diff options
828 files changed, 19670 insertions, 8403 deletions
@@ -68,6 +68,8 @@ Jacob Shin <Jacob.Shin@amd.com> James Bottomley <jejb@mulgrave.(none)> James Bottomley <jejb@titanic.il.steeleye.com> James E Wilson <wilson@specifix.com> +James Hogan <jhogan@kernel.org> <james.hogan@imgtec.com> +James Hogan <jhogan@kernel.org> <james@albanarts.com> James Ketrenos <jketreno@io.(none)> Javi Merino <javi.merino@kernel.org> <javi.merino@arm.com> <javier@osg.samsung.com> <javier.martinez@collabora.co.uk> diff --git a/Documentation/ABI/testing/sysfs-power b/Documentation/ABI/testing/sysfs-power index 713cab1d5f12..a1d1612f3651 100644 --- a/Documentation/ABI/testing/sysfs-power +++ b/Documentation/ABI/testing/sysfs-power @@ -127,7 +127,7 @@ Description: What; /sys/power/pm_trace_dev_match Date: October 2010 -Contact: James Hogan <james@albanarts.com> +Contact: James Hogan <jhogan@kernel.org> Description: The /sys/power/pm_trace_dev_match file contains the name of the device associated with the last PM event point saved in the RTC diff --git a/Documentation/core-api/workqueue.rst b/Documentation/core-api/workqueue.rst index 3943b5bfa8cf..00a5ba51e63f 100644 --- a/Documentation/core-api/workqueue.rst +++ b/Documentation/core-api/workqueue.rst @@ -39,8 +39,8 @@ up. Although MT wq wasted a lot of resource, the level of concurrency provided was unsatisfactory. The limitation was common to both ST and MT wq albeit less severe on MT. Each wq maintained its own separate -worker pool. A MT wq could provide only one execution context per CPU -while a ST wq one for the whole system. Work items had to compete for +worker pool. An MT wq could provide only one execution context per CPU +while an ST wq one for the whole system. Work items had to compete for those very limited execution contexts leading to various problems including proneness to deadlocks around the single execution context. @@ -151,7 +151,7 @@ Application Programming Interface (API) ``alloc_workqueue()`` allocates a wq. The original ``create_*workqueue()`` functions are deprecated and scheduled for -removal. ``alloc_workqueue()`` takes three arguments - @``name``, +removal. ``alloc_workqueue()`` takes three arguments - ``@name``, ``@flags`` and ``@max_active``. ``@name`` is the name of the wq and also used as the name of the rescuer thread if there is one. @@ -197,7 +197,7 @@ resources, scheduled and executed. served by worker threads with elevated nice level. Note that normal and highpri worker-pools don't interact with - each other. Each maintain its separate pool of workers and + each other. Each maintains its separate pool of workers and implements concurrency management among its workers. ``WQ_CPU_INTENSIVE`` @@ -249,8 +249,8 @@ unbound worker-pools and only one work item could be active at any given time thus achieving the same ordering property as ST wq. In the current implementation the above configuration only guarantees -ST behavior within a given NUMA node. Instead alloc_ordered_queue should -be used to achieve system wide ST behavior. +ST behavior within a given NUMA node. Instead ``alloc_ordered_queue()`` should +be used to achieve system-wide ST behavior. Example Execution Scenarios diff --git a/Documentation/cpu-freq/index.txt b/Documentation/cpu-freq/index.txt index 03a7cee6ac73..c15e75386a05 100644 --- a/Documentation/cpu-freq/index.txt +++ b/Documentation/cpu-freq/index.txt @@ -32,8 +32,6 @@ cpufreq-stats.txt - General description of sysfs cpufreq stats. index.txt - File index, Mailing list and Links (this document) -intel-pstate.txt - Intel pstate cpufreq driver specific file. - pcc-cpufreq.txt - PCC cpufreq driver specific file. diff --git a/Documentation/device-mapper/dm-raid.txt b/Documentation/device-mapper/dm-raid.txt index 4a0a7469fdd7..32df07e29f68 100644 --- a/Documentation/device-mapper/dm-raid.txt +++ b/Documentation/device-mapper/dm-raid.txt @@ -344,3 +344,4 @@ Version History (wrong raid10_copies/raid10_format sequence) 1.11.1 Add raid4/5/6 journal write-back support via journal_mode option 1.12.1 fix for MD deadlock between mddev_suspend() and md_write_start() available +1.13.0 Fix dev_health status at end of "recover" (was 'a', now 'A') diff --git a/Documentation/devicetree/bindings/leds/ams,as3645a.txt b/Documentation/devicetree/bindings/leds/ams,as3645a.txt index 12c5ef26ec73..fdc40e354a64 100644 --- a/Documentation/devicetree/bindings/leds/ams,as3645a.txt +++ b/Documentation/devicetree/bindings/leds/ams,as3645a.txt @@ -15,11 +15,14 @@ Required properties compatible : Must be "ams,as3645a". reg : The I2C address of the device. Typically 0x30. +#address-cells : 1 +#size-cells : 0 -Required properties of the "flash" child node -============================================= +Required properties of the flash child node (0) +=============================================== +reg: 0 flash-timeout-us: Flash timeout in microseconds. The value must be in the range [100000, 850000] and divisible by 50000. flash-max-microamp: Maximum flash current in microamperes. Has to be @@ -33,20 +36,21 @@ ams,input-max-microamp: Maximum flash controller input current. The and divisible by 50000. -Optional properties of the "flash" child node -============================================= +Optional properties of the flash child node +=========================================== label : The label of the flash LED. -Required properties of the "indicator" child node -================================================= +Required properties of the indicator child node (1) +=================================================== +reg: 1 led-max-microamp: Maximum indicator current. The allowed values are 2500, 5000, 7500 and 10000. -Optional properties of the "indicator" child node -================================================= +Optional properties of the indicator child node +=============================================== label : The label of the indicator LED. @@ -55,16 +59,20 @@ Example ======= as3645a@30 { + #address-cells: 1 + #size-cells: 0 reg = <0x30>; compatible = "ams,as3645a"; - flash { + flash@0 { + reg = <0x0>; flash-timeout-us = <150000>; flash-max-microamp = <320000>; led-max-microamp = <60000>; ams,input-max-microamp = <1750000>; label = "as3645a:flash"; }; - indicator { + indicator@1 { + reg = <0x1>; led-max-microamp = <10000>; label = "as3645a:indicator"; }; diff --git a/Documentation/devicetree/bindings/mmc/marvell,xenon-sdhci.txt b/Documentation/devicetree/bindings/mmc/marvell,xenon-sdhci.txt index b878a1e305af..ed1456f5c94d 100644 --- a/Documentation/devicetree/bindings/mmc/marvell,xenon-sdhci.txt +++ b/Documentation/devicetree/bindings/mmc/marvell,xenon-sdhci.txt @@ -16,11 +16,13 @@ Required Properties: - clocks: Array of clocks required for SDHC. - Require at least input clock for Xenon IP core. + Require at least input clock for Xenon IP core. For Armada AP806 and + CP110, the AXI clock is also mandatory. - clock-names: Array of names corresponding to clocks property. The input clock for Xenon IP core should be named as "core". + The input clock for the AXI bus must be named as "axi". - reg: * For "marvell,armada-3700-sdhci", two register areas. @@ -106,8 +108,8 @@ Example: compatible = "marvell,armada-ap806-sdhci"; reg = <0xaa0000 0x1000>; interrupts = <GIC_SPI 13 IRQ_TYPE_LEVEL_HIGH> - clocks = <&emmc_clk>; - clock-names = "core"; + clocks = <&emmc_clk>,<&axi_clk>; + clock-names = "core", "axi"; bus-width = <4>; marvell,xenon-phy-slow-mode; marvell,xenon-tun-count = <11>; @@ -126,8 +128,8 @@ Example: interrupts = <GIC_SPI 55 IRQ_TYPE_LEVEL_HIGH> vqmmc-supply = <&sd_vqmmc_regulator>; vmmc-supply = <&sd_vmmc_regulator>; - clocks = <&sdclk>; - clock-names = "core"; + clocks = <&sdclk>, <&axi_clk>; + clock-names = "core", "axi"; bus-width = <4>; marvell,xenon-tun-count = <9>; }; diff --git a/Documentation/devicetree/bindings/net/marvell-pp2.txt b/Documentation/devicetree/bindings/net/marvell-pp2.txt index 7e2dad08a12e..1814fa13f6ab 100644 --- a/Documentation/devicetree/bindings/net/marvell-pp2.txt +++ b/Documentation/devicetree/bindings/net/marvell-pp2.txt @@ -21,8 +21,9 @@ Required properties: - 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). + - AXI clock (only for armada-7k-pp2) +- clock-names: names of used clocks, must be "pp_clk", "gop_clk", "mg_clk" + and "axi_clk" (the 2 latter only for armada-7k-pp2). The ethernet ports are represented by subnodes. At least one port is required. @@ -78,8 +79,9 @@ 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"; + clocks = <&cpm_syscon0 1 3>, <&cpm_syscon0 1 9>, + <&cpm_syscon0 1 5>, <&cpm_syscon0 1 18>; + clock-names = "pp_clk", "gop_clk", "gp_clk", "axi_clk"; eth0: eth0 { interrupts = <ICU_GRP_NSR 39 IRQ_TYPE_LEVEL_HIGH>, diff --git a/Documentation/devicetree/bindings/net/rockchip-dwmac.txt b/Documentation/devicetree/bindings/net/rockchip-dwmac.txt index 6af8eed1adeb..9c16ee2965a2 100644 --- a/Documentation/devicetree/bindings/net/rockchip-dwmac.txt +++ b/Documentation/devicetree/bindings/net/rockchip-dwmac.txt @@ -4,6 +4,7 @@ The device node has following properties. Required properties: - compatible: should be "rockchip,<name>-gamc" + "rockchip,rk3128-gmac": found on RK312x SoCs "rockchip,rk3228-gmac": found on RK322x SoCs "rockchip,rk3288-gmac": found on RK3288 SoCs "rockchip,rk3328-gmac": found on RK3328 SoCs diff --git a/Documentation/devicetree/bindings/reset/snps,hsdk-reset.txt b/Documentation/devicetree/bindings/reset/snps,hsdk-reset.txt new file mode 100644 index 000000000000..830069b1c37c --- /dev/null +++ b/Documentation/devicetree/bindings/reset/snps,hsdk-reset.txt @@ -0,0 +1,28 @@ +Binding for the Synopsys HSDK reset controller + +This binding uses the common reset binding[1]. + +[1] Documentation/devicetree/bindings/reset/reset.txt + +Required properties: +- compatible: should be "snps,hsdk-reset". +- reg: should always contain 2 pairs address - length: first for reset + configuration register and second for corresponding SW reset and status bits + register. +- #reset-cells: from common reset binding; Should always be set to 1. + +Example: + reset: reset@880 { + compatible = "snps,hsdk-reset"; + #reset-cells = <1>; + reg = <0x8A0 0x4>, <0xFF0 0x4>; + }; + +Specifying reset lines connected to IP modules: + ethernet@.... { + .... + resets = <&reset HSDK_V1_ETH_RESET>; + .... + }; + +The index could be found in <dt-bindings/reset/snps,hsdk-reset.h> diff --git a/Documentation/devicetree/bindings/serial/renesas,sci-serial.txt b/Documentation/devicetree/bindings/serial/renesas,sci-serial.txt index 4fc96946f81d..cf504d0380ae 100644 --- a/Documentation/devicetree/bindings/serial/renesas,sci-serial.txt +++ b/Documentation/devicetree/bindings/serial/renesas,sci-serial.txt @@ -41,6 +41,8 @@ Required properties: - "renesas,hscif-r8a7795" for R8A7795 (R-Car H3) HSCIF compatible UART. - "renesas,scif-r8a7796" for R8A7796 (R-Car M3-W) SCIF compatible UART. - "renesas,hscif-r8a7796" for R8A7796 (R-Car M3-W) HSCIF compatible UART. + - "renesas,scif-r8a77970" for R8A77970 (R-Car V3M) SCIF compatible UART. + - "renesas,hscif-r8a77970" for R8A77970 (R-Car V3M) HSCIF compatible UART. - "renesas,scif-r8a77995" for R8A77995 (R-Car D3) SCIF compatible UART. - "renesas,hscif-r8a77995" for R8A77995 (R-Car D3) HSCIF compatible UART. - "renesas,scifa-sh73a0" for SH73A0 (SH-Mobile AG5) SCIFA compatible UART. diff --git a/Documentation/driver-model/driver.txt b/Documentation/driver-model/driver.txt index 4421135826a2..d661e6f7e6a0 100644 --- a/Documentation/driver-model/driver.txt +++ b/Documentation/driver-model/driver.txt @@ -196,12 +196,13 @@ struct driver_attribute { }; Device drivers can export attributes via their sysfs directories. -Drivers can declare attributes using a DRIVER_ATTR macro that works -identically to the DEVICE_ATTR macro. +Drivers can declare attributes using a DRIVER_ATTR_RW and DRIVER_ATTR_RO +macro that works identically to the DEVICE_ATTR_RW and DEVICE_ATTR_RO +macros. Example: -DRIVER_ATTR(debug,0644,show_debug,store_debug); +DRIVER_ATTR_RW(debug); This is equivalent to declaring: diff --git a/Documentation/filesystems/overlayfs.txt b/Documentation/filesystems/overlayfs.txt index 36f528a7fdd6..8caa60734647 100644 --- a/Documentation/filesystems/overlayfs.txt +++ b/Documentation/filesystems/overlayfs.txt @@ -210,8 +210,11 @@ path as another overlay mount and it may use a lower layer path that is beneath or above the path of another overlay lower layer path. Using an upper layer path and/or a workdir path that are already used by -another overlay mount is not allowed and will fail with EBUSY. Using +another overlay mount is not allowed and may fail with EBUSY. Using partially overlapping paths is not allowed but will not fail with EBUSY. +If files are accessed from two overlayfs mounts which share or overlap the +upper layer and/or workdir path the behavior of the overlay is undefined, +though it will not result in a crash or deadlock. Mounting an overlay using an upper layer path, where the upper layer path was previously used by another mounted overlay in combination with a diff --git a/Documentation/filesystems/sysfs.txt b/Documentation/filesystems/sysfs.txt index 24da7b32c489..9a3658cc399e 100644 --- a/Documentation/filesystems/sysfs.txt +++ b/Documentation/filesystems/sysfs.txt @@ -366,7 +366,8 @@ struct driver_attribute { Declaring: -DRIVER_ATTR(_name, _mode, _show, _store) +DRIVER_ATTR_RO(_name) +DRIVER_ATTR_RW(_name) Creation/Removal: diff --git a/Documentation/i2c/busses/i2c-i801 b/Documentation/i2c/busses/i2c-i801 index 0500193434cb..d47702456926 100644 --- a/Documentation/i2c/busses/i2c-i801 +++ b/Documentation/i2c/busses/i2c-i801 @@ -36,6 +36,7 @@ Supported adapters: * Intel Gemini Lake (SOC) * Intel Cannon Lake-H (PCH) * Intel Cannon Lake-LP (PCH) + * Intel Cedar Fork (PCH) Datasheets: Publicly available at the Intel website On Intel Patsburg and later chipsets, both the normal host SMBus controller diff --git a/MAINTAINERS b/MAINTAINERS index 6671f375f7fc..f1688510178a 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -5259,7 +5259,8 @@ S: Maintained F: drivers/iommu/exynos-iommu.c EZchip NPS platform support -M: Noam Camus <noamc@ezchip.com> +M: Elad Kanfi <eladkan@mellanox.com> +M: Vineet Gupta <vgupta@synopsys.com> S: Supported F: arch/arc/plat-eznps F: arch/arc/boot/dts/eznps.dts @@ -6738,7 +6739,7 @@ F: Documentation/devicetree/bindings/auxdisplay/img-ascii-lcd.txt F: drivers/auxdisplay/img-ascii-lcd.c IMGTEC IR DECODER DRIVER -M: James Hogan <james.hogan@imgtec.com> +M: James Hogan <jhogan@kernel.org> S: Maintained F: drivers/media/rc/img-ir/ @@ -6774,8 +6775,6 @@ F: drivers/ipack/ INFINIBAND SUBSYSTEM M: Doug Ledford <dledford@redhat.com> -M: Sean Hefty <sean.hefty@intel.com> -M: Hal Rosenstock <hal.rosenstock@gmail.com> L: linux-rdma@vger.kernel.org W: http://www.openfabrics.org/ Q: http://patchwork.kernel.org/project/linux-rdma/list/ @@ -7562,7 +7561,7 @@ F: arch/arm64/include/asm/kvm* F: arch/arm64/kvm/ KERNEL VIRTUAL MACHINE FOR MIPS (KVM/mips) -M: James Hogan <james.hogan@imgtec.com> +M: James Hogan <jhogan@kernel.org> L: linux-mips@linux-mips.org S: Supported F: arch/mips/include/uapi/asm/kvm* @@ -8264,6 +8263,12 @@ L: libertas-dev@lists.infradead.org S: Orphan F: drivers/net/wireless/marvell/libertas/ +MARVELL MACCHIATOBIN SUPPORT +M: Russell King <rmk@armlinux.org.uk> +L: linux-arm-kernel@lists.infradead.org +S: Maintained +F: arch/arm64/boot/dts/marvell/armada-8040-mcbin.dts + MARVELL MV643XX ETHERNET DRIVER M: Sebastian Hesselbarth <sebastian.hesselbarth@gmail.com> L: netdev@vger.kernel.org @@ -8597,6 +8602,12 @@ M: Sean Wang <sean.wang@mediatek.com> S: Maintained F: drivers/media/rc/mtk-cir.c +MEDIATEK PMIC LED DRIVER +M: Sean Wang <sean.wang@mediatek.com> +S: Maintained +F: drivers/leds/leds-mt6323.c +F: Documentation/devicetree/bindings/leds/leds-mt6323.txt + MEDIATEK ETHERNET DRIVER M: Felix Fietkau <nbd@openwrt.org> M: John Crispin <john@phrozen.org> @@ -8879,7 +8890,7 @@ F: Documentation/devicetree/bindings/media/meson-ao-cec.txt T: git git://linuxtv.org/media_tree.git METAG ARCHITECTURE -M: James Hogan <james.hogan@imgtec.com> +M: James Hogan <jhogan@kernel.org> L: linux-metag@vger.kernel.org T: git git://git.kernel.org/pub/scm/linux/kernel/git/jhogan/metag.git S: Odd Fixes @@ -9348,7 +9359,7 @@ NETWORK BLOCK DEVICE (NBD) M: Josef Bacik <jbacik@fb.com> S: Maintained L: linux-block@vger.kernel.org -L: nbd-general@lists.sourceforge.net +L: nbd@other.debian.org F: Documentation/blockdev/nbd.txt F: drivers/block/nbd.c F: include/uapi/linux/nbd.h @@ -11068,6 +11079,7 @@ F: drivers/net/ethernet/qlogic/qede/ QLOGIC QL4xxx RDMA DRIVER M: Ram Amrani <Ram.Amrani@cavium.com> +M: Michal Kalderon <Michal.Kalderon@cavium.com> M: Ariel Elior <Ariel.Elior@cavium.com> L: linux-rdma@vger.kernel.org S: Supported @@ -12925,9 +12937,9 @@ F: drivers/mmc/host/dw_mmc* SYNOPSYS HSDK RESET CONTROLLER DRIVER M: Eugeniy Paltsev <Eugeniy.Paltsev@synopsys.com> S: Supported -F: drivers/reset/reset-hsdk-v1.c -F: include/dt-bindings/reset/snps,hsdk-v1-reset.h -F: Documentation/devicetree/bindings/reset/snps,hsdk-v1-reset.txt +F: drivers/reset/reset-hsdk.c +F: include/dt-bindings/reset/snps,hsdk-reset.h +F: Documentation/devicetree/bindings/reset/snps,hsdk-reset.txt SYSTEM CONFIGURATION (SYSCON) M: Lee Jones <lee.jones@linaro.org> @@ -1,7 +1,7 @@ VERSION = 4 PATCHLEVEL = 14 SUBLEVEL = 0 -EXTRAVERSION = -rc2 +EXTRAVERSION = -rc4 NAME = Fearless Coyote # *DOCUMENTATION* @@ -1172,11 +1172,11 @@ headers_check: headers_install PHONY += kselftest kselftest: - $(Q)$(MAKE) -C tools/testing/selftests run_tests + $(Q)$(MAKE) -C $(srctree)/tools/testing/selftests run_tests PHONY += kselftest-clean kselftest-clean: - $(Q)$(MAKE) -C tools/testing/selftests clean + $(Q)$(MAKE) -C $(srctree)/tools/testing/selftests clean PHONY += kselftest-merge kselftest-merge: diff --git a/arch/alpha/include/asm/mmu_context.h b/arch/alpha/include/asm/mmu_context.h index 384bd47b5187..45c020a0fe76 100644 --- a/arch/alpha/include/asm/mmu_context.h +++ b/arch/alpha/include/asm/mmu_context.h @@ -8,6 +8,7 @@ */ #include <linux/mm_types.h> +#include <linux/sched.h> #include <asm/machvec.h> #include <asm/compiler.h> diff --git a/arch/arc/Kconfig b/arch/arc/Kconfig index a598641eed98..c84e67fdea09 100644 --- a/arch/arc/Kconfig +++ b/arch/arc/Kconfig @@ -24,7 +24,7 @@ config ARC select GENERIC_SMP_IDLE_THREAD select HAVE_ARCH_KGDB select HAVE_ARCH_TRACEHOOK - select HAVE_FUTEX_CMPXCHG + select HAVE_FUTEX_CMPXCHG if FUTEX select HAVE_IOREMAP_PROT select HAVE_KPROBES select HAVE_KRETPROBES diff --git a/arch/arc/Makefile b/arch/arc/Makefile index 3a4b52b7e09d..d37f49d6a27f 100644 --- a/arch/arc/Makefile +++ b/arch/arc/Makefile @@ -6,8 +6,6 @@ # published by the Free Software Foundation. # -UTS_MACHINE := arc - ifeq ($(CROSS_COMPILE),) ifndef CONFIG_CPU_BIG_ENDIAN CROSS_COMPILE := arc-linux- diff --git a/arch/arc/boot/dts/axs10x_mb.dtsi b/arch/arc/boot/dts/axs10x_mb.dtsi index 2367a67c5f10..e114000a84f5 100644 --- a/arch/arc/boot/dts/axs10x_mb.dtsi +++ b/arch/arc/boot/dts/axs10x_mb.dtsi @@ -44,7 +44,14 @@ mmcclk: mmcclk { compatible = "fixed-clock"; - clock-frequency = <50000000>; + /* + * DW sdio controller has external ciu clock divider + * controlled via register in SDIO IP. It divides + * sdio_ref_clk (which comes from CGU) by 16 for + * default. So default mmcclk clock (which comes + * to sdk_in) is 25000000 Hz. + */ + clock-frequency = <25000000>; #clock-cells = <0>; }; diff --git a/arch/arc/boot/dts/hsdk.dts b/arch/arc/boot/dts/hsdk.dts index 229d13adbce4..8adde1b492f1 100644 --- a/arch/arc/boot/dts/hsdk.dts +++ b/arch/arc/boot/dts/hsdk.dts @@ -12,6 +12,7 @@ /dts-v1/; #include <dt-bindings/net/ti-dp83867.h> +#include <dt-bindings/reset/snps,hsdk-reset.h> / { model = "snps,hsdk"; @@ -57,10 +58,10 @@ }; }; - core_clk: core-clk { + input_clk: input-clk { #clock-cells = <0>; compatible = "fixed-clock"; - clock-frequency = <500000000>; + clock-frequency = <33333333>; }; cpu_intc: cpu-interrupt-controller { @@ -102,6 +103,19 @@ ranges = <0x00000000 0xf0000000 0x10000000>; + cgu_rst: reset-controller@8a0 { + compatible = "snps,hsdk-reset"; + #reset-cells = <1>; + reg = <0x8A0 0x4>, <0xFF0 0x4>; + }; + + core_clk: core-clk@0 { + compatible = "snps,hsdk-core-pll-clock"; + reg = <0x00 0x10>, <0x14B8 0x4>; + #clock-cells = <0>; + clocks = <&input_clk>; + }; + serial: serial@5000 { compatible = "snps,dw-apb-uart"; reg = <0x5000 0x100>; @@ -120,7 +134,17 @@ mmcclk_ciu: mmcclk-ciu { compatible = "fixed-clock"; - clock-frequency = <100000000>; + /* + * DW sdio controller has external ciu clock divider + * controlled via register in SDIO IP. Due to its + * unexpected default value (it should devide by 1 + * but it devides by 8) SDIO IP uses wrong clock and + * works unstable (see STAR 9001204800) + * So add temporary fix and change clock frequency + * from 100000000 to 12500000 Hz until we fix dw sdio + * driver itself. + */ + clock-frequency = <12500000>; #clock-cells = <0>; }; @@ -141,6 +165,8 @@ clocks = <&gmacclk>; clock-names = "stmmaceth"; phy-handle = <&phy0>; + resets = <&cgu_rst HSDK_ETH_RESET>; + reset-names = "stmmaceth"; mdio { #address-cells = <1>; diff --git a/arch/arc/configs/axs101_defconfig b/arch/arc/configs/axs101_defconfig index 6980b966a364..ec7c849a5c8e 100644 --- a/arch/arc/configs/axs101_defconfig +++ b/arch/arc/configs/axs101_defconfig @@ -105,7 +105,7 @@ CONFIG_NLS_ISO8859_1=y # CONFIG_ENABLE_WARN_DEPRECATED is not set # CONFIG_ENABLE_MUST_CHECK is not set CONFIG_STRIP_ASM_SYMS=y -CONFIG_LOCKUP_DETECTOR=y +CONFIG_SOFTLOCKUP_DETECTOR=y CONFIG_DEFAULT_HUNG_TASK_TIMEOUT=10 # CONFIG_SCHED_DEBUG is not set # CONFIG_DEBUG_PREEMPT is not set diff --git a/arch/arc/configs/axs103_defconfig b/arch/arc/configs/axs103_defconfig index 2233f5777a71..63d3cf69e0b0 100644 --- a/arch/arc/configs/axs103_defconfig +++ b/arch/arc/configs/axs103_defconfig @@ -104,7 +104,7 @@ CONFIG_NLS_ISO8859_1=y # CONFIG_ENABLE_WARN_DEPRECATED is not set # CONFIG_ENABLE_MUST_CHECK is not set CONFIG_STRIP_ASM_SYMS=y -CONFIG_LOCKUP_DETECTOR=y +CONFIG_SOFTLOCKUP_DETECTOR=y CONFIG_DEFAULT_HUNG_TASK_TIMEOUT=10 # CONFIG_SCHED_DEBUG is not set # CONFIG_DEBUG_PREEMPT is not set diff --git a/arch/arc/configs/axs103_smp_defconfig b/arch/arc/configs/axs103_smp_defconfig index 30a3d4cf53d2..f613ecac14a7 100644 --- a/arch/arc/configs/axs103_smp_defconfig +++ b/arch/arc/configs/axs103_smp_defconfig @@ -107,7 +107,7 @@ CONFIG_NLS_ISO8859_1=y # CONFIG_ENABLE_WARN_DEPRECATED is not set # CONFIG_ENABLE_MUST_CHECK is not set CONFIG_STRIP_ASM_SYMS=y -CONFIG_LOCKUP_DETECTOR=y +CONFIG_SOFTLOCKUP_DETECTOR=y CONFIG_DEFAULT_HUNG_TASK_TIMEOUT=10 # CONFIG_SCHED_DEBUG is not set # CONFIG_DEBUG_PREEMPT is not set diff --git a/arch/arc/configs/haps_hs_smp_defconfig b/arch/arc/configs/haps_hs_smp_defconfig index 821a2e562f3f..3507be2af6fe 100644 --- a/arch/arc/configs/haps_hs_smp_defconfig +++ b/arch/arc/configs/haps_hs_smp_defconfig @@ -84,5 +84,5 @@ CONFIG_TMPFS=y CONFIG_NFS_FS=y # CONFIG_ENABLE_WARN_DEPRECATED is not set # CONFIG_ENABLE_MUST_CHECK is not set -CONFIG_LOCKUP_DETECTOR=y +CONFIG_SOFTLOCKUP_DETECTOR=y # CONFIG_DEBUG_PREEMPT is not set diff --git a/arch/arc/configs/hsdk_defconfig b/arch/arc/configs/hsdk_defconfig index 9a3fcf446388..15f0f6b5fec1 100644 --- a/arch/arc/configs/hsdk_defconfig +++ b/arch/arc/configs/hsdk_defconfig @@ -63,6 +63,7 @@ CONFIG_MMC_SDHCI=y CONFIG_MMC_SDHCI_PLTFM=y CONFIG_MMC_DW=y # CONFIG_IOMMU_SUPPORT is not set +CONFIG_RESET_HSDK=y CONFIG_EXT3_FS=y CONFIG_VFAT_FS=y CONFIG_TMPFS=y @@ -72,7 +73,7 @@ CONFIG_NLS_ISO8859_1=y # CONFIG_ENABLE_WARN_DEPRECATED is not set # CONFIG_ENABLE_MUST_CHECK is not set CONFIG_STRIP_ASM_SYMS=y -CONFIG_LOCKUP_DETECTOR=y +CONFIG_SOFTLOCKUP_DETECTOR=y CONFIG_DEFAULT_HUNG_TASK_TIMEOUT=10 # CONFIG_SCHED_DEBUG is not set # CONFIG_DEBUG_PREEMPT is not set diff --git a/arch/arc/configs/vdk_hs38_defconfig b/arch/arc/configs/vdk_hs38_defconfig index c0d6a010751a..4fcf4f2503f6 100644 --- a/arch/arc/configs/vdk_hs38_defconfig +++ b/arch/arc/configs/vdk_hs38_defconfig @@ -94,7 +94,7 @@ CONFIG_NLS_ISO8859_1=y # CONFIG_ENABLE_MUST_CHECK is not set CONFIG_STRIP_ASM_SYMS=y CONFIG_DEBUG_SHIRQ=y -CONFIG_LOCKUP_DETECTOR=y +CONFIG_SOFTLOCKUP_DETECTOR=y CONFIG_DEFAULT_HUNG_TASK_TIMEOUT=10 # CONFIG_SCHED_DEBUG is not set # CONFIG_DEBUG_PREEMPT is not set diff --git a/arch/arc/configs/vdk_hs38_smp_defconfig b/arch/arc/configs/vdk_hs38_smp_defconfig index 5c0971787acf..7b71464f6c2f 100644 --- a/arch/arc/configs/vdk_hs38_smp_defconfig +++ b/arch/arc/configs/vdk_hs38_smp_defconfig @@ -98,7 +98,7 @@ CONFIG_NLS_ISO8859_1=y # CONFIG_ENABLE_MUST_CHECK is not set CONFIG_STRIP_ASM_SYMS=y CONFIG_DEBUG_SHIRQ=y -CONFIG_LOCKUP_DETECTOR=y +CONFIG_SOFTLOCKUP_DETECTOR=y CONFIG_DEFAULT_HUNG_TASK_TIMEOUT=10 # CONFIG_SCHED_DEBUG is not set # CONFIG_DEBUG_PREEMPT is not set diff --git a/arch/arc/include/asm/arcregs.h b/arch/arc/include/asm/arcregs.h index ba8e802dba80..b1c56d35f2a9 100644 --- a/arch/arc/include/asm/arcregs.h +++ b/arch/arc/include/asm/arcregs.h @@ -98,6 +98,7 @@ /* Auxiliary registers */ #define AUX_IDENTITY 4 +#define AUX_EXEC_CTRL 8 #define AUX_INTR_VEC_BASE 0x25 #define AUX_VOL 0x5e @@ -135,12 +136,12 @@ struct bcr_identity { #endif }; -struct bcr_isa { +struct bcr_isa_arcv2 { #ifdef CONFIG_CPU_BIG_ENDIAN unsigned int div_rem:4, pad2:4, ldd:1, unalign:1, atomic:1, be:1, - pad1:11, atomic1:1, ver:8; + pad1:12, ver:8; #else - unsigned int ver:8, atomic1:1, pad1:11, be:1, atomic:1, unalign:1, + unsigned int ver:8, pad1:12, be:1, atomic:1, unalign:1, ldd:1, pad2:4, div_rem:4; #endif }; @@ -263,13 +264,13 @@ struct cpuinfo_arc { struct cpuinfo_arc_mmu mmu; struct cpuinfo_arc_bpu bpu; struct bcr_identity core; - struct bcr_isa isa; + struct bcr_isa_arcv2 isa; const char *details, *name; unsigned int vec_base; struct cpuinfo_arc_ccm iccm, dccm; struct { unsigned int swap:1, norm:1, minmax:1, barrel:1, crc:1, swape:1, pad1:2, - fpu_sp:1, fpu_dp:1, pad2:6, + fpu_sp:1, fpu_dp:1, dual_iss_enb:1, dual_iss_exist:1, pad2:4, debug:1, ap:1, smart:1, rtt:1, pad3:4, timer0:1, timer1:1, rtc:1, gfrc:1, pad4:4; } extn; diff --git a/arch/arc/kernel/setup.c b/arch/arc/kernel/setup.c index 877cec8f5ea2..fb83844daeea 100644 --- a/arch/arc/kernel/setup.c +++ b/arch/arc/kernel/setup.c @@ -51,6 +51,7 @@ static const struct id_to_str arc_cpu_rel[] = { { 0x51, "R2.0" }, { 0x52, "R2.1" }, { 0x53, "R3.0" }, + { 0x54, "R4.0" }, #endif { 0x00, NULL } }; @@ -62,6 +63,7 @@ static const struct id_to_str arc_cpu_nm[] = { #else { 0x40, "ARC EM" }, { 0x50, "ARC HS38" }, + { 0x54, "ARC HS48" }, #endif { 0x00, "Unknown" } }; @@ -119,11 +121,11 @@ static void read_arc_build_cfg_regs(void) struct bcr_generic bcr; struct cpuinfo_arc *cpu = &cpuinfo_arc700[smp_processor_id()]; const struct id_to_str *tbl; + struct bcr_isa_arcv2 isa; FIX_PTR(cpu); READ_BCR(AUX_IDENTITY, cpu->core); - READ_BCR(ARC_REG_ISA_CFG_BCR, cpu->isa); for (tbl = &arc_cpu_rel[0]; tbl->id != 0; tbl++) { if (cpu->core.family == tbl->id) { @@ -133,7 +135,7 @@ static void read_arc_build_cfg_regs(void) } for (tbl = &arc_cpu_nm[0]; tbl->id != 0; tbl++) { - if ((cpu->core.family & 0xF0) == tbl->id) + if ((cpu->core.family & 0xF4) == tbl->id) break; } cpu->name = tbl->str; @@ -192,6 +194,14 @@ static void read_arc_build_cfg_regs(void) cpu->bpu.full = bpu.ft; cpu->bpu.num_cache = 256 << bpu.bce; cpu->bpu.num_pred = 2048 << bpu.pte; + + if (cpu->core.family >= 0x54) { + unsigned int exec_ctrl; + + READ_BCR(AUX_EXEC_CTRL, exec_ctrl); + cpu->extn.dual_iss_exist = 1; + cpu->extn.dual_iss_enb = exec_ctrl & 1; + } } READ_BCR(ARC_REG_AP_BCR, bcr); @@ -205,18 +215,25 @@ static void read_arc_build_cfg_regs(void) cpu->extn.debug = cpu->extn.ap | cpu->extn.smart | cpu->extn.rtt; + READ_BCR(ARC_REG_ISA_CFG_BCR, isa); + /* some hacks for lack of feature BCR info in old ARC700 cores */ if (is_isa_arcompact()) { - if (!cpu->isa.ver) /* ISA BCR absent, use Kconfig info */ + if (!isa.ver) /* ISA BCR absent, use Kconfig info */ cpu->isa.atomic = IS_ENABLED(CONFIG_ARC_HAS_LLSC); - else - cpu->isa.atomic = cpu->isa.atomic1; + else { + /* ARC700_BUILD only has 2 bits of isa info */ + struct bcr_generic bcr = *(struct bcr_generic *)&isa; + cpu->isa.atomic = bcr.info & 1; + } cpu->isa.be = IS_ENABLED(CONFIG_CPU_BIG_ENDIAN); /* there's no direct way to distinguish 750 vs. 770 */ if (unlikely(cpu->core.family < 0x34 || cpu->mmu.ver < 3)) cpu->name = "ARC750"; + } else { + cpu->isa = isa; } } @@ -232,10 +249,11 @@ static char *arc_cpu_mumbojumbo(int cpu_id, char *buf, int len) "\nIDENTITY\t: ARCVER [%#02x] ARCNUM [%#02x] CHIPID [%#4x]\n", core->family, core->cpu_id, core->chip_id); - n += scnprintf(buf + n, len - n, "processor [%d]\t: %s %s (%s ISA) %s\n", + n += scnprintf(buf + n, len - n, "processor [%d]\t: %s %s (%s ISA) %s%s%s\n", cpu_id, cpu->name, cpu->details, is_isa_arcompact() ? "ARCompact" : "ARCv2", - IS_AVAIL1(cpu->isa.be, "[Big-Endian]")); + IS_AVAIL1(cpu->isa.be, "[Big-Endian]"), + IS_AVAIL3(cpu->extn.dual_iss_exist, cpu->extn.dual_iss_enb, " Dual-Issue")); n += scnprintf(buf + n, len - n, "Timers\t\t: %s%s%s%s%s%s\nISA Extn\t: ", IS_AVAIL1(cpu->extn.timer0, "Timer0 "), diff --git a/arch/arc/plat-axs10x/axs10x.c b/arch/arc/plat-axs10x/axs10x.c index f1ac6790da5f..cf14ebc36916 100644 --- a/arch/arc/plat-axs10x/axs10x.c +++ b/arch/arc/plat-axs10x/axs10x.c @@ -111,6 +111,13 @@ static void __init axs10x_early_init(void) axs10x_enable_gpio_intc_wire(); + /* + * Reset ethernet IP core. + * TODO: get rid of this quirk after axs10x reset driver (or simple + * reset driver) will be available in upstream. + */ + iowrite32((1 << 5), (void __iomem *) CREG_MB_SW_RESET); + scnprintf(mb, 32, "MainBoard v%d", mb_rev); axs10x_print_board_ver(CREG_MB_VER, mb); } diff --git a/arch/arc/plat-hsdk/Kconfig b/arch/arc/plat-hsdk/Kconfig index 5a6ed5afb009..bd08de4be75e 100644 --- a/arch/arc/plat-hsdk/Kconfig +++ b/arch/arc/plat-hsdk/Kconfig @@ -6,4 +6,5 @@ # menuconfig ARC_SOC_HSDK - bool "ARC HS Development Kit SOC" + bool "ARC HS Development Kit SOC" + select CLK_HSDK diff --git a/arch/arc/plat-hsdk/platform.c b/arch/arc/plat-hsdk/platform.c index a2e7fd17e36d..744e62e58788 100644 --- a/arch/arc/plat-hsdk/platform.c +++ b/arch/arc/plat-hsdk/platform.c @@ -38,6 +38,42 @@ static void __init hsdk_init_per_cpu(unsigned int cpu) #define CREG_PAE (CREG_BASE + 0x180) #define CREG_PAE_UPDATE (CREG_BASE + 0x194) +#define CREG_CORE_IF_CLK_DIV (CREG_BASE + 0x4B8) +#define CREG_CORE_IF_CLK_DIV_2 0x1 +#define CGU_BASE ARC_PERIPHERAL_BASE +#define CGU_PLL_STATUS (ARC_PERIPHERAL_BASE + 0x4) +#define CGU_PLL_CTRL (ARC_PERIPHERAL_BASE + 0x0) +#define CGU_PLL_STATUS_LOCK BIT(0) +#define CGU_PLL_STATUS_ERR BIT(1) +#define CGU_PLL_CTRL_1GHZ 0x3A10 +#define HSDK_PLL_LOCK_TIMEOUT 500 + +#define HSDK_PLL_LOCKED() \ + !!(ioread32((void __iomem *) CGU_PLL_STATUS) & CGU_PLL_STATUS_LOCK) + +#define HSDK_PLL_ERR() \ + !!(ioread32((void __iomem *) CGU_PLL_STATUS) & CGU_PLL_STATUS_ERR) + +static void __init hsdk_set_cpu_freq_1ghz(void) +{ + u32 timeout = HSDK_PLL_LOCK_TIMEOUT; + + /* + * As we set cpu clock which exceeds 500MHz, the divider for the interface + * clock must be programmed to div-by-2. + */ + iowrite32(CREG_CORE_IF_CLK_DIV_2, (void __iomem *) CREG_CORE_IF_CLK_DIV); + + /* Set cpu clock to 1GHz */ + iowrite32(CGU_PLL_CTRL_1GHZ, (void __iomem *) CGU_PLL_CTRL); + + while (!HSDK_PLL_LOCKED() && timeout--) + cpu_relax(); + + if (!HSDK_PLL_LOCKED() || HSDK_PLL_ERR()) + pr_err("Failed to setup CPU frequency to 1GHz!"); +} + static void __init hsdk_init_early(void) { /* @@ -52,6 +88,12 @@ static void __init hsdk_init_early(void) /* Really apply settings made above */ writel(1, (void __iomem *) CREG_PAE_UPDATE); + + /* + * Setup CPU frequency to 1GHz. + * TODO: remove it after smart hsdk pll driver will be introduced. + */ + hsdk_set_cpu_freq_1ghz(); } static const char *hsdk_compat[] __initconst = { diff --git a/arch/arm/boot/dts/am33xx.dtsi b/arch/arm/boot/dts/am33xx.dtsi index 7d7ca054c557..e58fab8aec5d 100644 --- a/arch/arm/boot/dts/am33xx.dtsi +++ b/arch/arm/boot/dts/am33xx.dtsi @@ -36,6 +36,8 @@ phy1 = &usb1_phy; ethernet0 = &cpsw_emac0; ethernet1 = &cpsw_emac1; + spi0 = &spi0; + spi1 = &spi1; }; cpus { diff --git a/arch/arm/boot/dts/am43x-epos-evm.dts b/arch/arm/boot/dts/am43x-epos-evm.dts index 9d276af7c539..081fa68b6f98 100644 --- a/arch/arm/boot/dts/am43x-epos-evm.dts +++ b/arch/arm/boot/dts/am43x-epos-evm.dts @@ -388,6 +388,7 @@ pinctrl-0 = <&cpsw_default>; pinctrl-1 = <&cpsw_sleep>; status = "okay"; + slaves = <1>; }; &davinci_mdio { @@ -402,11 +403,6 @@ phy-mode = "rmii"; }; -&cpsw_emac1 { - phy_id = <&davinci_mdio>, <1>; - phy-mode = "rmii"; -}; - &phy_sel { rmii-clock-ext; }; diff --git a/arch/arm/boot/dts/at91-sama5d27_som1_ek.dts b/arch/arm/boot/dts/at91-sama5d27_som1_ek.dts index 9c9088c99cc4..60cb084a8d92 100644 --- a/arch/arm/boot/dts/at91-sama5d27_som1_ek.dts +++ b/arch/arm/boot/dts/at91-sama5d27_som1_ek.dts @@ -67,7 +67,10 @@ usb1: ohci@00400000 { num-ports = <3>; - atmel,vbus-gpio = <&pioA PIN_PA10 GPIO_ACTIVE_HIGH>; + atmel,vbus-gpio = <0 /* &pioA PIN_PD20 GPIO_ACTIVE_HIGH */ + &pioA PIN_PA27 GPIO_ACTIVE_HIGH + 0 + >; pinctrl-names = "default"; pinctrl-0 = <&pinctrl_usb_default>; status = "okay"; @@ -120,7 +123,7 @@ pinctrl-names = "default"; pinctrl-0 = <&pinctrl_mikrobus2_uart>; atmel,use-dma-rx; - atmel-use-dma-tx; + atmel,use-dma-tx; status = "okay"; }; @@ -178,7 +181,7 @@ uart4: serial@fc00c000 { atmel,use-dma-rx; atmel,use-dma-tx; - pinctrl-name = "default"; + pinctrl-names = "default"; pinctrl-0 = <&pinctrl_mikrobus1_uart>; status = "okay"; }; @@ -330,7 +333,7 @@ }; pinctrl_led_gpio_default: led_gpio_default { - pinmux = <PIN_PA27__GPIO>, + pinmux = <PIN_PA10__GPIO>, <PIN_PB1__GPIO>, <PIN_PA31__GPIO>; bias-pull-up; @@ -396,7 +399,7 @@ }; pinctrl_usb_default: usb_default { - pinmux = <PIN_PA10__GPIO>, + pinmux = <PIN_PA27__GPIO>, <PIN_PD19__GPIO>; bias-disable; }; @@ -520,17 +523,17 @@ red { label = "red"; - gpios = <&pioA PIN_PA27 GPIO_ACTIVE_LOW>; + gpios = <&pioA PIN_PA10 GPIO_ACTIVE_HIGH>; }; green { label = "green"; - gpios = <&pioA PIN_PB1 GPIO_ACTIVE_LOW>; + gpios = <&pioA PIN_PB1 GPIO_ACTIVE_HIGH>; }; blue { label = "blue"; - gpios = <&pioA PIN_PA31 GPIO_ACTIVE_LOW>; + gpios = <&pioA PIN_PA31 GPIO_ACTIVE_HIGH>; linux,default-trigger = "heartbeat"; }; }; diff --git a/arch/arm/boot/dts/da850-evm.dts b/arch/arm/boot/dts/da850-evm.dts index 67e72bc72e80..c75507922f7d 100644 --- a/arch/arm/boot/dts/da850-evm.dts +++ b/arch/arm/boot/dts/da850-evm.dts @@ -15,6 +15,13 @@ compatible = "ti,da850-evm", "ti,da850"; model = "DA850/AM1808/OMAP-L138 EVM"; + aliases { + serial0 = &serial0; + serial1 = &serial1; + serial2 = &serial2; + ethernet0 = ð0; + }; + soc@1c00000 { pmx_core: pinmux@14120 { status = "okay"; diff --git a/arch/arm/boot/dts/dra7xx-clocks.dtsi b/arch/arm/boot/dts/dra7xx-clocks.dtsi index cf229dfabf61..e62b62875cba 100644 --- a/arch/arm/boot/dts/dra7xx-clocks.dtsi +++ b/arch/arm/boot/dts/dra7xx-clocks.dtsi @@ -1817,6 +1817,8 @@ clocks = <&abe_24m_fclk>, <&abe_sys_clk_div>, <&func_24m_clk>, <&atl_clkin3_ck>, <&atl_clkin2_ck>, <&atl_clkin1_ck>, <&atl_clkin0_ck>, <&sys_clkin2>, <&ref_clkin0_ck>, <&ref_clkin1_ck>, <&ref_clkin2_ck>, <&ref_clkin3_ck>, <&mlb_clk>, <&mlbp_clk>; ti,bit-shift = <24>; reg = <0x1868>; + assigned-clocks = <&mcasp3_ahclkx_mux>; + assigned-clock-parents = <&abe_24m_fclk>; }; mcasp3_aux_gfclk_mux: mcasp3_aux_gfclk_mux@1868 { diff --git a/arch/arm/boot/dts/omap3-n900.dts b/arch/arm/boot/dts/omap3-n900.dts index 26c20e1167b9..4acd32a1c4ef 100644 --- a/arch/arm/boot/dts/omap3-n900.dts +++ b/arch/arm/boot/dts/omap3-n900.dts @@ -144,15 +144,6 @@ io-channel-names = "temp", "bsi", "vbat"; }; - rear_camera: camera@0 { - compatible = "linux,camera"; - - module { - model = "TCM8341MD"; - sensor = <&cam1>; - }; - }; - pwm9: dmtimer-pwm { compatible = "ti,omap-dmtimer-pwm"; #pwm-cells = <3>; @@ -189,10 +180,8 @@ clock-lanes = <1>; data-lanes = <0>; lane-polarity = <0 0>; - clock-inv = <0>; /* Select strobe = <1> for back camera, <0> for front camera */ strobe = <1>; - crc = <0>; }; }; }; diff --git a/arch/arm/boot/dts/omap3-n950-n9.dtsi b/arch/arm/boot/dts/omap3-n950-n9.dtsi index cb47ae79a5f9..1b0bd72945f2 100644 --- a/arch/arm/boot/dts/omap3-n950-n9.dtsi +++ b/arch/arm/boot/dts/omap3-n950-n9.dtsi @@ -267,15 +267,19 @@ clock-frequency = <400000>; as3645a@30 { + #address-cells = <1>; + #size-cells = <0>; reg = <0x30>; compatible = "ams,as3645a"; - flash { + flash@0 { + reg = <0x0>; flash-timeout-us = <150000>; flash-max-microamp = <320000>; led-max-microamp = <60000>; - peak-current-limit = <1750000>; + ams,input-max-microamp = <1750000>; }; - indicator { + indicator@1 { + reg = <0x1>; led-max-microamp = <10000>; }; }; diff --git a/arch/arm/boot/dts/stm32429i-eval.dts b/arch/arm/boot/dts/stm32429i-eval.dts index 97b1c2321ba9..293ecb957227 100644 --- a/arch/arm/boot/dts/stm32429i-eval.dts +++ b/arch/arm/boot/dts/stm32429i-eval.dts @@ -47,6 +47,7 @@ /dts-v1/; #include "stm32f429.dtsi" +#include "stm32f429-pinctrl.dtsi" #include <dt-bindings/input/input.h> #include <dt-bindings/gpio/gpio.h> @@ -202,10 +203,8 @@ stmpe1600: stmpe1600@42 { compatible = "st,stmpe1600"; reg = <0x42>; - irq-gpio = <&gpioi 8 0>; - irq-trigger = <3>; interrupts = <8 3>; - interrupt-parent = <&exti>; + interrupt-parent = <&gpioi>; interrupt-controller; wakeup-source; diff --git a/arch/arm/boot/dts/stm32f4-pinctrl.dtsi b/arch/arm/boot/dts/stm32f4-pinctrl.dtsi new file mode 100644 index 000000000000..7f3560c0211d --- /dev/null +++ b/arch/arm/boot/dts/stm32f4-pinctrl.dtsi @@ -0,0 +1,343 @@ +/* + * Copyright 2017 - Alexandre Torgue <alexandre.torgue@st.com> + * + * This file is dual-licensed: you can use it either under the terms + * of the GPL or the X11 license, at your option. Note that this dual + * licensing only applies to this file, and not this project as a + * whole. + * + * a) This file 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 file 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. + * + * Or, alternatively, + * + * b) Permission is hereby granted, free of charge, to any person + * obtaining a copy of this software and associated documentation + * files (the "Software"), to deal in the Software without + * restriction, including without limitation the rights to use, + * copy, modify, merge, publish, distribute, sublicense, and/or + * sell copies of the Software, and to permit persons to whom the + * Software is furnished to do so, subject to the following + * conditions: + * + * The above copyright notice and this permission notice shall be + * included in all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES + * OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND + * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT + * HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, + * WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING + * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR + * OTHER DEALINGS IN THE SOFTWARE. + */ + +#include <dt-bindings/pinctrl/stm32f429-pinfunc.h> +#include <dt-bindings/mfd/stm32f4-rcc.h> + +/ { + soc { + pinctrl: pin-controller { + #address-cells = <1>; + #size-cells = <1>; + ranges = <0 0x40020000 0x3000>; + interrupt-parent = <&exti>; + st,syscfg = <&syscfg 0x8>; + pins-are-numbered; + + gpioa: gpio@40020000 { + gpio-controller; + #gpio-cells = <2>; + interrupt-controller; + #interrupt-cells = <2>; + reg = <0x0 0x400>; + clocks = <&rcc 0 STM32F4_AHB1_CLOCK(GPIOA)>; + st,bank-name = "GPIOA"; + }; + + gpiob: gpio@40020400 { + gpio-controller; + #gpio-cells = <2>; + interrupt-controller; + #interrupt-cells = <2>; + reg = <0x400 0x400>; + clocks = <&rcc 0 STM32F4_AHB1_CLOCK(GPIOB)>; + st,bank-name = "GPIOB"; + }; + + gpioc: gpio@40020800 { + gpio-controller; + #gpio-cells = <2>; + interrupt-controller; + #interrupt-cells = <2>; + reg = <0x800 0x400>; + clocks = <&rcc 0 STM32F4_AHB1_CLOCK(GPIOC)>; + st,bank-name = "GPIOC"; + }; + + gpiod: gpio@40020c00 { + gpio-controller; + #gpio-cells = <2>; + interrupt-controller; + #interrupt-cells = <2>; + reg = <0xc00 0x400>; + clocks = <&rcc 0 STM32F4_AHB1_CLOCK(GPIOD)>; + st,bank-name = "GPIOD"; + }; + + gpioe: gpio@40021000 { + gpio-controller; + #gpio-cells = <2>; + interrupt-controller; + #interrupt-cells = <2>; + reg = <0x1000 0x400>; + clocks = <&rcc 0 STM32F4_AHB1_CLOCK(GPIOE)>; + st,bank-name = "GPIOE"; + }; + + gpiof: gpio@40021400 { + gpio-controller; + #gpio-cells = <2>; + interrupt-controller; + #interrupt-cells = <2>; + reg = <0x1400 0x400>; + clocks = <&rcc 0 STM32F4_AHB1_CLOCK(GPIOF)>; + st,bank-name = "GPIOF"; + }; + + gpiog: gpio@40021800 { + gpio-controller; + #gpio-cells = <2>; + interrupt-controller; + #interrupt-cells = <2>; + reg = <0x1800 0x400>; + clocks = <&rcc 0 STM32F4_AHB1_CLOCK(GPIOG)>; + st,bank-name = "GPIOG"; + }; + + gpioh: gpio@40021c00 { + gpio-controller; + #gpio-cells = <2>; + interrupt-controller; + #interrupt-cells = <2>; + reg = <0x1c00 0x400>; + clocks = <&rcc 0 STM32F4_AHB1_CLOCK(GPIOH)>; + st,bank-name = "GPIOH"; + }; + + gpioi: gpio@40022000 { + gpio-controller; + #gpio-cells = <2>; + interrupt-controller; + #interrupt-cells = <2>; + reg = <0x2000 0x400>; + clocks = <&rcc 0 STM32F4_AHB1_CLOCK(GPIOI)>; + st,bank-name = "GPIOI"; + }; + + gpioj: gpio@40022400 { + gpio-controller; + #gpio-cells = <2>; + interrupt-controller; + #interrupt-cells = <2>; + reg = <0x2400 0x400>; + clocks = <&rcc 0 STM32F4_AHB1_CLOCK(GPIOJ)>; + st,bank-name = "GPIOJ"; + }; + + gpiok: gpio@40022800 { + gpio-controller; + #gpio-cells = <2>; + interrupt-controller; + #interrupt-cells = <2>; + reg = <0x2800 0x400>; + clocks = <&rcc 0 STM32F4_AHB1_CLOCK(GPIOK)>; + st,bank-name = "GPIOK"; + }; + + usart1_pins_a: usart1@0 { + pins1 { + pinmux = <STM32F429_PA9_FUNC_USART1_TX>; + bias-disable; + drive-push-pull; + slew-rate = <0>; + }; + pins2 { + pinmux = <STM32F429_PA10_FUNC_USART1_RX>; + bias-disable; + }; + }; + + usart3_pins_a: usart3@0 { + pins1 { + pinmux = <STM32F429_PB10_FUNC_USART3_TX>; + bias-disable; + drive-push-pull; + slew-rate = <0>; + }; + pins2 { + pinmux = <STM32F429_PB11_FUNC_USART3_RX>; + bias-disable; + }; + }; + + usbotg_fs_pins_a: usbotg_fs@0 { + pins { + pinmux = <STM32F429_PA10_FUNC_OTG_FS_ID>, + <STM32F429_PA11_FUNC_OTG_FS_DM>, + <STM32F429_PA12_FUNC_OTG_FS_DP>; + bias-disable; + drive-push-pull; + slew-rate = <2>; + }; + }; + + usbotg_fs_pins_b: usbotg_fs@1 { + pins { + pinmux = <STM32F429_PB12_FUNC_OTG_HS_ID>, + <STM32F429_PB14_FUNC_OTG_HS_DM>, + <STM32F429_PB15_FUNC_OTG_HS_DP>; + bias-disable; + drive-push-pull; + slew-rate = <2>; + }; + }; + + usbotg_hs_pins_a: usbotg_hs@0 { + pins { + pinmux = <STM32F429_PH4_FUNC_OTG_HS_ULPI_NXT>, + <STM32F429_PI11_FUNC_OTG_HS_ULPI_DIR>, + <STM32F429_PC0_FUNC_OTG_HS_ULPI_STP>, + <STM32F429_PA5_FUNC_OTG_HS_ULPI_CK>, + <STM32F429_PA3_FUNC_OTG_HS_ULPI_D0>, + <STM32F429_PB0_FUNC_OTG_HS_ULPI_D1>, + <STM32F429_PB1_FUNC_OTG_HS_ULPI_D2>, + <STM32F429_PB10_FUNC_OTG_HS_ULPI_D3>, + <STM32F429_PB11_FUNC_OTG_HS_ULPI_D4>, + <STM32F429_PB12_FUNC_OTG_HS_ULPI_D5>, + <STM32F429_PB13_FUNC_OTG_HS_ULPI_D6>, + <STM32F429_PB5_FUNC_OTG_HS_ULPI_D7>; + bias-disable; + drive-push-pull; + slew-rate = <2>; + }; + }; + + ethernet_mii: mii@0 { + pins { + pinmux = <STM32F429_PG13_FUNC_ETH_MII_TXD0_ETH_RMII_TXD0>, + <STM32F429_PG14_FUNC_ETH_MII_TXD1_ETH_RMII_TXD1>, + <STM32F429_PC2_FUNC_ETH_MII_TXD2>, + <STM32F429_PB8_FUNC_ETH_MII_TXD3>, + <STM32F429_PC3_FUNC_ETH_MII_TX_CLK>, + <STM32F429_PG11_FUNC_ETH_MII_TX_EN_ETH_RMII_TX_EN>, + <STM32F429_PA2_FUNC_ETH_MDIO>, + <STM32F429_PC1_FUNC_ETH_MDC>, + <STM32F429_PA1_FUNC_ETH_MII_RX_CLK_ETH_RMII_REF_CLK>, + <STM32F429_PA7_FUNC_ETH_MII_RX_DV_ETH_RMII_CRS_DV>, + <STM32F429_PC4_FUNC_ETH_MII_RXD0_ETH_RMII_RXD0>, + <STM32F429_PC5_FUNC_ETH_MII_RXD1_ETH_RMII_RXD1>, + <STM32F429_PH6_FUNC_ETH_MII_RXD2>, + <STM32F429_PH7_FUNC_ETH_MII_RXD3>; + slew-rate = <2>; + }; + }; + + adc3_in8_pin: adc@200 { + pins { + pinmux = <STM32F429_PF10_FUNC_ANALOG>; + }; + }; + + pwm1_pins: pwm@1 { + pins { + pinmux = <STM32F429_PA8_FUNC_TIM1_CH1>, + <STM32F429_PB13_FUNC_TIM1_CH1N>, + <STM32F429_PB12_FUNC_TIM1_BKIN>; + }; + }; + + pwm3_pins: pwm@3 { + pins { + pinmux = <STM32F429_PB4_FUNC_TIM3_CH1>, + <STM32F429_PB5_FUNC_TIM3_CH2>; + }; + }; + + i2c1_pins: i2c1@0 { + pins { + pinmux = <STM32F429_PB9_FUNC_I2C1_SDA>, + <STM32F429_PB6_FUNC_I2C1_SCL>; + bias-disable; + drive-open-drain; + slew-rate = <3>; + }; + }; + + ltdc_pins: ltdc@0 { + pins { + pinmux = <STM32F429_PI12_FUNC_LCD_HSYNC>, + <STM32F429_PI13_FUNC_LCD_VSYNC>, + <STM32F429_PI14_FUNC_LCD_CLK>, + <STM32F429_PI15_FUNC_LCD_R0>, + <STM32F429_PJ0_FUNC_LCD_R1>, + <STM32F429_PJ1_FUNC_LCD_R2>, + <STM32F429_PJ2_FUNC_LCD_R3>, + <STM32F429_PJ3_FUNC_LCD_R4>, + <STM32F429_PJ4_FUNC_LCD_R5>, + <STM32F429_PJ5_FUNC_LCD_R6>, + <STM32F429_PJ6_FUNC_LCD_R7>, + <STM32F429_PJ7_FUNC_LCD_G0>, + <STM32F429_PJ8_FUNC_LCD_G1>, + <STM32F429_PJ9_FUNC_LCD_G2>, + <STM32F429_PJ10_FUNC_LCD_G3>, + <STM32F429_PJ11_FUNC_LCD_G4>, + <STM32F429_PJ12_FUNC_LCD_B0>, + <STM32F429_PJ13_FUNC_LCD_B1>, + <STM32F429_PJ14_FUNC_LCD_B2>, + <STM32F429_PJ15_FUNC_LCD_B3>, + <STM32F429_PK0_FUNC_LCD_G5>, + <STM32F429_PK1_FUNC_LCD_G6>, + <STM32F429_PK2_FUNC_LCD_G7>, + <STM32F429_PK3_FUNC_LCD_B4>, + <STM32F429_PK4_FUNC_LCD_B5>, + <STM32F429_PK5_FUNC_LCD_B6>, + <STM32F429_PK6_FUNC_LCD_B7>, + <STM32F429_PK7_FUNC_LCD_DE>; + slew-rate = <2>; + }; + }; + + dcmi_pins: dcmi@0 { + pins { + pinmux = <STM32F429_PA4_FUNC_DCMI_HSYNC>, + <STM32F429_PB7_FUNC_DCMI_VSYNC>, + <STM32F429_PA6_FUNC_DCMI_PIXCLK>, + <STM32F429_PC6_FUNC_DCMI_D0>, + <STM32F429_PC7_FUNC_DCMI_D1>, + <STM32F429_PC8_FUNC_DCMI_D2>, + <STM32F429_PC9_FUNC_DCMI_D3>, + <STM32F429_PC11_FUNC_DCMI_D4>, + <STM32F429_PD3_FUNC_DCMI_D5>, + <STM32F429_PB8_FUNC_DCMI_D6>, + <STM32F429_PE6_FUNC_DCMI_D7>, + <STM32F429_PC10_FUNC_DCMI_D8>, + <STM32F429_PC12_FUNC_DCMI_D9>, + <STM32F429_PD6_FUNC_DCMI_D10>, + <STM32F429_PD2_FUNC_DCMI_D11>; + bias-disable; + drive-push-pull; + slew-rate = <3>; + }; + }; + }; + }; +}; diff --git a/arch/arm/boot/dts/stm32f429-disco.dts b/arch/arm/boot/dts/stm32f429-disco.dts index c66d617e4245..5ceb2cf3777f 100644 --- a/arch/arm/boot/dts/stm32f429-disco.dts +++ b/arch/arm/boot/dts/stm32f429-disco.dts @@ -47,6 +47,7 @@ /dts-v1/; #include "stm32f429.dtsi" +#include "stm32f429-pinctrl.dtsi" #include <dt-bindings/input/input.h> / { diff --git a/arch/arm/boot/dts/stm32f429-pinctrl.dtsi b/arch/arm/boot/dts/stm32f429-pinctrl.dtsi new file mode 100644 index 000000000000..3e7a17d9112e --- /dev/null +++ b/arch/arm/boot/dts/stm32f429-pinctrl.dtsi @@ -0,0 +1,95 @@ +/* + * Copyright 2017 - Alexandre Torgue <alexandre.torgue@st.com> + * + * This file is dual-licensed: you can use it either under the terms + * of the GPL or the X11 license, at your option. Note that this dual + * licensing only applies to this file, and not this project as a + * whole. + * + * a) This file 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 file 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. + * + * Or, alternatively, + * + * b) Permission is hereby granted, free of charge, to any person + * obtaining a copy of this software and associated documentation + * files (the "Software"), to deal in the Software without + * restriction, including without limitation the rights to use, + * copy, modify, merge, publish, distribute, sublicense, and/or + * sell copies of the Software, and to permit persons to whom the + * Software is furnished to do so, subject to the following + * conditions: + * + * The above copyright notice and this permission notice shall be + * included in all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES + * OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND + * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT + * HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, + * WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING + * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR + * OTHER DEALINGS IN THE SOFTWARE. + */ + +#include "stm32f4-pinctrl.dtsi" + +/ { + soc { + pinctrl: pin-controller { + compatible = "st,stm32f429-pinctrl"; + + gpioa: gpio@40020000 { + gpio-ranges = <&pinctrl 0 0 16>; + }; + + gpiob: gpio@40020400 { + gpio-ranges = <&pinctrl 0 16 16>; + }; + + gpioc: gpio@40020800 { + gpio-ranges = <&pinctrl 0 32 16>; + }; + + gpiod: gpio@40020c00 { + gpio-ranges = <&pinctrl 0 48 16>; + }; + + gpioe: gpio@40021000 { + gpio-ranges = <&pinctrl 0 64 16>; + }; + + gpiof: gpio@40021400 { + gpio-ranges = <&pinctrl 0 80 16>; + }; + + gpiog: gpio@40021800 { + gpio-ranges = <&pinctrl 0 96 16>; + }; + + gpioh: gpio@40021c00 { + gpio-ranges = <&pinctrl 0 112 16>; + }; + + gpioi: gpio@40022000 { + gpio-ranges = <&pinctrl 0 128 16>; + }; + + gpioj: gpio@40022400 { + gpio-ranges = <&pinctrl 0 144 16>; + }; + + gpiok: gpio@40022800 { + gpio-ranges = <&pinctrl 0 160 8>; + }; + }; + }; +}; diff --git a/arch/arm/boot/dts/stm32f429.dtsi b/arch/arm/boot/dts/stm32f429.dtsi index dd7e99b1f43b..5b36eb114ddc 100644 --- a/arch/arm/boot/dts/stm32f429.dtsi +++ b/arch/arm/boot/dts/stm32f429.dtsi @@ -47,7 +47,6 @@ #include "skeleton.dtsi" #include "armv7-m.dtsi" -#include <dt-bindings/pinctrl/stm32f429-pinfunc.h> #include <dt-bindings/clock/stm32fx-clock.h> #include <dt-bindings/mfd/stm32f4-rcc.h> @@ -591,302 +590,6 @@ status = "disabled"; }; - pinctrl: pin-controller { - #address-cells = <1>; - #size-cells = <1>; - compatible = "st,stm32f429-pinctrl"; - ranges = <0 0x40020000 0x3000>; - interrupt-parent = <&exti>; - st,syscfg = <&syscfg 0x8>; - pins-are-numbered; - - gpioa: gpio@40020000 { - gpio-controller; - #gpio-cells = <2>; - interrupt-controller; - #interrupt-cells = <2>; - reg = <0x0 0x400>; - clocks = <&rcc 0 STM32F4_AHB1_CLOCK(GPIOA)>; - st,bank-name = "GPIOA"; - }; - - gpiob: gpio@40020400 { - gpio-controller; - #gpio-cells = <2>; - interrupt-controller; - #interrupt-cells = <2>; - reg = <0x400 0x400>; - clocks = <&rcc 0 STM32F4_AHB1_CLOCK(GPIOB)>; - st,bank-name = "GPIOB"; - }; - - gpioc: gpio@40020800 { - gpio-controller; - #gpio-cells = <2>; - interrupt-controller; - #interrupt-cells = <2>; - reg = <0x800 0x400>; - clocks = <&rcc 0 STM32F4_AHB1_CLOCK(GPIOC)>; - st,bank-name = "GPIOC"; - }; - - gpiod: gpio@40020c00 { - gpio-controller; - #gpio-cells = <2>; - interrupt-controller; - #interrupt-cells = <2>; - reg = <0xc00 0x400>; - clocks = <&rcc 0 STM32F4_AHB1_CLOCK(GPIOD)>; - st,bank-name = "GPIOD"; - }; - - gpioe: gpio@40021000 { - gpio-controller; - #gpio-cells = <2>; - interrupt-controller; - #interrupt-cells = <2>; - reg = <0x1000 0x400>; - clocks = <&rcc 0 STM32F4_AHB1_CLOCK(GPIOE)>; - st,bank-name = "GPIOE"; - }; - - gpiof: gpio@40021400 { - gpio-controller; - #gpio-cells = <2>; - interrupt-controller; - #interrupt-cells = <2>; - reg = <0x1400 0x400>; - clocks = <&rcc 0 STM32F4_AHB1_CLOCK(GPIOF)>; - st,bank-name = "GPIOF"; - }; - - gpiog: gpio@40021800 { - gpio-controller; - #gpio-cells = <2>; - interrupt-controller; - #interrupt-cells = <2>; - reg = <0x1800 0x400>; - clocks = <&rcc 0 STM32F4_AHB1_CLOCK(GPIOG)>; - st,bank-name = "GPIOG"; - }; - - gpioh: gpio@40021c00 { - gpio-controller; - #gpio-cells = <2>; - interrupt-controller; - #interrupt-cells = <2>; - reg = <0x1c00 0x400>; - clocks = <&rcc 0 STM32F4_AHB1_CLOCK(GPIOH)>; - st,bank-name = "GPIOH"; - }; - - gpioi: gpio@40022000 { - gpio-controller; - #gpio-cells = <2>; - interrupt-controller; - #interrupt-cells = <2>; - reg = <0x2000 0x400>; - clocks = <&rcc 0 STM32F4_AHB1_CLOCK(GPIOI)>; - st,bank-name = "GPIOI"; - }; - - gpioj: gpio@40022400 { - gpio-controller; - #gpio-cells = <2>; - interrupt-controller; - #interrupt-cells = <2>; - reg = <0x2400 0x400>; - clocks = <&rcc 0 STM32F4_AHB1_CLOCK(GPIOJ)>; - st,bank-name = "GPIOJ"; - }; - - gpiok: gpio@40022800 { - gpio-controller; - #gpio-cells = <2>; - interrupt-controller; - #interrupt-cells = <2>; - reg = <0x2800 0x400>; - clocks = <&rcc 0 STM32F4_AHB1_CLOCK(GPIOK)>; - st,bank-name = "GPIOK"; - }; - - usart1_pins_a: usart1@0 { - pins1 { - pinmux = <STM32F429_PA9_FUNC_USART1_TX>; - bias-disable; - drive-push-pull; - slew-rate = <0>; - }; - pins2 { - pinmux = <STM32F429_PA10_FUNC_USART1_RX>; - bias-disable; - }; - }; - - usart3_pins_a: usart3@0 { - pins1 { - pinmux = <STM32F429_PB10_FUNC_USART3_TX>; - bias-disable; - drive-push-pull; - slew-rate = <0>; - }; - pins2 { - pinmux = <STM32F429_PB11_FUNC_USART3_RX>; - bias-disable; - }; - }; - - usbotg_fs_pins_a: usbotg_fs@0 { - pins { - pinmux = <STM32F429_PA10_FUNC_OTG_FS_ID>, - <STM32F429_PA11_FUNC_OTG_FS_DM>, - <STM32F429_PA12_FUNC_OTG_FS_DP>; - bias-disable; - drive-push-pull; - slew-rate = <2>; - }; - }; - - usbotg_fs_pins_b: usbotg_fs@1 { - pins { - pinmux = <STM32F429_PB12_FUNC_OTG_HS_ID>, - <STM32F429_PB14_FUNC_OTG_HS_DM>, - <STM32F429_PB15_FUNC_OTG_HS_DP>; - bias-disable; - drive-push-pull; - slew-rate = <2>; - }; - }; - - usbotg_hs_pins_a: usbotg_hs@0 { - pins { - pinmux = <STM32F429_PH4_FUNC_OTG_HS_ULPI_NXT>, - <STM32F429_PI11_FUNC_OTG_HS_ULPI_DIR>, - <STM32F429_PC0_FUNC_OTG_HS_ULPI_STP>, - <STM32F429_PA5_FUNC_OTG_HS_ULPI_CK>, - <STM32F429_PA3_FUNC_OTG_HS_ULPI_D0>, - <STM32F429_PB0_FUNC_OTG_HS_ULPI_D1>, - <STM32F429_PB1_FUNC_OTG_HS_ULPI_D2>, - <STM32F429_PB10_FUNC_OTG_HS_ULPI_D3>, - <STM32F429_PB11_FUNC_OTG_HS_ULPI_D4>, - <STM32F429_PB12_FUNC_OTG_HS_ULPI_D5>, - <STM32F429_PB13_FUNC_OTG_HS_ULPI_D6>, - <STM32F429_PB5_FUNC_OTG_HS_ULPI_D7>; - bias-disable; - drive-push-pull; - slew-rate = <2>; - }; - }; - - ethernet_mii: mii@0 { - pins { - pinmux = <STM32F429_PG13_FUNC_ETH_MII_TXD0_ETH_RMII_TXD0>, - <STM32F429_PG14_FUNC_ETH_MII_TXD1_ETH_RMII_TXD1>, - <STM32F429_PC2_FUNC_ETH_MII_TXD2>, - <STM32F429_PB8_FUNC_ETH_MII_TXD3>, - <STM32F429_PC3_FUNC_ETH_MII_TX_CLK>, - <STM32F429_PG11_FUNC_ETH_MII_TX_EN_ETH_RMII_TX_EN>, - <STM32F429_PA2_FUNC_ETH_MDIO>, - <STM32F429_PC1_FUNC_ETH_MDC>, - <STM32F429_PA1_FUNC_ETH_MII_RX_CLK_ETH_RMII_REF_CLK>, - <STM32F429_PA7_FUNC_ETH_MII_RX_DV_ETH_RMII_CRS_DV>, - <STM32F429_PC4_FUNC_ETH_MII_RXD0_ETH_RMII_RXD0>, - <STM32F429_PC5_FUNC_ETH_MII_RXD1_ETH_RMII_RXD1>, - <STM32F429_PH6_FUNC_ETH_MII_RXD2>, - <STM32F429_PH7_FUNC_ETH_MII_RXD3>; - slew-rate = <2>; - }; - }; - - adc3_in8_pin: adc@200 { - pins { - pinmux = <STM32F429_PF10_FUNC_ANALOG>; - }; - }; - - pwm1_pins: pwm@1 { - pins { - pinmux = <STM32F429_PA8_FUNC_TIM1_CH1>, - <STM32F429_PB13_FUNC_TIM1_CH1N>, - <STM32F429_PB12_FUNC_TIM1_BKIN>; - }; - }; - - pwm3_pins: pwm@3 { - pins { - pinmux = <STM32F429_PB4_FUNC_TIM3_CH1>, - <STM32F429_PB5_FUNC_TIM3_CH2>; - }; - }; - - i2c1_pins: i2c1@0 { - pins { - pinmux = <STM32F429_PB9_FUNC_I2C1_SDA>, - <STM32F429_PB6_FUNC_I2C1_SCL>; - bias-disable; - drive-open-drain; - slew-rate = <3>; - }; - }; - - ltdc_pins: ltdc@0 { - pins { - pinmux = <STM32F429_PI12_FUNC_LCD_HSYNC>, - <STM32F429_PI13_FUNC_LCD_VSYNC>, - <STM32F429_PI14_FUNC_LCD_CLK>, - <STM32F429_PI15_FUNC_LCD_R0>, - <STM32F429_PJ0_FUNC_LCD_R1>, - <STM32F429_PJ1_FUNC_LCD_R2>, - <STM32F429_PJ2_FUNC_LCD_R3>, - <STM32F429_PJ3_FUNC_LCD_R4>, - <STM32F429_PJ4_FUNC_LCD_R5>, - <STM32F429_PJ5_FUNC_LCD_R6>, - <STM32F429_PJ6_FUNC_LCD_R7>, - <STM32F429_PJ7_FUNC_LCD_G0>, - <STM32F429_PJ8_FUNC_LCD_G1>, - <STM32F429_PJ9_FUNC_LCD_G2>, - <STM32F429_PJ10_FUNC_LCD_G3>, - <STM32F429_PJ11_FUNC_LCD_G4>, - <STM32F429_PJ12_FUNC_LCD_B0>, - <STM32F429_PJ13_FUNC_LCD_B1>, - <STM32F429_PJ14_FUNC_LCD_B2>, - <STM32F429_PJ15_FUNC_LCD_B3>, - <STM32F429_PK0_FUNC_LCD_G5>, - <STM32F429_PK1_FUNC_LCD_G6>, - <STM32F429_PK2_FUNC_LCD_G7>, - <STM32F429_PK3_FUNC_LCD_B4>, - <STM32F429_PK4_FUNC_LCD_B5>, - <STM32F429_PK5_FUNC_LCD_B6>, - <STM32F429_PK6_FUNC_LCD_B7>, - <STM32F429_PK7_FUNC_LCD_DE>; - slew-rate = <2>; - }; - }; - - dcmi_pins: dcmi@0 { - pins { - pinmux = <STM32F429_PA4_FUNC_DCMI_HSYNC>, - <STM32F429_PB7_FUNC_DCMI_VSYNC>, - <STM32F429_PA6_FUNC_DCMI_PIXCLK>, - <STM32F429_PC6_FUNC_DCMI_D0>, - <STM32F429_PC7_FUNC_DCMI_D1>, - <STM32F429_PC8_FUNC_DCMI_D2>, - <STM32F429_PC9_FUNC_DCMI_D3>, - <STM32F429_PC11_FUNC_DCMI_D4>, - <STM32F429_PD3_FUNC_DCMI_D5>, - <STM32F429_PB8_FUNC_DCMI_D6>, - <STM32F429_PE6_FUNC_DCMI_D7>, - <STM32F429_PC10_FUNC_DCMI_D8>, - <STM32F429_PC12_FUNC_DCMI_D9>, - <STM32F429_PD6_FUNC_DCMI_D10>, - <STM32F429_PD2_FUNC_DCMI_D11>; - bias-disable; - drive-push-pull; - slew-rate = <3>; - }; - }; - }; - crc: crc@40023000 { compatible = "st,stm32f4-crc"; reg = <0x40023000 0x400>; diff --git a/arch/arm/boot/dts/stm32f469-disco.dts b/arch/arm/boot/dts/stm32f469-disco.dts index 6ae1f037f3f0..c18acbe4cf4e 100644 --- a/arch/arm/boot/dts/stm32f469-disco.dts +++ b/arch/arm/boot/dts/stm32f469-disco.dts @@ -47,6 +47,7 @@ /dts-v1/; #include "stm32f429.dtsi" +#include "stm32f469-pinctrl.dtsi" / { model = "STMicroelectronics STM32F469i-DISCO board"; diff --git a/arch/arm/boot/dts/stm32f469-pinctrl.dtsi b/arch/arm/boot/dts/stm32f469-pinctrl.dtsi new file mode 100644 index 000000000000..fff542662eea --- /dev/null +++ b/arch/arm/boot/dts/stm32f469-pinctrl.dtsi @@ -0,0 +1,96 @@ +/* + * Copyright 2017 - Alexandre Torgue <alexandre.torgue@st.com> + * + * This file is dual-licensed: you can use it either under the terms + * of the GPL or the X11 license, at your option. Note that this dual + * licensing only applies to this file, and not this project as a + * whole. + * + * a) This file 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 file 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. + * + * Or, alternatively, + * + * b) Permission is hereby granted, free of charge, to any person + * obtaining a copy of this software and associated documentation + * files (the "Software"), to deal in the Software without + * restriction, including without limitation the rights to use, + * copy, modify, merge, publish, distribute, sublicense, and/or + * sell copies of the Software, and to permit persons to whom the + * Software is furnished to do so, subject to the following + * conditions: + * + * The above copyright notice and this permission notice shall be + * included in all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES + * OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND + * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT + * HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, + * WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING + * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR + * OTHER DEALINGS IN THE SOFTWARE. + */ + +#include "stm32f4-pinctrl.dtsi" + +/ { + soc { + pinctrl: pin-controller { + compatible = "st,stm32f469-pinctrl"; + + gpioa: gpio@40020000 { + gpio-ranges = <&pinctrl 0 0 16>; + }; + + gpiob: gpio@40020400 { + gpio-ranges = <&pinctrl 0 16 16>; + }; + + gpioc: gpio@40020800 { + gpio-ranges = <&pinctrl 0 32 16>; + }; + + gpiod: gpio@40020c00 { + gpio-ranges = <&pinctrl 0 48 16>; + }; + + gpioe: gpio@40021000 { + gpio-ranges = <&pinctrl 0 64 16>; + }; + + gpiof: gpio@40021400 { + gpio-ranges = <&pinctrl 0 80 16>; + }; + + gpiog: gpio@40021800 { + gpio-ranges = <&pinctrl 0 96 16>; + }; + + gpioh: gpio@40021c00 { + gpio-ranges = <&pinctrl 0 112 16>; + }; + + gpioi: gpio@40022000 { + gpio-ranges = <&pinctrl 0 128 16>; + }; + + gpioj: gpio@40022400 { + gpio-ranges = <&pinctrl 0 144 6>, + <&pinctrl 12 156 4>; + }; + + gpiok: gpio@40022800 { + gpio-ranges = <&pinctrl 3 163 5>; + }; + }; + }; +}; diff --git a/arch/arm/configs/gemini_defconfig b/arch/arm/configs/gemini_defconfig index d2d75fa664a6..2a63fa10c813 100644 --- a/arch/arm/configs/gemini_defconfig +++ b/arch/arm/configs/gemini_defconfig @@ -32,6 +32,7 @@ CONFIG_BLK_DEV_RAM_SIZE=16384 CONFIG_BLK_DEV_SD=y # CONFIG_SCSI_LOWLEVEL is not set CONFIG_ATA=y +CONFIG_PATA_FTIDE010=y CONFIG_INPUT_EVDEV=y CONFIG_KEYBOARD_GPIO=y # CONFIG_INPUT_MOUSE is not set @@ -55,8 +56,8 @@ CONFIG_LEDS_GPIO=y CONFIG_LEDS_TRIGGERS=y CONFIG_LEDS_TRIGGER_HEARTBEAT=y CONFIG_RTC_CLASS=y -CONFIG_RTC_DRV_GEMINI=y CONFIG_DMADEVICES=y +CONFIG_AMBA_PL08X=y # CONFIG_DNOTIFY is not set CONFIG_TMPFS=y CONFIG_TMPFS_POSIX_ACL=y diff --git a/arch/arm/configs/pxa_defconfig b/arch/arm/configs/pxa_defconfig index 64e3a2a8cede..d5e1370ec303 100644 --- a/arch/arm/configs/pxa_defconfig +++ b/arch/arm/configs/pxa_defconfig @@ -471,7 +471,7 @@ CONFIG_LCD_PLATFORM=m CONFIG_LCD_TOSA=m CONFIG_BACKLIGHT_PWM=m CONFIG_BACKLIGHT_TOSA=m -CONFIG_FRAMEBUFFER_CONSOLE=m +CONFIG_FRAMEBUFFER_CONSOLE=y CONFIG_FRAMEBUFFER_CONSOLE_ROTATION=y CONFIG_LOGO=y CONFIG_SOUND=m diff --git a/arch/arm/configs/viper_defconfig b/arch/arm/configs/viper_defconfig index 44d4fa57ba0a..070e5074f1ee 100644 --- a/arch/arm/configs/viper_defconfig +++ b/arch/arm/configs/viper_defconfig @@ -113,7 +113,7 @@ CONFIG_FB_PXA_PARAMETERS=y CONFIG_BACKLIGHT_LCD_SUPPORT=y CONFIG_BACKLIGHT_PWM=m # CONFIG_VGA_CONSOLE is not set -CONFIG_FRAMEBUFFER_CONSOLE=m +CONFIG_FRAMEBUFFER_CONSOLE=y CONFIG_LOGO=y CONFIG_SOUND=m CONFIG_SND=m diff --git a/arch/arm/configs/zeus_defconfig b/arch/arm/configs/zeus_defconfig index 8d4c0c926c34..09e7050d5653 100644 --- a/arch/arm/configs/zeus_defconfig +++ b/arch/arm/configs/zeus_defconfig @@ -112,7 +112,7 @@ CONFIG_FB_PXA=m CONFIG_FB_PXA_PARAMETERS=y CONFIG_BACKLIGHT_LCD_SUPPORT=y # CONFIG_VGA_CONSOLE is not set -CONFIG_FRAMEBUFFER_CONSOLE=m +CONFIG_FRAMEBUFFER_CONSOLE=y CONFIG_LOGO=y CONFIG_SOUND=m CONFIG_SND=m diff --git a/arch/arm/mach-at91/pm.c b/arch/arm/mach-at91/pm.c index 5036f996e694..849014c01cf4 100644 --- a/arch/arm/mach-at91/pm.c +++ b/arch/arm/mach-at91/pm.c @@ -533,8 +533,8 @@ static void __init at91_pm_backup_init(void) } pm_bu->suspended = 0; - pm_bu->canary = virt_to_phys(&canary); - pm_bu->resume = virt_to_phys(cpu_resume); + pm_bu->canary = __pa_symbol(&canary); + pm_bu->resume = __pa_symbol(cpu_resume); return; diff --git a/arch/arm/mach-omap2/hsmmc.c b/arch/arm/mach-omap2/hsmmc.c index 5b614388d72f..6d28aa20a7d3 100644 --- a/arch/arm/mach-omap2/hsmmc.c +++ b/arch/arm/mach-omap2/hsmmc.c @@ -58,10 +58,10 @@ void omap_hsmmc_late_init(struct omap2_hsmmc_info *c) struct platform_device *pdev; int res; - if (omap_hsmmc_done != 1) + if (omap_hsmmc_done) return; - omap_hsmmc_done++; + omap_hsmmc_done = 1; for (; c->mmc; c++) { pdev = c->pdev; diff --git a/arch/arm/mach-omap2/omap_hwmod_7xx_data.c b/arch/arm/mach-omap2/omap_hwmod_7xx_data.c index f040244c57e7..2f4f7002f38d 100644 --- a/arch/arm/mach-omap2/omap_hwmod_7xx_data.c +++ b/arch/arm/mach-omap2/omap_hwmod_7xx_data.c @@ -839,6 +839,7 @@ static struct omap_hwmod dra7xx_gpio1_hwmod = { .name = "gpio1", .class = &dra7xx_gpio_hwmod_class, .clkdm_name = "wkupaon_clkdm", + .flags = HWMOD_CONTROL_OPT_CLKS_IN_RESET, .main_clk = "wkupaon_iclk_mux", .prcm = { .omap4 = { diff --git a/arch/arm64/boot/dts/amlogic/meson-gx-p23x-q20x.dtsi b/arch/arm64/boot/dts/amlogic/meson-gx-p23x-q20x.dtsi index c89010e56488..4157987f4a3d 100644 --- a/arch/arm64/boot/dts/amlogic/meson-gx-p23x-q20x.dtsi +++ b/arch/arm64/boot/dts/amlogic/meson-gx-p23x-q20x.dtsi @@ -168,7 +168,8 @@ &sd_emmc_a { status = "okay"; pinctrl-0 = <&sdio_pins>; - pinctrl-names = "default"; + pinctrl-1 = <&sdio_clk_gate_pins>; + pinctrl-names = "default", "clk-gate"; #address-cells = <1>; #size-cells = <0>; @@ -194,7 +195,8 @@ &sd_emmc_b { status = "okay"; pinctrl-0 = <&sdcard_pins>; - pinctrl-names = "default"; + pinctrl-1 = <&sdcard_clk_gate_pins>; + pinctrl-names = "default", "clk-gate"; bus-width = <4>; cap-sd-highspeed; @@ -212,10 +214,10 @@ &sd_emmc_c { status = "okay"; pinctrl-0 = <&emmc_pins>; - pinctrl-names = "default"; + pinctrl-1 = <&emmc_clk_gate_pins>; + pinctrl-names = "default", "clk-gate"; bus-width = <8>; - cap-sd-highspeed; cap-mmc-highspeed; max-frequency = <200000000>; non-removable; diff --git a/arch/arm64/boot/dts/amlogic/meson-gxbb-nanopi-k2.dts b/arch/arm64/boot/dts/amlogic/meson-gxbb-nanopi-k2.dts index 9697a7a79464..4b17a76959b2 100644 --- a/arch/arm64/boot/dts/amlogic/meson-gxbb-nanopi-k2.dts +++ b/arch/arm64/boot/dts/amlogic/meson-gxbb-nanopi-k2.dts @@ -107,6 +107,9 @@ states = <3300000 0>, <1800000 1>; + + regulator-settling-time-up-us = <100>; + regulator-settling-time-down-us = <5000>; }; wifi_32k: wifi-32k { @@ -250,7 +253,8 @@ &sd_emmc_a { status = "okay"; pinctrl-0 = <&sdio_pins>, <&sdio_irq_pins>; - pinctrl-names = "default"; + pinctrl-1 = <&sdio_clk_gate_pins>; + pinctrl-names = "default", "clk-gate"; #address-cells = <1>; #size-cells = <0>; @@ -276,11 +280,16 @@ &sd_emmc_b { status = "okay"; pinctrl-0 = <&sdcard_pins>; - pinctrl-names = "default"; + pinctrl-1 = <&sdcard_clk_gate_pins>; + pinctrl-names = "default", "clk-gate"; bus-width = <4>; cap-sd-highspeed; - max-frequency = <100000000>; + sd-uhs-sdr12; + sd-uhs-sdr25; + sd-uhs-sdr50; + sd-uhs-sdr104; + max-frequency = <200000000>; disable-wp; cd-gpios = <&gpio CARD_6 GPIO_ACTIVE_HIGH>; @@ -294,10 +303,10 @@ &sd_emmc_c { status = "disabled"; pinctrl-0 = <&emmc_pins>; - pinctrl-names = "default"; + pinctrl-1 = <&emmc_clk_gate_pins>; + pinctrl-names = "default", "clk-gate"; bus-width = <8>; - cap-sd-highspeed; max-frequency = <200000000>; non-removable; disable-wp; diff --git a/arch/arm64/boot/dts/amlogic/meson-gxbb-nexbox-a95x.dts b/arch/arm64/boot/dts/amlogic/meson-gxbb-nexbox-a95x.dts index 9c59c3c6d1b6..38dfdde5c147 100644 --- a/arch/arm64/boot/dts/amlogic/meson-gxbb-nexbox-a95x.dts +++ b/arch/arm64/boot/dts/amlogic/meson-gxbb-nexbox-a95x.dts @@ -51,7 +51,7 @@ / { compatible = "nexbox,a95x", "amlogic,meson-gxbb"; model = "NEXBOX A95X"; - + aliases { serial0 = &uart_AO; }; @@ -232,7 +232,8 @@ &sd_emmc_a { status = "okay"; pinctrl-0 = <&sdio_pins>; - pinctrl-names = "default"; + pinctrl-1 = <&sdio_clk_gate_pins>; + pinctrl-names = "default", "clk-gate"; #address-cells = <1>; #size-cells = <0>; @@ -253,7 +254,8 @@ &sd_emmc_b { status = "okay"; pinctrl-0 = <&sdcard_pins>; - pinctrl-names = "default"; + pinctrl-1 = <&sdcard_clk_gate_pins>; + pinctrl-names = "default", "clk-gate"; bus-width = <4>; cap-sd-highspeed; @@ -271,10 +273,10 @@ &sd_emmc_c { status = "okay"; pinctrl-0 = <&emmc_pins>; - pinctrl-names = "default"; + pinctrl-1 = <&emmc_clk_gate_pins>; + pinctrl-names = "default", "clk-gate"; bus-width = <8>; - cap-sd-highspeed; cap-mmc-highspeed; max-frequency = <200000000>; non-removable; diff --git a/arch/arm64/boot/dts/amlogic/meson-gxbb-odroidc2.dts b/arch/arm64/boot/dts/amlogic/meson-gxbb-odroidc2.dts index d147c853ab05..1ffa1c238a72 100644 --- a/arch/arm64/boot/dts/amlogic/meson-gxbb-odroidc2.dts +++ b/arch/arm64/boot/dts/amlogic/meson-gxbb-odroidc2.dts @@ -50,7 +50,7 @@ / { compatible = "hardkernel,odroid-c2", "amlogic,meson-gxbb"; model = "Hardkernel ODROID-C2"; - + aliases { serial0 = &uart_AO; }; @@ -253,7 +253,8 @@ &sd_emmc_b { status = "okay"; pinctrl-0 = <&sdcard_pins>; - pinctrl-names = "default"; + pinctrl-1 = <&sdcard_clk_gate_pins>; + pinctrl-names = "default", "clk-gate"; bus-width = <4>; cap-sd-highspeed; @@ -271,10 +272,10 @@ &sd_emmc_c { status = "okay"; pinctrl-0 = <&emmc_pins>; - pinctrl-names = "default"; + pinctrl-1 = <&emmc_clk_gate_pins>; + pinctrl-names = "default", "clk-gate"; bus-width = <8>; - cap-sd-highspeed; max-frequency = <200000000>; non-removable; disable-wp; diff --git a/arch/arm64/boot/dts/amlogic/meson-gxbb-p20x.dtsi b/arch/arm64/boot/dts/amlogic/meson-gxbb-p20x.dtsi index 81ffc689a5bf..23c08c3afd0a 100644 --- a/arch/arm64/boot/dts/amlogic/meson-gxbb-p20x.dtsi +++ b/arch/arm64/boot/dts/amlogic/meson-gxbb-p20x.dtsi @@ -194,7 +194,8 @@ &sd_emmc_a { status = "okay"; pinctrl-0 = <&sdio_pins>; - pinctrl-names = "default"; + pinctrl-1 = <&sdio_clk_gate_pins>; + pinctrl-names = "default", "clk-gate"; #address-cells = <1>; #size-cells = <0>; @@ -220,10 +221,14 @@ &sd_emmc_b { status = "okay"; pinctrl-0 = <&sdcard_pins>; - pinctrl-names = "default"; + pinctrl-1 = <&sdcard_clk_gate_pins>; + pinctrl-names = "default", "clk-gate"; bus-width = <4>; cap-sd-highspeed; + sd-uhs-sdr12; + sd-uhs-sdr25; + sd-uhs-sdr50; max-frequency = <100000000>; disable-wp; @@ -238,10 +243,10 @@ &sd_emmc_c { status = "okay"; pinctrl-0 = <&emmc_pins>; - pinctrl-names = "default"; + pinctrl-1 = <&emmc_clk_gate_pins>; + pinctrl-names = "default", "clk-gate"; bus-width = <8>; - cap-sd-highspeed; cap-mmc-highspeed; max-frequency = <200000000>; non-removable; diff --git a/arch/arm64/boot/dts/amlogic/meson-gxbb-vega-s95.dtsi b/arch/arm64/boot/dts/amlogic/meson-gxbb-vega-s95.dtsi index 346753fb6324..f2bc6dea1fc6 100644 --- a/arch/arm64/boot/dts/amlogic/meson-gxbb-vega-s95.dtsi +++ b/arch/arm64/boot/dts/amlogic/meson-gxbb-vega-s95.dtsi @@ -155,7 +155,8 @@ &sd_emmc_a { status = "okay"; pinctrl-0 = <&sdio_pins &sdio_irq_pins>; - pinctrl-names = "default"; + pinctrl-1 = <&sdio_clk_gate_pins>; + pinctrl-names = "default", "clk-gate"; #address-cells = <1>; #size-cells = <0>; @@ -181,7 +182,8 @@ &sd_emmc_b { status = "okay"; pinctrl-0 = <&sdcard_pins>; - pinctrl-names = "default"; + pinctrl-1 = <&sdcard_clk_gate_pins>; + pinctrl-names = "default", "clk-gate"; bus-width = <4>; cap-sd-highspeed; @@ -198,10 +200,10 @@ &sd_emmc_c { status = "okay"; pinctrl-0 = <&emmc_pins>; - pinctrl-names = "default"; + pinctrl-1 = <&emmc_clk_gate_pins>; + pinctrl-names = "default", "clk-gate"; bus-width = <8>; - cap-sd-highspeed; cap-mmc-highspeed; max-frequency = <200000000>; non-removable; diff --git a/arch/arm64/boot/dts/amlogic/meson-gxbb.dtsi b/arch/arm64/boot/dts/amlogic/meson-gxbb.dtsi index 52f1687e7a09..af834cdbba79 100644 --- a/arch/arm64/boot/dts/amlogic/meson-gxbb.dtsi +++ b/arch/arm64/boot/dts/amlogic/meson-gxbb.dtsi @@ -392,6 +392,17 @@ }; }; + emmc_clk_gate_pins: emmc_clk_gate { + mux { + groups = "BOOT_8"; + function = "gpio_periphs"; + }; + cfg-pull-down { + pins = "BOOT_8"; + bias-pull-down; + }; + }; + nor_pins: nor { mux { groups = "nor_d", @@ -430,6 +441,17 @@ }; }; + sdcard_clk_gate_pins: sdcard_clk_gate { + mux { + groups = "CARD_2"; + function = "gpio_periphs"; + }; + cfg-pull-down { + pins = "CARD_2"; + bias-pull-down; + }; + }; + sdio_pins: sdio { mux { groups = "sdio_d0", @@ -442,6 +464,17 @@ }; }; + sdio_clk_gate_pins: sdio_clk_gate { + mux { + groups = "GPIOX_4"; + function = "gpio_periphs"; + }; + cfg-pull-down { + pins = "GPIOX_4"; + bias-pull-down; + }; + }; + sdio_irq_pins: sdio_irq { mux { groups = "sdio_irq"; @@ -661,21 +694,21 @@ &sd_emmc_a { clocks = <&clkc CLKID_SD_EMMC_A>, - <&xtal>, + <&clkc CLKID_SD_EMMC_A_CLK0>, <&clkc CLKID_FCLK_DIV2>; clock-names = "core", "clkin0", "clkin1"; }; &sd_emmc_b { clocks = <&clkc CLKID_SD_EMMC_B>, - <&xtal>, + <&clkc CLKID_SD_EMMC_B_CLK0>, <&clkc CLKID_FCLK_DIV2>; clock-names = "core", "clkin0", "clkin1"; }; &sd_emmc_c { clocks = <&clkc CLKID_SD_EMMC_C>, - <&xtal>, + <&clkc CLKID_SD_EMMC_C_CLK0>, <&clkc CLKID_FCLK_DIV2>; clock-names = "core", "clkin0", "clkin1"; }; diff --git a/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-hwacom-amazetv.dts b/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-hwacom-amazetv.dts index 2a5804ce7f4b..977b4240f3c1 100644 --- a/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-hwacom-amazetv.dts +++ b/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-hwacom-amazetv.dts @@ -123,7 +123,8 @@ &sd_emmc_b { status = "okay"; pinctrl-0 = <&sdcard_pins>; - pinctrl-names = "default"; + pinctrl-1 = <&sdcard_clk_gate_pins>; + pinctrl-names = "default", "clk-gate"; bus-width = <4>; cap-sd-highspeed; @@ -141,10 +142,10 @@ &sd_emmc_c { status = "okay"; pinctrl-0 = <&emmc_pins>; - pinctrl-names = "default"; + pinctrl-1 = <&emmc_clk_gate_pins>; + pinctrl-names = "default", "clk-gate"; bus-width = <8>; - cap-sd-highspeed; cap-mmc-highspeed; max-frequency = <100000000>; non-removable; diff --git a/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-libretech-cc.dts b/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-libretech-cc.dts index 69ca14ac10fa..64c54c92e214 100644 --- a/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-libretech-cc.dts +++ b/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-libretech-cc.dts @@ -91,6 +91,9 @@ states = <3300000 0>, <1800000 1>; + + regulator-settling-time-up-us = <200>; + regulator-settling-time-down-us = <50000>; }; vddio_boot: regulator-vddio_boot { @@ -197,10 +200,14 @@ &sd_emmc_b { status = "okay"; pinctrl-0 = <&sdcard_pins>; - pinctrl-names = "default"; + pinctrl-1 = <&sdcard_clk_gate_pins>; + pinctrl-names = "default", "clk-gate"; bus-width = <4>; cap-sd-highspeed; + sd-uhs-sdr12; + sd-uhs-sdr25; + sd-uhs-sdr50; max-frequency = <100000000>; disable-wp; @@ -215,10 +222,12 @@ &sd_emmc_c { status = "okay"; pinctrl-0 = <&emmc_pins>; - pinctrl-names = "default"; + pinctrl-1 = <&emmc_clk_gate_pins>; + pinctrl-names = "default", "clk-gate"; bus-width = <8>; cap-mmc-highspeed; + mmc-ddr-3_3v; max-frequency = <50000000>; non-removable; disable-wp; diff --git a/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-nexbox-a95x.dts b/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-nexbox-a95x.dts index 4c2ac7650fcd..1b8f32867aa1 100644 --- a/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-nexbox-a95x.dts +++ b/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-nexbox-a95x.dts @@ -189,7 +189,8 @@ &sd_emmc_a { status = "okay"; pinctrl-0 = <&sdio_pins>; - pinctrl-names = "default"; + pinctrl-1 = <&sdio_clk_gate_pins>; + pinctrl-names = "default", "clk-gate"; #address-cells = <1>; #size-cells = <0>; @@ -210,7 +211,8 @@ &sd_emmc_b { status = "okay"; pinctrl-0 = <&sdcard_pins>; - pinctrl-names = "default"; + pinctrl-1 = <&sdcard_clk_gate_pins>; + pinctrl-names = "default", "clk-gate"; bus-width = <4>; cap-sd-highspeed; @@ -228,10 +230,10 @@ &sd_emmc_c { status = "okay"; pinctrl-0 = <&emmc_pins>; - pinctrl-names = "default"; + pinctrl-1 = <&emmc_clk_gate_pins>; + pinctrl-names = "default", "clk-gate"; bus-width = <8>; - cap-sd-highspeed; cap-mmc-highspeed; max-frequency = <200000000>; non-removable; diff --git a/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-p212.dtsi b/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-p212.dtsi index f3eea8e89d12..129af9068814 100644 --- a/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-p212.dtsi +++ b/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-p212.dtsi @@ -95,7 +95,8 @@ &sd_emmc_a { status = "okay"; pinctrl-0 = <&sdio_pins>; - pinctrl-names = "default"; + pinctrl-1 = <&sdio_clk_gate_pins>; + pinctrl-names = "default", "clk-gate"; #address-cells = <1>; #size-cells = <0>; @@ -116,7 +117,8 @@ &sd_emmc_b { status = "okay"; pinctrl-0 = <&sdcard_pins>; - pinctrl-names = "default"; + pinctrl-1 = <&sdcard_clk_gate_pins>; + pinctrl-names = "default", "clk-gate"; bus-width = <4>; cap-sd-highspeed; @@ -134,10 +136,10 @@ &sd_emmc_c { status = "okay"; pinctrl-0 = <&emmc_pins>; - pinctrl-names = "default"; + pinctrl-1 = <&emmc_clk_gate_pins>; + pinctrl-names = "default", "clk-gate"; bus-width = <8>; - cap-sd-highspeed; cap-mmc-highspeed; max-frequency = <200000000>; non-removable; diff --git a/arch/arm64/boot/dts/amlogic/meson-gxl.dtsi b/arch/arm64/boot/dts/amlogic/meson-gxl.dtsi index d6876e64979e..d8dd3298b15c 100644 --- a/arch/arm64/boot/dts/amlogic/meson-gxl.dtsi +++ b/arch/arm64/boot/dts/amlogic/meson-gxl.dtsi @@ -281,6 +281,17 @@ }; }; + emmc_clk_gate_pins: emmc_clk_gate { + mux { + groups = "BOOT_8"; + function = "gpio_periphs"; + }; + cfg-pull-down { + pins = "BOOT_8"; + bias-pull-down; + }; + }; + nor_pins: nor { mux { groups = "nor_d", @@ -319,6 +330,17 @@ }; }; + sdcard_clk_gate_pins: sdcard_clk_gate { + mux { + groups = "CARD_2"; + function = "gpio_periphs"; + }; + cfg-pull-down { + pins = "CARD_2"; + bias-pull-down; + }; + }; + sdio_pins: sdio { mux { groups = "sdio_d0", @@ -331,6 +353,17 @@ }; }; + sdio_clk_gate_pins: sdio_clk_gate { + mux { + groups = "GPIOX_4"; + function = "gpio_periphs"; + }; + cfg-pull-down { + pins = "GPIOX_4"; + bias-pull-down; + }; + }; + sdio_irq_pins: sdio_irq { mux { groups = "sdio_irq"; @@ -603,21 +636,21 @@ &sd_emmc_a { clocks = <&clkc CLKID_SD_EMMC_A>, - <&xtal>, + <&clkc CLKID_SD_EMMC_A_CLK0>, <&clkc CLKID_FCLK_DIV2>; clock-names = "core", "clkin0", "clkin1"; }; &sd_emmc_b { clocks = <&clkc CLKID_SD_EMMC_B>, - <&xtal>, + <&clkc CLKID_SD_EMMC_B_CLK0>, <&clkc CLKID_FCLK_DIV2>; clock-names = "core", "clkin0", "clkin1"; }; &sd_emmc_c { clocks = <&clkc CLKID_SD_EMMC_C>, - <&xtal>, + <&clkc CLKID_SD_EMMC_C_CLK0>, <&clkc CLKID_FCLK_DIV2>; clock-names = "core", "clkin0", "clkin1"; }; diff --git a/arch/arm64/boot/dts/amlogic/meson-gxm-nexbox-a1.dts b/arch/arm64/boot/dts/amlogic/meson-gxm-nexbox-a1.dts index 9b10c5f4f8c0..22c697732f66 100644 --- a/arch/arm64/boot/dts/amlogic/meson-gxm-nexbox-a1.dts +++ b/arch/arm64/boot/dts/amlogic/meson-gxm-nexbox-a1.dts @@ -175,7 +175,8 @@ &sd_emmc_b { status = "okay"; pinctrl-0 = <&sdcard_pins>; - pinctrl-names = "default"; + pinctrl-1 = <&sdcard_clk_gate_pins>; + pinctrl-names = "default", "clk-gate"; bus-width = <4>; cap-sd-highspeed; @@ -193,10 +194,10 @@ &sd_emmc_c { status = "okay"; pinctrl-0 = <&emmc_pins>; - pinctrl-names = "default"; + pinctrl-1 = <&emmc_clk_gate_pins>; + pinctrl-names = "default", "clk-gate"; bus-width = <8>; - cap-sd-highspeed; cap-mmc-highspeed; max-frequency = <200000000>; non-removable; diff --git a/arch/arm64/boot/dts/amlogic/meson-gxm-rbox-pro.dts b/arch/arm64/boot/dts/amlogic/meson-gxm-rbox-pro.dts index 08f1dd69b679..470f72bb863c 100644 --- a/arch/arm64/boot/dts/amlogic/meson-gxm-rbox-pro.dts +++ b/arch/arm64/boot/dts/amlogic/meson-gxm-rbox-pro.dts @@ -220,7 +220,6 @@ pinctrl-names = "default"; bus-width = <8>; - cap-sd-highspeed; cap-mmc-highspeed; max-frequency = <200000000>; non-removable; diff --git a/arch/arm64/boot/dts/marvell/armada-ap806.dtsi b/arch/arm64/boot/dts/marvell/armada-ap806.dtsi index 4d360713ed12..30d48ecf46e0 100644 --- a/arch/arm64/boot/dts/marvell/armada-ap806.dtsi +++ b/arch/arm64/boot/dts/marvell/armada-ap806.dtsi @@ -254,7 +254,7 @@ ap_syscon: system-controller@6f4000 { compatible = "syscon", "simple-mfd"; - reg = <0x6f4000 0x1000>; + reg = <0x6f4000 0x2000>; ap_clk: clock { compatible = "marvell,ap806-clock"; @@ -265,7 +265,7 @@ compatible = "marvell,ap806-pinctrl"; }; - ap_gpio: gpio { + ap_gpio: gpio@1040 { compatible = "marvell,armada-8k-gpio"; offset = <0x1040>; ngpios = <20>; diff --git a/arch/arm64/boot/dts/rockchip/rk3368.dtsi b/arch/arm64/boot/dts/rockchip/rk3368.dtsi index e0518b4bc6c2..19fbaa5e7bdd 100644 --- a/arch/arm64/boot/dts/rockchip/rk3368.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3368.dtsi @@ -113,8 +113,7 @@ compatible = "arm,cortex-a53", "arm,armv8"; reg = <0x0 0x0>; enable-method = "psci"; - clocks = <&cru ARMCLKL>; - operating-points-v2 = <&cluster0_opp>; + #cooling-cells = <2>; /* min followed by max */ }; @@ -123,8 +122,6 @@ compatible = "arm,cortex-a53", "arm,armv8"; reg = <0x0 0x1>; enable-method = "psci"; - clocks = <&cru ARMCLKL>; - operating-points-v2 = <&cluster0_opp>; }; cpu_l2: cpu@2 { @@ -132,8 +129,6 @@ compatible = "arm,cortex-a53", "arm,armv8"; reg = <0x0 0x2>; enable-method = "psci"; - clocks = <&cru ARMCLKL>; - operating-points-v2 = <&cluster0_opp>; }; cpu_l3: cpu@3 { @@ -141,8 +136,6 @@ compatible = "arm,cortex-a53", "arm,armv8"; reg = <0x0 0x3>; enable-method = "psci"; - clocks = <&cru ARMCLKL>; - operating-points-v2 = <&cluster0_opp>; }; cpu_b0: cpu@100 { @@ -150,8 +143,7 @@ compatible = "arm,cortex-a53", "arm,armv8"; reg = <0x0 0x100>; enable-method = "psci"; - clocks = <&cru ARMCLKB>; - operating-points-v2 = <&cluster1_opp>; + #cooling-cells = <2>; /* min followed by max */ }; @@ -160,8 +152,6 @@ compatible = "arm,cortex-a53", "arm,armv8"; reg = <0x0 0x101>; enable-method = "psci"; - clocks = <&cru ARMCLKB>; - operating-points-v2 = <&cluster1_opp>; }; cpu_b2: cpu@102 { @@ -169,8 +159,6 @@ compatible = "arm,cortex-a53", "arm,armv8"; reg = <0x0 0x102>; enable-method = "psci"; - clocks = <&cru ARMCLKB>; - operating-points-v2 = <&cluster1_opp>; }; cpu_b3: cpu@103 { @@ -178,62 +166,6 @@ compatible = "arm,cortex-a53", "arm,armv8"; reg = <0x0 0x103>; enable-method = "psci"; - clocks = <&cru ARMCLKB>; - operating-points-v2 = <&cluster1_opp>; - }; - }; - - cluster0_opp: opp-table0 { - compatible = "operating-points-v2"; - opp-shared; - - opp00 { - opp-hz = /bits/ 64 <312000000>; - opp-microvolt = <950000>; - clock-latency-ns = <40000>; - }; - opp01 { - opp-hz = /bits/ 64 <408000000>; - opp-microvolt = <950000>; - }; - opp02 { - opp-hz = /bits/ 64 <600000000>; - opp-microvolt = <950000>; - }; - opp03 { - opp-hz = /bits/ 64 <816000000>; - opp-microvolt = <1025000>; - }; - opp04 { - opp-hz = /bits/ 64 <1008000000>; - opp-microvolt = <1125000>; - }; - }; - - cluster1_opp: opp-table1 { - compatible = "operating-points-v2"; - opp-shared; - - opp00 { - opp-hz = /bits/ 64 <312000000>; - opp-microvolt = <950000>; - clock-latency-ns = <40000>; - }; - opp01 { - opp-hz = /bits/ 64 <408000000>; - opp-microvolt = <950000>; - }; - opp02 { - opp-hz = /bits/ 64 <600000000>; - opp-microvolt = <950000>; - }; - opp03 { - opp-hz = /bits/ 64 <816000000>; - opp-microvolt = <975000>; - }; - opp04 { - opp-hz = /bits/ 64 <1008000000>; - opp-microvolt = <1050000>; }; }; diff --git a/arch/arm64/boot/dts/rockchip/rk3399.dtsi b/arch/arm64/boot/dts/rockchip/rk3399.dtsi index d79e9b3265b9..ab7629c5b856 100644 --- a/arch/arm64/boot/dts/rockchip/rk3399.