +2540,7 @@ static u32 qed_grc_dump_modified_regs(struct qed_hwfn *p_hwfn, &attn_reg_arr[reg_idx]; u16 modes_buf_offset; bool eval_mode; + u32 addr; /* Check mode */ eval_mode = GET_FIELD(reg_data->mode.data, @@ -2349,19 +2551,23 @@ static u32 qed_grc_dump_modified_regs(struct qed_hwfn *p_hwfn, if (!eval_mode || qed_is_mode_match(p_hwfn, &modes_buf_offset)) { /* Mode match - read and dump registers */ - offset += qed_grc_dump_reg_entry(p_hwfn, - p_ptt, - dump_buf + offset, - dump, - reg_data->mask_address, - 1); - offset += qed_grc_dump_reg_entry(p_hwfn, - p_ptt, - dump_buf + offset, - dump, - GET_FIELD(reg_data->data, - DBG_ATTN_REG_STS_ADDRESS), - 1); + addr = reg_data->mask_address; + offset += + qed_grc_dump_reg_entry(p_hwfn, + p_ptt, + dump_buf + offset, + dump, + addr, + 1); + addr = GET_FIELD(reg_data->data, + DBG_ATTN_REG_STS_ADDRESS); + offset += + qed_grc_dump_reg_entry(p_hwfn, + p_ptt, + dump_buf + offset, + dump, + addr, + 1); num_reg_entries += 2; } } @@ -2369,18 +2575,21 @@ static u32 qed_grc_dump_modified_regs(struct qed_hwfn *p_hwfn, /* Write storm stall status registers */ for (storm_id = 0; storm_id < MAX_DBG_STORMS; storm_id++) { + u32 addr; + if (dev_data->block_in_reset[s_storm_defs[storm_id].block_id] && dump) continue; + addr = + BYTES_TO_DWORDS(s_storm_defs[storm_id].sem_fast_mem_addr + + SEM_FAST_REG_STALLED); offset += qed_grc_dump_reg_entry(p_hwfn, - p_ptt, - dump_buf + offset, - dump, - BYTES_TO_DWORDS(s_storm_defs[storm_id]. - sem_fast_mem_addr + - SEM_FAST_REG_STALLED), - 1); + p_ptt, + dump_buf + offset, + dump, + addr, + 1); num_reg_entries++; } @@ -2392,11 +2601,47 @@ static u32 qed_grc_dump_modified_regs(struct qed_hwfn *p_hwfn, return offset; } +/* Dumps registers that can't be represented in the debug arrays */ +static u32 qed_grc_dump_special_regs(struct qed_hwfn *p_hwfn, + struct qed_ptt *p_ptt, + u32 *dump_buf, bool dump) +{ + u32 offset = 0, addr; + + offset += qed_grc_dump_regs_hdr(dump_buf, + dump, 2, "eng", -1, NULL, NULL); + + /* Dump R/TDIF_REG_DEBUG_ERROR_INFO_SIZE (every 8'th register should be + * skipped). + */ + addr = BYTES_TO_DWORDS(RDIF_REG_DEBUG_ERROR_INFO); + offset += qed_grc_dump_reg_entry_skip(p_hwfn, + p_ptt, + dump_buf + offset, + dump, + addr, + RDIF_REG_DEBUG_ERROR_INFO_SIZE, + 7, + 1); + addr = BYTES_TO_DWORDS(TDIF_REG_DEBUG_ERROR_INFO); + offset += + qed_grc_dump_reg_entry_skip(p_hwfn, + p_ptt, + dump_buf + offset, + dump, + addr, + TDIF_REG_DEBUG_ERROR_INFO_SIZE, + 7, + 1); + + return offset; +} + /* Dumps a GRC memory header (section and params). * The following parameters are dumped: * name - name is dumped only if it's not NULL. - * addr - byte_addr is dumped only if name is NULL. - * len - dword_len is always dumped. + * addr - addr is dumped only if name is NULL. + * len - len is always dumped. * width - bit_width is dumped if it's not zero. * packed - packed=1 is dumped if it's not false. * mem_group - mem_group is always dumped. @@ -2408,8 +2653,8 @@ static u32 qed_grc_dump_mem_hdr(struct qed_hwfn *p_hwfn, u32 *dump_buf, bool dump, const char *name, - u32 byte_addr, - u32 dword_len, + u32 addr, + u32 len, u32 bit_width, bool packed, const char *mem_group, @@ -2419,7 +2664,7 @@ static u32 qed_grc_dump_mem_hdr(struct qed_hwfn *p_hwfn, u32 offset = 0; char buf[64]; - if (!dword_len) + if (!len) DP_NOTICE(p_hwfn, "Unexpected GRC Dump error: dumped memory size must be non-zero\n"); if (bit_width) @@ -2446,20 +2691,21 @@ static u32 qed_grc_dump_mem_hdr(struct qed_hwfn *p_hwfn, DP_VERBOSE(p_hwfn, QED_MSG_DEBUG, "Dumping %d registers from %s...\n", - dword_len, buf); + len, buf); } else { /* Dump address */ offset += qed_dump_num_param(dump_buf + offset, - dump, "addr", byte_addr); - if (dump && dword_len > 64) + dump, "addr", + DWORDS_TO_BYTES(addr)); + if (dump && len > 64) DP_VERBOSE(p_hwfn, QED_MSG_DEBUG, "Dumping %d registers from address 0x%x...\n", - dword_len, byte_addr); + len, (u32)DWORDS_TO_BYTES(addr)); } /* Dump len */ - offset += qed_dump_num_param(dump_buf + offset, dump, "len", dword_len); + offset += qed_dump_num_param(dump_buf + offset, dump, "len", len); /* Dump bit width */ if (bit_width) @@ -2492,8 +2738,8 @@ static u32 qed_grc_dump_mem(struct qed_hwfn *p_hwfn, u32 *dump_buf, bool dump, const char *name, - u32 byte_addr, - u32 dword_len, + u32 addr, + u32 len, u32 bit_width, bool packed, const char *mem_group, @@ -2505,21 +2751,14 @@ static u32 qed_grc_dump_mem(struct qed_hwfn *p_hwfn, dump_buf + offset, dump, name, - byte_addr, - dword_len, + addr, + len, bit_width, packed, mem_group, is_storm, storm_letter); - if (dump) { - u32 i; - - for (i = 0; i < dword_len; - i++, byte_addr += BYTES_IN_DWORD, offset++) - *(dump_buf + offset) = qed_rd(p_hwfn, p_ptt, byte_addr); - } else { - offset += dword_len; - } - + offset += qed_grc_dump_addr_range(p_hwfn, + p_ptt, + dump_buf + offset, dump, addr, len); return offset; } @@ -2575,25 +2814,41 @@ static u32 qed_grc_dump_mem_entries(struct qed_hwfn *p_hwfn, if (qed_grc_is_mem_included(p_hwfn, (enum block_id)cond_hdr->block_id, mem_group_id)) { - u32 mem_byte_addr = - DWORDS_TO_BYTES(GET_FIELD(mem->dword0, - DBG_DUMP_MEM_ADDRESS)); + u32 mem_addr = GET_FIELD(mem->dword0, + DBG_DUMP_MEM_ADDRESS); u32 mem_len = GET_FIELD(mem->dword1, DBG_DUMP_MEM_LENGTH); + enum dbg_grc_params grc_param; char storm_letter = 'a'; bool is_storm = false; /* Update memory length for CCFC/TCFC memories * according to number of LCIDs/LTIDs. */ - if (mem_group_id == MEM_GROUP_CONN_CFC_MEM) + if (mem_group_id == MEM_GROUP_CONN_CFC_MEM) { + if (mem_len % MAX_LCIDS != 0) { + DP_NOTICE(p_hwfn, + "Invalid CCFC connection memory size\n"); + return 0; + } + + grc_param = DBG_GRC_PARAM_NUM_LCIDS; mem_len = qed_grc_get_param(p_hwfn, - DBG_GRC_PARAM_NUM_LCIDS) - * (mem_len / MAX_LCIDS); - else if (mem_group_id == MEM_GROUP_TASK_CFC_MEM) + grc_param) * + (mem_len / MAX_LCIDS); + } else if (mem_group_id == + MEM_GROUP_TASK_CFC_MEM) { + if (mem_len % MAX_LTIDS != 0) { + DP_NOTICE(p_hwfn, + "Invalid TCFC task memory size\n"); + return 0; + } + + grc_param = DBG_GRC_PARAM_NUM_LTIDS; mem_len = qed_grc_get_param(p_hwfn, - DBG_GRC_PARAM_NUM_LTIDS) - * (mem_len / MAX_LTIDS); + grc_param) * + (mem_len / MAX_LTIDS); + } /* If memory is associated with Storm, update * Storm details. @@ -2610,7 +2865,7 @@ static u32 qed_grc_dump_mem_entries(struct qed_hwfn *p_hwfn, /* Dump memory */ offset += qed_grc_dump_mem(p_hwfn, p_ptt, dump_buf + offset, dump, NULL, - mem_byte_addr, mem_len, 0, + mem_addr, mem_len, 0, false, s_mem_group_names[mem_group_id], is_storm, storm_letter); @@ -2799,29 +3054,31 @@ static u32 qed_grc_dump_iors(struct qed_hwfn *p_hwfn, u32 offset = 0; for (storm_id = 0; storm_id < MAX_DBG_STORMS; storm_id++) { - if (qed_grc_is_storm_included(p_hwfn, - (enum dbg_storms)storm_id)) { - for (set_id = 0; set_id < NUM_IOR_SETS; set_id++) { - u32 addr = - s_storm_defs[storm_id].sem_fast_mem_addr + - SEM_FAST_REG_STORM_REG_FILE + - DWORDS_TO_BYTES(IOR_SET_OFFSET(set_id)); + struct storm_defs *storm = &s_storm_defs[storm_id]; - buf[strlen(buf) - 1] = '0' + set_id; - offset += qed_grc_dump_mem(p_hwfn, - p_ptt, - dump_buf + offset, - dump, - buf, - addr, - IORS_PER_SET, - 32, - false, - "ior", - true, - s_storm_defs - [storm_id].letter); - } + if (!qed_grc_is_storm_included(p_hwfn, + (enum dbg_storms)storm_id)) + continue; + + for (set_id = 0; set_id < NUM_IOR_SETS; set_id++) { + u32 dwords, addr; + + dwords = storm->sem_fast_mem_addr + + SEM_FAST_REG_STORM_REG_FILE; + addr = BYTES_TO_DWORDS(dwords) + IOR_SET_OFFSET(set_id); + buf[strlen(buf) - 1] = '0' + set_id; + offset += qed_grc_dump_mem(p_hwfn, + p_ptt, + dump_buf + offset, + dump, + buf, + addr, + IORS_PER_SET, + 32, + false, + "ior", + true, + storm->letter); } } @@ -2990,34 +3247,39 @@ static u32 qed_grc_dump_rss(struct qed_hwfn *p_hwfn, struct rss_mem_defs *rss_defs = &s_rss_mem_defs[rss_mem_id]; u32 num_entries = rss_defs->num_entries[dev_data->chip_id]; u32 entry_width = rss_defs->entry_width[dev_data->chip_id]; - u32 total_size = (num_entries * entry_width) / 32; + u32 total_dwords = (num_entries * entry_width) / 32; + u32 size = RSS_REG_RSS_RAM_DATA_SIZE; bool packed = (entry_width == 16); - u32 addr = rss_defs->addr; - u32 i, j; + u32 rss_addr = rss_defs->addr; + u32 i, addr; offset += qed_grc_dump_mem_hdr(p_hwfn, dump_buf + offset, dump, rss_defs->mem_name, - addr, - total_size, + 0, + total_dwords, entry_width, packed, rss_defs->type_name, false, 0); if (!dump) { - offset += total_size; + offset += total_dwords; continue; } /* Dump RSS data */ - for (i = 0; i < BYTES_TO_DWORDS(total_size); i++, addr++) { - qed_wr(p_hwfn, p_ptt, RSS_REG_RSS_RAM_ADDR, addr); - for (j = 0; j < BYTES_IN_DWORD; j++, offset++) - *(dump_buf + offset) = - qed_rd(p_hwfn, p_ptt, - RSS_REG_RSS_RAM_DATA + - DWORDS_TO_BYTES(j)); + for (i = 0; i < total_dwords; + i += RSS_REG_RSS_RAM_DATA_SIZE, rss_addr++) { + addr = BYTES_TO_DWORDS(RSS_REG_RSS_RAM_DATA); + qed_wr(p_hwfn, p_ptt, RSS_REG_RSS_RAM_ADDR, rss_addr); + offset += qed_grc_dump_addr_range(p_hwfn, + p_ptt, + dump_buf + + offset, + dump, + addr, + size); } } @@ -3030,19 +3292,19 @@ static u32 qed_grc_dump_big_ram(struct qed_hwfn *p_hwfn, u32 *dump_buf, bool dump, u8 big_ram_id) { struct dbg_tools_data *dev_data = &p_hwfn->dbg_info; + u32 total_blocks, ram_size, offset = 0, i; char mem_name[12] = "???_BIG_RAM"; char type_name[8] = "???_RAM"; - u32 ram_size, total_blocks; - u32 offset = 0, i, j; + struct big_ram_defs *big_ram; - total_blocks = - s_big_ram_defs[big_ram_id].num_of_blocks[dev_data->chip_id]; + big_ram = &s_big_ram_defs[big_ram_id]; + total_blocks = big_ram->num_of_blocks[dev_data->chip_id]; ram_size = total_blocks * BIG_RAM_BLOCK_SIZE_DWORDS; - strncpy(type_name, s_big_ram_defs[big_ram_id].instance_name, - strlen(s_big_ram_defs[big_ram_id].instance_name)); - strncpy(mem_name, s_big_ram_defs[big_ram_id].instance_name, - strlen(s_big_ram_defs[big_ram_id].instance_name)); + strncpy(type_name, big_ram->instance_name, + strlen(big_ram->instance_name)); + strncpy(mem_name, big_ram->instance_name, + strlen(big_ram->instance_name)); /* Dump memory header */ offset += qed_grc_dump_mem_hdr(p_hwfn, @@ -3059,13 +3321,17 @@ static u32 qed_grc_dump_big_ram(struct qed_hwfn *p_hwfn, /* Read and dump Big RAM data */ for (i = 0; i < total_blocks / 2; i++) { - qed_wr(p_hwfn, p_ptt, s_big_ram_defs[big_ram_id].addr_reg_addr, - i); - for (j = 0; j < 2 * BIG_RAM_BLOCK_SIZE_DWORDS; j++, offset++) - *(dump_buf + offset) = qed_rd(p_hwfn, p_ptt, - s_big_ram_defs[big_ram_id]. - data_reg_addr + - DWORDS_TO_BYTES(j)); + u32 addr, len; + + qed_wr(p_hwfn, p_ptt, big_ram->addr_reg_addr, i); + addr = BYTES_TO_DWORDS(big_ram->data_reg_addr); + len = 2 * BIG_RAM_BLOCK_SIZE_DWORDS; + offset += qed_grc_dump_addr_range(p_hwfn, + p_ptt, + dump_buf + offset, + dump, + addr, + len); } return offset; @@ -3075,11 +3341,11 @@ static u32 qed_grc_dump_mcp(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, u32 *dump_buf, bool dump) { bool block_enable[MAX_BLOCK_ID] = { 0 }; + u32 offset = 0, addr; bool halted = false; - u32 offset = 0; /* Halt MCP */ - if (dump) { + if (dump && !qed_grc_get_param(p_hwfn, DBG_GRC_PARAM_NO_MCP)) { halted = !qed_mcp_halt(p_hwfn, p_ptt); if (!halted) DP_NOTICE(p_hwfn, "MCP halt failed!\n"); @@ -3091,7 +3357,7 @@ static u32 qed_grc_dump_mcp(struct qed_hwfn *p_hwfn, dump_buf + offset, dump, NULL, - MCP_REG_SCRATCH, + BYTES_TO_DWORDS(MCP_REG_SCRATCH), MCP_REG_SCRATCH_SIZE, 0, false, "MCP", false, 0); @@ -3101,7 +3367,7 @@ static u32 qed_grc_dump_mcp(struct qed_hwfn *p_hwfn, dump_buf + offset, dump, NULL, - MCP_REG_CPU_REG_FILE, + BYTES_TO_DWORDS(MCP_REG_CPU_REG_FILE), MCP_REG_CPU_REG_FILE_SIZE, 0, false, "MCP", false, 0); @@ -3115,12 +3381,13 @@ static u32 qed_grc_dump_mcp(struct qed_hwfn *p_hwfn, /* Dump required non-MCP registers */ offset += qed_grc_dump_regs_hdr(dump_buf + offset, dump, 1, "eng", -1, "block", "MCP"); + addr = BYTES_TO_DWORDS(MISC_REG_SHARED_MEM_ADDR); offset += qed_grc_dump_reg_entry(p_hwfn, p_ptt, dump_buf + offset, dump, - BYTES_TO_DWORDS - (MISC_REG_SHARED_MEM_ADDR), 1); + addr, + 1); /* Release MCP */ if (halted && qed_mcp_resume(p_hwfn, p_ptt)) @@ -3212,7 +3479,7 @@ static u32 qed_grc_dump_static_debug(struct qed_hwfn *p_hwfn, { u32 block_dwords = NUM_DBG_BUS_LINES * STATIC_DEBUG_LINE_DWORDS; struct dbg_tools_data *dev_data = &p_hwfn->dbg_info; - u32 offset = 0, block_id, line_id, addr, i; + u32 offset = 0, block_id, line_id; struct block_defs *p_block_defs; if (dump) { @@ -3255,6 +3522,8 @@ static u32 qed_grc_dump_static_debug(struct qed_hwfn *p_hwfn, if (dump && !dev_data->block_in_reset[block_id]) { u8 dbg_client_id = p_block_defs->dbg_client_id[dev_data->chip_id]; + u32 addr = BYTES_TO_DWORDS(DBG_REG_CALENDAR_OUT_DATA); + u32 len = STATIC_DEBUG_LINE_DWORDS; /* Enable block's client */ qed_bus_enable_clients(p_hwfn, p_ptt, @@ -3270,11 +3539,13 @@ static u32 qed_grc_dump_static_debug(struct qed_hwfn *p_hwfn, 0xf, 0, 0, 0); /* Read debug line info */ - for (i = 0, addr = DBG_REG_CALENDAR_OUT_DATA; - i < STATIC_DEBUG_LINE_DWORDS; - i++, offset++, addr += BYTES_IN_DWORD) - dump_buf[offset] = qed_rd(p_hwfn, p_ptt, - addr); + offset += + qed_grc_dump_addr_range(p_hwfn, + p_ptt, + dump_buf + offset, + dump, + addr, + len); } /* Disable block's client and debug output */ @@ -3311,14 +3582,8 @@ static enum dbg_status qed_grc_dump(struct qed_hwfn *p_hwfn, u8 i, port_mode = 0; u32 offset = 0; - /* Check if emulation platform */ *num_dumped_dwords = 0; - /* Fill GRC parameters that were not set by the user with their default - * value. - */ - qed_dbg_grc_set_params_default(p_hwfn); - /* Find port mode */ if (dump) { switch (qed_rd(p_hwfn, p_ptt, MISC_REG_PORT_MODE)) { @@ -3370,15 +3635,14 @@ static enum dbg_status qed_grc_dump(struct qed_hwfn *p_hwfn, } /* Disable all parities using MFW command */ - if (dump) { + if (dump && !qed_grc_get_param(p_hwfn, DBG_GRC_PARAM_NO_MCP)) { parities_masked = !qed_mcp_mask_parities(p_hwfn, p_ptt, 1); if (!parities_masked) { + DP_NOTICE(p_hwfn, + "Failed to mask parities using MFW\n"); if (qed_grc_get_param (p_hwfn, DBG_GRC_PARAM_PARITY_SAFE)) return DBG_STATUS_MCP_COULD_NOT_MASK_PRTY; - else - DP_NOTICE(p_hwfn, - "Failed to mask parities using MFW\n"); } } @@ -3409,6 +3673,11 @@ static enum dbg_status qed_grc_dump(struct qed_hwfn *p_hwfn, offset, dump, block_enable, NULL, NULL); + + /* Dump special registers */ + offset += qed_grc_dump_special_regs(p_hwfn, + p_ptt, + dump_buf + offset, dump); } /* Dump memories */ @@ -3583,9 +3852,9 @@ static u32 qed_idle_chk_dump_failure(struct qed_hwfn *p_hwfn, } if (mode_match) { - u32 grc_addr = - DWORDS_TO_BYTES(GET_FIELD(reg->data, - DBG_IDLE_CHK_INFO_REG_ADDRESS)); + u32 addr = + GET_FIELD(reg->data, + DBG_IDLE_CHK_INFO_REG_ADDRESS); /* Write register header */ struct dbg_idle_chk_result_reg_hdr *reg_hdr = @@ -3597,16 +3866,19 @@ static u32 qed_idle_chk_dump_failure(struct qed_hwfn *p_hwfn, memset(reg_hdr, 0, sizeof(*reg_hdr)); reg_hdr->size = reg->size; SET_FIELD(reg_hdr->data, - DBG_IDLE_CHK_RESULT_REG_HDR_REG_ID, - rule->num_cond_regs + reg_id); + DBG_IDLE_CHK_RESULT_REG_HDR_REG_ID, + rule->num_cond_regs + reg_id); /* Write register values */ - for (i = 0; i < reg->size; - i++, offset++, grc_addr += 4) - dump_buf[offset] = - qed_rd(p_hwfn, p_ptt, grc_addr); - } + offset += + qed_grc_dump_addr_range(p_hwfn, + p_ptt, + dump_buf + offset, + dump, + addr, + reg->size); } + } } return offset; @@ -3621,7 +3893,7 @@ qed_idle_chk_dump_rule_entries(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, { struct dbg_tools_data *dev_data = &p_hwfn->dbg_info; u32 cond_reg_values[IDLE_CHK_MAX_ENTRIES_SIZE]; - u32 i, j, offset = 0; + u32 i, offset = 0; u16 entry_id; u8 reg_id; @@ -3664,73 +3936,83 @@ qed_idle_chk_dump_rule_entries(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, if (!check_rule && dump) continue; + if (!dump) { + u32 entry_dump_size = + qed_idle_chk_dump_failure(p_hwfn, + p_ptt, + dump_buf + offset, + false, + rule->rule_id, + rule, + 0, + NULL); + + offset += num_reg_entries * entry_dump_size; + (*num_failing_rules) += num_reg_entries; + continue; + } + /* Go over all register entries (number of entries is the same * for all condition registers). */ for (entry_id = 0; entry_id < num_reg_entries; entry_id++) { /* Read current entry of all condition registers */ - if (dump) { - u32 next_reg_offset = 0; - - for (reg_id = 0; - reg_id < rule->num_cond_regs; - reg_id++) { - const struct dbg_idle_chk_cond_reg - *reg = &cond_regs[reg_id]; - - /* Find GRC address (if it's a memory, - * the address of the specific entry is - * calculated). - */ - u32 grc_addr = - DWORDS_TO_BYTES( - GET_FIELD(reg->data, - DBG_IDLE_CHK_COND_REG_ADDRESS)); - - if (reg->num_entries > 1 || - reg->start_entry > 0) { - u32 padded_entry_size = - reg->entry_size > 1 ? - roundup_pow_of_two - (reg->entry_size) : 1; - - grc_addr += - DWORDS_TO_BYTES( - (reg->start_entry + - entry_id) - * padded_entry_size); - } + u32 next_reg_offset = 0; - /* Read registers */ - if (next_reg_offset + reg->entry_size >= - IDLE_CHK_MAX_ENTRIES_SIZE) { - DP_NOTICE(p_hwfn, - "idle check registers entry is too large\n"); - return 0; - } + for (reg_id = 0; reg_id < rule->num_cond_regs; + reg_id++) { + const struct dbg_idle_chk_cond_reg *reg = + &cond_regs[reg_id]; - for (j = 0; j < reg->entry_size; - j++, next_reg_offset++, - grc_addr += 4) - cond_reg_values[next_reg_offset] = - qed_rd(p_hwfn, p_ptt, grc_addr); + /* Find GRC address (if it's a memory,the + * address of the specific entry is calculated). + */ + u32 addr = + GET_FIELD(reg->data, + DBG_IDLE_CHK_COND_REG_ADDRESS); + + if (reg->num_entries > 1 || + reg->start_entry > 0) { + u32 padded_entry_size = + reg->entry_size > 1 ? + roundup_pow_of_two(reg->entry_size) : + 1; + + addr += (reg->start_entry + entry_id) * + padded_entry_size; } + + /* Read registers */ + if (next_reg_offset + reg->entry_size >= + IDLE_CHK_MAX_ENTRIES_SIZE) { + DP_NOTICE(p_hwfn, + "idle check registers entry is too large\n"); + return 0; + } + + next_reg_offset += + qed_grc_dump_addr_range(p_hwfn, + p_ptt, + cond_reg_values + + next_reg_offset, + dump, addr, + reg->entry_size); } /* Call rule's condition function - a return value of * true indicates failure. */ if ((*cond_arr[rule->cond_id])(cond_reg_values, - imm_values) || !dump) { + imm_values)) { offset += - qed_idle_chk_dump_failure(p_hwfn, - p_ptt, - dump_buf + offset, - dump, - rule->rule_id, - rule, - entry_id, - cond_reg_values); + qed_idle_chk_dump_failure(p_hwfn, + p_ptt, + dump_buf + offset, + dump, + rule->rule_id, + rule, + entry_id, + cond_reg_values); (*num_failing_rules)++; break; } @@ -3818,13 +4100,18 @@ static enum dbg_status qed_find_nvram_image(struct qed_hwfn *p_hwfn, struct mcp_file_att file_att; /* Call NVRAM get file command */ - if (qed_mcp_nvm_rd_cmd(p_hwfn, p_ptt, DRV_MSG_CODE_NVM_GET_FILE_ATT, - image_type, &ret_mcp_resp, &ret_mcp_param, - &ret_txn_size, (u32 *)&file_att) != 0) - return DBG_STATUS_NVRAM_GET_IMAGE_FAILED; + int nvm_result = qed_mcp_nvm_rd_cmd(p_hwfn, + p_ptt, + DRV_MSG_CODE_NVM_GET_FILE_ATT, + image_type, + &ret_mcp_resp, + &ret_mcp_param, + &ret_txn_size, + (u32 *)&file_att); /* Check response */ - if ((ret_mcp_resp & FW_MSG_CODE_MASK) != FW_MSG_CODE_NVM_OK) + if (nvm_result || + (ret_mcp_resp & FW_MSG_CODE_MASK) != FW_MSG_CODE_NVM_OK) return DBG_STATUS_NVRAM_GET_IMAGE_FAILED; /* Update return values */ @@ -3944,7 +4231,6 @@ static enum dbg_status qed_mcp_trace_get_meta_info(struct qed_hwfn *p_hwfn, u32 running_mfw_addr = MCP_REG_SCRATCH + SECTION_OFFSET(spad_trace_offsize) + QED_SECTION_SIZE(spad_trace_offsize) + trace_data_size_bytes; - enum dbg_status status; u32 nvram_image_type; *running_bundle_id = qed_rd(p_hwfn, p_ptt, running_mfw_addr); @@ -3955,30 +4241,12 @@ static enum dbg_status qed_mcp_trace_get_meta_info(struct qed_hwfn *p_hwfn, nvram_image_type = (*running_bundle_id == DIR_ID_1) ? NVM_TYPE_MFW_TRACE1 : NVM_TYPE_MFW_TRACE2; - status = qed_find_nvram_image(p_hwfn, - p_ptt, - nvram_image_type, - trace_meta_offset_bytes, - trace_meta_size_bytes); - - return status; -} - -/* Reads the MCP Trace data from the specified GRC address into the specified - * buffer. - */ -static void qed_mcp_trace_read_data(struct qed_hwfn *p_hwfn, - struct qed_ptt *p_ptt, - u32 grc_addr, u32 size_in_dwords, u32 *buf) -{ - u32 i; - DP_VERBOSE(p_hwfn, - QED_MSG_DEBUG, - "mcp_trace_read_data: reading trace data of size %d dwords from GRC address 0x%x\n", - size_in_dwords, grc_addr); - for (i = 0; i < size_in_dwords; i++, grc_addr += BYTES_IN_DWORD) - buf[i] = qed_rd(p_hwfn, p_ptt, grc_addr); + return qed_find_nvram_image(p_hwfn, + p_ptt, + nvram_image_type, + trace_meta_offset_bytes, + trace_meta_size_bytes); } /* Reads the MCP Trace meta data (from NVRAM or buffer) into the specified @@ -4034,11 +4302,14 @@ static enum dbg_status qed_mcp_trace_dump(struct qed_hwfn *p_hwfn, bool dump, u32 *num_dumped_dwords) { u32 trace_data_grc_addr, trace_data_size_bytes, trace_data_size_dwords; - u32 trace_meta_size_dwords, running_bundle_id, offset = 0; - u32 trace_meta_offset_bytes, trace_meta_size_bytes; + u32 trace_meta_size_dwords = 0, running_bundle_id, offset = 0; + u32 trace_meta_offset_bytes = 0, trace_meta_size_bytes = 0; enum dbg_status status; + bool mcp_access; int halted = 0; + mcp_access = !qed_grc_get_param(p_hwfn, DBG_GRC_PARAM_NO_MCP); + *num_dumped_dwords = 0; /* Get trace data info */ @@ -4060,7 +4331,7 @@ static enum dbg_status qed_mcp_trace_dump(struct qed_hwfn *p_hwfn, * consistent if halt fails, MCP trace is taken anyway, with a small * risk that it may be corrupt. */ - if (dump) { + if (dump && mcp_access) { halted = !qed_mcp_halt(p_hwfn, p_ptt); if (!halted) DP_NOTICE(p_hwfn, "MCP halt failed!\n"); @@ -4078,13 +4349,12 @@ static enum dbg_status qed_mcp_trace_dump(struct qed_hwfn *p_hwfn, dump, "size", trace_data_size_dwords); /* Read trace data from scratchpad into dump buffer */ - if (dump) - qed_mcp_trace_read_data(p_hwfn, - p_ptt, - trace_data_grc_addr, - trace_data_size_dwords, - dump_buf + offset); - offset += trace_data_size_dwords; + offset += qed_grc_dump_addr_range(p_hwfn, + p_ptt, + dump_buf + offset, + dump, + BYTES_TO_DWORDS(trace_data_grc_addr), + trace_data_size_dwords); /* Resume MCP (only if halt succeeded) */ if (halted && qed_mcp_resume(p_hwfn, p_ptt) != 0) @@ -4095,38 +4365,38 @@ static enum dbg_status qed_mcp_trace_dump(struct qed_hwfn *p_hwfn, dump, "mcp_trace_meta", 1); /* Read trace meta info */ - status = qed_mcp_trace_get_meta_info(p_hwfn, - p_ptt, - trace_data_size_bytes, - &running_bundle_id, - &trace_meta_offset_bytes, - &trace_meta_size_bytes); - if (status != DBG_STATUS_OK) - return status; + if (mcp_access) { + status = qed_mcp_trace_get_meta_info(p_hwfn, + p_ptt, + trace_data_size_bytes, + &running_bundle_id, + &trace_meta_offset_bytes, + &trace_meta_size_bytes); + if (status == DBG_STATUS_OK) + trace_meta_size_dwords = + BYTES_TO_DWORDS(trace_meta_size_bytes); + } - /* Dump trace meta size param (trace_meta_size_bytes is always - * dword-aligned). - */ - trace_meta_size_dwords = BYTES_TO_DWORDS(trace_meta_size_bytes); - offset += qed_dump_num_param(dump_buf + offset, dump, "size", - trace_meta_size_dwords); + /* Dump trace meta size param */ + offset += qed_dump_num_param(dump_buf + offset, + dump, "size", trace_meta_size_dwords); /* Read trace meta image into dump buffer */ - if (dump) { + if (dump && trace_meta_size_dwords) status = qed_mcp_trace_read_meta(p_hwfn, - p_ptt, - trace_meta_offset_bytes, - trace_meta_size_bytes, - dump_buf + offset); - if (status != DBG_STATUS_OK) - return status; - } - - offset += trace_meta_size_dwords; + p_ptt, + trace_meta_offset_bytes, + trace_meta_size_bytes, + dump_buf + offset); + if (status == DBG_STATUS_OK) + offset += trace_meta_size_dwords; *num_dumped_dwords = offset; - return DBG_STATUS_OK; + /* If no mcp access, indicate that the dump doesn't contain the meta + * data from NVRAM. + */ + return mcp_access ? status : DBG_STATUS_NVRAM_GET_IMAGE_FAILED; } /* Dump GRC FIFO */ @@ -4311,9 +4581,10 @@ static u32 qed_fw_asserts_dump(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, u32 *dump_buf, bool dump) { struct dbg_tools_data *dev_data = &p_hwfn->dbg_info; + struct fw_asserts_ram_section *asserts; char storm_letter_str[2] = "?"; struct fw_info fw_info; - u32 offset = 0, i; + u32 offset = 0; u8 storm_id; /* Dump global params */ @@ -4323,8 +4594,8 @@ static u32 qed_fw_asserts_dump(struct qed_hwfn *p_hwfn, offset += qed_dump_str_param(dump_buf + offset, dump, "dump-type", "fw-asserts"); for (storm_id = 0; storm_id < MAX_DBG_STORMS; storm_id++) { - u32 fw_asserts_section_addr, next_list_idx_addr, next_list_idx, - last_list_idx, element_addr; + u32 fw_asserts_section_addr, next_list_idx_addr, next_list_idx; + u32 last_list_idx, addr; if (dev_data->block_in_reset[s_storm_defs[storm_id].block_id]) continue; @@ -4332,6 +4603,8 @@ static u32 qed_fw_asserts_dump(struct qed_hwfn *p_hwfn, /* Read FW info for the current Storm */ qed_read_fw_info(p_hwfn, p_ptt, storm_id, &fw_info); + asserts = &fw_info.fw_asserts_section; + /* Dump FW Asserts section header and params */ storm_letter_str[0] = s_storm_defs[storm_id].letter; offset += qed_dump_section_hdr(dump_buf + offset, dump, @@ -4339,12 +4612,10 @@ static u32 qed_fw_asserts_dump(struct qed_hwfn *p_hwfn, offset += qed_dump_str_param(dump_buf + offset, dump, "storm", storm_letter_str); offset += qed_dump_num_param(dump_buf + offset, dump, "size", - fw_info.fw_asserts_section. - list_element_dword_size); + asserts->list_element_dword_size); if (!dump) { - offset += fw_info.fw_asserts_section. - list_element_dword_size; + offset += asserts->list_element_dword_size; continue; } @@ -4352,28 +4623,22 @@ static u32 qed_fw_asserts_dump(struct qed_hwfn *p_hwfn, fw_asserts_section_addr = s_storm_defs[storm_id].sem_fast_mem_addr + SEM_FAST_REG_INT_RAM + - RAM_LINES_TO_BYTES(fw_info.fw_asserts_section. - section_ram_line_offset); + RAM_LINES_TO_BYTES(asserts->section_ram_line_offset); next_list_idx_addr = fw_asserts_section_addr + - DWORDS_TO_BYTES(fw_info.fw_asserts_section. - list_next_index_dword_offset); + DWORDS_TO_BYTES(asserts->list_next_index_dword_offset); next_list_idx = qed_rd(p_hwfn, p_ptt, next_list_idx_addr); last_list_idx = (next_list_idx > 0 ? next_list_idx - : fw_info.fw_asserts_section.list_num_elements) - - 1; - element_addr = - fw_asserts_section_addr + - DWORDS_TO_BYTES(fw_info.fw_asserts_section. - list_dword_offset) + - last_list_idx * - DWORDS_TO_BYTES(fw_info.fw_asserts_section. - list_element_dword_size); - for (i = 0; - i < fw_info.fw_asserts_section.list_element_dword_size; - i++, offset++, element_addr += BYTES_IN_DWORD) - dump_buf[offset] = qed_rd(p_hwfn, p_ptt, element_addr); + : asserts->list_num_elements) - 1; + addr = BYTES_TO_DWORDS(fw_asserts_section_addr) + + asserts->list_dword_offset + + last_list_idx * asserts->list_element_dword_size; + offset += + qed_grc_dump_addr_range(p_hwfn, p_ptt, + dump_buf + offset, + dump, addr, + asserts->list_element_dword_size); } /* Dump last section */ @@ -4386,13 +4651,10 @@ static u32 qed_fw_asserts_dump(struct qed_hwfn *p_hwfn, enum dbg_status qed_dbg_set_bin_ptr(const u8 * const bin_ptr) { /* Convert binary data to debug arrays */ - u32 num_of_buffers = *(u32 *)bin_ptr; - struct bin_buffer_hdr *buf_array; + struct bin_buffer_hdr *buf_array = (struct bin_buffer_hdr *)bin_ptr; u8 buf_id; - buf_array = (struct bin_buffer_hdr *)((u32 *)bin_ptr + 1); - - for (buf_id = 0; buf_id < num_of_buffers; buf_id++) { + for (buf_id = 0; buf_id < MAX_BIN_DBG_BUFFER_TYPE; buf_id++) { s_dbg_arrays[buf_id].ptr = (u32 *)(bin_ptr + buf_array[buf_id].offset); s_dbg_arrays[buf_id].size_in_dwords = @@ -4402,6 +4664,17 @@ enum dbg_status qed_dbg_set_bin_ptr(const u8 * const bin_ptr) return DBG_STATUS_OK; } +/* Assign default GRC param values */ +void qed_dbg_grc_set_params_default(struct qed_hwfn *p_hwfn) +{ + struct dbg_tools_data *dev_data = &p_hwfn->dbg_info; + u32 i; + + for (i = 0; i < MAX_DBG_GRC_PARAMS; i++) + dev_data->grc.param_val[i] = + s_grc_param_defs[i].default_val[dev_data->chip_id]; +} + enum dbg_status qed_dbg_grc_get_dump_buf_size(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, u32 *buf_size) @@ -4441,8 +4714,9 @@ enum dbg_status qed_dbg_grc_dump(struct qed_hwfn *p_hwfn, /* GRC Dump */ status = qed_grc_dump(p_hwfn, p_ptt, dump_buf, true, num_dumped_dwords); - /* Clear all GRC params */ - qed_dbg_grc_clear_params(p_hwfn); + /* Revert GRC params to their default */ + qed_dbg_grc_set_params_default(p_hwfn); + return status; } @@ -4495,6 +4769,10 @@ enum dbg_status qed_dbg_idle_chk_dump(struct qed_hwfn *p_hwfn, /* Idle Check Dump */ *num_dumped_dwords = qed_idle_chk_dump(p_hwfn, p_ptt, dump_buf, true); + + /* Revert GRC params to their default */ + qed_dbg_grc_set_params_default(p_hwfn); + return DBG_STATUS_OK; } @@ -4519,11 +4797,15 @@ enum dbg_status qed_dbg_mcp_trace_dump(struct qed_hwfn *p_hwfn, u32 needed_buf_size_in_dwords; enum dbg_status status; - status = qed_dbg_mcp_trace_get_dump_buf_size(p_hwfn, p_ptt, + /* validate buffer size */ + status = + qed_dbg_mcp_trace_get_dump_buf_size(p_hwfn, p_ptt, &needed_buf_size_in_dwords); - if (status != DBG_STATUS_OK) + if (status != DBG_STATUS_OK && + status != DBG_STATUS_NVRAM_GET_IMAGE_FAILED) return status; + if (buf_size_in_dwords < needed_buf_size_in_dwords) return DBG_STATUS_DUMP_BUF_TOO_SMALL; @@ -4531,8 +4813,13 @@ enum dbg_status qed_dbg_mcp_trace_dump(struct qed_hwfn *p_hwfn, qed_update_blocks_reset_state(p_hwfn, p_ptt); /* Perform dump */ - return qed_mcp_trace_dump(p_hwfn, - p_ptt, dump_buf, true, num_dumped_dwords); + status = qed_mcp_trace_dump(p_hwfn, + p_ptt, dump_buf, true, num_dumped_dwords); + + /* Revert GRC params to their default */ + qed_dbg_grc_set_params_default(p_hwfn); + + return status; } enum dbg_status qed_dbg_reg_fifo_get_dump_buf_size(struct qed_hwfn *p_hwfn, @@ -4567,8 +4854,14 @@ enum dbg_status qed_dbg_reg_fifo_dump(struct qed_hwfn *p_hwfn, /* Update reset state */ qed_update_blocks_reset_state(p_hwfn, p_ptt); - return qed_reg_fifo_dump(p_hwfn, - p_ptt, dump_buf, true, num_dumped_dwords); + + status = qed_reg_fifo_dump(p_hwfn, + p_ptt, dump_buf, true, num_dumped_dwords); + + /* Revert GRC params to their default */ + qed_dbg_grc_set_params_default(p_hwfn); + + return status; } enum dbg_status qed_dbg_igu_fifo_get_dump_buf_size(struct qed_hwfn *p_hwfn, @@ -4603,8 +4896,13 @@ enum dbg_status qed_dbg_igu_fifo_dump(struct qed_hwfn *p_hwfn, /* Update reset state */ qed_update_blocks_reset_state(p_hwfn, p_ptt); - return qed_igu_fifo_dump(p_hwfn, - p_ptt, dump_buf, true, num_dumped_dwords); + + status = qed_igu_fifo_dump(p_hwfn, + p_ptt, dump_buf, true, num_dumped_dwords); + /* Revert GRC params to their default */ + qed_dbg_grc_set_params_default(p_hwfn); + + return status; } enum dbg_status @@ -4641,9 +4939,16 @@ enum dbg_status qed_dbg_protection_override_dump(struct qed_hwfn *p_hwfn, /* Update reset state */ qed_update_blocks_reset_state(p_hwfn, p_ptt); - return qed_protection_override_dump(p_hwfn, - p_ptt, - dump_buf, true, num_dumped_dwords); + + status = qed_protection_override_dump(p_hwfn, + p_ptt, + dump_buf, + true, num_dumped_dwords); + + /* Revert GRC params to their default */ + qed_dbg_grc_set_params_default(p_hwfn); + + return status; } enum dbg_status qed_dbg_fw_asserts_get_dump_buf_size(struct qed_hwfn *p_hwfn, @@ -5045,13 +5350,10 @@ static char s_temp_buf[MAX_MSG_LEN]; enum dbg_status qed_dbg_user_set_bin_ptr(const u8 * const bin_ptr) { /* Convert binary data to debug arrays */ - u32 num_of_buffers = *(u32 *)bin_ptr; - struct bin_buffer_hdr *buf_array; + struct bin_buffer_hdr *buf_array = (struct bin_buffer_hdr *)bin_ptr; u8 buf_id; - buf_array = (struct bin_buffer_hdr *)((u32 *)bin_ptr + 1); - - for (buf_id = 0; buf_id < num_of_buffers; buf_id++) { + for (buf_id = 0; buf_id < MAX_BIN_DBG_BUFFER_TYPE; buf_id++) { s_dbg_arrays[buf_id].ptr = (u32 *)(bin_ptr + buf_array[buf_id].offset); s_dbg_arrays[buf_id].size_in_dwords = @@ -5874,16 +6176,16 @@ static enum dbg_status qed_parse_reg_fifo_dump(struct qed_hwfn *p_hwfn, results_offset += sprintf(qed_get_buf_ptr(results_buf, results_offset), - "raw: 0x%016llx, address: 0x%07llx, access: %-5s, pf: %2lld, vf: %s, port: %lld, privilege: %-3s, protection: %-12s, master: %-4s, errors: ", + "raw: 0x%016llx, address: 0x%07x, access: %-5s, pf: %2d, vf: %s, port: %d, privilege: %-3s, protection: %-12s, master: %-4s, errors: ", elements[i].data, - GET_FIELD(elements[i].data, + (u32)GET_FIELD(elements[i].data, REG_FIFO_ELEMENT_ADDRESS) * REG_FIFO_ELEMENT_ADDR_FACTOR, s_access_strs[GET_FIELD(elements[i].data, REG_FIFO_ELEMENT_ACCESS)], - GET_FIELD(elements[i].data, - REG_FIFO_ELEMENT_PF), vf_str, - GET_FIELD(elements[i].data, + (u32)GET_FIELD(elements[i].data, + REG_FIFO_ELEMENT_PF), vf_str, + (u32)GET_FIELD(elements[i].data, REG_FIFO_ELEMENT_PORT), s_privilege_strs[GET_FIELD(elements[i]. data, @@ -6189,13 +6491,13 @@ qed_parse_protection_override_dump(struct qed_hwfn *p_hwfn, results_offset += sprintf(qed_get_buf_ptr(results_buf, results_offset), - "window %2d, address: 0x%07x, size: %7lld regs, read: %lld, write: %lld, read protection: %-12s, write protection: %-12s\n", + "window %2d, address: 0x%07x, size: %7d regs, read: %d, write: %d, read protection: %-12s, write protection: %-12s\n", i, address, - GET_FIELD(elements[i].data, + (u32)GET_FIELD(elements[i].data, PROTECTION_OVERRIDE_ELEMENT_WINDOW_SIZE), - GET_FIELD(elements[i].data, + (u32)GET_FIELD(elements[i].data, PROTECTION_OVERRIDE_ELEMENT_READ), - GET_FIELD(elements[i].data, + (u32)GET_FIELD(elements[i].data, PROTECTION_OVERRIDE_ELEMENT_WRITE), s_protection_strs[GET_FIELD(elements[i].data, PROTECTION_OVERRIDE_ELEMENT_READ_PROTECTION)], @@ -6508,7 +6810,7 @@ static enum dbg_status qed_dbg_dump(struct qed_hwfn *p_hwfn, */ rc = qed_features_lookup[feature_idx].get_size(p_hwfn, p_ptt, &buf_size_dwords); - if (rc != DBG_STATUS_OK) + if (rc != DBG_STATUS_OK && rc != DBG_STATUS_NVRAM_GET_IMAGE_FAILED) return rc; feature->buf_size = buf_size_dwords * sizeof(u32); feature->dump_buf = vmalloc(feature->buf_size); diff --git a/drivers/net/ethernet/qlogic/qed/qed_dev.c b/drivers/net/ethernet/qlogic/qed/qed_dev.c index e2a081ceaf52..8b5df71aa3c1 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_dev.c +++ b/drivers/net/ethernet/qlogic/qed/qed_dev.c @@ -674,11 +674,19 @@ int qed_final_cleanup(struct qed_hwfn *p_hwfn, return rc; } -static void qed_calc_hw_mode(struct qed_hwfn *p_hwfn) +static int qed_calc_hw_mode(struct qed_hwfn *p_hwfn) { int hw_mode = 0; - hw_mode = (1 << MODE_BB_B0); + if (QED_IS_BB_B0(p_hwfn->cdev)) { + hw_mode |= 1 << MODE_BB; + } else if (QED_IS_AH(p_hwfn->cdev)) { + hw_mode |= 1 << MODE_K2; + } else { + DP_NOTICE(p_hwfn, "Unknown chip type %#x\n", + p_hwfn->cdev->type); + return -EINVAL; + } switch (p_hwfn->cdev->num_ports_in_engines) { case 1: @@ -693,7 +701,7 @@ static void qed_calc_hw_mode(struct qed_hwfn *p_hwfn) default: DP_NOTICE(p_hwfn, "num_ports_in_engine = %d not supported\n", p_hwfn->cdev->num_ports_in_engines); - return; + return -EINVAL; } switch (p_hwfn->cdev->mf_mode) { @@ -719,6 +727,8 @@ static void qed_calc_hw_mode(struct qed_hwfn *p_hwfn) DP_VERBOSE(p_hwfn, (NETIF_MSG_PROBE | NETIF_MSG_IFUP), "Configuring function for hw_mode: 0x%08x\n", p_hwfn->hw_info.hw_mode); + + return 0; } /* Init run time data for all PFs on an engine. */ @@ -754,10 +764,10 @@ static int qed_hw_init_common(struct qed_hwfn *p_hwfn, struct qed_qm_info *qm_info = &p_hwfn->qm_info; struct qed_qm_common_rt_init_params params; struct qed_dev *cdev = p_hwfn->cdev; + u8 vf_id, max_num_vfs; u16 num_pfs, pf_id; u32 concrete_fid; int rc = 0; - u8 vf_id; qed_init_cau_rt_data(cdev); @@ -814,7 +824,8 @@ static int qed_hw_init_common(struct qed_hwfn *p_hwfn, qed_fid_pretend(p_hwfn, p_ptt, p_hwfn->rel_pf_id); } - for (vf_id = 0; vf_id < MAX_NUM_VFS_BB; vf_id++) { + max_num_vfs = QED_IS_AH(cdev) ? MAX_NUM_VFS_K2 : MAX_NUM_VFS_BB; + for (vf_id = 0; vf_id < max_num_vfs; vf_id++) { concrete_fid = qed_vfid_to_concrete(p_hwfn, vf_id); qed_fid_pretend(p_hwfn, p_ptt, (u16) concrete_fid); qed_wr(p_hwfn, p_ptt, CCFC_REG_STRONG_ENABLE_VF, 0x1); @@ -1135,7 +1146,9 @@ int qed_hw_init(struct qed_dev *cdev, /* Enable DMAE in PXP */ rc = qed_change_pci_hwfn(p_hwfn, p_hwfn->p_main_ptt, true); - qed_calc_hw_mode(p_hwfn); + rc = qed_calc_hw_mode(p_hwfn); + if (rc) + return rc; rc = qed_mcp_load_req(p_hwfn, p_hwfn->p_main_ptt, &load_code); if (rc) { @@ -1485,10 +1498,25 @@ static void qed_hw_hwfn_free(struct qed_hwfn *p_hwfn) static void qed_hw_hwfn_prepare(struct qed_hwfn *p_hwfn) { /* clear indirect access */ - qed_wr(p_hwfn, p_hwfn->p_main_ptt, PGLUE_B_REG_PGL_ADDR_88_F0, 0); - qed_wr(p_hwfn, p_hwfn->p_main_ptt, PGLUE_B_REG_PGL_ADDR_8C_F0, 0); - qed_wr(p_hwfn, p_hwfn->p_main_ptt, PGLUE_B_REG_PGL_ADDR_90_F0, 0); - qed_wr(p_hwfn, p_hwfn->p_main_ptt, PGLUE_B_REG_PGL_ADDR_94_F0, 0); + if (QED_IS_AH(p_hwfn->cdev)) { + qed_wr(p_hwfn, p_hwfn->p_main_ptt, + PGLUE_B_REG_PGL_ADDR_E8_F0_K2, 0); + qed_wr(p_hwfn, p_hwfn->p_main_ptt, + PGLUE_B_REG_PGL_ADDR_EC_F0_K2, 0); + qed_wr(p_hwfn, p_hwfn->p_main_ptt, + PGLUE_B_REG_PGL_ADDR_F0_F0_K2, 0); + qed_wr(p_hwfn, p_hwfn->p_main_ptt, + PGLUE_B_REG_PGL_ADDR_F4_F0_K2, 0); + } else { + qed_wr(p_hwfn, p_hwfn->p_main_ptt, + PGLUE_B_REG_PGL_ADDR_88_F0_BB, 0); + qed_wr(p_hwfn, p_hwfn->p_main_ptt, + PGLUE_B_REG_PGL_ADDR_8C_F0_BB, 0); + qed_wr(p_hwfn, p_hwfn->p_main_ptt, + PGLUE_B_REG_PGL_ADDR_90_F0_BB, 0); + qed_wr(p_hwfn, p_hwfn->p_main_ptt, + PGLUE_B_REG_PGL_ADDR_94_F0_BB, 0); + } /* Clean Previous errors if such exist */ qed_wr(p_hwfn, p_hwfn->p_main_ptt, @@ -1610,6 +1638,7 @@ static u32 qed_hw_get_dflt_resc_num(struct qed_hwfn *p_hwfn, enum qed_resources res_id) { u8 num_funcs = p_hwfn->num_funcs_on_engine; + bool b_ah = QED_IS_AH(p_hwfn->cdev); struct qed_sb_cnt_info sb_cnt_info; u32 dflt_resc_num = 0; @@ -1620,17 +1649,22 @@ static u32 qed_hw_get_dflt_resc_num(struct qed_hwfn *p_hwfn, dflt_resc_num = sb_cnt_info.sb_cnt; break; case QED_L2_QUEUE: - dflt_resc_num = MAX_NUM_L2_QUEUES_BB / num_funcs; + dflt_resc_num = (b_ah ? MAX_NUM_L2_QUEUES_K2 + : MAX_NUM_L2_QUEUES_BB) / num_funcs; break; case QED_VPORT: dflt_resc_num = MAX_NUM_VPORTS_BB / num_funcs; + dflt_resc_num = (b_ah ? MAX_NUM_VPORTS_K2 + : MAX_NUM_VPORTS_BB) / num_funcs; break; case QED_RSS_ENG: - dflt_resc_num = ETH_RSS_ENGINE_NUM_BB / num_funcs; + dflt_resc_num = (b_ah ? ETH_RSS_ENGINE_NUM_K2 + : ETH_RSS_ENGINE_NUM_BB) / num_funcs; break; case QED_PQ: /* The granularity of the PQs is 8 */ - dflt_resc_num = MAX_QM_TX_QUEUES_BB / num_funcs; + dflt_resc_num = (b_ah ? MAX_QM_TX_QUEUES_K2 + : MAX_QM_TX_QUEUES_BB) / num_funcs; dflt_resc_num &= ~0x7; break; case QED_RL: @@ -1642,7 +1676,8 @@ static u32 qed_hw_get_dflt_resc_num(struct qed_hwfn *p_hwfn, dflt_resc_num = ETH_NUM_MAC_FILTERS / num_funcs; break; case QED_ILT: - dflt_resc_num = PXP_NUM_ILT_RECORDS_BB / num_funcs; + dflt_resc_num = (b_ah ? PXP_NUM_ILT_RECORDS_K2 + : PXP_NUM_ILT_RECORDS_BB) / num_funcs; break; case QED_LL2_QUEUE: dflt_resc_num = MAX_NUM_LL2_RX_QUEUES / num_funcs; @@ -1653,7 +1688,10 @@ static u32 qed_hw_get_dflt_resc_num(struct qed_hwfn *p_hwfn, dflt_resc_num = NUM_OF_CMDQS_CQS / num_funcs; break; case QED_RDMA_STATS_QUEUE: - dflt_resc_num = RDMA_NUM_STATISTIC_COUNTERS_BB / num_funcs; + dflt_resc_num = (b_ah ? RDMA_NUM_STATISTIC_COUNTERS_K2 + : RDMA_NUM_STATISTIC_COUNTERS_BB) / + num_funcs; + break; default: break; @@ -1780,6 +1818,7 @@ out: static int qed_hw_get_resc(struct qed_hwfn *p_hwfn) { + bool b_ah = QED_IS_AH(p_hwfn->cdev); u8 res_id; int rc; @@ -1790,7 +1829,8 @@ static int qed_hw_get_resc(struct qed_hwfn *p_hwfn) } /* Sanity for ILT */ - if ((RESC_END(p_hwfn, QED_ILT) > PXP_NUM_ILT_RECORDS_BB)) { + if ((b_ah && (RESC_END(p_hwfn, QED_ILT) > PXP_NUM_ILT_RECORDS_K2)) || + (!b_ah && (RESC_END(p_hwfn, QED_ILT) > PXP_NUM_ILT_RECORDS_BB))) { DP_NOTICE(p_hwfn, "Can't assign ILT pages [%08x,...,%08x]\n", RESC_START(p_hwfn, QED_ILT), RESC_END(p_hwfn, QED_ILT) - 1); @@ -1860,9 +1900,15 @@ static int qed_hw_get_nvm_info(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt) case NVM_CFG1_GLOB_NETWORK_PORT_MODE_2X25G: p_hwfn->hw_info.port_mode = QED_PORT_MODE_DE_2X25G; break; + case NVM_CFG1_GLOB_NETWORK_PORT_MODE_2X10G: + p_hwfn->hw_info.port_mode = QED_PORT_MODE_DE_2X10G; + break; case NVM_CFG1_GLOB_NETWORK_PORT_MODE_1X25G: p_hwfn->hw_info.port_mode = QED_PORT_MODE_DE_1X25G; break; + case NVM_CFG1_GLOB_NETWORK_PORT_MODE_4X25G: + p_hwfn->hw_info.port_mode = QED_PORT_MODE_DE_4X25G; + break; default: DP_NOTICE(p_hwfn, "Unknown port mode in 0x%08x\n", core_cfg); break; @@ -1976,8 +2022,9 @@ static void qed_get_num_funcs(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt) { u8 num_funcs, enabled_func_idx = p_hwfn->rel_pf_id; u32 reg_function_hide, tmp, eng_mask, low_pfs_mask; + struct qed_dev *cdev = p_hwfn->cdev; - num_funcs = MAX_NUM_PFS_BB; + num_funcs = QED_IS_AH(cdev) ? MAX_NUM_PFS_K2 : MAX_NUM_PFS_BB; /* Bit 0 of MISCS_REG_FUNCTION_HIDE indicates whether the bypass values * in the other bits are selected. @@ -1990,12 +2037,17 @@ static void qed_get_num_funcs(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt) reg_function_hide = qed_rd(p_hwfn, p_ptt, MISCS_REG_FUNCTION_HIDE); if (reg_function_hide & 0x1) { - if (QED_PATH_ID(p_hwfn) && p_hwfn->cdev->num_hwfns == 1) { - num_funcs = 0; - eng_mask = 0xaaaa; + if (QED_IS_BB(cdev)) { + if (QED_PATH_ID(p_hwfn) && cdev->num_hwfns == 1) { + num_funcs = 0; + eng_mask = 0xaaaa; + } else { + num_funcs = 1; + eng_mask = 0x5554; + } } else { num_funcs = 1; - eng_mask = 0x5554; + eng_mask = 0xfffe; } /* Get the number of the enabled functions on the engine */ @@ -2027,24 +2079,12 @@ static void qed_get_num_funcs(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt) p_hwfn->enabled_func_idx, p_hwfn->num_funcs_on_engine); } -static int -qed_get_hw_info(struct qed_hwfn *p_hwfn, - struct qed_ptt *p_ptt, - enum qed_pci_personality personality) +static void qed_hw_info_port_num_bb(struct qed_hwfn *p_hwfn, + struct qed_ptt *p_ptt) { u32 port_mode; - int rc; - /* Since all information is common, only first hwfns should do this */ - if (IS_LEAD_HWFN(p_hwfn)) { - rc = qed_iov_hw_info(p_hwfn); - if (rc) - return rc; - } - - /* Read the port mode */ - port_mode = qed_rd(p_hwfn, p_ptt, - CNIG_REG_NW_PORT_MODE_BB_B0); + port_mode = qed_rd(p_hwfn, p_ptt, CNIG_REG_NW_PORT_MODE_BB_B0); if (port_mode < 3) { p_hwfn->cdev->num_ports_in_engines = 1; @@ -2057,6 +2097,54 @@ qed_get_hw_info(struct qed_hwfn *p_hwfn, /* Default num_ports_in_engines to something */ p_hwfn->cdev->num_ports_in_engines = 1; } +} + +static void qed_hw_info_port_num_ah(struct qed_hwfn *p_hwfn, + struct qed_ptt *p_ptt) +{ + u32 port; + int i; + + p_hwfn->cdev->num_ports_in_engines = 0; + + for (i = 0; i < MAX_NUM_PORTS_K2; i++) { + port = qed_rd(p_hwfn, p_ptt, + CNIG_REG_NIG_PORT0_CONF_K2 + (i * 4)); + if (port & 1) + p_hwfn->cdev->num_ports_in_engines++; + } + + if (!p_hwfn->cdev->num_ports_in_engines) { + DP_NOTICE(p_hwfn, "All NIG ports are inactive\n"); + + /* Default num_ports_in_engine to something */ + p_hwfn->cdev->num_ports_in_engines = 1; + } +} + +static void qed_hw_info_port_num(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt) +{ + if (QED_IS_BB(p_hwfn->cdev)) + qed_hw_info_port_num_bb(p_hwfn, p_ptt); + else + qed_hw_info_port_num_ah(p_hwfn, p_ptt); +} + +static int +qed_get_hw_info(struct qed_hwfn *p_hwfn, + struct qed_ptt *p_ptt, + enum qed_pci_personality personality) +{ + int rc; + + /* Since all information is common, only first hwfns should do this */ + if (IS_LEAD_HWFN(p_hwfn)) { + rc = qed_iov_hw_info(p_hwfn); + if (rc) + return rc; + } + + qed_hw_info_port_num(p_hwfn, p_ptt); qed_hw_get_nvm_info(p_hwfn, p_ptt); @@ -2096,19 +2184,33 @@ qed_get_hw_info(struct qed_hwfn *p_hwfn, static int qed_get_dev_info(struct qed_dev *cdev) { struct qed_hwfn *p_hwfn = QED_LEADING_HWFN(cdev); + u16 device_id_mask; u32 tmp; /* Read Vendor Id / Device Id */ pci_read_config_word(cdev->pdev, PCI_VENDOR_ID, &cdev->vendor_id); pci_read_config_word(cdev->pdev, PCI_DEVICE_ID, &cdev->device_id); + /* Determine type */ + device_id_mask = cdev->device_id & QED_DEV_ID_MASK; + switch (device_id_mask) { + case QED_DEV_ID_MASK_BB: + cdev->type = QED_DEV_TYPE_BB; + break; + case QED_DEV_ID_MASK_AH: + cdev->type = QED_DEV_TYPE_AH; + break; + default: + DP_NOTICE(p_hwfn, "Unknown device id 0x%x\n", cdev->device_id); + return -EBUSY; + } + cdev->chip_num = (u16)qed_rd(p_hwfn, p_hwfn->p_main_ptt, MISCS_REG_CHIP_NUM); cdev->chip_rev = (u16)qed_rd(p_hwfn, p_hwfn->p_main_ptt, MISCS_REG_CHIP_REV); MASK_FIELD(CHIP_REV, cdev->chip_rev); - cdev->type = QED_DEV_TYPE_BB; /* Learn number of HW-functions */ tmp = qed_rd(p_hwfn, p_hwfn->p_main_ptt, MISCS_REG_CMT_ENABLED_FOR_PAIR); @@ -2128,7 +2230,10 @@ static int qed_get_dev_info(struct qed_dev *cdev) MASK_FIELD(CHIP_METAL, cdev->chip_metal); DP_INFO(cdev->hwfns, - "Chip details - Num: %04x Rev: %04x Bond id: %04x Metal: %04x\n", + "Chip details - %s %c%d, Num: %04x Rev: %04x Bond id: %04x Metal: %04x\n", + QED_IS_BB(cdev) ? "BB" : "AH", + 'A' + cdev->chip_rev, + (int)cdev->chip_metal, cdev->chip_num, cdev->chip_rev, cdev->chip_bond_id, cdev->chip_metal); @@ -2389,9 +2494,8 @@ qed_chain_alloc_sanity_check(struct qed_dev *cdev, * size/capacity fields are of a u32 type. */ if ((cnt_type == QED_CHAIN_CNT_TYPE_U16 && - chain_size > 0x10000) || - (cnt_type == QED_CHAIN_CNT_TYPE_U32 && - chain_size > 0x100000000ULL)) { + chain_size > ((u32)U16_MAX + 1)) || + (cnt_type == QED_CHAIN_CNT_TYPE_U32 && chain_size > U32_MAX)) { DP_NOTICE(cdev, "The actual chain size (0x%llx) is larger than the maximal possible value\n", chain_size); @@ -3364,3 +3468,8 @@ void qed_clean_wfq_db(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt) memset(p_hwfn->qm_info.wfq_data, 0, sizeof(*p_hwfn->qm_info.wfq_data) * p_hwfn->qm_info.num_vports); } + +int qed_device_num_engines(struct qed_dev *cdev) +{ + return QED_IS_BB(cdev) ? 2 : 1; +} diff --git a/drivers/net/ethernet/qlogic/qed/qed_hsi.h b/drivers/net/ethernet/qlogic/qed/qed_hsi.h index 37c2bfb663bb..e9acdc96ba84 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_hsi.h +++ b/drivers/net/ethernet/qlogic/qed/qed_hsi.h @@ -574,6 +574,7 @@ enum core_event_opcode { CORE_EVENT_TX_QUEUE_STOP, CORE_EVENT_RX_QUEUE_START, CORE_EVENT_RX_QUEUE_STOP, + CORE_EVENT_RX_QUEUE_FLUSH, MAX_CORE_EVENT_OPCODE }; @@ -625,6 +626,7 @@ enum core_ramrod_cmd_id { CORE_RAMROD_TX_QUEUE_START, CORE_RAMROD_RX_QUEUE_STOP, CORE_RAMROD_TX_QUEUE_STOP, + CORE_RAMROD_RX_QUEUE_FLUSH, MAX_CORE_RAMROD_CMD_ID }; @@ -698,7 +700,8 @@ struct core_rx_slow_path_cqe { u8 type; u8 ramrod_cmd_id; __le16 echo; - __le32 reserved1[7]; + struct core_rx_cqe_opaque_data opaque_data; + __le32 reserved1[5]; }; union core_rx_cqe_union { @@ -735,45 +738,46 @@ struct core_rx_stop_ramrod_data { __le16 reserved2[2]; }; -struct core_tx_bd_flags { - u8 as_bitfield; -#define CORE_TX_BD_FLAGS_FORCE_VLAN_MODE_MASK 0x1 -#define CORE_TX_BD_FLAGS_FORCE_VLAN_MODE_SHIFT 0 -#define CORE_TX_BD_FLAGS_VLAN_INSERTION_MASK 0x1 -#define CORE_TX_BD_FLAGS_VLAN_INSERTION_SHIFT 1 -#define CORE_TX_BD_FLAGS_START_BD_MASK 0x1 -#define CORE_TX_BD_FLAGS_START_BD_SHIFT 2 -#define CORE_TX_BD_FLAGS_IP_CSUM_MASK 0x1 -#define CORE_TX_BD_FLAGS_IP_CSUM_SHIFT 3 -#define CORE_TX_BD_FLAGS_L4_CSUM_MASK 0x1 -#define CORE_TX_BD_FLAGS_L4_CSUM_SHIFT 4 -#define CORE_TX_BD_FLAGS_IPV6_EXT_MASK 0x1 -#define CORE_TX_BD_FLAGS_IPV6_EXT_SHIFT 5 -#define CORE_TX_BD_FLAGS_L4_PROTOCOL_MASK 0x1 -#define CORE_TX_BD_FLAGS_L4_PROTOCOL_SHIFT 6 -#define CORE_TX_BD_FLAGS_L4_PSEUDO_CSUM_MODE_MASK 0x1 -#define CORE_TX_BD_FLAGS_L4_PSEUDO_CSUM_MODE_SHIFT 7 +struct core_tx_bd_data { + __le16 as_bitfield; +#define CORE_TX_BD_DATA_FORCE_VLAN_MODE_MASK 0x1 +#define CORE_TX_BD_DATA_FORCE_VLAN_MODE_SHIFT 0 +#define CORE_TX_BD_DATA_VLAN_INSERTION_MASK 0x1 +#define CORE_TX_BD_DATA_VLAN_INSERTION_SHIFT 1 +#define CORE_TX_BD_DATA_START_BD_MASK 0x1 +#define CORE_TX_BD_DATA_START_BD_SHIFT 2 +#define CORE_TX_BD_DATA_IP_CSUM_MASK 0x1 +#define CORE_TX_BD_DATA_IP_CSUM_SHIFT 3 +#define CORE_TX_BD_DATA_L4_CSUM_MASK 0x1 +#define CORE_TX_BD_DATA_L4_CSUM_SHIFT 4 +#define CORE_TX_BD_DATA_IPV6_EXT_MASK 0x1 +#define CORE_TX_BD_DATA_IPV6_EXT_SHIFT 5 +#define CORE_TX_BD_DATA_L4_PROTOCOL_MASK 0x1 +#define CORE_TX_BD_DATA_L4_PROTOCOL_SHIFT 6 +#define CORE_TX_BD_DATA_L4_PSEUDO_CSUM_MODE_MASK 0x1 +#define CORE_TX_BD_DATA_L4_PSEUDO_CSUM_MODE_SHIFT 7 +#define CORE_TX_BD_DATA_NBDS_MASK 0xF +#define CORE_TX_BD_DATA_NBDS_SHIFT 8 +#define CORE_TX_BD_DATA_ROCE_FLAV_MASK 0x1 +#define CORE_TX_BD_DATA_ROCE_FLAV_SHIFT 12 +#define CORE_TX_BD_DATA_IP_LEN_MASK 0x1 +#define CORE_TX_BD_DATA_IP_LEN_SHIFT 13 +#define CORE_TX_BD_DATA_RESERVED0_MASK 0x3 +#define CORE_TX_BD_DATA_RESERVED0_SHIFT 14 }; struct core_tx_bd { struct regpair addr; __le16 nbytes; __le16 nw_vlan_or_lb_echo; - u8 bitfield0; -#define CORE_TX_BD_NBDS_MASK 0xF -#define CORE_TX_BD_NBDS_SHIFT 0 -#define CORE_TX_BD_ROCE_FLAV_MASK 0x1 -#define CORE_TX_BD_ROCE_FLAV_SHIFT 4 -#define CORE_TX_BD_RESERVED0_MASK 0x7 -#define CORE_TX_BD_RESERVED0_SHIFT 5 - struct core_tx_bd_flags bd_flags; + struct core_tx_bd_data bd_data; __le16 bitfield1; #define CORE_TX_BD_L4_HDR_OFFSET_W_MASK 0x3FFF #define CORE_TX_BD_L4_HDR_OFFSET_W_SHIFT 0 #define CORE_TX_BD_TX_DST_MASK 0x1 #define CORE_TX_BD_TX_DST_SHIFT 14 -#define CORE_TX_BD_RESERVED1_MASK 0x1 -#define CORE_TX_BD_RESERVED1_SHIFT 15 +#define CORE_TX_BD_RESERVED_MASK 0x1 +#define CORE_TX_BD_RESERVED_SHIFT 15 }; enum core_tx_dest { @@ -800,6 +804,14 @@ struct core_tx_stop_ramrod_data { __le32 reserved0[2]; }; +enum dcb_dhcp_update_flag { + DONT_UPDATE_DCB_DHCP, + UPDATE_DCB, + UPDATE_DSCP, + UPDATE_DCB_DSCP, + MAX_DCB_DHCP_UPDATE_FLAG +}; + struct eth_mstorm_per_pf_stat { struct regpair gre_discard_pkts; struct regpair vxlan_discard_pkts; @@ -893,6 +905,12 @@ union event_ring_element { struct event_ring_next_addr next_addr; }; +enum fw_flow_ctrl_mode { + flow_ctrl_pause, + flow_ctrl_pfc, + MAX_FW_FLOW_CTRL_MODE +}; + /* Major and Minor hsi Versions */ struct hsi_fp_ver_struct { u8 minor_ver_arr[2]; @@ -921,6 +939,7 @@ enum malicious_vf_error_id { ETH_EDPM_OUT_OF_SYNC, ETH_TUNN_IPV6_EXT_NBD_ERR, ETH_CONTROL_PACKET_VIOLATION, + ETH_ANTI_SPOOFING_ERR, MAX_MALICIOUS_VF_ERROR_ID }; @@ -1106,8 +1125,9 @@ struct tstorm_per_port_stat { struct regpair ll2_mac_filter_discard; struct regpair ll2_conn_disabled_discard; struct regpair iscsi_irregular_pkt; - struct regpair reserved; + struct regpair fcoe_irregular_pkt; struct regpair roce_irregular_pkt; + struct regpair reserved; struct regpair eth_irregular_pkt; struct regpair reserved1; struct regpair preroce_irregular_pkt; @@ -1648,6 +1668,11 @@ enum block_addr { GRCBASE_MS = 0x6a0000, GRCBASE_PHY_PCIE = 0x620000, GRCBASE_LED = 0x6b8000, + GRCBASE_AVS_WRAP = 0x6b0000, + GRCBASE_RGFS = 0x19d0000, + GRCBASE_TGFS = 0x19e0000, + GRCBASE_PTLD = 0x19f0000, + GRCBASE_YPLD = 0x1a10000, GRCBASE_MISC_AEU = 0x8000, GRCBASE_BAR0_MAP = 0x1c00000, MAX_BLOCK_ADDR @@ -1732,6 +1757,11 @@ enum block_id { BLOCK_MS, BLOCK_PHY_PCIE, BLOCK_LED, + BLOCK_AVS_WRAP, + BLOCK_RGFS, + BLOCK_TGFS, + BLOCK_PTLD, + BLOCK_YPLD, BLOCK_MISC_AEU, BLOCK_BAR0_MAP, MAX_BLOCK_ID @@ -1783,9 +1813,9 @@ struct dbg_attn_reg_result { __le32 data; #define DBG_ATTN_REG_RESULT_STS_ADDRESS_MASK 0xFFFFFF #define DBG_ATTN_REG_RESULT_STS_ADDRESS_SHIFT 0 -#define DBG_ATTN_REG_RESULT_NUM_ATTN_IDX_MASK 0xFF -#define DBG_ATTN_REG_RESULT_NUM_ATTN_IDX_SHIFT 24 - __le16 attn_idx_offset; +#define DBG_ATTN_REG_RESULT_NUM_REG_ATTN_MASK 0xFF +#define DBG_ATTN_REG_RESULT_NUM_REG_ATTN_SHIFT 24 + __le16 block_attn_offset; __le16 reserved; __le32 sts_val; __le32 mask_val; @@ -1815,12 +1845,12 @@ struct dbg_mode_hdr { /* Attention register */ struct dbg_attn_reg { struct dbg_mode_hdr mode; - __le16 attn_idx_offset; + __le16 block_attn_offset; __le32 data; #define DBG_ATTN_REG_STS_ADDRESS_MASK 0xFFFFFF #define DBG_ATTN_REG_STS_ADDRESS_SHIFT 0 -#define DBG_ATTN_REG_NUM_ATTN_IDX_MASK 0xFF -#define DBG_ATTN_REG_NUM_ATTN_IDX_SHIFT 24 +#define DBG_ATTN_REG_NUM_REG_ATTN_MASK 0xFF +#define DBG_ATTN_REG_NUM_REG_ATTN_SHIFT 24 __le32 sts_clr_address; __le32 mask_address; }; @@ -2001,6 +2031,20 @@ enum dbg_bus_clients { MAX_DBG_BUS_CLIENTS }; +enum dbg_bus_constraint_ops { + DBG_BUS_CONSTRAINT_OP_EQ, + DBG_BUS_CONSTRAINT_OP_NE, + DBG_BUS_CONSTRAINT_OP_LT, + DBG_BUS_CONSTRAINT_OP_LTC, + DBG_BUS_CONSTRAINT_OP_LE, + DBG_BUS_CONSTRAINT_OP_LEC, + DBG_BUS_CONSTRAINT_OP_GT, + DBG_BUS_CONSTRAINT_OP_GTC, + DBG_BUS_CONSTRAINT_OP_GE, + DBG_BUS_CONSTRAINT_OP_GEC, + MAX_DBG_BUS_CONSTRAINT_OPS +}; + /* Debug Bus memory address */ struct dbg_bus_mem_addr { __le32 lo; @@ -2092,10 +2136,18 @@ struct dbg_bus_data { * DBG_BUS_TARGET_ID_PCI. */ __le16 reserved; - struct dbg_bus_block_data blocks[80];/* Debug Bus data for each block */ + struct dbg_bus_block_data blocks[88];/* Debug Bus data for each block */ struct dbg_bus_storm_data storms[6]; /* Debug Bus data for each block */ }; +enum dbg_bus_filter_types { + DBG_BUS_FILTER_TYPE_OFF, + DBG_BUS_FILTER_TYPE_PRE, + DBG_BUS_FILTER_TYPE_POST, + DBG_BUS_FILTER_TYPE_ON, + MAX_DBG_BUS_FILTER_TYPES +}; + /* Debug bus frame modes */ enum dbg_bus_frame_modes { DBG_BUS_FRAME_MODE_0HW_4ST = 0, /* 0 HW dwords, 4 Storm dwords */ @@ -2104,6 +2156,40 @@ enum dbg_bus_frame_modes { MAX_DBG_BUS_FRAME_MODES }; +enum dbg_bus_input_types { + DBG_BUS_INPUT_TYPE_STORM, + DBG_BUS_INPUT_TYPE_BLOCK, + MAX_DBG_BUS_INPUT_TYPES +}; + +enum dbg_bus_other_engine_modes { + DBG_BUS_OTHER_ENGINE_MODE_NONE, + DBG_BUS_OTHER_ENGINE_MODE_DOUBLE_BW_TX, + DBG_BUS_OTHER_ENGINE_MODE_DOUBLE_BW_RX, + DBG_BUS_OTHER_ENGINE_MODE_CROSS_ENGINE_TX, + DBG_BUS_OTHER_ENGINE_MODE_CROSS_ENGINE_RX, + MAX_DBG_BUS_OTHER_ENGINE_MODES +}; + +enum dbg_bus_post_trigger_types { + DBG_BUS_POST_TRIGGER_RECORD, + DBG_BUS_POST_TRIGGER_DROP, + MAX_DBG_BUS_POST_TRIGGER_TYPES +}; + +enum dbg_bus_pre_trigger_types { + DBG_BUS_PRE_TRIGGER_START_FROM_ZERO, + DBG_BUS_PRE_TRIGGER_NUM_CHUNKS, + DBG_BUS_PRE_TRIGGER_DROP, + MAX_DBG_BUS_PRE_TRIGGER_TYPES +}; + +enum dbg_bus_semi_frame_modes { + DBG_BUS_SEMI_FRAME_MODE_0SLOW_4FAST = 0, + DBG_BUS_SEMI_FRAME_MODE_4SLOW_0FAST = 3, + MAX_DBG_BUS_SEMI_FRAME_MODES +}; + /* Debug bus states */ enum dbg_bus_states { DBG_BUS_STATE_IDLE, /* debug bus idle state (not recording) */ @@ -2115,6 +2201,19 @@ enum dbg_bus_states { MAX_DBG_BUS_STATES }; +enum dbg_bus_storm_modes { + DBG_BUS_STORM_MODE_PRINTF, + DBG_BUS_STORM_MODE_PRAM_ADDR, + DBG_BUS_STORM_MODE_DRA_RW, + DBG_BUS_STORM_MODE_DRA_W, + DBG_BUS_STORM_MODE_LD_ST_ADDR, + DBG_BUS_STORM_MODE_DRA_FSM, + DBG_BUS_STORM_MODE_RH, + DBG_BUS_STORM_MODE_FOC, + DBG_BUS_STORM_MODE_EXT_STORE, + MAX_DBG_BUS_STORM_MODES +}; + /* Debug bus target IDs */ enum dbg_bus_targets { /* records debug bus to DBG block internal buffer */ @@ -2128,13 +2227,10 @@ enum dbg_bus_targets { /* GRC Dump data */ struct dbg_grc_data { - __le32 param_val[40]; /* Value of each GRC parameter. Array size must - * match the enum dbg_grc_params. - */ - u8 param_set_by_user[40]; /* Indicates for each GRC parameter if it was - * set by the user (0/1). Array size must - * match the enum dbg_grc_params. - */ + u8 params_initialized; + u8 reserved1; + __le16 reserved2; + __le32 param_val[48]; }; /* Debug GRC params */ @@ -2181,6 +2277,8 @@ enum dbg_grc_params { DBG_GRC_PARAM_PARITY_SAFE, DBG_GRC_PARAM_DUMP_CM, /* dump CM memories (0/1) */ DBG_GRC_PARAM_DUMP_PHY, /* dump PHY memories (0/1) */ + DBG_GRC_PARAM_NO_MCP, + DBG_GRC_PARAM_NO_FW_VER, MAX_DBG_GRC_PARAMS }; @@ -2280,7 +2378,7 @@ struct dbg_tools_data { struct dbg_bus_data bus; /* Debug Bus data */ struct idle_chk_data idle_chk; /* Idle Check data */ u8 mode_enable[40]; /* Indicates if a mode is enabled (0/1) */ - u8 block_in_reset[80]; /* Indicates if a block is in reset state (0/1). + u8 block_in_reset[88]; /* Indicates if a block is in reset state (0/1). */ u8 chip_id; /* Chip ID (from enum chip_ids) */ u8 platform_id; /* Platform ID (from enum platform_ids) */ @@ -2404,7 +2502,7 @@ struct fw_info_location { enum init_modes { MODE_RESERVED, - MODE_BB_B0, + MODE_BB, MODE_K2, MODE_ASIC, MODE_RESERVED2, @@ -2418,7 +2516,6 @@ enum init_modes { MODE_PORTS_PER_ENG_2, MODE_PORTS_PER_ENG_4, MODE_100G, - MODE_40G, MODE_RESERVED6, MAX_INIT_MODES }; @@ -2686,6 +2783,13 @@ struct iro { */ enum dbg_status qed_dbg_set_bin_ptr(const u8 * const bin_ptr); /** + * @brief qed_dbg_grc_set_params_default - Reverts all GRC parameters to their + * default value. + * + * @param p_hwfn - HW device data + */ +void qed_dbg_grc_set_params_default(struct qed_hwfn *p_hwfn); +/** * @brief qed_dbg_grc_get_dump_buf_size - Returns the required buffer size for * GRC Dump. * @@ -3418,7 +3522,7 @@ void qed_set_geneve_enable(struct qed_hwfn *p_hwfn, #define MSTORM_TPA_TIMEOUT_US_SIZE (IRO[21].size) #define MSTORM_ETH_PF_STAT_OFFSET(pf_id) \ (IRO[22].base + ((pf_id) * IRO[22].m1)) -#define MSTORM_ETH_PF_STAT_SIZE (IRO[21].size) +#define MSTORM_ETH_PF_STAT_SIZE (IRO[22].size) #define USTORM_QUEUE_STAT_OFFSET(stat_counter_id) \ (IRO[23].base + ((stat_counter_id) * IRO[23].m1)) #define USTORM_QUEUE_STAT_SIZE (IRO[23].size) @@ -3482,7 +3586,7 @@ void qed_set_geneve_enable(struct qed_hwfn *p_hwfn, static const struct iro iro_arr[47] = { {0x0, 0x0, 0x0, 0x0, 0x8}, - {0x4cb0, 0x78, 0x0, 0x0, 0x78}, + {0x4cb0, 0x80, 0x0, 0x0, 0x80}, {0x6318, 0x20, 0x0, 0x0, 0x20}, {0xb00, 0x8, 0x0, 0x0, 0x4}, {0xa80, 0x8, 0x0, 0x0, 0x4}, @@ -3521,13 +3625,13 @@ static const struct iro iro_arr[47] = { {0xd888, 0x38, 0x0, 0x0, 0x24}, {0x12c38, 0x10, 0x0, 0x0, 0x8}, {0x11aa0, 0x38, 0x0, 0x0, 0x18}, - {0xa8c0, 0x30, 0x0, 0x0, 0x10}, - {0x86f8, 0x28, 0x0, 0x0, 0x18}, + {0xa8c0, 0x38, 0x0, 0x0, 0x10}, + {0x86f8, 0x30, 0x0, 0x0, 0x18}, {0x101f8, 0x10, 0x0, 0x0, 0x10}, {0xdd08, 0x48, 0x0, 0x0, 0x38}, {0x10660, 0x20, 0x0, 0x0, 0x20}, {0x2b80, 0x80, 0x0, 0x0, 0x10}, - {0x5000, 0x10, 0x0, 0x0, 0x10}, + {0x5020, 0x10, 0x0, 0x0, 0x10}, }; /* Runtime array offsets */ @@ -4595,6 +4699,12 @@ enum eth_ipv4_frag_type { MAX_ETH_IPV4_FRAG_TYPE }; +enum eth_ip_type { + ETH_IPV4, + ETH_IPV6, + MAX_ETH_IP_TYPE +}; + enum eth_ramrod_cmd_id { ETH_RAMROD_UNUSED, ETH_RAMROD_VPORT_START, @@ -4944,7 +5054,10 @@ struct vport_update_ramrod_data_cmn { u8 update_mtu_flg; __le16 mtu; - u8 reserved[2]; + u8 update_ctl_frame_checks_en_flg; + u8 ctl_frame_mac_check_en; + u8 ctl_frame_ethtype_check_en; + u8 reserved[15]; }; struct vport_update_ramrod_mcast { @@ -4962,6 +5075,492 @@ struct vport_update_ramrod_data { struct eth_vport_rss_config rss_config; }; +struct mstorm_eth_conn_ag_ctx { + u8 byte0; + u8 byte1; + u8 flags0; +#define MSTORM_ETH_CONN_AG_CTX_EXIST_IN_QM0_MASK 0x1 +#define MSTORM_ETH_CONN_AG_CTX_EXIST_IN_QM0_SHIFT 0 +#define MSTORM_ETH_CONN_AG_CTX_BIT1_MASK 0x1 +#define MSTORM_ETH_CONN_AG_CTX_BIT1_SHIFT 1 +#define MSTORM_ETH_CONN_AG_CTX_CF0_MASK 0x3 +#define MSTORM_ETH_CONN_AG_CTX_CF0_SHIFT 2 +#define MSTORM_ETH_CONN_AG_CTX_CF1_MASK 0x3 +#define MSTORM_ETH_CONN_AG_CTX_CF1_SHIFT 4 +#define MSTORM_ETH_CONN_AG_CTX_CF2_MASK 0x3 +#define MSTORM_ETH_CONN_AG_CTX_CF2_SHIFT 6 + u8 flags1; +#define MSTORM_ETH_CONN_AG_CTX_CF0EN_MASK 0x1 +#define MSTORM_ETH_CONN_AG_CTX_CF0EN_SHIFT 0 +#define MSTORM_ETH_CONN_AG_CTX_CF1EN_MASK 0x1 +#define MSTORM_ETH_CONN_AG_CTX_CF1EN_SHIFT 1 +#define MSTORM_ETH_CONN_AG_CTX_CF2EN_MASK 0x1 +#define MSTORM_ETH_CONN_AG_CTX_CF2EN_SHIFT 2 +#define MSTORM_ETH_CONN_AG_CTX_RULE0EN_MASK 0x1 +#define MSTORM_ETH_CONN_AG_CTX_RULE0EN_SHIFT 3 +#define MSTORM_ETH_CONN_AG_CTX_RULE1EN_MASK 0x1 +#define MSTORM_ETH_CONN_AG_CTX_RULE1EN_SHIFT 4 +#define MSTORM_ETH_CONN_AG_CTX_RULE2EN_MASK 0x1 +#define MSTORM_ETH_CONN_AG_CTX_RULE2EN_SHIFT 5 +#define MSTORM_ETH_CONN_AG_CTX_RULE3EN_MASK 0x1 +#define MSTORM_ETH_CONN_AG_CTX_RULE3EN_SHIFT 6 +#define MSTORM_ETH_CONN_AG_CTX_RULE4EN_MASK 0x1 +#define MSTORM_ETH_CONN_AG_CTX_RULE4EN_SHIFT 7 + __le16 word0; + __le16 word1; + __le32 reg0; + __le32 reg1; +}; + +struct xstorm_eth_conn_agctxdq_ext_ldpart { + u8 reserved0; + u8 eth_state; + u8 flags0; +#define XSTORMETHCONNAGCTXDQEXTLDPART_EXIST_IN_QM0_MASK 0x1 +#define XSTORMETHCONNAGCTXDQEXTLDPART_EXIST_IN_QM0_SHIFT 0 +#define XSTORMETHCONNAGCTXDQEXTLDPART_RESERVED1_MASK 0x1 +#define XSTORMETHCONNAGCTXDQEXTLDPART_RESERVED1_SHIFT 1 +#define XSTORMETHCONNAGCTXDQEXTLDPART_RESERVED2_MASK 0x1 +#define XSTORMETHCONNAGCTXDQEXTLDPART_RESERVED2_SHIFT 2 +#define XSTORMETHCONNAGCTXDQEXTLDPART_EXIST_IN_QM3_MASK 0x1 +#define XSTORMETHCONNAGCTXDQEXTLDPART_EXIST_IN_QM3_SHIFT 3 +#define XSTORMETHCONNAGCTXDQEXTLDPART_RESERVED3_MASK 0x1 +#define XSTORMETHCONNAGCTXDQEXTLDPART_RESERVED3_SHIFT 4 +#define XSTORMETHCONNAGCTXDQEXTLDPART_RESERVED4_MASK 0x1 +#define XSTORMETHCONNAGCTXDQEXTLDPART_RESERVED4_SHIFT 5 +#define XSTORMETHCONNAGCTXDQEXTLDPART_RESERVED5_MASK 0x1 +#define XSTORMETHCONNAGCTXDQEXTLDPART_RESERVED5_SHIFT 6 +#define XSTORMETHCONNAGCTXDQEXTLDPART_RESERVED6_MASK 0x1 +#define XSTORMETHCONNAGCTXDQEXTLDPART_RESERVED6_SHIFT 7 + u8 flags1; +#define XSTORMETHCONNAGCTXDQEXTLDPART_RESERVED7_MASK 0x1 +#define XSTORMETHCONNAGCTXDQEXTLDPART_RESERVED7_SHIFT 0 +#define XSTORMETHCONNAGCTXDQEXTLDPART_RESERVED8_MASK 0x1 +#define XSTORMETHCONNAGCTXDQEXTLDPART_RESERVED8_SHIFT 1 +#define XSTORMETHCONNAGCTXDQEXTLDPART_RESERVED9_MASK 0x1 +#define XSTORMETHCONNAGCTXDQEXTLDPART_RESERVED9_SHIFT 2 +#define XSTORMETHCONNAGCTXDQEXTLDPART_BIT11_MASK 0x1 +#define XSTORMETHCONNAGCTXDQEXTLDPART_BIT11_SHIFT 3 +#define XSTORMETHCONNAGCTXDQEXTLDPART_BIT12_MASK 0x1 +#define XSTORMETHCONNAGCTXDQEXTLDPART_BIT12_SHIFT 4 +#define XSTORMETHCONNAGCTXDQEXTLDPART_BIT13_MASK 0x1 +#define XSTORMETHCONNAGCTXDQEXTLDPART_BIT13_SHIFT 5 +#define XSTORMETHCONNAGCTXDQEXTLDPART_TX_RULE_ACTIVE_MASK 0x1 +#define XSTORMETHCONNAGCTXDQEXTLDPART_TX_RULE_ACTIVE_SHIFT 6 +#define XSTORMETHCONNAGCTXDQEXTLDPART_DQ_CF_ACTIVE_MASK 0x1 +#define XSTORMETHCONNAGCTXDQEXTLDPART_DQ_CF_ACTIVE_SHIFT 7 + u8 flags2; +#define XSTORMETHCONNAGCTXDQEXTLDPART_CF0_MASK 0x3 +#define XSTORMETHCONNAGCTXDQEXTLDPART_CF0_SHIFT 0 +#define XSTORMETHCONNAGCTXDQEXTLDPART_CF1_MASK 0x3 +#define XSTORMETHCONNAGCTXDQEXTLDPART_CF1_SHIFT 2 +#define XSTORMETHCONNAGCTXDQEXTLDPART_CF2_MASK 0x3 +#define XSTORMETHCONNAGCTXDQEXTLDPART_CF2_SHIFT 4 +#define XSTORMETHCONNAGCTXDQEXTLDPART_CF3_MASK 0x3 +#define XSTORMETHCONNAGCTXDQEXTLDPART_CF3_SHIFT 6 + u8 flags3; +#define XSTORMETHCONNAGCTXDQEXTLDPART_CF4_MASK 0x3 +#define XSTORMETHCONNAGCTXDQEXTLDPART_CF4_SHIFT 0 +#define XSTORMETHCONNAGCTXDQEXTLDPART_CF5_MASK 0x3 +#define XSTORMETHCONNAGCTXDQEXTLDPART_CF5_SHIFT 2 +#define XSTORMETHCONNAGCTXDQEXTLDPART_CF6_MASK 0x3 +#define XSTORMETHCONNAGCTXDQEXTLDPART_CF6_SHIFT 4 +#define XSTORMETHCONNAGCTXDQEXTLDPART_CF7_MASK 0x3 +#define XSTORMETHCONNAGCTXDQEXTLDPART_CF7_SHIFT 6 + u8 flags4; +#define XSTORMETHCONNAGCTXDQEXTLDPART_CF8_MASK 0x3 +#define XSTORMETHCONNAGCTXDQEXTLDPART_CF8_SHIFT 0 +#define XSTORMETHCONNAGCTXDQEXTLDPART_CF9_MASK 0x3 +#define XSTORMETHCONNAGCTXDQEXTLDPART_CF9_SHIFT 2 +#define XSTORMETHCONNAGCTXDQEXTLDPART_CF10_MASK 0x3 +#define XSTORMETHCONNAGCTXDQEXTLDPART_CF10_SHIFT 4 +#define XSTORMETHCONNAGCTXDQEXTLDPART_CF11_MASK 0x3 +#define XSTORMETHCONNAGCTXDQEXTLDPART_CF11_SHIFT 6 + u8 flags5; +#define XSTORMETHCONNAGCTXDQEXTLDPART_CF12_MASK 0x3 +#define XSTORMETHCONNAGCTXDQEXTLDPART_CF12_SHIFT 0 +#define XSTORMETHCONNAGCTXDQEXTLDPART_CF13_MASK 0x3 +#define XSTORMETHCONNAGCTXDQEXTLDPART_CF13_SHIFT 2 +#define XSTORMETHCONNAGCTXDQEXTLDPART_CF14_MASK 0x3 +#define XSTORMETHCONNAGCTXDQEXTLDPART_CF14_SHIFT 4 +#define XSTORMETHCONNAGCTXDQEXTLDPART_CF15_MASK 0x3 +#define XSTORMETHCONNAGCTXDQEXTLDPART_CF15_SHIFT 6 + u8 flags6; +#define XSTORMETHCONNAGCTXDQEXTLDPART_GO_TO_BD_CONS_CF_MASK 0x3 +#define XSTORMETHCONNAGCTXDQEXTLDPART_GO_TO_BD_CONS_CF_SHIFT 0 +#define XSTORMETHCONNAGCTXDQEXTLDPART_MULTI_UNICAST_CF_MASK 0x3 +#define XSTORMETHCONNAGCTXDQEXTLDPART_MULTI_UNICAST_CF_SHIFT 2 +#define XSTORMETHCONNAGCTXDQEXTLDPART_DQ_CF_MASK 0x3 +#define XSTORMETHCONNAGCTXDQEXTLDPART_DQ_CF_SHIFT 4 +#define XSTORMETHCONNAGCTXDQEXTLDPART_TERMINATE_CF_MASK 0x3 +#define XSTORMETHCONNAGCTXDQEXTLDPART_TERMINATE_CF_SHIFT 6 + u8 flags7; +#define XSTORMETHCONNAGCTXDQEXTLDPART_FLUSH_Q0_MASK 0x3 +#define XSTORMETHCONNAGCTXDQEXTLDPART_FLUSH_Q0_SHIFT 0 +#define XSTORMETHCONNAGCTXDQEXTLDPART_RESERVED10_MASK 0x3 +#define XSTORMETHCONNAGCTXDQEXTLDPART_RESERVED10_SHIFT 2 +#define XSTORMETHCONNAGCTXDQEXTLDPART_SLOW_PATH_MASK 0x3 +#define XSTORMETHCONNAGCTXDQEXTLDPART_SLOW_PATH_SHIFT 4 +#define XSTORMETHCONNAGCTXDQEXTLDPART_CF0EN_MASK 0x1 +#define XSTORMETHCONNAGCTXDQEXTLDPART_CF0EN_SHIFT 6 +#define XSTORMETHCONNAGCTXDQEXTLDPART_CF1EN_MASK 0x1 +#define XSTORMETHCONNAGCTXDQEXTLDPART_CF1EN_SHIFT 7 + u8 flags8; +#define XSTORMETHCONNAGCTXDQEXTLDPART_CF2EN_MASK 0x1 +#define XSTORMETHCONNAGCTXDQEXTLDPART_CF2EN_SHIFT 0 +#define XSTORMETHCONNAGCTXDQEXTLDPART_CF3EN_MASK 0x1 +#define XSTORMETHCONNAGCTXDQEXTLDPART_CF3EN_SHIFT 1 +#define XSTORMETHCONNAGCTXDQEXTLDPART_CF4EN_MASK 0x1 +#define XSTORMETHCONNAGCTXDQEXTLDPART_CF4EN_SHIFT 2 +#define XSTORMETHCONNAGCTXDQEXTLDPART_CF5EN_MASK 0x1 +#define XSTORMETHCONNAGCTXDQEXTLDPART_CF5EN_SHIFT 3 +#define XSTORMETHCONNAGCTXDQEXTLDPART_CF6EN_MASK 0x1 +#define XSTORMETHCONNAGCTXDQEXTLDPART_CF6EN_SHIFT 4 +#define XSTORMETHCONNAGCTXDQEXTLDPART_CF7EN_MASK 0x1 +#define XSTORMETHCONNAGCTXDQEXTLDPART_CF7EN_SHIFT 5 +#define XSTORMETHCONNAGCTXDQEXTLDPART_CF8EN_MASK 0x1 +#define XSTORMETHCONNAGCTXDQEXTLDPART_CF8EN_SHIFT 6 +#define XSTORMETHCONNAGCTXDQEXTLDPART_CF9EN_MASK 0x1 +#define XSTORMETHCONNAGCTXDQEXTLDPART_CF9EN_SHIFT 7 + u8 flags9; +#define XSTORMETHCONNAGCTXDQEXTLDPART_CF10EN_MASK 0x1 +#define XSTORMETHCONNAGCTXDQEXTLDPART_CF10EN_SHIFT 0 +#define XSTORMETHCONNAGCTXDQEXTLDPART_CF11EN_MASK 0x1 +#define XSTORMETHCONNAGCTXDQEXTLDPART_CF11EN_SHIFT 1 +#define XSTORMETHCONNAGCTXDQEXTLDPART_CF12EN_MASK 0x1 +#define XSTORMETHCONNAGCTXDQEXTLDPART_CF12EN_SHIFT 2 +#define XSTORMETHCONNAGCTXDQEXTLDPART_CF13EN_MASK 0x1 +#define XSTORMETHCONNAGCTXDQEXTLDPART_CF13EN_SHIFT 3 +#define XSTORMETHCONNAGCTXDQEXTLDPART_CF14EN_MASK 0x1 +#define XSTORMETHCONNAGCTXDQEXTLDPART_CF14EN_SHIFT 4 +#define XSTORMETHCONNAGCTXDQEXTLDPART_CF15EN_MASK 0x1 +#define XSTORMETHCONNAGCTXDQEXTLDPART_CF15EN_SHIFT 5 +#define XSTORMETHCONNAGCTXDQEXTLDPART_GO_TO_BD_CONS_CF_EN_MASK 0x1 +#define XSTORMETHCONNAGCTXDQEXTLDPART_GO_TO_BD_CONS_CF_EN_SHIFT 6 +#define XSTORMETHCONNAGCTXDQEXTLDPART_MULTI_UNICAST_CF_EN_MASK 0x1 +#define XSTORMETHCONNAGCTXDQEXTLDPART_MULTI_UNICAST_CF_EN_SHIFT 7 + u8 flags10; +#define XSTORMETHCONNAGCTXDQEXTLDPART_DQ_CF_EN_MASK 0x1 +#define XSTORMETHCONNAGCTXDQEXTLDPART_DQ_CF_EN_SHIFT 0 +#define XSTORMETHCONNAGCTXDQEXTLDPART_TERMINATE_CF_EN_MASK 0x1 +#define XSTORMETHCONNAGCTXDQEXTLDPART_TERMINATE_CF_EN_SHIFT 1 +#define XSTORMETHCONNAGCTXDQEXTLDPART_FLUSH_Q0_EN_MASK 0x1 +#define XSTORMETHCONNAGCTXDQEXTLDPART_FLUSH_Q0_EN_SHIFT 2 +#define XSTORMETHCONNAGCTXDQEXTLDPART_RESERVED11_MASK 0x1 +#define XSTORMETHCONNAGCTXDQEXTLDPART_RESERVED11_SHIFT 3 +#define XSTORMETHCONNAGCTXDQEXTLDPART_SLOW_PATH_EN_MASK 0x1 +#define XSTORMETHCONNAGCTXDQEXTLDPART_SLOW_PATH_EN_SHIFT 4 +#define XSTORMETHCONNAGCTXDQEXTLDPART_TPH_ENABLE_EN_RESERVED_MASK 0x1 +#define XSTORMETHCONNAGCTXDQEXTLDPART_TPH_ENABLE_EN_RESERVED_SHIFT 5 +#define XSTORMETHCONNAGCTXDQEXTLDPART_RESERVED12_MASK 0x1 +#define XSTORMETHCONNAGCTXDQEXTLDPART_RESERVED12_SHIFT 6 +#define XSTORMETHCONNAGCTXDQEXTLDPART_RESERVED13_MASK 0x1 +#define XSTORMETHCONNAGCTXDQEXTLDPART_RESERVED13_SHIFT 7 + u8 flags11; +#define XSTORMETHCONNAGCTXDQEXTLDPART_RESERVED14_MASK 0x1 +#define XSTORMETHCONNAGCTXDQEXTLDPART_RESERVED14_SHIFT 0 +#define XSTORMETHCONNAGCTXDQEXTLDPART_RESERVED15_MASK 0x1 +#define XSTORMETHCONNAGCTXDQEXTLDPART_RESERVED15_SHIFT 1 +#define XSTORMETHCONNAGCTXDQEXTLDPART_TX_DEC_RULE_EN_MASK 0x1 +#define XSTORMETHCONNAGCTXDQEXTLDPART_TX_DEC_RULE_EN_SHIFT 2 +#define XSTORMETHCONNAGCTXDQEXTLDPART_RULE5EN_MASK 0x1 +#define XSTORMETHCONNAGCTXDQEXTLDPART_RULE5EN_SHIFT 3 +#define XSTORMETHCONNAGCTXDQEXTLDPART_RULE6EN_MASK 0x1 +#define XSTORMETHCONNAGCTXDQEXTLDPART_RULE6EN_SHIFT 4 +#define XSTORMETHCONNAGCTXDQEXTLDPART_RULE7EN_MASK 0x1 +#define XSTORMETHCONNAGCTXDQEXTLDPART_RULE7EN_SHIFT 5 +#define XSTORMETHCONNAGCTXDQEXTLDPART_A0_RESERVED1_MASK 0x1 +#define XSTORMETHCONNAGCTXDQEXTLDPART_A0_RESERVED1_SHIFT 6 +#define XSTORMETHCONNAGCTXDQEXTLDPART_RULE9EN_MASK 0x1 +#define XSTORMETHCONNAGCTXDQEXTLDPART_RULE9EN_SHIFT 7 + u8 flags12; +#define XSTORMETHCONNAGCTXDQEXTLDPART_RULE10EN_MASK 0x1 +#define XSTORMETHCONNAGCTXDQEXTLDPART_RULE10EN_SHIFT 0 +#define XSTORMETHCONNAGCTXDQEXTLDPART_RULE11EN_MASK 0x1 +#define XSTORMETHCONNAGCTXDQEXTLDPART_RULE11EN_SHIFT 1 +#define XSTORMETHCONNAGCTXDQEXTLDPART_A0_RESERVED2_MASK 0x1 +#define XSTORMETHCONNAGCTXDQEXTLDPART_A0_RESERVED2_SHIFT 2 +#define XSTORMETHCONNAGCTXDQEXTLDPART_A0_RESERVED3_MASK 0x1 +#define XSTORMETHCONNAGCTXDQEXTLDPART_A0_RESERVED3_SHIFT 3 +#define XSTORMETHCONNAGCTXDQEXTLDPART_RULE14EN_MASK 0x1 +#define XSTORMETHCONNAGCTXDQEXTLDPART_RULE14EN_SHIFT 4 +#define XSTORMETHCONNAGCTXDQEXTLDPART_RULE15EN_MASK 0x1 +#define XSTORMETHCONNAGCTXDQEXTLDPART_RULE15EN_SHIFT 5 +#define XSTORMETHCONNAGCTXDQEXTLDPART_RULE16EN_MASK 0x1 +#define XSTORMETHCONNAGCTXDQEXTLDPART_RULE16EN_SHIFT 6 +#define XSTORMETHCONNAGCTXDQEXTLDPART_RULE17EN_MASK 0x1 +#define XSTORMETHCONNAGCTXDQEXTLDPART_RULE17EN_SHIFT 7 + u8 flags13; +#define XSTORMETHCONNAGCTXDQEXTLDPART_RULE18EN_MASK 0x1 +#define XSTORMETHCONNAGCTXDQEXTLDPART_RULE18EN_SHIFT 0 +#define XSTORMETHCONNAGCTXDQEXTLDPART_RULE19EN_MASK 0x1 +#define XSTORMETHCONNAGCTXDQEXTLDPART_RULE19EN_SHIFT 1 +#define XSTORMETHCONNAGCTXDQEXTLDPART_A0_RESERVED4_MASK 0x1 +#define XSTORMETHCONNAGCTXDQEXTLDPART_A0_RESERVED4_SHIFT 2 +#define XSTORMETHCONNAGCTXDQEXTLDPART_A0_RESERVED5_MASK 0x1 +#define XSTORMETHCONNAGCTXDQEXTLDPART_A0_RESERVED5_SHIFT 3 +#define XSTORMETHCONNAGCTXDQEXTLDPART_A0_RESERVED6_MASK 0x1 +#define XSTORMETHCONNAGCTXDQEXTLDPART_A0_RESERVED6_SHIFT 4 +#define XSTORMETHCONNAGCTXDQEXTLDPART_A0_RESERVED7_MASK 0x1 +#define XSTORMETHCONNAGCTXDQEXTLDPART_A0_RESERVED7_SHIFT 5 +#define XSTORMETHCONNAGCTXDQEXTLDPART_A0_RESERVED8_MASK 0x1 +#define XSTORMETHCONNAGCTXDQEXTLDPART_A0_RESERVED8_SHIFT 6 +#define XSTORMETHCONNAGCTXDQEXTLDPART_A0_RESERVED9_MASK 0x1 +#define XSTORMETHCONNAGCTXDQEXTLDPART_A0_RESERVED9_SHIFT 7 + u8 flags14; +#define XSTORMETHCONNAGCTXDQEXTLDPART_EDPM_USE_EXT_HDR_MASK 0x1 +#define XSTORMETHCONNAGCTXDQEXTLDPART_EDPM_USE_EXT_HDR_SHIFT 0 +#define XSTORMETHCONNAGCTXDQEXTLDPART_EDPM_SEND_RAW_L3L4_MASK 0x1 +#define XSTORMETHCONNAGCTXDQEXTLDPART_EDPM_SEND_RAW_L3L4_SHIFT 1 +#define XSTORMETHCONNAGCTXDQEXTLDPART_EDPM_INBAND_PROP_HDR_MASK 0x1 +#define XSTORMETHCONNAGCTXDQEXTLDPART_EDPM_INBAND_PROP_HDR_SHIFT 2 +#define XSTORMETHCONNAGCTXDQEXTLDPART_EDPM_SEND_EXT_TUNNEL_MASK 0x1 +#define XSTORMETHCONNAGCTXDQEXTLDPART_EDPM_SEND_EXT_TUNNEL_SHIFT 3 +#define XSTORMETHCONNAGCTXDQEXTLDPART_L2_EDPM_ENABLE_MASK 0x1 +#define XSTORMETHCONNAGCTXDQEXTLDPART_L2_EDPM_ENABLE_SHIFT 4 +#define XSTORMETHCONNAGCTXDQEXTLDPART_ROCE_EDPM_ENABLE_MASK 0x1 +#define XSTORMETHCONNAGCTXDQEXTLDPART_ROCE_EDPM_ENABLE_SHIFT 5 +#define XSTORMETHCONNAGCTXDQEXTLDPART_TPH_ENABLE_MASK 0x3 +#define XSTORMETHCONNAGCTXDQEXTLDPART_TPH_ENABLE_SHIFT 6 + u8 edpm_event_id; + __le16 physical_q0; + __le16 quota; + __le16 edpm_num_bds; + __le16 tx_bd_cons; + __le16 tx_bd_prod; + __le16 tx_class; + __le16 conn_dpi; + u8 byte3; + u8 byte4; + u8 byte5; + u8 byte6; + __le32 reg0; + __le32 reg1; + __le32 reg2; + __le32 reg3; + __le32 reg4; +}; + +struct xstorm_eth_hw_conn_ag_ctx { + u8 reserved0; + u8 eth_state; + u8 flags0; +#define XSTORM_ETH_HW_CONN_AG_CTX_EXIST_IN_QM0_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_EXIST_IN_QM0_SHIFT 0 +#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED1_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED1_SHIFT 1 +#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED2_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED2_SHIFT 2 +#define XSTORM_ETH_HW_CONN_AG_CTX_EXIST_IN_QM3_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_EXIST_IN_QM3_SHIFT 3 +#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED3_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED3_SHIFT 4 +#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED4_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED4_SHIFT 5 +#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED5_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED5_SHIFT 6 +#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED6_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED6_SHIFT 7 + u8 flags1; +#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED7_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED7_SHIFT 0 +#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED8_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED8_SHIFT 1 +#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED9_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED9_SHIFT 2 +#define XSTORM_ETH_HW_CONN_AG_CTX_BIT11_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_BIT11_SHIFT 3 +#define XSTORM_ETH_HW_CONN_AG_CTX_BIT12_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_BIT12_SHIFT 4 +#define XSTORM_ETH_HW_CONN_AG_CTX_BIT13_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_BIT13_SHIFT 5 +#define XSTORM_ETH_HW_CONN_AG_CTX_TX_RULE_ACTIVE_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_TX_RULE_ACTIVE_SHIFT 6 +#define XSTORM_ETH_HW_CONN_AG_CTX_DQ_CF_ACTIVE_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_DQ_CF_ACTIVE_SHIFT 7 + u8 flags2; +#define XSTORM_ETH_HW_CONN_AG_CTX_CF0_MASK 0x3 +#define XSTORM_ETH_HW_CONN_AG_CTX_CF0_SHIFT 0 +#define XSTORM_ETH_HW_CONN_AG_CTX_CF1_MASK 0x3 +#define XSTORM_ETH_HW_CONN_AG_CTX_CF1_SHIFT 2 +#define XSTORM_ETH_HW_CONN_AG_CTX_CF2_MASK 0x3 +#define XSTORM_ETH_HW_CONN_AG_CTX_CF2_SHIFT 4 +#define XSTORM_ETH_HW_CONN_AG_CTX_CF3_MASK 0x3 +#define XSTORM_ETH_HW_CONN_AG_CTX_CF3_SHIFT 6 + u8 flags3; +#define XSTORM_ETH_HW_CONN_AG_CTX_CF4_MASK 0x3 +#define XSTORM_ETH_HW_CONN_AG_CTX_CF4_SHIFT 0 +#define XSTORM_ETH_HW_CONN_AG_CTX_CF5_MASK 0x3 +#define XSTORM_ETH_HW_CONN_AG_CTX_CF5_SHIFT 2 +#define XSTORM_ETH_HW_CONN_AG_CTX_CF6_MASK 0x3 +#define XSTORM_ETH_HW_CONN_AG_CTX_CF6_SHIFT 4 +#define XSTORM_ETH_HW_CONN_AG_CTX_CF7_MASK 0x3 +#define XSTORM_ETH_HW_CONN_AG_CTX_CF7_SHIFT 6 + u8 flags4; +#define XSTORM_ETH_HW_CONN_AG_CTX_CF8_MASK 0x3 +#define XSTORM_ETH_HW_CONN_AG_CTX_CF8_SHIFT 0 +#define XSTORM_ETH_HW_CONN_AG_CTX_CF9_MASK 0x3 +#define XSTORM_ETH_HW_CONN_AG_CTX_CF9_SHIFT 2 +#define XSTORM_ETH_HW_CONN_AG_CTX_CF10_MASK 0x3 +#define XSTORM_ETH_HW_CONN_AG_CTX_CF10_SHIFT 4 +#define XSTORM_ETH_HW_CONN_AG_CTX_CF11_MASK 0x3 +#define XSTORM_ETH_HW_CONN_AG_CTX_CF11_SHIFT 6 + u8 flags5; +#define XSTORM_ETH_HW_CONN_AG_CTX_CF12_MASK 0x3 +#define XSTORM_ETH_HW_CONN_AG_CTX_CF12_SHIFT 0 +#define XSTORM_ETH_HW_CONN_AG_CTX_CF13_MASK 0x3 +#define XSTORM_ETH_HW_CONN_AG_CTX_CF13_SHIFT 2 +#define XSTORM_ETH_HW_CONN_AG_CTX_CF14_MASK 0x3 +#define XSTORM_ETH_HW_CONN_AG_CTX_CF14_SHIFT 4 +#define XSTORM_ETH_HW_CONN_AG_CTX_CF15_MASK 0x3 +#define XSTORM_ETH_HW_CONN_AG_CTX_CF15_SHIFT 6 + u8 flags6; +#define XSTORM_ETH_HW_CONN_AG_CTX_GO_TO_BD_CONS_CF_MASK 0x3 +#define XSTORM_ETH_HW_CONN_AG_CTX_GO_TO_BD_CONS_CF_SHIFT 0 +#define XSTORM_ETH_HW_CONN_AG_CTX_MULTI_UNICAST_CF_MASK 0x3 +#define XSTORM_ETH_HW_CONN_AG_CTX_MULTI_UNICAST_CF_SHIFT 2 +#define XSTORM_ETH_HW_CONN_AG_CTX_DQ_CF_MASK 0x3 +#define XSTORM_ETH_HW_CONN_AG_CTX_DQ_CF_SHIFT 4 +#define XSTORM_ETH_HW_CONN_AG_CTX_TERMINATE_CF_MASK 0x3 +#define XSTORM_ETH_HW_CONN_AG_CTX_TERMINATE_CF_SHIFT 6 + u8 flags7; +#define XSTORM_ETH_HW_CONN_AG_CTX_FLUSH_Q0_MASK 0x3 +#define XSTORM_ETH_HW_CONN_AG_CTX_FLUSH_Q0_SHIFT 0 +#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED10_MASK 0x3 +#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED10_SHIFT 2 +#define XSTORM_ETH_HW_CONN_AG_CTX_SLOW_PATH_MASK 0x3 +#define XSTORM_ETH_HW_CONN_AG_CTX_SLOW_PATH_SHIFT 4 +#define XSTORM_ETH_HW_CONN_AG_CTX_CF0EN_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_CF0EN_SHIFT 6 +#define XSTORM_ETH_HW_CONN_AG_CTX_CF1EN_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_CF1EN_SHIFT 7 + u8 flags8; +#define XSTORM_ETH_HW_CONN_AG_CTX_CF2EN_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_CF2EN_SHIFT 0 +#define XSTORM_ETH_HW_CONN_AG_CTX_CF3EN_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_CF3EN_SHIFT 1 +#define XSTORM_ETH_HW_CONN_AG_CTX_CF4EN_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_CF4EN_SHIFT 2 +#define XSTORM_ETH_HW_CONN_AG_CTX_CF5EN_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_CF5EN_SHIFT 3 +#define XSTORM_ETH_HW_CONN_AG_CTX_CF6EN_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_CF6EN_SHIFT 4 +#define XSTORM_ETH_HW_CONN_AG_CTX_CF7EN_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_CF7EN_SHIFT 5 +#define XSTORM_ETH_HW_CONN_AG_CTX_CF8EN_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_CF8EN_SHIFT 6 +#define XSTORM_ETH_HW_CONN_AG_CTX_CF9EN_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_CF9EN_SHIFT 7 + u8 flags9; +#define XSTORM_ETH_HW_CONN_AG_CTX_CF10EN_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_CF10EN_SHIFT 0 +#define XSTORM_ETH_HW_CONN_AG_CTX_CF11EN_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_CF11EN_SHIFT 1 +#define XSTORM_ETH_HW_CONN_AG_CTX_CF12EN_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_CF12EN_SHIFT 2 +#define XSTORM_ETH_HW_CONN_AG_CTX_CF13EN_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_CF13EN_SHIFT 3 +#define XSTORM_ETH_HW_CONN_AG_CTX_CF14EN_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_CF14EN_SHIFT 4 +#define XSTORM_ETH_HW_CONN_AG_CTX_CF15EN_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_CF15EN_SHIFT 5 +#define XSTORM_ETH_HW_CONN_AG_CTX_GO_TO_BD_CONS_CF_EN_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_GO_TO_BD_CONS_CF_EN_SHIFT 6 +#define XSTORM_ETH_HW_CONN_AG_CTX_MULTI_UNICAST_CF_EN_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_MULTI_UNICAST_CF_EN_SHIFT 7 + u8 flags10; +#define XSTORM_ETH_HW_CONN_AG_CTX_DQ_CF_EN_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_DQ_CF_EN_SHIFT 0 +#define XSTORM_ETH_HW_CONN_AG_CTX_TERMINATE_CF_EN_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_TERMINATE_CF_EN_SHIFT 1 +#define XSTORM_ETH_HW_CONN_AG_CTX_FLUSH_Q0_EN_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_FLUSH_Q0_EN_SHIFT 2 +#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED11_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED11_SHIFT 3 +#define XSTORM_ETH_HW_CONN_AG_CTX_SLOW_PATH_EN_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_SLOW_PATH_EN_SHIFT 4 +#define XSTORM_ETH_HW_CONN_AG_CTX_TPH_ENABLE_EN_RESERVED_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_TPH_ENABLE_EN_RESERVED_SHIFT 5 +#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED12_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED12_SHIFT 6 +#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED13_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED13_SHIFT 7 + u8 flags11; +#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED14_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED14_SHIFT 0 +#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED15_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED15_SHIFT 1 +#define XSTORM_ETH_HW_CONN_AG_CTX_TX_DEC_RULE_EN_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_TX_DEC_RULE_EN_SHIFT 2 +#define XSTORM_ETH_HW_CONN_AG_CTX_RULE5EN_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_RULE5EN_SHIFT 3 +#define XSTORM_ETH_HW_CONN_AG_CTX_RULE6EN_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_RULE6EN_SHIFT 4 +#define XSTORM_ETH_HW_CONN_AG_CTX_RULE7EN_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_RULE7EN_SHIFT 5 +#define XSTORM_ETH_HW_CONN_AG_CTX_A0_RESERVED1_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_A0_RESERVED1_SHIFT 6 +#define XSTORM_ETH_HW_CONN_AG_CTX_RULE9EN_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_RULE9EN_SHIFT 7 + u8 flags12; +#define XSTORM_ETH_HW_CONN_AG_CTX_RULE10EN_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_RULE10EN_SHIFT 0 +#define XSTORM_ETH_HW_CONN_AG_CTX_RULE11EN_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_RULE11EN_SHIFT 1 +#define XSTORM_ETH_HW_CONN_AG_CTX_A0_RESERVED2_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_A0_RESERVED2_SHIFT 2 +#define XSTORM_ETH_HW_CONN_AG_CTX_A0_RESERVED3_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_A0_RESERVED3_SHIFT 3 +#define XSTORM_ETH_HW_CONN_AG_CTX_RULE14EN_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_RULE14EN_SHIFT 4 +#define XSTORM_ETH_HW_CONN_AG_CTX_RULE15EN_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_RULE15EN_SHIFT 5 +#define XSTORM_ETH_HW_CONN_AG_CTX_RULE16EN_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_RULE16EN_SHIFT 6 +#define XSTORM_ETH_HW_CONN_AG_CTX_RULE17EN_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_RULE17EN_SHIFT 7 + u8 flags13; +#define XSTORM_ETH_HW_CONN_AG_CTX_RULE18EN_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_RULE18EN_SHIFT 0 +#define XSTORM_ETH_HW_CONN_AG_CTX_RULE19EN_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_RULE19EN_SHIFT 1 +#define XSTORM_ETH_HW_CONN_AG_CTX_A0_RESERVED4_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_A0_RESERVED4_SHIFT 2 +#define XSTORM_ETH_HW_CONN_AG_CTX_A0_RESERVED5_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_A0_RESERVED5_SHIFT 3 +#define XSTORM_ETH_HW_CONN_AG_CTX_A0_RESERVED6_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_A0_RESERVED6_SHIFT 4 +#define XSTORM_ETH_HW_CONN_AG_CTX_A0_RESERVED7_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_A0_RESERVED7_SHIFT 5 +#define XSTORM_ETH_HW_CONN_AG_CTX_A0_RESERVED8_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_A0_RESERVED8_SHIFT 6 +#define XSTORM_ETH_HW_CONN_AG_CTX_A0_RESERVED9_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_A0_RESERVED9_SHIFT 7 + u8 flags14; +#define XSTORM_ETH_HW_CONN_AG_CTX_EDPM_USE_EXT_HDR_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_EDPM_USE_EXT_HDR_SHIFT 0 +#define XSTORM_ETH_HW_CONN_AG_CTX_EDPM_SEND_RAW_L3L4_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_EDPM_SEND_RAW_L3L4_SHIFT 1 +#define XSTORM_ETH_HW_CONN_AG_CTX_EDPM_INBAND_PROP_HDR_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_EDPM_INBAND_PROP_HDR_SHIFT 2 +#define XSTORM_ETH_HW_CONN_AG_CTX_EDPM_SEND_EXT_TUNNEL_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_EDPM_SEND_EXT_TUNNEL_SHIFT 3 +#define XSTORM_ETH_HW_CONN_AG_CTX_L2_EDPM_ENABLE_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_L2_EDPM_ENABLE_SHIFT 4 +#define XSTORM_ETH_HW_CONN_AG_CTX_ROCE_EDPM_ENABLE_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_ROCE_EDPM_ENABLE_SHIFT 5 +#define XSTORM_ETH_HW_CONN_AG_CTX_TPH_ENABLE_MASK 0x3 +#define XSTORM_ETH_HW_CONN_AG_CTX_TPH_ENABLE_SHIFT 6 + u8 edpm_event_id; + __le16 physical_q0; + __le16 quota; + __le16 edpm_num_bds; + __le16 tx_bd_cons; + __le16 tx_bd_prod; + __le16 tx_class; + __le16 conn_dpi; +}; + struct mstorm_rdma_task_st_ctx { struct regpair temp[4]; }; @@ -6165,7 +6764,7 @@ struct ystorm_roce_conn_st_ctx { }; struct xstorm_roce_conn_st_ctx { - struct regpair temp[22]; + struct regpair temp[24]; }; struct tstorm_roce_conn_st_ctx { @@ -6220,7 +6819,7 @@ struct roce_create_qp_req_ramrod_data { __le16 mtu; __le16 pd; __le16 sq_num_pages; - __le16 reseved2; + __le16 low_latency_phy_queue; struct regpair sq_pbl_addr; struct regpair orq_pbl_addr; __le16 local_mac_addr[3]; @@ -6234,7 +6833,7 @@ struct roce_create_qp_req_ramrod_data { u8 stats_counter_id; u8 reserved3[7]; __le32 cq_cid; - __le16 physical_queue0; + __le16 regular_latency_phy_queue; __le16 dpi; }; @@ -6282,15 +6881,16 @@ struct roce_create_qp_resp_ramrod_data { __le32 dst_gid[4]; struct regpair qp_handle_for_cqe; struct regpair qp_handle_for_async; - __le32 reserved2[2]; + __le16 low_latency_phy_queue; + u8 reserved2[6]; __le32 cq_cid; - __le16 physical_queue0; + __le16 regular_latency_phy_queue; __le16 dpi; }; struct roce_destroy_qp_req_output_params { __le32 num_bound_mw; - __le32 reserved; + __le32 cq_prod; }; struct roce_destroy_qp_req_ramrod_data { @@ -6299,7 +6899,7 @@ struct roce_destroy_qp_req_ramrod_data { struct roce_destroy_qp_resp_output_params { __le32 num_invalidated_mw; - __le32 reserved; + __le32 cq_prod; }; struct roce_destroy_qp_resp_ramrod_data { @@ -7426,6 +8026,7 @@ struct ystorm_fcoe_conn_st_ctx { u8 fcp_rsp_size; __le16 mss; struct regpair reserved; + __le16 min_frame_size; u8 protection_info_flags; #define YSTORM_FCOE_CONN_ST_CTX_SUPPORT_PROTECTION_MASK 0x1 #define YSTORM_FCOE_CONN_ST_CTX_SUPPORT_PROTECTION_SHIFT 0 @@ -7444,7 +8045,6 @@ struct ystorm_fcoe_conn_st_ctx { #define YSTORM_FCOE_CONN_ST_CTX_RSRV_MASK 0x3F #define YSTORM_FCOE_CONN_ST_CTX_RSRV_SHIFT 2 u8 fcp_xfer_size; - u8 reserved3[2]; }; struct fcoe_vlan_fields { @@ -8273,10 +8873,10 @@ struct xstorm_iscsi_conn_ag_ctx { #define XSTORM_ISCSI_CONN_AG_CTX_DQ_FLUSH_MASK 0x3 #define XSTORM_ISCSI_CONN_AG_CTX_DQ_FLUSH_SHIFT 6 u8 flags7; -#define XSTORM_ISCSI_CONN_AG_CTX_FLUSH_Q0_MASK 0x3 -#define XSTORM_ISCSI_CONN_AG_CTX_FLUSH_Q0_SHIFT 0 -#define XSTORM_ISCSI_CONN_AG_CTX_FLUSH_Q1_MASK 0x3 -#define XSTORM_ISCSI_CONN_AG_CTX_FLUSH_Q1_SHIFT 2 +#define XSTORM_ISCSI_CONN_AG_CTX_MST_XCM_Q0_FLUSH_CF_MASK 0x3 +#define XSTORM_ISCSI_CONN_AG_CTX_MST_XCM_Q0_FLUSH_CF_SHIFT 0 +#define XSTORM_ISCSI_CONN_AG_CTX_UST_XCM_Q1_FLUSH_CF_MASK 0x3 +#define XSTORM_ISCSI_CONN_AG_CTX_UST_XCM_Q1_FLUSH_CF_SHIFT 2 #define XSTORM_ISCSI_CONN_AG_CTX_SLOW_PATH_MASK 0x3 #define XSTORM_ISCSI_CONN_AG_CTX_SLOW_PATH_SHIFT 4 #define XSTORM_ISCSI_CONN_AG_CTX_CF0EN_MASK 0x1 @@ -8322,10 +8922,10 @@ struct xstorm_iscsi_conn_ag_ctx { #define XSTORM_ISCSI_CONN_AG_CTX_CF18EN_SHIFT 0 #define XSTORM_ISCSI_CONN_AG_CTX_DQ_FLUSH_EN_MASK 0x1 #define XSTORM_ISCSI_CONN_AG_CTX_DQ_FLUSH_EN_SHIFT 1 -#define XSTORM_ISCSI_CONN_AG_CTX_FLUSH_Q0_EN_MASK 0x1 -#define XSTORM_ISCSI_CONN_AG_CTX_FLUSH_Q0_EN_SHIFT 2 -#define XSTORM_ISCSI_CONN_AG_CTX_FLUSH_Q1_EN_MASK 0x1 -#define XSTORM_ISCSI_CONN_AG_CTX_FLUSH_Q1_EN_SHIFT 3 +#define XSTORM_ISCSI_CONN_AG_CTX_MST_XCM_Q0_FLUSH_CF_EN_MASK 0x1 +#define XSTORM_ISCSI_CONN_AG_CTX_MST_XCM_Q0_FLUSH_CF_EN_SHIFT 2 +#define XSTORM_ISCSI_CONN_AG_CTX_UST_XCM_Q1_FLUSH_CF_EN_MASK 0x1 +#define XSTORM_ISCSI_CONN_AG_CTX_UST_XCM_Q1_FLUSH_CF_EN_SHIFT 3 #define XSTORM_ISCSI_CONN_AG_CTX_SLOW_PATH_EN_MASK 0x1 #define XSTORM_ISCSI_CONN_AG_CTX_SLOW_PATH_EN_SHIFT 4 #define XSTORM_ISCSI_CONN_AG_CTX_PROC_ONLY_CLEANUP_EN_MASK 0x1 @@ -8335,8 +8935,8 @@ struct xstorm_iscsi_conn_ag_ctx { #define XSTORM_ISCSI_CONN_AG_CTX_MORE_TO_SEND_DEC_RULE_EN_MASK 0x1 #define XSTORM_ISCSI_CONN_AG_CTX_MORE_TO_SEND_DEC_RULE_EN_SHIFT 7 u8 flags11; -#define XSTORM_ISCSI_CONN_AG_CTX_RULE2EN_MASK 0x1 -#define XSTORM_ISCSI_CONN_AG_CTX_RULE2EN_SHIFT 0 +#define XSTORM_ISCSI_CONN_AG_CTX_TX_BLOCKED_EN_MASK 0x1 +#define XSTORM_ISCSI_CONN_AG_CTX_TX_BLOCKED_EN_SHIFT 0 #define XSTORM_ISCSI_CONN_AG_CTX_RULE3EN_MASK 0x1 #define XSTORM_ISCSI_CONN_AG_CTX_RULE3EN_SHIFT 1 #define XSTORM_ISCSI_CONN_AG_CTX_RESERVED3_MASK 0x1 @@ -8440,7 +9040,7 @@ struct xstorm_iscsi_conn_ag_ctx { __le32 reg10; __le32 reg11; __le32 exp_stat_sn; - __le32 reg13; + __le32 ongoing_fast_rxmit_seq; __le32 reg14; __le32 reg15; __le32 reg16; @@ -8466,10 +9066,10 @@ struct tstorm_iscsi_conn_ag_ctx { #define TSTORM_ISCSI_CONN_AG_CTX_CF0_MASK 0x3 #define TSTORM_ISCSI_CONN_AG_CTX_CF0_SHIFT 6 u8 flags1; -#define TSTORM_ISCSI_CONN_AG_CTX_CF1_MASK 0x3 -#define TSTORM_ISCSI_CONN_AG_CTX_CF1_SHIFT 0 -#define TSTORM_ISCSI_CONN_AG_CTX_CF2_MASK 0x3 -#define TSTORM_ISCSI_CONN_AG_CTX_CF2_SHIFT 2 +#define TSTORM_ISCSI_CONN_AG_CTX_P2T_FLUSH_CF_MASK 0x3 +#define TSTORM_ISCSI_CONN_AG_CTX_P2T_FLUSH_CF_SHIFT 0 +#define TSTORM_ISCSI_CONN_AG_CTX_M2T_FLUSH_CF_MASK 0x3 +#define TSTORM_ISCSI_CONN_AG_CTX_M2T_FLUSH_CF_SHIFT 2 #define TSTORM_ISCSI_CONN_AG_CTX_TIMER_STOP_ALL_MASK 0x3 #define TSTORM_ISCSI_CONN_AG_CTX_TIMER_STOP_ALL_SHIFT 4 #define TSTORM_ISCSI_CONN_AG_CTX_CF4_MASK 0x3 @@ -8490,10 +9090,10 @@ struct tstorm_iscsi_conn_ag_ctx { #define TSTORM_ISCSI_CONN_AG_CTX_CF10_SHIFT 2 #define TSTORM_ISCSI_CONN_AG_CTX_CF0EN_MASK 0x1 #define TSTORM_ISCSI_CONN_AG_CTX_CF0EN_SHIFT 4 -#define TSTORM_ISCSI_CONN_AG_CTX_CF1EN_MASK 0x1 -#define TSTORM_ISCSI_CONN_AG_CTX_CF1EN_SHIFT 5 -#define TSTORM_ISCSI_CONN_AG_CTX_CF2EN_MASK 0x1 -#define TSTORM_ISCSI_CONN_AG_CTX_CF2EN_SHIFT 6 +#define TSTORM_ISCSI_CONN_AG_CTX_P2T_FLUSH_CF_EN_MASK 0x1 +#define TSTORM_ISCSI_CONN_AG_CTX_P2T_FLUSH_CF_EN_SHIFT 5 +#define TSTORM_ISCSI_CONN_AG_CTX_M2T_FLUSH_CF_EN_MASK 0x1 +#define TSTORM_ISCSI_CONN_AG_CTX_M2T_FLUSH_CF_EN_SHIFT 6 #define TSTORM_ISCSI_CONN_AG_CTX_TIMER_STOP_ALL_EN_MASK 0x1 #define TSTORM_ISCSI_CONN_AG_CTX_TIMER_STOP_ALL_EN_SHIFT 7 u8 flags4; @@ -8539,7 +9139,7 @@ struct tstorm_iscsi_conn_ag_ctx { __le32 reg6; __le32 reg7; __le32 reg8; - u8 byte2; + u8 cid_offload_cnt; u8 byte3; __le16 word0; }; @@ -8831,11 +9431,24 @@ struct eth_stats { u64 r511; u64 r1023; u64 r1518; - u64 r1522; - u64 r2047; - u64 r4095; - u64 r9216; - u64 r16383; + + union { + struct { + u64 r1522; + u64 r2047; + u64 r4095; + u64 r9216; + u64 r16383; + } bb0; + struct { + u64 unused1; + u64 r1519_to_max; + u64 unused2; + u64 unused3; + u64 unused4; + } ah0; + } u0; + u64 rfcs; u64 rxcf; u64 rxpf; @@ -8852,14 +9465,36 @@ struct eth_stats { u64 t511; u64 t1023; u64 t1518; - u64 t2047; - u64 t4095; - u64 t9216; - u64 t16383; + + union { + struct { + u64 t2047; + u64 t4095; + u64 t9216; + u64 t16383; + } bb1; + struct { + u64 t1519_to_max; + u64 unused6; + u64 unused7; + u64 unused8; + } ah1; + } u1; + u64 txpf; u64 txpp; - u64 tlpiec; - u64 tncl; + + union { + struct { + u64 tlpiec; + u64 tncl; + } bb2; + struct { + u64 unused9; + u64 unused10; + } ah2; + } u2; + u64 rbyte; u64 rxuca; u64 rxmca; @@ -9067,6 +9702,10 @@ struct dcb_dscp_map { struct public_global { u32 max_path; u32 max_ports; +#define MODE_1P 1 +#define MODE_2P 2 +#define MODE_3P 3 +#define MODE_4P 4 u32 debug_mb_offset; u32 phymod_dbg_mb_offset; struct couple_mode_teaming cmt; @@ -9659,6 +10298,8 @@ struct nvm_cfg1_glob { #define NVM_CFG1_GLOB_NETWORK_PORT_MODE_2X25G 0xC #define NVM_CFG1_GLOB_NETWORK_PORT_MODE_1X25G 0xD #define NVM_CFG1_GLOB_NETWORK_PORT_MODE_4X25G 0xE +#define NVM_CFG1_GLOB_NETWORK_PORT_MODE_2X10G 0xF + u32 e_lane_cfg1; u32 e_lane_cfg2; u32 f_lane_cfg1; diff --git a/drivers/net/ethernet/qlogic/qed/qed_init_fw_funcs.c b/drivers/net/ethernet/qlogic/qed/qed_init_fw_funcs.c index d891a6852695..2a50e2b7568f 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_init_fw_funcs.c +++ b/drivers/net/ethernet/qlogic/qed/qed_init_fw_funcs.c @@ -215,13 +215,6 @@ static void qed_cmdq_lines_voq_rt_init(struct qed_hwfn *p_hwfn, { u32 qm_line_crd; - /* In A0 - Limit the size of pbf queue so that only 511 commands with - * the minimum size of 4 (FCoE minimum size) - */ - bool is_bb_a0 = QED_IS_BB_A0(p_hwfn->cdev); - - if (is_bb_a0) - cmdq_lines = min_t(u32, cmdq_lines, 1022); qm_line_crd = QM_VOQ_LINE_CRD(cmdq_lines); OVERWRITE_RT_REG(p_hwfn, PBF_CMDQ_LINES_RT_OFFSET(voq), (u32)cmdq_lines); @@ -343,13 +336,11 @@ static void qed_tx_pq_map_rt_init( u16 first_pq_group = p_params->start_pq / QM_PF_QUEUE_GROUP_SIZE; u16 last_pq_group = (p_params->start_pq + num_pqs - 1) / QM_PF_QUEUE_GROUP_SIZE; - bool is_bb_a0 = QED_IS_BB_A0(p_hwfn->cdev); u16 i, pq_id, pq_group; /* a bit per Tx PQ indicating if the PQ is associated with a VF */ u32 tx_pq_vf_mask[MAX_QM_TX_QUEUES / QM_PF_QUEUE_GROUP_SIZE] = { 0 }; - u32 tx_pq_vf_mask_width = is_bb_a0 ? 32 : QM_PF_QUEUE_GROUP_SIZE; - u32 num_tx_pq_vf_masks = MAX_QM_TX_QUEUES / tx_pq_vf_mask_width; + u32 num_tx_pq_vf_masks = MAX_QM_TX_QUEUES / QM_PF_QUEUE_GROUP_SIZE; u32 pq_mem_4kb = QM_PQ_MEM_4KB(p_params->num_pf_cids); u32 vport_pq_mem_4kb = QM_PQ_MEM_4KB(p_params->num_vf_cids); u32 mem_addr_4kb = base_mem_addr_4kb; @@ -371,6 +362,10 @@ static void qed_tx_pq_map_rt_init( bool is_vf_pq = (i >= p_params->num_pf_pqs); struct qm_rf_pq_map tx_pq_map; + bool rl_valid = p_params->pq_params[i].rl_valid && + (p_params->pq_params[i].vport_id < + MAX_QM_GLOBAL_RLS); + /* update first Tx PQ of VPORT/TC */ u8 vport_id_in_pf = p_params->pq_params[i].vport_id - p_params->start_vport; @@ -389,14 +384,18 @@ static void qed_tx_pq_map_rt_init( (p_params->pf_id << QM_WFQ_VP_PQ_PF_SHIFT)); } + + if (p_params->pq_params[i].rl_valid && !rl_valid) + DP_NOTICE(p_hwfn, + "Invalid VPORT ID for rate limiter configuration"); /* fill PQ map entry */ memset(&tx_pq_map, 0, sizeof(tx_pq_map)); SET_FIELD(tx_pq_map.reg, QM_RF_PQ_MAP_PQ_VALID, 1); - SET_FIELD(tx_pq_map.reg, QM_RF_PQ_MAP_RL_VALID, - p_params->pq_params[i].rl_valid ? 1 : 0); + SET_FIELD(tx_pq_map.reg, + QM_RF_PQ_MAP_RL_VALID, rl_valid ? 1 : 0); SET_FIELD(tx_pq_map.reg, QM_RF_PQ_MAP_VP_PQ_ID, first_tx_pq_id); SET_FIELD(tx_pq_map.reg, QM_RF_PQ_MAP_RL_ID, - p_params->pq_params[i].rl_valid ? + rl_valid ? p_params->pq_params[i].vport_id : 0); SET_FIELD(tx_pq_map.reg, QM_RF_PQ_MAP_VOQ, voq); SET_FIELD(tx_pq_map.reg, QM_RF_PQ_MAP_WRR_WEIGHT_GROUP, @@ -413,8 +412,9 @@ static void qed_tx_pq_map_rt_init( /* if PQ is associated with a VF, add indication * to PQ VF mask */ - tx_pq_vf_mask[pq_id / tx_pq_vf_mask_width] |= - (1 << (pq_id % tx_pq_vf_mask_width)); + tx_pq_vf_mask[pq_id / + QM_PF_QUEUE_GROUP_SIZE] |= + BIT((pq_id % QM_PF_QUEUE_GROUP_SIZE)); mem_addr_4kb += vport_pq_mem_4kb; } else { mem_addr_4kb += pq_mem_4kb; @@ -480,8 +480,8 @@ static int qed_pf_wfq_rt_init(struct qed_hwfn *p_hwfn, if (p_params->pf_id < MAX_NUM_PFS_BB) crd_reg_offset = QM_REG_WFQPFCRD_RT_OFFSET; else - crd_reg_offset = QM_REG_WFQPFCRD_MSB_RT_OFFSET + - (p_params->pf_id % MAX_NUM_PFS_BB); + crd_reg_offset = QM_REG_WFQPFCRD_MSB_RT_OFFSET; + crd_reg_offset += p_params->pf_id % MAX_NUM_PFS_BB; inc_val = QM_WFQ_INC_VAL(p_params->pf_wfq); if (!inc_val || inc_val > QM_WFQ_MAX_INC_VAL) { @@ -498,11 +498,11 @@ static int qed_pf_wfq_rt_init(struct qed_hwfn *p_hwfn, QM_WFQ_CRD_REG_SIGN_BIT); } - STORE_RT_REG(p_hwfn, QM_REG_WFQPFWEIGHT_RT_OFFSET + p_params->pf_id, - inc_val); STORE_RT_REG(p_hwfn, QM_REG_WFQPFUPPERBOUND_RT_OFFSET + p_params->pf_id, QM_WFQ_UPPER_BOUND | QM_WFQ_CRD_REG_SIGN_BIT); + STORE_RT_REG(p_hwfn, QM_REG_WFQPFWEIGHT_RT_OFFSET + p_params->pf_id, + inc_val); return 0; } @@ -576,6 +576,12 @@ static int qed_vport_rl_rt_init(struct qed_hwfn *p_hwfn, { u8 i, vport_id; + if (start_vport + num_vports >= MAX_QM_GLOBAL_RLS) { + DP_NOTICE(p_hwfn, + "Invalid VPORT ID for rate limiter configuration"); + return -1; + } + /* go over all PF VPORTs */ for (i = 0, vport_id = start_vport; i < num_vports; i++, vport_id++) { u32 inc_val = QM_RL_INC_VAL(vport_params[i].vport_rl); @@ -785,6 +791,12 @@ int qed_init_vport_rl(struct qed_hwfn *p_hwfn, { u32 inc_val = QM_RL_INC_VAL(vport_rl); + if (vport_id >= MAX_QM_GLOBAL_RLS) { + DP_NOTICE(p_hwfn, + "Invalid VPORT ID for rate limiter configuration"); + return -1; + } + if (inc_val > QM_RL_MAX_INC_VAL) { DP_NOTICE(p_hwfn, "Invalid VPORT rate-limit configuration"); return -1; @@ -940,12 +952,6 @@ void qed_set_geneve_enable(struct qed_hwfn *p_hwfn, eth_geneve_enable ? 1 : 0); qed_wr(p_hwfn, p_ptt, NIG_REG_NGE_IP_ENABLE, ip_geneve_enable ? 1 : 0); - /* comp ver */ - reg_val = (ip_geneve_enable || eth_geneve_enable) ? 1 : 0; - qed_wr(p_hwfn, p_ptt, NIG_REG_NGE_COMP_VER, reg_val); - qed_wr(p_hwfn, p_ptt, PBF_REG_NGE_COMP_VER, reg_val); - qed_wr(p_hwfn, p_ptt, PRS_REG_NGE_COMP_VER, reg_val); - /* EDPM with geneve tunnel not supported in BB_B0 */ if (QED_IS_BB_B0(p_hwfn->cdev)) return; diff --git a/drivers/net/ethernet/qlogic/qed/qed_init_ops.c b/drivers/net/ethernet/qlogic/qed/qed_init_ops.c index 243b64e0d4dc..4a2e7be5bf72 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_init_ops.c +++ b/drivers/net/ethernet/qlogic/qed/qed_init_ops.c @@ -554,7 +554,7 @@ int qed_init_fw_data(struct qed_dev *cdev, const u8 *data) } /* First Dword contains metadata and should be skipped */ - buf_hdr = (struct bin_buffer_hdr *)(data + sizeof(u32)); + buf_hdr = (struct bin_buffer_hdr *)data; offset = buf_hdr[BIN_BUF_INIT_FW_VER_INFO].offset; fw->fw_ver_info = (struct fw_ver_info *)(data + offset); diff --git a/drivers/net/ethernet/qlogic/qed/qed_iscsi.c b/drivers/net/ethernet/qlogic/qed/qed_iscsi.c index 3a44d6b395fa..098766f7fe88 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_iscsi.c +++ b/drivers/net/ethernet/qlogic/qed/qed_iscsi.c @@ -190,6 +190,9 @@ qed_sp_iscsi_func_start(struct qed_hwfn *p_hwfn, p_init->num_sq_pages_in_ring = p_params->num_sq_pages_in_ring; p_init->num_r2tq_pages_in_ring = p_params->num_r2tq_pages_in_ring; p_init->num_uhq_pages_in_ring = p_params->num_uhq_pages_in_ring; + p_init->ooo_enable = p_params->ooo_enable; + p_init->ll2_rx_queue_id = p_hwfn->hw_info.resc_start[QED_LL2_QUEUE] + + p_params->ll2_ooo_queue_id; p_init->func_params.log_page_size = p_params->log_page_size; val = p_params->num_tasks; p_init->func_params.num_tasks = cpu_to_le16(val); @@ -786,6 +789,23 @@ static void qed_iscsi_release_connection(struct qed_hwfn *p_hwfn, spin_unlock_bh(&p_hwfn->p_iscsi_info->lock); } +void qed_iscsi_free_connection(struct qed_hwfn *p_hwfn, + struct qed_iscsi_conn *p_conn) +{ + qed_chain_free(p_hwfn->cdev, &p_conn->xhq); + qed_chain_free(p_hwfn->cdev, &p_conn->uhq); + qed_chain_free(p_hwfn->cdev, &p_conn->r2tq); + dma_free_coherent(&p_hwfn->cdev->pdev->dev, + sizeof(struct tcp_upload_params), + p_conn->tcp_upload_params_virt_addr, + p_conn->tcp_upload_params_phys_addr); + dma_free_coherent(&p_hwfn->cdev->pdev->dev, + sizeof(struct scsi_terminate_extra_params), + p_conn->queue_cnts_virt_addr, + p_conn->queue_cnts_phys_addr); + kfree(p_conn); +} + struct qed_iscsi_info *qed_iscsi_alloc(struct qed_hwfn *p_hwfn) { struct qed_iscsi_info *p_iscsi_info; @@ -807,6 +827,17 @@ void qed_iscsi_setup(struct qed_hwfn *p_hwfn, void qed_iscsi_free(struct qed_hwfn *p_hwfn, struct qed_iscsi_info *p_iscsi_info) { + struct qed_iscsi_conn *p_conn = NULL; + + while (!list_empty(&p_hwfn->p_iscsi_info->free_list)) { + p_conn = list_first_entry(&p_hwfn->p_iscsi_info->free_list, + struct qed_iscsi_conn, list_entry); + if (p_conn) { + list_del(&p_conn->list_entry); + qed_iscsi_free_connection(p_hwfn, p_conn); + } + } + kfree(p_iscsi_info); } diff --git a/drivers/net/ethernet/qlogic/qed/qed_l2.c b/drivers/net/ethernet/qlogic/qed/qed_l2.c index df932be5a4e5..4385ccbb5efb 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_l2.c +++ b/drivers/net/ethernet/qlogic/qed/qed_l2.c @@ -1470,13 +1470,20 @@ static void __qed_get_vport_pstats(struct qed_hwfn *p_hwfn, memset(&pstats, 0, sizeof(pstats)); qed_memcpy_from(p_hwfn, p_ptt, &pstats, pstats_addr, pstats_len); - p_stats->tx_ucast_bytes += HILO_64_REGPAIR(pstats.sent_ucast_bytes); - p_stats->tx_mcast_bytes += HILO_64_REGPAIR(pstats.sent_mcast_bytes); - p_stats->tx_bcast_bytes += HILO_64_REGPAIR(pstats.sent_bcast_bytes); - p_stats->tx_ucast_pkts += HILO_64_REGPAIR(pstats.sent_ucast_pkts); - p_stats->tx_mcast_pkts += HILO_64_REGPAIR(pstats.sent_mcast_pkts); - p_stats->tx_bcast_pkts += HILO_64_REGPAIR(pstats.sent_bcast_pkts); - p_stats->tx_err_drop_pkts += HILO_64_REGPAIR(pstats.error_drop_pkts); + p_stats->common.tx_ucast_bytes += + HILO_64_REGPAIR(pstats.sent_ucast_bytes); + p_stats->common.tx_mcast_bytes += + HILO_64_REGPAIR(pstats.sent_mcast_bytes); + p_stats->common.tx_bcast_bytes += + HILO_64_REGPAIR(pstats.sent_bcast_bytes); + p_stats->common.tx_ucast_pkts += + HILO_64_REGPAIR(pstats.sent_ucast_pkts); + p_stats->common.tx_mcast_pkts += + HILO_64_REGPAIR(pstats.sent_mcast_pkts); + p_stats->common.tx_bcast_pkts += + HILO_64_REGPAIR(pstats.sent_bcast_pkts); + p_stats->common.tx_err_drop_pkts += + HILO_64_REGPAIR(pstats.error_drop_pkts); } static void __qed_get_vport_tstats(struct qed_hwfn *p_hwfn, @@ -1502,10 +1509,10 @@ static void __qed_get_vport_tstats(struct qed_hwfn *p_hwfn, memset(&tstats, 0, sizeof(tstats)); qed_memcpy_from(p_hwfn, p_ptt, &tstats, tstats_addr, tstats_len); - p_stats->mftag_filter_discards += - HILO_64_REGPAIR(tstats.mftag_filter_discard); - p_stats->mac_filter_discards += - HILO_64_REGPAIR(tstats.eth_mac_filter_discard); + p_stats->common.mftag_filter_discards += + HILO_64_REGPAIR(tstats.mftag_filter_discard); + p_stats->common.mac_filter_discards += + HILO_64_REGPAIR(tstats.eth_mac_filter_discard); } static void __qed_get_vport_ustats_addrlen(struct qed_hwfn *p_hwfn, @@ -1539,12 +1546,15 @@ static void __qed_get_vport_ustats(struct qed_hwfn *p_hwfn, memset(&ustats, 0, sizeof(ustats)); qed_memcpy_from(p_hwfn, p_ptt, &ustats, ustats_addr, ustats_len); - p_stats->rx_ucast_bytes += HILO_64_REGPAIR(ustats.rcv_ucast_bytes); - p_stats->rx_mcast_bytes += HILO_64_REGPAIR(ustats.rcv_mcast_bytes); - p_stats->rx_bcast_bytes += HILO_64_REGPAIR(ustats.rcv_bcast_bytes); - p_stats->rx_ucast_pkts += HILO_64_REGPAIR(ustats.rcv_ucast_pkts); - p_stats->rx_mcast_pkts += HILO_64_REGPAIR(ustats.rcv_mcast_pkts); - p_stats->rx_bcast_pkts += HILO_64_REGPAIR(ustats.rcv_bcast_pkts); + p_stats->common.rx_ucast_bytes += + HILO_64_REGPAIR(ustats.rcv_ucast_bytes); + p_stats->common.rx_mcast_bytes += + HILO_64_REGPAIR(ustats.rcv_mcast_bytes); + p_stats->common.rx_bcast_bytes += + HILO_64_REGPAIR(ustats.rcv_bcast_bytes); + p_stats->common.rx_ucast_pkts += HILO_64_REGPAIR(ustats.rcv_ucast_pkts); + p_stats->common.rx_mcast_pkts += HILO_64_REGPAIR(ustats.rcv_mcast_pkts); + p_stats->common.rx_bcast_pkts += HILO_64_REGPAIR(ustats.rcv_bcast_pkts); } static void __qed_get_vport_mstats_addrlen(struct qed_hwfn *p_hwfn, @@ -1578,23 +1588,26 @@ static void __qed_get_vport_mstats(struct qed_hwfn *p_hwfn, memset(&mstats, 0, sizeof(mstats)); qed_memcpy_from(p_hwfn, p_ptt, &mstats, mstats_addr, mstats_len); - p_stats->no_buff_discards += HILO_64_REGPAIR(mstats.no_buff_discard); - p_stats->packet_too_big_discard += - HILO_64_REGPAIR(mstats.packet_too_big_discard); - p_stats->ttl0_discard += HILO_64_REGPAIR(mstats.ttl0_discard); - p_stats->tpa_coalesced_pkts += - HILO_64_REGPAIR(mstats.tpa_coalesced_pkts); - p_stats->tpa_coalesced_events += - HILO_64_REGPAIR(mstats.tpa_coalesced_events); - p_stats->tpa_aborts_num += HILO_64_REGPAIR(mstats.tpa_aborts_num); - p_stats->tpa_coalesced_bytes += - HILO_64_REGPAIR(mstats.tpa_coalesced_bytes); + p_stats->common.no_buff_discards += + HILO_64_REGPAIR(mstats.no_buff_discard); + p_stats->common.packet_too_big_discard += + HILO_64_REGPAIR(mstats.packet_too_big_discard); + p_stats->common.ttl0_discard += HILO_64_REGPAIR(mstats.ttl0_discard); + p_stats->common.tpa_coalesced_pkts += + HILO_64_REGPAIR(mstats.tpa_coalesced_pkts); + p_stats->common.tpa_coalesced_events += + HILO_64_REGPAIR(mstats.tpa_coalesced_events); + p_stats->common.tpa_aborts_num += + HILO_64_REGPAIR(mstats.tpa_aborts_num); + p_stats->common.tpa_coalesced_bytes += + HILO_64_REGPAIR(mstats.tpa_coalesced_bytes); } static void __qed_get_vport_port_stats(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, struct qed_eth_stats *p_stats) { + struct qed_eth_stats_common *p_common = &p_stats->common; struct port_stats port_stats; int j; @@ -1605,54 +1618,75 @@ static void __qed_get_vport_port_stats(struct qed_hwfn *p_hwfn, offsetof(struct public_port, stats), sizeof(port_stats)); - p_stats->rx_64_byte_packets += port_stats.eth.r64; - p_stats->rx_65_to_127_byte_packets += port_stats.eth.r127; - p_stats->rx_128_to_255_byte_packets += port_stats.eth.r255; - p_stats->rx_256_to_511_byte_packets += port_stats.eth.r511; - p_stats->rx_512_to_1023_byte_packets += port_stats.eth.r1023; - p_stats->rx_1024_to_1518_byte_packets += port_stats.eth.r1518; - p_stats->rx_1519_to_1522_byte_packets += port_stats.eth.r1522; - p_stats->rx_1519_to_2047_byte_packets += port_stats.eth.r2047; - p_stats->rx_2048_to_4095_byte_packets += port_stats.eth.r4095; - p_stats->rx_4096_to_9216_byte_packets += port_stats.eth.r9216; - p_stats->rx_9217_to_16383_byte_packets += port_stats.eth.r16383; - p_stats->rx_crc_errors += port_stats.eth.rfcs; - p_stats->rx_mac_crtl_frames += port_stats.eth.rxcf; - p_stats->rx_pause_frames += port_stats.eth.rxpf; - p_stats->rx_pfc_frames += port_stats.eth.rxpp; - p_stats->rx_align_errors += port_stats.eth.raln; - p_stats->rx_carrier_errors += port_stats.eth.rfcr; - p_stats->rx_oversize_packets += port_stats.eth.rovr; - p_stats->rx_jabbers += port_stats.eth.rjbr; - p_stats->rx_undersize_packets += port_stats.eth.rund; - p_stats->rx_fragments += port_stats.eth.rfrg; - p_stats->tx_64_byte_packets += port_stats.eth.t64; - p_stats->tx_65_to_127_byte_packets += port_stats.eth.t127; - p_stats->tx_128_to_255_byte_packets += port_stats.eth.t255; - p_stats->tx_256_to_511_byte_packets += port_stats.eth.t511; - p_stats->tx_512_to_1023_byte_packets += port_stats.eth.t1023; - p_stats->tx_1024_to_1518_byte_packets += port_stats.eth.t1518; - p_stats->tx_1519_to_2047_byte_packets += port_stats.eth.t2047; - p_stats->tx_2048_to_4095_byte_packets += port_stats.eth.t4095; - p_stats->tx_4096_to_9216_byte_packets += port_stats.eth.t9216; - p_stats->tx_9217_to_16383_byte_packets += port_stats.eth.t16383; - p_stats->tx_pause_frames += port_stats.eth.txpf; - p_stats->tx_pfc_frames += port_stats.eth.txpp; - p_stats->tx_lpi_entry_count += port_stats.eth.tlpiec; - p_stats->tx_total_collisions += port_stats.eth.tncl; - p_stats->rx_mac_bytes += port_stats.eth.rbyte; - p_stats->rx_mac_uc_packets += port_stats.eth.rxuca; - p_stats->rx_mac_mc_packets += port_stats.eth.rxmca; - p_stats->rx_mac_bc_packets += port_stats.eth.rxbca; - p_stats->rx_mac_frames_ok += port_stats.eth.rxpok; - p_stats->tx_mac_bytes += port_stats.eth.tbyte; - p_stats->tx_mac_uc_packets += port_stats.eth.txuca; - p_stats->tx_mac_mc_packets += port_stats.eth.txmca; - p_stats->tx_mac_bc_packets += port_stats.eth.txbca; - p_stats->tx_mac_ctrl_frames += port_stats.eth.txcf; + p_common->rx_64_byte_packets += port_stats.eth.r64; + p_common->rx_65_to_127_byte_packets += port_stats.eth.r127; + p_common->rx_128_to_255_byte_packets += port_stats.eth.r255; + p_common->rx_256_to_511_byte_packets += port_stats.eth.r511; + p_common->rx_512_to_1023_byte_packets += port_stats.eth.r1023; + p_common->rx_1024_to_1518_byte_packets += port_stats.eth.r1518; + p_common->rx_crc_errors += port_stats.eth.rfcs; + p_common->rx_mac_crtl_frames += port_stats.eth.rxcf; + p_common->rx_pause_frames += port_stats.eth.rxpf; + p_common->rx_pfc_frames += port_stats.eth.rxpp; + p_common->rx_align_errors += port_stats.eth.raln; + p_common->rx_carrier_errors += port_stats.eth.rfcr; + p_common->rx_oversize_packets += port_stats.eth.rovr; + p_common->rx_jabbers += port_stats.eth.rjbr; + p_common->rx_undersize_packets += port_stats.eth.rund; + p_common->rx_fragments += port_stats.eth.rfrg; + p_common->tx_64_byte_packets += port_stats.eth.t64; + p_common->tx_65_to_127_byte_packets += port_stats.eth.t127; + p_common->tx_128_to_255_byte_packets += port_stats.eth.t255; + p_common->tx_256_to_511_byte_packets += port_stats.eth.t511; + p_common->tx_512_to_1023_byte_packets += port_stats.eth.t1023; + p_common->tx_1024_to_1518_byte_packets += port_stats.eth.t1518; + p_common->tx_pause_frames += port_stats.eth.txpf; + p_common->tx_pfc_frames += port_stats.eth.txpp; + p_common->rx_mac_bytes += port_stats.eth.rbyte; + p_common->rx_mac_uc_packets += port_stats.eth.rxuca; + p_common->rx_mac_mc_packets += port_stats.eth.rxmca; + p_common->rx_mac_bc_packets += port_stats.eth.rxbca; + p_common->rx_mac_frames_ok += port_stats.eth.rxpok; + p_common->tx_mac_bytes += port_stats.eth.tbyte; + p_common->tx_mac_uc_packets += port_stats.eth.txuca; + p_common->tx_mac_mc_packets += port_stats.eth.txmca; + p_common->tx_mac_bc_packets += port_stats.eth.txbca; + p_common->tx_mac_ctrl_frames += port_stats.eth.txcf; for (j = 0; j < 8; j++) { - p_stats->brb_truncates += port_stats.brb.brb_truncate[j]; - p_stats->brb_discards += port_stats.brb.brb_discard[j]; + p_common->brb_truncates += port_stats.brb.brb_truncate[j]; + p_common->brb_discards += port_stats.brb.brb_discard[j]; + } + + if (QED_IS_BB(p_hwfn->cdev)) { + struct qed_eth_stats_bb *p_bb = &p_stats->bb; + + p_bb->rx_1519_to_1522_byte_packets += + port_stats.eth.u0.bb0.r1522; + p_bb->rx_1519_to_2047_byte_packets += + port_stats.eth.u0.bb0.r2047; + p_bb->rx_2048_to_4095_byte_packets += + port_stats.eth.u0.bb0.r4095; + p_bb->rx_4096_to_9216_byte_packets += + port_stats.eth.u0.bb0.r9216; + p_bb->rx_9217_to_16383_byte_packets += + port_stats.eth.u0.bb0.r16383; + p_bb->tx_1519_to_2047_byte_packets += + port_stats.eth.u1.bb1.t2047; + p_bb->tx_2048_to_4095_byte_packets += + port_stats.eth.u1.bb1.t4095; + p_bb->tx_4096_to_9216_byte_packets += + port_stats.eth.u1.bb1.t9216; + p_bb->tx_9217_to_16383_byte_packets += + port_stats.eth.u1.bb1.t16383; + p_bb->tx_lpi_entry_count += port_stats.eth.u2.bb2.tlpiec; + p_bb->tx_total_collisions += port_stats.eth.u2.bb2.tncl; + } else { + struct qed_eth_stats_ah *p_ah = &p_stats->ah; + + p_ah->rx_1519_to_max_byte_packets += + port_stats.eth.u0.ah0.r1519_to_max; + p_ah->tx_1519_to_max_byte_packets = + port_stats.eth.u1.ah1.t1519_to_max; } } diff --git a/drivers/net/ethernet/qlogic/qed/qed_ll2.c b/drivers/net/ethernet/qlogic/qed/qed_ll2.c index 9a0b9af10a57..178650aa0c6c 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_ll2.c +++ b/drivers/net/ethernet/qlogic/qed/qed_ll2.c @@ -211,6 +211,8 @@ static void qed_ll2b_complete_rx_packet(struct qed_hwfn *p_hwfn, /* If need to reuse or there's no replacement buffer, repost this */ if (rc) goto out_post; + dma_unmap_single(&cdev->pdev->dev, buffer->phys_addr, + cdev->ll2->rx_size, DMA_FROM_DEVICE); skb = build_skb(buffer->data, 0); if (!skb) { @@ -474,7 +476,7 @@ qed_ll2_rxq_completion_gsi(struct qed_hwfn *p_hwfn, static int qed_ll2_rxq_completion_reg(struct qed_hwfn *p_hwfn, struct qed_ll2_info *p_ll2_conn, union core_rx_cqe_union *p_cqe, - unsigned long lock_flags, + unsigned long *p_lock_flags, bool b_last_cqe) { struct qed_ll2_rx_queue *p_rx = &p_ll2_conn->rx_queue; @@ -495,10 +497,10 @@ static int qed_ll2_rxq_completion_reg(struct qed_hwfn *p_hwfn, "Mismatch between active_descq and the LL2 Rx chain\n"); list_add_tail(&p_pkt->list_entry, &p_rx->free_descq); - spin_unlock_irqrestore(&p_rx->lock, lock_flags); + spin_unlock_irqrestore(&p_rx->lock, *p_lock_flags); qed_ll2b_complete_rx_packet(p_hwfn, p_ll2_conn->my_id, p_pkt, &p_cqe->rx_cqe_fp, b_last_cqe); - spin_lock_irqsave(&p_rx->lock, lock_flags); + spin_lock_irqsave(&p_rx->lock, *p_lock_flags); return 0; } @@ -538,7 +540,8 @@ static int qed_ll2_rxq_completion(struct qed_hwfn *p_hwfn, void *cookie) break; case CORE_RX_CQE_TYPE_REGULAR: rc = qed_ll2_rxq_completion_reg(p_hwfn, p_ll2_conn, - cqe, flags, b_last_cqe); + cqe, &flags, + b_last_cqe); break; default: rc = -EIO; @@ -594,7 +597,7 @@ static u8 qed_ll2_convert_rx_parse_to_tx_flags(u16 parse_flags) u8 bd_flags = 0; if (GET_FIELD(parse_flags, PARSING_AND_ERR_FLAGS_TAG8021QEXIST)) - SET_FIELD(bd_flags, CORE_TX_BD_FLAGS_VLAN_INSERTION, 1); + SET_FIELD(bd_flags, CORE_TX_BD_DATA_VLAN_INSERTION, 1); return bd_flags; } @@ -755,8 +758,8 @@ qed_ooo_submit_tx_buffers(struct qed_hwfn *p_hwfn, p_buffer->placement_offset; parse_flags = p_buffer->parse_flags; bd_flags = qed_ll2_convert_rx_parse_to_tx_flags(parse_flags); - SET_FIELD(bd_flags, CORE_TX_BD_FLAGS_FORCE_VLAN_MODE, 1); - SET_FIELD(bd_flags, CORE_TX_BD_FLAGS_L4_PROTOCOL, 1); + SET_FIELD(bd_flags, CORE_TX_BD_DATA_FORCE_VLAN_MODE, 1); + SET_FIELD(bd_flags, CORE_TX_BD_DATA_L4_PROTOCOL, 1); rc = qed_ll2_prepare_tx_packet(p_hwfn, p_ll2_conn->my_id, 1, p_buffer->vlan, bd_flags, @@ -968,7 +971,7 @@ static int qed_ll2_start_ooo(struct qed_dev *cdev, { struct qed_hwfn *hwfn = QED_LEADING_HWFN(cdev); u8 *handle = &hwfn->pf_params.iscsi_pf_params.ll2_ooo_queue_id; - struct qed_ll2_conn ll2_info; + struct qed_ll2_conn ll2_info = { 0 }; int rc; ll2_info.conn_type = QED_LL2_TYPE_ISCSI_OOO; @@ -1588,33 +1591,34 @@ static void qed_ll2_prepare_tx_packet_set(struct qed_hwfn *p_hwfn, p_tx->cur_send_frag_num++; } -static void qed_ll2_prepare_tx_packet_set_bd(struct qed_hwfn *p_hwfn, - struct qed_ll2_info *p_ll2, - struct qed_ll2_tx_packet *p_curp, - u8 num_of_bds, - enum core_tx_dest tx_dest, - u16 vlan, - u8 bd_flags, - u16 l4_hdr_offset_w, - enum core_roce_flavor_type type, - dma_addr_t first_frag, - u16 first_frag_len) +static void +qed_ll2_prepare_tx_packet_set_bd(struct qed_hwfn *p_hwfn, + struct qed_ll2_info *p_ll2, + struct qed_ll2_tx_packet *p_curp, + u8 num_of_bds, + enum core_tx_dest tx_dest, + u16 vlan, + u8 bd_flags, + u16 l4_hdr_offset_w, + enum core_roce_flavor_type roce_flavor, + dma_addr_t first_frag, + u16 first_frag_len) { struct qed_chain *p_tx_chain = &p_ll2->tx_queue.txq_chain; u16 prod_idx = qed_chain_get_prod_idx(p_tx_chain); struct core_tx_bd *start_bd = NULL; - u16 frag_idx; + u16 bd_data = 0, frag_idx; start_bd = (struct core_tx_bd *)qed_chain_produce(p_tx_chain); start_bd->nw_vlan_or_lb_echo = cpu_to_le16(vlan); SET_FIELD(start_bd->bitfield1, CORE_TX_BD_L4_HDR_OFFSET_W, cpu_to_le16(l4_hdr_offset_w)); SET_FIELD(start_bd->bitfield1, CORE_TX_BD_TX_DST, tx_dest); - start_bd->bd_flags.as_bitfield = bd_flags; - start_bd->bd_flags.as_bitfield |= CORE_TX_BD_FLAGS_START_BD_MASK << - CORE_TX_BD_FLAGS_START_BD_SHIFT; - SET_FIELD(start_bd->bitfield0, CORE_TX_BD_NBDS, num_of_bds); - SET_FIELD(start_bd->bitfield0, CORE_TX_BD_ROCE_FLAV, type); + bd_data |= bd_flags; + SET_FIELD(bd_data, CORE_TX_BD_DATA_START_BD, 0x1); + SET_FIELD(bd_data, CORE_TX_BD_DATA_NBDS, num_of_bds); + SET_FIELD(bd_data, CORE_TX_BD_DATA_ROCE_FLAV, roce_flavor); + start_bd->bd_data.as_bitfield = cpu_to_le16(bd_data); DMA_REGPAIR_LE(start_bd->addr, first_frag); start_bd->nbytes = cpu_to_le16(first_frag_len); @@ -1639,9 +1643,8 @@ static void qed_ll2_prepare_tx_packet_set_bd(struct qed_hwfn *p_hwfn, struct core_tx_bd **p_bd = &p_curp->bds_set[frag_idx].txq_bd; *p_bd = (struct core_tx_bd *)qed_chain_produce(p_tx_chain); - (*p_bd)->bd_flags.as_bitfield = 0; + (*p_bd)->bd_data.as_bitfield = 0; (*p_bd)->bitfield1 = 0; - (*p_bd)->bitfield0 = 0; p_curp->bds_set[frag_idx].tx_frag = 0; p_curp->bds_set[frag_idx].frag_len = 0; } @@ -2238,11 +2241,11 @@ static int qed_ll2_start_xmit(struct qed_dev *cdev, struct sk_buff *skb) /* Request HW to calculate IP csum */ if (!((vlan_get_protocol(skb) == htons(ETH_P_IPV6)) && ipv6_hdr(skb)->nexthdr == NEXTHDR_IPV6)) - flags |= BIT(CORE_TX_BD_FLAGS_IP_CSUM_SHIFT); + flags |= BIT(CORE_TX_BD_DATA_IP_CSUM_SHIFT); if (skb_vlan_tag_present(skb)) { vlan = skb_vlan_tag_get(skb); - flags |= BIT(CORE_TX_BD_FLAGS_VLAN_INSERTION_SHIFT); + flags |= BIT(CORE_TX_BD_DATA_VLAN_INSERTION_SHIFT); } rc = qed_ll2_prepare_tx_packet(QED_LEADING_HWFN(cdev), diff --git a/drivers/net/ethernet/qlogic/qed/qed_main.c b/drivers/net/ethernet/qlogic/qed/qed_main.c index eef30a598b40..766c6f39ea63 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_main.c +++ b/drivers/net/ethernet/qlogic/qed/qed_main.c @@ -238,6 +238,7 @@ int qed_fill_dev_info(struct qed_dev *cdev, dev_info->rdma_supported = (cdev->hwfns[0].hw_info.personality == QED_PCI_ETH_ROCE); dev_info->is_mf_default = IS_MF_DEFAULT(&cdev->hwfns[0]); + dev_info->dev_type = cdev->type; ether_addr_copy(dev_info->hw_mac, cdev->hwfns[0].hw_info.hw_mac_addr); if (IS_PF(cdev)) { @@ -1653,8 +1654,10 @@ void qed_get_protocol_stats(struct qed_dev *cdev, switch (type) { case QED_MCP_LAN_STATS: qed_get_vport_stats(cdev, ð_stats); - stats->lan_stats.ucast_rx_pkts = eth_stats.rx_ucast_pkts; - stats->lan_stats.ucast_tx_pkts = eth_stats.tx_ucast_pkts; + stats->lan_stats.ucast_rx_pkts = + eth_stats.common.rx_ucast_pkts; + stats->lan_stats.ucast_tx_pkts = + eth_stats.common.tx_ucast_pkts; stats->lan_stats.fcs_err = -1; break; case QED_MCP_FCOE_STATS: diff --git a/drivers/net/ethernet/qlogic/qed/qed_mcp.h b/drivers/net/ethernet/qlogic/qed/qed_mcp.h index 368e88de146c..bdbfd6d4485e 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_mcp.h +++ b/drivers/net/ethernet/qlogic/qed/qed_mcp.h @@ -479,11 +479,10 @@ int qed_mcp_bist_nvm_test_get_image_att(struct qed_hwfn *p_hwfn, rel_pfid) #define MCP_PF_ID(p_hwfn) MCP_PF_ID_BY_REL(p_hwfn, (p_hwfn)->rel_pf_id) -/* TODO - this is only correct as long as only BB is supported, and - * no port-swapping is implemented; Afterwards we'll need to fix it. - */ -#define MFW_PORT(_p_hwfn) ((_p_hwfn)->abs_pf_id % \ - ((_p_hwfn)->cdev->num_ports_in_engines * 2)) +#define MFW_PORT(_p_hwfn) ((_p_hwfn)->abs_pf_id % \ + ((_p_hwfn)->cdev->num_ports_in_engines * \ + qed_device_num_engines((_p_hwfn)->cdev))) + struct qed_mcp_info { /* Spinlock used for protecting the access to the MFW mailbox */ spinlock_t lock; diff --git a/drivers/net/ethernet/qlogic/qed/qed_ooo.c b/drivers/net/ethernet/qlogic/qed/qed_ooo.c index 7d731c6cb892..378afce58b3f 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_ooo.c +++ b/drivers/net/ethernet/qlogic/qed/qed_ooo.c @@ -159,6 +159,8 @@ struct qed_ooo_info *qed_ooo_alloc(struct qed_hwfn *p_hwfn) if (!p_ooo_info->ooo_history.p_cqes) goto no_history_mem; + p_ooo_info->ooo_history.num_of_cqes = QED_MAX_NUM_OOO_HISTORY_ENTRIES; + return p_ooo_info; no_history_mem: diff --git a/drivers/net/ethernet/qlogic/qed/qed_ptp.c b/drivers/net/ethernet/qlogic/qed/qed_ptp.c index d27aa85da23c..80c9c0b172dd 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_ptp.c +++ b/drivers/net/ethernet/qlogic/qed/qed_ptp.c @@ -262,12 +262,20 @@ static int qed_ptp_hw_enable(struct qed_dev *cdev) qed_wr(p_hwfn, p_ptt, NIG_REG_TS_OUTPUT_ENABLE_PDA, 0x1); /* Pause free running counter */ - qed_wr(p_hwfn, p_ptt, NIG_REG_TIMESYNC_GEN_REG_BB, 2); + if (QED_IS_BB_B0(p_hwfn->cdev)) + qed_wr(p_hwfn, p_ptt, NIG_REG_TIMESYNC_GEN_REG_BB, 2); + if (QED_IS_AH(p_hwfn->cdev)) + qed_wr(p_hwfn, p_ptt, NIG_REG_TSGEN_FREECNT_UPDATE_K2, 2); qed_wr(p_hwfn, p_ptt, NIG_REG_TSGEN_FREE_CNT_VALUE_LSB, 0); qed_wr(p_hwfn, p_ptt, NIG_REG_TSGEN_FREE_CNT_VALUE_MSB, 0); /* Resume free running counter */ - qed_wr(p_hwfn, p_ptt, NIG_REG_TIMESYNC_GEN_REG_BB, 4); + if (QED_IS_BB_B0(p_hwfn->cdev)) + qed_wr(p_hwfn, p_ptt, NIG_REG_TIMESYNC_GEN_REG_BB, 4); + if (QED_IS_AH(p_hwfn->cdev)) { + qed_wr(p_hwfn, p_ptt, NIG_REG_TSGEN_FREECNT_UPDATE_K2, 4); + qed_wr(p_hwfn, p_ptt, NIG_REG_PTP_LATCH_OSTS_PKT_TIME, 1); + } /* Disable drift register */ qed_wr(p_hwfn, p_ptt, NIG_REG_TSGEN_DRIFT_CNTR_CONF, 0x0); diff --git a/drivers/net/ethernet/qlogic/qed/qed_reg_addr.h b/drivers/net/ethernet/qlogic/qed/qed_reg_addr.h index d59d9df60cd2..6d4ac7e2ee83 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_reg_addr.h +++ b/drivers/net/ethernet/qlogic/qed/qed_reg_addr.h @@ -160,13 +160,13 @@ 0x2e0704UL #define CCFC_REG_STRONG_ENABLE_PF \ 0x2e0708UL -#define PGLUE_B_REG_PGL_ADDR_88_F0 \ +#define PGLUE_B_REG_PGL_ADDR_88_F0_BB \ 0x2aa404UL -#define PGLUE_B_REG_PGL_ADDR_8C_F0 \ +#define PGLUE_B_REG_PGL_ADDR_8C_F0_BB \ 0x2aa408UL -#define PGLUE_B_REG_PGL_ADDR_90_F0 \ +#define PGLUE_B_REG_PGL_ADDR_90_F0_BB \ 0x2aa40cUL -#define PGLUE_B_REG_PGL_ADDR_94_F0 \ +#define PGLUE_B_REG_PGL_ADDR_94_F0_BB \ 0x2aa410UL #define PGLUE_B_REG_WAS_ERROR_PF_31_0_CLR \ 0x2aa138UL @@ -356,6 +356,10 @@ 0x238804UL #define RDIF_REG_STOP_ON_ERROR \ 0x300040UL +#define RDIF_REG_DEBUG_ERROR_INFO \ + 0x300400UL +#define RDIF_REG_DEBUG_ERROR_INFO_SIZE \ + 64 #define SRC_REG_SOFT_RST \ 0x23874cUL #define TCFC_REG_ACTIVITY_COUNTER \ @@ -370,6 +374,10 @@ 0x1700004UL #define TDIF_REG_STOP_ON_ERROR \ 0x310040UL +#define TDIF_REG_DEBUG_ERROR_INFO \ + 0x310400UL +#define TDIF_REG_DEBUG_ERROR_INFO_SIZE \ + 64 #define UCM_REG_INIT \ 0x1280000UL #define UMAC_REG_IPG_HD_BKP_CNTL_BB_B0 \ @@ -1236,6 +1244,26 @@ 0x1901534UL #define USEM_REG_DBG_FORCE_FRAME \ 0x1901538UL +#define NWS_REG_DBG_SELECT \ + 0x700128UL +#define NWS_REG_DBG_DWORD_ENABLE \ + 0x70012cUL +#define NWS_REG_DBG_SHIFT \ + 0x700130UL +#define NWS_REG_DBG_FORCE_VALID \ + 0x700134UL +#define NWS_REG_DBG_FORCE_FRAME \ + 0x700138UL +#define MS_REG_DBG_SELECT \ + 0x6a0228UL +#define MS_REG_DBG_DWORD_ENABLE \ + 0x6a022cUL +#define MS_REG_DBG_SHIFT \ + 0x6a0230UL +#define MS_REG_DBG_FORCE_VALID \ + 0x6a0234UL +#define MS_REG_DBG_FORCE_FRAME \ + 0x6a0238UL #define PCIE_REG_DBG_COMMON_SELECT \ 0x054398UL #define PCIE_REG_DBG_COMMON_DWORD_ENABLE \ @@ -1448,6 +1476,8 @@ 0x000b48UL #define RSS_REG_RSS_RAM_DATA \ 0x238c20UL +#define RSS_REG_RSS_RAM_DATA_SIZE \ + 4 #define MISC_REG_BLOCK_256B_EN \ 0x008c14UL #define NWS_REG_NWS_CMU \ @@ -1520,4 +1550,13 @@ #define NIG_REG_TIMESYNC_GEN_REG_BB 0x500d00UL #define NIG_REG_TSGEN_FREE_CNT_VALUE_LSB 0x5088a8UL #define NIG_REG_TSGEN_FREE_CNT_VALUE_MSB 0x5088acUL +#define NIG_REG_PTP_LATCH_OSTS_PKT_TIME 0x509040UL + +#define PGLUE_B_REG_PGL_ADDR_E8_F0_K2 0x2aaf98UL +#define PGLUE_B_REG_PGL_ADDR_EC_F0_K2 0x2aaf9cUL +#define PGLUE_B_REG_PGL_ADDR_F0_F0_K2 0x2aafa0UL +#define PGLUE_B_REG_PGL_ADDR_F4_F0_K2 0x2aafa4UL +#define NIG_REG_TSGEN_FREECNT_UPDATE_K2 0x509008UL +#define CNIG_REG_NIG_PORT0_CONF_K2 0x218200UL + #endif diff --git a/drivers/net/ethernet/qlogic/qed/qed_roce.c b/drivers/net/ethernet/qlogic/qed/qed_roce.c index d9ff6b28591c..4bef5c59627c 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_roce.c +++ b/drivers/net/ethernet/qlogic/qed/qed_roce.c @@ -66,13 +66,27 @@ #include "qed_roce.h" #include "qed_ll2.h" -void qed_async_roce_event(struct qed_hwfn *p_hwfn, - struct event_ring_entry *p_eqe) +static void qed_roce_free_real_icid(struct qed_hwfn *p_hwfn, u16 icid); + +void qed_roce_async_event(struct qed_hwfn *p_hwfn, + u8 fw_event_code, union rdma_eqe_data *rdma_data) { - struct qed_rdma_info *p_rdma_info = p_hwfn->p_rdma_info; + if (fw_event_code == ROCE_ASYNC_EVENT_DESTROY_QP_DONE) { + u16 icid = + (u16)le32_to_cpu(rdma_data->rdma_destroy_qp_data.cid); + + /* icid release in this async event can occur only if the icid + * was offloaded to the FW. In case it wasn't offloaded this is + * handled in qed_roce_sp_destroy_qp. + */ + qed_roce_free_real_icid(p_hwfn, icid); + } else { + struct qed_rdma_events *events = &p_hwfn->p_rdma_info->events; - p_rdma_info->events.affiliated_event(p_rdma_info->events.context, - p_eqe->opcode, &p_eqe->data); + events->affiliated_event(p_hwfn->p_rdma_info->events.context, + fw_event_code, + &rdma_data->async_handle); + } } static int qed_rdma_bmap_alloc(struct qed_hwfn *p_hwfn, @@ -113,6 +127,15 @@ static int qed_rdma_bmap_alloc_id(struct qed_hwfn *p_hwfn, return 0; } +static void qed_bmap_set_id(struct qed_hwfn *p_hwfn, + struct qed_bmap *bmap, u32 id_num) +{ + if (id_num >= bmap->max_count) + return; + + __set_bit(id_num, bmap->bitmap); +} + static void qed_bmap_release_id(struct qed_hwfn *p_hwfn, struct qed_bmap *bmap, u32 id_num) { @@ -129,6 +152,15 @@ static void qed_bmap_release_id(struct qed_hwfn *p_hwfn, } } +static int qed_bmap_test_id(struct qed_hwfn *p_hwfn, + struct qed_bmap *bmap, u32 id_num) +{ + if (id_num >= bmap->max_count) + return -1; + + return test_bit(id_num, bmap->bitmap); +} + static u32 qed_rdma_get_sb_id(void *p_hwfn, u32 rel_sb_id) { /* First sb id for RoCE is after all the l2 sb */ @@ -170,7 +202,8 @@ static int qed_rdma_alloc(struct qed_hwfn *p_hwfn, /* Queue zone lines are shared between RoCE and L2 in such a way that * they can be used by each without obstructing the other. */ - p_rdma_info->queue_zone_base = (u16)FEAT_NUM(p_hwfn, QED_L2_QUEUE); + p_rdma_info->queue_zone_base = (u16)RESC_START(p_hwfn, QED_L2_QUEUE); + p_rdma_info->max_queue_zones = (u16)RESC_NUM(p_hwfn, QED_L2_QUEUE); /* Allocate a struct with device params and fill it */ p_rdma_info->dev = kzalloc(sizeof(*p_rdma_info->dev), GFP_KERNEL); @@ -248,9 +281,18 @@ static int qed_rdma_alloc(struct qed_hwfn *p_hwfn, goto free_tid_map; } + /* Allocate bitmap for cids used for responders/requesters. */ + rc = qed_rdma_bmap_alloc(p_hwfn, &p_rdma_info->real_cid_map, num_cons); + if (rc) { + DP_VERBOSE(p_hwfn, QED_MSG_RDMA, + "Failed to allocate real cid bitmap, rc = %d\n", rc); + goto free_cid_map; + } DP_VERBOSE(p_hwfn, QED_MSG_RDMA, "Allocation successful\n"); return 0; +free_cid_map: + kfree(p_rdma_info->cid_map.bitmap); free_tid_map: kfree(p_rdma_info->tid_map.bitmap); free_toggle_map: @@ -273,7 +315,22 @@ free_rdma_info: static void qed_rdma_resc_free(struct qed_hwfn *p_hwfn) { + struct qed_bmap *rcid_map = &p_hwfn->p_rdma_info->real_cid_map; struct qed_rdma_info *p_rdma_info = p_hwfn->p_rdma_info; + int wait_count = 0; + + /* when destroying a_RoCE QP the control is returned to the user after + * the synchronous part. The asynchronous part may take a little longer. + * We delay for a short while if an async destroy QP is still expected. + * Beyond the added delay we clear the bitmap anyway. + */ + while (bitmap_weight(rcid_map->bitmap, rcid_map->max_count)) { + msleep(100); + if (wait_count++ > 20) { + DP_NOTICE(p_hwfn, "cid bitmap wait timed out\n"); + break; + } + } kfree(p_rdma_info->cid_map.bitmap); kfree(p_rdma_info->tid_map.bitmap); @@ -724,6 +781,14 @@ static void qed_rdma_cnq_prod_update(void *rdma_cxt, u8 qz_offset, u16 prod) u32 addr; p_hwfn = (struct qed_hwfn *)rdma_cxt; + + if (qz_offset > p_hwfn->p_rdma_info->max_queue_zones) { + DP_NOTICE(p_hwfn, + "queue zone offset %d is too large (max is %d)\n", + qz_offset, p_hwfn->p_rdma_info->max_queue_zones); + return; + } + qz_num = p_hwfn->p_rdma_info->queue_zone_base + qz_offset; addr = GTT_BAR0_MAP_REG_USDM_RAM + USTORM_COMMON_QUEUE_CONS_OFFSET(qz_num); @@ -1080,6 +1145,14 @@ static enum roce_flavor qed_roce_mode_to_flavor(enum roce_mode roce_mode) return flavor; } +void qed_roce_free_cid_pair(struct qed_hwfn *p_hwfn, u16 cid) +{ + spin_lock_bh(&p_hwfn->p_rdma_info->lock); + qed_bmap_release_id(p_hwfn, &p_hwfn->p_rdma_info->cid_map, cid); + qed_bmap_release_id(p_hwfn, &p_hwfn->p_rdma_info->cid_map, cid + 1); + spin_unlock_bh(&p_hwfn->p_rdma_info->lock); +} + static int qed_roce_alloc_cid(struct qed_hwfn *p_hwfn, u16 *cid) { struct qed_rdma_info *p_rdma_info = p_hwfn->p_rdma_info; @@ -1139,6 +1212,13 @@ err: return rc; } +static void qed_roce_set_real_cid(struct qed_hwfn *p_hwfn, u32 cid) +{ + spin_lock_bh(&p_hwfn->p_rdma_info->lock); + qed_bmap_set_id(p_hwfn, &p_hwfn->p_rdma_info->real_cid_map, cid); + spin_unlock_bh(&p_hwfn->p_rdma_info->lock); +} + static int qed_roce_sp_create_responder(struct qed_hwfn *p_hwfn, struct qed_rdma_qp *qp) { @@ -1147,7 +1227,8 @@ static int qed_roce_sp_create_responder(struct qed_hwfn *p_hwfn, union qed_qm_pq_params qm_params; enum roce_flavor roce_flavor; struct qed_spq_entry *p_ent; - u16 physical_queue0 = 0; + u16 regular_latency_queue; + enum protocol_type proto; int rc; DP_VERBOSE(p_hwfn, QED_MSG_RDMA, "icid = %08x\n", qp->icid); @@ -1229,15 +1310,19 @@ static int qed_roce_sp_create_responder(struct qed_hwfn *p_hwfn, p_ramrod->qp_handle_for_async.lo = cpu_to_le32(qp->qp_handle_async.lo); p_ramrod->qp_handle_for_cqe.hi = cpu_to_le32(qp->qp_handle.hi); p_ramrod->qp_handle_for_cqe.lo = cpu_to_le32(qp->qp_handle.lo); - p_ramrod->stats_counter_id = p_hwfn->rel_pf_id; p_ramrod->cq_cid = cpu_to_le32((p_hwfn->hw_info.opaque_fid << 16) | qp->rq_cq_id); memset(&qm_params, 0, sizeof(qm_params)); qm_params.roce.qpid = qp->icid >> 1; - physical_queue0 = qed_get_qm_pq(p_hwfn, PROTOCOLID_ROCE, &qm_params); + regular_latency_queue = qed_get_qm_pq(p_hwfn, PROTOCOLID_ROCE, + &qm_params); + + p_ramrod->regular_latency_phy_queue = + cpu_to_le16(regular_latency_queue); + p_ramrod->low_latency_phy_queue = + cpu_to_le16(regular_latency_queue); - p_ramrod->physical_queue0 = cpu_to_le16(physical_queue0); p_ramrod->dpi = cpu_to_le16(qp->dpi); qed_rdma_set_fw_mac(p_ramrod->remote_mac_addr, qp->remote_mac_addr); @@ -1253,13 +1338,19 @@ static int qed_roce_sp_create_responder(struct qed_hwfn *p_hwfn, rc = qed_spq_post(p_hwfn, p_ent, NULL); - DP_VERBOSE(p_hwfn, QED_MSG_RDMA, "rc = %d physical_queue0 = 0x%x\n", - rc, physical_queue0); + DP_VERBOSE(p_hwfn, QED_MSG_RDMA, + "rc = %d regular physical queue = 0x%x\n", rc, + regular_latency_queue); if (rc) goto err; qp->resp_offloaded = true; + qp->cq_prod = 0; + + proto = p_hwfn->p_rdma_info->proto; + qed_roce_set_real_cid(p_hwfn, qp->icid - + qed_cxt_get_proto_cid_start(p_hwfn, proto)); return rc; @@ -1280,7 +1371,8 @@ static int qed_roce_sp_create_requester(struct qed_hwfn *p_hwfn, union qed_qm_pq_params qm_params; enum roce_flavor roce_flavor; struct qed_spq_entry *p_ent; - u16 physical_queue0 = 0; + u16 regular_latency_queue; + enum protocol_type proto; int rc; DP_VERBOSE(p_hwfn, QED_MSG_RDMA, "icid = %08x\n", qp->icid); @@ -1351,15 +1443,19 @@ static int qed_roce_sp_create_requester(struct qed_hwfn *p_hwfn, p_ramrod->qp_handle_for_async.lo = cpu_to_le32(qp->qp_handle_async.lo); p_ramrod->qp_handle_for_cqe.hi = cpu_to_le32(qp->qp_handle.hi); p_ramrod->qp_handle_for_cqe.lo = cpu_to_le32(qp->qp_handle.lo); - p_ramrod->stats_counter_id = p_hwfn->rel_pf_id; - p_ramrod->cq_cid = cpu_to_le32((p_hwfn->hw_info.opaque_fid << 16) | - qp->sq_cq_id); + p_ramrod->cq_cid = + cpu_to_le32((p_hwfn->hw_info.opaque_fid << 16) | qp->sq_cq_id); memset(&qm_params, 0, sizeof(qm_params)); qm_params.roce.qpid = qp->icid >> 1; - physical_queue0 = qed_get_qm_pq(p_hwfn, PROTOCOLID_ROCE, &qm_params); + regular_latency_queue = qed_get_qm_pq(p_hwfn, PROTOCOLID_ROCE, + &qm_params); + + p_ramrod->regular_latency_phy_queue = + cpu_to_le16(regular_latency_queue); + p_ramrod->low_latency_phy_queue = + cpu_to_le16(regular_latency_queue); - p_ramrod->physical_queue0 = cpu_to_le16(physical_queue0); p_ramrod->dpi = cpu_to_le16(qp->dpi); qed_rdma_set_fw_mac(p_ramrod->remote_mac_addr, qp->remote_mac_addr); @@ -1378,6 +1474,10 @@ static int qed_roce_sp_create_requester(struct qed_hwfn *p_hwfn, goto err; qp->req_offloaded = true; + proto = p_hwfn->p_rdma_info->proto; + qed_roce_set_real_cid(p_hwfn, + qp->icid + 1 - + qed_cxt_get_proto_cid_start(p_hwfn, proto)); return rc; @@ -1577,7 +1677,8 @@ static int qed_roce_sp_modify_requester(struct qed_hwfn *p_hwfn, static int qed_roce_sp_destroy_qp_responder(struct qed_hwfn *p_hwfn, struct qed_rdma_qp *qp, - u32 *num_invalidated_mw) + u32 *num_invalidated_mw, + u32 *cq_prod) { struct roce_destroy_qp_resp_output_params *p_ramrod_res; struct roce_destroy_qp_resp_ramrod_data *p_ramrod; @@ -1588,8 +1689,22 @@ static int qed_roce_sp_destroy_qp_responder(struct qed_hwfn *p_hwfn, DP_VERBOSE(p_hwfn, QED_MSG_RDMA, "icid = %08x\n", qp->icid); - if (!qp->resp_offloaded) + *num_invalidated_mw = 0; + *cq_prod = qp->cq_prod; + + if (!qp->resp_offloaded) { + /* If a responder was never offload, we need to free the cids + * allocated in create_qp as a FW async event will never arrive + */ + u32 cid; + + cid = qp->icid - + qed_cxt_get_proto_cid_start(p_hwfn, + p_hwfn->p_rdma_info->proto); + qed_roce_free_cid_pair(p_hwfn, (u16)cid); + return 0; + } /* Get SPQ entry */ memset(&init_data, 0, sizeof(init_data)); @@ -1624,6 +1739,8 @@ static int qed_roce_sp_destroy_qp_responder(struct qed_hwfn *p_hwfn, goto err; *num_invalidated_mw = le32_to_cpu(p_ramrod_res->num_invalidated_mw); + *cq_prod = le32_to_cpu(p_ramrod_res->cq_prod); + qp->cq_prod = *cq_prod; /* Free IRQ - only if ramrod succeeded, in case FW is still using it */ dma_free_coherent(&p_hwfn->cdev->pdev->dev, @@ -1827,10 +1944,8 @@ static int qed_roce_query_qp(struct qed_hwfn *p_hwfn, out_params->draining = false; - if (rq_err_state) + if (rq_err_state || sq_err_state) qp->cur_state = QED_ROCE_QP_STATE_ERR; - else if (sq_err_state) - qp->cur_state = QED_ROCE_QP_STATE_SQE; else if (sq_draining) out_params->draining = true; out_params->state = qp->cur_state; @@ -1849,10 +1964,9 @@ err_resp: static int qed_roce_destroy_qp(struct qed_hwfn *p_hwfn, struct qed_rdma_qp *qp) { - struct qed_rdma_info *p_rdma_info = p_hwfn->p_rdma_info; u32 num_invalidated_mw = 0; u32 num_bound_mw = 0; - u32 start_cid; + u32 cq_prod; int rc; /* Destroys the specified QP */ @@ -1866,7 +1980,8 @@ static int qed_roce_destroy_qp(struct qed_hwfn *p_hwfn, struct qed_rdma_qp *qp) if (qp->cur_state != QED_ROCE_QP_STATE_RESET) { rc = qed_roce_sp_destroy_qp_responder(p_hwfn, qp, - &num_invalidated_mw); + &num_invalidated_mw, + &cq_prod); if (rc) return rc; @@ -1881,21 +1996,6 @@ static int qed_roce_destroy_qp(struct qed_hwfn *p_hwfn, struct qed_rdma_qp *qp) "number of invalidate memory windows is different from bounded ones\n"); return -EINVAL; } - - spin_lock_bh(&p_rdma_info->lock); - - start_cid = qed_cxt_get_proto_cid_start(p_hwfn, - p_rdma_info->proto); - - /* Release responder's icid */ - qed_bmap_release_id(p_hwfn, &p_rdma_info->cid_map, - qp->icid - start_cid); - - /* Release requester's icid */ - qed_bmap_release_id(p_hwfn, &p_rdma_info->cid_map, - qp->icid + 1 - start_cid); - - spin_unlock_bh(&p_rdma_info->lock); } return 0; @@ -2110,12 +2210,19 @@ static int qed_roce_modify_qp(struct qed_hwfn *p_hwfn, return rc; } else if (qp->cur_state == QED_ROCE_QP_STATE_RESET) { /* Any state -> RESET */ + u32 cq_prod; + + /* Send destroy responder ramrod */ + rc = qed_roce_sp_destroy_qp_responder(p_hwfn, + qp, + &num_invalidated_mw, + &cq_prod); - rc = qed_roce_sp_destroy_qp_responder(p_hwfn, qp, - &num_invalidated_mw); if (rc) return rc; + qp->cq_prod = cq_prod; + rc = qed_roce_sp_destroy_qp_requester(p_hwfn, qp, &num_bound_mw); @@ -2454,6 +2561,31 @@ static int qed_rdma_deregister_tid(void *rdma_cxt, u32 itid) return rc; } +static void qed_roce_free_real_icid(struct qed_hwfn *p_hwfn, u16 icid) +{ + struct qed_rdma_info *p_rdma_info = p_hwfn->p_rdma_info; + u32 start_cid, cid, xcid; + + /* an even icid belongs to a responder while an odd icid belongs to a + * requester. The 'cid' received as an input can be either. We calculate + * the "partner" icid and call it xcid. Only if both are free then the + * "cid" map can be cleared. + */ + start_cid = qed_cxt_get_proto_cid_start(p_hwfn, p_rdma_info->proto); + cid = icid - start_cid; + xcid = cid ^ 1; + + spin_lock_bh(&p_rdma_info->lock); + + qed_bmap_release_id(p_hwfn, &p_rdma_info->real_cid_map, cid); + if (qed_bmap_test_id(p_hwfn, &p_rdma_info->real_cid_map, xcid) == 0) { + qed_bmap_release_id(p_hwfn, &p_rdma_info->cid_map, cid); + qed_bmap_release_id(p_hwfn, &p_rdma_info->cid_map, xcid); + } + + spin_unlock_bh(&p_hwfn->p_rdma_info->lock); +} + static void *qed_rdma_get_rdma_ctx(struct qed_dev *cdev) { return QED_LEADING_HWFN(cdev); @@ -2773,7 +2905,7 @@ static int qed_roce_ll2_tx(struct qed_dev *cdev, : QED_LL2_RROCE; if (pkt->roce_mode == ROCE_V2_IPV4) - flags |= BIT(CORE_TX_BD_FLAGS_IP_CSUM_SHIFT); + flags |= BIT(CORE_TX_BD_DATA_IP_CSUM_SHIFT); /* Tx header */ rc = qed_ll2_prepare_tx_packet(QED_LEADING_HWFN(cdev), roce_ll2->handle, diff --git a/drivers/net/ethernet/qlogic/qed/qed_roce.h b/drivers/net/ethernet/qlogic/qed/qed_roce.h index 36cf4b2ab7fa..3ccc08a7c995 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_roce.h +++ b/drivers/net/ethernet/qlogic/qed/qed_roce.h @@ -82,6 +82,7 @@ struct qed_rdma_info { struct qed_bmap qp_map; struct qed_bmap srq_map; struct qed_bmap cid_map; + struct qed_bmap real_cid_map; struct qed_bmap dpi_map; struct qed_bmap toggle_bits; struct qed_rdma_events events; @@ -92,6 +93,7 @@ struct qed_rdma_info { u32 num_qps; u32 num_mrs; u16 queue_zone_base; + u16 max_queue_zones; enum protocol_type proto; }; @@ -153,6 +155,7 @@ struct qed_rdma_qp { dma_addr_t irq_phys_addr; u8 irq_num_pages; bool resp_offloaded; + u32 cq_prod; u8 remote_mac_addr[6]; u8 local_mac_addr[6]; @@ -163,8 +166,8 @@ struct qed_rdma_qp { #if IS_ENABLED(CONFIG_QED_RDMA) void qed_rdma_dpm_bar(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt); -void qed_async_roce_event(struct qed_hwfn *p_hwfn, - struct event_ring_entry *p_eqe); +void qed_roce_async_event(struct qed_hwfn *p_hwfn, + u8 fw_event_code, union rdma_eqe_data *rdma_data); void qed_ll2b_complete_tx_gsi_packet(struct qed_hwfn *p_hwfn, u8 connection_handle, void *cookie, @@ -187,7 +190,9 @@ void qed_ll2b_complete_rx_gsi_packet(struct qed_hwfn *p_hwfn, u16 src_mac_addr_lo, bool b_last_packet); #else static inline void qed_rdma_dpm_bar(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt) {} -static inline void qed_async_roce_event(struct qed_hwfn *p_hwfn, struct event_ring_entry *p_eqe) {} +static inline void qed_roce_async_event(struct qed_hwfn *p_hwfn, + u8 fw_event_code, + union rdma_eqe_data *rdma_data) {} static inline void qed_ll2b_complete_tx_gsi_packet(struct qed_hwfn *p_hwfn, u8 connection_handle, void *cookie, diff --git a/drivers/net/ethernet/qlogic/qed/qed_spq.c b/drivers/net/ethernet/qlogic/qed/qed_spq.c index 645328a9f0cf..54fbe3789cf3 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_spq.c +++ b/drivers/net/ethernet/qlogic/qed/qed_spq.c @@ -296,9 +296,12 @@ qed_async_event_completion(struct qed_hwfn *p_hwfn, struct event_ring_entry *p_eqe) { switch (p_eqe->protocol_id) { +#if IS_ENABLED(CONFIG_QED_RDMA) case PROTOCOLID_ROCE: - qed_async_roce_event(p_hwfn, p_eqe); + qed_roce_async_event(p_hwfn, p_eqe->opcode, + &p_eqe->data.rdma_data); return 0; +#endif case PROTOCOLID_COMMON: return qed_sriov_eqe_event(p_hwfn, p_eqe->opcode, @@ -306,14 +309,6 @@ qed_async_event_completion(struct qed_hwfn *p_hwfn, case PROTOCOLID_ISCSI: if (!IS_ENABLED(CONFIG_QED_ISCSI)) return -EINVAL; - if (p_eqe->opcode == ISCSI_EVENT_TYPE_ASYN_DELETE_OOO_ISLES) { - u32 cid = le32_to_cpu(p_eqe->data.iscsi_info.cid); - - qed_ooo_release_connection_isles(p_hwfn, - p_hwfn->p_ooo_info, - cid); - return 0; - } if (p_hwfn->p_iscsi_info->event_cb) { struct qed_iscsi_info *p_iscsi = p_hwfn->p_iscsi_info; diff --git a/drivers/net/ethernet/qlogic/qed/qed_sriov.c b/drivers/net/ethernet/qlogic/qed/qed_sriov.c index 253c2bbe1e4e..16f503c9b0af 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_sriov.c +++ b/drivers/net/ethernet/qlogic/qed/qed_sriov.c @@ -557,14 +557,30 @@ int qed_iov_hw_info(struct qed_hwfn *p_hwfn) return 0; } - /* Calculate the first VF index - this is a bit tricky; Basically, - * VFs start at offset 16 relative to PF0, and 2nd engine VFs begin - * after the first engine's VFs. + /* First VF index based on offset is tricky: + * - If ARI is supported [likely], offset - (16 - pf_id) would + * provide the number for eng0. 2nd engine Vfs would begin + * after the first engine's VFs. + * - If !ARI, VFs would start on next device. + * so offset - (256 - pf_id) would provide the number. + * Utilize the fact that (256 - pf_id) is achieved only by later + * to diffrentiate between the two. */ - cdev->p_iov_info->first_vf_in_pf = p_hwfn->cdev->p_iov_info->offset + - p_hwfn->abs_pf_id - 16; - if (QED_PATH_ID(p_hwfn)) - cdev->p_iov_info->first_vf_in_pf -= MAX_NUM_VFS_BB; + + if (p_hwfn->cdev->p_iov_info->offset < (256 - p_hwfn->abs_pf_id)) { + u32 first = p_hwfn->cdev->p_iov_info->offset + + p_hwfn->abs_pf_id - 16; + + cdev->p_iov_info->first_vf_in_pf = first; + + if (QED_PATH_ID(p_hwfn)) + cdev->p_iov_info->first_vf_in_pf -= MAX_NUM_VFS_BB; + } else { + u32 first = p_hwfn->cdev->p_iov_info->offset + + p_hwfn->abs_pf_id - 256; + + cdev->p_iov_info->first_vf_in_pf = first; + } DP_VERBOSE(p_hwfn, QED_MSG_IOV, "First VF in hwfn 0x%08x\n", diff --git a/drivers/net/ethernet/qlogic/qede/qede.h b/drivers/net/ethernet/qlogic/qede/qede.h index f2aaef2cfb86..e73a4a5165ee 100644 --- a/drivers/net/ethernet/qlogic/qede/qede.h +++ b/drivers/net/ethernet/qlogic/qede/qede.h @@ -50,7 +50,7 @@ #define QEDE_MAJOR_VERSION 8 #define QEDE_MINOR_VERSION 10 #define QEDE_REVISION_VERSION 10 -#define QEDE_ENGINEERING_VERSION 20 +#define QEDE_ENGINEERING_VERSION 21 #define DRV_MODULE_VERSION __stringify(QEDE_MAJOR_VERSION) "." \ __stringify(QEDE_MINOR_VERSION) "." \ __stringify(QEDE_REVISION_VERSION) "." \ @@ -58,7 +58,7 @@ #define DRV_MODULE_SYM qede -struct qede_stats { +struct qede_stats_common { u64 no_buff_discards; u64 packet_too_big_discard; u64 ttl0_discard; @@ -90,11 +90,6 @@ struct qede_stats { u64 rx_256_to_511_byte_packets; u64 rx_512_to_1023_byte_packets; u64 rx_1024_to_1518_byte_packets; - u64 rx_1519_to_1522_byte_packets; - u64 rx_1519_to_2047_byte_packets; - u64 rx_2048_to_4095_byte_packets; - u64 rx_4096_to_9216_byte_packets; - u64 rx_9217_to_16383_byte_packets; u64 rx_crc_errors; u64 rx_mac_crtl_frames; u64 rx_pause_frames; @@ -111,17 +106,39 @@ struct qede_stats { u64 tx_256_to_511_byte_packets; u64 tx_512_to_1023_byte_packets; u64 tx_1024_to_1518_byte_packets; + u64 tx_pause_frames; + u64 tx_pfc_frames; + u64 brb_truncates; + u64 brb_discards; + u64 tx_mac_ctrl_frames; +}; + +struct qede_stats_bb { + u64 rx_1519_to_1522_byte_packets; + u64 rx_1519_to_2047_byte_packets; + u64 rx_2048_to_4095_byte_packets; + u64 rx_4096_to_9216_byte_packets; + u64 rx_9217_to_16383_byte_packets; u64 tx_1519_to_2047_byte_packets; u64 tx_2048_to_4095_byte_packets; u64 tx_4096_to_9216_byte_packets; u64 tx_9217_to_16383_byte_packets; - u64 tx_pause_frames; - u64 tx_pfc_frames; u64 tx_lpi_entry_count; u64 tx_total_collisions; - u64 brb_truncates; - u64 brb_discards; - u64 tx_mac_ctrl_frames; +}; + +struct qede_stats_ah { + u64 rx_1519_to_max_byte_packets; + u64 tx_1519_to_max_byte_packets; +}; + +struct qede_stats { + struct qede_stats_common common; + + union { + struct qede_stats_bb bb; + struct qede_stats_ah ah; + }; }; struct qede_vlan { @@ -158,6 +175,10 @@ struct qede_dev { struct qed_dev_eth_info dev_info; #define QEDE_MAX_RSS_CNT(edev) ((edev)->dev_info.num_queues) #define QEDE_MAX_TSS_CNT(edev) ((edev)->dev_info.num_queues) +#define QEDE_IS_BB(edev) \ + ((edev)->dev_info.common.dev_type == QED_DEV_TYPE_BB) +#define QEDE_IS_AH(edev) \ + ((edev)->dev_info.common.dev_type == QED_DEV_TYPE_AH) struct qede_fastpath *fp_array; u8 req_num_tx; diff --git a/drivers/net/ethernet/qlogic/qede/qede_ethtool.c b/drivers/net/ethernet/qlogic/qede/qede_ethtool.c index 897953133245..4dcfe9614731 100644 --- a/drivers/net/ethernet/qlogic/qede/qede_ethtool.c +++ b/drivers/net/ethernet/qlogic/qede/qede_ethtool.c @@ -75,16 +75,33 @@ static const struct { QEDE_TQSTAT(stopped_cnt), }; -#define QEDE_STAT_OFFSET(stat_name) (offsetof(struct qede_stats, stat_name)) -#define QEDE_STAT_STRING(stat_name) (#stat_name) -#define _QEDE_STAT(stat_name, pf_only) \ - {QEDE_STAT_OFFSET(stat_name), QEDE_STAT_STRING(stat_name), pf_only} -#define QEDE_PF_STAT(stat_name) _QEDE_STAT(stat_name, true) -#define QEDE_STAT(stat_name) _QEDE_STAT(stat_name, false) +#define QEDE_STAT_OFFSET(stat_name, type, base) \ + (offsetof(type, stat_name) + (base)) +#define QEDE_STAT_STRING(stat_name) (#stat_name) +#define _QEDE_STAT(stat_name, type, base, attr) \ + {QEDE_STAT_OFFSET(stat_name, type, base), \ + QEDE_STAT_STRING(stat_name), \ + attr} +#define QEDE_STAT(stat_name) \ + _QEDE_STAT(stat_name, struct qede_stats_common, 0, 0x0) +#define QEDE_PF_STAT(stat_name) \ + _QEDE_STAT(stat_name, struct qede_stats_common, 0, \ + BIT(QEDE_STAT_PF_ONLY)) +#define QEDE_PF_BB_STAT(stat_name) \ + _QEDE_STAT(stat_name, struct qede_stats_bb, \ + offsetof(struct qede_stats, bb), \ + BIT(QEDE_STAT_PF_ONLY) | BIT(QEDE_STAT_BB_ONLY)) +#define QEDE_PF_AH_STAT(stat_name) \ + _QEDE_STAT(stat_name, struct qede_stats_ah, \ + offsetof(struct qede_stats, ah), \ + BIT(QEDE_STAT_PF_ONLY) | BIT(QEDE_STAT_AH_ONLY)) static const struct { u64 offset; char string[ETH_GSTRING_LEN]; - bool pf_only; + unsigned long attr; +#define QEDE_STAT_PF_ONLY 0 +#define QEDE_STAT_BB_ONLY 1 +#define QEDE_STAT_AH_ONLY 2 } qede_stats_arr[] = { QEDE_STAT(rx_ucast_bytes), QEDE_STAT(rx_mcast_bytes), @@ -106,22 +123,23 @@ static const struct { QEDE_PF_STAT(rx_256_to_511_byte_packets), QEDE_PF_STAT(rx_512_to_1023_byte_packets), QEDE_PF_STAT(rx_1024_to_1518_byte_packets), - QEDE_PF_STAT(rx_1519_to_1522_byte_packets), - QEDE_PF_STAT(rx_1519_to_2047_byte_packets), - QEDE_PF_STAT(rx_2048_to_4095_byte_packets), - QEDE_PF_STAT(rx_4096_to_9216_byte_packets), - QEDE_PF_STAT(rx_9217_to_16383_byte_packets), + QEDE_PF_BB_STAT(rx_1519_to_1522_byte_packets), + QEDE_PF_BB_STAT(rx_1519_to_2047_byte_packets), + QEDE_PF_BB_STAT(rx_2048_to_4095_byte_packets), + QEDE_PF_BB_STAT(rx_4096_to_9216_byte_packets), + QEDE_PF_BB_STAT(rx_9217_to_16383_byte_packets), + QEDE_PF_AH_STAT(rx_1519_to_max_byte_packets), QEDE_PF_STAT(tx_64_byte_packets), QEDE_PF_STAT(tx_65_to_127_byte_packets), QEDE_PF_STAT(tx_128_to_255_byte_packets), QEDE_PF_STAT(tx_256_to_511_byte_packets), QEDE_PF_STAT(tx_512_to_1023_byte_packets), QEDE_PF_STAT(tx_1024_to_1518_byte_packets), - QEDE_PF_STAT(tx_1519_to_2047_byte_packets), - QEDE_PF_STAT(tx_2048_to_4095_byte_packets), - QEDE_PF_STAT(tx_4096_to_9216_byte_packets), - QEDE_PF_STAT(tx_9217_to_16383_byte_packets), - + QEDE_PF_BB_STAT(tx_1519_to_2047_byte_packets), + QEDE_PF_BB_STAT(tx_2048_to_4095_byte_packets), + QEDE_PF_BB_STAT(tx_4096_to_9216_byte_packets), + QEDE_PF_BB_STAT(tx_9217_to_16383_byte_packets), + QEDE_PF_AH_STAT(tx_1519_to_max_byte_packets), QEDE_PF_STAT(rx_mac_crtl_frames), QEDE_PF_STAT(tx_mac_ctrl_frames), QEDE_PF_STAT(rx_pause_frames), @@ -136,8 +154,8 @@ static const struct { QEDE_PF_STAT(rx_jabbers), QEDE_PF_STAT(rx_undersize_packets), QEDE_PF_STAT(rx_fragments), - QEDE_PF_STAT(tx_lpi_entry_count), - QEDE_PF_STAT(tx_total_collisions), + QEDE_PF_BB_STAT(tx_lpi_entry_count), + QEDE_PF_BB_STAT(tx_total_collisions), QEDE_PF_STAT(brb_truncates), QEDE_PF_STAT(brb_discards), QEDE_STAT(no_buff_discards), @@ -155,6 +173,12 @@ static const struct { }; #define QEDE_NUM_STATS ARRAY_SIZE(qede_stats_arr) +#define QEDE_STAT_IS_PF_ONLY(i) \ + test_bit(QEDE_STAT_PF_ONLY, &qede_stats_arr[i].attr) +#define QEDE_STAT_IS_BB_ONLY(i) \ + test_bit(QEDE_STAT_BB_ONLY, &qede_stats_arr[i].attr) +#define QEDE_STAT_IS_AH_ONLY(i) \ + test_bit(QEDE_STAT_AH_ONLY, &qede_stats_arr[i].attr) enum { QEDE_PRI_FLAG_CMT, @@ -213,6 +237,13 @@ static void qede_get_strings_stats_rxq(struct qede_dev *edev, } } +static bool qede_is_irrelevant_stat(struct qede_dev *edev, int stat_index) +{ + return (IS_VF(edev) && QEDE_STAT_IS_PF_ONLY(stat_index)) || + (QEDE_IS_BB(edev) && QEDE_STAT_IS_AH_ONLY(stat_index)) || + (QEDE_IS_AH(edev) && QEDE_STAT_IS_BB_ONLY(stat_index)); +} + static void qede_get_strings_stats(struct qede_dev *edev, u8 *buf) { struct qede_fastpath *fp; @@ -234,7 +265,7 @@ static void qede_get_strings_stats(struct qede_dev *edev, u8 *buf) /* Account for non-queue statistics */ for (i = 0; i < QEDE_NUM_STATS; i++) { - if (IS_VF(edev) && qede_stats_arr[i].pf_only) + if (qede_is_irrelevant_stat(edev, i)) continue; strcpy(buf, qede_stats_arr[i].string); buf += ETH_GSTRING_LEN; @@ -309,7 +340,7 @@ static void qede_get_ethtool_stats(struct net_device *dev, } for (i = 0; i < QEDE_NUM_STATS; i++) { - if (IS_VF(edev) && qede_stats_arr[i].pf_only) + if (qede_is_irrelevant_stat(edev, i)) continue; *buf = *((u64 *)(((void *)&edev->stats) + qede_stats_arr[i].offset)); @@ -323,17 +354,13 @@ static void qede_get_ethtool_stats(struct net_device *dev, static int qede_get_sset_count(struct net_device *dev, int stringset) { struct qede_dev *edev = netdev_priv(dev); - int num_stats = QEDE_NUM_STATS; + int num_stats = QEDE_NUM_STATS, i; switch (stringset) { case ETH_SS_STATS: - if (IS_VF(edev)) { - int i; - - for (i = 0; i < QEDE_NUM_STATS; i++) - if (qede_stats_arr[i].pf_only) - num_stats--; - } + for (i = 0; i < QEDE_NUM_STATS; i++) + if (qede_is_irrelevant_stat(edev, i)) + num_stats--; /* Account for the Regular Tx statistics */ num_stats += QEDE_TSS_COUNT(edev) * QEDE_NUM_TQSTATS; diff --git a/drivers/net/ethernet/qlogic/qede/qede_main.c b/drivers/net/ethernet/qlogic/qede/qede_main.c index 3a78c3f25157..abd99109e532 100644 --- a/drivers/net/ethernet/qlogic/qede/qede_main.c +++ b/drivers/net/ethernet/qlogic/qede/qede_main.c @@ -84,6 +84,8 @@ static const struct qed_eth_ops *qed_ops; #define CHIP_NUM_57980S_50 0x1654 #define CHIP_NUM_57980S_25 0x1656 #define CHIP_NUM_57980S_IOV 0x1664 +#define CHIP_NUM_AH 0x8070 +#define CHIP_NUM_AH_IOV 0x8090 #ifndef PCI_DEVICE_ID_NX2_57980E #define PCI_DEVICE_ID_57980S_40 CHIP_NUM_57980S_40 @@ -93,6 +95,9 @@ static const struct qed_eth_ops *qed_ops; #define PCI_DEVICE_ID_57980S_50 CHIP_NUM_57980S_50 #define PCI_DEVICE_ID_57980S_25 CHIP_NUM_57980S_25 #define PCI_DEVICE_ID_57980S_IOV CHIP_NUM_57980S_IOV +#define PCI_DEVICE_ID_AH CHIP_NUM_AH +#define PCI_DEVICE_ID_AH_IOV CHIP_NUM_AH_IOV + #endif enum qede_pci_private { @@ -110,6 +115,10 @@ static const struct pci_device_id qede_pci_tbl[] = { #ifdef CONFIG_QED_SRIOV {PCI_VDEVICE(QLOGIC, PCI_DEVICE_ID_57980S_IOV), QEDE_PRIVATE_VF}, #endif + {PCI_VDEVICE(QLOGIC, PCI_DEVICE_ID_AH), QEDE_PRIVATE_PF}, +#ifdef CONFIG_QED_SRIOV + {PCI_VDEVICE(QLOGIC, PCI_DEVICE_ID_AH_IOV), QEDE_PRIVATE_VF}, +#endif { 0 } }; @@ -314,122 +323,135 @@ static int qede_close(struct net_device *ndev); void qede_fill_by_demand_stats(struct qede_dev *edev) { + struct qede_stats_common *p_common = &edev->stats.common; struct qed_eth_stats stats; edev->ops->get_vport_stats(edev->cdev, &stats); - edev->stats.no_buff_discards = stats.no_buff_discards; - edev->stats.packet_too_big_discard = stats.packet_too_big_discard; - edev->stats.ttl0_discard = stats.ttl0_discard; - edev->stats.rx_ucast_bytes = stats.rx_ucast_bytes; - edev->stats.rx_mcast_bytes = stats.rx_mcast_bytes; - edev->stats.rx_bcast_bytes = stats.rx_bcast_bytes; - edev->stats.rx_ucast_pkts = stats.rx_ucast_pkts; - edev->stats.rx_mcast_pkts = stats.rx_mcast_pkts; - edev->stats.rx_bcast_pkts = stats.rx_bcast_pkts; - edev->stats.mftag_filter_discards = stats.mftag_filter_discards; - edev->stats.mac_filter_discards = stats.mac_filter_discards; - - edev->stats.tx_ucast_bytes = stats.tx_ucast_bytes; - edev->stats.tx_mcast_bytes = stats.tx_mcast_bytes; - edev->stats.tx_bcast_bytes = stats.tx_bcast_bytes; - edev->stats.tx_ucast_pkts = stats.tx_ucast_pkts; - edev->stats.tx_mcast_pkts = stats.tx_mcast_pkts; - edev->stats.tx_bcast_pkts = stats.tx_bcast_pkts; - edev->stats.tx_err_drop_pkts = stats.tx_err_drop_pkts; - edev->stats.coalesced_pkts = stats.tpa_coalesced_pkts; - edev->stats.coalesced_events = stats.tpa_coalesced_events; - edev->stats.coalesced_aborts_num = stats.tpa_aborts_num; - edev->stats.non_coalesced_pkts = stats.tpa_not_coalesced_pkts; - edev->stats.coalesced_bytes = stats.tpa_coalesced_bytes; - - edev->stats.rx_64_byte_packets = stats.rx_64_byte_packets; - edev->stats.rx_65_to_127_byte_packets = stats.rx_65_to_127_byte_packets; - edev->stats.rx_128_to_255_byte_packets = - stats.rx_128_to_255_byte_packets; - edev->stats.rx_256_to_511_byte_packets = - stats.rx_256_to_511_byte_packets; - edev->stats.rx_512_to_1023_byte_packets = - stats.rx_512_to_1023_byte_packets; - edev->stats.rx_1024_to_1518_byte_packets = - stats.rx_1024_to_1518_byte_packets; - edev->stats.rx_1519_to_1522_byte_packets = - stats.rx_1519_to_1522_byte_packets; - edev->stats.rx_1519_to_2047_byte_packets = - stats.rx_1519_to_2047_byte_packets; - edev->stats.rx_2048_to_4095_byte_packets = - stats.rx_2048_to_4095_byte_packets; - edev->stats.rx_4096_to_9216_byte_packets = - stats.rx_4096_to_9216_byte_packets; - edev->stats.rx_9217_to_16383_byte_packets = - stats.rx_9217_to_16383_byte_packets; - edev->stats.rx_crc_errors = stats.rx_crc_errors; - edev->stats.rx_mac_crtl_frames = stats.rx_mac_crtl_frames; - edev->stats.rx_pause_frames = stats.rx_pause_frames; - edev->stats.rx_pfc_frames = stats.rx_pfc_frames; - edev->stats.rx_align_errors = stats.rx_align_errors; - edev->stats.rx_carrier_errors = stats.rx_carrier_errors; - edev->stats.rx_oversize_packets = stats.rx_oversize_packets; - edev->stats.rx_jabbers = stats.rx_jabbers; - edev->stats.rx_undersize_packets = stats.rx_undersize_packets; - edev->stats.rx_fragments = stats.rx_fragments; - edev->stats.tx_64_byte_packets = stats.tx_64_byte_packets; - edev->stats.tx_65_to_127_byte_packets = stats.tx_65_to_127_byte_packets; - edev->stats.tx_128_to_255_byte_packets = - stats.tx_128_to_255_byte_packets; - edev->stats.tx_256_to_511_byte_packets = - stats.tx_256_to_511_byte_packets; - edev->stats.tx_512_to_1023_byte_packets = - stats.tx_512_to_1023_byte_packets; - edev->stats.tx_1024_to_1518_byte_packets = - stats.tx_1024_to_1518_byte_packets; - edev->stats.tx_1519_to_2047_byte_packets = - stats.tx_1519_to_2047_byte_packets; - edev->stats.tx_2048_to_4095_byte_packets = - stats.tx_2048_to_4095_byte_packets; - edev->stats.tx_4096_to_9216_byte_packets = - stats.tx_4096_to_9216_byte_packets; - edev->stats.tx_9217_to_16383_byte_packets = - stats.tx_9217_to_16383_byte_packets; - edev->stats.tx_pause_frames = stats.tx_pause_frames; - edev->stats.tx_pfc_frames = stats.tx_pfc_frames; - edev->stats.tx_lpi_entry_count = stats.tx_lpi_entry_count; - edev->stats.tx_total_collisions = stats.tx_total_collisions; - edev->stats.brb_truncates = stats.brb_truncates; - edev->stats.brb_discards = stats.brb_discards; - edev->stats.tx_mac_ctrl_frames = stats.tx_mac_ctrl_frames; + + p_common->no_buff_discards = stats.common.no_buff_discards; + p_common->packet_too_big_discard = stats.common.packet_too_big_discard; + p_common->ttl0_discard = stats.common.ttl0_discard; + p_common->rx_ucast_bytes = stats.common.rx_ucast_bytes; + p_common->rx_mcast_bytes = stats.common.rx_mcast_bytes; + p_common->rx_bcast_bytes = stats.common.rx_bcast_bytes; + p_common->rx_ucast_pkts = stats.common.rx_ucast_pkts; + p_common->rx_mcast_pkts = stats.common.rx_mcast_pkts; + p_common->rx_bcast_pkts = stats.common.rx_bcast_pkts; + p_common->mftag_filter_discards = stats.common.mftag_filter_discards; + p_common->mac_filter_discards = stats.common.mac_filter_discards; + + p_common->tx_ucast_bytes = stats.common.tx_ucast_bytes; + p_common->tx_mcast_bytes = stats.common.tx_mcast_bytes; + p_common->tx_bcast_bytes = stats.common.tx_bcast_bytes; + p_common->tx_ucast_pkts = stats.common.tx_ucast_pkts; + p_common->tx_mcast_pkts = stats.common.tx_mcast_pkts; + p_common->tx_bcast_pkts = stats.common.tx_bcast_pkts; + p_common->tx_err_drop_pkts = stats.common.tx_err_drop_pkts; + p_common->coalesced_pkts = stats.common.tpa_coalesced_pkts; + p_common->coalesced_events = stats.common.tpa_coalesced_events; + p_common->coalesced_aborts_num = stats.common.tpa_aborts_num; + p_common->non_coalesced_pkts = stats.common.tpa_not_coalesced_pkts; + p_common->coalesced_bytes = stats.common.tpa_coalesced_bytes; + + p_common->rx_64_byte_packets = stats.common.rx_64_byte_packets; + p_common->rx_65_to_127_byte_packets = + stats.common.rx_65_to_127_byte_packets; + p_common->rx_128_to_255_byte_packets = + stats.common.rx_128_to_255_byte_packets; + p_common->rx_256_to_511_byte_packets = + stats.common.rx_256_to_511_byte_packets; + p_common->rx_512_to_1023_byte_packets = + stats.common.rx_512_to_1023_byte_packets; + p_common->rx_1024_to_1518_byte_packets = + stats.common.rx_1024_to_1518_byte_packets; + p_common->rx_crc_errors = stats.common.rx_crc_errors; + p_common->rx_mac_crtl_frames = stats.common.rx_mac_crtl_frames; + p_common->rx_pause_frames = stats.common.rx_pause_frames; + p_common->rx_pfc_frames = stats.common.rx_pfc_frames; + p_common->rx_align_errors = stats.common.rx_align_errors; + p_common->rx_carrier_errors = stats.common.rx_carrier_errors; + p_common->rx_oversize_packets = stats.common.rx_oversize_packets; + p_common->rx_jabbers = stats.common.rx_jabbers; + p_common->rx_undersize_packets = stats.common.rx_undersize_packets; + p_common->rx_fragments = stats.common.rx_fragments; + p_common->tx_64_byte_packets = stats.common.tx_64_byte_packets; + p_common->tx_65_to_127_byte_packets = + stats.common.tx_65_to_127_byte_packets; + p_common->tx_128_to_255_byte_packets = + stats.common.tx_128_to_255_byte_packets; + p_common->tx_256_to_511_byte_packets = + stats.common.tx_256_to_511_byte_packets; + p_common->tx_512_to_1023_byte_packets = + stats.common.tx_512_to_1023_byte_packets; + p_common->tx_1024_to_1518_byte_packets = + stats.common.tx_1024_to_1518_byte_packets; + p_common->tx_pause_frames = stats.common.tx_pause_frames; + p_common->tx_pfc_frames = stats.common.tx_pfc_frames; + p_common->brb_truncates = stats.common.brb_truncates; + p_common->brb_discards = stats.common.brb_discards; + p_common->tx_mac_ctrl_frames = stats.common.tx_mac_ctrl_frames; + + if (QEDE_IS_BB(edev)) { + struct qede_stats_bb *p_bb = &edev->stats.bb; + + p_bb->rx_1519_to_1522_byte_packets = + stats.bb.rx_1519_to_1522_byte_packets; + p_bb->rx_1519_to_2047_byte_packets = + stats.bb.rx_1519_to_2047_byte_packets; + p_bb->rx_2048_to_4095_byte_packets = + stats.bb.rx_2048_to_4095_byte_packets; + p_bb->rx_4096_to_9216_byte_packets = + stats.bb.rx_4096_to_9216_byte_packets; + p_bb->rx_9217_to_16383_byte_packets = + stats.bb.rx_9217_to_16383_byte_packets; + p_bb->tx_1519_to_2047_byte_packets = + stats.bb.tx_1519_to_2047_byte_packets; + p_bb->tx_2048_to_4095_byte_packets = + stats.bb.tx_2048_to_4095_byte_packets; + p_bb->tx_4096_to_9216_byte_packets = + stats.bb.tx_4096_to_9216_byte_packets; + p_bb->tx_9217_to_16383_byte_packets = + stats.bb.tx_9217_to_16383_byte_packets; + p_bb->tx_lpi_entry_count = stats.bb.tx_lpi_entry_count; + p_bb->tx_total_collisions = stats.bb.tx_total_collisions; + } else { + struct qede_stats_ah *p_ah = &edev->stats.ah; + + p_ah->rx_1519_to_max_byte_packets = + stats.ah.rx_1519_to_max_byte_packets; + p_ah->tx_1519_to_max_byte_packets = + stats.ah.tx_1519_to_max_byte_packets; + } } static void qede_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *stats) { struct qede_dev *edev = netdev_priv(dev); + struct qede_stats_common *p_common; qede_fill_by_demand_stats(edev); + p_common = &edev->stats.common; - stats->rx_packets = edev->stats.rx_ucast_pkts + - edev->stats.rx_mcast_pkts + - edev->stats.rx_bcast_pkts; - stats->tx_packets = edev->stats.tx_ucast_pkts + - edev->stats.tx_mcast_pkts + - edev->stats.tx_bcast_pkts; - - stats->rx_bytes = edev->stats.rx_ucast_bytes + - edev->stats.rx_mcast_bytes + - edev->stats.rx_bcast_bytes; + stats->rx_packets = p_common->rx_ucast_pkts + p_common->rx_mcast_pkts + + p_common->rx_bcast_pkts; + stats->tx_packets = p_common->tx_ucast_pkts + p_common->tx_mcast_pkts + + p_common->tx_bcast_pkts; - stats->tx_bytes = edev->stats.tx_ucast_bytes + - edev->stats.tx_mcast_bytes + - edev->stats.tx_bcast_bytes; + stats->rx_bytes = p_common->rx_ucast_bytes + p_common->rx_mcast_bytes + + p_common->rx_bcast_bytes; + stats->tx_bytes = p_common->tx_ucast_bytes + p_common->tx_mcast_bytes + + p_common->tx_bcast_bytes; - stats->tx_errors = edev->stats.tx_err_drop_pkts; - stats->multicast = edev->stats.rx_mcast_pkts + - edev->stats.rx_bcast_pkts; + stats->tx_errors = p_common->tx_err_drop_pkts; + stats->multicast = p_common->rx_mcast_pkts + p_common->rx_bcast_pkts; - stats->rx_fifo_errors = edev->stats.no_buff_discards; + stats->rx_fifo_errors = p_common->no_buff_discards; - stats->collisions = edev->stats.tx_total_collisions; - stats->rx_crc_errors = edev->stats.rx_crc_errors; - stats->rx_frame_errors = edev->stats.rx_align_errors; + if (QEDE_IS_BB(edev)) + stats->collisions = edev->stats.bb.tx_total_collisions; + stats->rx_crc_errors = p_common->rx_crc_errors; + stats->rx_frame_errors = p_common->rx_align_errors; } #ifdef CONFIG_QED_SRIOV diff --git a/drivers/net/ethernet/qlogic/qlge/qlge.h b/drivers/net/ethernet/qlogic/qlge/qlge.h index 6d31f92ef2b6..84ac50f92c9c 100644 --- a/drivers/net/ethernet/qlogic/qlge/qlge.h +++ b/drivers/net/ethernet/qlogic/qlge/qlge.h @@ -1162,8 +1162,8 @@ struct ob_mac_tso_iocb_rsp { struct ib_mac_iocb_rsp { u8 opcode; /* 0x20 */ u8 flags1; -#define IB_MAC_IOCB_RSP_OI 0x01 /* Overide intr delay */ -#define IB_MAC_IOCB_RSP_I 0x02 /* Disble Intr Generation */ +#define IB_MAC_IOCB_RSP_OI 0x01 /* Override intr delay */ +#define IB_MAC_IOCB_RSP_I 0x02 /* Disable Intr Generation */ #define IB_MAC_CSUM_ERR_MASK 0x1c /* A mask to use for csum errs */ #define IB_MAC_IOCB_RSP_TE 0x04 /* Checksum error */ #define IB_MAC_IOCB_RSP_NU 0x08 /* No checksum rcvd */ diff --git a/drivers/net/ethernet/qualcomm/emac/emac-sgmii-qdf2400.c b/drivers/net/ethernet/qualcomm/emac/emac-sgmii-qdf2400.c index f62c215be779..7116be485e61 100644 --- a/drivers/net/ethernet/qualcomm/emac/emac-sgmii-qdf2400.c +++ b/drivers/net/ethernet/qualcomm/emac/emac-sgmii-qdf2400.c @@ -26,6 +26,7 @@ /* SGMII digital lane registers */ #define EMAC_SGMII_LN_DRVR_CTRL0 0x000C +#define EMAC_SGMII_LN_DRVR_CTRL1 0x0010 #define EMAC_SGMII_LN_DRVR_TAP_EN 0x0018 #define EMAC_SGMII_LN_TX_MARGINING 0x001C #define EMAC_SGMII_LN_TX_PRE 0x0020 @@ -48,6 +49,7 @@ #define EMAC_SGMII_LN_RX_EN_SIGNAL 0x02AC #define EMAC_SGMII_LN_RX_MISC_CNTRL0 0x02B8 #define EMAC_SGMII_LN_DRVR_LOGIC_CLKDIV 0x02C8 +#define EMAC_SGMII_LN_RX_RESECODE_OFFSET 0x02CC /* SGMII digital lane register values */ #define UCDR_STEP_BY_TWO_MODE0 BIT(7) @@ -73,6 +75,8 @@ #define CML_GEAR_MODE(x) (((x) & 7) << 3) #define CML2CMOS_IBOOST_MODE(x) ((x) & 7) +#define RESCODE_OFFSET(x) ((x) & 0x1f) + #define MIXER_LOADB_MODE(x) (((x) & 0xf) << 2) #define MIXER_DATARATE_MODE(x) ((x) & 3) @@ -159,6 +163,8 @@ static const struct emac_reg_write sgmii_laned[] = { {EMAC_SGMII_LN_PARALLEL_RATE, PARALLEL_RATE_MODE0(1)}, {EMAC_SGMII_LN_TX_BAND_MODE, BAND_MODE0(1)}, {EMAC_SGMII_LN_RX_BAND, BAND_MODE0(2)}, + {EMAC_SGMII_LN_DRVR_CTRL1, RESCODE_OFFSET(7)}, + {EMAC_SGMII_LN_RX_RESECODE_OFFSET, RESCODE_OFFSET(9)}, {EMAC_SGMII_LN_LANE_MODE, LANE_MODE(26)}, {EMAC_SGMII_LN_RX_RCVR_PATH1_MODE0, CDR_PD_SEL_MODE0(2) | EN_DLL_MODE0 | EN_IQ_DCC_MODE0 | EN_IQCAL_MODE0}, diff --git a/drivers/net/ethernet/realtek/8139cp.c b/drivers/net/ethernet/realtek/8139cp.c index 672f6b696069..72233ab9474b 100644 --- a/drivers/net/ethernet/realtek/8139cp.c +++ b/drivers/net/ethernet/realtek/8139cp.c @@ -1406,27 +1406,29 @@ static int cp_get_sset_count (struct net_device *dev, int sset) } } -static int cp_get_settings(struct net_device *dev, struct ethtool_cmd *cmd) +static int cp_get_link_ksettings(struct net_device *dev, + struct ethtool_link_ksettings *cmd) { struct cp_private *cp = netdev_priv(dev); int rc; unsigned long flags; spin_lock_irqsave(&cp->lock, flags); - rc = mii_ethtool_gset(&cp->mii_if, cmd); + rc = mii_ethtool_get_link_ksettings(&cp->mii_if, cmd); spin_unlock_irqrestore(&cp->lock, flags); return rc; } -static int cp_set_settings(struct net_device *dev, struct ethtool_cmd *cmd) +static int cp_set_link_ksettings(struct net_device *dev, + const struct ethtool_link_ksettings *cmd) { struct cp_private *cp = netdev_priv(dev); int rc; unsigned long flags; spin_lock_irqsave(&cp->lock, flags); - rc = mii_ethtool_sset(&cp->mii_if, cmd); + rc = mii_ethtool_set_link_ksettings(&cp->mii_if, cmd); spin_unlock_irqrestore(&cp->lock, flags); return rc; @@ -1578,8 +1580,6 @@ static const struct ethtool_ops cp_ethtool_ops = { .get_drvinfo = cp_get_drvinfo, .get_regs_len = cp_get_regs_len, .get_sset_count = cp_get_sset_count, - .get_settings = cp_get_settings, - .set_settings = cp_set_settings, .nway_reset = cp_nway_reset, .get_link = ethtool_op_get_link, .get_msglevel = cp_get_msglevel, @@ -1593,6 +1593,8 @@ static const struct ethtool_ops cp_ethtool_ops = { .get_eeprom = cp_get_eeprom, .set_eeprom = cp_set_eeprom, .get_ringparam = cp_get_ringparam, + .get_link_ksettings = cp_get_link_ksettings, + .set_link_ksettings = cp_set_link_ksettings, }; static int cp_ioctl (struct net_device *dev, struct ifreq *rq, int cmd) diff --git a/drivers/net/ethernet/realtek/8139too.c b/drivers/net/ethernet/realtek/8139too.c index 89631753e799..ca22f2898664 100644 --- a/drivers/net/ethernet/realtek/8139too.c +++ b/drivers/net/ethernet/realtek/8139too.c @@ -2384,21 +2384,23 @@ static void rtl8139_get_drvinfo(struct net_device *dev, struct ethtool_drvinfo * strlcpy(info->bus_info, pci_name(tp->pci_dev), sizeof(info->bus_info)); } -static int rtl8139_get_settings(struct net_device *dev, struct ethtool_cmd *cmd) +static int rtl8139_get_link_ksettings(struct net_device *dev, + struct ethtool_link_ksettings *cmd) { struct rtl8139_private *tp = netdev_priv(dev); spin_lock_irq(&tp->lock); - mii_ethtool_gset(&tp->mii, cmd); + mii_ethtool_get_link_ksettings(&tp->mii, cmd); spin_unlock_irq(&tp->lock); return 0; } -static int rtl8139_set_settings(struct net_device *dev, struct ethtool_cmd *cmd) +static int rtl8139_set_link_ksettings(struct net_device *dev, + const struct ethtool_link_ksettings *cmd) { struct rtl8139_private *tp = netdev_priv(dev); int rc; spin_lock_irq(&tp->lock); - rc = mii_ethtool_sset(&tp->mii, cmd); + rc = mii_ethtool_set_link_ksettings(&tp->mii, cmd); spin_unlock_irq(&tp->lock); return rc; } @@ -2480,8 +2482,6 @@ static void rtl8139_get_strings(struct net_device *dev, u32 stringset, u8 *data) static const struct ethtool_ops rtl8139_ethtool_ops = { .get_drvinfo = rtl8139_get_drvinfo, - .get_settings = rtl8139_get_settings, - .set_settings = rtl8139_set_settings, .get_regs_len = rtl8139_get_regs_len, .get_regs = rtl8139_get_regs, .nway_reset = rtl8139_nway_reset, @@ -2493,6 +2493,8 @@ static const struct ethtool_ops rtl8139_ethtool_ops = { .get_strings = rtl8139_get_strings, .get_sset_count = rtl8139_get_sset_count, .get_ethtool_stats = rtl8139_get_ethtool_stats, + .get_link_ksettings = rtl8139_get_link_ksettings, + .set_link_ksettings = rtl8139_set_link_ksettings, }; static int netdev_ioctl(struct net_device *dev, struct ifreq *rq, int cmd) diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c index 81f18a833527..0a8f2817ea60 100644 --- a/drivers/net/ethernet/realtek/r8169.c +++ b/drivers/net/ethernet/realtek/r8169.c @@ -817,7 +817,8 @@ struct rtl8169_private { } csi_ops; int (*set_speed)(struct net_device *, u8 aneg, u16 sp, u8 dpx, u32 adv); - int (*get_settings)(struct net_device *, struct ethtool_cmd *); + int (*get_link_ksettings)(struct net_device *, + struct ethtool_link_ksettings *); void (*phy_reset_enable)(struct rtl8169_private *tp); void (*hw_start)(struct net_device *); unsigned int (*phy_reset_pending)(struct rtl8169_private *tp); @@ -2115,41 +2116,49 @@ static void rtl8169_rx_vlan_tag(struct RxDesc *desc, struct sk_buff *skb) __vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), swab16(opts2 & 0xffff)); } -static int rtl8169_gset_tbi(struct net_device *dev, struct ethtool_cmd *cmd) +static int rtl8169_get_link_ksettings_tbi(struct net_device *dev, + struct ethtool_link_ksettings *cmd) { struct rtl8169_private *tp = netdev_priv(dev); void __iomem *ioaddr = tp->mmio_addr; u32 status; + u32 supported, advertising; - cmd->supported = + supported = SUPPORTED_1000baseT_Full | SUPPORTED_Autoneg | SUPPORTED_FIBRE; - cmd->port = PORT_FIBRE; - cmd->transceiver = XCVR_INTERNAL; + cmd->base.port = PORT_FIBRE; status = RTL_R32(TBICSR); - cmd->advertising = (status & TBINwEnable) ? ADVERTISED_Autoneg : 0; - cmd->autoneg = !!(status & TBINwEnable); + advertising = (status & TBINwEnable) ? ADVERTISED_Autoneg : 0; + cmd->base.autoneg = !!