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3399.dtsi @@ -1629,9 +1629,9 @@ compatible = "rockchip,rk3399-mipi-dsi", "snps,dw-mipi-dsi"; reg = <0x0 0xff960000 0x0 0x8000>; interrupts = <GIC_SPI 45 IRQ_TYPE_LEVEL_HIGH 0>; - clocks = <&cru SCLK_MIPIDPHY_REF>, <&cru PCLK_MIPI_DSI0>, - <&cru SCLK_DPHY_TX0_CFG>; - clock-names = "ref", "pclk", "phy_cfg"; + clocks = <&cru SCLK_DPHY_PLL>, <&cru PCLK_MIPI_DSI0>, + <&cru SCLK_DPHY_TX0_CFG>, <&cru PCLK_VIO_GRF>; + clock-names = "ref", "pclk", "phy_cfg", "grf"; power-domains = <&power RK3399_PD_VIO>; rockchip,grf = <&grf>; status = "disabled"; diff --git a/arch/arm64/include/asm/memory.h b/arch/arm64/include/asm/memory.h index 3585a5e26151..f7c4d2146aed 100644 --- a/arch/arm64/include/asm/memory.h +++ b/arch/arm64/include/asm/memory.h @@ -95,16 +95,19 @@ #define KERNEL_END _end /* - * The size of the KASAN shadow region. This should be 1/8th of the - * size of the entire kernel virtual address space. + * KASAN requires 1/8th of the kernel virtual address space for the shadow + * region. KASAN can bloat the stack significantly, so double the (minimum) + * stack size when KASAN is in use. */ #ifdef CONFIG_KASAN #define KASAN_SHADOW_SIZE (UL(1) << (VA_BITS - 3)) +#define KASAN_THREAD_SHIFT 1 #else #define KASAN_SHADOW_SIZE (0) +#define KASAN_THREAD_SHIFT 0 #endif -#define MIN_THREAD_SHIFT 14 +#define MIN_THREAD_SHIFT (14 + KASAN_THREAD_SHIFT) /* * VMAP'd stacks are allocated at page granularity, so we must ensure that such diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h index bc4e92337d16..b46e54c2399b 100644 --- a/arch/arm64/include/asm/pgtable.h +++ b/arch/arm64/include/asm/pgtable.h @@ -401,7 +401,7 @@ static inline phys_addr_t pmd_page_paddr(pmd_t pmd) /* Find an entry in the third-level page table. */ #define pte_index(addr) (((addr) >> PAGE_SHIFT) & (PTRS_PER_PTE - 1)) -#define pte_offset_phys(dir,addr) (pmd_page_paddr(*(dir)) + pte_index(addr) * sizeof(pte_t)) +#define pte_offset_phys(dir,addr) (pmd_page_paddr(READ_ONCE(*(dir))) + pte_index(addr) * sizeof(pte_t)) #define pte_offset_kernel(dir,addr) ((pte_t *)__va(pte_offset_phys((dir), (addr)))) #define pte_offset_map(dir,addr) pte_offset_kernel((dir), (addr)) diff --git a/arch/arm64/kernel/armv8_deprecated.c b/arch/arm64/kernel/armv8_deprecated.c index f0e6d717885b..d06fbe4cd38d 100644 --- a/arch/arm64/kernel/armv8_deprecated.c +++ b/arch/arm64/kernel/armv8_deprecated.c @@ -649,4 +649,4 @@ static int __init armv8_deprecated_init(void) return 0; } -late_initcall(armv8_deprecated_init); +core_initcall(armv8_deprecated_init); diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c index cd52d365d1f0..21e2c95d24e7 100644 --- a/arch/arm64/kernel/cpufeature.c +++ b/arch/arm64/kernel/cpufeature.c @@ -1307,4 +1307,4 @@ static int __init enable_mrs_emulation(void) return 0; } -late_initcall(enable_mrs_emulation); +core_initcall(enable_mrs_emulation); diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c index f444f374bd7b..5d547deb6996 100644 --- a/arch/arm64/kernel/fpsimd.c +++ b/arch/arm64/kernel/fpsimd.c @@ -444,4 +444,4 @@ static int __init fpsimd_init(void) return 0; } -late_initcall(fpsimd_init); +core_initcall(fpsimd_init); diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S index 7434ec0c7a27..0b243ecaf7ac 100644 --- a/arch/arm64/kernel/head.S +++ b/arch/arm64/kernel/head.S @@ -384,6 +384,7 @@ ENTRY(kimage_vaddr) * booted in EL1 or EL2 respectively. */ ENTRY(el2_setup) + msr SPsel, #1 // We want to use SP_EL{1,2} mrs x0, CurrentEL cmp x0, #CurrentEL_EL2 b.eq 1f diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c index 89993c4be1be..b64958b23a7f 100644 --- a/arch/arm64/mm/fault.c +++ b/arch/arm64/mm/fault.c @@ -97,7 +97,7 @@ static void data_abort_decode(unsigned int esr) (esr & ESR_ELx_SF) >> ESR_ELx_SF_SHIFT, (esr & ESR_ELx_AR) >> ESR_ELx_AR_SHIFT); } else { - pr_alert(" ISV = 0, ISS = 0x%08lu\n", esr & ESR_ELx_ISS_MASK); + pr_alert(" ISV = 0, ISS = 0x%08lx\n", esr & ESR_ELx_ISS_MASK); } pr_alert(" CM = %lu, WnR = %lu\n", @@ -651,7 +651,7 @@ static const struct fault_info fault_info[] = { { do_translation_fault, SIGSEGV, SEGV_MAPERR, "level 0 translation fault" }, { do_translation_fault, SIGSEGV, SEGV_MAPERR, "level 1 translation fault" }, { do_translation_fault, SIGSEGV, SEGV_MAPERR, "level 2 translation fault" }, - { do_page_fault, SIGSEGV, SEGV_MAPERR, "level 3 translation fault" }, + { do_translation_fault, SIGSEGV, SEGV_MAPERR, "level 3 translation fault" }, { do_bad, SIGBUS, 0, "unknown 8" }, { do_page_fault, SIGSEGV, SEGV_ACCERR, "level 1 access flag fault" }, { do_page_fault, SIGSEGV, SEGV_ACCERR, "level 2 access flag fault" }, diff --git a/arch/m32r/Kconfig b/arch/m32r/Kconfig index 87cde1e4b38c..0777f3a8a1f3 100644 --- a/arch/m32r/Kconfig +++ b/arch/m32r/Kconfig @@ -194,6 +194,10 @@ config TIMER_DIVIDE int "Timer divider (integer)" default "128" +config CPU_BIG_ENDIAN + bool "Generate big endian code" + default n + config CPU_LITTLE_ENDIAN bool "Generate little endian code" default n diff --git a/arch/m32r/kernel/traps.c b/arch/m32r/kernel/traps.c index 647dd94a0c39..72b96f282689 100644 --- a/arch/m32r/kernel/traps.c +++ b/arch/m32r/kernel/traps.c @@ -114,6 +114,15 @@ static void set_eit_vector_entries(void) _flush_cache_copyback_all(); } +void abort(void) +{ + BUG(); + + /* if that doesn't kill us, halt */ + panic("Oops failed to kill thread"); +} +EXPORT_SYMBOL(abort); + void __init trap_init(void) { set_eit_vector_entries(); diff --git a/arch/microblaze/Kconfig b/arch/microblaze/Kconfig index 9d26abdf0dc1..4f798aa671dd 100644 --- a/arch/microblaze/Kconfig +++ b/arch/microblaze/Kconfig @@ -39,7 +39,7 @@ config MICROBLAZE # Endianness selection choice prompt "Endianness selection" - default CPU_BIG_ENDIAN + default CPU_LITTLE_ENDIAN help microblaze architectures can be configured for either little or big endian formats. Be sure to select the appropriate mode. diff --git a/arch/microblaze/include/uapi/asm/Kbuild b/arch/microblaze/include/uapi/asm/Kbuild index e77a596f3f1e..06609ca36115 100644 --- a/arch/microblaze/include/uapi/asm/Kbuild +++ b/arch/microblaze/include/uapi/asm/Kbuild @@ -7,6 +7,7 @@ generic-y += fcntl.h generic-y += ioctl.h generic-y += ioctls.h generic-y += ipcbuf.h +generic-y += kvm_para.h generic-y += mman.h generic-y += msgbuf.h generic-y += param.h diff --git a/arch/microblaze/kernel/dma.c b/arch/microblaze/kernel/dma.c index e45ada8fb006..94700c5270a9 100644 --- a/arch/microblaze/kernel/dma.c +++ b/arch/microblaze/kernel/dma.c @@ -165,7 +165,7 @@ int dma_direct_mmap_coherent(struct device *dev, struct vm_area_struct *vma, unsigned long attrs) { #ifdef CONFIG_MMU - unsigned long user_count = (vma->vm_end - vma->vm_start) >> PAGE_SHIFT; + unsigned long user_count = vma_pages(vma); unsigned long count = PAGE_ALIGN(size) >> PAGE_SHIFT; unsigned long off = vma->vm_pgoff; unsigned long pfn; diff --git a/arch/parisc/kernel/process.c b/arch/parisc/kernel/process.c index a45a67d526f8..30f92391a93e 100644 --- a/arch/parisc/kernel/process.c +++ b/arch/parisc/kernel/process.c @@ -146,7 +146,7 @@ void machine_power_off(void) /* prevent soft lockup/stalled CPU messages for endless loop. */ rcu_sysrq_start(); - lockup_detector_suspend(); + lockup_detector_soft_poweroff(); for (;;); } diff --git a/arch/powerpc/kernel/dt_cpu_ftrs.c b/arch/powerpc/kernel/dt_cpu_ftrs.c index 1df770e8cbe0..7275fed271af 100644 --- a/arch/powerpc/kernel/dt_cpu_ftrs.c +++ b/arch/powerpc/kernel/dt_cpu_ftrs.c @@ -102,10 +102,10 @@ static void cpufeatures_flush_tlb(void) case PVR_POWER8: case PVR_POWER8E: case PVR_POWER8NVL: - __flush_tlb_power8(POWER8_TLB_SETS); + __flush_tlb_power8(TLB_INVAL_SCOPE_GLOBAL); break; case PVR_POWER9: - __flush_tlb_power9(POWER9_TLB_SETS_HASH); + __flush_tlb_power9(TLB_INVAL_SCOPE_GLOBAL); break; default: pr_err("unknown CPU version for boot TLB flush\n"); diff --git a/arch/powerpc/kernel/mce_power.c b/arch/powerpc/kernel/mce_power.c index b76ca198e09c..72f153c6f3fa 100644 --- a/arch/powerpc/kernel/mce_power.c +++ b/arch/powerpc/kernel/mce_power.c @@ -624,5 +624,18 @@ long __machine_check_early_realmode_p8(struct pt_regs *regs) long __machine_check_early_realmode_p9(struct pt_regs *regs) { + /* + * On POWER9 DD2.1 and below, it's possible to get a machine check + * caused by a paste instruction where only DSISR bit 25 is set. This + * will result in the MCE handler seeing an unknown event and the kernel + * crashing. An MCE that occurs like this is spurious, so we don't need + * to do anything in terms of servicing it. If there is something that + * needs to be serviced, the CPU will raise the MCE again with the + * correct DSISR so that it can be serviced properly. So detect this + * case and mark it as handled. + */ + if (SRR1_MC_LOADSTORE(regs->msr) && regs->dsisr == 0x02000000) + return 1; + return mce_handle_error(regs, mce_p9_derror_table, mce_p9_ierror_table); } diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c index 0ac741fae90e..2e3bc16d02b2 100644 --- a/arch/powerpc/kernel/setup-common.c +++ b/arch/powerpc/kernel/setup-common.c @@ -904,9 +904,6 @@ void __init setup_arch(char **cmdline_p) #endif #endif -#ifdef CONFIG_PPC_64K_PAGES - init_mm.context.pte_frag = NULL; -#endif #ifdef CONFIG_SPAPR_TCE_IOMMU mm_iommu_init(&init_mm); #endif diff --git a/arch/powerpc/kernel/watchdog.c b/arch/powerpc/kernel/watchdog.c index 2f6eadd9408d..c702a8981452 100644 --- a/arch/powerpc/kernel/watchdog.c +++ b/arch/powerpc/kernel/watchdog.c @@ -310,9 +310,6 @@ static int start_wd_on_cpu(unsigned int cpu) if (!(watchdog_enabled & NMI_WATCHDOG_ENABLED)) return 0; - if (watchdog_suspended) - return 0; - if (!cpumask_test_cpu(cpu, &watchdog_cpumask)) return 0; @@ -358,36 +355,39 @@ static void watchdog_calc_timeouts(void) wd_timer_period_ms = watchdog_thresh * 1000 * 2 / 5; } -void watchdog_nmi_reconfigure(void) +void watchdog_nmi_stop(void) { int cpu; - watchdog_calc_timeouts(); - for_each_cpu(cpu, &wd_cpus_enabled) stop_wd_on_cpu(cpu); +} +void watchdog_nmi_start(void) +{ + int cpu; + + watchdog_calc_timeouts(); for_each_cpu_and(cpu, cpu_online_mask, &watchdog_cpumask) start_wd_on_cpu(cpu); } /* - * This runs after lockup_detector_init() which sets up watchdog_cpumask. + * Invoked from core watchdog init. */ -static int __init powerpc_watchdog_init(void) +int __init watchdog_nmi_probe(void) { int err; - watchdog_calc_timeouts(); - - err = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "powerpc/watchdog:online", - start_wd_on_cpu, stop_wd_on_cpu); - if (err < 0) + err = cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN, + "powerpc/watchdog:online", + start_wd_on_cpu, stop_wd_on_cpu); + if (err < 0) { pr_warn("Watchdog could not be initialized"); - + return err; + } return 0; } -arch_initcall(powerpc_watchdog_init); static void handle_backtrace_ipi(struct pt_regs *regs) { diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S index 17936f82d3c7..ec69fa45d5a2 100644 --- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S +++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S @@ -1121,6 +1121,13 @@ END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR) BEGIN_FTR_SECTION mtspr SPRN_PPR, r0 END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR) + +/* Move canary into DSISR to check for later */ +BEGIN_FTR_SECTION + li r0, 0x7fff + mtspr SPRN_HDSISR, r0 +END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300) + ld r0, VCPU_GPR(R0)(r4) ld r4, VCPU_GPR(R4)(r4) @@ -1956,9 +1963,14 @@ END_MMU_FTR_SECTION_IFSET(MMU_FTR_TYPE_RADIX) kvmppc_hdsi: ld r3, VCPU_KVM(r9) lbz r0, KVM_RADIX(r3) - cmpwi r0, 0 mfspr r4, SPRN_HDAR mfspr r6, SPRN_HDSISR +BEGIN_FTR_SECTION + /* Look for DSISR canary. If we find it, retry instruction */ + cmpdi r6, 0x7fff + beq 6f +END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300) + cmpwi r0, 0 bne .Lradix_hdsi /* on radix, just save DAR/DSISR/ASDR */ /* HPTE not found fault or protection fault? */ andis. r0, r6, (DSISR_NOHPTE | DSISR_PROTFAULT)@h diff --git a/arch/powerpc/kvm/book3s_xive.c b/arch/powerpc/kvm/book3s_xive.c index 13304622ab1c..bf457843e032 100644 --- a/arch/powerpc/kvm/book3s_xive.c +++ b/arch/powerpc/kvm/book3s_xive.c @@ -622,7 +622,7 @@ int kvmppc_xive_get_xive(struct kvm *kvm, u32 irq, u32 *server, return -EINVAL; state = &sb->irq_state[idx]; arch_spin_lock(&sb->lock); - *server = state->guest_server; + *server = state->act_server; *priority = state->guest_priority; arch_spin_unlock(&sb->lock); @@ -1331,7 +1331,7 @@ static int xive_get_source(struct kvmppc_xive *xive, long irq, u64 addr) xive->saved_src_count++; /* Convert saved state into something compatible with xics */ - val = state->guest_server; + val = state->act_server; prio = state->saved_scan_prio; if (prio == MASKED) { @@ -1507,7 +1507,6 @@ static int xive_set_source(struct kvmppc_xive *xive, long irq, u64 addr) /* First convert prio and mark interrupt as untargetted */ act_prio = xive_prio_from_guest(guest_prio); state->act_priority = MASKED; - state->guest_server = server; /* * We need to drop the lock due to the mutex below. Hopefully diff --git a/arch/powerpc/kvm/book3s_xive.h b/arch/powerpc/kvm/book3s_xive.h index 5938f7644dc1..6ba63f8e8a61 100644 --- a/arch/powerpc/kvm/book3s_xive.h +++ b/arch/powerpc/kvm/book3s_xive.h @@ -35,7 +35,6 @@ struct kvmppc_xive_irq_state { struct xive_irq_data *pt_data; /* XIVE Pass-through associated data */ /* Targetting as set by guest */ - u32 guest_server; /* Current guest selected target */ u8 guest_priority; /* Guest set priority */ u8 saved_priority; /* Saved priority when masking */ diff --git a/arch/powerpc/mm/pgtable_32.c b/arch/powerpc/mm/pgtable_32.c index 65eda1997c3f..f6c7f54c0515 100644 --- a/arch/powerpc/mm/pgtable_32.c +++ b/arch/powerpc/mm/pgtable_32.c @@ -361,9 +361,9 @@ static int change_page_attr(struct page *page, int numpages, pgprot_t prot) break; } wmb(); + local_irq_restore(flags); flush_tlb_kernel_range((unsigned long)page_address(start), (unsigned long)page_address(page)); - local_irq_restore(flags); return err; } diff --git a/arch/powerpc/platforms/powernv/setup.c b/arch/powerpc/platforms/powernv/setup.c index 897aa1400eb8..bbb73aa0eb8f 100644 --- a/arch/powerpc/platforms/powernv/setup.c +++ b/arch/powerpc/platforms/powernv/setup.c @@ -272,7 +272,15 @@ static void pnv_kexec_cpu_down(int crash_shutdown, int secondary) #ifdef CONFIG_MEMORY_HOTPLUG_SPARSE static unsigned long pnv_memory_block_size(void) { - return 256UL * 1024 * 1024; + /* + * We map the kernel linear region with 1GB large pages on radix. For + * memory hot unplug to work our memory block size must be at least + * this size. + */ + if (radix_enabled()) + return 1UL * 1024 * 1024 * 1024; + else + return 256UL * 1024 * 1024; } #endif diff --git a/arch/powerpc/sysdev/fsl_rio.c b/arch/powerpc/sysdev/fsl_rio.c index 9234be1e66f5..5011ffea4e4b 100644 --- a/arch/powerpc/sysdev/fsl_rio.c +++ b/arch/powerpc/sysdev/fsl_rio.c @@ -71,6 +71,8 @@ #define RIWAR_WRTYP_ALLOC 0x00006000 #define RIWAR_SIZE_MASK 0x0000003F +static DEFINE_SPINLOCK(fsl_rio_config_lock); + #define __fsl_read_rio_config(x, addr, err, op) \ __asm__ __volatile__( \ "1: "op" %1,0(%2)\n" \ @@ -184,6 +186,7 @@ fsl_rio_config_read(struct rio_mport *mport, int index, u16 destid, u8 hopcount, u32 offset, int len, u32 *val) { struct rio_priv *priv = mport->priv; + unsigned long flags; u8 *data; u32 rval, err = 0; @@ -197,6 +200,8 @@ fsl_rio_config_read(struct rio_mport *mport, int index, u16 destid, if (offset > (0x1000000 - len) || !IS_ALIGNED(offset, len)) return -EINVAL; + spin_lock_irqsave(&fsl_rio_config_lock, flags); + out_be32(&priv->maint_atmu_regs->rowtar, (destid << 22) | (hopcount << 12) | (offset >> 12)); out_be32(&priv->maint_atmu_regs->rowtear, (destid >> 10)); @@ -213,6 +218,7 @@ fsl_rio_config_read(struct rio_mport *mport, int index, u16 destid, __fsl_read_rio_config(rval, data, err, "lwz"); break; default: + spin_unlock_irqrestore(&fsl_rio_config_lock, flags); return -EINVAL; } @@ -221,6 +227,7 @@ fsl_rio_config_read(struct rio_mport *mport, int index, u16 destid, err, destid, hopcount, offset); } + spin_unlock_irqrestore(&fsl_rio_config_lock, flags); *val = rval; return err; @@ -244,7 +251,10 @@ fsl_rio_config_write(struct rio_mport *mport, int index, u16 destid, u8 hopcount, u32 offset, int len, u32 val) { struct rio_priv *priv = mport->priv; + unsigned long flags; u8 *data; + int ret = 0; + pr_debug ("fsl_rio_config_write:" " index %d destid %d hopcount %d offset %8.8x len %d val %8.8x\n", @@ -255,6 +265,8 @@ fsl_rio_config_write(struct rio_mport *mport, int index, u16 destid, if (offset > (0x1000000 - len) || !IS_ALIGNED(offset, len)) return -EINVAL; + spin_lock_irqsave(&fsl_rio_config_lock, flags); + out_be32(&priv->maint_atmu_regs->rowtar, (destid << 22) | (hopcount << 12) | (offset >> 12)); out_be32(&priv->maint_atmu_regs->rowtear, (destid >> 10)); @@ -271,10 +283,11 @@ fsl_rio_config_write(struct rio_mport *mport, int index, u16 destid, out_be32((u32 *) data, val); break; default: - return -EINVAL; + ret = -EINVAL; } + spin_unlock_irqrestore(&fsl_rio_config_lock, flags); - return 0; + return ret; } static void fsl_rio_inbound_mem_init(struct rio_priv *priv) diff --git a/arch/powerpc/sysdev/fsl_rmu.c b/arch/powerpc/sysdev/fsl_rmu.c index ab7a74c75be8..88b35a3dcdc5 100644 --- a/arch/powerpc/sysdev/fsl_rmu.c +++ b/arch/powerpc/sysdev/fsl_rmu.c @@ -104,6 +104,8 @@ #define DOORBELL_MESSAGE_SIZE 0x08 +static DEFINE_SPINLOCK(fsl_rio_doorbell_lock); + struct rio_msg_regs { u32 omr; u32 osr; @@ -626,9 +628,13 @@ err_out: int fsl_rio_doorbell_send(struct rio_mport *mport, int index, u16 destid, u16 data) { + unsigned long flags; + pr_debug("fsl_doorbell_send: index %d destid %4.4x data %4.4x\n", index, destid, data); + spin_lock_irqsave(&fsl_rio_doorbell_lock, flags); + /* In the serial version silicons, such as MPC8548, MPC8641, * below operations is must be. */ @@ -638,6 +644,8 @@ int fsl_rio_doorbell_send(struct rio_mport *mport, out_be32(&dbell->dbell_regs->oddatr, (index << 20) | data); out_be32(&dbell->dbell_regs->odmr, 0x00000001); + spin_unlock_irqrestore(&fsl_rio_doorbell_lock, flags); + return 0; } diff --git a/arch/powerpc/sysdev/xive/common.c b/arch/powerpc/sysdev/xive/common.c index f387318678b9..a3b8d7d1316e 100644 --- a/arch/powerpc/sysdev/xive/common.c +++ b/arch/powerpc/sysdev/xive/common.c @@ -1402,6 +1402,14 @@ void xive_teardown_cpu(void) if (xive_ops->teardown_cpu) xive_ops->teardown_cpu(cpu, xc); + +#ifdef CONFIG_SMP + /* Get rid of IPI */ + xive_cleanup_cpu_ipi(cpu, xc); +#endif + + /* Disable and free the queues */ + xive_cleanup_cpu_queues(cpu, xc); } void xive_kexec_teardown_cpu(int secondary) diff --git a/arch/powerpc/sysdev/xive/spapr.c b/arch/powerpc/sysdev/xive/spapr.c index f24a70bc6855..d9c4c9366049 100644 --- a/arch/powerpc/sysdev/xive/spapr.c +++ b/arch/powerpc/sysdev/xive/spapr.c @@ -431,7 +431,11 @@ static int xive_spapr_get_ipi(unsigned int cpu, struct xive_cpu *xc) static void xive_spapr_put_ipi(unsigned int cpu, struct xive_cpu *xc) { + if (!xc->hw_ipi) + return; + xive_irq_bitmap_free(xc->hw_ipi); + xc->hw_ipi = 0; } #endif /* CONFIG_SMP */ diff --git a/arch/sh/include/cpu-sh2a/cpu/sh7264.h b/arch/sh/include/cpu-sh2a/cpu/sh7264.h index 4d1ef6d74bd6..2ae0e938b657 100644 --- a/arch/sh/include/cpu-sh2a/cpu/sh7264.h +++ b/arch/sh/include/cpu-sh2a/cpu/sh7264.h @@ -43,9 +43,7 @@ enum { GPIO_PG7, GPIO_PG6, GPIO_PG5, GPIO_PG4, GPIO_PG3, GPIO_PG2, GPIO_PG1, GPIO_PG0, - /* Port H */ - GPIO_PH7, GPIO_PH6, GPIO_PH5, GPIO_PH4, - GPIO_PH3, GPIO_PH2, GPIO_PH1, GPIO_PH0, + /* Port H - Port H does not have a Data Register */ /* Port I - not on device */ diff --git a/arch/sh/include/cpu-sh2a/cpu/sh7269.h b/arch/sh/include/cpu-sh2a/cpu/sh7269.h index 2a0ca8780f0d..13c495a9fc00 100644 --- a/arch/sh/include/cpu-sh2a/cpu/sh7269.h +++ b/arch/sh/include/cpu-sh2a/cpu/sh7269.h @@ -45,9 +45,7 @@ enum { GPIO_PG7, GPIO_PG6, GPIO_PG5, GPIO_PG4, GPIO_PG3, GPIO_PG2, GPIO_PG1, GPIO_PG0, - /* Port H */ - GPIO_PH7, GPIO_PH6, GPIO_PH5, GPIO_PH4, - GPIO_PH3, GPIO_PH2, GPIO_PH1, GPIO_PH0, + /* Port H - Port H does not have a Data Register */ /* Port I - not on device */ diff --git a/arch/sh/include/cpu-sh4/cpu/sh7722.h b/arch/sh/include/cpu-sh4/cpu/sh7722.h index 3bb74e534d0f..78961ab78a5a 100644 --- a/arch/sh/include/cpu-sh4/cpu/sh7722.h +++ b/arch/sh/include/cpu-sh4/cpu/sh7722.h @@ -67,7 +67,7 @@ enum { GPIO_PTN3, GPIO_PTN2, GPIO_PTN1, GPIO_PTN0, /* PTQ */ - GPIO_PTQ7, GPIO_PTQ6, GPIO_PTQ5, GPIO_PTQ4, + GPIO_PTQ6, GPIO_PTQ5, GPIO_PTQ4, GPIO_PTQ3, GPIO_PTQ2, GPIO_PTQ1, GPIO_PTQ0, /* PTR */ diff --git a/arch/sh/include/cpu-sh4/cpu/sh7757.h b/arch/sh/include/cpu-sh4/cpu/sh7757.h index 5340f3bc1863..b40fb541e72a 100644 --- a/arch/sh/include/cpu-sh4/cpu/sh7757.h +++ b/arch/sh/include/cpu-sh4/cpu/sh7757.h @@ -40,7 +40,7 @@ enum { /* PTJ */ GPIO_PTJ0, GPIO_PTJ1, GPIO_PTJ2, GPIO_PTJ3, - GPIO_PTJ4, GPIO_PTJ5, GPIO_PTJ6, GPIO_PTJ7_RESV, + GPIO_PTJ4, GPIO_PTJ5, GPIO_PTJ6, /* PTK */ GPIO_PTK0, GPIO_PTK1, GPIO_PTK2, GPIO_PTK3, @@ -48,7 +48,7 @@ enum { /* PTL */ GPIO_PTL0, GPIO_PTL1, GPIO_PTL2, GPIO_PTL3, - GPIO_PTL4, GPIO_PTL5, GPIO_PTL6, GPIO_PTL7_RESV, + GPIO_PTL4, GPIO_PTL5, GPIO_PTL6, /* PTM */ GPIO_PTM0, GPIO_PTM1, GPIO_PTM2, GPIO_PTM3, @@ -56,7 +56,7 @@ enum { /* PTN */ GPIO_PTN0, GPIO_PTN1, GPIO_PTN2, GPIO_PTN3, - GPIO_PTN4, GPIO_PTN5, GPIO_PTN6, GPIO_PTN7_RESV, + GPIO_PTN4, GPIO_PTN5, GPIO_PTN6, /* PTO */ GPIO_PTO0, GPIO_PTO1, GPIO_PTO2, GPIO_PTO3, @@ -68,7 +68,7 @@ enum { /* PTQ */ GPIO_PTQ0, GPIO_PTQ1, GPIO_PTQ2, GPIO_PTQ3, - GPIO_PTQ4, GPIO_PTQ5, GPIO_PTQ6, GPIO_PTQ7_RESV, + GPIO_PTQ4, GPIO_PTQ5, GPIO_PTQ6, /* PTR */ GPIO_PTR0, GPIO_PTR1, GPIO_PTR2, GPIO_PTR3, diff --git a/arch/um/kernel/time.c b/arch/um/kernel/time.c index 0b034ebbda2a..7f69d17de354 100644 --- a/arch/um/kernel/time.c +++ b/arch/um/kernel/time.c @@ -98,7 +98,7 @@ static struct clocksource timer_clocksource = { .flags = CLOCK_SOURCE_IS_CONTINUOUS, }; -static void __init timer_setup(void) +static void __init um_timer_setup(void) { int err; @@ -132,5 +132,5 @@ void read_persistent_clock(struct timespec *ts) void __init time_init(void) { timer_set_signal_handler(); - late_time_init = timer_setup; + late_time_init = um_timer_setup; } diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index 829e89cfcee2..9fb9a1f1e47b 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -4409,10 +4409,9 @@ static __init int fixup_ht_bug(void) return 0; } - if (lockup_detector_suspend() != 0) { - pr_debug("failed to disable PMU erratum BJ122, BV98, HSD29 workaround\n"); - return 0; - } + cpus_read_lock(); + + hardlockup_detector_perf_stop(); x86_pmu.flags &= ~(PMU_FL_EXCL_CNTRS | PMU_FL_EXCL_ENABLED); @@ -4420,9 +4419,7 @@ static __init int fixup_ht_bug(void) x86_pmu.commit_scheduling = NULL; x86_pmu.stop_scheduling = NULL; - lockup_detector_resume(); - - cpus_read_lock(); + hardlockup_detector_perf_restart(); for_each_online_cpu(c) free_excl_cntrs(c); diff --git a/arch/x86/events/intel/cstate.c b/arch/x86/events/intel/cstate.c index 4cf100ff2a37..72db0664a53d 100644 --- a/arch/x86/events/intel/cstate.c +++ b/arch/x86/events/intel/cstate.c @@ -552,6 +552,7 @@ static const struct x86_cpu_id intel_cstates_match[] __initconst = { X86_CSTATES_MODEL(INTEL_FAM6_SKYLAKE_MOBILE, snb_cstates), X86_CSTATES_MODEL(INTEL_FAM6_SKYLAKE_DESKTOP, snb_cstates), + X86_CSTATES_MODEL(INTEL_FAM6_SKYLAKE_X, snb_cstates), X86_CSTATES_MODEL(INTEL_FAM6_KABYLAKE_MOBILE, snb_cstates), X86_CSTATES_MODEL(INTEL_FAM6_KABYLAKE_DESKTOP, snb_cstates), @@ -560,6 +561,9 @@ static const struct x86_cpu_id intel_cstates_match[] __initconst = { X86_CSTATES_MODEL(INTEL_FAM6_XEON_PHI_KNM, knl_cstates), X86_CSTATES_MODEL(INTEL_FAM6_ATOM_GOLDMONT, glm_cstates), + X86_CSTATES_MODEL(INTEL_FAM6_ATOM_DENVERTON, glm_cstates), + + X86_CSTATES_MODEL(INTEL_FAM6_ATOM_GEMINI_LAKE, glm_cstates), { }, }; MODULE_DEVICE_TABLE(x86cpu, intel_cstates_match); diff --git a/arch/x86/events/intel/rapl.c b/arch/x86/events/intel/rapl.c index 8e2457cb6b4a..005908ee9333 100644 --- a/arch/x86/events/intel/rapl.c +++ b/arch/x86/events/intel/rapl.c @@ -775,6 +775,9 @@ static const struct x86_cpu_id rapl_cpu_match[] __initconst = { X86_RAPL_MODEL_MATCH(INTEL_FAM6_KABYLAKE_DESKTOP, skl_rapl_init), X86_RAPL_MODEL_MATCH(INTEL_FAM6_ATOM_GOLDMONT, hsw_rapl_init), + X86_RAPL_MODEL_MATCH(INTEL_FAM6_ATOM_DENVERTON, hsw_rapl_init), + + X86_RAPL_MODEL_MATCH(INTEL_FAM6_ATOM_GEMINI_LAKE, hsw_rapl_init), {}, }; diff --git a/arch/x86/events/intel/uncore_snbep.c b/arch/x86/events/intel/uncore_snbep.c index db1fe377e6dd..a7196818416a 100644 --- a/arch/x86/events/intel/uncore_snbep.c +++ b/arch/x86/events/intel/uncore_snbep.c @@ -3462,7 +3462,7 @@ static struct intel_uncore_ops skx_uncore_iio_ops = { static struct intel_uncore_type skx_uncore_iio = { .name = "iio", .num_counters = 4, - .num_boxes = 5, + .num_boxes = 6, .perf_ctr_bits = 48, .event_ctl = SKX_IIO0_MSR_PMON_CTL0, .perf_ctr = SKX_IIO0_MSR_PMON_CTR0, @@ -3492,7 +3492,7 @@ static const struct attribute_group skx_uncore_format_group = { static struct intel_uncore_type skx_uncore_irp = { .name = "irp", .num_counters = 2, - .num_boxes = 5, + .num_boxes = 6, .perf_ctr_bits = 48, .event_ctl = SKX_IRP0_MSR_PMON_CTL0, .perf_ctr = SKX_IRP0_MSR_PMON_CTR0, diff --git a/arch/x86/events/msr.c b/arch/x86/events/msr.c index 4bb3ec69e8ea..06723671ae4e 100644 --- a/arch/x86/events/msr.c +++ b/arch/x86/events/msr.c @@ -63,6 +63,14 @@ static bool test_intel(int idx) case INTEL_FAM6_ATOM_SILVERMONT1: case INTEL_FAM6_ATOM_SILVERMONT2: case INTEL_FAM6_ATOM_AIRMONT: + + case INTEL_FAM6_ATOM_GOLDMONT: + case INTEL_FAM6_ATOM_DENVERTON: + + case INTEL_FAM6_ATOM_GEMINI_LAKE: + + case INTEL_FAM6_XEON_PHI_KNL: + case INTEL_FAM6_XEON_PHI_KNM: if (idx == PERF_MSR_SMI) return true; break; diff --git a/arch/x86/ia32/ia32_signal.c b/arch/x86/ia32/ia32_signal.c index e0bb46c02857..0e2a5edbce00 100644 --- a/arch/x86/ia32/ia32_signal.c +++ b/arch/x86/ia32/ia32_signal.c @@ -231,7 +231,7 @@ static void __user *get_sigframe(struct ksignal *ksig, struct pt_regs *regs, ksig->ka.sa.sa_restorer) sp = (unsigned long) ksig->ka.sa.sa_restorer; - if (fpu->fpstate_active) { + if (fpu->initialized) { unsigned long fx_aligned, math_size; sp = fpu__alloc_mathframe(sp, 1, &fx_aligned, &math_size); diff --git a/arch/x86/include/asm/asm.h b/arch/x86/include/asm/asm.h index c1eadbaf1115..b0dc91f4bedc 100644 --- a/arch/x86/include/asm/asm.h +++ b/arch/x86/include/asm/asm.h @@ -11,10 +11,12 @@ # define __ASM_FORM_COMMA(x) " " #x "," #endif -#ifdef CONFIG_X86_32 +#ifndef __x86_64__ +/* 32 bit */ # define __ASM_SEL(a,b) __ASM_FORM(a) # define __ASM_SEL_RAW(a,b) __ASM_FORM_RAW(a) #else +/* 64 bit */ # define __ASM_SEL(a,b) __ASM_FORM(b) # define __ASM_SEL_RAW(a,b) __ASM_FORM_RAW(b) #endif @@ -139,8 +141,8 @@ * gets set up by the containing function. If you forget to do this, objtool * may print a "call without frame pointer save/setup" warning. */ -register unsigned int __asm_call_sp asm("esp"); -#define ASM_CALL_CONSTRAINT "+r" (__asm_call_sp) +register unsigned long current_stack_pointer asm(_ASM_SP); +#define ASM_CALL_CONSTRAINT "+r" (current_stack_pointer) #endif #endif /* _ASM_X86_ASM_H */ diff --git a/arch/x86/include/asm/fpu/internal.h b/arch/x86/include/asm/fpu/internal.h index 554cdb205d17..e3221ffa304e 100644 --- a/arch/x86/include/asm/fpu/internal.h +++ b/arch/x86/include/asm/fpu/internal.h @@ -23,11 +23,9 @@ /* * High level FPU state handling functions: */ -extern void fpu__activate_curr(struct fpu *fpu); -extern void fpu__activate_fpstate_read(struct fpu *fpu); -extern void fpu__activate_fpstate_write(struct fpu *fpu); -extern void fpu__current_fpstate_write_begin(void); -extern void fpu__current_fpstate_write_end(void); +extern void fpu__initialize(struct fpu *fpu); +extern void fpu__prepare_read(struct fpu *fpu); +extern void fpu__prepare_write(struct fpu *fpu); extern void fpu__save(struct fpu *fpu); extern void fpu__restore(struct fpu *fpu); extern int fpu__restore_sig(void __user *buf, int ia32_frame); @@ -120,20 +118,11 @@ extern void fpstate_sanitize_xstate(struct fpu *fpu); err; \ }) -#define check_insn(insn, output, input...) \ -({ \ - int err; \ +#define kernel_insn(insn, output, input...) \ asm volatile("1:" #insn "\n\t" \ "2:\n" \ - ".section .fixup,\"ax\"\n" \ - "3: movl $-1,%[err]\n" \ - " jmp 2b\n" \ - ".previous\n" \ - _ASM_EXTABLE(1b, 3b) \ - : [err] "=r" (err), output \ - : "0"(0), input); \ - err; \ -}) + _ASM_EXTABLE_HANDLE(1b, 2b, ex_handler_fprestore) \ + : output : input) static inline int copy_fregs_to_user(struct fregs_state __user *fx) { @@ -153,20 +142,16 @@ static inline int copy_fxregs_to_user(struct fxregs_state __user *fx) static inline void copy_kernel_to_fxregs(struct fxregs_state *fx) { - int err; - if (IS_ENABLED(CONFIG_X86_32)) { - err = check_insn(fxrstor %[fx], "=m" (*fx), [fx] "m" (*fx)); + kernel_insn(fxrstor %[fx], "=m" (*fx), [fx] "m" (*fx)); } else { if (IS_ENABLED(CONFIG_AS_FXSAVEQ)) { - err = check_insn(fxrstorq %[fx], "=m" (*fx), [fx] "m" (*fx)); + kernel_insn(fxrstorq %[fx], "=m" (*fx), [fx] "m" (*fx)); } else { /* See comment in copy_fxregs_to_kernel() below. */ - err = check_insn(rex64/fxrstor (%[fx]), "=m" (*fx), [fx] "R" (fx), "m" (*fx)); + kernel_insn(rex64/fxrstor (%[fx]), "=m" (*fx), [fx] "R" (fx), "m" (*fx)); } } - /* Copying from a kernel buffer to FPU registers should never fail: */ - WARN_ON_FPU(err); } static inline int copy_user_to_fxregs(struct fxregs_state __user *fx) @@ -183,9 +168,7 @@ static inline int copy_user_to_fxregs(struct fxregs_state __user *fx) static inline void copy_kernel_to_fregs(struct fregs_state *fx) { - int err = check_insn(frstor %[fx], "=m" (*fx), [fx] "m" (*fx)); - - WARN_ON_FPU(err); + kernel_insn(frstor %[fx], "=m" (*fx), [fx] "m" (*fx)); } static inline int copy_user_to_fregs(struct fregs_state __user *fx) @@ -281,18 +264,13 @@ static inline void copy_fxregs_to_kernel(struct fpu *fpu) * Use XRSTORS to restore context if it is enabled. XRSTORS supports compact * XSAVE area format. */ -#define XSTATE_XRESTORE(st, lmask, hmask, err) \ +#define XSTATE_XRESTORE(st, lmask, hmask) \ asm volatile(ALTERNATIVE(XRSTOR, \ XRSTORS, X86_FEATURE_XSAVES) \ "\n" \ - "xor %[err], %[err]\n" \ "3:\n" \ - ".pushsection .fixup,\"ax\"\n" \ - "4: movl $-2, %[err]\n" \ - "jmp 3b\n" \ - ".popsection\n" \ - _ASM_EXTABLE(661b, 4b) \ - : [err] "=r" (err) \ + _ASM_EXTABLE_HANDLE(661b, 3b, ex_handler_fprestore)\ + : \ : "D" (st), "m" (*st), "a" (lmask), "d" (hmask) \ : "memory") @@ -336,7 +314,10 @@ static inline void copy_kernel_to_xregs_booting(struct xregs_state *xstate) else XSTATE_OP(XRSTOR, xstate, lmask, hmask, err); - /* We should never fault when copying from a kernel buffer: */ + /* + * We should never fault when copying from a kernel buffer, and the FPU + * state we set at boot time should be valid. + */ WARN_ON_FPU(err); } @@ -350,7 +331,7 @@ static inline void copy_xregs_to_kernel(struct xregs_state *xstate) u32 hmask = mask >> 32; int err; - WARN_ON(!alternatives_patched); + WARN_ON_FPU(!alternatives_patched); XSTATE_XSAVE(xstate, lmask, hmask, err); @@ -365,12 +346,8 @@ static inline void copy_kernel_to_xregs(struct xregs_state *xstate, u64 mask) { u32 lmask = mask; u32 hmask = mask >> 32; - int err; - - XSTATE_XRESTORE(xstate, lmask, hmask, err); - /* We should never fault when copying from a kernel buffer: */ - WARN_ON_FPU(err); + XSTATE_XRESTORE(xstate, lmask, hmask); } /* @@ -526,38 +503,17 @@ static inline int fpregs_state_valid(struct fpu *fpu, unsigned int cpu) */ static inline void fpregs_deactivate(struct fpu *fpu) { - WARN_ON_FPU(!fpu->fpregs_active); - - fpu->fpregs_active = 0; this_cpu_write(fpu_fpregs_owner_ctx, NULL); trace_x86_fpu_regs_deactivated(fpu); } static inline void fpregs_activate(struct fpu *fpu) { - WARN_ON_FPU(fpu->fpregs_active); - - fpu->fpregs_active = 1; this_cpu_write(fpu_fpregs_owner_ctx, fpu); trace_x86_fpu_regs_activated(fpu); } /* - * The question "does this thread have fpu access?" - * is slightly racy, since preemption could come in - * and revoke it immediately after the test. - * - * However, even in that very unlikely scenario, - * we can just assume we have FPU access - typically - * to save the FP state - we'll just take a #NM - * fault and get the FPU access back. - */ -static inline int fpregs_active(void) -{ - return current->thread.fpu.fpregs_active; -} - -/* * FPU state switching for scheduling. * * This is a two-stage process: @@ -571,14 +527,13 @@ static inline int fpregs_active(void) static inline void switch_fpu_prepare(struct fpu *old_fpu, int cpu) { - if (old_fpu->fpregs_active) { + if (old_fpu->initialized) { if (!copy_fpregs_to_fpstate(old_fpu)) old_fpu->last_cpu = -1; else old_fpu->last_cpu = cpu; /* But leave fpu_fpregs_owner_ctx! */ - old_fpu->fpregs_active = 0; trace_x86_fpu_regs_deactivated(old_fpu); } else old_fpu->last_cpu = -1; @@ -595,7 +550,7 @@ switch_fpu_prepare(struct fpu *old_fpu, int cpu) static inline void switch_fpu_finish(struct fpu *new_fpu, int cpu) { bool preload = static_cpu_has(X86_FEATURE_FPU) && - new_fpu->fpstate_active; + new_fpu->initialized; if (preload) { if (!fpregs_state_valid(new_fpu, cpu)) @@ -617,8 +572,7 @@ static inline void user_fpu_begin(void) struct fpu *fpu = ¤t->thread.fpu; preempt_disable(); - if (!fpregs_active()) - fpregs_activate(fpu); + fpregs_activate(fpu); preempt_enable(); } diff --git a/arch/x86/include/asm/fpu/types.h b/arch/x86/include/asm/fpu/types.h index 3c80f5b9c09d..a1520575d86b 100644 --- a/arch/x86/include/asm/fpu/types.h +++ b/arch/x86/include/asm/fpu/types.h @@ -68,6 +68,9 @@ struct fxregs_state { /* Default value for fxregs_state.mxcsr: */ #define MXCSR_DEFAULT 0x1f80 +/* Copy both mxcsr & mxcsr_flags with a single u64 memcpy: */ +#define MXCSR_AND_FLAGS_SIZE sizeof(u64) + /* * Software based FPU emulation state. This is arbitrary really, * it matches the x87 format to make it easier to understand: @@ -290,36 +293,13 @@ struct fpu { unsigned int last_cpu; /* - * @fpstate_active: + * @initialized: * - * This flag indicates whether this context is active: if the task + * This flag indicates whether this context is initialized: if the task * is not running then we can restore from this context, if the task * is running then we should save into this context. */ - unsigned char fpstate_active; - - /* - * @fpregs_active: - * - * This flag determines whether a given context is actively - * loaded into the FPU's registers and that those registers - * represent the task's current FPU state. - * - * Note the interaction with fpstate_active: - * - * # task does not use the FPU: - * fpstate_active == 0 - * - * # task uses the FPU and regs are active: - * fpstate_active == 1 && fpregs_active == 1 - * - * # the regs are inactive but still match fpstate: - * fpstate_active == 1 && fpregs_active == 0 && fpregs_owner == fpu - * - * The third state is what we use for the lazy restore optimization - * on lazy-switching CPUs. - */ - unsigned char fpregs_active; + unsigned char initialized; /* * @state: diff --git a/arch/x86/include/asm/fpu/xstate.h b/arch/x86/include/asm/fpu/xstate.h index 1b2799e0699a..83fee2469eb7 100644 --- a/arch/x86/include/asm/fpu/xstate.h +++ b/arch/x86/include/asm/fpu/xstate.h @@ -48,8 +48,12 @@ void fpu__xstate_clear_all_cpu_caps(void); void *get_xsave_addr(struct xregs_state *xsave, int xstate); const void *get_xsave_field_ptr(int xstate_field); int using_compacted_format(void); -int copyout_from_xsaves(unsigned int pos, unsigned int count, void *kbuf, - void __user *ubuf, struct xregs_state *xsave); -int copyin_to_xsaves(const void *kbuf, const void __user *ubuf, - struct xregs_state *xsave); +int copy_xstate_to_kernel(void *kbuf, struct xregs_state *xsave, unsigned int offset, unsigned int size); +int copy_xstate_to_user(void __user *ubuf, struct xregs_state *xsave, unsigned int offset, unsigned int size); +int copy_kernel_to_xstate(struct xregs_state *xsave, const void *kbuf); +int copy_user_to_xstate(struct xregs_state *xsave, const void __user *ubuf); + +/* Validate an xstate header supplied by userspace (ptrace or sigreturn) */ +extern int validate_xstate_header(const struct xstate_header *hdr); + #endif diff --git a/arch/x86/include/asm/kvm_para.h b/arch/x86/include/asm/kvm_para.h index bc62e7cbf1b1..59ad3d132353 100644 --- a/arch/x86/include/asm/kvm_para.h +++ b/arch/x86/include/asm/kvm_para.h @@ -88,7 +88,7 @@ static inline long kvm_hypercall4(unsigned int nr, unsigned long p1, bool kvm_para_available(void); unsigned int kvm_arch_para_features(void); void __init kvm_guest_init(void); -void kvm_async_pf_task_wait(u32 token); +void kvm_async_pf_task_wait(u32 token, int interrupt_kernel); void kvm_async_pf_task_wake(u32 token); u32 kvm_read_and_reset_pf_reason(void); extern void kvm_disable_steal_time(void); @@ -103,7 +103,7 @@ static inline void kvm_spinlock_init(void) #else /* CONFIG_KVM_GUEST */ #define kvm_guest_init() do {} while (0) -#define kvm_async_pf_task_wait(T) do {} while(0) +#define kvm_async_pf_task_wait(T, I) do {} while(0) #define kvm_async_pf_task_wake(T) do {} while(0) static inline bool kvm_para_available(void) diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h index 5161da1a0fa0..89e7eeb5cec1 100644 --- a/arch/x86/include/asm/thread_info.h +++ b/arch/x86/include/asm/thread_info.h @@ -158,17 +158,6 @@ struct thread_info { */ #ifndef __ASSEMBLY__ -static inline unsigned long current_stack_pointer(void) -{ - unsigned long sp; -#ifdef CONFIG_X86_64 - asm("mov %%rsp,%0" : "=g" (sp)); -#else - asm("mov %%esp,%0" : "=g" (sp)); -#endif - return sp; -} - /* * Walks up the stack frames to make sure that the specified object is * entirely contained by a single stack frame. diff --git a/arch/x86/include/asm/trace/fpu.h b/arch/x86/include/asm/trace/fpu.h index 342e59789fcd..39f7a27bef13 100644 --- a/arch/x86/include/asm/trace/fpu.h +++ b/arch/x86/include/asm/trace/fpu.h @@ -12,25 +12,22 @@ DECLARE_EVENT_CLASS(x86_fpu, TP_STRUCT__entry( __field(struct fpu *, fpu) - __field(bool, fpregs_active) - __field(bool, fpstate_active) + __field(bool, initialized) __field(u64, xfeatures) __field(u64, xcomp_bv) ), TP_fast_assign( __entry->fpu = fpu; - __entry->fpregs_active = fpu->fpregs_active; - __entry->fpstate_active = fpu->fpstate_active; + __entry->initialized = fpu->initialized; if (boot_cpu_has(X86_FEATURE_OSXSAVE)) { __entry->xfeatures = fpu->state.xsave.header.xfeatures; __entry->xcomp_bv = fpu->state.xsave.header.xcomp_bv; } ), - TP_printk("x86/fpu: %p fpregs_active: %d fpstate_active: %d xfeatures: %llx xcomp_bv: %llx", + TP_printk("x86/fpu: %p initialized: %d xfeatures: %llx xcomp_bv: %llx", __entry->fpu, - __entry->fpregs_active, - __entry->fpstate_active, + __entry->initialized, __entry->xfeatures, __entry->xcomp_bv ) diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h index 78e8fcc87d4c..4b892917edeb 100644 --- a/arch/x86/include/asm/uaccess.h +++ b/arch/x86/include/asm/uaccess.h @@ -337,7 +337,7 @@ do { \ _ASM_EXTABLE(1b, 4b) \ _ASM_EXTABLE(2b, 4b) \ : "=r" (retval), "=&A"(x) \ - : "m" (__m(__ptr)), "m" __m(((u32 *)(__ptr)) + 1), \ + : "m" (__m(__ptr)), "m" __m(((u32 __user *)(__ptr)) + 1), \ "i" (errret), "0" (retval)); \ }) diff --git a/arch/x86/include/asm/xen/hypercall.h b/arch/x86/include/asm/xen/hypercall.h index 128a1a0b1450..7cb282e9e587 100644 --- a/arch/x86/include/asm/xen/hypercall.h +++ b/arch/x86/include/asm/xen/hypercall.h @@ -551,13 +551,13 @@ static inline void MULTI_update_descriptor(struct multicall_entry *mcl, u64 maddr, struct desc_struct desc) { - u32 *p = (u32 *) &desc; - mcl->op = __HYPERVISOR_update_descriptor; if (sizeof(maddr) == sizeof(long)) { mcl->args[0] = maddr; mcl->args[1] = *(unsigned long *)&desc; } else { + u32 *p = (u32 *)&desc; + mcl->args[0] = maddr; mcl->args[1] = maddr >> 32; mcl->args[2] = *p++; diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c index e1114f070c2d..f92a6593de1e 100644 --- a/arch/x86/kernel/fpu/core.c +++ b/arch/x86/kernel/fpu/core.c @@ -100,7 +100,7 @@ void __kernel_fpu_begin(void) kernel_fpu_disable(); - if (fpu->fpregs_active) { + if (fpu->initialized) { /* * Ignore return value -- we don't care if reg state * is clobbered. @@ -116,7 +116,7 @@ void __kernel_fpu_end(void) { struct fpu *fpu = ¤t->thread.fpu; - if (fpu->fpregs_active) + if (fpu->initialized) copy_kernel_to_fpregs(&fpu->state); kernel_fpu_enable(); @@ -148,7 +148,7 @@ void fpu__save(struct fpu *fpu) preempt_disable(); trace_x86_fpu_before_save(fpu); - if (fpu->fpregs_active) { + if (fpu->initialized) { if (!copy_fpregs_to_fpstate(fpu)) { copy_kernel_to_fpregs(&fpu->state); } @@ -189,10 +189,9 @@ EXPORT_SYMBOL_GPL(fpstate_init); int fpu__copy(struct fpu *dst_fpu, struct fpu *src_fpu) { - dst_fpu->fpregs_active = 0; dst_fpu->last_cpu = -1; - if (!src_fpu->fpstate_active || !static_cpu_has(X86_FEATURE_FPU)) + if (!src_fpu->initialized || !static_cpu_has(X86_FEATURE_FPU)) return 0; WARN_ON_FPU(src_fpu != ¤t->thread.fpu); @@ -206,26 +205,14 @@ int fpu__copy(struct fpu *dst_fpu, struct fpu *src_fpu) /* * Save current FPU registers directly into the child * FPU context, without any memory-to-memory copying. - * In lazy mode, if the FPU context isn't loaded into - * fpregs, CR0.TS will be set and do_device_not_available - * will load the FPU context. * - * We have to do all this with preemption disabled, - * mostly because of the FNSAVE case, because in that - * case we must not allow preemption in the window - * between the FNSAVE and us marking the context lazy. - * - * It shouldn't be an issue as even FNSAVE is plenty - * fast in terms of critical section length. + * ( The function 'fails' in the FNSAVE case, which destroys + * register contents so we have to copy them back. ) */ - preempt_disable(); if (!copy_fpregs_to_fpstate(dst_fpu)) { - memcpy(&src_fpu->state, &dst_fpu->state, - fpu_kernel_xstate_size); - + memcpy(&src_fpu->state, &dst_fpu->state, fpu_kernel_xstate_size); copy_kernel_to_fpregs(&src_fpu->state); } - preempt_enable(); trace_x86_fpu_copy_src(src_fpu); trace_x86_fpu_copy_dst(dst_fpu); @@ -237,45 +224,48 @@ int fpu__copy(struct fpu *dst_fpu, struct fpu *src_fpu) * Activate the current task's in-memory FPU context, * if it has not been used before: */ -void fpu__activate_curr(struct fpu *fpu) +void fpu__initialize(struct fpu *fpu) { WARN_ON_FPU(fpu != ¤t->thread.fpu); - if (!fpu->fpstate_active) { + if (!fpu->initialized) { fpstate_init(&fpu->state); trace_x86_fpu_init_state(fpu); trace_x86_fpu_activate_state(fpu); /* Safe to do for the current task: */ - fpu->fpstate_active = 1; + fpu->initialized = 1; } } -EXPORT_SYMBOL_GPL(fpu__activate_curr); +EXPORT_SYMBOL_GPL(fpu__initialize); /* * This function must be called before we read a task's fpstate. * - * If the task has not used the FPU before then initialize its - * fpstate. + * There's two cases where this gets called: + * + * - for the current task (when coredumping), in which case we have + * to save the latest FPU registers into the fpstate, + * + * - or it's called for stopped tasks (ptrace), in which case the + * registers were already saved by the context-switch code when + * the task scheduled out - we only have to initialize the registers + * if they've never been initialized. * * If the task has used the FPU before then save it. */ -void fpu__activate_fpstate_read(struct fpu *fpu) +void fpu__prepare_read(struct fpu *fpu) { - /* - * If fpregs are active (in the current CPU), then - * copy them to the fpstate: - */ - if (fpu->fpregs_active) { + if (fpu == ¤t->thread.fpu) { fpu__save(fpu); } else { - if (!fpu->fpstate_active) { + if (!fpu->initialized) { fpstate_init(&fpu->state); trace_x86_fpu_init_state(fpu); trace_x86_fpu_activate_state(fpu); /* Safe to do for current and for stopped child tasks: */ - fpu->fpstate_active = 1; + fpu->initialized = 1; } } } @@ -283,17 +273,17 @@ void fpu__activate_fpstate_read(struct fpu *fpu) /* * This function must be called before we write a task's fpstate. * - * If the task has used the FPU before then unlazy it. + * If the task has used the FPU before then invalidate any cached FPU registers. * If the task has not used the FPU before then initialize its fpstate. * * After this function call, after registers in the fpstate are * modified and the child task has woken up, the child task will * restore the modified FPU state from the modified context. If we - * didn't clear its lazy status here then the lazy in-registers + * didn't clear its cached status here then the cached in-registers * state pending on its former CPU could be restored, corrupting * the modifications. */ -void fpu__activate_fpstate_write(struct fpu *fpu) +void fpu__prepare_write(struct fpu *fpu) { /* * Only stopped child tasks can be used to modify the FPU @@ -301,8 +291,8 @@ void fpu__activate_fpstate_write(struct fpu *fpu) */ WARN_ON_FPU(fpu == ¤t->thread.fpu); - if (fpu->fpstate_active) { - /* Invalidate any lazy state: */ + if (fpu->initialized) { + /* Invalidate any cached state: */ __fpu_invalidate_fpregs_state(fpu); } else { fpstate_init(&fpu->state); @@ -310,74 +300,11 @@ void fpu__activate_fpstate_write(struct fpu *fpu) trace_x86_fpu_activate_state(fpu); /* Safe to do for stopped child tasks: */ - fpu->fpstate_active = 1; + fpu->initialized = 1; } } /* - * This function must be called before we write the current - * task's fpstate. - * - * This call gets the current FPU register state and moves - * it in to the 'fpstate'. Preemption is disabled so that - * no writes to the 'fpstate' can occur from context - * swiches. - * - * Must be followed by a fpu__current_fpstate_write_end(). - */ -void fpu__current_fpstate_write_begin(void) -{ - struct fpu *fpu = ¤t->thread.fpu; - - /* - * Ensure that the context-switching code does not write - * over the fpstate while we are doing our update. - */ - preempt_disable(); - - /* - * Move the fpregs in to the fpu's 'fpstate'. - */ - fpu__activate_fpstate_read(fpu); - - /* - * The caller is about to write to 'fpu'. Ensure that no - * CPU thinks that its fpregs match the fpstate. This - * ensures we will not be lazy and skip a XRSTOR in the - * future. - */ - __fpu_invalidate_fpregs_state(fpu); -} - -/* - * This function must be paired with fpu__current_fpstate_write_begin() - * - * This will ensure that the modified fpstate gets placed back in - * the fpregs if necessary. - * - * Note: This function may be called whether or not an _actual_ - * write to the fpstate occurred. - */ -void fpu__current_fpstate_write_end(void) -{ - struct fpu *fpu = ¤t->thread.fpu; - - /* - * 'fpu' now has an updated copy of the state, but the - * registers may still be out of date. Update them with - * an XRSTOR if they are active. - */ - if (fpregs_active()) - copy_kernel_to_fpregs(&fpu->state); - - /* - * Our update is done and the fpregs/fpstate are in sync - * if necessary. Context switches can happen again. - */ - preempt_enable(); -} - -/* * 'fpu__restore()' is called to copy FPU registers from * the FPU fpstate to the live hw registers and to activate * access to the hardware registers, so that FPU instructions @@ -389,7 +316,7 @@ void fpu__current_fpstate_write_end(void) */ void fpu__restore(struct fpu *fpu) { - fpu__activate_curr(fpu); + fpu__initialize(fpu); /* Avoid __kernel_fpu_begin() right after fpregs_activate() */ kernel_fpu_disable(); @@ -414,15 +341,17 @@ void fpu__drop(struct fpu *fpu) { preempt_disable(); - if (fpu->fpregs_active) { - /* Ignore delayed exceptions from user space */ - asm volatile("1: fwait\n" - "2:\n" - _ASM_EXTABLE(1b, 2b)); - fpregs_deactivate(fpu); + if (fpu == ¤t->thread.fpu) { + if (fpu->initialized) { + /* Ignore delayed exceptions from user space */ + asm volatile("1: fwait\n" + "2:\n" + _ASM_EXTABLE(1b, 2b)); + fpregs_deactivate(fpu); + } } - fpu->fpstate_active = 0; + fpu->initialized = 0; trace_x86_fpu_dropped(fpu); @@ -462,9 +391,11 @@ void fpu__clear(struct fpu *fpu) * Make sure fpstate is cleared and initialized. */ if (static_cpu_has(X86_FEATURE_FPU)) { - fpu__activate_curr(fpu); + preempt_disable(); + fpu__initialize(fpu); user_fpu_begin(); copy_init_fpstate_to_fpregs(); + preempt_enable(); } } diff --git a/arch/x86/kernel/fpu/init.c b/arch/x86/kernel/fpu/init.c index d5d44c452624..7affb7e3d9a5 100644 --- a/arch/x86/kernel/fpu/init.c +++ b/arch/x86/kernel/fpu/init.c @@ -240,7 +240,7 @@ static void __init fpu__init_system_ctx_switch(void) WARN_ON_FPU(!on_boot_cpu); on_boot_cpu = 0; - WARN_ON_FPU(current->thread.fpu.fpstate_active); + WARN_ON_FPU(current->thread.fpu.initialized); } /* diff --git a/arch/x86/kernel/fpu/regset.c b/arch/x86/kernel/fpu/regset.c index b188b16841e3..3ea151372389 100644 --- a/arch/x86/kernel/fpu/regset.c +++ b/arch/x86/kernel/fpu/regset.c @@ -16,14 +16,14 @@ int regset_fpregs_active(struct task_struct *target, const struct user_regset *r { struct fpu *target_fpu = &target->thread.fpu; - return target_fpu->fpstate_active ? regset->n : 0; + return target_fpu->initialized ? regset->n : 0; } int regset_xregset_fpregs_active(struct task_struct *target, const struct user_regset *regset) { struct fpu *target_fpu = &target->thread.fpu; - if (boot_cpu_has(X86_FEATURE_FXSR) && target_fpu->fpstate_active) + if (boot_cpu_has(X86_FEATURE_FXSR) && target_fpu->initialized) return regset->n; else return 0; @@ -38,7 +38,7 @@ int xfpregs_get(struct task_struct *target, const struct user_regset *regset, if (!boot_cpu_has(X86_FEATURE_FXSR)) return -ENODEV; - fpu__activate_fpstate_read(fpu); + fpu__prepare_read(fpu); fpstate_sanitize_xstate(fpu); return user_regset_copyout(&pos, &count, &kbuf, &ubuf, @@ -55,7 +55,7 @@ int xfpregs_set(struct task_struct *target, const struct user_regset *regset, if (!boot_cpu_has(X86_FEATURE_FXSR)) return -ENODEV; - fpu__activate_fpstate_write(fpu); + fpu__prepare_write(fpu); fpstate_sanitize_xstate(fpu); ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, @@ -89,10 +89,13 @@ int xstateregs_get(struct task_struct *target, const struct user_regset *regset, xsave = &fpu->state.xsave; - fpu__activate_fpstate_read(fpu); + fpu__prepare_read(fpu); if (using_compacted_format()) { - ret = copyout_from_xsaves(pos, count, kbuf, ubuf, xsave); + if (kbuf) + ret = copy_xstate_to_kernel(kbuf, xsave, pos, count); + else + ret = copy_xstate_to_user(ubuf, xsave, pos, count); } else { fpstate_sanitize_xstate(fpu); /* @@ -129,28 +132,29 @@ int xstateregs_set(struct task_struct *target, const struct user_regset *regset, xsave = &fpu->state.xsave; - fpu__activate_fpstate_write(fpu); + fpu__prepare_write(fpu); - if (boot_cpu_has(X86_FEATURE_XSAVES)) - ret = copyin_to_xsaves(kbuf, ubuf, xsave); - else + if (using_compacted_format()) { + if (kbuf) + ret = copy_kernel_to_xstate(xsave, kbuf); + else + ret = copy_user_to_xstate(xsave, ubuf); + } else { ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, xsave, 0, -1); - - /* - * In case of failure, mark all states as init: - */ - if (ret) - fpstate_init(&fpu->state); + if (!ret) + ret = validate_xstate_header(&xsave->header); + } /* * mxcsr reserved bits must be masked to zero for security reasons. */ xsave->i387.mxcsr &= mxcsr_feature_mask; - xsave->header.xfeatures &= xfeatures_mask; + /* - * These bits must be zero. + * In case of failure, mark all states as init: */ - memset(&xsave->header.reserved, 0, 48); + if (ret) + fpstate_init(&fpu->state); return ret; } @@ -299,7 +303,7 @@ int fpregs_get(struct task_struct *target, const struct user_regset *regset, struct fpu *fpu = &target->thread.fpu; struct user_i387_ia32_struct env; - fpu__activate_fpstate_read(fpu); + fpu__prepare_read(fpu); if (!boot_cpu_has(X86_FEATURE_FPU)) return fpregs_soft_get(target, regset, pos, count, kbuf, ubuf); @@ -329,7 +333,7 @@ int fpregs_set(struct task_struct *target, const struct user_regset *regset, struct user_i387_ia32_struct env; int ret; - fpu__activate_fpstate_write(fpu); + fpu__prepare_write(fpu); fpstate_sanitize_xstate(fpu); if (!boot_cpu_has(X86_FEATURE_FPU)) @@ -369,7 +373,7 @@ int dump_fpu(struct pt_regs *regs, struct user_i387_struct *ufpu) struct fpu *fpu = &tsk->thread.fpu; int fpvalid; - fpvalid = fpu->fpstate_active; + fpvalid = fpu->initialized; if (fpvalid) fpvalid = !fpregs_get(tsk, NULL, 0, sizeof(struct user_i387_ia32_struct), diff --git a/arch/x86/kernel/fpu/signal.c b/arch/x86/kernel/fpu/signal.c index 83c23c230b4c..fb639e70048f 100644 --- a/arch/x86/kernel/fpu/signal.c +++ b/arch/x86/kernel/fpu/signal.c @@ -155,7 +155,8 @@ static inline int copy_fpregs_to_sigframe(struct xregs_state __user *buf) */ int copy_fpstate_to_sigframe(void __user *buf, void __user *buf_fx, int size) { - struct xregs_state *xsave = ¤t->thread.fpu.state.xsave; + struct fpu *fpu = ¤t->thread.fpu; + struct xregs_state *xsave = &fpu->state.xsave; struct task_struct *tsk = current; int ia32_fxstate = (buf != buf_fx); @@ -170,13 +171,13 @@ int copy_fpstate_to_sigframe(void __user *buf, void __user *buf_fx, int size) sizeof(struct user_i387_ia32_struct), NULL, (struct _fpstate_32 __user *) buf) ? -1 : 1; - if (fpregs_active() || using_compacted_format()) { + if (fpu->initialized || using_compacted_format()) { /* Save the live register state to the user directly. */ if (copy_fpregs_to_sigframe(buf_fx)) return -1; /* Update the thread's fxstate to save the fsave header. */ if (ia32_fxstate) - copy_fxregs_to_kernel(&tsk->thread.fpu); + copy_fxregs_to_kernel(fpu); } else { /* * It is a *bug* if kernel uses compacted-format for xsave @@ -189,7 +190,7 @@ int copy_fpstate_to_sigframe(void __user *buf, void __user *buf_fx, int size) return -1; } - fpstate_sanitize_xstate(&tsk->thread.fpu); + fpstate_sanitize_xstate(fpu); if (__copy_to_user(buf_fx, xsave, fpu_user_xstate_size)) return -1; } @@ -213,8 +214,11 @@ sanitize_restored_xstate(struct task_struct *tsk, struct xstate_header *header = &xsave->header; if (use_xsave()) { - /* These bits must be zero. */ - memset(header->reserved, 0, 48); + /* + * Note: we don't need to zero the reserved bits in the + * xstate_header here because we either didn't copy them at all, + * or we checked earlier that they aren't set. + */ /* * Init the state that is not present in the memory @@ -223,7 +227,7 @@ sanitize_restored_xstate(struct task_struct *tsk, if (fx_only) header->xfeatures = XFEATURE_MASK_FPSSE; else - header->xfeatures &= (xfeatures_mask & xfeatures); + header->xfeatures &= xfeatures; } if (use_fxsr()) { @@ -279,7 +283,7 @@ static int __fpu__restore_sig(void __user *buf, void __user *buf_fx, int size) if (!access_ok(VERIFY_READ, buf, size)) return -EACCES; - fpu__activate_curr(fpu); + fpu__initialize(fpu); if (!static_cpu_has(X86_FEATURE_FPU)) return fpregs_soft_set(current, NULL, @@ -307,28 +311,29 @@ static int __fpu__restore_sig(void __user *buf, void __user *buf_fx, int size) /* * For 32-bit frames with fxstate, copy the user state to the * thread's fpu state, reconstruct fxstate from the fsave - * header. Sanitize the copied state etc. + * header. Validate and sanitize the copied state. */ struct fpu *fpu = &tsk->thread.fpu; struct user_i387_ia32_struct env; int err = 0; /* - * Drop the current fpu which clears fpu->fpstate_active. This ensures + * Drop the current fpu which clears fpu->initialized. This ensures * that any context-switch during the copy of the new state, * avoids the intermediate state from getting restored/saved. * Thus avoiding the new restored state from getting corrupted. * We will be ready to restore/save the state only after - * fpu->fpstate_active is again set. + * fpu->initialized is again set. */ fpu__drop(fpu); if (using_compacted_format()) { - err = copyin_to_xsaves(NULL, buf_fx, - &fpu->state.xsave); + err = copy_user_to_xstate(&fpu->state.xsave, buf_fx); } else { - err = __copy_from_user(&fpu->state.xsave, - buf_fx, state_size); + err = __copy_from_user(&fpu->state.xsave, buf_fx, state_size); + + if (!err && state_size > offsetof(struct xregs_state, header)) + err = validate_xstate_header(&fpu->state.xsave.header); } if (err || __copy_from_user(&env, buf, sizeof(env))) { @@ -339,7 +344,7 @@ static int __fpu__restore_sig(void __user *buf, void __user *buf_fx, int size) sanitize_restored_xstate(tsk, &env, xfeatures, fx_only); } - fpu->fpstate_active = 1; + fpu->initialized = 1; preempt_disable(); fpu__restore(fpu); preempt_enable(); diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c index c24ac1efb12d..f1d5476c9022 100644 --- a/arch/x86/kernel/fpu/xstate.c +++ b/arch/x86/kernel/fpu/xstate.c @@ -483,6 +483,30 @@ int using_compacted_format(void) return boot_cpu_has(X86_FEATURE_XSAVES); } +/* Validate an xstate header supplied by userspace (ptrace or sigreturn) */ +int validate_xstate_header(const struct xstate_header *hdr) +{ + /* No unknown or supervisor features may be set */ + if (hdr->xfeatures & (~xfeatures_mask | XFEATURE_MASK_SUPERVISOR)) + return -EINVAL; + + /* Userspace must use the uncompacted format */ + if (hdr->xcomp_bv) + return -EINVAL; + + /* + * If 'reserved' is shrunken to add a new field, make sure to validate + * that new field here! + */ + BUILD_BUG_ON(sizeof(hdr->reserved) != 48); + + /* No reserved bits may be set */ + if (memchr_inv(hdr->reserved, 0, sizeof(hdr->reserved))) + return -EINVAL; + + return 0; +} + static void __xstate_dump_leaves(void) { int i; @@ -867,7 +891,7 @@ const void *get_xsave_field_ptr(int xsave_state) { struct fpu *fpu = ¤t->thread.fpu; - if (!fpu->fpstate_active) + if (!fpu->initialized) return NULL; /* * fpu__save() takes the CPU's xstate registers @@ -921,38 +945,129 @@ int arch_set_user_pkey_access(struct task_struct *tsk, int pkey, #endif /* ! CONFIG_ARCH_HAS_PKEYS */ /* + * Weird legacy quirk: SSE and YMM states store information in the + * MXCSR and MXCSR_FLAGS fields of the FP area. That means if the FP + * area is marked as unused in the xfeatures header, we need to copy + * MXCSR and MXCSR_FLAGS if either SSE or YMM are in use. + */ +static inline bool xfeatures_mxcsr_quirk(u64 xfeatures) +{ + if (!(xfeatures & (XFEATURE_MASK_SSE|XFEATURE_MASK_YMM))) + return false; + + if (xfeatures & XFEATURE_MASK_FP) + return false; + + return true; +} + +/* * This is similar to user_regset_copyout(), but will not add offset to * the source data pointer or increment pos, count, kbuf, and ubuf. */ -static inline int xstate_copyout(unsigned int pos, unsigned int count, - void *kbuf, void __user *ubuf, - const void *data, const int start_pos, - const int end_pos) +static inline void +__copy_xstate_to_kernel(void *kbuf, const void *data, + unsigned int offset, unsigned int size, unsigned int size_total) { - if ((count == 0) || (pos < start_pos)) - return 0; + if (offset < size_total) { + unsigned int copy = min(size, size_total - offset); - if (end_pos < 0 || pos < end_pos) { - unsigned int copy = (end_pos < 0 ? count : min(count, end_pos - pos)); + memcpy(kbuf + offset, data, copy); + } +} - if (kbuf) { - memcpy(kbuf + pos, data, copy); - } else { - if (__copy_to_user(ubuf + pos, data, copy)) - return -EFAULT; +/* + * Convert from kernel XSAVES compacted format to standard format and copy + * to a kernel-space ptrace buffer. + * + * It supports partial copy but pos always starts from zero. This is called + * from xstateregs_get() and there we check the CPU has XSAVES. + */ +int copy_xstate_to_kernel(void *kbuf, struct xregs_state *xsave, unsigned int offset_start, unsigned int size_total) +{ + unsigned int offset, size; + struct xstate_header header; + int i; + + /* + * Currently copy_regset_to_user() starts from pos 0: + */ + if (unlikely(offset_start != 0)) + return -EFAULT; + + /* + * The destination is a ptrace buffer; we put in only user xstates: + */ + memset(&header, 0, sizeof(header)); + header.xfeatures = xsave->header.xfeatures; + header.xfeatures &= ~XFEATURE_MASK_SUPERVISOR; + + /* + * Copy xregs_state->header: + */ + offset = offsetof(struct xregs_state, header); + size = sizeof(header); + + __copy_xstate_to_kernel(kbuf, &header, offset, size, size_total); + + for (i = 0; i < XFEATURE_MAX; i++) { + /* + * Copy only in-use xstates: + */ + if ((header.xfeatures >> i) & 1) { + void *src = __raw_xsave_addr(xsave, 1 << i); + + offset = xstate_offsets[i]; + size = xstate_sizes[i]; + + /* The next component has to fit fully into the output buffer: */ + if (offset + size > size_total) + break; + + __copy_xstate_to_kernel(kbuf, src, offset, size, size_total); } + + } + + if (xfeatures_mxcsr_quirk(header.xfeatures)) { + offset = offsetof(struct fxregs_state, mxcsr); + size = MXCSR_AND_FLAGS_SIZE; + __copy_xstate_to_kernel(kbuf, &xsave->i387.mxcsr, offset, size, size_total); + } + + /* + * Fill xsave->i387.sw_reserved value for ptrace frame: + */ + offset = offsetof(struct fxregs_state, sw_reserved); + size = sizeof(xstate_fx_sw_bytes); + + __copy_xstate_to_kernel(kbuf, xstate_fx_sw_bytes, offset, size, size_total); + + return 0; +} + +static inline int +__copy_xstate_to_user(void __user *ubuf, const void *data, unsigned int offset, unsigned int size, unsigned int size_total) +{ + if (!size) + return 0; + + if (offset < size_total) { + unsigned int copy = min(size, size_total - offset); + + if (__copy_to_user(ubuf + offset, data, copy)) + return -EFAULT; } return 0; } /* * Convert from kernel XSAVES compacted format to standard format and copy - * to a ptrace buffer. It supports partial copy but pos always starts from + * to a user-space buffer. It supports partial copy but pos always starts from * zero. This is called from xstateregs_get() and there we check the CPU * has XSAVES. */ -int copyout_from_xsaves(unsigned int pos, unsigned int count, void *kbuf, - void __user *ubuf, struct xregs_state *xsave) +int copy_xstate_to_user(void __user *ubuf, struct xregs_state *xsave, unsigned int offset_start, unsigned int size_total) { unsigned int offset, size; int ret, i; @@ -961,7 +1076,7 @@ int copyout_from_xsaves(unsigned int pos, unsigned int count, void *kbuf, /* * Currently copy_regset_to_user() starts from pos 0: */ - if (unlikely(pos != 0)) + if (unlikely(offset_start != 0)) return -EFAULT; /* @@ -977,8 +1092,7 @@ int copyout_from_xsaves(unsigned int pos, unsigned int count, void *kbuf, offset = offsetof(struct xregs_state, header); size = sizeof(header); - ret = xstate_copyout(offset, size, kbuf, ubuf, &header, 0, count); - + ret = __copy_xstate_to_user(ubuf, &header, offset, size, size_total); if (ret) return ret; @@ -992,25 +1106,30 @@ int copyout_from_xsaves(unsigned int pos, unsigned int count, void *kbuf, offset = xstate_offsets[i]; size = xstate_sizes[i]; - ret = xstate_copyout(offset, size, kbuf, ubuf, src, 0, count); + /* The next component has to fit fully into the output buffer: */ + if (offset + size > size_total) + break; + ret = __copy_xstate_to_user(ubuf, src, offset, size, size_total); if (ret) return ret; - - if (offset + size >= count) - break; } } + if (xfeatures_mxcsr_quirk(header.xfeatures)) { + offset = offsetof(struct fxregs_state, mxcsr); + size = MXCSR_AND_FLAGS_SIZE; + __copy_xstate_to_user(ubuf, &xsave->i387.mxcsr, offset, size, size_total); + } + /* * Fill xsave->i387.sw_reserved value for ptrace frame: */ offset = offsetof(struct fxregs_state, sw_reserved); size = sizeof(xstate_fx_sw_bytes); - ret = xstate_copyout(offset, size, kbuf, ubuf, xstate_fx_sw_bytes, 0, count); - + ret = __copy_xstate_to_user(ubuf, xstate_fx_sw_bytes, offset, size, size_total); if (ret) return ret; @@ -1018,55 +1137,98 @@ int copyout_from_xsaves(unsigned int pos, unsigned int count, void *kbuf, } /* - * Convert from a ptrace standard-format buffer to kernel XSAVES format - * and copy to the target thread. This is called from xstateregs_set() and - * there we check the CPU has XSAVES and a whole standard-sized buffer - * exists. + * Convert from a ptrace standard-format kernel buffer to kernel XSAVES format + * and copy to the target thread. This is called from xstateregs_set(). */ -int copyin_to_xsaves(const void *kbuf, const void __user *ubuf, - struct xregs_state *xsave) +int copy_kernel_to_xstate(struct xregs_state *xsave, const void *kbuf) { unsigned int offset, size; int i; - u64 xfeatures; - u64 allowed_features; + struct xstate_header hdr; offset = offsetof(struct xregs_state, header); - size = sizeof(xfeatures); + size = sizeof(hdr); - if (kbuf) { - memcpy(&xfeatures, kbuf + offset, size); - } else { - if (__copy_from_user(&xfeatures, ubuf + offset, size)) - return -EFAULT; + memcpy(&hdr, kbuf + offset, size); + + if (validate_xstate_header(&hdr)) + return -EINVAL; + + for (i = 0; i < XFEATURE_MAX; i++) { + u64 mask = ((u64)1 << i); + + if (hdr.xfeatures & mask) { + void *dst = __raw_xsave_addr(xsave, 1 << i); + + offset = xstate_offsets[i]; + size = xstate_sizes[i]; + + memcpy(dst, kbuf + offset, size); + } + } + + if (xfeatures_mxcsr_quirk(hdr.xfeatures)) { + offset = offsetof(struct fxregs_state, mxcsr); + size = MXCSR_AND_FLAGS_SIZE; + memcpy(&xsave->i387.mxcsr, kbuf + offset, size); } /* - * Reject if the user sets any disabled or supervisor features: + * The state that came in from userspace was user-state only. + * Mask all the user states out of 'xfeatures': + */ + xsave->header.xfeatures &= XFEATURE_MASK_SUPERVISOR; + + /* + * Add back in the features that came in from userspace: */ - allowed_features = xfeatures_mask & ~XFEATURE_MASK_SUPERVISOR; + xsave->header.xfeatures |= hdr.xfeatures; - if (xfeatures & ~allowed_features) + return 0; +} + +/* + * Convert from a ptrace or sigreturn standard-format user-space buffer to + * kernel XSAVES format and copy to the target thread. This is called from + * xstateregs_set(), as well as potentially from the sigreturn() and + * rt_sigreturn() system calls. + */ +int copy_user_to_xstate(struct xregs_state *xsave, const void __user *ubuf) +{ + unsigned int offset, size; + int i; + struct xstate_header hdr; + + offset = offsetof(struct xregs_state, header); + size = sizeof(hdr); + + if (__copy_from_user(&hdr, ubuf + offset, size)) + return -EFAULT; + + if (validate_xstate_header(&hdr)) return -EINVAL; for (i = 0; i < XFEATURE_MAX; i++) { u64 mask = ((u64)1 << i); - if (xfeatures & mask) { + if (hdr.xfeatures & mask) { void *dst = __raw_xsave_addr(xsave, 1 << i); offset = xstate_offsets[i]; size = xstate_sizes[i]; - if (kbuf) { - memcpy(dst, kbuf + offset, size); - } else { - if (__copy_from_user(dst, ubuf + offset, size)) - return -EFAULT; - } + if (__copy_from_user(dst, ubuf + offset, size)) + return -EFAULT; } } + if (xfeatures_mxcsr_quirk(hdr.xfeatures)) { + offset = offsetof(struct fxregs_state, mxcsr); + size = MXCSR_AND_FLAGS_SIZE; + if (__copy_from_user(&xsave->i387.mxcsr, ubuf + offset, size)) + return -EFAULT; + } + /* * The state that came in from userspace was user-state only. * Mask all the user states out of 'xfeatures': @@ -1076,7 +1238,7 @@ int copyin_to_xsaves(const void *kbuf, const void __user *ubuf, /* * Add back in the features that came in from userspace: */ - xsave->header.xfeatures |= xfeatures; + xsave->header.xfeatures |= hdr.xfeatures; return 0; } diff --git a/arch/x86/kernel/irq_32.c b/arch/x86/kernel/irq_32.c index 1f38d9a4d9de..d4eb450144fd 100644 --- a/arch/x86/kernel/irq_32.c +++ b/arch/x86/kernel/irq_32.c @@ -64,7 +64,7 @@ static void call_on_stack(void *func, void *stack) static inline void *current_stack(void) { - return (void *)(current_stack_pointer() & ~(THREAD_SIZE - 1)); + return (void *)(current_stack_pointer & ~(THREAD_SIZE - 1)); } static inline int execute_on_irq_stack(int overflow, struct irq_desc *desc) @@ -88,7 +88,7 @@ static inline int execute_on_irq_stack(int overflow, struct irq_desc *desc) /* Save the next esp at the bottom of the stack */ prev_esp = (u32 *)irqstk; - *prev_esp = current_stack_pointer(); + *prev_esp = current_stack_pointer; if (unlikely(overflow)) call_on_stack(print_stack_overflow, isp); @@ -139,7 +139,7 @@ void do_softirq_own_stack(void) /* Push the previous esp onto the stack */ prev_esp = (u32 *)irqstk; - *prev_esp = current_stack_pointer(); + *prev_esp = current_stack_pointer; call_on_stack(__do_softirq, isp); } diff --git a/arch/x86/kernel/ksysfs.c b/arch/x86/kernel/ksysfs.c index 4b0592ca9e47..8c1cc08f514f 100644 --- a/arch/x86/kernel/ksysfs.c +++ b/arch/x86/kernel/ksysfs.c @@ -299,7 +299,7 @@ static int __init create_setup_data_nodes(struct kobject *parent) return 0; out_clean_nodes: - for (j = i - 1; j > 0; j--) + for (j = i - 1; j >= 0; j--) cleanup_setup_data_node(*(kobjp + j)); kfree(kobjp); out_setup_data_kobj: diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c index aa60a08b65b1..8bb9594d0761 100644 --- a/arch/x86/kernel/kvm.c +++ b/arch/x86/kernel/kvm.c @@ -117,7 +117,11 @@ static struct kvm_task_sleep_node *_find_apf_task(struct kvm_task_sleep_head *b, return NULL; } -void kvm_async_pf_task_wait(u32 token) +/* + * @interrupt_kernel: Is this called from a routine which interrupts the kernel + * (other than user space)? + */ +void kvm_async_pf_task_wait(u32 token, int interrupt_kernel) { u32 key = hash_32(token, KVM_TASK_SLEEP_HASHBITS); struct kvm_task_sleep_head *b = &async_pf_sleepers[key]; @@ -140,7 +144,10 @@ void kvm_async_pf_task_wait(u32 token) n.token = token; n.cpu = smp_processor_id(); - n.halted = is_idle_task(current) || preempt_count() > 1; + n.halted = is_idle_task(current) || + (IS_ENABLED(CONFIG_PREEMPT_COUNT) + ? preempt_count() > 1 || rcu_preempt_depth() + : interrupt_kernel); init_swait_queue_head(&n.wq); hlist_add_head(&n.link, &b->list); raw_spin_unlock(&b->lock); @@ -268,7 +275,7 @@ do_async_page_fault(struct pt_regs *regs, unsigned long error_code) case KVM_PV_REASON_PAGE_NOT_PRESENT: /* page is swapped out by the host. */ prev_state = exception_enter(); - kvm_async_pf_task_wait((u32)read_cr2()); + kvm_async_pf_task_wait((u32)read_cr2(), !user_mode(regs)); exception_exit(prev_state); break; case KVM_PV_REASON_PAGE_READY: diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c index e04442345fc0..4e188fda5961 100644 --- a/arch/x86/kernel/signal.c +++ b/arch/x86/kernel/signal.c @@ -263,7 +263,7 @@ get_sigframe(struct k_sigaction *ka, struct pt_regs *regs, size_t frame_size, sp = (unsigned long) ka->sa.sa_restorer; } - if (fpu->fpstate_active) { + if (fpu->initialized) { sp = fpu__alloc_mathframe(sp, IS_ENABLED(CONFIG_X86_32), &buf_fx, &math_size); *fpstate = (void __user *)sp; @@ -279,7 +279,7 @@ get_sigframe(struct k_sigaction *ka, struct pt_regs *regs, size_t frame_size, return (void __user *)-1L; /* save i387 and extended state */ - if (fpu->fpstate_active && + if (fpu->initialized && copy_fpstate_to_sigframe(*fpstate, (void __user *)buf_fx, math_size) < 0) return (void __user *)-1L; @@ -755,7 +755,7 @@ handle_signal(struct ksignal *ksig, struct pt_regs *regs) /* * Ensure the signal handler starts with the new fpu state. */ - if (fpu->fpstate_active) + if (fpu->initialized) fpu__clear(fpu); } signal_setup_done(failed, ksig, stepping); diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index 34ea3651362e..67db4f43309e 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -142,7 +142,7 @@ void ist_begin_non_atomic(struct pt_regs *regs) * from double_fault. */ BUG_ON((unsigned long)(current_top_of_stack() - - current_stack_pointer()) >= THREAD_SIZE); + current_stack_pointer) >= THREAD_SIZE); preempt_enable_no_resched(); } diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig index 3ea624452f93..3c48bc8bf08c 100644 --- a/arch/x86/kvm/Kconfig +++ b/arch/x86/kvm/Kconfig @@ -23,6 +23,7 @@ config KVM depends on HIGH_RES_TIMERS # for TASKSTATS/TASK_DELAY_ACCT: depends on NET && MULTIUSER + depends on X86_LOCAL_APIC select PREEMPT_NOTIFIERS select MMU_NOTIFIER select ANON_INODES diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index a36254cbf776..d90cdc77e077 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -425,8 +425,10 @@ static int fastop(struct x86_emulate_ctxt *ctxt, void (*fop)(struct fastop *)); #op " %al \n\t" \ FOP_RET -asm(".global kvm_fastop_exception \n" - "kvm_fastop_exception: xor %esi, %esi; ret"); +asm(".pushsection .fixup, \"ax\"\n" + ".global kvm_fastop_exception \n" + "kvm_fastop_exception: xor %esi, %esi; ret\n" + ".popsection"); FOP_START(setcc) FOP_SETCC(seto) diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index eca30c1eb1d9..106d4a029a8a 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -3837,7 +3837,7 @@ int kvm_handle_page_fault(struct kvm_vcpu *vcpu, u64 error_code, case KVM_PV_REASON_PAGE_NOT_PRESENT: vcpu->arch.apf.host_apf_reason = 0; local_irq_disable(); - kvm_async_pf_task_wait(fault_address); + kvm_async_pf_task_wait(fault_address, 0); local_irq_enable(); break; case KVM_PV_REASON_PAGE_READY: diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 6970249c09fc..a2b804e10c95 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -200,6 +200,8 @@ struct loaded_vmcs { int cpu; bool launched; bool nmi_known_unmasked; + unsigned long vmcs_host_cr3; /* May not match real cr3 */ + unsigned long vmcs_host_cr4; /* May not match real cr4 */ struct list_head loaded_vmcss_on_cpu_link; }; @@ -600,8 +602,6 @@ struct vcpu_vmx { int gs_ldt_reload_needed; int fs_reload_needed; u64 msr_host_bndcfgs; - unsigned long vmcs_host_cr3; /* May not match real cr3 */ - unsigned long vmcs_host_cr4; /* May not match real cr4 */ } host_state; struct { int vm86_active; @@ -2202,46 +2202,44 @@ static void vmx_vcpu_pi_load(struct kvm_vcpu *vcpu, int cpu) struct pi_desc old, new; unsigned int dest; - if (!kvm_arch_has_assigned_device(vcpu->kvm) || - !irq_remapping_cap(IRQ_POSTING_CAP) || - !kvm_vcpu_apicv_active(vcpu)) + /* + * In case of hot-plug or hot-unplug, we may have to undo + * vmx_vcpu_pi_put even if there is no assigned device. And we + * always keep PI.NDST up to date for simplicity: it makes the + * code easier, and CPU migration is not a fast path. + */ + if (!pi_test_sn(pi_desc) && vcpu->cpu == cpu) return; + /* + * First handle the simple case where no cmpxchg is necessary; just + * allow posting non-urgent interrupts. + * + * If the 'nv' field is POSTED_INTR_WAKEUP_VECTOR, do not change + * PI.NDST: pi_post_block will do it for us and the wakeup_handler + * expects the VCPU to be on the blocked_vcpu_list that matches + * PI.NDST. + */ + if (pi_desc->nv == POSTED_INTR_WAKEUP_VECTOR || + vcpu->cpu == cpu) { + pi_clear_sn(pi_desc); + return; + } + + /* The full case. */ do { old.control = new.control = pi_desc->control; - /* - * If 'nv' field is POSTED_INTR_WAKEUP_VECTOR, there - * are two possible cases: - * 1. After running 'pre_block', context switch - * happened. For this case, 'sn' was set in - * vmx_vcpu_put(), so we need to clear it here. - * 2. After running 'pre_block', we were blocked, - * and woken up by some other guy. For this case, - * we don't need to do anything, 'pi_post_block' - * will do everything for us. However, we cannot - * check whether it is case #1 or case #2 here - * (maybe, not needed), so we also clear sn here, - * I think it is not a big deal. - */ - if (pi_desc->nv != POSTED_INTR_WAKEUP_VECTOR) { - if (vcpu->cpu != cpu) { - dest = cpu_physical_id(cpu); - - if (x2apic_enabled()) - new.ndst = dest; - else - new.ndst = (dest << 8) & 0xFF00; - } + dest = cpu_physical_id(cpu); - /* set 'NV' to 'notification vector' */ - new.nv = POSTED_INTR_VECTOR; - } + if (x2apic_enabled()) + new.ndst = dest; + else + new.ndst = (dest << 8) & 0xFF00; - /* Allow posting non-urgent interrupts */ new.sn = 0; - } while (cmpxchg(&pi_desc->control, old.control, - new.control) != old.control); + } while (cmpxchg64(&pi_desc->control, old.control, + new.control) != old.control); } static void decache_tsc_multiplier(struct vcpu_vmx *vmx) @@ -5178,12 +5176,12 @@ static void vmx_set_constant_host_state(struct vcpu_vmx *vmx) */ cr3 = __read_cr3(); vmcs_writel(HOST_CR3, cr3); /* 22.2.3 FIXME: shadow tables */ - vmx->host_state.vmcs_host_cr3 = cr3; + vmx->loaded_vmcs->vmcs_host_cr3 = cr3; /* Save the most likely value for this task's CR4 in the VMCS. */ cr4 = cr4_read_shadow(); vmcs_writel(HOST_CR4, cr4); /* 22.2.3, 22.2.5 */ - vmx->host_state.vmcs_host_cr4 = cr4; + vmx->loaded_vmcs->vmcs_host_cr4 = cr4; vmcs_write16(HOST_CS_SELECTOR, __KERNEL_CS); /* 22.2.4 */ #ifdef CONFIG_X86_64 @@ -9273,15 +9271,15 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu) vmcs_writel(GUEST_RIP, vcpu->arch.regs[VCPU_REGS_RIP]); cr3 = __get_current_cr3_fast(); - if (unlikely(cr3 != vmx->host_state.vmcs_host_cr3)) { + if (unlikely(cr3 != vmx->loaded_vmcs->vmcs_host_cr3)) { vmcs_writel(HOST_CR3, cr3); - vmx->host_state.vmcs_host_cr3 = cr3; + vmx->loaded_vmcs->vmcs_host_cr3 = cr3; } cr4 = cr4_read_shadow(); - if (unlikely(cr4 != vmx->host_state.vmcs_host_cr4)) { + if (unlikely(cr4 != vmx->loaded_vmcs->vmcs_host_cr4)) { vmcs_writel(HOST_CR4, cr4); - vmx->host_state.vmcs_host_cr4 = cr4; + vmx->loaded_vmcs->vmcs_host_cr4 = cr4; } /* When single-stepping over STI and MOV SS, we must clear the @@ -9591,6 +9589,13 @@ static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id) vmx->msr_ia32_feature_control_valid_bits = FEATURE_CONTROL_LOCKED; + /* + * Enforce invariant: pi_desc.nv is always either POSTED_INTR_VECTOR + * or POSTED_INTR_WAKEUP_VECTOR. + */ + vmx->pi_desc.nv = POSTED_INTR_VECTOR; + vmx->pi_desc.sn = 1; + return &vmx->vcpu; free_vmcs: @@ -9839,7 +9844,8 @@ static void vmx_inject_page_fault_nested(struct kvm_vcpu *vcpu, WARN_ON(!is_guest_mode(vcpu)); - if (nested_vmx_is_page_fault_vmexit(vmcs12, fault->error_code)) { + if (nested_vmx_is_page_fault_vmexit(vmcs12, fault->error_code) && + !to_vmx(vcpu)->nested.nested_run_pending) { vmcs12->vm_exit_intr_error_code = fault->error_code; nested_vmx_vmexit(vcpu, EXIT_REASON_EXCEPTION_NMI, PF_VECTOR | INTR_TYPE_HARD_EXCEPTION | @@ -11704,6 +11710,37 @@ static void vmx_enable_log_dirty_pt_masked(struct kvm *kvm, kvm_mmu_clear_dirty_pt_masked(kvm, memslot, offset, mask); } +static void __pi_post_block(struct kvm_vcpu *vcpu) +{ + struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu); + struct pi_desc old, new; + unsigned int dest; + + do { + old.control = new.control = pi_desc->control; + WARN(old.nv != POSTED_INTR_WAKEUP_VECTOR, + "Wakeup handler not enabled while the VCPU is blocked\n"); + + dest = cpu_physical_id(vcpu->cpu); + + if (x2apic_enabled()) + new.ndst = dest; + else + new.ndst = (dest << 8) & 0xFF00; + + /* set 'NV' to 'notification vector' */ + new.nv = POSTED_INTR_VECTOR; + } while (cmpxchg64(&pi_desc->control, old.control, + new.control) != old.control); + + if (!WARN_ON_ONCE(vcpu->pre_pcpu == -1)) { + spin_lock(&per_cpu(blocked_vcpu_on_cpu_lock, vcpu->pre_pcpu)); + list_del(&vcpu->blocked_vcpu_list); + spin_unlock(&per_cpu(blocked_vcpu_on_cpu_lock, vcpu->pre_pcpu)); + vcpu->pre_pcpu = -1; + } +} + /* * This routine does the following things for vCPU which is going * to be blocked if VT-d PI is enabled. @@ -11719,7 +11756,6 @@ static void vmx_enable_log_dirty_pt_masked(struct kvm *kvm, */ static int pi_pre_block(struct kvm_vcpu *vcpu) { - unsigned long flags; unsigned int dest; struct pi_desc old, new; struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu); @@ -11729,34 +11765,20 @@ static int pi_pre_block(struct kvm_vcpu *vcpu) !kvm_vcpu_apicv_active(vcpu)) return 0; - vcpu->pre_pcpu = vcpu->cpu; - spin_lock_irqsave(&per_cpu(blocked_vcpu_on_cpu_lock, - vcpu->pre_pcpu), flags); - list_add_tail(&vcpu->blocked_vcpu_list, - &per_cpu(blocked_vcpu_on_cpu, - vcpu->pre_pcpu)); - spin_unlock_irqrestore(&per_cpu(blocked_vcpu_on_cpu_lock, - vcpu->pre_pcpu), flags); + WARN_ON(irqs_disabled()); + local_irq_disable(); + if (!WARN_ON_ONCE(vcpu->pre_pcpu != -1)) { + vcpu->pre_pcpu = vcpu->cpu; + spin_lock(&per_cpu(blocked_vcpu_on_cpu_lock, vcpu->pre_pcpu)); + list_add_tail(&vcpu->blocked_vcpu_list, + &per_cpu(blocked_vcpu_on_cpu, + vcpu->pre_pcpu)); + spin_unlock(&per_cpu(blocked_vcpu_on_cpu_lock, vcpu->pre_pcpu)); + } do { old.control = new.control = pi_desc->control; - /* - * We should not block the vCPU if - * an interrupt is posted for it. - */ - if (pi_test_on(pi_desc) == 1) { - spin_lock_irqsave(&per_cpu(blocked_vcpu_on_cpu_lock, - vcpu->pre_pcpu), flags); - list_del(&vcpu->blocked_vcpu_list); - spin_unlock_irqrestore( - &per_cpu(blocked_vcpu_on_cpu_lock, - vcpu->pre_pcpu), flags); - vcpu->pre_pcpu = -1; - - return 1; - } - WARN((pi_desc->sn == 1), "Warning: SN field of posted-interrupts " "is set before blocking\n"); @@ -11778,10 +11800,15 @@ static int pi_pre_block(struct kvm_vcpu *vcpu) /* set 'NV' to 'wakeup vector' */ new.nv = POSTED_INTR_WAKEUP_VECTOR; - } while (cmpxchg(&pi_desc->control, old.control, - new.control) != old.control); + } while (cmpxchg64(&pi_desc->control, old.control, + new.control) != old.control); - return 0; + /* We should not block the vCPU if an interrupt is posted for it. */ + if (pi_test_on(pi_desc) == 1) + __pi_post_block(vcpu); + + local_irq_enable(); + return (vcpu->pre_pcpu == -1); } static int vmx_pre_block(struct kvm_vcpu *vcpu) @@ -11797,44 +11824,13 @@ static int vmx_pre_block(struct kvm_vcpu *vcpu) static void pi_post_block(struct kvm_vcpu *vcpu) { - struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu); - struct pi_desc old, new; - unsigned int dest; - unsigned long flags; - - if (!kvm_arch_has_assigned_device(vcpu->kvm) || - !irq_remapping_cap(IRQ_POSTING_CAP) || - !kvm_vcpu_apicv_active(vcpu)) + if (vcpu->pre_pcpu == -1) return; - do { - old.control = new.control = pi_desc->control; - - dest = cpu_physical_id(vcpu->cpu); - - if (x2apic_enabled()) - new.ndst = dest; - else - new.ndst = (dest << 8) & 0xFF00; - - /* Allow posting non-urgent interrupts */ - new.sn = 0; - - /* set 'NV' to 'notification vector' */ - new.nv = POSTED_INTR_VECTOR; - } while (cmpxchg(&pi_desc->control, old.control, - new.control) != old.control); - - if(vcpu->pre_pcpu != -1) { - spin_lock_irqsave( - &per_cpu(blocked_vcpu_on_cpu_lock, - vcpu->pre_pcpu), flags); - list_del(&vcpu->blocked_vcpu_list); - spin_unlock_irqrestore( - &per_cpu(blocked_vcpu_on_cpu_lock, - vcpu->pre_pcpu), flags); - vcpu->pre_pcpu = -1; - } + WARN_ON(irqs_disabled()); + local_irq_disable(); + __pi_post_block(vcpu); + local_irq_enable(); } static void vmx_post_block(struct kvm_vcpu *vcpu) diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index cd17b7d9a107..03869eb7fcd6 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -7225,7 +7225,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) int r; sigset_t sigsaved; - fpu__activate_curr(fpu); + fpu__initialize(fpu); if (vcpu->sigset_active) sigprocmask(SIG_SETMASK, &vcpu->sigset, &sigsaved); diff --git a/arch/x86/math-emu/fpu_entry.c b/arch/x86/math-emu/fpu_entry.c index d4a7df2205b8..220638a4cb94 100644 --- a/arch/x86/math-emu/fpu_entry.c +++ b/arch/x86/math-emu/fpu_entry.c @@ -114,7 +114,7 @@ void math_emulate(struct math_emu_info *info) struct desc_struct code_descriptor; struct fpu *fpu = ¤t->thread.fpu; - fpu__activate_curr(fpu); + fpu__initialize(fpu); #ifdef RE_ENTRANT_CHECKING if (emulating) { diff --git a/arch/x86/mm/extable.c b/arch/x86/mm/extable.c index c076f710de4c..c3521e2be396 100644 --- a/arch/x86/mm/extable.c +++ b/arch/x86/mm/extable.c @@ -2,6 +2,7 @@ #include <linux/uaccess.h> #include <linux/sched/debug.h> +#include <asm/fpu/internal.h> #include <asm/traps.h> #include <asm/kdebug.h> @@ -78,6 +79,29 @@ bool ex_handler_refcount(const struct exception_table_entry *fixup, } EXPORT_SYMBOL_GPL(ex_handler_refcount); +/* + * Handler for when we fail to restore a task's FPU state. We should never get + * here because the FPU state of a task using the FPU (task->thread.fpu.state) + * should always be valid. However, past bugs have allowed userspace to set + * reserved bits in the XSAVE area using PTRACE_SETREGSET or sys_rt_sigreturn(). + * These caused XRSTOR to fail when switching to the task, leaking the FPU + * registers of the task previously executing on the CPU. Mitigate this class + * of vulnerability by restoring from the initial state (essentially, zeroing + * out all the FPU registers) if we can't restore from the task's FPU state. + */ +bool ex_handler_fprestore(const struct exception_table_entry *fixup, + struct pt_regs *regs, int trapnr) +{ + regs->ip = ex_fixup_addr(fixup); + + WARN_ONCE(1, "Bad FPU state detected at %pB, reinitializing FPU registers.", + (void *)instruction_pointer(regs)); + + __copy_kernel_to_fpregs(&init_fpstate, -1); + return true; +} +EXPORT_SYMBOL_GPL(ex_handler_fprestore); + bool ex_handler_ext(const struct exception_table_entry *fixup, struct pt_regs *regs, int trapnr) { diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index 39567b5c33da..e2baeaa053a5 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -192,8 +192,7 @@ is_prefetch(struct pt_regs *regs, unsigned long error_code, unsigned long addr) * 6. T1 : reaches here, sees vma_pkey(vma)=5, when we really * faulted on a pte with its pkey=4. */ -static void fill_sig_info_pkey(int si_code, siginfo_t *info, - struct vm_area_struct *vma) +static void fill_sig_info_pkey(int si_code, siginfo_t *info, u32 *pkey) { /* This is effectively an #ifdef */ if (!boot_cpu_has(X86_FEATURE_OSPKE)) @@ -209,7 +208,7 @@ static void fill_sig_info_pkey(int si_code, siginfo_t *info, * valid VMA, so we should never reach this without a * valid VMA. */ - if (!vma) { + if (!pkey) { WARN_ONCE(1, "PKU fault with no VMA passed in"); info->si_pkey = 0; return; @@ -219,13 +218,12 @@ static void fill_sig_info_pkey(int si_code, siginfo_t *info, * absolutely guranteed to be 100% accurate because of * the race explained above. */ - info->si_pkey = vma_pkey(vma); + info->si_pkey = *pkey; } static void force_sig_info_fault(int si_signo, int si_code, unsigned long address, - struct task_struct *tsk, struct vm_area_struct *vma, - int fault) + struct task_struct *tsk, u32 *pkey, int fault) { unsigned lsb = 0; siginfo_t info; @@ -240,7 +238,7 @@ force_sig_info_fault(int si_signo, int si_code, unsigned long address, lsb = PAGE_SHIFT; info.si_addr_lsb = lsb; - fill_sig_info_pkey(si_code, &info, vma); + fill_sig_info_pkey(si_code, &info, pkey); force_sig_info(si_signo, &info, tsk); } @@ -762,8 +760,6 @@ no_context(struct pt_regs *regs, unsigned long error_code, struct task_struct *tsk = current; unsigned long flags; int sig; - /* No context means no VMA to pass down */ - struct vm_area_struct *vma = NULL; /* Are we prepared to handle this kernel fault? */ if (fixup_exception(regs, X86_TRAP_PF)) { @@ -788,7 +784,7 @@ no_context(struct pt_regs *regs, unsigned long error_code, /* XXX: hwpoison faults will set the wrong code. */ force_sig_info_fault(signal, si_code, address, - tsk, vma, 0); + tsk, NULL, 0); } /* @@ -896,8 +892,7 @@ show_signal_msg(struct pt_regs *regs, unsigned long error_code, static void __bad_area_nosemaphore(struct pt_regs *regs, unsigned long error_code, - unsigned long address, struct vm_area_struct *vma, - int si_code) + unsigned long address, u32 *pkey, int si_code) { struct task_struct *tsk = current; @@ -945,7 +940,7 @@ __bad_area_nosemaphore(struct pt_regs *regs, unsigned long error_code, tsk->thread.error_code = error_code; tsk->thread.trap_nr = X86_TRAP_PF; - force_sig_info_fault(SIGSEGV, si_code, address, tsk, vma, 0); + force_sig_info_fault(SIGSEGV, si_code, address, tsk, pkey, 0); return; } @@ -958,9 +953,9 @@ __bad_area_nosemaphore(struct pt_regs *regs, unsigned long error_code, static noinline void bad_area_nosemaphore(struct pt_regs *regs, unsigned long error_code, - unsigned long address, struct vm_area_struct *vma) + unsigned long address, u32 *pkey) { - __bad_area_nosemaphore(regs, error_code, address, vma, SEGV_MAPERR); + __bad_area_nosemaphore(regs, error_code, address, pkey, SEGV_MAPERR); } static void @@ -968,6 +963,10 @@ __bad_area(struct pt_regs *regs, unsigned long error_code, unsigned long address, struct vm_area_struct *vma, int si_code) { struct mm_struct *mm = current->mm; + u32 pkey; + + if (vma) + pkey = vma_pkey(vma); /* * Something tried to access memory that isn't in our memory map.. @@ -975,7 +974,8 @@ __bad_area(struct pt_regs *regs, unsigned long error_code, */ up_read(&mm->mmap_sem); - __bad_area_nosemaphore(regs, error_code, address, vma, si_code); + __bad_area_nosemaphore(regs, error_code, address, + (vma) ? &pkey : NULL, si_code); } static noinline void @@ -1018,7 +1018,7 @@ bad_area_access_error(struct pt_regs *regs, unsigned long error_code, static void do_sigbus(struct pt_regs *regs, unsigned long error_code, unsigned long address, - struct vm_area_struct *vma, unsigned int fault) + u32 *pkey, unsigned int fault) { struct task_struct *tsk = current; int code = BUS_ADRERR; @@ -1045,13 +1045,12 @@ do_sigbus(struct pt_regs *regs, unsigned long error_code, unsigned long address, code = BUS_MCEERR_AR; } #endif - force_sig_info_fault(SIGBUS, code, address, tsk, vma, fault); + force_sig_info_fault(SIGBUS, code, address, tsk, pkey, fault); } static noinline void mm_fault_error(struct pt_regs *regs, unsigned long error_code, - unsigned long address, struct vm_area_struct *vma, - unsigned int fault) + unsigned long address, u32 *pkey, unsigned int fault) { if (fatal_signal_pending(current) && !