(status & TBINwEnable); - ethtool_cmd_speed_set(cmd, SPEED_1000); - cmd->duplex = DUPLEX_FULL; /* Always set */ + cmd->base.speed = SPEED_1000; + cmd->base.duplex = DUPLEX_FULL; /* Always set */ + + ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.supported, + supported); + ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.advertising, + advertising); return 0; } -static int rtl8169_gset_xmii(struct net_device *dev, struct ethtool_cmd *cmd) +static int rtl8169_get_link_ksettings_xmii(struct net_device *dev, + struct ethtool_link_ksettings *cmd) { struct rtl8169_private *tp = netdev_priv(dev); - return mii_ethtool_gset(&tp->mii, cmd); + return mii_ethtool_get_link_ksettings(&tp->mii, cmd); } -static int rtl8169_get_settings(struct net_device *dev, struct ethtool_cmd *cmd) +static int rtl8169_get_link_ksettings(struct net_device *dev, + struct ethtool_link_ksettings *cmd) { struct rtl8169_private *tp = netdev_priv(dev); int rc; rtl_lock_work(tp); - rc = tp->get_settings(dev, cmd); + rc = tp->get_link_ksettings(dev, cmd); rtl_unlock_work(tp); return rc; @@ -2356,7 +2365,6 @@ static const struct ethtool_ops rtl8169_ethtool_ops = { .get_drvinfo = rtl8169_get_drvinfo, .get_regs_len = rtl8169_get_regs_len, .get_link = ethtool_op_get_link, - .get_settings = rtl8169_get_settings, .set_settings = rtl8169_set_settings, .get_msglevel = rtl8169_get_msglevel, .set_msglevel = rtl8169_set_msglevel, @@ -2368,6 +2376,7 @@ static const struct ethtool_ops rtl8169_ethtool_ops = { .get_ethtool_stats = rtl8169_get_ethtool_stats, .get_ts_info = ethtool_op_get_ts_info, .nway_reset = rtl8169_nway_reset, + .get_link_ksettings = rtl8169_get_link_ksettings, }; static void rtl8169_get_mac_version(struct rtl8169_private *tp, @@ -8351,14 +8360,14 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) if (rtl_tbi_enabled(tp)) { tp->set_speed = rtl8169_set_speed_tbi; - tp->get_settings = rtl8169_gset_tbi; + tp->get_link_ksettings = rtl8169_get_link_ksettings_tbi; tp->phy_reset_enable = rtl8169_tbi_reset_enable; tp->phy_reset_pending = rtl8169_tbi_reset_pending; tp->link_ok = rtl8169_tbi_link_ok; tp->do_ioctl = rtl_tbi_ioctl; } else { tp->set_speed = rtl8169_set_speed_xmii; - tp->get_settings = rtl8169_gset_xmii; + tp->get_link_ksettings = rtl8169_get_link_ksettings_xmii; tp->phy_reset_enable = rtl8169_xmii_reset_enable; tp->phy_reset_pending = rtl8169_xmii_reset_pending; tp->link_ok = rtl8169_xmii_link_ok; @@ -8444,9 +8453,7 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) tp->opts1_mask = (tp->mac_version != RTL_GIGA_MAC_VER_01) ? ~(RxBOVF | RxFOVF) : ~0; - init_timer(&tp->timer); - tp->timer.data = (unsigned long) dev; - tp->timer.function = rtl8169_phy_timer; + setup_timer(&tp->timer, rtl8169_phy_timer, (unsigned long)dev); tp->rtl_fw = RTL_FIRMWARE_UNKNOWN; diff --git a/drivers/net/ethernet/rocker/rocker_main.c b/drivers/net/ethernet/rocker/rocker_main.c index 0f63a44a955d..bab13613b138 100644 --- a/drivers/net/ethernet/rocker/rocker_main.c +++ b/drivers/net/ethernet/rocker/rocker_main.c @@ -33,6 +33,7 @@ #include <net/rtnetlink.h> #include <net/netevent.h> #include <net/arp.h> +#include <net/fib_rules.h> #include <linux/io-64-nonatomic-lo-hi.h> #include <generated/utsrelease.h> @@ -1115,7 +1116,7 @@ rocker_cmd_get_port_settings_ethtool_proc(const struct rocker_port *rocker_port, const struct rocker_desc_info *desc_info, void *priv) { - struct ethtool_cmd *ecmd = priv; + struct ethtool_link_ksettings *ecmd = priv; const struct rocker_tlv *attrs[ROCKER_TLV_CMD_MAX + 1]; const struct rocker_tlv *info_attrs[ROCKER_TLV_CMD_PORT_SETTINGS_MAX + 1]; u32 speed; @@ -1137,13 +1138,14 @@ rocker_cmd_get_port_settings_ethtool_proc(const struct rocker_port *rocker_port, duplex = rocker_tlv_get_u8(info_attrs[ROCKER_TLV_CMD_PORT_SETTINGS_DUPLEX]); autoneg = rocker_tlv_get_u8(info_attrs[ROCKER_TLV_CMD_PORT_SETTINGS_AUTONEG]); - ecmd->transceiver = XCVR_INTERNAL; - ecmd->supported = SUPPORTED_TP; - ecmd->phy_address = 0xff; - ecmd->port = PORT_TP; - ethtool_cmd_speed_set(ecmd, speed); - ecmd->duplex = duplex ? DUPLEX_FULL : DUPLEX_HALF; - ecmd->autoneg = autoneg ? AUTONEG_ENABLE : AUTONEG_DISABLE; + ethtool_link_ksettings_zero_link_mode(ecmd, supported); + ethtool_link_ksettings_add_link_mode(ecmd, supported, TP); + + ecmd->base.phy_address = 0xff; + ecmd->base.port = PORT_TP; + ecmd->base.speed = speed; + ecmd->base.duplex = duplex ? DUPLEX_FULL : DUPLEX_HALF; + ecmd->base.autoneg = autoneg ? AUTONEG_ENABLE : AUTONEG_DISABLE; return 0; } @@ -1250,7 +1252,7 @@ rocker_cmd_set_port_settings_ethtool_prep(const struct rocker_port *rocker_port, struct rocker_desc_info *desc_info, void *priv) { - struct ethtool_cmd *ecmd = priv; + struct ethtool_link_ksettings *ecmd = priv; struct rocker_tlv *cmd_info; if (rocker_tlv_put_u16(desc_info, ROCKER_TLV_CMD_TYPE, @@ -1263,13 +1265,13 @@ rocker_cmd_set_port_settings_ethtool_prep(const struct rocker_port *rocker_port, rocker_port->pport)) return -EMSGSIZE; if (rocker_tlv_put_u32(desc_info, ROCKER_TLV_CMD_PORT_SETTINGS_SPEED, - ethtool_cmd_speed(ecmd))) + ecmd->base.speed)) return -EMSGSIZE; if (rocker_tlv_put_u8(desc_info, ROCKER_TLV_CMD_PORT_SETTINGS_DUPLEX, - ecmd->duplex)) + ecmd->base.duplex)) return -EMSGSIZE; if (rocker_tlv_put_u8(desc_info, ROCKER_TLV_CMD_PORT_SETTINGS_AUTONEG, - ecmd->autoneg)) + ecmd->base.autoneg)) return -EMSGSIZE; rocker_tlv_nest_end(desc_info, cmd_info); return 0; @@ -1347,8 +1349,9 @@ rocker_cmd_set_port_learning_prep(const struct rocker_port *rocker_port, return 0; } -static int rocker_cmd_get_port_settings_ethtool(struct rocker_port *rocker_port, - struct ethtool_cmd *ecmd) +static int +rocker_cmd_get_port_settings_ethtool(struct rocker_port *rocker_port, + struct ethtool_link_ksettings *ecmd) { return rocker_cmd_exec(rocker_port, false, rocker_cmd_get_port_settings_prep, NULL, @@ -1373,12 +1376,17 @@ static int rocker_cmd_get_port_settings_mode(struct rocker_port *rocker_port, rocker_cmd_get_port_settings_mode_proc, p_mode); } -static int rocker_cmd_set_port_settings_ethtool(struct rocker_port *rocker_port, - struct ethtool_cmd *ecmd) +static int +rocker_cmd_set_port_settings_ethtool(struct rocker_port *rocker_port, + const struct ethtool_link_ksettings *ecmd) { + struct ethtool_link_ksettings copy_ecmd; + + memcpy(©_ecmd, ecmd, sizeof(copy_ecmd)); + return rocker_cmd_exec(rocker_port, false, rocker_cmd_set_port_settings_ethtool_prep, - ecmd, NULL, NULL); + ©_ecmd, NULL, NULL); } static int rocker_cmd_set_port_settings_macaddr(struct rocker_port *rocker_port, @@ -2168,7 +2176,10 @@ static const struct switchdev_ops rocker_port_switchdev_ops = { struct rocker_fib_event_work { struct work_struct work; - struct fib_entry_notifier_info fen_info; + union { + struct fib_entry_notifier_info fen_info; + struct fib_rule_notifier_info fr_info; + }; struct rocker *rocker; unsigned long event; }; @@ -2178,6 +2189,7 @@ static void rocker_router_fib_event_work(struct work_struct *work) struct rocker_fib_event_work *fib_work = container_of(work, struct rocker_fib_event_work, work); struct rocker *rocker = fib_work->rocker; + struct fib_rule *rule; int err; /* Protect internal structures from changes */ @@ -2195,7 +2207,10 @@ static void rocker_router_fib_event_work(struct work_struct *work) break; case FIB_EVENT_RULE_ADD: /* fall through */ case FIB_EVENT_RULE_DEL: - rocker_world_fib4_abort(rocker); + rule = fib_work->fr_info.rule; + if (!fib4_rule_default(rule)) + rocker_world_fib4_abort(rocker); + fib_rule_put(rule); break; } rtnl_unlock(); @@ -2226,6 +2241,11 @@ static int rocker_router_fib_event(struct notifier_block *nb, */ fib_info_hold(fib_work->fen_info.fi); break; + case FIB_EVENT_RULE_ADD: /* fall through */ + case FIB_EVENT_RULE_DEL: + memcpy(&fib_work->fr_info, ptr, sizeof(fib_work->fr_info)); + fib_rule_get(fib_work->fr_info.rule); + break; } queue_work(rocker->rocker_owq, &fib_work->work); @@ -2237,16 +2257,18 @@ static int rocker_router_fib_event(struct notifier_block *nb, * ethtool interface ********************/ -static int rocker_port_get_settings(struct net_device *dev, - struct ethtool_cmd *ecmd) +static int +rocker_port_get_link_ksettings(struct net_device *dev, + struct ethtool_link_ksettings *ecmd) { struct rocker_port *rocker_port = netdev_priv(dev); return rocker_cmd_get_port_settings_ethtool(rocker_port, ecmd); } -static int rocker_port_set_settings(struct net_device *dev, - struct ethtool_cmd *ecmd) +static int +rocker_port_set_link_ksettings(struct net_device *dev, + const struct ethtool_link_ksettings *ecmd) { struct rocker_port *rocker_port = netdev_priv(dev); @@ -2388,13 +2410,13 @@ static int rocker_port_get_sset_count(struct net_device *netdev, int sset) } static const struct ethtool_ops rocker_port_ethtool_ops = { - .get_settings = rocker_port_get_settings, - .set_settings = rocker_port_set_settings, .get_drvinfo = rocker_port_get_drvinfo, .get_link = ethtool_op_get_link, .get_strings = rocker_port_get_strings, .get_ethtool_stats = rocker_port_get_stats, .get_sset_count = rocker_port_get_sset_count, + .get_link_ksettings = rocker_port_get_link_ksettings, + .set_link_ksettings = rocker_port_set_link_ksettings, }; /***************** diff --git a/drivers/net/ethernet/sfc/falcon/tx.c b/drivers/net/ethernet/sfc/falcon/tx.c index 104fb15a73f2..f6daf09b8627 100644 --- a/drivers/net/ethernet/sfc/falcon/tx.c +++ b/drivers/net/ethernet/sfc/falcon/tx.c @@ -437,11 +437,13 @@ int ef4_setup_tc(struct net_device *net_dev, u32 handle, __be16 proto, if (ntc->type != TC_SETUP_MQPRIO) return -EINVAL; - num_tc = ntc->tc; + num_tc = ntc->mqprio->num_tc; if (ef4_nic_rev(efx) < EF4_REV_FALCON_B0 || num_tc > EF4_MAX_TX_TC) return -EINVAL; + ntc->mqprio->hw = TC_MQPRIO_HW_OFFLOAD_TCS; + if (num_tc == net_dev->num_tc) return 0; diff --git a/drivers/net/ethernet/sfc/tx.c b/drivers/net/ethernet/sfc/tx.c index ff88d60aa6d5..3bdf87f31087 100644 --- a/drivers/net/ethernet/sfc/tx.c +++ b/drivers/net/ethernet/sfc/tx.c @@ -665,11 +665,13 @@ int efx_setup_tc(struct net_device *net_dev, u32 handle, __be16 proto, if (ntc->type != TC_SETUP_MQPRIO) return -EINVAL; - num_tc = ntc->tc; + num_tc = ntc->mqprio->num_tc; if (num_tc > EFX_MAX_TX_TC) return -EINVAL; + ntc->mqprio->hw = TC_MQPRIO_HW_OFFLOAD_TCS; + if (num_tc == net_dev->num_tc) return 0; diff --git a/drivers/net/ethernet/sgi/ioc3-eth.c b/drivers/net/ethernet/sgi/ioc3-eth.c index 57e6cef81ebe..52ead5524de7 100644 --- a/drivers/net/ethernet/sgi/ioc3-eth.c +++ b/drivers/net/ethernet/sgi/ioc3-eth.c @@ -1558,25 +1558,27 @@ static void ioc3_get_drvinfo (struct net_device *dev, strlcpy(info->bus_info, pci_name(ip->pdev), sizeof(info->bus_info)); } -static int ioc3_get_settings(struct net_device *dev, struct ethtool_cmd *cmd) +static int ioc3_get_link_ksettings(struct net_device *dev, + struct ethtool_link_ksettings *cmd) { struct ioc3_private *ip = netdev_priv(dev); int rc; spin_lock_irq(&ip->ioc3_lock); - rc = mii_ethtool_gset(&ip->mii, cmd); + rc = mii_ethtool_get_link_ksettings(&ip->mii, cmd); spin_unlock_irq(&ip->ioc3_lock); return rc; } -static int ioc3_set_settings(struct net_device *dev, struct ethtool_cmd *cmd) +static int ioc3_set_link_ksettings(struct net_device *dev, + const struct ethtool_link_ksettings *cmd) { struct ioc3_private *ip = netdev_priv(dev); int rc; spin_lock_irq(&ip->ioc3_lock); - rc = mii_ethtool_sset(&ip->mii, cmd); + rc = mii_ethtool_set_link_ksettings(&ip->mii, cmd); spin_unlock_irq(&ip->ioc3_lock); return rc; @@ -1608,10 +1610,10 @@ static u32 ioc3_get_link(struct net_device *dev) static const struct ethtool_ops ioc3_ethtool_ops = { .get_drvinfo = ioc3_get_drvinfo, - .get_settings = ioc3_get_settings, - .set_settings = ioc3_set_settings, .nway_reset = ioc3_nway_reset, .get_link = ioc3_get_link, + .get_link_ksettings = ioc3_get_link_ksettings, + .set_link_ksettings = ioc3_set_link_ksettings, }; static int ioc3_ioctl(struct net_device *dev, struct ifreq *rq, int cmd) diff --git a/drivers/net/ethernet/silan/sc92031.c b/drivers/net/ethernet/silan/sc92031.c index 6c2e2b311c16..751c81848f35 100644 --- a/drivers/net/ethernet/silan/sc92031.c +++ b/drivers/net/ethernet/silan/sc92031.c @@ -1122,14 +1122,16 @@ static void sc92031_poll_controller(struct net_device *dev) } #endif -static int sc92031_ethtool_get_settings(struct net_device *dev, - struct ethtool_cmd *cmd) +static int +sc92031_ethtool_get_link_ksettings(struct net_device *dev, + struct ethtool_link_ksettings *cmd) { struct sc92031_priv *priv = netdev_priv(dev); void __iomem *port_base = priv->port_base; u8 phy_address; u32 phy_ctrl; u16 output_status; + u32 supported, advertising; spin_lock_bh(&priv->lock); @@ -1142,68 +1144,77 @@ static int sc92031_ethtool_get_settings(struct net_device *dev, spin_unlock_bh(&priv->lock); - cmd->supported = SUPPORTED_10baseT_Half | SUPPORTED_10baseT_Full + supported = SUPPORTED_10baseT_Half | SUPPORTED_10baseT_Full | SUPPORTED_100baseT_Half | SUPPORTED_100baseT_Full | SUPPORTED_Autoneg | SUPPORTED_TP | SUPPORTED_MII; - cmd->advertising = ADVERTISED_TP | ADVERTISED_MII; + advertising = ADVERTISED_TP | ADVERTISED_MII; if ((phy_ctrl & (PhyCtrlDux | PhyCtrlSpd100 | PhyCtrlSpd10)) == (PhyCtrlDux | PhyCtrlSpd100 | PhyCtrlSpd10)) - cmd->advertising |= ADVERTISED_Autoneg; + advertising |= ADVERTISED_Autoneg; if ((phy_ctrl & PhyCtrlSpd10) == PhyCtrlSpd10) - cmd->advertising |= ADVERTISED_10baseT_Half; + advertising |= ADVERTISED_10baseT_Half; if ((phy_ctrl & (PhyCtrlSpd10 | PhyCtrlDux)) == (PhyCtrlSpd10 | PhyCtrlDux)) - cmd->advertising |= ADVERTISED_10baseT_Full; + advertising |= ADVERTISED_10baseT_Full; if ((phy_ctrl & PhyCtrlSpd100) == PhyCtrlSpd100) - cmd->advertising |= ADVERTISED_100baseT_Half; + advertising |= ADVERTISED_100baseT_Half; if ((phy_ctrl & (PhyCtrlSpd100 | PhyCtrlDux)) == (PhyCtrlSpd100 | PhyCtrlDux)) - cmd->advertising |= ADVERTISED_100baseT_Full; + advertising |= ADVERTISED_100baseT_Full; if (phy_ctrl & PhyCtrlAne) - cmd->advertising |= ADVERTISED_Autoneg; + advertising |= ADVERTISED_Autoneg; - ethtool_cmd_speed_set(cmd, - (output_status & 0x2) ? SPEED_100 : SPEED_10); - cmd->duplex = (output_status & 0x4) ? DUPLEX_FULL : DUPLEX_HALF; - cmd->port = PORT_MII; - cmd->phy_address = phy_address; - cmd->transceiver = XCVR_INTERNAL; - cmd->autoneg = (phy_ctrl & PhyCtrlAne) ? AUTONEG_ENABLE : AUTONEG_DISABLE; + cmd->base.speed = (output_status & 0x2) ? SPEED_100 : SPEED_10; + cmd->base.duplex = (output_status & 0x4) ? DUPLEX_FULL : DUPLEX_HALF; + cmd->base.port = PORT_MII; + cmd->base.phy_address = phy_address; + cmd->base.autoneg = (phy_ctrl & PhyCtrlAne) ? + AUTONEG_ENABLE : AUTONEG_DISABLE; + + ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.supported, + supported); + ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.advertising, + advertising); return 0; } -static int sc92031_ethtool_set_settings(struct net_device *dev, - struct ethtool_cmd *cmd) +static int +sc92031_ethtool_set_link_ksettings(struct net_device *dev, + const struct ethtool_link_ksettings *cmd) { struct sc92031_priv *priv = netdev_priv(dev); void __iomem *port_base = priv->port_base; - u32 speed = ethtool_cmd_speed(cmd); + u32 speed = cmd->base.speed; u32 phy_ctrl; u32 old_phy_ctrl; + u32 advertising; + + ethtool_convert_link_mode_to_legacy_u32(&advertising, + cmd->link_modes.advertising); if (!(speed == SPEED_10 || speed == SPEED_100)) return -EINVAL; - if (!(cmd->duplex == DUPLEX_HALF || cmd->duplex == DUPLEX_FULL)) - return -EINVAL; - if (!(cmd->port == PORT_MII)) + if (!(cmd->base.duplex == DUPLEX_HALF || + cmd->base.duplex == DUPLEX_FULL)) return -EINVAL; - if (!(cmd->phy_address == 0x1f)) + if (!(cmd->base.port == PORT_MII)) return -EINVAL; - if (!(cmd->transceiver == XCVR_INTERNAL)) + if (!(cmd->base.phy_address == 0x1f)) return -EINVAL; - if (!(cmd->autoneg == AUTONEG_DISABLE || cmd->autoneg == AUTONEG_ENABLE)) + if (!(cmd->base.autoneg == AUTONEG_DISABLE || + cmd->base.autoneg == AUTONEG_ENABLE)) return -EINVAL; - if (cmd->autoneg == AUTONEG_ENABLE) { - if (!(cmd->advertising & (ADVERTISED_Autoneg + if (cmd->base.autoneg == AUTONEG_ENABLE) { + if (!(advertising & (ADVERTISED_Autoneg | ADVERTISED_100baseT_Full | ADVERTISED_100baseT_Half | ADVERTISED_10baseT_Full @@ -1213,15 +1224,15 @@ static int sc92031_ethtool_set_settings(struct net_device *dev, phy_ctrl = PhyCtrlAne; // FIXME: I'm not sure what the original code was trying to do - if (cmd->advertising & ADVERTISED_Autoneg) + if (advertising & ADVERTISED_Autoneg) phy_ctrl |= PhyCtrlDux | PhyCtrlSpd100 | PhyCtrlSpd10; - if (cmd->advertising & ADVERTISED_100baseT_Full) + if (advertising & ADVERTISED_100baseT_Full) phy_ctrl |= PhyCtrlDux | PhyCtrlSpd100; - if (cmd->advertising & ADVERTISED_100baseT_Half) + if (advertising & ADVERTISED_100baseT_Half) phy_ctrl |= PhyCtrlSpd100; - if (cmd->advertising & ADVERTISED_10baseT_Full) + if (advertising & ADVERTISED_10baseT_Full) phy_ctrl |= PhyCtrlSpd10 | PhyCtrlDux; - if (cmd->advertising & ADVERTISED_10baseT_Half) + if (advertising & ADVERTISED_10baseT_Half) phy_ctrl |= PhyCtrlSpd10; } else { // FIXME: Whole branch guessed @@ -1232,7 +1243,7 @@ static int sc92031_ethtool_set_settings(struct net_device *dev, else /* cmd->speed == SPEED_100 */ phy_ctrl |= PhyCtrlSpd100; - if (cmd->duplex == DUPLEX_FULL) + if (cmd->base.duplex == DUPLEX_FULL) phy_ctrl |= PhyCtrlDux; } @@ -1368,8 +1379,6 @@ static void sc92031_ethtool_get_ethtool_stats(struct net_device *dev, } static const struct ethtool_ops sc92031_ethtool_ops = { - .get_settings = sc92031_ethtool_get_settings, - .set_settings = sc92031_ethtool_set_settings, .get_wol = sc92031_ethtool_get_wol, .set_wol = sc92031_ethtool_set_wol, .nway_reset = sc92031_ethtool_nway_reset, @@ -1377,6 +1386,8 @@ static const struct ethtool_ops sc92031_ethtool_ops = { .get_strings = sc92031_ethtool_get_strings, .get_sset_count = sc92031_ethtool_get_sset_count, .get_ethtool_stats = sc92031_ethtool_get_ethtool_stats, + .get_link_ksettings = sc92031_ethtool_get_link_ksettings, + .set_link_ksettings = sc92031_ethtool_set_link_ksettings, }; diff --git a/drivers/net/ethernet/sis/sis190.c b/drivers/net/ethernet/sis/sis190.c index 210e35d079dd..02da106c6e04 100644 --- a/drivers/net/ethernet/sis/sis190.c +++ b/drivers/net/ethernet/sis/sis190.c @@ -1734,18 +1734,20 @@ static void sis190_set_speed_auto(struct net_device *dev) BMCR_ANENABLE | BMCR_ANRESTART | BMCR_RESET); } -static int sis190_get_settings(struct net_device *dev, struct ethtool_cmd *cmd) +static int sis190_get_link_ksettings(struct net_device *dev, + struct ethtool_link_ksettings *cmd) { struct sis190_private *tp = netdev_priv(dev); - return mii_ethtool_gset(&tp->mii_if, cmd); + return mii_ethtool_get_link_ksettings(&tp->mii_if, cmd); } -static int sis190_set_settings(struct net_device *dev, struct ethtool_cmd *cmd) +static int sis190_set_link_ksettings(struct net_device *dev, + const struct ethtool_link_ksettings *cmd) { struct sis190_private *tp = netdev_priv(dev); - return mii_ethtool_sset(&tp->mii_if, cmd); + return mii_ethtool_set_link_ksettings(&tp->mii_if, cmd); } static void sis190_get_drvinfo(struct net_device *dev, @@ -1797,8 +1799,6 @@ static void sis190_set_msglevel(struct net_device *dev, u32 value) } static const struct ethtool_ops sis190_ethtool_ops = { - .get_settings = sis190_get_settings, - .set_settings = sis190_set_settings, .get_drvinfo = sis190_get_drvinfo, .get_regs_len = sis190_get_regs_len, .get_regs = sis190_get_regs, @@ -1806,6 +1806,8 @@ static const struct ethtool_ops sis190_ethtool_ops = { .get_msglevel = sis190_get_msglevel, .set_msglevel = sis190_set_msglevel, .nway_reset = sis190_nway_reset, + .get_link_ksettings = sis190_get_link_ksettings, + .set_link_ksettings = sis190_set_link_ksettings, }; static int sis190_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) diff --git a/drivers/net/ethernet/sis/sis900.c b/drivers/net/ethernet/sis/sis900.c index 1b6f6171d078..40bd88362e3d 100644 --- a/drivers/net/ethernet/sis/sis900.c +++ b/drivers/net/ethernet/sis/sis900.c @@ -2035,23 +2035,23 @@ static u32 sis900_get_link(struct net_device *net_dev) return mii_link_ok(&sis_priv->mii_info); } -static int sis900_get_settings(struct net_device *net_dev, - struct ethtool_cmd *cmd) +static int sis900_get_link_ksettings(struct net_device *net_dev, + struct ethtool_link_ksettings *cmd) { struct sis900_private *sis_priv = netdev_priv(net_dev); spin_lock_irq(&sis_priv->lock); - mii_ethtool_gset(&sis_priv->mii_info, cmd); + mii_ethtool_get_link_ksettings(&sis_priv->mii_info, cmd); spin_unlock_irq(&sis_priv->lock); return 0; } -static int sis900_set_settings(struct net_device *net_dev, - struct ethtool_cmd *cmd) +static int sis900_set_link_ksettings(struct net_device *net_dev, + const struct ethtool_link_ksettings *cmd) { struct sis900_private *sis_priv = netdev_priv(net_dev); int rt; spin_lock_irq(&sis_priv->lock); - rt = mii_ethtool_sset(&sis_priv->mii_info, cmd); + rt = mii_ethtool_set_link_ksettings(&sis_priv->mii_info, cmd); spin_unlock_irq(&sis_priv->lock); return rt; } @@ -2129,11 +2129,11 @@ static const struct ethtool_ops sis900_ethtool_ops = { .get_msglevel = sis900_get_msglevel, .set_msglevel = sis900_set_msglevel, .get_link = sis900_get_link, - .get_settings = sis900_get_settings, - .set_settings = sis900_set_settings, .nway_reset = sis900_nway_reset, .get_wol = sis900_get_wol, - .set_wol = sis900_set_wol + .set_wol = sis900_set_wol, + .get_link_ksettings = sis900_get_link_ksettings, + .set_link_ksettings = sis900_set_link_ksettings, }; /** diff --git a/drivers/net/ethernet/smsc/epic100.c b/drivers/net/ethernet/smsc/epic100.c index 5f2737189c72..db6dcb06193d 100644 --- a/drivers/net/ethernet/smsc/epic100.c +++ b/drivers/net/ethernet/smsc/epic100.c @@ -1387,25 +1387,27 @@ static void netdev_get_drvinfo (struct net_device *dev, struct ethtool_drvinfo * strlcpy(info->bus_info, pci_name(np->pci_dev), sizeof(info->bus_info)); } -static int netdev_get_settings(struct net_device *dev, struct ethtool_cmd *cmd) +static int netdev_get_link_ksettings(struct net_device *dev, + struct ethtool_link_ksettings *cmd) { struct epic_private *np = netdev_priv(dev); int rc; spin_lock_irq(&np->lock); - rc = mii_ethtool_gset(&np->mii, cmd); + rc = mii_ethtool_get_link_ksettings(&np->mii, cmd); spin_unlock_irq(&np->lock); return rc; } -static int netdev_set_settings(struct net_device *dev, struct ethtool_cmd *cmd) +static int netdev_set_link_ksettings(struct net_device *dev, + const struct ethtool_link_ksettings *cmd) { struct epic_private *np = netdev_priv(dev); int rc; spin_lock_irq(&np->lock); - rc = mii_ethtool_sset(&np->mii, cmd); + rc = mii_ethtool_set_link_ksettings(&np->mii, cmd); spin_unlock_irq(&np->lock); return rc; @@ -1460,14 +1462,14 @@ static void ethtool_complete(struct net_device *dev) static const struct ethtool_ops netdev_ethtool_ops = { .get_drvinfo = netdev_get_drvinfo, - .get_settings = netdev_get_settings, - .set_settings = netdev_set_settings, .nway_reset = netdev_nway_reset, .get_link = netdev_get_link, .get_msglevel = netdev_get_msglevel, .set_msglevel = netdev_set_msglevel, .begin = ethtool_begin, - .complete = ethtool_complete + .complete = ethtool_complete, + .get_link_ksettings = netdev_get_link_ksettings, + .set_link_ksettings = netdev_set_link_ksettings, }; static int netdev_ioctl(struct net_device *dev, struct ifreq *rq, int cmd) diff --git a/drivers/net/ethernet/smsc/smc911x.c b/drivers/net/ethernet/smsc/smc911x.c index 4f19c6166182..36307d34f641 100644 --- a/drivers/net/ethernet/smsc/smc911x.c +++ b/drivers/net/ethernet/smsc/smc911x.c @@ -1446,40 +1446,40 @@ static int smc911x_close(struct net_device *dev) * Ethtool support */ static int -smc911x_ethtool_getsettings(struct net_device *dev, struct ethtool_cmd *cmd) +smc911x_ethtool_get_link_ksettings(struct net_device *dev, + struct ethtool_link_ksettings *cmd) { struct smc911x_local *lp = netdev_priv(dev); int ret, status; unsigned long flags; + u32 supported; DBG(SMC_DEBUG_FUNC, dev, "--> %s\n", __func__); - cmd->maxtxpkt = 1; - cmd->maxrxpkt = 1; if (lp->phy_type != 0) { spin_lock_irqsave(&lp->lock, flags); - ret = mii_ethtool_gset(&lp->mii, cmd); + ret = mii_ethtool_get_link_ksettings(&lp->mii, cmd); spin_unlock_irqrestore(&lp->lock, flags); } else { - cmd->supported = SUPPORTED_10baseT_Half | + supported = SUPPORTED_10baseT_Half | SUPPORTED_10baseT_Full | SUPPORTED_TP | SUPPORTED_AUI; if (lp->ctl_rspeed == 10) - ethtool_cmd_speed_set(cmd, SPEED_10); + cmd->base.speed = SPEED_10; else if (lp->ctl_rspeed == 100) - ethtool_cmd_speed_set(cmd, SPEED_100); - - cmd->autoneg = AUTONEG_DISABLE; - if (lp->mii.phy_id==1) - cmd->transceiver = XCVR_INTERNAL; - else - cmd->transceiver = XCVR_EXTERNAL; - cmd->port = 0; + cmd->base.speed = SPEED_100; + + cmd->base.autoneg = AUTONEG_DISABLE; + cmd->base.port = 0; SMC_GET_PHY_SPECIAL(lp, lp->mii.phy_id, status); - cmd->duplex = + cmd->base.duplex = (status & (PHY_SPECIAL_SPD_10FULL_ | PHY_SPECIAL_SPD_100FULL_)) ? DUPLEX_FULL : DUPLEX_HALF; + + ethtool_convert_legacy_u32_to_link_mode( + cmd->link_modes.supported, supported); + ret = 0; } @@ -1487,7 +1487,8 @@ smc911x_ethtool_getsettings(struct net_device *dev, struct ethtool_cmd *cmd) } static int -smc911x_ethtool_setsettings(struct net_device *dev, struct ethtool_cmd *cmd) +smc911x_ethtool_set_link_ksettings(struct net_device *dev, + const struct ethtool_link_ksettings *cmd) { struct smc911x_local *lp = netdev_priv(dev); int ret; @@ -1495,16 +1496,18 @@ smc911x_ethtool_setsettings(struct net_device *dev, struct ethtool_cmd *cmd) if (lp->phy_type != 0) { spin_lock_irqsave(&lp->lock, flags); - ret = mii_ethtool_sset(&lp->mii, cmd); + ret = mii_ethtool_set_link_ksettings(&lp->mii, cmd); spin_unlock_irqrestore(&lp->lock, flags); } else { - if (cmd->autoneg != AUTONEG_DISABLE || - cmd->speed != SPEED_10 || - (cmd->duplex != DUPLEX_HALF && cmd->duplex != DUPLEX_FULL) || - (cmd->port != PORT_TP && cmd->port != PORT_AUI)) + if (cmd->base.autoneg != AUTONEG_DISABLE || + cmd->base.speed != SPEED_10 || + (cmd->base.duplex != DUPLEX_HALF && + cmd->base.duplex != DUPLEX_FULL) || + (cmd->base.port != PORT_TP && + cmd->base.port != PORT_AUI)) return -EINVAL; - lp->ctl_rfduplx = cmd->duplex == DUPLEX_FULL; + lp->ctl_rfduplx = cmd->base.duplex == DUPLEX_FULL; ret = 0; } @@ -1686,8 +1689,6 @@ static int smc911x_ethtool_geteeprom_len(struct net_device *dev) } static const struct ethtool_ops smc911x_ethtool_ops = { - .get_settings = smc911x_ethtool_getsettings, - .set_settings = smc911x_ethtool_setsettings, .get_drvinfo = smc911x_ethtool_getdrvinfo, .get_msglevel = smc911x_ethtool_getmsglevel, .set_msglevel = smc911x_ethtool_setmsglevel, @@ -1698,6 +1699,8 @@ static const struct ethtool_ops smc911x_ethtool_ops = { .get_eeprom_len = smc911x_ethtool_geteeprom_len, .get_eeprom = smc911x_ethtool_geteeprom, .set_eeprom = smc911x_ethtool_seteeprom, + .get_link_ksettings = smc911x_ethtool_get_link_ksettings, + .set_link_ksettings = smc911x_ethtool_set_link_ksettings, }; /* diff --git a/drivers/net/ethernet/smsc/smc91c92_cs.c b/drivers/net/ethernet/smsc/smc91c92_cs.c index 97280daba27f..976aa876789a 100644 --- a/drivers/net/ethernet/smsc/smc91c92_cs.c +++ b/drivers/net/ethernet/smsc/smc91c92_cs.c @@ -1843,56 +1843,60 @@ static int smc_link_ok(struct net_device *dev) } } -static int smc_netdev_get_ecmd(struct net_device *dev, struct ethtool_cmd *ecmd) +static int smc_netdev_get_ecmd(struct net_device *dev, + struct ethtool_link_ksettings *ecmd) { - u16 tmp; - unsigned int ioaddr = dev->base_addr; + u16 tmp; + unsigned int ioaddr = dev->base_addr; + u32 supported; - ecmd->supported = (SUPPORTED_TP | SUPPORTED_AUI | - SUPPORTED_10baseT_Half | SUPPORTED_10baseT_Full); - - SMC_SELECT_BANK(1); - tmp = inw(ioaddr + CONFIG); - ecmd->port = (tmp & CFG_AUI_SELECT) ? PORT_AUI : PORT_TP; - ecmd->transceiver = XCVR_INTERNAL; - ethtool_cmd_speed_set(ecmd, SPEED_10); - ecmd->phy_address = ioaddr + MGMT; + supported = (SUPPORTED_TP | SUPPORTED_AUI | + SUPPORTED_10baseT_Half | SUPPORTED_10baseT_Full); - SMC_SELECT_BANK(0); - tmp = inw(ioaddr + TCR); - ecmd->duplex = (tmp & TCR_FDUPLX) ? DUPLEX_FULL : DUPLEX_HALF; + SMC_SELECT_BANK(1); + tmp = inw(ioaddr + CONFIG); + ecmd->base.port = (tmp & CFG_AUI_SELECT) ? PORT_AUI : PORT_TP; + ecmd->base.speed = SPEED_10; + ecmd->base.phy_address = ioaddr + MGMT; - return 0; + SMC_SELECT_BANK(0); + tmp = inw(ioaddr + TCR); + ecmd->base.duplex = (tmp & TCR_FDUPLX) ? DUPLEX_FULL : DUPLEX_HALF; + + ethtool_convert_legacy_u32_to_link_mode(ecmd->link_modes.supported, + supported); + + return 0; } -static int smc_netdev_set_ecmd(struct net_device *dev, struct ethtool_cmd *ecmd) +static int smc_netdev_set_ecmd(struct net_device *dev, + const struct ethtool_link_ksettings *ecmd) { - u16 tmp; - unsigned int ioaddr = dev->base_addr; + u16 tmp; + unsigned int ioaddr = dev->base_addr; - if (ethtool_cmd_speed(ecmd) != SPEED_10) - return -EINVAL; - if (ecmd->duplex != DUPLEX_HALF && ecmd->duplex != DUPLEX_FULL) - return -EINVAL; - if (ecmd->port != PORT_TP && ecmd->port != PORT_AUI) - return -EINVAL; - if (ecmd->transceiver != XCVR_INTERNAL) - return -EINVAL; + if (ecmd->base.speed != SPEED_10) + return -EINVAL; + if (ecmd->base.duplex != DUPLEX_HALF && + ecmd->base.duplex != DUPLEX_FULL) + return -EINVAL; + if (ecmd->base.port != PORT_TP && ecmd->base.port != PORT_AUI) + return -EINVAL; - if (ecmd->port == PORT_AUI) - smc_set_xcvr(dev, 1); - else - smc_set_xcvr(dev, 0); + if (ecmd->base.port == PORT_AUI) + smc_set_xcvr(dev, 1); + else + smc_set_xcvr(dev, 0); - SMC_SELECT_BANK(0); - tmp = inw(ioaddr + TCR); - if (ecmd->duplex == DUPLEX_FULL) - tmp |= TCR_FDUPLX; - else - tmp &= ~TCR_FDUPLX; - outw(tmp, ioaddr + TCR); - - return 0; + SMC_SELECT_BANK(0); + tmp = inw(ioaddr + TCR); + if (ecmd->base.duplex == DUPLEX_FULL) + tmp |= TCR_FDUPLX; + else + tmp &= ~TCR_FDUPLX; + outw(tmp, ioaddr + TCR); + + return 0; } static int check_if_running(struct net_device *dev) @@ -1908,7 +1912,8 @@ static void smc_get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *info strlcpy(info->version, DRV_VERSION, sizeof(info->version)); } -static int smc_get_settings(struct net_device *dev, struct ethtool_cmd *ecmd) +static int smc_get_link_ksettings(struct net_device *dev, + struct ethtool_link_ksettings *ecmd) { struct smc_private *smc = netdev_priv(dev); unsigned int ioaddr = dev->base_addr; @@ -1919,7 +1924,7 @@ static int smc_get_settings(struct net_device *dev, struct ethtool_cmd *ecmd) spin_lock_irqsave(&smc->lock, flags); SMC_SELECT_BANK(3); if (smc->cfg & CFG_MII_SELECT) - ret = mii_ethtool_gset(&smc->mii_if, ecmd); + ret = mii_ethtool_get_link_ksettings(&smc->mii_if, ecmd); else ret = smc_netdev_get_ecmd(dev, ecmd); SMC_SELECT_BANK(saved_bank); @@ -1927,7 +1932,8 @@ static int smc_get_settings(struct net_device *dev, struct ethtool_cmd *ecmd) return ret; } -static int smc_set_settings(struct net_device *dev, struct ethtool_cmd *ecmd) +static int smc_set_link_ksettings(struct net_device *dev, + const struct ethtool_link_ksettings *ecmd) { struct smc_private *smc = netdev_priv(dev); unsigned int ioaddr = dev->base_addr; @@ -1938,7 +1944,7 @@ static int smc_set_settings(struct net_device *dev, struct ethtool_cmd *ecmd) spin_lock_irqsave(&smc->lock, flags); SMC_SELECT_BANK(3); if (smc->cfg & CFG_MII_SELECT) - ret = mii_ethtool_sset(&smc->mii_if, ecmd); + ret = mii_ethtool_set_link_ksettings(&smc->mii_if, ecmd); else ret = smc_netdev_set_ecmd(dev, ecmd); SMC_SELECT_BANK(saved_bank); @@ -1982,10 +1988,10 @@ static int smc_nway_reset(struct net_device *dev) static const struct ethtool_ops ethtool_ops = { .begin = check_if_running, .get_drvinfo = smc_get_drvinfo, - .get_settings = smc_get_settings, - .set_settings = smc_set_settings, .get_link = smc_get_link, .nway_reset = smc_nway_reset, + .get_link_ksettings = smc_get_link_ksettings, + .set_link_ksettings = smc_set_link_ksettings, }; static int smc_ioctl (struct net_device *dev, struct ifreq *rq, int cmd) diff --git a/drivers/net/ethernet/smsc/smc91x.c b/drivers/net/ethernet/smsc/smc91x.c index 65077c77082a..91e9bd7159ab 100644 --- a/drivers/net/ethernet/smsc/smc91x.c +++ b/drivers/net/ethernet/smsc/smc91x.c @@ -1535,32 +1535,33 @@ static int smc_close(struct net_device *dev) * Ethtool support */ static int -smc_ethtool_getsettings(struct net_device *dev, struct ethtool_cmd *cmd) +smc_ethtool_get_link_ksettings(struct net_device *dev, + struct ethtool_link_ksettings *cmd) { struct smc_local *lp = netdev_priv(dev); int ret; - cmd->maxtxpkt = 1; - cmd->maxrxpkt = 1; - if (lp->phy_type != 0) { spin_lock_irq(&lp->lock); - ret = mii_ethtool_gset(&lp->mii, cmd); + ret = mii_ethtool_get_link_ksettings(&lp->mii, cmd); spin_unlock_irq(&lp->lock); } else { - cmd->supported = SUPPORTED_10baseT_Half | + u32 supported = SUPPORTED_10baseT_Half | SUPPORTED_10baseT_Full | SUPPORTED_TP | SUPPORTED_AUI; if (lp->ctl_rspeed == 10) - ethtool_cmd_speed_set(cmd, SPEED_10); + cmd->base.speed = SPEED_10; else if (lp->ctl_rspeed == 100) - ethtool_cmd_speed_set(cmd, SPEED_100); + cmd->base.speed = SPEED_100; + + cmd->base.autoneg = AUTONEG_DISABLE; + cmd->base.port = 0; + cmd->base.duplex = lp->tcr_cur_mode & TCR_SWFDUP ? + DUPLEX_FULL : DUPLEX_HALF; - cmd->autoneg = AUTONEG_DISABLE; - cmd->transceiver = XCVR_INTERNAL; - cmd->port = 0; - cmd->duplex = lp->tcr_cur_mode & TCR_SWFDUP ? DUPLEX_FULL : DUPLEX_HALF; + ethtool_convert_legacy_u32_to_link_mode( + cmd->link_modes.supported, supported); ret = 0; } @@ -1569,24 +1570,26 @@ smc_ethtool_getsettings(struct net_device *dev, struct ethtool_cmd *cmd) } static int -smc_ethtool_setsettings(struct net_device *dev, struct ethtool_cmd *cmd) +smc_ethtool_set_link_ksettings(struct net_device *dev, + const struct ethtool_link_ksettings *cmd) { struct smc_local *lp = netdev_priv(dev); int ret; if (lp->phy_type != 0) { spin_lock_irq(&lp->lock); - ret = mii_ethtool_sset(&lp->mii, cmd); + ret = mii_ethtool_set_link_ksettings(&lp->mii, cmd); spin_unlock_irq(&lp->lock); } else { - if (cmd->autoneg != AUTONEG_DISABLE || - cmd->speed != SPEED_10 || - (cmd->duplex != DUPLEX_HALF && cmd->duplex != DUPLEX_FULL) || - (cmd->port != PORT_TP && cmd->port != PORT_AUI)) + if (cmd->base.autoneg != AUTONEG_DISABLE || + cmd->base.speed != SPEED_10 || + (cmd->base.duplex != DUPLEX_HALF && + cmd->base.duplex != DUPLEX_FULL) || + (cmd->base.port != PORT_TP && cmd->base.port != PORT_AUI)) return -EINVAL; -// lp->port = cmd->port; - lp->ctl_rfduplx = cmd->duplex == DUPLEX_FULL; +// lp->port = cmd->base.port; + lp->ctl_rfduplx = cmd->base.duplex == DUPLEX_FULL; // if (netif_running(dev)) // smc_set_port(dev); @@ -1744,8 +1747,6 @@ static int smc_ethtool_seteeprom(struct net_device *dev, static const struct ethtool_ops smc_ethtool_ops = { - .get_settings = smc_ethtool_getsettings, - .set_settings = smc_ethtool_setsettings, .get_drvinfo = smc_ethtool_getdrvinfo, .get_msglevel = smc_ethtool_getmsglevel, @@ -1755,6 +1756,8 @@ static const struct ethtool_ops smc_ethtool_ops = { .get_eeprom_len = smc_ethtool_geteeprom_len, .get_eeprom = smc_ethtool_geteeprom, .set_eeprom = smc_ethtool_seteeprom, + .get_link_ksettings = smc_ethtool_get_link_ksettings, + .set_link_ksettings = smc_ethtool_set_link_ksettings, }; static const struct net_device_ops smc_netdev_ops = { diff --git a/drivers/net/ethernet/stmicro/stmmac/common.h b/drivers/net/ethernet/stmicro/stmmac/common.h index 04d9245b7149..badc4414d67b 100644 --- a/drivers/net/ethernet/stmicro/stmmac/common.h +++ b/drivers/net/ethernet/stmicro/stmmac/common.h @@ -324,6 +324,9 @@ struct dma_features { unsigned int number_tx_queues; /* Alternate (enhanced) DESC mode */ unsigned int enh_desc; + /* TX and RX FIFO sizes */ + unsigned int tx_fifo_size; + unsigned int rx_fifo_size; }; /* GMAC TX FIFO is 8K, Rx FIFO is 16K */ @@ -413,6 +416,14 @@ struct stmmac_dma_ops { int (*reset)(void __iomem *ioaddr); void (*init)(void __iomem *ioaddr, struct stmmac_dma_cfg *dma_cfg, u32 dma_tx, u32 dma_rx, int atds); + void (*init_chan)(void __iomem *ioaddr, + struct stmmac_dma_cfg *dma_cfg, u32 chan); + void (*init_rx_chan)(void __iomem *ioaddr, + struct stmmac_dma_cfg *dma_cfg, + u32 dma_rx_phy, u32 chan); + void (*init_tx_chan)(void __iomem *ioaddr, + struct stmmac_dma_cfg *dma_cfg, + u32 dma_tx_phy, u32 chan); /* Configure the AXI Bus Mode Register */ void (*axi)(void __iomem *ioaddr, struct stmmac_axi *axi); /* Dump DMA registers */ @@ -421,25 +432,28 @@ struct stmmac_dma_ops { * An invalid value enables the store-and-forward mode */ void (*dma_mode)(void __iomem *ioaddr, int txmode, int rxmode, int rxfifosz); + void (*dma_rx_mode)(void __iomem *ioaddr, int mode, u32 channel, + int fifosz); + void (*dma_tx_mode)(void __iomem *ioaddr, int mode, u32 channel); /* To track extra statistic (if supported) */ void (*dma_diagnostic_fr) (void *data, struct stmmac_extra_stats *x, void __iomem *ioaddr); void (*enable_dma_transmission) (void __iomem *ioaddr); - void (*enable_dma_irq) (void __iomem *ioaddr); - void (*disable_dma_irq) (void __iomem *ioaddr); - void (*start_tx) (void __iomem *ioaddr); - void (*stop_tx) (void __iomem *ioaddr); - void (*start_rx) (void __iomem *ioaddr); - void (*stop_rx) (void __iomem *ioaddr); + void (*enable_dma_irq)(void __iomem *ioaddr, u32 chan); + void (*disable_dma_irq)(void __iomem *ioaddr, u32 chan); + void (*start_tx)(void __iomem *ioaddr, u32 chan); + void (*stop_tx)(void __iomem *ioaddr, u32 chan); + void (*start_rx)(void __iomem *ioaddr, u32 chan); + void (*stop_rx)(void __iomem *ioaddr, u32 chan); int (*dma_interrupt) (void __iomem *ioaddr, - struct stmmac_extra_stats *x); + struct stmmac_extra_stats *x, u32 chan); /* If supported then get the optional core features */ void (*get_hw_feature)(void __iomem *ioaddr, struct dma_features *dma_cap); /* Program the HW RX Watchdog */ - void (*rx_watchdog) (void __iomem *ioaddr, u32 riwt); - void (*set_tx_ring_len)(void __iomem *ioaddr, u32 len); - void (*set_rx_ring_len)(void __iomem *ioaddr, u32 len); + void (*rx_watchdog)(void __iomem *ioaddr, u32 riwt, u32 number_chan); + void (*set_tx_ring_len)(void __iomem *ioaddr, u32 len, u32 chan); + void (*set_rx_ring_len)(void __iomem *ioaddr, u32 len, u32 chan); void (*set_rx_tail_ptr)(void __iomem *ioaddr, u32 tail_ptr, u32 chan); void (*set_tx_tail_ptr)(void __iomem *ioaddr, u32 tail_ptr, u32 chan); void (*enable_tso)(void __iomem *ioaddr, bool en, u32 chan); @@ -454,17 +468,32 @@ struct stmmac_ops { /* Enable and verify that the IPC module is supported */ int (*rx_ipc)(struct mac_device_info *hw); /* Enable RX Queues */ - void (*rx_queue_enable)(struct mac_device_info *hw, u32 queue); + void (*rx_queue_enable)(struct mac_device_info *hw, u8 mode, u32 queue); + /* Program RX Algorithms */ + void (*prog_mtl_rx_algorithms)(struct mac_device_info *hw, u32 rx_alg); + /* Program TX Algorithms */ + void (*prog_mtl_tx_algorithms)(struct mac_device_info *hw, u32 tx_alg); + /* Set MTL TX queues weight */ + void (*set_mtl_tx_queue_weight)(struct mac_device_info *hw, + u32 weight, u32 queue); + /* RX MTL queue to RX dma mapping */ + void (*map_mtl_to_dma)(struct mac_device_info *hw, u32 queue, u32 chan); + /* Configure AV Algorithm */ + void (*config_cbs)(struct mac_device_info *hw, u32 send_slope, + u32 idle_slope, u32 high_credit, u32 low_credit, + u32 queue); /* Dump MAC registers */ void (*dump_regs)(struct mac_device_info *hw, u32 *reg_space); /* Handle extra events on specific interrupts hw dependent */ int (*host_irq_status)(struct mac_device_info *hw, struct stmmac_extra_stats *x); + /* Handle MTL interrupts */ + int (*host_mtl_irq_status)(struct mac_device_info *hw, u32 chan); /* Multicast filter setting */ void (*set_filter)(struct mac_device_info *hw, struct net_device *dev); /* Flow control setting */ void (*flow_ctrl)(struct mac_device_info *hw, unsigned int duplex, - unsigned int fc, unsigned int pause_time); + unsigned int fc, unsigned int pause_time, u32 tx_cnt); /* Set power management mode (e.g. magic frame) */ void (*pmt)(struct mac_device_info *hw, unsigned long mode); /* Set/Get Unicast MAC addresses */ @@ -477,7 +506,8 @@ struct stmmac_ops { void (*reset_eee_mode)(struct mac_device_info *hw); void (*set_eee_timer)(struct mac_device_info *hw, int ls, int tw); void (*set_eee_pls)(struct mac_device_info *hw, int link); - void (*debug)(void __iomem *ioaddr, struct stmmac_extra_stats *x); + void (*debug)(void __iomem *ioaddr, struct stmmac_extra_stats *x, + u32 rx_queues, u32 tx_queues); /* PCS calls */ void (*pcs_ctrl_ane)(void __iomem *ioaddr, bool ane, bool srgmi_ral, bool loopback); diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-dwc-qos-eth.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-dwc-qos-eth.c index 1a3fa3d9f855..dd6a2f9791cc 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-dwc-qos-eth.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-dwc-qos-eth.c @@ -14,16 +14,34 @@ #include <linux/clk.h> #include <linux/clk-provider.h> #include <linux/device.h> +#include <linux/gpio/consumer.h> #include <linux/ethtool.h> #include <linux/io.h> +#include <linux/iopoll.h> #include <linux/ioport.h> #include <linux/module.h> +#include <linux/of_device.h> #include <linux/of_net.h> #include <linux/mfd/syscon.h> #include <linux/platform_device.h> +#include <linux/reset.h> #include <linux/stmmac.h> #include "stmmac_platform.h" +#include "dwmac4.h" + +struct tegra_eqos { + struct device *dev; + void __iomem *regs; + + struct reset_control *rst; + struct clk *clk_master; + struct clk *clk_slave; + struct clk *clk_tx; + struct clk *clk_rx; + + struct gpio_desc *reset; +}; static int dwc_eth_dwmac_config_dt(struct platform_device *pdev, struct plat_stmmacenet_data *plat_dat) @@ -106,13 +124,309 @@ static int dwc_eth_dwmac_config_dt(struct platform_device *pdev, return 0; } +static void *dwc_qos_probe(struct platform_device *pdev, + struct plat_stmmacenet_data *plat_dat, + struct stmmac_resources *stmmac_res) +{ + int err; + + plat_dat->stmmac_clk = devm_clk_get(&pdev->dev, "apb_pclk"); + if (IS_ERR(plat_dat->stmmac_clk)) { + dev_err(&pdev->dev, "apb_pclk clock not found.\n"); + return ERR_CAST(plat_dat->stmmac_clk); + } + + err = clk_prepare_enable(plat_dat->stmmac_clk); + if (err < 0) { + dev_err(&pdev->dev, "failed to enable apb_pclk clock: %d\n", + err); + return ERR_PTR(err); + } + + plat_dat->pclk = devm_clk_get(&pdev->dev, "phy_ref_clk"); + if (IS_ERR(plat_dat->pclk)) { + dev_err(&pdev->dev, "phy_ref_clk clock not found.\n"); + err = PTR_ERR(plat_dat->pclk); + goto disable; + } + + err = clk_prepare_enable(plat_dat->pclk); + if (err < 0) { + dev_err(&pdev->dev, "failed to enable phy_ref clock: %d\n", + err); + goto disable; + } + + return NULL; + +disable: + clk_disable_unprepare(plat_dat->stmmac_clk); + return ERR_PTR(err); +} + +static int dwc_qos_remove(struct platform_device *pdev) +{ + struct net_device *ndev = platform_get_drvdata(pdev); + struct stmmac_priv *priv = netdev_priv(ndev); + + clk_disable_unprepare(priv->plat->pclk); + clk_disable_unprepare(priv->plat->stmmac_clk); + + return 0; +} + +#define SDMEMCOMPPADCTRL 0x8800 +#define SDMEMCOMPPADCTRL_PAD_E_INPUT_OR_E_PWRD BIT(31) + +#define AUTO_CAL_CONFIG 0x8804 +#define AUTO_CAL_CONFIG_START BIT(31) +#define AUTO_CAL_CONFIG_ENABLE BIT(29) + +#define AUTO_CAL_STATUS 0x880c +#define AUTO_CAL_STATUS_ACTIVE BIT(31) + +static void tegra_eqos_fix_speed(void *priv, unsigned int speed) +{ + struct tegra_eqos *eqos = priv; + unsigned long rate = 125000000; + bool needs_calibration = false; + u32 value; + int err; + + switch (speed) { + case SPEED_1000: + needs_calibration = true; + rate = 125000000; + break; + + case SPEED_100: + needs_calibration = true; + rate = 25000000; + break; + + case SPEED_10: + rate = 2500000; + break; + + default: + dev_err(eqos->dev, "invalid speed %u\n", speed); + break; + } + + if (needs_calibration) { + /* calibrate */ + value = readl(eqos->regs + SDMEMCOMPPADCTRL); + value |= SDMEMCOMPPADCTRL_PAD_E_INPUT_OR_E_PWRD; + writel(value, eqos->regs + SDMEMCOMPPADCTRL); + + udelay(1); + + value = readl(eqos->regs + AUTO_CAL_CONFIG); + value |= AUTO_CAL_CONFIG_START | AUTO_CAL_CONFIG_ENABLE; + writel(value, eqos->regs + AUTO_CAL_CONFIG); + + err = readl_poll_timeout_atomic(eqos->regs + AUTO_CAL_STATUS, + value, + value & AUTO_CAL_STATUS_ACTIVE, + 1, 10); + if (err < 0) { + dev_err(eqos->dev, "calibration did not start\n"); + goto failed; + } + + err = readl_poll_timeout_atomic(eqos->regs + AUTO_CAL_STATUS, + value, + (value & AUTO_CAL_STATUS_ACTIVE) == 0, + 20, 200); + if (err < 0) { + dev_err(eqos->dev, "calibration didn't finish\n"); + goto failed; + } + + failed: + value = readl(eqos->regs + SDMEMCOMPPADCTRL); + value &= ~SDMEMCOMPPADCTRL_PAD_E_INPUT_OR_E_PWRD; + writel(value, eqos->regs + SDMEMCOMPPADCTRL); + } else { + value = readl(eqos->regs + AUTO_CAL_CONFIG); + value &= ~AUTO_CAL_CONFIG_ENABLE; + writel(value, eqos->regs + AUTO_CAL_CONFIG); + } + + err = clk_set_rate(eqos->clk_tx, rate); + if (err < 0) + dev_err(eqos->dev, "failed to set TX rate: %d\n", err); +} + +static int tegra_eqos_init(struct platform_device *pdev, void *priv) +{ + struct tegra_eqos *eqos = priv; + unsigned long rate; + u32 value; + + rate = clk_get_rate(eqos->clk_slave); + + value = (rate / 1000000) - 1; + writel(value, eqos->regs + GMAC_1US_TIC_COUNTER); + + return 0; +} + +static void *tegra_eqos_probe(struct platform_device *pdev, + struct plat_stmmacenet_data *data, + struct stmmac_resources *res) +{ + struct tegra_eqos *eqos; + int err; + + eqos = devm_kzalloc(&pdev->dev, sizeof(*eqos), GFP_KERNEL); + if (!eqos) { + err = -ENOMEM; + goto error; + } + + eqos->dev = &pdev->dev; + eqos->regs = res->addr; + + eqos->clk_master = devm_clk_get(&pdev->dev, "master_bus"); + if (IS_ERR(eqos->clk_master)) { + err = PTR_ERR(eqos->clk_master); + goto error; + } + + err = clk_prepare_enable(eqos->clk_master); + if (err < 0) + goto error; + + eqos->clk_slave = devm_clk_get(&pdev->dev, "slave_bus"); + if (IS_ERR(eqos->clk_slave)) { + err = PTR_ERR(eqos->clk_slave); + goto disable_master; + } + + data->stmmac_clk = eqos->clk_slave; + + err = clk_prepare_enable(eqos->clk_slave); + if (err < 0) + goto disable_master; + + eqos->clk_rx = devm_clk_get(&pdev->dev, "rx"); + if (IS_ERR(eqos->clk_rx)) { + err = PTR_ERR(eqos->clk_rx); + goto disable_slave; + } + + err = clk_prepare_enable(eqos->clk_rx); + if (err < 0) + goto disable_slave; + + eqos->clk_tx = devm_clk_get(&pdev->dev, "tx"); + if (IS_ERR(eqos->clk_tx)) { + err = PTR_ERR(eqos->clk_tx); + goto disable_rx; + } + + err = clk_prepare_enable(eqos->clk_tx); + if (err < 0) + goto disable_rx; + + eqos->reset = devm_gpiod_get(&pdev->dev, "phy-reset", GPIOD_OUT_HIGH); + if (IS_ERR(eqos->reset)) { + err = PTR_ERR(eqos->reset); + goto disable_tx; + } + + usleep_range(2000, 4000); + gpiod_set_value(eqos->reset, 0); + + eqos->rst = devm_reset_control_get(&pdev->dev, "eqos"); + if (IS_ERR(eqos->rst)) { + err = PTR_ERR(eqos->rst); + goto reset_phy; + } + + err = reset_control_assert(eqos->rst); + if (err < 0) + goto reset_phy; + + usleep_range(2000, 4000); + + err = reset_control_deassert(eqos->rst); + if (err < 0) + goto reset_phy; + + usleep_range(2000, 4000); + + data->fix_mac_speed = tegra_eqos_fix_speed; + data->init = tegra_eqos_init; + data->bsp_priv = eqos; + + err = tegra_eqos_init(pdev, eqos); + if (err < 0) + goto reset; + +out: + return eqos; + +reset: + reset_control_assert(eqos->rst); +reset_phy: + gpiod_set_value(eqos->reset, 1); +disable_tx: + clk_disable_unprepare(eqos->clk_tx); +disable_rx: + clk_disable_unprepare(eqos->clk_rx); +disable_slave: + clk_disable_unprepare(eqos->clk_slave); +disable_master: + clk_disable_unprepare(eqos->clk_master); +error: + eqos = ERR_PTR(err); + goto out; +} + +static int tegra_eqos_remove(struct platform_device *pdev) +{ + struct tegra_eqos *eqos = get_stmmac_bsp_priv(&pdev->dev); + + reset_control_assert(eqos->rst); + gpiod_set_value(eqos->reset, 1); + clk_disable_unprepare(eqos->clk_tx); + clk_disable_unprepare(eqos->clk_rx); + clk_disable_unprepare(eqos->clk_slave); + clk_disable_unprepare(eqos->clk_master); + + return 0; +} + +struct dwc_eth_dwmac_data { + void *(*probe)(struct platform_device *pdev, + struct plat_stmmacenet_data *data, + struct stmmac_resources *res); + int (*remove)(struct platform_device *pdev); +}; + +static const struct dwc_eth_dwmac_data dwc_qos_data = { + .probe = dwc_qos_probe, + .remove = dwc_qos_remove, +}; + +static const struct dwc_eth_dwmac_data tegra_eqos_data = { + .probe = tegra_eqos_probe, + .remove = tegra_eqos_remove, +}; + static int dwc_eth_dwmac_probe(struct platform_device *pdev) { + const struct dwc_eth_dwmac_data *data; struct plat_stmmacenet_data *plat_dat; struct stmmac_resources stmmac_res; struct resource *res; + void *priv; int ret; + data = of_device_get_match_data(&pdev->dev); + memset(&stmmac_res, 0, sizeof(struct stmmac_resources)); /** @@ -138,39 +452,26 @@ static int dwc_eth_dwmac_probe(struct platform_device *pdev) if (IS_ERR(plat_dat)) return PTR_ERR(plat_dat); - plat_dat->stmmac_clk = devm_clk_get(&pdev->dev, "apb_pclk"); - if (IS_ERR(plat_dat->stmmac_clk)) { - dev_err(&pdev->dev, "apb_pclk clock not found.\n"); - ret = PTR_ERR(plat_dat->stmmac_clk); - plat_dat->stmmac_clk = NULL; - goto err_remove_config_dt; - } - clk_prepare_enable(plat_dat->stmmac_clk); - - plat_dat->pclk = devm_clk_get(&pdev->dev, "phy_ref_clk"); - if (IS_ERR(plat_dat->pclk)) { - dev_err(&pdev->dev, "phy_ref_clk clock not found.\n"); - ret = PTR_ERR(plat_dat->pclk); - plat_dat->pclk = NULL; - goto err_out_clk_dis_phy; + priv = data->probe(pdev, plat_dat, &stmmac_res); + if (IS_ERR(priv)) { + ret = PTR_ERR(priv); + dev_err(&pdev->dev, "failed to probe subdriver: %d\n", ret); + goto remove_config; } - clk_prepare_enable(plat_dat->pclk); ret = dwc_eth_dwmac_config_dt(pdev, plat_dat); if (ret) - goto err_out_clk_dis_aper; + goto remove; ret = stmmac_dvr_probe(&pdev->dev, plat_dat, &stmmac_res); if (ret) - goto err_out_clk_dis_aper; + goto remove; - return 0; + return ret; -err_out_clk_dis_aper: - clk_disable_unprepare(plat_dat->pclk); -err_out_clk_dis_phy: - clk_disable_unprepare(plat_dat->stmmac_clk); -err_remove_config_dt: +remove: + data->remove(pdev); +remove_config: stmmac_remove_config_dt(pdev, plat_dat); return ret; @@ -178,11 +479,29 @@ err_remove_config_dt: static int dwc_eth_dwmac_remove(struct platform_device *pdev) { - return stmmac_pltfr_remove(pdev); + struct net_device *ndev = platform_get_drvdata(pdev); + struct stmmac_priv *priv = netdev_priv(ndev); + const struct dwc_eth_dwmac_data *data; + int err; + + data = of_device_get_match_data(&pdev->dev); + + err = stmmac_dvr_remove(&pdev->dev); + if (err < 0) + dev_err(&pdev->dev, "failed to remove platform: %d\n", err); + + err = data->remove(pdev); + if (err < 0) + dev_err(&pdev->dev, "failed to remove subdriver: %d\n", err); + + stmmac_remove_config_dt(pdev, priv->plat); + + return err; } static const struct of_device_id dwc_eth_dwmac_match[] = { - { .compatible = "snps,dwc-qos-ethernet-4.10", }, + { .compatible = "snps,dwc-qos-ethernet-4.10", .data = &dwc_qos_data }, + { .compatible = "nvidia,tegra186-eqos", .data = &tegra_eqos_data }, { } }; MODULE_DEVICE_TABLE(of, dwc_eth_dwmac_match); diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c b/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c index 19b9b3087099..7f78f7746a5b 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c @@ -216,7 +216,8 @@ static void dwmac1000_set_filter(struct mac_device_info *hw, static void dwmac1000_flow_ctrl(struct mac_device_info *hw, unsigned int duplex, - unsigned int fc, unsigned int pause_time) + unsigned int fc, unsigned int pause_time, + u32 tx_cnt) { void __iomem *ioaddr = hw->pcsr; /* Set flow such that DZPQ in Mac Register 6 is 0, @@ -412,7 +413,8 @@ static void dwmac1000_get_adv_lp(void __iomem *ioaddr, struct rgmii_adv *adv) dwmac_get_adv_lp(ioaddr, GMAC_PCS_BASE, adv); } -static void dwmac1000_debug(void __iomem *ioaddr, struct stmmac_extra_stats *x) +static void dwmac1000_debug(void __iomem *ioaddr, struct stmmac_extra_stats *x, + u32 rx_queues, u32 tx_queues) { u32 value = readl(ioaddr + GMAC_DEBUG); diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac1000_dma.c b/drivers/net/ethernet/stmicro/stmmac/dwmac1000_dma.c index d3654a447046..471a9aa6ac94 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac1000_dma.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac1000_dma.c @@ -247,7 +247,8 @@ static void dwmac1000_get_hw_feature(void __iomem *ioaddr, dma_cap->enh_desc = (hw_cap & DMA_HW_FEAT_ENHDESSEL) >> 24; } -static void dwmac1000_rx_watchdog(void __iomem *ioaddr, u32 riwt) +static void dwmac1000_rx_watchdog(void __iomem *ioaddr, u32 riwt, + u32 number_chan) { writel(riwt, ioaddr + DMA_RX_WATCHDOG); } diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac100_core.c b/drivers/net/ethernet/stmicro/stmmac/dwmac100_core.c index e370ccec6176..524135e6dd89 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac100_core.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac100_core.c @@ -131,7 +131,8 @@ static void dwmac100_set_filter(struct mac_device_info *hw, } static void dwmac100_flow_ctrl(struct mac_device_info *hw, unsigned int duplex, - unsigned int fc, unsigned int pause_time) + unsigned int fc, unsigned int pause_time, + u32 tx_cnt) { void __iomem *ioaddr = hw->pcsr; unsigned int flow = MAC_FLOW_CTRL_ENABLE; diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4.h b/drivers/net/ethernet/stmicro/stmmac/dwmac4.h index db45134fddf0..54bcdb4d10db 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac4.h +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4.h @@ -25,6 +25,7 @@ #define GMAC_RXQ_CTRL0 0x000000a0 #define GMAC_INT_STATUS 0x000000b0 #define GMAC_INT_EN 0x000000b4 +#define GMAC_1US_TIC_COUNTER 0x000000dc #define GMAC_PCS_BASE 0x000000e0 #define GMAC_PHYIF_CONTROL_STATUS 0x000000f8 #define GMAC_PMT 0x000000c0 @@ -148,6 +149,8 @@ enum power_event { /* MAC HW features1 bitmap */ #define GMAC_HW_FEAT_AVSEL BIT(20) #define GMAC_HW_TSOEN BIT(18) +#define GMAC_HW_TXFIFOSIZE GENMASK(10, 6) +#define GMAC_HW_RXFIFOSIZE GENMASK(4, 0) /* MAC HW features2 bitmap */ #define GMAC_HW_FEAT_TXCHCNT GENMASK(21, 18) @@ -161,8 +164,25 @@ enum power_event { #define GMAC_HI_REG_AE BIT(31) /* MTL registers */ +#define MTL_OPERATION_MODE 0x00000c00 +#define MTL_OPERATION_SCHALG_MASK GENMASK(6, 5) +#define MTL_OPERATION_SCHALG_WRR (0x0 << 5) +#define MTL_OPERATION_SCHALG_WFQ (0x1 << 5) +#define MTL_OPERATION_SCHALG_DWRR (0x2 << 5) +#define MTL_OPERATION_SCHALG_SP (0x3 << 5) +#define MTL_OPERATION_RAA BIT(2) +#define MTL_OPERATION_RAA_SP (0x0 << 2) +#define MTL_OPERATION_RAA_WSP (0x1 << 2) + #define MTL_INT_STATUS 0x00000c20 -#define MTL_INT_Q0 BIT(0) +#define MTL_INT_QX(x) BIT(x) + +#define MTL_RXQ_DMA_MAP0 0x00000c30 /* queue 0 to 3 */ +#define MTL_RXQ_DMA_MAP1 0x00000c34 /* queue 4 to 7 */ +#define MTL_RXQ_DMA_Q04MDMACH_MASK GENMASK(3, 0) +#define MTL_RXQ_DMA_Q04MDMACH(x) ((x) << 0) +#define MTL_RXQ_DMA_QXMDMACH_MASK(x) GENMASK(11 + (8 * ((x) - 1)), 8 * (x)) +#define MTL_RXQ_DMA_QXMDMACH(chan, q) ((chan) << (8 * (q))) #define MTL_CHAN_BASE_ADDR 0x00000d00 #define MTL_CHAN_BASE_OFFSET 0x40 @@ -180,6 +200,7 @@ enum power_event { #define MTL_OP_MODE_TSF BIT(1) #define MTL_OP_MODE_TQS_MASK GENMASK(24, 16) +#define MTL_OP_MODE_TQS_SHIFT 16 #define MTL_OP_MODE_TTC_MASK 0x70 #define MTL_OP_MODE_TTC_SHIFT 4 @@ -193,6 +214,17 @@ enum power_event { #define MTL_OP_MODE_TTC_384 (6 << MTL_OP_MODE_TTC_SHIFT) #define MTL_OP_MODE_TTC_512 (7 << MTL_OP_MODE_TTC_SHIFT) +#define MTL_OP_MODE_RQS_MASK GENMASK(29, 20) +#define MTL_OP_MODE_RQS_SHIFT 20 + +#define MTL_OP_MODE_RFD_MASK GENMASK(19, 14) +#define MTL_OP_MODE_RFD_SHIFT 14 + +#define MTL_OP_MODE_RFA_MASK GENMASK(13, 8) +#define MTL_OP_MODE_RFA_SHIFT 8 + +#define MTL_OP_MODE_EHFC BIT(7) + #define MTL_OP_MODE_RTC_MASK 0x18 #define MTL_OP_MODE_RTC_SHIFT 3 @@ -201,6 +233,46 @@ enum power_event { #define MTL_OP_MODE_RTC_96 (2 << MTL_OP_MODE_RTC_SHIFT) #define MTL_OP_MODE_RTC_128 (3 << MTL_OP_MODE_RTC_SHIFT) +/* MTL ETS Control register */ +#define MTL_ETS_CTRL_BASE_ADDR 0x00000d10 +#define MTL_ETS_CTRL_BASE_OFFSET 0x40 +#define MTL_ETSX_CTRL_BASE_ADDR(x) (MTL_ETS_CTRL_BASE_ADDR + \ + ((x) * MTL_ETS_CTRL_BASE_OFFSET)) + +#define MTL_ETS_CTRL_CC BIT(3) +#define MTL_ETS_CTRL_AVALG BIT(2) + +/* MTL Queue Quantum Weight */ +#define MTL_TXQ_WEIGHT_BASE_ADDR 0x00000d18 +#define MTL_TXQ_WEIGHT_BASE_OFFSET 0x40 +#define MTL_TXQX_WEIGHT_BASE_ADDR(x) (MTL_TXQ_WEIGHT_BASE_ADDR + \ + ((x) * MTL_TXQ_WEIGHT_BASE_OFFSET)) +#define MTL_TXQ_WEIGHT_ISCQW_MASK GENMASK(20, 0) + +/* MTL sendSlopeCredit register */ +#define MTL_SEND_SLP_CRED_BASE_ADDR 0x00000d1c +#define MTL_SEND_SLP_CRED_OFFSET 0x40 +#define MTL_SEND_SLP_CREDX_BASE_ADDR(x) (MTL_SEND_SLP_CRED_BASE_ADDR + \ + ((x) * MTL_SEND_SLP_CRED_OFFSET)) + +#define MTL_SEND_SLP_CRED_SSC_MASK GENMASK(13, 0) + +/* MTL hiCredit register */ +#define MTL_HIGH_CRED_BASE_ADDR 0x00000d20 +#define MTL_HIGH_CRED_OFFSET 0x40 +#define MTL_HIGH_CREDX_BASE_ADDR(x) (MTL_HIGH_CRED_BASE_ADDR + \ + ((x) * MTL_HIGH_CRED_OFFSET)) + +#define MTL_HIGH_CRED_HC_MASK GENMASK(28, 0) + +/* MTL loCredit register */ +#define MTL_LOW_CRED_BASE_ADDR 0x00000d24 +#define MTL_LOW_CRED_OFFSET 0x40 +#define MTL_LOW_CREDX_BASE_ADDR(x) (MTL_LOW_CRED_BASE_ADDR + \ + ((x) * MTL_LOW_CRED_OFFSET)) + +#define MTL_HIGH_CRED_LC_MASK GENMASK(28, 0) + /* MTL debug */ #define MTL_DEBUG_TXSTSFSTS BIT(5) #define MTL_DEBUG_TXFSTS BIT(4) diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c index 1e79e6529c4a..10599dbc232f 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c @@ -59,17 +59,143 @@ static void dwmac4_core_init(struct mac_device_info *hw, int mtu) writel(value, ioaddr + GMAC_INT_EN); } -static void dwmac4_rx_queue_enable(struct mac_device_info *hw, u32 queue) +static void dwmac4_rx_queue_enable(struct mac_device_info *hw, + u8 mode, u32 queue) { void __iomem *ioaddr = hw->pcsr; u32 value = readl(ioaddr + GMAC_RXQ_CTRL0); value &= GMAC_RX_QUEUE_CLEAR(queue); - value |= GMAC_RX_AV_QUEUE_ENABLE(queue); + if (mode == MTL_QUEUE_AVB) + value |= GMAC_RX_AV_QUEUE_ENABLE(queue); + else if (mode == MTL_QUEUE_DCB) + value |= GMAC_RX_DCB_QUEUE_ENABLE(queue); writel(value, ioaddr + GMAC_RXQ_CTRL0); } +static void dwmac4_prog_mtl_rx_algorithms(struct mac_device_info *hw, + u32 rx_alg) +{ + void __iomem *ioaddr = hw->pcsr; + u32 value = readl(ioaddr + MTL_OPERATION_MODE); + + value &= ~MTL_OPERATION_RAA; + switch (rx_alg) { + case MTL_RX_ALGORITHM_SP: + value |= MTL_OPERATION_RAA_SP; + break; + case MTL_RX_ALGORITHM_WSP: + value |= MTL_OPERATION_RAA_WSP; + break; + default: + break; + } + + writel(value, ioaddr + MTL_OPERATION_MODE); +} + +static void dwmac4_prog_mtl_tx_algorithms(struct mac_device_info *hw, + u32 tx_alg) +{ + void __iomem *ioaddr = hw->pcsr; + u32 value = readl(ioaddr + MTL_OPERATION_MODE); + + value &= ~MTL_OPERATION_SCHALG_MASK; + switch (tx_alg) { + case MTL_TX_ALGORITHM_WRR: + value |= MTL_OPERATION_SCHALG_WRR; + break; + case MTL_TX_ALGORITHM_WFQ: + value |= MTL_OPERATION_SCHALG_WFQ; + break; + case MTL_TX_ALGORITHM_DWRR: + value |= MTL_OPERATION_SCHALG_DWRR; + break; + case MTL_TX_ALGORITHM_SP: + value |= MTL_OPERATION_SCHALG_SP; + break; + default: + break; + } +} + +static void dwmac4_set_mtl_tx_queue_weight(struct mac_device_info *hw, + u32 weight, u32 queue) +{ + void __iomem *ioaddr = hw->pcsr; + u32 value = readl(ioaddr + MTL_TXQX_WEIGHT_BASE_ADDR(queue)); + + value &= ~MTL_TXQ_WEIGHT_ISCQW_MASK; + value |= weight & MTL_TXQ_WEIGHT_ISCQW_MASK; + writel(value, ioaddr + MTL_TXQX_WEIGHT_BASE_ADDR(queue)); +} + +static void dwmac4_map_mtl_dma(struct mac_device_info *hw, u32 queue, u32 chan) +{ + void __iomem *ioaddr = hw->pcsr; + u32 value; + + if (queue < 4) + value = readl(ioaddr + MTL_RXQ_DMA_MAP0); + else + value = readl(ioaddr + MTL_RXQ_DMA_MAP1); + + if (queue == 0 || queue == 4) { + value &= ~MTL_RXQ_DMA_Q04MDMACH_MASK; + value |= MTL_RXQ_DMA_Q04MDMACH(chan); + } else { + value &= ~MTL_RXQ_DMA_QXMDMACH_MASK(queue); + value |= MTL_RXQ_DMA_QXMDMACH(chan, queue); + } + + if (queue < 4) + writel(value, ioaddr + MTL_RXQ_DMA_MAP0); + else + writel(value, ioaddr + MTL_RXQ_DMA_MAP1); +} + +static void dwmac4_config_cbs(struct mac_device_info *hw, + u32 send_slope, u32 idle_slope, + u32 high_credit, u32 low_credit, u32 queue) +{ + void __iomem *ioaddr = hw->pcsr; + u32 value; + + pr_debug("Queue %d configured as AVB. Parameters:\n", queue); + pr_debug("\tsend_slope: 0x%08x\n", send_slope); + pr_debug("\tidle_slope: 0x%08x\n", idle_slope); + pr_debug("\thigh_credit: 0x%08x\n", high_credit); + pr_debug("\tlow_credit: 0x%08x\n", low_credit); + + /* enable AV algorithm */ + value = readl(ioaddr + MTL_ETSX_CTRL_BASE_ADDR(queue)); + value |= MTL_ETS_CTRL_AVALG; + value |= MTL_ETS_CTRL_CC; + writel(value, ioaddr + MTL_ETSX_CTRL_BASE_ADDR(queue)); + + /* configure send slope */ + value = readl(ioaddr + MTL_SEND_SLP_CREDX_BASE_ADDR(queue)); + value &= ~MTL_SEND_SLP_CRED_SSC_MASK; + value |= send_slope & MTL_SEND_SLP_CRED_SSC_MASK; + writel(value, ioaddr + MTL_SEND_SLP_CREDX_BASE_ADDR(queue)); + + /* configure idle slope (same register as tx weight) */ + dwmac4_set_mtl_tx_queue_weight(hw, idle_slope, queue); + + /* configure high credit */ + value = readl(ioaddr + MTL_HIGH_CREDX_BASE_ADDR(queue)); + value &= ~MTL_HIGH_CRED_HC_MASK; + value |= high_credit & MTL_HIGH_CRED_HC_MASK; + writel(value, ioaddr + MTL_HIGH_CREDX_BASE_ADDR(queue)); + + /* configure high credit */ + value = readl(ioaddr + MTL_LOW_CREDX_BASE_ADDR(queue)); + value &= ~MTL_HIGH_CRED_LC_MASK; + value |= low_credit & MTL_HIGH_CRED_LC_MASK; + writel(value, ioaddr + MTL_LOW_CREDX_BASE_ADDR(queue)); +} + static void dwmac4_dump_regs(struct mac_device_info *hw, u32 *reg_space) { void __iomem *ioaddr = hw->pcsr; @@ -251,11 +377,12 @@ static void dwmac4_set_filter(struct mac_device_info *hw, } static void dwmac4_flow_ctrl(struct mac_device_info *hw, unsigned int duplex, - unsigned int fc, unsigned int pause_time) + unsigned int fc, unsigned int pause_time, + u32 tx_cnt) { void __iomem *ioaddr = hw->pcsr; - u32 channel = STMMAC_CHAN0; /* FIXME */ unsigned int flow = 0; + u32 queue = 0; pr_debug("GMAC Flow-Control:\n"); if (fc & FLOW_RX) { @@ -265,13 +392,18 @@ static void dwmac4_flow_ctrl(struct mac_device_info *hw, unsigned int duplex, } if (fc & FLOW_TX) { pr_debug("\tTransmit Flow-Control ON\n"); - flow |= GMAC_TX_FLOW_CTRL_TFE; - writel(flow, ioaddr + GMAC_QX_TX_FLOW_CTRL(channel)); - if (duplex) { + if (duplex) pr_debug("\tduplex mode: PAUSE %d\n", pause_time); - flow |= (pause_time << GMAC_TX_FLOW_CTRL_PT_SHIFT); - writel(flow, ioaddr + GMAC_QX_TX_FLOW_CTRL(channel)); + + for (queue = 0; queue < tx_cnt; queue++) { + flow |= GMAC_TX_FLOW_CTRL_TFE; + + if (duplex) + flow |= + (pause_time << GMAC_TX_FLOW_CTRL_PT_SHIFT); + + writel(flow, ioaddr + GMAC_QX_TX_FLOW_CTRL(queue)); } } } @@ -325,11 +457,34 @@ static void dwmac4_phystatus(void __iomem *ioaddr, struct stmmac_extra_stats *x) } } +static int dwmac4_irq_mtl_status(struct mac_device_info *hw, u32 chan) +{ + void __iomem *ioaddr = hw->pcsr; + u32 mtl_int_qx_status; + int ret = 0; + + mtl_int_qx_status = readl(ioaddr + MTL_INT_STATUS); + + /* Check MTL Interrupt */ + if (mtl_int_qx_status & MTL_INT_QX(chan)) { + /* read Queue x Interrupt status */ + u32 status = readl(ioaddr + MTL_CHAN_INT_CTRL(chan)); + + if (status & MTL_RX_OVERFLOW_INT) { + /* clear Interrupt */ + writel(status | MTL_RX_OVERFLOW_INT, + ioaddr + MTL_CHAN_INT_CTRL(chan)); + ret = CORE_IRQ_MTL_RX_OVERFLOW; + } + } + + return ret; +} + static int dwmac4_irq_status(struct mac_device_info *hw, struct stmmac_extra_stats *x) { void __iomem *ioaddr = hw->pcsr; - u32 mtl_int_qx_status; u32 intr_status; int ret = 0; @@ -348,20 +503,6 @@ static int dwmac4_irq_status(struct mac_device_info *hw, x->irq_receive_pmt_irq_n++; } - mtl_int_qx_status = readl(ioaddr + MTL_INT_STATUS); - /* Check MTL Interrupt: Currently only one queue is used: Q0. */ - if (mtl_int_qx_status & MTL_INT_Q0) { - /* read Queue 0 Interrupt status */ - u32 status = readl(ioaddr + MTL_CHAN_INT_CTRL(STMMAC_CHAN0)); - - if (status & MTL_RX_OVERFLOW_INT) { - /* clear Interrupt */ - writel(status | MTL_RX_OVERFLOW_INT, - ioaddr + MTL_CHAN_INT_CTRL(STMMAC_CHAN0)); - ret = CORE_IRQ_MTL_RX_OVERFLOW; - } - } - dwmac_pcs_isr(ioaddr, GMAC_PCS_BASE, intr_status, x); if (intr_status & PCS_RGSMIIIS_IRQ) dwmac4_phystatus(ioaddr, x); @@ -369,64 +510,69 @@ static int dwmac4_irq_status(struct mac_device_info *hw, return ret; } -static void dwmac4_debug(void __iomem *ioaddr, struct stmmac_extra_stats *x) +static void dwmac4_debug(void __iomem *ioaddr, struct stmmac_extra_stats *x, + u32 rx_queues, u32 tx_queues) { u32 value; - - /* Currently only channel 0 is supported */ - value = readl(ioaddr + MTL_CHAN_TX_DEBUG(STMMAC_CHAN0)); - - if (value & MTL_DEBUG_TXSTSFSTS) - x->mtl_tx_status_fifo_full++; - if (value & MTL_DEBUG_TXFSTS) - x->mtl_tx_fifo_not_empty++; - if (value & MTL_DEBUG_TWCSTS) - x->mmtl_fifo_ctrl++; - if (value & MTL_DEBUG_TRCSTS_MASK) { - u32 trcsts = (value & MTL_DEBUG_TRCSTS_MASK) - >> MTL_DEBUG_TRCSTS_SHIFT; - if (trcsts == MTL_DEBUG_TRCSTS_WRITE) - x->mtl_tx_fifo_read_ctrl_write++; - else if (trcsts == MTL_DEBUG_TRCSTS_TXW) - x->mtl_tx_fifo_read_ctrl_wait++; - else if (trcsts == MTL_DEBUG_TRCSTS_READ) - x->mtl_tx_fifo_read_ctrl_read++; - else - x->mtl_tx_fifo_read_ctrl_idle++; + u32 queue; + + for (queue = 0; queue < tx_queues; queue++) { + value = readl(ioaddr + MTL_CHAN_TX_DEBUG(queue)); + + if (value & MTL_DEBUG_TXSTSFSTS) + x->mtl_tx_status_fifo_full++; + if (value & MTL_DEBUG_TXFSTS) + x->mtl_tx_fifo_not_empty++; + if (value & MTL_DEBUG_TWCSTS) + x->mmtl_fifo_ctrl++; + if (value & MTL_DEBUG_TRCSTS_MASK) { + u32 trcsts = (value & MTL_DEBUG_TRCSTS_MASK) + >> MTL_DEBUG_TRCSTS_SHIFT; + if (trcsts == MTL_DEBUG_TRCSTS_WRITE) + x->mtl_tx_fifo_read_ctrl_write++; + else if (trcsts == MTL_DEBUG_TRCSTS_TXW) + x->mtl_tx_fifo_read_ctrl_wait++; + else if (trcsts == MTL_DEBUG_TRCSTS_READ) + x->mtl_tx_fifo_read_ctrl_read++; + else + x->mtl_tx_fifo_read_ctrl_idle++; + } + if (value & MTL_DEBUG_TXPAUSED) + x->mac_tx_in_pause++; } - if (value & MTL_DEBUG_TXPAUSED) - x->mac_tx_in_pause++; - value = readl(ioaddr + MTL_CHAN_RX_DEBUG(STMMAC_CHAN0)); + for (queue = 0; queue < rx_queues; queue++) { + value = readl(ioaddr + MTL_CHAN_RX_DEBUG(queue)); - if (value & MTL_DEBUG_RXFSTS_MASK) { - u32 rxfsts = (value & MTL_DEBUG_RXFSTS_MASK) - >> MTL_DEBUG_RRCSTS_SHIFT; + if (value & MTL_DEBUG_RXFSTS_MASK) { + u32 rxfsts = (value & MTL_DEBUG_RXFSTS_MASK) + >> MTL_DEBUG_RRCSTS_SHIFT; - if (rxfsts == MTL_DEBUG_RXFSTS_FULL) - x->mtl_rx_fifo_fill_level_full++; - else if (rxfsts == MTL_DEBUG_RXFSTS_AT) - x->mtl_rx_fifo_fill_above_thresh++; - else if (rxfsts == MTL_DEBUG_RXFSTS_BT) - x->mtl_rx_fifo_fill_below_thresh++; - else - x->mtl_rx_fifo_fill_level_empty++; - } - if (value & MTL_DEBUG_RRCSTS_MASK) { - u32 rrcsts = (value & MTL_DEBUG_RRCSTS_MASK) >> - MTL_DEBUG_RRCSTS_SHIFT; - - if (rrcsts == MTL_DEBUG_RRCSTS_FLUSH) - x->mtl_rx_fifo_read_ctrl_flush++; - else if (rrcsts == MTL_DEBUG_RRCSTS_RSTAT) - x->mtl_rx_fifo_read_ctrl_read_data++; - else if (rrcsts == MTL_DEBUG_RRCSTS_RDATA) - x->mtl_rx_fifo_read_ctrl_status++; - else - x->mtl_rx_fifo_read_ctrl_idle++; + if (rxfsts == MTL_DEBUG_RXFSTS_FULL) + x->mtl_rx_fifo_fill_level_full++; + else if (rxfsts == MTL_DEBUG_RXFSTS_AT) + x->mtl_rx_fifo_fill_above_thresh++; + else if (rxfsts == MTL_DEBUG_RXFSTS_BT) + x->mtl_rx_fifo_fill_below_thresh++; + else + x->mtl_rx_fifo_fill_level_empty++; + } + if (value & MTL_DEBUG_RRCSTS_MASK) { + u32 rrcsts = (value & MTL_DEBUG_RRCSTS_MASK) >> + MTL_DEBUG_RRCSTS_SHIFT; + + if (rrcsts == MTL_DEBUG_RRCSTS_FLUSH) + x->mtl_rx_fifo_read_ctrl_flush++; + else if (rrcsts == MTL_DEBUG_RRCSTS_RSTAT) + x->mtl_rx_fifo_read_ctrl_read_data++; + else if (rrcsts == MTL_DEBUG_RRCSTS_RDATA) + x->mtl_rx_fifo_read_ctrl_status++; + else + x->mtl_rx_fifo_read_ctrl_idle++; + } + if (value & MTL_DEBUG_RWCSTS) + x->mtl_rx_fifo_ctrl_active++; } - if (value & MTL_DEBUG_RWCSTS) - x->mtl_rx_fifo_ctrl_active++; /* GMAC debug */ value = readl(ioaddr + GMAC_DEBUG); @@ -457,8 +603,14 @@ static const struct stmmac_ops dwmac4_ops = { .core_init = dwmac4_core_init, .rx_ipc = dwmac4_rx_ipc_enable, .rx_queue_enable = dwmac4_rx_queue_enable, + .prog_mtl_rx_algorithms = dwmac4_prog_mtl_rx_algorithms, + .prog_mtl_tx_algorithms = dwmac4_prog_mtl_tx_algorithms, + .set_mtl_tx_queue_weight = dwmac4_set_mtl_tx_queue_weight, + .map_mtl_to_dma = dwmac4_map_mtl_dma, + .config_cbs = dwmac4_config_cbs, .dump_regs = dwmac4_dump_regs, .host_irq_status = dwmac4_irq_status, + .host_mtl_irq_status = dwmac4_irq_mtl_status, .flow_ctrl = dwmac4_flow_ctrl, .pmt = dwmac4_pmt, .set_umac_addr = dwmac4_set_umac_addr, diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.c index f97b0d5d9987..eec8463057fd 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.c @@ -71,36 +71,48 @@ static void dwmac4_dma_axi(void __iomem *ioaddr, struct stmmac_axi *axi) writel(value, ioaddr + DMA_SYS_BUS_MODE); } -static void dwmac4_dma_init_channel(void __iomem *ioaddr, - struct stmmac_dma_cfg *dma_cfg, - u32 dma_tx_phy, u32 dma_rx_phy, - u32 channel) +void dwmac4_dma_init_rx_chan(void __iomem *ioaddr, + struct stmmac_dma_cfg *dma_cfg, + u32 dma_rx_phy, u32 chan) { u32 value; - int txpbl = dma_cfg->txpbl ?: dma_cfg->pbl; - int rxpbl = dma_cfg->rxpbl ?: dma_cfg->pbl; + u32 rxpbl = dma_cfg->rxpbl ?: dma_cfg->pbl; - /* set PBL for each channels. Currently we affect same configuration - * on each channel - */ - value = readl(ioaddr + DMA_CHAN_CONTROL(channel)); - if (dma_cfg->pblx8) - value = value | DMA_BUS_MODE_PBL; - writel(value, ioaddr + DMA_CHAN_CONTROL(channel)); + value = readl(ioaddr + DMA_CHAN_RX_CONTROL(chan)); + value = value | (rxpbl << DMA_BUS_MODE_RPBL_SHIFT); + writel(value, ioaddr + DMA_CHAN_RX_CONTROL(chan)); + + writel(dma_rx_phy, ioaddr + DMA_CHAN_RX_BASE_ADDR(chan)); +} - value = readl(ioaddr + DMA_CHAN_TX_CONTROL(channel)); +void dwmac4_dma_init_tx_chan(void __iomem *ioaddr, + struct stmmac_dma_cfg *dma_cfg, + u32 dma_tx_phy, u32 chan) +{ + u32 value; + u32 txpbl = dma_cfg->txpbl ?: dma_cfg->pbl; + + value = readl(ioaddr + DMA_CHAN_TX_CONTROL(chan)); value = value | (txpbl << DMA_BUS_MODE_PBL_SHIFT); - writel(value, ioaddr + DMA_CHAN_TX_CONTROL(channel)); + writel(value, ioaddr + DMA_CHAN_TX_CONTROL(chan)); - value = readl(ioaddr + DMA_CHAN_RX_CONTROL(channel)); - value = value | (rxpbl << DMA_BUS_MODE_RPBL_SHIFT); - writel(value, ioaddr + DMA_CHAN_RX_CONTROL(channel)); + writel(dma_tx_phy, ioaddr + DMA_CHAN_TX_BASE_ADDR(chan)); +} - /* Mask interrupts by writing to CSR7 */ - writel(DMA_CHAN_INTR_DEFAULT_MASK, ioaddr + DMA_CHAN_INTR_ENA(channel)); +void dwmac4_dma_init_channel(void __iomem *ioaddr, + struct stmmac_dma_cfg *dma_cfg, u32 chan) +{ + u32 value; + + /* common channel control register config */ + value = readl(ioaddr + DMA_CHAN_CONTROL(chan)); + if (dma_cfg->pblx8) + value = value | DMA_BUS_MODE_PBL; + writel(value, ioaddr + DMA_CHAN_CONTROL(chan)); - writel(dma_tx_phy, ioaddr + DMA_CHAN_TX_BASE_ADDR(channel)); - writel(dma_rx_phy, ioaddr + DMA_CHAN_RX_BASE_ADDR(channel)); + /* Mask interrupts by writing to CSR7 */ + writel(DMA_CHAN_INTR_DEFAULT_MASK, + ioaddr + DMA_CHAN_INTR_ENA(chan)); } static void dwmac4_dma_init(void __iomem *ioaddr, @@ -108,7 +120,6 @@ static void dwmac4_dma_init(void __iomem *ioaddr, u32 dma_tx, u32 dma_rx, int atds) { u32 value = readl(ioaddr + DMA_SYS_BUS_MODE); - int i; /* Set the Fixed burst mode */ if (dma_cfg->fixed_burst) @@ -122,9 +133,6 @@ static void dwmac4_dma_init(void __iomem *ioaddr, value |= DMA_SYS_BUS_AAL; writel(value, ioaddr + DMA_SYS_BUS_MODE); - - for (i = 0; i < DMA_CHANNEL_NB_MAX; i++) - dwmac4_dma_init_channel(ioaddr, dma_cfg, dma_tx, dma_rx, i); } static void _dwmac4_dump_dma_regs(void __iomem *ioaddr, u32 channel, @@ -174,46 +182,121 @@ static void dwmac4_dump_dma_regs(void __iomem *ioaddr, u32 *reg_space) _dwmac4_dump_dma_regs(ioaddr, i, reg_space); } -static void dwmac4_rx_watchdog(void __iomem *ioaddr, u32 riwt) +static void dwmac4_rx_watchdog(void __iomem *ioaddr, u32 riwt, u32 number_chan) { - int i; + u32 chan; - for (i = 0; i < DMA_CHANNEL_NB_MAX; i++) - writel(riwt, ioaddr + DMA_CHAN_RX_WATCHDOG(i)); + for (chan = 0; chan < number_chan; chan++) + writel(riwt, ioaddr + DMA_CHAN_RX_WATCHDOG(chan)); } -static void dwmac4_dma_chan_op_mode(void __iomem *ioaddr, int txmode, - int rxmode, u32 channel) +static void dwmac4_dma_rx_chan_op_mode(void __iomem *ioaddr, int mode, + u32 channel, int fifosz) { - u32 mtl_tx_op, mtl_rx_op, mtl_rx_int; + unsigned int rqs = fifosz / 256 - 1; + u32 mtl_rx_op, mtl_rx_int; - /* Following code only done for channel 0, other channels not yet - * supported. - */ - mtl_tx_op = readl(ioaddr + MTL_CHAN_TX_OP_MODE(channel)); + mtl_rx_op = readl(ioaddr + MTL_CHAN_RX_OP_MODE(channel)); + + if (mode == SF_DMA_MODE) { + pr_debug("GMAC: enable RX store and forward mode\n"); + mtl_rx_op |= MTL_OP_MODE_RSF; + } else { + pr_debug("GMAC: disable RX SF mode (threshold %d)\n", mode); + mtl_rx_op &= ~MTL_OP_MODE_RSF; + mtl_rx_op &= MTL_OP_MODE_RTC_MASK; + if (mode <= 32) + mtl_rx_op |= MTL_OP_MODE_RTC_32; + else if (mode <= 64) + mtl_rx_op |= MTL_OP_MODE_RTC_64; + else if (mode <= 96) + mtl_rx_op |= MTL_OP_MODE_RTC_96; + else + mtl_rx_op |= MTL_OP_MODE_RTC_128; + } + + mtl_rx_op &= ~MTL_OP_MODE_RQS_MASK; + mtl_rx_op |= rqs << MTL_OP_MODE_RQS_SHIFT; + + /* enable flow control only if each channel gets 4 KiB or more FIFO */ + if (fifosz >= 4096) { + unsigned int rfd, rfa; + + mtl_rx_op |= MTL_OP_MODE_EHFC; + + /* Set Threshold for Activating Flow Control to min 2 frames, + * i.e. 1500 * 2 = 3000 bytes. + * + * Set Threshold for Deactivating Flow Control to min 1 frame, + * i.e. 1500 bytes. + */ + switch (fifosz) { + case 4096: + /* This violates the above formula because of FIFO size + * limit therefore overflow may occur in spite of this. + */ + rfd = 0x03; /* Full-2.5K */ + rfa = 0x01; /* Full-1.5K */ + break; + + case 8192: + rfd = 0x06; /* Full-4K */ + rfa = 0x0a; /* Full-6K */ + break; + + case 16384: + rfd = 0x06; /* Full-4K */ + rfa = 0x12; /* Full-10K */ + break; + + default: + rfd = 0x06; /* Full-4K */ + rfa = 0x1e; /* Full-16K */ + break; + } + + mtl_rx_op &= ~MTL_OP_MODE_RFD_MASK; + mtl_rx_op |= rfd << MTL_OP_MODE_RFD_SHIFT; - if (txmode == SF_DMA_MODE) { + mtl_rx_op &= ~MTL_OP_MODE_RFA_MASK; + mtl_rx_op |= rfa << MTL_OP_MODE_RFA_SHIFT; + } + + writel(mtl_rx_op, ioaddr + MTL_CHAN_RX_OP_MODE(channel)); + + /* Enable MTL RX overflow */ + mtl_rx_int = readl(ioaddr + MTL_CHAN_INT_CTRL(channel)); + writel(mtl_rx_int | MTL_RX_OVERFLOW_INT_EN, + ioaddr + MTL_CHAN_INT_CTRL(channel)); +} + +static void dwmac4_dma_tx_chan_op_mode(void __iomem *ioaddr, int mode, + u32 channel) +{ + u32 mtl_tx_op = readl(ioaddr + MTL_CHAN_TX_OP_MODE(channel)); + + if (mode == SF_DMA_MODE) { pr_debug("GMAC: enable TX store and forward mode\n"); /* Transmit COE type 2 cannot be done in cut-through mode. */ mtl_tx_op |= MTL_OP_MODE_TSF; } else { - pr_debug("GMAC: disabling TX SF (threshold %d)\n", txmode); + pr_debug("GMAC: disabling TX SF (threshold %d)\n", mode); mtl_tx_op &= ~MTL_OP_MODE_TSF; mtl_tx_op &= MTL_OP_MODE_TTC_MASK; /* Set the transmit threshold */ - if (txmode <= 32) + if (mode <= 32) mtl_tx_op |= MTL_OP_MODE_TTC_32; - else if (txmode <= 64) + else if (mode <= 64) mtl_tx_op |= MTL_OP_MODE_TTC_64; - else if (txmode <= 96) + else if (mode <= 96) mtl_tx_op |= MTL_OP_MODE_TTC_96; - else if (txmode <= 128) + else if (mode <= 128) mtl_tx_op |= MTL_OP_MODE_TTC_128; - else if (txmode <= 192) + else if (mode <= 192) mtl_tx_op |= MTL_OP_MODE_TTC_192; - else if (txmode <= 256) + else if (mode <= 256) mtl_tx_op |= MTL_OP_MODE_TTC_256; - else if (txmode <= 384) + else if (mode <= 384) mtl_tx_op |= MTL_OP_MODE_TTC_384; else mtl_tx_op |= MTL_OP_MODE_TTC_512; @@ -230,39 +313,6 @@ static void dwmac4_dma_chan_op_mode(void __iomem *ioaddr, int txmode, */ mtl_tx_op |= MTL_OP_MODE_TXQEN | MTL_OP_MODE_TQS_MASK; writel(mtl_tx_op, ioaddr + MTL_CHAN_TX_OP_MODE(channel)); - - mtl_rx_op = readl(ioaddr + MTL_CHAN_RX_OP_MODE(channel)); - - if (rxmode == SF_DMA_MODE) { - pr_debug("GMAC: enable RX store and forward mode\n"); - mtl_rx_op |= MTL_OP_MODE_RSF; - } else { - pr_debug("GMAC: disable RX SF mode (threshold %d)\n", rxmode); - mtl_rx_op &= ~MTL_OP_MODE_RSF; - mtl_rx_op &= MTL_OP_MODE_RTC_MASK; - if (rxmode <= 32) - mtl_rx_op |= MTL_OP_MODE_RTC_32; - else if (rxmode <= 64) - mtl_rx_op |= MTL_OP_MODE_RTC_64; - else if (rxmode <= 96) - mtl_rx_op |= MTL_OP_MODE_RTC_96; - else - mtl_rx_op |= MTL_OP_MODE_RTC_128; - } - - writel(mtl_rx_op, ioaddr + MTL_CHAN_RX_OP_MODE(channel)); - - /* Enable MTL RX overflow */ - mtl_rx_int = readl(ioaddr + MTL_CHAN_INT_CTRL(channel)); - writel(mtl_rx_int | MTL_RX_OVERFLOW_INT_EN, - ioaddr + MTL_CHAN_INT_CTRL(channel)); -} - -static void dwmac4_dma_operation_mode(void __iomem *ioaddr, int txmode, - int rxmode, int rxfifosz) -{ - /* Only Channel 0 is actually configured and used */ - dwmac4_dma_chan_op_mode(ioaddr, txmode, rxmode, 0); } static void dwmac4_get_hw_feature(void __iomem *ioaddr, @@ -294,6 +344,11 @@ static void dwmac4_get_hw_feature(void __iomem *ioaddr, hw_cap = readl(ioaddr + GMAC_HW_FEATURE1); dma_cap->av = (hw_cap & GMAC_HW_FEAT_AVSEL) >> 20; dma_cap->tsoen = (hw_cap & GMAC_HW_TSOEN) >> 18; + /* RX and TX FIFO sizes are encoded as log2(n / 128). Undo that by + * shifting and store the sizes in bytes. + */ + dma_cap->tx_fifo_size = 128 << ((hw_cap & GMAC_HW_TXFIFOSIZE) >> 6); + dma_cap->rx_fifo_size = 128 << ((hw_cap & GMAC_HW_RXFIFOSIZE) >> 0); /* MAC HW feature2 */ hw_cap = readl(ioaddr + GMAC_HW_FEATURE2); /* TX and RX number of channels */ @@ -332,9 +387,13 @@ static void dwmac4_enable_tso(void __iomem *ioaddr, bool en, u32 chan) const struct stmmac_dma_ops dwmac4_dma_ops = { .reset = dwmac4_dma_reset, .init = dwmac4_dma_init, + .init_chan = dwmac4_dma_init_channel, + .init_rx_chan = dwmac4_dma_init_rx_chan, + .init_tx_chan = dwmac4_dma_init_tx_chan, .axi = dwmac4_dma_axi, .dump_regs = dwmac4_dump_dma_regs, - .dma_mode = dwmac4_dma_operation_mode, + .dma_rx_mode = dwmac4_dma_rx_chan_op_mode, + .dma_tx_mode = dwmac4_dma_tx_chan_op_mode, .enable_dma_irq = dwmac4_enable_dma_irq, .disable_dma_irq = dwmac4_disable_dma_irq, .start_tx = dwmac4_dma_start_tx, @@ -354,9 +413,13 @@ const struct stmmac_dma_ops dwmac4_dma_ops = { const struct stmmac_dma_ops dwmac410_dma_ops = { .reset = dwmac4_dma_reset, .init = dwmac4_dma_init, + .init_chan = dwmac4_dma_init_channel, + .init_rx_chan = dwmac4_dma_init_rx_chan, + .init_tx_chan = dwmac4_dma_init_tx_chan, .axi = dwmac4_dma_axi, .dump_regs = dwmac4_dump_dma_regs, - .dma_mode = dwmac4_dma_operation_mode, + .dma_rx_mode = dwmac4_dma_rx_chan_op_mode, + .dma_tx_mode = dwmac4_dma_tx_chan_op_mode, .enable_dma_irq = dwmac410_enable_dma_irq, .disable_dma_irq = dwmac4_disable_dma_irq, .start_tx = dwmac4_dma_start_tx, diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.h b/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.h index 1b06df749e2b..8474bf961dd0 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.h +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.h @@ -185,17 +185,17 @@ int dwmac4_dma_reset(void __iomem *ioaddr); void dwmac4_enable_dma_transmission(void __iomem *ioaddr, u32 tail_ptr); -void dwmac4_enable_dma_irq(void __iomem *ioaddr); -void dwmac410_enable_dma_irq(void __iomem *ioaddr); -void dwmac4_disable_dma_irq(void __iomem *ioaddr); -void dwmac4_dma_start_tx(void __iomem *ioaddr); -void dwmac4_dma_stop_tx(void __iomem *ioaddr); -void dwmac4_dma_start_rx(void __iomem *ioaddr); -void dwmac4_dma_stop_rx(void __iomem *ioaddr); +void dwmac4_enable_dma_irq(void __iomem *ioaddr, u32 chan); +void dwmac410_enable_dma_irq(void __iomem *ioaddr, u32 chan); +void dwmac4_disable_dma_irq(void __iomem *ioaddr, u32 chan); +void dwmac4_dma_start_tx(void __iomem *ioaddr, u32 chan); +void dwmac4_dma_stop_tx(void __iomem *ioaddr, u32 chan); +void dwmac4_dma_start_rx(void __iomem *ioaddr, u32 chan); +void dwmac4_dma_stop_rx(void __iomem *ioaddr, u32 chan); int dwmac4_dma_interrupt(void __iomem *ioaddr, - struct stmmac_extra_stats *x); -void dwmac4_set_rx_ring_len(void __iomem *ioaddr, u32 len); -void dwmac4_set_tx_ring_len(void __iomem *ioaddr, u32 len); + struct stmmac_extra_stats *x, u32 chan); +void dwmac4_set_rx_ring_len(void __iomem *ioaddr, u32 len, u32 chan); +void dwmac4_set_tx_ring_len(void __iomem *ioaddr, u32 len, u32 chan); void dwmac4_set_rx_tail_ptr(void __iomem *ioaddr, u32 tail_ptr, u32 chan); void dwmac4_set_tx_tail_ptr(void __iomem *ioaddr, u32 tail_ptr, u32 chan); diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_lib.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_lib.c index c7326d5b2f43..49f5687879df 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_lib.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_lib.c @@ -37,96 +37,96 @@ int dwmac4_dma_reset(void __iomem *ioaddr) void dwmac4_set_rx_tail_ptr(void __iomem *ioaddr, u32 tail_ptr, u32 chan) { - writel(tail_ptr, ioaddr + DMA_CHAN_RX_END_ADDR(0)); + writel(tail_ptr, ioaddr + DMA_CHAN_RX_END_ADDR(chan)); } void dwmac4_set_tx_tail_ptr(void __iomem *ioaddr, u32 tail_ptr, u32 chan) { - writel(tail_ptr, ioaddr + DMA_CHAN_TX_END_ADDR(0)); + writel(tail_ptr, ioaddr + DMA_CHAN_TX_END_ADDR(chan)); } -void dwmac4_dma_start_tx(void __iomem *ioaddr) +void dwmac4_dma_start_tx(void __iomem *ioaddr, u32 chan) { - u32 value = readl(ioaddr + DMA_CHAN_TX_CONTROL(STMMAC_CHAN0)); + u32 value = readl(ioaddr + DMA_CHAN_TX_CONTROL(chan)); value |= DMA_CONTROL_ST; - writel(value, ioaddr + DMA_CHAN_TX_CONTROL(STMMAC_CHAN0)); + writel(value, ioaddr + DMA_CHAN_TX_CONTROL(chan)); value = readl(ioaddr + GMAC_CONFIG); value |= GMAC_CONFIG_TE; writel(value, ioaddr + GMAC_CONFIG); } -void dwmac4_dma_stop_tx(void __iomem *ioaddr) +void dwmac4_dma_stop_tx(void __iomem *ioaddr, u32 chan) { - u32 value = readl(ioaddr + DMA_CHAN_TX_CONTROL(STMMAC_CHAN0)); + u32 value = readl(ioaddr + DMA_CHAN_TX_CONTROL(chan)); value &= ~DMA_CONTROL_ST; - writel(value, ioaddr + DMA_CHAN_TX_CONTROL(STMMAC_CHAN0)); + writel(value, ioaddr + DMA_CHAN_TX_CONTROL(chan)); value = readl(ioaddr + GMAC_CONFIG); value &= ~GMAC_CONFIG_TE; writel(value, ioaddr + GMAC_CONFIG); } -void dwmac4_dma_start_rx(void __iomem *ioaddr) +void dwmac4_dma_start_rx(void __iomem *ioaddr, u32 chan) { - u32 value = readl(ioaddr + DMA_CHAN_RX_CONTROL(STMMAC_CHAN0)); + u32 value = readl(ioaddr + DMA_CHAN_RX_CONTROL(chan)); value |= DMA_CONTROL_SR; - writel(value, ioaddr + DMA_CHAN_RX_CONTROL(STMMAC_CHAN0)); + writel(value, ioaddr + DMA_CHAN_RX_CONTROL(chan)); value = readl(ioaddr + GMAC_CONFIG); value |= GMAC_CONFIG_RE; writel(value, ioaddr + GMAC_CONFIG); } -void dwmac4_dma_stop_rx(void __iomem *ioaddr) +void dwmac4_dma_stop_rx(void __iomem *ioaddr, u32 chan) { - u32 value = readl(ioaddr + DMA_CHAN_RX_CONTROL(STMMAC_CHAN0)); + u32 value = readl(ioaddr + DMA_CHAN_RX_CONTROL(chan)); value &= ~DMA_CONTROL_SR; - writel(value, ioaddr + DMA_CHAN_RX_CONTROL(STMMAC_CHAN0)); + writel(value, ioaddr + DMA_CHAN_RX_CONTROL(chan)); value = readl(ioaddr + GMAC_CONFIG); value &= ~GMAC_CONFIG_RE; writel(value, ioaddr + GMAC_CONFIG); } -void dwmac4_set_tx_ring_len(void __iomem *ioaddr, u32 len) +void dwmac4_set_tx_ring_len(void __iomem *ioaddr, u32 len, u32 chan) { - writel(len, ioaddr + DMA_CHAN_TX_RING_LEN(STMMAC_CHAN0)); + writel(len, ioaddr + DMA_CHAN_TX_RING_LEN(chan)); } -void dwmac4_set_rx_ring_len(void __iomem *ioaddr, u32 len) +void dwmac4_set_rx_ring_len(void __iomem *ioaddr, u32 len, u32 chan) { - writel(len, ioaddr + DMA_CHAN_RX_RING_LEN(STMMAC_CHAN0)); + writel(len, ioaddr + DMA_CHAN_RX_RING_LEN(chan)); } -void dwmac4_enable_dma_irq(void __iomem *ioaddr) +void dwmac4_enable_dma_irq(void __iomem *ioaddr, u32 chan) { writel(DMA_CHAN_INTR_DEFAULT_MASK, ioaddr + - DMA_CHAN_INTR_ENA(STMMAC_CHAN0)); + DMA_CHAN_INTR_ENA(chan)); } -void dwmac410_enable_dma_irq(void __iomem *ioaddr) +void dwmac410_enable_dma_irq(void __iomem *ioaddr, u32 chan) { writel(DMA_CHAN_INTR_DEFAULT_MASK_4_10, - ioaddr + DMA_CHAN_INTR_ENA(STMMAC_CHAN0)); + ioaddr + DMA_CHAN_INTR_ENA(chan)); } -void dwmac4_disable_dma_irq(void __iomem *ioaddr) +void dwmac4_disable_dma_irq(void __iomem *ioaddr, u32 chan) { - writel(0, ioaddr + DMA_CHAN_INTR_ENA(STMMAC_CHAN0)); + writel(0, ioaddr + DMA_CHAN_INTR_ENA(chan)); } int dwmac4_dma_interrupt(void __iomem *ioaddr, - struct stmmac_extra_stats *x) + struct stmmac_extra_stats *x, u32 chan) { int ret = 0; - u32 intr_status = readl(ioaddr + DMA_CHAN_STATUS(0)); + u32 intr_status = readl(ioaddr + DMA_CHAN_STATUS(chan)); /* ABNORMAL interrupts */ if (unlikely(intr_status & DMA_CHAN_STATUS_AIS)) { @@ -153,7 +153,7 @@ int dwmac4_dma_interrupt(void __iomem *ioaddr, if (likely(intr_status & DMA_CHAN_STATUS_RI)) { u32 value; - value = readl(ioaddr + DMA_CHAN_INTR_ENA(STMMAC_CHAN0)); + value = readl(ioaddr + DMA_CHAN_INTR_ENA(chan)); /* to schedule NAPI on real RIE event. */ if (likely(value & DMA_CHAN_INTR_ENA_RIE)) { x->rx_normal_irq_n++; @@ -172,7 +172,7 @@ int dwmac4_dma_interrupt(void __iomem *ioaddr, * status [21-0] expect reserved bits [5-3] */ writel((intr_status & 0x3fffc7), - ioaddr + DMA_CHAN_STATUS(STMMAC_CHAN0)); + ioaddr + DMA_CHAN_STATUS(chan)); return ret; } diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac_dma.h b/drivers/net/ethernet/stmicro/stmmac/dwmac_dma.h index 56e485f79077..9091df86723a 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac_dma.h +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac_dma.h @@ -137,13 +137,14 @@ #define DMA_CONTROL_FTF 0x00100000 /* Flush transmit FIFO */ void dwmac_enable_dma_transmission(void __iomem *ioaddr); -void dwmac_enable_dma_irq(void __iomem *ioaddr); -void dwmac_disable_dma_irq(void __iomem *ioaddr); -void dwmac_dma_start_tx(void __iomem *ioaddr); -void dwmac_dma_stop_tx(void __iomem *ioaddr); -void dwmac_dma_start_rx(void __iomem *ioaddr); -void dwmac_dma_stop_rx(void __iomem *ioaddr); -int dwmac_dma_interrupt(void __iomem *ioaddr, struct stmmac_extra_stats *x); +void dwmac_enable_dma_irq(void __iomem *ioaddr, u32 chan); +void dwmac_disable_dma_irq(void __iomem *ioaddr, u32 chan); +void dwmac_dma_start_tx(void __iomem *ioaddr, u32 chan); +void dwmac_dma_stop_tx(void __iomem *ioaddr, u32 chan); +void dwmac_dma_start_rx(void __iomem *ioaddr, u32 chan); +void dwmac_dma_stop_rx(void __iomem *ioaddr, u32 chan); +int dwmac_dma_interrupt(void __iomem *ioaddr, struct stmmac_extra_stats *x, + u32 chan); int dwmac_dma_reset(void __iomem *ioaddr); #endif /* __DWMAC_DMA_H__ */ diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac_lib.c b/drivers/net/ethernet/stmicro/stmmac/dwmac_lib.c index e60bfca2a763..38f94305aab5 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac_lib.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac_lib.c @@ -47,38 +47,38 @@ void dwmac_enable_dma_transmission(void __iomem *ioaddr) writel(1, ioaddr + DMA_XMT_POLL_DEMAND); } -void dwmac_enable_dma_irq(void __iomem *ioaddr) +void dwmac_enable_dma_irq(void __iomem *ioaddr, u32 chan) { writel(DMA_INTR_DEFAULT_MASK, ioaddr + DMA_INTR_ENA); } -void dwmac_disable_dma_irq(void __iomem *ioaddr) +void dwmac_disable_dma_irq(void __iomem *ioaddr, u32 chan) { writel(0, ioaddr + DMA_INTR_ENA); } -void dwmac_dma_start_tx(void __iomem *ioaddr) +void dwmac_dma_start_tx(void __iomem *ioaddr, u32 chan) { u32 value = readl(ioaddr + DMA_CONTROL); value |= DMA_CONTROL_ST; writel(value, ioaddr + DMA_CONTROL); } -void dwmac_dma_stop_tx(void __iomem *ioaddr) +void dwmac_dma_stop_tx(void __iomem *ioaddr, u32 chan) { u32 value = readl(ioaddr + DMA_CONTROL); value &= ~DMA_CONTROL_ST; writel(value, ioaddr + DMA_CONTROL); } -void dwmac_dma_start_rx(void __iomem *ioaddr) +void dwmac_dma_start_rx(void __iomem *ioaddr, u32 chan) { u32 value = readl(ioaddr + DMA_CONTROL); value |= DMA_CONTROL_SR; writel(value, ioaddr + DMA_CONTROL); } -void dwmac_dma_stop_rx(void __iomem *ioaddr) +void dwmac_dma_stop_rx(void __iomem *ioaddr, u32 chan) { u32 value = readl(ioaddr + DMA_CONTROL); value &= ~DMA_CONTROL_SR; @@ -156,7 +156,7 @@ static void show_rx_process_state(unsigned int status) #endif int dwmac_dma_interrupt(void __iomem *ioaddr, - struct stmmac_extra_stats *x) + struct stmmac_extra_stats *x, u32 chan) { int ret = 0; /* read the status register (CSR5) */ diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c index 85d64114e159..16808e48ca1c 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c @@ -481,6 +481,7 @@ stmmac_set_pauseparam(struct net_device *netdev, struct ethtool_pauseparam *pause) { struct stmmac_priv *priv = netdev_priv(netdev); + u32 tx_cnt = priv->plat->tx_queues_to_use; struct phy_device *phy = netdev->phydev; int new_pause = FLOW_OFF; @@ -511,7 +512,7 @@ stmmac_set_pauseparam(struct net_device *netdev, } priv->hw->mac->flow_ctrl(priv->hw, phy->duplex, priv->flow_ctrl, - priv->pause); + priv->pause, tx_cnt); return 0; } @@ -519,6 +520,8 @@ static void stmmac_get_ethtool_stats(struct net_device *dev, struct ethtool_stats *dummy, u64 *data) { struct stmmac_priv *priv = netdev_priv(dev); + u32 rx_queues_count = priv->plat->rx_queues_to_use; + u32 tx_queues_count = priv->plat->tx_queues_to_use; int i, j = 0; /* Update the DMA HW counters for dwmac10/100 */ @@ -549,7 +552,8 @@ static void stmmac_get_ethtool_stats(struct net_device *dev, if ((priv->hw->mac->debug) && (priv->synopsys_id >= DWMAC_CORE_3_50)) priv->hw->mac->debug(priv->ioaddr, - (void *)&priv->xstats); + (void *)&priv->xstats, + rx_queues_count, tx_queues_count); } for (i = 0; i < STMMAC_STATS_LEN; i++) { char *p = (char *)priv + stmmac_gstrings_stats[i].stat_offset; @@ -726,6 +730,7 @@ static int stmmac_set_coalesce(struct net_device *dev, struct ethtool_coalesce *ec) { struct stmmac_priv *priv = netdev_priv(dev); + u32 rx_cnt = priv->plat->rx_queues_to_use; unsigned int rx_riwt; /* Check not supported parameters */ @@ -764,7 +769,7 @@ static int stmmac_set_coalesce(struct net_device *dev, priv->tx_coal_frames = ec->tx_max_coalesced_frames; priv->tx_coal_timer = ec->tx_coalesce_usecs; priv->rx_riwt = rx_riwt; - priv->hw->dma->rx_watchdog(priv->ioaddr, priv->rx_riwt); + priv->hw->dma->rx_watchdog(priv->ioaddr, priv->rx_riwt, rx_cnt); return 0; } diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index 4498a3861aa3..d3a21519e4c0 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -673,6 +673,19 @@ static void stmmac_release_ptp(struct stmmac_priv *priv) } /** + * stmmac_mac_flow_ctrl - Configure flow control in all queues + * @priv: driver private structure + * Description: It is used for configuring the flow control in all queues + */ +static void stmmac_mac_flow_ctrl(struct stmmac_priv *priv, u32 duplex) +{ + u32 tx_cnt = priv->plat->tx_queues_to_use; + + priv->hw->mac->flow_ctrl(priv->hw, duplex, priv->flow_ctrl, + priv->pause, tx_cnt); +} + +/** * stmmac_adjust_link - adjusts the link parameters * @dev: net device structure * Description: this is the helper called by the physical abstraction layer @@ -687,7 +700,6 @@ static void stmmac_adjust_link(struct net_device *dev) struct phy_device *phydev = dev->phydev; unsigned long flags; int new_state = 0; - unsigned int fc = priv->flow_ctrl, pause_time = priv->pause; if (!phydev) return; @@ -709,8 +721,7 @@ static void stmmac_adjust_link(struct net_device *dev) } /* Flow Control operation */ if (phydev->pause) - priv->hw->mac->flow_ctrl(priv->hw, phydev->duplex, - fc, pause_time); + stmmac_mac_flow_ctrl(priv, phydev->duplex); if (phydev->speed != priv->speed) { new_state = 1; @@ -1256,19 +1267,104 @@ static void free_dma_desc_resources(struct stmmac_priv *priv) */ static void stmmac_mac_enable_rx_queues(struct stmmac_priv *priv) { - int rx_count = priv->dma_cap.number_rx_queues; - int queue = 0; + u32 rx_queues_count = priv->plat->rx_queues_to_use; + int queue; + u8 mode; - /* If GMAC does not have multiple queues, then this is not necessary*/ - if (rx_count == 1) - return; + for (queue = 0; queue < rx_queues_count; queue++) { + mode = priv->plat->rx_queues_cfg[queue].mode_to_use; + priv->hw->mac->rx_queue_enable(priv->hw, mode, queue); + } +} - /** - * If the core is synthesized with multiple rx queues / multiple - * dma channels, then rx queues will be disabled by default. - * For now only rx queue 0 is enabled. - */ - priv->hw->mac->rx_queue_enable(priv->hw, queue); +/** + * stmmac_start_rx_dma - start RX DMA channel + * @priv: driver private structure + * @chan: RX channel index + * Description: + * This starts a RX DMA channel + */ +static void stmmac_start_rx_dma(struct stmmac_priv *priv, u32 chan) +{ + netdev_dbg(priv->dev, "DMA RX processes started in channel %d\n", chan); + priv->hw->dma->start_rx(priv->ioaddr, chan); +} + +/** + * stmmac_start_tx_dma - start TX DMA channel + * @priv: driver private structure + * @chan: TX channel index + * Description: + * This starts a TX DMA channel + */ +static void stmmac_start_tx_dma(struct stmmac_priv *priv, u32 chan) +{ + netdev_dbg(priv->dev, "DMA TX processes started in channel %d\n", chan); + priv->hw->dma->start_tx(priv->ioaddr, chan); +} + +/** + * stmmac_stop_rx_dma - stop RX DMA channel + * @priv: driver private structure + * @chan: RX channel index + * Description: + * This stops a RX DMA channel + */ +static void stmmac_stop_rx_dma(struct stmmac_priv *priv, u32 chan) +{ + netdev_dbg(priv->dev, "DMA RX processes stopped in channel %d\n", chan); + priv->hw->dma->stop_rx(priv->ioaddr, chan); +} + +/** + * stmmac_stop_tx_dma - stop TX DMA channel + * @priv: driver private structure + * @chan: TX channel index + * Description: + * This stops a TX DMA channel + */ +static void stmmac_stop_tx_dma(struct stmmac_priv *priv, u32 chan) +{ + netdev_dbg(priv->dev, "DMA TX processes stopped in channel %d\n", chan); + priv->hw->dma->stop_tx(priv->ioaddr, chan); +} + +/** + * stmmac_start_all_dma - start all RX and TX DMA channels + * @priv: driver private structure + * Description: + * This starts all the RX and TX DMA channels + */ +static void stmmac_start_all_dma(struct stmmac_priv *priv) +{ + u32 rx_channels_count = priv->plat->rx_queues_to_use; + u32 tx_channels_count = priv->plat->tx_queues_to_use; + u32 chan = 0; + + for (chan = 0; chan < rx_channels_count; chan++) + stmmac_start_rx_dma(priv, chan); + + for (chan = 0; chan < tx_channels_count; chan++) + stmmac_start_tx_dma(priv, chan); +} + +/** + * stmmac_stop_all_dma - stop all RX and TX DMA channels + * @priv: driver private structure + * Description: + * This stops the RX and TX DMA channels + */ +static void stmmac_stop_all_dma(struct stmmac_priv *priv) +{ + u32 rx_channels_count = priv->plat->rx_queues_to_use; + u32 tx_channels_count = priv->plat->tx_queues_to_use; + u32 chan = 0; + + for (chan = 0; chan < rx_channels_count; chan++) + stmmac_stop_rx_dma(priv, chan); + + for (chan = 0; chan < tx_channels_count; chan++) + stmmac_stop_tx_dma(priv, chan); } /** @@ -1279,11 +1375,20 @@ static void stmmac_mac_enable_rx_queues(struct stmmac_priv *priv) */ static void stmmac_dma_operation_mode(struct stmmac_priv *priv) { + u32 rx_channels_count = priv->plat->rx_queues_to_use; + u32 tx_channels_count = priv->plat->tx_queues_to_use; int rxfifosz = priv->plat->rx_fifo_size; + u32 txmode = 0; + u32 rxmode = 0; + u32 chan = 0; - if (priv->plat->force_thresh_dma_mode) - priv->hw->dma->dma_mode(priv->ioaddr, tc, tc, rxfifosz); - else if (priv->plat->force_sf_dma_mode || priv->plat->tx_coe) { + if (rxfifosz == 0) + rxfifosz = priv->dma_cap.rx_fifo_size; + + if (priv->plat->force_thresh_dma_mode) { + txmode = tc; + rxmode = tc; + } else if (priv->plat->force_sf_dma_mode || priv->plat->tx_coe) { /* * In case of GMAC, SF mode can be enabled * to perform the TX COE in HW. This depends on: @@ -1291,12 +1396,26 @@ static void stmmac_dma_operation_mode(struct stmmac_priv *priv) * 2) There is no bugged Jumbo frame support * that needs to not insert csum in the TDES. */ - priv->hw->dma->dma_mode(priv->ioaddr, SF_DMA_MODE, SF_DMA_MODE, - rxfifosz); + txmode = SF_DMA_MODE; + rxmode = SF_DMA_MODE; priv->xstats.threshold = SF_DMA_MODE; - } else - priv->hw->dma->dma_mode(priv->ioaddr, tc, SF_DMA_MODE, + } else { + txmode = tc; + rxmode = SF_DMA_MODE; + } + + /* configure all channels */ + if (priv->synopsys_id >= DWMAC_CORE_4_00) { + for (chan = 0; chan < rx_channels_count; chan++) + priv->hw->dma->dma_rx_mode(priv->ioaddr, rxmode, chan, + rxfifosz); + + for (chan = 0; chan < tx_channels_count; chan++) + priv->hw->dma->dma_tx_mode(priv->ioaddr, txmode, chan); + } else { + priv->hw->dma->dma_mode(priv->ioaddr, txmode, rxmode, rxfifosz); + } } /** @@ -1393,28 +1512,29 @@ static void stmmac_tx_clean(struct stmmac_priv *priv) netif_tx_unlock(priv->dev); } -static inline void stmmac_enable_dma_irq(struct stmmac_priv *priv) +static inline void stmmac_enable_dma_irq(struct stmmac_priv *priv, u32 chan) { - priv->hw->dma->enable_dma_irq(priv->ioaddr); + priv->hw->dma->enable_dma_irq(priv->ioaddr, chan); } -static inline void stmmac_disable_dma_irq(struct stmmac_priv *priv) +static inline void stmmac_disable_dma_irq(struct stmmac_priv *priv, u32 chan) { - priv->hw->dma->disable_dma_irq(priv->ioaddr); + priv->hw->dma->disable_dma_irq(priv->ioaddr, chan); } /** * stmmac_tx_err - to manage the tx error * @priv: driver private structure + * @chan: channel index * Description: it cleans the descriptors and restarts the transmission * in case of transmission errors. */ -static void stmmac_tx_err(struct stmmac_priv *priv) +static void stmmac_tx_err(struct stmmac_priv *priv, u32 chan) { int i; netif_stop_queue(priv->dev); - priv->hw->dma->stop_tx(priv->ioaddr); + stmmac_stop_tx_dma(priv, chan); dma_free_tx_skbufs(priv); for (i = 0; i < DMA_TX_SIZE; i++) if (priv->extend_desc) @@ -1428,13 +1548,41 @@ static void stmmac_tx_err(struct stmmac_priv *priv) priv->dirty_tx = 0; priv->cur_tx = 0; netdev_reset_queue(priv->dev); - priv->hw->dma->start_tx(priv->ioaddr); + stmmac_start_tx_dma(priv, chan); priv->dev->stats.tx_errors++; netif_wake_queue(priv->dev); } /** + * stmmac_set_dma_operation_mode - Set DMA operation mode by channel + * @priv: driver private structure + * @txmode: TX operating mode + * @rxmode: RX operating mode + * @chan: channel index + * Description: it is used for configuring of the DMA operation mode in + * runtime in order to program the tx/rx DMA thresholds or Store-And-Forward + * mode. + */ +static void stmmac_set_dma_operation_mode(struct stmmac_priv *priv, u32 txmode, + u32 rxmode, u32 chan) +{ + int rxfifosz = priv->plat->rx_fifo_size; + + if (rxfifosz == 0) + rxfifosz = priv->dma_cap.rx_fifo_size; + + if (priv->synopsys_id >= DWMAC_CORE_4_00) { + priv->hw->dma->dma_rx_mode(priv->ioaddr, rxmode, chan, + rxfifosz); + priv->hw->dma->dma_tx_mode(priv->ioaddr, txmode, chan); + } else { + priv->hw->dma->dma_mode(priv->ioaddr, txmode, rxmode, + rxfifosz); + } +} + +/** * stmmac_dma_interrupt - DMA ISR * @priv: driver private structure * Description: this is the DMA ISR. It is called by the main ISR. @@ -1443,31 +1591,41 @@ static void stmmac_tx_err(struct stmmac_priv *priv) */ static void stmmac_dma_interrupt(struct stmmac_priv *priv) { + u32 tx_channel_count = priv->plat->tx_queues_to_use; int status; - int rxfifosz = priv->plat->rx_fifo_size; + u32 chan; + + for (chan = 0; chan < tx_channel_count; chan++) { + status = priv->hw->dma->dma_interrupt(priv->ioaddr, + &priv->xstats, chan); + if (likely((status & handle_rx)) || (status & handle_tx)) { + if (likely(napi_schedule_prep(&priv->napi))) { + stmmac_disable_dma_irq(priv, chan); + __napi_schedule(&priv->napi); + } + } - status = priv->hw->dma->dma_interrupt(priv->ioaddr, &priv->xstats); - if (likely((status & handle_rx)) || (status & handle_tx)) { - if (likely(napi_schedule_prep(&priv->napi))) { - stmmac_disable_dma_irq(priv); - __napi_schedule(&priv->napi); + if (unlikely(status & tx_hard_error_bump_tc)) { + /* Try to bump up the dma threshold on this failure */ + if (unlikely(priv->xstats.threshold != SF_DMA_MODE) && + (tc <= 256)) { + tc += 64; + if (priv->plat->force_thresh_dma_mode) + stmmac_set_dma_operation_mode(priv, + tc, + tc, + chan); + else + stmmac_set_dma_operation_mode(priv, + tc, + SF_DMA_MODE, + chan); + priv->xstats.threshold = tc; + } + } else if (unlikely(status == tx_hard_error)) { + stmmac_tx_err(priv, chan); } } - if (unlikely(status & tx_hard_error_bump_tc)) { - /* Try to bump up the dma threshold on this failure */ - if (unlikely(priv->xstats.threshold != SF_DMA_MODE) && - (tc <= 256)) { - tc += 64; - if (priv->plat->force_thresh_dma_mode) - priv->hw->dma->dma_mode(priv->ioaddr, tc, tc, - rxfifosz); - else - priv->hw->dma->dma_mode(priv->ioaddr, tc, - SF_DMA_MODE, rxfifosz); - priv->xstats.threshold = tc; - } - } else if (unlikely(status == tx_hard_error)) - stmmac_tx_err(priv); } /** @@ -1574,6 +1732,11 @@ static void stmmac_check_ether_addr(struct stmmac_priv *priv) */ static int stmmac_init_dma_engine(struct stmmac_priv *priv) { + u32 rx_channels_count = priv->plat->rx_queues_to_use; + u32 tx_channels_count = priv->plat->tx_queues_to_use; + u32 dummy_dma_rx_phy = 0; + u32 dummy_dma_tx_phy = 0; + u32 chan = 0; int atds = 0; int ret = 0; @@ -1591,19 +1754,43 @@ static int stmmac_init_dma_engine(struct stmmac_priv *priv) return ret; } - priv->hw->dma->init(priv->ioaddr, priv->plat->dma_cfg, - priv->dma_tx_phy, priv->dma_rx_phy, atds); - if (priv->synopsys_id >= DWMAC_CORE_4_00) { - priv->rx_tail_addr = priv->dma_rx_phy + - (DMA_RX_SIZE * sizeof(struct dma_desc)); - priv->hw->dma->set_rx_tail_ptr(priv->ioaddr, priv->rx_tail_addr, - STMMAC_CHAN0); + /* DMA Configuration */ + priv->hw->dma->init(priv->ioaddr, priv->plat->dma_cfg, + dummy_dma_tx_phy, dummy_dma_rx_phy, atds); + + /* DMA RX Channel Configuration */ + for (chan = 0; chan < rx_channels_count; chan++) { + priv->hw->dma->init_rx_chan(priv->ioaddr, + priv->plat->dma_cfg, + priv->dma_rx_phy, chan); + + priv->rx_tail_addr = priv->dma_rx_phy + + (DMA_RX_SIZE * sizeof(struct dma_desc)); + priv->hw->dma->set_rx_tail_ptr(priv->ioaddr, + priv->rx_tail_addr, + chan); + } - priv->tx_tail_addr = priv->dma_tx_phy + - (DMA_TX_SIZE * sizeof(struct dma_desc)); - priv->hw->dma->set_tx_tail_ptr(priv->ioaddr, priv->tx_tail_addr, - STMMAC_CHAN0); + /* DMA TX Channel Configuration */ + for (chan = 0; chan < tx_channels_count; chan++) { + priv->hw->dma->init_chan(priv->ioaddr, + priv->plat->dma_cfg, + chan); + + priv->hw->dma->init_tx_chan(priv->ioaddr, + priv->plat->dma_cfg, + priv->dma_tx_phy, chan); + + priv->tx_tail_addr = priv->dma_tx_phy + + (DMA_TX_SIZE * sizeof(struct dma_desc)); + priv->hw->dma->set_tx_tail_ptr(priv->ioaddr, + priv->tx_tail_addr, + chan); + } + } else { + priv->hw->dma->init(priv->ioaddr, priv->plat->dma_cfg, + priv->dma_tx_phy, priv->dma_rx_phy, atds); } if (priv->plat->axi && priv->hw->dma->axi) @@ -1644,6 +1831,125 @@ static void stmmac_init_tx_coalesce(struct stmmac_priv *priv) add_timer(&priv->txtimer); } +static void stmmac_set_rings_length(struct stmmac_priv *priv) +{ + u32 rx_channels_count = priv->plat->rx_queues_to_use; + u32 tx_channels_count = priv->plat->tx_queues_to_use; + u32 chan; + + /* set TX ring length */ + if (priv->hw->dma->set_tx_ring_len) { + for (chan = 0; chan < tx_channels_count; chan++) + priv->hw->dma->set_tx_ring_len(priv->ioaddr, + (DMA_TX_SIZE - 1), chan); + } + + /* set RX ring length */ + if (priv->hw->dma->set_rx_ring_len) { + for (chan = 0; chan < rx_channels_count; chan++) + priv->hw->dma->set_rx_ring_len(priv->ioaddr, + (DMA_RX_SIZE - 1), chan); + } +} + +/** + * stmmac_set_tx_queue_weight - Set TX queue weight + * @priv: driver private structure + * Description: It is used for setting TX queues weight + */ +static void stmmac_set_tx_queue_weight(struct stmmac_priv *priv) +{ + u32 tx_queues_count = priv->plat->tx_queues_to_use; + u32 weight; + u32 queue; + + for (queue = 0; queue < tx_queues_count; queue++) { + weight = priv->plat->tx_queues_cfg[queue].weight; + priv->hw->mac->set_mtl_tx_queue_weight(priv->hw, weight, queue); + } +} + +/** + * stmmac_configure_cbs - Configure CBS in TX queue + * @priv: driver private structure + * Description: It is used for configuring CBS in AVB TX queues + */ +static void stmmac_configure_cbs(struct stmmac_priv *priv) +{ + u32 tx_queues_count = priv->plat->tx_queues_to_use; + u32 mode_to_use; + u32 queue; + + for (queue = 0; queue < tx_queues_count; queue++) { + mode_to_use = priv->plat->tx_queues_cfg[queue].mode_to_use; + if (mode_to_use == MTL_QUEUE_DCB) + continue; + + priv->hw->mac->config_cbs(priv->hw, + priv->plat->tx_queues_cfg[queue].send_slope, + priv->plat->tx_queues_cfg[queue].idle_slope, + priv->plat->tx_queues_cfg[queue].high_credit, + priv->plat->tx_queues_cfg[queue].low_credit, + queue); + } +} + +/** + * stmmac_rx_queue_dma_chan_map - Map RX queue to RX dma channel + * @priv: driver private structure + * Description: It is used for mapping RX queues to RX dma channels + */ +static void stmmac_rx_queue_dma_chan_map(struct stmmac_priv *priv) +{ + u32 rx_queues_count = priv->plat->rx_queues_to_use; + u32 queue; + u32 chan; + + for (queue = 0; queue < rx_queues_count; queue++) { + chan = priv->plat->rx_queues_cfg[queue].chan; + priv->hw->mac->map_mtl_to_dma(priv->hw, queue, chan); + } +} + +/** + * stmmac_mtl_configuration - Configure MTL + * @priv: driver private structure + * Description: It is used for configurring MTL + */ +static void stmmac_mtl_configuration(struct stmmac_priv *priv) +{ + u32 rx_queues_count = priv->plat->rx_queues_to_use; + u32 tx_queues_count = priv->plat->tx_queues_to_use; + + if (tx_queues_count > 1 && priv->hw->mac->set_mtl_tx_queue_weight) + stmmac_set_tx_queue_weight(priv); + + /* Configure MTL RX algorithms */ + if (rx_queues_count > 1 && priv->hw->mac->prog_mtl_rx_algorithms) + priv->hw->mac->prog_mtl_rx_algorithms(priv->hw, + priv->plat->rx_sched_algorithm); + + /* Configure MTL TX algorithms */ + if (tx_queues_count > 1 && priv->hw->mac->prog_mtl_tx_algorithms) + priv->hw->mac->prog_mtl_tx_algorithms(priv->hw, + priv->plat->tx_sched_algorithm); + + /* Configure CBS in AVB TX queues */ + if (tx_queues_count > 1 && priv->hw->mac->config_cbs) + stmmac_configure_cbs(priv); + + /* Map RX MTL to DMA channels */ + if (rx_queues_count > 1 && priv->hw->mac->map_mtl_to_dma) + stmmac_rx_queue_dma_chan_map(priv); + + /* Enable MAC RX Queues */ + if (rx_queues_count > 1 && priv->hw->mac->rx_queue_enable) + stmmac_mac_enable_rx_queues(priv); + + /* Set the HW DMA mode and the COE */ + stmmac_dma_operation_mode(priv); +} + /** * stmmac_hw_setup - setup mac in a usable state. * @dev : pointer to the device structure. @@ -1659,6 +1965,9 @@ static void stmmac_init_tx_coalesce(struct stmmac_priv *priv) static int stmmac_hw_setup(struct net_device *dev, bool init_ptp) { struct stmmac_priv *priv = netdev_priv(dev); + u32 rx_cnt = priv->plat->rx_queues_to_use; + u32 tx_cnt = priv->plat->tx_queues_to_use; + u32 chan; int ret; /* DMA initialization and SW reset */ @@ -1688,9 +1997,9 @@ static int stmmac_hw_setup(struct net_device *dev, bool init_ptp) /* Initialize the MAC Core */ priv->hw->mac->core_init(priv->hw, dev->mtu); - /* Initialize MAC RX Queues */ - if (priv->hw->mac->rx_queue_enable) - stmmac_mac_enable_rx_queues(priv); + /* Initialize MTL*/ + if (priv->synopsys_id >= DWMAC_CORE_4_00) + stmmac_mtl_configuration(priv); ret = priv->hw->mac->rx_ipc(priv->hw); if (!ret) { @@ -1705,12 +2014,13 @@ static int stmmac_hw_setup(struct net_device *dev, bool init_ptp) else stmmac_set_mac(priv->ioaddr, true); - /* Set the HW DMA mode and the COE */ - stmmac_dma_operation_mode(priv); - stmmac_mmc_setup(priv); if (init_ptp) { + ret = clk_prepare_enable(priv->plat->clk_ptp_ref); + if (ret < 0) + netdev_warn(priv->dev, "failed to enable PTP reference clock: %d\n", ret); + ret = stmmac_init_ptp(priv); if (ret == -EOPNOTSUPP) netdev_warn(priv->dev, "PTP not supported by HW\n"); @@ -1725,35 +2035,37 @@ static int stmmac_hw_setup(struct net_device *dev, bool init_ptp) __func__); #endif /* Start the ball rolling... */ - netdev_dbg(priv->dev, "DMA RX/TX processes started...\n"); - priv->hw->dma->start_tx(priv->ioaddr); - priv->hw->dma->start_rx(priv->ioaddr); + stmmac_start_all_dma(priv); priv->tx_lpi_timer = STMMAC_DEFAULT_TWT_LS; if ((priv->use_riwt) && (priv->hw->dma->rx_watchdog)) { priv->rx_riwt = MAX_DMA_RIWT; - priv->hw->dma->rx_watchdog(priv->ioaddr, MAX_DMA_RIWT); + priv->hw->dma->rx_watchdog(priv->ioaddr, MAX_DMA_RIWT, rx_cnt); } if (priv->hw->pcs && priv->hw->mac->pcs_ctrl_ane) priv->hw->mac->pcs_ctrl_ane(priv->hw, 1, priv->hw->ps, 0); - /* set TX ring length */ - if (priv->hw->dma->set_tx_ring_len) - priv->hw->dma->set_tx_ring_len(priv->ioaddr, - (DMA_TX_SIZE - 1)); - /* set RX ring length */ - if (priv->hw->dma->set_rx_ring_len) - priv->hw->dma->set_rx_ring_len(priv->ioaddr, - (DMA_RX_SIZE - 1)); + /* set TX and RX rings length */ + stmmac_set_rings_length(priv); + /* Enable TSO */ - if (priv->tso) - priv->hw->dma->enable_tso(priv->ioaddr, 1, STMMAC_CHAN0); + if (priv->tso) { + for (chan = 0; chan < tx_cnt; chan++) + priv->hw->dma->enable_tso(priv->ioaddr, 1, chan); + } return 0; } +static void stmmac_hw_teardown(struct net_device *dev) +{ + struct stmmac_priv *priv = netdev_priv(dev); + + clk_disable_unprepare(priv->plat->clk_ptp_ref); +} + /** * stmmac_open - open entry point of the driver * @dev : pointer to the device structure. @@ -1821,7 +2133,7 @@ static int stmmac_open(struct net_device *dev) netdev_err(priv->dev, "%s: ERROR: allocating the IRQ %d (error: %d)\n", __func__, dev->irq, ret); - goto init_error; + goto irq_error; } /* Request the Wake IRQ in case of another line is used for WoL */ @@ -1858,7 +2170,12 @@ lpiirq_error: free_irq(priv->wol_irq, dev); wolirq_error: free_irq(dev->irq, dev); +irq_error: + if (dev->phydev) + phy_stop(dev->phydev); + del_timer_sync(&priv->txtimer); + stmmac_hw_teardown(dev); init_error: free_dma_desc_resources(priv); dma_desc_error: @@ -1901,8 +2218,7 @@ static int stmmac_release(struct net_device *dev) free_irq(priv->lpi_irq, dev); /* Stop TX/RX DMA and clear the descriptors */ - priv->hw->dma->stop_tx(priv->ioaddr); - priv->hw->dma->stop_rx(priv->ioaddr); + stmmac_stop_all_dma(priv); /* Release and free the Rx/Tx resources */ free_dma_desc_resources(priv); @@ -2063,6 +2379,8 @@ static netdev_tx_t stmmac_tso_xmit(struct sk_buff *skb, struct net_device *dev) des = skb_frag_dma_map(priv->device, frag, 0, skb_frag_size(frag), DMA_TO_DEVICE); + if (dma_mapping_error(priv->device, des)) + goto dma_map_err; stmmac_tso_allocator(priv, des, skb_frag_size(frag), (i == nfrags - 1)); @@ -2661,6 +2979,7 @@ static int stmmac_poll(struct napi_struct *napi, int budget) { struct stmmac_priv *priv = container_of(napi, struct stmmac_priv, napi); int work_done = 0; + u32 chan = STMMAC_CHAN0; priv->xstats.napi_poll++; stmmac_tx_clean(priv); @@ -2668,7 +2987,7 @@ static int stmmac_poll(struct napi_struct *napi, int budget) work_done = stmmac_rx(priv, budget); if (work_done < budget) { napi_complete_done(napi, work_done); - stmmac_enable_dma_irq(priv); + stmmac_enable_dma_irq(priv, chan); } return work_done; } @@ -2684,9 +3003,10 @@ static int stmmac_poll(struct napi_struct *napi, int budget) static void stmmac_tx_timeout(struct net_device *dev) { struct stmmac_priv *priv = netdev_priv(dev); + u32 chan = STMMAC_CHAN0; /* Clear Tx resources and restart transmitting again */ - stmmac_tx_err(priv); + stmmac_tx_err(priv, chan); } /** @@ -2795,6 +3115,12 @@ static irqreturn_t stmmac_interrupt(int irq, void *dev_id) { struct net_device *dev = (struct net_device *)dev_id; struct stmmac_priv *priv = netdev_priv(dev); + u32 rx_cnt = priv->plat->rx_queues_to_use; + u32 tx_cnt = priv->plat->tx_queues_to_use; + u32 queues_count; + u32 queue; + + queues_count = (rx_cnt > tx_cnt) ? rx_cnt : tx_cnt; if (priv->irq_wake) pm_wakeup_event(priv->device, 0); @@ -2808,16 +3134,27 @@ static irqreturn_t stmmac_interrupt(int irq, void *dev_id) if ((priv->plat->has_gmac) || (priv->plat->has_gmac4)) { int status = priv->hw->mac->host_irq_status(priv->hw, &priv->xstats); + if (unlikely(status)) { /* For LPI we need to save the tx status */ if (status & CORE_IRQ_TX_PATH_IN_LPI_MODE) priv->tx_path_in_lpi_mode = true; if (status & CORE_IRQ_TX_PATH_EXIT_LPI_MODE) priv->tx_path_in_lpi_mode = false; - if (status & CORE_IRQ_MTL_RX_OVERFLOW && priv->hw->dma->set_rx_tail_ptr) - priv->hw->dma->set_rx_tail_ptr(priv->ioaddr, - priv->rx_tail_addr, - STMMAC_CHAN0); + } + + if (priv->synopsys_id >= DWMAC_CORE_4_00) { + for (queue = 0; queue < queues_count; queue++) { + status |= + priv->hw->mac->host_mtl_irq_status(priv->hw, + queue); + + if (status & CORE_IRQ_MTL_RX_OVERFLOW && + priv->hw->dma->set_rx_tail_ptr) + priv->hw->dma->set_rx_tail_ptr(priv->ioaddr, + priv->rx_tail_addr, + queue); + } } /* PCS link status */ @@ -3369,8 +3706,7 @@ int stmmac_dvr_remove(struct device *dev) netdev_info(priv->dev, "%s: removing driver", __func__); - priv->hw->dma->stop_rx(priv->ioaddr); - priv->hw->dma->stop_tx(priv->ioaddr); + stmmac_stop_all_dma(priv); stmmac_set_mac(priv->ioaddr, false); netif_carrier_off(ndev); @@ -3416,8 +3752,7 @@ int stmmac_suspend(struct device *dev) napi_disable(&priv->napi); /* Stop TX/RX DMA */ - priv->hw->dma->stop_tx(priv->ioaddr); - priv->hw->dma->stop_rx(priv->ioaddr); + stmmac_stop_all_dma(priv); /* Enable Power down mode by programming the PMT regs */ if (device_may_wakeup(priv->device)) { diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c index 5c9e462276b9..cea472a7c335 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c @@ -88,6 +88,10 @@ static void stmmac_default_data(struct plat_stmmacenet_data *plat) /* Set the maxmtu to a default of JUMBO_LEN */ plat->maxmtu = JUMBO_LEN; + + /* Set default number of RX and TX queues to use */ + plat->tx_queues_to_use = 1; + plat->rx_queues_to_use = 1; } static int quark_default_data(struct plat_stmmacenet_data *plat, diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c index 433a84239a68..37f550ae76a5 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c @@ -108,7 +108,7 @@ static struct stmmac_axi *stmmac_axi_setup(struct platform_device *pdev) if (!np) return NULL; - axi = kzalloc(sizeof(*axi), GFP_KERNEL); + axi = devm_kzalloc(&pdev->dev, sizeof(*axi), GFP_KERNEL); if (!axi) { of_node_put(np); return ERR_PTR(-ENOMEM); @@ -132,6 +132,118 @@ static struct stmmac_axi *stmmac_axi_setup(struct platform_device *pdev) } /** + * stmmac_mtl_setup - parse DT parameters for multiple queues configuration + * @pdev: platform device + */ +static void stmmac_mtl_setup(struct platform_device *pdev, + struct plat_stmmacenet_data *plat) +{ + struct device_node *q_node; + struct device_node *rx_node; + struct device_node *tx_node; + u8 queue = 0; + + rx_node = of_parse_phandle(pdev->dev.of_node, "snps,mtl-rx-config", 0); + if (!rx_node) + return; + + tx_node = of_parse_phandle(pdev->dev.of_node, "snps,mtl-tx-config", 0); + if (!tx_node) { + of_node_put(rx_node); + return; + } + + /* Processing RX queues common config */ + if (of_property_read_u8(rx_node, "snps,rx-queues-to-use", + &plat->rx_queues_to_use)) + plat->rx_queues_to_use = 1; + + if (of_property_read_bool(rx_node, "snps,rx-sched-sp")) + plat->rx_sched_algorithm = MTL_RX_ALGORITHM_SP; + else if (of_property_read_bool(rx_node, "snps,rx-sched-wsp")) + plat->rx_sched_algorithm = MTL_RX_ALGORITHM_WSP; + else + plat->rx_sched_algorithm = MTL_RX_ALGORITHM_SP; + + /* Processing individual RX queue config */ + for_each_child_of_node(rx_node, q_node) { + if (queue >= plat->rx_queues_to_use) + break; + + if (of_property_read_bool(q_node, "snps,dcb-algorithm")) + plat->rx_queues_cfg[queue].mode_to_use = MTL_QUEUE_DCB; + else if (of_property_read_bool(q_node, "snps,avb-algorithm")) + plat->rx_queues_cfg[queue].mode_to_use = MTL_QUEUE_AVB; + else + plat->rx_queues_cfg[queue].mode_to_use = MTL_QUEUE_DCB; + + if (of_property_read_u8(q_node, "snps,map-to-dma-channel", + &plat->rx_queues_cfg[queue].chan)) + plat->rx_queues_cfg[queue].chan = queue; + /* TODO: Dynamic mapping to be included in the future */ + + queue++; + } + + /* Processing TX queues common config */ + if (of_property_read_u8(tx_node, "snps,tx-queues-to-use", + &plat->tx_queues_to_use)) + plat->tx_queues_to_use = 1; + + if (of_property_read_bool(tx_node, "snps,tx-sched-wrr")) + plat->tx_sched_algorithm = MTL_TX_ALGORITHM_WRR; + else if (of_property_read_bool(tx_node, "snps,tx-sched-wfq")) + plat->tx_sched_algorithm = MTL_TX_ALGORITHM_WFQ; + else if (of_property_read_bool(tx_node, "snps,tx-sched-dwrr")) + plat->tx_sched_algorithm = MTL_TX_ALGORITHM_DWRR; + else if (of_property_read_bool(tx_node, "snps,tx-sched-sp")) + plat->tx_sched_algorithm = MTL_TX_ALGORITHM_SP; + else + plat->tx_sched_algorithm = MTL_TX_ALGORITHM_SP; + + queue = 0; + + /* Processing individual TX queue config */ + for_each_child_of_node(tx_node, q_node) { + if (queue >= plat->tx_queues_to_use) + break; + + if (of_property_read_u8(q_node, "snps,weight", + &plat->tx_queues_cfg[queue].weight)) + plat->tx_queues_cfg[queue].weight = 0x10 + queue; + + if (of_property_read_bool(q_node, "snps,dcb-algorithm")) { + plat->tx_queues_cfg[queue].mode_to_use = MTL_QUEUE_DCB; + } else if (of_property_read_bool(q_node, + "snps,avb-algorithm")) { + plat->tx_queues_cfg[queue].mode_to_use = MTL_QUEUE_AVB; + + /* Credit Base Shaper parameters used by AVB */ + if (of_property_read_u32(q_node, "snps,send_slope", + &plat->tx_queues_cfg[queue].send_slope)) + plat->tx_queues_cfg[queue].send_slope = 0x0; + if (of_property_read_u32(q_node, "snps,idle_slope", + &plat->tx_queues_cfg[queue].idle_slope)) + plat->tx_queues_cfg[queue].idle_slope = 0x0; + if (of_property_read_u32(q_node, "snps,high_credit", + &plat->tx_queues_cfg[queue].high_credit)) + plat->tx_queues_cfg[queue].high_credit = 0x0; + if (of_property_read_u32(q_node, "snps,low_credit", + &plat->tx_queues_cfg[queue].low_credit)) + plat->tx_queues_cfg[queue].low_credit = 0x0; + } else { + plat->tx_queues_cfg[queue].mode_to_use = MTL_QUEUE_DCB; + } + + queue++; + } + + of_node_put(rx_node); + of_node_put(tx_node); + of_node_put(q_node); +} + +/** * stmmac_dt_phy - parse device-tree driver parameters to allocate PHY resources * @plat: driver data platform structure * @np: device tree node @@ -340,6 +452,8 @@ stmmac_probe_config_dt(struct platform_device *pdev, const char **mac) plat->axi = stmmac_axi_setup(pdev); + stmmac_mtl_setup(pdev, plat); + /* clock setup */ plat->stmmac_clk = devm_clk_get(&pdev->dev, STMMAC_RESOURCE_NAME); @@ -359,13 +473,12 @@ stmmac_probe_config_dt(struct platform_device *pdev, const char **mac) clk_prepare_enable(plat->pclk); /* Fall-back to main clock in case of no PTP ref is passed */ - plat->clk_ptp_ref = devm_clk_get(&pdev->dev, "clk_ptp_ref"); + plat->clk_ptp_ref = devm_clk_get(&pdev->dev, "ptp_ref"); if (IS_ERR(plat->clk_ptp_ref)) { plat->clk_ptp_rate = clk_get_rate(plat->stmmac_clk); plat->clk_ptp_ref = NULL; dev_warn(&pdev->dev, "PTP uses main clock\n"); } else { - clk_prepare_enable(plat->clk_ptp_ref); plat->clk_ptp_rate = clk_get_rate(plat->clk_ptp_ref); dev_dbg(&pdev->dev, "PTP rate %d\n", plat->clk_ptp_rate); } diff --git a/drivers/net/ethernet/sun/cassini.c b/drivers/net/ethernet/sun/cassini.c index 0e8e89f17dbb..382993c1561c 100644 --- a/drivers/net/ethernet/sun/cassini.c +++ b/drivers/net/ethernet/sun/cassini.c @@ -691,7 +691,8 @@ static void cas_mif_poll(struct cas *cp, const int enable) } /* Must be invoked under cp->lock */ -static void cas_begin_auto_negotiation(struct cas *cp, struct ethtool_cmd *ep) +static void cas_begin_auto_negotiation(struct cas *cp, + const struct ethtool_link_ksettings *ep) { u16 ctl; #if 1 @@ -704,16 +705,16 @@ static void cas_begin_auto_negotiation(struct cas *cp, struct ethtool_cmd *ep) if (!ep) goto start_aneg; lcntl = cp->link_cntl; - if (ep->autoneg == AUTONEG_ENABLE) + if (ep->base.autoneg == AUTONEG_ENABLE) { cp->link_cntl = BMCR_ANENABLE; - else { - u32 speed = ethtool_cmd_speed(ep); + } else { + u32 speed = ep->base.speed; cp->link_cntl = 0; if (speed == SPEED_100) cp->link_cntl |= BMCR_SPEED100; else if (speed == SPEED_1000) cp->link_cntl |= CAS_BMCR_SPEED1000; - if (ep->duplex == DUPLEX_FULL) + if (ep->base.duplex == DUPLEX_FULL) cp->link_cntl |= BMCR_FULLDPLX; } #if 1 @@ -4528,19 +4529,21 @@ static void cas_get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *info strlcpy(info->bus_info, pci_name(cp->pdev), sizeof(info->bus_info)); } -static int cas_get_settings(struct net_device *dev, struct ethtool_cmd *cmd) +static int cas_get_link_ksettings(struct net_device *dev, + struct ethtool_link_ksettings *cmd) { struct cas *cp = netdev_priv(dev); u16 bmcr; int full_duplex, speed, pause; unsigned long flags; enum link_state linkstate = link_up; + u32 supported, advertising; - cmd->advertising = 0; - cmd->supported = SUPPORTED_Autoneg; + advertising = 0; + supported = SUPPORTED_Autoneg; if (cp->cas_flags & CAS_FLAG_1000MB_CAP) { - cmd->supported |= SUPPORTED_1000baseT_Full; - cmd->advertising |= ADVERTISED_1000baseT_Full; + supported |= SUPPORTED_1000baseT_Full; + advertising |= ADVERTISED_1000baseT_Full; } /* Record PHY settings if HW is on. */ @@ -4548,17 +4551,15 @@ static int cas_get_settings(struct net_device *dev, struct ethtool_cmd *cmd) bmcr = 0; linkstate = cp->lstate; if (CAS_PHY_MII(cp->phy_type)) { - cmd->port = PORT_MII; - cmd->transceiver = (cp->cas_flags & CAS_FLAG_SATURN) ? - XCVR_INTERNAL : XCVR_EXTERNAL; - cmd->phy_address = cp->phy_addr; - cmd->advertising |= ADVERTISED_TP | ADVERTISED_MII | + cmd->base.port = PORT_MII; + cmd->base.phy_address = cp->phy_addr; + advertising |= ADVERTISED_TP | ADVERTISED_MII | ADVERTISED_10baseT_Half | ADVERTISED_10baseT_Full | ADVERTISED_100baseT_Half | ADVERTISED_100baseT_Full; - cmd->supported |= + supported |= (SUPPORTED_10baseT_Half | SUPPORTED_10baseT_Full | SUPPORTED_100baseT_Half | @@ -4574,11 +4575,10 @@ static int cas_get_settings(struct net_device *dev, struct ethtool_cmd *cmd) } } else { - cmd->port = PORT_FIBRE; - cmd->transceiver = XCVR_INTERNAL; - cmd->phy_address = 0; - cmd->supported |= SUPPORTED_FIBRE; - cmd->advertising |= ADVERTISED_FIBRE; + cmd->base.port = PORT_FIBRE; + cmd->base.phy_address = 0; + supported |= SUPPORTED_FIBRE; + advertising |= ADVERTISED_FIBRE; if (cp->hw_running) { /* pcs uses the same bits as mii */ @@ -4590,21 +4590,20 @@ static int cas_get_settings(struct net_device *dev, struct ethtool_cmd *cmd) spin_unlock_irqrestore(&cp->lock, flags); if (bmcr & BMCR_ANENABLE) { - cmd->advertising |= ADVERTISED_Autoneg; - cmd->autoneg = AUTONEG_ENABLE; - ethtool_cmd_speed_set(cmd, ((speed == 10) ? + advertising |= ADVERTISED_Autoneg; + cmd->base.autoneg = AUTONEG_ENABLE; + cmd->base.speed = ((speed == 10) ? SPEED_10 : ((speed == 1000) ? - SPEED_1000 : SPEED_100))); - cmd->duplex = full_duplex ? DUPLEX_FULL : DUPLEX_HALF; + SPEED_1000 : SPEED_100)); + cmd->base.duplex = full_duplex ? DUPLEX_FULL : DUPLEX_HALF; } else { - cmd->autoneg = AUTONEG_DISABLE; - ethtool_cmd_speed_set(cmd, ((bmcr & CAS_BMCR_SPEED1000) ? + cmd->base.autoneg = AUTONEG_DISABLE; + cmd->base.speed = ((bmcr & CAS_BMCR_SPEED1000) ? SPEED_1000 : ((bmcr & BMCR_SPEED100) ? - SPEED_100 : SPEED_10))); - cmd->duplex = - (bmcr & BMCR_FULLDPLX) ? + SPEED_100 : SPEED_10)); + cmd->base.duplex = (bmcr & BMCR_FULLDPLX) ? DUPLEX_FULL : DUPLEX_HALF; } if (linkstate != link_up) { @@ -4619,39 +4618,46 @@ static int cas_get_settings(struct net_device *dev, struct ethtool_cmd *cmd) * settings that we configured. */ if (cp->link_cntl & BMCR_ANENABLE) { - ethtool_cmd_speed_set(cmd, 0); - cmd->duplex = 0xff; + cmd->base.speed = 0; + cmd->base.duplex = 0xff; } else { - ethtool_cmd_speed_set(cmd, SPEED_10); + cmd->base.speed = SPEED_10; if (cp->link_cntl & BMCR_SPEED100) { - ethtool_cmd_speed_set(cmd, SPEED_100); + cmd->base.speed = SPEED_100; } else if (cp->link_cntl & CAS_BMCR_SPEED1000) { - ethtool_cmd_speed_set(cmd, SPEED_1000); + cmd->base.speed = SPEED_1000; } - cmd->duplex = (cp->link_cntl & BMCR_FULLDPLX)? + cmd->base.duplex = (cp->link_cntl & BMCR_FULLDPLX) ? DUPLEX_FULL : DUPLEX_HALF; } } + + ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.supported, + supported); + ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.advertising, + advertising); + return 0; } -static int cas_set_settings(struct net_device *dev, struct ethtool_cmd *cmd) +static int cas_set_link_ksettings(struct net_device *dev, + const struct ethtool_link_ksettings *cmd) { struct cas *cp = netdev_priv(dev); unsigned long flags; - u32 speed = ethtool_cmd_speed(cmd); + u32 speed = cmd->base.speed; /* Verify the settings we care about. */ - if (cmd->autoneg != AUTONEG_ENABLE && - cmd->autoneg != AUTONEG_DISABLE) + if (cmd->base.autoneg != AUTONEG_ENABLE && + cmd->base.autoneg != AUTONEG_DISABLE) return -EINVAL; - if (cmd->autoneg == AUTONEG_DISABLE && + if (cmd->base.autoneg == AUTONEG_DISABLE && ((speed != SPEED_1000 && speed != SPEED_100 && speed != SPEED_10) || - (cmd->duplex != DUPLEX_HALF && - cmd->duplex != DUPLEX_FULL))) + (cmd->base.duplex != DUPLEX_HALF && + cmd->base.duplex != DUPLEX_FULL))) return -EINVAL; /* Apply settings and restart link process. */ @@ -4753,8 +4759,6 @@ static void cas_get_ethtool_stats(struct net_device *dev, static const struct ethtool_ops cas_ethtool_ops = { .get_drvinfo = cas_get_drvinfo, - .get_settings = cas_get_settings, - .set_settings = cas_set_settings, .nway_reset = cas_nway_reset, .get_link = cas_get_link, .get_msglevel = cas_get_msglevel, @@ -4764,6 +4768,8 @@ static const struct ethtool_ops cas_ethtool_ops = { .get_sset_count = cas_get_sset_count, .get_strings = cas_get_strings, .get_ethtool_stats = cas_get_ethtool_stats, + .get_link_ksettings = cas_get_link_ksettings, + .set_link_ksettings = cas_set_link_ksettings, }; static int cas_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) diff --git a/drivers/net/ethernet/sun/ldmvsw.c b/drivers/net/ethernet/sun/ldmvsw.c index 89952deae47f..5a90fed06260 100644 --- a/drivers/net/ethernet/sun/ldmvsw.c +++ b/drivers/net/ethernet/sun/ldmvsw.c @@ -1,6 +1,6 @@ /* ldmvsw.c: Sun4v LDOM Virtual Switch Driver. * - * Copyright (C) 2016 Oracle. All rights reserved. + * Copyright (C) 2016-2017 Oracle. All rights reserved. */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt @@ -41,8 +41,8 @@ static u8 vsw_port_hwaddr[ETH_ALEN] = {0xFE, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF}; #define DRV_MODULE_NAME "ldmvsw" -#define DRV_MODULE_VERSION "1.1" -#define DRV_MODULE_RELDATE "February 3, 2017" +#define DRV_MODULE_VERSION "1.2" +#define DRV_MODULE_RELDATE "March 4, 2017" static char version[] = DRV_MODULE_NAME " " DRV_MODULE_VERSION " (" DRV_MODULE_RELDATE ")"; @@ -123,6 +123,20 @@ static void vsw_set_rx_mode(struct net_device *dev) return sunvnet_set_rx_mode_common(dev, port->vp); } +int ldmvsw_open(struct net_device *dev) +{ + struct vnet_port *port = netdev_priv(dev); + struct vio_driver_state *vio = &port->vio; + + /* reset the channel */ + vio_link_state_change(vio, LDC_EVENT_RESET); + vnet_port_reset(port); + vio_port_up(vio); + + return 0; +} +EXPORT_SYMBOL_GPL(ldmvsw_open); + #ifdef CONFIG_NET_POLL_CONTROLLER static void vsw_poll_controller(struct net_device *dev) { @@ -133,7 +147,7 @@ static void vsw_poll_controller(struct net_device *dev) #endif static const struct net_device_ops vsw_ops = { - .ndo_open = sunvnet_open_common, + .ndo_open = ldmvsw_open, .ndo_stop = sunvnet_close_common, .ndo_set_rx_mode = vsw_set_rx_mode, .ndo_set_mac_address = sunvnet_set_mac_addr_common, @@ -365,6 +379,11 @@ static int vsw_port_probe(struct vio_dev *vdev, const struct vio_device_id *id) napi_enable(&port->napi); vio_port_up(&port->vio); + /* assure no carrier until we receive an LDC_EVENT_UP, + * even if the vsw config script tries to force us up + */ + netif_carrier_off(dev); + netdev_info(dev, "LDOM vsw-port %pM\n", dev->dev_addr); pr_info("%s: PORT ( remote-mac %pM%s )\n", dev->name, diff --git a/drivers/net/ethernet/sun/niu.c b/drivers/net/ethernet/sun/niu.c index 57978056b336..2dcca249eb9c 100644 --- a/drivers/net/ethernet/sun/niu.c +++ b/drivers/net/ethernet/sun/niu.c @@ -6813,7 +6813,8 @@ static void niu_get_drvinfo(struct net_device *dev, sizeof(info->bus_info)); } -static int niu_get_settings(struct net_device *dev, struct ethtool_cmd *cmd) +static int niu_get_link_ksettings(struct net_device *dev, + struct ethtool_link_ksettings *cmd) { struct niu *np = netdev_priv(dev); struct niu_link_config *lp; @@ -6821,28 +6822,30 @@ static int niu_get_settings(struct net_device *dev, struct ethtool_cmd *cmd) lp = &np->link_config; memset(cmd, 0, sizeof(*cmd)); - cmd->phy_address = np->phy_addr; - cmd->supported = lp->supported; - cmd->advertising = lp->active_advertising; - cmd->autoneg = lp->active_autoneg; - ethtool_cmd_speed_set(cmd, lp->active_speed); - cmd->duplex = lp->active_duplex; - cmd->port = (np->flags & NIU_FLAGS_FIBER) ? PORT_FIBRE : PORT_TP; - cmd->transceiver = (np->flags & NIU_FLAGS_XCVR_SERDES) ? - XCVR_EXTERNAL : XCVR_INTERNAL; + cmd->base.phy_address = np->phy_addr; + ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.supported, + lp->supported); + ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.advertising, + lp->active_advertising); + cmd->base.autoneg = lp->active_autoneg; + cmd->base.speed = lp->active_speed; + cmd->base.duplex = lp->active_duplex; + cmd->base.port = (np->flags & NIU_FLAGS_FIBER) ? PORT_FIBRE : PORT_TP; return 0; } -static int niu_set_settings(struct net_device *dev, struct ethtool_cmd *cmd) +static int niu_set_link_ksettings(struct net_device *dev, + const struct ethtool_link_ksettings *cmd) { struct niu *np = netdev_priv(dev); struct niu_link_config *lp = &np->link_config; - lp->advertising = cmd->advertising; - lp->speed = ethtool_cmd_speed(cmd); - lp->duplex = cmd->duplex; - lp->autoneg = cmd->autoneg; + ethtool_convert_link_mode_to_legacy_u32(&lp->advertising, + cmd->link_modes.advertising); + lp->speed = cmd->base.speed; + lp->duplex = cmd->base.duplex; + lp->autoneg = cmd->base.autoneg; return niu_init_link(np); } @@ -7902,14 +7905,14 @@ static const struct ethtool_ops niu_ethtool_ops = { .nway_reset = niu_nway_reset, .get_eeprom_len = niu_get_eeprom_len, .get_eeprom = niu_get_eeprom, - .get_settings = niu_get_settings, - .set_settings = niu_set_settings, .get_strings = niu_get_strings, .get_sset_count = niu_get_sset_count, .get_ethtool_stats = niu_get_ethtool_stats, .set_phys_id = niu_set_phys_id, .get_rxnfc = niu_get_nfc, .set_rxnfc = niu_set_nfc, + .get_link_ksettings = niu_get_link_ksettings, + .set_link_ksettings = niu_set_link_ksettings, }; static int niu_ldg_assign_ldn(struct niu *np, struct niu_parent *parent, diff --git a/drivers/net/ethernet/sun/sungem.c b/drivers/net/ethernet/sun/sungem.c index 5c5952e782cd..dbfca0466760 100644 --- a/drivers/net/ethernet/sun/sungem.c +++ b/drivers/net/ethernet/sun/sungem.c @@ -1250,12 +1250,17 @@ static void gem_stop_dma(struct gem *gp) // XXX dbl check what that function should do when called on PCS PHY -static void gem_begin_auto_negotiation(struct gem *gp, struct ethtool_cmd *ep) +static void gem_begin_auto_negotiation(struct gem *gp, + const struct ethtool_link_ksettings *ep) { u32 advertise, features; int autoneg; int speed; int duplex; + u32 advertising; + + ethtool_convert_link_mode_to_legacy_u32(&advertising, + ep->link_modes.advertising); if (gp->phy_type != phy_mii_mdio0 && gp->phy_type != phy_mii_mdio1) @@ -1278,13 +1283,13 @@ static void gem_begin_auto_negotiation(struct gem *gp, struct ethtool_cmd *ep) /* Setup link parameters */ if (!ep) goto start_aneg; - if (ep->autoneg == AUTONEG_ENABLE) { - advertise = ep->advertising; + if (ep->base.autoneg == AUTONEG_ENABLE) { + advertise = advertising; autoneg = 1; } else { autoneg = 0; - speed = ethtool_cmd_speed(ep); - duplex = ep->duplex; + speed = ep->base.speed; + duplex = ep->base.duplex; } start_aneg: @@ -2515,85 +2520,96 @@ static void gem_get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *info strlcpy(info->bus_info, pci_name(gp->pdev), sizeof(info->bus_info)); } -static int gem_get_settings(struct net_device *dev, struct ethtool_cmd *cmd) +static int gem_get_link_ksettings(struct net_device *dev, + struct ethtool_link_ksettings *cmd) { struct gem *gp = netdev_priv(dev); + u32 supported, advertising; if (gp->phy_type == phy_mii_mdio0 || gp->phy_type == phy_mii_mdio1) { if (gp->phy_mii.def) - cmd->supported = gp->phy_mii.def->features; + supported = gp->phy_mii.def->features; else - cmd->supported = (SUPPORTED_10baseT_Half | + supported = (SUPPORTED_10baseT_Half | SUPPORTED_10baseT_Full); /* XXX hardcoded stuff for now */ - cmd->port = PORT_MII; - cmd->transceiver = XCVR_EXTERNAL; - cmd->phy_address = 0; /* XXX fixed PHYAD */ + cmd->base.port = PORT_MII; + cmd->base.phy_address = 0; /* XXX fixed PHYAD */ /* Return current PHY settings */ - cmd->autoneg = gp->want_autoneg; - ethtool_cmd_speed_set(cmd, gp->phy_mii.speed); - cmd->duplex = gp->phy_mii.duplex; - cmd->advertising = gp->phy_mii.advertising; + cmd->base.autoneg = gp->want_autoneg; + cmd->base.speed = gp->phy_mii.speed; + cmd->base.duplex = gp->phy_mii.duplex; + advertising = gp->phy_mii.advertising; /* If we started with a forced mode, we don't have a default * advertise set, we need to return something sensible so * userland can re-enable autoneg properly. */ - if (cmd->advertising == 0) - cmd->advertising = cmd->supported; + if (advertising == 0) + advertising = supported; } else { // XXX PCS ? - cmd->supported = + supported = (SUPPORTED_10baseT_Half | SUPPORTED_10baseT_Full | SUPPORTED_100baseT_Half | SUPPORTED_100baseT_Full | SUPPORTED_Autoneg); - cmd->advertising = cmd->supported; - ethtool_cmd_speed_set(cmd, 0); - cmd->duplex = cmd->port = cmd->phy_address = - cmd->transceiver = cmd->autoneg = 0; + advertising = supported; + cmd->base.speed = 0; + cmd->base.duplex = 0; + cmd->base.port = 0; + cmd->base.phy_address = 0; + cmd->base.autoneg = 0; /* serdes means usually a Fibre connector, with most fixed */ if (gp->phy_type == phy_serdes) { - cmd->port = PORT_FIBRE; - cmd->supported = (SUPPORTED_1000baseT_Half | + cmd->base.port = PORT_FIBRE; + supported = (SUPPORTED_1000baseT_Half | SUPPORTED_1000baseT_Full | SUPPORTED_FIBRE | SUPPORTED_Autoneg | SUPPORTED_Pause | SUPPORTED_Asym_Pause); - cmd->advertising = cmd->supported; - cmd->transceiver = XCVR_INTERNAL; + advertising = supported; if (gp->lstate == link_up) - ethtool_cmd_speed_set(cmd, SPEED_1000); - cmd->duplex = DUPLEX_FULL; - cmd->autoneg = 1; + cmd->base.speed = SPEED_1000; + cmd->base.duplex = DUPLEX_FULL; + cmd->base.autoneg = 1; } } - cmd->maxtxpkt = cmd->maxrxpkt = 0; + + ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.supported, + supported); + ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.advertising, + advertising); return 0; } -static int gem_set_settings(struct net_device *dev, struct ethtool_cmd *cmd) +static int gem_set_link_ksettings(struct net_device *dev, + const struct ethtool_link_ksettings *cmd) { struct gem *gp = netdev_priv(dev); - u32 speed = ethtool_cmd_speed(cmd); + u32 speed = cmd->base.speed; + u32 advertising; + + ethtool_convert_link_mode_to_legacy_u32(&advertising, + cmd->link_modes.advertising); /* Verify the settings we care about. */ - if (cmd->autoneg != AUTONEG_ENABLE && - cmd->autoneg != AUTONEG_DISABLE) + if (cmd->base.autoneg != AUTONEG_ENABLE && + cmd->base.autoneg != AUTONEG_DISABLE) return -EINVAL; - if (cmd->autoneg == AUTONEG_ENABLE && - cmd->advertising == 0) + if (cmd->base.autoneg == AUTONEG_ENABLE && + advertising == 0) return -EINVAL; - if (cmd->autoneg == AUTONEG_DISABLE && + if (cmd->base.autoneg == AUTONEG_DISABLE && ((speed != SPEED_1000 && speed != SPEED_100 && speed != SPEED_10) || - (cmd->duplex != DUPLEX_HALF && - cmd->duplex != DUPLEX_FULL))) + (cmd->base.duplex != DUPLEX_HALF && + cmd->base.duplex != DUPLEX_FULL))) return -EINVAL; /* Apply settings and restart link process. */ @@ -2666,13 +2682,13 @@ static int gem_set_wol(struct net_device *dev, struct ethtool_wolinfo *wol) static const struct ethtool_ops gem_ethtool_ops = { .get_drvinfo = gem_get_drvinfo, .get_link = ethtool_op_get_link, - .get_settings = gem_get_settings, - .set_settings = gem_set_settings, .nway_reset = gem_nway_reset, .get_msglevel = gem_get_msglevel, .set_msglevel = gem_set_msglevel, .get_wol = gem_get_wol, .set_wol = gem_set_wol, + .get_link_ksettings = gem_get_link_ksettings, + .set_link_ksettings = gem_set_link_ksettings, }; static int gem_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) diff --git a/drivers/net/ethernet/sun/sunhme.c b/drivers/net/ethernet/sun/sunhme.c index 72ff05cd3ed8..53ff66ef53ac 100644 --- a/drivers/net/ethernet/sun/sunhme.c +++ b/drivers/net/ethernet/sun/sunhme.c @@ -1294,9 +1294,10 @@ static void happy_meal_init_rings(struct happy_meal *hp) } /* hp->happy_lock must be held */ -static void happy_meal_begin_auto_negotiation(struct happy_meal *hp, - void __iomem *tregs, - struct ethtool_cmd *ep) +static void +happy_meal_begin_auto_negotiation(struct happy_meal *hp, + void __iomem *tregs, + const struct ethtool_link_ksettings *ep) { int timeout; @@ -1309,7 +1310,7 @@ static void happy_meal_begin_auto_negotiation(struct happy_meal *hp, /* XXX Check BMSR_ANEGCAPABLE, should not be necessary though. */ hp->sw_advertise = happy_meal_tcvr_read(hp, tregs, MII_ADVERTISE); - if (ep == NULL || ep->autoneg == AUTONEG_ENABLE) { + if (!ep || ep->base.autoneg == AUTONEG_ENABLE) { /* Advertise everything we can support. */ if (hp->sw_bmsr & BMSR_10HALF) hp->sw_advertise |= (ADVERTISE_10HALF); @@ -1384,14 +1385,14 @@ force_link: /* Disable auto-negotiation in BMCR, enable the duplex and * speed setting, init the timer state machine, and fire it off. */ - if (ep == NULL || ep->autoneg == AUTONEG_ENABLE) { + if (!ep || ep->base.autoneg == AUTONEG_ENABLE) { hp->sw_bmcr = BMCR_SPEED100; } else { - if (ethtool_cmd_speed(ep) == SPEED_100) + if (ep->base.speed == SPEED_100) hp->sw_bmcr = BMCR_SPEED100; else hp->sw_bmcr = 0; - if (ep->duplex == DUPLEX_FULL) + if (ep->base.duplex == DUPLEX_FULL) hp->sw_bmcr |= BMCR_FULLDPLX; } happy_meal_tcvr_write(hp, tregs, MII_BMCR, hp->sw_bmcr); @@ -2434,20 +2435,21 @@ static void happy_meal_set_multicast(struct net_device *dev) } /* Ethtool support... */ -static int hme_get_settings(struct net_device *dev, struct ethtool_cmd *cmd) +static int hme_get_link_ksettings(struct net_device *dev, + struct ethtool_link_ksettings *cmd) { struct happy_meal *hp = netdev_priv(dev); u32 speed; + u32 supported; - cmd->supported = + supported = (SUPPORTED_10baseT_Half | SUPPORTED_10baseT_Full | SUPPORTED_100baseT_Half | SUPPORTED_100baseT_Full | SUPPORTED_Autoneg | SUPPORTED_TP | SUPPORTED_MII); /* XXX hardcoded stuff for now */ - cmd->port = PORT_TP; /* XXX no MII support */ - cmd->transceiver = XCVR_INTERNAL; /* XXX no external xcvr support */ - cmd->phy_address = 0; /* XXX fixed PHYAD */ + cmd->base.port = PORT_TP; /* XXX no MII support */ + cmd->base.phy_address = 0; /* XXX fixed PHYAD */ /* Record PHY settings. */ spin_lock_irq(&hp->happy_lock); @@ -2456,41 +2458,45 @@ static int hme_get_settings(struct net_device *dev, struct ethtool_cmd *cmd) spin_unlock_irq(&hp->happy_lock); if (hp->sw_bmcr & BMCR_ANENABLE) { - cmd->autoneg = AUTONEG_ENABLE; + cmd->base.autoneg = AUTONEG_ENABLE; speed = ((hp->sw_lpa & (LPA_100HALF | LPA_100FULL)) ? SPEED_100 : SPEED_10); if (speed == SPEED_100) - cmd->duplex = + cmd->base.duplex = (hp->sw_lpa & (LPA_100FULL)) ? DUPLEX_FULL : DUPLEX_HALF; else - cmd->duplex = + cmd->base.duplex = (hp->sw_lpa & (LPA_10FULL)) ? DUPLEX_FULL : DUPLEX_HALF; } else { - cmd->autoneg = AUTONEG_DISABLE; + cmd->base.autoneg = AUTONEG_DISABLE; speed = (hp->sw_bmcr & BMCR_SPEED100) ? SPEED_100 : SPEED_10; - cmd->duplex = + cmd->base.duplex = (hp->sw_bmcr & BMCR_FULLDPLX) ? DUPLEX_FULL : DUPLEX_HALF; } - ethtool_cmd_speed_set(cmd, speed); + cmd->base.speed = speed; + ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.supported, + supported); + return 0; } -static int hme_set_settings(struct net_device *dev, struct ethtool_cmd *cmd) +static int hme_set_link_ksettings(struct net_device *dev, + const struct ethtool_link_ksettings *cmd) { struct happy_meal *hp = netdev_priv(dev); /* Verify the settings we care about. */ - if (cmd->autoneg != AUTONEG_ENABLE && - cmd->autoneg != AUTONEG_DISABLE) + if (cmd->base.autoneg != AUTONEG_ENABLE && + cmd->base.autoneg != AUTONEG_DISABLE) return -EINVAL; - if (cmd->autoneg == AUTONEG_DISABLE && - ((ethtool_cmd_speed(cmd) != SPEED_100 && - ethtool_cmd_speed(cmd) != SPEED_10) || - (cmd->duplex != DUPLEX_HALF && - cmd->duplex != DUPLEX_FULL))) + if (cmd->base.autoneg == AUTONEG_DISABLE && + ((cmd->base.speed != SPEED_100 && + cmd->base.speed != SPEED_10) || + (cmd->base.duplex != DUPLEX_HALF && + cmd->base.duplex != DUPLEX_FULL))) return -EINVAL; /* Ok, do it to it. */ @@ -2537,10 +2543,10 @@ static u32 hme_get_link(struct net_device *dev) } static const struct ethtool_ops hme_ethtool_ops = { - .get_settings = hme_get_settings, - .set_settings = hme_set_settings, .get_drvinfo = hme_get_drvinfo, .get_link = hme_get_link, + .get_link_ksettings = hme_get_link_ksettings, + .set_link_ksettings = hme_set_link_ksettings, }; static int hme_version_printed; diff --git a/drivers/net/ethernet/sun/sunvnet.c b/drivers/net/ethernet/sun/sunvnet.c index 4cc2571f71c6..0b95105f7060 100644 --- a/drivers/net/ethernet/sun/sunvnet.c +++ b/drivers/net/ethernet/sun/sunvnet.c @@ -1,7 +1,7 @@ /* sunvnet.c: Sun LDOM Virtual Network Driver. * * Copyright (C) 2007, 2008 David S. Miller <[email protected]> - * Copyright (C) 2016 Oracle. All rights reserved. + * Copyright (C) 2016-2017 Oracle. All rights reserved. */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt @@ -77,11 +77,125 @@ static void vnet_set_msglevel(struct net_device *dev, u32 value) vp->msg_enable = value; } +static const struct { + const char string[ETH_GSTRING_LEN]; +} ethtool_stats_keys[] = { + { "rx_packets" }, + { "tx_packets" }, + { "rx_bytes" }, + { "tx_bytes" }, + { "rx_errors" }, + { "tx_errors" }, + { "rx_dropped" }, + { "tx_dropped" }, + { "multicast" }, + { "rx_length_errors" }, + { "rx_frame_errors" }, + { "rx_missed_errors" }, + { "tx_carrier_errors" }, + { "nports" }, +}; + +static int vnet_get_sset_count(struct net_device *dev, int sset) +{ + struct vnet *vp = (struct vnet *)netdev_priv(dev); + + switch (sset) { + case ETH_SS_STATS: + return ARRAY_SIZE(ethtool_stats_keys) + + (NUM_VNET_PORT_STATS * vp->nports); + default: + return -EOPNOTSUPP; + } +} + +static void vnet_get_strings(struct net_device *dev, u32 stringset, u8 *buf) +{ + struct vnet *vp = (struct vnet *)netdev_priv(dev); + struct vnet_port *port; + char *p = (char *)buf; + + switch (stringset) { + case ETH_SS_STATS: + memcpy(buf, ðtool_stats_keys, sizeof(ethtool_stats_keys)); + p += sizeof(ethtool_stats_keys); + + rcu_read_lock(); + list_for_each_entry_rcu(port, &vp->port_list, list) { + snprintf(p, ETH_GSTRING_LEN, "p%u.%s-%pM", + port->q_index, port->switch_port ? "s" : "q", + port->raddr); + p += ETH_GSTRING_LEN; + snprintf(p, ETH_GSTRING_LEN, "p%u.rx_packets", + port->q_index); + p += ETH_GSTRING_LEN; + snprintf(p, ETH_GSTRING_LEN, "p%u.tx_packets", + port->q_index); + p += ETH_GSTRING_LEN; + snprintf(p, ETH_GSTRING_LEN, "p%u.rx_bytes", + port->q_index); + p += ETH_GSTRING_LEN; + snprintf(p, ETH_GSTRING_LEN, "p%u.tx_bytes", + port->q_index); + p += ETH_GSTRING_LEN; + snprintf(p, ETH_GSTRING_LEN, "p%u.event_up", + port->q_index); + p += ETH_GSTRING_LEN; + snprintf(p, ETH_GSTRING_LEN, "p%u.event_reset", + port->q_index); + p += ETH_GSTRING_LEN; + } + rcu_read_unlock(); + break; + default: + WARN_ON(1); + break; + } +} + +static void vnet_get_ethtool_stats(struct net_device *dev, + struct ethtool_stats *estats, u64 *data) +{ + struct vnet *vp = (struct vnet *)netdev_priv(dev); + struct vnet_port *port; + int i = 0; + + data[i++] = dev->stats.rx_packets; + data[i++] = dev->stats.tx_packets; + data[i++] = dev->stats.rx_bytes; + data[i++] = dev->stats.tx_bytes; + data[i++] = dev->stats.rx_errors; + data[i++] = dev->stats.tx_errors; + data[i++] = dev->stats.rx_dropped; + data[i++] = dev->stats.tx_dropped; + data[i++] = dev->stats.multicast; + data[i++] = dev->stats.rx_length_errors; + data[i++] = dev->stats.rx_frame_errors; + data[i++] = dev->stats.rx_missed_errors; + data[i++] = dev->stats.tx_carrier_errors; + data[i++] = vp->nports; + + rcu_read_lock(); + list_for_each_entry_rcu(port, &vp->port_list, list) { + data[i++] = port->q_index; + data[i++] = port->stats.rx_packets; + data[i++] = port->stats.tx_packets; + data[i++] = port->stats.rx_bytes; + data[i++] = port->stats.tx_bytes; + data[i++] = port->stats.event_up; + data[i++] = port->stats.event_reset; + } + rcu_read_unlock(); +} + static const struct ethtool_ops vnet_ethtool_ops = { .get_drvinfo = vnet_get_drvinfo, .get_msglevel = vnet_get_msglevel, .set_msglevel = vnet_set_msglevel, .get_link = ethtool_op_get_link, + .get_sset_count = vnet_get_sset_count, + .get_strings = vnet_get_strings, + .get_ethtool_stats = vnet_get_ethtool_stats, }; static LIST_HEAD(vnet_list); diff --git a/drivers/net/ethernet/sun/sunvnet_common.c b/drivers/net/ethernet/sun/sunvnet_common.c index fa2d11ca9b81..9e86833249d4 100644 --- a/drivers/net/ethernet/sun/sunvnet_common.c +++ b/drivers/net/ethernet/sun/sunvnet_common.c @@ -1,7 +1,7 @@ /* sunvnet.c: Sun LDOM Virtual Network Driver. * * Copyright (C) 2007, 2008 David S. Miller <[email protected]> - * Copyright (C) 2016 Oracle. All rights reserved. + * Copyright (C) 2016-2017 Oracle. All rights reserved. */ #include <linux/module.h> @@ -43,7 +43,6 @@ MODULE_LICENSE("GPL"); MODULE_VERSION("1.1"); static int __vnet_tx_trigger(struct vnet_port *port, u32 start); -static void vnet_port_reset(struct vnet_port *port); static inline u32 vnet_tx_dring_avail(struct vio_dring_state *dr) { @@ -410,8 +409,12 @@ static int vnet_rx_one(struct vnet_port *port, struct vio_net_desc *desc) skb->ip_summed = port->switch_port ? CHECKSUM_NONE : CHECKSUM_PARTIAL; + if (unlikely(is_multicast_ether_addr(eth_hdr(skb)->h_dest))) + dev->stats.multicast++; dev->stats.rx_packets++; dev->stats.rx_bytes += len; + port->stats.rx_packets++; + port->stats.rx_bytes += len; napi_gro_receive(&port->napi, skb); return 0; @@ -747,6 +750,13 @@ static int vnet_event_napi(struct vnet_port *port, int budget) /* RESET takes precedent over any other event */ if (port->rx_event & LDC_EVENT_RESET) { + /* a link went down */ + + if (port->vsw == 1) { + netif_tx_stop_all_queues(dev); + netif_carrier_off(dev); + } + vio_link_state_change(vio, LDC_EVENT_RESET); vnet_port_reset(port); vio_port_up(vio); @@ -762,12 +772,21 @@ static int vnet_event_napi(struct vnet_port *port, int budget) maybe_tx_wakeup(port); port->rx_event = 0; + port->stats.event_reset++; return 0; } if (port->rx_event & LDC_EVENT_UP) { + /* a link came up */ + + if (port->vsw == 1) { + netif_carrier_on(port->dev); + netif_tx_start_all_queues(port->dev); + } + vio_link_state_change(vio, LDC_EVENT_UP); port->rx_event = 0; + port->stats.event_up++; return 0; } @@ -1417,6 +1436,8 @@ ldc_start_done: dev->stats.tx_packets++; dev->stats.tx_bytes += port->tx_bufs[txi].skb->len; + port->stats.tx_packets++; + port->stats.tx_bytes += port->tx_bufs[txi].skb->len; dr->prod = (dr->prod + 1) & (VNET_TX_RING_SIZE - 1); if (unlikely(vnet_tx_dring_avail(dr) < 1)) { @@ -1631,7 +1652,7 @@ void sunvnet_port_free_tx_bufs_common(struct vnet_port *port) } EXPORT_SYMBOL_GPL(sunvnet_port_free_tx_bufs_common); -static void vnet_port_reset(struct vnet_port *port) +void vnet_port_reset(struct vnet_port *port) { del_timer(&port->clean_timer); sunvnet_port_free_tx_bufs_common(port); @@ -1639,6 +1660,7 @@ static void vnet_port_reset(struct vnet_port *port) port->tso = (port->vsw == 0); /* no tso in vsw, misbehaves in bridge */ port->tsolen = 0; } +EXPORT_SYMBOL_GPL(vnet_port_reset); static int vnet_port_alloc_tx_ring(struct vnet_port *port) { @@ -1708,20 +1730,32 @@ EXPORT_SYMBOL_GPL(sunvnet_poll_controller_common); void sunvnet_port_add_txq_common(struct vnet_port *port) { struct vnet *vp = port->vp; - int n; + int smallest = 0; + int i; + + /* find the first least-used q + * When there are more ldoms than q's, we start to + * double up on ports per queue. + */ + for (i = 0; i < VNET_MAX_TXQS; i++) { + if (vp->q_used[i] == 0) { + smallest = i; + break; + } + if (vp->q_used[i] < vp->q_used[smallest]) + smallest = i; + } - n = vp->nports++; - n = n & (VNET_MAX_TXQS - 1); - port->q_index = n; - netif_tx_wake_queue(netdev_get_tx_queue(VNET_PORT_TO_NET_DEVICE(port), - port->q_index)); + vp->nports++; + vp->q_used[smallest]++; + port->q_index = smallest; } EXPORT_SYMBOL_GPL(sunvnet_port_add_txq_common); void sunvnet_port_rm_txq_common(struct vnet_port *port) { port->vp->nports--; - netif_tx_stop_queue(netdev_get_tx_queue(VNET_PORT_TO_NET_DEVICE(port), - port->q_index)); + port->vp->q_used[port->q_index]--; + port->q_index = 0; } EXPORT_SYMBOL_GPL(sunvnet_port_rm_txq_common); diff --git a/drivers/net/ethernet/sun/sunvnet_common.h b/drivers/net/ethernet/sun/sunvnet_common.h index ce5c824128a3..b20d6fa7ef25 100644 --- a/drivers/net/ethernet/sun/sunvnet_common.h +++ b/drivers/net/ethernet/sun/sunvnet_common.h @@ -35,6 +35,19 @@ struct vnet_tx_entry { struct vnet; +struct vnet_port_stats { + /* keep them all the same size */ + u32 rx_bytes; + u32 tx_bytes; + u32 rx_packets; + u32 tx_packets; + u32 event_up; + u32 event_reset; + u32 q_placeholder; +}; + +#define NUM_VNET_PORT_STATS (sizeof(struct vnet_port_stats) / sizeof(u32)) + /* Structure to describe a vnet-port or vsw-port in the MD. * If the vsw bit is set, this structure represents a vswitch * port, and the net_device can be found from ->dev. If the @@ -44,6 +57,8 @@ struct vnet; struct vnet_port { struct vio_driver_state vio; + struct vnet_port_stats stats; + struct hlist_node hash; u8 raddr[ETH_ALEN]; unsigned switch_port:1; @@ -97,22 +112,15 @@ struct vnet_mcast_entry { }; struct vnet { - /* Protects port_list and port_hash. */ - spinlock_t lock; - + spinlock_t lock; /* Protects port_list and port_hash. */ struct net_device *dev; - u32 msg_enable; - + u8 q_used[VNET_MAX_TXQS]; struct list_head port_list; - struct hlist_head port_hash[VNET_PORT_HASH_SIZE]; - struct vnet_mcast_entry *mcast_list; - struct list_head list; u64 local_mac; - int nports; }; @@ -139,6 +147,7 @@ int sunvnet_handle_attr_common(struct vio_driver_state *vio, void *arg); void sunvnet_handshake_complete_common(struct vio_driver_state *vio); int sunvnet_poll_common(struct napi_struct *napi, int budget); void sunvnet_port_free_tx_bufs_common(struct vnet_port *port); +void vnet_port_reset(struct vnet_port *port); bool sunvnet_port_is_up_common(struct vnet_port *vnet); void sunvnet_port_add_txq_common(struct vnet_port *port); void sunvnet_port_rm_txq_common(struct vnet_port *port); diff --git a/drivers/net/ethernet/synopsys/Kconfig b/drivers/net/ethernet/synopsys/Kconfig new file mode 100644 index 000000000000..a9503884e1c2 --- /dev/null +++ b/drivers/net/ethernet/synopsys/Kconfig @@ -0,0 +1,41 @@ +# +# Synopsys network device configuration +# + +config NET_VENDOR_SYNOPSYS + bool "Synopsys devices" + default y + ---help--- + If you have a network (Ethernet) device belonging to this class, say Y. + + Note that the answer to this question doesn't directly affect the + kernel: saying N will just cause the configurator to skip all + the questions about Synopsys devices. If you say Y, you will be asked + for your specific device in the following questions. + +if NET_VENDOR_SYNOPSYS + +config DWC_XLGMAC + tristate "Synopsys DWC Enterprise Ethernet (XLGMAC) driver support" + depends on HAS_IOMEM && HAS_DMA + select BITREVERSE + select CRC32 + ---help--- + This driver supports the Synopsys DesignWare Cores Enterprise + Ethernet (dwc-xlgmac). + +if DWC_XLGMAC + +config DWC_XLGMAC_PCI + tristate "XLGMAC PCI bus support" + depends on DWC_XLGMAC && PCI + ---help--- + This selects the pci bus support for the dwc-xlgmac driver. + This driver was tested on Synopsys XLGMAC IP Prototyping Kit. + + If you have a controller with this interface, say Y or M here. + If unsure, say N. + +endif # DWC_XLGMAC + +endif # NET_VENDOR_SYNOPSYS diff --git a/drivers/net/ethernet/synopsys/Makefile b/drivers/net/ethernet/synopsys/Makefile new file mode 100644 index 000000000000..c06e2eb3be90 --- /dev/null +++ b/drivers/net/ethernet/synopsys/Makefile @@ -0,0 +1,9 @@ +# +# Makefile for the Synopsys network device drivers. +# + +obj-$(CONFIG_DWC_XLGMAC) += dwc-xlgmac.o +dwc-xlgmac-objs := dwc-xlgmac-net.o dwc-xlgmac-desc.o \ + dwc-xlgmac-hw.o dwc-xlgmac-common.o + +dwc-xlgmac-$(CONFIG_DWC_XLGMAC_PCI) += dwc-xlgmac-pci.o diff --git a/drivers/net/ethernet/synopsys/dwc-xlgmac-common.c b/drivers/net/ethernet/synopsys/dwc-xlgmac-common.c new file mode 100644 index 000000000000..726d78ac4907 --- /dev/null +++ b/drivers/net/ethernet/synopsys/dwc-xlgmac-common.c @@ -0,0 +1,736 @@ +/* Synopsys DesignWare Core Enterprise Ethernet (XLGMAC) Driver + * + * Copyright (c) 2017 Synopsys, Inc. (www.synopsys.com) + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the + * Free Software Foundation; either version 2 of the License, or (at your + * option) any later version. + * + * This Synopsys DWC XLGMAC software driver and associated documentation + * (hereinafter the "Software") is an unsupported proprietary work of + * Synopsys, Inc. unless otherwise expressly agreed to in writing between + * Synopsys and you. The Software IS NOT an item of Licensed Software or a + * Licensed Product under any End User Software License Agreement or + * Agreement for Licensed Products with Synopsys or any supplement thereto. + * Synopsys is a registered trademark of Synopsys, Inc. Other names included + * in the SOFTWARE may be the trademarks of their respective owners. + */ + +#include <linux/kernel.h> +#include <linux/module.h> + +#include "dwc-xlgmac.h" +#include "dwc-xlgmac-reg.h" + +static int debug = -1; +module_param(debug, int, 0644); +MODULE_PARM_DESC(debug, "DWC ethernet debug level (0=none,...,16=all)"); +static const u32 default_msg_level = (NETIF_MSG_LINK | NETIF_MSG_IFDOWN | + NETIF_MSG_IFUP); + +static unsigned char dev_addr[6] = {0, 0x55, 0x7b, 0xb5, 0x7d, 0xf7}; + +static void xlgmac_read_mac_addr(struct xlgmac_pdata *pdata) +{ + struct net_device *netdev = pdata->netdev; + + /* Currently it uses a static mac address for test */ + memcpy(pdata->mac_addr, dev_addr, netdev->addr_len); +} + +static void xlgmac_default_config(struct xlgmac_pdata *pdata) +{ + pdata->tx_osp_mode = DMA_OSP_ENABLE; + pdata->tx_sf_mode = MTL_TSF_ENABLE; + pdata->rx_sf_mode = MTL_RSF_DISABLE; + pdata->pblx8 = DMA_PBL_X8_ENABLE; + pdata->tx_pbl = DMA_PBL_32; + pdata->rx_pbl = DMA_PBL_32; + pdata->tx_threshold = MTL_TX_THRESHOLD_128; + pdata->rx_threshold = MTL_RX_THRESHOLD_128; + pdata->tx_pause = 1; + pdata->rx_pause = 1; + pdata->phy_speed = SPEED_25000; + pdata->sysclk_rate = XLGMAC_SYSCLOCK; + + strlcpy(pdata->drv_name, XLGMAC_DRV_NAME, sizeof(pdata->drv_name)); + strlcpy(pdata->drv_ver, XLGMAC_DRV_VERSION, sizeof(pdata->drv_ver)); +} + +static void xlgmac_init_all_ops(struct xlgmac_pdata *pdata) +{ + xlgmac_init_desc_ops(&pdata->desc_ops); + xlgmac_init_hw_ops(&pdata->hw_ops); +} + +static int xlgmac_init(struct xlgmac_pdata *pdata) +{ + struct xlgmac_hw_ops *hw_ops = &pdata->hw_ops; + struct net_device *netdev = pdata->netdev; + unsigned int i; + int ret; + + /* Set default configuration data */ + xlgmac_default_config(pdata); + + /* Set irq, base_addr, MAC address, */ + netdev->irq = pdata->dev_irq; + netdev->base_addr = (unsigned long)pdata->mac_regs; + xlgmac_read_mac_addr(pdata); + memcpy(netdev->dev_addr, pdata->mac_addr, netdev->addr_len); + + /* Set all the function pointers */ + xlgmac_init_all_ops(pdata); + + /* Issue software reset to device */ + hw_ops->exit(pdata); + + /* Populate the hardware features */ + xlgmac_get_all_hw_features(pdata); + xlgmac_print_all_hw_features(pdata); + + /* TODO: Set the PHY mode to XLGMII */ + + /* Set the DMA mask */ + ret = dma_set_mask_and_coherent(pdata->dev, + DMA_BIT_MASK(pdata->hw_feat.dma_width)); + if (ret) { + dev_err(pdata->dev, "dma_set_mask_and_coherent failed\n"); + return ret; + } + + /* Channel and ring params initializtion + * pdata->channel_count; + * pdata->tx_ring_count; + * pdata->rx_ring_count; + * pdata->tx_desc_count; + * pdata->rx_desc_count; + */ + BUILD_BUG_ON_NOT_POWER_OF_2(XLGMAC_TX_DESC_CNT); + pdata->tx_desc_count = XLGMAC_TX_DESC_CNT; + if (pdata->tx_desc_count & (pdata->tx_desc_count - 1)) { + dev_err(pdata->dev, "tx descriptor count (%d) is not valid\n", + pdata->tx_desc_count); + ret = -EINVAL; + return ret; + } + BUILD_BUG_ON_NOT_POWER_OF_2(XLGMAC_RX_DESC_CNT); + pdata->rx_desc_count = XLGMAC_RX_DESC_CNT; + if (pdata->rx_desc_count & (pdata->rx_desc_count - 1)) { + dev_err(pdata->dev, "rx descriptor count (%d) is not valid\n", + pdata->rx_desc_count); + ret = -EINVAL; + return ret; + } + + pdata->tx_ring_count = min_t(unsigned int, num_online_cpus(), + pdata->hw_feat.tx_ch_cnt); + pdata->tx_ring_count = min_t(unsigned int, pdata->tx_ring_count, + pdata->hw_feat.tx_q_cnt); + pdata->tx_q_count = pdata->tx_ring_count; + ret = netif_set_real_num_tx_queues(netdev, pdata->tx_q_count); + if (ret) { + dev_err(pdata->dev, "error setting real tx queue count\n"); + return ret; + } + + pdata->rx_ring_count = min_t(unsigned int, + netif_get_num_default_rss_queues(), + pdata->hw_feat.rx_ch_cnt); + pdata->rx_ring_count = min_t(unsigned int, pdata->rx_ring_count, + pdata->hw_feat.rx_q_cnt); + pdata->rx_q_count = pdata->rx_ring_count; + ret = netif_set_real_num_rx_queues(netdev, pdata->rx_q_count); + if (ret) { + dev_err(pdata->dev, "error setting real rx queue count\n"); + return ret; + } + + pdata->channel_count = + max_t(unsigned int, pdata->tx_ring_count, pdata->rx_ring_count); + + /* Initialize RSS hash key and lookup table */ + netdev_rss_key_fill(pdata->rss_key, sizeof(pdata->rss_key)); + + for (i = 0; i < XLGMAC_RSS_MAX_TABLE_SIZE; i++) + pdata->rss_table[i] = XLGMAC_SET_REG_BITS( + pdata->rss_table[i], + MAC_RSSDR_DMCH_POS, + MAC_RSSDR_DMCH_LEN, + i % pdata->rx_ring_count); + + pdata->rss_options = XLGMAC_SET_REG_BITS( + pdata->rss_options, + MAC_RSSCR_IP2TE_POS, + MAC_RSSCR_IP2TE_LEN, 1); + pdata->rss_options = XLGMAC_SET_REG_BITS( + pdata->rss_options, + MAC_RSSCR_TCP4TE_POS, + MAC_RSSCR_TCP4TE_LEN, 1); + pdata->rss_options = XLGMAC_SET_REG_BITS( + pdata->rss_options, + MAC_RSSCR_UDP4TE_POS, + MAC_RSSCR_UDP4TE_LEN, 1); + + /* Set device operations */ + netdev->netdev_ops = xlgmac_get_netdev_ops(); + + /* Set device features */ + if (pdata->hw_feat.tso) { + netdev->hw_features = NETIF_F_TSO; + netdev->hw_features |= NETIF_F_TSO6; + netdev->hw_features |= NETIF_F_SG; + netdev->hw_features |= NETIF_F_IP_CSUM; + netdev->hw_features |= NETIF_F_IPV6_CSUM; + } else if (pdata->hw_feat.tx_coe) { + netdev->hw_features = NETIF_F_IP_CSUM; + netdev->hw_features |= NETIF_F_IPV6_CSUM; + } + + if (pdata->hw_feat.rx_coe) { + netdev->hw_features |= NETIF_F_RXCSUM; + netdev->hw_features |= NETIF_F_GRO; + } + + if (pdata->hw_feat.rss) + netdev->hw_features |= NETIF_F_RXHASH; + + netdev->vlan_features |= netdev->hw_features; + + netdev->hw_features |= NETIF_F_HW_VLAN_CTAG_RX; + if (pdata->hw_feat.sa_vlan_ins) + netdev->hw_features |= NETIF_F_HW_VLAN_CTAG_TX; + if (pdata->hw_feat.vlhash) + netdev->hw_features |= NETIF_F_HW_VLAN_CTAG_FILTER; + + netdev->features |= netdev->hw_features; + pdata->netdev_features = netdev->features; + + netdev->priv_flags |= IFF_UNICAST_FLT; + + /* Use default watchdog timeout */ + netdev->watchdog_timeo = 0; + + /* Tx coalesce parameters initialization */ + pdata->tx_usecs = XLGMAC_INIT_DMA_TX_USECS; + pdata->tx_frames = XLGMAC_INIT_DMA_TX_FRAMES; + + /* Rx coalesce parameters initialization */ + pdata->rx_riwt = hw_ops->usec_to_riwt(pdata, XLGMAC_INIT_DMA_RX_USECS); + pdata->rx_usecs = XLGMAC_INIT_DMA_RX_USECS; + pdata->rx_frames = XLGMAC_INIT_DMA_RX_FRAMES; + + return 0; +} + +int xlgmac_drv_probe(struct device *dev, struct xlgmac_resources *res) +{ + struct xlgmac_pdata *pdata; + struct net_device *netdev; + int ret; + + netdev = alloc_etherdev_mq(sizeof(struct xlgmac_pdata), + XLGMAC_MAX_DMA_CHANNELS); + + if (!netdev) { + dev_err(dev, "alloc_etherdev failed\n"); + return -ENOMEM; + } + + SET_NETDEV_DEV(netdev, dev); + dev_set_drvdata(dev, netdev); + pdata = netdev_priv(netdev); + pdata->dev = dev; + pdata->netdev = netdev; + + pdata->dev_irq = res->irq; + pdata->mac_regs = res->addr; + + mutex_init(&pdata->rss_mutex); + pdata->msg_enable = netif_msg_init(debug, default_msg_level); + + ret = xlgmac_init(pdata); + if (ret) { + dev_err(dev, "xlgmac init failed\n"); + goto err_free_netdev; + } + + ret = register_netdev(netdev); + if (ret) { + dev_err(dev, "net device registration failed\n"); + goto err_free_netdev; + } + + return 0; + +err_free_netdev: + free_netdev(netdev); + + return ret; +} + +int xlgmac_drv_remove(struct device *dev) +{ + struct net_device *netdev = dev_get_drvdata(dev); + + unregister_netdev(netdev); + free_netdev(netdev); + + return 0; +} + +void xlgmac_dump_tx_desc(struct xlgmac_pdata *pdata, + struct xlgmac_ring *ring, + unsigned int idx, + unsigned int count, + unsigned int flag) +{ + struct xlgmac_desc_data *desc_data; + struct xlgmac_dma_desc *dma_desc; + + while (count--) { + desc_data = XLGMAC_GET_DESC_DATA(ring, idx); + dma_desc = desc_data->dma_desc; + + netdev_dbg(pdata->netdev, "TX: dma_desc=%p, dma_desc_addr=%pad\n", + desc_data->dma_desc, &desc_data->dma_desc_addr); + netdev_dbg(pdata->netdev, + "TX_NORMAL_DESC[%d %s] = %08x:%08x:%08x:%08x\n", idx, + (flag == 1) ? "QUEUED FOR TX" : "TX BY DEVICE", + le32_to_cpu(dma_desc->desc0), + le32_to_cpu(dma_desc->desc1), + le32_to_cpu(dma_desc->desc2), + le32_to_cpu(dma_desc->desc3)); + + idx++; + } +} + +void xlgmac_dump_rx_desc(struct xlgmac_pdata *pdata, + struct xlgmac_ring *ring, + unsigned int idx) +{ + struct xlgmac_desc_data *desc_data; + struct xlgmac_dma_desc *dma_desc; + + desc_data = XLGMAC_GET_DESC_DATA(ring, idx); + dma_desc = desc_data->dma_desc; + + netdev_dbg(pdata->netdev, "RX: dma_desc=%p, dma_desc_addr=%pad\n", + desc_data->dma_desc, &desc_data->dma_desc_addr); + netdev_dbg(pdata->netdev, + "RX_NORMAL_DESC[%d RX BY DEVICE] = %08x:%08x:%08x:%08x\n", + idx, + le32_to_cpu(dma_desc->desc0), + le32_to_cpu(dma_desc->desc1), + le32_to_cpu(dma_desc->desc2), + le32_to_cpu(dma_desc->desc3)); +} + +void xlgmac_print_pkt(struct net_device *netdev, + struct sk_buff *skb, bool tx_rx) +{ + struct ethhdr *eth = (struct ethhdr *)skb->data; + unsigned char *buf = skb->data; + unsigned char buffer[128]; + unsigned int i, j; + + netdev_dbg(netdev, "\n************** SKB dump ****************\n"); + + netdev_dbg(netdev, "%s packet of %d bytes\n", + (tx_rx ? "TX" : "RX"), skb->len); + + netdev_dbg(netdev, "Dst MAC addr: %pM\n", eth->h_dest); + netdev_dbg(netdev, "Src MAC addr: %pM\n", eth->h_source); + netdev_dbg(netdev, "Protocol: %#06hx\n", ntohs(eth->h_proto)); + + for (i = 0, j = 0; i < skb->len;) { + j += snprintf(buffer + j, sizeof(buffer) - j, "%02hhx", + buf[i++]); + + if ((i % 32) == 0) { + netdev_dbg(netdev, " %#06x: %s\n", i - 32, buffer); + j = 0; + } else if ((i % 16) == 0) { + buffer[j++] = ' '; + buffer[j++] = ' '; + } else if ((i % 4) == 0) { + buffer[j++] = ' '; + } + } + if (i % 32) + netdev_dbg(netdev, " %#06x: %s\n", i - (i % 32), buffer); + + netdev_dbg(netdev, "\n************** SKB dump ****************\n"); +} + +void xlgmac_get_all_hw_features(struct xlgmac_pdata *pdata) +{ + struct xlgmac_hw_features *hw_feat = &pdata->hw_feat; + unsigned int mac_hfr0, mac_hfr1, mac_hfr2; + + mac_hfr0 = readl(pdata->mac_regs + MAC_HWF0R); + mac_hfr1 = readl(pdata->mac_regs + MAC_HWF1R); + mac_hfr2 = readl(pdata->mac_regs + MAC_HWF2R); + + memset(hw_feat, 0, sizeof(*hw_feat)); + + hw_feat->version = readl(pdata->mac_regs + MAC_VR); + + /* Hardware feature register 0 */ + hw_feat->phyifsel = XLGMAC_GET_REG_BITS(mac_hfr0, + MAC_HWF0R_PHYIFSEL_POS, + MAC_HWF0R_PHYIFSEL_LEN); + hw_feat->vlhash = XLGMAC_GET_REG_BITS(mac_hfr0, + MAC_HWF0R_VLHASH_POS, + MAC_HWF0R_VLHASH_LEN); + hw_feat->sma = XLGMAC_GET_REG_BITS(mac_hfr0, + MAC_HWF0R_SMASEL_POS, + MAC_HWF0R_SMASEL_LEN); + hw_feat->rwk = XLGMAC_GET_REG_BITS(mac_hfr0, + MAC_HWF0R_RWKSEL_POS, + MAC_HWF0R_RWKSEL_LEN); + hw_feat->mgk = XLGMAC_GET_REG_BITS(mac_hfr0, + MAC_HWF0R_MGKSEL_POS, + MAC_HWF0R_MGKSEL_LEN); + hw_feat->mmc = XLGMAC_GET_REG_BITS(mac_hfr0, + MAC_HWF0R_MMCSEL_POS, + MAC_HWF0R_MMCSEL_LEN); + hw_feat->aoe = XLGMAC_GET_REG_BITS(mac_hfr0, + MAC_HWF0R_ARPOFFSEL_POS, + MAC_HWF0R_ARPOFFSEL_LEN); + hw_feat->ts = XLGMAC_GET_REG_BITS(mac_hfr0, + MAC_HWF0R_TSSEL_POS, + MAC_HWF0R_TSSEL_LEN); + hw_feat->eee = XLGMAC_GET_REG_BITS(mac_hfr0, + MAC_HWF0R_EEESEL_POS, + MAC_HWF0R_EEESEL_LEN); + hw_feat->tx_coe = XLGMAC_GET_REG_BITS(mac_hfr0, + MAC_HWF0R_TXCOESEL_POS, + MAC_HWF0R_TXCOESEL_LEN); + hw_feat->rx_coe = XLGMAC_GET_REG_BITS(mac_hfr0, + MAC_HWF0R_RXCOESEL_POS, + MAC_HWF0R_RXCOESEL_LEN); + hw_feat->addn_mac = XLGMAC_GET_REG_BITS(mac_hfr0, + MAC_HWF0R_ADDMACADRSEL_POS, + MAC_HWF0R_ADDMACADRSEL_LEN); + hw_feat->ts_src = XLGMAC_GET_REG_BITS(mac_hfr0, + MAC_HWF0R_TSSTSSEL_POS, + MAC_HWF0R_TSSTSSEL_LEN); + hw_feat->sa_vlan_ins = XLGMAC_GET_REG_BITS(mac_hfr0, + MAC_HWF0R_SAVLANINS_POS, + MAC_HWF0R_SAVLANINS_LEN); + + /* Hardware feature register 1 */ + hw_feat->rx_fifo_size = XLGMAC_GET_REG_BITS(mac_hfr1, + MAC_HWF1R_RXFIFOSIZE_POS, + MAC_HWF1R_RXFIFOSIZE_LEN); + hw_feat->tx_fifo_size = XLGMAC_GET_REG_BITS(mac_hfr1, + MAC_HWF1R_TXFIFOSIZE_POS, + MAC_HWF1R_TXFIFOSIZE_LEN); + hw_feat->adv_ts_hi = XLGMAC_GET_REG_BITS(mac_hfr1, + MAC_HWF1R_ADVTHWORD_POS, + MAC_HWF1R_ADVTHWORD_LEN); + hw_feat->dma_width = XLGMAC_GET_REG_BITS(mac_hfr1, + MAC_HWF1R_ADDR64_POS, + MAC_HWF1R_ADDR64_LEN); + hw_feat->dcb = XLGMAC_GET_REG_BITS(mac_hfr1, + MAC_HWF1R_DCBEN_POS, + MAC_HWF1R_DCBEN_LEN); + hw_feat->sph = XLGMAC_GET_REG_BITS(mac_hfr1, + MAC_HWF1R_SPHEN_POS, + MAC_HWF1R_SPHEN_LEN); + hw_feat->tso = XLGMAC_GET_REG_BITS(mac_hfr1, + MAC_HWF1R_TSOEN_POS, + MAC_HWF1R_TSOEN_LEN); + hw_feat->dma_debug = XLGMAC_GET_REG_BITS(mac_hfr1, + MAC_HWF1R_DBGMEMA_POS, + MAC_HWF1R_DBGMEMA_LEN); + hw_feat->rss = XLGMAC_GET_REG_BITS(mac_hfr1, + MAC_HWF1R_RSSEN_POS, + MAC_HWF1R_RSSEN_LEN); + hw_feat->tc_cnt = XLGMAC_GET_REG_BITS(mac_hfr1, + MAC_HWF1R_NUMTC_POS, + MAC_HWF1R_NUMTC_LEN); + hw_feat->hash_table_size = XLGMAC_GET_REG_BITS(mac_hfr1, + MAC_HWF1R_HASHTBLSZ_POS, + MAC_HWF1R_HASHTBLSZ_LEN); + hw_feat->l3l4_filter_num = XLGMAC_GET_REG_BITS(mac_hfr1, + MAC_HWF1R_L3L4FNUM_POS, + MAC_HWF1R_L3L4FNUM_LEN); + + /* Hardware feature register 2 */ + hw_feat->rx_q_cnt = XLGMAC_GET_REG_BITS(mac_hfr2, + MAC_HWF2R_RXQCNT_POS, + MAC_HWF2R_RXQCNT_LEN); + hw_feat->tx_q_cnt = XLGMAC_GET_REG_BITS(mac_hfr2, + MAC_HWF2R_TXQCNT_POS, + MAC_HWF2R_TXQCNT_LEN); + hw_feat->rx_ch_cnt = XLGMAC_GET_REG_BITS(mac_hfr2, + MAC_HWF2R_RXCHCNT_POS, + MAC_HWF2R_RXCHCNT_LEN); + hw_feat->tx_ch_cnt = XLGMAC_GET_REG_BITS(mac_hfr2, + MAC_HWF2R_TXCHCNT_POS, + MAC_HWF2R_TXCHCNT_LEN); + hw_feat->pps_out_num = XLGMAC_GET_REG_BITS(mac_hfr2, + MAC_HWF2R_PPSOUTNUM_POS, + MAC_HWF2R_PPSOUTNUM_LEN); + hw_feat->aux_snap_num = XLGMAC_GET_REG_BITS(mac_hfr2, + MAC_HWF2R_AUXSNAPNUM_POS, + MAC_HWF2R_AUXSNAPNUM_LEN); + + /* Translate the Hash Table size into actual number */ + switch (hw_feat->hash_table_size) { + case 0: + break; + case 1: + hw_feat->hash_table_size = 64; + break; + case 2: + hw_feat->hash_table_size = 128; + break; + case 3: + hw_feat->hash_table_size = 256; + break; + } + + /* Translate the address width setting into actual number */ + switch (hw_feat->dma_width) { + case 0: + hw_feat->dma_width = 32; + break; + case 1: + hw_feat->dma_width = 40; + break; + case 2: + hw_feat->dma_width = 48; + break; + default: + hw_feat->dma_width = 32; + } + + /* The Queue, Channel and TC counts are zero based so increment them + * to get the actual number + */ + hw_feat->rx_q_cnt++; + hw_feat->tx_q_cnt++; + hw_feat->rx_ch_cnt++; + hw_feat->tx_ch_cnt++; + hw_feat->tc_cnt++; +} + +void xlgmac_print_all_hw_features(struct xlgmac_pdata *pdata) +{ + char *str = NULL; + + XLGMAC_PR("\n"); + XLGMAC_PR("=====================================================\n"); + XLGMAC_PR("\n"); + XLGMAC_PR("HW support following features\n"); + XLGMAC_PR("\n"); + /* HW Feature Register0 */ + XLGMAC_PR("VLAN Hash Filter Selected : %s\n", + pdata->hw_feat.vlhash ? "YES" : "NO"); + XLGMAC_PR("SMA (MDIO) Interface : %s\n", + pdata->hw_feat.sma ? "YES" : "NO"); + XLGMAC_PR("PMT Remote Wake-up Packet Enable : %s\n", + pdata->hw_feat.rwk ? "YES" : "NO"); + XLGMAC_PR("PMT Magic Packet Enable : %s\n", + pdata->hw_feat.mgk ? "YES" : "NO"); + XLGMAC_PR("RMON/MMC Module Enable : %s\n", + pdata->hw_feat.mmc ? "YES" : "NO"); + XLGMAC_PR("ARP Offload Enabled : %s\n", + pdata->hw_feat.aoe ? "YES" : "NO"); + XLGMAC_PR("IEEE 1588-2008 Timestamp Enabled : %s\n", + pdata->hw_feat.ts ? "YES" : "NO"); + XLGMAC_PR("Energy Efficient Ethernet Enabled : %s\n", + pdata->hw_feat.eee ? "YES" : "NO"); + XLGMAC_PR("Transmit Checksum Offload Enabled : %s\n", + pdata->hw_feat.tx_coe ? "YES" : "NO"); + XLGMAC_PR("Receive Checksum Offload Enabled : %s\n", + pdata->hw_feat.rx_coe ? "YES" : "NO"); + XLGMAC_PR("Additional MAC Addresses 1-31 Selected : %s\n", + pdata->hw_feat.addn_mac ? "YES" : "NO"); + + switch (pdata->hw_feat.ts_src) { + case 0: + str = "RESERVED"; + break; + case 1: + str = "INTERNAL"; + break; + case 2: + str = "EXTERNAL"; + break; + case 3: + str = "BOTH"; + break; + } + XLGMAC_PR("Timestamp System Time Source : %s\n", str); + + XLGMAC_PR("Source Address or VLAN Insertion Enable : %s\n", + pdata->hw_feat.sa_vlan_ins ? "YES" : "NO"); + + /* HW Feature Register1 */ + switch (pdata->hw_feat.rx_fifo_size) { + case 0: + str = "128 bytes"; + break; + case 1: + str = "256 bytes"; + break; + case 2: + str = "512 bytes"; + break; + case 3: + str = "1 KBytes"; + break; + case 4: + str = "2 KBytes"; + break; + case 5: + str = "4 KBytes"; + break; + case 6: + str = "8 KBytes"; + break; + case 7: + str = "16 KBytes"; + break; + case 8: + str = "32 kBytes"; + break; + case 9: + str = "64 KBytes"; + break; + case 10: + str = "128 KBytes"; + break; + case 11: + str = "256 KBytes"; + break; + default: + str = "RESERVED"; + } + XLGMAC_PR("MTL Receive FIFO Size : %s\n", str); + + switch (pdata->hw_feat.tx_fifo_size) { + case 0: + str = "128 bytes"; + break; + case 1: + str = "256 bytes"; + break; + case 2: + str = "512 bytes"; + break; + case 3: + str = "1 KBytes"; + break; + case 4: + str = "2 KBytes"; + break; + case 5: + str = "4 KBytes"; + break; + case 6: + str = "8 KBytes"; + break; + case 7: + str = "16 KBytes"; + break; + case 8: + str = "32 kBytes"; + break; + case 9: + str = "64 KBytes"; + break; + case 10: + str = "128 KBytes"; + break; + case 11: + str = "256 KBytes"; + break; + default: + str = "RESERVED"; + } + XLGMAC_PR("MTL Transmit FIFO Size : %s\n", str); + + XLGMAC_PR("IEEE 1588 High Word Register Enable : %s\n", + pdata->hw_feat.adv_ts_hi ? "YES" : "NO"); + XLGMAC_PR("Address width : %u\n", + pdata->hw_feat.dma_width); + XLGMAC_PR("DCB Feature Enable : %s\n", + pdata->hw_feat.dcb ? "YES" : "NO"); + XLGMAC_PR("Split Header Feature Enable : %s\n", + pdata->hw_feat.sph ? "YES" : "NO"); + XLGMAC_PR("TCP Segmentation Offload Enable : %s\n", + pdata->hw_feat.tso ? "YES" : "NO"); + XLGMAC_PR("DMA Debug Registers Enabled : %s\n", + pdata->hw_feat.dma_debug ? "YES" : "NO"); + XLGMAC_PR("RSS Feature Enabled : %s\n", + pdata->hw_feat.rss ? "YES" : "NO"); + XLGMAC_PR("Number of Traffic classes : %u\n", + (pdata->hw_feat.tc_cnt)); + XLGMAC_PR("Hash Table Size : %u\n", + pdata->hw_feat.hash_table_size); + XLGMAC_PR("Total number of L3 or L4 Filters : %u\n", + pdata->hw_feat.l3l4_filter_num); + + /* HW Feature Register2 */ + XLGMAC_PR("Number of MTL Receive Queues : %u\n", + pdata->hw_feat.rx_q_cnt); + XLGMAC_PR("Number of MTL Transmit Queues : %u\n", + pdata->hw_feat.tx_q_cnt); + XLGMAC_PR("Number of DMA Receive Channels : %u\n", + pdata->hw_feat.rx_ch_cnt); + XLGMAC_PR("Number of DMA Transmit Channels : %u\n", + pdata->hw_feat.tx_ch_cnt); + + switch (pdata->hw_feat.pps_out_num) { + case 0: + str = "No PPS output"; + break; + case 1: + str = "1 PPS output"; + break; + case 2: + str = "2 PPS output"; + break; + case 3: + str = "3 PPS output"; + break; + case 4: + str = "4 PPS output"; + break; + default: + str = "RESERVED"; + } + XLGMAC_PR("Number of PPS Outputs : %s\n", str); + + switch (pdata->hw_feat.aux_snap_num) { + case 0: + str = "No auxiliary input"; + break; + case 1: + str = "1 auxiliary input"; + break; + case 2: + str = "2 auxiliary input"; + break; + case 3: + str = "3 auxiliary input"; + break; + case 4: + str = "4 auxiliary input"; + break; + default: + str = "RESERVED"; + } + XLGMAC_PR("Number of Auxiliary Snapshot Inputs : %s", str); + + XLGMAC_PR("\n"); + XLGMAC_PR("=====================================================\n"); + XLGMAC_PR("\n"); +} diff --git a/drivers/net/ethernet/synopsys/dwc-xlgmac-desc.c b/drivers/net/ethernet/synopsys/dwc-xlgmac-desc.c new file mode 100644 index 000000000000..55c796ed7d26 --- /dev/null +++ b/drivers/net/ethernet/synopsys/dwc-xlgmac-desc.c @@ -0,0 +1,648 @@ +/* Synopsys DesignWare Core Enterprise Ethernet (XLGMAC) Driver + * + * Copyright (c) 2017 Synopsys, Inc. (www.synopsys.com) + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the + * Free Software Foundation; either version 2 of the License, or (at your + * option) any later version. + * + * This Synopsys DWC XLGMAC software driver and associated documentation + * (hereinafter the "Software") is an unsupported proprietary work of + * Synopsys, Inc. unless otherwise expressly agreed to in writing between + * Synopsys and you. The Software IS NOT an item of Licensed Software or a + * Licensed Product under any End User Software License Agreement or + * Agreement for Licensed Products with Synopsys or any supplement thereto. + * Synopsys is a registered trademark of Synopsys, Inc. Other names included + * in the SOFTWARE may be the trademarks of their respective owners. + */ + +#include "dwc-xlgmac.h" +#include "dwc-xlgmac-reg.h" + +static void xlgmac_unmap_desc_data(struct xlgmac_pdata *pdata, + struct xlgmac_desc_data *desc_data) +{ + if (desc_data->skb_dma) { + if (desc_data->mapped_as_page) { + dma_unmap_page(pdata->dev, desc_data->skb_dma, + desc_data->skb_dma_len, DMA_TO_DEVICE); + } else { + dma_unmap_single(pdata->dev, desc_data->skb_dma, + desc_data->skb_dma_len, DMA_TO_DEVICE); + } + desc_data->skb_dma = 0; + desc_data->skb_dma_len = 0; + } + + if (desc_data->skb) { + dev_kfree_skb_any(desc_data->skb); + desc_data->skb = NULL; + } + + if (desc_data->rx.hdr.pa.pages) + put_page(desc_data->rx.hdr.pa.pages); + + if (desc_data->rx.hdr.pa_unmap.pages) { + dma_unmap_page(pdata->dev, desc_data->rx.hdr.pa_unmap.pages_dma, + desc_data->rx.hdr.pa_unmap.pages_len, + DMA_FROM_DEVICE); + put_page(desc_data->rx.hdr.pa_unmap.pages); + } + + if (desc_data->rx.buf.pa.pages) + put_page(desc_data->rx.buf.pa.pages); + + if (desc_data->rx.buf.pa_unmap.pages) { + dma_unmap_page(pdata->dev, desc_data->rx.buf.pa_unmap.pages_dma, + desc_data->rx.buf.pa_unmap.pages_len, + DMA_FROM_DEVICE); + put_page(desc_data->rx.buf.pa_unmap.pages); + } + + memset(&desc_data->tx, 0, sizeof(desc_data->tx)); + memset(&desc_data->rx, 0, sizeof(desc_data->rx)); + + desc_data->mapped_as_page = 0; + + if (desc_data->state_saved) { + desc_data->state_saved = 0; + desc_data->state.skb = NULL; + desc_data->state.len = 0; + desc_data->state.error = 0; + } +} + +static void xlgmac_free_ring(struct xlgmac_pdata *pdata, + struct xlgmac_ring *ring) +{ + struct xlgmac_desc_data *desc_data; + unsigned int i; + + if (!ring) + return; + + if (ring->desc_data_head) { + for (i = 0; i < ring->dma_desc_count; i++) { + desc_data = XLGMAC_GET_DESC_DATA(ring, i); + xlgmac_unmap_desc_data(pdata, desc_data); + } + + kfree(ring->desc_data_head); + ring->desc_data_head = NULL; + } + + if (ring->rx_hdr_pa.pages) { + dma_unmap_page(pdata->dev, ring->rx_hdr_pa.pages_dma, + ring->rx_hdr_pa.pages_len, DMA_FROM_DEVICE); + put_page(ring->rx_hdr_pa.pages); + + ring->rx_hdr_pa.pages = NULL; + ring->rx_hdr_pa.pages_len = 0; + ring->rx_hdr_pa.pages_offset = 0; + ring->rx_hdr_pa.pages_dma = 0; + } + + if (ring->rx_buf_pa.pages) { + dma_unmap_page(pdata->dev, ring->rx_buf_pa.pages_dma, + ring->rx_buf_pa.pages_len, DMA_FROM_DEVICE); + put_page(ring->rx_buf_pa.pages); + + ring->rx_buf_pa.pages = NULL; + ring->rx_buf_pa.pages_len = 0; + ring->rx_buf_pa.pages_offset = 0; + ring->rx_buf_pa.pages_dma = 0; + } + + if (ring->dma_desc_head) { + dma_free_coherent(pdata->dev, + (sizeof(struct xlgmac_dma_desc) * + ring->dma_desc_count), + ring->dma_desc_head, + ring->dma_desc_head_addr); + ring->dma_desc_head = NULL; + } +} + +static int xlgmac_init_ring(struct xlgmac_pdata *pdata, + struct xlgmac_ring *ring, + unsigned int dma_desc_count) +{ + if (!ring) + return 0; + + /* Descriptors */ + ring->dma_desc_count = dma_desc_count; + ring->dma_desc_head = dma_alloc_coherent(pdata->dev, + (sizeof(struct xlgmac_dma_desc) * + dma_desc_count), + &ring->dma_desc_head_addr, + GFP_KERNEL); + if (!ring->dma_desc_head) + return -ENOMEM; + + /* Array of descriptor data */ + ring->desc_data_head = kcalloc(dma_desc_count, + sizeof(struct xlgmac_desc_data), + GFP_KERNEL); + if (!ring->desc_data_head) + return -ENOMEM; + + netif_dbg(pdata, drv, pdata->netdev, + "dma_desc_head=%p, dma_desc_head_addr=%pad, desc_data_head=%p\n", + ring->dma_desc_head, + &ring->dma_desc_head_addr, + ring->desc_data_head); + + return 0; +} + +static void xlgmac_free_rings(struct xlgmac_pdata *pdata) +{ + struct xlgmac_channel *channel; + unsigned int i; + + if (!pdata->channel_head) + return; + + channel = pdata->channel_head; + for (i = 0; i < pdata->channel_count; i++, channel++) { + xlgmac_free_ring(pdata, channel->tx_ring); + xlgmac_free_ring(pdata, channel->rx_ring); + } +} + +static int xlgmac_alloc_rings(struct xlgmac_pdata *pdata) +{ + struct xlgmac_channel *channel; + unsigned int i; + int ret; + + channel = pdata->channel_head; + for (i = 0; i < pdata->channel_count; i++, channel++) { + netif_dbg(pdata, drv, pdata->netdev, "%s - Tx ring:\n", + channel->name); + + ret = xlgmac_init_ring(pdata, channel->tx_ring, + pdata->tx_desc_count); + + if (ret) { + netdev_alert(pdata->netdev, + "error initializing Tx ring"); + goto err_init_ring; + } + + netif_dbg(pdata, drv, pdata->netdev, "%s - Rx ring:\n", + channel->name); + + ret = xlgmac_init_ring(pdata, channel->rx_ring, + pdata->rx_desc_count); + if (ret) { + netdev_alert(pdata->netdev, + "error initializing Rx ring\n"); + goto err_init_ring; + } + } + + return 0; + +err_init_ring: + xlgmac_free_rings(pdata); + + return ret; +} + +static void xlgmac_free_channels(struct xlgmac_pdata *pdata) +{ + if (!pdata->channel_head) + return; + + kfree(pdata->channel_head->tx_ring); + pdata->channel_head->tx_ring = NULL; + + kfree(pdata->channel_head->rx_ring); + pdata->channel_head->rx_ring = NULL; + + kfree(pdata->channel_head); + + pdata->channel_head = NULL; + pdata->channel_count = 0; +} + +static int xlgmac_alloc_channels(struct xlgmac_pdata *pdata) +{ + struct xlgmac_channel *channel_head, *channel; + struct xlgmac_ring *tx_ring, *rx_ring; + int ret = -ENOMEM; + unsigned int i; + + channel_head = kcalloc(pdata->channel_count, + sizeof(struct xlgmac_channel), GFP_KERNEL); + if (!channel_head) + return ret; + + netif_dbg(pdata, drv, pdata->netdev, + "channel_head=%p\n", channel_head); + + tx_ring = kcalloc(pdata->tx_ring_count, sizeof(struct xlgmac_ring), + GFP_KERNEL); + if (!tx_ring) + goto err_tx_ring; + + rx_ring = kcalloc(pdata->rx_ring_count, sizeof(struct xlgmac_ring), + GFP_KERNEL); + if (!rx_ring) + goto err_rx_ring; + + for (i = 0, channel = channel_head; i < pdata->channel_count; + i++, channel++) { + snprintf(channel->name, sizeof(channel->name), "channel-%u", i); + channel->pdata = pdata; + channel->queue_index = i; + channel->dma_regs = pdata->mac_regs + DMA_CH_BASE + + (DMA_CH_INC * i); + + if (pdata->per_channel_irq) { + /* Get the per DMA interrupt */ + ret = pdata->channel_irq[i]; + if (ret < 0) { + netdev_err(pdata->netdev, + "get_irq %u failed\n", + i + 1); + goto err_irq; + } + channel->dma_irq = ret; + } + + if (i < pdata->tx_ring_count) + channel->tx_ring = tx_ring++; + + if (i < pdata->rx_ring_count) + channel->rx_ring = rx_ring++; + + netif_dbg(pdata, drv, pdata->netdev, + "%s: dma_regs=%p, tx_ring=%p, rx_ring=%p\n", + channel->name, channel->dma_regs, + channel->tx_ring, channel->rx_ring); + } + + pdata->channel_head = channel_head; + + return 0; + +err_irq: + kfree(rx_ring); + +err_rx_ring: + kfree(tx_ring); + +err_tx_ring: + kfree(channel_head); + + return ret; +} + +static void xlgmac_free_channels_and_rings(struct xlgmac_pdata *pdata) +{ + xlgmac_free_rings(pdata); + + xlgmac_free_channels(pdata); +} + +static int xlgmac_alloc_channels_and_rings(struct xlgmac_pdata *pdata) +{ + int ret; + + ret = xlgmac_alloc_channels(pdata); + if (ret) + goto err_alloc; + + ret = xlgmac_alloc_rings(pdata); + if (ret) + goto err_alloc; + + return 0; + +err_alloc: + xlgmac_free_channels_and_rings(pdata); + + return ret; +} + +static int xlgmac_alloc_pages(struct xlgmac_pdata *pdata, + struct xlgmac_page_alloc *pa, + gfp_t gfp, int order) +{ + struct page *pages = NULL; + dma_addr_t pages_dma; + int ret; + + /* Try to obtain pages, decreasing order if necessary */ + gfp |= __GFP_COLD | __GFP_COMP | __GFP_NOWARN; + while (order >= 0) { + pages = alloc_pages(gfp, order); + if (pages) + break; + + order--; + } + if (!pages) + return -ENOMEM; + + /* Map the pages */ + pages_dma = dma_map_page(pdata->dev, pages, 0, + PAGE_SIZE << order, DMA_FROM_DEVICE); + ret = dma_mapping_error(pdata->dev, pages_dma); + if (ret) { + put_page(pages); + return ret; + } + + pa->pages = pages; + pa->pages_len = PAGE_SIZE << order; + pa->pages_offset = 0; + pa->pages_dma = pages_dma; + + return 0; +} + +static void xlgmac_set_buffer_data(struct xlgmac_buffer_data *bd, + struct xlgmac_page_alloc *pa, + unsigned int len) +{ + get_page(pa->pages); + bd->pa = *pa; + + bd->dma_base = pa->pages_dma; + bd->dma_off = pa->pages_offset; + bd->dma_len = len; + + pa->pages_offset += len; + if ((pa->pages_offset + len) > pa->pages_len) { + /* This data descriptor is responsible for unmapping page(s) */ + bd->pa_unmap = *pa; + + /* Get a new allocation next time */ + pa->pages = NULL; + pa->pages_len = 0; + pa->pages_offset = 0; + pa->pages_dma = 0; + } +} + +static int xlgmac_map_rx_buffer(struct xlgmac_pdata *pdata, + struct xlgmac_ring *ring, + struct xlgmac_desc_data *desc_data) +{ + int order, ret; + + if (!ring->rx_hdr_pa.pages) { + ret = xlgmac_alloc_pages(pdata, &ring->rx_hdr_pa, + GFP_ATOMIC, 0); + if (ret) + return ret; + } + + if (!ring->rx_buf_pa.pages) { + order = max_t(int, PAGE_ALLOC_COSTLY_ORDER - 1, 0); + ret = xlgmac_alloc_pages(pdata, &ring->rx_buf_pa, + GFP_ATOMIC, order); + if (ret) + return ret; + } + + /* Set up the header page info */ + xlgmac_set_buffer_data(&desc_data->rx.hdr, &ring->rx_hdr_pa, + XLGMAC_SKB_ALLOC_SIZE); + + /* Set up the buffer page info */ + xlgmac_set_buffer_data(&desc_data->rx.buf, &ring->rx_buf_pa, + pdata->rx_buf_size); + + return 0; +} + +static void xlgmac_tx_desc_init(struct xlgmac_pdata *pdata) +{ + struct xlgmac_hw_ops *hw_ops = &pdata->hw_ops; + struct xlgmac_desc_data *desc_data; + struct xlgmac_dma_desc *dma_desc; + struct xlgmac_channel *channel; + struct xlgmac_ring *ring; + dma_addr_t dma_desc_addr; + unsigned int i, j; + + channel = pdata->channel_head; + for (i = 0; i < pdata->channel_count; i++, channel++) { + ring = channel->tx_ring; + if (!ring) + break; + + dma_desc = ring->dma_desc_head; + dma_desc_addr = ring->dma_desc_head_addr; + + for (j = 0; j < ring->dma_desc_count; j++) { + desc_data = XLGMAC_GET_DESC_DATA(ring, j); + + desc_data->dma_desc = dma_desc; + desc_data->dma_desc_addr = dma_desc_addr; + + dma_desc++; + dma_desc_addr += sizeof(struct xlgmac_dma_desc); + } + + ring->cur = 0; + ring->dirty = 0; + memset(&ring->tx, 0, sizeof(ring->tx)); + + hw_ops->tx_desc_init(channel); + } +} + +static void xlgmac_rx_desc_init(struct xlgmac_pdata *pdata) +{ + struct xlgmac_hw_ops *hw_ops = &pdata->hw_ops; + struct xlgmac_desc_data *desc_data; + struct xlgmac_dma_desc *dma_desc; + struct xlgmac_channel *channel; + struct xlgmac_ring *ring; + dma_addr_t dma_desc_addr; + unsigned int i, j; + + channel = pdata->channel_head; + for (i = 0; i < pdata->channel_count; i++, channel++) { + ring = channel->rx_ring; + if (!ring) + break; + + dma_desc = ring->dma_desc_head; + dma_desc_addr = ring->dma_desc_head_addr; + + for (j = 0; j < ring->dma_desc_count; j++) { + desc_data = XLGMAC_GET_DESC_DATA(ring, j); + + desc_data->dma_desc = dma_desc; + desc_data->dma_desc_addr = dma_desc_addr; + + if (xlgmac_map_rx_buffer(pdata, ring, desc_data)) + break; + + dma_desc++; + dma_desc_addr += sizeof(struct xlgmac_dma_desc); + } + + ring->cur = 0; + ring->dirty = 0; + + hw_ops->rx_desc_init(channel); + } +} + +static int xlgmac_map_tx_skb(struct xlgmac_channel *channel, + struct sk_buff *skb) +{ + struct xlgmac_pdata *pdata = channel->pdata; + struct xlgmac_ring *ring = channel->tx_ring; + unsigned int start_index, cur_index; + struct xlgmac_desc_data *desc_data; + unsigned int offset, datalen, len; + struct xlgmac_pkt_info *pkt_info; + struct skb_frag_struct *frag; + unsigned int tso, vlan; + dma_addr_t skb_dma; + unsigned int i; + + offset = 0; + start_index = ring->cur; + cur_index = ring->cur; + + pkt_info = &ring->pkt_info; + pkt_info->desc_count = 0; + pkt_info->length = 0; + + tso = XLGMAC_GET_REG_BITS(pkt_info->attributes, + TX_PACKET_ATTRIBUTES_TSO_ENABLE_POS, + TX_PACKET_ATTRIBUTES_TSO_ENABLE_LEN); + vlan = XLGMAC_GET_REG_BITS(pkt_info->attributes, + TX_PACKET_ATTRIBUTES_VLAN_CTAG_POS, + TX_PACKET_ATTRIBUTES_VLAN_CTAG_LEN); + + /* Save space for a context descriptor if needed */ + if ((tso && (pkt_info->mss != ring->tx.cur_mss)) || + (vlan && (pkt_info->vlan_ctag != ring->tx.cur_vlan_ctag))) + cur_index++; + desc_data = XLGMAC_GET_DESC_DATA(ring, cur_index); + + if (tso) { + /* Map the TSO header */ + skb_dma = dma_map_single(pdata->dev, skb->data, + pkt_info->header_len, DMA_TO_DEVICE); + if (dma_mapping_error(pdata->dev, skb_dma)) { + netdev_alert(pdata->netdev, "dma_map_single failed\n"); + goto err_out; + } + desc_data->skb_dma = skb_dma; + desc_data->skb_dma_len = pkt_info->header_len; + netif_dbg(pdata, tx_queued, pdata->netdev, + "skb header: index=%u, dma=%pad, len=%u\n", + cur_index, &skb_dma, pkt_info->header_len); + + offset = pkt_info->header_len; + + pkt_info->length += pkt_info->header_len; + + cur_index++; + desc_data = XLGMAC_GET_DESC_DATA(ring, cur_index); + } + + /* Map the (remainder of the) packet */ + for (datalen = skb_headlen(skb) - offset; datalen; ) { + len = min_t(unsigned int, datalen, XLGMAC_TX_MAX_BUF_SIZE); + + skb_dma = dma_map_single(pdata->dev, skb->data + offset, len, + DMA_TO_DEVICE); + if (dma_mapping_error(pdata->dev, skb_dma)) { + netdev_alert(pdata->netdev, "dma_map_single failed\n"); + goto err_out; + } + desc_data->skb_dma = skb_dma; + desc_data->skb_dma_len = len; + netif_dbg(pdata, tx_queued, pdata->netdev, + "skb data: index=%u, dma=%pad, len=%u\n", + cur_index, &skb_dma, len); + + datalen -= len; + offset += len; + + pkt_info->length += len; + + cur_index++; + desc_data = XLGMAC_GET_DESC_DATA(ring, cur_index); + } + + for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { + netif_dbg(pdata, tx_queued, pdata->netdev, + "mapping frag %u\n", i); + + frag = &skb_shinfo(skb)->frags[i]; + offset = 0; + + for (datalen = skb_frag_size(frag); datalen; ) { + len = min_t(unsigned int, datalen, + XLGMAC_TX_MAX_BUF_SIZE); + + skb_dma = skb_frag_dma_map(pdata->dev, frag, offset, + len, DMA_TO_DEVICE); + if (dma_mapping_error(pdata->dev, skb_dma)) { + netdev_alert(pdata->netdev, + "skb_frag_dma_map failed\n"); + goto err_out; + } + desc_data->skb_dma = skb_dma; + desc_data->skb_dma_len = len; + desc_data->mapped_as_page = 1; + netif_dbg(pdata, tx_queued, pdata->netdev, + "skb frag: index=%u, dma=%pad, len=%u\n", + cur_index, &skb_dma, len); + + datalen -= len; + offset += len; + + pkt_info->length += len; + + cur_index++; + desc_data = XLGMAC_GET_DESC_DATA(ring, cur_index); + } + } + + /* Save the skb address in the last entry. We always have some data + * that has been mapped so desc_data is always advanced past the last + * piece of mapped data - use the entry pointed to by cur_index - 1. + */ + desc_data = XLGMAC_GET_DESC_DATA(ring, cur_index - 1); + desc_data->skb = skb; + + /* Save the number of descriptor entries used */ + pkt_info->desc_count = cur_index - start_index; + + return pkt_info->desc_count; + +err_out: + while (start_index < cur_index) { + desc_data = XLGMAC_GET_DESC_DATA(ring, start_index++); + xlgmac_unmap_desc_data(pdata, desc_data); + } + + return 0; +} + +void xlgmac_init_desc_ops(struct xlgmac_desc_ops *desc_ops) +{ + desc_ops->alloc_channles_and_rings = xlgmac_alloc_channels_and_rings; + desc_ops->free_channels_and_rings = xlgmac_free_channels_and_rings; + desc_ops->map_tx_skb = xlgmac_map_tx_skb; + desc_ops->map_rx_buffer = xlgmac_map_rx_buffer; + desc_ops->unmap_desc_data = xlgmac_unmap_desc_data; + desc_ops->tx_desc_init = xlgmac_tx_desc_init; + desc_ops->rx_desc_init = xlgmac_rx_desc_init; +} diff --git a/drivers/net/ethernet/synopsys/dwc-xlgmac-hw.c b/drivers/net/ethernet/synopsys/dwc-xlgmac-hw.c new file mode 100644 index 000000000000..5cf3e90d4834 --- /dev/null +++ b/drivers/net/ethernet/synopsys/dwc-xlgmac-hw.c @@ -0,0 +1,3146 @@ +/* Synopsys DesignWare Core Enterprise Ethernet (XLGMAC) Driver + * + * Copyright (c) 2017 Synopsys, Inc. (www.synopsys.com) + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the + * Free Software Foundation; either version 2 of the License, or (at your + * option) any later version. + * + * This Synopsys DWC XLGMAC software driver and associated documentation + * (hereinafter the "Software") is an unsupported proprietary work of + * Synopsys, Inc. unless otherwise expressly agreed to in writing between + * Synopsys and you. The Software IS NOT an item of Licensed Software or a + * Licensed Product under any End User Software License Agreement or + * Agreement for Licensed Products with Synopsys or any supplement thereto. + * Synopsys is a registered trademark of Synopsys, Inc. Other names included + * in the SOFTWARE may be the trademarks of their respective owners. + */ + +#include <linux/phy.h> +#include <linux/mdio.h> +#include <linux/clk.h> +#include <linux/bitrev.h> +#include <linux/crc32.h> + +#include "dwc-xlgmac.h" +#include "dwc-xlgmac-reg.h" + +static int xlgmac_tx_complete(struct xlgmac_dma_desc *dma_desc) +{ + return !XLGMAC_GET_REG_BITS_LE(dma_desc->desc3, + TX_NORMAL_DESC3_OWN_POS, + TX_NORMAL_DESC3_OWN_LEN); +} + +static int xlgmac_disable_rx_csum(struct xlgmac_pdata *pdata) +{ + u32 regval; + + regval = readl(pdata->mac_regs + MAC_RCR); + regval = XLGMAC_SET_REG_BITS(regval, MAC_RCR_IPC_POS, + MAC_RCR_IPC_LEN, 0); + writel(regval, pdata->mac_regs + MAC_RCR); + + return 0; +} + +static int xlgmac_enable_rx_csum(struct xlgmac_pdata *pdata) +{ + u32 regval; + + regval = readl(pdata->mac_regs + MAC_RCR); + regval = XLGMAC_SET_REG_BITS(regval, MAC_RCR_IPC_POS, + MAC_RCR_IPC_LEN, 1); + writel(regval, pdata->mac_regs + MAC_RCR); + + return 0; +} + +static int xlgmac_set_mac_address(struct xlgmac_pdata *pdata, u8 *addr) +{ + unsigned int mac_addr_hi, mac_addr_lo; + + mac_addr_hi = (addr[5] << 8) | (addr[4] << 0); + mac_addr_lo = (addr[3] << 24) | (addr[2] << 16) | + (addr[1] << 8) | (addr[0] << 0); + + writel(mac_addr_hi, pdata->mac_regs + MAC_MACA0HR); + writel(mac_addr_lo, pdata->mac_regs + MAC_MACA0LR); + + return 0; +} + +static void xlgmac_set_mac_reg(struct xlgmac_pdata *pdata, + struct netdev_hw_addr *ha, + unsigned int *mac_reg) +{ + unsigned int mac_addr_hi, mac_addr_lo; + u8 *mac_addr; + + mac_addr_lo = 0; + mac_addr_hi = 0; + + if (ha) { + mac_addr = (u8 *)&mac_addr_lo; + mac_addr[0] = ha->addr[0]; + mac_addr[1] = ha->addr[1]; + mac_addr[2] = ha->addr[2]; + mac_addr[3] = ha->addr[3]; + mac_addr = (u8 *)&mac_addr_hi; + mac_addr[0] = ha->addr[4]; + mac_addr[1] = ha->addr[5]; + + netif_dbg(pdata, drv, pdata->netdev, + "adding mac address %pM at %#x\n", + ha->addr, *mac_reg); + + mac_addr_hi = XLGMAC_SET_REG_BITS(mac_addr_hi, + MAC_MACA1HR_AE_POS, + MAC_MACA1HR_AE_LEN, + 1); + } + + writel(mac_addr_hi, pdata->mac_regs + *mac_reg); + *mac_reg += MAC_MACA_INC; + writel(mac_addr_lo, pdata->mac_regs + *mac_reg); + *mac_reg += MAC_MACA_INC; +} + +static int xlgmac_enable_rx_vlan_stripping(struct xlgmac_pdata *pdata) +{ + u32 regval; + + regval = readl(pdata->mac_regs + MAC_VLANTR); + /* Put the VLAN tag in the Rx descriptor */ + regval = XLGMAC_SET_REG_BITS(regval, MAC_VLANTR_EVLRXS_POS, + MAC_VLANTR_EVLRXS_LEN, 1); + /* Don't check the VLAN type */ + regval = XLGMAC_SET_REG_BITS(regval, MAC_VLANTR_DOVLTC_POS, + MAC_VLANTR_DOVLTC_LEN, 1); + /* Check only C-TAG (0x8100) packets */ + regval = XLGMAC_SET_REG_BITS(regval, MAC_VLANTR_ERSVLM_POS, + MAC_VLANTR_ERSVLM_LEN, 0); + /* Don't consider an S-TAG (0x88A8) packet as a VLAN packet */ + regval = XLGMAC_SET_REG_BITS(regval, MAC_VLANTR_ESVL_POS, + MAC_VLANTR_ESVL_LEN, 0); + /* Enable VLAN tag stripping */ + regval = XLGMAC_SET_REG_BITS(regval, MAC_VLANTR_EVLS_POS, + MAC_VLANTR_EVLS_LEN, 0x3); + writel(regval, pdata->mac_regs + MAC_VLANTR); + + return 0; +} + +static int xlgmac_disable_rx_vlan_stripping(struct xlgmac_pdata *pdata) +{ + u32 regval; + + regval = readl(pdata->mac_regs + MAC_VLANTR); + regval = XLGMAC_SET_REG_BITS(regval, MAC_VLANTR_EVLS_POS, + MAC_VLANTR_EVLS_LEN, 0); + writel(regval, pdata->mac_regs + MAC_VLANTR); + + return 0; +} + +static int xlgmac_enable_rx_vlan_filtering(struct xlgmac_pdata *pdata) +{ + u32 regval; + + regval = readl(pdata->mac_regs + MAC_PFR); + /* Enable VLAN filtering */ + regval = XLGMAC_SET_REG_BITS(regval, MAC_PFR_VTFE_POS, + MAC_PFR_VTFE_LEN, 1); + writel(regval, pdata->mac_regs + MAC_PFR); + + regval = readl(pdata->mac_regs + MAC_VLANTR); + /* Enable VLAN Hash Table filtering */ + regval = XLGMAC_SET_REG_BITS(regval, MAC_VLANTR_VTHM_POS, + MAC_VLANTR_VTHM_LEN, 1); + /* Disable VLAN tag inverse matching */ + regval = XLGMAC_SET_REG_BITS(regval, MAC_VLANTR_VTIM_POS, + MAC_VLANTR_VTIM_LEN, 0); + /* Only filter on the lower 12-bits of the VLAN tag */ + regval = XLGMAC_SET_REG_BITS(regval, MAC_VLANTR_ETV_POS, + MAC_VLANTR_ETV_LEN, 1); + /* In order for the VLAN Hash Table filtering to be effective, + * the VLAN tag identifier in the VLAN Tag Register must not + * be zero. Set the VLAN tag identifier to "1" to enable the + * VLAN Hash Table filtering. This implies that a VLAN tag of + * 1 will always pass filtering. + */ + regval = XLGMAC_SET_REG_BITS(regval, MAC_VLANTR_VL_POS, + MAC_VLANTR_VL_LEN, 1); + writel(regval, pdata->mac_regs + MAC_VLANTR); + + return 0; +} + +static int xlgmac_disable_rx_vlan_filtering(struct xlgmac_pdata *pdata) +{ + u32 regval; + + regval = readl(pdata->mac_regs + MAC_PFR); + /* Disable VLAN filtering */ + regval = XLGMAC_SET_REG_BITS(regval, MAC_PFR_VTFE_POS, + MAC_PFR_VTFE_LEN, 0); + writel(regval, pdata->mac_regs + MAC_PFR); + + return 0; +} + +static u32 xlgmac_vid_crc32_le(__le16 vid_le) +{ + unsigned char *data = (unsigned char *)&vid_le; + unsigned char data_byte = 0; + u32 poly = 0xedb88320; + u32 crc = ~0; + u32 temp = 0; + int i, bits; + + bits = get_bitmask_order(VLAN_VID_MASK); + for (i = 0; i < bits; i++) { + if ((i % 8) == 0) + data_byte = data[i / 8]; + + temp = ((crc & 1) ^ data_byte) & 1; + crc >>= 1; + data_byte >>= 1; + + if (temp) + crc ^= poly; + } + + return crc; +} + +static int xlgmac_update_vlan_hash_table(struct xlgmac_pdata *pdata) +{ + u16 vlan_hash_table = 0; + __le16 vid_le; + u32 regval; + u32 crc; + u16 vid; + + /* Generate the VLAN Hash Table value */ + for_each_set_bit(vid, pdata->active_vlans, VLAN_N_VID) { + /* Get the CRC32 value of the VLAN ID */ + vid_le = cpu_to_le16(vid); + crc = bitrev32(~xlgmac_vid_crc32_le(vid_le)) >> 28; + + vlan_hash_table |= (1 << crc); + } + + regval = readl(pdata->mac_regs + MAC_VLANHTR); + /* Set the VLAN Hash Table filtering register */ + regval = XLGMAC_SET_REG_BITS(regval, MAC_VLANHTR_VLHT_POS, + MAC_VLANHTR_VLHT_LEN, vlan_hash_table); + writel(regval, pdata->mac_regs + MAC_VLANHTR); + + return 0; +} + +static int xlgmac_set_promiscuous_mode(struct xlgmac_pdata *pdata, + unsigned int enable) +{ + unsigned int val = enable ? 1 : 0; + u32 regval; + + regval = XLGMAC_GET_REG_BITS(readl(pdata->mac_regs + MAC_PFR), + MAC_PFR_PR_POS, MAC_PFR_PR_LEN); + if (regval == val) + return 0; + + netif_dbg(pdata, drv, pdata->netdev, "%s promiscuous mode\n", + enable ? "entering" : "leaving"); + + regval = readl(pdata->mac_regs + MAC_PFR); + regval = XLGMAC_SET_REG_BITS(regval, MAC_PFR_PR_POS, + MAC_PFR_PR_LEN, val); + writel(regval, pdata->mac_regs + MAC_PFR); + + /* Hardware will still perform VLAN filtering in promiscuous mode */ + if (enable) { + xlgmac_disable_rx_vlan_filtering(pdata); + } else { + if (pdata->netdev->features & NETIF_F_HW_VLAN_CTAG_FILTER) + xlgmac_enable_rx_vlan_filtering(pdata); + } + + return 0; +} + +static int xlgmac_set_all_multicast_mode(struct xlgmac_pdata *pdata, + unsigned int enable) +{ + unsigned int val = enable ? 1 : 0; + u32 regval; + + regval = XLGMAC_GET_REG_BITS(readl(pdata->mac_regs + MAC_PFR), + MAC_PFR_PM_POS, MAC_PFR_PM_LEN); + if (regval == val) + return 0; + + netif_dbg(pdata, drv, pdata->netdev, "%s allmulti mode\n", + enable ? "entering" : "leaving"); + + regval = readl(pdata->mac_regs + MAC_PFR); + regval = XLGMAC_SET_REG_BITS(regval, MAC_PFR_PM_POS, + MAC_PFR_PM_LEN, val); + writel(regval, pdata->mac_regs + MAC_PFR); + + return 0; +} + +static void xlgmac_set_mac_addn_addrs(struct xlgmac_pdata *pdata) +{ + struct net_device *netdev = pdata->netdev; + struct netdev_hw_addr *ha; + unsigned int addn_macs; + unsigned int mac_reg; + + mac_reg = MAC_MACA1HR; + addn_macs = pdata->hw_feat.addn_mac; + + if (netdev_uc_count(netdev) > addn_macs) { + xlgmac_set_promiscuous_mode(pdata, 1); + } else { + netdev_for_each_uc_addr(ha, netdev) { + xlgmac_set_mac_reg(pdata, ha, &mac_reg); + addn_macs--; + } + + if (netdev_mc_count(netdev) > addn_macs) { + xlgmac_set_all_multicast_mode(pdata, 1); + } else { + netdev_for_each_mc_addr(ha, netdev) { + xlgmac_set_mac_reg(pdata, ha, &mac_reg); + addn_macs--; + } + } + } + + /* Clear remaining additional MAC address entries */ + while (addn_macs--) + xlgmac_set_mac_reg(pdata, NULL, &mac_reg); +} + +static void xlgmac_set_mac_hash_table(struct xlgmac_pdata *pdata) +{ + unsigned int hash_table_shift, hash_table_count; + u32 hash_table[XLGMAC_MAC_HASH_TABLE_SIZE]; + struct net_device *netdev = pdata->netdev; + struct netdev_hw_addr *ha; + unsigned int hash_reg; + unsigned int i; + u32 crc; + + hash_table_shift = 26 - (pdata->hw_feat.hash_table_size >> 7); + hash_table_count = pdata->hw_feat.hash_table_size / 32; + memset(hash_table, 0, sizeof(hash_table)); + + /* Build the MAC Hash Table register values */ + netdev_for_each_uc_addr(ha, netdev) { + crc = bitrev32(~crc32_le(~0, ha->addr, ETH_ALEN)); + crc >>= hash_table_shift; + hash_table[crc >> 5] |= (1 << (crc & 0x1f)); + } + + netdev_for_each_mc_addr(ha, netdev) { + crc = bitrev32(~crc32_le(~0, ha->addr, ETH_ALEN)); + crc >>= hash_table_shift; + hash_table[crc >> 5] |= (1 << (crc & 0x1f)); + } + + /* Set the MAC Hash Table registers */ + hash_reg = MAC_HTR0; + for (i = 0; i < hash_table_count; i++) { + writel(hash_table[i], pdata->mac_regs + hash_reg); + hash_reg += MAC_HTR_INC; + } +} + +static int xlgmac_add_mac_addresses(struct xlgmac_pdata *pdata) +{ + if (pdata->hw_feat.hash_table_size) + xlgmac_set_mac_hash_table(pdata); + else + xlgmac_set_mac_addn_addrs(pdata); + + return 0; +} + +static void xlgmac_config_mac_address(struct xlgmac_pdata *pdata) +{ + u32 regval; + + xlgmac_set_mac_address(pdata, pdata->netdev->dev_addr); + + /* Filtering is done using perfect filtering and hash filtering */ + if (pdata->hw_feat.hash_table_size) { + regval = readl(pdata->mac_regs + MAC_PFR); + regval = XLGMAC_SET_REG_BITS(regval, MAC_PFR_HPF_POS, + MAC_PFR_HPF_LEN, 1); + regval = XLGMAC_SET_REG_BITS(regval, MAC_PFR_HUC_POS, + MAC_PFR_HUC_LEN, 1); + regval = XLGMAC_SET_REG_BITS(regval, MAC_PFR_HMC_POS, + MAC_PFR_HMC_LEN, 1); + writel(regval, pdata->mac_regs + MAC_PFR); + } +} + +static void xlgmac_config_jumbo_enable(struct xlgmac_pdata *pdata) +{ + unsigned int val; + u32 regval; + + val = (pdata->netdev->mtu > XLGMAC_STD_PACKET_MTU) ? 1 : 0; + + regval = readl(pdata->mac_regs + MAC_RCR); + regval = XLGMAC_SET_REG_BITS(regval, MAC_RCR_JE_POS, + MAC_RCR_JE_LEN, val); + writel(regval, pdata->mac_regs + MAC_RCR); +} + +static void xlgmac_config_checksum_offload(struct xlgmac_pdata *pdata) +{ + if (pdata->netdev->features & NETIF_F_RXCSUM) + xlgmac_enable_rx_csum(pdata); + else + xlgmac_disable_rx_csum(pdata); +} + +static void xlgmac_config_vlan_support(struct xlgmac_pdata *pdata) +{ + u32 regval; + + regval = readl(pdata->mac_regs + MAC_VLANIR); + /* Indicate that VLAN Tx CTAGs come from context descriptors */ + regval = XLGMAC_SET_REG_BITS(regval, MAC_VLANIR_CSVL_POS, + MAC_VLANIR_CSVL_LEN, 0); + regval = XLGMAC_SET_REG_BITS(regval, MAC_VLANIR_VLTI_POS, + MAC_VLANIR_VLTI_LEN, 1); + writel(regval, pdata->mac_regs + MAC_VLANIR); + + /* Set the current VLAN Hash Table register value */ + xlgmac_update_vlan_hash_table(pdata); + + if (pdata->netdev->features & NETIF_F_HW_VLAN_CTAG_FILTER) + xlgmac_enable_rx_vlan_filtering(pdata); + else + xlgmac_disable_rx_vlan_filtering(pdata); + + if (pdata->netdev->features & NETIF_F_HW_VLAN_CTAG_RX) + xlgmac_enable_rx_vlan_stripping(pdata); + else + xlgmac_disable_rx_vlan_stripping(pdata); +} + +static int xlgmac_config_rx_mode(struct xlgmac_pdata *pdata) +{ + struct net_device *netdev = pdata->netdev; + unsigned int pr_mode, am_mode; + + pr_mode = ((netdev->flags & IFF_PROMISC) != 0); + am_mode = ((netdev->flags & IFF_ALLMULTI) != 0); + + xlgmac_set_promiscuous_mode(pdata, pr_mode); + xlgmac_set_all_multicast_mode(pdata, am_mode); + + xlgmac_add_mac_addresses(pdata); + + return 0; +} + +static void xlgmac_prepare_tx_stop(struct xlgmac_pdata *pdata, + struct xlgmac_channel *channel) +{ + unsigned int tx_dsr, tx_pos, tx_qidx; + unsigned long tx_timeout; + unsigned int tx_status; + + /* Calculate the status register to read and the position within */ + if (channel->queue_index < DMA_DSRX_FIRST_QUEUE) { + tx_dsr = DMA_DSR0; + tx_pos = (channel->queue_index * DMA_DSR_Q_LEN) + + DMA_DSR0_TPS_START; + } else { + tx_qidx = channel->queue_index - DMA_DSRX_FIRST_QUEUE; + + tx_dsr = DMA_DSR1 + ((tx_qidx / DMA_DSRX_QPR) * DMA_DSRX_INC); + tx_pos = ((tx_qidx % DMA_DSRX_QPR) * DMA_DSR_Q_LEN) + + DMA_DSRX_TPS_START; + } + + /* The Tx engine cannot be stopped if it is actively processing + * descriptors. Wait for the Tx engine to enter the stopped or + * suspended state. Don't wait forever though... + */ + tx_timeout = jiffies + (XLGMAC_DMA_STOP_TIMEOUT * HZ); + while (time_before(jiffies, tx_timeout)) { + tx_status = readl(pdata->mac_regs + tx_dsr); + tx_status = XLGMAC_GET_REG_BITS(tx_status, tx_pos, + DMA_DSR_TPS_LEN); + if ((tx_status == DMA_TPS_STOPPED) || + (tx_status == DMA_TPS_SUSPENDED)) + break; + + usleep_range(500, 1000); + } + + if (!time_before(jiffies, tx_timeout)) + netdev_info(pdata->netdev, + "timed out waiting for Tx DMA channel %u to stop\n", + channel->queue_index); +} + +static void xlgmac_enable_tx(struct xlgmac_pdata *pdata) +{ + struct xlgmac_channel *channel; + unsigned int i; + u32 regval; + + /* Enable each Tx DMA channel */ + channel = pdata->channel_head; + for (i = 0; i < pdata->channel_count; i++, channel++) { + if (!channel->tx_ring) + break; + + regval = readl(XLGMAC_DMA_REG(channel, DMA_CH_TCR)); + regval = XLGMAC_SET_REG_BITS(regval, DMA_CH_TCR_ST_POS, + DMA_CH_TCR_ST_LEN, 1); + writel(regval, XLGMAC_DMA_REG(channel, DMA_CH_TCR)); + } + + /* Enable each Tx queue */ + for (i = 0; i < pdata->tx_q_count; i++) { + regval = readl(XLGMAC_MTL_REG(pdata, i, MTL_Q_TQOMR)); + regval = XLGMAC_SET_REG_BITS(regval, MTL_Q_TQOMR_TXQEN_POS, + MTL_Q_TQOMR_TXQEN_LEN, + MTL_Q_ENABLED); + writel(regval, XLGMAC_MTL_REG(pdata, i, MTL_Q_TQOMR)); + } + + /* Enable MAC Tx */ + regval = readl(pdata->mac_regs + MAC_TCR); + regval = XLGMAC_SET_REG_BITS(regval, MAC_TCR_TE_POS, + MAC_TCR_TE_LEN, 1); + writel(regval, pdata->mac_regs + MAC_TCR); +} + +static void xlgmac_disable_tx(struct xlgmac_pdata *pdata) +{ + struct xlgmac_channel *channel; + unsigned int i; + u32 regval; + + /* Prepare for Tx DMA channel stop */ + channel = pdata->channel_head; + for (i = 0; i < pdata->channel_count; i++, channel++) { + if (!channel->tx_ring) + break; + + xlgmac_prepare_tx_stop(pdata, channel); + } + + /* Disable MAC Tx */ + regval = readl(pdata->mac_regs + MAC_TCR); + regval = XLGMAC_SET_REG_BITS(regval, MAC_TCR_TE_POS, + MAC_TCR_TE_LEN, 0); + writel(regval, pdata->mac_regs + MAC_TCR); + + /* Disable each Tx queue */ + for (i = 0; i < pdata->tx_q_count; i++) { + regval = readl(XLGMAC_MTL_REG(pdata, i, MTL_Q_TQOMR)); + regval = XLGMAC_SET_REG_BITS(regval, MTL_Q_TQOMR_TXQEN_POS, + MTL_Q_TQOMR_TXQEN_LEN, 0); + writel(regval, XLGMAC_MTL_REG(pdata, i, MTL_Q_TQOMR)); + } + + /* Disable each Tx DMA channel */ + channel = pdata->channel_head; + for (i = 0; i < pdata->channel_count; i++, channel++) { + if (!channel->tx_ring) + break; + + regval = readl(XLGMAC_DMA_REG(channel, DMA_CH_TCR)); + regval = XLGMAC_SET_REG_BITS(regval, DMA_CH_TCR_ST_POS, + DMA_CH_TCR_ST_LEN, 0); + writel(regval, XLGMAC_DMA_REG(channel, DMA_CH_TCR)); + } +} + +static void xlgmac_prepare_rx_stop(struct xlgmac_pdata *pdata, + unsigned int queue) +{ + unsigned int rx_status, prxq, rxqsts; + unsigned long rx_timeout; + + /* The Rx engine cannot be stopped if it is actively processing + * packets. Wait for the Rx queue to empty the Rx fifo. Don't + * wait forever though... + */ + rx_timeout = jiffies + (XLGMAC_DMA_STOP_TIMEOUT * HZ); + while (time_before(jiffies, rx_timeout)) { + rx_status = readl(XLGMAC_MTL_REG(pdata, queue, MTL_Q_RQDR)); + prxq = XLGMAC_GET_REG_BITS(rx_status, MTL_Q_RQDR_PRXQ_POS, + MTL_Q_RQDR_PRXQ_LEN); + rxqsts = XLGMAC_GET_REG_BITS(rx_status, MTL_Q_RQDR_RXQSTS_POS, + MTL_Q_RQDR_RXQSTS_LEN); + if ((prxq == 0) && (rxqsts == 0)) + break; + + usleep_range(500, 1000); + } + + if (!time_before(jiffies, rx_timeout)) + netdev_info(pdata->netdev, + "timed out waiting for Rx queue %u to empty\n", + queue); +} + +static void xlgmac_enable_rx(struct xlgmac_pdata *pdata) +{ + struct xlgmac_channel *channel; + unsigned int regval, i; + + /* Enable each Rx DMA channel */ + channel = pdata->channel_head; + for (i = 0; i < pdata->channel_count; i++, channel++) { + if (!channel->rx_ring) + break; + + regval = readl(XLGMAC_DMA_REG(channel, DMA_CH_RCR)); + regval = XLGMAC_SET_REG_BITS(regval, DMA_CH_RCR_SR_POS, + DMA_CH_RCR_SR_LEN, 1); + writel(regval, XLGMAC_DMA_REG(channel, DMA_CH_RCR)); + } + + /* Enable each Rx queue */ + regval = 0; + for (i = 0; i < pdata->rx_q_count; i++) + regval |= (0x02 << (i << 1)); + writel(regval, pdata->mac_regs + MAC_RQC0R); + + /* Enable MAC Rx */ + regval = readl(pdata->mac_regs + MAC_RCR); + regval = XLGMAC_SET_REG_BITS(regval, MAC_RCR_DCRCC_POS, + MAC_RCR_DCRCC_LEN, 1); + regval = XLGMAC_SET_REG_BITS(regval, MAC_RCR_CST_POS, + MAC_RCR_CST_LEN, 1); + regval = XLGMAC_SET_REG_BITS(regval, MAC_RCR_ACS_POS, + MAC_RCR_ACS_LEN, 1); + regval = XLGMAC_SET_REG_BITS(regval, MAC_RCR_RE_POS, + MAC_RCR_RE_LEN, 1); + writel(regval, pdata->mac_regs + MAC_RCR); +} + +static void xlgmac_disable_rx(struct xlgmac_pdata *pdata) +{ + struct xlgmac_channel *channel; + unsigned int i; + u32 regval; + + /* Disable MAC Rx */ + regval = readl(pdata->mac_regs + MAC_RCR); + regval = XLGMAC_SET_REG_BITS(regval, MAC_RCR_DCRCC_POS, + MAC_RCR_DCRCC_LEN, 0); + regval = XLGMAC_SET_REG_BITS(regval, MAC_RCR_CST_POS, + MAC_RCR_CST_LEN, 0); + regval = XLGMAC_SET_REG_BITS(regval, MAC_RCR_ACS_POS, + MAC_RCR_ACS_LEN, 0); + regval = XLGMAC_SET_REG_BITS(regval, MAC_RCR_RE_POS, + MAC_RCR_RE_LEN, 0); + writel(regval, pdata->mac_regs + MAC_RCR); + + /* Prepare for Rx DMA channel stop */ + for (i = 0; i < pdata->rx_q_count; i++) + xlgmac_prepare_rx_stop(pdata, i); + + /* Disable each Rx queue */ + writel(0, pdata->mac_regs + MAC_RQC0R); + + /* Disable each Rx DMA channel */ + channel = pdata->channel_head; + for (i = 0; i < pdata->channel_count; i++, channel++) { + if (!channel->rx_ring) + break; + + regval = readl(XLGMAC_DMA_REG(channel, DMA_CH_RCR)); + regval = XLGMAC_SET_REG_BITS(regval, DMA_CH_RCR_SR_POS, + DMA_CH_RCR_SR_LEN, 0); + writel(regval, XLGMAC_DMA_REG(channel, DMA_CH_RCR)); + } +} + +static void xlgmac_tx_start_xmit(struct xlgmac_channel *channel, + struct xlgmac_ring *ring) +{ + struct xlgmac_pdata *pdata = channel->pdata; + struct xlgmac_desc_data *desc_data; + + /* Make sure everything is written before the register write */ + wmb(); + + /* Issue a poll command to Tx DMA by writing address + * of next immediate free descriptor + */ + desc_data = XLGMAC_GET_DESC_DATA(ring, ring->cur); + writel(lower_32_bits(desc_data->dma_desc_addr), + XLGMAC_DMA_REG(channel, DMA_CH_TDTR_LO)); + + /* Start the Tx timer */ + if (pdata->tx_usecs && !channel->tx_timer_active) { + channel->tx_timer_active = 1; + mod_timer(&channel->tx_timer, + jiffies + usecs_to_jiffies(pdata->tx_usecs)); + } + + ring->tx.xmit_more = 0; +} + +static void xlgmac_dev_xmit(struct xlgmac_channel *channel) +{ + struct xlgmac_pdata *pdata = channel->pdata; + struct xlgmac_ring *ring = channel->tx_ring; + unsigned int tso_context, vlan_context; + struct xlgmac_desc_data *desc_data; + struct xlgmac_dma_desc *dma_desc; + struct xlgmac_pkt_info *pkt_info; + unsigned int csum, tso, vlan; + int start_index = ring->cur; + int cur_index = ring->cur; + unsigned int tx_set_ic; + int i; + + pkt_info = &ring->pkt_info; + csum = XLGMAC_GET_REG_BITS(pkt_info->attributes, + TX_PACKET_ATTRIBUTES_CSUM_ENABLE_POS, + TX_PACKET_ATTRIBUTES_CSUM_ENABLE_LEN); + tso = XLGMAC_GET_REG_BITS(pkt_info->attributes, + TX_PACKET_ATTRIBUTES_TSO_ENABLE_POS, + TX_PACKET_ATTRIBUTES_TSO_ENABLE_LEN); + vlan = XLGMAC_GET_REG_BITS(pkt_info->attributes, + TX_PACKET_ATTRIBUTES_VLAN_CTAG_POS, + TX_PACKET_ATTRIBUTES_VLAN_CTAG_LEN); + + if (tso && (pkt_info->mss != ring->tx.cur_mss)) + tso_context = 1; + else + tso_context = 0; + + if (vlan && (pkt_info->vlan_ctag != ring->tx.cur_vlan_ctag)) + vlan_context = 1; + else + vlan_context = 0; + + /* Determine if an interrupt should be generated for this Tx: + * Interrupt: + * - Tx frame count exceeds the frame count setting + * - Addition of Tx frame count to the frame count since the + * last interrupt was set exceeds the frame count setting + * No interrupt: + * - No frame count setting specified (ethtool -C ethX tx-frames 0) + * - Addition of Tx frame count to the frame count since the + * last interrupt was set does not exceed the frame count setting + */ + ring->coalesce_count += pkt_info->tx_packets; + if (!pdata->tx_frames) + tx_set_ic = 0; + else if (pkt_info->tx_packets > pdata->tx_frames) + tx_set_ic = 1; + else if ((ring->coalesce_count % pdata->tx_frames) < + pkt_info->tx_packets) + tx_set_ic = 1; + else + tx_set_ic = 0; + + desc_data = XLGMAC_GET_DESC_DATA(ring, cur_index); + dma_desc = desc_data->dma_desc; + + /* Create a context descriptor if this is a TSO pkt_info */ + if (tso_context || vlan_context) { + if (tso_context) { + netif_dbg(pdata, tx_queued, pdata->netdev, + "TSO context descriptor, mss=%u\n", + pkt_info->mss); + + /* Set the MSS size */ + dma_desc->desc2 = XLGMAC_SET_REG_BITS_LE( + dma_desc->desc2, + TX_CONTEXT_DESC2_MSS_POS, + TX_CONTEXT_DESC2_MSS_LEN, + pkt_info->mss); + + /* Mark it as a CONTEXT descriptor */ + dma_desc->desc3 = XLGMAC_SET_REG_BITS_LE( + dma_desc->desc3, + TX_CONTEXT_DESC3_CTXT_POS, + TX_CONTEXT_DESC3_CTXT_LEN, + 1); + + /* Indicate this descriptor contains the MSS */ + dma_desc->desc3 = XLGMAC_SET_REG_BITS_LE( + dma_desc->desc3, + TX_CONTEXT_DESC3_TCMSSV_POS, + TX_CONTEXT_DESC3_TCMSSV_LEN, + 1); + + ring->tx.cur_mss = pkt_info->mss; + } + + if (vlan_context) { + netif_dbg(pdata, tx_queued, pdata->netdev, + "VLAN context descriptor, ctag=%u\n", + pkt_info->vlan_ctag); + + /* Mark it as a CONTEXT descriptor */ + dma_desc->desc3 = XLGMAC_SET_REG_BITS_LE( + dma_desc->desc3, + TX_CONTEXT_DESC3_CTXT_POS, + TX_CONTEXT_DESC3_CTXT_LEN, + 1); + + /* Set the VLAN tag */ + dma_desc->desc3 = XLGMAC_SET_REG_BITS_LE( + dma_desc->desc3, + TX_CONTEXT_DESC3_VT_POS, + TX_CONTEXT_DESC3_VT_LEN, + pkt_info->vlan_ctag); + + /* Indicate this descriptor contains the VLAN tag */ + dma_desc->desc3 = XLGMAC_SET_REG_BITS_LE( + dma_desc->desc3, + TX_CONTEXT_DESC3_VLTV_POS, + TX_CONTEXT_DESC3_VLTV_LEN, + 1); + + ring->tx.cur_vlan_ctag = pkt_info->vlan_ctag; + } + + cur_index++; + desc_data = XLGMAC_GET_DESC_DATA(ring, cur_index); + dma_desc = desc_data->dma_desc; + } + + /* Update buffer address (for TSO this is the header) */ + dma_desc->desc0 = cpu_to_le32(lower_32_bits(desc_data->skb_dma)); + dma_desc->desc1 = cpu_to_le32(upper_32_bits(desc_data->skb_dma)); + + /* Update the buffer length */ + dma_desc->desc2 = XLGMAC_SET_REG_BITS_LE( + dma_desc->desc2, + TX_NORMAL_DESC2_HL_B1L_POS, + TX_NORMAL_DESC2_HL_B1L_LEN, + desc_data->skb_dma_len); + + /* VLAN tag insertion check */ + if (vlan) + dma_desc->desc2 = XLGMAC_SET_REG_BITS_LE( + dma_desc->desc2, + TX_NORMAL_DESC2_VTIR_POS, + TX_NORMAL_DESC2_VTIR_LEN, + TX_NORMAL_DESC2_VLAN_INSERT); + + /* Timestamp enablement check */ + if (XLGMAC_GET_REG_BITS(pkt_info->attributes, + TX_PACKET_ATTRIBUTES_PTP_POS, + TX_PACKET_ATTRIBUTES_PTP_LEN)) + dma_desc->desc2 = XLGMAC_SET_REG_BITS_LE( + dma_desc->desc2, + TX_NORMAL_DESC2_TTSE_POS, + TX_NORMAL_DESC2_TTSE_LEN, + 1); + + /* Mark it as First Descriptor */ + dma_desc->desc3 = XLGMAC_SET_REG_BITS_LE( + dma_desc->desc3, + TX_NORMAL_DESC3_FD_POS, + TX_NORMAL_DESC3_FD_LEN, + 1); + + /* Mark it as a NORMAL descriptor */ + dma_desc->desc3 = XLGMAC_SET_REG_BITS_LE( + dma_desc->desc3, + TX_NORMAL_DESC3_CTXT_POS, + TX_NORMAL_DESC3_CTXT_LEN, + 0); + + /* Set OWN bit if not the first descriptor */ + if (cur_index != start_index) + dma_desc->desc3 = XLGMAC_SET_REG_BITS_LE( + dma_desc->desc3, + TX_NORMAL_DESC3_OWN_POS, + TX_NORMAL_DESC3_OWN_LEN, + 1); + + if (tso) { + /* Enable TSO */ + dma_desc->desc3 = XLGMAC_SET_REG_BITS_LE( + dma_desc->desc3, + TX_NORMAL_DESC3_TSE_POS, + TX_NORMAL_DESC3_TSE_LEN, 1); + dma_desc->desc3 = XLGMAC_SET_REG_BITS_LE( + dma_desc->desc3, + TX_NORMAL_DESC3_TCPPL_POS, + TX_NORMAL_DESC3_TCPPL_LEN, + pkt_info->tcp_payload_len); + dma_desc->desc3 = XLGMAC_SET_REG_BITS_LE( + dma_desc->desc3, + TX_NORMAL_DESC3_TCPHDRLEN_POS, + TX_NORMAL_DESC3_TCPHDRLEN_LEN, + pkt_info->tcp_header_len / 4); + + pdata->stats.tx_tso_packets++; + } else { + /* Enable CRC and Pad Insertion */ + dma_desc->desc3 = XLGMAC_SET_REG_BITS_LE( + dma_desc->desc3, + TX_NORMAL_DESC3_CPC_POS, + TX_NORMAL_DESC3_CPC_LEN, 0); + + /* Enable HW CSUM */ + if (csum) + dma_desc->desc3 = XLGMAC_SET_REG_BITS_LE( + dma_desc->desc3, + TX_NORMAL_DESC3_CIC_POS, + TX_NORMAL_DESC3_CIC_LEN, + 0x3); + + /* Set the total length to be transmitted */ + dma_desc->desc3 = XLGMAC_SET_REG_BITS_LE( + dma_desc->desc3, + TX_NORMAL_DESC3_FL_POS, + TX_NORMAL_DESC3_FL_LEN, + pkt_info->length); + } + + for (i = cur_index - start_index + 1; i < pkt_info->desc_count; i++) { + cur_index++; + desc_data = XLGMAC_GET_DESC_DATA(ring, cur_index); + dma_desc = desc_data->dma_desc; + + /* Update buffer address */ + dma_desc->desc0 = + cpu_to_le32(lower_32_bits(desc_data->skb_dma)); + dma_desc->desc1 = + cpu_to_le32(upper_32_bits(desc_data->skb_dma)); + + /* Update the buffer length */ + dma_desc->desc2 = XLGMAC_SET_REG_BITS_LE( + dma_desc->desc2, + TX_NORMAL_DESC2_HL_B1L_POS, + TX_NORMAL_DESC2_HL_B1L_LEN, + desc_data->skb_dma_len); + + /* Set OWN bit */ + dma_desc->desc3 = XLGMAC_SET_REG_BITS_LE( + dma_desc->desc3, + TX_NORMAL_DESC3_OWN_POS, + TX_NORMAL_DESC3_OWN_LEN, 1); + + /* Mark it as NORMAL descriptor */ + dma_desc->desc3 = XLGMAC_SET_REG_BITS_LE( + dma_desc->desc3, + TX_NORMAL_DESC3_CTXT_POS, + TX_NORMAL_DESC3_CTXT_LEN, 0); + + /* Enable HW CSUM */ + if (csum) + dma_desc->desc3 = XLGMAC_SET_REG_BITS_LE( + dma_desc->desc3, + TX_NORMAL_DESC3_CIC_POS, + TX_NORMAL_DESC3_CIC_LEN, + 0x3); + } + + /* Set LAST bit for the last descriptor */ + dma_desc->desc3 = XLGMAC_SET_REG_BITS_LE( + dma_desc->desc3, + TX_NORMAL_DESC3_LD_POS, + TX_NORMAL_DESC3_LD_LEN, 1); + + /* Set IC bit based on Tx coalescing settings */ + if (tx_set_ic) + dma_desc->desc2 = XLGMAC_SET_REG_BITS_LE( + dma_desc->desc2, + TX_NORMAL_DESC2_IC_POS, + TX_NORMAL_DESC2_IC_LEN, 1); + + /* Save the Tx info to report back during cleanup */ + desc_data->tx.packets = pkt_info->tx_packets; + desc_data->tx.bytes = pkt_info->tx_bytes; + + /* In case the Tx DMA engine is running, make sure everything + * is written to the descriptor(s) before setting the OWN bit + * for the first descriptor + */ + dma_wmb(); + + /* Set OWN bit for the first descriptor */ + desc_data = XLGMAC_GET_DESC_DATA(ring, start_index); + dma_desc = desc_data->dma_desc; + dma_desc->desc3 = XLGMAC_SET_REG_BITS_LE( + dma_desc->desc3, + TX_NORMAL_DESC3_OWN_POS, + TX_NORMAL_DESC3_OWN_LEN, 1); + + if (netif_msg_tx_queued(pdata)) + xlgmac_dump_tx_desc(pdata, ring, start_index, + pkt_info->desc_count, 1); + + /* Make sure ownership is written to the descriptor */ + smp_wmb(); + + ring->cur = cur_index + 1; + if (!pkt_info->skb->xmit_more || + netif_xmit_stopped(netdev_get_tx_queue(pdata->netdev, + channel->queue_index))) + xlgmac_tx_start_xmit(channel, ring); + else + ring->tx.xmit_more = 1; + + XLGMAC_PR("%s: descriptors %u to %u written\n", + channel->name, start_index & (ring->dma_desc_count - 1), + (ring->cur - 1) & (ring->dma_desc_count - 1)); +} + +static void xlgmac_get_rx_tstamp(struct xlgmac_pkt_info *pkt_info, + struct xlgmac_dma_desc *dma_desc) +{ + u32 tsa, tsd; + u64 nsec; + + tsa = XLGMAC_GET_REG_BITS_LE(dma_desc->desc3, + RX_CONTEXT_DESC3_TSA_POS, + RX_CONTEXT_DESC3_TSA_LEN); + tsd = XLGMAC_GET_REG_BITS_LE(dma_desc->desc3, + RX_CONTEXT_DESC3_TSD_POS, + RX_CONTEXT_DESC3_TSD_LEN); + if (tsa && !tsd) { + nsec = le32_to_cpu(dma_desc->desc1); + nsec <<= 32; + nsec |= le32_to_cpu(dma_desc->desc0); + if (nsec != 0xffffffffffffffffULL) { + pkt_info->rx_tstamp = nsec; + pkt_info->attributes = XLGMAC_SET_REG_BITS( + pkt_info->attributes, + RX_PACKET_ATTRIBUTES_RX_TSTAMP_POS, + RX_PACKET_ATTRIBUTES_RX_TSTAMP_LEN, + 1); + } + } +} + +static void xlgmac_tx_desc_reset(struct xlgmac_desc_data *desc_data) +{ + struct xlgmac_dma_desc *dma_desc = desc_data->dma_desc; + + /* Reset the Tx descriptor + * Set buffer 1 (lo) address to zero + * Set buffer 1 (hi) address to zero + * Reset all other control bits (IC, TTSE, B2L & B1L) + * Reset all other control bits (OWN, CTXT, FD, LD, CPC, CIC, etc) + */ + dma_desc->desc0 = 0; + dma_desc->desc1 = 0; + dma_desc->desc2 = 0; + dma_desc->desc3 = 0; + + /* Make sure ownership is written to the descriptor */ + dma_wmb(); +} + +static void xlgmac_tx_desc_init(struct xlgmac_channel *channel) +{ + struct xlgmac_ring *ring = channel->tx_ring; + struct xlgmac_desc_data *desc_data; + int start_index = ring->cur; + int i; + + /* Initialze all descriptors */ + for (i = 0; i < ring->dma_desc_count; i++) { + desc_data = XLGMAC_GET_DESC_DATA(ring, i); + + /* Initialize Tx descriptor */ + xlgmac_tx_desc_reset(desc_data); + } + + /* Update the total number of Tx descriptors */ + writel(ring->dma_desc_count - 1, XLGMAC_DMA_REG(channel, DMA_CH_TDRLR)); + + /* Update the starting address of descriptor ring */ + desc_data = XLGMAC_GET_DESC_DATA(ring, start_index); + writel(upper_32_bits(desc_data->dma_desc_addr), + XLGMAC_DMA_REG(channel, DMA_CH_TDLR_HI)); + writel(lower_32_bits(desc_data->dma_desc_addr), + XLGMAC_DMA_REG(channel, DMA_CH_TDLR_LO)); +} + +static void xlgmac_rx_desc_reset(struct xlgmac_pdata *pdata, + struct xlgmac_desc_data *desc_data, + unsigned int index) +{ + struct xlgmac_dma_desc *dma_desc = desc_data->dma_desc; + unsigned int rx_frames = pdata->rx_frames; + unsigned int rx_usecs = pdata->rx_usecs; + dma_addr_t hdr_dma, buf_dma; + unsigned int inte; + + if (!rx_usecs && !rx_frames) { + /* No coalescing, interrupt for every descriptor */ + inte = 1; + } else { + /* Set interrupt based on Rx frame coalescing setting */ + if (rx_frames && !((index + 1) % rx_frames)) + inte = 1; + else + inte = 0; + } + + /* Reset the Rx descriptor + * Set buffer 1 (lo) address to header dma address (lo) + * Set buffer 1 (hi) address to header dma address (hi) + * Set buffer 2 (lo) address to buffer dma address (lo) + * Set buffer 2 (hi) address to buffer dma address (hi) and + * set control bits OWN and INTE + */ + hdr_dma = desc_data->rx.hdr.dma_base + desc_data->rx.hdr.dma_off; + buf_dma = desc_data->rx.buf.dma_base + desc_data->rx.buf.dma_off; + dma_desc->desc0 = cpu_to_le32(lower_32_bits(hdr_dma)); + dma_desc->desc1 = cpu_to_le32(upper_32_bits(hdr_dma)); + dma_desc->desc2 = cpu_to_le32(lower_32_bits(buf_dma)); + dma_desc->desc3 = cpu_to_le32(upper_32_bits(buf_dma)); + + dma_desc->desc3 = XLGMAC_SET_REG_BITS_LE( + dma_desc->desc3, + RX_NORMAL_DESC3_INTE_POS, + RX_NORMAL_DESC3_INTE_LEN, + inte); + + /* Since the Rx DMA engine is likely running, make sure everything + * is written to the descriptor(s) before setting the OWN bit + * for the descriptor + */ + dma_wmb(); + + dma_desc->desc3 = XLGMAC_SET_REG_BITS_LE( + dma_desc->desc3, + RX_NORMAL_DESC3_OWN_POS, + RX_NORMAL_DESC3_OWN_LEN, + 1); + + /* Make sure ownership is written to the descriptor */ + dma_wmb(); +} + +static void xlgmac_rx_desc_init(struct xlgmac_channel *channel) +{ + struct xlgmac_pdata *pdata = channel->pdata; + struct xlgmac_ring *ring = channel->rx_ring; + unsigned int start_index = ring->cur; + struct xlgmac_desc_data *desc_data; + unsigned int i; + + /* Initialize all descriptors */ + for (i = 0; i < ring->dma_desc_count; i++) { + desc_data = XLGMAC_GET_DESC_DATA(ring, i); + + /* Initialize Rx descriptor */ + xlgmac_rx_desc_reset(pdata, desc_data, i); + } + + /* Update the total number of Rx descriptors */ + writel(ring->dma_desc_count - 1, XLGMAC_DMA_REG(channel, DMA_CH_RDRLR)); + + /* Update the starting address of descriptor ring */ + desc_data = XLGMAC_GET_DESC_DATA(ring, start_index); + writel(upper_32_bits(desc_data->dma_desc_addr), + XLGMAC_DMA_REG(channel, DMA_CH_RDLR_HI)); + writel(lower_32_bits(desc_data->dma_desc_addr), + XLGMAC_DMA_REG(channel, DMA_CH_RDLR_LO)); + + /* Update the Rx Descriptor Tail Pointer */ + desc_data = XLGMAC_GET_DESC_DATA(ring, start_index + + ring->dma_desc_count - 1); + writel(lower_32_bits(desc_data->dma_desc_addr), + XLGMAC_DMA_REG(channel, DMA_CH_RDTR_LO)); +} + +static int xlgmac_is_context_desc(struct xlgmac_dma_desc *dma_desc) +{ + /* Rx and Tx share CTXT bit, so check TDES3.CTXT bit */ + return XLGMAC_GET_REG_BITS_LE(dma_desc->desc3, + TX_NORMAL_DESC3_CTXT_POS, + TX_NORMAL_DESC3_CTXT_LEN); +} + +static int xlgmac_is_last_desc(struct xlgmac_dma_desc *dma_desc) +{ + /* Rx and Tx share LD bit, so check TDES3.LD bit */ + return XLGMAC_GET_REG_BITS_LE(dma_desc->desc3, + TX_NORMAL_DESC3_LD_POS, + TX_NORMAL_DESC3_LD_LEN); +} + +static int xlgmac_disable_tx_flow_control(struct xlgmac_pdata *pdata) +{ + unsigned int max_q_count, q_count; + unsigned int reg, regval; + unsigned int i; + + /* Clear MTL flow control */ + for (i = 0; i < pdata->rx_q_count; i++) { + regval = readl(XLGMAC_MTL_REG(pdata, i, MTL_Q_RQOMR)); + regval = XLGMAC_SET_REG_BITS(regval, MTL_Q_RQOMR_EHFC_POS, + MTL_Q_RQOMR_EHFC_LEN, 0); + writel(regval, XLGMAC_MTL_REG(pdata, i, MTL_Q_RQOMR)); + } + + /* Clear MAC flow control */ + max_q_count = XLGMAC_MAX_FLOW_CONTROL_QUEUES; + q_count = min_t(unsigned int, pdata->tx_q_count, max_q_count); + reg = MAC_Q0TFCR; + for (i = 0; i < q_count; i++) { + regval = readl(pdata->mac_regs + reg); + regval = XLGMAC_SET_REG_BITS(regval, + MAC_Q0TFCR_TFE_POS, + MAC_Q0TFCR_TFE_LEN, + 0); + writel(regval, pdata->mac_regs + reg); + + reg += MAC_QTFCR_INC; + } + + return 0; +} + +static int xlgmac_enable_tx_flow_control(struct xlgmac_pdata *pdata) +{ + unsigned int max_q_count, q_count; + unsigned int reg, regval; + unsigned int i; + + /* Set MTL flow control */ + for (i = 0; i < pdata->rx_q_count; i++) { + regval = readl(XLGMAC_MTL_REG(pdata, i, MTL_Q_RQOMR)); + regval = XLGMAC_SET_REG_BITS(regval, MTL_Q_RQOMR_EHFC_POS, + MTL_Q_RQOMR_EHFC_LEN, 1); + writel(regval, XLGMAC_MTL_REG(pdata, i, MTL_Q_RQOMR)); + } + + /* Set MAC flow control */ + max_q_count = XLGMAC_MAX_FLOW_CONTROL_QUEUES; + q_count = min_t(unsigned int, pdata->tx_q_count, max_q_count); + reg = MAC_Q0TFCR; + for (i = 0; i < q_count; i++) { + regval = readl(pdata->mac_regs + reg); + + /* Enable transmit flow control */ + regval = XLGMAC_SET_REG_BITS(regval, MAC_Q0TFCR_TFE_POS, + MAC_Q0TFCR_TFE_LEN, 1); + /* Set pause time */ + regval = XLGMAC_SET_REG_BITS(regval, MAC_Q0TFCR_PT_POS, + MAC_Q0TFCR_PT_LEN, 0xffff); + + writel(regval, pdata->mac_regs + reg); + + reg += MAC_QTFCR_INC; + } + + return 0; +} + +static int xlgmac_disable_rx_flow_control(struct xlgmac_pdata *pdata) +{ + u32 regval; + + regval = readl(pdata->mac_regs + MAC_RFCR); + regval = XLGMAC_SET_REG_BITS(regval, MAC_RFCR_RFE_POS, + MAC_RFCR_RFE_LEN, 0); + writel(regval, pdata->mac_regs + MAC_RFCR); + + return 0; +} + +static int xlgmac_enable_rx_flow_control(struct xlgmac_pdata *pdata) +{ + u32 regval; + + regval = readl(pdata->mac_regs + MAC_RFCR); + regval = XLGMAC_SET_REG_BITS(regval, MAC_RFCR_RFE_POS, + MAC_RFCR_RFE_LEN, 1); + writel(regval, pdata->mac_regs + MAC_RFCR); + + return 0; +} + +static int xlgmac_config_tx_flow_control(struct xlgmac_pdata *pdata) +{ + if (pdata->tx_pause) + xlgmac_enable_tx_flow_control(pdata); + else + xlgmac_disable_tx_flow_control(pdata); + + return 0; +} + +static int xlgmac_config_rx_flow_control(struct xlgmac_pdata *pdata) +{ + if (pdata->rx_pause) + xlgmac_enable_rx_flow_control(pdata); + else + xlgmac_disable_rx_flow_control(pdata); + + return 0; +} + +static int xlgmac_config_rx_coalesce(struct xlgmac_pdata *pdata) +{ + struct xlgmac_channel *channel; + unsigned int i; + u32 regval; + + channel = pdata->channel_head; + for (i = 0; i < pdata->channel_count; i++, channel++) { + if (!channel->rx_ring) + break; + + regval = readl(XLGMAC_DMA_REG(channel, DMA_CH_RIWT)); + regval = XLGMAC_SET_REG_BITS(regval, DMA_CH_RIWT_RWT_POS, + DMA_CH_RIWT_RWT_LEN, + pdata->rx_riwt); + writel(regval, XLGMAC_DMA_REG(channel, DMA_CH_RIWT)); + } + + return 0; +} + +static void xlgmac_config_flow_control(struct xlgmac_pdata *pdata) +{ + xlgmac_config_tx_flow_control(pdata); + xlgmac_config_rx_flow_control(pdata); +} + +static void xlgmac_config_rx_fep_enable(struct xlgmac_pdata *pdata) +{ + unsigned int i; + u32 regval; + + for (i = 0; i < pdata->rx_q_count; i++) { + regval = readl(XLGMAC_MTL_REG(pdata, i, MTL_Q_RQOMR)); + regval = XLGMAC_SET_REG_BITS(regval, MTL_Q_RQOMR_FEP_POS, + MTL_Q_RQOMR_FEP_LEN, 1); + writel(regval, XLGMAC_MTL_REG(pdata, i, MTL_Q_RQOMR)); + } +} + +static void xlgmac_config_rx_fup_enable(struct xlgmac_pdata *pdata) +{ + unsigned int i; + u32 regval; + + for (i = 0; i < pdata->rx_q_count; i++) { + regval = readl(XLGMAC_MTL_REG(pdata, i, MTL_Q_RQOMR)); + regval = XLGMAC_SET_REG_BITS(regval, MTL_Q_RQOMR_FUP_POS, + MTL_Q_RQOMR_FUP_LEN, 1); + writel(regval, XLGMAC_MTL_REG(pdata, i, MTL_Q_RQOMR)); + } +} + +static int xlgmac_config_tx_coalesce(struct xlgmac_pdata *pdata) +{ + return 0; +} + +static void xlgmac_config_rx_buffer_size(struct xlgmac_pdata *pdata) +{ + struct xlgmac_channel *channel; + unsigned int i; + u32 regval; + + channel = pdata->channel_head; + for (i = 0; i < pdata->channel_count; i++, channel++) { + if (!channel->rx_ring) + break; + + regval = readl(XLGMAC_DMA_REG(channel, DMA_CH_RCR)); + regval = XLGMAC_SET_REG_BITS(regval, DMA_CH_RCR_RBSZ_POS, + DMA_CH_RCR_RBSZ_LEN, + pdata->rx_buf_size); + writel(regval, XLGMAC_DMA_REG(channel, DMA_CH_RCR)); + } +} + +static void xlgmac_config_tso_mode(struct xlgmac_pdata *pdata) +{ + struct xlgmac_channel *channel; + unsigned int i; + u32 regval; + + channel = pdata->channel_head; + for (i = 0; i < pdata->channel_count; i++, channel++) { + if (!channel->tx_ring) + break; + + if (pdata->hw_feat.tso) { + regval = readl(XLGMAC_DMA_REG(channel, DMA_CH_TCR)); + regval = XLGMAC_SET_REG_BITS(regval, DMA_CH_TCR_TSE_POS, + DMA_CH_TCR_TSE_LEN, 1); + writel(regval, XLGMAC_DMA_REG(channel, DMA_CH_TCR)); + } + } +} + +static void xlgmac_config_sph_mode(struct xlgmac_pdata *pdata) +{ + struct xlgmac_channel *channel; + unsigned int i; + u32 regval; + + channel = pdata->channel_head; + for (i = 0; i < pdata->channel_count; i++, channel++) { + if (!channel->rx_ring) + break; + + regval = readl(XLGMAC_DMA_REG(channel, DMA_CH_CR)); + regval = XLGMAC_SET_REG_BITS(regval, DMA_CH_CR_SPH_POS, + DMA_CH_CR_SPH_LEN, 1); + writel(regval, XLGMAC_DMA_REG(channel, DMA_CH_CR)); + } + + regval = readl(pdata->mac_regs + MAC_RCR); + regval = XLGMAC_SET_REG_BITS(regval, MAC_RCR_HDSMS_POS, + MAC_RCR_HDSMS_LEN, + XLGMAC_SPH_HDSMS_SIZE); + writel(regval, pdata->mac_regs + MAC_RCR); +} + +static unsigned int xlgmac_usec_to_riwt(struct xlgmac_pdata *pdata, + unsigned int usec) +{ + unsigned long rate; + unsigned int ret; + + rate = pdata->sysclk_rate; + + /* Convert the input usec value to the watchdog timer value. Each + * watchdog timer value is equivalent to 256 clock cycles. + * Calculate the required value as: + * ( usec * ( system_clock_mhz / 10^6 ) / 256 + */ + ret = (usec * (rate / 1000000)) / 256; + + return ret; +} + +static unsigned int xlgmac_riwt_to_usec(struct xlgmac_pdata *pdata, + unsigned int riwt) +{ + unsigned long rate; + unsigned int ret; + + rate = pdata->sysclk_rate; + + /* Convert the input watchdog timer value to the usec value. Each + * watchdog timer value is equivalent to 256 clock cycles. + * Calculate the required value as: + * ( riwt * 256 ) / ( system_clock_mhz / 10^6 ) + */ + ret = (riwt * 256) / (rate / 1000000); + + return ret; +} + +static int xlgmac_config_rx_threshold(struct xlgmac_pdata *pdata, + unsigned int val) +{ + unsigned int i; + u32 regval; + + for (i = 0; i < pdata->rx_q_count; i++) { + regval = readl(XLGMAC_MTL_REG(pdata, i, MTL_Q_RQOMR)); + regval = XLGMAC_SET_REG_BITS(regval, MTL_Q_RQOMR_RTC_POS, + MTL_Q_RQOMR_RTC_LEN, val); + writel(regval, XLGMAC_MTL_REG(pdata, i, MTL_Q_RQOMR)); + } + + return 0; +} + +static void xlgmac_config_mtl_mode(struct xlgmac_pdata *pdata) +{ + unsigned int i; + u32 regval; + + /* Set Tx to weighted round robin scheduling algorithm */ + regval = readl(pdata->mac_regs + MTL_OMR); + regval = XLGMAC_SET_REG_BITS(regval, MTL_OMR_ETSALG_POS, + MTL_OMR_ETSALG_LEN, MTL_ETSALG_WRR); + writel(regval, pdata->mac_regs + MTL_OMR); + + /* Set Tx traffic classes to use WRR algorithm with equal weights */ + for (i = 0; i < pdata->hw_feat.tc_cnt; i++) { + regval = readl(XLGMAC_MTL_REG(pdata, i, MTL_TC_ETSCR)); + regval = XLGMAC_SET_REG_BITS(regval, MTL_TC_ETSCR_TSA_POS, + MTL_TC_ETSCR_TSA_LEN, MTL_TSA_ETS); + writel(regval, XLGMAC_MTL_REG(pdata, i, MTL_TC_ETSCR)); + + regval = readl(XLGMAC_MTL_REG(pdata, i, MTL_TC_QWR)); + regval = XLGMAC_SET_REG_BITS(regval, MTL_TC_QWR_QW_POS, + MTL_TC_QWR_QW_LEN, 1); + writel(regval, XLGMAC_MTL_REG(pdata, i, MTL_TC_QWR)); + } + + /* Set Rx to strict priority algorithm */ + regval = readl(pdata->mac_regs + MTL_OMR); + regval = XLGMAC_SET_REG_BITS(regval, MTL_OMR_RAA_POS, + MTL_OMR_RAA_LEN, MTL_RAA_SP); + writel(regval, pdata->mac_regs + MTL_OMR); +} + +static void xlgmac_config_queue_mapping(struct xlgmac_pdata *pdata) +{ + unsigned int ppq, ppq_extra, prio, prio_queues; + unsigned int qptc, qptc_extra, queue; + unsigned int reg, regval; + unsigned int mask; + unsigned int i, j; + + /* Map the MTL Tx Queues to Traffic Classes + * Note: Tx Queues >= Traffic Classes + */ + qptc = pdata->tx_q_count / pdata->hw_feat.tc_cnt; + qptc_extra = pdata->tx_q_count % pdata->hw_feat.tc_cnt; + + for (i = 0, queue = 0; i < pdata->hw_feat.tc_cnt; i++) { + for (j = 0; j < qptc; j++) { + netif_dbg(pdata, drv, pdata->netdev, + "TXq%u mapped to TC%u\n", queue, i); + regval = readl(XLGMAC_MTL_REG(pdata, queue, + MTL_Q_TQOMR)); + regval = XLGMAC_SET_REG_BITS(regval, + MTL_Q_TQOMR_Q2TCMAP_POS, + MTL_Q_TQOMR_Q2TCMAP_LEN, + i); + writel(regval, XLGMAC_MTL_REG(pdata, queue, + MTL_Q_TQOMR)); + queue++; + } + + if (i < qptc_extra) { + netif_dbg(pdata, drv, pdata->netdev, + "TXq%u mapped to TC%u\n", queue, i); + regval = readl(XLGMAC_MTL_REG(pdata, queue, + MTL_Q_TQOMR)); + regval = XLGMAC_SET_REG_BITS(regval, + MTL_Q_TQOMR_Q2TCMAP_POS, + MTL_Q_TQOMR_Q2TCMAP_LEN, + i); + writel(regval, XLGMAC_MTL_REG(pdata, queue, + MTL_Q_TQOMR)); + queue++; + } + } + + /* Map the 8 VLAN priority values to available MTL Rx queues */ + prio_queues = min_t(unsigned int, IEEE_8021QAZ_MAX_TCS, + pdata->rx_q_count); + ppq = IEEE_8021QAZ_MAX_TCS / prio_queues; + ppq_extra = IEEE_8021QAZ_MAX_TCS % prio_queues; + + reg = MAC_RQC2R; + regval = 0; + for (i = 0, prio = 0; i < prio_queues;) { + mask = 0; + for (j = 0; j < ppq; j++) { + netif_dbg(pdata, drv, pdata->netdev, + "PRIO%u mapped to RXq%u\n", prio, i); + mask |= (1 << prio); + prio++; + } + + if (i < ppq_extra) { + netif_dbg(pdata, drv, pdata->netdev, + "PRIO%u mapped to RXq%u\n", prio, i); + mask |= (1 << prio); + prio++; + } + + regval |= (mask << ((i++ % MAC_RQC2_Q_PER_REG) << 3)); + + if ((i % MAC_RQC2_Q_PER_REG) && (i != prio_queues)) + continue; + + writel(regval, pdata->mac_regs + reg); + reg += MAC_RQC2_INC; + regval = 0; + } + + /* Configure one to one, MTL Rx queue to DMA Rx channel mapping + * ie Q0 <--> CH0, Q1 <--> CH1 ... Q11 <--> CH11 + */ + reg = MTL_RQDCM0R; + regval = readl(pdata->mac_regs + reg); + regval |= (MTL_RQDCM0R_Q0MDMACH | MTL_RQDCM0R_Q1MDMACH | + MTL_RQDCM0R_Q2MDMACH | MTL_RQDCM0R_Q3MDMACH); + writel(regval, pdata->mac_regs + reg); + + reg += MTL_RQDCM_INC; + regval = readl(pdata->mac_regs + reg); + regval |= (MTL_RQDCM1R_Q4MDMACH | MTL_RQDCM1R_Q5MDMACH | + MTL_RQDCM1R_Q6MDMACH | MTL_RQDCM1R_Q7MDMACH); + writel(regval, pdata->mac_regs + reg); + + reg += MTL_RQDCM_INC; + regval = readl(pdata->mac_regs + reg); + regval |= (MTL_RQDCM2R_Q8MDMACH | MTL_RQDCM2R_Q9MDMACH | + MTL_RQDCM2R_Q10MDMACH | MTL_RQDCM2R_Q11MDMACH); + writel(regval, pdata->mac_regs + reg); +} + +static unsigned int xlgmac_calculate_per_queue_fifo( + unsigned int fifo_size, + unsigned int queue_count) +{ + unsigned int q_fifo_size; + unsigned int p_fifo; + + /* Calculate the configured fifo size */ + q_fifo_size = 1 << (fifo_size + 7); + + /* The configured value may not be the actual amount of fifo RAM */ + q_fifo_size = min_t(unsigned int, XLGMAC_MAX_FIFO, q_fifo_size); + + q_fifo_size = q_fifo_size / queue_count; + + /* Each increment in the queue fifo size represents 256 bytes of + * fifo, with 0 representing 256 bytes. Distribute the fifo equally + * between the queues. + */ + p_fifo = q_fifo_size / 256; + if (p_fifo) + p_fifo--; + + return p_fifo; +} + +static void xlgmac_config_tx_fifo_size(struct xlgmac_pdata *pdata) +{ + unsigned int fifo_size; + unsigned int i; + u32 regval; + + fifo_size = xlgmac_calculate_per_queue_fifo( + pdata->hw_feat.tx_fifo_size, + pdata->tx_q_count); + + for (i = 0; i < pdata->tx_q_count; i++) { + regval = readl(XLGMAC_MTL_REG(pdata, i, MTL_Q_TQOMR)); + regval = XLGMAC_SET_REG_BITS(regval, MTL_Q_TQOMR_TQS_POS, + MTL_Q_TQOMR_TQS_LEN, fifo_size); + writel(regval, XLGMAC_MTL_REG(pdata, i, MTL_Q_TQOMR)); + } + + netif_info(pdata, drv, pdata->netdev, + "%d Tx hardware queues, %d byte fifo per queue\n", + pdata->tx_q_count, ((fifo_size + 1) * 256)); +} + +static void xlgmac_config_rx_fifo_size(struct xlgmac_pdata *pdata) +{ + unsigned int fifo_size; + unsigned int i; + u32 regval; + + fifo_size = xlgmac_calculate_per_queue_fifo( + pdata->hw_feat.rx_fifo_size, + pdata->rx_q_count); + + for (i = 0; i < pdata->rx_q_count; i++) { + regval = readl(XLGMAC_MTL_REG(pdata, i, MTL_Q_RQOMR)); + regval = XLGMAC_SET_REG_BITS(regval, MTL_Q_RQOMR_RQS_POS, + MTL_Q_RQOMR_RQS_LEN, fifo_size); + writel(regval, XLGMAC_MTL_REG(pdata, i, MTL_Q_RQOMR)); + } + + netif_info(pdata, drv, pdata->netdev, + "%d Rx hardware queues, %d byte fifo per queue\n", + pdata->rx_q_count, ((fifo_size + 1) * 256)); +} + +static void xlgmac_config_flow_control_threshold(struct xlgmac_pdata *pdata) +{ + unsigned int i; + u32 regval; + + for (i = 0; i < pdata->rx_q_count; i++) { + regval = readl(XLGMAC_MTL_REG(pdata, i, MTL_Q_RQFCR)); + /* Activate flow control when less than 4k left in fifo */ + regval = XLGMAC_SET_REG_BITS(regval, MTL_Q_RQFCR_RFA_POS, + MTL_Q_RQFCR_RFA_LEN, 2); + /* De-activate flow control when more than 6k left in fifo */ + regval = XLGMAC_SET_REG_BITS(regval, MTL_Q_RQFCR_RFD_POS, + MTL_Q_RQFCR_RFD_LEN, 4); + writel(regval, XLGMAC_MTL_REG(pdata, i, MTL_Q_RQFCR)); + } +} + +static int xlgmac_config_tx_threshold(struct xlgmac_pdata *pdata, + unsigned int val) +{ + unsigned int i; + u32 regval; + + for (i = 0; i < pdata->tx_q_count; i++) { + regval = readl(XLGMAC_MTL_REG(pdata, i, MTL_Q_TQOMR)); + regval = XLGMAC_SET_REG_BITS(regval, MTL_Q_TQOMR_TTC_POS, + MTL_Q_TQOMR_TTC_LEN, val); + writel(regval, XLGMAC_MTL_REG(pdata, i, MTL_Q_TQOMR)); + } + + return 0; +} + +static int xlgmac_config_rsf_mode(struct xlgmac_pdata *pdata, + unsigned int val) +{ + unsigned int i; + u32 regval; + + for (i = 0; i < pdata->rx_q_count; i++) { + regval = readl(XLGMAC_MTL_REG(pdata, i, MTL_Q_RQOMR)); + regval = XLGMAC_SET_REG_BITS(regval, MTL_Q_RQOMR_RSF_POS, + MTL_Q_RQOMR_RSF_LEN, val); + writel(regval, XLGMAC_MTL_REG(pdata, i, MTL_Q_RQOMR)); + } + + return 0; +} + +static int xlgmac_config_tsf_mode(struct xlgmac_pdata *pdata, + unsigned int val) +{ + unsigned int i; + u32 regval; + + for (i = 0; i < pdata->tx_q_count; i++) { + regval = readl(XLGMAC_MTL_REG(pdata, i, MTL_Q_TQOMR)); + regval = XLGMAC_SET_REG_BITS(regval, MTL_Q_TQOMR_TSF_POS, + MTL_Q_TQOMR_TSF_LEN, val); + writel(regval, XLGMAC_MTL_REG(pdata, i, MTL_Q_TQOMR)); + } + + return 0; +} + +static int xlgmac_config_osp_mode(struct xlgmac_pdata *pdata) +{ + struct xlgmac_channel *channel; + unsigned int i; + u32 regval; + + channel = pdata->channel_head; + for (i = 0; i < pdata->channel_count; i++, channel++) { + if (!channel->tx_ring) + break; + + regval = readl(XLGMAC_DMA_REG(channel, DMA_CH_TCR)); + regval = XLGMAC_SET_REG_BITS(regval, DMA_CH_TCR_OSP_POS, + DMA_CH_TCR_OSP_LEN, + pdata->tx_osp_mode); + writel(regval, XLGMAC_DMA_REG(channel, DMA_CH_TCR)); + } + + return 0; +} + +static int xlgmac_config_pblx8(struct xlgmac_pdata *pdata) +{ + struct xlgmac_channel *channel; + unsigned int i; + u32 regval; + + channel = pdata->channel_head; + for (i = 0; i < pdata->channel_count; i++, channel++) { + regval = readl(XLGMAC_DMA_REG(channel, DMA_CH_CR)); + regval = XLGMAC_SET_REG_BITS(regval, DMA_CH_CR_PBLX8_POS, + DMA_CH_CR_PBLX8_LEN, + pdata->pblx8); + writel(regval, XLGMAC_DMA_REG(channel, DMA_CH_CR)); + } + + return 0; +} + +static int xlgmac_get_tx_pbl_val(struct xlgmac_pdata *pdata) +{ + u32 regval; + + regval = readl(XLGMAC_DMA_REG(pdata->channel_head, DMA_CH_TCR)); + regval = XLGMAC_GET_REG_BITS(regval, DMA_CH_TCR_PBL_POS, + DMA_CH_TCR_PBL_LEN); + return regval; +} + +static int xlgmac_config_tx_pbl_val(struct xlgmac_pdata *pdata) +{ + struct xlgmac_channel *channel; + unsigned int i; + u32 regval; + + channel = pdata->channel_head; + for (i = 0; i < pdata->channel_count; i++, channel++) { + if (!channel->tx_ring) + break; + + regval = readl(XLGMAC_DMA_REG(channel, DMA_CH_TCR)); + regval = XLGMAC_SET_REG_BITS(regval, DMA_CH_TCR_PBL_POS, + DMA_CH_TCR_PBL_LEN, + pdata->tx_pbl); + writel(regval, XLGMAC_DMA_REG(channel, DMA_CH_TCR)); + } + + return 0; +} + +static int xlgmac_get_rx_pbl_val(struct xlgmac_pdata *pdata) +{ + u32 regval; + + regval = readl(XLGMAC_DMA_REG(pdata->channel_head, DMA_CH_RCR)); + regval = XLGMAC_GET_REG_BITS(regval, DMA_CH_RCR_PBL_POS, + DMA_CH_RCR_PBL_LEN); + return regval; +} + +static int xlgmac_config_rx_pbl_val(struct xlgmac_pdata *pdata) +{ + struct xlgmac_channel *channel; + unsigned int i; + u32 regval; + + channel = pdata->channel_head; + for (i = 0; i < pdata->channel_count; i++, channel++) { + if (!channel->rx_ring) + break; + + regval = readl(XLGMAC_DMA_REG(channel, DMA_CH_RCR)); + regval = XLGMAC_SET_REG_BITS(regval, DMA_CH_RCR_PBL_POS, + DMA_CH_RCR_PBL_LEN, + pdata->rx_pbl); + writel(regval, XLGMAC_DMA_REG(channel, DMA_CH_RCR)); + } + + return 0; +} + +static u64 xlgmac_mmc_read(struct xlgmac_pdata *pdata, unsigned int reg_lo) +{ + bool read_hi; + u64 val; + + switch (reg_lo) { + /* These registers are always 64 bit */ + case MMC_TXOCTETCOUNT_GB_LO: + case MMC_TXOCTETCOUNT_G_LO: + case MMC_RXOCTETCOUNT_GB_LO: + case MMC_RXOCTETCOUNT_G_LO: + read_hi = true; + break; + + default: + read_hi = false; + } + + val = (u64)readl(pdata->mac_regs + reg_lo); + + if (read_hi) + val |= ((u64)readl(pdata->mac_regs + reg_lo + 4) << 32); + + return val; +} + +static void xlgmac_tx_mmc_int(struct xlgmac_pdata *pdata) +{ + unsigned int mmc_isr = readl(pdata->mac_regs + MMC_TISR); + struct xlgmac_stats *stats = &pdata->stats; + + if (XLGMAC_GET_REG_BITS(mmc_isr, + MMC_TISR_TXOCTETCOUNT_GB_POS, + MMC_TISR_TXOCTETCOUNT_GB_LEN)) + stats->txoctetcount_gb += + xlgmac_mmc_read(pdata, MMC_TXOCTETCOUNT_GB_LO); + + if (XLGMAC_GET_REG_BITS(mmc_isr, + MMC_TISR_TXFRAMECOUNT_GB_POS, + MMC_TISR_TXFRAMECOUNT_GB_LEN)) + stats->txframecount_gb += + xlgmac_mmc_read(pdata, MMC_TXFRAMECOUNT_GB_LO); + + if (XLGMAC_GET_REG_BITS(mmc_isr, + MMC_TISR_TXBROADCASTFRAMES_G_POS, + MMC_TISR_TXBROADCASTFRAMES_G_LEN)) + stats->txbroadcastframes_g += + xlgmac_mmc_read(pdata, MMC_TXBROADCASTFRAMES_G_LO); + + if (XLGMAC_GET_REG_BITS(mmc_isr, + MMC_TISR_TXMULTICASTFRAMES_G_POS, + MMC_TISR_TXMULTICASTFRAMES_G_LEN)) + stats->txmulticastframes_g += + xlgmac_mmc_read(pdata, MMC_TXMULTICASTFRAMES_G_LO); + + if (XLGMAC_GET_REG_BITS(mmc_isr, + MMC_TISR_TX64OCTETS_GB_POS, + MMC_TISR_TX64OCTETS_GB_LEN)) + stats->tx64octets_gb += + xlgmac_mmc_read(pdata, MMC_TX64OCTETS_GB_LO); + + if (XLGMAC_GET_REG_BITS(mmc_isr, + MMC_TISR_TX65TO127OCTETS_GB_POS, + MMC_TISR_TX65TO127OCTETS_GB_LEN)) + stats->tx65to127octets_gb += + xlgmac_mmc_read(pdata, MMC_TX65TO127OCTETS_GB_LO); + + if (XLGMAC_GET_REG_BITS(mmc_isr, + MMC_TISR_TX128TO255OCTETS_GB_POS, + MMC_TISR_TX128TO255OCTETS_GB_LEN)) + stats->tx128to255octets_gb += + xlgmac_mmc_read(pdata, MMC_TX128TO255OCTETS_GB_LO); + + if (XLGMAC_GET_REG_BITS(mmc_isr, + MMC_TISR_TX256TO511OCTETS_GB_POS, + MMC_TISR_TX256TO511OCTETS_GB_LEN)) + stats->tx256to511octets_gb += + xlgmac_mmc_read(pdata, MMC_TX256TO511OCTETS_GB_LO); + + if (XLGMAC_GET_REG_BITS(mmc_isr, + MMC_TISR_TX512TO1023OCTETS_GB_POS, + MMC_TISR_TX512TO1023OCTETS_GB_LEN)) + stats->tx512to1023octets_gb += + xlgmac_mmc_read(pdata, MMC_TX512TO1023OCTETS_GB_LO); + + if (XLGMAC_GET_REG_BITS(mmc_isr, + MMC_TISR_TX1024TOMAXOCTETS_GB_POS, + MMC_TISR_TX1024TOMAXOCTETS_GB_LEN)) + stats->tx1024tomaxoctets_gb += + xlgmac_mmc_read(pdata, MMC_TX1024TOMAXOCTETS_GB_LO); + + if (XLGMAC_GET_REG_BITS(mmc_isr, + MMC_TISR_TXUNICASTFRAMES_GB_POS, + MMC_TISR_TXUNICASTFRAMES_GB_LEN)) + stats->txunicastframes_gb += + xlgmac_mmc_read(pdata, MMC_TXUNICASTFRAMES_GB_LO); + + if (XLGMAC_GET_REG_BITS(mmc_isr, + MMC_TISR_TXMULTICASTFRAMES_GB_POS, + MMC_TISR_TXMULTICASTFRAMES_GB_LEN)) + stats->txmulticastframes_gb += + xlgmac_mmc_read(pdata, MMC_TXMULTICASTFRAMES_GB_LO); + + if (XLGMAC_GET_REG_BITS(mmc_isr, + MMC_TISR_TXBROADCASTFRAMES_GB_POS, + MMC_TISR_TXBROADCASTFRAMES_GB_LEN)) + stats->txbroadcastframes_g += + xlgmac_mmc_read(pdata, MMC_TXBROADCASTFRAMES_GB_LO); + + if (XLGMAC_GET_REG_BITS(mmc_isr, + MMC_TISR_TXUNDERFLOWERROR_POS, + MMC_TISR_TXUNDERFLOWERROR_LEN)) + stats->txunderflowerror += + xlgmac_mmc_read(pdata, MMC_TXUNDERFLOWERROR_LO); + + if (XLGMAC_GET_REG_BITS(mmc_isr, + MMC_TISR_TXOCTETCOUNT_G_POS, + MMC_TISR_TXOCTETCOUNT_G_LEN)) + stats->txoctetcount_g += + xlgmac_mmc_read(pdata, MMC_TXOCTETCOUNT_G_LO); + + if (XLGMAC_GET_REG_BITS(mmc_isr, + MMC_TISR_TXFRAMECOUNT_G_POS, + MMC_TISR_TXFRAMECOUNT_G_LEN)) + stats->txframecount_g += + xlgmac_mmc_read(pdata, MMC_TXFRAMECOUNT_G_LO); + + if (XLGMAC_GET_REG_BITS(mmc_isr, + MMC_TISR_TXPAUSEFRAMES_POS, + MMC_TISR_TXPAUSEFRAMES_LEN)) + stats->txpauseframes += + xlgmac_mmc_read(pdata, MMC_TXPAUSEFRAMES_LO); + + if (XLGMAC_GET_REG_BITS(mmc_isr, + MMC_TISR_TXVLANFRAMES_G_POS, + MMC_TISR_TXVLANFRAMES_G_LEN)) + stats->txvlanframes_g += + xlgmac_mmc_read(pdata, MMC_TXVLANFRAMES_G_LO); +} + +static void xlgmac_rx_mmc_int(struct xlgmac_pdata *pdata) +{ + unsigned int mmc_isr = readl(pdata->mac_regs + MMC_RISR); + struct xlgmac_stats *stats = &pdata->stats; + + if (XLGMAC_GET_REG_BITS(mmc_isr, + MMC_RISR_RXFRAMECOUNT_GB_POS, + MMC_RISR_RXFRAMECOUNT_GB_LEN)) + stats->rxframecount_gb += + xlgmac_mmc_read(pdata, MMC_RXFRAMECOUNT_GB_LO); + + if (XLGMAC_GET_REG_BITS(mmc_isr, + MMC_RISR_RXOCTETCOUNT_GB_POS, + MMC_RISR_RXOCTETCOUNT_GB_LEN)) + stats->rxoctetcount_gb += + xlgmac_mmc_read(pdata, MMC_RXOCTETCOUNT_GB_LO); + + if (XLGMAC_GET_REG_BITS(mmc_isr, + MMC_RISR_RXOCTETCOUNT_G_POS, + MMC_RISR_RXOCTETCOUNT_G_LEN)) + stats->rxoctetcount_g += + xlgmac_mmc_read(pdata, MMC_RXOCTETCOUNT_G_LO); + + if (XLGMAC_GET_REG_BITS(mmc_isr, + MMC_RISR_RXBROADCASTFRAMES_G_POS, + MMC_RISR_RXBROADCASTFRAMES_G_LEN)) + stats->rxbroadcastframes_g += + xlgmac_mmc_read(pdata, MMC_RXBROADCASTFRAMES_G_LO); + + if (XLGMAC_GET_REG_BITS(mmc_isr, + MMC_RISR_RXMULTICASTFRAMES_G_POS, + MMC_RISR_RXMULTICASTFRAMES_G_LEN)) + stats->rxmulticastframes_g += + xlgmac_mmc_read(pdata, MMC_RXMULTICASTFRAMES_G_LO); + + if (XLGMAC_GET_REG_BITS(mmc_isr, + MMC_RISR_RXCRCERROR_POS, + MMC_RISR_RXCRCERROR_LEN)) + stats->rxcrcerror += + xlgmac_mmc_read(pdata, MMC_RXCRCERROR_LO); + + if (XLGMAC_GET_REG_BITS(mmc_isr, + MMC_RISR_RXRUNTERROR_POS, + MMC_RISR_RXRUNTERROR_LEN)) + stats->rxrunterror += + xlgmac_mmc_read(pdata, MMC_RXRUNTERROR); + + if (XLGMAC_GET_REG_BITS(mmc_isr, + MMC_RISR_RXJABBERERROR_POS, + MMC_RISR_RXJABBERERROR_LEN)) + stats->rxjabbererror += + xlgmac_mmc_read(pdata, MMC_RXJABBERERROR); + + if (XLGMAC_GET_REG_BITS(mmc_isr, + MMC_RISR_RXUNDERSIZE_G_POS, + MMC_RISR_RXUNDERSIZE_G_LEN)) + stats->rxundersize_g += + xlgmac_mmc_read(pdata, MMC_RXUNDERSIZE_G); + + if (XLGMAC_GET_REG_BITS(mmc_isr, + MMC_RISR_RXOVERSIZE_G_POS, + MMC_RISR_RXOVERSIZE_G_LEN)) + stats->rxoversize_g += + xlgmac_mmc_read(pdata, MMC_RXOVERSIZE_G); + + if (XLGMAC_GET_REG_BITS(mmc_isr, + MMC_RISR_RX64OCTETS_GB_POS, + MMC_RISR_RX64OCTETS_GB_LEN)) + stats->rx64octets_gb += + xlgmac_mmc_read(pdata, MMC_RX64OCTETS_GB_LO); + + if (XLGMAC_GET_REG_BITS(mmc_isr, + MMC_RISR_RX65TO127OCTETS_GB_POS, + MMC_RISR_RX65TO127OCTETS_GB_LEN)) + stats->rx65to127octets_gb += + xlgmac_mmc_read(pdata, MMC_RX65TO127OCTETS_GB_LO); + + if (XLGMAC_GET_REG_BITS(mmc_isr, + MMC_RISR_RX128TO255OCTETS_GB_POS, + MMC_RISR_RX128TO255OCTETS_GB_LEN)) + stats->rx128to255octets_gb += + xlgmac_mmc_read(pdata, MMC_RX128TO255OCTETS_GB_LO); + + if (XLGMAC_GET_REG_BITS(mmc_isr, + MMC_RISR_RX256TO511OCTETS_GB_POS, + MMC_RISR_RX256TO511OCTETS_GB_LEN)) + stats->rx256to511octets_gb += + xlgmac_mmc_read(pdata, MMC_RX256TO511OCTETS_GB_LO); + + if (XLGMAC_GET_REG_BITS(mmc_isr, + MMC_RISR_RX512TO1023OCTETS_GB_POS, + MMC_RISR_RX512TO1023OCTETS_GB_LEN)) + stats->rx512to1023octets_gb += + xlgmac_mmc_read(pdata, MMC_RX512TO1023OCTETS_GB_LO); + + if (XLGMAC_GET_REG_BITS(mmc_isr, + MMC_RISR_RX1024TOMAXOCTETS_GB_POS, + MMC_RISR_RX1024TOMAXOCTETS_GB_LEN)) + stats->rx1024tomaxoctets_gb += + xlgmac_mmc_read(pdata, MMC_RX1024TOMAXOCTETS_GB_LO); + + if (XLGMAC_GET_REG_BITS(mmc_isr, + MMC_RISR_RXUNICASTFRAMES_G_POS, + MMC_RISR_RXUNICASTFRAMES_G_LEN)) + stats->rxunicastframes_g += + xlgmac_mmc_read(pdata, MMC_RXUNICASTFRAMES_G_LO); + + if (XLGMAC_GET_REG_BITS(mmc_isr, + MMC_RISR_RXLENGTHERROR_POS, + MMC_RISR_RXLENGTHERROR_LEN)) + stats->rxlengtherror += + xlgmac_mmc_read(pdata, MMC_RXLENGTHERROR_LO); + + if (XLGMAC_GET_REG_BITS(mmc_isr, + MMC_RISR_RXOUTOFRANGETYPE_POS, + MMC_RISR_RXOUTOFRANGETYPE_LEN)) + stats->rxoutofrangetype += + xlgmac_mmc_read(pdata, MMC_RXOUTOFRANGETYPE_LO); + + if (XLGMAC_GET_REG_BITS(mmc_isr, + MMC_RISR_RXPAUSEFRAMES_POS, + MMC_RISR_RXPAUSEFRAMES_LEN)) + stats->rxpauseframes += + xlgmac_mmc_read(pdata, MMC_RXPAUSEFRAMES_LO); + + if (XLGMAC_GET_REG_BITS(mmc_isr, + MMC_RISR_RXFIFOOVERFLOW_POS, + MMC_RISR_RXFIFOOVERFLOW_LEN)) + stats->rxfifooverflow += + xlgmac_mmc_read(pdata, MMC_RXFIFOOVERFLOW_LO); + + if (XLGMAC_GET_REG_BITS(mmc_isr, + MMC_RISR_RXVLANFRAMES_GB_POS, + MMC_RISR_RXVLANFRAMES_GB_LEN)) + stats->rxvlanframes_gb += + xlgmac_mmc_read(pdata, MMC_RXVLANFRAMES_GB_LO); + + if (XLGMAC_GET_REG_BITS(mmc_isr, + MMC_RISR_RXWATCHDOGERROR_POS, + MMC_RISR_RXWATCHDOGERROR_LEN)) + stats->rxwatchdogerror += + xlgmac_mmc_read(pdata, MMC_RXWATCHDOGERROR); +} + +static void xlgmac_read_mmc_stats(struct xlgmac_pdata *pdata) +{ + struct xlgmac_stats *stats = &pdata->stats; + u32 regval; + + /* Freeze counters */ + regval = readl(pdata->mac_regs + MMC_CR); + regval = XLGMAC_SET_REG_BITS(regval, MMC_CR_MCF_POS, + MMC_CR_MCF_LEN, 1); + writel(regval, pdata->mac_regs + MMC_CR); + + stats->txoctetcount_gb += + xlgmac_mmc_read(pdata, MMC_TXOCTETCOUNT_GB_LO); + + stats->txframecount_gb += + xlgmac_mmc_read(pdata, MMC_TXFRAMECOUNT_GB_LO); + + stats->txbroadcastframes_g += + xlgmac_mmc_read(pdata, MMC_TXBROADCASTFRAMES_G_LO); + + stats->txmulticastframes_g += + xlgmac_mmc_read(pdata, MMC_TXMULTICASTFRAMES_G_LO); + + stats->tx64octets_gb += + xlgmac_mmc_read(pdata, MMC_TX64OCTETS_GB_LO); + + stats->tx65to127octets_gb += + xlgmac_mmc_read(pdata, MMC_TX65TO127OCTETS_GB_LO); + + stats->tx128to255octets_gb += + xlgmac_mmc_read(pdata, MMC_TX128TO255OCTETS_GB_LO); + + stats->tx256to511octets_gb += + xlgmac_mmc_read(pdata, MMC_TX256TO511OCTETS_GB_LO); + + stats->tx512to1023octets_gb += + xlgmac_mmc_read(pdata, MMC_TX512TO1023OCTETS_GB_LO); + + stats->tx1024tomaxoctets_gb += + xlgmac_mmc_read(pdata, MMC_TX1024TOMAXOCTETS_GB_LO); + + stats->txunicastframes_gb += + xlgmac_mmc_read(pdata, MMC_TXUNICASTFRAMES_GB_LO); + + stats->txmulticastframes_gb += + xlgmac_mmc_read(pdata, MMC_TXMULTICASTFRAMES_GB_LO); + + stats->txbroadcastframes_g += + xlgmac_mmc_read(pdata, MMC_TXBROADCASTFRAMES_GB_LO); + + stats->txunderflowerror += + xlgmac_mmc_read(pdata, MMC_TXUNDERFLOWERROR_LO); + + stats->txoctetcount_g += + xlgmac_mmc_read(pdata, MMC_TXOCTETCOUNT_G_LO); + + stats->txframecount_g += + xlgmac_mmc_read(pdata, MMC_TXFRAMECOUNT_G_LO); + + stats->txpauseframes += + xlgmac_mmc_read(pdata, MMC_TXPAUSEFRAMES_LO); + + stats->txvlanframes_g += + xlgmac_mmc_read(pdata, MMC_TXVLANFRAMES_G_LO); + + stats->rxframecount_gb += + xlgmac_mmc_read(pdata, MMC_RXFRAMECOUNT_GB_LO); + + stats->rxoctetcount_gb += + xlgmac_mmc_read(pdata, MMC_RXOCTETCOUNT_GB_LO); + + stats->rxoctetcount_g += + xlgmac_mmc_read(pdata, MMC_RXOCTETCOUNT_G_LO); + + stats->rxbroadcastframes_g += + xlgmac_mmc_read(pdata, MMC_RXBROADCASTFRAMES_G_LO); + + stats->rxmulticastframes_g += + xlgmac_mmc_read(pdata, MMC_RXMULTICASTFRAMES_G_LO); + + stats->rxcrcerror += + xlgmac_mmc_read(pdata, MMC_RXCRCERROR_LO); + + stats->rxrunterror += + xlgmac_mmc_read(pdata, MMC_RXRUNTERROR); + + stats->rxjabbererror += + xlgmac_mmc_read(pdata, MMC_RXJABBERERROR); + + stats->rxundersize_g += + xlgmac_mmc_read(pdata, MMC_RXUNDERSIZE_G); + + stats->rxoversize_g += + xlgmac_mmc_read(pdata, MMC_RXOVERSIZE_G); + + stats->rx64octets_gb += + xlgmac_mmc_read(pdata, MMC_RX64OCTETS_GB_LO); + + stats->rx65to127octets_gb += + xlgmac_mmc_read(pdata, MMC_RX65TO127OCTETS_GB_LO); + + stats->rx128to255octets_gb += + xlgmac_mmc_read(pdata, MMC_RX128TO255OCTETS_GB_LO); + + stats->rx256to511octets_gb += + xlgmac_mmc_read(pdata, MMC_RX256TO511OCTETS_GB_LO); + + stats->rx512to1023octets_gb += + xlgmac_mmc_read(pdata, MMC_RX512TO1023OCTETS_GB_LO); + + stats->rx1024tomaxoctets_gb += + xlgmac_mmc_read(pdata, MMC_RX1024TOMAXOCTETS_GB_LO); + + stats->rxunicastframes_g += + xlgmac_mmc_read(pdata, MMC_RXUNICASTFRAMES_G_LO); + + stats->rxlengtherror += + xlgmac_mmc_read(pdata, MMC_RXLENGTHERROR_LO); + + stats->rxoutofrangetype += + xlgmac_mmc_read(pdata, MMC_RXOUTOFRANGETYPE_LO); + + stats->rxpauseframes += + xlgmac_mmc_read(pdata, MMC_RXPAUSEFRAMES_LO); + + stats->rxfifooverflow += + xlgmac_mmc_read(pdata, MMC_RXFIFOOVERFLOW_LO); + + stats->rxvlanframes_gb += + xlgmac_mmc_read(pdata, MMC_RXVLANFRAMES_GB_LO); + + stats->rxwatchdogerror += + xlgmac_mmc_read(pdata, MMC_RXWATCHDOGERROR); + + /* Un-freeze counters */ + regval = readl(pdata->mac_regs + MMC_CR); + regval = XLGMAC_SET_REG_BITS(regval, MMC_CR_MCF_POS, + MMC_CR_MCF_LEN, 0); + writel(regval, pdata->mac_regs + MMC_CR); +} + +static void xlgmac_config_mmc(struct xlgmac_pdata *pdata) +{ + u32 regval; + + regval = readl(pdata->mac_regs + MMC_CR); + /* Set counters to reset on read */ + regval = XLGMAC_SET_REG_BITS(regval, MMC_CR_ROR_POS, + MMC_CR_ROR_LEN, 1); + /* Reset the counters */ + regval = XLGMAC_SET_REG_BITS(regval, MMC_CR_CR_POS, + MMC_CR_CR_LEN, 1); + writel(regval, pdata->mac_regs + MMC_CR); +} + +static int xlgmac_write_rss_reg(struct xlgmac_pdata *pdata, unsigned int type, + unsigned int index, unsigned int val) +{ + unsigned int wait; + int ret = 0; + u32 regval; + + mutex_lock(&pdata->rss_mutex); + + regval = XLGMAC_GET_REG_BITS(readl(pdata->mac_regs + MAC_RSSAR), + MAC_RSSAR_OB_POS, MAC_RSSAR_OB_LEN); + if (regval) { + ret = -EBUSY; + goto unlock; + } + + writel(val, pdata->mac_regs + MAC_RSSDR); + + regval = readl(pdata->mac_regs + MAC_RSSAR); + regval = XLGMAC_SET_REG_BITS(regval, MAC_RSSAR_RSSIA_POS, + MAC_RSSAR_RSSIA_LEN, index); + regval = XLGMAC_SET_REG_BITS(regval, MAC_RSSAR_ADDRT_POS, + MAC_RSSAR_ADDRT_LEN, type); + regval = XLGMAC_SET_REG_BITS(regval, MAC_RSSAR_CT_POS, + MAC_RSSAR_CT_LEN, 0); + regval = XLGMAC_SET_REG_BITS(regval, MAC_RSSAR_OB_POS, + MAC_RSSAR_OB_LEN, 1); + writel(regval, pdata->mac_regs + MAC_RSSAR); + + wait = 1000; + while (wait--) { + regval = XLGMAC_GET_REG_BITS(readl(pdata->mac_regs + MAC_RSSAR), + MAC_RSSAR_OB_POS, + MAC_RSSAR_OB_LEN); + if (!regval) + goto unlock; + + usleep_range(1000, 1500); + } + + ret = -EBUSY; + +unlock: + mutex_unlock(&pdata->rss_mutex); + + return ret; +} + +static int xlgmac_write_rss_hash_key(struct xlgmac_pdata *pdata) +{ + unsigned int key_regs = sizeof(pdata->rss_key) / sizeof(u32); + unsigned int *key = (unsigned int *)&pdata->rss_key; + int ret; + + while (key_regs--) { + ret = xlgmac_write_rss_reg(pdata, XLGMAC_RSS_HASH_KEY_TYPE, + key_regs, *key++); + if (ret) + return ret; + } + + return 0; +} + +static int xlgmac_write_rss_lookup_table(struct xlgmac_pdata *pdata) +{ + unsigned int i; + int ret; + + for (i = 0; i < ARRAY_SIZE(pdata->rss_table); i++) { + ret = xlgmac_write_rss_reg(pdata, + XLGMAC_RSS_LOOKUP_TABLE_TYPE, i, + pdata->rss_table[i]); + if (ret) + return ret; + } + + return 0; +} + +static int xlgmac_set_rss_hash_key(struct xlgmac_pdata *pdata, const u8 *key) +{ + memcpy(pdata->rss_key, key, sizeof(pdata->rss_key)); + + return xlgmac_write_rss_hash_key(pdata); +} + +static int xlgmac_set_rss_lookup_table(struct xlgmac_pdata *pdata, + const u32 *table) +{ + unsigned int i; + u32 tval; + + for (i = 0; i < ARRAY_SIZE(pdata->rss_table); i++) { + tval = table[i]; + pdata->rss_table[i] = XLGMAC_SET_REG_BITS( + pdata->rss_table[i], + MAC_RSSDR_DMCH_POS, + MAC_RSSDR_DMCH_LEN, + tval); + } + + return xlgmac_write_rss_lookup_table(pdata); +} + +static int xlgmac_enable_rss(struct xlgmac_pdata *pdata) +{ + u32 regval; + int ret; + + if (!pdata->hw_feat.rss) + return -EOPNOTSUPP; + + /* Program the hash key */ + ret = xlgmac_write_rss_hash_key(pdata); + if (ret) + return ret; + + /* Program the lookup table */ + ret = xlgmac_write_rss_lookup_table(pdata); + if (ret) + return ret; + + /* Set the RSS options */ + writel(pdata->rss_options, pdata->mac_regs + MAC_RSSCR); + + /* Enable RSS */ + regval = readl(pdata->mac_regs + MAC_RSSCR); + regval = XLGMAC_SET_REG_BITS(regval, MAC_RSSCR_RSSE_POS, + MAC_RSSCR_RSSE_LEN, 1); + writel(regval, pdata->mac_regs + MAC_RSSCR); + + return 0; +} + +static int xlgmac_disable_rss(struct xlgmac_pdata *pdata) +{ + u32 regval; + + if (!pdata->hw_feat.rss) + return -EOPNOTSUPP; + + regval = readl(pdata->mac_regs + MAC_RSSCR); + regval = XLGMAC_SET_REG_BITS(regval, MAC_RSSCR_RSSE_POS, + MAC_RSSCR_RSSE_LEN, 0); + writel(regval, pdata->mac_regs + MAC_RSSCR); + + return 0; +} + +static void xlgmac_config_rss(struct xlgmac_pdata *pdata) +{ + int ret; + + if (!pdata->hw_feat.rss) + return; + + if (pdata->netdev->features & NETIF_F_RXHASH) + ret = xlgmac_enable_rss(pdata); + else + ret = xlgmac_disable_rss(pdata); + + if (ret) + netdev_err(pdata->netdev, + "error configuring RSS, RSS disabled\n"); +} + +static void xlgmac_enable_dma_interrupts(struct xlgmac_pdata *pdata) +{ + unsigned int dma_ch_isr, dma_ch_ier; + struct xlgmac_channel *channel; + unsigned int i; + + channel = pdata->channel_head; + for (i = 0; i < pdata->channel_count; i++, channel++) { + /* Clear all the interrupts which are set */ + dma_ch_isr = readl(XLGMAC_DMA_REG(channel, DMA_CH_SR)); + writel(dma_ch_isr, XLGMAC_DMA_REG(channel, DMA_CH_SR)); + + /* Clear all interrupt enable bits */ + dma_ch_ier = 0; + + /* Enable following interrupts + * NIE - Normal Interrupt Summary Enable + * AIE - Abnormal Interrupt Summary Enable + * FBEE - Fatal Bus Error Enable + */ + dma_ch_ier = XLGMAC_SET_REG_BITS(dma_ch_ier, + DMA_CH_IER_NIE_POS, + DMA_CH_IER_NIE_LEN, 1); + dma_ch_ier = XLGMAC_SET_REG_BITS(dma_ch_ier, + DMA_CH_IER_AIE_POS, + DMA_CH_IER_AIE_LEN, 1); + dma_ch_ier = XLGMAC_SET_REG_BITS(dma_ch_ier, + DMA_CH_IER_FBEE_POS, + DMA_CH_IER_FBEE_LEN, 1); + + if (channel->tx_ring) { + /* Enable the following Tx interrupts + * TIE - Transmit Interrupt Enable (unless using + * per channel interrupts) + */ + if (!pdata->per_channel_irq) + dma_ch_ier = XLGMAC_SET_REG_BITS( + dma_ch_ier, + DMA_CH_IER_TIE_POS, + DMA_CH_IER_TIE_LEN, + 1); + } + if (channel->rx_ring) { + /* Enable following Rx interrupts + * RBUE - Receive Buffer Unavailable Enable + * RIE - Receive Interrupt Enable (unless using + * per channel interrupts) + */ + dma_ch_ier = XLGMAC_SET_REG_BITS( + dma_ch_ier, + DMA_CH_IER_RBUE_POS, + DMA_CH_IER_RBUE_LEN, + 1); + if (!pdata->per_channel_irq) + dma_ch_ier = XLGMAC_SET_REG_BITS( + dma_ch_ier, + DMA_CH_IER_RIE_POS, + DMA_CH_IER_RIE_LEN, + 1); + } + + writel(dma_ch_isr, XLGMAC_DMA_REG(channel, DMA_CH_IER)); + } +} + +static void xlgmac_enable_mtl_interrupts(struct xlgmac_pdata *pdata) +{ + unsigned int q_count, i; + unsigned int mtl_q_isr; + + q_count = max(pdata->hw_feat.tx_q_cnt, pdata->hw_feat.rx_q_cnt); + for (i = 0; i < q_count; i++) { + /* Clear all the interrupts which are set */ + mtl_q_isr = readl(XLGMAC_MTL_REG(pdata, i, MTL_Q_ISR)); + writel(mtl_q_isr, XLGMAC_MTL_REG(pdata, i, MTL_Q_ISR)); + + /* No MTL interrupts to be enabled */ + writel(0, XLGMAC_MTL_REG(pdata, i, MTL_Q_IER)); + } +} + +static void xlgmac_enable_mac_interrupts(struct xlgmac_pdata *pdata) +{ + unsigned int mac_ier = 0; + u32 regval; + + /* Enable Timestamp interrupt */ + mac_ier = XLGMAC_SET_REG_BITS(mac_ier, MAC_IER_TSIE_POS, + MAC_IER_TSIE_LEN, 1); + + writel(mac_ier, pdata->mac_regs + MAC_IER); + + /* Enable all counter interrupts */ + regval = readl(pdata->mac_regs + MMC_RIER); + regval = XLGMAC_SET_REG_BITS(regval, MMC_RIER_ALL_INTERRUPTS_POS, + MMC_RIER_ALL_INTERRUPTS_LEN, 0xffffffff); + writel(regval, pdata->mac_regs + MMC_RIER); + regval = readl(pdata->mac_regs + MMC_TIER); + regval = XLGMAC_SET_REG_BITS(regval, MMC_TIER_ALL_INTERRUPTS_POS, + MMC_TIER_ALL_INTERRUPTS_LEN, 0xffffffff); + writel(regval, pdata->mac_regs + MMC_TIER); +} + +static int xlgmac_set_xlgmii_25000_speed(struct xlgmac_pdata *pdata) +{ + u32 regval; + + regval = XLGMAC_GET_REG_BITS(readl(pdata->mac_regs + MAC_TCR), + MAC_TCR_SS_POS, MAC_TCR_SS_LEN); + if (regval == 0x1) + return 0; + + regval = readl(pdata->mac_regs + MAC_TCR); + regval = XLGMAC_SET_REG_BITS(regval, MAC_TCR_SS_POS, + MAC_TCR_SS_LEN, 0x1); + writel(regval, pdata->mac_regs + MAC_TCR); + + return 0; +} + +static int xlgmac_set_xlgmii_40000_speed(struct xlgmac_pdata *pdata) +{ + u32 regval; + + regval = XLGMAC_GET_REG_BITS(readl(pdata->mac_regs + MAC_TCR), + MAC_TCR_SS_POS, MAC_TCR_SS_LEN); + if (regval == 0) + return 0; + + regval = readl(pdata->mac_regs + MAC_TCR); + regval = XLGMAC_SET_REG_BITS(regval, MAC_TCR_SS_POS, + MAC_TCR_SS_LEN, 0); + writel(regval, pdata->mac_regs + MAC_TCR); + + return 0; +} + +static int xlgmac_set_xlgmii_50000_speed(struct xlgmac_pdata *pdata) +{ + u32 regval; + + regval = XLGMAC_GET_REG_BITS(readl(pdata->mac_regs + MAC_TCR), + MAC_TCR_SS_POS, MAC_TCR_SS_LEN); + if (regval == 0x2) + return 0; + + regval = readl(pdata->mac_regs + MAC_TCR); + regval = XLGMAC_SET_REG_BITS(regval, MAC_TCR_SS_POS, + MAC_TCR_SS_LEN, 0x2); + writel(regval, pdata->mac_regs + MAC_TCR); + + return 0; +} + +static int xlgmac_set_xlgmii_100000_speed(struct xlgmac_pdata *pdata) +{ + u32 regval; + + regval = XLGMAC_GET_REG_BITS(readl(pdata->mac_regs + MAC_TCR), + MAC_TCR_SS_POS, MAC_TCR_SS_LEN); + if (regval == 0x3) + return 0; + + regval = readl(pdata->mac_regs + MAC_TCR); + regval = XLGMAC_SET_REG_BITS(regval, MAC_TCR_SS_POS, + MAC_TCR_SS_LEN, 0x3); + writel(regval, pdata->mac_regs + MAC_TCR); + + return 0; +} + +static void xlgmac_config_mac_speed(struct xlgmac_pdata *pdata) +{ + switch (pdata->phy_speed) { + case SPEED_100000: + xlgmac_set_xlgmii_100000_speed(pdata); + break; + + case SPEED_50000: + xlgmac_set_xlgmii_50000_speed(pdata); + break; + + case SPEED_40000: + xlgmac_set_xlgmii_40000_speed(pdata); + break; + + case SPEED_25000: + xlgmac_set_xlgmii_25000_speed(pdata); + break; + } +} + +static int xlgmac_dev_read(struct xlgmac_channel *channel) +{ + struct xlgmac_pdata *pdata = channel->pdata; + struct xlgmac_ring *ring = channel->rx_ring; + struct net_device *netdev = pdata->netdev; + struct xlgmac_desc_data *desc_data; + struct xlgmac_dma_desc *dma_desc; + struct xlgmac_pkt_info *pkt_info; + unsigned int err, etlt, l34t; + + desc_data = XLGMAC_GET_DESC_DATA(ring, ring->cur); + dma_desc = desc_data->dma_desc; + pkt_info = &ring->pkt_info; + + /* Check for data availability */ + if (XLGMAC_GET_REG_BITS_LE(dma_desc->desc3, + RX_NORMAL_DESC3_OWN_POS, + RX_NORMAL_DESC3_OWN_LEN)) + return 1; + + /* Make sure descriptor fields are read after reading the OWN bit */ + dma_rmb(); + + if (netif_msg_rx_status(pdata)) + xlgmac_dump_rx_desc(pdata, ring, ring->cur); + + if (XLGMAC_GET_REG_BITS_LE(dma_desc->desc3, + RX_NORMAL_DESC3_CTXT_POS, + RX_NORMAL_DESC3_CTXT_LEN)) { + /* Timestamp Context Descriptor */ + xlgmac_get_rx_tstamp(pkt_info, dma_desc); + + pkt_info->attributes = XLGMAC_SET_REG_BITS( + pkt_info->attributes, + RX_PACKET_ATTRIBUTES_CONTEXT_POS, + RX_PACKET_ATTRIBUTES_CONTEXT_LEN, + 1); + pkt_info->attributes = XLGMAC_SET_REG_BITS( + pkt_info->attributes, + RX_PACKET_ATTRIBUTES_CONTEXT_NEXT_POS, + RX_PACKET_ATTRIBUTES_CONTEXT_NEXT_LEN, + 0); + return 0; + } + + /* Normal Descriptor, be sure Context Descriptor bit is off */ + pkt_info->attributes = XLGMAC_SET_REG_BITS( + pkt_info->attributes, + RX_PACKET_ATTRIBUTES_CONTEXT_POS, + RX_PACKET_ATTRIBUTES_CONTEXT_LEN, + 0); + + /* Indicate if a Context Descriptor is next */ + if (XLGMAC_GET_REG_BITS_LE(dma_desc->desc3, + RX_NORMAL_DESC3_CDA_POS, + RX_NORMAL_DESC3_CDA_LEN)) + pkt_info->attributes = XLGMAC_SET_REG_BITS( + pkt_info->attributes, + RX_PACKET_ATTRIBUTES_CONTEXT_NEXT_POS, + RX_PACKET_ATTRIBUTES_CONTEXT_NEXT_LEN, + 1); + + /* Get the header length */ + if (XLGMAC_GET_REG_BITS_LE(dma_desc->desc3, + RX_NORMAL_DESC3_FD_POS, + RX_NORMAL_DESC3_FD_LEN)) { + desc_data->rx.hdr_len = XLGMAC_GET_REG_BITS_LE(dma_desc->desc2, + RX_NORMAL_DESC2_HL_POS, + RX_NORMAL_DESC2_HL_LEN); + if (desc_data->rx.hdr_len) + pdata->stats.rx_split_header_packets++; + } + + /* Get the RSS hash */ + if (XLGMAC_GET_REG_BITS_LE(dma_desc->desc3, + RX_NORMAL_DESC3_RSV_POS, + RX_NORMAL_DESC3_RSV_LEN)) { + pkt_info->attributes = XLGMAC_SET_REG_BITS( + pkt_info->attributes, + RX_PACKET_ATTRIBUTES_RSS_HASH_POS, + RX_PACKET_ATTRIBUTES_RSS_HASH_LEN, + 1); + + pkt_info->rss_hash = le32_to_cpu(dma_desc->desc1); + + l34t = XLGMAC_GET_REG_BITS_LE(dma_desc->desc3, + RX_NORMAL_DESC3_L34T_POS, + RX_NORMAL_DESC3_L34T_LEN); + switch (l34t) { + case RX_DESC3_L34T_IPV4_TCP: + case RX_DESC3_L34T_IPV4_UDP: + case RX_DESC3_L34T_IPV6_TCP: + case RX_DESC3_L34T_IPV6_UDP: + pkt_info->rss_hash_type = PKT_HASH_TYPE_L4; + break; + default: + pkt_info->rss_hash_type = PKT_HASH_TYPE_L3; + } + } + + /* Get the pkt_info length */ + desc_data->rx.len = XLGMAC_GET_REG_BITS_LE(dma_desc->desc3, + RX_NORMAL_DESC3_PL_POS, + RX_NORMAL_DESC3_PL_LEN); + + if (!XLGMAC_GET_REG_BITS_LE(dma_desc->desc3, + RX_NORMAL_DESC3_LD_POS, + RX_NORMAL_DESC3_LD_LEN)) { + /* Not all the data has been transferred for this pkt_info */ + pkt_info->attributes = XLGMAC_SET_REG_BITS( + pkt_info->attributes, + RX_PACKET_ATTRIBUTES_INCOMPLETE_POS, + RX_PACKET_ATTRIBUTES_INCOMPLETE_LEN, + 1); + return 0; + } + + /* This is the last of the data for this pkt_info */ + pkt_info->attributes = XLGMAC_SET_REG_BITS( + pkt_info->attributes, + RX_PACKET_ATTRIBUTES_INCOMPLETE_POS, + RX_PACKET_ATTRIBUTES_INCOMPLETE_LEN, + 0); + + /* Set checksum done indicator as appropriate */ + if (netdev->features & NETIF_F_RXCSUM) + pkt_info->attributes = XLGMAC_SET_REG_BITS( + pkt_info->attributes, + RX_PACKET_ATTRIBUTES_CSUM_DONE_POS, + RX_PACKET_ATTRIBUTES_CSUM_DONE_LEN, + 1); + + /* Check for errors (only valid in last descriptor) */ + err = XLGMAC_GET_REG_BITS_LE(dma_desc->desc3, + RX_NORMAL_DESC3_ES_POS, + RX_NORMAL_DESC3_ES_LEN); + etlt = XLGMAC_GET_REG_BITS_LE(dma_desc->desc3, + RX_NORMAL_DESC3_ETLT_POS, + RX_NORMAL_DESC3_ETLT_LEN); + netif_dbg(pdata, rx_status, netdev, "err=%u, etlt=%#x\n", err, etlt); + + if (!err || !etlt) { + /* No error if err is 0 or etlt is 0 */ + if ((etlt == 0x09) && + (netdev->features & NETIF_F_HW_VLAN_CTAG_RX)) { + pkt_info->attributes = XLGMAC_SET_REG_BITS( + pkt_info->attributes, + RX_PACKET_ATTRIBUTES_VLAN_CTAG_POS, + RX_PACKET_ATTRIBUTES_VLAN_CTAG_LEN, + 1); + pkt_info->vlan_ctag = + XLGMAC_GET_REG_BITS_LE(dma_desc->desc0, + RX_NORMAL_DESC0_OVT_POS, + RX_NORMAL_DESC0_OVT_LEN); + netif_dbg(pdata, rx_status, netdev, "vlan-ctag=%#06x\n", + pkt_info->vlan_ctag); + } + } else { + if ((etlt == 0x05) || (etlt == 0x06)) + pkt_info->attributes = XLGMAC_SET_REG_BITS( + pkt_info->attributes, + RX_PACKET_ATTRIBUTES_CSUM_DONE_POS, + RX_PACKET_ATTRIBUTES_CSUM_DONE_LEN, + 0); + else + pkt_info->errors = XLGMAC_SET_REG_BITS( + pkt_info->errors, + RX_PACKET_ERRORS_FRAME_POS, + RX_PACKET_ERRORS_FRAME_LEN, + 1); + } + + XLGMAC_PR("%s - descriptor=%u (cur=%d)\n", channel->name, + ring->cur & (ring->dma_desc_count - 1), ring->cur); + + return 0; +} + +static int xlgmac_enable_int(struct xlgmac_channel *channel, + enum xlgmac_int int_id) +{ + unsigned int dma_ch_ier; + + dma_ch_ier = readl(XLGMAC_DMA_REG(channel, DMA_CH_IER)); + + switch (int_id) { + case XLGMAC_INT_DMA_CH_SR_TI: + dma_ch_ier = XLGMAC_SET_REG_BITS( + dma_ch_ier, DMA_CH_IER_TIE_POS, + DMA_CH_IER_TIE_LEN, 1); + break; + case XLGMAC_INT_DMA_CH_SR_TPS: + dma_ch_ier = XLGMAC_SET_REG_BITS( + dma_ch_ier, DMA_CH_IER_TXSE_POS, + DMA_CH_IER_TXSE_LEN, 1); + break; + case XLGMAC_INT_DMA_CH_SR_TBU: + dma_ch_ier = XLGMAC_SET_REG_BITS( + dma_ch_ier, DMA_CH_IER_TBUE_POS, + DMA_CH_IER_TBUE_LEN, 1); + break; + case XLGMAC_INT_DMA_CH_SR_RI: + dma_ch_ier = XLGMAC_SET_REG_BITS( + dma_ch_ier, DMA_CH_IER_RIE_POS, + DMA_CH_IER_RIE_LEN, 1); + break; + case XLGMAC_INT_DMA_CH_SR_RBU: + dma_ch_ier = XLGMAC_SET_REG_BITS( + dma_ch_ier, DMA_CH_IER_RBUE_POS, + DMA_CH_IER_RBUE_LEN, 1); + break; + case XLGMAC_INT_DMA_CH_SR_RPS: + dma_ch_ier = XLGMAC_SET_REG_BITS( + dma_ch_ier, DMA_CH_IER_RSE_POS, + DMA_CH_IER_RSE_LEN, 1); + break; + case XLGMAC_INT_DMA_CH_SR_TI_RI: + dma_ch_ier = XLGMAC_SET_REG_BITS( + dma_ch_ier, DMA_CH_IER_TIE_POS, + DMA_CH_IER_TIE_LEN, 1); + dma_ch_ier = XLGMAC_SET_REG_BITS( + dma_ch_ier, DMA_CH_IER_RIE_POS, + DMA_CH_IER_RIE_LEN, 1); + break; + case XLGMAC_INT_DMA_CH_SR_FBE: + dma_ch_ier = XLGMAC_SET_REG_BITS( + dma_ch_ier, DMA_CH_IER_FBEE_POS, + DMA_CH_IER_FBEE_LEN, 1); + break; + case XLGMAC_INT_DMA_ALL: + dma_ch_ier |= channel->saved_ier; + break; + default: + return -1; + } + + writel(dma_ch_ier, XLGMAC_DMA_REG(channel, DMA_CH_IER)); + + return 0; +} + +static int xlgmac_disable_int(struct xlgmac_channel *channel, + enum xlgmac_int int_id) +{ + unsigned int dma_ch_ier; + + dma_ch_ier = readl(XLGMAC_DMA_REG(channel, DMA_CH_IER)); + + switch (int_id) { + case XLGMAC_INT_DMA_CH_SR_TI: + dma_ch_ier = XLGMAC_SET_REG_BITS( + dma_ch_ier, DMA_CH_IER_TIE_POS, + DMA_CH_IER_TIE_LEN, 0); + break; + case XLGMAC_INT_DMA_CH_SR_TPS: + dma_ch_ier = XLGMAC_SET_REG_BITS( + dma_ch_ier, DMA_CH_IER_TXSE_POS, + DMA_CH_IER_TXSE_LEN, 0); + break; + case XLGMAC_INT_DMA_CH_SR_TBU: + dma_ch_ier = XLGMAC_SET_REG_BITS( + dma_ch_ier, DMA_CH_IER_TBUE_POS, + DMA_CH_IER_TBUE_LEN, 0); + break; + case XLGMAC_INT_DMA_CH_SR_RI: + dma_ch_ier = XLGMAC_SET_REG_BITS( + dma_ch_ier, DMA_CH_IER_RIE_POS, + DMA_CH_IER_RIE_LEN, 0); + break; + case XLGMAC_INT_DMA_CH_SR_RBU: + dma_ch_ier = XLGMAC_SET_REG_BITS( + dma_ch_ier, DMA_CH_IER_RBUE_POS, + DMA_CH_IER_RBUE_LEN, 0); + break; + case XLGMAC_INT_DMA_CH_SR_RPS: + dma_ch_ier = XLGMAC_SET_REG_BITS( + dma_ch_ier, DMA_CH_IER_RSE_POS, + DMA_CH_IER_RSE_LEN, 0); + break; + case XLGMAC_INT_DMA_CH_SR_TI_RI: + dma_ch_ier = XLGMAC_SET_REG_BITS( + dma_ch_ier, DMA_CH_IER_TIE_POS, + DMA_CH_IER_TIE_LEN, 0); + dma_ch_ier = XLGMAC_SET_REG_BITS( + dma_ch_ier, DMA_CH_IER_RIE_POS, + DMA_CH_IER_RIE_LEN, 0); + break; + case XLGMAC_INT_DMA_CH_SR_FBE: + dma_ch_ier = XLGMAC_SET_REG_BITS( + dma_ch_ier, DMA_CH_IER_FBEE_POS, + DMA_CH_IER_FBEE_LEN, 0); + break; + case XLGMAC_INT_DMA_ALL: + channel->saved_ier = dma_ch_ier & XLGMAC_DMA_INTERRUPT_MASK; + dma_ch_ier &= ~XLGMAC_DMA_INTERRUPT_MASK; + break; + default: + return -1; + } + + writel(dma_ch_ier, XLGMAC_DMA_REG(channel, DMA_CH_IER)); + + return 0; +} + +static int xlgmac_flush_tx_queues(struct xlgmac_pdata *pdata) +{ + unsigned int i, count; + u32 regval; + + for (i = 0; i < pdata->tx_q_count; i++) { + regval = readl(XLGMAC_MTL_REG(pdata, i, MTL_Q_TQOMR)); + regval = XLGMAC_SET_REG_BITS(regval, MTL_Q_TQOMR_FTQ_POS, + MTL_Q_TQOMR_FTQ_LEN, 1); + writel(regval, XLGMAC_MTL_REG(pdata, i, MTL_Q_TQOMR)); + } + + /* Poll Until Poll Condition */ + for (i = 0; i < pdata->tx_q_count; i++) { + count = 2000; + regval = readl(XLGMAC_MTL_REG(pdata, i, MTL_Q_TQOMR)); + regval = XLGMAC_GET_REG_BITS(regval, MTL_Q_TQOMR_FTQ_POS, + MTL_Q_TQOMR_FTQ_LEN); + while (--count && regval) + usleep_range(500, 600); + + if (!count) + return -EBUSY; + } + + return 0; +} + +static void xlgmac_config_dma_bus(struct xlgmac_pdata *pdata) +{ + u32 regval; + + regval = readl(pdata->mac_regs + DMA_SBMR); + /* Set enhanced addressing mode */ + regval = XLGMAC_SET_REG_BITS(regval, DMA_SBMR_EAME_POS, + DMA_SBMR_EAME_LEN, 1); + /* Set the System Bus mode */ + regval = XLGMAC_SET_REG_BITS(regval, DMA_SBMR_UNDEF_POS, + DMA_SBMR_UNDEF_LEN, 1); + regval = XLGMAC_SET_REG_BITS(regval, DMA_SBMR_BLEN_256_POS, + DMA_SBMR_BLEN_256_LEN, 1); + writel(regval, pdata->mac_regs + DMA_SBMR); +} + +static int xlgmac_hw_init(struct xlgmac_pdata *pdata) +{ + struct xlgmac_desc_ops *desc_ops = &pdata->desc_ops; + int ret; + + /* Flush Tx queues */ + ret = xlgmac_flush_tx_queues(pdata); + if (ret) + return ret; + + /* Initialize DMA related features */ + xlgmac_config_dma_bus(pdata); + xlgmac_config_osp_mode(pdata); + xlgmac_config_pblx8(pdata); + xlgmac_config_tx_pbl_val(pdata); + xlgmac_config_rx_pbl_val(pdata); + xlgmac_config_rx_coalesce(pdata); + xlgmac_config_tx_coalesce(pdata); + xlgmac_config_rx_buffer_size(pdata); + xlgmac_config_tso_mode(pdata); + xlgmac_config_sph_mode(pdata); + xlgmac_config_rss(pdata); + desc_ops->tx_desc_init(pdata); + desc_ops->rx_desc_init(pdata); + xlgmac_enable_dma_interrupts(pdata); + + /* Initialize MTL related features */ + xlgmac_config_mtl_mode(pdata); + xlgmac_config_queue_mapping(pdata); + xlgmac_config_tsf_mode(pdata, pdata->tx_sf_mode); + xlgmac_config_rsf_mode(pdata, pdata->rx_sf_mode); + xlgmac_config_tx_threshold(pdata, pdata->tx_threshold); + xlgmac_config_rx_threshold(pdata, pdata->rx_threshold); + xlgmac_config_tx_fifo_size(pdata); + xlgmac_config_rx_fifo_size(pdata); + xlgmac_config_flow_control_threshold(pdata); + xlgmac_config_rx_fep_enable(pdata); + xlgmac_config_rx_fup_enable(pdata); + xlgmac_enable_mtl_interrupts(pdata); + + /* Initialize MAC related features */ + xlgmac_config_mac_address(pdata); + xlgmac_config_rx_mode(pdata); + xlgmac_config_jumbo_enable(pdata); + xlgmac_config_flow_control(pdata); + xlgmac_config_mac_speed(pdata); + xlgmac_config_checksum_offload(pdata); + xlgmac_config_vlan_support(pdata); + xlgmac_config_mmc(pdata); + xlgmac_enable_mac_interrupts(pdata); + + return 0; +} + +static int xlgmac_hw_exit(struct xlgmac_pdata *pdata) +{ + unsigned int count = 2000; + u32 regval; + + /* Issue a software reset */ + regval = readl(pdata->mac_regs + DMA_MR); + regval = XLGMAC_SET_REG_BITS(regval, DMA_MR_SWR_POS, + DMA_MR_SWR_LEN, 1); + writel(regval, pdata->mac_regs + DMA_MR); + usleep_range(10, 15); + + /* Poll Until Poll Condition */ + while (--count && + XLGMAC_GET_REG_BITS(readl(pdata->mac_regs + DMA_MR), + DMA_MR_SWR_POS, DMA_MR_SWR_LEN)) + usleep_range(500, 600); + + if (!count) + return -EBUSY; + + return 0; +} + +void xlgmac_init_hw_ops(struct xlgmac_hw_ops *hw_ops) +{ + hw_ops->init = xlgmac_hw_init; + hw_ops->exit = xlgmac_hw_exit; + + hw_ops->tx_complete = xlgmac_tx_complete; + + hw_ops->enable_tx = xlgmac_enable_tx; + hw_ops->disable_tx = xlgmac_disable_tx; + hw_ops->enable_rx = xlgmac_enable_rx; + hw_ops->disable_rx = xlgmac_disable_rx; + + hw_ops->dev_xmit = xlgmac_dev_xmit; + hw_ops->dev_read = xlgmac_dev_read; + hw_ops->enable_int = xlgmac_enable_int; + hw_ops->disable_int = xlgmac_disable_int; + + hw_ops->set_mac_address = xlgmac_set_mac_address; + hw_ops->config_rx_mode = xlgmac_config_rx_mode; + hw_ops->enable_rx_csum = xlgmac_enable_rx_csum; + hw_ops->disable_rx_csum = xlgmac_disable_rx_csum; + + /* For MII speed configuration */ + hw_ops->set_xlgmii_25000_speed = xlgmac_set_xlgmii_25000_speed; + hw_ops->set_xlgmii_40000_speed = xlgmac_set_xlgmii_40000_speed; + hw_ops->set_xlgmii_50000_speed = xlgmac_set_xlgmii_50000_speed; + hw_ops->set_xlgmii_100000_speed = xlgmac_set_xlgmii_100000_speed; + + /* For descriptor related operation */ + hw_ops->tx_desc_init = xlgmac_tx_desc_init; + hw_ops->rx_desc_init = xlgmac_rx_desc_init; + hw_ops->tx_desc_reset = xlgmac_tx_desc_reset; + hw_ops->rx_desc_reset = xlgmac_rx_desc_reset; + hw_ops->is_last_desc = xlgmac_is_last_desc; + hw_ops->is_context_desc = xlgmac_is_context_desc; + hw_ops->tx_start_xmit = xlgmac_tx_start_xmit; + + /* For Flow Control */ + hw_ops->config_tx_flow_control = xlgmac_config_tx_flow_control; + hw_ops->config_rx_flow_control = xlgmac_config_rx_flow_control; + + /* For Vlan related config */ + hw_ops->enable_rx_vlan_stripping = xlgmac_enable_rx_vlan_stripping; + hw_ops->disable_rx_vlan_stripping = xlgmac_disable_rx_vlan_stripping; + hw_ops->enable_rx_vlan_filtering = xlgmac_enable_rx_vlan_filtering; + hw_ops->disable_rx_vlan_filtering = xlgmac_disable_rx_vlan_filtering; + hw_ops->update_vlan_hash_table = xlgmac_update_vlan_hash_table; + + /* For RX coalescing */ + hw_ops->config_rx_coalesce = xlgmac_config_rx_coalesce; + hw_ops->config_tx_coalesce = xlgmac_config_tx_coalesce; + hw_ops->usec_to_riwt = xlgmac_usec_to_riwt; + hw_ops->riwt_to_usec = xlgmac_riwt_to_usec; + + /* For RX and TX threshold config */ + hw_ops->config_rx_threshold = xlgmac_config_rx_threshold; + hw_ops->config_tx_threshold = xlgmac_config_tx_threshold; + + /* For RX and TX Store and Forward Mode config */ + hw_ops->config_rsf_mode = xlgmac_config_rsf_mode; + hw_ops->config_tsf_mode = xlgmac_config_tsf_mode; + + /* For TX DMA Operating on Second Frame config */ + hw_ops->config_osp_mode = xlgmac_config_osp_mode; + + /* For RX and TX PBL config */ + hw_ops->config_rx_pbl_val = xlgmac_config_rx_pbl_val; + hw_ops->get_rx_pbl_val = xlgmac_get_rx_pbl_val; + hw_ops->config_tx_pbl_val = xlgmac_config_tx_pbl_val; + hw_ops->get_tx_pbl_val = xlgmac_get_tx_pbl_val; + hw_ops->config_pblx8 = xlgmac_config_pblx8; + + /* For MMC statistics support */ + hw_ops->tx_mmc_int = xlgmac_tx_mmc_int; + hw_ops->rx_mmc_int = xlgmac_rx_mmc_int; + hw_ops->read_mmc_stats = xlgmac_read_mmc_stats; + + /* For Receive Side Scaling */ + hw_ops->enable_rss = xlgmac_enable_rss; + hw_ops->disable_rss = xlgmac_disable_rss; + hw_ops->set_rss_hash_key = xlgmac_set_rss_hash_key; + hw_ops->set_rss_lookup_table = xlgmac_set_rss_lookup_table; +} diff --git a/drivers/net/ethernet/synopsys/dwc-xlgmac-net.c b/drivers/net/ethernet/synopsys/dwc-xlgmac-net.c new file mode 100644 index 000000000000..5e8428be3d66 --- /dev/null +++ b/drivers/net/ethernet/synopsys/dwc-xlgmac-net.c @@ -0,0 +1,1334 @@ +/* Synopsys DesignWare Core Enterprise Ethernet (XLGMAC) Driver + * + * Copyright (c) 2017 Synopsys, Inc. (www.synopsys.com) + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the + * Free Software Foundation; either version 2 of the License, or (at your + * option) any later version. + * + * This Synopsys DWC XLGMAC software driver and associated documentation + * (hereinafter the "Software") is an unsupported proprietary work of + * Synopsys, Inc. unless otherwise expressly agreed to in writing between + * Synopsys and you. The Software IS NOT an item of Licensed Software or a + * Licensed Product under any End User Software License Agreement or + * Agreement for Licensed Products with Synopsys or any supplement thereto. + * Synopsys is a registered trademark of Synopsys, Inc. Other names included + * in the SOFTWARE may be the trademarks of their respective owners. + */ + +#include <linux/netdevice.h> +#include <linux/tcp.h> + +#include "dwc-xlgmac.h" +#include "dwc-xlgmac-reg.h" + +static int xlgmac_one_poll(struct napi_struct *, int); +static int xlgmac_all_poll(struct napi_struct *, int); + +static inline unsigned int xlgmac_tx_avail_desc(struct xlgmac_ring *ring) +{ + return (ring->dma_desc_count - (ring->cur - ring->dirty)); +} + +static inline unsigned int xlgmac_rx_dirty_desc(struct xlgmac_ring *ring) +{ + return (ring->cur - ring->dirty); +} + +static int xlgmac_maybe_stop_tx_queue( + struct xlgmac_channel *channel, + struct xlgmac_ring *ring, + unsigned int count) +{ + struct xlgmac_pdata *pdata = channel->pdata; + + if (count > xlgmac_tx_avail_desc(ring)) { + netif_info(pdata, drv, pdata->netdev, + "Tx queue stopped, not enough descriptors available\n"); + netif_stop_subqueue(pdata->netdev, channel->queue_index); + ring->tx.queue_stopped = 1; + + /* If we haven't notified the hardware because of xmit_more + * support, tell it now + */ + if (ring->tx.xmit_more) + pdata->hw_ops.tx_start_xmit(channel, ring); + + return NETDEV_TX_BUSY; + } + + return 0; +} + +static void xlgmac_prep_vlan(struct sk_buff *skb, + struct xlgmac_pkt_info *pkt_info) +{ + if (skb_vlan_tag_present(skb)) + pkt_info->vlan_ctag = skb_vlan_tag_get(skb); +} + +static int xlgmac_prep_tso(struct sk_buff *skb, + struct xlgmac_pkt_info *pkt_info) +{ + int ret; + + if (!XLGMAC_GET_REG_BITS(pkt_info->attributes, + TX_PACKET_ATTRIBUTES_TSO_ENABLE_POS, + TX_PACKET_ATTRIBUTES_TSO_ENABLE_LEN)) + return 0; + + ret = skb_cow_head(skb, 0); + if (ret) + return ret; + + pkt_info->header_len = skb_transport_offset(skb) + tcp_hdrlen(skb); + pkt_info->tcp_header_len = tcp_hdrlen(skb); + pkt_info->tcp_payload_len = skb->len - pkt_info->header_len; + pkt_info->mss = skb_shinfo(skb)->gso_size; + + XLGMAC_PR("header_len=%u\n", pkt_info->header_len); + XLGMAC_PR("tcp_header_len=%u, tcp_payload_len=%u\n", + pkt_info->tcp_header_len, pkt_info->tcp_payload_len); + XLGMAC_PR("mss=%u\n", pkt_info->mss); + + /* Update the number of packets that will ultimately be transmitted + * along with the extra bytes for each extra packet + */ + pkt_info->tx_packets = skb_shinfo(skb)->gso_segs; + pkt_info->tx_bytes += (pkt_info->tx_packets - 1) * pkt_info->header_len; + + return 0; +} + +static int xlgmac_is_tso(struct sk_buff *skb) +{ + if (skb->ip_summed != CHECKSUM_PARTIAL) + return 0; + + if (!skb_is_gso(skb)) + return 0; + + return 1; +} + +static void xlgmac_prep_tx_pkt(struct xlgmac_pdata *pdata, + struct xlgmac_ring *ring, + struct sk_buff *skb, + struct xlgmac_pkt_info *pkt_info) +{ + struct skb_frag_struct *frag; + unsigned int context_desc; + unsigned int len; + unsigned int i; + + pkt_info->skb = skb; + + context_desc = 0; + pkt_info->desc_count = 0; + + pkt_info->tx_packets = 1; + pkt_info->tx_bytes = skb->len; + + if (xlgmac_is_tso(skb)) { + /* TSO requires an extra descriptor if mss is different */ + if (skb_shinfo(skb)->gso_size != ring->tx.cur_mss) { + context_desc = 1; + pkt_info->desc_count++; + } + + /* TSO requires an extra descriptor for TSO header */ + pkt_info->desc_count++; + + pkt_info->attributes = XLGMAC_SET_REG_BITS( + pkt_info->attributes, + TX_PACKET_ATTRIBUTES_TSO_ENABLE_POS, + TX_PACKET_ATTRIBUTES_TSO_ENABLE_LEN, + 1); + pkt_info->attributes = XLGMAC_SET_REG_BITS( + pkt_info->attributes, + TX_PACKET_ATTRIBUTES_CSUM_ENABLE_POS, + TX_PACKET_ATTRIBUTES_CSUM_ENABLE_LEN, + 1); + } else if (skb->ip_summed == CHECKSUM_PARTIAL) + pkt_info->attributes = XLGMAC_SET_REG_BITS( + pkt_info->attributes, + TX_PACKET_ATTRIBUTES_CSUM_ENABLE_POS, + TX_PACKET_ATTRIBUTES_CSUM_ENABLE_LEN, + 1); + + if (skb_vlan_tag_present(skb)) { + /* VLAN requires an extra descriptor if tag is different */ + if (skb_vlan_tag_get(skb) != ring->tx.cur_vlan_ctag) + /* We can share with the TSO context descriptor */ + if (!context_desc) { + context_desc = 1; + pkt_info->desc_count++; + } + + pkt_info->attributes = XLGMAC_SET_REG_BITS( + pkt_info->attributes, + TX_PACKET_ATTRIBUTES_VLAN_CTAG_POS, + TX_PACKET_ATTRIBUTES_VLAN_CTAG_LEN, + 1); + } + + for (len = skb_headlen(skb); len;) { + pkt_info->desc_count++; + len -= min_t(unsigned int, len, XLGMAC_TX_MAX_BUF_SIZE); + } + + for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { + frag = &skb_shinfo(skb)->frags[i]; + for (len = skb_frag_size(frag); len; ) { + pkt_info->desc_count++; + len -= min_t(unsigned int, len, XLGMAC_TX_MAX_BUF_SIZE); + } + } +} + +static int xlgmac_calc_rx_buf_size(struct net_device *netdev, unsigned int mtu) +{ + unsigned int rx_buf_size; + + if (mtu > XLGMAC_JUMBO_PACKET_MTU) { + netdev_alert(netdev, "MTU exceeds maximum supported value\n"); + return -EINVAL; + } + + rx_buf_size = mtu + ETH_HLEN + ETH_FCS_LEN + VLAN_HLEN; + rx_buf_size = clamp_val(rx_buf_size, XLGMAC_RX_MIN_BUF_SIZE, PAGE_SIZE); + + rx_buf_size = (rx_buf_size + XLGMAC_RX_BUF_ALIGN - 1) & + ~(XLGMAC_RX_BUF_ALIGN - 1); + + return rx_buf_size; +} + +static void xlgmac_enable_rx_tx_ints(struct xlgmac_pdata *pdata) +{ + struct xlgmac_hw_ops *hw_ops = &pdata->hw_ops; + struct xlgmac_channel *channel; + enum xlgmac_int int_id; + unsigned int i; + + channel = pdata->channel_head; + for (i = 0; i < pdata->channel_count; i++, channel++) { + if (channel->tx_ring && channel->rx_ring) + int_id = XLGMAC_INT_DMA_CH_SR_TI_RI; + else if (channel->tx_ring) + int_id = XLGMAC_INT_DMA_CH_SR_TI; + else if (channel->rx_ring) + int_id = XLGMAC_INT_DMA_CH_SR_RI; + else + continue; + + hw_ops->enable_int(channel, int_id); + } +} + +static void xlgmac_disable_rx_tx_ints(struct xlgmac_pdata *pdata) +{ + struct xlgmac_hw_ops *hw_ops = &pdata->hw_ops; + struct xlgmac_channel *channel; + enum xlgmac_int int_id; + unsigned int i; + + channel = pdata->channel_head; + for (i = 0; i < pdata->channel_count; i++, channel++) { + if (channel->tx_ring && channel->rx_ring) + int_id = XLGMAC_INT_DMA_CH_SR_TI_RI; + else if (channel->tx_ring) + int_id = XLGMAC_INT_DMA_CH_SR_TI; + else if (channel->rx_ring) + int_id = XLGMAC_INT_DMA_CH_SR_RI; + else + continue; + + hw_ops->disable_int(channel, int_id); + } +} + +static irqreturn_t xlgmac_isr(int irq, void *data) +{ + unsigned int dma_isr, dma_ch_isr, mac_isr; + struct xlgmac_pdata *pdata = data; + struct xlgmac_channel *channel; + struct xlgmac_hw_ops *hw_ops; + unsigned int i, ti, ri; + + hw_ops = &pdata->hw_ops; + + /* The DMA interrupt status register also reports MAC and MTL + * interrupts. So for polling mode, we just need to check for + * this register to be non-zero + */ + dma_isr = readl(pdata->mac_regs + DMA_ISR); + if (!dma_isr) + return IRQ_HANDLED; + + netif_dbg(pdata, intr, pdata->netdev, "DMA_ISR=%#010x\n", dma_isr); + + for (i = 0; i < pdata->channel_count; i++) { + if (!(dma_isr & (1 << i))) + continue; + + channel = pdata->channel_head + i; + + dma_ch_isr = readl(XLGMAC_DMA_REG(channel, DMA_CH_SR)); + netif_dbg(pdata, intr, pdata->netdev, "DMA_CH%u_ISR=%#010x\n", + i, dma_ch_isr); + + /* The TI or RI interrupt bits may still be set even if using + * per channel DMA interrupts. Check to be sure those are not + * enabled before using the private data napi structure. + */ + ti = XLGMAC_GET_REG_BITS(dma_ch_isr, DMA_CH_SR_TI_POS, + DMA_CH_SR_TI_LEN); + ri = XLGMAC_GET_REG_BITS(dma_ch_isr, DMA_CH_SR_RI_POS, + DMA_CH_SR_RI_LEN); + if (!pdata->per_channel_irq && (ti || ri)) { + if (napi_schedule_prep(&pdata->napi)) { + /* Disable Tx and Rx interrupts */ + xlgmac_disable_rx_tx_ints(pdata); + + /* Turn on polling */ + __napi_schedule_irqoff(&pdata->napi); + } + } + + if (XLGMAC_GET_REG_BITS(dma_ch_isr, DMA_CH_SR_RBU_POS, + DMA_CH_SR_RBU_LEN)) + pdata->stats.rx_buffer_unavailable++; + + /* Restart the device on a Fatal Bus Error */ + if (XLGMAC_GET_REG_BITS(dma_ch_isr, DMA_CH_SR_FBE_POS, + DMA_CH_SR_FBE_LEN)) + schedule_work(&pdata->restart_work); + + /* Clear all interrupt signals */ + writel(dma_ch_isr, XLGMAC_DMA_REG(channel, DMA_CH_SR)); + } + + if (XLGMAC_GET_REG_BITS(dma_isr, DMA_ISR_MACIS_POS, + DMA_ISR_MACIS_LEN)) { + mac_isr = readl(pdata->mac_regs + MAC_ISR); + + if (XLGMAC_GET_REG_BITS(mac_isr, MAC_ISR_MMCTXIS_POS, + MAC_ISR_MMCTXIS_LEN)) + hw_ops->tx_mmc_int(pdata); + + if (XLGMAC_GET_REG_BITS(mac_isr, MAC_ISR_MMCRXIS_POS, + MAC_ISR_MMCRXIS_LEN)) + hw_ops->rx_mmc_int(pdata); + } + + return IRQ_HANDLED; +} + +static irqreturn_t xlgmac_dma_isr(int irq, void *data) +{ + struct xlgmac_channel *channel = data; + + /* Per channel DMA interrupts are enabled, so we use the per + * channel napi structure and not the private data napi structure + */ + if (napi_schedule_prep(&channel->napi)) { + /* Disable Tx and Rx interrupts */ + disable_irq_nosync(channel->dma_irq); + + /* Turn on polling */ + __napi_schedule_irqoff(&channel->napi); + } + + return IRQ_HANDLED; +} + +static void xlgmac_tx_timer(unsigned long data) +{ + struct xlgmac_channel *channel = (struct xlgmac_channel *)data; + struct xlgmac_pdata *pdata = channel->pdata; + struct napi_struct *napi; + + napi = (pdata->per_channel_irq) ? &channel->napi : &pdata->napi; + + if (napi_schedule_prep(napi)) { + /* Disable Tx and Rx interrupts */ + if (pdata->per_channel_irq) + disable_irq_nosync(channel->dma_irq); + else + xlgmac_disable_rx_tx_ints(pdata); + + /* Turn on polling */ + __napi_schedule(napi); + } + + channel->tx_timer_active = 0; +} + +static void xlgmac_init_timers(struct xlgmac_pdata *pdata) +{ + struct xlgmac_channel *channel; + unsigned int i; + + channel = pdata->channel_head; + for (i = 0; i < pdata->channel_count; i++, channel++) { + if (!channel->tx_ring) + break; + + setup_timer(&channel->tx_timer, xlgmac_tx_timer, + (unsigned long)channel); + } +} + +static void xlgmac_stop_timers(struct xlgmac_pdata *pdata) +{ + struct xlgmac_channel *channel; + unsigned int i; + + channel = pdata->channel_head; + for (i = 0; i < pdata->channel_count; i++, channel++) { + if (!channel->tx_ring) + break; + + del_timer_sync(&channel->tx_timer); + } +} + +static void xlgmac_napi_enable(struct xlgmac_pdata *pdata, unsigned int add) +{ + struct xlgmac_channel *channel; + unsigned int i; + + if (pdata->per_channel_irq) { + channel = pdata->channel_head; + for (i = 0; i < pdata->channel_count; i++, channel++) { + if (add) + netif_napi_add(pdata->netdev, &channel->napi, + xlgmac_one_poll, + NAPI_POLL_WEIGHT); + + napi_enable(&channel->napi); + } + } else { + if (add) + netif_napi_add(pdata->netdev, &pdata->napi, + xlgmac_all_poll, NAPI_POLL_WEIGHT); + + napi_enable(&pdata->napi); + } +} + +static void xlgmac_napi_disable(struct xlgmac_pdata *pdata, unsigned int del) +{ + struct xlgmac_channel *channel; + unsigned int i; + + if (pdata->per_channel_irq) { + channel = pdata->channel_head; + for (i = 0; i < pdata->channel_count; i++, channel++) { + napi_disable(&channel->napi); + + if (del) + netif_napi_del(&channel->napi); + } + } else { + napi_disable(&pdata->napi); + + if (del) + netif_napi_del(&pdata->napi); + } +} + +static int xlgmac_request_irqs(struct xlgmac_pdata *pdata) +{ + struct net_device *netdev = pdata->netdev; + struct xlgmac_channel *channel; + unsigned int i; + int ret; + + ret = devm_request_irq(pdata->dev, pdata->dev_irq, xlgmac_isr, + IRQF_SHARED, netdev->name, pdata); + if (ret) { + netdev_alert(netdev, "error requesting irq %d\n", + pdata->dev_irq); + return ret; + } + + if (!pdata->per_channel_irq) + return 0; + + channel = pdata->channel_head; + for (i = 0; i < pdata->channel_count; i++, channel++) { + snprintf(channel->dma_irq_name, + sizeof(channel->dma_irq_name) - 1, + "%s-TxRx-%u", netdev_name(netdev), + channel->queue_index); + + ret = devm_request_irq(pdata->dev, channel->dma_irq, + xlgmac_dma_isr, 0, + channel->dma_irq_name, channel); + if (ret) { + netdev_alert(netdev, "error requesting irq %d\n", + channel->dma_irq); + goto err_irq; + } + } + + return 0; + +err_irq: + /* Using an unsigned int, 'i' will go to UINT_MAX and exit */ + for (i--, channel--; i < pdata->channel_count; i--, channel--) + devm_free_irq(pdata->dev, channel->dma_irq, channel); + + devm_free_irq(pdata->dev, pdata->dev_irq, pdata); + + return ret; +} + +static void xlgmac_free_irqs(struct xlgmac_pdata *pdata) +{ + struct xlgmac_channel *channel; + unsigned int i; + + devm_free_irq(pdata->dev, pdata->dev_irq, pdata); + + if (!pdata->per_channel_irq) + return; + + channel = pdata->channel_head; + for (i = 0; i < pdata->channel_count; i++, channel++) + devm_free_irq(pdata->dev, channel->dma_irq, channel); +} + +static void xlgmac_free_tx_data(struct xlgmac_pdata *pdata) +{ + struct xlgmac_desc_ops *desc_ops = &pdata->desc_ops; + struct xlgmac_desc_data *desc_data; + struct xlgmac_channel *channel; + struct xlgmac_ring *ring; + unsigned int i, j; + + channel = pdata->channel_head; + for (i = 0; i < pdata->channel_count; i++, channel++) { + ring = channel->tx_ring; + if (!ring) + break; + + for (j = 0; j < ring->dma_desc_count; j++) { + desc_data = XLGMAC_GET_DESC_DATA(ring, j); + desc_ops->unmap_desc_data(pdata, desc_data); + } + } +} + +static void xlgmac_free_rx_data(struct xlgmac_pdata *pdata) +{ + struct xlgmac_desc_ops *desc_ops = &pdata->desc_ops; + struct xlgmac_desc_data *desc_data; + struct xlgmac_channel *channel; + struct xlgmac_ring *ring; + unsigned int i, j; + + channel = pdata->channel_head; + for (i = 0; i < pdata->channel_count; i++, channel++) { + ring = channel->rx_ring; + if (!ring) + break; + + for (j = 0; j < ring->dma_desc_count; j++) { + desc_data = XLGMAC_GET_DESC_DATA(ring, j); + desc_ops->unmap_desc_data(pdata, desc_data); + } + } +} + +static int xlgmac_start(struct xlgmac_pdata *pdata) +{ + struct xlgmac_hw_ops *hw_ops = &pdata->hw_ops; + struct net_device *netdev = pdata->netdev; + int ret; + + hw_ops->init(pdata); + xlgmac_napi_enable(pdata, 1); + + ret = xlgmac_request_irqs(pdata); + if (ret) + goto err_napi; + + hw_ops->enable_tx(pdata); + hw_ops->enable_rx(pdata); + netif_tx_start_all_queues(netdev); + + return 0; + +err_napi: + xlgmac_napi_disable(pdata, 1); + hw_ops->exit(pdata); + + return ret; +} + +static void xlgmac_stop(struct xlgmac_pdata *pdata) +{ + struct xlgmac_hw_ops *hw_ops = &pdata->hw_ops; + struct net_device *netdev = pdata->netdev; + struct xlgmac_channel *channel; + struct netdev_queue *txq; + unsigned int i; + + netif_tx_stop_all_queues(netdev); + xlgmac_stop_timers(pdata); + hw_ops->disable_tx(pdata); + hw_ops->disable_rx(pdata); + xlgmac_free_irqs(pdata); + xlgmac_napi_disable(pdata, 1); + hw_ops->exit(pdata); + + channel = pdata->channel_head; + for (i = 0; i < pdata->channel_count; i++, channel++) { + if (!channel->tx_ring) + continue; + + txq = netdev_get_tx_queue(netdev, channel->queue_index); + netdev_tx_reset_queue(txq); + } +} + +static void xlgmac_restart_dev(struct xlgmac_pdata *pdata) +{ + /* If not running, "restart" will happen on open */ + if (!netif_running(pdata->netdev)) + return; + + xlgmac_stop(pdata); + + xlgmac_free_tx_data(pdata); + xlgmac_free_rx_data(pdata); + + xlgmac_start(pdata); +} + +static void xlgmac_restart(struct work_struct *work) +{ + struct xlgmac_pdata *pdata = container_of(work, + struct xlgmac_pdata, + restart_work); + + rtnl_lock(); + + xlgmac_restart_dev(pdata); + + rtnl_unlock(); +} + +static int xlgmac_open(struct net_device *netdev) +{ + struct xlgmac_pdata *pdata = netdev_priv(netdev); + struct xlgmac_desc_ops *desc_ops; + int ret; + + desc_ops = &pdata->desc_ops; + + /* TODO: Initialize the phy */ + + /* Calculate the Rx buffer size before allocating rings */ + ret = xlgmac_calc_rx_buf_size(netdev, netdev->mtu); + if (ret < 0) + return ret; + pdata->rx_buf_size = ret; + + /* Allocate the channels and rings */ + ret = desc_ops->alloc_channles_and_rings(pdata); + if (ret) + return ret; + + INIT_WORK(&pdata->restart_work, xlgmac_restart); + xlgmac_init_timers(pdata); + + ret = xlgmac_start(pdata); + if (ret) + goto err_channels_and_rings; + + return 0; + +err_channels_and_rings: + desc_ops->free_channels_and_rings(pdata); + + return ret; +} + +static int xlgmac_close(struct net_device *netdev) +{ + struct xlgmac_pdata *pdata = netdev_priv(netdev); + struct xlgmac_desc_ops *desc_ops; + + desc_ops = &pdata->desc_ops; + + /* Stop the device */ + xlgmac_stop(pdata); + + /* Free the channels and rings */ + desc_ops->free_channels_and_rings(pdata); + + return 0; +} + +static void xlgmac_tx_timeout(struct net_device *netdev) +{ + struct xlgmac_pdata *pdata = netdev_priv(netdev); + + netdev_warn(netdev, "tx timeout, device restarting\n"); + schedule_work(&pdata->restart_work); +} + +static int xlgmac_xmit(struct sk_buff *skb, struct net_device *netdev) +{ + struct xlgmac_pdata *pdata = netdev_priv(netdev); + struct xlgmac_pkt_info *tx_pkt_info; + struct xlgmac_desc_ops *desc_ops; + struct xlgmac_channel *channel; + struct xlgmac_hw_ops *hw_ops; + struct netdev_queue *txq; + struct xlgmac_ring *ring; + int ret; + + desc_ops = &pdata->desc_ops; + hw_ops = &pdata->hw_ops; + + XLGMAC_PR("skb->len = %d\n", skb->len); + + channel = pdata->channel_head + skb->queue_mapping; + txq = netdev_get_tx_queue(netdev, channel->queue_index); + ring = channel->tx_ring; + tx_pkt_info = &ring->pkt_info; + + if (skb->len == 0) { + netif_err(pdata, tx_err, netdev, + "empty skb received from stack\n"); + dev_kfree_skb_any(skb); + return NETDEV_TX_OK; + } + + /* Prepare preliminary packet info for TX */ + memset(tx_pkt_info, 0, sizeof(*tx_pkt_info)); + xlgmac_prep_tx_pkt(pdata, ring, skb, tx_pkt_info); + + /* Check that there are enough descriptors available */ + ret = xlgmac_maybe_stop_tx_queue(channel, ring, + tx_pkt_info->desc_count); + if (ret) + return ret; + + ret = xlgmac_prep_tso(skb, tx_pkt_info); + if (ret) { + netif_err(pdata, tx_err, netdev, + "error processing TSO packet\n"); + dev_kfree_skb_any(skb); + return ret; + } + xlgmac_prep_vlan(skb, tx_pkt_info); + + if (!desc_ops->map_tx_skb(channel, skb)) { + dev_kfree_skb_any(skb); + return NETDEV_TX_OK; + } + + /* Report on the actual number of bytes (to be) sent */ + netdev_tx_sent_queue(txq, tx_pkt_info->tx_bytes); + + /* Configure required descriptor fields for transmission */ + hw_ops->dev_xmit(channel); + + if (netif_msg_pktdata(pdata)) + xlgmac_print_pkt(netdev, skb, true); + + /* Stop the queue in advance if there may not be enough descriptors */ + xlgmac_maybe_stop_tx_queue(channel, ring, XLGMAC_TX_MAX_DESC_NR); + + return NETDEV_TX_OK; +} + +static void xlgmac_get_stats64(struct net_device *netdev, + struct rtnl_link_stats64 *s) +{ + struct xlgmac_pdata *pdata = netdev_priv(netdev); + struct xlgmac_stats *pstats = &pdata->stats; + + pdata->hw_ops.read_mmc_stats(pdata); + + s->rx_packets = pstats->rxframecount_gb; + s->rx_bytes = pstats->rxoctetcount_gb; + s->rx_errors = pstats->rxframecount_gb - + pstats->rxbroadcastframes_g - + pstats->rxmulticastframes_g - + pstats->rxunicastframes_g; + s->multicast = pstats->rxmulticastframes_g; + s->rx_length_errors = pstats->rxlengtherror; + s->rx_crc_errors = pstats->rxcrcerror; + s->rx_fifo_errors = pstats->rxfifooverflow; + + s->tx_packets = pstats->txframecount_gb; + s->tx_bytes = pstats->txoctetcount_gb; + s->tx_errors = pstats->txframecount_gb - pstats->txframecount_g; + s->tx_dropped = netdev->stats.tx_dropped; +} + +static int xlgmac_set_mac_address(struct net_device *netdev, void *addr) +{ + struct xlgmac_pdata *pdata = netdev_priv(netdev); + struct xlgmac_hw_ops *hw_ops = &pdata->hw_ops; + struct sockaddr *saddr = addr; + + if (!is_valid_ether_addr(saddr->sa_data)) + return -EADDRNOTAVAIL; + + memcpy(netdev->dev_addr, saddr->sa_data, netdev->addr_len); + + hw_ops->set_mac_address(pdata, netdev->dev_addr); + + return 0; +} + +static int xlgmac_ioctl(struct net_device *netdev, + struct ifreq *ifreq, int cmd) +{ + if (!netif_running(netdev)) + return -ENODEV; + + return 0; +} + +static int xlgmac_change_mtu(struct net_device *netdev, int mtu) +{ + struct xlgmac_pdata *pdata = netdev_priv(netdev); + int ret; + + ret = xlgmac_calc_rx_buf_size(netdev, mtu); + if (ret < 0) + return ret; + + pdata->rx_buf_size = ret; + netdev->mtu = mtu; + + xlgmac_restart_dev(pdata); + + return 0; +} + +static int xlgmac_vlan_rx_add_vid(struct net_device *netdev, + __be16 proto, + u16 vid) +{ + struct xlgmac_pdata *pdata = netdev_priv(netdev); + struct xlgmac_hw_ops *hw_ops = &pdata->hw_ops; + + set_bit(vid, pdata->active_vlans); + hw_ops->update_vlan_hash_table(pdata); + + return 0; +} + +static int xlgmac_vlan_rx_kill_vid(struct net_device *netdev, + __be16 proto, + u16 vid) +{ + struct xlgmac_pdata *pdata = netdev_priv(netdev); + struct xlgmac_hw_ops *hw_ops = &pdata->hw_ops; + + clear_bit(vid, pdata->active_vlans); + hw_ops->update_vlan_hash_table(pdata); + + return 0; +} + +#ifdef CONFIG_NET_POLL_CONTROLLER +static void xlgmac_poll_controller(struct net_device *netdev) +{ + struct xlgmac_pdata *pdata = netdev_priv(netdev); + struct xlgmac_channel *channel; + unsigned int i; + + if (pdata->per_channel_irq) { + channel = pdata->channel_head; + for (i = 0; i < pdata->channel_count; i++, channel++) + xlgmac_dma_isr(channel->dma_irq, channel); + } else { + disable_irq(pdata->dev_irq); + xlgmac_isr(pdata->dev_irq, pdata); + enable_irq(pdata->dev_irq); + } +} +#endif /* CONFIG_NET_POLL_CONTROLLER */ + +static int xlgmac_set_features(struct net_device *netdev, + netdev_features_t features) +{ + netdev_features_t rxhash, rxcsum, rxvlan, rxvlan_filter; + struct xlgmac_pdata *pdata = netdev_priv(netdev); + struct xlgmac_hw_ops *hw_ops = &pdata->hw_ops; + int ret = 0; + + rxhash = pdata->netdev_features & NETIF_F_RXHASH; + rxcsum = pdata->netdev_features & NETIF_F_RXCSUM; + rxvlan = pdata->netdev_features & NETIF_F_HW_VLAN_CTAG_RX; + rxvlan_filter = pdata->netdev_features & NETIF_F_HW_VLAN_CTAG_FILTER; + + if ((features & NETIF_F_RXHASH) && !rxhash) + ret = hw_ops->enable_rss(pdata); + else if (!(features & NETIF_F_RXHASH) && rxhash) + ret = hw_ops->disable_rss(pdata); + if (ret) + return ret; + + if ((features & NETIF_F_RXCSUM) && !rxcsum) + hw_ops->enable_rx_csum(pdata); + else if (!(features & NETIF_F_RXCSUM) && rxcsum) + hw_ops->disable_rx_csum(pdata); + + if ((features & NETIF_F_HW_VLAN_CTAG_RX) && !rxvlan) + hw_ops->enable_rx_vlan_stripping(pdata); + else if (!(features & NETIF_F_HW_VLAN_CTAG_RX) && rxvlan) + hw_ops->disable_rx_vlan_stripping(pdata); + + if ((features & NETIF_F_HW_VLAN_CTAG_FILTER) && !rxvlan_filter) + hw_ops->enable_rx_vlan_filtering(pdata); + else if (!(features & NETIF_F_HW_VLAN_CTAG_FILTER) && rxvlan_filter) + hw_ops->disable_rx_vlan_filtering(pdata); + + pdata->netdev_features = features; + + return 0; +} + +static void xlgmac_set_rx_mode(struct net_device *netdev) +{ + struct xlgmac_pdata *pdata = netdev_priv(netdev); + struct xlgmac_hw_ops *hw_ops = &pdata->hw_ops; + + hw_ops->config_rx_mode(pdata); +} + +static const struct net_device_ops xlgmac_netdev_ops = { + .ndo_open = xlgmac_open, + .ndo_stop = xlgmac_close, + .ndo_start_xmit = xlgmac_xmit, + .ndo_tx_timeout = xlgmac_tx_timeout, + .ndo_get_stats64 = xlgmac_get_stats64, + .ndo_change_mtu = xlgmac_change_mtu, + .ndo_set_mac_address = xlgmac_set_mac_address, + .ndo_validate_addr = eth_validate_addr, + .ndo_do_ioctl = xlgmac_ioctl, + .ndo_vlan_rx_add_vid = xlgmac_vlan_rx_add_vid, + .ndo_vlan_rx_kill_vid = xlgmac_vlan_rx_kill_vid, +#ifdef CONFIG_NET_POLL_CONTROLLER + .ndo_poll_controller = xlgmac_poll_controller, +#endif + .ndo_set_features = xlgmac_set_features, + .ndo_set_rx_mode = xlgmac_set_rx_mode, +}; + +const struct net_device_ops *xlgmac_get_netdev_ops(void) +{ + return &xlgmac_netdev_ops; +} + +static void xlgmac_rx_refresh(struct xlgmac_channel *channel) +{ + struct xlgmac_pdata *pdata = channel->pdata; + struct xlgmac_ring *ring = channel->rx_ring; + struct xlgmac_desc_data *desc_data; + struct xlgmac_desc_ops *desc_ops; + struct xlgmac_hw_ops *hw_ops; + + desc_ops = &pdata->desc_ops; + hw_ops = &pdata->hw_ops; + + while (ring->dirty != ring->cur) { + desc_data = XLGMAC_GET_DESC_DATA(ring, ring->dirty); + + /* Reset desc_data values */ + desc_ops->unmap_desc_data(pdata, desc_data); + + if (desc_ops->map_rx_buffer(pdata, ring, desc_data)) + break; + + hw_ops->rx_desc_reset(pdata, desc_data, ring->dirty); + + ring->dirty++; + } + + /* Make sure everything is written before the register write */ + wmb(); + + /* Update the Rx Tail Pointer Register with address of + * the last cleaned entry + */ + desc_data = XLGMAC_GET_DESC_DATA(ring, ring->dirty - 1); + writel(lower_32_bits(desc_data->dma_desc_addr), + XLGMAC_DMA_REG(channel, DMA_CH_RDTR_LO)); +} + +static struct sk_buff *xlgmac_create_skb(struct xlgmac_pdata *pdata, + struct napi_struct *napi, + struct xlgmac_desc_data *desc_data, + unsigned int len) +{ + unsigned int copy_len; + struct sk_buff *skb; + u8 *packet; + + skb = napi_alloc_skb(napi, desc_data->rx.hdr.dma_len); + if (!skb) + return NULL; + + /* Start with the header buffer which may contain just the header + * or the header plus data + */ + dma_sync_single_range_for_cpu(pdata->dev, desc_data->rx.hdr.dma_base, + desc_data->rx.hdr.dma_off, + desc_data->rx.hdr.dma_len, + DMA_FROM_DEVICE); + + packet = page_address(desc_data->rx.hdr.pa.pages) + + desc_data->rx.hdr.pa.pages_offset; + copy_len = (desc_data->rx.hdr_len) ? desc_data->rx.hdr_len : len; + copy_len = min(desc_data->rx.hdr.dma_len, copy_len); + skb_copy_to_linear_data(skb, packet, copy_len); + skb_put(skb, copy_len); + + len -= copy_len; + if (len) { + /* Add the remaining data as a frag */ + dma_sync_single_range_for_cpu(pdata->dev, + desc_data->rx.buf.dma_base, + desc_data->rx.buf.dma_off, + desc_data->rx.buf.dma_len, + DMA_FROM_DEVICE); + + skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, + desc_data->rx.buf.pa.pages, + desc_data->rx.buf.pa.pages_offset, + len, desc_data->rx.buf.dma_len); + desc_data->rx.buf.pa.pages = NULL; + } + + return skb; +} + +static int xlgmac_tx_poll(struct xlgmac_channel *channel) +{ + struct xlgmac_pdata *pdata = channel->pdata; + struct xlgmac_ring *ring = channel->tx_ring; + struct net_device *netdev = pdata->netdev; + unsigned int tx_packets = 0, tx_bytes = 0; + struct xlgmac_desc_data *desc_data; + struct xlgmac_dma_desc *dma_desc; + struct xlgmac_desc_ops *desc_ops; + struct xlgmac_hw_ops *hw_ops; + struct netdev_queue *txq; + int processed = 0; + unsigned int cur; + + desc_ops = &pdata->desc_ops; + hw_ops = &pdata->hw_ops; + + /* Nothing to do if there isn't a Tx ring for this channel */ + if (!ring) + return 0; + + cur = ring->cur; + + /* Be sure we get ring->cur before accessing descriptor data */ + smp_rmb(); + + txq = netdev_get_tx_queue(netdev, channel->queue_index); + + while ((processed < XLGMAC_TX_DESC_MAX_PROC) && + (ring->dirty != cur)) { + desc_data = XLGMAC_GET_DESC_DATA(ring, ring->dirty); + dma_desc = desc_data->dma_desc; + + if (!hw_ops->tx_complete(dma_desc)) + break; + + /* Make sure descriptor fields are read after reading + * the OWN bit + */ + dma_rmb(); + + if (netif_msg_tx_done(pdata)) + xlgmac_dump_tx_desc(pdata, ring, ring->dirty, 1, 0); + + if (hw_ops->is_last_desc(dma_desc)) { + tx_packets += desc_data->tx.packets; + tx_bytes += desc_data->tx.bytes; + } + + /* Free the SKB and reset the descriptor for re-use */ + desc_ops->unmap_desc_data(pdata, desc_data); + hw_ops->tx_desc_reset(desc_data); + + processed++; + ring->dirty++; + } + + if (!processed) + return 0; + + netdev_tx_completed_queue(txq, tx_packets, tx_bytes); + + if ((ring->tx.queue_stopped == 1) && + (xlgmac_tx_avail_desc(ring) > XLGMAC_TX_DESC_MIN_FREE)) { + ring->tx.queue_stopped = 0; + netif_tx_wake_queue(txq); + } + + XLGMAC_PR("processed=%d\n", processed); + + return processed; +} + +static int xlgmac_rx_poll(struct xlgmac_channel *channel, int budget) +{ + struct xlgmac_pdata *pdata = channel->pdata; + struct xlgmac_ring *ring = channel->rx_ring; + struct net_device *netdev = pdata->netdev; + unsigned int len, dma_desc_len, max_len; + unsigned int context_next, context; + struct xlgmac_desc_data *desc_data; + struct xlgmac_pkt_info *pkt_info; + unsigned int incomplete, error; + struct xlgmac_hw_ops *hw_ops; + unsigned int received = 0; + struct napi_struct *napi; + struct sk_buff *skb; + int packet_count = 0; + + hw_ops = &pdata->hw_ops; + + /* Nothing to do if there isn't a Rx ring for this channel */ + if (!ring) + return 0; + + incomplete = 0; + context_next = 0; + + napi = (pdata->per_channel_irq) ? &channel->napi : &pdata->napi; + + desc_data = XLGMAC_GET_DESC_DATA(ring, ring->cur); + pkt_info = &ring->pkt_info; + while (packet_count < budget) { + /* First time in loop see if we need to restore state */ + if (!received && desc_data->state_saved) { + skb = desc_data->state.skb; + error = desc_data->state.error; + len = desc_data->state.len; + } else { + memset(pkt_info, 0, sizeof(*pkt_info)); + skb = NULL; + error = 0; + len = 0; + } + +read_again: + desc_data = XLGMAC_GET_DESC_DATA(ring, ring->cur); + + if (xlgmac_rx_dirty_desc(ring) > XLGMAC_RX_DESC_MAX_DIRTY) + xlgmac_rx_refresh(channel); + + if (hw_ops->dev_read(channel)) + break; + + received++; + ring->cur++; + + incomplete = XLGMAC_GET_REG_BITS( + pkt_info->attributes, + RX_PACKET_ATTRIBUTES_INCOMPLETE_POS, + RX_PACKET_ATTRIBUTES_INCOMPLETE_LEN); + context_next = XLGMAC_GET_REG_BITS( + pkt_info->attributes, + RX_PACKET_ATTRIBUTES_CONTEXT_NEXT_POS, + RX_PACKET_ATTRIBUTES_CONTEXT_NEXT_LEN); + context = XLGMAC_GET_REG_BITS( + pkt_info->attributes, + RX_PACKET_ATTRIBUTES_CONTEXT_POS, + RX_PACKET_ATTRIBUTES_CONTEXT_LEN); + + /* Earlier error, just drain the remaining data */ + if ((incomplete || context_next) && error) + goto read_again; + + if (error || pkt_info->errors) { + if (pkt_info->errors) + netif_err(pdata, rx_err, netdev, + "error in received packet\n"); + dev_kfree_skb(skb); + goto next_packet; + } + + if (!context) { + /* Length is cumulative, get this descriptor's length */ + dma_desc_len = desc_data->rx.len - len; + len += dma_desc_len; + + if (dma_desc_len && !skb) { + skb = xlgmac_create_skb(pdata, napi, desc_data, + dma_desc_len); + if (!skb) + error = 1; + } else if (dma_desc_len) { + dma_sync_single_range_for_cpu( + pdata->dev, + desc_data->rx.buf.dma_base, + desc_data->rx.buf.dma_off, + desc_data->rx.buf.dma_len, + DMA_FROM_DEVICE); + + skb_add_rx_frag( + skb, skb_shinfo(skb)->nr_frags, + desc_data->rx.buf.pa.pages, + desc_data->rx.buf.pa.pages_offset, + dma_desc_len, + desc_data->rx.buf.dma_len); + desc_data->rx.buf.pa.pages = NULL; + } + } + + if (incomplete || context_next) + goto read_again; + + if (!skb) + goto next_packet; + + /* Be sure we don't exceed the configured MTU */ + max_len = netdev->mtu + ETH_HLEN; + if (!(netdev->features & NETIF_F_HW_VLAN_CTAG_RX) && + (skb->protocol == htons(ETH_P_8021Q))) + max_len += VLAN_HLEN; + + if (skb->len > max_len) { + netif_err(pdata, rx_err, netdev, + "packet length exceeds configured MTU\n"); + dev_kfree_skb(skb); + goto next_packet; + } + + if (netif_msg_pktdata(pdata)) + xlgmac_print_pkt(netdev, skb, false); + + skb_checksum_none_assert(skb); + if (XLGMAC_GET_REG_BITS(pkt_info->attributes, + RX_PACKET_ATTRIBUTES_CSUM_DONE_POS, + RX_PACKET_ATTRIBUTES_CSUM_DONE_LEN)) + skb->ip_summed = CHECKSUM_UNNECESSARY; + + if (XLGMAC_GET_REG_BITS(pkt_info->attributes, + RX_PACKET_ATTRIBUTES_VLAN_CTAG_POS, + RX_PACKET_ATTRIBUTES_VLAN_CTAG_LEN)) + __vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), + pkt_info->vlan_ctag); + + if (XLGMAC_GET_REG_BITS(pkt_info->attributes, + RX_PACKET_ATTRIBUTES_RSS_HASH_POS, + RX_PACKET_ATTRIBUTES_RSS_HASH_LEN)) + skb_set_hash(skb, pkt_info->rss_hash, + pkt_info->rss_hash_type); + + skb->dev = netdev; + skb->protocol = eth_type_trans(skb, netdev); + skb_record_rx_queue(skb, channel->queue_index); + + napi_gro_receive(napi, skb); + +next_packet: + packet_count++; + } + + /* Check if we need to save state before leaving */ + if (received && (incomplete || context_next)) { + desc_data = XLGMAC_GET_DESC_DATA(ring, ring->cur); + desc_data->state_saved = 1; + desc_data->state.skb = skb; + desc_data->state.len = len; + desc_data->state.error = error; + } + + XLGMAC_PR("packet_count = %d\n", packet_count); + + return packet_count; +} + +static int xlgmac_one_poll(struct napi_struct *napi, int budget) +{ + struct xlgmac_channel *channel = container_of(napi, + struct xlgmac_channel, + napi); + int processed = 0; + + XLGMAC_PR("budget=%d\n", budget); + + /* Cleanup Tx ring first */ + xlgmac_tx_poll(channel); + + /* Process Rx ring next */ + processed = xlgmac_rx_poll(channel, budget); + + /* If we processed everything, we are done */ + if (processed < budget) { + /* Turn off polling */ + napi_complete_done(napi, processed); + + /* Enable Tx and Rx interrupts */ + enable_irq(channel->dma_irq); + } + + XLGMAC_PR("received = %d\n", processed); + + return processed; +} + +static int xlgmac_all_poll(struct napi_struct *napi, int budget) +{ + struct xlgmac_pdata *pdata = container_of(napi, + struct xlgmac_pdata, + napi); + struct xlgmac_channel *channel; + int processed, last_processed; + int ring_budget; + unsigned int i; + + XLGMAC_PR("budget=%d\n", budget); + + processed = 0; + ring_budget = budget / pdata->rx_ring_count; + do { + last_processed = processed; + + channel = pdata->channel_head; + for (i = 0; i < pdata->channel_count; i++, channel++) { + /* Cleanup Tx ring first */ + xlgmac_tx_poll(channel); + + /* Process Rx ring next */ + if (ring_budget > (budget - processed)) + ring_budget = budget - processed; + processed += xlgmac_rx_poll(channel, ring_budget); + } + } while ((processed < budget) && (processed != last_processed)); + + /* If we processed everything, we are done */ + if (processed < budget) { + /* Turn off polling */ + napi_complete_done(napi, processed); + + /* Enable Tx and Rx interrupts */ + xlgmac_enable_rx_tx_ints(pdata); + } + + XLGMAC_PR("received = %d\n", processed); + + return processed; +} diff --git a/drivers/net/ethernet/synopsys/dwc-xlgmac-pci.c b/drivers/net/ethernet/synopsys/dwc-xlgmac-pci.c new file mode 100644 index 000000000000..504e80de7bba --- /dev/null +++ b/drivers/net/ethernet/synopsys/dwc-xlgmac-pci.c @@ -0,0 +1,80 @@ +/* Synopsys DesignWare Core Enterprise Ethernet (XLGMAC) Driver + * + * Copyright (c) 2017 Synopsys, Inc. (www.synopsys.com) + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the + * Free Software Foundation; either version 2 of the License, or (at your + * option) any later version. + * + * This Synopsys DWC XLGMAC software driver and associated documentation + * (hereinafter the "Software") is an unsupported proprietary work of + * Synopsys, Inc. unless otherwise expressly agreed to in writing between + * Synopsys and you. The Software IS NOT an item of Licensed Software or a + * Licensed Product under any End User Software License Agreement or + * Agreement for Licensed Products with Synopsys or any supplement thereto. + * Synopsys is a registered trademark of Synopsys, Inc. Other names included + * in the SOFTWARE may be the trademarks of their respective owners. + */ + +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/pci.h> + +#include "dwc-xlgmac.h" +#include "dwc-xlgmac-reg.h" + +static int xlgmac_probe(struct pci_dev *pcidev, const struct pci_device_id *id) +{ + struct device *dev = &pcidev->dev; + struct xlgmac_resources res; + int i, ret; + + ret = pcim_enable_device(pcidev); + if (ret) { + dev_err(dev, "ERROR: failed to enable device\n"); + return ret; + } + + for (i = 0; i <= PCI_STD_RESOURCE_END; i++) { + if (pci_resource_len(pcidev, i) == 0) + continue; + ret = pcim_iomap_regions(pcidev, BIT(i), XLGMAC_DRV_NAME); + if (ret) + return ret; + break; + } + + pci_set_master(pcidev); + + memset(&res, 0, sizeof(res)); + res.irq = pcidev->irq; + res.addr = pcim_iomap_table(pcidev)[i]; + + return xlgmac_drv_probe(&pcidev->dev, &res); +} + +static void xlgmac_remove(struct pci_dev *pcidev) +{ + xlgmac_drv_remove(&pcidev->dev); +} + +static const struct pci_device_id xlgmac_pci_tbl[] = { + { PCI_DEVICE(PCI_VENDOR_ID_SYNOPSYS, 0x7302) }, + { 0 } +}; +MODULE_DEVICE_TABLE(pci, xlgmac_pci_tbl); + +static struct pci_driver xlgmac_pci_driver = { + .name = XLGMAC_DRV_NAME, + .id_table = xlgmac_pci_tbl, + .probe = xlgmac_probe, + .remove = xlgmac_remove, +}; + +module_pci_driver(xlgmac_pci_driver); + +MODULE_DESCRIPTION(XLGMAC_DRV_DESC); +MODULE_VERSION(XLGMAC_DRV_VERSION); +MODULE_AUTHOR("Jie Deng <[email protected]>"); +MODULE_LICENSE("Dual BSD/GPL"); diff --git a/drivers/net/ethernet/synopsys/dwc-xlgmac-reg.h b/drivers/net/ethernet/synopsys/dwc-xlgmac-reg.h new file mode 100644 index 000000000000..782448128a89 --- /dev/null +++ b/drivers/net/ethernet/synopsys/dwc-xlgmac-reg.h @@ -0,0 +1,746 @@ +/* Synopsys DesignWare Core Enterprise Ethernet (XLGMAC) Driver + * + * Copyright (c) 2017 Synopsys, Inc. (www.synopsys.com) + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the + * Free Software Foundation; either version 2 of the License, or (at your + * option) any later version. + * + * This Synopsys DWC XLGMAC software driver and associated documentation + * (hereinafter the "Software") is an unsupported proprietary work of + * Synopsys, Inc. unless otherwise expressly agreed to in writing between + * Synopsys and you. The Software IS NOT an item of Licensed Software or a + * Licensed Product under any End User Software License Agreement or + * Agreement for Licensed Products with Synopsys or any supplement thereto. + * Synopsys is a registered trademark of Synopsys, Inc. Other names included + * in the SOFTWARE may be the trademarks of their respective owners. + */ + +#ifndef __DWC_XLGMAC_REG_H__ +#define __DWC_XLGMAC_REG_H__ + +/* MAC register offsets */ +#define MAC_TCR 0x0000 +#define MAC_RCR 0x0004 +#define MAC_PFR 0x0008 +#define MAC_HTR0 0x0010 +#define MAC_VLANTR 0x0050 +#define MAC_VLANHTR 0x0058 +#define MAC_VLANIR 0x0060 +#define MAC_Q0TFCR 0x0070 +#define MAC_RFCR 0x0090 +#define MAC_RQC0R 0x00a0 +#define MAC_RQC1R 0x00a4 +#define MAC_RQC2R 0x00a8 +#define MAC_RQC3R 0x00ac +#define MAC_ISR 0x00b0 +#define MAC_IER 0x00b4 +#define MAC_VR 0x0110 +#define MAC_HWF0R 0x011c +#define MAC_HWF1R 0x0120 +#define MAC_HWF2R 0x0124 +#define MAC_MACA0HR 0x0300 +#define MAC_MACA0LR 0x0304 +#define MAC_MACA1HR 0x0308 +#define MAC_MACA1LR 0x030c +#define MAC_RSSCR 0x0c80 +#define MAC_RSSAR 0x0c88 +#define MAC_RSSDR 0x0c8c + +#define MAC_QTFCR_INC 4 +#define MAC_MACA_INC 4 +#define MAC_HTR_INC 4 +#define MAC_RQC2_INC 4 +#define MAC_RQC2_Q_PER_REG 4 + +/* MAC register entry bit positions and sizes */ +#define MAC_HWF0R_ADDMACADRSEL_POS 18 +#define MAC_HWF0R_ADDMACADRSEL_LEN 5 +#define MAC_HWF0R_ARPOFFSEL_POS 9 +#define MAC_HWF0R_ARPOFFSEL_LEN 1 +#define MAC_HWF0R_EEESEL_POS 13 +#define MAC_HWF0R_EEESEL_LEN 1 +#define MAC_HWF0R_PHYIFSEL_POS 1 +#define MAC_HWF0R_PHYIFSEL_LEN 2 +#define MAC_HWF0R_MGKSEL_POS 7 +#define MAC_HWF0R_MGKSEL_LEN 1 +#define MAC_HWF0R_MMCSEL_POS 8 +#define MAC_HWF0R_MMCSEL_LEN 1 +#define MAC_HWF0R_RWKSEL_POS 6 +#define MAC_HWF0R_RWKSEL_LEN 1 +#define MAC_HWF0R_RXCOESEL_POS 16 +#define MAC_HWF0R_RXCOESEL_LEN 1 +#define MAC_HWF0R_SAVLANINS_POS 27 +#define MAC_HWF0R_SAVLANINS_LEN 1 +#define MAC_HWF0R_SMASEL_POS 5 +#define MAC_HWF0R_SMASEL_LEN 1 +#define MAC_HWF0R_TSSEL_POS 12 +#define MAC_HWF0R_TSSEL_LEN 1 +#define MAC_HWF0R_TSSTSSEL_POS 25 +#define MAC_HWF0R_TSSTSSEL_LEN 2 +#define MAC_HWF0R_TXCOESEL_POS 14 +#define MAC_HWF0R_TXCOESEL_LEN 1 +#define MAC_HWF0R_VLHASH_POS 4 +#define MAC_HWF0R_VLHASH_LEN 1 +#define MAC_HWF1R_ADDR64_POS 14 +#define MAC_HWF1R_ADDR64_LEN 2 +#define MAC_HWF1R_ADVTHWORD_POS 13 +#define MAC_HWF1R_ADVTHWORD_LEN 1 +#define MAC_HWF1R_DBGMEMA_POS 19 +#define MAC_HWF1R_DBGMEMA_LEN 1 +#define MAC_HWF1R_DCBEN_POS 16 +#define MAC_HWF1R_DCBEN_LEN 1 +#define MAC_HWF1R_HASHTBLSZ_POS 24 +#define MAC_HWF1R_HASHTBLSZ_LEN 3 +#define MAC_HWF1R_L3L4FNUM_POS 27 +#define MAC_HWF1R_L3L4FNUM_LEN 4 +#define MAC_HWF1R_NUMTC_POS 21 +#define MAC_HWF1R_NUMTC_LEN 3 +#define MAC_HWF1R_RSSEN_POS 20 +#define MAC_HWF1R_RSSEN_LEN 1 +#define MAC_HWF1R_RXFIFOSIZE_POS 0 +#define MAC_HWF1R_RXFIFOSIZE_LEN 5 +#define MAC_HWF1R_SPHEN_POS 17 +#define MAC_HWF1R_SPHEN_LEN 1 +#define MAC_HWF1R_TSOEN_POS 18 +#define MAC_HWF1R_TSOEN_LEN 1 +#define MAC_HWF1R_TXFIFOSIZE_POS 6 +#define MAC_HWF1R_TXFIFOSIZE_LEN 5 +#define MAC_HWF2R_AUXSNAPNUM_POS 28 +#define MAC_HWF2R_AUXSNAPNUM_LEN 3 +#define MAC_HWF2R_PPSOUTNUM_POS 24 +#define MAC_HWF2R_PPSOUTNUM_LEN 3 +#define MAC_HWF2R_RXCHCNT_POS 12 +#define MAC_HWF2R_RXCHCNT_LEN 4 +#define MAC_HWF2R_RXQCNT_POS 0 +#define MAC_HWF2R_RXQCNT_LEN 4 +#define MAC_HWF2R_TXCHCNT_POS 18 +#define MAC_HWF2R_TXCHCNT_LEN 4 +#define MAC_HWF2R_TXQCNT_POS 6 +#define MAC_HWF2R_TXQCNT_LEN 4 +#define MAC_IER_TSIE_POS 12 +#define MAC_IER_TSIE_LEN 1 +#define MAC_ISR_MMCRXIS_POS 9 +#define MAC_ISR_MMCRXIS_LEN 1 +#define MAC_ISR_MMCTXIS_POS 10 +#define MAC_ISR_MMCTXIS_LEN 1 +#define MAC_ISR_PMTIS_POS 4 +#define MAC_ISR_PMTIS_LEN 1 +#define MAC_ISR_TSIS_POS 12 +#define MAC_ISR_TSIS_LEN 1 +#define MAC_MACA1HR_AE_POS 31 +#define MAC_MACA1HR_AE_LEN 1 +#define MAC_PFR_HMC_POS 2 +#define MAC_PFR_HMC_LEN 1 +#define MAC_PFR_HPF_POS 10 +#define MAC_PFR_HPF_LEN 1 +#define MAC_PFR_HUC_POS 1 +#define MAC_PFR_HUC_LEN 1 +#define MAC_PFR_PM_POS 4 +#define MAC_PFR_PM_LEN 1 +#define MAC_PFR_PR_POS 0 +#define MAC_PFR_PR_LEN 1 +#define MAC_PFR_VTFE_POS 16 +#define MAC_PFR_VTFE_LEN 1 +#define MAC_Q0TFCR_PT_POS 16 +#define MAC_Q0TFCR_PT_LEN 16 +#define MAC_Q0TFCR_TFE_POS 1 +#define MAC_Q0TFCR_TFE_LEN 1 +#define MAC_RCR_ACS_POS 1 +#define MAC_RCR_ACS_LEN 1 +#define MAC_RCR_CST_POS 2 +#define MAC_RCR_CST_LEN 1 +#define MAC_RCR_DCRCC_POS 3 +#define MAC_RCR_DCRCC_LEN 1 +#define MAC_RCR_HDSMS_POS 12 +#define MAC_RCR_HDSMS_LEN 3 +#define MAC_RCR_IPC_POS 9 +#define MAC_RCR_IPC_LEN 1 +#define MAC_RCR_JE_POS 8 +#define MAC_RCR_JE_LEN 1 +#define MAC_RCR_LM_POS 10 +#define MAC_RCR_LM_LEN 1 +#define MAC_RCR_RE_POS 0 +#define MAC_RCR_RE_LEN 1 +#define MAC_RFCR_PFCE_POS 8 +#define MAC_RFCR_PFCE_LEN 1 +#define MAC_RFCR_RFE_POS 0 +#define MAC_RFCR_RFE_LEN 1 +#define MAC_RFCR_UP_POS 1 +#define MAC_RFCR_UP_LEN 1 +#define MAC_RQC0R_RXQ0EN_POS 0 +#define MAC_RQC0R_RXQ0EN_LEN 2 +#define MAC_RSSAR_ADDRT_POS 2 +#define MAC_RSSAR_ADDRT_LEN 1 +#define MAC_RSSAR_CT_POS 1 +#define MAC_RSSAR_CT_LEN 1 +#define MAC_RSSAR_OB_POS 0 +#define MAC_RSSAR_OB_LEN 1 +#define MAC_RSSAR_RSSIA_POS 8 +#define MAC_RSSAR_RSSIA_LEN 8 +#define MAC_RSSCR_IP2TE_POS 1 +#define MAC_RSSCR_IP2TE_LEN 1 +#define MAC_RSSCR_RSSE_POS 0 +#define MAC_RSSCR_RSSE_LEN 1 +#define MAC_RSSCR_TCP4TE_POS 2 +#define MAC_RSSCR_TCP4TE_LEN 1 +#define MAC_RSSCR_UDP4TE_POS 3 +#define MAC_RSSCR_UDP4TE_LEN 1 +#define MAC_RSSDR_DMCH_POS 0 +#define MAC_RSSDR_DMCH_LEN 4 +#define MAC_TCR_SS_POS 28 +#define MAC_TCR_SS_LEN 3 +#define MAC_TCR_TE_POS 0 +#define MAC_TCR_TE_LEN 1 +#define MAC_VLANHTR_VLHT_POS 0 +#define MAC_VLANHTR_VLHT_LEN 16 +#define MAC_VLANIR_VLTI_POS 20 +#define MAC_VLANIR_VLTI_LEN 1 +#define MAC_VLANIR_CSVL_POS 19 +#define MAC_VLANIR_CSVL_LEN 1 +#define MAC_VLANTR_DOVLTC_POS 20 +#define MAC_VLANTR_DOVLTC_LEN 1 +#define MAC_VLANTR_ERSVLM_POS 19 +#define MAC_VLANTR_ERSVLM_LEN 1 +#define MAC_VLANTR_ESVL_POS 18 +#define MAC_VLANTR_ESVL_LEN 1 +#define MAC_VLANTR_ETV_POS 16 +#define MAC_VLANTR_ETV_LEN 1 +#define MAC_VLANTR_EVLS_POS 21 +#define MAC_VLANTR_EVLS_LEN 2 +#define MAC_VLANTR_EVLRXS_POS 24 +#define MAC_VLANTR_EVLRXS_LEN 1 +#define MAC_VLANTR_VL_POS 0 +#define MAC_VLANTR_VL_LEN 16 +#define MAC_VLANTR_VTHM_POS 25 +#define MAC_VLANTR_VTHM_LEN 1 +#define MAC_VLANTR_VTIM_POS 17 +#define MAC_VLANTR_VTIM_LEN 1 +#define MAC_VR_DEVID_POS 8 +#define MAC_VR_DEVID_LEN 8 +#define MAC_VR_SNPSVER_POS 0 +#define MAC_VR_SNPSVER_LEN 8 +#define MAC_VR_USERVER_POS 16 +#define MAC_VR_USERVER_LEN 8 + +/* MMC register offsets */ +#define MMC_CR 0x0800 +#define MMC_RISR 0x0804 +#define MMC_TISR 0x0808 +#define MMC_RIER 0x080c +#define MMC_TIER 0x0810 +#define MMC_TXOCTETCOUNT_GB_LO 0x0814 +#define MMC_TXFRAMECOUNT_GB_LO 0x081c +#define MMC_TXBROADCASTFRAMES_G_LO 0x0824 +#define MMC_TXMULTICASTFRAMES_G_LO 0x082c +#define MMC_TX64OCTETS_GB_LO 0x0834 +#define MMC_TX65TO127OCTETS_GB_LO 0x083c +#define MMC_TX128TO255OCTETS_GB_LO 0x0844 +#define MMC_TX256TO511OCTETS_GB_LO 0x084c +#define MMC_TX512TO1023OCTETS_GB_LO 0x0854 +#define MMC_TX1024TOMAXOCTETS_GB_LO 0x085c +#define MMC_TXUNICASTFRAMES_GB_LO 0x0864 +#define MMC_TXMULTICASTFRAMES_GB_LO 0x086c +#define MMC_TXBROADCASTFRAMES_GB_LO 0x0874 +#define MMC_TXUNDERFLOWERROR_LO 0x087c +#define MMC_TXOCTETCOUNT_G_LO 0x0884 +#define MMC_TXFRAMECOUNT_G_LO 0x088c +#define MMC_TXPAUSEFRAMES_LO 0x0894 +#define MMC_TXVLANFRAMES_G_LO 0x089c +#define MMC_RXFRAMECOUNT_GB_LO 0x0900 +#define MMC_RXOCTETCOUNT_GB_LO 0x0908 +#define MMC_RXOCTETCOUNT_G_LO 0x0910 +#define MMC_RXBROADCASTFRAMES_G_LO 0x0918 +#define MMC_RXMULTICASTFRAMES_G_LO 0x0920 +#define MMC_RXCRCERROR_LO 0x0928 +#define MMC_RXRUNTERROR 0x0930 +#define MMC_RXJABBERERROR 0x0934 +#define MMC_RXUNDERSIZE_G 0x0938 +#define MMC_RXOVERSIZE_G 0x093c +#define MMC_RX64OCTETS_GB_LO 0x0940 +#define MMC_RX65TO127OCTETS_GB_LO 0x0948 +#define MMC_RX128TO255OCTETS_GB_LO 0x0950 +#define MMC_RX256TO511OCTETS_GB_LO 0x0958 +#define MMC_RX512TO1023OCTETS_GB_LO 0x0960 +#define MMC_RX1024TOMAXOCTETS_GB_LO 0x0968 +#define MMC_RXUNICASTFRAMES_G_LO 0x0970 +#define MMC_RXLENGTHERROR_LO 0x0978 +#define MMC_RXOUTOFRANGETYPE_LO 0x0980 +#define MMC_RXPAUSEFRAMES_LO 0x0988 +#define MMC_RXFIFOOVERFLOW_LO 0x0990 +#define MMC_RXVLANFRAMES_GB_LO 0x0998 +#define MMC_RXWATCHDOGERROR 0x09a0 + +/* MMC register entry bit positions and sizes */ +#define MMC_CR_CR_POS 0 +#define MMC_CR_CR_LEN 1 +#define MMC_CR_CSR_POS 1 +#define MMC_CR_CSR_LEN 1 +#define MMC_CR_ROR_POS 2 +#define MMC_CR_ROR_LEN 1 +#define MMC_CR_MCF_POS 3 +#define MMC_CR_MCF_LEN 1 +#define MMC_CR_MCT_POS 4 +#define MMC_CR_MCT_LEN 2 +#define MMC_RIER_ALL_INTERRUPTS_POS 0 +#define MMC_RIER_ALL_INTERRUPTS_LEN 23 +#define MMC_RISR_RXFRAMECOUNT_GB_POS 0 +#define MMC_RISR_RXFRAMECOUNT_GB_LEN 1 +#define MMC_RISR_RXOCTETCOUNT_GB_POS 1 +#define MMC_RISR_RXOCTETCOUNT_GB_LEN 1 +#define MMC_RISR_RXOCTETCOUNT_G_POS 2 +#define MMC_RISR_RXOCTETCOUNT_G_LEN 1 +#define MMC_RISR_RXBROADCASTFRAMES_G_POS 3 +#define MMC_RISR_RXBROADCASTFRAMES_G_LEN 1 +#define MMC_RISR_RXMULTICASTFRAMES_G_POS 4 +#define MMC_RISR_RXMULTICASTFRAMES_G_LEN 1 +#define MMC_RISR_RXCRCERROR_POS 5 +#define MMC_RISR_RXCRCERROR_LEN 1 +#define MMC_RISR_RXRUNTERROR_POS 6 +#define MMC_RISR_RXRUNTERROR_LEN 1 +#define MMC_RISR_RXJABBERERROR_POS 7 +#define MMC_RISR_RXJABBERERROR_LEN 1 +#define MMC_RISR_RXUNDERSIZE_G_POS 8 +#define MMC_RISR_RXUNDERSIZE_G_LEN 1 +#define MMC_RISR_RXOVERSIZE_G_POS 9 +#define MMC_RISR_RXOVERSIZE_G_LEN 1 +#define MMC_RISR_RX64OCTETS_GB_POS 10 +#define MMC_RISR_RX64OCTETS_GB_LEN 1 +#define MMC_RISR_RX65TO127OCTETS_GB_POS 11 +#define MMC_RISR_RX65TO127OCTETS_GB_LEN 1 +#define MMC_RISR_RX128TO255OCTETS_GB_POS 12 +#define MMC_RISR_RX128TO255OCTETS_GB_LEN 1 +#define MMC_RISR_RX256TO511OCTETS_GB_POS 13 +#define MMC_RISR_RX256TO511OCTETS_GB_LEN 1 +#define MMC_RISR_RX512TO1023OCTETS_GB_POS 14 +#define MMC_RISR_RX512TO1023OCTETS_GB_LEN 1 +#define MMC_RISR_RX1024TOMAXOCTETS_GB_POS 15 +#define MMC_RISR_RX1024TOMAXOCTETS_GB_LEN 1 +#define MMC_RISR_RXUNICASTFRAMES_G_POS 16 +#define MMC_RISR_RXUNICASTFRAMES_G_LEN 1 +#define MMC_RISR_RXLENGTHERROR_POS 17 +#define MMC_RISR_RXLENGTHERROR_LEN 1 +#define MMC_RISR_RXOUTOFRANGETYPE_POS 18 +#define MMC_RISR_RXOUTOFRANGETYPE_LEN 1 +#define MMC_RISR_RXPAUSEFRAMES_POS 19 +#define MMC_RISR_RXPAUSEFRAMES_LEN 1 +#define MMC_RISR_RXFIFOOVERFLOW_POS 20 +#define MMC_RISR_RXFIFOOVERFLOW_LEN 1 +#define MMC_RISR_RXVLANFRAMES_GB_POS 21 +#define MMC_RISR_RXVLANFRAMES_GB_LEN 1 +#define MMC_RISR_RXWATCHDOGERROR_POS 22 +#define MMC_RISR_RXWATCHDOGERROR_LEN 1 +#define MMC_TIER_ALL_INTERRUPTS_POS 0 +#define MMC_TIER_ALL_INTERRUPTS_LEN 18 +#define MMC_TISR_TXOCTETCOUNT_GB_POS 0 +#define MMC_TISR_TXOCTETCOUNT_GB_LEN 1 +#define MMC_TISR_TXFRAMECOUNT_GB_POS 1 +#define MMC_TISR_TXFRAMECOUNT_GB_LEN 1 +#define MMC_TISR_TXBROADCASTFRAMES_G_POS 2 +#define MMC_TISR_TXBROADCASTFRAMES_G_LEN 1 +#define MMC_TISR_TXMULTICASTFRAMES_G_POS 3 +#define MMC_TISR_TXMULTICASTFRAMES_G_LEN 1 +#define MMC_TISR_TX64OCTETS_GB_POS 4 +#define MMC_TISR_TX64OCTETS_GB_LEN 1 +#define MMC_TISR_TX65TO127OCTETS_GB_POS 5 +#define MMC_TISR_TX65TO127OCTETS_GB_LEN 1 +#define MMC_TISR_TX128TO255OCTETS_GB_POS 6 +#define MMC_TISR_TX128TO255OCTETS_GB_LEN 1 +#define MMC_TISR_TX256TO511OCTETS_GB_POS 7 +#define MMC_TISR_TX256TO511OCTETS_GB_LEN 1 +#define MMC_TISR_TX512TO1023OCTETS_GB_POS 8 +#define MMC_TISR_TX512TO1023OCTETS_GB_LEN 1 +#define MMC_TISR_TX1024TOMAXOCTETS_GB_POS 9 +#define MMC_TISR_TX1024TOMAXOCTETS_GB_LEN 1 +#define MMC_TISR_TXUNICASTFRAMES_GB_POS 10 +#define MMC_TISR_TXUNICASTFRAMES_GB_LEN 1 +#define MMC_TISR_TXMULTICASTFRAMES_GB_POS 11 +#define MMC_TISR_TXMULTICASTFRAMES_GB_LEN 1 +#define MMC_TISR_TXBROADCASTFRAMES_GB_POS 12 +#define MMC_TISR_TXBROADCASTFRAMES_GB_LEN 1 +#define MMC_TISR_TXUNDERFLOWERROR_POS 13 +#define MMC_TISR_TXUNDERFLOWERROR_LEN 1 +#define MMC_TISR_TXOCTETCOUNT_G_POS 14 +#define MMC_TISR_TXOCTETCOUNT_G_LEN 1 +#define MMC_TISR_TXFRAMECOUNT_G_POS 15 +#define MMC_TISR_TXFRAMECOUNT_G_LEN 1 +#define MMC_TISR_TXPAUSEFRAMES_POS 16 +#define MMC_TISR_TXPAUSEFRAMES_LEN 1 +#define MMC_TISR_TXVLANFRAMES_G_POS 17 +#define MMC_TISR_TXVLANFRAMES_G_LEN 1 + +/* MTL register offsets */ +#define MTL_OMR 0x1000 +#define MTL_FDDR 0x1010 +#define MTL_RQDCM0R 0x1030 + +#define MTL_RQDCM_INC 4 +#define MTL_RQDCM_Q_PER_REG 4 + +/* MTL register entry bit positions and sizes */ +#define MTL_OMR_ETSALG_POS 5 +#define MTL_OMR_ETSALG_LEN 2 +#define MTL_OMR_RAA_POS 2 +#define MTL_OMR_RAA_LEN 1 + +/* MTL queue register offsets + * Multiple queues can be active. The first queue has registers + * that begin at 0x1100. Each subsequent queue has registers that + * are accessed using an offset of 0x80 from the previous queue. + */ +#define MTL_Q_BASE 0x1100 +#define MTL_Q_INC 0x80 + +#define MTL_Q_TQOMR 0x00 +#define MTL_Q_RQOMR 0x40 +#define MTL_Q_RQDR 0x48 +#define MTL_Q_RQFCR 0x50 +#define MTL_Q_IER 0x70 +#define MTL_Q_ISR 0x74 + +/* MTL queue register entry bit positions and sizes */ +#define MTL_Q_RQDR_PRXQ_POS 16 +#define MTL_Q_RQDR_PRXQ_LEN 14 +#define MTL_Q_RQDR_RXQSTS_POS 4 +#define MTL_Q_RQDR_RXQSTS_LEN 2 +#define MTL_Q_RQFCR_RFA_POS 1 +#define MTL_Q_RQFCR_RFA_LEN 6 +#define MTL_Q_RQFCR_RFD_POS 17 +#define MTL_Q_RQFCR_RFD_LEN 6 +#define MTL_Q_RQOMR_EHFC_POS 7 +#define MTL_Q_RQOMR_EHFC_LEN 1 +#define MTL_Q_RQOMR_RQS_POS 16 +#define MTL_Q_RQOMR_RQS_LEN 9 +#define MTL_Q_RQOMR_RSF_POS 5 +#define MTL_Q_RQOMR_RSF_LEN 1 +#define MTL_Q_RQOMR_FEP_POS 4 +#define MTL_Q_RQOMR_FEP_LEN 1 +#define MTL_Q_RQOMR_FUP_POS 3 +#define MTL_Q_RQOMR_FUP_LEN 1 +#define MTL_Q_RQOMR_RTC_POS 0 +#define MTL_Q_RQOMR_RTC_LEN 2 +#define MTL_Q_TQOMR_FTQ_POS 0 +#define MTL_Q_TQOMR_FTQ_LEN 1 +#define MTL_Q_TQOMR_Q2TCMAP_POS 8 +#define MTL_Q_TQOMR_Q2TCMAP_LEN 3 +#define MTL_Q_TQOMR_TQS_POS 16 +#define MTL_Q_TQOMR_TQS_LEN 10 +#define MTL_Q_TQOMR_TSF_POS 1 +#define MTL_Q_TQOMR_TSF_LEN 1 +#define MTL_Q_TQOMR_TTC_POS 4 +#define MTL_Q_TQOMR_TTC_LEN 3 +#define MTL_Q_TQOMR_TXQEN_POS 2 +#define MTL_Q_TQOMR_TXQEN_LEN 2 + +/* MTL queue register value */ +#define MTL_RSF_DISABLE 0x00 +#define MTL_RSF_ENABLE 0x01 +#define MTL_TSF_DISABLE 0x00 +#define MTL_TSF_ENABLE 0x01 + +#define MTL_RX_THRESHOLD_64 0x00 +#define MTL_RX_THRESHOLD_96 0x02 +#define MTL_RX_THRESHOLD_128 0x03 +#define MTL_TX_THRESHOLD_64 0x00 +#define MTL_TX_THRESHOLD_96 0x02 +#define MTL_TX_THRESHOLD_128 0x03 +#define MTL_TX_THRESHOLD_192 0x04 +#define MTL_TX_THRESHOLD_256 0x05 +#define MTL_TX_THRESHOLD_384 0x06 +#define MTL_TX_THRESHOLD_512 0x07 + +#define MTL_ETSALG_WRR 0x00 +#define MTL_ETSALG_WFQ 0x01 +#define MTL_ETSALG_DWRR 0x02 +#define MTL_RAA_SP 0x00 +#define MTL_RAA_WSP 0x01 + +#define MTL_Q_DISABLED 0x00 +#define MTL_Q_ENABLED 0x02 + +#define MTL_RQDCM0R_Q0MDMACH 0x0 +#define MTL_RQDCM0R_Q1MDMACH 0x00000100 +#define MTL_RQDCM0R_Q2MDMACH 0x00020000 +#define MTL_RQDCM0R_Q3MDMACH 0x03000000 +#define MTL_RQDCM1R_Q4MDMACH 0x00000004 +#define MTL_RQDCM1R_Q5MDMACH 0x00000500 +#define MTL_RQDCM1R_Q6MDMACH 0x00060000 +#define MTL_RQDCM1R_Q7MDMACH 0x07000000 +#define MTL_RQDCM2R_Q8MDMACH 0x00000008 +#define MTL_RQDCM2R_Q9MDMACH 0x00000900 +#define MTL_RQDCM2R_Q10MDMACH 0x000A0000 +#define MTL_RQDCM2R_Q11MDMACH 0x0B000000 + +/* MTL traffic class register offsets + * Multiple traffic classes can be active. The first class has registers + * that begin at 0x1100. Each subsequent queue has registers that + * are accessed using an offset of 0x80 from the previous queue. + */ +#define MTL_TC_BASE MTL_Q_BASE +#define MTL_TC_INC MTL_Q_INC + +#define MTL_TC_ETSCR 0x10 +#define MTL_TC_ETSSR 0x14 +#define MTL_TC_QWR 0x18 + +/* MTL traffic class register entry bit positions and sizes */ +#define MTL_TC_ETSCR_TSA_POS 0 +#define MTL_TC_ETSCR_TSA_LEN 2 +#define MTL_TC_QWR_QW_POS 0 +#define MTL_TC_QWR_QW_LEN 21 + +/* MTL traffic class register value */ +#define MTL_TSA_SP 0x00 +#define MTL_TSA_ETS 0x02 + +/* DMA register offsets */ +#define DMA_MR 0x3000 +#define DMA_SBMR 0x3004 +#define DMA_ISR 0x3008 +#define DMA_DSR0 0x3020 +#define DMA_DSR1 0x3024 + +/* DMA register entry bit positions and sizes */ +#define DMA_ISR_MACIS_POS 17 +#define DMA_ISR_MACIS_LEN 1 +#define DMA_ISR_MTLIS_POS 16 +#define DMA_ISR_MTLIS_LEN 1 +#define DMA_MR_SWR_POS 0 +#define DMA_MR_SWR_LEN 1 +#define DMA_SBMR_EAME_POS 11 +#define DMA_SBMR_EAME_LEN 1 +#define DMA_SBMR_BLEN_64_POS 5 +#define DMA_SBMR_BLEN_64_LEN 1 +#define DMA_SBMR_BLEN_128_POS 6 +#define DMA_SBMR_BLEN_128_LEN 1 +#define DMA_SBMR_BLEN_256_POS 7 +#define DMA_SBMR_BLEN_256_LEN 1 +#define DMA_SBMR_UNDEF_POS 0 +#define DMA_SBMR_UNDEF_LEN 1 + +/* DMA register values */ +#define DMA_DSR_RPS_LEN 4 +#define DMA_DSR_TPS_LEN 4 +#define DMA_DSR_Q_LEN (DMA_DSR_RPS_LEN + DMA_DSR_TPS_LEN) +#define DMA_DSR0_TPS_START 12 +#define DMA_DSRX_FIRST_QUEUE 3 +#define DMA_DSRX_INC 4 +#define DMA_DSRX_QPR 4 +#define DMA_DSRX_TPS_START 4 +#define DMA_TPS_STOPPED 0x00 +#define DMA_TPS_SUSPENDED 0x06 + +/* DMA channel register offsets + * Multiple channels can be active. The first channel has registers + * that begin at 0x3100. Each subsequent channel has registers that + * are accessed using an offset of 0x80 from the previous channel. + */ +#define DMA_CH_BASE 0x3100 +#define DMA_CH_INC 0x80 + +#define DMA_CH_CR 0x00 +#define DMA_CH_TCR 0x04 +#define DMA_CH_RCR 0x08 +#define DMA_CH_TDLR_HI 0x10 +#define DMA_CH_TDLR_LO 0x14 +#define DMA_CH_RDLR_HI 0x18 +#define DMA_CH_RDLR_LO 0x1c +#define DMA_CH_TDTR_LO 0x24 +#define DMA_CH_RDTR_LO 0x2c +#define DMA_CH_TDRLR 0x30 +#define DMA_CH_RDRLR 0x34 +#define DMA_CH_IER 0x38 +#define DMA_CH_RIWT 0x3c +#define DMA_CH_SR 0x60 + +/* DMA channel register entry bit positions and sizes */ +#define DMA_CH_CR_PBLX8_POS 16 +#define DMA_CH_CR_PBLX8_LEN 1 +#define DMA_CH_CR_SPH_POS 24 +#define DMA_CH_CR_SPH_LEN 1 +#define DMA_CH_IER_AIE_POS 15 +#define DMA_CH_IER_AIE_LEN 1 +#define DMA_CH_IER_FBEE_POS 12 +#define DMA_CH_IER_FBEE_LEN 1 +#define DMA_CH_IER_NIE_POS 16 +#define DMA_CH_IER_NIE_LEN 1 +#define DMA_CH_IER_RBUE_POS 7 +#define DMA_CH_IER_RBUE_LEN 1 +#define DMA_CH_IER_RIE_POS 6 +#define DMA_CH_IER_RIE_LEN 1 +#define DMA_CH_IER_RSE_POS 8 +#define DMA_CH_IER_RSE_LEN 1 +#define DMA_CH_IER_TBUE_POS 2 +#define DMA_CH_IER_TBUE_LEN 1 +#define DMA_CH_IER_TIE_POS 0 +#define DMA_CH_IER_TIE_LEN 1 +#define DMA_CH_IER_TXSE_POS 1 +#define DMA_CH_IER_TXSE_LEN 1 +#define DMA_CH_RCR_PBL_POS 16 +#define DMA_CH_RCR_PBL_LEN 6 +#define DMA_CH_RCR_RBSZ_POS 1 +#define DMA_CH_RCR_RBSZ_LEN 14 +#define DMA_CH_RCR_SR_POS 0 +#define DMA_CH_RCR_SR_LEN 1 +#define DMA_CH_RIWT_RWT_POS 0 +#define DMA_CH_RIWT_RWT_LEN 8 +#define DMA_CH_SR_FBE_POS 12 +#define DMA_CH_SR_FBE_LEN 1 +#define DMA_CH_SR_RBU_POS 7 +#define DMA_CH_SR_RBU_LEN 1 +#define DMA_CH_SR_RI_POS 6 +#define DMA_CH_SR_RI_LEN 1 +#define DMA_CH_SR_RPS_POS 8 +#define DMA_CH_SR_RPS_LEN 1 +#define DMA_CH_SR_TBU_POS 2 +#define DMA_CH_SR_TBU_LEN 1 +#define DMA_CH_SR_TI_POS 0 +#define DMA_CH_SR_TI_LEN 1 +#define DMA_CH_SR_TPS_POS 1 +#define DMA_CH_SR_TPS_LEN 1 +#define DMA_CH_TCR_OSP_POS 4 +#define DMA_CH_TCR_OSP_LEN 1 +#define DMA_CH_TCR_PBL_POS 16 +#define DMA_CH_TCR_PBL_LEN 6 +#define DMA_CH_TCR_ST_POS 0 +#define DMA_CH_TCR_ST_LEN 1 +#define DMA_CH_TCR_TSE_POS 12 +#define DMA_CH_TCR_TSE_LEN 1 + +/* DMA channel register values */ +#define DMA_OSP_DISABLE 0x00 +#define DMA_OSP_ENABLE 0x01 +#define DMA_PBL_1 1 +#define DMA_PBL_2 2 +#define DMA_PBL_4 4 +#define DMA_PBL_8 8 +#define DMA_PBL_16 16 +#define DMA_PBL_32 32 +#define DMA_PBL_64 64 +#define DMA_PBL_128 128 +#define DMA_PBL_256 256 +#define DMA_PBL_X8_DISABLE 0x00 +#define DMA_PBL_X8_ENABLE 0x01 + +/* Descriptor/Packet entry bit positions and sizes */ +#define RX_PACKET_ERRORS_CRC_POS 2 +#define RX_PACKET_ERRORS_CRC_LEN 1 +#define RX_PACKET_ERRORS_FRAME_POS 3 +#define RX_PACKET_ERRORS_FRAME_LEN 1 +#define RX_PACKET_ERRORS_LENGTH_POS 0 +#define RX_PACKET_ERRORS_LENGTH_LEN 1 +#define RX_PACKET_ERRORS_OVERRUN_POS 1 +#define RX_PACKET_ERRORS_OVERRUN_LEN 1 + +#define RX_PACKET_ATTRIBUTES_CSUM_DONE_POS 0 +#define RX_PACKET_ATTRIBUTES_CSUM_DONE_LEN 1 +#define RX_PACKET_ATTRIBUTES_VLAN_CTAG_POS 1 +#define RX_PACKET_ATTRIBUTES_VLAN_CTAG_LEN 1 +#define RX_PACKET_ATTRIBUTES_INCOMPLETE_POS 2 +#define RX_PACKET_ATTRIBUTES_INCOMPLETE_LEN 1 +#define RX_PACKET_ATTRIBUTES_CONTEXT_NEXT_POS 3 +#define RX_PACKET_ATTRIBUTES_CONTEXT_NEXT_LEN 1 +#define RX_PACKET_ATTRIBUTES_CONTEXT_POS 4 +#define RX_PACKET_ATTRIBUTES_CONTEXT_LEN 1 +#define RX_PACKET_ATTRIBUTES_RX_TSTAMP_POS 5 +#define RX_PACKET_ATTRIBUTES_RX_TSTAMP_LEN 1 +#define RX_PACKET_ATTRIBUTES_RSS_HASH_POS 6 +#define RX_PACKET_ATTRIBUTES_RSS_HASH_LEN 1 + +#define RX_NORMAL_DESC0_OVT_POS 0 +#define RX_NORMAL_DESC0_OVT_LEN 16 +#define RX_NORMAL_DESC2_HL_POS 0 +#define RX_NORMAL_DESC2_HL_LEN 10 +#define RX_NORMAL_DESC3_CDA_POS 27 +#define RX_NORMAL_DESC3_CDA_LEN 1 +#define RX_NORMAL_DESC3_CTXT_POS 30 +#define RX_NORMAL_DESC3_CTXT_LEN 1 +#define RX_NORMAL_DESC3_ES_POS 15 +#define RX_NORMAL_DESC3_ES_LEN 1 +#define RX_NORMAL_DESC3_ETLT_POS 16 +#define RX_NORMAL_DESC3_ETLT_LEN 4 +#define RX_NORMAL_DESC3_FD_POS 29 +#define RX_NORMAL_DESC3_FD_LEN 1 +#define RX_NORMAL_DESC3_INTE_POS 30 +#define RX_NORMAL_DESC3_INTE_LEN 1 +#define RX_NORMAL_DESC3_L34T_POS 20 +#define RX_NORMAL_DESC3_L34T_LEN 4 +#define RX_NORMAL_DESC3_LD_POS 28 +#define RX_NORMAL_DESC3_LD_LEN 1 +#define RX_NORMAL_DESC3_OWN_POS 31 +#define RX_NORMAL_DESC3_OWN_LEN 1 +#define RX_NORMAL_DESC3_PL_POS 0 +#define RX_NORMAL_DESC3_PL_LEN 14 +#define RX_NORMAL_DESC3_RSV_POS 26 +#define RX_NORMAL_DESC3_RSV_LEN 1 + +#define RX_DESC3_L34T_IPV4_TCP 1 +#define RX_DESC3_L34T_IPV4_UDP 2 +#define RX_DESC3_L34T_IPV4_ICMP 3 +#define RX_DESC3_L34T_IPV6_TCP 9 +#define RX_DESC3_L34T_IPV6_UDP 10 +#define RX_DESC3_L34T_IPV6_ICMP 11 + +#define RX_CONTEXT_DESC3_TSA_POS 4 +#define RX_CONTEXT_DESC3_TSA_LEN 1 +#define RX_CONTEXT_DESC3_TSD_POS 6 +#define RX_CONTEXT_DESC3_TSD_LEN 1 + +#define TX_PACKET_ATTRIBUTES_CSUM_ENABLE_POS 0 +#define TX_PACKET_ATTRIBUTES_CSUM_ENABLE_LEN 1 +#define TX_PACKET_ATTRIBUTES_TSO_ENABLE_POS 1 +#define TX_PACKET_ATTRIBUTES_TSO_ENABLE_LEN 1 +#define TX_PACKET_ATTRIBUTES_VLAN_CTAG_POS 2 +#define TX_PACKET_ATTRIBUTES_VLAN_CTAG_LEN 1 +#define TX_PACKET_ATTRIBUTES_PTP_POS 3 +#define TX_PACKET_ATTRIBUTES_PTP_LEN 1 + +#define TX_CONTEXT_DESC2_MSS_POS 0 +#define TX_CONTEXT_DESC2_MSS_LEN 15 +#define TX_CONTEXT_DESC3_CTXT_POS 30 +#define TX_CONTEXT_DESC3_CTXT_LEN 1 +#define TX_CONTEXT_DESC3_TCMSSV_POS 26 +#define TX_CONTEXT_DESC3_TCMSSV_LEN 1 +#define TX_CONTEXT_DESC3_VLTV_POS 16 +#define TX_CONTEXT_DESC3_VLTV_LEN 1 +#define TX_CONTEXT_DESC3_VT_POS 0 +#define TX_CONTEXT_DESC3_VT_LEN 16 + +#define TX_NORMAL_DESC2_HL_B1L_POS 0 +#define TX_NORMAL_DESC2_HL_B1L_LEN 14 +#define TX_NORMAL_DESC2_IC_POS 31 +#define TX_NORMAL_DESC2_IC_LEN 1 +#define TX_NORMAL_DESC2_TTSE_POS 30 +#define TX_NORMAL_DESC2_TTSE_LEN 1 +#define TX_NORMAL_DESC2_VTIR_POS 14 +#define TX_NORMAL_DESC2_VTIR_LEN 2 +#define TX_NORMAL_DESC3_CIC_POS 16 +#define TX_NORMAL_DESC3_CIC_LEN 2 +#define TX_NORMAL_DESC3_CPC_POS 26 +#define TX_NORMAL_DESC3_CPC_LEN 2 +#define TX_NORMAL_DESC3_CTXT_POS 30 +#define TX_NORMAL_DESC3_CTXT_LEN 1 +#define TX_NORMAL_DESC3_FD_POS 29 +#define TX_NORMAL_DESC3_FD_LEN 1 +#define TX_NORMAL_DESC3_FL_POS 0 +#define TX_NORMAL_DESC3_FL_LEN 15 +#define TX_NORMAL_DESC3_LD_POS 28 +#define TX_NORMAL_DESC3_LD_LEN 1 +#define TX_NORMAL_DESC3_OWN_POS 31 +#define TX_NORMAL_DESC3_OWN_LEN 1 +#define TX_NORMAL_DESC3_TCPHDRLEN_POS 19 +#define TX_NORMAL_DESC3_TCPHDRLEN_LEN 4 +#define TX_NORMAL_DESC3_TCPPL_POS 0 +#define TX_NORMAL_DESC3_TCPPL_LEN 18 +#define TX_NORMAL_DESC3_TSE_POS 18 +#define TX_NORMAL_DESC3_TSE_LEN 1 + +#define TX_NORMAL_DESC2_VLAN_INSERT 0x2 + +#define XLGMAC_MTL_REG(pdata, n, reg) \ + ((pdata)->mac_regs + MTL_Q_BASE + ((n) * MTL_Q_INC) + (reg)) + +#define XLGMAC_DMA_REG(channel, reg) ((channel)->dma_regs + (reg)) + +#endif /* __DWC_XLGMAC_REG_H__ */ diff --git a/drivers/net/ethernet/synopsys/dwc-xlgmac.h b/drivers/net/ethernet/synopsys/dwc-xlgmac.h new file mode 100644 index 000000000000..7a4dc643b2b9 --- /dev/null +++ b/drivers/net/ethernet/synopsys/dwc-xlgmac.h @@ -0,0 +1,651 @@ +/* Synopsys DesignWare Core Enterprise Ethernet (XLGMAC) Driver + * + * Copyright (c) 2017 Synopsys, Inc. (www.synopsys.com) + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the + * Free Software Foundation; either version 2 of the License, or (at your + * option) any later version. + * + * This Synopsys DWC XLGMAC software driver and associated documentation + * (hereinafter the "Software") is an unsupported proprietary work of + * Synopsys, Inc. unless otherwise expressly agreed to in writing between + * Synopsys and you. The Software IS NOT an item of Licensed Software or a + * Licensed Product under any End User Software License Agreement or + * Agreement for Licensed Products with Synopsys or any supplement thereto. + * Synopsys is a registered trademark of Synopsys, Inc. Other names included + * in the SOFTWARE may be the trademarks of their respective owners. + */ + +#ifndef __DWC_XLGMAC_H__ +#define __DWC_XLGMAC_H__ + +#include <linux/dma-mapping.h> +#include <linux/netdevice.h> +#include <linux/workqueue.h> +#include <linux/phy.h> +#include <linux/if_vlan.h> +#include <linux/bitops.h> +#include <linux/timecounter.h> + +#define XLGMAC_DRV_NAME "dwc-xlgmac" +#define XLGMAC_DRV_VERSION "1.0.0" +#define XLGMAC_DRV_DESC "Synopsys DWC XLGMAC Driver" + +/* Descriptor related parameters */ +#define XLGMAC_TX_DESC_CNT 1024 +#define XLGMAC_TX_DESC_MIN_FREE (XLGMAC_TX_DESC_CNT >> 3) +#define XLGMAC_TX_DESC_MAX_PROC (XLGMAC_TX_DESC_CNT >> 1) +#define XLGMAC_RX_DESC_CNT 1024 +#define XLGMAC_RX_DESC_MAX_DIRTY (XLGMAC_RX_DESC_CNT >> 3) + +/* Descriptors required for maximum contiguous TSO/GSO packet */ +#define XLGMAC_TX_MAX_SPLIT ((GSO_MAX_SIZE / XLGMAC_TX_MAX_BUF_SIZE) + 1) + +/* Maximum possible descriptors needed for a SKB */ +#define XLGMAC_TX_MAX_DESC_NR (MAX_SKB_FRAGS + XLGMAC_TX_MAX_SPLIT + 2) + +#define XLGMAC_TX_MAX_BUF_SIZE (0x3fff & ~(64 - 1)) +#define XLGMAC_RX_MIN_BUF_SIZE (ETH_FRAME_LEN + ETH_FCS_LEN + VLAN_HLEN) +#define XLGMAC_RX_BUF_ALIGN 64 + +/* Maximum Size for Splitting the Header Data + * Keep in sync with SKB_ALLOC_SIZE + * 3'b000: 64 bytes, 3'b001: 128 bytes + * 3'b010: 256 bytes, 3'b011: 512 bytes + * 3'b100: 1023 bytes , 3'b101'3'b111: Reserved + */ +#define XLGMAC_SPH_HDSMS_SIZE 3 +#define XLGMAC_SKB_ALLOC_SIZE 512 + +#define XLGMAC_MAX_FIFO 81920 + +#define XLGMAC_MAX_DMA_CHANNELS 16 +#define XLGMAC_DMA_STOP_TIMEOUT 5 +#define XLGMAC_DMA_INTERRUPT_MASK 0x31c7 + +/* Default coalescing parameters */ +#define XLGMAC_INIT_DMA_TX_USECS 1000 +#define XLGMAC_INIT_DMA_TX_FRAMES 25 +#define XLGMAC_INIT_DMA_RX_USECS 30 +#define XLGMAC_INIT_DMA_RX_FRAMES 25 + +/* Flow control queue count */ +#define XLGMAC_MAX_FLOW_CONTROL_QUEUES 8 + +/* System clock is 125 MHz */ +#define XLGMAC_SYSCLOCK 125000000 + +/* Maximum MAC address hash table size (256 bits = 8 bytes) */ +#define XLGMAC_MAC_HASH_TABLE_SIZE 8 + +/* Receive Side Scaling */ +#define XLGMAC_RSS_HASH_KEY_SIZE 40 +#define XLGMAC_RSS_MAX_TABLE_SIZE 256 +#define XLGMAC_RSS_LOOKUP_TABLE_TYPE 0 +#define XLGMAC_RSS_HASH_KEY_TYPE 1 + +#define XLGMAC_STD_PACKET_MTU 1500 +#define XLGMAC_JUMBO_PACKET_MTU 9000 + +/* Helper macro for descriptor handling + * Always use XLGMAC_GET_DESC_DATA to access the descriptor data + */ +#define XLGMAC_GET_DESC_DATA(ring, idx) ({ \ + typeof(ring) _ring = (ring); \ + ((_ring)->desc_data_head + \ + ((idx) & ((_ring)->dma_desc_count - 1))); \ +}) + +#define XLGMAC_GET_REG_BITS(var, pos, len) ({ \ + typeof(pos) _pos = (pos); \ + typeof(len) _len = (len); \ + ((var) & GENMASK(_pos + _len - 1, _pos)) >> (_pos); \ +}) + +#define XLGMAC_GET_REG_BITS_LE(var, pos, len) ({ \ + typeof(pos) _pos = (pos); \ + typeof(len) _len = (len); \ + typeof(var) _var = le32_to_cpu((var)); \ + ((_var) & GENMASK(_pos + _len - 1, _pos)) >> (_pos); \ +}) + +#define XLGMAC_SET_REG_BITS(var, pos, len, val) ({ \ + typeof(var) _var = (var); \ + typeof(pos) _pos = (pos); \ + typeof(len) _len = (len); \ + typeof(val) _val = (val); \ + _val = (_val << _pos) & GENMASK(_pos + _len - 1, _pos); \ + _var = (_var & ~GENMASK(_pos + _len - 1, _pos)) | _val; \ +}) + +#define XLGMAC_SET_REG_BITS_LE(var, pos, len, val) ({ \ + typeof(var) _var = (var); \ + typeof(pos) _pos = (pos); \ + typeof(len) _len = (len); \ + typeof(val) _val = (val); \ + _val = (_val << _pos) & GENMASK(_pos + _len - 1, _pos); \ + _var = (_var & ~GENMASK(_pos + _len - 1, _pos)) | _val; \ + cpu_to_le32(_var); \ +}) + +struct xlgmac_pdata; + +enum xlgmac_int { + XLGMAC_INT_DMA_CH_SR_TI, + XLGMAC_INT_DMA_CH_SR_TPS, + XLGMAC_INT_DMA_CH_SR_TBU, + XLGMAC_INT_DMA_CH_SR_RI, + XLGMAC_INT_DMA_CH_SR_RBU, + XLGMAC_INT_DMA_CH_SR_RPS, + XLGMAC_INT_DMA_CH_SR_TI_RI, + XLGMAC_INT_DMA_CH_SR_FBE, + XLGMAC_INT_DMA_ALL, +}; + +struct xlgmac_stats { + /* MMC TX counters */ + u64 txoctetcount_gb; + u64 txframecount_gb; + u64 txbroadcastframes_g; + u64 txmulticastframes_g; + u64 tx64octets_gb; + u64 tx65to127octets_gb; + u64 tx128to255octets_gb; + u64 tx256to511octets_gb; + u64 tx512to1023octets_gb; + u64 tx1024tomaxoctets_gb; + u64 txunicastframes_gb; + u64 txmulticastframes_gb; + u64 txbroadcastframes_gb; + u64 txunderflowerror; + u64 txoctetcount_g; + u64 txframecount_g; + u64 txpauseframes; + u64 txvlanframes_g; + + /* MMC RX counters */ + u64 rxframecount_gb; + u64 rxoctetcount_gb; + u64 rxoctetcount_g; + u64 rxbroadcastframes_g; + u64 rxmulticastframes_g; + u64 rxcrcerror; + u64 rxrunterror; + u64 rxjabbererror; + u64 rxundersize_g; + u64 rxoversize_g; + u64 rx64octets_gb; + u64 rx65to127octets_gb; + u64 rx128to255octets_gb; + u64 rx256to511octets_gb; + u64 rx512to1023octets_gb; + u64 rx1024tomaxoctets_gb; + u64 rxunicastframes_g; + u64 rxlengtherror; + u64 rxoutofrangetype; + u64 rxpauseframes; + u64 rxfifooverflow; + u64 rxvlanframes_gb; + u64 rxwatchdogerror; + + /* Extra counters */ + u64 tx_tso_packets; + u64 rx_split_header_packets; + u64 rx_buffer_unavailable; +}; + +struct xlgmac_ring_buf { + struct sk_buff *skb; + dma_addr_t skb_dma; + unsigned int skb_len; +}; + +/* Common Tx and Rx DMA hardware descriptor */ +struct xlgmac_dma_desc { + __le32 desc0; + __le32 desc1; + __le32 desc2; + __le32 desc3; +}; + +/* Page allocation related values */ +struct xlgmac_page_alloc { + struct page *pages; + unsigned int pages_len; + unsigned int pages_offset; + + dma_addr_t pages_dma; +}; + +/* Ring entry buffer data */ +struct xlgmac_buffer_data { + struct xlgmac_page_alloc pa; + struct xlgmac_page_alloc pa_unmap; + + dma_addr_t dma_base; + unsigned long dma_off; + unsigned int dma_len; +}; + +/* Tx-related desc data */ +struct xlgmac_tx_desc_data { + unsigned int packets; /* BQL packet count */ + unsigned int bytes; /* BQL byte count */ +}; + +/* Rx-related desc data */ +struct xlgmac_rx_desc_data { + struct xlgmac_buffer_data hdr; /* Header locations */ + struct xlgmac_buffer_data buf; /* Payload locations */ + + unsigned short hdr_len; /* Length of received header */ + unsigned short len; /* Length of received packet */ +}; + +struct xlgmac_pkt_info { + struct sk_buff *skb; + + unsigned int attributes; + + unsigned int errors; + + /* descriptors needed for this packet */ + unsigned int desc_count; + unsigned int length; + + unsigned int tx_packets; + unsigned int tx_bytes; + + unsigned int header_len; + unsigned int tcp_header_len; + unsigned int tcp_payload_len; + unsigned short mss; + + unsigned short vlan_ctag; + + u64 rx_tstamp; + + u32 rss_hash; + enum pkt_hash_types rss_hash_type; +}; + +struct xlgmac_desc_data { + /* dma_desc: Virtual address of descriptor + * dma_desc_addr: DMA address of descriptor + */ + struct xlgmac_dma_desc *dma_desc; + dma_addr_t dma_desc_addr; + + /* skb: Virtual address of SKB + * skb_dma: DMA address of SKB data + * skb_dma_len: Length of SKB DMA area + */ + struct sk_buff *skb; + dma_addr_t skb_dma; + unsigned int skb_dma_len; + + /* Tx/Rx -related data */ + struct xlgmac_tx_desc_data tx; + struct xlgmac_rx_desc_data rx; + + unsigned int mapped_as_page; + + /* Incomplete receive save location. If the budget is exhausted + * or the last descriptor (last normal descriptor or a following + * context descriptor) has not been DMA'd yet the current state + * of the receive processing needs to be saved. + */ + unsigned int state_saved; + struct { + struct sk_buff *skb; + unsigned int len; + unsigned int error; + } state; +}; + +struct xlgmac_ring { + /* Per packet related information */ + struct xlgmac_pkt_info pkt_info; + + /* Virtual/DMA addresses of DMA descriptor list and the total count */ + struct xlgmac_dma_desc *dma_desc_head; + dma_addr_t dma_desc_head_addr; + unsigned int dma_desc_count; + + /* Array of descriptor data corresponding the DMA descriptor + * (always use the XLGMAC_GET_DESC_DATA macro to access this data) + */ + struct xlgmac_desc_data *desc_data_head; + + /* Page allocation for RX buffers */ + struct xlgmac_page_alloc rx_hdr_pa; + struct xlgmac_page_alloc rx_buf_pa; + + /* Ring index values + * cur - Tx: index of descriptor to be used for current transfer + * Rx: index of descriptor to check for packet availability + * dirty - Tx: index of descriptor to check for transfer complete + * Rx: index of descriptor to check for buffer reallocation + */ + unsigned int cur; + unsigned int dirty; + + /* Coalesce frame count used for interrupt bit setting */ + unsigned int coalesce_count; + + union { + struct { + unsigned int xmit_more; + unsigned int queue_stopped; + unsigned short cur_mss; + unsigned short cur_vlan_ctag; + } tx; + }; +} ____cacheline_aligned; + +struct xlgmac_channel { + char name[16]; + + /* Address of private data area for device */ + struct xlgmac_pdata *pdata; + + /* Queue index and base address of queue's DMA registers */ + unsigned int queue_index; + void __iomem *dma_regs; + + /* Per channel interrupt irq number */ + int dma_irq; + char dma_irq_name[IFNAMSIZ + 32]; + + /* Netdev related settings */ + struct napi_struct napi; + + unsigned int saved_ier; + + unsigned int tx_timer_active; + struct timer_list tx_timer; + + struct xlgmac_ring *tx_ring; + struct xlgmac_ring *rx_ring; +} ____cacheline_aligned; + +struct xlgmac_desc_ops { + int (*alloc_channles_and_rings)(struct xlgmac_pdata *pdata); + void (*free_channels_and_rings)(struct xlgmac_pdata *pdata); + int (*map_tx_skb)(struct xlgmac_channel *channel, + struct sk_buff *skb); + int (*map_rx_buffer)(struct xlgmac_pdata *pdata, + struct xlgmac_ring *ring, + struct xlgmac_desc_data *desc_data); + void (*unmap_desc_data)(struct xlgmac_pdata *pdata, + struct xlgmac_desc_data *desc_data); + void (*tx_desc_init)(struct xlgmac_pdata *pdata); + void (*rx_desc_init)(struct xlgmac_pdata *pdata); +}; + +struct xlgmac_hw_ops { + int (*init)(struct xlgmac_pdata *pdata); + int (*exit)(struct xlgmac_pdata *pdata); + + int (*tx_complete)(struct xlgmac_dma_desc *dma_desc); + + void (*enable_tx)(struct xlgmac_pdata *pdata); + void (*disable_tx)(struct xlgmac_pdata *pdata); + void (*enable_rx)(struct xlgmac_pdata *pdata); + void (*disable_rx)(struct xlgmac_pdata *pdata); + + int (*enable_int)(struct xlgmac_channel *channel, + enum xlgmac_int int_id); + int (*disable_int)(struct xlgmac_channel *channel, + enum xlgmac_int int_id); + void (*dev_xmit)(struct xlgmac_channel *channel); + int (*dev_read)(struct xlgmac_channel *channel); + + int (*set_mac_address)(struct xlgmac_pdata *pdata, u8 *addr); + int (*config_rx_mode)(struct xlgmac_pdata *pdata); + int (*enable_rx_csum)(struct xlgmac_pdata *pdata); + int (*disable_rx_csum)(struct xlgmac_pdata *pdata); + + /* For MII speed configuration */ + int (*set_xlgmii_25000_speed)(struct xlgmac_pdata *pdata); + int (*set_xlgmii_40000_speed)(struct xlgmac_pdata *pdata); + int (*set_xlgmii_50000_speed)(struct xlgmac_pdata *pdata); + int (*set_xlgmii_100000_speed)(struct xlgmac_pdata *pdata); + + /* For descriptor related operation */ + void (*tx_desc_init)(struct xlgmac_channel *channel); + void (*rx_desc_init)(struct xlgmac_channel *channel); + void (*tx_desc_reset)(struct xlgmac_desc_data *desc_data); + void (*rx_desc_reset)(struct xlgmac_pdata *pdata, + struct xlgmac_desc_data *desc_data, + unsigned int index); + int (*is_last_desc)(struct xlgmac_dma_desc *dma_desc); + int (*is_context_desc)(struct xlgmac_dma_desc *dma_desc); + void (*tx_start_xmit)(struct xlgmac_channel *channel, + struct xlgmac_ring *ring); + + /* For Flow Control */ + int (*config_tx_flow_control)(struct xlgmac_pdata *pdata); + int (*config_rx_flow_control)(struct xlgmac_pdata *pdata); + + /* For Vlan related config */ + int (*enable_rx_vlan_stripping)(struct xlgmac_pdata *pdata); + int (*disable_rx_vlan_stripping)(struct xlgmac_pdata *pdata); + int (*enable_rx_vlan_filtering)(struct xlgmac_pdata *pdata); + int (*disable_rx_vlan_filtering)(struct xlgmac_pdata *pdata); + int (*update_vlan_hash_table)(struct xlgmac_pdata *pdata); + + /* For RX coalescing */ + int (*config_rx_coalesce)(struct xlgmac_pdata *pdata); + int (*config_tx_coalesce)(struct xlgmac_pdata *pdata); + unsigned int (*usec_to_riwt)(struct xlgmac_pdata *pdata, + unsigned int usec); + unsigned int (*riwt_to_usec)(struct xlgmac_pdata *pdata, + unsigned int riwt); + + /* For RX and TX threshold config */ + int (*config_rx_threshold)(struct xlgmac_pdata *pdata, + unsigned int val); + int (*config_tx_threshold)(struct xlgmac_pdata *pdata, + unsigned int val); + + /* For RX and TX Store and Forward Mode config */ + int (*config_rsf_mode)(struct xlgmac_pdata *pdata, + unsigned int val); + int (*config_tsf_mode)(struct xlgmac_pdata *pdata, + unsigned int val); + + /* For TX DMA Operate on Second Frame config */ + int (*config_osp_mode)(struct xlgmac_pdata *pdata); + + /* For RX and TX PBL config */ + int (*config_rx_pbl_val)(struct xlgmac_pdata *pdata); + int (*get_rx_pbl_val)(struct xlgmac_pdata *pdata); + int (*config_tx_pbl_val)(struct xlgmac_pdata *pdata); + int (*get_tx_pbl_val)(struct xlgmac_pdata *pdata); + int (*config_pblx8)(struct xlgmac_pdata *pdata); + + /* For MMC statistics */ + void (*rx_mmc_int)(struct xlgmac_pdata *pdata); + void (*tx_mmc_int)(struct xlgmac_pdata *pdata); + void (*read_mmc_stats)(struct xlgmac_pdata *pdata); + + /* For Receive Side Scaling */ + int (*enable_rss)(struct xlgmac_pdata *pdata); + int (*disable_rss)(struct xlgmac_pdata *pdata); + int (*set_rss_hash_key)(struct xlgmac_pdata *pdata, + const u8 *key); + int (*set_rss_lookup_table)(struct xlgmac_pdata *pdata, + const u32 *table); +}; + +/* This structure contains flags that indicate what hardware features + * or configurations are present in the device. + */ +struct xlgmac_hw_features { + /* HW Version */ + unsigned int version; + + /* HW Feature Register0 */ + unsigned int phyifsel; /* PHY interface support */ + unsigned int vlhash; /* VLAN Hash Filter */ + unsigned int sma; /* SMA(MDIO) Interface */ + unsigned int rwk; /* PMT remote wake-up packet */ + unsigned int mgk; /* PMT magic packet */ + unsigned int mmc; /* RMON module */ + unsigned int aoe; /* ARP Offload */ + unsigned int ts; /* IEEE 1588-2008 Advanced Timestamp */ + unsigned int eee; /* Energy Efficient Ethernet */ + unsigned int tx_coe; /* Tx Checksum Offload */ + unsigned int rx_coe; /* Rx Checksum Offload */ + unsigned int addn_mac; /* Additional MAC Addresses */ + unsigned int ts_src; /* Timestamp Source */ + unsigned int sa_vlan_ins; /* Source Address or VLAN Insertion */ + + /* HW Feature Register1 */ + unsigned int rx_fifo_size; /* MTL Receive FIFO Size */ + unsigned int tx_fifo_size; /* MTL Transmit FIFO Size */ + unsigned int adv_ts_hi; /* Advance Timestamping High Word */ + unsigned int dma_width; /* DMA width */ + unsigned int dcb; /* DCB Feature */ + unsigned int sph; /* Split Header Feature */ + unsigned int tso; /* TCP Segmentation Offload */ + unsigned int dma_debug; /* DMA Debug Registers */ + unsigned int rss; /* Receive Side Scaling */ + unsigned int tc_cnt; /* Number of Traffic Classes */ + unsigned int hash_table_size; /* Hash Table Size */ + unsigned int l3l4_filter_num; /* Number of L3-L4 Filters */ + + /* HW Feature Register2 */ + unsigned int rx_q_cnt; /* Number of MTL Receive Queues */ + unsigned int tx_q_cnt; /* Number of MTL Transmit Queues */ + unsigned int rx_ch_cnt; /* Number of DMA Receive Channels */ + unsigned int tx_ch_cnt; /* Number of DMA Transmit Channels */ + unsigned int pps_out_num; /* Number of PPS outputs */ + unsigned int aux_snap_num; /* Number of Aux snapshot inputs */ +}; + +struct xlgmac_resources { + void __iomem *addr; + int irq; +}; + +struct xlgmac_pdata { + struct net_device *netdev; + struct device *dev; + + struct xlgmac_hw_ops hw_ops; + struct xlgmac_desc_ops desc_ops; + + /* Device statistics */ + struct xlgmac_stats stats; + + u32 msg_enable; + + /* MAC registers base */ + void __iomem *mac_regs; + + /* Hardware features of the device */ + struct xlgmac_hw_features hw_feat; + + struct work_struct restart_work; + + /* Rings for Tx/Rx on a DMA channel */ + struct xlgmac_channel *channel_head; + unsigned int channel_count; + unsigned int tx_ring_count; + unsigned int rx_ring_count; + unsigned int tx_desc_count; + unsigned int rx_desc_count; + unsigned int tx_q_count; + unsigned int rx_q_count; + + /* Tx/Rx common settings */ + unsigned int pblx8; + + /* Tx settings */ + unsigned int tx_sf_mode; + unsigned int tx_threshold; + unsigned int tx_pbl; + unsigned int tx_osp_mode; + + /* Rx settings */ + unsigned int rx_sf_mode; + unsigned int rx_threshold; + unsigned int rx_pbl; + + /* Tx coalescing settings */ + unsigned int tx_usecs; + unsigned int tx_frames; + + /* Rx coalescing settings */ + unsigned int rx_riwt; + unsigned int rx_usecs; + unsigned int rx_frames; + + /* Current Rx buffer size */ + unsigned int rx_buf_size; + + /* Flow control settings */ + unsigned int tx_pause; + unsigned int rx_pause; + + /* Device interrupt number */ + int dev_irq; + unsigned int per_channel_irq; + int channel_irq[XLGMAC_MAX_DMA_CHANNELS]; + + /* Netdev related settings */ + unsigned char mac_addr[ETH_ALEN]; + netdev_features_t netdev_features; + struct napi_struct napi; + + /* Filtering support */ + unsigned long active_vlans[BITS_TO_LONGS(VLAN_N_VID)]; + + /* Device clocks */ + unsigned long sysclk_rate; + + /* RSS addressing mutex */ + struct mutex rss_mutex; + + /* Receive Side Scaling settings */ + u8 rss_key[XLGMAC_RSS_HASH_KEY_SIZE]; + u32 rss_table[XLGMAC_RSS_MAX_TABLE_SIZE]; + u32 rss_options; + + int phy_speed; + + char drv_name[32]; + char drv_ver[32]; +}; + +void xlgmac_init_desc_ops(struct xlgmac_desc_ops *desc_ops); +void xlgmac_init_hw_ops(struct xlgmac_hw_ops *hw_ops); +const struct net_device_ops *xlgmac_get_netdev_ops(void); +void xlgmac_dump_tx_desc(struct xlgmac_pdata *pdata, + struct xlgmac_ring *ring, + unsigned int idx, + unsigned int count, + unsigned int flag); +void xlgmac_dump_rx_desc(struct xlgmac_pdata *pdata, + struct xlgmac_ring *ring, + unsigned int idx); +void xlgmac_print_pkt(struct net_device *netdev, + struct sk_buff *skb, bool tx_rx); +void xlgmac_get_all_hw_features(struct xlgmac_pdata *pdata); +void xlgmac_print_all_hw_features(struct xlgmac_pdata *pdata); +int xlgmac_drv_probe(struct device *dev, + struct xlgmac_resources *res); +int xlgmac_drv_remove(struct device *dev); + +/* For debug prints */ +#ifdef XLGMAC_DEBUG +#define XLGMAC_PR(fmt, args...) \ + pr_alert("[%s,%d]:" fmt, __func__, __LINE__, ## args) +#else +#define XLGMAC_PR(x...) do { } while (0) +#endif + +#endif /* __DWC_XLGMAC_H__ */ diff --git a/drivers/net/ethernet/ti/netcp_core.c b/drivers/net/ethernet/ti/netcp_core.c index 7c7ae0890e90..9027c9c509b5 100644 --- a/drivers/net/ethernet/ti/netcp_core.c +++ b/drivers/net/ethernet/ti/netcp_core.c @@ -1882,6 +1882,7 @@ static u16 netcp_select_queue(struct net_device *dev, struct sk_buff *skb, static int netcp_setup_tc(struct net_device *dev, u32 handle, __be16 proto, struct tc_to_netdev *tc) { + u8 num_tc; int i; /* setup tc must be called under rtnl lock */ @@ -1890,15 +1891,18 @@ static int netcp_setup_tc(struct net_device *dev, u32 handle, __be16 proto, if (tc->type != TC_SETUP_MQPRIO) return -EINVAL; + tc->mqprio->hw = TC_MQPRIO_HW_OFFLOAD_TCS; + num_tc = tc->mqprio->num_tc; + /* Sanity-check the number of traffic classes requested */ if ((dev->real_num_tx_queues <= 1) || - (dev->real_num_tx_queues < tc->tc)) + (dev->real_num_tx_queues < num_tc)) return -EINVAL; /* Configure traffic class to queue mappings */ - if (tc->tc) { - netdev_set_num_tc(dev, tc->tc); - for (i = 0; i < tc->tc; i++) + if (num_tc) { + netdev_set_num_tc(dev, num_tc); + for (i = 0; i < num_tc; i++) netdev_set_tc_queue(dev, i, 1, i); } else { netdev_reset_tc(dev); diff --git a/drivers/net/ethernet/toshiba/ps3_gelic_net.c b/drivers/net/ethernet/toshiba/ps3_gelic_net.c index 72013314bba8..fa6a06571187 100644 --- a/drivers/net/ethernet/toshiba/ps3_gelic_net.c +++ b/drivers/net/ethernet/toshiba/ps3_gelic_net.c @@ -1206,61 +1206,68 @@ void gelic_net_get_drvinfo(struct net_device *netdev, strlcpy(info->version, DRV_VERSION, sizeof(info->version)); } -static int gelic_ether_get_settings(struct net_device *netdev, - struct ethtool_cmd *cmd) +static int gelic_ether_get_link_ksettings(struct net_device *netdev, + struct ethtool_link_ksettings *cmd) { struct gelic_card *card = netdev_card(netdev); + u32 supported, advertising; gelic_card_get_ether_port_status(card, 0); if (card->ether_port_status & GELIC_LV1_ETHER_FULL_DUPLEX) - cmd->duplex = DUPLEX_FULL; + cmd->base.duplex = DUPLEX_FULL; else - cmd->duplex = DUPLEX_HALF; + cmd->base.duplex = DUPLEX_HALF; switch (card->ether_port_status & GELIC_LV1_ETHER_SPEED_MASK) { case GELIC_LV1_ETHER_SPEED_10: - ethtool_cmd_speed_set(cmd, SPEED_10); + cmd->base.speed = SPEED_10; break; case GELIC_LV1_ETHER_SPEED_100: - ethtool_cmd_speed_set(cmd, SPEED_100); + cmd->base.speed = SPEED_100; break; case GELIC_LV1_ETHER_SPEED_1000: - ethtool_cmd_speed_set(cmd, SPEED_1000); + cmd->base.speed = SPEED_1000; break; default: pr_info("%s: speed unknown\n", __func__); - ethtool_cmd_speed_set(cmd, SPEED_10); + cmd->base.speed = SPEED_10; break; } - cmd->supported = SUPPORTED_TP | SUPPORTED_Autoneg | + supported = SUPPORTED_TP | SUPPORTED_Autoneg | SUPPORTED_10baseT_Half | SUPPORTED_10baseT_Full | SUPPORTED_100baseT_Half | SUPPORTED_100baseT_Full | SUPPORTED_1000baseT_Full; - cmd->advertising = cmd->supported; + advertising = supported; if (card->link_mode & GELIC_LV1_ETHER_AUTO_NEG) { - cmd->autoneg = AUTONEG_ENABLE; + cmd->base.autoneg = AUTONEG_ENABLE; } else { - cmd->autoneg = AUTONEG_DISABLE; - cmd->advertising &= ~ADVERTISED_Autoneg; + cmd->base.autoneg = AUTONEG_DISABLE; + advertising &= ~ADVERTISED_Autoneg; } - cmd->port = PORT_TP; + cmd->base.port = PORT_TP; + + ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.supported, + supported); + ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.advertising, + advertising); return 0; } -static int gelic_ether_set_settings(struct net_device *netdev, - struct ethtool_cmd *cmd) +static int +gelic_ether_set_link_ksettings(struct net_device *netdev, + const struct ethtool_link_ksettings *cmd) { struct gelic_card *card = netdev_card(netdev); u64 mode; int ret; - if (cmd->autoneg == AUTONEG_ENABLE) { + if (cmd->base.autoneg == AUTONEG_ENABLE) { mode = GELIC_LV1_ETHER_AUTO_NEG; } else { - switch (cmd->speed) { + switch (cmd->base.speed) { case SPEED_10: mode = GELIC_LV1_ETHER_SPEED_10; break; @@ -1273,9 +1280,9 @@ static int gelic_ether_set_settings(struct net_device *netdev, default: return -EINVAL; } - if (cmd->duplex == DUPLEX_FULL) + if (cmd->base.duplex == DUPLEX_FULL) { mode |= GELIC_LV1_ETHER_FULL_DUPLEX; - else if (cmd->speed == SPEED_1000) { + } else if (cmd->base.speed == SPEED_1000) { pr_info("1000 half duplex is not supported.