(error_code & PF_USER)) { no_context(regs, error_code, address, 0, 0); @@ -1075,9 +1074,9 @@ mm_fault_error(struct pt_regs *regs, unsigned long error_code, } else { if (fault & (VM_FAULT_SIGBUS|VM_FAULT_HWPOISON| VM_FAULT_HWPOISON_LARGE)) - do_sigbus(regs, error_code, address, vma, fault); + do_sigbus(regs, error_code, address, pkey, fault); else if (fault & VM_FAULT_SIGSEGV) - bad_area_nosemaphore(regs, error_code, address, vma); + bad_area_nosemaphore(regs, error_code, address, pkey); else BUG(); } @@ -1267,6 +1266,7 @@ __do_page_fault(struct pt_regs *regs, unsigned long error_code, struct mm_struct *mm; int fault, major = 0; unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE; + u32 pkey; tsk = current; mm = tsk->mm; @@ -1467,9 +1467,10 @@ good_area: return; } + pkey = vma_pkey(vma); up_read(&mm->mmap_sem); if (unlikely(fault & VM_FAULT_ERROR)) { - mm_fault_error(regs, error_code, address, vma, fault); + mm_fault_error(regs, error_code, address, &pkey, fault); return; } diff --git a/arch/x86/mm/mem_encrypt.c b/arch/x86/mm/mem_encrypt.c index 3fcc8e01683b..16c5f37933a2 100644 --- a/arch/x86/mm/mem_encrypt.c +++ b/arch/x86/mm/mem_encrypt.c @@ -10,6 +10,8 @@ * published by the Free Software Foundation. */ +#define DISABLE_BRANCH_PROFILING + #include <linux/linkage.h> #include <linux/init.h> #include <linux/mm.h> diff --git a/arch/x86/mm/pkeys.c b/arch/x86/mm/pkeys.c index 2dab69a706ec..d7bc0eea20a5 100644 --- a/arch/x86/mm/pkeys.c +++ b/arch/x86/mm/pkeys.c @@ -18,7 +18,6 @@ #include <asm/cpufeature.h> /* boot_cpu_has, ... */ #include <asm/mmu_context.h> /* vma_pkey() */ -#include <asm/fpu/internal.h> /* fpregs_active() */ int __execute_only_pkey(struct mm_struct *mm) { @@ -45,7 +44,7 @@ int __execute_only_pkey(struct mm_struct *mm) */ preempt_disable(); if (!need_to_set_mm_pkey && - fpregs_active() && + current->thread.fpu.initialized && !__pkru_allows_read(read_pkru(), execute_only_pkey)) { preempt_enable(); return execute_only_pkey; diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c index 93fe97cce581..49d9778376d7 100644 --- a/arch/x86/mm/tlb.c +++ b/arch/x86/mm/tlb.c @@ -191,7 +191,7 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next, * mapped in the new pgd, we'll double-fault. Forcibly * map it. */ - unsigned int index = pgd_index(current_stack_pointer()); + unsigned int index = pgd_index(current_stack_pointer); pgd_t *pgd = next->pgd + index; if (unlikely(pgd_none(*pgd))) diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c index 8c9573660d51..0554e8aef4d5 100644 --- a/arch/x86/net/bpf_jit_comp.c +++ b/arch/x86/net/bpf_jit_comp.c @@ -284,9 +284,9 @@ static void emit_bpf_tail_call(u8 **pprog) /* if (index >= array->map.max_entries) * goto out; */ - EMIT4(0x48, 0x8B, 0x46, /* mov rax, qword ptr [rsi + 16] */ + EMIT2(0x89, 0xD2); /* mov edx, edx */ + EMIT3(0x39, 0x56, /* cmp dword ptr [rsi + 16], edx */ offsetof(struct bpf_array, map.max_entries)); - EMIT3(0x48, 0x39, 0xD0); /* cmp rax, rdx */ #define OFFSET1 43 /* number of bytes to jump */ EMIT2(X86_JBE, OFFSET1); /* jbe out */ label1 = cnt; diff --git a/arch/x86/xen/mmu_pv.c b/arch/x86/xen/mmu_pv.c index 7330cb3b2283..71495f1a86d7 100644 --- a/arch/x86/xen/mmu_pv.c +++ b/arch/x86/xen/mmu_pv.c @@ -1238,21 +1238,16 @@ static void __init xen_pagetable_cleanhighmap(void) * from _brk_limit way up to the max_pfn_mapped (which is the end of * the ramdisk). We continue on, erasing PMD entries that point to page * tables - do note that they are accessible at this stage via __va. - * For good measure we also round up to the PMD - which means that if + * As Xen is aligning the memory end to a 4MB boundary, for good + * measure we also round up to PMD_SIZE * 2 - which means that if * anybody is using __ka address to the initial boot-stack - and try * to use it - they are going to crash. The xen_start_info has been * taken care of already in xen_setup_kernel_pagetable. */ addr = xen_start_info->pt_base; - size = roundup(xen_start_info->nr_pt_frames * PAGE_SIZE, PMD_SIZE); + size = xen_start_info->nr_pt_frames * PAGE_SIZE; - xen_cleanhighmap(addr, addr + size); + xen_cleanhighmap(addr, roundup(addr + size, PMD_SIZE * 2)); xen_start_info->pt_base = (unsigned long)__va(__pa(xen_start_info->pt_base)); -#ifdef DEBUG - /* This is superfluous and is not necessary, but you know what - * lets do it. The MODULES_VADDR -> MODULES_END should be clear of - * anything at this stage. */ - xen_cleanhighmap(MODULES_VADDR, roundup(MODULES_VADDR, PUD_SIZE) - 1); -#endif } #endif diff --git a/block/blk-core.c b/block/blk-core.c index aebe676225e6..048be4aa6024 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -854,6 +854,9 @@ struct request_queue *blk_alloc_queue_node(gfp_t gfp_mask, int node_id) kobject_init(&q->kobj, &blk_queue_ktype); +#ifdef CONFIG_BLK_DEV_IO_TRACE + mutex_init(&q->blk_trace_mutex); +#endif mutex_init(&q->sysfs_lock); spin_lock_init(&q->__queue_lock); diff --git a/block/blk-mq-debugfs.c b/block/blk-mq-debugfs.c index 980e73095643..de294d775acf 100644 --- a/block/blk-mq-debugfs.c +++ b/block/blk-mq-debugfs.c @@ -815,10 +815,14 @@ int blk_mq_debugfs_register(struct request_queue *q) goto err; /* - * blk_mq_init_hctx() attempted to do this already, but q->debugfs_dir + * blk_mq_init_sched() attempted to do this already, but q->debugfs_dir * didn't exist yet (because we don't know what to name the directory * until the queue is registered to a gendisk). */ + if (q->elevator && !q->sched_debugfs_dir) + blk_mq_debugfs_register_sched(q); + + /* Similarly, blk_mq_init_hctx() couldn't do this previously. */ queue_for_each_hw_ctx(q, hctx, i) { if (!hctx->debugfs_dir && blk_mq_debugfs_register_hctx(q, hctx)) goto err; diff --git a/block/blk-throttle.c b/block/blk-throttle.c index 0fea76aa0f3f..17816a028dcb 100644 --- a/block/blk-throttle.c +++ b/block/blk-throttle.c @@ -1911,11 +1911,11 @@ static void throtl_upgrade_state(struct throtl_data *td) tg->disptime = jiffies - 1; throtl_select_dispatch(sq); - throtl_schedule_next_dispatch(sq, false); + throtl_schedule_next_dispatch(sq, true); } rcu_read_unlock(); throtl_select_dispatch(&td->service_queue); - throtl_schedule_next_dispatch(&td->service_queue, false); + throtl_schedule_next_dispatch(&td->service_queue, true); queue_work(kthrotld_workqueue, &td->dispatch_work); } diff --git a/block/bsg-lib.c b/block/bsg-lib.c index c82408c7cc3c..15d25ccd51a5 100644 --- a/block/bsg-lib.c +++ b/block/bsg-lib.c @@ -154,7 +154,6 @@ static int bsg_prepare_job(struct device *dev, struct request *req) failjob_rls_rqst_payload: kfree(job->request_payload.sg_list); failjob_rls_job: - kfree(job); return -ENOMEM; } @@ -208,20 +207,34 @@ static int bsg_init_rq(struct request_queue *q, struct request *req, gfp_t gfp) struct bsg_job *job = blk_mq_rq_to_pdu(req); struct scsi_request *sreq = &job->sreq; + /* called right after the request is allocated for the request_queue */ + + sreq->sense = kzalloc(SCSI_SENSE_BUFFERSIZE, gfp); + if (!sreq->sense) + return -ENOMEM; + + return 0; +} + +static void bsg_initialize_rq(struct request *req) +{ + struct bsg_job *job = blk_mq_rq_to_pdu(req); + struct scsi_request *sreq = &job->sreq; + void *sense = sreq->sense; + + /* called right before the request is given to the request_queue user */ + memset(job, 0, sizeof(*job)); scsi_req_init(sreq); + + sreq->sense = sense; sreq->sense_len = SCSI_SENSE_BUFFERSIZE; - sreq->sense = kzalloc(sreq->sense_len, gfp); - if (!sreq->sense) - return -ENOMEM; job->req = req; - job->reply = sreq->sense; + job->reply = sense; job->reply_len = sreq->sense_len; job->dd_data = job + 1; - - return 0; } static void bsg_exit_rq(struct request_queue *q, struct request *req) @@ -252,6 +265,7 @@ struct request_queue *bsg_setup_queue(struct device *dev, const char *name, q->cmd_size = sizeof(struct bsg_job) + dd_job_size; q->init_rq_fn = bsg_init_rq; q->exit_rq_fn = bsg_exit_rq; + q->initialize_rq_fn = bsg_initialize_rq; q->request_fn = bsg_request_fn; ret = blk_init_allocated_queue(q); diff --git a/block/partition-generic.c b/block/partition-generic.c index 86e8fe1adcdb..88c555db4e5d 100644 --- a/block/partition-generic.c +++ b/block/partition-generic.c @@ -112,7 +112,7 @@ ssize_t part_stat_show(struct device *dev, struct device_attribute *attr, char *buf) { struct hd_struct *p = dev_to_part(dev); - struct request_queue *q = dev_to_disk(dev)->queue; + struct request_queue *q = part_to_disk(p)->queue; unsigned int inflight[2]; int cpu; diff --git a/drivers/acpi/apei/ghes.c b/drivers/acpi/apei/ghes.c index 077f9bad6f44..3c3a37b8503b 100644 --- a/drivers/acpi/apei/ghes.c +++ b/drivers/acpi/apei/ghes.c @@ -743,17 +743,19 @@ static int ghes_proc(struct ghes *ghes) } ghes_do_proc(ghes, ghes->estatus); +out: + ghes_clear_estatus(ghes); + + if (rc == -ENOENT) + return rc; + /* * GHESv2 type HEST entries introduce support for error acknowledgment, * so only acknowledge the error if this support is present. */ - if (is_hest_type_generic_v2(ghes)) { - rc = ghes_ack_error(ghes->generic_v2); - if (rc) - return rc; - } -out: - ghes_clear_estatus(ghes); + if (is_hest_type_generic_v2(ghes)) + return ghes_ack_error(ghes->generic_v2); + return rc; } diff --git a/drivers/acpi/arm64/iort.c b/drivers/acpi/arm64/iort.c index 9565d572f8dd..de56394dd161 100644 --- a/drivers/acpi/arm64/iort.c +++ b/drivers/acpi/arm64/iort.c @@ -1178,12 +1178,44 @@ dev_put: return ret; } +static bool __init iort_enable_acs(struct acpi_iort_node *iort_node) +{ + if (iort_node->type == ACPI_IORT_NODE_PCI_ROOT_COMPLEX) { + struct acpi_iort_node *parent; + struct acpi_iort_id_mapping *map; + int i; + + map = ACPI_ADD_PTR(struct acpi_iort_id_mapping, iort_node, + iort_node->mapping_offset); + + for (i = 0; i < iort_node->mapping_count; i++, map++) { + if (!map->output_reference) + continue; + + parent = ACPI_ADD_PTR(struct acpi_iort_node, + iort_table, map->output_reference); + /* + * If we detect a RC->SMMU mapping, make sure + * we enable ACS on the system. + */ + if ((parent->type == ACPI_IORT_NODE_SMMU) || + (parent->type == ACPI_IORT_NODE_SMMU_V3)) { + pci_request_acs(); + return true; + } + } + } + + return false; +} + static void __init iort_init_platform_devices(void) { struct acpi_iort_node *iort_node, *iort_end; struct acpi_table_iort *iort; struct fwnode_handle *fwnode; int i, ret; + bool acs_enabled = false; /* * iort_table and iort both point to the start of IORT table, but @@ -1203,6 +1235,9 @@ static void __init iort_init_platform_devices(void) return; } + if (!acs_enabled) + acs_enabled = iort_enable_acs(iort_node); + if ((iort_node->type == ACPI_IORT_NODE_SMMU) || (iort_node->type == ACPI_IORT_NODE_SMMU_V3)) { diff --git a/drivers/android/binder.c b/drivers/android/binder.c index d055b3f2a207..ab34239a76ee 100644 --- a/drivers/android/binder.c +++ b/drivers/android/binder.c @@ -2217,7 +2217,7 @@ static void binder_transaction_buffer_release(struct binder_proc *proc, debug_id, (u64)fda->num_fds); continue; } - fd_array = (u32 *)(parent_buffer + fda->parent_offset); + fd_array = (u32 *)(parent_buffer + (uintptr_t)fda->parent_offset); for (fd_index = 0; fd_index < fda->num_fds; fd_index++) task_close_fd(proc, fd_array[fd_index]); } break; @@ -2326,7 +2326,6 @@ static int binder_translate_handle(struct flat_binder_object *fp, (u64)node->ptr); binder_node_unlock(node); } else { - int ret; struct binder_ref_data dest_rdata; binder_node_unlock(node); @@ -2442,7 +2441,7 @@ static int binder_translate_fd_array(struct binder_fd_array_object *fda, */ parent_buffer = parent->buffer - binder_alloc_get_user_buffer_offset(&target_proc->alloc); - fd_array = (u32 *)(parent_buffer + fda->parent_offset); + fd_array = (u32 *)(parent_buffer + (uintptr_t)fda->parent_offset); if (!IS_ALIGNED((unsigned long)fd_array, sizeof(u32))) { binder_user_error("%d:%d parent offset not aligned correctly.\n", proc->pid, thread->pid); @@ -2508,7 +2507,7 @@ static int binder_fixup_parent(struct binder_transaction *t, proc->pid, thread->pid); return -EINVAL; } - parent_buffer = (u8 *)(parent->buffer - + parent_buffer = (u8 *)((uintptr_t)parent->buffer - binder_alloc_get_user_buffer_offset( &target_proc->alloc)); *(binder_uintptr_t *)(parent_buffer + bp->parent_offset) = bp->buffer; @@ -3083,6 +3082,7 @@ static void binder_transaction(struct binder_proc *proc, err_dead_proc_or_thread: return_error = BR_DEAD_REPLY; return_error_line = __LINE__; + binder_dequeue_work(proc, tcomplete); err_translate_failed: err_bad_object_type: err_bad_offset: diff --git a/drivers/android/binder_alloc.c b/drivers/android/binder_alloc.c index 8fe165844e47..064f5e31ec55 100644 --- a/drivers/android/binder_alloc.c +++ b/drivers/android/binder_alloc.c @@ -913,6 +913,7 @@ enum lru_status binder_alloc_free_page(struct list_head *item, struct binder_alloc *alloc; uintptr_t page_addr; size_t index; + struct vm_area_struct *vma; alloc = page->alloc; if (!mutex_trylock(&alloc->mutex)) @@ -923,16 +924,22 @@ enum lru_status binder_alloc_free_page(struct list_head *item, index = page - alloc->pages; page_addr = (uintptr_t)alloc->buffer + index * PAGE_SIZE; - if (alloc->vma) { + vma = alloc->vma; + if (vma) { mm = get_task_mm(alloc->tsk); if (!mm) goto err_get_task_mm_failed; if (!down_write_trylock(&mm->mmap_sem)) goto err_down_write_mmap_sem_failed; + } + + list_lru_isolate(lru, item); + spin_unlock(lock); + if (vma) { trace_binder_unmap_user_start(alloc, index); - zap_page_range(alloc->vma, + zap_page_range(vma, page_addr + alloc->user_buffer_offset, PAGE_SIZE); @@ -950,13 +957,12 @@ enum lru_status binder_alloc_free_page(struct list_head *item, trace_binder_unmap_kernel_end(alloc, index); - list_lru_isolate(lru, item); - + spin_lock(lock); mutex_unlock(&alloc->mutex); - return LRU_REMOVED; + return LRU_REMOVED_RETRY; err_down_write_mmap_sem_failed: - mmput(mm); + mmput_async(mm); err_get_task_mm_failed: err_page_already_freed: mutex_unlock(&alloc->mutex); diff --git a/drivers/ata/ahci.c b/drivers/ata/ahci.c index cb9b0e9090e3..9f78bb03bb76 100644 --- a/drivers/ata/ahci.c +++ b/drivers/ata/ahci.c @@ -621,8 +621,11 @@ static void ahci_pci_save_initial_config(struct pci_dev *pdev, static int ahci_pci_reset_controller(struct ata_host *host) { struct pci_dev *pdev = to_pci_dev(host->dev); + int rc; - ahci_reset_controller(host); + rc = ahci_reset_controller(host); + if (rc) + return rc; if (pdev->vendor == PCI_VENDOR_ID_INTEL) { struct ahci_host_priv *hpriv = host->private_data; diff --git a/drivers/ata/ata_piix.c b/drivers/ata/ata_piix.c index 8401c3b5be92..b702c20fbc2b 100644 --- a/drivers/ata/ata_piix.c +++ b/drivers/ata/ata_piix.c @@ -492,6 +492,7 @@ static const struct ich_laptop ich_laptop[] = { { 0x27DF, 0x152D, 0x0778 }, /* ICH7 on unknown Intel */ { 0x24CA, 0x1025, 0x0061 }, /* ICH4 on ACER Aspire 2023WLMi */ { 0x24CA, 0x1025, 0x003d }, /* ICH4 on ACER TM290 */ + { 0x24CA, 0x10CF, 0x11AB }, /* ICH4M on Fujitsu-Siemens Lifebook S6120 */ { 0x266F, 0x1025, 0x0066 }, /* ICH6 on ACER Aspire 1694WLMi */ { 0x2653, 0x1043, 0x82D8 }, /* ICH6M on Asus Eee 701 */ { 0x27df, 0x104d, 0x900e }, /* ICH7 on Sony TZ-90 */ diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c index 1945a8ea2099..ee4c1ec9dca0 100644 --- a/drivers/ata/libata-core.c +++ b/drivers/ata/libata-core.c @@ -3234,19 +3234,19 @@ static const struct ata_timing ata_timing[] = { }; #define ENOUGH(v, unit) (((v)-1)/(unit)+1) -#define EZ(v, unit) ((v)?ENOUGH(v, unit):0) +#define EZ(v, unit) ((v)?ENOUGH(((v) * 1000), unit):0) static void ata_timing_quantize(const struct ata_timing *t, struct ata_timing *q, int T, int UT) { - q->setup = EZ(t->setup * 1000, T); - q->act8b = EZ(t->act8b * 1000, T); - q->rec8b = EZ(t->rec8b * 1000, T); - q->cyc8b = EZ(t->cyc8b * 1000, T); - q->active = EZ(t->active * 1000, T); - q->recover = EZ(t->recover * 1000, T); - q->dmack_hold = EZ(t->dmack_hold * 1000, T); - q->cycle = EZ(t->cycle * 1000, T); - q->udma = EZ(t->udma * 1000, UT); + q->setup = EZ(t->setup, T); + q->act8b = EZ(t->act8b, T); + q->rec8b = EZ(t->rec8b, T); + q->cyc8b = EZ(t->cyc8b, T); + q->active = EZ(t->active, T); + q->recover = EZ(t->recover, T); + q->dmack_hold = EZ(t->dmack_hold, T); + q->cycle = EZ(t->cycle, T); + q->udma = EZ(t->udma, UT); } void ata_timing_merge(const struct ata_timing *a, const struct ata_timing *b, diff --git a/drivers/auxdisplay/charlcd.c b/drivers/auxdisplay/charlcd.c index cfeb049a01ef..642afd88870b 100644 --- a/drivers/auxdisplay/charlcd.c +++ b/drivers/auxdisplay/charlcd.c @@ -647,18 +647,25 @@ static ssize_t charlcd_write(struct file *file, const char __user *buf, static int charlcd_open(struct inode *inode, struct file *file) { struct charlcd_priv *priv = to_priv(the_charlcd); + int ret; + ret = -EBUSY; if (!atomic_dec_and_test(&charlcd_available)) - return -EBUSY; /* open only once at a time */ + goto fail; /* open only once at a time */ + ret = -EPERM; if (file->f_mode & FMODE_READ) /* device is write-only */ - return -EPERM; + goto fail; if (priv->must_clear) { charlcd_clear_display(&priv->lcd); priv->must_clear = false; } return nonseekable_open(inode, file); + + fail: + atomic_inc(&charlcd_available); + return ret; } static int charlcd_release(struct inode *inode, struct file *file) diff --git a/drivers/auxdisplay/panel.c b/drivers/auxdisplay/panel.c index df126dcdaf18..6911acd896d9 100644 --- a/drivers/auxdisplay/panel.c +++ b/drivers/auxdisplay/panel.c @@ -1105,14 +1105,21 @@ static ssize_t keypad_read(struct file *file, static int keypad_open(struct inode *inode, struct file *file) { + int ret; + + ret = -EBUSY; if (!atomic_dec_and_test(&keypad_available)) - return -EBUSY; /* open only once at a time */ + goto fail; /* open only once at a time */ + ret = -EPERM; if (file->f_mode & FMODE_WRITE) /* device is read-only */ - return -EPERM; + goto fail; keypad_buflen = 0; /* flush the buffer on opening */ return 0; + fail: + atomic_inc(&keypad_available); + return ret; } static int keypad_release(struct inode *inode, struct file *file) diff --git a/drivers/base/arch_topology.c b/drivers/base/arch_topology.c index 41be9ff7d70a..6df7d6676a48 100644 --- a/drivers/base/arch_topology.c +++ b/drivers/base/arch_topology.c @@ -166,11 +166,11 @@ bool __init topology_parse_cpu_capacity(struct device_node *cpu_node, int cpu) } #ifdef CONFIG_CPU_FREQ -static cpumask_var_t cpus_to_visit; -static void parsing_done_workfn(struct work_struct *work); -static DECLARE_WORK(parsing_done_work, parsing_done_workfn); +static cpumask_var_t cpus_to_visit __initdata; +static void __init parsing_done_workfn(struct work_struct *work); +static __initdata DECLARE_WORK(parsing_done_work, parsing_done_workfn); -static int +static int __init init_cpu_capacity_callback(struct notifier_block *nb, unsigned long val, void *data) @@ -206,7 +206,7 @@ init_cpu_capacity_callback(struct notifier_block *nb, return 0; } -static struct notifier_block init_cpu_capacity_notifier = { +static struct notifier_block init_cpu_capacity_notifier __initdata = { .notifier_call = init_cpu_capacity_callback, }; @@ -232,7 +232,7 @@ static int __init register_cpufreq_notifier(void) } core_initcall(register_cpufreq_notifier); -static void parsing_done_workfn(struct work_struct *work) +static void __init parsing_done_workfn(struct work_struct *work) { cpufreq_unregister_notifier(&init_cpu_capacity_notifier, CPUFREQ_POLICY_NOTIFIER); diff --git a/drivers/base/platform.c b/drivers/base/platform.c index d1bd99271066..9045c5f3734e 100644 --- a/drivers/base/platform.c +++ b/drivers/base/platform.c @@ -868,7 +868,8 @@ static ssize_t driver_override_store(struct device *dev, struct platform_device *pdev = to_platform_device(dev); char *driver_override, *old, *cp; - if (count > PATH_MAX) + /* We need to keep extra room for a newline */ + if (count >= (PAGE_SIZE - 1)) return -EINVAL; driver_override = kstrndup(buf, count, GFP_KERNEL); diff --git a/drivers/base/power/opp/core.c b/drivers/base/power/opp/core.c index a8cc14fd8ae4..a6de32530693 100644 --- a/drivers/base/power/opp/core.c +++ b/drivers/base/power/opp/core.c @@ -1581,6 +1581,9 @@ static int _opp_set_availability(struct device *dev, unsigned long freq, opp->available = availability_req; + dev_pm_opp_get(opp); + mutex_unlock(&opp_table->lock); + /* Notify the change of the OPP availability */ if (availability_req) blocking_notifier_call_chain(&opp_table->head, OPP_EVENT_ENABLE, @@ -1589,8 +1592,12 @@ static int _opp_set_availability(struct device *dev, unsigned long freq, blocking_notifier_call_chain(&opp_table->head, OPP_EVENT_DISABLE, opp); + dev_pm_opp_put(opp); + goto put_table; + unlock: mutex_unlock(&opp_table->lock); +put_table: dev_pm_opp_put_opp_table(opp_table); return r; } diff --git a/drivers/block/Kconfig b/drivers/block/Kconfig index 4a438b8abe27..2dfe99b328f8 100644 --- a/drivers/block/Kconfig +++ b/drivers/block/Kconfig @@ -17,7 +17,7 @@ if BLK_DEV config BLK_DEV_NULL_BLK tristate "Null test block driver" - depends on CONFIGFS_FS + select CONFIGFS_FS config BLK_DEV_FD tristate "Normal floppy disk support" diff --git a/drivers/block/brd.c b/drivers/block/brd.c index bbd0d186cfc0..2d7178f7754e 100644 --- a/drivers/block/brd.c +++ b/drivers/block/brd.c @@ -342,7 +342,7 @@ static long __brd_direct_access(struct brd_device *brd, pgoff_t pgoff, if (!brd) return -ENODEV; - page = brd_insert_page(brd, PFN_PHYS(pgoff) / 512); + page = brd_insert_page(brd, (sector_t)pgoff << PAGE_SECTORS_SHIFT); if (!page) return -ENOSPC; *kaddr = page_address(page); diff --git a/drivers/block/loop.h b/drivers/block/loop.h index f68c1d50802f..1f3956702993 100644 --- a/drivers/block/loop.h +++ b/drivers/block/loop.h @@ -67,10 +67,8 @@ struct loop_device { struct loop_cmd { struct kthread_work work; struct request *rq; - union { - bool use_aio; /* use AIO interface to handle I/O */ - atomic_t ref; /* only for aio */ - }; + bool use_aio; /* use AIO interface to handle I/O */ + atomic_t ref; /* only for aio */ long ret; struct kiocb iocb; struct bio_vec *bvec; diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c index 2aa87cbdede0..883dfebd3014 100644 --- a/drivers/block/nbd.c +++ b/drivers/block/nbd.c @@ -820,9 +820,13 @@ static blk_status_t nbd_queue_rq(struct blk_mq_hw_ctx *hctx, * appropriate. */ ret = nbd_handle_cmd(cmd, hctx->queue_num); + if (ret < 0) + ret = BLK_STS_IOERR; + else if (!ret) + ret = BLK_STS_OK; complete(&cmd->send_complete); - return ret < 0 ? BLK_STS_IOERR : BLK_STS_OK; + return ret; } static int nbd_add_socket(struct nbd_device *nbd, unsigned long arg, @@ -1194,6 +1198,12 @@ static int nbd_ioctl(struct block_device *bdev, fmode_t mode, if (!capable(CAP_SYS_ADMIN)) return -EPERM; + /* The block layer will pass back some non-nbd ioctls in case we have + * special handling for them, but we don't so just return an error. + */ + if (_IOC_TYPE(cmd) != 0xab) + return -EINVAL; + mutex_lock(&nbd->config_lock); /* Don't allow ioctl operations on a nbd device that was created with diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c index 2981c27d3aae..f149d3e61234 100644 --- a/drivers/block/zram/zram_drv.c +++ b/drivers/block/zram/zram_drv.c @@ -766,27 +766,6 @@ static void zram_slot_unlock(struct zram *zram, u32 index) bit_spin_unlock(ZRAM_ACCESS, &zram->table[index].value); } -static bool zram_same_page_read(struct zram *zram, u32 index, - struct page *page, - unsigned int offset, unsigned int len) -{ - zram_slot_lock(zram, index); - if (unlikely(!zram_get_handle(zram, index) || - zram_test_flag(zram, index, ZRAM_SAME))) { - void *mem; - - zram_slot_unlock(zram, index); - mem = kmap_atomic(page); - zram_fill_page(mem + offset, len, - zram_get_element(zram, index)); - kunmap_atomic(mem); - return true; - } - zram_slot_unlock(zram, index); - - return false; -} - static void zram_meta_free(struct zram *zram, u64 disksize) { size_t num_pages = disksize >> PAGE_SHIFT; @@ -884,11 +863,20 @@ static int __zram_bvec_read(struct zram *zram, struct page *page, u32 index, zram_slot_unlock(zram, index); } - if (zram_same_page_read(zram, index, page, 0, PAGE_SIZE)) - return 0; - zram_slot_lock(zram, index); handle = zram_get_handle(zram, index); + if (!handle || zram_test_flag(zram, index, ZRAM_SAME)) { + unsigned long value; + void *mem; + + value = handle ? zram_get_element(zram, index) : 0; + mem = kmap_atomic(page); + zram_fill_page(mem, PAGE_SIZE, value); + kunmap_atomic(mem); + zram_slot_unlock(zram, index); + return 0; + } + size = zram_get_obj_size(zram, index); src = zs_map_object(zram->mem_pool, handle, ZS_MM_RO); diff --git a/drivers/clk/clk-bulk.c b/drivers/clk/clk-bulk.c index c834f5abfc49..4c10456f8a32 100644 --- a/drivers/clk/clk-bulk.c +++ b/drivers/clk/clk-bulk.c @@ -105,6 +105,7 @@ err: return ret; } +EXPORT_SYMBOL_GPL(clk_bulk_prepare); #endif /* CONFIG_HAVE_CLK_PREPARE */ diff --git a/drivers/clk/rockchip/clk-rk3128.c b/drivers/clk/rockchip/clk-rk3128.c index 62d7854e4b87..5970a50671b9 100644 --- a/drivers/clk/rockchip/clk-rk3128.c +++ b/drivers/clk/rockchip/clk-rk3128.c @@ -315,13 +315,13 @@ static struct rockchip_clk_branch common_clk_branches[] __initdata = { RK2928_CLKGATE_CON(10), 8, GFLAGS), GATE(SCLK_PVTM_CORE, "clk_pvtm_core", "xin24m", 0, - RK2928_CLKGATE_CON(10), 8, GFLAGS), + RK2928_CLKGATE_CON(10), 0, GFLAGS), GATE(SCLK_PVTM_GPU, "clk_pvtm_gpu", "xin24m", 0, - RK2928_CLKGATE_CON(10), 8, GFLAGS), + RK2928_CLKGATE_CON(10), 1, GFLAGS), GATE(SCLK_PVTM_FUNC, "clk_pvtm_func", "xin24m", 0, - RK2928_CLKGATE_CON(10), 8, GFLAGS), + RK2928_CLKGATE_CON(10), 2, GFLAGS), GATE(SCLK_MIPI_24M, "clk_mipi_24m", "xin24m", CLK_IGNORE_UNUSED, - RK2928_CLKGATE_CON(10), 8, GFLAGS), + RK2928_CLKGATE_CON(2), 15, GFLAGS), COMPOSITE(SCLK_SDMMC, "sclk_sdmmc0", mux_mmc_src_p, 0, RK2928_CLKSEL_CON(11), 6, 2, MFLAGS, 0, 6, DFLAGS, @@ -541,7 +541,7 @@ static struct rockchip_clk_branch common_clk_branches[] __initdata = { GATE(0, "pclk_grf", "pclk_cpu", CLK_IGNORE_UNUSED, RK2928_CLKGATE_CON(5), 4, GFLAGS), GATE(0, "pclk_mipiphy", "pclk_cpu", CLK_IGNORE_UNUSED, RK2928_CLKGATE_CON(5), 0, GFLAGS), - GATE(0, "pclk_pmu", "pclk_pmu_pre", CLK_IGNORE_UNUSED, RK2928_CLKGATE_CON(9), 2, GFLAGS), + GATE(0, "pclk_pmu", "pclk_pmu_pre", 0, RK2928_CLKGATE_CON(9), 2, GFLAGS), GATE(0, "pclk_pmu_niu", "pclk_pmu_pre", CLK_IGNORE_UNUSED, RK2928_CLKGATE_CON(9), 3, GFLAGS), /* PD_MMC */ @@ -577,6 +577,8 @@ static const char *const rk3128_critical_clocks[] __initconst = { "aclk_peri", "hclk_peri", "pclk_peri", + "pclk_pmu", + "sclk_timer5", }; static struct rockchip_clk_provider *__init rk3128_common_clk_init(struct device_node *np) diff --git a/drivers/clk/samsung/clk-exynos4.c b/drivers/clk/samsung/clk-exynos4.c index e40b77583c47..d8d3cb67b402 100644 --- a/drivers/clk/samsung/clk-exynos4.c +++ b/drivers/clk/samsung/clk-exynos4.c @@ -294,6 +294,18 @@ static const struct samsung_clk_reg_dump src_mask_suspend_e4210[] = { #define PLL_ENABLED (1 << 31) #define PLL_LOCKED (1 << 29) +static void exynos4_clk_enable_pll(u32 reg) +{ + u32 pll_con = readl(reg_base + reg); + pll_con |= PLL_ENABLED; + writel(pll_con, reg_base + reg); + + while (!(pll_con & PLL_LOCKED)) { + cpu_relax(); + pll_con = readl(reg_base + reg); + } +} + static void exynos4_clk_wait_for_pll(u32 reg) { u32 pll_con; @@ -315,6 +327,9 @@ static int exynos4_clk_suspend(void) samsung_clk_save(reg_base, exynos4_save_pll, ARRAY_SIZE(exynos4_clk_pll_regs)); + exynos4_clk_enable_pll(EPLL_CON0); + exynos4_clk_enable_pll(VPLL_CON0); + if (exynos4_soc == EXYNOS4210) { samsung_clk_save(reg_base, exynos4_save_soc, ARRAY_SIZE(exynos4210_clk_save)); diff --git a/drivers/clocksource/numachip.c b/drivers/clocksource/numachip.c index 6a20dc8b253f..9a7d7f0f23fe 100644 --- a/drivers/clocksource/numachip.c +++ b/drivers/clocksource/numachip.c @@ -43,7 +43,7 @@ static int numachip2_set_next_event(unsigned long delta, struct clock_event_devi return 0; } -static struct clock_event_device numachip2_clockevent = { +static const struct clock_event_device numachip2_clockevent __initconst = { .name = "numachip2", .rating = 400, .set_next_event = numachip2_set_next_event, diff --git a/drivers/cpufreq/cpufreq-dt-platdev.c b/drivers/cpufreq/cpufreq-dt-platdev.c index 430edadca527..a753c50e9e41 100644 --- a/drivers/cpufreq/cpufreq-dt-platdev.c +++ b/drivers/cpufreq/cpufreq-dt-platdev.c @@ -118,6 +118,10 @@ static const struct of_device_id blacklist[] __initconst = { { .compatible = "sigma,tango4", }, + { .compatible = "ti,am33xx", }, + { .compatible = "ti,am43", }, + { .compatible = "ti,dra7", }, + { } }; diff --git a/drivers/fpga/altera-cvp.c b/drivers/fpga/altera-cvp.c index 08629ee69d11..00e73d28077c 100644 --- a/drivers/fpga/altera-cvp.c +++ b/drivers/fpga/altera-cvp.c @@ -361,12 +361,12 @@ static const struct fpga_manager_ops altera_cvp_ops = { .write_complete = altera_cvp_write_complete, }; -static ssize_t show_chkcfg(struct device_driver *dev, char *buf) +static ssize_t chkcfg_show(struct device_driver *dev, char *buf) { return snprintf(buf, 3, "%d\n", altera_cvp_chkcfg); } -static ssize_t store_chkcfg(struct device_driver *drv, const char *buf, +static ssize_t chkcfg_store(struct device_driver *drv, const char *buf, size_t count) { int ret; @@ -378,7 +378,7 @@ static ssize_t store_chkcfg(struct device_driver *drv, const char *buf, return count; } -static DRIVER_ATTR(chkcfg, 0600, show_chkcfg, store_chkcfg); +static DRIVER_ATTR_RW(chkcfg); static int altera_cvp_probe(struct pci_dev *pdev, const struct pci_device_id *dev_id); diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v6_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v6_0.c index d228f5a99044..dbbe986f90f2 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v6_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v6_0.c @@ -636,7 +636,194 @@ static void gfx_v6_0_tiling_mode_table_init(struct amdgpu_device *adev) NUM_BANKS(ADDR_SURF_2_BANK); for (reg_offset = 0; reg_offset < num_tile_mode_states; reg_offset++) WREG32(mmGB_TILE_MODE0 + reg_offset, tilemode[reg_offset]); - } else if (adev->asic_type == CHIP_OLAND || adev->asic_type == CHIP_HAINAN) { + } else if (adev->asic_type == CHIP_OLAND) { + tilemode[0] = MICRO_TILE_MODE(ADDR_SURF_DEPTH_MICRO_TILING) | + ARRAY_MODE(ARRAY_2D_TILED_THIN1) | + PIPE_CONFIG(ADDR_SURF_P4_8x16) | + TILE_SPLIT(ADDR_SURF_TILE_SPLIT_64B) | + NUM_BANKS(ADDR_SURF_16_BANK) | + BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) | + BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_4) | + MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_4); + tilemode[1] = MICRO_TILE_MODE(ADDR_SURF_DEPTH_MICRO_TILING) | + ARRAY_MODE(ARRAY_2D_TILED_THIN1) | + PIPE_CONFIG(ADDR_SURF_P4_8x16) | + TILE_SPLIT(ADDR_SURF_TILE_SPLIT_128B) | + NUM_BANKS(ADDR_SURF_16_BANK) | + BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) | + BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_4) | + MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_4); + tilemode[2] = MICRO_TILE_MODE(ADDR_SURF_DEPTH_MICRO_TILING) | + ARRAY_MODE(ARRAY_2D_TILED_THIN1) | + PIPE_CONFIG(ADDR_SURF_P4_8x16) | + TILE_SPLIT(ADDR_SURF_TILE_SPLIT_256B) | + NUM_BANKS(ADDR_SURF_16_BANK) | + BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) | + BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_4) | + MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_4); + tilemode[3] = MICRO_TILE_MODE(ADDR_SURF_DEPTH_MICRO_TILING) | + ARRAY_MODE(ARRAY_2D_TILED_THIN1) | + PIPE_CONFIG(ADDR_SURF_P4_8x16) | + TILE_SPLIT(ADDR_SURF_TILE_SPLIT_128B) | + NUM_BANKS(ADDR_SURF_16_BANK) | + BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) | + BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_4) | + MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_4); + tilemode[4] = MICRO_TILE_MODE(ADDR_SURF_DEPTH_MICRO_TILING) | + ARRAY_MODE(ARRAY_1D_TILED_THIN1) | + PIPE_CONFIG(ADDR_SURF_P4_8x16) | + TILE_SPLIT(ADDR_SURF_TILE_SPLIT_64B) | + NUM_BANKS(ADDR_SURF_16_BANK) | + BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) | + BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_2) | + MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2); + tilemode[5] = MICRO_TILE_MODE(ADDR_SURF_DEPTH_MICRO_TILING) | + ARRAY_MODE(ARRAY_2D_TILED_THIN1) | + PIPE_CONFIG(ADDR_SURF_P4_8x16) | + TILE_SPLIT(split_equal_to_row_size) | + NUM_BANKS(ADDR_SURF_16_BANK) | + BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) | + BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_2) | + MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2); + tilemode[6] = MICRO_TILE_MODE(ADDR_SURF_DEPTH_MICRO_TILING) | + ARRAY_MODE(ARRAY_2D_TILED_THIN1) | + PIPE_CONFIG(ADDR_SURF_P4_8x16) | + TILE_SPLIT(split_equal_to_row_size) | + NUM_BANKS(ADDR_SURF_16_BANK) | + BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) | + BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_1) | + MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2); + tilemode[7] = MICRO_TILE_MODE(ADDR_SURF_DEPTH_MICRO_TILING) | + ARRAY_MODE(ARRAY_2D_TILED_THIN1) | + PIPE_CONFIG(ADDR_SURF_P4_8x16) | + TILE_SPLIT(split_equal_to_row_size) | + NUM_BANKS(ADDR_SURF_16_BANK) | + BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) | + BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_4) | + MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_4); + tilemode[8] = MICRO_TILE_MODE(ADDR_SURF_DISPLAY_MICRO_TILING) | + ARRAY_MODE(ARRAY_LINEAR_ALIGNED) | + PIPE_CONFIG(ADDR_SURF_P4_8x16) | + TILE_SPLIT(ADDR_SURF_TILE_SPLIT_64B) | + NUM_BANKS(ADDR_SURF_16_BANK) | + BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) | + BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_2) | + MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2); + tilemode[9] = MICRO_TILE_MODE(ADDR_SURF_DISPLAY_MICRO_TILING) | + ARRAY_MODE(ARRAY_1D_TILED_THIN1) | + PIPE_CONFIG(ADDR_SURF_P4_8x16) | + TILE_SPLIT(ADDR_SURF_TILE_SPLIT_64B) | + NUM_BANKS(ADDR_SURF_16_BANK) | + BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) | + BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_2) | + MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2); + tilemode[10] = MICRO_TILE_MODE(ADDR_SURF_DISPLAY_MICRO_TILING) | + ARRAY_MODE(ARRAY_2D_TILED_THIN1) | + PIPE_CONFIG(ADDR_SURF_P4_8x16) | + TILE_SPLIT(ADDR_SURF_TILE_SPLIT_256B) | + NUM_BANKS(ADDR_SURF_16_BANK) | + BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) | + BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_4) | + MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_4); + tilemode[11] = MICRO_TILE_MODE(ADDR_SURF_DISPLAY_MICRO_TILING) | + ARRAY_MODE(ARRAY_2D_TILED_THIN1) | + PIPE_CONFIG(ADDR_SURF_P4_8x16) | + TILE_SPLIT(ADDR_SURF_TILE_SPLIT_256B) | + NUM_BANKS(ADDR_SURF_16_BANK) | + BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) | + BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_2) | + MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2); + tilemode[12] = MICRO_TILE_MODE(ADDR_SURF_DISPLAY_MICRO_TILING) | + ARRAY_MODE(ARRAY_2D_TILED_THIN1) | + PIPE_CONFIG(ADDR_SURF_P4_8x16) | + TILE_SPLIT(ADDR_SURF_TILE_SPLIT_512B) | + NUM_BANKS(ADDR_SURF_16_BANK) | + BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) | + BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_1) | + MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2); + tilemode[13] = MICRO_TILE_MODE(ADDR_SURF_THIN_MICRO_TILING) | + ARRAY_MODE(ARRAY_1D_TILED_THIN1) | + PIPE_CONFIG(ADDR_SURF_P4_8x16) | + TILE_SPLIT(ADDR_SURF_TILE_SPLIT_64B) | + NUM_BANKS(ADDR_SURF_16_BANK) | + BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) | + BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_2) | + MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2); + tilemode[14] = MICRO_TILE_MODE(ADDR_SURF_THIN_MICRO_TILING) | + ARRAY_MODE(ARRAY_2D_TILED_THIN1) | + PIPE_CONFIG(ADDR_SURF_P4_8x16) | + TILE_SPLIT(ADDR_SURF_TILE_SPLIT_256B) | + NUM_BANKS(ADDR_SURF_16_BANK) | + BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) | + BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_4) | + MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2); + tilemode[15] = MICRO_TILE_MODE(ADDR_SURF_THIN_MICRO_TILING) | + ARRAY_MODE(ARRAY_2D_TILED_THIN1) | + PIPE_CONFIG(ADDR_SURF_P4_8x16) | + TILE_SPLIT(ADDR_SURF_TILE_SPLIT_256B) | + NUM_BANKS(ADDR_SURF_16_BANK) | + BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) | + BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_2) | + MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2); + tilemode[16] = MICRO_TILE_MODE(ADDR_SURF_THIN_MICRO_TILING) | + ARRAY_MODE(ARRAY_2D_TILED_THIN1) | + PIPE_CONFIG(ADDR_SURF_P4_8x16) | + TILE_SPLIT(ADDR_SURF_TILE_SPLIT_512B) | + NUM_BANKS(ADDR_SURF_16_BANK) | + BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) | + BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_1) | + MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2); + tilemode[17] = MICRO_TILE_MODE(ADDR_SURF_THIN_MICRO_TILING) | + ARRAY_MODE(ARRAY_2D_TILED_THIN1) | + PIPE_CONFIG(ADDR_SURF_P4_8x16) | + TILE_SPLIT(split_equal_to_row_size) | + NUM_BANKS(ADDR_SURF_16_BANK) | + BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) | + BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_1) | + MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2); + tilemode[21] = MICRO_TILE_MODE(ADDR_SURF_THIN_MICRO_TILING) | + ARRAY_MODE(ARRAY_2D_TILED_THIN1) | + PIPE_CONFIG(ADDR_SURF_P8_32x32_8x16) | + TILE_SPLIT(ADDR_SURF_TILE_SPLIT_256B) | + NUM_BANKS(ADDR_SURF_16_BANK) | + BANK_WIDTH(ADDR_SURF_BANK_WIDTH_2) | + BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_4) | + MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2); + tilemode[22] = MICRO_TILE_MODE(ADDR_SURF_THIN_MICRO_TILING) | + ARRAY_MODE(ARRAY_2D_TILED_THIN1) | + PIPE_CONFIG(ADDR_SURF_P8_32x32_8x16) | + TILE_SPLIT(ADDR_SURF_TILE_SPLIT_256B) | + NUM_BANKS(ADDR_SURF_16_BANK) | + BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) | + BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_4) | + MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_4); + tilemode[23] = MICRO_TILE_MODE(ADDR_SURF_THIN_MICRO_TILING) | + ARRAY_MODE(ARRAY_2D_TILED_THIN1) | + PIPE_CONFIG(ADDR_SURF_P8_32x32_8x16) | + TILE_SPLIT(ADDR_SURF_TILE_SPLIT_256B) | + NUM_BANKS(ADDR_SURF_16_BANK) | + BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) | + BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_2) | + MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2); + tilemode[24] = MICRO_TILE_MODE(ADDR_SURF_THIN_MICRO_TILING) | + ARRAY_MODE(ARRAY_2D_TILED_THIN1) | + PIPE_CONFIG(ADDR_SURF_P8_32x32_8x16) | + TILE_SPLIT(ADDR_SURF_TILE_SPLIT_512B) | + NUM_BANKS(ADDR_SURF_16_BANK) | + BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) | + BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_1) | + MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2); + tilemode[25] = MICRO_TILE_MODE(ADDR_SURF_THIN_MICRO_TILING) | + ARRAY_MODE(ARRAY_2D_TILED_THIN1) | + PIPE_CONFIG(ADDR_SURF_P8_32x32_8x16) | + TILE_SPLIT(ADDR_SURF_TILE_SPLIT_1KB) | + NUM_BANKS(ADDR_SURF_8_BANK) | + BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) | + BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_1) | + MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_1); + for (reg_offset = 0; reg_offset < num_tile_mode_states; reg_offset++) + WREG32(mmGB_TILE_MODE0 + reg_offset, tilemode[reg_offset]); + } else if (adev->asic_type == CHIP_HAINAN) { tilemode[0] = MICRO_TILE_MODE(ADDR_SURF_DEPTH_MICRO_TILING) | ARRAY_MODE(ARRAY_2D_TILED_THIN1) | PIPE_CONFIG(ADDR_SURF_P2) | diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c index e4a8c2e52cb2..660b3fbade41 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c @@ -892,6 +892,8 @@ static int kfd_ioctl_get_tile_config(struct file *filep, int err = 0; dev = kfd_device_by_id(args->gpu_id); + if (!dev) + return -EINVAL; dev->kfd2kgd->get_tile_config(dev->kgd, &config); diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_events.c b/drivers/gpu/drm/amd/amdkfd/kfd_events.c index 5979158c3f7b..944abfad39c1 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_events.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_events.c @@ -292,7 +292,10 @@ static int create_signal_event(struct file *devkfd, struct kfd_event *ev) { if (p->signal_event_count == KFD_SIGNAL_EVENT_LIMIT) { - pr_warn("Signal event wasn't created because limit was reached\n"); + if (!p->signal_event_limit_reached) { + pr_warn("Signal event wasn't created because limit was reached\n"); + p->signal_event_limit_reached = true; + } return -ENOMEM; } diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_kernel_queue.c b/drivers/gpu/drm/amd/amdkfd/kfd_kernel_queue.c index 0649dd43e780..ed71ad40e8f7 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_kernel_queue.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_kernel_queue.c @@ -184,7 +184,7 @@ static void uninitialize(struct kernel_queue *kq) if (kq->queue->properties.type == KFD_QUEUE_TYPE_HIQ) kq->mqd->destroy_mqd(kq->mqd, kq->queue->mqd, - false, + KFD_PREEMPT_TYPE_WAVEFRONT_RESET, QUEUE_PREEMPT_DEFAULT_TIMEOUT_MS, kq->queue->pipe, kq->queue->queue); @@ -210,6 +210,11 @@ static int acquire_packet_buffer(struct kernel_queue *kq, uint32_t wptr, rptr; unsigned int *queue_address; + /* When rptr == wptr, the buffer is empty. + * When rptr == wptr + 1, the buffer is full. + * It is always rptr that advances to the position of wptr, rather than + * the opposite. So we can only use up to queue_size_dwords - 1 dwords. + */ rptr = *kq->rptr_kernel; wptr = *kq->wptr_kernel; queue_address = (unsigned int *)kq->pq_kernel_addr; @@ -219,11 +224,10 @@ static int acquire_packet_buffer(struct kernel_queue *kq, pr_debug("wptr: %d\n", wptr); pr_debug("queue_address 0x%p\n", queue_address); - available_size = (rptr - 1 - wptr + queue_size_dwords) % + available_size = (rptr + queue_size_dwords - 1 - wptr) % queue_size_dwords; - if (packet_size_in_dwords >= queue_size_dwords || - packet_size_in_dwords >= available_size) { + if (packet_size_in_dwords > available_size) { /* * make sure calling functions know * acquire_packet_buffer() failed @@ -233,6 +237,14 @@ static int acquire_packet_buffer(struct kernel_queue *kq, } if (wptr + packet_size_in_dwords >= queue_size_dwords) { + /* make sure after rolling back to position 0, there is + * still enough space. + */ + if (packet_size_in_dwords >= rptr) { + *buffer_ptr = NULL; + return -ENOMEM; + } + /* fill nops, roll back and start at position 0 */ while (wptr > 0) { queue_address[wptr] = kq->nop_packet; wptr = (wptr + 1) % queue_size_dwords; diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h index b397ec726400..b87e96cee5fa 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h +++ b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h @@ -521,6 +521,7 @@ struct kfd_process { struct list_head signal_event_pages; u32 next_nonsignal_event_id; size_t signal_event_count; + bool signal_event_limit_reached; }; /** diff --git a/drivers/gpu/drm/etnaviv/etnaviv_gem.c b/drivers/gpu/drm/etnaviv/etnaviv_gem.c index 5a634594a6ce..57881167ccd2 100644 --- a/drivers/gpu/drm/etnaviv/etnaviv_gem.c +++ b/drivers/gpu/drm/etnaviv/etnaviv_gem.c @@ -551,12 +551,15 @@ static const struct etnaviv_gem_ops etnaviv_gem_shmem_ops = { void etnaviv_gem_free_object(struct drm_gem_object *obj) { struct etnaviv_gem_object *etnaviv_obj = to_etnaviv_bo(obj); + struct etnaviv_drm_private *priv = obj->dev->dev_private; struct etnaviv_vram_mapping *mapping, *tmp; /* object should not be active */ WARN_ON(is_active(etnaviv_obj)); + mutex_lock(&priv->gem_lock); list_del(&etnaviv_obj->gem_node); + mutex_unlock(&priv->gem_lock); list_for_each_entry_safe(mapping, tmp, &etnaviv_obj->vram_list, obj_node) { diff --git a/drivers/gpu/drm/etnaviv/etnaviv_gem_submit.c b/drivers/gpu/drm/etnaviv/etnaviv_gem_submit.c index 026ef4e02f85..46dfe0737f43 100644 --- a/drivers/gpu/drm/etnaviv/etnaviv_gem_submit.c +++ b/drivers/gpu/drm/etnaviv/etnaviv_gem_submit.c @@ -445,8 +445,10 @@ int etnaviv_ioctl_gem_submit(struct drm_device *dev, void *data, cmdbuf->user_size = ALIGN(args->stream_size, 8); ret = etnaviv_gpu_submit(gpu, submit, cmdbuf); - if (ret == 0) - cmdbuf = NULL; + if (ret) + goto out; + + cmdbuf = NULL; if (args->flags & ETNA_SUBMIT_FENCE_FD_OUT) { /* diff --git a/drivers/gpu/drm/i915/intel_audio.c b/drivers/gpu/drm/i915/intel_audio.c index d805b6e6fe71..27743be5b768 100644 --- a/drivers/gpu/drm/i915/intel_audio.c +++ b/drivers/gpu/drm/i915/intel_audio.c @@ -606,11 +606,6 @@ void intel_audio_codec_enable(struct intel_encoder *intel_encoder, connector->encoder->base.id, connector->encoder->name); - /* ELD Conn_Type */ - connector->eld[5] &= ~(3 << 2); - if (intel_crtc_has_dp_encoder(crtc_state)) - connector->eld[5] |= (1 << 2); - connector->eld[6] = drm_av_sync_delay(connector, adjusted_mode) / 2; if (dev_priv->display.audio_codec_enable) diff --git a/drivers/gpu/drm/i915/intel_bios.c b/drivers/gpu/drm/i915/intel_bios.c index 183e87e8ea31..00c6aee0a9a1 100644 --- a/drivers/gpu/drm/i915/intel_bios.c +++ b/drivers/gpu/drm/i915/intel_bios.c @@ -1163,6 +1163,13 @@ static void parse_ddi_port(struct drm_i915_private *dev_priv, enum port port, is_hdmi = is_dvi && (child->common.device_type & DEVICE_TYPE_NOT_HDMI_OUTPUT) == 0; is_edp = is_dp && (child->common.device_type & DEVICE_TYPE_INTERNAL_CONNECTOR); + if (port == PORT_A && is_dvi) { + DRM_DEBUG_KMS("VBT claims port A supports DVI%s, ignoring\n", + is_hdmi ? "/HDMI" : ""); + is_dvi = false; + is_hdmi = false; + } + info->supports_dvi = is_dvi; info->supports_hdmi = is_hdmi; info->supports_dp = is_dp; diff --git a/drivers/gpu/drm/i915/intel_csr.c b/drivers/gpu/drm/i915/intel_csr.c index 965988f79a55..92c1f8e166dc 100644 --- a/drivers/gpu/drm/i915/intel_csr.c +++ b/drivers/gpu/drm/i915/intel_csr.c @@ -216,7 +216,7 @@ static void gen9_set_dc_state_debugmask(struct drm_i915_private *dev_priv) mask = DC_STATE_DEBUG_MASK_MEMORY_UP; - if (IS_BROXTON(dev_priv)) + if (IS_GEN9_LP(dev_priv)) mask |= DC_STATE_DEBUG_MASK_CORES; /* The below bit doesn't need to be cleared ever afterwards */ diff --git a/drivers/gpu/drm/i915/intel_ddi.c b/drivers/gpu/drm/i915/intel_ddi.c index 4b4fd1f8110b..476681d5940c 100644 --- a/drivers/gpu/drm/i915/intel_ddi.c +++ b/drivers/gpu/drm/i915/intel_ddi.c @@ -1655,7 +1655,8 @@ bool intel_ddi_get_hw_state(struct intel_encoder *encoder, out: if (ret && IS_GEN9_LP(dev_priv)) { tmp = I915_READ(BXT_PHY_CTL(port)); - if ((tmp & (BXT_PHY_LANE_POWERDOWN_ACK | + if ((tmp & (BXT_PHY_CMNLANE_POWERDOWN_ACK | + BXT_PHY_LANE_POWERDOWN_ACK | BXT_PHY_LANE_ENABLED)) != BXT_PHY_LANE_ENABLED) DRM_ERROR("Port %c enabled but PHY powered down? " "(PHY_CTL %08x)\n", port_name(port), tmp); diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c index 00cd17c76fdc..64f7b51ed97c 100644 --- a/drivers/gpu/drm/i915/intel_display.c +++ b/drivers/gpu/drm/i915/intel_display.c @@ -12359,7 +12359,6 @@ static void intel_atomic_commit_tail(struct drm_atomic_state *state) struct drm_crtc_state *old_crtc_state, *new_crtc_state; struct drm_crtc *crtc; struct intel_crtc_state *intel_cstate; - bool hw_check = intel_state->modeset; u64 put_domains[I915_MAX_PIPES] = {}; unsigned crtc_vblank_mask = 0; int i; @@ -12376,7 +12375,6 @@ static void intel_atomic_commit_tail(struct drm_atomic_state *state) if (needs_modeset(new_crtc_state) || to_intel_crtc_state(new_crtc_state)->update_pipe) { - hw_check = true; put_domains[to_intel_crtc(crtc)->pipe] = modeset_get_crtc_power_domains(crtc, diff --git a/drivers/gpu/drm/i915/intel_dpio_phy.c b/drivers/gpu/drm/i915/intel_dpio_phy.c index 09b670929786..de38d014ed39 100644 --- a/drivers/gpu/drm/i915/intel_dpio_phy.c +++ b/drivers/gpu/drm/i915/intel_dpio_phy.c @@ -208,12 +208,6 @@ static const struct bxt_ddi_phy_info glk_ddi_phy_info[] = { }, }; -static u32 bxt_phy_port_mask(const struct bxt_ddi_phy_info *phy_info) -{ - return (phy_info->dual_channel * BIT(phy_info->channel[DPIO_CH1].port)) | - BIT(phy_info->channel[DPIO_CH0].port); -} - static const struct bxt_ddi_phy_info * bxt_get_phy_list(struct drm_i915_private *dev_priv, int *count) { @@ -313,7 +307,6 @@ bool bxt_ddi_phy_is_enabled(struct drm_i915_private *dev_priv, enum dpio_phy phy) { const struct bxt_ddi_phy_info *phy_info; - enum port port; phy_info = bxt_get_phy_info(dev_priv, phy); @@ -335,19 +328,6 @@ bool bxt_ddi_phy_is_enabled(struct drm_i915_private *dev_priv, return false; } - for_each_port_masked(port, bxt_phy_port_mask(phy_info)) { - u32 tmp = I915_READ(BXT_PHY_CTL(port)); - - if (tmp & BXT_PHY_CMNLANE_POWERDOWN_ACK) { - DRM_DEBUG_DRIVER("DDI PHY %d powered, but common lane " - "for port %c powered down " - "(PHY_CTL %08x)\n", - phy, port_name(port), tmp); - - return false; - } - } - return true; } diff --git a/drivers/gpu/drm/i915/intel_modes.c b/drivers/gpu/drm/i915/intel_modes.c index 951e834dd274..28a778b785ac 100644 --- a/drivers/gpu/drm/i915/intel_modes.c +++ b/drivers/gpu/drm/i915/intel_modes.c @@ -30,6 +30,21 @@ #include "intel_drv.h" #include "i915_drv.h" +static void intel_connector_update_eld_conn_type(struct drm_connector *connector) +{ + u8 conn_type; + + if (connector->connector_type == DRM_MODE_CONNECTOR_DisplayPort || + connector->connector_type == DRM_MODE_CONNECTOR_eDP) { + conn_type = DRM_ELD_CONN_TYPE_DP; + } else { + conn_type = DRM_ELD_CONN_TYPE_HDMI; + } + + connector->eld[DRM_ELD_SAD_COUNT_CONN_TYPE] &= ~DRM_ELD_CONN_TYPE_MASK; + connector->eld[DRM_ELD_SAD_COUNT_CONN_TYPE] |= conn_type; +} + /** * intel_connector_update_modes - update connector from edid * @connector: DRM connector device to use @@ -44,6 +59,8 @@ int intel_connector_update_modes(struct drm_connector *connector, ret = drm_add_edid_modes(connector, edid); drm_edid_to_eld(connector, edid); + intel_connector_update_eld_conn_type(connector); + return ret; } diff --git a/drivers/gpu/drm/i915/intel_runtime_pm.c b/drivers/gpu/drm/i915/intel_runtime_pm.c index b66d8e136aa3..b3a087cb0860 100644 --- a/drivers/gpu/drm/i915/intel_runtime_pm.c +++ b/drivers/gpu/drm/i915/intel_runtime_pm.c @@ -2782,6 +2782,9 @@ static void cnl_display_core_init(struct drm_i915_private *dev_priv, bool resume /* 6. Enable DBUF */ gen9_dbuf_enable(dev_priv); + + if (resume && dev_priv->csr.dmc_payload) + intel_csr_load_program(dev_priv); } #undef CNL_PROCMON_IDX diff --git a/drivers/gpu/drm/qxl/qxl_display.c b/drivers/gpu/drm/qxl/qxl_display.c index 14c5613b4388..afbf50d0c08f 100644 --- a/drivers/gpu/drm/qxl/qxl_display.c +++ b/drivers/gpu/drm/qxl/qxl_display.c @@ -509,23 +509,25 @@ static void qxl_primary_atomic_update(struct drm_plane *plane, .y2 = qfb->base.height }; - if (!old_state->fb) { - qxl_io_log(qdev, - "create primary fb: %dx%d,%d,%d\n", - bo->surf.width, bo->surf.height, - bo->surf.stride, bo->surf.format); + if (old_state->fb) { + qfb_old = to_qxl_framebuffer(old_state->fb); + bo_old = gem_to_qxl_bo(qfb_old->obj); + } else { + bo_old = NULL; + } - qxl_io_create_primary(qdev, 0, bo); - bo->is_primary = true; + if (bo == bo_old) return; - } else { - qfb_old = to_qxl_framebuffer(old_state->fb); - bo_old = gem_to_qxl_bo(qfb_old->obj); + if (bo_old && bo_old->is_primary) { + qxl_io_destroy_primary(qdev); bo_old->is_primary = false; } - bo->is_primary = true; + if (!bo->is_primary) { + qxl_io_create_primary(qdev, 0, bo); + bo->is_primary = true; + } qxl_draw_dirty_fb(qdev, qfb, bo, 0, 0, &norect, 1, 1); } @@ -534,13 +536,15 @@ static void qxl_primary_atomic_disable(struct drm_plane *plane, { struct qxl_device *qdev = plane->dev->dev_private; - if (old_state->fb) - { struct qxl_framebuffer *qfb = + if (old_state->fb) { + struct qxl_framebuffer *qfb = to_qxl_framebuffer(old_state->fb); struct qxl_bo *bo = gem_to_qxl_bo(qfb->obj); - qxl_io_destroy_primary(qdev); - bo->is_primary = false; + if (bo->is_primary) { + qxl_io_destroy_primary(qdev); + bo->is_primary = false; + } } } @@ -698,14 +702,15 @@ static void qxl_plane_cleanup_fb(struct drm_plane *plane, struct drm_gem_object *obj; struct qxl_bo *user_bo; - if (!plane->state->fb) { - /* we never executed prepare_fb, so there's nothing to + if (!old_state->fb) { + /* + * we never executed prepare_fb, so there's nothing to * unpin. */ return; } - obj = to_qxl_framebuffer(plane->state->fb)->obj; + obj = to_qxl_framebuffer(old_state->fb)->obj; user_bo = gem_to_qxl_bo(obj); qxl_bo_unpin(user_bo); } diff --git a/drivers/gpu/drm/radeon/radeon_device.c b/drivers/gpu/drm/radeon/radeon_device.c index 997131d58c7f..ffc10cadcf34 100644 --- a/drivers/gpu/drm/radeon/radeon_device.c +++ b/drivers/gpu/drm/radeon/radeon_device.c @@ -1663,7 +1663,7 @@ int radeon_suspend_kms(struct drm_device *dev, bool suspend, radeon_agp_suspend(rdev); pci_save_state(dev->pdev); - if (freeze && rdev->family >= CHIP_CEDAR) { + if (freeze && rdev->family >= CHIP_CEDAR && !(rdev->flags & RADEON_IS_IGP)) { rdev->asic->asic_reset(rdev, true); pci_restore_state(dev->pdev); } else if (suspend) { diff --git a/drivers/gpu/drm/sun4i/Kconfig b/drivers/gpu/drm/sun4i/Kconfig index 06f05302ee75..882d85db9053 100644 --- a/drivers/gpu/drm/sun4i/Kconfig +++ b/drivers/gpu/drm/sun4i/Kconfig @@ -26,7 +26,7 @@ config DRM_SUN4I_HDMI_CEC bool "Allwinner A10 HDMI CEC Support" depends on DRM_SUN4I_HDMI select CEC_CORE - depends on CEC_PIN + select CEC_PIN help Choose this option if you have an Allwinner SoC with an HDMI controller and want to use CEC. diff --git a/drivers/gpu/drm/sun4i/sun4i_hdmi.h b/drivers/gpu/drm/sun4i/sun4i_hdmi.h index 1457750988da..a1f8cba251a2 100644 --- a/drivers/gpu/drm/sun4i/sun4i_hdmi.h +++ b/drivers/gpu/drm/sun4i/sun4i_hdmi.h @@ -15,7 +15,7 @@ #include <drm/drm_connector.h> #include <drm/drm_encoder.h> -#include <media/cec.h> +#include <media/cec-pin.h> #define SUN4I_HDMI_CTRL_REG 0x004 #define SUN4I_HDMI_CTRL_ENABLE BIT(31) diff --git a/drivers/gpu/drm/sun4i/sun4i_hdmi_enc.c b/drivers/gpu/drm/sun4i/sun4i_hdmi_enc.c index 9ea6cd5a1370..3cf1a6932fac 100644 --- a/drivers/gpu/drm/sun4i/sun4i_hdmi_enc.c +++ b/drivers/gpu/drm/sun4i/sun4i_hdmi_enc.c @@ -302,26 +302,29 @@ static int sun4i_hdmi_bind(struct device *dev, struct device *master, hdmi->mod_clk = devm_clk_get(dev, "mod"); if (IS_ERR(hdmi->mod_clk)) { dev_err(dev, "Couldn't get the HDMI mod clock\n"); - return PTR_ERR(hdmi->mod_clk); + ret = PTR_ERR(hdmi->mod_clk); + goto err_disable_bus_clk; } clk_prepare_enable(hdmi->mod_clk); hdmi->pll0_clk = devm_clk_get(dev, "pll-0"); if (IS_ERR(hdmi->pll0_clk)) { dev_err(dev, "Couldn't get the HDMI PLL 0 clock\n"); - return PTR_ERR(hdmi->pll0_clk); + ret = PTR_ERR(hdmi->pll0_clk); + goto err_disable_mod_clk; } hdmi->pll1_clk = devm_clk_get(dev, "pll-1"); if (IS_ERR(hdmi->pll1_clk)) { dev_err(dev, "Couldn't get the HDMI PLL 1 clock\n"); - return PTR_ERR(hdmi->pll1_clk); + ret = PTR_ERR(hdmi->pll1_clk); + goto err_disable_mod_clk; } ret = sun4i_tmds_create(hdmi); if (ret) { dev_err(dev, "Couldn't create the TMDS clock\n"); - return ret; + goto err_disable_mod_clk; } writel(SUN4I_HDMI_CTRL_ENABLE, hdmi->base + SUN4I_HDMI_CTRL_REG); @@ -362,7 +365,7 @@ static int sun4i_hdmi_bind(struct device *dev, struct device *master, ret = sun4i_hdmi_i2c_create(dev, hdmi); if (ret) { dev_err(dev, "Couldn't create the HDMI I2C adapter\n"); - return ret; + goto err_disable_mod_clk; } drm_encoder_helper_add(&hdmi->encoder, @@ -422,6 +425,10 @@ err_cleanup_connector: drm_encoder_cleanup(&hdmi->encoder); err_del_i2c_adapter: i2c_del_adapter(hdmi->i2c); +err_disable_mod_clk: + clk_disable_unprepare(hdmi->mod_clk); +err_disable_bus_clk: + clk_disable_unprepare(hdmi->bus_clk); return ret; } @@ -434,6 +441,8 @@ static void sun4i_hdmi_unbind(struct device *dev, struct device *master, drm_connector_cleanup(&hdmi->connector); drm_encoder_cleanup(&hdmi->encoder); i2c_del_adapter(hdmi->i2c); + clk_disable_unprepare(hdmi->mod_clk); + clk_disable_unprepare(hdmi->bus_clk); } static const struct component_ops sun4i_hdmi_ops = { diff --git a/drivers/gpu/drm/tegra/trace.h b/drivers/gpu/drm/tegra/trace.h index e9b7cdad5c4c..5a1ab4046e92 100644 --- a/drivers/gpu/drm/tegra/trace.h +++ b/drivers/gpu/drm/tegra/trace.h @@ -63,6 +63,6 @@ DEFINE_EVENT(register_access, sor_readl, /* This part must be outside protection */ #undef TRACE_INCLUDE_PATH -#define TRACE_INCLUDE_PATH . +#define TRACE_INCLUDE_PATH ../../drivers/gpu/drm/tegra #define TRACE_INCLUDE_FILE trace #include <trace/define_trace.h> diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h index b397a14ab970..a98919199858 100644 --- a/drivers/hid/hid-ids.h +++ b/drivers/hid/hid-ids.h @@ -533,6 +533,7 @@ #define USB_VENDOR_ID_IDEACOM 0x1cb6 #define USB_DEVICE_ID_IDEACOM_IDC6650 0x6650 #define USB_DEVICE_ID_IDEACOM_IDC6651 0x6651 +#define USB_DEVICE_ID_IDEACOM_IDC6680 0x6680 #define USB_VENDOR_ID_ILITEK 0x222a #define USB_DEVICE_ID_ILITEK_MULTITOUCH 0x0001 @@ -660,6 +661,7 @@ #define USB_DEVICE_ID_LENOVO_CBTKBD 0x6048 #define USB_DEVICE_ID_LENOVO_TPPRODOCK 0x6067 #define USB_DEVICE_ID_LENOVO_X1_COVER 0x6085 +#define USB_DEVICE_ID_LENOVO_X1_TAB 0x60a3 #define USB_VENDOR_ID_LG 0x1fd2 #define USB_DEVICE_ID_LG_MULTITOUCH 0x0064 diff --git a/drivers/hid/hid-multitouch.c b/drivers/hid/hid-multitouch.c index 440b999304a5..9e8c4d2ba11d 100644 --- a/drivers/hid/hid-multitouch.c +++ b/drivers/hid/hid-multitouch.c @@ -930,6 +930,7 @@ static int mt_input_mapping(struct hid_device *hdev, struct hid_input *hi, field->application != HID_DG_PEN && field->application != HID_DG_TOUCHPAD && field->application != HID_GD_KEYBOARD && + field->application != HID_GD_SYSTEM_CONTROL && field->application != HID_CP_CONSUMER_CONTROL && field->application != HID_GD_WIRELESS_RADIO_CTLS && !(field->application == HID_VD_ASUS_CUSTOM_MEDIA_KEYS && @@ -1419,6 +1420,12 @@ static const struct hid_device_id mt_devices[] = { USB_VENDOR_ID_ALPS_JP, HID_DEVICE_ID_ALPS_U1_DUAL_3BTN_PTP) }, + /* Lenovo X1 TAB Gen 2 */ + { .driver_data = MT_CLS_WIN_8_DUAL, + HID_DEVICE(BUS_USB, HID_GROUP_MULTITOUCH_WIN_8, + USB_VENDOR_ID_LENOVO, + USB_DEVICE_ID_LENOVO_X1_TAB) }, + /* Anton devices */ { .driver_data = MT_CLS_EXPORT_ALL_INPUTS, MT_USB_DEVICE(USB_VENDOR_ID_ANTON, diff --git a/drivers/hid/hid-rmi.c b/drivers/hid/hid-rmi.c index 5b40c2614599..ef241d66562e 100644 --- a/drivers/hid/hid-rmi.c +++ b/drivers/hid/hid-rmi.c @@ -436,17 +436,24 @@ static int rmi_post_resume(struct hid_device *hdev) if (!(data->device_flags & RMI_DEVICE)) return 0; - ret = rmi_reset_attn_mode(hdev); + /* Make sure the HID device is ready to receive events */ + ret = hid_hw_open(hdev); if (ret) return ret; + ret = rmi_reset_attn_mode(hdev); + if (ret) + goto out; + ret = rmi_driver_resume(rmi_dev, false); if (ret) { hid_warn(hdev, "Failed to resume device: %d\n", ret); - return ret; + goto out; } - return 0; +out: + hid_hw_close(hdev); + return ret; } #endif /* CONFIG_PM */ diff --git a/drivers/hid/hidraw.c b/drivers/hid/hidraw.c index ec530454e6f6..5fbe0f81ab2e 100644 --- a/drivers/hid/hidraw.c +++ b/drivers/hid/hidraw.c @@ -337,8 +337,8 @@ static void drop_ref(struct hidraw *hidraw, int exists_bit) kfree(hidraw); } else { /* close device for last reader */ - hid_hw_power(hidraw->hid, PM_HINT_NORMAL); hid_hw_close(hidraw->hid); + hid_hw_power(hidraw->hid, PM_HINT_NORMAL); } } } diff --git a/drivers/hid/i2c-hid/i2c-hid.c b/drivers/hid/i2c-hid/i2c-hid.c index 77396145d2d0..9145c2129a96 100644 --- a/drivers/hid/i2c-hid/i2c-hid.c +++ b/drivers/hid/i2c-hid/i2c-hid.c @@ -543,7 +543,8 @@ static int i2c_hid_alloc_buffers(struct i2c_hid *ihid, size_t report_size) { /* the worst case is computed from the set_report command with a * reportID > 15 and the maximum report length */ - int args_len = sizeof(__u8) + /* optional ReportID byte */ + int args_len = sizeof(__u8) + /* ReportID */ + sizeof(__u8) + /* optional ReportID byte */ sizeof(__u16) + /* data register */ sizeof(__u16) + /* size of the report */ report_size; /* report */ diff --git a/drivers/hid/usbhid/hid-quirks.c b/drivers/hid/usbhid/hid-quirks.c index a83fa76655b9..f489a5cfcb48 100644 --- a/drivers/hid/usbhid/hid-quirks.c +++ b/drivers/hid/usbhid/hid-quirks.c @@ -99,6 +99,7 @@ static const struct hid_blacklist { { USB_VENDOR_ID_HP, USB_PRODUCT_ID_HP_LOGITECH_OEM_USB_OPTICAL_MOUSE_0A4A, HID_QUIRK_ALWAYS_POLL }, { USB_VENDOR_ID_HP, USB_PRODUCT_ID_HP_LOGITECH_OEM_USB_OPTICAL_MOUSE_0B4A, HID_QUIRK_ALWAYS_POLL }, { USB_VENDOR_ID_HP, USB_PRODUCT_ID_HP_PIXART_OEM_USB_OPTICAL_MOUSE, HID_QUIRK_ALWAYS_POLL }, + { USB_VENDOR_ID_IDEACOM, USB_DEVICE_ID_IDEACOM_IDC6680, HID_QUIRK_MULTI_INPUT }, { USB_VENDOR_ID_LOGITECH, USB_DEVICE_ID_LOGITECH_C007, HID_QUIRK_ALWAYS_POLL }, { USB_VENDOR_ID_LOGITECH, USB_DEVICE_ID_LOGITECH_C077, HID_QUIRK_ALWAYS_POLL }, { USB_VENDOR_ID_LOGITECH, USB_DEVICE_ID_LOGITECH_KEYBOARD_G710_PLUS, HID_QUIRK_NOGET }, diff --git a/drivers/hid/wacom_sys.c b/drivers/hid/wacom_sys.c index e82a696a1d07..906e654fb0ba 100644 --- a/drivers/hid/wacom_sys.c +++ b/drivers/hid/wacom_sys.c @@ -668,8 +668,10 @@ static struct wacom_hdev_data *wacom_get_hdev_data(struct hid_device *hdev) /* Try to find an already-probed interface from the same device */ list_for_each_entry(data, &wacom_udev_list, list) { - if (compare_device_paths(hdev, data->dev, '/')) + if (compare_device_paths(hdev, data->dev, '/')) { + kref_get(&data->kref); return data; + } } /* Fallback to finding devices that appear to be "siblings" */ @@ -766,6 +768,9 @@ static int wacom_led_control(struct wacom *wacom) if (!wacom->led.groups) return -ENOTSUPP; + if (wacom->wacom_wac.features.type == REMOTE) + return -ENOTSUPP; + if (wacom->wacom_wac.pid) { /* wireless connected */ report_id = WAC_CMD_WL_LED_CONTROL; buf_size = 13; diff --git a/drivers/hid/wacom_wac.c b/drivers/hid/wacom_wac.c index bb17d7bbefd3..aa692e28b2cd 100644 --- a/drivers/hid/wacom_wac.c +++ b/drivers/hid/wacom_wac.c @@ -567,8 +567,8 @@ static int wacom_intuos_pad(struct wacom_wac *wacom) keys = data[9] & 0x07; } } else { - buttons = ((data[6] & 0x10) << 10) | - ((data[5] & 0x10) << 9) | + buttons = ((data[6] & 0x10) << 5) | + ((data[5] & 0x10) << 4) | ((data[6] & 0x0F) << 4) | (data[5] & 0x0F); } @@ -1227,11 +1227,17 @@ static void wacom_intuos_pro2_bt_pen(struct wacom_wac *wacom) continue; if (range) { + /* Fix rotation alignment: userspace expects zero at left */ + int16_t rotation = (int16_t)get_unaligned_le16(&frame[9]); + rotation += 1800/4; + if (rotation > 899) + rotation -= 1800; + input_report_abs(pen_input, ABS_X, get_unaligned_le16(&frame[1])); input_report_abs(pen_input, ABS_Y, get_unaligned_le16(&frame[3])); - input_report_abs(pen_input, ABS_TILT_X, frame[7]); - input_report_abs(pen_input, ABS_TILT_Y, frame[8]); - input_report_abs(pen_input, ABS_Z, get_unaligned_le16(&frame[9])); + input_report_abs(pen_input, ABS_TILT_X, (char)frame[7]); + input_report_abs(pen_input, ABS_TILT_Y, (char)frame[8]); + input_report_abs(pen_input, ABS_Z, rotation); input_report_abs(pen_input, ABS_WHEEL, get_unaligned_le16(&frame[11])); } input_report_abs(pen_input, ABS_PRESSURE, get_unaligned_le16(&frame[5])); @@ -1319,12 +1325,19 @@ static void wacom_intuos_pro2_bt_pad(struct wacom_wac *wacom) unsigned char *data = wacom->data; int buttons = (data[282] << 1) | ((data[281] >> 6) & 0x01); - int ring = data[285]; - int prox = buttons | (ring & 0x80); + int ring = data[285] & 0x7F; + bool ringstatus = data[285] & 0x80; + bool prox = buttons || ringstatus; + + /* Fix touchring data: userspace expects 0 at left and increasing clockwise */ + ring = 71 - ring; + ring += 3*72/16; + if (ring > 71) + ring -= 72; wacom_report_numbered_buttons(pad_input, 9, buttons); - input_report_abs(pad_input, ABS_WHEEL, (ring & 0x80) ? (ring & 0x7f) : 0); + input_report_abs(pad_input, ABS_WHEEL, ringstatus ? ring : 0); input_report_key(pad_input, wacom->tool[1], prox ? 1 : 0); input_report_abs(pad_input, ABS_MISC, prox ? PAD_DEVICE_ID : 0); @@ -1616,6 +1629,20 @@ static int wacom_tpc_irq(struct wacom_wac *wacom, size_t len) return 0; } +static int wacom_offset_rotation(struct input_dev *input, struct hid_usage *usage, + int value, int num, int denom) +{ + struct input_absinfo *abs = &input->absinfo[usage->code]; + int range = (abs->maximum - abs->minimum + 1); + + value += num*range/denom; + if (value > abs->maximum) + value -= range; + else if (value < abs->minimum) + value += range; + return value; +} + int wacom_equivalent_usage(int usage) { if ((usage & HID_USAGE_PAGE) == WACOM_HID_UP_WACOMDIGITIZER) { @@ -1898,6 +1925,7 @@ static void wacom_wac_pad_event(struct hid_device *hdev, struct hid_field *field unsigned equivalent_usage = wacom_equivalent_usage(usage->hid); int i; bool is_touch_on = value; + bool do_report = false; /* * Avoid reporting this event and setting inrange_state if this usage @@ -1912,6 +1940,29 @@ static void wacom_wac_pad_event(struct hid_device *hdev, struct hid_field *field } switch (equivalent_usage) { + case WACOM_HID_WD_TOUCHRING: + /* + * Userspace expects touchrings to increase in value with + * clockwise gestures and have their zero point at the + * tablet's left. HID events "should" be clockwise- + * increasing and zero at top, though the MobileStudio + * Pro and 2nd-gen Intuos Pro don't do this... + */ + if (hdev->vendor == 0x56a && + (hdev->product == 0x34d || hdev->product == 0x34e || /* MobileStudio Pro */ + hdev->product == 0x357 || hdev->product == 0x358)) { /* Intuos Pro 2 */ + value = (field->logical_maximum - value); + + if (hdev->product == 0x357 || hdev->product == 0x358) + value = wacom_offset_rotation(input, usage, value, 3, 16); + else if (hdev->product == 0x34d || hdev->product == 0x34e) + value = wacom_offset_rotation(input, usage, value, 1, 2); + } + else { + value = wacom_offset_rotation(input, usage, value, 1, 4); + } + do_report = true; + break; case WACOM_HID_WD_TOUCHRINGSTATUS: if (!value) input_event(input, usage->type, usage->code, 0); @@ -1945,10 +1996,14 @@ static void wacom_wac_pad_event(struct hid_device *hdev, struct hid_field *field value, i); /* fall through*/ default: + do_report = true; + break; + } + + if (do_report) { input_event(input, usage->type, usage->code, value); if (value) wacom_wac->hid_data.pad_input_event_flag = true; - break; } } @@ -2086,22 +2141,34 @@ static void wacom_wac_pen_event(struct hid_device *hdev, struct hid_field *field wacom_wac->hid_data.tipswitch |= value; return; case HID_DG_TOOLSERIALNUMBER: - wacom_wac->serial[0] = (wacom_wac->serial[0] & ~0xFFFFFFFFULL); - wacom_wac->serial[0] |= (__u32)value; + if (value) { + wacom_wac->serial[0] = (wacom_wac->serial[0] & ~0xFFFFFFFFULL); + wacom_wac->serial[0] |= (__u32)value; + } return; + case HID_DG_TWIST: + /* + * Userspace expects pen twist to have its zero point when + * the buttons/finger is on the tablet's left. HID values + * are zero when buttons are toward the top. + */ + value = wacom_offset_rotation(input, usage, value, 1, 4); + break; case WACOM_HID_WD_SENSE: wacom_wac->hid_data.sense_state = value; return; case WACOM_HID_WD_SERIALHI: - wacom_wac->serial[0] = (wacom_wac->serial[0] & 0xFFFFFFFF); - wacom_wac->serial[0] |= ((__u64)value) << 32; - /* - * Non-USI EMR devices may contain additional tool type - * information here. See WACOM_HID_WD_TOOLTYPE case for - * more details. - */ - if (value >> 20 == 1) { - wacom_wac->id[0] |= value & 0xFFFFF; + if (value) { + wacom_wac->serial[0] = (wacom_wac->serial[0] & 0xFFFFFFFF); + wacom_wac->serial[0] |= ((__u64)value) << 32; + /* + * Non-USI EMR devices may contain additional tool type + * information here. See WACOM_HID_WD_TOOLTYPE case for + * more details. + */ + if (value >> 20 == 1) { + wacom_wac->id[0] |= value & 0xFFFFF; + } } return; case WACOM_HID_WD_TOOLTYPE: @@ -2205,7 +2272,7 @@ static void wacom_wac_pen_report(struct hid_device *hdev, input_report_key(input, wacom_wac->tool[0], prox); if (wacom_wac->serial[0]) { input_event(input, EV_MSC, MSC_SERIAL, wacom_wac->serial[0]); - input_report_abs(input, ABS_MISC, id); + input_report_abs(input, ABS_MISC, prox ? id : 0); } wacom_wac->hid_data.tipswitch = false; @@ -2216,6 +2283,7 @@ static void wacom_wac_pen_report(struct hid_device *hdev, if (!prox) { wacom_wac->tool[0] = 0; wacom_wac->id[0] = 0; + wacom_wac->serial[0] = 0; } } diff --git a/drivers/hv/channel_mgmt.c b/drivers/hv/channel_mgmt.c index 060df71c2e8b..bcbb031f7263 100644 --- a/drivers/hv/channel_mgmt.c +++ b/drivers/hv/channel_mgmt.c @@ -936,14 +936,10 @@ static void vmbus_onoffer_rescind(struct vmbus_channel_message_header *hdr) void vmbus_hvsock_device_unregister(struct vmbus_channel *channel) { - mutex_lock(&vmbus_connection.channel_mutex); - BUG_ON(!is_hvsock_channel(channel)); channel->rescind = true; vmbus_device_unregister(channel->device_obj); - - mutex_unlock(&vmbus_connection.channel_mutex); } EXPORT_SYMBOL_GPL(vmbus_hvsock_device_unregister); diff --git a/drivers/hv/hv_fcopy.c b/drivers/hv/hv_fcopy.c index daa75bd41f86..2364281d8593 100644 --- a/drivers/hv/hv_fcopy.c +++ b/drivers/hv/hv_fcopy.c @@ -170,6 +170,10 @@ static void fcopy_send_data(struct work_struct *dummy) out_src = smsg_out; break; + case WRITE_TO_FILE: + out_src = fcopy_transaction.fcopy_msg; + out_len = sizeof(struct hv_do_fcopy); + break; default: out_src = fcopy_transaction.fcopy_msg; out_len = fcopy_transaction.recv_len; diff --git a/drivers/hwmon/xgene-hwmon.c b/drivers/hwmon/xgene-hwmon.c index 9c0dbb8191ad..e1be61095532 100644 --- a/drivers/hwmon/xgene-hwmon.c +++ b/drivers/hwmon/xgene-hwmon.c @@ -630,7 +630,7 @@ static int xgene_hwmon_probe(struct platform_device *pdev) sizeof(struct slimpro_resp_msg) * ASYNC_MSG_FIFO_SIZE, GFP_KERNEL); if (rc) - goto out_mbox_free; + return -ENOMEM; INIT_WORK(&ctx->workq, xgene_hwmon_evt_work); @@ -646,7 +646,8 @@ static int xgene_hwmon_probe(struct platform_device *pdev) if (IS_ERR(ctx->mbox_chan)) { dev_err(&pdev->dev, "SLIMpro mailbox channel request failed\n"); - return -ENODEV; + rc = -ENODEV; + goto out_mbox_free; } } else { struct acpi_pcct_hw_reduced *cppc_ss; @@ -654,7 +655,8 @@ static int xgene_hwmon_probe(struct platform_device *pdev) if (device_property_read_u32(&pdev->dev, "pcc-channel", &ctx->mbox_idx)) { dev_err(&pdev->dev, "no pcc-channel property\n"); - return -ENODEV; + rc = -ENODEV; + goto out_mbox_free; } cl->rx_callback = xgene_hwmon_pcc_rx_cb; @@ -662,7 +664,8 @@ static int xgene_hwmon_probe(struct platform_device *pdev) if (IS_ERR(ctx->mbox_chan)) { dev_err(&pdev->dev, "PPC channel request failed\n"); - return -ENODEV; + rc = -ENODEV; + goto out_mbox_free; } /* @@ -675,13 +678,13 @@ static int xgene_hwmon_probe(struct platform_device *pdev) if (!cppc_ss) { dev_err(&pdev->dev, "PPC subspace not found\n"); rc = -ENODEV; - goto out_mbox_free; + goto out; } if (!ctx->mbox_chan->mbox->txdone_irq) { dev_err(&pdev->dev, "PCC IRQ not supported\n"); rc = -ENODEV; - goto out_mbox_free; + goto out; } /* @@ -696,14 +699,14 @@ static int xgene_hwmon_probe(struct platform_device *pdev) } else { dev_err(&pdev->dev, "Failed to get PCC comm region\n"); rc = -ENODEV; - goto out_mbox_free; + goto out; } if (!ctx->pcc_comm_addr) { dev_err(&pdev->dev, "Failed to ioremap PCC comm region\n"); rc = -ENOMEM; - goto out_mbox_free; + goto out; } /* diff --git a/drivers/hwtracing/intel_th/pci.c b/drivers/hwtracing/intel_th/pci.c index bc9cebc30526..c2a2ce8ee541 100644 --- a/drivers/hwtracing/intel_th/pci.c +++ b/drivers/hwtracing/intel_th/pci.c @@ -144,6 +144,11 @@ static const struct pci_device_id intel_th_pci_id_table[] = { .driver_data = (kernel_ulong_t)0, }, { + /* Lewisburg PCH */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xa1a6), + .driver_data = (kernel_ulong_t)0, + }, + { /* Gemini Lake */ PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x318e), .driver_data = (kernel_ulong_t)&intel_th_2x, @@ -158,6 +163,11 @@ static const struct pci_device_id intel_th_pci_id_table[] = { PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x9da6), .driver_data = (kernel_ulong_t)&intel_th_2x, }, + { + /* Cedar Fork PCH */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x18e1), + .driver_data = (kernel_ulong_t)&intel_th_2x, + }, { 0 }, }; diff --git a/drivers/hwtracing/stm/core.c b/drivers/hwtracing/stm/core.c index 9414900575d8..f129869e05a9 100644 --- a/drivers/hwtracing/stm/core.c +++ b/drivers/hwtracing/stm/core.c @@ -1119,7 +1119,7 @@ void stm_source_unregister_device(struct stm_source_data *data) stm_source_link_drop(src); - device_destroy(&stm_source_class, src->dev.devt); + device_unregister(&src->dev); } EXPORT_SYMBOL_GPL(stm_source_unregister_device); diff --git a/drivers/i2c/busses/Kconfig b/drivers/i2c/busses/Kconfig index c06dce2c1da7..45a3f3ca29b3 100644 --- a/drivers/i2c/busses/Kconfig +++ b/drivers/i2c/busses/Kconfig @@ -131,6 +131,7 @@ config I2C_I801 Gemini Lake (SOC) Cannon Lake-H (PCH) Cannon Lake-LP (PCH) + Cedar Fork (PCH) This driver can also be built as a module. If so, the module will be called i2c-i801. diff --git a/drivers/i2c/busses/i2c-i801.c b/drivers/i2c/busses/i2c-i801.c index e114e4e00d29..9e12a53ef7b8 100644 --- a/drivers/i2c/busses/i2c-i801.c +++ b/drivers/i2c/busses/i2c-i801.c @@ -68,6 +68,7 @@ * Gemini Lake (SOC) 0x31d4 32 hard yes yes yes * Cannon Lake-H (PCH) 0xa323 32 hard yes yes yes * Cannon Lake-LP (PCH) 0x9da3 32 hard yes yes yes + * Cedar Fork (PCH) 0x18df 32 hard yes yes yes * * Features supported by this driver: * Software PEC no @@ -204,6 +205,7 @@ /* Older devices have their ID defined in <linux/pci_ids.h> */ #define PCI_DEVICE_ID_INTEL_BAYTRAIL_SMBUS 0x0f12 +#define PCI_DEVICE_ID_INTEL_CDF_SMBUS 0x18df #define PCI_DEVICE_ID_INTEL_DNV_SMBUS 0x19df #define PCI_DEVICE_ID_INTEL_COUGARPOINT_SMBUS 0x1c22 #define PCI_DEVICE_ID_INTEL_PATSBURG_SMBUS 0x1d22 @@ -1025,6 +1027,7 @@ static const struct pci_device_id i801_ids[] = { { PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_BRASWELL_SMBUS) }, { PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_SUNRISEPOINT_H_SMBUS) }, { PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_SUNRISEPOINT_LP_SMBUS) }, + { PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_CDF_SMBUS) }, { PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_DNV_SMBUS) }, { PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_BROXTON_SMBUS) }, { PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_LEWISBURG_SMBUS) }, @@ -1513,6 +1516,7 @@ static int i801_probe(struct pci_dev *dev, const struct pci_device_id *id) case PCI_DEVICE_ID_INTEL_CANNONLAKE_LP_SMBUS: case PCI_DEVICE_ID_INTEL_LEWISBURG_SMBUS: case PCI_DEVICE_ID_INTEL_LEWISBURG_SSKU_SMBUS: + case PCI_DEVICE_ID_INTEL_CDF_SMBUS: case PCI_DEVICE_ID_INTEL_DNV_SMBUS: case PCI_DEVICE_ID_INTEL_KABYLAKE_PCH_H_SMBUS: priv->features |= FEATURE_I2C_BLOCK_READ; diff --git a/drivers/i2c/busses/i2c-img-scb.c b/drivers/i2c/busses/i2c-img-scb.c index 84fb35f6837f..eb1d91b986fd 100644 --- a/drivers/i2c/busses/i2c-img-scb.c +++ b/drivers/i2c/busses/i2c-img-scb.c @@ -1459,6 +1459,6 @@ static struct platform_driver img_scb_i2c_driver = { }; module_platform_driver(img_scb_i2c_driver); -MODULE_AUTHOR("James Hogan <james.hogan@imgtec.com>"); +MODULE_AUTHOR("James Hogan <jhogan@kernel.org>"); MODULE_DESCRIPTION("IMG host I2C driver"); MODULE_LICENSE("GPL v2"); diff --git a/drivers/i2c/busses/i2c-sprd.c b/drivers/i2c/busses/i2c-sprd.c index 22e08ae1704f..25fcc3c1e32b 100644 --- a/drivers/i2c/busses/i2c-sprd.c +++ b/drivers/i2c/busses/i2c-sprd.c @@ -627,6 +627,7 @@ static const struct dev_pm_ops sprd_i2c_pm_ops = { static const struct of_device_id sprd_i2c_of_match[] = { { .compatible = "sprd,sc9860-i2c", }, + {}, }; static struct platform_driver sprd_i2c_driver = { diff --git a/drivers/i2c/busses/i2c-stm32f7.c b/drivers/i2c/busses/i2c-stm32f7.c index 47c67b0ca896..d4a6e9c2e9aa 100644 --- a/drivers/i2c/busses/i2c-stm32f7.c +++ b/drivers/i2c/busses/i2c-stm32f7.c @@ -215,7 +215,7 @@ struct stm32f7_i2c_dev { unsigned int msg_num; unsigned int msg_id; struct stm32f7_i2c_msg f7_msg; - struct stm32f7_i2c_setup *setup; + struct stm32f7_i2c_setup setup; struct stm32f7_i2c_timings timing; }; @@ -265,7 +265,7 @@ static struct stm32f7_i2c_spec i2c_specs[] = { }, }; -struct stm32f7_i2c_setup stm32f7_setup = { +static const struct stm32f7_i2c_setup stm32f7_setup = { .rise_time = STM32F7_I2C_RISE_TIME_DEFAULT, .fall_time = STM32F7_I2C_FALL_TIME_DEFAULT, .dnf = STM32F7_I2C_DNF_DEFAULT, @@ -537,7 +537,7 @@ static void stm32f7_i2c_hw_config(struct stm32f7_i2c_dev *i2c_dev) writel_relaxed(timing, i2c_dev->base + STM32F7_I2C_TIMINGR); /* Enable I2C */ - if (i2c_dev->setup->analog_filter) + if (i2c_dev->setup.analog_filter) stm32f7_i2c_clr_bits(i2c_dev->base + STM32F7_I2C_CR1, STM32F7_I2C_CR1_ANFOFF); else @@ -887,22 +887,19 @@ static int stm32f7_i2c_probe(struct platform_device *pdev) } setup = of_device_get_match_data(&pdev->dev); - i2c_dev->setup->rise_time = setup->rise_time; - i2c_dev->setup->fall_time = setup->fall_time; - i2c_dev->setup->dnf = setup->dnf; - i2c_dev->setup->analog_filter = setup->analog_filter; + i2c_dev->setup = *setup; ret = device_property_read_u32(i2c_dev->dev, "i2c-scl-rising-time-ns", &rise_time); if (!ret) - i2c_dev->setup->rise_time = rise_time; + i2c_dev->setup.rise_time = rise_time; ret = device_property_read_u32(i2c_dev->dev, "i2c-scl-falling-time-ns", &fall_time); if (!ret) - i2c_dev->setup->fall_time = fall_time; + i2c_dev->setup.fall_time = fall_time; - ret = stm32f7_i2c_setup_timing(i2c_dev, i2c_dev->setup); + ret = stm32f7_i2c_setup_timing(i2c_dev, &i2c_dev->setup); if (ret) goto clk_free; diff --git a/drivers/ide/ide-probe.c b/drivers/ide/ide-probe.c index 01b2adfd8226..eaf39e5db08b 100644 --- a/drivers/ide/ide-probe.c +++ b/drivers/ide/ide-probe.c @@ -1451,6 +1451,7 @@ int ide_host_register(struct ide_host *host, const struct ide_port_info *d, if (hwif_init(hwif) == 0) { printk(KERN_INFO "%s: failed to initialize IDE " "interface\n", hwif->name); + device_unregister(hwif->portdev); device_unregister(&hwif->gendev); ide_disable_port(hwif); continue; diff --git a/drivers/ide/ide-scan-pci.c b/drivers/ide/ide-scan-pci.c index 86aa88aeb3a6..acf874800ca4 100644 --- a/drivers/ide/ide-scan-pci.c +++ b/drivers/ide/ide-scan-pci.c @@ -56,6 +56,7 @@ static int __init ide_scan_pcidev(struct pci_dev *dev) { struct list_head *l; struct pci_driver *d; + int ret; list_for_each(l, &ide_pci_drivers) { d = list_entry(l, struct pci_driver, node); @@ -63,10 +64,14 @@ static int __init ide_scan_pcidev(struct pci_dev *dev) const struct pci_device_id *id = pci_match_id(d->id_table, dev); - if (id != NULL && d->probe(dev, id) >= 0) { - dev->driver = d; - pci_dev_get(dev); - return 1; + if (id != NULL) { + pci_assign_irq(dev); + ret = d->probe(dev, id); + if (ret >= 0) { + dev->driver = d; + pci_dev_get(dev); + return 1; + } } } } diff --git a/drivers/ide/setup-pci.c b/drivers/ide/setup-pci.c index 112d2fe1bcdb..fdc8e813170c 100644 --- a/drivers/ide/setup-pci.c +++ b/drivers/ide/setup-pci.c @@ -179,6 +179,7 @@ EXPORT_SYMBOL_GPL(ide_setup_pci_noise); /** * ide_pci_enable - do PCI enables * @dev: PCI device + * @bars: PCI BARs mask * @d: IDE port info * * Enable the IDE PCI device. We attempt to enable the device in full @@ -189,9 +190,10 @@ EXPORT_SYMBOL_GPL(ide_setup_pci_noise); * Returns zero on success or an error code */ -static int ide_pci_enable(struct pci_dev *dev, const struct ide_port_info *d) +static int ide_pci_enable(struct pci_dev *dev, int bars, + const struct ide_port_info *d) { - int ret, bars; + int ret; if (pci_enable_device(dev)) { ret = pci_enable_device_io(dev); @@ -216,18 +218,6 @@ static int ide_pci_enable(struct pci_dev *dev, const struct ide_port_info *d) goto out; } - if (d->host_flags & IDE_HFLAG_SINGLE) - bars = (1 << 2) - 1; - else - bars = (1 << 4) - 1; - - if ((d->host_flags & IDE_HFLAG_NO_DMA) == 0) { - if (d->host_flags & IDE_HFLAG_CS5520) - bars |= (1 << 2); - else - bars |= (1 << 4); - } - ret = pci_request_selected_regions(dev, bars, d->name); if (ret < 0) printk(KERN_ERR "%s %s: can't reserve resources\n", @@ -403,6 +393,7 @@ int ide_hwif_setup_dma(ide_hwif_t *hwif, const struct ide_port_info *d) /** * ide_setup_pci_controller - set up IDE PCI * @dev: PCI device + * @bars: PCI BARs mask * @d: IDE port info * @noisy: verbose flag * @@ -411,7 +402,7 @@ int ide_hwif_setup_dma(ide_hwif_t *hwif, const struct ide_port_info *d) * and enables it if need be */ -static int ide_setup_pci_controller(struct pci_dev *dev, +static int ide_setup_pci_controller(struct pci_dev *dev, int bars, const struct ide_port_info *d, int noisy) { int ret; @@ -420,7 +411,7 @@ static int ide_setup_pci_controller(struct pci_dev *dev, if (noisy) ide_setup_pci_noise(dev, d); - ret = ide_pci_enable(dev, d); + ret = ide_pci_enable(dev, bars, d); if (ret < 0) goto out; @@ -428,16 +419,20 @@ static int ide_setup_pci_controller(struct pci_dev *dev, if (ret < 0) { printk(KERN_ERR "%s %s: error accessing PCI regs\n", d->name, pci_name(dev)); - goto out; + goto out_free_bars; } if (!(pcicmd & PCI_COMMAND_IO)) { /* is device disabled? */ ret = ide_pci_configure(dev, d); if (ret < 0) - goto out; + goto out_free_bars; printk(KERN_INFO "%s %s: device enabled (Linux)\n", d->name, pci_name(dev)); } + goto out; + +out_free_bars: + pci_release_selected_regions(dev, bars); out: return ret; } @@ -540,13 +535,28 @@ int ide_pci_init_two(struct pci_dev *dev1, struct pci_dev *dev2, { struct pci_dev *pdev[] = { dev1, dev2 }; struct ide_host *host; - int ret, i, n_ports = dev2 ? 4 : 2; + int ret, i, n_ports = dev2 ? 4 : 2, bars; struct ide_hw hw[4], *hws[] = { NULL, NULL, NULL, NULL }; + if (d->host_flags & IDE_HFLAG_SINGLE) + bars = (1 << 2) - 1; + else + bars = (1 << 4) - 1; + + if ((d->host_flags & IDE_HFLAG_NO_DMA) == 0) { + if (d->host_flags & IDE_HFLAG_CS5520) + bars |= (1 << 2); + else + bars |= (1 << 4); + } + for (i = 0; i < n_ports / 2; i++) { - ret = ide_setup_pci_controller(pdev[i], d, !i); - if (ret < 0) + ret = ide_setup_pci_controller(pdev[i], bars, d, !i); + if (ret < 0) { + if (i == 1) + pci_release_selected_regions(pdev[0], bars); goto out; + } ide_pci_setup_ports(pdev[i], d, &hw[i*2], &hws[i*2]); } @@ -554,7 +564,7 @@ int ide_pci_init_two(struct pci_dev *dev1, struct pci_dev *dev2, host = ide_host_alloc(d, hws, n_ports); if (host == NULL) { ret = -ENOMEM; - goto out; + goto out_free_bars; } host->dev[0] = &dev1->dev; @@ -576,7 +586,7 @@ int ide_pci_init_two(struct pci_dev *dev1, struct pci_dev *dev2, * do_ide_setup_pci_device() on the first device! */ if (ret < 0) - goto out; + goto out_free_bars; /* fixup IRQ */ if (ide_pci_is_in_compatibility_mode(pdev[i])) { @@ -589,6 +599,13 @@ int ide_pci_init_two(struct pci_dev *dev1, struct pci_dev *dev2, ret = ide_host_register(host, d, hws); if (ret) ide_host_free(host); + else + goto out; + +out_free_bars: + i = n_ports / 2; + while (i--) + pci_release_selected_regions(pdev[i], bars); out: return ret; } diff --git a/drivers/iio/adc/ad7793.c b/drivers/iio/adc/ad7793.c index e6706a09e100..47c3d7f32900 100644 --- a/drivers/iio/adc/ad7793.c +++ b/drivers/iio/adc/ad7793.c @@ -257,7 +257,7 @@ static int ad7793_setup(struct iio_dev *indio_dev, unsigned int vref_mv) { struct ad7793_state *st = iio_priv(indio_dev); - int i, ret = -1; + int i, ret; unsigned long long scale_uv; u32 id; @@ -266,7 +266,7 @@ static int ad7793_setup(struct iio_dev *indio_dev, return ret; /* reset the serial interface */ - ret = spi_write(st->sd.spi, (u8 *)&ret, sizeof(ret)); + ret = ad_sd_reset(&st->sd, 32); if (ret < 0) goto out; usleep_range(500, 2000); /* Wait for at least 500us */ diff --git a/drivers/iio/adc/ad_sigma_delta.c b/drivers/iio/adc/ad_sigma_delta.c index d10bd0c97233..22c4c17cd996 100644 --- a/drivers/iio/adc/ad_sigma_delta.c +++ b/drivers/iio/adc/ad_sigma_delta.c @@ -177,6 +177,34 @@ out: } EXPORT_SYMBOL_GPL(ad_sd_read_reg); +/** + * ad_sd_reset() - Reset the serial interface + * + * @sigma_delta: The sigma delta device + * @reset_length: Number of SCLKs with DIN = 1 + * + * Returns 0 on success, an error code otherwise. + **/ +int ad_sd_reset(struct ad_sigma_delta *sigma_delta, + unsigned int reset_length) +{ + uint8_t *buf; + unsigned int size; + int ret; + + size = DIV_ROUND_UP(reset_length, 8); + buf = kcalloc(size, sizeof(*buf), GFP_KERNEL); + if (!buf) + return -ENOMEM; + + memset(buf, 0xff, size); + ret = spi_write(sigma_delta->spi, buf, size); + kfree(buf); + + return ret; +} +EXPORT_SYMBOL_GPL(ad_sd_reset); + static int ad_sd_calibrate(struct ad_sigma_delta *sigma_delta, unsigned int mode, unsigned int channel) { diff --git a/drivers/iio/adc/mcp320x.c b/drivers/iio/adc/mcp320x.c index 634717ae12f3..071dd23a33d9 100644 --- a/drivers/iio/adc/mcp320x.c +++ b/drivers/iio/adc/mcp320x.c @@ -17,6 +17,8 @@ * MCP3204 * MCP3208 * ------------ + * 13 bit converter + * MCP3301 * * Datasheet can be found here: * http://ww1.microchip.com/downloads/en/DeviceDoc/21293C.pdf mcp3001 @@ -96,7 +98,7 @@ static int mcp320x_channel_to_tx_data(int device_index, } static int mcp320x_adc_conversion(struct mcp320x *adc, u8 channel, - bool differential, int device_index) + bool differential, int device_index, int *val) { int ret; @@ -117,19 +119,25 @@ static int mcp320x_adc_conversion(struct mcp320x *adc, u8 channel, switch (device_index) { case mcp3001: - return (adc->rx_buf[0] << 5 | adc->rx_buf[1] >> 3); + *val = (adc->rx_buf[0] << 5 | adc->rx_buf[1] >> 3); + return 0; case mcp3002: case mcp3004: case mcp3008: - return (adc->rx_buf[0] << 2 | adc->rx_buf[1] >> 6); + *val = (adc->rx_buf[0] << 2 | adc->rx_buf[1] >> 6); + return 0; case mcp3201: - return (adc->rx_buf[0] << 7 | adc->rx_buf[1] >> 1); + *val = (adc->rx_buf[0] << 7 | adc->rx_buf[1] >> 1); + return 0; case mcp3202: case mcp3204: case mcp3208: - return (adc->rx_buf[0] << 4 | adc->rx_buf[1] >> 4); + *val = (adc->rx_buf[0] << 4 | adc->rx_buf[1] >> 4); + return 0; case mcp3301: - return sign_extend32((adc->rx_buf[0] & 0x1f) << 8 | adc->rx_buf[1], 12); + *val = sign_extend32((adc->rx_buf[0] & 0x1f) << 8 + | adc->rx_buf[1], 12); + return 0; default: return -EINVAL; } @@ -150,12 +158,10 @@ static int mcp320x_read_raw(struct iio_dev *indio_dev, switch (mask) { case IIO_CHAN_INFO_RAW: ret = mcp320x_adc_conversion(adc, channel->address, - channel->differential, device_index); - + channel->differential, device_index, val); if (ret < 0) goto out; - *val = ret; ret = IIO_VAL_INT; break; @@ -312,6 +318,7 @@ static int mcp320x_probe(struct spi_device *spi) indio_dev->name = spi_get_device_id(spi)->name; indio_dev->modes = INDIO_DIRECT_MODE; indio_dev->info = &mcp320x_info; + spi_set_drvdata(spi, indio_dev); chip_info = &mcp320x_chip_infos[spi_get_device_id(spi)->driver_data]; indio_dev->channels = chip_info->channels; diff --git a/drivers/iio/adc/stm32-adc.c b/drivers/iio/adc/stm32-adc.c index e3c15f88075f..4df32cf1650e 100644 --- a/drivers/iio/adc/stm32-adc.c +++ b/drivers/iio/adc/stm32-adc.c @@ -1666,7 +1666,7 @@ static int stm32_adc_chan_of_init(struct iio_dev *indio_dev) num_channels = of_property_count_u32_elems(node, "st,adc-channels"); if (num_channels < 0 || - num_channels >= adc_info->max_channels) { + num_channels > adc_info->max_channels) { dev_err(&indio_dev->dev, "Bad st,adc-channels?\n"); return num_channels < 0 ? num_channels : -EINVAL; } diff --git a/drivers/iio/adc/ti-ads1015.c b/drivers/iio/adc/ti-ads1015.c index d1210024f6bc..e0dc20488335 100644 --- a/drivers/iio/adc/ti-ads1015.c +++ b/drivers/iio/adc/ti-ads1015.c @@ -52,7 +52,7 @@ #define ADS1015_CFG_COMP_QUE_MASK GENMASK(1, 0) #define ADS1015_CFG_COMP_LAT_MASK BIT(2) -#define ADS1015_CFG_COMP_POL_MASK BIT(2) +#define ADS1015_CFG_COMP_POL_MASK BIT(3) #define ADS1015_CFG_COMP_MODE_MASK BIT(4) #define ADS1015_CFG_DR_MASK GENMASK(7, 5) #define ADS1015_CFG_MOD_MASK BIT(8) @@ -1017,10 +1017,12 @@ static int ads1015_probe(struct i2c_client *client, switch (irq_trig) { case IRQF_TRIGGER_LOW: - cfg_comp |= ADS1015_CFG_COMP_POL_LOW; + cfg_comp |= ADS1015_CFG_COMP_POL_LOW << + ADS1015_CFG_COMP_POL_SHIFT; break; case IRQF_TRIGGER_HIGH: - cfg_comp |= ADS1015_CFG_COMP_POL_HIGH; + cfg_comp |= ADS1015_CFG_COMP_POL_HIGH << + ADS1015_CFG_COMP_POL_SHIFT; break; default: return -EINVAL; diff --git a/drivers/iio/adc/twl4030-madc.c b/drivers/iio/adc/twl4030-madc.c index 1edd99f0c5e5..e3cfb91bffc6 100644 --- a/drivers/iio/adc/twl4030-madc.c +++ b/drivers/iio/adc/twl4030-madc.c @@ -887,21 +887,27 @@ static int twl4030_madc_probe(struct platform_device *pdev) /* Enable 3v1 bias regulator for MADC[3:6] */ madc->usb3v1 = devm_regulator_get(madc->dev, "vusb3v1"); - if (IS_ERR(madc->usb3v1)) - return -ENODEV; + if (IS_ERR(madc->usb3v1)) { + ret = -ENODEV; + goto err_i2c; + } ret = regulator_enable(madc->usb3v1); - if (ret) + if (ret) { dev_err(madc->dev, "could not enable 3v1 bias regulator\n"); + goto err_i2c; + } ret = iio_device_register(iio_dev); if (ret) { dev_err(&pdev->dev, "could not register iio device\n"); - goto err_i2c; + goto err_usb3v1; } return 0; +err_usb3v1: + regulator_disable(madc->usb3v1); err_i2c: twl4030_madc_set_current_generator(madc, 0, 0); err_current_generator: diff --git a/drivers/iio/common/st_sensors/st_sensors_core.c b/drivers/iio/common/st_sensors/st_sensors_core.c index d99bb1460fe2..02e833b14db0 100644 --- a/drivers/iio/common/st_sensors/st_sensors_core.c +++ b/drivers/iio/common/st_sensors/st_sensors_core.c @@ -463,8 +463,17 @@ int st_sensors_set_dataready_irq(struct iio_dev *indio_dev, bool enable) u8 drdy_mask; struct st_sensor_data *sdata = iio_priv(indio_dev); - if (!sdata->sensor_settings->drdy_irq.addr) + if (!sdata->sensor_settings->drdy_irq.addr) { + /* + * there are some devices (e.g. LIS3MDL) where drdy line is + * routed to a given pin and it is not possible to select a + * different one. Take into account irq status register + * to understand if irq trigger can be properly supported + */ + if (sdata->sensor_settings->drdy_irq.addr_stat_drdy) + sdata->hw_irq_trigger = enable; return 0; + } /* Enable/Disable the interrupt generator 1. */ if (sdata->sensor_settings->drdy_irq.ig1.en_addr > 0) { diff --git a/drivers/iio/industrialio-core.c b/drivers/iio/industrialio-core.c index 17ec4cee51dc..a47428b4d31b 100644 --- a/drivers/iio/industrialio-core.c +++ b/drivers/iio/industrialio-core.c @@ -310,8 +310,10 @@ static ssize_t iio_debugfs_read_reg(struct file *file, char __user *userbuf, ret = indio_dev->info->debugfs_reg_access(indio_dev, indio_dev->cached_reg_addr, 0, &val); - if (ret) + if (ret) { dev_err(indio_dev->dev.parent, "%s: read failed\n", __func__); + return ret; + } len = snprintf(buf, sizeof(buf), "0x%X\n", val); diff --git a/drivers/iio/magnetometer/st_magn_core.c b/drivers/iio/magnetometer/st_magn_core.c index e68368b5b2a3..08aafba4481c 100644 --- a/drivers/iio/magnetometer/st_magn_core.c +++ b/drivers/iio/magnetometer/st_magn_core.c @@ -315,6 +315,10 @@ static const struct st_sensor_settings st_magn_sensors_settings[] = { }, }, }, + .drdy_irq = { + /* drdy line is routed drdy pin */ + .addr_stat_drdy = ST_SENSORS_DEFAULT_STAT_ADDR, + }, .multi_read_bit = true, .bootime = 2, }, diff --git a/drivers/iio/pressure/bmp280-core.c b/drivers/iio/pressure/bmp280-core.c index 0d2ea3ee371b..8f26428804a2 100644 --- a/drivers/iio/pressure/bmp280-core.c +++ b/drivers/iio/pressure/bmp280-core.c @@ -573,7 +573,7 @@ static int bmp280_chip_config(struct bmp280_data *data) u8 osrs = BMP280_OSRS_TEMP_X(data->oversampling_temp + 1) | BMP280_OSRS_PRESS_X(data->oversampling_press + 1); - ret = regmap_update_bits(data->regmap, BMP280_REG_CTRL_MEAS, + ret = regmap_write_bits(data->regmap, BMP280_REG_CTRL_MEAS, BMP280_OSRS_TEMP_MASK | BMP280_OSRS_PRESS_MASK | BMP280_MODE_MASK, diff --git a/drivers/iio/trigger/stm32-timer-trigger.c b/drivers/iio/trigger/stm32-timer-trigger.c index 9b9053494daf..eb212f8c8879 100644 --- a/drivers/iio/trigger/stm32-timer-trigger.c +++ b/drivers/iio/trigger/stm32-timer-trigger.c @@ -174,6 +174,7 @@ static void stm32_timer_stop(struct stm32_timer_trigger *priv) clk_disable(priv->clk); /* Stop timer */ + regmap_update_bits(priv->regmap, TIM_CR1, TIM_CR1_ARPE, 0); regmap_update_bits(priv->regmap, TIM_CR1, TIM_CR1_CEN, 0); regmap_write(priv->regmap, TIM_PSC, 0); regmap_write(priv->regmap, TIM_ARR, 0); @@ -715,8 +716,9 @@ static ssize_t stm32_count_set_preset(struct iio_dev *indio_dev, if (ret) return ret; + /* TIMx_ARR register shouldn't be buffered (ARPE=0) */ + regmap_update_bits(priv->regmap, TIM_CR1, TIM_CR1_ARPE, 0); regmap_write(priv->regmap, TIM_ARR, preset); - regmap_update_bits(priv->regmap, TIM_CR1, TIM_CR1_ARPE, TIM_CR1_ARPE); return len; } diff --git a/drivers/infiniband/Kconfig b/drivers/infiniband/Kconfig index 3726205c8704..98ac46ed7214 100644 --- a/drivers/infiniband/Kconfig +++ b/drivers/infiniband/Kconfig @@ -1,6 +1,5 @@ menuconfig INFINIBAND tristate "InfiniBand support" - depends on PCI || BROKEN depends on HAS_IOMEM depends on NET depends on INET @@ -46,6 +45,7 @@ config INFINIBAND_EXP_USER_ACCESS config INFINIBAND_USER_MEM bool depends on INFINIBAND_USER_ACCESS != n + depends on MMU default y config INFINIBAND_ON_DEMAND_PAGING diff --git a/drivers/infiniband/core/addr.c b/drivers/infiniband/core/addr.c index 12523f630b61..d2f74721b3ba 100644 --- a/drivers/infiniband/core/addr.c +++ b/drivers/infiniband/core/addr.c @@ -852,7 +852,7 @@ static struct notifier_block nb = { int addr_init(void) { - addr_wq = alloc_ordered_workqueue("ib_addr", WQ_MEM_RECLAIM); + addr_wq = alloc_ordered_workqueue("ib_addr", 0); if (!addr_wq) return -ENOMEM; diff --git a/drivers/infiniband/core/cm.c b/drivers/infiniband/core/cm.c index 4c4b46586af2..f6b159d79977 100644 --- a/drivers/infiniband/core/cm.c +++ b/drivers/infiniband/core/cm.c @@ -1472,31 +1472,29 @@ static void cm_format_path_lid_from_req(struct cm_req_msg *req_msg, if (primary_path->rec_type != SA_PATH_REC_TYPE_OPA) { sa_path_set_dlid(primary_path, - htonl(ntohs(req_msg->primary_local_lid))); + ntohs(req_msg->primary_local_lid)); sa_path_set_slid(primary_path, - htonl(ntohs(req_msg->primary_remote_lid))); + ntohs(req_msg->primary_remote_lid)); } else { lid = opa_get_lid_from_gid(&req_msg->primary_local_gid); - sa_path_set_dlid(primary_path, cpu_to_be32(lid)); + sa_path_set_dlid(primary_path, lid); lid = opa_get_lid_from_gid(&req_msg->primary_remote_gid); - sa_path_set_slid(primary_path, cpu_to_be32(lid)); + sa_path_set_slid(primary_path, lid); } if (!cm_req_has_alt_path(req_msg)) return; if (alt_path->rec_type != SA_PATH_REC_TYPE_OPA) { - sa_path_set_dlid(alt_path, - htonl(ntohs(req_msg->alt_local_lid))); - sa_path_set_slid(alt_path, - htonl(ntohs(req_msg->alt_remote_lid))); + sa_path_set_dlid(alt_path, ntohs(req_msg->alt_local_lid)); + sa_path_set_slid(alt_path, ntohs(req_msg->alt_remote_lid)); } else { lid = opa_get_lid_from_gid(&req_msg->alt_local_gid); - sa_path_set_dlid(alt_path, cpu_to_be32(lid)); + sa_path_set_dlid(alt_path, lid); lid = opa_get_lid_from_gid(&req_msg->alt_remote_gid); - sa_path_set_slid(alt_path, cpu_to_be32(lid)); + sa_path_set_slid(alt_path, lid); } } @@ -1575,7 +1573,7 @@ static void cm_format_req_event(struct cm_work *work, param->bth_pkey = cm_get_bth_pkey(work); param->port = cm_id_priv->av.port->port_num; param->primary_path = &work->path[0]; - if (req_msg->alt_local_lid) + if (cm_req_has_alt_path(req_msg)) param->alternate_path = &work->path[1]; else param->alternate_path = NULL; @@ -1856,7 +1854,8 @@ static int cm_req_handler(struct cm_work *work) cm_process_routed_req(req_msg, work->mad_recv_wc->wc); memset(&work->path[0], 0, sizeof(work->path[0])); - memset(&work->path[1], 0, sizeof(work->path[1])); + if (cm_req_has_alt_path(req_msg)) + memset(&work->path[1], 0, sizeof(work->path[1])); grh = rdma_ah_read_grh(&cm_id_priv->av.ah_attr); ret = ib_get_cached_gid(work->port->cm_dev->ib_device, work->port->port_num, @@ -2810,6 +2809,7 @@ int ib_send_cm_mra(struct ib_cm_id *cm_id, msg_response = CM_MSG_RESPONSE_OTHER; break; } + /* fall through */ default: ret = -EINVAL; goto error1; @@ -3037,14 +3037,14 @@ static void cm_format_path_lid_from_lap(struct cm_lap_msg *lap_msg, u32 lid; if (path->rec_type != SA_PATH_REC_TYPE_OPA) { - sa_path_set_dlid(path, htonl(ntohs(lap_msg->alt_local_lid))); - sa_path_set_slid(path, htonl(ntohs(lap_msg->alt_remote_lid))); + sa_path_set_dlid(path, ntohs(lap_msg->alt_local_lid)); + sa_path_set_slid(path, ntohs(lap_msg->alt_remote_lid)); } else { lid = opa_get_lid_from_gid(&lap_msg->alt_local_gid); - sa_path_set_dlid(path, cpu_to_be32(lid)); + sa_path_set_dlid(path, lid); lid = opa_get_lid_from_gid(&lap_msg->alt_remote_gid); - sa_path_set_slid(path, cpu_to_be32(lid)); + sa_path_set_slid(path, lid); } } @@ -3817,14 +3817,16 @@ static void cm_recv_handler(struct ib_mad_agent *mad_agent, struct cm_port *port = mad_agent->context; struct cm_work *work; enum ib_cm_event_type event; + bool alt_path = false; u16 attr_id; int paths = 0; int going_down = 0; switch (mad_recv_wc->recv_buf.mad->mad_hdr.attr_id) { case CM_REQ_ATTR_ID: - paths = 1 + (((struct cm_req_msg *) mad_recv_wc->recv_buf.mad)-> - alt_local_lid != 0); + alt_path = cm_req_has_alt_path((struct cm_req_msg *) + mad_recv_wc->recv_buf.mad); + paths = 1 + (alt_path != 0); event = IB_CM_REQ_RECEIVED; break; case CM_MRA_ATTR_ID: diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c index 852c8fec8088..fa79c7076ccd 100644 --- a/drivers/infiniband/core/cma.c +++ b/drivers/infiniband/core/cma.c @@ -1540,7 +1540,7 @@ static struct rdma_id_private *cma_id_from_event(struct ib_cm_id *cm_id, return id_priv; } -static inline int cma_user_data_offset(struct rdma_id_private *id_priv) +static inline u8 cma_user_data_offset(struct rdma_id_private *id_priv) { return cma_family(id_priv) == AF_IB ? 0 : sizeof(struct cma_hdr); } @@ -1942,7 +1942,8 @@ static int cma_req_handler(struct ib_cm_id *cm_id, struct ib_cm_event *ib_event) struct rdma_id_private *listen_id, *conn_id = NULL; struct rdma_cm_event event; struct net_device *net_dev; - int offset, ret; + u8 offset; + int ret; listen_id = cma_id_from_event(cm_id, ib_event, &net_dev); if (IS_ERR(listen_id)) @@ -3440,7 +3441,8 @@ static int cma_resolve_ib_udp(struct rdma_id_private *id_priv, struct ib_cm_sidr_req_param req; struct ib_cm_id *id; void *private_data; - int offset, ret; + u8 offset; + int ret; memset(&req, 0, sizeof req); offset = cma_user_data_offset(id_priv); @@ -3497,7 +3499,8 @@ static int cma_connect_ib(struct rdma_id_private *id_priv, struct rdma_route *route; void *private_data; struct ib_cm_id *id; - int offset, ret; + u8 offset; + int ret; memset(&req, 0, sizeof req); offset = cma_user_data_offset(id_priv); diff --git a/drivers/infiniband/core/iwcm.c b/drivers/infiniband/core/iwcm.c index fcf42f6bb82a..e9e189ec7502 100644 --- a/drivers/infiniband/core/iwcm.c +++ b/drivers/infiniband/core/iwcm.c @@ -447,9 +447,6 @@ static void destroy_cm_id(struct iw_cm_id *cm_id) */ void iw_destroy_cm_id(struct iw_cm_id *cm_id) { - struct iwcm_id_private *cm_id_priv; - - cm_id_priv = container_of(cm_id, struct iwcm_id_private, id); destroy_cm_id(cm_id); } EXPORT_SYMBOL(iw_destroy_cm_id); diff --git a/drivers/infiniband/core/rw.c b/drivers/infiniband/core/rw.c index 6ca607e8e293..c8963e91f92a 100644 --- a/drivers/infiniband/core/rw.c +++ b/drivers/infiniband/core/rw.c @@ -384,21 +384,17 @@ int rdma_rw_ctx_signature_init(struct rdma_rw_ctx *ctx, struct ib_qp *qp, count += ret; prev_wr = &ctx->sig->data.reg_wr.wr; - if (prot_sg_cnt) { - ret = rdma_rw_init_one_mr(qp, port_num, &ctx->sig->prot, - prot_sg, prot_sg_cnt, 0); - if (ret < 0) - goto out_destroy_data_mr; - count += ret; + ret = rdma_rw_init_one_mr(qp, port_num, &ctx->sig->prot, + prot_sg, prot_sg_cnt, 0); + if (ret < 0) + goto out_destroy_data_mr; + count += ret; - if (ctx->sig->prot.inv_wr.next) - prev_wr->next = &ctx->sig->prot.inv_wr; - else - prev_wr->next = &ctx->sig->prot.reg_wr.wr; - prev_wr = &ctx->sig->prot.reg_wr.wr; - } else { - ctx->sig->prot.mr = NULL; - } + if (ctx->sig->prot.inv_wr.next) + prev_wr->next = &ctx->sig->prot.inv_wr; + else + prev_wr->next = &ctx->sig->prot.reg_wr.wr; + prev_wr = &ctx->sig->prot.reg_wr.wr; ctx->sig->sig_mr = ib_mr_pool_get(qp, &qp->sig_mrs); if (!ctx->sig->sig_mr) { diff --git a/drivers/infiniband/core/sysfs.c b/drivers/infiniband/core/sysfs.c index abc5ab581f82..e30d86fa1855 100644 --- a/drivers/infiniband/core/sysfs.c +++ b/drivers/infiniband/core/sysfs.c @@ -108,8 +108,22 @@ static ssize_t port_attr_show(struct kobject *kobj, return port_attr->show(p, port_attr, buf); } +static ssize_t port_attr_store(struct kobject *kobj, + struct attribute *attr, + const char *buf, size_t count) +{ + struct port_attribute *port_attr = + container_of(attr, struct port_attribute, attr); + struct ib_port *p = container_of(kobj, struct ib_port, kobj); + + if (!port_attr->store) + return -EIO; + return port_attr->store(p, port_attr, buf, count); +} + static const struct sysfs_ops port_sysfs_ops = { - .show = port_attr_show + .show = port_attr_show, + .store = port_attr_store }; static ssize_t gid_attr_show(struct kobject *kobj, diff --git a/drivers/infiniband/core/user_mad.c b/drivers/infiniband/core/user_mad.c index c1696e6084b2..4b64dd02e090 100644 --- a/drivers/infiniband/core/user_mad.c +++ b/drivers/infiniband/core/user_mad.c @@ -229,7 +229,16 @@ static void recv_handler(struct ib_mad_agent *agent, packet->mad.hdr.status = 0; packet->mad.hdr.length = hdr_size(file) + mad_recv_wc->mad_len; packet->mad.hdr.qpn = cpu_to_be32(mad_recv_wc->wc->src_qp); - packet->mad.hdr.lid = ib_lid_be16(mad_recv_wc->wc->slid); + /* + * On OPA devices it is okay to lose the upper 16 bits of LID as this + * information is obtained elsewhere. Mask off the upper 16 bits. + */ + if (agent->device->port_immutable[agent->port_num].core_cap_flags & + RDMA_CORE_PORT_INTEL_OPA) + packet->mad.hdr.lid = ib_lid_be16(0xFFFF & + mad_recv_wc->wc->slid); + else + packet->mad.hdr.lid = ib_lid_be16(mad_recv_wc->wc->slid); packet->mad.hdr.sl = mad_recv_wc->wc->sl; packet->mad.hdr.path_bits = mad_recv_wc->wc->dlid_path_bits; packet->mad.hdr.pkey_index = mad_recv_wc->wc->pkey_index; @@ -506,7 +515,7 @@ static ssize_t ib_umad_write(struct file *filp, const char __user *buf, rdma_ah_set_dgid_raw(&ah_attr, packet->mad.hdr.gid); } - ah = rdma_create_ah(agent->qp->pd, &ah_attr); + ah = rdma_create_user_ah(agent->qp->pd, &ah_attr, NULL); if (IS_ERR(ah)) { ret = PTR_ERR(ah); goto err_up; diff --git a/drivers/infiniband/core/uverbs.h b/drivers/infiniband/core/uverbs.h index 37c8903e7fd0..ee2739ae4305 100644 --- a/drivers/infiniband/core/uverbs.h +++ b/drivers/infiniband/core/uverbs.h @@ -47,21 +47,28 @@ #include <rdma/ib_umem.h> #include <rdma/ib_user_verbs.h> -#define INIT_UDATA(udata, ibuf, obuf, ilen, olen) \ - do { \ - (udata)->inbuf = (const void __user *) (ibuf); \ - (udata)->outbuf = (void __user *) (obuf); \ - (udata)->inlen = (ilen); \ - (udata)->outlen = (olen); \ - } while (0) +static inline void +ib_uverbs_init_udata(struct ib_udata *udata, + const void __user *ibuf, + void __user *obuf, + size_t ilen, size_t olen) +{ + udata->inbuf = ibuf; + udata->outbuf = obuf; + udata->inlen = ilen; + udata->outlen = olen; +} -#define INIT_UDATA_BUF_OR_NULL(udata, ibuf, obuf, ilen, olen) \ - do { \ - (udata)->inbuf = (ilen) ? (const void __user *) (ibuf) : NULL; \ - (udata)->outbuf = (olen) ? (void __user *) (obuf) : NULL; \ - (udata)->inlen = (ilen); \ - (udata)->outlen = (olen); \ - } while (0) +static inline void +ib_uverbs_init_udata_buf_or_null(struct ib_udata *udata, + const void __user *ibuf, + void __user *obuf, + size_t ilen, size_t olen) +{ + ib_uverbs_init_udata(udata, + ilen ? ibuf : NULL, olen ? obuf : NULL, + ilen, olen); +} /* * Our lifetime rules for these structs are the following: diff --git a/drivers/infiniband/core/uverbs_cmd.c b/drivers/infiniband/core/uverbs_cmd.c index 52a2cf2d83aa..d31e4bc58e9a 100644 --- a/drivers/infiniband/core/uverbs_cmd.c +++ b/drivers/infiniband/core/uverbs_cmd.c @@ -91,8 +91,8 @@ ssize_t ib_uverbs_get_context(struct ib_uverbs_file *file, goto err; } - INIT_UDATA(&udata, buf + sizeof(cmd), - (unsigned long) cmd.response + sizeof(resp), + ib_uverbs_init_udata(&udata, buf + sizeof(cmd), + u64_to_user_ptr(cmd.response) + sizeof(resp), in_len - sizeof(cmd) - sizeof(struct ib_uverbs_cmd_hdr), out_len - sizeof(resp)); @@ -141,8 +141,7 @@ ssize_t ib_uverbs_get_context(struct ib_uverbs_file *file, goto err_fd; } - if (copy_to_user((void __user *) (unsigned long) cmd.response, - &resp, sizeof resp)) { + if (copy_to_user(u64_to_user_ptr(cmd.response), &resp, sizeof resp)) { ret = -EFAULT; goto err_file; } @@ -238,8 +237,7 @@ ssize_t ib_uverbs_query_device(struct ib_uverbs_file *file, memset(&resp, 0, sizeof resp); copy_query_dev_fields(file, ib_dev, &resp, &ib_dev->attrs); - if (copy_to_user((void __user *) (unsigned long) cmd.response, - &resp, sizeof resp)) + if (copy_to_user(u64_to_user_ptr(cmd.response), &resp, sizeof resp)) return -EFAULT; return in_len; @@ -295,8 +293,7 @@ ssize_t ib_uverbs_query_port(struct ib_uverbs_file *file, resp.link_layer = rdma_port_get_link_layer(ib_dev, cmd.port_num); - if (copy_to_user((void __user *) (unsigned long) cmd.response, - &resp, sizeof resp)) + if (copy_to_user(u64_to_user_ptr(cmd.response), &resp, sizeof resp)) return -EFAULT; return in_len; @@ -320,8 +317,8 @@ ssize_t ib_uverbs_alloc_pd(struct ib_uverbs_file *file, if (copy_from_user(&cmd, buf, sizeof cmd)) return -EFAULT; - INIT_UDATA(&udata, buf + sizeof(cmd), - (unsigned long) cmd.response + sizeof(resp), + ib_uverbs_init_udata(&udata, buf + sizeof(cmd), + u64_to_user_ptr(cmd.response) + sizeof(resp), in_len - sizeof(cmd) - sizeof(struct ib_uverbs_cmd_hdr), out_len - sizeof(resp)); @@ -344,8 +341,7 @@ ssize_t ib_uverbs_alloc_pd(struct ib_uverbs_file *file, memset(&resp, 0, sizeof resp); resp.pd_handle = uobj->id; - if (copy_to_user((void __user *) (unsigned long) cmd.response, - &resp, sizeof resp)) { + if (copy_to_user(u64_to_user_ptr(cmd.response), &resp, sizeof resp)) { ret = -EFAULT; goto err_copy; } @@ -490,8 +486,8 @@ ssize_t ib_uverbs_open_xrcd(struct ib_uverbs_file *file, if (copy_from_user(&cmd, buf, sizeof cmd)) return -EFAULT; - INIT_UDATA(&udata, buf + sizeof(cmd), - (unsigned long) cmd.response + sizeof(resp), + ib_uverbs_init_udata(&udata, buf + sizeof(cmd), + u64_to_user_ptr(cmd.response) + sizeof(resp), in_len - sizeof(cmd) - sizeof(struct ib_uverbs_cmd_hdr), out_len - sizeof(resp)); @@ -556,8 +552,7 @@ ssize_t ib_uverbs_open_xrcd(struct ib_uverbs_file *file, atomic_inc(&xrcd->usecnt); } - if (copy_to_user((void __user *) (unsigned long) cmd.response, - &resp, sizeof resp)) { + if (copy_to_user(u64_to_user_ptr(cmd.response), &resp, sizeof resp)) { ret = -EFAULT; goto err_copy; } @@ -655,8 +650,8 @@ ssize_t ib_uverbs_reg_mr(struct ib_uverbs_file *file, if (copy_from_user(&cmd, buf, sizeof cmd)) return -EFAULT; - INIT_UDATA(&udata, buf + sizeof(cmd), - (unsigned long) cmd.response + sizeof(resp), + ib_uverbs_init_udata(&udata, buf + sizeof(cmd), + u64_to_user_ptr(cmd.response) + sizeof(resp), in_len - sizeof(cmd) - sizeof(struct ib_uverbs_cmd_hdr), out_len - sizeof(resp)); @@ -705,8 +700,7 @@ ssize_t ib_uverbs_reg_mr(struct ib_uverbs_file *file, resp.rkey = mr->rkey; resp.mr_handle = uobj->id; - if (copy_to_user((void __user *) (unsigned long) cmd.response, - &resp, sizeof resp)) { + if (copy_to_user(u64_to_user_ptr(cmd.response), &resp, sizeof resp)) { ret = -EFAULT; goto err_copy; } @@ -748,8 +742,8 @@ ssize_t ib_uverbs_rereg_mr(struct ib_uverbs_file *file, if (copy_from_user(&cmd, buf, sizeof(cmd))) return -EFAULT; - INIT_UDATA(&udata, buf + sizeof(cmd), - (unsigned long) cmd.response + sizeof(resp), + ib_uverbs_init_udata(&udata, buf + sizeof(cmd), + u64_to_user_ptr(cmd.response) + sizeof(resp), in_len - sizeof(cmd) - sizeof(struct ib_uverbs_cmd_hdr), out_len - sizeof(resp)); @@ -800,8 +794,7 @@ ssize_t ib_uverbs_rereg_mr(struct ib_uverbs_file *file, resp.lkey = mr->lkey; resp.rkey = mr->rkey; - if (copy_to_user((void __user *)(unsigned long)cmd.response, - &resp, sizeof(resp))) + if (copy_to_user(u64_to_user_ptr(cmd.response), &resp, sizeof(resp))) ret = -EFAULT; else ret = in_len; @@ -867,8 +860,8 @@ ssize_t ib_uverbs_alloc_mw(struct ib_uverbs_file *file, goto err_free; } - INIT_UDATA(&udata, buf + sizeof(cmd), - (unsigned long)cmd.response + sizeof(resp), + ib_uverbs_init_udata(&udata, buf + sizeof(cmd), + u64_to_user_ptr(cmd.response) + sizeof(resp), in_len - sizeof(cmd) - sizeof(struct ib_uverbs_cmd_hdr), out_len - sizeof(resp)); @@ -889,8 +882,7 @@ ssize_t ib_uverbs_alloc_mw(struct ib_uverbs_file *file, resp.rkey = mw->rkey; resp.mw_handle = uobj->id; - if (copy_to_user((void __user *)(unsigned long)cmd.response, - &resp, sizeof(resp))) { + if (copy_to_user(u64_to_user_ptr(cmd.response), &resp, sizeof(resp))) { ret = -EFAULT; goto err_copy; } @@ -956,8 +948,7 @@ ssize_t ib_uverbs_create_comp_channel(struct ib_uverbs_file *file, uobj_file.uobj); ib_uverbs_init_event_queue(&ev_file->ev_queue); - if (copy_to_user((void __user *) (unsigned long) cmd.response, - &resp, sizeof resp)) { + if (copy_to_user(u64_to_user_ptr(cmd.response), &resp, sizeof resp)) { uobj_alloc_abort(uobj); return -EFAULT; } @@ -1087,10 +1078,11 @@ ssize_t ib_uverbs_create_cq(struct ib_uverbs_file *file, if (copy_from_user(&cmd, buf, sizeof(cmd))) return -EFAULT; - INIT_UDATA(&ucore, buf, (unsigned long)cmd.response, sizeof(cmd), sizeof(resp)); + ib_uverbs_init_udata(&ucore, buf, u64_to_user_ptr(cmd.response), + sizeof(cmd), sizeof(resp)); - INIT_UDATA(&uhw, buf + sizeof(cmd), - (unsigned long)cmd.response + sizeof(resp), + ib_uverbs_init_udata(&uhw, buf + sizeof(cmd), + u64_to_user_ptr(cmd.response) + sizeof(resp), in_len - sizeof(cmd) - sizeof(struct ib_uverbs_cmd_hdr), out_len - sizeof(resp)); @@ -1173,8 +1165,8 @@ ssize_t ib_uverbs_resize_cq(struct ib_uverbs_file *file, if (copy_from_user(&cmd, buf, sizeof cmd)) return -EFAULT; - INIT_UDATA(&udata, buf + sizeof(cmd), - (unsigned long) cmd.response + sizeof(resp), + ib_uverbs_init_udata(&udata, buf + sizeof(cmd), + u64_to_user_ptr(cmd.response) + sizeof(resp), in_len - sizeof(cmd) - sizeof(struct ib_uverbs_cmd_hdr), out_len - sizeof(resp)); @@ -1188,8 +1180,7 @@ ssize_t ib_uverbs_resize_cq(struct ib_uverbs_file *file, resp.cqe = cq->cqe; - if (copy_to_user((void __user *) (unsigned long) cmd.response, - &resp, sizeof resp.cqe)) + if (copy_to_user(u64_to_user_ptr(cmd.response), &resp, sizeof resp.cqe)) ret = -EFAULT; out: @@ -1249,7 +1240,7 @@ ssize_t ib_uverbs_poll_cq(struct ib_uverbs_file *file, return -EINVAL; /* we copy a struct ib_uverbs_poll_cq_resp to user space */ - header_ptr = (void __user *)(unsigned long) cmd.response; + header_ptr = u64_to_user_ptr(cmd.response); data_ptr = header_ptr + sizeof resp; memset(&resp, 0, sizeof resp); @@ -1343,8 +1334,7 @@ ssize_t ib_uverbs_destroy_cq(struct ib_uverbs_file *file, resp.async_events_reported = obj->async_events_reported; uverbs_uobject_put(uobj); - if (copy_to_user((void __user *) (unsigned long) cmd.response, - &resp, sizeof resp)) + if (copy_to_user(u64_to_user_ptr(cmd.response), &resp, sizeof resp)) return -EFAULT; return in_len; @@ -1650,10 +1640,10 @@ ssize_t ib_uverbs_create_qp(struct ib_uverbs_file *file, if (copy_from_user(&cmd, buf, sizeof(cmd))) return -EFAULT; - INIT_UDATA(&ucore, buf, (unsigned long)cmd.response, sizeof(cmd), - resp_size); - INIT_UDATA(&uhw, buf + sizeof(cmd), - (unsigned long)cmd.response + resp_size, + ib_uverbs_init_udata(&ucore, buf, u64_to_user_ptr(cmd.response), + sizeof(cmd), resp_size); + ib_uverbs_init_udata(&uhw, buf + sizeof(cmd), + u64_to_user_ptr(cmd.response) + resp_size, in_len - sizeof(cmd) - sizeof(struct ib_uverbs_cmd_hdr), out_len - resp_size); @@ -1750,8 +1740,8 @@ ssize_t ib_uverbs_open_qp(struct ib_uverbs_file *file, if (copy_from_user(&cmd, buf, sizeof cmd)) return -EFAULT; - INIT_UDATA(&udata, buf + sizeof(cmd), - (unsigned long) cmd.response + sizeof(resp), + ib_uverbs_init_udata(&udata, buf + sizeof(cmd), + u64_to_user_ptr(cmd.response) + sizeof(resp), in_len - sizeof(cmd) - sizeof(struct ib_uverbs_cmd_hdr), out_len - sizeof(resp)); @@ -1795,8 +1785,7 @@ ssize_t ib_uverbs_open_qp(struct ib_uverbs_file *file, resp.qpn = qp->qp_num; resp.qp_handle = obj->uevent.uobject.id; - if (copy_to_user((void __user *) (unsigned long) cmd.response, - &resp, sizeof resp)) { + if (copy_to_user(u64_to_user_ptr(cmd.response), &resp, sizeof resp)) { ret = -EFAULT; goto err_destroy; } @@ -1911,8 +1900,7 @@ ssize_t ib_uverbs_query_qp(struct ib_uverbs_file *file, resp.max_inline_data = init_attr->cap.max_inline_data; resp.sq_sig_all = init_attr->sq_sig_type == IB_SIGNAL_ALL_WR; - if (copy_to_user((void __user *) (unsigned long) cmd.response, - &resp, sizeof resp)) + if (copy_to_user(u64_to_user_ptr(cmd.response), &resp, sizeof resp)) ret = -EFAULT; out: @@ -2042,7 +2030,7 @@ ssize_t ib_uverbs_modify_qp(struct ib_uverbs_file *file, ~((IB_USER_LEGACY_LAST_QP_ATTR_MASK << 1) - 1)) return -EOPNOTSUPP; - INIT_UDATA(&udata, buf + sizeof(cmd.base), NULL, + ib_uverbs_init_udata(&udata, buf + sizeof(cmd.base), NULL, in_len - sizeof(cmd.base) - sizeof(struct ib_uverbs_cmd_hdr), out_len); @@ -2126,8 +2114,7 @@ ssize_t ib_uverbs_destroy_qp(struct ib_uverbs_file *file, resp.events_reported = obj->uevent.events_reported; uverbs_uobject_put(uobj); - if (copy_to_user((void __user *) (unsigned long) cmd.response, - &resp, sizeof resp)) + if (copy_to_user(u64_to_user_ptr(cmd.response), &resp, sizeof resp)) return -EFAULT; return in_len; @@ -2311,8 +2298,7 @@ ssize_t ib_uverbs_post_send(struct ib_uverbs_file *file, break; } - if (copy_to_user((void __user *) (unsigned long) cmd.response, - &resp, sizeof resp)) + if (copy_to_user(u64_to_user_ptr(cmd.response), &resp, sizeof resp)) ret = -EFAULT; out_put: @@ -2460,8 +2446,7 @@ ssize_t ib_uverbs_post_recv(struct ib_uverbs_file *file, } } - if (copy_to_user((void __user *) (unsigned long) cmd.response, - &resp, sizeof resp)) + if (copy_to_user(u64_to_user_ptr(cmd.response), &resp, sizeof resp)) ret = -EFAULT; out: @@ -2510,8 +2495,7 @@ ssize_t ib_uverbs_post_srq_recv(struct ib_uverbs_file *file, break; } - if (copy_to_user((void __user *) (unsigned long) cmd.response, - &resp, sizeof resp)) + if (copy_to_user(u64_to_user_ptr(cmd.response), &resp, sizeof resp)) ret = -EFAULT; out: @@ -2537,7 +2521,6 @@ ssize_t ib_uverbs_create_ah(struct ib_uverbs_file *file, struct rdma_ah_attr attr; int ret; struct ib_udata udata; - u8 *dmac; if (out_len < sizeof resp) return -ENOSPC; @@ -2548,8 +2531,8 @@ ssize_t ib_uverbs_create_ah(struct ib_uverbs_file *file, if (!rdma_is_port_valid(ib_dev, cmd.attr.port_num)) return -EINVAL; - INIT_UDATA(&udata, buf + sizeof(cmd), - (unsigned long)cmd.response + sizeof(resp), + ib_uverbs_init_udata(&udata, buf + sizeof(cmd), + u64_to_user_ptr(cmd.response) + sizeof(resp), in_len - sizeof(cmd) - sizeof(struct ib_uverbs_cmd_hdr), out_len - sizeof(resp)); @@ -2580,28 +2563,20 @@ ssize_t ib_uverbs_create_ah(struct ib_uverbs_file *file, } else { rdma_ah_set_ah_flags(&attr, 0); } - dmac = rdma_ah_retrieve_dmac(&attr); - if (dmac) - memset(dmac, 0, ETH_ALEN); - - ah = pd->device->create_ah(pd, &attr, &udata); + ah = rdma_create_user_ah(pd, &attr, &udata); if (IS_ERR(ah)) { ret = PTR_ERR(ah); goto err_put; } - ah->device = pd->device; - ah->pd = pd; - atomic_inc(&pd->usecnt); ah->uobject = uobj; uobj->user_handle = cmd.user_handle; uobj->object = ah; resp.ah_handle = uobj->id; - if (copy_to_user((void __user *) (unsigned long) cmd.response, - &resp, sizeof resp)) { + if (copy_to_user(u64_to_user_ptr(cmd.response), &resp, sizeof resp)) { ret = -EFAULT; goto err_copy; } @@ -3627,8 +3602,8 @@ ssize_t ib_uverbs_create_srq(struct ib_uverbs_file *file, xcmd.max_sge = cmd.max_sge; xcmd.srq_limit = cmd.srq_limit; - INIT_UDATA(&udata, buf + sizeof(cmd), - (unsigned long) cmd.response + sizeof(resp), + ib_uverbs_init_udata(&udata, buf + sizeof(cmd), + u64_to_user_ptr(cmd.response) + sizeof(resp), in_len - sizeof(cmd) - sizeof(struct ib_uverbs_cmd_hdr), out_len - sizeof(resp)); @@ -3654,8 +3629,8 @@ ssize_t ib_uverbs_create_xsrq(struct ib_uverbs_file *file, if (copy_from_user(&cmd, buf, sizeof cmd)) return -EFAULT; - INIT_UDATA(&udata, buf + sizeof(cmd), - (unsigned long) cmd.response + sizeof(resp), + ib_uverbs_init_udata(&udata, buf + sizeof(cmd), + u64_to_user_ptr(cmd.response) + sizeof(resp), in_len - sizeof(cmd) - sizeof(struct ib_uverbs_cmd_hdr), out_len - sizeof(resp)); @@ -3680,7 +3655,7 @@ ssize_t ib_uverbs_modify_srq(struct ib_uverbs_file *file, if (copy_from_user(&cmd, buf, sizeof cmd)) return -EFAULT; - INIT_UDATA(&udata, buf + sizeof cmd, NULL, in_len - sizeof cmd, + ib_uverbs_init_udata(&udata, buf + sizeof cmd, NULL, in_len - sizeof cmd, out_len); srq = uobj_get_obj_read(srq, cmd.srq_handle, file->ucontext); @@ -3731,8 +3706,7 @@ ssize_t ib_uverbs_query_srq(struct ib_uverbs_file *file, resp.max_sge = attr.max_sge; resp.srq_limit = attr.srq_limit; - if (copy_to_user((void __user *) (unsigned long) cmd.response, - &resp, sizeof resp)) + if (copy_to_user(u64_to_user_ptr(cmd.response), &resp, sizeof resp)) return -EFAULT; return in_len; @@ -3773,8 +3747,7 @@ ssize_t ib_uverbs_destroy_srq(struct ib_uverbs_file *file, } resp.events_reported = obj->events_reported; uverbs_uobject_put(uobj); - if (copy_to_user((void __user *)(unsigned long)cmd.response, - &resp, sizeof(resp))) + if (copy_to_user(u64_to_user_ptr(cmd.response), &resp, sizeof(resp))) return -EFAULT; return in_len; diff --git a/drivers/infiniband/core/uverbs_ioctl.c b/drivers/infiniband/core/uverbs_ioctl.c index 5286ad57d903..71ff2644e053 100644 --- a/drivers/infiniband/core/uverbs_ioctl.c +++ b/drivers/infiniband/core/uverbs_ioctl.c @@ -241,9 +241,7 @@ static long ib_uverbs_cmd_verbs(struct ib_device *ib_dev, struct uverbs_attr *curr_attr; unsigned long *curr_bitmap; size_t ctx_size; -#ifdef UVERBS_OPTIMIZE_USING_STACK_SZ uintptr_t data[UVERBS_OPTIMIZE_USING_STACK_SZ / sizeof(uintptr_t)]; -#endif if (hdr->reserved) return -EINVAL; @@ -269,13 +267,10 @@ static long ib_uverbs_cmd_verbs(struct ib_device *ib_dev, (method_spec->num_child_attrs / BITS_PER_LONG + method_spec->num_buckets); -#ifdef UVERBS_OPTIMIZE_USING_STACK_SZ if (ctx_size <= UVERBS_OPTIMIZE_USING_STACK_SZ) ctx = (void *)data; - if (!ctx) -#endif - ctx = kmalloc(ctx_size, GFP_KERNEL); + ctx = kmalloc(ctx_size, GFP_KERNEL); if (!ctx) return -ENOMEM; @@ -311,10 +306,8 @@ static long ib_uverbs_cmd_verbs(struct ib_device *ib_dev, err = uverbs_handle_method(buf, ctx->uattrs, hdr->num_attrs, ib_dev, file, method_spec, ctx->uverbs_attr_bundle); out: -#ifdef UVERBS_OPTIMIZE_USING_STACK_SZ - if (ctx_size > UVERBS_OPTIMIZE_USING_STACK_SZ) -#endif - kfree(ctx); + if (ctx != (void *)data) + kfree(ctx); return err; } diff --git a/drivers/infiniband/core/uverbs_ioctl_merge.c b/drivers/infiniband/core/uverbs_ioctl_merge.c index 76ddb6564578..062485f9300d 100644 --- a/drivers/infiniband/core/uverbs_ioctl_merge.c +++ b/drivers/infiniband/core/uverbs_ioctl_merge.c @@ -376,7 +376,7 @@ static struct uverbs_method_spec *build_method_with_attrs(const struct uverbs_me min_id) || WARN(attr_obj_with_special_access && !(attr->flags & UVERBS_ATTR_SPEC_F_MANDATORY), - "ib_uverbs: Tried to merge attr (%d) but it's an object with new/destroy aceess but isn't mandatory\n", + "ib_uverbs: Tried to merge attr (%d) but it's an object with new/destroy access but isn't mandatory\n", min_id) || WARN(IS_ATTR_OBJECT(attr) && attr->flags & UVERBS_ATTR_SPEC_F_MIN_SZ, diff --git a/drivers/infiniband/core/uverbs_main.c b/drivers/infiniband/core/uverbs_main.c index dc2aed6fb21b..b5febfd84ee5 100644 --- a/drivers/infiniband/core/uverbs_main.c +++ b/drivers/infiniband/core/uverbs_main.c @@ -763,7 +763,7 @@ static ssize_t ib_uverbs_write(struct file *filp, const char __user *buf, } if (!access_ok(VERIFY_WRITE, - (void __user *) (unsigned long) ex_hdr.response, + u64_to_user_ptr(ex_hdr.response), (hdr.out_words + ex_hdr.provider_out_words) * 8)) { ret = -EFAULT; goto out; @@ -775,19 +775,17 @@ static ssize_t ib_uverbs_write(struct file *filp, const char __user *buf, } } - INIT_UDATA_BUF_OR_NULL(&ucore, buf, (unsigned long) ex_hdr.response, - hdr.in_words * 8, hdr.out_words * 8); + ib_uverbs_init_udata_buf_or_null(&ucore, buf, + u64_to_user_ptr(ex_hdr.response), + hdr.in_words * 8, hdr.out_words * 8); - INIT_UDATA_BUF_OR_NULL(&uhw, - buf + ucore.inlen, - (unsigned long) ex_hdr.response + ucore.outlen, - ex_hdr.provider_in_words * 8, - ex_hdr.provider_out_words * 8); + ib_uverbs_init_udata_buf_or_null(&uhw, + buf + ucore.inlen, + u64_to_user_ptr(ex_hdr.response) + ucore.outlen, + ex_hdr.provider_in_words * 8, + ex_hdr.provider_out_words * 8); - ret = uverbs_ex_cmd_table[command](file, - ib_dev, - &ucore, - &uhw); + ret = uverbs_ex_cmd_table[command](file, ib_dev, &ucore, &uhw); if (!ret) ret = written_count; } else { diff --git a/drivers/infiniband/core/uverbs_marshall.c b/drivers/infiniband/core/uverbs_marshall.c index bd0acf376af0..aeb2824efbc7 100644 --- a/drivers/infiniband/core/uverbs_marshall.c +++ b/drivers/infiniband/core/uverbs_marshall.c @@ -176,18 +176,18 @@ EXPORT_SYMBOL(ib_copy_path_rec_to_user); void ib_copy_path_rec_from_user(struct sa_path_rec *dst, struct ib_user_path_rec *src) { - __be32 slid, dlid; + u32 slid, dlid; memset(dst, 0, sizeof(*dst)); if ((ib_is_opa_gid((union ib_gid *)src->sgid)) || (ib_is_opa_gid((union ib_gid *)src->dgid))) { dst->rec_type = SA_PATH_REC_TYPE_OPA; - slid = htonl(opa_get_lid_from_gid((union ib_gid *)src->sgid)); - dlid = htonl(opa_get_lid_from_gid((union ib_gid *)src->dgid)); + slid = opa_get_lid_from_gid((union ib_gid *)src->sgid); + dlid = opa_get_lid_from_gid((union ib_gid *)src->dgid); } else { dst->rec_type = SA_PATH_REC_TYPE_IB; - slid = htonl(ntohs(src->slid)); - dlid = htonl(ntohs(src->dlid)); + slid = ntohs(src->slid); + dlid = ntohs(src->dlid); } memcpy(dst->dgid.raw, src->dgid, sizeof dst->dgid); memcpy(dst->sgid.raw, src->sgid, sizeof dst->sgid); diff --git a/drivers/infiniband/core/uverbs_std_types.c b/drivers/infiniband/core/uverbs_std_types.c index 0a98579700ec..b095bce7f238 100644 --- a/drivers/infiniband/core/uverbs_std_types.c +++ b/drivers/infiniband/core/uverbs_std_types.c @@ -246,7 +246,8 @@ static void create_udata(struct uverbs_attr_bundle *ctx, outbuf_len = uhw_out->ptr_attr.len; } - INIT_UDATA_BUF_OR_NULL(udata, inbuf, outbuf, inbuf_len, outbuf_len); + ib_uverbs_init_udata_buf_or_null(udata, inbuf, outbuf, inbuf_len, + outbuf_len); } static int uverbs_create_cq_handler(struct ib_device *ib_dev, diff --git a/drivers/infiniband/core/verbs.c b/drivers/infiniband/core/verbs.c index de57d6c11a25..d8f1a5d34f4f 100644 --- a/drivers/infiniband/core/verbs.c +++ b/drivers/infiniband/core/verbs.c @@ -53,6 +53,9 @@ #include "core_priv.h" +static int ib_resolve_eth_dmac(struct ib_device *device, + struct rdma_ah_attr *ah_attr); + static const char * const ib_events[] = { [IB_EVENT_CQ_ERR] = "CQ error", [IB_EVENT_QP_FATAL] = "QP fatal error", @@ -302,11 +305,13 @@ EXPORT_SYMBOL(ib_dealloc_pd); /* Address handles */ -struct ib_ah *rdma_create_ah(struct ib_pd *pd, struct rdma_ah_attr *ah_attr) +static struct ib_ah *_rdma_create_ah(struct ib_pd *pd, + struct rdma_ah_attr *ah_attr, + struct ib_udata *udata) { struct ib_ah *ah; - ah = pd->device->create_ah(pd, ah_attr, NULL); + ah = pd->device->create_ah(pd, ah_attr, udata); if (!IS_ERR(ah)) { ah->device = pd->device; @@ -318,8 +323,42 @@ struct ib_ah *rdma_create_ah(struct ib_pd *pd, struct rdma_ah_attr *ah_attr) return ah; } + +struct ib_ah *rdma_create_ah(struct ib_pd *pd, struct rdma_ah_attr *ah_attr) +{ + return _rdma_create_ah(pd, ah_attr, NULL); +} EXPORT_SYMBOL(rdma_create_ah); +/** + * rdma_create_user_ah - Creates an address handle for the + * given address vector. + * It resolves destination mac address for ah attribute of RoCE type. + * @pd: The protection domain associated with the address handle. + * @ah_attr: The attributes of the address vector. + * @udata: pointer to user's input output buffer information need by + * provider driver. + * + * It returns 0 on success and returns appropriate error code on error. + * The address handle is used to reference a local or global destination + * in all UD QP post sends. + */ +struct ib_ah *rdma_create_user_ah(struct ib_pd *pd, + struct rdma_ah_attr *ah_attr, + struct ib_udata *udata) +{ + int err; + + if (ah_attr->type == RDMA_AH_ATTR_TYPE_ROCE) { + err = ib_resolve_eth_dmac(pd->device, ah_attr); + if (err) + return ERR_PTR(err); + } + + return _rdma_create_ah(pd, ah_attr, udata); +} +EXPORT_SYMBOL(rdma_create_user_ah); + int ib_get_rdma_header_version(const union rdma_network_hdr *hdr) { const struct iphdr *ip4h = (struct iphdr *)&hdr->roce4grh; @@ -1221,8 +1260,8 @@ int ib_modify_qp_is_ok(enum ib_qp_state cur_state, enum ib_qp_state next_state, } EXPORT_SYMBOL(ib_modify_qp_is_ok); -int ib_resolve_eth_dmac(struct ib_device *device, - struct rdma_ah_attr *ah_attr) +static int ib_resolve_eth_dmac(struct ib_device *device, + struct rdma_ah_attr *ah_attr) { int ret = 0; struct ib_global_route *grh; @@ -1281,7 +1320,6 @@ int ib_resolve_eth_dmac(struct ib_device *device, out: return ret; } -EXPORT_SYMBOL(ib_resolve_eth_dmac); /** * ib_modify_qp_with_udata - Modifies the attributes for the specified QP. diff --git a/drivers/infiniband/hw/bnxt_re/ib_verbs.c b/drivers/infiniband/hw/bnxt_re/ib_verbs.c index 0d89621d9fe8..ebcdfb4f5f75 100644 --- a/drivers/infiniband/hw/bnxt_re/ib_verbs.c +++ b/drivers/infiniband/hw/bnxt_re/ib_verbs.c @@ -729,14 +729,6 @@ struct ib_ah *bnxt_re_create_ah(struct ib_pd *ib_pd, ah->qplib_ah.nw_type = CMDQ_CREATE_AH_TYPE_V1; break; } - rc = rdma_addr_find_l2_eth_by_grh(&sgid, &grh->dgid, - ah_attr->roce.dmac, &vlan_tag, - &sgid_attr.ndev->ifindex, - NULL); - if (rc) { - dev_err(rdev_to_dev(rdev), "Failed to get dmac\n"); - goto fail; - } } memcpy(ah->qplib_ah.dmac, ah_attr->roce.dmac, ETH_ALEN); @@ -1643,7 +1635,7 @@ static int bnxt_re_build_qp1_send_v2(struct bnxt_re_qp *qp, u8 ip_version = 0; u16 vlan_id = 0xFFFF; void *buf; - int i, rc = 0, size; + int i, rc = 0; memset(&qp->qp1_hdr, 0, sizeof(qp->qp1_hdr)); @@ -1760,7 +1752,7 @@ static int bnxt_re_build_qp1_send_v2(struct bnxt_re_qp *qp, /* Pack the QP1 to the transmit buffer */ buf = bnxt_qplib_get_qp1_sq_buf(&qp->qplib_qp, &sge); if (buf) { - size = ib_ud_header_pack(&qp->qp1_hdr, buf); + ib_ud_header_pack(&qp->qp1_hdr, buf); for (i = wqe->num_sge; i; i--) { wqe->sg_list[i].addr = wqe->sg_list[i - 1].addr; wqe->sg_list[i].lkey = wqe->sg_list[i - 1].lkey; @@ -2216,7 +2208,7 @@ static int bnxt_re_post_recv_shadow_qp(struct bnxt_re_dev *rdev, struct ib_recv_wr *wr) { struct bnxt_qplib_swqe wqe; - int rc = 0, payload_sz = 0; + int rc = 0; memset(&wqe, 0, sizeof(wqe)); while (wr) { @@ -2231,8 +2223,7 @@ static int bnxt_re_post_recv_shadow_qp(struct bnxt_re_dev *rdev, rc = -EINVAL; break; } - payload_sz = bnxt_re_build_sgl(wr->sg_list, wqe.sg_list, - wr->num_sge); + bnxt_re_build_sgl(wr->sg_list, wqe.sg_list, wr->num_sge); wqe.wr_id = wr->wr_id; wqe.type = BNXT_QPLIB_SWQE_TYPE_RECV; @@ -2569,7 +2560,7 @@ static void bnxt_re_process_req_wc(struct ib_wc *wc, struct bnxt_qplib_cqe *cqe) static int bnxt_re_check_packet_type(u16 raweth_qp1_flags, u16 raweth_qp1_flags2) { - bool is_udp = false, is_ipv6 = false, is_ipv4 = false; + bool is_ipv6 = false, is_ipv4 = false; /* raweth_qp1_flags Bit 9-6 indicates itype */ if ((raweth_qp1_flags & CQ_RES_RAWETH_QP1_RAWETH_QP1_FLAGS_ITYPE_ROCE) @@ -2580,7 +2571,6 @@ static int bnxt_re_check_packet_type(u16 raweth_qp1_flags, CQ_RES_RAWETH_QP1_RAWETH_QP1_FLAGS2_IP_CS_CALC && raweth_qp1_flags2 & CQ_RES_RAWETH_QP1_RAWETH_QP1_FLAGS2_L4_CS_CALC) { - is_udp = true; /* raweth_qp1_flags2 Bit 8 indicates ip_type. 0-v4 1 - v6 */ (raweth_qp1_flags2 & CQ_RES_RAWETH_QP1_RAWETH_QP1_FLAGS2_IP_TYPE) ? diff --git a/drivers/infiniband/hw/bnxt_re/main.c b/drivers/infiniband/hw/bnxt_re/main.c index e7450ea92aa9..aafc19aa5de1 100644 --- a/drivers/infiniband/hw/bnxt_re/main.c +++ b/drivers/infiniband/hw/bnxt_re/main.c @@ -78,6 +78,7 @@ static struct list_head bnxt_re_dev_list = LIST_HEAD_INIT(bnxt_re_dev_list); /* Mutex to protect the list of bnxt_re devices added */ static DEFINE_MUTEX(bnxt_re_dev_lock); static struct workqueue_struct *bnxt_re_wq; +static void bnxt_re_ib_unreg(struct bnxt_re_dev *rdev, bool lock_wait); /* for handling bnxt_en callbacks later */ static void bnxt_re_stop(void *p) @@ -92,11 +93,22 @@ static void bnxt_re_sriov_config(void *p, int num_vfs) { } +static void bnxt_re_shutdown(void *p) +{ + struct bnxt_re_dev *rdev = p; + + if (!rdev) + return; + + bnxt_re_ib_unreg(rdev, false); +} + static struct bnxt_ulp_ops bnxt_re_ulp_ops = { .ulp_async_notifier = NULL, .ulp_stop = bnxt_re_stop, .ulp_start = bnxt_re_start, - .ulp_sriov_config = bnxt_re_sriov_config + .ulp_sriov_config = bnxt_re_sriov_config, + .ulp_shutdown = bnxt_re_shutdown }; /* RoCE -> Net driver */ @@ -1071,9 +1083,10 @@ static int bnxt_re_ib_reg(struct bnxt_re_dev *rdev) */ rc = bnxt_qplib_alloc_rcfw_channel(rdev->en_dev->pdev, &rdev->rcfw, BNXT_RE_MAX_QPC_COUNT); - if (rc) + if (rc) { + pr_err("Failed to allocate RCFW Channel: %#x\n", rc); goto fail; - + } rc = bnxt_re_net_ring_alloc (rdev, rdev->rcfw.creq.pbl[PBL_LVL_0].pg_map_arr, rdev->rcfw.creq.pbl[rdev->rcfw.creq.level].pg_count, diff --git a/drivers/infiniband/hw/bnxt_re/qplib_fp.c b/drivers/infiniband/hw/bnxt_re/qplib_fp.c index e8afc47f8949..a82044dacce0 100644 --- a/drivers/infiniband/hw/bnxt_re/qplib_fp.c +++ b/drivers/infiniband/hw/bnxt_re/qplib_fp.c @@ -160,11 +160,6 @@ void bnxt_qplib_add_flush_qp(struct bnxt_qplib_qp *qp) static void __bnxt_qplib_del_flush_qp(struct bnxt_qplib_qp *qp) { - struct bnxt_qplib_cq *scq, *rcq; - - scq = qp->scq; - rcq = qp->rcq; - if (qp->sq.flushed) { qp->sq.flushed = false; list_del(&qp->sq_flush); @@ -1360,7 +1355,7 @@ int bnxt_qplib_post_send(struct bnxt_qplib_qp *qp, break; } - /* else, just fall thru */ + /* fall thru */ case BNXT_QPLIB_SWQE_TYPE_SEND_WITH_IMM: case BNXT_QPLIB_SWQE_TYPE_SEND_WITH_INV: { diff --git a/drivers/infiniband/hw/bnxt_re/qplib_rcfw.c b/drivers/infiniband/hw/bnxt_re/qplib_rcfw.c index 2bdb1562bd21..6d116146fa3c 100644 --- a/drivers/infiniband/hw/bnxt_re/qplib_rcfw.c +++ b/drivers/infiniband/hw/bnxt_re/qplib_rcfw.c @@ -88,7 +88,6 @@ static int __send_message(struct bnxt_qplib_rcfw *rcfw, struct cmdq_base *req, unsigned long flags; u32 size, opcode; u16 cookie, cbit; - int pg, idx; u8 *preq; opcode = req->opcode; @@ -149,9 +148,6 @@ static int __send_message(struct bnxt_qplib_rcfw *rcfw, struct cmdq_base *req, preq = (u8 *)req; size = req->cmd_size * BNXT_QPLIB_CMDQE_UNITS; do { - pg = 0; - idx = 0; - /* Locate the next cmdq slot */ sw_prod = HWQ_CMP(cmdq->prod, cmdq); cmdqe = &cmdq_ptr[get_cmdq_pg(sw_prod)][get_cmdq_idx(sw_prod)]; @@ -172,14 +168,14 @@ static int __send_message(struct bnxt_qplib_rcfw *rcfw, struct cmdq_base *req, rcfw->seq_num++; cmdq_prod = cmdq->prod; - if (rcfw->flags & FIRMWARE_FIRST_FLAG) { + if (test_bit(FIRMWARE_FIRST_FLAG, &rcfw->flags)) { /* The very first doorbell write * is required to set this flag * which prompts the FW to reset * its internal pointers */ - cmdq_prod |= FIRMWARE_FIRST_FLAG; - rcfw->flags &= ~FIRMWARE_FIRST_FLAG; + cmdq_prod |= BIT(FIRMWARE_FIRST_FLAG); + clear_bit(FIRMWARE_FIRST_FLAG, &rcfw->flags); } /* ring CMDQ DB */ @@ -622,7 +618,7 @@ int bnxt_qplib_enable_rcfw_channel(struct pci_dev *pdev, /* General */ rcfw->seq_num = 0; - rcfw->flags = FIRMWARE_FIRST_FLAG; + set_bit(FIRMWARE_FIRST_FLAG, &rcfw->flags); bmap_size = BITS_TO_LONGS(RCFW_MAX_OUTSTANDING_CMD * sizeof(unsigned long)); rcfw->cmdq_bitmap = kzalloc(bmap_size, GFP_KERNEL); diff --git a/drivers/infiniband/hw/bnxt_re/qplib_rcfw.h b/drivers/infiniband/hw/bnxt_re/qplib_rcfw.h index 85b16da287f9..2946a7cfae82 100644 --- a/drivers/infiniband/hw/bnxt_re/qplib_rcfw.h +++ b/drivers/infiniband/hw/bnxt_re/qplib_rcfw.h @@ -162,9 +162,9 @@ struct bnxt_qplib_rcfw { unsigned long *cmdq_bitmap; u32 bmap_size; unsigned long flags; -#define FIRMWARE_INITIALIZED_FLAG BIT(0) -#define FIRMWARE_FIRST_FLAG BIT(31) -#define FIRMWARE_TIMED_OUT BIT(3) +#define FIRMWARE_INITIALIZED_FLAG 0 +#define FIRMWARE_FIRST_FLAG 31 +#define FIRMWARE_TIMED_OUT 3 wait_queue_head_t waitq; int (*aeq_handler)(struct bnxt_qplib_rcfw *, struct creq_func_event *); diff --git a/drivers/infiniband/hw/bnxt_re/qplib_res.h b/drivers/infiniband/hw/bnxt_re/qplib_res.h index e87207526d2c..2e5c052da5a9 100644 --- a/drivers/infiniband/hw/bnxt_re/qplib_res.h +++ b/drivers/infiniband/hw/bnxt_re/qplib_res.h @@ -169,7 +169,7 @@ struct bnxt_qplib_ctx { u32 cq_count; struct bnxt_qplib_hwq cq_tbl; struct bnxt_qplib_hwq tim_tbl; -#define MAX_TQM_ALLOC_REQ 32 +#define MAX_TQM_ALLOC_REQ 48 #define MAX_TQM_ALLOC_BLK_SIZE 8 u8 tqm_count[MAX_TQM_ALLOC_REQ]; struct bnxt_qplib_hwq tqm_pde; diff --git a/drivers/infiniband/hw/bnxt_re/qplib_sp.c b/drivers/infiniband/hw/bnxt_re/qplib_sp.c index e277e54a05eb..9543ce51a28a 100644 --- a/drivers/infiniband/hw/bnxt_re/qplib_sp.c +++ b/drivers/infiniband/hw/bnxt_re/qplib_sp.c @@ -720,13 +720,12 @@ int bnxt_qplib_map_tc2cos(struct bnxt_qplib_res *res, u16 *cids) struct cmdq_map_tc_to_cos req; struct creq_map_tc_to_cos_resp resp; u16 cmd_flags = 0; - int rc = 0; RCFW_CMD_PREP(req, MAP_TC_TO_COS, cmd_flags); req.cos0 = cpu_to_le16(cids[0]); req.cos1 = cpu_to_le16(cids[1]); - rc = bnxt_qplib_rcfw_send_message(rcfw, (void *)&req, - (void *)&resp, NULL, 0); + bnxt_qplib_rcfw_send_message(rcfw, (void *)&req, (void *)&resp, NULL, + 0); return 0; } diff --git a/drivers/infiniband/hw/bnxt_re/roce_hsi.h b/drivers/infiniband/hw/bnxt_re/roce_hsi.h index eeb55b2db57e..c3cba6063a03 100644 --- a/drivers/infiniband/hw/bnxt_re/roce_hsi.h +++ b/drivers/infiniband/hw/bnxt_re/roce_hsi.h @@ -2644,7 +2644,7 @@ struct creq_query_func_resp_sb { u8 l2_db_space_size; __le16 max_srq; __le32 max_gid; - __le32 tqm_alloc_reqs[8]; + __le32 tqm_alloc_reqs[12]; }; /* Set resources command response (16 bytes) */ diff --git a/drivers/infiniband/hw/cxgb3/Kconfig b/drivers/infiniband/hw/cxgb3/Kconfig index 2b6352b85485..431be733fbbe 100644 --- a/drivers/infiniband/hw/cxgb3/Kconfig +++ b/drivers/infiniband/hw/cxgb3/Kconfig @@ -1,6 +1,6 @@ config INFINIBAND_CXGB3 tristate "Chelsio RDMA Driver" - depends on CHELSIO_T3 && INET + depends on CHELSIO_T3 select GENERIC_ALLOCATOR ---help--- This is an iWARP/RDMA driver for the Chelsio T3 1GbE and diff --git a/drivers/infiniband/hw/cxgb3/cxio_hal.c b/drivers/infiniband/hw/cxgb3/cxio_hal.c index 3eff6541bd6f..3328acc53c2a 100644 --- a/drivers/infiniband/hw/cxgb3/cxio_hal.c +++ b/drivers/infiniband/hw/cxgb3/cxio_hal.c @@ -404,12 +404,10 @@ static void insert_sq_cqe(struct t3_wq *wq, struct t3_cq *cq, int cxio_flush_sq(struct t3_wq *wq, struct t3_cq *cq, int count) { - __u32 ptr; + __u32 ptr = wq->sq_rptr + count; int flushed = 0; - struct t3_swsq *sqp = wq->sq + Q_PTR2IDX(wq->sq_rptr, wq->sq_size_log2); + struct t3_swsq *sqp = wq->sq + Q_PTR2IDX(ptr, wq->sq_size_log2); - ptr = wq->sq_rptr + count; - sqp = wq->sq + Q_PTR2IDX(ptr, wq->sq_size_log2); while (ptr != wq->sq_wptr) { sqp->signaled = 0; insert_sq_cqe(wq, cq, sqp); diff --git a/drivers/infiniband/hw/cxgb3/iwch_cm.c b/drivers/infiniband/hw/cxgb3/iwch_cm.c index 86975370a4c0..1c90c86fc8b8 100644 --- a/drivers/infiniband/hw/cxgb3/iwch_cm.c +++ b/drivers/infiniband/hw/cxgb3/iwch_cm.c @@ -107,7 +107,7 @@ static struct workqueue_struct *workq; static struct sk_buff_head rxq; static struct sk_buff *get_skb(struct sk_buff *skb, int len, gfp_t gfp); -static void ep_timeout(unsigned long arg); +static void ep_timeout(struct timer_list *t); static void connect_reply_upcall(struct iwch_ep *ep, int status); static void start_ep_timer(struct iwch_ep *ep) @@ -119,8 +119,6 @@ static void start_ep_timer(struct iwch_ep *ep) } else get_ep(&ep->com); ep->timer.expires = jiffies + ep_timeout_secs * HZ; - ep->timer.data = (unsigned long)ep; - ep->timer.function = ep_timeout; add_timer(&ep->timer); } @@ -1399,7 +1397,7 @@ static int pass_accept_req(struct t3cdev *tdev, struct sk_buff *skb, void *ctx) child_ep->l2t = l2t; child_ep->dst = dst; child_ep->hwtid = hwtid; - init_timer(&child_ep->timer); + timer_setup(&child_ep->timer, ep_timeout, 0); cxgb3_insert_tid(tdev, &t3c_client, child_ep, hwtid); accept_cr(child_ep, req->peer_ip, skb); goto out; @@ -1719,9 +1717,9 @@ static int ec_status(struct t3cdev *tdev, struct sk_buff *skb, void *ctx) return CPL_RET_BUF_DONE; } -static void ep_timeout(unsigned long arg) +static void ep_timeout(struct timer_list *t) { - struct iwch_ep *ep = (struct iwch_ep *)arg; + struct iwch_ep *ep = from_timer(ep, t, timer); struct iwch_qp_attributes attrs; unsigned long flags; int abort = 1; @@ -1760,8 +1758,8 @@ static void ep_timeout(unsigned long arg) int iwch_reject_cr(struct iw_cm_id *cm_id, const void *pdata, u8 pdata_len) { - int err; struct iwch_ep *ep = to_ep(cm_id); + pr_debug("%s ep %p tid %u\n", __func__, ep, ep->hwtid); if (state_read(&ep->com) == DEAD) { @@ -1772,8 +1770,8 @@ int iwch_reject_cr(struct iw_cm_id *cm_id, const void *pdata, u8 pdata_len) if (mpa_rev == 0) abort_connection(ep, NULL, GFP_KERNEL); else { - err = send_mpa_reject(ep, pdata, pdata_len); - err = iwch_ep_disconnect(ep, 0, GFP_KERNEL); + send_mpa_reject(ep, pdata, pdata_len); + iwch_ep_disconnect(ep, 0, GFP_KERNEL); } put_ep(&ep->com); return 0; @@ -1899,7 +1897,7 @@ int iwch_connect(struct iw_cm_id *cm_id, struct iw_cm_conn_param *conn_param) err = -ENOMEM; goto out; } - init_timer(&ep->timer); + timer_setup(&ep->timer, ep_timeout, 0); ep->plen = conn_param->private_data_len; if (ep->plen) memcpy(ep->mpa_pkt + sizeof(struct mpa_message), diff --git a/drivers/infiniband/hw/cxgb3/iwch_provider.c b/drivers/infiniband/hw/cxgb3/iwch_provider.c index 099e76f3758a..a578ca559e11 100644 --- a/drivers/infiniband/hw/cxgb3/iwch_provider.c +++ b/drivers/infiniband/hw/cxgb3/iwch_provider.c @@ -969,7 +969,6 @@ static struct ib_qp *iwch_create_qp(struct ib_pd *pd, insert_mmap(ucontext, mm2); } qhp->ibqp.qp_num = qhp->wq.qpid; - init_timer(&(qhp->timer)); pr_debug("%s sq_num_entries %d, rq_num_entries %d qpid 0x%0x qhp %p dma_addr 0x%llx size %d rq_addr 0x%x\n", __func__, qhp->attr.sq_num_entries, qhp->attr.rq_num_entries, qhp->wq.qpid, qhp, (unsigned long long)qhp->wq.dma_addr, diff --git a/drivers/infiniband/hw/cxgb3/iwch_provider.h b/drivers/infiniband/hw/cxgb3/iwch_provider.h index 9e216edec4c0..2e38ddefea8a 100644 --- a/drivers/infiniband/hw/cxgb3/iwch_provider.h +++ b/drivers/infiniband/hw/cxgb3/iwch_provider.h @@ -168,7 +168,6 @@ struct iwch_qp { atomic_t refcnt; wait_queue_head_t wait; enum IWCH_QP_FLAGS flags; - struct timer_list timer; }; static inline int qp_quiesced(struct iwch_qp *qhp) diff --git a/drivers/infiniband/hw/cxgb3/iwch_qp.c b/drivers/infiniband/hw/cxgb3/iwch_qp.c index 7f633da0185d..3871e1fd8395 100644 --- a/drivers/infiniband/hw/cxgb3/iwch_qp.c +++ b/drivers/infiniband/hw/cxgb3/iwch_qp.c @@ -722,10 +722,13 @@ int iwch_post_terminate(struct iwch_qp *qhp, struct respQ_msg_t *rsp_msg) */ static void __flush_qp(struct iwch_qp *qhp, struct iwch_cq *rchp, struct iwch_cq *schp) + __releases(&qhp->lock) + __acquires(&qhp->lock) { int count; int flushed; + lockdep_assert_held(&qhp->lock); pr_debug("%s qhp %p rchp %p schp %p\n", __func__, qhp, rchp, schp); /* take a ref on the qhp since we must release the lock */ diff --git a/drivers/infiniband/hw/cxgb4/Kconfig b/drivers/infiniband/hw/cxgb4/Kconfig index afe8b28e0878..0a671a61fc92 100644 --- a/drivers/infiniband/hw/cxgb4/Kconfig +++ b/drivers/infiniband/hw/cxgb4/Kconfig @@ -1,6 +1,6 @@ config INFINIBAND_CXGB4 tristate "Chelsio T4/T5 RDMA Driver" - depends on CHELSIO_T4 && INET && (IPV6 || IPV6=n) + depends on CHELSIO_T4 && INET select CHELSIO_LIB select GENERIC_ALLOCATOR ---help--- diff --git a/drivers/infiniband/hw/cxgb4/cm.c b/drivers/infiniband/hw/cxgb4/cm.c index daf7a56e5d7e..7eb8a85e4d42 100644 --- a/drivers/infiniband/hw/cxgb4/cm.c +++ b/drivers/infiniband/hw/cxgb4/cm.c @@ -99,10 +99,6 @@ module_param(enable_tcp_window_scaling, int, 0644); MODULE_PARM_DESC(enable_tcp_window_scaling, "Enable tcp window scaling (default=1)"); -int c4iw_debug; -module_param(c4iw_debug, int, 0644); -MODULE_PARM_DESC(c4iw_debug, "obsolete"); - static int peer2peer = 1; module_param(peer2peer, int, 0644); MODULE_PARM_DESC(peer2peer, "Support peer2peer ULPs (default=1)"); @@ -144,7 +140,7 @@ static struct workqueue_struct *workq; static struct sk_buff_head rxq; static struct sk_buff *get_skb(struct sk_buff *skb, int len, gfp_t gfp); -static void ep_timeout(unsigned long arg); +static void ep_timeout(struct timer_list *t); static void connect_reply_upcall(struct c4iw_ep *ep, int status); static int sched(struct c4iw_dev *dev, struct sk_buff *skb); @@ -180,7 +176,7 @@ static void ref_qp(struct c4iw_ep *ep) static void start_ep_timer(struct c4iw_ep *ep) { - pr_debug("%s ep %p\n", __func__, ep); + pr_debug("ep %p\n", ep); if (timer_pending(&ep->timer)) { pr_err("%s timer already started! ep %p\n", __func__, ep); @@ -189,14 +185,12 @@ static void start_ep_timer(struct c4iw_ep *ep) clear_bit(TIMEOUT, &ep->com.flags); c4iw_get_ep(&ep->com); ep->timer.expires = jiffies + ep_timeout_secs * HZ; - ep->timer.data = (unsigned long)ep; - ep->timer.function = ep_timeout; add_timer(&ep->timer); } static int stop_ep_timer(struct c4iw_ep *ep) { - pr_debug("%s ep %p stopping\n", __func__, ep); + pr_debug("ep %p stopping\n", ep); del_timer_sync(&ep->timer); if (!test_and_set_bit(TIMEOUT, &ep->com.flags)) { c4iw_put_ep(&ep->com); @@ -212,7 +206,7 @@ static int c4iw_l2t_send(struct c4iw_rdev *rdev, struct sk_buff *skb, if (c4iw_fatal_error(rdev)) { kfree_skb(skb); - pr_debug("%s - device in error state - dropping\n", __func__); + pr_err("%s - device in error state - dropping\n", __func__); return -EIO; } error = cxgb4_l2t_send(rdev->lldi.ports[0], skb, l2e); @@ -229,7 +223,7 @@ int c4iw_ofld_send(struct c4iw_rdev *rdev, struct sk_buff *skb) if (c4iw_fatal_error(rdev)) { kfree_skb(skb); - pr_debug("%s - device in error state - dropping\n", __func__); + pr_err("%s - device in error state - dropping\n", __func__); return -EIO; } error = cxgb4_ofld_send(rdev->lldi.ports[0], skb); @@ -263,10 +257,10 @@ static void set_emss(struct c4iw_ep *ep, u16 opt) if (ep->emss < 128) ep->emss = 128; if (ep->emss & 7) - pr_debug("Warning: misaligned mtu idx %u mss %u emss=%u\n", - TCPOPT_MSS_G(opt), ep->mss, ep->emss); - pr_debug("%s mss_idx %u mss %u emss=%u\n", __func__, TCPOPT_MSS_G(opt), - ep->mss, ep->emss); + pr_warn("Warning: misaligned mtu idx %u mss %u emss=%u\n", + TCPOPT_MSS_G(opt), ep->mss, ep->emss); + pr_debug("mss_idx %u mss %u emss=%u\n", TCPOPT_MSS_G(opt), ep->mss, + ep->emss); } static enum c4iw_ep_state state_read(struct c4iw_ep_common *epc) @@ -287,7 +281,7 @@ static void __state_set(struct c4iw_ep_common *epc, enum c4iw_ep_state new) static void state_set(struct c4iw_ep_common *epc, enum c4iw_ep_state new) { mutex_lock(&epc->mutex); - pr_debug("%s - %s -> %s\n", __func__, states[epc->state], states[new]); + pr_debug("%s -> %s\n", states[epc->state], states[new]); __state_set(epc, new); mutex_unlock(&epc->mutex); return; @@ -318,11 +312,18 @@ static void *alloc_ep(int size, gfp_t gfp) epc = kzalloc(size, gfp); if (epc) { + epc->wr_waitp = c4iw_alloc_wr_wait(gfp); + if (!epc->wr_waitp) { + kfree(epc); + epc = NULL; + goto out; + } kref_init(&epc->kref); mutex_init(&epc->mutex); - c4iw_init_wr_wait(&epc->wr_wait); + c4iw_init_wr_wait(epc->wr_waitp); } - pr_debug("%s alloc ep %p\n", __func__, epc); + pr_debug("alloc ep %p\n", epc); +out: return epc; } @@ -384,7 +385,7 @@ void _c4iw_free_ep(struct kref *kref) struct c4iw_ep *ep; ep = container_of(kref, struct c4iw_ep, com.kref); - pr_debug("%s ep %p state %s\n", __func__, ep, states[ep->com.state]); + pr_debug("ep %p state %s\n", ep, states[ep->com.state]); if (test_bit(QP_REFERENCED, &ep->com.flags)) deref_qp(ep); if (test_bit(RELEASE_RESOURCES, &ep->com.flags)) { @@ -407,6 +408,7 @@ void _c4iw_free_ep(struct kref *kref) } if (!skb_queue_empty(&ep->com.ep_skb_list)) skb_queue_purge(&ep->com.ep_skb_list); + c4iw_put_wr_wait(ep->com.wr_waitp); kfree(ep); } @@ -570,7 +572,7 @@ static void abort_arp_failure(void *handle, struct sk_buff *skb) struct c4iw_rdev *rdev = &ep->com.dev->rdev; struct cpl_abort_req *req = cplhdr(skb); - pr_debug("%s rdev %p\n", __func__, rdev); + pr_debug("rdev %p\n", rdev); req->cmd = CPL_ABORT_NO_RST; skb_get(skb); ret = c4iw_ofld_send(rdev, skb); @@ -647,7 +649,7 @@ static int send_halfclose(struct c4iw_ep *ep) struct sk_buff *skb = skb_dequeue(&ep->com.ep_skb_list); u32 wrlen = roundup(sizeof(struct cpl_close_con_req), 16); - pr_debug("%s ep %p tid %u\n", __func__, ep, ep->hwtid); + pr_debug("ep %p tid %u\n", ep, ep->hwtid); if (WARN_ON(!skb)) return -ENOMEM; @@ -662,7 +664,7 @@ static int send_abort(struct c4iw_ep *ep) u32 wrlen = roundup(sizeof(struct cpl_abort_req), 16); struct sk_buff *req_skb = skb_dequeue(&ep->com.ep_skb_list); - pr_debug("%s ep %p tid %u\n", __func__, ep, ep->hwtid); + pr_debug("ep %p tid %u\n", ep, ep->hwtid); if (WARN_ON(!req_skb)) return -ENOMEM; @@ -725,7 +727,7 @@ static int send_connect(struct c4iw_ep *ep) roundup(sizev4, 16) : roundup(sizev6, 16); - pr_debug("%s ep %p atid %u\n", __func__, ep, ep->atid); + pr_debug("ep %p atid %u\n", ep, ep->atid); skb = get_skb(NULL, wrlen, GFP_KERNEL); if (!skb) { @@ -824,13 +826,13 @@ static int send_connect(struct c4iw_ep *ep) t5req->params = cpu_to_be64(FILTER_TUPLE_V(params)); t5req->rsvd = cpu_to_be32(isn); - pr_debug("%s snd_isn %u\n", __func__, t5req->rsvd); + pr_debug("snd_isn %u\n", t5req->rsvd); t5req->opt2 = cpu_to_be32(opt2); } else { t6req->params = cpu_to_be64(FILTER_TUPLE_V(params)); t6req->rsvd = cpu_to_be32(isn); - pr_debug("%s snd_isn %u\n", __func__, t6req->rsvd); + pr_debug("snd_isn %u\n", t6req->rsvd); t6req->opt2 = cpu_to_be32(opt2); } } @@ -877,13 +879,13 @@ static int send_connect(struct c4iw_ep *ep) t5req6->params = cpu_to_be64(FILTER_TUPLE_V(params)); t5req6->rsvd = cpu_to_be32(isn); - pr_debug("%s snd_isn %u\n", __func__, t5req6->rsvd); + pr_debug("snd_isn %u\n", t5req6->rsvd); t5req6->opt2 = cpu_to_be32(opt2); } else { t6req6->params = cpu_to_be64(FILTER_TUPLE_V(params)); t6req6->rsvd = cpu_to_be32(isn); - pr_debug("%s snd_isn %u\n", __func__, t6req6->rsvd); + pr_debug("snd_isn %u\n", t6req6->rsvd); t6req6->opt2 = cpu_to_be32(opt2); } @@ -907,8 +909,8 @@ static int send_mpa_req(struct c4iw_ep *ep, struct sk_buff *skb, struct mpa_message *mpa; struct mpa_v2_conn_params mpa_v2_params; - pr_debug("%s ep %p tid %u pd_len %d\n", - __func__, ep, ep->hwtid, ep->plen); + pr_debug("ep %p tid %u pd_len %d\n", + ep, ep->hwtid, ep->plen); BUG_ON(skb_cloned(skb)); @@ -961,7 +963,7 @@ static int send_mpa_req(struct c4iw_ep *ep, struct sk_buff *skb, if (mpa_rev_to_use == 2) { mpa->private_data_size = htons(ntohs(mpa->private_data_size) + sizeof (struct mpa_v2_conn_params)); - pr_debug("%s initiator ird %u ord %u\n", __func__, ep->ird, + pr_debug("initiator ird %u ord %u\n", ep->ird, ep->ord); mpa_v2_params.ird = htons((u16)ep->ird); mpa_v2_params.ord = htons((u16)ep->ord); @@ -1014,8 +1016,8 @@ static int send_mpa_reject(struct c4iw_ep *ep, const void *pdata, u8 plen) struct sk_buff *skb; struct mpa_v2_conn_params mpa_v2_params; - pr_debug("%s ep %p tid %u pd_len %d\n", - __func__, ep, ep->hwtid, ep->plen); + pr_debug("ep %p tid %u pd_len %d\n", + ep, ep->hwtid, ep->plen); mpalen = sizeof(*mpa) + plen; if (ep->mpa_attr.version == 2 && ep->mpa_attr.enhanced_rdma_conn) @@ -1094,8 +1096,8 @@ static int send_mpa_reply(struct c4iw_ep *ep, const void *pdata, u8 plen) struct sk_buff *skb; struct mpa_v2_conn_params mpa_v2_params; - pr_debug("%s ep %p tid %u pd_len %d\n", - __func__, ep, ep->hwtid, ep->plen); + pr_debug("ep %p tid %u pd_len %d\n", + ep, ep->hwtid, ep->plen); mpalen = sizeof(*mpa) + plen; if (ep->mpa_attr.version == 2 && ep->mpa_attr.enhanced_rdma_conn) @@ -1185,7 +1187,7 @@ static int act_establish(struct c4iw_dev *dev, struct sk_buff *skb) ep = lookup_atid(t, atid); - pr_debug("%s ep %p tid %u snd_isn %u rcv_isn %u\n", __func__, ep, tid, + pr_debug("ep %p tid %u snd_isn %u rcv_isn %u\n", ep, tid, be32_to_cpu(req->snd_isn), be32_to_cpu(req->rcv_isn)); mutex_lock(&ep->com.mutex); @@ -1229,7 +1231,7 @@ static void close_complete_upcall(struct c4iw_ep *ep, int status) { struct iw_cm_event event; - pr_debug("%s ep %p tid %u\n", __func__, ep, ep->hwtid); + pr_debug("ep %p tid %u\n", ep, ep->hwtid); memset(&event, 0, sizeof(event)); event.event = IW_CM_EVENT_CLOSE; event.status = status; @@ -1246,7 +1248,7 @@ static void peer_close_upcall(struct c4iw_ep *ep) { struct iw_cm_event event; - pr_debug("%s ep %p tid %u\n", __func__, ep, ep->hwtid); + pr_debug("ep %p tid %u\n", ep, ep->hwtid); memset(&event, 0, sizeof(event)); event.event = IW_CM_EVENT_DISCONNECT; if (ep->com.cm_id) { @@ -1261,7 +1263,7 @@ static void peer_abort_upcall(struct c4iw_ep *ep) { struct iw_cm_event event; - pr_debug("%s ep %p tid %u\n", __func__, ep, ep->hwtid); + pr_debug("ep %p tid %u\n", ep, ep->hwtid); memset(&event, 0, sizeof(event)); event.event = IW_CM_EVENT_CLOSE; event.status = -ECONNRESET; @@ -1278,8 +1280,8 @@ static void connect_reply_upcall(struct c4iw_ep *ep, int status) { struct iw_cm_event event; - pr_debug("%s ep %p tid %u status %d\n", - __func__, ep, ep->hwtid, status); + pr_debug("ep %p tid %u status %d\n", + ep, ep->hwtid, status); memset(&event, 0, sizeof(event)); event.event = IW_CM_EVENT_CONNECT_REPLY; event.status = status; @@ -1308,7 +1310,7 @@ static void connect_reply_upcall(struct c4iw_ep *ep, int status) } } - pr_debug("%s ep %p tid %u status %d\n", __func__, ep, + pr_debug("ep %p tid %u status %d\n", ep, ep->hwtid, status); set_bit(CONN_RPL_UPCALL, &ep->com.history); ep->com.cm_id->event_handler(ep->com.cm_id, &event); @@ -1322,7 +1324,7 @@ static int connect_request_upcall(struct c4iw_ep *ep) struct iw_cm_event event; int ret; - pr_debug("%s ep %p tid %u\n", __func__, ep, ep->hwtid); + pr_debug("ep %p tid %u\n", ep, ep->hwtid); memset(&event, 0, sizeof(event)); event.event = IW_CM_EVENT_CONNECT_REQUEST; memcpy(&event.local_addr, &ep->com.local_addr, @@ -1359,13 +1361,13 @@ static void established_upcall(struct c4iw_ep *ep) { struct iw_cm_event event; - pr_debug("%s ep %p tid %u\n", __func__, ep, ep->hwtid); + pr_debug("ep %p tid %u\n", ep, ep->hwtid); memset(&event, 0, sizeof(event)); event.event = IW_CM_EVENT_ESTABLISHED; event.ird = ep->ord; event.ord = ep->ird; if (ep->com.cm_id) { - pr_debug("%s ep %p tid %u\n", __func__, ep, ep->hwtid); + pr_debug("ep %p tid %u\n", ep, ep->hwtid); ep->com.cm_id->event_handler(ep->com.cm_id, &event); set_bit(ESTAB_UPCALL, &ep->com.history); } @@ -1377,8 +1379,8 @@ static int update_rx_credits(struct c4iw_ep *ep, u32 credits) u32 wrlen = roundup(sizeof(struct cpl_rx_data_ack), 16); u32 credit_dack; - pr_debug("%s ep %p tid %u credits %u\n", - __func__, ep, ep->hwtid, credits); + pr_debug("ep %p tid %u credits %u\n", + ep, ep->hwtid, credits); skb = get_skb(NULL, wrlen, GFP_KERNEL); if (!skb) { pr_err("update_rx_credits - cannot alloc skb!\n"); @@ -1429,7 +1431,7 @@ static int process_mpa_reply(struct c4iw_ep *ep, struct sk_buff *skb) int err; int disconnect = 0; - pr_debug("%s ep %p tid %u\n", __func__, ep, ep->hwtid); + pr_debug("ep %p tid %u\n", ep, ep->hwtid); /* * If we get more than the supported amount of private data @@ -1527,8 +1529,7 @@ static int process_mpa_reply(struct c4iw_ep *ep, struct sk_buff *skb) MPA_V2_IRD_ORD_MASK; resp_ord = ntohs(mpa_v2_params->ord) & MPA_V2_IRD_ORD_MASK; - pr_debug("%s responder ird %u ord %u ep ird %u ord %u\n", - __func__, + pr_debug("responder ird %u ord %u ep ird %u ord %u\n", resp_ird, resp_ord, ep->ird, ep->ord); /* @@ -1573,8 +1574,8 @@ static int process_mpa_reply(struct c4iw_ep *ep, struct sk_buff *skb) if (peer2peer) ep->mpa_attr.p2p_type = p2p_type; - pr_debug("%s - crc_enabled=%d, recv_marker_enabled=%d, xmit_marker_enabled=%d, version=%d p2p_type=%d local-p2p_type = %d\n", - __func__, ep->mpa_attr.crc_enabled, + pr_debug("crc_enabled=%d, recv_marker_enabled=%d, xmit_marker_enabled=%d, version=%d p2p_type=%d local-p2p_type = %d\n", + ep->mpa_attr.crc_enabled, ep->mpa_attr.recv_marker_enabled, ep->mpa_attr.xmit_marker_enabled, ep->mpa_attr.version, ep->mpa_attr.p2p_type, p2p_type); @@ -1670,7 +1671,7 @@ static int process_mpa_request(struct c4iw_ep *ep, struct sk_buff *skb) struct mpa_v2_conn_params *mpa_v2_params; u16 plen; - pr_debug("%s ep %p tid %u\n", __func__, ep, ep->hwtid); + pr_debug("ep %p tid %u\n", ep, ep->hwtid); /* * If we get more than the supported amount of private data @@ -1679,7 +1680,7 @@ static int process_mpa_request(struct c4iw_ep *ep, struct sk_buff *skb) if (ep->mpa_pkt_len + skb->len > sizeof(ep->mpa_pkt)) goto err_stop_timer; - pr_debug("%s enter (%s line %u)\n", __func__, __FILE__, __LINE__); + pr_debug("enter (%s line %u)\n", __FILE__, __LINE__); /* * Copy the new data into our accumulation buffer. @@ -1695,7 +1696,7 @@ static int process_mpa_request(struct c4iw_ep *ep, struct sk_buff *skb) if (ep->mpa_pkt_len < sizeof(*mpa)) return 0; - pr_debug("%s enter (%s line %u)\n", __func__, __FILE__, __LINE__); + pr_debug("enter (%s line %u)\n", __FILE__, __LINE__); mpa = (struct mpa_message *) ep->mpa_pkt; /* @@ -1758,8 +1759,8 @@ static int process_mpa_request(struct c4iw_ep *ep, struct sk_buff *skb) MPA_V2_IRD_ORD_MASK; ep->ord = min_t(u32, ep->ord, cur_max_read_depth(ep->com.dev)); - pr_debug("%s initiator ird %u ord %u\n", - __func__, ep->ird, ep->ord); + pr_debug("initiator ird %u ord %u\n", + ep->ird, ep->ord); if (ntohs(mpa_v2_params->ird) & MPA_V2_PEER2PEER_MODEL) if (peer2peer) { if (ntohs(mpa_v2_params->ord) & @@ -1776,8 +1777,7 @@ static int process_mpa_request(struct c4iw_ep *ep, struct sk_buff *skb) if (peer2peer) ep->mpa_attr.p2p_type = p2p_type; - pr_debug("%s - crc_enabled=%d, recv_marker_enabled=%d, xmit_marker_enabled=%d, version=%d p2p_type=%d\n", - __func__, + pr_debug("crc_enabled=%d, recv_marker_enabled=%d, xmit_marker_enabled=%d, version=%d p2p_type=%d\n", ep->mpa_attr.crc_enabled, ep->mpa_attr.recv_marker_enabled, ep->mpa_attr.xmit_marker_enabled, ep->mpa_attr.version, ep->mpa_attr.p2p_type); @@ -1816,7 +1816,7 @@ static int rx_data(struct c4iw_dev *dev, struct sk_buff *skb) ep = get_ep_from_tid(dev, tid); if (!ep) return 0; - pr_debug("%s ep %p tid %u dlen %u\n", __func__, ep, ep->hwtid, dlen); + pr_debug("ep %p tid %u dlen %u\n", ep, ep->hwtid, dlen); skb_pull(skb, sizeof(*hdr)); skb_trim(skb, dlen); mutex_lock(&ep->com.mutex); @@ -1870,11 +1870,11 @@ static int abort_rpl(struct c4iw_dev *dev, struct sk_buff *skb) pr_warn("Abort rpl to freed endpoint\n"); return 0; } - pr_debug("%s ep %p tid %u\n", __func__, ep, ep->hwtid); + pr_debug("ep %p tid %u\n", ep, ep->hwtid); mutex_lock(&ep->com.mutex); switch (ep->com.state) { case ABORTING: - c4iw_wake_up(&ep->com.wr_wait, -ECONNRESET); + c4iw_wake_up_noref(ep->com.wr_waitp, -ECONNRESET); __state_set(&ep->com, DEAD); release = 1; break; @@ -1994,8 +1994,8 @@ static void set_tcp_window(struct c4iw_ep *ep, struct port_info *pi) { ep->snd_win = snd_win; ep->rcv_win = rcv_win; - pr_debug("%s snd_win %d rcv_win %d\n", - __func__, ep->snd_win, ep->rcv_win); + pr_debug("snd_win %d rcv_win %d\n", + ep->snd_win, ep->rcv_win); } #define ACT_OPEN_RETRY_COUNT 2 @@ -2100,9 +2100,8 @@ static int c4iw_reconnect(struct c4iw_ep *ep) int iptype; __u8 *ra; - pr_debug("%s qp %p cm_id %p\n", __func__, ep->com.qp, ep->com.cm_id); - init_timer(&ep->timer); - c4iw_init_wr_wait(&ep->com.wr_wait); + pr_debug("qp %p cm_id %p\n", ep->com.qp, ep->com.cm_id); + c4iw_init_wr_wait(ep->com.wr_waitp); /* When MPA revision is different on nodes, the node with MPA_rev=2 * tries to reconnect with MPA_rev 1 for the same EP through @@ -2163,8 +2162,8 @@ static int c4iw_reconnect(struct c4iw_ep *ep) goto fail4; } - pr_debug("%s txq_idx %u tx_chan %u smac_idx %u rss_qid %u l2t_idx %u\n", - __func__, ep->txq_idx, ep->tx_chan, ep->smac_idx, ep->rss_qid, + pr_debug("txq_idx %u tx_chan %u smac_idx %u rss_qid %u l2t_idx %u\n", + ep->txq_idx, ep->tx_chan, ep->smac_idx, ep->rss_qid, ep->l2t->idx); state_set(&ep->com, CONNECTING); @@ -2215,12 +2214,12 @@ static int act_open_rpl(struct c4iw_dev *dev, struct sk_buff *skb) la6 = (struct sockaddr_in6 *)&ep->com.local_addr; ra6 = (struct sockaddr_in6 *)&ep->com.remote_addr; - pr_debug("%s ep %p atid %u status %u errno %d\n", __func__, ep, atid, + pr_debug("ep %p atid %u status %u errno %d\n", ep, atid, status, status2errno(status)); if (cxgb_is_neg_adv(status)) { - pr_debug("%s Connection problems for atid %u status %u (%s)\n", - __func__, atid, status, neg_adv_str(status)); + pr_debug("Connection problems for atid %u status %u (%s)\n", + atid, status, neg_adv_str(status)); ep->stats.connect_neg_adv++; mutex_lock(&dev->rdev.stats.lock); dev->rdev.stats.neg_adv++; @@ -2316,12 +2315,12 @@ static int pass_open_rpl(struct c4iw_dev *dev, struct sk_buff *skb) struct c4iw_listen_ep *ep = get_ep_from_stid(dev, stid); if (!ep) { - pr_debug("%s stid %d lookup failure!\n", __func__, stid); + pr_warn("%s stid %d lookup failure!\n", __func__, stid); goto out; } - pr_debug("%s ep %p status %d error %d\n", __func__, ep, + pr_debug("ep %p status %d error %d\n", ep, rpl->status, status2errno(rpl->status)); - c4iw_wake_up(&ep->com.wr_wait, status2errno(rpl->status)); + c4iw_wake_up_noref(ep->com.wr_waitp, status2errno(rpl->status)); c4iw_put_ep(&ep->com); out: return 0; @@ -2334,11 +2333,11 @@ static int close_listsrv_rpl(struct c4iw_dev *dev, struct sk_buff *skb) struct c4iw_listen_ep *ep = get_ep_from_stid(dev, stid); if (!ep) { - pr_debug("%s stid %d lookup failure!\n", __func__, stid); + pr_warn("%s stid %d lookup failure!\n", __func__, stid); goto out; } - pr_debug("%s ep %p\n", __func__, ep); - c4iw_wake_up(&ep->com.wr_wait, status2errno(rpl->status)); + pr_debug("ep %p\n", ep); + c4iw_wake_up_noref(ep->com.wr_waitp, status2errno(rpl->status)); c4iw_put_ep(&ep->com); out: return 0; @@ -2356,7 +2355,7 @@ static int accept_cr(struct c4iw_ep *ep, struct sk_buff *skb, int win; enum chip_type adapter_type = ep->com.dev->rdev.lldi.adapter_type; - pr_debug("%s ep %p tid %u\n", __func__, ep, ep->hwtid); + pr_debug("ep %p tid %u\n", ep, ep->hwtid); BUG_ON(skb_cloned(skb)); skb_get(skb); @@ -2427,7 +2426,7 @@ static int accept_cr(struct c4iw_ep *ep, struct sk_buff *skb, if (peer2peer) isn += 4; rpl5->iss = cpu_to_be32(isn); - pr_debug("%s iss %u\n", __func__, be32_to_cpu(rpl5->iss)); + pr_debug("iss %u\n", be32_to_cpu(rpl5->iss)); } rpl->opt0 = cpu_to_be64(opt0); @@ -2440,7 +2439,7 @@ static int accept_cr(struct c4iw_ep *ep, struct sk_buff *skb, static void reject_cr(struct c4iw_dev *dev, u32 hwtid, struct sk_buff *skb) { - pr_debug("%s c4iw_dev %p tid %u\n", __func__, dev, hwtid); + pr_debug("c4iw_dev %p tid %u\n", dev, hwtid); BUG_ON(skb_cloned(skb)); skb_trim(skb, sizeof(struct cpl_tid_release)); release_tid(&dev->rdev, hwtid, skb); @@ -2466,13 +2465,13 @@ static int pass_accept_req(struct c4iw_dev *dev, struct sk_buff *skb) parent_ep = (struct c4iw_ep *)get_ep_from_stid(dev, stid); if (!parent_ep) { - pr_debug("%s connect request on invalid stid %d\n", - __func__, stid); + pr_err("%s connect request on invalid stid %d\n", + __func__, stid); goto reject; } if (state_read(&parent_ep->com) != LISTEN) { - pr_debug("%s - listening ep not in LISTEN\n", __func__); + pr_err("%s - listening ep not in LISTEN\n", __func__); goto reject; } @@ -2481,16 +2480,16 @@ static int pass_accept_req(struct c4iw_dev *dev, struct sk_buff *skb) /* Find output route */ if (iptype == 4) { - pr_debug("%s parent ep %p hwtid %u laddr %pI4 raddr %pI4 lport %d rport %d peer_mss %d\n" - , __func__, parent_ep, hwtid, + pr_debug("parent ep %p hwtid %u laddr %pI4 raddr %pI4 lport %d rport %d peer_mss %d\n" + , parent_ep, hwtid, local_ip, peer_ip, ntohs(local_port), ntohs(peer_port), peer_mss); dst = cxgb_find_route(&dev->rdev.lldi, get_real_dev, *(__be32 *)local_ip, *(__be32 *)peer_ip, local_port, peer_port, tos); } else { - pr_debug("%s parent ep %p hwtid %u laddr %pI6 raddr %pI6 lport %d rport %d peer_mss %d\n" - , __func__, parent_ep, hwtid, + pr_debug("parent ep %p hwtid %u laddr %pI6 raddr %pI6 lport %d rport %d peer_mss %d\n" + , parent_ep, hwtid, local_ip, peer_ip, ntohs(local_port), ntohs(peer_port), peer_mss); dst = cxgb_find_route6(&dev->rdev.lldi, get_real_dev, @@ -2576,10 +2575,10 @@ static int pass_accept_req(struct c4iw_dev *dev, struct sk_buff *skb) child_ep->dst = dst; child_ep->hwtid = hwtid; - pr_debug("%s tx_chan %u smac_idx %u rss_qid %u\n", __func__, + pr_debug("tx_chan %u smac_idx %u rss_qid %u\n", child_ep->tx_chan, child_ep->smac_idx, child_ep->rss_qid); - init_timer(&child_ep->timer); + timer_setup(&child_ep->timer, ep_timeout, 0); cxgb4_insert_tid(t, child_ep, hwtid, child_ep->com.local_addr.ss_family); insert_ep_tid(child_ep); @@ -2613,11 +2612,11 @@ static int pass_establish(struct c4iw_dev *dev, struct sk_buff *skb) int ret; ep = get_ep_from_tid(dev, tid); - pr_debug("%s ep %p tid %u\n", __func__, ep, ep->hwtid); + pr_debug("ep %p tid %u\n", ep, ep->hwtid); ep->snd_seq = be32_to_cpu(req->snd_isn); ep->rcv_seq = be32_to_cpu(req->rcv_isn); - pr_debug("%s ep %p hwtid %u tcp_opt 0x%02x\n", __func__, ep, tid, + pr_debug("ep %p hwtid %u tcp_opt 0x%02x\n", ep, tid, ntohs(req->tcp_opt)); set_emss(ep, ntohs(req->tcp_opt)); @@ -2650,7 +2649,7 @@ static int peer_close(struct c4iw_dev *dev, struct sk_buff *skb) if (!ep) return 0; - pr_debug("%s ep %p tid %u\n", __func__, ep, ep->hwtid); + pr_debug("ep %p tid %u\n", ep, ep->hwtid); dst_confirm(ep->dst); set_bit(PEER_CLOSE, &ep->com.history); @@ -2673,12 +2672,12 @@ static int peer_close(struct c4iw_dev *dev, struct sk_buff *skb) */ __state_set(&ep->com, CLOSING); pr_debug("waking up ep %p tid %u\n", ep, ep->hwtid); - c4iw_wake_up(&ep->com.wr_wait, -ECONNRESET); + c4iw_wake_up_noref(ep->com.wr_waitp, -ECONNRESET); break; case MPA_REP_SENT: __state_set(&ep->com, CLOSING); pr_debug("waking up ep %p tid %u\n", ep, ep->hwtid); - c4iw_wake_up(&ep->com.wr_wait, -ECONNRESET); + c4iw_wake_up_noref(ep->com.wr_waitp, -ECONNRESET); break; case FPDU_MODE: start_ep_timer(ep); @@ -2741,16 +2740,16 @@ static int peer_abort(struct c4iw_dev *dev, struct sk_buff *skb) return 0; if (cxgb_is_neg_adv(req->status)) { - pr_debug("%s Negative advice on abort- tid %u status %d (%s)\n", - __func__, ep->hwtid, req->status, - neg_adv_str(req->status)); + pr_warn("%s Negative advice on abort- tid %u status %d (%s)\n", + __func__, ep->hwtid, req->status, + neg_adv_str(req->status)); ep->stats.abort_neg_adv++; mutex_lock(&dev->rdev.stats.lock); dev->rdev.stats.neg_adv++; mutex_unlock(&dev->rdev.stats.lock); goto deref_ep; } - pr_debug("%s ep %p tid %u state %u\n", __func__, ep, ep->hwtid, + pr_debug("ep %p tid %u state %u\n", ep, ep->hwtid, ep->com.state); set_bit(PEER_ABORT, &ep->com.history); @@ -2760,7 +2759,7 @@ static int peer_abort(struct c4iw_dev *dev, struct sk_buff *skb) * MPA_REQ_SENT */ if (ep->com.state != MPA_REQ_SENT) - c4iw_wake_up(&ep->com.wr_wait, -ECONNRESET); + c4iw_wake_up_noref(ep->com.wr_waitp, -ECONNRESET); mutex_lock(&ep->com.mutex); switch (ep->com.state) { @@ -2783,8 +2782,8 @@ static int peer_abort(struct c4iw_dev *dev, struct sk_buff *skb) * do some housekeeping so as to re-initiate the * connection */ - pr_debug("%s: mpa_rev=%d. Retrying with mpav1\n", - __func__, mpa_rev); + pr_info("%s: mpa_rev=%d. Retrying with mpav1\n", + __func__, mpa_rev); ep->retry_with_mpa_v1 = 1; } break; @@ -2810,7 +2809,7 @@ static int peer_abort(struct c4iw_dev *dev, struct sk_buff *skb) case ABORTING: break; case DEAD: - pr_debug("%s PEER_ABORT IN DEAD STATE!!!!