\n"); return -EINVAL; } @@ -1370,11 +1377,11 @@ done: static const struct ethtool_ops gelic_ether_ethtool_ops = { .get_drvinfo = gelic_net_get_drvinfo, - .get_settings = gelic_ether_get_settings, - .set_settings = gelic_ether_set_settings, .get_link = ethtool_op_get_link, .get_wol = gelic_net_get_wol, .set_wol = gelic_net_set_wol, + .get_link_ksettings = gelic_ether_get_link_ksettings, + .set_link_ksettings = gelic_ether_set_link_ksettings, }; /** diff --git a/drivers/net/ethernet/toshiba/spider_net_ethtool.c b/drivers/net/ethernet/toshiba/spider_net_ethtool.c index ffe519382e11..16bd036d0682 100644 --- a/drivers/net/ethernet/toshiba/spider_net_ethtool.c +++ b/drivers/net/ethernet/toshiba/spider_net_ethtool.c @@ -47,19 +47,23 @@ static struct { }; static int -spider_net_ethtool_get_settings(struct net_device *netdev, - struct ethtool_cmd *cmd) +spider_net_ethtool_get_link_ksettings(struct net_device *netdev, + struct ethtool_link_ksettings *cmd) { struct spider_net_card *card; card = netdev_priv(netdev); - cmd->supported = (SUPPORTED_1000baseT_Full | - SUPPORTED_FIBRE); - cmd->advertising = (ADVERTISED_1000baseT_Full | - ADVERTISED_FIBRE); - cmd->port = PORT_FIBRE; - ethtool_cmd_speed_set(cmd, card->phy.speed); - cmd->duplex = DUPLEX_FULL; + ethtool_link_ksettings_zero_link_mode(cmd, supported); + ethtool_link_ksettings_add_link_mode(cmd, supported, 1000baseT_Full); + ethtool_link_ksettings_add_link_mode(cmd, supported, FIBRE); + + ethtool_link_ksettings_zero_link_mode(cmd, advertising); + ethtool_link_ksettings_add_link_mode(cmd, advertising, 1000baseT_Full); + ethtool_link_ksettings_add_link_mode(cmd, advertising, FIBRE); + + cmd->base.port = PORT_FIBRE; + cmd->base.speed = card->phy.speed; + cmd->base.duplex = DUPLEX_FULL; return 0; } @@ -166,7 +170,6 @@ static void spider_net_get_strings(struct net_device *netdev, u32 stringset, } const struct ethtool_ops spider_net_ethtool_ops = { - .get_settings = spider_net_ethtool_get_settings, .get_drvinfo = spider_net_ethtool_get_drvinfo, .get_wol = spider_net_ethtool_get_wol, .get_msglevel = spider_net_ethtool_get_msglevel, @@ -177,5 +180,6 @@ const struct ethtool_ops spider_net_ethtool_ops = { .get_strings = spider_net_get_strings, .get_sset_count = spider_net_get_sset_count, .get_ethtool_stats = spider_net_get_ethtool_stats, + .get_link_ksettings = spider_net_ethtool_get_link_ksettings, }; diff --git a/drivers/net/ethernet/tundra/tsi108_eth.c b/drivers/net/ethernet/tundra/tsi108_eth.c index c5583991da4a..5ac6eaa9e785 100644 --- a/drivers/net/ethernet/tundra/tsi108_eth.c +++ b/drivers/net/ethernet/tundra/tsi108_eth.c @@ -1499,27 +1499,29 @@ static void tsi108_init_mac(struct net_device *dev) TSI_WRITE(TSI108_EC_INTMASK, ~0); } -static int tsi108_get_settings(struct net_device *dev, struct ethtool_cmd *cmd) +static int tsi108_get_link_ksettings(struct net_device *dev, + struct ethtool_link_ksettings *cmd) { struct tsi108_prv_data *data = netdev_priv(dev); unsigned long flags; int rc; spin_lock_irqsave(&data->txlock, flags); - rc = mii_ethtool_gset(&data->mii_if, cmd); + rc = mii_ethtool_get_link_ksettings(&data->mii_if, cmd); spin_unlock_irqrestore(&data->txlock, flags); return rc; } -static int tsi108_set_settings(struct net_device *dev, struct ethtool_cmd *cmd) +static int tsi108_set_link_ksettings(struct net_device *dev, + const struct ethtool_link_ksettings *cmd) { struct tsi108_prv_data *data = netdev_priv(dev); unsigned long flags; int rc; spin_lock_irqsave(&data->txlock, flags); - rc = mii_ethtool_sset(&data->mii_if, cmd); + rc = mii_ethtool_set_link_ksettings(&data->mii_if, cmd); spin_unlock_irqrestore(&data->txlock, flags); return rc; @@ -1535,8 +1537,8 @@ static int tsi108_do_ioctl(struct net_device *dev, struct ifreq *rq, int cmd) static const struct ethtool_ops tsi108_ethtool_ops = { .get_link = ethtool_op_get_link, - .get_settings = tsi108_get_settings, - .set_settings = tsi108_set_settings, + .get_link_ksettings = tsi108_get_link_ksettings, + .set_link_ksettings = tsi108_set_link_ksettings, }; static const struct net_device_ops tsi108_netdev_ops = { diff --git a/drivers/net/ethernet/via/via-rhine.c b/drivers/net/ethernet/via/via-rhine.c index c068c58428f7..4cf41f779d0e 100644 --- a/drivers/net/ethernet/via/via-rhine.c +++ b/drivers/net/ethernet/via/via-rhine.c @@ -2303,25 +2303,27 @@ static void netdev_get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *i strlcpy(info->bus_info, dev_name(hwdev), sizeof(info->bus_info)); } -static int netdev_get_settings(struct net_device *dev, struct ethtool_cmd *cmd) +static int netdev_get_link_ksettings(struct net_device *dev, + struct ethtool_link_ksettings *cmd) { struct rhine_private *rp = netdev_priv(dev); int rc; mutex_lock(&rp->task_lock); - rc = mii_ethtool_gset(&rp->mii_if, cmd); + rc = mii_ethtool_get_link_ksettings(&rp->mii_if, cmd); mutex_unlock(&rp->task_lock); return rc; } -static int netdev_set_settings(struct net_device *dev, struct ethtool_cmd *cmd) +static int netdev_set_link_ksettings(struct net_device *dev, + const struct ethtool_link_ksettings *cmd) { struct rhine_private *rp = netdev_priv(dev); int rc; mutex_lock(&rp->task_lock); - rc = mii_ethtool_sset(&rp->mii_if, cmd); + rc = mii_ethtool_set_link_ksettings(&rp->mii_if, cmd); rhine_set_carrier(&rp->mii_if); mutex_unlock(&rp->task_lock); @@ -2391,14 +2393,14 @@ static int rhine_set_wol(struct net_device *dev, struct ethtool_wolinfo *wol) static const struct ethtool_ops netdev_ethtool_ops = { .get_drvinfo = netdev_get_drvinfo, - .get_settings = netdev_get_settings, - .set_settings = netdev_set_settings, .nway_reset = netdev_nway_reset, .get_link = netdev_get_link, .get_msglevel = netdev_get_msglevel, .set_msglevel = netdev_set_msglevel, .get_wol = rhine_get_wol, .set_wol = rhine_set_wol, + .get_link_ksettings = netdev_get_link_ksettings, + .set_link_ksettings = netdev_set_link_ksettings, }; static int netdev_ioctl(struct net_device *dev, struct ifreq *rq, int cmd) diff --git a/drivers/net/ethernet/via/via-velocity.c b/drivers/net/ethernet/via/via-velocity.c index d088788b27a7..ef9538ee53d0 100644 --- a/drivers/net/ethernet/via/via-velocity.c +++ b/drivers/net/ethernet/via/via-velocity.c @@ -3291,15 +3291,17 @@ static void velocity_ethtool_down(struct net_device *dev) velocity_set_power_state(vptr, PCI_D3hot); } -static int velocity_get_settings(struct net_device *dev, - struct ethtool_cmd *cmd) +static int velocity_get_link_ksettings(struct net_device *dev, + struct ethtool_link_ksettings *cmd) { struct velocity_info *vptr = netdev_priv(dev); struct mac_regs __iomem *regs = vptr->mac_regs; u32 status; + u32 supported, advertising; + status = check_connection_type(vptr->mac_regs); - cmd->supported = SUPPORTED_TP | + supported = SUPPORTED_TP | SUPPORTED_Autoneg | SUPPORTED_10baseT_Half | SUPPORTED_10baseT_Full | @@ -3308,9 +3310,9 @@ static int velocity_get_settings(struct net_device *dev, SUPPORTED_1000baseT_Half | SUPPORTED_1000baseT_Full; - cmd->advertising = ADVERTISED_TP | ADVERTISED_Autoneg; + advertising = ADVERTISED_TP | ADVERTISED_Autoneg; if (vptr->options.spd_dpx == SPD_DPX_AUTO) { - cmd->advertising |= + advertising |= ADVERTISED_10baseT_Half | ADVERTISED_10baseT_Full | ADVERTISED_100baseT_Half | @@ -3320,19 +3322,19 @@ static int velocity_get_settings(struct net_device *dev, } else { switch (vptr->options.spd_dpx) { case SPD_DPX_1000_FULL: - cmd->advertising |= ADVERTISED_1000baseT_Full; + advertising |= ADVERTISED_1000baseT_Full; break; case SPD_DPX_100_HALF: - cmd->advertising |= ADVERTISED_100baseT_Half; + advertising |= ADVERTISED_100baseT_Half; break; case SPD_DPX_100_FULL: - cmd->advertising |= ADVERTISED_100baseT_Full; + advertising |= ADVERTISED_100baseT_Full; break; case SPD_DPX_10_HALF: - cmd->advertising |= ADVERTISED_10baseT_Half; + advertising |= ADVERTISED_10baseT_Half; break; case SPD_DPX_10_FULL: - cmd->advertising |= ADVERTISED_10baseT_Full; + advertising |= ADVERTISED_10baseT_Full; break; default: break; @@ -3340,30 +3342,35 @@ static int velocity_get_settings(struct net_device *dev, } if (status & VELOCITY_SPEED_1000) - ethtool_cmd_speed_set(cmd, SPEED_1000); + cmd->base.speed = SPEED_1000; else if (status & VELOCITY_SPEED_100) - ethtool_cmd_speed_set(cmd, SPEED_100); + cmd->base.speed = SPEED_100; else - ethtool_cmd_speed_set(cmd, SPEED_10); + cmd->base.speed = SPEED_10; - cmd->autoneg = (status & VELOCITY_AUTONEG_ENABLE) ? AUTONEG_ENABLE : AUTONEG_DISABLE; - cmd->port = PORT_TP; - cmd->transceiver = XCVR_INTERNAL; - cmd->phy_address = readb(®s->MIIADR) & 0x1F; + cmd->base.autoneg = (status & VELOCITY_AUTONEG_ENABLE) ? + AUTONEG_ENABLE : AUTONEG_DISABLE; + cmd->base.port = PORT_TP; + cmd->base.phy_address = readb(®s->MIIADR) & 0x1F; if (status & VELOCITY_DUPLEX_FULL) - cmd->duplex = DUPLEX_FULL; + cmd->base.duplex = DUPLEX_FULL; else - cmd->duplex = DUPLEX_HALF; + cmd->base.duplex = DUPLEX_HALF; + + ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.supported, + supported); + ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.advertising, + advertising); return 0; } -static int velocity_set_settings(struct net_device *dev, - struct ethtool_cmd *cmd) +static int velocity_set_link_ksettings(struct net_device *dev, + const struct ethtool_link_ksettings *cmd) { struct velocity_info *vptr = netdev_priv(dev); - u32 speed = ethtool_cmd_speed(cmd); + u32 speed = cmd->base.speed; u32 curr_status; u32 new_status = 0; int ret = 0; @@ -3371,11 +3378,12 @@ static int velocity_set_settings(struct net_device *dev, curr_status = check_connection_type(vptr->mac_regs); curr_status &= (~VELOCITY_LINK_FAIL); - new_status |= ((cmd->autoneg) ? VELOCITY_AUTONEG_ENABLE : 0); + new_status |= ((cmd->base.autoneg) ? VELOCITY_AUTONEG_ENABLE : 0); new_status |= ((speed == SPEED_1000) ? VELOCITY_SPEED_1000 : 0); new_status |= ((speed == SPEED_100) ? VELOCITY_SPEED_100 : 0); new_status |= ((speed == SPEED_10) ? VELOCITY_SPEED_10 : 0); - new_status |= ((cmd->duplex == DUPLEX_FULL) ? VELOCITY_DUPLEX_FULL : 0); + new_status |= ((cmd->base.duplex == DUPLEX_FULL) ? + VELOCITY_DUPLEX_FULL : 0); if ((new_status & VELOCITY_AUTONEG_ENABLE) && (new_status != (curr_status | VELOCITY_AUTONEG_ENABLE))) { @@ -3644,8 +3652,6 @@ static void velocity_get_ethtool_stats(struct net_device *dev, } static const struct ethtool_ops velocity_ethtool_ops = { - .get_settings = velocity_get_settings, - .set_settings = velocity_set_settings, .get_drvinfo = velocity_get_drvinfo, .get_wol = velocity_ethtool_get_wol, .set_wol = velocity_ethtool_set_wol, @@ -3658,7 +3664,9 @@ static const struct ethtool_ops velocity_ethtool_ops = { .get_coalesce = velocity_get_coalesce, .set_coalesce = velocity_set_coalesce, .begin = velocity_ethtool_up, - .complete = velocity_ethtool_down + .complete = velocity_ethtool_down, + .get_link_ksettings = velocity_get_link_ksettings, + .set_link_ksettings = velocity_set_link_ksettings, }; #if defined(CONFIG_PM) && defined(CONFIG_INET) diff --git a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c index b96e96919e31..33c595f4691d 100644 --- a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c +++ b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c @@ -301,7 +301,7 @@ static void axienet_set_mac_address(struct net_device *ndev, if (address) memcpy(ndev->dev_addr, address, ETH_ALEN); if (!is_valid_ether_addr(ndev->dev_addr)) - eth_random_addr(ndev->dev_addr); + eth_hw_addr_random(ndev); /* Set up unicast MAC address filter set its mac address */ axienet_iow(lp, XAE_UAW0_OFFSET, diff --git a/drivers/net/fjes/fjes_ethtool.c b/drivers/net/fjes/fjes_ethtool.c index 6575f880f1be..7d101714c2ef 100644 --- a/drivers/net/fjes/fjes_ethtool.c +++ b/drivers/net/fjes/fjes_ethtool.c @@ -175,16 +175,15 @@ static void fjes_get_drvinfo(struct net_device *netdev, "platform:%s", plat_dev->name); } -static int fjes_get_settings(struct net_device *netdev, - struct ethtool_cmd *ecmd) +static int fjes_get_link_ksettings(struct net_device *netdev, + struct ethtool_link_ksettings *ecmd) { - ecmd->supported = 0; - ecmd->advertising = 0; - ecmd->duplex = DUPLEX_FULL; - ecmd->autoneg = AUTONEG_DISABLE; - ecmd->transceiver = XCVR_DUMMY1; - ecmd->port = PORT_NONE; - ethtool_cmd_speed_set(ecmd, 20000); /* 20Gb/s */ + ethtool_link_ksettings_zero_link_mode(ecmd, supported); + ethtool_link_ksettings_zero_link_mode(ecmd, advertising); + ecmd->base.duplex = DUPLEX_FULL; + ecmd->base.autoneg = AUTONEG_DISABLE; + ecmd->base.port = PORT_NONE; + ecmd->base.speed = 20000; /* 20Gb/s */ return 0; } @@ -296,7 +295,6 @@ static int fjes_get_dump_data(struct net_device *netdev, } static const struct ethtool_ops fjes_ethtool_ops = { - .get_settings = fjes_get_settings, .get_drvinfo = fjes_get_drvinfo, .get_ethtool_stats = fjes_get_ethtool_stats, .get_strings = fjes_get_strings, @@ -306,6 +304,7 @@ static const struct ethtool_ops fjes_ethtool_ops = { .set_dump = fjes_set_dump, .get_dump_flag = fjes_get_dump_flag, .get_dump_data = fjes_get_dump_data, + .get_link_ksettings = fjes_get_link_ksettings, }; void fjes_set_ethtool_ops(struct net_device *netdev) diff --git a/drivers/net/gtp.c b/drivers/net/gtp.c index 89698741682f..3e1854f34420 100644 --- a/drivers/net/gtp.c +++ b/drivers/net/gtp.c @@ -58,6 +58,9 @@ struct pdp_ctx { struct in_addr ms_addr_ip4; struct in_addr sgsn_addr_ip4; + struct sock *sk; + struct net_device *dev; + atomic_t tx_seq; struct rcu_head rcu_head; }; @@ -66,8 +69,8 @@ struct pdp_ctx { struct gtp_dev { struct list_head list; - struct socket *sock0; - struct socket *sock1u; + struct sock *sk0; + struct sock *sk1u; struct net_device *dev; @@ -84,6 +87,8 @@ struct gtp_net { static u32 gtp_h_initval; +static void pdp_context_delete(struct pdp_ctx *pctx); + static inline u32 gtp0_hashfn(u64 tid) { u32 *tid32 = (u32 *) &tid; @@ -175,9 +180,42 @@ static bool gtp_check_src_ms(struct sk_buff *skb, struct pdp_ctx *pctx, return false; } +static int gtp_rx(struct pdp_ctx *pctx, struct sk_buff *skb, unsigned int hdrlen) +{ + struct pcpu_sw_netstats *stats; + + if (!gtp_check_src_ms(skb, pctx, hdrlen)) { + netdev_dbg(pctx->dev, "No PDP ctx for this MS\n"); + return 1; + } + + /* Get rid of the GTP + UDP headers. */ + if (iptunnel_pull_header(skb, hdrlen, skb->protocol, + !net_eq(sock_net(pctx->sk), dev_net(pctx->dev)))) + return -1; + + netdev_dbg(pctx->dev, "forwarding packet from GGSN to uplink\n"); + + /* Now that the UDP and the GTP header have been removed, set up the + * new network header. This is required by the upper layer to + * calculate the transport header. + */ + skb_reset_network_header(skb); + + skb->dev = pctx->dev; + + stats = this_cpu_ptr(pctx->dev->tstats); + u64_stats_update_begin(&stats->syncp); + stats->rx_packets++; + stats->rx_bytes += skb->len; + u64_stats_update_end(&stats->syncp); + + netif_rx(skb); + return 0; +} + /* 1 means pass up to the stack, -1 means drop and 0 means decapsulated. */ -static int gtp0_udp_encap_recv(struct gtp_dev *gtp, struct sk_buff *skb, - bool xnet) +static int gtp0_udp_encap_recv(struct gtp_dev *gtp, struct sk_buff *skb) { unsigned int hdrlen = sizeof(struct udphdr) + sizeof(struct gtp0_header); @@ -201,17 +239,10 @@ static int gtp0_udp_encap_recv(struct gtp_dev *gtp, struct sk_buff *skb, return 1; } - if (!gtp_check_src_ms(skb, pctx, hdrlen)) { - netdev_dbg(gtp->dev, "No PDP ctx for this MS\n"); - return 1; - } - - /* Get rid of the GTP + UDP headers. */ - return iptunnel_pull_header(skb, hdrlen, skb->protocol, xnet); + return gtp_rx(pctx, skb, hdrlen); } -static int gtp1u_udp_encap_recv(struct gtp_dev *gtp, struct sk_buff *skb, - bool xnet) +static int gtp1u_udp_encap_recv(struct gtp_dev *gtp, struct sk_buff *skb) { unsigned int hdrlen = sizeof(struct udphdr) + sizeof(struct gtp1_header); @@ -250,37 +281,33 @@ static int gtp1u_udp_encap_recv(struct gtp_dev *gtp, struct sk_buff *skb, return 1; } - if (!gtp_check_src_ms(skb, pctx, hdrlen)) { - netdev_dbg(gtp->dev, "No PDP ctx for this MS\n"); - return 1; - } - - /* Get rid of the GTP + UDP headers. */ - return iptunnel_pull_header(skb, hdrlen, skb->protocol, xnet); + return gtp_rx(pctx, skb, hdrlen); } -static void gtp_encap_disable(struct gtp_dev *gtp) +static void gtp_encap_destroy(struct sock *sk) { - if (gtp->sock0 && gtp->sock0->sk) { - udp_sk(gtp->sock0->sk)->encap_type = 0; - rcu_assign_sk_user_data(gtp->sock0->sk, NULL); - } - if (gtp->sock1u && gtp->sock1u->sk) { - udp_sk(gtp->sock1u->sk)->encap_type = 0; - rcu_assign_sk_user_data(gtp->sock1u->sk, NULL); - } + struct gtp_dev *gtp; - gtp->sock0 = NULL; - gtp->sock1u = NULL; + gtp = rcu_dereference_sk_user_data(sk); + if (gtp) { + udp_sk(sk)->encap_type = 0; + rcu_assign_sk_user_data(sk, NULL); + sock_put(sk); + } } -static void gtp_encap_destroy(struct sock *sk) +static void gtp_encap_disable_sock(struct sock *sk) { - struct gtp_dev *gtp; + if (!sk) + return; - gtp = rcu_dereference_sk_user_data(sk); - if (gtp) - gtp_encap_disable(gtp); + gtp_encap_destroy(sk); +} + +static void gtp_encap_disable(struct gtp_dev *gtp) +{ + gtp_encap_disable_sock(gtp->sk0); + gtp_encap_disable_sock(gtp->sk1u); } /* UDP encapsulation receive handler. See net/ipv4/udp.c. @@ -288,10 +315,8 @@ static void gtp_encap_destroy(struct sock *sk) */ static int gtp_encap_recv(struct sock *sk, struct sk_buff *skb) { - struct pcpu_sw_netstats *stats; struct gtp_dev *gtp; - bool xnet; - int ret; + int ret = 0; gtp = rcu_dereference_sk_user_data(sk); if (!gtp) @@ -299,16 +324,14 @@ static int gtp_encap_recv(struct sock *sk, struct sk_buff *skb) netdev_dbg(gtp->dev, "encap_recv sk=%p\n", sk); - xnet = !net_eq(sock_net(sk), dev_net(gtp->dev)); - switch (udp_sk(sk)->encap_type) { case UDP_ENCAP_GTP0: netdev_dbg(gtp->dev, "received GTP0 packet\n"); - ret = gtp0_udp_encap_recv(gtp, skb, xnet); + ret = gtp0_udp_encap_recv(gtp, skb); break; case UDP_ENCAP_GTP1U: netdev_dbg(gtp->dev, "received GTP1U packet\n"); - ret = gtp1u_udp_encap_recv(gtp, skb, xnet); + ret = gtp1u_udp_encap_recv(gtp, skb); break; default: ret = -1; /* Shouldn't happen. */ @@ -317,33 +340,17 @@ static int gtp_encap_recv(struct sock *sk, struct sk_buff *skb) switch (ret) { case 1: netdev_dbg(gtp->dev, "pass up to the process\n"); - return 1; + break; case 0: - netdev_dbg(gtp->dev, "forwarding packet from GGSN to uplink\n"); break; case -1: netdev_dbg(gtp->dev, "GTP packet has been dropped\n"); kfree_skb(skb); - return 0; + ret = 0; + break; } - /* Now that the UDP and the GTP header have been removed, set up the - * new network header. This is required by the upper layer to - * calculate the transport header. - */ - skb_reset_network_header(skb); - - skb->dev = gtp->dev; - - stats = this_cpu_ptr(gtp->dev->tstats); - u64_stats_update_begin(&stats->syncp); - stats->rx_packets++; - stats->rx_bytes += skb->len; - u64_stats_update_end(&stats->syncp); - - netif_rx(skb); - - return 0; + return ret; } static int gtp_dev_init(struct net_device *dev) @@ -367,8 +374,9 @@ static void gtp_dev_uninit(struct net_device *dev) free_percpu(dev->tstats); } -static struct rtable *ip4_route_output_gtp(struct net *net, struct flowi4 *fl4, - const struct sock *sk, __be32 daddr) +static struct rtable *ip4_route_output_gtp(struct flowi4 *fl4, + const struct sock *sk, + __be32 daddr) { memset(fl4, 0, sizeof(*fl4)); fl4->flowi4_oif = sk->sk_bound_dev_if; @@ -377,7 +385,7 @@ static struct rtable *ip4_route_output_gtp(struct net *net, struct flowi4 *fl4, fl4->flowi4_tos = RT_CONN_FLAGS(sk); fl4->flowi4_proto = sk->sk_protocol; - return ip_route_output_key(net, fl4); + return ip_route_output_key(sock_net(sk), fl4); } static inline void gtp0_push_header(struct sk_buff *skb, struct pdp_ctx *pctx) @@ -466,7 +474,6 @@ static int gtp_build_skb_ip4(struct sk_buff *skb, struct net_device *dev, struct rtable *rt; struct flowi4 fl4; struct iphdr *iph; - struct sock *sk; __be16 df; int mtu; @@ -482,30 +489,7 @@ static int gtp_build_skb_ip4(struct sk_buff *skb, struct net_device *dev, } netdev_dbg(dev, "found PDP context %p\n", pctx); - switch (pctx->gtp_version) { - case GTP_V0: - if (gtp->sock0) - sk = gtp->sock0->sk; - else - sk = NULL; - break; - case GTP_V1: - if (gtp->sock1u) - sk = gtp->sock1u->sk; - else - sk = NULL; - break; - default: - return -ENOENT; - } - - if (!sk) { - netdev_dbg(dev, "no userspace socket is available, skip\n"); - return -ENOENT; - } - - rt = ip4_route_output_gtp(sock_net(sk), &fl4, gtp->sock0->sk, - pctx->sgsn_addr_ip4.s_addr); + rt = ip4_route_output_gtp(&fl4, pctx->sk, pctx->sgsn_addr_ip4.s_addr); if (IS_ERR(rt)) { netdev_dbg(dev, "no route to SSGN %pI4\n", &pctx->sgsn_addr_ip4.s_addr); @@ -550,7 +534,7 @@ static int gtp_build_skb_ip4(struct sk_buff *skb, struct net_device *dev, goto err_rt; } - gtp_set_pktinfo_ipv4(pktinfo, sk, iph, pctx, rt, &fl4, dev); + gtp_set_pktinfo_ipv4(pktinfo, pctx->sk, iph, pctx, rt, &fl4, dev); gtp_push_header(skb, pktinfo); return 0; @@ -640,27 +624,23 @@ static void gtp_link_setup(struct net_device *dev) static int gtp_hashtable_new(struct gtp_dev *gtp, int hsize); static void gtp_hashtable_free(struct gtp_dev *gtp); -static int gtp_encap_enable(struct net_device *dev, struct gtp_dev *gtp, - int fd_gtp0, int fd_gtp1); +static int gtp_encap_enable(struct gtp_dev *gtp, struct nlattr *data[]); static int gtp_newlink(struct net *src_net, struct net_device *dev, struct nlattr *tb[], struct nlattr *data[]) { - int hashsize, err, fd0, fd1; struct gtp_dev *gtp; struct gtp_net *gn; + int hashsize, err; - if (!data[IFLA_GTP_FD0] || !data[IFLA_GTP_FD1]) + if (!data[IFLA_GTP_FD0] && !data[IFLA_GTP_FD1]) return -EINVAL; gtp = netdev_priv(dev); - fd0 = nla_get_u32(data[IFLA_GTP_FD0]); - fd1 = nla_get_u32(data[IFLA_GTP_FD1]); - - err = gtp_encap_enable(dev, gtp, fd0, fd1); + err = gtp_encap_enable(gtp, data); if (err < 0) - goto out_err; + return err; if (!data[IFLA_GTP_PDP_HASHSIZE]) hashsize = 1024; @@ -688,7 +668,6 @@ out_hashtable: gtp_hashtable_free(gtp); out_encap: gtp_encap_disable(gtp); -out_err: return err; } @@ -747,21 +726,6 @@ static struct rtnl_link_ops gtp_link_ops __read_mostly = { .fill_info = gtp_fill_info, }; -static struct net *gtp_genl_get_net(struct net *src_net, struct nlattr *tb[]) -{ - struct net *net; - - /* Examine the link attributes and figure out which network namespace - * we are talking about. - */ - if (tb[GTPA_NET_NS_FD]) - net = get_net_ns_by_fd(nla_get_u32(tb[GTPA_NET_NS_FD])); - else - net = get_net(src_net); - - return net; -} - static int gtp_hashtable_new(struct gtp_dev *gtp, int hsize) { int i; @@ -791,85 +755,111 @@ static void gtp_hashtable_free(struct gtp_dev *gtp) struct pdp_ctx *pctx; int i; - for (i = 0; i < gtp->hash_size; i++) { - hlist_for_each_entry_rcu(pctx, >p->tid_hash[i], hlist_tid) { - hlist_del_rcu(&pctx->hlist_tid); - hlist_del_rcu(&pctx->hlist_addr); - kfree_rcu(pctx, rcu_head); - } - } + for (i = 0; i < gtp->hash_size; i++) + hlist_for_each_entry_rcu(pctx, >p->tid_hash[i], hlist_tid) + pdp_context_delete(pctx); + synchronize_rcu(); kfree(gtp->addr_hash); kfree(gtp->tid_hash); } -static int gtp_encap_enable(struct net_device *dev, struct gtp_dev *gtp, - int fd_gtp0, int fd_gtp1) +static struct sock *gtp_encap_enable_socket(int fd, int type, + struct gtp_dev *gtp) { struct udp_tunnel_sock_cfg tuncfg = {NULL}; - struct socket *sock0, *sock1u; + struct socket *sock; + struct sock *sk; int err; - netdev_dbg(dev, "enable gtp on %d, %d\n", fd_gtp0, fd_gtp1); + pr_debug("enable gtp on %d, %d\n", fd, type); - sock0 = sockfd_lookup(fd_gtp0, &err); - if (sock0 == NULL) { - netdev_dbg(dev, "socket fd=%d not found (gtp0)\n", fd_gtp0); - return -ENOENT; + sock = sockfd_lookup(fd, &err); + if (!sock) { + pr_debug("gtp socket fd=%d not found\n", fd); + return NULL; } - if (sock0->sk->sk_protocol != IPPROTO_UDP) { - netdev_dbg(dev, "socket fd=%d not UDP\n", fd_gtp0); - err = -EINVAL; - goto err1; - } - - sock1u = sockfd_lookup(fd_gtp1, &err); - if (sock1u == NULL) { - netdev_dbg(dev, "socket fd=%d not found (gtp1u)\n", fd_gtp1); - err = -ENOENT; - goto err1; + if (sock->sk->sk_protocol != IPPROTO_UDP) { + pr_debug("socket fd=%d not UDP\n", fd); + sk = ERR_PTR(-EINVAL); + goto out_sock; } - if (sock1u->sk->sk_protocol != IPPROTO_UDP) { - netdev_dbg(dev, "socket fd=%d not UDP\n", fd_gtp1); - err = -EINVAL; - goto err2; + if (rcu_dereference_sk_user_data(sock->sk)) { + sk = ERR_PTR(-EBUSY); + goto out_sock; } - netdev_dbg(dev, "enable gtp on %p, %p\n", sock0, sock1u); - - gtp->sock0 = sock0; - gtp->sock1u = sock1u; + sk = sock->sk; + sock_hold(sk); tuncfg.sk_user_data = gtp; + tuncfg.encap_type = type; tuncfg.encap_rcv = gtp_encap_recv; tuncfg.encap_destroy = gtp_encap_destroy; - tuncfg.encap_type = UDP_ENCAP_GTP0; - setup_udp_tunnel_sock(sock_net(gtp->sock0->sk), gtp->sock0, &tuncfg); - - tuncfg.encap_type = UDP_ENCAP_GTP1U; - setup_udp_tunnel_sock(sock_net(gtp->sock1u->sk), gtp->sock1u, &tuncfg); + setup_udp_tunnel_sock(sock_net(sock->sk), sock, &tuncfg); - err = 0; -err2: - sockfd_put(sock1u); -err1: - sockfd_put(sock0); - return err; +out_sock: + sockfd_put(sock); + return sk; } -static struct net_device *gtp_find_dev(struct net *net, int ifindex) +static int gtp_encap_enable(struct gtp_dev *gtp, struct nlattr *data[]) { - struct gtp_net *gn = net_generic(net, gtp_net_id); - struct gtp_dev *gtp; + struct sock *sk1u = NULL; + struct sock *sk0 = NULL; - list_for_each_entry_rcu(gtp, &gn->gtp_dev_list, list) { - if (ifindex == gtp->dev->ifindex) - return gtp->dev; + if (data[IFLA_GTP_FD0]) { + u32 fd0 = nla_get_u32(data[IFLA_GTP_FD0]); + + sk0 = gtp_encap_enable_socket(fd0, UDP_ENCAP_GTP0, gtp); + if (IS_ERR(sk0)) + return PTR_ERR(sk0); } - return NULL; + + if (data[IFLA_GTP_FD1]) { + u32 fd1 = nla_get_u32(data[IFLA_GTP_FD1]); + + sk1u = gtp_encap_enable_socket(fd1, UDP_ENCAP_GTP1U, gtp); + if (IS_ERR(sk1u)) { + if (sk0) + gtp_encap_disable_sock(sk0); + return PTR_ERR(sk1u); + } + } + + gtp->sk0 = sk0; + gtp->sk1u = sk1u; + + return 0; +} + +static struct gtp_dev *gtp_find_dev(struct net *src_net, struct nlattr *nla[]) +{ + struct gtp_dev *gtp = NULL; + struct net_device *dev; + struct net *net; + + /* Examine the link attributes and figure out which network namespace + * we are talking about. + */ + if (nla[GTPA_NET_NS_FD]) + net = get_net_ns_by_fd(nla_get_u32(nla[GTPA_NET_NS_FD])); + else + net = get_net(src_net); + + if (IS_ERR(net)) + return NULL; + + /* Check if there's an existing gtpX device to configure */ + dev = dev_get_by_index_rcu(net, nla_get_u32(nla[GTPA_LINK])); + if (dev->netdev_ops == >p_netdev_ops) + gtp = netdev_priv(dev); + + put_net(net); + return gtp; } static void ipv4_pdp_fill(struct pdp_ctx *pctx, struct genl_info *info) @@ -899,9 +889,10 @@ static void ipv4_pdp_fill(struct pdp_ctx *pctx, struct genl_info *info) } } -static int ipv4_pdp_add(struct net_device *dev, struct genl_info *info) +static int ipv4_pdp_add(struct gtp_dev *gtp, struct sock *sk, + struct genl_info *info) { - struct gtp_dev *gtp = netdev_priv(dev); + struct net_device *dev = gtp->dev; u32 hash_ms, hash_tid = 0; struct pdp_ctx *pctx; bool found = false; @@ -940,6 +931,9 @@ static int ipv4_pdp_add(struct net_device *dev, struct genl_info *info) if (pctx == NULL) return -ENOMEM; + sock_hold(sk); + pctx->sk = sk; + pctx->dev = gtp->dev; ipv4_pdp_fill(pctx, info); atomic_set(&pctx->tx_seq, 0); @@ -976,10 +970,27 @@ static int ipv4_pdp_add(struct net_device *dev, struct genl_info *info) return 0; } +static void pdp_context_free(struct rcu_head *head) +{ + struct pdp_ctx *pctx = container_of(head, struct pdp_ctx, rcu_head); + + sock_put(pctx->sk); + kfree(pctx); +} + +static void pdp_context_delete(struct pdp_ctx *pctx) +{ + hlist_del_rcu(&pctx->hlist_tid); + hlist_del_rcu(&pctx->hlist_addr); + call_rcu(&pctx->rcu_head, pdp_context_free); +} + static int gtp_genl_new_pdp(struct sk_buff *skb, struct genl_info *info) { - struct net_device *dev; - struct net *net; + unsigned int version; + struct gtp_dev *gtp; + struct sock *sk; + int err; if (!info->attrs[GTPA_VERSION] || !info->attrs[GTPA_LINK] || @@ -987,7 +998,9 @@ static int gtp_genl_new_pdp(struct sk_buff *skb, struct genl_info *info) !info->attrs[GTPA_MS_ADDRESS]) return -EINVAL; - switch (nla_get_u32(info->attrs[GTPA_VERSION])) { + version = nla_get_u32(info->attrs[GTPA_VERSION]); + + switch (version) { case GTP_V0: if (!info->attrs[GTPA_TID] || !info->attrs[GTPA_FLOW]) @@ -1003,77 +1016,101 @@ static int gtp_genl_new_pdp(struct sk_buff *skb, struct genl_info *info) return -EINVAL; } - net = gtp_genl_get_net(sock_net(skb->sk), info->attrs); - if (IS_ERR(net)) - return PTR_ERR(net); + rcu_read_lock(); - /* Check if there's an existing gtpX device to configure */ - dev = gtp_find_dev(net, nla_get_u32(info->attrs[GTPA_LINK])); - if (dev == NULL) { - put_net(net); - return -ENODEV; + gtp = gtp_find_dev(sock_net(skb->sk), info->attrs); + if (!gtp) { + err = -ENODEV; + goto out_unlock; + } + + if (version == GTP_V0) + sk = gtp->sk0; + else if (version == GTP_V1) + sk = gtp->sk1u; + else + sk = NULL; + + if (!sk) { + err = -ENODEV; + goto out_unlock; } - put_net(net); - return ipv4_pdp_add(dev, info); + err = ipv4_pdp_add(gtp, sk, info); + +out_unlock: + rcu_read_unlock(); + return err; } -static int gtp_genl_del_pdp(struct sk_buff *skb, struct genl_info *info) +static struct pdp_ctx *gtp_find_pdp_by_link(struct net *net, + struct nlattr *nla[]) { - struct net_device *dev; - struct pdp_ctx *pctx; struct gtp_dev *gtp; - struct net *net; - if (!info->attrs[GTPA_VERSION] || - !info->attrs[GTPA_LINK]) - return -EINVAL; + gtp = gtp_find_dev(net, nla); + if (!gtp) + return ERR_PTR(-ENODEV); - net = gtp_genl_get_net(sock_net(skb->sk), info->attrs); - if (IS_ERR(net)) - return PTR_ERR(net); + if (nla[GTPA_MS_ADDRESS]) { + __be32 ip = nla_get_be32(nla[GTPA_MS_ADDRESS]); - /* Check if there's an existing gtpX device to configure */ - dev = gtp_find_dev(net, nla_get_u32(info->attrs[GTPA_LINK])); - if (dev == NULL) { - put_net(net); - return -ENODEV; + return ipv4_pdp_find(gtp, ip); + } else if (nla[GTPA_VERSION]) { + u32 gtp_version = nla_get_u32(nla[GTPA_VERSION]); + + if (gtp_version == GTP_V0 && nla[GTPA_TID]) + return gtp0_pdp_find(gtp, nla_get_u64(nla[GTPA_TID])); + else if (gtp_version == GTP_V1 && nla[GTPA_I_TEI]) + return gtp1_pdp_find(gtp, nla_get_u32(nla[GTPA_I_TEI])); } - put_net(net); - gtp = netdev_priv(dev); + return ERR_PTR(-EINVAL); +} - switch (nla_get_u32(info->attrs[GTPA_VERSION])) { - case GTP_V0: - if (!info->attrs[GTPA_TID]) - return -EINVAL; - pctx = gtp0_pdp_find(gtp, nla_get_u64(info->attrs[GTPA_TID])); - break; - case GTP_V1: - if (!info->attrs[GTPA_I_TEI]) - return -EINVAL; - pctx = gtp1_pdp_find(gtp, nla_get_u64(info->attrs[GTPA_I_TEI])); - break; +static struct pdp_ctx *gtp_find_pdp(struct net *net, struct nlattr *nla[]) +{ + struct pdp_ctx *pctx; - default: + if (nla[GTPA_LINK]) + pctx = gtp_find_pdp_by_link(net, nla); + else + pctx = ERR_PTR(-EINVAL); + + if (!pctx) + pctx = ERR_PTR(-ENOENT); + + return pctx; +} + +static int gtp_genl_del_pdp(struct sk_buff *skb, struct genl_info *info) +{ + struct pdp_ctx *pctx; + int err = 0; + + if (!info->attrs[GTPA_VERSION]) return -EINVAL; - } - if (pctx == NULL) - return -ENOENT; + rcu_read_lock(); + + pctx = gtp_find_pdp(sock_net(skb->sk), info->attrs); + if (IS_ERR(pctx)) { + err = PTR_ERR(pctx); + goto out_unlock; + } if (pctx->gtp_version == GTP_V0) - netdev_dbg(dev, "GTPv0-U: deleting tunnel id = %llx (pdp %p)\n", + netdev_dbg(pctx->dev, "GTPv0-U: deleting tunnel id = %llx (pdp %p)\n", pctx->u.v0.tid, pctx); else if (pctx->gtp_version == GTP_V1) - netdev_dbg(dev, "GTPv1-U: deleting tunnel id = %x/%x (pdp %p)\n", + netdev_dbg(pctx->dev, "GTPv1-U: deleting tunnel id = %x/%x (pdp %p)\n", pctx->u.v1.i_tei, pctx->u.v1.o_tei, pctx); - hlist_del_rcu(&pctx->hlist_tid); - hlist_del_rcu(&pctx->hlist_addr); - kfree_rcu(pctx, rcu_head); + pdp_context_delete(pctx); - return 0; +out_unlock: + rcu_read_unlock(); + return err; } static struct genl_family gtp_genl_family; @@ -1117,59 +1154,17 @@ nla_put_failure: static int gtp_genl_get_pdp(struct sk_buff *skb, struct genl_info *info) { struct pdp_ctx *pctx = NULL; - struct net_device *dev; struct sk_buff *skb2; - struct gtp_dev *gtp; - u32 gtp_version; - struct net *net; int err; - if (!info->attrs[GTPA_VERSION] || - !info->attrs[GTPA_LINK]) + if (!info->attrs[GTPA_VERSION]) return -EINVAL; - gtp_version = nla_get_u32(info->attrs[GTPA_VERSION]); - switch (gtp_version) { - case GTP_V0: - case GTP_V1: - break; - default: - return -EINVAL; - } - - net = gtp_genl_get_net(sock_net(skb->sk), info->attrs); - if (IS_ERR(net)) - return PTR_ERR(net); - - /* Check if there's an existing gtpX device to configure */ - dev = gtp_find_dev(net, nla_get_u32(info->attrs[GTPA_LINK])); - if (dev == NULL) { - put_net(net); - return -ENODEV; - } - put_net(net); - - gtp = netdev_priv(dev); - rcu_read_lock(); - if (gtp_version == GTP_V0 && - info->attrs[GTPA_TID]) { - u64 tid = nla_get_u64(info->attrs[GTPA_TID]); - - pctx = gtp0_pdp_find(gtp, tid); - } else if (gtp_version == GTP_V1 && - info->attrs[GTPA_I_TEI]) { - u32 tid = nla_get_u32(info->attrs[GTPA_I_TEI]); - - pctx = gtp1_pdp_find(gtp, tid); - } else if (info->attrs[GTPA_MS_ADDRESS]) { - __be32 ip = nla_get_be32(info->attrs[GTPA_MS_ADDRESS]); - - pctx = ipv4_pdp_find(gtp, ip); - } - if (pctx == NULL) { - err = -ENOENT; + pctx = gtp_find_pdp(sock_net(skb->sk), info->attrs); + if (IS_ERR(pctx)) { + err = PTR_ERR(pctx); goto err_unlock; } diff --git a/drivers/net/hyperv/hyperv_net.h b/drivers/net/hyperv/hyperv_net.h index d3e73ac158ae..6b5f75217694 100644 --- a/drivers/net/hyperv/hyperv_net.h +++ b/drivers/net/hyperv/hyperv_net.h @@ -196,6 +196,7 @@ int netvsc_recv_callback(struct net_device *net, const struct ndis_tcp_ip_checksum_info *csum_info, const struct ndis_pkt_8021q_info *vlan); void netvsc_channel_cb(void *context); +int netvsc_poll(struct napi_struct *napi, int budget); int rndis_filter_open(struct netvsc_device *nvdev); int rndis_filter_close(struct netvsc_device *nvdev); int rndis_filter_device_add(struct hv_device *dev, @@ -700,6 +701,8 @@ struct net_device_context { u32 tx_checksum_mask; + u32 tx_send_table[VRSS_SEND_TAB_SIZE]; + /* Ethtool settings */ u8 duplex; u32 speed; @@ -720,6 +723,7 @@ struct net_device_context { /* Per channel data */ struct netvsc_channel { struct vmbus_channel *channel; + struct napi_struct napi; struct multi_send_data msd; struct multi_recv_comp mrc; atomic_t queue_sends; @@ -757,7 +761,6 @@ struct netvsc_device { struct nvsp_message revoke_packet; - u32 send_table[VRSS_SEND_TAB_SIZE]; u32 max_chn; u32 num_chn; spinlock_t sc_lock; /* Protects num_sc_offered variable */ @@ -1424,9 +1427,6 @@ struct rndis_message { ((void *) rndis_msg) -#define __struct_bcount(x) - - #define RNDIS_HEADER_SIZE (sizeof(struct rndis_message) - \ sizeof(union rndis_message_container)) diff --git a/drivers/net/hyperv/netvsc.c b/drivers/net/hyperv/netvsc.c index d35ebd993b38..989b7cd99380 100644 --- a/drivers/net/hyperv/netvsc.c +++ b/drivers/net/hyperv/netvsc.c @@ -91,15 +91,6 @@ static void free_netvsc_device(struct netvsc_device *nvdev) } -static inline bool netvsc_channel_idle(const struct netvsc_device *net_device, - u16 q_idx) -{ - const struct netvsc_channel *nvchan = &net_device->chan_table[q_idx]; - - return atomic_read(&net_device->num_outstanding_recvs) == 0 && - atomic_read(&nvchan->queue_sends) == 0; -} - static struct netvsc_device *get_outbound_net_device(struct hv_device *device) { struct netvsc_device *net_device = hv_device_to_netvsc_device(device); @@ -556,6 +547,7 @@ void netvsc_device_remove(struct hv_device *device) struct net_device *ndev = hv_get_drvdata(device); struct net_device_context *net_device_ctx = netdev_priv(ndev); struct netvsc_device *net_device = net_device_ctx->nvdev; + int i; netvsc_disconnect_vsp(device); @@ -570,6 +562,9 @@ void netvsc_device_remove(struct hv_device *device) /* Now, we can close the channel safely */ vmbus_close(device->channel); + for (i = 0; i < net_device->num_chn; i++) + napi_disable(&net_device->chan_table[i].napi); + /* Release all resources */ free_netvsc_device(net_device); } @@ -600,9 +595,9 @@ static inline void netvsc_free_send_slot(struct netvsc_device *net_device, static void netvsc_send_tx_complete(struct netvsc_device *net_device, struct vmbus_channel *incoming_channel, struct hv_device *device, - struct vmpacket_descriptor *packet) + const struct vmpacket_descriptor *desc) { - struct sk_buff *skb = (struct sk_buff *)(unsigned long)packet->trans_id; + struct sk_buff *skb = (struct sk_buff *)(unsigned long)desc->trans_id; struct net_device *ndev = hv_get_drvdata(device); struct net_device_context *net_device_ctx = netdev_priv(ndev); struct vmbus_channel *channel = device->channel; @@ -647,14 +642,11 @@ static void netvsc_send_tx_complete(struct netvsc_device *net_device, static void netvsc_send_completion(struct netvsc_device *net_device, struct vmbus_channel *incoming_channel, struct hv_device *device, - struct vmpacket_descriptor *packet) + const struct vmpacket_descriptor *desc) { - struct nvsp_message *nvsp_packet; + struct nvsp_message *nvsp_packet = hv_pkt_data(desc); struct net_device *ndev = hv_get_drvdata(device); - nvsp_packet = (struct nvsp_message *)((unsigned long)packet + - (packet->offset8 << 3)); - switch (nvsp_packet->hdr.msg_type) { case NVSP_MSG_TYPE_INIT_COMPLETE: case NVSP_MSG1_TYPE_SEND_RECV_BUF_COMPLETE: @@ -668,7 +660,7 @@ static void netvsc_send_completion(struct netvsc_device *net_device, case NVSP_MSG1_TYPE_SEND_RNDIS_PKT_COMPLETE: netvsc_send_tx_complete(net_device, incoming_channel, - device, packet); + device, desc); break; default: @@ -1066,28 +1058,29 @@ static inline struct recv_comp_data *get_recv_comp_slot( return rcd; } -static void netvsc_receive(struct net_device *ndev, +static int netvsc_receive(struct net_device *ndev, struct netvsc_device *net_device, struct net_device_context *net_device_ctx, struct hv_device *device, struct vmbus_channel *channel, - struct vmtransfer_page_packet_header *vmxferpage_packet, + const struct vmpacket_descriptor *desc, struct nvsp_message *nvsp) { + const struct vmtransfer_page_packet_header *vmxferpage_packet + = container_of(desc, const struct vmtransfer_page_packet_header, d); + u16 q_idx = channel->offermsg.offer.sub_channel_index; char *recv_buf = net_device->recv_buf; u32 status = NVSP_STAT_SUCCESS; int i; int count = 0; int ret; - struct recv_comp_data *rcd; - u16 q_idx = channel->offermsg.offer.sub_channel_index; /* Make sure this is a valid nvsp packet */ if (unlikely(nvsp->hdr.msg_type != NVSP_MSG1_TYPE_SEND_RNDIS_PKT)) { netif_err(net_device_ctx, rx_err, ndev, "Unknown nvsp packet type received %u\n", nvsp->hdr.msg_type); - return; + return 0; } if (unlikely(vmxferpage_packet->xfer_pageset_id != NETVSC_RECEIVE_BUFFER_ID)) { @@ -1095,7 +1088,7 @@ static void netvsc_receive(struct net_device *ndev, "Invalid xfer page set id - expecting %x got %x\n", NETVSC_RECEIVE_BUFFER_ID, vmxferpage_packet->xfer_pageset_id); - return; + return 0; } count = vmxferpage_packet->range_cnt; @@ -1111,40 +1104,36 @@ static void netvsc_receive(struct net_device *ndev, channel, data, buflen); } - if (!net_device->chan_table[q_idx].mrc.buf) { + if (net_device->chan_table[q_idx].mrc.buf) { + struct recv_comp_data *rcd; + + rcd = get_recv_comp_slot(net_device, channel, q_idx); + if (rcd) { + rcd->tid = vmxferpage_packet->d.trans_id; + rcd->status = status; + } else { + netdev_err(ndev, "Recv_comp full buf q:%hd, tid:%llx\n", + q_idx, vmxferpage_packet->d.trans_id); + } + } else { ret = netvsc_send_recv_completion(channel, vmxferpage_packet->d.trans_id, status); if (ret) netdev_err(ndev, "Recv_comp q:%hd, tid:%llx, err:%d\n", q_idx, vmxferpage_packet->d.trans_id, ret); - return; - } - - rcd = get_recv_comp_slot(net_device, channel, q_idx); - - if (!rcd) { - netdev_err(ndev, "Recv_comp full buf q:%hd, tid:%llx\n", - q_idx, vmxferpage_packet->d.trans_id); - return; } - - rcd->tid = vmxferpage_packet->d.trans_id; - rcd->status = status; + return count; } static void netvsc_send_table(struct hv_device *hdev, struct nvsp_message *nvmsg) { - struct netvsc_device *nvscdev; struct net_device *ndev = hv_get_drvdata(hdev); + struct net_device_context *net_device_ctx = netdev_priv(ndev); int i; u32 count, *tab; - nvscdev = get_outbound_net_device(hdev); - if (!nvscdev) - return; - count = nvmsg->msg.v5_msg.send_table.count; if (count != VRSS_SEND_TAB_SIZE) { netdev_err(ndev, "Received wrong send-table size:%u\n", count); @@ -1155,7 +1144,7 @@ static void netvsc_send_table(struct hv_device *hdev, nvmsg->msg.v5_msg.send_table.offset); for (i = 0; i < count; i++) - nvscdev->send_table[i] = tab[i]; + net_device_ctx->tx_send_table[i] = tab[i]; } static void netvsc_send_vf(struct net_device_context *net_device_ctx, @@ -1180,17 +1169,15 @@ static inline void netvsc_receive_inband(struct hv_device *hdev, } } -static void netvsc_process_raw_pkt(struct hv_device *device, - struct vmbus_channel *channel, - struct netvsc_device *net_device, - struct net_device *ndev, - u64 request_id, - struct vmpacket_descriptor *desc) +static int netvsc_process_raw_pkt(struct hv_device *device, + struct vmbus_channel *channel, + struct netvsc_device *net_device, + struct net_device *ndev, + u64 request_id, + const struct vmpacket_descriptor *desc) { struct net_device_context *net_device_ctx = netdev_priv(ndev); - struct nvsp_message *nvmsg - = (struct nvsp_message *)((unsigned long)desc - + (desc->offset8 << 3)); + struct nvsp_message *nvmsg = hv_pkt_data(desc); switch (desc->type) { case VM_PKT_COMP: @@ -1198,10 +1185,8 @@ static void netvsc_process_raw_pkt(struct hv_device *device, break; case VM_PKT_DATA_USING_XFER_PAGES: - netvsc_receive(ndev, net_device, net_device_ctx, - device, channel, - (struct vmtransfer_page_packet_header *)desc, - nvmsg); + return netvsc_receive(ndev, net_device, net_device_ctx, + device, channel, desc, nvmsg); break; case VM_PKT_DATA_INBAND: @@ -1213,47 +1198,75 @@ static void netvsc_process_raw_pkt(struct hv_device *device, desc->type, request_id); break; } + + return 0; } -void netvsc_channel_cb(void *context) +static struct hv_device *netvsc_channel_to_device(struct vmbus_channel *channel) { - struct vmbus_channel *channel = context; - u16 q_idx = channel->offermsg.offer.sub_channel_index; - struct hv_device *device; - struct netvsc_device *net_device; - struct vmpacket_descriptor *desc; - struct net_device *ndev; - bool need_to_commit = false; - - if (channel->primary_channel != NULL) - device = channel->primary_channel->device_obj; - else - device = channel->device_obj; + struct vmbus_channel *primary = channel->primary_channel; - ndev = hv_get_drvdata(device); - if (unlikely(!ndev)) - return; + return primary ? primary->device_obj : channel->device_obj; +} - net_device = net_device_to_netvsc_device(ndev); - if (unlikely(net_device->destroy) && - netvsc_channel_idle(net_device, q_idx)) - return; +/* Network processing softirq + * Process data in incoming ring buffer from host + * Stops when ring is empty or budget is met or exceeded. + */ +int netvsc_poll(struct napi_struct *napi, int budget) +{ + struct netvsc_channel *nvchan + = container_of(napi, struct netvsc_channel, napi); + struct vmbus_channel *channel = nvchan->channel; + struct hv_device *device = netvsc_channel_to_device(channel); + u16 q_idx = channel->offermsg.offer.sub_channel_index; + struct net_device *ndev = hv_get_drvdata(device); + struct netvsc_device *net_device = net_device_to_netvsc_device(ndev); + const struct vmpacket_descriptor *desc; + int work_done = 0; - /* commit_rd_index() -> hv_signal_on_read() needs this. */ - init_cached_read_index(channel); + desc = hv_pkt_iter_first(channel); + while (desc) { + int count; - while ((desc = get_next_pkt_raw(channel)) != NULL) { - netvsc_process_raw_pkt(device, channel, net_device, - ndev, desc->trans_id, desc); + count = netvsc_process_raw_pkt(device, channel, net_device, + ndev, desc->trans_id, desc); + work_done += count; + desc = __hv_pkt_iter_next(channel, desc); - put_pkt_raw(channel, desc); - need_to_commit = true; + /* If receive packet budget is exhausted, reschedule */ + if (work_done >= budget) { + work_done = budget; + break; + } } + hv_pkt_iter_close(channel); - if (need_to_commit) - commit_rd_index(channel); + /* If budget was not exhausted and + * not doing busy poll + * then re-enable host interrupts + * and reschedule if ring is not empty. + */ + if (work_done < budget && + napi_complete_done(napi, work_done) && + hv_end_read(&channel->inbound) != 0) + napi_reschedule(napi); netvsc_chk_recv_comp(net_device, channel, q_idx); + return work_done; +} + +/* Call back when data is available in host ring buffer. + * Processing is deferred until network softirq (NAPI) + */ +void netvsc_channel_cb(void *context) +{ + struct netvsc_channel *nvchan = context; + + /* disable interupts from host */ + hv_begin_read(&nvchan->channel->inbound); + + napi_schedule(&nvchan->napi); } /* @@ -1275,10 +1288,16 @@ int netvsc_device_add(struct hv_device *device, net_device->ring_size = ring_size; + /* Because the device uses NAPI, all the interrupt batching and + * control is done via Net softirq, not the channel handling + */ + set_channel_read_mode(device->channel, HV_CALL_ISR); + /* Open the channel */ ret = vmbus_open(device->channel, ring_size * PAGE_SIZE, ring_size * PAGE_SIZE, NULL, 0, - netvsc_channel_cb, device->channel); + netvsc_channel_cb, + net_device->chan_table); if (ret != 0) { netdev_err(ndev, "unable to open channel: %d\n", ret); @@ -1292,8 +1311,16 @@ int netvsc_device_add(struct hv_device *device, * chn_table with the default channel to use it before subchannels are * opened. */ - for (i = 0; i < VRSS_CHANNEL_MAX; i++) - net_device->chan_table[i].channel = device->channel; + for (i = 0; i < VRSS_CHANNEL_MAX; i++) { + struct netvsc_channel *nvchan = &net_device->chan_table[i]; + + nvchan->channel = device->channel; + netif_napi_add(ndev, &nvchan->napi, + netvsc_poll, NAPI_POLL_WEIGHT); + } + + /* Enable NAPI handler for init callbacks */ + napi_enable(&net_device->chan_table[0].napi); /* Writing nvdev pointer unlocks netvsc_send(), make sure chn_table is * populated. @@ -1313,6 +1340,8 @@ int netvsc_device_add(struct hv_device *device, return ret; close: + napi_disable(&net_device->chan_table[0].napi); + /* Now, we can close the channel safely */ vmbus_close(device->channel); diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c index bc05c895d958..191372486a87 100644 --- a/drivers/net/hyperv/netvsc_drv.c +++ b/drivers/net/hyperv/netvsc_drv.c @@ -206,17 +206,15 @@ static u16 netvsc_select_queue(struct net_device *ndev, struct sk_buff *skb, void *accel_priv, select_queue_fallback_t fallback) { struct net_device_context *net_device_ctx = netdev_priv(ndev); - struct netvsc_device *nvsc_dev = net_device_ctx->nvdev; + unsigned int num_tx_queues = ndev->real_num_tx_queues; struct sock *sk = skb->sk; int q_idx = sk_tx_queue_get(sk); - if (q_idx < 0 || skb->ooo_okay || - q_idx >= ndev->real_num_tx_queues) { + if (q_idx < 0 || skb->ooo_okay || q_idx >= num_tx_queues) { u16 hash = __skb_tx_hash(ndev, skb, VRSS_SEND_TAB_SIZE); int new_idx; - new_idx = nvsc_dev->send_table[hash] - % nvsc_dev->num_chn; + new_idx = net_device_ctx->tx_send_table[hash] % num_tx_queues; if (q_idx != new_idx && sk && sk_fullsock(sk) && rcu_access_pointer(sk->sk_dst_cache)) @@ -225,9 +223,6 @@ static u16 netvsc_select_queue(struct net_device *ndev, struct sk_buff *skb, q_idx = new_idx; } - if (unlikely(!nvsc_dev->chan_table[q_idx].channel)) - q_idx = 0; - return q_idx; } @@ -589,13 +584,14 @@ void netvsc_linkstatus_callback(struct hv_device *device_obj, } static struct sk_buff *netvsc_alloc_recv_skb(struct net_device *net, + struct napi_struct *napi, const struct ndis_tcp_ip_checksum_info *csum_info, const struct ndis_pkt_8021q_info *vlan, void *data, u32 buflen) { struct sk_buff *skb; - skb = netdev_alloc_skb_ip_align(net, buflen); + skb = napi_alloc_skb(napi, buflen); if (!skb) return skb; @@ -642,11 +638,11 @@ int netvsc_recv_callback(struct net_device *net, { struct net_device_context *net_device_ctx = netdev_priv(net); struct netvsc_device *net_device = net_device_ctx->nvdev; + u16 q_idx = channel->offermsg.offer.sub_channel_index; + struct netvsc_channel *nvchan = &net_device->chan_table[q_idx]; struct net_device *vf_netdev; struct sk_buff *skb; struct netvsc_stats *rx_stats; - u16 q_idx = channel->offermsg.offer.sub_channel_index; - if (net->reg_state != NETREG_REGISTERED) return NVSP_STAT_FAIL; @@ -664,7 +660,8 @@ int netvsc_recv_callback(struct net_device *net, net = vf_netdev; /* Allocate a skb - TODO direct I/O to pages? */ - skb = netvsc_alloc_recv_skb(net, csum_info, vlan, data, len); + skb = netvsc_alloc_recv_skb(net, &nvchan->napi, + csum_info, vlan, data, len); if (unlikely(!skb)) { ++net->stats.rx_dropped; rcu_read_unlock(); @@ -679,7 +676,7 @@ int netvsc_recv_callback(struct net_device *net, * on the synthetic device because modifying the VF device * statistics will not work correctly. */ - rx_stats = &net_device->chan_table[q_idx].rx_stats; + rx_stats = &nvchan->rx_stats; u64_stats_update_begin(&rx_stats->syncp); rx_stats->packets++; rx_stats->bytes += len; @@ -690,12 +687,7 @@ int netvsc_recv_callback(struct net_device *net, ++rx_stats->multicast; u64_stats_update_end(&rx_stats->syncp); - /* - * Pass the skb back up. Network stack will deallocate the skb when it - * is done. - * TODO - use NAPI? - */ - netif_receive_skb(skb); + napi_gro_receive(&nvchan->napi, skb); rcu_read_unlock(); return 0; @@ -792,18 +784,19 @@ static int netvsc_set_channels(struct net_device *net, return ret; } -static bool netvsc_validate_ethtool_ss_cmd(const struct ethtool_cmd *cmd) +static bool +netvsc_validate_ethtool_ss_cmd(const struct ethtool_link_ksettings *cmd) { - struct ethtool_cmd diff1 = *cmd; - struct ethtool_cmd diff2 = {}; + struct ethtool_link_ksettings diff1 = *cmd; + struct ethtool_link_ksettings diff2 = {}; - ethtool_cmd_speed_set(&diff1, 0); - diff1.duplex = 0; + diff1.base.speed = 0; + diff1.base.duplex = 0; /* advertising and cmd are usually set */ - diff1.advertising = 0; - diff1.cmd = 0; + ethtool_link_ksettings_zero_link_mode(&diff1, advertising); + diff1.base.cmd = 0; /* We set port to PORT_OTHER */ - diff2.port = PORT_OTHER; + diff2.base.port = PORT_OTHER; return !memcmp(&diff1, &diff2, sizeof(diff1)); } @@ -816,30 +809,32 @@ static void netvsc_init_settings(struct net_device *dev) ndc->duplex = DUPLEX_UNKNOWN; } -static int netvsc_get_settings(struct net_device *dev, struct ethtool_cmd *cmd) +static int netvsc_get_link_ksettings(struct net_device *dev, + struct ethtool_link_ksettings *cmd) { struct net_device_context *ndc = netdev_priv(dev); - ethtool_cmd_speed_set(cmd, ndc->speed); - cmd->duplex = ndc->duplex; - cmd->port = PORT_OTHER; + cmd->base.speed = ndc->speed; + cmd->base.duplex = ndc->duplex; + cmd->base.port = PORT_OTHER; return 0; } -static int netvsc_set_settings(struct net_device *dev, struct ethtool_cmd *cmd) +static int netvsc_set_link_ksettings(struct net_device *dev, + const struct ethtool_link_ksettings *cmd) { struct net_device_context *ndc = netdev_priv(dev); u32 speed; - speed = ethtool_cmd_speed(cmd); + speed = cmd->base.speed; if (!ethtool_validate_speed(speed) || - !ethtool_validate_duplex(cmd->duplex) || + !ethtool_validate_duplex(cmd->base.duplex) || !netvsc_validate_ethtool_ss_cmd(cmd)) return -EINVAL; ndc->speed = speed; - ndc->duplex = cmd->duplex; + ndc->duplex = cmd->base.duplex; return 0; } @@ -1173,13 +1168,13 @@ static const struct ethtool_ops ethtool_ops = { .get_channels = netvsc_get_channels, .set_channels = netvsc_set_channels, .get_ts_info = ethtool_op_get_ts_info, - .get_settings = netvsc_get_settings, - .set_settings = netvsc_set_settings, .get_rxnfc = netvsc_get_rxnfc, .get_rxfh_key_size = netvsc_get_rxfh_key_size, .get_rxfh_indir_size = netvsc_rss_indir_size, .get_rxfh = netvsc_get_rxfh, .set_rxfh = netvsc_set_rxfh, + .get_link_ksettings = netvsc_get_link_ksettings, + .set_link_ksettings = netvsc_set_link_ksettings, }; static const struct net_device_ops device_ops = { diff --git a/drivers/net/hyperv/rndis_filter.c b/drivers/net/hyperv/rndis_filter.c index 19356f56b7b1..382b9a62e3c4 100644 --- a/drivers/net/hyperv/rndis_filter.c +++ b/drivers/net/hyperv/rndis_filter.c @@ -996,21 +996,28 @@ static void netvsc_sc_open(struct vmbus_channel *new_sc) hv_get_drvdata(new_sc->primary_channel->device_obj); struct netvsc_device *nvscdev = net_device_to_netvsc_device(ndev); u16 chn_index = new_sc->offermsg.offer.sub_channel_index; - int ret; + struct netvsc_channel *nvchan; unsigned long flags; + int ret; if (chn_index >= nvscdev->num_chn) return; - nvscdev->chan_table[chn_index].mrc.buf + nvchan = nvscdev->chan_table + chn_index; + nvchan->mrc.buf = vzalloc(NETVSC_RECVSLOT_MAX * sizeof(struct recv_comp_data)); + if (!nvchan->mrc.buf) + return; + ret = vmbus_open(new_sc, nvscdev->ring_size * PAGE_SIZE, nvscdev->ring_size * PAGE_SIZE, NULL, 0, - netvsc_channel_cb, new_sc); + netvsc_channel_cb, nvchan); if (ret == 0) - nvscdev->chan_table[chn_index].channel = new_sc; + nvchan->channel = new_sc; + + napi_enable(&nvchan->napi); spin_lock_irqsave(&nvscdev->sc_lock, flags); nvscdev->num_sc_offered--; diff --git a/drivers/net/ntb_netdev.c b/drivers/net/ntb_netdev.c index 36877ba65516..4daf3d0926a8 100644 --- a/drivers/net/ntb_netdev.c +++ b/drivers/net/ntb_netdev.c @@ -372,18 +372,19 @@ static void ntb_get_drvinfo(struct net_device *ndev, strlcpy(info->bus_info, pci_name(dev->pdev), sizeof(info->bus_info)); } -static int ntb_get_settings(struct net_device *dev, struct ethtool_cmd *cmd) +static int ntb_get_link_ksettings(struct net_device *dev, + struct ethtool_link_ksettings *cmd) { - cmd->supported = SUPPORTED_Backplane; - cmd->advertising = ADVERTISED_Backplane; - ethtool_cmd_speed_set(cmd, SPEED_UNKNOWN); - cmd->duplex = DUPLEX_FULL; - cmd->port = PORT_OTHER; - cmd->phy_address = 0; - cmd->transceiver = XCVR_DUMMY1; - cmd->autoneg = AUTONEG_ENABLE; - cmd->maxtxpkt = 0; - cmd->maxrxpkt = 0; + ethtool_link_ksettings_zero_link_mode(cmd, supported); + ethtool_link_ksettings_add_link_mode(cmd, supported, Backplane); + ethtool_link_ksettings_zero_link_mode(cmd, advertising); + ethtool_link_ksettings_add_link_mode(cmd, advertising, Backplane); + + cmd->base.speed = SPEED_UNKNOWN; + cmd->base.duplex = DUPLEX_FULL; + cmd->base.port = PORT_OTHER; + cmd->base.phy_address = 0; + cmd->base.autoneg = AUTONEG_ENABLE; return 0; } @@ -391,7 +392,7 @@ static int ntb_get_settings(struct net_device *dev, struct ethtool_cmd *cmd) static const struct ethtool_ops ntb_ethtool_ops = { .get_drvinfo = ntb_get_drvinfo, .get_link = ethtool_op_get_link, - .get_settings = ntb_get_settings, + .get_link_ksettings = ntb_get_link_ksettings, }; static const struct ntb_queue_handlers ntb_netdev_handlers = { diff --git a/drivers/net/phy/bcm-phy-lib.c b/drivers/net/phy/bcm-phy-lib.c index ab9ad689617c..9656dbeb5de5 100644 --- a/drivers/net/phy/bcm-phy-lib.c +++ b/drivers/net/phy/bcm-phy-lib.c @@ -1,5 +1,5 @@ /* - * Copyright (C) 2015 Broadcom Corporation + * Copyright (C) 2015-2017 Broadcom * * This program is free software; you can redistribute it and/or * modify it under the terms of the GNU General Public License as @@ -221,9 +221,9 @@ int bcm_phy_set_eee(struct phy_device *phydev, bool enable) return val; if (enable) - val |= (MDIO_AN_EEE_ADV_100TX | MDIO_AN_EEE_ADV_1000T); + val |= (MDIO_EEE_100TX | MDIO_EEE_1000T); else - val &= ~(MDIO_AN_EEE_ADV_100TX | MDIO_AN_EEE_ADV_1000T); + val &= ~(MDIO_EEE_100TX | MDIO_EEE_1000T); phy_write_mmd_indirect(phydev, BCM_CL45VEN_EEE_ADV, MDIO_MMD_AN, (u32)val); diff --git a/drivers/net/phy/bcm7xxx.c b/drivers/net/phy/bcm7xxx.c index d1c2614dad3a..caa9f6e17f34 100644 --- a/drivers/net/phy/bcm7xxx.c +++ b/drivers/net/phy/bcm7xxx.c @@ -1,7 +1,7 @@ /* * Broadcom BCM7xxx internal transceivers support. * - * Copyright (C) 2014, Broadcom Corporation + * Copyright (C) 2014-2017 Broadcom * * This program is free software; you can redistribute it and/or * modify it under the terms of the GNU General Public License @@ -19,7 +19,7 @@ /* Broadcom BCM7xxx internal PHY registers */ -/* 40nm only register definitions */ +/* EPHY only register definitions */ #define MII_BCM7XXX_100TX_AUX_CTL 0x10 #define MII_BCM7XXX_100TX_FALSE_CAR 0x13 #define MII_BCM7XXX_100TX_DISC 0x14 @@ -27,6 +27,19 @@ #define MII_BCM7XXX_64CLK_MDIO BIT(12) #define MII_BCM7XXX_TEST 0x1f #define MII_BCM7XXX_SHD_MODE_2 BIT(2) +#define MII_BCM7XXX_SHD_2_ADDR_CTRL 0xe +#define MII_BCM7XXX_SHD_2_CTRL_STAT 0xf +#define MII_BCM7XXX_SHD_2_BIAS_TRIM 0x1a +#define MII_BCM7XXX_SHD_3_AN_EEE_ADV 0x3 +#define MII_BCM7XXX_SHD_3_PCS_CTRL_2 0x6 +#define MII_BCM7XXX_PCS_CTRL_2_DEF 0x4400 +#define MII_BCM7XXX_SHD_3_AN_STAT 0xb +#define MII_BCM7XXX_AN_NULL_MSG_EN BIT(0) +#define MII_BCM7XXX_AN_EEE_EN BIT(1) +#define MII_BCM7XXX_SHD_3_EEE_THRESH 0xe +#define MII_BCM7XXX_EEE_THRESH_DEF 0x50 +#define MII_BCM7XXX_SHD_3_TL4 0x23 +#define MII_BCM7XXX_TL4_RST_MSK (BIT(2) | BIT(1)) /* 28nm only register definitions */ #define MISC_ADDR(base, channel) base, channel @@ -286,6 +299,181 @@ static int phy_set_clr_bits(struct phy_device *dev, int location, return v; } +static int bcm7xxx_28nm_ephy_01_afe_config_init(struct phy_device *phydev) +{ + int ret; + + /* set shadow mode 2 */ + ret = phy_set_clr_bits(phydev, MII_BCM7XXX_TEST, + MII_BCM7XXX_SHD_MODE_2, 0); + if (ret < 0) + return ret; + + /* Set current trim values INT_trim = -1, Ext_trim =0 */ + ret = phy_write(phydev, MII_BCM7XXX_SHD_2_BIAS_TRIM, 0x3BE0); + if (ret < 0) + goto reset_shadow_mode; + + /* Cal reset */ + ret = phy_write(phydev, MII_BCM7XXX_SHD_2_ADDR_CTRL, + MII_BCM7XXX_SHD_3_TL4); + if (ret < 0) + goto reset_shadow_mode; + ret = phy_set_clr_bits(phydev, MII_BCM7XXX_SHD_2_CTRL_STAT, + MII_BCM7XXX_TL4_RST_MSK, 0); + if (ret < 0) + goto reset_shadow_mode; + + /* Cal reset disable */ + ret = phy_write(phydev, MII_BCM7XXX_SHD_2_ADDR_CTRL, + MII_BCM7XXX_SHD_3_TL4); + if (ret < 0) + goto reset_shadow_mode; + ret = phy_set_clr_bits(phydev, MII_BCM7XXX_SHD_2_CTRL_STAT, + 0, MII_BCM7XXX_TL4_RST_MSK); + if (ret < 0) + goto reset_shadow_mode; + +reset_shadow_mode: + /* reset shadow mode 2 */ + ret = phy_set_clr_bits(phydev, MII_BCM7XXX_TEST, 0, + MII_BCM7XXX_SHD_MODE_2); + if (ret < 0) + return ret; + + return 0; +} + +/* The 28nm EPHY does not support Clause 45 (MMD) used by bcm-phy-lib */ +static int bcm7xxx_28nm_ephy_apd_enable(struct phy_device *phydev) +{ + int ret; + + /* set shadow mode 1 */ + ret = phy_set_clr_bits(phydev, MII_BRCM_FET_BRCMTEST, + MII_BRCM_FET_BT_SRE, 0); + if (ret < 0) + return ret; + + /* Enable auto-power down */ + ret = phy_set_clr_bits(phydev, MII_BRCM_FET_SHDW_AUXSTAT2, + MII_BRCM_FET_SHDW_AS2_APDE, 0); + if (ret < 0) + return ret; + + /* reset shadow mode 1 */ + ret = phy_set_clr_bits(phydev, MII_BRCM_FET_BRCMTEST, 0, + MII_BRCM_FET_BT_SRE); + if (ret < 0) + return ret; + + return 0; +} + +static int bcm7xxx_28nm_ephy_eee_enable(struct phy_device *phydev) +{ + int ret; + + /* set shadow mode 2 */ + ret = phy_set_clr_bits(phydev, MII_BCM7XXX_TEST, + MII_BCM7XXX_SHD_MODE_2, 0); + if (ret < 0) + return ret; + + /* Advertise supported modes */ + ret = phy_write(phydev, MII_BCM7XXX_SHD_2_ADDR_CTRL, + MII_BCM7XXX_SHD_3_AN_EEE_ADV); + if (ret < 0) + goto reset_shadow_mode; + ret = phy_write(phydev, MII_BCM7XXX_SHD_2_CTRL_STAT, + MDIO_EEE_100TX); + if (ret < 0) + goto reset_shadow_mode; + + /* Restore Defaults */ + ret = phy_write(phydev, MII_BCM7XXX_SHD_2_ADDR_CTRL, + MII_BCM7XXX_SHD_3_PCS_CTRL_2); + if (ret < 0) + goto reset_shadow_mode; + ret = phy_write(phydev, MII_BCM7XXX_SHD_2_CTRL_STAT, + MII_BCM7XXX_PCS_CTRL_2_DEF); + if (ret < 0) + goto reset_shadow_mode; + + ret = phy_write(phydev, MII_BCM7XXX_SHD_2_ADDR_CTRL, + MII_BCM7XXX_SHD_3_EEE_THRESH); + if (ret < 0) + goto reset_shadow_mode; + ret = phy_write(phydev, MII_BCM7XXX_SHD_2_CTRL_STAT, + MII_BCM7XXX_EEE_THRESH_DEF); + if (ret < 0) + goto reset_shadow_mode; + + /* Enable EEE autonegotiation */ + ret = phy_write(phydev, MII_BCM7XXX_SHD_2_ADDR_CTRL, + MII_BCM7XXX_SHD_3_AN_STAT); + if (ret < 0) + goto reset_shadow_mode; + ret = phy_write(phydev, MII_BCM7XXX_SHD_2_CTRL_STAT, + (MII_BCM7XXX_AN_NULL_MSG_EN | MII_BCM7XXX_AN_EEE_EN)); + if (ret < 0) + goto reset_shadow_mode; + +reset_shadow_mode: + /* reset shadow mode 2 */ + ret = phy_set_clr_bits(phydev, MII_BCM7XXX_TEST, 0, + MII_BCM7XXX_SHD_MODE_2); + if (ret < 0) + return ret; + + /* Restart autoneg */ + phy_write(phydev, MII_BMCR, + (BMCR_SPEED100 | BMCR_ANENABLE | BMCR_ANRESTART)); + + return 0; +} + +static int bcm7xxx_28nm_ephy_config_init(struct phy_device *phydev) +{ + u8 rev = phydev->phy_id & ~phydev->drv->phy_id_mask; + int ret = 0; + + pr_info_once("%s: %s PHY revision: 0x%02x\n", + phydev_name(phydev), phydev->drv->name, rev); + + /* Dummy read to a register to workaround a possible issue upon reset + * where the internal inverter may not allow the first MDIO transaction + * to pass the MDIO management controller and make us return 0xffff for + * such reads. + */ + phy_read(phydev, MII_BMSR); + + /* Apply AFE software work-around if necessary */ + if (rev == 0x01) { + ret = bcm7xxx_28nm_ephy_01_afe_config_init(phydev); + if (ret) + return ret; + } + + ret = bcm7xxx_28nm_ephy_eee_enable(phydev); + if (ret) + return ret; + + return bcm7xxx_28nm_ephy_apd_enable(phydev); +} + +static int bcm7xxx_28nm_ephy_resume(struct phy_device *phydev) +{ + int ret; + + /* Re-apply workarounds coming out suspend/resume */ + ret = bcm7xxx_28nm_ephy_config_init(phydev); + if (ret) + return ret; + + return genphy_config_aneg(phydev); +} + static int bcm7xxx_config_init(struct phy_device *phydev) { int ret; @@ -434,6 +622,23 @@ static int bcm7xxx_28nm_probe(struct phy_device *phydev) .probe = bcm7xxx_28nm_probe, \ } +#define BCM7XXX_28NM_EPHY(_oui, _name) \ +{ \ + .phy_id = (_oui), \ + .phy_id_mask = 0xfffffff0, \ + .name = _name, \ + .features = PHY_BASIC_FEATURES, \ + .flags = PHY_IS_INTERNAL, \ + .config_init = bcm7xxx_28nm_ephy_config_init, \ + .config_aneg = genphy_config_aneg, \ + .read_status = genphy_read_status, \ + .resume = bcm7xxx_28nm_ephy_resume, \ + .get_sset_count = bcm_phy_get_sset_count, \ + .get_strings = bcm_phy_get_strings, \ + .get_stats = bcm7xxx_28nm_get_phy_stats, \ + .probe = bcm7xxx_28nm_probe, \ +} + #define BCM7XXX_40NM_EPHY(_oui, _name) \ { \ .phy_id = (_oui), \ @@ -450,6 +655,9 @@ static int bcm7xxx_28nm_probe(struct phy_device *phydev) static struct phy_driver bcm7xxx_driver[] = { BCM7XXX_28NM_GPHY(PHY_ID_BCM7250, "Broadcom BCM7250"), + BCM7XXX_28NM_EPHY(PHY_ID_BCM7260, "Broadcom BCM7260"), + BCM7XXX_28NM_EPHY(PHY_ID_BCM7268, "Broadcom BCM7268"), + BCM7XXX_28NM_EPHY(PHY_ID_BCM7271, "Broadcom BCM7271"), BCM7XXX_28NM_GPHY(PHY_ID_BCM7278, "Broadcom BCM7278"), BCM7XXX_28NM_GPHY(PHY_ID_BCM7364, "Broadcom BCM7364"), BCM7XXX_28NM_GPHY(PHY_ID_BCM7366, "Broadcom BCM7366"), @@ -466,6 +674,9 @@ static struct phy_driver bcm7xxx_driver[] = { static struct mdio_device_id __maybe_unused bcm7xxx_tbl[] = { { PHY_ID_BCM7250, 0xfffffff0, }, + { PHY_ID_BCM7260, 0xfffffff0, }, + { PHY_ID_BCM7268, 0xfffffff0, }, + { PHY_ID_BCM7271, 0xfffffff0, }, { PHY_ID_BCM7278, 0xfffffff0, }, { PHY_ID_BCM7364, 0xfffffff0, }, { PHY_ID_BCM7366, 0xfffffff0, }, diff --git a/drivers/net/phy/marvell.c b/drivers/net/phy/marvell.c index f9d0fa315a47..272b051a0199 100644 --- a/drivers/net/phy/marvell.c +++ b/drivers/net/phy/marvell.c @@ -1883,17 +1883,6 @@ static int m88e1510_probe(struct phy_device *phydev) return m88e1510_hwmon_probe(phydev); } -static void marvell_remove(struct phy_device *phydev) -{ -#ifdef CONFIG_HWMON - - struct marvell_priv *priv = phydev->priv; - - if (priv && priv->hwmon_dev) - hwmon_device_unregister(priv->hwmon_dev); -#endif -} - static struct phy_driver marvell_drivers[] = { { .phy_id = MARVELL_PHY_ID_88E1101, @@ -1974,7 +1963,6 @@ static struct phy_driver marvell_drivers[] = { .features = PHY_GBIT_FEATURES, .flags = PHY_HAS_INTERRUPT, .probe = &m88e1121_probe, - .remove = &marvell_remove, .config_init = &m88e1121_config_init, .config_aneg = &m88e1121_config_aneg, .read_status = &marvell_read_status, @@ -2087,7 +2075,6 @@ static struct phy_driver marvell_drivers[] = { .features = PHY_GBIT_FEATURES | SUPPORTED_FIBRE, .flags = PHY_HAS_INTERRUPT, .probe = &m88e1510_probe, - .remove = &marvell_remove, .config_init = &m88e1510_config_init, .config_aneg = &m88e1510_config_aneg, .read_status = &marvell_read_status, @@ -2109,7 +2096,6 @@ static struct phy_driver marvell_drivers[] = { .features = PHY_GBIT_FEATURES, .flags = PHY_HAS_INTERRUPT, .probe = m88e1510_probe, - .remove = &marvell_remove, .config_init = &marvell_config_init, .config_aneg = &m88e1510_config_aneg, .read_status = &marvell_read_status, @@ -2127,7 +2113,6 @@ static struct phy_driver marvell_drivers[] = { .phy_id_mask = MARVELL_PHY_ID_MASK, .name = "Marvell 88E1545", .probe = m88e1510_probe, - .remove = &marvell_remove, .features = PHY_GBIT_FEATURES, .flags = PHY_HAS_INTERRUPT, .config_init = &marvell_config_init, diff --git a/drivers/net/phy/mdio-bcm-unimac.c b/drivers/net/phy/mdio-bcm-unimac.c index 8c73b2e771dd..34395230ce70 100644 --- a/drivers/net/phy/mdio-bcm-unimac.c +++ b/drivers/net/phy/mdio-bcm-unimac.c @@ -1,7 +1,7 @@ /* * Broadcom UniMAC MDIO bus controller driver * - * Copyright (C) 2014, Broadcom Corporation + * Copyright (C) 2014-2017 Broadcom * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License as published by @@ -228,6 +228,7 @@ static int unimac_mdio_remove(struct platform_device *pdev) } static const struct of_device_id unimac_mdio_ids[] = { + { .compatible = "brcm,genet-mdio-v5", }, { .compatible = "brcm,genet-mdio-v4", }, { .compatible = "brcm,genet-mdio-v3", }, { .compatible = "brcm,genet-mdio-v2", }, diff --git a/drivers/net/phy/mdio-xgene.c b/drivers/net/phy/mdio-xgene.c index f095051beb54..3e2ac07b6e37 100644 --- a/drivers/net/phy/mdio-xgene.c +++ b/drivers/net/phy/mdio-xgene.c @@ -229,7 +229,7 @@ static int xgene_xfi_mdio_write(struct mii_bus *bus, int phy_id, val = SET_VAL(HSTPHYADX, phy_id) | SET_VAL(HSTREGADX, reg) | SET_VAL(HSTMIIMWRDAT, data); - xgene_enet_wr_mdio_csr(addr, MIIM_FIELD_ADDR, data); + xgene_enet_wr_mdio_csr(addr, MIIM_FIELD_ADDR, val); val = HSTLDCMD | SET_VAL(HSTMIIMCMD, MIIM_CMD_LEGACY_WRITE); xgene_enet_wr_mdio_csr(addr, MIIM_COMMAND_ADDR, val); diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c index daec6555f3b1..5198ccfa347f 100644 --- a/drivers/net/phy/phy_device.c +++ b/drivers/net/phy/phy_device.c @@ -1864,7 +1864,7 @@ static struct phy_driver genphy_driver[] = { .phy_id = 0xffffffff, .phy_id_mask = 0xffffffff, .name = "Generic PHY", - .soft_reset = genphy_soft_reset, + .soft_reset = genphy_no_soft_reset, .config_init = genphy_config_init, .features = PHY_GBIT_FEATURES | SUPPORTED_MII | SUPPORTED_AUI | SUPPORTED_FIBRE | diff --git a/drivers/net/phy/spi_ks8995.c b/drivers/net/phy/spi_ks8995.c index 93ffedfa2994..1e2d4f1179da 100644 --- a/drivers/net/phy/spi_ks8995.c +++ b/drivers/net/phy/spi_ks8995.c @@ -491,13 +491,14 @@ static int ks8995_probe(struct spi_device *spi) if (err) return err; - ks->regs_attr.size = ks->chip->regs_size; memcpy(&ks->regs_attr, &ks8995_registers_attr, sizeof(ks->regs_attr)); + ks->regs_attr.size = ks->chip->regs_size; err = ks8995_reset(ks); if (err) return err; + sysfs_attr_init(&ks->regs_attr.attr); err = sysfs_create_bin_file(&spi->dev.kobj, &ks->regs_attr); if (err) { dev_err(&spi->dev, "unable to create sysfs file, err=%d\n", diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c index 4a24b5d15f5a..1b52520715ae 100644 --- a/drivers/net/team/team.c +++ b/drivers/net/team/team.c @@ -2072,6 +2072,7 @@ static int team_dev_type_check_change(struct net_device *dev, static void team_setup(struct net_device *dev) { ether_setup(dev); + dev->max_mtu = ETH_MAX_MTU; dev->netdev_ops = &team_netdev_ops; dev->ethtool_ops = &team_ethtool_ops; diff --git a/drivers/net/tun.c b/drivers/net/tun.c index dc1b1dd9157c..16dfb4cb1980 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -822,7 +822,18 @@ static void tun_net_uninit(struct net_device *dev) /* Net device open. */ static int tun_net_open(struct net_device *dev) { + struct tun_struct *tun = netdev_priv(dev); + int i; + netif_tx_start_all_queues(dev); + + for (i = 0; i < tun->numqueues; i++) { + struct tun_file *tfile; + + tfile = rtnl_dereference(tun->tfiles[i]); + tfile->socket.sk->sk_write_space(tfile->socket.sk); + } + return 0; } @@ -1103,9 +1114,10 @@ static unsigned int tun_chr_poll(struct file *file, poll_table *wait) if (!skb_array_empty(&tfile->tx_array)) mask |= POLLIN | POLLRDNORM; - if (sock_writeable(sk) || - (!test_and_set_bit(SOCKWQ_ASYNC_NOSPACE, &sk->sk_socket->flags) && - sock_writeable(sk))) + if (tun->dev->flags & IFF_UP && + (sock_writeable(sk) || + (!test_and_set_bit(SOCKWQ_ASYNC_NOSPACE, &sk->sk_socket->flags) && + sock_writeable(sk)))) mask |= POLLOUT | POLLWRNORM; if (tun->dev->reg_state != NETREG_REGISTERED) @@ -2430,18 +2442,16 @@ static struct miscdevice tun_miscdev = { /* ethtool interface */ -static int tun_get_settings(struct net_device *dev, struct ethtool_cmd *cmd) -{ - cmd->supported = 0; - cmd->advertising = 0; - ethtool_cmd_speed_set(cmd, SPEED_10); - cmd->duplex = DUPLEX_FULL; - cmd->port = PORT_TP; - cmd->phy_address = 0; - cmd->transceiver = XCVR_INTERNAL; - cmd->autoneg = AUTONEG_DISABLE; - cmd->maxtxpkt = 0; - cmd->maxrxpkt = 0; +static int tun_get_link_ksettings(struct net_device *dev, + struct ethtool_link_ksettings *cmd) +{ + ethtool_link_ksettings_zero_link_mode(cmd, supported); + ethtool_link_ksettings_zero_link_mode(cmd, advertising); + cmd->base.speed = SPEED_10; + cmd->base.duplex = DUPLEX_FULL; + cmd->base.port = PORT_TP; + cmd->base.phy_address = 0; + cmd->base.autoneg = AUTONEG_DISABLE; return 0; } @@ -2504,7 +2514,6 @@ static int tun_set_coalesce(struct net_device *dev, } static const struct ethtool_ops tun_ethtool_ops = { - .get_settings = tun_get_settings, .get_drvinfo = tun_get_drvinfo, .get_msglevel = tun_get_msglevel, .set_msglevel = tun_set_msglevel, @@ -2512,6 +2521,7 @@ static const struct ethtool_ops tun_ethtool_ops = { .get_ts_info = ethtool_op_get_ts_info, .get_coalesce = tun_get_coalesce, .set_coalesce = tun_set_coalesce, + .get_link_ksettings = tun_get_link_ksettings, }; static int tun_queue_resize(struct tun_struct *tun) @@ -2570,7 +2580,6 @@ static int __init tun_init(void) int ret = 0; pr_info("%s, %s\n", DRV_DESCRIPTION, DRV_VERSION); - pr_info("%s\n", DRV_COPYRIGHT); ret = rtnl_link_register(&tun_link_ops); if (ret) { diff --git a/drivers/net/usb/ax88179_178a.c b/drivers/net/usb/ax88179_178a.c index a3a7db0702d8..4a0ae7ce83f6 100644 --- a/drivers/net/usb/ax88179_178a.c +++ b/drivers/net/usb/ax88179_178a.c @@ -620,16 +620,18 @@ ax88179_get_eeprom(struct net_device *net, struct ethtool_eeprom *eeprom, return 0; } -static int ax88179_get_settings(struct net_device *net, struct ethtool_cmd *cmd) +static int ax88179_get_link_ksettings(struct net_device *net, + struct ethtool_link_ksettings *cmd) { struct usbnet *dev = netdev_priv(net); - return mii_ethtool_gset(&dev->mii, cmd); + return mii_ethtool_get_link_ksettings(&dev->mii, cmd); } -static int ax88179_set_settings(struct net_device *net, struct ethtool_cmd *cmd) +static int ax88179_set_link_ksettings(struct net_device *net, + const struct ethtool_link_ksettings *cmd) { struct usbnet *dev = netdev_priv(net); - return mii_ethtool_sset(&dev->mii, cmd); + return mii_ethtool_set_link_ksettings(&dev->mii, cmd); } static int @@ -826,11 +828,11 @@ static const struct ethtool_ops ax88179_ethtool_ops = { .set_wol = ax88179_set_wol, .get_eeprom_len = ax88179_get_eeprom_len, .get_eeprom = ax88179_get_eeprom, - .get_settings = ax88179_get_settings, - .set_settings = ax88179_set_settings, .get_eee = ax88179_get_eee, .set_eee = ax88179_set_eee, .nway_reset = usbnet_nway_reset, + .get_link_ksettings = ax88179_get_link_ksettings, + .set_link_ksettings = ax88179_set_link_ksettings, }; static void ax88179_set_multicast(struct net_device *net) diff --git a/drivers/net/usb/catc.c b/drivers/net/usb/catc.c index 0acc9b640419..fce92f0e5abd 100644 --- a/drivers/net/usb/catc.c +++ b/drivers/net/usb/catc.c @@ -688,29 +688,34 @@ static void catc_get_drvinfo(struct net_device *dev, usb_make_path(catc->usbdev, info->bus_info, sizeof(info->bus_info)); } -static int catc_get_settings(struct net_device *dev, struct ethtool_cmd *cmd) +static int catc_get_link_ksettings(struct net_device *dev, + struct ethtool_link_ksettings *cmd) { struct catc *catc = netdev_priv(dev); if (!catc->is_f5u011) return -EOPNOTSUPP; - cmd->supported = SUPPORTED_10baseT_Half | SUPPORTED_TP; - cmd->advertising = ADVERTISED_10baseT_Half | ADVERTISED_TP; - ethtool_cmd_speed_set(cmd, SPEED_10); - cmd->duplex = DUPLEX_HALF; - cmd->port = PORT_TP; - cmd->phy_address = 0; - cmd->transceiver = XCVR_INTERNAL; - cmd->autoneg = AUTONEG_DISABLE; - cmd->maxtxpkt = 1; - cmd->maxrxpkt = 1; + ethtool_link_ksettings_zero_link_mode(cmd, supported); + ethtool_link_ksettings_add_link_mode(cmd, supported, 10baseT_Half); + ethtool_link_ksettings_add_link_mode(cmd, supported, TP); + + ethtool_link_ksettings_zero_link_mode(cmd, advertising); + ethtool_link_ksettings_add_link_mode(cmd, advertising, 10baseT_Half); + ethtool_link_ksettings_add_link_mode(cmd, advertising, TP); + + cmd->base.speed = SPEED_10; + cmd->base.duplex = DUPLEX_HALF; + cmd->base.port = PORT_TP; + cmd->base.phy_address = 0; + cmd->base.autoneg = AUTONEG_DISABLE; + return 0; } static const struct ethtool_ops ops = { .get_drvinfo = catc_get_drvinfo, - .get_settings = catc_get_settings, - .get_link = ethtool_op_get_link + .get_link = ethtool_op_get_link, + .get_link_ksettings = catc_get_link_ksettings, }; /* diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c index 986243c932cc..4b85e95ab754 100644 --- a/drivers/net/usb/r8152.c +++ b/drivers/net/usb/r8152.c @@ -1761,6 +1761,7 @@ static int rx_bottom(struct r8152 *tp, int budget) unsigned long flags; struct list_head *cursor, *next, rx_queue; int ret = 0, work_done = 0; + struct napi_struct *napi = &tp->napi; if (!skb_queue_empty(&tp->rx_queue)) { while (work_done < budget) { @@ -1773,7 +1774,7 @@ static int rx_bottom(struct r8152 *tp, int budget) break; pkt_len = skb->len; - napi_gro_receive(&tp->napi, skb); + napi_gro_receive(napi, skb); work_done++; stats->rx_packets++; stats->rx_bytes += pkt_len; @@ -1823,7 +1824,7 @@ static int rx_bottom(struct r8152 *tp, int budget) pkt_len -= CRC_SIZE; rx_data += sizeof(struct rx_desc); - skb = napi_alloc_skb(&tp->napi, pkt_len); + skb = napi_alloc_skb(napi, pkt_len); if (!skb) { stats->rx_dropped++; goto find_next_rx; @@ -1835,7 +1836,7 @@ static int rx_bottom(struct r8152 *tp, int budget) skb->protocol = eth_type_trans(skb, netdev); rtl_rx_vlan_tag(rx_desc, skb); if (work_done < budget) { - napi_gro_receive(&tp->napi, skb); + napi_gro_receive(napi, skb); work_done++; stats->rx_packets++; stats->rx_bytes += pkt_len; @@ -3150,6 +3151,7 @@ static bool rtl8153_in_nway(struct r8152 *tp) static void set_carrier(struct r8152 *tp) { struct net_device *netdev = tp->netdev; + struct napi_struct *napi = &tp->napi; u8 speed; speed = rtl8152_get_speed(tp); @@ -3159,7 +3161,7 @@ static void set_carrier(struct r8152 *tp) tp->rtl_ops.enable(tp); set_bit(RTL8152_SET_RX_MODE, &tp->flags); netif_stop_queue(netdev); - napi_disable(&tp->napi); + napi_disable(napi); netif_carrier_on(netdev); rtl_start_rx(tp); napi_enable(&tp->napi); @@ -3169,9 +3171,9 @@ static void set_carrier(struct r8152 *tp) } else { if (netif_carrier_ok(netdev)) { netif_carrier_off(netdev); - napi_disable(&tp->napi); + napi_disable(napi); tp->rtl_ops.disable(tp); - napi_enable(&tp->napi); + napi_enable(napi); netif_info(tp, link, netdev, "carrier off\n"); } } @@ -3633,11 +3635,13 @@ static int rtl8152_runtime_suspend(struct r8152 *tp) tp->rtl_ops.autosuspend_en(tp, true); if (netif_carrier_ok(netdev)) { - napi_disable(&tp->napi); + struct napi_struct *napi = &tp->napi; + + napi_disable(napi); rtl_stop_rx(tp); rxdy_gated_en(tp, false); ocp_write_dword(tp, MCU_TYPE_PLA, PLA_RCR, rcr); - napi_enable(&tp->napi); + napi_enable(napi); } } @@ -3653,12 +3657,14 @@ static int rtl8152_system_suspend(struct r8152 *tp) netif_device_detach(netdev); if (netif_running(netdev) && test_bit(WORK_ENABLE, &tp->flags)) { + struct napi_struct *napi = &tp->napi; + clear_bit(WORK_ENABLE, &tp->flags); usb_kill_urb(tp->intr_urb); - napi_disable(&tp->napi); + napi_disable(napi); cancel_delayed_work_sync(&tp->schedule); tp->rtl_ops.down(tp); - napi_enable(&tp->napi); + napi_enable(napi); } return ret; @@ -3684,35 +3690,38 @@ static int rtl8152_suspend(struct usb_interface *intf, pm_message_t message) static int rtl8152_resume(struct usb_interface *intf) { struct r8152 *tp = usb_get_intfdata(intf); + struct net_device *netdev = tp->netdev; mutex_lock(&tp->control); if (!test_bit(SELECTIVE_SUSPEND, &tp->flags)) { tp->rtl_ops.init(tp); queue_delayed_work(system_long_wq, &tp->hw_phy_work, 0); - netif_device_attach(tp->netdev); + netif_device_attach(netdev); } - if (netif_running(tp->netdev) && tp->netdev->flags & IFF_UP) { + if (netif_running(netdev) && netdev->flags & IFF_UP) { if (test_bit(SELECTIVE_SUSPEND, &tp->flags)) { + struct napi_struct *napi = &tp->napi; + tp->rtl_ops.autosuspend_en(tp, false); - napi_disable(&tp->napi); + napi_disable(napi); set_bit(WORK_ENABLE, &tp->flags); - if (netif_carrier_ok(tp->netdev)) + if (netif_carrier_ok(netdev)) rtl_start_rx(tp); - napi_enable(&tp->napi); + napi_enable(napi); clear_bit(SELECTIVE_SUSPEND, &tp->flags); smp_mb__after_atomic(); if (!list_empty(&tp->rx_done)) napi_schedule(&tp->napi); } else { tp->rtl_ops.up(tp); - netif_carrier_off(tp->netdev); + netif_carrier_off(netdev); set_bit(WORK_ENABLE, &tp->flags); } usb_submit_urb(tp->intr_urb, GFP_KERNEL); } else if (test_bit(SELECTIVE_SUSPEND, &tp->flags)) { - if (tp->netdev->flags & IFF_UP) + if (netdev->flags & IFF_UP) tp->rtl_ops.autosuspend_en(tp, false); clear_bit(SELECTIVE_SUSPEND, &tp->flags); } @@ -3800,7 +3809,8 @@ static void rtl8152_get_drvinfo(struct net_device *netdev, } static -int rtl8152_get_settings(struct net_device *netdev, struct ethtool_cmd *cmd) +int rtl8152_get_link_ksettings(struct net_device *netdev, + struct ethtool_link_ksettings *cmd) { struct r8152 *tp = netdev_priv(netdev); int ret; @@ -3814,7 +3824,7 @@ int rtl8152_get_settings(struct net_device *netdev, struct ethtool_cmd *cmd) mutex_lock(&tp->control); - ret = mii_ethtool_gset(&tp->mii, cmd); + ret = mii_ethtool_get_link_ksettings(&tp->mii, cmd); mutex_unlock(&tp->control); @@ -3824,7 +3834,8 @@ out: return ret; } -static int rtl8152_set_settings(struct net_device *dev, struct ethtool_cmd *cmd) +static int rtl8152_set_link_ksettings(struct net_device *dev, + const struct ethtool_link_ksettings *cmd) { struct r8152 *tp = netdev_priv(dev); int ret; @@ -3835,11 +3846,12 @@ static int rtl8152_set_settings(struct net_device *dev, struct ethtool_cmd *cmd) mutex_lock(&tp->control); - ret = rtl8152_set_speed(tp, cmd->autoneg, cmd->speed, cmd->duplex); + ret = rtl8152_set_speed(tp, cmd->base.autoneg, cmd->base.speed, + cmd->base.duplex); if (!ret) { - tp->autoneg = cmd->autoneg; - tp->speed = cmd->speed; - tp->duplex = cmd->duplex; + tp->autoneg = cmd->base.autoneg; + tp->speed = cmd->base.speed; + tp->duplex = cmd->base.duplex; } mutex_unlock(&tp->control); @@ -4117,8 +4129,6 @@ static int rtl8152_set_coalesce(struct net_device *netdev, static const struct ethtool_ops ops = { .get_drvinfo = rtl8152_get_drvinfo, - .get_settings = rtl8152_get_settings, - .set_settings = rtl8152_set_settings, .get_link = ethtool_op_get_link, .nway_reset = rtl8152_nway_reset, .get_msglevel = rtl8152_get_msglevel, @@ -4132,6 +4142,8 @@ static const struct ethtool_ops ops = { .set_coalesce = rtl8152_set_coalesce, .get_eee = rtl_ethtool_get_eee, .set_eee = rtl_ethtool_set_eee, + .get_link_ksettings = rtl8152_get_link_ksettings, + .set_link_ksettings = rtl8152_set_link_ksettings, }; static int rtl8152_ioctl(struct net_device *netdev, struct ifreq *rq, int cmd) diff --git a/drivers/net/usb/rtl8150.c b/drivers/net/usb/rtl8150.c index c81c79110cef..daaa88a66f40 100644 --- a/drivers/net/usb/rtl8150.c +++ b/drivers/net/usb/rtl8150.c @@ -791,47 +791,52 @@ static void rtl8150_get_drvinfo(struct net_device *netdev, struct ethtool_drvinf usb_make_path(dev->udev, info->bus_info, sizeof(info->bus_info)); } -static int rtl8150_get_settings(struct net_device *netdev, struct ethtool_cmd *ecmd) +static int rtl8150_get_link_ksettings(struct net_device *netdev, + struct ethtool_link_ksettings *ecmd) { rtl8150_t *dev = netdev_priv(netdev); short lpa, bmcr; + u32 supported; - ecmd->supported = (SUPPORTED_10baseT_Half | + supported = (SUPPORTED_10baseT_Half | SUPPORTED_10baseT_Full | SUPPORTED_100baseT_Half | SUPPORTED_100baseT_Full | SUPPORTED_Autoneg | SUPPORTED_TP | SUPPORTED_MII); - ecmd->port = PORT_TP; - ecmd->transceiver = XCVR_INTERNAL; - ecmd->phy_address = dev->phy; + ecmd->base.port = PORT_TP; + ecmd->base.phy_address = dev->phy; get_registers(dev, BMCR, 2, &bmcr); get_registers(dev, ANLP, 2, &lpa); if (bmcr & BMCR_ANENABLE) { u32 speed = ((lpa & (LPA_100HALF | LPA_100FULL)) ? SPEED_100 : SPEED_10); - ethtool_cmd_speed_set(ecmd, speed); - ecmd->autoneg = AUTONEG_ENABLE; + ecmd->base.speed = speed; + ecmd->base.autoneg = AUTONEG_ENABLE; if (speed == SPEED_100) - ecmd->duplex = (lpa & LPA_100FULL) ? + ecmd->base.duplex = (lpa & LPA_100FULL) ? DUPLEX_FULL : DUPLEX_HALF; else - ecmd->duplex = (lpa & LPA_10FULL) ? + ecmd->base.duplex = (lpa & LPA_10FULL) ? DUPLEX_FULL : DUPLEX_HALF; } else { - ecmd->autoneg = AUTONEG_DISABLE; - ethtool_cmd_speed_set(ecmd, ((bmcr & BMCR_SPEED100) ? - SPEED_100 : SPEED_10)); - ecmd->duplex = (bmcr & BMCR_FULLDPLX) ? + ecmd->base.autoneg = AUTONEG_DISABLE; + ecmd->base.speed = ((bmcr & BMCR_SPEED100) ? + SPEED_100 : SPEED_10); + ecmd->base.duplex = (bmcr & BMCR_FULLDPLX) ? DUPLEX_FULL : DUPLEX_HALF; } + + ethtool_convert_legacy_u32_to_link_mode(ecmd->link_modes.supported, + supported); + return 0; } static const struct ethtool_ops ops = { .get_drvinfo = rtl8150_get_drvinfo, - .get_settings = rtl8150_get_settings, - .get_link = ethtool_op_get_link + .get_link = ethtool_op_get_link, + .get_link_ksettings = rtl8150_get_link_ksettings, }; static int rtl8150_ioctl(struct net_device *netdev, struct ifreq *rq, int cmd) diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c index 22379da63400..7f28021d9d93 100644 --- a/drivers/net/vrf.c +++ b/drivers/net/vrf.c @@ -340,6 +340,7 @@ static netdev_tx_t is_ip_tx_frame(struct sk_buff *skb, struct net_device *dev) static netdev_tx_t vrf_xmit(struct sk_buff *skb, struct net_device *dev) { + int len = skb->len; netdev_tx_t ret = is_ip_tx_frame(skb, dev); if (likely(ret == NET_XMIT_SUCCESS || ret == NET_XMIT_CN)) { @@ -347,7 +348,7 @@ static netdev_tx_t vrf_xmit(struct sk_buff *skb, struct net_device *dev) u64_stats_update_begin(&dstats->syncp); dstats->tx_pkts++; - dstats->tx_bytes += skb->len; + dstats->tx_bytes += len; u64_stats_update_end(&dstats->syncp); } else { this_cpu_inc(dev->dstats->tx_drps); @@ -746,14 +747,18 @@ static int do_vrf_add_slave(struct net_device *dev, struct net_device *port_dev) { int ret; + port_dev->priv_flags |= IFF_L3MDEV_SLAVE; ret = netdev_master_upper_dev_link(port_dev, dev, NULL, NULL); if (ret < 0) - return ret; + goto err; - port_dev->priv_flags |= IFF_L3MDEV_SLAVE; cycle_netdev(port_dev); return 0; + +err: + port_dev->priv_flags &= ~IFF_L3MDEV_SLAVE; + return ret; } static int vrf_add_slave(struct net_device *dev, struct net_device *port_dev) diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c index e375560cc74e..09855be219e9 100644 --- a/drivers/net/vxlan.c +++ b/drivers/net/vxlan.c @@ -276,9 +276,9 @@ static int vxlan_fdb_info(struct sk_buff *skb, struct vxlan_dev *vxlan, send_eth = send_ip = true; if (type == RTM_GETNEIGH) { - ndm->ndm_family = AF_INET; send_ip = !vxlan_addr_any(&rdst->remote_ip); send_eth = !is_zero_ether_addr(fdb->eth_addr); + ndm->ndm_family = send_ip ? rdst->remote_ip.sa.sa_family : AF_INET; } else ndm->ndm_family = AF_BRIDGE; ndm->ndm_state = fdb->state; @@ -2976,6 +2976,44 @@ static int vxlan_dev_configure(struct net *src_net, struct net_device *dev, return 0; } +static int __vxlan_dev_create(struct net *net, struct net_device *dev, + struct vxlan_config *conf) +{ + struct vxlan_net *vn = net_generic(net, vxlan_net_id); + struct vxlan_dev *vxlan = netdev_priv(dev); + int err; + + err = vxlan_dev_configure(net, dev, conf, false); + if (err) + return err; + + dev->ethtool_ops = &vxlan_ethtool_ops; + + /* create an fdb entry for a valid default destination */ + if (!vxlan_addr_any(&vxlan->default_dst.remote_ip)) { + err = vxlan_fdb_create(vxlan, all_zeros_mac, + &vxlan->default_dst.remote_ip, + NUD_REACHABLE | NUD_PERMANENT, + NLM_F_EXCL | NLM_F_CREATE, + vxlan->cfg.dst_port, + vxlan->default_dst.remote_vni, + vxlan->default_dst.remote_vni, + vxlan->default_dst.remote_ifindex, + NTF_SELF); + if (err) + return err; + } + + err = register_netdevice(dev); + if (err) { + vxlan_fdb_delete_default(vxlan, vxlan->default_dst.remote_vni); + return err; + } + + list_add(&vxlan->next, &vn->vxlan_list); + return 0; +} + static int vxlan_nl2conf(struct nlattr *tb[], struct nlattr *data[], struct net_device *dev, struct vxlan_config *conf, bool changelink) @@ -3172,8 +3210,6 @@ static int vxlan_nl2conf(struct nlattr *tb[], struct nlattr *data[], static int vxlan_newlink(struct net *src_net, struct net_device *dev, struct nlattr *tb[], struct nlattr *data[]) { - struct vxlan_net *vn = net_generic(src_net, vxlan_net_id); - struct vxlan_dev *vxlan = netdev_priv(dev); struct vxlan_config conf; int err; @@ -3181,36 +3217,7 @@ static int vxlan_newlink(struct net *src_net, struct net_device *dev, if (err) return err; - err = vxlan_dev_configure(src_net, dev, &conf, false); - if (err) - return err; - - dev->ethtool_ops = &vxlan_ethtool_ops; - - /* create an fdb entry for a valid default destination */ - if (!vxlan_addr_any(&vxlan->default_dst.remote_ip)) { - err = vxlan_fdb_create(vxlan, all_zeros_mac, - &vxlan->default_dst.remote_ip, - NUD_REACHABLE | NUD_PERMANENT, - NLM_F_EXCL | NLM_F_CREATE, - vxlan->cfg.dst_port, - vxlan->default_dst.remote_vni, - vxlan->default_dst.remote_vni, - vxlan->default_dst.remote_ifindex, - NTF_SELF); - if (err) - return err; - } - - err = register_netdevice(dev); - if (err) { - vxlan_fdb_delete_default(vxlan, vxlan->default_dst.remote_vni); - return err; - } - - list_add(&vxlan->next, &vn->vxlan_list); - - return 0; + return __vxlan_dev_create(src_net, dev, &conf); } static int vxlan_changelink(struct net_device *dev, struct nlattr *tb[], @@ -3440,7 +3447,7 @@ struct net_device *vxlan_dev_create(struct net *net, const char *name, if (IS_ERR(dev)) return dev; - err = vxlan_dev_configure(net, dev, conf, false); + err = __vxlan_dev_create(net, dev, conf); if (err < 0) { free_netdev(dev); return ERR_PTR(err); diff --git a/drivers/net/wan/fsl_ucc_hdlc.c b/drivers/net/wan/fsl_ucc_hdlc.c index a5045b5279d7..6742ae605660 100644 --- a/drivers/net/wan/fsl_ucc_hdlc.c +++ b/drivers/net/wan/fsl_ucc_hdlc.c @@ -381,8 +381,8 @@ static netdev_tx_t ucc_hdlc_tx(struct sk_buff *skb, struct net_device *dev) /* set bd status and length */ bd_status = (bd_status & T_W_S) | T_R_S | T_I_S | T_L_S | T_TC_S; - iowrite16be(bd_status, &bd->status); iowrite16be(skb->len, &bd->length); + iowrite16be(bd_status, &bd->status); /* Move to next BD in the ring */ if (!(bd_status & T_W_S)) @@ -457,7 +457,7 @@ static int hdlc_rx_done(struct ucc_hdlc_private *priv, int rx_work_limit) struct sk_buff *skb; hdlc_device *hdlc = dev_to_hdlc(dev); struct qe_bd *bd; - u32 bd_status; + u16 bd_status; u16 length, howmany = 0; u8 *bdbuffer; int i; diff --git a/drivers/net/wimax/i2400m/usb.c b/drivers/net/wimax/i2400m/usb.c index e7f5910a6519..f8eb66ef2944 100644 --- a/drivers/net/wimax/i2400m/usb.c +++ b/drivers/net/wimax/i2400m/usb.c @@ -467,6 +467,9 @@ int i2400mu_probe(struct usb_interface *iface, struct i2400mu *i2400mu; struct usb_device *usb_dev = interface_to_usbdev(iface); + if (iface->cur_altsetting->desc.bNumEndpoints < 4) + return -ENODEV; + if (usb_dev->speed != USB_SPEED_HIGH) dev_err(dev, "device not connected as high speed\n"); diff --git a/drivers/net/xen-netback/interface.c b/drivers/net/xen-netback/interface.c index 829b26cd4549..8397f6c92451 100644 --- a/drivers/net/xen-netback/interface.c +++ b/drivers/net/xen-netback/interface.c @@ -165,13 +165,17 @@ static int xenvif_start_xmit(struct sk_buff *skb, struct net_device *dev) { struct xenvif *vif = netdev_priv(dev); struct xenvif_queue *queue = NULL; - unsigned int num_queues = vif->num_queues; + unsigned int num_queues; u16 index; struct xenvif_rx_cb *cb; BUG_ON(skb->dev != dev); - /* Drop the packet if queues are not set up */ + /* Drop the packet if queues are not set up. + * This handler should be called inside an RCU read section + * so we don't need to enter it here explicitly. + */ + num_queues = READ_ONCE(vif->num_queues); if (num_queues < 1) goto drop; @@ -222,18 +226,18 @@ static struct net_device_stats *xenvif_get_stats(struct net_device *dev) { struct xenvif *vif = netdev_priv(dev); struct xenvif_queue *queue = NULL; + unsigned int num_queues; u64 rx_bytes = 0; u64 rx_packets = 0; u64 tx_bytes = 0; u64 tx_packets = 0; unsigned int index; - spin_lock(&vif->lock); - if (vif->queues == NULL) - goto out; + rcu_read_lock(); + num_queues = READ_ONCE(vif->num_queues); /* Aggregate tx and rx stats from each queue */ - for (index = 0; index < vif->num_queues; ++index) { + for (index = 0; index < num_queues; ++index) { queue = &vif->queues[index]; rx_bytes += queue->stats.rx_bytes; rx_packets += queue->stats.rx_packets; @@ -241,8 +245,7 @@ static struct net_device_stats *xenvif_get_stats(struct net_device *dev) tx_packets += queue->stats.tx_packets; } -out: - spin_unlock(&vif->lock); + rcu_read_unlock(); vif->dev->stats.rx_bytes = rx_bytes; vif->dev->stats.rx_packets = rx_packets; @@ -378,10 +381,13 @@ static void xenvif_get_ethtool_stats(struct net_device *dev, struct ethtool_stats *stats, u64 * data) { struct xenvif *vif = netdev_priv(dev); - unsigned int num_queues = vif->num_queues; + unsigned int num_queues; int i; unsigned int queue_index; + rcu_read_lock(); + num_queues = READ_ONCE(vif->num_queues); + for (i = 0; i < ARRAY_SIZE(xenvif_stats); i++) { unsigned long accum = 0; for (queue_index = 0; queue_index < num_queues; ++queue_index) { @@ -390,6 +396,8 @@ static void xenvif_get_ethtool_stats(struct net_device *dev, } data[i] = accum; } + + rcu_read_unlock(); } static void xenvif_get_strings(struct net_device *dev, u32 stringset, u8 * data) diff --git a/drivers/net/xen-netback/netback.c b/drivers/net/xen-netback/netback.c index f9bcf4a665bc..602d408fa25e 100644 --- a/drivers/net/xen-netback/netback.c +++ b/drivers/net/xen-netback/netback.c @@ -214,7 +214,7 @@ static void xenvif_fatal_tx_err(struct xenvif *vif) netdev_err(vif->dev, "fatal error; disabling device\n"); vif->disabled = true; /* Disable the vif from queue 0's kthread */ - if (vif->queues) + if (vif->num_queues) xenvif_kick_thread(&vif->queues[0]); } diff --git a/drivers/net/xen-netback/xenbus.c b/drivers/net/xen-netback/xenbus.c index d2d7cd9145b1..a56d3eab35dd 100644 --- a/drivers/net/xen-netback/xenbus.c +++ b/drivers/net/xen-netback/xenbus.c @@ -495,26 +495,26 @@ static void backend_disconnect(struct backend_info *be) struct xenvif *vif = be->vif; if (vif) { + unsigned int num_queues = vif->num_queues; unsigned int queue_index; - struct xenvif_queue *queues; xen_unregister_watchers(vif); #ifdef CONFIG_DEBUG_FS xenvif_debugfs_delif(vif); #endif /* CONFIG_DEBUG_FS */ xenvif_disconnect_data(vif); - for (queue_index = 0; - queue_index < vif->num_queues; - ++queue_index) - xenvif_deinit_queue(&vif->queues[queue_index]); - spin_lock(&vif->lock); - queues = vif->queues; + /* At this point some of the handlers may still be active + * so we need to have additional synchronization here. + */ vif->num_queues = 0; - vif->queues = NULL; - spin_unlock(&vif->lock); + synchronize_net(); - vfree(queues); + for (queue_index = 0; queue_index < num_queues; ++queue_index) + xenvif_deinit_queue(&vif->queues[queue_index]); + + vfree(vif->queues); + vif->queues = NULL; xenvif_disconnect_ctrl(vif); } diff --git a/drivers/pci/dwc/pci-exynos.c b/drivers/pci/dwc/pci-exynos.c index 993b650ef275..44f774c12fb2 100644 --- a/drivers/pci/dwc/pci-exynos.c +++ b/drivers/pci/dwc/pci-exynos.c @@ -132,10 +132,6 @@ static int exynos5440_pcie_get_mem_resources(struct platform_device *pdev, struct device *dev = pci->dev; struct resource *res; - /* If using the PHY framework, doesn't need to get other resource */ - if (ep->using_phy) - return 0; - ep->mem_res = devm_kzalloc(dev, sizeof(*ep->mem_res), GFP_KERNEL); if (!ep->mem_res) return -ENOMEM; @@ -145,6 +141,10 @@ static int exynos5440_pcie_get_mem_resources(struct platform_device *pdev, if (IS_ERR(ep->mem_res->elbi_base)) return PTR_ERR(ep->mem_res->elbi_base); + /* If using the PHY framework, doesn't need to get other resource */ + if (ep->using_phy) + return 0; + res = platform_get_resource(pdev, IORESOURCE_MEM, 1); ep->mem_res->phy_base = devm_ioremap_resource(dev, res); if (IS_ERR(ep->mem_res->phy_base)) diff --git a/drivers/pci/pcie/aspm.c b/drivers/pci/pcie/aspm.c index 973472c23d89..1dfa10cc566b 100644 --- a/drivers/pci/pcie/aspm.c +++ b/drivers/pci/pcie/aspm.c @@ -478,7 +478,7 @@ static void aspm_calc_l1ss_info(struct pcie_link_state *link, static void pcie_aspm_cap_init(struct pcie_link_state *link, int blacklist) { - struct pci_dev *child, *parent = link->pdev; + struct pci_dev *child = link->downstream, *parent = link->pdev; struct pci_bus *linkbus = parent->subordinate; struct aspm_register_info upreg, dwreg; @@ -491,9 +491,7 @@ static void pcie_aspm_cap_init(struct pcie_link_state *link, int blacklist) /* Get upstream/downstream components' register state */ pcie_get_aspm_reg(parent, &upreg); - child = pci_function_0(linkbus); pcie_get_aspm_reg(child, &dwreg); - link->downstream = child; /* * If ASPM not supported, don't mess with the clocks and link, @@ -800,6 +798,7 @@ static struct pcie_link_state *alloc_pcie_link_state(struct pci_dev *pdev) INIT_LIST_HEAD(&link->children); INIT_LIST_HEAD(&link->link); link->pdev = pdev; + link->downstream = pci_function_0(pdev->subordinate); /* * Root Ports and PCI/PCI-X to PCIe Bridges are roots of PCIe diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c index f754453fe754..673683660b5c 100644 --- a/drivers/pci/quirks.c +++ b/drivers/pci/quirks.c @@ -2174,6 +2174,7 @@ DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_LSI_LOGIC, 0x005d, quirk_blacklist_vpd); DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_LSI_LOGIC, 0x005f, quirk_blacklist_vpd); DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATTANSIC, PCI_ANY_ID, quirk_blacklist_vpd); +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_QLOGIC, 0x2261, quirk_blacklist_vpd); /* * For Broadcom 5706, 5708, 5709 rev. A nics, any read beyond the diff --git a/drivers/pinctrl/qcom/pinctrl-msm.c b/drivers/pinctrl/qcom/pinctrl-msm.c index f8e9e1c2b2f6..c978be5eb9eb 100644 --- a/drivers/pinctrl/qcom/pinctrl-msm.c +++ b/drivers/pinctrl/qcom/pinctrl-msm.c @@ -422,6 +422,20 @@ static int msm_gpio_direction_output(struct gpio_chip *chip, unsigned offset, in return 0; } +static int msm_gpio_get_direction(struct gpio_chip *chip, unsigned int offset) +{ + struct msm_pinctrl *pctrl = gpiochip_get_data(chip); + const struct msm_pingroup *g; + u32 val; + + g = &pctrl->soc->groups[offset]; + + val = readl(pctrl->regs + g->ctl_reg); + + /* 0 = output, 1 = input */ + return val & BIT(g->oe_bit) ? 0 : 1; +} + static int msm_gpio_get(struct gpio_chip *chip, unsigned offset) { const struct msm_pingroup *g; @@ -510,6 +524,7 @@ static void msm_gpio_dbg_show(struct seq_file *s, struct gpio_chip *chip) static struct gpio_chip msm_gpio_template = { .direction_input = msm_gpio_direction_input, .direction_output = msm_gpio_direction_output, + .get_direction = msm_gpio_get_direction, .get = msm_gpio_get, .set = msm_gpio_set, .request = gpiochip_generic_request, diff --git a/drivers/pinctrl/uniphier/pinctrl-uniphier-ld11.c b/drivers/pinctrl/uniphier/pinctrl-uniphier-ld11.c index 77a0236ee781..83f8864fa76a 100644 --- a/drivers/pinctrl/uniphier/pinctrl-uniphier-ld11.c +++ b/drivers/pinctrl/uniphier/pinctrl-uniphier-ld11.c @@ -390,22 +390,22 @@ static const struct pinctrl_pin_desc uniphier_ld11_pins[] = { UNIPHIER_PINCTRL_PIN(140, "AO1D0", 140, 140, UNIPHIER_PIN_DRV_1BIT, 140, UNIPHIER_PIN_PULL_DOWN), - UNIPHIER_PINCTRL_PIN(141, "TCON0", 141, + UNIPHIER_PINCTRL_PIN(141, "AO1D1", 141, 141, UNIPHIER_PIN_DRV_1BIT, 141, UNIPHIER_PIN_PULL_DOWN), - UNIPHIER_PINCTRL_PIN(142, "TCON1", 142, + UNIPHIER_PINCTRL_PIN(142, "AO1D2", 142, 142, UNIPHIER_PIN_DRV_1BIT, 142, UNIPHIER_PIN_PULL_DOWN), - UNIPHIER_PINCTRL_PIN(143, "TCON2", 143, + UNIPHIER_PINCTRL_PIN(143, "XIRQ9", 143, 143, UNIPHIER_PIN_DRV_1BIT, 143, UNIPHIER_PIN_PULL_DOWN), - UNIPHIER_PINCTRL_PIN(144, "TCON3", 144, + UNIPHIER_PINCTRL_PIN(144, "XIRQ10", 144, 144, UNIPHIER_PIN_DRV_1BIT, 144, UNIPHIER_PIN_PULL_DOWN), - UNIPHIER_PINCTRL_PIN(145, "TCON4", 145, + UNIPHIER_PINCTRL_PIN(145, "XIRQ11", 145, 145, UNIPHIER_PIN_DRV_1BIT, 145, UNIPHIER_PIN_PULL_DOWN), - UNIPHIER_PINCTRL_PIN(146, "TCON5", 146, + UNIPHIER_PINCTRL_PIN(146, "XIRQ13", 146, 146, UNIPHIER_PIN_DRV_1BIT, 146, UNIPHIER_PIN_PULL_DOWN), UNIPHIER_PINCTRL_PIN(147, "PWMA", 147, diff --git a/drivers/platform/x86/asus-nb-wmi.c b/drivers/platform/x86/asus-nb-wmi.c index 5be4783e40d4..dea98ffb6f60 100644 --- a/drivers/platform/x86/asus-nb-wmi.c +++ b/drivers/platform/x86/asus-nb-wmi.c @@ -103,15 +103,6 @@ static struct quirk_entry quirk_asus_x200ca = { .wapf = 2, }; -static struct quirk_entry quirk_no_rfkill = { - .no_rfkill = true, -}; - -static struct quirk_entry quirk_no_rfkill_wapf4 = { - .wapf = 4, - .no_rfkill = true, -}; - static struct quirk_entry quirk_asus_ux303ub = { .wmi_backlight_native = true, }; @@ -194,7 +185,7 @@ static const struct dmi_system_id asus_quirks[] = { DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."), DMI_MATCH(DMI_PRODUCT_NAME, "X456UA"), }, - .driver_data = &quirk_no_rfkill_wapf4, + .driver_data = &quirk_asus_wapf4, }, { .callback = dmi_matched, @@ -203,7 +194,7 @@ static const struct dmi_system_id asus_quirks[] = { DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."), DMI_MATCH(DMI_PRODUCT_NAME, "X456UF"), }, - .driver_data = &quirk_no_rfkill_wapf4, + .driver_data = &quirk_asus_wapf4, }, { .callback = dmi_matched, @@ -369,42 +360,6 @@ static const struct dmi_system_id asus_quirks[] = { }, { .callback = dmi_matched, - .ident = "ASUSTeK COMPUTER INC. X555UB", - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."), - DMI_MATCH(DMI_PRODUCT_NAME, "X555UB"), - }, - .driver_data = &quirk_no_rfkill, - }, - { - .callback = dmi_matched, - .ident = "ASUSTeK COMPUTER INC. N552VW", - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."), - DMI_MATCH(DMI_PRODUCT_NAME, "N552VW"), - }, - .driver_data = &quirk_no_rfkill, - }, - { - .callback = dmi_matched, - .ident = "ASUSTeK COMPUTER INC. U303LB", - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."), - DMI_MATCH(DMI_PRODUCT_NAME, "U303LB"), - }, - .driver_data = &quirk_no_rfkill, - }, - { - .callback = dmi_matched, - .ident = "ASUSTeK COMPUTER INC. Z550MA", - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."), - DMI_MATCH(DMI_PRODUCT_NAME, "Z550MA"), - }, - .driver_data = &quirk_no_rfkill, - }, - { - .callback = dmi_matched, .ident = "ASUSTeK COMPUTER INC. UX303UB", .matches = { DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."), diff --git a/drivers/platform/x86/asus-wmi.c b/drivers/platform/x86/asus-wmi.c index 43cb680adbb4..8fe5890bf539 100644 --- a/drivers/platform/x86/asus-wmi.c +++ b/drivers/platform/x86/asus-wmi.c @@ -159,6 +159,8 @@ MODULE_LICENSE("GPL"); #define USB_INTEL_XUSB2PR 0xD0 #define PCI_DEVICE_ID_INTEL_LYNXPOINT_LP_XHCI 0x9c31 +static const char * const ashs_ids[] = { "ATK4001", "ATK4002", NULL }; + struct bios_args { u32 arg0; u32 arg1; @@ -2051,6 +2053,16 @@ static int asus_wmi_fan_init(struct asus_wmi *asus) return 0; } +static bool ashs_present(void) +{ + int i = 0; + while (ashs_ids[i]) { + if (acpi_dev_found(ashs_ids[i++])) + return true; + } + return false; +} + /* * WMI Driver */ @@ -2095,7 +2107,11 @@ static int asus_wmi_add(struct platform_device *pdev) if (err) goto fail_leds; - if (!asus->driver->quirks->no_rfkill) { + asus_wmi_get_devstate(asus, ASUS_WMI_DEVID_WLAN, &result); + if (result & (ASUS_WMI_DSTS_PRESENCE_BIT | ASUS_WMI_DSTS_USER_BIT)) + asus->driver->wlan_ctrl_by_user = 1; + + if (!(asus->driver->wlan_ctrl_by_user && ashs_present())) { err = asus_wmi_rfkill_init(asus); if (err) goto fail_rfkill; @@ -2134,10 +2150,6 @@ static int asus_wmi_add(struct platform_device *pdev) if (err) goto fail_debugfs; - asus_wmi_get_devstate(asus, ASUS_WMI_DEVID_WLAN, &result); - if (result & (ASUS_WMI_DSTS_PRESENCE_BIT | ASUS_WMI_DSTS_USER_BIT)) - asus->driver->wlan_ctrl_by_user = 1; - return 0; fail_debugfs: diff --git a/drivers/platform/x86/asus-wmi.h b/drivers/platform/x86/asus-wmi.h index fdff626c3b51..c9589d9342bb 100644 --- a/drivers/platform/x86/asus-wmi.h +++ b/drivers/platform/x86/asus-wmi.h @@ -39,7 +39,6 @@ struct key_entry; struct asus_wmi; struct quirk_entry { - bool no_rfkill; bool hotplug_wireless; bool scalar_panel_brightness; bool store_backlight_power; diff --git a/drivers/platform/x86/fujitsu-laptop.c b/drivers/platform/x86/fujitsu-laptop.c index 2b218b1d13e5..e12cc3504d48 100644 --- a/drivers/platform/x86/fujitsu-laptop.c +++ b/drivers/platform/x86/fujitsu-laptop.c @@ -78,18 +78,18 @@ #define FUJITSU_LCD_N_LEVELS 8 -#define ACPI_FUJITSU_CLASS "fujitsu" -#define ACPI_FUJITSU_HID "FUJ02B1" -#define ACPI_FUJITSU_DRIVER_NAME "Fujitsu laptop FUJ02B1 ACPI brightness driver" -#define ACPI_FUJITSU_DEVICE_NAME "Fujitsu FUJ02B1" -#define ACPI_FUJITSU_HOTKEY_HID "FUJ02E3" -#define ACPI_FUJITSU_HOTKEY_DRIVER_NAME "Fujitsu laptop FUJ02E3 ACPI hotkeys driver" -#define ACPI_FUJITSU_HOTKEY_DEVICE_NAME "Fujitsu FUJ02E3" +#define ACPI_FUJITSU_CLASS "fujitsu" +#define ACPI_FUJITSU_BL_HID "FUJ02B1" +#define ACPI_FUJITSU_BL_DRIVER_NAME "Fujitsu laptop FUJ02B1 ACPI brightness driver" +#define ACPI_FUJITSU_BL_DEVICE_NAME "Fujitsu FUJ02B1" +#define ACPI_FUJITSU_LAPTOP_HID "FUJ02E3" +#define ACPI_FUJITSU_LAPTOP_DRIVER_NAME "Fujitsu laptop FUJ02E3 ACPI hotkeys driver" +#define ACPI_FUJITSU_LAPTOP_DEVICE_NAME "Fujitsu FUJ02E3" #define ACPI_FUJITSU_NOTIFY_CODE1 0x80 /* FUNC interface - command values */ -#define FUNC_RFKILL 0x1000 +#define FUNC_FLAGS 0x1000 #define FUNC_LEDS 0x1001 #define FUNC_BUTTONS 0x1002 #define FUNC_BACKLIGHT 0x1004 @@ -97,6 +97,11 @@ /* FUNC interface - responses */ #define UNSUPPORTED_CMD 0x80000000 +/* FUNC interface - status flags */ +#define FLAG_RFKILL 0x020 +#define FLAG_LID 0x100 +#define FLAG_DOCK 0x200 + #if IS_ENABLED(CONFIG_LEDS_CLASS) /* FUNC interface - LED control */ #define FUNC_LED_OFF 0x1 @@ -136,7 +141,7 @@ #endif /* Device controlling the backlight and associated keys */ -struct fujitsu_t { +struct fujitsu_bl { acpi_handle acpi_handle; struct acpi_device *dev; struct input_dev *input; @@ -150,12 +155,12 @@ struct fujitsu_t { unsigned int brightness_level; }; -static struct fujitsu_t *fujitsu; +static struct fujitsu_bl *fujitsu_bl; static int use_alt_lcd_levels = -1; static int disable_brightness_adjust = -1; -/* Device used to access other hotkeys on the laptop */ -struct fujitsu_hotkey_t { +/* Device used to access hotkeys and other features on the laptop */ +struct fujitsu_laptop { acpi_handle acpi_handle; struct acpi_device *dev; struct input_dev *input; @@ -163,17 +168,15 @@ struct fujitsu_hotkey_t { struct platform_device *pf_device; struct kfifo fifo; spinlock_t fifo_lock; - int rfkill_supported; - int rfkill_state; + int flags_supported; + int flags_state; int logolamp_registered; int kblamps_registered; int radio_led_registered; int eco_led_registered; }; -static struct fujitsu_hotkey_t *fujitsu_hotkey; - -static void acpi_fujitsu_hotkey_notify(struct acpi_device *device, u32 event); +static struct fujitsu_laptop *fujitsu_laptop; #if IS_ENABLED(CONFIG_LEDS_CLASS) static enum led_brightness logolamp_get(struct led_classdev *cdev); @@ -222,8 +225,6 @@ static struct led_classdev eco_led = { static u32 dbg_level = 0x03; #endif -static void acpi_fujitsu_notify(struct acpi_device *device, u32 event); - /* Fujitsu ACPI interface function */ static int call_fext_func(int cmd, int arg0, int arg1, int arg2) @@ -239,7 +240,7 @@ static int call_fext_func(int cmd, int arg0, int arg1, int arg2) unsigned long long value; acpi_handle handle = NULL; - status = acpi_get_handle(fujitsu_hotkey->acpi_handle, "FUNC", &handle); + status = acpi_get_handle(fujitsu_laptop->acpi_handle, "FUNC", &handle); if (ACPI_FAILURE(status)) { vdbg_printk(FUJLAPTOP_DBG_ERROR, "FUNC interface is not present\n"); @@ -300,9 +301,9 @@ static int radio_led_set(struct led_classdev *cdev, enum led_brightness brightness) { if (brightness >= LED_FULL) - return call_fext_func(FUNC_RFKILL, 0x5, RADIO_LED_ON, RADIO_LED_ON); + return call_fext_func(FUNC_FLAGS, 0x5, RADIO_LED_ON, RADIO_LED_ON); else - return call_fext_func(FUNC_RFKILL, 0x5, RADIO_LED_ON, 0x0); + return call_fext_func(FUNC_FLAGS, 0x5, RADIO_LED_ON, 0x0); } static int eco_led_set(struct led_classdev *cdev, @@ -346,7 +347,7 @@ static enum led_brightness radio_led_get(struct led_classdev *cdev) { enum led_brightness brightness = LED_OFF; - if (call_fext_func(FUNC_RFKILL, 0x4, 0x0, 0x0) & RADIO_LED_ON) + if (call_fext_func(FUNC_FLAGS, 0x4, 0x0, 0x0) & RADIO_LED_ON) brightness = LED_FULL; return brightness; @@ -373,10 +374,10 @@ static int set_lcd_level(int level) vdbg_printk(FUJLAPTOP_DBG_TRACE, "set lcd level via SBLL [%d]\n", level); - if (level < 0 || level >= fujitsu->max_brightness) + if (level < 0 || level >= fujitsu_bl->max_brightness) return -EINVAL; - status = acpi_get_handle(fujitsu->acpi_handle, "SBLL", &handle); + status = acpi_get_handle(fujitsu_bl->acpi_handle, "SBLL", &handle); if (ACPI_FAILURE(status)) { vdbg_printk(FUJLAPTOP_DBG_ERROR, "SBLL not present\n"); return -ENODEV; @@ -398,10 +399,10 @@ static int set_lcd_level_alt(int level) vdbg_printk(FUJLAPTOP_DBG_TRACE, "set lcd level via SBL2 [%d]\n", level); - if (level < 0 || level >= fujitsu->max_brightness) + if (level < 0 || level >= fujitsu_bl->max_brightness) return -EINVAL; - status = acpi_get_handle(fujitsu->acpi_handle, "SBL2", &handle); + status = acpi_get_handle(fujitsu_bl->acpi_handle, "SBL2", &handle); if (ACPI_FAILURE(status)) { vdbg_printk(FUJLAPTOP_DBG_ERROR, "SBL2 not present\n"); return -ENODEV; @@ -421,19 +422,19 @@ static int get_lcd_level(void) vdbg_printk(FUJLAPTOP_DBG_TRACE, "get lcd level via GBLL\n"); - status = - acpi_evaluate_integer(fujitsu->acpi_handle, "GBLL", NULL, &state); + status = acpi_evaluate_integer(fujitsu_bl->acpi_handle, "GBLL", NULL, + &state); if (ACPI_FAILURE(status)) return 0; - fujitsu->brightness_level = state & 0x0fffffff; + fujitsu_bl->brightness_level = state & 0x0fffffff; if (state & 0x80000000) - fujitsu->brightness_changed = 1; + fujitsu_bl->brightness_changed = 1; else - fujitsu->brightness_changed = 0; + fujitsu_bl->brightness_changed = 0; - return fujitsu->brightness_level; + return fujitsu_bl->brightness_level; } static int get_max_brightness(void) @@ -443,14 +444,14 @@ static int get_max_brightness(void) vdbg_printk(FUJLAPTOP_DBG_TRACE, "get max lcd level via RBLL\n"); - status = - acpi_evaluate_integer(fujitsu->acpi_handle, "RBLL", NULL, &state); + status = acpi_evaluate_integer(fujitsu_bl->acpi_handle, "RBLL", NULL, + &state); if (ACPI_FAILURE(status)) return -1; - fujitsu->max_brightness = state; + fujitsu_bl->max_brightness = state; - return fujitsu->max_brightness; + return fujitsu_bl->max_brightness; } /* Backlight device stuff */ @@ -483,7 +484,7 @@ static int bl_update_status(struct backlight_device *b) return ret; } -static const struct backlight_ops fujitsubl_ops = { +static const struct backlight_ops fujitsu_bl_ops = { .get_brightness = bl_get_brightness, .update_status = bl_update_status, }; @@ -511,7 +512,7 @@ show_brightness_changed(struct device *dev, int ret; - ret = fujitsu->brightness_changed; + ret = fujitsu_bl->brightness_changed; if (ret < 0) return ret; @@ -539,7 +540,7 @@ static ssize_t store_lcd_level(struct device *dev, int level, ret; if (sscanf(buf, "%i", &level) != 1 - || (level < 0 || level >= fujitsu->max_brightness)) + || (level < 0 || level >= fujitsu_bl->max_brightness)) return -EINVAL; if (use_alt_lcd_levels) @@ -567,9 +568,9 @@ static ssize_t show_lid_state(struct device *dev, struct device_attribute *attr, char *buf) { - if (!(fujitsu_hotkey->rfkill_supported & 0x100)) + if (!(fujitsu_laptop->flags_supported & FLAG_LID)) return sprintf(buf, "unknown\n"); - if (fujitsu_hotkey->rfkill_state & 0x100) + if (fujitsu_laptop->flags_state & FLAG_LID) return sprintf(buf, "open\n"); else return sprintf(buf, "closed\n"); @@ -579,9 +580,9 @@ static ssize_t show_dock_state(struct device *dev, struct device_attribute *attr, char *buf) { - if (!(fujitsu_hotkey->rfkill_supported & 0x200)) + if (!(fujitsu_laptop->flags_supported & FLAG_DOCK)) return sprintf(buf, "unknown\n"); - if (fujitsu_hotkey->rfkill_state & 0x200) + if (fujitsu_laptop->flags_state & FLAG_DOCK) return sprintf(buf, "docked\n"); else return sprintf(buf, "undocked\n"); @@ -591,9 +592,9 @@ static ssize_t show_radios_state(struct device *dev, struct device_attribute *attr, char *buf) { - if (!(fujitsu_hotkey->rfkill_supported & 0x20)) + if (!(fujitsu_laptop->flags_supported & FLAG_RFKILL)) return sprintf(buf, "unknown\n"); - if (fujitsu_hotkey->rfkill_state & 0x20) + if (fujitsu_laptop->flags_state & FLAG_RFKILL) return sprintf(buf, "on\n"); else return sprintf(buf, "killed\n"); @@ -607,7 +608,7 @@ static DEVICE_ATTR(lid, 0444, show_lid_state, ignore_store); static DEVICE_ATTR(dock, 0444, show_dock_state, ignore_store); static DEVICE_ATTR(radios, 0444, show_radios_state, ignore_store); -static struct attribute *fujitsupf_attributes[] = { +static struct attribute *fujitsu_pf_attributes[] = { &dev_attr_brightness_changed.attr, &dev_attr_max_brightness.attr, &dev_attr_lcd_level.attr, @@ -617,11 +618,11 @@ static struct attribute *fujitsupf_attributes[] = { NULL }; -static struct attribute_group fujitsupf_attribute_group = { - .attrs = fujitsupf_attributes +static struct attribute_group fujitsu_pf_attribute_group = { + .attrs = fujitsu_pf_attributes }; -static struct platform_driver fujitsupf_driver = { +static struct platform_driver fujitsu_pf_driver = { .driver = { .name = "fujitsu-laptop", } @@ -630,39 +631,30 @@ static struct platform_driver fujitsupf_driver = { static void __init dmi_check_cb_common(const struct dmi_system_id *id) { pr_info("Identified laptop model '%s'\n", id->ident); - if (use_alt_lcd_levels == -1) { - if (acpi_has_method(NULL, - "\\_SB.PCI0.LPCB.FJEX.SBL2")) - use_alt_lcd_levels = 1; - else - use_alt_lcd_levels = 0; - vdbg_printk(FUJLAPTOP_DBG_TRACE, "auto-detected usealt as " - "%i\n", use_alt_lcd_levels); - } } static int __init dmi_check_cb_s6410(const struct dmi_system_id *id) { dmi_check_cb_common(id); - fujitsu->keycode1 = KEY_SCREENLOCK; /* "Lock" */ - fujitsu->keycode2 = KEY_HELP; /* "Mobility Center" */ + fujitsu_bl->keycode1 = KEY_SCREENLOCK; /* "Lock" */ + fujitsu_bl->keycode2 = KEY_HELP; /* "Mobility Center" */ return 1; } static int __init dmi_check_cb_s6420(const struct dmi_system_id *id) { dmi_check_cb_common(id); - fujitsu->keycode1 = KEY_SCREENLOCK; /* "Lock" */ - fujitsu->keycode2 = KEY_HELP; /* "Mobility Center" */ + fujitsu_bl->keycode1 = KEY_SCREENLOCK; /* "Lock" */ + fujitsu_bl->keycode2 = KEY_HELP; /* "Mobility Center" */ return 1; } static int __init dmi_check_cb_p8010(const struct dmi_system_id *id) { dmi_check_cb_common(id); - fujitsu->keycode1 = KEY_HELP; /* "Support" */ - fujitsu->keycode3 = KEY_SWITCHVIDEOMODE; /* "Presentation" */ - fujitsu->keycode4 = KEY_WWW; /* "Internet" */ + fujitsu_bl->keycode1 = KEY_HELP; /* "Support" */ + fujitsu_bl->keycode3 = KEY_SWITCHVIDEOMODE; /* "Presentation" */ + fujitsu_bl->keycode4 = KEY_WWW; /* "Internet" */ return 1; } @@ -693,7 +685,7 @@ static const struct dmi_system_id fujitsu_dmi_table[] __initconst = { /* ACPI device for LCD brightness control */ -static int acpi_fujitsu_add(struct acpi_device *device) +static int acpi_fujitsu_bl_add(struct acpi_device *device) { int state = 0; struct input_dev *input; @@ -702,22 +694,22 @@ static int acpi_fujitsu_add(struct acpi_device *device) if (!device) return -EINVAL; - fujitsu->acpi_handle = device->handle; - sprintf(acpi_device_name(device), "%s", ACPI_FUJITSU_DEVICE_NAME); + fujitsu_bl->acpi_handle = device->handle; + sprintf(acpi_device_name(device), "%s", ACPI_FUJITSU_BL_DEVICE_NAME); sprintf(acpi_device_class(device), "%s", ACPI_FUJITSU_CLASS); - device->driver_data = fujitsu; + device->driver_data = fujitsu_bl; - fujitsu->input = input = input_allocate_device(); + fujitsu_bl->input = input = input_allocate_device(); if (!input) { error = -ENOMEM; goto err_stop; } - snprintf(fujitsu->phys, sizeof(fujitsu->phys), + snprintf(fujitsu_bl->phys, sizeof(fujitsu_bl->phys), "%s/video/input0", acpi_device_hid(device)); input->name = acpi_device_name(device); - input->phys = fujitsu->phys; + input->phys = fujitsu_bl->phys; input->id.bustype = BUS_HOST; input->id.product = 0x06; input->dev.parent = &device->dev; @@ -730,7 +722,7 @@ static int acpi_fujitsu_add(struct acpi_device *device) if (error) goto err_free_input_dev; - error = acpi_bus_update_power(fujitsu->acpi_handle, &state); + error = acpi_bus_update_power(fujitsu_bl->acpi_handle, &state); if (error) { pr_err("Error reading power state\n"); goto err_unregister_input_dev; @@ -740,7 +732,7 @@ static int acpi_fujitsu_add(struct acpi_device *device) acpi_device_name(device), acpi_device_bid(device), !device->power.state ? "on" : "off"); - fujitsu->dev = device; + fujitsu_bl->dev = device; if (acpi_has_method(device->handle, METHOD_NAME__INI)) { vdbg_printk(FUJLAPTOP_DBG_INFO, "Invoking _INI\n"); @@ -750,6 +742,15 @@ static int acpi_fujitsu_add(struct acpi_device *device) pr_err("_INI Method failed\n"); } + if (use_alt_lcd_levels == -1) { + if (acpi_has_method(NULL, "\\_SB.PCI0.LPCB.FJEX.SBL2")) + use_alt_lcd_levels = 1; + else + use_alt_lcd_levels = 0; + vdbg_printk(FUJLAPTOP_DBG_TRACE, "auto-detected usealt as %i\n", + use_alt_lcd_levels); + } + /* do config (detect defaults) */ use_alt_lcd_levels = use_alt_lcd_levels == 1 ? 1 : 0; disable_brightness_adjust = disable_brightness_adjust == 1 ? 1 : 0; @@ -758,7 +759,7 @@ static int acpi_fujitsu_add(struct acpi_device *device) use_alt_lcd_levels, disable_brightness_adjust); if (get_max_brightness() <= 0) - fujitsu->max_brightness = FUJITSU_LCD_N_LEVELS; + fujitsu_bl->max_brightness = FUJITSU_LCD_N_LEVELS; get_lcd_level(); return 0; @@ -772,38 +773,38 @@ err_stop: return error; } -static int acpi_fujitsu_remove(struct acpi_device *device) +static int acpi_fujitsu_bl_remove(struct acpi_device *device) { - struct fujitsu_t *fujitsu = acpi_driver_data(device); - struct input_dev *input = fujitsu->input; + struct fujitsu_bl *fujitsu_bl = acpi_driver_data(device); + struct input_dev *input = fujitsu_bl->input; input_unregister_device(input); - fujitsu->acpi_handle = NULL; + fujitsu_bl->acpi_handle = NULL; return 0; } /* Brightness notify */ -static void acpi_fujitsu_notify(struct acpi_device *device, u32 event) +static void acpi_fujitsu_bl_notify(struct acpi_device *device, u32 event) { struct input_dev *input; int keycode; int oldb, newb; - input = fujitsu->input; + input = fujitsu_bl->input; switch (event) { case ACPI_FUJITSU_NOTIFY_CODE1: keycode = 0; - oldb = fujitsu->brightness_level; + oldb = fujitsu_bl->brightness_level; get_lcd_level(); - newb = fujitsu->brightness_level; + newb = fujitsu_bl->brightness_level; vdbg_printk(FUJLAPTOP_DBG_TRACE, "brightness button event [%i -> %i (%i)]\n", - oldb, newb, fujitsu->brightness_changed); + oldb, newb, fujitsu_bl->brightness_changed); if (oldb < newb) { if (disable_brightness_adjust != 1) { @@ -840,7 +841,7 @@ static void acpi_fujitsu_notify(struct acpi_device *device, u32 event) /* ACPI device for hotkey handling */ -static int acpi_fujitsu_hotkey_add(struct acpi_device *device) +static int acpi_fujitsu_laptop_add(struct acpi_device *device) { int result = 0; int state = 0; @@ -851,42 +852,42 @@ static int acpi_fujitsu_hotkey_add(struct acpi_device *device) if (!device) return -EINVAL; - fujitsu_hotkey->acpi_handle = device->handle; + fujitsu_laptop->acpi_handle = device->handle; sprintf(acpi_device_name(device), "%s", - ACPI_FUJITSU_HOTKEY_DEVICE_NAME); + ACPI_FUJITSU_LAPTOP_DEVICE_NAME); sprintf(acpi_device_class(device), "%s", ACPI_FUJITSU_CLASS); - device->driver_data = fujitsu_hotkey; + device->driver_data = fujitsu_laptop; /* kfifo */ - spin_lock_init(&fujitsu_hotkey->fifo_lock); - error = kfifo_alloc(&fujitsu_hotkey->fifo, RINGBUFFERSIZE * sizeof(int), + spin_lock_init(&fujitsu_laptop->fifo_lock); + error = kfifo_alloc(&fujitsu_laptop->fifo, RINGBUFFERSIZE * sizeof(int), GFP_KERNEL); if (error) { pr_err("kfifo_alloc failed\n"); goto err_stop; } - fujitsu_hotkey->input = input = input_allocate_device(); + fujitsu_laptop->input = input = input_allocate_device(); if (!input) { error = -ENOMEM; goto err_free_fifo; } - snprintf(fujitsu_hotkey->phys, sizeof(fujitsu_hotkey->phys), + snprintf(fujitsu_laptop->phys, sizeof(fujitsu_laptop->phys), "%s/video/input0", acpi_device_hid(device)); input->name = acpi_device_name(device); - input->phys = fujitsu_hotkey->phys; + input->phys = fujitsu_laptop->phys; input->id.bustype = BUS_HOST; input->id.product = 0x06; input->dev.parent = &device->dev; set_bit(EV_KEY, input->evbit); - set_bit(fujitsu->keycode1, input->keybit); - set_bit(fujitsu->keycode2, input->keybit); - set_bit(fujitsu->keycode3, input->keybit); - set_bit(fujitsu->keycode4, input->keybit); - set_bit(fujitsu->keycode5, input->keybit); + set_bit(fujitsu_bl->keycode1, input->keybit); + set_bit(fujitsu_bl->keycode2, input->keybit); + set_bit(fujitsu_bl->keycode3, input->keybit); + set_bit(fujitsu_bl->keycode4, input->keybit); + set_bit(fujitsu_bl->keycode5, input->keybit); set_bit(KEY_TOUCHPAD_TOGGLE, input->keybit); set_bit(KEY_UNKNOWN, input->keybit); @@ -894,7 +895,7 @@ static int acpi_fujitsu_hotkey_add(struct acpi_device *device) if (error) goto err_free_input_dev; - error = acpi_bus_update_power(fujitsu_hotkey->acpi_handle, &state); + error = acpi_bus_update_power(fujitsu_laptop->acpi_handle, &state); if (error) { pr_err("Error reading power state\n"); goto err_unregister_input_dev; @@ -904,7 +905,7 @@ static int acpi_fujitsu_hotkey_add(struct acpi_device *device) acpi_device_name(device), acpi_device_bid(device), !device->power.state ? "on" : "off"); - fujitsu_hotkey->dev = device; + fujitsu_laptop->dev = device; if (acpi_has_method(device->handle, METHOD_NAME__INI)) { vdbg_printk(FUJLAPTOP_DBG_INFO, "Invoking _INI\n"); @@ -920,27 +921,27 @@ static int acpi_fujitsu_hotkey_add(struct acpi_device *device) ; /* No action, result is discarded */ vdbg_printk(FUJLAPTOP_DBG_INFO, "Discarded %i ringbuffer entries\n", i); - fujitsu_hotkey->rfkill_supported = - call_fext_func(FUNC_RFKILL, 0x0, 0x0, 0x0); + fujitsu_laptop->flags_supported = + call_fext_func(FUNC_FLAGS, 0x0, 0x0, 0x0); /* Make sure our bitmask of supported functions is cleared if the RFKILL function block is not implemented, like on the S7020. */ - if (fujitsu_hotkey->rfkill_supported == UNSUPPORTED_CMD) - fujitsu_hotkey->rfkill_supported = 0; + if (fujitsu_laptop->flags_supported == UNSUPPORTED_CMD) + fujitsu_laptop->flags_supported = 0; - if (fujitsu_hotkey->rfkill_supported) - fujitsu_hotkey->rfkill_state = - call_fext_func(FUNC_RFKILL, 0x4, 0x0, 0x0); + if (fujitsu_laptop->flags_supported) + fujitsu_laptop->flags_state = + call_fext_func(FUNC_FLAGS, 0x4, 0x0, 0x0); /* Suspect this is a keymap of the application panel, print it */ pr_info("BTNI: [0x%x]\n", call_fext_func(FUNC_BUTTONS, 0x0, 0x0, 0x0)); #if IS_ENABLED(CONFIG_LEDS_CLASS) if (call_fext_func(FUNC_LEDS, 0x0, 0x0, 0x0) & LOGOLAMP_POWERON) { - result = led_classdev_register(&fujitsu->pf_device->dev, + result = led_classdev_register(&fujitsu_bl->pf_device->dev, &logolamp_led); if (result == 0) { - fujitsu_hotkey->logolamp_registered = 1; + fujitsu_laptop->logolamp_registered = 1; } else { pr_err("Could not register LED handler for logo lamp, error %i\n", result); @@ -949,10 +950,10 @@ static int acpi_fujitsu_hotkey_add(struct acpi_device *device) if ((call_fext_func(FUNC_LEDS, 0x0, 0x0, 0x0) & KEYBOARD_LAMPS) && (call_fext_func(FUNC_BUTTONS, 0x0, 0x0, 0x0) == 0x0)) { - result = led_classdev_register(&fujitsu->pf_device->dev, + result = led_classdev_register(&fujitsu_bl->pf_device->dev, &kblamps_led); if (result == 0) { - fujitsu_hotkey->kblamps_registered = 1; + fujitsu_laptop->kblamps_registered = 1; } else { pr_err("Could not register LED handler for keyboard lamps, error %i\n", result); @@ -966,10 +967,10 @@ static int acpi_fujitsu_hotkey_add(struct acpi_device *device) * that an RF LED is present. */ if (call_fext_func(FUNC_BUTTONS, 0x0, 0x0, 0x0) & BIT(24)) { - result = led_classdev_register(&fujitsu->pf_device->dev, + result = led_classdev_register(&fujitsu_bl->pf_device->dev, &radio_led); if (result == 0) { - fujitsu_hotkey->radio_led_registered = 1; + fujitsu_laptop->radio_led_registered = 1; } else { pr_err("Could not register LED handler for radio LED, error %i\n", result); @@ -983,10 +984,10 @@ static int acpi_fujitsu_hotkey_add(struct acpi_device *device) */ if ((call_fext_func(FUNC_LEDS, 0x0, 0x0, 0x0) & BIT(14)) && (call_fext_func(FUNC_LEDS, 0x2, ECO_LED, 0x0) != UNSUPPORTED_CMD)) { - result = led_classdev_register(&fujitsu->pf_device->dev, + result = led_classdev_register(&fujitsu_bl->pf_device->dev, &eco_led); if (result == 0) { - fujitsu_hotkey->eco_led_registered = 1; + fujitsu_laptop->eco_led_registered = 1; } else { pr_err("Could not register LED handler for eco LED, error %i\n", result); @@ -1002,47 +1003,47 @@ err_unregister_input_dev: err_free_input_dev: input_free_device(input); err_free_fifo: - kfifo_free(&fujitsu_hotkey->fifo); + kfifo_free(&fujitsu_laptop->fifo); err_stop: return error; } -static int acpi_fujitsu_hotkey_remove(struct acpi_device *device) +static int acpi_fujitsu_laptop_remove(struct acpi_device *device) { - struct fujitsu_hotkey_t *fujitsu_hotkey = acpi_driver_data(device); - struct input_dev *input = fujitsu_hotkey->input; + struct fujitsu_laptop *fujitsu_laptop = acpi_driver_data(device); + struct input_dev *input = fujitsu_laptop->input; #if IS_ENABLED(CONFIG_LEDS_CLASS) - if (fujitsu_hotkey->logolamp_registered) + if (fujitsu_laptop->logolamp_registered) led_classdev_unregister(&logolamp_led); - if (fujitsu_hotkey->kblamps_registered) + if (fujitsu_laptop->kblamps_registered) led_classdev_unregister(&kblamps_led); - if (fujitsu_hotkey->radio_led_registered) + if (fujitsu_laptop->radio_led_registered) led_classdev_unregister(&radio_led); - if (fujitsu_hotkey->eco_led_registered) + if (fujitsu_laptop->eco_led_registered) led_classdev_unregister(&eco_led); #endif input_unregister_device(input); - kfifo_free(&fujitsu_hotkey->fifo); + kfifo_free(&fujitsu_laptop->fifo); - fujitsu_hotkey->acpi_handle = NULL; + fujitsu_laptop->acpi_handle = NULL; return 0; } -static void acpi_fujitsu_hotkey_press(int keycode) +static void acpi_fujitsu_laptop_press(int keycode) { - struct input_dev *input = fujitsu_hotkey->input; + struct input_dev *input = fujitsu_laptop->input; int status; - status = kfifo_in_locked(&fujitsu_hotkey->fifo, + status = kfifo_in_locked(&fujitsu_laptop->fifo, (unsigned char *)&keycode, sizeof(keycode), - &fujitsu_hotkey->fifo_lock); + &fujitsu_laptop->fifo_lock); if (status != sizeof(keycode)) { vdbg_printk(FUJLAPTOP_DBG_WARN, "Could not push keycode [0x%x]\n", keycode); @@ -1054,16 +1055,16 @@ static void acpi_fujitsu_hotkey_press(int keycode) "Push keycode into ringbuffer [%d]\n", keycode); } -static void acpi_fujitsu_hotkey_release(void) +static void acpi_fujitsu_laptop_release(void) { - struct input_dev *input = fujitsu_hotkey->input; + struct input_dev *input = fujitsu_laptop->input; int keycode, status; while (true) { - status = kfifo_out_locked(&fujitsu_hotkey->fifo, + status = kfifo_out_locked(&fujitsu_laptop->fifo, (unsigned char *)&keycode, sizeof(keycode), - &fujitsu_hotkey->fifo_lock); + &fujitsu_laptop->fifo_lock); if (status != sizeof(keycode)) return; input_report_key(input, keycode, 0); @@ -1073,14 +1074,14 @@ static void acpi_fujitsu_hotkey_release(void) } } -static void acpi_fujitsu_hotkey_notify(struct acpi_device *device, u32 event) +static void acpi_fujitsu_laptop_notify(struct acpi_device *device, u32 event) { struct input_dev *input; int keycode; unsigned int irb = 1; int i; - input = fujitsu_hotkey->input; + input = fujitsu_laptop->input; if (event != ACPI_FUJITSU_NOTIFY_CODE1) { keycode = KEY_UNKNOWN; @@ -1093,9 +1094,9 @@ static void acpi_fujitsu_hotkey_notify(struct acpi_device *device, u32 event) return; } - if (fujitsu_hotkey->rfkill_supported) - fujitsu_hotkey->rfkill_state = - call_fext_func(FUNC_RFKILL, 0x4, 0x0, 0x0); + if (fujitsu_laptop->flags_supported) + fujitsu_laptop->flags_state = + call_fext_func(FUNC_FLAGS, 0x4, 0x0, 0x0); i = 0; while ((irb = @@ -1103,19 +1104,19 @@ static void acpi_fujitsu_hotkey_notify(struct acpi_device *device, u32 event) && (i++) < MAX_HOTKEY_RINGBUFFER_SIZE) { switch (irb & 0x4ff) { case KEY1_CODE: - keycode = fujitsu->keycode1; + keycode = fujitsu_bl->keycode1; break; case KEY2_CODE: - keycode = fujitsu->keycode2; + keycode = fujitsu_bl->keycode2; break; case KEY3_CODE: - keycode = fujitsu->keycode3; + keycode = fujitsu_bl->keycode3; break; case KEY4_CODE: - keycode = fujitsu->keycode4; + keycode = fujitsu_bl->keycode4; break; case KEY5_CODE: - keycode = fujitsu->keycode5; + keycode = fujitsu_bl->keycode5; break; case 0: keycode = 0; @@ -1128,17 +1129,17 @@ static void acpi_fujitsu_hotkey_notify(struct acpi_device *device, u32 event) } if (keycode > 0) - acpi_fujitsu_hotkey_press(keycode); + acpi_fujitsu_laptop_press(keycode); else if (keycode == 0) - acpi_fujitsu_hotkey_release(); + acpi_fujitsu_laptop_release(); } /* On some models (first seen on the Skylake-based Lifebook * E736/E746/E756), the touchpad toggle hotkey (Fn+F4) is - * handled in software; its state is queried using FUNC_RFKILL + * handled in software; its state is queried using FUNC_FLAGS */ - if ((fujitsu_hotkey->rfkill_supported & BIT(26)) && - (call_fext_func(FUNC_RFKILL, 0x1, 0x0, 0x0) & BIT(26))) { + if ((fujitsu_laptop->flags_supported & BIT(26)) && + (call_fext_func(FUNC_FLAGS, 0x1, 0x0, 0x0) & BIT(26))) { keycode = KEY_TOUCHPAD_TOGGLE; input_report_key(input, keycode, 1); input_sync(input); @@ -1150,83 +1151,81 @@ static void acpi_fujitsu_hotkey_notify(struct acpi_device *device, u32 event) /* Initialization */ -static const struct acpi_device_id fujitsu_device_ids[] = { - {ACPI_FUJITSU_HID, 0}, +static const struct acpi_device_id fujitsu_bl_device_ids[] = { + {ACPI_FUJITSU_BL_HID, 0}, {"", 0}, }; -static struct acpi_driver acpi_fujitsu_driver = { - .name = ACPI_FUJITSU_DRIVER_NAME, +static struct acpi_driver acpi_fujitsu_bl_driver = { + .name = ACPI_FUJITSU_BL_DRIVER_NAME, .class = ACPI_FUJITSU_CLASS, - .ids = fujitsu_device_ids, + .ids = fujitsu_bl_device_ids, .ops = { - .add = acpi_fujitsu_add, - .remove = acpi_fujitsu_remove, - .notify = acpi_fujitsu_notify, + .add = acpi_fujitsu_bl_add, + .remove = acpi_fujitsu_bl_remove, + .notify = acpi_fujitsu_bl_notify, }, }; -static const struct acpi_device_id fujitsu_hotkey_device_ids[] = { - {ACPI_FUJITSU_HOTKEY_HID, 0}, +static const struct acpi_device_id fujitsu_laptop_device_ids[] = { + {ACPI_FUJITSU_LAPTOP_HID, 0}, {"", 0}, }; -static struct acpi_driver acpi_fujitsu_hotkey_driver = { - .name = ACPI_FUJITSU_HOTKEY_DRIVER_NAME, +static struct acpi_driver acpi_fujitsu_laptop_driver = { + .name = ACPI_FUJITSU_LAPTOP_DRIVER_NAME, .class = ACPI_FUJITSU_CLASS, - .ids = fujitsu_hotkey_device_ids, + .ids = fujitsu_laptop_device_ids, .ops = { - .add = acpi_fujitsu_hotkey_add, - .remove = acpi_fujitsu_hotkey_remove, - .notify = acpi_fujitsu_hotkey_notify, + .add = acpi_fujitsu_laptop_add, + .remove = acpi_fujitsu_laptop_remove, + .notify = acpi_fujitsu_laptop_notify, }, }; static const struct acpi_device_id fujitsu_ids[] __used = { - {ACPI_FUJITSU_HID, 0}, - {ACPI_FUJITSU_HOTKEY_HID, 0}, + {ACPI_FUJITSU_BL_HID, 0}, + {ACPI_FUJITSU_LAPTOP_HID, 0}, {"", 0} }; MODULE_DEVICE_TABLE(acpi, fujitsu_ids); static int __init fujitsu_init(void) { - int ret, result, max_brightness; + int ret, max_brightness; if (acpi_disabled) return -ENODEV; - fujitsu = kzalloc(sizeof(struct fujitsu_t), GFP_KERNEL); - if (!fujitsu) + fujitsu_bl = kzalloc(sizeof(struct fujitsu_bl), GFP_KERNEL); + if (!fujitsu_bl) return -ENOMEM; - fujitsu->keycode1 = KEY_PROG1; - fujitsu->keycode2 = KEY_PROG2; - fujitsu->keycode3 = KEY_PROG3; - fujitsu->keycode4 = KEY_PROG4; - fujitsu->keycode5 = KEY_RFKILL; + fujitsu_bl->keycode1 = KEY_PROG1; + fujitsu_bl->keycode2 = KEY_PROG2; + fujitsu_bl->keycode3 = KEY_PROG3; + fujitsu_bl->keycode4 = KEY_PROG4; + fujitsu_bl->keycode5 = KEY_RFKILL; dmi_check_system(fujitsu_dmi_table); - result = acpi_bus_register_driver(&acpi_fujitsu_driver); - if (result < 0) { - ret = -ENODEV; + ret = acpi_bus_register_driver(&acpi_fujitsu_bl_driver); + if (ret) goto fail_acpi; - } /* Register platform stuff */ - fujitsu->pf_device = platform_device_alloc("fujitsu-laptop", -1); - if (!fujitsu->pf_device) { + fujitsu_bl->pf_device = platform_device_alloc("fujitsu-laptop", -1); + if (!fujitsu_bl->pf_device) { ret = -ENOMEM; goto fail_platform_driver; } - ret = platform_device_add(fujitsu->pf_device); + ret = platform_device_add(fujitsu_bl->pf_device); if (ret) goto fail_platform_device1; ret = - sysfs_create_group(&fujitsu->pf_device->dev.kobj, - &fujitsupf_attribute_group); + sysfs_create_group(&fujitsu_bl->pf_device->dev.kobj, + &fujitsu_pf_attribute_group); if (ret) goto fail_platform_device2; @@ -1236,90 +1235,88 @@ static int __init fujitsu_init(void) struct backlight_properties props; memset(&props, 0, sizeof(struct backlight_properties)); - max_brightness = fujitsu->max_brightness; + max_brightness = fujitsu_bl->max_brightness; props.type = BACKLIGHT_PLATFORM; props.max_brightness = max_brightness - 1; - fujitsu->bl_device = backlight_device_register("fujitsu-laptop", - NULL, NULL, - &fujitsubl_ops, - &props); - if (IS_ERR(fujitsu->bl_device)) { - ret = PTR_ERR(fujitsu->bl_device); - fujitsu->bl_device = NULL; + fujitsu_bl->bl_device = backlight_device_register("fujitsu-laptop", + NULL, NULL, + &fujitsu_bl_ops, + &props); + if (IS_ERR(fujitsu_bl->bl_device)) { + ret = PTR_ERR(fujitsu_bl->bl_device); + fujitsu_bl->bl_device = NULL; goto fail_sysfs_group; } - fujitsu->bl_device->props.brightness = fujitsu->brightness_level; + fujitsu_bl->bl_device->props.brightness = fujitsu_bl->brightness_level; } - ret = platform_driver_register(&fujitsupf_driver); + ret = platform_driver_register(&fujitsu_pf_driver); if (ret) goto fail_backlight; - /* Register hotkey driver */ + /* Register laptop driver */ - fujitsu_hotkey = kzalloc(sizeof(struct fujitsu_hotkey_t), GFP_KERNEL); - if (!fujitsu_hotkey) { + fujitsu_laptop = kzalloc(sizeof(struct fujitsu_laptop), GFP_KERNEL); + if (!fujitsu_laptop) { ret = -ENOMEM; - goto fail_hotkey; + goto fail_laptop; } - result = acpi_bus_register_driver(&acpi_fujitsu_hotkey_driver); - if (result < 0) { - ret = -ENODEV; - goto fail_hotkey1; - } + ret = acpi_bus_register_driver(&acpi_fujitsu_laptop_driver); + if (ret) + goto fail_laptop1; /* Sync backlight power status (needs FUJ02E3 device, hence deferred) */ if (acpi_video_get_backlight_type() == acpi_backlight_vendor) { if (call_fext_func(FUNC_BACKLIGHT, 0x2, 0x4, 0x0) == 3) - fujitsu->bl_device->props.power = FB_BLANK_POWERDOWN; + fujitsu_bl->bl_device->props.power = FB_BLANK_POWERDOWN; else - fujitsu->bl_device->props.power = FB_BLANK_UNBLANK; + fujitsu_bl->bl_device->props.power = FB_BLANK_UNBLANK; } pr_info("driver " FUJITSU_DRIVER_VERSION " successfully loaded\n"); return 0; -fail_hotkey1: - kfree(fujitsu_hotkey); -fail_hotkey: - platform_driver_unregister(&fujitsupf_driver); +fail_laptop1: + kfree(fujitsu_laptop); +fail_laptop: + platform_driver_unregister(&fujitsu_pf_driver); fail_backlight: - backlight_device_unregister(fujitsu->bl_device); + backlight_device_unregister(fujitsu_bl->bl_device); fail_sysfs_group: - sysfs_remove_group(&fujitsu->pf_device->dev.kobj, - &fujitsupf_attribute_group); + sysfs_remove_group(&fujitsu_bl->pf_device->dev.kobj, + &fujitsu_pf_attribute_group); fail_platform_device2: - platform_device_del(fujitsu->pf_device); + platform_device_del(fujitsu_bl->pf_device); fail_platform_device1: - platform_device_put(fujitsu->pf_device); + platform_device_put(fujitsu_bl->pf_device); fail_platform_driver: - acpi_bus_unregister_driver(&acpi_fujitsu_driver); + acpi_bus_unregister_driver(&acpi_fujitsu_bl_driver); fail_acpi: - kfree(fujitsu); + kfree(fujitsu_bl); return ret; } static void __exit fujitsu_cleanup(void) { - acpi_bus_unregister_driver(&acpi_fujitsu_hotkey_driver); + acpi_bus_unregister_driver(&acpi_fujitsu_laptop_driver); - kfree(fujitsu_hotkey); + kfree(fujitsu_laptop); - platform_driver_unregister(&fujitsupf_driver); + platform_driver_unregister(&fujitsu_pf_driver); - backlight_device_unregister(fujitsu->bl_device); + backlight_device_unregister(fujitsu_bl->bl_device); - sysfs_remove_group(&fujitsu->pf_device->dev.kobj, - &fujitsupf_attribute_group); + sysfs_remove_group(&fujitsu_bl->pf_device->dev.kobj, + &fujitsu_pf_attribute_group); - platform_device_unregister(fujitsu->pf_device); + platform_device_unregister(fujitsu_bl->pf_device); - acpi_bus_unregister_driver(&acpi_fujitsu_driver); + acpi_bus_unregister_driver(&acpi_fujitsu_bl_driver); - kfree(fujitsu); + kfree(fujitsu_bl); pr_info("driver unloaded\n"); } @@ -1341,7 +1338,3 @@ MODULE_AUTHOR("Jonathan Woithe, Peter Gruber, Tony Vroon"); MODULE_DESCRIPTION("Fujitsu laptop extras support"); MODULE_VERSION(FUJITSU_DRIVER_VERSION); MODULE_LICENSE("GPL"); - -MODULE_ALIAS("dmi:*:svnFUJITSUSIEMENS:*:pvr:rvnFUJITSU:rnFJNB1D3:*:cvrS6410:*"); -MODULE_ALIAS("dmi:*:svnFUJITSUSIEMENS:*:pvr:rvnFUJITSU:rnFJNB1E6:*:cvrS6420:*"); -MODULE_ALIAS("dmi:*:svnFUJITSU:*:pvr:rvnFUJITSU:rnFJNB19C:*:cvrS7020:*"); diff --git a/drivers/scsi/Kconfig b/drivers/scsi/Kconfig index 230043c1c90f..4bf55b5d78be 100644 --- a/drivers/scsi/Kconfig +++ b/drivers/scsi/Kconfig @@ -1241,19 +1241,32 @@ config SCSI_LPFC tristate "Emulex LightPulse Fibre Channel Support" depends on PCI && SCSI depends on SCSI_FC_ATTRS - depends on NVME_FC && NVME_TARGET_FC select CRC_T10DIF - help + ---help--- This lpfc driver supports the Emulex LightPulse Family of Fibre Channel PCI host adapters. config SCSI_LPFC_DEBUG_FS bool "Emulex LightPulse Fibre Channel debugfs Support" depends on SCSI_LPFC && DEBUG_FS - help + ---help--- This makes debugging information from the lpfc driver available via the debugfs filesystem. +config LPFC_NVME_INITIATOR + bool "Emulex LightPulse Fibre Channel NVME Initiator Support" + depends on SCSI_LPFC && NVME_FC + ---help--- + This enables NVME Initiator support in the Emulex lpfc driver. + +config LPFC_NVME_TARGET + bool "Emulex LightPulse Fibre Channel NVME Initiator Support" + depends on SCSI_LPFC && NVME_TARGET_FC + ---help--- + This enables NVME Target support in the Emulex lpfc driver. + Target enablement must still be enabled on a per adapter + basis by module parameters. + config SCSI_SIM710 tristate "Simple 53c710 SCSI support (Compaq, NCR machines)" depends on (EISA || MCA) && SCSI diff --git a/drivers/scsi/aacraid/src.c b/drivers/scsi/aacraid/src.c index 2e5338dec621..7b0410e0f569 100644 --- a/drivers/scsi/aacraid/src.c +++ b/drivers/scsi/aacraid/src.c @@ -468,7 +468,7 @@ err_out: return -1; err_blink: - return (status > 16) & 0xFF; + return (status >> 16) & 0xFF; } static inline u32 aac_get_vector(struct aac_dev *dev) diff --git a/drivers/scsi/aic7xxx/aic79xx_core.c b/drivers/scsi/aic7xxx/aic79xx_core.c index 109e2c99e6c1..95d8f25cbcca 100644 --- a/drivers/scsi/aic7xxx/aic79xx_core.c +++ b/drivers/scsi/aic7xxx/aic79xx_core.c @@ -6278,7 +6278,7 @@ ahd_reset(struct ahd_softc *ahd, int reinit) * does not disable its parity logic prior to * the start of the reset. This may cause a * parity error to be detected and thus a - * spurious SERR or PERR assertion. Disble + * spurious SERR or PERR assertion. Disable * PERR and SERR responses during the CHIPRST. */ mod_cmd = cmd & ~(PCIM_CMD_PERRESPEN|PCIM_CMD_SERRESPEN); diff --git a/drivers/scsi/libiscsi.c b/drivers/scsi/libiscsi.c index 07c08ce68d70..894b1e3ebd56 100644 --- a/drivers/scsi/libiscsi.c +++ b/drivers/scsi/libiscsi.c @@ -561,8 +561,12 @@ static void iscsi_complete_task(struct iscsi_task *task, int state) WARN_ON_ONCE(task->state == ISCSI_TASK_FREE); task->state = state; - if (!list_empty(&task->running)) + spin_lock_bh(&conn->taskqueuelock); + if (!list_empty(&task->running)) { + pr_debug_once("%s while task on list", __func__); list_del_init(&task->running); + } + spin_unlock_bh(&conn->taskqueuelock); if (conn->task == task) conn->task = NULL; @@ -784,7 +788,9 @@ __iscsi_conn_send_pdu(struct iscsi_conn *conn, struct iscsi_hdr *hdr, if (session->tt->xmit_task(task)) goto free_task; } else { + spin_lock_bh(&conn->taskqueuelock); list_add_tail(&task->running, &conn->mgmtqueue); + spin_unlock_bh(&conn->taskqueuelock); iscsi_conn_queue_work(conn); } @@ -1475,8 +1481,10 @@ void iscsi_requeue_task(struct iscsi_task *task) * this may be on the requeue list already if the xmit_task callout * is handling the r2ts while we are adding new ones */ + spin_lock_bh(&conn->taskqueuelock); if (list_empty(&task->running)) list_add_tail(&task->running, &conn->requeue); + spin_unlock_bh(&conn->taskqueuelock); iscsi_conn_queue_work(conn); } EXPORT_SYMBOL_GPL(iscsi_requeue_task); @@ -1513,22 +1521,26 @@ static int iscsi_data_xmit(struct iscsi_conn *conn) * only have one nop-out as a ping from us and targets should not * overflow us with nop-ins */ + spin_lock_bh(&conn->taskqueuelock); check_mgmt: while (!list_empty(&conn->mgmtqueue)) { conn->task = list_entry(conn->mgmtqueue.next, struct iscsi_task, running); list_del_init(&conn->task->running); + spin_unlock_bh(&conn->taskqueuelock); if (iscsi_prep_mgmt_task(conn, conn->task)) { /* regular RX path uses back_lock */ spin_lock_bh(&conn->session->back_lock); __iscsi_put_task(conn->task); spin_unlock_bh(&conn->session->back_lock); conn->task = NULL; + spin_lock_bh(&conn->taskqueuelock); continue; } rc = iscsi_xmit_task(conn); if (rc) goto done; + spin_lock_bh(&conn->taskqueuelock); } /* process pending command queue */ @@ -1536,19 +1548,24 @@ check_mgmt: conn->task = list_entry(conn->cmdqueue.next, struct iscsi_task, running); list_del_init(&conn->task->running); + spin_unlock_bh(&conn->taskqueuelock); if (conn->session->state == ISCSI_STATE_LOGGING_OUT) { fail_scsi_task(conn->task, DID_IMM_RETRY); + spin_lock_bh(&conn->taskqueuelock); continue; } rc = iscsi_prep_scsi_cmd_pdu(conn->task); if (rc) { if (rc == -ENOMEM || rc == -EACCES) { + spin_lock_bh(&conn->taskqueuelock); list_add_tail(&conn->task->running, &conn->cmdqueue); conn->task = NULL; + spin_unlock_bh(&conn->taskqueuelock); goto done; } else fail_scsi_task(conn->task, DID_ABORT); + spin_lock_bh(&conn->taskqueuelock); continue; } rc = iscsi_xmit_task(conn); @@ -1559,6 +1576,7 @@ check_mgmt: * we need to check the mgmt queue for nops that need to * be sent to aviod starvation */ + spin_lock_bh(&conn->taskqueuelock); if (!list_empty(&conn->mgmtqueue)) goto check_mgmt; } @@ -1578,12 +1596,15 @@ check_mgmt: conn->task = task; list_del_init(&conn->task->running); conn->task->state = ISCSI_TASK_RUNNING; + spin_unlock_bh(&conn->taskqueuelock); rc = iscsi_xmit_task(conn); if (rc) goto done; + spin_lock_bh(&conn->taskqueuelock); if (!list_empty(&conn->mgmtqueue)) goto check_mgmt; } + spin_unlock_bh(&conn->taskqueuelock); spin_unlock_bh(&conn->session->frwd_lock); return -ENODATA; @@ -1739,7 +1760,9 @@ int iscsi_queuecommand(struct Scsi_Host *host, struct scsi_cmnd *sc) goto prepd_reject; } } else { + spin_lock_bh(&conn->taskqueuelock); list_add_tail(&task->running, &conn->cmdqueue); + spin_unlock_bh(&conn->taskqueuelock); iscsi_conn_queue_work(conn); } @@ -2897,6 +2920,7 @@ iscsi_conn_setup(struct iscsi_cls_session *cls_session, int dd_size, INIT_LIST_HEAD(&conn->mgmtqueue); INIT_LIST_HEAD(&conn->cmdqueue); INIT_LIST_HEAD(&conn->requeue); + spin_lock_init(&conn->taskqueuelock); INIT_WORK(&conn->xmitwork, iscsi_xmitworker); /* allocate login_task used for the login/text sequences */ diff --git a/drivers/scsi/lpfc/lpfc.h b/drivers/scsi/lpfc/lpfc.h index 0bba2e30b4f0..257bbdd0f0b8 100644 --- a/drivers/scsi/lpfc/lpfc.h +++ b/drivers/scsi/lpfc/lpfc.h @@ -99,12 +99,13 @@ struct lpfc_sli2_slim; #define FC_MAX_ADPTMSG 64 #define MAX_HBAEVT 32 +#define MAX_HBAS_NO_RESET 16 /* Number of MSI-X vectors the driver uses */ #define LPFC_MSIX_VECTORS 2 /* lpfc wait event data ready flag */ -#define LPFC_DATA_READY (1<<0) +#define LPFC_DATA_READY 0 /* bit 0 */ /* queue dump line buffer size */ #define LPFC_LBUF_SZ 128 @@ -692,6 +693,7 @@ struct lpfc_hba { * capability */ #define HBA_NVME_IOQ_FLUSH 0x80000 /* NVME IO queues flushed. */ +#define NVME_XRI_ABORT_EVENT 0x100000 uint32_t fcp_ring_in_use; /* When polling test if intr-hndlr active*/ struct lpfc_dmabuf slim2p; diff --git a/drivers/scsi/lpfc/lpfc_attr.c b/drivers/scsi/lpfc/lpfc_attr.c index 5c783ef7f260..5c3be3e6f5e2 100644 --- a/drivers/scsi/lpfc/lpfc_attr.c +++ b/drivers/scsi/lpfc/lpfc_attr.c @@ -3010,6 +3010,12 @@ MODULE_PARM_DESC(lpfc_poll, "FCP ring polling mode control:" static DEVICE_ATTR(lpfc_poll, S_IRUGO | S_IWUSR, lpfc_poll_show, lpfc_poll_store); +int lpfc_no_hba_reset_cnt; +unsigned long lpfc_no_hba_reset[MAX_HBAS_NO_RESET] = { + 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0}; +module_param_array(lpfc_no_hba_reset, ulong, &lpfc_no_hba_reset_cnt, 0444); +MODULE_PARM_DESC(lpfc_no_hba_reset, "WWPN of HBAs that should not be reset"); + LPFC_ATTR(sli_mode, 0, 0, 3, "SLI mode selector:" " 0 - auto (SLI-3 if supported)," @@ -4451,7 +4457,8 @@ lpfc_fcp_imax_store(struct device *dev, struct device_attribute *attr, return -EINVAL; phba->cfg_fcp_imax = (uint32_t)val; - for (i = 0; i < phba->io_channel_irqs; i++) + + for (i = 0; i < phba->io_channel_irqs; i += LPFC_MAX_EQ_DELAY_EQID_CNT) lpfc_modify_hba_eq_delay(phba, i); return strlen(buf); diff --git a/drivers/scsi/lpfc/lpfc_crtn.h b/drivers/scsi/lpfc/lpfc_crtn.h index 843dd73004da..54e6ac42fbcd 100644 --- a/drivers/scsi/lpfc/lpfc_crtn.h +++ b/drivers/scsi/lpfc/lpfc_crtn.h @@ -384,7 +384,7 @@ void lpfc_free_sysfs_attr(struct lpfc_vport *); extern struct device_attribute *lpfc_hba_attrs[]; extern struct device_attribute *lpfc_vport_attrs[]; extern struct scsi_host_template lpfc_template; -extern struct scsi_host_template lpfc_template_s3; +extern struct scsi_host_template lpfc_template_no_hr; extern struct scsi_host_template lpfc_template_nvme; extern struct scsi_host_template lpfc_vport_template; extern struct fc_function_template lpfc_transport_functions; @@ -554,3 +554,5 @@ void lpfc_nvme_abort_fcreq_cmpl(struct lpfc_hba *phba, struct lpfc_wcqe_complete *abts_cmpl); extern int lpfc_enable_nvmet_cnt; extern unsigned long long lpfc_enable_nvmet[]; +extern int lpfc_no_hba_reset_cnt; +extern unsigned long lpfc_no_hba_reset[]; diff --git a/drivers/scsi/lpfc/lpfc_ct.c b/drivers/scsi/lpfc/lpfc_ct.c index c22bb3f887e1..d3e9af983015 100644 --- a/drivers/scsi/lpfc/lpfc_ct.c +++ b/drivers/scsi/lpfc/lpfc_ct.c @@ -939,8 +939,8 @@ lpfc_cmpl_ct_cmd_gft_id(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb, "FC4 x%08x, Data: x%08x x%08x\n", ndlp, did, ndlp->nlp_fc4_type, FC_TYPE_FCP, FC_TYPE_NVME); + ndlp->nlp_prev_state = NLP_STE_REG_LOGIN_ISSUE; } - ndlp->nlp_prev_state = NLP_STE_REG_LOGIN_ISSUE; lpfc_nlp_set_state(vport, ndlp, NLP_STE_PRLI_ISSUE); lpfc_issue_els_prli(vport, ndlp, 0); } else diff --git a/drivers/scsi/lpfc/lpfc_debugfs.c b/drivers/scsi/lpfc/lpfc_debugfs.c index 9f4798e9d938..913eed822cb8 100644 --- a/drivers/scsi/lpfc/lpfc_debugfs.c +++ b/drivers/scsi/lpfc/lpfc_debugfs.c @@ -3653,17 +3653,6 @@ lpfc_idiag_queacc_write(struct file *file, const char __user *buf, idiag.ptr_private = phba->sli4_hba.nvmels_cq; goto pass_check; } - /* NVME LS complete queue */ - if (phba->sli4_hba.nvmels_cq && - phba->sli4_hba.nvmels_cq->queue_id == queid) { - /* Sanity check */ - rc = lpfc_idiag_que_param_check( - phba->sli4_hba.nvmels_cq, index, count); - if (rc) - goto error_out; - idiag.ptr_private = phba->sli4_hba.nvmels_cq; - goto pass_check; - } /* FCP complete queue */ if (phba->sli4_hba.fcp_cq) { for (qidx = 0; qidx < phba->cfg_fcp_io_channel; @@ -3738,17 +3727,6 @@ lpfc_idiag_queacc_write(struct file *file, const char __user *buf, idiag.ptr_private = phba->sli4_hba.nvmels_wq; goto pass_check; } - /* NVME LS work queue */ - if (phba->sli4_hba.nvmels_wq && - phba->sli4_hba.nvmels_wq->queue_id == queid) { - /* Sanity check */ - rc = lpfc_idiag_que_param_check( - phba->sli4_hba.nvmels_wq, index, count); - if (rc) - goto error_out; - idiag.ptr_private = phba->sli4_hba.nvmels_wq; - goto pass_check; - } /* FCP work queue */ if (phba->sli4_hba.fcp_wq) { for (qidx = 0; qidx < phba->cfg_fcp_io_channel; diff --git a/drivers/scsi/lpfc/lpfc_els.c b/drivers/scsi/lpfc/lpfc_els.c index 2d26440e6f2f..d9c61d030034 100644 --- a/drivers/scsi/lpfc/lpfc_els.c +++ b/drivers/scsi/lpfc/lpfc_els.c @@ -5177,15 +5177,15 @@ lpfc_rdp_res_speed(struct fc_rdp_port_speed_desc *desc, struct lpfc_hba *phba) static uint32_t lpfc_rdp_res_diag_port_names(struct fc_rdp_port_name_desc *desc, - struct lpfc_hba *phba) + struct lpfc_vport *vport) { desc->tag = cpu_to_be32(RDP_PORT_NAMES_DESC_TAG); - memcpy(desc->port_names.wwnn, phba->wwnn, + memcpy(desc->port_names.wwnn, &vport->fc_nodename, sizeof(desc->port_names.wwnn)); - memcpy(desc->port_names.wwpn, phba->wwpn, + memcpy(desc->port_names.wwpn, &vport->fc_portname, sizeof(desc->port_names.wwpn)); desc->length = cpu_to_be32(sizeof(desc->port_names)); @@ -5279,7 +5279,7 @@ lpfc_els_rdp_cmpl(struct lpfc_hba *phba, struct lpfc_rdp_context *rdp_context, len += lpfc_rdp_res_link_error((struct fc_rdp_link_error_status_desc *) (len + pcmd), &rdp_context->link_stat); len += lpfc_rdp_res_diag_port_names((struct fc_rdp_port_name_desc *) - (len + pcmd), phba); + (len + pcmd), vport); len += lpfc_rdp_res_attach_port_names((struct fc_rdp_port_name_desc *) (len + pcmd), vport, ndlp); len += lpfc_rdp_res_fec_desc((struct fc_fec_rdp_desc *)(len + pcmd), @@ -8371,11 +8371,17 @@ lpfc_cmpl_reg_new_vport(struct lpfc_hba *phba, LPFC_MBOXQ_t *pmb) spin_lock_irq(shost->host_lock); vport->fc_flag |= FC_VPORT_NEEDS_REG_VPI; spin_unlock_irq(shost->host_lock); - if (vport->port_type == LPFC_PHYSICAL_PORT - && !