\n", __func__); + pr_warn("%s PEER_ABORT IN DEAD STATE!!!!\n", __func__); mutex_unlock(&ep->com.mutex); goto deref_ep; default: @@ -2875,7 +2874,7 @@ static int close_con_rpl(struct c4iw_dev *dev, struct sk_buff *skb) if (!ep) return 0; - pr_debug("%s ep %p tid %u\n", __func__, ep, ep->hwtid); + pr_debug("ep %p tid %u\n", ep, ep->hwtid); /* The cm_id may be null if we failed to connect */ mutex_lock(&ep->com.mutex); @@ -2950,19 +2949,19 @@ static int fw4_ack(struct c4iw_dev *dev, struct sk_buff *skb) ep = get_ep_from_tid(dev, tid); if (!ep) return 0; - pr_debug("%s ep %p tid %u credits %u\n", - __func__, ep, ep->hwtid, credits); + pr_debug("ep %p tid %u credits %u\n", + ep, ep->hwtid, credits); if (credits == 0) { - pr_debug("%s 0 credit ack ep %p tid %u state %u\n", - __func__, ep, ep->hwtid, state_read(&ep->com)); + pr_debug("0 credit ack ep %p tid %u state %u\n", + ep, ep->hwtid, state_read(&ep->com)); goto out; } dst_confirm(ep->dst); if (ep->mpa_skb) { - pr_debug("%s last streaming msg ack ep %p tid %u state %u initiator %u freeing skb\n", - __func__, ep, ep->hwtid, - state_read(&ep->com), ep->mpa_attr.initiator ? 1 : 0); + pr_debug("last streaming msg ack ep %p tid %u state %u initiator %u freeing skb\n", + ep, ep->hwtid, state_read(&ep->com), + ep->mpa_attr.initiator ? 1 : 0); mutex_lock(&ep->com.mutex); kfree_skb(ep->mpa_skb); ep->mpa_skb = NULL; @@ -2980,7 +2979,7 @@ int c4iw_reject_cr(struct iw_cm_id *cm_id, const void *pdata, u8 pdata_len) int abort; struct c4iw_ep *ep = to_ep(cm_id); - pr_debug("%s ep %p tid %u\n", __func__, ep, ep->hwtid); + pr_debug("ep %p tid %u\n", ep, ep->hwtid); mutex_lock(&ep->com.mutex); if (ep->com.state != MPA_REQ_RCVD) { @@ -3011,7 +3010,7 @@ int c4iw_accept_cr(struct iw_cm_id *cm_id, struct iw_cm_conn_param *conn_param) struct c4iw_qp *qp = get_qhp(h, conn_param->qpn); int abort = 0; - pr_debug("%s ep %p tid %u\n", __func__, ep, ep->hwtid); + pr_debug("ep %p tid %u\n", ep, ep->hwtid); mutex_lock(&ep->com.mutex); if (ep->com.state != MPA_REQ_RCVD) { @@ -3064,7 +3063,7 @@ int c4iw_accept_cr(struct iw_cm_id *cm_id, struct iw_cm_conn_param *conn_param) ep->ird = 1; } - pr_debug("%s %d ird %d ord %d\n", __func__, __LINE__, ep->ird, ep->ord); + pr_debug("ird %d ord %d\n", ep->ird, ep->ord); ep->com.cm_id = cm_id; ref_cm_id(&ep->com); @@ -3204,7 +3203,7 @@ int c4iw_connect(struct iw_cm_id *cm_id, struct iw_cm_conn_param *conn_param) goto fail1; } - init_timer(&ep->timer); + timer_setup(&ep->timer, ep_timeout, 0); ep->plen = conn_param->private_data_len; if (ep->plen) memcpy(ep->mpa_pkt + sizeof(struct mpa_message), @@ -3220,12 +3219,12 @@ int c4iw_connect(struct iw_cm_id *cm_id, struct iw_cm_conn_param *conn_param) ep->com.dev = dev; ep->com.qp = get_qhp(dev, conn_param->qpn); if (!ep->com.qp) { - pr_debug("%s qpn 0x%x not found!\n", __func__, conn_param->qpn); + pr_warn("%s qpn 0x%x not found!\n", __func__, conn_param->qpn); err = -EINVAL; goto fail2; } ref_qp(ep); - pr_debug("%s qpn 0x%x qp %p cm_id %p\n", __func__, conn_param->qpn, + pr_debug("qpn 0x%x qp %p cm_id %p\n", conn_param->qpn, ep->com.qp, cm_id); /* @@ -3263,8 +3262,8 @@ int c4iw_connect(struct iw_cm_id *cm_id, struct iw_cm_conn_param *conn_param) } /* find a route */ - pr_debug("%s saddr %pI4 sport 0x%x raddr %pI4 rport 0x%x\n", - __func__, &laddr->sin_addr, ntohs(laddr->sin_port), + pr_debug("saddr %pI4 sport 0x%x raddr %pI4 rport 0x%x\n", + &laddr->sin_addr, ntohs(laddr->sin_port), ra, ntohs(raddr->sin_port)); ep->dst = cxgb_find_route(&dev->rdev.lldi, get_real_dev, laddr->sin_addr.s_addr, @@ -3285,8 +3284,8 @@ int c4iw_connect(struct iw_cm_id *cm_id, struct iw_cm_conn_param *conn_param) } /* find a route */ - pr_debug("%s saddr %pI6 sport 0x%x raddr %pI6 rport 0x%x\n", - __func__, laddr6->sin6_addr.s6_addr, + pr_debug("saddr %pI6 sport 0x%x raddr %pI6 rport 0x%x\n", + laddr6->sin6_addr.s6_addr, ntohs(laddr6->sin6_port), raddr6->sin6_addr.s6_addr, ntohs(raddr6->sin6_port)); ep->dst = cxgb_find_route6(&dev->rdev.lldi, get_real_dev, @@ -3309,8 +3308,8 @@ int c4iw_connect(struct iw_cm_id *cm_id, struct iw_cm_conn_param *conn_param) goto fail4; } - pr_debug("%s txq_idx %u tx_chan %u smac_idx %u rss_qid %u l2t_idx %u\n", - __func__, ep->txq_idx, ep->tx_chan, ep->smac_idx, ep->rss_qid, + pr_debug("txq_idx %u tx_chan %u smac_idx %u rss_qid %u l2t_idx %u\n", + ep->txq_idx, ep->tx_chan, ep->smac_idx, ep->rss_qid, ep->l2t->idx); state_set(&ep->com, CONNECTING); @@ -3348,14 +3347,14 @@ static int create_server6(struct c4iw_dev *dev, struct c4iw_listen_ep *ep) if (err) return err; } - c4iw_init_wr_wait(&ep->com.wr_wait); + c4iw_init_wr_wait(ep->com.wr_waitp); err = cxgb4_create_server6(ep->com.dev->rdev.lldi.ports[0], ep->stid, &sin6->sin6_addr, sin6->sin6_port, ep->com.dev->rdev.lldi.rxq_ids[0]); if (!err) err = c4iw_wait_for_reply(&ep->com.dev->rdev, - &ep->com.wr_wait, + ep->com.wr_waitp, 0, 0, __func__); else if (err > 0) err = net_xmit_errno(err); @@ -3391,13 +3390,13 @@ static int create_server4(struct c4iw_dev *dev, struct c4iw_listen_ep *ep) } } while (err == -EBUSY); } else { - c4iw_init_wr_wait(&ep->com.wr_wait); + c4iw_init_wr_wait(ep->com.wr_waitp); err = cxgb4_create_server(ep->com.dev->rdev.lldi.ports[0], ep->stid, sin->sin_addr.s_addr, sin->sin_port, 0, ep->com.dev->rdev.lldi.rxq_ids[0]); if (!err) err = c4iw_wait_for_reply(&ep->com.dev->rdev, - &ep->com.wr_wait, + ep->com.wr_waitp, 0, 0, __func__); else if (err > 0) err = net_xmit_errno(err); @@ -3424,7 +3423,7 @@ int c4iw_create_listen(struct iw_cm_id *cm_id, int backlog) goto fail1; } skb_queue_head_init(&ep->com.ep_skb_list); - pr_debug("%s ep %p\n", __func__, ep); + pr_debug("ep %p\n", ep); ep->com.cm_id = cm_id; ref_cm_id(&ep->com); ep->com.dev = dev; @@ -3478,7 +3477,7 @@ int c4iw_destroy_listen(struct iw_cm_id *cm_id) int err; struct c4iw_listen_ep *ep = to_listen_ep(cm_id); - pr_debug("%s ep %p\n", __func__, ep); + pr_debug("ep %p\n", ep); might_sleep(); state_set(&ep->com, DEAD); @@ -3489,13 +3488,13 @@ int c4iw_destroy_listen(struct iw_cm_id *cm_id) ep->com.dev->rdev.lldi.rxq_ids[0], 0); } else { struct sockaddr_in6 *sin6; - c4iw_init_wr_wait(&ep->com.wr_wait); + c4iw_init_wr_wait(ep->com.wr_waitp); err = cxgb4_remove_server( ep->com.dev->rdev.lldi.ports[0], ep->stid, ep->com.dev->rdev.lldi.rxq_ids[0], 0); if (err) goto done; - err = c4iw_wait_for_reply(&ep->com.dev->rdev, &ep->com.wr_wait, + err = c4iw_wait_for_reply(&ep->com.dev->rdev, ep->com.wr_waitp, 0, 0, __func__); sin6 = (struct sockaddr_in6 *)&ep->com.local_addr; cxgb4_clip_release(ep->com.dev->rdev.lldi.ports[0], @@ -3519,7 +3518,7 @@ int c4iw_ep_disconnect(struct c4iw_ep *ep, int abrupt, gfp_t gfp) mutex_lock(&ep->com.mutex); - pr_debug("%s ep %p state %s, abrupt %d\n", __func__, ep, + pr_debug("ep %p state %s, abrupt %d\n", ep, states[ep->com.state], abrupt); /* @@ -3573,8 +3572,8 @@ int c4iw_ep_disconnect(struct c4iw_ep *ep, int abrupt, gfp_t gfp) case MORIBUND: case ABORTING: case DEAD: - pr_debug("%s ignoring disconnect ep %p state %u\n", - __func__, ep, ep->com.state); + pr_info("%s ignoring disconnect ep %p state %u\n", + __func__, ep, ep->com.state); break; default: BUG(); @@ -3636,6 +3635,7 @@ static void active_ofld_conn_reply(struct c4iw_dev *dev, struct sk_buff *skb, send_fw_act_open_req(ep, atid); return; } + /* fall through */ case FW_EADDRINUSE: set_bit(ACT_RETRY_INUSE, &ep->com.history); if (ep->retry_count++ < ACT_OPEN_RETRY_COUNT) { @@ -3678,7 +3678,7 @@ static void passive_ofld_conn_reply(struct c4iw_dev *dev, struct sk_buff *skb, rpl_skb = (struct sk_buff *)(unsigned long)req->cookie; BUG_ON(!rpl_skb); if (req->retval) { - pr_debug("%s passive open failure %d\n", __func__, req->retval); + pr_err("%s passive open failure %d\n", __func__, req->retval); mutex_lock(&dev->rdev.stats.lock); dev->rdev.stats.pas_ofld_conn_fails++; mutex_unlock(&dev->rdev.stats.lock); @@ -3874,7 +3874,6 @@ static int rx_pkt(struct c4iw_dev *dev, struct sk_buff *skb) struct net_device *pdev; u16 rss_qid, eth_hdr_len; int step; - u32 tx_chan; struct neighbour *neigh; /* Drop all non-SYN packets */ @@ -3895,8 +3894,8 @@ static int rx_pkt(struct c4iw_dev *dev, struct sk_buff *skb) lep = (struct c4iw_ep *)get_ep_from_stid(dev, stid); if (!lep) { - pr_debug("%s connect request on invalid stid %d\n", - __func__, stid); + pr_warn("%s connect request on invalid stid %d\n", + __func__, stid); goto reject; } @@ -3933,7 +3932,7 @@ static int rx_pkt(struct c4iw_dev *dev, struct sk_buff *skb) skb_set_transport_header(skb, (void *)tcph - (void *)rss); skb_get(skb); - pr_debug("%s lip 0x%x lport %u pip 0x%x pport %u tos %d\n", __func__, + pr_debug("lip 0x%x lport %u pip 0x%x pport %u tos %d\n", ntohl(iph->daddr), ntohs(tcph->dest), ntohl(iph->saddr), ntohs(tcph->source), iph->tos); @@ -3941,15 +3940,13 @@ static int rx_pkt(struct c4iw_dev *dev, struct sk_buff *skb) iph->daddr, iph->saddr, tcph->dest, tcph->source, iph->tos); if (!dst) { - pr_err("%s - failed to find dst entry!\n", - __func__); + pr_err("%s - failed to find dst entry!\n", __func__); goto reject; } neigh = dst_neigh_lookup_skb(dst, skb); if (!neigh) { - pr_err("%s - failed to allocate neigh!\n", - __func__); + pr_err("%s - failed to allocate neigh!\n", __func__); goto free_dst; } @@ -3958,14 +3955,12 @@ static int rx_pkt(struct c4iw_dev *dev, struct sk_buff *skb) e = cxgb4_l2t_get(dev->rdev.lldi.l2t, neigh, pdev, 0); pi = (struct port_info *)netdev_priv(pdev); - tx_chan = cxgb4_port_chan(pdev); dev_put(pdev); } else { pdev = get_real_dev(neigh->dev); e = cxgb4_l2t_get(dev->rdev.lldi.l2t, neigh, pdev, 0); pi = (struct port_info *)netdev_priv(pdev); - tx_chan = cxgb4_port_chan(pdev); } neigh_release(neigh); if (!e) { @@ -4032,8 +4027,7 @@ static void process_timeout(struct c4iw_ep *ep) int abort = 1; mutex_lock(&ep->com.mutex); - pr_debug("%s ep %p tid %u state %d\n", __func__, ep, ep->hwtid, - ep->com.state); + pr_debug("ep %p tid %u state %d\n", ep, ep->hwtid, ep->com.state); set_bit(TIMEDOUT, &ep->com.history); switch (ep->com.state) { case MPA_REQ_SENT: @@ -4119,9 +4113,9 @@ static void process_work(struct work_struct *work) static DECLARE_WORK(skb_work, process_work); -static void ep_timeout(unsigned long arg) +static void ep_timeout(struct timer_list *t) { - struct c4iw_ep *ep = (struct c4iw_ep *)arg; + struct c4iw_ep *ep = from_timer(ep, t, timer); int kickit = 0; spin_lock(&timeout_lock); @@ -4176,15 +4170,15 @@ static int fw6_msg(struct c4iw_dev *dev, struct sk_buff *skb) struct c4iw_wr_wait *wr_waitp; int ret; - pr_debug("%s type %u\n", __func__, rpl->type); + pr_debug("type %u\n", rpl->type); switch (rpl->type) { case FW6_TYPE_WR_RPL: ret = (int)((be64_to_cpu(rpl->data[0]) >> 8) & 0xff); wr_waitp = (struct c4iw_wr_wait *)(__force unsigned long) rpl->data[1]; - pr_debug("%s wr_waitp %p ret %u\n", __func__, wr_waitp, ret); + pr_debug("wr_waitp %p ret %u\n", wr_waitp, ret); if (wr_waitp) - c4iw_wake_up(wr_waitp, ret ? -ret : 0); + c4iw_wake_up_deref(wr_waitp, ret ? -ret : 0); kfree_skb(skb); break; case FW6_TYPE_CQE: @@ -4214,15 +4208,14 @@ static int peer_abort_intr(struct c4iw_dev *dev, struct sk_buff *skb) return 0; } if (cxgb_is_neg_adv(req->status)) { - pr_debug("%s Negative advice on abort- tid %u status %d (%s)\n", - __func__, ep->hwtid, req->status, + pr_warn("%s Negative advice on abort- tid %u status %d (%s)\n", + __func__, ep->hwtid, req->status, neg_adv_str(req->status)); goto out; } - pr_debug("%s ep %p tid %u state %u\n", __func__, ep, ep->hwtid, - ep->com.state); + pr_debug("ep %p tid %u state %u\n", ep, ep->hwtid, ep->com.state); - c4iw_wake_up(&ep->com.wr_wait, -ECONNRESET); + c4iw_wake_up_noref(ep->com.wr_waitp, -ECONNRESET); out: sched(dev, skb); return 0; diff --git a/drivers/infiniband/hw/cxgb4/cq.c b/drivers/infiniband/hw/cxgb4/cq.c index be07da1997e6..8e2d490e757a 100644 --- a/drivers/infiniband/hw/cxgb4/cq.c +++ b/drivers/infiniband/hw/cxgb4/cq.c @@ -33,12 +33,12 @@ #include "iw_cxgb4.h" static int destroy_cq(struct c4iw_rdev *rdev, struct t4_cq *cq, - struct c4iw_dev_ucontext *uctx, struct sk_buff *skb) + struct c4iw_dev_ucontext *uctx, struct sk_buff *skb, + struct c4iw_wr_wait *wr_waitp) { struct fw_ri_res_wr *res_wr; struct fw_ri_res *res; int wr_len; - struct c4iw_wr_wait wr_wait; int ret; wr_len = sizeof *res_wr + sizeof *res; @@ -50,17 +50,14 @@ static int destroy_cq(struct c4iw_rdev *rdev, struct t4_cq *cq, FW_RI_RES_WR_NRES_V(1) | FW_WR_COMPL_F); res_wr->len16_pkd = cpu_to_be32(DIV_ROUND_UP(wr_len, 16)); - res_wr->cookie = (uintptr_t)&wr_wait; + res_wr->cookie = (uintptr_t)wr_waitp; res = res_wr->res; res->u.cq.restype = FW_RI_RES_TYPE_CQ; res->u.cq.op = FW_RI_RES_OP_RESET; res->u.cq.iqid = cpu_to_be32(cq->cqid); - c4iw_init_wr_wait(&wr_wait); - ret = c4iw_ofld_send(rdev, skb); - if (!ret) { - ret = c4iw_wait_for_reply(rdev, &wr_wait, 0, 0, __func__); - } + c4iw_init_wr_wait(wr_waitp); + ret = c4iw_ref_send_wait(rdev, skb, wr_waitp, 0, 0, __func__); kfree(cq->sw_queue); dma_free_coherent(&(rdev->lldi.pdev->dev), @@ -71,13 +68,13 @@ static int destroy_cq(struct c4iw_rdev *rdev, struct t4_cq *cq, } static int create_cq(struct c4iw_rdev *rdev, struct t4_cq *cq, - struct c4iw_dev_ucontext *uctx) + struct c4iw_dev_ucontext *uctx, + struct c4iw_wr_wait *wr_waitp) { struct fw_ri_res_wr *res_wr; struct fw_ri_res *res; int wr_len; int user = (uctx != &rdev->uctx); - struct c4iw_wr_wait wr_wait; int ret; struct sk_buff *skb; @@ -119,7 +116,7 @@ static int create_cq(struct c4iw_rdev *rdev, struct t4_cq *cq, FW_RI_RES_WR_NRES_V(1) | FW_WR_COMPL_F); res_wr->len16_pkd = cpu_to_be32(DIV_ROUND_UP(wr_len, 16)); - res_wr->cookie = (uintptr_t)&wr_wait; + res_wr->cookie = (uintptr_t)wr_waitp; res = res_wr->res; res->u.cq.restype = FW_RI_RES_TYPE_CQ; res->u.cq.op = FW_RI_RES_OP_WRITE; @@ -139,13 +136,8 @@ static int create_cq(struct c4iw_rdev *rdev, struct t4_cq *cq, res->u.cq.iqsize = cpu_to_be16(cq->size); res->u.cq.iqaddr = cpu_to_be64(cq->dma_addr); - c4iw_init_wr_wait(&wr_wait); - - ret = c4iw_ofld_send(rdev, skb); - if (ret) - goto err4; - pr_debug("%s wait_event wr_wait %p\n", __func__, &wr_wait); - ret = c4iw_wait_for_reply(rdev, &wr_wait, 0, 0, __func__); + c4iw_init_wr_wait(wr_waitp); + ret = c4iw_ref_send_wait(rdev, skb, wr_waitp, 0, 0, __func__); if (ret) goto err4; @@ -178,7 +170,7 @@ static void insert_recv_cqe(struct t4_wq *wq, struct t4_cq *cq) { struct t4_cqe cqe; - pr_debug("%s wq %p cq %p sw_cidx %u sw_pidx %u\n", __func__, + pr_debug("wq %p cq %p sw_cidx %u sw_pidx %u\n", wq, cq, cq->sw_cidx, cq->sw_pidx); memset(&cqe, 0, sizeof(cqe)); cqe.header = cpu_to_be32(CQE_STATUS_V(T4_ERR_SWFLUSH) | @@ -197,7 +189,7 @@ int c4iw_flush_rq(struct t4_wq *wq, struct t4_cq *cq, int count) int in_use = wq->rq.in_use - count; BUG_ON(in_use < 0); - pr_debug("%s wq %p cq %p rq.in_use %u skip count %u\n", __func__, + pr_debug("wq %p cq %p rq.in_use %u skip count %u\n", wq, cq, wq->rq.in_use, count); while (in_use--) { insert_recv_cqe(wq, cq); @@ -211,7 +203,7 @@ static void insert_sq_cqe(struct t4_wq *wq, struct t4_cq *cq, { struct t4_cqe cqe; - pr_debug("%s wq %p cq %p sw_cidx %u sw_pidx %u\n", __func__, + pr_debug("wq %p cq %p sw_cidx %u sw_pidx %u\n", wq, cq, cq->sw_cidx, cq->sw_pidx); memset(&cqe, 0, sizeof(cqe)); cqe.header = cpu_to_be32(CQE_STATUS_V(T4_ERR_SWFLUSH) | @@ -281,8 +273,8 @@ static void flush_completed_wrs(struct t4_wq *wq, struct t4_cq *cq) /* * Insert this completed cqe into the swcq. */ - pr_debug("%s moving cqe into swcq sq idx %u cq idx %u\n", - __func__, cidx, cq->sw_pidx); + pr_debug("moving cqe into swcq sq idx %u cq idx %u\n", + cidx, cq->sw_pidx); swsqe->cqe.header |= htonl(CQE_SWCQE_V(1)); cq->sw_queue[cq->sw_pidx] = swsqe->cqe; t4_swcq_produce(cq); @@ -337,7 +329,7 @@ void c4iw_flush_hw_cq(struct c4iw_cq *chp) struct t4_swsqe *swsqe; int ret; - pr_debug("%s cqid 0x%x\n", __func__, chp->cq.cqid); + pr_debug("cqid 0x%x\n", chp->cq.cqid); ret = t4_next_hw_cqe(&chp->cq, &hw_cqe); /* @@ -430,7 +422,7 @@ void c4iw_count_rcqes(struct t4_cq *cq, struct t4_wq *wq, int *count) u32 ptr; *count = 0; - pr_debug("%s count zero %d\n", __func__, *count); + pr_debug("count zero %d\n", *count); ptr = cq->sw_cidx; while (ptr != cq->sw_pidx) { cqe = &cq->sw_queue[ptr]; @@ -440,7 +432,7 @@ void c4iw_count_rcqes(struct t4_cq *cq, struct t4_wq *wq, int *count) if (++ptr == cq->size) ptr = 0; } - pr_debug("%s cq %p count %d\n", __func__, cq, *count); + pr_debug("cq %p count %d\n", cq, *count); } /* @@ -471,8 +463,8 @@ static int poll_cq(struct t4_wq *wq, struct t4_cq *cq, struct t4_cqe *cqe, if (ret) return ret; - pr_debug("%s CQE OVF %u qpid 0x%0x genbit %u type %u status 0x%0x opcode 0x%0x len 0x%0x wrid_hi_stag 0x%x wrid_low_msn 0x%x\n", - __func__, CQE_OVFBIT(hw_cqe), CQE_QPID(hw_cqe), + pr_debug("CQE OVF %u qpid 0x%0x genbit %u type %u status 0x%0x opcode 0x%0x len 0x%0x wrid_hi_stag 0x%x wrid_low_msn 0x%x\n", + CQE_OVFBIT(hw_cqe), CQE_QPID(hw_cqe), CQE_GENBIT(hw_cqe), CQE_TYPE(hw_cqe), CQE_STATUS(hw_cqe), CQE_OPCODE(hw_cqe), CQE_LEN(hw_cqe), CQE_WRID_HI(hw_cqe), CQE_WRID_LOW(hw_cqe)); @@ -603,8 +595,8 @@ static int poll_cq(struct t4_wq *wq, struct t4_cq *cq, struct t4_cqe *cqe, if (!SW_CQE(hw_cqe) && (CQE_WRID_SQ_IDX(hw_cqe) != wq->sq.cidx)) { struct t4_swsqe *swsqe; - pr_debug("%s out of order completion going in sw_sq at idx %u\n", - __func__, CQE_WRID_SQ_IDX(hw_cqe)); + pr_debug("out of order completion going in sw_sq at idx %u\n", + CQE_WRID_SQ_IDX(hw_cqe)); swsqe = &wq->sq.sw_sq[CQE_WRID_SQ_IDX(hw_cqe)]; swsqe->cqe = *hw_cqe; swsqe->complete = 1; @@ -638,13 +630,13 @@ proc_cqe: BUG_ON(wq->sq.in_use <= 0 && wq->sq.in_use >= wq->sq.size); wq->sq.cidx = (uint16_t)idx; - pr_debug("%s completing sq idx %u\n", __func__, wq->sq.cidx); + pr_debug("completing sq idx %u\n", wq->sq.cidx); *cookie = wq->sq.sw_sq[wq->sq.cidx].wr_id; if (c4iw_wr_log) c4iw_log_wr_stats(wq, hw_cqe); t4_sq_consume(wq); } else { - pr_debug("%s completing rq idx %u\n", __func__, wq->rq.cidx); + pr_debug("completing rq idx %u\n", wq->rq.cidx); *cookie = wq->rq.sw_rq[wq->rq.cidx].wr_id; BUG_ON(t4_rq_empty(wq)); if (c4iw_wr_log) @@ -661,12 +653,12 @@ flush_wq: skip_cqe: if (SW_CQE(hw_cqe)) { - pr_debug("%s cq %p cqid 0x%x skip sw cqe cidx %u\n", - __func__, cq, cq->cqid, cq->sw_cidx); + pr_debug("cq %p cqid 0x%x skip sw cqe cidx %u\n", + cq, cq->cqid, cq->sw_cidx); t4_swcq_consume(cq); } else { - pr_debug("%s cq %p cqid 0x%x skip hw cqe cidx %u\n", - __func__, cq, cq->cqid, cq->cidx); + pr_debug("cq %p cqid 0x%x skip hw cqe cidx %u\n", + cq, cq->cqid, cq->cidx); t4_hwcq_consume(cq); } return ret; @@ -712,8 +704,8 @@ static int c4iw_poll_cq_one(struct c4iw_cq *chp, struct ib_wc *wc) wc->vendor_err = CQE_STATUS(&cqe); wc->wc_flags = 0; - pr_debug("%s qpid 0x%x type %d opcode %d status 0x%x len %u wrid hi 0x%x lo 0x%x cookie 0x%llx\n", - __func__, CQE_QPID(&cqe), + pr_debug("qpid 0x%x type %d opcode %d status 0x%x len %u wrid hi 0x%x lo 0x%x cookie 0x%llx\n", + CQE_QPID(&cqe), CQE_TYPE(&cqe), CQE_OPCODE(&cqe), CQE_STATUS(&cqe), CQE_LEN(&cqe), CQE_WRID_HI(&cqe), CQE_WRID_LOW(&cqe), @@ -857,7 +849,7 @@ int c4iw_destroy_cq(struct ib_cq *ib_cq) struct c4iw_cq *chp; struct c4iw_ucontext *ucontext; - pr_debug("%s ib_cq %p\n", __func__, ib_cq); + pr_debug("ib_cq %p\n", ib_cq); chp = to_c4iw_cq(ib_cq); remove_handle(chp->rhp, &chp->rhp->cqidr, chp->cq.cqid); @@ -868,8 +860,8 @@ int c4iw_destroy_cq(struct ib_cq *ib_cq) : NULL; destroy_cq(&chp->rhp->rdev, &chp->cq, ucontext ? &ucontext->uctx : &chp->cq.rdev->uctx, - chp->destroy_skb); - chp->destroy_skb = NULL; + chp->destroy_skb, chp->wr_waitp); + c4iw_put_wr_wait(chp->wr_waitp); kfree(chp); return 0; } @@ -889,7 +881,7 @@ struct ib_cq *c4iw_create_cq(struct ib_device *ibdev, size_t memsize, hwentries; struct c4iw_mm_entry *mm, *mm2; - pr_debug("%s ib_dev %p entries %d\n", __func__, ibdev, entries); + pr_debug("ib_dev %p entries %d\n", ibdev, entries); if (attr->flags) return ERR_PTR(-EINVAL); @@ -901,12 +893,18 @@ struct ib_cq *c4iw_create_cq(struct ib_device *ibdev, chp = kzalloc(sizeof(*chp), GFP_KERNEL); if (!chp) return ERR_PTR(-ENOMEM); + chp->wr_waitp = c4iw_alloc_wr_wait(GFP_KERNEL); + if (!chp->wr_waitp) { + ret = -ENOMEM; + goto err_free_chp; + } + c4iw_init_wr_wait(chp->wr_waitp); wr_len = sizeof(struct fw_ri_res_wr) + sizeof(struct fw_ri_res); chp->destroy_skb = alloc_skb(wr_len, GFP_KERNEL); if (!chp->destroy_skb) { ret = -ENOMEM; - goto err1; + goto err_free_wr_wait; } if (ib_context) @@ -947,9 +945,10 @@ struct ib_cq *c4iw_create_cq(struct ib_device *ibdev, chp->cq.vector = vector; ret = create_cq(&rhp->rdev, &chp->cq, - ucontext ? &ucontext->uctx : &rhp->rdev.uctx); + ucontext ? &ucontext->uctx : &rhp->rdev.uctx, + chp->wr_waitp); if (ret) - goto err2; + goto err_free_skb; chp->rhp = rhp; chp->cq.size--; /* status page */ @@ -960,16 +959,16 @@ struct ib_cq *c4iw_create_cq(struct ib_device *ibdev, init_waitqueue_head(&chp->wait); ret = insert_handle(rhp, &rhp->cqidr, chp, chp->cq.cqid); if (ret) - goto err3; + goto err_destroy_cq; if (ucontext) { ret = -ENOMEM; mm = kmalloc(sizeof *mm, GFP_KERNEL); if (!mm) - goto err4; + goto err_remove_handle; mm2 = kmalloc(sizeof *mm2, GFP_KERNEL); if (!mm2) - goto err5; + goto err_free_mm; uresp.qid_mask = rhp->rdev.cqmask; uresp.cqid = chp->cq.cqid; @@ -984,7 +983,7 @@ struct ib_cq *c4iw_create_cq(struct ib_device *ibdev, ret = ib_copy_to_udata(udata, &uresp, sizeof(uresp) - sizeof(uresp.reserved)); if (ret) - goto err6; + goto err_free_mm2; mm->key = uresp.key; mm->addr = virt_to_phys(chp->cq.queue); @@ -996,23 +995,25 @@ struct ib_cq *c4iw_create_cq(struct ib_device *ibdev, mm2->len = PAGE_SIZE; insert_mmap(ucontext, mm2); } - pr_debug("%s cqid 0x%0x chp %p size %u memsize %zu, dma_addr 0x%0llx\n", - __func__, chp->cq.cqid, chp, chp->cq.size, + pr_debug("cqid 0x%0x chp %p size %u memsize %zu, dma_addr 0x%0llx\n", + chp->cq.cqid, chp, chp->cq.size, chp->cq.memsize, (unsigned long long)chp->cq.dma_addr); return &chp->ibcq; -err6: +err_free_mm2: kfree(mm2); -err5: +err_free_mm: kfree(mm); -err4: +err_remove_handle: remove_handle(rhp, &rhp->cqidr, chp->cq.cqid); -err3: +err_destroy_cq: destroy_cq(&chp->rhp->rdev, &chp->cq, ucontext ? &ucontext->uctx : &rhp->rdev.uctx, - chp->destroy_skb); -err2: + chp->destroy_skb, chp->wr_waitp); +err_free_skb: kfree_skb(chp->destroy_skb); -err1: +err_free_wr_wait: + c4iw_put_wr_wait(chp->wr_waitp); +err_free_chp: kfree(chp); return ERR_PTR(ret); } diff --git a/drivers/infiniband/hw/cxgb4/device.c b/drivers/infiniband/hw/cxgb4/device.c index fc886f81b885..33bfddf3b064 100644 --- a/drivers/infiniband/hw/cxgb4/device.c +++ b/drivers/infiniband/hw/cxgb4/device.c @@ -811,8 +811,8 @@ static int c4iw_rdev_open(struct c4iw_rdev *rdev) rdev->qpmask = rdev->lldi.udb_density - 1; rdev->cqmask = rdev->lldi.ucq_density - 1; - pr_debug("%s dev %s stag start 0x%0x size 0x%0x num stags %d pbl start 0x%0x size 0x%0x rq start 0x%0x size 0x%0x qp qid start %u size %u cq qid start %u size %u\n", - __func__, pci_name(rdev->lldi.pdev), rdev->lldi.vr->stag.start, + pr_debug("dev %s stag start 0x%0x size 0x%0x num stags %d pbl start 0x%0x size 0x%0x rq start 0x%0x size 0x%0x qp qid start %u size %u cq qid start %u size %u\n", + pci_name(rdev->lldi.pdev), rdev->lldi.vr->stag.start, rdev->lldi.vr->stag.size, c4iw_num_stags(rdev), rdev->lldi.vr->pbl.start, rdev->lldi.vr->pbl.size, rdev->lldi.vr->rq.start, @@ -935,7 +935,7 @@ static void c4iw_dealloc(struct uld_ctx *ctx) static void c4iw_remove(struct uld_ctx *ctx) { - pr_debug("%s c4iw_dev %p\n", __func__, ctx->dev); + pr_debug("c4iw_dev %p\n", ctx->dev); c4iw_unregister_device(ctx->dev); c4iw_dealloc(ctx); } @@ -969,8 +969,8 @@ static struct c4iw_dev *c4iw_alloc(const struct cxgb4_lld_info *infop) devp->rdev.lldi = *infop; /* init various hw-queue params based on lld info */ - pr_debug("%s: Ing. padding boundary is %d, egrsstatuspagesize = %d\n", - __func__, devp->rdev.lldi.sge_ingpadboundary, + pr_debug("Ing. padding boundary is %d, egrsstatuspagesize = %d\n", + devp->rdev.lldi.sge_ingpadboundary, devp->rdev.lldi.sge_egrstatuspagesize); devp->rdev.hw_queue.t4_eq_status_entries = @@ -1069,8 +1069,8 @@ static void *c4iw_uld_add(const struct cxgb4_lld_info *infop) } ctx->lldi = *infop; - pr_debug("%s found device %s nchan %u nrxq %u ntxq %u nports %u\n", - __func__, pci_name(ctx->lldi.pdev), + pr_debug("found device %s nchan %u nrxq %u ntxq %u nports %u\n", + pci_name(ctx->lldi.pdev), ctx->lldi.nchan, ctx->lldi.nrxq, ctx->lldi.ntxq, ctx->lldi.nports); @@ -1102,8 +1102,8 @@ static inline struct sk_buff *copy_gl_to_skb_pkt(const struct pkt_gl *gl, if (unlikely(!skb)) return NULL; - __skb_put(skb, gl->tot_len + sizeof(struct cpl_pass_accept_req) + - sizeof(struct rss_header) - pktshift); + __skb_put(skb, gl->tot_len + sizeof(struct cpl_pass_accept_req) + + sizeof(struct rss_header) - pktshift); /* * This skb will contain: @@ -1203,7 +1203,7 @@ static int c4iw_uld_state_change(void *handle, enum cxgb4_state new_state) { struct uld_ctx *ctx = handle; - pr_debug("%s new_state %u\n", __func__, new_state); + pr_debug("new_state %u\n", new_state); switch (new_state) { case CXGB4_STATE_UP: pr_info("%s: Up\n", pci_name(ctx->lldi.pdev)); @@ -1518,6 +1518,27 @@ static struct cxgb4_uld_info c4iw_uld_info = { .control = c4iw_uld_control, }; +void _c4iw_free_wr_wait(struct kref *kref) +{ + struct c4iw_wr_wait *wr_waitp; + + wr_waitp = container_of(kref, struct c4iw_wr_wait, kref); + pr_debug("Free wr_wait %p\n", wr_waitp); + kfree(wr_waitp); +} + +struct c4iw_wr_wait *c4iw_alloc_wr_wait(gfp_t gfp) +{ + struct c4iw_wr_wait *wr_waitp; + + wr_waitp = kzalloc(sizeof(*wr_waitp), gfp); + if (wr_waitp) { + kref_init(&wr_waitp->kref); + pr_debug("wr_wait %p\n", wr_waitp); + } + return wr_waitp; +} + static int __init c4iw_init_module(void) { int err; diff --git a/drivers/infiniband/hw/cxgb4/ev.c b/drivers/infiniband/hw/cxgb4/ev.c index 8f963df0bffc..b8c7cc938bce 100644 --- a/drivers/infiniband/hw/cxgb4/ev.c +++ b/drivers/infiniband/hw/cxgb4/ev.c @@ -234,7 +234,7 @@ int c4iw_ev_handler(struct c4iw_dev *dev, u32 qid) if (atomic_dec_and_test(&chp->refcnt)) wake_up(&chp->wait); } else { - pr_debug("%s unknown cqid 0x%x\n", __func__, qid); + pr_warn("%s unknown cqid 0x%x\n", __func__, qid); spin_unlock_irqrestore(&dev->lock, flag); } return 0; diff --git a/drivers/infiniband/hw/cxgb4/iw_cxgb4.h b/drivers/infiniband/hw/cxgb4/iw_cxgb4.h index 819a30635d53..788ddb6aa57b 100644 --- a/drivers/infiniband/hw/cxgb4/iw_cxgb4.h +++ b/drivers/infiniband/hw/cxgb4/iw_cxgb4.h @@ -202,18 +202,50 @@ static inline int c4iw_num_stags(struct c4iw_rdev *rdev) struct c4iw_wr_wait { struct completion completion; int ret; + struct kref kref; }; +void _c4iw_free_wr_wait(struct kref *kref); + +static inline void c4iw_put_wr_wait(struct c4iw_wr_wait *wr_waitp) +{ + pr_debug("wr_wait %p ref before put %u\n", wr_waitp, + kref_read(&wr_waitp->kref)); + WARN_ON(kref_read(&wr_waitp->kref) == 0); + kref_put(&wr_waitp->kref, _c4iw_free_wr_wait); +} + +static inline void c4iw_get_wr_wait(struct c4iw_wr_wait *wr_waitp) +{ + pr_debug("wr_wait %p ref before get %u\n", wr_waitp, + kref_read(&wr_waitp->kref)); + WARN_ON(kref_read(&wr_waitp->kref) == 0); + kref_get(&wr_waitp->kref); +} + static inline void c4iw_init_wr_wait(struct c4iw_wr_wait *wr_waitp) { wr_waitp->ret = 0; init_completion(&wr_waitp->completion); } -static inline void c4iw_wake_up(struct c4iw_wr_wait *wr_waitp, int ret) +static inline void _c4iw_wake_up(struct c4iw_wr_wait *wr_waitp, int ret, + bool deref) { wr_waitp->ret = ret; complete(&wr_waitp->completion); + if (deref) + c4iw_put_wr_wait(wr_waitp); +} + +static inline void c4iw_wake_up_noref(struct c4iw_wr_wait *wr_waitp, int ret) +{ + _c4iw_wake_up(wr_waitp, ret, false); +} + +static inline void c4iw_wake_up_deref(struct c4iw_wr_wait *wr_waitp, int ret) +{ + _c4iw_wake_up(wr_waitp, ret, true); } static inline int c4iw_wait_for_reply(struct c4iw_rdev *rdev, @@ -230,18 +262,40 @@ static inline int c4iw_wait_for_reply(struct c4iw_rdev *rdev, ret = wait_for_completion_timeout(&wr_waitp->completion, C4IW_WR_TO); if (!ret) { - pr_debug("%s - Device %s not responding (disabling device) - tid %u qpid %u\n", - func, pci_name(rdev->lldi.pdev), hwtid, qpid); + pr_err("%s - Device %s not responding (disabling device) - tid %u qpid %u\n", + func, pci_name(rdev->lldi.pdev), hwtid, qpid); rdev->flags |= T4_FATAL_ERROR; wr_waitp->ret = -EIO; + goto out; } -out: if (wr_waitp->ret) pr_debug("%s: FW reply %d tid %u qpid %u\n", pci_name(rdev->lldi.pdev), wr_waitp->ret, hwtid, qpid); +out: return wr_waitp->ret; } +int c4iw_ofld_send(struct c4iw_rdev *rdev, struct sk_buff *skb); + +static inline int c4iw_ref_send_wait(struct c4iw_rdev *rdev, + struct sk_buff *skb, + struct c4iw_wr_wait *wr_waitp, + u32 hwtid, u32 qpid, + const char *func) +{ + int ret; + + pr_debug("%s wr_wait %p hwtid %u qpid %u\n", func, wr_waitp, hwtid, + qpid); + c4iw_get_wr_wait(wr_waitp); + ret = c4iw_ofld_send(rdev, skb); + if (ret) { + c4iw_put_wr_wait(wr_waitp); + return ret; + } + return c4iw_wait_for_reply(rdev, wr_waitp, hwtid, qpid, func); +} + enum db_state { NORMAL = 0, FLOW_CONTROL = 1, @@ -394,6 +448,7 @@ struct c4iw_mr { dma_addr_t mpl_addr; u32 max_mpl_len; u32 mpl_len; + struct c4iw_wr_wait *wr_waitp; }; static inline struct c4iw_mr *to_c4iw_mr(struct ib_mr *ibmr) @@ -407,6 +462,7 @@ struct c4iw_mw { struct sk_buff *dereg_skb; u64 kva; struct tpt_attributes attr; + struct c4iw_wr_wait *wr_waitp; }; static inline struct c4iw_mw *to_c4iw_mw(struct ib_mw *ibmw) @@ -423,6 +479,7 @@ struct c4iw_cq { spinlock_t comp_handler_lock; atomic_t refcnt; wait_queue_head_t wait; + struct c4iw_wr_wait *wr_waitp; }; static inline struct c4iw_cq *to_c4iw_cq(struct ib_cq *ibcq) @@ -480,10 +537,10 @@ struct c4iw_qp { struct mutex mutex; struct kref kref; wait_queue_head_t wait; - struct timer_list timer; int sq_sig_all; struct work_struct free_work; struct c4iw_ucontext *ucontext; + struct c4iw_wr_wait *wr_waitp; }; static inline struct c4iw_qp *to_c4iw_qp(struct ib_qp *ibqp) @@ -537,8 +594,7 @@ static inline struct c4iw_mm_entry *remove_mmap(struct c4iw_ucontext *ucontext, if (mm->key == key && mm->len == len) { list_del_init(&mm->entry); spin_unlock(&ucontext->mmap_lock); - pr_debug("%s key 0x%x addr 0x%llx len %d\n", - __func__, key, + pr_debug("key 0x%x addr 0x%llx len %d\n", key, (unsigned long long)mm->addr, mm->len); return mm; } @@ -551,8 +607,8 @@ static inline void insert_mmap(struct c4iw_ucontext *ucontext, struct c4iw_mm_entry *mm) { spin_lock(&ucontext->mmap_lock); - pr_debug("%s key 0x%x addr 0x%llx len %d\n", - __func__, mm->key, (unsigned long long)mm->addr, mm->len); + pr_debug("key 0x%x addr 0x%llx len %d\n", + mm->key, (unsigned long long)mm->addr, mm->len); list_add_tail(&mm->entry, &ucontext->mmaps); spin_unlock(&ucontext->mmap_lock); } @@ -671,16 +727,14 @@ enum c4iw_mmid_state { #define MPA_V2_IRD_ORD_MASK 0x3FFF #define c4iw_put_ep(ep) { \ - pr_debug("put_ep (via %s:%u) ep %p refcnt %d\n", \ - __func__, __LINE__, \ + pr_debug("put_ep ep %p refcnt %d\n", \ ep, kref_read(&((ep)->kref))); \ WARN_ON(kref_read(&((ep)->kref)) < 1); \ kref_put(&((ep)->kref), _c4iw_free_ep); \ } #define c4iw_get_ep(ep) { \ - pr_debug("get_ep (via %s:%u) ep %p, refcnt %d\n", \ - __func__, __LINE__, \ + pr_debug("get_ep ep %p, refcnt %d\n", \ ep, kref_read(&((ep)->kref))); \ kref_get(&((ep)->kref)); \ } @@ -841,7 +895,7 @@ struct c4iw_ep_common { struct mutex mutex; struct sockaddr_storage local_addr; struct sockaddr_storage remote_addr; - struct c4iw_wr_wait wr_wait; + struct c4iw_wr_wait *wr_waitp; unsigned long flags; unsigned long history; }; @@ -990,7 +1044,6 @@ u32 c4iw_pblpool_alloc(struct c4iw_rdev *rdev, int size); void c4iw_pblpool_free(struct c4iw_rdev *rdev, u32 addr, int size); u32 c4iw_ocqp_pool_alloc(struct c4iw_rdev *rdev, int size); void c4iw_ocqp_pool_free(struct c4iw_rdev *rdev, u32 addr, int size); -int c4iw_ofld_send(struct c4iw_rdev *rdev, struct sk_buff *skb); void c4iw_flush_hw_cq(struct c4iw_cq *chp); void c4iw_count_rcqes(struct t4_cq *cq, struct t4_wq *wq, int *count); int c4iw_ep_disconnect(struct c4iw_ep *ep, int abrupt, gfp_t gfp); @@ -1018,5 +1071,6 @@ extern int db_fc_threshold; extern int db_coalescing_threshold; extern int use_dsgl; void c4iw_invalidate_mr(struct c4iw_dev *rhp, u32 rkey); +struct c4iw_wr_wait *c4iw_alloc_wr_wait(gfp_t gfp); #endif diff --git a/drivers/infiniband/hw/cxgb4/mem.c b/drivers/infiniband/hw/cxgb4/mem.c index c2fba76becd4..7e0eb201cc26 100644 --- a/drivers/infiniband/hw/cxgb4/mem.c +++ b/drivers/infiniband/hw/cxgb4/mem.c @@ -60,18 +60,18 @@ static int mr_exceeds_hw_limits(struct c4iw_dev *dev, u64 length) static int _c4iw_write_mem_dma_aligned(struct c4iw_rdev *rdev, u32 addr, u32 len, dma_addr_t data, - int wait, struct sk_buff *skb) + struct sk_buff *skb, + struct c4iw_wr_wait *wr_waitp) { struct ulp_mem_io *req; struct ulptx_sgl *sgl; u8 wr_len; int ret = 0; - struct c4iw_wr_wait wr_wait; addr &= 0x7FFFFFF; - if (wait) - c4iw_init_wr_wait(&wr_wait); + if (wr_waitp) + c4iw_init_wr_wait(wr_waitp); wr_len = roundup(sizeof(*req) + sizeof(*sgl), 16); if (!skb) { @@ -84,8 +84,8 @@ static int _c4iw_write_mem_dma_aligned(struct c4iw_rdev *rdev, u32 addr, req = __skb_put_zero(skb, wr_len); INIT_ULPTX_WR(req, wr_len, 0, 0); req->wr.wr_hi = cpu_to_be32(FW_WR_OP_V(FW_ULPTX_WR) | - (wait ? FW_WR_COMPL_F : 0)); - req->wr.wr_lo = wait ? (__force __be64)(unsigned long) &wr_wait : 0L; + (wr_waitp ? FW_WR_COMPL_F : 0)); + req->wr.wr_lo = wr_waitp ? (__force __be64)(unsigned long)wr_waitp : 0L; req->wr.wr_mid = cpu_to_be32(FW_WR_LEN16_V(DIV_ROUND_UP(wr_len, 16))); req->cmd = cpu_to_be32(ULPTX_CMD_V(ULP_TX_MEM_WRITE) | T5_ULP_MEMIO_ORDER_V(1) | @@ -100,22 +100,21 @@ static int _c4iw_write_mem_dma_aligned(struct c4iw_rdev *rdev, u32 addr, sgl->len0 = cpu_to_be32(len); sgl->addr0 = cpu_to_be64(data); - ret = c4iw_ofld_send(rdev, skb); - if (ret) - return ret; - if (wait) - ret = c4iw_wait_for_reply(rdev, &wr_wait, 0, 0, __func__); + if (wr_waitp) + ret = c4iw_ref_send_wait(rdev, skb, wr_waitp, 0, 0, __func__); + else + ret = c4iw_ofld_send(rdev, skb); return ret; } static int _c4iw_write_mem_inline(struct c4iw_rdev *rdev, u32 addr, u32 len, - void *data, struct sk_buff *skb) + void *data, struct sk_buff *skb, + struct c4iw_wr_wait *wr_waitp) { struct ulp_mem_io *req; struct ulptx_idata *sc; u8 wr_len, *to_dp, *from_dp; int copy_len, num_wqe, i, ret = 0; - struct c4iw_wr_wait wr_wait; __be32 cmd = cpu_to_be32(ULPTX_CMD_V(ULP_TX_MEM_WRITE)); if (is_t4(rdev->lldi.adapter_type)) @@ -124,9 +123,9 @@ static int _c4iw_write_mem_inline(struct c4iw_rdev *rdev, u32 addr, u32 len, cmd |= cpu_to_be32(T5_ULP_MEMIO_IMM_F); addr &= 0x7FFFFFF; - pr_debug("%s addr 0x%x len %u\n", __func__, addr, len); + pr_debug("addr 0x%x len %u\n", addr, len); num_wqe = DIV_ROUND_UP(len, C4IW_MAX_INLINE_SIZE); - c4iw_init_wr_wait(&wr_wait); + c4iw_init_wr_wait(wr_waitp); for (i = 0; i < num_wqe; i++) { copy_len = len > C4IW_MAX_INLINE_SIZE ? C4IW_MAX_INLINE_SIZE : @@ -147,7 +146,7 @@ static int _c4iw_write_mem_inline(struct c4iw_rdev *rdev, u32 addr, u32 len, if (i == (num_wqe-1)) { req->wr.wr_hi = cpu_to_be32(FW_WR_OP_V(FW_ULPTX_WR) | FW_WR_COMPL_F); - req->wr.wr_lo = (__force __be64)(unsigned long)&wr_wait; + req->wr.wr_lo = (__force __be64)(unsigned long)wr_waitp; } else req->wr.wr_hi = cpu_to_be32(FW_WR_OP_V(FW_ULPTX_WR)); req->wr.wr_mid = cpu_to_be32( @@ -173,19 +172,23 @@ static int _c4iw_write_mem_inline(struct c4iw_rdev *rdev, u32 addr, u32 len, if (copy_len % T4_ULPTX_MIN_IO) memset(to_dp + copy_len, 0, T4_ULPTX_MIN_IO - (copy_len % T4_ULPTX_MIN_IO)); - ret = c4iw_ofld_send(rdev, skb); - skb = NULL; + if (i == (num_wqe-1)) + ret = c4iw_ref_send_wait(rdev, skb, wr_waitp, 0, 0, + __func__); + else + ret = c4iw_ofld_send(rdev, skb); if (ret) - return ret; + break; + skb = NULL; len -= C4IW_MAX_INLINE_SIZE; } - ret = c4iw_wait_for_reply(rdev, &wr_wait, 0, 0, __func__); return ret; } static int _c4iw_write_mem_dma(struct c4iw_rdev *rdev, u32 addr, u32 len, - void *data, struct sk_buff *skb) + void *data, struct sk_buff *skb, + struct c4iw_wr_wait *wr_waitp) { u32 remain = len; u32 dmalen; @@ -208,7 +211,7 @@ static int _c4iw_write_mem_dma(struct c4iw_rdev *rdev, u32 addr, u32 len, dmalen = T4_ULPTX_MAX_DMA; remain -= dmalen; ret = _c4iw_write_mem_dma_aligned(rdev, addr, dmalen, daddr, - !remain, skb); + skb, remain ? NULL : wr_waitp); if (ret) goto out; addr += dmalen >> 5; @@ -216,7 +219,8 @@ static int _c4iw_write_mem_dma(struct c4iw_rdev *rdev, u32 addr, u32 len, daddr += dmalen; } if (remain) - ret = _c4iw_write_mem_inline(rdev, addr, remain, data, skb); + ret = _c4iw_write_mem_inline(rdev, addr, remain, data, skb, + wr_waitp); out: dma_unmap_single(&rdev->lldi.pdev->dev, save, len, DMA_TO_DEVICE); return ret; @@ -227,23 +231,33 @@ out: * If data is NULL, clear len byte of memory to zero. */ static int write_adapter_mem(struct c4iw_rdev *rdev, u32 addr, u32 len, - void *data, struct sk_buff *skb) + void *data, struct sk_buff *skb, + struct c4iw_wr_wait *wr_waitp) { - if (rdev->lldi.ulptx_memwrite_dsgl && use_dsgl) { - if (len > inline_threshold) { - if (_c4iw_write_mem_dma(rdev, addr, len, data, skb)) { - pr_warn_ratelimited("%s: dma map failure (non fatal)\n", - pci_name(rdev->lldi.pdev)); - return _c4iw_write_mem_inline(rdev, addr, len, - data, skb); - } else { - return 0; - } - } else - return _c4iw_write_mem_inline(rdev, addr, - len, data, skb); - } else - return _c4iw_write_mem_inline(rdev, addr, len, data, skb); + int ret; + + if (!rdev->lldi.ulptx_memwrite_dsgl || !use_dsgl) { + ret = _c4iw_write_mem_inline(rdev, addr, len, data, skb, + wr_waitp); + goto out; + } + + if (len <= inline_threshold) { + ret = _c4iw_write_mem_inline(rdev, addr, len, data, skb, + wr_waitp); + goto out; + } + + ret = _c4iw_write_mem_dma(rdev, addr, len, data, skb, wr_waitp); + if (ret) { + pr_warn_ratelimited("%s: dma map failure (non fatal)\n", + pci_name(rdev->lldi.pdev)); + ret = _c4iw_write_mem_inline(rdev, addr, len, data, skb, + wr_waitp); + } +out: + return ret; + } /* @@ -257,7 +271,7 @@ static int write_tpt_entry(struct c4iw_rdev *rdev, u32 reset_tpt_entry, enum fw_ri_stag_type type, enum fw_ri_mem_perms perm, int bind_enabled, u32 zbva, u64 to, u64 len, u8 page_size, u32 pbl_size, u32 pbl_addr, - struct sk_buff *skb) + struct sk_buff *skb, struct c4iw_wr_wait *wr_waitp) { int err; struct fw_ri_tpte tpt; @@ -285,8 +299,8 @@ static int write_tpt_entry(struct c4iw_rdev *rdev, u32 reset_tpt_entry, mutex_unlock(&rdev->stats.lock); *stag = (stag_idx << 8) | (atomic_inc_return(&key) & 0xff); } - pr_debug("%s stag_state 0x%0x type 0x%0x pdid 0x%0x, stag_idx 0x%x\n", - __func__, stag_state, type, pdid, stag_idx); + pr_debug("stag_state 0x%0x type 0x%0x pdid 0x%0x, stag_idx 0x%x\n", + stag_state, type, pdid, stag_idx); /* write TPT entry */ if (reset_tpt_entry) @@ -311,7 +325,7 @@ static int write_tpt_entry(struct c4iw_rdev *rdev, u32 reset_tpt_entry, } err = write_adapter_mem(rdev, stag_idx + (rdev->lldi.vr->stag.start >> 5), - sizeof(tpt), &tpt, skb); + sizeof(tpt), &tpt, skb, wr_waitp); if (reset_tpt_entry) { c4iw_put_resource(&rdev->resource.tpt_table, stag_idx); @@ -323,45 +337,50 @@ static int write_tpt_entry(struct c4iw_rdev *rdev, u32 reset_tpt_entry, } static int write_pbl(struct c4iw_rdev *rdev, __be64 *pbl, - u32 pbl_addr, u32 pbl_size) + u32 pbl_addr, u32 pbl_size, struct c4iw_wr_wait *wr_waitp) { int err; - pr_debug("%s *pdb_addr 0x%x, pbl_base 0x%x, pbl_size %d\n", - __func__, pbl_addr, rdev->lldi.vr->pbl.start, + pr_debug("*pdb_addr 0x%x, pbl_base 0x%x, pbl_size %d\n", + pbl_addr, rdev->lldi.vr->pbl.start, pbl_size); - err = write_adapter_mem(rdev, pbl_addr >> 5, pbl_size << 3, pbl, NULL); + err = write_adapter_mem(rdev, pbl_addr >> 5, pbl_size << 3, pbl, NULL, + wr_waitp); return err; } static int dereg_mem(struct c4iw_rdev *rdev, u32 stag, u32 pbl_size, - u32 pbl_addr, struct sk_buff *skb) + u32 pbl_addr, struct sk_buff *skb, + struct c4iw_wr_wait *wr_waitp) { return write_tpt_entry(rdev, 1, &stag, 0, 0, 0, 0, 0, 0, 0UL, 0, 0, - pbl_size, pbl_addr, skb); + pbl_size, pbl_addr, skb, wr_waitp); } -static int allocate_window(struct c4iw_rdev *rdev, u32 * stag, u32 pdid) +static int allocate_window(struct c4iw_rdev *rdev, u32 *stag, u32 pdid, + struct c4iw_wr_wait *wr_waitp) { *stag = T4_STAG_UNSET; return write_tpt_entry(rdev, 0, stag, 0, pdid, FW_RI_STAG_MW, 0, 0, 0, - 0UL, 0, 0, 0, 0, NULL); + 0UL, 0, 0, 0, 0, NULL, wr_waitp); } static int deallocate_window(struct c4iw_rdev *rdev, u32 stag, - struct sk_buff *skb) + struct sk_buff *skb, + struct c4iw_wr_wait *wr_waitp) { return write_tpt_entry(rdev, 1, &stag, 0, 0, 0, 0, 0, 0, 0UL, 0, 0, 0, - 0, skb); + 0, skb, wr_waitp); } static int allocate_stag(struct c4iw_rdev *rdev, u32 *stag, u32 pdid, - u32 pbl_size, u32 pbl_addr) + u32 pbl_size, u32 pbl_addr, + struct c4iw_wr_wait *wr_waitp) { *stag = T4_STAG_UNSET; return write_tpt_entry(rdev, 0, stag, 0, pdid, FW_RI_STAG_NSMR, 0, 0, 0, - 0UL, 0, 0, pbl_size, pbl_addr, NULL); + 0UL, 0, 0, pbl_size, pbl_addr, NULL, wr_waitp); } static int finish_mem_reg(struct c4iw_mr *mhp, u32 stag) @@ -372,7 +391,7 @@ static int finish_mem_reg(struct c4iw_mr *mhp, u32 stag) mhp->attr.stag = stag; mmid = stag >> 8; mhp->ibmr.rkey = mhp->ibmr.lkey = stag; - pr_debug("%s mmid 0x%x mhp %p\n", __func__, mmid, mhp); + pr_debug("mmid 0x%x mhp %p\n", mmid, mhp); return insert_handle(mhp->rhp, &mhp->rhp->mmidr, mhp, mmid); } @@ -388,14 +407,15 @@ static int register_mem(struct c4iw_dev *rhp, struct c4iw_pd *php, mhp->attr.mw_bind_enable, mhp->attr.zbva, mhp->attr.va_fbo, mhp->attr.len ? mhp->attr.len : -1, shift - 12, - mhp->attr.pbl_size, mhp->attr.pbl_addr, NULL); + mhp->attr.pbl_size, mhp->attr.pbl_addr, NULL, + mhp->wr_waitp); if (ret) return ret; ret = finish_mem_reg(mhp, stag); if (ret) { dereg_mem(&rhp->rdev, mhp->attr.stag, mhp->attr.pbl_size, - mhp->attr.pbl_addr, mhp->dereg_skb); + mhp->attr.pbl_addr, mhp->dereg_skb, mhp->wr_waitp); mhp->dereg_skb = NULL; } return ret; @@ -422,18 +442,24 @@ struct ib_mr *c4iw_get_dma_mr(struct ib_pd *pd, int acc) int ret; u32 stag = T4_STAG_UNSET; - pr_debug("%s ib_pd %p\n", __func__, pd); + pr_debug("ib_pd %p\n", pd); php = to_c4iw_pd(pd); rhp = php->rhp; mhp = kzalloc(sizeof(*mhp), GFP_KERNEL); if (!mhp) return ERR_PTR(-ENOMEM); + mhp->wr_waitp = c4iw_alloc_wr_wait(GFP_KERNEL); + if (!mhp->wr_waitp) { + ret = -ENOMEM; + goto err_free_mhp; + } + c4iw_init_wr_wait(mhp->wr_waitp); mhp->dereg_skb = alloc_skb(SGE_MAX_WR_LEN, GFP_KERNEL); if (!mhp->dereg_skb) { ret = -ENOMEM; - goto err0; + goto err_free_wr_wait; } mhp->rhp = rhp; @@ -449,20 +475,22 @@ struct ib_mr *c4iw_get_dma_mr(struct ib_pd *pd, int acc) ret = write_tpt_entry(&rhp->rdev, 0, &stag, 1, php->pdid, FW_RI_STAG_NSMR, mhp->attr.perms, mhp->attr.mw_bind_enable, 0, 0, ~0ULL, 0, 0, 0, - NULL); + NULL, mhp->wr_waitp); if (ret) - goto err1; + goto err_free_skb; ret = finish_mem_reg(mhp, stag); if (ret) - goto err2; + goto err_dereg_mem; return &mhp->ibmr; -err2: +err_dereg_mem: dereg_mem(&rhp->rdev, mhp->attr.stag, mhp->attr.pbl_size, - mhp->attr.pbl_addr, mhp->dereg_skb); -err1: + mhp->attr.pbl_addr, mhp->dereg_skb, mhp->wr_waitp); +err_free_wr_wait: + c4iw_put_wr_wait(mhp->wr_waitp); +err_free_skb: kfree_skb(mhp->dereg_skb); -err0: +err_free_mhp: kfree(mhp); return ERR_PTR(ret); } @@ -473,13 +501,13 @@ struct ib_mr *c4iw_reg_user_mr(struct ib_pd *pd, u64 start, u64 length, __be64 *pages; int shift, n, len; int i, k, entry; - int err = 0; + int err = -ENOMEM; struct scatterlist *sg; struct c4iw_dev *rhp; struct c4iw_pd *php; struct c4iw_mr *mhp; - pr_debug("%s ib_pd %p\n", __func__, pd); + pr_debug("ib_pd %p\n", pd); if (length == ~0ULL) return ERR_PTR(-EINVAL); @@ -496,34 +524,31 @@ struct ib_mr *c4iw_reg_user_mr(struct ib_pd *pd, u64 start, u64 length, mhp = kzalloc(sizeof(*mhp), GFP_KERNEL); if (!mhp) return ERR_PTR(-ENOMEM); + mhp->wr_waitp = c4iw_alloc_wr_wait(GFP_KERNEL); + if (!mhp->wr_waitp) + goto err_free_mhp; mhp->dereg_skb = alloc_skb(SGE_MAX_WR_LEN, GFP_KERNEL); - if (!mhp->dereg_skb) { - kfree(mhp); - return ERR_PTR(-ENOMEM); - } + if (!mhp->dereg_skb) + goto err_free_wr_wait; mhp->rhp = rhp; mhp->umem = ib_umem_get(pd->uobject->context, start, length, acc, 0); - if (IS_ERR(mhp->umem)) { - err = PTR_ERR(mhp->umem); - kfree_skb(mhp->dereg_skb); - kfree(mhp); - return ERR_PTR(err); - } + if (IS_ERR(mhp->umem)) + goto err_free_skb; shift = mhp->umem->page_shift; n = mhp->umem->nmap; err = alloc_pbl(mhp, n); if (err) - goto err; + goto err_umem_release; pages = (__be64 *) __get_free_page(GFP_KERNEL); if (!pages) { err = -ENOMEM; - goto err_pbl; + goto err_pbl_free; } i = n = 0; @@ -536,7 +561,8 @@ struct ib_mr *c4iw_reg_user_mr(struct ib_pd *pd, u64 start, u64 length, if (i == PAGE_SIZE / sizeof *pages) { err = write_pbl(&mhp->rhp->rdev, pages, - mhp->attr.pbl_addr + (n << 3), i); + mhp->attr.pbl_addr + (n << 3), i, + mhp->wr_waitp); if (err) goto pbl_done; n += i; @@ -547,12 +573,13 @@ struct ib_mr *c4iw_reg_user_mr(struct ib_pd *pd, u64 start, u64 length, if (i) err = write_pbl(&mhp->rhp->rdev, pages, - mhp->attr.pbl_addr + (n << 3), i); + mhp->attr.pbl_addr + (n << 3), i, + mhp->wr_waitp); pbl_done: free_page((unsigned long) pages); if (err) - goto err_pbl; + goto err_pbl_free; mhp->attr.pdid = php->pdid; mhp->attr.zbva = 0; @@ -563,17 +590,20 @@ pbl_done: err = register_mem(rhp, php, mhp, shift); if (err) - goto err_pbl; + goto err_pbl_free; return &mhp->ibmr; -err_pbl: +err_pbl_free: c4iw_pblpool_free(&mhp->rhp->rdev, mhp->attr.pbl_addr, mhp->attr.pbl_size << 3); - -err: +err_umem_release: ib_umem_release(mhp->umem); +err_free_skb: kfree_skb(mhp->dereg_skb); +err_free_wr_wait: + c4iw_put_wr_wait(mhp->wr_waitp); +err_free_mhp: kfree(mhp); return ERR_PTR(err); } @@ -597,13 +627,19 @@ struct ib_mw *c4iw_alloc_mw(struct ib_pd *pd, enum ib_mw_type type, if (!mhp) return ERR_PTR(-ENOMEM); + mhp->wr_waitp = c4iw_alloc_wr_wait(GFP_KERNEL); + if (!mhp->wr_waitp) { + ret = -ENOMEM; + goto free_mhp; + } + mhp->dereg_skb = alloc_skb(SGE_MAX_WR_LEN, GFP_KERNEL); if (!mhp->dereg_skb) { ret = -ENOMEM; - goto free_mhp; + goto free_wr_wait; } - ret = allocate_window(&rhp->rdev, &stag, php->pdid); + ret = allocate_window(&rhp->rdev, &stag, php->pdid, mhp->wr_waitp); if (ret) goto free_skb; mhp->rhp = rhp; @@ -616,13 +652,16 @@ struct ib_mw *c4iw_alloc_mw(struct ib_pd *pd, enum ib_mw_type type, ret = -ENOMEM; goto dealloc_win; } - pr_debug("%s mmid 0x%x mhp %p stag 0x%x\n", __func__, mmid, mhp, stag); + pr_debug("mmid 0x%x mhp %p stag 0x%x\n", mmid, mhp, stag); return &(mhp->ibmw); dealloc_win: - deallocate_window(&rhp->rdev, mhp->attr.stag, mhp->dereg_skb); + deallocate_window(&rhp->rdev, mhp->attr.stag, mhp->dereg_skb, + mhp->wr_waitp); free_skb: kfree_skb(mhp->dereg_skb); +free_wr_wait: + c4iw_put_wr_wait(mhp->wr_waitp); free_mhp: kfree(mhp); return ERR_PTR(ret); @@ -638,10 +677,12 @@ int c4iw_dealloc_mw(struct ib_mw *mw) rhp = mhp->rhp; mmid = (mw->rkey) >> 8; remove_handle(rhp, &rhp->mmidr, mmid); - deallocate_window(&rhp->rdev, mhp->attr.stag, mhp->dereg_skb); + deallocate_window(&rhp->rdev, mhp->attr.stag, mhp->dereg_skb, + mhp->wr_waitp); kfree_skb(mhp->dereg_skb); + c4iw_put_wr_wait(mhp->wr_waitp); kfree(mhp); - pr_debug("%s ib_mw %p mmid 0x%x ptr %p\n", __func__, mw, mmid, mhp); + pr_debug("ib_mw %p mmid 0x%x ptr %p\n", mw, mmid, mhp); return 0; } @@ -671,23 +712,31 @@ struct ib_mr *c4iw_alloc_mr(struct ib_pd *pd, goto err; } + mhp->wr_waitp = c4iw_alloc_wr_wait(GFP_KERNEL); + if (!mhp->wr_waitp) { + ret = -ENOMEM; + goto err_free_mhp; + } + c4iw_init_wr_wait(mhp->wr_waitp); + mhp->mpl = dma_alloc_coherent(&rhp->rdev.lldi.pdev->dev, length, &mhp->mpl_addr, GFP_KERNEL); if (!mhp->mpl) { ret = -ENOMEM; - goto err_mpl; + goto err_free_wr_wait; } mhp->max_mpl_len = length; mhp->rhp = rhp; ret = alloc_pbl(mhp, max_num_sg); if (ret) - goto err1; + goto err_free_dma; mhp->attr.pbl_size = max_num_sg; ret = allocate_stag(&rhp->rdev, &stag, php->pdid, - mhp->attr.pbl_size, mhp->attr.pbl_addr); + mhp->attr.pbl_size, mhp->attr.pbl_addr, + mhp->wr_waitp); if (ret) - goto err2; + goto err_free_pbl; mhp->attr.pdid = php->pdid; mhp->attr.type = FW_RI_STAG_NSMR; mhp->attr.stag = stag; @@ -696,21 +745,23 @@ struct ib_mr *c4iw_alloc_mr(struct ib_pd *pd, mhp->ibmr.rkey = mhp->ibmr.lkey = stag; if (insert_handle(rhp, &rhp->mmidr, mhp, mmid)) { ret = -ENOMEM; - goto err3; + goto err_dereg; } - pr_debug("%s mmid 0x%x mhp %p stag 0x%x\n", __func__, mmid, mhp, stag); + pr_debug("mmid 0x%x mhp %p stag 0x%x\n", mmid, mhp, stag); return &(mhp->ibmr); -err3: +err_dereg: dereg_mem(&rhp->rdev, stag, mhp->attr.pbl_size, - mhp->attr.pbl_addr, mhp->dereg_skb); -err2: + mhp->attr.pbl_addr, mhp->dereg_skb, mhp->wr_waitp); +err_free_pbl: c4iw_pblpool_free(&mhp->rhp->rdev, mhp->attr.pbl_addr, mhp->attr.pbl_size << 3); -err1: +err_free_dma: dma_free_coherent(&mhp->rhp->rdev.lldi.pdev->dev, mhp->max_mpl_len, mhp->mpl, mhp->mpl_addr); -err_mpl: +err_free_wr_wait: + c4iw_put_wr_wait(mhp->wr_waitp); +err_free_mhp: kfree(mhp); err: return ERR_PTR(ret); @@ -744,7 +795,7 @@ int c4iw_dereg_mr(struct ib_mr *ib_mr) struct c4iw_mr *mhp; u32 mmid; - pr_debug("%s ib_mr %p\n", __func__, ib_mr); + pr_debug("ib_mr %p\n", ib_mr); mhp = to_c4iw_mr(ib_mr); rhp = mhp->rhp; @@ -754,7 +805,7 @@ int c4iw_dereg_mr(struct ib_mr *ib_mr) dma_free_coherent(&mhp->rhp->rdev.lldi.pdev->dev, mhp->max_mpl_len, mhp->mpl, mhp->mpl_addr); dereg_mem(&rhp->rdev, mhp->attr.stag, mhp->attr.pbl_size, - mhp->attr.pbl_addr, mhp->dereg_skb); + mhp->attr.pbl_addr, mhp->dereg_skb, mhp->wr_waitp); if (mhp->attr.pbl_size) c4iw_pblpool_free(&mhp->rhp->rdev, mhp->attr.pbl_addr, mhp->attr.pbl_size << 3); @@ -762,7 +813,8 @@ int c4iw_dereg_mr(struct ib_mr *ib_mr) kfree((void *) (unsigned long) mhp->kva); if (mhp->umem) ib_umem_release(mhp->umem); - pr_debug("%s mmid 0x%x ptr %p\n", __func__, mmid, mhp); + pr_debug("mmid 0x%x ptr %p\n", mmid, mhp); + c4iw_put_wr_wait(mhp->wr_waitp); kfree(mhp); return 0; } diff --git a/drivers/infiniband/hw/cxgb4/provider.c b/drivers/infiniband/hw/cxgb4/provider.c index 346e8334279a..fb99a05562a3 100644 --- a/drivers/infiniband/hw/cxgb4/provider.c +++ b/drivers/infiniband/hw/cxgb4/provider.c @@ -102,7 +102,7 @@ void _c4iw_free_ucontext(struct kref *kref) ucontext = container_of(kref, struct c4iw_ucontext, kref); rhp = to_c4iw_dev(ucontext->ibucontext.device); - pr_debug("%s ucontext %p\n", __func__, ucontext); + pr_debug("ucontext %p\n", ucontext); list_for_each_entry_safe(mm, tmp, &ucontext->mmaps, entry) kfree(mm); c4iw_release_dev_ucontext(&rhp->rdev, &ucontext->uctx); @@ -113,7 +113,7 @@ static int c4iw_dealloc_ucontext(struct ib_ucontext *context) { struct c4iw_ucontext *ucontext = to_c4iw_ucontext(context); - pr_debug("%s context %p\n", __func__, context); + pr_debug("context %p\n", context); c4iw_put_ucontext(ucontext); return 0; } @@ -127,7 +127,7 @@ static struct ib_ucontext *c4iw_alloc_ucontext(struct ib_device *ibdev, int ret = 0; struct c4iw_mm_entry *mm = NULL; - pr_debug("%s ibdev %p\n", __func__, ibdev); + pr_debug("ibdev %p\n", ibdev); context = kzalloc(sizeof(*context), GFP_KERNEL); if (!context) { ret = -ENOMEM; @@ -185,7 +185,7 @@ static int c4iw_mmap(struct ib_ucontext *context, struct vm_area_struct *vma) struct c4iw_ucontext *ucontext; u64 addr; - pr_debug("%s pgoff 0x%lx key 0x%x len %d\n", __func__, vma->vm_pgoff, + pr_debug("pgoff 0x%lx key 0x%x len %d\n", vma->vm_pgoff, key, len); if (vma->vm_start & (PAGE_SIZE-1)) @@ -251,7 +251,7 @@ static int c4iw_deallocate_pd(struct ib_pd *pd) php = to_c4iw_pd(pd); rhp = php->rhp; - pr_debug("%s ibpd %p pdid 0x%x\n", __func__, pd, php->pdid); + pr_debug("ibpd %p pdid 0x%x\n", pd, php->pdid); c4iw_put_resource(&rhp->rdev.resource.pdid_table, php->pdid); mutex_lock(&rhp->rdev.stats.lock); rhp->rdev.stats.pd.cur--; @@ -268,7 +268,7 @@ static struct ib_pd *c4iw_allocate_pd(struct ib_device *ibdev, u32 pdid; struct c4iw_dev *rhp; - pr_debug("%s ibdev %p\n", __func__, ibdev); + pr_debug("ibdev %p\n", ibdev); rhp = (struct c4iw_dev *) ibdev; pdid = c4iw_get_resource(&rhp->rdev.resource.pdid_table); if (!pdid) @@ -291,14 +291,14 @@ static struct ib_pd *c4iw_allocate_pd(struct ib_device *ibdev, if (rhp->rdev.stats.pd.cur > rhp->rdev.stats.pd.max) rhp->rdev.stats.pd.max = rhp->rdev.stats.pd.cur; mutex_unlock(&rhp->rdev.stats.lock); - pr_debug("%s pdid 0x%0x ptr 0x%p\n", __func__, pdid, php); + pr_debug("pdid 0x%0x ptr 0x%p\n", pdid, php); return &php->ibpd; } static int c4iw_query_pkey(struct ib_device *ibdev, u8 port, u16 index, u16 *pkey) { - pr_debug("%s ibdev %p\n", __func__, ibdev); + pr_debug("ibdev %p\n", ibdev); *pkey = 0; return 0; } @@ -308,8 +308,8 @@ static int c4iw_query_gid(struct ib_device *ibdev, u8 port, int index, { struct c4iw_dev *dev; - pr_debug("%s ibdev %p, port %d, index %d, gid %p\n", - __func__, ibdev, port, index, gid); + pr_debug("ibdev %p, port %d, index %d, gid %p\n", + ibdev, port, index, gid); dev = to_c4iw_dev(ibdev); BUG_ON(port == 0); memset(&(gid->raw[0]), 0, sizeof(gid->raw)); @@ -323,7 +323,7 @@ static int c4iw_query_device(struct ib_device *ibdev, struct ib_device_attr *pro struct c4iw_dev *dev; - pr_debug("%s ibdev %p\n", __func__, ibdev); + pr_debug("ibdev %p\n", ibdev); if (uhw->inlen || uhw->outlen) return -EINVAL; @@ -364,7 +364,7 @@ static int c4iw_query_port(struct ib_device *ibdev, u8 port, struct net_device *netdev; struct in_device *inetdev; - pr_debug("%s ibdev %p\n", __func__, ibdev); + pr_debug("ibdev %p\n", ibdev); dev = to_c4iw_dev(ibdev); netdev = dev->rdev.lldi.ports[port-1]; @@ -406,7 +406,7 @@ static ssize_t show_rev(struct device *dev, struct device_attribute *attr, { struct c4iw_dev *c4iw_dev = container_of(dev, struct c4iw_dev, ibdev.dev); - pr_debug("%s dev 0x%p\n", __func__, dev); + pr_debug("dev 0x%p\n", dev); return sprintf(buf, "%d\n", CHELSIO_CHIP_RELEASE(c4iw_dev->rdev.lldi.adapter_type)); } @@ -419,7 +419,7 @@ static ssize_t show_hca(struct device *dev, struct device_attribute *attr, struct ethtool_drvinfo info; struct net_device *lldev = c4iw_dev->rdev.lldi.ports[0]; - pr_debug("%s dev 0x%p\n", __func__, dev); + pr_debug("dev 0x%p\n", dev); lldev->ethtool_ops->get_drvinfo(lldev, &info); return sprintf(buf, "%s\n", info.driver); } @@ -429,7 +429,7 @@ static ssize_t show_board(struct device *dev, struct device_attribute *attr, { struct c4iw_dev *c4iw_dev = container_of(dev, struct c4iw_dev, ibdev.dev); - pr_debug("%s dev 0x%p\n", __func__, dev); + pr_debug("dev 0x%p\n", dev); return sprintf(buf, "%x.%x\n", c4iw_dev->rdev.lldi.pdev->vendor, c4iw_dev->rdev.lldi.pdev->device); } @@ -521,7 +521,7 @@ static void get_dev_fw_str(struct ib_device *dev, char *str) { struct c4iw_dev *c4iw_dev = container_of(dev, struct c4iw_dev, ibdev); - pr_debug("%s dev 0x%p\n", __func__, dev); + pr_debug("dev 0x%p\n", dev); snprintf(str, IB_FW_VERSION_NAME_MAX, "%u.%u.%u.%u", FW_HDR_FW_VER_MAJOR_G(c4iw_dev->rdev.lldi.fw_vers), @@ -535,7 +535,7 @@ int c4iw_register_device(struct c4iw_dev *dev) int ret; int i; - pr_debug("%s c4iw_dev %p\n", __func__, dev); + pr_debug("c4iw_dev %p\n", dev); BUG_ON(!dev->rdev.lldi.ports[0]); strlcpy(dev->ibdev.name, "cxgb4_%d", IB_DEVICE_NAME_MAX); memset(&dev->ibdev.node_guid, 0, sizeof(dev->ibdev.node_guid)); @@ -645,7 +645,7 @@ void c4iw_unregister_device(struct c4iw_dev *dev) { int i; - pr_debug("%s c4iw_dev %p\n", __func__, dev); + pr_debug("c4iw_dev %p\n", dev); for (i = 0; i < ARRAY_SIZE(c4iw_class_attributes); ++i) device_remove_file(&dev->ibdev.dev, c4iw_class_attributes[i]); diff --git a/drivers/infiniband/hw/cxgb4/qp.c b/drivers/infiniband/hw/cxgb4/qp.c index cb7fc0d35d1d..57b23e33eb8b 100644 --- a/drivers/infiniband/hw/cxgb4/qp.c +++ b/drivers/infiniband/hw/cxgb4/qp.c @@ -194,13 +194,13 @@ void __iomem *c4iw_bar2_addrs(struct c4iw_rdev *rdev, unsigned int qid, static int create_qp(struct c4iw_rdev *rdev, struct t4_wq *wq, struct t4_cq *rcq, struct t4_cq *scq, - struct c4iw_dev_ucontext *uctx) + struct c4iw_dev_ucontext *uctx, + struct c4iw_wr_wait *wr_waitp) { int user = (uctx != &rdev->uctx); struct fw_ri_res_wr *res_wr; struct fw_ri_res *res; int wr_len; - struct c4iw_wr_wait wr_wait; struct sk_buff *skb; int ret = 0; int eqsize; @@ -254,8 +254,8 @@ static int create_qp(struct c4iw_rdev *rdev, struct t4_wq *wq, ret = -ENOMEM; goto free_sq; } - pr_debug("%s sq base va 0x%p pa 0x%llx rq base va 0x%p pa 0x%llx\n", - __func__, wq->sq.queue, + pr_debug("sq base va 0x%p pa 0x%llx rq base va 0x%p pa 0x%llx\n", + wq->sq.queue, (unsigned long long)virt_to_phys(wq->sq.queue), wq->rq.queue, (unsigned long long)virt_to_phys(wq->rq.queue)); @@ -299,7 +299,7 @@ static int create_qp(struct c4iw_rdev *rdev, struct t4_wq *wq, FW_RI_RES_WR_NRES_V(2) | FW_WR_COMPL_F); res_wr->len16_pkd = cpu_to_be32(DIV_ROUND_UP(wr_len, 16)); - res_wr->cookie = (uintptr_t)&wr_wait; + res_wr->cookie = (uintptr_t)wr_waitp; res = res_wr->res; res->u.sqrq.restype = FW_RI_RES_TYPE_SQ; res->u.sqrq.op = FW_RI_RES_OP_WRITE; @@ -352,17 +352,13 @@ static int create_qp(struct c4iw_rdev *rdev, struct t4_wq *wq, res->u.sqrq.eqid = cpu_to_be32(wq->rq.qid); res->u.sqrq.eqaddr = cpu_to_be64(wq->rq.dma_addr); - c4iw_init_wr_wait(&wr_wait); - - ret = c4iw_ofld_send(rdev, skb); - if (ret) - goto free_dma; - ret = c4iw_wait_for_reply(rdev, &wr_wait, 0, wq->sq.qid, __func__); + c4iw_init_wr_wait(wr_waitp); + ret = c4iw_ref_send_wait(rdev, skb, wr_waitp, 0, wq->sq.qid, __func__); if (ret) goto free_dma; - pr_debug("%s sqid 0x%x rqid 0x%x kdb 0x%p sq_bar2_addr %p rq_bar2_addr %p\n", - __func__, wq->sq.qid, wq->rq.qid, wq->db, + pr_debug("sqid 0x%x rqid 0x%x kdb 0x%p sq_bar2_addr %p rq_bar2_addr %p\n", + wq->sq.qid, wq->rq.qid, wq->db, wq->sq.bar2_va, wq->rq.bar2_va); return 0; @@ -724,12 +720,13 @@ static void free_qp_work(struct work_struct *work) ucontext = qhp->ucontext; rhp = qhp->rhp; - pr_debug("%s qhp %p ucontext %p\n", __func__, qhp, ucontext); + pr_debug("qhp %p ucontext %p\n", qhp, ucontext); destroy_qp(&rhp->rdev, &qhp->wq, ucontext ? &ucontext->uctx : &rhp->rdev.uctx); if (ucontext) c4iw_put_ucontext(ucontext); + c4iw_put_wr_wait(qhp->wr_waitp); kfree(qhp); } @@ -738,19 +735,19 @@ static void queue_qp_free(struct kref *kref) struct c4iw_qp *qhp; qhp = container_of(kref, struct c4iw_qp, kref); - pr_debug("%s qhp %p\n", __func__, qhp); + pr_debug("qhp %p\n", qhp); queue_work(qhp->rhp->rdev.free_workq, &qhp->free_work); } void c4iw_qp_add_ref(struct ib_qp *qp) { - pr_debug("%s ib_qp %p\n", __func__, qp); + pr_debug("ib_qp %p\n", qp); kref_get(&to_c4iw_qp(qp)->kref); } void c4iw_qp_rem_ref(struct ib_qp *qp) { - pr_debug("%s ib_qp %p\n", __func__, qp); + pr_debug("ib_qp %p\n", qp); kref_put(&to_c4iw_qp(qp)->kref, queue_qp_free); } @@ -958,8 +955,8 @@ int c4iw_post_send(struct ib_qp *ibqp, struct ib_send_wr *wr, c4iw_invalidate_mr(qhp->rhp, wr->ex.invalidate_rkey); break; default: - pr_debug("%s post of type=%d TBD!\n", __func__, - wr->opcode); + pr_warn("%s post of type=%d TBD!\n", __func__, + wr->opcode); err = -EINVAL; } if (err) { @@ -980,8 +977,7 @@ int c4iw_post_send(struct ib_qp *ibqp, struct ib_send_wr *wr, init_wr_hdr(wqe, qhp->wq.sq.pidx, fw_opcode, fw_flags, len16); - pr_debug("%s cookie 0x%llx pidx 0x%x opcode 0x%x read_len %u\n", - __func__, + pr_debug("cookie 0x%llx pidx 0x%x opcode 0x%x read_len %u\n", (unsigned long long)wr->wr_id, qhp->wq.sq.pidx, swsqe->opcode, swsqe->read_len); wr = wr->next; @@ -1057,8 +1053,7 @@ int c4iw_post_receive(struct ib_qp *ibqp, struct ib_recv_wr *wr, wqe->recv.r2[1] = 0; wqe->recv.r2[2] = 0; wqe->recv.len16 = len16; - pr_debug("%s cookie 0x%llx pidx %u\n", - __func__, + pr_debug("cookie 0x%llx pidx %u\n", (unsigned long long)wr->wr_id, qhp->wq.rq.pidx); t4_rq_produce(&qhp->wq, len16); idx += DIV_ROUND_UP(len16*16, T4_EQ_ENTRY_SIZE); @@ -1218,7 +1213,7 @@ static void post_terminate(struct c4iw_qp *qhp, struct t4_cqe *err_cqe, struct sk_buff *skb; struct terminate_message *term; - pr_debug("%s qhp %p qid 0x%x tid %u\n", __func__, qhp, qhp->wq.sq.qid, + pr_debug("qhp %p qid 0x%x tid %u\n", qhp, qhp->wq.sq.qid, qhp->ep->hwtid); skb = skb_dequeue(&qhp->ep->com.ep_skb_list); @@ -1255,7 +1250,7 @@ static void __flush_qp(struct c4iw_qp *qhp, struct c4iw_cq *rchp, int rq_flushed, sq_flushed; unsigned long flag; - pr_debug("%s qhp %p rchp %p schp %p\n", __func__, qhp, rchp, schp); + pr_debug("qhp %p rchp %p schp %p\n", qhp, rchp, schp); /* locking hierarchy: cq lock first, then qp lock. */ spin_lock_irqsave(&rchp->lock, flag); @@ -1340,8 +1335,7 @@ static int rdma_fini(struct c4iw_dev *rhp, struct c4iw_qp *qhp, int ret; struct sk_buff *skb; - pr_debug("%s qhp %p qid 0x%x tid %u\n", __func__, qhp, qhp->wq.sq.qid, - ep->hwtid); + pr_debug("qhp %p qid 0x%x tid %u\n", qhp, qhp->wq.sq.qid, ep->hwtid); skb = skb_dequeue(&ep->com.ep_skb_list); if (WARN_ON(!skb)) @@ -1357,23 +1351,20 @@ static int rdma_fini(struct c4iw_dev *rhp, struct c4iw_qp *qhp, wqe->flowid_len16 = cpu_to_be32( FW_WR_FLOWID_V(ep->hwtid) | FW_WR_LEN16_V(DIV_ROUND_UP(sizeof(*wqe), 16))); - wqe->cookie = (uintptr_t)&ep->com.wr_wait; + wqe->cookie = (uintptr_t)ep->com.wr_waitp; wqe->u.fini.type = FW_RI_TYPE_FINI; - ret = c4iw_ofld_send(&rhp->rdev, skb); - if (ret) - goto out; - ret = c4iw_wait_for_reply(&rhp->rdev, &ep->com.wr_wait, qhp->ep->hwtid, - qhp->wq.sq.qid, __func__); -out: - pr_debug("%s ret %d\n", __func__, ret); + ret = c4iw_ref_send_wait(&rhp->rdev, skb, ep->com.wr_waitp, + qhp->ep->hwtid, qhp->wq.sq.qid, __func__); + + pr_debug("ret %d\n", ret); return ret; } static void build_rtr_msg(u8 p2p_type, struct fw_ri_init *init) { - pr_debug("%s p2p_type = %d\n", __func__, p2p_type); + pr_debug("p2p_type = %d\n", p2p_type); memset(&init->u, 0, sizeof init->u); switch (p2p_type) { case FW_RI_INIT_P2PTYPE_RDMA_WRITE: @@ -1402,7 +1393,7 @@ static int rdma_init(struct c4iw_dev *rhp, struct c4iw_qp *qhp) int ret; struct sk_buff *skb; - pr_debug("%s qhp %p qid 0x%x tid %u ird %u ord %u\n", __func__, qhp, + pr_debug("qhp %p qid 0x%x tid %u ird %u ord %u\n", qhp, qhp->wq.sq.qid, qhp->ep->hwtid, qhp->ep->ird, qhp->ep->ord); skb = alloc_skb(sizeof *wqe, GFP_KERNEL); @@ -1427,7 +1418,7 @@ static int rdma_init(struct c4iw_dev *rhp, struct c4iw_qp *qhp) FW_WR_FLOWID_V(qhp->ep->hwtid) | FW_WR_LEN16_V(DIV_ROUND_UP(sizeof(*wqe), 16))); - wqe->cookie = (uintptr_t)&qhp->ep->com.wr_wait; + wqe->cookie = (uintptr_t)qhp->ep->com.wr_waitp; wqe->u.init.type = FW_RI_TYPE_INIT; wqe->u.init.mpareqbit_p2ptype = @@ -1464,18 +1455,14 @@ static int rdma_init(struct c4iw_dev *rhp, struct c4iw_qp *qhp) if (qhp->attr.mpa_attr.initiator) build_rtr_msg(qhp->attr.mpa_attr.p2p_type, &wqe->u.init); - ret = c4iw_ofld_send(&rhp->rdev, skb); - if (ret) - goto err1; - - ret = c4iw_wait_for_reply(&rhp->rdev, &qhp->ep->com.wr_wait, - qhp->ep->hwtid, qhp->wq.sq.qid, __func__); + ret = c4iw_ref_send_wait(&rhp->rdev, skb, qhp->ep->com.wr_waitp, + qhp->ep->hwtid, qhp->wq.sq.qid, __func__); if (!ret) goto out; -err1: + free_ird(rhp, qhp->attr.max_ird); out: - pr_debug("%s ret %d\n", __func__, ret); + pr_debug("ret %d\n", ret); return ret; } @@ -1492,8 +1479,7 @@ int c4iw_modify_qp(struct c4iw_dev *rhp, struct c4iw_qp *qhp, int free = 0; struct c4iw_ep *ep = NULL; - pr_debug("%s qhp %p sqid 0x%x rqid 0x%x ep %p state %d -> %d\n", - __func__, + pr_debug("qhp %p sqid 0x%x rqid 0x%x ep %p state %d -> %d\n", qhp, qhp->wq.sq.qid, qhp->wq.rq.qid, qhp->ep, qhp->attr.state, (mask & C4IW_QP_ATTR_NEXT_STATE) ? attrs->next_state : -1); @@ -1680,7 +1666,7 @@ int c4iw_modify_qp(struct c4iw_dev *rhp, struct c4iw_qp *qhp, } goto out; err: - pr_debug("%s disassociating ep %p qpid 0x%x\n", __func__, qhp->ep, + pr_debug("disassociating ep %p qpid 0x%x\n", qhp->ep, qhp->wq.sq.qid); /* disassociate the LLP connection */ @@ -1717,7 +1703,7 @@ out: */ if (free) c4iw_put_ep(&ep->com); - pr_debug("%s exit state %d\n", __func__, qhp->attr.state); + pr_debug("exit state %d\n", qhp->attr.state); return ret; } @@ -1747,7 +1733,7 @@ int c4iw_destroy_qp(struct ib_qp *ib_qp) c4iw_qp_rem_ref(ib_qp); - pr_debug("%s ib_qp %p qpid 0x%0x\n", __func__, ib_qp, qhp->wq.sq.qid); + pr_debug("ib_qp %p qpid 0x%0x\n", ib_qp, qhp->wq.sq.qid); return 0; } @@ -1766,7 +1752,7 @@ struct ib_qp *c4iw_create_qp(struct ib_pd *pd, struct ib_qp_init_attr *attrs, struct c4iw_mm_entry *sq_key_mm, *rq_key_mm = NULL, *sq_db_key_mm; struct c4iw_mm_entry *rq_db_key_mm = NULL, *ma_sync_key_mm = NULL; - pr_debug("%s ib_pd %p\n", __func__, pd); + pr_debug("ib_pd %p\n", pd); if (attrs->qp_type != IB_QPT_RC) return ERR_PTR(-EINVAL); @@ -1798,6 +1784,13 @@ struct ib_qp *c4iw_create_qp(struct ib_pd *pd, struct ib_qp_init_attr *attrs, qhp = kzalloc(sizeof(*qhp), GFP_KERNEL); if (!qhp) return ERR_PTR(-ENOMEM); + + qhp->wr_waitp = c4iw_alloc_wr_wait(GFP_KERNEL); + if (!qhp->wr_waitp) { + ret = -ENOMEM; + goto err_free_qhp; + } + qhp->wq.sq.size = sqsize; qhp->wq.sq.memsize = (sqsize + rhp->rdev.hw_queue.t4_eq_status_entries) * @@ -1814,9 +1807,10 @@ struct ib_qp *c4iw_create_qp(struct ib_pd *pd, struct ib_qp_init_attr *attrs, } ret = create_qp(&rhp->rdev, &qhp->wq, &schp->cq, &rchp->cq, - ucontext ? &ucontext->uctx : &rhp->rdev.uctx); + ucontext ? &ucontext->uctx : &rhp->rdev.uctx, + qhp->wr_waitp); if (ret) - goto err1; + goto err_free_wr_wait; attrs->cap.max_recv_wr = rqsize - 1; attrs->cap.max_send_wr = sqsize - 1; @@ -1847,35 +1841,35 @@ struct ib_qp *c4iw_create_qp(struct ib_pd *pd, struct ib_qp_init_attr *attrs, ret = insert_handle(rhp, &rhp->qpidr, qhp, qhp->wq.sq.qid); if (ret) - goto err2; + goto err_destroy_qp; if (udata) { sq_key_mm = kmalloc(sizeof(*sq_key_mm), GFP_KERNEL); if (!sq_key_mm) { ret = -ENOMEM; - goto err3; + goto err_remove_handle; } rq_key_mm = kmalloc(sizeof(*rq_key_mm), GFP_KERNEL); if (!rq_key_mm) { ret = -ENOMEM; - goto err4; + goto err_free_sq_key; } sq_db_key_mm = kmalloc(sizeof(*sq_db_key_mm), GFP_KERNEL); if (!sq_db_key_mm) { ret = -ENOMEM; - goto err5; + goto err_free_rq_key; } rq_db_key_mm = kmalloc(sizeof(*rq_db_key_mm), GFP_KERNEL); if (!rq_db_key_mm) { ret = -ENOMEM; - goto err6; + goto err_free_sq_db_key; } if (t4_sq_onchip(&qhp->wq.sq)) { ma_sync_key_mm = kmalloc(sizeof(*ma_sync_key_mm), GFP_KERNEL); if (!ma_sync_key_mm) { ret = -ENOMEM; - goto err7; + goto err_free_rq_db_key; } uresp.flags = C4IW_QPF_ONCHIP; } else @@ -1905,7 +1899,7 @@ struct ib_qp *c4iw_create_qp(struct ib_pd *pd, struct ib_qp_init_attr *attrs, spin_unlock(&ucontext->mmap_lock); ret = ib_copy_to_udata(udata, &uresp, sizeof uresp); if (ret) - goto err8; + goto err_free_ma_sync_key; sq_key_mm->key = uresp.sq_key; sq_key_mm->addr = qhp->wq.sq.phys_addr; sq_key_mm->len = PAGE_ALIGN(qhp->wq.sq.memsize); @@ -1935,30 +1929,30 @@ struct ib_qp *c4iw_create_qp(struct ib_pd *pd, struct ib_qp_init_attr *attrs, qhp->ucontext = ucontext; } qhp->ibqp.qp_num = qhp->wq.sq.qid; - init_timer(&(qhp->timer)); INIT_LIST_HEAD(&qhp->db_fc_entry); - pr_debug("%s sq id %u size %u memsize %zu num_entries %u rq id %u size %u memsize %zu num_entries %u\n", - __func__, + pr_debug("sq id %u size %u memsize %zu num_entries %u rq id %u size %u memsize %zu num_entries %u\n", qhp->wq.sq.qid, qhp->wq.sq.size, qhp->wq.sq.memsize, attrs->cap.max_send_wr, qhp->wq.rq.qid, qhp->wq.rq.size, qhp->wq.rq.memsize, attrs->cap.max_recv_wr); return &qhp->ibqp; -err8: +err_free_ma_sync_key: kfree(ma_sync_key_mm); -err7: +err_free_rq_db_key: kfree(rq_db_key_mm); -err6: +err_free_sq_db_key: kfree(sq_db_key_mm); -err5: +err_free_rq_key: kfree(rq_key_mm); -err4: +err_free_sq_key: kfree(sq_key_mm); -err3: +err_remove_handle: remove_handle(rhp, &rhp->qpidr, qhp->wq.sq.qid); -err2: +err_destroy_qp: destroy_qp(&rhp->rdev, &qhp->wq, ucontext ? &ucontext->uctx : &rhp->rdev.uctx); -err1: +err_free_wr_wait: + c4iw_put_wr_wait(qhp->wr_waitp); +err_free_qhp: kfree(qhp); return ERR_PTR(ret); } @@ -1971,7 +1965,7 @@ int c4iw_ib_modify_qp(struct ib_qp *ibqp, struct ib_qp_attr *attr, enum c4iw_qp_attr_mask mask = 0; struct c4iw_qp_attributes attrs; - pr_debug("%s ib_qp %p\n", __func__, ibqp); + pr_debug("ib_qp %p\n", ibqp); /* iwarp does not support the RTR state */ if ((attr_mask & IB_QP_STATE) && (attr->qp_state == IB_QPS_RTR)) @@ -2017,7 +2011,7 @@ int c4iw_ib_modify_qp(struct ib_qp *ibqp, struct ib_qp_attr *attr, struct ib_qp *c4iw_get_qp(struct ib_device *dev, int qpn) { - pr_debug("%s ib_dev %p qpn 0x%x\n", __func__, dev, qpn); + pr_debug("ib_dev %p qpn 0x%x\n", dev, qpn); return (struct ib_qp *)get_qhp(to_c4iw_dev(dev), qpn); } diff --git a/drivers/infiniband/hw/cxgb4/resource.c b/drivers/infiniband/hw/cxgb4/resource.c index 8ff0cbe5cb16..3cf25997ed2b 100644 --- a/drivers/infiniband/hw/cxgb4/resource.c +++ b/drivers/infiniband/hw/cxgb4/resource.c @@ -90,7 +90,7 @@ u32 c4iw_get_resource(struct c4iw_id_table *id_table) void c4iw_put_resource(struct c4iw_id_table *id_table, u32 entry) { - pr_debug("%s entry 0x%x\n", __func__, entry); + pr_debug("entry 0x%x\n", entry); c4iw_id_free(id_table, entry); } @@ -141,7 +141,7 @@ u32 c4iw_get_cqid(struct c4iw_rdev *rdev, struct c4iw_dev_ucontext *uctx) } out: mutex_unlock(&uctx->lock); - pr_debug("%s qid 0x%x\n", __func__, qid); + pr_debug("qid 0x%x\n", qid); mutex_lock(&rdev->stats.lock); if (rdev->stats.qid.cur > rdev->stats.qid.max) rdev->stats.qid.max = rdev->stats.qid.cur; @@ -157,7 +157,7 @@ void c4iw_put_cqid(struct c4iw_rdev *rdev, u32 qid, entry = kmalloc(sizeof *entry, GFP_KERNEL); if (!entry) return; - pr_debug("%s qid 0x%x\n", __func__, qid); + pr_debug("qid 0x%x\n", qid); entry->qid = qid; mutex_lock(&uctx->lock); list_add_tail(&entry->entry, &uctx->cqids); @@ -215,7 +215,7 @@ u32 c4iw_get_qpid(struct c4iw_rdev *rdev, struct c4iw_dev_ucontext *uctx) } out: mutex_unlock(&uctx->lock); - pr_debug("%s qid 0x%x\n", __func__, qid); + pr_debug("qid 0x%x\n", qid); mutex_lock(&rdev->stats.lock); if (rdev->stats.qid.cur > rdev->stats.qid.max) rdev->stats.qid.max = rdev->stats.qid.cur; @@ -231,7 +231,7 @@ void c4iw_put_qpid(struct c4iw_rdev *rdev, u32 qid, entry = kmalloc(sizeof *entry, GFP_KERNEL); if (!entry) return; - pr_debug("%s qid 0x%x\n", __func__, qid); + pr_debug("qid 0x%x\n", qid); entry->qid = qid; mutex_lock(&uctx->lock); list_add_tail(&entry->entry, &uctx->qpids); @@ -254,7 +254,7 @@ void c4iw_destroy_resource(struct c4iw_resource *rscp) u32 c4iw_pblpool_alloc(struct c4iw_rdev *rdev, int size) { unsigned long addr = gen_pool_alloc(rdev->pbl_pool, size); - pr_debug("%s addr 0x%x size %d\n", __func__, (u32)addr, size); + pr_debug("addr 0x%x size %d\n", (u32)addr, size); mutex_lock(&rdev->stats.lock); if (addr) { rdev->stats.pbl.cur += roundup(size, 1 << MIN_PBL_SHIFT); @@ -268,7 +268,7 @@ u32 c4iw_pblpool_alloc(struct c4iw_rdev *rdev, int size) void c4iw_pblpool_free(struct c4iw_rdev *rdev, u32 addr, int size) { - pr_debug("%s addr 0x%x size %d\n", __func__, addr, size); + pr_debug("addr 0x%x size %d\n", addr, size); mutex_lock(&rdev->stats.lock); rdev->stats.pbl.cur -= roundup(size, 1 << MIN_PBL_SHIFT); mutex_unlock(&rdev->stats.lock); @@ -290,8 +290,8 @@ int c4iw_pblpool_create(struct c4iw_rdev *rdev) while (pbl_start < pbl_top) { pbl_chunk = min(pbl_top - pbl_start + 1, pbl_chunk); if (gen_pool_add(rdev->pbl_pool, pbl_start, pbl_chunk, -1)) { - pr_debug("%s failed to add PBL chunk (%x/%x)\n", - __func__, pbl_start, pbl_chunk); + pr_debug("failed to add PBL chunk (%x/%x)\n", + pbl_start, pbl_chunk); if (pbl_chunk <= 1024 << MIN_PBL_SHIFT) { pr_warn("Failed to add all PBL chunks (%x/%x)\n", pbl_start, pbl_top - pbl_start); @@ -299,8 +299,8 @@ int c4iw_pblpool_create(struct c4iw_rdev *rdev) } pbl_chunk >>= 1; } else { - pr_debug("%s added PBL chunk (%x/%x)\n", - __func__, pbl_start, pbl_chunk); + pr_debug("added PBL chunk (%x/%x)\n", + pbl_start, pbl_chunk); pbl_start += pbl_chunk; } } @@ -322,7 +322,7 @@ void c4iw_pblpool_destroy(struct c4iw_rdev *rdev) u32 c4iw_rqtpool_alloc(struct c4iw_rdev *rdev, int size) { unsigned long addr = gen_pool_alloc(rdev->rqt_pool, size << 6); - pr_debug("%s addr 0x%x size %d\n", __func__, (u32)addr, size << 6); + pr_debug("addr 0x%x size %d\n", (u32)addr, size << 6); if (!addr) pr_warn_ratelimited("%s: Out of RQT memory\n", pci_name(rdev->lldi.pdev)); @@ -339,7 +339,7 @@ u32 c4iw_rqtpool_alloc(struct c4iw_rdev *rdev, int size) void c4iw_rqtpool_free(struct c4iw_rdev *rdev, u32 addr, int size) { - pr_debug("%s addr 0x%x size %d\n", __func__, addr, size << 6); + pr_debug("addr 0x%x size %d\n", addr, size << 6); mutex_lock(&rdev->stats.lock); rdev->stats.rqt.cur -= roundup(size << 6, 1 << MIN_RQT_SHIFT); mutex_unlock(&rdev->stats.lock); @@ -361,8 +361,8 @@ int c4iw_rqtpool_create(struct c4iw_rdev *rdev) while (rqt_start < rqt_top) { rqt_chunk = min(rqt_top - rqt_start + 1, rqt_chunk); if (gen_pool_add(rdev->rqt_pool, rqt_start, rqt_chunk, -1)) { - pr_debug("%s failed to add RQT chunk (%x/%x)\n", - __func__, rqt_start, rqt_chunk); + pr_debug("failed to add RQT chunk (%x/%x)\n", + rqt_start, rqt_chunk); if (rqt_chunk <= 1024 << MIN_RQT_SHIFT) { pr_warn("Failed to add all RQT chunks (%x/%x)\n", rqt_start, rqt_top - rqt_start); @@ -370,8 +370,8 @@ int c4iw_rqtpool_create(struct c4iw_rdev *rdev) } rqt_chunk >>= 1; } else { - pr_debug("%s added RQT chunk (%x/%x)\n", - __func__, rqt_start, rqt_chunk); + pr_debug("added RQT chunk (%x/%x)\n", + rqt_start, rqt_chunk); rqt_start += rqt_chunk; } } @@ -391,7 +391,7 @@ void c4iw_rqtpool_destroy(struct c4iw_rdev *rdev) u32 c4iw_ocqp_pool_alloc(struct c4iw_rdev *rdev, int size) { unsigned long addr = gen_pool_alloc(rdev->ocqp_pool, size); - pr_debug("%s addr 0x%x size %d\n", __func__, (u32)addr, size); + pr_debug("addr 0x%x size %d\n", (u32)addr, size); if (addr) { mutex_lock(&rdev->stats.lock); rdev->stats.ocqp.cur += roundup(size, 1 << MIN_OCQP_SHIFT); @@ -404,7 +404,7 @@ u32 c4iw_ocqp_pool_alloc(struct c4iw_rdev *rdev, int size) void c4iw_ocqp_pool_free(struct c4iw_rdev *rdev, u32 addr, int size) { - pr_debug("%s addr 0x%x size %d\n", __func__, addr, size); + pr_debug("addr 0x%x size %d\n", addr, size); mutex_lock(&rdev->stats.lock); rdev->stats.ocqp.cur -= roundup(size, 1 << MIN_OCQP_SHIFT); mutex_unlock(&rdev->stats.lock); @@ -426,8 +426,8 @@ int c4iw_ocqp_pool_create(struct c4iw_rdev *rdev) while (start < top) { chunk = min(top - start + 1, chunk); if (gen_pool_add(rdev->ocqp_pool, start, chunk, -1)) { - pr_debug("%s failed to add OCQP chunk (%x/%x)\n", - __func__, start, chunk); + pr_debug("failed to add OCQP chunk (%x/%x)\n", + start, chunk); if (chunk <= 1024 << MIN_OCQP_SHIFT) { pr_warn("Failed to add all OCQP chunks (%x/%x)\n", start, top - start); @@ -435,8 +435,8 @@ int c4iw_ocqp_pool_create(struct c4iw_rdev *rdev) } chunk >>= 1; } else { - pr_debug("%s added OCQP chunk (%x/%x)\n", - __func__, start, chunk); + pr_debug("added OCQP chunk (%x/%x)\n", + start, chunk); start += chunk; } } diff --git a/drivers/infiniband/hw/cxgb4/t4.h b/drivers/infiniband/hw/cxgb4/t4.h index e765c00303cd..427aaf20d77c 100644 --- a/drivers/infiniband/hw/cxgb4/t4.h +++ b/drivers/infiniband/hw/cxgb4/t4.h @@ -171,7 +171,7 @@ struct t4_cqe { __be32 msn; } rcqe; struct { - u32 stag; + __be32 stag; u16 nada2; u16 cidx; } scqe; @@ -466,14 +466,12 @@ static inline void t4_ring_sq_db(struct t4_wq *wq, u16 inc, union t4_wr *wqe) wmb(); if (wq->sq.bar2_va) { if (inc == 1 && wq->sq.bar2_qid == 0 && wqe) { - pr_debug("%s: WC wq->sq.pidx = %d\n", - __func__, wq->sq.pidx); + pr_debug("WC wq->sq.pidx = %d\n", wq->sq.pidx); pio_copy((u64 __iomem *) (wq->sq.bar2_va + SGE_UDB_WCDOORBELL), (u64 *)wqe); } else { - pr_debug("%s: DB wq->sq.pidx = %d\n", - __func__, wq->sq.pidx); + pr_debug("DB wq->sq.pidx = %d\n", wq->sq.pidx); writel(PIDX_T5_V(inc) | QID_V(wq->sq.bar2_qid), wq->sq.bar2_va + SGE_UDB_KDOORBELL); } @@ -493,14 +491,12 @@ static inline void t4_ring_rq_db(struct t4_wq *wq, u16 inc, wmb(); if (wq->rq.bar2_va) { if (inc == 1 && wq->rq.bar2_qid == 0 && wqe) { - pr_debug("%s: WC wq->rq.pidx = %d\n", - __func__, wq->rq.pidx); + pr_debug("WC wq->rq.pidx = %d\n", wq->rq.pidx); pio_copy((u64 __iomem *) (wq->rq.bar2_va + SGE_UDB_WCDOORBELL), (void *)wqe); } else { - pr_debug("%s: DB wq->rq.pidx = %d\n", - __func__, wq->rq.pidx); + pr_debug("DB wq->rq.pidx = %d\n", wq->rq.pidx); writel(PIDX_T5_V(inc) | QID_V(wq->rq.bar2_qid), wq->rq.bar2_va + SGE_UDB_KDOORBELL); } @@ -601,8 +597,8 @@ static inline void t4_swcq_produce(struct t4_cq *cq) { cq->sw_in_use++; if (cq->sw_in_use == cq->size) { - pr_debug("%s cxgb4 sw cq overflow cqid %u\n", - __func__, cq->cqid); + pr_warn("%s cxgb4 sw cq overflow cqid %u\n", + __func__, cq->cqid); cq->error = 1; BUG_ON(1); } @@ -673,8 +669,8 @@ static inline int t4_next_hw_cqe(struct t4_cq *cq, struct t4_cqe **cqe) static inline struct t4_cqe *t4_next_sw_cqe(struct t4_cq *cq) { if (cq->sw_in_use == cq->size) { - pr_debug("%s cxgb4 sw cq overflow cqid %u\n", - __func__, cq->cqid); + pr_warn("%s cxgb4 sw cq overflow cqid %u\n", + __func__, cq->cqid); cq->error = 1; BUG_ON(1); return NULL; diff --git a/drivers/infiniband/hw/hfi1/aspm.h b/drivers/infiniband/hw/hfi1/aspm.h index 522b40ed9937..e8133870ee87 100644 --- a/drivers/infiniband/hw/hfi1/aspm.h +++ b/drivers/infiniband/hw/hfi1/aspm.h @@ -218,9 +218,9 @@ unlock: } /* Timer function for re-enabling ASPM in the absence of interrupt activity */ -static inline void aspm_ctx_timer_function(unsigned long data) +static inline void aspm_ctx_timer_function(struct timer_list *t) { - struct hfi1_ctxtdata *rcd = (struct hfi1_ctxtdata *)data; + struct hfi1_ctxtdata *rcd = from_timer(rcd, t, aspm_timer); unsigned long flags; spin_lock_irqsave(&rcd->aspm_lock, flags); @@ -281,8 +281,7 @@ static inline void aspm_enable_all(struct hfi1_devdata *dd) static inline void aspm_ctx_init(struct hfi1_ctxtdata *rcd) { spin_lock_init(&rcd->aspm_lock); - setup_timer(&rcd->aspm_timer, aspm_ctx_timer_function, - (unsigned long)rcd); + timer_setup(&rcd->aspm_timer, aspm_ctx_timer_function, 0); rcd->aspm_intr_supported = rcd->dd->aspm_supported && aspm_mode == ASPM_MODE_DYNAMIC && rcd->ctxt < rcd->dd->first_dyn_alloc_ctxt; diff --git a/drivers/infiniband/hw/hfi1/chip.c b/drivers/infiniband/hw/hfi1/chip.c index 0be42787759f..05e03a05fcc9 100644 --- a/drivers/infiniband/hw/hfi1/chip.c +++ b/drivers/infiniband/hw/hfi1/chip.c @@ -5538,9 +5538,9 @@ static void handle_cce_err(struct hfi1_devdata *dd, u32 unused, u64 reg) * associated with them. */ #define RCVERR_CHECK_TIME 10 -static void update_rcverr_timer(unsigned long opaque) +static void update_rcverr_timer(struct timer_list *t) { - struct hfi1_devdata *dd = (struct hfi1_devdata *)opaque; + struct hfi1_devdata *dd = from_timer(dd, t, rcverr_timer); struct hfi1_pportdata *ppd = dd->pport; u32 cur_ovfl_cnt = read_dev_cntr(dd, C_RCV_OVF, CNTR_INVALID_VL); @@ -5559,7 +5559,7 @@ static void update_rcverr_timer(unsigned long opaque) static int init_rcverr(struct hfi1_devdata *dd) { - setup_timer(&dd->rcverr_timer, update_rcverr_timer, (unsigned long)dd); + timer_setup(&dd->rcverr_timer, update_rcverr_timer, 0); /* Assume the hardware counter has been reset */ dd->rcv_ovfl_cnt = 0; return mod_timer(&dd->rcverr_timer, jiffies + HZ * RCVERR_CHECK_TIME); @@ -5567,9 +5567,8 @@ static int init_rcverr(struct hfi1_devdata *dd) static void free_rcverr(struct hfi1_devdata *dd) { - if (dd->rcverr_timer.data) + if (dd->rcverr_timer.function) del_timer_sync(&dd->rcverr_timer); - dd->rcverr_timer.data = 0; } static void handle_rxe_err(struct hfi1_devdata *dd, u32 unused, u64 reg) @@ -6520,12 +6519,11 @@ static void _dc_start(struct hfi1_devdata *dd) if (!dd->dc_shutdown) return; - /* Take the 8051 out of reset */ - write_csr(dd, DC_DC8051_CFG_RST, 0ull); - /* Wait until 8051 is ready */ - if (wait_fm_ready(dd, TIMEOUT_8051_START)) - dd_dev_err(dd, "%s: timeout starting 8051 firmware\n", - __func__); + /* + * Take the 8051 out of reset, wait until 8051 is ready, and set host + * version bit. + */ + release_and_wait_ready_8051_firmware(dd); /* Take away reset for LCB and RX FPE (set in lcb_shutdown). */ write_csr(dd, DCC_CFG_RESET, 0x10); @@ -8595,30 +8593,23 @@ int write_lcb_csr(struct hfi1_devdata *dd, u32 addr, u64 data) } /* + * If the 8051 is in reset mode (dd->dc_shutdown == 1), this function + * will still continue executing. + * * Returns: * < 0 = Linux error, not able to get access * > 0 = 8051 command RETURN_CODE */ -static int do_8051_command( - struct hfi1_devdata *dd, - u32 type, - u64 in_data, - u64 *out_data) +static int _do_8051_command(struct hfi1_devdata *dd, u32 type, u64 in_data, + u64 *out_data) { u64 reg, completed; int