(vport->fc_flag & FC_LOGO_RCVD_DID_CHNG)) - lpfc_issue_init_vfi(vport); - else + if (mb->mbxStatus == MBX_NOT_FINISHED) + break; + if ((vport->port_type == LPFC_PHYSICAL_PORT) && + !(vport->fc_flag & FC_LOGO_RCVD_DID_CHNG)) { + if (phba->sli_rev == LPFC_SLI_REV4) + lpfc_issue_init_vfi(vport); + else + lpfc_initial_flogi(vport); + } else { lpfc_initial_fdisc(vport); + } break; } } else { diff --git a/drivers/scsi/lpfc/lpfc_hbadisc.c b/drivers/scsi/lpfc/lpfc_hbadisc.c index 194a14d5f8a9..180b072beef6 100644 --- a/drivers/scsi/lpfc/lpfc_hbadisc.c +++ b/drivers/scsi/lpfc/lpfc_hbadisc.c @@ -313,8 +313,7 @@ lpfc_dev_loss_tmo_handler(struct lpfc_nodelist *ndlp) ndlp->nlp_state, ndlp->nlp_rpi); } - if (!(vport->load_flag & FC_UNLOADING) && - !(ndlp->nlp_flag & NLP_DELAY_TMO) && + if (!(ndlp->nlp_flag & NLP_DELAY_TMO) && !(ndlp->nlp_flag & NLP_NPR_2B_DISC) && (ndlp->nlp_state != NLP_STE_UNMAPPED_NODE) && (ndlp->nlp_state != NLP_STE_REG_LOGIN_ISSUE) && @@ -641,6 +640,8 @@ lpfc_work_done(struct lpfc_hba *phba) lpfc_handle_rrq_active(phba); if (phba->hba_flag & FCP_XRI_ABORT_EVENT) lpfc_sli4_fcp_xri_abort_event_proc(phba); + if (phba->hba_flag & NVME_XRI_ABORT_EVENT) + lpfc_sli4_nvme_xri_abort_event_proc(phba); if (phba->hba_flag & ELS_XRI_ABORT_EVENT) lpfc_sli4_els_xri_abort_event_proc(phba); if (phba->hba_flag & ASYNC_EVENT) @@ -2173,7 +2174,7 @@ lpfc_mbx_cmpl_fcf_scan_read_fcf_rec(struct lpfc_hba *phba, LPFC_MBOXQ_t *mboxq) uint32_t boot_flag, addr_mode; uint16_t fcf_index, next_fcf_index; struct lpfc_fcf_rec *fcf_rec = NULL; - uint16_t vlan_id; + uint16_t vlan_id = LPFC_FCOE_NULL_VID; bool select_new_fcf; int rc; @@ -4020,9 +4021,11 @@ lpfc_register_remote_port(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp) rdata = rport->dd_data; /* break the link before dropping the ref */ ndlp->rport = NULL; - if (rdata && rdata->pnode == ndlp) - lpfc_nlp_put(ndlp); - rdata->pnode = NULL; + if (rdata) { + if (rdata->pnode == ndlp) + lpfc_nlp_put(ndlp); + rdata->pnode = NULL; + } /* drop reference for earlier registeration */ put_device(&rport->dev); } @@ -4344,9 +4347,8 @@ lpfc_initialize_node(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp, { INIT_LIST_HEAD(&ndlp->els_retry_evt.evt_listp); INIT_LIST_HEAD(&ndlp->dev_loss_evt.evt_listp); - init_timer(&ndlp->nlp_delayfunc); - ndlp->nlp_delayfunc.function = lpfc_els_retry_delay; - ndlp->nlp_delayfunc.data = (unsigned long)ndlp; + setup_timer(&ndlp->nlp_delayfunc, lpfc_els_retry_delay, + (unsigned long)ndlp); ndlp->nlp_DID = did; ndlp->vport = vport; ndlp->phba = vport->phba; @@ -4606,9 +4608,9 @@ lpfc_sli4_dequeue_nport_iocbs(struct lpfc_hba *phba, pring = qp->pring; if (!pring) continue; - spin_lock_irq(&pring->ring_lock); + spin_lock(&pring->ring_lock); __lpfc_dequeue_nport_iocbs(phba, ndlp, pring, dequeue_list); - spin_unlock_irq(&pring->ring_lock); + spin_unlock(&pring->ring_lock); } spin_unlock_irq(&phba->hbalock); } diff --git a/drivers/scsi/lpfc/lpfc_hw4.h b/drivers/scsi/lpfc/lpfc_hw4.h index cfdb068a3bfc..15277705cb6b 100644 --- a/drivers/scsi/lpfc/lpfc_hw4.h +++ b/drivers/scsi/lpfc/lpfc_hw4.h @@ -1001,7 +1001,7 @@ struct eq_delay_info { uint32_t phase; uint32_t delay_multi; }; -#define LPFC_MAX_EQ_DELAY 8 +#define LPFC_MAX_EQ_DELAY_EQID_CNT 8 struct sgl_page_pairs { uint32_t sgl_pg0_addr_lo; @@ -1070,7 +1070,7 @@ struct lpfc_mbx_modify_eq_delay { union { struct { uint32_t num_eq; - struct eq_delay_info eq[LPFC_MAX_EQ_DELAY]; + struct eq_delay_info eq[LPFC_MAX_EQ_DELAY_EQID_CNT]; } request; struct { uint32_t word0; diff --git a/drivers/scsi/lpfc/lpfc_init.c b/drivers/scsi/lpfc/lpfc_init.c index 0ee429d773f3..2697d49da4d7 100644 --- a/drivers/scsi/lpfc/lpfc_init.c +++ b/drivers/scsi/lpfc/lpfc_init.c @@ -3555,6 +3555,44 @@ out_free_mem: return rc; } +static uint64_t +lpfc_get_wwpn(struct lpfc_hba *phba) +{ + uint64_t wwn; + int rc; + LPFC_MBOXQ_t *mboxq; + MAILBOX_t *mb; + + + mboxq = (LPFC_MBOXQ_t *) mempool_alloc(phba->mbox_mem_pool, + GFP_KERNEL); + if (!mboxq) + return (uint64_t)-1; + + /* First get WWN of HBA instance */ + lpfc_read_nv(phba, mboxq); + rc = lpfc_sli_issue_mbox(phba, mboxq, MBX_POLL); + if (rc != MBX_SUCCESS) { + lpfc_printf_log(phba, KERN_ERR, LOG_SLI, + "6019 Mailbox failed , mbxCmd x%x " + "READ_NV, mbxStatus x%x\n", + bf_get(lpfc_mqe_command, &mboxq->u.mqe), + bf_get(lpfc_mqe_status, &mboxq->u.mqe)); + mempool_free(mboxq, phba->mbox_mem_pool); + return (uint64_t) -1; + } + mb = &mboxq->u.mb; + memcpy(&wwn, (char *)mb->un.varRDnvp.portname, sizeof(uint64_t)); + /* wwn is WWPN of HBA instance */ + mempool_free(mboxq, phba->mbox_mem_pool); + if (phba->sli_rev == LPFC_SLI_REV4) + return be64_to_cpu(wwn); + else + return (((wwn & 0xffffffff00000000) >> 32) | + ((wwn & 0x00000000ffffffff) << 32)); + +} + /** * lpfc_sli4_nvme_sgl_update - update xri-sgl sizing and mapping * @phba: pointer to lpfc hba data structure. @@ -3676,17 +3714,32 @@ lpfc_create_port(struct lpfc_hba *phba, int instance, struct device *dev) struct lpfc_vport *vport; struct Scsi_Host *shost = NULL; int error = 0; + int i; + uint64_t wwn; + bool use_no_reset_hba = false; + + wwn = lpfc_get_wwpn(phba); + + for (i = 0; i < lpfc_no_hba_reset_cnt; i++) { + if (wwn == lpfc_no_hba_reset[i]) { + lpfc_printf_log(phba, KERN_ERR, LOG_SLI, + "6020 Setting use_no_reset port=%llx\n", + wwn); + use_no_reset_hba = true; + break; + } + } if (phba->cfg_enable_fc4_type & LPFC_ENABLE_FCP) { if (dev != &phba->pcidev->dev) { shost = scsi_host_alloc(&lpfc_vport_template, sizeof(struct lpfc_vport)); } else { - if (phba->sli_rev == LPFC_SLI_REV4) + if (!use_no_reset_hba) shost = scsi_host_alloc(&lpfc_template, sizeof(struct lpfc_vport)); else - shost = scsi_host_alloc(&lpfc_template_s3, + shost = scsi_host_alloc(&lpfc_template_no_hr, sizeof(struct lpfc_vport)); } } else if (phba->cfg_enable_fc4_type & LPFC_ENABLE_NVME) { @@ -3734,17 +3787,14 @@ lpfc_create_port(struct lpfc_hba *phba, int instance, struct device *dev) INIT_LIST_HEAD(&vport->rcv_buffer_list); spin_lock_init(&vport->work_port_lock); - init_timer(&vport->fc_disctmo); - vport->fc_disctmo.function = lpfc_disc_timeout; - vport->fc_disctmo.data = (unsigned long)vport; + setup_timer(&vport->fc_disctmo, lpfc_disc_timeout, + (unsigned long)vport); - init_timer(&vport->els_tmofunc); - vport->els_tmofunc.function = lpfc_els_timeout; - vport->els_tmofunc.data = (unsigned long)vport; + setup_timer(&vport->els_tmofunc, lpfc_els_timeout, + (unsigned long)vport); - init_timer(&vport->delayed_disc_tmo); - vport->delayed_disc_tmo.function = lpfc_delayed_disc_tmo; - vport->delayed_disc_tmo.data = (unsigned long)vport; + setup_timer(&vport->delayed_disc_tmo, lpfc_delayed_disc_tmo, + (unsigned long)vport); error = scsi_add_host_with_dma(shost, dev, &phba->pcidev->dev); if (error) @@ -5406,21 +5456,15 @@ lpfc_setup_driver_resource_phase1(struct lpfc_hba *phba) INIT_LIST_HEAD(&phba->luns); /* MBOX heartbeat timer */ - init_timer(&psli->mbox_tmo); - psli->mbox_tmo.function = lpfc_mbox_timeout; - psli->mbox_tmo.data = (unsigned long) phba; + setup_timer(&psli->mbox_tmo, lpfc_mbox_timeout, (unsigned long)phba); /* Fabric block timer */ - init_timer(&phba->fabric_block_timer); - phba->fabric_block_timer.function = lpfc_fabric_block_timeout; - phba->fabric_block_timer.data = (unsigned long) phba; + setup_timer(&phba->fabric_block_timer, lpfc_fabric_block_timeout, + (unsigned long)phba); /* EA polling mode timer */ - init_timer(&phba->eratt_poll); - phba->eratt_poll.function = lpfc_poll_eratt; - phba->eratt_poll.data = (unsigned long) phba; + setup_timer(&phba->eratt_poll, lpfc_poll_eratt, + (unsigned long)phba); /* Heartbeat timer */ - init_timer(&phba->hb_tmofunc); - phba->hb_tmofunc.function = lpfc_hb_timeout; - phba->hb_tmofunc.data = (unsigned long)phba; + setup_timer(&phba->hb_tmofunc, lpfc_hb_timeout, (unsigned long)phba); return 0; } @@ -5446,9 +5490,8 @@ lpfc_sli_driver_resource_setup(struct lpfc_hba *phba) */ /* FCP polling mode timer */ - init_timer(&phba->fcp_poll_timer); - phba->fcp_poll_timer.function = lpfc_poll_timeout; - phba->fcp_poll_timer.data = (unsigned long) phba; + setup_timer(&phba->fcp_poll_timer, lpfc_poll_timeout, + (unsigned long)phba); /* Host attention work mask setup */ phba->work_ha_mask = (HA_ERATT | HA_MBATT | HA_LATT); @@ -5482,7 +5525,8 @@ lpfc_sli_driver_resource_setup(struct lpfc_hba *phba) /* Initialize the host templates the configured values. */ lpfc_vport_template.sg_tablesize = phba->cfg_sg_seg_cnt; - lpfc_template_s3.sg_tablesize = phba->cfg_sg_seg_cnt; + lpfc_template_no_hr.sg_tablesize = phba->cfg_sg_seg_cnt; + lpfc_template.sg_tablesize = phba->cfg_sg_seg_cnt; /* There are going to be 2 reserved BDEs: 1 FCP cmnd + 1 FCP rsp */ if (phba->cfg_enable_bg) { @@ -5617,14 +5661,11 @@ lpfc_sli4_driver_resource_setup(struct lpfc_hba *phba) * Initialize timers used by driver */ - init_timer(&phba->rrq_tmr); - phba->rrq_tmr.function = lpfc_rrq_timeout; - phba->rrq_tmr.data = (unsigned long)phba; + setup_timer(&phba->rrq_tmr, lpfc_rrq_timeout, (unsigned long)phba); /* FCF rediscover timer */ - init_timer(&phba->fcf.redisc_wait); - phba->fcf.redisc_wait.function = lpfc_sli4_fcf_redisc_wait_tmo; - phba->fcf.redisc_wait.data = (unsigned long)phba; + setup_timer(&phba->fcf.redisc_wait, lpfc_sli4_fcf_redisc_wait_tmo, + (unsigned long)phba); /* * Control structure for handling external multi-buffer mailbox @@ -5706,6 +5747,7 @@ lpfc_sli4_driver_resource_setup(struct lpfc_hba *phba) /* Initialize the host templates with the updated values. */ lpfc_vport_template.sg_tablesize = phba->cfg_sg_seg_cnt; lpfc_template.sg_tablesize = phba->cfg_sg_seg_cnt; + lpfc_template_no_hr.sg_tablesize = phba->cfg_sg_seg_cnt; if (phba->cfg_sg_dma_buf_size <= LPFC_MIN_SG_SLI4_BUF_SZ) phba->cfg_sg_dma_buf_size = LPFC_MIN_SG_SLI4_BUF_SZ; @@ -5736,6 +5778,8 @@ lpfc_sli4_driver_resource_setup(struct lpfc_hba *phba) /* Initialize the Abort nvme buffer list used by driver */ spin_lock_init(&phba->sli4_hba.abts_nvme_buf_list_lock); INIT_LIST_HEAD(&phba->sli4_hba.lpfc_abts_nvme_buf_list); + /* Fast-path XRI aborted CQ Event work queue list */ + INIT_LIST_HEAD(&phba->sli4_hba.sp_nvme_xri_aborted_work_queue); } /* This abort list used by worker thread */ @@ -8712,12 +8756,9 @@ lpfc_sli4_queue_setup(struct lpfc_hba *phba) } } - /* - * Configure EQ delay multipier for interrupt coalescing using - * MODIFY_EQ_DELAY for all EQs created, LPFC_MAX_EQ_DELAY at a time. - */ - for (qidx = 0; qidx < io_channel; qidx += LPFC_MAX_EQ_DELAY) + for (qidx = 0; qidx < io_channel; qidx += LPFC_MAX_EQ_DELAY_EQID_CNT) lpfc_modify_hba_eq_delay(phba, qidx); + return 0; out_destroy: @@ -8973,6 +9014,11 @@ lpfc_sli4_cq_event_release_all(struct lpfc_hba *phba) /* Pending ELS XRI abort events */ list_splice_init(&phba->sli4_hba.sp_els_xri_aborted_work_queue, &cqelist); + if (phba->cfg_enable_fc4_type & LPFC_ENABLE_NVME) { + /* Pending NVME XRI abort events */ + list_splice_init(&phba->sli4_hba.sp_nvme_xri_aborted_work_queue, + &cqelist); + } /* Pending asynnc events */ list_splice_init(&phba->sli4_hba.sp_asynce_work_queue, &cqelist); @@ -10400,12 +10446,7 @@ lpfc_pci_remove_one_s3(struct pci_dev *pdev) fc_remove_host(shost); scsi_remove_host(shost); - /* Perform ndlp cleanup on the physical port. The nvme and nvmet - * localports are destroyed after to cleanup all transport memory. - */ lpfc_cleanup(vport); - lpfc_nvmet_destroy_targetport(phba); - lpfc_nvme_destroy_localport(vport); /* * Bring down the SLI Layer. This step disable all interrupts, @@ -12018,6 +12059,7 @@ static struct pci_driver lpfc_driver = { .id_table = lpfc_id_table, .probe = lpfc_pci_probe_one, .remove = lpfc_pci_remove_one, + .shutdown = lpfc_pci_remove_one, .suspend = lpfc_pci_suspend_one, .resume = lpfc_pci_resume_one, .err_handler = &lpfc_err_handler, diff --git a/drivers/scsi/lpfc/lpfc_mem.c b/drivers/scsi/lpfc/lpfc_mem.c index c61d8d692ede..5986c7957199 100644 --- a/drivers/scsi/lpfc/lpfc_mem.c +++ b/drivers/scsi/lpfc/lpfc_mem.c @@ -646,7 +646,6 @@ lpfc_sli4_nvmet_alloc(struct lpfc_hba *phba) } dma_buf->iocbq = lpfc_sli_get_iocbq(phba); - dma_buf->iocbq->iocb_flag = LPFC_IO_NVMET; if (!dma_buf->iocbq) { kfree(dma_buf->context); pci_pool_free(phba->lpfc_drb_pool, dma_buf->dbuf.virt, @@ -658,6 +657,7 @@ lpfc_sli4_nvmet_alloc(struct lpfc_hba *phba) "2621 Ran out of nvmet iocb/WQEs\n"); return NULL; } + dma_buf->iocbq->iocb_flag = LPFC_IO_NVMET; nvmewqe = dma_buf->iocbq; wqe = (union lpfc_wqe128 *)&nvmewqe->wqe; /* Initialize WQE */ diff --git a/drivers/scsi/lpfc/lpfc_nvme.c b/drivers/scsi/lpfc/lpfc_nvme.c index 609a908ea9db..0a4c19081409 100644 --- a/drivers/scsi/lpfc/lpfc_nvme.c +++ b/drivers/scsi/lpfc/lpfc_nvme.c @@ -316,7 +316,7 @@ lpfc_nvme_gen_req(struct lpfc_vport *vport, struct lpfc_dmabuf *bmp, bf_set(wqe_dfctl, &wqe->gen_req.wge_ctl, 0); bf_set(wqe_si, &wqe->gen_req.wge_ctl, 1); bf_set(wqe_la, &wqe->gen_req.wge_ctl, 1); - bf_set(wqe_rctl, &wqe->gen_req.wge_ctl, FC_RCTL_DD_UNSOL_CTL); + bf_set(wqe_rctl, &wqe->gen_req.wge_ctl, FC_RCTL_ELS4_REQ); bf_set(wqe_type, &wqe->gen_req.wge_ctl, FC_TYPE_NVME); /* Word 6 */ @@ -620,15 +620,15 @@ lpfc_nvme_adj_fcp_sgls(struct lpfc_vport *vport, * Embed the payload in the last half of the WQE * WQE words 16-30 get the NVME CMD IU payload * - * WQE Word 16 is already setup with flags - * WQE words 17-19 get payload Words 2-4 + * WQE words 16-19 get payload Words 1-4 * WQE words 20-21 get payload Words 6-7 * WQE words 22-29 get payload Words 16-23 */ - wptr = &wqe->words[17]; /* WQE ptr */ + wptr = &wqe->words[16]; /* WQE ptr */ dptr = (uint32_t *)nCmd->cmdaddr; /* payload ptr */ - dptr += 2; /* Skip Words 0-1 in payload */ + dptr++; /* Skip Word 0 in payload */ + *wptr++ = *dptr++; /* Word 1 */ *wptr++ = *dptr++; /* Word 2 */ *wptr++ = *dptr++; /* Word 3 */ *wptr++ = *dptr++; /* Word 4 */ @@ -978,9 +978,6 @@ lpfc_nvme_prep_io_cmd(struct lpfc_vport *vport, bf_set(wqe_cmd_type, &wqe->generic.wqe_com, NVME_WRITE_CMD); - /* Word 16 */ - wqe->words[16] = LPFC_NVME_EMBED_WRITE; - phba->fc4NvmeOutputRequests++; } else { /* Word 7 */ @@ -1002,9 +999,6 @@ lpfc_nvme_prep_io_cmd(struct lpfc_vport *vport, bf_set(wqe_cmd_type, &wqe->generic.wqe_com, NVME_READ_CMD); - /* Word 16 */ - wqe->words[16] = LPFC_NVME_EMBED_READ; - phba->fc4NvmeInputRequests++; } } else { @@ -1026,9 +1020,6 @@ lpfc_nvme_prep_io_cmd(struct lpfc_vport *vport, /* Word 11 */ bf_set(wqe_cmd_type, &wqe->generic.wqe_com, NVME_READ_CMD); - /* Word 16 */ - wqe->words[16] = LPFC_NVME_EMBED_CMD; - phba->fc4NvmeControlRequests++; } /* @@ -1286,6 +1277,7 @@ lpfc_nvme_fcp_io_submit(struct nvme_fc_local_port *pnvme_lport, pnvme_fcreq->private = (void *)lpfc_ncmd; lpfc_ncmd->nvmeCmd = pnvme_fcreq; lpfc_ncmd->nrport = rport; + lpfc_ncmd->ndlp = ndlp; lpfc_ncmd->start_time = jiffies; lpfc_nvme_prep_io_cmd(vport, lpfc_ncmd, ndlp); @@ -1319,7 +1311,7 @@ lpfc_nvme_fcp_io_submit(struct nvme_fc_local_port *pnvme_lport, "sid: x%x did: x%x oxid: x%x\n", ret, vport->fc_myDID, ndlp->nlp_DID, lpfc_ncmd->cur_iocbq.sli4_xritag); - ret = -EINVAL; + ret = -EBUSY; goto out_free_nvme_buf; } @@ -1821,10 +1813,10 @@ lpfc_post_nvme_sgl_list(struct lpfc_hba *phba, pdma_phys_sgl1, cur_xritag); if (status) { /* failure, put on abort nvme list */ - lpfc_ncmd->exch_busy = 1; + lpfc_ncmd->flags |= LPFC_SBUF_XBUSY; } else { /* success, put on NVME buffer list */ - lpfc_ncmd->exch_busy = 0; + lpfc_ncmd->flags &= ~LPFC_SBUF_XBUSY; lpfc_ncmd->status = IOSTAT_SUCCESS; num_posted++; } @@ -1854,10 +1846,10 @@ lpfc_post_nvme_sgl_list(struct lpfc_hba *phba, struct lpfc_nvme_buf, list); if (status) { /* failure, put on abort nvme list */ - lpfc_ncmd->exch_busy = 1; + lpfc_ncmd->flags |= LPFC_SBUF_XBUSY; } else { /* success, put on NVME buffer list */ - lpfc_ncmd->exch_busy = 0; + lpfc_ncmd->flags &= ~LPFC_SBUF_XBUSY; lpfc_ncmd->status = IOSTAT_SUCCESS; num_posted++; } @@ -2099,7 +2091,7 @@ lpfc_release_nvme_buf(struct lpfc_hba *phba, struct lpfc_nvme_buf *lpfc_ncmd) unsigned long iflag = 0; lpfc_ncmd->nonsg_phys = 0; - if (lpfc_ncmd->exch_busy) { + if (lpfc_ncmd->flags & LPFC_SBUF_XBUSY) { spin_lock_irqsave(&phba->sli4_hba.abts_nvme_buf_list_lock, iflag); lpfc_ncmd->nvmeCmd = NULL; @@ -2135,11 +2127,12 @@ lpfc_release_nvme_buf(struct lpfc_hba *phba, struct lpfc_nvme_buf *lpfc_ncmd) int lpfc_nvme_create_localport(struct lpfc_vport *vport) { + int ret = 0; struct lpfc_hba *phba = vport->phba; struct nvme_fc_port_info nfcp_info; struct nvme_fc_local_port *localport; struct lpfc_nvme_lport *lport; - int len, ret = 0; + int len; /* Initialize this localport instance. The vport wwn usage ensures * that NPIV is accounted for. @@ -2156,8 +2149,12 @@ lpfc_nvme_create_localport(struct lpfc_vport *vport) /* localport is allocated from the stack, but the registration * call allocates heap memory as well as the private area. */ +#ifdef CONFIG_LPFC_NVME_INITIATOR ret = nvme_fc_register_localport(&nfcp_info, &lpfc_nvme_template, &vport->phba->pcidev->dev, &localport); +#else + ret = -ENOMEM; +#endif if (!ret) { lpfc_printf_vlog(vport, KERN_INFO, LOG_NVME | LOG_NVME_DISC, "6005 Successfully registered local " @@ -2173,10 +2170,10 @@ lpfc_nvme_create_localport(struct lpfc_vport *vport) lport->vport = vport; INIT_LIST_HEAD(&lport->rport_list); vport->nvmei_support = 1; + len = lpfc_new_nvme_buf(vport, phba->sli4_hba.nvme_xri_max); + vport->phba->total_nvme_bufs += len; } - len = lpfc_new_nvme_buf(vport, phba->sli4_hba.nvme_xri_max); - vport->phba->total_nvme_bufs += len; return ret; } @@ -2193,6 +2190,7 @@ lpfc_nvme_create_localport(struct lpfc_vport *vport) void lpfc_nvme_destroy_localport(struct lpfc_vport *vport) { +#ifdef CONFIG_LPFC_NVME_INITIATOR struct nvme_fc_local_port *localport; struct lpfc_nvme_lport *lport; struct lpfc_nvme_rport *rport = NULL, *rport_next = NULL; @@ -2208,7 +2206,6 @@ lpfc_nvme_destroy_localport(struct lpfc_vport *vport) lpfc_printf_vlog(vport, KERN_INFO, LOG_NVME, "6011 Destroying NVME localport %p\n", localport); - list_for_each_entry_safe(rport, rport_next, &lport->rport_list, list) { /* The last node ref has to get released now before the rport * private memory area is released by the transport. @@ -2222,6 +2219,7 @@ lpfc_nvme_destroy_localport(struct lpfc_vport *vport) "6008 rport fail destroy %x\n", ret); wait_for_completion_timeout(&rport->rport_unreg_done, 5); } + /* lport's rport list is clear. Unregister * lport and release resources. */ @@ -2245,6 +2243,7 @@ lpfc_nvme_destroy_localport(struct lpfc_vport *vport) "Failed, status x%x\n", ret); } +#endif } void @@ -2275,6 +2274,7 @@ lpfc_nvme_update_localport(struct lpfc_vport *vport) int lpfc_nvme_register_port(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp) { +#ifdef CONFIG_LPFC_NVME_INITIATOR int ret = 0; struct nvme_fc_local_port *localport; struct lpfc_nvme_lport *lport; @@ -2348,7 +2348,6 @@ lpfc_nvme_register_port(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp) rpinfo.port_role |= FC_PORT_ROLE_NVME_INITIATOR; rpinfo.port_name = wwn_to_u64(ndlp->nlp_portname.u.wwn); rpinfo.node_name = wwn_to_u64(ndlp->nlp_nodename.u.wwn); - ret = nvme_fc_register_remoteport(localport, &rpinfo, &remote_port); if (!ret) { @@ -2384,6 +2383,9 @@ lpfc_nvme_register_port(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp) ndlp->nlp_type, ndlp->nlp_DID, ndlp); } return ret; +#else + return 0; +#endif } /* lpfc_nvme_unregister_port - unbind the DID and port_role from this rport. @@ -2401,6 +2403,7 @@ lpfc_nvme_register_port(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp) void lpfc_nvme_unregister_port(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp) { +#ifdef CONFIG_LPFC_NVME_INITIATOR int ret; struct nvme_fc_local_port *localport; struct lpfc_nvme_lport *lport; @@ -2458,7 +2461,61 @@ lpfc_nvme_unregister_port(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp) return; input_err: +#endif lpfc_printf_vlog(vport, KERN_ERR, LOG_NVME_DISC, "6168: State error: lport %p, rport%p FCID x%06x\n", vport->localport, ndlp->rport, ndlp->nlp_DID); } + +/** + * lpfc_sli4_nvme_xri_aborted - Fast-path process of NVME xri abort + * @phba: pointer to lpfc hba data structure. + * @axri: pointer to the fcp xri abort wcqe structure. + * + * This routine is invoked by the worker thread to process a SLI4 fast-path + * FCP aborted xri. + **/ +void +lpfc_sli4_nvme_xri_aborted(struct lpfc_hba *phba, + struct sli4_wcqe_xri_aborted *axri) +{ + uint16_t xri = bf_get(lpfc_wcqe_xa_xri, axri); + uint16_t rxid = bf_get(lpfc_wcqe_xa_remote_xid, axri); + struct lpfc_nvme_buf *lpfc_ncmd, *next_lpfc_ncmd; + struct lpfc_nodelist *ndlp; + unsigned long iflag = 0; + int rrq_empty = 0; + + if (!(phba->cfg_enable_fc4_type & LPFC_ENABLE_NVME)) + return; + spin_lock_irqsave(&phba->hbalock, iflag); + spin_lock(&phba->sli4_hba.abts_nvme_buf_list_lock); + list_for_each_entry_safe(lpfc_ncmd, next_lpfc_ncmd, + &phba->sli4_hba.lpfc_abts_nvme_buf_list, + list) { + if (lpfc_ncmd->cur_iocbq.sli4_xritag == xri) { + list_del(&lpfc_ncmd->list); + lpfc_ncmd->flags &= ~LPFC_SBUF_XBUSY; + lpfc_ncmd->status = IOSTAT_SUCCESS; + spin_unlock( + &phba->sli4_hba.abts_nvme_buf_list_lock); + + rrq_empty = list_empty(&phba->active_rrq_list); + spin_unlock_irqrestore(&phba->hbalock, iflag); + ndlp = lpfc_ncmd->ndlp; + if (ndlp) { + lpfc_set_rrq_active( + phba, ndlp, + lpfc_ncmd->cur_iocbq.sli4_lxritag, + rxid, 1); + lpfc_sli4_abts_err_handler(phba, ndlp, axri); + } + lpfc_release_nvme_buf(phba, lpfc_ncmd); + if (rrq_empty) + lpfc_worker_wake_up(phba); + return; + } + } + spin_unlock(&phba->sli4_hba.abts_nvme_buf_list_lock); + spin_unlock_irqrestore(&phba->hbalock, iflag); +} diff --git a/drivers/scsi/lpfc/lpfc_nvme.h b/drivers/scsi/lpfc/lpfc_nvme.h index b2fae5e813f8..1347deb8dd6c 100644 --- a/drivers/scsi/lpfc/lpfc_nvme.h +++ b/drivers/scsi/lpfc/lpfc_nvme.h @@ -57,6 +57,7 @@ struct lpfc_nvme_buf { struct list_head list; struct nvmefc_fcp_req *nvmeCmd; struct lpfc_nvme_rport *nrport; + struct lpfc_nodelist *ndlp; uint32_t timeout; diff --git a/drivers/scsi/lpfc/lpfc_nvmet.c b/drivers/scsi/lpfc/lpfc_nvmet.c index c421e1738ee9..b7739a554fe0 100644 --- a/drivers/scsi/lpfc/lpfc_nvmet.c +++ b/drivers/scsi/lpfc/lpfc_nvmet.c @@ -571,6 +571,7 @@ lpfc_nvmet_xmt_fcp_op(struct nvmet_fc_target_port *tgtport, lpfc_printf_log(phba, KERN_ERR, LOG_NVME_IOERR, "6102 Bad state IO x%x aborted\n", ctxp->oxid); + rc = -ENXIO; goto aerr; } @@ -580,6 +581,7 @@ lpfc_nvmet_xmt_fcp_op(struct nvmet_fc_target_port *tgtport, lpfc_printf_log(phba, KERN_ERR, LOG_NVME_IOERR, "6152 FCP Drop IO x%x: Prep\n", ctxp->oxid); + rc = -ENXIO; goto aerr; } @@ -618,8 +620,9 @@ lpfc_nvmet_xmt_fcp_op(struct nvmet_fc_target_port *tgtport, ctxp->wqeq->hba_wqidx = 0; nvmewqeq->context2 = NULL; nvmewqeq->context3 = NULL; + rc = -EBUSY; aerr: - return -ENXIO; + return rc; } static void @@ -668,9 +671,13 @@ lpfc_nvmet_create_targetport(struct lpfc_hba *phba) lpfc_tgttemplate.target_features = NVMET_FCTGTFEAT_READDATA_RSP | NVMET_FCTGTFEAT_NEEDS_CMD_CPUSCHED; +#ifdef CONFIG_LPFC_NVME_TARGET error = nvmet_fc_register_targetport(&pinfo, &lpfc_tgttemplate, &phba->pcidev->dev, &phba->targetport); +#else + error = -ENOMEM; +#endif if (error) { lpfc_printf_log(phba, KERN_ERR, LOG_NVME_DISC, "6025 Cannot register NVME targetport " @@ -731,9 +738,25 @@ lpfc_nvmet_update_targetport(struct lpfc_hba *phba) return 0; } +/** + * lpfc_sli4_nvmet_xri_aborted - Fast-path process of nvmet xri abort + * @phba: pointer to lpfc hba data structure. + * @axri: pointer to the nvmet xri abort wcqe structure. + * + * This routine is invoked by the worker thread to process a SLI4 fast-path + * NVMET aborted xri. + **/ +void +lpfc_sli4_nvmet_xri_aborted(struct lpfc_hba *phba, + struct sli4_wcqe_xri_aborted *axri) +{ + /* TODO: work in progress */ +} + void lpfc_nvmet_destroy_targetport(struct lpfc_hba *phba) { +#ifdef CONFIG_LPFC_NVME_TARGET struct lpfc_nvmet_tgtport *tgtp; if (phba->nvmet_support == 0) @@ -745,6 +768,7 @@ lpfc_nvmet_destroy_targetport(struct lpfc_hba *phba) wait_for_completion_timeout(&tgtp->tport_unreg_done, 5); } phba->targetport = NULL; +#endif } /** @@ -764,6 +788,7 @@ static void lpfc_nvmet_unsol_ls_buffer(struct lpfc_hba *phba, struct lpfc_sli_ring *pring, struct hbq_dmabuf *nvmebuf) { +#ifdef CONFIG_LPFC_NVME_TARGET struct lpfc_nvmet_tgtport *tgtp; struct fc_frame_header *fc_hdr; struct lpfc_nvmet_rcv_ctx *ctxp; @@ -844,6 +869,7 @@ dropit: atomic_inc(&tgtp->xmt_ls_abort); lpfc_nvmet_unsol_ls_issue_abort(phba, ctxp, sid, oxid); +#endif } /** @@ -865,6 +891,7 @@ lpfc_nvmet_unsol_fcp_buffer(struct lpfc_hba *phba, struct rqb_dmabuf *nvmebuf, uint64_t isr_timestamp) { +#ifdef CONFIG_LPFC_NVME_TARGET struct lpfc_nvmet_rcv_ctx *ctxp; struct lpfc_nvmet_tgtport *tgtp; struct fc_frame_header *fc_hdr; @@ -955,7 +982,7 @@ lpfc_nvmet_unsol_fcp_buffer(struct lpfc_hba *phba, atomic_inc(&tgtp->rcv_fcp_cmd_drop); lpfc_printf_log(phba, KERN_ERR, LOG_NVME_IOERR, - "6159 FCP Drop IO x%x: nvmet_fc_rcv_fcp_req x%x\n", + "6159 FCP Drop IO x%x: err x%x\n", ctxp->oxid, rc); dropit: lpfc_nvmeio_data(phba, "NVMET FCP DROP: xri x%x sz %d from %06x\n", @@ -970,6 +997,7 @@ dropit: /* We assume a rcv'ed cmd ALWAYs fits into 1 buffer */ lpfc_nvmet_rq_post(phba, NULL, &nvmebuf->hbuf); } +#endif } /** @@ -1114,7 +1142,7 @@ lpfc_nvmet_prep_ls_wqe(struct lpfc_hba *phba, bf_set(wqe_dfctl, &wqe->xmit_sequence.wge_ctl, 0); bf_set(wqe_ls, &wqe->xmit_sequence.wge_ctl, 1); bf_set(wqe_la, &wqe->xmit_sequence.wge_ctl, 0); - bf_set(wqe_rctl, &wqe->xmit_sequence.wge_ctl, FC_RCTL_DD_SOL_CTL); + bf_set(wqe_rctl, &wqe->xmit_sequence.wge_ctl, FC_RCTL_ELS4_REP); bf_set(wqe_type, &wqe->xmit_sequence.wge_ctl, FC_TYPE_NVME); /* Word 6 */ @@ -1445,7 +1473,6 @@ lpfc_nvmet_prep_fcp_wqe(struct lpfc_hba *phba, case NVMET_FCOP_RSP: /* Words 0 - 2 */ - sgel = &rsp->sg[0]; physaddr = rsp->rspdma; wqe->fcp_trsp.bde.tus.f.bdeFlags = BUFF_TYPE_BDE_64; wqe->fcp_trsp.bde.tus.f.bdeSize = rsp->rsplen; @@ -1681,8 +1708,8 @@ lpfc_nvmet_unsol_issue_abort(struct lpfc_hba *phba, struct lpfc_nodelist *ndlp; lpfc_printf_log(phba, KERN_INFO, LOG_NVME_ABTS, - "6067 %s: Entrypoint: sid %x xri %x\n", __func__, - sid, xri); + "6067 Abort: sid %x xri x%x/x%x\n", + sid, xri, ctxp->wqeq->sli4_xritag); tgtp = (struct lpfc_nvmet_tgtport *)phba->targetport->private; @@ -1693,7 +1720,7 @@ lpfc_nvmet_unsol_issue_abort(struct lpfc_hba *phba, atomic_inc(&tgtp->xmt_abort_rsp_error); lpfc_printf_log(phba, KERN_WARNING, LOG_NVME_ABTS, "6134 Drop ABTS - wrong NDLP state x%x.\n", - ndlp->nlp_state); + (ndlp) ? ndlp->nlp_state : NLP_STE_MAX_STATE); /* No failure to an ABTS request. */ return 0; @@ -1791,7 +1818,7 @@ lpfc_nvmet_sol_fcp_issue_abort(struct lpfc_hba *phba, atomic_inc(&tgtp->xmt_abort_rsp_error); lpfc_printf_log(phba, KERN_WARNING, LOG_NVME_ABTS, "6160 Drop ABTS - wrong NDLP state x%x.\n", - ndlp->nlp_state); + (ndlp) ? ndlp->nlp_state : NLP_STE_MAX_STATE); /* No failure to an ABTS request. */ return 0; diff --git a/drivers/scsi/lpfc/lpfc_scsi.c b/drivers/scsi/lpfc/lpfc_scsi.c index 9d6384af9fce..54fd0c81ceaf 100644 --- a/drivers/scsi/lpfc/lpfc_scsi.c +++ b/drivers/scsi/lpfc/lpfc_scsi.c @@ -5953,12 +5953,13 @@ struct scsi_host_template lpfc_template_nvme = { .track_queue_depth = 0, }; -struct scsi_host_template lpfc_template_s3 = { +struct scsi_host_template lpfc_template_no_hr = { .module = THIS_MODULE, .name = LPFC_DRIVER_NAME, .proc_name = LPFC_DRIVER_NAME, .info = lpfc_info, .queuecommand = lpfc_queuecommand, + .eh_timed_out = fc_eh_timed_out, .eh_abort_handler = lpfc_abort_handler, .eh_device_reset_handler = lpfc_device_reset_handler, .eh_target_reset_handler = lpfc_target_reset_handler, @@ -6015,7 +6016,6 @@ struct scsi_host_template lpfc_vport_template = { .eh_abort_handler = lpfc_abort_handler, .eh_device_reset_handler = lpfc_device_reset_handler, .eh_target_reset_handler = lpfc_target_reset_handler, - .eh_bus_reset_handler = lpfc_bus_reset_handler, .slave_alloc = lpfc_slave_alloc, .slave_configure = lpfc_slave_configure, .slave_destroy = lpfc_slave_destroy, diff --git a/drivers/scsi/lpfc/lpfc_sli.c b/drivers/scsi/lpfc/lpfc_sli.c index e43e5e23c24b..1c9fa45df7eb 100644 --- a/drivers/scsi/lpfc/lpfc_sli.c +++ b/drivers/scsi/lpfc/lpfc_sli.c @@ -1,3 +1,4 @@ + /******************************************************************* * This file is part of the Emulex Linux Device Driver for * * Fibre Channel Host Bus Adapters. * @@ -952,7 +953,7 @@ __lpfc_sli_get_els_sglq(struct lpfc_hba *phba, struct lpfc_iocbq *piocbq) start_sglq = sglq; while (!found) { if (!sglq) - return NULL; + break; if (ndlp && ndlp->active_rrqs_xri_bitmap && test_bit(sglq->sli4_lxritag, ndlp->active_rrqs_xri_bitmap)) { @@ -12213,6 +12214,41 @@ void lpfc_sli4_fcp_xri_abort_event_proc(struct lpfc_hba *phba) } /** + * lpfc_sli4_nvme_xri_abort_event_proc - Process nvme xri abort event + * @phba: pointer to lpfc hba data structure. + * + * This routine is invoked by the worker thread to process all the pending + * SLI4 NVME abort XRI events. + **/ +void lpfc_sli4_nvme_xri_abort_event_proc(struct lpfc_hba *phba) +{ + struct lpfc_cq_event *cq_event; + + /* First, declare the fcp xri abort event has been handled */ + spin_lock_irq(&phba->hbalock); + phba->hba_flag &= ~NVME_XRI_ABORT_EVENT; + spin_unlock_irq(&phba->hbalock); + /* Now, handle all the fcp xri abort events */ + while (!list_empty(&phba->sli4_hba.sp_nvme_xri_aborted_work_queue)) { + /* Get the first event from the head of the event queue */ + spin_lock_irq(&phba->hbalock); + list_remove_head(&phba->sli4_hba.sp_nvme_xri_aborted_work_queue, + cq_event, struct lpfc_cq_event, list); + spin_unlock_irq(&phba->hbalock); + /* Notify aborted XRI for NVME work queue */ + if (phba->nvmet_support) { + lpfc_sli4_nvmet_xri_aborted(phba, + &cq_event->cqe.wcqe_axri); + } else { + lpfc_sli4_nvme_xri_aborted(phba, + &cq_event->cqe.wcqe_axri); + } + /* Free the event processed back to the free pool */ + lpfc_sli4_cq_event_release(phba, cq_event); + } +} + +/** * lpfc_sli4_els_xri_abort_event_proc - Process els xri abort event * @phba: pointer to lpfc hba data structure. * @@ -12709,10 +12745,22 @@ lpfc_sli4_sp_handle_abort_xri_wcqe(struct lpfc_hba *phba, spin_unlock_irqrestore(&phba->hbalock, iflags); workposted = true; break; + case LPFC_NVME: + spin_lock_irqsave(&phba->hbalock, iflags); + list_add_tail(&cq_event->list, + &phba->sli4_hba.sp_nvme_xri_aborted_work_queue); + /* Set the nvme xri abort event flag */ + phba->hba_flag |= NVME_XRI_ABORT_EVENT; + spin_unlock_irqrestore(&phba->hbalock, iflags); + workposted = true; + break; default: lpfc_printf_log(phba, KERN_ERR, LOG_SLI, - "0603 Invalid work queue CQE subtype (x%x)\n", - cq->subtype); + "0603 Invalid CQ subtype %d: " + "%08x %08x %08x %08x\n", + cq->subtype, wcqe->word0, wcqe->parameter, + wcqe->word2, wcqe->word3); + lpfc_sli4_cq_event_release(phba, cq_event); workposted = false; break; } @@ -13827,6 +13875,8 @@ lpfc_dual_chute_pci_bar_map(struct lpfc_hba *phba, uint16_t pci_barset) * @startq: The starting FCP EQ to modify * * This function sends an MODIFY_EQ_DELAY mailbox command to the HBA. + * The command allows up to LPFC_MAX_EQ_DELAY_EQID_CNT EQ ID's to be + * updated in one mailbox command. * * The @phba struct is used to send mailbox command to HBA. The @startq * is used to get the starting FCP EQ to change. @@ -13879,7 +13929,7 @@ lpfc_modify_hba_eq_delay(struct lpfc_hba *phba, uint32_t startq) eq_delay->u.request.eq[cnt].phase = 0; eq_delay->u.request.eq[cnt].delay_multi = dmult; cnt++; - if (cnt >= LPFC_MAX_EQ_DELAY) + if (cnt >= LPFC_MAX_EQ_DELAY_EQID_CNT) break; } eq_delay->u.request.num_eq = cnt; @@ -15185,17 +15235,17 @@ lpfc_mrq_create(struct lpfc_hba *phba, struct lpfc_queue **hrqp, drq = drqp[idx]; cq = cqp[idx]; - if (hrq->entry_count != drq->entry_count) { - status = -EINVAL; - goto out; - } - /* sanity check on queue memory */ if (!hrq || !drq || !cq) { status = -ENODEV; goto out; } + if (hrq->entry_count != drq->entry_count) { + status = -EINVAL; + goto out; + } + if (idx == 0) { bf_set(lpfc_mbx_rq_create_num_pages, &rq_create->u.request, diff --git a/drivers/scsi/lpfc/lpfc_sli4.h b/drivers/scsi/lpfc/lpfc_sli4.h index 91153c9f6d18..710458cf11d6 100644 --- a/drivers/scsi/lpfc/lpfc_sli4.h +++ b/drivers/scsi/lpfc/lpfc_sli4.h @@ -642,6 +642,7 @@ struct lpfc_sli4_hba { struct list_head sp_asynce_work_queue; struct list_head sp_fcp_xri_aborted_work_queue; struct list_head sp_els_xri_aborted_work_queue; + struct list_head sp_nvme_xri_aborted_work_queue; struct list_head sp_unsol_work_queue; struct lpfc_sli4_link link_state; struct lpfc_sli4_lnk_info lnk_info; @@ -794,9 +795,14 @@ void lpfc_sli4_fcf_redisc_event_proc(struct lpfc_hba *); int lpfc_sli4_resume_rpi(struct lpfc_nodelist *, void (*)(struct lpfc_hba *, LPFC_MBOXQ_t *), void *); void lpfc_sli4_fcp_xri_abort_event_proc(struct lpfc_hba *); +void lpfc_sli4_nvme_xri_abort_event_proc(struct lpfc_hba *phba); void lpfc_sli4_els_xri_abort_event_proc(struct lpfc_hba *); void lpfc_sli4_fcp_xri_aborted(struct lpfc_hba *, struct sli4_wcqe_xri_aborted *); +void lpfc_sli4_nvme_xri_aborted(struct lpfc_hba *phba, + struct sli4_wcqe_xri_aborted *axri); +void lpfc_sli4_nvmet_xri_aborted(struct lpfc_hba *phba, + struct sli4_wcqe_xri_aborted *axri); void lpfc_sli4_els_xri_aborted(struct lpfc_hba *, struct sli4_wcqe_xri_aborted *); void lpfc_sli4_vport_delete_els_xri_aborted(struct lpfc_vport *); diff --git a/drivers/scsi/lpfc/lpfc_version.h b/drivers/scsi/lpfc/lpfc_version.h index 86c6c9b26b82..d4e95e28f4e3 100644 --- a/drivers/scsi/lpfc/lpfc_version.h +++ b/drivers/scsi/lpfc/lpfc_version.h @@ -20,7 +20,7 @@ * included with this package. * *******************************************************************/ -#define LPFC_DRIVER_VERSION "11.2.0.7" +#define LPFC_DRIVER_VERSION "11.2.0.10" #define LPFC_DRIVER_NAME "lpfc" /* Used for SLI 2/3 */ diff --git a/drivers/scsi/mpt3sas/mpt3sas_base.h b/drivers/scsi/mpt3sas/mpt3sas_base.h index 7fe7e6ed595b..8981806fb13f 100644 --- a/drivers/scsi/mpt3sas/mpt3sas_base.h +++ b/drivers/scsi/mpt3sas/mpt3sas_base.h @@ -1442,9 +1442,6 @@ void mpt3sas_transport_update_links(struct MPT3SAS_ADAPTER *ioc, u64 sas_address, u16 handle, u8 phy_number, u8 link_rate); extern struct sas_function_template mpt3sas_transport_functions; extern struct scsi_transport_template *mpt3sas_transport_template; -extern int scsi_internal_device_block(struct scsi_device *sdev); -extern int scsi_internal_device_unblock(struct scsi_device *sdev, - enum scsi_device_state new_state); /* trigger data externs */ void mpt3sas_send_trigger_data_event(struct MPT3SAS_ADAPTER *ioc, struct SL_WH_TRIGGERS_EVENT_DATA_T *event_data); diff --git a/drivers/scsi/mpt3sas/mpt3sas_scsih.c b/drivers/scsi/mpt3sas/mpt3sas_scsih.c index 46e866c36c8a..919ba2bb15f1 100644 --- a/drivers/scsi/mpt3sas/mpt3sas_scsih.c +++ b/drivers/scsi/mpt3sas/mpt3sas_scsih.c @@ -2859,7 +2859,7 @@ _scsih_internal_device_block(struct scsi_device *sdev, sas_device_priv_data->sas_target->handle); sas_device_priv_data->block = 1; - r = scsi_internal_device_block(sdev); + r = scsi_internal_device_block(sdev, false); if (r == -EINVAL) sdev_printk(KERN_WARNING, sdev, "device_block failed with return(%d) for handle(0x%04x)\n", @@ -2895,7 +2895,7 @@ _scsih_internal_device_unblock(struct scsi_device *sdev, "performing a block followed by an unblock\n", r, sas_device_priv_data->sas_target->handle); sas_device_priv_data->block = 1; - r = scsi_internal_device_block(sdev); + r = scsi_internal_device_block(sdev, false); if (r) sdev_printk(KERN_WARNING, sdev, "retried device_block " "failed with return(%d) for handle(0x%04x)\n", @@ -4677,7 +4677,6 @@ _scsih_io_done(struct MPT3SAS_ADAPTER *ioc, u16 smid, u8 msix_index, u32 reply) struct MPT3SAS_DEVICE *sas_device_priv_data; u32 response_code = 0; unsigned long flags; - unsigned int sector_sz; mpi_reply = mpt3sas_base_get_reply_virt_addr(ioc, reply); @@ -4742,20 +4741,6 @@ _scsih_io_done(struct MPT3SAS_ADAPTER *ioc, u16 smid, u8 msix_index, u32 reply) } xfer_cnt = le32_to_cpu(mpi_reply->TransferCount); - - /* In case of bogus fw or device, we could end up having - * unaligned partial completion. We can force alignment here, - * then scsi-ml does not need to handle this misbehavior. - */ - sector_sz = scmd->device->sector_size; - if (unlikely(!blk_rq_is_passthrough(scmd->request) && sector_sz && - xfer_cnt % sector_sz)) { - sdev_printk(KERN_INFO, scmd->device, - "unaligned partial completion avoided (xfer_cnt=%u, sector_sz=%u)\n", - xfer_cnt, sector_sz); - xfer_cnt = round_down(xfer_cnt, sector_sz); - } - scsi_set_resid(scmd, scsi_bufflen(scmd) - xfer_cnt); if (ioc_status & MPI2_IOCSTATUS_FLAG_LOG_INFO_AVAILABLE) log_info = le32_to_cpu(mpi_reply->IOCLogInfo); diff --git a/drivers/scsi/qedf/Makefile b/drivers/scsi/qedf/Makefile index 64e9f507ce32..414f2a772a5f 100644 --- a/drivers/scsi/qedf/Makefile +++ b/drivers/scsi/qedf/Makefile @@ -1,5 +1,5 @@ obj-$(CONFIG_QEDF) := qedf.o qedf-y = qedf_dbg.o qedf_main.o qedf_io.o qedf_fip.o \ - qedf_attr.o qedf_els.o + qedf_attr.o qedf_els.o drv_scsi_fw_funcs.o drv_fcoe_fw_funcs.o qedf-$(CONFIG_DEBUG_FS) += qedf_debugfs.o diff --git a/drivers/scsi/qedf/drv_fcoe_fw_funcs.c b/drivers/scsi/qedf/drv_fcoe_fw_funcs.c new file mode 100644 index 000000000000..bb812db48da6 --- /dev/null +++ b/drivers/scsi/qedf/drv_fcoe_fw_funcs.c @@ -0,0 +1,190 @@ +/* QLogic FCoE Offload Driver + * Copyright (c) 2016 Cavium Inc. + * + * This software is available under the terms of the GNU General Public License + * (GPL) Version 2, available from the file COPYING in the main directory of + * this source tree. + */ +#include "drv_fcoe_fw_funcs.h" +#include "drv_scsi_fw_funcs.h" + +#define FCOE_RX_ID ((u32)0x0000FFFF) + +static inline void init_common_sqe(struct fcoe_task_params *task_params, + enum fcoe_sqe_request_type request_type) +{ + memset(task_params->sqe, 0, sizeof(*(task_params->sqe))); + SET_FIELD(task_params->sqe->flags, FCOE_WQE_REQ_TYPE, + request_type); + task_params->sqe->task_id = task_params->itid; +} + +int init_initiator_rw_fcoe_task(struct fcoe_task_params *task_params, + struct scsi_sgl_task_params *sgl_task_params, + struct regpair sense_data_buffer_phys_addr, + u32 task_retry_id, + u8 fcp_cmd_payload[32]) +{ + struct fcoe_task_context *ctx = task_params->context; + struct ystorm_fcoe_task_st_ctx *y_st_ctx; + struct tstorm_fcoe_task_st_ctx *t_st_ctx; + struct ustorm_fcoe_task_ag_ctx *u_ag_ctx; + struct mstorm_fcoe_task_st_ctx *m_st_ctx; + u32 io_size, val; + bool slow_sgl; + + memset(ctx, 0, sizeof(*(ctx))); + slow_sgl = scsi_is_slow_sgl(sgl_task_params->num_sges, + sgl_task_params->small_mid_sge); + io_size = (task_params->task_type == FCOE_TASK_TYPE_WRITE_INITIATOR ? + task_params->tx_io_size : task_params->rx_io_size); + + /* Ystorm ctx */ + y_st_ctx = &ctx->ystorm_st_context; + y_st_ctx->data_2_trns_rem = cpu_to_le32(io_size); + y_st_ctx->task_rety_identifier = cpu_to_le32(task_retry_id); + y_st_ctx->task_type = task_params->task_type; + memcpy(&y_st_ctx->tx_info_union.fcp_cmd_payload, + fcp_cmd_payload, sizeof(struct fcoe_fcp_cmd_payload)); + + /* Tstorm ctx */ + t_st_ctx = &ctx->tstorm_st_context; + t_st_ctx->read_only.dev_type = (task_params->is_tape_device == 1 ? + FCOE_TASK_DEV_TYPE_TAPE : + FCOE_TASK_DEV_TYPE_DISK); + t_st_ctx->read_only.cid = cpu_to_le32(task_params->conn_cid); + val = cpu_to_le32(task_params->cq_rss_number); + t_st_ctx->read_only.glbl_q_num = val; + t_st_ctx->read_only.fcp_cmd_trns_size = cpu_to_le32(io_size); + t_st_ctx->read_only.task_type = task_params->task_type; + SET_FIELD(t_st_ctx->read_write.flags, + FCOE_TSTORM_FCOE_TASK_ST_CTX_READ_WRITE_EXP_FIRST_FRAME, 1); + t_st_ctx->read_write.rx_id = cpu_to_le32(FCOE_RX_ID); + + /* Ustorm ctx */ + u_ag_ctx = &ctx->ustorm_ag_context; + u_ag_ctx->global_cq_num = cpu_to_le32(task_params->cq_rss_number); + + /* Mstorm buffer for sense/rsp data placement */ + m_st_ctx = &ctx->mstorm_st_context; + val = cpu_to_le32(sense_data_buffer_phys_addr.hi); + m_st_ctx->rsp_buf_addr.hi = val; + val = cpu_to_le32(sense_data_buffer_phys_addr.lo); + m_st_ctx->rsp_buf_addr.lo = val; + + if (task_params->task_type == FCOE_TASK_TYPE_WRITE_INITIATOR) { + /* Ystorm ctx */ + y_st_ctx->expect_first_xfer = 1; + + /* Set the amount of super SGEs. Can be up to 4. */ + SET_FIELD(y_st_ctx->sgl_mode, + YSTORM_FCOE_TASK_ST_CTX_TX_SGL_MODE, + (slow_sgl ? SCSI_TX_SLOW_SGL : SCSI_FAST_SGL)); + init_scsi_sgl_context(&y_st_ctx->sgl_params, + &y_st_ctx->data_desc, + sgl_task_params); + + /* Mstorm ctx */ + SET_FIELD(m_st_ctx->flags, + MSTORM_FCOE_TASK_ST_CTX_TX_SGL_MODE, + (slow_sgl ? SCSI_TX_SLOW_SGL : SCSI_FAST_SGL)); + } else { + /* Tstorm ctx */ + SET_FIELD(t_st_ctx->read_write.flags, + FCOE_TSTORM_FCOE_TASK_ST_CTX_READ_WRITE_RX_SGL_MODE, + (slow_sgl ? SCSI_TX_SLOW_SGL : SCSI_FAST_SGL)); + + /* Mstorm ctx */ + m_st_ctx->data_2_trns_rem = cpu_to_le32(io_size); + init_scsi_sgl_context(&m_st_ctx->sgl_params, + &m_st_ctx->data_desc, + sgl_task_params); + } + + init_common_sqe(task_params, SEND_FCOE_CMD); + return 0; +} + +int init_initiator_midpath_unsolicited_fcoe_task( + struct fcoe_task_params *task_params, + struct fcoe_tx_mid_path_params *mid_path_fc_header, + struct scsi_sgl_task_params *tx_sgl_task_params, + struct scsi_sgl_task_params *rx_sgl_task_params, + u8 fw_to_place_fc_header) +{ + struct fcoe_task_context *ctx = task_params->context; + struct ystorm_fcoe_task_st_ctx *y_st_ctx; + struct tstorm_fcoe_task_st_ctx *t_st_ctx; + struct ustorm_fcoe_task_ag_ctx *u_ag_ctx; + struct mstorm_fcoe_task_st_ctx *m_st_ctx; + u32 val; + + memset(ctx, 0, sizeof(*(ctx))); + + /* Init Ystorm */ + y_st_ctx = &ctx->ystorm_st_context; + init_scsi_sgl_context(&y_st_ctx->sgl_params, + &y_st_ctx->data_desc, + tx_sgl_task_params); + SET_FIELD(y_st_ctx->sgl_mode, + YSTORM_FCOE_TASK_ST_CTX_TX_SGL_MODE, SCSI_FAST_SGL); + y_st_ctx->data_2_trns_rem = cpu_to_le32(task_params->tx_io_size); + y_st_ctx->task_type = task_params->task_type; + memcpy(&y_st_ctx->tx_info_union.tx_params.mid_path, + mid_path_fc_header, sizeof(struct fcoe_tx_mid_path_params)); + + /* Init Mstorm */ + m_st_ctx = &ctx->mstorm_st_context; + init_scsi_sgl_context(&m_st_ctx->sgl_params, + &m_st_ctx->data_desc, + rx_sgl_task_params); + SET_FIELD(m_st_ctx->flags, + MSTORM_FCOE_TASK_ST_CTX_MP_INCLUDE_FC_HEADER, + fw_to_place_fc_header); + m_st_ctx->data_2_trns_rem = cpu_to_le32(task_params->rx_io_size); + + /* Init Tstorm */ + t_st_ctx = &ctx->tstorm_st_context; + t_st_ctx->read_only.cid = cpu_to_le32(task_params->conn_cid); + val = cpu_to_le32(task_params->cq_rss_number); + t_st_ctx->read_only.glbl_q_num = val; + t_st_ctx->read_only.task_type = task_params->task_type; + SET_FIELD(t_st_ctx->read_write.flags, + FCOE_TSTORM_FCOE_TASK_ST_CTX_READ_WRITE_EXP_FIRST_FRAME, 1); + t_st_ctx->read_write.rx_id = cpu_to_le32(FCOE_RX_ID); + + /* Init Ustorm */ + u_ag_ctx = &ctx->ustorm_ag_context; + u_ag_ctx->global_cq_num = cpu_to_le32(task_params->cq_rss_number); + + /* Init SQE */ + init_common_sqe(task_params, SEND_FCOE_MIDPATH); + task_params->sqe->additional_info_union.burst_length = + tx_sgl_task_params->total_buffer_size; + SET_FIELD(task_params->sqe->flags, + FCOE_WQE_NUM_SGES, tx_sgl_task_params->num_sges); + SET_FIELD(task_params->sqe->flags, FCOE_WQE_SGL_MODE, + SCSI_FAST_SGL); + + return 0; +} + +int init_initiator_abort_fcoe_task(struct fcoe_task_params *task_params) +{ + init_common_sqe(task_params, SEND_FCOE_ABTS_REQUEST); + return 0; +} + +int init_initiator_cleanup_fcoe_task(struct fcoe_task_params *task_params) +{ + init_common_sqe(task_params, FCOE_EXCHANGE_CLEANUP); + return 0; +} + +int init_initiator_sequence_recovery_fcoe_task( + struct fcoe_task_params *task_params, u32 off) +{ + init_common_sqe(task_params, FCOE_SEQUENCE_RECOVERY); + task_params->sqe->additional_info_union.seq_rec_updated_offset = off; + return 0; +} diff --git a/drivers/scsi/qedf/drv_fcoe_fw_funcs.h b/drivers/scsi/qedf/drv_fcoe_fw_funcs.h new file mode 100644 index 000000000000..617529b058f4 --- /dev/null +++ b/drivers/scsi/qedf/drv_fcoe_fw_funcs.h @@ -0,0 +1,93 @@ +/* QLogic FCoE Offload Driver + * Copyright (c) 2016 Cavium Inc. + * + * This software is available under the terms of the GNU General Public License + * (GPL) Version 2, available from the file COPYING in the main directory of + * this source tree. + */ +#ifndef _FCOE_FW_FUNCS_H +#define _FCOE_FW_FUNCS_H +#include "drv_scsi_fw_funcs.h" +#include "qedf_hsi.h" +#include <linux/qed/qed_if.h> + +struct fcoe_task_params { + /* Output parameter [set/filled by the HSI function] */ + struct fcoe_task_context *context; + + /* Output parameter [set/filled by the HSI function] */ + struct fcoe_wqe *sqe; + enum fcoe_task_type task_type; + u32 tx_io_size; /* in bytes */ + u32 rx_io_size; /* in bytes */ + u32 conn_cid; + u16 itid; + u8 cq_rss_number; + + /* Whether it's Tape device or not (0=Disk, 1=Tape) */ + u8 is_tape_device; +}; + +/** + * @brief init_initiator_rw_fcoe_task - Initializes FCoE task context for + * read/write task types and init fcoe_sqe + * + * @param task_params - Pointer to task parameters struct + * @param sgl_task_params - Pointer to SGL task params + * @param sense_data_buffer_phys_addr - Pointer to sense data buffer + * @param task_retry_id - retry identification - Used only for Tape device + * @param fcp_cmnd_payload - FCP CMD Payload + */ +int init_initiator_rw_fcoe_task(struct fcoe_task_params *task_params, + struct scsi_sgl_task_params *sgl_task_params, + struct regpair sense_data_buffer_phys_addr, + u32 task_retry_id, + u8 fcp_cmd_payload[32]); + +/** + * @brief init_initiator_midpath_fcoe_task - Initializes FCoE task context for + * midpath/unsolicited task types and init fcoe_sqe + * + * @param task_params - Pointer to task parameters struct + * @param mid_path_fc_header - FC header + * @param tx_sgl_task_params - Pointer to Tx SGL task params + * @param rx_sgl_task_params - Pointer to Rx SGL task params + * @param fw_to_place_fc_header - Indication if the FW will place the FC header + * in addition to the data arrives. + */ +int init_initiator_midpath_unsolicited_fcoe_task( + struct fcoe_task_params *task_params, + struct fcoe_tx_mid_path_params *mid_path_fc_header, + struct scsi_sgl_task_params *tx_sgl_task_params, + struct scsi_sgl_task_params *rx_sgl_task_params, + u8 fw_to_place_fc_header); + +/** + * @brief init_initiator_abort_fcoe_task - Initializes FCoE task context for + * abort task types and init fcoe_sqe + * + * @param task_params - Pointer to task parameters struct + */ +int init_initiator_abort_fcoe_task(struct fcoe_task_params *task_params); + +/** + * @brief init_initiator_cleanup_fcoe_task - Initializes FCoE task context for + * cleanup task types and init fcoe_sqe + * + * + * @param task_params - Pointer to task parameters struct + */ +int init_initiator_cleanup_fcoe_task(struct fcoe_task_params *task_params); + +/** + * @brief init_initiator_cleanup_fcoe_task - Initializes FCoE task context for + * sequence recovery task types and init fcoe_sqe + * + * + * @param task_params - Pointer to task parameters struct + * @param desired_offset - The desired offest the task will be re-sent from + */ +int init_initiator_sequence_recovery_fcoe_task( + struct fcoe_task_params *task_params, + u32 desired_offset); +#endif diff --git a/drivers/scsi/qedf/drv_scsi_fw_funcs.c b/drivers/scsi/qedf/drv_scsi_fw_funcs.c new file mode 100644 index 000000000000..11e0cc082ec0 --- /dev/null +++ b/drivers/scsi/qedf/drv_scsi_fw_funcs.c @@ -0,0 +1,44 @@ +/* QLogic FCoE Offload Driver + * Copyright (c) 2016 Cavium Inc. + * + * This software is available under the terms of the GNU General Public License + * (GPL) Version 2, available from the file COPYING in the main directory of + * this source tree. + */ +#include "drv_scsi_fw_funcs.h" + +#define SCSI_NUM_SGES_IN_CACHE 0x4 + +bool scsi_is_slow_sgl(u16 num_sges, bool small_mid_sge) +{ + return (num_sges > SCSI_NUM_SGES_SLOW_SGL_THR && small_mid_sge); +} + +void init_scsi_sgl_context(struct scsi_sgl_params *ctx_sgl_params, + struct scsi_cached_sges *ctx_data_desc, + struct scsi_sgl_task_params *sgl_task_params) +{ + /* no need to check for sgl_task_params->sgl validity */ + u8 num_sges_to_init = sgl_task_params->num_sges > + SCSI_NUM_SGES_IN_CACHE ? SCSI_NUM_SGES_IN_CACHE : + sgl_task_params->num_sges; + u8 sge_index; + u32 val; + + val = cpu_to_le32(sgl_task_params->sgl_phys_addr.lo); + ctx_sgl_params->sgl_addr.lo = val; + val = cpu_to_le32(sgl_task_params->sgl_phys_addr.hi); + ctx_sgl_params->sgl_addr.hi = val; + val = cpu_to_le32(sgl_task_params->total_buffer_size); + ctx_sgl_params->sgl_total_length = val; + ctx_sgl_params->sgl_num_sges = cpu_to_le16(sgl_task_params->num_sges); + + for (sge_index = 0; sge_index < num_sges_to_init; sge_index++) { + val = cpu_to_le32(sgl_task_params->sgl[sge_index].sge_addr.lo); + ctx_data_desc->sge[sge_index].sge_addr.lo = val; + val = cpu_to_le32(sgl_task_params->sgl[sge_index].sge_addr.hi); + ctx_data_desc->sge[sge_index].sge_addr.hi = val; + val = cpu_to_le32(sgl_task_params->sgl[sge_index].sge_len); + ctx_data_desc->sge[sge_index].sge_len = val; + } +} diff --git a/drivers/scsi/qedf/drv_scsi_fw_funcs.h b/drivers/scsi/qedf/drv_scsi_fw_funcs.h new file mode 100644 index 000000000000..9cb45410bc45 --- /dev/null +++ b/drivers/scsi/qedf/drv_scsi_fw_funcs.h @@ -0,0 +1,85 @@ +/* QLogic FCoE Offload Driver + * Copyright (c) 2016 Cavium Inc. + * + * This software is available under the terms of the GNU General Public License + * (GPL) Version 2, available from the file COPYING in the main directory of + * this source tree. + */ +#ifndef _SCSI_FW_FUNCS_H +#define _SCSI_FW_FUNCS_H +#include <linux/qed/common_hsi.h> +#include <linux/qed/storage_common.h> +#include <linux/qed/fcoe_common.h> + +struct scsi_sgl_task_params { + struct scsi_sge *sgl; + struct regpair sgl_phys_addr; + u32 total_buffer_size; + u16 num_sges; + + /* true if SGL contains a small (< 4KB) SGE in middle(not 1st or last) + * -> relevant for tx only + */ + bool small_mid_sge; +}; + +struct scsi_dif_task_params { + u32 initial_ref_tag; + bool initial_ref_tag_is_valid; + u16 application_tag; + u16 application_tag_mask; + u16 dif_block_size_log; + bool dif_on_network; + bool dif_on_host; + u8 host_guard_type; + u8 protection_type; + u8 ref_tag_mask; + bool crc_seed; + + /* Enable Connection error upon DIF error (segments with DIF errors are + * dropped) + */ + bool tx_dif_conn_err_en; + bool ignore_app_tag; + bool keep_ref_tag_const; + bool validate_guard; + bool validate_app_tag; + bool validate_ref_tag; + bool forward_guard; + bool forward_app_tag; + bool forward_ref_tag; + bool forward_app_tag_with_mask; + bool forward_ref_tag_with_mask; +}; + +struct scsi_initiator_cmd_params { + /* for cdb_size > default CDB size (extended CDB > 16 bytes) -> + * pointer to the CDB buffer SGE + */ + struct scsi_sge extended_cdb_sge; + + /* Physical address of sense data buffer for sense data - 256B buffer */ + struct regpair sense_data_buffer_phys_addr; +}; + +/** + * @brief scsi_is_slow_sgl - checks for slow SGL + * + * @param num_sges - number of sges in SGL + * @param small_mid_sge - True is the SGL contains an SGE which is smaller than + * 4KB and its not the 1st or last SGE in the SGL + */ +bool scsi_is_slow_sgl(u16 num_sges, bool small_mid_sge); + +/** + * @brief init_scsi_sgl_context - initializes SGL task context + * + * @param sgl_params - SGL context parameters to initialize (output parameter) + * @param data_desc - context struct containing SGEs array to set (output + * parameter) + * @param sgl_task_params - SGL parameters (input) + */ +void init_scsi_sgl_context(struct scsi_sgl_params *sgl_params, + struct scsi_cached_sges *ctx_data_desc, + struct scsi_sgl_task_params *sgl_task_params); +#endif diff --git a/drivers/scsi/qedf/qedf.h b/drivers/scsi/qedf/qedf.h index 96346a1b1515..40aeb6bb96a2 100644 --- a/drivers/scsi/qedf/qedf.h +++ b/drivers/scsi/qedf/qedf.h @@ -26,6 +26,7 @@ #include <linux/qed/qed_ll2_if.h> #include "qedf_version.h" #include "qedf_dbg.h" +#include "drv_fcoe_fw_funcs.h" /* Helpers to extract upper and lower 32-bits of pointer */ #define U64_HI(val) ((u32)(((u64)(val)) >> 32)) @@ -59,19 +60,17 @@ #define UPSTREAM_KEEP 1 struct qedf_mp_req { - uint8_t tm_flags; - uint32_t req_len; void *req_buf; dma_addr_t req_buf_dma; - struct fcoe_sge *mp_req_bd; + struct scsi_sge *mp_req_bd; dma_addr_t mp_req_bd_dma; struct fc_frame_header req_fc_hdr; uint32_t resp_len; void *resp_buf; dma_addr_t resp_buf_dma; - struct fcoe_sge *mp_resp_bd; + struct scsi_sge *mp_resp_bd; dma_addr_t mp_resp_bd_dma; struct fc_frame_header resp_fc_hdr; }; @@ -119,6 +118,7 @@ struct qedf_ioreq { #define QEDF_CMD_IN_CLEANUP 0x2 #define QEDF_CMD_SRR_SENT 0x3 u8 io_req_flags; + uint8_t tm_flags; struct qedf_rport *fcport; unsigned long flags; enum qedf_ioreq_event event; @@ -130,6 +130,8 @@ struct qedf_ioreq { struct completion tm_done; struct completion abts_done; struct fcoe_task_context *task; + struct fcoe_task_params *task_params; + struct scsi_sgl_task_params *sgl_task_params; int idx; /* * Need to allocate enough room for both sense data and FCP response data @@ -199,8 +201,8 @@ struct qedf_rport { dma_addr_t sq_pbl_dma; u32 sq_pbl_size; u32 sid; -#define QEDF_RPORT_TYPE_DISK 1 -#define QEDF_RPORT_TYPE_TAPE 2 +#define QEDF_RPORT_TYPE_DISK 0 +#define QEDF_RPORT_TYPE_TAPE 1 uint dev_type; /* Disk or tape */ struct list_head peers; }; @@ -391,7 +393,7 @@ struct qedf_ctx { struct io_bdt { struct qedf_ioreq *io_req; - struct fcoe_sge *bd_tbl; + struct scsi_sge *bd_tbl; dma_addr_t bd_tbl_dma; u16 bd_valid; }; @@ -400,7 +402,7 @@ struct qedf_cmd_mgr { struct qedf_ctx *qedf; u16 idx; struct io_bdt **io_bdt_pool; -#define FCOE_PARAMS_NUM_TASKS 4096 +#define FCOE_PARAMS_NUM_TASKS 2048 struct qedf_ioreq cmds[FCOE_PARAMS_NUM_TASKS]; spinlock_t lock; atomic_t free_list_cnt; @@ -465,9 +467,8 @@ extern void qedf_cmd_timer_set(struct qedf_ctx *qedf, struct qedf_ioreq *io_req, unsigned int timer_msec); extern int qedf_init_mp_req(struct qedf_ioreq *io_req); extern void qedf_init_mp_task(struct qedf_ioreq *io_req, - struct fcoe_task_context *task_ctx); -extern void qedf_add_to_sq(struct qedf_rport *fcport, u16 xid, - u32 ptu_invalidate, enum fcoe_task_type req_type, u32 offset); + struct fcoe_task_context *task_ctx, struct fcoe_wqe *wqe); +extern u16 qedf_get_sqe_idx(struct qedf_rport *fcport); extern void qedf_ring_doorbell(struct qedf_rport *fcport); extern void qedf_process_els_compl(struct qedf_ctx *qedf, struct fcoe_cqe *cqe, struct qedf_ioreq *els_req); diff --git a/drivers/scsi/qedf/qedf_dbg.h b/drivers/scsi/qedf/qedf_dbg.h index 23bd70628a2f..7d173f48a81e 100644 --- a/drivers/scsi/qedf/qedf_dbg.h +++ b/drivers/scsi/qedf/qedf_dbg.h @@ -81,14 +81,17 @@ struct qedf_dbg_ctx { #define QEDF_INFO(pdev, level, fmt, ...) \ qedf_dbg_info(pdev, __func__, __LINE__, level, fmt, \ ## __VA_ARGS__) - -extern void qedf_dbg_err(struct qedf_dbg_ctx *qedf, const char *func, u32 line, +__printf(4, 5) +void qedf_dbg_err(struct qedf_dbg_ctx *qedf, const char *func, u32 line, const char *fmt, ...); -extern void qedf_dbg_warn(struct qedf_dbg_ctx *qedf, const char *func, u32 line, +__printf(4, 5) +void qedf_dbg_warn(struct qedf_dbg_ctx *qedf, const char *func, u32 line, const char *, ...); -extern void qedf_dbg_notice(struct qedf_dbg_ctx *qedf, const char *func, +__printf(4, 5) +void qedf_dbg_notice(struct qedf_dbg_ctx *qedf, const char *func, u32 line, const char *, ...); -extern void qedf_dbg_info(struct qedf_dbg_ctx *qedf, const char *func, u32 line, +__printf(5, 6) +void qedf_dbg_info(struct qedf_dbg_ctx *qedf, const char *func, u32 line, u32 info, const char *fmt, ...); /* GRC Dump related defines */ diff --git a/drivers/scsi/qedf/qedf_els.c b/drivers/scsi/qedf/qedf_els.c index 59f3e5c73a13..c505d41f6dc8 100644 --- a/drivers/scsi/qedf/qedf_els.c +++ b/drivers/scsi/qedf/qedf_els.c @@ -25,6 +25,9 @@ static int qedf_initiate_els(struct qedf_rport *fcport, unsigned int op, uint16_t xid; uint32_t start_time = jiffies / HZ; uint32_t current_time; + struct fcoe_wqe *sqe; + unsigned long flags; + u16 sqe_idx; QEDF_INFO(&(qedf->dbg_ctx), QEDF_LOG_ELS, "Sending ELS\n"); @@ -113,20 +116,25 @@ retry_els: /* Obtain exchange id */ xid = els_req->xid; + spin_lock_irqsave(&fcport->rport_lock, flags); + + sqe_idx = qedf_get_sqe_idx(fcport); + sqe = &fcport->sq[sqe_idx]; + memset(sqe, 0, sizeof(struct fcoe_wqe)); + /* Initialize task context for this IO request */ task = qedf_get_task_mem(&qedf->tasks, xid); - qedf_init_mp_task(els_req, task); + qedf_init_mp_task(els_req, task, sqe); /* Put timer on original I/O request */ if (timer_msec) qedf_cmd_timer_set(qedf, els_req, timer_msec); - qedf_add_to_sq(fcport, xid, 0, FCOE_TASK_TYPE_MIDPATH, 0); - /* Ring doorbell */ QEDF_INFO(&(qedf->dbg_ctx), QEDF_LOG_ELS, "Ringing doorbell for ELS " "req\n"); qedf_ring_doorbell(fcport); + spin_unlock_irqrestore(&fcport->rport_lock, flags); els_err: return rc; } @@ -604,6 +612,8 @@ static void qedf_initiate_seq_cleanup(struct qedf_ioreq *orig_io_req, struct qedf_rport *fcport; unsigned long flags; struct qedf_els_cb_arg *cb_arg; + struct fcoe_wqe *sqe; + u16 sqe_idx; fcport = orig_io_req->fcport; @@ -631,8 +641,13 @@ static void qedf_initiate_seq_cleanup(struct qedf_ioreq *orig_io_req, spin_lock_irqsave(&fcport->rport_lock, flags); - qedf_add_to_sq(fcport, orig_io_req->xid, 0, - FCOE_TASK_TYPE_SEQUENCE_CLEANUP, offset); + sqe_idx = qedf_get_sqe_idx(fcport); + sqe = &fcport->sq[sqe_idx]; + memset(sqe, 0, sizeof(struct fcoe_wqe)); + orig_io_req->task_params->sqe = sqe; + + init_initiator_sequence_recovery_fcoe_task(orig_io_req->task_params, + offset); qedf_ring_doorbell(fcport); spin_unlock_irqrestore(&fcport->rport_lock, flags); diff --git a/drivers/scsi/qedf/qedf_fip.c b/drivers/scsi/qedf/qedf_fip.c index 868d423380d1..ed58b9104f58 100644 --- a/drivers/scsi/qedf/qedf_fip.c +++ b/drivers/scsi/qedf/qedf_fip.c @@ -203,7 +203,7 @@ void qedf_fip_recv(struct qedf_ctx *qedf, struct sk_buff *skb) case FIP_DT_MAC: mp = (struct fip_mac_desc *)desc; QEDF_INFO(&(qedf->dbg_ctx), QEDF_LOG_LL2, - "fd_mac=%pM.\n", __func__, mp->fd_mac); + "fd_mac=%pM\n", mp->fd_mac); ether_addr_copy(cvl_mac, mp->fd_mac); break; case FIP_DT_NAME: diff --git a/drivers/scsi/qedf/qedf_io.c b/drivers/scsi/qedf/qedf_io.c index ee0dcf9d3aba..1d7f90d0adc1 100644 --- a/drivers/scsi/qedf/qedf_io.c +++ b/drivers/scsi/qedf/qedf_io.c @@ -96,7 +96,7 @@ void qedf_cmd_mgr_free(struct qedf_cmd_mgr *cmgr) if (!cmgr->io_bdt_pool) goto free_cmd_pool; - bd_tbl_sz = QEDF_MAX_BDS_PER_CMD * sizeof(struct fcoe_sge); + bd_tbl_sz = QEDF_MAX_BDS_PER_CMD * sizeof(struct scsi_sge); for (i = 0; i < num_ios; i++) { bdt_info = cmgr->io_bdt_pool[i]; if (bdt_info->bd_tbl) { @@ -119,6 +119,8 @@ free_cmd_pool: for (i = 0; i < num_ios; i++) { io_req = &cmgr->cmds[i]; + kfree(io_req->sgl_task_params); + kfree(io_req->task_params); /* Make sure we free per command sense buffer */ if (io_req->sense_buffer) dma_free_coherent(&qedf->pdev->dev, @@ -178,7 +180,7 @@ struct qedf_cmd_mgr *qedf_cmd_mgr_alloc(struct qedf_ctx *qedf) spin_lock_init(&cmgr->lock); /* - * Initialize list of qedf_ioreq. + * Initialize I/O request fields. */ xid = QEDF_MIN_XID; @@ -196,6 +198,29 @@ struct qedf_cmd_mgr *qedf_cmd_mgr_alloc(struct qedf_ctx *qedf) GFP_KERNEL); if (!io_req->sense_buffer) goto mem_err; + + /* Allocate task parameters to pass to f/w init funcions */ + io_req->task_params = kzalloc(sizeof(*io_req->task_params), + GFP_KERNEL); + if (!io_req->task_params) { + QEDF_ERR(&(qedf->dbg_ctx), + "Failed to allocate task_params for xid=0x%x\n", + i); + goto mem_err; + } + + /* + * Allocate scatter/gather list info to pass to f/w init + * functions. + */ + io_req->sgl_task_params = kzalloc( + sizeof(struct scsi_sgl_task_params), GFP_KERNEL); + if (!io_req->sgl_task_params) { + QEDF_ERR(&(qedf->dbg_ctx), + "Failed to allocate sgl_task_params for xid=0x%x\n", + i); + goto mem_err; + } } /* Allocate pool of io_bdts - one for each qedf_ioreq */ @@ -211,8 +236,8 @@ struct qedf_cmd_mgr *qedf_cmd_mgr_alloc(struct qedf_ctx *qedf) cmgr->io_bdt_pool[i] = kmalloc(sizeof(struct io_bdt), GFP_KERNEL); if (!cmgr->io_bdt_pool[i]) { - QEDF_WARN(&(qedf->dbg_ctx), "Failed to alloc " - "io_bdt_pool[%d].\n", i); + QEDF_WARN(&(qedf->dbg_ctx), + "Failed to alloc io_bdt_pool[%d].\n", i); goto mem_err; } } @@ -220,11 +245,11 @@ struct qedf_cmd_mgr *qedf_cmd_mgr_alloc(struct qedf_ctx *qedf) for (i = 0; i < num_ios; i++) { bdt_info = cmgr->io_bdt_pool[i]; bdt_info->bd_tbl = dma_alloc_coherent(&qedf->pdev->dev, - QEDF_MAX_BDS_PER_CMD * sizeof(struct fcoe_sge), + QEDF_MAX_BDS_PER_CMD * sizeof(struct scsi_sge), &bdt_info->bd_tbl_dma, GFP_KERNEL); if (!bdt_info->bd_tbl) { - QEDF_WARN(&(qedf->dbg_ctx), "Failed to alloc " - "bdt_tbl[%d].\n", i); + QEDF_WARN(&(qedf->dbg_ctx), + "Failed to alloc bdt_tbl[%d].\n", i); goto mem_err; } } @@ -318,6 +343,7 @@ struct qedf_ioreq *qedf_alloc_cmd(struct qedf_rport *fcport, u8 cmd_type) } bd_tbl->io_req = io_req; io_req->cmd_type = cmd_type; + io_req->tm_flags = 0; /* Reset sequence offset data */ io_req->rx_buf_off = 0; @@ -336,10 +362,9 @@ static void qedf_free_mp_resc(struct qedf_ioreq *io_req) { struct qedf_mp_req *mp_req = &(io_req->mp_req); struct qedf_ctx *qedf = io_req->fcport->qedf; - uint64_t sz = sizeof(struct fcoe_sge); + uint64_t sz = sizeof(struct scsi_sge); /* clear tm flags */ - mp_req->tm_flags = 0; if (mp_req->mp_req_bd) { dma_free_coherent(&qedf->pdev->dev, sz, mp_req->mp_req_bd, mp_req->mp_req_bd_dma); @@ -387,7 +412,7 @@ void qedf_release_cmd(struct kref *ref) static int qedf_split_bd(struct qedf_ioreq *io_req, u64 addr, int sg_len, int bd_index) { - struct fcoe_sge *bd = io_req->bd_tbl->bd_tbl; + struct scsi_sge *bd = io_req->bd_tbl->bd_tbl; int frag_size, sg_frags; sg_frags = 0; @@ -398,7 +423,7 @@ static int qedf_split_bd(struct qedf_ioreq *io_req, u64 addr, int sg_len, frag_size = sg_len; bd[bd_index + sg_frags].sge_addr.lo = U64_LO(addr); bd[bd_index + sg_frags].sge_addr.hi = U64_HI(addr); - bd[bd_index + sg_frags].size = (uint16_t)frag_size; + bd[bd_index + sg_frags].sge_len = (uint16_t)frag_size; addr += (u64)frag_size; sg_frags++; @@ -413,7 +438,7 @@ static int qedf_map_sg(struct qedf_ioreq *io_req) struct Scsi_Host *host = sc->device->host; struct fc_lport *lport = shost_priv(host); struct qedf_ctx *qedf = lport_priv(lport); - struct fcoe_sge *bd = io_req->bd_tbl->bd_tbl; + struct scsi_sge *bd = io_req->bd_tbl->bd_tbl; struct scatterlist *sg; int byte_count = 0; int sg_count = 0; @@ -439,7 +464,7 @@ static int qedf_map_sg(struct qedf_ioreq *io_req) bd[bd_count].sge_addr.lo = (addr & 0xffffffff); bd[bd_count].sge_addr.hi = (addr >> 32); - bd[bd_count].size = (u16)sg_len; + bd[bd_count].sge_len = (u16)sg_len; return ++bd_count; } @@ -480,7 +505,7 @@ static int qedf_map_sg(struct qedf_ioreq *io_req) sg_frags = 1; bd[bd_count].sge_addr.lo = U64_LO(addr); bd[bd_count].sge_addr.hi = U64_HI(addr); - bd[bd_count].size = (uint16_t)sg_len; + bd[bd_count].sge_len = (uint16_t)sg_len; } bd_count += sg_frags; @@ -498,7 +523,7 @@ static int qedf_map_sg(struct qedf_ioreq *io_req) static int qedf_build_bd_list_from_sg(struct qedf_ioreq *io_req) { struct scsi_cmnd *sc = io_req->sc_cmd; - struct fcoe_sge *bd = io_req->bd_tbl->bd_tbl; + struct scsi_sge *bd = io_req->bd_tbl->bd_tbl; int bd_count; if (scsi_sg_count(sc)) { @@ -508,7 +533,7 @@ static int qedf_build_bd_list_from_sg(struct qedf_ioreq *io_req) } else { bd_count = 0; bd[0].sge_addr.lo = bd[0].sge_addr.hi = 0; - bd[0].size = 0; + bd[0].sge_len = 0; } io_req->bd_tbl->bd_valid = bd_count; @@ -529,430 +554,223 @@ static void qedf_build_fcp_cmnd(struct qedf_ioreq *io_req, /* 4 bytes: flag info */ fcp_cmnd->fc_pri_ta = 0; - fcp_cmnd->fc_tm_flags = io_req->mp_req.tm_flags; + fcp_cmnd->fc_tm_flags = io_req->tm_flags; fcp_cmnd->fc_flags = io_req->io_req_flags; fcp_cmnd->fc_cmdref = 0; /* Populate data direction */ - if (sc_cmd->sc_data_direction == DMA_TO_DEVICE) - fcp_cmnd->fc_flags |= FCP_CFL_WRDATA; - else if (sc_cmd->sc_data_direction == DMA_FROM_DEVICE) + if (io_req->cmd_type == QEDF_TASK_MGMT_CMD) { fcp_cmnd->fc_flags |= FCP_CFL_RDDATA; + } else { + if (sc_cmd->sc_data_direction == DMA_TO_DEVICE) + fcp_cmnd->fc_flags |= FCP_CFL_WRDATA; + else if (sc_cmd->sc_data_direction == DMA_FROM_DEVICE) + fcp_cmnd->fc_flags |= FCP_CFL_RDDATA; + } fcp_cmnd->fc_pri_ta = FCP_PTA_SIMPLE; /* 16 bytes: CDB information */ - memcpy(fcp_cmnd->fc_cdb, sc_cmd->cmnd, sc_cmd->cmd_len); + if (io_req->cmd_type != QEDF_TASK_MGMT_CMD) + memcpy(fcp_cmnd->fc_cdb, sc_cmd->cmnd, sc_cmd->cmd_len); /* 4 bytes: FCP data length */ fcp_cmnd->fc_dl = htonl(io_req->data_xfer_len); - } static void qedf_init_task(struct qedf_rport *fcport, struct fc_lport *lport, - struct qedf_ioreq *io_req, u32 *ptu_invalidate, - struct fcoe_task_context *task_ctx) + struct qedf_ioreq *io_req, struct fcoe_task_context *task_ctx, + struct fcoe_wqe *sqe) { enum fcoe_task_type task_type; struct scsi_cmnd *sc_cmd = io_req->sc_cmd; struct io_bdt *bd_tbl = io_req->bd_tbl; - union fcoe_data_desc_ctx *data_desc; - u32 *fcp_cmnd; + u8 fcp_cmnd[32]; u32 tmp_fcp_cmnd[8]; - int cnt, i; - int bd_count; + int bd_count = 0; struct qedf_ctx *qedf = fcport->qedf; uint16_t cq_idx = smp_processor_id() % qedf->num_queues; - u8 tmp_sgl_mode = 0; - u8 mst_sgl_mode = 0; + struct regpair sense_data_buffer_phys_addr; + u32 tx_io_size = 0; + u32 rx_io_size = 0; + int i, cnt; - memset(task_ctx, 0, sizeof(struct fcoe_task_context)); + /* Note init_initiator_rw_fcoe_task memsets the task context */ io_req->task = task_ctx; + memset(task_ctx, 0, sizeof(struct fcoe_task_context)); + memset(io_req->task_params, 0, sizeof(struct fcoe_task_params)); + memset(io_req->sgl_task_params, 0, sizeof(struct scsi_sgl_task_params)); - if (sc_cmd->sc_data_direction == DMA_TO_DEVICE) - task_type = FCOE_TASK_TYPE_WRITE_INITIATOR; - else + /* Set task type bassed on DMA directio of command */ + if (io_req->cmd_type == QEDF_TASK_MGMT_CMD) { task_type = FCOE_TASK_TYPE_READ_INITIATOR; - - /* Y Storm context */ - task_ctx->ystorm_st_context.expect_first_xfer = 1; - task_ctx->ystorm_st_context.data_2_trns_rem = io_req->data_xfer_len; - /* Check if this is required */ - task_ctx->ystorm_st_context.ox_id = io_req->xid; - task_ctx->ystorm_st_context.task_rety_identifier = - io_req->task_retry_identifier; - - /* T Storm ag context */ - SET_FIELD(task_ctx->tstorm_ag_context.flags0, - TSTORM_FCOE_TASK_AG_CTX_CONNECTION_TYPE, PROTOCOLID_FCOE); - task_ctx->tstorm_ag_context.icid = (u16)fcport->fw_cid; - - /* T Storm st context */ - SET_FIELD(task_ctx->tstorm_st_context.read_write.flags, - FCOE_TSTORM_FCOE_TASK_ST_CTX_READ_WRITE_EXP_FIRST_FRAME, - 1); - task_ctx->tstorm_st_context.read_write.rx_id = 0xffff; - - task_ctx->tstorm_st_context.read_only.dev_type = - FCOE_TASK_DEV_TYPE_DISK; - task_ctx->tstorm_st_context.read_only.conf_supported = 0; - task_ctx->tstorm_st_context.read_only.cid = fcport->fw_cid; - - /* Completion queue for response. */ - task_ctx->tstorm_st_context.read_only.glbl_q_num = cq_idx; - task_ctx->tstorm_st_context.read_only.fcp_cmd_trns_size = - io_req->data_xfer_len; - task_ctx->tstorm_st_context.read_write.e_d_tov_exp_timeout_val = - lport->e_d_tov; - - task_ctx->ustorm_ag_context.global_cq_num = cq_idx; - io_req->fp_idx = cq_idx; - - bd_count = bd_tbl->bd_valid; - if (task_type == FCOE_TASK_TYPE_WRITE_INITIATOR) { - /* Setup WRITE task */ - struct fcoe_sge *fcoe_bd_tbl = bd_tbl->bd_tbl; - - task_ctx->ystorm_st_context.task_type = - FCOE_TASK_TYPE_WRITE_INITIATOR; - data_desc = &task_ctx->ystorm_st_context.data_desc; - - if (io_req->use_slowpath) { - SET_FIELD(task_ctx->ystorm_st_context.sgl_mode, - YSTORM_FCOE_TASK_ST_CTX_TX_SGL_MODE, - FCOE_SLOW_SGL); - data_desc->slow.base_sgl_addr.lo = - U64_LO(bd_tbl->bd_tbl_dma); - data_desc->slow.base_sgl_addr.hi = - U64_HI(bd_tbl->bd_tbl_dma); - data_desc->slow.remainder_num_sges = bd_count; - data_desc->slow.curr_sge_off = 0; - data_desc->slow.curr_sgl_index = 0; - qedf->slow_sge_ios++; - io_req->sge_type = QEDF_IOREQ_SLOW_SGE; - } else { - SET_FIELD(task_ctx->ystorm_st_context.sgl_mode, - YSTORM_FCOE_TASK_ST_CTX_TX_SGL_MODE, - (bd_count <= 4) ? (enum fcoe_sgl_mode)bd_count : - FCOE_MUL_FAST_SGES); - - if (bd_count == 1) { - data_desc->single_sge.sge_addr.lo = - fcoe_bd_tbl->sge_addr.lo; - data_desc->single_sge.sge_addr.hi = - fcoe_bd_tbl->sge_addr.hi; - data_desc->single_sge.size = - fcoe_bd_tbl->size; - data_desc->single_sge.is_valid_sge = 0; - qedf->single_sge_ios++; - io_req->sge_type = QEDF_IOREQ_SINGLE_SGE; - } else { - data_desc->fast.sgl_start_addr.lo = - U64_LO(bd_tbl->bd_tbl_dma); - data_desc->fast.sgl_start_addr.hi = - U64_HI(bd_tbl->bd_tbl_dma); - data_desc->fast.sgl_byte_offset = - data_desc->fast.sgl_start_addr.lo & - (QEDF_PAGE_SIZE - 1); - if (data_desc->fast.sgl_byte_offset > 0) - QEDF_ERR(&(qedf->dbg_ctx), - "byte_offset=%u for xid=0x%x.\n", - io_req->xid, - data_desc->fast.sgl_byte_offset); - data_desc->fast.task_reuse_cnt = - io_req->reuse_count; - io_req->reuse_count++; - if (io_req->reuse_count == QEDF_MAX_REUSE) { - *ptu_invalidate = 1; - io_req->reuse_count = 0; - } - qedf->fast_sge_ios++; - io_req->sge_type = QEDF_IOREQ_FAST_SGE; - } - } - - /* T Storm context */ - task_ctx->tstorm_st_context.read_only.task_type = - FCOE_TASK_TYPE_WRITE_INITIATOR; - - /* M Storm context */ - tmp_sgl_mode = GET_FIELD(task_ctx->ystorm_st_context.sgl_mode, - YSTORM_FCOE_TASK_ST_CTX_TX_SGL_MODE); - SET_FIELD(task_ctx->mstorm_st_context.non_fp.tx_rx_sgl_mode, - FCOE_MSTORM_FCOE_TASK_ST_CTX_NON_FP_TX_SGL_MODE, - tmp_sgl_mode); - } else { - /* Setup READ task */ - - /* M Storm context */ - struct fcoe_sge *fcoe_bd_tbl = bd_tbl->bd_tbl; - - data_desc = &task_ctx->mstorm_st_context.fp.data_desc; - task_ctx->mstorm_st_context.fp.data_2_trns_rem = - io_req->data_xfer_len; - - if (io_req->use_slowpath) { - SET_FIELD( - task_ctx->mstorm_st_context.non_fp.tx_rx_sgl_mode, - FCOE_MSTORM_FCOE_TASK_ST_CTX_NON_FP_RX_SGL_MODE, - FCOE_SLOW_SGL); - data_desc->slow.base_sgl_addr.lo = - U64_LO(bd_tbl->bd_tbl_dma); - data_desc->slow.base_sgl_addr.hi = - U64_HI(bd_tbl->bd_tbl_dma); - data_desc->slow.remainder_num_sges = - bd_count; - data_desc->slow.curr_sge_off = 0; - data_desc->slow.curr_sgl_index = 0; - qedf->slow_sge_ios++; - io_req->sge_type = QEDF_IOREQ_SLOW_SGE; + if (sc_cmd->sc_data_direction == DMA_TO_DEVICE) { + task_type = FCOE_TASK_TYPE_WRITE_INITIATOR; + tx_io_size = io_req->data_xfer_len; } else { - SET_FIELD( - task_ctx->mstorm_st_context.non_fp.tx_rx_sgl_mode, - FCOE_MSTORM_FCOE_TASK_ST_CTX_NON_FP_RX_SGL_MODE, - (bd_count <= 4) ? (enum fcoe_sgl_mode)bd_count : - FCOE_MUL_FAST_SGES); - - if (bd_count == 1) { - data_desc->single_sge.sge_addr.lo = - fcoe_bd_tbl->sge_addr.lo; - data_desc->single_sge.sge_addr.hi = - fcoe_bd_tbl->sge_addr.hi; - data_desc->single_sge.size = - fcoe_bd_tbl->size; - data_desc->single_sge.is_valid_sge = 0; - qedf->single_sge_ios++; - io_req->sge_type = QEDF_IOREQ_SINGLE_SGE; - } else { - data_desc->fast.sgl_start_addr.lo = - U64_LO(bd_tbl->bd_tbl_dma); - data_desc->fast.sgl_start_addr.hi = - U64_HI(bd_tbl->bd_tbl_dma); - data_desc->fast.sgl_byte_offset = 0; - data_desc->fast.task_reuse_cnt = - io_req->reuse_count; - io_req->reuse_count++; - if (io_req->reuse_count == QEDF_MAX_REUSE) { - *ptu_invalidate = 1; - io_req->reuse_count = 0; - } - qedf->fast_sge_ios++; - io_req->sge_type = QEDF_IOREQ_FAST_SGE; - } + task_type = FCOE_TASK_TYPE_READ_INITIATOR; + rx_io_size = io_req->data_xfer_len; } - - /* Y Storm context */ - task_ctx->ystorm_st_context.expect_first_xfer = 0; - task_ctx->ystorm_st_context.task_type = - FCOE_TASK_TYPE_READ_INITIATOR; - - /* T Storm context */ - task_ctx->tstorm_st_context.read_only.task_type = - FCOE_TASK_TYPE_READ_INITIATOR; - mst_sgl_mode = GET_FIELD( - task_ctx->mstorm_st_context.non_fp.tx_rx_sgl_mode, - FCOE_MSTORM_FCOE_TASK_ST_CTX_NON_FP_RX_SGL_MODE); - SET_FIELD(task_ctx->tstorm_st_context.read_write.flags, - FCOE_TSTORM_FCOE_TASK_ST_CTX_READ_WRITE_RX_SGL_MODE, - mst_sgl_mode); } + /* Setup the fields for fcoe_task_params */ + io_req->task_params->context = task_ctx; + io_req->task_params->sqe = sqe; + io_req->task_params->task_type = task_type; + io_req->task_params->tx_io_size = tx_io_size; + io_req->task_params->rx_io_size = rx_io_size; + io_req->task_params->conn_cid = fcport->fw_cid; + io_req->task_params->itid = io_req->xid; + io_req->task_params->cq_rss_number = cq_idx; + io_req->task_params->is_tape_device = fcport->dev_type; + + /* Fill in information for scatter/gather list */ + if (io_req->cmd_type != QEDF_TASK_MGMT_CMD) { + bd_count = bd_tbl->bd_valid; + io_req->sgl_task_params->sgl = bd_tbl->bd_tbl; + io_req->sgl_task_params->sgl_phys_addr.lo = + U64_LO(bd_tbl->bd_tbl_dma); + io_req->sgl_task_params->sgl_phys_addr.hi = + U64_HI(bd_tbl->bd_tbl_dma); + io_req->sgl_task_params->num_sges = bd_count; + io_req->sgl_task_params->total_buffer_size = + scsi_bufflen(io_req->sc_cmd); + io_req->sgl_task_params->small_mid_sge = + io_req->use_slowpath; + } + + /* Fill in physical address of sense buffer */ + sense_data_buffer_phys_addr.lo = U64_LO(io_req->sense_buffer_dma); + sense_data_buffer_phys_addr.hi = U64_HI(io_req->sense_buffer_dma); + /* fill FCP_CMND IU */ - fcp_cmnd = (u32 *)task_ctx->ystorm_st_context.tx_info_union.fcp_cmd_payload.opaque; - qedf_build_fcp_cmnd(io_req, (struct fcp_cmnd *)&tmp_fcp_cmnd); + qedf_build_fcp_cmnd(io_req, (struct fcp_cmnd *)tmp_fcp_cmnd); /* Swap fcp_cmnd since FC is big endian */ cnt = sizeof(struct fcp_cmnd) / sizeof(u32); - for (i = 0; i < cnt; i++) { - *fcp_cmnd = cpu_to_be32(tmp_fcp_cmnd[i]); - fcp_cmnd++; + tmp_fcp_cmnd[i] = cpu_to_be32(tmp_fcp_cmnd[i]); + } + memcpy(fcp_cmnd, tmp_fcp_cmnd, sizeof(struct fcp_cmnd)); + + init_initiator_rw_fcoe_task(io_req->task_params, + io_req->sgl_task_params, + sense_data_buffer_phys_addr, + io_req->task_retry_identifier, fcp_cmnd); + + /* Increment SGL type counters */ + if (bd_count == 1) { + qedf->single_sge_ios++; + io_req->sge_type = QEDF_IOREQ_SINGLE_SGE; + } else if (io_req->use_slowpath) { + qedf->slow_sge_ios++; + io_req->sge_type = QEDF_IOREQ_SLOW_SGE; + } else { + qedf->fast_sge_ios++; + io_req->sge_type = QEDF_IOREQ_FAST_SGE; } - - /* M Storm context - Sense buffer */ - task_ctx->mstorm_st_context.non_fp.rsp_buf_addr.lo = - U64_LO(io_req->sense_buffer_dma); - task_ctx->mstorm_st_context.non_fp.rsp_buf_addr.hi = - U64_HI(io_req->sense_buffer_dma); } void qedf_init_mp_task(struct qedf_ioreq *io_req, - struct fcoe_task_context *task_ctx) + struct fcoe_task_context *task_ctx, struct fcoe_wqe *sqe) { struct qedf_mp_req *mp_req = &(io_req->mp_req); struct qedf_rport *fcport = io_req->fcport; struct qedf_ctx *qedf = io_req->fcport->qedf; struct fc_frame_header *fc_hdr; - enum fcoe_task_type task_type = 0; - union fcoe_data_desc_ctx *data_desc; + struct fcoe_tx_mid_path_params task_fc_hdr; + struct scsi_sgl_task_params tx_sgl_task_params; + struct scsi_sgl_task_params rx_sgl_task_params; - QEDF_INFO(&(qedf->dbg_ctx), QEDF_LOG_DISC, "Initializing MP task " - "for cmd_type = %d\n", io_req->cmd_type); + QEDF_INFO(&(qedf->dbg_ctx), QEDF_LOG_DISC, + "Initializing MP task for cmd_type=%d\n", + io_req->cmd_type); qedf->control_requests++; - /* Obtain task_type */ - if ((io_req->cmd_type == QEDF_TASK_MGMT_CMD) || - (io_req->cmd_type == QEDF_ELS)) { - task_type = FCOE_TASK_TYPE_MIDPATH; - } else if (io_req->cmd_type == QEDF_ABTS) { - task_type = FCOE_TASK_TYPE_ABTS; - } - + memset(&tx_sgl_task_params, 0, sizeof(struct scsi_sgl_task_params)); + memset(&rx_sgl_task_params, 0, sizeof(struct scsi_sgl_task_params)); memset(task_ctx, 0, sizeof(struct fcoe_task_context)); + memset(&task_fc_hdr, 0, sizeof(struct fcoe_tx_mid_path_params)); /* Setup the task from io_req for easy reference */ io_req->task = task_ctx; - QEDF_INFO(&(qedf->dbg_ctx), QEDF_LOG_DISC, "task type = %d\n", - task_type); - - /* YSTORM only */ - { - /* Initialize YSTORM task context */ - struct fcoe_tx_mid_path_params *task_fc_hdr = - &task_ctx->ystorm_st_context.tx_info_union.tx_params.mid_path; - memset(task_fc_hdr, 0, sizeof(struct fcoe_tx_mid_path_params)); - task_ctx->ystorm_st_context.task_rety_identifier = - io_req->task_retry_identifier; - - /* Init SGL parameters */ - if ((task_type == FCOE_TASK_TYPE_MIDPATH) || - (task_type == FCOE_TASK_TYPE_UNSOLICITED)) { - data_desc = &task_ctx->ystorm_st_context.data_desc; - data_desc->slow.base_sgl_addr.lo = - U64_LO(mp_req->mp_req_bd_dma); - data_desc->slow.base_sgl_addr.hi = - U64_HI(mp_req->mp_req_bd_dma); - data_desc->slow.remainder_num_sges = 1; - data_desc->slow.curr_sge_off = 0; - data_desc->slow.curr_sgl_index = 0; - } - - fc_hdr = &(mp_req->req_fc_hdr); - if (task_type == FCOE_TASK_TYPE_MIDPATH) { - fc_hdr->fh_ox_id = io_req->xid; - fc_hdr->fh_rx_id = htons(0xffff); - } else if (task_type == FCOE_TASK_TYPE_UNSOLICITED) { - fc_hdr->fh_rx_id = io_req->xid; - } + /* Setup the fields for fcoe_task_params */ + io_req->task_params->context = task_ctx; + io_req->task_params->sqe = sqe; + io_req->task_params->task_type = FCOE_TASK_TYPE_MIDPATH; + io_req->task_params->tx_io_size = io_req->data_xfer_len; + /* rx_io_size tells the f/w how large a response buffer we have */ + io_req->task_params->rx_io_size = PAGE_SIZE; + io_req->task_params->conn_cid = fcport->fw_cid; + io_req->task_params->itid = io_req->xid; + /* Return middle path commands on CQ 0 */ + io_req->task_params->cq_rss_number = 0; + io_req->task_params->is_tape_device = fcport->dev_type; + + fc_hdr = &(mp_req->req_fc_hdr); + /* Set OX_ID and RX_ID based on driver task id */ + fc_hdr->fh_ox_id = io_req->xid; + fc_hdr->fh_rx_id = htons(0xffff); + + /* Set up FC header information */ + task_fc_hdr.parameter = fc_hdr->fh_parm_offset; + task_fc_hdr.r_ctl = fc_hdr->fh_r_ctl; + task_fc_hdr.type = fc_hdr->fh_type; + task_fc_hdr.cs_ctl = fc_hdr->fh_cs_ctl; + task_fc_hdr.df_ctl = fc_hdr->fh_df_ctl; + task_fc_hdr.rx_id = fc_hdr->fh_rx_id; + task_fc_hdr.ox_id = fc_hdr->fh_ox_id; + + /* Set up s/g list parameters for request buffer */ + tx_sgl_task_params.sgl = mp_req->mp_req_bd; + tx_sgl_task_params.sgl_phys_addr.lo = U64_LO(mp_req->mp_req_bd_dma); + tx_sgl_task_params.sgl_phys_addr.hi = U64_HI(mp_req->mp_req_bd_dma); + tx_sgl_task_params.num_sges = 1; + /* Set PAGE_SIZE for now since sg element is that size ??? */ + tx_sgl_task_params.total_buffer_size = io_req->data_xfer_len; + tx_sgl_task_params.small_mid_sge = 0; + + /* Set up s/g list parameters for request buffer */ + rx_sgl_task_params.sgl = mp_req->mp_resp_bd; + rx_sgl_task_params.sgl_phys_addr.lo = U64_LO(mp_req->mp_resp_bd_dma); + rx_sgl_task_params.sgl_phys_addr.hi = U64_HI(mp_req->mp_resp_bd_dma); + rx_sgl_task_params.num_sges = 1; + /* Set PAGE_SIZE for now since sg element is that size ??? */ + rx_sgl_task_params.total_buffer_size = PAGE_SIZE; + rx_sgl_task_params.small_mid_sge = 0; - /* Fill FC Header into middle path buffer */ - task_fc_hdr->parameter = fc_hdr->fh_parm_offset; - task_fc_hdr->r_ctl = fc_hdr->fh_r_ctl; - task_fc_hdr->type = fc_hdr->fh_type; - task_fc_hdr->cs_ctl = fc_hdr->fh_cs_ctl; - task_fc_hdr->df_ctl = fc_hdr->fh_df_ctl; - task_fc_hdr->rx_id = fc_hdr->fh_rx_id; - task_fc_hdr->ox_id = fc_hdr->fh_ox_id; - - task_ctx->ystorm_st_context.data_2_trns_rem = - io_req->data_xfer_len; - task_ctx->ystorm_st_context.task_type = task_type; - } - - /* TSTORM ONLY */ - { - task_ctx->tstorm_ag_context.icid = (u16)fcport->fw_cid; - task_ctx->tstorm_st_context.read_only.cid = fcport->fw_cid; - /* Always send middle-path repsonses on CQ #0 */ - task_ctx->tstorm_st_context.read_only.glbl_q_num = 0; - io_req->fp_idx = 0; - SET_FIELD(task_ctx->tstorm_ag_context.flags0, - TSTORM_FCOE_TASK_AG_CTX_CONNECTION_TYPE, - PROTOCOLID_FCOE); - task_ctx->tstorm_st_context.read_only.task_type = task_type; - SET_FIELD(task_ctx->tstorm_st_context.read_write.flags, - FCOE_TSTORM_FCOE_TASK_ST_CTX_READ_WRITE_EXP_FIRST_FRAME, - 1); - task_ctx->tstorm_st_context.read_write.rx_id = 0xffff; - } - - /* MSTORM only */ - { - if (task_type == FCOE_TASK_TYPE_MIDPATH) { - /* Initialize task context */ - data_desc = &task_ctx->mstorm_st_context.fp.data_desc; - - /* Set cache sges address and length */ - data_desc->slow.base_sgl_addr.lo = - U64_LO(mp_req->mp_resp_bd_dma); - data_desc->slow.base_sgl_addr.hi = - U64_HI(mp_req->mp_resp_bd_dma); - data_desc->slow.remainder_num_sges = 1; - data_desc->slow.curr_sge_off = 0; - data_desc->slow.curr_sgl_index = 0; - /* - * Also need to fil in non-fastpath response address - * for middle path commands. - */ - task_ctx->mstorm_st_context.non_fp.rsp_buf_addr.lo = - U64_LO(mp_req->mp_resp_bd_dma); - task_ctx->mstorm_st_context.non_fp.rsp_buf_addr.hi = - U64_HI(mp_req->mp_resp_bd_dma); - } - } - - /* USTORM ONLY */ - { - task_ctx->ustorm_ag_context.global_cq_num = 0; - } + /* + * Last arg is 0 as previous code did not set that we wanted the + * fc header information. + */ + init_initiator_midpath_unsolicited_fcoe_task(io_req->task_params, + &task_fc_hdr, + &tx_sgl_task_params, + &rx_sgl_task_params, 0); - /* I/O stats. Middle path commands always use slow SGEs */ - qedf->slow_sge_ios++; - io_req->sge_type = QEDF_IOREQ_SLOW_SGE; + /* Midpath requests always consume 1 SGE */ + qedf->single_sge_ios++; } -void qedf_add_to_sq(struct qedf_rport *fcport, u16 xid, u32 ptu_invalidate, - enum fcoe_task_type req_type, u32 offset) +/* Presumed that fcport->rport_lock is held */ +u16 qedf_get_sqe_idx(struct qedf_rport *fcport) { - struct fcoe_wqe *sqe; uint16_t total_sqe = (fcport->sq_mem_size)/(sizeof(struct fcoe_wqe)); + u16 rval; - sqe = &fcport->sq[fcport->sq_prod_idx]; + rval = fcport->sq_prod_idx; + /* Adjust ring index */ fcport->sq_prod_idx++; fcport->fw_sq_prod_idx++; if (fcport->sq_prod_idx == total_sqe) fcport->sq_prod_idx = 0; - switch (req_type) { - case FCOE_TASK_TYPE_WRITE_INITIATOR: - case FCOE_TASK_TYPE_READ_INITIATOR: - SET_FIELD(sqe->flags, FCOE_WQE_REQ_TYPE, SEND_FCOE_CMD); - if (ptu_invalidate) - SET_FIELD(sqe->flags, FCOE_WQE_INVALIDATE_PTU, 1); - break; - case FCOE_TASK_TYPE_MIDPATH: - SET_FIELD(sqe->flags, FCOE_WQE_REQ_TYPE, SEND_FCOE_MIDPATH); - break; - case FCOE_TASK_TYPE_ABTS: - SET_FIELD(sqe->flags, FCOE_WQE_REQ_TYPE, - SEND_FCOE_ABTS_REQUEST); - break; - case FCOE_TASK_TYPE_EXCHANGE_CLEANUP: - SET_FIELD(sqe->flags, FCOE_WQE_REQ_TYPE, - FCOE_EXCHANGE_CLEANUP); - break; - case FCOE_TASK_TYPE_SEQUENCE_CLEANUP: - SET_FIELD(sqe->flags, FCOE_WQE_REQ_TYPE, - FCOE_SEQUENCE_RECOVERY); - /* NOTE: offset param only used for sequence recovery */ - sqe->additional_info_union.seq_rec_updated_offset = offset; - break; - case FCOE_TASK_TYPE_UNSOLICITED: - break; - default: - break; - } - - sqe->task_id = xid; - - /* Make sure SQ data is coherent */ - wmb(); - + return rval; } void qedf_ring_doorbell(struct qedf_rport *fcport) @@ -1029,7 +847,8 @@ int qedf_post_io_req(struct qedf_rport *fcport, struct qedf_ioreq *io_req) struct fcoe_task_context *task_ctx; u16 xid; enum fcoe_task_type req_type = 0; - u32 ptu_invalidate = 0; + struct fcoe_wqe *sqe; + u16 sqe_idx; /* Initialize rest of io_req fileds */ io_req->data_xfer_len = scsi_bufflen(sc_cmd); @@ -1061,6 +880,16 @@ int qedf_post_io_req(struct qedf_rport *fcport, struct qedf_ioreq *io_req) return -EAGAIN; } + if (!test_bit(QEDF_RPORT_SESSION_READY, &fcport->flags)) { + QEDF_ERR(&(qedf->dbg_ctx), "Session not offloaded yet.\n"); + kref_put(&io_req->refcount, qedf_release_cmd); + } + + /* Obtain free SQE */ + sqe_idx = qedf_get_sqe_idx(fcport); + sqe = &fcport->sq[sqe_idx]; + memset(sqe, 0, sizeof(struct fcoe_wqe)); + /* Get the task context */ task_ctx = qedf_get_task_mem(&qedf->tasks, xid); if (!task_ctx) { @@ -1070,15 +899,7 @@ int qedf_post_io_req(struct qedf_rport *fcport, struct qedf_ioreq *io_req) return -EINVAL; } - qedf_init_task(fcport, lport, io_req, &ptu_invalidate, task_ctx); - - if (!test_bit(QEDF_RPORT_SESSION_READY, &fcport->flags)) { - QEDF_ERR(&(qedf->dbg_ctx), "Session not offloaded yet.\n"); - kref_put(&io_req->refcount, qedf_release_cmd); - } - - /* Obtain free SQ entry */ - qedf_add_to_sq(fcport, xid, ptu_invalidate, req_type, 0); + qedf_init_task(fcport, lport, io_req, task_ctx, sqe); /* Ring doorbell */ qedf_ring_doorbell(fcport); @@ -1342,7 +1163,7 @@ void qedf_scsi_completion(struct qedf_ctx *qedf, struct fcoe_cqe *cqe, } else { refcount = kref_read(&io_req->refcount); QEDF_INFO(&(qedf->dbg_ctx), QEDF_LOG_IO, - "%d:0:%d:%d xid=0x%0x op=0x%02x " + "%d:0:%d:%lld xid=0x%0x op=0x%02x " "lba=%02x%02x%02x%02x cdb_status=%d " "fcp_resid=0x%x refcount=%d.\n", qedf->lport->host->host_no, sc_cmd->device->id, @@ -1426,7 +1247,7 @@ void qedf_scsi_done(struct qedf_ctx *qedf, struct qedf_ioreq *io_req, sc_cmd->result = result << 16; refcount = kref_read(&io_req->refcount); - QEDF_INFO(&(qedf->dbg_ctx), QEDF_LOG_IO, "%d:0:%d:%d: Completing " + QEDF_INFO(&(qedf->dbg_ctx), QEDF_LOG_IO, "%d:0:%d:%lld: Completing " "sc_cmd=%p result=0x%08x op=0x%02x lba=0x%02x%02x%02x%02x, " "allowed=%d retries=%d refcount=%d.\n", qedf->lport->host->host_no, sc_cmd->device->id, @@ -1661,6 +1482,8 @@ int qedf_initiate_abts(struct qedf_ioreq *io_req, bool return_scsi_cmd_on_abts) u32 r_a_tov = 0; int rc = 0; unsigned long flags; + struct fcoe_wqe *sqe; + u16 sqe_idx; r_a_tov = rdata->r_a_tov; lport = qedf->lport; @@ -1712,10 +1535,12 @@ int qedf_initiate_abts(struct qedf_ioreq *io_req, bool return_scsi_cmd_on_abts) spin_lock_irqsave(&fcport->rport_lock, flags); - /* Add ABTS to send queue */ - qedf_add_to_sq(fcport, xid, 0, FCOE_TASK_TYPE_ABTS, 0); + sqe_idx = qedf_get_sqe_idx(fcport); + sqe = &fcport->sq[sqe_idx]; + memset(sqe, 0, sizeof(struct fcoe_wqe)); + io_req->task_params->sqe = sqe; - /* Ring doorbell */ + init_initiator_abort_fcoe_task(io_req->task_params); qedf_ring_doorbell(fcport); spin_unlock_irqrestore(&fcport->rport_lock, flags); @@ -1784,8 +1609,8 @@ void qedf_process_abts_compl(struct qedf_ctx *qedf, struct fcoe_cqe *cqe, int qedf_init_mp_req(struct qedf_ioreq *io_req) { struct qedf_mp_req *mp_req; - struct fcoe_sge *mp_req_bd; - struct fcoe_sge *mp_resp_bd; + struct scsi_sge *mp_req_bd; + struct scsi_sge *mp_resp_bd; struct qedf_ctx *qedf = io_req->fcport->qedf; dma_addr_t addr; uint64_t sz; @@ -1819,7 +1644,7 @@ int qedf_init_mp_req(struct qedf_ioreq *io_req) } /* Allocate and map mp_req_bd and mp_resp_bd */ - sz = sizeof(struct fcoe_sge); + sz = sizeof(struct scsi_sge); mp_req->mp_req_bd = dma_alloc_coherent(&qedf->pdev->dev, sz, &mp_req->mp_req_bd_dma, GFP_KERNEL); if (!mp_req->mp_req_bd) { @@ -1841,7 +1666,7 @@ int qedf_init_mp_req(struct qedf_ioreq *io_req) mp_req_bd = mp_req->mp_req_bd; mp_req_bd->sge_addr.lo = U64_LO(addr); mp_req_bd->sge_addr.hi = U64_HI(addr); - mp_req_bd->size = QEDF_PAGE_SIZE; + mp_req_bd->sge_len = QEDF_PAGE_SIZE; /* * MP buffer is either a task mgmt command or an ELS. @@ -1852,7 +1677,7 @@ int qedf_init_mp_req(struct qedf_ioreq *io_req) addr = mp_req->resp_buf_dma; mp_resp_bd->sge_addr.lo = U64_LO(addr); mp_resp_bd->sge_addr.hi = U64_HI(addr); - mp_resp_bd->size = QEDF_PAGE_SIZE; + mp_resp_bd->sge_len = QEDF_PAGE_SIZE; return 0; } @@ -1895,6 +1720,8 @@ int qedf_initiate_cleanup(struct qedf_ioreq *io_req, int tmo = 0; int rc = SUCCESS; unsigned long flags; + struct fcoe_wqe *sqe; + u16 sqe_idx; fcport = io_req->fcport; if (!fcport) { @@ -1940,12 +1767,16 @@ int qedf_initiate_cleanup(struct qedf_ioreq *io_req, init_completion(&io_req->tm_done); - /* Obtain free SQ entry */ spin_lock_irqsave(&fcport->rport_lock, flags); - qedf_add_to_sq(fcport, xid, 0, FCOE_TASK_TYPE_EXCHANGE_CLEANUP, 0); - /* Ring doorbell */ + sqe_idx = qedf_get_sqe_idx(fcport); + sqe = &fcport->sq[sqe_idx]; + memset(sqe, 0, sizeof(struct fcoe_wqe)); + io_req->task_params->sqe = sqe; + + init_initiator_cleanup_fcoe_task(io_req->task_params); qedf_ring_doorbell(fcport); + spin_unlock_irqrestore(&fcport->rport_lock, flags); tmo = wait_for_completion_timeout(&io_req->tm_done, @@ -1991,16 +1822,15 @@ static int qedf_execute_tmf(struct qedf_rport *fcport, struct scsi_cmnd *sc_cmd, uint8_t tm_flags) { struct qedf_ioreq *io_req; - struct qedf_mp_req *tm_req; struct fcoe_task_context *task; - struct fc_frame_header *fc_hdr; - struct fcp_cmnd *fcp_cmnd; struct qedf_ctx *qedf = fcport->qedf; + struct fc_lport *lport = qedf->lport; int rc = 0; uint16_t xid; - uint32_t sid, did; int tmo = 0; unsigned long flags; + struct fcoe_wqe *sqe; + u16 sqe_idx; if (!sc_cmd) { QEDF_ERR(&(qedf->dbg_ctx), "invalid arg\n"); @@ -2031,36 +1861,14 @@ static int qedf_execute_tmf(struct qedf_rport *fcport, struct scsi_cmnd *sc_cmd, /* Set the return CPU to be the same as the request one */ io_req->cpu = smp_processor_id(); - tm_req = (struct qedf_mp_req *)&(io_req->mp_req); - - rc = qedf_init_mp_req(io_req); - if (rc == FAILED) { - QEDF_ERR(&(qedf->dbg_ctx), "Task mgmt MP request init " - "failed\n"); - kref_put(&io_req->refcount, qedf_release_cmd); - goto reset_tmf_err; - } - /* Set TM flags */ - io_req->io_req_flags = 0; - tm_req->tm_flags = tm_flags; + io_req->io_req_flags = QEDF_READ; + io_req->data_xfer_len = 0; + io_req->tm_flags = tm_flags; /* Default is to return a SCSI command when an error occurs */ io_req->return_scsi_cmd_on_abts = true; - /* Fill FCP_CMND */ - qedf_build_fcp_cmnd(io_req, (struct fcp_cmnd *)tm_req->req_buf); - fcp_cmnd = (struct fcp_cmnd *)tm_req->req_buf; - memset(fcp_cmnd->fc_cdb, 0, FCP_CMND_LEN); - fcp_cmnd->fc_dl = 0; - - /* Fill FC header */ - fc_hdr = &(tm_req->req_fc_hdr); - sid = fcport->sid; - did = fcport->rdata->ids.port_id; - __fc_fill_fc_hdr(fc_hdr, FC_RCTL_DD_UNSOL_CMD, sid, did, - FC_TYPE_FCP, FC_FC_FIRST_SEQ | FC_FC_END_SEQ | - FC_FC_SEQ_INIT, 0); /* Obtain exchange id */ xid = io_req->xid; @@ -2069,16 +1877,18 @@ static int qedf_execute_tmf(struct qedf_rport *fcport, struct scsi_cmnd *sc_cmd, /* Initialize task context for this IO request */ task = qedf_get_task_mem(&qedf->tasks, xid); - qedf_init_mp_task(io_req, task); init_completion(&io_req->tm_done); - /* Obtain free SQ entry */ spin_lock_irqsave(&fcport->rport_lock, flags); - qedf_add_to_sq(fcport, xid, 0, FCOE_TASK_TYPE_MIDPATH, 0); - /* Ring doorbell */ + sqe_idx = qedf_get_sqe_idx(fcport); + sqe = &fcport->sq[sqe_idx]; + memset(sqe, 0, sizeof(struct fcoe_wqe)); + + qedf_init_task(fcport, lport, io_req, task, sqe); qedf_ring_doorbell(fcport); + spin_unlock_irqrestore(&fcport->rport_lock, flags); tmo = wait_for_completion_timeout(&io_req->tm_done, @@ -2162,14 +1972,6 @@ void qedf_process_tmf_compl(struct qedf_ctx *qedf, struct fcoe_cqe *cqe, struct qedf_ioreq *io_req) { struct fcoe_cqe_rsp_info *fcp_rsp; - struct fcoe_cqe_midpath_info *mp_info; - - - /* Get TMF response length from CQE */ - mp_info = &cqe->cqe_info.midpath_info; - io_req->mp_req.resp_len = mp_info->data_placement_size; - QEDF_INFO(&(qedf->dbg_ctx), QEDF_LOG_SCSI_TM, - "Response len is %d.\n", io_req->mp_req.resp_len); fcp_rsp = &cqe->cqe_info.rsp_info; qedf_parse_fcp_rsp(io_req, fcp_rsp); diff --git a/drivers/scsi/qedf/qedf_main.c b/drivers/scsi/qedf/qedf_main.c index d9d7a86b5f8b..8e2a160490e6 100644 --- a/drivers/scsi/qedf/qedf_main.c +++ b/drivers/scsi/qedf/qedf_main.c @@ -2456,8 +2456,8 @@ static int qedf_alloc_bdq(struct qedf_ctx *qedf) } QEDF_INFO(&(qedf->dbg_ctx), QEDF_LOG_DISC, - "BDQ PBL addr=0x%p dma=0x%llx.\n", qedf->bdq_pbl, - qedf->bdq_pbl_dma); + "BDQ PBL addr=0x%p dma=%pad\n", + qedf->bdq_pbl, &qedf->bdq_pbl_dma); /* * Populate BDQ PBL with physical and virtual address of individual diff --git a/drivers/scsi/qedi/Makefile b/drivers/scsi/qedi/Makefile index 2b3e16b24299..90a6925577cc 100644 --- a/drivers/scsi/qedi/Makefile +++ b/drivers/scsi/qedi/Makefile @@ -1,5 +1,5 @@ obj-$(CONFIG_QEDI) := qedi.o qedi-y := qedi_main.o qedi_iscsi.o qedi_fw.o qedi_sysfs.o \ - qedi_dbg.o + qedi_dbg.o qedi_fw_api.o qedi-$(CONFIG_DEBUG_FS) += qedi_debugfs.o diff --git a/drivers/scsi/qedi/qedi_debugfs.c b/drivers/scsi/qedi/qedi_debugfs.c index 955936274241..59417199bf36 100644 --- a/drivers/scsi/qedi/qedi_debugfs.c +++ b/drivers/scsi/qedi/qedi_debugfs.c @@ -14,7 +14,7 @@ #include <linux/debugfs.h> #include <linux/module.h> -int do_not_recover; +int qedi_do_not_recover; static struct dentry *qedi_dbg_root; void @@ -74,22 +74,22 @@ qedi_dbg_exit(void) static ssize_t qedi_dbg_do_not_recover_enable(struct qedi_dbg_ctx *qedi_dbg) { - if (!do_not_recover) - do_not_recover = 1; + if (!qedi_do_not_recover) + qedi_do_not_recover = 1; QEDI_INFO(qedi_dbg, QEDI_LOG_DEBUGFS, "do_not_recover=%d\n", - do_not_recover); + qedi_do_not_recover); return 0; } static ssize_t qedi_dbg_do_not_recover_disable(struct qedi_dbg_ctx *qedi_dbg) { - if (do_not_recover) - do_not_recover = 0; + if (qedi_do_not_recover) + qedi_do_not_recover = 0; QEDI_INFO(qedi_dbg, QEDI_LOG_DEBUGFS, "do_not_recover=%d\n", - do_not_recover); + qedi_do_not_recover); return 0; } @@ -141,7 +141,7 @@ qedi_dbg_do_not_recover_cmd_read(struct file *filp, char __user *buffer, if (*ppos) return 0; - cnt = sprintf(buffer, "do_not_recover=%d\n", do_not_recover); + cnt = sprintf(buffer, "do_not_recover=%d\n", qedi_do_not_recover); cnt = min_t(int, count, cnt - *ppos); *ppos += cnt; return cnt; diff --git a/drivers/scsi/qedi/qedi_fw.c b/drivers/scsi/qedi/qedi_fw.c index c9f0ef4e11b3..d6978cbc56f0 100644 --- a/drivers/scsi/qedi/qedi_fw.c +++ b/drivers/scsi/qedi/qedi_fw.c @@ -14,6 +14,8 @@ #include "qedi.h" #include "qedi_iscsi.h" #include "qedi_gbl.h" +#include "qedi_fw_iscsi.h" +#include "qedi_fw_scsi.h" static int qedi_send_iscsi_tmf(struct qedi_conn *qedi_conn, struct iscsi_task *mtask); @@ -53,8 +55,8 @@ static void qedi_process_logout_resp(struct qedi_ctx *qedi, resp_hdr->exp_cmdsn = cpu_to_be32(cqe_logout_response->exp_cmd_sn); resp_hdr->max_cmdsn = cpu_to_be32(cqe_logout_response->max_cmd_sn); - resp_hdr->t2wait = cpu_to_be32(cqe_logout_response->time2wait); - resp_hdr->t2retain = cpu_to_be32(cqe_logout_response->time2retain); + resp_hdr->t2wait = cpu_to_be32(cqe_logout_response->time_2_wait); + resp_hdr->t2retain = cpu_to_be32(cqe_logout_response->time_2_retain); QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_TID, "Freeing tid=0x%x for cid=0x%x\n", @@ -975,81 +977,6 @@ exit_fp_process: return; } -static void qedi_add_to_sq(struct qedi_conn *qedi_conn, struct iscsi_task *task, - u16 tid, uint16_t ptu_invalidate, int is_cleanup) -{ - struct iscsi_wqe *wqe; - struct iscsi_wqe_field *cont_field; - struct qedi_endpoint *ep; - struct scsi_cmnd *sc = task->sc; - struct iscsi_login_req *login_hdr; - struct qedi_cmd *cmd = task->dd_data; - - login_hdr = (struct iscsi_login_req *)task->hdr; - ep = qedi_conn->ep; - wqe = &ep->sq[ep->sq_prod_idx]; - - memset(wqe, 0, sizeof(*wqe)); - - ep->sq_prod_idx++; - ep->fw_sq_prod_idx++; - if (ep->sq_prod_idx == QEDI_SQ_SIZE) - ep->sq_prod_idx = 0; - - if (is_cleanup) { - SET_FIELD(wqe->flags, ISCSI_WQE_WQE_TYPE, - ISCSI_WQE_TYPE_TASK_CLEANUP); - wqe->task_id = tid; - return; - } - - if (ptu_invalidate) { - SET_FIELD(wqe->flags, ISCSI_WQE_PTU_INVALIDATE, - ISCSI_WQE_SET_PTU_INVALIDATE); - } - - cont_field = &wqe->cont_prevtid_union.cont_field; - - switch (task->hdr->opcode & ISCSI_OPCODE_MASK) { - case ISCSI_OP_LOGIN: - case ISCSI_OP_TEXT: - SET_FIELD(wqe->flags, ISCSI_WQE_WQE_TYPE, - ISCSI_WQE_TYPE_MIDDLE_PATH); - SET_FIELD(wqe->flags, ISCSI_WQE_NUM_FAST_SGES, - 1); - cont_field->contlen_cdbsize_field = ntoh24(login_hdr->dlength); - break; - case ISCSI_OP_LOGOUT: - case ISCSI_OP_NOOP_OUT: - case ISCSI_OP_SCSI_TMFUNC: - SET_FIELD(wqe->flags, ISCSI_WQE_WQE_TYPE, - ISCSI_WQE_TYPE_NORMAL); - break; - default: - if (!sc) - break; - - SET_FIELD(wqe->flags, ISCSI_WQE_WQE_TYPE, - ISCSI_WQE_TYPE_NORMAL); - cont_field->contlen_cdbsize_field = - (sc->sc_data_direction == DMA_TO_DEVICE) ? - scsi_bufflen(sc) : 0; - if (cmd->use_slowpath) - SET_FIELD(wqe->flags, ISCSI_WQE_NUM_FAST_SGES, 0); - else - SET_FIELD(wqe->flags, ISCSI_WQE_NUM_FAST_SGES, - (sc->sc_data_direction == - DMA_TO_DEVICE) ? - min((u16)QEDI_FAST_SGE_COUNT, - (u16)cmd->io_tbl.sge_valid) : 0); - break; - } - - wqe->task_id = tid; - /* Make sure SQ data is coherent */ - wmb(); -} - static void qedi_ring_doorbell(struct qedi_conn *qedi_conn) { struct iscsi_db_data dbell = { 0 }; @@ -1076,96 +1003,116 @@ static void qedi_ring_doorbell(struct qedi_conn *qedi_conn) qedi_conn->iscsi_conn_id); } +static u16 qedi_get_wqe_idx(struct qedi_conn *qedi_conn) +{ + struct qedi_endpoint *ep; + u16 rval; + + ep = qedi_conn->ep; + rval = ep->sq_prod_idx; + + /* Increament SQ index */ + ep->sq_prod_idx++; + ep->fw_sq_prod_idx++; + if (ep->sq_prod_idx == QEDI_SQ_SIZE) + ep->sq_prod_idx = 0; + + return rval; +} + int qedi_send_iscsi_login(struct qedi_conn *qedi_conn, struct iscsi_task *task) { - struct qedi_ctx *qedi = qedi_conn->qedi; + struct iscsi_login_req_hdr login_req_pdu_header; + struct scsi_sgl_task_params tx_sgl_task_params; + struct scsi_sgl_task_params rx_sgl_task_params; + struct iscsi_task_params task_params; struct iscsi_task_context *fw_task_ctx; + struct qedi_ctx *qedi = qedi_conn->qedi; struct iscsi_login_req *login_hdr; - struct iscsi_login_req_hdr *fw_login_req = NULL; - struct iscsi_cached_sge_ctx *cached_sge = NULL; - struct iscsi_sge *single_sge = NULL; - struct iscsi_sge *req_sge = NULL; - struct iscsi_sge *resp_sge = NULL; + struct scsi_sge *req_sge = NULL; + struct scsi_sge *resp_sge = NULL; struct qedi_cmd *qedi_cmd; - s16 ptu_invalidate = 0; + struct qedi_endpoint *ep; s16 tid = 0; + u16 sq_idx = 0; + int rval = 0; - req_sge = (struct iscsi_sge *)qedi_conn->gen_pdu.req_bd_tbl; - resp_sge = (struct iscsi_sge *)qedi_conn->gen_pdu.resp_bd_tbl; + req_sge = (struct scsi_sge *)qedi_conn->gen_pdu.req_bd_tbl; + resp_sge = (struct scsi_sge *)qedi_conn->gen_pdu.resp_bd_tbl; qedi_cmd = (struct qedi_cmd *)task->dd_data; + ep = qedi_conn->ep; login_hdr = (struct iscsi_login_req *)task->hdr; tid = qedi_get_task_idx(qedi); if (tid == -1) return -ENOMEM; - fw_task_ctx = qedi_get_task_mem(&qedi->tasks, tid); + fw_task_ctx = + (struct iscsi_task_context *)qedi_get_task_mem(&qedi->tasks, tid); memset(fw_task_ctx, 0, sizeof(struct iscsi_task_context)); qedi_cmd->task_id = tid; - /* Ystorm context */ - fw_login_req = &fw_task_ctx->ystorm_st_context.pdu_hdr.login_req; - fw_login_req->opcode = login_hdr->opcode; - fw_login_req->version_min = login_hdr->min_version; - fw_login_req->version_max = login_hdr->max_version; - fw_login_req->flags_attr = login_hdr->flags; - fw_login_req->isid_tabc = *((u16 *)login_hdr->isid + 2); - fw_login_req->isid_d = *((u32 *)login_hdr->isid); - fw_login_req->tsih = login_hdr->tsih; - qedi_update_itt_map(qedi, tid, task->itt, qedi_cmd); - fw_login_req->itt = qedi_set_itt(tid, get_itt(task->itt)); - fw_login_req->cid = qedi_conn->iscsi_conn_id; - fw_login_req->cmd_sn = be32_to_cpu(login_hdr->cmdsn); - fw_login_req->exp_stat_sn = be32_to_cpu(login_hdr->exp_statsn); - fw_login_req->exp_stat_sn = 0; - - if (qedi->tid_reuse_count[tid] == QEDI_MAX_TASK_NUM) { - ptu_invalidate = 1; - qedi->tid_reuse_count[tid] = 0; - } + memset(&task_params, 0, sizeof(task_params)); + memset(&login_req_pdu_header, 0, sizeof(login_req_pdu_header)); + memset(&tx_sgl_task_params, 0, sizeof(tx_sgl_task_params)); + memset(&rx_sgl_task_params, 0, sizeof(rx_sgl_task_params)); + /* Update header info */ + login_req_pdu_header.opcode = login_hdr->opcode; + login_req_pdu_header.version_min = login_hdr->min_version; + login_req_pdu_header.version_max = login_hdr->max_version; + login_req_pdu_header.flags_attr = login_hdr->flags; + login_req_pdu_header.isid_tabc = swab32p((u32 *)login_hdr->isid); + login_req_pdu_header.isid_d = swab16p((u16 *)&login_hdr->isid[4]); + + login_req_pdu_header.tsih = login_hdr->tsih; + login_req_pdu_header.hdr_second_dword = ntoh24(login_hdr->dlength); - fw_task_ctx->ystorm_st_context.state.reuse_count = - qedi->tid_reuse_count[tid]; - fw_task_ctx->mstorm_st_context.reuse_count = - qedi->tid_reuse_count[tid]++; - cached_sge = - &fw_task_ctx->ystorm_st_context.state.sgl_ctx_union.cached_sge; - cached_sge->sge.sge_len = req_sge->sge_len; - cached_sge->sge.sge_addr.lo = (u32)(qedi_conn->gen_pdu.req_dma_addr); - cached_sge->sge.sge_addr.hi = - (u32)((u64)qedi_conn->gen_pdu.req_dma_addr >> 32); - - /* Mstorm context */ - single_sge = &fw_task_ctx->mstorm_st_context.sgl_union.single_sge; - fw_task_ctx->mstorm_st_context.task_type = 0x2; - fw_task_ctx->mstorm_ag_context.task_cid = (u16)qedi_conn->iscsi_conn_id; - single_sge->sge_addr.lo = resp_sge->sge_addr.lo; - single_sge->sge_addr.hi = resp_sge->sge_addr.hi; - single_sge->sge_len = resp_sge->sge_len; - - SET_FIELD(fw_task_ctx->mstorm_st_context.flags.mflags, - ISCSI_MFLAGS_SINGLE_SGE, 1); - SET_FIELD(fw_task_ctx->mstorm_st_context.flags.mflags, - ISCSI_MFLAGS_SLOW_IO, 0); - fw_task_ctx->mstorm_st_context.sgl_size = 1; - fw_task_ctx->mstorm_st_context.rem_task_size = resp_sge->sge_len; - - /* Ustorm context */ - fw_task_ctx->ustorm_st_context.rem_rcv_len = resp_sge->sge_len; - fw_task_ctx->ustorm_st_context.exp_data_transfer_len = - ntoh24(login_hdr->dlength); - fw_task_ctx->ustorm_st_context.exp_data_sn = 0; - fw_task_ctx->ustorm_st_context.cq_rss_number = 0; - fw_task_ctx->ustorm_st_context.task_type = 0x2; - fw_task_ctx->ustorm_ag_context.icid = (u16)qedi_conn->iscsi_conn_id; - fw_task_ctx->ustorm_ag_context.exp_data_acked = - ntoh24(login_hdr->dlength); - SET_FIELD(fw_task_ctx->ustorm_ag_context.flags1, - USTORM_ISCSI_TASK_AG_CTX_R2T2RECV, 1); - SET_FIELD(fw_task_ctx->ustorm_st_context.flags, - USTORM_ISCSI_TASK_ST_CTX_LOCAL_COMP, 0); + qedi_update_itt_map(qedi, tid, task->itt, qedi_cmd); + login_req_pdu_header.itt = qedi_set_itt(tid, get_itt(task->itt)); + login_req_pdu_header.cid = qedi_conn->iscsi_conn_id; + login_req_pdu_header.cmd_sn = be32_to_cpu(login_hdr->cmdsn); + login_req_pdu_header.exp_stat_sn = be32_to_cpu(login_hdr->exp_statsn); + login_req_pdu_header.exp_stat_sn = 0; + + /* Fill tx AHS and rx buffer */ + tx_sgl_task_params.sgl = + (struct scsi_sge *)qedi_conn->gen_pdu.req_bd_tbl; + tx_sgl_task_params.sgl_phys_addr.lo = + (u32)(qedi_conn->gen_pdu.req_dma_addr); + tx_sgl_task_params.sgl_phys_addr.hi = + (u32)((u64)qedi_conn->gen_pdu.req_dma_addr >> 32); + tx_sgl_task_params.total_buffer_size = ntoh24(login_hdr->dlength); + tx_sgl_task_params.num_sges = 1; + + rx_sgl_task_params.sgl = + (struct scsi_sge *)qedi_conn->gen_pdu.resp_bd_tbl; + rx_sgl_task_params.sgl_phys_addr.lo = + (u32)(qedi_conn->gen_pdu.resp_dma_addr); + rx_sgl_task_params.sgl_phys_addr.hi = + (u32)((u64)qedi_conn->gen_pdu.resp_dma_addr >> 32); + rx_sgl_task_params.total_buffer_size = resp_sge->sge_len; + rx_sgl_task_params.num_sges = 1; + + /* Fill fw input params */ + task_params.context = fw_task_ctx; + task_params.conn_icid = (u16)qedi_conn->iscsi_conn_id; + task_params.itid = tid; + task_params.cq_rss_number = 0; + task_params.tx_io_size = ntoh24(login_hdr->dlength); + task_params.rx_io_size = resp_sge->sge_len; + + sq_idx = qedi_get_wqe_idx(qedi_conn); + task_params.sqe = &ep->sq[sq_idx]; + + memset(task_params.sqe, 0, sizeof(struct iscsi_wqe)); + rval = init_initiator_login_request_task(&task_params, + &login_req_pdu_header, + &tx_sgl_task_params, + &rx_sgl_task_params); + if (rval) + return -1; spin_lock(&qedi_conn->list_lock); list_add_tail(&qedi_cmd->io_cmd, &qedi_conn->active_cmd_list); @@ -1173,7 +1120,6 @@ int qedi_send_iscsi_login(struct qedi_conn *qedi_conn, qedi_conn->active_cmd_count++; spin_unlock(&qedi_conn->list_lock); - qedi_add_to_sq(qedi_conn, task, tid, ptu_invalidate, false); qedi_ring_doorbell(qedi_conn); return 0; } @@ -1181,65 +1127,64 @@ int qedi_send_iscsi_login(struct qedi_conn *qedi_conn, int qedi_send_iscsi_logout(struct qedi_conn *qedi_conn, struct iscsi_task *task) { - struct qedi_ctx *qedi = qedi_conn->qedi; - struct iscsi_logout_req_hdr *fw_logout_req = NULL; - struct iscsi_task_context *fw_task_ctx = NULL; + struct iscsi_logout_req_hdr logout_pdu_header; + struct scsi_sgl_task_params tx_sgl_task_params; + struct scsi_sgl_task_params rx_sgl_task_params; + struct iscsi_task_params task_params; + struct iscsi_task_context *fw_task_ctx; struct iscsi_logout *logout_hdr = NULL; - struct qedi_cmd *qedi_cmd = NULL; - s16 tid = 0; - s16 ptu_invalidate = 0; + struct qedi_ctx *qedi = qedi_conn->qedi; + struct qedi_cmd *qedi_cmd; + struct qedi_endpoint *ep; + s16 tid = 0; + u16 sq_idx = 0; + int rval = 0; qedi_cmd = (struct qedi_cmd *)task->dd_data; logout_hdr = (struct iscsi_logout *)task->hdr; + ep = qedi_conn->ep; tid = qedi_get_task_idx(qedi); if (tid == -1) return -ENOMEM; - fw_task_ctx = qedi_get_task_mem(&qedi->tasks, tid); - + fw_task_ctx = + (struct iscsi_task_context *)qedi_get_task_mem(&qedi->tasks, tid); memset(fw_task_ctx, 0, sizeof(struct iscsi_task_context)); + qedi_cmd->task_id = tid; - /* Ystorm context */ - fw_logout_req = &fw_task_ctx->ystorm_st_context.pdu_hdr.logout_req; - fw_logout_req->opcode = ISCSI_OPCODE_LOGOUT_REQUEST; - fw_logout_req->reason_code = 0x80 | logout_hdr->flags; - qedi_update_itt_map(qedi, tid, task->itt, qedi_cmd); - fw_logout_req->itt = qedi_set_itt(tid, get_itt(task->itt)); - fw_logout_req->exp_stat_sn = be32_to_cpu(logout_hdr->exp_statsn); - fw_logout_req->cmd_sn = be32_to_cpu(logout_hdr->cmdsn); + memset(&task_params, 0, sizeof(task_params)); + memset(&logout_pdu_header, 0, sizeof(logout_pdu_header)); + memset(&tx_sgl_task_params, 0, sizeof(tx_sgl_task_params)); + memset(&rx_sgl_task_params, 0, sizeof(rx_sgl_task_params)); - if (qedi->tid_reuse_count[tid] == QEDI_MAX_TASK_NUM) { - ptu_invalidate = 1; - qedi->tid_reuse_count[tid] = 0; - } - fw_task_ctx->ystorm_st_context.state.reuse_count = - qedi->tid_reuse_count[tid]; - fw_task_ctx->mstorm_st_context.reuse_count = - qedi->tid_reuse_count[tid]++; - fw_logout_req->cid = qedi_conn->iscsi_conn_id; - fw_task_ctx->ystorm_st_context.state.buffer_offset[0] = 0; - - /* Mstorm context */ - fw_task_ctx->mstorm_st_context.task_type = ISCSI_TASK_TYPE_MIDPATH; - fw_task_ctx->mstorm_ag_context.task_cid = (u16)qedi_conn->iscsi_conn_id; - - /* Ustorm context */ - fw_task_ctx->ustorm_st_context.rem_rcv_len = 0; - fw_task_ctx->ustorm_st_context.exp_data_transfer_len = 0; - fw_task_ctx->ustorm_st_context.exp_data_sn = 0; - fw_task_ctx->ustorm_st_context.task_type = ISCSI_TASK_TYPE_MIDPATH; - fw_task_ctx->ustorm_st_context.cq_rss_number = 0; - - SET_FIELD(fw_task_ctx->ustorm_st_context.flags, - USTORM_ISCSI_TASK_ST_CTX_LOCAL_COMP, 0); - SET_FIELD(fw_task_ctx->ustorm_st_context.reg1.reg1_map, - ISCSI_REG1_NUM_FAST_SGES, 0); - - fw_task_ctx->ustorm_ag_context.icid = (u16)qedi_conn->iscsi_conn_id; - SET_FIELD(fw_task_ctx->ustorm_ag_context.flags1, - USTORM_ISCSI_TASK_AG_CTX_R2T2RECV, 1); + /* Update header info */ + logout_pdu_header.opcode = logout_hdr->opcode; + logout_pdu_header.reason_code = 0x80 | logout_hdr->flags; + qedi_update_itt_map(qedi, tid, task->itt, qedi_cmd); + logout_pdu_header.itt = qedi_set_itt(tid, get_itt(task->itt)); + logout_pdu_header.exp_stat_sn = be32_to_cpu(logout_hdr->exp_statsn); + logout_pdu_header.cmd_sn = be32_to_cpu(logout_hdr->cmdsn); + logout_pdu_header.cid = qedi_conn->iscsi_conn_id; + + /* Fill fw input params */ + task_params.context = fw_task_ctx; + task_params.conn_icid = (u16)qedi_conn->iscsi_conn_id; + task_params.itid = tid; + task_params.cq_rss_number = 0; + task_params.tx_io_size = 0; + task_params.rx_io_size = 0; + + sq_idx = qedi_get_wqe_idx(qedi_conn); + task_params.sqe = &ep->sq[sq_idx]; + memset(task_params.sqe, 0, sizeof(struct iscsi_wqe)); + + rval = init_initiator_logout_request_task(&task_params, + &logout_pdu_header, + NULL, NULL); + if (rval) + return -1; spin_lock(&qedi_conn->list_lock); list_add_tail(&qedi_cmd->io_cmd, &qedi_conn->active_cmd_list); @@ -1247,9 +1192,7 @@ int qedi_send_iscsi_logout(struct qedi_conn *qedi_conn, qedi_conn->active_cmd_count++; spin_unlock(&qedi_conn->list_lock); - qedi_add_to_sq(qedi_conn, task, tid, ptu_invalidate, false); qedi_ring_doorbell(qedi_conn); - return 0; } @@ -1461,9 +1404,9 @@ static void qedi_tmf_work(struct work_struct *work) get_itt(tmf_hdr->rtt), get_itt(ctask->itt), cmd->task_id, qedi_conn->iscsi_conn_id); - if (do_not_recover) { + if (qedi_do_not_recover) { QEDI_ERR(&qedi->dbg_ctx, "DONT SEND CLEANUP/ABORT %d\n", - do_not_recover); + qedi_do_not_recover); goto abort_ret; } @@ -1533,47 +1476,46 @@ ldel_exit: static int qedi_send_iscsi_tmf(struct qedi_conn *qedi_conn, struct iscsi_task *mtask) { - struct iscsi_conn *conn = qedi_conn->cls_conn->dd_data; + struct iscsi_tmf_request_hdr tmf_pdu_header; + struct iscsi_task_params task_params; struct qedi_ctx *qedi = qedi_conn->qedi; struct iscsi_task_context *fw_task_ctx; - struct iscsi_tmf_request_hdr *fw_tmf_request; - struct iscsi_sge *single_sge; - struct qedi_cmd *qedi_cmd; - struct qedi_cmd *cmd; + struct iscsi_conn *conn = qedi_conn->cls_conn->dd_data; struct iscsi_task *ctask; struct iscsi_tm *tmf_hdr; - struct iscsi_sge *req_sge; - struct iscsi_sge *resp_sge; - u32 lun[2]; - s16 tid = 0, ptu_invalidate = 0; + struct qedi_cmd *qedi_cmd; + struct qedi_cmd *cmd; + struct qedi_endpoint *ep; + u32 scsi_lun[2]; + s16 tid = 0; + u16 sq_idx = 0; + int rval = 0; - req_sge = (struct iscsi_sge *)qedi_conn->gen_pdu.req_bd_tbl; - resp_sge = (struct iscsi_sge *)qedi_conn->gen_pdu.resp_bd_tbl; - qedi_cmd = (struct qedi_cmd *)mtask->dd_data; tmf_hdr = (struct iscsi_tm *)mtask->hdr; + qedi_cmd = (struct qedi_cmd *)mtask->dd_data; + ep = qedi_conn->ep; - tid = qedi_cmd->task_id; - qedi_update_itt_map(qedi, tid, mtask->itt, qedi_cmd); + tid = qedi_get_task_idx(qedi); + if (tid == -1) + return -ENOMEM; - fw_task_ctx = qedi_get_task_mem(&qedi->tasks, tid); + fw_task_ctx = + (struct iscsi_task_context *)qedi_get_task_mem(&qedi->tasks, tid); memset(fw_task_ctx, 0, sizeof(struct iscsi_task_context)); - fw_tmf_request = &fw_task_ctx->ystorm_st_context.pdu_hdr.tmf_request; - fw_tmf_request->itt = qedi_set_itt(tid, get_itt(mtask->itt)); - fw_tmf_request->cmd_sn = be32_to_cpu(tmf_hdr->cmdsn); + qedi_cmd->task_id = tid; - memcpy(lun, &tmf_hdr->lun, sizeof(struct scsi_lun)); - fw_tmf_request->lun.lo = be32_to_cpu(lun[0]); - fw_tmf_request->lun.hi = be32_to_cpu(lun[1]); + memset(&task_params, 0, sizeof(task_params)); + memset(&tmf_pdu_header, 0, sizeof(tmf_pdu_header)); - if (qedi->tid_reuse_count[tid] == QEDI_MAX_TASK_NUM) { - ptu_invalidate = 1; - qedi->tid_reuse_count[tid] = 0; - } - fw_task_ctx->ystorm_st_context.state.reuse_count = - qedi->tid_reuse_count[tid]; - fw_task_ctx->mstorm_st_context.reuse_count = - qedi->tid_reuse_count[tid]++; + /* Update header info */ + qedi_update_itt_map(qedi, tid, mtask->itt, qedi_cmd); + tmf_pdu_header.itt = qedi_set_itt(tid, get_itt(mtask->itt)); + tmf_pdu_header.cmd_sn = be32_to_cpu(tmf_hdr->cmdsn); + + memcpy(scsi_lun, &tmf_hdr->lun, sizeof(struct scsi_lun)); + tmf_pdu_header.lun.lo = be32_to_cpu(scsi_lun[0]); + tmf_pdu_header.lun.hi = be32_to_cpu(scsi_lun[1]); if ((tmf_hdr->flags & ISCSI_FLAG_TM_FUNC_MASK) == ISCSI_TM_FUNC_ABORT_TASK) { @@ -1584,53 +1526,34 @@ static int qedi_send_iscsi_tmf(struct qedi_conn *qedi_conn, return 0; } cmd = (struct qedi_cmd *)ctask->dd_data; - fw_tmf_request->rtt = + tmf_pdu_header.rtt = qedi_set_itt(cmd->task_id, get_itt(tmf_hdr->rtt)); } else { - fw_tmf_request->rtt = ISCSI_RESERVED_TAG; + tmf_pdu_header.rtt = ISCSI_RESERVED_TAG; } - fw_tmf_request->opcode = tmf_hdr->opcode; - fw_tmf_request->function = tmf_hdr->flags; - fw_tmf_request->hdr_second_dword = ntoh24(tmf_hdr->dlength); - fw_tmf_request->ref_cmd_sn = be32_to_cpu(tmf_hdr->refcmdsn); - - single_sge = &fw_task_ctx->mstorm_st_context.sgl_union.single_sge; - fw_task_ctx->mstorm_st_context.task_type = ISCSI_TASK_TYPE_MIDPATH; - fw_task_ctx->mstorm_ag_context.task_cid = (u16)qedi_conn->iscsi_conn_id; - single_sge->sge_addr.lo = resp_sge->sge_addr.lo; - single_sge->sge_addr.hi = resp_sge->sge_addr.hi; - single_sge->sge_len = resp_sge->sge_len; - - SET_FIELD(fw_task_ctx->mstorm_st_context.flags.mflags, - ISCSI_MFLAGS_SINGLE_SGE, 1); - SET_FIELD(fw_task_ctx->mstorm_st_context.flags.mflags, - ISCSI_MFLAGS_SLOW_IO, 0); - fw_task_ctx->mstorm_st_context.sgl_size = 1; - fw_task_ctx->mstorm_st_context.rem_task_size = resp_sge->sge_len; - - /* Ustorm context */ - fw_task_ctx->ustorm_st_context.rem_rcv_len = 0; - fw_task_ctx->ustorm_st_context.exp_data_transfer_len = 0; - fw_task_ctx->ustorm_st_context.exp_data_sn = 0; - fw_task_ctx->ustorm_st_context.task_type = ISCSI_TASK_TYPE_MIDPATH; - fw_task_ctx->ustorm_st_context.cq_rss_number = 0; - - SET_FIELD(fw_task_ctx->ustorm_st_context.flags, - USTORM_ISCSI_TASK_ST_CTX_LOCAL_COMP, 0); - SET_FIELD(fw_task_ctx->ustorm_st_context.reg1.reg1_map, - ISCSI_REG1_NUM_FAST_SGES, 0); - - fw_task_ctx->ustorm_ag_context.icid = (u16)qedi_conn->iscsi_conn_id; - SET_FIELD(fw_task_ctx->ustorm_ag_context.flags1, - USTORM_ISCSI_TASK_AG_CTX_R2T2RECV, 1); - fw_task_ctx->ustorm_st_context.lun.lo = be32_to_cpu(lun[0]); - fw_task_ctx->ustorm_st_context.lun.hi = be32_to_cpu(lun[1]); + tmf_pdu_header.opcode = tmf_hdr->opcode; + tmf_pdu_header.function = tmf_hdr->flags; + tmf_pdu_header.hdr_second_dword = ntoh24(tmf_hdr->dlength); + tmf_pdu_header.ref_cmd_sn = be32_to_cpu(tmf_hdr->refcmdsn); - QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_SCSI_TM, - "Add TMF to SQ, tmf tid=0x%x, itt=0x%x, cid=0x%x\n", - tid, mtask->itt, qedi_conn->iscsi_conn_id); + /* Fill fw input params */ + task_params.context = fw_task_ctx; + task_params.conn_icid = (u16)qedi_conn->iscsi_conn_id; + task_params.itid = tid; + task_params.cq_rss_number = 0; + task_params.tx_io_size = 0; + task_params.rx_io_size = 0; + + sq_idx = qedi_get_wqe_idx(qedi_conn); + task_params.sqe = &ep->sq[sq_idx]; + + memset(task_params.sqe, 0, sizeof(struct iscsi_wqe)); + rval = init_initiator_tmf_request_task(&task_params, + &tmf_pdu_header); + if (rval) + return -1; spin_lock(&qedi_conn->list_lock); list_add_tail(&qedi_cmd->io_cmd, &qedi_conn->active_cmd_list); @@ -1638,7 +1561,6 @@ static int qedi_send_iscsi_tmf(struct qedi_conn *qedi_conn, qedi_conn->active_cmd_count++; spin_unlock(&qedi_conn->list_lock); - qedi_add_to_sq(qedi_conn, mtask, tid, ptu_invalidate, false); qedi_ring_doorbell(qedi_conn); return 0; } @@ -1689,101 +1611,98 @@ int qedi_iscsi_abort_work(struct qedi_conn *qedi_conn, int qedi_send_iscsi_text(struct qedi_conn *qedi_conn, struct iscsi_task *task) { - struct qedi_ctx *qedi = qedi_conn->qedi; + struct iscsi_text_request_hdr text_request_pdu_header; + struct scsi_sgl_task_params tx_sgl_task_params; + struct scsi_sgl_task_params rx_sgl_task_params; + struct iscsi_task_params task_params; struct iscsi_task_context *fw_task_ctx; - struct iscsi_text_request_hdr *fw_text_request; - struct iscsi_cached_sge_ctx *cached_sge; - struct iscsi_sge *single_sge; - struct qedi_cmd *qedi_cmd; - /* For 6.5 hdr iscsi_hdr */ + struct qedi_ctx *qedi = qedi_conn->qedi; struct iscsi_text *text_hdr; - struct iscsi_sge *req_sge; - struct iscsi_sge *resp_sge; - s16 ptu_invalidate = 0; + struct scsi_sge *req_sge = NULL; + struct scsi_sge *resp_sge = NULL; + struct qedi_cmd *qedi_cmd; + struct qedi_endpoint *ep; s16 tid = 0; + u16 sq_idx = 0; + int rval = 0; - req_sge = (struct iscsi_sge *)qedi_conn->gen_pdu.req_bd_tbl; - resp_sge = (struct iscsi_sge *)qedi_conn->gen_pdu.resp_bd_tbl; + req_sge = (struct scsi_sge *)qedi_conn->gen_pdu.req_bd_tbl; + resp_sge = (struct scsi_sge *)qedi_conn->gen_pdu.resp_bd_tbl; qedi_cmd = (struct qedi_cmd *)task->dd_data; text_hdr = (struct iscsi_text *)task->hdr; + ep = qedi_conn->ep; tid = qedi_get_task_idx(qedi); if (tid == -1) return -ENOMEM; - fw_task_ctx = qedi_get_task_mem(&qedi->tasks, tid); + fw_task_ctx = + (struct iscsi_task_context *)qedi_get_task_mem(&qedi->tasks, tid); memset(fw_task_ctx, 0, sizeof(struct iscsi_task_context)); qedi_cmd->task_id = tid; - /* Ystorm context */ - fw_text_request = - &fw_task_ctx->ystorm_st_context.pdu_hdr.text_request; - fw_text_request->opcode = text_hdr->opcode; - fw_text_request->flags_attr = text_hdr->flags; + memset(&task_params, 0, sizeof(task_params)); + memset(&text_request_pdu_header, 0, sizeof(text_request_pdu_header)); + memset(&tx_sgl_task_params, 0, sizeof(tx_sgl_task_params)); + memset(&rx_sgl_task_params, 0, sizeof(rx_sgl_task_params)); + + /* Update header info */ + text_request_pdu_header.opcode = text_hdr->opcode; + text_request_pdu_header.flags_attr = text_hdr->flags; qedi_update_itt_map(qedi, tid, task->itt, qedi_cmd); - fw_text_request->itt = qedi_set_itt(tid, get_itt(task->itt)); - fw_text_request->ttt = text_hdr->ttt; - fw_text_request->cmd_sn = be32_to_cpu(text_hdr->cmdsn); - fw_text_request->exp_stat_sn = be32_to_cpu(text_hdr->exp_statsn); - fw_text_request->hdr_second_dword = ntoh24(text_hdr->dlength); - - if (qedi->tid_reuse_count[tid] == QEDI_MAX_TASK_NUM) { - ptu_invalidate = 1; - qedi->tid_reuse_count[tid] = 0; - } - fw_task_ctx->ystorm_st_context.state.reuse_count = - qedi->tid_reuse_count[tid]; - fw_task_ctx->mstorm_st_context.reuse_count = - qedi->tid_reuse_count[tid]++; - - cached_sge = - &fw_task_ctx->ystorm_st_context.state.sgl_ctx_union.cached_sge; - cached_sge->sge.sge_len = req_sge->sge_len; - cached_sge->sge.sge_addr.lo = (u32)(qedi_conn->gen_pdu.req_dma_addr); - cached_sge->sge.sge_addr.hi = + text_request_pdu_header.itt = qedi_set_itt(tid, get_itt(task->itt)); + text_request_pdu_header.ttt = text_hdr->ttt; + text_request_pdu_header.cmd_sn = be32_to_cpu(text_hdr->cmdsn); + text_request_pdu_header.exp_stat_sn = be32_to_cpu(text_hdr->exp_statsn); + text_request_pdu_header.hdr_second_dword = ntoh24(text_hdr->dlength); + + /* Fill tx AHS and rx buffer */ + tx_sgl_task_params.sgl = + (struct scsi_sge *)qedi_conn->gen_pdu.req_bd_tbl; + tx_sgl_task_params.sgl_phys_addr.lo = + (u32)(qedi_conn->gen_pdu.req_dma_addr); + tx_sgl_task_params.sgl_phys_addr.hi = (u32)((u64)qedi_conn->gen_pdu.req_dma_addr >> 32); + tx_sgl_task_params.total_buffer_size = req_sge->sge_len; + tx_sgl_task_params.num_sges = 1; + + rx_sgl_task_params.sgl = + (struct scsi_sge *)qedi_conn->gen_pdu.resp_bd_tbl; + rx_sgl_task_params.sgl_phys_addr.lo = + (u32)(qedi_conn->gen_pdu.resp_dma_addr); + rx_sgl_task_params.sgl_phys_addr.hi = + (u32)((u64)qedi_conn->gen_pdu.resp_dma_addr >> 32); + rx_sgl_task_params.total_buffer_size = resp_sge->sge_len; + rx_sgl_task_params.num_sges = 1; + + /* Fill fw input params */ + task_params.context = fw_task_ctx; + task_params.conn_icid = (u16)qedi_conn->iscsi_conn_id; + task_params.itid = tid; + task_params.cq_rss_number = 0; + task_params.tx_io_size = ntoh24(text_hdr->dlength); + task_params.rx_io_size = resp_sge->sge_len; + + sq_idx = qedi_get_wqe_idx(qedi_conn); + task_params.sqe = &ep->sq[sq_idx]; + + memset(task_params.sqe, 0, sizeof(struct iscsi_wqe)); + rval = init_initiator_text_request_task(&task_params, + &text_request_pdu_header, + &tx_sgl_task_params, + &rx_sgl_task_params); + if (rval) + return -1; - /* Mstorm context */ - single_sge = &fw_task_ctx->mstorm_st_context.sgl_union.single_sge; - fw_task_ctx->mstorm_st_context.task_type = 0x2; - fw_task_ctx->mstorm_ag_context.task_cid = (u16)qedi_conn->iscsi_conn_id; - single_sge->sge_addr.lo = resp_sge->sge_addr.lo; - single_sge->sge_addr.hi = resp_sge->sge_addr.hi; - single_sge->sge_len = resp_sge->sge_len; - - SET_FIELD(fw_task_ctx->mstorm_st_context.flags.mflags, - ISCSI_MFLAGS_SINGLE_SGE, 1); - SET_FIELD(fw_task_ctx->mstorm_st_context.flags.mflags, - ISCSI_MFLAGS_SLOW_IO, 0); - fw_task_ctx->mstorm_st_context.sgl_size = 1; - fw_task_ctx->mstorm_st_context.rem_task_size = resp_sge->sge_len; - - /* Ustorm context */ - fw_task_ctx->ustorm_ag_context.exp_data_acked = - ntoh24(text_hdr->dlength); - fw_task_ctx->ustorm_st_context.rem_rcv_len = resp_sge->sge_len; - fw_task_ctx->ustorm_st_context.exp_data_transfer_len = - ntoh24(text_hdr->dlength); - fw_task_ctx->ustorm_st_context.exp_data_sn = - be32_to_cpu(text_hdr->exp_statsn); - fw_task_ctx->ustorm_st_context.cq_rss_number = 0; - fw_task_ctx->ustorm_st_context.task_type = 0x2; - fw_task_ctx->ustorm_ag_context.icid = (u16)qedi_conn->iscsi_conn_id; - SET_FIELD(fw_task_ctx->ustorm_ag_context.flags1, - USTORM_ISCSI_TASK_AG_CTX_R2T2RECV, 1); - - /* Add command in active command list */ spin_lock(&qedi_conn->list_lock); list_add_tail(&qedi_cmd->io_cmd, &qedi_conn->active_cmd_list); qedi_cmd->io_cmd_in_list = true; qedi_conn->active_cmd_count++; spin_unlock(&qedi_conn->list_lock); - qedi_add_to_sq(qedi_conn, task, tid, ptu_invalidate, false); qedi_ring_doorbell(qedi_conn); - return 0; } @@ -1791,58 +1710,62 @@ int qedi_send_iscsi_nopout(struct qedi_conn *qedi_conn, struct iscsi_task *task, char *datap, int data_len, int unsol) { + struct iscsi_nop_out_hdr nop_out_pdu_header; + struct scsi_sgl_task_params tx_sgl_task_params; + struct scsi_sgl_task_params rx_sgl_task_params; + struct iscsi_task_params task_params; struct qedi_ctx *qedi = qedi_conn->qedi; struct iscsi_task_context *fw_task_ctx; - struct iscsi_nop_out_hdr *fw_nop_out; - struct qedi_cmd *qedi_cmd; - /* For 6.5 hdr iscsi_hdr */ struct iscsi_nopout *nopout_hdr; - struct iscsi_cached_sge_ctx *cached_sge; - struct iscsi_sge *single_sge; - struct iscsi_sge *req_sge; - struct iscsi_sge *resp_sge; - u32 lun[2]; - s16 ptu_invalidate = 0; + struct scsi_sge *req_sge = NULL; + struct scsi_sge *resp_sge = NULL; + struct qedi_cmd *qedi_cmd; + struct qedi_endpoint *ep; + u32 scsi_lun[2]; s16 tid = 0; + u16 sq_idx = 0; + int rval = 0; - req_sge = (struct iscsi_sge *)qedi_conn->gen_pdu.req_bd_tbl; - resp_sge = (struct iscsi_sge *)qedi_conn->gen_pdu.resp_bd_tbl; + req_sge = (struct scsi_sge *)qedi_conn->gen_pdu.req_bd_tbl; + resp_sge = (struct scsi_sge *)qedi_conn->gen_pdu.resp_bd_tbl; qedi_cmd = (struct qedi_cmd *)task->dd_data; nopout_hdr = (struct iscsi_nopout *)task->hdr; + ep = qedi_conn->ep; tid = qedi_get_task_idx(qedi); - if (tid == -1) { - QEDI_WARN(&qedi->dbg_ctx, "Invalid tid\n"); + if (tid == -1) return -ENOMEM; - } - - fw_task_ctx = qedi_get_task_mem(&qedi->tasks, tid); + fw_task_ctx = + (struct iscsi_task_context *)qedi_get_task_mem(&qedi->tasks, tid); memset(fw_task_ctx, 0, sizeof(struct iscsi_task_context)); + qedi_cmd->task_id = tid; - /* Ystorm context */ - fw_nop_out = &fw_task_ctx->ystorm_st_context.pdu_hdr.nop_out; - SET_FIELD(fw_nop_out->flags_attr, ISCSI_NOP_OUT_HDR_CONST1, 1); - SET_FIELD(fw_nop_out->flags_attr, ISCSI_NOP_OUT_HDR_RSRV, 0); + memset(&task_params, 0, sizeof(task_params)); + memset(&nop_out_pdu_header, 0, sizeof(nop_out_pdu_header)); + memset(&tx_sgl_task_params, 0, sizeof(tx_sgl_task_params)); + memset(&rx_sgl_task_params, 0, sizeof(rx_sgl_task_params)); + + /* Update header info */ + nop_out_pdu_header.opcode = nopout_hdr->opcode; + SET_FIELD(nop_out_pdu_header.flags_attr, ISCSI_NOP_OUT_HDR_CONST1, 1); + SET_FIELD(nop_out_pdu_header.flags_attr, ISCSI_NOP_OUT_HDR_RSRV, 0); - memcpy(lun, &nopout_hdr->lun, sizeof(struct scsi_lun)); - fw_nop_out->lun.lo = be32_to_cpu(lun[0]); - fw_nop_out->lun.hi = be32_to_cpu(lun[1]); + memcpy(scsi_lun, &nopout_hdr->lun, sizeof(struct scsi_lun)); + nop_out_pdu_header.lun.lo = be32_to_cpu(scsi_lun[0]); + nop_out_pdu_header.lun.hi = be32_to_cpu(scsi_lun[1]); + nop_out_pdu_header.cmd_sn = be32_to_cpu(nopout_hdr->cmdsn); + nop_out_pdu_header.exp_stat_sn = be32_to_cpu(nopout_hdr->exp_statsn); qedi_update_itt_map(qedi, tid, task->itt, qedi_cmd); if (nopout_hdr->ttt != ISCSI_TTT_ALL_ONES) { - fw_nop_out->itt = be32_to_cpu(nopout_hdr->itt); - fw_nop_out->ttt = be32_to_cpu(nopout_hdr->ttt); - fw_task_ctx->ystorm_st_context.state.buffer_offset[0] = 0; - fw_task_ctx->ystorm_st_context.state.local_comp = 1; - SET_FIELD(fw_task_ctx->ustorm_st_context.flags, - USTORM_ISCSI_TASK_ST_CTX_LOCAL_COMP, 1); + nop_out_pdu_header.itt = be32_to_cpu(nopout_hdr->itt); + nop_out_pdu_header.ttt = be32_to_cpu(nopout_hdr->ttt); } else { - fw_nop_out->itt = qedi_set_itt(tid, get_itt(task->itt)); - fw_nop_out->ttt = ISCSI_TTT_ALL_ONES; - fw_task_ctx->ystorm_st_context.state.buffer_offset[0] = 0; + nop_out_pdu_header.itt = qedi_set_itt(tid, get_itt(task->itt)); + nop_out_pdu_header.ttt = ISCSI_TTT_ALL_ONES; spin_lock(&qedi_conn->list_lock); list_add_tail(&qedi_cmd->io_cmd, &qedi_conn->active_cmd_list); @@ -1851,53 +1774,46 @@ int qedi_send_iscsi_nopout(struct qedi_conn *qedi_conn, spin_unlock(&qedi_conn->list_lock); } - fw_nop_out->opcode = ISCSI_OPCODE_NOP_OUT; - fw_nop_out->cmd_sn = be32_to_cpu(nopout_hdr->cmdsn); - fw_nop_out->exp_stat_sn = be32_to_cpu(nopout_hdr->exp_statsn); - - cached_sge = - &fw_task_ctx->ystorm_st_context.state.sgl_ctx_union.cached_sge; - cached_sge->sge.sge_len = req_sge->sge_len; - cached_sge->sge.sge_addr.lo = (u32)(qedi_conn->gen_pdu.req_dma_addr); - cached_sge->sge.sge_addr.hi = - (u32)((u64)qedi_conn->gen_pdu.req_dma_addr >> 32); - - /* Mstorm context */ - fw_task_ctx->mstorm_st_context.task_type = ISCSI_TASK_TYPE_MIDPATH; - fw_task_ctx->mstorm_ag_context.task_cid = (u16)qedi_conn->iscsi_conn_id; - - single_sge = &fw_task_ctx->mstorm_st_context.sgl_union.single_sge; - single_sge->sge_addr.lo = resp_sge->sge_addr.lo; - single_sge->sge_addr.hi = resp_sge->sge_addr.hi; - single_sge->sge_len = resp_sge->sge_len; - fw_task_ctx->mstorm_st_context.rem_task_size = resp_sge->sge_len; - - if (qedi->tid_reuse_count[tid] == QEDI_MAX_TASK_NUM) { - ptu_invalidate = 1; - qedi->tid_reuse_count[tid] = 0; - } - fw_task_ctx->ystorm_st_context.state.reuse_count = - qedi->tid_reuse_count[tid]; - fw_task_ctx->mstorm_st_context.reuse_count = - qedi->tid_reuse_count[tid]++; - /* Ustorm context */ - fw_task_ctx->ustorm_st_context.rem_rcv_len = resp_sge->sge_len; - fw_task_ctx->ustorm_st_context.exp_data_transfer_len = data_len; - fw_task_ctx->ustorm_st_context.exp_data_sn = 0; - fw_task_ctx->ustorm_st_context.task_type = ISCSI_TASK_TYPE_MIDPATH; - fw_task_ctx->ustorm_st_context.cq_rss_number = 0; - - SET_FIELD(fw_task_ctx->ustorm_st_context.reg1.reg1_map, - ISCSI_REG1_NUM_FAST_SGES, 0); - - fw_task_ctx->ustorm_ag_context.icid = (u16)qedi_conn->iscsi_conn_id; - SET_FIELD(fw_task_ctx->ustorm_ag_context.flags1, - USTORM_ISCSI_TASK_AG_CTX_R2T2RECV, 1); - - fw_task_ctx->ustorm_st_context.lun.lo = be32_to_cpu(lun[0]); - fw_task_ctx->ustorm_st_context.lun.hi = be32_to_cpu(lun[1]); - - qedi_add_to_sq(qedi_conn, task, tid, ptu_invalidate, false); + /* Fill tx AHS and rx buffer */ + if (data_len) { + tx_sgl_task_params.sgl = + (struct scsi_sge *)qedi_conn->gen_pdu.req_bd_tbl; + tx_sgl_task_params.sgl_phys_addr.lo = + (u32)(qedi_conn->gen_pdu.req_dma_addr); + tx_sgl_task_params.sgl_phys_addr.hi = + (u32)((u64)qedi_conn->gen_pdu.req_dma_addr >> 32); + tx_sgl_task_params.total_buffer_size = data_len; + tx_sgl_task_params.num_sges = 1; + + rx_sgl_task_params.sgl = + (struct scsi_sge *)qedi_conn->gen_pdu.resp_bd_tbl; + rx_sgl_task_params.sgl_phys_addr.lo = + (u32)(qedi_conn->gen_pdu.resp_dma_addr); + rx_sgl_task_params.sgl_phys_addr.hi = + (u32)((u64)qedi_conn->gen_pdu.resp_dma_addr >> 32); + rx_sgl_task_params.total_buffer_size = resp_sge->sge_len; + rx_sgl_task_params.num_sges = 1; + } + + /* Fill fw input params */ + task_params.context = fw_task_ctx; + task_params.conn_icid = (u16)qedi_conn->iscsi_conn_id; + task_params.itid = tid; + task_params.cq_rss_number = 0; + task_params.tx_io_size = data_len; + task_params.rx_io_size = resp_sge->sge_len; + + sq_idx = qedi_get_wqe_idx(qedi_conn); + task_params.sqe = &ep->sq[sq_idx]; + + memset(task_params.sqe, 0, sizeof(struct iscsi_wqe)); + rval = init_initiator_nop_out_task(&task_params, + &nop_out_pdu_header, + &tx_sgl_task_params, + &rx_sgl_task_params); + if (rval) + return -1; + qedi_ring_doorbell(qedi_conn); return 0; } @@ -1905,7 +1821,7 @@ int qedi_send_iscsi_nopout(struct qedi_conn *qedi_conn, static int qedi_split_bd(struct qedi_cmd *cmd, u64 addr, int sg_len, int bd_index) { - struct iscsi_sge *bd = cmd->io_tbl.sge_tbl; + struct scsi_sge *bd = cmd->io_tbl.sge_tbl; int frag_size, sg_frags; sg_frags = 0; @@ -1938,7 +1854,7 @@ static int qedi_split_bd(struct qedi_cmd *cmd, u64 addr, int sg_len, static int qedi_map_scsi_sg(struct qedi_ctx *qedi, struct qedi_cmd *cmd) { struct scsi_cmnd *sc = cmd->scsi_cmd; - struct iscsi_sge *bd = cmd->io_tbl.sge_tbl; + struct scsi_sge *bd = cmd->io_tbl.sge_tbl; struct scatterlist *sg; int byte_count = 0; int bd_count = 0; @@ -2040,7 +1956,7 @@ static void qedi_iscsi_map_sg_list(struct qedi_cmd *cmd) if (bd_count == 0) return; } else { - struct iscsi_sge *bd = cmd->io_tbl.sge_tbl; + struct scsi_sge *bd = cmd->io_tbl.sge_tbl; bd[0].sge_addr.lo = 0; bd[0].sge_addr.hi = 0; @@ -2136,244 +2052,182 @@ int qedi_iscsi_send_ioreq(struct iscsi_task *task) struct qedi_conn *qedi_conn = conn->dd_data; struct qedi_cmd *cmd = task->dd_data; struct scsi_cmnd *sc = task->sc; + struct iscsi_cmd_hdr cmd_pdu_header; + struct scsi_sgl_task_params tx_sgl_task_params; + struct scsi_sgl_task_params rx_sgl_task_params; + struct scsi_sgl_task_params *prx_sgl = NULL; + struct scsi_sgl_task_params *ptx_sgl = NULL; + struct iscsi_task_params task_params; + struct iscsi_conn_params conn_params; + struct scsi_initiator_cmd_params cmd_params; struct iscsi_task_context *fw_task_ctx; - struct iscsi_cached_sge_ctx *cached_sge; - struct iscsi_phys_sgl_ctx *phys_sgl; - struct iscsi_virt_sgl_ctx *virt_sgl; - struct ystorm_iscsi_task_st_ctx *yst_cxt; - struct mstorm_iscsi_task_st_ctx *mst_cxt; - struct iscsi_sgl *sgl_struct; - struct iscsi_sge *single_sge; + struct iscsi_cls_conn *cls_conn; struct iscsi_scsi_req *hdr = (struct iscsi_scsi_req *)task->hdr; - struct iscsi_sge *bd = cmd->io_tbl.sge_tbl; - enum iscsi_task_type task_type; - struct iscsi_cmd_hdr *fw_cmd; - u32 lun[2]; - u32 exp_data; - u16 cq_idx = smp_processor_id() % qedi->num_queues; - s16 ptu_invalidate = 0; + enum iscsi_task_type task_type = MAX_ISCSI_TASK_TYPE; + struct qedi_endpoint *ep; + u32 scsi_lun[2]; s16 tid = 0; - u8 num_fast_sgs; + u16 sq_idx = 0; + u16 cq_idx; + int rval = 0; - tid = qedi_get_task_idx(qedi); - if (tid == -1) - return -ENOMEM; + ep = qedi_conn->ep; + cls_conn = qedi_conn->cls_conn; + conn = cls_conn->dd_data; qedi_iscsi_map_sg_list(cmd); + int_to_scsilun(sc->device->lun, (struct scsi_lun *)scsi_lun); - int_to_scsilun(sc->device->lun, (struct scsi_lun *)lun); - fw_task_ctx = qedi_get_task_mem(&qedi->tasks, tid); + tid = qedi_get_task_idx(qedi); + if (tid == -1) + return -ENOMEM; + fw_task_ctx = + (struct iscsi_task_context *)qedi_get_task_mem(&qedi->tasks, tid); memset(fw_task_ctx, 0, sizeof(struct iscsi_task_context)); - cmd->task_id = tid; - /* Ystorm context */ - fw_cmd = &fw_task_ctx->ystorm_st_context.pdu_hdr.cmd; - SET_FIELD(fw_cmd->flags_attr, ISCSI_CMD_HDR_ATTR, ISCSI_ATTR_SIMPLE); + cmd->task_id = tid; + memset(&task_params, 0, sizeof(task_params)); + memset(&cmd_pdu_header, 0, sizeof(cmd_pdu_header)); + memset(&tx_sgl_task_params, 0, sizeof(tx_sgl_task_params)); + memset(&rx_sgl_task_params, 0, sizeof(rx_sgl_task_params)); + memset(&conn_params, 0, sizeof(conn_params)); + memset(&cmd_params, 0, sizeof(cmd_params)); + + cq_idx = smp_processor_id() % qedi->num_queues; + /* Update header info */ + SET_FIELD(cmd_pdu_header.flags_attr, ISCSI_CMD_HDR_ATTR, + ISCSI_ATTR_SIMPLE); if (sc->sc_data_direction == DMA_TO_DEVICE) { - if (conn->session->initial_r2t_en) { - exp_data = min((conn->session->imm_data_en * - conn->max_xmit_dlength), - conn->session->first_burst); - exp_data = min(exp_data, scsi_bufflen(sc)); - fw_task_ctx->ustorm_ag_context.exp_data_acked = - cpu_to_le32(exp_data); - } else { - fw_task_ctx->ustorm_ag_context.exp_data_acked = - min(conn->session->first_burst, scsi_bufflen(sc)); - } - - SET_FIELD(fw_cmd->flags_attr, ISCSI_CMD_HDR_WRITE, 1); + SET_FIELD(cmd_pdu_header.flags_attr, + ISCSI_CMD_HDR_WRITE, 1); task_type = ISCSI_TASK_TYPE_INITIATOR_WRITE; } else { - if (scsi_bufflen(sc)) - SET_FIELD(fw_cmd->flags_attr, ISCSI_CMD_HDR_READ, 1); + SET_FIELD(cmd_pdu_header.flags_attr, + ISCSI_CMD_HDR_READ, 1); task_type = ISCSI_TASK_TYPE_INITIATOR_READ; } - fw_cmd->lun.lo = be32_to_cpu(lun[0]); - fw_cmd->lun.hi = be32_to_cpu(lun[1]); + cmd_pdu_header.lun.lo = be32_to_cpu(scsi_lun[0]); + cmd_pdu_header.lun.hi = be32_to_cpu(scsi_lun[1]); qedi_update_itt_map(qedi, tid, task->itt, cmd); - fw_cmd->itt = qedi_set_itt(tid, get_itt(task->itt)); - fw_cmd->expected_transfer_length = scsi_bufflen(sc); - fw_cmd->cmd_sn = be32_to_cpu(hdr->cmdsn); - fw_cmd->opcode = hdr->opcode; - qedi_cpy_scsi_cdb(sc, (u32 *)fw_cmd->cdb); - - /* Mstorm context */ - fw_task_ctx->mstorm_st_context.sense_db.lo = (u32)cmd->sense_buffer_dma; - fw_task_ctx->mstorm_st_context.sense_db.hi = - (u32)((u64)cmd->sense_buffer_dma >> 32); - fw_task_ctx->mstorm_ag_context.task_cid = qedi_conn->iscsi_conn_id; - fw_task_ctx->mstorm_st_context.task_type = task_type; - - if (qedi->tid_reuse_count[tid] == QEDI_MAX_TASK_NUM) { - ptu_invalidate = 1; - qedi->tid_reuse_count[tid] = 0; - } - fw_task_ctx->ystorm_st_context.state.reuse_count = - qedi->tid_reuse_count[tid]; - fw_task_ctx->mstorm_st_context.reuse_count = - qedi->tid_reuse_count[tid]++; - - /* Ustorm context */ - fw_task_ctx->ustorm_st_context.rem_rcv_len = scsi_bufflen(sc); - fw_task_ctx->ustorm_st_context.exp_data_transfer_len = scsi_bufflen(sc); - fw_task_ctx->ustorm_st_context.exp_data_sn = - be32_to_cpu(hdr->exp_statsn); - fw_task_ctx->ustorm_st_context.task_type = task_type; - fw_task_ctx->ustorm_st_context.cq_rss_number = cq_idx; - fw_task_ctx->ustorm_ag_context.icid = (u16)qedi_conn->iscsi_conn_id; - - SET_FIELD(fw_task_ctx->ustorm_ag_context.flags1, - USTORM_ISCSI_TASK_AG_CTX_R2T2RECV, 1); - SET_FIELD(fw_task_ctx->ustorm_st_context.flags, - USTORM_ISCSI_TASK_ST_CTX_LOCAL_COMP, 0); - - num_fast_sgs = (cmd->io_tbl.sge_valid ? - min((u16)QEDI_FAST_SGE_COUNT, - (u16)cmd->io_tbl.sge_valid) : 0); - SET_FIELD(fw_task_ctx->ustorm_st_context.reg1.reg1_map, - ISCSI_REG1_NUM_FAST_SGES, num_fast_sgs); - - fw_task_ctx->ustorm_st_context.lun.lo = be32_to_cpu(lun[0]); - fw_task_ctx->ustorm_st_context.lun.hi = be32_to_cpu(lun[1]); - - QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_IO, "Total sge count [%d]\n", - cmd->io_tbl.sge_valid); - - yst_cxt = &fw_task_ctx->ystorm_st_context; - mst_cxt = &fw_task_ctx->mstorm_st_context; - /* Tx path */ + cmd_pdu_header.itt = qedi_set_itt(tid, get_itt(task->itt)); + cmd_pdu_header.expected_transfer_length = cpu_to_be32(hdr->data_length); + cmd_pdu_header.hdr_second_dword = ntoh24(hdr->dlength); + cmd_pdu_header.cmd_sn = be32_to_cpu(hdr->cmdsn); + cmd_pdu_header.opcode = hdr->opcode; + qedi_cpy_scsi_cdb(sc, (u32 *)cmd_pdu_header.cdb); + + /* Fill tx AHS and rx buffer */ if (task_type == ISCSI_TASK_TYPE_INITIATOR_WRITE) { - /* not considering superIO or FastIO */ - if (cmd->io_tbl.sge_valid == 1) { - cached_sge = &yst_cxt->state.sgl_ctx_union.cached_sge; - cached_sge->sge.sge_addr.lo = bd[0].sge_addr.lo; - cached_sge->sge.sge_addr.hi = bd[0].sge_addr.hi; - cached_sge->sge.sge_len = bd[0].sge_len; - qedi->cached_sgls++; - } else if ((cmd->io_tbl.sge_valid != 1) && cmd->use_slowpath) { - SET_FIELD(fw_task_ctx->mstorm_st_context.flags.mflags, - ISCSI_MFLAGS_SLOW_IO, 1); - SET_FIELD(fw_task_ctx->ustorm_st_context.reg1.reg1_map, - ISCSI_REG1_NUM_FAST_SGES, 0); - phys_sgl = &yst_cxt->state.sgl_ctx_union.phys_sgl; - phys_sgl->sgl_base.lo = (u32)(cmd->io_tbl.sge_tbl_dma); - phys_sgl->sgl_base.hi = - (u32)((u64)cmd->io_tbl.sge_tbl_dma >> 32); - phys_sgl->sgl_size = cmd->io_tbl.sge_valid; - qedi->slow_sgls++; - } else if ((cmd->io_tbl.sge_valid != 1) && !cmd->use_slowpath) { - SET_FIELD(fw_task_ctx->mstorm_st_context.flags.mflags, - ISCSI_MFLAGS_SLOW_IO, 0); - SET_FIELD(fw_task_ctx->ustorm_st_context.reg1.reg1_map, - ISCSI_REG1_NUM_FAST_SGES, - min((u16)QEDI_FAST_SGE_COUNT, - (u16)cmd->io_tbl.sge_valid)); - virt_sgl = &yst_cxt->state.sgl_ctx_union.virt_sgl; - virt_sgl->sgl_base.lo = (u32)(cmd->io_tbl.sge_tbl_dma); - virt_sgl->sgl_base.hi = + tx_sgl_task_params.sgl = cmd->io_tbl.sge_tbl; + tx_sgl_task_params.sgl_phys_addr.lo = + (u32)(cmd->io_tbl.sge_tbl_dma); + tx_sgl_task_params.sgl_phys_addr.hi = (u32)((u64)cmd->io_tbl.sge_tbl_dma >> 32); - virt_sgl->sgl_initial_offset = - (u32)bd[0].sge_addr.lo & (QEDI_PAGE_SIZE - 1); - qedi->fast_sgls++; - } - fw_task_ctx->mstorm_st_context.sgl_size = cmd->io_tbl.sge_valid; - fw_task_ctx->mstorm_st_context.rem_task_size = scsi_bufflen(sc); - } else { - /* Rx path */ - if (cmd->io_tbl.sge_valid == 1) { - SET_FIELD(fw_task_ctx->mstorm_st_context.flags.mflags, - ISCSI_MFLAGS_SLOW_IO, 0); - SET_FIELD(fw_task_ctx->mstorm_st_context.flags.mflags, - ISCSI_MFLAGS_SINGLE_SGE, 1); - single_sge = &mst_cxt->sgl_union.single_sge; - single_sge->sge_addr.lo = bd[0].sge_addr.lo; - single_sge->sge_addr.hi = bd[0].sge_addr.hi; - single_sge->sge_len = bd[0].sge_len; - qedi->cached_sgls++; - } else if ((cmd->io_tbl.sge_valid != 1) && cmd->use_slowpath) { - sgl_struct = &mst_cxt->sgl_union.sgl_struct; - sgl_struct->sgl_addr.lo = - (u32)(cmd->io_tbl.sge_tbl_dma); - sgl_struct->sgl_addr.hi = - (u32)((u64)cmd->io_tbl.sge_tbl_dma >> 32); - SET_FIELD(fw_task_ctx->mstorm_st_context.flags.mflags, - ISCSI_MFLAGS_SLOW_IO, 1); - SET_FIELD(fw_task_ctx->ustorm_st_context.reg1.reg1_map, - ISCSI_REG1_NUM_FAST_SGES, 0); - sgl_struct->updated_sge_size = 0; - sgl_struct->updated_sge_offset = 0; - qedi->slow_sgls++; - } else if ((cmd->io_tbl.sge_valid != 1) && !cmd->use_slowpath) { - sgl_struct = &mst_cxt->sgl_union.sgl_struct; - sgl_struct->sgl_addr.lo = - (u32)(cmd->io_tbl.sge_tbl_dma); - sgl_struct->sgl_addr.hi = - (u32)((u64)cmd->io_tbl.sge_tbl_dma >> 32); - sgl_struct->byte_offset = - (u32)bd[0].sge_addr.lo & (QEDI_PAGE_SIZE - 1); - SET_FIELD(fw_task_ctx->mstorm_st_context.flags.mflags, - ISCSI_MFLAGS_SLOW_IO, 0); - SET_FIELD(fw_task_ctx->ustorm_st_context.reg1.reg1_map, - ISCSI_REG1_NUM_FAST_SGES, 0); - sgl_struct->updated_sge_size = 0; - sgl_struct->updated_sge_offset = 0; - qedi->fast_sgls++; - } - fw_task_ctx->mstorm_st_context.sgl_size = cmd->io_tbl.sge_valid; - fw_task_ctx->mstorm_st_context.rem_task_size = scsi_bufflen(sc); - } - - if (cmd->io_tbl.sge_valid == 1) - /* Singel-SGL */ - qedi->use_cached_sge = true; - else { + tx_sgl_task_params.total_buffer_size = scsi_bufflen(sc); + tx_sgl_task_params.num_sges = cmd->io_tbl.sge_valid; if (cmd->use_slowpath) - qedi->use_slow_sge = true; - else - qedi->use_fast_sge = true; - } + tx_sgl_task_params.small_mid_sge = true; + } else if (task_type == ISCSI_TASK_TYPE_INITIATOR_READ) { + rx_sgl_task_params.sgl = cmd->io_tbl.sge_tbl; + rx_sgl_task_params.sgl_phys_addr.lo = + (u32)(cmd->io_tbl.sge_tbl_dma); + rx_sgl_task_params.sgl_phys_addr.hi = + (u32)((u64)cmd->io_tbl.sge_tbl_dma >> 32); + rx_sgl_task_params.total_buffer_size = scsi_bufflen(sc); + rx_sgl_task_params.num_sges = cmd->io_tbl.sge_valid; + } + + /* Add conn param */ + conn_params.first_burst_length = conn->session->first_burst; + conn_params.max_send_pdu_length = conn->max_xmit_dlength; + conn_params.max_burst_length = conn->session->max_burst; + if (conn->session->initial_r2t_en) + conn_params.initial_r2t = true; + if (conn->session->imm_data_en) + conn_params.immediate_data = true; + + /* Add cmd params */ + cmd_params.sense_data_buffer_phys_addr.lo = (u32)cmd->sense_buffer_dma; + cmd_params.sense_data_buffer_phys_addr.hi = + (u32)((u64)cmd->sense_buffer_dma >> 32); + /* Fill fw input params */ + task_params.context = fw_task_ctx; + task_params.conn_icid = (u16)qedi_conn->iscsi_conn_id; + task_params.itid = tid; + task_params.cq_rss_number = cq_idx; + if (task_type == ISCSI_TASK_TYPE_INITIATOR_WRITE) + task_params.tx_io_size = scsi_bufflen(sc); + else if (task_type == ISCSI_TASK_TYPE_INITIATOR_READ) + task_params.rx_io_size = scsi_bufflen(sc); + + sq_idx = qedi_get_wqe_idx(qedi_conn); + task_params.sqe = &ep->sq[sq_idx]; + QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_IO, - "%s: %s-SGL: num_sges=0x%x first-sge-lo=0x%x first-sge-hi=0x%x", + "%s: %s-SGL: sg_len=0x%x num_sges=0x%x first-sge-lo=0x%x first-sge-hi=0x%x\n", (task_type == ISCSI_TASK_TYPE_INITIATOR_WRITE) ? "Write " : "Read ", (cmd->io_tbl.sge_valid == 1) ? "Single" : (cmd->use_slowpath ? "SLOW" : "FAST"), - (u16)cmd->io_tbl.sge_valid, (u32)(cmd->io_tbl.sge_tbl_dma), + (u16)cmd->io_tbl.sge_valid, scsi_bufflen(sc), + (u32)(cmd->io_tbl.sge_tbl_dma), (u32)((u64)cmd->io_tbl.sge_tbl_dma >> 32)); - /* Add command in active command list */ + memset(task_params.sqe, 0, sizeof(struct iscsi_wqe)); + + if (task_params.tx_io_size != 0) + ptx_sgl = &tx_sgl_task_params; + if (task_params.rx_io_size != 0) + prx_sgl = &rx_sgl_task_params; + + rval = init_initiator_rw_iscsi_task(&task_params, &conn_params, + &cmd_params, &cmd_pdu_header, + ptx_sgl, prx_sgl, + NULL); + if (rval) + return -1; + spin_lock(&qedi_conn->list_lock); list_add_tail(&cmd->io_cmd, &qedi_conn->active_cmd_list); cmd->io_cmd_in_list = true; qedi_conn->active_cmd_count++; spin_unlock(&qedi_conn->list_lock); - qedi_add_to_sq(qedi_conn, task, tid, ptu_invalidate, false); qedi_ring_doorbell(qedi_conn); - if (qedi_io_tracing) - qedi_trace_io(qedi, task, tid, QEDI_IO_TRACE_REQ); - return 0; } int qedi_iscsi_cleanup_task(struct iscsi_task *task, bool mark_cmd_node_deleted) { + struct iscsi_task_params task_params; + struct qedi_endpoint *ep; struct iscsi_conn *conn = task->conn; struct qedi_conn *qedi_conn = conn->dd_data; struct qedi_cmd *cmd = task->dd_data; - s16 ptu_invalidate = 0; + u16 sq_idx = 0; + int rval = 0; QEDI_INFO(&qedi_conn->qedi->dbg_ctx, QEDI_LOG_SCSI_TM, "issue cleanup tid=0x%x itt=0x%x task_state=%d cmd_state=0%x cid=0x%x\n", cmd->task_id, get_itt(task->itt), task->state, cmd->state, qedi_conn->iscsi_conn_id); - qedi_add_to_sq(qedi_conn, task, cmd->task_id, ptu_invalidate, true); - qedi_ring_doorbell(qedi_conn); + memset(&task_params, 0, sizeof(task_params)); + ep = qedi_conn->ep; + + sq_idx = qedi_get_wqe_idx(qedi_conn); + + task_params.sqe = &ep->sq[sq_idx]; + memset(task_params.sqe, 0, sizeof(struct iscsi_wqe)); + task_params.itid = cmd->task_id; + rval = init_cleanup_task(&task_params); + if (rval) + return rval; + + qedi_ring_doorbell(qedi_conn); return 0; } diff --git a/drivers/scsi/qedi/qedi_fw_api.c b/drivers/scsi/qedi/qedi_fw_api.c new file mode 100644 index 000000000000..fd354d4e03eb --- /dev/null +++ b/drivers/scsi/qedi/qedi_fw_api.c @@ -0,0 +1,781 @@ +/* QLogic iSCSI Offload Driver + * Copyright (c) 2016 Cavium Inc. + * + * This software is available under the terms of the GNU General Public License + * (GPL) Version 2, available from the file COPYING in the main directory of + * this source tree. + */ + +#include <linux/types.h> +#include <asm/byteorder.h> +#include "qedi_hsi.h" +#include <linux/qed/qed_if.h> + +#include "qedi_fw_iscsi.h" +#include "qedi_fw_scsi.h" + +#define SCSI_NUM_SGES_IN_CACHE 0x4 + +static bool scsi_is_slow_sgl(u16 num_sges, bool small_mid_sge) +{ + return (num_sges > SCSI_NUM_SGES_SLOW_SGL_THR && small_mid_sge); +} + +static +void init_scsi_sgl_context(struct scsi_sgl_params *ctx_sgl_params, + struct scsi_cached_sges *ctx_data_desc, + struct scsi_sgl_task_params *sgl_task_params) +{ + u8 sge_index; + u8 num_sges; + u32 val; + + num_sges = (sgl_task_params->num_sges > SCSI_NUM_SGES_IN_CACHE) ? + SCSI_NUM_SGES_IN_CACHE : sgl_task_params->num_sges; + + /* sgl params */ + val = cpu_to_le32(sgl_task_params->sgl_phys_addr.lo); + ctx_sgl_params->sgl_addr.lo = val; + val = cpu_to_le32(sgl_task_params->sgl_phys_addr.hi); + ctx_sgl_params->sgl_addr.hi = val; + val = cpu_to_le32(sgl_task_params->total_buffer_size); + ctx_sgl_params->sgl_total_length = val; + ctx_sgl_params->sgl_num_sges = cpu_to_le16(sgl_task_params->num_sges); + + for (sge_index = 0; sge_index < num_sges; sge_index++) { + val = cpu_to_le32(sgl_task_params->sgl[sge_index].sge_addr.lo); + ctx_data_desc->sge[sge_index].sge_addr.lo = val; + val = cpu_to_le32(sgl_task_params->sgl[sge_index].sge_addr.hi); + ctx_data_desc->sge[sge_index].sge_addr.hi = val; + val = cpu_to_le32(sgl_task_params->sgl[sge_index].sge_len); + ctx_data_desc->sge[sge_index].sge_len = val; + } +} + +static u32 calc_rw_task_size(struct iscsi_task_params *task_params, + enum iscsi_task_type task_type, + struct scsi_sgl_task_params *sgl_task_params, + struct scsi_dif_task_params *dif_task_params) +{ + u32 io_size; + + if (task_type == ISCSI_TASK_TYPE_INITIATOR_WRITE || + task_type == ISCSI_TASK_TYPE_TARGET_READ) + io_size = task_params->tx_io_size; + else + io_size = task_params->rx_io_size; + + if (!io_size) + return 0; + + if (!dif_task_params) + return io_size; + + return !dif_task_params->dif_on_network ? + io_size : sgl_task_params->total_buffer_size; +} + +static void +init_dif_context_flags(struct iscsi_dif_flags *ctx_dif_flags, + struct scsi_dif_task_params *dif_task_params) +{ + if (!dif_task_params) + return; + + SET_FIELD(ctx_dif_flags->flags, ISCSI_DIF_FLAGS_PROT_INTERVAL_SIZE_LOG, + dif_task_params->dif_block_size_log); + SET_FIELD(ctx_dif_flags->flags, ISCSI_DIF_FLAGS_DIF_TO_PEER, + dif_task_params->dif_on_network ? 1 : 0); + SET_FIELD(ctx_dif_flags->flags, ISCSI_DIF_FLAGS_HOST_INTERFACE, + dif_task_params->dif_on_host ? 1 : 0); +} + +static void init_sqe(struct iscsi_task_params *task_params, + struct scsi_sgl_task_params *sgl_task_params, + struct scsi_dif_task_params *dif_task_params, + struct iscsi_common_hdr *pdu_header, + struct scsi_initiator_cmd_params *cmd_params, + enum iscsi_task_type task_type, + bool is_cleanup) +{ + if (!task_params->sqe) + return; + + memset(task_params->sqe, 0, sizeof(*task_params->sqe)); + task_params->sqe->task_id = cpu_to_le16(task_params->itid); + if (is_cleanup) { + SET_FIELD(task_params->sqe->flags, ISCSI_WQE_WQE_TYPE, + ISCSI_WQE_TYPE_TASK_CLEANUP); + return; + } + + switch (task_type) { + case ISCSI_TASK_TYPE_INITIATOR_WRITE: + { + u32 buf_size = 0; + u32 num_sges = 0; + + init_dif_context_flags(&task_params->sqe->prot_flags, + dif_task_params); + + SET_FIELD(task_params->sqe->flags, ISCSI_WQE_WQE_TYPE, + ISCSI_WQE_TYPE_NORMAL); + + if (task_params->tx_io_size) { + buf_size = calc_rw_task_size(task_params, task_type, + sgl_task_params, + dif_task_params); + + if (scsi_is_slow_sgl(sgl_task_params->num_sges, + sgl_task_params->small_mid_sge)) + num_sges = ISCSI_WQE_NUM_SGES_SLOWIO; + else + num_sges = min(sgl_task_params->num_sges, + (u16)SCSI_NUM_SGES_SLOW_SGL_THR); + } + + SET_FIELD(task_params->sqe->flags, ISCSI_WQE_NUM_SGES, num_sges); + SET_FIELD(task_params->sqe->contlen_cdbsize, ISCSI_WQE_CONT_LEN, + buf_size); + + if (GET_FIELD(pdu_header->hdr_second_dword, + ISCSI_CMD_HDR_TOTAL_AHS_LEN)) + SET_FIELD(task_params->sqe->contlen_cdbsize, ISCSI_WQE_CDB_SIZE, + cmd_params->extended_cdb_sge.sge_len); + } + break; + case ISCSI_TASK_TYPE_INITIATOR_READ: + SET_FIELD(task_params->sqe->flags, ISCSI_WQE_WQE_TYPE, + ISCSI_WQE_TYPE_NORMAL); + + if (GET_FIELD(pdu_header->hdr_second_dword, + ISCSI_CMD_HDR_TOTAL_AHS_LEN)) + SET_FIELD(task_params->sqe->contlen_cdbsize, + ISCSI_WQE_CDB_SIZE, + cmd_params->extended_cdb_sge.sge_len); + break; + case ISCSI_TASK_TYPE_LOGIN_RESPONSE: + case ISCSI_TASK_TYPE_MIDPATH: + { + bool advance_statsn = true; + + if (task_type == ISCSI_TASK_TYPE_LOGIN_RESPONSE) + SET_FIELD(task_params->sqe->flags, ISCSI_WQE_WQE_TYPE, + ISCSI_WQE_TYPE_LOGIN); + else + SET_FIELD(task_params->sqe->flags, ISCSI_WQE_WQE_TYPE, + ISCSI_WQE_TYPE_MIDDLE_PATH); + + if (task_type == ISCSI_TASK_TYPE_MIDPATH) { + u8 opcode = GET_FIELD(pdu_header->hdr_first_byte, + ISCSI_COMMON_HDR_OPCODE); + + if (opcode != ISCSI_OPCODE_TEXT_RESPONSE && + (opcode != ISCSI_OPCODE_NOP_IN || + pdu_header->itt == ISCSI_TTT_ALL_ONES)) + advance_statsn = false; + } + + SET_FIELD(task_params->sqe->flags, ISCSI_WQE_RESPONSE, + advance_statsn ? 1 : 0); + + if (task_params->tx_io_size) { + SET_FIELD(task_params->sqe->contlen_cdbsize, + ISCSI_WQE_CONT_LEN, task_params->tx_io_size); + + if (scsi_is_slow_sgl(sgl_task_params->num_sges, + sgl_task_params->small_mid_sge)) + SET_FIELD(task_params->sqe->flags, ISCSI_WQE_NUM_SGES, + ISCSI_WQE_NUM_SGES_SLOWIO); + else + SET_FIELD(task_params->sqe->flags, ISCSI_WQE_NUM_SGES, + min(sgl_task_params->num_sges, + (u16)SCSI_NUM_SGES_SLOW_SGL_THR)); + } + } + break; + default: + break; + } +} + +static void init_default_iscsi_task(struct iscsi_task_params *task_params, + struct data_hdr *pdu_header, + enum iscsi_task_type task_type) +{ + struct iscsi_task_context *context; + u16 index; + u32 val; + + context = task_params->context; + memset(context, 0, sizeof(*context)); + + for (index = 0; index < + ARRAY_SIZE(context->ystorm_st_context.pdu_hdr.data.data); + index++) { + val = cpu_to_le32(pdu_header->data[index]); + context->ystorm_st_context.pdu_hdr.data.data[index] = val; + } + + context->mstorm_st_context.task_type = task_type; + context->mstorm_ag_context.task_cid = + cpu_to_le16(task_params->conn_icid); + + SET_FIELD(context->ustorm_ag_context.flags1, + USTORM_ISCSI_TASK_AG_CTX_R2T2RECV, 1); + + context->ustorm_st_context.task_type = task_type; + context->ustorm_st_context.cq_rss_number = task_params->cq_rss_number; + context->ustorm_ag_context.icid = cpu_to_le16(task_params->conn_icid); +} + +static +void init_initiator_rw_cdb_ystorm_context(struct ystorm_iscsi_task_st_ctx *ystc, + struct scsi_initiator_cmd_params *cmd) +{ + union iscsi_task_hdr *ctx_pdu_hdr = &ystc->pdu_hdr; + u32 val; + + if (!cmd->extended_cdb_sge.sge_len) + return; + + SET_FIELD(ctx_pdu_hdr->ext_cdb_cmd.hdr_second_dword, + ISCSI_EXT_CDB_CMD_HDR_CDB_SIZE, + cmd->extended_cdb_sge.sge_len); + val = cpu_to_le32(cmd->extended_cdb_sge.sge_addr.lo); + ctx_pdu_hdr->ext_cdb_cmd.cdb_sge.sge_addr.lo = val; + val = cpu_to_le32(cmd->extended_cdb_sge.sge_addr.hi); + ctx_pdu_hdr->ext_cdb_cmd.cdb_sge.sge_addr.hi = val; + val = cpu_to_le32(cmd->extended_cdb_sge.sge_len); + ctx_pdu_hdr->ext_cdb_cmd.cdb_sge.sge_len = val; +} + +static +void init_ustorm_task_contexts(struct ustorm_iscsi_task_st_ctx *ustorm_st_cxt, + struct ustorm_iscsi_task_ag_ctx *ustorm_ag_cxt, + u32 remaining_recv_len, + u32 expected_data_transfer_len, + u8 num_sges, bool tx_dif_conn_err_en) +{ + u32 val; + + ustorm_st_cxt->rem_rcv_len = cpu_to_le32(remaining_recv_len); + ustorm_ag_cxt->exp_data_acked = cpu_to_le32(expected_data_transfer_len); + val = cpu_to_le32(expected_data_transfer_len); + ustorm_st_cxt->exp_data_transfer_len = val; + SET_FIELD(ustorm_st_cxt->reg1.reg1_map, ISCSI_REG1_NUM_SGES, num_sges); + SET_FIELD(ustorm_ag_cxt->flags2, + USTORM_ISCSI_TASK_AG_CTX_DIF_ERROR_CF_EN, + tx_dif_conn_err_en ? 1 : 0); +} + +static +void set_rw_exp_data_acked_and_cont_len(struct iscsi_task_context *context, + struct iscsi_conn_params *conn_params, + enum iscsi_task_type task_type, + u32 task_size, + u32 exp_data_transfer_len, + u8 total_ahs_length) +{ + u32 max_unsolicited_data = 0, val; + + if (total_ahs_length && + (task_type == ISCSI_TASK_TYPE_INITIATOR_WRITE || + task_type == ISCSI_TASK_TYPE_INITIATOR_READ)) + SET_FIELD(context->ustorm_st_context.flags2, + USTORM_ISCSI_TASK_ST_CTX_AHS_EXIST, 1); + + switch (task_type) { + case ISCSI_TASK_TYPE_INITIATOR_WRITE: + if (!conn_params->initial_r2t) + max_unsolicited_data = conn_params->first_burst_length; + else if (conn_params->immediate_data) + max_unsolicited_data = + min(conn_params->first_burst_length, + conn_params->max_send_pdu_length); + + context->ustorm_ag_context.exp_data_acked = + cpu_to_le32(total_ahs_length == 0 ? + min(exp_data_transfer_len, + max_unsolicited_data) : + ((u32)(total_ahs_length + + ISCSI_AHS_CNTL_SIZE))); + break; + case ISCSI_TASK_TYPE_TARGET_READ: + val = cpu_to_le32(exp_data_transfer_len); + context->ustorm_ag_context.exp_data_acked = val; + break; + case ISCSI_TASK_TYPE_INITIATOR_READ: + context->ustorm_ag_context.exp_data_acked = + cpu_to_le32((total_ahs_length == 0 ? 0 : + total_ahs_length + + ISCSI_AHS_CNTL_SIZE)); + break; + case ISCSI_TASK_TYPE_TARGET_WRITE: + val = cpu_to_le32(task_size); + context->ustorm_ag_context.exp_cont_len = val; + break; + default: + break; + } +} + +static +void init_rtdif_task_context(struct rdif_task_context *rdif_context, + struct tdif_task_context *tdif_context, + struct scsi_dif_task_params *dif_task_params, + enum iscsi_task_type task_type) +{ + u32 val; + + if (!dif_task_params->dif_on_network || !dif_task_params->dif_on_host) + return; + + if (task_type == ISCSI_TASK_TYPE_TARGET_WRITE || + task_type == ISCSI_TASK_TYPE_INITIATOR_READ) { + rdif_context->app_tag_value = + cpu_to_le16(dif_task_params->application_tag); + rdif_context->partial_crc_value = cpu_to_le16(0xffff); + val = cpu_to_le32(dif_task_params->initial_ref_tag); + rdif_context->initial_ref_tag = val; + rdif_context->app_tag_mask = + cpu_to_le16(dif_task_params->application_tag_mask); + SET_FIELD(rdif_context->flags0, RDIF_TASK_CONTEXT_CRC_SEED, + dif_task_params->crc_seed ? 1 : 0); + SET_FIELD(rdif_context->flags0, RDIF_TASK_CONTEXT_HOSTGUARDTYPE, + dif_task_params->host_guard_type); + SET_FIELD(rdif_context->flags0, + RDIF_TASK_CONTEXT_PROTECTIONTYPE, + dif_task_params->protection_type); + SET_FIELD(rdif_context->flags0, + RDIF_TASK_CONTEXT_INITIALREFTAGVALID, 1); + SET_FIELD(rdif_context->flags0, + RDIF_TASK_CONTEXT_KEEPREFTAGCONST, + dif_task_params->keep_ref_tag_const ? 1 : 0); + SET_FIELD(rdif_context->flags1, + RDIF_TASK_CONTEXT_VALIDATEAPPTAG, + (dif_task_params->validate_app_tag && + dif_task_params->dif_on_network) ? 1 : 0); + SET_FIELD(rdif_context->flags1, + RDIF_TASK_CONTEXT_VALIDATEGUARD, + (dif_task_params->validate_guard && + dif_task_params->dif_on_network) ? 1 : 0); + SET_FIELD(rdif_context->flags1, + RDIF_TASK_CONTEXT_VALIDATEREFTAG, + (dif_task_params->validate_ref_tag && + dif_task_params->dif_on_network) ? 1 : 0); + SET_FIELD(rdif_context->flags1, + RDIF_TASK_CONTEXT_HOSTINTERFACE, + dif_task_params->dif_on_host ? 1 : 0); + SET_FIELD(rdif_context->flags1, + RDIF_TASK_CONTEXT_NETWORKINTERFACE, + dif_task_params->dif_on_network ? 1 : 0); + SET_FIELD(rdif_context->flags1, + RDIF_TASK_CONTEXT_FORWARDGUARD, + dif_task_params->forward_guard ? 1 : 0); + SET_FIELD(rdif_context->flags1, + RDIF_TASK_CONTEXT_FORWARDAPPTAG, + dif_task_params->forward_app_tag ? 1 : 0); + SET_FIELD(rdif_context->flags1, + RDIF_TASK_CONTEXT_FORWARDREFTAG, + dif_task_params->forward_ref_tag ? 1 : 0); + SET_FIELD(rdif_context->flags1, + RDIF_TASK_CONTEXT_FORWARDAPPTAGWITHMASK, + dif_task_params->forward_app_tag_with_mask ? 1 : 0); + SET_FIELD(rdif_context->flags1, + RDIF_TASK_CONTEXT_FORWARDREFTAGWITHMASK, + dif_task_params->forward_ref_tag_with_mask ? 1 : 0); + SET_FIELD(rdif_context->flags1, + RDIF_TASK_CONTEXT_INTERVALSIZE, + dif_task_params->dif_block_size_log - 9); + SET_FIELD(rdif_context->state, + RDIF_TASK_CONTEXT_REFTAGMASK, + dif_task_params->ref_tag_mask); + SET_FIELD(rdif_context->state, RDIF_TASK_CONTEXT_IGNOREAPPTAG, + dif_task_params->ignore_app_tag); + } + + if (task_type == ISCSI_TASK_TYPE_TARGET_READ || + task_type == ISCSI_TASK_TYPE_INITIATOR_WRITE) { + tdif_context->app_tag_value = + cpu_to_le16(dif_task_params->application_tag); + tdif_context->partial_crc_valueB = + cpu_to_le16(dif_task_params->crc_seed ? 0xffff : 0x0000); + tdif_context->partial_crc_value_a = + cpu_to_le16(dif_task_params->crc_seed ? 0xffff : 0x0000); + SET_FIELD(tdif_context->flags0, TDIF_TASK_CONTEXT_CRC_SEED, + dif_task_params->crc_seed ? 1 : 0); + + SET_FIELD(tdif_context->flags0, + TDIF_TASK_CONTEXT_SETERRORWITHEOP, + dif_task_params->tx_dif_conn_err_en ? 1 : 0); + SET_FIELD(tdif_context->flags1, TDIF_TASK_CONTEXT_FORWARDGUARD, + dif_task_params->forward_guard ? 1 : 0); + SET_FIELD(tdif_context->flags1, TDIF_TASK_CONTEXT_FORWARDAPPTAG, + dif_task_params->forward_app_tag ? 1 : 0); + SET_FIELD(tdif_context->flags1, TDIF_TASK_CONTEXT_FORWARDREFTAG, + dif_task_params->forward_ref_tag ? 1 : 0); + SET_FIELD(tdif_context->flags1, TDIF_TASK_CONTEXT_INTERVALSIZE, + dif_task_params->dif_block_size_log - 9); + SET_FIELD(tdif_context->flags1, TDIF_TASK_CONTEXT_HOSTINTERFACE, + dif_task_params->dif_on_host ? 1 : 0); + SET_FIELD(tdif_context->flags1, + TDIF_TASK_CONTEXT_NETWORKINTERFACE, + dif_task_params->dif_on_network ? 1 : 0); + val = cpu_to_le32(dif_task_params->initial_ref_tag); + tdif_context->initial_ref_tag = val; + tdif_context->app_tag_mask = + cpu_to_le16(dif_task_params->application_tag_mask); + SET_FIELD(tdif_context->flags0, + TDIF_TASK_CONTEXT_HOSTGUARDTYPE, + dif_task_params->host_guard_type); + SET_FIELD(tdif_context->flags0, + TDIF_TASK_CONTEXT_PROTECTIONTYPE, + dif_task_params->protection_type); + SET_FIELD(tdif_context->flags0, + TDIF_TASK_CONTEXT_INITIALREFTAGVALID, + dif_task_params->initial_ref_tag_is_valid ? 1 : 0); + SET_FIELD(tdif_context->flags0, + TDIF_TASK_CONTEXT_KEEPREFTAGCONST, + dif_task_params->keep_ref_tag_const ? 1 : 0); + SET_FIELD(tdif_context->flags1, TDIF_TASK_CONTEXT_VALIDATEGUARD, + (dif_task_params->validate_guard && + dif_task_params->dif_on_host) ? 1 : 0); + SET_FIELD(tdif_context->flags1, + TDIF_TASK_CONTEXT_VALIDATEAPPTAG, + (dif_task_params->validate_app_tag && + dif_task_params->dif_on_host) ? 1 : 0); + SET_FIELD(tdif_context->flags1, + TDIF_TASK_CONTEXT_VALIDATEREFTAG, + (dif_task_params->validate_ref_tag && + dif_task_params->dif_on_host) ? 1 : 0); + SET_FIELD(tdif_context->flags1, + TDIF_TASK_CONTEXT_FORWARDAPPTAGWITHMASK, + dif_task_params->forward_app_tag_with_mask ? 1 : 0); + SET_FIELD(tdif_context->flags1, + TDIF_TASK_CONTEXT_FORWARDREFTAGWITHMASK, + dif_task_params->forward_ref_tag_with_mask ? 1 : 0); + SET_FIELD(tdif_context->flags1, + TDIF_TASK_CONTEXT_REFTAGMASK, + dif_task_params->ref_tag_mask); + SET_FIELD(tdif_context->flags0, + TDIF_TASK_CONTEXT_IGNOREAPPTAG, + dif_task_params->ignore_app_tag ? 1 : 0); + } +} + +static void set_local_completion_context(struct iscsi_task_context *context) +{ + SET_FIELD(context->ystorm_st_context.state.flags, + YSTORM_ISCSI_TASK_STATE_LOCAL_COMP, 1); + SET_FIELD(context->ustorm_st_context.flags, + USTORM_ISCSI_TASK_ST_CTX_LOCAL_COMP, 1); +} + +static int init_rw_iscsi_task(struct iscsi_task_params *task_params, + enum iscsi_task_type task_type, + struct iscsi_conn_params *conn_params, + struct iscsi_common_hdr *pdu_header, + struct scsi_sgl_task_params *sgl_task_params, + struct scsi_initiator_cmd_params *cmd_params, + struct scsi_dif_task_params *dif_task_params) +{ + u32 exp_data_transfer_len = conn_params->max_burst_length; + struct iscsi_task_context *cxt; + bool slow_io = false; + u32 task_size, val; + u8 num_sges = 0; + + task_size = calc_rw_task_size(task_params, task_type, sgl_task_params, + dif_task_params); + + init_default_iscsi_task(task_params, (struct data_hdr *)pdu_header, + task_type); + + cxt = task_params->context; + + val = cpu_to_le32(task_size); + cxt->ystorm_st_context.pdu_hdr.cmd.expected_transfer_length = val; + init_initiator_rw_cdb_ystorm_context(&cxt->ystorm_st_context, + cmd_params); + val = cpu_to_le32(cmd_params->sense_data_buffer_phys_addr.lo); + cxt->mstorm_st_context.sense_db.lo = val; + + val = cpu_to_le32(cmd_params->sense_data_buffer_phys_addr.hi); + cxt->mstorm_st_context.sense_db.hi = val; + + if (task_params->tx_io_size) { + init_dif_context_flags(&cxt->ystorm_st_context.state.dif_flags, + dif_task_params); + init_scsi_sgl_context(&cxt->ystorm_st_context.state.sgl_params, + &cxt->ystorm_st_context.state.data_desc, + sgl_task_params); + + slow_io = scsi_is_slow_sgl(sgl_task_params->num_sges, + sgl_task_params->small_mid_sge); + + num_sges = !slow_io ? min_t(u16, sgl_task_params->num_sges, + (u16)SCSI_NUM_SGES_SLOW_SGL_THR) : + ISCSI_WQE_NUM_SGES_SLOWIO; + + if (slow_io) { + SET_FIELD(cxt->ystorm_st_context.state.flags, + YSTORM_ISCSI_TASK_STATE_SLOW_IO, 1); + } + } else if (task_params->rx_io_size) { + init_dif_context_flags(&cxt->mstorm_st_context.dif_flags, + dif_task_params); + init_scsi_sgl_context(&cxt->mstorm_st_context.sgl_params, + &cxt->mstorm_st_context.data_desc, + sgl_task_params); + num_sges = !scsi_is_slow_sgl(sgl_task_params->num_sges, + sgl_task_params->small_mid_sge) ? + min_t(u16, sgl_task_params->num_sges, + (u16)SCSI_NUM_SGES_SLOW_SGL_THR) : + ISCSI_WQE_NUM_SGES_SLOWIO; + cxt->mstorm_st_context.rem_task_size = cpu_to_le32(task_size); + } + + if (exp_data_transfer_len > task_size || + task_type != ISCSI_TASK_TYPE_TARGET_WRITE) + exp_data_transfer_len = task_size; + + init_ustorm_task_contexts(&task_params->context->ustorm_st_context, + &task_params->context->ustorm_ag_context, + task_size, exp_data_transfer_len, num_sges, + dif_task_params ? + dif_task_params->tx_dif_conn_err_en : false); + + set_rw_exp_data_acked_and_cont_len(task_params->context, conn_params, + task_type, task_size, + exp_data_transfer_len, + GET_FIELD(pdu_header->hdr_second_dword, + ISCSI_CMD_HDR_TOTAL_AHS_LEN)); + + if (dif_task_params) + init_rtdif_task_context(&task_params->context->rdif_context, + &task_params->context->tdif_context, + dif_task_params, task_type); + + init_sqe(task_params, sgl_task_params, dif_task_params, pdu_header, + cmd_params, task_type, false); + + return 0; +} + +int init_initiator_rw_iscsi_task(struct iscsi_task_params *task_params, + struct iscsi_conn_params *conn_params, + struct scsi_initiator_cmd_params *cmd_params, + struct iscsi_cmd_hdr *cmd_header, + struct scsi_sgl_task_params *tx_sgl_params, + struct scsi_sgl_task_params *rx_sgl_params, + struct scsi_dif_task_params *dif_task_params) +{ + if (GET_FIELD(cmd_header->flags_attr, ISCSI_CMD_HDR_WRITE)) + return init_rw_iscsi_task(task_params, + ISCSI_TASK_TYPE_INITIATOR_WRITE, + conn_params, + (struct iscsi_common_hdr *)cmd_header, + tx_sgl_params, cmd_params, + dif_task_params); + else if (GET_FIELD(cmd_header->flags_attr, ISCSI_CMD_HDR_READ)) + return init_rw_iscsi_task(task_params, + ISCSI_TASK_TYPE_INITIATOR_READ, + conn_params, + (struct iscsi_common_hdr *)cmd_header, + rx_sgl_params, cmd_params, + dif_task_params); + else + return -1; +} + +int init_initiator_login_request_task(struct iscsi_task_params *task_params, + struct iscsi_login_req_hdr *login_header, + struct scsi_sgl_task_params *tx_params, + struct scsi_sgl_task_params *rx_params) +{ + struct iscsi_task_context *cxt; + + cxt = task_params->context; + + init_default_iscsi_task(task_params, + (struct data_hdr *)login_header, + ISCSI_TASK_TYPE_MIDPATH); + + init_ustorm_task_contexts(&cxt->ustorm_st_context, + &cxt->ustorm_ag_context, + task_params->rx_io_size ? + rx_params->total_buffer_size : 0, + task_params->tx_io_size ? + tx_params->total_buffer_size : 0, 0, + 0); + + if (task_params->tx_io_size) + init_scsi_sgl_context(&cxt->ystorm_st_context.state.sgl_params, + &cxt->ystorm_st_context.state.data_desc, + tx_params); + + if (task_params->rx_io_size) + init_scsi_sgl_context(&cxt->mstorm_st_context.sgl_params, + &cxt->mstorm_st_context.data_desc, + rx_params); + + cxt->mstorm_st_context.rem_task_size = + cpu_to_le32(task_params->rx_io_size ? + rx_params->total_buffer_size : 0); + + init_sqe(task_params, tx_params, NULL, + (struct iscsi_common_hdr *)login_header, NULL, + ISCSI_TASK_TYPE_MIDPATH, false); + + return 0; +} + +int init_initiator_nop_out_task(struct iscsi_task_params *task_params, + struct iscsi_nop_out_hdr *nop_out_pdu_header, + struct scsi_sgl_task_params *tx_sgl_task_params, + struct scsi_sgl_task_params *rx_sgl_task_params) +{ + struct iscsi_task_context *cxt; + + cxt = task_params->context; + + init_default_iscsi_task(task_params, + (struct data_hdr *)nop_out_pdu_header, + ISCSI_TASK_TYPE_MIDPATH); + + if (nop_out_pdu_header->itt == ISCSI_ITT_ALL_ONES) + set_local_completion_context(task_params->context); + + if (task_params->tx_io_size) + init_scsi_sgl_context(&cxt->ystorm_st_context.state.sgl_params, + &cxt->ystorm_st_context.state.data_desc, + tx_sgl_task_params); + + if (task_params->rx_io_size) + init_scsi_sgl_context(&cxt->mstorm_st_context.sgl_params, + &cxt->mstorm_st_context.data_desc, + rx_sgl_task_params); + + init_ustorm_task_contexts(&cxt->ustorm_st_context, + &cxt->ustorm_ag_context, + task_params->rx_io_size ? + rx_sgl_task_params->total_buffer_size : 0, + task_params->tx_io_size ? + tx_sgl_task_params->total_buffer_size : 0, + 0, 0); + + cxt->mstorm_st_context.rem_task_size = + cpu_to_le32(task_params->rx_io_size ? + rx_sgl_task_params->total_buffer_size : + 0); + + init_sqe(task_params, tx_sgl_task_params, NULL, + (struct iscsi_common_hdr *)nop_out_pdu_header, NULL, + ISCSI_TASK_TYPE_MIDPATH, false); + + return 0; +} + +int init_initiator_logout_request_task(struct iscsi_task_params *task_params, + struct iscsi_logout_req_hdr *logout_hdr, + struct scsi_sgl_task_params *tx_params, + struct scsi_sgl_task_params *rx_params) +{ + struct iscsi_task_context *cxt; + + cxt = task_params->context; + + init_default_iscsi_task(task_params, + (struct data_hdr *)logout_hdr, + ISCSI_TASK_TYPE_MIDPATH); + + if (task_params->tx_io_size) + init_scsi_sgl_context(&cxt->ystorm_st_context.state.sgl_params, + &cxt->ystorm_st_context.state.data_desc, + tx_params); + + if (task_params->rx_io_size) + init_scsi_sgl_context(&cxt->mstorm_st_context.sgl_params, + &cxt->mstorm_st_context.data_desc, + rx_params); + + init_ustorm_task_contexts(&cxt->ustorm_st_context, + &cxt->ustorm_ag_context, + task_params->rx_io_size ? + rx_params->total_buffer_size : 0, + task_params->tx_io_size ? + tx_params->total_buffer_size : 0, + 0, 0); + + cxt->mstorm_st_context.rem_task_size = + cpu_to_le32(task_params->rx_io_size ? + rx_params->total_buffer_size : 0); + + init_sqe(task_params, tx_params, NULL, + (struct iscsi_common_hdr *)logout_hdr, NULL, + ISCSI_TASK_TYPE_MIDPATH, false); + + return 0; +} + +int init_initiator_tmf_request_task(struct iscsi_task_params *task_params, + struct iscsi_tmf_request_hdr *tmf_header) +{ + init_default_iscsi_task(task_params, (struct data_hdr *)tmf_header, + ISCSI_TASK_TYPE_MIDPATH); + + init_sqe(task_params, NULL, NULL, + (struct iscsi_common_hdr *)tmf_header, NULL, + ISCSI_TASK_TYPE_MIDPATH, false); + + return 0; +} + +int init_initiator_text_request_task(struct iscsi_task_params *task_params, + struct iscsi_text_request_hdr *text_header, + struct scsi_sgl_task_params *tx_params, + struct scsi_sgl_task_params *rx_params) +{ + struct iscsi_task_context *cxt; + + cxt = task_params->context; + + init_default_iscsi_task(task_params, + (struct data_hdr *)text_header, + ISCSI_TASK_TYPE_MIDPATH); + + if (task_params->tx_io_size) + init_scsi_sgl_context(&cxt->ystorm_st_context.state.sgl_params, + &cxt->ystorm_st_context.state.data_desc, + tx_params); + + if (task_params->rx_io_size) + init_scsi_sgl_context(&cxt->mstorm_st_context.sgl_params, + &cxt->mstorm_st_context.data_desc, + rx_params); + + cxt->mstorm_st_context.rem_task_size = + cpu_to_le32(task_params->rx_io_size ? + rx_params->total_buffer_size : 0); + + init_ustorm_task_contexts(&cxt->ustorm_st_context, + &cxt->ustorm_ag_context, + task_params->rx_io_size ? + rx_params->total_buffer_size : 0, + task_params->tx_io_size ? + tx_params->total_buffer_size : 0, 0, 0); + + init_sqe(task_params, tx_params, NULL, + (struct iscsi_common_hdr *)text_header, NULL, + ISCSI_TASK_TYPE_MIDPATH, false); + + return 0; +} + +int init_cleanup_task(struct iscsi_task_params *task_params) +{ + init_sqe(task_params, NULL, NULL, NULL, NULL, ISCSI_TASK_TYPE_MIDPATH, + true); + return 0; +} diff --git a/drivers/scsi/qedi/qedi_fw_iscsi.h b/drivers/scsi/qedi/qedi_fw_iscsi.h new file mode 100644 index 000000000000..b6f24f91849d --- /dev/null +++ b/drivers/scsi/qedi/qedi_fw_iscsi.h @@ -0,0 +1,117 @@ +/* + * QLogic iSCSI Offload Driver + * Copyright (c) 2016 Cavium Inc. + * + * This software is available under the terms of the GNU General Public License + * (GPL) Version 2, available from the file COPYING in the main directory of + * this source tree. + */ + +#ifndef _QEDI_FW_ISCSI_H_ +#define _QEDI_FW_ISCSI_H_ + +#include "qedi_fw_scsi.h" + +struct iscsi_task_params { + struct iscsi_task_context *context; + struct iscsi_wqe *sqe; + u32 tx_io_size; + u32 rx_io_size; + u16 conn_icid; + u16 itid; + u8 cq_rss_number; +}; + +struct iscsi_conn_params { + u32 first_burst_length; + u32 max_send_pdu_length; + u32 max_burst_length; + bool initial_r2t; + bool immediate_data; +}; + +/* @brief init_initiator_read_iscsi_task - initializes iSCSI Initiator Read + * task context. + * + * @param task_params - Pointer to task parameters struct + * @param conn_params - Connection Parameters + * @param cmd_params - command specific parameters + * @param cmd_pdu_header - PDU Header Parameters + * @param sgl_task_params - Pointer to SGL task params + * @param dif_task_params - Pointer to DIF parameters struct + */ +int init_initiator_rw_iscsi_task(struct iscsi_task_params *task_params, + struct iscsi_conn_params *conn_params, + struct scsi_initiator_cmd_params *cmd_params, + struct iscsi_cmd_hdr *cmd_pdu_header, + struct scsi_sgl_task_params *tx_sgl_params, + struct scsi_sgl_task_params *rx_sgl_params, + struct scsi_dif_task_params *dif_task_params); + +/* @brief init_initiator_login_request_task - initializes iSCSI Initiator Login + * Request task context. + * + * @param task_params - Pointer to task parameters struct + * @param login_req_pdu_header - PDU Header Parameters + * @param tx_sgl_task_params - Pointer to SGL task params + * @param rx_sgl_task_params - Pointer to SGL task params + */ +int init_initiator_login_request_task(struct iscsi_task_params *task_params, + struct iscsi_login_req_hdr *login_header, + struct scsi_sgl_task_params *tx_params, + struct scsi_sgl_task_params *rx_params); + +/* @brief init_initiator_nop_out_task - initializes iSCSI Initiator NOP Out + * task context. + * + * @param task_params - Pointer to task parameters struct + * @param nop_out_pdu_header - PDU Header Parameters + * @param tx_sgl_task_params - Pointer to SGL task params + * @param rx_sgl_task_params - Pointer to SGL task params + */ +int init_initiator_nop_out_task(struct iscsi_task_params *task_params, + struct iscsi_nop_out_hdr *nop_out_pdu_header, + struct scsi_sgl_task_params *tx_sgl_params, + struct scsi_sgl_task_params *rx_sgl_params); + +/* @brief init_initiator_logout_request_task - initializes iSCSI Initiator + * Logout Request task context. + * + * @param task_params - Pointer to task parameters struct + * @param logout_pdu_header - PDU Header Parameters + * @param tx_sgl_task_params - Pointer to SGL task params + * @param rx_sgl_task_params - Pointer to SGL task params + */ +int init_initiator_logout_request_task(struct iscsi_task_params *task_params, + struct iscsi_logout_req_hdr *logout_hdr, + struct scsi_sgl_task_params *tx_params, + struct scsi_sgl_task_params *rx_params); + +/* @brief init_initiator_tmf_request_task - initializes iSCSI Initiator TMF + * task context. + * + * @param task_params - Pointer to task parameters struct + * @param tmf_pdu_header - PDU Header Parameters + */ +int init_initiator_tmf_request_task(struct iscsi_task_params *task_params, + struct iscsi_tmf_request_hdr *tmf_header); + +/* @brief init_initiator_text_request_task - initializes iSCSI Initiator Text + * Request task context. + * + * @param task_params - Pointer to task parameters struct + * @param text_request_pdu_header - PDU Header Parameters + * @param tx_sgl_task_params - Pointer to Tx SGL task params + * @param rx_sgl_task_params - Pointer to Rx SGL task params + */ +int init_initiator_text_request_task(struct iscsi_task_params *task_params, + struct iscsi_text_request_hdr *text_header, + struct scsi_sgl_task_params *tx_params, + struct scsi_sgl_task_params *rx_params); + +/* @brief init_cleanup_task - initializes Clean task (SQE) + * + * @param task_params - Pointer to task parameters struct + */ +int init_cleanup_task(struct iscsi_task_params *task_params); +#endif diff --git a/drivers/scsi/qedi/qedi_fw_scsi.h b/drivers/scsi/qedi/qedi_fw_scsi.h new file mode 100644 index 000000000000..cdaf918f1019 --- /dev/null +++ b/drivers/scsi/qedi/qedi_fw_scsi.h @@ -0,0 +1,55 @@ +/* + * QLogic iSCSI Offload Driver + * Copyright (c) 2016 Cavium Inc. + * + * This software is available under the terms of the GNU General Public License + * (GPL) Version 2, available from the file COPYING in the main directory of + * this source tree. + */ + +#ifndef _QEDI_FW_SCSI_H_ +#define _QEDI_FW_SCSI_H_ + +#include <linux/types.h> +#include <asm/byteorder.h> +#include "qedi_hsi.h" +#include <linux/qed/qed_if.h> + +struct scsi_sgl_task_params { + struct scsi_sge *sgl; + struct regpair sgl_phys_addr; + u32 total_buffer_size; + u16 num_sges; + bool small_mid_sge; +}; + +struct scsi_dif_task_params { + u32 initial_ref_tag; + bool initial_ref_tag_is_valid; + u16 application_tag; + u16 application_tag_mask; + u16 dif_block_size_log; + bool dif_on_network; + bool dif_on_host; + u8 host_guard_type; + u8 protection_type; + u8 ref_tag_mask; + bool crc_seed; + bool tx_dif_conn_err_en; + bool ignore_app_tag; + bool keep_ref_tag_const; + bool validate_guard; + bool validate_app_tag; + bool validate_ref_tag; + bool forward_guard; + bool forward_app_tag; + bool forward_ref_tag; + bool forward_app_tag_with_mask; + bool forward_ref_tag_with_mask; +}; + +struct scsi_initiator_cmd_params { + struct scsi_sge extended_cdb_sge; + struct regpair sense_data_buffer_phys_addr; +}; +#endif diff --git a/drivers/scsi/qedi/qedi_gbl.h b/drivers/scsi/qedi/qedi_gbl.h index 8e488de88ece..63d793f46064 100644 --- a/drivers/scsi/qedi/qedi_gbl.h +++ b/drivers/scsi/qedi/qedi_gbl.h @@ -12,8 +12,14 @@ #include "qedi_iscsi.h" +#ifdef CONFIG_DEBUG_FS +extern int qedi_do_not_recover; +#else +#define qedi_do_not_recover (0) +#endif + extern uint qedi_io_tracing; -extern int do_not_recover; + extern struct scsi_host_template qedi_host_template; extern struct iscsi_transport qedi_iscsi_transport; extern const struct qed_iscsi_ops *qedi_ops; diff --git a/drivers/scsi/qedi/qedi_iscsi.c b/drivers/scsi/qedi/qedi_iscsi.c index b9f79d36142d..d1de172bebac 100644 --- a/drivers/scsi/qedi/qedi_iscsi.c +++ b/drivers/scsi/qedi/qedi_iscsi.c @@ -175,7 +175,7 @@ static void qedi_destroy_cmd_pool(struct qedi_ctx *qedi, if (cmd->io_tbl.sge_tbl) dma_free_coherent(&qedi->pdev->dev, QEDI_ISCSI_MAX_BDS_PER_CMD * - sizeof(struct iscsi_sge), + sizeof(struct scsi_sge), cmd->io_tbl.sge_tbl, cmd->io_tbl.sge_tbl_dma); @@ -191,7 +191,7 @@ static int qedi_alloc_sget(struct qedi_ctx *qedi, struct iscsi_session *session, struct qedi_cmd *cmd) { struct qedi_io_bdt *io = &cmd->io_tbl; - struct iscsi_sge *sge; + struct scsi_sge *sge; io->sge_tbl = dma_alloc_coherent(&qedi->pdev->dev, QEDI_ISCSI_MAX_BDS_PER_CMD * @@ -708,22 +708,20 @@ static void qedi_conn_get_stats(struct iscsi_cls_conn *cls_conn, static void qedi_iscsi_prep_generic_pdu_bd(struct qedi_conn *qedi_conn) { - struct iscsi_sge *bd_tbl; + struct scsi_sge *bd_tbl; - bd_tbl = (struct iscsi_sge *)qedi_conn->gen_pdu.req_bd_tbl; + bd_tbl = (struct scsi_sge *)qedi_conn->gen_pdu.req_bd_tbl; bd_tbl->sge_addr.hi = (u32)((u64)qedi_conn->gen_pdu.req_dma_addr >> 32); bd_tbl->sge_addr.lo = (u32)qedi_conn->gen_pdu.req_dma_addr; bd_tbl->sge_len = qedi_conn->gen_pdu.req_wr_ptr - qedi_conn->gen_pdu.req_buf; - bd_tbl->reserved0 = 0; - bd_tbl = (struct iscsi_sge *)qedi_conn->gen_pdu.resp_bd_tbl; + bd_tbl = (struct scsi_sge *)qedi_conn->gen_pdu.resp_bd_tbl; bd_tbl->sge_addr.hi = (u32)((u64)qedi_conn->gen_pdu.resp_dma_addr >> 32); bd_tbl->sge_addr.lo = (u32)qedi_conn->gen_pdu.resp_dma_addr; bd_tbl->sge_len = ISCSI_DEF_MAX_RECV_SEG_LEN; - bd_tbl->reserved0 = 0; } static int qedi_iscsi_send_generic_request(struct iscsi_task *task) @@ -833,7 +831,7 @@ qedi_ep_connect(struct Scsi_Host *shost, struct sockaddr *dst_addr, return ERR_PTR(ret); } - if (do_not_recover) { + if (qedi_do_not_recover) { ret = -ENOMEM; return ERR_PTR(ret); } @@ -957,7 +955,7 @@ static int qedi_ep_poll(struct iscsi_endpoint *ep, int timeout_ms) struct qedi_endpoint *qedi_ep; int ret = 0; - if (do_not_recover) + if (qedi_do_not_recover) return 1; qedi_ep = ep->dd_data; @@ -1025,7 +1023,7 @@ static void qedi_ep_disconnect(struct iscsi_endpoint *ep) } if (test_bit(QEDI_IN_RECOVERY, &qedi->flags)) { - if (do_not_recover) { + if (qedi_do_not_recover) { QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_INFO, "Do not recover cid=0x%x\n", qedi_ep->iscsi_cid); @@ -1039,7 +1037,7 @@ static void qedi_ep_disconnect(struct iscsi_endpoint *ep) } } - if (do_not_recover) + if (qedi_do_not_recover) goto ep_exit_recover; switch (qedi_ep->state) { diff --git a/drivers/scsi/qedi/qedi_iscsi.h b/drivers/scsi/qedi/qedi_iscsi.h index d3c06bbddb4e..3247287cb0e7 100644 --- a/drivers/scsi/qedi/qedi_iscsi.h +++ b/drivers/scsi/qedi/qedi_iscsi.h @@ -102,7 +102,7 @@ struct qedi_endpoint { #define QEDI_SQ_WQES_MIN 16 struct qedi_io_bdt { - struct iscsi_sge *sge_tbl; + struct scsi_sge *sge_tbl; dma_addr_t sge_tbl_dma; u16 sge_valid; }; diff --git a/drivers/scsi/qedi/qedi_main.c b/drivers/scsi/qedi/qedi_main.c index 5eda21d903e9..8e3d92807cb8 100644 --- a/drivers/scsi/qedi/qedi_main.c +++ b/drivers/scsi/qedi/qedi_main.c @@ -1805,7 +1805,7 @@ static int __qedi_probe(struct pci_dev *pdev, int mode) */ qedi_ops->common->update_pf_params(qedi->cdev, &qedi->pf_params); - qedi_setup_int(qedi); + rc = qedi_setup_int(qedi); if (rc) goto stop_iscsi_func; diff --git a/drivers/scsi/qedi/qedi_version.h b/drivers/scsi/qedi/qedi_version.h index 9543a1b139d4..d61e3ac22e67 100644 --- a/drivers/scsi/qedi/qedi_version.h +++ b/drivers/scsi/qedi/qedi_version.h @@ -7,8 +7,8 @@ * this source tree. */ -#define QEDI_MODULE_VERSION "8.10.3.0" +#define QEDI_MODULE_VERSION "8.10.4.0" #define QEDI_DRIVER_MAJOR_VER 8 #define QEDI_DRIVER_MINOR_VER 10 -#define QEDI_DRIVER_REV_VER 3 +#define QEDI_DRIVER_REV_VER 4 #define QEDI_DRIVER_ENG_VER 0 diff --git a/drivers/scsi/qla2xxx/qla_dbg.c b/drivers/scsi/qla2xxx/qla_dbg.c index 21d9fb7fc887..51b4179469d1 100644 --- a/drivers/scsi/qla2xxx/qla_dbg.c +++ b/drivers/scsi/qla2xxx/qla_dbg.c @@ -2707,13 +2707,9 @@ ql_dump_buffer(uint32_t level, scsi_qla_host_t *vha, int32_t id, "%-+5d 0 1 2 3 4 5 6 7 8 9 A B C D E F\n", size); ql_dbg(level, vha, id, "----- -----------------------------------------------\n"); - for (cnt = 0; cnt < size; cnt++, buf++) { - if (cnt % 16 == 0) - ql_dbg(level, vha, id, "%04x:", cnt & ~0xFU); - printk(" %02x", *buf); - if (cnt % 16 == 15) - printk("\n"); + for (cnt = 0; cnt < size; cnt += 16) { + ql_dbg(level, vha, id, "%04x: ", cnt); + print_hex_dump(KERN_CONT, "", DUMP_PREFIX_NONE, 16, 1, + buf + cnt, min(16U, size - cnt), false); } - if (cnt % 16 != 0) - printk("\n"); } diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c index ba2286652ff6..19125d72f322 100644 --- a/drivers/scsi/scsi_lib.c +++ b/drivers/scsi/scsi_lib.c @@ -2932,6 +2932,8 @@ EXPORT_SYMBOL(scsi_target_resume); /** * scsi_internal_device_block - internal function to put a device temporarily into the SDEV_BLOCK state * @sdev: device to block + * @wait: Whether or not to wait until ongoing .queuecommand() / + * .queue_rq() calls have finished. * * Block request made by scsi lld's to temporarily stop all * scsi commands on the specified device. May sleep. @@ -2949,7 +2951,7 @@ EXPORT_SYMBOL(scsi_target_resume); * remove the rport mutex lock and unlock calls from srp_queuecommand(). */ int -scsi_internal_device_block(struct scsi_device *sdev) +scsi_internal_device_block(struct scsi_device *sdev, bool wait) { struct request_queue *q = sdev->request_queue; unsigned long flags; @@ -2969,12 +2971,16 @@ scsi_internal_device_block(struct scsi_device *sdev) * request queue. */ if (q->mq_ops) { - blk_mq_quiesce_queue(q); + if (wait) + blk_mq_quiesce_queue(q); + else + blk_mq_stop_hw_queues(q); } else { spin_lock_irqsave(q->queue_lock, flags); blk_stop_queue(q); spin_unlock_irqrestore(q->queue_lock, flags); - scsi_wait_for_queuecommand(sdev); + if (wait) + scsi_wait_for_queuecommand(sdev); } return 0; @@ -3036,7 +3042,7 @@ EXPORT_SYMBOL_GPL(scsi_internal_device_unblock); static void device_block(struct scsi_device *sdev, void *data) { - scsi_internal_device_block(sdev); + scsi_internal_device_block(sdev, true); } static int diff --git a/drivers/scsi/scsi_priv.h b/drivers/scsi/scsi_priv.h index 99bfc985e190..f11bd102d6d5 100644 --- a/drivers/scsi/scsi_priv.h +++ b/drivers/scsi/scsi_priv.h @@ -188,8 +188,5 @@ static inline void scsi_dh_remove_device(struct scsi_device *sdev) { } */ #define SCSI_DEVICE_BLOCK_MAX_TIMEOUT 600 /* units in seconds */ -extern int scsi_internal_device_block(struct scsi_device *sdev); -extern int scsi_internal_device_unblock(struct scsi_device *sdev, - enum scsi_device_state new_state); #endif /* _SCSI_PRIV_H */ diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c index c7839f6c35cc..fcfeddc79331 100644 --- a/drivers/scsi/sd.c +++ b/drivers/scsi/sd.c @@ -1783,6 +1783,8 @@ static int sd_done(struct scsi_cmnd *SCpnt) { int result = SCpnt->result; unsigned int good_bytes = result ? 0 : scsi_bufflen(SCpnt); + unsigned int sector_size = SCpnt->device->sector_size; + unsigned int resid; struct scsi_sense_hdr sshdr; struct scsi_disk *sdkp = scsi_disk(SCpnt->request->rq_disk); struct request *req = SCpnt->request; @@ -1813,6 +1815,21 @@ static int sd_done(struct scsi_cmnd *SCpnt) scsi_set_resid(SCpnt, blk_rq_bytes(req)); } break; + default: + /* + * In case of bogus fw or device, we could end up having + * an unaligned partial completion. Check this here and force + * alignment. + */ + resid = scsi_get_resid(SCpnt); + if (resid & (sector_size - 1)) { + sd_printk(KERN_INFO, sdkp, + "Unaligned partial completion (resid=%u, sector_sz=%u)\n", + resid, sector_size); + resid = min(scsi_bufflen(SCpnt), + round_up(resid, sector_size)); + scsi_set_resid(SCpnt, resid); + } } if (result) { @@ -3075,23 +3092,6 @@ static void sd_probe_async(void *data, async_cookie_t cookie) put_device(&sdkp->dev); } -struct sd_devt { - int idx; - struct disk_devt disk_devt; -}; - -static void sd_devt_release(struct disk_devt *disk_devt) -{ - struct sd_devt *sd_devt = container_of(disk_devt, struct sd_devt, - disk_devt); - - spin_lock(&sd_index_lock); - ida_remove(&sd_index_ida, sd_devt->idx); - spin_unlock(&sd_index_lock); - - kfree(sd_devt); -} - /** * sd_probe - called during driver initialization and whenever a * new scsi device is attached to the system. It is called once @@ -3113,7 +3113,6 @@ static void sd_devt_release(struct disk_devt *disk_devt) static int sd_probe(struct device *dev) { struct scsi_device *sdp = to_scsi_device(dev); - struct sd_devt *sd_devt; struct scsi_disk *sdkp; struct gendisk *gd; int index; @@ -3139,13 +3138,9 @@ static int sd_probe(struct device *dev) if (!sdkp) goto out; - sd_devt = kzalloc(sizeof(*sd_devt), GFP_KERNEL); - if (!sd_devt) - goto out_free; - gd = alloc_disk(SD_MINORS); if (!gd) - goto out_free_devt; + goto out_free; do { if (!ida_pre_get(&sd_index_ida, GFP_KERNEL)) @@ -3161,11 +3156,6 @@ static int sd_probe(struct device *dev) goto out_put; } - atomic_set(&sd_devt->disk_devt.count, 1); - sd_devt->disk_devt.release = sd_devt_release; - sd_devt->idx = index; - gd->disk_devt = &sd_devt->disk_devt; - error = sd_format_disk_name("sd", index, gd->disk_name, DISK_NAME_LEN); if (error) { sdev_printk(KERN_WARNING, sdp, "SCSI disk (sd) name length exceeded.\n"); @@ -3205,12 +3195,11 @@ static int sd_probe(struct device *dev) return 0; out_free_index: - put_disk_devt(&sd_devt->disk_devt); - sd_devt = NULL; + spin_lock(&sd_index_lock); + ida_remove(&sd_index_ida, index); + spin_unlock(&sd_index_lock); out_put: put_disk(gd); - out_free_devt: - kfree(sd_devt); out_free: kfree(sdkp); out: @@ -3271,7 +3260,10 @@ static void scsi_disk_release(struct device *dev) struct scsi_disk *sdkp = to_scsi_disk(dev); struct gendisk *disk = sdkp->disk; - put_disk_devt(disk->disk_devt); + spin_lock(&sd_index_lock); + ida_remove(&sd_index_ida, sdkp->index); + spin_unlock(&sd_index_lock); + disk->private_data = NULL; put_disk(disk); put_device(&sdkp->device->sdev_gendev); diff --git a/drivers/scsi/storvsc_drv.c b/drivers/scsi/storvsc_drv.c index 638e5f427c90..016639d7fef1 100644 --- a/drivers/scsi/storvsc_drv.c +++ b/drivers/scsi/storvsc_drv.c @@ -400,8 +400,6 @@ MODULE_PARM_DESC(storvsc_vcpus_per_sub_channel, "Ratio of VCPUs to subchannels") */ static int storvsc_timeout = 180; -static int msft_blist_flags = BLIST_TRY_VPD_PAGES; - #if IS_ENABLED(CONFIG_SCSI_FC_ATTRS) static struct scsi_transport_template *fc_transport_template; #endif @@ -1383,6 +1381,22 @@ static int storvsc_do_io(struct hv_device *device, return ret; } +static int storvsc_device_alloc(struct scsi_device *sdevice) +{ + /* + * Set blist flag to permit the reading of the VPD pages even when + * the target may claim SPC-2 compliance. MSFT targets currently + * claim SPC-2 compliance while they implement post SPC-2 features. + * With this flag we can correctly handle WRITE_SAME_16 issues. + * + * Hypervisor reports SCSI_UNKNOWN type for DVD ROM device but + * still supports REPORT LUN. + */ + sdevice->sdev_bflags = BLIST_REPORTLUN2 | BLIST_TRY_VPD_PAGES; + + return 0; +} + static int storvsc_device_configure(struct scsi_device *sdevice) { @@ -1396,14 +1410,6 @@ static int storvsc_device_configure(struct scsi_device *sdevice) sdevice->no_write_same = 1; /* - * Add blist flags to permit the reading of the VPD pages even when - * the target may claim SPC-2 compliance. MSFT targets currently - * claim SPC-2 compliance while they implement post SPC-2 features. - * With this patch we can correctly handle WRITE_SAME_16 issues. - */ - sdevice->sdev_bflags |= msft_blist_flags; - - /* * If the host is WIN8 or WIN8 R2, claim conformance to SPC-3 * if the device is a MSFT virtual device. If the host is * WIN10 or newer, allow write_same. @@ -1661,6 +1667,7 @@ static struct scsi_host_template scsi_driver = { .eh_host_reset_handler = storvsc_host_reset_handler, .proc_name = "storvsc_host", .eh_timed_out = storvsc_eh_timed_out, + .slave_alloc = storvsc_device_alloc, .slave_configure = storvsc_device_configure, .cmd_per_lun = 255, .this_id = -1, diff --git a/drivers/scsi/ufs/ufs.h b/drivers/scsi/ufs/ufs.h index 318e4a1f76c9..54deeb754db5 100644 --- a/drivers/scsi/ufs/ufs.h +++ b/drivers/scsi/ufs/ufs.h @@ -146,7 +146,7 @@ enum attr_idn { /* Descriptor idn for Query requests */ enum desc_idn { QUERY_DESC_IDN_DEVICE = 0x0, - QUERY_DESC_IDN_CONFIGURAION = 0x1, + QUERY_DESC_IDN_CONFIGURATION = 0x1, QUERY_DESC_IDN_UNIT = 0x2, QUERY_DESC_IDN_RFU_0 = 0x3, QUERY_DESC_IDN_INTERCONNECT = 0x4, @@ -162,19 +162,13 @@ enum desc_header_offset { QUERY_DESC_DESC_TYPE_OFFSET = 0x01, }; -enum ufs_desc_max_size { - QUERY_DESC_DEVICE_MAX_SIZE = 0x40, - QUERY_DESC_CONFIGURAION_MAX_SIZE = 0x90, - QUERY_DESC_UNIT_MAX_SIZE = 0x23, - QUERY_DESC_INTERCONNECT_MAX_SIZE = 0x06, - /* - * Max. 126 UNICODE characters (2 bytes per character) plus 2 bytes - * of descriptor header. - */ - QUERY_DESC_STRING_MAX_SIZE = 0xFE, - QUERY_DESC_GEOMETRY_MAX_SIZE = 0x44, - QUERY_DESC_POWER_MAX_SIZE = 0x62, - QUERY_DESC_RFU_MAX_SIZE = 0x00, +enum ufs_desc_def_size { + QUERY_DESC_DEVICE_DEF_SIZE = 0x40, + QUERY_DESC_CONFIGURATION_DEF_SIZE = 0x90, + QUERY_DESC_UNIT_DEF_SIZE = 0x23, + QUERY_DESC_INTERCONNECT_DEF_SIZE = 0x06, + QUERY_DESC_GEOMETRY_DEF_SIZE = 0x44, + QUERY_DESC_POWER_DEF_SIZE = 0x62, }; /* Unit descriptor parameters offsets in bytes*/ diff --git a/drivers/scsi/ufs/ufshcd.c b/drivers/scsi/ufs/ufshcd.c index dc6efbd1be8e..1359913bf840 100644 --- a/drivers/scsi/ufs/ufshcd.c +++ b/drivers/scsi/ufs/ufshcd.c @@ -100,19 +100,6 @@ #define ufshcd_hex_dump(prefix_str, buf, len) \ print_hex_dump(KERN_ERR, prefix_str, DUMP_PREFIX_OFFSET, 16, 4, buf, len, false) -static u32 ufs_query_desc_max_size[] = { - QUERY_DESC_DEVICE_MAX_SIZE, - QUERY_DESC_CONFIGURAION_MAX_SIZE, - QUERY_DESC_UNIT_MAX_SIZE, - QUERY_DESC_RFU_MAX_SIZE, - QUERY_DESC_INTERCONNECT_MAX_SIZE, - QUERY_DESC_STRING_MAX_SIZE, - QUERY_DESC_RFU_MAX_SIZE, - QUERY_DESC_GEOMETRY_MAX_SIZE, - QUERY_DESC_POWER_MAX_SIZE, - QUERY_DESC_RFU_MAX_SIZE, -}; - enum { UFSHCD_MAX_CHANNEL = 0, UFSHCD_MAX_ID = 1, @@ -2857,7 +2844,7 @@ static int __ufshcd_query_descriptor(struct ufs_hba *hba, goto out; } - if (*buf_len <= QUERY_DESC_MIN_SIZE || *buf_len > QUERY_DESC_MAX_SIZE) { + if (*buf_len < QUERY_DESC_MIN_SIZE || *buf_len > QUERY_DESC_MAX_SIZE) { dev_err(hba->dev, "%s: descriptor buffer size (%d) is out of range\n", __func__, *buf_len); err = -EINVAL; @@ -2938,6 +2925,92 @@ static int ufshcd_query_descriptor_retry(struct ufs_hba *hba, } /** + * ufshcd_read_desc_length - read the specified descriptor length from header + * @hba: Pointer to adapter instance + * @desc_id: descriptor idn value + * @desc_index: descriptor index + * @desc_length: pointer to variable to read the length of descriptor + * + * Return 0 in case of success, non-zero otherwise + */ +static int ufshcd_read_desc_length(struct ufs_hba *hba, + enum desc_idn desc_id, + int desc_index, + int *desc_length) +{ + int ret; + u8 header[QUERY_DESC_HDR_SIZE]; + int header_len = QUERY_DESC_HDR_SIZE; + + if (desc_id >= QUERY_DESC_IDN_MAX) + return -EINVAL; + + ret = ufshcd_query_descriptor_retry(hba, UPIU_QUERY_OPCODE_READ_DESC, + desc_id, desc_index, 0, header, + &header_len); + + if (ret) { + dev_err(hba->dev, "%s: Failed to get descriptor header id %d", + __func__, desc_id); + return ret; + } else if (desc_id != header[QUERY_DESC_DESC_TYPE_OFFSET]) { + dev_warn(hba->dev, "%s: descriptor header id %d and desc_id %d mismatch", + __func__, header[QUERY_DESC_DESC_TYPE_OFFSET], + desc_id); + ret = -EINVAL; + } + + *desc_length = header[QUERY_DESC_LENGTH_OFFSET]; + return ret; + +} + +/** + * ufshcd_map_desc_id_to_length - map descriptor IDN to its length + * @hba: Pointer to adapter instance + * @desc_id: descriptor idn value + * @desc_len: mapped desc length (out) + * + * Return 0 in case of success, non-zero otherwise + */ +int ufshcd_map_desc_id_to_length(struct ufs_hba *hba, + enum desc_idn desc_id, int *desc_len) +{ + switch (desc_id) { + case QUERY_DESC_IDN_DEVICE: + *desc_len = hba->desc_size.dev_desc; + break; + case QUERY_DESC_IDN_POWER: + *desc_len = hba->desc_size.pwr_desc; + break; + case QUERY_DESC_IDN_GEOMETRY: + *desc_len = hba->desc_size.geom_desc; + break; + case QUERY_DESC_IDN_CONFIGURATION: + *desc_len = hba->desc_size.conf_desc; + break; + case QUERY_DESC_IDN_UNIT: + *desc_len = hba->desc_size.unit_desc; + break; + case QUERY_DESC_IDN_INTERCONNECT: + *desc_len = hba->desc_size.interc_desc; + break; + case QUERY_DESC_IDN_STRING: + *desc_len = QUERY_DESC_MAX_SIZE; + break; + case QUERY_DESC_IDN_RFU_0: + case QUERY_DESC_IDN_RFU_1: + *desc_len = 0; + break; + default: + *desc_len = 0; + return -EINVAL; + } + return 0; +} +EXPORT_SYMBOL(ufshcd_map_desc_id_to_length); + +/** * ufshcd_read_desc_param - read the specified descriptor parameter * @hba: Pointer to adapter instance * @desc_id: descriptor idn value @@ -2951,42 +3024,49 @@ static int ufshcd_query_descriptor_retry(struct ufs_hba *hba, static int ufshcd_read_desc_param(struct ufs_hba *hba, enum desc_idn desc_id, int desc_index, - u32 param_offset, + u8 param_offset, u8 *param_read_buf, - u32 param_size) + u8 param_size) { int ret; u8 *desc_buf; - u32 buff_len; + int buff_len; bool is_kmalloc = true; - /* safety checks */ - if (desc_id >= QUERY_DESC_IDN_MAX) + /* Safety check */ + if (desc_id >= QUERY_DESC_IDN_MAX || !param_size) return -EINVAL; - buff_len = ufs_query_desc_max_size[desc_id]; - if ((param_offset + param_size) > buff_len) - return -EINVAL; + /* Get the max length of descriptor from structure filled up at probe + * time. + */ + ret = ufshcd_map_desc_id_to_length(hba, desc_id, &buff_len); - if (!param_offset && (param_size == buff_len)) { - /* memory space already available to hold full descriptor */ - desc_buf = param_read_buf; - is_kmalloc = false; - } else { - /* allocate memory to hold full descriptor */ + /* Sanity checks */ + if (ret || !buff_len) { + dev_err(hba->dev, "%s: Failed to get full descriptor length", + __func__); + return ret; + } + + /* Check whether we need temp memory */ + if (param_offset != 0 || param_size < buff_len) { desc_buf = kmalloc(buff_len, GFP_KERNEL); if (!desc_buf) return -ENOMEM; + } else { + desc_buf = param_read_buf; + is_kmalloc = false; } + /* Request for full descriptor */ ret = ufshcd_query_descriptor_retry(hba, UPIU_QUERY_OPCODE_READ_DESC, - desc_id, desc_index, 0, desc_buf, - &buff_len); + desc_id, desc_index, 0, + desc_buf, &buff_len); if (ret) { dev_err(hba->dev, "%s: Failed reading descriptor. desc_id %d, desc_index %d, param_offset %d, ret %d", __func__, desc_id, desc_index, param_offset, ret); - goto out; } @@ -2998,25 +3078,9 @@ static int ufshcd_read_desc_param(struct ufs_hba *hba, goto out; } - /* - * While reading variable size descriptors (like string descriptor), - * some UFS devices may report the "LENGTH" (field in "Transaction - * Specific fields" of Query Response UPIU) same as what was requested - * in Query Request UPIU instead of reporting the actual size of the - * variable size descriptor. - * Although it's safe to ignore the "LENGTH" field for variable size - * descriptors as we can always derive the length of the descriptor from - * the descriptor header fields. Hence this change impose the length - * match check only for fixed size descriptors (for which we always - * request the correct size as part of Query Request UPIU). - */ - if ((desc_id != QUERY_DESC_IDN_STRING) && - (buff_len != desc_buf[QUERY_DESC_LENGTH_OFFSET])) { - dev_err(hba->dev, "%s: desc_buf length mismatch: buff_len %d, buff_len(desc_header) %d", - __func__, buff_len, desc_buf[QUERY_DESC_LENGTH_OFFSET]); - ret = -EINVAL; - goto out; - } + /* Check wherher we will not copy more data, than available */ + if (is_kmalloc && param_size > buff_len) + param_size = buff_len; if (is_kmalloc) memcpy(param_read_buf, &desc_buf[param_offset], param_size); @@ -5919,8 +5983,8 @@ static int ufshcd_set_icc_levels_attr(struct ufs_hba *hba, u32 icc_level) static void ufshcd_init_icc_levels(struct ufs_hba *hba) { int ret; - int buff_len = QUERY_DESC_POWER_MAX_SIZE; - u8 desc_buf[QUERY_DESC_POWER_MAX_SIZE]; + int buff_len = hba->desc_size.pwr_desc; + u8 desc_buf[hba->desc_size.pwr_desc]; ret = ufshcd_read_power_desc(hba, desc_buf, buff_len); if (ret) { @@ -6017,11 +6081,10 @@ static int ufs_get_device_desc(struct ufs_hba *hba, { int err; u8 model_index; - u8 str_desc_buf[QUERY_DESC_STRING_MAX_SIZE + 1] = {0}; - u8 desc_buf[QUERY_DESC_DEVICE_MAX_SIZE]; + u8 str_desc_buf[QUERY_DESC_MAX_SIZE + 1] = {0}; + u8 desc_buf[hba->desc_size.dev_desc]; - err = ufshcd_read_device_desc(hba, desc_buf, - QUERY_DESC_DEVICE_MAX_SIZE); + err = ufshcd_read_device_desc(hba, desc_buf, hba->desc_size.dev_desc); if (err) { dev_err(hba->dev, "%s: Failed reading Device Desc. err = %d\n", __func__, err); @@ -6038,14 +6101,14 @@ static int ufs_get_device_desc(struct ufs_hba *hba, model_index = desc_buf[DEVICE_DESC_PARAM_PRDCT_NAME]; err = ufshcd_read_string_desc(hba, model_index, str_desc_buf, - QUERY_DESC_STRING_MAX_SIZE, ASCII_STD); + QUERY_DESC_MAX_SIZE, ASCII_STD); if (err) { dev_err(hba->dev, "%s: Failed reading Product Name. err = %d\n", __func__, err); goto out; } - str_desc_buf[QUERY_DESC_STRING_MAX_SIZE] = '\0'; + str_desc_buf[QUERY_DESC_MAX_SIZE] = '\0'; strlcpy(dev_desc->model, (str_desc_buf + QUERY_DESC_HDR_SIZE), min_t(u8, str_desc_buf[QUERY_DESC_LENGTH_OFFSET], MAX_MODEL_LEN)); @@ -6251,6 +6314,51 @@ static void ufshcd_clear_dbg_ufs_stats(struct ufs_hba *hba) hba->req_abort_count = 0; } +static void ufshcd_init_desc_sizes(struct ufs_hba *hba) +{ + int err; + + err = ufshcd_read_desc_length(hba, QUERY_DESC_IDN_DEVICE, 0, + &hba->desc_size.dev_desc); + if (err) + hba->desc_size.dev_desc = QUERY_DESC_DEVICE_DEF_SIZE; + + err = ufshcd_read_desc_length(hba, QUERY_DESC_IDN_POWER, 0, + &hba->desc_size.pwr_desc); + if (err) + hba->desc_size.pwr_desc = QUERY_DESC_POWER_DEF_SIZE; + + err = ufshcd_read_desc_length(hba, QUERY_DESC_IDN_INTERCONNECT, 0, + &hba->desc_size.interc_desc); + if (err) + hba->desc_size.interc_desc = QUERY_DESC_INTERCONNECT_DEF_SIZE; + + err = ufshcd_read_desc_length(hba, QUERY_DESC_IDN_CONFIGURATION, 0, + &hba->desc_size.conf_desc); + if (err) + hba->desc_size.conf_desc = QUERY_DESC_CONFIGURATION_DEF_SIZE; + + err = ufshcd_read_desc_length(hba, QUERY_DESC_IDN_UNIT, 0, + &hba->desc_size.unit_desc); + if (err) + hba->desc_size.unit_desc = QUERY_DESC_UNIT_DEF_SIZE; + + err = ufshcd_read_desc_length(hba, QUERY_DESC_IDN_GEOMETRY, 0, + &hba->desc_size.geom_desc); + if (err) + hba->desc_size.geom_desc = QUERY_DESC_GEOMETRY_DEF_SIZE; +} + +static void ufshcd_def_desc_sizes(struct ufs_hba *hba) +{ + hba->desc_size.dev_desc = QUERY_DESC_DEVICE_DEF_SIZE; + hba->desc_size.pwr_desc = QUERY_DESC_POWER_DEF_SIZE; + hba->desc_size.interc_desc = QUERY_DESC_INTERCONNECT_DEF_SIZE; + hba->desc_size.conf_desc = QUERY_DESC_CONFIGURATION_DEF_SIZE; + hba->desc_size.unit_desc = QUERY_DESC_UNIT_DEF_SIZE; + hba->desc_size.geom_desc = QUERY_DESC_GEOMETRY_DEF_SIZE; +} + /** * ufshcd_probe_hba - probe hba to detect device and initialize * @hba: per-adapter instance @@ -6285,6 +6393,9 @@ static int ufshcd_probe_hba(struct ufs_hba *hba) if (ret) goto out; + /* Init check for device descriptor sizes */ + ufshcd_init_desc_sizes(hba); + ret = ufs_get_device_desc(hba, &card); if (ret) { dev_err(hba->dev, "%s: Failed getting device info. err = %d\n", @@ -6320,6 +6431,7 @@ static int ufshcd_probe_hba(struct ufs_hba *hba) /* set the state as operational after switching to desired gear */ hba->ufshcd_state = UFSHCD_STATE_OPERATIONAL; + /* * If we are in error handling context or in power management callbacks * context, no need to scan the host @@ -7774,6 +7886,9 @@ int ufshcd_init(struct ufs_hba *hba, void __iomem *mmio_base, unsigned int irq) hba->mmio_base = mmio_base; hba->irq = irq; + /* Set descriptor lengths to specification defaults */ + ufshcd_def_desc_sizes(hba); + err = ufshcd_hba_init(hba); if (err) goto out_error; diff --git a/drivers/scsi/ufs/ufshcd.h b/drivers/scsi/ufs/ufshcd.h index 7630600217a2..cdc8bd05f7df 100644 --- a/drivers/scsi/ufs/ufshcd.h +++ b/drivers/scsi/ufs/ufshcd.h @@ -220,6 +220,15 @@ struct ufs_dev_cmd { struct ufs_query query; }; +struct ufs_desc_size { + int dev_desc; + int pwr_desc; + int geom_desc; + int interc_desc; + int unit_desc; + int conf_desc; +}; + /** * struct ufs_clk_info - UFS clock related info * @list: list headed by hba->clk_list_head @@ -483,6 +492,7 @@ struct ufs_stats { * @clk_list_head: UFS host controller clocks list node head * @pwr_info: holds current power mode * @max_pwr_info: keeps the device max valid pwm + * @desc_size: descriptor sizes reported by device * @urgent_bkops_lvl: keeps track of urgent bkops level for device * @is_urgent_bkops_lvl_checked: keeps track if the urgent bkops level for * device is known or not. @@ -666,6 +676,7 @@ struct ufs_hba { bool is_urgent_bkops_lvl_checked; struct rw_semaphore clk_scaling_lock; + struct ufs_desc_size desc_size; }; /* Returns true if clocks can be gated. Otherwise false */ @@ -832,6 +843,10 @@ int ufshcd_query_flag(struct ufs_hba *hba, enum query_opcode opcode, enum flag_idn idn, bool *flag_res); int ufshcd_hold(struct ufs_hba *hba, bool async); void ufshcd_release(struct ufs_hba *hba); + +int ufshcd_map_desc_id_to_length(struct ufs_hba *hba, enum desc_idn desc_id, + int *desc_length); + u32 ufshcd_get_local_unipro_ver(struct ufs_hba *hba); /* Wrapper functions for safely calling variant operations */ diff --git a/drivers/scsi/vmw_pvscsi.c b/drivers/scsi/vmw_pvscsi.c index ef474a748744..c374e3b5c678 100644 --- a/drivers/scsi/vmw_pvscsi.c +++ b/drivers/scsi/vmw_pvscsi.c @@ -1487,7 +1487,7 @@ static int pvscsi_probe(struct pci_dev *pdev, const struct pci_device_id *id) irq_flag &= ~PCI_IRQ_MSI; error = pci_alloc_irq_vectors(adapter->dev, 1, 1, irq_flag); - if (error) + if (error < 0) goto out_reset_adapter; adapter->use_req_threshold = pvscsi_setup_req_threshold(adapter, true); diff --git a/drivers/staging/lustre/lnet/lnet/lib-socket.c b/drivers/staging/lustre/lnet/lnet/lib-socket.c index b7b87ecefcdf..9fca8d225ee0 100644 --- a/drivers/staging/lustre/lnet/lnet/lib-socket.c +++ b/drivers/staging/lustre/lnet/lnet/lib-socket.c @@ -532,7 +532,7 @@ lnet_sock_accept(struct socket **newsockp, struct socket *sock) newsock->ops = sock->ops; - rc = sock->ops->accept(sock, newsock, O_NONBLOCK); + rc = sock->ops->accept(sock, newsock, O_NONBLOCK, false); if (rc == -EAGAIN) { /* Nothing ready, so wait for activity */ init_waitqueue_entry(&wait, current); @@ -540,7 +540,7 @@ lnet_sock_accept(struct socket **newsockp, struct socket *sock) set_current_state(TASK_INTERRUPTIBLE); schedule(); remove_wait_queue(sk_sleep(sock->sk), &wait); - rc = sock->ops->accept(sock, newsock, O_NONBLOCK); + rc = sock->ops->accept(sock, newsock, O_NONBLOCK, false); } if (rc) diff --git a/drivers/staging/octeon/ethernet-rx.c b/drivers/staging/octeon/ethernet-rx.c index 7f8cf875157c..65a285631994 100644 --- a/drivers/staging/octeon/ethernet-rx.c +++ b/drivers/staging/octeon/ethernet-rx.c @@ -336,7 +336,6 @@ static int cvm_oct_poll(struct oct_rx_group *rx_group, int budget) if (likely((port < TOTAL_NUMBER_OF_PORTS) && cvm_oct_device[port])) { struct net_device *dev = cvm_oct_device[port]; - struct octeon_ethernet *priv = netdev_priv(dev); /* * Only accept packets for devices that are diff --git a/drivers/staging/vc04_services/Kconfig b/drivers/staging/vc04_services/Kconfig index e61e4ca064a8..74094fff4367 100644 --- a/drivers/staging/vc04_services/Kconfig +++ b/drivers/staging/vc04_services/Kconfig @@ -1,6 +1,7 @@ config BCM2835_VCHIQ tristate "Videocore VCHIQ" depends on HAS_DMA + depends on OF depends on RASPBERRYPI_FIRMWARE || (COMPILE_TEST && !RASPBERRYPI_FIRMWARE) default y help diff --git a/drivers/tty/n_hdlc.c b/drivers/tty/n_hdlc.c index 1bacbc3b19a0..e94aea8c0d05 100644 --- a/drivers/tty/n_hdlc.c +++ b/drivers/tty/n_hdlc.c @@ -114,7 +114,7 @@ #define DEFAULT_TX_BUF_COUNT 3 struct n_hdlc_buf { - struct n_hdlc_buf *link; + struct list_head list_item; int count; char buf[1]; }; @@ -122,8 +122,7 @@ struct n_hdlc_buf { #define N_HDLC_BUF_SIZE (sizeof(struct n_hdlc_buf) + maxframe) struct n_hdlc_buf_list { - struct n_hdlc_buf *head; - struct n_hdlc_buf *tail; + struct list_head list; int count; spinlock_t spinlock; }; @@ -136,7 +135,6 @@ struct n_hdlc_buf_list { * @backup_tty - TTY to use if tty gets closed * @tbusy - reentrancy flag for tx wakeup code * @woke_up - FIXME: describe this field - * @tbuf - currently transmitting tx buffer * @tx_buf_list - list of pending transmit frame buffers * @rx_buf_list - list of received frame buffers * @tx_free_buf_list - list unused transmit frame buffers @@ -149,7 +147,6 @@ struct n_hdlc { struct tty_struct *backup_tty; int tbusy; int woke_up; - struct n_hdlc_buf *tbuf; struct n_hdlc_buf_list tx_buf_list; struct n_hdlc_buf_list rx_buf_list; struct n_hdlc_buf_list tx_free_buf_list; @@ -159,6 +156,8 @@ struct n_hdlc { /* * HDLC buffer list manipulation functions */ +static void n_hdlc_buf_return(struct n_hdlc_buf_list *buf_list, + struct n_hdlc_buf *buf); static void n_hdlc_buf_put(struct n_hdlc_buf_list *list, struct n_hdlc_buf *buf); static struct n_hdlc_buf *n_hdlc_buf_get(struct n_hdlc_buf_list *list); @@ -208,16 +207,9 @@ static void flush_tx_queue(struct tty_struct *tty) { struct n_hdlc *n_hdlc = tty2n_hdlc(tty); struct n_hdlc_buf *buf; - unsigned long flags; while ((buf = n_hdlc_buf_get(&n_hdlc->tx_buf_list))) n_hdlc_buf_put(&n_hdlc->tx_free_buf_list, buf); - spin_lock_irqsave(&n_hdlc->tx_buf_list.spinlock, flags); - if (n_hdlc->tbuf) { - n_hdlc_buf_put(&n_hdlc->tx_free_buf_list, n_hdlc->tbuf); - n_hdlc->tbuf = NULL; - } - spin_unlock_irqrestore(&n_hdlc->tx_buf_list.spinlock, flags); } static struct tty_ldisc_ops n_hdlc_ldisc = { @@ -283,7 +275,6 @@ static void n_hdlc_release(struct n_hdlc *n_hdlc) } else break; } - kfree(n_hdlc->tbuf); kfree(n_hdlc); } /* end of n_hdlc_release() */ @@ -402,13 +393,7 @@ static void n_hdlc_send_frames(struct n_hdlc *n_hdlc, struct tty_struct *tty) n_hdlc->woke_up = 0; spin_unlock_irqrestore(&n_hdlc->tx_buf_list.spinlock, flags); - /* get current transmit buffer or get new transmit */ - /* buffer from list of pending transmit buffers */ - - tbuf = n_hdlc->tbuf; - if (!tbuf) - tbuf = n_hdlc_buf_get(&n_hdlc->tx_buf_list); - + tbuf = n_hdlc_buf_get(&n_hdlc->tx_buf_list); while (tbuf) { if (debuglevel >= DEBUG_LEVEL_INFO) printk("%s(%d)sending frame %p, count=%d\n", @@ -420,7 +405,7 @@ static void n_hdlc_send_frames(struct n_hdlc *n_hdlc, struct tty_struct *tty) /* rollback was possible and has been done */ if (actual == -ERESTARTSYS) { - n_hdlc->tbuf = tbuf; + n_hdlc_buf_return(&n_hdlc->tx_buf_list, tbuf); break; } /* if transmit error, throw frame away by */ @@ -435,10 +420,7 @@ static void n_hdlc_send_frames(struct n_hdlc *n_hdlc, struct tty_struct *tty) /* free current transmit buffer */ n_hdlc_buf_put(&n_hdlc->tx_free_buf_list, tbuf); - - /* this tx buffer is done */ - n_hdlc->tbuf = NULL; - + /* wait up sleeping writers */ wake_up_interruptible(&tty->write_wait); @@ -448,10 +430,12 @@ static void n_hdlc_send_frames(struct n_hdlc *n_hdlc, struct tty_struct *tty) if (debuglevel >= DEBUG_LEVEL_INFO) printk("%s(%d)frame %p pending\n", __FILE__,__LINE__,tbuf); - - /* buffer not accepted by driver */ - /* set this buffer as pending buffer */ - n_hdlc->tbuf = tbuf; + + /* + * the buffer was not accepted by driver, + * return it back into tx queue + */ + n_hdlc_buf_return(&n_hdlc->tx_buf_list, tbuf); break; } } @@ -749,7 +733,8 @@ static int n_hdlc_tty_ioctl(struct tty_struct *tty, struct file *file, int error = 0; int count; unsigned long flags; - + struct n_hdlc_buf *buf = NULL; + if (debuglevel >= DEBUG_LEVEL_INFO) printk("%s(%d)n_hdlc_tty_ioctl() called %d\n", __FILE__,__LINE__,cmd); @@ -763,8 +748,10 @@ static int n_hdlc_tty_ioctl(struct tty_struct *tty, struct file *file, /* report count of read data available */ /* in next available frame (if any) */ spin_lock_irqsave(&n_hdlc->rx_buf_list.spinlock,flags); - if (n_hdlc->rx_buf_list.head) - count = n_hdlc->rx_buf_list.head->count; + buf = list_first_entry_or_null(&n_hdlc->rx_buf_list.list, + struct n_hdlc_buf, list_item); + if (buf) + count = buf->count; else count = 0; spin_unlock_irqrestore(&n_hdlc->rx_buf_list.spinlock,flags); @@ -776,8 +763,10 @@ static int n_hdlc_tty_ioctl(struct tty_struct *tty, struct file *file, count = tty_chars_in_buffer(tty); /* add size of next output frame in queue */ spin_lock_irqsave(&n_hdlc->tx_buf_list.spinlock,flags); - if (n_hdlc->tx_buf_list.head) - count += n_hdlc->tx_buf_list.head->count; + buf = list_first_entry_or_null(&n_hdlc->tx_buf_list.list, + struct n_hdlc_buf, list_item); + if (buf) + count += buf->count; spin_unlock_irqrestore(&n_hdlc->tx_buf_list.spinlock,flags); error = put_user(count, (int __user *)arg); break; @@ -825,14 +814,14 @@ static unsigned int n_hdlc_tty_poll(struct tty_struct *tty, struct file *filp, poll_wait(filp, &tty->write_wait, wait); /* set bits for operations that won't block */ - if (n_hdlc->rx_buf_list.head) + if (!list_empty(&n_hdlc->rx_buf_list.list)) mask |= POLLIN | POLLRDNORM; /* readable */ if (test_bit(TTY_OTHER_CLOSED, &tty->flags)) mask |= POLLHUP; if (tty_hung_up_p(filp)) mask |= POLLHUP; if (!tty_is_writelocked(tty) && - n_hdlc->tx_free_buf_list.head) + !list_empty(&n_hdlc->tx_free_buf_list.list)) mask |= POLLOUT | POLLWRNORM; /* writable */ } return mask; @@ -856,7 +845,12 @@ static struct n_hdlc *n_hdlc_alloc(void) spin_lock_init(&n_hdlc->tx_free_buf_list.spinlock); spin_lock_init(&n_hdlc->rx_buf_list.spinlock); spin_lock_init(&n_hdlc->tx_buf_list.spinlock); - + + INIT_LIST_HEAD(&n_hdlc->rx_free_buf_list.list); + INIT_LIST_HEAD(&n_hdlc->tx_free_buf_list.list); + INIT_LIST_HEAD(&n_hdlc->rx_buf_list.list); + INIT_LIST_HEAD(&n_hdlc->tx_buf_list.list); + /* allocate free rx buffer list */ for(i=0;i<DEFAULT_RX_BUF_COUNT;i++) { buf = kmalloc(N_HDLC_BUF_SIZE, GFP_KERNEL); @@ -884,53 +878,65 @@ static struct n_hdlc *n_hdlc_alloc(void) } /* end of n_hdlc_alloc() */ /** + * n_hdlc_buf_return - put the HDLC buffer after the head of the specified list + * @buf_list - pointer to the buffer list + * @buf - pointer to the buffer + */ +static void n_hdlc_buf_return(struct n_hdlc_buf_list *buf_list, + struct n_hdlc_buf *buf) +{ + unsigned long flags; + + spin_lock_irqsave(&buf_list->spinlock, flags); + + list_add(&buf->list_item, &buf_list->list); + buf_list->count++; + + spin_unlock_irqrestore(&buf_list->spinlock, flags); +} + +/** * n_hdlc_buf_put - add specified HDLC buffer to tail of specified list - * @list - pointer to buffer list + * @buf_list - pointer to buffer list * @buf - pointer to buffer */ -static void n_hdlc_buf_put(struct n_hdlc_buf_list *list, +static void n_hdlc_buf_put(struct n_hdlc_buf_list *buf_list, struct n_hdlc_buf *buf) { unsigned long flags; - spin_lock_irqsave(&list->spinlock,flags); - - buf->link=NULL; - if (list->tail) - list->tail->link = buf; - else - list->head = buf; - list->tail = buf; - (list->count)++; - - spin_unlock_irqrestore(&list->spinlock,flags); - + + spin_lock_irqsave(&buf_list->spinlock, flags); + + list_add_tail(&buf->list_item, &buf_list->list); + buf_list->count++; + + spin_unlock_irqrestore(&buf_list->spinlock, flags); } /* end of n_hdlc_buf_put() */ /** * n_hdlc_buf_get - remove and return an HDLC buffer from list - * @list - pointer to HDLC buffer list + * @buf_list - pointer to HDLC buffer list * * Remove and return an HDLC buffer from the head of the specified HDLC buffer * list. * Returns a pointer to HDLC buffer if available, otherwise %NULL. */ -static struct n_hdlc_buf* n_hdlc_buf_get(struct n_hdlc_buf_list *list) +static struct n_hdlc_buf *n_hdlc_buf_get(struct n_hdlc_buf_list *buf_list) { unsigned long flags; struct n_hdlc_buf *buf; - spin_lock_irqsave(&list->spinlock,flags); - - buf = list->head; + + spin_lock_irqsave(&buf_list->spinlock, flags); + + buf = list_first_entry_or_null(&buf_list->list, + struct n_hdlc_buf, list_item); if (buf) { - list->head = buf->link; - (list->count)--; + list_del(&buf->list_item); + buf_list->count--; } - if (!list->head) - list->tail = NULL; - - spin_unlock_irqrestore(&list->spinlock,flags); + + spin_unlock_irqrestore(&buf_list->spinlock, flags); return buf; - } /* end of n_hdlc_buf_get() */ static char hdlc_banner[] __initdata = diff --git a/drivers/tty/serial/samsung.c b/drivers/tty/serial/samsung.c index b4f86c219db1..7a17aedbf902 100644 --- a/drivers/tty/serial/samsung.c +++ b/drivers/tty/serial/samsung.c @@ -1031,8 +1031,10 @@ static int s3c64xx_serial_startup(struct uart_port *port) if (ourport->dma) { ret = s3c24xx_serial_request_dma(ourport); if (ret < 0) { - dev_warn(port->dev, "DMA request failed\n"); - return ret; + dev_warn(port->dev, + "DMA request failed, DMA will not be used\n"); + devm_kfree(port->dev, ourport->dma); + ourport->dma = NULL; } } diff --git a/drivers/usb/dwc3/dwc3-omap.c b/drivers/usb/dwc3/dwc3-omap.c index 2092e46b1380..f8d0747810e7 100644 --- a/drivers/usb/dwc3/dwc3-omap.c +++ b/drivers/usb/dwc3/dwc3-omap.c @@ -250,6 +250,7 @@ static void dwc3_omap_set_mailbox(struct dwc3_omap *omap, val = dwc3_omap_read_utmi_ctrl(omap); val |= USBOTGSS_UTMI_OTG_CTRL_IDDIG; dwc3_omap_write_utmi_ctrl(omap, val); + break; case OMAP_DWC3_VBUS_OFF: val = dwc3_omap_read_utmi_ctrl(omap); @@ -392,7 +393,7 @@ static void dwc3_omap_set_utmi_mode(struct dwc3_omap *omap) { u32 reg; struct device_node *node = omap->dev->of_node; - int utmi_mode = 0; + u32 utmi_mode = 0; reg = dwc3_omap_read_utmi_ctrl(omap); diff --git a/drivers/usb/dwc3/gadget.c b/drivers/usb/dwc3/gadget.c index 4db97ecae885..0d75158e43fe 100644 --- a/drivers/usb/dwc3/gadget.c +++ b/drivers/usb/dwc3/gadget.c @@ -1342,6 +1342,68 @@ static int dwc3_gadget_ep_dequeue(struct usb_ep *ep, if (r == req) { /* wait until it is processed */ dwc3_stop_active_transfer(dwc, dep->number, true); + + /* + * If request was already started, this means we had to + * stop the transfer. With that we also need to ignore + * all TRBs used by the request, however TRBs can only + * be modified after completion of END_TRANSFER + * command. So what we do here is that we wait for + * END_TRANSFER completion and only after that, we jump + * over TRBs by clearing HWO and incrementing dequeue + * pointer. + * + * Note that we have 2 possible types of transfers here: + * + * i) Linear buffer request + * ii) SG-list based request + * + * SG-list based requests will have r->num_pending_sgs + * set to a valid number (> 0). Linear requests, + * normally use a single TRB. + * + * For each of these two cases, if r->unaligned flag is + * set, one extra TRB has been used to align transfer + * size to wMaxPacketSize. + * + * All of these cases need to be taken into + * consideration so we don't mess up our TRB ring + * pointers. + */ + wait_event_lock_irq(dep->wait_end_transfer, + !(dep->flags & DWC3_EP_END_TRANSFER_PENDING), + dwc->lock); + + if (!r->trb) + goto out1; + + if (r->num_pending_sgs) { + struct dwc3_trb *trb; + int i = 0; + + for (i = 0; i < r->num_pending_sgs; i++) { + trb = r->trb + i; + trb->ctrl &= ~DWC3_TRB_CTRL_HWO; + dwc3_ep_inc_deq(dep); + } + + if (r->unaligned) { + trb = r->trb + r->num_pending_sgs + 1; + trb->ctrl &= ~DWC3_TRB_CTRL_HWO; + dwc3_ep_inc_deq(dep); + } + } else { + struct dwc3_trb *trb = r->trb; + + trb->ctrl &= ~DWC3_TRB_CTRL_HWO; + dwc3_ep_inc_deq(dep); + + if (r->unaligned) { + trb = r->trb + 1; + trb->ctrl &= ~DWC3_TRB_CTRL_HWO; + dwc3_ep_inc_deq(dep); + } + } goto out1; } dev_err(dwc->dev, "request %p was not queued to %s\n", @@ -1352,6 +1414,7 @@ static int dwc3_gadget_ep_dequeue(struct usb_ep *ep, out1: /* giveback the request */ + dep->queued_requests--; dwc3_gadget_giveback(dep, req, -ECONNRESET); out0: @@ -2126,12 +2189,12 @@ static int __dwc3_cleanup_done_trbs(struct dwc3 *dwc, struct dwc3_ep *dep, return 1; } - if ((trb->ctrl & DWC3_TRB_CTRL_HWO) && status != -ESHUTDOWN) - return 1; - count = trb->size & DWC3_TRB_SIZE_MASK; req->remaining += count; + if ((trb->ctrl & DWC3_TRB_CTRL_HWO) && status != -ESHUTDOWN) + return 1; + if (dep->direction) { if (count) { trb_status = DWC3_TRB_SIZE_TRBSTS(trb->size); @@ -3228,15 +3291,10 @@ void dwc3_gadget_exit(struct dwc3 *dwc) int dwc3_gadget_suspend(struct dwc3 *dwc) { - int ret; - if (!dwc->gadget_driver) return 0; - ret = dwc3_gadget_run_stop(dwc, false, false); - if (ret < 0) - return ret; - + dwc3_gadget_run_stop(dwc, false, false); dwc3_disconnect_gadget(dwc); __dwc3_gadget_stop(dwc); diff --git a/drivers/usb/dwc3/gadget.h b/drivers/usb/dwc3/gadget.h index 3129bcf74d7d..265e223ab645 100644 --- a/drivers/usb/dwc3/gadget.h +++ b/drivers/usb/dwc3/gadget.h @@ -28,23 +28,23 @@ struct dwc3; #define gadget_to_dwc(g) (container_of(g, struct dwc3, gadget)) /* DEPCFG parameter 1 */ -#define DWC3_DEPCFG_INT_NUM(n) ((n) << 0) +#define DWC3_DEPCFG_INT_NUM(n) (((n) & 0x1f) << 0) #define DWC3_DEPCFG_XFER_COMPLETE_EN (1 << 8) #define DWC3_DEPCFG_XFER_IN_PROGRESS_EN (1 << 9) #define DWC3_DEPCFG_XFER_NOT_READY_EN (1 << 10) #define DWC3_DEPCFG_FIFO_ERROR_EN (1 << 11) #define DWC3_DEPCFG_STREAM_EVENT_EN (1 << 13) -#define DWC3_DEPCFG_BINTERVAL_M1(n) ((n) << 16) +#define DWC3_DEPCFG_BINTERVAL_M1(n) (((n) & 0xff) << 16) #define DWC3_DEPCFG_STREAM_CAPABLE (1 << 24) -#define DWC3_DEPCFG_EP_NUMBER(n) ((n) << 25) +#define DWC3_DEPCFG_EP_NUMBER(n) (((n) & 0x1f) << 25) #define DWC3_DEPCFG_BULK_BASED (1 << 30) #define DWC3_DEPCFG_FIFO_BASED (1 << 31) /* DEPCFG parameter 0 */ -#define DWC3_DEPCFG_EP_TYPE(n) ((n) << 1) -#define DWC3_DEPCFG_MAX_PACKET_SIZE(n) ((n) << 3) -#define DWC3_DEPCFG_FIFO_NUMBER(n) ((n) << 17) -#define DWC3_DEPCFG_BURST_SIZE(n) ((n) << 22) +#define DWC3_DEPCFG_EP_TYPE(n) (((n) & 0x3) << 1) +#define DWC3_DEPCFG_MAX_PACKET_SIZE(n) (((n) & 0x7ff) << 3) +#define DWC3_DEPCFG_FIFO_NUMBER(n) (((n) & 0x1f) << 17) +#define DWC3_DEPCFG_BURST_SIZE(n) (((n) & 0xf) << 22) #define DWC3_DEPCFG_DATA_SEQ_NUM(n) ((n) << 26) /* This applies for core versions earlier than 1.94a */ #define DWC3_DEPCFG_IGN_SEQ_NUM (1 << 31) diff --git a/drivers/usb/gadget/configfs.c b/drivers/usb/gadget/configfs.c index 78c44979dde3..cbff3b02840d 100644 --- a/drivers/usb/gadget/configfs.c +++ b/drivers/usb/gadget/configfs.c @@ -269,6 +269,7 @@ static ssize_t gadget_dev_desc_UDC_store(struct config_item *item, ret = unregister_gadget(gi); if (ret) goto err; + kfree(name); } else { if (gi->composite.gadget_driver.udc_name) { ret = -EBUSY; diff --git a/drivers/usb/gadget/function/f_fs.c b/drivers/usb/gadget/function/f_fs.c index a5b7cd615698..a0085571824d 100644 --- a/drivers/usb/gadget/function/f_fs.c +++ b/drivers/usb/gadget/function/f_fs.c @@ -1834,11 +1834,14 @@ static int ffs_func_eps_enable(struct ffs_function *func) spin_lock_irqsave(&func->ffs->eps_lock, flags); while(count--) { struct usb_endpoint_descriptor *ds; + struct usb_ss_ep_comp_descriptor *comp_desc = NULL; + int needs_comp_desc = false; int desc_idx; - if (ffs->gadget->speed == USB_SPEED_SUPER) + if (ffs->gadget->speed == USB_SPEED_SUPER) { desc_idx = 2; - else if (ffs->gadget->speed == USB_SPEED_HIGH) + needs_comp_desc = true; + } else if (ffs->gadget->speed == USB_SPEED_HIGH) desc_idx = 1; else desc_idx = 0; @@ -1855,6 +1858,14 @@ static int ffs_func_eps_enable(struct ffs_function *func) ep->ep->driver_data = ep; ep->ep->desc = ds; + + comp_desc = (struct usb_ss_ep_comp_descriptor *)(ds + + USB_DT_ENDPOINT_SIZE); + ep->ep->maxburst = comp_desc->bMaxBurst + 1; + + if (needs_comp_desc) + ep->ep->comp_desc = comp_desc; + ret = usb_ep_enable(ep->ep); if (likely(!ret)) { epfile->ep = ep; @@ -2253,7 +2264,7 @@ static int __ffs_data_do_os_desc(enum ffs_os_desc_type type, if (len < sizeof(*d) || d->bFirstInterfaceNumber >= ffs->interfaces_count || - d->Reserved1) + !d->Reserved1) return -EINVAL; for (i = 0; i < ARRAY_SIZE(d->Reserved2); ++i) if (d->Reserved2[i]) diff --git a/drivers/usb/gadget/function/f_uvc.c b/drivers/usb/gadget/function/f_uvc.c index 27ed51b5082f..29b41b5dee04 100644 --- a/drivers/usb/gadget/function/f_uvc.c +++ b/drivers/usb/gadget/function/f_uvc.c @@ -258,13 +258,6 @@ uvc_function_setup(struct usb_function *f, const struct usb_ctrlrequest *ctrl) memcpy(&uvc_event->req, ctrl, sizeof(uvc_event->req)); v4l2_event_queue(&uvc->vdev, &v4l2_event); - /* Pass additional setup data to userspace */ - if (uvc->event_setup_out && uvc->event_length) { - uvc->control_req->length = uvc->event_length; - return usb_ep_queue(uvc->func.config->cdev->gadget->ep0, - uvc->control_req, GFP_ATOMIC); - } - return 0; } diff --git a/drivers/usb/gadget/legacy/inode.c b/drivers/usb/gadget/legacy/inode.c index a2615d64d07c..a2c916869293 100644 --- a/drivers/usb/gadget/legacy/inode.c +++ b/drivers/usb/gadget/legacy/inode.c @@ -84,8 +84,7 @@ static int ep_open(struct inode *, struct file *); /* /dev/gadget/$CHIP represents ep0 and the whole device */ enum ep0_state { - /* DISBLED is the initial state. - */ + /* DISABLED is the initial state. */ STATE_DEV_DISABLED = 0, /* Only one open() of /dev/gadget/$CHIP; only one file tracks @@ -1782,8 +1781,10 @@ dev_config (struct file *fd, const char __user *buf, size_t len, loff_t *ptr) spin_lock_irq (&dev->lock); value = -EINVAL; - if (dev->buf) + if (dev->buf) { + kfree(kbuf); goto fail; + } dev->buf = kbuf; /* full or low speed config */ diff --git a/drivers/usb/gadget/udc/atmel_usba_udc.c b/drivers/usb/gadget/udc/atmel_usba_udc.c index 11bbce28bc23..2035906b8ced 100644 --- a/drivers/usb/gadget/udc/atmel_usba_udc.c +++ b/drivers/usb/gadget/udc/atmel_usba_udc.c @@ -610,7 +610,7 @@ usba_ep_enable(struct usb_ep *_ep, const struct usb_endpoint_descriptor *desc) { struct usba_ep *ep = to_usba_ep(_ep); struct usba_udc *udc = ep->udc; - unsigned long flags, ept_cfg, maxpacket; + unsigned long flags, maxpacket; unsigned int nr_trans; DBG(DBG_GADGET, "%s: ep_enable: desc=%p\n", ep->ep.name, desc); @@ -630,7 +630,7 @@ usba_ep_enable(struct usb_ep *_ep, const struct usb_endpoint_descriptor *desc) ep->is_in = 0; DBG(DBG_ERR, "%s: EPT_CFG = 0x%lx (maxpacket = %lu)\n", - ep->ep.name, ept_cfg, maxpacket); + ep->ep.name, ep->ept_cfg, maxpacket); if (usb_endpoint_dir_in(desc)) { ep->is_in = 1; diff --git a/drivers/usb/gadget/udc/dummy_hcd.c b/drivers/usb/gadget/udc/dummy_hcd.c index c60abe3a68f9..8cabc5944d5f 100644 --- a/drivers/usb/gadget/udc/dummy_hcd.c +++ b/drivers/usb/gadget/udc/dummy_hcd.c @@ -1031,6 +1031,8 @@ static int dummy_udc_probe(struct platform_device *pdev) int rc; dum = *((void **)dev_get_platdata(&pdev->dev)); + /* Clear usb_gadget region for new registration to udc-core */ + memzero_explicit(&dum->gadget, sizeof(struct usb_gadget)); dum->gadget.name = gadget_name; dum->gadget.ops = &dummy_ops; dum->gadget.max_speed = USB_SPEED_SUPER; diff --git a/drivers/usb/gadget/udc/net2280.c b/drivers/usb/gadget/udc/net2280.c index 85504419ab31..3828c2ec8623 100644 --- a/drivers/usb/gadget/udc/net2280.c +++ b/drivers/usb/gadget/udc/net2280.c @@ -1146,15 +1146,15 @@ static int scan_dma_completions(struct net2280_ep *ep) */ while (!list_empty(&ep->queue)) { struct net2280_request *req; - u32 tmp; + u32 req_dma_count; req = list_entry(ep->queue.next, struct net2280_request, queue); if (!req->valid) break; rmb(); - tmp = le32_to_cpup(&req->td->dmacount); - if ((tmp & BIT(VALID_BIT)) != 0) + req_dma_count = le32_to_cpup(&req->td->dmacount); + if ((req_dma_count & BIT(VALID_BIT)) != 0) break; /* SHORT_PACKET_TRANSFERRED_INTERRUPT handles "usb-short" @@ -1163,40 +1163,41 @@ static int scan_dma_completions(struct net2280_ep *ep) */ if (unlikely(req->td->dmadesc == 0)) { /* paranoia */ - tmp = readl(&ep->dma->dmacount); - if (tmp & DMA_BYTE_COUNT_MASK) + u32 const ep_dmacount = readl(&ep->dma->dmacount); + + if (ep_dmacount & DMA_BYTE_COUNT_MASK) break; /* single transfer mode */ - dma_done(ep, req, tmp, 0); + dma_done(ep, req, req_dma_count, 0); num_completed++; break; } else if (!ep->is_in && (req->req.length % ep->ep.maxpacket) && !(ep->dev->quirks & PLX_PCIE)) { - tmp = readl(&ep->regs->ep_stat); + u32 const ep_stat = readl(&ep->regs->ep_stat); /* AVOID TROUBLE HERE by not issuing short reads from * your gadget driver. That helps avoids errata 0121, * 0122, and 0124; not all cases trigger the warning. */ - if ((tmp & BIT(NAK_OUT_PACKETS)) == 0) { + if ((ep_stat & BIT(NAK_OUT_PACKETS)) == 0) { ep_warn(ep->dev, "%s lost packet sync!\n", ep->ep.name); req->req.status = -EOVERFLOW; } else { - tmp = readl(&ep->regs->ep_avail); - if (tmp) { + u32 const ep_avail = readl(&ep->regs->ep_avail); + if (ep_avail) { /* fifo gets flushed later */ ep->out_overflow = 1; ep_dbg(ep->dev, "%s dma, discard %d len %d\n", - ep->ep.name, tmp, + ep->ep.name, ep_avail, req->req.length); req->req.status = -EOVERFLOW; } } } - dma_done(ep, req, tmp, 0); + dma_done(ep, req, req_dma_count, 0); num_completed++; } diff --git a/drivers/usb/gadget/udc/pxa27x_udc.c b/drivers/usb/gadget/udc/pxa27x_udc.c index e1335ad5bce9..832c4fdbe985 100644 --- a/drivers/usb/gadget/udc/pxa27x_udc.c +++ b/drivers/usb/gadget/udc/pxa27x_udc.c @@ -2534,9 +2534,10 @@ static int pxa_udc_remove(struct platform_device *_dev) usb_del_gadget_udc(&udc->gadget); pxa_cleanup_debugfs(udc); - if (!IS_ERR_OR_NULL(udc->transceiver)) + if (!IS_ERR_OR_NULL(udc->transceiver)) { usb_unregister_notifier(udc->transceiver, &pxa27x_udc_phy); - usb_put_phy(udc->transceiver); + usb_put_phy(udc->transceiver); + } udc->transceiver = NULL; the_controller = NULL; diff --git a/drivers/usb/host/ohci-at91.c b/drivers/usb/host/ohci-at91.c index 414e3c376dbb..5302f988e7e6 100644 --- a/drivers/usb/host/ohci-at91.c +++ b/drivers/usb/host/ohci-at91.c @@ -350,7 +350,7 @@ static int ohci_at91_hub_control(struct usb_hcd *hcd, u16 typeReq, u16 wValue, case USB_PORT_FEAT_SUSPEND: dev_dbg(hcd->self.controller, "SetPortFeat: SUSPEND\n"); - if (valid_port(wIndex)) { + if (valid_port(wIndex) && ohci_at91->sfr_regmap) { ohci_at91_port_suspend(ohci_at91->sfr_regmap, 1); return 0; @@ -393,7 +393,7 @@ static int ohci_at91_hub_control(struct usb_hcd *hcd, u16 typeReq, u16 wValue, case USB_PORT_FEAT_SUSPEND: dev_dbg(hcd->self.controller, "ClearPortFeature: SUSPEND\n"); - if (valid_port(wIndex)) { + if (valid_port(wIndex) && ohci_at91->sfr_regmap) { ohci_at91_port_suspend(ohci_at91->sfr_regmap, 0); return 0; diff --git a/drivers/usb/host/xhci-dbg.c b/drivers/usb/host/xhci-dbg.c index 363d125300ea..2b4a00fa735d 100644 --- a/drivers/usb/host/xhci-dbg.c +++ b/drivers/usb/host/xhci-dbg.c @@ -109,7 +109,7 @@ static void xhci_print_cap_regs(struct xhci_hcd *xhci) xhci_dbg(xhci, "RTSOFF 0x%x:\n", temp & RTSOFF_MASK); /* xhci 1.1 controllers have the HCCPARAMS2 register */ - if (hci_version > 100) { + if (hci_version > 0x100) { temp = readl(&xhci->cap_regs->hcc_params2); xhci_dbg(xhci, "HCC PARAMS2 0x%x:\n", (unsigned int) temp); xhci_dbg(xhci, " HC %s Force save context capability", diff --git a/drivers/usb/host/xhci-mtk.c b/drivers/usb/host/xhci-mtk.c index 9066ec9e0c2e..67d5dc79b6b5 100644 --- a/drivers/usb/host/xhci-mtk.c +++ b/drivers/usb/host/xhci-mtk.c @@ -382,7 +382,6 @@ static int usb_wakeup_of_property_parse(struct xhci_hcd_mtk *mtk, static int xhci_mtk_setup(struct usb_hcd *hcd); static const struct xhci_driver_overrides xhci_mtk_overrides __initconst = { - .extra_priv_size = sizeof(struct xhci_hcd), .reset = xhci_mtk_setup, }; @@ -678,13 +677,13 @@ static int xhci_mtk_probe(struct platform_device *pdev) goto power_off_phys; } - if (HCC_MAX_PSA(xhci->hcc_params) >= 4) - xhci->shared_hcd->can_do_streams = 1; - ret = usb_add_hcd(hcd, irq, IRQF_SHARED); if (ret) goto put_usb3_hcd; + if (HCC_MAX_PSA(xhci->hcc_params) >= 4) + xhci->shared_hcd->can_do_streams = 1; + ret = usb_add_hcd(xhci->shared_hcd, irq, IRQF_SHARED); if (ret) goto dealloc_usb2_hcd; diff --git a/drivers/usb/host/xhci-plat.c b/drivers/usb/host/xhci-plat.c index 6d33b42ffcf5..bd02a6cd8e2c 100644 --- a/drivers/usb/host/xhci-plat.c +++ b/drivers/usb/host/xhci-plat.c @@ -286,6 +286,8 @@ static int xhci_plat_remove(struct platform_device *dev) struct xhci_hcd *xhci = hcd_to_xhci(hcd); struct clk *clk = xhci->clk; + xhci->xhc_state |= XHCI_STATE_REMOVING; + usb_remove_hcd(xhci->shared_hcd); usb_phy_shutdown(hcd->usb_phy); diff --git a/drivers/usb/host/xhci-tegra.c b/drivers/usb/host/xhci-tegra.c index a59fafb4b329..74436f8ca538 100644 --- a/drivers/usb/host/xhci-tegra.c +++ b/drivers/usb/host/xhci-tegra.c @@ -1308,7 +1308,6 @@ static int tegra_xhci_setup(struct usb_hcd *hcd) } static const struct xhci_driver_overrides tegra_xhci_overrides __initconst = { - .extra_priv_size = sizeof(struct xhci_hcd), .reset = tegra_xhci_setup, }; diff --git a/drivers/usb/host/xhci.c b/drivers/usb/host/xhci.c index 6d6c46000e56..50aee8b7718b 100644 --- a/drivers/usb/host/xhci.c +++ b/drivers/usb/host/xhci.c @@ -868,7 +868,7 @@ static void xhci_disable_port_wake_on_bits(struct xhci_hcd *xhci) spin_lock_irqsave(&xhci->lock, flags); - /* disble usb3 ports Wake bits*/ + /* disable usb3 ports Wake bits */ port_index = xhci->num_usb3_ports; port_array = xhci->usb3_ports; while (port_index--) { @@ -879,7 +879,7 @@ static void xhci_disable_port_wake_on_bits(struct xhci_hcd *xhci) writel(t2, port_array[port_index]); } - /* disble usb2 ports Wake bits*/ + /* disable usb2 ports Wake bits */ port_index = xhci->num_usb2_ports; port_array = xhci->usb2_ports; while (port_index--) { diff --git a/drivers/usb/misc/iowarrior.c b/drivers/usb/misc/iowarrior.c index 095778ff984d..37c63cb39714 100644 --- a/drivers/usb/misc/iowarrior.c +++ b/drivers/usb/misc/iowarrior.c @@ -781,12 +781,6 @@ static int iowarrior_probe(struct usb_interface *interface, iface_desc = interface->cur_altsetting; dev->product_id = le16_to_cpu(udev->descriptor.idProduct); - if (iface_desc->desc.bNumEndpoints < 1) { - dev_err(&interface->dev, "Invalid number of endpoints\n"); - retval = -EINVAL; - goto error; - } - /* set up the endpoint information */ for (i = 0; i < iface_desc->desc.bNumEndpoints; ++i) { endpoint = &iface_desc->endpoint[i].desc; @@ -797,6 +791,21 @@ static int iowarrior_probe(struct usb_interface *interface, /* this one will match for the IOWarrior56 only */ dev->int_out_endpoint = endpoint; } + + if (!dev->int_in_endpoint) { + dev_err(&interface->dev, "no interrupt-in endpoint found\n"); + retval = -ENODEV; + goto error; + } + + if (dev->product_id == USB_DEVICE_ID_CODEMERCS_IOW56) { + if (!dev->int_out_endpoint) { + dev_err(&interface->dev, "no interrupt-out endpoint found\n"); + retval = -ENODEV; + goto error; + } + } + /* we have to check the report_size often, so remember it in the endianness suitable for our machine */ dev->report_size = usb_endpoint_maxp(dev->int_in_endpoint); if ((dev->interface->cur_altsetting->desc.bInterfaceNumber == 0) && diff --git a/drivers/usb/misc/usb251xb.c b/drivers/usb/misc/usb251xb.c index 4e18600dc9b4..91f66d68bcb7 100644 --- a/drivers/usb/misc/usb251xb.c +++ b/drivers/usb/misc/usb251xb.c @@ -375,18 +375,24 @@ static int usb251xb_get_ofdata(struct usb251xb *hub, if (of_get_property(np, "dynamic-power-switching", NULL)) hub->conf_data2 |= BIT(7); - if (of_get_property(np, "oc-delay-100us", NULL)) { - hub->conf_data2 &= ~BIT(5); - hub->conf_data2 &= ~BIT(4); - } else if (of_get_property(np, "oc-delay-4ms", NULL)) { - hub->conf_data2 &= ~BIT(5); - hub->conf_data2 |= BIT(4); - } else if (of_get_property(np, "oc-delay-8ms", NULL)) { - hub->conf_data2 |= BIT(5); - hub->conf_data2 &= ~BIT(4); - } else if (of_get_property(np, "oc-delay-16ms", NULL)) { - hub->conf_data2 |= BIT(5); - hub->conf_data2 |= BIT(4); + if (!of_property_read_u32(np, "oc-delay-us", property_u32)) { + if (*property_u32 == 100) { + /* 100 us*/ + hub->conf_data2 &= ~BIT(5); + hub->conf_data2 &= ~BIT(4); + } else if (*property_u32 == 4000) { + /* 4 ms */ + hub->conf_data2 &= ~BIT(5); + hub->conf_data2 |= BIT(4); + } else if (*property_u32 == 16000) { + /* 16 ms */ + hub->conf_data2 |= BIT(5); + hub->conf_data2 |= BIT(4); + } else { + /* 8 ms (DEFAULT) */ + hub->conf_data2 |= BIT(5); + hub->conf_data2 &= ~BIT(4); + } } if (of_get_property(np, "compound-device", NULL)) @@ -432,30 +438,9 @@ static int usb251xb_get_ofdata(struct usb251xb *hub, } } - hub->max_power_sp = USB251XB_DEF_MAX_POWER_SELF; - if (!of_property_read_u32(np, "max-sp-power", property_u32)) - hub->max_power_sp = min_t(u8, be32_to_cpu(*property_u32) / 2, - 250); - - hub->max_power_bp = USB251XB_DEF_MAX_POWER_BUS; - if (!of_property_read_u32(np, "max-bp-power", property_u32)) - hub->max_power_bp = min_t(u8, be32_to_cpu(*property_u32) / 2, - 250); - - hub->max_current_sp = USB251XB_DEF_MAX_CURRENT_SELF; - if (!of_property_read_u32(np, "max-sp-current", property_u32)) - hub->max_current_sp = min_t(u8, be32_to_cpu(*property_u32) / 2, - 250); - - hub->max_current_bp = USB251XB_DEF_MAX_CURRENT_BUS; - if (!of_property_read_u32(np, "max-bp-current", property_u32)) - hub->max_current_bp = min_t(u8, be32_to_cpu(*property_u32) / 2, - 250); - hub->power_on_time = USB251XB_DEF_POWER_ON_TIME; - if (!of_property_read_u32(np, "power-on-time", property_u32)) - hub->power_on_time = min_t(u8, be32_to_cpu(*property_u32) / 2, - 255); + if (!of_property_read_u32(np, "power-on-time-ms", property_u32)) + hub->power_on_time = min_t(u8, *property_u32 / 2, 255); if (of_property_read_u16_array(np, "language-id", &hub->lang_id, 1)) hub->lang_id = USB251XB_DEF_LANGUAGE_ID; @@ -492,6 +477,10 @@ static int usb251xb_get_ofdata(struct usb251xb *hub, /* The following parameters are currently not exposed to devicetree, but * may be as soon as needed. */ + hub->max_power_sp = USB251XB_DEF_MAX_POWER_SELF; + hub->max_power_bp = USB251XB_DEF_MAX_POWER_BUS; + hub->max_current_sp = USB251XB_DEF_MAX_CURRENT_SELF; + hub->max_current_bp = USB251XB_DEF_MAX_CURRENT_BUS; hub->bat_charge_en = USB251XB_DEF_BATTERY_CHARGING_ENABLE; hub->boost_up = USB251XB_DEF_BOOST_UP; hub->boost_x = USB251XB_DEF_BOOST_X; diff --git a/drivers/usb/phy/phy-isp1301.c b/drivers/usb/phy/phy-isp1301.c index db68156568e6..b3b33cf7ddf6 100644 --- a/drivers/usb/phy/phy-isp1301.c +++ b/drivers/usb/phy/phy-isp1301.c @@ -33,6 +33,12 @@ static const struct i2c_device_id isp1301_id[] = { }; MODULE_DEVICE_TABLE(i2c, isp1301_id); +static const struct of_device_id isp1301_of_match[] = { + {.compatible = "nxp,isp1301" }, + { }, +}; +MODULE_DEVICE_TABLE(of, isp1301_of_match); + static struct i2c_client *isp1301_i2c_client; static int __isp1301_write(struct isp1301 *isp, u8 reg, u8 value, u8 clear) @@ -130,6 +136,7 @@ static int isp1301_remove(struct i2c_client *client) static struct i2c_driver isp1301_driver = { .driver = { .name = DRV_NAME, + .of_match_table = of_match_ptr(isp1301_of_match), }, .probe = isp1301_probe, .remove = isp1301_remove, diff --git a/drivers/usb/serial/digi_acceleport.c b/drivers/usb/serial/digi_acceleport.c index ab78111e0968..6537d3ca2797 100644 --- a/drivers/usb/serial/digi_acceleport.c +++ b/drivers/usb/serial/digi_acceleport.c @@ -1500,7 +1500,7 @@ static int digi_read_oob_callback(struct urb *urb) return -1; /* handle each oob command */ - for (i = 0; i < urb->actual_length - 4; i += 4) { + for (i = 0; i < urb->actual_length - 3; i += 4) { opcode = buf[i]; line = buf[i + 1]; status = buf[i + 2]; diff --git a/drivers/usb/serial/io_ti.c b/drivers/usb/serial/io_ti.c index ceaeebaa6f90..a76b95d32157 100644 --- a/drivers/usb/serial/io_ti.c +++ b/drivers/usb/serial/io_ti.c @@ -1674,6 +1674,12 @@ static void edge_interrupt_callback(struct urb *urb) function = TIUMP_GET_FUNC_FROM_CODE(data[0]); dev_dbg(dev, "%s - port_number %d, function %d, info 0x%x\n", __func__, port_number, function, data[1]); + + if (port_number >= edge_serial->serial->num_ports) { + dev_err(dev, "bad port number %d\n", port_number); + goto exit; + } + port = edge_serial->serial->port[port_number]; edge_port = usb_get_serial_port_data(port); if (!edge_port) { @@ -1755,7 +1761,7 @@ static void edge_bulk_in_callback(struct urb *urb) port_number = edge_port->port->port_number; - if (edge_port->lsr_event) { + if (urb->actual_length > 0 && edge_port->lsr_event) { edge_port->lsr_event = 0; dev_dbg(dev, "%s ===== Port %u LSR Status = %02x, Data = %02x ======\n", __func__, port_number, edge_port->lsr_mask, *data); diff --git a/drivers/usb/serial/omninet.c b/drivers/usb/serial/omninet.c index a180b17d2432..dd706953b466 100644 --- a/drivers/usb/serial/omninet.c +++ b/drivers/usb/serial/omninet.c @@ -31,7 +31,6 @@ #define BT_IGNITIONPRO_ID 0x2000 /* function prototypes */ -static int omninet_open(struct tty_struct *tty, struct usb_serial_port *port); static void omninet_process_read_urb(struct urb *urb); static void omninet_write_bulk_callback(struct urb *urb); static int omninet_write(struct tty_struct *tty, struct usb_serial_port *port, @@ -60,7 +59,6 @@ static struct usb_serial_driver zyxel_omninet_device = { .attach = omninet_attach, .port_probe = omninet_port_probe, .port_remove = omninet_port_remove, - .open = omninet_open, .write = omninet_write, .write_room = omninet_write_room, .write_bulk_callback = omninet_write_bulk_callback, @@ -140,17 +138,6 @@ static int omninet_port_remove(struct usb_serial_port *port) return 0; } -static int omninet_open(struct tty_struct *tty, struct usb_serial_port *port) -{ - struct usb_serial *serial = port->serial; - struct usb_serial_port *wport; - - wport = serial->port[1]; - tty_port_tty_set(&wport->port, tty); - - return usb_serial_generic_open(tty, port); -} - #define OMNINET_HEADERLEN 4 #define OMNINET_BULKOUTSIZE 64 #define OMNINET_PAYLOADSIZE (OMNINET_BULKOUTSIZE - OMNINET_HEADERLEN) diff --git a/drivers/usb/serial/safe_serial.c b/drivers/usb/serial/safe_serial.c index 93c6c9b08daa..8a069aa154ed 100644 --- a/drivers/usb/serial/safe_serial.c +++ b/drivers/usb/serial/safe_serial.c @@ -200,6 +200,11 @@ static void safe_process_read_urb(struct urb *urb) if (!safe) goto out; + if (length < 2) { + dev_err(&port->dev, "malformed packet\n"); + return; + } + fcs = fcs_compute10(data, length, CRC10_INITFCS); if (fcs) { dev_err(&port->dev, "%s - bad CRC %x\n", __func__, fcs); diff --git a/drivers/usb/storage/unusual_devs.h b/drivers/usb/storage/unusual_devs.h index 16cc18369111..9129f6cb8230 100644 --- a/drivers/usb/storage/unusual_devs.h +++ b/drivers/usb/storage/unusual_devs.h @@ -2071,6 +2071,20 @@ UNUSUAL_DEV( 0x1370, 0x6828, 0x0110, 0x0110, USB_SC_DEVICE, USB_PR_DEVICE, NULL, US_FL_IGNORE_RESIDUE ), +/* + * Reported by Tobias Jakobi <[email protected]> + * The INIC-3619 bridge is used in the StarTech SLSODDU33B + * SATA-USB enclosure for slimline optical drives. + * + * The quirk enables MakeMKV to properly exchange keys with + * an installed BD drive. + */ +UNUSUAL_DEV( 0x13fd, 0x3609, 0x0209, 0x0209, + "Initio Corporation", + "INIC-3619", + USB_SC_DEVICE, USB_PR_DEVICE, NULL, + US_FL_IGNORE_RESIDUE ), + /* Reported by Qinglin Ye <[email protected]> */ UNUSUAL_DEV( 0x13fe, 0x3600, 0x0100, 0x0100, "Kingston", diff --git a/drivers/xen/swiotlb-xen.c b/drivers/xen/swiotlb-xen.c index f8afc6dcc29f..e8cef1ad0fe3 100644 --- a/drivers/xen/swiotlb-xen.c +++ b/drivers/xen/swiotlb-xen.c @@ -681,3 +681,50 @@ xen_swiotlb_set_dma_mask(struct device *dev, u64 dma_mask) return 0; } EXPORT_SYMBOL_GPL(xen_swiotlb_set_dma_mask); + +/* + * Create userspace mapping for the DMA-coherent memory. + * This function should be called with the pages from the current domain only, + * passing pages mapped from other domains would lead to memory corruption. + */ +int +xen_swiotlb_dma_mmap(struct device *dev, struct vm_area_struct *vma, + void *cpu_addr, dma_addr_t dma_addr, size_t size, + unsigned long attrs) +{ +#if defined(CONFIG_ARM) || defined(CONFIG_ARM64) + if (__generic_dma_ops(dev)->mmap) + return __generic_dma_ops(dev)->mmap(dev, vma, cpu_addr, + dma_addr, size, attrs); +#endif + return dma_common_mmap(dev, vma, cpu_addr, dma_addr, size); +} +EXPORT_SYMBOL_GPL(xen_swiotlb_dma_mmap); + +/* + * This function should be called with the pages from the current domain only, + * passing pages mapped from other domains would lead to memory corruption. + */ +int +xen_swiotlb_get_sgtable(struct device *dev, struct sg_table *sgt, + void *cpu_addr, dma_addr_t handle, size_t size, + unsigned long attrs) +{ +#if defined(CONFIG_ARM) || defined(CONFIG_ARM64) + if (__generic_dma_ops(dev)->get_sgtable) { +#if 0 + /* + * This check verifies that the page belongs to the current domain and + * is not one mapped from another domain. + * This check is for debug only, and should not go to production build + */ + unsigned long bfn = PHYS_PFN(dma_to_phys(dev, handle)); + BUG_ON (!page_is_ram(bfn)); +#endif + return __generic_dma_ops(dev)->get_sgtable(dev, sgt, cpu_addr, + handle, size, attrs); + } +#endif + return dma_common_get_sgtable(dev, sgt, cpu_addr, handle, size); +} +EXPORT_SYMBOL_GPL(xen_swiotlb_get_sgtable); diff --git a/drivers/xen/xenbus/xenbus_dev_frontend.c b/drivers/xen/xenbus/xenbus_dev_frontend.c index 4d343eed08f5..1f4733b80c87 100644 --- a/drivers/xen/xenbus/xenbus_dev_frontend.c +++ b/drivers/xen/xenbus/xenbus_dev_frontend.c @@ -55,7 +55,6 @@ #include <linux/string.h> #include <linux/slab.h> #include <linux/miscdevice.h> -#include <linux/init.h> #include <xen/xenbus.h> #include <xen/xen.h> diff --git a/fs/dlm/lowcomms.c b/fs/dlm/lowcomms.c index 7d398d300e97..9382db998ec9 100644 --- a/fs/dlm/lowcomms.c +++ b/fs/dlm/lowcomms.c @@ -743,7 +743,7 @@ static int tcp_accept_from_sock(struct connection *con) newsock->type = con->sock->type; newsock->ops = con->sock->ops; - result = con->sock->ops->accept(con->sock, newsock, O_NONBLOCK); + result = con->sock->ops->accept(con->sock, newsock, O_NONBLOCK, true); if (result < 0) goto accept_err; diff --git a/fs/fat/inode.c b/fs/fat/inode.c index 338d2f73eb29..a2c05f2ada6d 100644 --- a/fs/fat/inode.c +++ b/fs/fat/inode.c @@ -1359,6 +1359,16 @@ out: return 0; } +static void fat_dummy_inode_init(struct inode *inode) +{ + /* Initialize this dummy inode to work as no-op. */ + MSDOS_I(inode)->mmu_private = 0; + MSDOS_I(inode)->i_start = 0; + MSDOS_I(inode)->i_logstart = 0; + MSDOS_I(inode)->i_attrs = 0; + MSDOS_I(inode)->i_pos = 0; +} + static int fat_read_root(struct inode *inode) { struct msdos_sb_info *sbi = MSDOS_SB(inode->i_sb); @@ -1803,12 +1813,13 @@ int fat_fill_super(struct super_block *sb, void *data, int silent, int isvfat, fat_inode = new_inode(sb); if (!fat_inode) goto out_fail; - MSDOS_I(fat_inode)->i_pos = 0; + fat_dummy_inode_init(fat_inode); sbi->fat_inode = fat_inode; fsinfo_inode = new_inode(sb); if (!fsinfo_inode) goto out_fail; + fat_dummy_inode_init(fsinfo_inode); fsinfo_inode->i_ino = MSDOS_FSINFO_INO; sbi->fsinfo_inode = fsinfo_inode; insert_inode_hash(fsinfo_inode); diff --git a/fs/gfs2/incore.h b/fs/gfs2/incore.h index c45084ac642d..511e1ed7e2de 100644 --- a/fs/gfs2/incore.h +++ b/fs/gfs2/incore.h @@ -207,7 +207,7 @@ struct lm_lockname { struct gfs2_sbd *ln_sbd; u64 ln_number; unsigned int ln_type; -}; +} __packed __aligned(sizeof(int)); #define lm_name_equal(name1, name2) \ (((name1)->ln_number == (name2)->ln_number) && \ diff --git a/fs/iomap.c b/fs/iomap.c index 3ca1a8e44135..141c3cd55a8b 100644 --- a/fs/iomap.c +++ b/fs/iomap.c @@ -846,7 +846,8 @@ iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter, struct address_space *mapping = iocb->ki_filp->f_mapping; struct inode *inode = file_inode(iocb->ki_filp); size_t count = iov_iter_count(iter); - loff_t pos = iocb->ki_pos, end = iocb->ki_pos + count - 1, ret = 0; + loff_t pos = iocb->ki_pos, start = pos; + loff_t end = iocb->ki_pos + count - 1, ret = 0; unsigned int flags = IOMAP_DIRECT; struct blk_plug plug; struct iomap_dio *dio; @@ -887,12 +888,12 @@ iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter, } if (mapping->nrpages) { - ret = filemap_write_and_wait_range(mapping, iocb->ki_pos, end); + ret = filemap_write_and_wait_range(mapping, start, end); if (ret) goto out_free_dio; ret = invalidate_inode_pages2_range(mapping, - iocb->ki_pos >> PAGE_SHIFT, end >> PAGE_SHIFT); + start >> PAGE_SHIFT, end >> PAGE_SHIFT); WARN_ON_ONCE(ret); ret = 0; } @@ -941,6 +942,8 @@ iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter, __set_current_state(TASK_RUNNING); } + ret = iomap_dio_complete(dio); + /* * Try again to invalidate clean pages which might have been cached by * non-direct readahead, or faulted in by get_user_pages() if the source @@ -949,12 +952,12 @@ iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter, * this invalidation fails, tough, the write still worked... */ if (iov_iter_rw(iter) == WRITE && mapping->nrpages) { - ret = invalidate_inode_pages2_range(mapping, - iocb->ki_pos >> PAGE_SHIFT, end >> PAGE_SHIFT); - WARN_ON_ONCE(ret); + int err = invalidate_inode_pages2_range(mapping, + start >> PAGE_SHIFT, end >> PAGE_SHIFT); + WARN_ON_ONCE(err); } - return iomap_dio_complete(dio); + return ret; out_free_dio: kfree(dio); diff --git a/fs/ocfs2/cluster/tcp.c b/fs/ocfs2/cluster/tcp.c index 4348027384f5..d0ab7e56d0b4 100644 --- a/fs/ocfs2/cluster/tcp.c +++ b/fs/ocfs2/cluster/tcp.c @@ -1863,7 +1863,7 @@ static int o2net_accept_one(struct socket *sock, int *more) new_sock->type = sock->type; new_sock->ops = sock->ops; - ret = sock->ops->accept(sock, new_sock, O_NONBLOCK); + ret = sock->ops->accept(sock, new_sock, O_NONBLOCK, false); if (ret < 0) goto out; diff --git a/fs/overlayfs/util.c b/fs/overlayfs/util.c index 1953986ee6bc..6e610a205e15 100644 --- a/fs/overlayfs/util.c +++ b/fs/overlayfs/util.c @@ -12,7 +12,6 @@ #include <linux/slab.h> #include <linux/cred.h> #include <linux/xattr.h> -#include <linux/sched/signal.h> #include "overlayfs.h" #include "ovl_entry.h" diff --git a/fs/timerfd.c b/fs/timerfd.c index 384fa759a563..c543cdb5f8ed 100644 --- a/fs/timerfd.c +++ b/fs/timerfd.c @@ -400,9 +400,9 @@ SYSCALL_DEFINE2(timerfd_create, int, clockid, int, flags) clockid != CLOCK_BOOTTIME_ALARM)) return -EINVAL; - if (!capable(CAP_WAKE_ALARM) && - (clockid == CLOCK_REALTIME_ALARM || - clockid == CLOCK_BOOTTIME_ALARM)) + if ((clockid == CLOCK_REALTIME_ALARM || + clockid == CLOCK_BOOTTIME_ALARM) && + !capable(CAP_WAKE_ALARM)) return -EPERM; ctx = kzalloc(sizeof(*ctx), GFP_KERNEL); @@ -449,7 +449,7 @@ static int do_timerfd_settime(int ufd, int flags, return ret; ctx = f.file->private_data; - if (!capable(CAP_WAKE_ALARM) && isalarm(ctx)) { + if (isalarm(ctx) && !capable(CAP_WAKE_ALARM)) { fdput(f); return -EPERM; } diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c index 973607df579d..1d227b0fcf49 100644 --- a/fs/userfaultfd.c +++ b/fs/userfaultfd.c @@ -138,8 +138,6 @@ out: * userfaultfd_ctx_get - Acquires a reference to the internal userfaultfd * context. * @ctx: [in] Pointer to the userfaultfd context. - * - * Returns: In case of success, returns not zero. */ static void userfaultfd_ctx_get(struct userfaultfd_ctx *ctx) { @@ -267,6 +265,7 @@ static inline bool userfaultfd_must_wait(struct userfaultfd_ctx *ctx, { struct mm_struct *mm = ctx->mm; pgd_t *pgd; + p4d_t *p4d; pud_t *pud; pmd_t *pmd, _pmd; pte_t *pte; @@ -277,7 +276,10 @@ static inline bool userfaultfd_must_wait(struct userfaultfd_ctx *ctx, pgd = pgd_offset(mm, address); if (!pgd_present(*pgd)) goto out; - pud = pud_offset(pgd, address); + p4d = p4d_offset(pgd, address); + if (!p4d_present(*p4d)) + goto out; + pud = pud_offset(p4d, address); if (!pud_present(*pud)) goto out; pmd = pmd_offset(pud, address); @@ -490,7 +492,7 @@ int handle_userfault(struct vm_fault *vmf, unsigned long reason) * in such case. */ down_read(&mm->mmap_sem); - ret = 0; + ret = VM_FAULT_NOPAGE; } } @@ -527,10 +529,11 @@ out: return ret; } -static int userfaultfd_event_wait_completion(struct userfaultfd_ctx *ctx, - struct userfaultfd_wait_queue *ewq) +static void userfaultfd_event_wait_completion(struct userfaultfd_ctx *ctx, + struct userfaultfd_wait_queue *ewq) { - int ret = 0; + if (WARN_ON_ONCE(current->flags & PF_EXITING)) + goto out; ewq->ctx = ctx; init_waitqueue_entry(&ewq->wq, current); @@ -547,8 +550,16 @@ static int userfaultfd_event_wait_completion(struct userfaultfd_ctx *ctx, break; if (ACCESS_ONCE(ctx->released) || fatal_signal_pending(current)) { - ret = -1; __remove_wait_queue(&ctx->event_wqh, &ewq->wq); + if (ewq->msg.event == UFFD_EVENT_FORK) { + struct userfaultfd_ctx *new; + + new = (struct userfaultfd_ctx *) + (unsigned long) + ewq->msg.arg.reserved.reserved1; + + userfaultfd_ctx_put(new); + } break; } @@ -566,9 +577,8 @@ static int userfaultfd_event_wait_completion(struct userfaultfd_ctx *ctx, * ctx may go away after this if the userfault pseudo fd is * already released. */ - +out: userfaultfd_ctx_put(ctx); - return ret; } static void userfaultfd_event_complete(struct userfaultfd_ctx *ctx, @@ -626,7 +636,7 @@ int dup_userfaultfd(struct vm_area_struct *vma, struct list_head *fcs) return 0; } -static int dup_fctx(struct userfaultfd_fork_ctx *fctx) +static void dup_fctx(struct userfaultfd_fork_ctx *fctx) { struct userfaultfd_ctx *ctx = fctx->orig; struct userfaultfd_wait_queue ewq; @@ -636,17 +646,15 @@ static int dup_fctx(struct userfaultfd_fork_ctx *fctx) ewq.msg.event = UFFD_EVENT_FORK; ewq.msg.arg.reserved.reserved1 = (unsigned long)fctx->new; - return userfaultfd_event_wait_completion(ctx, &ewq); + userfaultfd_event_wait_completion(ctx, &ewq); } void dup_userfaultfd_complete(struct list_head *fcs) { - int ret = 0; struct userfaultfd_fork_ctx *fctx, *n; list_for_each_entry_safe(fctx, n, fcs, list) { - if (!ret) - ret = dup_fctx(fctx); + dup_fctx(fctx); list_del(&fctx->list); kfree(fctx); } @@ -689,8 +697,7 @@ void mremap_userfaultfd_complete(struct vm_userfaultfd_ctx *vm_ctx, userfaultfd_event_wait_completion(ctx, &ewq); } -void userfaultfd_remove(struct vm_area_struct *vma, - struct vm_area_struct **prev, +bool userfaultfd_remove(struct vm_area_struct *vma, unsigned long start, unsigned long end) { struct mm_struct *mm = vma->vm_mm; @@ -699,13 +706,11 @@ void userfaultfd_remove(struct vm_area_struct *vma, ctx = vma->vm_userfaultfd_ctx.ctx; if (!ctx || !(ctx->features & UFFD_FEATURE_EVENT_REMOVE)) - return; + return true; userfaultfd_ctx_get(ctx); up_read(&mm->mmap_sem); - *prev = NULL; /* We wait for ACK w/o the mmap semaphore */ - msg_init(&ewq.msg); ewq.msg.event = UFFD_EVENT_REMOVE; @@ -714,7 +719,7 @@ void userfaultfd_remove(struct vm_area_struct *vma, userfaultfd_event_wait_completion(ctx, &ewq); - down_read(&mm->mmap_sem); + return false; } static bool has_unmap_ctx(struct userfaultfd_ctx *ctx, struct list_head *unmaps, @@ -775,34 +780,6 @@ void userfaultfd_unmap_complete(struct mm_struct *mm, struct list_head *uf) } } -void userfaultfd_exit(struct mm_struct *mm) -{ - struct vm_area_struct *vma = mm->mmap; - - /* - * We can do the vma walk without locking because the caller - * (exit_mm) knows it now has exclusive access - */ - while (vma) { - struct userfaultfd_ctx *ctx = vma->vm_userfaultfd_ctx.ctx; - - if (ctx && (ctx->features & UFFD_FEATURE_EVENT_EXIT)) { - struct userfaultfd_wait_queue ewq; - - userfaultfd_ctx_get(ctx); - - msg_init(&ewq.msg); - ewq.msg.event = UFFD_EVENT_EXIT; - - userfaultfd_event_wait_completion(ctx, &ewq); - - ctx->features &= ~UFFD_FEATURE_EVENT_EXIT; - } - - vma = vma->vm_next; - } -} - static int userfaultfd_release(struct inode *inode, struct file *file) { struct userfaultfd_ctx *ctx = file->private_data; diff --git a/fs/xfs/kmem.c b/fs/xfs/kmem.c index 2dfdc62f795e..70a5b55e0870 100644 --- a/fs/xfs/kmem.c +++ b/fs/xfs/kmem.c @@ -25,24 +25,6 @@ #include "kmem.h" #include "xfs_message.h" -/* - * Greedy allocation. May fail and may return vmalloced memory. - */ -void * -kmem_zalloc_greedy(size_t *size, size_t minsize, size_t maxsize) -{ - void *ptr; - size_t kmsize = maxsize; - - while (!(ptr = vzalloc(kmsize))) { - if ((kmsize >>= 1) <= minsize) - kmsize = minsize; - } - if (ptr) - *size = kmsize; - return ptr; -} - void * kmem_alloc(size_t size, xfs_km_flags_t flags) { diff --git a/fs/xfs/kmem.h b/fs/xfs/kmem.h index 689f746224e7..f0fc84fcaac2 100644 --- a/fs/xfs/kmem.h +++ b/fs/xfs/kmem.h @@ -69,8 +69,6 @@ static inline void kmem_free(const void *ptr) } -extern void *kmem_zalloc_greedy(size_t *, size_t, size_t); - static inline void * kmem_zalloc(size_t size, xfs_km_flags_t flags) { diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c index a9c66d47757a..9bd104f32908 100644 --- a/fs/xfs/libxfs/xfs_bmap.c +++ b/fs/xfs/libxfs/xfs_bmap.c @@ -763,8 +763,8 @@ xfs_bmap_extents_to_btree( args.type = XFS_ALLOCTYPE_START_BNO; args.fsbno = XFS_INO_TO_FSB(mp, ip->i_ino); } else if (dfops->dop_low) { -try_another_ag: args.type = XFS_ALLOCTYPE_START_BNO; +try_another_ag: args.fsbno = *firstblock; } else { args.type = XFS_ALLOCTYPE_NEAR_BNO; @@ -790,13 +790,17 @@ try_another_ag: if (xfs_sb_version_hasreflink(&cur->bc_mp->m_sb) && args.fsbno == NULLFSBLOCK && args.type == XFS_ALLOCTYPE_NEAR_BNO) { - dfops->dop_low = true; + args.type = XFS_ALLOCTYPE_FIRST_AG; goto try_another_ag; } + if (WARN_ON_ONCE(args.fsbno == NULLFSBLOCK)) { + xfs_iroot_realloc(ip, -1, whichfork); + xfs_btree_del_cursor(cur, XFS_BTREE_ERROR); + return -ENOSPC; + } /* * Allocation can't fail, the space was reserved. */ - ASSERT(args.fsbno != NULLFSBLOCK); ASSERT(*firstblock == NULLFSBLOCK || args.agno >= XFS_FSB_TO_AGNO(mp, *firstblock)); *firstblock = cur->bc_private.b.firstblock = args.fsbno; @@ -4150,6 +4154,19 @@ xfs_bmapi_read( return 0; } +/* + * Add a delayed allocation extent to an inode. Blocks are reserved from the + * global pool and the extent inserted into the inode in-core extent tree. + * + * On entry, got refers to the first extent beyond the offset of the extent to + * allocate or eof is specified if no such extent exists. On return, got refers + * to the extent record that was inserted to the inode fork. + * + * Note that the allocated extent may have been merged with contiguous extents + * during insertion into the inode fork. Thus, got does not reflect the current + * state of the inode fork on return. If necessary, the caller can use lastx to + * look up the updated record in the inode fork. + */ int xfs_bmapi_reserve_delalloc( struct xfs_inode *ip, @@ -4236,13 +4253,8 @@ xfs_bmapi_reserve_delalloc( got->br_startblock = nullstartblock(indlen); got->br_blockcount = alen; got->br_state = XFS_EXT_NORM; - xfs_bmap_add_extent_hole_delay(ip, whichfork, lastx, got); - /* - * Update our extent pointer, given that xfs_bmap_add_extent_hole_delay - * might have merged it into one of the neighbouring ones. - */ - xfs_bmbt_get_all(xfs_iext_get_ext(ifp, *lastx), got); + xfs_bmap_add_extent_hole_delay(ip, whichfork, lastx, got); /* * Tag the inode if blocks were preallocated. Note that COW fork @@ -4254,10 +4266,6 @@ xfs_bmapi_reserve_delalloc( if (whichfork == XFS_COW_FORK && (prealloc || aoff < off || alen > len)) xfs_inode_set_cowblocks_tag(ip); - ASSERT(got->br_startoff <= aoff); - ASSERT(got->br_startoff + got->br_blockcount >= aoff + alen); - ASSERT(isnullstartblock(got->br_startblock)); - ASSERT(got->br_state == XFS_EXT_NORM); return 0; out_unreserve_blocks: diff --git a/fs/xfs/libxfs/xfs_bmap_btree.c b/fs/xfs/libxfs/xfs_bmap_btree.c index f93072b58a58..fd55db479385 100644 --- a/fs/xfs/libxfs/xfs_bmap_btree.c +++ b/fs/xfs/libxfs/xfs_bmap_btree.c @@ -447,8 +447,8 @@ xfs_bmbt_alloc_block( if (args.fsbno == NULLFSBLOCK) { args.fsbno = be64_to_cpu(start->l); -try_another_ag: args.type = XFS_ALLOCTYPE_START_BNO; +try_another_ag: /* * Make sure there is sufficient room left in the AG to * complete a full tree split for an extent insert. If @@ -488,8 +488,8 @@ try_another_ag: if (xfs_sb_version_hasreflink(&cur->bc_mp->m_sb) && args.fsbno == NULLFSBLOCK && args.type == XFS_ALLOCTYPE_NEAR_BNO) { - cur->bc_private.b.dfops->dop_low = true; args.fsbno = cur->bc_private.b.firstblock; + args.type = XFS_ALLOCTYPE_FIRST_AG; goto try_another_ag; } @@ -506,7 +506,7 @@ try_another_ag: goto error0; cur->bc_private.b.dfops->dop_low = true; } - if (args.fsbno == NULLFSBLOCK) { + if (WARN_ON_ONCE(args.fsbno == NULLFSBLOCK)) { XFS_BTREE_TRACE_CURSOR(cur, XBT_EXIT); *stat = 0; return 0; diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c index bf65a9ea8642..61494295d92f 100644 --- a/fs/xfs/xfs_aops.c +++ b/fs/xfs/xfs_aops.c @@ -274,54 +274,49 @@ xfs_end_io( struct xfs_ioend *ioend = container_of(work, struct xfs_ioend, io_work); struct xfs_inode *ip = XFS_I(ioend->io_inode); + xfs_off_t offset = ioend->io_offset; + size_t size = ioend->io_size; int error = ioend->io_bio->bi_error; /* - * Set an error if the mount has shut down and proceed with end I/O - * processing so it can perform whatever cleanups are necessary. + * Just clean up the in-memory strutures if the fs has been shut down. */ - if (XFS_FORCED_SHUTDOWN(ip->i_mount)) + if (XFS_FORCED_SHUTDOWN(ip->i_mount)) { error = -EIO; + goto done; + } /* - * For a CoW extent, we need to move the mapping from the CoW fork - * to the data fork. If instead an error happened, just dump the - * new blocks. + * Clean up any COW blocks on an I/O error. */ - if (ioend->io_type == XFS_IO_COW) { - if (error) - goto done; - if (ioend->io_bio->bi_error) { - error = xfs_reflink_cancel_cow_range(ip, - ioend->io_offset, ioend->io_size); - goto done; + if (unlikely(error)) { + switch (ioend->io_type) { + case XFS_IO_COW: + xfs_reflink_cancel_cow_range(ip, offset, size, true); + break; } - error = xfs_reflink_end_cow(ip, ioend->io_offset, - ioend->io_size); - if (error) - goto done; + + goto done; } /* - * For unwritten extents we need to issue transactions to convert a - * range to normal written extens after the data I/O has finished. - * Detecting and handling completion IO errors is done individually - * for each case as different cleanup operations need to be performed - * on error. + * Success: commit the COW or unwritten blocks if needed. */ - if (ioend->io_type == XFS_IO_UNWRITTEN) { - if (error) - goto done; - error = xfs_iomap_write_unwritten(ip, ioend->io_offset, - ioend->io_size); - } else if (ioend->io_append_trans) { - error = xfs_setfilesize_ioend(ioend, error); - } else { - ASSERT(!xfs_ioend_is_append(ioend) || - ioend->io_type == XFS_IO_COW); + switch (ioend->io_type) { + case XFS_IO_COW: + error = xfs_reflink_end_cow(ip, offset, size); + break; + case XFS_IO_UNWRITTEN: + error = xfs_iomap_write_unwritten(ip, offset, size); + break; + default: + ASSERT(!xfs_ioend_is_append(ioend) || ioend->io_append_trans); + break; } done: + if (ioend->io_append_trans) + error = xfs_setfilesize_ioend(ioend, error); xfs_destroy_ioend(ioend, error); } diff --git a/fs/xfs/xfs_icache.c b/fs/xfs/xfs_icache.c index 7234b9748c36..3531f8f72fa5 100644 --- a/fs/xfs/xfs_icache.c +++ b/fs/xfs/xfs_icache.c @@ -1608,7 +1608,7 @@ xfs_inode_free_cowblocks( xfs_ilock(ip, XFS_IOLOCK_EXCL); xfs_ilock(ip, XFS_MMAPLOCK_EXCL); - ret = xfs_reflink_cancel_cow_range(ip, 0, NULLFILEOFF); + ret = xfs_reflink_cancel_cow_range(ip, 0, NULLFILEOFF, false); xfs_iunlock(ip, XFS_MMAPLOCK_EXCL); xfs_iunlock(ip, XFS_IOLOCK_EXCL); diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c index edfa6a55b064..7eaf1ef74e3c 100644 --- a/fs/xfs/xfs_inode.c +++ b/fs/xfs/xfs_inode.c @@ -1615,7 +1615,7 @@ xfs_itruncate_extents( /* Remove all pending CoW reservations. */ error = xfs_reflink_cancel_cow_blocks(ip, &tp, first_unmap_block, - last_block); + last_block, true); if (error) goto out; diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c index 41662fb14e87..288ee5b840d7 100644 --- a/fs/xfs/xfs_iomap.c +++ b/fs/xfs/xfs_iomap.c @@ -630,6 +630,11 @@ retry: goto out_unlock; } + /* + * Flag newly allocated delalloc blocks with IOMAP_F_NEW so we punch + * them out if the write happens to fail. + */ + iomap->flags = IOMAP_F_NEW; trace_xfs_iomap_alloc(ip, offset, count, 0, &got); done: if (isnullstartblock(got.br_startblock)) @@ -1071,16 +1076,22 @@ xfs_file_iomap_end_delalloc( struct xfs_inode *ip, loff_t offset, loff_t length, - ssize_t written) + ssize_t written, + struct iomap *iomap) { struct xfs_mount *mp = ip->i_mount; xfs_fileoff_t start_fsb; xfs_fileoff_t end_fsb; int error = 0; - /* behave as if the write failed if drop writes is enabled */ - if (xfs_mp_drop_writes(mp)) + /* + * Behave as if the write failed if drop writes is enabled. Set the NEW + * flag to force delalloc cleanup. + */ + if (xfs_mp_drop_writes(mp)) { + iomap->flags |= IOMAP_F_NEW; written = 0; + } /* * start_fsb refers to the first unused block after a short write. If @@ -1094,14 +1105,14 @@ xfs_file_iomap_end_delalloc( end_fsb = XFS_B_TO_FSB(mp, offset + length); /* - * Trim back delalloc blocks if we didn't manage to write the whole - * range reserved. + * Trim delalloc blocks if they were allocated by this write and we + * didn't manage to write the whole range. * * We don't need to care about racing delalloc as we hold i_mutex * across the reserve/allocate/unreserve calls. If there are delalloc * blocks in the range, they are ours. */ - if (start_fsb < end_fsb) { + if ((iomap->flags & IOMAP_F_NEW) && start_fsb < end_fsb) { truncate_pagecache_range(VFS_I(ip), XFS_FSB_TO_B(mp, start_fsb), XFS_FSB_TO_B(mp, end_fsb) - 1); @@ -1131,7 +1142,7 @@ xfs_file_iomap_end( { if ((flags & IOMAP_WRITE) && iomap->type == IOMAP_DELALLOC) return xfs_file_iomap_end_delalloc(XFS_I(inode), offset, - length, written); + length, written, iomap); return 0; } diff --git a/fs/xfs/xfs_itable.c b/fs/xfs/xfs_itable.c index 66e881790c17..2a6d9b1558e0 100644 --- a/fs/xfs/xfs_itable.c +++ b/fs/xfs/xfs_itable.c @@ -361,7 +361,6 @@ xfs_bulkstat( xfs_agino_t agino; /* inode # in allocation group */ xfs_agnumber_t agno; /* allocation group number */ xfs_btree_cur_t *cur; /* btree cursor for ialloc btree */ - size_t irbsize; /* size of irec buffer in bytes */ xfs_inobt_rec_incore_t *irbuf; /* start of irec buffer */ int nirbuf; /* size of irbuf */ int ubcount; /* size of user's buffer */ @@ -388,11 +387,10 @@ xfs_bulkstat( *ubcountp = 0; *done = 0; - irbuf = kmem_zalloc_greedy(&irbsize, PAGE_SIZE, PAGE_SIZE * 4); + irbuf = kmem_zalloc_large(PAGE_SIZE * 4, KM_SLEEP); if (!irbuf) return -ENOMEM; - - nirbuf = irbsize / sizeof(*irbuf); + nirbuf = (PAGE_SIZE * 4) / sizeof(*irbuf); /* * Loop over the allocation groups, starting from the last diff --git a/fs/xfs/xfs_mount.c b/fs/xfs/xfs_mount.c index 450bde68bb75..688ebff1f663 100644 --- a/fs/xfs/xfs_mount.c +++ b/fs/xfs/xfs_mount.c @@ -513,8 +513,7 @@ STATIC void xfs_set_inoalignment(xfs_mount_t *mp) { if (xfs_sb_version_hasalign(&mp->m_sb) && - mp->m_sb.sb_inoalignmt >= - XFS_B_TO_FSBT(mp, mp->m_inode_cluster_size)) + mp->m_sb.sb_inoalignmt >= xfs_icluster_size_fsb(mp)) mp->m_inoalign_mask = mp->m_sb.sb_inoalignmt - 1; else mp->m_inoalign_mask = 0; diff --git a/fs/xfs/xfs_reflink.c b/fs/xfs/xfs_reflink.c index da6d08fb359c..4a84c5ea266d 100644 --- a/fs/xfs/xfs_reflink.c +++ b/fs/xfs/xfs_reflink.c @@ -548,14 +548,18 @@ xfs_reflink_trim_irec_to_next_cow( } /* - * Cancel all pending CoW reservations for some block range of an inode. + * Cancel CoW reservations for some block range of an inode. + * + * If cancel_real is true this function cancels all COW fork extents for the + * inode; if cancel_real is false, real extents are not cleared. */ int xfs_reflink_cancel_cow_blocks( struct xfs_inode *ip, struct xfs_trans **tpp, xfs_fileoff_t offset_fsb, - xfs_fileoff_t end_fsb) + xfs_fileoff_t end_fsb, + bool cancel_real) { struct xfs_ifork *ifp = XFS_IFORK_PTR(ip, XFS_COW_FORK); struct xfs_bmbt_irec got, del; @@ -579,7 +583,7 @@ xfs_reflink_cancel_cow_blocks( &idx, &got, &del); if (error) break; - } else { + } else if (del.br_state == XFS_EXT_UNWRITTEN || cancel_real) { xfs_trans_ijoin(*tpp, ip, 0); xfs_defer_init(&dfops, &firstfsb); @@ -621,13 +625,17 @@ xfs_reflink_cancel_cow_blocks( } /* - * Cancel all pending CoW reservations for some byte range of an inode. + * Cancel CoW reservations for some byte range of an inode. + * + * If cancel_real is true this function cancels all COW fork extents for the + * inode; if cancel_real is false, real extents are not cleared. */ int xfs_reflink_cancel_cow_range( struct xfs_inode *ip, xfs_off_t offset, - xfs_off_t count) + xfs_off_t count, + bool cancel_real) { struct xfs_trans *tp; xfs_fileoff_t offset_fsb; @@ -653,7 +661,8 @@ xfs_reflink_cancel_cow_range( xfs_trans_ijoin(tp, ip, 0); /* Scrape out the old CoW reservations */ - error = xfs_reflink_cancel_cow_blocks(ip, &tp, offset_fsb, end_fsb); + error = xfs_reflink_cancel_cow_blocks(ip, &tp, offset_fsb, end_fsb, + cancel_real); if (error) goto out_cancel; @@ -1450,7 +1459,7 @@ next: * We didn't find any shared blocks so turn off the reflink flag. * First, get rid of any leftover CoW mappings. */ - error = xfs_reflink_cancel_cow_blocks(ip, tpp, 0, NULLFILEOFF); + error = xfs_reflink_cancel_cow_blocks(ip, tpp, 0, NULLFILEOFF, true); if (error) return error; diff --git a/fs/xfs/xfs_reflink.h b/fs/xfs/xfs_reflink.h index 33ac9b8db683..d29a7967f029 100644 --- a/fs/xfs/xfs_reflink.h +++ b/fs/xfs/xfs_reflink.h @@ -39,9 +39,9 @@ extern void xfs_reflink_trim_irec_to_next_cow(struct xfs_inode *ip, extern int xfs_reflink_cancel_cow_blocks(struct xfs_inode *ip, struct xfs_trans **tpp, xfs_fileoff_t offset_fsb, - xfs_fileoff_t end_fsb); + xfs_fileoff_t end_fsb, bool cancel_real); extern int xfs_reflink_cancel_cow_range(struct xfs_inode *ip, xfs_off_t offset, - xfs_off_t count); + xfs_off_t count, bool cancel_real); extern int xfs_reflink_end_cow(struct xfs_inode *ip, xfs_off_t offset, xfs_off_t count); extern int xfs_reflink_recover_cow(struct xfs_mount *mp); diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c index 890862f2447c..685c042a120f 100644 --- a/fs/xfs/xfs_super.c +++ b/fs/xfs/xfs_super.c @@ -953,7 +953,7 @@ xfs_fs_destroy_inode( XFS_STATS_INC(ip->i_mount, vn_remove); if (xfs_is_reflink_inode(ip)) { - error = xfs_reflink_cancel_cow_range(ip, 0, NULLFILEOFF); + error = xfs_reflink_cancel_cow_range(ip, 0, NULLFILEOFF, true); if (error && !XFS_FORCED_SHUTDOWN(ip->i_mount)) xfs_warn(ip->i_mount, "Error %d while evicting CoW blocks for inode %llu.", diff --git a/include/asm-generic/4level-fixup.h b/include/asm-generic/4level-fixup.h index 5bdab6bffd23..928fd66b1271 100644 --- a/include/asm-generic/4level-fixup.h +++ b/include/asm-generic/4level-fixup.h @@ -15,7 +15,6 @@ ((unlikely(pgd_none(*(pud))) && __pmd_alloc(mm, pud, address))? \ NULL: pmd_offset(pud, address)) -#define pud_alloc(mm, pgd, address) (pgd) #define pud_offset(pgd, start) (pgd) #define pud_none(pud) 0 #define pud_bad(pud) 0 @@ -35,4 +34,6 @@ #undef pud_addr_end #define pud_addr_end(addr, end) (end) +#include <asm-generic/5level-fixup.h> + #endif diff --git a/include/asm-generic/5level-fixup.h b/include/asm-generic/5level-fixup.h new file mode 100644 index 000000000000..b5ca82dc4175 --- /dev/null +++ b/include/asm-generic/5level-fixup.h @@ -0,0 +1,41 @@ +#ifndef _5LEVEL_FIXUP_H +#define _5LEVEL_FIXUP_H + +#define __ARCH_HAS_5LEVEL_HACK +#define __PAGETABLE_P4D_FOLDED + +#define P4D_SHIFT PGDIR_SHIFT +#define P4D_SIZE PGDIR_SIZE +#define P4D_MASK PGDIR_MASK +#define PTRS_PER_P4D 1 + +#define p4d_t pgd_t + +#define pud_alloc(mm, p4d, address) \ + ((unlikely(pgd_none(*(p4d))) && __pud_alloc(mm, p4d, address)) ? \ + NULL : pud_offset(p4d, address)) + +#define p4d_alloc(mm, pgd, address) (pgd) +#define p4d_offset(pgd, start) (pgd) +#define p4d_none(p4d) 0 +#define p4d_bad(p4d) 0 +#define p4d_present(p4d) 1 +#define p4d_ERROR(p4d) do { } while (0) +#define p4d_clear(p4d) pgd_clear(p4d) +#define p4d_val(p4d) pgd_val(p4d) +#define p4d_populate(mm, p4d, pud) pgd_populate(mm, p4d, pud) +#define p4d_page(p4d) pgd_page(p4d) +#define p4d_page_vaddr(p4d) pgd_page_vaddr(p4d) + +#define __p4d(x) __pgd(x) +#define set_p4d(p4dp, p4d) set_pgd(p4dp, p4d) + +#undef p4d_free_tlb +#define p4d_free_tlb(tlb, x, addr) do { } while (0) +#define p4d_free(mm, x) do { } while (0) +#define __p4d_free_tlb(tlb, x, addr) do { } while (0) + +#undef p4d_addr_end +#define p4d_addr_end(addr, end) (end) + +#endif diff --git a/include/asm-generic/pgtable-nop4d-hack.h b/include/asm-generic/pgtable-nop4d-hack.h new file mode 100644 index 000000000000..752fb7511750 --- /dev/null +++ b/include/asm-generic/pgtable-nop4d-hack.h @@ -0,0 +1,62 @@ +#ifndef _PGTABLE_NOP4D_HACK_H +#define _PGTABLE_NOP4D_HACK_H + +#ifndef __ASSEMBLY__ +#include <asm-generic/5level-fixup.h> + +#define __PAGETABLE_PUD_FOLDED + +/* + * Having the pud type consist of a pgd gets the size right, and allows + * us to conceptually access the pgd entry that this pud is folded into + * without casting. + */ +typedef struct { pgd_t pgd; } pud_t; + +#define PUD_SHIFT PGDIR_SHIFT +#define PTRS_PER_PUD 1 +#define PUD_SIZE (1UL << PUD_SHIFT) +#define PUD_MASK (~(PUD_SIZE-1)) + +/* + * The "pgd_xxx()" functions here are trivial for a folded two-level + * setup: the pud is never bad, and a pud always exists (as it's folded + * into the pgd entry) + */ +static inline int pgd_none(pgd_t pgd) { return 0; } +static inline int pgd_bad(pgd_t pgd) { return 0; } +static inline int pgd_present(pgd_t pgd) { return 1; } +static inline void pgd_clear(pgd_t *pgd) { } +#define pud_ERROR(pud) (pgd_ERROR((pud).pgd)) + +#define pgd_populate(mm, pgd, pud) do { } while (0) +/* + * (puds are folded into pgds so this doesn't get actually called, + * but the define is needed for a generic inline function.) + */ +#define set_pgd(pgdptr, pgdval) set_pud((pud_t *)(pgdptr), (pud_t) { pgdval }) + +static inline pud_t *pud_offset(pgd_t *pgd, unsigned long address) +{ + return (pud_t *)pgd; +} + +#define pud_val(x) (pgd_val((x).pgd)) +#define __pud(x) ((pud_t) { __pgd(x) }) + +#define pgd_page(pgd) (pud_page((pud_t){ pgd })) +#define pgd_page_vaddr(pgd) (pud_page_vaddr((pud_t){ pgd })) + +/* + * allocating and freeing a pud is trivial: the 1-entry pud is + * inside the pgd, so has no extra memory associated with it. + */ +#define pud_alloc_one(mm, address) NULL +#define pud_free(mm, x) do { } while (0) +#define __pud_free_tlb(tlb, x, a) do { } while (0) + +#undef pud_addr_end +#define pud_addr_end(addr, end) (end) + +#endif /* __ASSEMBLY__ */ +#endif /* _PGTABLE_NOP4D_HACK_H */ diff --git a/include/asm-generic/pgtable-nop4d.h b/include/asm-generic/pgtable-nop4d.h new file mode 100644 index 000000000000..de364ecb8df6 --- /dev/null +++ b/include/asm-generic/pgtable-nop4d.h @@ -0,0 +1,56 @@ +#ifndef _PGTABLE_NOP4D_H +#define _PGTABLE_NOP4D_H + +#ifndef __ASSEMBLY__ + +#define __PAGETABLE_P4D_FOLDED + +typedef struct { pgd_t pgd; } p4d_t; + +#define P4D_SHIFT PGDIR_SHIFT +#define PTRS_PER_P4D 1 +#define P4D_SIZE (1UL << P4D_SHIFT) +#define P4D_MASK (~(P4D_SIZE-1)) + +/* + * The "pgd_xxx()" functions here are trivial for a folded two-level + * setup: the p4d is never bad, and a p4d always exists (as it's folded + * into the pgd entry) + */ +static inline int pgd_none(pgd_t pgd) { return 0; } +static inline int pgd_bad(pgd_t pgd) { return 0; } +static inline int pgd_present(pgd_t pgd) { return 1; } +static inline void pgd_clear(pgd_t *pgd) { } +#define p4d_ERROR(p4d) (pgd_ERROR((p4d).pgd)) + +#define pgd_populate(mm, pgd, p4d) do { } while (0) +/* + * (p4ds are folded into pgds so this doesn't get actually called, + * but the define is needed for a generic inline function.) + */ +#define set_pgd(pgdptr, pgdval) set_p4d((p4d_t *)(pgdptr), (p4d_t) { pgdval }) + +static inline p4d_t *p4d_offset(pgd_t *pgd, unsigned long address) +{ + return (p4d_t *)pgd; +} + +#define p4d_val(x) (pgd_val((x).pgd)) +#define __p4d(x) ((p4d_t) { __pgd(x) }) + +#define pgd_page(pgd) (p4d_page((p4d_t){ pgd })) +#define pgd_page_vaddr(pgd) (p4d_page_vaddr((p4d_t){ pgd })) + +/* + * allocating and freeing a p4d is trivial: the 1-entry p4d is + * inside the pgd, so has no extra memory associated with it. + */ +#define p4d_alloc_one(mm, address) NULL +#define p4d_free(mm, x) do { } while (0) +#define __p4d_free_tlb(tlb, x, a) do { } while (0) + +#undef p4d_addr_end +#define p4d_addr_end(addr, end) (end) + +#endif /* __ASSEMBLY__ */ +#endif /* _PGTABLE_NOP4D_H */ diff --git a/include/asm-generic/pgtable-nopud.h b/include/asm-generic/pgtable-nopud.h index 810431d8351b..c2b9b96d6268 100644 --- a/include/asm-generic/pgtable-nopud.h +++ b/include/asm-generic/pgtable-nopud.h @@ -3,52 +3,57 @@ #ifndef __ASSEMBLY__ +#ifdef __ARCH_USE_5LEVEL_HACK +#include <asm-generic/pgtable-nop4d-hack.h> +#else +#include <asm-generic/pgtable-nop4d.h> + #define __PAGETABLE_PUD_FOLDED /* - * Having the pud type consist of a pgd gets the size right, and allows - * us to conceptually access the pgd entry that this pud is folded into + * Having the pud type consist of a p4d gets the size right, and allows + * us to conceptually access the p4d entry that this pud is folded into * without casting. */ -typedef struct { pgd_t pgd; } pud_t; +typedef struct { p4d_t p4d; } pud_t; -#define PUD_SHIFT PGDIR_SHIFT +#define PUD_SHIFT P4D_SHIFT #define PTRS_PER_PUD 1 #define PUD_SIZE (1UL << PUD_SHIFT) #define PUD_MASK (~(PUD_SIZE-1)) /* - * The "pgd_xxx()" functions here are trivial for a folded two-level + * The "p4d_xxx()" functions here are trivial for a folded two-level * setup: the pud is never bad, and a pud always exists (as it's folded - * into the pgd entry) + * into the p4d entry) */ -static inline int pgd_none(pgd_t pgd) { return 0; } -static inline int pgd_bad(pgd_t pgd) { return 0; } -static inline int pgd_present(pgd_t pgd) { return 1; } -static inline void pgd_clear(pgd_t *pgd) { } -#define pud_ERROR(pud) (pgd_ERROR((pud).pgd)) +static inline int p4d_none(p4d_t p4d) { return 0; } +static inline int p4d_bad(p4d_t p4d) { return 0; } +static inline int p4d_present(p4d_t p4d) { return 1; } +static inline void p4d_clear(p4d_t *p4d) { } +#define pud_ERROR(pud) (p4d_ERROR((pud).p4d)) -#define pgd_populate(mm, pgd, pud) do { } while (0) +#define p4d_populate(mm, p4d, pud) do { } while (0) /* - * (puds are folded into pgds so this doesn't get actually called, + * (puds are folded into p4ds so this doesn't get actually called, * but the define is needed for a generic inline function.) */ -#define set_pgd(pgdptr, pgdval) set_pud((pud_t *)(pgdptr), (pud_t) { pgdval }) +#define set_p4d(p4dptr, p4dval) set_pud((pud_t *)(p4dptr), (pud_t) { p4dval }) -static inline pud_t * pud_offset(pgd_t * pgd, unsigned long address) +static inline pud_t *pud_offset(p4d_t *p4d, unsigned long address) { - return (pud_t *)pgd; + return (pud_t *)p4d; } -#define pud_val(x) (pgd_val((x).pgd)) -#define __pud(x) ((pud_t) { __pgd(x) } ) +#define pud_val(x) (p4d_val((x).p4d)) +#define __pud(x) ((pud_t) { __p4d(x) }) -#define pgd_page(pgd) (pud_page((pud_t){ pgd })) -#define pgd_page_vaddr(pgd) (pud_page_vaddr((pud_t){ pgd })) +#define p4d_page(p4d) (pud_page((pud_t){ p4d })) +#define p4d_page_vaddr(p4d) (pud_page_vaddr((pud_t){ p4d })) /* * allocating and freeing a pud is trivial: the 1-entry pud is - * inside the pgd, so has no extra memory associated with it. + * inside the p4d, so has no extra memory associated with it. */ #define pud_alloc_one(mm, address) NULL #define pud_free(mm, x) do { } while (0) @@ -58,4 +63,5 @@ static inline pud_t * pud_offset(pgd_t * pgd, unsigned long address) #define pud_addr_end(addr, end) (end) #endif /* __ASSEMBLY__ */ +#endif /* !__ARCH_USE_5LEVEL_HACK */ #endif /* _PGTABLE_NOPUD_H */ diff --git a/include/asm-generic/pgtable.h b/include/asm-generic/pgtable.h index f4ca23b158b3..1fad160f35de 100644 --- a/include/asm-generic/pgtable.h +++ b/include/asm-generic/pgtable.h @@ -10,9 +10,9 @@ #include <linux/bug.h> #include <linux/errno.h> -#if 4 - defined(__PAGETABLE_PUD_FOLDED) - defined(__PAGETABLE_PMD_FOLDED) != \ - CONFIG_PGTABLE_LEVELS -#error CONFIG_PGTABLE_LEVELS is not consistent with __PAGETABLE_{PUD,PMD}_FOLDED +#if 5 - defined(__PAGETABLE_P4D_FOLDED) - defined(__PAGETABLE_PUD_FOLDED) - \ + defined(__PAGETABLE_PMD_FOLDED) != CONFIG_PGTABLE_LEVELS +#error CONFIG_PGTABLE_LEVELS is not consistent with __PAGETABLE_{P4D,PUD,PMD}_FOLDED #endif /* @@ -424,6 +424,13 @@ static inline pgprot_t pgprot_modify(pgprot_t oldprot, pgprot_t newprot) (__boundary - 1 < (end) - 1)? __boundary: (end); \ }) +#ifndef p4d_addr_end +#define p4d_addr_end(addr, end) \ +({ unsigned long __boundary = ((addr) + P4D_SIZE) & P4D_MASK; \ + (__boundary - 1 < (end) - 1)? __boundary: (end); \ +}) +#endif + #ifndef pud_addr_end #define pud_addr_end(addr, end) \ ({ unsigned long __boundary = ((addr) + PUD_SIZE) & PUD_MASK; \ @@ -444,6 +451,7 @@ static inline pgprot_t pgprot_modify(pgprot_t oldprot, pgprot_t newprot) * Do the tests inline, but report and clear the bad entry in mm/memory.c. */ void pgd_clear_bad(pgd_t *); +void p4d_clear_bad(p4d_t *); void pud_clear_bad(pud_t *); void pmd_clear_bad(pmd_t *); @@ -458,6 +466,17 @@ static inline int pgd_none_or_clear_bad(pgd_t *pgd) return 0; } +static inline int p4d_none_or_clear_bad(p4d_t *p4d) +{ + if (p4d_none(*p4d)) + return 1; + if (unlikely(p4d_bad(*p4d))) { + p4d_clear_bad(p4d); + return 1; + } + return 0; +} + static inline int pud_none_or_clear_bad(pud_t *pud) { if (pud_none(*pud)) @@ -844,11 +863,30 @@ static inline int pmd_protnone(pmd_t pmd) #endif /* CONFIG_MMU */ #ifdef CONFIG_HAVE_ARCH_HUGE_VMAP + +#ifndef __PAGETABLE_P4D_FOLDED +int p4d_set_huge(p4d_t *p4d, phys_addr_t addr, pgprot_t prot); +int p4d_clear_huge(p4d_t *p4d); +#else +static inline int p4d_set_huge(p4d_t *p4d, phys_addr_t addr, pgprot_t prot) +{ + return 0; +} +static inline int p4d_clear_huge(p4d_t *p4d) +{ + return 0; +} +#endif /* !__PAGETABLE_P4D_FOLDED */ + int pud_set_huge(pud_t *pud, phys_addr_t addr, pgprot_t prot); int pmd_set_huge(pmd_t *pmd, phys_addr_t addr, pgprot_t prot); int pud_clear_huge(pud_t *pud); int pmd_clear_huge(pmd_t *pmd); #else /* !CONFIG_HAVE_ARCH_HUGE_VMAP */ +static inline int p4d_set_huge(p4d_t *p4d, phys_addr_t addr, pgprot_t prot) +{ + return 0; +} static inline int pud_set_huge(pud_t *pud, phys_addr_t addr, pgprot_t prot) { return 0; @@ -857,6 +895,10 @@ static inline int pmd_set_huge(pmd_t *pmd, phys_addr_t addr, pgprot_t prot) { return 0; } +static inline int p4d_clear_huge(p4d_t *p4d) +{ + return 0; +} static inline int pud_clear_huge(pud_t *pud) { return 0; diff --git a/include/asm-generic/tlb.h b/include/asm-generic/tlb.h index 4329bc6ef04b..8afa4335e5b2 100644 --- a/include/asm-generic/tlb.h +++ b/include/asm-generic/tlb.h @@ -270,6 +270,12 @@ static inline void tlb_remove_check_page_size_change(struct mmu_gather *tlb, __pte_free_tlb(tlb, ptep, address); \ } while (0) +#define pmd_free_tlb(tlb, pmdp, address) \ + do { \ + __tlb_adjust_range(tlb, address, PAGE_SIZE); \ + __pmd_free_tlb(tlb, pmdp, address); \ + } while (0) + #ifndef __ARCH_HAS_4LEVEL_HACK #define pud_free_tlb(tlb, pudp, address) \ do { \ @@ -278,11 +284,13 @@ static inline void tlb_remove_check_page_size_change(struct mmu_gather *tlb, } while (0) #endif -#define pmd_free_tlb(tlb, pmdp, address) \ +#ifndef __ARCH_HAS_5LEVEL_HACK +#define p4d_free_tlb(tlb, pudp, address) \ do { \ - __tlb_adjust_range(tlb, address, PAGE_SIZE); \ - __pmd_free_tlb(tlb, pmdp, address); \ + __tlb_adjust_range(tlb, address, PAGE_SIZE); \ + __p4d_free_tlb(tlb, pudp, address); \ } while (0) +#endif #define tlb_migrate_finish(mm) do {} while (0) diff --git a/include/crypto/if_alg.h b/include/crypto/if_alg.h index a2bfd7843f18..e2b9c6fe2714 100644 --- a/include/crypto/if_alg.h +++ b/include/crypto/if_alg.h @@ -73,7 +73,7 @@ int af_alg_unregister_type(const struct af_alg_type *type); int af_alg_release(struct socket *sock); void af_alg_release_parent(struct sock *sk); -int af_alg_accept(struct sock *sk, struct socket *newsock); +int af_alg_accept(struct sock *sk, struct socket *newsock, bool kern); int af_alg_make_sg(struct af_alg_sgl *sgl, struct iov_iter *iter, int len); void af_alg_free_sg(struct af_alg_sgl *sgl); diff --git a/include/dt-bindings/sound/cs42l42.h b/include/dt-bindings/sound/cs42l42.h index 399a123aed58..db69d84ed7d1 100644 --- a/include/dt-bindings/sound/cs42l42.h +++ b/include/dt-bindings/sound/cs42l42.h @@ -20,7 +20,7 @@ #define CS42L42_HPOUT_LOAD_1NF 0 #define CS42L42_HPOUT_LOAD_10NF 1 -/* HPOUT Clamp to GND Overide */ +/* HPOUT Clamp to GND Override */ #define CS42L42_HPOUT_CLAMP_EN 0 #define CS42L42_HPOUT_CLAMP_DIS 1 diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 796016e63c1d..5a7da607ca04 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -435,7 +435,6 @@ struct request_queue { struct delayed_work delay_work; struct backing_dev_info *backing_dev_info; - struct disk_devt *disk_devt; /* * The queue owner gets to use this for whatever they like. diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 909fc033173a..da8c64ca8dc9 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -35,6 +35,7 @@ struct bpf_map_ops { void *(*map_fd_get_ptr)(struct bpf_map *map, struct file *map_file, int fd); void (*map_fd_put_ptr)(void *ptr); + u32 (*map_gen_lookup)(struct bpf_map *map, struct bpf_insn *insn_buf); }; struct bpf_map { diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index a13b031dc6b8..5efb4db44e1e 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -66,7 +66,10 @@ struct bpf_verifier_state_list { }; struct bpf_insn_aux_data { - enum bpf_reg_type ptr_type; /* pointer type for load/store insns */ + union { + enum bpf_reg_type ptr_type; /* pointer type for load/store insns */ + struct bpf_map *map_ptr; /* pointer for call insn into lookup_elem */ + }; }; #define MAX_USED_MAPS 64 /* max number of maps accessed by one eBPF program */ diff --git a/include/linux/brcmphy.h b/include/linux/brcmphy.h index 55e517130311..abcda9b458ab 100644 --- a/include/linux/brcmphy.h +++ b/include/linux/brcmphy.h @@ -25,6 +25,9 @@ #define PHY_ID_BCM57780 0x03625d90 #define PHY_ID_BCM7250 0xae025280 +#define PHY_ID_BCM7260 0xae025190 +#define PHY_ID_BCM7268 0xae025090 +#define PHY_ID_BCM7271 0xae0253b0 #define PHY_ID_BCM7278 0xae0251a0 #define PHY_ID_BCM7364 0xae025260 #define PHY_ID_BCM7366 0x600d8490 diff --git a/include/linux/ceph/libceph.h b/include/linux/ceph/libceph.h index 1816c5e26581..88cd5dc8e238 100644 --- a/include/linux/ceph/libceph.h +++ b/include/linux/ceph/libceph.h @@ -48,6 +48,7 @@ struct ceph_options { unsigned long mount_timeout; /* jiffies */ unsigned long osd_idle_ttl; /* jiffies */ unsigned long osd_keepalive_timeout; /* jiffies */ + unsigned long osd_request_timeout; /* jiffies */ /* * any type that can't be simply compared or doesn't need need @@ -68,6 +69,7 @@ struct ceph_options { #define CEPH_MOUNT_TIMEOUT_DEFAULT msecs_to_jiffies(60 * 1000) #define CEPH_OSD_KEEPALIVE_DEFAULT msecs_to_jiffies(5 * 1000) #define CEPH_OSD_IDLE_TTL_DEFAULT msecs_to_jiffies(60 * 1000) +#define CEPH_OSD_REQUEST_TIMEOUT_DEFAULT 0 /* no timeout */ #define CEPH_MONC_HUNT_INTERVAL msecs_to_jiffies(3 * 1000) #define CEPH_MONC_PING_INTERVAL msecs_to_jiffies(10 * 1000) diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h index 2ea0c282f3dc..c125b5d9e13c 100644 --- a/include/linux/ceph/osd_client.h +++ b/include/linux/ceph/osd_client.h @@ -189,6 +189,7 @@ struct ceph_osd_request { /* internal */ unsigned long r_stamp; /* jiffies, send or check time */ + unsigned long r_start_stamp; /* jiffies */ int r_attempts; struct ceph_eversion r_replay_version; /* aka reassert_version */ u32 r_last_force_resend; diff --git a/include/linux/dccp.h b/include/linux/dccp.h index 61d042bbbf60..68449293c4b6 100644 --- a/include/linux/dccp.h +++ b/include/linux/dccp.h @@ -163,6 +163,7 @@ struct dccp_request_sock { __u64 dreq_isr; __u64 dreq_gsr; __be32 dreq_service; + spinlock_t dreq_lock; struct list_head dreq_featneg; __u32 dreq_timestamp_echo; __u32 dreq_timestamp_time; diff --git a/include/linux/etherdevice.h b/include/linux/etherdevice.h index c62b709b1ce0..2d9f80848d4b 100644 --- a/include/linux/etherdevice.h +++ b/include/linux/etherdevice.h @@ -447,21 +447,6 @@ static inline void eth_addr_dec(u8 *addr) } /** - * ether_addr_greater - Compare two Ethernet addresses - * @addr1: Pointer to a six-byte array containing the Ethernet address - * @addr2: Pointer other six-byte array containing the Ethernet address - * - * Compare two Ethernet addresses, returns true addr1 is greater than addr2 - */ -static inline bool ether_addr_greater(const u8 *addr1, const u8 *addr2) -{ - u64 u1 = ether_addr_to_u64(addr1); - u64 u2 = ether_addr_to_u64(addr2); - - return u1 > u2; -} - -/** * is_etherdev_addr - Tell if given Ethernet address belongs to the device. * @dev: Pointer to a device structure * @addr: Pointer to a six-byte array containing the Ethernet address diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h index 9ded8c6d8176..83cc9863444b 100644 --- a/include/linux/ethtool.h +++ b/include/linux/ethtool.h @@ -60,6 +60,7 @@ enum ethtool_phys_id_state { enum { ETH_RSS_HASH_TOP_BIT, /* Configurable RSS hash function - Toeplitz */ ETH_RSS_HASH_XOR_BIT, /* Configurable RSS hash function - Xor */ + ETH_RSS_HASH_CRC32_BIT, /* Configurable RSS hash function - Crc32 */ /* * Add your fresh new hash function bits above and remember to update @@ -73,6 +74,7 @@ enum { #define ETH_RSS_HASH_TOP __ETH_RSS_HASH(TOP) #define ETH_RSS_HASH_XOR __ETH_RSS_HASH(XOR) +#define ETH_RSS_HASH_CRC32 __ETH_RSS_HASH(CRC32) #define ETH_RSS_HASH_UNKNOWN 0 #define ETH_RSS_HASH_NO_CHANGE 0 diff --git a/include/linux/filter.h b/include/linux/filter.h index 0c167fdee5f7..dffa072b7b79 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -409,6 +409,7 @@ struct bpf_prog { u16 pages; /* Number of allocated pages */ kmemcheck_bitfield_begin(meta); u16 jited:1, /* Is our filter JIT'ed? */ + locked:1, /* Program image locked? */ gpl_compatible:1, /* Is filter GPL compatible? */ cb_access:1, /* Is control block accessed? */ dst_needed:1, /* Do we need dst entry? */ @@ -554,22 +555,29 @@ static inline bool bpf_prog_was_classic(const struct bpf_prog *prog) #ifdef CONFIG_ARCH_HAS_SET_MEMORY static inline void bpf_prog_lock_ro(struct bpf_prog *fp) { - set_memory_ro((unsigned long)fp, fp->pages); + fp->locked = 1; + WARN_ON_ONCE(set_memory_ro((unsigned long)fp, fp->pages)); } static inline void bpf_prog_unlock_ro(struct bpf_prog *fp) { - set_memory_rw((unsigned long)fp, fp->pages); + if (fp->locked) { + WARN_ON_ONCE(set_memory_rw((unsigned long)fp, fp->pages)); + /* In case set_memory_rw() fails, we want to be the first + * to crash here instead of some random place later on. + */ + fp->locked = 0; + } } static inline void bpf_jit_binary_lock_ro(struct bpf_binary_header *hdr) { - set_memory_ro((unsigned long)hdr, hdr->pages); + WARN_ON_ONCE(set_memory_ro((unsigned long)hdr, hdr->pages)); } static inline void bpf_jit_binary_unlock_ro(struct bpf_binary_header *hdr) { - set_memory_rw((unsigned long)hdr, hdr->pages); + WARN_ON_ONCE(set_memory_rw((unsigned long)hdr, hdr->pages)); } #else static inline void bpf_prog_lock_ro(struct bpf_prog *fp) @@ -685,6 +693,11 @@ static inline bool bpf_jit_is_ebpf(void) # endif } +static inline bool ebpf_jit_enabled(void) +{ + return bpf_jit_enable && bpf_jit_is_ebpf(); +} + static inline bool bpf_prog_ebpf_jited(const struct bpf_prog *fp) { return fp->jited && bpf_jit_is_ebpf(); @@ -745,6 +758,11 @@ void bpf_prog_kallsyms_del(struct bpf_prog *fp); #else /* CONFIG_BPF_JIT */ +static inline bool ebpf_jit_enabled(void) +{ + return false; +} + static inline bool bpf_prog_ebpf_jited(const struct bpf_prog *fp) { return false; diff --git a/include/linux/fs.h b/include/linux/fs.h index aad3fd0ff5f8..7251f7bb45e8 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2678,7 +2678,7 @@ static const char * const kernel_read_file_str[] = { static inline const char *kernel_read_file_id_str(enum kernel_read_file_id id) { - if (id < 0 || id >= READING_MAX_ID) + if ((unsigned)id >= READING_MAX_ID) return kernel_read_file_str[READING_UNKNOWN]; return kernel_read_file_str[id]; diff --git a/include/linux/genhd.h b/include/linux/genhd.h index a999d281a2f1..76f39754e7b0 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -167,13 +167,6 @@ struct blk_integrity { }; #endif /* CONFIG_BLK_DEV_INTEGRITY */ -struct disk_devt { - atomic_t count; - void (*release)(struct disk_devt *disk_devt); -}; - -void put_disk_devt(struct disk_devt *disk_devt); -void get_disk_devt(struct disk_devt *disk_devt); struct gendisk { /* major, first_minor and minors are input parameters only, @@ -183,7 +176,6 @@ struct gendisk { int first_minor; int minors; /* maximum number of minors, =1 for * disks that can't be partitioned. */ - struct disk_devt *disk_devt; char disk_name[DISK_NAME_LEN]; /* name of major driver */ char *(*devnode)(struct gendisk *gd, umode_t *mode); diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 503099d8aada..b857fc8cc2ec 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -122,7 +122,7 @@ struct page *follow_huge_pmd(struct mm_struct *mm, unsigned long address, struct page *follow_huge_pud(struct mm_struct *mm, unsigned long address, pud_t *pud, int flags); int pmd_huge(pmd_t pmd); -int pud_huge(pud_t pmd); +int pud_huge(pud_t pud); unsigned long hugetlb_change_protection(struct vm_area_struct *vma, unsigned long address, unsigned long end, pgprot_t newprot); @@ -197,6 +197,9 @@ static inline void __unmap_hugepage_range(struct mmu_gather *tlb, #ifndef pgd_huge #define pgd_huge(x) 0 #endif +#ifndef p4d_huge +#define p4d_huge(x) 0 +#endif #ifndef pgd_write static inline int pgd_write(pgd_t pgd) diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h index 62bbf3c1aa4a..36162485d663 100644 --- a/include/linux/hyperv.h +++ b/include/linux/hyperv.h @@ -1504,14 +1504,6 @@ static inline void hv_signal_on_read(struct vmbus_channel *channel) return; } -static inline void -init_cached_read_index(struct vmbus_channel *channel) -{ - struct hv_ring_buffer_info *rbi = &channel->inbound; - - rbi->cached_read_index = rbi->ring_buffer->read_index; -} - /* * Mask off host interrupt callback notifications */ @@ -1545,76 +1537,48 @@ static inline u32 hv_end_read(struct hv_ring_buffer_info *rbi) /* * An API to support in-place processing of incoming VMBUS packets. */ -#define VMBUS_PKT_TRAILER 8 -static inline struct vmpacket_descriptor * -get_next_pkt_raw(struct vmbus_channel *channel) +/* Get data payload associated with descriptor */ +static inline void *hv_pkt_data(const struct vmpacket_descriptor *desc) { - struct hv_ring_buffer_info *ring_info = &channel->inbound; - u32 priv_read_loc = ring_info->priv_read_index; - void *ring_buffer = hv_get_ring_buffer(ring_info); - u32 dsize = ring_info->ring_datasize; - /* - * delta is the difference between what is available to read and - * what was already consumed in place. We commit read index after - * the whole batch is processed. - */ - u32 delta = priv_read_loc >= ring_info->ring_buffer->read_index ? - priv_read_loc - ring_info->ring_buffer->read_index : - (dsize - ring_info->ring_buffer->read_index) + priv_read_loc; - u32 bytes_avail_toread = (hv_get_bytes_to_read(ring_info) - delta); - - if (bytes_avail_toread < sizeof(struct vmpacket_descriptor)) - return NULL; - - return ring_buffer + priv_read_loc; + return (void *)((unsigned long)desc + (desc->offset8 << 3)); } -/* - * A helper function to step through packets "in-place" - * This API is to be called after each successful call - * get_next_pkt_raw(). - */ -static inline void put_pkt_raw(struct vmbus_channel *channel, - struct vmpacket_descriptor *desc) +/* Get data size associated with descriptor */ +static inline u32 hv_pkt_datalen(const struct vmpacket_descriptor *desc) { - struct hv_ring_buffer_info *ring_info = &channel->inbound; - u32 packetlen = desc->len8 << 3; - u32 dsize = ring_info->ring_datasize; - - /* - * Include the packet trailer. - */ - ring_info->priv_read_index += packetlen + VMBUS_PKT_TRAILER; - ring_info->priv_read_index %= dsize; + return (desc->len8 << 3) - (desc->offset8 << 3); } + +struct vmpacket_descriptor * +hv_pkt_iter_first(struct vmbus_channel *channel); + +struct vmpacket_descriptor * +__hv_pkt_iter_next(struct vmbus_channel *channel, + const struct vmpacket_descriptor *pkt); + +void hv_pkt_iter_close(struct vmbus_channel *channel); + /* - * This call commits the read index and potentially signals the host. - * Here is the pattern for using the "in-place" consumption APIs: - * - * init_cached_read_index(); - * - * while (get_next_pkt_raw() { - * process the packet "in-place"; - * put_pkt_raw(); - * } - * if (packets processed in place) - * commit_rd_index(); + * Get next packet descriptor from iterator + * If at end of list, return NULL and update host. */ -static inline void commit_rd_index(struct vmbus_channel *channel) +static inline struct vmpacket_descriptor * +hv_pkt_iter_next(struct vmbus_channel *channel, + const struct vmpacket_descriptor *pkt) { - struct hv_ring_buffer_info *ring_info = &channel->inbound; - /* - * Make sure all reads are done before we update the read index since - * the writer may start writing to the read area once the read index - * is updated. - */ - virt_rmb(); - ring_info->ring_buffer->read_index = ring_info->priv_read_index; + struct vmpacket_descriptor *nxt; + + nxt = __hv_pkt_iter_next(channel, pkt); + if (!nxt) + hv_pkt_iter_close(channel); - hv_signal_on_read(channel); + return nxt; } +#define foreach_vmbus_pkt(pkt, channel) \ + for (pkt = hv_pkt_iter_first(channel); pkt; \ + pkt = hv_pkt_iter_next(channel, pkt)) #endif /* _HYPERV_H */ diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index 71be5b330d21..f0d79bd054ca 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -70,6 +70,7 @@ struct ipv6_devconf { #endif __u32 enhanced_dad; __u32 addr_gen_mode; + __s32 disable_policy; struct ctl_table_header *sysctl_header; }; diff --git a/include/linux/irqchip/arm-gic-v3.h b/include/linux/irqchip/arm-gic-v3.h index 672cfef72fc8..97cbca19430d 100644 --- a/include/linux/irqchip/arm-gic-v3.h +++ b/include/linux/irqchip/arm-gic-v3.h @@ -373,6 +373,8 @@ #define ICC_IGRPEN0_EL1_MASK (1 << ICC_IGRPEN0_EL1_SHIFT) #define ICC_IGRPEN1_EL1_SHIFT 0 #define ICC_IGRPEN1_EL1_MASK (1 << ICC_IGRPEN1_EL1_SHIFT) +#define ICC_SRE_EL1_DIB (1U << 2) +#define ICC_SRE_EL1_DFB (1U << 1) #define ICC_SRE_EL1_SRE (1U << 0) /* diff --git a/include/linux/irqdomain.h b/include/linux/irqdomain.h index 188eced6813e..9f3616085423 100644 --- a/include/linux/irqdomain.h +++ b/include/linux/irqdomain.h @@ -524,6 +524,10 @@ static inline struct irq_domain *irq_find_matching_fwnode( { return NULL; } +static inline bool irq_domain_check_msi_remap(void) +{ + return false; +} #endif /* !CONFIG_IRQ_DOMAIN */ #endif /* _LINUX_IRQDOMAIN_H */ diff --git a/include/linux/jump_label.h b/include/linux/jump_label.h index 8e06d758ee48..2afd74b9d844 100644 --- a/include/linux/jump_label.h +++ b/include/linux/jump_label.h @@ -90,6 +90,13 @@ extern bool static_key_initialized; struct static_key { atomic_t enabled; /* + * Note: + * To make anonymous unions work with old compilers, the static + * initialization of them requires brackets. This creates a dependency + * on the order of the struct with the initializers. If any fields + * are added, STATIC_KEY_INIT_TRUE and STATIC_KEY_INIT_FALSE may need + * to be modified. + * * bit 0 => 1 if key is initially true * 0 if initially false * bit 1 => 1 if points to struct static_key_mod @@ -166,10 +173,10 @@ extern void static_key_disable(struct static_key *key); */ #define STATIC_KEY_INIT_TRUE \ { .enabled = { 1 }, \ - .entries = (void *)JUMP_TYPE_TRUE } + { .entries = (void *)JUMP_TYPE_TRUE } } #define STATIC_KEY_INIT_FALSE \ { .enabled = { 0 }, \ - .entries = (void *)JUMP_TYPE_FALSE } + { .entries = (void *)JUMP_TYPE_FALSE } } #else /* !HAVE_JUMP_LABEL */ diff --git a/include/linux/kasan.h b/include/linux/kasan.h index ceb3fe78a0d3..1c823bef4c15 100644 --- a/include/linux/kasan.h +++ b/include/linux/kasan.h @@ -18,6 +18,7 @@ extern unsigned char kasan_zero_page[PAGE_SIZE]; extern pte_t kasan_zero_pte[PTRS_PER_PTE]; extern pmd_t kasan_zero_pmd[PTRS_PER_PMD]; extern pud_t kasan_zero_pud[PTRS_PER_PUD]; +extern p4d_t kasan_zero_p4d[PTRS_PER_P4D]; void kasan_populate_zero_shadow(const void *shadow_start, const void *shadow_end); diff --git a/include/linux/list_nulls.h b/include/linux/list_nulls.h index b01fe1009084..87ff4f58a2f0 100644 --- a/include/linux/list_nulls.h +++ b/include/linux/list_nulls.h @@ -29,6 +29,11 @@ struct hlist_nulls_node { ((ptr)->first = (struct hlist_nulls_node *) NULLS_MARKER(nulls)) #define hlist_nulls_entry(ptr, type, member) container_of(ptr,type,member) + +#define hlist_nulls_entry_safe(ptr, type, member) \ + ({ typeof(ptr) ____ptr = (ptr); \ + !is_a_nulls(____ptr) ? hlist_nulls_entry(____ptr, type, member) : NULL; \ + }) /** * ptr_is_a_nulls - Test if a ptr is a nulls * @ptr: ptr to be tested diff --git a/include/linux/mm.h b/include/linux/mm.h index 0d65dd72c0f4..5f01c88f0800 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1560,14 +1560,24 @@ static inline pte_t *get_locked_pte(struct mm_struct *mm, unsigned long addr, return ptep; } +#ifdef __PAGETABLE_P4D_FOLDED +static inline int __p4d_alloc(struct mm_struct *mm, pgd_t *pgd, + unsigned long address) +{ + return 0; +} +#else +int __p4d_alloc(struct mm_struct *mm, pgd_t *pgd, unsigned long address); +#endif + #ifdef __PAGETABLE_PUD_FOLDED -static inline int __pud_alloc(struct mm_struct *mm, pgd_t *pgd, +static inline int __pud_alloc(struct mm_struct *mm, p4d_t *p4d, unsigned long address) { return 0; } #else -int __pud_alloc(struct mm_struct *mm, pgd_t *pgd, unsigned long address); +int __pud_alloc(struct mm_struct *mm, p4d_t *p4d, unsigned long address); #endif #if defined(__PAGETABLE_PMD_FOLDED) || !defined(CONFIG_MMU) @@ -1619,11 +1629,22 @@ int __pte_alloc_kernel(pmd_t *pmd, unsigned long address); * Remove it when 4level-fixup.h has been removed. */ #if defined(CONFIG_MMU) && !defined(__ARCH_HAS_4LEVEL_HACK) -static inline pud_t *pud_alloc(struct mm_struct *mm, pgd_t *pgd, unsigned long address) + +#ifndef __ARCH_HAS_5LEVEL_HACK +static inline p4d_t *p4d_alloc(struct mm_struct *mm, pgd_t *pgd, + unsigned long address) +{ + return (unlikely(pgd_none(*pgd)) && __p4d_alloc(mm, pgd, address)) ? + NULL : p4d_offset(pgd, address); +} + +static inline pud_t *pud_alloc(struct mm_struct *mm, p4d_t *p4d, + unsigned long address) { - return (unlikely(pgd_none(*pgd)) && __pud_alloc(mm, pgd, address))? - NULL: pud_offset(pgd, address); + return (unlikely(p4d_none(*p4d)) && __pud_alloc(mm, p4d, address)) ? + NULL : pud_offset(p4d, address); } +#endif /* !__ARCH_HAS_5LEVEL_HACK */ static inline pmd_t *pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long address) { @@ -2385,7 +2406,8 @@ void sparse_mem_maps_populate_node(struct page **map_map, struct page *sparse_mem_map_populate(unsigned long pnum, int nid); pgd_t *vmemmap_pgd_populate(unsigned long addr, int node); -pud_t *vmemmap_pud_populate(pgd_t *pgd, unsigned long addr, int node); +p4d_t *vmemmap_p4d_populate(pgd_t *pgd, unsigned long addr, int node); +pud_t *vmemmap_pud_populate(p4d_t *p4d, unsigned long addr, int node); pmd_t *vmemmap_pmd_populate(pud_t *pud, unsigned long addr, int node); pte_t *vmemmap_pte_populate(pmd_t *pmd, unsigned long addr, int node); void *vmemmap_alloc_block(unsigned long size, int node); diff --git a/include/linux/net.h b/include/linux/net.h index cd0c8bd0a1de..0620f5e18c96 100644 --- a/include/linux/net.h +++ b/include/linux/net.h @@ -146,7 +146,7 @@ struct proto_ops { int (*socketpair)(struct socket *sock1, struct socket *sock2); int (*accept) (struct socket *sock, - struct socket *newsock, int flags); + struct socket *newsock, int flags, bool kern); int (*getname) (struct socket *sock, struct sockaddr *addr, int *sockaddr_len, int peer); diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 97456b2539e4..b7365b587818 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -786,11 +786,11 @@ struct tc_cls_u32_offload; struct tc_to_netdev { unsigned int type; union { - u8 tc; struct tc_cls_u32_offload *cls_u32; struct tc_cls_flower_offload *cls_flower; struct tc_cls_matchall_offload *cls_mall; struct tc_cls_bpf_offload *cls_bpf; + struct tc_mqprio_qopt *mqprio; }; bool egress_dev; }; diff --git a/include/linux/phy.h b/include/linux/phy.h index 772476028a65..43a774873aa9 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -837,6 +837,10 @@ int genphy_read_status(struct phy_device *phydev); int genphy_suspend(struct phy_device *phydev); int genphy_resume(struct phy_device *phydev); int genphy_soft_reset(struct phy_device *phydev); +static inline int genphy_no_soft_reset(struct phy_device *phydev) +{ + return 0; +} void phy_driver_unregister(struct phy_driver *drv); void phy_drivers_unregister(struct phy_driver *drv, int n); int phy_driver_register(struct phy_driver *new_driver, struct module *owner); diff --git a/include/linux/purgatory.h b/include/linux/purgatory.h new file mode 100644 index 000000000000..d60d4e278609 --- /dev/null +++ b/include/linux/purgatory.h @@ -0,0 +1,23 @@ +#ifndef _LINUX_PURGATORY_H +#define _LINUX_PURGATORY_H + +#include <linux/types.h> +#include <crypto/sha.h> +#include <uapi/linux/kexec.h> + +struct kexec_sha_region { + unsigned long start; + unsigned long len; +}; + +/* + * These forward declarations serve two purposes: + * + * 1) Make sparse happy when checking arch/purgatory + * 2) Document that these are required to be global so the symbol + * lookup in kexec works + */ +extern struct kexec_sha_region purgatory_sha_regions[KEXEC_SEGMENT_MAX]; +extern u8 purgatory_sha256_digest[SHA256_DIGEST_SIZE]; + +#endif diff --git a/include/linux/qed/common_hsi.h b/include/linux/qed/common_hsi.h index 52966b9bfde3..fbab6e0514f0 100644 --- a/include/linux/qed/common_hsi.h +++ b/include/linux/qed/common_hsi.h @@ -100,8 +100,8 @@ #define MAX_NUM_LL2_TX_STATS_COUNTERS 32 #define FW_MAJOR_VERSION 8 -#define FW_MINOR_VERSION 10 -#define FW_REVISION_VERSION 10 +#define FW_MINOR_VERSION 15 +#define FW_REVISION_VERSION 3 #define FW_ENGINEERING_VERSION 0 /***********************/ @@ -187,6 +187,9 @@ /* DEMS */ #define DQ_DEMS_LEGACY 0 +#define DQ_DEMS_TOE_MORE_TO_SEND 3 +#define DQ_DEMS_TOE_LOCAL_ADV_WND 4 +#define DQ_DEMS_ROCE_CQ_CONS 7 /* XCM agg val selection */ #define DQ_XCM_AGG_VAL_SEL_WORD2 0 @@ -214,6 +217,9 @@ #define DQ_XCM_ISCSI_MORE_TO_SEND_SEQ_CMD DQ_XCM_AGG_VAL_SEL_REG3 #define DQ_XCM_ISCSI_EXP_STAT_SN_CMD DQ_XCM_AGG_VAL_SEL_REG6 #define DQ_XCM_ROCE_SQ_PROD_CMD DQ_XCM_AGG_VAL_SEL_WORD4 +#define DQ_XCM_TOE_TX_BD_PROD_CMD DQ_XCM_AGG_VAL_SEL_WORD4 +#define DQ_XCM_TOE_MORE_TO_SEND_SEQ_CMD DQ_XCM_AGG_VAL_SEL_REG3 +#define DQ_XCM_TOE_LOCAL_ADV_WND_SEQ_CMD DQ_XCM_AGG_VAL_SEL_REG4 /* UCM agg val selection (HW) */ #define DQ_UCM_AGG_VAL_SEL_WORD0 0 @@ -269,6 +275,8 @@ #define DQ_XCM_ISCSI_DQ_FLUSH_CMD BIT(DQ_XCM_AGG_FLG_SHIFT_CF19) #define DQ_XCM_ISCSI_SLOW_PATH_CMD BIT(DQ_XCM_AGG_FLG_SHIFT_CF22) #define DQ_XCM_ISCSI_PROC_ONLY_CLEANUP_CMD BIT(DQ_XCM_AGG_FLG_SHIFT_CF23) +#define DQ_XCM_TOE_DQ_FLUSH_CMD BIT(DQ_XCM_AGG_FLG_SHIFT_CF19) +#define DQ_XCM_TOE_SLOW_PATH_CMD BIT(DQ_XCM_AGG_FLG_SHIFT_CF22) /* UCM agg counter flag selection (HW) */ #define DQ_UCM_AGG_FLG_SHIFT_CF0 0 @@ -285,6 +293,9 @@ #define DQ_UCM_ETH_PMD_RX_ARM_CMD BIT(DQ_UCM_AGG_FLG_SHIFT_CF5) #define DQ_UCM_ROCE_CQ_ARM_SE_CF_CMD BIT(DQ_UCM_AGG_FLG_SHIFT_CF4) #define DQ_UCM_ROCE_CQ_ARM_CF_CMD BIT(DQ_UCM_AGG_FLG_SHIFT_CF5) +#define DQ_UCM_TOE_TIMER_STOP_ALL_CMD BIT(DQ_UCM_AGG_FLG_SHIFT_CF3) +#define DQ_UCM_TOE_SLOW_PATH_CF_CMD BIT(DQ_UCM_AGG_FLG_SHIFT_CF4) +#define DQ_UCM_TOE_DQ_CF_CMD BIT(DQ_UCM_AGG_FLG_SHIFT_CF5) /* TCM agg counter flag selection (HW) */ #define DQ_TCM_AGG_FLG_SHIFT_CF0 0 @@ -301,6 +312,9 @@ #define DQ_TCM_FCOE_TIMER_STOP_ALL_CMD BIT(DQ_TCM_AGG_FLG_SHIFT_CF3) #define DQ_TCM_ISCSI_FLUSH_Q0_CMD BIT(DQ_TCM_AGG_FLG_SHIFT_CF1) #define DQ_TCM_ISCSI_TIMER_STOP_ALL_CMD BIT(DQ_TCM_AGG_FLG_SHIFT_CF3) +#define DQ_TCM_TOE_FLUSH_Q0_CMD BIT(DQ_TCM_AGG_FLG_SHIFT_CF1) +#define DQ_TCM_TOE_TIMER_STOP_ALL_CMD BIT(DQ_TCM_AGG_FLG_SHIFT_CF3) +#define DQ_TCM_IWARP_POST_RQ_CF_CMD BIT(DQ_TCM_AGG_FLG_SHIFT_CF1) /* PWM address mapping */ #define DQ_PWM_OFFSET_DPM_BASE 0x0 @@ -689,6 +703,16 @@ struct iscsi_eqe_data { #define ISCSI_EQE_DATA_RESERVED0_SHIFT 7 }; +struct rdma_eqe_destroy_qp { + __le32 cid; + u8 reserved[4]; +}; + +union rdma_eqe_data { + struct regpair async_handle; + struct rdma_eqe_destroy_qp rdma_destroy_qp_data; +}; + struct malicious_vf_eqe_data { u8 vf_id; u8 err_id; @@ -705,9 +729,9 @@ union event_ring_data { u8 bytes[8]; struct vf_pf_channel_eqe_data vf_pf_channel; struct iscsi_eqe_data iscsi_info; + union rdma_eqe_data rdma_data; struct malicious_vf_eqe_data malicious_vf; struct initial_cleanup_eqe_data vf_init_cleanup; - struct regpair roce_handle; }; /* Event Ring Entry */ diff --git a/include/linux/qed/eth_common.h b/include/linux/qed/eth_common.h index 4b402fb0eaad..34d93eb5bfba 100644 --- a/include/linux/qed/eth_common.h +++ b/include/linux/qed/eth_common.h @@ -49,6 +49,9 @@ #define ETH_RX_CQE_PAGE_SIZE_BYTES 4096 #define ETH_RX_NUM_NEXT_PAGE_BDS 2 +#define ETH_MAX_TUNN_LSO_INNER_IPV4_OFFSET 253 +#define ETH_MAX_TUNN_LSO_INNER_IPV6_OFFSET 251 + #define ETH_TX_MIN_BDS_PER_NON_LSO_PKT 1 #define ETH_TX_MAX_BDS_PER_NON_LSO_PACKET 18 #define ETH_TX_MAX_BDS_PER_LSO_PACKET 255 diff --git a/include/linux/qed/fcoe_common.h b/include/linux/qed/fcoe_common.h index 2e417a45c5f7..947a635d04bb 100644 --- a/include/linux/qed/fcoe_common.h +++ b/include/linux/qed/fcoe_common.h @@ -109,13 +109,6 @@ struct fcoe_conn_terminate_ramrod_data { struct regpair terminate_params_addr; }; -struct fcoe_fast_sgl_ctx { - struct regpair sgl_start_addr; - __le32 sgl_byte_offset; - __le16 task_reuse_cnt; - __le16 init_offset_in_first_sge; -}; - struct fcoe_slow_sgl_ctx { struct regpair base_sgl_addr; __le16 curr_sge_off; @@ -124,23 +117,16 @@ struct fcoe_slow_sgl_ctx { __le16 reserved; }; -struct fcoe_sge { - struct regpair sge_addr; - __le16 size; - __le16 reserved0; - u8 reserved1[3]; - u8 is_valid_sge; -}; - -union fcoe_data_desc_ctx { - struct fcoe_fast_sgl_ctx fast; - struct fcoe_slow_sgl_ctx slow; - struct fcoe_sge single_sge; -}; - union fcoe_dix_desc_ctx { struct fcoe_slow_sgl_ctx dix_sgl; - struct fcoe_sge cached_dix_sge; + struct scsi_sge cached_dix_sge; +}; + +struct fcoe_fast_sgl_ctx { + struct regpair sgl_start_addr; + __le32 sgl_byte_offset; + __le16 task_reuse_cnt; + __le16 init_offset_in_first_sge; }; struct fcoe_fcp_cmd_payload { @@ -172,57 +158,6 @@ enum fcoe_mode_type { MAX_FCOE_MODE_TYPE }; -struct fcoe_mstorm_fcoe_task_st_ctx_fp { - __le16 flags; -#define FCOE_MSTORM_FCOE_TASK_ST_CTX_FP_RSRV0_MASK 0x7FFF -#define FCOE_MSTORM_FCOE_TASK_ST_CTX_FP_RSRV0_SHIFT 0 -#define FCOE_MSTORM_FCOE_TASK_ST_CTX_FP_MP_INCLUDE_FC_HEADER_MASK 0x1 -#define FCOE_MSTORM_FCOE_TASK_ST_CTX_FP_MP_INCLUDE_FC_HEADER_SHIFT 15 - __le16 difDataResidue; - __le16 parent_id; - __le16 single_sge_saved_offset; - __le32 data_2_trns_rem; - __le32 offset_in_io; - union fcoe_dix_desc_ctx dix_desc; - union fcoe_data_desc_ctx data_desc; -}; - -struct fcoe_mstorm_fcoe_task_st_ctx_non_fp { - __le16 flags; -#define FCOE_MSTORM_FCOE_TASK_ST_CTX_NON_FP_HOST_INTERFACE_MASK 0x3 -#define FCOE_MSTORM_FCOE_TASK_ST_CTX_NON_FP_HOST_INTERFACE_SHIFT 0 -#define FCOE_MSTORM_FCOE_TASK_ST_CTX_NON_FP_DIF_TO_PEER_MASK 0x1 -#define FCOE_MSTORM_FCOE_TASK_ST_CTX_NON_FP_DIF_TO_PEER_SHIFT 2 -#define FCOE_MSTORM_FCOE_TASK_ST_CTX_NON_FP_VALIDATE_DIX_APP_TAG_MASK 0x1 -#define FCOE_MSTORM_FCOE_TASK_ST_CTX_NON_FP_VALIDATE_DIX_APP_TAG_SHIFT 3 -#define FCOE_MSTORM_FCOE_TASK_ST_CTX_NON_FP_INTERVAL_SIZE_LOG_MASK 0xF -#define FCOE_MSTORM_FCOE_TASK_ST_CTX_NON_FP_INTERVAL_SIZE_LOG_SHIFT 4 -#define FCOE_MSTORM_FCOE_TASK_ST_CTX_NON_FP_DIX_BLOCK_SIZE_MASK 0x3 -#define FCOE_MSTORM_FCOE_TASK_ST_CTX_NON_FP_DIX_BLOCK_SIZE_SHIFT 8 -#define FCOE_MSTORM_FCOE_TASK_ST_CTX_NON_FP_RESERVED_MASK 0x1 -#define FCOE_MSTORM_FCOE_TASK_ST_CTX_NON_FP_RESERVED_SHIFT 10 -#define FCOE_MSTORM_FCOE_TASK_ST_CTX_NON_FP_HAS_FIRST_PACKET_ARRIVED_MASK 0x1 -#define FCOE_MSTORM_FCOE_TASK_ST_CTX_NON_FP_HAS_FIRST_PACKET_ARRIVED_SHIFT 11 -#define FCOE_MSTORM_FCOE_TASK_ST_CTX_NON_FP_VALIDATE_DIX_REF_TAG_MASK 0x1 -#define FCOE_MSTORM_FCOE_TASK_ST_CTX_NON_FP_VALIDATE_DIX_REF_TAG_SHIFT 12 -#define FCOE_MSTORM_FCOE_TASK_ST_CTX_NON_FP_DIX_CACHED_SGE_FLG_MASK 0x1 -#define FCOE_MSTORM_FCOE_TASK_ST_CTX_NON_FP_DIX_CACHED_SGE_FLG_SHIFT 13 -#define FCOE_MSTORM_FCOE_TASK_ST_CTX_NON_FP_OFFSET_IN_IO_VALID_MASK 0x1 -#define FCOE_MSTORM_FCOE_TASK_ST_CTX_NON_FP_OFFSET_IN_IO_VALID_SHIFT 14 -#define FCOE_MSTORM_FCOE_TASK_ST_CTX_NON_FP_DIF_SUPPORTED_MASK 0x1 -#define FCOE_MSTORM_FCOE_TASK_ST_CTX_NON_FP_DIF_SUPPORTED_SHIFT 15 - u8 tx_rx_sgl_mode; -#define FCOE_MSTORM_FCOE_TASK_ST_CTX_NON_FP_TX_SGL_MODE_MASK 0x7 -#define FCOE_MSTORM_FCOE_TASK_ST_CTX_NON_FP_TX_SGL_MODE_SHIFT 0 -#define FCOE_MSTORM_FCOE_TASK_ST_CTX_NON_FP_RX_SGL_MODE_MASK 0x7 -#define FCOE_MSTORM_FCOE_TASK_ST_CTX_NON_FP_RX_SGL_MODE_SHIFT 3 -#define FCOE_MSTORM_FCOE_TASK_ST_CTX_NON_FP_RSRV1_MASK 0x3 -#define FCOE_MSTORM_FCOE_TASK_ST_CTX_NON_FP_RSRV1_SHIFT 6 - u8 rsrv2; - __le32 num_prm_zero_read; - struct regpair rsp_buf_addr; -}; - struct fcoe_rx_stat { struct regpair fcoe_rx_byte_cnt; struct regpair fcoe_rx_data_pkt_cnt; @@ -236,16 +171,6 @@ struct fcoe_rx_stat { __le32 rsrv; }; -enum fcoe_sgl_mode { - FCOE_SLOW_SGL, - FCOE_SINGLE_FAST_SGE, - FCOE_2_FAST_SGE, - FCOE_3_FAST_SGE, - FCOE_4_FAST_SGE, - FCOE_MUL_FAST_SGES, - MAX_FCOE_SGL_MODE -}; - struct fcoe_stat_ramrod_data { struct regpair stat_params_addr; }; @@ -328,22 +253,24 @@ union fcoe_tx_info_union_ctx { struct ystorm_fcoe_task_st_ctx { u8 task_type; u8 sgl_mode; -#define YSTORM_FCOE_TASK_ST_CTX_TX_SGL_MODE_MASK 0x7 +#define YSTORM_FCOE_TASK_ST_CTX_TX_SGL_MODE_MASK 0x1 #define YSTORM_FCOE_TASK_ST_CTX_TX_SGL_MODE_SHIFT 0 -#define YSTORM_FCOE_TASK_ST_CTX_RSRV_MASK 0x1F -#define YSTORM_FCOE_TASK_ST_CTX_RSRV_SHIFT 3 +#define YSTORM_FCOE_TASK_ST_CTX_RSRV_MASK 0x7F +#define YSTORM_FCOE_TASK_ST_CTX_RSRV_SHIFT 1 u8 cached_dix_sge; u8 expect_first_xfer; __le32 num_pbf_zero_write; union protection_info_union_ctx protection_info_union; __le32 data_2_trns_rem; + struct scsi_sgl_params sgl_params; + u8 reserved1[12]; union fcoe_tx_info_union_ctx tx_info_union; union fcoe_dix_desc_ctx dix_desc; - union fcoe_data_desc_ctx data_desc; + struct scsi_cached_sges data_desc; __le16 ox_id; __le16 rx_id; __le32 task_rety_identifier; - __le32 reserved1[2]; + u8 reserved2[8]; }; struct ystorm_fcoe_task_ag_ctx { @@ -484,22 +411,22 @@ struct tstorm_fcoe_task_ag_ctx { struct fcoe_tstorm_fcoe_task_st_ctx_read_write { union fcoe_cleanup_addr_exp_ro_union cleanup_addr_exp_ro_union; __le16 flags; -#define FCOE_TSTORM_FCOE_TASK_ST_CTX_READ_WRITE_RX_SGL_MODE_MASK 0x7 +#define FCOE_TSTORM_FCOE_TASK_ST_CTX_READ_WRITE_RX_SGL_MODE_MASK 0x1 #define FCOE_TSTORM_FCOE_TASK_ST_CTX_READ_WRITE_RX_SGL_MODE_SHIFT 0 #define FCOE_TSTORM_FCOE_TASK_ST_CTX_READ_WRITE_EXP_FIRST_FRAME_MASK 0x1 -#define FCOE_TSTORM_FCOE_TASK_ST_CTX_READ_WRITE_EXP_FIRST_FRAME_SHIFT 3 +#define FCOE_TSTORM_FCOE_TASK_ST_CTX_READ_WRITE_EXP_FIRST_FRAME_SHIFT 1 #define FCOE_TSTORM_FCOE_TASK_ST_CTX_READ_WRITE_SEQ_ACTIVE_MASK 0x1 -#define FCOE_TSTORM_FCOE_TASK_ST_CTX_READ_WRITE_SEQ_ACTIVE_SHIFT 4 +#define FCOE_TSTORM_FCOE_TASK_ST_CTX_READ_WRITE_SEQ_ACTIVE_SHIFT 2 #define FCOE_TSTORM_FCOE_TASK_ST_CTX_READ_WRITE_SEQ_TIMEOUT_MASK 0x1 -#define FCOE_TSTORM_FCOE_TASK_ST_CTX_READ_WRITE_SEQ_TIMEOUT_SHIFT 5 +#define FCOE_TSTORM_FCOE_TASK_ST_CTX_READ_WRITE_SEQ_TIMEOUT_SHIFT 3 #define FCOE_TSTORM_FCOE_TASK_ST_CTX_READ_WRITE_SINGLE_PKT_IN_EX_MASK 0x1 -#define FCOE_TSTORM_FCOE_TASK_ST_CTX_READ_WRITE_SINGLE_PKT_IN_EX_SHIFT 6 +#define FCOE_TSTORM_FCOE_TASK_ST_CTX_READ_WRITE_SINGLE_PKT_IN_EX_SHIFT 4 #define FCOE_TSTORM_FCOE_TASK_ST_CTX_READ_WRITE_OOO_RX_SEQ_STAT_MASK 0x1 -#define FCOE_TSTORM_FCOE_TASK_ST_CTX_READ_WRITE_OOO_RX_SEQ_STAT_SHIFT 7 +#define FCOE_TSTORM_FCOE_TASK_ST_CTX_READ_WRITE_OOO_RX_SEQ_STAT_SHIFT 5 #define FCOE_TSTORM_FCOE_TASK_ST_CTX_READ_WRITE_CQ_ADD_ADV_MASK 0x3 -#define FCOE_TSTORM_FCOE_TASK_ST_CTX_READ_WRITE_CQ_ADD_ADV_SHIFT 8 -#define FCOE_TSTORM_FCOE_TASK_ST_CTX_READ_WRITE_RSRV1_MASK 0x3F -#define FCOE_TSTORM_FCOE_TASK_ST_CTX_READ_WRITE_RSRV1_SHIFT 10 +#define FCOE_TSTORM_FCOE_TASK_ST_CTX_READ_WRITE_CQ_ADD_ADV_SHIFT 6 +#define FCOE_TSTORM_FCOE_TASK_ST_CTX_READ_WRITE_RSRV1_MASK 0xFF +#define FCOE_TSTORM_FCOE_TASK_ST_CTX_READ_WRITE_RSRV1_SHIFT 8 __le16 seq_cnt; u8 seq_id; u8 ooo_rx_seq_id; @@ -582,8 +509,34 @@ struct mstorm_fcoe_task_ag_ctx { }; struct mstorm_fcoe_task_st_ctx { - struct fcoe_mstorm_fcoe_task_st_ctx_non_fp non_fp; - struct fcoe_mstorm_fcoe_task_st_ctx_fp fp; + struct regpair rsp_buf_addr; + __le32 rsrv[2]; + struct scsi_sgl_params sgl_params; + __le32 data_2_trns_rem; + __le32 data_buffer_offset; + __le16 parent_id; + __le16 flags; +#define MSTORM_FCOE_TASK_ST_CTX_INTERVAL_SIZE_LOG_MASK 0xF +#define MSTORM_FCOE_TASK_ST_CTX_INTERVAL_SIZE_LOG_SHIFT 0 +#define MSTORM_FCOE_TASK_ST_CTX_HOST_INTERFACE_MASK 0x3 +#define MSTORM_FCOE_TASK_ST_CTX_HOST_INTERFACE_SHIFT 4 +#define MSTORM_FCOE_TASK_ST_CTX_DIF_TO_PEER_MASK 0x1 +#define MSTORM_FCOE_TASK_ST_CTX_DIF_TO_PEER_SHIFT 6 +#define MSTORM_FCOE_TASK_ST_CTX_MP_INCLUDE_FC_HEADER_MASK 0x1 +#define MSTORM_FCOE_TASK_ST_CTX_MP_INCLUDE_FC_HEADER_SHIFT 7 +#define MSTORM_FCOE_TASK_ST_CTX_DIX_BLOCK_SIZE_MASK 0x3 +#define MSTORM_FCOE_TASK_ST_CTX_DIX_BLOCK_SIZE_SHIFT 8 +#define MSTORM_FCOE_TASK_ST_CTX_VALIDATE_DIX_REF_TAG_MASK 0x1 +#define MSTORM_FCOE_TASK_ST_CTX_VALIDATE_DIX_REF_TAG_SHIFT 10 +#define MSTORM_FCOE_TASK_ST_CTX_DIX_CACHED_SGE_FLG_MASK 0x1 +#define MSTORM_FCOE_TASK_ST_CTX_DIX_CACHED_SGE_FLG_SHIFT 11 +#define MSTORM_FCOE_TASK_ST_CTX_DIF_SUPPORTED_MASK 0x1 +#define MSTORM_FCOE_TASK_ST_CTX_DIF_SUPPORTED_SHIFT 12 +#define MSTORM_FCOE_TASK_ST_CTX_TX_SGL_MODE_MASK 0x1 +#define MSTORM_FCOE_TASK_ST_CTX_TX_SGL_MODE_SHIFT 13 +#define MSTORM_FCOE_TASK_ST_CTX_RESERVED_MASK 0x3 +#define MSTORM_FCOE_TASK_ST_CTX_RESERVED_SHIFT 14 + struct scsi_cached_sges data_desc; }; struct ustorm_fcoe_task_ag_ctx { @@ -646,6 +599,7 @@ struct ustorm_fcoe_task_ag_ctx { struct fcoe_task_context { struct ystorm_fcoe_task_st_ctx ystorm_st_context; + struct regpair ystorm_st_padding[2]; struct tdif_task_context tdif_context; struct ystorm_fcoe_task_ag_ctx ystorm_ag_context; struct tstorm_fcoe_task_ag_ctx tstorm_ag_context; @@ -668,20 +622,20 @@ struct fcoe_tx_stat { struct fcoe_wqe { __le16 task_id; __le16 flags; -#define FCOE_WQE_REQ_TYPE_MASK 0xF -#define FCOE_WQE_REQ_TYPE_SHIFT 0 -#define FCOE_WQE_SGL_MODE_MASK 0x7 -#define FCOE_WQE_SGL_MODE_SHIFT 4 -#define FCOE_WQE_CONTINUATION_MASK 0x1 -#define FCOE_WQE_CONTINUATION_SHIFT 7 -#define FCOE_WQE_INVALIDATE_PTU_MASK 0x1 -#define FCOE_WQE_INVALIDATE_PTU_SHIFT 8 -#define FCOE_WQE_SUPER_IO_MASK 0x1 -#define FCOE_WQE_SUPER_IO_SHIFT 9 -#define FCOE_WQE_SEND_AUTO_RSP_MASK 0x1 -#define FCOE_WQE_SEND_AUTO_RSP_SHIFT 10 -#define FCOE_WQE_RESERVED0_MASK 0x1F -#define FCOE_WQE_RESERVED0_SHIFT 11 +#define FCOE_WQE_REQ_TYPE_MASK 0xF +#define FCOE_WQE_REQ_TYPE_SHIFT 0 +#define FCOE_WQE_SGL_MODE_MASK 0x1 +#define FCOE_WQE_SGL_MODE_SHIFT 4 +#define FCOE_WQE_CONTINUATION_MASK 0x1 +#define FCOE_WQE_CONTINUATION_SHIFT 5 +#define FCOE_WQE_SEND_AUTO_RSP_MASK 0x1 +#define FCOE_WQE_SEND_AUTO_RSP_SHIFT 6 +#define FCOE_WQE_RESERVED_MASK 0x1 +#define FCOE_WQE_RESERVED_SHIFT 7 +#define FCOE_WQE_NUM_SGES_MASK 0xF +#define FCOE_WQE_NUM_SGES_SHIFT 8 +#define FCOE_WQE_RESERVED1_MASK 0xF +#define FCOE_WQE_RESERVED1_SHIFT 12 union fcoe_additional_info_union additional_info_union; }; diff --git a/include/linux/qed/iscsi_common.h b/include/linux/qed/iscsi_common.h index 4c5747babcf6..69949f8e354b 100644 --- a/include/linux/qed/iscsi_common.h +++ b/include/linux/qed/iscsi_common.h @@ -39,17 +39,9 @@ /* iSCSI HSI constants */ #define ISCSI_DEFAULT_MTU (1500) -/* Current iSCSI HSI version number composed of two fields (16 bit) */ -#define ISCSI_HSI_MAJOR_VERSION (0) -#define ISCSI_HSI_MINOR_VERSION (0) - /* KWQ (kernel work queue) layer codes */ #define ISCSI_SLOW_PATH_LAYER_CODE (6) -/* CQE completion status */ -#define ISCSI_EQE_COMPLETION_SUCCESS (0x0) -#define ISCSI_EQE_RST_CONN_RCVD (0x1) - /* iSCSI parameter defaults */ #define ISCSI_DEFAULT_HEADER_DIGEST (0) #define ISCSI_DEFAULT_DATA_DIGEST (0) @@ -68,6 +60,10 @@ #define ISCSI_MIN_VAL_MAX_OUTSTANDING_R2T (1) #define ISCSI_MAX_VAL_MAX_OUTSTANDING_R2T (0xff) +#define ISCSI_AHS_CNTL_SIZE 4 + +#define ISCSI_WQE_NUM_SGES_SLOWIO (0xf) + /* iSCSI reserved params */ #define ISCSI_ITT_ALL_ONES (0xffffffff) #define ISCSI_TTT_ALL_ONES (0xffffffff) @@ -173,19 +169,6 @@ struct iscsi_async_msg_hdr { __le32 reserved7; }; -struct iscsi_sge { - struct regpair sge_addr; - __le16 sge_len; - __le16 reserved0; - __le32 reserved1; -}; - -struct iscsi_cached_sge_ctx { - struct iscsi_sge sge; - struct regpair reserved; - __le32 dsgl_curr_offset[2]; -}; - struct iscsi_cmd_hdr { __le16 reserved1; u8 flags_attr; @@ -229,8 +212,13 @@ struct iscsi_common_hdr { #define ISCSI_COMMON_HDR_DATA_SEG_LEN_SHIFT 0 #define ISCSI_COMMON_HDR_TOTAL_AHS_LEN_MASK 0xFF #define ISCSI_COMMON_HDR_TOTAL_AHS_LEN_SHIFT 24 - __le32 lun_reserved[4]; - __le32 data[6]; + struct regpair lun_reserved; + __le32 itt; + __le32 ttt; + __le32 cmdstat_sn; + __le32 exp_statcmd_sn; + __le32 max_cmd_sn; + __le32 data[3]; }; struct iscsi_conn_offload_params { @@ -246,8 +234,10 @@ struct iscsi_conn_offload_params { #define ISCSI_CONN_OFFLOAD_PARAMS_TCP_ON_CHIP_1B_SHIFT 0 #define ISCSI_CONN_OFFLOAD_PARAMS_TARGET_MODE_MASK 0x1 #define ISCSI_CONN_OFFLOAD_PARAMS_TARGET_MODE_SHIFT 1 -#define ISCSI_CONN_OFFLOAD_PARAMS_RESERVED1_MASK 0x3F -#define ISCSI_CONN_OFFLOAD_PARAMS_RESERVED1_SHIFT 2 +#define ISCSI_CONN_OFFLOAD_PARAMS_RESTRICTED_MODE_MASK 0x1 +#define ISCSI_CONN_OFFLOAD_PARAMS_RESTRICTED_MODE_SHIFT 2 +#define ISCSI_CONN_OFFLOAD_PARAMS_RESERVED1_MASK 0x1F +#define ISCSI_CONN_OFFLOAD_PARAMS_RESERVED1_SHIFT 3 u8 pbl_page_size_log; u8 pbe_page_size_log; u8 default_cq; @@ -278,8 +268,12 @@ struct iscsi_conn_update_ramrod_params { #define ISCSI_CONN_UPDATE_RAMROD_PARAMS_INITIAL_R2T_SHIFT 2 #define ISCSI_CONN_UPDATE_RAMROD_PARAMS_IMMEDIATE_DATA_MASK 0x1 #define ISCSI_CONN_UPDATE_RAMROD_PARAMS_IMMEDIATE_DATA_SHIFT 3 -#define ISCSI_CONN_UPDATE_RAMROD_PARAMS_RESERVED1_MASK 0xF -#define ISCSI_CONN_UPDATE_RAMROD_PARAMS_RESERVED1_SHIFT 4 +#define ISCSI_CONN_UPDATE_RAMROD_PARAMS_DIF_BLOCK_SIZE_MASK 0x1 +#define ISCSI_CONN_UPDATE_RAMROD_PARAMS_DIF_BLOCK_SIZE_SHIFT 4 +#define ISCSI_CONN_UPDATE_RAMROD_PARAMS_DIF_ON_HOST_EN_MASK 0x1 +#define ISCSI_CONN_UPDATE_RAMROD_PARAMS_DIF_ON_HOST_EN_SHIFT 5 +#define ISCSI_CONN_UPDATE_RAMROD_PARAMS_RESERVED1_MASK 0x3 +#define ISCSI_CONN_UPDATE_RAMROD_PARAMS_RESERVED1_SHIFT 6 u8 reserved0[3]; __le32 max_seq_size; __le32 max_send_pdu_length; @@ -312,7 +306,7 @@ struct iscsi_ext_cdb_cmd_hdr { __le32 expected_transfer_length; __le32 cmd_sn; __le32 exp_stat_sn; - struct iscsi_sge cdb_sge; + struct scsi_sge cdb_sge; }; struct iscsi_login_req_hdr { @@ -519,8 +513,8 @@ struct iscsi_logout_response_hdr { __le32 exp_cmd_sn; __le32 max_cmd_sn; __le32 reserved4; - __le16 time2retain; - __le16 time2wait; + __le16 time_2_retain; + __le16 time_2_wait; __le32 reserved5[1]; }; @@ -602,7 +596,7 @@ struct iscsi_tmf_response_hdr { #define ISCSI_TMF_RESPONSE_HDR_TOTAL_AHS_LEN_SHIFT 24 struct regpair reserved0; __le32 itt; - __le32 rtt; + __le32 reserved1; __le32 stat_sn; __le32 exp_cmd_sn; __le32 max_cmd_sn; @@ -641,7 +635,7 @@ struct iscsi_reject_hdr { #define ISCSI_REJECT_HDR_TOTAL_AHS_LEN_MASK 0xFF #define ISCSI_REJECT_HDR_TOTAL_AHS_LEN_SHIFT 24 struct regpair reserved0; - __le32 reserved1; + __le32 all_ones; __le32 reserved2; __le32 stat_sn; __le32 exp_cmd_sn; @@ -688,7 +682,9 @@ struct iscsi_cqe_solicited { __le16 itid; u8 task_type; u8 fw_dbg_field; - __le32 reserved1[2]; + u8 caused_conn_err; + u8 reserved0[3]; + __le32 reserved1[1]; union iscsi_task_hdr iscsi_hdr; }; @@ -727,35 +723,6 @@ enum iscsi_cqe_unsolicited_type { MAX_ISCSI_CQE_UNSOLICITED_TYPE }; -struct iscsi_virt_sgl_ctx { - struct regpair sgl_base; - struct regpair dsgl_base; - __le32 sgl_initial_offset; - __le32 dsgl_initial_offset; - __le32 dsgl_curr_offset[2]; -}; - -struct iscsi_sgl_var_params { - u8 sgl_ptr; - u8 dsgl_ptr; - __le16 sge_offset; - __le16 dsge_offset; -}; - -struct iscsi_phys_sgl_ctx { - struct regpair sgl_base; - struct regpair dsgl_base; - u8 sgl_size; - u8 dsgl_size; - __le16 reserved; - struct iscsi_sgl_var_params var_params[2]; -}; - -union iscsi_data_desc_ctx { - struct iscsi_virt_sgl_ctx virt_sgl; - struct iscsi_phys_sgl_ctx phys_sgl; - struct iscsi_cached_sge_ctx cached_sge; -}; struct iscsi_debug_modes { u8 flags; @@ -771,8 +738,10 @@ struct iscsi_debug_modes { #define ISCSI_DEBUG_MODES_ASSERT_IF_RECV_REJECT_OR_ASYNC_SHIFT 4 #define ISCSI_DEBUG_MODES_ASSERT_IF_RECV_NOP_MASK 0x1 #define ISCSI_DEBUG_MODES_ASSERT_IF_RECV_NOP_SHIFT 5 -#define ISCSI_DEBUG_MODES_RESERVED0_MASK 0x3 -#define ISCSI_DEBUG_MODES_RESERVED0_SHIFT 6 +#define ISCSI_DEBUG_MODES_ASSERT_IF_DATA_DIGEST_ERROR_MASK 0x1 +#define ISCSI_DEBUG_MODES_ASSERT_IF_DATA_DIGEST_ERROR_SHIFT 6 +#define ISCSI_DEBUG_MODES_ASSERT_IF_DIF_ERROR_MASK 0x1 +#define ISCSI_DEBUG_MODES_ASSERT_IF_DIF_ERROR_SHIFT 7 }; struct iscsi_dif_flags { @@ -806,7 +775,6 @@ enum iscsi_eqe_opcode { ISCSI_EVENT_TYPE_ASYN_FIN_WAIT2, ISCSI_EVENT_TYPE_ISCSI_CONN_ERROR, ISCSI_EVENT_TYPE_TCP_CONN_ERROR, - ISCSI_EVENT_TYPE_ASYN_DELETE_OOO_ISLES, MAX_ISCSI_EQE_OPCODE }; @@ -856,31 +824,11 @@ enum iscsi_error_types { ISCSI_CONN_ERROR_PROTOCOL_ERR_DIF_TX, ISCSI_CONN_ERROR_SENSE_DATA_LENGTH, ISCSI_CONN_ERROR_DATA_PLACEMENT_ERROR, + ISCSI_CONN_ERROR_INVALID_ITT, ISCSI_ERROR_UNKNOWN, MAX_ISCSI_ERROR_TYPES }; -struct iscsi_mflags { - u8 mflags; -#define ISCSI_MFLAGS_SLOW_IO_MASK 0x1 -#define ISCSI_MFLAGS_SLOW_IO_SHIFT 0 -#define ISCSI_MFLAGS_SINGLE_SGE_MASK 0x1 -#define ISCSI_MFLAGS_SINGLE_SGE_SHIFT 1 -#define ISCSI_MFLAGS_RESERVED_MASK 0x3F -#define ISCSI_MFLAGS_RESERVED_SHIFT 2 -}; - -struct iscsi_sgl { - struct regpair sgl_addr; - __le16 updated_sge_size; - __le16 updated_sge_offset; - __le32 byte_offset; -}; - -union iscsi_mstorm_sgl { - struct iscsi_sgl sgl_struct; - struct iscsi_sge single_sge; -}; enum iscsi_ramrod_cmd_id { ISCSI_RAMROD_CMD_ID_UNUSED = 0, @@ -896,10 +844,10 @@ enum iscsi_ramrod_cmd_id { struct iscsi_reg1 { __le32 reg1_map; -#define ISCSI_REG1_NUM_FAST_SGES_MASK 0x7 -#define ISCSI_REG1_NUM_FAST_SGES_SHIFT 0 -#define ISCSI_REG1_RESERVED1_MASK 0x1FFFFFFF -#define ISCSI_REG1_RESERVED1_SHIFT 3 +#define ISCSI_REG1_NUM_SGES_MASK 0xF +#define ISCSI_REG1_NUM_SGES_SHIFT 0 +#define ISCSI_REG1_RESERVED1_MASK 0xFFFFFFF +#define ISCSI_REG1_RESERVED1_SHIFT 4 }; union iscsi_seq_num { @@ -967,22 +915,33 @@ struct iscsi_spe_func_init { }; struct ystorm_iscsi_task_state { - union iscsi_data_desc_ctx sgl_ctx_union; - __le32 buffer_offset[2]; - __le16 bytes_nxt_dif; - __le16 rxmit_bytes_nxt_dif; - union iscsi_seq_num seq_num_union; - u8 dif_bytes_leftover; - u8 rxmit_dif_bytes_leftover; - __le16 reuse_count; - struct iscsi_dif_flags dif_flags; - u8 local_comp; + struct scsi_cached_sges data_desc; + struct scsi_sgl_params sgl_params; __le32 exp_r2t_sn; - __le32 sgl_offset[2]; + __le32 buffer_offset; + union iscsi_seq_num seq_num; + struct iscsi_dif_flags dif_flags; + u8 flags; +#define YSTORM_ISCSI_TASK_STATE_LOCAL_COMP_MASK 0x1 +#define YSTORM_ISCSI_TASK_STATE_LOCAL_COMP_SHIFT 0 +#define YSTORM_ISCSI_TASK_STATE_SLOW_IO_MASK 0x1 +#define YSTORM_ISCSI_TASK_STATE_SLOW_IO_SHIFT 1 +#define YSTORM_ISCSI_TASK_STATE_RESERVED0_MASK 0x3F +#define YSTORM_ISCSI_TASK_STATE_RESERVED0_SHIFT 2 +}; + +struct ystorm_iscsi_task_rxmit_opt { + __le32 fast_rxmit_sge_offset; + __le32 scan_start_buffer_offset; + __le32 fast_rxmit_buffer_offset; + u8 scan_start_sgl_index; + u8 fast_rxmit_sgl_index; + __le16 reserved; }; struct ystorm_iscsi_task_st_ctx { struct ystorm_iscsi_task_state state; + struct ystorm_iscsi_task_rxmit_opt rxmit_opt; union iscsi_task_hdr pdu_hdr; }; @@ -1152,25 +1111,16 @@ struct ustorm_iscsi_task_ag_ctx { }; struct mstorm_iscsi_task_st_ctx { - union iscsi_mstorm_sgl sgl_union; - struct iscsi_dif_flags dif_flags; - struct iscsi_mflags flags; - u8 sgl_size; - u8 host_sge_index; - __le16 dix_cur_sge_offset; - __le16 dix_cur_sge_size; - __le32 data_offset_rtid; - u8 dif_offset; - u8 dix_sgl_size; - u8 dix_sge_index; + struct scsi_cached_sges data_desc; + struct scsi_sgl_params sgl_params; + __le32 rem_task_size; + __le32 data_buffer_offset; u8 task_type; + struct iscsi_dif_flags dif_flags; + u8 reserved0[2]; struct regpair sense_db; - struct regpair dix_sgl_cur_sge; - __le32 rem_task_size; - __le16 reuse_count; - __le16 dif_data_residue; - u8 reserved0[4]; - __le32 reserved1[1]; + __le32 expected_itt; + __le32 reserved1; }; struct ustorm_iscsi_task_st_ctx { @@ -1184,7 +1134,7 @@ struct ustorm_iscsi_task_st_ctx { #define USTORM_ISCSI_TASK_ST_CTX_AHS_EXIST_SHIFT 0 #define USTORM_ISCSI_TASK_ST_CTX_RESERVED1_MASK 0x7F #define USTORM_ISCSI_TASK_ST_CTX_RESERVED1_SHIFT 1 - u8 reserved2; + struct iscsi_dif_flags dif_flags; __le16 reserved3; __le32 reserved4; __le32 reserved5; @@ -1207,10 +1157,10 @@ struct ustorm_iscsi_task_st_ctx { #define USTORM_ISCSI_TASK_ST_CTX_LOCAL_COMP_SHIFT 2 #define USTORM_ISCSI_TASK_ST_CTX_Q0_R2TQE_WRITE_MASK 0x1 #define USTORM_ISCSI_TASK_ST_CTX_Q0_R2TQE_WRITE_SHIFT 3 -#define USTORM_ISCSI_TASK_ST_CTX_TOTALDATAACKED_DONE_MASK 0x1 -#define USTORM_ISCSI_TASK_ST_CTX_TOTALDATAACKED_DONE_SHIFT 4 -#define USTORM_ISCSI_TASK_ST_CTX_HQSCANNED_DONE_MASK 0x1 -#define USTORM_ISCSI_TASK_ST_CTX_HQSCANNED_DONE_SHIFT 5 +#define USTORM_ISCSI_TASK_ST_CTX_TOTAL_DATA_ACKED_DONE_MASK 0x1 +#define USTORM_ISCSI_TASK_ST_CTX_TOTAL_DATA_ACKED_DONE_SHIFT 4 +#define USTORM_ISCSI_TASK_ST_CTX_HQ_SCANNED_DONE_MASK 0x1 +#define USTORM_ISCSI_TASK_ST_CTX_HQ_SCANNED_DONE_SHIFT 5 #define USTORM_ISCSI_TASK_ST_CTX_R2T2RECV_DONE_MASK 0x1 #define USTORM_ISCSI_TASK_ST_CTX_R2T2RECV_DONE_SHIFT 6 #define USTORM_ISCSI_TASK_ST_CTX_RESERVED0_MASK 0x1 @@ -1220,7 +1170,6 @@ struct ustorm_iscsi_task_st_ctx { struct iscsi_task_context { struct ystorm_iscsi_task_st_ctx ystorm_st_context; - struct regpair ystorm_st_padding[2]; struct ystorm_iscsi_task_ag_ctx ystorm_ag_context; struct regpair ystorm_ag_padding[2]; struct tdif_task_context tdif_context; @@ -1272,32 +1221,22 @@ struct iscsi_uhqe { #define ISCSI_UHQE_TASK_ID_LO_SHIFT 24 }; -struct iscsi_wqe_field { - __le32 contlen_cdbsize_field; -#define ISCSI_WQE_FIELD_CONT_LEN_MASK 0xFFFFFF -#define ISCSI_WQE_FIELD_CONT_LEN_SHIFT 0 -#define ISCSI_WQE_FIELD_CDB_SIZE_MASK 0xFF -#define ISCSI_WQE_FIELD_CDB_SIZE_SHIFT 24 -}; - -union iscsi_wqe_field_union { - struct iscsi_wqe_field cont_field; - __le32 prev_tid; -}; struct iscsi_wqe { __le16 task_id; u8 flags; #define ISCSI_WQE_WQE_TYPE_MASK 0x7 #define ISCSI_WQE_WQE_TYPE_SHIFT 0 -#define ISCSI_WQE_NUM_FAST_SGES_MASK 0x7 -#define ISCSI_WQE_NUM_FAST_SGES_SHIFT 3 -#define ISCSI_WQE_PTU_INVALIDATE_MASK 0x1 -#define ISCSI_WQE_PTU_INVALIDATE_SHIFT 6 +#define ISCSI_WQE_NUM_SGES_MASK 0xF +#define ISCSI_WQE_NUM_SGES_SHIFT 3 #define ISCSI_WQE_RESPONSE_MASK 0x1 #define ISCSI_WQE_RESPONSE_SHIFT 7 struct iscsi_dif_flags prot_flags; - union iscsi_wqe_field_union cont_prevtid_union; + __le32 contlen_cdbsize; +#define ISCSI_WQE_CONT_LEN_MASK 0xFFFFFF +#define ISCSI_WQE_CONT_LEN_SHIFT 0 +#define ISCSI_WQE_CDB_SIZE_MASK 0xFF +#define ISCSI_WQE_CDB_SIZE_SHIFT 24 }; enum iscsi_wqe_type { @@ -1318,17 +1257,15 @@ struct iscsi_xhqe { u8 total_ahs_length; u8 opcode; u8 flags; -#define ISCSI_XHQE_NUM_FAST_SGES_MASK 0x7 -#define ISCSI_XHQE_NUM_FAST_SGES_SHIFT 0 -#define ISCSI_XHQE_FINAL_MASK 0x1 -#define ISCSI_XHQE_FINAL_SHIFT 3 -#define ISCSI_XHQE_SUPER_IO_MASK 0x1 -#define ISCSI_XHQE_SUPER_IO_SHIFT 4 -#define ISCSI_XHQE_STATUS_BIT_MASK 0x1 -#define ISCSI_XHQE_STATUS_BIT_SHIFT 5 -#define ISCSI_XHQE_RESERVED_MASK 0x3 -#define ISCSI_XHQE_RESERVED_SHIFT 6 - union iscsi_seq_num seq_num_union; +#define ISCSI_XHQE_FINAL_MASK 0x1 +#define ISCSI_XHQE_FINAL_SHIFT 0 +#define ISCSI_XHQE_STATUS_BIT_MASK 0x1 +#define ISCSI_XHQE_STATUS_BIT_SHIFT 1 +#define ISCSI_XHQE_NUM_SGES_MASK 0xF +#define ISCSI_XHQE_NUM_SGES_SHIFT 2 +#define ISCSI_XHQE_RESERVED0_MASK 0x3 +#define ISCSI_XHQE_RESERVED0_SHIFT 6 + union iscsi_seq_num seq_num; __le16 reserved1; }; diff --git a/include/linux/qed/qed_if.h b/include/linux/qed/qed_if.h index fde56c436f71..8e0065c52857 100644 --- a/include/linux/qed/qed_if.h +++ b/include/linux/qed/qed_if.h @@ -300,6 +300,11 @@ struct qed_sb_info { struct qed_dev *cdev; }; +enum qed_dev_type { + QED_DEV_TYPE_BB, + QED_DEV_TYPE_AH, +}; + struct qed_dev_info { unsigned long pci_mem_start; unsigned long pci_mem_end; @@ -325,6 +330,8 @@ struct qed_dev_info { u16 mtu; bool wol_support; + + enum qed_dev_type dev_type; }; enum qed_sb_type { @@ -752,7 +759,7 @@ enum qed_mf_mode { QED_MF_NPAR, }; -struct qed_eth_stats { +struct qed_eth_stats_common { u64 no_buff_discards; u64 packet_too_big_discard; u64 ttl0_discard; @@ -784,11 +791,6 @@ struct qed_eth_stats { u64 rx_256_to_511_byte_packets; u64 rx_512_to_1023_byte_packets; u64 rx_1024_to_1518_byte_packets; - u64 rx_1519_to_1522_byte_packets; - u64 rx_1519_to_2047_byte_packets; - u64 rx_2048_to_4095_byte_packets; - u64 rx_4096_to_9216_byte_packets; - u64 rx_9217_to_16383_byte_packets; u64 rx_crc_errors; u64 rx_mac_crtl_frames; u64 rx_pause_frames; @@ -805,14 +807,8 @@ struct qed_eth_stats { u64 tx_256_to_511_byte_packets; u64 tx_512_to_1023_byte_packets; u64 tx_1024_to_1518_byte_packets; - u64 tx_1519_to_2047_byte_packets; - u64 tx_2048_to_4095_byte_packets; - u64 tx_4096_to_9216_byte_packets; - u64 tx_9217_to_16383_byte_packets; u64 tx_pause_frames; u64 tx_pfc_frames; - u64 tx_lpi_entry_count; - u64 tx_total_collisions; u64 brb_truncates; u64 brb_discards; u64 rx_mac_bytes; @@ -827,6 +823,34 @@ struct qed_eth_stats { u64 tx_mac_ctrl_frames; }; +struct qed_eth_stats_bb { + u64 rx_1519_to_1522_byte_packets; + u64 rx_1519_to_2047_byte_packets; + u64 rx_2048_to_4095_byte_packets; + u64 rx_4096_to_9216_byte_packets; + u64 rx_9217_to_16383_byte_packets; + u64 tx_1519_to_2047_byte_packets; + u64 tx_2048_to_4095_byte_packets; + u64 tx_4096_to_9216_byte_packets; + u64 tx_9217_to_16383_byte_packets; + u64 tx_lpi_entry_count; + u64 tx_total_collisions; +}; + +struct qed_eth_stats_ah { + u64 rx_1519_to_max_byte_packets; + u64 tx_1519_to_max_byte_packets; +}; + +struct qed_eth_stats { + struct qed_eth_stats_common common; + + union { + struct qed_eth_stats_bb bb; + struct qed_eth_stats_ah ah; + }; +}; + #define QED_SB_IDX 0x0002 #define RX_PI 0 diff --git a/include/linux/qed/rdma_common.h b/include/linux/qed/rdma_common.h index f773aa5e746f..72c770f9f666 100644 --- a/include/linux/qed/rdma_common.h +++ b/include/linux/qed/rdma_common.h @@ -52,7 +52,8 @@ #define RDMA_MAX_PDS (64 * 1024) #define RDMA_NUM_STATISTIC_COUNTERS MAX_NUM_VPORTS -#define RDMA_NUM_STATISTIC_COUNTERS_BB MAX_NUM_VPORTS_BB +#define RDMA_NUM_STATISTIC_COUNTERS_K2 MAX_NUM_VPORTS_K2 +#define RDMA_NUM_STATISTIC_COUNTERS_BB MAX_NUM_VPORTS_BB #define RDMA_TASK_TYPE (PROTOCOLID_ROCE) diff --git a/include/linux/qed/roce_common.h b/include/linux/qed/roce_common.h index bad02df213df..866f063026de 100644 --- a/include/linux/qed/roce_common.h +++ b/include/linux/qed/roce_common.h @@ -38,4 +38,21 @@ #define ROCE_MAX_QPS (32 * 1024) +enum roce_async_events_type { + ROCE_ASYNC_EVENT_NONE = 0, + ROCE_ASYNC_EVENT_COMM_EST = 1, + ROCE_ASYNC_EVENT_SQ_DRAINED, + ROCE_ASYNC_EVENT_SRQ_LIMIT, + ROCE_ASYNC_EVENT_LAST_WQE_REACHED, + ROCE_ASYNC_EVENT_CQ_ERR, + ROCE_ASYNC_EVENT_LOCAL_INVALID_REQUEST_ERR, + ROCE_ASYNC_EVENT_LOCAL_CATASTROPHIC_ERR, + ROCE_ASYNC_EVENT_LOCAL_ACCESS_ERR, + ROCE_ASYNC_EVENT_QP_CATASTROPHIC_ERR, + ROCE_ASYNC_EVENT_CQ_OVERFLOW_ERR, + ROCE_ASYNC_EVENT_SRQ_EMPTY, + ROCE_ASYNC_EVENT_DESTROY_QP_DONE, + MAX_ROCE_ASYNC_EVENTS_TYPE +}; + #endif /* __ROCE_COMMON__ */ diff --git a/include/linux/qed/storage_common.h b/include/linux/qed/storage_common.h index 03f3e37ab059..08df82a096b6 100644 --- a/include/linux/qed/storage_common.h +++ b/include/linux/qed/storage_common.h @@ -40,6 +40,8 @@ #define BDQ_ID_IMM_DATA (1) #define BDQ_NUM_IDS (2) +#define SCSI_NUM_SGES_SLOW_SGL_THR 8 + #define BDQ_MAX_EXTERNAL_RING_SIZE (1 << 15) struct scsi_bd { @@ -52,6 +54,16 @@ struct scsi_bdq_ram_drv_data { __le16 reserved0[3]; }; +struct scsi_sge { + struct regpair sge_addr; + __le32 sge_len; + __le32 reserved; +}; + +struct scsi_cached_sges { + struct scsi_sge sge[4]; +}; + struct scsi_drv_cmdq { __le16 cmdq_cons; __le16 reserved0; @@ -99,11 +111,19 @@ struct scsi_ram_per_bdq_resource_drv_data { struct scsi_bdq_ram_drv_data drv_data_per_bdq_id[BDQ_NUM_IDS]; }; -struct scsi_sge { - struct regpair sge_addr; - __le16 sge_len; - __le16 reserved0; - __le32 reserved1; +enum scsi_sgl_mode { + SCSI_TX_SLOW_SGL, + SCSI_FAST_SGL, + MAX_SCSI_SGL_MODE +}; + +struct scsi_sgl_params { + struct regpair sgl_addr; + __le32 sgl_total_length; + __le32 sge_offset; + __le16 sgl_num_sges; + u8 sgl_index; + u8 reserved; }; struct scsi_terminate_extra_params { diff --git a/include/linux/qed/tcp_common.h b/include/linux/qed/tcp_common.h index 46fe7856f1b2..a5e843268f0e 100644 --- a/include/linux/qed/tcp_common.h +++ b/include/linux/qed/tcp_common.h @@ -173,6 +173,7 @@ enum tcp_seg_placement_event { TCP_EVENT_ADD_ISLE_RIGHT, TCP_EVENT_ADD_ISLE_LEFT, TCP_EVENT_JOIN, + TCP_EVENT_DELETE_ISLES, TCP_EVENT_NOP, MAX_TCP_SEG_PLACEMENT_EVENT }; diff --git a/include/linux/random.h b/include/linux/random.h index 7bd2403e4fef..ed5c3838780d 100644 --- a/include/linux/random.h +++ b/include/linux/random.h @@ -37,14 +37,26 @@ extern void get_random_bytes(void *buf, int nbytes); extern int add_random_ready_callback(struct random_ready_callback *rdy); extern void del_random_ready_callback(struct random_ready_callback *rdy); extern void get_random_bytes_arch(void *buf, int nbytes); -extern int random_int_secret_init(void); #ifndef MODULE extern const struct file_operations random_fops, urandom_fops; #endif -unsigned int get_random_int(void); -unsigned long get_random_long(void); +u32 get_random_u32(void); +u64 get_random_u64(void); +static inline unsigned int get_random_int(void) +{ + return get_random_u32(); +} +static inline unsigned long get_random_long(void) +{ +#if BITS_PER_LONG == 64 + return get_random_u64(); +#else + return get_random_u32(); +#endif +} + unsigned long randomize_page(unsigned long start, unsigned long range); u32 prandom_u32(void); diff --git a/include/linux/rculist_nulls.h b/include/linux/rculist_nulls.h index 4ae95f7e8597..a23a33153180 100644 --- a/include/linux/rculist_nulls.h +++ b/include/linux/rculist_nulls.h @@ -156,5 +156,19 @@ static inline void hlist_nulls_add_tail_rcu(struct hlist_nulls_node *n, ({ tpos = hlist_nulls_entry(pos, typeof(*tpos), member); 1; }); \ pos = rcu_dereference_raw(hlist_nulls_next_rcu(pos))) +/** + * hlist_nulls_for_each_entry_safe - + * iterate over list of given type safe against removal of list entry + * @tpos: the type * to use as a loop cursor. + * @pos: the &struct hlist_nulls_node to use as a loop cursor. + * @head: the head for your list. + * @member: the name of the hlist_nulls_node within the struct. + */ +#define hlist_nulls_for_each_entry_safe(tpos, pos, head, member) \ + for (({barrier();}), \ + pos = rcu_dereference_raw(hlist_nulls_first_rcu(head)); \ + (!is_a_nulls(pos)) && \ + ({ tpos = hlist_nulls_entry(pos, typeof(*tpos), member); \ + pos = rcu_dereference_raw(hlist_nulls_next_rcu(pos)); 1; });) #endif #endif diff --git a/include/linux/regulator/machine.h b/include/linux/regulator/machine.h index ad3e5158e586..c9f795e9a2ee 100644 --- a/include/linux/regulator/machine.h +++ b/include/linux/regulator/machine.h @@ -65,7 +65,7 @@ struct regulator_state { int uV; /* suspend voltage */ unsigned int mode; /* suspend regulator operating mode */ int enabled; /* is regulator enabled in this suspend state */ - int disabled; /* is the regulator disbled in this suspend state */ + int disabled; /* is the regulator disabled in this suspend state */ }; /** diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h index fc273e9d5f67..be47b859e954 100644 --- a/include/linux/stmmac.h +++ b/include/linux/stmmac.h @@ -28,6 +28,9 @@ #include <linux/platform_device.h> +#define MTL_MAX_RX_QUEUES 8 +#define MTL_MAX_TX_QUEUES 8 + #define STMMAC_RX_COE_NONE 0 #define STMMAC_RX_COE_TYPE1 1 #define STMMAC_RX_COE_TYPE2 2 @@ -44,6 +47,18 @@ #define STMMAC_CSR_150_250M 0x4 /* MDC = clk_scr_i/102 */ #define STMMAC_CSR_250_300M 0x5 /* MDC = clk_scr_i/122 */ +/* MTL algorithms identifiers */ +#define MTL_TX_ALGORITHM_WRR 0x0 +#define MTL_TX_ALGORITHM_WFQ 0x1 +#define MTL_TX_ALGORITHM_DWRR 0x2 +#define MTL_TX_ALGORITHM_SP 0x3 +#define MTL_RX_ALGORITHM_SP 0x4 +#define MTL_RX_ALGORITHM_WSP 0x5 + +/* RX/TX Queue Mode */ +#define MTL_QUEUE_DCB 0x0 +#define MTL_QUEUE_AVB 0x1 + /* The MDC clock could be set higher than the IEEE 802.3 * specified frequency limit 0f 2.5 MHz, by programming a clock divider * of value different than the above defined values. The resultant MDIO @@ -109,6 +124,21 @@ struct stmmac_axi { bool axi_rb; }; +struct stmmac_rxq_cfg { + u8 mode_to_use; + u8 chan; +}; + +struct stmmac_txq_cfg { + u8 weight; + u8 mode_to_use; + /* Credit Base Shaper parameters */ + u32 send_slope; + u32 idle_slope; + u32 high_credit; + u32 low_credit; +}; + struct plat_stmmacenet_data { int bus_id; int phy_addr; @@ -133,6 +163,12 @@ struct plat_stmmacenet_data { int unicast_filter_entries; int tx_fifo_size; int rx_fifo_size; + u8 rx_queues_to_use; + u8 tx_queues_to_use; + u8 rx_sched_algorithm; + u8 tx_sched_algorithm; + struct stmmac_rxq_cfg rx_queues_cfg[MTL_MAX_RX_QUEUES]; + struct stmmac_txq_cfg tx_queues_cfg[MTL_MAX_TX_QUEUES]; void (*fix_mac_speed)(void *priv, unsigned int speed); int (*init)(struct platform_device *pdev, void *priv); void (*exit)(struct platform_device *pdev, void *priv); diff --git a/include/linux/user_namespace.h b/include/linux/user_namespace.h index be765234c0a2..32354b4b4b2b 100644 --- a/include/linux/user_namespace.h +++ b/include/linux/user_namespace.h @@ -72,7 +72,7 @@ struct ucounts { struct hlist_node node; struct user_namespace *ns; kuid_t uid; - atomic_t count; + int count; atomic_t ucount[UCOUNT_COUNTS]; }; diff --git a/include/linux/userfaultfd_k.h b/include/linux/userfaultfd_k.h index 0468548acebf..48a3483dccb1 100644 --- a/include/linux/userfaultfd_k.h +++ b/include/linux/userfaultfd_k.h @@ -61,8 +61,7 @@ extern void mremap_userfaultfd_complete(struct vm_userfaultfd_ctx *, unsigned long from, unsigned long to, unsigned long len); -extern void userfaultfd_remove(struct vm_area_struct *vma, - struct vm_area_struct **prev, +extern bool userfaultfd_remove(struct vm_area_struct *vma, unsigned long start, unsigned long end); @@ -72,8 +71,6 @@ extern int userfaultfd_unmap_prep(struct vm_area_struct *vma, extern void userfaultfd_unmap_complete(struct mm_struct *mm, struct list_head *uf); -extern void userfaultfd_exit(struct mm_struct *mm); - #else /* CONFIG_USERFAULTFD */ /* mm helpers */ @@ -120,11 +117,11 @@ static inline void mremap_userfaultfd_complete(struct vm_userfaultfd_ctx *ctx, { } -static inline void userfaultfd_remove(struct vm_area_struct *vma, - struct vm_area_struct **prev, +static inline bool userfaultfd_remove(struct vm_area_struct *vma, unsigned long start, unsigned long end) { + return true; } static inline int userfaultfd_unmap_prep(struct vm_area_struct *vma, @@ -139,10 +136,6 @@ static inline void userfaultfd_unmap_complete(struct mm_struct *mm, { } -static inline void userfaultfd_exit(struct mm_struct *mm) -{ -} - #endif /* CONFIG_USERFAULTFD */ #endif /* _LINUX_USERFAULTFD_K_H */ diff --git a/include/linux/vm_event_item.h b/include/linux/vm_event_item.h index 6aa1b6cb5828..a80b7b59cf33 100644 --- a/include/linux/vm_event_item.h +++ b/include/linux/vm_event_item.h @@ -79,6 +79,9 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT, THP_SPLIT_PAGE_FAILED, THP_DEFERRED_SPLIT_PAGE, THP_SPLIT_PMD, +#ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD + THP_SPLIT_PUD, +#endif THP_ZERO_PAGE_ALLOC, THP_ZERO_PAGE_ALLOC_FAILED, #endif diff --git a/include/linux/wait.h b/include/linux/wait.h index aacb1282d19a..db076ca7f11d 100644 --- a/include/linux/wait.h +++ b/include/linux/wait.h @@ -620,30 +620,19 @@ do { \ __ret; \ }) +extern int do_wait_intr(wait_queue_head_t *, wait_queue_t *); +extern int do_wait_intr_irq(wait_queue_head_t *, wait_queue_t *); -#define __wait_event_interruptible_locked(wq, condition, exclusive, irq) \ +#define __wait_event_interruptible_locked(wq, condition, exclusive, fn) \ ({ \ - int __ret = 0; \ + int __ret; \ DEFINE_WAIT(__wait); \ if (exclusive) \ __wait.flags |= WQ_FLAG_EXCLUSIVE; \ do { \ - if (likely(list_empty(&__wait.task_list))) \ - __add_wait_queue_tail(&(wq), &__wait); \ - set_current_state(TASK_INTERRUPTIBLE); \ - if (signal_pending(current)) { \ - __ret = -ERESTARTSYS; \ + __ret = fn(&(wq), &__wait); \ + if (__ret) \ break; \ - } \ - if (irq) \ - spin_unlock_irq(&(wq).lock); \ - else \ - spin_unlock(&(wq).lock); \ - schedule(); \ - if (irq) \ - spin_lock_irq(&(wq).lock); \ - else \ - spin_lock(&(wq).lock); \ } while (!