return_code; unsigned long timeout; + lockdep_assert_held(&dd->dc8051_lock); hfi1_cdbg(DC8051, "type %d, data 0x%012llx", type, in_data); - mutex_lock(&dd->dc8051_lock); - - /* We can't send any commands to the 8051 if it's in reset */ - if (dd->dc_shutdown) { - return_code = -ENODEV; - goto fail; - } - /* * If an 8051 host command timed out previously, then the 8051 is * stuck. @@ -8719,6 +8710,29 @@ static int do_8051_command( write_csr(dd, DC_DC8051_CFG_HOST_CMD_0, 0); fail: + return return_code; +} + +/* + * Returns: + * < 0 = Linux error, not able to get access + * > 0 = 8051 command RETURN_CODE + */ +static int do_8051_command(struct hfi1_devdata *dd, u32 type, u64 in_data, + u64 *out_data) +{ + int return_code; + + mutex_lock(&dd->dc8051_lock); + /* We can't send any commands to the 8051 if it's in reset */ + if (dd->dc_shutdown) { + return_code = -ENODEV; + goto fail; + } + + return_code = _do_8051_command(dd, type, in_data, out_data); + +fail: mutex_unlock(&dd->dc8051_lock); return return_code; } @@ -8728,16 +8742,17 @@ static int set_physical_link_state(struct hfi1_devdata *dd, u64 state) return do_8051_command(dd, HCMD_CHANGE_PHY_STATE, state, NULL); } -int load_8051_config(struct hfi1_devdata *dd, u8 field_id, - u8 lane_id, u32 config_data) +static int _load_8051_config(struct hfi1_devdata *dd, u8 field_id, + u8 lane_id, u32 config_data) { u64 data; int ret; + lockdep_assert_held(&dd->dc8051_lock); data = (u64)field_id << LOAD_DATA_FIELD_ID_SHIFT | (u64)lane_id << LOAD_DATA_LANE_ID_SHIFT | (u64)config_data << LOAD_DATA_DATA_SHIFT; - ret = do_8051_command(dd, HCMD_LOAD_CONFIG_DATA, data, NULL); + ret = _do_8051_command(dd, HCMD_LOAD_CONFIG_DATA, data, NULL); if (ret != HCMD_SUCCESS) { dd_dev_err(dd, "load 8051 config: field id %d, lane %d, err %d\n", @@ -8746,6 +8761,18 @@ int load_8051_config(struct hfi1_devdata *dd, u8 field_id, return ret; } +int load_8051_config(struct hfi1_devdata *dd, u8 field_id, + u8 lane_id, u32 config_data) +{ + int return_code; + + mutex_lock(&dd->dc8051_lock); + return_code = _load_8051_config(dd, field_id, lane_id, config_data); + mutex_unlock(&dd->dc8051_lock); + + return return_code; +} + /* * Read the 8051 firmware "registers". Use the RAM directly. Always * set the result, even on error. @@ -8861,13 +8888,14 @@ int write_host_interface_version(struct hfi1_devdata *dd, u8 version) u32 frame; u32 mask; + lockdep_assert_held(&dd->dc8051_lock); mask = (HOST_INTERFACE_VERSION_MASK << HOST_INTERFACE_VERSION_SHIFT); read_8051_config(dd, RESERVED_REGISTERS, GENERAL_CONFIG, &frame); /* Clear, then set field */ frame &= ~mask; frame |= ((u32)version << HOST_INTERFACE_VERSION_SHIFT); - return load_8051_config(dd, RESERVED_REGISTERS, GENERAL_CONFIG, - frame); + return _load_8051_config(dd, RESERVED_REGISTERS, GENERAL_CONFIG, + frame); } void read_misc_status(struct hfi1_devdata *dd, u8 *ver_major, u8 *ver_minor, @@ -9161,25 +9189,6 @@ static int do_quick_linkup(struct hfi1_devdata *dd) } /* - * Set the SerDes to internal loopback mode. - * Returns 0 on success, -errno on error. - */ -static int set_serdes_loopback_mode(struct hfi1_devdata *dd) -{ - int ret; - - ret = set_physical_link_state(dd, PLS_INTERNAL_SERDES_LOOPBACK); - if (ret == HCMD_SUCCESS) - return 0; - dd_dev_err(dd, - "Set physical link state to SerDes Loopback failed with return %d\n", - ret); - if (ret >= 0) - ret = -EINVAL; - return ret; -} - -/* * Do all special steps to set up loopback. */ static int init_loopback(struct hfi1_devdata *dd) @@ -9204,13 +9213,11 @@ static int init_loopback(struct hfi1_devdata *dd) return 0; } - /* handle serdes loopback */ - if (loopback == LOOPBACK_SERDES) { - /* internal serdes loopack needs quick linkup on RTL */ - if (dd->icode == ICODE_RTL_SILICON) - quick_linkup = 1; - return set_serdes_loopback_mode(dd); - } + /* + * SerDes loopback init sequence is handled in set_local_link_attributes + */ + if (loopback == LOOPBACK_SERDES) + return 0; /* LCB loopback - handled at poll time */ if (loopback == LOOPBACK_LCB) { @@ -9269,7 +9276,7 @@ static int set_local_link_attributes(struct hfi1_pportdata *ppd) u8 tx_polarity_inversion; u8 rx_polarity_inversion; int ret; - + u32 misc_bits = 0; /* reset our fabric serdes to clear any lingering problems */ fabric_serdes_reset(dd); @@ -9315,7 +9322,14 @@ static int set_local_link_attributes(struct hfi1_pportdata *ppd) if (ret != HCMD_SUCCESS) goto set_local_link_attributes_fail; - ret = write_vc_local_link_width(dd, 0, 0, + /* + * SerDes loopback init sequence requires + * setting bit 0 of MISC_CONFIG_BITS + */ + if (loopback == LOOPBACK_SERDES) + misc_bits |= 1 << LOOPBACK_SERDES_CONFIG_BIT_MASK_SHIFT; + + ret = write_vc_local_link_width(dd, misc_bits, 0, opa_to_vc_link_widths( ppd->link_width_enabled)); if (ret != HCMD_SUCCESS) @@ -9952,7 +9966,7 @@ int hfi1_get_ib_cfg(struct hfi1_pportdata *ppd, int which) goto unimplemented; case HFI1_IB_CFG_OP_VLS: - val = ppd->vls_operational; + val = ppd->actual_vls_operational; break; case HFI1_IB_CFG_VL_HIGH_CAP: /* VL arb high priority table size */ val = VL_ARB_HIGH_PRIO_TABLE_SIZE; @@ -9967,7 +9981,7 @@ int hfi1_get_ib_cfg(struct hfi1_pportdata *ppd, int which) val = ppd->phy_error_threshold; break; case HFI1_IB_CFG_LINKDEFAULT: /* IB link default (sleep/poll) */ - val = dd->link_default; + val = HLS_DEFAULT; break; case HFI1_IB_CFG_HRTBT: /* Heartbeat off/enable/auto */ @@ -10170,6 +10184,10 @@ static const char * const state_complete_reasons[] = { [0x33] = "Link partner completed the VerifyCap state, but the passing lanes do not meet the local link width policy", [0x34] = tx_out_of_policy, + [0x35] = "Negotiated link width is mutually exclusive", + [0x36] = + "Timed out before receiving verifycap frames in VerifyCap.Exchange", + [0x37] = "Unable to resolve secure data exchange", }; static const char *state_complete_reason_code_string(struct hfi1_pportdata *ppd, @@ -10298,9 +10316,6 @@ static void force_logical_link_state_down(struct hfi1_pportdata *ppd) write_csr(dd, DC_LCB_CFG_ALLOW_LINK_UP, 0); write_csr(dd, DC_LCB_CFG_IGNORE_LOST_RCLK, 0); - /* adjust ppd->statusp, if needed */ - update_statusp(ppd, IB_PORT_DOWN); - dd_dev_info(ppd->dd, "logical state forced to LINK_DOWN\n"); } @@ -10382,6 +10397,7 @@ static int goto_offline(struct hfi1_pportdata *ppd, u8 rem_reason) force_logical_link_state_down(ppd); ppd->host_link_state = HLS_LINK_COOLDOWN; /* LCB access allowed */ + update_statusp(ppd, IB_PORT_DOWN); /* * The LNI has a mandatory wait time after the physical state @@ -10569,7 +10585,7 @@ int set_link_state(struct hfi1_pportdata *ppd, u32 state) orig_new_state = state; if (state == HLS_DN_DOWNDEF) - state = dd->link_default; + state = HLS_DEFAULT; /* interpret poll -> poll as a link bounce */ poll_bounce = ppd->host_link_state == HLS_DN_POLL && @@ -10643,6 +10659,7 @@ int set_link_state(struct hfi1_pportdata *ppd, u32 state) handle_linkup_change(dd, 1); ppd->host_link_state = HLS_UP_INIT; + update_statusp(ppd, IB_PORT_INIT); break; case HLS_UP_ARMED: if (ppd->host_link_state != HLS_UP_INIT) @@ -10664,6 +10681,7 @@ int set_link_state(struct hfi1_pportdata *ppd, u32 state) break; } ppd->host_link_state = HLS_UP_ARMED; + update_statusp(ppd, IB_PORT_ARMED); /* * The simulator does not currently implement SMA messages, * so neighbor_normal is not set. Set it here when we first @@ -10686,6 +10704,7 @@ int set_link_state(struct hfi1_pportdata *ppd, u32 state) /* tell all engines to go running */ sdma_all_running(dd); ppd->host_link_state = HLS_UP_ACTIVE; + update_statusp(ppd, IB_PORT_ACTIVE); /* Signal the IB layer that the port has went active */ event.device = &dd->verbs_dev.rdi.ibdev; @@ -12089,9 +12108,8 @@ static void free_cntrs(struct hfi1_devdata *dd) struct hfi1_pportdata *ppd; int i; - if (dd->synth_stats_timer.data) + if (dd->synth_stats_timer.function) del_timer_sync(&dd->synth_stats_timer); - dd->synth_stats_timer.data = 0; ppd = (struct hfi1_pportdata *)(dd + 1); for (i = 0; i < dd->num_pports; i++, ppd++) { kfree(ppd->cntrs); @@ -12367,9 +12385,9 @@ static void do_update_synth_timer(struct work_struct *work) } } -static void update_synth_timer(unsigned long opaque) +static void update_synth_timer(struct timer_list *t) { - struct hfi1_devdata *dd = (struct hfi1_devdata *)opaque; + struct hfi1_devdata *dd = from_timer(dd, t, synth_stats_timer); queue_work(dd->update_cntr_wq, &dd->update_cntr_work); mod_timer(&dd->synth_stats_timer, jiffies + HZ * SYNTH_CNT_TIME); @@ -12387,8 +12405,7 @@ static int init_cntrs(struct hfi1_devdata *dd) const int bit_type_32_sz = strlen(bit_type_32); /* set up the stats timer; the add_timer is done at the end */ - setup_timer(&dd->synth_stats_timer, update_synth_timer, - (unsigned long)dd); + timer_setup(&dd->synth_stats_timer, update_synth_timer, 0); /***********************/ /* per device counters */ @@ -12701,6 +12718,17 @@ const char *opa_pstate_name(u32 pstate) return "unknown"; } +/** + * update_statusp - Update userspace status flag + * @ppd: Port data structure + * @state: port state information + * + * Actual port status is determined by the host_link_state value + * in the ppd. + * + * host_link_state MUST be updated before updating the user space + * statusp. + */ static void update_statusp(struct hfi1_pportdata *ppd, u32 state) { /* @@ -12726,9 +12754,11 @@ static void update_statusp(struct hfi1_pportdata *ppd, u32 state) break; } } + dd_dev_info(ppd->dd, "logical state changed to %s (0x%x)\n", + opa_lstate_name(state), state); } -/* +/** * wait_logical_linkstate - wait for an IB link state change to occur * @ppd: port device * @state: the state to wait for @@ -12759,11 +12789,6 @@ static int wait_logical_linkstate(struct hfi1_pportdata *ppd, u32 state, msleep(20); } - update_statusp(ppd, state); - dd_dev_info(ppd->dd, - "logical state changed to %s (0x%x)\n", - opa_lstate_name(state), - state); return 0; } @@ -12910,6 +12935,32 @@ int hfi1_tempsense_rd(struct hfi1_devdata *dd, struct hfi1_temp *temp) return ret; } +/** + * get_int_mask - get 64 bit int mask + * @dd - the devdata + * @i - the csr (relative to CCE_INT_MASK) + * + * Returns the mask with the urgent interrupt mask + * bit clear for kernel receive contexts. + */ +static u64 get_int_mask(struct hfi1_devdata *dd, u32 i) +{ + u64 mask = U64_MAX; /* default to no change */ + + if (i >= (IS_RCVURGENT_START / 64) && i < (IS_RCVURGENT_END / 64)) { + int j = (i - (IS_RCVURGENT_START / 64)) * 64; + int k = !j ? IS_RCVURGENT_START % 64 : 0; + + if (j) + j -= IS_RCVURGENT_START % 64; + /* j = 0..dd->first_dyn_alloc_ctxt - 1,k = 0..63 */ + for (; j < dd->first_dyn_alloc_ctxt && k < 64; j++, k++) + /* convert to bit in mask and clear */ + mask &= ~BIT_ULL(k); + } + return mask; +} + /* ========================================================================= */ /* @@ -12923,9 +12974,12 @@ void set_intr_state(struct hfi1_devdata *dd, u32 enable) * In HFI, the mask needs to be 1 to allow interrupts. */ if (enable) { - /* enable all interrupts */ - for (i = 0; i < CCE_NUM_INT_CSRS; i++) - write_csr(dd, CCE_INT_MASK + (8 * i), ~(u64)0); + /* enable all interrupts but urgent on kernel contexts */ + for (i = 0; i < CCE_NUM_INT_CSRS; i++) { + u64 mask = get_int_mask(dd, i); + + write_csr(dd, CCE_INT_MASK + (8 * i), mask); + } init_qsfp_int(dd); } else { @@ -12980,7 +13034,7 @@ static void clean_up_interrupts(struct hfi1_devdata *dd) if (!me->arg) /* => no irq, no affinity */ continue; hfi1_put_irq_affinity(dd, me); - free_irq(me->irq, me->arg); + pci_free_irq(dd->pcidev, i, me->arg); } /* clean structures */ @@ -12990,7 +13044,7 @@ static void clean_up_interrupts(struct hfi1_devdata *dd) } else { /* INTx */ if (dd->requested_intx_irq) { - free_irq(dd->pcidev->irq, dd); + pci_free_irq(dd->pcidev, 0, dd); dd->requested_intx_irq = 0; } disable_intx(dd->pcidev); @@ -13049,10 +13103,8 @@ static int request_intx_irq(struct hfi1_devdata *dd) { int ret; - snprintf(dd->intx_name, sizeof(dd->intx_name), DRIVER_NAME "_%d", - dd->unit); - ret = request_irq(dd->pcidev->irq, general_interrupt, - IRQF_SHARED, dd->intx_name, dd); + ret = pci_request_irq(dd->pcidev, 0, general_interrupt, NULL, dd, + DRIVER_NAME "_%d", dd->unit); if (ret) dd_dev_err(dd, "unable to request INTx interrupt, err %d\n", ret); @@ -13074,7 +13126,7 @@ static int request_msix_irqs(struct hfi1_devdata *dd) first_sdma = last_general; last_sdma = first_sdma + dd->num_sdma; first_rx = last_sdma; - last_rx = first_rx + dd->n_krcv_queues + HFI1_NUM_VNIC_CTXT; + last_rx = first_rx + dd->n_krcv_queues + dd->num_vnic_contexts; /* VNIC MSIx interrupts get mapped when VNIC contexts are created */ dd->first_dyn_msix_idx = first_rx + dd->n_krcv_queues; @@ -13095,13 +13147,14 @@ static int request_msix_irqs(struct hfi1_devdata *dd) int idx; struct hfi1_ctxtdata *rcd = NULL; struct sdma_engine *sde = NULL; + char name[MAX_NAME_SIZE]; - /* obtain the arguments to request_irq */ + /* obtain the arguments to pci_request_irq */ if (first_general <= i && i < last_general) { idx = i - first_general; handler = general_interrupt; arg = dd; - snprintf(me->name, sizeof(me->name), + snprintf(name, sizeof(name), DRIVER_NAME "_%d", dd->unit); err_info = "general"; me->type = IRQ_GENERAL; @@ -13110,14 +13163,14 @@ static int request_msix_irqs(struct hfi1_devdata *dd) sde = &dd->per_sdma[idx]; handler = sdma_interrupt; arg = sde; - snprintf(me->name, sizeof(me->name), + snprintf(name, sizeof(name), DRIVER_NAME "_%d sdma%d", dd->unit, idx); err_info = "sdma"; remap_sdma_interrupts(dd, idx, i); me->type = IRQ_SDMA; } else if (first_rx <= i && i < last_rx) { idx = i - first_rx; - rcd = hfi1_rcd_get_by_index(dd, idx); + rcd = hfi1_rcd_get_by_index_safe(dd, idx); if (rcd) { /* * Set the interrupt register and mask for this @@ -13129,7 +13182,7 @@ static int request_msix_irqs(struct hfi1_devdata *dd) handler = receive_context_interrupt; thread = receive_context_thread; arg = rcd; - snprintf(me->name, sizeof(me->name), + snprintf(name, sizeof(name), DRIVER_NAME "_%d kctxt%d", dd->unit, idx); err_info = "receive context"; @@ -13150,18 +13203,10 @@ static int request_msix_irqs(struct hfi1_devdata *dd) if (!arg) continue; /* make sure the name is terminated */ - me->name[sizeof(me->name) - 1] = 0; + name[sizeof(name) - 1] = 0; me->irq = pci_irq_vector(dd->pcidev, i); - /* - * On err return me->irq. Don't need to clear this - * because 'arg' has not been set, and cleanup will - * do the right thing. - */ - if (me->irq < 0) - return me->irq; - - ret = request_threaded_irq(me->irq, handler, thread, 0, - me->name, arg); + ret = pci_request_irq(dd->pcidev, i, handler, thread, arg, + name); if (ret) { dd_dev_err(dd, "unable to allocate %s interrupt, irq %d, index %d, err %d\n", @@ -13169,7 +13214,7 @@ static int request_msix_irqs(struct hfi1_devdata *dd) return ret; } /* - * assign arg after request_irq call, so it will be + * assign arg after pci_request_irq call, so it will be * cleaned up */ me->arg = arg; @@ -13187,7 +13232,7 @@ void hfi1_vnic_synchronize_irq(struct hfi1_devdata *dd) int i; if (!dd->num_msix_entries) { - synchronize_irq(dd->pcidev->irq); + synchronize_irq(pci_irq_vector(dd->pcidev, 0)); return; } @@ -13208,7 +13253,7 @@ void hfi1_reset_vnic_msix_info(struct hfi1_ctxtdata *rcd) return; hfi1_put_irq_affinity(dd, me); - free_irq(me->irq, me->arg); + pci_free_irq(dd->pcidev, rcd->msix_intr, me->arg); me->arg = NULL; } @@ -13231,28 +13276,21 @@ void hfi1_set_vnic_msix_info(struct hfi1_ctxtdata *rcd) rcd->ireg = (IS_RCVAVAIL_START + idx) / 64; rcd->imask = ((u64)1) << ((IS_RCVAVAIL_START + idx) % 64); - - snprintf(me->name, sizeof(me->name), - DRIVER_NAME "_%d kctxt%d", dd->unit, idx); - me->name[sizeof(me->name) - 1] = 0; me->type = IRQ_RCVCTXT; me->irq = pci_irq_vector(dd->pcidev, rcd->msix_intr); - if (me->irq < 0) { - dd_dev_err(dd, "vnic irq vector request (idx %d) fail %d\n", - idx, me->irq); - return; - } remap_intr(dd, IS_RCVAVAIL_START + idx, rcd->msix_intr); - ret = request_threaded_irq(me->irq, receive_context_interrupt, - receive_context_thread, 0, me->name, arg); + ret = pci_request_irq(dd->pcidev, rcd->msix_intr, + receive_context_interrupt, + receive_context_thread, arg, + DRIVER_NAME "_%d kctxt%d", dd->unit, idx); if (ret) { dd_dev_err(dd, "vnic irq request (irq %d, idx %d) fail %d\n", me->irq, idx, ret); return; } /* - * assign arg after request_irq call, so it will be + * assign arg after pci_request_irq call, so it will be * cleaned up */ me->arg = arg; @@ -13261,7 +13299,7 @@ void hfi1_set_vnic_msix_info(struct hfi1_ctxtdata *rcd) if (ret) { dd_dev_err(dd, "unable to pin IRQ %d\n", ret); - free_irq(me->irq, me->arg); + pci_free_irq(dd->pcidev, rcd->msix_intr, me->arg); } } @@ -13294,8 +13332,9 @@ static int set_up_interrupts(struct hfi1_devdata *dd) * slow source, SDMACleanupDone) * N interrupts - one per used SDMA engine * M interrupt - one per kernel receive context + * V interrupt - one for each VNIC context */ - total = 1 + dd->num_sdma + dd->n_krcv_queues + HFI1_NUM_VNIC_CTXT; + total = 1 + dd->num_sdma + dd->n_krcv_queues + dd->num_vnic_contexts; /* ask for MSI-X interrupts */ request = request_msix(dd, total); @@ -13356,15 +13395,18 @@ fail: * in array of contexts * freectxts - number of free user contexts * num_send_contexts - number of PIO send contexts being used + * num_vnic_contexts - number of contexts reserved for VNIC */ static int set_up_context_variables(struct hfi1_devdata *dd) { unsigned long num_kernel_contexts; + u16 num_vnic_contexts = HFI1_NUM_VNIC_CTXT; int total_contexts; int ret; unsigned ngroups; int qos_rmt_count; int user_rmt_reduced; + u32 n_usr_ctxts; /* * Kernel receive contexts: @@ -13393,59 +13435,63 @@ static int set_up_context_variables(struct hfi1_devdata *dd) num_kernel_contexts); num_kernel_contexts = dd->chip_send_contexts - num_vls - 1; } + + /* Accommodate VNIC contexts if possible */ + if ((num_kernel_contexts + num_vnic_contexts) > dd->chip_rcv_contexts) { + dd_dev_err(dd, "No receive contexts available for VNIC\n"); + num_vnic_contexts = 0; + } + total_contexts = num_kernel_contexts + num_vnic_contexts; + /* * User contexts: * - default to 1 user context per real (non-HT) CPU core if * num_user_contexts is negative */ if (num_user_contexts < 0) - num_user_contexts = - cpumask_weight(&node_affinity.real_cpu_mask); - - total_contexts = num_kernel_contexts + num_user_contexts; - + n_usr_ctxts = cpumask_weight(&node_affinity.real_cpu_mask); + else + n_usr_ctxts = num_user_contexts; /* * Adjust the counts given a global max. */ - if (total_contexts > dd->chip_rcv_contexts) { + if (total_contexts + n_usr_ctxts > dd->chip_rcv_contexts) { dd_dev_err(dd, - "Reducing # user receive contexts to: %d, from %d\n", - (int)(dd->chip_rcv_contexts - num_kernel_contexts), - (int)num_user_contexts); - num_user_contexts = dd->chip_rcv_contexts - num_kernel_contexts; + "Reducing # user receive contexts to: %d, from %u\n", + (int)(dd->chip_rcv_contexts - total_contexts), + n_usr_ctxts); /* recalculate */ - total_contexts = num_kernel_contexts + num_user_contexts; + n_usr_ctxts = dd->chip_rcv_contexts - total_contexts; } /* each user context requires an entry in the RMT */ qos_rmt_count = qos_rmt_entries(dd, NULL, NULL); - if (qos_rmt_count + num_user_contexts > NUM_MAP_ENTRIES) { + if (qos_rmt_count + n_usr_ctxts > NUM_MAP_ENTRIES) { user_rmt_reduced = NUM_MAP_ENTRIES - qos_rmt_count; dd_dev_err(dd, - "RMT size is reducing the number of user receive contexts from %d to %d\n", - (int)num_user_contexts, + "RMT size is reducing the number of user receive contexts from %u to %d\n", + n_usr_ctxts, user_rmt_reduced); /* recalculate */ - num_user_contexts = user_rmt_reduced; - total_contexts = num_kernel_contexts + num_user_contexts; + n_usr_ctxts = user_rmt_reduced; } - /* Accommodate VNIC contexts */ - if ((total_contexts + HFI1_NUM_VNIC_CTXT) <= dd->chip_rcv_contexts) - total_contexts += HFI1_NUM_VNIC_CTXT; + total_contexts += n_usr_ctxts; /* the first N are kernel contexts, the rest are user/vnic contexts */ dd->num_rcv_contexts = total_contexts; dd->n_krcv_queues = num_kernel_contexts; dd->first_dyn_alloc_ctxt = num_kernel_contexts; - dd->num_user_contexts = num_user_contexts; - dd->freectxts = num_user_contexts; + dd->num_vnic_contexts = num_vnic_contexts; + dd->num_user_contexts = n_usr_ctxts; + dd->freectxts = n_usr_ctxts; dd_dev_info(dd, - "rcv contexts: chip %d, used %d (kernel %d, user %d)\n", + "rcv contexts: chip %d, used %d (kernel %d, vnic %u, user %u)\n", (int)dd->chip_rcv_contexts, (int)dd->num_rcv_contexts, (int)dd->n_krcv_queues, - (int)dd->num_rcv_contexts - dd->n_krcv_queues); + dd->num_vnic_contexts, + dd->num_user_contexts); /* * Receive array allocation: @@ -14962,8 +15008,6 @@ struct hfi1_devdata *hfi1_init_dd(struct pci_dev *pdev, init_vl_arb_caches(ppd); } - dd->link_default = HLS_DN_POLL; - /* * Do remaining PCIe setup and save PCIe values in dd. * Any error printing is already done by the init code. diff --git a/drivers/infiniband/hw/hfi1/chip.h b/drivers/infiniband/hw/hfi1/chip.h index 50b8645d0b87..fc122c1b1eea 100644 --- a/drivers/infiniband/hw/hfi1/chip.h +++ b/drivers/infiniband/hw/hfi1/chip.h @@ -583,6 +583,9 @@ enum { #define LOOPBACK_LCB 2 #define LOOPBACK_CABLE 3 /* external cable */ +/* set up serdes bit in MISC_CONFIG_BITS */ +#define LOOPBACK_SERDES_CONFIG_BIT_MASK_SHIFT 0 + /* read and write hardware registers */ u64 read_csr(const struct hfi1_devdata *dd, u32 offset); void write_csr(const struct hfi1_devdata *dd, u32 offset, u64 value); @@ -710,6 +713,7 @@ void read_misc_status(struct hfi1_devdata *dd, u8 *ver_major, u8 *ver_minor, u8 *ver_patch); int write_host_interface_version(struct hfi1_devdata *dd, u8 version); void read_guid(struct hfi1_devdata *dd); +int release_and_wait_ready_8051_firmware(struct hfi1_devdata *dd); int wait_fm_ready(struct hfi1_devdata *dd, u32 mstimeout); void set_link_down_reason(struct hfi1_pportdata *ppd, u8 lcl_reason, u8 neigh_reason, u8 rem_reason); diff --git a/drivers/infiniband/hw/hfi1/common.h b/drivers/infiniband/hw/hfi1/common.h index 3e27794ec750..7108d4d92259 100644 --- a/drivers/infiniband/hw/hfi1/common.h +++ b/drivers/infiniband/hw/hfi1/common.h @@ -328,6 +328,7 @@ struct diag_pkt { #define SC15_PACKET 0xF #define SIZE_OF_CRC 1 #define SIZE_OF_LT 1 +#define MAX_16B_PADDING 12 /* CRC = 4, LT = 1, Pad = 0 to 7 bytes */ #define LIM_MGMT_P_KEY 0x7FFF #define FULL_MGMT_P_KEY 0xFFFF diff --git a/drivers/infiniband/hw/hfi1/debugfs.c b/drivers/infiniband/hw/hfi1/debugfs.c index 36ae1fd86502..76157cc03eca 100644 --- a/drivers/infiniband/hw/hfi1/debugfs.c +++ b/drivers/infiniband/hw/hfi1/debugfs.c @@ -165,6 +165,17 @@ static void _opcode_stats_seq_stop(struct seq_file *s, void *v) { } +static int opcode_stats_show(struct seq_file *s, u8 i, u64 packets, u64 bytes) +{ + if (!packets && !bytes) + return SEQ_SKIP; + seq_printf(s, "%02x %llu/%llu\n", i, + (unsigned long long)packets, + (unsigned long long)bytes); + + return 0; +} + static int _opcode_stats_seq_show(struct seq_file *s, void *v) { loff_t *spos = v; @@ -182,19 +193,49 @@ static int _opcode_stats_seq_show(struct seq_file *s, void *v) } hfi1_rcd_put(rcd); } - if (!n_packets && !n_bytes) - return SEQ_SKIP; - seq_printf(s, "%02llx %llu/%llu\n", i, - (unsigned long long)n_packets, - (unsigned long long)n_bytes); - - return 0; + return opcode_stats_show(s, i, n_packets, n_bytes); } DEBUGFS_SEQ_FILE_OPS(opcode_stats); DEBUGFS_SEQ_FILE_OPEN(opcode_stats) DEBUGFS_FILE_OPS(opcode_stats); +static void *_tx_opcode_stats_seq_start(struct seq_file *s, loff_t *pos) +{ + return _opcode_stats_seq_start(s, pos); +} + +static void *_tx_opcode_stats_seq_next(struct seq_file *s, void *v, loff_t *pos) +{ + return _opcode_stats_seq_next(s, v, pos); +} + +static void _tx_opcode_stats_seq_stop(struct seq_file *s, void *v) +{ +} + +static int _tx_opcode_stats_seq_show(struct seq_file *s, void *v) +{ + loff_t *spos = v; + loff_t i = *spos; + int j; + u64 n_packets = 0, n_bytes = 0; + struct hfi1_ibdev *ibd = (struct hfi1_ibdev *)s->private; + struct hfi1_devdata *dd = dd_from_dev(ibd); + + for_each_possible_cpu(j) { + struct hfi1_opcode_stats_perctx *s = + per_cpu_ptr(dd->tx_opstats, j); + n_packets += s->stats[i].n_packets; + n_bytes += s->stats[i].n_bytes; + } + return opcode_stats_show(s, i, n_packets, n_bytes); +} + +DEBUGFS_SEQ_FILE_OPS(tx_opcode_stats); +DEBUGFS_SEQ_FILE_OPEN(tx_opcode_stats) +DEBUGFS_FILE_OPS(tx_opcode_stats); + static void *_ctx_stats_seq_start(struct seq_file *s, loff_t *pos) { struct hfi1_ibdev *ibd = (struct hfi1_ibdev *)s->private; @@ -243,7 +284,7 @@ static int _ctx_stats_seq_show(struct seq_file *s, void *v) spos = v; i = *spos; - rcd = hfi1_rcd_get_by_index(dd, i); + rcd = hfi1_rcd_get_by_index_safe(dd, i); if (!rcd) return SEQ_SKIP; @@ -402,7 +443,7 @@ static int _rcds_seq_show(struct seq_file *s, void *v) loff_t *spos = v; loff_t i = *spos; - rcd = hfi1_rcd_get_by_index(dd, i); + rcd = hfi1_rcd_get_by_index_safe(dd, i); if (rcd) seqfile_dump_rcd(s, rcd); hfi1_rcd_put(rcd); @@ -1363,6 +1404,7 @@ void hfi1_dbg_ibdev_init(struct hfi1_ibdev *ibd) return; } DEBUGFS_SEQ_FILE_CREATE(opcode_stats, ibd->hfi1_ibdev_dbg, ibd); + DEBUGFS_SEQ_FILE_CREATE(tx_opcode_stats, ibd->hfi1_ibdev_dbg, ibd); DEBUGFS_SEQ_FILE_CREATE(ctx_stats, ibd->hfi1_ibdev_dbg, ibd); DEBUGFS_SEQ_FILE_CREATE(qp_stats, ibd->hfi1_ibdev_dbg, ibd); DEBUGFS_SEQ_FILE_CREATE(sdes, ibd->hfi1_ibdev_dbg, ibd); diff --git a/drivers/infiniband/hw/hfi1/driver.c b/drivers/infiniband/hw/hfi1/driver.c index 7372cc00cb2d..07a32a1c1303 100644 --- a/drivers/infiniband/hw/hfi1/driver.c +++ b/drivers/infiniband/hw/hfi1/driver.c @@ -433,6 +433,12 @@ static inline void init_packet(struct hfi1_ctxtdata *rcd, packet->numpkt = 0; } +/* We support only two types - 9B and 16B for now */ +static const hfi1_handle_cnp hfi1_handle_cnp_tbl[2] = { + [HFI1_PKT_TYPE_9B] = &return_cnp, + [HFI1_PKT_TYPE_16B] = &return_cnp_16B +}; + void hfi1_process_ecn_slowpath(struct rvt_qp *qp, struct hfi1_packet *pkt, bool do_cnp) { @@ -866,7 +872,7 @@ static inline void set_nodma_rtail(struct hfi1_devdata *dd, u16 ctxt) * interrupt handler for all statically allocated kernel contexts. */ if (ctxt >= dd->first_dyn_alloc_ctxt) { - rcd = hfi1_rcd_get_by_index(dd, ctxt); + rcd = hfi1_rcd_get_by_index_safe(dd, ctxt); if (rcd) { rcd->do_interrupt = &handle_receive_interrupt_nodma_rtail; @@ -895,7 +901,7 @@ static inline void set_dma_rtail(struct hfi1_devdata *dd, u16 ctxt) * interrupt handler for all statically allocated kernel contexts. */ if (ctxt >= dd->first_dyn_alloc_ctxt) { - rcd = hfi1_rcd_get_by_index(dd, ctxt); + rcd = hfi1_rcd_get_by_index_safe(dd, ctxt); if (rcd) { rcd->do_interrupt = &handle_receive_interrupt_dma_rtail; @@ -1252,9 +1258,9 @@ void shutdown_led_override(struct hfi1_pportdata *ppd) write_csr(dd, DCC_CFG_LED_CNTRL, 0); } -static void run_led_override(unsigned long opaque) +static void run_led_override(struct timer_list *t) { - struct hfi1_pportdata *ppd = (struct hfi1_pportdata *)opaque; + struct hfi1_pportdata *ppd = from_timer(ppd, t, led_override_timer); struct hfi1_devdata *dd = ppd->dd; unsigned long timeout; int phase_idx; @@ -1298,8 +1304,7 @@ void hfi1_start_led_override(struct hfi1_pportdata *ppd, unsigned int timeon, * timeout so the handler will be called soon to look at our request. */ if (!timer_pending(&ppd->led_override_timer)) { - setup_timer(&ppd->led_override_timer, run_led_override, - (unsigned long)ppd); + timer_setup(&ppd->led_override_timer, run_led_override, 0); ppd->led_override_timer.expires = jiffies + 1; add_timer(&ppd->led_override_timer); atomic_set(&ppd->led_override_timer_active, 1); diff --git a/drivers/infiniband/hw/hfi1/file_ops.c b/drivers/infiniband/hw/hfi1/file_ops.c index d9a1e9893136..7750a9c38b06 100644 --- a/drivers/infiniband/hw/hfi1/file_ops.c +++ b/drivers/infiniband/hw/hfi1/file_ops.c @@ -78,16 +78,20 @@ static unsigned int hfi1_poll(struct file *fp, struct poll_table_struct *pt); static int hfi1_file_mmap(struct file *fp, struct vm_area_struct *vma); static u64 kvirt_to_phys(void *addr); -static int assign_ctxt(struct hfi1_filedata *fd, struct hfi1_user_info *uinfo); +static int assign_ctxt(struct hfi1_filedata *fd, unsigned long arg, u32 len); static void init_subctxts(struct hfi1_ctxtdata *uctxt, const struct hfi1_user_info *uinfo); static int init_user_ctxt(struct hfi1_filedata *fd, struct hfi1_ctxtdata *uctxt); static void user_init(struct hfi1_ctxtdata *uctxt); -static int get_ctxt_info(struct hfi1_filedata *fd, void __user *ubase, - __u32 len); -static int get_base_info(struct hfi1_filedata *fd, void __user *ubase, - __u32 len); +static int get_ctxt_info(struct hfi1_filedata *fd, unsigned long arg, u32 len); +static int get_base_info(struct hfi1_filedata *fd, unsigned long arg, u32 len); +static int user_exp_rcv_setup(struct hfi1_filedata *fd, unsigned long arg, + u32 len); +static int user_exp_rcv_clear(struct hfi1_filedata *fd, unsigned long arg, + u32 len); +static int user_exp_rcv_invalid(struct hfi1_filedata *fd, unsigned long arg, + u32 len); static int setup_base_ctxt(struct hfi1_filedata *fd, struct hfi1_ctxtdata *uctxt); static int setup_subctxt(struct hfi1_ctxtdata *uctxt); @@ -101,10 +105,11 @@ static void deallocate_ctxt(struct hfi1_ctxtdata *uctxt); static unsigned int poll_urgent(struct file *fp, struct poll_table_struct *pt); static unsigned int poll_next(struct file *fp, struct poll_table_struct *pt); static int user_event_ack(struct hfi1_ctxtdata *uctxt, u16 subctxt, - unsigned long events); -static int set_ctxt_pkey(struct hfi1_ctxtdata *uctxt, u16 subctxt, u16 pkey); + unsigned long arg); +static int set_ctxt_pkey(struct hfi1_ctxtdata *uctxt, unsigned long arg); +static int ctxt_reset(struct hfi1_ctxtdata *uctxt); static int manage_rcvq(struct hfi1_ctxtdata *uctxt, u16 subctxt, - int start_stop); + unsigned long arg); static int vma_fault(struct vm_fault *vmf); static long hfi1_file_ioctl(struct file *fp, unsigned int cmd, unsigned long arg); @@ -221,13 +226,8 @@ static long hfi1_file_ioctl(struct file *fp, unsigned int cmd, { struct hfi1_filedata *fd = fp->private_data; struct hfi1_ctxtdata *uctxt = fd->uctxt; - struct hfi1_user_info uinfo; - struct hfi1_tid_info tinfo; int ret = 0; - unsigned long addr; int uval = 0; - unsigned long ul_uval = 0; - u16 uval16 = 0; hfi1_cdbg(IOCTL, "IOCTL recv: 0x%x", cmd); if (cmd != HFI1_IOCTL_ASSIGN_CTXT && @@ -237,171 +237,55 @@ static long hfi1_file_ioctl(struct file *fp, unsigned int cmd, switch (cmd) { case HFI1_IOCTL_ASSIGN_CTXT: - if (uctxt) - return -EINVAL; - - if (copy_from_user(&uinfo, - (struct hfi1_user_info __user *)arg, - sizeof(uinfo))) - return -EFAULT; - - ret = assign_ctxt(fd, &uinfo); + ret = assign_ctxt(fd, arg, _IOC_SIZE(cmd)); break; + case HFI1_IOCTL_CTXT_INFO: - ret = get_ctxt_info(fd, (void __user *)(unsigned long)arg, - sizeof(struct hfi1_ctxt_info)); + ret = get_ctxt_info(fd, arg, _IOC_SIZE(cmd)); break; + case HFI1_IOCTL_USER_INFO: - ret = get_base_info(fd, (void __user *)(unsigned long)arg, - sizeof(struct hfi1_base_info)); + ret = get_base_info(fd, arg, _IOC_SIZE(cmd)); break; + case HFI1_IOCTL_CREDIT_UPD: if (uctxt) sc_return_credits(uctxt->sc); break; case HFI1_IOCTL_TID_UPDATE: - if (copy_from_user(&tinfo, - (struct hfi11_tid_info __user *)arg, - sizeof(tinfo))) - return -EFAULT; - - ret = hfi1_user_exp_rcv_setup(fd, &tinfo); - if (!ret) { - /* - * Copy the number of tidlist entries we used - * and the length of the buffer we registered. - */ - addr = arg + offsetof(struct hfi1_tid_info, tidcnt); - if (copy_to_user((void __user *)addr, &tinfo.tidcnt, - sizeof(tinfo.tidcnt))) - return -EFAULT; - - addr = arg + offsetof(struct hfi1_tid_info, length); - if (copy_to_user((void __user *)addr, &tinfo.length, - sizeof(tinfo.length))) - ret = -EFAULT; - } + ret = user_exp_rcv_setup(fd, arg, _IOC_SIZE(cmd)); break; case HFI1_IOCTL_TID_FREE: - if (copy_from_user(&tinfo, - (struct hfi11_tid_info __user *)arg, - sizeof(tinfo))) - return -EFAULT; - - ret = hfi1_user_exp_rcv_clear(fd, &tinfo); - if (ret) - break; - addr = arg + offsetof(struct hfi1_tid_info, tidcnt); - if (copy_to_user((void __user *)addr, &tinfo.tidcnt, - sizeof(tinfo.tidcnt))) - ret = -EFAULT; + ret = user_exp_rcv_clear(fd, arg, _IOC_SIZE(cmd)); break; case HFI1_IOCTL_TID_INVAL_READ: - if (copy_from_user(&tinfo, - (struct hfi11_tid_info __user *)arg, - sizeof(tinfo))) - return -EFAULT; - - ret = hfi1_user_exp_rcv_invalid(fd, &tinfo); - if (ret) - break; - addr = arg + offsetof(struct hfi1_tid_info, tidcnt); - if (copy_to_user((void __user *)addr, &tinfo.tidcnt, - sizeof(tinfo.tidcnt))) - ret = -EFAULT; + ret = user_exp_rcv_invalid(fd, arg, _IOC_SIZE(cmd)); break; case HFI1_IOCTL_RECV_CTRL: - ret = get_user(uval, (int __user *)arg); - if (ret != 0) - return -EFAULT; - ret = manage_rcvq(uctxt, fd->subctxt, uval); + ret = manage_rcvq(uctxt, fd->subctxt, arg); break; case HFI1_IOCTL_POLL_TYPE: - ret = get_user(uval, (int __user *)arg); - if (ret != 0) + if (get_user(uval, (int __user *)arg)) return -EFAULT; uctxt->poll_type = (typeof(uctxt->poll_type))uval; break; case HFI1_IOCTL_ACK_EVENT: - ret = get_user(ul_uval, (unsigned long __user *)arg); - if (ret != 0) - return -EFAULT; - ret = user_event_ack(uctxt, fd->subctxt, ul_uval); + ret = user_event_ack(uctxt, fd->subctxt, arg); break; case HFI1_IOCTL_SET_PKEY: - ret = get_user(uval16, (u16 __user *)arg); - if (ret != 0) - return -EFAULT; - if (HFI1_CAP_IS_USET(PKEY_CHECK)) - ret = set_ctxt_pkey(uctxt, fd->subctxt, uval16); - else - return -EPERM; + ret = set_ctxt_pkey(uctxt, arg); break; - case HFI1_IOCTL_CTXT_RESET: { - struct send_context *sc; - struct hfi1_devdata *dd; - - if (!uctxt || !uctxt->dd || !uctxt->sc) - return -EINVAL; - - /* - * There is no protection here. User level has to - * guarantee that no one will be writing to the send - * context while it is being re-initialized. - * If user level breaks that guarantee, it will break - * it's own context and no one else's. - */ - dd = uctxt->dd; - sc = uctxt->sc; - /* - * Wait until the interrupt handler has marked the - * context as halted or frozen. Report error if we time - * out. - */ - wait_event_interruptible_timeout( - sc->halt_wait, (sc->flags & SCF_HALTED), - msecs_to_jiffies(SEND_CTXT_HALT_TIMEOUT)); - if (!(sc->flags & SCF_HALTED)) - return -ENOLCK; - - /* - * If the send context was halted due to a Freeze, - * wait until the device has been "unfrozen" before - * resetting the context. - */ - if (sc->flags & SCF_FROZEN) { - wait_event_interruptible_timeout( - dd->event_queue, - !(ACCESS_ONCE(dd->flags) & HFI1_FROZEN), - msecs_to_jiffies(SEND_CTXT_HALT_TIMEOUT)); - if (dd->flags & HFI1_FROZEN) - return -ENOLCK; - - if (dd->flags & HFI1_FORCED_FREEZE) - /* - * Don't allow context reset if we are into - * forced freeze - */ - return -ENODEV; - - sc_disable(sc); - ret = sc_enable(sc); - hfi1_rcvctrl(dd, HFI1_RCVCTRL_CTXT_ENB, uctxt); - } else { - ret = sc_restart(sc); - } - if (!ret) - sc_return_credits(sc); + case HFI1_IOCTL_CTXT_RESET: + ret = ctxt_reset(uctxt); break; - } case HFI1_IOCTL_GET_VERS: uval = HFI1_USER_SWVERSION; @@ -595,9 +479,8 @@ static int hfi1_file_mmap(struct file *fp, struct vm_area_struct *vma) * Use the page where this context's flags are. User level * knows where it's own bitmap is within the page. */ - memaddr = (unsigned long)(dd->events + - ((uctxt->ctxt - dd->first_dyn_alloc_ctxt) * - HFI1_MAX_SHARED_CTXTS)) & PAGE_MASK; + memaddr = (unsigned long) + (dd->events + uctxt_offset(uctxt)) & PAGE_MASK; memlen = PAGE_SIZE; /* * v3.7 removes VM_RESERVED but the effect is kept by @@ -779,8 +662,7 @@ static int hfi1_file_close(struct inode *inode, struct file *fp) * Clear any left over, unhandled events so the next process that * gets this context doesn't get confused. */ - ev = dd->events + ((uctxt->ctxt - dd->first_dyn_alloc_ctxt) * - HFI1_MAX_SHARED_CTXTS) + fdata->subctxt; + ev = dd->events + uctxt_offset(uctxt) + fdata->subctxt; *ev = 0; spin_lock_irqsave(&dd->uctxt_lock, flags); @@ -891,21 +773,29 @@ static int complete_subctxt(struct hfi1_filedata *fd) return ret; } -static int assign_ctxt(struct hfi1_filedata *fd, struct hfi1_user_info *uinfo) +static int assign_ctxt(struct hfi1_filedata *fd, unsigned long arg, u32 len) { int ret; - unsigned int swmajor, swminor; + unsigned int swmajor; struct hfi1_ctxtdata *uctxt = NULL; + struct hfi1_user_info uinfo; + + if (fd->uctxt) + return -EINVAL; + + if (sizeof(uinfo) != len) + return -EINVAL; - swmajor = uinfo->userversion >> 16; + if (copy_from_user(&uinfo, (void __user *)arg, sizeof(uinfo))) + return -EFAULT; + + swmajor = uinfo.userversion >> 16; if (swmajor != HFI1_USER_SWMAJOR) return -ENODEV; - if (uinfo->subctxt_cnt > HFI1_MAX_SHARED_CTXTS) + if (uinfo.subctxt_cnt > HFI1_MAX_SHARED_CTXTS) return -EINVAL; - swminor = uinfo->userversion & 0xffff; - /* * Acquire the mutex to protect against multiple creations of what * could be a shared base context. @@ -915,14 +805,14 @@ static int assign_ctxt(struct hfi1_filedata *fd, struct hfi1_user_info *uinfo) * Get a sub context if available (fd->uctxt will be set). * ret < 0 error, 0 no context, 1 sub-context found */ - ret = find_sub_ctxt(fd, uinfo); + ret = find_sub_ctxt(fd, &uinfo); /* * Allocate a base context if context sharing is not required or a * sub context wasn't found. */ if (!ret) - ret = allocate_ctxt(fd, fd->dd, uinfo, &uctxt); + ret = allocate_ctxt(fd, fd->dd, &uinfo, &uctxt); mutex_unlock(&hfi1_mutex); @@ -1230,12 +1120,13 @@ static void user_init(struct hfi1_ctxtdata *uctxt) hfi1_rcvctrl(uctxt->dd, rcvctrl_ops, uctxt); } -static int get_ctxt_info(struct hfi1_filedata *fd, void __user *ubase, - __u32 len) +static int get_ctxt_info(struct hfi1_filedata *fd, unsigned long arg, u32 len) { struct hfi1_ctxt_info cinfo; struct hfi1_ctxtdata *uctxt = fd->uctxt; - int ret = 0; + + if (sizeof(cinfo) != len) + return -EINVAL; memset(&cinfo, 0, sizeof(cinfo)); cinfo.runtime_flags = (((uctxt->flags >> HFI1_CAP_MISC_SHIFT) & @@ -1265,10 +1156,10 @@ static int get_ctxt_info(struct hfi1_filedata *fd, void __user *ubase, cinfo.rcvegr_size = uctxt->egrbufs.rcvtid_size; trace_hfi1_ctxt_info(uctxt->dd, uctxt->ctxt, fd->subctxt, cinfo); - if (copy_to_user(ubase, &cinfo, sizeof(cinfo))) - ret = -EFAULT; + if (copy_to_user((void __user *)arg, &cinfo, len)) + return -EFAULT; - return ret; + return 0; } static int init_user_ctxt(struct hfi1_filedata *fd, @@ -1344,18 +1235,18 @@ done: return ret; } -static int get_base_info(struct hfi1_filedata *fd, void __user *ubase, - __u32 len) +static int get_base_info(struct hfi1_filedata *fd, unsigned long arg, u32 len) { struct hfi1_base_info binfo; struct hfi1_ctxtdata *uctxt = fd->uctxt; struct hfi1_devdata *dd = uctxt->dd; - ssize_t sz; unsigned offset; - int ret = 0; trace_hfi1_uctxtdata(uctxt->dd, uctxt, fd->subctxt); + if (sizeof(binfo) != len) + return -EINVAL; + memset(&binfo, 0, sizeof(binfo)); binfo.hw_version = dd->revision; binfo.sw_version = HFI1_KERN_SWVERSION; @@ -1385,39 +1276,152 @@ static int get_base_info(struct hfi1_filedata *fd, void __user *ubase, fd->subctxt, uctxt->egrbufs.rcvtids[0].dma); binfo.sdma_comp_bufbase = HFI1_MMAP_TOKEN(SDMA_COMP, uctxt->ctxt, - fd->subctxt, 0); + fd->subctxt, 0); /* * user regs are at * (RXE_PER_CONTEXT_USER + (ctxt * RXE_PER_CONTEXT_SIZE)) */ binfo.user_regbase = HFI1_MMAP_TOKEN(UREGS, uctxt->ctxt, - fd->subctxt, 0); - offset = offset_in_page((((uctxt->ctxt - dd->first_dyn_alloc_ctxt) * - HFI1_MAX_SHARED_CTXTS) + fd->subctxt) * - sizeof(*dd->events)); + fd->subctxt, 0); + offset = offset_in_page((uctxt_offset(uctxt) + fd->subctxt) * + sizeof(*dd->events)); binfo.events_bufbase = HFI1_MMAP_TOKEN(EVENTS, uctxt->ctxt, - fd->subctxt, - offset); + fd->subctxt, + offset); binfo.status_bufbase = HFI1_MMAP_TOKEN(STATUS, uctxt->ctxt, - fd->subctxt, - dd->status); + fd->subctxt, + dd->status); if (HFI1_CAP_IS_USET(DMA_RTAIL)) binfo.rcvhdrtail_base = HFI1_MMAP_TOKEN(RTAIL, uctxt->ctxt, - fd->subctxt, 0); + fd->subctxt, 0); if (uctxt->subctxt_cnt) { binfo.subctxt_uregbase = HFI1_MMAP_TOKEN(SUBCTXT_UREGS, - uctxt->ctxt, - fd->subctxt, 0); - binfo.subctxt_rcvhdrbuf = HFI1_MMAP_TOKEN(SUBCTXT_RCV_HDRQ, uctxt->ctxt, fd->subctxt, 0); + binfo.subctxt_rcvhdrbuf = HFI1_MMAP_TOKEN(SUBCTXT_RCV_HDRQ, + uctxt->ctxt, + fd->subctxt, 0); binfo.subctxt_rcvegrbuf = HFI1_MMAP_TOKEN(SUBCTXT_EGRBUF, - uctxt->ctxt, - fd->subctxt, 0); + uctxt->ctxt, + fd->subctxt, 0); } - sz = (len < sizeof(binfo)) ? len : sizeof(binfo); - if (copy_to_user(ubase, &binfo, sz)) + + if (copy_to_user((void __user *)arg, &binfo, len)) + return -EFAULT; + + return 0; +} + +/** + * user_exp_rcv_setup - Set up the given tid rcv list + * @fd: file data of the current driver instance + * @arg: ioctl argumnent for user space information + * @len: length of data structure associated with ioctl command + * + * Wrapper to validate ioctl information before doing _rcv_setup. + * + */ +static int user_exp_rcv_setup(struct hfi1_filedata *fd, unsigned long arg, + u32 len) +{ + int ret; + unsigned long addr; + struct hfi1_tid_info tinfo; + + if (sizeof(tinfo) != len) + return -EINVAL; + + if (copy_from_user(&tinfo, (void __user *)arg, (sizeof(tinfo)))) + return -EFAULT; + + ret = hfi1_user_exp_rcv_setup(fd, &tinfo); + if (!ret) { + /* + * Copy the number of tidlist entries we used + * and the length of the buffer we registered. + */ + addr = arg + offsetof(struct hfi1_tid_info, tidcnt); + if (copy_to_user((void __user *)addr, &tinfo.tidcnt, + sizeof(tinfo.tidcnt))) + return -EFAULT; + + addr = arg + offsetof(struct hfi1_tid_info, length); + if (copy_to_user((void __user *)addr, &tinfo.length, + sizeof(tinfo.length))) + ret = -EFAULT; + } + + return ret; +} + +/** + * user_exp_rcv_clear - Clear the given tid rcv list + * @fd: file data of the current driver instance + * @arg: ioctl argumnent for user space information + * @len: length of data structure associated with ioctl command + * + * The hfi1_user_exp_rcv_clear() can be called from the error path. Because + * of this, we need to use this wrapper to copy the user space information + * before doing the clear. + */ +static int user_exp_rcv_clear(struct hfi1_filedata *fd, unsigned long arg, + u32 len) +{ + int ret; + unsigned long addr; + struct hfi1_tid_info tinfo; + + if (sizeof(tinfo) != len) + return -EINVAL; + + if (copy_from_user(&tinfo, (void __user *)arg, (sizeof(tinfo)))) + return -EFAULT; + + ret = hfi1_user_exp_rcv_clear(fd, &tinfo); + if (!ret) { + addr = arg + offsetof(struct hfi1_tid_info, tidcnt); + if (copy_to_user((void __user *)addr, &tinfo.tidcnt, + sizeof(tinfo.tidcnt))) + return -EFAULT; + } + + return ret; +} + +/** + * user_exp_rcv_invalid - Invalidate the given tid rcv list + * @fd: file data of the current driver instance + * @arg: ioctl argumnent for user space information + * @len: length of data structure associated with ioctl command + * + * Wrapper to validate ioctl information before doing _rcv_invalid. + * + */ +static int user_exp_rcv_invalid(struct hfi1_filedata *fd, unsigned long arg, + u32 len) +{ + int ret; + unsigned long addr; + struct hfi1_tid_info tinfo; + + if (sizeof(tinfo) != len) + return -EINVAL; + + if (!fd->invalid_tids) + return -EINVAL; + + if (copy_from_user(&tinfo, (void __user *)arg, (sizeof(tinfo)))) + return -EFAULT; + + ret = hfi1_user_exp_rcv_invalid(fd, &tinfo); + if (ret) + return ret; + + addr = arg + offsetof(struct hfi1_tid_info, tidcnt); + if (copy_to_user((void __user *)addr, &tinfo.tidcnt, + sizeof(tinfo.tidcnt))) ret = -EFAULT; + return ret; } @@ -1485,14 +1489,13 @@ int hfi1_set_uevent_bits(struct hfi1_pportdata *ppd, const int evtbit) ctxt++) { uctxt = hfi1_rcd_get_by_index(dd, ctxt); if (uctxt) { - unsigned long *evs = dd->events + - (uctxt->ctxt - dd->first_dyn_alloc_ctxt) * - HFI1_MAX_SHARED_CTXTS; + unsigned long *evs; int i; /* * subctxt_cnt is 0 if not shared, so do base * separately, first, then remaining subctxt, if any */ + evs = dd->events + uctxt_offset(uctxt); set_bit(evtbit, evs); for (i = 1; i < uctxt->subctxt_cnt; i++) set_bit(evtbit, evs + i); @@ -1514,13 +1517,18 @@ int hfi1_set_uevent_bits(struct hfi1_pportdata *ppd, const int evtbit) * re-init the software copy of the head register */ static int manage_rcvq(struct hfi1_ctxtdata *uctxt, u16 subctxt, - int start_stop) + unsigned long arg) { struct hfi1_devdata *dd = uctxt->dd; unsigned int rcvctrl_op; + int start_stop; if (subctxt) - goto bail; + return 0; + + if (get_user(start_stop, (int __user *)arg)) + return -EFAULT; + /* atomically clear receive enable ctxt. */ if (start_stop) { /* @@ -1539,7 +1547,7 @@ static int manage_rcvq(struct hfi1_ctxtdata *uctxt, u16 subctxt, } hfi1_rcvctrl(dd, rcvctrl_op, uctxt); /* always; new head should be equal to new tail; see above */ -bail: + return 0; } @@ -1549,17 +1557,20 @@ bail: * set, if desired, and checks again in future. */ static int user_event_ack(struct hfi1_ctxtdata *uctxt, u16 subctxt, - unsigned long events) + unsigned long arg) { int i; struct hfi1_devdata *dd = uctxt->dd; unsigned long *evs; + unsigned long events; if (!dd->events) return 0; - evs = dd->events + ((uctxt->ctxt - dd->first_dyn_alloc_ctxt) * - HFI1_MAX_SHARED_CTXTS) + subctxt; + if (get_user(events, (unsigned long __user *)arg)) + return -EFAULT; + + evs = dd->events + uctxt_offset(uctxt) + subctxt; for (i = 0; i <= _HFI1_MAX_EVENT_BIT; i++) { if (!test_bit(i, &events)) @@ -1569,26 +1580,89 @@ static int user_event_ack(struct hfi1_ctxtdata *uctxt, u16 subctxt, return 0; } -static int set_ctxt_pkey(struct hfi1_ctxtdata *uctxt, u16 subctxt, u16 pkey) +static int set_ctxt_pkey(struct hfi1_ctxtdata *uctxt, unsigned long arg) { - int ret = -ENOENT, i, intable = 0; + int i; struct hfi1_pportdata *ppd = uctxt->ppd; struct hfi1_devdata *dd = uctxt->dd; + u16 pkey; - if (pkey == LIM_MGMT_P_KEY || pkey == FULL_MGMT_P_KEY) { - ret = -EINVAL; - goto done; - } + if (!HFI1_CAP_IS_USET(PKEY_CHECK)) + return -EPERM; + + if (get_user(pkey, (u16 __user *)arg)) + return -EFAULT; + + if (pkey == LIM_MGMT_P_KEY || pkey == FULL_MGMT_P_KEY) + return -EINVAL; for (i = 0; i < ARRAY_SIZE(ppd->pkeys); i++) - if (pkey == ppd->pkeys[i]) { - intable = 1; - break; - } + if (pkey == ppd->pkeys[i]) + return hfi1_set_ctxt_pkey(dd, uctxt, pkey); + + return -ENOENT; +} + +/** + * ctxt_reset - Reset the user context + * @uctxt: valid user context + */ +static int ctxt_reset(struct hfi1_ctxtdata *uctxt) +{ + struct send_context *sc; + struct hfi1_devdata *dd; + int ret = 0; + + if (!uctxt || !uctxt->dd || !uctxt->sc) + return -EINVAL; + + /* + * There is no protection here. User level has to guarantee that + * no one will be writing to the send context while it is being + * re-initialized. If user level breaks that guarantee, it will + * break it's own context and no one else's. + */ + dd = uctxt->dd; + sc = uctxt->sc; + + /* + * Wait until the interrupt handler has marked the context as + * halted or frozen. Report error if we time out. + */ + wait_event_interruptible_timeout( + sc->halt_wait, (sc->flags & SCF_HALTED), + msecs_to_jiffies(SEND_CTXT_HALT_TIMEOUT)); + if (!(sc->flags & SCF_HALTED)) + return -ENOLCK; + + /* + * If the send context was halted due to a Freeze, wait until the + * device has been "unfrozen" before resetting the context. + */ + if (sc->flags & SCF_FROZEN) { + wait_event_interruptible_timeout( + dd->event_queue, + !(READ_ONCE(dd->flags) & HFI1_FROZEN), + msecs_to_jiffies(SEND_CTXT_HALT_TIMEOUT)); + if (dd->flags & HFI1_FROZEN) + return -ENOLCK; + + if (dd->flags & HFI1_FORCED_FREEZE) + /* + * Don't allow context reset if we are into + * forced freeze + */ + return -ENODEV; + + sc_disable(sc); + ret = sc_enable(sc); + hfi1_rcvctrl(dd, HFI1_RCVCTRL_CTXT_ENB, uctxt); + } else { + ret = sc_restart(sc); + } + if (!ret) + sc_return_credits(sc); - if (intable) - ret = hfi1_set_ctxt_pkey(dd, uctxt, pkey); -done: return ret; } diff --git a/drivers/infiniband/hw/hfi1/firmware.c b/drivers/infiniband/hw/hfi1/firmware.c index 5aea8f47e670..98868df78a7e 100644 --- a/drivers/infiniband/hw/hfi1/firmware.c +++ b/drivers/infiniband/hw/hfi1/firmware.c @@ -70,6 +70,11 @@ #define ALT_FW_PCIE_NAME "hfi1_pcie_d.fw" #define HOST_INTERFACE_VERSION 1 +MODULE_FIRMWARE(DEFAULT_FW_8051_NAME_ASIC); +MODULE_FIRMWARE(DEFAULT_FW_FABRIC_NAME); +MODULE_FIRMWARE(DEFAULT_FW_SBUS_NAME); +MODULE_FIRMWARE(DEFAULT_FW_PCIE_NAME); + static uint fw_8051_load = 1; static uint fw_fabric_serdes_load = 1; static uint fw_pcie_serdes_load = 1; @@ -113,6 +118,12 @@ struct css_header { #define MU_SIZE 8 #define EXPONENT_SIZE 4 +/* size of platform configuration partition */ +#define MAX_PLATFORM_CONFIG_FILE_SIZE 4096 + +/* size of file of plaform configuration encoded in format version 4 */ +#define PLATFORM_CONFIG_FORMAT_4_FILE_SIZE 528 + /* the file itself */ struct firmware_file { struct css_header css_header; @@ -965,6 +976,46 @@ int wait_fm_ready(struct hfi1_devdata *dd, u32 mstimeout) } /* + * Clear all reset bits, releasing the 8051. + * Wait for firmware to be ready to accept host requests. + * Then, set host version bit. + * + * This function executes even if the 8051 is in reset mode when + * dd->dc_shutdown == 1. + * + * Expects dd->dc8051_lock to be held. + */ +int release_and_wait_ready_8051_firmware(struct hfi1_devdata *dd) +{ + int ret; + + lockdep_assert_held(&dd->dc8051_lock); + /* clear all reset bits, releasing the 8051 */ + write_csr(dd, DC_DC8051_CFG_RST, 0ull); + + /* + * Wait for firmware to be ready to accept host + * requests. + */ + ret = wait_fm_ready(dd, TIMEOUT_8051_START); + if (ret) { + dd_dev_err(dd, "8051 start timeout, current FW state 0x%x\n", + get_firmware_state(dd)); + return ret; + } + + ret = write_host_interface_version(dd, HOST_INTERFACE_VERSION); + if (ret != HCMD_SUCCESS) { + dd_dev_err(dd, + "Failed to set host interface version, return 0x%x\n", + ret); + return -EIO; + } + + return 0; +} + +/* * Load the 8051 firmware. */ static int load_8051_firmware(struct hfi1_devdata *dd, @@ -1029,31 +1080,22 @@ static int load_8051_firmware(struct hfi1_devdata *dd, if (ret) return ret; - /* clear all reset bits, releasing the 8051 */ - write_csr(dd, DC_DC8051_CFG_RST, 0ull); - /* + * Clear all reset bits, releasing the 8051. * DC reset step 5. Wait for firmware to be ready to accept host * requests. + * Then, set host version bit. */ - ret = wait_fm_ready(dd, TIMEOUT_8051_START); - if (ret) { /* timed out */ - dd_dev_err(dd, "8051 start timeout, current state 0x%x\n", - get_firmware_state(dd)); - return -ETIMEDOUT; - } + mutex_lock(&dd->dc8051_lock); + ret = release_and_wait_ready_8051_firmware(dd); + mutex_unlock(&dd->dc8051_lock); + if (ret) + return ret; read_misc_status(dd, &ver_major, &ver_minor, &ver_patch); dd_dev_info(dd, "8051 firmware version %d.%d.%d\n", (int)ver_major, (int)ver_minor, (int)ver_patch); dd->dc8051_ver = dc8051_ver(ver_major, ver_minor, ver_patch); - ret = write_host_interface_version(dd, HOST_INTERFACE_VERSION); - if (ret != HCMD_SUCCESS) { - dd_dev_err(dd, - "Failed to set host interface version, return 0x%x\n", - ret); - return -EIO; - } return 0; } @@ -1387,7 +1429,14 @@ int acquire_hw_mutex(struct hfi1_devdata *dd) unsigned long timeout; int try = 0; u8 mask = 1 << dd->hfi1_id; - u8 user; + u8 user = (u8)read_csr(dd, ASIC_CFG_MUTEX); + + if (user == mask) { + dd_dev_info(dd, + "Hardware mutex already acquired, mutex mask %u\n", + (u32)mask); + return 0; + } retry: timeout = msecs_to_jiffies(HM_TIMEOUT) + jiffies; @@ -1418,7 +1467,15 @@ retry: void release_hw_mutex(struct hfi1_devdata *dd) { - write_csr(dd, ASIC_CFG_MUTEX, 0); + u8 mask = 1 << dd->hfi1_id; + u8 user = (u8)read_csr(dd, ASIC_CFG_MUTEX); + + if (user != mask) + dd_dev_warn(dd, + "Unable to release hardware mutex, mutex mask %u, my mask %u\n", + (u32)user, (u32)mask); + else + write_csr(dd, ASIC_CFG_MUTEX, 0); } /* return the given resource bit(s) as a mask for the given HFI */ @@ -1733,7 +1790,7 @@ static int check_meta_version(struct hfi1_devdata *dd, u32 *system_table) ver_start /= 8; meta_ver = *((u8 *)system_table + ver_start) & ((1 << ver_len) - 1); - if (meta_ver < 5) { + if (meta_ver < 4) { dd_dev_info( dd, "%s:Please update platform config\n", __func__); return -EINVAL; @@ -1774,7 +1831,20 @@ int parse_platform_config(struct hfi1_devdata *dd) /* Field is file size in DWORDs */ file_length = (*ptr) * 4; - ptr++; + + /* + * Length can't be larger than partition size. Assume platform + * config format version 4 is being used. Interpret the file size + * field as header instead by not moving the pointer. + */ + if (file_length > MAX_PLATFORM_CONFIG_FILE_SIZE) { + dd_dev_info(dd, + "%s:File length out of bounds, using alternative format\n", + __func__); + file_length = PLATFORM_CONFIG_FORMAT_4_FILE_SIZE; + } else { + ptr++; + } if (file_length > dd->platform_config.size) { dd_dev_info(dd, "%s:File claims to be larger than read size\n", @@ -1789,7 +1859,8 @@ int parse_platform_config(struct hfi1_devdata *dd) /* * In both cases where we proceed, using the self-reported file length - * is the safer option + * is the safer option. In case of old format a predefined value is + * being used. */ while (ptr < (u32 *)(dd->platform_config.data + file_length)) { header1 = *ptr; diff --git a/drivers/infiniband/hw/hfi1/hfi.h b/drivers/infiniband/hw/hfi1/hfi.h index 3ac9c307a285..08d394f384c6 100644 --- a/drivers/infiniband/hw/hfi1/hfi.h +++ b/drivers/infiniband/hw/hfi1/hfi.h @@ -164,9 +164,7 @@ extern const struct pci_error_handlers hfi1_pci_err_handler; * Below contains all data related to a single context (formerly called port). */ -#ifdef CONFIG_DEBUG_FS struct hfi1_opcode_stats_perctx; -#endif struct ctxt_eager_bufs { ssize_t size; /* total size of eager buffers */ @@ -283,7 +281,7 @@ struct hfi1_ctxtdata { u64 imask; /* clear interrupt mask */ int ireg; /* clear interrupt register */ unsigned numa_id; /* numa node of this context */ - /* verbs stats per CTX */ + /* verbs rx_stats per rcd */ struct hfi1_opcode_stats_perctx *opstats; /* Is ASPM interrupt supported for this context */ @@ -390,6 +388,7 @@ struct hfi1_packet { /* * OPA 16B L2/L4 Encodings */ +#define OPA_16B_L4_9B 0x00 #define OPA_16B_L2_TYPE 0x02 #define OPA_16B_L4_IB_LOCAL 0x09 #define OPA_16B_L4_IB_GLOBAL 0x0A @@ -535,6 +534,8 @@ struct rvt_sge_state; #define HLS_UP (HLS_UP_INIT | HLS_UP_ARMED | HLS_UP_ACTIVE) #define HLS_DOWN ~(HLS_UP) +#define HLS_DEFAULT HLS_DN_POLL + /* use this MTU size if none other is given */ #define HFI1_DEFAULT_ACTIVE_MTU 10240 /* use this MTU size as the default maximum */ @@ -616,7 +617,6 @@ struct hfi1_msix_entry { enum irq_type type; int irq; void *arg; - char name[MAX_NAME_SIZE]; cpumask_t mask; struct irq_affinity_notify notify; }; @@ -1047,6 +1047,8 @@ struct hfi1_devdata { u64 z_send_schedule; u64 __percpu *send_schedule; + /* number of reserved contexts for VNIC usage */ + u16 num_vnic_contexts; /* number of receive contexts in use by the driver */ u32 num_rcv_contexts; /* number of pio send contexts in use by the driver */ @@ -1109,8 +1111,7 @@ struct hfi1_devdata { u16 rcvegrbufsize_shift; /* both sides of the PCIe link are gen3 capable */ u8 link_gen3_capable; - /* default link down value (poll/sleep) */ - u8 link_default; + u8 dc_shutdown; /* localbus width (1, 2,4,8,16,32) from config space */ u32 lbus_width; /* localbus speed in MHz */ @@ -1183,7 +1184,6 @@ struct hfi1_devdata { /* INTx information */ u32 requested_intx_irq; /* did we request one? */ - char intx_name[MAX_NAME_SIZE]; /* INTx name */ /* general interrupt: mask of handled interrupts */ u64 gi_mask[CCE_NUM_INT_CSRS]; @@ -1274,6 +1274,8 @@ struct hfi1_devdata { /* receive context data */ struct hfi1_ctxtdata **rcd; u64 __percpu *int_counter; + /* verbs tx opcode stats */ + struct hfi1_opcode_stats_perctx __percpu *tx_opstats; /* device (not port) flags, basically device capabilities */ u16 flags; /* Number of physical ports available */ @@ -1295,7 +1297,6 @@ struct hfi1_devdata { u8 oui1; u8 oui2; u8 oui3; - u8 dc_shutdown; /* Timer and counter used to detect RcvBufOvflCnt changes */ struct timer_list rcverr_timer; @@ -1373,8 +1374,12 @@ struct hfi1_filedata { extern struct list_head hfi1_dev_list; extern spinlock_t hfi1_devs_lock; struct hfi1_devdata *hfi1_lookup(int unit); -extern u32 hfi1_cpulist_count; -extern unsigned long *hfi1_cpulist; + +static inline unsigned long uctxt_offset(struct hfi1_ctxtdata *uctxt) +{ + return (uctxt->ctxt - uctxt->dd->first_dyn_alloc_ctxt) * + HFI1_MAX_SHARED_CTXTS; +} int hfi1_init(struct hfi1_devdata *dd, int reinit); int hfi1_count_active_units(void); @@ -1396,6 +1401,8 @@ void hfi1_init_pportdata(struct pci_dev *pdev, struct hfi1_pportdata *ppd, void hfi1_free_ctxtdata(struct hfi1_devdata *dd, struct hfi1_ctxtdata *rcd); int hfi1_rcd_put(struct hfi1_ctxtdata *rcd); void hfi1_rcd_get(struct hfi1_ctxtdata *rcd); +struct hfi1_ctxtdata *hfi1_rcd_get_by_index_safe(struct hfi1_devdata *dd, + u16 ctxt); struct hfi1_ctxtdata *hfi1_rcd_get_by_index(struct hfi1_devdata *dd, u16 ctxt); int handle_receive_interrupt(struct hfi1_ctxtdata *rcd, int thread); int handle_receive_interrupt_nodma_rtail(struct hfi1_ctxtdata *rcd, int thread); @@ -1531,11 +1538,6 @@ typedef void (*hfi1_handle_cnp)(struct hfi1_ibport *ibp, struct rvt_qp *qp, u32 remote_qpn, u32 pkey, u32 slid, u32 dlid, u8 sc5, const struct ib_grh *old_grh); -/* We support only two types - 9B and 16B for now */ -static const hfi1_handle_cnp hfi1_handle_cnp_tbl[2] = { - [HFI1_PKT_TYPE_9B] = &return_cnp, - [HFI1_PKT_TYPE_16B] = &return_cnp_16B -}; #define PKEY_CHECK_INVALID -1 int egress_pkey_check(struct hfi1_pportdata *ppd, u32 slid, u16 pkey, u8 sc5, int8_t s_pkey_index); diff --git a/drivers/infiniband/hw/hfi1/init.c b/drivers/infiniband/hw/hfi1/init.c index fba77001c3a7..f29e7a327f29 100644 --- a/drivers/infiniband/hw/hfi1/init.c +++ b/drivers/infiniband/hw/hfi1/init.c @@ -123,8 +123,6 @@ MODULE_PARM_DESC(user_credit_return_threshold, "Credit return threshold for user static inline u64 encode_rcv_header_entry_size(u16 size); static struct idr hfi1_unit_table; -u32 hfi1_cpulist_count; -unsigned long *hfi1_cpulist; static int hfi1_create_kctxt(struct hfi1_devdata *dd, struct hfi1_pportdata *ppd) @@ -286,6 +284,27 @@ static int allocate_rcd_index(struct hfi1_devdata *dd, } /** + * hfi1_rcd_get_by_index_safe - validate the ctxt index before accessing the + * array + * @dd: pointer to a valid devdata structure + * @ctxt: the index of an possilbe rcd + * + * This is a wrapper for hfi1_rcd_get_by_index() to validate that the given + * ctxt index is valid. + * + * The caller is responsible for making the _put(). + * + */ +struct hfi1_ctxtdata *hfi1_rcd_get_by_index_safe(struct hfi1_devdata *dd, + u16 ctxt) +{ + if (ctxt < dd->num_rcv_contexts) + return hfi1_rcd_get_by_index(dd, ctxt); + + return NULL; +} + +/** * hfi1_rcd_get_by_index * @dd: pointer to a valid devdata structure * @ctxt: the index of an possilbe rcd @@ -1006,7 +1025,7 @@ static void stop_timers(struct hfi1_devdata *dd) for (pidx = 0; pidx < dd->num_pports; ++pidx) { ppd = dd->pport + pidx; - if (ppd->led_override_timer.data) { + if (ppd->led_override_timer.function) { del_timer_sync(&ppd->led_override_timer); atomic_set(&ppd->led_override_timer_active, 0); } @@ -1198,6 +1217,7 @@ static void __hfi1_free_devdata(struct kobject *kobj) free_percpu(dd->int_counter); free_percpu(dd->rcv_limit); free_percpu(dd->send_schedule); + free_percpu(dd->tx_opstats); rvt_dealloc_device(&dd->verbs_dev.rdi); } @@ -1272,39 +1292,27 @@ struct hfi1_devdata *hfi1_alloc_devdata(struct pci_dev *pdev, size_t extra) dd->int_counter = alloc_percpu(u64); if (!dd->int_counter) { ret = -ENOMEM; - hfi1_early_err(&pdev->dev, - "Could not allocate per-cpu int_counter\n"); goto bail; } dd->rcv_limit = alloc_percpu(u64); if (!dd->rcv_limit) { ret = -ENOMEM; - hfi1_early_err(&pdev->dev, - "Could not allocate per-cpu rcv_limit\n"); goto bail; } dd->send_schedule = alloc_percpu(u64); if (!dd->send_schedule) { ret = -ENOMEM; - hfi1_early_err(&pdev->dev, - "Could not allocate per-cpu int_counter\n"); goto bail; } - if (!hfi1_cpulist_count) { - u32 count = num_online_cpus(); - - hfi1_cpulist = kcalloc(BITS_TO_LONGS(count), sizeof(long), - GFP_KERNEL); - if (hfi1_cpulist) - hfi1_cpulist_count = count; - else - hfi1_early_err( - &pdev->dev, - "Could not alloc cpulist info, cpu affinity might be wrong\n"); + dd->tx_opstats = alloc_percpu(struct hfi1_opcode_stats_perctx); + if (!dd->tx_opstats) { + ret = -ENOMEM; + goto bail; } + kobject_init(&dd->kobj, &hfi1_devdata_type); return dd; @@ -1477,8 +1485,6 @@ static void __exit hfi1_mod_cleanup(void) node_affinity_destroy(); hfi1_wss_exit(); hfi1_dbg_exit(); - hfi1_cpulist_count = 0; - kfree(hfi1_cpulist); idr_destroy(&hfi1_unit_table); dispose_firmware(); /* asymmetric with obtain_firmware() */ diff --git a/drivers/infiniband/hw/hfi1/intr.c b/drivers/infiniband/hw/hfi1/intr.c index 96845dfed5c5..3e3184ddab5b 100644 --- a/drivers/infiniband/hw/hfi1/intr.c +++ b/drivers/infiniband/hw/hfi1/intr.c @@ -53,6 +53,8 @@ #include "common.h" #include "sdma.h" +#define LINK_UP_DELAY 500 /* in microseconds */ + /** * format_hwmsg - format a single hwerror message * @msg message buffer @@ -102,9 +104,16 @@ static void signal_ib_event(struct hfi1_pportdata *ppd, enum ib_event_type ev) ib_dispatch_event(&event); } -/* +/** + * handle_linkup_change - finish linkup/down state changes + * @dd: valid device + * @linkup: link state information + * * Handle a linkup or link down notification. + * The HW needs time to finish its link up state change. Give it that chance. + * * This is called outside an interrupt. + * */ void handle_linkup_change(struct hfi1_devdata *dd, u32 linkup) { @@ -151,6 +160,9 @@ void handle_linkup_change(struct hfi1_devdata *dd, u32 linkup) ppd->neighbor_guid, ppd->neighbor_type, ppd->neighbor_port_number); + /* HW needs LINK_UP_DELAY to settle, give it that chance */ + udelay(LINK_UP_DELAY); + /* physical link went up */ ppd->linkup = 1; ppd->offline_disabled_reason = diff --git a/drivers/infiniband/hw/hfi1/mad.c b/drivers/infiniband/hw/hfi1/mad.c index f4c0ffc040cc..e648f589bade 100644 --- a/drivers/infiniband/hw/hfi1/mad.c +++ b/drivers/infiniband/hw/hfi1/mad.c @@ -98,6 +98,16 @@ static inline void clear_opa_smp_data(struct opa_smp *smp) memset(data, 0, size); } +static u16 hfi1_lookup_pkey_value(struct hfi1_ibport *ibp, int pkey_idx) +{ + struct hfi1_pportdata *ppd = ppd_from_ibp(ibp); + + if (pkey_idx < ARRAY_SIZE(ppd->pkeys)) + return ppd->pkeys[pkey_idx]; + + return 0; +} + void hfi1_event_pkey_change(struct hfi1_devdata *dd, u8 port) { struct ib_event event; @@ -399,9 +409,9 @@ static void send_trap(struct hfi1_ibport *ibp, struct trap_node *trap) ib_free_send_mad(send_buf); } -void hfi1_handle_trap_timer(unsigned long data) +void hfi1_handle_trap_timer(struct timer_list *t) { - struct hfi1_ibport *ibp = (struct hfi1_ibport *)data; + struct hfi1_ibport *ibp = from_timer(ibp, t, rvp.trap_timer); struct trap_node *trap = NULL; unsigned long flags; int i; @@ -711,6 +721,7 @@ static int check_mkey(struct hfi1_ibport *ibp, struct ib_mad_hdr *mad, /* Bad mkey not a violation below level 2 */ if (ibp->rvp.mkeyprot < 2) break; + /* fall through */ case IB_MGMT_METHOD_SET: case IB_MGMT_METHOD_TRAP_REPRESS: if (ibp->rvp.mkey_violations != 0xFFFF) @@ -2888,7 +2899,6 @@ static int pma_get_opa_datacounters(struct opa_pma_mad *pmp, struct _vls_dctrs *vlinfo; size_t response_data_size; u32 num_ports; - u8 num_pslm; u8 lq, num_vls; u8 res_lli, res_ler; u64 port_mask; @@ -2898,7 +2908,6 @@ static int pma_get_opa_datacounters(struct opa_pma_mad *pmp, int vfi; num_ports = be32_to_cpu(pmp->mad_hdr.attr_mod) >> 24; - num_pslm = hweight64(be64_to_cpu(req->port_select_mask[3])); num_vls = hweight32(be32_to_cpu(req->vl_select_mask)); vl_select_mask = be32_to_cpu(req->vl_select_mask); res_lli = (u8)(be32_to_cpu(req->resolution) & MSK_LLI) >> MSK_LLI_SFT; @@ -4260,6 +4269,18 @@ void clear_linkup_counters(struct hfi1_devdata *dd) dd->err_info_xmit_constraint.status &= ~OPA_EI_STATUS_SMASK; } +static int is_full_mgmt_pkey_in_table(struct hfi1_ibport *ibp) +{ + unsigned int i; + struct hfi1_pportdata *ppd = ppd_from_ibp(ibp); + + for (i = 0; i < ARRAY_SIZE(ppd->pkeys); ++i) + if (ppd->pkeys[i] == FULL_MGMT_P_KEY) + return 1; + + return 0; +} + /* * is_local_mad() returns 1 if 'mad' is sent from, and destined to the * local node, 0 otherwise. @@ -4293,7 +4314,6 @@ static int opa_local_smp_check(struct hfi1_ibport *ibp, const struct ib_wc *in_wc) { struct hfi1_pportdata *ppd = ppd_from_ibp(ibp); - u16 slid = ib_lid_cpu16(in_wc->slid); u16 pkey; if (in_wc->pkey_index >= ARRAY_SIZE(ppd->pkeys)) @@ -4320,10 +4340,71 @@ static int opa_local_smp_check(struct hfi1_ibport *ibp, */ if (pkey == LIM_MGMT_P_KEY || pkey == FULL_MGMT_P_KEY) return 0; - ingress_pkey_table_fail(ppd, pkey, slid); + /* + * On OPA devices it is okay to lose the upper 16 bits of LID as this + * information is obtained elsewhere. Mask off the upper 16 bits. + */ + ingress_pkey_table_fail(ppd, pkey, ib_lid_cpu16(0xFFFF & in_wc->slid)); return 1; } +/** + * hfi1_pkey_validation_pma - It validates PKEYs for incoming PMA MAD packets. + * @ibp: IB port data + * @in_mad: MAD packet with header and data + * @in_wc: Work completion data such as source LID, port number, etc. + * + * These are all the possible logic rules for validating a pkey: + * + * a) If pkey neither FULL_MGMT_P_KEY nor LIM_MGMT_P_KEY, + * and NOT self-originated packet: + * Drop MAD packet as it should always be part of the + * management partition unless it's a self-originated packet. + * + * b) If pkey_index -> FULL_MGMT_P_KEY, and LIM_MGMT_P_KEY in pkey table: + * The packet is coming from a management node and the receiving node + * is also a management node, so it is safe for the packet to go through. + * + * c) If pkey_index -> FULL_MGMT_P_KEY, and LIM_MGMT_P_KEY is NOT in pkey table: + * Drop the packet as LIM_MGMT_P_KEY should always be in the pkey table. + * It could be an FM misconfiguration. + * + * d) If pkey_index -> LIM_MGMT_P_KEY and FULL_MGMT_P_KEY is NOT in pkey table: + * It is safe for the packet to go through since a non-management node is + * talking to another non-management node. + * + * e) If pkey_index -> LIM_MGMT_P_KEY and FULL_MGMT_P_KEY in pkey table: + * Drop the packet because a non-management node is talking to a + * management node, and it could be an attack. + * + * For the implementation, these rules can be simplied to only checking + * for (a) and (e). There's no need to check for rule (b) as + * the packet doesn't need to be dropped. Rule (c) is not possible in + * the driver as LIM_MGMT_P_KEY is always in the pkey table. + * + * Return: + * 0 - pkey is okay, -EINVAL it's a bad pkey + */ +static int hfi1_pkey_validation_pma(struct hfi1_ibport *ibp, + const struct opa_mad *in_mad, + const struct ib_wc *in_wc) +{ + u16 pkey_value = hfi1_lookup_pkey_value(ibp, in_wc->pkey_index); + + /* Rule (a) from above */ + if (!is_local_mad(ibp, in_mad, in_wc) && + pkey_value != LIM_MGMT_P_KEY && + pkey_value != FULL_MGMT_P_KEY) + return -EINVAL; + + /* Rule (e) from above */ + if (pkey_value == LIM_MGMT_P_KEY && + is_full_mgmt_pkey_in_table(ibp)) + return -EINVAL; + + return 0; +} + static int process_subn_opa(struct ib_device *ibdev, int mad_flags, u8 port, const struct opa_mad *in_mad, struct opa_mad *out_mad, @@ -4663,8 +4744,11 @@ static int hfi1_process_opa_mad(struct ib_device *ibdev, int mad_flags, out_mad, &resp_len); goto bail; case IB_MGMT_CLASS_PERF_MGMT: - ret = process_perf_opa(ibdev, port, in_mad, out_mad, - &resp_len); + ret = hfi1_pkey_validation_pma(ibp, in_mad, in_wc); + if (ret) + return IB_MAD_RESULT_FAILURE; + + ret = process_perf_opa(ibdev, port, in_mad, out_mad, &resp_len); goto bail; default: diff --git a/drivers/infiniband/hw/hfi1/mad.h b/drivers/infiniband/hw/hfi1/mad.h index 4c1245072093..a4f8ac16332c 100644 --- a/drivers/infiniband/hw/hfi1/mad.h +++ b/drivers/infiniband/hw/hfi1/mad.h @@ -428,6 +428,6 @@ struct sc2vlnt { COUNTER_MASK(1, 4)) void hfi1_event_pkey_change(struct hfi1_devdata *dd, u8 port); -void hfi1_handle_trap_timer(unsigned long data); +void hfi1_handle_trap_timer(struct timer_list *t); #endif /* _HFI1_MAD_H */ diff --git a/drivers/infiniband/hw/hfi1/rc.c b/drivers/infiniband/hw/hfi1/rc.c index e1cf0c08ca6f..32d7bbe9738c 100644 --- a/drivers/infiniband/hw/hfi1/rc.c +++ b/drivers/infiniband/hw/hfi1/rc.c @@ -276,7 +276,6 @@ int hfi1_make_rc_req(struct rvt_qp *qp, struct hfi1_pkt_state *ps) if (IS_ERR(ps->s_txreq)) goto bail_no_tx; - ps->s_txreq->phdr.hdr.hdr_type = priv->hdr_type; if (priv->hdr_type == HFI1_PKT_TYPE_9B) { /* header size in 32-bit words LRH+BTH = (8+12)/4. */ hwords = 5; @@ -2175,7 +2174,7 @@ send_middle: goto no_immediate_data; if (opcode == OP(SEND_ONLY_WITH_INVALIDATE)) goto send_last_inv; - /* FALLTHROUGH for SEND_ONLY_WITH_IMMEDIATE */ + /* FALLTHROUGH -- for SEND_ONLY_WITH_IMMEDIATE */ case OP(SEND_LAST_WITH_IMMEDIATE): send_last_imm: wc.ex.imm_data = ohdr->u.imm_data; diff --git a/drivers/infiniband/hw/hfi1/ruc.c b/drivers/infiniband/hw/hfi1/ruc.c index b3291f0fde9a..d450d4d4bda3 100644 --- a/drivers/infiniband/hw/hfi1/ruc.c +++ b/drivers/infiniband/hw/hfi1/ruc.c @@ -825,11 +825,9 @@ static inline void hfi1_make_ruc_header_9B(struct rvt_qp *qp, { struct hfi1_qp_priv *priv = qp->priv; struct hfi1_ibport *ibp = ps->ibp; - struct hfi1_pportdata *ppd = ppd_from_ibp(ibp); u32 bth1 = 0; u16 pkey = hfi1_get_pkey(ibp, qp->s_pkey_index); u16 lrh0 = HFI1_LRH_BTH; - u16 slid; u8 extra_bytes = -ps->s_txreq->s_cur_size & 3; u32 nwords = SIZE_OF_CRC + ((ps->s_txreq->s_cur_size + extra_bytes) >> 2); @@ -866,13 +864,6 @@ static inline void hfi1_make_ruc_header_9B(struct rvt_qp *qp, bth1 |= (IB_BECN_MASK << IB_BECN_SHIFT); } hfi1_make_ruc_bth(qp, ohdr, bth0, bth1, bth2); - - if (!ppd->lid) - slid = be16_to_cpu(IB_LID_PERMISSIVE); - else - slid = ppd->lid | - (rdma_ah_get_path_bits(&qp->remote_ah_attr) & - ((1 << ppd->lmc) - 1)); hfi1_make_ib_hdr(&ps->s_txreq->phdr.hdr.ibh, lrh0, qp->s_hdrwords + nwords, diff --git a/drivers/infiniband/hw/hfi1/sdma.c b/drivers/infiniband/hw/hfi1/sdma.c index 6781bcdb10b3..6a1b8e479616 100644 --- a/drivers/infiniband/hw/hfi1/sdma.c +++ b/drivers/infiniband/hw/hfi1/sdma.c @@ -491,10 +491,10 @@ static void sdma_err_progress_check_schedule(struct sdma_engine *sde) } } -static void sdma_err_progress_check(unsigned long data) +static void sdma_err_progress_check(struct timer_list *t) { unsigned index; - struct sdma_engine *sde = (struct sdma_engine *)data; + struct sdma_engine *sde = from_timer(sde, t, err_progress_check_timer); dd_dev_err(sde->dd, "SDE progress check event\n"); for (index = 0; index < sde->dd->num_sdma; index++) { @@ -1392,6 +1392,13 @@ int sdma_init(struct hfi1_devdata *dd, u8 port) return ret; idle_cnt = ns_to_cclock(dd, idle_cnt); + if (idle_cnt) + dd->default_desc1 = + SDMA_DESC1_HEAD_TO_HOST_FLAG; + else + dd->default_desc1 = + SDMA_DESC1_INT_REQ_FLAG; + if (!sdma_desct_intr) sdma_desct_intr = SDMA_DESC_INTR; @@ -1436,13 +1443,6 @@ int sdma_init(struct hfi1_devdata *dd, u8 port) sde->tail_csr = get_kctxt_csr_addr(dd, this_idx, SD(TAIL)); - if (idle_cnt) - dd->default_desc1 = - SDMA_DESC1_HEAD_TO_HOST_FLAG; - else - dd->default_desc1 = - SDMA_DESC1_INT_REQ_FLAG; - tasklet_init(&sde->sdma_hw_clean_up_task, sdma_hw_clean_up_task, (unsigned long)sde); @@ -1453,8 +1453,8 @@ int sdma_init(struct hfi1_devdata *dd, u8 port) sde->progress_check_head = 0; - setup_timer(&sde->err_progress_check_timer, - sdma_err_progress_check, (unsigned long)sde); + timer_setup(&sde->err_progress_check_timer, + sdma_err_progress_check, 0); sde->descq = dma_zalloc_coherent( &dd->pcidev->dev, @@ -1465,13 +1465,8 @@ int sdma_init(struct hfi1_devdata *dd, u8 port) if (!sde->descq) goto bail; sde->tx_ring = - kcalloc(descq_cnt, sizeof(struct sdma_txreq *), - GFP_KERNEL); - if (!sde->tx_ring) - sde->tx_ring = - vzalloc( - sizeof(struct sdma_txreq *) * - descq_cnt); + kvzalloc_node(sizeof(struct sdma_txreq *) * descq_cnt, + GFP_KERNEL, dd->node); if (!sde->tx_ring) goto bail; } @@ -2144,7 +2139,6 @@ void sdma_dumpstate(struct sdma_engine *sde) static void dump_sdma_state(struct sdma_engine *sde) { - struct hw_sdma_desc *descq; struct hw_sdma_desc *descqp; u64 desc[2]; u64 addr; @@ -2155,7 +2149,6 @@ static void dump_sdma_state(struct sdma_engine *sde) head = sde->descq_head & sde->sdma_mask; tail = sde->descq_tail & sde->sdma_mask; cnt = sdma_descq_freecnt(sde); - descq = sde->descq; dd_dev_err(sde->dd, "SDMA (%u) descq_head: %u descq_tail: %u freecnt: %u FLE %d\n", @@ -2593,7 +2586,7 @@ static void __sdma_process_event(struct sdma_engine *sde, * 7220, e.g. */ ss->go_s99_running = 1; - /* fall through and start dma engine */ + /* fall through -- and start dma engine */ case sdma_event_e10_go_hw_start: /* This reference means the state machine is started */ sdma_get(&sde->state); @@ -3016,6 +3009,7 @@ static void __sdma_process_event(struct sdma_engine *sde, case sdma_event_e60_hw_halted: need_progress = 1; sdma_err_progress_check_schedule(sde); + /* fall through */ case sdma_event_e90_sw_halted: /* * SW initiated halt does not perform engines diff --git a/drivers/infiniband/hw/hfi1/sysfs.c b/drivers/infiniband/hw/hfi1/sysfs.c index 6d2702ef34ac..25e867393463 100644 --- a/drivers/infiniband/hw/hfi1/sysfs.c +++ b/drivers/infiniband/hw/hfi1/sysfs.c @@ -543,7 +543,7 @@ static ssize_t show_nctxts(struct device *device, * give a more accurate picture of total contexts available. */ return scnprintf(buf, PAGE_SIZE, "%u\n", - min(dd->num_rcv_contexts - dd->first_dyn_alloc_ctxt, + min(dd->num_user_contexts, (u32)dd->sc_sizes[SC_USER].count)); } diff --git a/drivers/infiniband/hw/hfi1/trace.c b/drivers/infiniband/hw/hfi1/trace.c index 9938bb983ce6..959a80429ee9 100644 --- a/drivers/infiniband/hw/hfi1/trace.c +++ b/drivers/infiniband/hw/hfi1/trace.c @@ -1,5 +1,5 @@ /* - * Copyright(c) 2015, 2016 Intel Corporation. + * Copyright(c) 2015 - 2017 Intel Corporation. * * This file is provided under a dual BSD/GPLv2 license. When using or * redistributing this file, you may do so under either license. @@ -91,12 +91,17 @@ u8 hfi1_trace_opa_hdr_len(struct hfi1_opa_header *opa_hdr) return __get_16b_hdr_len(&opa_hdr->opah); } -const char *hfi1_trace_get_packet_str(struct hfi1_packet *packet) +const char *hfi1_trace_get_packet_l4_str(u8 l4) { - if (packet->etype != RHF_RCV_TYPE_BYPASS) - return "IB"; + if (l4) + return "16B"; + else + return "9B"; +} - switch (hfi1_16B_get_l2(packet->hdr)) { +const char *hfi1_trace_get_packet_l2_str(u8 l2) +{ + switch (l2) { case 0: return "0"; case 1: @@ -109,14 +114,6 @@ const char *hfi1_trace_get_packet_str(struct hfi1_packet *packet) return ""; } -const char *hfi1_trace_get_packet_type_str(u8 l4) -{ - if (l4) - return "16B"; - else - return "9B"; -} - #define IMM_PRN "imm:%d" #define RETH_PRN "reth vaddr:0x%.16llx rkey:0x%.8x dlen:0x%.8x" #define AETH_PRN "aeth syn:0x%.2x %s msn:0x%.8x" @@ -154,7 +151,7 @@ void hfi1_trace_parse_9b_bth(struct ib_other_headers *ohdr, *opcode = ib_bth_get_opcode(ohdr); *tver = ib_bth_get_tver(ohdr); *pkey = ib_bth_get_pkey(ohdr); - *psn = ib_bth_get_psn(ohdr); + *psn = mask_psn(ib_bth_get_psn(ohdr)); *qpn = ib_bth_get_qpn(ohdr); } @@ -169,7 +166,7 @@ void hfi1_trace_parse_16b_bth(struct ib_other_headers *ohdr, *pad = ib_bth_get_pad(ohdr); *se = ib_bth_get_se(ohdr); *tver = ib_bth_get_tver(ohdr); - *psn = ib_bth_get_psn(ohdr); + *psn = mask_psn(ib_bth_get_psn(ohdr)); *qpn = ib_bth_get_qpn(ohdr); } diff --git a/drivers/infiniband/hw/hfi1/trace.h b/drivers/infiniband/hw/hfi1/trace.h index af50c0793450..8540463ef3f7 100644 --- a/drivers/infiniband/hw/hfi1/trace.h +++ b/drivers/infiniband/hw/hfi1/trace.h @@ -44,6 +44,16 @@ * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. * */ + +#define packettype_name(etype) { RHF_RCV_TYPE_##etype, #etype } +#define show_packettype(etype) \ +__print_symbolic(etype, \ + packettype_name(EXPECTED), \ + packettype_name(EAGER), \ + packettype_name(IB), \ + packettype_name(ERROR), \ + packettype_name(BYPASS)) + #include "trace_dbg.h" #include "trace_misc.h" #include "trace_ctxts.h" diff --git a/drivers/infiniband/hw/hfi1/trace_ibhdrs.h b/drivers/infiniband/hw/hfi1/trace_ibhdrs.h index 6721f84dafa5..fb631278eccd 100644 --- a/drivers/infiniband/hw/hfi1/trace_ibhdrs.h +++ b/drivers/infiniband/hw/hfi1/trace_ibhdrs.h @@ -1,5 +1,5 @@ /* - * Copyright(c) 2015, 2016 Intel Corporation. + * Copyright(c) 2015 - 2017 Intel Corporation. * * This file is provided under a dual BSD/GPLv2 license. When using or * redistributing this file, you may do so under either license. @@ -99,8 +99,7 @@ u8 ibhdr_exhdr_len(struct ib_header *hdr); const char *parse_everbs_hdrs(struct trace_seq *p, u8 opcode, void *ehdrs); u8 hfi1_trace_opa_hdr_len(struct hfi1_opa_header *opah); u8 hfi1_trace_packet_hdr_len(struct hfi1_packet *packet); -const char *hfi1_trace_get_packet_type_str(u8 l4); -const char *hfi1_trace_get_packet_str(struct hfi1_packet *packet); +const char *hfi1_trace_get_packet_l4_str(u8 l4); void hfi1_trace_parse_9b_bth(struct ib_other_headers *ohdr, u8 *ack, u8 *becn, u8 *fecn, u8 *mig, u8 *se, u8 *pad, u8 *opcode, u8 *tver, @@ -129,6 +128,8 @@ const char *hfi1_trace_fmt_bth(struct trace_seq *p, bool bypass, u8 se, u8 pad, u8 opcode, const char *opname, u8 tver, u16 pkey, u32 psn, u32 qpn); +const char *hfi1_trace_get_packet_l2_str(u8 l2); + #define __parse_ib_ehdrs(op, ehdrs) parse_everbs_hdrs(p, op, ehdrs) #define lrh_name(lrh) { HFI1_##lrh, #lrh } @@ -136,8 +137,6 @@ const char *hfi1_trace_fmt_bth(struct trace_seq *p, bool bypass, __print_symbolic(lrh, \ lrh_name(LRH_BTH), \ lrh_name(LRH_GRH)) -#define PKT_ENTRY(pkt) __string(ptype, hfi1_trace_get_packet_str(packet)) -#define PKT_ASSIGN(pkt) __assign_str(ptype, hfi1_trace_get_packet_str(packet)) DECLARE_EVENT_CLASS(hfi1_input_ibhdr_template, TP_PROTO(struct hfi1_devdata *dd, @@ -146,12 +145,12 @@ DECLARE_EVENT_CLASS(hfi1_input_ibhdr_template, TP_ARGS(dd, packet, sc5), TP_STRUCT__entry( DD_DEV_ENTRY(dd) - PKT_ENTRY(packet) - __field(bool, bypass) + __field(u8, etype) __field(u8, ack) __field(u8, age) __field(u8, becn) __field(u8, fecn) + __field(u8, l2) __field(u8, l4) __field(u8, lnh) __field(u8, lver) @@ -176,10 +175,10 @@ DECLARE_EVENT_CLASS(hfi1_input_ibhdr_template, ), TP_fast_assign( DD_DEV_ASSIGN(dd); - PKT_ASSIGN(packet); - if (packet->etype == RHF_RCV_TYPE_BYPASS) { - __entry->bypass = true; + __entry->etype = packet->etype; + __entry->l2 = hfi1_16B_get_l2(packet->hdr); + if (__entry->etype == RHF_RCV_TYPE_BYPASS) { hfi1_trace_parse_16b_hdr(packet->hdr, &__entry->age, &__entry->becn, @@ -203,7 +202,6 @@ DECLARE_EVENT_CLASS(hfi1_input_ibhdr_template, &__entry->psn, &__entry->qpn); } else { - __entry->bypass = false; hfi1_trace_parse_9b_hdr(packet->hdr, sc5, &__entry->lnh, &__entry->lver, @@ -233,9 +231,13 @@ DECLARE_EVENT_CLASS(hfi1_input_ibhdr_template, ), TP_printk("[%s] (%s) %s %s hlen:%d %s", __get_str(dev), - __get_str(ptype), + __entry->etype != RHF_RCV_TYPE_BYPASS ? + show_packettype(__entry->etype) : + hfi1_trace_get_packet_l2_str( + __entry->l2), hfi1_trace_fmt_lrh(p, - __entry->bypass, + __entry->etype == + RHF_RCV_TYPE_BYPASS, __entry->age, __entry->becn, __entry->fecn, @@ -252,7 +254,8 @@ DECLARE_EVENT_CLASS(hfi1_input_ibhdr_template, __entry->dlid, __entry->slid), hfi1_trace_fmt_bth(p, - __entry->bypass, + __entry->etype == + RHF_RCV_TYPE_BYPASS, __entry->ack, __entry->becn, __entry->fecn, @@ -284,7 +287,7 @@ DECLARE_EVENT_CLASS(hfi1_output_ibhdr_template, TP_ARGS(dd, opah, sc5), TP_STRUCT__entry( DD_DEV_ENTRY(dd) - __field(bool, bypass) + __field(u8, hdr_type) __field(u8, ack) __field(u8, age) __field(u8, becn) @@ -316,8 +319,8 @@ DECLARE_EVENT_CLASS(hfi1_output_ibhdr_template, DD_DEV_ASSIGN(dd); - if (opah->hdr_type) { - __entry->bypass = true; + __entry->hdr_type = opah->hdr_type; + if (__entry->hdr_type) { hfi1_trace_parse_16b_hdr(&opah->opah, &__entry->age, &__entry->becn, @@ -331,7 +334,7 @@ DECLARE_EVENT_CLASS(hfi1_output_ibhdr_template, &__entry->dlid, &__entry->slid); - if (entry->l4 == OPA_16B_L4_IB_LOCAL) + if (__entry->l4 == OPA_16B_L4_IB_LOCAL) ohdr = &opah->opah.u.oth; else ohdr = &opah->opah.u.l.oth; @@ -345,7 +348,7 @@ DECLARE_EVENT_CLASS(hfi1_output_ibhdr_template, &__entry->psn, &__entry->qpn); } else { - __entry->bypass = false; + __entry->l4 = OPA_16B_L4_9B; hfi1_trace_parse_9b_hdr(&opah->ibh, sc5, &__entry->lnh, &__entry->lver, @@ -354,7 +357,7 @@ DECLARE_EVENT_CLASS(hfi1_output_ibhdr_template, &__entry->len, &__entry->dlid, &__entry->slid); - if (entry->lnh == HFI1_LRH_BTH) + if (__entry->lnh == HFI1_LRH_BTH) ohdr = &opah->ibh.u.oth; else ohdr = &opah->ibh.u.l.oth; @@ -378,9 +381,9 @@ DECLARE_EVENT_CLASS(hfi1_output_ibhdr_template, ), TP_printk("[%s] (%s) %s %s hlen:%d %s", __get_str(dev), - hfi1_trace_get_packet_type_str(__entry->l4), + hfi1_trace_get_packet_l4_str(__entry->l4), hfi1_trace_fmt_lrh(p, - __entry->bypass, + !!__entry->hdr_type, __entry->age, __entry->becn, __entry->fecn, @@ -397,7 +400,7 @@ DECLARE_EVENT_CLASS(hfi1_output_ibhdr_template, __entry->dlid, __entry->slid), hfi1_trace_fmt_bth(p, - __entry->bypass, + !!