(condition)); \ __remove_wait_queue(&(wq), &__wait); \ __set_current_state(TASK_RUNNING); \ @@ -676,7 +665,7 @@ do { \ */ #define wait_event_interruptible_locked(wq, condition) \ ((condition) \ - ? 0 : __wait_event_interruptible_locked(wq, condition, 0, 0)) + ? 0 : __wait_event_interruptible_locked(wq, condition, 0, do_wait_intr)) /** * wait_event_interruptible_locked_irq - sleep until a condition gets true @@ -703,7 +692,7 @@ do { \ */ #define wait_event_interruptible_locked_irq(wq, condition) \ ((condition) \ - ? 0 : __wait_event_interruptible_locked(wq, condition, 0, 1)) + ? 0 : __wait_event_interruptible_locked(wq, condition, 0, do_wait_intr_irq)) /** * wait_event_interruptible_exclusive_locked - sleep exclusively until a condition gets true @@ -734,7 +723,7 @@ do { \ */ #define wait_event_interruptible_exclusive_locked(wq, condition) \ ((condition) \ - ? 0 : __wait_event_interruptible_locked(wq, condition, 1, 0)) + ? 0 : __wait_event_interruptible_locked(wq, condition, 1, do_wait_intr)) /** * wait_event_interruptible_exclusive_locked_irq - sleep until a condition gets true @@ -765,7 +754,7 @@ do { \ */ #define wait_event_interruptible_exclusive_locked_irq(wq, condition) \ ((condition) \ - ? 0 : __wait_event_interruptible_locked(wq, condition, 1, 1)) + ? 0 : __wait_event_interruptible_locked(wq, condition, 1, do_wait_intr_irq)) #define __wait_event_killable(wq, condition) \ diff --git a/include/media/vsp1.h b/include/media/vsp1.h index 458b400373d4..38aac554dbba 100644 --- a/include/media/vsp1.h +++ b/include/media/vsp1.h @@ -20,8 +20,17 @@ struct device; int vsp1_du_init(struct device *dev); -int vsp1_du_setup_lif(struct device *dev, unsigned int width, - unsigned int height); +/** + * struct vsp1_du_lif_config - VSP LIF configuration + * @width: output frame width + * @height: output frame height + */ +struct vsp1_du_lif_config { + unsigned int width; + unsigned int height; +}; + +int vsp1_du_setup_lif(struct device *dev, const struct vsp1_du_lif_config *cfg); struct vsp1_du_atomic_config { u32 pixelformat; diff --git a/include/net/dsa.h b/include/net/dsa.h index 4e13e695f025..e42897fd7a96 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -233,6 +233,10 @@ struct dsa_switch { u32 phys_mii_mask; struct mii_bus *slave_mii_bus; + /* Ageing Time limits in msecs */ + unsigned int ageing_time_min; + unsigned int ageing_time_max; + /* Dynamically allocated ports, keep last */ size_t num_ports; struct dsa_port ports[]; @@ -248,6 +252,11 @@ static inline bool dsa_is_dsa_port(struct dsa_switch *ds, int p) return !!((ds->dsa_port_mask) & (1 << p)); } +static inline bool dsa_is_normal_port(struct dsa_switch *ds, int p) +{ + return !dsa_is_cpu_port(ds, p) && !dsa_is_dsa_port(ds, p); +} + static inline bool dsa_is_port_initialized(struct dsa_switch *ds, int p) { return ds->enabled_port_mask & (1 << p) && ds->ports[p].netdev; diff --git a/include/net/fib_rules.h b/include/net/fib_rules.h index 8dbfdf728cd8..1243b9c7694e 100644 --- a/include/net/fib_rules.h +++ b/include/net/fib_rules.h @@ -141,6 +141,7 @@ int fib_rules_lookup(struct fib_rules_ops *, struct flowi *, int flags, struct fib_lookup_arg *); int fib_default_rule_add(struct fib_rules_ops *, u32 pref, u32 table, u32 flags); +bool fib_rule_matchall(const struct fib_rule *rule); int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr *nlh); int fib_nl_delrule(struct sk_buff *skb, struct nlmsghdr *nlh); diff --git a/include/net/inet_common.h b/include/net/inet_common.h index b7952d55b9c0..f39ae697347f 100644 --- a/include/net/inet_common.h +++ b/include/net/inet_common.h @@ -20,7 +20,8 @@ int __inet_stream_connect(struct socket *sock, struct sockaddr *uaddr, int addr_len, int flags, int is_sendmsg); int inet_dgram_connect(struct socket *sock, struct sockaddr *uaddr, int addr_len, int flags); -int inet_accept(struct socket *sock, struct socket *newsock, int flags); +int inet_accept(struct socket *sock, struct socket *newsock, int flags, + bool kern); int inet_sendmsg(struct socket *sock, struct msghdr *msg, size_t size); ssize_t inet_sendpage(struct socket *sock, struct page *page, int offset, size_t size, int flags); diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h index 826f198374f8..c7a577976bec 100644 --- a/include/net/inet_connection_sock.h +++ b/include/net/inet_connection_sock.h @@ -258,7 +258,7 @@ inet_csk_rto_backoff(const struct inet_connection_sock *icsk, return (unsigned long)min_t(u64, when, max_when); } -struct sock *inet_csk_accept(struct sock *sk, int flags, int *err); +struct sock *inet_csk_accept(struct sock *sk, int flags, int *err, bool kern); int inet_csk_get_port(struct sock *sk, unsigned short snum); diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h index 368bb4024b78..272e62e139e0 100644 --- a/include/net/ip_fib.h +++ b/include/net/ip_fib.h @@ -213,6 +213,11 @@ struct fib_entry_notifier_info { u32 tb_id; }; +struct fib_rule_notifier_info { + struct fib_notifier_info info; /* must be first */ + struct fib_rule *rule; +}; + struct fib_nh_notifier_info { struct fib_notifier_info info; /* must be first */ struct fib_nh *fib_nh; @@ -232,9 +237,21 @@ enum fib_event_type { int register_fib_notifier(struct notifier_block *nb, void (*cb)(struct notifier_block *nb)); int unregister_fib_notifier(struct notifier_block *nb); +int call_fib_notifier(struct notifier_block *nb, struct net *net, + enum fib_event_type event_type, + struct fib_notifier_info *info); int call_fib_notifiers(struct net *net, enum fib_event_type event_type, struct fib_notifier_info *info); +void fib_notify(struct net *net, struct notifier_block *nb); +#ifdef CONFIG_IP_MULTIPLE_TABLES +void fib_rules_notify(struct net *net, struct notifier_block *nb); +#else +static inline void fib_rules_notify(struct net *net, struct notifier_block *nb) +{ +} +#endif + struct fib_table { struct hlist_node tb_hlist; u32 tb_id; @@ -299,6 +316,11 @@ static inline int fib_lookup(struct net *net, const struct flowi4 *flp, return err; } +static inline bool fib4_rule_default(const struct fib_rule *rule) +{ + return true; +} + #else /* CONFIG_IP_MULTIPLE_TABLES */ int __net_init fib4_rules_init(struct net *net); void __net_exit fib4_rules_exit(struct net *net); @@ -343,6 +365,8 @@ out: return err; } +bool fib4_rule_default(const struct fib_rule *rule); + #endif /* CONFIG_IP_MULTIPLE_TABLES */ /* Exported by fib_frontend.c */ diff --git a/include/net/irda/timer.h b/include/net/irda/timer.h index cb2615ccf761..d784f242cf7b 100644 --- a/include/net/irda/timer.h +++ b/include/net/irda/timer.h @@ -59,7 +59,7 @@ struct lap_cb; * Slot timer must never exceed 85 ms, and must always be at least 25 ms, * suggested to 75-85 msec by IrDA lite. This doesn't work with a lot of * devices, and other stackes uses a lot more, so it's best we do it as well - * (Note : this is the default value and sysctl overides it - Jean II) + * (Note : this is the default value and sysctl overrides it - Jean II) */ #define SLOT_TIMEOUT (90*HZ/1000) diff --git a/include/net/mpls_iptunnel.h b/include/net/mpls_iptunnel.h index 179253f9dcfd..a18af6a16eb5 100644 --- a/include/net/mpls_iptunnel.h +++ b/include/net/mpls_iptunnel.h @@ -19,6 +19,8 @@ struct mpls_iptunnel_encap { u32 label[MAX_NEW_LABELS]; u8 labels; + u8 ttl_propagate; + u8 default_ttl; }; static inline struct mpls_iptunnel_encap *mpls_lwtunnel_encap(struct lwtunnel_state *lwtstate) diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h index 622d2da27135..2e9d649ba169 100644 --- a/include/net/netns/ipv4.h +++ b/include/net/netns/ipv4.h @@ -33,7 +33,6 @@ struct inet_timewait_death_row { atomic_t tw_count; struct inet_hashinfo *hashinfo ____cacheline_aligned_in_smp; - int sysctl_tw_recycle; int sysctl_max_tw_buckets; }; diff --git a/include/net/netns/mpls.h b/include/net/netns/mpls.h index d29203651c01..6608b3693385 100644 --- a/include/net/netns/mpls.h +++ b/include/net/netns/mpls.h @@ -9,8 +9,11 @@ struct mpls_route; struct ctl_table_header; struct netns_mpls { + int ip_ttl_propagate; + int default_ttl; size_t platform_labels; struct mpls_route __rcu * __rcu *platform_label; + struct ctl_table_header *ctl; }; diff --git a/include/net/pkt_sched.h b/include/net/pkt_sched.h index f1b76b8e6d2d..bec46f63f10c 100644 --- a/include/net/pkt_sched.h +++ b/include/net/pkt_sched.h @@ -92,7 +92,7 @@ int unregister_qdisc(struct Qdisc_ops *qops); void qdisc_get_default(char *id, size_t len); int qdisc_set_default(const char *id); -void qdisc_hash_add(struct Qdisc *q); +void qdisc_hash_add(struct Qdisc *q, bool invisible); void qdisc_hash_del(struct Qdisc *q); struct Qdisc *qdisc_lookup(struct net_device *dev, u32 handle); struct Qdisc *qdisc_lookup_class(struct net_device *dev, u32 handle); diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index aeec4086afb2..65d502610314 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -66,6 +66,7 @@ struct Qdisc { #define TCQ_F_NOPARENT 0x40 /* root of its hierarchy : * qdisc_tree_decrease_qlen() should stop. */ +#define TCQ_F_INVISIBLE 0x80 /* invisible by default in dump */ u32 limit; const struct Qdisc_ops *ops; struct qdisc_size_table __rcu *stab; diff --git a/include/net/sctp/sm.h b/include/net/sctp/sm.h index b6f682ec184a..47113f2c4b0a 100644 --- a/include/net/sctp/sm.h +++ b/include/net/sctp/sm.h @@ -293,6 +293,22 @@ struct sctp_chunk *sctp_process_strreset_inreq( struct sctp_association *asoc, union sctp_params param, struct sctp_ulpevent **evp); +struct sctp_chunk *sctp_process_strreset_tsnreq( + struct sctp_association *asoc, + union sctp_params param, + struct sctp_ulpevent **evp); +struct sctp_chunk *sctp_process_strreset_addstrm_out( + struct sctp_association *asoc, + union sctp_params param, + struct sctp_ulpevent **evp); +struct sctp_chunk *sctp_process_strreset_addstrm_in( + struct sctp_association *asoc, + union sctp_params param, + struct sctp_ulpevent **evp); +struct sctp_chunk *sctp_process_strreset_resp( + struct sctp_association *asoc, + union sctp_params param, + struct sctp_ulpevent **evp); /* Prototypes for statetable processing. */ diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h index a244db5e5ff7..07a0b128625a 100644 --- a/include/net/sctp/structs.h +++ b/include/net/sctp/structs.h @@ -476,7 +476,8 @@ struct sctp_pf { int (*send_verify) (struct sctp_sock *, union sctp_addr *); int (*supported_addrs)(const struct sctp_sock *, __be16 *); struct sock *(*create_accept_sk) (struct sock *sk, - struct sctp_association *asoc); + struct sctp_association *asoc, + bool kern); int (*addr_to_user)(struct sctp_sock *sk, union sctp_addr *addr); void (*to_sk_saddr)(union sctp_addr *, struct sock *sk); void (*to_sk_daddr)(union sctp_addr *, struct sock *sk); diff --git a/include/net/sctp/ulpevent.h b/include/net/sctp/ulpevent.h index 324b5965fc4d..1060494ac230 100644 --- a/include/net/sctp/ulpevent.h +++ b/include/net/sctp/ulpevent.h @@ -132,6 +132,14 @@ struct sctp_ulpevent *sctp_ulpevent_make_stream_reset_event( const struct sctp_association *asoc, __u16 flags, __u16 stream_num, __u16 *stream_list, gfp_t gfp); +struct sctp_ulpevent *sctp_ulpevent_make_assoc_reset_event( + const struct sctp_association *asoc, __u16 flags, + __u32 local_tsn, __u32 remote_tsn, gfp_t gfp); + +struct sctp_ulpevent *sctp_ulpevent_make_stream_change_event( + const struct sctp_association *asoc, __u16 flags, + __u32 strchange_instrms, __u32 strchange_outstrms, gfp_t gfp); + void sctp_ulpevent_read_sndrcvinfo(const struct sctp_ulpevent *event, struct msghdr *); void sctp_ulpevent_read_rcvinfo(const struct sctp_ulpevent *event, diff --git a/include/net/secure_seq.h b/include/net/secure_seq.h index 0caee631a836..fe236b3429f0 100644 --- a/include/net/secure_seq.h +++ b/include/net/secure_seq.h @@ -6,10 +6,10 @@ u32 secure_ipv4_port_ephemeral(__be32 saddr, __be32 daddr, __be16 dport); u32 secure_ipv6_port_ephemeral(const __be32 *saddr, const __be32 *daddr, __be16 dport); -u32 secure_tcp_sequence_number(__be32 saddr, __be32 daddr, +u32 secure_tcp_seq_and_tsoff(__be32 saddr, __be32 daddr, + __be16 sport, __be16 dport, u32 *tsoff); +u32 secure_tcpv6_seq_and_tsoff(const __be32 *saddr, const __be32 *daddr, __be16 sport, __be16 dport, u32 *tsoff); -u32 secure_tcpv6_sequence_number(const __be32 *saddr, const __be32 *daddr, - __be16 sport, __be16 dport, u32 *tsoff); u64 secure_dccp_sequence_number(__be32 saddr, __be32 daddr, __be16 sport, __be16 dport); u64 secure_dccpv6_sequence_number(__be32 *saddr, __be32 *daddr, diff --git a/include/net/sock.h b/include/net/sock.h index 5e5997654db6..08142be8938e 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -236,6 +236,7 @@ struct sock_common { * @sk_shutdown: mask of %SEND_SHUTDOWN and/or %RCV_SHUTDOWN * @sk_userlocks: %SO_SNDBUF and %SO_RCVBUF settings * @sk_lock: synchronizer + * @sk_kern_sock: True if sock is using kernel lock classes * @sk_rcvbuf: size of receive buffer in bytes * @sk_wq: sock wait queue and async head * @sk_rx_dst: receive input route used by early demux @@ -430,7 +431,8 @@ struct sock { #endif kmemcheck_bitfield_begin(flags); - unsigned int sk_padding : 2, + unsigned int sk_padding : 1, + sk_kern_sock : 1, sk_no_check_tx : 1, sk_no_check_rx : 1, sk_userlocks : 4, @@ -1015,7 +1017,8 @@ struct proto { int addr_len); int (*disconnect)(struct sock *sk, int flags); - struct sock * (*accept)(struct sock *sk, int flags, int *err); + struct sock * (*accept)(struct sock *sk, int flags, int *err, + bool kern); int (*ioctl)(struct sock *sk, int cmd, unsigned long arg); @@ -1573,7 +1576,7 @@ int sock_cmsg_send(struct sock *sk, struct msghdr *msg, int sock_no_bind(struct socket *, struct sockaddr *, int); int sock_no_connect(struct socket *, struct sockaddr *, int, int); int sock_no_socketpair(struct socket *, struct socket *); -int sock_no_accept(struct socket *, struct socket *, int); +int sock_no_accept(struct socket *, struct socket *, int, bool); int sock_no_getname(struct socket *, struct sockaddr *, int *, int); unsigned int sock_no_poll(struct file *, struct socket *, struct poll_table_struct *); @@ -1780,11 +1783,8 @@ __sk_dst_set(struct sock *sk, struct dst_entry *dst) sk_tx_queue_clear(sk); sk->sk_dst_pending_confirm = 0; - /* - * This can be called while sk is owned by the caller only, - * with no state that can be checked in a rcu_dereference_check() cond - */ - old_dst = rcu_dereference_raw(sk->sk_dst_cache); + old_dst = rcu_dereference_protected(sk->sk_dst_cache, + lockdep_sock_is_held(sk)); rcu_assign_pointer(sk->sk_dst_cache, dst); dst_release(old_dst); } diff --git a/include/net/tc_act/tc_vlan.h b/include/net/tc_act/tc_vlan.h index 48cca321ee6c..9690c047b6cf 100644 --- a/include/net/tc_act/tc_vlan.h +++ b/include/net/tc_act/tc_vlan.h @@ -49,4 +49,9 @@ static inline __be16 tcf_vlan_push_proto(const struct tc_action *a) return to_vlan(a)->tcfv_push_proto; } +static inline u8 tcf_vlan_push_prio(const struct tc_action *a) +{ + return to_vlan(a)->tcfv_push_prio; +} + #endif /* __NET_TC_VLAN_H */ diff --git a/include/net/tcp.h b/include/net/tcp.h index 6ec4ea652f3f..e614ad4d613e 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -406,11 +406,7 @@ void tcp_clear_retrans(struct tcp_sock *tp); void tcp_update_metrics(struct sock *sk); void tcp_init_metrics(struct sock *sk); void tcp_metrics_init(void); -bool tcp_peer_is_proven(struct request_sock *req, struct dst_entry *dst, - bool paws_check, bool timestamps); -bool tcp_remember_stamp(struct sock *sk); -bool tcp_tw_remember_stamp(struct inet_timewait_sock *tw); -void tcp_fetch_timewait_stamp(struct sock *sk, struct dst_entry *dst); +bool tcp_peer_is_proven(struct request_sock *req, struct dst_entry *dst); void tcp_disable_fack(struct tcp_sock *tp); void tcp_close(struct sock *sk, long timeout); void tcp_init_sock(struct sock *sk); @@ -1814,9 +1810,8 @@ struct tcp_request_sock_ops { __u16 *mss); #endif struct dst_entry *(*route_req)(const struct sock *sk, struct flowi *fl, - const struct request_sock *req, - bool *strict); - __u32 (*init_seq)(const struct sk_buff *skb, u32 *tsoff); + const struct request_sock *req); + __u32 (*init_seq_tsoff)(const struct sk_buff *skb, u32 *tsoff); int (*send_synack)(const struct sock *sk, struct dst_entry *dst, struct flowi *fl, struct request_sock *req, struct tcp_fastopen_cookie *foc, diff --git a/include/scsi/libiscsi.h b/include/scsi/libiscsi.h index b0e275de6dec..583875ea136a 100644 --- a/include/scsi/libiscsi.h +++ b/include/scsi/libiscsi.h @@ -196,6 +196,7 @@ struct iscsi_conn { struct iscsi_task *task; /* xmit task in progress */ /* xmit */ + spinlock_t taskqueuelock; /* protects the next three lists */ struct list_head mgmtqueue; /* mgmt (control) xmit queue */ struct list_head cmdqueue; /* data-path cmd queue */ struct list_head requeue; /* tasks needing another run */ diff --git a/include/scsi/scsi_device.h b/include/scsi/scsi_device.h index 6f22b39f1b0c..080c7ce9bae8 100644 --- a/include/scsi/scsi_device.h +++ b/include/scsi/scsi_device.h @@ -472,6 +472,10 @@ static inline int scsi_device_created(struct scsi_device *sdev) sdev->sdev_state == SDEV_CREATED_BLOCK; } +int scsi_internal_device_block(struct scsi_device *sdev, bool wait); +int scsi_internal_device_unblock(struct scsi_device *sdev, + enum scsi_device_state new_state); + /* accessor functions for the SCSI parameters */ static inline int scsi_device_sync(struct scsi_device *sdev) { diff --git a/include/trace/events/syscalls.h b/include/trace/events/syscalls.h index 14e49c798135..b35533b94277 100644 --- a/include/trace/events/syscalls.h +++ b/include/trace/events/syscalls.h @@ -1,5 +1,6 @@ #undef TRACE_SYSTEM #define TRACE_SYSTEM raw_syscalls +#undef TRACE_INCLUDE_FILE #define TRACE_INCLUDE_FILE syscalls #if !defined(_TRACE_EVENTS_SYSCALLS_H) || defined(TRACE_HEADER_MULTI_READ) diff --git a/include/uapi/linux/ipv6.h b/include/uapi/linux/ipv6.h index 8ef9e75e004e..d8f6a1ac9af4 100644 --- a/include/uapi/linux/ipv6.h +++ b/include/uapi/linux/ipv6.h @@ -183,6 +183,7 @@ enum { DEVCONF_SEG6_REQUIRE_HMAC, DEVCONF_ENHANCED_DAD, DEVCONF_ADDR_GEN_MODE, + DEVCONF_DISABLE_POLICY, DEVCONF_MAX }; diff --git a/include/uapi/linux/mpls_iptunnel.h b/include/uapi/linux/mpls_iptunnel.h index d80a0498f77e..f5e45095b0bb 100644 --- a/include/uapi/linux/mpls_iptunnel.h +++ b/include/uapi/linux/mpls_iptunnel.h @@ -16,11 +16,13 @@ /* MPLS tunnel attributes * [RTA_ENCAP] = { * [MPLS_IPTUNNEL_DST] + * [MPLS_IPTUNNEL_TTL] * } */ enum { MPLS_IPTUNNEL_UNSPEC, MPLS_IPTUNNEL_DST, + MPLS_IPTUNNEL_TTL, __MPLS_IPTUNNEL_MAX, }; #define MPLS_IPTUNNEL_MAX (__MPLS_IPTUNNEL_MAX - 1) diff --git a/include/uapi/linux/packet_diag.h b/include/uapi/linux/packet_diag.h index d08c63f3dd6f..0c5d5dd61b6a 100644 --- a/include/uapi/linux/packet_diag.h +++ b/include/uapi/linux/packet_diag.h @@ -64,7 +64,7 @@ struct packet_diag_mclist { __u32 pdmc_count; __u16 pdmc_type; __u16 pdmc_alen; - __u8 pdmc_addr[MAX_ADDR_LEN]; + __u8 pdmc_addr[32]; /* MAX_ADDR_LEN */ }; struct packet_diag_ring { diff --git a/include/uapi/linux/pkt_sched.h b/include/uapi/linux/pkt_sched.h index df7451d35131..099bf5528fed 100644 --- a/include/uapi/linux/pkt_sched.h +++ b/include/uapi/linux/pkt_sched.h @@ -617,6 +617,14 @@ struct tc_drr_stats { #define TC_QOPT_BITMASK 15 #define TC_QOPT_MAX_QUEUE 16 +enum { + TC_MQPRIO_HW_OFFLOAD_NONE, /* no offload requested */ + TC_MQPRIO_HW_OFFLOAD_TCS, /* offload TCs, no queue counts */ + __TC_MQPRIO_HW_OFFLOAD_MAX +}; + +#define TC_MQPRIO_HW_OFFLOAD_MAX (__TC_MQPRIO_HW_OFFLOAD_MAX - 1) + struct tc_mqprio_qopt { __u8 num_tc; __u8 prio_tc_map[TC_QOPT_BITMASK + 1]; diff --git a/include/uapi/linux/rtnetlink.h b/include/uapi/linux/rtnetlink.h index 6546917d605a..3dd72aee4d32 100644 --- a/include/uapi/linux/rtnetlink.h +++ b/include/uapi/linux/rtnetlink.h @@ -319,6 +319,7 @@ enum rtattr_type_t { RTA_EXPIRES, RTA_PAD, RTA_UID, + RTA_TTL_PROPAGATE, __RTA_MAX }; @@ -545,6 +546,7 @@ enum { TCA_STATS2, TCA_STAB, TCA_PAD, + TCA_DUMP_INVISIBLE, __TCA_MAX }; diff --git a/include/uapi/linux/sctp.h b/include/uapi/linux/sctp.h index d3ae381fcf33..7212870ef5d7 100644 --- a/include/uapi/linux/sctp.h +++ b/include/uapi/linux/sctp.h @@ -115,6 +115,7 @@ typedef __s32 sctp_assoc_t; #define SCTP_PR_SUPPORTED 113 #define SCTP_DEFAULT_PRINFO 114 #define SCTP_PR_ASSOC_STATUS 115 +#define SCTP_RECONFIG_SUPPORTED 117 #define SCTP_ENABLE_STREAM_RESET 118 #define SCTP_RESET_STREAMS 119 #define SCTP_RESET_ASSOC 120 @@ -502,6 +503,28 @@ struct sctp_stream_reset_event { __u16 strreset_stream_list[]; }; +#define SCTP_ASSOC_RESET_DENIED 0x0004 +#define SCTP_ASSOC_RESET_FAILED 0x0008 +struct sctp_assoc_reset_event { + __u16 assocreset_type; + __u16 assocreset_flags; + __u32 assocreset_length; + sctp_assoc_t assocreset_assoc_id; + __u32 assocreset_local_tsn; + __u32 assocreset_remote_tsn; +}; + +#define SCTP_ASSOC_CHANGE_DENIED 0x0004 +#define SCTP_ASSOC_CHANGE_FAILED 0x0008 +struct sctp_stream_change_event { + __u16 strchange_type; + __u16 strchange_flags; + __u32 strchange_length; + sctp_assoc_t strchange_assoc_id; + __u16 strchange_instrms; + __u16 strchange_outstrms; +}; + /* * Described in Section 7.3 * Ancillary Data and Notification Interest Options @@ -518,6 +541,8 @@ struct sctp_event_subscribe { __u8 sctp_authentication_event; __u8 sctp_sender_dry_event; __u8 sctp_stream_reset_event; + __u8 sctp_assoc_reset_event; + __u8 sctp_stream_change_event; }; /* @@ -543,6 +568,8 @@ union sctp_notification { struct sctp_authkey_event sn_authkey_event; struct sctp_sender_dry_event sn_sender_dry_event; struct sctp_stream_reset_event sn_strreset_event; + struct sctp_assoc_reset_event sn_assocreset_event; + struct sctp_stream_change_event sn_strchange_event; }; /* Section 5.3.1 @@ -572,6 +599,10 @@ enum sctp_sn_type { #define SCTP_SENDER_DRY_EVENT SCTP_SENDER_DRY_EVENT SCTP_STREAM_RESET_EVENT, #define SCTP_STREAM_RESET_EVENT SCTP_STREAM_RESET_EVENT + SCTP_ASSOC_RESET_EVENT, +#define SCTP_ASSOC_RESET_EVENT SCTP_ASSOC_RESET_EVENT + SCTP_STREAM_CHANGE_EVENT, +#define SCTP_STREAM_CHANGE_EVENT SCTP_STREAM_CHANGE_EVENT }; /* Notification error codes used to fill up the error fields in some diff --git a/include/uapi/linux/snmp.h b/include/uapi/linux/snmp.h index 3b2bed7ca9a4..cec0e171d20c 100644 --- a/include/uapi/linux/snmp.h +++ b/include/uapi/linux/snmp.h @@ -177,7 +177,6 @@ enum LINUX_MIB_TIMEWAITED, /* TimeWaited */ LINUX_MIB_TIMEWAITRECYCLED, /* TimeWaitRecycled */ LINUX_MIB_TIMEWAITKILLED, /* TimeWaitKilled */ - LINUX_MIB_PAWSPASSIVEREJECTED, /* PAWSPassiveRejected */ LINUX_MIB_PAWSACTIVEREJECTED, /* PAWSActiveRejected */ LINUX_MIB_PAWSESTABREJECTED, /* PAWSEstabRejected */ LINUX_MIB_DELAYEDACKS, /* DelayedACKs */ diff --git a/include/uapi/linux/userfaultfd.h b/include/uapi/linux/userfaultfd.h index c055947c5c98..3b059530dac9 100644 --- a/include/uapi/linux/userfaultfd.h +++ b/include/uapi/linux/userfaultfd.h @@ -18,8 +18,7 @@ * means the userland is reading). */ #define UFFD_API ((__u64)0xAA) -#define UFFD_API_FEATURES (UFFD_FEATURE_EVENT_EXIT | \ - UFFD_FEATURE_EVENT_FORK | \ +#define UFFD_API_FEATURES (UFFD_FEATURE_EVENT_FORK | \ UFFD_FEATURE_EVENT_REMAP | \ UFFD_FEATURE_EVENT_REMOVE | \ UFFD_FEATURE_EVENT_UNMAP | \ @@ -113,7 +112,6 @@ struct uffd_msg { #define UFFD_EVENT_REMAP 0x14 #define UFFD_EVENT_REMOVE 0x15 #define UFFD_EVENT_UNMAP 0x16 -#define UFFD_EVENT_EXIT 0x17 /* flags for UFFD_EVENT_PAGEFAULT */ #define UFFD_PAGEFAULT_FLAG_WRITE (1<<0) /* If this was a write fault */ @@ -163,7 +161,6 @@ struct uffdio_api { #define UFFD_FEATURE_MISSING_HUGETLBFS (1<<4) #define UFFD_FEATURE_MISSING_SHMEM (1<<5) #define UFFD_FEATURE_EVENT_UNMAP (1<<6) -#define UFFD_FEATURE_EVENT_EXIT (1<<7) __u64 features; __u64 ioctls; diff --git a/include/xen/swiotlb-xen.h b/include/xen/swiotlb-xen.h index a0083be5d529..1f6d78f044b6 100644 --- a/include/xen/swiotlb-xen.h +++ b/include/xen/swiotlb-xen.h @@ -2,6 +2,7 @@ #define __LINUX_SWIOTLB_XEN_H #include <linux/dma-direction.h> +#include <linux/scatterlist.h> #include <linux/swiotlb.h> extern int xen_swiotlb_init(int verbose, bool early); @@ -55,4 +56,14 @@ xen_swiotlb_dma_supported(struct device *hwdev, u64 mask); extern int xen_swiotlb_set_dma_mask(struct device *dev, u64 dma_mask); + +extern int +xen_swiotlb_dma_mmap(struct device *dev, struct vm_area_struct *vma, + void *cpu_addr, dma_addr_t dma_addr, size_t size, + unsigned long attrs); + +extern int +xen_swiotlb_get_sgtable(struct device *dev, struct sg_table *sgt, + void *cpu_addr, dma_addr_t handle, size_t size, + unsigned long attrs); #endif /* __LINUX_SWIOTLB_XEN_H */ diff --git a/init/main.c b/init/main.c index eae2f15657c6..f9c9d9948203 100644 --- a/init/main.c +++ b/init/main.c @@ -882,7 +882,6 @@ static void __init do_basic_setup(void) do_ctors(); usermodehelper_enable(); do_initcalls(); - random_int_secret_init(); } static void __init do_pre_smp_initcalls(void) diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c index 6b6f41f0b211..bcf9955fac95 100644 --- a/kernel/bpf/arraymap.c +++ b/kernel/bpf/arraymap.c @@ -1,4 +1,5 @@ /* Copyright (c) 2011-2014 PLUMgrid, http://plumgrid.com + * Copyright (c) 2016,2017 Facebook * * This program is free software; you can redistribute it and/or * modify it under the terms of version 2 of the GNU General Public @@ -113,6 +114,33 @@ static void *array_map_lookup_elem(struct bpf_map *map, void *key) return array->value + array->elem_size * index; } +/* emit BPF instructions equivalent to C code of array_map_lookup_elem() */ +static u32 array_map_gen_lookup(struct bpf_map *map, struct bpf_insn *insn_buf) +{ + struct bpf_array *array = container_of(map, struct bpf_array, map); + struct bpf_insn *insn = insn_buf; + u32 elem_size = array->elem_size; + const int ret = BPF_REG_0; + const int map_ptr = BPF_REG_1; + const int index = BPF_REG_2; + + *insn++ = BPF_ALU64_IMM(BPF_ADD, map_ptr, offsetof(struct bpf_array, value)); + *insn++ = BPF_LDX_MEM(BPF_W, ret, index, 0); + *insn++ = BPF_JMP_IMM(BPF_JGE, ret, array->map.max_entries, + elem_size == 1 ? 2 : 3); + if (elem_size == 1) { + /* nop */ + } else if (is_power_of_2(elem_size)) { + *insn++ = BPF_ALU64_IMM(BPF_LSH, ret, ilog2(elem_size)); + } else { + *insn++ = BPF_ALU64_IMM(BPF_MUL, ret, elem_size); + } + *insn++ = BPF_ALU64_REG(BPF_ADD, ret, map_ptr); + *insn++ = BPF_JMP_IMM(BPF_JA, 0, 0, 1); + *insn++ = BPF_MOV64_IMM(ret, 0); + return insn - insn_buf; +} + /* Called from eBPF program */ static void *percpu_array_map_lookup_elem(struct bpf_map *map, void *key) { @@ -267,6 +295,7 @@ static const struct bpf_map_ops array_ops = { .map_lookup_elem = array_map_lookup_elem, .map_update_elem = array_map_update_elem, .map_delete_elem = array_map_delete_elem, + .map_gen_lookup = array_map_gen_lookup, }; static struct bpf_map_type_list array_type __ro_after_init = { diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c index 3ea87fb19a94..000153acb6d5 100644 --- a/kernel/bpf/hashtab.c +++ b/kernel/bpf/hashtab.c @@ -13,11 +13,12 @@ #include <linux/bpf.h> #include <linux/jhash.h> #include <linux/filter.h> +#include <linux/rculist_nulls.h> #include "percpu_freelist.h" #include "bpf_lru_list.h" struct bucket { - struct hlist_head head; + struct hlist_nulls_head head; raw_spinlock_t lock; }; @@ -44,9 +45,14 @@ enum extra_elem_state { /* each htab element is struct htab_elem + key + value */ struct htab_elem { union { - struct hlist_node hash_node; - struct bpf_htab *htab; - struct pcpu_freelist_node fnode; + struct hlist_nulls_node hash_node; + struct { + void *padding; + union { + struct bpf_htab *htab; + struct pcpu_freelist_node fnode; + }; + }; }; union { struct rcu_head rcu; @@ -162,7 +168,8 @@ skip_percpu_elems: offsetof(struct htab_elem, lru_node), htab->elem_size, htab->map.max_entries); else - pcpu_freelist_populate(&htab->freelist, htab->elems, + pcpu_freelist_populate(&htab->freelist, + htab->elems + offsetof(struct htab_elem, fnode), htab->elem_size, htab->map.max_entries); return 0; @@ -217,6 +224,11 @@ static struct bpf_map *htab_map_alloc(union bpf_attr *attr) int err, i; u64 cost; + BUILD_BUG_ON(offsetof(struct htab_elem, htab) != + offsetof(struct htab_elem, hash_node.pprev)); + BUILD_BUG_ON(offsetof(struct htab_elem, fnode.next) != + offsetof(struct htab_elem, hash_node.pprev)); + if (lru && !capable(CAP_SYS_ADMIN)) /* LRU implementation is much complicated than other * maps. Hence, limit to CAP_SYS_ADMIN for now. @@ -326,7 +338,7 @@ static struct bpf_map *htab_map_alloc(union bpf_attr *attr) goto free_htab; for (i = 0; i < htab->n_buckets; i++) { - INIT_HLIST_HEAD(&htab->buckets[i].head); + INIT_HLIST_NULLS_HEAD(&htab->buckets[i].head, i); raw_spin_lock_init(&htab->buckets[i].lock); } @@ -366,28 +378,56 @@ static inline struct bucket *__select_bucket(struct bpf_htab *htab, u32 hash) return &htab->buckets[hash & (htab->n_buckets - 1)]; } -static inline struct hlist_head *select_bucket(struct bpf_htab *htab, u32 hash) +static inline struct hlist_nulls_head *select_bucket(struct bpf_htab *htab, u32 hash) { return &__select_bucket(htab, hash)->head; } -static struct htab_elem *lookup_elem_raw(struct hlist_head *head, u32 hash, +/* this lookup function can only be called with bucket lock taken */ +static struct htab_elem *lookup_elem_raw(struct hlist_nulls_head *head, u32 hash, void *key, u32 key_size) { + struct hlist_nulls_node *n; struct htab_elem *l; - hlist_for_each_entry_rcu(l, head, hash_node) + hlist_nulls_for_each_entry_rcu(l, n, head, hash_node) if (l->hash == hash && !memcmp(&l->key, key, key_size)) return l; return NULL; } -/* Called from syscall or from eBPF program */ +/* can be called without bucket lock. it will repeat the loop in + * the unlikely event when elements moved from one bucket into another + * while link list is being walked + */ +static struct htab_elem *lookup_nulls_elem_raw(struct hlist_nulls_head *head, + u32 hash, void *key, + u32 key_size, u32 n_buckets) +{ + struct hlist_nulls_node *n; + struct htab_elem *l; + +again: + hlist_nulls_for_each_entry_rcu(l, n, head, hash_node) + if (l->hash == hash && !memcmp(&l->key, key, key_size)) + return l; + + if (unlikely(get_nulls_value(n) != (hash & (n_buckets - 1)))) + goto again; + + return NULL; +} + +/* Called from syscall or from eBPF program directly, so + * arguments have to match bpf_map_lookup_elem() exactly. + * The return value is adjusted by BPF instructions + * in htab_map_gen_lookup(). + */ static void *__htab_map_lookup_elem(struct bpf_map *map, void *key) { struct bpf_htab *htab = container_of(map, struct bpf_htab, map); - struct hlist_head *head; + struct hlist_nulls_head *head; struct htab_elem *l; u32 hash, key_size; @@ -400,7 +440,7 @@ static void *__htab_map_lookup_elem(struct bpf_map *map, void *key) head = select_bucket(htab, hash); - l = lookup_elem_raw(head, hash, key, key_size); + l = lookup_nulls_elem_raw(head, hash, key, key_size, htab->n_buckets); return l; } @@ -415,6 +455,30 @@ static void *htab_map_lookup_elem(struct bpf_map *map, void *key) return NULL; } +/* inline bpf_map_lookup_elem() call. + * Instead of: + * bpf_prog + * bpf_map_lookup_elem + * map->ops->map_lookup_elem + * htab_map_lookup_elem + * __htab_map_lookup_elem + * do: + * bpf_prog + * __htab_map_lookup_elem + */ +static u32 htab_map_gen_lookup(struct bpf_map *map, struct bpf_insn *insn_buf) +{ + struct bpf_insn *insn = insn_buf; + const int ret = BPF_REG_0; + + *insn++ = BPF_EMIT_CALL((u64 (*)(u64, u64, u64, u64, u64))__htab_map_lookup_elem); + *insn++ = BPF_JMP_IMM(BPF_JEQ, ret, 0, 1); + *insn++ = BPF_ALU64_IMM(BPF_ADD, ret, + offsetof(struct htab_elem, key) + + round_up(map->key_size, 8)); + return insn - insn_buf; +} + static void *htab_lru_map_lookup_elem(struct bpf_map *map, void *key) { struct htab_elem *l = __htab_map_lookup_elem(map, key); @@ -433,8 +497,9 @@ static void *htab_lru_map_lookup_elem(struct bpf_map *map, void *key) static bool htab_lru_map_delete_node(void *arg, struct bpf_lru_node *node) { struct bpf_htab *htab = (struct bpf_htab *)arg; - struct htab_elem *l, *tgt_l; - struct hlist_head *head; + struct htab_elem *l = NULL, *tgt_l; + struct hlist_nulls_head *head; + struct hlist_nulls_node *n; unsigned long flags; struct bucket *b; @@ -444,9 +509,9 @@ static bool htab_lru_map_delete_node(void *arg, struct bpf_lru_node *node) raw_spin_lock_irqsave(&b->lock, flags); - hlist_for_each_entry_rcu(l, head, hash_node) + hlist_nulls_for_each_entry_rcu(l, n, head, hash_node) if (l == tgt_l) { - hlist_del_rcu(&l->hash_node); + hlist_nulls_del_rcu(&l->hash_node); break; } @@ -459,7 +524,7 @@ static bool htab_lru_map_delete_node(void *arg, struct bpf_lru_node *node) static int htab_map_get_next_key(struct bpf_map *map, void *key, void *next_key) { struct bpf_htab *htab = container_of(map, struct bpf_htab, map); - struct hlist_head *head; + struct hlist_nulls_head *head; struct htab_elem *l, *next_l; u32 hash, key_size; int i; @@ -473,7 +538,7 @@ static int htab_map_get_next_key(struct bpf_map *map, void *key, void *next_key) head = select_bucket(htab, hash); /* lookup the key */ - l = lookup_elem_raw(head, hash, key, key_size); + l = lookup_nulls_elem_raw(head, hash, key, key_size, htab->n_buckets); if (!l) { i = 0; @@ -481,7 +546,7 @@ static int htab_map_get_next_key(struct bpf_map *map, void *key, void *next_key) } /* key was found, get next key in the same bucket */ - next_l = hlist_entry_safe(rcu_dereference_raw(hlist_next_rcu(&l->hash_node)), + next_l = hlist_nulls_entry_safe(rcu_dereference_raw(hlist_nulls_next_rcu(&l->hash_node)), struct htab_elem, hash_node); if (next_l) { @@ -500,7 +565,7 @@ find_first_elem: head = select_bucket(htab, i); /* pick first element in the bucket */ - next_l = hlist_entry_safe(rcu_dereference_raw(hlist_first_rcu(head)), + next_l = hlist_nulls_entry_safe(rcu_dereference_raw(hlist_nulls_first_rcu(head)), struct htab_elem, hash_node); if (next_l) { /* if it's not empty, just return it */ @@ -582,9 +647,13 @@ static struct htab_elem *alloc_htab_elem(struct bpf_htab *htab, void *key, int err = 0; if (prealloc) { - l_new = (struct htab_elem *)pcpu_freelist_pop(&htab->freelist); - if (!l_new) + struct pcpu_freelist_node *l; + + l = pcpu_freelist_pop(&htab->freelist); + if (!l) err = -E2BIG; + else + l_new = container_of(l, struct htab_elem, fnode); } else { if (atomic_inc_return(&htab->count) > htab->map.max_entries) { atomic_dec(&htab->count); @@ -661,7 +730,7 @@ static int htab_map_update_elem(struct bpf_map *map, void *key, void *value, { struct bpf_htab *htab = container_of(map, struct bpf_htab, map); struct htab_elem *l_new = NULL, *l_old; - struct hlist_head *head; + struct hlist_nulls_head *head; unsigned long flags; struct bucket *b; u32 key_size, hash; @@ -700,9 +769,9 @@ static int htab_map_update_elem(struct bpf_map *map, void *key, void *value, /* add new element to the head of the list, so that * concurrent search will find it before old elem */ - hlist_add_head_rcu(&l_new->hash_node, head); + hlist_nulls_add_head_rcu(&l_new->hash_node, head); if (l_old) { - hlist_del_rcu(&l_old->hash_node); + hlist_nulls_del_rcu(&l_old->hash_node); free_htab_elem(htab, l_old); } ret = 0; @@ -716,7 +785,7 @@ static int htab_lru_map_update_elem(struct bpf_map *map, void *key, void *value, { struct bpf_htab *htab = container_of(map, struct bpf_htab, map); struct htab_elem *l_new, *l_old = NULL; - struct hlist_head *head; + struct hlist_nulls_head *head; unsigned long flags; struct bucket *b; u32 key_size, hash; @@ -757,10 +826,10 @@ static int htab_lru_map_update_elem(struct bpf_map *map, void *key, void *value, /* add new element to the head of the list, so that * concurrent search will find it before old elem */ - hlist_add_head_rcu(&l_new->hash_node, head); + hlist_nulls_add_head_rcu(&l_new->hash_node, head); if (l_old) { bpf_lru_node_set_ref(&l_new->lru_node); - hlist_del_rcu(&l_old->hash_node); + hlist_nulls_del_rcu(&l_old->hash_node); } ret = 0; @@ -781,7 +850,7 @@ static int __htab_percpu_map_update_elem(struct bpf_map *map, void *key, { struct bpf_htab *htab = container_of(map, struct bpf_htab, map); struct htab_elem *l_new = NULL, *l_old; - struct hlist_head *head; + struct hlist_nulls_head *head; unsigned long flags; struct bucket *b; u32 key_size, hash; @@ -820,7 +889,7 @@ static int __htab_percpu_map_update_elem(struct bpf_map *map, void *key, ret = PTR_ERR(l_new); goto err; } - hlist_add_head_rcu(&l_new->hash_node, head); + hlist_nulls_add_head_rcu(&l_new->hash_node, head); } ret = 0; err: @@ -834,7 +903,7 @@ static int __htab_lru_percpu_map_update_elem(struct bpf_map *map, void *key, { struct bpf_htab *htab = container_of(map, struct bpf_htab, map); struct htab_elem *l_new = NULL, *l_old; - struct hlist_head *head; + struct hlist_nulls_head *head; unsigned long flags; struct bucket *b; u32 key_size, hash; @@ -882,7 +951,7 @@ static int __htab_lru_percpu_map_update_elem(struct bpf_map *map, void *key, } else { pcpu_copy_value(htab, htab_elem_get_ptr(l_new, key_size), value, onallcpus); - hlist_add_head_rcu(&l_new->hash_node, head); + hlist_nulls_add_head_rcu(&l_new->hash_node, head); l_new = NULL; } ret = 0; @@ -910,7 +979,7 @@ static int htab_lru_percpu_map_update_elem(struct bpf_map *map, void *key, static int htab_map_delete_elem(struct bpf_map *map, void *key) { struct bpf_htab *htab = container_of(map, struct bpf_htab, map); - struct hlist_head *head; + struct hlist_nulls_head *head; struct bucket *b; struct htab_elem *l; unsigned long flags; @@ -930,7 +999,7 @@ static int htab_map_delete_elem(struct bpf_map *map, void *key) l = lookup_elem_raw(head, hash, key, key_size); if (l) { - hlist_del_rcu(&l->hash_node); + hlist_nulls_del_rcu(&l->hash_node); free_htab_elem(htab, l); ret = 0; } @@ -942,7 +1011,7 @@ static int htab_map_delete_elem(struct bpf_map *map, void *key) static int htab_lru_map_delete_elem(struct bpf_map *map, void *key) { struct bpf_htab *htab = container_of(map, struct bpf_htab, map); - struct hlist_head *head; + struct hlist_nulls_head *head; struct bucket *b; struct htab_elem *l; unsigned long flags; @@ -962,7 +1031,7 @@ static int htab_lru_map_delete_elem(struct bpf_map *map, void *key) l = lookup_elem_raw(head, hash, key, key_size); if (l) { - hlist_del_rcu(&l->hash_node); + hlist_nulls_del_rcu(&l->hash_node); ret = 0; } @@ -977,12 +1046,12 @@ static void delete_all_elements(struct bpf_htab *htab) int i; for (i = 0; i < htab->n_buckets; i++) { - struct hlist_head *head = select_bucket(htab, i); - struct hlist_node *n; + struct hlist_nulls_head *head = select_bucket(htab, i); + struct hlist_nulls_node *n; struct htab_elem *l; - hlist_for_each_entry_safe(l, n, head, hash_node) { - hlist_del_rcu(&l->hash_node); + hlist_nulls_for_each_entry_safe(l, n, head, hash_node) { + hlist_nulls_del_rcu(&l->hash_node); if (l->state != HTAB_EXTRA_ELEM_USED) htab_elem_free(htab, l); } @@ -1021,6 +1090,7 @@ static const struct bpf_map_ops htab_ops = { .map_lookup_elem = htab_map_lookup_elem, .map_update_elem = htab_map_update_elem, .map_delete_elem = htab_map_delete_elem, + .map_gen_lookup = htab_map_gen_lookup, }; static struct bpf_map_type_list htab_type __ro_after_init = { diff --git a/kernel/bpf/lpm_trie.c b/kernel/bpf/lpm_trie.c index 8bfe0afaee10..b37bd9ab7f57 100644 --- a/kernel/bpf/lpm_trie.c +++ b/kernel/bpf/lpm_trie.c @@ -500,9 +500,15 @@ unlock: raw_spin_unlock(&trie->lock); } +static int trie_get_next_key(struct bpf_map *map, void *key, void *next_key) +{ + return -ENOTSUPP; +} + static const struct bpf_map_ops trie_ops = { .map_alloc = trie_alloc, .map_free = trie_free, + .map_get_next_key = trie_get_next_key, .map_lookup_elem = trie_lookup_elem, .map_update_elem = trie_update_elem, .map_delete_elem = trie_delete_elem, diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 7af0dcc5d755..48c914b983bd 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -586,59 +586,6 @@ void bpf_register_prog_type(struct bpf_prog_type_list *tl) list_add(&tl->list_node, &bpf_prog_types); } -/* fixup insn->imm field of bpf_call instructions: - * if (insn->imm == BPF_FUNC_map_lookup_elem) - * insn->imm = bpf_map_lookup_elem - __bpf_call_base; - * else if (insn->imm == BPF_FUNC_map_update_elem) - * insn->imm = bpf_map_update_elem - __bpf_call_base; - * else ... - * - * this function is called after eBPF program passed verification - */ -static void fixup_bpf_calls(struct bpf_prog *prog) -{ - const struct bpf_func_proto *fn; - int i; - - for (i = 0; i < prog->len; i++) { - struct bpf_insn *insn = &prog->insnsi[i]; - - if (insn->code == (BPF_JMP | BPF_CALL)) { - /* we reach here when program has bpf_call instructions - * and it passed bpf_check(), means that - * ops->get_func_proto must have been supplied, check it - */ - BUG_ON(!prog->aux->ops->get_func_proto); - - if (insn->imm == BPF_FUNC_get_route_realm) - prog->dst_needed = 1; - if (insn->imm == BPF_FUNC_get_prandom_u32) - bpf_user_rnd_init_once(); - if (insn->imm == BPF_FUNC_xdp_adjust_head) - prog->xdp_adjust_head = 1; - if (insn->imm == BPF_FUNC_tail_call) { - /* mark bpf_tail_call as different opcode - * to avoid conditional branch in - * interpeter for every normal call - * and to prevent accidental JITing by - * JIT compiler that doesn't support - * bpf_tail_call yet - */ - insn->imm = 0; - insn->code |= BPF_X; - continue; - } - - fn = prog->aux->ops->get_func_proto(insn->imm); - /* all functions that have prototype and verifier allowed - * programs to call them, must be real in-kernel functions - */ - BUG_ON(!fn->func); - insn->imm = fn->func - __bpf_call_base; - } - } -} - /* drop refcnt on maps used by eBPF program and free auxilary data */ static void free_used_maps(struct bpf_prog_aux *aux) { @@ -892,9 +839,6 @@ static int bpf_prog_load(union bpf_attr *attr) if (err < 0) goto free_used_maps; - /* fixup BPF_CALL->imm field */ - fixup_bpf_calls(prog); - /* eBPF program is ready to be JITed */ prog = bpf_prog_select_runtime(prog, &err); if (err < 0) diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 796b68d00119..90bf46787603 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -1273,7 +1273,7 @@ static void clear_all_pkt_pointers(struct bpf_verifier_env *env) } } -static int check_call(struct bpf_verifier_env *env, int func_id) +static int check_call(struct bpf_verifier_env *env, int func_id, int insn_idx) { struct bpf_verifier_state *state = &env->cur_state; const struct bpf_func_proto *fn = NULL; @@ -1369,6 +1369,7 @@ static int check_call(struct bpf_verifier_env *env, int func_id) } regs[BPF_REG_0].map_ptr = meta.map_ptr; regs[BPF_REG_0].id = ++env->id_gen; + env->insn_aux_data[insn_idx].map_ptr = meta.map_ptr; } else { verbose("unknown return type %d of func %s#%d\n", fn->ret_type, func_id_name(func_id), func_id); @@ -2940,7 +2941,7 @@ static int do_check(struct bpf_verifier_env *env) return -EINVAL; } - err = check_call(env, insn->imm); + err = check_call(env, insn->imm, insn_idx); if (err) return err; @@ -3162,6 +3163,41 @@ static void convert_pseudo_ld_imm64(struct bpf_verifier_env *env) insn->src_reg = 0; } +/* single env->prog->insni[off] instruction was replaced with the range + * insni[off, off + cnt). Adjust corresponding insn_aux_data by copying + * [0, off) and [off, end) to new locations, so the patched range stays zero + */ +static int adjust_insn_aux_data(struct bpf_verifier_env *env, u32 prog_len, + u32 off, u32 cnt) +{ + struct bpf_insn_aux_data *new_data, *old_data = env->insn_aux_data; + + if (cnt == 1) + return 0; + new_data = vzalloc(sizeof(struct bpf_insn_aux_data) * prog_len); + if (!new_data) + return -ENOMEM; + memcpy(new_data, old_data, sizeof(struct bpf_insn_aux_data) * off); + memcpy(new_data + off + cnt - 1, old_data + off, + sizeof(struct bpf_insn_aux_data) * (prog_len - off - cnt + 1)); + env->insn_aux_data = new_data; + vfree(old_data); + return 0; +} + +static struct bpf_prog *bpf_patch_insn_data(struct bpf_verifier_env *env, u32 off, + const struct bpf_insn *patch, u32 len) +{ + struct bpf_prog *new_prog; + + new_prog = bpf_patch_insn_single(env->prog, off, patch, len); + if (!new_prog) + return NULL; + if (adjust_insn_aux_data(env, new_prog->len, off, len)) + return NULL; + return new_prog; +} + /* convert load instructions that access fields of 'struct __sk_buff' * into sequence of instructions that access fields of 'struct sk_buff' */ @@ -3181,10 +3217,10 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env) verbose("bpf verifier is misconfigured\n"); return -EINVAL; } else if (cnt) { - new_prog = bpf_patch_insn_single(env->prog, 0, - insn_buf, cnt); + new_prog = bpf_patch_insn_data(env, 0, insn_buf, cnt); if (!new_prog) return -ENOMEM; + env->prog = new_prog; delta += cnt - 1; } @@ -3209,7 +3245,7 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env) else continue; - if (env->insn_aux_data[i].ptr_type != PTR_TO_CTX) + if (env->insn_aux_data[i + delta].ptr_type != PTR_TO_CTX) continue; cnt = ops->convert_ctx_access(type, insn, insn_buf, env->prog); @@ -3218,8 +3254,7 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env) return -EINVAL; } - new_prog = bpf_patch_insn_single(env->prog, i + delta, insn_buf, - cnt); + new_prog = bpf_patch_insn_data(env, i + delta, insn_buf, cnt); if (!new_prog) return -ENOMEM; @@ -3233,6 +3268,83 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env) return 0; } +/* fixup insn->imm field of bpf_call instructions + * and inline eligible helpers as explicit sequence of BPF instructions + * + * this function is called after eBPF program passed verification + */ +static int fixup_bpf_calls(struct bpf_verifier_env *env) +{ + struct bpf_prog *prog = env->prog; + struct bpf_insn *insn = prog->insnsi; + const struct bpf_func_proto *fn; + const int insn_cnt = prog->len; + struct bpf_insn insn_buf[16]; + struct bpf_prog *new_prog; + struct bpf_map *map_ptr; + int i, cnt, delta = 0; + + for (i = 0; i < insn_cnt; i++, insn++) { + if (insn->code != (BPF_JMP | BPF_CALL)) + continue; + + if (insn->imm == BPF_FUNC_get_route_realm) + prog->dst_needed = 1; + if (insn->imm == BPF_FUNC_get_prandom_u32) + bpf_user_rnd_init_once(); + if (insn->imm == BPF_FUNC_xdp_adjust_head) + prog->xdp_adjust_head = 1; + if (insn->imm == BPF_FUNC_tail_call) { + /* mark bpf_tail_call as different opcode to avoid + * conditional branch in the interpeter for every normal + * call and to prevent accidental JITing by JIT compiler + * that doesn't support bpf_tail_call yet + */ + insn->imm = 0; + insn->code |= BPF_X; + continue; + } + + if (ebpf_jit_enabled() && insn->imm == BPF_FUNC_map_lookup_elem) { + map_ptr = env->insn_aux_data[i + delta].map_ptr; + if (!map_ptr->ops->map_gen_lookup) + goto patch_call_imm; + + cnt = map_ptr->ops->map_gen_lookup(map_ptr, insn_buf); + if (cnt == 0 || cnt >= ARRAY_SIZE(insn_buf)) { + verbose("bpf verifier is misconfigured\n"); + return -EINVAL; + } + + new_prog = bpf_patch_insn_data(env, i + delta, insn_buf, + cnt); + if (!new_prog) + return -ENOMEM; + + delta += cnt - 1; + + /* keep walking new program and skip insns we just inserted */ + env->prog = prog = new_prog; + insn = new_prog->insnsi + i + delta; + continue; + } + +patch_call_imm: + fn = prog->aux->ops->get_func_proto(insn->imm); + /* all functions that have prototype and verifier allowed + * programs to call them, must be real in-kernel functions + */ + if (!fn->func) { + verbose("kernel subsystem misconfigured func %s#%d\n", + func_id_name(insn->imm), insn->imm); + return -EFAULT; + } + insn->imm = fn->func - __bpf_call_base; + } + + return 0; +} + static void free_states(struct bpf_verifier_env *env) { struct bpf_verifier_state_list *sl, *sln; @@ -3328,6 +3440,9 @@ skip_full_check: /* program is valid, convert *(u32*)(ctx + off) accesses */ ret = convert_ctx_accesses(env); + if (ret == 0) + ret = fixup_bpf_calls(env); + if (log_level && log_len >= log_size - 1) { BUG_ON(log_len >= log_size); /* verifier log exceeded user supplied buffer */ diff --git a/kernel/cgroup/cgroup-v1.c b/kernel/cgroup/cgroup-v1.c index 56eba9caa632..1dc22f6b49f5 100644 --- a/kernel/cgroup/cgroup-v1.c +++ b/kernel/cgroup/cgroup-v1.c @@ -1329,7 +1329,7 @@ static int cgroup_css_links_read(struct seq_file *seq, void *v) struct task_struct *task; int count = 0; - seq_printf(seq, "css_set %p\n", cset); + seq_printf(seq, "css_set %pK\n", cset); list_for_each_entry(task, &cset->tasks, cg_list) { if (count++ > MAX_TASKS_SHOWN_PER_CSS) diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index 0125589c7428..48851327a15e 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -2669,7 +2669,7 @@ static bool css_visible(struct cgroup_subsys_state *css) * * Returns 0 on success, -errno on failure. On failure, csses which have * been processed already aren't cleaned up. The caller is responsible for - * cleaning up with cgroup_apply_control_disble(). + * cleaning up with cgroup_apply_control_disable(). */ static int cgroup_apply_control_enable(struct cgroup *cgrp) { diff --git a/kernel/cgroup/pids.c b/kernel/cgroup/pids.c index e756dae49300..2237201d66d5 100644 --- a/kernel/cgroup/pids.c +++ b/kernel/cgroup/pids.c @@ -229,7 +229,7 @@ static int pids_can_fork(struct task_struct *task) /* Only log the first time events_limit is incremented. */ if (atomic64_inc_return(&pids->events_limit) == 1) { pr_info("cgroup: fork rejected by pids controller in "); - pr_cont_cgroup_path(task_cgroup(current, pids_cgrp_id)); + pr_cont_cgroup_path(css->cgroup); pr_cont("\n"); } cgroup_file_notify(&pids->events_file); diff --git a/kernel/events/core.c b/kernel/events/core.c index 6f41548f2e32..a17ed56c8ce1 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -998,7 +998,7 @@ list_update_cgroup_event(struct perf_event *event, */ #define PERF_CPU_HRTIMER (1000 / HZ) /* - * function must be called with interrupts disbled + * function must be called with interrupts disabled */ static enum hrtimer_restart perf_mux_hrtimer_handler(struct hrtimer *hr) { diff --git a/kernel/exit.c b/kernel/exit.c index e126ebf2400c..516acdb0e0ec 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -554,7 +554,6 @@ static void exit_mm(void) enter_lazy_tlb(mm, current); task_unlock(current); mm_update_next_owner(mm); - userfaultfd_exit(mm); mmput(mm); if (test_thread_flag(TIF_MEMDIE)) exit_oom_victim(); diff --git a/kernel/kexec_file.c b/kernel/kexec_file.c index b56a558e406d..b118735fea9d 100644 --- a/kernel/kexec_file.c +++ b/kernel/kexec_file.c @@ -614,13 +614,13 @@ static int kexec_calculate_store_digests(struct kimage *image) ret = crypto_shash_final(desc, digest); if (ret) goto out_free_digest; - ret = kexec_purgatory_get_set_symbol(image, "sha_regions", - sha_regions, sha_region_sz, 0); + ret = kexec_purgatory_get_set_symbol(image, "purgatory_sha_regions", + sha_regions, sha_region_sz, 0); if (ret) goto out_free_digest; - ret = kexec_purgatory_get_set_symbol(image, "sha256_digest", - digest, SHA256_DIGEST_SIZE, 0); + ret = kexec_purgatory_get_set_symbol(image, "purgatory_sha256_digest", + digest, SHA256_DIGEST_SIZE, 0); if (ret) goto out_free_digest; } diff --git a/kernel/kexec_internal.h b/kernel/kexec_internal.h index 4cef7e4706b0..799a8a452187 100644 --- a/kernel/kexec_internal.h +++ b/kernel/kexec_internal.h @@ -15,11 +15,7 @@ int kimage_is_destination_range(struct kimage *image, extern struct mutex kexec_mutex; #ifdef CONFIG_KEXEC_FILE -struct kexec_sha_region { - unsigned long start; - unsigned long len; -}; - +#include <linux/purgatory.h> void kimage_file_post_load_cleanup(struct kimage *image); #else /* CONFIG_KEXEC_FILE */ static inline void kimage_file_post_load_cleanup(struct kimage *image) { } diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c index 12e38c213b70..a95e5d1f4a9c 100644 --- a/kernel/locking/lockdep.c +++ b/kernel/locking/lockdep.c @@ -3262,10 +3262,17 @@ static int __lock_acquire(struct lockdep_map *lock, unsigned int subclass, if (depth) { hlock = curr->held_locks + depth - 1; if (hlock->class_idx == class_idx && nest_lock) { - if (hlock->references) + if (hlock->references) { + /* + * Check: unsigned int references:12, overflow. + */ + if (DEBUG_LOCKS_WARN_ON(hlock->references == (1 << 12)-1)) + return 0; + hlock->references++; - else + } else { hlock->references = 2; + } return 1; } diff --git a/kernel/locking/test-ww_mutex.c b/kernel/locking/test-ww_mutex.c index da6c9a34f62f..6b7abb334ca6 100644 --- a/kernel/locking/test-ww_mutex.c +++ b/kernel/locking/test-ww_mutex.c @@ -50,7 +50,7 @@ static void test_mutex_work(struct work_struct *work) if (mtx->flags & TEST_MTX_TRY) { while (!ww_mutex_trylock(&mtx->mutex)) - cpu_relax(); + cond_resched(); } else { ww_mutex_lock(&mtx->mutex, NULL); } @@ -88,7 +88,7 @@ static int __test_mutex(unsigned int flags) ret = -EINVAL; break; } - cpu_relax(); + cond_resched(); } while (time_before(jiffies, timeout)); } else { ret = wait_for_completion_timeout(&mtx.done, TIMEOUT); @@ -627,7 +627,7 @@ static int __init test_ww_mutex_init(void) if (ret) return ret; - ret = stress(4096, hweight32(STRESS_ALL)*ncpus, 1<<12, STRESS_ALL); + ret = stress(4095, hweight32(STRESS_ALL)*ncpus, 1<<12, STRESS_ALL); if (ret) return ret; diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 956383844116..3b31fc05a0f1 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -3287,10 +3287,15 @@ pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf) struct task_struct *p; /* - * Optimization: we know that if all tasks are in - * the fair class we can call that function directly: + * Optimization: we know that if all tasks are in the fair class we can + * call that function directly, but only if the @prev task wasn't of a + * higher scheduling class, because otherwise those loose the + * opportunity to pull in more work from other CPUs. */ - if (likely(rq->nr_running == rq->cfs.h_nr_running)) { + if (likely((prev->sched_class == &idle_sched_class || + prev->sched_class == &fair_sched_class) && + rq->nr_running == rq->cfs.h_nr_running)) { + p = fair_sched_class.pick_next_task(rq, prev, rf); if (unlikely(p == RETRY_TASK)) goto again; diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c index 8f8de3d4d6b7..cd7cd489f739 100644 --- a/kernel/sched/cpufreq_schedutil.c +++ b/kernel/sched/cpufreq_schedutil.c @@ -36,6 +36,7 @@ struct sugov_policy { u64 last_freq_update_time; s64 freq_update_delay_ns; unsigned int next_freq; + unsigned int cached_raw_freq; /* The next fields are only needed if fast switch cannot be used. */ struct irq_work irq_work; @@ -52,7 +53,6 @@ struct sugov_cpu { struct update_util_data update_util; struct sugov_policy *sg_policy; - unsigned int cached_raw_freq; unsigned long iowait_boost; unsigned long iowait_boost_max; u64 last_update; @@ -116,7 +116,7 @@ static void sugov_update_commit(struct sugov_policy *sg_policy, u64 time, /** * get_next_freq - Compute a new frequency for a given cpufreq policy. - * @sg_cpu: schedutil cpu object to compute the new frequency for. + * @sg_policy: schedutil policy object to compute the new frequency for. * @util: Current CPU utilization. * @max: CPU capacity. * @@ -136,19 +136,18 @@ static void sugov_update_commit(struct sugov_policy *sg_policy, u64 time, * next_freq (as calculated above) is returned, subject to policy min/max and * cpufreq driver limitations. */ -static unsigned int get_next_freq(struct sugov_cpu *sg_cpu, unsigned long util, - unsigned long max) +static unsigned int get_next_freq(struct sugov_policy *sg_policy, + unsigned long util, unsigned long max) { - struct sugov_policy *sg_policy = sg_cpu->sg_policy; struct cpufreq_policy *policy = sg_policy->policy; unsigned int freq = arch_scale_freq_invariant() ? policy->cpuinfo.max_freq : policy->cur; freq = (freq + (freq >> 2)) * util / max; - if (freq == sg_cpu->cached_raw_freq && sg_policy->next_freq != UINT_MAX) + if (freq == sg_policy->cached_raw_freq && sg_policy->next_freq != UINT_MAX) return sg_policy->next_freq; - sg_cpu->cached_raw_freq = freq; + sg_policy->cached_raw_freq = freq; return cpufreq_driver_resolve_freq(policy, freq); } @@ -213,7 +212,7 @@ static void sugov_update_single(struct update_util_data *hook, u64 time, } else { sugov_get_util(&util, &max); sugov_iowait_boost(sg_cpu, &util, &max); - next_f = get_next_freq(sg_cpu, util, max); + next_f = get_next_freq(sg_policy, util, max); } sugov_update_commit(sg_policy, time, next_f); } @@ -267,7 +266,7 @@ static unsigned int sugov_next_freq_shared(struct sugov_cpu *sg_cpu, sugov_iowait_boost(j_sg_cpu, &util, &max); } - return get_next_freq(sg_cpu, util, max); + return get_next_freq(sg_policy, util, max); } static void sugov_update_shared(struct update_util_data *hook, u64 time, @@ -580,6 +579,7 @@ static int sugov_start(struct cpufreq_policy *policy) sg_policy->next_freq = UINT_MAX; sg_policy->work_in_progress = false; sg_policy->need_freq_update = false; + sg_policy->cached_raw_freq = 0; for_each_cpu(cpu, policy->cpus) { struct sugov_cpu *sg_cpu = &per_cpu(sugov_cpu, cpu); @@ -590,7 +590,6 @@ static int sugov_start(struct cpufreq_policy *policy) sg_cpu->max = 0; sg_cpu->flags = SCHED_CPUFREQ_RT; sg_cpu->last_update = 0; - sg_cpu->cached_raw_freq = 0; sg_cpu->iowait_boost = 0; sg_cpu->iowait_boost_max = policy->cpuinfo.max_freq; cpufreq_add_update_util_hook(cpu, &sg_cpu->update_util, diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 3e88b35ac157..dea138964b91 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -5799,7 +5799,7 @@ static int select_idle_cpu(struct task_struct *p, struct sched_domain *sd, int t * Due to large variance we need a large fuzz factor; hackbench in * particularly is sensitive here. */ - if ((avg_idle / 512) < avg_cost) + if (sched_feat(SIS_AVG_CPU) && (avg_idle / 512) < avg_cost) return -1; time = local_clock(); diff --git a/kernel/sched/features.h b/kernel/sched/features.h index 69631fa46c2f..1b3c8189b286 100644 --- a/kernel/sched/features.h +++ b/kernel/sched/features.h @@ -51,6 +51,11 @@ SCHED_FEAT(NONTASK_CAPACITY, true) */ SCHED_FEAT(TTWU_QUEUE, true) +/* + * When doing wakeups, attempt to limit superfluous scans of the LLC domain. + */ +SCHED_FEAT(SIS_AVG_CPU, false) + #ifdef HAVE_RT_PUSH_IPI /* * In order to avoid a thundering herd attack of CPUs that are diff --git a/kernel/sched/wait.c b/kernel/sched/wait.c index 4d2ea6f25568..b8c84c6dee64 100644 --- a/kernel/sched/wait.c +++ b/kernel/sched/wait.c @@ -242,6 +242,45 @@ long prepare_to_wait_event(wait_queue_head_t *q, wait_queue_t *wait, int state) } EXPORT_SYMBOL(prepare_to_wait_event); +/* + * Note! These two wait functions are entered with the + * wait-queue lock held (and interrupts off in the _irq + * case), so there is no race with testing the wakeup + * condition in the caller before they add the wait + * entry to the wake queue. + */ +int do_wait_intr(wait_queue_head_t *wq, wait_queue_t *wait) +{ + if (likely(list_empty(&wait->task_list))) + __add_wait_queue_tail(wq, wait); + + set_current_state(TASK_INTERRUPTIBLE); + if (signal_pending(current)) + return -ERESTARTSYS; + + spin_unlock(&wq->lock); + schedule(); + spin_lock(&wq->lock); + return 0; +} +EXPORT_SYMBOL(do_wait_intr); + +int do_wait_intr_irq(wait_queue_head_t *wq, wait_queue_t *wait) +{ + if (likely(list_empty(&wait->task_list))) + __add_wait_queue_tail(wq, wait); + + set_current_state(TASK_INTERRUPTIBLE); + if (signal_pending(current)) + return -ERESTARTSYS; + + spin_unlock_irq(&wq->lock); + schedule(); + spin_lock_irq(&wq->lock); + return 0; +} +EXPORT_SYMBOL(do_wait_intr_irq); + /** * finish_wait - clean up after waiting in a queue * @q: waitqueue waited on diff --git a/kernel/time/jiffies.c b/kernel/time/jiffies.c index 7906b3f0c41a..497719127bf9 100644 --- a/kernel/time/jiffies.c +++ b/kernel/time/jiffies.c @@ -125,7 +125,7 @@ int register_refined_jiffies(long cycles_per_second) shift_hz += cycles_per_tick/2; do_div(shift_hz, cycles_per_tick); /* Calculate nsec_per_tick using shift_hz */ - nsec_per_tick = (u64)TICK_NSEC << 8; + nsec_per_tick = (u64)NSEC_PER_SEC << 8; nsec_per_tick += (u32)shift_hz/2; do_div(nsec_per_tick, (u32)shift_hz); diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig index d5038005eb5d..d4a06e714645 100644 --- a/kernel/trace/Kconfig +++ b/kernel/trace/Kconfig @@ -429,7 +429,7 @@ config BLK_DEV_IO_TRACE If unsure, say N. -config KPROBE_EVENT +config KPROBE_EVENTS depends on KPROBES depends on HAVE_REGS_AND_STACK_ACCESS_API bool "Enable kprobes-based dynamic events" @@ -447,7 +447,7 @@ config KPROBE_EVENT This option is also required by perf-probe subcommand of perf tools. If you want to use perf tools, this option is strongly recommended. -config UPROBE_EVENT +config UPROBE_EVENTS bool "Enable uprobes-based dynamic events" depends on ARCH_SUPPORTS_UPROBES depends on MMU @@ -466,7 +466,7 @@ config UPROBE_EVENT config BPF_EVENTS depends on BPF_SYSCALL - depends on (KPROBE_EVENT || UPROBE_EVENT) && PERF_EVENTS + depends on (KPROBE_EVENTS || UPROBE_EVENTS) && PERF_EVENTS bool default y help diff --git a/kernel/trace/Makefile b/kernel/trace/Makefile index e57980845549..90f2701d92a7 100644 --- a/kernel/trace/Makefile +++ b/kernel/trace/Makefile @@ -57,7 +57,7 @@ obj-$(CONFIG_EVENT_TRACING) += trace_events_filter.o obj-$(CONFIG_EVENT_TRACING) += trace_events_trigger.o obj-$(CONFIG_HIST_TRIGGERS) += trace_events_hist.o obj-$(CONFIG_BPF_EVENTS) += bpf_trace.o -obj-$(CONFIG_KPROBE_EVENT) += trace_kprobe.o +obj-$(CONFIG_KPROBE_EVENTS) += trace_kprobe.o obj-$(CONFIG_TRACEPOINTS) += power-traces.o ifeq ($(CONFIG_PM),y) obj-$(CONFIG_TRACEPOINTS) += rpm-traces.o @@ -66,7 +66,7 @@ ifeq ($(CONFIG_TRACING),y) obj-$(CONFIG_KGDB_KDB) += trace_kdb.o endif obj-$(CONFIG_PROBE_EVENTS) += trace_probe.o -obj-$(CONFIG_UPROBE_EVENT) += trace_uprobe.o +obj-$(CONFIG_UPROBE_EVENTS) += trace_uprobe.o obj-$(CONFIG_TRACEPOINT_BENCHMARK) += trace_benchmark.o diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 0d1597c9ee30..b9691ee8f6c1 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -4416,16 +4416,24 @@ static int __init set_graph_notrace_function(char *str) } __setup("ftrace_graph_notrace=", set_graph_notrace_function); +static int __init set_graph_max_depth_function(char *str) +{ + if (!str) + return 0; + fgraph_max_depth = simple_strtoul(str, NULL, 0); + return 1; +} +__setup("ftrace_graph_max_depth=", set_graph_max_depth_function); + static void __init set_ftrace_early_graph(char *buf, int enable) { int ret; char *func; struct ftrace_hash *hash; - if (enable) - hash = ftrace_graph_hash; - else - hash = ftrace_graph_notrace_hash; + hash = alloc_ftrace_hash(FTRACE_HASH_DEFAULT_BITS); + if (WARN_ON(!hash)) + return; while (buf) { func = strsep(&buf, ","); @@ -4435,6 +4443,11 @@ static void __init set_ftrace_early_graph(char *buf, int enable) printk(KERN_DEBUG "ftrace: function %s not " "traceable\n", func); } + + if (enable) + ftrace_graph_hash = hash; + else + ftrace_graph_notrace_hash = hash; } #endif /* CONFIG_FUNCTION_GRAPH_TRACER */ @@ -5488,7 +5501,7 @@ static void ftrace_ops_assist_func(unsigned long ip, unsigned long parent_ip, * Normally the mcount trampoline will call the ops->func, but there * are times that it should not. For example, if the ops does not * have its own recursion protection, then it should call the - * ftrace_ops_recurs_func() instead. + * ftrace_ops_assist_func() instead. * * Returns the function that the trampoline should call for @ops. */ diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 707445ceb7ef..f35109514a01 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -4341,22 +4341,22 @@ static const char readme_msg[] = "\t\t\t traces\n" #endif #endif /* CONFIG_STACK_TRACER */ -#ifdef CONFIG_KPROBE_EVENT +#ifdef CONFIG_KPROBE_EVENTS " kprobe_events\t\t- Add/remove/show the kernel dynamic events\n" "\t\t\t Write into this file to define/undefine new trace events.\n" #endif -#ifdef CONFIG_UPROBE_EVENT +#ifdef CONFIG_UPROBE_EVENTS " uprobe_events\t\t- Add/remove/show the userspace dynamic events\n" "\t\t\t Write into this file to define/undefine new trace events.\n" #endif -#if defined(CONFIG_KPROBE_EVENT) || defined(CONFIG_UPROBE_EVENT) +#if defined(CONFIG_KPROBE_EVENTS) || defined(CONFIG_UPROBE_EVENTS) "\t accepts: event-definitions (one definition per line)\n" "\t Format: p|r[:[<group>/]<event>] <place> [<args>]\n" "\t -:[<group>/]<event>\n" -#ifdef CONFIG_KPROBE_EVENT +#ifdef CONFIG_KPROBE_EVENTS "\t place: [<module>:]<symbol>[+<offset>]|<memaddr>\n" #endif -#ifdef CONFIG_UPROBE_EVENT +#ifdef CONFIG_UPROBE_EVENTS "\t place: <path>:<offset>\n" #endif "\t args: <name>=fetcharg[:type]\n" diff --git a/kernel/trace/trace_probe.h b/kernel/trace/trace_probe.h index 0c0ae54d44c6..903273c93e61 100644 --- a/kernel/trace/trace_probe.h +++ b/kernel/trace/trace_probe.h @@ -248,7 +248,7 @@ ASSIGN_FETCH_FUNC(file_offset, ftype), \ #define FETCH_TYPE_STRING 0 #define FETCH_TYPE_STRSIZE 1 -#ifdef CONFIG_KPROBE_EVENT +#ifdef CONFIG_KPROBE_EVENTS struct symbol_cache; unsigned long update_symbol_cache(struct symbol_cache *sc); void free_symbol_cache(struct symbol_cache *sc); @@ -278,7 +278,7 @@ alloc_symbol_cache(const char *sym, long offset) { return NULL; } -#endif /* CONFIG_KPROBE_EVENT */ +#endif /* CONFIG_KPROBE_EVENTS */ struct probe_arg { struct fetch_param fetch; diff --git a/kernel/trace/trace_stack.c b/kernel/trace/trace_stack.c index 1d68b5b7ad41..5fb1f2c87e6b 100644 --- a/kernel/trace/trace_stack.c +++ b/kernel/trace/trace_stack.c @@ -65,7 +65,7 @@ void stack_trace_print(void) } /* - * When arch-specific code overides this function, the following + * When arch-specific code overrides this function, the following * data should be filled up, assuming stack_trace_max_lock is held to * prevent concurrent updates. * stack_trace_index[] diff --git a/kernel/ucount.c b/kernel/ucount.c index 62630a40ab3a..b4eeee03934f 100644 --- a/kernel/ucount.c +++ b/kernel/ucount.c @@ -144,7 +144,7 @@ static struct ucounts *get_ucounts(struct user_namespace *ns, kuid_t uid) new->ns = ns; new->uid = uid; - atomic_set(&new->count, 0); + new->count = 0; spin_lock_irq(&ucounts_lock); ucounts = find_ucounts(ns, uid, hashent); @@ -155,8 +155,10 @@ static struct ucounts *get_ucounts(struct user_namespace *ns, kuid_t uid) ucounts = new; } } - if (!atomic_add_unless(&ucounts->count, 1, INT_MAX)) + if (ucounts->count == INT_MAX) ucounts = NULL; + else + ucounts->count += 1; spin_unlock_irq(&ucounts_lock); return ucounts; } @@ -165,13 +167,15 @@ static void put_ucounts(struct ucounts *ucounts) { unsigned long flags; - if (atomic_dec_and_test(&ucounts->count)) { - spin_lock_irqsave(&ucounts_lock, flags); + spin_lock_irqsave(&ucounts_lock, flags); + ucounts->count -= 1; + if (!ucounts->count) hlist_del_init(&ucounts->node); - spin_unlock_irqrestore(&ucounts_lock, flags); + else + ucounts = NULL; + spin_unlock_irqrestore(&ucounts_lock, flags); - kfree(ucounts); - } + kfree(ucounts); } static inline bool atomic_inc_below(atomic_t *v, int u) diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 072cbc9b175d..c0168b7da1ea 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -1507,6 +1507,7 @@ static void __queue_delayed_work(int cpu, struct workqueue_struct *wq, struct timer_list *timer = &dwork->timer; struct work_struct *work = &dwork->work; + WARN_ON_ONCE(!wq); WARN_ON_ONCE(timer->function != delayed_work_timer_fn || timer->data != (unsigned long)dwork); WARN_ON_ONCE(timer_pending(timer)); diff --git a/lib/ioremap.c b/lib/ioremap.c index a3e14ce92a56..4bb30206b942 100644 --- a/lib/ioremap.c +++ b/lib/ioremap.c @@ -14,6 +14,7 @@ #include <asm/pgtable.h> #ifdef CONFIG_HAVE_ARCH_HUGE_VMAP +static int __read_mostly ioremap_p4d_capable; static int __read_mostly ioremap_pud_capable; static int __read_mostly ioremap_pmd_capable; static int __read_mostly ioremap_huge_disabled; @@ -35,6 +36,11 @@ void __init ioremap_huge_init(void) } } +static inline int ioremap_p4d_enabled(void) +{ + return ioremap_p4d_capable; +} + static inline int ioremap_pud_enabled(void) { return ioremap_pud_capable; @@ -46,6 +52,7 @@ static inline int ioremap_pmd_enabled(void) } #else /* !CONFIG_HAVE_ARCH_HUGE_VMAP */ +static inline int ioremap_p4d_enabled(void) { return 0; } static inline int ioremap_pud_enabled(void) { return 0; } static inline int ioremap_pmd_enabled(void) { return 0; } #endif /* CONFIG_HAVE_ARCH_HUGE_VMAP */ @@ -94,14 +101,14 @@ static inline int ioremap_pmd_range(pud_t *pud, unsigned long addr, return 0; } -static inline int ioremap_pud_range(pgd_t *pgd, unsigned long addr, +static inline int ioremap_pud_range(p4d_t *p4d, unsigned long addr, unsigned long end, phys_addr_t phys_addr, pgprot_t prot) { pud_t *pud; unsigned long next; phys_addr -= addr; - pud = pud_alloc(&init_mm, pgd, addr); + pud = pud_alloc(&init_mm, p4d, addr); if (!pud) return -ENOMEM; do { @@ -120,6 +127,32 @@ static inline int ioremap_pud_range(pgd_t *pgd, unsigned long addr, return 0; } +static inline int ioremap_p4d_range(pgd_t *pgd, unsigned long addr, + unsigned long end, phys_addr_t phys_addr, pgprot_t prot) +{ + p4d_t *p4d; + unsigned long next; + + phys_addr -= addr; + p4d = p4d_alloc(&init_mm, pgd, addr); + if (!p4d) + return -ENOMEM; + do { + next = p4d_addr_end(addr, end); + + if (ioremap_p4d_enabled() && + ((next - addr) == P4D_SIZE) && + IS_ALIGNED(phys_addr + addr, P4D_SIZE)) { + if (p4d_set_huge(p4d, phys_addr + addr, prot)) + continue; + } + + if (ioremap_pud_range(p4d, addr, next, phys_addr + addr, prot)) + return -ENOMEM; + } while (p4d++, addr = next, addr != end); + return 0; +} + int ioremap_page_range(unsigned long addr, unsigned long end, phys_addr_t phys_addr, pgprot_t prot) { @@ -135,7 +168,7 @@ int ioremap_page_range(unsigned long addr, pgd = pgd_offset_k(addr); do { next = pgd_addr_end(addr, end); - err = ioremap_pud_range(pgd, addr, next, phys_addr+addr, prot); + err = ioremap_p4d_range(pgd, addr, next, phys_addr+addr, prot); if (err) break; } while (pgd++, addr = next, addr != end); diff --git a/lib/radix-tree.c b/lib/radix-tree.c index 5ed506d648c4..691a9ad48497 100644 --- a/lib/radix-tree.c +++ b/lib/radix-tree.c @@ -2129,8 +2129,8 @@ int ida_pre_get(struct ida *ida, gfp_t gfp) struct ida_bitmap *bitmap = kmalloc(sizeof(*bitmap), gfp); if (!bitmap) return 0; - bitmap = this_cpu_cmpxchg(ida_bitmap, NULL, bitmap); - kfree(bitmap); + if (this_cpu_cmpxchg(ida_bitmap, NULL, bitmap)) + kfree(bitmap); } return 1; diff --git a/lib/refcount.c b/lib/refcount.c index 1d33366189d1..aa09ad3c30b0 100644 --- a/lib/refcount.c +++ b/lib/refcount.c @@ -58,7 +58,7 @@ bool refcount_add_not_zero(unsigned int i, refcount_t *r) val = old; } - WARN(new == UINT_MAX, "refcount_t: saturated; leaking memory.\n"); + WARN_ONCE(new == UINT_MAX, "refcount_t: saturated; leaking memory.\n"); return true; } @@ -66,7 +66,7 @@ EXPORT_SYMBOL_GPL(refcount_add_not_zero); void refcount_add(unsigned int i, refcount_t *r) { - WARN(!refcount_add_not_zero(i, r), "refcount_t: addition on 0; use-after-free.\n"); + WARN_ONCE(!refcount_add_not_zero(i, r), "refcount_t: addition on 0; use-after-free.\n"); } EXPORT_SYMBOL_GPL(refcount_add); @@ -97,7 +97,7 @@ bool refcount_inc_not_zero(refcount_t *r) val = old; } - WARN(new == UINT_MAX, "refcount_t: saturated; leaking memory.\n"); + WARN_ONCE(new == UINT_MAX, "refcount_t: saturated; leaking memory.\n"); return true; } @@ -111,7 +111,7 @@ EXPORT_SYMBOL_GPL(refcount_inc_not_zero); */ void refcount_inc(refcount_t *r) { - WARN(!refcount_inc_not_zero(r), "refcount_t: increment on 0; use-after-free.\n"); + WARN_ONCE(!refcount_inc_not_zero(r), "refcount_t: increment on 0; use-after-free.\n"); } EXPORT_SYMBOL_GPL(refcount_inc); @@ -125,7 +125,7 @@ bool refcount_sub_and_test(unsigned int i, refcount_t *r) new = val - i; if (new > val) { - WARN(new > val, "refcount_t: underflow; use-after-free.\n"); + WARN_ONCE(new > val, "refcount_t: underflow; use-after-free.\n"); return false; } @@ -164,7 +164,7 @@ EXPORT_SYMBOL_GPL(refcount_dec_and_test); void refcount_dec(refcount_t *r) { - WARN(refcount_dec_and_test(r), "refcount_t: decrement hit 0; leaking memory.\n"); + WARN_ONCE(refcount_dec_and_test(r), "refcount_t: decrement hit 0; leaking memory.\n"); } EXPORT_SYMBOL_GPL(refcount_dec); @@ -204,7 +204,7 @@ bool refcount_dec_not_one(refcount_t *r) new = val - 1; if (new > val) { - WARN(new > val, "refcount_t: underflow; use-after-free.\n"); + WARN_ONCE(new > val, "refcount_t: underflow; use-after-free.\n"); return true; } diff --git a/mm/backing-dev.c b/mm/backing-dev.c index 6d861d090e9f..c6f2a37028c2 100644 --- a/mm/backing-dev.c +++ b/mm/backing-dev.c @@ -683,33 +683,26 @@ static int cgwb_bdi_init(struct backing_dev_info *bdi) static void cgwb_bdi_destroy(struct backing_dev_info *bdi) { struct radix_tree_iter iter; - struct rb_node *rbn; void **slot; WARN_ON(test_bit(WB_registered, &bdi->wb.state)); spin_lock_irq(&cgwb_lock); - radix_tree_for_each_slot(slot, &bdi->cgwb_tree, &iter, 0) cgwb_kill(*slot); - - while ((rbn = rb_first(&bdi->cgwb_congested_tree))) { - struct bdi_writeback_congested *congested = - rb_entry(rbn, struct bdi_writeback_congested, rb_node); - - rb_erase(rbn, &bdi->cgwb_congested_tree); - congested->bdi = NULL; /* mark @congested unlinked */ - } - spin_unlock_irq(&cgwb_lock); /* - * All cgwb's and their congested states must be shutdown and - * released before returning. Drain the usage counter to wait for - * all cgwb's and cgwb_congested's ever created on @bdi. + * All cgwb's must be shutdown and released before returning. Drain + * the usage counter to wait for all cgwb's ever created on @bdi. */ atomic_dec(&bdi->usage_cnt); wait_event(cgwb_release_wait, !atomic_read(&bdi->usage_cnt)); + /* + * Grab back our reference so that we hold it when @bdi gets + * re-registered. + */ + atomic_inc(&bdi->usage_cnt); } /** @@ -749,6 +742,21 @@ void wb_blkcg_offline(struct blkcg *blkcg) spin_unlock_irq(&cgwb_lock); } +static void cgwb_bdi_exit(struct backing_dev_info *bdi) +{ + struct rb_node *rbn; + + spin_lock_irq(&cgwb_lock); + while ((rbn = rb_first(&bdi->cgwb_congested_tree))) { + struct bdi_writeback_congested *congested = + rb_entry(rbn, struct bdi_writeback_congested, rb_node); + + rb_erase(rbn, &bdi->cgwb_congested_tree); + congested->bdi = NULL; /* mark @congested unlinked */ + } + spin_unlock_irq(&cgwb_lock); +} + #else /* CONFIG_CGROUP_WRITEBACK */ static int cgwb_bdi_init(struct backing_dev_info *bdi) @@ -769,7 +777,9 @@ static int cgwb_bdi_init(struct backing_dev_info *bdi) return 0; } -static void cgwb_bdi_destroy(struct backing_dev_info *bdi) +static void cgwb_bdi_destroy(struct backing_dev_info *bdi) { } + +static void cgwb_bdi_exit(struct backing_dev_info *bdi) { wb_congested_put(bdi->wb_congested); } @@ -857,6 +867,8 @@ int bdi_register_owner(struct backing_dev_info *bdi, struct device *owner) MINOR(owner->devt)); if (rc) return rc; + /* Leaking owner reference... */ + WARN_ON(bdi->owner); bdi->owner = owner; get_device(owner); return 0; @@ -898,6 +910,7 @@ static void bdi_exit(struct backing_dev_info *bdi) { WARN_ON_ONCE(bdi->dev); wb_exit(&bdi->wb); + cgwb_bdi_exit(bdi); } static void release_bdi(struct kref *ref) @@ -226,6 +226,7 @@ struct page *follow_page_mask(struct vm_area_struct *vma, unsigned int *page_mask) { pgd_t *pgd; + p4d_t *p4d; pud_t *pud; pmd_t *pmd; spinlock_t *ptl; @@ -243,8 +244,13 @@ struct page *follow_page_mask(struct vm_area_struct *vma, pgd = pgd_offset(mm, address); if (pgd_none(*pgd) || unlikely(pgd_bad(*pgd))) return no_page_table(vma, flags); - - pud = pud_offset(pgd, address); + p4d = p4d_offset(pgd, address); + if (p4d_none(*p4d)) + return no_page_table(vma, flags); + BUILD_BUG_ON(p4d_huge(*p4d)); + if (unlikely(p4d_bad(*p4d))) + return no_page_table(vma, flags); + pud = pud_offset(p4d, address); if (pud_none(*pud)) return no_page_table(vma, flags); if (pud_huge(*pud) && vma->vm_flags & VM_HUGETLB) { @@ -325,6 +331,7 @@ static int get_gate_page(struct mm_struct *mm, unsigned long address, struct page **page) { pgd_t *pgd; + p4d_t *p4d; pud_t *pud; pmd_t *pmd; pte_t *pte; @@ -338,7 +345,9 @@ static int get_gate_page(struct mm_struct *mm, unsigned long address, else pgd = pgd_offset_gate(mm, address); BUG_ON(pgd_none(*pgd)); - pud = pud_offset(pgd, address); + p4d = p4d_offset(pgd, address); + BUG_ON(p4d_none(*p4d)); + pud = pud_offset(p4d, address); BUG_ON(pud_none(*pud)); pmd = pmd_offset(pud, address); if (pmd_none(*pmd)) @@ -1400,13 +1409,13 @@ static int gup_pmd_range(pud_t pud, unsigned long addr, unsigned long end, return 1; } -static int gup_pud_range(pgd_t pgd, unsigned long addr, unsigned long end, +static int gup_pud_range(p4d_t p4d, unsigned long addr, unsigned long end, int write, struct page **pages, int *nr) { unsigned long next; pud_t *pudp; - pudp = pud_offset(&pgd, addr); + pudp = pud_offset(&p4d, addr); do { pud_t pud = READ_ONCE(*pudp); @@ -1428,6 +1437,31 @@ static int gup_pud_range(pgd_t pgd, unsigned long addr, unsigned long end, return 1; } +static int gup_p4d_range(pgd_t pgd, unsigned long addr, unsigned long end, + int write, struct page **pages, int *nr) +{ + unsigned long next; + p4d_t *p4dp; + + p4dp = p4d_offset(&pgd, addr); + do { + p4d_t p4d = READ_ONCE(*p4dp); + + next = p4d_addr_end(addr, end); + if (p4d_none(p4d)) + return 0; + BUILD_BUG_ON(p4d_huge(p4d)); + if (unlikely(is_hugepd(__hugepd(p4d_val(p4d))))) { + if (!gup_huge_pd(__hugepd(p4d_val(p4d)), addr, + P4D_SHIFT, next, write, pages, nr)) + return 0; + } else if (!gup_pud_range(p4d, addr, next, write, pages, nr)) + return 0; + } while (p4dp++, addr = next, addr != end); + + return 1; +} + /* * Like get_user_pages_fast() except it's IRQ-safe in that it won't fall back to * the regular GUP. It will only return non-negative values. @@ -1478,7 +1512,7 @@ int __get_user_pages_fast(unsigned long start, int nr_pages, int write, if (!gup_huge_pd(__hugepd(pgd_val(pgd)), addr, PGDIR_SHIFT, next, write, pages, &nr)) break; - } else if (!gup_pud_range(pgd, addr, next, write, pages, &nr)) + } else if (!gup_p4d_range(pgd, addr, next, write, pages, &nr)) break; } while (pgdp++, addr = next, addr != end); local_irq_restore(flags); diff --git a/mm/huge_memory.c b/mm/huge_memory.c index d36b2af4d1bf..1ebc93e179f3 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -1828,7 +1828,7 @@ static void __split_huge_pud_locked(struct vm_area_struct *vma, pud_t *pud, VM_BUG_ON_VMA(vma->vm_end < haddr + HPAGE_PUD_SIZE, vma); VM_BUG_ON(!pud_trans_huge(*pud) && !pud_devmap(*pud)); - count_vm_event(THP_SPLIT_PMD); + count_vm_event(THP_SPLIT_PUD); pudp_huge_clear_flush_notify(vma, haddr, pud); } @@ -2048,6 +2048,7 @@ void split_huge_pmd_address(struct vm_area_struct *vma, unsigned long address, bool freeze, struct page *page) { pgd_t *pgd; + p4d_t *p4d; pud_t *pud; pmd_t *pmd; @@ -2055,7 +2056,11 @@ void split_huge_pmd_address(struct vm_area_struct *vma, unsigned long address, if (!pgd_present(*pgd)) return; - pud = pud_offset(pgd, address); + p4d = p4d_offset(pgd, address); + if (!p4d_present(*p4d)) + return; + + pud = pud_offset(p4d, address); if (!pud_present(*pud)) return; diff --git a/mm/hugetlb.c b/mm/hugetlb.c index a7aa811b7d14..3d0aab9ee80d 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -4555,7 +4555,8 @@ out: int huge_pmd_unshare(struct mm_struct *mm, unsigned long *addr, pte_t *ptep) { pgd_t *pgd = pgd_offset(mm, *addr); - pud_t *pud = pud_offset(pgd, *addr); + p4d_t *p4d = p4d_offset(pgd, *addr); + pud_t *pud = pud_offset(p4d, *addr); BUG_ON(page_count(virt_to_page(ptep)) == 0); if (page_count(virt_to_page(ptep)) == 1) @@ -4586,11 +4587,13 @@ pte_t *huge_pte_alloc(struct mm_struct *mm, unsigned long addr, unsigned long sz) { pgd_t *pgd; + p4d_t *p4d; pud_t *pud; pte_t *pte = NULL; pgd = pgd_offset(mm, addr); - pud = pud_alloc(mm, pgd, addr); + p4d = p4d_offset(pgd, addr); + pud = pud_alloc(mm, p4d, addr); if (pud) { if (sz == PUD_SIZE) { pte = (pte_t *)pud; @@ -4610,18 +4613,22 @@ pte_t *huge_pte_alloc(struct mm_struct *mm, pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr) { pgd_t *pgd; + p4d_t *p4d; pud_t *pud; - pmd_t *pmd = NULL; + pmd_t *pmd; pgd = pgd_offset(mm, addr); - if (pgd_present(*pgd)) { - pud = pud_offset(pgd, addr); - if (pud_present(*pud)) { - if (pud_huge(*pud)) - return (pte_t *)pud; - pmd = pmd_offset(pud, addr); - } - } + if (!pgd_present(*pgd)) + return NULL; + p4d = p4d_offset(pgd, addr); + if (!p4d_present(*p4d)) + return NULL; + pud = pud_offset(p4d, addr); + if (!pud_present(*pud)) + return NULL; + if (pud_huge(*pud)) + return (pte_t *)pud; + pmd = pmd_offset(pud, addr); return (pte_t *) pmd; } diff --git a/mm/kasan/kasan_init.c b/mm/kasan/kasan_init.c index 31238dad85fb..b96a5f773d88 100644 --- a/mm/kasan/kasan_init.c +++ b/mm/kasan/kasan_init.c @@ -30,6 +30,9 @@ */ unsigned char kasan_zero_page[PAGE_SIZE] __page_aligned_bss; +#if CONFIG_PGTABLE_LEVELS > 4 +p4d_t kasan_zero_p4d[PTRS_PER_P4D] __page_aligned_bss; +#endif #if CONFIG_PGTABLE_LEVELS > 3 pud_t kasan_zero_pud[PTRS_PER_PUD] __page_aligned_bss; #endif @@ -82,10 +85,10 @@ static void __init zero_pmd_populate(pud_t *pud, unsigned long addr, } while (pmd++, addr = next, addr != end); } -static void __init zero_pud_populate(pgd_t *pgd, unsigned long addr, +static void __init zero_pud_populate(p4d_t *p4d, unsigned long addr, unsigned long end) { - pud_t *pud = pud_offset(pgd, addr); + pud_t *pud = pud_offset(p4d, addr); unsigned long next; do { @@ -107,6 +110,23 @@ static void __init zero_pud_populate(pgd_t *pgd, unsigned long addr, } while (pud++, addr = next, addr != end); } +static void __init zero_p4d_populate(pgd_t *pgd, unsigned long addr, + unsigned long end) +{ + p4d_t *p4d = p4d_offset(pgd, addr); + unsigned long next; + + do { + next = p4d_addr_end(addr, end); + + if (p4d_none(*p4d)) { + p4d_populate(&init_mm, p4d, + early_alloc(PAGE_SIZE, NUMA_NO_NODE)); + } + zero_pud_populate(p4d, addr, next); + } while (p4d++, addr = next, addr != end); +} + /** * kasan_populate_zero_shadow - populate shadow memory region with * kasan_zero_page @@ -125,6 +145,7 @@ void __init kasan_populate_zero_shadow(const void *shadow_start, next = pgd_addr_end(addr, end); if (IS_ALIGNED(addr, PGDIR_SIZE) && end - addr >= PGDIR_SIZE) { + p4d_t *p4d; pud_t *pud; pmd_t *pmd; @@ -135,9 +156,22 @@ void __init kasan_populate_zero_shadow(const void *shadow_start, * 3,2 - level page tables where we don't have * puds,pmds, so pgd_populate(), pud_populate() * is noops. + * + * The ifndef is required to avoid build breakage. + * + * With 5level-fixup.h, pgd_populate() is not nop and + * we reference kasan_zero_p4d. It's not defined + * unless 5-level paging enabled. + * + * The ifndef can be dropped once all KASAN-enabled + * architectures will switch to pgtable-nop4d.h. */ - pgd_populate(&init_mm, pgd, lm_alias(kasan_zero_pud)); - pud = pud_offset(pgd, addr); +#ifndef __ARCH_HAS_5LEVEL_HACK + pgd_populate(&init_mm, pgd, lm_alias(kasan_zero_p4d)); +#endif + p4d = p4d_offset(pgd, addr); + p4d_populate(&init_mm, p4d, lm_alias(kasan_zero_pud)); + pud = pud_offset(p4d, addr); pud_populate(&init_mm, pud, lm_alias(kasan_zero_pmd)); pmd = pmd_offset(pud, addr); pmd_populate_kernel(&init_mm, pmd, lm_alias(kasan_zero_pte)); @@ -148,6 +182,6 @@ void __init kasan_populate_zero_shadow(const void *shadow_start, pgd_populate(&init_mm, pgd, early_alloc(PAGE_SIZE, NUMA_NO_NODE)); } - zero_pud_populate(pgd, addr, next); + zero_p4d_populate(pgd, addr, next); } while (pgd++, addr = next, addr != end); } diff --git a/mm/kasan/quarantine.c b/mm/kasan/quarantine.c index 6f1ed1630873..3a8ddf8baf7d 100644 --- a/mm/kasan/quarantine.c +++ b/mm/kasan/quarantine.c @@ -25,6 +25,7 @@ #include <linux/printk.h> #include <linux/shrinker.h> #include <linux/slab.h> +#include <linux/srcu.h> #include <linux/string.h> #include <linux/types.h> @@ -103,6 +104,7 @@ static int quarantine_tail; /* Total size of all objects in global_quarantine across all batches. */ static unsigned long quarantine_size; static DEFINE_SPINLOCK(quarantine_lock); +DEFINE_STATIC_SRCU(remove_cache_srcu); /* Maximum size of the global queue. */ static unsigned long quarantine_max_size; @@ -173,17 +175,22 @@ void quarantine_put(struct kasan_free_meta *info, struct kmem_cache *cache) struct qlist_head *q; struct qlist_head temp = QLIST_INIT; + /* + * Note: irq must be disabled until after we move the batch to the + * global quarantine. Otherwise quarantine_remove_cache() can miss + * some objects belonging to the cache if they are in our local temp + * list. quarantine_remove_cache() executes on_each_cpu() at the + * beginning which ensures that it either sees the objects in per-cpu + * lists or in the global quarantine. + */ local_irq_save(flags); q = this_cpu_ptr(&cpu_quarantine); qlist_put(q, &info->quarantine_link, cache->size); - if (unlikely(q->bytes > QUARANTINE_PERCPU_SIZE)) + if (unlikely(q->bytes > QUARANTINE_PERCPU_SIZE)) { qlist_move_all(q, &temp); - local_irq_restore(flags); - - if (unlikely(!qlist_empty(&temp))) { - spin_lock_irqsave(&quarantine_lock, flags); + spin_lock(&quarantine_lock); WRITE_ONCE(quarantine_size, quarantine_size + temp.bytes); qlist_move_all(&temp, &global_quarantine[quarantine_tail]); if (global_quarantine[quarantine_tail].bytes >= @@ -196,20 +203,33 @@ void quarantine_put(struct kasan_free_meta *info, struct kmem_cache *cache) if (new_tail != quarantine_head) quarantine_tail = new_tail; } - spin_unlock_irqrestore(&quarantine_lock, flags); + spin_unlock(&quarantine_lock); } + + local_irq_restore(flags); } void quarantine_reduce(void) { size_t total_size, new_quarantine_size, percpu_quarantines; unsigned long flags; + int srcu_idx; struct qlist_head to_free = QLIST_INIT; if (likely(READ_ONCE(quarantine_size) <= READ_ONCE(quarantine_max_size))) return; + /* + * srcu critical section ensures that quarantine_remove_cache() + * will not miss objects belonging to the cache while they are in our + * local to_free list. srcu is chosen because (1) it gives us private + * grace period domain that does not interfere with anything else, + * and (2) it allows synchronize_srcu() to return without waiting + * if there are no pending read critical sections (which is the + * expected case). + */ + srcu_idx = srcu_read_lock(&remove_cache_srcu); spin_lock_irqsave(&quarantine_lock, flags); /* @@ -237,6 +257,7 @@ void quarantine_reduce(void) spin_unlock_irqrestore(&quarantine_lock, flags); qlist_free_all(&to_free, NULL); + srcu_read_unlock(&remove_cache_srcu, srcu_idx); } static void qlist_move_cache(struct qlist_head *from, @@ -280,12 +301,28 @@ void quarantine_remove_cache(struct kmem_cache *cache) unsigned long flags, i; struct qlist_head to_free = QLIST_INIT; + /* + * Must be careful to not miss any objects that are being moved from + * per-cpu list to the global quarantine in quarantine_put(), + * nor objects being freed in quarantine_reduce(). on_each_cpu() + * achieves the first goal, while synchronize_srcu() achieves the + * second. + */ on_each_cpu(per_cpu_remove_cache, cache, 1); spin_lock_irqsave(&quarantine_lock, flags); - for (i = 0; i < QUARANTINE_BATCHES; i++) + for (i = 0; i < QUARANTINE_BATCHES; i++) { + if (qlist_empty(&global_quarantine[i])) + continue; qlist_move_cache(&global_quarantine[i], &to_free, cache); + /* Scanning whole quarantine can take a while. */ + spin_unlock_irqrestore(&quarantine_lock, flags); + cond_resched(); + spin_lock_irqsave(&quarantine_lock, flags); + } spin_unlock_irqrestore(&quarantine_lock, flags); qlist_free_all(&to_free, cache); + + synchronize_srcu(&remove_cache_srcu); } diff --git a/mm/madvise.c b/mm/madvise.c index dc5927c812d3..7a2abf0127ae 100644 --- a/mm/madvise.c +++ b/mm/madvise.c @@ -513,7 +513,43 @@ static long madvise_dontneed(struct vm_area_struct *vma, if (!can_madv_dontneed_vma(vma)) return -EINVAL; - userfaultfd_remove(vma, prev, start, end); + if (!userfaultfd_remove(vma, start, end)) { + *prev = NULL; /* mmap_sem has been dropped, prev is stale */ + + down_read(¤t->mm->mmap_sem); + vma = find_vma(current->mm, start); + if (!vma) + return -ENOMEM; + if (start < vma->vm_start) { + /* + * This "vma" under revalidation is the one + * with the lowest vma->vm_start where start + * is also < vma->vm_end. If start < + * vma->vm_start it means an hole materialized + * in the user address space within the + * virtual range passed to MADV_DONTNEED. + */ + return -ENOMEM; + } + if (!can_madv_dontneed_vma(vma)) + return -EINVAL; + if (end > vma->vm_end) { + /* + * Don't fail if end > vma->vm_end. If the old + * vma was splitted while the mmap_sem was + * released the effect of the concurrent + * operation may not cause MADV_DONTNEED to + * have an undefined result. There may be an + * adjacent next vma that we'll walk + * next. userfaultfd_remove() will generate an + * UFFD_EVENT_REMOVE repetition on the + * end-vma->vm_end range, but the manager can + * handle a repetition fine. + */ + end = vma->vm_end; + } + VM_WARN_ON(start >= end); + } zap_page_range(vma, start, end - start); return 0; } @@ -554,8 +590,10 @@ static long madvise_remove(struct vm_area_struct *vma, * mmap_sem. */ get_file(f); - userfaultfd_remove(vma, prev, start, end); - up_read(¤t->mm->mmap_sem); + if (userfaultfd_remove(vma, start, end)) { + /* mmap_sem was not released by userfaultfd_remove() */ + up_read(¤t->mm->mmap_sem); + } error = vfs_fallocate(f, FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE, offset, end - start); diff --git a/mm/memblock.c b/mm/memblock.c index b64b47803e52..696f06d17c4e 100644 --- a/mm/memblock.c +++ b/mm/memblock.c @@ -1118,7 +1118,10 @@ unsigned long __init_memblock memblock_next_valid_pfn(unsigned long pfn, } } while (left < right); - return min(PHYS_PFN(type->regions[right].base), max_pfn); + if (right == type->cnt) + return max_pfn; + else + return min(PHYS_PFN(type->regions[right].base), max_pfn); } /** diff --git a/mm/memcontrol.c b/mm/memcontrol.c index c52ec893e241..2bd7541d7c11 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -466,6 +466,8 @@ static void mem_cgroup_update_tree(struct mem_cgroup *memcg, struct page *page) struct mem_cgroup_tree_per_node *mctz; mctz = soft_limit_tree_from_page(page); + if (!mctz) + return; /* * Necessary to update all ancestors when hierarchy is used. * because their event counter is not touched. @@ -503,7 +505,8 @@ static void mem_cgroup_remove_from_trees(struct mem_cgroup *memcg) for_each_node(nid) { mz = mem_cgroup_nodeinfo(memcg, nid); mctz = soft_limit_tree_node(nid); - mem_cgroup_remove_exceeded(mz, mctz); + if (mctz) + mem_cgroup_remove_exceeded(mz, mctz); } } @@ -2558,7 +2561,7 @@ unsigned long mem_cgroup_soft_limit_reclaim(pg_data_t *pgdat, int order, * is empty. Do it lockless to prevent lock bouncing. Races * are acceptable as soft limit is best effort anyway. */ - if (RB_EMPTY_ROOT(&mctz->rb_root)) + if (!mctz || RB_EMPTY_ROOT(&mctz->rb_root)) return 0; /* @@ -4135,17 +4138,22 @@ static void free_mem_cgroup_per_node_info(struct mem_cgroup *memcg, int node) kfree(memcg->nodeinfo[node]); } -static void mem_cgroup_free(struct mem_cgroup *memcg) +static void __mem_cgroup_free(struct mem_cgroup *memcg) { int node; - memcg_wb_domain_exit(memcg); for_each_node(node) free_mem_cgroup_per_node_info(memcg, node); free_percpu(memcg->stat); kfree(memcg); } +static void mem_cgroup_free(struct mem_cgroup *memcg) +{ + memcg_wb_domain_exit(memcg); + __mem_cgroup_free(memcg); +} + static struct mem_cgroup *mem_cgroup_alloc(void) { struct mem_cgroup *memcg; @@ -4196,7 +4204,7 @@ static struct mem_cgroup *mem_cgroup_alloc(void) fail: if (memcg->id.id > 0) idr_remove(&mem_cgroup_idr, memcg->id.id); - mem_cgroup_free(memcg); + __mem_cgroup_free(memcg); return NULL; } diff --git a/mm/memory.c b/mm/memory.c index a97a4cec2e1f..235ba51b2fbf 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -445,7 +445,7 @@ static inline void free_pmd_range(struct mmu_gather *tlb, pud_t *pud, mm_dec_nr_pmds(tlb->mm); } -static inline void free_pud_range(struct mmu_gather *tlb, pgd_t *pgd, +static inline void free_pud_range(struct mmu_gather *tlb, p4d_t *p4d, unsigned long addr, unsigned long end, unsigned long floor, unsigned long ceiling) { @@ -454,7 +454,7 @@ static inline void free_pud_range(struct mmu_gather *tlb, pgd_t *pgd, unsigned long start; start = addr; - pud = pud_offset(pgd, addr); + pud = pud_offset(p4d, addr); do { next = pud_addr_end(addr, end); if (pud_none_or_clear_bad(pud)) @@ -462,6 +462,39 @@ static inline void free_pud_range(struct mmu_gather *tlb, pgd_t *pgd, free_pmd_range(tlb, pud, addr, next, floor, ceiling); } while (pud++, addr = next, addr != end); + start &= P4D_MASK; + if (start < floor) + return; + if (ceiling) { + ceiling &= P4D_MASK; + if (!ceiling) + return; + } + if (end - 1 > ceiling - 1) + return; + + pud = pud_offset(p4d, start); + p4d_clear(p4d); + pud_free_tlb(tlb, pud, start); +} + +static inline void free_p4d_range(struct mmu_gather *tlb, pgd_t *pgd, + unsigned long addr, unsigned long end, + unsigned long floor, unsigned long ceiling) +{ + p4d_t *p4d; + unsigned long next; + unsigned long start; + + start = addr; + p4d = p4d_offset(pgd, addr); + do { + next = p4d_addr_end(addr, end); + if (p4d_none_or_clear_bad(p4d)) + continue; + free_pud_range(tlb, p4d, addr, next, floor, ceiling); + } while (p4d++, addr = next, addr != end); + start &= PGDIR_MASK; if (start < floor) return; @@ -473,9 +506,9 @@ static inline void free_pud_range(struct mmu_gather *tlb, pgd_t *pgd, if (end - 1 > ceiling - 1) return; - pud = pud_offset(pgd, start); + p4d = p4d_offset(pgd, start); pgd_clear(pgd); - pud_free_tlb(tlb, pud, start); + p4d_free_tlb(tlb, p4d, start); } /* @@ -539,7 +572,7 @@ void free_pgd_range(struct mmu_gather *tlb, next = pgd_addr_end(addr, end); if (pgd_none_or_clear_bad(pgd)) continue; - free_pud_range(tlb, pgd, addr, next, floor, ceiling); + free_p4d_range(tlb, pgd, addr, next, floor, ceiling); } while (pgd++, addr = next, addr != end); } @@ -658,7 +691,8 @@ static void print_bad_pte(struct vm_area_struct *vma, unsigned long addr, pte_t pte, struct page *page) { pgd_t *pgd = pgd_offset(vma->vm_mm, addr); - pud_t *pud = pud_offset(pgd, addr); + p4d_t *p4d = p4d_offset(pgd, addr); + pud_t *pud = pud_offset(p4d, addr); pmd_t *pmd = pmd_offset(pud, addr); struct address_space *mapping; pgoff_t index; @@ -1023,16 +1057,16 @@ static inline int copy_pmd_range(struct mm_struct *dst_mm, struct mm_struct *src } static inline int copy_pud_range(struct mm_struct *dst_mm, struct mm_struct *src_mm, - pgd_t *dst_pgd, pgd_t *src_pgd, struct vm_area_struct *vma, + p4d_t *dst_p4d, p4d_t *src_p4d, struct vm_area_struct *vma, unsigned long addr, unsigned long end) { pud_t *src_pud, *dst_pud; unsigned long next; - dst_pud = pud_alloc(dst_mm, dst_pgd, addr); + dst_pud = pud_alloc(dst_mm, dst_p4d, addr); if (!dst_pud) return -ENOMEM; - src_pud = pud_offset(src_pgd, addr); + src_pud = pud_offset(src_p4d, addr); do { next = pud_addr_end(addr, end); if (pud_trans_huge(*src_pud) || pud_devmap(*src_pud)) { @@ -1056,6 +1090,28 @@ static inline int copy_pud_range(struct mm_struct *dst_mm, struct mm_struct *src return 0; } +static inline int copy_p4d_range(struct mm_struct *dst_mm, struct mm_struct *src_mm, + pgd_t *dst_pgd, pgd_t *src_pgd, struct vm_area_struct *vma, + unsigned long addr, unsigned long end) +{ + p4d_t *src_p4d, *dst_p4d; + unsigned long next; + + dst_p4d = p4d_alloc(dst_mm, dst_pgd, addr); + if (!dst_p4d) + return -ENOMEM; + src_p4d = p4d_offset(src_pgd, addr); + do { + next = p4d_addr_end(addr, end); + if (p4d_none_or_clear_bad(src_p4d)) + continue; + if (copy_pud_range(dst_mm, src_mm, dst_p4d, src_p4d, + vma, addr, next)) + return -ENOMEM; + } while (dst_p4d++, src_p4d++, addr = next, addr != end); + return 0; +} + int copy_page_range(struct mm_struct *dst_mm, struct mm_struct *src_mm, struct vm_area_struct *vma) { @@ -1111,7 +1167,7 @@ int copy_page_range(struct mm_struct *dst_mm, struct mm_struct *src_mm, next = pgd_addr_end(addr, end); if (pgd_none_or_clear_bad(src_pgd)) continue; - if (unlikely(copy_pud_range(dst_mm, src_mm, dst_pgd, src_pgd, + if (unlikely(copy_p4d_range(dst_mm, src_mm, dst_pgd, src_pgd, vma, addr, next))) { ret = -ENOMEM; break; @@ -1267,14 +1323,14 @@ next: } static inline unsigned long zap_pud_range(struct mmu_gather *tlb, - struct vm_area_struct *vma, pgd_t *pgd, + struct vm_area_struct *vma, p4d_t *p4d, unsigned long addr, unsigned long end, struct zap_details *details) { pud_t *pud; unsigned long next; - pud = pud_offset(pgd, addr); + pud = pud_offset(p4d, addr); do { next = pud_addr_end(addr, end); if (pud_trans_huge(*pud) || pud_devmap(*pud)) { @@ -1295,6 +1351,25 @@ next: return addr; } +static inline unsigned long zap_p4d_range(struct mmu_gather *tlb, + struct vm_area_struct *vma, pgd_t *pgd, + unsigned long addr, unsigned long end, + struct zap_details *details) +{ + p4d_t *p4d; + unsigned long next; + + p4d = p4d_offset(pgd, addr); + do { + next = p4d_addr_end(addr, end); + if (p4d_none_or_clear_bad(p4d)) + continue; + next = zap_pud_range(tlb, vma, p4d, addr, next, details); + } while (p4d++, addr = next, addr != end); + + return addr; +} + void unmap_page_range(struct mmu_gather *tlb, struct vm_area_struct *vma, unsigned long addr, unsigned long end, @@ -1310,7 +1385,7 @@ void unmap_page_range(struct mmu_gather *tlb, next = pgd_addr_end(addr, end); if (pgd_none_or_clear_bad(pgd)) continue; - next = zap_pud_range(tlb, vma, pgd, addr, next, details); + next = zap_p4d_range(tlb, vma, pgd, addr, next, details); } while (pgd++, addr = next, addr != end); tlb_end_vma(tlb, vma); } @@ -1465,16 +1540,24 @@ EXPORT_SYMBOL_GPL(zap_vma_ptes); pte_t *__get_locked_pte(struct mm_struct *mm, unsigned long addr, spinlock_t **ptl) { - pgd_t *pgd = pgd_offset(mm, addr); - pud_t *pud = pud_alloc(mm, pgd, addr); - if (pud) { - pmd_t *pmd = pmd_alloc(mm, pud, addr); - if (pmd) { - VM_BUG_ON(pmd_trans_huge(*pmd)); - return pte_alloc_map_lock(mm, pmd, addr, ptl); - } - } - return NULL; + pgd_t *pgd; + p4d_t *p4d; + pud_t *pud; + pmd_t *pmd; + + pgd = pgd_offset(mm, addr); + p4d = p4d_alloc(mm, pgd, addr); + if (!p4d) + return NULL; + pud = pud_alloc(mm, p4d, addr); + if (!pud) + return NULL; + pmd = pmd_alloc(mm, pud, addr); + if (!pmd) + return NULL; + + VM_BUG_ON(pmd_trans_huge(*pmd)); + return pte_alloc_map_lock(mm, pmd, addr, ptl); } /* @@ -1740,7 +1823,7 @@ static inline int remap_pmd_range(struct mm_struct *mm, pud_t *pud, return 0; } -static inline int remap_pud_range(struct mm_struct *mm, pgd_t *pgd, +static inline int remap_pud_range(struct mm_struct *mm, p4d_t *p4d, unsigned long addr, unsigned long end, unsigned long pfn, pgprot_t prot) { @@ -1748,7 +1831,7 @@ static inline int remap_pud_range(struct mm_struct *mm, pgd_t *pgd, unsigned long next; pfn -= addr >> PAGE_SHIFT; - pud = pud_alloc(mm, pgd, addr); + pud = pud_alloc(mm, p4d, addr); if (!pud) return -ENOMEM; do { @@ -1760,6 +1843,26 @@ static inline int remap_pud_range(struct mm_struct *mm, pgd_t *pgd, return 0; } +static inline int remap_p4d_range(struct mm_struct *mm, pgd_t *pgd, + unsigned long addr, unsigned long end, + unsigned long pfn, pgprot_t prot) +{ + p4d_t *p4d; + unsigned long next; + + pfn -= addr >> PAGE_SHIFT; + p4d = p4d_alloc(mm, pgd, addr); + if (!p4d) + return -ENOMEM; + do { + next = p4d_addr_end(addr, end); + if (remap_pud_range(mm, p4d, addr, next, + pfn + (addr >> PAGE_SHIFT), prot)) + return -ENOMEM; + } while (p4d++, addr = next, addr != end); + return 0; +} + /** * remap_pfn_range - remap kernel memory to userspace * @vma: user vma to map to @@ -1816,7 +1919,7 @@ int remap_pfn_range(struct vm_area_struct *vma, unsigned long addr, flush_cache_range(vma, addr, end); do { next = pgd_addr_end(addr, end); - err = remap_pud_range(mm, pgd, addr, next, + err = remap_p4d_range(mm, pgd, addr, next, pfn + (addr >> PAGE_SHIFT), prot); if (err) break; @@ -1932,7 +2035,7 @@ static int apply_to_pmd_range(struct mm_struct *mm, pud_t *pud, return err; } -static int apply_to_pud_range(struct mm_struct *mm, pgd_t *pgd, +static int apply_to_pud_range(struct mm_struct *mm, p4d_t *p4d, unsigned long addr, unsigned long end, pte_fn_t fn, void *data) { @@ -1940,7 +2043,7 @@ static int apply_to_pud_range(struct mm_struct *mm, pgd_t *pgd, unsigned long next; int err; - pud = pud_alloc(mm, pgd, addr); + pud = pud_alloc(mm, p4d, addr); if (!pud) return -ENOMEM; do { @@ -1952,6 +2055,26 @@ static int apply_to_pud_range(struct mm_struct *mm, pgd_t *pgd, return err; } +static int apply_to_p4d_range(struct mm_struct *mm, pgd_t *pgd, + unsigned long addr, unsigned long end, + pte_fn_t fn, void *data) +{ + p4d_t *p4d; + unsigned long next; + int err; + + p4d = p4d_alloc(mm, pgd, addr); + if (!p4d) + return -ENOMEM; + do { + next = p4d_addr_end(addr, end); + err = apply_to_pud_range(mm, p4d, addr, next, fn, data); + if (err) + break; + } while (p4d++, addr = next, addr != end); + return err; +} + /* * Scan a region of virtual memory, filling in page tables as necessary * and calling a provided function on each leaf page table. @@ -1970,7 +2093,7 @@ int apply_to_page_range(struct mm_struct *mm, unsigned long addr, pgd = pgd_offset(mm, addr); do { next = pgd_addr_end(addr, end); - err = apply_to_pud_range(mm, pgd, addr, next, fn, data); + err = apply_to_p4d_range(mm, pgd, addr, next, fn, data); if (err) break; } while (pgd++, addr = next, addr != end); @@ -3653,11 +3776,15 @@ static int __handle_mm_fault(struct vm_area_struct *vma, unsigned long address, }; struct mm_struct *mm = vma->vm_mm; pgd_t *pgd; + p4d_t *p4d; int ret; pgd = pgd_offset(mm, address); + p4d = p4d_alloc(mm, pgd, address); + if (!p4d) + return VM_FAULT_OOM; - vmf.pud = pud_alloc(mm, pgd, address); + vmf.pud = pud_alloc(mm, p4d, address); if (!vmf.pud) return VM_FAULT_OOM; if (pud_none(*vmf.pud) && transparent_hugepage_enabled(vma)) { @@ -3779,12 +3906,35 @@ int handle_mm_fault(struct vm_area_struct *vma, unsigned long address, } EXPORT_SYMBOL_GPL(handle_mm_fault); +#ifndef __PAGETABLE_P4D_FOLDED +/* + * Allocate p4d page table. + * We've already handled the fast-path in-line. + */ +int __p4d_alloc(struct mm_struct *mm, pgd_t *pgd, unsigned long address) +{ + p4d_t *new = p4d_alloc_one(mm, address); + if (!new) + return -ENOMEM; + + smp_wmb(); /* See comment in __pte_alloc */ + + spin_lock(&mm->page_table_lock); + if (pgd_present(*pgd)) /* Another has populated it */ + p4d_free(mm, new); + else + pgd_populate(mm, pgd, new); + spin_unlock(&mm->page_table_lock); + return 0; +} +#endif /* __PAGETABLE_P4D_FOLDED */ + #ifndef __PAGETABLE_PUD_FOLDED /* * Allocate page upper directory. * We've already handled the fast-path in-line. */ -int __pud_alloc(struct mm_struct *mm, pgd_t *pgd, unsigned long address) +int __pud_alloc(struct mm_struct *mm, p4d_t *p4d, unsigned long address) { pud_t *new = pud_alloc_one(mm, address); if (!new) @@ -3793,10 +3943,17 @@ int __pud_alloc(struct mm_struct *mm, pgd_t *pgd, unsigned long address) smp_wmb(); /* See comment in __pte_alloc */ spin_lock(&mm->page_table_lock); - if (pgd_present(*pgd)) /* Another has populated it */ +#ifndef __ARCH_HAS_5LEVEL_HACK + if (p4d_present(*p4d)) /* Another has populated it */ pud_free(mm, new); else - pgd_populate(mm, pgd, new); + p4d_populate(mm, p4d, new); +#else + if (pgd_present(*p4d)) /* Another has populated it */ + pud_free(mm, new); + else + pgd_populate(mm, p4d, new); +#endif /* __ARCH_HAS_5LEVEL_HACK */ spin_unlock(&mm->page_table_lock); return 0; } @@ -3839,6 +3996,7 @@ static int __follow_pte_pmd(struct mm_struct *mm, unsigned long address, pte_t **ptepp, pmd_t **pmdpp, spinlock_t **ptlp) { pgd_t *pgd; + p4d_t *p4d; pud_t *pud; pmd_t *pmd; pte_t *ptep; @@ -3847,7 +4005,11 @@ static int __follow_pte_pmd(struct mm_struct *mm, unsigned long address, if (pgd_none(*pgd) || unlikely(pgd_bad(*pgd))) goto out; - pud = pud_offset(pgd, address); + p4d = p4d_offset(pgd, address); + if (p4d_none(*p4d) || unlikely(p4d_bad(*p4d))) + goto out; + + pud = pud_offset(p4d, address); if (pud_none(*pud) || unlikely(pud_bad(*pud))) goto out; diff --git a/mm/mlock.c b/mm/mlock.c index 1050511f8b2b..0dd9ca18e19e 100644 --- a/mm/mlock.c +++ b/mm/mlock.c @@ -380,6 +380,7 @@ static unsigned long __munlock_pagevec_fill(struct pagevec *pvec, pte = get_locked_pte(vma->vm_mm, start, &ptl); /* Make sure we do not cross the page table boundary */ end = pgd_addr_end(start, end); + end = p4d_addr_end(start, end); end = pud_addr_end(start, end); end = pmd_addr_end(start, end); @@ -442,7 +443,7 @@ void munlock_vma_pages_range(struct vm_area_struct *vma, while (start < end) { struct page *page; - unsigned int page_mask; + unsigned int page_mask = 0; unsigned long page_increm; struct pagevec pvec; struct zone *zone; @@ -456,8 +457,7 @@ void munlock_vma_pages_range(struct vm_area_struct *vma, * suits munlock very well (and if somehow an abnormal page * has sneaked into the range, we won't oops here: great). */ - page = follow_page_mask(vma, start, FOLL_GET | FOLL_DUMP, - &page_mask); + page = follow_page(vma, start, FOLL_GET | FOLL_DUMP); if (page && !IS_ERR(page)) { if (PageTransTail(page)) { @@ -468,8 +468,8 @@ void munlock_vma_pages_range(struct vm_area_struct *vma, /* * Any THP page found by follow_page_mask() may * have gotten split before reaching - * munlock_vma_page(), so we need to recompute - * the page_mask here. + * munlock_vma_page(), so we need to compute + * the page_mask here instead. */ page_mask = munlock_vma_page(page); unlock_page(page); diff --git a/mm/mprotect.c b/mm/mprotect.c index 848e946b08e5..8edd0d576254 100644 --- a/mm/mprotect.c +++ b/mm/mprotect.c @@ -193,14 +193,14 @@ static inline unsigned long change_pmd_range(struct vm_area_struct *vma, } static inline unsigned long change_pud_range(struct vm_area_struct *vma, - pgd_t *pgd, unsigned long addr, unsigned long end, + p4d_t *p4d, unsigned long addr, unsigned long end, pgprot_t newprot, int dirty_accountable, int prot_numa) { pud_t *pud; unsigned long next; unsigned long pages = 0; - pud = pud_offset(pgd, addr); + pud = pud_offset(p4d, addr); do { next = pud_addr_end(addr, end); if (pud_none_or_clear_bad(pud)) @@ -212,6 +212,26 @@ static inline unsigned long change_pud_range(struct vm_area_struct *vma, return pages; } +static inline unsigned long change_p4d_range(struct vm_area_struct *vma, + pgd_t *pgd, unsigned long addr, unsigned long end, + pgprot_t newprot, int dirty_accountable, int prot_numa) +{ + p4d_t *p4d; + unsigned long next; + unsigned long pages = 0; + + p4d = p4d_offset(pgd, addr); + do { + next = p4d_addr_end(addr, end); + if (p4d_none_or_clear_bad(p4d)) + continue; + pages += change_pud_range(vma, p4d, addr, next, newprot, + dirty_accountable, prot_numa); + } while (p4d++, addr = next, addr != end); + + return pages; +} + static unsigned long change_protection_range(struct vm_area_struct *vma, unsigned long addr, unsigned long end, pgprot_t newprot, int dirty_accountable, int prot_numa) @@ -230,7 +250,7 @@ static unsigned long change_protection_range(struct vm_area_struct *vma, next = pgd_addr_end(addr, end); if (pgd_none_or_clear_bad(pgd)) continue; - pages += change_pud_range(vma, pgd, addr, next, newprot, + pages += change_p4d_range(vma, pgd, addr, next, newprot, dirty_accountable, prot_numa); } while (pgd++, addr = next, addr != end); diff --git a/mm/mremap.c b/mm/mremap.c index 8233b0105c82..cd8a1b199ef9 100644 --- a/mm/mremap.c +++ b/mm/mremap.c @@ -32,6 +32,7 @@ static pmd_t *get_old_pmd(struct mm_struct *mm, unsigned long addr) { pgd_t *pgd; + p4d_t *p4d; pud_t *pud; pmd_t *pmd; @@ -39,7 +40,11 @@ static pmd_t *get_old_pmd(struct mm_struct *mm, unsigned long addr) if (pgd_none_or_clear_bad(pgd)) return NULL; - pud = pud_offset(pgd, addr); + p4d = p4d_offset(pgd, addr); + if (p4d_none_or_clear_bad(p4d)) + return NULL; + + pud = pud_offset(p4d, addr); if (pud_none_or_clear_bad(pud)) return NULL; @@ -54,11 +59,15 @@ static pmd_t *alloc_new_pmd(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long addr) { pgd_t *pgd; + p4d_t *p4d; pud_t *pud; pmd_t *pmd; pgd = pgd_offset(mm, addr); - pud = pud_alloc(mm, pgd, addr); + p4d = p4d_alloc(mm, pgd, addr); + if (!p4d) + return NULL; + pud = pud_alloc(mm, p4d, addr); if (!pud) return NULL; diff --git a/mm/page_alloc.c b/mm/page_alloc.c index eaa64d2ffdc5..6cbde310abed 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -873,7 +873,8 @@ done_merging: higher_page = page + (combined_pfn - pfn); buddy_pfn = __find_buddy_pfn(combined_pfn, order + 1); higher_buddy = higher_page + (buddy_pfn - combined_pfn); - if (page_is_buddy(higher_page, higher_buddy, order + 1)) { + if (pfn_valid_within(buddy_pfn) && + page_is_buddy(higher_page, higher_buddy, order + 1)) { list_add_tail(&page->lru, &zone->free_area[order].free_list[migratetype]); goto out; diff --git a/mm/page_vma_mapped.c b/mm/page_vma_mapped.c index a23001a22c15..c4c9def8ffea 100644 --- a/mm/page_vma_mapped.c +++ b/mm/page_vma_mapped.c @@ -104,6 +104,7 @@ bool page_vma_mapped_walk(struct page_vma_mapped_walk *pvmw) struct mm_struct *mm = pvmw->vma->vm_mm; struct page *page = pvmw->page; pgd_t *pgd; + p4d_t *p4d; pud_t *pud; /* The only possible pmd mapping has been handled on last iteration */ @@ -133,7 +134,10 @@ restart: pgd = pgd_offset(mm, pvmw->address); if (!pgd_present(*pgd)) return false; - pud = pud_offset(pgd, pvmw->address); + p4d = p4d_offset(pgd, pvmw->address); + if (!p4d_present(*p4d)) + return false; + pud = pud_offset(p4d, pvmw->address); if (!pud_present(*pud)) return false; pvmw->pmd = pmd_offset(pud, pvmw->address); diff --git a/mm/pagewalk.c b/mm/pagewalk.c index 03761577ae86..60f7856e508f 100644 --- a/mm/pagewalk.c +++ b/mm/pagewalk.c @@ -69,14 +69,14 @@ again: return err; } -static int walk_pud_range(pgd_t *pgd, unsigned long addr, unsigned long end, +static int walk_pud_range(p4d_t *p4d, unsigned long addr, unsigned long end, struct mm_walk *walk) { pud_t *pud; unsigned long next; int err = 0; - pud = pud_offset(pgd, addr); + pud = pud_offset(p4d, addr); do { again: next = pud_addr_end(addr, end); @@ -113,6 +113,32 @@ static int walk_pud_range(pgd_t *pgd, unsigned long addr, unsigned long end, return err; } +static int walk_p4d_range(pgd_t *pgd, unsigned long addr, unsigned long end, + struct mm_walk *walk) +{ + p4d_t *p4d; + unsigned long next; + int err = 0; + + p4d = p4d_offset(pgd, addr); + do { + next = p4d_addr_end(addr, end); + if (p4d_none_or_clear_bad(p4d)) { + if (walk->pte_hole) + err = walk->pte_hole(addr, next, walk); + if (err) + break; + continue; + } + if (walk->pmd_entry || walk->pte_entry) + err = walk_pud_range(p4d, addr, next, walk); + if (err) + break; + } while (p4d++, addr = next, addr != end); + + return err; +} + static int walk_pgd_range(unsigned long addr, unsigned long end, struct mm_walk *walk) { @@ -131,7 +157,7 @@ static int walk_pgd_range(unsigned long addr, unsigned long end, continue; } if (walk->pmd_entry || walk->pte_entry) - err = walk_pud_range(pgd, addr, next, walk); + err = walk_p4d_range(pgd, addr, next, walk); if (err) break; } while (pgd++, addr = next, addr != end); diff --git a/mm/percpu-vm.c b/mm/percpu-vm.c index 538998a137d2..9ac639499bd1 100644 --- a/mm/percpu-vm.c +++ b/mm/percpu-vm.c @@ -21,7 +21,6 @@ static struct page *pcpu_chunk_page(struct pcpu_chunk *chunk, /** * pcpu_get_pages - get temp pages array - * @chunk: chunk of interest * * Returns pointer to array of pointers to struct page which can be indexed * with pcpu_page_idx(). Note that there is only one array and accesses @@ -30,7 +29,7 @@ static struct page *pcpu_chunk_page(struct pcpu_chunk *chunk, * RETURNS: * Pointer to temp pages array on success. */ -static struct page **pcpu_get_pages(struct pcpu_chunk *chunk_alloc) +static struct page **pcpu_get_pages(void) { static struct page **pages; size_t pages_size = pcpu_nr_units * pcpu_unit_pages * sizeof(pages[0]); @@ -275,7 +274,7 @@ static int pcpu_populate_chunk(struct pcpu_chunk *chunk, { struct page **pages; - pages = pcpu_get_pages(chunk); + pages = pcpu_get_pages(); if (!pages) return -ENOMEM; @@ -313,7 +312,7 @@ static void pcpu_depopulate_chunk(struct pcpu_chunk *chunk, * successful population attempt so the temp pages array must * be available now. */ - pages = pcpu_get_pages(chunk); + pages = pcpu_get_pages(); BUG_ON(!pages); /* unmap and free */ diff --git a/mm/percpu.c b/mm/percpu.c index 5696039b5c07..60a6488e9e6d 100644 --- a/mm/percpu.c +++ b/mm/percpu.c @@ -1011,8 +1011,11 @@ area_found: mutex_unlock(&pcpu_alloc_mutex); } - if (chunk != pcpu_reserved_chunk) + if (chunk != pcpu_reserved_chunk) { + spin_lock_irqsave(&pcpu_lock, flags); pcpu_nr_empty_pop_pages -= occ_pages; + spin_unlock_irqrestore(&pcpu_lock, flags); + } if (pcpu_nr_empty_pop_pages < PCPU_EMPTY_POP_PAGES_LOW) pcpu_schedule_balance_work(); diff --git a/mm/pgtable-generic.c b/mm/pgtable-generic.c index 4ed5908c65b0..c99d9512a45b 100644 --- a/mm/pgtable-generic.c +++ b/mm/pgtable-generic.c @@ -22,6 +22,12 @@ void pgd_clear_bad(pgd_t *pgd) pgd_clear(pgd); } +void p4d_clear_bad(p4d_t *p4d) +{ + p4d_ERROR(*p4d); + p4d_clear(p4d); +} + void pud_clear_bad(pud_t *pud) { pud_ERROR(*pud); diff --git a/mm/rmap.c b/mm/rmap.c index 2da487d6cea8..49ed681ccc7b 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -684,6 +684,7 @@ unsigned long page_address_in_vma(struct page *page, struct vm_area_struct *vma) pmd_t *mm_find_pmd(struct mm_struct *mm, unsigned long address) { pgd_t *pgd; + p4d_t *p4d; pud_t *pud; pmd_t *pmd = NULL; pmd_t pmde; @@ -692,7 +693,11 @@ pmd_t *mm_find_pmd(struct mm_struct *mm, unsigned long address) if (!pgd_present(*pgd)) goto out; - pud = pud_offset(pgd, address); + p4d = p4d_offset(pgd, address); + if (!p4d_present(*p4d)) + goto out; + + pud = pud_offset(p4d, address); if (!pud_present(*pud)) goto out; @@ -1316,12 +1321,6 @@ static int try_to_unmap_one(struct page *page, struct vm_area_struct *vma, } while (page_vma_mapped_walk(&pvmw)) { - subpage = page - page_to_pfn(page) + pte_pfn(*pvmw.pte); - address = pvmw.address; - - /* Unexpected PMD-mapped THP? */ - VM_BUG_ON_PAGE(!pvmw.pte, page); - /* * If the page is mlock()d, we cannot swap it out. * If it's recently referenced (perhaps page_referenced @@ -1345,6 +1344,13 @@ static int try_to_unmap_one(struct page *page, struct vm_area_struct *vma, continue; } + /* Unexpected PMD-mapped THP? */ + VM_BUG_ON_PAGE(!pvmw.pte, page); + + subpage = page - page_to_pfn(page) + pte_pfn(*pvmw.pte); + address = pvmw.address; + + if (!(flags & TTU_IGNORE_ACCESS)) { if (ptep_clear_flush_young_notify(vma, address, pvmw.pte)) { diff --git a/mm/sparse-vmemmap.c b/mm/sparse-vmemmap.c index 574c67b663fe..a56c3989f773 100644 --- a/mm/sparse-vmemmap.c +++ b/mm/sparse-vmemmap.c @@ -196,9 +196,9 @@ pmd_t * __meminit vmemmap_pmd_populate(pud_t *pud, unsigned long addr, int node) return pmd; } -pud_t * __meminit vmemmap_pud_populate(pgd_t *pgd, unsigned long addr, int node) +pud_t * __meminit vmemmap_pud_populate(p4d_t *p4d, unsigned long addr, int node) { - pud_t *pud = pud_offset(pgd, addr); + pud_t *pud = pud_offset(p4d, addr); if (pud_none(*pud)) { void *p = vmemmap_alloc_block(PAGE_SIZE, node); if (!p) @@ -208,6 +208,18 @@ pud_t * __meminit vmemmap_pud_populate(pgd_t *pgd, unsigned long addr, int node) return pud; } +p4d_t * __meminit vmemmap_p4d_populate(pgd_t *pgd, unsigned long addr, int node) +{ + p4d_t *p4d = p4d_offset(pgd, addr); + if (p4d_none(*p4d)) { + void *p = vmemmap_alloc_block(PAGE_SIZE, node); + if (!p) + return NULL; + p4d_populate(&init_mm, p4d, p); + } + return p4d; +} + pgd_t * __meminit vmemmap_pgd_populate(unsigned long addr, int node) { pgd_t *pgd = pgd_offset_k(addr); @@ -225,6 +237,7 @@ int __meminit vmemmap_populate_basepages(unsigned long start, { unsigned long addr = start; pgd_t *pgd; + p4d_t *p4d; pud_t *pud; pmd_t *pmd; pte_t *pte; @@ -233,7 +246,10 @@ int __meminit vmemmap_populate_basepages(unsigned long start, pgd = vmemmap_pgd_populate(addr, node); if (!pgd) return -ENOMEM; - pud = vmemmap_pud_populate(pgd, addr, node); + p4d = vmemmap_p4d_populate(pgd, addr, node); + if (!p4d) + return -ENOMEM; + pud = vmemmap_pud_populate(p4d, addr, node); if (!pud) return -ENOMEM; pmd = vmemmap_pmd_populate(pud, addr, node); diff --git a/mm/swapfile.c b/mm/swapfile.c index 521ef9b6064f..178130880b90 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -1517,7 +1517,7 @@ static inline int unuse_pmd_range(struct vm_area_struct *vma, pud_t *pud, return 0; } -static inline int unuse_pud_range(struct vm_area_struct *vma, pgd_t *pgd, +static inline int unuse_pud_range(struct vm_area_struct *vma, p4d_t *p4d, unsigned long addr, unsigned long end, swp_entry_t entry, struct page *page) { @@ -1525,7 +1525,7 @@ static inline int unuse_pud_range(struct vm_area_struct *vma, pgd_t *pgd, unsigned long next; int ret; - pud = pud_offset(pgd, addr); + pud = pud_offset(p4d, addr); do { next = pud_addr_end(addr, end); if (pud_none_or_clear_bad(pud)) @@ -1537,6 +1537,26 @@ static inline int unuse_pud_range(struct vm_area_struct *vma, pgd_t *pgd, return 0; } +static inline int unuse_p4d_range(struct vm_area_struct *vma, pgd_t *pgd, + unsigned long addr, unsigned long end, + swp_entry_t entry, struct page *page) +{ + p4d_t *p4d; + unsigned long next; + int ret; + + p4d = p4d_offset(pgd, addr); + do { + next = p4d_addr_end(addr, end); + if (p4d_none_or_clear_bad(p4d)) + continue; + ret = unuse_pud_range(vma, p4d, addr, next, entry, page); + if (ret) + return ret; + } while (p4d++, addr = next, addr != end); + return 0; +} + static int unuse_vma(struct vm_area_struct *vma, swp_entry_t entry, struct page *page) { @@ -1560,7 +1580,7 @@ static int unuse_vma(struct vm_area_struct *vma, next = pgd_addr_end(addr, end); if (pgd_none_or_clear_bad(pgd)) continue; - ret = unuse_pud_range(vma, pgd, addr, next, entry, page); + ret = unuse_p4d_range(vma, pgd, addr, next, entry, page); if (ret) return ret; } while (pgd++, addr = next, addr != end); diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c index 479e631d43c2..8bcb501bce60 100644 --- a/mm/userfaultfd.c +++ b/mm/userfaultfd.c @@ -128,19 +128,22 @@ out_unlock: static pmd_t *mm_alloc_pmd(struct mm_struct *mm, unsigned long address) { pgd_t *pgd; + p4d_t *p4d; pud_t *pud; - pmd_t *pmd = NULL; pgd = pgd_offset(mm, address); - pud = pud_alloc(mm, pgd, address); - if (pud) - /* - * Note that we didn't run this because the pmd was - * missing, the *pmd may be already established and in - * turn it may also be a trans_huge_pmd. - */ - pmd = pmd_alloc(mm, pud, address); - return pmd; + p4d = p4d_alloc(mm, pgd, address); + if (!p4d) + return NULL; + pud = pud_alloc(mm, p4d, address); + if (!pud) + return NULL; + /* + * Note that we didn't run this because the pmd was + * missing, the *pmd may be already established and in + * turn it may also be a trans_huge_pmd. + */ + return pmd_alloc(mm, pud, address); } #ifdef CONFIG_HUGETLB_PAGE diff --git a/mm/vmalloc.c b/mm/vmalloc.c index b4024d688f38..0dd80222b20b 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -86,12 +86,12 @@ static void vunmap_pmd_range(pud_t *pud, unsigned long addr, unsigned long end) } while (pmd++, addr = next, addr != end); } -static void vunmap_pud_range(pgd_t *pgd, unsigned long addr, unsigned long end) +static void vunmap_pud_range(p4d_t *p4d, unsigned long addr, unsigned long end) { pud_t *pud; unsigned long next; - pud = pud_offset(pgd, addr); + pud = pud_offset(p4d, addr); do { next = pud_addr_end(addr, end); if (pud_clear_huge(pud)) @@ -102,6 +102,22 @@ static void vunmap_pud_range(pgd_t *pgd, unsigned long addr, unsigned long end) } while (pud++, addr = next, addr != end); } +static void vunmap_p4d_range(pgd_t *pgd, unsigned long addr, unsigned long end) +{ + p4d_t *p4d; + unsigned long next; + + p4d = p4d_offset(pgd, addr); + do { + next = p4d_addr_end(addr, end); + if (p4d_clear_huge(p4d)) + continue; + if (p4d_none_or_clear_bad(p4d)) + continue; + vunmap_pud_range(p4d, addr, next); + } while (p4d++, addr = next, addr != end); +} + static void vunmap_page_range(unsigned long addr, unsigned long end) { pgd_t *pgd; @@ -113,7 +129,7 @@ static void vunmap_page_range(unsigned long addr, unsigned long end) next = pgd_addr_end(addr, end); if (pgd_none_or_clear_bad(pgd)) continue; - vunmap_pud_range(pgd, addr, next); + vunmap_p4d_range(pgd, addr, next); } while (pgd++, addr = next, addr != end); } @@ -160,13 +176,13 @@ static int vmap_pmd_range(pud_t *pud, unsigned long addr, return 0; } -static int vmap_pud_range(pgd_t *pgd, unsigned long addr, +static int vmap_pud_range(p4d_t *p4d, unsigned long addr, unsigned long end, pgprot_t prot, struct page **pages, int *nr) { pud_t *pud; unsigned long next; - pud = pud_alloc(&init_mm, pgd, addr); + pud = pud_alloc(&init_mm, p4d, addr); if (!pud) return -ENOMEM; do { @@ -177,6 +193,23 @@ static int vmap_pud_range(pgd_t *pgd, unsigned long addr, return 0; } +static int vmap_p4d_range(pgd_t *pgd, unsigned long addr, + unsigned long end, pgprot_t prot, struct page **pages, int *nr) +{ + p4d_t *p4d; + unsigned long next; + + p4d = p4d_alloc(&init_mm, pgd, addr); + if (!p4d) + return -ENOMEM; + do { + next = p4d_addr_end(addr, end); + if (vmap_pud_range(p4d, addr, next, prot, pages, nr)) + return -ENOMEM; + } while (p4d++, addr = next, addr != end); + return 0; +} + /* * Set up page tables in kva (addr, end). The ptes shall have prot "prot", and * will have pfns corresponding to the "pages" array. @@ -196,7 +229,7 @@ static int vmap_page_range_noflush(unsigned long start, unsigned long end, pgd = pgd_offset_k(addr); do { next = pgd_addr_end(addr, end); - err = vmap_pud_range(pgd, addr, next, prot, pages, &nr); + err = vmap_p4d_range(pgd, addr, next, prot, pages, &nr); if (err) return err; } while (pgd++, addr = next, addr != end); @@ -237,6 +270,10 @@ struct page *vmalloc_to_page(const void *vmalloc_addr) unsigned long addr = (unsigned long) vmalloc_addr; struct page *page = NULL; pgd_t *pgd = pgd_offset_k(addr); + p4d_t *p4d; + pud_t *pud; + pmd_t *pmd; + pte_t *ptep, pte; /* * XXX we might need to change this if we add VIRTUAL_BUG_ON for @@ -244,21 +281,23 @@ struct page *vmalloc_to_page(const void *vmalloc_addr) */ VIRTUAL_BUG_ON(!is_vmalloc_or_module_addr(vmalloc_addr)); - if (!pgd_none(*pgd)) { - pud_t *pud = pud_offset(pgd, addr); - if (!pud_none(*pud)) { - pmd_t *pmd = pmd_offset(pud, addr); - if (!pmd_none(*pmd)) { - pte_t *ptep, pte; - - ptep = pte_offset_map(pmd, addr); - pte = *ptep; - if (pte_present(pte)) - page = pte_page(pte); - pte_unmap(ptep); - } - } - } + if (pgd_none(*pgd)) + return NULL; + p4d = p4d_offset(pgd, addr); + if (p4d_none(*p4d)) + return NULL; + pud = pud_offset(p4d, addr); + if (pud_none(*pud)) + return NULL; + pmd = pmd_offset(pud, addr); + if (pmd_none(*pmd)) + return NULL; + + ptep = pte_offset_map(pmd, addr); + pte = *ptep; + if (pte_present(pte)) + page = pte_page(pte); + pte_unmap(ptep); return page; } EXPORT_SYMBOL(vmalloc_to_page); diff --git a/mm/vmstat.c b/mm/vmstat.c index 69f9aff39a2e..b1947f0cbee2 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -1065,6 +1065,9 @@ const char * const vmstat_text[] = { "thp_split_page_failed", "thp_deferred_split_page", "thp_split_pmd", +#ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD + "thp_split_pud", +#endif "thp_zero_page_alloc", "thp_zero_page_alloc_failed", #endif diff --git a/net/atm/common.c b/net/atm/common.c index 9613381f5db0..f06422f4108d 100644 --- a/net/atm/common.c +++ b/net/atm/common.c @@ -62,21 +62,16 @@ static void vcc_remove_socket(struct sock *sk) write_unlock_irq(&vcc_sklist_lock); } -static struct sk_buff *alloc_tx(struct atm_vcc *vcc, unsigned int size) +static bool vcc_tx_ready(struct atm_vcc *vcc, unsigned int size) { - struct sk_buff *skb; struct sock *sk = sk_atm(vcc); if (sk_wmem_alloc_get(sk) && !atm_may_send(vcc, size)) { pr_debug("Sorry: wmem_alloc = %d, size = %d, sndbuf = %d\n", sk_wmem_alloc_get(sk), size, sk->sk_sndbuf); - return NULL; + return false; } - while (!(skb = alloc_skb(size, GFP_KERNEL))) - schedule(); - pr_debug("%d += %d\n", sk_wmem_alloc_get(sk), skb->truesize); - atomic_add(skb->truesize, &sk->sk_wmem_alloc); - return skb; + return true; } static void vcc_sock_destruct(struct sock *sk) @@ -606,7 +601,7 @@ int vcc_sendmsg(struct socket *sock, struct msghdr *m, size_t size) eff = (size+3) & ~3; /* align to word boundary */ prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); error = 0; - while (!(skb = alloc_tx(vcc, eff))) { + while (!vcc_tx_ready(vcc, eff)) { if (m->msg_flags & MSG_DONTWAIT) { error = -EAGAIN; break; @@ -628,6 +623,15 @@ int vcc_sendmsg(struct socket *sock, struct msghdr *m, size_t size) finish_wait(sk_sleep(sk), &wait); if (error) goto out; + + skb = alloc_skb(eff, GFP_KERNEL); + if (!skb) { + error = -ENOMEM; + goto out; + } + pr_debug("%d += %d\n", sk_wmem_alloc_get(sk), skb->truesize); + atomic_add(skb->truesize, &sk->sk_wmem_alloc); + skb->dev = NULL; /* for paths shared with net_device interfaces */ ATM_SKB(skb)->atm_options = vcc->atm_options; if (!copy_from_iter_full(skb_put(skb, size), size, &m->msg_iter)) { diff --git a/net/atm/svc.c b/net/atm/svc.c index db9794ec61d8..5589de7086af 100644 --- a/net/atm/svc.c +++ b/net/atm/svc.c @@ -318,7 +318,8 @@ out: return error; } -static int svc_accept(struct socket *sock, struct socket *newsock, int flags) +static int svc_accept(struct socket *sock, struct socket *newsock, int flags, + bool kern) { struct sock *sk = sock->sk; struct sk_buff *skb; @@ -329,7 +330,7 @@ static int svc_accept(struct socket *sock, struct socket *newsock, int flags) lock_sock(sk); - error = svc_create(sock_net(sk), newsock, 0, 0); + error = svc_create(sock_net(sk), newsock, 0, kern); if (error) goto out; diff --git a/net/ax25/af_ax25.c b/net/ax25/af_ax25.c index a8e42cedf1db..b7c486752b3a 100644 --- a/net/ax25/af_ax25.c +++ b/net/ax25/af_ax25.c @@ -1320,7 +1320,8 @@ out_release: return err; } -static int ax25_accept(struct socket *sock, struct socket *newsock, int flags) +static int ax25_accept(struct socket *sock, struct socket *newsock, int flags, + bool kern) { struct sk_buff *skb; struct sock *newsk; diff --git a/net/bluetooth/l2cap_sock.c b/net/bluetooth/l2cap_sock.c index f307b145ea54..507b80d59dec 100644 --- a/net/bluetooth/l2cap_sock.c +++ b/net/bluetooth/l2cap_sock.c @@ -301,7 +301,7 @@ done: } static int l2cap_sock_accept(struct socket *sock, struct socket *newsock, - int flags) + int flags, bool kern) { DEFINE_WAIT_FUNC(wait, woken_wake_function); struct sock *sk = sock->sk, *nsk; diff --git a/net/bluetooth/rfcomm/sock.c b/net/bluetooth/rfcomm/sock.c index aa1a814ceddc..ac3c650cb234 100644 --- a/net/bluetooth/rfcomm/sock.c +++ b/net/bluetooth/rfcomm/sock.c @@ -471,7 +471,8 @@ done: return err; } -static int rfcomm_sock_accept(struct socket *sock, struct socket *newsock, int flags) +static int rfcomm_sock_accept(struct socket *sock, struct socket *newsock, int flags, + bool kern) { DEFINE_WAIT_FUNC(wait, woken_wake_function); struct sock *sk = sock->sk, *nsk; diff --git a/net/bluetooth/sco.c b/net/bluetooth/sco.c index e4e9a2da1e7e..728e0c8dc8e7 100644 --- a/net/bluetooth/sco.c +++ b/net/bluetooth/sco.c @@ -627,7 +627,7 @@ done: } static int sco_sock_accept(struct socket *sock, struct socket *newsock, - int flags) + int flags, bool kern) { DEFINE_WAIT_FUNC(wait, woken_wake_function); struct sock *sk = sock->sk, *ch; diff --git a/net/bridge/br_input.c b/net/bridge/br_input.c index 236f34244dbe..013f2290bfa5 100644 --- a/net/bridge/br_input.c +++ b/net/bridge/br_input.c @@ -30,6 +30,7 @@ EXPORT_SYMBOL(br_should_route_hook); static int br_netif_receive_skb(struct net *net, struct sock *sk, struct sk_buff *skb) { + br_drop_fake_rtable(skb); return netif_receive_skb(skb); } diff --git a/net/bridge/br_netfilter_hooks.c b/net/bridge/br_netfilter_hooks.c index 52739e6c610e..d20b01b8d103 100644 --- a/net/bridge/br_netfilter_hooks.c +++ b/net/bridge/br_netfilter_hooks.c @@ -521,21 +521,6 @@ static unsigned int br_nf_pre_routing(void *priv, } -/* PF_BRIDGE/LOCAL_IN ************************************************/ -/* The packet is locally destined, which requires a real - * dst_entry, so detach the fake one. On the way up, the - * packet would pass through PRE_ROUTING again (which already - * took place when the packet entered the bridge), but we - * register an IPv4 PRE_ROUTING 'sabotage' hook that will - * prevent this from happening. */ -static unsigned int br_nf_local_in(void *priv, - struct sk_buff *skb, - const struct nf_hook_state *state) -{ - br_drop_fake_rtable(skb); - return NF_ACCEPT; -} - /* PF_BRIDGE/FORWARD *************************************************/ static int br_nf_forward_finish(struct net *net, struct sock *sk, struct sk_buff *skb) { @@ -908,12 +893,6 @@ static struct nf_hook_ops br_nf_ops[] __read_mostly = { .priority = NF_BR_PRI_BRNF, }, { - .hook = br_nf_local_in, - .pf = NFPROTO_BRIDGE, - .hooknum = NF_BR_LOCAL_IN, - .priority = NF_BR_PRI_BRNF, - }, - { .hook = br_nf_forward_ip, .pf = NFPROTO_BRIDGE, .hooknum = NF_BR_FORWARD, diff --git a/net/ceph/ceph_common.c b/net/ceph/ceph_common.c index 464e88599b9d..108533859a53 100644 --- a/net/ceph/ceph_common.c +++ b/net/ceph/ceph_common.c @@ -230,6 +230,7 @@ enum { Opt_osdkeepalivetimeout, Opt_mount_timeout, Opt_osd_idle_ttl, + Opt_osd_request_timeout, Opt_last_int, /* int args above */ Opt_fsid, @@ -256,6 +257,7 @@ static match_table_t opt_tokens = { {Opt_osdkeepalivetimeout, "osdkeepalive=%d"}, {Opt_mount_timeout, "mount_timeout=%d"}, {Opt_osd_idle_ttl, "osd_idle_ttl=%d"}, + {Opt_osd_request_timeout, "osd_request_timeout=%d"}, /* int args above */ {Opt_fsid, "fsid=%s"}, {Opt_name, "name=%s"}, @@ -361,6 +363,7 @@ ceph_parse_options(char *options, const char *dev_name, opt->osd_keepalive_timeout = CEPH_OSD_KEEPALIVE_DEFAULT; opt->mount_timeout = CEPH_MOUNT_TIMEOUT_DEFAULT; opt->osd_idle_ttl = CEPH_OSD_IDLE_TTL_DEFAULT; + opt->osd_request_timeout = CEPH_OSD_REQUEST_TIMEOUT_DEFAULT; /* get mon ip(s) */ /* ip1[:port1][,ip2[:port2]...] */ @@ -473,6 +476,15 @@ ceph_parse_options(char *options, const char *dev_name, } opt->mount_timeout = msecs_to_jiffies(intval * 1000); break; + case Opt_osd_request_timeout: + /* 0 is "wait forever" (i.e. infinite timeout) */ + if (intval < 0 || intval > INT_MAX / 1000) { + pr_err("osd_request_timeout out of range\n"); + err = -EINVAL; + goto out; + } + opt->osd_request_timeout = msecs_to_jiffies(intval * 1000); + break; case Opt_share: opt->flags &= ~CEPH_OPT_NOSHARE; @@ -557,6 +569,9 @@ int ceph_print_client_options(struct seq_file *m, struct ceph_client *client) if (opt->osd_keepalive_timeout != CEPH_OSD_KEEPALIVE_DEFAULT) seq_printf(m, "osdkeepalivetimeout=%d,", jiffies_to_msecs(opt->osd_keepalive_timeout) / 1000); + if (opt->osd_request_timeout != CEPH_OSD_REQUEST_TIMEOUT_DEFAULT) + seq_printf(m, "osd_request_timeout=%d,", + jiffies_to_msecs(opt->osd_request_timeout) / 1000); /* drop redundant comma */ if (m->count != pos) diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c index b65bbf9f45eb..e15ea9e4c495 100644 --- a/net/ceph/osd_client.c +++ b/net/ceph/osd_client.c @@ -1709,6 +1709,8 @@ static void account_request(struct ceph_osd_request *req) req->r_flags |= CEPH_OSD_FLAG_ONDISK; atomic_inc(&req->r_osdc->num_requests); + + req->r_start_stamp = jiffies; } static void submit_request(struct ceph_osd_request *req, bool wrlocked) @@ -1789,6 +1791,14 @@ static void cancel_request(struct ceph_osd_request *req) ceph_osdc_put_request(req); } +static void abort_request(struct ceph_osd_request *req, int err) +{ + dout("%s req %p tid %llu err %d\n", __func__, req, req->r_tid, err); + + cancel_map_check(req); + complete_request(req, err); +} + static void check_pool_dne(struct ceph_osd_request *req) { struct ceph_osd_client *osdc = req->r_osdc; @@ -2487,6 +2497,7 @@ static void handle_timeout(struct work_struct *work) container_of(work, struct ceph_osd_client, timeout_work.work); struct ceph_options *opts = osdc->client->options; unsigned long cutoff = jiffies - opts->osd_keepalive_timeout; + unsigned long expiry_cutoff = jiffies - opts->osd_request_timeout; LIST_HEAD(slow_osds); struct rb_node *n, *p; @@ -2502,15 +2513,23 @@ static void handle_timeout(struct work_struct *work) struct ceph_osd *osd = rb_entry(n, struct ceph_osd, o_node); bool found = false; - for (p = rb_first(&osd->o_requests); p; p = rb_next(p)) { + for (p = rb_first(&osd->o_requests); p; ) { struct ceph_osd_request *req = rb_entry(p, struct ceph_osd_request, r_node); + p = rb_next(p); /* abort_request() */ + if (time_before(req->r_stamp, cutoff)) { dout(" req %p tid %llu on osd%d is laggy\n", req, req->r_tid, osd->o_osd); found = true; } + if (opts->osd_request_timeout && + time_before(req->r_start_stamp, expiry_cutoff)) { + pr_err_ratelimited("tid %llu on osd%d timeout\n", + req->r_tid, osd->o_osd); + abort_request(req, -ETIMEDOUT); + } } for (p = rb_first(&osd->o_linger_requests); p; p = rb_next(p)) { struct ceph_osd_linger_request *lreq = @@ -2530,6 +2549,21 @@ static void handle_timeout(struct work_struct *work) list_move_tail(&osd->o_keepalive_item, &slow_osds); } + if (opts->osd_request_timeout) { + for (p = rb_first(&osdc->homeless_osd.o_requests); p; ) { + struct ceph_osd_request *req = + rb_entry(p, struct ceph_osd_request, r_node); + + p = rb_next(p); /* abort_request() */ + + if (time_before(req->r_start_stamp, expiry_cutoff)) { + pr_err_ratelimited("tid %llu on osd%d timeout\n", + req->r_tid, osdc->homeless_osd.o_osd); + abort_request(req, -ETIMEDOUT); + } + } + } + if (atomic_read(&osdc->num_homeless) || !list_empty(&slow_osds)) maybe_request_map(osdc); diff --git a/net/ceph/osdmap.c b/net/ceph/osdmap.c index 6824c0ec8373..ffe9e904d4d1 100644 --- a/net/ceph/osdmap.c +++ b/net/ceph/osdmap.c @@ -390,9 +390,8 @@ static struct crush_map *crush_decode(void *pbyval, void *end) dout("crush decode tunable chooseleaf_stable = %d\n", c->chooseleaf_stable); - crush_finalize(c); - done: + crush_finalize(c); dout("crush_decode success\n"); return c; @@ -1380,7 +1379,6 @@ static int decode_new_up_state_weight(void **p, void *end, if ((map->osd_state[osd] & CEPH_OSD_EXISTS) && (xorstate & CEPH_OSD_EXISTS)) { pr_info("osd%d does not exist\n", osd); - map->osd_weight[osd] = CEPH_OSD_IN; ret = set_primary_affinity(map, osd, CEPH_OSD_DEFAULT_PRIMARY_AFFINITY); if (ret) diff --git a/net/core/dev.c b/net/core/dev.c index 8637b2b71f3d..7869ae3837ca 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -1304,6 +1304,7 @@ void netdev_notify_peers(struct net_device *dev) { rtnl_lock(); call_netdevice_notifiers(NETDEV_NOTIFY_PEERS, dev); + call_netdevice_notifiers(NETDEV_RESEND_IGMP, dev); rtnl_unlock(); } EXPORT_SYMBOL(netdev_notify_peers); diff --git a/net/core/drop_monitor.c b/net/core/drop_monitor.c index fb55327dcfea..70ccda233bd1 100644 --- a/net/core/drop_monitor.c +++ b/net/core/drop_monitor.c @@ -412,9 +412,8 @@ static int __init init_net_drop_monitor(void) for_each_possible_cpu(cpu) { data = &per_cpu(dm_cpu_data, cpu); INIT_WORK(&data->dm_alert_work, send_dm_alert); - init_timer(&data->send_timer); - data->send_timer.data = (unsigned long)data; - data->send_timer.function = sched_send_work; + setup_timer(&data->send_timer, sched_send_work, + (unsigned long)data); spin_lock_init(&data->lock); reset_per_cpu_data(data); } diff --git a/net/core/ethtool.c b/net/core/ethtool.c index aecb2c7241b6..905a88ad28e0 100644 --- a/net/core/ethtool.c +++ b/net/core/ethtool.c @@ -109,6 +109,7 @@ static const char rss_hash_func_strings[ETH_RSS_HASH_FUNCS_COUNT][ETH_GSTRING_LEN] = { [ETH_RSS_HASH_TOP_BIT] = "toeplitz", [ETH_RSS_HASH_XOR_BIT] = "xor", + [ETH_RSS_HASH_CRC32_BIT] = "crc32", }; static const char diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c index b6791d94841d..816e3ccb0ec9 100644 --- a/net/core/fib_rules.c +++ b/net/core/fib_rules.c @@ -23,6 +23,20 @@ static const struct fib_kuid_range fib_kuid_range_unset = { KUIDT_INIT(~0), }; +bool fib_rule_matchall(const struct fib_rule *rule) +{ + if (rule->iifindex || rule->oifindex || rule->mark || rule->tun_id || + rule->flags) + return false; + if (rule->suppress_ifgroup != -1 || rule->suppress_prefixlen != -1) + return false; + if (!uid_eq(rule->uid_range.start, fib_kuid_range_unset.start) || + !uid_eq(rule->uid_range.end, fib_kuid_range_unset.end)) + return false; + return true; +} +EXPORT_SYMBOL_GPL(fib_rule_matchall); + int fib_default_rule_add(struct fib_rules_ops *ops, u32 pref, u32 table, u32 flags) { diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c index c35aae13c8d2..5f3ae922fcd1 100644 --- a/net/core/flow_dissector.c +++ b/net/core/flow_dissector.c @@ -113,6 +113,216 @@ __be32 __skb_flow_get_ports(const struct sk_buff *skb, int thoff, u8 ip_proto, } EXPORT_SYMBOL(__skb_flow_get_ports); +enum flow_dissect_ret { + FLOW_DISSECT_RET_OUT_GOOD, + FLOW_DISSECT_RET_OUT_BAD, + FLOW_DISSECT_RET_OUT_PROTO_AGAIN, +}; + +static enum flow_dissect_ret +__skb_flow_dissect_mpls(const struct sk_buff *skb, + struct flow_dissector *flow_dissector, + void *target_container, void *data, int nhoff, int hlen) +{ + struct flow_dissector_key_keyid *key_keyid; + struct mpls_label *hdr, _hdr[2]; + + if (!dissector_uses_key(flow_dissector, + FLOW_DISSECTOR_KEY_MPLS_ENTROPY)) + return FLOW_DISSECT_RET_OUT_GOOD; + + hdr = __skb_header_pointer(skb, nhoff, sizeof(_hdr), data, + hlen, &_hdr); + if (!hdr) + return FLOW_DISSECT_RET_OUT_BAD; + + if ((ntohl(hdr[0].entry) & MPLS_LS_LABEL_MASK) >> + MPLS_LS_LABEL_SHIFT == MPLS_LABEL_ENTROPY) { + key_keyid = skb_flow_dissector_target(flow_dissector, + FLOW_DISSECTOR_KEY_MPLS_ENTROPY, + target_container); + key_keyid->keyid = hdr[1].entry & htonl(MPLS_LS_LABEL_MASK); + } + return FLOW_DISSECT_RET_OUT_GOOD; +} + +static enum flow_dissect_ret +__skb_flow_dissect_arp(const struct sk_buff *skb, + struct flow_dissector *flow_dissector, + void *target_container, void *data, int nhoff, int hlen) +{ + struct flow_dissector_key_arp *key_arp; + struct { + unsigned char ar_sha[ETH_ALEN]; + unsigned char ar_sip[4]; + unsigned char ar_tha[ETH_ALEN]; + unsigned char ar_tip[4]; + } *arp_eth, _arp_eth; + const struct arphdr *arp; + struct arphdr *_arp; + + if (!dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_ARP)) + return FLOW_DISSECT_RET_OUT_GOOD; + + arp = __skb_header_pointer(skb, nhoff, sizeof(_arp), data, + hlen, &_arp); + if (!arp) + return FLOW_DISSECT_RET_OUT_BAD; + + if (arp->ar_hrd != htons(ARPHRD_ETHER) || + arp->ar_pro != htons(ETH_P_IP) || + arp->ar_hln != ETH_ALEN || + arp->ar_pln != 4 || + (arp->ar_op != htons(ARPOP_REPLY) && + arp->ar_op != htons(ARPOP_REQUEST))) + return FLOW_DISSECT_RET_OUT_BAD; + + arp_eth = __skb_header_pointer(skb, nhoff + sizeof(_arp), + sizeof(_arp_eth), data, + hlen, &_arp_eth); + if (!arp_eth) + return FLOW_DISSECT_RET_OUT_BAD; + + key_arp = skb_flow_dissector_target(flow_dissector, + FLOW_DISSECTOR_KEY_ARP, + target_container); + + memcpy(&key_arp->sip, arp_eth->ar_sip, sizeof(key_arp->sip)); + memcpy(&key_arp->tip, arp_eth->ar_tip, sizeof(key_arp->tip)); + + /* Only store the lower byte of the opcode; + * this covers ARPOP_REPLY and ARPOP_REQUEST. + */ + key_arp->op = ntohs(arp->ar_op) & 0xff; + + ether_addr_copy(key_arp->sha, arp_eth->ar_sha); + ether_addr_copy(key_arp->tha, arp_eth->ar_tha); + + return FLOW_DISSECT_RET_OUT_GOOD; +} + +static enum flow_dissect_ret +__skb_flow_dissect_gre(const struct sk_buff *skb, + struct flow_dissector_key_control *key_control, + struct flow_dissector *flow_dissector, + void *target_container, void *data, + __be16 *p_proto, int *p_nhoff, int *p_hlen, + unsigned int flags) +{ + struct flow_dissector_key_keyid *key_keyid; + struct gre_base_hdr *hdr, _hdr; + int offset = 0; + u16 gre_ver; + + hdr = __skb_header_pointer(skb, *p_nhoff, sizeof(_hdr), + data, *p_hlen, &_hdr); + if (!hdr) + return FLOW_DISSECT_RET_OUT_BAD; + + /* Only look inside GRE without routing */ + if (hdr->flags & GRE_ROUTING) + return FLOW_DISSECT_RET_OUT_GOOD; + + /* Only look inside GRE for version 0 and 1 */ + gre_ver = ntohs(hdr->flags & GRE_VERSION); + if (gre_ver > 1) + return FLOW_DISSECT_RET_OUT_GOOD; + + *p_proto = hdr->protocol; + if (gre_ver) { + /* Version1 must be PPTP, and check the flags */ + if (!(*p_proto == GRE_PROTO_PPP && (hdr->flags & GRE_KEY))) + return FLOW_DISSECT_RET_OUT_GOOD; + } + + offset += sizeof(struct gre_base_hdr); + + if (hdr->flags & GRE_CSUM) + offset += sizeof(((struct gre_full_hdr *) 0)->csum) + + sizeof(((struct gre_full_hdr *) 0)->reserved1); + + if (hdr->flags & GRE_KEY) { + const __be32 *keyid; + __be32 _keyid; + + keyid = __skb_header_pointer(skb, *p_nhoff + offset, + sizeof(_keyid), + data, *p_hlen, &_keyid); + if (!keyid) + return FLOW_DISSECT_RET_OUT_BAD; + + if (dissector_uses_key(flow_dissector, + FLOW_DISSECTOR_KEY_GRE_KEYID)) { + key_keyid = skb_flow_dissector_target(flow_dissector, + FLOW_DISSECTOR_KEY_GRE_KEYID, + target_container); + if (gre_ver == 0) + key_keyid->keyid = *keyid; + else + key_keyid->keyid = *keyid & GRE_PPTP_KEY_MASK; + } + offset += sizeof(((struct gre_full_hdr *) 0)->key); + } + + if (hdr->flags & GRE_SEQ) + offset += sizeof(((struct pptp_gre_header *) 0)->seq); + + if (gre_ver == 0) { + if (*p_proto == htons(ETH_P_TEB)) { + const struct ethhdr *eth; + struct ethhdr _eth; + + eth = __skb_header_pointer(skb, *p_nhoff + offset, + sizeof(_eth), + data, *p_hlen, &_eth); + if (!eth) + return FLOW_DISSECT_RET_OUT_BAD; + *p_proto = eth->h_proto; + offset += sizeof(*eth); + + /* Cap headers that we access via pointers at the + * end of the Ethernet header as our maximum alignment + * at that point is only 2 bytes. + */ + if (NET_IP_ALIGN) + *p_hlen = *p_nhoff + offset; + } + } else { /* version 1, must be PPTP */ + u8 _ppp_hdr[PPP_HDRLEN]; + u8 *ppp_hdr; + + if (hdr->flags & GRE_ACK) + offset += sizeof(((struct pptp_gre_header *) 0)->ack); + + ppp_hdr = __skb_header_pointer(skb, *p_nhoff + offset, + sizeof(_ppp_hdr), + data, *p_hlen, _ppp_hdr); + if (!ppp_hdr) + return FLOW_DISSECT_RET_OUT_BAD; + + switch (PPP_PROTOCOL(ppp_hdr)) { + case PPP_IP: + *p_proto = htons(ETH_P_IP); + break; + case PPP_IPV6: + *p_proto = htons(ETH_P_IPV6); + break; + default: + /* Could probably catch some more like MPLS */ + break; + } + + offset += PPP_HDRLEN; + } + + *p_nhoff += offset; + key_control->flags |= FLOW_DIS_ENCAPSULATION; + if (flags & FLOW_DISSECTOR_F_STOP_AT_ENCAP) + return FLOW_DISSECT_RET_OUT_GOOD; + + return FLOW_DISSECT_RET_OUT_PROTO_AGAIN; +} + /** * __skb_flow_dissect - extract the flow_keys struct and return it * @skb: sk_buff to extract the flow from, can be NULL if the rest are specified @@ -138,12 +348,10 @@ bool __skb_flow_dissect(const struct sk_buff *skb, struct flow_dissector_key_control *key_control; struct flow_dissector_key_basic *key_basic; struct flow_dissector_key_addrs *key_addrs; - struct flow_dissector_key_arp *key_arp; struct flow_dissector_key_ports *key_ports; struct flow_dissector_key_icmp *key_icmp; struct flow_dissector_key_tags *key_tags; struct flow_dissector_key_vlan *key_vlan; - struct flow_dissector_key_keyid *key_keyid; bool skip_vlan = false; u8 ip_proto = 0; bool ret; @@ -181,7 +389,7 @@ bool __skb_flow_dissect(const struct sk_buff *skb, memcpy(key_eth_addrs, ð->h_dest, sizeof(*key_eth_addrs)); } -again: +proto_again: switch (proto) { case htons(ETH_P_IP): { const struct iphdr *iph; @@ -284,7 +492,7 @@ ipv6: proto = vlan->h_vlan_encapsulated_proto; nhoff += sizeof(*vlan); if (skip_vlan) - goto again; + goto proto_again; } skip_vlan = true; @@ -307,7 +515,7 @@ ipv6: } } - goto again; + goto proto_again; } case htons(ETH_P_PPP_SES): { struct { @@ -349,31 +557,17 @@ ipv6: } case htons(ETH_P_MPLS_UC): - case htons(ETH_P_MPLS_MC): { - struct mpls_label *hdr, _hdr[2]; + case htons(ETH_P_MPLS_MC): mpls: - hdr = __skb_header_pointer(skb, nhoff, sizeof(_hdr), data, - hlen, &_hdr); - if (!hdr) - goto out_bad; - - if ((ntohl(hdr[0].entry) & MPLS_LS_LABEL_MASK) >> - MPLS_LS_LABEL_SHIFT == MPLS_LABEL_ENTROPY) { - if (dissector_uses_key(flow_dissector, - FLOW_DISSECTOR_KEY_MPLS_ENTROPY)) { - key_keyid = skb_flow_dissector_target(flow_dissector, - FLOW_DISSECTOR_KEY_MPLS_ENTROPY, - target_container); - key_keyid->keyid = hdr[1].entry & - htonl(MPLS_LS_LABEL_MASK); - } - + switch (__skb_flow_dissect_mpls(skb, flow_dissector, + target_container, data, + nhoff, hlen)) { + case FLOW_DISSECT_RET_OUT_GOOD: goto out_good; + case FLOW_DISSECT_RET_OUT_BAD: + default: + goto out_bad; } - - goto out_good; - } - case htons(ETH_P_FCOE): if ((hlen - nhoff) < FCOE_HEADER_LEN) goto out_bad; @@ -382,177 +576,33 @@ mpls: goto out_good; case htons(ETH_P_ARP): - case htons(ETH_P_RARP): { - struct { - unsigned char ar_sha[ETH_ALEN]; - unsigned char ar_sip[4]; - unsigned char ar_tha[ETH_ALEN]; - unsigned char ar_tip[4]; - } *arp_eth, _arp_eth; - const struct arphdr *arp; - struct arphdr *_arp; - - arp = __skb_header_pointer(skb, nhoff, sizeof(_arp), data, - hlen, &_arp); - if (!arp) - goto out_bad; - - if (arp->ar_hrd != htons(ARPHRD_ETHER) || - arp->ar_pro != htons(ETH_P_IP) || - arp->ar_hln != ETH_ALEN || - arp->ar_pln != 4 || - (arp->ar_op != htons(ARPOP_REPLY) && - arp->ar_op != htons(ARPOP_REQUEST))) - goto out_bad; - - arp_eth = __skb_header_pointer(skb, nhoff + sizeof(_arp), - sizeof(_arp_eth), data, - hlen, - &_arp_eth); - if (!arp_eth) + case htons(ETH_P_RARP): + switch (__skb_flow_dissect_arp(skb, flow_dissector, + target_container, data, + nhoff, hlen)) { + case FLOW_DISSECT_RET_OUT_GOOD: + goto out_good; + case FLOW_DISSECT_RET_OUT_BAD: + default: goto out_bad; - - if (dissector_uses_key(flow_dissector, - FLOW_DISSECTOR_KEY_ARP)) { - - key_arp = skb_flow_dissector_target(flow_dissector, - FLOW_DISSECTOR_KEY_ARP, - target_container); - - memcpy(&key_arp->sip, arp_eth->ar_sip, - sizeof(key_arp->sip)); - memcpy(&key_arp->tip, arp_eth->ar_tip, - sizeof(key_arp->tip)); - - /* Only store the lower byte of the opcode; - * this covers ARPOP_REPLY and ARPOP_REQUEST. - */ - key_arp->op = ntohs(arp->ar_op) & 0xff; - - ether_addr_copy(key_arp->sha, arp_eth->ar_sha); - ether_addr_copy(key_arp->tha, arp_eth->ar_tha); } - - goto out_good; - } - default: goto out_bad; } ip_proto_again: switch (ip_proto) { - case IPPROTO_GRE: { - struct gre_base_hdr *hdr, _hdr; - u16 gre_ver; - int offset = 0; - - hdr = __skb_header_pointer(skb, nhoff, sizeof(_hdr), data, hlen, &_hdr); - if (!hdr) + case IPPROTO_GRE: + switch (__skb_flow_dissect_gre(skb, key_control, flow_dissector, + target_container, data, + &proto, &nhoff, &hlen, flags)) { + case FLOW_DISSECT_RET_OUT_GOOD: + goto out_good; + case FLOW_DISSECT_RET_OUT_BAD: goto out_bad; - - /* Only look inside GRE without routing */ - if (hdr->flags & GRE_ROUTING) - break; - - /* Only look inside GRE for version 0 and 1 */ - gre_ver = ntohs(hdr->flags & GRE_VERSION); - if (gre_ver > 1) - break; - - proto = hdr->protocol; - if (gre_ver) { - /* Version1 must be PPTP, and check the flags */ - if (!(proto == GRE_PROTO_PPP && (hdr->flags & GRE_KEY))) - break; - } - - offset += sizeof(struct gre_base_hdr); - - if (hdr->flags & GRE_CSUM) - offset += sizeof(((struct gre_full_hdr *)0)->csum) + - sizeof(((struct gre_full_hdr *)0)->reserved1); - - if (hdr->flags & GRE_KEY) { - const __be32 *keyid; - __be32 _keyid; - - keyid = __skb_header_pointer(skb, nhoff + offset, sizeof(_keyid), - data, hlen, &_keyid); - if (!keyid) - goto out_bad; - - if (dissector_uses_key(flow_dissector, - FLOW_DISSECTOR_KEY_GRE_KEYID)) { - key_keyid = skb_flow_dissector_target(flow_dissector, - FLOW_DISSECTOR_KEY_GRE_KEYID, - target_container); - if (gre_ver == 0) - key_keyid->keyid = *keyid; - else - key_keyid->keyid = *keyid & GRE_PPTP_KEY_MASK; - } - offset += sizeof(((struct gre_full_hdr *)0)->key); + case FLOW_DISSECT_RET_OUT_PROTO_AGAIN: + goto proto_again; } - - if (hdr->flags & GRE_SEQ) - offset += sizeof(((struct pptp_gre_header *)0)->seq); - - if (gre_ver == 0) { - if (proto == htons(ETH_P_TEB)) { - const struct ethhdr *eth; - struct ethhdr _eth; - - eth = __skb_header_pointer(skb, nhoff + offset, - sizeof(_eth), - data, hlen, &_eth); - if (!eth) - goto out_bad; - proto = eth->h_proto; - offset += sizeof(*eth); - - /* Cap headers that we access via pointers at the - * end of the Ethernet header as our maximum alignment - * at that point is only 2 bytes. - */ - if (NET_IP_ALIGN) - hlen = (nhoff + offset); - } - } else { /* version 1, must be PPTP */ - u8 _ppp_hdr[PPP_HDRLEN]; - u8 *ppp_hdr; - - if (hdr->flags & GRE_ACK) - offset += sizeof(((struct pptp_gre_header *)0)->ack); - - ppp_hdr = __skb_header_pointer(skb, nhoff + offset, - sizeof(_ppp_hdr), - data, hlen, _ppp_hdr); - if (!ppp_hdr) - goto out_bad; - - switch (PPP_PROTOCOL(ppp_hdr)) { - case PPP_IP: - proto = htons(ETH_P_IP); - break; - case PPP_IPV6: - proto = htons(ETH_P_IPV6); - break; - default: - /* Could probably catch some more like MPLS */ - break; - } - - offset += PPP_HDRLEN; - } - - nhoff += offset; - key_control->flags |= FLOW_DIS_ENCAPSULATION; - if (flags & FLOW_DISSECTOR_F_STOP_AT_ENCAP) - goto out_good; - - goto again; - } case NEXTHDR_HOP: case NEXTHDR_ROUTING: case NEXTHDR_DEST: { diff --git a/net/core/lwtunnel.c b/net/core/lwtunnel.c index 6df9f8fabf0c..b5888190223c 100644 --- a/net/core/lwtunnel.c +++ b/net/core/lwtunnel.c @@ -162,7 +162,6 @@ int lwtunnel_valid_encap_type_attr(struct nlattr *attr, int remaining) struct rtnexthop *rtnh = (struct rtnexthop *)attr; struct nlattr *nla_entype; struct nlattr *attrs; - struct nlattr *nla; u16 encap_type; int attrlen; @@ -170,7 +169,6 @@ int lwtunnel_valid_encap_type_attr(struct nlattr *attr, int remaining) attrlen = rtnh_attrlen(rtnh); if (attrlen > 0) { attrs = rtnh_attrs(rtnh); - nla = nla_find(attrs, attrlen, RTA_ENCAP); nla_entype = nla_find(attrs, attrlen, RTA_ENCAP_TYPE); if (nla_entype) { diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c index 3945821e9c1f..65ea0ff4017c 100644 --- a/net/core/net-sysfs.c +++ b/net/core/net-sysfs.c @@ -953,7 +953,7 @@ net_rx_queue_update_kobjects(struct net_device *dev, int old_num, int new_num) while (--i >= new_num) { struct kobject *kobj = &dev->_rx[i].kobj; - if (!list_empty(&dev_net(dev)->exit_list)) + if (!atomic_read(&dev_net(dev)->count)) kobj->uevent_suppress = 1; if (dev->sysfs_rx_queue_group) sysfs_remove_group(kobj, dev->sysfs_rx_queue_group); @@ -1371,7 +1371,7 @@ netdev_queue_update_kobjects(struct net_device *dev, int old_num, int new_num) while (--i >= new_num) { struct netdev_queue *queue = dev->_tx + i; - if (!list_empty(&dev_net(dev)->exit_list)) + if (!atomic_read(&dev_net(dev)->count)) queue->kobj.uevent_suppress = 1; #ifdef CONFIG_BQL sysfs_remove_group(&queue->kobj, &dql_group); @@ -1558,7 +1558,7 @@ void netdev_unregister_kobject(struct net_device *ndev) { struct device *dev = &(ndev->dev); - if (!list_empty(&dev_net(ndev)->exit_list)) + if (!atomic_read(&dev_net(ndev)->count)) dev_set_uevent_suppress(dev, 1); kobject_get(&dev->kobj); diff --git a/net/core/secure_seq.c b/net/core/secure_seq.c index 758f140b6bed..fb87e78a2cc7 100644 --- a/net/core/secure_seq.c +++ b/net/core/secure_seq.c @@ -45,8 +45,8 @@ static u32 seq_scale(u32 seq) #endif #if IS_ENABLED(CONFIG_IPV6) -u32 secure_tcpv6_sequence_number(const __be32 *saddr, const __be32 *daddr, - __be16 sport, __be16 dport, u32 *tsoff) +u32 secure_tcpv6_seq_and_tsoff(const __be32 *saddr, const __be32 *daddr, + __be16 sport, __be16 dport, u32 *tsoff) { const struct { struct in6_addr saddr; @@ -66,7 +66,7 @@ u32 secure_tcpv6_sequence_number(const __be32 *saddr, const __be32 *daddr, *tsoff = sysctl_tcp_timestamps == 1 ? (hash >> 32) : 0; return seq_scale(hash); } -EXPORT_SYMBOL(secure_tcpv6_sequence_number); +EXPORT_SYMBOL(secure_tcpv6_seq_and_tsoff); u32 secure_ipv6_port_ephemeral(const __be32 *saddr, const __be32 *daddr, __be16 dport) @@ -89,14 +89,13 @@ EXPORT_SYMBOL(secure_ipv6_port_ephemeral); #ifdef CONFIG_INET -/* secure_tcp_sequence_number(a, b, 0, d) == secure_ipv4_port_ephemeral(a, b, d), +/* secure_tcp_seq_and_tsoff(a, b, 0, d) == secure_ipv4_port_ephemeral(a, b, d), * but fortunately, `sport' cannot be 0 in any circumstances. If this changes, * it would be easy enough to have the former function use siphash_4u32, passing * the arguments as separate u32. */ - -u32 secure_tcp_sequence_number(__be32 saddr, __be32 daddr, - __be16 sport, __be16 dport, u32 *tsoff) +u32 secure_tcp_seq_and_tsoff(__be32 saddr, __be32 daddr, + __be16 sport, __be16 dport, u32 *tsoff) { u64 hash; net_secret_init(); diff --git a/net/core/skbuff.c b/net/core/skbuff.c index f3557958e9bf..cd4ba8c6b609 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -3828,13 +3828,14 @@ void skb_complete_tx_timestamp(struct sk_buff *skb, if (!skb_may_tx_timestamp(sk, false)) return; - /* take a reference to prevent skb_orphan() from freeing the socket */ - sock_hold(sk); - - *skb_hwtstamps(skb) = *hwtstamps; - __skb_complete_tx_timestamp(skb, sk, SCM_TSTAMP_SND); - - sock_put(sk); + /* Take a reference to prevent skb_orphan() from freeing the socket, + * but only if the socket refcount is not zero. + */ + if (likely(atomic_inc_not_zero(&sk->sk_refcnt))) { + *skb_hwtstamps(skb) = *hwtstamps; + __skb_complete_tx_timestamp(skb, sk, SCM_TSTAMP_SND); + sock_put(sk); + } } EXPORT_SYMBOL_GPL(skb_complete_tx_timestamp); @@ -3893,7 +3894,7 @@ void skb_complete_wifi_ack(struct sk_buff *skb, bool acked) { struct sock *sk = skb->sk; struct sock_exterr_skb *serr; - int err; + int err = 1; skb->wifi_acked_valid = 1; skb->wifi_acked = acked; @@ -3903,14 +3904,15 @@ void skb_complete_wifi_ack(struct sk_buff *skb, bool acked) serr->ee.ee_errno = ENOMSG; serr->ee.ee_origin = SO_EE_ORIGIN_TXSTATUS; - /* take a reference to prevent skb_orphan() from freeing the socket */ - sock_hold(sk); - - err = sock_queue_err_skb(sk, skb); + /* Take a reference to prevent skb_orphan() from freeing the socket, + * but only if the socket refcount is not zero. + */ + if (likely(atomic_inc_not_zero(&sk->sk_refcnt))) { + err = sock_queue_err_skb(sk, skb); + sock_put(sk); + } if (err) kfree_skb(skb); - - sock_put(sk); } EXPORT_SYMBOL_GPL(skb_complete_wifi_ack); diff --git a/net/core/sock.c b/net/core/sock.c index f6fd79f33097..a83731c36761 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -197,73 +197,117 @@ EXPORT_SYMBOL(sk_net_capable); /* * Each address family might have different locking rules, so we have - * one slock key per address family: + * one slock key per address family and separate keys for internal and + * userspace sockets. */ static struct lock_class_key af_family_keys[AF_MAX]; +static struct lock_class_key af_family_kern_keys[AF_MAX]; static struct lock_class_key af_family_slock_keys[AF_MAX]; +static struct lock_class_key af_family_kern_slock_keys[AF_MAX]; /* * Make lock validator output more readable. (we pre-construct these * strings build-time, so that runtime initialization of socket * locks is fast): */ + +#define _sock_locks(x) \ + x "AF_UNSPEC", x "AF_UNIX" , x "AF_INET" , \ + x "AF_AX25" , x "AF_IPX" , x "AF_APPLETALK", \ + x "AF_NETROM", x "AF_BRIDGE" , x "AF_ATMPVC" , \ + x "AF_X25" , x "AF_INET6" , x "AF_ROSE" , \ + x "AF_DECnet", x "AF_NETBEUI" , x "AF_SECURITY" , \ + x "AF_KEY" , x "AF_NETLINK" , x "AF_PACKET" , \ + x "AF_ASH" , x "AF_ECONET" , x "AF_ATMSVC" , \ + x "AF_RDS" , x "AF_SNA" , x "AF_IRDA" , \ + x "AF_PPPOX" , x "AF_WANPIPE" , x "AF_LLC" , \ + x "27" , x "28" , x "AF_CAN" , \ + x "AF_TIPC" , x "AF_BLUETOOTH", x "IUCV" , \ + x "AF_RXRPC" , x "AF_ISDN" , x "AF_PHONET" , \ + x "AF_IEEE802154", x "AF_CAIF" , x "AF_ALG" , \ + x "AF_NFC" , x "AF_VSOCK" , x "AF_KCM" , \ + x "AF_QIPCRTR", x "AF_SMC" , x "AF_MAX" + static const char *const af_family_key_strings[AF_MAX+1] = { - "sk_lock-AF_UNSPEC", "sk_lock-AF_UNIX" , "sk_lock-AF_INET" , - "sk_lock-AF_AX25" , "sk_lock-AF_IPX" , "sk_lock-AF_APPLETALK", - "sk_lock-AF_NETROM", "sk_lock-AF_BRIDGE" , "sk_lock-AF_ATMPVC" , - "sk_lock-AF_X25" , "sk_lock-AF_INET6" , "sk_lock-AF_ROSE" , - "sk_lock-AF_DECnet", "sk_lock-AF_NETBEUI" , "sk_lock-AF_SECURITY" , - "sk_lock-AF_KEY" , "sk_lock-AF_NETLINK" , "sk_lock-AF_PACKET" , - "sk_lock-AF_ASH" , "sk_lock-AF_ECONET" , "sk_lock-AF_ATMSVC" , - "sk_lock-AF_RDS" , "sk_lock-AF_SNA" , "sk_lock-AF_IRDA" , - "sk_lock-AF_PPPOX" , "sk_lock-AF_WANPIPE" , "sk_lock-AF_LLC" , - "sk_lock-27" , "sk_lock-28" , "sk_lock-AF_CAN" , - "sk_lock-AF_TIPC" , "sk_lock-AF_BLUETOOTH", "sk_lock-IUCV" , - "sk_lock-AF_RXRPC" , "sk_lock-AF_ISDN" , "sk_lock-AF_PHONET" , - "sk_lock-AF_IEEE802154", "sk_lock-AF_CAIF" , "sk_lock-AF_ALG" , - "sk_lock-AF_NFC" , "sk_lock-AF_VSOCK" , "sk_lock-AF_KCM" , - "sk_lock-AF_QIPCRTR", "sk_lock-AF_SMC" , "sk_lock-AF_MAX" + _sock_locks("sk_lock-") }; static const char *const af_family_slock_key_strings[AF_MAX+1] = { - "slock-AF_UNSPEC", "slock-AF_UNIX" , "slock-AF_INET" , - "slock-AF_AX25" , "slock-AF_IPX" , "slock-AF_APPLETALK", - "slock-AF_NETROM", "slock-AF_BRIDGE" , "slock-AF_ATMPVC" , - "slock-AF_X25" , "slock-AF_INET6" , "slock-AF_ROSE" , - "slock-AF_DECnet", "slock-AF_NETBEUI" , "slock-AF_SECURITY" , - "slock-AF_KEY" , "slock-AF_NETLINK" , "slock-AF_PACKET" , - "slock-AF_ASH" , "slock-AF_ECONET" , "slock-AF_ATMSVC" , - "slock-AF_RDS" , "slock-AF_SNA" , "slock-AF_IRDA" , - "slock-AF_PPPOX" , "slock-AF_WANPIPE" , "slock-AF_LLC" , - "slock-27" , "slock-28" , "slock-AF_CAN" , - "slock-AF_TIPC" , "slock-AF_BLUETOOTH", "slock-AF_IUCV" , - "slock-AF_RXRPC" , "slock-AF_ISDN" , "slock-AF_PHONET" , - "slock-AF_IEEE802154", "slock-AF_CAIF" , "slock-AF_ALG" , - "slock-AF_NFC" , "slock-AF_VSOCK" ,"slock-AF_KCM" , - "slock-AF_QIPCRTR", "slock-AF_SMC" , "slock-AF_MAX" + _sock_locks("slock-") }; static const char *const af_family_clock_key_strings[AF_MAX+1] = { - "clock-AF_UNSPEC", "clock-AF_UNIX" , "clock-AF_INET" , - "clock-AF_AX25" , "clock-AF_IPX" , "clock-AF_APPLETALK", - "clock-AF_NETROM", "clock-AF_BRIDGE" , "clock-AF_ATMPVC" , - "clock-AF_X25" , "clock-AF_INET6" , "clock-AF_ROSE" , - "clock-AF_DECnet", "clock-AF_NETBEUI" , "clock-AF_SECURITY" , - "clock-AF_KEY" , "clock-AF_NETLINK" , "clock-AF_PACKET" , - "clock-AF_ASH" , "clock-AF_ECONET" , "clock-AF_ATMSVC" , - "clock-AF_RDS" , "clock-AF_SNA" , "clock-AF_IRDA" , - "clock-AF_PPPOX" , "clock-AF_WANPIPE" , "clock-AF_LLC" , - "clock-27" , "clock-28" , "clock-AF_CAN" , - "clock-AF_TIPC" , "clock-AF_BLUETOOTH", "clock-AF_IUCV" , - "clock-AF_RXRPC" , "clock-AF_ISDN" , "clock-AF_PHONET" , - "clock-AF_IEEE802154", "clock-AF_CAIF" , "clock-AF_ALG" , - "clock-AF_NFC" , "clock-AF_VSOCK" , "clock-AF_KCM" , - "clock-AF_QIPCRTR", "clock-AF_SMC" , "clock-AF_MAX" + _sock_locks("clock-") +}; + +static const char *const af_family_kern_key_strings[AF_MAX+1] = { + _sock_locks("k-sk_lock-") +}; +static const char *const af_family_kern_slock_key_strings[AF_MAX+1] = { + _sock_locks("k-slock-") +}; +static const char *const af_family_kern_clock_key_strings[AF_MAX+1] = { + _sock_locks("k-clock-") +}; +static const char *const af_family_rlock_key_strings[AF_MAX+1] = { + "rlock-AF_UNSPEC", "rlock-AF_UNIX" , "rlock-AF_INET" , + "rlock-AF_AX25" , "rlock-AF_IPX" , "rlock-AF_APPLETALK", + "rlock-AF_NETROM", "rlock-AF_BRIDGE" , "rlock-AF_ATMPVC" , + "rlock-AF_X25" , "rlock-AF_INET6" , "rlock-AF_ROSE" , + "rlock-AF_DECnet", "rlock-AF_NETBEUI" , "rlock-AF_SECURITY" , + "rlock-AF_KEY" , "rlock-AF_NETLINK" , "rlock-AF_PACKET" , + "rlock-AF_ASH" , "rlock-AF_ECONET" , "rlock-AF_ATMSVC" , + "rlock-AF_RDS" , "rlock-AF_SNA" , "rlock-AF_IRDA" , + "rlock-AF_PPPOX" , "rlock-AF_WANPIPE" , "rlock-AF_LLC" , + "rlock-27" , "rlock-28" , "rlock-AF_CAN" , + "rlock-AF_TIPC" , "rlock-AF_BLUETOOTH", "rlock-AF_IUCV" , + "rlock-AF_RXRPC" , "rlock-AF_ISDN" , "rlock-AF_PHONET" , + "rlock-AF_IEEE802154", "rlock-AF_CAIF" , "rlock-AF_ALG" , + "rlock-AF_NFC" , "rlock-AF_VSOCK" , "rlock-AF_KCM" , + "rlock-AF_QIPCRTR", "rlock-AF_SMC" , "rlock-AF_MAX" +}; +static const char *const af_family_wlock_key_strings[AF_MAX+1] = { + "wlock-AF_UNSPEC", "wlock-AF_UNIX" , "wlock-AF_INET" , + "wlock-AF_AX25" , "wlock-AF_IPX" , "wlock-AF_APPLETALK", + "wlock-AF_NETROM", "wlock-AF_BRIDGE" , "wlock-AF_ATMPVC" , + "wlock-AF_X25" , "wlock-AF_INET6" , "wlock-AF_ROSE" , + "wlock-AF_DECnet", "wlock-AF_NETBEUI" , "wlock-AF_SECURITY" , + "wlock-AF_KEY" , "wlock-AF_NETLINK" , "wlock-AF_PACKET" , + "wlock-AF_ASH" , "wlock-AF_ECONET" , "wlock-AF_ATMSVC" , + "wlock-AF_RDS" , "wlock-AF_SNA" , "wlock-AF_IRDA" , + "wlock-AF_PPPOX" , "wlock-AF_WANPIPE" , "wlock-AF_LLC" , + "wlock-27" , "wlock-28" , "wlock-AF_CAN" , + "wlock-AF_TIPC" , "wlock-AF_BLUETOOTH", "wlock-AF_IUCV" , + "wlock-AF_RXRPC" , "wlock-AF_ISDN" , "wlock-AF_PHONET" , + "wlock-AF_IEEE802154", "wlock-AF_CAIF" , "wlock-AF_ALG" , + "wlock-AF_NFC" , "wlock-AF_VSOCK" , "wlock-AF_KCM" , + "wlock-AF_QIPCRTR", "wlock-AF_SMC" , "wlock-AF_MAX" +}; +static const char *const af_family_elock_key_strings[AF_MAX+1] = { + "elock-AF_UNSPEC", "elock-AF_UNIX" , "elock-AF_INET" , + "elock-AF_AX25" , "elock-AF_IPX" , "elock-AF_APPLETALK", + "elock-AF_NETROM", "elock-AF_BRIDGE" , "elock-AF_ATMPVC" , + "elock-AF_X25" , "elock-AF_INET6" , "elock-AF_ROSE" , + "elock-AF_DECnet", "elock-AF_NETBEUI" , "elock-AF_SECURITY" , + "elock-AF_KEY" , "elock-AF_NETLINK" , "elock-AF_PACKET" , + "elock-AF_ASH" , "elock-AF_ECONET" , "elock-AF_ATMSVC" , + "elock-AF_RDS" , "elock-AF_SNA" , "elock-AF_IRDA" , + "elock-AF_PPPOX" , "elock-AF_WANPIPE" , "elock-AF_LLC" , + "elock-27" , "elock-28" , "elock-AF_CAN" , + "elock-AF_TIPC" , "elock-AF_BLUETOOTH", "elock-AF_IUCV" , + "elock-AF_RXRPC" , "elock-AF_ISDN" , "elock-AF_PHONET" , + "elock-AF_IEEE802154", "elock-AF_CAIF" , "elock-AF_ALG" , + "elock-AF_NFC" , "elock-AF_VSOCK" , "elock-AF_KCM" , + "elock-AF_QIPCRTR", "elock-AF_SMC" , "elock-AF_MAX" }; /* - * sk_callback_lock locking rules are per-address-family, + * sk_callback_lock and sk queues locking rules are per-address-family, * so split the lock classes by using a per-AF key: */ static struct lock_class_key af_callback_keys[AF_MAX]; +static struct lock_class_key af_rlock_keys[AF_MAX]; +static struct lock_class_key af_wlock_keys[AF_MAX]; +static struct lock_class_key af_elock_keys[AF_MAX]; +static struct lock_class_key af_kern_callback_keys[AF_MAX]; /* Take into consideration the size of the struct sk_buff overhead in the * determination of these values, since that is non-constant across @@ -1293,7 +1337,16 @@ lenout: */ static inline void sock_lock_init(struct sock *sk) { - sock_lock_init_class_and_name(sk, + if (sk->sk_kern_sock) + sock_lock_init_class_and_name( + sk, + af_family_kern_slock_key_strings[sk->sk_family], + af_family_kern_slock_keys + sk->sk_family, + af_family_kern_key_strings[sk->sk_family], + af_family_kern_keys + sk->sk_family); + else + sock_lock_init_class_and_name( + sk, af_family_slock_key_strings[sk->sk_family], af_family_slock_keys + sk->sk_family, af_family_key_strings[sk->sk_family], @@ -1399,6 +1452,7 @@ struct sock *sk_alloc(struct net *net, int family, gfp_t priority, * why we need sk_prot_creator -acme */ sk->sk_prot = sk->sk_prot_creator = prot; + sk->sk_kern_sock = kern; sock_lock_init(sk); sk->sk_net_refcnt = kern ? 