__entry->hdr_type, __entry->ack, __entry->becn, __entry->fecn, diff --git a/drivers/infiniband/hw/hfi1/trace_rx.h b/drivers/infiniband/hw/hfi1/trace_rx.h index f9909d240dcc..4d487fee105d 100644 --- a/drivers/infiniband/hw/hfi1/trace_rx.h +++ b/drivers/infiniband/hw/hfi1/trace_rx.h @@ -1,5 +1,5 @@ /* - * Copyright(c) 2015, 2016 Intel Corporation. + * Copyright(c) 2015 - 2017 Intel Corporation. * * This file is provided under a dual BSD/GPLv2 license. When using or * redistributing this file, you may do so under either license. @@ -62,15 +62,6 @@ __print_symbolic(type, \ #undef TRACE_SYSTEM #define TRACE_SYSTEM hfi1_rx -#define packettype_name(etype) { RHF_RCV_TYPE_##etype, #etype } -#define show_packettype(etype) \ -__print_symbolic(etype, \ - packettype_name(EXPECTED), \ - packettype_name(EAGER), \ - packettype_name(IB), \ - packettype_name(ERROR), \ - packettype_name(BYPASS)) - TRACE_EVENT(hfi1_rcvhdr, TP_PROTO(struct hfi1_devdata *dd, u32 ctxt, diff --git a/drivers/infiniband/hw/hfi1/uc.c b/drivers/infiniband/hw/hfi1/uc.c index 0b646173ca22..fcd81866e332 100644 --- a/drivers/infiniband/hw/hfi1/uc.c +++ b/drivers/infiniband/hw/hfi1/uc.c @@ -93,7 +93,6 @@ int hfi1_make_uc_req(struct rvt_qp *qp, struct hfi1_pkt_state *ps) goto done_free_tx; } - ps->s_txreq->phdr.hdr.hdr_type = priv->hdr_type; if (priv->hdr_type == HFI1_PKT_TYPE_9B) { /* header size in 32-bit words LRH+BTH = (8+12)/4. */ hwords = 5; diff --git a/drivers/infiniband/hw/hfi1/ud.c b/drivers/infiniband/hw/hfi1/ud.c index 2ba74fdd6f15..84c7dbec0c28 100644 --- a/drivers/infiniband/hw/hfi1/ud.c +++ b/drivers/infiniband/hw/hfi1/ud.c @@ -854,7 +854,6 @@ void hfi1_ud_rcv(struct hfi1_packet *packet) int mgmt_pkey_idx = -1; struct hfi1_ibport *ibp = rcd_to_iport(packet->rcd); struct hfi1_pportdata *ppd = ppd_from_ibp(ibp); - struct ib_header *hdr = packet->hdr; void *data = packet->payload; u32 tlen = packet->tlen; struct rvt_qp *qp = packet->qp; @@ -880,7 +879,6 @@ void hfi1_ud_rcv(struct hfi1_packet *packet) dlid_is_permissive = (dlid == permissive_lid); slid_is_permissive = (slid == permissive_lid); } else { - hdr = packet->hdr; pkey = ib_bth_get_pkey(ohdr); dlid_is_permissive = (dlid == be16_to_cpu(IB_LID_PERMISSIVE)); slid_is_permissive = (slid == be16_to_cpu(IB_LID_PERMISSIVE)); diff --git a/drivers/infiniband/hw/hfi1/user_exp_rcv.c b/drivers/infiniband/hw/hfi1/user_exp_rcv.c index 6f6c14df383e..c1c596adcd01 100644 --- a/drivers/infiniband/hw/hfi1/user_exp_rcv.c +++ b/drivers/infiniband/hw/hfi1/user_exp_rcv.c @@ -542,14 +542,10 @@ int hfi1_user_exp_rcv_invalid(struct hfi1_filedata *fd, { struct hfi1_ctxtdata *uctxt = fd->uctxt; unsigned long *ev = uctxt->dd->events + - (((uctxt->ctxt - uctxt->dd->first_dyn_alloc_ctxt) * - HFI1_MAX_SHARED_CTXTS) + fd->subctxt); + (uctxt_offset(uctxt) + fd->subctxt); u32 *array; int ret = 0; - if (!fd->invalid_tids) - return -EINVAL; - /* * copy_to_user() can sleep, which will leave the invalid_lock * locked and cause the MMU notifier to be blocked on the lock @@ -942,8 +938,7 @@ static int tid_rb_invalidate(void *arg, struct mmu_rb_node *mnode) * process in question. */ ev = uctxt->dd->events + - (((uctxt->ctxt - uctxt->dd->first_dyn_alloc_ctxt) * - HFI1_MAX_SHARED_CTXTS) + fdata->subctxt); + (uctxt_offset(uctxt) + fdata->subctxt); set_bit(_HFI1_EVENT_TID_MMU_NOTIFY_BIT, ev); } fdata->invalid_tid_idx++; diff --git a/drivers/infiniband/hw/hfi1/user_sdma.c b/drivers/infiniband/hw/hfi1/user_sdma.c index c0c0e0445cbf..01b9a9c6c2af 100644 --- a/drivers/infiniband/hw/hfi1/user_sdma.c +++ b/drivers/infiniband/hw/hfi1/user_sdma.c @@ -956,10 +956,8 @@ static int pin_sdma_pages(struct user_sdma_request *req, struct hfi1_user_sdma_pkt_q *pq = req->pq; pages = kcalloc(npages, sizeof(*pages), GFP_KERNEL); - if (!pages) { - SDMA_DBG(req, "Failed page array alloc"); + if (!pages) return -ENOMEM; - } memcpy(pages, node->pages, node->npages * sizeof(*pages)); npages -= node->npages; @@ -1254,20 +1252,25 @@ static int set_txreq_header_ahg(struct user_sdma_request *req, struct user_sdma_txreq *tx, u32 datalen) { u32 ahg[AHG_KDETH_ARRAY_SIZE]; - int diff = 0; + int idx = 0; u8 omfactor; /* KDETH.OM */ struct hfi1_user_sdma_pkt_q *pq = req->pq; struct hfi1_pkt_header *hdr = &req->hdr; u16 pbclen = le16_to_cpu(hdr->pbc[0]); u32 val32, tidval = 0, lrhlen = get_lrh_len(*hdr, pad_len(datalen)); + size_t array_size = ARRAY_SIZE(ahg); if (PBC2LRH(pbclen) != lrhlen) { /* PBC.PbcLengthDWs */ - AHG_HEADER_SET(ahg, diff, 0, 0, 12, - cpu_to_le16(LRH2PBC(lrhlen))); + idx = ahg_header_set(ahg, idx, array_size, 0, 0, 12, + (__force u16)cpu_to_le16(LRH2PBC(lrhlen))); + if (idx < 0) + return idx; /* LRH.PktLen (we need the full 16 bits due to byte swap) */ - AHG_HEADER_SET(ahg, diff, 3, 0, 16, - cpu_to_be16(lrhlen >> 2)); + idx = ahg_header_set(ahg, idx, array_size, 3, 0, 16, + (__force u16)cpu_to_be16(lrhlen >> 2)); + if (idx < 0) + return idx; } /* @@ -1278,12 +1281,23 @@ static int set_txreq_header_ahg(struct user_sdma_request *req, (HFI1_CAP_IS_KSET(EXTENDED_PSN) ? 0x7fffffff : 0xffffff); if (unlikely(tx->flags & TXREQ_FLAGS_REQ_ACK)) val32 |= 1UL << 31; - AHG_HEADER_SET(ahg, diff, 6, 0, 16, cpu_to_be16(val32 >> 16)); - AHG_HEADER_SET(ahg, diff, 6, 16, 16, cpu_to_be16(val32 & 0xffff)); + idx = ahg_header_set(ahg, idx, array_size, 6, 0, 16, + (__force u16)cpu_to_be16(val32 >> 16)); + if (idx < 0) + return idx; + idx = ahg_header_set(ahg, idx, array_size, 6, 16, 16, + (__force u16)cpu_to_be16(val32 & 0xffff)); + if (idx < 0) + return idx; /* KDETH.Offset */ - AHG_HEADER_SET(ahg, diff, 15, 0, 16, - cpu_to_le16(req->koffset & 0xffff)); - AHG_HEADER_SET(ahg, diff, 15, 16, 16, cpu_to_le16(req->koffset >> 16)); + idx = ahg_header_set(ahg, idx, array_size, 15, 0, 16, + (__force u16)cpu_to_le16(req->koffset & 0xffff)); + if (idx < 0) + return idx; + idx = ahg_header_set(ahg, idx, array_size, 15, 16, 16, + (__force u16)cpu_to_le16(req->koffset >> 16)); + if (idx < 0) + return idx; if (req_opcode(req->info.ctrl) == EXPECTED) { __le16 val; @@ -1310,10 +1324,13 @@ static int set_txreq_header_ahg(struct user_sdma_request *req, KDETH_OM_MAX_SIZE) ? KDETH_OM_LARGE_SHIFT : KDETH_OM_SMALL_SHIFT; /* KDETH.OM and KDETH.OFFSET (TID) */ - AHG_HEADER_SET(ahg, diff, 7, 0, 16, - ((!!(omfactor - KDETH_OM_SMALL_SHIFT)) << 15 | + idx = ahg_header_set( + ahg, idx, array_size, 7, 0, 16, + ((!!(omfactor - KDETH_OM_SMALL_SHIFT)) << 15 | ((req->tidoffset >> omfactor) - & 0x7fff))); + & 0x7fff))); + if (idx < 0) + return idx; /* KDETH.TIDCtrl, KDETH.TID, KDETH.Intr, KDETH.SH */ val = cpu_to_le16(((EXP_TID_GET(tidval, CTRL) & 0x3) << 10) | (EXP_TID_GET(tidval, IDX) & 0x3ff)); @@ -1330,21 +1347,22 @@ static int set_txreq_header_ahg(struct user_sdma_request *req, AHG_KDETH_INTR_SHIFT)); } - AHG_HEADER_SET(ahg, diff, 7, 16, 14, val); + idx = ahg_header_set(ahg, idx, array_size, + 7, 16, 14, (__force u16)val); + if (idx < 0) + return idx; } - if (diff < 0) - return diff; trace_hfi1_sdma_user_header_ahg(pq->dd, pq->ctxt, pq->subctxt, req->info.comp_idx, req->sde->this_idx, - req->ahg_idx, ahg, diff, tidval); + req->ahg_idx, ahg, idx, tidval); sdma_txinit_ahg(&tx->txreq, SDMA_TXREQ_F_USE_AHG, - datalen, req->ahg_idx, diff, + datalen, req->ahg_idx, idx, ahg, sizeof(req->hdr), user_sdma_txreq_cb); - return diff; + return idx; } /* diff --git a/drivers/infiniband/hw/hfi1/user_sdma.h b/drivers/infiniband/hw/hfi1/user_sdma.h index 9b8bb5634c0d..a3d192424344 100644 --- a/drivers/infiniband/hw/hfi1/user_sdma.h +++ b/drivers/infiniband/hw/hfi1/user_sdma.h @@ -80,15 +80,26 @@ #define PBC2LRH(x) ((((x) & 0xfff) << 2) - 4) #define LRH2PBC(x) ((((x) >> 2) + 1) & 0xfff) -#define AHG_HEADER_SET(arr, idx, dw, bit, width, value) \ - do { \ - if ((idx) < ARRAY_SIZE((arr))) \ - (arr)[(idx++)] = sdma_build_ahg_descriptor( \ - (__force u16)(value), (dw), (bit), \ - (width)); \ - else \ - return -ERANGE; \ - } while (0) +/** + * Build an SDMA AHG header update descriptor and save it to an array. + * @arr - Array to save the descriptor to. + * @idx - Index of the array at which the descriptor will be saved. + * @array_size - Size of the array arr. + * @dw - Update index into the header in DWs. + * @bit - Start bit. + * @width - Field width. + * @value - 16 bits of immediate data to write into the field. + * Returns -ERANGE if idx is invalid. If successful, returns the next index + * (idx + 1) of the array to be used for the next descriptor. + */ +static inline int ahg_header_set(u32 *arr, int idx, size_t array_size, + u8 dw, u8 bit, u8 width, u16 value) +{ + if ((size_t)idx >= array_size) + return -ERANGE; + arr[idx++] = sdma_build_ahg_descriptor(value, dw, bit, width); + return idx; +} /* Tx request flag bits */ #define TXREQ_FLAGS_REQ_ACK BIT(0) /* Set the ACK bit in the header */ diff --git a/drivers/infiniband/hw/hfi1/verbs.c b/drivers/infiniband/hw/hfi1/verbs.c index e232f3c608b4..a38785e224cc 100644 --- a/drivers/infiniband/hw/hfi1/verbs.c +++ b/drivers/infiniband/hw/hfi1/verbs.c @@ -146,6 +146,9 @@ static int pio_wait(struct rvt_qp *qp, /* Length of buffer to create verbs txreq cache name */ #define TXREQ_NAME_LEN 24 +/* 16B trailing buffer */ +static const u8 trail_buf[MAX_16B_PADDING]; + static uint wss_threshold; module_param(wss_threshold, uint, S_IRUGO); MODULE_PARM_DESC(wss_threshold, "Percentage (1-100) of LLC to use as a threshold for a cacheless copy"); @@ -667,9 +670,9 @@ void hfi1_16B_rcv(struct hfi1_packet *packet) * This is called from a timer to check for QPs * which need kernel memory in order to send a packet. */ -static void mem_timer(unsigned long data) +static void mem_timer(struct timer_list *t) { - struct hfi1_ibdev *dev = (struct hfi1_ibdev *)data; + struct hfi1_ibdev *dev = from_timer(dev, t, mem_timer); struct list_head *list = &dev->memwait; struct rvt_qp *qp = NULL; struct iowait *wait; @@ -793,6 +796,27 @@ bail_txadd: return ret; } +/** + * update_tx_opstats - record stats by opcode + * @qp; the qp + * @ps: transmit packet state + * @plen: the plen in dwords + * + * This is a routine to record the tx opstats after a + * packet has been presented to the egress mechanism. + */ +static void update_tx_opstats(struct rvt_qp *qp, struct hfi1_pkt_state *ps, + u32 plen) +{ +#ifdef CONFIG_DEBUG_FS + struct hfi1_devdata *dd = dd_from_ibdev(qp->ibqp.device); + struct hfi1_opcode_stats_perctx *s = get_cpu_ptr(dd->tx_opstats); + + inc_opstats(plen * 4, &s->stats[ps->opcode]); + put_cpu_ptr(s); +#endif +} + /* * Build the number of DMA descriptors needed to send length bytes of data. * @@ -812,9 +836,7 @@ static int build_verbs_tx_desc( int ret = 0; struct hfi1_sdma_header *phdr = &tx->phdr; u16 hdrbytes = tx->hdr_dwords << 2; - u32 *hdr; u8 extra_bytes = 0; - static char trail_buf[12]; /* CRC = 4, LT = 1, Pad = 0 to 7 bytes */ if (tx->phdr.hdr.hdr_type) { /* @@ -823,9 +845,6 @@ static int build_verbs_tx_desc( */ extra_bytes = hfi1_get_16b_padding(hdrbytes - 8, length) + (SIZE_OF_CRC << 2) + SIZE_OF_LT; - hdr = (u32 *)&phdr->hdr.opah; - } else { - hdr = (u32 *)&phdr->hdr.ibh; } if (!ahg_info->ahgcount) { ret = sdma_txinit_ahg( @@ -869,9 +888,9 @@ static int build_verbs_tx_desc( } /* add icrc, lt byte, and padding to flit */ - if (extra_bytes != 0) + if (extra_bytes) ret = sdma_txadd_kvaddr(sde->dd, &tx->txreq, - trail_buf, extra_bytes); + (void *)trail_buf, extra_bytes); bail_txadd: return ret; @@ -891,14 +910,12 @@ int hfi1_verbs_send_dma(struct rvt_qp *qp, struct hfi1_pkt_state *ps, u8 sc5 = priv->s_sc; int ret; u32 dwords; - bool bypass = false; if (ps->s_txreq->phdr.hdr.hdr_type) { u8 extra_bytes = hfi1_get_16b_padding((hdrwords << 2), len); dwords = (len + extra_bytes + (SIZE_OF_CRC << 2) + SIZE_OF_LT) >> 2; - bypass = true; } else { dwords = (len + 3) >> 2; } @@ -938,6 +955,8 @@ int hfi1_verbs_send_dma(struct rvt_qp *qp, struct hfi1_pkt_state *ps, goto bail_ecomm; return ret; } + + update_tx_opstats(qp, ps, plen); trace_sdma_output_ibhdr(dd_from_ibdev(qp->ibqp.device), &ps->s_txreq->phdr.hdr, ib_is_sc5(sc5)); return ret; @@ -1033,8 +1052,6 @@ int hfi1_verbs_send_pio(struct rvt_qp *qp, struct hfi1_pkt_state *ps, int wc_status = IB_WC_SUCCESS; int ret = 0; pio_release_cb cb = NULL; - u32 lrh0_16b; - bool bypass = false; u8 extra_bytes = 0; if (ps->s_txreq->phdr.hdr.hdr_type) { @@ -1043,8 +1060,6 @@ int hfi1_verbs_send_pio(struct rvt_qp *qp, struct hfi1_pkt_state *ps, extra_bytes = pad_size + (SIZE_OF_CRC << 2) + SIZE_OF_LT; dwords = (len + extra_bytes) >> 2; hdr = (u32 *)&ps->s_txreq->phdr.hdr.opah; - lrh0_16b = ps->s_txreq->phdr.hdr.opah.lrh[0]; - bypass = true; } else { dwords = (len + 3) >> 2; hdr = (u32 *)&ps->s_txreq->phdr.hdr.ibh; @@ -1128,21 +1143,14 @@ int hfi1_verbs_send_pio(struct rvt_qp *qp, struct hfi1_pkt_state *ps, len -= slen; } } - /* - * Bypass packet will need to copy additional - * bytes to accommodate for CRC and LT bytes - */ - if (extra_bytes) { - u8 *empty_buf; + /* add icrc, lt byte, and padding to flit */ + if (extra_bytes) + seg_pio_copy_mid(pbuf, trail_buf, extra_bytes); - empty_buf = kcalloc(extra_bytes, sizeof(u8), - GFP_KERNEL); - seg_pio_copy_mid(pbuf, empty_buf, extra_bytes); - kfree(empty_buf); - } seg_pio_copy_end(pbuf); } + update_tx_opstats(qp, ps, plen); trace_pio_output_ibhdr(dd_from_ibdev(qp->ibqp.device), &ps->s_txreq->phdr.hdr, ib_is_sc5(sc5)); @@ -1636,8 +1644,7 @@ static void init_ibport(struct hfi1_pportdata *ppd) for (i = 0; i < RVT_MAX_TRAP_LISTS ; i++) INIT_LIST_HEAD(&ibp->rvp.trap_lists[i].list); - setup_timer(&ibp->rvp.trap_timer, hfi1_handle_trap_timer, - (unsigned long)ibp); + timer_setup(&ibp->rvp.trap_timer, hfi1_handle_trap_timer, 0); spin_lock_init(&ibp->rvp.lock); /* Set the prefix to the default value (see ch. 4.1.1) */ @@ -1844,7 +1851,7 @@ int hfi1_register_ib_device(struct hfi1_devdata *dd) /* Only need to initialize non-zero fields. */ - setup_timer(&dev->mem_timer, mem_timer, (unsigned long)dev); + timer_setup(&dev->mem_timer, mem_timer, 0); seqlock_init(&dev->iowait_lock); seqlock_init(&dev->txwait_lock); diff --git a/drivers/infiniband/hw/hfi1/verbs_txreq.h b/drivers/infiniband/hw/hfi1/verbs_txreq.h index 76216f2ef35a..cec7a4b34d16 100644 --- a/drivers/infiniband/hw/hfi1/verbs_txreq.h +++ b/drivers/infiniband/hw/hfi1/verbs_txreq.h @@ -92,6 +92,8 @@ static inline struct verbs_txreq *get_txreq(struct hfi1_ibdev *dev, tx->psc = priv->s_sendcontext; /* so that we can test if the sdma decriptors are there */ tx->txreq.num_desc = 0; + /* Set the header type */ + tx->phdr.hdr.hdr_type = priv->hdr_type; return tx; } diff --git a/drivers/infiniband/hw/hfi1/vnic_main.c b/drivers/infiniband/hw/hfi1/vnic_main.c index f419cbb05928..1a17708be46a 100644 --- a/drivers/infiniband/hw/hfi1/vnic_main.c +++ b/drivers/infiniband/hw/hfi1/vnic_main.c @@ -840,6 +840,9 @@ struct net_device *hfi1_vnic_alloc_rn(struct ib_device *device, struct rdma_netdev *rn; int i, size, rc; + if (!dd->num_vnic_contexts) + return ERR_PTR(-ENOMEM); + if (!port_num || (port_num > dd->num_pports)) return ERR_PTR(-EINVAL); @@ -848,7 +851,7 @@ struct net_device *hfi1_vnic_alloc_rn(struct ib_device *device, size = sizeof(struct opa_vnic_rdma_netdev) + sizeof(*vinfo); netdev = alloc_netdev_mqs(size, name, name_assign_type, setup, - dd->chip_sdma_engines, HFI1_NUM_VNIC_CTXT); + dd->chip_sdma_engines, dd->num_vnic_contexts); if (!netdev) return ERR_PTR(-ENOMEM); @@ -856,7 +859,7 @@ struct net_device *hfi1_vnic_alloc_rn(struct ib_device *device, vinfo = opa_vnic_dev_priv(netdev); vinfo->dd = dd; vinfo->num_tx_q = dd->chip_sdma_engines; - vinfo->num_rx_q = HFI1_NUM_VNIC_CTXT; + vinfo->num_rx_q = dd->num_vnic_contexts; vinfo->netdev = netdev; rn->free_rdma_netdev = hfi1_vnic_free_rn; rn->set_id = hfi1_vnic_set_vesw_id; diff --git a/drivers/infiniband/hw/hns/Kconfig b/drivers/infiniband/hw/hns/Kconfig index 61c93bbd230d..fddb5fdf92de 100644 --- a/drivers/infiniband/hw/hns/Kconfig +++ b/drivers/infiniband/hw/hns/Kconfig @@ -1,10 +1,31 @@ config INFINIBAND_HNS tristate "HNS RoCE Driver" depends on NET_VENDOR_HISILICON - depends on (ARM64 || (COMPILE_TEST && 64BIT)) && HNS && HNS_DSAF && HNS_ENET + depends on ARM64 || (COMPILE_TEST && 64BIT) ---help--- This is a RoCE/RDMA driver for the Hisilicon RoCE engine. The engine - is used in Hisilicon Hi1610 and more further ICT SoC. + is used in Hisilicon Hip06 and more further ICT SoC based on + platform device. To compile this driver as a module, choose M here: the module will be called hns-roce. + +config INFINIBAND_HNS_HIP06 + tristate "Hisilicon Hip06 Family RoCE support" + depends on INFINIBAND_HNS && HNS && HNS_DSAF && HNS_ENET + ---help--- + RoCE driver support for Hisilicon RoCE engine in Hisilicon Hip06 and + Hip07 SoC. These RoCE engines are platform devices. + + To compile this driver as a module, choose M here: the module + will be called hns-roce-hw-v1. + +config INFINIBAND_HNS_HIP08 + tristate "Hisilicon Hip08 Family RoCE support" + depends on INFINIBAND_HNS && PCI && HNS3 + ---help--- + RoCE driver support for Hisilicon RoCE engine in Hisilicon Hip08 SoC. + The RoCE engine is a PCI device. + + To compile this driver as a module, choose M here: the module + will be called hns-roce-hw-v2. diff --git a/drivers/infiniband/hw/hns/Makefile b/drivers/infiniband/hw/hns/Makefile index 7e8ebd24dcae..ff426a625e13 100644 --- a/drivers/infiniband/hw/hns/Makefile +++ b/drivers/infiniband/hw/hns/Makefile @@ -2,7 +2,13 @@ # Makefile for the Hisilicon RoCE drivers. # +ccflags-y := -Idrivers/net/ethernet/hisilicon/hns3 + obj-$(CONFIG_INFINIBAND_HNS) += hns-roce.o hns-roce-objs := hns_roce_main.o hns_roce_cmd.o hns_roce_eq.o hns_roce_pd.o \ hns_roce_ah.o hns_roce_hem.o hns_roce_mr.o hns_roce_qp.o \ - hns_roce_cq.o hns_roce_alloc.o hns_roce_hw_v1.o + hns_roce_cq.o hns_roce_alloc.o +obj-$(CONFIG_INFINIBAND_HNS_HIP06) += hns-roce-hw-v1.o +hns-roce-hw-v1-objs := hns_roce_hw_v1.o +obj-$(CONFIG_INFINIBAND_HNS_HIP08) += hns-roce-hw-v2.o +hns-roce-hw-v2-objs := hns_roce_hw_v2.o diff --git a/drivers/infiniband/hw/hns/hns_roce_ah.c b/drivers/infiniband/hw/hns/hns_roce_ah.c index d545302b8ef8..7dd6a66ea244 100644 --- a/drivers/infiniband/hw/hns/hns_roce_ah.c +++ b/drivers/infiniband/hw/hns/hns_roce_ah.c @@ -44,11 +44,10 @@ struct ib_ah *hns_roce_create_ah(struct ib_pd *ibpd, struct ib_udata *udata) { struct hns_roce_dev *hr_dev = to_hr_dev(ibpd->device); - struct device *dev = &hr_dev->pdev->dev; + struct device *dev = hr_dev->dev; struct ib_gid_attr gid_attr; struct hns_roce_ah *ah; u16 vlan_tag = 0xffff; - struct in6_addr in6; const struct ib_global_route *grh = rdma_ah_read_grh(ah_attr); union ib_gid sgid; int ret; @@ -58,18 +57,7 @@ struct ib_ah *hns_roce_create_ah(struct ib_pd *ibpd, return ERR_PTR(-ENOMEM); /* Get mac address */ - memcpy(&in6, grh->dgid.raw, sizeof(grh->dgid.raw)); - if (rdma_is_multicast_addr(&in6)) { - rdma_get_mcast_mac(&in6, ah->av.mac); - } else { - u8 *dmac = rdma_ah_retrieve_dmac(ah_attr); - - if (!dmac) { - kfree(ah); - return ERR_PTR(-EINVAL); - } - memcpy(ah->av.mac, dmac, ETH_ALEN); - } + memcpy(ah->av.mac, ah_attr->roce.dmac, ETH_ALEN); /* Get source gid */ ret = ib_get_cached_gid(ibpd->device, rdma_ah_get_port_num(ah_attr), diff --git a/drivers/infiniband/hw/hns/hns_roce_alloc.c b/drivers/infiniband/hw/hns/hns_roce_alloc.c index e1b433cdd5e2..3e4c5253ab5c 100644 --- a/drivers/infiniband/hw/hns/hns_roce_alloc.c +++ b/drivers/infiniband/hw/hns/hns_roce_alloc.c @@ -67,6 +67,7 @@ void hns_roce_bitmap_free(struct hns_roce_bitmap *bitmap, unsigned long obj, { hns_roce_bitmap_free_range(bitmap, obj, 1, rr); } +EXPORT_SYMBOL_GPL(hns_roce_bitmap_free); int hns_roce_bitmap_alloc_range(struct hns_roce_bitmap *bitmap, int cnt, int align, unsigned long *obj) @@ -160,39 +161,47 @@ void hns_roce_buf_free(struct hns_roce_dev *hr_dev, u32 size, struct hns_roce_buf *buf) { int i; - struct device *dev = &hr_dev->pdev->dev; + struct device *dev = hr_dev->dev; u32 bits_per_long = BITS_PER_LONG; if (buf->nbufs == 1) { dma_free_coherent(dev, size, buf->direct.buf, buf->direct.map); } else { - if (bits_per_long == 64) + if (bits_per_long == 64 && buf->page_shift == PAGE_SHIFT) vunmap(buf->direct.buf); for (i = 0; i < buf->nbufs; ++i) if (buf->page_list[i].buf) - dma_free_coherent(&hr_dev->pdev->dev, PAGE_SIZE, + dma_free_coherent(dev, 1 << buf->page_shift, buf->page_list[i].buf, buf->page_list[i].map); kfree(buf->page_list); } } +EXPORT_SYMBOL_GPL(hns_roce_buf_free); int hns_roce_buf_alloc(struct hns_roce_dev *hr_dev, u32 size, u32 max_direct, - struct hns_roce_buf *buf) + struct hns_roce_buf *buf, u32 page_shift) { int i = 0; dma_addr_t t; struct page **pages; - struct device *dev = &hr_dev->pdev->dev; + struct device *dev = hr_dev->dev; u32 bits_per_long = BITS_PER_LONG; + u32 page_size = 1 << page_shift; + u32 order; /* SQ/RQ buf lease than one page, SQ + RQ = 8K */ if (size <= max_direct) { buf->nbufs = 1; /* Npages calculated by page_size */ - buf->npages = 1 << get_order(size); - buf->page_shift = PAGE_SHIFT; + order = get_order(size); + if (order <= page_shift - PAGE_SHIFT) + order = 0; + else + order -= page_shift - PAGE_SHIFT; + buf->npages = 1 << order; + buf->page_shift = page_shift; /* MTT PA must be recorded in 4k alignment, t is 4k aligned */ buf->direct.buf = dma_alloc_coherent(dev, size, &t, GFP_KERNEL); if (!buf->direct.buf) @@ -207,9 +216,9 @@ int hns_roce_buf_alloc(struct hns_roce_dev *hr_dev, u32 size, u32 max_direct, memset(buf->direct.buf, 0, size); } else { - buf->nbufs = (size + PAGE_SIZE - 1) / PAGE_SIZE; + buf->nbufs = (size + page_size - 1) / page_size; buf->npages = buf->nbufs; - buf->page_shift = PAGE_SHIFT; + buf->page_shift = page_shift; buf->page_list = kcalloc(buf->nbufs, sizeof(*buf->page_list), GFP_KERNEL); @@ -218,16 +227,16 @@ int hns_roce_buf_alloc(struct hns_roce_dev *hr_dev, u32 size, u32 max_direct, for (i = 0; i < buf->nbufs; ++i) { buf->page_list[i].buf = dma_alloc_coherent(dev, - PAGE_SIZE, &t, + page_size, &t, GFP_KERNEL); if (!buf->page_list[i].buf) goto err_free; buf->page_list[i].map = t; - memset(buf->page_list[i].buf, 0, PAGE_SIZE); + memset(buf->page_list[i].buf, 0, page_size); } - if (bits_per_long == 64) { + if (bits_per_long == 64 && page_shift == PAGE_SHIFT) { pages = kmalloc_array(buf->nbufs, sizeof(*pages), GFP_KERNEL); if (!pages) @@ -241,6 +250,8 @@ int hns_roce_buf_alloc(struct hns_roce_dev *hr_dev, u32 size, u32 max_direct, kfree(pages); if (!buf->direct.buf) goto err_free; + } else { + buf->direct.buf = NULL; } } diff --git a/drivers/infiniband/hw/hns/hns_roce_cmd.c b/drivers/infiniband/hw/hns/hns_roce_cmd.c index b94dcd823ad1..1085cb249bc1 100644 --- a/drivers/infiniband/hw/hns/hns_roce_cmd.c +++ b/drivers/infiniband/hw/hns/hns_roce_cmd.c @@ -38,69 +38,7 @@ #define CMD_POLL_TOKEN 0xffff #define CMD_MAX_NUM 32 -#define STATUS_MASK 0xff #define CMD_TOKEN_MASK 0x1f -#define GO_BIT_TIMEOUT_MSECS 10000 - -enum { - HCR_TOKEN_OFFSET = 0x14, - HCR_STATUS_OFFSET = 0x18, - HCR_GO_BIT = 15, -}; - -static int cmd_pending(struct hns_roce_dev *hr_dev) -{ - u32 status = readl(hr_dev->cmd.hcr + HCR_TOKEN_OFFSET); - - return (!!(status & (1 << HCR_GO_BIT))); -} - -/* this function should be serialized with "hcr_mutex" */ -static int __hns_roce_cmd_mbox_post_hw(struct hns_roce_dev *hr_dev, - u64 in_param, u64 out_param, - u32 in_modifier, u8 op_modifier, u16 op, - u16 token, int event) -{ - struct hns_roce_cmdq *cmd = &hr_dev->cmd; - struct device *dev = &hr_dev->pdev->dev; - u32 __iomem *hcr = (u32 *)cmd->hcr; - int ret = -EAGAIN; - unsigned long end; - u32 val = 0; - - end = msecs_to_jiffies(GO_BIT_TIMEOUT_MSECS) + jiffies; - while (cmd_pending(hr_dev)) { - if (time_after(jiffies, end)) { - dev_dbg(dev, "jiffies=%d end=%d\n", (int)jiffies, - (int)end); - goto out; - } - cond_resched(); - } - - roce_set_field(val, ROCEE_MB6_ROCEE_MB_CMD_M, ROCEE_MB6_ROCEE_MB_CMD_S, - op); - roce_set_field(val, ROCEE_MB6_ROCEE_MB_CMD_MDF_M, - ROCEE_MB6_ROCEE_MB_CMD_MDF_S, op_modifier); - roce_set_bit(val, ROCEE_MB6_ROCEE_MB_EVENT_S, event); - roce_set_bit(val, ROCEE_MB6_ROCEE_MB_HW_RUN_S, 1); - roce_set_field(val, ROCEE_MB6_ROCEE_MB_TOKEN_M, - ROCEE_MB6_ROCEE_MB_TOKEN_S, token); - - __raw_writeq(cpu_to_le64(in_param), hcr + 0); - __raw_writeq(cpu_to_le64(out_param), hcr + 2); - __raw_writel(cpu_to_le32(in_modifier), hcr + 4); - /* Memory barrier */ - wmb(); - - __raw_writel(cpu_to_le32(val), hcr + 5); - - mmiowb(); - ret = 0; - -out: - return ret; -} static int hns_roce_cmd_mbox_post_hw(struct hns_roce_dev *hr_dev, u64 in_param, u64 out_param, u32 in_modifier, @@ -108,12 +46,11 @@ static int hns_roce_cmd_mbox_post_hw(struct hns_roce_dev *hr_dev, u64 in_param, int event) { struct hns_roce_cmdq *cmd = &hr_dev->cmd; - int ret = -EAGAIN; + int ret; mutex_lock(&cmd->hcr_mutex); - ret = __hns_roce_cmd_mbox_post_hw(hr_dev, in_param, out_param, - in_modifier, op_modifier, op, token, - event); + ret = hr_dev->hw->post_mbox(hr_dev, in_param, out_param, in_modifier, + op_modifier, op, token, event); mutex_unlock(&cmd->hcr_mutex); return ret; @@ -125,10 +62,7 @@ static int __hns_roce_cmd_mbox_poll(struct hns_roce_dev *hr_dev, u64 in_param, u8 op_modifier, u16 op, unsigned long timeout) { - struct device *dev = &hr_dev->pdev->dev; - u8 __iomem *hcr = hr_dev->cmd.hcr; - unsigned long end = 0; - u32 status = 0; + struct device *dev = hr_dev->dev; int ret; ret = hns_roce_cmd_mbox_post_hw(hr_dev, in_param, out_param, @@ -136,29 +70,10 @@ static int __hns_roce_cmd_mbox_poll(struct hns_roce_dev *hr_dev, u64 in_param, CMD_POLL_TOKEN, 0); if (ret) { dev_err(dev, "[cmd_poll]hns_roce_cmd_mbox_post_hw failed\n"); - goto out; - } - - end = msecs_to_jiffies(timeout) + jiffies; - while (cmd_pending(hr_dev) && time_before(jiffies, end)) - cond_resched(); - - if (cmd_pending(hr_dev)) { - dev_err(dev, "[cmd_poll]hw run cmd TIMEDOUT!\n"); - ret = -ETIMEDOUT; - goto out; + return ret; } - status = le32_to_cpu((__force __be32) - __raw_readl(hcr + HCR_STATUS_OFFSET)); - if ((status & STATUS_MASK) != 0x1) { - dev_err(dev, "mailbox status 0x%x!\n", status); - ret = -EBUSY; - goto out; - } - -out: - return ret; + return hr_dev->hw->chk_mbox(hr_dev, timeout); } static int hns_roce_cmd_mbox_poll(struct hns_roce_dev *hr_dev, u64 in_param, @@ -196,9 +111,9 @@ static int __hns_roce_cmd_mbox_wait(struct hns_roce_dev *hr_dev, u64 in_param, unsigned long timeout) { struct hns_roce_cmdq *cmd = &hr_dev->cmd; - struct device *dev = &hr_dev->pdev->dev; struct hns_roce_cmd_context *context; - int ret = 0; + struct device *dev = hr_dev->dev; + int ret; spin_lock(&cmd->context_lock); WARN_ON(cmd->free_head < 0); @@ -269,17 +184,17 @@ int hns_roce_cmd_mbox(struct hns_roce_dev *hr_dev, u64 in_param, u64 out_param, in_modifier, op_modifier, op, timeout); } +EXPORT_SYMBOL_GPL(hns_roce_cmd_mbox); int hns_roce_cmd_init(struct hns_roce_dev *hr_dev) { - struct device *dev = &hr_dev->pdev->dev; + struct device *dev = hr_dev->dev; mutex_init(&hr_dev->cmd.hcr_mutex); sema_init(&hr_dev->cmd.poll_sem, 1); hr_dev->cmd.use_events = 0; hr_dev->cmd.toggle = 1; hr_dev->cmd.max_cmds = CMD_MAX_NUM; - hr_dev->cmd.hcr = hr_dev->reg_base + ROCEE_MB1_REG; hr_dev->cmd.pool = dma_pool_create("hns_roce_cmd", dev, HNS_ROCE_MAILBOX_SIZE, HNS_ROCE_MAILBOX_SIZE, 0); @@ -356,6 +271,7 @@ struct hns_roce_cmd_mailbox return mailbox; } +EXPORT_SYMBOL_GPL(hns_roce_alloc_cmd_mailbox); void hns_roce_free_cmd_mailbox(struct hns_roce_dev *hr_dev, struct hns_roce_cmd_mailbox *mailbox) @@ -366,3 +282,4 @@ void hns_roce_free_cmd_mailbox(struct hns_roce_dev *hr_dev, dma_pool_free(hr_dev->cmd.pool, mailbox->buf, mailbox->dma); kfree(mailbox); } +EXPORT_SYMBOL_GPL(hns_roce_free_cmd_mailbox); diff --git a/drivers/infiniband/hw/hns/hns_roce_cmd.h b/drivers/infiniband/hw/hns/hns_roce_cmd.h index f5a9ee2fc53d..f0039a7166d8 100644 --- a/drivers/infiniband/hw/hns/hns_roce_cmd.h +++ b/drivers/infiniband/hw/hns/hns_roce_cmd.h @@ -37,6 +37,57 @@ #define HNS_ROCE_CMD_TIMEOUT_MSECS 10000 enum { + /* QPC BT commands */ + HNS_ROCE_CMD_WRITE_QPC_BT0 = 0x0, + HNS_ROCE_CMD_WRITE_QPC_BT1 = 0x1, + HNS_ROCE_CMD_WRITE_QPC_BT2 = 0x2, + HNS_ROCE_CMD_READ_QPC_BT0 = 0x4, + HNS_ROCE_CMD_READ_QPC_BT1 = 0x5, + HNS_ROCE_CMD_READ_QPC_BT2 = 0x6, + HNS_ROCE_CMD_DESTROY_QPC_BT0 = 0x8, + HNS_ROCE_CMD_DESTROY_QPC_BT1 = 0x9, + HNS_ROCE_CMD_DESTROY_QPC_BT2 = 0xa, + + /* QPC operation */ + HNS_ROCE_CMD_MODIFY_QPC = 0x41, + HNS_ROCE_CMD_QUERY_QPC = 0x42, + + HNS_ROCE_CMD_MODIFY_CQC = 0x52, + /* CQC BT commands */ + HNS_ROCE_CMD_WRITE_CQC_BT0 = 0x10, + HNS_ROCE_CMD_WRITE_CQC_BT1 = 0x11, + HNS_ROCE_CMD_WRITE_CQC_BT2 = 0x12, + HNS_ROCE_CMD_READ_CQC_BT0 = 0x14, + HNS_ROCE_CMD_READ_CQC_BT1 = 0x15, + HNS_ROCE_CMD_READ_CQC_BT2 = 0x1b, + HNS_ROCE_CMD_DESTROY_CQC_BT0 = 0x18, + HNS_ROCE_CMD_DESTROY_CQC_BT1 = 0x19, + HNS_ROCE_CMD_DESTROY_CQC_BT2 = 0x1a, + + /* MPT BT commands */ + HNS_ROCE_CMD_WRITE_MPT_BT0 = 0x20, + HNS_ROCE_CMD_WRITE_MPT_BT1 = 0x21, + HNS_ROCE_CMD_WRITE_MPT_BT2 = 0x22, + HNS_ROCE_CMD_READ_MPT_BT0 = 0x24, + HNS_ROCE_CMD_READ_MPT_BT1 = 0x25, + HNS_ROCE_CMD_READ_MPT_BT2 = 0x26, + HNS_ROCE_CMD_DESTROY_MPT_BT0 = 0x28, + HNS_ROCE_CMD_DESTROY_MPT_BT1 = 0x29, + HNS_ROCE_CMD_DESTROY_MPT_BT2 = 0x2a, + + /* SRQC BT commands */ + HNS_ROCE_CMD_WRITE_SRQC_BT0 = 0x30, + HNS_ROCE_CMD_WRITE_SRQC_BT1 = 0x31, + HNS_ROCE_CMD_WRITE_SRQC_BT2 = 0x32, + HNS_ROCE_CMD_READ_SRQC_BT0 = 0x34, + HNS_ROCE_CMD_READ_SRQC_BT1 = 0x35, + HNS_ROCE_CMD_READ_SRQC_BT2 = 0x36, + HNS_ROCE_CMD_DESTROY_SRQC_BT0 = 0x38, + HNS_ROCE_CMD_DESTROY_SRQC_BT1 = 0x39, + HNS_ROCE_CMD_DESTROY_SRQC_BT2 = 0x3a, +}; + +enum { /* TPT commands */ HNS_ROCE_CMD_SW2HW_MPT = 0xd, HNS_ROCE_CMD_HW2SW_MPT = 0xf, diff --git a/drivers/infiniband/hw/hns/hns_roce_common.h b/drivers/infiniband/hw/hns/hns_roce_common.h index 4af403e1348c..7ecb7a4147a8 100644 --- a/drivers/infiniband/hw/hns/hns_roce_common.h +++ b/drivers/infiniband/hw/hns/hns_roce_common.h @@ -341,6 +341,7 @@ #define ROCEE_BT_CMD_L_REG 0x200 #define ROCEE_MB1_REG 0x210 +#define ROCEE_MB6_REG 0x224 #define ROCEE_DB_SQ_L_0_REG 0x230 #define ROCEE_DB_OTHERS_L_0_REG 0x238 #define ROCEE_QP1C_CFG0_0_REG 0x270 @@ -362,4 +363,26 @@ #define ROCEE_ECC_UCERR_ALM0_REG 0xB34 #define ROCEE_ECC_CERR_ALM0_REG 0xB40 +/* V2 ROCEE REG */ +#define ROCEE_TX_CMQ_BASEADDR_L_REG 0x07000 +#define ROCEE_TX_CMQ_BASEADDR_H_REG 0x07004 +#define ROCEE_TX_CMQ_DEPTH_REG 0x07008 +#define ROCEE_TX_CMQ_TAIL_REG 0x07010 +#define ROCEE_TX_CMQ_HEAD_REG 0x07014 + +#define ROCEE_RX_CMQ_BASEADDR_L_REG 0x07018 +#define ROCEE_RX_CMQ_BASEADDR_H_REG 0x0701c +#define ROCEE_RX_CMQ_DEPTH_REG 0x07020 +#define ROCEE_RX_CMQ_TAIL_REG 0x07024 +#define ROCEE_RX_CMQ_HEAD_REG 0x07028 + +#define ROCEE_VF_SMAC_CFG0_REG 0x12000 +#define ROCEE_VF_SMAC_CFG1_REG 0x12004 + +#define ROCEE_VF_SGID_CFG0_REG 0x10000 +#define ROCEE_VF_SGID_CFG1_REG 0x10004 +#define ROCEE_VF_SGID_CFG2_REG 0x10008 +#define ROCEE_VF_SGID_CFG3_REG 0x1000c +#define ROCEE_VF_SGID_CFG4_REG 0x10010 + #endif /* _HNS_ROCE_COMMON_H */ diff --git a/drivers/infiniband/hw/hns/hns_roce_cq.c b/drivers/infiniband/hw/hns/hns_roce_cq.c index b89fd711019e..f558f95d8827 100644 --- a/drivers/infiniband/hw/hns/hns_roce_cq.c +++ b/drivers/infiniband/hw/hns/hns_roce_cq.c @@ -58,7 +58,7 @@ static void hns_roce_ib_cq_event(struct hns_roce_cq *hr_cq, if (event_type != HNS_ROCE_EVENT_TYPE_CQ_ID_INVALID && event_type != HNS_ROCE_EVENT_TYPE_CQ_ACCESS_ERROR && event_type != HNS_ROCE_EVENT_TYPE_CQ_OVERFLOW) { - dev_err(&hr_dev->pdev->dev, + dev_err(hr_dev->dev, "hns_roce_ib: Unexpected event type 0x%x on CQ %06lx\n", event_type, hr_cq->cqn); return; @@ -85,17 +85,23 @@ static int hns_roce_cq_alloc(struct hns_roce_dev *hr_dev, int nent, struct hns_roce_uar *hr_uar, struct hns_roce_cq *hr_cq, int vector) { - struct hns_roce_cmd_mailbox *mailbox = NULL; - struct hns_roce_cq_table *cq_table = NULL; - struct device *dev = &hr_dev->pdev->dev; + struct hns_roce_cmd_mailbox *mailbox; + struct hns_roce_hem_table *mtt_table; + struct hns_roce_cq_table *cq_table; + struct device *dev = hr_dev->dev; dma_addr_t dma_handle; - u64 *mtts = NULL; - int ret = 0; + u64 *mtts; + int ret; cq_table = &hr_dev->cq_table; /* Get the physical address of cq buf */ - mtts = hns_roce_table_find(&hr_dev->mr_table.mtt_table, + if (hns_roce_check_whether_mhop(hr_dev, HEM_TYPE_CQE)) + mtt_table = &hr_dev->mr_table.mtt_cqe_table; + else + mtt_table = &hr_dev->mr_table.mtt_table; + + mtts = hns_roce_table_find(hr_dev, mtt_table, hr_mtt->first_seg, &dma_handle); if (!mtts) { dev_err(dev, "CQ alloc.Failed to find cq buf addr.\n"); @@ -182,21 +188,22 @@ static int hns_roce_hw2sw_cq(struct hns_roce_dev *dev, void hns_roce_free_cq(struct hns_roce_dev *hr_dev, struct hns_roce_cq *hr_cq) { struct hns_roce_cq_table *cq_table = &hr_dev->cq_table; - struct device *dev = &hr_dev->pdev->dev; + struct device *dev = hr_dev->dev; int ret; ret = hns_roce_hw2sw_cq(hr_dev, NULL, hr_cq->cqn); if (ret) dev_err(dev, "HW2SW_CQ failed (%d) for CQN %06lx\n", ret, hr_cq->cqn); - - /* Waiting interrupt process procedure carried out */ - synchronize_irq(hr_dev->eq_table.eq[hr_cq->vector].irq); - - /* wait for all interrupt processed */ - if (atomic_dec_and_test(&hr_cq->refcount)) - complete(&hr_cq->free); - wait_for_completion(&hr_cq->free); + if (hr_dev->eq_table.eq) { + /* Waiting interrupt process procedure carried out */ + synchronize_irq(hr_dev->eq_table.eq[hr_cq->vector].irq); + + /* wait for all interrupt processed */ + if (atomic_dec_and_test(&hr_cq->refcount)) + complete(&hr_cq->free); + wait_for_completion(&hr_cq->free); + } spin_lock_irq(&cq_table->lock); radix_tree_delete(&cq_table->tree, hr_cq->cqn); @@ -205,6 +212,7 @@ void hns_roce_free_cq(struct hns_roce_dev *hr_dev, struct hns_roce_cq *hr_cq) hns_roce_table_put(hr_dev, &cq_table->table, hr_cq->cqn); hns_roce_bitmap_free(&cq_table->bitmap, hr_cq->cqn, BITMAP_NO_RR); } +EXPORT_SYMBOL_GPL(hns_roce_free_cq); static int hns_roce_ib_get_cq_umem(struct hns_roce_dev *hr_dev, struct ib_ucontext *context, @@ -212,14 +220,31 @@ static int hns_roce_ib_get_cq_umem(struct hns_roce_dev *hr_dev, struct ib_umem **umem, u64 buf_addr, int cqe) { int ret; + u32 page_shift; + u32 npages; *umem = ib_umem_get(context, buf_addr, cqe * hr_dev->caps.cq_entry_sz, IB_ACCESS_LOCAL_WRITE, 1); if (IS_ERR(*umem)) return PTR_ERR(*umem); - ret = hns_roce_mtt_init(hr_dev, ib_umem_page_count(*umem), - (*umem)->page_shift, &buf->hr_mtt); + if (hns_roce_check_whether_mhop(hr_dev, HEM_TYPE_CQE)) + buf->hr_mtt.mtt_type = MTT_TYPE_CQE; + else + buf->hr_mtt.mtt_type = MTT_TYPE_WQE; + + if (hr_dev->caps.cqe_buf_pg_sz) { + npages = (ib_umem_page_count(*umem) + + (1 << hr_dev->caps.cqe_buf_pg_sz) - 1) / + (1 << hr_dev->caps.cqe_buf_pg_sz); + page_shift = PAGE_SHIFT + hr_dev->caps.cqe_buf_pg_sz; + ret = hns_roce_mtt_init(hr_dev, npages, page_shift, + &buf->hr_mtt); + } else { + ret = hns_roce_mtt_init(hr_dev, ib_umem_page_count(*umem), + (*umem)->page_shift, + &buf->hr_mtt); + } if (ret) goto err_buf; @@ -241,12 +266,19 @@ static int hns_roce_ib_alloc_cq_buf(struct hns_roce_dev *hr_dev, struct hns_roce_cq_buf *buf, u32 nent) { int ret; + u32 page_shift = PAGE_SHIFT + hr_dev->caps.cqe_buf_pg_sz; ret = hns_roce_buf_alloc(hr_dev, nent * hr_dev->caps.cq_entry_sz, - PAGE_SIZE * 2, &buf->hr_buf); + (1 << page_shift) * 2, &buf->hr_buf, + page_shift); if (ret) goto out; + if (hns_roce_check_whether_mhop(hr_dev, HEM_TYPE_CQE)) + buf->hr_mtt.mtt_type = MTT_TYPE_CQE; + else + buf->hr_mtt.mtt_type = MTT_TYPE_WQE; + ret = hns_roce_mtt_init(hr_dev, buf->hr_buf.npages, buf->hr_buf.page_shift, &buf->hr_mtt); if (ret) @@ -281,13 +313,13 @@ struct ib_cq *hns_roce_ib_create_cq(struct ib_device *ib_dev, struct ib_udata *udata) { struct hns_roce_dev *hr_dev = to_hr_dev(ib_dev); - struct device *dev = &hr_dev->pdev->dev; + struct device *dev = hr_dev->dev; struct hns_roce_ib_create_cq ucmd; struct hns_roce_cq *hr_cq = NULL; struct hns_roce_uar *uar = NULL; int vector = attr->comp_vector; int cq_entries = attr->cqe; - int ret = 0; + int ret; if (cq_entries < 1 || cq_entries > hr_dev->caps.max_cqes) { dev_err(dev, "Creat CQ failed. entries=%d, max=%d\n", @@ -295,13 +327,12 @@ struct ib_cq *hns_roce_ib_create_cq(struct ib_device *ib_dev, return ERR_PTR(-EINVAL); } - hr_cq = kmalloc(sizeof(*hr_cq), GFP_KERNEL); + hr_cq = kzalloc(sizeof(*hr_cq), GFP_KERNEL); if (!hr_cq) return ERR_PTR(-ENOMEM); - /* In v1 engine, parameter verification */ - if (cq_entries < HNS_ROCE_MIN_CQE_NUM) - cq_entries = HNS_ROCE_MIN_CQE_NUM; + if (hr_dev->caps.min_cqes) + cq_entries = max(cq_entries, hr_dev->caps.min_cqes); cq_entries = roundup_pow_of_two((unsigned int)cq_entries); hr_cq->ib_cq.cqe = cq_entries - 1; @@ -335,8 +366,8 @@ struct ib_cq *hns_roce_ib_create_cq(struct ib_device *ib_dev, } uar = &hr_dev->priv_uar; - hr_cq->cq_db_l = hr_dev->reg_base + ROCEE_DB_OTHERS_L_0_REG + - 0x1000 * uar->index; + hr_cq->cq_db_l = hr_dev->reg_base + hr_dev->odb_offset + + DB_REG_OFFSET * uar->index; } /* Allocate cq index, fill cq_context */ @@ -353,7 +384,7 @@ struct ib_cq *hns_roce_ib_create_cq(struct ib_device *ib_dev, * problems if tptr is set to zero here, so we initialze it in user * space. */ - if (!context) + if (!context && hr_cq->tptr_addr) *hr_cq->tptr_addr = 0; /* Get created cq handler and carry out event */ @@ -385,6 +416,7 @@ err_cq: kfree(hr_cq); return ERR_PTR(ret); } +EXPORT_SYMBOL_GPL(hns_roce_ib_create_cq); int hns_roce_ib_destroy_cq(struct ib_cq *ib_cq) { @@ -410,10 +442,11 @@ int hns_roce_ib_destroy_cq(struct ib_cq *ib_cq) return ret; } +EXPORT_SYMBOL_GPL(hns_roce_ib_destroy_cq); void hns_roce_cq_completion(struct hns_roce_dev *hr_dev, u32 cqn) { - struct device *dev = &hr_dev->pdev->dev; + struct device *dev = hr_dev->dev; struct hns_roce_cq *cq; cq = radix_tree_lookup(&hr_dev->cq_table.tree, @@ -429,7 +462,7 @@ void hns_roce_cq_completion(struct hns_roce_dev *hr_dev, u32 cqn) void hns_roce_cq_event(struct hns_roce_dev *hr_dev, u32 cqn, int event_type) { struct hns_roce_cq_table *cq_table = &hr_dev->cq_table; - struct device *dev = &hr_dev->pdev->dev; + struct device *dev = hr_dev->dev; struct hns_roce_cq *cq; cq = radix_tree_lookup(&cq_table->tree, diff --git a/drivers/infiniband/hw/hns/hns_roce_device.h b/drivers/infiniband/hw/hns/hns_roce_device.h index e493a61e14e1..31c7ab8fcdbe 100644 --- a/drivers/infiniband/hw/hns/hns_roce_device.h +++ b/drivers/infiniband/hw/hns/hns_roce_device.h @@ -78,6 +78,8 @@ #define HNS_ROCE_MAX_GID_NUM 16 #define HNS_ROCE_GID_SIZE 16 +#define HNS_ROCE_HOP_NUM_0 0xff + #define BITMAP_NO_RR 0 #define BITMAP_RR 1 @@ -168,6 +170,11 @@ enum { HNS_ROCE_OPCODE_RDMA_WITH_IMM_RECEIVE = 0x07, }; +enum hns_roce_mtt_type { + MTT_TYPE_WQE, + MTT_TYPE_CQE, +}; + #define HNS_ROCE_CMD_SUCCESS 1 #define HNS_ROCE_PORT_DOWN 0 @@ -229,15 +236,21 @@ struct hns_roce_hem_table { unsigned long num_obj; /*Single obj size */ unsigned long obj_size; + unsigned long table_chunk_size; int lowmem; struct mutex mutex; struct hns_roce_hem **hem; + u64 **bt_l1; + dma_addr_t *bt_l1_dma_addr; + u64 **bt_l0; + dma_addr_t *bt_l0_dma_addr; }; struct hns_roce_mtt { - unsigned long first_seg; - int order; - int page_shift; + unsigned long first_seg; + int order; + int page_shift; + enum hns_roce_mtt_type mtt_type; }; /* Only support 4K page size for mr register */ @@ -255,6 +268,19 @@ struct hns_roce_mr { int type; /* MR's register type */ u64 *pbl_buf;/* MR's PBL space */ dma_addr_t pbl_dma_addr; /* MR's PBL space PA */ + u32 pbl_size;/* PA number in the PBL */ + u64 pbl_ba;/* page table address */ + u32 l0_chunk_last_num;/* L0 last number */ + u32 l1_chunk_last_num;/* L1 last number */ + u64 **pbl_bt_l2;/* PBL BT L2 */ + u64 **pbl_bt_l1;/* PBL BT L1 */ + u64 *pbl_bt_l0;/* PBL BT L0 */ + dma_addr_t *pbl_l2_dma_addr;/* PBL BT L2 dma addr */ + dma_addr_t *pbl_l1_dma_addr;/* PBL BT L1 dma addr */ + dma_addr_t pbl_l0_dma_addr;/* PBL BT L0 dma addr */ + u32 pbl_ba_pg_sz;/* BT chunk page size */ + u32 pbl_buf_pg_sz;/* buf chunk page size */ + u32 pbl_hop_num;/* multi-hop number */ }; struct hns_roce_mr_table { @@ -262,6 +288,8 @@ struct hns_roce_mr_table { struct hns_roce_buddy mtt_buddy; struct hns_roce_hem_table mtt_table; struct hns_roce_hem_table mtpt_table; + struct hns_roce_buddy mtt_cqe_buddy; + struct hns_roce_hem_table mtt_cqe_table; }; struct hns_roce_wq { @@ -277,6 +305,12 @@ struct hns_roce_wq { void __iomem *db_reg_l; }; +struct hns_roce_sge { + int sge_cnt; /* SGE num */ + int offset; + int sge_shift;/* SGE size */ +}; + struct hns_roce_buf_list { void *buf; dma_addr_t map; @@ -367,7 +401,6 @@ struct hns_roce_cmd_context { struct hns_roce_cmdq { struct dma_pool *pool; - u8 __iomem *hcr; struct mutex hcr_mutex; struct semaphore poll_sem; /* @@ -429,6 +462,9 @@ struct hns_roce_qp { atomic_t refcount; struct completion free; + + struct hns_roce_sge sge; + u32 next_sge; }; struct hns_roce_sqp { @@ -439,7 +475,6 @@ struct hns_roce_ib_iboe { spinlock_t lock; struct net_device *netdevs[HNS_ROCE_MAX_PORTS]; struct notifier_block nb; - struct notifier_block nb_inet; u8 phy_port[HNS_ROCE_MAX_PORTS]; }; @@ -477,16 +512,20 @@ struct hns_roce_caps { u32 max_wqes; /* 16k */ u32 max_sq_desc_sz; /* 64 */ u32 max_rq_desc_sz; /* 64 */ + u32 max_srq_desc_sz; int max_qp_init_rdma; int max_qp_dest_rdma; int num_cqs; int max_cqes; + int min_cqes; + u32 min_wqes; int reserved_cqs; int num_aeq_vectors; /* 1 */ int num_comp_vectors; /* 32 ceq */ int num_other_vectors; int num_mtpts; u32 num_mtt_segs; + u32 num_cqe_segs; int reserved_mrws; int reserved_uars; int num_pds; @@ -499,19 +538,51 @@ struct hns_roce_caps { int qpc_entry_sz; int irrl_entry_sz; int cqc_entry_sz; + u32 pbl_ba_pg_sz; + u32 pbl_buf_pg_sz; + u32 pbl_hop_num; int aeqe_depth; int ceqe_depth[HNS_ROCE_COMP_VEC_NUM]; enum ib_mtu max_mtu; + u32 qpc_bt_num; + u32 srqc_bt_num; + u32 cqc_bt_num; + u32 mpt_bt_num; + u32 qpc_ba_pg_sz; + u32 qpc_buf_pg_sz; + u32 qpc_hop_num; + u32 srqc_ba_pg_sz; + u32 srqc_buf_pg_sz; + u32 srqc_hop_num; + u32 cqc_ba_pg_sz; + u32 cqc_buf_pg_sz; + u32 cqc_hop_num; + u32 mpt_ba_pg_sz; + u32 mpt_buf_pg_sz; + u32 mpt_hop_num; + u32 mtt_ba_pg_sz; + u32 mtt_buf_pg_sz; + u32 mtt_hop_num; + u32 cqe_ba_pg_sz; + u32 cqe_buf_pg_sz; + u32 cqe_hop_num; + u32 chunk_sz; /* chunk size in non multihop mode*/ }; struct hns_roce_hw { int (*reset)(struct hns_roce_dev *hr_dev, bool enable); - void (*hw_profile)(struct hns_roce_dev *hr_dev); + int (*cmq_init)(struct hns_roce_dev *hr_dev); + void (*cmq_exit)(struct hns_roce_dev *hr_dev); + int (*hw_profile)(struct hns_roce_dev *hr_dev); int (*hw_init)(struct hns_roce_dev *hr_dev); void (*hw_exit)(struct hns_roce_dev *hr_dev); + int (*post_mbox)(struct hns_roce_dev *hr_dev, u64 in_param, + u64 out_param, u32 in_modifier, u8 op_modifier, u16 op, + u16 token, int event); + int (*chk_mbox)(struct hns_roce_dev *hr_dev, unsigned long timeout); void (*set_gid)(struct hns_roce_dev *hr_dev, u8 port, int gid_index, union ib_gid *gid); - void (*set_mac)(struct hns_roce_dev *hr_dev, u8 phy_port, u8 *addr); + int (*set_mac)(struct hns_roce_dev *hr_dev, u8 phy_port, u8 *addr); void (*set_mtu)(struct hns_roce_dev *hr_dev, u8 phy_port, enum ib_mtu mtu); int (*write_mtpt)(void *mb_buf, struct hns_roce_mr *mr, @@ -519,8 +590,11 @@ struct hns_roce_hw { void (*write_cqc)(struct hns_roce_dev *hr_dev, struct hns_roce_cq *hr_cq, void *mb_buf, u64 *mtts, dma_addr_t dma_handle, int nent, u32 vector); + int (*set_hem)(struct hns_roce_dev *hr_dev, + struct hns_roce_hem_table *table, int obj, int step_idx); int (*clear_hem)(struct hns_roce_dev *hr_dev, - struct hns_roce_hem_table *table, int obj); + struct hns_roce_hem_table *table, int obj, + int step_idx); int (*query_qp)(struct ib_qp *ibqp, struct ib_qp_attr *qp_attr, int qp_attr_mask, struct ib_qp_init_attr *qp_init_attr); int (*modify_qp)(struct ib_qp *ibqp, const struct ib_qp_attr *attr, @@ -535,12 +609,14 @@ struct hns_roce_hw { int (*poll_cq)(struct ib_cq *ibcq, int num_entries, struct ib_wc *wc); int (*dereg_mr)(struct hns_roce_dev *hr_dev, struct hns_roce_mr *mr); int (*destroy_cq)(struct ib_cq *ibcq); - void *priv; + int (*modify_cq)(struct ib_cq *cq, u16 cq_count, u16 cq_period); }; struct hns_roce_dev { struct ib_device ib_dev; struct platform_device *pdev; + struct pci_dev *pci_dev; + struct device *dev; struct hns_roce_uar priv_uar; const char *irq_names[HNS_ROCE_MAX_IRQ_NUM]; spinlock_t sm_lock; @@ -569,9 +645,12 @@ struct hns_roce_dev { int cmd_mod; int loop_idc; + u32 sdb_offset; + u32 odb_offset; dma_addr_t tptr_dma_addr; /*only for hw v1*/ u32 tptr_size; /*only for hw v1*/ - struct hns_roce_hw *hw; + const struct hns_roce_hw *hw; + void *priv; }; static inline struct hns_roce_dev *to_hr_dev(struct ib_device *ib_dev) @@ -635,12 +714,14 @@ static inline struct hns_roce_qp static inline void *hns_roce_buf_offset(struct hns_roce_buf *buf, int offset) { u32 bits_per_long_val = BITS_PER_LONG; + u32 page_size = 1 << buf->page_shift; - if (bits_per_long_val == 64 || buf->nbufs == 1) + if ((bits_per_long_val == 64 && buf->page_shift == PAGE_SHIFT) || + buf->nbufs == 1) return (char *)(buf->direct.buf) + offset; else - return (char *)(buf->page_list[offset >> PAGE_SHIFT].buf) + - (offset & (PAGE_SIZE - 1)); + return (char *)(buf->page_list[offset >> buf->page_shift].buf) + + (offset & (page_size - 1)); } int hns_roce_init_uar_table(struct hns_roce_dev *dev); @@ -711,7 +792,7 @@ unsigned long key_to_hw_index(u32 key); void hns_roce_buf_free(struct hns_roce_dev *hr_dev, u32 size, struct hns_roce_buf *buf); int hns_roce_buf_alloc(struct hns_roce_dev *hr_dev, u32 size, u32 max_direct, - struct hns_roce_buf *buf); + struct hns_roce_buf *buf, u32 page_shift); int hns_roce_ib_umem_write_mtt(struct hns_roce_dev *hr_dev, struct hns_roce_mtt *mtt, struct ib_umem *umem); @@ -723,6 +804,7 @@ int hns_roce_modify_qp(struct ib_qp *ibqp, struct ib_qp_attr *attr, int attr_mask, struct ib_udata *udata); void *get_recv_wqe(struct hns_roce_qp *hr_qp, int n); void *get_send_wqe(struct hns_roce_qp *hr_qp, int n); +void *get_send_extend_sge(struct hns_roce_qp *hr_qp, int n); bool hns_roce_wq_overflow(struct hns_roce_wq *hr_wq, int nreq, struct ib_cq *ib_cq); enum hns_roce_qp_state to_hns_roce_state(enum ib_qp_state state); @@ -749,7 +831,7 @@ void hns_roce_cq_completion(struct hns_roce_dev *hr_dev, u32 cqn); void hns_roce_cq_event(struct hns_roce_dev *hr_dev, u32 cqn, int event_type); void hns_roce_qp_event(struct hns_roce_dev *hr_dev, u32 qpn, int event_type); int hns_get_gid_index(struct hns_roce_dev *hr_dev, u8 port, int gid_index); - -extern struct hns_roce_hw hns_roce_hw_v1; +int hns_roce_init(struct hns_roce_dev *hr_dev); +void hns_roce_exit(struct hns_roce_dev *hr_dev); #endif /* _HNS_ROCE_DEVICE_H */ diff --git a/drivers/infiniband/hw/hns/hns_roce_eq.c b/drivers/infiniband/hw/hns/hns_roce_eq.c index b0f43735de1a..d184431e2bf5 100644 --- a/drivers/infiniband/hw/hns/hns_roce_eq.c +++ b/drivers/infiniband/hw/hns/hns_roce_eq.c @@ -558,7 +558,7 @@ static int hns_roce_create_eq(struct hns_roce_dev *hr_dev, writel(eqshift_val, eqc); /* Configure eq extended address 12~44bit */ - writel((u32)(eq->buf_list[0].map >> 12), (u8 *)eqc + 4); + writel((u32)(eq->buf_list[0].map >> 12), eqc + 4); /* * Configure eq extended address 45~49 bit. @@ -572,13 +572,13 @@ static int hns_roce_create_eq(struct hns_roce_dev *hr_dev, roce_set_field(eqcuridx_val, ROCEE_CAEP_AEQE_CUR_IDX_CAEP_AEQE_CUR_IDX_M, ROCEE_CAEP_AEQE_CUR_IDX_CAEP_AEQE_CUR_IDX_S, 0); - writel(eqcuridx_val, (u8 *)eqc + 8); + writel(eqcuridx_val, eqc + 8); /* Configure eq consumer index */ roce_set_field(eqconsindx_val, ROCEE_CAEP_AEQE_CONS_IDX_CAEP_AEQE_CONS_IDX_M, ROCEE_CAEP_AEQE_CONS_IDX_CAEP_AEQE_CONS_IDX_S, 0); - writel(eqconsindx_val, (u8 *)eqc + 0xc); + writel(eqconsindx_val, eqc + 0xc); return 0; diff --git a/drivers/infiniband/hw/hns/hns_roce_hem.c b/drivers/infiniband/hw/hns/hns_roce_hem.c index c5104e0b2916..576eb3bb1f2d 100644 --- a/drivers/infiniband/hw/hns/hns_roce_hem.c +++ b/drivers/infiniband/hw/hns/hns_roce_hem.c @@ -36,14 +36,165 @@ #include "hns_roce_hem.h" #include "hns_roce_common.h" -#define HNS_ROCE_HEM_ALLOC_SIZE (1 << 17) -#define HNS_ROCE_TABLE_CHUNK_SIZE (1 << 17) - #define DMA_ADDR_T_SHIFT 12 #define BT_BA_SHIFT 32 -struct hns_roce_hem *hns_roce_alloc_hem(struct hns_roce_dev *hr_dev, int npages, - gfp_t gfp_mask) +bool hns_roce_check_whether_mhop(struct hns_roce_dev *hr_dev, u32 type) +{ + if ((hr_dev->caps.qpc_hop_num && type == HEM_TYPE_QPC) || + (hr_dev->caps.mpt_hop_num && type == HEM_TYPE_MTPT) || + (hr_dev->caps.cqc_hop_num && type == HEM_TYPE_CQC) || + (hr_dev->caps.srqc_hop_num && type == HEM_TYPE_SRQC) || + (hr_dev->caps.cqe_hop_num && type == HEM_TYPE_CQE) || + (hr_dev->caps.mtt_hop_num && type == HEM_TYPE_MTT)) + return true; + + return false; +} +EXPORT_SYMBOL_GPL(hns_roce_check_whether_mhop); + +static bool hns_roce_check_hem_null(struct hns_roce_hem **hem, u64 start_idx, + u32 bt_chunk_num) +{ + int i; + + for (i = 0; i < bt_chunk_num; i++) + if (hem[start_idx + i]) + return false; + + return true; +} + +static bool hns_roce_check_bt_null(u64 **bt, u64 start_idx, u32 bt_chunk_num) +{ + int i; + + for (i = 0; i < bt_chunk_num; i++) + if (bt[start_idx + i]) + return false; + + return true; +} + +static int hns_roce_get_bt_num(u32 table_type, u32 hop_num) +{ + if (check_whether_bt_num_3(table_type, hop_num)) + return 3; + else if (check_whether_bt_num_2(table_type, hop_num)) + return 2; + else if (check_whether_bt_num_1(table_type, hop_num)) + return 1; + else + return 0; +} + +int hns_roce_calc_hem_mhop(struct hns_roce_dev *hr_dev, + struct hns_roce_hem_table *table, unsigned long *obj, + struct hns_roce_hem_mhop *mhop) +{ + struct device *dev = hr_dev->dev; + u32 chunk_ba_num; + u32 table_idx; + u32 bt_num; + u32 chunk_size; + + switch (table->type) { + case HEM_TYPE_QPC: + mhop->buf_chunk_size = 1 << (hr_dev->caps.qpc_buf_pg_sz + + PAGE_SHIFT); + mhop->bt_chunk_size = 1 << (hr_dev->caps.qpc_ba_pg_sz + + PAGE_SHIFT); + mhop->ba_l0_num = hr_dev->caps.qpc_bt_num; + mhop->hop_num = hr_dev->caps.qpc_hop_num; + break; + case HEM_TYPE_MTPT: + mhop->buf_chunk_size = 1 << (hr_dev->caps.mpt_buf_pg_sz + + PAGE_SHIFT); + mhop->bt_chunk_size = 1 << (hr_dev->caps.mpt_ba_pg_sz + + PAGE_SHIFT); + mhop->ba_l0_num = hr_dev->caps.mpt_bt_num; + mhop->hop_num = hr_dev->caps.mpt_hop_num; + break; + case HEM_TYPE_CQC: + mhop->buf_chunk_size = 1 << (hr_dev->caps.cqc_buf_pg_sz + + PAGE_SHIFT); + mhop->bt_chunk_size = 1 << (hr_dev->caps.cqc_ba_pg_sz + + PAGE_SHIFT); + mhop->ba_l0_num = hr_dev->caps.cqc_bt_num; + mhop->hop_num = hr_dev->caps.cqc_hop_num; + break; + case HEM_TYPE_SRQC: + mhop->buf_chunk_size = 1 << (hr_dev->caps.srqc_buf_pg_sz + + PAGE_SHIFT); + mhop->bt_chunk_size = 1 << (hr_dev->caps.srqc_ba_pg_sz + + PAGE_SHIFT); + mhop->ba_l0_num = hr_dev->caps.srqc_bt_num; + mhop->hop_num = hr_dev->caps.srqc_hop_num; + break; + case HEM_TYPE_MTT: + mhop->buf_chunk_size = 1 << (hr_dev->caps.mtt_buf_pg_sz + + PAGE_SHIFT); + mhop->bt_chunk_size = 1 << (hr_dev->caps.mtt_ba_pg_sz + + PAGE_SHIFT); + mhop->ba_l0_num = mhop->bt_chunk_size / 8; + mhop->hop_num = hr_dev->caps.mtt_hop_num; + break; + case HEM_TYPE_CQE: + mhop->buf_chunk_size = 1 << (hr_dev->caps.cqe_buf_pg_sz + + PAGE_SHIFT); + mhop->bt_chunk_size = 1 << (hr_dev->caps.cqe_ba_pg_sz + + PAGE_SHIFT); + mhop->ba_l0_num = mhop->bt_chunk_size / 8; + mhop->hop_num = hr_dev->caps.cqe_hop_num; + break; + default: + dev_err(dev, "Table %d not support multi-hop addressing!\n", + table->type); + return -EINVAL; + } + + if (!obj) + return 0; + + /* + * QPC/MTPT/CQC/SRQC alloc hem for buffer pages. + * MTT/CQE alloc hem for bt pages. + */ + bt_num = hns_roce_get_bt_num(table->type, mhop->hop_num); + chunk_ba_num = mhop->bt_chunk_size / 8; + chunk_size = table->type < HEM_TYPE_MTT ? mhop->buf_chunk_size : + mhop->bt_chunk_size; + table_idx = (*obj & (table->num_obj - 1)) / + (chunk_size / table->obj_size); + switch (bt_num) { + case 3: + mhop->l2_idx = table_idx & (chunk_ba_num - 1); + mhop->l1_idx = table_idx / chunk_ba_num & (chunk_ba_num - 1); + mhop->l0_idx = table_idx / chunk_ba_num / chunk_ba_num; + break; + case 2: + mhop->l1_idx = table_idx & (chunk_ba_num - 1); + mhop->l0_idx = table_idx / chunk_ba_num; + break; + case 1: + mhop->l0_idx = table_idx; + break; + default: + dev_err(dev, "Table %d not support hop_num = %d!\n", + table->type, mhop->hop_num); + return -EINVAL; + } + if (mhop->l0_idx >= mhop->ba_l0_num) + mhop->l0_idx %= mhop->ba_l0_num; + + return 0; +} +EXPORT_SYMBOL_GPL(hns_roce_calc_hem_mhop); + +static struct hns_roce_hem *hns_roce_alloc_hem(struct hns_roce_dev *hr_dev, + int npages, + unsigned long hem_alloc_size, + gfp_t gfp_mask) { struct hns_roce_hem_chunk *chunk = NULL; struct hns_roce_hem *hem; @@ -61,7 +212,7 @@ struct hns_roce_hem *hns_roce_alloc_hem(struct hns_roce_dev *hr_dev, int npages, hem->refcount = 0; INIT_LIST_HEAD(&hem->chunk_list); - order = get_order(HNS_ROCE_HEM_ALLOC_SIZE); + order = get_order(hem_alloc_size); while (npages > 0) { if (!chunk) { @@ -84,7 +235,7 @@ struct hns_roce_hem *hns_roce_alloc_hem(struct hns_roce_dev *hr_dev, int npages, * memory, directly return fail. */ mem = &chunk->mem[chunk->npages]; - buf = dma_alloc_coherent(&hr_dev->pdev->dev, PAGE_SIZE << order, + buf = dma_alloc_coherent(hr_dev->dev, PAGE_SIZE << order, &sg_dma_address(mem), gfp_mask); if (!buf) goto fail; @@ -115,7 +266,7 @@ void hns_roce_free_hem(struct hns_roce_dev *hr_dev, struct hns_roce_hem *hem) list_for_each_entry_safe(chunk, tmp, &hem->chunk_list, list) { for (i = 0; i < chunk->npages; ++i) - dma_free_coherent(&hr_dev->pdev->dev, + dma_free_coherent(hr_dev->dev, chunk->mem[i].length, lowmem_page_address(sg_page(&chunk->mem[i])), sg_dma_address(&chunk->mem[i])); @@ -128,8 +279,8 @@ void hns_roce_free_hem(struct hns_roce_dev *hr_dev, struct hns_roce_hem *hem) static int hns_roce_set_hem(struct hns_roce_dev *hr_dev, struct hns_roce_hem_table *table, unsigned long obj) { - struct device *dev = &hr_dev->pdev->dev; spinlock_t *lock = &hr_dev->bt_cmd_lock; + struct device *dev = hr_dev->dev; unsigned long end = 0; unsigned long flags; struct hns_roce_hem_iter iter; @@ -142,7 +293,7 @@ static int hns_roce_set_hem(struct hns_roce_dev *hr_dev, /* Find the HEM(Hardware Entry Memory) entry */ unsigned long i = (obj & (table->num_obj - 1)) / - (HNS_ROCE_TABLE_CHUNK_SIZE / table->obj_size); + (table->table_chunk_size / table->obj_size); switch (table->type) { case HEM_TYPE_QPC: @@ -209,14 +360,185 @@ static int hns_roce_set_hem(struct hns_roce_dev *hr_dev, return ret; } +static int hns_roce_table_mhop_get(struct hns_roce_dev *hr_dev, + struct hns_roce_hem_table *table, + unsigned long obj) +{ + struct device *dev = hr_dev->dev; + struct hns_roce_hem_mhop mhop; + struct hns_roce_hem_iter iter; + u32 buf_chunk_size; + u32 bt_chunk_size; + u32 chunk_ba_num; + u32 hop_num; + u32 size; + u32 bt_num; + u64 hem_idx; + u64 bt_l1_idx = 0; + u64 bt_l0_idx = 0; + u64 bt_ba; + unsigned long mhop_obj = obj; + int bt_l1_allocated = 0; + int bt_l0_allocated = 0; + int step_idx; + int ret; + + ret = hns_roce_calc_hem_mhop(hr_dev, table, &mhop_obj, &mhop); + if (ret) + return ret; + + buf_chunk_size = mhop.buf_chunk_size; + bt_chunk_size = mhop.bt_chunk_size; + hop_num = mhop.hop_num; + chunk_ba_num = bt_chunk_size / 8; + + bt_num = hns_roce_get_bt_num(table->type, hop_num); + switch (bt_num) { + case 3: + hem_idx = mhop.l0_idx * chunk_ba_num * chunk_ba_num + + mhop.l1_idx * chunk_ba_num + mhop.l2_idx; + bt_l1_idx = mhop.l0_idx * chunk_ba_num + mhop.l1_idx; + bt_l0_idx = mhop.l0_idx; + break; + case 2: + hem_idx = mhop.l0_idx * chunk_ba_num + mhop.l1_idx; + bt_l0_idx = mhop.l0_idx; + break; + case 1: + hem_idx = mhop.l0_idx; + break; + default: + dev_err(dev, "Table %d not support hop_num = %d!\n", + table->type, hop_num); + return -EINVAL; + } + + mutex_lock(&table->mutex); + + if (table->hem[hem_idx]) { + ++table->hem[hem_idx]->refcount; + goto out; + } + + /* alloc L1 BA's chunk */ + if ((check_whether_bt_num_3(table->type, hop_num) || + check_whether_bt_num_2(table->type, hop_num)) && + !table->bt_l0[bt_l0_idx]) { + table->bt_l0[bt_l0_idx] = dma_alloc_coherent(dev, bt_chunk_size, + &(table->bt_l0_dma_addr[bt_l0_idx]), + GFP_KERNEL); + if (!table->bt_l0[bt_l0_idx]) { + ret = -ENOMEM; + goto out; + } + bt_l0_allocated = 1; + + /* set base address to hardware */ + if (table->type < HEM_TYPE_MTT) { + step_idx = 0; + if (hr_dev->hw->set_hem(hr_dev, table, obj, step_idx)) { + ret = -ENODEV; + dev_err(dev, "set HEM base address to HW failed!\n"); + goto err_dma_alloc_l1; + } + } + } + + /* alloc L2 BA's chunk */ + if (check_whether_bt_num_3(table->type, hop_num) && + !table->bt_l1[bt_l1_idx]) { + table->bt_l1[bt_l1_idx] = dma_alloc_coherent(dev, bt_chunk_size, + &(table->bt_l1_dma_addr[bt_l1_idx]), + GFP_KERNEL); + if (!table->bt_l1[bt_l1_idx]) { + ret = -ENOMEM; + goto err_dma_alloc_l1; + } + bt_l1_allocated = 1; + *(table->bt_l0[bt_l0_idx] + mhop.l1_idx) = + table->bt_l1_dma_addr[bt_l1_idx]; + + /* set base address to hardware */ + step_idx = 1; + if (hr_dev->hw->set_hem(hr_dev, table, obj, step_idx)) { + ret = -ENODEV; + dev_err(dev, "set HEM base address to HW failed!\n"); + goto err_alloc_hem_buf; + } + } + + /* + * alloc buffer space chunk for QPC/MTPT/CQC/SRQC. + * alloc bt space chunk for MTT/CQE. + */ + size = table->type < HEM_TYPE_MTT ? buf_chunk_size : bt_chunk_size; + table->hem[hem_idx] = hns_roce_alloc_hem(hr_dev, + size >> PAGE_SHIFT, + size, + (table->lowmem ? GFP_KERNEL : + GFP_HIGHUSER) | __GFP_NOWARN); + if (!table->hem[hem_idx]) { + ret = -ENOMEM; + goto err_alloc_hem_buf; + } + + hns_roce_hem_first(table->hem[hem_idx], &iter); + bt_ba = hns_roce_hem_addr(&iter); + + if (table->type < HEM_TYPE_MTT) { + if (hop_num == 2) { + *(table->bt_l1[bt_l1_idx] + mhop.l2_idx) = bt_ba; + step_idx = 2; + } else if (hop_num == 1) { + *(table->bt_l0[bt_l0_idx] + mhop.l1_idx) = bt_ba; + step_idx = 1; + } else if (hop_num == HNS_ROCE_HOP_NUM_0) { + step_idx = 0; + } + + /* set HEM base address to hardware */ + if (hr_dev->hw->set_hem(hr_dev, table, obj, step_idx)) { + ret = -ENODEV; + dev_err(dev, "set HEM base address to HW failed!\n"); + goto err_alloc_hem_buf; + } + } else if (hop_num == 2) { + *(table->bt_l0[bt_l0_idx] + mhop.l1_idx) = bt_ba; + } + + ++table->hem[hem_idx]->refcount; + goto out; + +err_alloc_hem_buf: + if (bt_l1_allocated) { + dma_free_coherent(dev, bt_chunk_size, table->bt_l1[bt_l1_idx], + table->bt_l1_dma_addr[bt_l1_idx]); + table->bt_l1[bt_l1_idx] = NULL; + } + +err_dma_alloc_l1: + if (bt_l0_allocated) { + dma_free_coherent(dev, bt_chunk_size, table->bt_l0[bt_l0_idx], + table->bt_l0_dma_addr[bt_l0_idx]); + table->bt_l0[bt_l0_idx] = NULL; + } + +out: + mutex_unlock(&table->mutex); + return ret; +} + int hns_roce_table_get(struct hns_roce_dev *hr_dev, struct hns_roce_hem_table *table, unsigned long obj) { - struct device *dev = &hr_dev->pdev->dev; + struct device *dev = hr_dev->dev; int ret = 0; unsigned long i; - i = (obj & (table->num_obj - 1)) / (HNS_ROCE_TABLE_CHUNK_SIZE / + if (hns_roce_check_whether_mhop(hr_dev, table->type)) + return hns_roce_table_mhop_get(hr_dev, table, obj); + + i = (obj & (table->num_obj - 1)) / (table->table_chunk_size / table->obj_size); mutex_lock(&table->mutex); @@ -227,7 +549,8 @@ int hns_roce_table_get(struct hns_roce_dev *hr_dev, } table->hem[i] = hns_roce_alloc_hem(hr_dev, - HNS_ROCE_TABLE_CHUNK_SIZE >> PAGE_SHIFT, + table->table_chunk_size >> PAGE_SHIFT, + table->table_chunk_size, (table->lowmem ? GFP_KERNEL : GFP_HIGHUSER) | __GFP_NOWARN); if (!table->hem[i]) { @@ -237,6 +560,8 @@ int hns_roce_table_get(struct hns_roce_dev *hr_dev, /* Set HEM base address(128K/page, pa) to Hardware */ if (hns_roce_set_hem(hr_dev, table, obj)) { + hns_roce_free_hem(hr_dev, table->hem[i]); + table->hem[i] = NULL; ret = -ENODEV; dev_err(dev, "set HEM base address to HW failed.\n"); goto out; @@ -248,20 +573,139 @@ out: return ret; } +static void hns_roce_table_mhop_put(struct hns_roce_dev *hr_dev, + struct hns_roce_hem_table *table, + unsigned long obj, + int check_refcount) +{ + struct device *dev = hr_dev->dev; + struct hns_roce_hem_mhop mhop; + unsigned long mhop_obj = obj; + u32 bt_chunk_size; + u32 chunk_ba_num; + u32 hop_num; + u32 start_idx; + u32 bt_num; + u64 hem_idx; + u64 bt_l1_idx = 0; + int ret; + + ret = hns_roce_calc_hem_mhop(hr_dev, table, &mhop_obj, &mhop); + if (ret) + return; + + bt_chunk_size = mhop.bt_chunk_size; + hop_num = mhop.hop_num; + chunk_ba_num = bt_chunk_size / 8; + + bt_num = hns_roce_get_bt_num(table->type, hop_num); + switch (bt_num) { + case 3: + hem_idx = mhop.l0_idx * chunk_ba_num * chunk_ba_num + + mhop.l1_idx * chunk_ba_num + mhop.l2_idx; + bt_l1_idx = mhop.l0_idx * chunk_ba_num + mhop.l1_idx; + break; + case 2: + hem_idx = mhop.l0_idx * chunk_ba_num + mhop.l1_idx; + break; + case 1: + hem_idx = mhop.l0_idx; + break; + default: + dev_err(dev, "Table %d not support hop_num = %d!\n", + table->type, hop_num); + return; + } + + mutex_lock(&table->mutex); + + if (check_refcount && (--table->hem[hem_idx]->refcount > 0)) { + mutex_unlock(&table->mutex); + return; + } + + if (table->type < HEM_TYPE_MTT && hop_num == 1) { + if (hr_dev->hw->clear_hem(hr_dev, table, obj, 1)) + dev_warn(dev, "Clear HEM base address failed.\n"); + } else if (table->type < HEM_TYPE_MTT && hop_num == 2) { + if (hr_dev->hw->clear_hem(hr_dev, table, obj, 2)) + dev_warn(dev, "Clear HEM base address failed.\n"); + } else if (table->type < HEM_TYPE_MTT && + hop_num == HNS_ROCE_HOP_NUM_0) { + if (hr_dev->hw->clear_hem(hr_dev, table, obj, 0)) + dev_warn(dev, "Clear HEM base address failed.\n"); + } + + /* + * free buffer space chunk for QPC/MTPT/CQC/SRQC. + * free bt space chunk for MTT/CQE. + */ + hns_roce_free_hem(hr_dev, table->hem[hem_idx]); + table->hem[hem_idx] = NULL; + + if (check_whether_bt_num_2(table->type, hop_num)) { + start_idx = mhop.l0_idx * chunk_ba_num; + if (hns_roce_check_hem_null(table->hem, start_idx, + chunk_ba_num)) { + if (table->type < HEM_TYPE_MTT && + hr_dev->hw->clear_hem(hr_dev, table, obj, 0)) + dev_warn(dev, "Clear HEM base address failed.\n"); + + dma_free_coherent(dev, bt_chunk_size, + table->bt_l0[mhop.l0_idx], + table->bt_l0_dma_addr[mhop.l0_idx]); + table->bt_l0[mhop.l0_idx] = NULL; + } + } else if (check_whether_bt_num_3(table->type, hop_num)) { + start_idx = mhop.l0_idx * chunk_ba_num * chunk_ba_num + + mhop.l1_idx * chunk_ba_num; + if (hns_roce_check_hem_null(table->hem, start_idx, + chunk_ba_num)) { + if (hr_dev->hw->clear_hem(hr_dev, table, obj, 1)) + dev_warn(dev, "Clear HEM base address failed.\n"); + + dma_free_coherent(dev, bt_chunk_size, + table->bt_l1[bt_l1_idx], + table->bt_l1_dma_addr[bt_l1_idx]); + table->bt_l1[bt_l1_idx] = NULL; + + start_idx = mhop.l0_idx * chunk_ba_num; + if (hns_roce_check_bt_null(table->bt_l1, start_idx, + chunk_ba_num)) { + if (hr_dev->hw->clear_hem(hr_dev, table, obj, + 0)) + dev_warn(dev, "Clear HEM base address failed.\n"); + + dma_free_coherent(dev, bt_chunk_size, + table->bt_l0[mhop.l0_idx], + table->bt_l0_dma_addr[mhop.l0_idx]); + table->bt_l0[mhop.l0_idx] = NULL; + } + } + } + + mutex_unlock(&table->mutex); +} + void hns_roce_table_put(struct hns_roce_dev *hr_dev, struct hns_roce_hem_table *table, unsigned long obj) { - struct device *dev = &hr_dev->pdev->dev; + struct device *dev = hr_dev->dev; unsigned long i; + if (hns_roce_check_whether_mhop(hr_dev, table->type)) { + hns_roce_table_mhop_put(hr_dev, table, obj, 1); + return; + } + i = (obj & (table->num_obj - 1)) / - (HNS_ROCE_TABLE_CHUNK_SIZE / table->obj_size); + (table->table_chunk_size / table->obj_size); mutex_lock(&table->mutex); if (--table->hem[i]->refcount == 0) { /* Clear HEM base address */ - if (hr_dev->hw->clear_hem(hr_dev, table, obj)) + if (hr_dev->hw->clear_hem(hr_dev, table, obj, 0)) dev_warn(dev, "Clear HEM base address failed.\n"); hns_roce_free_hem(hr_dev, table->hem[i]); @@ -271,23 +715,46 @@ void hns_roce_table_put(struct hns_roce_dev *hr_dev, mutex_unlock(&table->mutex); } -void *hns_roce_table_find(struct hns_roce_hem_table *table, unsigned long obj, - dma_addr_t *dma_handle) +void *hns_roce_table_find(struct hns_roce_dev *hr_dev, + struct hns_roce_hem_table *table, + unsigned long obj, dma_addr_t *dma_handle) { struct hns_roce_hem_chunk *chunk; - unsigned long idx; - int i; - int offset, dma_offset; + struct hns_roce_hem_mhop mhop; struct hns_roce_hem *hem; struct page *page = NULL; + unsigned long mhop_obj = obj; + unsigned long idx; + int offset, dma_offset; + int i, j; + u32 hem_idx = 0; if (!table->lowmem) return NULL; mutex_lock(&table->mutex); - idx = (obj & (table->num_obj - 1)) * table->obj_size; - hem = table->hem[idx / HNS_ROCE_TABLE_CHUNK_SIZE]; - dma_offset = offset = idx % HNS_ROCE_TABLE_CHUNK_SIZE; + + if (!hns_roce_check_whether_mhop(hr_dev, table->type)) { + idx = (obj & (table->num_obj - 1)) * table->obj_size; + hem = table->hem[idx / table->table_chunk_size]; + dma_offset = offset = idx % table->table_chunk_size; + } else { + hns_roce_calc_hem_mhop(hr_dev, table, &mhop_obj, &mhop); + /* mtt mhop */ + i = mhop.l0_idx; + j = mhop.l1_idx; + if (mhop.hop_num == 2) + hem_idx = i * (mhop.bt_chunk_size / 8) + j; + else if (mhop.hop_num == 1 || + mhop.hop_num == HNS_ROCE_HOP_NUM_0) + hem_idx = i; + + hem = table->hem[hem_idx]; + dma_offset = offset = (obj & (table->num_obj - 1)) * + table->obj_size % mhop.bt_chunk_size; + if (mhop.hop_num == 2) + dma_offset = offset = 0; + } if (!hem) goto out; @@ -314,14 +781,21 @@ out: mutex_unlock(&table->mutex); return page ? lowmem_page_address(page) + offset : NULL; } +EXPORT_SYMBOL_GPL(hns_roce_table_find); int hns_roce_table_get_range(struct hns_roce_dev *hr_dev, struct hns_roce_hem_table *table, unsigned long start, unsigned long end) { - unsigned long inc = HNS_ROCE_TABLE_CHUNK_SIZE / table->obj_size; - unsigned long i = 0; - int ret = 0; + struct hns_roce_hem_mhop mhop; + unsigned long inc = table->table_chunk_size / table->obj_size; + unsigned long i; + int ret; + + if (hns_roce_check_whether_mhop(hr_dev, table->type)) { + hns_roce_calc_hem_mhop(hr_dev, table, NULL, &mhop); + inc = mhop.bt_chunk_size / table->obj_size; + } /* Allocate MTT entry memory according to chunk(128K) */ for (i = start; i <= end; i += inc) { @@ -344,10 +818,16 @@ void hns_roce_table_put_range(struct hns_roce_dev *hr_dev, struct hns_roce_hem_table *table, unsigned long start, unsigned long end) { + struct hns_roce_hem_mhop mhop; + unsigned long inc = table->table_chunk_size / table->obj_size; unsigned long i; - for (i = start; i <= end; - i += HNS_ROCE_TABLE_CHUNK_SIZE / table->obj_size) + if (hns_roce_check_whether_mhop(hr_dev, table->type)) { + hns_roce_calc_hem_mhop(hr_dev, table, NULL, &mhop); + inc = mhop.bt_chunk_size / table->obj_size; + } + + for (i = start; i <= end; i += inc) hns_roce_table_put(hr_dev, table, i); } @@ -356,15 +836,120 @@ int hns_roce_init_hem_table(struct hns_roce_dev *hr_dev, unsigned long obj_size, unsigned long nobj, int use_lowmem) { + struct device *dev = hr_dev->dev; unsigned long obj_per_chunk; unsigned long num_hem; - obj_per_chunk = HNS_ROCE_TABLE_CHUNK_SIZE / obj_size; - num_hem = (nobj + obj_per_chunk - 1) / obj_per_chunk; + if (!hns_roce_check_whether_mhop(hr_dev, type)) { + table->table_chunk_size = hr_dev->caps.chunk_sz; + obj_per_chunk = table->table_chunk_size / obj_size; + num_hem = (nobj + obj_per_chunk - 1) / obj_per_chunk; + + table->hem = kcalloc(num_hem, sizeof(*table->hem), GFP_KERNEL); + if (!table->hem) + return -ENOMEM; + } else { + unsigned long buf_chunk_size; + unsigned long bt_chunk_size; + unsigned long bt_chunk_num; + unsigned long num_bt_l0 = 0; + u32 hop_num; + + switch (type) { + case HEM_TYPE_QPC: + buf_chunk_size = 1 << (hr_dev->caps.qpc_buf_pg_sz + + PAGE_SHIFT); + bt_chunk_size = 1 << (hr_dev->caps.qpc_ba_pg_sz + + PAGE_SHIFT); + num_bt_l0 = hr_dev->caps.qpc_bt_num; + hop_num = hr_dev->caps.qpc_hop_num; + break; + case HEM_TYPE_MTPT: + buf_chunk_size = 1 << (hr_dev->caps.mpt_buf_pg_sz + + PAGE_SHIFT); + bt_chunk_size = 1 << (hr_dev->caps.mpt_ba_pg_sz + + PAGE_SHIFT); + num_bt_l0 = hr_dev->caps.mpt_bt_num; + hop_num = hr_dev->caps.mpt_hop_num; + break; + case HEM_TYPE_CQC: + buf_chunk_size = 1 << (hr_dev->caps.cqc_buf_pg_sz + + PAGE_SHIFT); + bt_chunk_size = 1 << (hr_dev->caps.cqc_ba_pg_sz + + PAGE_SHIFT); + num_bt_l0 = hr_dev->caps.cqc_bt_num; + hop_num = hr_dev->caps.cqc_hop_num; + break; + case HEM_TYPE_SRQC: + buf_chunk_size = 1 << (hr_dev->caps.srqc_buf_pg_sz + + PAGE_SHIFT); + bt_chunk_size = 1 << (hr_dev->caps.srqc_ba_pg_sz + + PAGE_SHIFT); + num_bt_l0 = hr_dev->caps.srqc_bt_num; + hop_num = hr_dev->caps.srqc_hop_num; + break; + case HEM_TYPE_MTT: + buf_chunk_size = 1 << (hr_dev->caps.mtt_ba_pg_sz + + PAGE_SHIFT); + bt_chunk_size = buf_chunk_size; + hop_num = hr_dev->caps.mtt_hop_num; + break; + case HEM_TYPE_CQE: + buf_chunk_size = 1 << (hr_dev->caps.cqe_ba_pg_sz + + PAGE_SHIFT); + bt_chunk_size = buf_chunk_size; + hop_num = hr_dev->caps.cqe_hop_num; + break; + default: + dev_err(dev, + "Table %d not support to init hem table here!\n", + type); + return -EINVAL; + } + obj_per_chunk = buf_chunk_size / obj_size; + num_hem = (nobj + obj_per_chunk - 1) / obj_per_chunk; + bt_chunk_num = bt_chunk_size / 8; + if (table->type >= HEM_TYPE_MTT) + num_bt_l0 = bt_chunk_num; + + table->hem = kcalloc(num_hem, sizeof(*table->hem), + GFP_KERNEL); + if (!table->hem) + goto err_kcalloc_hem_buf; + + if (check_whether_bt_num_3(table->type, hop_num)) { + unsigned long num_bt_l1; + + num_bt_l1 = (num_hem + bt_chunk_num - 1) / + bt_chunk_num; + table->bt_l1 = kcalloc(num_bt_l1, + sizeof(*table->bt_l1), + GFP_KERNEL); + if (!table->bt_l1) + goto err_kcalloc_bt_l1; + + table->bt_l1_dma_addr = kcalloc(num_bt_l1, + sizeof(*table->bt_l1_dma_addr), + GFP_KERNEL); + + if (!table->bt_l1_dma_addr) + goto err_kcalloc_l1_dma; + } - table->hem = kcalloc(num_hem, sizeof(*table->hem), GFP_KERNEL); - if (!table->hem) - return -ENOMEM; + if (check_whether_bt_num_2(table->type, hop_num) || + check_whether_bt_num_3(table->type, hop_num)) { + table->bt_l0 = kcalloc(num_bt_l0, sizeof(*table->bt_l0), + GFP_KERNEL); + if (!table->bt_l0) + goto err_kcalloc_bt_l0; + + table->bt_l0_dma_addr = kcalloc(num_bt_l0, + sizeof(*table->bt_l0_dma_addr), + GFP_KERNEL); + if (!table->bt_l0_dma_addr) + goto err_kcalloc_l0_dma; + } + } table->type = type; table->num_hem = num_hem; @@ -374,18 +959,72 @@ int hns_roce_init_hem_table(struct hns_roce_dev *hr_dev, mutex_init(&table->mutex); return 0; + +err_kcalloc_l0_dma: + kfree(table->bt_l0); + table->bt_l0 = NULL; + +err_kcalloc_bt_l0: + kfree(table->bt_l1_dma_addr); + table->bt_l1_dma_addr = NULL; + +err_kcalloc_l1_dma: + kfree(table->bt_l1); + table->bt_l1 = NULL; + +err_kcalloc_bt_l1: + kfree(table->hem); + table->hem = NULL; + +err_kcalloc_hem_buf: + return -ENOMEM; +} + +static void hns_roce_cleanup_mhop_hem_table(struct hns_roce_dev *hr_dev, + struct hns_roce_hem_table *table) +{ + struct hns_roce_hem_mhop mhop; + u32 buf_chunk_size; + int i; + u64 obj; + + hns_roce_calc_hem_mhop(hr_dev, table, NULL, &mhop); + buf_chunk_size = table->type < HEM_TYPE_MTT ? mhop.buf_chunk_size : + mhop.bt_chunk_size; + + for (i = 0; i < table->num_hem; ++i) { + obj = i * buf_chunk_size / table->obj_size; + if (table->hem[i]) + hns_roce_table_mhop_put(hr_dev, table, obj, 0); + } + + kfree(table->hem); + table->hem = NULL; + kfree(table->bt_l1); + table->bt_l1 = NULL; + kfree(table->bt_l1_dma_addr); + table->bt_l1_dma_addr = NULL; + kfree(table->bt_l0); + table->bt_l0 = NULL; + kfree(table->bt_l0_dma_addr); + table->bt_l0_dma_addr = NULL; } void hns_roce_cleanup_hem_table(struct hns_roce_dev *hr_dev, struct hns_roce_hem_table *table) { - struct device *dev = &hr_dev->pdev->dev; + struct device *dev = hr_dev->dev; unsigned long i; + if (hns_roce_check_whether_mhop(hr_dev, table->type)) { + hns_roce_cleanup_mhop_hem_table(hr_dev, table); + return; + } + for (i = 0; i < table->num_hem; ++i) if (table->hem[i]) { if (hr_dev->hw->clear_hem(hr_dev, table, - i * HNS_ROCE_TABLE_CHUNK_SIZE / table->obj_size)) + i * table->table_chunk_size / table->obj_size, 0)) dev_err(dev, "Clear HEM base address failed.\n"); hns_roce_free_hem(hr_dev, table->hem[i]); @@ -401,4 +1040,7 @@ void hns_roce_cleanup_hem(struct hns_roce_dev *hr_dev) hns_roce_cleanup_hem_table(hr_dev, &hr_dev->qp_table.qp_table); hns_roce_cleanup_hem_table(hr_dev, &hr_dev->mr_table.mtpt_table); hns_roce_cleanup_hem_table(hr_dev, &hr_dev->mr_table.mtt_table); + if (hns_roce_check_whether_mhop(hr_dev, HEM_TYPE_CQE)) + hns_roce_cleanup_hem_table(hr_dev, + &hr_dev->mr_table.mtt_cqe_table); } diff --git a/drivers/infiniband/hw/hns/hns_roce_hem.h b/drivers/infiniband/hw/hns/hns_roce_hem.h index 435748858252..af28bbf31c7f 100644 --- a/drivers/infiniband/hw/hns/hns_roce_hem.h +++ b/drivers/infiniband/hw/hns/hns_roce_hem.h @@ -47,6 +47,7 @@ enum { /* UNMAP HEM */ HEM_TYPE_MTT, + HEM_TYPE_CQE, HEM_TYPE_IRRL, }; @@ -54,6 +55,18 @@ enum { ((256 - sizeof(struct list_head) - 2 * sizeof(int)) / \ (sizeof(struct scatterlist))) +#define check_whether_bt_num_3(type, hop_num) \ + (type < HEM_TYPE_MTT && hop_num == 2) + +#define check_whether_bt_num_2(type, hop_num) \ + ((type < HEM_TYPE_MTT && hop_num == 1) || \ + (type >= HEM_TYPE_MTT && hop_num == 2)) + +#define check_whether_bt_num_1(type, hop_num) \ + ((type < HEM_TYPE_MTT && hop_num == HNS_ROCE_HOP_NUM_0) || \ + (type >= HEM_TYPE_MTT && hop_num == 1) || \ + (type >= HEM_TYPE_MTT && hop_num == HNS_ROCE_HOP_NUM_0)) + enum { HNS_ROCE_HEM_PAGE_SHIFT = 12, HNS_ROCE_HEM_PAGE_SIZE = 1 << HNS_ROCE_HEM_PAGE_SHIFT, @@ -77,12 +90,23 @@ struct hns_roce_hem_iter { int page_idx; }; +struct hns_roce_hem_mhop { + u32 hop_num; + u32 buf_chunk_size; + u32 bt_chunk_size; + u32 ba_l0_num; + u32 l0_idx;/* level 0 base address table index */ + u32 l1_idx;/* level 1 base address table index */ + u32 l2_idx;/* level 2 base address table index */ +}; + void hns_roce_free_hem(struct hns_roce_dev *hr_dev, struct hns_roce_hem *hem); int hns_roce_table_get(struct hns_roce_dev *hr_dev, struct hns_roce_hem_table *table, unsigned long obj); void hns_roce_table_put(struct hns_roce_dev *hr_dev, struct hns_roce_hem_table *table, unsigned long obj); -void *hns_roce_table_find(struct hns_roce_hem_table *table, unsigned long obj, +void *hns_roce_table_find(struct hns_roce_dev *hr_dev, + struct hns_roce_hem_table *table, unsigned long obj, dma_addr_t *dma_handle); int hns_roce_table_get_range(struct hns_roce_dev *hr_dev, struct hns_roce_hem_table *table, @@ -97,6 +121,10 @@ int hns_roce_init_hem_table(struct hns_roce_dev *hr_dev, void hns_roce_cleanup_hem_table(struct hns_roce_dev *hr_dev, struct hns_roce_hem_table *table); void hns_roce_cleanup_hem(struct hns_roce_dev *hr_dev); +int hns_roce_calc_hem_mhop(struct hns_roce_dev *hr_dev, + struct hns_roce_hem_table *table, unsigned long *obj, + struct hns_roce_hem_mhop *mhop); +bool hns_roce_check_whether_mhop(struct hns_roce_dev *hr_dev, u32 type); static inline void hns_roce_hem_first(struct hns_roce_hem *hem, struct hns_roce_hem_iter *iter) @@ -105,7 +133,7 @@ static inline void hns_roce_hem_first(struct hns_roce_hem *hem, iter->chunk = list_empty(&hem->chunk_list) ? NULL : list_entry(hem->chunk_list.next, struct hns_roce_hem_chunk, list); - iter->page_idx = 0; + iter->page_idx = 0; } static inline int hns_roce_hem_last(struct hns_roce_hem_iter *iter) diff --git a/drivers/infiniband/hw/hns/hns_roce_hw_v1.c b/drivers/infiniband/hw/hns/hns_roce_hw_v1.c index 747efd1ae5a6..00cbfc97bea8 100644 --- a/drivers/infiniband/hw/hns/hns_roce_hw_v1.c +++ b/drivers/infiniband/hw/hns/hns_roce_hw_v1.c @@ -34,6 +34,7 @@ #include <linux/acpi.h> #include <linux/etherdevice.h> #include <linux/of.h> +#include <linux/of_platform.h> #include <rdma/ib_umem.h> #include "hns_roce_common.h" #include "hns_roce_device.h" @@ -56,8 +57,8 @@ static void set_raddr_seg(struct hns_roce_wqe_raddr_seg *rseg, u64 remote_addr, rseg->len = 0; } -int hns_roce_v1_post_send(struct ib_qp *ibqp, struct ib_send_wr *wr, - struct ib_send_wr **bad_wr) +static int hns_roce_v1_post_send(struct ib_qp *ibqp, struct ib_send_wr *wr, + struct ib_send_wr **bad_wr) { struct hns_roce_dev *hr_dev = to_hr_dev(ibqp->device); struct hns_roce_ah *ah = to_hr_ah(ud_wr(wr)->ah); @@ -316,8 +317,8 @@ out: return ret; } -int hns_roce_v1_post_recv(struct ib_qp *ibqp, struct ib_recv_wr *wr, - struct ib_recv_wr **bad_wr) +static int hns_roce_v1_post_recv(struct ib_qp *ibqp, struct ib_recv_wr *wr, + struct ib_recv_wr **bad_wr) { int ret = 0; int nreq = 0; @@ -472,7 +473,7 @@ static void hns_roce_set_sdb_ext(struct hns_roce_dev *hr_dev, u32 ext_sdb_alept, dma_addr_t sdb_dma_addr; u32 val; - priv = (struct hns_roce_v1_priv *)hr_dev->hw->priv; + priv = (struct hns_roce_v1_priv *)hr_dev->priv; db = &priv->db_table; /* Configure extend SDB threshold */ @@ -511,7 +512,7 @@ static void hns_roce_set_odb_ext(struct hns_roce_dev *hr_dev, u32 ext_odb_alept, dma_addr_t odb_dma_addr; u32 val; - priv = (struct hns_roce_v1_priv *)hr_dev->hw->priv; + priv = (struct hns_roce_v1_priv *)hr_dev->priv; db = &priv->db_table; /* Configure extend ODB threshold */ @@ -547,7 +548,7 @@ static int hns_roce_db_ext_init(struct hns_roce_dev *hr_dev, u32 sdb_ext_mod, dma_addr_t odb_dma_addr; int ret = 0; - priv = (struct hns_roce_v1_priv *)hr_dev->hw->priv; + priv = (struct hns_roce_v1_priv *)hr_dev->priv; db = &priv->db_table; db->ext_db = kmalloc(sizeof(*db->ext_db), GFP_KERNEL); @@ -668,7 +669,7 @@ static int hns_roce_v1_rsv_lp_qp(struct hns_roce_dev *hr_dev) u8 port = 0; u8 sl; - priv = (struct hns_roce_v1_priv *)hr_dev->hw->priv; + priv = (struct hns_roce_v1_priv *)hr_dev->priv; free_mr = &priv->free_mr; /* Reserved cq for loop qp */ @@ -816,7 +817,7 @@ static void hns_roce_v1_release_lp_qp(struct hns_roce_dev *hr_dev) int ret; int i; - priv = (struct hns_roce_v1_priv *)hr_dev->hw->priv; + priv = (struct hns_roce_v1_priv *)hr_dev->priv; free_mr = &priv->free_mr; for (i = 0; i < HNS_ROCE_V1_RESV_QP; i++) { @@ -850,7 +851,7 @@ static int hns_roce_db_init(struct hns_roce_dev *hr_dev) u32 odb_evt_mod; int ret = 0; - priv = (struct hns_roce_v1_priv *)hr_dev->hw->priv; + priv = (struct hns_roce_v1_priv *)hr_dev->priv; db = &priv->db_table; memset(db, 0, sizeof(*db)); @@ -876,7 +877,7 @@ static int hns_roce_db_init(struct hns_roce_dev *hr_dev) return 0; } -void hns_roce_v1_recreate_lp_qp_work_fn(struct work_struct *work) +static void hns_roce_v1_recreate_lp_qp_work_fn(struct work_struct *work) { struct hns_roce_recreate_lp_qp_work *lp_qp_work; struct hns_roce_dev *hr_dev; @@ -906,11 +907,13 @@ static int hns_roce_v1_recreate_lp_qp(struct hns_roce_dev *hr_dev) unsigned long end = msecs_to_jiffies(HNS_ROCE_V1_RECREATE_LP_QP_TIMEOUT_MSECS) + jiffies; - priv = (struct hns_roce_v1_priv *)hr_dev->hw->priv; + priv = (struct hns_roce_v1_priv *)hr_dev->priv; free_mr = &priv->free_mr; lp_qp_work = kzalloc(sizeof(struct hns_roce_recreate_lp_qp_work), GFP_KERNEL); + if (!lp_qp_work) + return -ENOMEM; INIT_WORK(&(lp_qp_work->work), hns_roce_v1_recreate_lp_qp_work_fn); @@ -982,7 +985,7 @@ static void hns_roce_v1_mr_free_work_fn(struct work_struct *work) hr_dev = to_hr_dev(mr_work->ib_dev); dev = &hr_dev->pdev->dev; - priv = (struct hns_roce_v1_priv *)hr_dev->hw->priv; + priv = (struct hns_roce_v1_priv *)hr_dev->priv; free_mr = &priv->free_mr; mr_free_cq = free_mr->mr_free_cq; @@ -1001,6 +1004,11 @@ static void hns_roce_v1_mr_free_work_fn(struct work_struct *work) } } + if (!ne) { + dev_err(dev, "Reserved loop qp is absent!\n"); + goto free_work; + } + do { ret = hns_roce_v1_poll_cq(&mr_free_cq->ib_cq, ne, wc); if (ret < 0) { @@ -1025,7 +1033,8 @@ free_work: kfree(mr_work); } -int hns_roce_v1_dereg_mr(struct hns_roce_dev *hr_dev, struct hns_roce_mr *mr) +static int hns_roce_v1_dereg_mr(struct hns_roce_dev *hr_dev, + struct hns_roce_mr *mr) { struct device *dev = &hr_dev->pdev->dev; struct hns_roce_mr_free_work *mr_work; @@ -1038,7 +1047,7 @@ int hns_roce_v1_dereg_mr(struct hns_roce_dev *hr_dev, struct hns_roce_mr *mr) int npages; int ret = 0; - priv = (struct hns_roce_v1_priv *)hr_dev->hw->priv; + priv = (struct hns_roce_v1_priv *)hr_dev->priv; free_mr = &priv->free_mr; if (mr->enabled) { @@ -1103,7 +1112,7 @@ static void hns_roce_db_free(struct hns_roce_dev *hr_dev) struct hns_roce_v1_priv *priv; struct hns_roce_db_table *db; - priv = (struct hns_roce_v1_priv *)hr_dev->hw->priv; + priv = (struct hns_roce_v1_priv *)hr_dev->priv; db = &priv->db_table; if (db->sdb_ext_mod) { @@ -1133,7 +1142,7 @@ static int hns_roce_raq_init(struct hns_roce_dev *hr_dev) struct hns_roce_raq_table *raq; struct device *dev = &hr_dev->pdev->dev; - priv = (struct hns_roce_v1_priv *)hr_dev->hw->priv; + priv = (struct hns_roce_v1_priv *)hr_dev->priv; raq = &priv->raq_table; raq->e_raq_buf = kzalloc(sizeof(*(raq->e_raq_buf)), GFP_KERNEL); @@ -1210,7 +1219,7 @@ static void hns_roce_raq_free(struct hns_roce_dev *hr_dev) struct hns_roce_v1_priv *priv; struct hns_roce_raq_table *raq; - priv = (struct hns_roce_v1_priv *)hr_dev->hw->priv; + priv = (struct hns_roce_v1_priv *)hr_dev->priv; raq = &priv->raq_table; dma_free_coherent(dev, HNS_ROCE_V1_RAQ_SIZE, raq->e_raq_buf->buf, @@ -1244,7 +1253,7 @@ static int hns_roce_bt_init(struct hns_roce_dev *hr_dev) struct hns_roce_v1_priv *priv; int ret; - priv = (struct hns_roce_v1_priv *)hr_dev->hw->priv; + priv = (struct hns_roce_v1_priv *)hr_dev->priv; priv->bt_table.qpc_buf.buf = dma_alloc_coherent(dev, HNS_ROCE_BT_RSV_BUF_SIZE, &priv->bt_table.qpc_buf.map, @@ -1286,7 +1295,7 @@ static void hns_roce_bt_free(struct hns_roce_dev *hr_dev) struct device *dev = &hr_dev->pdev->dev; struct hns_roce_v1_priv *priv; - priv = (struct hns_roce_v1_priv *)hr_dev->hw->priv; + priv = (struct hns_roce_v1_priv *)hr_dev->priv; dma_free_coherent(dev, HNS_ROCE_BT_RSV_BUF_SIZE, priv->bt_table.cqc_buf.buf, priv->bt_table.cqc_buf.map); @@ -1304,7 +1313,7 @@ static int hns_roce_tptr_init(struct hns_roce_dev *hr_dev) struct hns_roce_buf_list *tptr_buf; struct hns_roce_v1_priv *priv; - priv = (struct hns_roce_v1_priv *)hr_dev->hw->priv; + priv = (struct hns_roce_v1_priv *)hr_dev->priv; tptr_buf = &priv->tptr_table.tptr_buf; /* @@ -1330,7 +1339,7 @@ static void hns_roce_tptr_free(struct hns_roce_dev *hr_dev) struct hns_roce_buf_list *tptr_buf; struct hns_roce_v1_priv *priv; - priv = (struct hns_roce_v1_priv *)hr_dev->hw->priv; + priv = (struct hns_roce_v1_priv *)hr_dev->priv; tptr_buf = &priv->tptr_table.tptr_buf; dma_free_coherent(dev, HNS_ROCE_V1_TPTR_BUF_SIZE, @@ -1344,7 +1353,7 @@ static int hns_roce_free_mr_init(struct hns_roce_dev *hr_dev) struct hns_roce_v1_priv *priv; int ret = 0; - priv = (struct hns_roce_v1_priv *)hr_dev->hw->priv; + priv = (struct hns_roce_v1_priv *)hr_dev->priv; free_mr = &priv->free_mr; free_mr->free_mr_wq = create_singlethread_workqueue("hns_roce_free_mr"); @@ -1368,7 +1377,7 @@ static void hns_roce_free_mr_free(struct hns_roce_dev *hr_dev) struct hns_roce_free_mr *free_mr; struct hns_roce_v1_priv *priv; - priv = (struct hns_roce_v1_priv *)hr_dev->hw->priv; + priv = (struct hns_roce_v1_priv *)hr_dev->priv; free_mr = &priv->free_mr; flush_workqueue(free_mr->free_mr_wq); @@ -1383,7 +1392,7 @@ static void hns_roce_free_mr_free(struct hns_roce_dev *hr_dev) * @enable: true -- drop reset, false -- reset * return 0 - success , negative --fail */ -int hns_roce_v1_reset(struct hns_roce_dev *hr_dev, bool dereset) +static int hns_roce_v1_reset(struct hns_roce_dev *hr_dev, bool dereset) { struct device_node *dsaf_node; struct device *dev = &hr_dev->pdev->dev; @@ -1432,7 +1441,7 @@ static int hns_roce_des_qp_init(struct hns_roce_dev *hr_dev) struct hns_roce_v1_priv *priv; struct hns_roce_des_qp *des_qp; - priv = (struct hns_roce_v1_priv *)hr_dev->hw->priv; + priv = (struct hns_roce_v1_priv *)hr_dev->priv; des_qp = &priv->des_qp; des_qp->requeue_flag = 1; @@ -1450,7 +1459,7 @@ static void hns_roce_des_qp_free(struct hns_roce_dev *hr_dev) struct hns_roce_v1_priv *priv; struct hns_roce_des_qp *des_qp; - priv = (struct hns_roce_v1_priv *)hr_dev->hw->priv; + priv = (struct hns_roce_v1_priv *)hr_dev->priv; des_qp = &priv->des_qp; des_qp->requeue_flag = 0; @@ -1458,7 +1467,7 @@ static void hns_roce_des_qp_free(struct hns_roce_dev *hr_dev) destroy_workqueue(des_qp->qp_wq); } -void hns_roce_v1_profile(struct hns_roce_dev *hr_dev) +static int hns_roce_v1_profile(struct hns_roce_dev *hr_dev) { int i = 0; struct hns_roce_caps *caps = &hr_dev->caps; @@ -1474,7 +1483,9 @@ void hns_roce_v1_profile(struct hns_roce_dev *hr_dev) caps->num_qps = HNS_ROCE_V1_MAX_QP_NUM; caps->max_wqes = HNS_ROCE_V1_MAX_WQE_NUM; + caps->min_wqes = HNS_ROCE_MIN_WQE_NUM; caps->num_cqs = HNS_ROCE_V1_MAX_CQ_NUM; + caps->min_cqes = HNS_ROCE_MIN_CQE_NUM; caps->max_cqes = HNS_ROCE_V1_MAX_CQE_NUM; caps->max_sq_sg = HNS_ROCE_V1_SG_NUM; caps->max_rq_sg = HNS_ROCE_V1_SG_NUM; @@ -1503,6 +1514,7 @@ void hns_roce_v1_profile(struct hns_roce_dev *hr_dev) caps->reserved_mrws = 1; caps->reserved_uars = 0; caps->reserved_cqs = 0; + caps->chunk_sz = HNS_ROCE_V1_TABLE_CHUNK_SIZE; for (i = 0; i < caps->num_ports; i++) caps->pkey_table_len[i] = 1; @@ -1524,9 +1536,11 @@ void hns_roce_v1_profile(struct hns_roce_dev *hr_dev) caps->local_ca_ack_delay = le32_to_cpu(roce_read(hr_dev, ROCEE_ACK_DELAY_REG)); caps->max_mtu = IB_MTU_2048; + + return 0; } -int hns_roce_v1_init(struct hns_roce_dev *hr_dev) +static int hns_roce_v1_init(struct hns_roce_dev *hr_dev) { int ret; u32 val; @@ -1605,7 +1619,7 @@ error_failed_raq_init: return ret; } -void hns_roce_v1_exit(struct hns_roce_dev *hr_dev) +static void hns_roce_v1_exit(struct hns_roce_dev *hr_dev) { hns_roce_port_enable(hr_dev, HNS_ROCE_PORT_DOWN); hns_roce_free_mr_free(hr_dev); @@ -1616,8 +1630,81 @@ void hns_roce_v1_exit(struct hns_roce_dev *hr_dev) hns_roce_db_free(hr_dev); } -void hns_roce_v1_set_gid(struct hns_roce_dev *hr_dev, u8 port, int gid_index, - union ib_gid *gid) +static int hns_roce_v1_cmd_pending(struct hns_roce_dev *hr_dev) +{ + u32 status = readl(hr_dev->reg_base + ROCEE_MB6_REG); + + return (!!