0 : 1; if (likely(sk->sk_net_refcnt)) @@ -1478,6 +1532,27 @@ void sk_free(struct sock *sk) } EXPORT_SYMBOL(sk_free); +static void sk_init_common(struct sock *sk) +{ + skb_queue_head_init(&sk->sk_receive_queue); + skb_queue_head_init(&sk->sk_write_queue); + skb_queue_head_init(&sk->sk_error_queue); + + rwlock_init(&sk->sk_callback_lock); + lockdep_set_class_and_name(&sk->sk_receive_queue.lock, + af_rlock_keys + sk->sk_family, + af_family_rlock_key_strings[sk->sk_family]); + lockdep_set_class_and_name(&sk->sk_write_queue.lock, + af_wlock_keys + sk->sk_family, + af_family_wlock_key_strings[sk->sk_family]); + lockdep_set_class_and_name(&sk->sk_error_queue.lock, + af_elock_keys + sk->sk_family, + af_family_elock_key_strings[sk->sk_family]); + lockdep_set_class_and_name(&sk->sk_callback_lock, + af_callback_keys + sk->sk_family, + af_family_clock_key_strings[sk->sk_family]); +} + /** * sk_clone_lock - clone a socket, and lock its clone * @sk: the socket to clone @@ -1511,13 +1586,7 @@ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority) */ atomic_set(&newsk->sk_wmem_alloc, 1); atomic_set(&newsk->sk_omem_alloc, 0); - skb_queue_head_init(&newsk->sk_receive_queue); - skb_queue_head_init(&newsk->sk_write_queue); - - rwlock_init(&newsk->sk_callback_lock); - lockdep_set_class_and_name(&newsk->sk_callback_lock, - af_callback_keys + newsk->sk_family, - af_family_clock_key_strings[newsk->sk_family]); + sk_init_common(newsk); newsk->sk_dst_cache = NULL; newsk->sk_dst_pending_confirm = 0; @@ -1528,7 +1597,6 @@ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority) newsk->sk_userlocks = sk->sk_userlocks & ~SOCK_BINDPORT_LOCK; sock_reset_flag(newsk, SOCK_DONE); - skb_queue_head_init(&newsk->sk_error_queue); filter = rcu_dereference_protected(newsk->sk_filter, 1); if (filter != NULL) @@ -2277,7 +2345,8 @@ int sock_no_socketpair(struct socket *sock1, struct socket *sock2) } EXPORT_SYMBOL(sock_no_socketpair); -int sock_no_accept(struct socket *sock, struct socket *newsock, int flags) +int sock_no_accept(struct socket *sock, struct socket *newsock, int flags, + bool kern) { return -EOPNOTSUPP; } @@ -2454,10 +2523,7 @@ EXPORT_SYMBOL(sk_stop_timer); void sock_init_data(struct socket *sock, struct sock *sk) { - skb_queue_head_init(&sk->sk_receive_queue); - skb_queue_head_init(&sk->sk_write_queue); - skb_queue_head_init(&sk->sk_error_queue); - + sk_init_common(sk); sk->sk_send_head = NULL; init_timer(&sk->sk_timer); @@ -2481,7 +2547,14 @@ void sock_init_data(struct socket *sock, struct sock *sk) } rwlock_init(&sk->sk_callback_lock); - lockdep_set_class_and_name(&sk->sk_callback_lock, + if (sk->sk_kern_sock) + lockdep_set_class_and_name( + &sk->sk_callback_lock, + af_kern_callback_keys + sk->sk_family, + af_family_kern_clock_key_strings[sk->sk_family]); + else + lockdep_set_class_and_name( + &sk->sk_callback_lock, af_callback_keys + sk->sk_family, af_family_clock_key_strings[sk->sk_family]); diff --git a/net/dccp/ccids/ccid2.c b/net/dccp/ccids/ccid2.c index f053198e730c..5e3a7302f774 100644 --- a/net/dccp/ccids/ccid2.c +++ b/net/dccp/ccids/ccid2.c @@ -749,6 +749,7 @@ static void ccid2_hc_tx_exit(struct sock *sk) for (i = 0; i < hc->tx_seqbufc; i++) kfree(hc->tx_seqbuf[i]); hc->tx_seqbufc = 0; + dccp_ackvec_parsed_cleanup(&hc->tx_av_chunks); } static void ccid2_hc_rx_packet_recv(struct sock *sk, struct sk_buff *skb) diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c index 409d0cfd3447..b99168b0fabf 100644 --- a/net/dccp/ipv4.c +++ b/net/dccp/ipv4.c @@ -289,7 +289,8 @@ static void dccp_v4_err(struct sk_buff *skb, u32 info) switch (type) { case ICMP_REDIRECT: - dccp_do_redirect(skb, sk); + if (!sock_owned_by_user(sk)) + dccp_do_redirect(skb, sk); goto out; case ICMP_SOURCE_QUENCH: /* Just silently ignore these. */ diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c index 233b57367758..d9b6a4e403e7 100644 --- a/net/dccp/ipv6.c +++ b/net/dccp/ipv6.c @@ -122,10 +122,12 @@ static void dccp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, np = inet6_sk(sk); if (type == NDISC_REDIRECT) { - struct dst_entry *dst = __sk_dst_check(sk, np->dst_cookie); + if (!sock_owned_by_user(sk)) { + struct dst_entry *dst = __sk_dst_check(sk, np->dst_cookie); - if (dst) - dst->ops->redirect(dst, sk, skb); + if (dst) + dst->ops->redirect(dst, sk, skb); + } goto out; } diff --git a/net/dccp/minisocks.c b/net/dccp/minisocks.c index e267e6f4c9a5..abd07a443219 100644 --- a/net/dccp/minisocks.c +++ b/net/dccp/minisocks.c @@ -142,6 +142,13 @@ struct sock *dccp_check_req(struct sock *sk, struct sk_buff *skb, struct dccp_request_sock *dreq = dccp_rsk(req); bool own_req; + /* TCP/DCCP listeners became lockless. + * DCCP stores complex state in its request_sock, so we need + * a protection for them, now this code runs without being protected + * by the parent (listener) lock. + */ + spin_lock_bh(&dreq->dreq_lock); + /* Check for retransmitted REQUEST */ if (dccp_hdr(skb)->dccph_type == DCCP_PKT_REQUEST) { @@ -156,7 +163,7 @@ struct sock *dccp_check_req(struct sock *sk, struct sk_buff *skb, inet_rtx_syn_ack(sk, req); } /* Network Duplicate, discard packet */ - return NULL; + goto out; } DCCP_SKB_CB(skb)->dccpd_reset_code = DCCP_RESET_CODE_PACKET_ERROR; @@ -182,20 +189,20 @@ struct sock *dccp_check_req(struct sock *sk, struct sk_buff *skb, child = inet_csk(sk)->icsk_af_ops->syn_recv_sock(sk, skb, req, NULL, req, &own_req); - if (!child) - goto listen_overflow; - - return inet_csk_complete_hashdance(sk, child, req, own_req); + if (child) { + child = inet_csk_complete_hashdance(sk, child, req, own_req); + goto out; + } -listen_overflow: - dccp_pr_debug("listen_overflow!\n"); DCCP_SKB_CB(skb)->dccpd_reset_code = DCCP_RESET_CODE_TOO_BUSY; drop: if (dccp_hdr(skb)->dccph_type != DCCP_PKT_RESET) req->rsk_ops->send_reset(sk, skb); inet_csk_reqsk_queue_drop(sk, req); - return NULL; +out: + spin_unlock_bh(&dreq->dreq_lock); + return child; } EXPORT_SYMBOL_GPL(dccp_check_req); @@ -246,6 +253,7 @@ int dccp_reqsk_init(struct request_sock *req, { struct dccp_request_sock *dreq = dccp_rsk(req); + spin_lock_init(&dreq->dreq_lock); inet_rsk(req)->ir_rmt_port = dccp_hdr(skb)->dccph_sport; inet_rsk(req)->ir_num = ntohs(dccp_hdr(skb)->dccph_dport); inet_rsk(req)->acked = 0; diff --git a/net/decnet/af_decnet.c b/net/decnet/af_decnet.c index e6e79eda9763..9afa2a5030b2 100644 --- a/net/decnet/af_decnet.c +++ b/net/decnet/af_decnet.c @@ -132,6 +132,7 @@ Version 0.0.6 2.1.110 07-aug-98 Eduardo Marcelo Serrat #include <net/neighbour.h> #include <net/dst.h> #include <net/fib_rules.h> +#include <net/tcp.h> #include <net/dn.h> #include <net/dn_nsp.h> #include <net/dn_dev.h> @@ -1070,7 +1071,8 @@ static struct sk_buff *dn_wait_for_connect(struct sock *sk, long *timeo) return skb == NULL ? ERR_PTR(err) : skb; } -static int dn_accept(struct socket *sock, struct socket *newsock, int flags) +static int dn_accept(struct socket *sock, struct socket *newsock, int flags, + bool kern) { struct sock *sk = sock->sk, *newsk; struct sk_buff *skb = NULL; @@ -1099,7 +1101,7 @@ static int dn_accept(struct socket *sock, struct socket *newsock, int flags) cb = DN_SKB_CB(skb); sk->sk_ack_backlog--; - newsk = dn_alloc_sock(sock_net(sk), newsock, sk->sk_allocation, 0); + newsk = dn_alloc_sock(sock_net(sk), newsock, sk->sk_allocation, kern); if (newsk == NULL) { release_sock(sk); kfree_skb(skb); @@ -1468,18 +1470,18 @@ static int __dn_setsockopt(struct socket *sock, int level,int optname, char __us case DSO_NODELAY: if (optlen != sizeof(int)) return -EINVAL; - if (scp->nonagle == 2) + if (scp->nonagle == TCP_NAGLE_CORK) return -EINVAL; - scp->nonagle = (u.val == 0) ? 0 : 1; + scp->nonagle = (u.val == 0) ? 0 : TCP_NAGLE_OFF; /* if (scp->nonagle == 1) { Push pending frames } */ break; case DSO_CORK: if (optlen != sizeof(int)) return -EINVAL; - if (scp->nonagle == 1) + if (scp->nonagle == TCP_NAGLE_OFF) return -EINVAL; - scp->nonagle = (u.val == 0) ? 0 : 2; + scp->nonagle = (u.val == 0) ? 0 : TCP_NAGLE_CORK; /* if (scp->nonagle == 0) { Push pending frames } */ break; @@ -1607,14 +1609,14 @@ static int __dn_getsockopt(struct socket *sock, int level,int optname, char __us case DSO_NODELAY: if (r_len > sizeof(int)) r_len = sizeof(int); - val = (scp->nonagle == 1); + val = (scp->nonagle == TCP_NAGLE_OFF); r_data = &val; break; case DSO_CORK: if (r_len > sizeof(int)) r_len = sizeof(int); - val = (scp->nonagle == 2); + val = (scp->nonagle == TCP_NAGLE_CORK); r_data = &val; break; diff --git a/net/dsa/slave.c b/net/dsa/slave.c index c34872e1febc..78128acfbf63 100644 --- a/net/dsa/slave.c +++ b/net/dsa/slave.c @@ -419,8 +419,8 @@ static int dsa_slave_vlan_filtering(struct net_device *dev, return 0; } -static int dsa_fastest_ageing_time(struct dsa_switch *ds, - unsigned int ageing_time) +static unsigned int dsa_fastest_ageing_time(struct dsa_switch *ds, + unsigned int ageing_time) { int i; @@ -443,9 +443,13 @@ static int dsa_slave_ageing_time(struct net_device *dev, unsigned long ageing_jiffies = clock_t_to_jiffies(attr->u.ageing_time); unsigned int ageing_time = jiffies_to_msecs(ageing_jiffies); - /* bridge skips -EOPNOTSUPP, so skip the prepare phase */ - if (switchdev_trans_ph_prepare(trans)) + if (switchdev_trans_ph_prepare(trans)) { + if (ds->ageing_time_min && ageing_time < ds->ageing_time_min) + return -ERANGE; + if (ds->ageing_time_max && ageing_time > ds->ageing_time_max) + return -ERANGE; return 0; + } /* Keep the fastest ageing time in case of multiple bridges */ p->dp->ageing_time = ageing_time; diff --git a/net/ipv4/Makefile b/net/ipv4/Makefile index c6d4238ff94a..f83de23a30e7 100644 --- a/net/ipv4/Makefile +++ b/net/ipv4/Makefile @@ -11,7 +11,7 @@ obj-y := route.o inetpeer.o protocol.o \ tcp_rate.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 \ + fib_frontend.o fib_semantics.o fib_trie.o fib_notifier.o \ inet_fragment.o ping.o ip_tunnel_core.o gre_offload.o obj-$(CONFIG_NET_IP_TUNNEL) += ip_tunnel.o diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 602d40f43687..6b1fc6e4278e 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -689,11 +689,12 @@ EXPORT_SYMBOL(inet_stream_connect); * Accept a pending connection. The TCP layer now gives BSD semantics. */ -int inet_accept(struct socket *sock, struct socket *newsock, int flags) +int inet_accept(struct socket *sock, struct socket *newsock, int flags, + bool kern) { struct sock *sk1 = sock->sk; int err = -EINVAL; - struct sock *sk2 = sk1->sk_prot->accept(sk1, flags, &err); + struct sock *sk2 = sk1->sk_prot->accept(sk1, flags, &err, kern); if (!sk2) goto do_err; @@ -1487,8 +1488,10 @@ int inet_gro_complete(struct sk_buff *skb, int nhoff) int proto = iph->protocol; int err = -ENOSYS; - if (skb->encapsulation) + if (skb->encapsulation) { + skb_set_inner_protocol(skb, cpu_to_be16(ETH_P_IP)); skb_set_inner_network_header(skb, nhoff); + } csum_replace2(&iph->check, iph->tot_len, newlen); iph->tot_len = newlen; diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index cebedd545e5e..927f1d4b8c80 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -1192,6 +1192,18 @@ out: return done; } +static __be32 in_dev_select_addr(const struct in_device *in_dev, + int scope) +{ + for_primary_ifa(in_dev) { + if (ifa->ifa_scope != RT_SCOPE_LINK && + ifa->ifa_scope <= scope) + return ifa->ifa_local; + } endfor_ifa(in_dev); + + return 0; +} + __be32 inet_select_addr(const struct net_device *dev, __be32 dst, int scope) { __be32 addr = 0; @@ -1228,13 +1240,9 @@ no_in_dev: if (master_idx && (dev = dev_get_by_index_rcu(net, master_idx)) && (in_dev = __in_dev_get_rcu(dev))) { - for_primary_ifa(in_dev) { - if (ifa->ifa_scope != RT_SCOPE_LINK && - ifa->ifa_scope <= scope) { - addr = ifa->ifa_local; - goto out_unlock; - } - } endfor_ifa(in_dev); + addr = in_dev_select_addr(in_dev, scope); + if (addr) + goto out_unlock; } /* Not loopback addresses on loopback should be preferred @@ -1249,13 +1257,9 @@ no_in_dev: if (!in_dev) continue; - for_primary_ifa(in_dev) { - if (ifa->ifa_scope != RT_SCOPE_LINK && - ifa->ifa_scope <= scope) { - addr = ifa->ifa_local; - goto out_unlock; - } - } endfor_ifa(in_dev); + addr = in_dev_select_addr(in_dev, scope); + if (addr) + goto out_unlock; } out_unlock: rcu_read_unlock(); diff --git a/net/ipv4/fib_notifier.c b/net/ipv4/fib_notifier.c new file mode 100644 index 000000000000..e0714d975947 --- /dev/null +++ b/net/ipv4/fib_notifier.c @@ -0,0 +1,86 @@ +#include <linux/rtnetlink.h> +#include <linux/notifier.h> +#include <linux/rcupdate.h> +#include <linux/kernel.h> +#include <net/net_namespace.h> +#include <net/netns/ipv4.h> +#include <net/ip_fib.h> + +static ATOMIC_NOTIFIER_HEAD(fib_chain); + +int call_fib_notifier(struct notifier_block *nb, struct net *net, + enum fib_event_type event_type, + struct fib_notifier_info *info) +{ + info->net = net; + return nb->notifier_call(nb, event_type, info); +} + +int call_fib_notifiers(struct net *net, enum fib_event_type event_type, + struct fib_notifier_info *info) +{ + net->ipv4.fib_seq++; + info->net = net; + return atomic_notifier_call_chain(&fib_chain, event_type, info); +} + +static unsigned int fib_seq_sum(void) +{ + unsigned int fib_seq = 0; + struct net *net; + + rtnl_lock(); + for_each_net(net) + fib_seq += net->ipv4.fib_seq; + rtnl_unlock(); + + return fib_seq; +} + +static bool fib_dump_is_consistent(struct notifier_block *nb, + void (*cb)(struct notifier_block *nb), + unsigned int fib_seq) +{ + atomic_notifier_chain_register(&fib_chain, nb); + if (fib_seq == fib_seq_sum()) + return true; + atomic_notifier_chain_unregister(&fib_chain, nb); + if (cb) + cb(nb); + return false; +} + +#define FIB_DUMP_MAX_RETRIES 5 +int register_fib_notifier(struct notifier_block *nb, + void (*cb)(struct notifier_block *nb)) +{ + int retries = 0; + + do { + unsigned int fib_seq = fib_seq_sum(); + struct net *net; + + /* Mutex semantics guarantee that every change done to + * FIB tries before we read the change sequence counter + * is now visible to us. + */ + rcu_read_lock(); + for_each_net_rcu(net) { + fib_rules_notify(net, nb); + fib_notify(net, nb); + } + rcu_read_unlock(); + + if (fib_dump_is_consistent(nb, cb, fib_seq)) + return 0; + } while (++retries < FIB_DUMP_MAX_RETRIES); + + return -EBUSY; +} +EXPORT_SYMBOL(register_fib_notifier); + +int unregister_fib_notifier(struct notifier_block *nb) +{ + return atomic_notifier_chain_unregister(&fib_chain, nb); +} +EXPORT_SYMBOL(unregister_fib_notifier); diff --git a/net/ipv4/fib_rules.c b/net/ipv4/fib_rules.c index 2e50062f642d..778ecf977eb2 100644 --- a/net/ipv4/fib_rules.c +++ b/net/ipv4/fib_rules.c @@ -47,6 +47,27 @@ struct fib4_rule { #endif }; +static bool fib4_rule_matchall(const struct fib_rule *rule) +{ + struct fib4_rule *r = container_of(rule, struct fib4_rule, common); + + if (r->dst_len || r->src_len || r->tos) + return false; + return fib_rule_matchall(rule); +} + +bool fib4_rule_default(const struct fib_rule *rule) +{ + if (!fib4_rule_matchall(rule) || rule->action != FR_ACT_TO_TBL || + rule->l3mdev) + return false; + if (rule->table != RT_TABLE_LOCAL && rule->table != RT_TABLE_MAIN && + rule->table != RT_TABLE_DEFAULT) + return false; + return true; +} +EXPORT_SYMBOL_GPL(fib4_rule_default); + int __fib_lookup(struct net *net, struct flowi4 *flp, struct fib_result *res, unsigned int flags) { @@ -164,12 +185,36 @@ static struct fib_table *fib_empty_table(struct net *net) return NULL; } +static int call_fib_rule_notifier(struct notifier_block *nb, struct net *net, + enum fib_event_type event_type, + struct fib_rule *rule) +{ + struct fib_rule_notifier_info info = { + .rule = rule, + }; + + return call_fib_notifier(nb, net, event_type, &info.info); +} + static int call_fib_rule_notifiers(struct net *net, - enum fib_event_type event_type) + enum fib_event_type event_type, + struct fib_rule *rule) +{ + struct fib_rule_notifier_info info = { + .rule = rule, + }; + + return call_fib_notifiers(net, event_type, &info.info); +} + +/* Called with rcu_read_lock() */ +void fib_rules_notify(struct net *net, struct notifier_block *nb) { - struct fib_notifier_info info; + struct fib_rules_ops *ops = net->ipv4.rules_ops; + struct fib_rule *rule; - return call_fib_notifiers(net, event_type, &info); + list_for_each_entry_rcu(rule, &ops->rules_list, list) + call_fib_rule_notifier(nb, net, FIB_EVENT_RULE_ADD, rule); } static const struct nla_policy fib4_rule_policy[FRA_MAX+1] = { @@ -228,7 +273,7 @@ static int fib4_rule_configure(struct fib_rule *rule, struct sk_buff *skb, rule4->tos = frh->tos; net->ipv4.fib_has_custom_rules = true; - call_fib_rule_notifiers(net, FIB_EVENT_RULE_ADD); + call_fib_rule_notifiers(net, FIB_EVENT_RULE_ADD, rule); err = 0; errout: @@ -250,7 +295,7 @@ static int fib4_rule_delete(struct fib_rule *rule) net->ipv4.fib_num_tclassid_users--; #endif net->ipv4.fib_has_custom_rules = true; - call_fib_rule_notifiers(net, FIB_EVENT_RULE_DEL); + call_fib_rule_notifiers(net, FIB_EVENT_RULE_DEL, rule); errout: return err; } diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index 2f0d8233950f..1201409ba1dc 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -84,43 +84,6 @@ #include <trace/events/fib.h> #include "fib_lookup.h" -static unsigned int fib_seq_sum(void) -{ - unsigned int fib_seq = 0; - struct net *net; - - rtnl_lock(); - for_each_net(net) - fib_seq += net->ipv4.fib_seq; - rtnl_unlock(); - - return fib_seq; -} - -static ATOMIC_NOTIFIER_HEAD(fib_chain); - -static int call_fib_notifier(struct notifier_block *nb, struct net *net, - enum fib_event_type event_type, - struct fib_notifier_info *info) -{ - info->net = net; - return nb->notifier_call(nb, event_type, info); -} - -static void fib_rules_notify(struct net *net, struct notifier_block *nb, - enum fib_event_type event_type) -{ -#ifdef CONFIG_IP_MULTIPLE_TABLES - struct fib_notifier_info info; - - if (net->ipv4.fib_has_custom_rules) - call_fib_notifier(nb, net, event_type, &info); -#endif -} - -static void fib_notify(struct net *net, struct notifier_block *nb, - enum fib_event_type event_type); - static int call_fib_entry_notifier(struct notifier_block *nb, struct net *net, enum fib_event_type event_type, u32 dst, int dst_len, struct fib_info *fi, @@ -137,62 +100,6 @@ static int call_fib_entry_notifier(struct notifier_block *nb, struct net *net, return call_fib_notifier(nb, net, event_type, &info.info); } -static bool fib_dump_is_consistent(struct notifier_block *nb, - void (*cb)(struct notifier_block *nb), - unsigned int fib_seq) -{ - atomic_notifier_chain_register(&fib_chain, nb); - if (fib_seq == fib_seq_sum()) - return true; - atomic_notifier_chain_unregister(&fib_chain, nb); - if (cb) - cb(nb); - return false; -} - -#define FIB_DUMP_MAX_RETRIES 5 -int register_fib_notifier(struct notifier_block *nb, - void (*cb)(struct notifier_block *nb)) -{ - int retries = 0; - - do { - unsigned int fib_seq = fib_seq_sum(); - struct net *net; - - /* Mutex semantics guarantee that every change done to - * FIB tries before we read the change sequence counter - * is now visible to us. - */ - rcu_read_lock(); - for_each_net_rcu(net) { - fib_rules_notify(net, nb, FIB_EVENT_RULE_ADD); - fib_notify(net, nb, FIB_EVENT_ENTRY_ADD); - } - rcu_read_unlock(); - - if (fib_dump_is_consistent(nb, cb, fib_seq)) - return 0; - } while (++retries < FIB_DUMP_MAX_RETRIES); - - return -EBUSY; -} -EXPORT_SYMBOL(register_fib_notifier); - -int unregister_fib_notifier(struct notifier_block *nb) -{ - return atomic_notifier_chain_unregister(&fib_chain, nb); -} -EXPORT_SYMBOL(unregister_fib_notifier); - -int call_fib_notifiers(struct net *net, enum fib_event_type event_type, - struct fib_notifier_info *info) -{ - net->ipv4.fib_seq++; - info->net = net; - return atomic_notifier_call_chain(&fib_chain, event_type, info); -} - static int call_fib_entry_notifiers(struct net *net, enum fib_event_type event_type, u32 dst, int dst_len, struct fib_info *fi, @@ -1995,8 +1902,7 @@ int fib_table_flush(struct net *net, struct fib_table *tb) } static void fib_leaf_notify(struct net *net, struct key_vector *l, - struct fib_table *tb, struct notifier_block *nb, - enum fib_event_type event_type) + struct fib_table *tb, struct notifier_block *nb) { struct fib_alias *fa; @@ -2012,22 +1918,21 @@ static void fib_leaf_notify(struct net *net, struct key_vector *l, if (tb->tb_id != fa->tb_id) continue; - call_fib_entry_notifier(nb, net, event_type, l->key, + call_fib_entry_notifier(nb, net, FIB_EVENT_ENTRY_ADD, l->key, KEYLENGTH - fa->fa_slen, fi, fa->fa_tos, fa->fa_type, fa->tb_id); } } static void fib_table_notify(struct net *net, struct fib_table *tb, - struct notifier_block *nb, - enum fib_event_type event_type) + struct notifier_block *nb) { struct trie *t = (struct trie *)tb->tb_data; struct key_vector *l, *tp = t->kv; t_key key = 0; while ((l = leaf_walk_rcu(&tp, key)) != NULL) { - fib_leaf_notify(net, l, tb, nb, event_type); + fib_leaf_notify(net, l, tb, nb); key = l->key + 1; /* stop in case of wrap around */ @@ -2036,8 +1941,7 @@ static void fib_table_notify(struct net *net, struct fib_table *tb, } } -static void fib_notify(struct net *net, struct notifier_block *nb, - enum fib_event_type event_type) +void fib_notify(struct net *net, struct notifier_block *nb) { unsigned int h; @@ -2046,7 +1950,7 @@ static void fib_notify(struct net *net, struct notifier_block *nb, struct fib_table *tb; hlist_for_each_entry_rcu(tb, head, tb_hlist) - fib_table_notify(net, tb, nb, event_type); + fib_table_notify(net, tb, nb); } } diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index b4d5980ade3b..5e313c1ac94f 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -424,7 +424,7 @@ static int inet_csk_wait_for_connect(struct sock *sk, long timeo) /* * This will accept the next outstanding connection. */ -struct sock *inet_csk_accept(struct sock *sk, int flags, int *err) +struct sock *inet_csk_accept(struct sock *sk, int flags, int *err, bool kern) { struct inet_connection_sock *icsk = inet_csk(sk); struct request_sock_queue *queue = &icsk->icsk_accept_queue; diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 737ce826d7ec..7a3fd25e8913 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -966,7 +966,7 @@ static int __ip_append_data(struct sock *sk, cork->length += length; if ((((length + fragheaderlen) > mtu) || (skb && skb_is_gso(skb))) && (sk->sk_protocol == IPPROTO_UDP) && - (rt->dst.dev->features & NETIF_F_UFO) && !rt->dst.header_len && + (rt->dst.dev->features & NETIF_F_UFO) && !dst_xfrm(&rt->dst) && (sk->sk_type == SOCK_DGRAM) && !sk->sk_no_check_tx) { err = ip_ufo_append_data(sk, queue, getfrag, from, length, hh_len, fragheaderlen, transhdrlen, diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c index 69cf49e8356d..4ccbf464d1ac 100644 --- a/net/ipv4/proc.c +++ b/net/ipv4/proc.c @@ -199,7 +199,6 @@ static const struct snmp_mib snmp4_net_list[] = { SNMP_MIB_ITEM("TW", LINUX_MIB_TIMEWAITED), SNMP_MIB_ITEM("TWRecycled", LINUX_MIB_TIMEWAITRECYCLED), SNMP_MIB_ITEM("TWKilled", LINUX_MIB_TIMEWAITKILLED), - SNMP_MIB_ITEM("PAWSPassive", LINUX_MIB_PAWSPASSIVEREJECTED), SNMP_MIB_ITEM("PAWSActive", LINUX_MIB_PAWSACTIVEREJECTED), SNMP_MIB_ITEM("PAWSEstab", LINUX_MIB_PAWSESTABREJECTED), SNMP_MIB_ITEM("DelayedACKs", LINUX_MIB_DELAYEDACKS), diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index d6880a6149ee..11aaef0939b2 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -981,13 +981,6 @@ static struct ctl_table ipv4_net_table[] = { .proc_handler = proc_dointvec }, { - .procname = "tcp_tw_recycle", - .data = &init_net.ipv4.tcp_death_row.sysctl_tw_recycle, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec - }, - { .procname = "tcp_max_syn_backlog", .data = &init_net.ipv4.sysctl_max_syn_backlog, .maxlen = sizeof(int), diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 39c393cc0fd3..bb09c7095988 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -6324,36 +6324,14 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops, goto drop_and_free; if (isn && tmp_opt.tstamp_ok) - af_ops->init_seq(skb, &tcp_rsk(req)->ts_off); + af_ops->init_seq_tsoff(skb, &tcp_rsk(req)->ts_off); if (!want_cookie && !isn) { - /* VJ's idea. We save last timestamp seen - * from the destination in peer table, when entering - * state TIME-WAIT, and check against it before - * accepting new connection request. - * - * If "isn" is not zero, this request hit alive - * timewait bucket, so that all the necessary checks - * are made in the function processing timewait state. - */ - if (net->ipv4.tcp_death_row.sysctl_tw_recycle) { - bool strict; - - dst = af_ops->route_req(sk, &fl, req, &strict); - - if (dst && strict && - !tcp_peer_is_proven(req, dst, true, - tmp_opt.saw_tstamp)) { - NET_INC_STATS(sock_net(sk), LINUX_MIB_PAWSPASSIVEREJECTED); - goto drop_and_release; - } - } /* Kill the following clause, if you dislike this way. */ - else if (!net->ipv4.sysctl_tcp_syncookies && - (net->ipv4.sysctl_max_syn_backlog - inet_csk_reqsk_queue_len(sk) < - (net->ipv4.sysctl_max_syn_backlog >> 2)) && - !tcp_peer_is_proven(req, dst, false, - tmp_opt.saw_tstamp)) { + if (!net->ipv4.sysctl_tcp_syncookies && + (net->ipv4.sysctl_max_syn_backlog - inet_csk_reqsk_queue_len(sk) < + (net->ipv4.sysctl_max_syn_backlog >> 2)) && + !tcp_peer_is_proven(req, dst)) { /* Without syncookies last quarter of * backlog is filled with destinations, * proven to be alive. @@ -6366,10 +6344,10 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops, goto drop_and_release; } - isn = af_ops->init_seq(skb, &tcp_rsk(req)->ts_off); + isn = af_ops->init_seq_tsoff(skb, &tcp_rsk(req)->ts_off); } if (!dst) { - dst = af_ops->route_req(sk, &fl, req, NULL); + dst = af_ops->route_req(sk, &fl, req); if (!dst) goto drop_and_free; } diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 9a89b8deafae..7482b5d11861 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -94,12 +94,12 @@ static int tcp_v4_md5_hash_hdr(char *md5_hash, const struct tcp_md5sig_key *key, struct inet_hashinfo tcp_hashinfo; EXPORT_SYMBOL(tcp_hashinfo); -static u32 tcp_v4_init_sequence(const struct sk_buff *skb, u32 *tsoff) +static u32 tcp_v4_init_seq_and_tsoff(const struct sk_buff *skb, u32 *tsoff) { - return secure_tcp_sequence_number(ip_hdr(skb)->daddr, - ip_hdr(skb)->saddr, - tcp_hdr(skb)->dest, - tcp_hdr(skb)->source, tsoff); + return secure_tcp_seq_and_tsoff(ip_hdr(skb)->daddr, + ip_hdr(skb)->saddr, + tcp_hdr(skb)->dest, + tcp_hdr(skb)->source, tsoff); } int tcp_twsk_unique(struct sock *sk, struct sock *sktw, void *twp) @@ -198,10 +198,6 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) tp->write_seq = 0; } - if (tcp_death_row->sysctl_tw_recycle && - !tp->rx_opt.ts_recent_stamp && fl4->daddr == daddr) - tcp_fetch_timewait_stamp(sk, &rt->dst); - inet->inet_dport = usin->sin_port; sk_daddr_set(sk, daddr); @@ -236,11 +232,11 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) rt = NULL; if (likely(!tp->repair)) { - seq = secure_tcp_sequence_number(inet->inet_saddr, - inet->inet_daddr, - inet->inet_sport, - usin->sin_port, - &tp->tsoffset); + seq = secure_tcp_seq_and_tsoff(inet->inet_saddr, + inet->inet_daddr, + inet->inet_sport, + usin->sin_port, + &tp->tsoffset); if (!tp->write_seq) tp->write_seq = seq; } @@ -279,10 +275,13 @@ EXPORT_SYMBOL(tcp_v4_connect); */ void tcp_v4_mtu_reduced(struct sock *sk) { - struct dst_entry *dst; struct inet_sock *inet = inet_sk(sk); - u32 mtu = tcp_sk(sk)->mtu_info; + struct dst_entry *dst; + u32 mtu; + if ((1 << sk->sk_state) & (TCPF_LISTEN | TCPF_CLOSE)) + return; + mtu = tcp_sk(sk)->mtu_info; dst = inet_csk_update_pmtu(sk, mtu); if (!dst) return; @@ -428,7 +427,8 @@ void tcp_v4_err(struct sk_buff *icmp_skb, u32 info) switch (type) { case ICMP_REDIRECT: - do_redirect(icmp_skb, sk); + if (!sock_owned_by_user(sk)) + do_redirect(icmp_skb, sk); goto out; case ICMP_SOURCE_QUENCH: /* Just silently ignore these. */ @@ -1213,19 +1213,9 @@ static void tcp_v4_init_req(struct request_sock *req, static struct dst_entry *tcp_v4_route_req(const struct sock *sk, struct flowi *fl, - const struct request_sock *req, - bool *strict) + const struct request_sock *req) { - struct dst_entry *dst = inet_csk_route_req(sk, &fl->u.ip4, req); - - if (strict) { - if (fl->u.ip4.daddr == inet_rsk(req)->ir_rmt_addr) - *strict = true; - else - *strict = false; - } - - return dst; + return inet_csk_route_req(sk, &fl->u.ip4, req); } struct request_sock_ops tcp_request_sock_ops __read_mostly = { @@ -1249,7 +1239,7 @@ static const struct tcp_request_sock_ops tcp_request_sock_ipv4_ops = { .cookie_init_seq = cookie_v4_init_sequence, #endif .route_req = tcp_v4_route_req, - .init_seq = tcp_v4_init_sequence, + .init_seq_tsoff = tcp_v4_init_seq_and_tsoff, .send_synack = tcp_v4_send_synack, }; @@ -2462,7 +2452,6 @@ static int __net_init tcp_sk_init(struct net *net) net->ipv4.sysctl_tcp_tw_reuse = 0; cnt = tcp_hashinfo.ehash_mask + 1; - net->ipv4.tcp_death_row.sysctl_tw_recycle = 0; net->ipv4.tcp_death_row.sysctl_max_tw_buckets = (cnt + 1) / 2; net->ipv4.tcp_death_row.hashinfo = &tcp_hashinfo; diff --git a/net/ipv4/tcp_metrics.c b/net/ipv4/tcp_metrics.c index 0f46e5fe31ad..9d0d4f39e42b 100644 --- a/net/ipv4/tcp_metrics.c +++ b/net/ipv4/tcp_metrics.c @@ -45,8 +45,6 @@ struct tcp_metrics_block { struct inetpeer_addr tcpm_saddr; struct inetpeer_addr tcpm_daddr; unsigned long tcpm_stamp; - u32 tcpm_ts; - u32 tcpm_ts_stamp; u32 tcpm_lock; u32 tcpm_vals[TCP_METRIC_MAX_KERNEL + 1]; struct tcp_fastopen_metrics tcpm_fastopen; @@ -123,8 +121,6 @@ static void tcpm_suck_dst(struct tcp_metrics_block *tm, tm->tcpm_vals[TCP_METRIC_SSTHRESH] = dst_metric_raw(dst, RTAX_SSTHRESH); tm->tcpm_vals[TCP_METRIC_CWND] = dst_metric_raw(dst, RTAX_CWND); tm->tcpm_vals[TCP_METRIC_REORDERING] = dst_metric_raw(dst, RTAX_REORDERING); - tm->tcpm_ts = 0; - tm->tcpm_ts_stamp = 0; if (fastopen_clear) { tm->tcpm_fastopen.mss = 0; tm->tcpm_fastopen.syn_loss = 0; @@ -273,48 +269,6 @@ static struct tcp_metrics_block *__tcp_get_metrics_req(struct request_sock *req, return tm; } -static struct tcp_metrics_block *__tcp_get_metrics_tw(struct inet_timewait_sock *tw) -{ - struct tcp_metrics_block *tm; - struct inetpeer_addr saddr, daddr; - unsigned int hash; - struct net *net; - - if (tw->tw_family == AF_INET) { - inetpeer_set_addr_v4(&saddr, tw->tw_rcv_saddr); - inetpeer_set_addr_v4(&daddr, tw->tw_daddr); - hash = ipv4_addr_hash(tw->tw_daddr); - } -#if IS_ENABLED(CONFIG_IPV6) - else if (tw->tw_family == AF_INET6) { - if (ipv6_addr_v4mapped(&tw->tw_v6_daddr)) { - inetpeer_set_addr_v4(&saddr, tw->tw_rcv_saddr); - inetpeer_set_addr_v4(&daddr, tw->tw_daddr); - hash = ipv4_addr_hash(tw->tw_daddr); - } else { - inetpeer_set_addr_v6(&saddr, &tw->tw_v6_rcv_saddr); - inetpeer_set_addr_v6(&daddr, &tw->tw_v6_daddr); - hash = ipv6_addr_hash(&tw->tw_v6_daddr); - } - } -#endif - else - return NULL; - - net = twsk_net(tw); - hash ^= net_hash_mix(net); - hash = hash_32(hash, tcp_metrics_hash_log); - - for (tm = rcu_dereference(tcp_metrics_hash[hash].chain); tm; - tm = rcu_dereference(tm->tcpm_next)) { - if (addr_same(&tm->tcpm_saddr, &saddr) && - addr_same(&tm->tcpm_daddr, &daddr) && - net_eq(tm_net(tm), net)) - break; - } - return tm; -} - static struct tcp_metrics_block *tcp_get_metrics(struct sock *sk, struct dst_entry *dst, bool create) @@ -573,8 +527,7 @@ reset: tp->snd_cwnd_stamp = tcp_time_stamp; } -bool tcp_peer_is_proven(struct request_sock *req, struct dst_entry *dst, - bool paws_check, bool timestamps) +bool tcp_peer_is_proven(struct request_sock *req, struct dst_entry *dst) { struct tcp_metrics_block *tm; bool ret; @@ -584,94 +537,10 @@ bool tcp_peer_is_proven(struct request_sock *req, struct dst_entry *dst, rcu_read_lock(); tm = __tcp_get_metrics_req(req, dst); - if (paws_check) { - if (tm && - (u32)get_seconds() - tm->tcpm_ts_stamp < TCP_PAWS_MSL && - ((s32)(tm->tcpm_ts - req->ts_recent) > TCP_PAWS_WINDOW || - !timestamps)) - ret = false; - else - ret = true; - } else { - if (tm && tcp_metric_get(tm, TCP_METRIC_RTT) && tm->tcpm_ts_stamp) - ret = true; - else - ret = false; - } - rcu_read_unlock(); - - return ret; -} - -void tcp_fetch_timewait_stamp(struct sock *sk, struct dst_entry *dst) -{ - struct tcp_metrics_block *tm; - - rcu_read_lock(); - tm = tcp_get_metrics(sk, dst, true); - if (tm) { - struct tcp_sock *tp = tcp_sk(sk); - - if ((u32)get_seconds() - tm->tcpm_ts_stamp <= TCP_PAWS_MSL) { - tp->rx_opt.ts_recent_stamp = tm->tcpm_ts_stamp; - tp->rx_opt.ts_recent = tm->tcpm_ts; - } - } - rcu_read_unlock(); -} -EXPORT_SYMBOL_GPL(tcp_fetch_timewait_stamp); - -/* VJ's idea. Save last timestamp seen from this destination and hold - * it at least for normal timewait interval to use for duplicate - * segment detection in subsequent connections, before they enter - * synchronized state. - */ -bool tcp_remember_stamp(struct sock *sk) -{ - struct dst_entry *dst = __sk_dst_get(sk); - bool ret = false; - - if (dst) { - struct tcp_metrics_block *tm; - - rcu_read_lock(); - tm = tcp_get_metrics(sk, dst, true); - if (tm) { - struct tcp_sock *tp = tcp_sk(sk); - - if ((s32)(tm->tcpm_ts - tp->rx_opt.ts_recent) <= 0 || - ((u32)get_seconds() - tm->tcpm_ts_stamp > TCP_PAWS_MSL && - tm->tcpm_ts_stamp <= (u32)tp->rx_opt.ts_recent_stamp)) { - tm->tcpm_ts_stamp = (u32)tp->rx_opt.ts_recent_stamp; - tm->tcpm_ts = tp->rx_opt.ts_recent; - } - ret = true; - } - rcu_read_unlock(); - } - return ret; -} - -bool tcp_tw_remember_stamp(struct inet_timewait_sock *tw) -{ - struct tcp_metrics_block *tm; - bool ret = false; - - rcu_read_lock(); - tm = __tcp_get_metrics_tw(tw); - if (tm) { - const struct tcp_timewait_sock *tcptw; - struct sock *sk = (struct sock *) tw; - - tcptw = tcp_twsk(sk); - if ((s32)(tm->tcpm_ts - tcptw->tw_ts_recent) <= 0 || - ((u32)get_seconds() - tm->tcpm_ts_stamp > TCP_PAWS_MSL && - tm->tcpm_ts_stamp <= (u32)tcptw->tw_ts_recent_stamp)) { - tm->tcpm_ts_stamp = (u32)tcptw->tw_ts_recent_stamp; - tm->tcpm_ts = tcptw->tw_ts_recent; - } + if (tm && tcp_metric_get(tm, TCP_METRIC_RTT)) ret = true; - } + else + ret = false; rcu_read_unlock(); return ret; @@ -791,14 +660,6 @@ static int tcp_metrics_fill_info(struct sk_buff *msg, jiffies - tm->tcpm_stamp, TCP_METRICS_ATTR_PAD) < 0) goto nla_put_failure; - if (tm->tcpm_ts_stamp) { - if (nla_put_s32(msg, TCP_METRICS_ATTR_TW_TS_STAMP, - (s32) (get_seconds() - tm->tcpm_ts_stamp)) < 0) - goto nla_put_failure; - if (nla_put_u32(msg, TCP_METRICS_ATTR_TW_TSVAL, - tm->tcpm_ts) < 0) - goto nla_put_failure; - } { int n = 0; diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index 7e16243cdb58..692f974e5abe 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -94,7 +94,6 @@ tcp_timewait_state_process(struct inet_timewait_sock *tw, struct sk_buff *skb, struct tcp_options_received tmp_opt; struct tcp_timewait_sock *tcptw = tcp_twsk((struct sock *)tw); bool paws_reject = false; - struct inet_timewait_death_row *tcp_death_row = &sock_net((struct sock*)tw)->ipv4.tcp_death_row; tmp_opt.saw_tstamp = 0; if (th->doff > (sizeof(*th) >> 2) && tcptw->tw_ts_recent_stamp) { @@ -149,12 +148,7 @@ tcp_timewait_state_process(struct inet_timewait_sock *tw, struct sk_buff *skb, tcptw->tw_ts_recent = tmp_opt.rcv_tsval; } - if (tcp_death_row->sysctl_tw_recycle && - tcptw->tw_ts_recent_stamp && - tcp_tw_remember_stamp(tw)) - inet_twsk_reschedule(tw, tw->tw_timeout); - else - inet_twsk_reschedule(tw, TCP_TIMEWAIT_LEN); + inet_twsk_reschedule(tw, TCP_TIMEWAIT_LEN); return TCP_TW_ACK; } @@ -259,12 +253,8 @@ void tcp_time_wait(struct sock *sk, int state, int timeo) const struct inet_connection_sock *icsk = inet_csk(sk); const struct tcp_sock *tp = tcp_sk(sk); struct inet_timewait_sock *tw; - bool recycle_ok = false; struct inet_timewait_death_row *tcp_death_row = &sock_net(sk)->ipv4.tcp_death_row; - if (tcp_death_row->sysctl_tw_recycle && tp->rx_opt.ts_recent_stamp) - recycle_ok = tcp_remember_stamp(sk); - tw = inet_twsk_alloc(sk, tcp_death_row, state); if (tw) { @@ -317,13 +307,9 @@ void tcp_time_wait(struct sock *sk, int state, int timeo) if (timeo < rto) timeo = rto; - if (recycle_ok) { - tw->tw_timeout = rto; - } else { - tw->tw_timeout = TCP_TIMEWAIT_LEN; - if (state == TCP_TIME_WAIT) - timeo = TCP_TIMEWAIT_LEN; - } + tw->tw_timeout = TCP_TIMEWAIT_LEN; + if (state == TCP_TIME_WAIT) + timeo = TCP_TIMEWAIT_LEN; inet_twsk_schedule(tw, timeo); /* Linkage updates. */ diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index 40d893556e67..b2ab411c6d37 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -249,7 +249,8 @@ void tcp_delack_timer_handler(struct sock *sk) sk_mem_reclaim_partial(sk); - if (sk->sk_state == TCP_CLOSE || !(icsk->icsk_ack.pending & ICSK_ACK_TIMER)) + if (((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN)) || + !(icsk->icsk_ack.pending & ICSK_ACK_TIMER)) goto out; if (time_after(icsk->icsk_ack.timeout, jiffies)) { @@ -552,7 +553,8 @@ void tcp_write_timer_handler(struct sock *sk) struct inet_connection_sock *icsk = inet_csk(sk); int event; - if (sk->sk_state == TCP_CLOSE || !icsk->icsk_pending) + if (((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN)) || + !icsk->icsk_pending) goto out; if (time_after(icsk->icsk_timeout, jiffies)) { diff --git a/net/ipv4/tcp_westwood.c b/net/ipv4/tcp_westwood.c index fed66dc0e0f5..9775453b8d17 100644 --- a/net/ipv4/tcp_westwood.c +++ b/net/ipv4/tcp_westwood.c @@ -265,8 +265,8 @@ static size_t tcp_westwood_info(struct sock *sk, u32 ext, int *attr, if (ext & (1 << (INET_DIAG_VEGASINFO - 1))) { info->vegas.tcpv_enabled = 1; info->vegas.tcpv_rttcnt = 0; - info->vegas.tcpv_rtt = jiffies_to_usecs(ca->rtt), - info->vegas.tcpv_minrtt = jiffies_to_usecs(ca->rtt_min), + info->vegas.tcpv_rtt = jiffies_to_usecs(ca->rtt); + info->vegas.tcpv_minrtt = jiffies_to_usecs(ca->rtt_min); *attr = INET_DIAG_VEGASINFO; return sizeof(struct tcpvegas_info); diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 363172527e43..8c69768a5c46 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -245,6 +245,7 @@ static struct ipv6_devconf ipv6_devconf __read_mostly = { #endif .enhanced_dad = 1, .addr_gen_mode = IN6_ADDR_GEN_MODE_EUI64, + .disable_policy = 0, }; static struct ipv6_devconf ipv6_devconf_dflt __read_mostly = { @@ -297,6 +298,7 @@ static struct ipv6_devconf ipv6_devconf_dflt __read_mostly = { #endif .enhanced_dad = 1, .addr_gen_mode = IN6_ADDR_GEN_MODE_EUI64, + .disable_policy = 0, }; /* Check if a valid qdisc is available */ @@ -944,6 +946,7 @@ ipv6_add_addr(struct inet6_dev *idev, const struct in6_addr *addr, const struct in6_addr *peer_addr, int pfxlen, int scope, u32 flags, u32 valid_lft, u32 prefered_lft) { + struct net *net = dev_net(idev->dev); struct inet6_ifaddr *ifa = NULL; struct rt6_info *rt; unsigned int hash; @@ -990,6 +993,10 @@ ipv6_add_addr(struct inet6_dev *idev, const struct in6_addr *addr, goto out; } + if (net->ipv6.devconf_all->disable_policy || + idev->cnf.disable_policy) + rt->dst.flags |= DST_NOPOLICY; + neigh_parms_data_state_setall(idev->nd_parms); ifa->addr = *addr; @@ -5003,6 +5010,7 @@ static inline void ipv6_store_devconf(struct ipv6_devconf *cnf, #endif array[DEVCONF_ENHANCED_DAD] = cnf->enhanced_dad; array[DEVCONF_ADDR_GEN_MODE] = cnf->addr_gen_mode; + array[DEVCONF_DISABLE_POLICY] = cnf->disable_policy; } static inline size_t inet6_ifla6_size(void) @@ -5827,6 +5835,105 @@ int addrconf_sysctl_ignore_routes_with_linkdown(struct ctl_table *ctl, return ret; } +static +void addrconf_set_nopolicy(struct rt6_info *rt, int action) +{ + if (rt) { + if (action) + rt->dst.flags |= DST_NOPOLICY; + else + rt->dst.flags &= ~DST_NOPOLICY; + } +} + +static +void addrconf_disable_policy_idev(struct inet6_dev *idev, int val) +{ + struct inet6_ifaddr *ifa; + + read_lock_bh(&idev->lock); + list_for_each_entry(ifa, &idev->addr_list, if_list) { + spin_lock(&ifa->lock); + if (ifa->rt) { + struct rt6_info *rt = ifa->rt; + struct fib6_table *table = rt->rt6i_table; + int cpu; + + read_lock(&table->tb6_lock); + addrconf_set_nopolicy(ifa->rt, val); + if (rt->rt6i_pcpu) { + for_each_possible_cpu(cpu) { + struct rt6_info **rtp; + + rtp = per_cpu_ptr(rt->rt6i_pcpu, cpu); + addrconf_set_nopolicy(*rtp, val); + } + } + read_unlock(&table->tb6_lock); + } + spin_unlock(&ifa->lock); + } + read_unlock_bh(&idev->lock); +} + +static +int addrconf_disable_policy(struct ctl_table *ctl, int *valp, int val) +{ + struct inet6_dev *idev; + struct net *net; + + if (!rtnl_trylock()) + return restart_syscall(); + + *valp = val; + + net = (struct net *)ctl->extra2; + if (valp == &net->ipv6.devconf_dflt->disable_policy) { + rtnl_unlock(); + return 0; + } + + if (valp == &net->ipv6.devconf_all->disable_policy) { + struct net_device *dev; + + for_each_netdev(net, dev) { + idev = __in6_dev_get(dev); + if (idev) + addrconf_disable_policy_idev(idev, val); + } + } else { + idev = (struct inet6_dev *)ctl->extra1; + addrconf_disable_policy_idev(idev, val); + } + + rtnl_unlock(); + return 0; +} + +static +int addrconf_sysctl_disable_policy(struct ctl_table *ctl, int write, + void __user *buffer, size_t *lenp, + loff_t *ppos) +{ + int *valp = ctl->data; + int val = *valp; + loff_t pos = *ppos; + struct ctl_table lctl; + int ret; + + lctl = *ctl; + lctl.data = &val; + ret = proc_dointvec(&lctl, write, buffer, lenp, ppos); + + if (write && (*valp != val)) + ret = addrconf_disable_policy(ctl, valp, val); + + if (ret) + *ppos = pos; + + return ret; +} + static int minus_one = -1; static const int one = 1; static const int two_five_five = 255; @@ -6185,6 +6292,13 @@ static const struct ctl_table addrconf_sysctl[] = { .proc_handler = addrconf_sysctl_addr_gen_mode, }, { + .procname = "disable_policy", + .data = &ipv6_devconf.disable_policy, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = addrconf_sysctl_disable_policy, + }, + { /* sentinel */ } }; diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index 04db40620ea6..a9a9553ee63d 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -920,12 +920,12 @@ static int __init inet6_init(void) err = register_pernet_subsys(&inet6_net_ops); if (err) goto register_pernet_fail; - err = icmpv6_init(); - if (err) - goto icmp_fail; err = ip6_mr_init(); if (err) goto ipmr_fail; + err = icmpv6_init(); + if (err) + goto icmp_fail; err = ndisc_init(); if (err) goto ndisc_fail; @@ -1061,10 +1061,10 @@ igmp_fail: ndisc_cleanup(); ndisc_fail: ip6_mr_cleanup(); -ipmr_fail: - icmpv6_cleanup(); icmp_fail: unregister_pernet_subsys(&inet6_net_ops); +ipmr_fail: + icmpv6_cleanup(); register_pernet_fail: sock_unregister(PF_INET6); rtnl_unregister_all(PF_INET6); diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index e4266746e4a2..d4bf2c68a545 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -923,6 +923,8 @@ add: ins = &rt->dst.rt6_next; iter = *ins; while (iter) { + if (iter->rt6i_metric > rt->rt6i_metric) + break; if (rt6_qualify_for_ecmp(iter)) { *ins = iter->dst.rt6_next; fib6_purge_rt(iter, fn, info->nl_net); diff --git a/net/ipv6/ip6_offload.c b/net/ipv6/ip6_offload.c index 0838e6d01d2e..93e58a5e1837 100644 --- a/net/ipv6/ip6_offload.c +++ b/net/ipv6/ip6_offload.c @@ -294,8 +294,10 @@ 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) + if (skb->encapsulation) { + skb_set_inner_protocol(skb, cpu_to_be16(ETH_P_IPV6)); skb_set_inner_network_header(skb, nhoff); + } iph->payload_len = htons(skb->len - nhoff - sizeof(*iph)); diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 528b3c1f3fde..58f6288e9ba5 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -768,13 +768,14 @@ slow_path: * Fragment the datagram. */ - *prevhdr = NEXTHDR_FRAGMENT; troom = rt->dst.dev->needed_tailroom; /* * Keep copying data until we run out. */ while (left > 0) { + u8 *fragnexthdr_offset; + len = left; /* IF: it doesn't fit, use 'mtu' - the data space left */ if (len > mtu) @@ -819,6 +820,10 @@ slow_path: */ skb_copy_from_linear_data(skb, skb_network_header(frag), hlen); + fragnexthdr_offset = skb_network_header(frag); + fragnexthdr_offset += prevhdr - skb_network_header(skb); + *fragnexthdr_offset = NEXTHDR_FRAGMENT; + /* * Build fragment header. */ @@ -1385,7 +1390,7 @@ emsgsize: if ((((length + fragheaderlen) > mtu) || (skb && skb_is_gso(skb))) && (sk->sk_protocol == IPPROTO_UDP) && - (rt->dst.dev->features & NETIF_F_UFO) && !rt->dst.header_len && + (rt->dst.dev->features & NETIF_F_UFO) && !dst_xfrm(&rt->dst) && (sk->sk_type == SOCK_DGRAM) && !udp_get_no_check6_tx(sk)) { err = ip6_ufo_append_data(sk, queue, getfrag, from, length, hh_len, fragheaderlen, exthdrlen, diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c index 644ba59fbd9d..3d8a3b63b4fd 100644 --- a/net/ipv6/ip6_vti.c +++ b/net/ipv6/ip6_vti.c @@ -485,11 +485,15 @@ vti6_xmit(struct sk_buff *skb, struct net_device *dev, struct flowi *fl) if (!skb->ignore_df && skb->len > mtu) { skb_dst(skb)->ops->update_pmtu(dst, NULL, skb, mtu); - if (skb->protocol == htons(ETH_P_IPV6)) + if (skb->protocol == htons(ETH_P_IPV6)) { + if (mtu < IPV6_MIN_MTU) + mtu = IPV6_MIN_MTU; + icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu); - else + } else { icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED, htonl(mtu)); + } return -EMSGSIZE; } diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 229bfcc451ef..35c58b669ebd 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -3299,7 +3299,6 @@ static size_t rt6_nlmsg_size(struct rt6_info *rt) nexthop_len = nla_total_size(0) /* RTA_MULTIPATH */ + NLA_ALIGN(sizeof(struct rtnexthop)) + nla_total_size(16) /* RTA_GATEWAY */ - + nla_total_size(4) /* RTA_OIF */ + lwtunnel_get_encap_size(rt->dst.lwtstate); nexthop_len *= rt->rt6i_nsiblings; @@ -3323,7 +3322,7 @@ static size_t rt6_nlmsg_size(struct rt6_info *rt) } static int rt6_nexthop_info(struct sk_buff *skb, struct rt6_info *rt, - unsigned int *flags) + unsigned int *flags, bool skip_oif) { if (!netif_running(rt->dst.dev) || !netif_carrier_ok(rt->dst.dev)) { *flags |= RTNH_F_LINKDOWN; @@ -3336,7 +3335,8 @@ static int rt6_nexthop_info(struct sk_buff *skb, struct rt6_info *rt, goto nla_put_failure; } - if (rt->dst.dev && + /* not needed for multipath encoding b/c it has a rtnexthop struct */ + if (!skip_oif && rt->dst.dev && nla_put_u32(skb, RTA_OIF, rt->dst.dev->ifindex)) goto nla_put_failure; @@ -3350,6 +3350,7 @@ nla_put_failure: return -EMSGSIZE; } +/* add multipath next hop */ static int rt6_add_nexthop(struct sk_buff *skb, struct rt6_info *rt) { struct rtnexthop *rtnh; @@ -3362,7 +3363,7 @@ static int rt6_add_nexthop(struct sk_buff *skb, struct rt6_info *rt) rtnh->rtnh_hops = 0; rtnh->rtnh_ifindex = rt->dst.dev ? rt->dst.dev->ifindex : 0; - if (rt6_nexthop_info(skb, rt, &flags) < 0) + if (rt6_nexthop_info(skb, rt, &flags, true) < 0) goto nla_put_failure; rtnh->rtnh_flags = flags; @@ -3515,7 +3516,7 @@ static int rt6_fill_node(struct net *net, nla_nest_end(skb, mp); } else { - if (rt6_nexthop_info(skb, rt, &rtm->rtm_flags) < 0) + if (rt6_nexthop_info(skb, rt, &rtm->rtm_flags, false) < 0) goto nla_put_failure; } diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 60a5295a7de6..0f08d718a002 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -101,12 +101,12 @@ static void inet6_sk_rx_dst_set(struct sock *sk, const struct sk_buff *skb) } } -static u32 tcp_v6_init_sequence(const struct sk_buff *skb, u32 *tsoff) +static u32 tcp_v6_init_seq_and_tsoff(const struct sk_buff *skb, u32 *tsoff) { - return secure_tcpv6_sequence_number(ipv6_hdr(skb)->daddr.s6_addr32, - ipv6_hdr(skb)->saddr.s6_addr32, - tcp_hdr(skb)->dest, - tcp_hdr(skb)->source, tsoff); + return secure_tcpv6_seq_and_tsoff(ipv6_hdr(skb)->daddr.s6_addr32, + ipv6_hdr(skb)->saddr.s6_addr32, + tcp_hdr(skb)->dest, + tcp_hdr(skb)->source, tsoff); } static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr, @@ -265,11 +265,6 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr, sk->sk_gso_type = SKB_GSO_TCPV6; ip6_dst_store(sk, dst, NULL, NULL); - if (tcp_death_row->sysctl_tw_recycle && - !tp->rx_opt.ts_recent_stamp && - ipv6_addr_equal(&fl6.daddr, &sk->sk_v6_daddr)) - tcp_fetch_timewait_stamp(sk, dst); - icsk->icsk_ext_hdr_len = 0; if (opt) icsk->icsk_ext_hdr_len = opt->opt_flen + @@ -287,11 +282,11 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr, sk_set_txhash(sk); if (likely(!tp->repair)) { - seq = secure_tcpv6_sequence_number(np->saddr.s6_addr32, - sk->sk_v6_daddr.s6_addr32, - inet->inet_sport, - inet->inet_dport, - &tp->tsoffset); + seq = secure_tcpv6_seq_and_tsoff(np->saddr.s6_addr32, + sk->sk_v6_daddr.s6_addr32, + inet->inet_sport, + inet->inet_dport, + &tp->tsoffset); if (!tp->write_seq) tp->write_seq = seq; } @@ -391,10 +386,12 @@ static void tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, np = inet6_sk(sk); if (type == NDISC_REDIRECT) { - struct dst_entry *dst = __sk_dst_check(sk, np->dst_cookie); + if (!sock_owned_by_user(sk)) { + struct dst_entry *dst = __sk_dst_check(sk, np->dst_cookie); - if (dst) - dst->ops->redirect(dst, sk, skb); + if (dst) + dst->ops->redirect(dst, sk, skb); + } goto out; } @@ -725,11 +722,8 @@ static void tcp_v6_init_req(struct request_sock *req, static struct dst_entry *tcp_v6_route_req(const struct sock *sk, struct flowi *fl, - const struct request_sock *req, - bool *strict) + const struct request_sock *req) { - if (strict) - *strict = true; return inet6_csk_route_req(sk, &fl->u.ip6, req, IPPROTO_TCP); } @@ -755,7 +749,7 @@ static const struct tcp_request_sock_ops tcp_request_sock_ipv6_ops = { .cookie_init_seq = cookie_v6_init_sequence, #endif .route_req = tcp_v6_route_req, - .init_seq = tcp_v6_init_sequence, + .init_seq_tsoff = tcp_v6_init_seq_and_tsoff, .send_synack = tcp_v6_send_synack, }; diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 4e4c401e3bc6..08a188ffe070 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -864,6 +864,64 @@ discard: return 0; } +static struct sock *__udp6_lib_demux_lookup(struct net *net, + __be16 loc_port, const struct in6_addr *loc_addr, + __be16 rmt_port, const struct in6_addr *rmt_addr, + int dif) +{ + struct sock *sk; + + rcu_read_lock(); + sk = __udp6_lib_lookup(net, rmt_addr, rmt_port, loc_addr, loc_port, + dif, &udp_table, NULL); + if (sk && !atomic_inc_not_zero(&sk->sk_refcnt)) + sk = NULL; + rcu_read_unlock(); + + return sk; +} + +static void udp_v6_early_demux(struct sk_buff *skb) +{ + struct net *net = dev_net(skb->dev); + const struct udphdr *uh; + struct sock *sk; + struct dst_entry *dst; + int dif = skb->dev->ifindex; + + if (!pskb_may_pull(skb, skb_transport_offset(skb) + + sizeof(struct udphdr))) + return; + + uh = udp_hdr(skb); + + if (skb->pkt_type == PACKET_HOST) + sk = __udp6_lib_demux_lookup(net, uh->dest, + &ipv6_hdr(skb)->daddr, + uh->source, &ipv6_hdr(skb)->saddr, + dif); + else + return; + + if (!sk) + return; + + skb->sk = sk; + skb->destructor = sock_efree; + dst = READ_ONCE(sk->sk_rx_dst); + + if (dst) + dst = dst_check(dst, inet6_sk(sk)->rx_dst_cookie); + if (dst) { + if (dst->flags & DST_NOCACHE) { + if (likely(atomic_inc_not_zero(&dst->__refcnt))) + skb_dst_set(skb, dst); + } else { + skb_dst_set_noref(skb, dst); + } + } +} + static __inline__ int udpv6_rcv(struct sk_buff *skb) { return __udp6_lib_rcv(skb, &udp_table, IPPROTO_UDP); @@ -1379,6 +1437,7 @@ int compat_udpv6_getsockopt(struct sock *sk, int level, int optname, #endif static const struct inet6_protocol udpv6_protocol = { + .early_demux = udp_v6_early_demux, .handler = udpv6_rcv, .err_handler = udpv6_err, .flags = INET6_PROTO_NOPOLICY|INET6_PROTO_FINAL, diff --git a/net/irda/af_irda.c b/net/irda/af_irda.c index 81adc29a448d..8d77ad5cadaf 100644 --- a/net/irda/af_irda.c +++ b/net/irda/af_irda.c @@ -828,7 +828,8 @@ out: * Wait for incoming connection * */ -static int irda_accept(struct socket *sock, struct socket *newsock, int flags) +static int irda_accept(struct socket *sock, struct socket *newsock, int flags, + bool kern) { struct sock *sk = sock->sk; struct irda_sock *new, *self = irda_sk(sk); @@ -836,7 +837,7 @@ static int irda_accept(struct socket *sock, struct socket *newsock, int flags) struct sk_buff *skb = NULL; int err; - err = irda_create(sock_net(sk), newsock, sk->sk_protocol, 0); + err = irda_create(sock_net(sk), newsock, sk->sk_protocol, kern); if (err) return err; diff --git a/net/iucv/af_iucv.c b/net/iucv/af_iucv.c index 89bbde1081ce..84de7b6326dc 100644 --- a/net/iucv/af_iucv.c +++ b/net/iucv/af_iucv.c @@ -938,7 +938,7 @@ done: /* Accept a pending connection */ static int iucv_sock_accept(struct socket *sock, struct socket *newsock, - int flags) + int flags, bool kern) { DECLARE_WAITQUEUE(wait, current); struct sock *sk = sock->sk, *nsk; diff --git a/net/llc/af_llc.c b/net/llc/af_llc.c index 06186d608a27..cb4fff785cbf 100644 --- a/net/llc/af_llc.c +++ b/net/llc/af_llc.c @@ -641,11 +641,13 @@ static void llc_cmsg_rcv(struct msghdr *msg, struct sk_buff *skb) * @sock: Socket which connections arrive on. * @newsock: Socket to move incoming connection to. * @flags: User specified operational flags. + * @kern: If the socket is kernel internal * * Accept a new incoming connection. * Returns 0 upon success, negative otherwise. */ -static int llc_ui_accept(struct socket *sock, struct socket *newsock, int flags) +static int llc_ui_accept(struct socket *sock, struct socket *newsock, int flags, + bool kern) { struct sock *sk = sock->sk, *newsk; struct llc_sock *llc, *newllc; diff --git a/net/mpls/af_mpls.c b/net/mpls/af_mpls.c index 3818686182b2..f7a08e5f9763 100644 --- a/net/mpls/af_mpls.c +++ b/net/mpls/af_mpls.c @@ -32,7 +32,9 @@ #define MPLS_NEIGH_TABLE_UNSPEC (NEIGH_LINK_TABLE + 1) static int zero = 0; +static int one = 1; static int label_limit = (1 << 20) - 1; +static int ttl_max = 255; static void rtmsg_lfib(int event, u32 label, struct mpls_route *rt, struct nlmsghdr *nlh, struct net *net, u32 portid, @@ -220,8 +222,8 @@ out: return &rt->rt_nh[nh_index]; } -static bool mpls_egress(struct mpls_route *rt, struct sk_buff *skb, - struct mpls_entry_decoded dec) +static bool mpls_egress(struct net *net, struct mpls_route *rt, + struct sk_buff *skb, struct mpls_entry_decoded dec) { enum mpls_payload_type payload_type; bool success = false; @@ -246,22 +248,46 @@ static bool mpls_egress(struct mpls_route *rt, struct sk_buff *skb, switch (payload_type) { case MPT_IPV4: { struct iphdr *hdr4 = ip_hdr(skb); + u8 new_ttl; skb->protocol = htons(ETH_P_IP); + + /* If propagating TTL, take the decremented TTL from + * the incoming MPLS header, otherwise decrement the + * TTL, but only if not 0 to avoid underflow. + */ + if (rt->rt_ttl_propagate == MPLS_TTL_PROP_ENABLED || + (rt->rt_ttl_propagate == MPLS_TTL_PROP_DEFAULT && + net->mpls.ip_ttl_propagate)) + new_ttl = dec.ttl; + else + new_ttl = hdr4->ttl ? hdr4->ttl - 1 : 0; + csum_replace2(&hdr4->check, htons(hdr4->ttl << 8), - htons(dec.ttl << 8)); - hdr4->ttl = dec.ttl; + htons(new_ttl << 8)); + hdr4->ttl = new_ttl; success = true; break; } case MPT_IPV6: { struct ipv6hdr *hdr6 = ipv6_hdr(skb); skb->protocol = htons(ETH_P_IPV6); - hdr6->hop_limit = dec.ttl; + + /* If propagating TTL, take the decremented TTL from + * the incoming MPLS header, otherwise decrement the + * hop limit, but only if not 0 to avoid underflow. + */ + if (rt->rt_ttl_propagate == MPLS_TTL_PROP_ENABLED || + (rt->rt_ttl_propagate == MPLS_TTL_PROP_DEFAULT && + net->mpls.ip_ttl_propagate)) + hdr6->hop_limit = dec.ttl; + else if (hdr6->hop_limit) + hdr6->hop_limit = hdr6->hop_limit - 1; success = true; break; } case MPT_UNSPEC: + /* Should have decided which protocol it is by now */ break; } @@ -361,7 +387,7 @@ static int mpls_forward(struct sk_buff *skb, struct net_device *dev, if (unlikely(!new_header_size && dec.bos)) { /* Penultimate hop popping */ - if (!mpls_egress(rt, skb, dec)) + if (!mpls_egress(dev_net(out_dev), rt, skb, dec)) goto err; } else { bool bos; @@ -412,6 +438,7 @@ static struct packet_type mpls_packet_type __read_mostly = { static const struct nla_policy rtm_mpls_policy[RTA_MAX+1] = { [RTA_DST] = { .type = NLA_U32 }, [RTA_OIF] = { .type = NLA_U32 }, + [RTA_TTL_PROPAGATE] = { .type = NLA_U8 }, }; struct mpls_route_config { @@ -421,6 +448,7 @@ struct mpls_route_config { u8 rc_via_alen; u8 rc_via[MAX_VIA_ALEN]; u32 rc_label; + u8 rc_ttl_propagate; u8 rc_output_labels; u32 rc_output_label[MAX_NEW_LABELS]; u32 rc_nlflags; @@ -856,6 +884,7 @@ static int mpls_route_add(struct mpls_route_config *cfg) rt->rt_protocol = cfg->rc_protocol; rt->rt_payload_type = cfg->rc_payload_type; + rt->rt_ttl_propagate = cfg->rc_ttl_propagate; if (cfg->rc_mp) err = mpls_nh_build_multi(cfg, rt); @@ -1288,7 +1317,8 @@ static void mpls_ifdown(struct net_device *dev, int event) /* fall through */ case NETDEV_CHANGE: nh->nh_flags |= RTNH_F_LINKDOWN; - ACCESS_ONCE(rt->rt_nhn_alive) = rt->rt_nhn_alive - 1; + if (event != NETDEV_UNREGISTER) + ACCESS_ONCE(rt->rt_nhn_alive) = rt->rt_nhn_alive - 1; break; } if (event == NETDEV_UNREGISTER) @@ -1576,6 +1606,7 @@ static int rtm_to_route_config(struct sk_buff *skb, struct nlmsghdr *nlh, cfg->rc_label = LABEL_NOT_SPECIFIED; cfg->rc_protocol = rtm->rtm_protocol; cfg->rc_via_table = MPLS_NEIGH_TABLE_UNSPEC; + cfg->rc_ttl_propagate = MPLS_TTL_PROP_DEFAULT; cfg->rc_nlflags = nlh->nlmsg_flags; cfg->rc_nlinfo.portid = NETLINK_CB(skb).portid; cfg->rc_nlinfo.nlh = nlh; @@ -1622,6 +1653,17 @@ static int rtm_to_route_config(struct sk_buff *skb, struct nlmsghdr *nlh, cfg->rc_mp_len = nla_len(nla); break; } + case RTA_TTL_PROPAGATE: + { + u8 ttl_propagate = nla_get_u8(nla); + + if (ttl_propagate > 1) + goto errout; + cfg->rc_ttl_propagate = ttl_propagate ? + MPLS_TTL_PROP_ENABLED : + MPLS_TTL_PROP_DISABLED; + break; + } default: /* Unsupported attribute */ goto errout; @@ -1682,6 +1724,15 @@ static int mpls_dump_route(struct sk_buff *skb, u32 portid, u32 seq, int event, if (nla_put_labels(skb, RTA_DST, 1, &label)) goto nla_put_failure; + + if (rt->rt_ttl_propagate != MPLS_TTL_PROP_DEFAULT) { + bool ttl_propagate = + rt->rt_ttl_propagate == MPLS_TTL_PROP_ENABLED; + + if (nla_put_u8(skb, RTA_TTL_PROPAGATE, + ttl_propagate)) + goto nla_put_failure; + } if (rt->rt_nhn == 1) { const struct mpls_nh *nh = rt->rt_nh; @@ -1792,7 +1843,8 @@ static inline size_t lfib_nlmsg_size(struct mpls_route *rt) { size_t payload = NLMSG_ALIGN(sizeof(struct rtmsg)) - + nla_total_size(4); /* RTA_DST */ + + nla_total_size(4) /* RTA_DST */ + + nla_total_size(1); /* RTA_TTL_PROPAGATE */ if (rt->rt_nhn == 1) { struct mpls_nh *nh = rt->rt_nh; @@ -1876,6 +1928,7 @@ static int resize_platform_label_table(struct net *net, size_t limit) RCU_INIT_POINTER(rt0->rt_nh->nh_dev, lo); rt0->rt_protocol = RTPROT_KERNEL; rt0->rt_payload_type = MPT_IPV4; + rt0->rt_ttl_propagate = MPLS_TTL_PROP_DEFAULT; rt0->rt_nh->nh_via_table = NEIGH_LINK_TABLE; rt0->rt_nh->nh_via_alen = lo->addr_len; memcpy(__mpls_nh_via(rt0, rt0->rt_nh), lo->dev_addr, @@ -1889,6 +1942,7 @@ static int resize_platform_label_table(struct net *net, size_t limit) RCU_INIT_POINTER(rt2->rt_nh->nh_dev, lo); rt2->rt_protocol = RTPROT_KERNEL; rt2->rt_payload_type = MPT_IPV6; + rt0->rt_ttl_propagate = MPLS_TTL_PROP_DEFAULT; rt2->rt_nh->nh_via_table = NEIGH_LINK_TABLE; rt2->rt_nh->nh_via_alen = lo->addr_len; memcpy(__mpls_nh_via(rt2, rt2->rt_nh), lo->dev_addr, @@ -1970,6 +2024,9 @@ static int mpls_platform_labels(struct ctl_table *table, int write, return ret; } +#define MPLS_NS_SYSCTL_OFFSET(field) \ + (&((struct net *)0)->field) + static const struct ctl_table mpls_table[] = { { .procname = "platform_labels", @@ -1978,21 +2035,47 @@ static const struct ctl_table mpls_table[] = { .mode = 0644, .proc_handler = mpls_platform_labels, }, + { + .procname = "ip_ttl_propagate", + .data = MPLS_NS_SYSCTL_OFFSET(mpls.ip_ttl_propagate), + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = &zero, + .extra2 = &one, + }, + { + .procname = "default_ttl", + .data = MPLS_NS_SYSCTL_OFFSET(mpls.default_ttl), + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = &one, + .extra2 = &ttl_max, + }, { } }; static int mpls_net_init(struct net *net) { struct ctl_table *table; + int i; net->mpls.platform_labels = 0; net->mpls.platform_label = NULL; + net->mpls.ip_ttl_propagate = 1; + net->mpls.default_ttl = 255; table = kmemdup(mpls_table, sizeof(mpls_table), GFP_KERNEL); if (table == NULL) return -ENOMEM; - table[0].data = net; + /* Table data contains only offsets relative to the base of + * the mdev at this point, so make them absolute. + */ + for (i = 0; i < ARRAY_SIZE(mpls_table) - 1; i++) + table[i].data = (char *)net + (uintptr_t)table[i].data; + net->mpls.ctl = register_net_sysctl(net, "net/mpls", table); if (net->mpls.ctl == NULL) { kfree(table); @@ -2028,6 +2111,7 @@ static void mpls_net_exit(struct net *net) for (index = 0; index < platform_labels; index++) { struct mpls_route *rt = rtnl_dereference(platform_label[index]); RCU_INIT_POINTER(platform_label[index], NULL); + mpls_notify_route(net, index, rt, NULL, NULL); mpls_rt_free(rt); } rtnl_unlock(); diff --git a/net/mpls/internal.h b/net/mpls/internal.h index 76360d8b9579..62928d8fabd1 100644 --- a/net/mpls/internal.h +++ b/net/mpls/internal.h @@ -90,6 +90,12 @@ struct mpls_nh { /* next hop label forwarding entry */ u8 nh_via_table; }; +enum mpls_ttl_propagation { + MPLS_TTL_PROP_DEFAULT, + MPLS_TTL_PROP_ENABLED, + MPLS_TTL_PROP_DISABLED, +}; + /* The route, nexthops and vias are stored together in the same memory * block: * @@ -116,6 +122,7 @@ struct mpls_route { /* next hop label forwarding entry */ u8 rt_protocol; u8 rt_payload_type; u8 rt_max_alen; + u8 rt_ttl_propagate; unsigned int rt_nhn; unsigned int rt_nhn_alive; struct mpls_nh rt_nh[0]; diff --git a/net/mpls/mpls_iptunnel.c b/net/mpls/mpls_iptunnel.c index e4e4424f9eb1..22f71fce0bfb 100644 --- a/net/mpls/mpls_iptunnel.c +++ b/net/mpls/mpls_iptunnel.c @@ -29,6 +29,7 @@ static const struct nla_policy mpls_iptunnel_policy[MPLS_IPTUNNEL_MAX + 1] = { [MPLS_IPTUNNEL_DST] = { .type = NLA_U32 }, + [MPLS_IPTUNNEL_TTL] = { .type = NLA_U8 }, }; static unsigned int mpls_encap_size(struct mpls_iptunnel_encap *en) @@ -49,6 +50,7 @@ static int mpls_xmit(struct sk_buff *skb) struct rtable *rt = NULL; struct rt6_info *rt6 = NULL; struct mpls_dev *out_mdev; + struct net *net; int err = 0; bool bos; int i; @@ -56,17 +58,7 @@ static int mpls_xmit(struct sk_buff *skb) /* Find the output device */ out_dev = dst->dev; - - /* Obtain the ttl */ - if (dst->ops->family == AF_INET) { - ttl = ip_hdr(skb)->ttl; - rt = (struct rtable *)dst; - } else if (dst->ops->family == AF_INET6) { - ttl = ipv6_hdr(skb)->hop_limit; - rt6 = (struct rt6_info *)dst; - } else { - goto drop; - } + net = dev_net(out_dev); skb_orphan(skb); @@ -78,6 +70,38 @@ static int mpls_xmit(struct sk_buff *skb) tun_encap_info = mpls_lwtunnel_encap(dst->lwtstate); + /* Obtain the ttl using the following set of rules. + * + * LWT ttl propagation setting: + * - disabled => use default TTL value from LWT + * - enabled => use TTL value from IPv4/IPv6 header + * - default => + * Global ttl propagation setting: + * - disabled => use default TTL value from global setting + * - enabled => use TTL value from IPv4/IPv6 header + */ + if (dst->ops->family == AF_INET) { + if (tun_encap_info->ttl_propagate == MPLS_TTL_PROP_DISABLED) + ttl = tun_encap_info->default_ttl; + else if (tun_encap_info->ttl_propagate == MPLS_TTL_PROP_DEFAULT && + !net->mpls.ip_ttl_propagate) + ttl = net->mpls.default_ttl; + else + ttl = ip_hdr(skb)->ttl; + rt = (struct rtable *)dst; + } else if (dst->ops->family == AF_INET6) { + if (tun_encap_info->ttl_propagate == MPLS_TTL_PROP_DISABLED) + ttl = tun_encap_info->default_ttl; + else if (tun_encap_info->ttl_propagate == MPLS_TTL_PROP_DEFAULT && + !net->mpls.ip_ttl_propagate) + ttl = net->mpls.default_ttl; + else + ttl = ipv6_hdr(skb)->hop_limit; + rt6 = (struct rt6_info *)dst; + } else { + goto drop; + } + /* Verify the destination can hold the packet */ new_header_size = mpls_encap_size(tun_encap_info); mtu = mpls_dev_mtu(out_dev); @@ -160,6 +184,17 @@ static int mpls_build_state(struct nlattr *nla, &tun_encap_info->labels, tun_encap_info->label); if (ret) goto errout; + + tun_encap_info->ttl_propagate = MPLS_TTL_PROP_DEFAULT; + + if (tb[MPLS_IPTUNNEL_TTL]) { + tun_encap_info->default_ttl = nla_get_u8(tb[MPLS_IPTUNNEL_TTL]); + /* TTL 0 implies propagate from IP header */ + tun_encap_info->ttl_propagate = tun_encap_info->default_ttl ? + MPLS_TTL_PROP_DISABLED : + MPLS_TTL_PROP_ENABLED; + } + newts->type = LWTUNNEL_ENCAP_MPLS; newts->flags |= LWTUNNEL_STATE_XMIT_REDIRECT; newts->headroom = mpls_encap_size(tun_encap_info); @@ -186,6 +221,10 @@ static int mpls_fill_encap_info(struct sk_buff *skb, tun_encap_info->label)) goto nla_put_failure; + if (tun_encap_info->ttl_propagate != MPLS_TTL_PROP_DEFAULT && + nla_put_u8(skb, MPLS_IPTUNNEL_TTL, tun_encap_info->default_ttl)) + goto nla_put_failure; + return 0; nla_put_failure: @@ -195,10 +234,16 @@ nla_put_failure: static int mpls_encap_nlsize(struct lwtunnel_state *lwtstate) { struct mpls_iptunnel_encap *tun_encap_info; + int nlsize; tun_encap_info = mpls_lwtunnel_encap(lwtstate); - return nla_total_size(tun_encap_info->labels * 4); + nlsize = nla_total_size(tun_encap_info->labels * 4); + + if (tun_encap_info->ttl_propagate != MPLS_TTL_PROP_DEFAULT) + nlsize += nla_total_size(1); + + return nlsize; } static int mpls_encap_cmp(struct lwtunnel_state *a, struct lwtunnel_state *b) @@ -207,7 +252,9 @@ static int mpls_encap_cmp(struct lwtunnel_state *a, struct lwtunnel_state *b) struct mpls_iptunnel_encap *b_hdr = mpls_lwtunnel_encap(b); int l; - if (a_hdr->labels != b_hdr->labels) + if (a_hdr->labels != b_hdr->labels || + a_hdr->ttl_propagate != b_hdr->ttl_propagate || + a_hdr->default_ttl != b_hdr->default_ttl) return 1; for (l = 0; l < MAX_NEW_LABELS; l++) diff --git a/net/netrom/af_netrom.c b/net/netrom/af_netrom.c index 4bbf4526b885..ebf16f7f9089 100644 --- a/net/netrom/af_netrom.c +++ b/net/netrom/af_netrom.c @@ -765,7 +765,8 @@ out_release: return err; } -static int nr_accept(struct socket *sock, struct socket *newsock, int flags) +static int nr_accept(struct socket *sock, struct socket *newsock, int flags, + bool kern) { struct sk_buff *skb; struct sock *newsk; diff --git a/net/nfc/llcp_sock.c b/net/nfc/llcp_sock.c index 879885b31cce..2ffb18e73df6 100644 --- a/net/nfc/llcp_sock.c +++ b/net/nfc/llcp_sock.c @@ -441,7 +441,7 @@ struct sock *nfc_llcp_accept_dequeue(struct sock *parent, } static int llcp_sock_accept(struct socket *sock, struct socket *newsock, - int flags) + int flags, bool kern) { DECLARE_WAITQUEUE(wait, current); struct sock *sk = sock->sk, *new_sk; diff --git a/net/phonet/pep.c b/net/phonet/pep.c index 222bedcd9575..e81537991ddf 100644 --- a/net/phonet/pep.c +++ b/net/phonet/pep.c @@ -772,7 +772,8 @@ static void pep_sock_close(struct sock *sk, long timeout) sock_put(sk); } -static struct sock *pep_sock_accept(struct sock *sk, int flags, int *errp) +static struct sock *pep_sock_accept(struct sock *sk, int flags, int *errp, + bool kern) { struct pep_sock *pn = pep_sk(sk), *newpn; struct sock *newsk = NULL; @@ -846,7 +847,8 @@ static struct sock *pep_sock_accept(struct sock *sk, int flags, int *errp) } /* Create a new to-be-accepted sock */ - newsk = sk_alloc(sock_net(sk), PF_PHONET, GFP_KERNEL, sk->sk_prot, 0); + newsk = sk_alloc(sock_net(sk), PF_PHONET, GFP_KERNEL, sk->sk_prot, + kern); if (!newsk) { pep_reject_conn(sk, skb, PN_PIPE_ERR_OVERLOAD, GFP_KERNEL); err = -ENOBUFS; diff --git a/net/phonet/socket.c b/net/phonet/socket.c index a6c8da3ee893..64634e3ec2fc 100644 --- a/net/phonet/socket.c +++ b/net/phonet/socket.c @@ -305,7 +305,7 @@ out: } static int pn_socket_accept(struct socket *sock, struct socket *newsock, - int flags) + int flags, bool kern) { struct sock *sk = sock->sk; struct sock *newsk; @@ -314,7 +314,7 @@ static int pn_socket_accept(struct socket *sock, struct socket *newsock, if (unlikely(sk->sk_state != TCP_LISTEN)) return -EINVAL; - newsk = sk->sk_prot->accept(sk, flags, &err); + newsk = sk->sk_prot->accept(sk, flags, &err, kern); if (!newsk) return err; diff --git a/net/rds/connection.c b/net/rds/connection.c index 0e04dcceb1d4..1fa75ab7b733 100644 --- a/net/rds/connection.c +++ b/net/rds/connection.c @@ -429,6 +429,7 @@ void rds_conn_destroy(struct rds_connection *conn) */ rds_cong_remove_conn(conn); + put_net(conn->c_net); kmem_cache_free(rds_conn_slab, conn); spin_lock_irqsave(&rds_conn_lock, flags); diff --git a/net/rds/ib_cm.c b/net/rds/ib_cm.c index ce3775abc6e7..80fb6f63e768 100644 --- a/net/rds/ib_cm.c +++ b/net/rds/ib_cm.c @@ -442,7 +442,7 @@ static int rds_ib_setup_qp(struct rds_connection *conn) ic->i_send_cq = NULL; ibdev_put_vector(rds_ibdev, ic->i_scq_vector); rdsdebug("ib_create_cq send failed: %d\n", ret); - goto out; + goto rds_ibdev_out; } ic->i_rcq_vector = ibdev_get_unused_vector(rds_ibdev); @@ -456,19 +456,19 @@ static int rds_ib_setup_qp(struct rds_connection *conn) ic->i_recv_cq = NULL; ibdev_put_vector(rds_ibdev, ic->i_rcq_vector); rdsdebug("ib_create_cq recv failed: %d\n", ret); - goto out; + goto send_cq_out; } ret = ib_req_notify_cq(ic->i_send_cq, IB_CQ_NEXT_COMP); if (ret) { rdsdebug("ib_req_notify_cq send failed: %d\n", ret); - goto out; + goto recv_cq_out; } ret = ib_req_notify_cq(ic->i_recv_cq, IB_CQ_SOLICITED); if (ret) { rdsdebug("ib_req_notify_cq recv failed: %d\n", ret); - goto out; + goto recv_cq_out; } /* XXX negotiate max send/recv with remote? */ @@ -494,7 +494,7 @@ static int rds_ib_setup_qp(struct rds_connection *conn) ret = rdma_create_qp(ic->i_cm_id, ic->i_pd, &attr); if (ret) { rdsdebug("rdma_create_qp failed: %d\n", ret); - goto out; + goto recv_cq_out; } ic->i_send_hdrs = ib_dma_alloc_coherent(dev, @@ -504,7 +504,7 @@ static int rds_ib_setup_qp(struct rds_connection *conn) if (!ic->i_send_hdrs) { ret = -ENOMEM; rdsdebug("ib_dma_alloc_coherent send failed\n"); - goto out; + goto qp_out; } ic->i_recv_hdrs = ib_dma_alloc_coherent(dev, @@ -514,7 +514,7 @@ static int rds_ib_setup_qp(struct rds_connection *conn) if (!ic->i_recv_hdrs) { ret = -ENOMEM; rdsdebug("ib_dma_alloc_coherent recv failed\n"); - goto out; + goto send_hdrs_dma_out; } ic->i_ack = ib_dma_alloc_coherent(dev, sizeof(struct rds_header), @@ -522,7 +522,7 @@ static int rds_ib_setup_qp(struct rds_connection *conn) if (!ic->i_ack) { ret = -ENOMEM; rdsdebug("ib_dma_alloc_coherent ack failed\n"); - goto out; + goto recv_hdrs_dma_out; } ic->i_sends = vzalloc_node(ic->i_send_ring.w_nr * sizeof(struct rds_ib_send_work), @@ -530,7 +530,7 @@ static int rds_ib_setup_qp(struct rds_connection *conn) if (!ic->i_sends) { ret = -ENOMEM; rdsdebug("send allocation failed\n"); - goto out; + goto ack_dma_out; } ic->i_recvs = vzalloc_node(ic->i_recv_ring.w_nr * sizeof(struct rds_ib_recv_work), @@ -538,7 +538,7 @@ static int rds_ib_setup_qp(struct rds_connection *conn) if (!ic->i_recvs) { ret = -ENOMEM; rdsdebug("recv allocation failed\n"); - goto out; + goto sends_out; } rds_ib_recv_init_ack(ic); @@ -546,8 +546,33 @@ static int rds_ib_setup_qp(struct rds_connection *conn) rdsdebug("conn %p pd %p cq %p %p\n", conn, ic->i_pd, ic->i_send_cq, ic->i_recv_cq); -out: + return ret; + +sends_out: + vfree(ic->i_sends); +ack_dma_out: + ib_dma_free_coherent(dev, sizeof(struct rds_header), + ic->i_ack, ic->i_ack_dma); +recv_hdrs_dma_out: + ib_dma_free_coherent(dev, ic->i_recv_ring.w_nr * + sizeof(struct rds_header), + ic->i_recv_hdrs, ic->i_recv_hdrs_dma); +send_hdrs_dma_out: + ib_dma_free_coherent(dev, ic->i_send_ring.w_nr * + sizeof(struct rds_header), + ic->i_send_hdrs, ic->i_send_hdrs_dma); +qp_out: + rdma_destroy_qp(ic->i_cm_id); +recv_cq_out: + if (!ib_destroy_cq(ic->i_recv_cq)) + ic->i_recv_cq = NULL; +send_cq_out: + if (!ib_destroy_cq(ic->i_send_cq)) + ic->i_send_cq = NULL; +rds_ibdev_out: + rds_ib_remove_conn(rds_ibdev, conn); rds_ib_dev_put(rds_ibdev); + return ret; } @@ -677,9 +702,8 @@ int rds_ib_cm_handle_connect(struct rdma_cm_id *cm_id, event->param.conn.initiator_depth); /* rdma_accept() calls rdma_reject() internally if it fails */ - err = rdma_accept(cm_id, &conn_param); - if (err) - rds_ib_conn_error(conn, "rdma_accept failed (%d)\n", err); + if (rdma_accept(cm_id, &conn_param)) + rds_ib_conn_error(conn, "rdma_accept failed\n"); out: if (conn) diff --git a/net/rds/ib_fmr.c b/net/rds/ib_fmr.c index 4fe8f4fec4ee..86ef907067bb 100644 --- a/net/rds/ib_fmr.c +++ b/net/rds/ib_fmr.c @@ -78,17 +78,15 @@ struct rds_ib_mr *rds_ib_alloc_fmr(struct rds_ib_device *rds_ibdev, int npages) return ibmr; out_no_cigar: - if (ibmr) { - if (fmr->fmr) - ib_dealloc_fmr(fmr->fmr); - kfree(ibmr); - } + kfree(ibmr); atomic_dec(&pool->item_count); + return ERR_PTR(err); } -int rds_ib_map_fmr(struct rds_ib_device *rds_ibdev, struct rds_ib_mr *ibmr, - struct scatterlist *sg, unsigned int nents) +static int rds_ib_map_fmr(struct rds_ib_device *rds_ibdev, + struct rds_ib_mr *ibmr, struct scatterlist *sg, + unsigned int nents) { struct ib_device *dev = rds_ibdev->dev; struct rds_ib_fmr *fmr = &ibmr->u.fmr; @@ -114,29 +112,39 @@ int rds_ib_map_fmr(struct rds_ib_device *rds_ibdev, struct rds_ib_mr *ibmr, u64 dma_addr = ib_sg_dma_address(dev, &scat[i]); if (dma_addr & ~PAGE_MASK) { - if (i > 0) + if (i > 0) { + ib_dma_unmap_sg(dev, sg, nents, + DMA_BIDIRECTIONAL); return -EINVAL; - else + } else { ++page_cnt; + } } if ((dma_addr + dma_len) & ~PAGE_MASK) { - if (i < sg_dma_len - 1) + if (i < sg_dma_len - 1) { + ib_dma_unmap_sg(dev, sg, nents, + DMA_BIDIRECTIONAL); return -EINVAL; - else + } else { ++page_cnt; + } } len += dma_len; } page_cnt += len >> PAGE_SHIFT; - if (page_cnt > ibmr->pool->fmr_attr.max_pages) + if (page_cnt > ibmr->pool->fmr_attr.max_pages) { + ib_dma_unmap_sg(dev, sg, nents, DMA_BIDIRECTIONAL); return -EINVAL; + } dma_pages = kmalloc_node(sizeof(u64) * page_cnt, GFP_ATOMIC, rdsibdev_to_node(rds_ibdev)); - if (!dma_pages) + if (!dma_pages) { + ib_dma_unmap_sg(dev, sg, nents, DMA_BIDIRECTIONAL); return -ENOMEM; + } page_cnt = 0; for (i = 0; i < sg_dma_len; ++i) { @@ -149,8 +157,10 @@ int rds_ib_map_fmr(struct rds_ib_device *rds_ibdev, struct rds_ib_mr *ibmr, } ret = ib_map_phys_fmr(fmr->fmr, dma_pages, page_cnt, io_addr); - if (ret) + if (ret) { + ib_dma_unmap_sg(dev, sg, nents, DMA_BIDIRECTIONAL); goto out; + } /* Success - we successfully remapped the MR, so we can * safely tear down the old mapping. diff --git a/net/rds/ib_mr.h b/net/rds/ib_mr.h index 5d6e98a79a5e..0ea4ab017a8c 100644 --- a/net/rds/ib_mr.h +++ b/net/rds/ib_mr.h @@ -125,8 +125,6 @@ void rds_ib_mr_exit(void); void __rds_ib_teardown_mr(struct rds_ib_mr *); void rds_ib_teardown_mr(struct rds_ib_mr *); struct rds_ib_mr *rds_ib_alloc_fmr(struct rds_ib_device *, int); -int rds_ib_map_fmr(struct rds_ib_device *, struct rds_ib_mr *, - struct scatterlist *, unsigned int); struct rds_ib_mr *rds_ib_reuse_mr(struct rds_ib_mr_pool *); int rds_ib_flush_mr_pool(struct rds_ib_mr_pool *, int, struct rds_ib_mr **); struct rds_ib_mr *rds_ib_reg_fmr(struct rds_ib_device *, struct scatterlist *, diff --git a/net/rds/rds.h b/net/rds/rds.h index 39518ef7af4d..82d38ccf5e8b 100644 --- a/net/rds/rds.h +++ b/net/rds/rds.h @@ -147,7 +147,7 @@ struct rds_connection { /* Protocol version */ unsigned int c_version; - possible_net_t c_net; + struct net *c_net; struct list_head c_map_item; unsigned long c_map_queued; @@ -162,13 +162,13 @@ struct rds_connection { static inline struct net *rds_conn_net(struct rds_connection *conn) { - return read_pnet(&conn->c_net); + return conn->c_net; } static inline void rds_conn_net_set(struct rds_connection *conn, struct net *net) { - write_pnet(&conn->c_net, net); + conn->c_net = get_net(net); } #define RDS_FLAG_CONG_BITMAP 0x01 diff --git a/net/rds/tcp.c b/net/rds/tcp.c index a973d3b4dff0..225690076773 100644 --- a/net/rds/tcp.c +++ b/net/rds/tcp.c @@ -484,9 +484,10 @@ static void __net_exit rds_tcp_exit_net(struct net *net) * we do need to clean up the listen socket here. */ if (rtn->rds_tcp_listen_sock) { - rds_tcp_listen_stop(rtn->rds_tcp_listen_sock); + struct socket *lsock = rtn->rds_tcp_listen_sock; + rtn->rds_tcp_listen_sock = NULL; - flush_work(&rtn->rds_tcp_accept_w); + rds_tcp_listen_stop(lsock, &rtn->rds_tcp_accept_w); } } @@ -523,13 +524,13 @@ static void rds_tcp_kill_sock(struct net *net) struct rds_tcp_connection *tc, *_tc; LIST_HEAD(tmp_list); struct rds_tcp_net *rtn = net_generic(net, rds_tcp_netid); + struct socket *lsock = rtn->rds_tcp_listen_sock; - rds_tcp_listen_stop(rtn->rds_tcp_listen_sock); rtn->rds_tcp_listen_sock = NULL; - flush_work(&rtn->rds_tcp_accept_w); + rds_tcp_listen_stop(lsock, &rtn->rds_tcp_accept_w); spin_lock_irq(&rds_tcp_conn_lock); list_for_each_entry_safe(tc, _tc, &rds_tcp_conn_list, t_tcp_node) { - struct net *c_net = read_pnet(&tc->t_cpath->cp_conn->c_net); + struct net *c_net = tc->t_cpath->cp_conn->c_net; if (net != c_net || !tc->t_sock) continue; @@ -546,8 +547,12 @@ static void rds_tcp_kill_sock(struct net *net) void *rds_tcp_listen_sock_def_readable(struct net *net) { struct rds_tcp_net *rtn = net_generic(net, rds_tcp_netid); + struct socket *lsock = rtn->rds_tcp_listen_sock; + + if (!lsock) + return NULL; - return rtn->rds_tcp_listen_sock->sk->sk_user_data; + return lsock->sk->sk_user_data; } static int rds_tcp_dev_event(struct notifier_block *this, @@ -584,7 +589,7 @@ static void rds_tcp_sysctl_reset(struct net *net) spin_lock_irq(&rds_tcp_conn_lock); list_for_each_entry_safe(tc, _tc, &rds_tcp_conn_list, t_tcp_node) { - struct net *c_net = read_pnet(&tc->t_cpath->cp_conn->c_net); + struct net *c_net = tc->t_cpath->cp_conn->c_net; if (net != c_net || !tc->t_sock) continue; @@ -638,19 +643,19 @@ static int rds_tcp_init(void) goto out; } - ret = register_netdevice_notifier(&rds_tcp_dev_notifier); - if (ret) { - pr_warn("could not register rds_tcp_dev_notifier\n"); + ret = rds_tcp_recv_init(); + if (ret) goto out_slab; - } ret = register_pernet_subsys(&rds_tcp_net_ops); if (ret) - goto out_notifier; + goto out_recv; - ret = rds_tcp_recv_init(); - if (ret) + ret = register_netdevice_notifier(&rds_tcp_dev_notifier); + if (ret) { + pr_warn("could not register rds_tcp_dev_notifier\n"); goto out_pernet; + } rds_trans_register(&rds_tcp_transport); @@ -660,9 +665,8 @@ static int rds_tcp_init(void) out_pernet: unregister_pernet_subsys(&rds_tcp_net_ops); -out_notifier: - if (unregister_netdevice_notifier(&rds_tcp_dev_notifier)) - pr_warn("could not unregister rds_tcp_dev_notifier\n"); +out_recv: + rds_tcp_recv_exit(); out_slab: kmem_cache_destroy(rds_tcp_conn_slab); out: diff --git a/net/rds/tcp.h b/net/rds/tcp.h index 9a1cc8906576..56ea6620fcf9 100644 --- a/net/rds/tcp.h +++ b/net/rds/tcp.h @@ -66,7 +66,7 @@ void rds_tcp_state_change(struct sock *sk); /* tcp_listen.c */ struct socket *rds_tcp_listen_init(struct net *); -void rds_tcp_listen_stop(struct socket *); +void rds_tcp_listen_stop(struct socket *sock, struct work_struct *acceptor); void rds_tcp_listen_data_ready(struct sock *sk); int rds_tcp_accept_one(struct socket *sock); int rds_tcp_keepalive(struct socket *sock); diff --git a/net/rds/tcp_listen.c b/net/rds/tcp_listen.c index 67d0929c7d3d..507678853e6c 100644 --- a/net/rds/tcp_listen.c +++ b/net/rds/tcp_listen.c @@ -133,7 +133,7 @@ int rds_tcp_accept_one(struct socket *sock) new_sock->type = sock->type; new_sock->ops = sock->ops; - ret = sock->ops->accept(sock, new_sock, O_NONBLOCK); + ret = sock->ops->accept(sock, new_sock, O_NONBLOCK, true); if (ret < 0) goto out; @@ -223,6 +223,9 @@ void rds_tcp_listen_data_ready(struct sock *sk) * before it has been accepted and the accepter has set up their * data_ready.. we only want to queue listen work for our listening * socket + * + * (*ready)() may be null if we are racing with netns delete, and + * the listen socket is being torn down. */ if (sk->sk_state == TCP_LISTEN) rds_tcp_accept_work(sk); @@ -231,7 +234,8 @@ void rds_tcp_listen_data_ready(struct sock *sk) out: read_unlock_bh(&sk->sk_callback_lock); - ready(sk); + if (ready) + ready(sk); } struct socket *rds_tcp_listen_init(struct net *net) @@ -271,7 +275,7 @@ out: return NULL; } -void rds_tcp_listen_stop(struct socket *sock) +void rds_tcp_listen_stop(struct socket *sock, struct work_struct *acceptor) { struct sock *sk; @@ -292,5 +296,6 @@ void rds_tcp_listen_stop(struct socket *sock) /* wait for accepts to stop and close the socket */ flush_workqueue(rds_wq); + flush_work(acceptor); sock_release(sock); } diff --git a/net/rose/af_rose.c b/net/rose/af_rose.c index b8a1df2c9785..4a9729257023 100644 --- a/net/rose/af_rose.c +++ b/net/rose/af_rose.c @@ -871,7 +871,8 @@ out_release: return err; } -static int rose_accept(struct socket *sock, struct socket *newsock, int flags) +static int rose_accept(struct socket *sock, struct socket *newsock, int flags, + bool kern) { struct sk_buff *skb; struct sock *newsk; diff --git a/net/rxrpc/input.c b/net/rxrpc/input.c index 9f4cfa25af7c..18b2ad8be8e2 100644 --- a/net/rxrpc/input.c +++ b/net/rxrpc/input.c @@ -420,6 +420,7 @@ static void rxrpc_input_data(struct rxrpc_call *call, struct sk_buff *skb, u16 skew) { struct rxrpc_skb_priv *sp = rxrpc_skb(skb); + enum rxrpc_call_state state; unsigned int offset = sizeof(struct rxrpc_wire_header); unsigned int ix; rxrpc_serial_t serial = sp->hdr.serial, ack_serial = 0; @@ -434,14 +435,15 @@ static void rxrpc_input_data(struct rxrpc_call *call, struct sk_buff *skb, _proto("Rx DATA %%%u { #%u f=%02x }", sp->hdr.serial, seq, sp->hdr.flags); - if (call->state >= RXRPC_CALL_COMPLETE) + state = READ_ONCE(call->state); + if (state >= RXRPC_CALL_COMPLETE) return; /* Received data implicitly ACKs all of the request packets we sent * when we're acting as a client. */ - if ((call->state == RXRPC_CALL_CLIENT_SEND_REQUEST || - call->state == RXRPC_CALL_CLIENT_AWAIT_REPLY) && + if ((state == RXRPC_CALL_CLIENT_SEND_REQUEST || + state == RXRPC_CALL_CLIENT_AWAIT_REPLY) && !rxrpc_receiving_reply(call)) return; @@ -650,6 +652,7 @@ static void rxrpc_input_ackinfo(struct rxrpc_call *call, struct sk_buff *skb, struct rxrpc_skb_priv *sp = rxrpc_skb(skb); struct rxrpc_peer *peer; unsigned int mtu; + bool wake = false; u32 rwind = ntohl(ackinfo->rwind); _proto("Rx ACK %%%u Info { rx=%u max=%u rwin=%u jm=%u }", @@ -657,9 +660,14 @@ static void rxrpc_input_ackinfo(struct rxrpc_call *call, struct sk_buff *skb, ntohl(ackinfo->rxMTU), ntohl(ackinfo->maxMTU), rwind, ntohl(ackinfo->jumbo_max)); - if (rwind > RXRPC_RXTX_BUFF_SIZE - 1) - rwind = RXRPC_RXTX_BUFF_SIZE - 1; - call->tx_winsize = rwind; + if (call->tx_winsize != rwind) { + if (rwind > RXRPC_RXTX_BUFF_SIZE - 1) + rwind = RXRPC_RXTX_BUFF_SIZE - 1; + if (rwind > call->tx_winsize) + wake = true; + call->tx_winsize = rwind; + } + if (call->cong_ssthresh > rwind) call->cong_ssthresh = rwind; @@ -673,6 +681,9 @@ static void rxrpc_input_ackinfo(struct rxrpc_call *call, struct sk_buff *skb, spin_unlock_bh(&peer->lock); _net("Net MTU %u (maxdata %u)", peer->mtu, peer->maxdata); } + + if (wake) + wake_up(&call->waitq); } /* @@ -799,7 +810,7 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb, return rxrpc_proto_abort("AK0", call, 0); /* Ignore ACKs unless we are or have just been transmitting. */ - switch (call->state) { + switch (READ_ONCE(call->state)) { case RXRPC_CALL_CLIENT_SEND_REQUEST: case RXRPC_CALL_CLIENT_AWAIT_REPLY: case RXRPC_CALL_SERVER_SEND_REPLY: @@ -940,7 +951,7 @@ static void rxrpc_input_call_packet(struct rxrpc_call *call, static void rxrpc_input_implicit_end_call(struct rxrpc_connection *conn, struct rxrpc_call *call) { - switch (call->state) { + switch (READ_ONCE(call->state)) { case RXRPC_CALL_SERVER_AWAIT_ACK: rxrpc_call_completed(call); break; diff --git a/net/rxrpc/recvmsg.c b/net/rxrpc/recvmsg.c index 6491ca46a03f..3e2f1a8e9c5b 100644 --- a/net/rxrpc/recvmsg.c +++ b/net/rxrpc/recvmsg.c @@ -527,7 +527,7 @@ try_again: msg->msg_namelen = len; } - switch (call->state) { + switch (READ_ONCE(call->state)) { case RXRPC_CALL_SERVER_ACCEPTING: ret = rxrpc_recvmsg_new_call(rx, call, msg, flags); break; @@ -640,7 +640,7 @@ int rxrpc_kernel_recv_data(struct socket *sock, struct rxrpc_call *call, mutex_lock(&call->user_mutex); - switch (call->state) { + switch (READ_ONCE(call->state)) { case RXRPC_CALL_CLIENT_RECV_REPLY: case RXRPC_CALL_SERVER_RECV_REQUEST: case RXRPC_CALL_SERVER_ACK_REQUEST: diff --git a/net/rxrpc/sendmsg.c b/net/rxrpc/sendmsg.c index bc2d3dcff9de..97ab214ca411 100644 --- a/net/rxrpc/sendmsg.c +++ b/net/rxrpc/sendmsg.c @@ -488,6 +488,7 @@ rxrpc_new_client_call_for_sendmsg(struct rxrpc_sock *rx, struct msghdr *msg, int rxrpc_do_sendmsg(struct rxrpc_sock *rx, struct msghdr *msg, size_t len) __releases(&rx->sk.sk_lock.slock) { + enum rxrpc_call_state state; enum rxrpc_command cmd; struct rxrpc_call *call; unsigned long user_call_ID = 0; @@ -526,13 +527,17 @@ int rxrpc_do_sendmsg(struct rxrpc_sock *rx, struct msghdr *msg, size_t len) return PTR_ERR(call); /* ... and we have the call lock. */ } else { - ret = -EBUSY; - if (call->state == RXRPC_CALL_UNINITIALISED || - call->state == RXRPC_CALL_CLIENT_AWAIT_CONN || - call->state == RXRPC_CALL_SERVER_PREALLOC || - call->state == RXRPC_CALL_SERVER_SECURING || - call->state == RXRPC_CALL_SERVER_ACCEPTING) + switch (READ_ONCE(call->state)) { + case RXRPC_CALL_UNINITIALISED: + case RXRPC_CALL_CLIENT_AWAIT_CONN: + case RXRPC_CALL_SERVER_PREALLOC: + case RXRPC_CALL_SERVER_SECURING: + case RXRPC_CALL_SERVER_ACCEPTING: + ret = -EBUSY; goto error_release_sock; + default: + break; + } ret = mutex_lock_interruptible(&call->user_mutex); release_sock(&rx->sk); @@ -542,10 +547,11 @@ int rxrpc_do_sendmsg(struct rxrpc_sock *rx, struct msghdr *msg, size_t len) } } + state = READ_ONCE(call->state); _debug("CALL %d USR %lx ST %d on CONN %p", - call->debug_id, call->user_call_ID, call->state, call->conn); + call->debug_id, call->user_call_ID, state, call->conn); - if (call->state >= RXRPC_CALL_COMPLETE) { + if (state >= RXRPC_CALL_COMPLETE) { /* it's too late for this call */ ret = -ESHUTDOWN; } else if (cmd == RXRPC_CMD_SEND_ABORT) { @@ -555,12 +561,12 @@ int rxrpc_do_sendmsg(struct rxrpc_sock *rx, struct msghdr *msg, size_t len) } else if (cmd != RXRPC_CMD_SEND_DATA) { ret = -EINVAL; } else if (rxrpc_is_client_call(call) && - call->state != RXRPC_CALL_CLIENT_SEND_REQUEST) { + state != RXRPC_CALL_CLIENT_SEND_REQUEST) { /* request phase complete for this client call */ ret = -EPROTO; } else if (rxrpc_is_service_call(call) && - call->state != RXRPC_CALL_SERVER_ACK_REQUEST && - call->state != RXRPC_CALL_SERVER_SEND_REPLY) { + state != RXRPC_CALL_SERVER_ACK_REQUEST && + state != RXRPC_CALL_SERVER_SEND_REPLY) { /* Reply phase not begun or not complete for service call. */ ret = -EPROTO; } else { @@ -605,14 +611,21 @@ int rxrpc_kernel_send_data(struct socket *sock, struct rxrpc_call *call, _debug("CALL %d USR %lx ST %d on CONN %p", call->debug_id, call->user_call_ID, call->state, call->conn); - if (call->state >= RXRPC_CALL_COMPLETE) { - ret = -ESHUTDOWN; /* it's too late for this call */ - } else if (call->state != RXRPC_CALL_CLIENT_SEND_REQUEST && - call->state != RXRPC_CALL_SERVER_ACK_REQUEST && - call->state != RXRPC_CALL_SERVER_SEND_REPLY) { - ret = -EPROTO; /* request phase complete for this client call */ - } else { + switch (READ_ONCE(call->state)) { + case RXRPC_CALL_CLIENT_SEND_REQUEST: + case RXRPC_CALL_SERVER_ACK_REQUEST: + case RXRPC_CALL_SERVER_SEND_REPLY: ret = rxrpc_send_data(rxrpc_sk(sock->sk), call, msg, len); + break; + case RXRPC_CALL_COMPLETE: + read_lock_bh(&call->state_lock); + ret = -call->error; + read_unlock_bh(&call->state_lock); + break; + default: + /* Request phase complete for this client call */ + ret = -EPROTO; + break; } mutex_unlock(&call->user_mutex); diff --git a/net/sched/act_connmark.c b/net/sched/act_connmark.c index ab8062909962..f9bb43c25697 100644 --- a/net/sched/act_connmark.c +++ b/net/sched/act_connmark.c @@ -113,6 +113,9 @@ static int tcf_connmark_init(struct net *net, struct nlattr *nla, if (ret < 0) return ret; + if (!tb[TCA_CONNMARK_PARMS]) + return -EINVAL; + parm = nla_data(tb[TCA_CONNMARK_PARMS]); if (!tcf_hash_check(tn, parm->index, a, bind)) { diff --git a/net/sched/act_ife.c b/net/sched/act_ife.c index 71e7ff22f7c9..c75ea5c9102c 100644 --- a/net/sched/act_ife.c +++ b/net/sched/act_ife.c @@ -603,8 +603,8 @@ nla_put_failure: return -1; } -int find_decode_metaid(struct sk_buff *skb, struct tcf_ife_info *ife, - u16 metaid, u16 mlen, void *mdata) +static int find_decode_metaid(struct sk_buff *skb, struct tcf_ife_info *ife, + u16 metaid, u16 mlen, void *mdata) { struct tcf_meta_info *e; diff --git a/net/sched/act_skbmod.c b/net/sched/act_skbmod.c index 3b7074e23024..c736627f8f4a 100644 --- a/net/sched/act_skbmod.c +++ b/net/sched/act_skbmod.c @@ -228,7 +228,6 @@ static int tcf_skbmod_dump(struct sk_buff *skb, struct tc_action *a, return skb->len; nla_put_failure: - rcu_read_unlock(); nlmsg_trim(skb, b); return -1; } diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index bcf49cd22786..62567bfe52c7 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -274,7 +274,7 @@ static struct Qdisc *qdisc_match_from_root(struct Qdisc *root, u32 handle) return NULL; } -void qdisc_hash_add(struct Qdisc *q) +void qdisc_hash_add(struct Qdisc *q, bool invisible) { if ((q->parent != TC_H_ROOT) && !(q->flags & TCQ_F_INGRESS)) { struct Qdisc *root = qdisc_dev(q)->qdisc; @@ -282,6 +282,8 @@ void qdisc_hash_add(struct Qdisc *q) WARN_ON_ONCE(root == &noop_qdisc); ASSERT_RTNL(); hash_add_rcu(qdisc_dev(q)->qdisc_hash, &q->hash, q->handle); + if (invisible) + q->flags |= TCQ_F_INVISIBLE; } } EXPORT_SYMBOL(qdisc_hash_add); @@ -1003,7 +1005,7 @@ static struct Qdisc *qdisc_create(struct net_device *dev, goto err_out4; } - qdisc_hash_add(sch); + qdisc_hash_add(sch, false); return sch; } @@ -1401,9 +1403,14 @@ nla_put_failure: return -1; } -static bool tc_qdisc_dump_ignore(struct Qdisc *q) +static bool tc_qdisc_dump_ignore(struct Qdisc *q, bool dump_invisible) { - return (q->flags & TCQ_F_BUILTIN) ? true : false; + if (q->flags & TCQ_F_BUILTIN) + return true; + if ((q->flags & TCQ_F_INVISIBLE) && !dump_invisible) + return true; + + return false; } static int qdisc_notify(struct net *net, struct sk_buff *oskb, @@ -1417,12 +1424,12 @@ static int qdisc_notify(struct net *net, struct sk_buff *oskb, if (!skb) return -ENOBUFS; - if (old && !tc_qdisc_dump_ignore(old)) { + if (old && !tc_qdisc_dump_ignore(old, false)) { if (tc_fill_qdisc(skb, old, clid, portid, n->nlmsg_seq, 0, RTM_DELQDISC) < 0) goto err_out; } - if (new && !tc_qdisc_dump_ignore(new)) { + if (new && !tc_qdisc_dump_ignore(new, false)) { if (tc_fill_qdisc(skb, new, clid, portid, n->nlmsg_seq, old ? NLM_F_REPLACE : 0, RTM_NEWQDISC) < 0) goto err_out; @@ -1439,7 +1446,8 @@ err_out: static int tc_dump_qdisc_root(struct Qdisc *root, struct sk_buff *skb, struct netlink_callback *cb, - int *q_idx_p, int s_q_idx, bool recur) + int *q_idx_p, int s_q_idx, bool recur, + bool dump_invisible) { int ret = 0, q_idx = *q_idx_p; struct Qdisc *q; @@ -1452,7 +1460,7 @@ static int tc_dump_qdisc_root(struct Qdisc *root, struct sk_buff *skb, if (q_idx < s_q_idx) { q_idx++; } else { - if (!tc_qdisc_dump_ignore(q) && + if (!tc_qdisc_dump_ignore(q, dump_invisible) && tc_fill_qdisc(skb, q, q->parent, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NLM_F_MULTI, RTM_NEWQDISC) <= 0) @@ -1474,7 +1482,7 @@ static int tc_dump_qdisc_root(struct Qdisc *root, struct sk_buff *skb, q_idx++; continue; } - if (!tc_qdisc_dump_ignore(q) && + if (!tc_qdisc_dump_ignore(q, dump_invisible) && tc_fill_qdisc(skb, q, q->parent, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NLM_F_MULTI, RTM_NEWQDISC) <= 0) @@ -1496,12 +1504,21 @@ static int tc_dump_qdisc(struct sk_buff *skb, struct netlink_callback *cb) int idx, q_idx; int s_idx, s_q_idx; struct net_device *dev; + const struct nlmsghdr *nlh = cb->nlh; + struct tcmsg *tcm = nlmsg_data(nlh); + struct nlattr *tca[TCA_MAX + 1]; + int err; s_idx = cb->args[0]; s_q_idx = q_idx = cb->args[1]; idx = 0; ASSERT_RTNL(); + + err = nlmsg_parse(nlh, sizeof(*tcm), tca, TCA_MAX, NULL); + if (err < 0) + return err; + for_each_netdev(net, dev) { struct netdev_queue *dev_queue; @@ -1512,13 +1529,14 @@ static int tc_dump_qdisc(struct sk_buff *skb, struct netlink_callback *cb) q_idx = 0; if (tc_dump_qdisc_root(dev->qdisc, skb, cb, &q_idx, s_q_idx, - true) < 0) + true, tca[TCA_DUMP_INVISIBLE]) < 0) goto done; dev_queue = dev_ingress_queue(dev); if (dev_queue && tc_dump_qdisc_root(dev_queue->qdisc_sleeping, skb, cb, - &q_idx, s_q_idx, false) < 0) + &q_idx, s_q_idx, false, + tca[TCA_DUMP_INVISIBLE]) < 0) goto done; cont: @@ -1762,7 +1780,7 @@ static int tc_dump_tclass_qdisc(struct Qdisc *q, struct sk_buff *skb, { struct qdisc_dump_args arg; - if (tc_qdisc_dump_ignore(q) || + if (tc_qdisc_dump_ignore(q, false) || *t_p < s_t || !q->ops->cl_ops || (tcm->tcm_parent && TC_H_MAJ(tcm->tcm_parent) != q->handle)) { diff --git a/net/sched/sch_cbq.c b/net/sched/sch_cbq.c index d6ca18dc04c3..cf93e5ff3d63 100644 --- a/net/sched/sch_cbq.c +++ b/net/sched/sch_cbq.c @@ -1161,6 +1161,8 @@ static int cbq_init(struct Qdisc *sch, struct nlattr *opt) sch->handle); if (!q->link.q) q->link.q = &noop_qdisc; + else + qdisc_hash_add(q->link.q, true); q->link.priority = TC_CBQ_MAXPRIO - 1; q->link.priority2 = TC_CBQ_MAXPRIO - 1; @@ -1600,6 +1602,9 @@ cbq_change_class(struct Qdisc *sch, u32 classid, u32 parentid, struct nlattr **t cl->q = qdisc_create_dflt(sch->dev_queue, &pfifo_qdisc_ops, classid); if (!cl->q) cl->q = &noop_qdisc; + else + qdisc_hash_add(cl->q, true); + cl->common.classid = classid; cl->tparent = parent; cl->qdisc = sch; diff --git a/net/sched/sch_drr.c b/net/sched/sch_drr.c index bb4cbdf75004..9fe67e257dfa 100644 --- a/net/sched/sch_drr.c +++ b/net/sched/sch_drr.c @@ -117,6 +117,8 @@ static int drr_change_class(struct Qdisc *sch, u32 classid, u32 parentid, &pfifo_qdisc_ops, classid); if (cl->qdisc == NULL) cl->qdisc = &noop_qdisc; + else + qdisc_hash_add(cl->qdisc, true); if (tca[TCA_RATE]) { err = gen_replace_estimator(&cl->bstats, NULL, &cl->rate_est, diff --git a/net/sched/sch_dsmark.c b/net/sched/sch_dsmark.c index 802ac7c2e5e8..1b98cb2160ff 100644 --- a/net/sched/sch_dsmark.c +++ b/net/sched/sch_dsmark.c @@ -368,6 +368,8 @@ static int dsmark_init(struct Qdisc *sch, struct nlattr *opt) p->q = qdisc_create_dflt(sch->dev_queue, &pfifo_qdisc_ops, sch->handle); if (p->q == NULL) p->q = &noop_qdisc; + else + qdisc_hash_add(p->q, true); pr_debug("%s: qdisc %p\n", __func__, p->q); diff --git a/net/sched/sch_fq_codel.c b/net/sched/sch_fq_codel.c index 9f3a884d1590..097bbe9857a5 100644 --- a/net/sched/sch_fq_codel.c +++ b/net/sched/sch_fq_codel.c @@ -288,7 +288,6 @@ static struct sk_buff *fq_codel_dequeue(struct Qdisc *sch) struct fq_codel_flow *flow; struct list_head *head; u32 prev_drop_count, prev_ecn_mark; - unsigned int prev_backlog; begin: head = &q->new_flows; @@ -307,7 +306,6 @@ begin: prev_drop_count = q->cstats.drop_count; prev_ecn_mark = q->cstats.ecn_mark; - prev_backlog = sch->qstats.backlog; skb = codel_dequeue(sch, &sch->qstats.backlog, &q->cparams, &flow->cvars, &q->cstats, qdisc_pkt_len, diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c index b052b27a984e..3e64d23e098c 100644 --- a/net/sched/sch_generic.c +++ b/net/sched/sch_generic.c @@ -795,7 +795,7 @@ static void attach_default_qdiscs(struct net_device *dev) } #ifdef CONFIG_NET_SCHED if (dev->qdisc) - qdisc_hash_add(dev->qdisc); + qdisc_hash_add(dev->qdisc, false); #endif } diff --git a/net/sched/sch_hfsc.c b/net/sched/sch_hfsc.c index 3ffaa6fb0990..0198c6cdda49 100644 --- a/net/sched/sch_hfsc.c +++ b/net/sched/sch_hfsc.c @@ -1066,6 +1066,8 @@ hfsc_change_class(struct Qdisc *sch, u32 classid, u32 parentid, &pfifo_qdisc_ops, classid); if (cl->qdisc == NULL) cl->qdisc = &noop_qdisc; + else + qdisc_hash_add(cl->qdisc, true); INIT_LIST_HEAD(&cl->children); cl->vt_tree = RB_ROOT; cl->cf_tree = RB_ROOT; @@ -1425,6 +1427,8 @@ hfsc_init_qdisc(struct Qdisc *sch, struct nlattr *opt) sch->handle); if (q->root.qdisc == NULL) q->root.qdisc = &noop_qdisc; + else + qdisc_hash_add(q->root.qdisc, true); INIT_LIST_HEAD(&q->root.children); q->root.vt_tree = RB_ROOT; q->root.cf_tree = RB_ROOT; diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c index 4cd5fb134bc9..95867033542e 100644 --- a/net/sched/sch_htb.c +++ b/net/sched/sch_htb.c @@ -1460,6 +1460,8 @@ static int htb_change_class(struct Qdisc *sch, u32 classid, qdisc_class_hash_insert(&q->clhash, &cl->common); if (parent) parent->children++; + if (cl->un.leaf.q != &noop_qdisc) + qdisc_hash_add(cl->un.leaf.q, true); } else { if (tca[TCA_RATE]) { err = gen_replace_estimator(&cl->bstats, NULL, diff --git a/net/sched/sch_mq.c b/net/sched/sch_mq.c index 20b7f1646f69..cadfdd4f1e52 100644 --- a/net/sched/sch_mq.c +++ b/net/sched/sch_mq.c @@ -84,7 +84,7 @@ static void mq_attach(struct Qdisc *sch) qdisc_destroy(old); #ifdef CONFIG_NET_SCHED if (ntx < dev->real_num_tx_queues) - qdisc_hash_add(qdisc); + qdisc_hash_add(qdisc, false); #endif } diff --git a/net/sched/sch_mqprio.c b/net/sched/sch_mqprio.c index 922683418e53..0a4cf27ea54b 100644 --- a/net/sched/sch_mqprio.c +++ b/net/sched/sch_mqprio.c @@ -21,14 +21,13 @@ struct mqprio_sched { struct Qdisc **qdiscs; - int hw_owned; + int hw_offload; }; static void mqprio_destroy(struct Qdisc *sch) { struct net_device *dev = qdisc_dev(sch); struct mqprio_sched *priv = qdisc_priv(sch); - struct tc_to_netdev tc = {.type = TC_SETUP_MQPRIO}; unsigned int ntx; if (priv->qdiscs) { @@ -39,10 +38,15 @@ static void mqprio_destroy(struct Qdisc *sch) kfree(priv->qdiscs); } - if (priv->hw_owned && dev->netdev_ops->ndo_setup_tc) + if (priv->hw_offload && dev->netdev_ops->ndo_setup_tc) { + struct tc_mqprio_qopt offload = { 0 }; + struct tc_to_netdev tc = { .type = TC_SETUP_MQPRIO, + { .mqprio = &offload } }; + dev->netdev_ops->ndo_setup_tc(dev, sch->handle, 0, &tc); - else + } else { netdev_set_num_tc(dev, 0); + } } static int mqprio_parse_opt(struct net_device *dev, struct tc_mqprio_qopt *qopt) @@ -59,15 +63,20 @@ static int mqprio_parse_opt(struct net_device *dev, struct tc_mqprio_qopt *qopt) return -EINVAL; } - /* net_device does not support requested operation */ - if (qopt->hw && !dev->netdev_ops->ndo_setup_tc) - return -EINVAL; + /* Limit qopt->hw to maximum supported offload value. Drivers have + * the option of overriding this later if they don't support the a + * given offload type. + */ + if (qopt->hw > TC_MQPRIO_HW_OFFLOAD_MAX) + qopt->hw = TC_MQPRIO_HW_OFFLOAD_MAX; - /* if hw owned qcount and qoffset are taken from LLD so - * no reason to verify them here + /* If hardware offload is requested we will leave it to the device + * to either populate the queue counts itself or to validate the + * provided queue counts. If ndo_setup_tc is not present then + * hardware doesn't support offload and we should return an error. */ if (qopt->hw) - return 0; + return dev->netdev_ops->ndo_setup_tc ? 0 : -EINVAL; for (i = 0; i < qopt->num_tc; i++) { unsigned int last = qopt->offset[i] + qopt->count[i]; @@ -139,13 +148,15 @@ static int mqprio_init(struct Qdisc *sch, struct nlattr *opt) * supplied and verified mapping */ if (qopt->hw) { - struct tc_to_netdev tc = {.type = TC_SETUP_MQPRIO, - { .tc = qopt->num_tc }}; + struct tc_mqprio_qopt offload = *qopt; + struct tc_to_netdev tc = { .type = TC_SETUP_MQPRIO, + { .mqprio = &offload } }; - priv->hw_owned = 1; err = dev->netdev_ops->ndo_setup_tc(dev, sch->handle, 0, &tc); if (err) return err; + + priv->hw_offload = offload.hw; } else { netdev_set_num_tc(dev, qopt->num_tc); for (i = 0; i < qopt->num_tc; i++) @@ -175,7 +186,7 @@ static void mqprio_attach(struct Qdisc *sch) if (old) qdisc_destroy(old); if (ntx < dev->real_num_tx_queues) - qdisc_hash_add(qdisc); + qdisc_hash_add(qdisc, false); } kfree(priv->qdiscs); priv->qdiscs = NULL; @@ -243,7 +254,7 @@ static int mqprio_dump(struct Qdisc *sch, struct sk_buff *skb) opt.num_tc = netdev_get_num_tc(dev); memcpy(opt.prio_tc_map, dev->prio_tc_map, sizeof(opt.prio_tc_map)); - opt.hw = priv->hw_owned; + opt.hw = priv->hw_offload; for (i = 0; i < netdev_get_num_tc(dev); i++) { opt.count[i] = dev->tc_to_txq[i].count; diff --git a/net/sched/sch_multiq.c b/net/sched/sch_multiq.c index e7839a0d0eaa..43a3a10b3c81 100644 --- a/net/sched/sch_multiq.c +++ b/net/sched/sch_multiq.c @@ -217,6 +217,8 @@ static int multiq_tune(struct Qdisc *sch, struct nlattr *opt) sch_tree_lock(sch); old = q->queues[i]; q->queues[i] = child; + if (child != &noop_qdisc) + qdisc_hash_add(child, true); if (old != &noop_qdisc) { qdisc_tree_reduce_backlog(old, diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c index c8bb62a1e744..94b4928ad413 100644 --- a/net/sched/sch_netem.c +++ b/net/sched/sch_netem.c @@ -462,7 +462,7 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch, /* If a delay is expected, orphan the skb. (orphaning usually takes * place at TX completion time, so _before_ the link transit delay) */ - if (q->latency || q->jitter) + if (q->latency || q->jitter || q->rate) skb_orphan_partial(skb); /* @@ -530,21 +530,31 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch, now = psched_get_time(); if (q->rate) { - struct sk_buff *last; + struct netem_skb_cb *last = NULL; + + if (sch->q.tail) + last = netem_skb_cb(sch->q.tail); + if (q->t_root.rb_node) { + struct sk_buff *t_skb; + struct netem_skb_cb *t_last; + + t_skb = netem_rb_to_skb(rb_last(&q->t_root)); + t_last = netem_skb_cb(t_skb); + if (!last || + t_last->time_to_send > last->time_to_send) { + last = t_last; + } + } - if (sch->q.qlen) - last = sch->q.tail; - else - last = netem_rb_to_skb(rb_last(&q->t_root)); if (last) { /* * Last packet in queue is reference point (now), * calculate this time bonus and subtract * from delay. */ - delay -= netem_skb_cb(last)->time_to_send - now; + delay -= last->time_to_send - now; delay = max_t(psched_tdiff_t, 0, delay); - now = netem_skb_cb(last)->time_to_send; + now = last->time_to_send; } delay += packet_len_2_sched_time(qdisc_pkt_len(skb), q); diff --git a/net/sched/sch_prio.c b/net/sched/sch_prio.c index d4d7db267b6e..92c2e6d448d7 100644 --- a/net/sched/sch_prio.c +++ b/net/sched/sch_prio.c @@ -192,8 +192,11 @@ static int prio_tune(struct Qdisc *sch, struct nlattr *opt) qdisc_destroy(child); } - for (i = oldbands; i < q->bands; i++) + for (i = oldbands; i < q->bands; i++) { q->queues[i] = queues[i]; + if (q->queues[i] != &noop_qdisc) + qdisc_hash_add(q->queues[i], true); + } sch_tree_unlock(sch); return 0; diff --git a/net/sched/sch_qfq.c b/net/sched/sch_qfq.c index f9e712ce2d15..6c85f3e9239b 100644 --- a/net/sched/sch_qfq.c +++ b/net/sched/sch_qfq.c @@ -494,6 +494,8 @@ static int qfq_change_class(struct Qdisc *sch, u32 classid, u32 parentid, goto destroy_class; } + if (cl->qdisc != &noop_qdisc) + qdisc_hash_add(cl->qdisc, true); sch_tree_lock(sch); qdisc_class_hash_insert(&q->clhash, &cl->common); sch_tree_unlock(sch); diff --git a/net/sched/sch_red.c b/net/sched/sch_red.c index 249b2a18acbd..799ea6dd69b2 100644 --- a/net/sched/sch_red.c +++ b/net/sched/sch_red.c @@ -191,6 +191,8 @@ static int red_change(struct Qdisc *sch, struct nlattr *opt) return PTR_ERR(child); } + if (child != &noop_qdisc) + qdisc_hash_add(child, true); sch_tree_lock(sch); q->flags = ctl->flags; q->limit = ctl->limit; diff --git a/net/sched/sch_sfb.c b/net/sched/sch_sfb.c index fe6963d21519..ae862f172c94 100644 --- a/net/sched/sch_sfb.c +++ b/net/sched/sch_sfb.c @@ -513,6 +513,8 @@ static int sfb_change(struct Qdisc *sch, struct nlattr *opt) if (IS_ERR(child)) return PTR_ERR(child); + if (child != &noop_qdisc) + qdisc_hash_add(child, true); sch_tree_lock(sch); qdisc_tree_reduce_backlog(q->qdisc, q->qdisc->q.qlen, diff --git a/net/sched/sch_tbf.c b/net/sched/sch_tbf.c index 303355c449ab..9850126129a3 100644 --- a/net/sched/sch_tbf.c +++ b/net/sched/sch_tbf.c @@ -396,6 +396,8 @@ static int tbf_change(struct Qdisc *sch, struct nlattr *opt) q->qdisc->qstats.backlog); qdisc_destroy(q->qdisc); q->qdisc = child; + if (child != &noop_qdisc) + qdisc_hash_add(child, true); } q->limit = qopt->limit; if (tb[TCA_TBF_PBURST]) diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c index 063baac5b9fe..961ee59f696a 100644 --- a/net/sctp/ipv6.c +++ b/net/sctp/ipv6.c @@ -640,14 +640,15 @@ static sctp_scope_t sctp_v6_scope(union sctp_addr *addr) /* Create and initialize a new sk for the socket to be returned by accept(). */ static struct sock *sctp_v6_create_accept_sk(struct sock *sk, - struct sctp_association *asoc) + struct sctp_association *asoc, + bool kern) { struct sock *newsk; struct ipv6_pinfo *newnp, *np = inet6_sk(sk); struct sctp6_sock *newsctp6sk; struct ipv6_txoptions *opt; - newsk = sk_alloc(sock_net(sk), PF_INET6, GFP_KERNEL, sk->sk_prot, 0); + newsk = sk_alloc(sock_net(sk), PF_INET6, GFP_KERNEL, sk->sk_prot, kern); if (!newsk) goto out; diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c index 1b6d4574d2b0..989a900383b5 100644 --- a/net/sctp/protocol.c +++ b/net/sctp/protocol.c @@ -575,10 +575,11 @@ static int sctp_v4_is_ce(const struct sk_buff *skb) /* Create and initialize a new sk for the socket returned by accept(). */ static struct sock *sctp_v4_create_accept_sk(struct sock *sk, - struct sctp_association *asoc) + struct sctp_association *asoc, + bool kern) { struct sock *newsk = sk_alloc(sock_net(sk), PF_INET, GFP_KERNEL, - sk->sk_prot, 0); + sk->sk_prot, kern); struct inet_sock *newinet; if (!newsk) diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c index e03bb1aab4d0..ab1374fa5ab0 100644 --- a/net/sctp/sm_statefuns.c +++ b/net/sctp/sm_statefuns.c @@ -3872,9 +3872,18 @@ sctp_disposition_t sctp_sf_do_reconf(struct net *net, else if (param.p->type == SCTP_PARAM_RESET_IN_REQUEST) reply = sctp_process_strreset_inreq( (struct sctp_association *)asoc, param, &ev); - /* More handles for other types will be added here, by now it - * just ignores other types. - */ + else if (param.p->type == SCTP_PARAM_RESET_TSN_REQUEST) + reply = sctp_process_strreset_tsnreq( + (struct sctp_association *)asoc, param, &ev); + else if (param.p->type == SCTP_PARAM_RESET_ADD_OUT_STREAMS) + reply = sctp_process_strreset_addstrm_out( + (struct sctp_association *)asoc, param, &ev); + else if (param.p->type == SCTP_PARAM_RESET_ADD_IN_STREAMS) + reply = sctp_process_strreset_addstrm_in( + (struct sctp_association *)asoc, param, &ev); + else if (param.p->type == SCTP_PARAM_RESET_RESPONSE) + reply = sctp_process_strreset_resp( + (struct sctp_association *)asoc, param, &ev); if (ev) sctp_add_cmd_sf(commands, SCTP_CMD_EVENT_ULP, diff --git a/net/sctp/socket.c b/net/sctp/socket.c index 6f0a9be50f50..72cc3ecf6516 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -3758,6 +3758,39 @@ out: return retval; } +static int sctp_setsockopt_reconfig_supported(struct sock *sk, + char __user *optval, + unsigned int optlen) +{ + struct sctp_assoc_value params; + struct sctp_association *asoc; + int retval = -EINVAL; + + if (optlen != sizeof(params)) + goto out; + + if (copy_from_user(¶ms, optval, optlen)) { + retval = -EFAULT; + goto out; + } + + asoc = sctp_id2assoc(sk, params.assoc_id); + if (asoc) { + asoc->reconf_enable = !!params.assoc_value; + } else if (!params.assoc_id) { + struct sctp_sock *sp = sctp_sk(sk); + + sp->ep->reconf_enable = !!params.assoc_value; + } else { + goto out; + } + + retval = 0; + +out: + return retval; +} + static int sctp_setsockopt_enable_strreset(struct sock *sk, char __user *optval, unsigned int optlen) @@ -4038,6 +4071,9 @@ static int sctp_setsockopt(struct sock *sk, int level, int optname, case SCTP_DEFAULT_PRINFO: retval = sctp_setsockopt_default_prinfo(sk, optval, optlen); break; + case SCTP_RECONFIG_SUPPORTED: + retval = sctp_setsockopt_reconfig_supported(sk, optval, optlen); + break; case SCTP_ENABLE_STREAM_RESET: retval = sctp_setsockopt_enable_strreset(sk, optval, optlen); break; @@ -4116,7 +4152,7 @@ static int sctp_disconnect(struct sock *sk, int flags) * descriptor will be returned from accept() to represent the newly * formed association. */ -static struct sock *sctp_accept(struct sock *sk, int flags, int *err) +static struct sock *sctp_accept(struct sock *sk, int flags, int *err, bool kern) { struct sctp_sock *sp; struct sctp_endpoint *ep; @@ -4151,7 +4187,7 @@ static struct sock *sctp_accept(struct sock *sk, int flags, int *err) */ asoc = list_entry(ep->asocs.next, struct sctp_association, asocs); - newsk = sp->pf->create_accept_sk(sk, asoc); + newsk = sp->pf->create_accept_sk(sk, asoc, kern); if (!newsk) { error = -ENOMEM; goto out; @@ -6540,6 +6576,47 @@ out: return retval; } +static int sctp_getsockopt_reconfig_supported(struct sock *sk, int len, + char __user *optval, + int __user *optlen) +{ + struct sctp_assoc_value params; + struct sctp_association *asoc; + int retval = -EFAULT; + + if (len < sizeof(params)) { + retval = -EINVAL; + goto out; + } + + len = sizeof(params); + if (copy_from_user(¶ms, optval, len)) + goto out; + + asoc = sctp_id2assoc(sk, params.assoc_id); + if (asoc) { + params.assoc_value = asoc->reconf_enable; + } else if (!params.assoc_id) { + struct sctp_sock *sp = sctp_sk(sk); + + params.assoc_value = sp->ep->reconf_enable; + } else { + retval = -EINVAL; + goto out; + } + + if (put_user(len, optlen)) + goto out; + + if (copy_to_user(optval, ¶ms, len)) + goto out; + + retval = 0; + +out: + return retval; +} + static int sctp_getsockopt_enable_strreset(struct sock *sk, int len, char __user *optval, int __user *optlen) @@ -6748,6 +6825,10 @@ static int sctp_getsockopt(struct sock *sk, int level, int optname, retval = sctp_getsockopt_pr_assocstatus(sk, len, optval, optlen); break; + case SCTP_RECONFIG_SUPPORTED: + retval = sctp_getsockopt_reconfig_supported(sk, len, optval, + optlen); + break; case SCTP_ENABLE_STREAM_RESET: retval = sctp_getsockopt_enable_strreset(sk, len, optval, optlen); diff --git a/net/sctp/stream.c b/net/sctp/stream.c index 1c6cc04fa3a4..961d0a1e99d1 100644 --- a/net/sctp/stream.c +++ b/net/sctp/stream.c @@ -267,18 +267,6 @@ int sctp_send_add_streams(struct sctp_association *asoc, stream->out = streamout; } - if (in) { - struct sctp_stream_in *streamin; - - streamin = krealloc(stream->in, incnt * sizeof(*streamin), - GFP_KERNEL); - if (!streamin) - goto out; - - memset(streamin + stream->incnt, 0, in * sizeof(*streamin)); - stream->in = streamin; - } - chunk = sctp_make_strreset_addstrm(asoc, out, in); if (!chunk) goto out; @@ -303,13 +291,14 @@ out: } static sctp_paramhdr_t *sctp_chunk_lookup_strreset_param( - struct sctp_association *asoc, __u32 resp_seq) + struct sctp_association *asoc, __u32 resp_seq, + __be16 type) { struct sctp_chunk *chunk = asoc->strreset_chunk; struct sctp_reconf_chunk *hdr; union sctp_params param; - if (ntohl(resp_seq) != asoc->strreset_outseq || !chunk) + if (!chunk) return NULL; hdr = (struct sctp_reconf_chunk *)chunk->chunk_hdr; @@ -320,7 +309,8 @@ static sctp_paramhdr_t *sctp_chunk_lookup_strreset_param( */ struct sctp_strreset_tsnreq *req = param.v; - if (req->request_seq == resp_seq) + if ((!resp_seq || req->request_seq == resp_seq) && + (!type || type == req->param_hdr.type)) return param.v; } @@ -361,13 +351,9 @@ struct sctp_chunk *sctp_process_strreset_outreq( goto out; if (asoc->strreset_chunk) { - sctp_paramhdr_t *param_hdr; - struct sctp_transport *t; - - param_hdr = sctp_chunk_lookup_strreset_param( - asoc, outreq->response_seq); - if (!param_hdr || param_hdr->type != - SCTP_PARAM_RESET_IN_REQUEST) { + if (!sctp_chunk_lookup_strreset_param( + asoc, outreq->response_seq, + SCTP_PARAM_RESET_IN_REQUEST)) { /* same process with outstanding isn't 0 */ result = SCTP_STRRESET_ERR_IN_PROGRESS; goto out; @@ -377,6 +363,8 @@ struct sctp_chunk *sctp_process_strreset_outreq( asoc->strreset_outseq++; if (!asoc->strreset_outstanding) { + struct sctp_transport *t; + t = asoc->strreset_chunk->transport; if (del_timer(&t->reconf_timer)) sctp_transport_put(t); @@ -477,3 +465,367 @@ out: return chunk; } + +struct sctp_chunk *sctp_process_strreset_tsnreq( + struct sctp_association *asoc, + union sctp_params param, + struct sctp_ulpevent **evp) +{ + __u32 init_tsn = 0, next_tsn = 0, max_tsn_seen; + struct sctp_strreset_tsnreq *tsnreq = param.v; + struct sctp_stream *stream = asoc->stream; + __u32 result = SCTP_STRRESET_DENIED; + __u32 request_seq; + __u16 i; + + request_seq = ntohl(tsnreq->request_seq); + if (request_seq > asoc->strreset_inseq) { + result = SCTP_STRRESET_ERR_BAD_SEQNO; + goto out; + } else if (request_seq == asoc->strreset_inseq) { + asoc->strreset_inseq++; + } + + if (!(asoc->strreset_enable & SCTP_ENABLE_RESET_ASSOC_REQ)) + goto out; + + if (asoc->strreset_outstanding) { + result = SCTP_STRRESET_ERR_IN_PROGRESS; + goto out; + } + + /* G3: The same processing as though a SACK chunk with no gap report + * and a cumulative TSN ACK of the Sender's Next TSN minus 1 were + * received MUST be performed. + */ + max_tsn_seen = sctp_tsnmap_get_max_tsn_seen(&asoc->peer.tsn_map); + sctp_ulpq_reasm_flushtsn(&asoc->ulpq, max_tsn_seen); + sctp_ulpq_abort_pd(&asoc->ulpq, GFP_ATOMIC); + + /* G1: Compute an appropriate value for the Receiver's Next TSN -- the + * TSN that the peer should use to send the next DATA chunk. The + * value SHOULD be the smallest TSN not acknowledged by the + * receiver of the request plus 2^31. + */ + init_tsn = sctp_tsnmap_get_ctsn(&asoc->peer.tsn_map) + (1 << 31); + sctp_tsnmap_init(&asoc->peer.tsn_map, SCTP_TSN_MAP_INITIAL, + init_tsn, GFP_ATOMIC); + + /* G4: The same processing as though a FWD-TSN chunk (as defined in + * [RFC3758]) with all streams affected and a new cumulative TSN + * ACK of the Receiver's Next TSN minus 1 were received MUST be + * performed. + */ + sctp_outq_free(&asoc->outqueue); + + /* G2: Compute an appropriate value for the local endpoint's next TSN, + * i.e., the next TSN assigned by the receiver of the SSN/TSN reset + * chunk. The value SHOULD be the highest TSN sent by the receiver + * of the request plus 1. + */ + next_tsn = asoc->next_tsn; + asoc->ctsn_ack_point = next_tsn - 1; + asoc->adv_peer_ack_point = asoc->ctsn_ack_point; + + /* G5: The next expected and outgoing SSNs MUST be reset to 0 for all + * incoming and outgoing streams. + */ + for (i = 0; i < stream->outcnt; i++) + stream->out[i].ssn = 0; + for (i = 0; i < stream->incnt; i++) + stream->in[i].ssn = 0; + + result = SCTP_STRRESET_PERFORMED; + + *evp = sctp_ulpevent_make_assoc_reset_event(asoc, 0, init_tsn, + next_tsn, GFP_ATOMIC); + +out: + return sctp_make_strreset_tsnresp(asoc, result, request_seq, + next_tsn, init_tsn); +} + +struct sctp_chunk *sctp_process_strreset_addstrm_out( + struct sctp_association *asoc, + union sctp_params param, + struct sctp_ulpevent **evp) +{ + struct sctp_strreset_addstrm *addstrm = param.v; + struct sctp_stream *stream = asoc->stream; + __u32 result = SCTP_STRRESET_DENIED; + struct sctp_stream_in *streamin; + __u32 request_seq, incnt; + __u16 in; + + request_seq = ntohl(addstrm->request_seq); + if (request_seq > asoc->strreset_inseq) { + result = SCTP_STRRESET_ERR_BAD_SEQNO; + goto out; + } else if (request_seq == asoc->strreset_inseq) { + asoc->strreset_inseq++; + } + + if (!(asoc->strreset_enable & SCTP_ENABLE_CHANGE_ASSOC_REQ)) + goto out; + + if (asoc->strreset_chunk) { + if (!sctp_chunk_lookup_strreset_param( + asoc, 0, SCTP_PARAM_RESET_ADD_IN_STREAMS)) { + /* same process with outstanding isn't 0 */ + result = SCTP_STRRESET_ERR_IN_PROGRESS; + goto out; + } + + asoc->strreset_outstanding--; + asoc->strreset_outseq++; + + if (!asoc->strreset_outstanding) { + struct sctp_transport *t; + + t = asoc->strreset_chunk->transport; + if (del_timer(&t->reconf_timer)) + sctp_transport_put(t); + + sctp_chunk_put(asoc->strreset_chunk); + asoc->strreset_chunk = NULL; + } + } + + in = ntohs(addstrm->number_of_streams); + incnt = stream->incnt + in; + if (!in || incnt > SCTP_MAX_STREAM) + goto out; + + streamin = krealloc(stream->in, incnt * sizeof(*streamin), + GFP_ATOMIC); + if (!streamin) + goto out; + + memset(streamin + stream->incnt, 0, in * sizeof(*streamin)); + stream->in = streamin; + stream->incnt = incnt; + + result = SCTP_STRRESET_PERFORMED; + + *evp = sctp_ulpevent_make_stream_change_event(asoc, + 0, ntohs(addstrm->number_of_streams), 0, GFP_ATOMIC); + +out: + return sctp_make_strreset_resp(asoc, result, request_seq); +} + +struct sctp_chunk *sctp_process_strreset_addstrm_in( + struct sctp_association *asoc, + union sctp_params param, + struct sctp_ulpevent **evp) +{ + struct sctp_strreset_addstrm *addstrm = param.v; + struct sctp_stream *stream = asoc->stream; + __u32 result = SCTP_STRRESET_DENIED; + struct sctp_stream_out *streamout; + struct sctp_chunk *chunk = NULL; + __u32 request_seq, outcnt; + __u16 out; + + request_seq = ntohl(addstrm->request_seq); + if (request_seq > asoc->strreset_inseq) { + result = SCTP_STRRESET_ERR_BAD_SEQNO; + goto out; + } else if (request_seq == asoc->strreset_inseq) { + asoc->strreset_inseq++; + } + + if (!(asoc->strreset_enable & SCTP_ENABLE_CHANGE_ASSOC_REQ)) + goto out; + + if (asoc->strreset_outstanding) { + result = SCTP_STRRESET_ERR_IN_PROGRESS; + goto out; + } + + out = ntohs(addstrm->number_of_streams); + outcnt = stream->outcnt + out; + if (!out || outcnt > SCTP_MAX_STREAM) + goto out; + + streamout = krealloc(stream->out, outcnt * sizeof(*streamout), + GFP_ATOMIC); + if (!streamout) + goto out; + + memset(streamout + stream->outcnt, 0, out * sizeof(*streamout)); + stream->out = streamout; + + chunk = sctp_make_strreset_addstrm(asoc, out, 0); + if (!chunk) + goto out; + + asoc->strreset_chunk = chunk; + asoc->strreset_outstanding = 1; + sctp_chunk_hold(asoc->strreset_chunk); + + stream->outcnt = outcnt; + + *evp = sctp_ulpevent_make_stream_change_event(asoc, + 0, 0, ntohs(addstrm->number_of_streams), GFP_ATOMIC); + +out: + if (!chunk) + chunk = sctp_make_strreset_resp(asoc, result, request_seq); + + return chunk; +} + +struct sctp_chunk *sctp_process_strreset_resp( + struct sctp_association *asoc, + union sctp_params param, + struct sctp_ulpevent **evp) +{ + struct sctp_strreset_resp *resp = param.v; + struct sctp_stream *stream = asoc->stream; + struct sctp_transport *t; + __u16 i, nums, flags = 0; + sctp_paramhdr_t *req; + __u32 result; + + req = sctp_chunk_lookup_strreset_param(asoc, resp->response_seq, 0); + if (!req) + return NULL; + + result = ntohl(resp->result); + if (result != SCTP_STRRESET_PERFORMED) { + /* if in progress, do nothing but retransmit */ + if (result == SCTP_STRRESET_IN_PROGRESS) + return NULL; + else if (result == SCTP_STRRESET_DENIED) + flags = SCTP_STREAM_RESET_DENIED; + else + flags = SCTP_STREAM_RESET_FAILED; + } + + if (req->type == SCTP_PARAM_RESET_OUT_REQUEST) { + struct sctp_strreset_outreq *outreq; + __u16 *str_p = NULL; + + outreq = (struct sctp_strreset_outreq *)req; + nums = (ntohs(outreq->param_hdr.length) - sizeof(*outreq)) / 2; + + if (result == SCTP_STRRESET_PERFORMED) { + if (nums) { + str_p = outreq->list_of_streams; + for (i = 0; i < nums; i++) + stream->out[ntohs(str_p[i])].ssn = 0; + } else { + for (i = 0; i < stream->outcnt; i++) + stream->out[i].ssn = 0; + } + + flags = SCTP_STREAM_RESET_OUTGOING_SSN; + } + + for (i = 0; i < stream->outcnt; i++) + stream->out[i].state = SCTP_STREAM_OPEN; + + *evp = sctp_ulpevent_make_stream_reset_event(asoc, flags, + nums, str_p, GFP_ATOMIC); + } else if (req->type == SCTP_PARAM_RESET_IN_REQUEST) { + struct sctp_strreset_inreq *inreq; + __u16 *str_p = NULL; + + /* if the result is performed, it's impossible for inreq */ + if (result == SCTP_STRRESET_PERFORMED) + return NULL; + + inreq = (struct sctp_strreset_inreq *)req; + nums = (ntohs(inreq->param_hdr.length) - sizeof(*inreq)) / 2; + + str_p = inreq->list_of_streams; + *evp = sctp_ulpevent_make_stream_reset_event(asoc, flags, + nums, str_p, GFP_ATOMIC); + } else if (req->type == SCTP_PARAM_RESET_TSN_REQUEST) { + struct sctp_strreset_resptsn *resptsn; + __u32 stsn, rtsn; + + /* check for resptsn, as sctp_verify_reconf didn't do it*/ + if (ntohs(param.p->length) != sizeof(*resptsn)) + return NULL; + + resptsn = (struct sctp_strreset_resptsn *)resp; + stsn = ntohl(resptsn->senders_next_tsn); + rtsn = ntohl(resptsn->receivers_next_tsn); + + if (result == SCTP_STRRESET_PERFORMED) { + __u32 mtsn = sctp_tsnmap_get_max_tsn_seen( + &asoc->peer.tsn_map); + + sctp_ulpq_reasm_flushtsn(&asoc->ulpq, mtsn); + sctp_ulpq_abort_pd(&asoc->ulpq, GFP_ATOMIC); + + sctp_tsnmap_init(&asoc->peer.tsn_map, + SCTP_TSN_MAP_INITIAL, + stsn, GFP_ATOMIC); + + sctp_outq_free(&asoc->outqueue); + + asoc->next_tsn = rtsn; + asoc->ctsn_ack_point = asoc->next_tsn - 1; + asoc->adv_peer_ack_point = asoc->ctsn_ack_point; + + for (i = 0; i < stream->outcnt; i++) + stream->out[i].ssn = 0; + for (i = 0; i < stream->incnt; i++) + stream->in[i].ssn = 0; + } + + for (i = 0; i < stream->outcnt; i++) + stream->out[i].state = SCTP_STREAM_OPEN; + + *evp = sctp_ulpevent_make_assoc_reset_event(asoc, flags, + stsn, rtsn, GFP_ATOMIC); + } else if (req->type == SCTP_PARAM_RESET_ADD_OUT_STREAMS) { + struct sctp_strreset_addstrm *addstrm; + __u16 number; + + addstrm = (struct sctp_strreset_addstrm *)req; + nums = ntohs(addstrm->number_of_streams); + number = stream->outcnt - nums; + + if (result == SCTP_STRRESET_PERFORMED) + for (i = number; i < stream->outcnt; i++) + stream->out[i].state = SCTP_STREAM_OPEN; + else + stream->outcnt = number; + + *evp = sctp_ulpevent_make_stream_change_event(asoc, flags, + 0, nums, GFP_ATOMIC); + } else if (req->type == SCTP_PARAM_RESET_ADD_IN_STREAMS) { + struct sctp_strreset_addstrm *addstrm; + + /* if the result is performed, it's impossible for addstrm in + * request. + */ + if (result == SCTP_STRRESET_PERFORMED) + return NULL; + + addstrm = (struct sctp_strreset_addstrm *)req; + nums = ntohs(addstrm->number_of_streams); + + *evp = sctp_ulpevent_make_stream_change_event(asoc, flags, + nums, 0, GFP_ATOMIC); + } + + asoc->strreset_outstanding--; + asoc->strreset_outseq++; + + /* remove everything for this reconf request */ + if (!asoc->strreset_outstanding) { + t = asoc->strreset_chunk->transport; + if (del_timer(&t->reconf_timer)) + sctp_transport_put(t); + + sctp_chunk_put(asoc->strreset_chunk); + asoc->strreset_chunk = NULL; + } + + return NULL; +} diff --git a/net/sctp/sysctl.c b/net/sctp/sysctl.c index daf8554fd42a..0e732f68c2bf 100644 --- a/net/sctp/sysctl.c +++ b/net/sctp/sysctl.c @@ -275,6 +275,13 @@ static struct ctl_table sctp_net_table[] = { .proc_handler = proc_dointvec, }, { + .procname = "reconf_enable", + .data = &init_net.sctp.reconf_enable, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, + { .procname = "auth_enable", .data = &init_net.sctp.auth_enable, .maxlen = sizeof(int), diff --git a/net/sctp/ulpevent.c b/net/sctp/ulpevent.c index c8881bc542a0..ec2b3e013c2f 100644 --- a/net/sctp/ulpevent.c +++ b/net/sctp/ulpevent.c @@ -883,6 +883,62 @@ struct sctp_ulpevent *sctp_ulpevent_make_stream_reset_event( return event; } +struct sctp_ulpevent *sctp_ulpevent_make_assoc_reset_event( + const struct sctp_association *asoc, __u16 flags, __u32 local_tsn, + __u32 remote_tsn, gfp_t gfp) +{ + struct sctp_assoc_reset_event *areset; + struct sctp_ulpevent *event; + struct sk_buff *skb; + + event = sctp_ulpevent_new(sizeof(struct sctp_assoc_reset_event), + MSG_NOTIFICATION, gfp); + if (!event) + return NULL; + + skb = sctp_event2skb(event); + areset = (struct sctp_assoc_reset_event *) + skb_put(skb, sizeof(struct sctp_assoc_reset_event)); + + areset->assocreset_type = SCTP_ASSOC_RESET_EVENT; + areset->assocreset_flags = flags; + areset->assocreset_length = sizeof(struct sctp_assoc_reset_event); + sctp_ulpevent_set_owner(event, asoc); + areset->assocreset_assoc_id = sctp_assoc2id(asoc); + areset->assocreset_local_tsn = local_tsn; + areset->assocreset_remote_tsn = remote_tsn; + + return event; +} + +struct sctp_ulpevent *sctp_ulpevent_make_stream_change_event( + const struct sctp_association *asoc, __u16 flags, + __u32 strchange_instrms, __u32 strchange_outstrms, gfp_t gfp) +{ + struct sctp_stream_change_event *schange; + struct sctp_ulpevent *event; + struct sk_buff *skb; + + event = sctp_ulpevent_new(sizeof(struct sctp_stream_change_event), + MSG_NOTIFICATION, gfp); + if (!event) + return NULL; + + skb = sctp_event2skb(event); + schange = (struct sctp_stream_change_event *) + skb_put(skb, sizeof(struct sctp_stream_change_event)); + + schange->strchange_type = SCTP_STREAM_CHANGE_EVENT; + schange->strchange_flags = flags; + schange->strchange_length = sizeof(struct sctp_stream_change_event); + sctp_ulpevent_set_owner(event, asoc); + schange->strchange_assoc_id = sctp_assoc2id(asoc); + schange->strchange_instrms = strchange_instrms; + schange->strchange_outstrms = strchange_outstrms; + + return event; +} + /* Return the notification type, assuming this is a notification * event. */ diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c index 85837ab90e89..093803786eac 100644 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@ -944,7 +944,7 @@ out: } static int smc_accept(struct socket *sock, struct socket *new_sock, - int flags) + int flags, bool kern) { struct sock *sk = sock->sk, *nsk; DECLARE_WAITQUEUE(wait, current); diff --git a/net/socket.c b/net/socket.c index 2c1e8677ff2d..e034fe4164be 100644 --- a/net/socket.c +++ b/net/socket.c @@ -1506,7 +1506,7 @@ SYSCALL_DEFINE4(accept4, int, fd, struct sockaddr __user *, upeer_sockaddr, if (err) goto out_fd; - err = sock->ops->accept(sock, newsock, sock->file->f_flags); + err = sock->ops->accept(sock, newsock, sock->file->f_flags, false); if (err < 0) goto out_fd; @@ -1731,6 +1731,7 @@ SYSCALL_DEFINE6(recvfrom, int, fd, void __user *, ubuf, size_t, size, /* We assume all kernel code knows the size of sockaddr_storage */ msg.msg_namelen = 0; msg.msg_iocb = NULL; + msg.msg_flags = 0; if (sock->file->f_flags & O_NONBLOCK) flags |= MSG_DONTWAIT; err = sock_recvmsg(sock, &msg, flags); @@ -3238,7 +3239,7 @@ int kernel_accept(struct socket *sock, struct socket **newsock, int flags) if (err < 0) goto done; - err = sock->ops->accept(sock, *newsock, flags); + err = sock->ops->accept(sock, *newsock, flags, true); if (err < 0) { sock_release(*newsock); *newsock = NULL; diff --git a/net/tipc/socket.c b/net/tipc/socket.c index 43e4045e72bc..7130e73bd42c 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -115,7 +115,8 @@ static void tipc_data_ready(struct sock *sk); static void tipc_write_space(struct sock *sk); static void tipc_sock_destruct(struct sock *sk); static int tipc_release(struct socket *sock); -static int tipc_accept(struct socket *sock, struct socket *new_sock, int flags); +static int tipc_accept(struct socket *sock, struct socket *new_sock, int flags, + bool kern); static void tipc_sk_timeout(unsigned long data); static int tipc_sk_publish(struct tipc_sock *tsk, uint scope, struct tipc_name_seq const *seq); @@ -2029,7 +2030,8 @@ static int tipc_wait_for_accept(struct socket *sock, long timeo) * * Returns 0 on success, errno otherwise */ -static int tipc_accept(struct socket *sock, struct socket *new_sock, int flags) +static int tipc_accept(struct socket *sock, struct socket *new_sock, int flags, + bool kern) { struct sock *new_sk, *sk = sock->sk; struct sk_buff *buf; @@ -2051,7 +2053,7 @@ static int tipc_accept(struct socket *sock, struct socket *new_sock, int flags) buf = skb_peek(&sk->sk_receive_queue); - res = tipc_sk_create(sock_net(sock->sk), new_sock, 0, 0); + res = tipc_sk_create(sock_net(sock->sk), new_sock, 0, kern); if (res) goto exit; security_sk_clone(sock->sk, new_sock->sk); diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index ee37b390260a..928691c43408 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -636,7 +636,7 @@ static int unix_bind(struct socket *, struct sockaddr *, int); static int unix_stream_connect(struct socket *, struct sockaddr *, int addr_len, int flags); static int unix_socketpair(struct socket *, struct socket *); -static int unix_accept(struct socket *, struct socket *, int); +static int unix_accept(struct socket *, struct socket *, int, bool); static int unix_getname(struct socket *, struct sockaddr *, int *, int); static unsigned int unix_poll(struct file *, struct socket *, poll_table *); static unsigned int unix_dgram_poll(struct file *, struct socket *, @@ -1402,7 +1402,8 @@ static void unix_sock_inherit_flags(const struct socket *old, set_bit(SOCK_PASSSEC, &new->flags); } -static int unix_accept(struct socket *sock, struct socket *newsock, int flags) +static int unix_accept(struct socket *sock, struct socket *newsock, int flags, + bool kern) { struct sock *sk = sock->sk; struct sock *tsk; diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c index 9192ead66751..9f770f33c100 100644 --- a/net/vmw_vsock/af_vsock.c +++ b/net/vmw_vsock/af_vsock.c @@ -1250,7 +1250,8 @@ out: return err; } -static int vsock_accept(struct socket *sock, struct socket *newsock, int flags) +static int vsock_accept(struct socket *sock, struct socket *newsock, int flags, + bool kern) { struct sock *listener; int err; diff --git a/net/x25/af_x25.c b/net/x25/af_x25.c index fd28a49dbe8f..8b911c29860e 100644 --- a/net/x25/af_x25.c +++ b/net/x25/af_x25.c @@ -852,7 +852,8 @@ static int x25_wait_for_data(struct sock *sk, long timeout) return rc; } -static int x25_accept(struct socket *sock, struct socket *newsock, int flags) +static int x25_accept(struct socket *sock, struct socket *newsock, int flags, + bool kern) { struct sock *sk = sock->sk; struct sock *newsk; diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index 0806dccdf507..236cbbc0ab9c 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -1243,7 +1243,7 @@ static inline int policy_to_flow_dir(int dir) } static struct xfrm_policy *xfrm_sk_policy_lookup(const struct sock *sk, int dir, - const struct flowi *fl) + const struct flowi *fl, u16 family) { struct xfrm_policy *pol; @@ -1251,8 +1251,7 @@ static struct xfrm_policy *xfrm_sk_policy_lookup(const struct sock *sk, int dir, again: pol = rcu_dereference(sk->sk_policy[dir]); if (pol != NULL) { - bool match = xfrm_selector_match(&pol->selector, fl, - sk->sk_family); + bool match = xfrm_selector_match(&pol->selector, fl, family); int err = 0; if (match) { @@ -2239,7 +2238,7 @@ struct dst_entry *xfrm_lookup(struct net *net, struct dst_entry *dst_orig, sk = sk_const_to_full_sk(sk); if (sk && sk->sk_policy[XFRM_POLICY_OUT]) { num_pols = 1; - pols[0] = xfrm_sk_policy_lookup(sk, XFRM_POLICY_OUT, fl); + pols[0] = xfrm_sk_policy_lookup(sk, XFRM_POLICY_OUT, fl, family); err = xfrm_expand_policies(fl, family, pols, &num_pols, &num_xfrms); if (err < 0) @@ -2518,7 +2517,7 @@ int __xfrm_policy_check(struct sock *sk, int dir, struct sk_buff *skb, pol = NULL; sk = sk_to_full_sk(sk); if (sk && sk->sk_policy[dir]) { - pol = xfrm_sk_policy_lookup(sk, dir, &fl); + pol = xfrm_sk_policy_lookup(sk, dir, &fl, family); if (IS_ERR(pol)) { XFRM_INC_STATS(net, LINUX_MIB_XFRMINPOLERROR); return 0; @@ -3069,6 +3068,11 @@ static int __net_init xfrm_net_init(struct net *net) { int rv; + /* Initialize the per-net locks here */ + spin_lock_init(&net->xfrm.xfrm_state_lock); + spin_lock_init(&net->xfrm.xfrm_policy_lock); + mutex_init(&net->xfrm.xfrm_cfg_mutex); + rv = xfrm_statistics_init(net); if (rv < 0) goto out_statistics; @@ -3085,11 +3089,6 @@ static int __net_init xfrm_net_init(struct net *net) if (rv < 0) goto out; - /* Initialize the per-net locks here */ - spin_lock_init(&net->xfrm.xfrm_state_lock); - spin_lock_init(&net->xfrm.xfrm_policy_lock); - mutex_init(&net->xfrm.xfrm_cfg_mutex); - return 0; out: diff --git a/samples/bpf/map_perf_test_kern.c b/samples/bpf/map_perf_test_kern.c index a91872a97742..9da2a3441b0a 100644 --- a/samples/bpf/map_perf_test_kern.c +++ b/samples/bpf/map_perf_test_kern.c @@ -65,6 +65,13 @@ struct bpf_map_def SEC("maps") lpm_trie_map_alloc = { .map_flags = BPF_F_NO_PREALLOC, }; +struct bpf_map_def SEC("maps") array_map = { + .type = BPF_MAP_TYPE_ARRAY, + .key_size = sizeof(u32), + .value_size = sizeof(long), + .max_entries = MAX_ENTRIES, +}; + SEC("kprobe/sys_getuid") int stress_hmap(struct pt_regs *ctx) { @@ -165,5 +172,31 @@ int stress_lpm_trie_map_alloc(struct pt_regs *ctx) return 0; } +SEC("kprobe/sys_getpgid") +int stress_hash_map_lookup(struct pt_regs *ctx) +{ + u32 key = 1, i; + long *value; + +#pragma clang loop unroll(full) + for (i = 0; i < 64; ++i) + value = bpf_map_lookup_elem(&hash_map, &key); + + return 0; +} + +SEC("kprobe/sys_getpgrp") +int stress_array_map_lookup(struct pt_regs *ctx) +{ + u32 key = 1, i; + long *value; + +#pragma clang loop unroll(full) + for (i = 0; i < 64; ++i) + value = bpf_map_lookup_elem(&array_map, &key); + + return 0; +} + char _license[] SEC("license") = "GPL"; u32 _version SEC("version") = LINUX_VERSION_CODE; diff --git a/samples/bpf/map_perf_test_user.c b/samples/bpf/map_perf_test_user.c index 680260a91f50..e29ff318a793 100644 --- a/samples/bpf/map_perf_test_user.c +++ b/samples/bpf/map_perf_test_user.c @@ -38,6 +38,8 @@ static __u64 time_get_ns(void) #define LRU_HASH_PREALLOC (1 << 4) #define PERCPU_LRU_HASH_PREALLOC (1 << 5) #define LPM_KMALLOC (1 << 6) +#define HASH_LOOKUP (1 << 7) +#define ARRAY_LOOKUP (1 << 8) static int test_flags = ~0; @@ -125,6 +127,30 @@ static void test_lpm_kmalloc(int cpu) cpu, MAX_CNT * 1000000000ll / (time_get_ns() - start_time)); } +static void test_hash_lookup(int cpu) +{ + __u64 start_time; + int i; + + start_time = time_get_ns(); + for (i = 0; i < MAX_CNT; i++) + syscall(__NR_getpgid, 0); + printf("%d:hash_lookup %lld lookups per sec\n", + cpu, MAX_CNT * 1000000000ll * 64 / (time_get_ns() - start_time)); +} + +static void test_array_lookup(int cpu) +{ + __u64 start_time; + int i; + + start_time = time_get_ns(); + for (i = 0; i < MAX_CNT; i++) + syscall(__NR_getpgrp, 0); + printf("%d:array_lookup %lld lookups per sec\n", + cpu, MAX_CNT * 1000000000ll * 64 / (time_get_ns() - start_time)); +} + static void loop(int cpu) { cpu_set_t cpuset; @@ -153,6 +179,12 @@ static void loop(int cpu) if (test_flags & LPM_KMALLOC) test_lpm_kmalloc(cpu); + + if (test_flags & HASH_LOOKUP) + test_hash_lookup(cpu); + + if (test_flags & ARRAY_LOOKUP) + test_array_lookup(cpu); } static void run_perf_test(int tasks) diff --git a/scripts/gcc-plugins/sancov_plugin.c b/scripts/gcc-plugins/sancov_plugin.c index 9b0b5cbc5b89..0f98634c20a0 100644 --- a/scripts/gcc-plugins/sancov_plugin.c +++ b/scripts/gcc-plugins/sancov_plugin.c @@ -133,7 +133,7 @@ __visible int plugin_init(struct plugin_name_args *plugin_info, struct plugin_gc #if BUILDING_GCC_VERSION < 6000 register_callback(plugin_name, PLUGIN_START_UNIT, &sancov_start_unit, NULL); register_callback(plugin_name, PLUGIN_REGISTER_GGC_ROOTS, NULL, (void *)>_ggc_r_gt_sancov); - register_callback(plugin_name, PLUGIN_PASS_MANAGER_SETUP, NULL, &sancov_plugin_pass_info); + register_callback(plugin_name, PLUGIN_PASS_MANAGER_SETUP, NULL, &sancov_pass_info); #endif return 0; diff --git a/scripts/module-common.lds b/scripts/module-common.lds index cf7e52e4781b..9b6e246a45d0 100644 --- a/scripts/module-common.lds +++ b/scripts/module-common.lds @@ -22,4 +22,6 @@ SECTIONS { . = ALIGN(8); .init_array 0 : { *(SORT(.init_array.*)) *(.init_array) } + + __jump_table 0 : ALIGN(8) { KEEP(*(__jump_table)) } } diff --git a/scripts/spelling.txt b/scripts/spelling.txt index 0458b037c8a1..0545f5a8cabe 100644 --- a/scripts/spelling.txt +++ b/scripts/spelling.txt @@ -372,6 +372,8 @@ disassocation||disassociation disapear||disappear disapeared||disappeared disappared||disappeared +disble||disable +disbled||disabled disconnet||disconnect discontinous||discontinuous dispertion||dispersion @@ -732,6 +734,7 @@ oustanding||outstanding overaall||overall overhread||overhead overlaping||overlapping +overide||override overrided||overridden overriden||overridden overun||overrun diff --git a/sound/soc/amd/acp-pcm-dma.c b/sound/soc/amd/acp-pcm-dma.c index ec1067a679da..08b1399d1da2 100644 --- a/sound/soc/amd/acp-pcm-dma.c +++ b/sound/soc/amd/acp-pcm-dma.c @@ -89,7 +89,7 @@ static void acp_reg_write(u32 val, void __iomem *acp_mmio, u32 reg) writel(val, acp_mmio + (reg * 4)); } -/* Configure a given dma channel parameters - enable/disble, +/* Configure a given dma channel parameters - enable/disable, * number of descriptors, priority */ static void config_acp_dma_channel(void __iomem *acp_mmio, u8 ch_num, diff --git a/tools/hv/bondvf.sh b/tools/hv/bondvf.sh index 4aa5369ffa4e..d85968cb1bf2 100755 --- a/tools/hv/bondvf.sh +++ b/tools/hv/bondvf.sh @@ -101,9 +101,25 @@ function create_bond_cfg_redhat { echo BONDING_OPTS=\"mode=active-backup miimon=100 primary=$2\" >>$fn } +function del_eth_cfg_ubuntu { + local fn=$cfgdir/interfaces + local tmpfl=$(mktemp) + + local nic_start='^[ \t]*(auto|iface|mapping|allow-.*)[ \t]+'$1 + local nic_end='^[ \t]*(auto|iface|mapping|allow-.*|source)' + + awk "/$nic_end/{x=0} x{next} /$nic_start/{x=1;next} 1" $fn >$tmpfl + + cp $tmpfl $fn + + rm $tmpfl +} + function create_eth_cfg_ubuntu { local fn=$cfgdir/interfaces + del_eth_cfg_ubuntu $1 + echo $'\n'auto $1 >>$fn echo iface $1 inet manual >>$fn echo bond-master $2 >>$fn @@ -119,6 +135,8 @@ function create_eth_cfg_pri_ubuntu { function create_bond_cfg_ubuntu { local fn=$cfgdir/interfaces + del_eth_cfg_ubuntu $1 + echo $'\n'auto $1 >>$fn echo iface $1 inet dhcp >>$fn echo bond-mode active-backup >>$fn diff --git a/tools/include/uapi/linux/bpf_perf_event.h b/tools/include/uapi/linux/bpf_perf_event.h new file mode 100644 index 000000000000..067427259820 --- /dev/null +++ b/tools/include/uapi/linux/bpf_perf_event.h @@ -0,0 +1,18 @@ +/* Copyright (c) 2016 Facebook + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of version 2 of the GNU General Public + * License as published by the Free Software Foundation. + */ +#ifndef _UAPI__LINUX_BPF_PERF_EVENT_H__ +#define _UAPI__LINUX_BPF_PERF_EVENT_H__ + +#include <linux/types.h> +#include <linux/ptrace.h> + +struct bpf_perf_event_data { + struct pt_regs regs; + __u64 sample_period; +}; + +#endif /* _UAPI__LINUX_BPF_PERF_EVENT_H__ */ diff --git a/tools/lguest/lguest.c b/tools/lguest/lguest.c index 11c8d9bc762e..5d19fdf80292 100644 --- a/tools/lguest/lguest.c +++ b/tools/lguest/lguest.c @@ -1387,7 +1387,7 @@ static bool pci_data_iowrite(u16 port, u32 mask, u32 val) /* Allow writing to any other BAR, or expansion ROM */ iowrite(portoff, val, mask, &d->config_words[reg]); return true; - /* We let them overide latency timer and cacheline size */ + /* We let them override latency timer and cacheline size */ } else if (&d->config_words[reg] == (void *)&d->config.cacheline_size) { /* Only let them change the first two fields. */ if (mask == 0xFFFFFFFF) diff --git a/tools/lib/bpf/Makefile b/tools/lib/bpf/Makefile index e2efddf10231..1f5300e56b44 100644 --- a/tools/lib/bpf/Makefile +++ b/tools/lib/bpf/Makefile @@ -132,7 +132,7 @@ else Q = @ endif -# Disable command line variables (CFLAGS) overide from top +# Disable command line variables (CFLAGS) override from top # level Makefile (perf), otherwise build Makefile will get # the same command line setup. MAKEOVERRIDES= diff --git a/tools/lib/traceevent/Makefile b/tools/lib/traceevent/Makefile index 47076b15eebe..9b8555ea3459 100644 --- a/tools/lib/traceevent/Makefile +++ b/tools/lib/traceevent/Makefile @@ -135,7 +135,7 @@ else Q = @ endif -# Disable command line variables (CFLAGS) overide from top +# Disable command line variables (CFLAGS) override from top # level Makefile (perf), otherwise build Makefile will get # the same command line setup. MAKEOVERRIDES= diff --git a/tools/lib/traceevent/event-parse.h b/tools/lib/traceevent/event-parse.h index 66342804161c..0c03538df74c 100644 --- a/tools/lib/traceevent/event-parse.h +++ b/tools/lib/traceevent/event-parse.h @@ -140,7 +140,7 @@ struct pevent_plugin_option { * struct pevent_plugin_option PEVENT_PLUGIN_OPTIONS[] = { * { * .name = "option-name", - * .plugin_alias = "overide-file-name", (optional) + * .plugin_alias = "override-file-name", (optional) * .description = "description of option to show users", * }, * { diff --git a/tools/objtool/builtin-check.c b/tools/objtool/builtin-check.c index 4cfdbb5b6967..066086dd59a8 100644 --- a/tools/objtool/builtin-check.c +++ b/tools/objtool/builtin-check.c @@ -805,11 +805,20 @@ static struct rela *find_switch_table(struct objtool_file *file, insn->jump_dest->offset > orig_insn->offset)) break; + /* look for a relocation which references .rodata */ text_rela = find_rela_by_dest_range(insn->sec, insn->offset, insn->len); - if (text_rela && text_rela->sym == file->rodata->sym) - return find_rela_by_dest(file->rodata, - text_rela->addend); + if (!text_rela || text_rela->sym != file->rodata->sym) + continue; + + /* + * Make sure the .rodata address isn't associated with a + * symbol. gcc jump tables are anonymous data. + */ + if (find_symbol_containing(file->rodata, text_rela->addend)) + continue; + + return find_rela_by_dest(file->rodata, text_rela->addend); } return NULL; diff --git a/tools/objtool/elf.c b/tools/objtool/elf.c index 0d7983ac63ef..d897702ce742 100644 --- a/tools/objtool/elf.c +++ b/tools/objtool/elf.c @@ -85,6 +85,18 @@ struct symbol *find_symbol_by_offset(struct section *sec, unsigned long offset) return NULL; } +struct symbol *find_symbol_containing(struct section *sec, unsigned long offset) +{ + struct symbol *sym; + + list_for_each_entry(sym, &sec->symbol_list, list) + if (sym->type != STT_SECTION && + offset >= sym->offset && offset < sym->offset + sym->len) + return sym; + + return NULL; +} + struct rela *find_rela_by_dest_range(struct section *sec, unsigned long offset, unsigned int len) { diff --git a/tools/objtool/elf.h b/tools/objtool/elf.h index aa1ff6596684..731973e1a3f5 100644 --- a/tools/objtool/elf.h +++ b/tools/objtool/elf.h @@ -79,6 +79,7 @@ struct elf { struct elf *elf_open(const char *name); struct section *find_section_by_name(struct elf *elf, const char *name); struct symbol *find_symbol_by_offset(struct section *sec, unsigned long offset); +struct symbol *find_symbol_containing(struct section *sec, unsigned long offset); struct rela *find_rela_by_dest(struct section *sec, unsigned long offset); struct rela *find_rela_by_dest_range(struct section *sec, unsigned long offset, unsigned int len); diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-insn-decoder.c b/tools/perf/util/intel-pt-decoder/intel-pt-insn-decoder.c index 7913363bde5c..4f3c758d875d 100644 --- a/tools/perf/util/intel-pt-decoder/intel-pt-insn-decoder.c +++ b/tools/perf/util/intel-pt-decoder/intel-pt-insn-decoder.c @@ -31,7 +31,7 @@ #error Instruction buffer size too small #endif -/* Based on branch_type() from perf_event_intel_lbr.c */ +/* Based on branch_type() from arch/x86/events/intel/lbr.c */ static void intel_pt_insn_decoder(struct insn *insn, struct intel_pt_insn *intel_pt_insn) { diff --git a/tools/testing/ktest/ktest.pl b/tools/testing/ktest/ktest.pl index 6e4eb2fc2d1e..0c8b61f8398e 100755 --- a/tools/testing/ktest/ktest.pl +++ b/tools/testing/ktest/ktest.pl @@ -1880,6 +1880,7 @@ sub get_grub_index { sub wait_for_input { my ($fp, $time) = @_; + my $start_time; my $rin; my $rout; my $nr; @@ -1895,17 +1896,22 @@ sub wait_for_input vec($rin, fileno($fp), 1) = 1; vec($rin, fileno(\*STDIN), 1) = 1; + $start_time = time; + while (1) { $nr = select($rout=$rin, undef, undef, $time); - if ($nr <= 0) { - return undef; - } + last if ($nr <= 0); # copy data from stdin to the console if (vec($rout, fileno(\*STDIN), 1) == 1) { - sysread(\*STDIN, $buf, 1000); - syswrite($fp, $buf, 1000); + $nr = sysread(\*STDIN, $buf, 1000); + syswrite($fp, $buf, $nr) if ($nr > 0); + } + + # The timeout is based on time waiting for the fp data + if (vec($rout, fileno($fp), 1) != 1) { + last if (defined($time) && (time - $start_time > $time)); next; } @@ -1917,12 +1923,11 @@ sub wait_for_input last if ($ch eq "\n"); } - if (!length($line)) { - return undef; - } + last if (!length($line)); return $line; } + return undef; } sub reboot_to { diff --git a/tools/testing/radix-tree/Makefile b/tools/testing/radix-tree/Makefile index f11315bedefc..6a9480c03cbd 100644 --- a/tools/testing/radix-tree/Makefile +++ b/tools/testing/radix-tree/Makefile @@ -1,6 +1,7 @@ CFLAGS += -I. -I../../include -g -O2 -Wall -D_LGPL_SOURCE -fsanitize=address -LDFLAGS += -lpthread -lurcu +LDFLAGS += -fsanitize=address +LDLIBS+= -lpthread -lurcu TARGETS = main idr-test multiorder CORE_OFILES := radix-tree.o idr.o linux.o test.o find_bit.o OFILES = main.o $(CORE_OFILES) regression1.o regression2.o regression3.o \ @@ -10,23 +11,25 @@ ifndef SHIFT SHIFT=3 endif +ifeq ($(BUILD), 32) + CFLAGS += -m32 + LDFLAGS += -m32 +endif + targets: mapshift $(TARGETS) main: $(OFILES) - $(CC) $(CFLAGS) $(LDFLAGS) $^ -o main idr-test: idr-test.o $(CORE_OFILES) - $(CC) $(CFLAGS) $(LDFLAGS) $^ -o idr-test multiorder: multiorder.o $(CORE_OFILES) - $(CC) $(CFLAGS) $(LDFLAGS) $^ -o multiorder clean: $(RM) $(TARGETS) *.o radix-tree.c idr.c generated/map-shift.h vpath %.c ../../lib -$(OFILES): *.h */*.h generated/map-shift.h \ +$(OFILES): Makefile *.h */*.h generated/map-shift.h \ ../../include/linux/*.h \ ../../include/asm/*.h \ ../../../include/linux/radix-tree.h \ @@ -41,7 +44,7 @@ idr.c: ../../../lib/idr.c .PHONY: mapshift mapshift: - @if ! grep -qw $(SHIFT) generated/map-shift.h; then \ + @if ! grep -qws $(SHIFT) generated/map-shift.h; then \ echo "#define RADIX_TREE_MAP_SHIFT $(SHIFT)" > \ generated/map-shift.h; \ fi diff --git a/tools/testing/radix-tree/benchmark.c b/tools/testing/radix-tree/benchmark.c index 9b09ddfe462f..99c40f3ed133 100644 --- a/tools/testing/radix-tree/benchmark.c +++ b/tools/testing/radix-tree/benchmark.c @@ -17,6 +17,9 @@ #include <time.h> #include "test.h" +#define for_each_index(i, base, order) \ + for (i = base; i < base + (1 << order); i++) + #define NSEC_PER_SEC 1000000000L static long long benchmark_iter(struct radix_tree_root *root, bool tagged) @@ -57,27 +60,176 @@ again: return nsec; } +static void benchmark_insert(struct radix_tree_root *root, + unsigned long size, unsigned long step, int order) +{ + struct timespec start, finish; + unsigned long index; + long long nsec; + + clock_gettime(CLOCK_MONOTONIC, &start); + + for (index = 0 ; index < size ; index += step) + item_insert_order(root, index, order); + + clock_gettime(CLOCK_MONOTONIC, &finish); + + nsec = (finish.tv_sec - start.tv_sec) * NSEC_PER_SEC + + (finish.tv_nsec - start.tv_nsec); + + printv(2, "Size: %8ld, step: %8ld, order: %d, insertion: %15lld ns\n", + size, step, order, nsec); +} + +static void benchmark_tagging(struct radix_tree_root *root, + unsigned long size, unsigned long step, int order) +{ + struct timespec start, finish; + unsigned long index; + long long nsec; + + clock_gettime(CLOCK_MONOTONIC, &start); + + for (index = 0 ; index < size ; index += step) + radix_tree_tag_set(root, index, 0); + + clock_gettime(CLOCK_MONOTONIC, &finish); + + nsec = (finish.tv_sec - start.tv_sec) * NSEC_PER_SEC + + (finish.tv_nsec - start.tv_nsec); + + printv(2, "Size: %8ld, step: %8ld, order: %d, tagging: %17lld ns\n", + size, step, order, nsec); +} + +static void benchmark_delete(struct radix_tree_root *root, + unsigned long size, unsigned long step, int order) +{ + struct timespec start, finish; + unsigned long index, i; + long long nsec; + + clock_gettime(CLOCK_MONOTONIC, &start); + + for (index = 0 ; index < size ; index += step) + for_each_index(i, index, order) + item_delete(root, i); + + clock_gettime(CLOCK_MONOTONIC, &finish); + + nsec = (finish.tv_sec - start.tv_sec) * NSEC_PER_SEC + + (finish.tv_nsec - start.tv_nsec); + + printv(2, "Size: %8ld, step: %8ld, order: %d, deletion: %16lld ns\n", + size, step, order, nsec); +} + static void benchmark_size(unsigned long size, unsigned long step, int order) { RADIX_TREE(tree, GFP_KERNEL); long long normal, tagged; - unsigned long index; - for (index = 0 ; index < size ; index += step) { - item_insert_order(&tree, index, order); - radix_tree_tag_set(&tree, index, 0); - } + benchmark_insert(&tree, size, step, order); + benchmark_tagging(&tree, size, step, order); tagged = benchmark_iter(&tree, true); normal = benchmark_iter(&tree, false); - printv(2, "Size %ld, step %6ld, order %d tagged %10lld ns, normal %10lld ns\n", - size, step, order, tagged, normal); + printv(2, "Size: %8ld, step: %8ld, order: %d, tagged iteration: %8lld ns\n", + size, step, order, tagged); + printv(2, "Size: %8ld, step: %8ld, order: %d, normal iteration: %8lld ns\n", + size, step, order, normal); + + benchmark_delete(&tree, size, step, order); item_kill_tree(&tree); rcu_barrier(); } +static long long __benchmark_split(unsigned long index, + int old_order, int new_order) +{ + struct timespec start, finish; + long long nsec; + RADIX_TREE(tree, GFP_ATOMIC); + + item_insert_order(&tree, index, old_order); + + clock_gettime(CLOCK_MONOTONIC, &start); + radix_tree_split(&tree, index, new_order); + clock_gettime(CLOCK_MONOTONIC, &finish); + nsec = (finish.tv_sec - start.tv_sec) * NSEC_PER_SEC + + (finish.tv_nsec - start.tv_nsec); + + item_kill_tree(&tree); + + return nsec; + +} + +static void benchmark_split(unsigned long size, unsigned long step) +{ + int i, j, idx; + long long nsec = 0; + + + for (idx = 0; idx < size; idx += step) { + for (i = 3; i < 11; i++) { + for (j = 0; j < i; j++) { + nsec += __benchmark_split(idx, i, j); + } + } + } + + printv(2, "Size %8ld, step %8ld, split time %10lld ns\n", + size, step, nsec); + +} + +static long long __benchmark_join(unsigned long index, + unsigned order1, unsigned order2) +{ + unsigned long loc; + struct timespec start, finish; + long long nsec; + void *item, *item2 = item_create(index + 1, order1); + RADIX_TREE(tree, GFP_KERNEL); + + item_insert_order(&tree, index, order2); + item = radix_tree_lookup(&tree, index); + + clock_gettime(CLOCK_MONOTONIC, &start); + radix_tree_join(&tree, index + 1, order1, item2); + clock_gettime(CLOCK_MONOTONIC, &finish); + nsec = (finish.tv_sec - start.tv_sec) * NSEC_PER_SEC + + (finish.tv_nsec - start.tv_nsec); + + loc = find_item(&tree, item); + if (loc == -1) + free(item); + + item_kill_tree(&tree); + + return nsec; +} + +static void benchmark_join(unsigned long step) +{ + int i, j, idx; + long long nsec = 0; + + for (idx = 0; idx < 1 << 10; idx += step) { + for (i = 1; i < 15; i++) { + for (j = 0; j < i; j++) { + nsec += __benchmark_join(idx, i, j); + } + } + } + + printv(2, "Size %8d, step %8ld, join time %10lld ns\n", + 1 << 10, step, nsec); +} + void benchmark(void) { unsigned long size[] = {1 << 10, 1 << 20, 0}; @@ -95,4 +247,11 @@ void benchmark(void) for (c = 0; size[c]; c++) for (s = 0; step[s]; s++) benchmark_size(size[c], step[s] << 9, 9); + + for (c = 0; size[c]; c++) + for (s = 0; step[s]; s++) + benchmark_split(size[c], step[s]); + + for (s = 0; step[s]; s++) + benchmark_join(step[s]); } diff --git a/tools/testing/radix-tree/idr-test.c b/tools/testing/radix-tree/idr-test.c index a26098c6123d..30cd0b296f1a 100644 --- a/tools/testing/radix-tree/idr-test.c +++ b/tools/testing/radix-tree/idr-test.c @@ -153,6 +153,30 @@ void idr_nowait_test(void) idr_destroy(&idr); } +void idr_get_next_test(void) +{ + unsigned long i; + int nextid; + DEFINE_IDR(idr); + + int indices[] = {4, 7, 9, 15, 65, 128, 1000, 99999, 0}; + + for(i = 0; indices[i]; i++) { + struct item *item = item_create(indices[i], 0); + assert(idr_alloc(&idr, item, indices[i], indices[i+1], + GFP_KERNEL) == indices[i]); + } + + for(i = 0, nextid = 0; indices[i]; i++) { + idr_get_next(&idr, &nextid); + assert(nextid == indices[i]); + nextid++; + } + + idr_for_each(&idr, item_idr_free, &idr); + idr_destroy(&idr); +} + void idr_checks(void) { unsigned long i; @@ -202,6 +226,7 @@ void idr_checks(void) idr_alloc_test(); idr_null_test(); idr_nowait_test(); + idr_get_next_test(); } /* @@ -338,7 +363,7 @@ void ida_check_random(void) { DEFINE_IDA(ida); DECLARE_BITMAP(bitmap, 2048); - int id; + int id, err; unsigned int i; time_t s = time(NULL); @@ -352,8 +377,11 @@ void ida_check_random(void) ida_remove(&ida, bit); } else { __set_bit(bit, bitmap); - ida_pre_get(&ida, GFP_KERNEL); - assert(!ida_get_new_above(&ida, bit, &id)); + do { + ida_pre_get(&ida, GFP_KERNEL); + err = ida_get_new_above(&ida, bit, &id); + } while (err == -ENOMEM); + assert(!err); assert(id == bit); } } @@ -362,6 +390,24 @@ void ida_check_random(void) goto repeat; } +void ida_simple_get_remove_test(void) +{ + DEFINE_IDA(ida); + unsigned long i; + + for (i = 0; i < 10000; i++) { + assert(ida_simple_get(&ida, 0, 20000, GFP_KERNEL) == i); + } + assert(ida_simple_get(&ida, 5, 30, GFP_KERNEL) < 0); + + for (i = 0; i < 10000; i++) { + ida_simple_remove(&ida, i); + } + assert(ida_is_empty(&ida)); + + ida_destroy(&ida); +} + void ida_checks(void) { DEFINE_IDA(ida); @@ -428,15 +474,41 @@ void ida_checks(void) ida_check_max(); ida_check_conv(); ida_check_random(); + ida_simple_get_remove_test(); radix_tree_cpu_dead(1); } +static void *ida_random_fn(void *arg) +{ + rcu_register_thread(); + ida_check_random(); + rcu_unregister_thread(); + return NULL; +} + +void ida_thread_tests(void) +{ + pthread_t threads[10]; + int i; + + for (i = 0; i < ARRAY_SIZE(threads); i++) + if (pthread_create(&threads[i], NULL, ida_random_fn, NULL)) { + perror("creating ida thread"); + exit(1); + } + + while (i--) + pthread_join(threads[i], NULL); +} + int __weak main(void) { radix_tree_init(); idr_checks(); ida_checks(); + ida_thread_tests(); + radix_tree_cpu_dead(1); rcu_barrier(); if (nr_allocated) printf("nr_allocated = %d\n", nr_allocated); diff --git a/tools/testing/radix-tree/main.c b/tools/testing/radix-tree/main.c index b829127d5670..bc9a78449572 100644 --- a/tools/testing/radix-tree/main.c +++ b/tools/testing/radix-tree/main.c @@ -368,6 +368,7 @@ int main(int argc, char **argv) iteration_test(0, 10 + 90 * long_run); iteration_test(7, 10 + 90 * long_run); single_thread_tests(long_run); + ida_thread_tests(); /* Free any remaining preallocated nodes */ radix_tree_cpu_dead(0); diff --git a/tools/testing/radix-tree/tag_check.c b/tools/testing/radix-tree/tag_check.c index d4ff00989245..36dcf7d6945d 100644 --- a/tools/testing/radix-tree/tag_check.c +++ b/tools/testing/radix-tree/tag_check.c @@ -330,6 +330,34 @@ static void single_check(void) item_kill_tree(&tree); } +void radix_tree_clear_tags_test(void) +{ + unsigned long index; + struct radix_tree_node *node; + struct radix_tree_iter iter; + void **slot; + + RADIX_TREE(tree, GFP_KERNEL); + + item_insert(&tree, 0); + item_tag_set(&tree, 0, 0); + __radix_tree_lookup(&tree, 0, &node, &slot); + radix_tree_clear_tags(&tree, node, slot); + assert(item_tag_get(&tree, 0, 0) == 0); + + for (index = 0; index < 1000; index++) { + item_insert(&tree, index); + item_tag_set(&tree, index, 0); + } + + radix_tree_for_each_slot(slot, &tree, &iter, 0) { + radix_tree_clear_tags(&tree, iter.node, slot); + assert(item_tag_get(&tree, iter.index, 0) == 0); + } + + item_kill_tree(&tree); +} + void tag_check(void) { single_check(); @@ -347,4 +375,5 @@ void tag_check(void) thrash_tags(); rcu_barrier(); printv(2, "after thrash_tags: %d allocated\n", nr_allocated); + radix_tree_clear_tags_test(); } diff --git a/tools/testing/radix-tree/test.h b/tools/testing/radix-tree/test.h index b30e11d9d271..0f8220cc6166 100644 --- a/tools/testing/radix-tree/test.h +++ b/tools/testing/radix-tree/test.h @@ -36,6 +36,7 @@ void iteration_test(unsigned order, unsigned duration); void benchmark(void); void idr_checks(void); void ida_checks(void); +void ida_thread_tests(void); struct item * item_tag_set(struct radix_tree_root *root, unsigned long index, int tag); diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile index 4b498265dae6..67531f47781b 100644 --- a/tools/testing/selftests/bpf/Makefile +++ b/tools/testing/selftests/bpf/Makefile @@ -1,12 +1,14 @@ LIBDIR := ../../../lib BPFOBJ := $(LIBDIR)/bpf/bpf.o -CFLAGS += -Wall -O2 -lcap -I../../../include/uapi -I$(LIBDIR) +CFLAGS += -Wall -O2 -lcap -I../../../include/uapi -I$(LIBDIR) $(BPFOBJ) TEST_GEN_PROGS = test_verifier test_tag test_maps test_lru_map test_lpm_map TEST_PROGS := test_kmod.sh +all: $(TEST_GEN_PROGS) + .PHONY: all clean force # force a rebuild of BPFOBJ when its dependencies are updated diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c index e1f5b9eea1e8..d1555e4240c0 100644 --- a/tools/testing/selftests/bpf/test_verifier.c +++ b/tools/testing/selftests/bpf/test_verifier.c @@ -8,6 +8,8 @@ * License as published by the Free Software Foundation. */ +#include <asm/types.h> +#include <linux/types.h> #include <stdint.h> #include <stdio.h> #include <stdlib.h> @@ -4583,10 +4585,12 @@ static bool is_admin(void) cap_flag_value_t sysadmin = CAP_CLEAR; const cap_value_t cap_val = CAP_SYS_ADMIN; +#ifdef CAP_IS_SUPPORTED if (!CAP_IS_SUPPORTED(CAP_SETFCAP)) { perror("cap_get_flag"); return false; } +#endif caps = cap_get_proc(); if (!caps) { perror("cap_get_proc"); diff --git a/tools/testing/selftests/powerpc/harness.c b/tools/testing/selftests/powerpc/harness.c index 248a820048df..66d31de60b9a 100644 --- a/tools/testing/selftests/powerpc/harness.c +++ b/tools/testing/selftests/powerpc/harness.c @@ -114,9 +114,11 @@ int test_harness(int (test_function)(void), char *name) rc = run_test(test_function, name); - if (rc == MAGIC_SKIP_RETURN_VALUE) + if (rc == MAGIC_SKIP_RETURN_VALUE) { test_skip(name); - else + /* so that skipped test is not marked as failed */ + rc = 0; + } else test_finish(name, rc); return rc; diff --git a/tools/testing/selftests/powerpc/include/vsx_asm.h b/tools/testing/selftests/powerpc/include/vsx_asm.h index d828bfb6ef2d..54064ced9e95 100644 --- a/tools/testing/selftests/powerpc/include/vsx_asm.h +++ b/tools/testing/selftests/powerpc/include/vsx_asm.h @@ -16,56 +16,56 @@ */ FUNC_START(load_vsx) li r5,0 - lxvx vs20,r5,r3 + lxvd2x vs20,r5,r3 addi r5,r5,16 - lxvx vs21,r5,r3 + lxvd2x vs21,r5,r3 addi r5,r5,16 - lxvx vs22,r5,r3 + lxvd2x vs22,r5,r3 addi r5,r5,16 - lxvx vs23,r5,r3 + lxvd2x vs23,r5,r3 addi r5,r5,16 - lxvx vs24,r5,r3 + lxvd2x vs24,r5,r3 addi r5,r5,16 - lxvx vs25,r5,r3 + lxvd2x vs25,r5,r3 addi r5,r5,16 - lxvx vs26,r5,r3 + lxvd2x vs26,r5,r3 addi r5,r5,16 - lxvx vs27,r5,r3 + lxvd2x vs27,r5,r3 addi r5,r5,16 - lxvx vs28,r5,r3 + lxvd2x vs28,r5,r3 addi r5,r5,16 - lxvx vs29,r5,r3 + lxvd2x vs29,r5,r3 addi r5,r5,16 - lxvx vs30,r5,r3 + lxvd2x vs30,r5,r3 addi r5,r5,16 - lxvx vs31,r5,r3 + lxvd2x vs31,r5,r3 blr FUNC_END(load_vsx) FUNC_START(store_vsx) li r5,0 - stxvx vs20,r5,r3 + stxvd2x vs20,r5,r3 addi r5,r5,16 - stxvx vs21,r5,r3 + stxvd2x vs21,r5,r3 addi r5,r5,16 - stxvx vs22,r5,r3 + stxvd2x vs22,r5,r3 addi r5,r5,16 - stxvx vs23,r5,r3 + stxvd2x vs23,r5,r3 addi r5,r5,16 - stxvx vs24,r5,r3 + stxvd2x vs24,r5,r3 addi r5,r5,16 - stxvx vs25,r5,r3 + stxvd2x vs25,r5,r3 addi r5,r5,16 - stxvx vs26,r5,r3 + stxvd2x vs26,r5,r3 addi r5,r5,16 - stxvx vs27,r5,r3 + stxvd2x vs27,r5,r3 addi r5,r5,16 - stxvx vs28,r5,r3 + stxvd2x vs28,r5,r3 addi r5,r5,16 - stxvx vs29,r5,r3 + stxvd2x vs29,r5,r3 addi r5,r5,16 - stxvx vs30,r5,r3 + stxvd2x vs30,r5,r3 addi r5,r5,16 - stxvx vs31,r5,r3 + stxvd2x vs31,r5,r3 blr FUNC_END(store_vsx) diff --git a/tools/testing/selftests/vm/Makefile b/tools/testing/selftests/vm/Makefile index 4cff7e7ddcc4..41642ba5e318 100644 --- a/tools/testing/selftests/vm/Makefile +++ b/tools/testing/selftests/vm/Makefile @@ -1,5 +1,9 @@ # Makefile for vm selftests +ifndef OUTPUT + OUTPUT := $(shell pwd) +endif + CFLAGS = -Wall -I ../../../../usr/include $(EXTRA_CFLAGS) LDLIBS = -lrt TEST_GEN_FILES = compaction_test diff --git a/tools/testing/selftests/x86/fsgsbase.c b/tools/testing/selftests/x86/fsgsbase.c index 5b2b4b3c634c..b4967d875236 100644 --- a/tools/testing/selftests/x86/fsgsbase.c +++ b/tools/testing/selftests/x86/fsgsbase.c @@ -245,7 +245,7 @@ void do_unexpected_base(void) long ret; asm volatile ("int $0x80" : "=a" (ret) : "a" (243), "b" (low_desc) - : "flags"); + : "r8", "r9", "r10", "r11"); memcpy(&desc, low_desc, sizeof(desc)); munmap(low_desc, sizeof(desc)); diff --git a/tools/testing/selftests/x86/ldt_gdt.c b/tools/testing/selftests/x86/ldt_gdt.c index 4af47079cf04..f6121612e769 100644 --- a/tools/testing/selftests/x86/ldt_gdt.c +++ b/tools/testing/selftests/x86/ldt_gdt.c @@ -45,6 +45,12 @@ #define AR_DB (1 << 22) #define AR_G (1 << 23) +#ifdef __x86_64__ +# define INT80_CLOBBERS "r8", "r9", "r10", "r11" +#else +# define INT80_CLOBBERS +#endif + static int nerrs; /* Points to an array of 1024 ints, each holding its own index. */ @@ -588,7 +594,7 @@ static int invoke_set_thread_area(void) asm volatile ("int $0x80" : "=a" (ret), "+m" (low_user_desc) : "a" (243), "b" (low_user_desc) - : "flags"); + : INT80_CLOBBERS); return ret; } @@ -657,7 +663,7 @@ static void test_gdt_invalidation(void) "+a" (eax) : "m" (low_user_desc_clear), [arg1] "r" ((unsigned int)(unsigned long)low_user_desc_clear) - : "flags"); + : INT80_CLOBBERS); if (sel != 0) { result = "FAIL"; @@ -688,7 +694,7 @@ static void test_gdt_invalidation(void) "+a" (eax) : "m" (low_user_desc_clear), [arg1] "r" ((unsigned int)(unsigned long)low_user_desc_clear) - : "flags"); + : INT80_CLOBBERS); if (sel != 0) { result = "FAIL"; @@ -721,7 +727,7 @@ static void test_gdt_invalidation(void) "+a" (eax) : "m" (low_user_desc_clear), [arg1] "r" ((unsigned int)(unsigned long)low_user_desc_clear) - : "flags"); + : INT80_CLOBBERS); #ifdef __x86_64__ syscall(SYS_arch_prctl, ARCH_GET_FS, &new_base); @@ -774,7 +780,7 @@ static void test_gdt_invalidation(void) "+a" (eax) : "m" (low_user_desc_clear), [arg1] "r" ((unsigned int)(unsigned long)low_user_desc_clear) - : "flags"); + : INT80_CLOBBERS); #ifdef __x86_64__ syscall(SYS_arch_prctl, ARCH_GET_GS, &new_base); diff --git a/tools/testing/selftests/x86/ptrace_syscall.c b/tools/testing/selftests/x86/ptrace_syscall.c index b037ce9cf116..eaea92439708 100644 --- a/tools/testing/selftests/x86/ptrace_syscall.c +++ b/tools/testing/selftests/x86/ptrace_syscall.c @@ -58,7 +58,8 @@ static void do_full_int80(struct syscall_args32 *args) asm volatile ("int $0x80" : "+a" (args->nr), "+b" (args->arg0), "+c" (args->arg1), "+d" (args->arg2), - "+S" (args->arg3), "+D" (args->arg4), "+r" (bp)); + "+S" (args->arg3), "+D" (args->arg4), "+r" (bp) + : : "r8", "r9", "r10", "r11"); args->arg5 = bp; #else sys32_helper(args, int80_and_ret); diff --git a/tools/testing/selftests/x86/single_step_syscall.c b/tools/testing/selftests/x86/single_step_syscall.c index 50c26358e8b7..a48da95c18fd 100644 --- a/tools/testing/selftests/x86/single_step_syscall.c +++ b/tools/testing/selftests/x86/single_step_syscall.c @@ -56,9 +56,11 @@ static volatile sig_atomic_t sig_traps; #ifdef __x86_64__ # define REG_IP REG_RIP # define WIDTH "q" +# define INT80_CLOBBERS "r8", "r9", "r10", "r11" #else # define REG_IP REG_EIP # define WIDTH "l" +# define INT80_CLOBBERS #endif static unsigned long get_eflags(void) @@ -140,7 +142,8 @@ int main() printf("[RUN]\tSet TF and check int80\n"); set_eflags(get_eflags() | X86_EFLAGS_TF); - asm volatile ("int $0x80" : "=a" (tmp) : "a" (SYS_getpid)); + asm volatile ("int $0x80" : "=a" (tmp) : "a" (SYS_getpid) + : INT80_CLOBBERS); check_result(); /* diff --git a/virt/kvm/arm/vgic/vgic-its.c b/virt/kvm/arm/vgic/vgic-its.c index 571b64a01c50..8d1da1af4b09 100644 --- a/virt/kvm/arm/vgic/vgic-its.c +++ b/virt/kvm/arm/vgic/vgic-its.c @@ -360,29 +360,6 @@ static int its_sync_lpi_pending_table(struct kvm_vcpu *vcpu) return ret; } -static unsigned long vgic_mmio_read_its_ctlr(struct kvm *vcpu, - struct vgic_its *its, - gpa_t addr, unsigned int len) -{ - u32 reg = 0; - - mutex_lock(&its->cmd_lock); - if (its->creadr == its->cwriter) - reg |= GITS_CTLR_QUIESCENT; - if (its->enabled) - reg |= GITS_CTLR_ENABLE; - mutex_unlock(&its->cmd_lock); - - return reg; -} - -static void vgic_mmio_write_its_ctlr(struct kvm *kvm, struct vgic_its *its, - gpa_t addr, unsigned int len, - unsigned long val) -{ - its->enabled = !!(val & GITS_CTLR_ENABLE); -} - static unsigned long vgic_mmio_read_its_typer(struct kvm *kvm, struct vgic_its *its, gpa_t addr, unsigned int len) @@ -1161,33 +1138,16 @@ static void vgic_mmio_write_its_cbaser(struct kvm *kvm, struct vgic_its *its, #define ITS_CMD_SIZE 32 #define ITS_CMD_OFFSET(reg) ((reg) & GENMASK(19, 5)) -/* - * By writing to CWRITER the guest announces new commands to be processed. - * To avoid any races in the first place, we take the its_cmd lock, which - * protects our ring buffer variables, so that there is only one user - * per ITS handling commands at a given time. - */ -static void vgic_mmio_write_its_cwriter(struct kvm *kvm, struct vgic_its *its, - gpa_t addr, unsigned int len, - unsigned long val) +/* Must be called with the cmd_lock held. */ +static void vgic_its_process_commands(struct kvm *kvm, struct vgic_its *its) { gpa_t cbaser; u64 cmd_buf[4]; - u32 reg; - if (!its) - return; - - mutex_lock(&its->cmd_lock); - - reg = update_64bit_reg(its->cwriter, addr & 7, len, val); - reg = ITS_CMD_OFFSET(reg); - if (reg >= ITS_CMD_BUFFER_SIZE(its->cbaser)) { - mutex_unlock(&its->cmd_lock); + /* Commands are only processed when the ITS is enabled. */ + if (!its->enabled) return; - } - its->cwriter = reg; cbaser = CBASER_ADDRESS(its->cbaser); while (its->cwriter != its->creadr) { @@ -1207,6 +1167,34 @@ static void vgic_mmio_write_its_cwriter(struct kvm *kvm, struct vgic_its *its, if (its->creadr == ITS_CMD_BUFFER_SIZE(its->cbaser)) its->creadr = 0; } +} + +/* + * By writing to CWRITER the guest announces new commands to be processed. + * To avoid any races in the first place, we take the its_cmd lock, which + * protects our ring buffer variables, so that there is only one user + * per ITS handling commands at a given time. + */ +static void vgic_mmio_write_its_cwriter(struct kvm *kvm, struct vgic_its *its, + gpa_t addr, unsigned int len, + unsigned long val) +{ + u64 reg; + + if (!its) + return; + + mutex_lock(&its->cmd_lock); + + reg = update_64bit_reg(its->cwriter, addr & 7, len, val); + reg = ITS_CMD_OFFSET(reg); + if (reg >= ITS_CMD_BUFFER_SIZE(its->cbaser)) { + mutex_unlock(&its->cmd_lock); + return; + } + its->cwriter = reg; + + vgic_its_process_commands(kvm, its); mutex_unlock(&its->cmd_lock); } @@ -1287,6 +1275,39 @@ static void vgic_mmio_write_its_baser(struct kvm *kvm, *regptr = reg; } +static unsigned long vgic_mmio_read_its_ctlr(struct kvm *vcpu, + struct vgic_its *its, + gpa_t addr, unsigned int len) +{ + u32 reg = 0; + + mutex_lock(&its->cmd_lock); + if (its->creadr == its->cwriter) + reg |= GITS_CTLR_QUIESCENT; + if (its->enabled) + reg |= GITS_CTLR_ENABLE; + mutex_unlock(&its->cmd_lock); + + return reg; +} + +static void vgic_mmio_write_its_ctlr(struct kvm *kvm, struct vgic_its *its, + gpa_t addr, unsigned int len, + unsigned long val) +{ + mutex_lock(&its->cmd_lock); + + its->enabled = !!(val & GITS_CTLR_ENABLE); + + /* + * Try to process any pending commands. This function bails out early + * if the ITS is disabled or no commands have been queued. + */ + vgic_its_process_commands(kvm, its); + + mutex_unlock(&its->cmd_lock); +} + #define REGISTER_ITS_DESC(off, rd, wr, length, acc) \ { \ .reg_offset = off, \ diff --git a/virt/kvm/arm/vgic/vgic-mmio.c b/virt/kvm/arm/vgic/vgic-mmio.c index 3654b4c835ef..2a5db1352722 100644 --- a/virt/kvm/arm/vgic/vgic-mmio.c +++ b/virt/kvm/arm/vgic/vgic-mmio.c @@ -180,21 +180,37 @@ unsigned long vgic_mmio_read_active(struct kvm_vcpu *vcpu, static void vgic_mmio_change_active(struct kvm_vcpu *vcpu, struct vgic_irq *irq, bool new_active_state) { + struct kvm_vcpu *requester_vcpu; spin_lock(&irq->irq_lock); + + /* + * The vcpu parameter here can mean multiple things depending on how + * this function is called; when handling a trap from the kernel it + * depends on the GIC version, and these functions are also called as + * part of save/restore from userspace. + * + * Therefore, we have to figure out the requester in a reliable way. + * + * When accessing VGIC state from user space, the requester_vcpu is + * NULL, which is fine, because we guarantee that no VCPUs are running + * when accessing VGIC state from user space so irq->vcpu->cpu is + * always -1. + */ + requester_vcpu = kvm_arm_get_running_vcpu(); + /* * If this virtual IRQ was written into a list register, we * have to make sure the CPU that runs the VCPU thread has - * synced back LR state to the struct vgic_irq. We can only - * know this for sure, when either this irq is not assigned to - * anyone's AP list anymore, or the VCPU thread is not - * running on any CPUs. + * synced back the LR state to the struct vgic_irq. * - * In the opposite case, we know the VCPU thread may be on its - * way back from the guest and still has to sync back this - * IRQ, so we release and re-acquire the spin_lock to let the - * other thread sync back the IRQ. + * As long as the conditions below are true, we know the VCPU thread + * may be on its way back from the guest (we kicked the VCPU thread in + * vgic_change_active_prepare) and still has to sync back this IRQ, + * so we release and re-acquire the spin_lock to let the other thread + * sync back the IRQ. */ while (irq->vcpu && /* IRQ may have state in an LR somewhere */ + irq->vcpu != requester_vcpu && /* Current thread is not the VCPU thread */ irq->vcpu->cpu != -1) /* VCPU thread is running */ cond_resched_lock(&irq->irq_lock); diff --git a/virt/kvm/arm/vgic/vgic-v3.c b/virt/kvm/arm/vgic/vgic-v3.c index edc6ee2dc852..be0f4c3e0142 100644 --- a/virt/kvm/arm/vgic/vgic-v3.c +++ b/virt/kvm/arm/vgic/vgic-v3.c @@ -229,10 +229,13 @@ void vgic_v3_enable(struct kvm_vcpu *vcpu) /* * If we are emulating a GICv3, we do it in an non-GICv2-compatible * way, so we force SRE to 1 to demonstrate this to the guest. + * Also, we don't support any form of IRQ/FIQ bypass. * This goes with the spec allowing the value to be RAO/WI. */ if (vcpu->kvm->arch.vgic.vgic_model == KVM_DEV_TYPE_ARM_VGIC_V3) { - vgic_v3->vgic_sre = ICC_SRE_EL1_SRE; + vgic_v3->vgic_sre = (ICC_SRE_EL1_DIB | + ICC_SRE_EL1_DFB | + ICC_SRE_EL1_SRE); vcpu->arch.vgic_cpu.pendbaser = INITIAL_PENDBASER_VALUE; } else { vgic_v3->vgic_sre = 0; |