(status & (1 << HCR_GO_BIT))); +} + +static int hns_roce_v1_post_mbox(struct hns_roce_dev *hr_dev, u64 in_param, + u64 out_param, u32 in_modifier, u8 op_modifier, + u16 op, u16 token, int event) +{ + u32 __iomem *hcr = (u32 __iomem *)(hr_dev->reg_base + ROCEE_MB1_REG); + unsigned long end; + u32 val = 0; + + end = msecs_to_jiffies(GO_BIT_TIMEOUT_MSECS) + jiffies; + while (hns_roce_v1_cmd_pending(hr_dev)) { + if (time_after(jiffies, end)) { + dev_err(hr_dev->dev, "jiffies=%d end=%d\n", + (int)jiffies, (int)end); + return -EAGAIN; + } + cond_resched(); + } + + roce_set_field(val, ROCEE_MB6_ROCEE_MB_CMD_M, ROCEE_MB6_ROCEE_MB_CMD_S, + op); + roce_set_field(val, ROCEE_MB6_ROCEE_MB_CMD_MDF_M, + ROCEE_MB6_ROCEE_MB_CMD_MDF_S, op_modifier); + roce_set_bit(val, ROCEE_MB6_ROCEE_MB_EVENT_S, event); + roce_set_bit(val, ROCEE_MB6_ROCEE_MB_HW_RUN_S, 1); + roce_set_field(val, ROCEE_MB6_ROCEE_MB_TOKEN_M, + ROCEE_MB6_ROCEE_MB_TOKEN_S, token); + + __raw_writeq(cpu_to_le64(in_param), hcr + 0); + __raw_writeq(cpu_to_le64(out_param), hcr + 2); + __raw_writel(cpu_to_le32(in_modifier), hcr + 4); + /* Memory barrier */ + wmb(); + + __raw_writel(cpu_to_le32(val), hcr + 5); + + mmiowb(); + + return 0; +} + +static int hns_roce_v1_chk_mbox(struct hns_roce_dev *hr_dev, + unsigned long timeout) +{ + u8 __iomem *hcr = hr_dev->reg_base + ROCEE_MB1_REG; + unsigned long end = 0; + u32 status = 0; + + end = msecs_to_jiffies(timeout) + jiffies; + while (hns_roce_v1_cmd_pending(hr_dev) && time_before(jiffies, end)) + cond_resched(); + + if (hns_roce_v1_cmd_pending(hr_dev)) { + dev_err(hr_dev->dev, "[cmd_poll]hw run cmd TIMEDOUT!\n"); + return -ETIMEDOUT; + } + + status = le32_to_cpu((__force __be32) + __raw_readl(hcr + HCR_STATUS_OFFSET)); + if ((status & STATUS_MASK) != 0x1) { + dev_err(hr_dev->dev, "mailbox status 0x%x!\n", status); + return -EBUSY; + } + + return 0; +} + +static void hns_roce_v1_set_gid(struct hns_roce_dev *hr_dev, u8 port, + int gid_index, union ib_gid *gid) { u32 *p = NULL; u8 gid_idx = 0; @@ -1641,7 +1728,8 @@ void hns_roce_v1_set_gid(struct hns_roce_dev *hr_dev, u8 port, int gid_index, (HNS_ROCE_V1_GID_NUM * gid_idx)); } -void hns_roce_v1_set_mac(struct hns_roce_dev *hr_dev, u8 phy_port, u8 *addr) +static int hns_roce_v1_set_mac(struct hns_roce_dev *hr_dev, u8 phy_port, + u8 *addr) { u32 reg_smac_l; u16 reg_smac_h; @@ -1654,8 +1742,13 @@ void hns_roce_v1_set_mac(struct hns_roce_dev *hr_dev, u8 phy_port, u8 *addr) * because of smac not equal to dmac. * We Need to release and create reserved qp again. */ - if (hr_dev->hw->dereg_mr && hns_roce_v1_recreate_lp_qp(hr_dev)) - dev_warn(&hr_dev->pdev->dev, "recreate lp qp timeout!\n"); + if (hr_dev->hw->dereg_mr) { + int ret; + + ret = hns_roce_v1_recreate_lp_qp(hr_dev); + if (ret && ret != -ETIMEDOUT) + return ret; + } p = (u32 *)(&addr[0]); reg_smac_l = *p; @@ -1670,10 +1763,12 @@ void hns_roce_v1_set_mac(struct hns_roce_dev *hr_dev, u8 phy_port, u8 *addr) ROCEE_SMAC_H_ROCEE_SMAC_H_S, reg_smac_h); roce_write(hr_dev, ROCEE_SMAC_H_0_REG + phy_port * PHY_PORT_OFFSET, val); + + return 0; } -void hns_roce_v1_set_mtu(struct hns_roce_dev *hr_dev, u8 phy_port, - enum ib_mtu mtu) +static void hns_roce_v1_set_mtu(struct hns_roce_dev *hr_dev, u8 phy_port, + enum ib_mtu mtu) { u32 val; @@ -1685,8 +1780,8 @@ void hns_roce_v1_set_mtu(struct hns_roce_dev *hr_dev, u8 phy_port, val); } -int hns_roce_v1_write_mtpt(void *mb_buf, struct hns_roce_mr *mr, - unsigned long mtpt_idx) +static int hns_roce_v1_write_mtpt(void *mb_buf, struct hns_roce_mr *mr, + unsigned long mtpt_idx) { struct hns_roce_v1_mpt_entry *mpt_entry; struct scatterlist *sg; @@ -1858,7 +1953,7 @@ static struct hns_roce_cqe *next_cqe_sw(struct hns_roce_cq *hr_cq) return get_sw_cqe(hr_cq, hr_cq->cons_index); } -void hns_roce_v1_cq_set_ci(struct hns_roce_cq *hr_cq, u32 cons_index) +static void hns_roce_v1_cq_set_ci(struct hns_roce_cq *hr_cq, u32 cons_index) { u32 doorbell[2]; @@ -1931,9 +2026,10 @@ static void hns_roce_v1_cq_clean(struct hns_roce_cq *hr_cq, u32 qpn, spin_unlock_irq(&hr_cq->lock); } -void hns_roce_v1_write_cqc(struct hns_roce_dev *hr_dev, - struct hns_roce_cq *hr_cq, void *mb_buf, u64 *mtts, - dma_addr_t dma_handle, int nent, u32 vector) +static void hns_roce_v1_write_cqc(struct hns_roce_dev *hr_dev, + struct hns_roce_cq *hr_cq, void *mb_buf, + u64 *mtts, dma_addr_t dma_handle, int nent, + u32 vector) { struct hns_roce_cq_context *cq_context = NULL; struct hns_roce_buf_list *tptr_buf; @@ -1941,7 +2037,7 @@ void hns_roce_v1_write_cqc(struct hns_roce_dev *hr_dev, dma_addr_t tptr_dma_addr; int offset; - priv = (struct hns_roce_v1_priv *)hr_dev->hw->priv; + priv = (struct hns_roce_v1_priv *)hr_dev->priv; tptr_buf = &priv->tptr_table.tptr_buf; cq_context = mb_buf; @@ -2018,7 +2114,13 @@ void hns_roce_v1_write_cqc(struct hns_roce_dev *hr_dev, cq_context->cqc_byte_32 = cpu_to_le32(cq_context->cqc_byte_32); } -int hns_roce_v1_req_notify_cq(struct ib_cq *ibcq, enum ib_cq_notify_flags flags) +static int hns_roce_v1_modify_cq(struct ib_cq *cq, u16 cq_count, u16 cq_period) +{ + return -EOPNOTSUPP; +} + +static int hns_roce_v1_req_notify_cq(struct ib_cq *ibcq, + enum ib_cq_notify_flags flags) { struct hns_roce_cq *hr_cq = to_hr_cq(ibcq); u32 notification_flag; @@ -2279,8 +2381,9 @@ int hns_roce_v1_poll_cq(struct ib_cq *ibcq, int num_entries, struct ib_wc *wc) return ret; } -int hns_roce_v1_clear_hem(struct hns_roce_dev *hr_dev, - struct hns_roce_hem_table *table, int obj) +static int hns_roce_v1_clear_hem(struct hns_roce_dev *hr_dev, + struct hns_roce_hem_table *table, int obj, + int step_idx) { struct device *dev = &hr_dev->pdev->dev; struct hns_roce_v1_priv *priv; @@ -2289,7 +2392,7 @@ int hns_roce_v1_clear_hem(struct hns_roce_dev *hr_dev, void __iomem *bt_cmd; u64 bt_ba = 0; - priv = (struct hns_roce_v1_priv *)hr_dev->hw->priv; + priv = (struct hns_roce_v1_priv *)hr_dev->priv; switch (table->type) { case HEM_TYPE_QPC: @@ -2441,14 +2544,14 @@ static int hns_roce_v1_m_sqp(struct ib_qp *ibqp, const struct ib_qp_attr *attr, int rq_pa_start; u32 reg_val; u64 *mtts; - u32 *addr; + u32 __iomem *addr; context = kzalloc(sizeof(*context), GFP_KERNEL); if (!context) return -ENOMEM; /* Search QP buf's MTTs */ - mtts = hns_roce_table_find(&hr_dev->mr_table.mtt_table, + mtts = hns_roce_table_find(hr_dev, &hr_dev->mr_table.mtt_table, hr_qp->mtt.first_seg, &dma_handle); if (!mtts) { dev_err(dev, "qp buf pa find failed\n"); @@ -2523,8 +2626,9 @@ static int hns_roce_v1_m_sqp(struct ib_qp *ibqp, const struct ib_qp_attr *attr, QP1C_BYTES_40_SQ_CUR_IDX_S, 0); /* Copy context to QP1C register */ - addr = (u32 *)(hr_dev->reg_base + ROCEE_QP1C_CFG0_0_REG + - hr_qp->phy_port * sizeof(*context)); + addr = (u32 __iomem *)(hr_dev->reg_base + + ROCEE_QP1C_CFG0_0_REG + + hr_qp->phy_port * sizeof(*context)); writel(context->qp1c_bytes_4, addr); writel(context->sq_rq_bt_l, addr + 1); @@ -2595,7 +2699,7 @@ static int hns_roce_v1_m_qp(struct ib_qp *ibqp, const struct ib_qp_attr *attr, return -ENOMEM; /* Search qp buf's mtts */ - mtts = hns_roce_table_find(&hr_dev->mr_table.mtt_table, + mtts = hns_roce_table_find(hr_dev, &hr_dev->mr_table.mtt_table, hr_qp->mtt.first_seg, &dma_handle); if (mtts == NULL) { dev_err(dev, "qp buf pa find failed\n"); @@ -2603,8 +2707,8 @@ static int hns_roce_v1_m_qp(struct ib_qp *ibqp, const struct ib_qp_attr *attr, } /* Search IRRL's mtts */ - mtts_2 = hns_roce_table_find(&hr_dev->qp_table.irrl_table, hr_qp->qpn, - &dma_handle_2); + mtts_2 = hns_roce_table_find(hr_dev, &hr_dev->qp_table.irrl_table, + hr_qp->qpn, &dma_handle_2); if (mtts_2 == NULL) { dev_err(dev, "qp irrl_table find failed\n"); goto out; @@ -2800,10 +2904,11 @@ static int hns_roce_v1_m_qp(struct ib_qp *ibqp, const struct ib_qp_attr *attr, QP_CONTEXT_QPC_BYTES_32_RESPONDER_RESOURCES_S, ilog2((unsigned int)attr->max_dest_rd_atomic)); - roce_set_field(context->qpc_bytes_36, - QP_CONTEXT_QPC_BYTES_36_DEST_QP_M, - QP_CONTEXT_QPC_BYTES_36_DEST_QP_S, - attr->dest_qp_num); + if (attr_mask & IB_QP_DEST_QPN) + roce_set_field(context->qpc_bytes_36, + QP_CONTEXT_QPC_BYTES_36_DEST_QP_M, + QP_CONTEXT_QPC_BYTES_36_DEST_QP_S, + attr->dest_qp_num); /* Configure GID index */ port_num = rdma_ah_get_port_num(&attr->ah_attr); @@ -3143,7 +3248,7 @@ static int hns_roce_v1_m_qp(struct ib_qp *ibqp, const struct ib_qp_attr *attr, if (ibqp->uobject) { hr_qp->rq.db_reg_l = hr_dev->reg_base + - ROCEE_DB_OTHERS_L_0_REG + + hr_dev->odb_offset + DB_REG_OFFSET * hr_dev->priv_uar.index; } @@ -3177,9 +3282,10 @@ out: return ret; } -int hns_roce_v1_modify_qp(struct ib_qp *ibqp, const struct ib_qp_attr *attr, - int attr_mask, enum ib_qp_state cur_state, - enum ib_qp_state new_state) +static int hns_roce_v1_modify_qp(struct ib_qp *ibqp, + const struct ib_qp_attr *attr, int attr_mask, + enum ib_qp_state cur_state, + enum ib_qp_state new_state) { if (ibqp->qp_type == IB_QPT_GSI || ibqp->qp_type == IB_QPT_SMI) @@ -3270,6 +3376,7 @@ static int hns_roce_v1_q_sqp(struct ib_qp *ibqp, struct ib_qp_attr *qp_attr, qp_attr->path_mtu = IB_MTU_256; qp_attr->path_mig_state = IB_MIG_ARMED; qp_attr->qkey = QKEY_VAL; + qp_attr->ah_attr.type = RDMA_AH_ATTR_TYPE_ROCE; qp_attr->rq_psn = 0; qp_attr->sq_psn = 0; qp_attr->dest_qp_num = 1; @@ -3351,6 +3458,7 @@ static int hns_roce_v1_q_qp(struct ib_qp *ibqp, struct ib_qp_attr *qp_attr, QP_CONTEXT_QPC_BYTES_48_MTU_M, QP_CONTEXT_QPC_BYTES_48_MTU_S); qp_attr->path_mig_state = IB_MIG_ARMED; + qp_attr->ah_attr.type = RDMA_AH_ATTR_TYPE_ROCE; if (hr_qp->ibqp.qp_type == IB_QPT_UD) qp_attr->qkey = QKEY_VAL; @@ -3406,10 +3514,10 @@ static int hns_roce_v1_q_qp(struct ib_qp *ibqp, struct ib_qp_attr *qp_attr, QP_CONTEXT_QPC_BYTES_12_P_KEY_INDEX_S); qp_attr->port_num = hr_qp->port + 1; qp_attr->sq_draining = 0; - qp_attr->max_rd_atomic = roce_get_field(context->qpc_bytes_156, + qp_attr->max_rd_atomic = 1 << roce_get_field(context->qpc_bytes_156, QP_CONTEXT_QPC_BYTES_156_INITIATOR_DEPTH_M, QP_CONTEXT_QPC_BYTES_156_INITIATOR_DEPTH_S); - qp_attr->max_dest_rd_atomic = roce_get_field(context->qpc_bytes_32, + qp_attr->max_dest_rd_atomic = 1 << roce_get_field(context->qpc_bytes_32, QP_CONTEXT_QPC_BYTES_32_RESPONDER_RESOURCES_M, QP_CONTEXT_QPC_BYTES_32_RESPONDER_RESOURCES_S); qp_attr->min_rnr_timer = (u8)(roce_get_field(context->qpc_bytes_24, @@ -3444,8 +3552,9 @@ out: return ret; } -int hns_roce_v1_query_qp(struct ib_qp *ibqp, struct ib_qp_attr *qp_attr, - int qp_attr_mask, struct ib_qp_init_attr *qp_init_attr) +static int hns_roce_v1_query_qp(struct ib_qp *ibqp, struct ib_qp_attr *qp_attr, + int qp_attr_mask, + struct ib_qp_init_attr *qp_init_attr) { struct hns_roce_qp *hr_qp = to_hr_qp(ibqp); @@ -3454,6 +3563,53 @@ int hns_roce_v1_query_qp(struct ib_qp *ibqp, struct ib_qp_attr *qp_attr, hns_roce_v1_q_qp(ibqp, qp_attr, qp_attr_mask, qp_init_attr); } +static void hns_roce_check_sdb_status(struct hns_roce_dev *hr_dev, + u32 *old_send, u32 *old_retry, + u32 *tsp_st, u32 *success_flags) +{ + u32 sdb_retry_cnt; + u32 sdb_send_ptr; + u32 cur_cnt, old_cnt; + u32 send_ptr; + + sdb_send_ptr = roce_read(hr_dev, ROCEE_SDB_SEND_PTR_REG); + sdb_retry_cnt = roce_read(hr_dev, ROCEE_SDB_RETRY_CNT_REG); + cur_cnt = roce_get_field(sdb_send_ptr, + ROCEE_SDB_SEND_PTR_SDB_SEND_PTR_M, + ROCEE_SDB_SEND_PTR_SDB_SEND_PTR_S) + + roce_get_field(sdb_retry_cnt, + ROCEE_SDB_RETRY_CNT_SDB_RETRY_CT_M, + ROCEE_SDB_RETRY_CNT_SDB_RETRY_CT_S); + if (!roce_get_bit(*tsp_st, ROCEE_CNT_CLR_CE_CNT_CLR_CE_S)) { + old_cnt = roce_get_field(*old_send, + ROCEE_SDB_SEND_PTR_SDB_SEND_PTR_M, + ROCEE_SDB_SEND_PTR_SDB_SEND_PTR_S) + + roce_get_field(*old_retry, + ROCEE_SDB_RETRY_CNT_SDB_RETRY_CT_M, + ROCEE_SDB_RETRY_CNT_SDB_RETRY_CT_S); + if (cur_cnt - old_cnt > SDB_ST_CMP_VAL) + *success_flags = 1; + } else { + old_cnt = roce_get_field(*old_send, + ROCEE_SDB_SEND_PTR_SDB_SEND_PTR_M, + ROCEE_SDB_SEND_PTR_SDB_SEND_PTR_S); + if (cur_cnt - old_cnt > SDB_ST_CMP_VAL) { + *success_flags = 1; + } else { + send_ptr = roce_get_field(*old_send, + ROCEE_SDB_SEND_PTR_SDB_SEND_PTR_M, + ROCEE_SDB_SEND_PTR_SDB_SEND_PTR_S) + + roce_get_field(sdb_retry_cnt, + ROCEE_SDB_RETRY_CNT_SDB_RETRY_CT_M, + ROCEE_SDB_RETRY_CNT_SDB_RETRY_CT_S); + roce_set_field(*old_send, + ROCEE_SDB_SEND_PTR_SDB_SEND_PTR_M, + ROCEE_SDB_SEND_PTR_SDB_SEND_PTR_S, + send_ptr); + } + } +} + static int check_qp_db_process_status(struct hns_roce_dev *hr_dev, struct hns_roce_qp *hr_qp, u32 sdb_issue_ptr, @@ -3461,12 +3617,10 @@ static int check_qp_db_process_status(struct hns_roce_dev *hr_dev, u32 *wait_stage) { struct device *dev = &hr_dev->pdev->dev; - u32 sdb_retry_cnt, old_retry; u32 sdb_send_ptr, old_send; u32 success_flags = 0; - u32 cur_cnt, old_cnt; unsigned long end; - u32 send_ptr; + u32 old_retry; u32 inv_cnt; u32 tsp_st; @@ -3524,47 +3678,9 @@ static int check_qp_db_process_status(struct hns_roce_dev *hr_dev, msleep(HNS_ROCE_V1_CHECK_DB_SLEEP_MSECS); - sdb_send_ptr = roce_read(hr_dev, - ROCEE_SDB_SEND_PTR_REG); - sdb_retry_cnt = roce_read(hr_dev, - ROCEE_SDB_RETRY_CNT_REG); - cur_cnt = roce_get_field(sdb_send_ptr, - ROCEE_SDB_SEND_PTR_SDB_SEND_PTR_M, - ROCEE_SDB_SEND_PTR_SDB_SEND_PTR_S) + - roce_get_field(sdb_retry_cnt, - ROCEE_SDB_RETRY_CNT_SDB_RETRY_CT_M, - ROCEE_SDB_RETRY_CNT_SDB_RETRY_CT_S); - if (!roce_get_bit(tsp_st, - ROCEE_CNT_CLR_CE_CNT_CLR_CE_S)) { - old_cnt = roce_get_field(old_send, - ROCEE_SDB_SEND_PTR_SDB_SEND_PTR_M, - ROCEE_SDB_SEND_PTR_SDB_SEND_PTR_S) + - roce_get_field(old_retry, - ROCEE_SDB_RETRY_CNT_SDB_RETRY_CT_M, - ROCEE_SDB_RETRY_CNT_SDB_RETRY_CT_S); - if (cur_cnt - old_cnt > SDB_ST_CMP_VAL) - success_flags = 1; - } else { - old_cnt = roce_get_field(old_send, - ROCEE_SDB_SEND_PTR_SDB_SEND_PTR_M, - ROCEE_SDB_SEND_PTR_SDB_SEND_PTR_S); - if (cur_cnt - old_cnt > - SDB_ST_CMP_VAL) { - success_flags = 1; - } else { - send_ptr = - roce_get_field(old_send, - ROCEE_SDB_SEND_PTR_SDB_SEND_PTR_M, - ROCEE_SDB_SEND_PTR_SDB_SEND_PTR_S) + - roce_get_field(sdb_retry_cnt, - ROCEE_SDB_RETRY_CNT_SDB_RETRY_CT_M, - ROCEE_SDB_RETRY_CNT_SDB_RETRY_CT_S); - roce_set_field(old_send, - ROCEE_SDB_SEND_PTR_SDB_SEND_PTR_M, - ROCEE_SDB_SEND_PTR_SDB_SEND_PTR_S, - send_ptr); - } - } + hns_roce_check_sdb_status(hr_dev, &old_send, + &old_retry, &tsp_st, + &success_flags); } while (!success_flags); } @@ -3664,7 +3780,7 @@ static void hns_roce_v1_destroy_qp_work_fn(struct work_struct *work) qp_work_entry = container_of(work, struct hns_roce_qp_work, work); hr_dev = to_hr_dev(qp_work_entry->ib_dev); dev = &hr_dev->pdev->dev; - priv = (struct hns_roce_v1_priv *)hr_dev->hw->priv; + priv = (struct hns_roce_v1_priv *)hr_dev->priv; hr_qp = qp_work_entry->qp; qpn = hr_qp->qpn; @@ -3781,7 +3897,7 @@ int hns_roce_v1_destroy_qp(struct ib_qp *ibqp) qp_work->sdb_inv_cnt = qp_work_entry.sdb_inv_cnt; qp_work->sche_cnt = qp_work_entry.sche_cnt; - priv = (struct hns_roce_v1_priv *)hr_dev->hw->priv; + priv = (struct hns_roce_v1_priv *)hr_dev->priv; queue_work(priv->des_qp.qp_wq, &qp_work->work); dev_dbg(dev, "Begin destroy QP(0x%lx) work.\n", hr_qp->qpn); } @@ -3789,7 +3905,7 @@ int hns_roce_v1_destroy_qp(struct ib_qp *ibqp) return 0; } -int hns_roce_v1_destroy_cq(struct ib_cq *ibcq) +static int hns_roce_v1_destroy_cq(struct ib_cq *ibcq) { struct hns_roce_dev *hr_dev = to_hr_dev(ibcq->device); struct hns_roce_cq *hr_cq = to_hr_cq(ibcq); @@ -3841,18 +3957,19 @@ int hns_roce_v1_destroy_cq(struct ib_cq *ibcq) return ret; } -struct hns_roce_v1_priv hr_v1_priv; - -struct hns_roce_hw hns_roce_hw_v1 = { +static const struct hns_roce_hw hns_roce_hw_v1 = { .reset = hns_roce_v1_reset, .hw_profile = hns_roce_v1_profile, .hw_init = hns_roce_v1_init, .hw_exit = hns_roce_v1_exit, + .post_mbox = hns_roce_v1_post_mbox, + .chk_mbox = hns_roce_v1_chk_mbox, .set_gid = hns_roce_v1_set_gid, .set_mac = hns_roce_v1_set_mac, .set_mtu = hns_roce_v1_set_mtu, .write_mtpt = hns_roce_v1_write_mtpt, .write_cqc = hns_roce_v1_write_cqc, + .modify_cq = hns_roce_v1_modify_cq, .clear_hem = hns_roce_v1_clear_hem, .modify_qp = hns_roce_v1_modify_qp, .query_qp = hns_roce_v1_query_qp, @@ -3863,5 +3980,258 @@ struct hns_roce_hw hns_roce_hw_v1 = { .poll_cq = hns_roce_v1_poll_cq, .dereg_mr = hns_roce_v1_dereg_mr, .destroy_cq = hns_roce_v1_destroy_cq, - .priv = &hr_v1_priv, }; + +static const struct of_device_id hns_roce_of_match[] = { + { .compatible = "hisilicon,hns-roce-v1", .data = &hns_roce_hw_v1, }, + {}, +}; +MODULE_DEVICE_TABLE(of, hns_roce_of_match); + +static const struct acpi_device_id hns_roce_acpi_match[] = { + { "HISI00D1", (kernel_ulong_t)&hns_roce_hw_v1 }, + {}, +}; +MODULE_DEVICE_TABLE(acpi, hns_roce_acpi_match); + +static int hns_roce_node_match(struct device *dev, void *fwnode) +{ + return dev->fwnode == fwnode; +} + +static struct +platform_device *hns_roce_find_pdev(struct fwnode_handle *fwnode) +{ + struct device *dev; + + /* get the 'device' corresponding to the matching 'fwnode' */ + dev = bus_find_device(&platform_bus_type, NULL, + fwnode, hns_roce_node_match); + /* get the platform device */ + return dev ? to_platform_device(dev) : NULL; +} + +static int hns_roce_get_cfg(struct hns_roce_dev *hr_dev) +{ + struct device *dev = &hr_dev->pdev->dev; + struct platform_device *pdev = NULL; + struct net_device *netdev = NULL; + struct device_node *net_node; + struct resource *res; + int port_cnt = 0; + u8 phy_port; + int ret; + int i; + + /* check if we are compatible with the underlying SoC */ + if (dev_of_node(dev)) { + const struct of_device_id *of_id; + + of_id = of_match_node(hns_roce_of_match, dev->of_node); + if (!of_id) { + dev_err(dev, "device is not compatible!\n"); + return -ENXIO; + } + hr_dev->hw = (const struct hns_roce_hw *)of_id->data; + if (!hr_dev->hw) { + dev_err(dev, "couldn't get H/W specific DT data!\n"); + return -ENXIO; + } + } else if (is_acpi_device_node(dev->fwnode)) { + const struct acpi_device_id *acpi_id; + + acpi_id = acpi_match_device(hns_roce_acpi_match, dev); + if (!acpi_id) { + dev_err(dev, "device is not compatible!\n"); + return -ENXIO; + } + hr_dev->hw = (const struct hns_roce_hw *) acpi_id->driver_data; + if (!hr_dev->hw) { + dev_err(dev, "couldn't get H/W specific ACPI data!\n"); + return -ENXIO; + } + } else { + dev_err(dev, "can't read compatibility data from DT or ACPI\n"); + return -ENXIO; + } + + /* get the mapped register base address */ + res = platform_get_resource(hr_dev->pdev, IORESOURCE_MEM, 0); + if (!res) { + dev_err(dev, "memory resource not found!\n"); + return -EINVAL; + } + hr_dev->reg_base = devm_ioremap_resource(dev, res); + if (IS_ERR(hr_dev->reg_base)) + return PTR_ERR(hr_dev->reg_base); + + /* read the node_guid of IB device from the DT or ACPI */ + ret = device_property_read_u8_array(dev, "node-guid", + (u8 *)&hr_dev->ib_dev.node_guid, + GUID_LEN); + if (ret) { + dev_err(dev, "couldn't get node_guid from DT or ACPI!\n"); + return ret; + } + + /* get the RoCE associated ethernet ports or netdevices */ + for (i = 0; i < HNS_ROCE_MAX_PORTS; i++) { + if (dev_of_node(dev)) { + net_node = of_parse_phandle(dev->of_node, "eth-handle", + i); + if (!net_node) + continue; + pdev = of_find_device_by_node(net_node); + } else if (is_acpi_device_node(dev->fwnode)) { + struct acpi_reference_args args; + struct fwnode_handle *fwnode; + + ret = acpi_node_get_property_reference(dev->fwnode, + "eth-handle", + i, &args); + if (ret) + continue; + fwnode = acpi_fwnode_handle(args.adev); + pdev = hns_roce_find_pdev(fwnode); + } else { + dev_err(dev, "cannot read data from DT or ACPI\n"); + return -ENXIO; + } + + if (pdev) { + netdev = platform_get_drvdata(pdev); + phy_port = (u8)i; + if (netdev) { + hr_dev->iboe.netdevs[port_cnt] = netdev; + hr_dev->iboe.phy_port[port_cnt] = phy_port; + } else { + dev_err(dev, "no netdev found with pdev %s\n", + pdev->name); + return -ENODEV; + } + port_cnt++; + } + } + + if (port_cnt == 0) { + dev_err(dev, "unable to get eth-handle for available ports!\n"); + return -EINVAL; + } + + hr_dev->caps.num_ports = port_cnt; + + /* cmd issue mode: 0 is poll, 1 is event */ + hr_dev->cmd_mod = 1; + hr_dev->loop_idc = 0; + hr_dev->sdb_offset = ROCEE_DB_SQ_L_0_REG; + hr_dev->odb_offset = ROCEE_DB_OTHERS_L_0_REG; + + /* read the interrupt names from the DT or ACPI */ + ret = device_property_read_string_array(dev, "interrupt-names", + hr_dev->irq_names, + HNS_ROCE_MAX_IRQ_NUM); + if (ret < 0) { + dev_err(dev, "couldn't get interrupt names from DT or ACPI!\n"); + return ret; + } + + /* fetch the interrupt numbers */ + for (i = 0; i < HNS_ROCE_MAX_IRQ_NUM; i++) { + hr_dev->irq[i] = platform_get_irq(hr_dev->pdev, i); + if (hr_dev->irq[i] <= 0) { + dev_err(dev, "platform get of irq[=%d] failed!\n", i); + return -EINVAL; + } + } + + return 0; +} + +/** + * hns_roce_probe - RoCE driver entrance + * @pdev: pointer to platform device + * Return : int + * + */ +static int hns_roce_probe(struct platform_device *pdev) +{ + int ret; + struct hns_roce_dev *hr_dev; + struct device *dev = &pdev->dev; + + hr_dev = (struct hns_roce_dev *)ib_alloc_device(sizeof(*hr_dev)); + if (!hr_dev) + return -ENOMEM; + + hr_dev->priv = kzalloc(sizeof(struct hns_roce_v1_priv), GFP_KERNEL); + if (!hr_dev->priv) { + ret = -ENOMEM; + goto error_failed_kzalloc; + } + + hr_dev->pdev = pdev; + hr_dev->dev = dev; + platform_set_drvdata(pdev, hr_dev); + + if (dma_set_mask_and_coherent(dev, DMA_BIT_MASK(64ULL)) && + dma_set_mask_and_coherent(dev, DMA_BIT_MASK(32ULL))) { + dev_err(dev, "Not usable DMA addressing mode\n"); + ret = -EIO; + goto error_failed_get_cfg; + } + + ret = hns_roce_get_cfg(hr_dev); + if (ret) { + dev_err(dev, "Get Configuration failed!\n"); + goto error_failed_get_cfg; + } + + ret = hns_roce_init(hr_dev); + if (ret) { + dev_err(dev, "RoCE engine init failed!\n"); + goto error_failed_get_cfg; + } + + return 0; + +error_failed_get_cfg: + kfree(hr_dev->priv); + +error_failed_kzalloc: + ib_dealloc_device(&hr_dev->ib_dev); + + return ret; +} + +/** + * hns_roce_remove - remove RoCE device + * @pdev: pointer to platform device + */ +static int hns_roce_remove(struct platform_device *pdev) +{ + struct hns_roce_dev *hr_dev = platform_get_drvdata(pdev); + + hns_roce_exit(hr_dev); + kfree(hr_dev->priv); + ib_dealloc_device(&hr_dev->ib_dev); + + return 0; +} + +static struct platform_driver hns_roce_driver = { + .probe = hns_roce_probe, + .remove = hns_roce_remove, + .driver = { + .name = DRV_NAME, + .of_match_table = hns_roce_of_match, + .acpi_match_table = ACPI_PTR(hns_roce_acpi_match), + }, +}; + +module_platform_driver(hns_roce_driver); + +MODULE_LICENSE("Dual BSD/GPL"); +MODULE_AUTHOR("Wei Hu <xavier.huwei@huawei.com>"); +MODULE_AUTHOR("Nenglong Zhao <zhaonenglong@hisilicon.com>"); +MODULE_AUTHOR("Lijun Ou <oulijun@huawei.com>"); +MODULE_DESCRIPTION("Hisilicon Hip06 Family RoCE Driver"); diff --git a/drivers/infiniband/hw/hns/hns_roce_hw_v1.h b/drivers/infiniband/hw/hns/hns_roce_hw_v1.h index b213b5e6fef1..21a07ef0afc9 100644 --- a/drivers/infiniband/hw/hns/hns_roce_hw_v1.h +++ b/drivers/infiniband/hw/hns/hns_roce_hw_v1.h @@ -72,6 +72,8 @@ #define HNS_ROCE_V1_CQE_ENTRY_SIZE 32 #define HNS_ROCE_V1_PAGE_SIZE_SUPPORT 0xFFFFF000 +#define HNS_ROCE_V1_TABLE_CHUNK_SIZE (1 << 17) + #define HNS_ROCE_V1_EXT_RAQ_WF 8 #define HNS_ROCE_V1_RAQ_ENTRY 64 #define HNS_ROCE_V1_RAQ_DEPTH 32768 @@ -948,6 +950,11 @@ struct hns_roce_qp_context { #define QP_CONTEXT_QPC_BYTES_188_TX_RETRY_CUR_INDEX_M \ (((1UL << 15) - 1) << QP_CONTEXT_QPC_BYTES_188_TX_RETRY_CUR_INDEX_S) +#define STATUS_MASK 0xff +#define GO_BIT_TIMEOUT_MSECS 10000 +#define HCR_STATUS_OFFSET 0x18 +#define HCR_GO_BIT 15 + struct hns_roce_rq_db { u32 u32_4; u32 u32_8; diff --git a/drivers/infiniband/hw/hns/hns_roce_hw_v2.c b/drivers/infiniband/hw/hns/hns_roce_hw_v2.c new file mode 100644 index 000000000000..b0736c32e5d1 --- /dev/null +++ b/drivers/infiniband/hw/hns/hns_roce_hw_v2.c @@ -0,0 +1,3176 @@ +/* + * Copyright (c) 2016-2017 Hisilicon Limited. + * + * This software is available to you under a choice of one of two + * licenses. You may choose to be licensed under the terms of the GNU + * General Public License (GPL) Version 2, available from the file + * COPYING in the main directory of this source tree, or the + * OpenIB.org BSD license below: + * + * Redistribution and use in source and binary forms, with or + * without modification, are permitted provided that the following + * conditions are met: + * + * - Redistributions of source code must retain the above + * copyright notice, this list of conditions and the following + * disclaimer. + * + * - Redistributions in binary form must reproduce the above + * copyright notice, this list of conditions and the following + * disclaimer in the documentation and/or other materials + * provided with the distribution. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND + * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS + * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN + * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN + * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE + * SOFTWARE. + */ + +#include <linux/acpi.h> +#include <linux/etherdevice.h> +#include <linux/interrupt.h> +#include <linux/kernel.h> +#include <rdma/ib_umem.h> + +#include "hnae3.h" +#include "hns_roce_common.h" +#include "hns_roce_device.h" +#include "hns_roce_cmd.h" +#include "hns_roce_hem.h" +#include "hns_roce_hw_v2.h" + +static void set_data_seg_v2(struct hns_roce_v2_wqe_data_seg *dseg, + struct ib_sge *sg) +{ + dseg->lkey = cpu_to_le32(sg->lkey); + dseg->addr = cpu_to_le64(sg->addr); + dseg->len = cpu_to_le32(sg->length); +} + +static int hns_roce_v2_post_send(struct ib_qp *ibqp, struct ib_send_wr *wr, + struct ib_send_wr **bad_wr) +{ + struct hns_roce_dev *hr_dev = to_hr_dev(ibqp->device); + struct hns_roce_v2_rc_send_wqe *rc_sq_wqe; + struct hns_roce_qp *qp = to_hr_qp(ibqp); + struct hns_roce_v2_wqe_data_seg *dseg; + struct device *dev = hr_dev->dev; + struct hns_roce_v2_db sq_db; + unsigned int sge_ind = 0; + unsigned int wqe_sz = 0; + unsigned long flags; + unsigned int ind; + void *wqe = NULL; + int ret = 0; + int nreq; + int i; + + if (unlikely(ibqp->qp_type != IB_QPT_RC)) { + dev_err(dev, "Not supported QP(0x%x)type!\n", ibqp->qp_type); + *bad_wr = NULL; + return -EOPNOTSUPP; + } + + if (unlikely(qp->state != IB_QPS_RTS && qp->state != IB_QPS_SQD)) { + dev_err(dev, "Post WQE fail, QP state %d err!\n", qp->state); + *bad_wr = wr; + return -EINVAL; + } + + spin_lock_irqsave(&qp->sq.lock, flags); + ind = qp->sq_next_wqe; + sge_ind = qp->next_sge; + + for (nreq = 0; wr; ++nreq, wr = wr->next) { + if (hns_roce_wq_overflow(&qp->sq, nreq, qp->ibqp.send_cq)) { + ret = -ENOMEM; + *bad_wr = wr; + goto out; + } + + if (unlikely(wr->num_sge > qp->sq.max_gs)) { + dev_err(dev, "num_sge=%d > qp->sq.max_gs=%d\n", + wr->num_sge, qp->sq.max_gs); + ret = -EINVAL; + *bad_wr = wr; + goto out; + } + + wqe = get_send_wqe(qp, ind & (qp->sq.wqe_cnt - 1)); + qp->sq.wrid[(qp->sq.head + nreq) & (qp->sq.wqe_cnt - 1)] = + wr->wr_id; + + + rc_sq_wqe = wqe; + memset(rc_sq_wqe, 0, sizeof(*rc_sq_wqe)); + for (i = 0; i < wr->num_sge; i++) + rc_sq_wqe->msg_len += wr->sg_list[i].length; + + rc_sq_wqe->inv_key_immtdata = send_ieth(wr); + + switch (wr->opcode) { + case IB_WR_RDMA_READ: + roce_set_field(rc_sq_wqe->byte_4, + V2_RC_SEND_WQE_BYTE_4_OPCODE_M, + V2_RC_SEND_WQE_BYTE_4_OPCODE_S, + HNS_ROCE_V2_WQE_OP_RDMA_READ); + rc_sq_wqe->rkey = cpu_to_le32(rdma_wr(wr)->rkey); + rc_sq_wqe->va = cpu_to_le64(rdma_wr(wr)->remote_addr); + break; + case IB_WR_RDMA_WRITE: + roce_set_field(rc_sq_wqe->byte_4, + V2_RC_SEND_WQE_BYTE_4_OPCODE_M, + V2_RC_SEND_WQE_BYTE_4_OPCODE_S, + HNS_ROCE_V2_WQE_OP_RDMA_WRITE); + rc_sq_wqe->rkey = cpu_to_le32(rdma_wr(wr)->rkey); + rc_sq_wqe->va = cpu_to_le64(rdma_wr(wr)->remote_addr); + break; + case IB_WR_RDMA_WRITE_WITH_IMM: + roce_set_field(rc_sq_wqe->byte_4, + V2_RC_SEND_WQE_BYTE_4_OPCODE_M, + V2_RC_SEND_WQE_BYTE_4_OPCODE_S, + HNS_ROCE_V2_WQE_OP_RDMA_WRITE_WITH_IMM); + rc_sq_wqe->rkey = cpu_to_le32(rdma_wr(wr)->rkey); + rc_sq_wqe->va = cpu_to_le64(rdma_wr(wr)->remote_addr); + break; + case IB_WR_SEND: + roce_set_field(rc_sq_wqe->byte_4, + V2_RC_SEND_WQE_BYTE_4_OPCODE_M, + V2_RC_SEND_WQE_BYTE_4_OPCODE_S, + HNS_ROCE_V2_WQE_OP_SEND); + break; + case IB_WR_SEND_WITH_INV: + roce_set_field(rc_sq_wqe->byte_4, + V2_RC_SEND_WQE_BYTE_4_OPCODE_M, + V2_RC_SEND_WQE_BYTE_4_OPCODE_S, + HNS_ROCE_V2_WQE_OP_SEND_WITH_INV); + break; + case IB_WR_SEND_WITH_IMM: + roce_set_field(rc_sq_wqe->byte_4, + V2_RC_SEND_WQE_BYTE_4_OPCODE_M, + V2_RC_SEND_WQE_BYTE_4_OPCODE_S, + HNS_ROCE_V2_WQE_OP_SEND_WITH_IMM); + break; + case IB_WR_LOCAL_INV: + roce_set_field(rc_sq_wqe->byte_4, + V2_RC_SEND_WQE_BYTE_4_OPCODE_M, + V2_RC_SEND_WQE_BYTE_4_OPCODE_S, + HNS_ROCE_V2_WQE_OP_LOCAL_INV); + break; + case IB_WR_ATOMIC_CMP_AND_SWP: + roce_set_field(rc_sq_wqe->byte_4, + V2_RC_SEND_WQE_BYTE_4_OPCODE_M, + V2_RC_SEND_WQE_BYTE_4_OPCODE_S, + HNS_ROCE_V2_WQE_OP_ATOM_CMP_AND_SWAP); + break; + case IB_WR_ATOMIC_FETCH_AND_ADD: + roce_set_field(rc_sq_wqe->byte_4, + V2_RC_SEND_WQE_BYTE_4_OPCODE_M, + V2_RC_SEND_WQE_BYTE_4_OPCODE_S, + HNS_ROCE_V2_WQE_OP_ATOM_FETCH_AND_ADD); + break; + case IB_WR_MASKED_ATOMIC_CMP_AND_SWP: + roce_set_field(rc_sq_wqe->byte_4, + V2_RC_SEND_WQE_BYTE_4_OPCODE_M, + V2_RC_SEND_WQE_BYTE_4_OPCODE_S, + HNS_ROCE_V2_WQE_OP_ATOM_MSK_CMP_AND_SWAP); + break; + case IB_WR_MASKED_ATOMIC_FETCH_AND_ADD: + roce_set_field(rc_sq_wqe->byte_4, + V2_RC_SEND_WQE_BYTE_4_OPCODE_M, + V2_RC_SEND_WQE_BYTE_4_OPCODE_S, + HNS_ROCE_V2_WQE_OP_ATOM_MSK_FETCH_AND_ADD); + break; + default: + roce_set_field(rc_sq_wqe->byte_4, + V2_RC_SEND_WQE_BYTE_4_OPCODE_M, + V2_RC_SEND_WQE_BYTE_4_OPCODE_S, + HNS_ROCE_V2_WQE_OP_MASK); + break; + } + + roce_set_bit(rc_sq_wqe->byte_4, V2_RC_SEND_WQE_BYTE_4_CQE_S, 1); + + wqe += sizeof(struct hns_roce_v2_rc_send_wqe); + dseg = wqe; + if (wr->send_flags & IB_SEND_INLINE && wr->num_sge) { + if (rc_sq_wqe->msg_len > + hr_dev->caps.max_sq_inline) { + ret = -EINVAL; + *bad_wr = wr; + dev_err(dev, "inline len(1-%d)=%d, illegal", + rc_sq_wqe->msg_len, + hr_dev->caps.max_sq_inline); + goto out; + } + + for (i = 0; i < wr->num_sge; i++) { + memcpy(wqe, ((void *)wr->sg_list[i].addr), + wr->sg_list[i].length); + wqe += wr->sg_list[i].length; + wqe_sz += wr->sg_list[i].length; + } + + roce_set_bit(rc_sq_wqe->byte_4, + V2_RC_SEND_WQE_BYTE_4_INLINE_S, 1); + } else { + if (wr->num_sge <= 2) { + for (i = 0; i < wr->num_sge; i++) + set_data_seg_v2(dseg + i, + wr->sg_list + i); + } else { + roce_set_field(rc_sq_wqe->byte_20, + V2_RC_SEND_WQE_BYTE_20_MSG_START_SGE_IDX_M, + V2_RC_SEND_WQE_BYTE_20_MSG_START_SGE_IDX_S, + sge_ind & (qp->sge.sge_cnt - 1)); + + for (i = 0; i < 2; i++) + set_data_seg_v2(dseg + i, + wr->sg_list + i); + + dseg = get_send_extend_sge(qp, + sge_ind & (qp->sge.sge_cnt - 1)); + + for (i = 0; i < wr->num_sge - 2; i++) { + set_data_seg_v2(dseg + i, + wr->sg_list + 2 + i); + sge_ind++; + } + } + + roce_set_field(rc_sq_wqe->byte_16, + V2_RC_SEND_WQE_BYTE_16_SGE_NUM_M, + V2_RC_SEND_WQE_BYTE_16_SGE_NUM_S, + wr->num_sge); + wqe_sz += wr->num_sge * + sizeof(struct hns_roce_v2_wqe_data_seg); + } + ind++; + } + +out: + if (likely(nreq)) { + qp->sq.head += nreq; + /* Memory barrier */ + wmb(); + + sq_db.byte_4 = 0; + sq_db.parameter = 0; + + roce_set_field(sq_db.byte_4, V2_DB_BYTE_4_TAG_M, + V2_DB_BYTE_4_TAG_S, qp->doorbell_qpn); + roce_set_field(sq_db.byte_4, V2_DB_BYTE_4_CMD_M, + V2_DB_BYTE_4_CMD_S, HNS_ROCE_V2_SQ_DB); + roce_set_field(sq_db.parameter, V2_DB_PARAMETER_CONS_IDX_M, + V2_DB_PARAMETER_CONS_IDX_S, + qp->sq.head & ((qp->sq.wqe_cnt << 1) - 1)); + roce_set_field(sq_db.parameter, V2_DB_PARAMETER_SL_M, + V2_DB_PARAMETER_SL_S, qp->sl); + + hns_roce_write64_k((__be32 *)&sq_db, qp->sq.db_reg_l); + + qp->sq_next_wqe = ind; + qp->next_sge = sge_ind; + } + + spin_unlock_irqrestore(&qp->sq.lock, flags); + + return ret; +} + +static int hns_roce_v2_post_recv(struct ib_qp *ibqp, struct ib_recv_wr *wr, + struct ib_recv_wr **bad_wr) +{ + struct hns_roce_dev *hr_dev = to_hr_dev(ibqp->device); + struct hns_roce_qp *hr_qp = to_hr_qp(ibqp); + struct hns_roce_v2_wqe_data_seg *dseg; + struct device *dev = hr_dev->dev; + struct hns_roce_v2_db rq_db; + unsigned long flags; + void *wqe = NULL; + int ret = 0; + int nreq; + int ind; + int i; + + spin_lock_irqsave(&hr_qp->rq.lock, flags); + ind = hr_qp->rq.head & (hr_qp->rq.wqe_cnt - 1); + + if (hr_qp->state == IB_QPS_RESET || hr_qp->state == IB_QPS_ERR) { + spin_unlock_irqrestore(&hr_qp->rq.lock, flags); + *bad_wr = wr; + return -EINVAL; + } + + for (nreq = 0; wr; ++nreq, wr = wr->next) { + if (hns_roce_wq_overflow(&hr_qp->rq, nreq, + hr_qp->ibqp.recv_cq)) { + ret = -ENOMEM; + *bad_wr = wr; + goto out; + } + + if (unlikely(wr->num_sge > hr_qp->rq.max_gs)) { + dev_err(dev, "rq:num_sge=%d > qp->sq.max_gs=%d\n", + wr->num_sge, hr_qp->rq.max_gs); + ret = -EINVAL; + *bad_wr = wr; + goto out; + } + + wqe = get_recv_wqe(hr_qp, ind); + dseg = (struct hns_roce_v2_wqe_data_seg *)wqe; + for (i = 0; i < wr->num_sge; i++) { + if (!wr->sg_list[i].length) + continue; + set_data_seg_v2(dseg, wr->sg_list + i); + dseg++; + } + + if (i < hr_qp->rq.max_gs) { + dseg[i].lkey = cpu_to_be32(HNS_ROCE_INVALID_LKEY); + dseg[i].addr = 0; + } + + hr_qp->rq.wrid[ind] = wr->wr_id; + + ind = (ind + 1) & (hr_qp->rq.wqe_cnt - 1); + } + +out: + if (likely(nreq)) { + hr_qp->rq.head += nreq; + /* Memory barrier */ + wmb(); + + rq_db.byte_4 = 0; + rq_db.parameter = 0; + + roce_set_field(rq_db.byte_4, V2_DB_BYTE_4_TAG_M, + V2_DB_BYTE_4_TAG_S, hr_qp->qpn); + roce_set_field(rq_db.byte_4, V2_DB_BYTE_4_CMD_M, + V2_DB_BYTE_4_CMD_S, HNS_ROCE_V2_RQ_DB); + roce_set_field(rq_db.parameter, V2_DB_PARAMETER_CONS_IDX_M, + V2_DB_PARAMETER_CONS_IDX_S, hr_qp->rq.head); + + hns_roce_write64_k((__be32 *)&rq_db, hr_qp->rq.db_reg_l); + } + spin_unlock_irqrestore(&hr_qp->rq.lock, flags); + + return ret; +} + +static int hns_roce_cmq_space(struct hns_roce_v2_cmq_ring *ring) +{ + int ntu = ring->next_to_use; + int ntc = ring->next_to_clean; + int used = (ntu - ntc + ring->desc_num) % ring->desc_num; + + return ring->desc_num - used - 1; +} + +static int hns_roce_alloc_cmq_desc(struct hns_roce_dev *hr_dev, + struct hns_roce_v2_cmq_ring *ring) +{ + int size = ring->desc_num * sizeof(struct hns_roce_cmq_desc); + + ring->desc = kzalloc(size, GFP_KERNEL); + if (!ring->desc) + return -ENOMEM; + + ring->desc_dma_addr = dma_map_single(hr_dev->dev, ring->desc, size, + DMA_BIDIRECTIONAL); + if (dma_mapping_error(hr_dev->dev, ring->desc_dma_addr)) { + ring->desc_dma_addr = 0; + kfree(ring->desc); + ring->desc = NULL; + return -ENOMEM; + } + + return 0; +} + +static void hns_roce_free_cmq_desc(struct hns_roce_dev *hr_dev, + struct hns_roce_v2_cmq_ring *ring) +{ + dma_unmap_single(hr_dev->dev, ring->desc_dma_addr, + ring->desc_num * sizeof(struct hns_roce_cmq_desc), + DMA_BIDIRECTIONAL); + kfree(ring->desc); +} + +static int hns_roce_init_cmq_ring(struct hns_roce_dev *hr_dev, bool ring_type) +{ + struct hns_roce_v2_priv *priv = (struct hns_roce_v2_priv *)hr_dev->priv; + struct hns_roce_v2_cmq_ring *ring = (ring_type == TYPE_CSQ) ? + &priv->cmq.csq : &priv->cmq.crq; + + ring->flag = ring_type; + ring->next_to_clean = 0; + ring->next_to_use = 0; + + return hns_roce_alloc_cmq_desc(hr_dev, ring); +} + +static void hns_roce_cmq_init_regs(struct hns_roce_dev *hr_dev, bool ring_type) +{ + struct hns_roce_v2_priv *priv = (struct hns_roce_v2_priv *)hr_dev->priv; + struct hns_roce_v2_cmq_ring *ring = (ring_type == TYPE_CSQ) ? + &priv->cmq.csq : &priv->cmq.crq; + dma_addr_t dma = ring->desc_dma_addr; + + if (ring_type == TYPE_CSQ) { + roce_write(hr_dev, ROCEE_TX_CMQ_BASEADDR_L_REG, (u32)dma); + roce_write(hr_dev, ROCEE_TX_CMQ_BASEADDR_H_REG, + upper_32_bits(dma)); + roce_write(hr_dev, ROCEE_TX_CMQ_DEPTH_REG, + (ring->desc_num >> HNS_ROCE_CMQ_DESC_NUM_S) | + HNS_ROCE_CMQ_ENABLE); + roce_write(hr_dev, ROCEE_TX_CMQ_HEAD_REG, 0); + roce_write(hr_dev, ROCEE_TX_CMQ_TAIL_REG, 0); + } else { + roce_write(hr_dev, ROCEE_RX_CMQ_BASEADDR_L_REG, (u32)dma); + roce_write(hr_dev, ROCEE_RX_CMQ_BASEADDR_H_REG, + upper_32_bits(dma)); + roce_write(hr_dev, ROCEE_RX_CMQ_DEPTH_REG, + (ring->desc_num >> HNS_ROCE_CMQ_DESC_NUM_S) | + HNS_ROCE_CMQ_ENABLE); + roce_write(hr_dev, ROCEE_RX_CMQ_HEAD_REG, 0); + roce_write(hr_dev, ROCEE_RX_CMQ_TAIL_REG, 0); + } +} + +static int hns_roce_v2_cmq_init(struct hns_roce_dev *hr_dev) +{ + struct hns_roce_v2_priv *priv = (struct hns_roce_v2_priv *)hr_dev->priv; + int ret; + + /* Setup the queue entries for command queue */ + priv->cmq.csq.desc_num = 1024; + priv->cmq.crq.desc_num = 1024; + + /* Setup the lock for command queue */ + spin_lock_init(&priv->cmq.csq.lock); + spin_lock_init(&priv->cmq.crq.lock); + + /* Setup Tx write back timeout */ + priv->cmq.tx_timeout = HNS_ROCE_CMQ_TX_TIMEOUT; + + /* Init CSQ */ + ret = hns_roce_init_cmq_ring(hr_dev, TYPE_CSQ); + if (ret) { + dev_err(hr_dev->dev, "Init CSQ error, ret = %d.\n", ret); + return ret; + } + + /* Init CRQ */ + ret = hns_roce_init_cmq_ring(hr_dev, TYPE_CRQ); + if (ret) { + dev_err(hr_dev->dev, "Init CRQ error, ret = %d.\n", ret); + goto err_crq; + } + + /* Init CSQ REG */ + hns_roce_cmq_init_regs(hr_dev, TYPE_CSQ); + + /* Init CRQ REG */ + hns_roce_cmq_init_regs(hr_dev, TYPE_CRQ); + + return 0; + +err_crq: + hns_roce_free_cmq_desc(hr_dev, &priv->cmq.csq); + + return ret; +} + +static void hns_roce_v2_cmq_exit(struct hns_roce_dev *hr_dev) +{ + struct hns_roce_v2_priv *priv = (struct hns_roce_v2_priv *)hr_dev->priv; + + hns_roce_free_cmq_desc(hr_dev, &priv->cmq.csq); + hns_roce_free_cmq_desc(hr_dev, &priv->cmq.crq); +} + +static void hns_roce_cmq_setup_basic_desc(struct hns_roce_cmq_desc *desc, + enum hns_roce_opcode_type opcode, + bool is_read) +{ + memset((void *)desc, 0, sizeof(struct hns_roce_cmq_desc)); + desc->opcode = cpu_to_le16(opcode); + desc->flag = + cpu_to_le16(HNS_ROCE_CMD_FLAG_NO_INTR | HNS_ROCE_CMD_FLAG_IN); + if (is_read) + desc->flag |= cpu_to_le16(HNS_ROCE_CMD_FLAG_WR); + else + desc->flag &= cpu_to_le16(~HNS_ROCE_CMD_FLAG_WR); +} + +static int hns_roce_cmq_csq_done(struct hns_roce_dev *hr_dev) +{ + struct hns_roce_v2_priv *priv = (struct hns_roce_v2_priv *)hr_dev->priv; + u32 head = roce_read(hr_dev, ROCEE_TX_CMQ_HEAD_REG); + + return head == priv->cmq.csq.next_to_use; +} + +static int hns_roce_cmq_csq_clean(struct hns_roce_dev *hr_dev) +{ + struct hns_roce_v2_priv *priv = (struct hns_roce_v2_priv *)hr_dev->priv; + struct hns_roce_v2_cmq_ring *csq = &priv->cmq.csq; + struct hns_roce_cmq_desc *desc; + u16 ntc = csq->next_to_clean; + u32 head; + int clean = 0; + + desc = &csq->desc[ntc]; + head = roce_read(hr_dev, ROCEE_TX_CMQ_HEAD_REG); + while (head != ntc) { + memset(desc, 0, sizeof(*desc)); + ntc++; + if (ntc == csq->desc_num) + ntc = 0; + desc = &csq->desc[ntc]; + clean++; + } + csq->next_to_clean = ntc; + + return clean; +} + +static int hns_roce_cmq_send(struct hns_roce_dev *hr_dev, + struct hns_roce_cmq_desc *desc, int num) +{ + struct hns_roce_v2_priv *priv = (struct hns_roce_v2_priv *)hr_dev->priv; + struct hns_roce_v2_cmq_ring *csq = &priv->cmq.csq; + struct hns_roce_cmq_desc *desc_to_use; + bool complete = false; + u32 timeout = 0; + int handle = 0; + u16 desc_ret; + int ret = 0; + int ntc; + + spin_lock_bh(&csq->lock); + + if (num > hns_roce_cmq_space(csq)) { + spin_unlock_bh(&csq->lock); + return -EBUSY; + } + + /* + * Record the location of desc in the cmq for this time + * which will be use for hardware to write back + */ + ntc = csq->next_to_use; + + while (handle < num) { + desc_to_use = &csq->desc[csq->next_to_use]; + *desc_to_use = desc[handle]; + dev_dbg(hr_dev->dev, "set cmq desc:\n"); + csq->next_to_use++; + if (csq->next_to_use == csq->desc_num) + csq->next_to_use = 0; + handle++; + } + + /* Write to hardware */ + roce_write(hr_dev, ROCEE_TX_CMQ_TAIL_REG, csq->next_to_use); + + /* + * If the command is sync, wait for the firmware to write back, + * if multi descriptors to be sent, use the first one to check + */ + if ((desc->flag) & HNS_ROCE_CMD_FLAG_NO_INTR) { + do { + if (hns_roce_cmq_csq_done(hr_dev)) + break; + udelay(1); + timeout++; + } while (timeout < priv->cmq.tx_timeout); + } + + if (hns_roce_cmq_csq_done(hr_dev)) { + complete = true; + handle = 0; + while (handle < num) { + /* get the result of hardware write back */ + desc_to_use = &csq->desc[ntc]; + desc[handle] = *desc_to_use; + dev_dbg(hr_dev->dev, "Get cmq desc:\n"); + desc_ret = desc[handle].retval; + if (desc_ret == CMD_EXEC_SUCCESS) + ret = 0; + else + ret = -EIO; + priv->cmq.last_status = desc_ret; + ntc++; + handle++; + if (ntc == csq->desc_num) + ntc = 0; + } + } + + if (!complete) + ret = -EAGAIN; + + /* clean the command send queue */ + handle = hns_roce_cmq_csq_clean(hr_dev); + if (handle != num) + dev_warn(hr_dev->dev, "Cleaned %d, need to clean %d\n", + handle, num); + + spin_unlock_bh(&csq->lock); + + return ret; +} + +static int hns_roce_cmq_query_hw_info(struct hns_roce_dev *hr_dev) +{ + struct hns_roce_query_version *resp; + struct hns_roce_cmq_desc desc; + int ret; + + hns_roce_cmq_setup_basic_desc(&desc, HNS_ROCE_OPC_QUERY_HW_VER, true); + ret = hns_roce_cmq_send(hr_dev, &desc, 1); + if (ret) + return ret; + + resp = (struct hns_roce_query_version *)desc.data; + hr_dev->hw_rev = le32_to_cpu(resp->rocee_hw_version); + hr_dev->vendor_id = le32_to_cpu(resp->rocee_vendor_id); + + return 0; +} + +static int hns_roce_config_global_param(struct hns_roce_dev *hr_dev) +{ + struct hns_roce_cfg_global_param *req; + struct hns_roce_cmq_desc desc; + + hns_roce_cmq_setup_basic_desc(&desc, HNS_ROCE_OPC_CFG_GLOBAL_PARAM, + false); + + req = (struct hns_roce_cfg_global_param *)desc.data; + memset(req, 0, sizeof(*req)); + roce_set_field(req->time_cfg_udp_port, + CFG_GLOBAL_PARAM_DATA_0_ROCEE_TIME_1US_CFG_M, + CFG_GLOBAL_PARAM_DATA_0_ROCEE_TIME_1US_CFG_S, 0x3e8); + roce_set_field(req->time_cfg_udp_port, + CFG_GLOBAL_PARAM_DATA_0_ROCEE_UDP_PORT_M, + CFG_GLOBAL_PARAM_DATA_0_ROCEE_UDP_PORT_S, 0x12b7); + + return hns_roce_cmq_send(hr_dev, &desc, 1); +} + +static int hns_roce_query_pf_resource(struct hns_roce_dev *hr_dev) +{ + struct hns_roce_cmq_desc desc[2]; + struct hns_roce_pf_res *res; + int ret; + int i; + + for (i = 0; i < 2; i++) { + hns_roce_cmq_setup_basic_desc(&desc[i], + HNS_ROCE_OPC_QUERY_PF_RES, true); + + if (i == 0) + desc[i].flag |= cpu_to_le16(HNS_ROCE_CMD_FLAG_NEXT); + else + desc[i].flag &= ~cpu_to_le16(HNS_ROCE_CMD_FLAG_NEXT); + } + + ret = hns_roce_cmq_send(hr_dev, desc, 2); + if (ret) + return ret; + + res = (struct hns_roce_pf_res *)desc[0].data; + + hr_dev->caps.qpc_bt_num = roce_get_field(res->qpc_bt_idx_num, + PF_RES_DATA_1_PF_QPC_BT_NUM_M, + PF_RES_DATA_1_PF_QPC_BT_NUM_S); + hr_dev->caps.srqc_bt_num = roce_get_field(res->srqc_bt_idx_num, + PF_RES_DATA_2_PF_SRQC_BT_NUM_M, + PF_RES_DATA_2_PF_SRQC_BT_NUM_S); + hr_dev->caps.cqc_bt_num = roce_get_field(res->cqc_bt_idx_num, + PF_RES_DATA_3_PF_CQC_BT_NUM_M, + PF_RES_DATA_3_PF_CQC_BT_NUM_S); + hr_dev->caps.mpt_bt_num = roce_get_field(res->mpt_bt_idx_num, + PF_RES_DATA_4_PF_MPT_BT_NUM_M, + PF_RES_DATA_4_PF_MPT_BT_NUM_S); + + return 0; +} + +static int hns_roce_alloc_vf_resource(struct hns_roce_dev *hr_dev) +{ + struct hns_roce_cmq_desc desc[2]; + struct hns_roce_vf_res_a *req_a; + struct hns_roce_vf_res_b *req_b; + int i; + + req_a = (struct hns_roce_vf_res_a *)desc[0].data; + req_b = (struct hns_roce_vf_res_b *)desc[1].data; + memset(req_a, 0, sizeof(*req_a)); + memset(req_b, 0, sizeof(*req_b)); + for (i = 0; i < 2; i++) { + hns_roce_cmq_setup_basic_desc(&desc[i], + HNS_ROCE_OPC_ALLOC_VF_RES, false); + + if (i == 0) + desc[i].flag |= cpu_to_le16(HNS_ROCE_CMD_FLAG_NEXT); + else + desc[i].flag &= ~cpu_to_le16(HNS_ROCE_CMD_FLAG_NEXT); + + if (i == 0) { + roce_set_field(req_a->vf_qpc_bt_idx_num, + VF_RES_A_DATA_1_VF_QPC_BT_IDX_M, + VF_RES_A_DATA_1_VF_QPC_BT_IDX_S, 0); + roce_set_field(req_a->vf_qpc_bt_idx_num, + VF_RES_A_DATA_1_VF_QPC_BT_NUM_M, + VF_RES_A_DATA_1_VF_QPC_BT_NUM_S, + HNS_ROCE_VF_QPC_BT_NUM); + + roce_set_field(req_a->vf_srqc_bt_idx_num, + VF_RES_A_DATA_2_VF_SRQC_BT_IDX_M, + VF_RES_A_DATA_2_VF_SRQC_BT_IDX_S, 0); + roce_set_field(req_a->vf_srqc_bt_idx_num, + VF_RES_A_DATA_2_VF_SRQC_BT_NUM_M, + VF_RES_A_DATA_2_VF_SRQC_BT_NUM_S, + HNS_ROCE_VF_SRQC_BT_NUM); + + roce_set_field(req_a->vf_cqc_bt_idx_num, + VF_RES_A_DATA_3_VF_CQC_BT_IDX_M, + VF_RES_A_DATA_3_VF_CQC_BT_IDX_S, 0); + roce_set_field(req_a->vf_cqc_bt_idx_num, + VF_RES_A_DATA_3_VF_CQC_BT_NUM_M, + VF_RES_A_DATA_3_VF_CQC_BT_NUM_S, + HNS_ROCE_VF_CQC_BT_NUM); + + roce_set_field(req_a->vf_mpt_bt_idx_num, + VF_RES_A_DATA_4_VF_MPT_BT_IDX_M, + VF_RES_A_DATA_4_VF_MPT_BT_IDX_S, 0); + roce_set_field(req_a->vf_mpt_bt_idx_num, + VF_RES_A_DATA_4_VF_MPT_BT_NUM_M, + VF_RES_A_DATA_4_VF_MPT_BT_NUM_S, + HNS_ROCE_VF_MPT_BT_NUM); + + roce_set_field(req_a->vf_eqc_bt_idx_num, + VF_RES_A_DATA_5_VF_EQC_IDX_M, + VF_RES_A_DATA_5_VF_EQC_IDX_S, 0); + roce_set_field(req_a->vf_eqc_bt_idx_num, + VF_RES_A_DATA_5_VF_EQC_NUM_M, + VF_RES_A_DATA_5_VF_EQC_NUM_S, + HNS_ROCE_VF_EQC_NUM); + } else { + roce_set_field(req_b->vf_smac_idx_num, + VF_RES_B_DATA_1_VF_SMAC_IDX_M, + VF_RES_B_DATA_1_VF_SMAC_IDX_S, 0); + roce_set_field(req_b->vf_smac_idx_num, + VF_RES_B_DATA_1_VF_SMAC_NUM_M, + VF_RES_B_DATA_1_VF_SMAC_NUM_S, + HNS_ROCE_VF_SMAC_NUM); + + roce_set_field(req_b->vf_sgid_idx_num, + VF_RES_B_DATA_2_VF_SGID_IDX_M, + VF_RES_B_DATA_2_VF_SGID_IDX_S, 0); + roce_set_field(req_b->vf_sgid_idx_num, + VF_RES_B_DATA_2_VF_SGID_NUM_M, + VF_RES_B_DATA_2_VF_SGID_NUM_S, + HNS_ROCE_VF_SGID_NUM); + + roce_set_field(req_b->vf_qid_idx_sl_num, + VF_RES_B_DATA_3_VF_QID_IDX_M, + VF_RES_B_DATA_3_VF_QID_IDX_S, 0); + roce_set_field(req_b->vf_qid_idx_sl_num, + VF_RES_B_DATA_3_VF_SL_NUM_M, + VF_RES_B_DATA_3_VF_SL_NUM_S, + HNS_ROCE_VF_SL_NUM); + } + } + + return hns_roce_cmq_send(hr_dev, desc, 2); +} + +static int hns_roce_v2_set_bt(struct hns_roce_dev *hr_dev) +{ + u8 srqc_hop_num = hr_dev->caps.srqc_hop_num; + u8 qpc_hop_num = hr_dev->caps.qpc_hop_num; + u8 cqc_hop_num = hr_dev->caps.cqc_hop_num; + u8 mpt_hop_num = hr_dev->caps.mpt_hop_num; + struct hns_roce_cfg_bt_attr *req; + struct hns_roce_cmq_desc desc; + + hns_roce_cmq_setup_basic_desc(&desc, HNS_ROCE_OPC_CFG_BT_ATTR, false); + req = (struct hns_roce_cfg_bt_attr *)desc.data; + memset(req, 0, sizeof(*req)); + + roce_set_field(req->vf_qpc_cfg, CFG_BT_ATTR_DATA_0_VF_QPC_BA_PGSZ_M, + CFG_BT_ATTR_DATA_0_VF_QPC_BA_PGSZ_S, + hr_dev->caps.qpc_ba_pg_sz); + roce_set_field(req->vf_qpc_cfg, CFG_BT_ATTR_DATA_0_VF_QPC_BUF_PGSZ_M, + CFG_BT_ATTR_DATA_0_VF_QPC_BUF_PGSZ_S, + hr_dev->caps.qpc_buf_pg_sz); + roce_set_field(req->vf_qpc_cfg, CFG_BT_ATTR_DATA_0_VF_QPC_HOPNUM_M, + CFG_BT_ATTR_DATA_0_VF_QPC_HOPNUM_S, + qpc_hop_num == HNS_ROCE_HOP_NUM_0 ? 0 : qpc_hop_num); + + roce_set_field(req->vf_srqc_cfg, CFG_BT_ATTR_DATA_1_VF_SRQC_BA_PGSZ_M, + CFG_BT_ATTR_DATA_1_VF_SRQC_BA_PGSZ_S, + hr_dev->caps.srqc_ba_pg_sz); + roce_set_field(req->vf_srqc_cfg, CFG_BT_ATTR_DATA_1_VF_SRQC_BUF_PGSZ_M, + CFG_BT_ATTR_DATA_1_VF_SRQC_BUF_PGSZ_S, + hr_dev->caps.srqc_buf_pg_sz); + roce_set_field(req->vf_srqc_cfg, CFG_BT_ATTR_DATA_1_VF_SRQC_HOPNUM_M, + CFG_BT_ATTR_DATA_1_VF_SRQC_HOPNUM_S, + srqc_hop_num == HNS_ROCE_HOP_NUM_0 ? 0 : srqc_hop_num); + + roce_set_field(req->vf_cqc_cfg, CFG_BT_ATTR_DATA_2_VF_CQC_BA_PGSZ_M, + CFG_BT_ATTR_DATA_2_VF_CQC_BA_PGSZ_S, + hr_dev->caps.cqc_ba_pg_sz); + roce_set_field(req->vf_cqc_cfg, CFG_BT_ATTR_DATA_2_VF_CQC_BUF_PGSZ_M, + CFG_BT_ATTR_DATA_2_VF_CQC_BUF_PGSZ_S, + hr_dev->caps.cqc_buf_pg_sz); + roce_set_field(req->vf_cqc_cfg, CFG_BT_ATTR_DATA_2_VF_CQC_HOPNUM_M, + CFG_BT_ATTR_DATA_2_VF_CQC_HOPNUM_S, + cqc_hop_num == HNS_ROCE_HOP_NUM_0 ? 0 : cqc_hop_num); + + roce_set_field(req->vf_mpt_cfg, CFG_BT_ATTR_DATA_3_VF_MPT_BA_PGSZ_M, + CFG_BT_ATTR_DATA_3_VF_MPT_BA_PGSZ_S, + hr_dev->caps.mpt_ba_pg_sz); + roce_set_field(req->vf_mpt_cfg, CFG_BT_ATTR_DATA_3_VF_MPT_BUF_PGSZ_M, + CFG_BT_ATTR_DATA_3_VF_MPT_BUF_PGSZ_S, + hr_dev->caps.mpt_buf_pg_sz); + roce_set_field(req->vf_mpt_cfg, CFG_BT_ATTR_DATA_3_VF_MPT_HOPNUM_M, + CFG_BT_ATTR_DATA_3_VF_MPT_HOPNUM_S, + mpt_hop_num == HNS_ROCE_HOP_NUM_0 ? 0 : mpt_hop_num); + + return hns_roce_cmq_send(hr_dev, &desc, 1); +} + +static int hns_roce_v2_profile(struct hns_roce_dev *hr_dev) +{ + struct hns_roce_caps *caps = &hr_dev->caps; + int ret; + + ret = hns_roce_cmq_query_hw_info(hr_dev); + if (ret) { + dev_err(hr_dev->dev, "Query firmware version fail, ret = %d.\n", + ret); + return ret; + } + + ret = hns_roce_config_global_param(hr_dev); + if (ret) { + dev_err(hr_dev->dev, "Configure global param fail, ret = %d.\n", + ret); + } + + /* Get pf resource owned by every pf */ + ret = hns_roce_query_pf_resource(hr_dev); + if (ret) { + dev_err(hr_dev->dev, "Query pf resource fail, ret = %d.\n", + ret); + return ret; + } + + ret = hns_roce_alloc_vf_resource(hr_dev); + if (ret) { + dev_err(hr_dev->dev, "Allocate vf resource fail, ret = %d.\n", + ret); + return ret; + } + + hr_dev->vendor_part_id = 0; + hr_dev->sys_image_guid = 0; + + caps->num_qps = HNS_ROCE_V2_MAX_QP_NUM; + caps->max_wqes = HNS_ROCE_V2_MAX_WQE_NUM; + caps->num_cqs = HNS_ROCE_V2_MAX_CQ_NUM; + caps->max_cqes = HNS_ROCE_V2_MAX_CQE_NUM; + caps->max_sq_sg = HNS_ROCE_V2_MAX_SQ_SGE_NUM; + caps->max_rq_sg = HNS_ROCE_V2_MAX_RQ_SGE_NUM; + caps->max_sq_inline = HNS_ROCE_V2_MAX_SQ_INLINE; + caps->num_uars = HNS_ROCE_V2_UAR_NUM; + caps->phy_num_uars = HNS_ROCE_V2_PHY_UAR_NUM; + caps->num_aeq_vectors = 1; + caps->num_comp_vectors = 63; + caps->num_other_vectors = 0; + caps->num_mtpts = HNS_ROCE_V2_MAX_MTPT_NUM; + caps->num_mtt_segs = HNS_ROCE_V2_MAX_MTT_SEGS; + caps->num_cqe_segs = HNS_ROCE_V2_MAX_CQE_SEGS; + caps->num_pds = HNS_ROCE_V2_MAX_PD_NUM; + caps->max_qp_init_rdma = HNS_ROCE_V2_MAX_QP_INIT_RDMA; + caps->max_qp_dest_rdma = HNS_ROCE_V2_MAX_QP_DEST_RDMA; + caps->max_sq_desc_sz = HNS_ROCE_V2_MAX_SQ_DESC_SZ; + caps->max_rq_desc_sz = HNS_ROCE_V2_MAX_RQ_DESC_SZ; + caps->max_srq_desc_sz = HNS_ROCE_V2_MAX_SRQ_DESC_SZ; + caps->qpc_entry_sz = HNS_ROCE_V2_QPC_ENTRY_SZ; + caps->irrl_entry_sz = HNS_ROCE_V2_IRRL_ENTRY_SZ; + caps->cqc_entry_sz = HNS_ROCE_V2_CQC_ENTRY_SZ; + caps->mtpt_entry_sz = HNS_ROCE_V2_MTPT_ENTRY_SZ; + caps->mtt_entry_sz = HNS_ROCE_V2_MTT_ENTRY_SZ; + caps->cq_entry_sz = HNS_ROCE_V2_CQE_ENTRY_SIZE; + caps->page_size_cap = HNS_ROCE_V2_PAGE_SIZE_SUPPORTED; + caps->reserved_lkey = 0; + caps->reserved_pds = 0; + caps->reserved_mrws = 1; + caps->reserved_uars = 0; + caps->reserved_cqs = 0; + + caps->qpc_ba_pg_sz = 0; + caps->qpc_buf_pg_sz = 0; + caps->qpc_hop_num = HNS_ROCE_CONTEXT_HOP_NUM; + caps->srqc_ba_pg_sz = 0; + caps->srqc_buf_pg_sz = 0; + caps->srqc_hop_num = HNS_ROCE_HOP_NUM_0; + caps->cqc_ba_pg_sz = 0; + caps->cqc_buf_pg_sz = 0; + caps->cqc_hop_num = HNS_ROCE_CONTEXT_HOP_NUM; + caps->mpt_ba_pg_sz = 0; + caps->mpt_buf_pg_sz = 0; + caps->mpt_hop_num = HNS_ROCE_CONTEXT_HOP_NUM; + caps->pbl_ba_pg_sz = 0; + caps->pbl_buf_pg_sz = 0; + caps->pbl_hop_num = HNS_ROCE_PBL_HOP_NUM; + caps->mtt_ba_pg_sz = 0; + caps->mtt_buf_pg_sz = 0; + caps->mtt_hop_num = HNS_ROCE_MTT_HOP_NUM; + caps->cqe_ba_pg_sz = 0; + caps->cqe_buf_pg_sz = 0; + caps->cqe_hop_num = HNS_ROCE_CQE_HOP_NUM; + caps->chunk_sz = HNS_ROCE_V2_TABLE_CHUNK_SIZE; + + caps->pkey_table_len[0] = 1; + caps->gid_table_len[0] = 2; + caps->local_ca_ack_delay = 0; + caps->max_mtu = IB_MTU_4096; + + ret = hns_roce_v2_set_bt(hr_dev); + if (ret) + dev_err(hr_dev->dev, "Configure bt attribute fail, ret = %d.\n", + ret); + + return ret; +} + +static int hns_roce_v2_cmd_pending(struct hns_roce_dev *hr_dev) +{ + u32 status = readl(hr_dev->reg_base + ROCEE_VF_MB_STATUS_REG); + + return status >> HNS_ROCE_HW_RUN_BIT_SHIFT; +} + +static int hns_roce_v2_cmd_complete(struct hns_roce_dev *hr_dev) +{ + u32 status = readl(hr_dev->reg_base + ROCEE_VF_MB_STATUS_REG); + + return status & HNS_ROCE_HW_MB_STATUS_MASK; +} + +static int hns_roce_v2_post_mbox(struct hns_roce_dev *hr_dev, u64 in_param, + u64 out_param, u32 in_modifier, u8 op_modifier, + u16 op, u16 token, int event) +{ + struct device *dev = hr_dev->dev; + u32 __iomem *hcr = (u32 __iomem *)(hr_dev->reg_base + + ROCEE_VF_MB_CFG0_REG); + unsigned long end; + u32 val0 = 0; + u32 val1 = 0; + + end = msecs_to_jiffies(HNS_ROCE_V2_GO_BIT_TIMEOUT_MSECS) + jiffies; + while (hns_roce_v2_cmd_pending(hr_dev)) { + if (time_after(jiffies, end)) { + dev_dbg(dev, "jiffies=%d end=%d\n", (int)jiffies, + (int)end); + return -EAGAIN; + } + cond_resched(); + } + + roce_set_field(val0, HNS_ROCE_VF_MB4_TAG_MASK, + HNS_ROCE_VF_MB4_TAG_SHIFT, in_modifier); + roce_set_field(val0, HNS_ROCE_VF_MB4_CMD_MASK, + HNS_ROCE_VF_MB4_CMD_SHIFT, op); + roce_set_field(val1, HNS_ROCE_VF_MB5_EVENT_MASK, + HNS_ROCE_VF_MB5_EVENT_SHIFT, event); + roce_set_field(val1, HNS_ROCE_VF_MB5_TOKEN_MASK, + HNS_ROCE_VF_MB5_TOKEN_SHIFT, token); + + __raw_writeq(cpu_to_le64(in_param), hcr + 0); + __raw_writeq(cpu_to_le64(out_param), hcr + 2); + + /* Memory barrier */ + wmb(); + + __raw_writel(cpu_to_le32(val0), hcr + 4); + __raw_writel(cpu_to_le32(val1), hcr + 5); + + mmiowb(); + + return 0; +} + +static int hns_roce_v2_chk_mbox(struct hns_roce_dev *hr_dev, + unsigned long timeout) +{ + struct device *dev = hr_dev->dev; + unsigned long end = 0; + u32 status; + + end = msecs_to_jiffies(timeout) + jiffies; + while (hns_roce_v2_cmd_pending(hr_dev) && time_before(jiffies, end)) + cond_resched(); + + if (hns_roce_v2_cmd_pending(hr_dev)) { + dev_err(dev, "[cmd_poll]hw run cmd TIMEDOUT!\n"); + return -ETIMEDOUT; + } + + status = hns_roce_v2_cmd_complete(hr_dev); + if (status != 0x1) { + dev_err(dev, "mailbox status 0x%x!\n", status); + return -EBUSY; + } + + return 0; +} + +static void hns_roce_v2_set_gid(struct hns_roce_dev *hr_dev, u8 port, + int gid_index, union ib_gid *gid) +{ + u32 *p; + u32 val; + + p = (u32 *)&gid->raw[0]; + roce_raw_write(*p, hr_dev->reg_base + ROCEE_VF_SGID_CFG0_REG + + 0x20 * gid_index); + + p = (u32 *)&gid->raw[4]; + roce_raw_write(*p, hr_dev->reg_base + ROCEE_VF_SGID_CFG1_REG + + 0x20 * gid_index); + + p = (u32 *)&gid->raw[8]; + roce_raw_write(*p, hr_dev->reg_base + ROCEE_VF_SGID_CFG2_REG + + 0x20 * gid_index); + + p = (u32 *)&gid->raw[0xc]; + roce_raw_write(*p, hr_dev->reg_base + ROCEE_VF_SGID_CFG3_REG + + 0x20 * gid_index); + + val = roce_read(hr_dev, ROCEE_VF_SGID_CFG4_REG + 0x20 * gid_index); + roce_set_field(val, ROCEE_VF_SGID_CFG4_SGID_TYPE_M, + ROCEE_VF_SGID_CFG4_SGID_TYPE_S, 0); + + roce_write(hr_dev, ROCEE_VF_SGID_CFG4_REG + 0x20 * gid_index, val); +} + +static int hns_roce_v2_set_mac(struct hns_roce_dev *hr_dev, u8 phy_port, + u8 *addr) +{ + u16 reg_smac_h; + u32 reg_smac_l; + u32 val; + + reg_smac_l = *(u32 *)(&addr[0]); + roce_raw_write(reg_smac_l, hr_dev->reg_base + ROCEE_VF_SMAC_CFG0_REG + + 0x08 * phy_port); + val = roce_read(hr_dev, ROCEE_VF_SMAC_CFG1_REG + 0x08 * phy_port); + + reg_smac_h = *(u16 *)(&addr[4]); + roce_set_field(val, ROCEE_VF_SMAC_CFG1_VF_SMAC_H_M, + ROCEE_VF_SMAC_CFG1_VF_SMAC_H_S, reg_smac_h); + roce_write(hr_dev, ROCEE_VF_SMAC_CFG1_REG + 0x08 * phy_port, val); + + return 0; +} + +static int hns_roce_v2_write_mtpt(void *mb_buf, struct hns_roce_mr *mr, + unsigned long mtpt_idx) +{ + struct hns_roce_v2_mpt_entry *mpt_entry; + struct scatterlist *sg; + u64 *pages; + int entry; + int i; + + mpt_entry = mb_buf; + memset(mpt_entry, 0, sizeof(*mpt_entry)); + + roce_set_field(mpt_entry->byte_4_pd_hop_st, V2_MPT_BYTE_4_MPT_ST_M, + V2_MPT_BYTE_4_MPT_ST_S, V2_MPT_ST_VALID); + roce_set_field(mpt_entry->byte_4_pd_hop_st, V2_MPT_BYTE_4_PBL_HOP_NUM_M, + V2_MPT_BYTE_4_PBL_HOP_NUM_S, mr->pbl_hop_num == + HNS_ROCE_HOP_NUM_0 ? 0 : mr->pbl_hop_num); + roce_set_field(mpt_entry->byte_4_pd_hop_st, + V2_MPT_BYTE_4_PBL_BA_PG_SZ_M, + V2_MPT_BYTE_4_PBL_BA_PG_SZ_S, mr->pbl_ba_pg_sz); + roce_set_field(mpt_entry->byte_4_pd_hop_st, V2_MPT_BYTE_4_PD_M, + V2_MPT_BYTE_4_PD_S, mr->pd); + mpt_entry->byte_4_pd_hop_st = cpu_to_le32(mpt_entry->byte_4_pd_hop_st); + + roce_set_bit(mpt_entry->byte_8_mw_cnt_en, V2_MPT_BYTE_8_RA_EN_S, 0); + roce_set_bit(mpt_entry->byte_8_mw_cnt_en, V2_MPT_BYTE_8_R_INV_EN_S, 1); + roce_set_bit(mpt_entry->byte_8_mw_cnt_en, V2_MPT_BYTE_8_L_INV_EN_S, 0); + roce_set_bit(mpt_entry->byte_8_mw_cnt_en, V2_MPT_BYTE_8_BIND_EN_S, + (mr->access & IB_ACCESS_MW_BIND ? 1 : 0)); + roce_set_bit(mpt_entry->byte_8_mw_cnt_en, V2_MPT_BYTE_8_ATOMIC_EN_S, 0); + roce_set_bit(mpt_entry->byte_8_mw_cnt_en, V2_MPT_BYTE_8_RR_EN_S, + (mr->access & IB_ACCESS_REMOTE_READ ? 1 : 0)); + roce_set_bit(mpt_entry->byte_8_mw_cnt_en, V2_MPT_BYTE_8_RW_EN_S, + (mr->access & IB_ACCESS_REMOTE_WRITE ? 1 : 0)); + roce_set_bit(mpt_entry->byte_8_mw_cnt_en, V2_MPT_BYTE_8_LW_EN_S, + (mr->access & IB_ACCESS_LOCAL_WRITE ? 1 : 0)); + mpt_entry->byte_8_mw_cnt_en = cpu_to_le32(mpt_entry->byte_8_mw_cnt_en); + + roce_set_bit(mpt_entry->byte_12_mw_pa, V2_MPT_BYTE_12_PA_S, + mr->type == MR_TYPE_MR ? 0 : 1); + mpt_entry->byte_12_mw_pa = cpu_to_le32(mpt_entry->byte_12_mw_pa); + + mpt_entry->len_l = cpu_to_le32(lower_32_bits(mr->size)); + mpt_entry->len_h = cpu_to_le32(upper_32_bits(mr->size)); + mpt_entry->lkey = cpu_to_le32(mr->key); + mpt_entry->va_l = cpu_to_le32(lower_32_bits(mr->iova)); + mpt_entry->va_h = cpu_to_le32(upper_32_bits(mr->iova)); + + if (mr->type == MR_TYPE_DMA) + return 0; + + mpt_entry->pbl_size = cpu_to_le32(mr->pbl_size); + + mpt_entry->pbl_ba_l = cpu_to_le32(lower_32_bits(mr->pbl_ba >> 3)); + roce_set_field(mpt_entry->byte_48_mode_ba, V2_MPT_BYTE_48_PBL_BA_H_M, + V2_MPT_BYTE_48_PBL_BA_H_S, + upper_32_bits(mr->pbl_ba >> 3)); + mpt_entry->byte_48_mode_ba = cpu_to_le32(mpt_entry->byte_48_mode_ba); + + pages = (u64 *)__get_free_page(GFP_KERNEL); + if (!pages) + return -ENOMEM; + + i = 0; + for_each_sg(mr->umem->sg_head.sgl, sg, mr->umem->nmap, entry) { + pages[i] = ((u64)sg_dma_address(sg)) >> 6; + + /* Record the first 2 entry directly to MTPT table */ + if (i >= HNS_ROCE_V2_MAX_INNER_MTPT_NUM - 1) + break; + i++; + } + + mpt_entry->pa0_l = cpu_to_le32(lower_32_bits(pages[0])); + roce_set_field(mpt_entry->byte_56_pa0_h, V2_MPT_BYTE_56_PA0_H_M, + V2_MPT_BYTE_56_PA0_H_S, + upper_32_bits(pages[0])); + mpt_entry->byte_56_pa0_h = cpu_to_le32(mpt_entry->byte_56_pa0_h); + + mpt_entry->pa1_l = cpu_to_le32(lower_32_bits(pages[1])); + roce_set_field(mpt_entry->byte_64_buf_pa1, V2_MPT_BYTE_64_PA1_H_M, + V2_MPT_BYTE_64_PA1_H_S, upper_32_bits(pages[1])); + + free_page((unsigned long)pages); + + roce_set_field(mpt_entry->byte_64_buf_pa1, + V2_MPT_BYTE_64_PBL_BUF_PG_SZ_M, + V2_MPT_BYTE_64_PBL_BUF_PG_SZ_S, mr->pbl_buf_pg_sz); + mpt_entry->byte_64_buf_pa1 = cpu_to_le32(mpt_entry->byte_64_buf_pa1); + + return 0; +} + +static void *get_cqe_v2(struct hns_roce_cq *hr_cq, int n) +{ + return hns_roce_buf_offset(&hr_cq->hr_buf.hr_buf, + n * HNS_ROCE_V2_CQE_ENTRY_SIZE); +} + +static void *get_sw_cqe_v2(struct hns_roce_cq *hr_cq, int n) +{ + struct hns_roce_v2_cqe *cqe = get_cqe_v2(hr_cq, n & hr_cq->ib_cq.cqe); + + /* Get cqe when Owner bit is Conversely with the MSB of cons_idx */ + return (roce_get_bit(cqe->byte_4, V2_CQE_BYTE_4_OWNER_S) ^ + !!(n & (hr_cq->ib_cq.cqe + 1))) ? cqe : NULL; +} + +static struct hns_roce_v2_cqe *next_cqe_sw_v2(struct hns_roce_cq *hr_cq) +{ + return get_sw_cqe_v2(hr_cq, hr_cq->cons_index); +} + +static void hns_roce_v2_cq_set_ci(struct hns_roce_cq *hr_cq, u32 cons_index) +{ + struct hns_roce_v2_cq_db cq_db; + + cq_db.byte_4 = 0; + cq_db.parameter = 0; + + roce_set_field(cq_db.byte_4, V2_CQ_DB_BYTE_4_TAG_M, + V2_CQ_DB_BYTE_4_TAG_S, hr_cq->cqn); + roce_set_field(cq_db.byte_4, V2_CQ_DB_BYTE_4_CMD_M, + V2_CQ_DB_BYTE_4_CMD_S, HNS_ROCE_V2_CQ_DB_PTR); + + roce_set_field(cq_db.parameter, V2_CQ_DB_PARAMETER_CONS_IDX_M, + V2_CQ_DB_PARAMETER_CONS_IDX_S, + cons_index & ((hr_cq->cq_depth << 1) - 1)); + roce_set_field(cq_db.parameter, V2_CQ_DB_PARAMETER_CMD_SN_M, + V2_CQ_DB_PARAMETER_CMD_SN_S, 1); + + hns_roce_write64_k((__be32 *)&cq_db, hr_cq->cq_db_l); + +} + +static void __hns_roce_v2_cq_clean(struct hns_roce_cq *hr_cq, u32 qpn, + struct hns_roce_srq *srq) +{ + struct hns_roce_v2_cqe *cqe, *dest; + u32 prod_index; + int nfreed = 0; + u8 owner_bit; + + for (prod_index = hr_cq->cons_index; get_sw_cqe_v2(hr_cq, prod_index); + ++prod_index) { + if (prod_index == hr_cq->cons_index + hr_cq->ib_cq.cqe) + break; + } + + /* + * Now backwards through the CQ, removing CQ entries + * that match our QP by overwriting them with next entries. + */ + while ((int) --prod_index - (int) hr_cq->cons_index >= 0) { + cqe = get_cqe_v2(hr_cq, prod_index & hr_cq->ib_cq.cqe); + if ((roce_get_field(cqe->byte_16, V2_CQE_BYTE_16_LCL_QPN_M, + V2_CQE_BYTE_16_LCL_QPN_S) & + HNS_ROCE_V2_CQE_QPN_MASK) == qpn) { + /* In v1 engine, not support SRQ */ + ++nfreed; + } else if (nfreed) { + dest = get_cqe_v2(hr_cq, (prod_index + nfreed) & + hr_cq->ib_cq.cqe); + owner_bit = roce_get_bit(dest->byte_4, + V2_CQE_BYTE_4_OWNER_S); + memcpy(dest, cqe, sizeof(*cqe)); + roce_set_bit(dest->byte_4, V2_CQE_BYTE_4_OWNER_S, + owner_bit); + } + } + + if (nfreed) { + hr_cq->cons_index += nfreed; + /* + * Make sure update of buffer contents is done before + * updating consumer index. + */ + wmb(); + hns_roce_v2_cq_set_ci(hr_cq, hr_cq->cons_index); + } +} + +static void hns_roce_v2_cq_clean(struct hns_roce_cq *hr_cq, u32 qpn, + struct hns_roce_srq *srq) +{ + spin_lock_irq(&hr_cq->lock); + __hns_roce_v2_cq_clean(hr_cq, qpn, srq); + spin_unlock_irq(&hr_cq->lock); +} + +static void hns_roce_v2_write_cqc(struct hns_roce_dev *hr_dev, + struct hns_roce_cq *hr_cq, void *mb_buf, + u64 *mtts, dma_addr_t dma_handle, int nent, + u32 vector) +{ + struct hns_roce_v2_cq_context *cq_context; + + cq_context = mb_buf; + memset(cq_context, 0, sizeof(*cq_context)); + + roce_set_field(cq_context->byte_4_pg_ceqn, V2_CQC_BYTE_4_CQ_ST_M, + V2_CQC_BYTE_4_CQ_ST_S, V2_CQ_STATE_VALID); + roce_set_field(cq_context->byte_4_pg_ceqn, V2_CQC_BYTE_4_SHIFT_M, + V2_CQC_BYTE_4_SHIFT_S, ilog2((unsigned int)nent)); + roce_set_field(cq_context->byte_4_pg_ceqn, V2_CQC_BYTE_4_CEQN_M, + V2_CQC_BYTE_4_CEQN_S, vector); + cq_context->byte_4_pg_ceqn = cpu_to_le32(cq_context->byte_4_pg_ceqn); + + roce_set_field(cq_context->byte_8_cqn, V2_CQC_BYTE_8_CQN_M, + V2_CQC_BYTE_8_CQN_S, hr_cq->cqn); + + cq_context->cqe_cur_blk_addr = (u32)(mtts[0] >> PAGE_ADDR_SHIFT); + cq_context->cqe_cur_blk_addr = + cpu_to_le32(cq_context->cqe_cur_blk_addr); + + roce_set_field(cq_context->byte_16_hop_addr, + V2_CQC_BYTE_16_CQE_CUR_BLK_ADDR_M, + V2_CQC_BYTE_16_CQE_CUR_BLK_ADDR_S, + cpu_to_le32((mtts[0]) >> (32 + PAGE_ADDR_SHIFT))); + roce_set_field(cq_context->byte_16_hop_addr, + V2_CQC_BYTE_16_CQE_HOP_NUM_M, + V2_CQC_BYTE_16_CQE_HOP_NUM_S, hr_dev->caps.cqe_hop_num == + HNS_ROCE_HOP_NUM_0 ? 0 : hr_dev->caps.cqe_hop_num); + + cq_context->cqe_nxt_blk_addr = (u32)(mtts[1] >> PAGE_ADDR_SHIFT); + roce_set_field(cq_context->byte_24_pgsz_addr, + V2_CQC_BYTE_24_CQE_NXT_BLK_ADDR_M, + V2_CQC_BYTE_24_CQE_NXT_BLK_ADDR_S, + cpu_to_le32((mtts[1]) >> (32 + PAGE_ADDR_SHIFT))); + roce_set_field(cq_context->byte_24_pgsz_addr, + V2_CQC_BYTE_24_CQE_BA_PG_SZ_M, + V2_CQC_BYTE_24_CQE_BA_PG_SZ_S, + hr_dev->caps.cqe_ba_pg_sz); + roce_set_field(cq_context->byte_24_pgsz_addr, + V2_CQC_BYTE_24_CQE_BUF_PG_SZ_M, + V2_CQC_BYTE_24_CQE_BUF_PG_SZ_S, + hr_dev->caps.cqe_buf_pg_sz); + + cq_context->cqe_ba = (u32)(dma_handle >> 3); + + roce_set_field(cq_context->byte_40_cqe_ba, V2_CQC_BYTE_40_CQE_BA_M, + V2_CQC_BYTE_40_CQE_BA_S, (dma_handle >> (32 + 3))); +} + +static int hns_roce_v2_req_notify_cq(struct ib_cq *ibcq, + enum ib_cq_notify_flags flags) +{ + struct hns_roce_cq *hr_cq = to_hr_cq(ibcq); + u32 notification_flag; + u32 doorbell[2]; + + doorbell[0] = 0; + doorbell[1] = 0; + + notification_flag = (flags & IB_CQ_SOLICITED_MASK) == IB_CQ_SOLICITED ? + V2_CQ_DB_REQ_NOT : V2_CQ_DB_REQ_NOT_SOL; + /* + * flags = 0; Notification Flag = 1, next + * flags = 1; Notification Flag = 0, solocited + */ + roce_set_field(doorbell[0], V2_CQ_DB_BYTE_4_TAG_M, V2_DB_BYTE_4_TAG_S, + hr_cq->cqn); + roce_set_field(doorbell[0], V2_CQ_DB_BYTE_4_CMD_M, V2_DB_BYTE_4_CMD_S, + HNS_ROCE_V2_CQ_DB_NTR); + roce_set_field(doorbell[1], V2_CQ_DB_PARAMETER_CONS_IDX_M, + V2_CQ_DB_PARAMETER_CONS_IDX_S, + hr_cq->cons_index & ((hr_cq->cq_depth << 1) - 1)); + roce_set_field(doorbell[1], V2_CQ_DB_PARAMETER_CMD_SN_M, + V2_CQ_DB_PARAMETER_CMD_SN_S, 1); + roce_set_bit(doorbell[1], V2_CQ_DB_PARAMETER_NOTIFY_S, + notification_flag); + + hns_roce_write64_k(doorbell, hr_cq->cq_db_l); + + return 0; +} + +static int hns_roce_v2_poll_one(struct hns_roce_cq *hr_cq, + struct hns_roce_qp **cur_qp, struct ib_wc *wc) +{ + struct hns_roce_dev *hr_dev; + struct hns_roce_v2_cqe *cqe; + struct hns_roce_qp *hr_qp; + struct hns_roce_wq *wq; + int is_send; + u16 wqe_ctr; + u32 opcode; + u32 status; + int qpn; + + /* Find cqe according to consumer index */ + cqe = next_cqe_sw_v2(hr_cq); + if (!cqe) + return -EAGAIN; + + ++hr_cq->cons_index; + /* Memory barrier */ + rmb(); + + /* 0->SQ, 1->RQ */ + is_send = !roce_get_bit(cqe->byte_4, V2_CQE_BYTE_4_S_R_S); + + qpn = roce_get_field(cqe->byte_16, V2_CQE_BYTE_16_LCL_QPN_M, + V2_CQE_BYTE_16_LCL_QPN_S); + + if (!*cur_qp || (qpn & HNS_ROCE_V2_CQE_QPN_MASK) != (*cur_qp)->qpn) { + hr_dev = to_hr_dev(hr_cq->ib_cq.device); + hr_qp = __hns_roce_qp_lookup(hr_dev, qpn); + if (unlikely(!hr_qp)) { + dev_err(hr_dev->dev, "CQ %06lx with entry for unknown QPN %06x\n", + hr_cq->cqn, (qpn & HNS_ROCE_V2_CQE_QPN_MASK)); + return -EINVAL; + } + *cur_qp = hr_qp; + } + + wc->qp = &(*cur_qp)->ibqp; + wc->vendor_err = 0; + + status = roce_get_field(cqe->byte_4, V2_CQE_BYTE_4_STATUS_M, + V2_CQE_BYTE_4_STATUS_S); + switch (status & HNS_ROCE_V2_CQE_STATUS_MASK) { + case HNS_ROCE_CQE_V2_SUCCESS: + wc->status = IB_WC_SUCCESS; + break; + case HNS_ROCE_CQE_V2_LOCAL_LENGTH_ERR: + wc->status = IB_WC_LOC_LEN_ERR; + break; + case HNS_ROCE_CQE_V2_LOCAL_QP_OP_ERR: + wc->status = IB_WC_LOC_QP_OP_ERR; + break; + case HNS_ROCE_CQE_V2_LOCAL_PROT_ERR: + wc->status = IB_WC_LOC_PROT_ERR; + break; + case HNS_ROCE_CQE_V2_WR_FLUSH_ERR: + wc->status = IB_WC_WR_FLUSH_ERR; + break; + case HNS_ROCE_CQE_V2_MW_BIND_ERR: + wc->status = IB_WC_MW_BIND_ERR; + break; + case HNS_ROCE_CQE_V2_BAD_RESP_ERR: + wc->status = IB_WC_BAD_RESP_ERR; + break; + case HNS_ROCE_CQE_V2_LOCAL_ACCESS_ERR: + wc->status = IB_WC_LOC_ACCESS_ERR; + break; + case HNS_ROCE_CQE_V2_REMOTE_INVAL_REQ_ERR: + wc->status = IB_WC_REM_INV_REQ_ERR; + break; + case HNS_ROCE_CQE_V2_REMOTE_ACCESS_ERR: + wc->status = IB_WC_REM_ACCESS_ERR; + break; + case HNS_ROCE_CQE_V2_REMOTE_OP_ERR: + wc->status = IB_WC_REM_OP_ERR; + break; + case HNS_ROCE_CQE_V2_TRANSPORT_RETRY_EXC_ERR: + wc->status = IB_WC_RETRY_EXC_ERR; + break; + case HNS_ROCE_CQE_V2_RNR_RETRY_EXC_ERR: + wc->status = IB_WC_RNR_RETRY_EXC_ERR; + break; + case HNS_ROCE_CQE_V2_REMOTE_ABORT_ERR: + wc->status = IB_WC_REM_ABORT_ERR; + break; + default: + wc->status = IB_WC_GENERAL_ERR; + break; + } + + /* CQE status error, directly return */ + if (wc->status != IB_WC_SUCCESS) + return 0; + + if (is_send) { + wc->wc_flags = 0; + /* SQ corresponding to CQE */ + switch (roce_get_field(cqe->byte_4, V2_CQE_BYTE_4_OPCODE_M, + V2_CQE_BYTE_4_OPCODE_S) & 0x1f) { + case HNS_ROCE_SQ_OPCODE_SEND: + wc->opcode = IB_WC_SEND; + break; + case HNS_ROCE_SQ_OPCODE_SEND_WITH_INV: + wc->opcode = IB_WC_SEND; + break; + case HNS_ROCE_SQ_OPCODE_SEND_WITH_IMM: + wc->opcode = IB_WC_SEND; + wc->wc_flags |= IB_WC_WITH_IMM; + break; + case HNS_ROCE_SQ_OPCODE_RDMA_READ: + wc->opcode = IB_WC_RDMA_READ; + wc->byte_len = le32_to_cpu(cqe->byte_cnt); + break; + case HNS_ROCE_SQ_OPCODE_RDMA_WRITE: + wc->opcode = IB_WC_RDMA_WRITE; + break; + case HNS_ROCE_SQ_OPCODE_RDMA_WRITE_WITH_IMM: + wc->opcode = IB_WC_RDMA_WRITE; + wc->wc_flags |= IB_WC_WITH_IMM; + break; + case HNS_ROCE_SQ_OPCODE_LOCAL_INV: + wc->opcode = IB_WC_LOCAL_INV; + wc->wc_flags |= IB_WC_WITH_INVALIDATE; + break; + case HNS_ROCE_SQ_OPCODE_ATOMIC_COMP_AND_SWAP: + wc->opcode = IB_WC_COMP_SWAP; + wc->byte_len = 8; + break; + case HNS_ROCE_SQ_OPCODE_ATOMIC_FETCH_AND_ADD: + wc->opcode = IB_WC_FETCH_ADD; + wc->byte_len = 8; + break; + case HNS_ROCE_SQ_OPCODE_ATOMIC_MASK_COMP_AND_SWAP: + wc->opcode = IB_WC_MASKED_COMP_SWAP; + wc->byte_len = 8; + break; + case HNS_ROCE_SQ_OPCODE_ATOMIC_MASK_FETCH_AND_ADD: + wc->opcode = IB_WC_MASKED_FETCH_ADD; + wc->byte_len = 8; + break; + case HNS_ROCE_SQ_OPCODE_FAST_REG_WR: + wc->opcode = IB_WC_REG_MR; + break; + case HNS_ROCE_SQ_OPCODE_BIND_MW: + wc->opcode = IB_WC_REG_MR; + break; + default: + wc->status = IB_WC_GENERAL_ERR; + break; + } + + wq = &(*cur_qp)->sq; + if ((*cur_qp)->sq_signal_bits) { + /* + * If sg_signal_bit is 1, + * firstly tail pointer updated to wqe + * which current cqe correspond to + */ + wqe_ctr = (u16)roce_get_field(cqe->byte_4, + V2_CQE_BYTE_4_WQE_INDX_M, + V2_CQE_BYTE_4_WQE_INDX_S); + wq->tail += (wqe_ctr - (u16)wq->tail) & + (wq->wqe_cnt - 1); + } + + wc->wr_id = wq->wrid[wq->tail & (wq->wqe_cnt - 1)]; + ++wq->tail; + } else { + /* RQ correspond to CQE */ + wc->byte_len = le32_to_cpu(cqe->byte_cnt); + + opcode = roce_get_field(cqe->byte_4, V2_CQE_BYTE_4_OPCODE_M, + V2_CQE_BYTE_4_OPCODE_S); + switch (opcode & 0x1f) { + case HNS_ROCE_V2_OPCODE_RDMA_WRITE_IMM: + wc->opcode = IB_WC_RECV_RDMA_WITH_IMM; + wc->wc_flags = IB_WC_WITH_IMM; + wc->ex.imm_data = le32_to_cpu(cqe->rkey_immtdata); + break; + case HNS_ROCE_V2_OPCODE_SEND: + wc->opcode = IB_WC_RECV; + wc->wc_flags = 0; + break; + case HNS_ROCE_V2_OPCODE_SEND_WITH_IMM: + wc->opcode = IB_WC_RECV; + wc->wc_flags = IB_WC_WITH_IMM; + wc->ex.imm_data = le32_to_cpu(cqe->rkey_immtdata); + break; + case HNS_ROCE_V2_OPCODE_SEND_WITH_INV: + wc->opcode = IB_WC_RECV; + wc->wc_flags = IB_WC_WITH_INVALIDATE; + wc->ex.invalidate_rkey = cqe->rkey_immtdata; + break; + default: + wc->status = IB_WC_GENERAL_ERR; + break; + } + + /* Update tail pointer, record wr_id */ + wq = &(*cur_qp)->rq; + wc->wr_id = wq->wrid[wq->tail & (wq->wqe_cnt - 1)]; + ++wq->tail; + + wc->sl = (u8)roce_get_field(cqe->byte_32, V2_CQE_BYTE_32_SL_M, + V2_CQE_BYTE_32_SL_S); + wc->src_qp = (u8)roce_get_field(cqe->byte_32, + V2_CQE_BYTE_32_RMT_QPN_M, + V2_CQE_BYTE_32_RMT_QPN_S); + wc->wc_flags |= (roce_get_bit(cqe->byte_32, + V2_CQE_BYTE_32_GRH_S) ? + IB_WC_GRH : 0); + } + + return 0; +} + +static int hns_roce_v2_poll_cq(struct ib_cq *ibcq, int num_entries, + struct ib_wc *wc) +{ + struct hns_roce_cq *hr_cq = to_hr_cq(ibcq); + struct hns_roce_qp *cur_qp = NULL; + unsigned long flags; + int npolled; + + spin_lock_irqsave(&hr_cq->lock, flags); + + for (npolled = 0; npolled < num_entries; ++npolled) { + if (hns_roce_v2_poll_one(hr_cq, &cur_qp, wc + npolled)) + break; + } + + if (npolled) { + /* Memory barrier */ + wmb(); + hns_roce_v2_cq_set_ci(hr_cq, hr_cq->cons_index); + } + + spin_unlock_irqrestore(&hr_cq->lock, flags); + + return npolled; +} + +static int hns_roce_v2_set_hem(struct hns_roce_dev *hr_dev, + struct hns_roce_hem_table *table, int obj, + int step_idx) +{ + struct device *dev = hr_dev->dev; + struct hns_roce_cmd_mailbox *mailbox; + struct hns_roce_hem_iter iter; + struct hns_roce_hem_mhop mhop; + struct hns_roce_hem *hem; + unsigned long mhop_obj = obj; + int i, j, k; + int ret = 0; + u64 hem_idx = 0; + u64 l1_idx = 0; + u64 bt_ba = 0; + u32 chunk_ba_num; + u32 hop_num; + u16 op = 0xff; + + if (!hns_roce_check_whether_mhop(hr_dev, table->type)) + return 0; + + hns_roce_calc_hem_mhop(hr_dev, table, &mhop_obj, &mhop); + i = mhop.l0_idx; + j = mhop.l1_idx; + k = mhop.l2_idx; + hop_num = mhop.hop_num; + chunk_ba_num = mhop.bt_chunk_size / 8; + + if (hop_num == 2) { + hem_idx = i * chunk_ba_num * chunk_ba_num + j * chunk_ba_num + + k; + l1_idx = i * chunk_ba_num + j; + } else if (hop_num == 1) { + hem_idx = i * chunk_ba_num + j; + } else if (hop_num == HNS_ROCE_HOP_NUM_0) { + hem_idx = i; + } + + switch (table->type) { + case HEM_TYPE_QPC: + op = HNS_ROCE_CMD_WRITE_QPC_BT0; + break; + case HEM_TYPE_MTPT: + op = HNS_ROCE_CMD_WRITE_MPT_BT0; + break; + case HEM_TYPE_CQC: + op = HNS_ROCE_CMD_WRITE_CQC_BT0; + break; + case HEM_TYPE_SRQC: + op = HNS_ROCE_CMD_WRITE_SRQC_BT0; + break; + default: + dev_warn(dev, "Table %d not to be written by mailbox!\n", + table->type); + return 0; + } + op += step_idx; + + mailbox = hns_roce_alloc_cmd_mailbox(hr_dev); + if (IS_ERR(mailbox)) + return PTR_ERR(mailbox); + + if (check_whether_last_step(hop_num, step_idx)) { + hem = table->hem[hem_idx]; + for (hns_roce_hem_first(hem, &iter); + !hns_roce_hem_last(&iter); hns_roce_hem_next(&iter)) { + bt_ba = hns_roce_hem_addr(&iter); + + /* configure the ba, tag, and op */ + ret = hns_roce_cmd_mbox(hr_dev, bt_ba, mailbox->dma, + obj, 0, op, + HNS_ROCE_CMD_TIMEOUT_MSECS); + } + } else { + if (step_idx == 0) + bt_ba = table->bt_l0_dma_addr[i]; + else if (step_idx == 1 && hop_num == 2) + bt_ba = table->bt_l1_dma_addr[l1_idx]; + + /* configure the ba, tag, and op */ + ret = hns_roce_cmd_mbox(hr_dev, bt_ba, mailbox->dma, obj, + 0, op, HNS_ROCE_CMD_TIMEOUT_MSECS); + } + + hns_roce_free_cmd_mailbox(hr_dev, mailbox); + return ret; +} + +static int hns_roce_v2_clear_hem(struct hns_roce_dev *hr_dev, + struct hns_roce_hem_table *table, int obj, + int step_idx) +{ + struct device *dev = hr_dev->dev; + struct hns_roce_cmd_mailbox *mailbox; + int ret = 0; + u16 op = 0xff; + + if (!hns_roce_check_whether_mhop(hr_dev, table->type)) + return 0; + + switch (table->type) { + case HEM_TYPE_QPC: + op = HNS_ROCE_CMD_DESTROY_QPC_BT0; + break; + case HEM_TYPE_MTPT: + op = HNS_ROCE_CMD_DESTROY_MPT_BT0; + break; + case HEM_TYPE_CQC: + op = HNS_ROCE_CMD_DESTROY_CQC_BT0; + break; + case HEM_TYPE_SRQC: + op = HNS_ROCE_CMD_DESTROY_SRQC_BT0; + break; + default: + dev_warn(dev, "Table %d not to be destroyed by mailbox!\n", + table->type); + return 0; + } + op += step_idx; + + mailbox = hns_roce_alloc_cmd_mailbox(hr_dev); + if (IS_ERR(mailbox)) + return PTR_ERR(mailbox); + + /* configure the tag and op */ + ret = hns_roce_cmd_mbox(hr_dev, 0, mailbox->dma, obj, 0, op, + HNS_ROCE_CMD_TIMEOUT_MSECS); + + hns_roce_free_cmd_mailbox(hr_dev, mailbox); + return ret; +} + +static int hns_roce_v2_qp_modify(struct hns_roce_dev *hr_dev, + struct hns_roce_mtt *mtt, + enum ib_qp_state cur_state, + enum ib_qp_state new_state, + struct hns_roce_v2_qp_context *context, + struct hns_roce_qp *hr_qp) +{ + struct hns_roce_cmd_mailbox *mailbox; + int ret; + + mailbox = hns_roce_alloc_cmd_mailbox(hr_dev); + if (IS_ERR(mailbox)) + return PTR_ERR(mailbox); + + memcpy(mailbox->buf, context, sizeof(*context) * 2); + + ret = hns_roce_cmd_mbox(hr_dev, mailbox->dma, 0, hr_qp->qpn, 0, + HNS_ROCE_CMD_MODIFY_QPC, + HNS_ROCE_CMD_TIMEOUT_MSECS); + + hns_roce_free_cmd_mailbox(hr_dev, mailbox); + + return ret; +} + +static void modify_qp_reset_to_init(struct ib_qp *ibqp, + const struct ib_qp_attr *attr, + struct hns_roce_v2_qp_context *context, + struct hns_roce_v2_qp_context *qpc_mask) +{ + struct hns_roce_qp *hr_qp = to_hr_qp(ibqp); + + /* + * In v2 engine, software pass context and context mask to hardware + * when modifying qp. If software need modify some fields in context, + * we should set all bits of the relevant fields in context mask to + * 0 at the same time, else set them to 0x1. + */ + roce_set_field(context->byte_4_sqpn_tst, V2_QPC_BYTE_4_TST_M, + V2_QPC_BYTE_4_TST_S, to_hr_qp_type(hr_qp->ibqp.qp_type)); + roce_set_field(qpc_mask->byte_4_sqpn_tst, V2_QPC_BYTE_4_TST_M, + V2_QPC_BYTE_4_TST_S, 0); + + roce_set_field(context->byte_4_sqpn_tst, V2_QPC_BYTE_4_SGE_SHIFT_M, + V2_QPC_BYTE_4_SGE_SHIFT_S, hr_qp->sq.max_gs > 2 ? + ilog2((unsigned int)hr_qp->sge.sge_cnt) : 0); + roce_set_field(qpc_mask->byte_4_sqpn_tst, V2_QPC_BYTE_4_SGE_SHIFT_M, + V2_QPC_BYTE_4_SGE_SHIFT_S, 0); + + roce_set_field(context->byte_4_sqpn_tst, V2_QPC_BYTE_4_SQPN_M, + V2_QPC_BYTE_4_SQPN_S, hr_qp->qpn); + roce_set_field(qpc_mask->byte_4_sqpn_tst, V2_QPC_BYTE_4_SQPN_M, + V2_QPC_BYTE_4_SQPN_S, 0); + + roce_set_field(context->byte_16_buf_ba_pg_sz, V2_QPC_BYTE_16_PD_M, + V2_QPC_BYTE_16_PD_S, to_hr_pd(ibqp->pd)->pdn); + roce_set_field(qpc_mask->byte_16_buf_ba_pg_sz, V2_QPC_BYTE_16_PD_M, + V2_QPC_BYTE_16_PD_S, 0); + + roce_set_field(context->byte_20_smac_sgid_idx, V2_QPC_BYTE_20_RQWS_M, + V2_QPC_BYTE_20_RQWS_S, ilog2(hr_qp->rq.max_gs)); + roce_set_field(qpc_mask->byte_20_smac_sgid_idx, V2_QPC_BYTE_20_RQWS_M, + V2_QPC_BYTE_20_RQWS_S, 0); + + roce_set_field(context->byte_20_smac_sgid_idx, + V2_QPC_BYTE_20_SQ_SHIFT_M, V2_QPC_BYTE_20_SQ_SHIFT_S, + ilog2((unsigned int)hr_qp->sq.wqe_cnt)); + roce_set_field(qpc_mask->byte_20_smac_sgid_idx, + V2_QPC_BYTE_20_SQ_SHIFT_M, V2_QPC_BYTE_20_SQ_SHIFT_S, 0); + + roce_set_field(context->byte_20_smac_sgid_idx, + V2_QPC_BYTE_20_RQ_SHIFT_M, V2_QPC_BYTE_20_RQ_SHIFT_S, + ilog2((unsigned int)hr_qp->rq.wqe_cnt)); + roce_set_field(qpc_mask->byte_20_smac_sgid_idx, + V2_QPC_BYTE_20_RQ_SHIFT_M, V2_QPC_BYTE_20_RQ_SHIFT_S, 0); + + /* No VLAN need to set 0xFFF */ + roce_set_field(context->byte_24_mtu_tc, V2_QPC_BYTE_24_VLAN_IDX_M, + V2_QPC_BYTE_24_VLAN_IDX_S, 0xfff); + roce_set_field(qpc_mask->byte_24_mtu_tc, V2_QPC_BYTE_24_VLAN_IDX_M, + V2_QPC_BYTE_24_VLAN_IDX_S, 0); + + /* + * Set some fields in context to zero, Because the default values + * of all fields in context are zero, we need not set them to 0 again. + * but we should set the relevant fields of context mask to 0. + */ + roce_set_bit(qpc_mask->byte_56_dqpn_err, V2_QPC_BYTE_56_SQ_TX_ERR_S, 0); + roce_set_bit(qpc_mask->byte_56_dqpn_err, V2_QPC_BYTE_56_SQ_RX_ERR_S, 0); + roce_set_bit(qpc_mask->byte_56_dqpn_err, V2_QPC_BYTE_56_RQ_TX_ERR_S, 0); + roce_set_bit(qpc_mask->byte_56_dqpn_err, V2_QPC_BYTE_56_RQ_RX_ERR_S, 0); + + roce_set_field(qpc_mask->byte_60_qpst_mapid, V2_QPC_BYTE_60_MAPID_M, + V2_QPC_BYTE_60_MAPID_S, 0); + + roce_set_bit(qpc_mask->byte_60_qpst_mapid, + V2_QPC_BYTE_60_INNER_MAP_IND_S, 0); + roce_set_bit(qpc_mask->byte_60_qpst_mapid, V2_QPC_BYTE_60_SQ_MAP_IND_S, + 0); + roce_set_bit(qpc_mask->byte_60_qpst_mapid, V2_QPC_BYTE_60_RQ_MAP_IND_S, + 0); + roce_set_bit(qpc_mask->byte_60_qpst_mapid, V2_QPC_BYTE_60_EXT_MAP_IND_S, + 0); + roce_set_bit(qpc_mask->byte_60_qpst_mapid, V2_QPC_BYTE_60_SQ_RLS_IND_S, + 0); + roce_set_bit(qpc_mask->byte_60_qpst_mapid, V2_QPC_BYTE_60_SQ_EXT_IND_S, + 0); + roce_set_bit(qpc_mask->byte_28_at_fl, V2_QPC_BYTE_28_CNP_TX_FLAG_S, 0); + roce_set_bit(qpc_mask->byte_28_at_fl, V2_QPC_BYTE_28_CE_FLAG_S, 0); + + roce_set_bit(context->byte_76_srqn_op_en, V2_QPC_BYTE_76_RRE_S, + !!(attr->qp_access_flags & IB_ACCESS_REMOTE_READ)); + roce_set_bit(qpc_mask->byte_76_srqn_op_en, V2_QPC_BYTE_76_RRE_S, 0); + + roce_set_bit(context->byte_76_srqn_op_en, V2_QPC_BYTE_76_RWE_S, + !!(attr->qp_access_flags & IB_ACCESS_REMOTE_WRITE)); + roce_set_bit(qpc_mask->byte_76_srqn_op_en, V2_QPC_BYTE_76_RWE_S, 0); + + roce_set_bit(context->byte_76_srqn_op_en, V2_QPC_BYTE_76_ATE_S, + !!(attr->qp_access_flags & IB_ACCESS_REMOTE_ATOMIC)); + roce_set_bit(qpc_mask->byte_76_srqn_op_en, V2_QPC_BYTE_76_ATE_S, 0); + + roce_set_bit(qpc_mask->byte_76_srqn_op_en, V2_QPC_BYTE_76_RQIE_S, 0); + + roce_set_field(context->byte_80_rnr_rx_cqn, V2_QPC_BYTE_80_RX_CQN_M, + V2_QPC_BYTE_80_RX_CQN_S, to_hr_cq(ibqp->recv_cq)->cqn); + roce_set_field(qpc_mask->byte_80_rnr_rx_cqn, V2_QPC_BYTE_80_RX_CQN_M, + V2_QPC_BYTE_80_RX_CQN_S, 0); + if (ibqp->srq) { + roce_set_field(context->byte_76_srqn_op_en, + V2_QPC_BYTE_76_SRQN_M, V2_QPC_BYTE_76_SRQN_S, + to_hr_srq(ibqp->srq)->srqn); + roce_set_field(qpc_mask->byte_76_srqn_op_en, + V2_QPC_BYTE_76_SRQN_M, V2_QPC_BYTE_76_SRQN_S, 0); + roce_set_bit(context->byte_76_srqn_op_en, + V2_QPC_BYTE_76_SRQ_EN_S, 1); + roce_set_bit(qpc_mask->byte_76_srqn_op_en, + V2_QPC_BYTE_76_SRQ_EN_S, 0); + } + + roce_set_field(qpc_mask->byte_84_rq_ci_pi, + V2_QPC_BYTE_84_RQ_PRODUCER_IDX_M, + V2_QPC_BYTE_84_RQ_PRODUCER_IDX_S, 0); + roce_set_field(qpc_mask->byte_84_rq_ci_pi, + V2_QPC_BYTE_84_RQ_CONSUMER_IDX_M, + V2_QPC_BYTE_84_RQ_CONSUMER_IDX_S, 0); + + roce_set_field(qpc_mask->byte_92_srq_info, V2_QPC_BYTE_92_SRQ_INFO_M, + V2_QPC_BYTE_92_SRQ_INFO_S, 0); + + roce_set_field(qpc_mask->byte_96_rx_reqmsn, V2_QPC_BYTE_96_RX_REQ_MSN_M, + V2_QPC_BYTE_96_RX_REQ_MSN_S, 0); + + roce_set_field(qpc_mask->byte_104_rq_sge, + V2_QPC_BYTE_104_RQ_CUR_WQE_SGE_NUM_M, + V2_QPC_BYTE_104_RQ_CUR_WQE_SGE_NUM_S, 0); + + roce_set_bit(qpc_mask->byte_108_rx_reqepsn, + V2_QPC_BYTE_108_RX_REQ_PSN_ERR_S, 0); + roce_set_field(qpc_mask->byte_108_rx_reqepsn, + V2_QPC_BYTE_108_RX_REQ_LAST_OPTYPE_M, + V2_QPC_BYTE_108_RX_REQ_LAST_OPTYPE_S, 0); + roce_set_bit(qpc_mask->byte_108_rx_reqepsn, + V2_QPC_BYTE_108_RX_REQ_RNR_S, 0); + + qpc_mask->rq_rnr_timer = 0; + qpc_mask->rx_msg_len = 0; + qpc_mask->rx_rkey_pkt_info = 0; + qpc_mask->rx_va = 0; + + roce_set_field(qpc_mask->byte_132_trrl, V2_QPC_BYTE_132_TRRL_HEAD_MAX_M, + V2_QPC_BYTE_132_TRRL_HEAD_MAX_S, 0); + roce_set_field(qpc_mask->byte_132_trrl, V2_QPC_BYTE_132_TRRL_TAIL_MAX_M, + V2_QPC_BYTE_132_TRRL_TAIL_MAX_S, 0); + + roce_set_bit(qpc_mask->byte_140_raq, V2_QPC_BYTE_140_RSVD_RAQ_MAP_S, 0); + roce_set_field(qpc_mask->byte_140_raq, V2_QPC_BYTE_140_RAQ_TRRL_HEAD_M, + V2_QPC_BYTE_140_RAQ_TRRL_HEAD_S, 0); + roce_set_field(qpc_mask->byte_140_raq, V2_QPC_BYTE_140_RAQ_TRRL_TAIL_M, + V2_QPC_BYTE_140_RAQ_TRRL_TAIL_S, 0); + + roce_set_field(qpc_mask->byte_144_raq, + V2_QPC_BYTE_144_RAQ_RTY_INI_PSN_M, + V2_QPC_BYTE_144_RAQ_RTY_INI_PSN_S, 0); + roce_set_bit(qpc_mask->byte_144_raq, V2_QPC_BYTE_144_RAQ_RTY_INI_IND_S, + 0); + roce_set_field(qpc_mask->byte_144_raq, V2_QPC_BYTE_144_RAQ_CREDIT_M, + V2_QPC_BYTE_144_RAQ_CREDIT_S, 0); + roce_set_bit(qpc_mask->byte_144_raq, V2_QPC_BYTE_144_RESP_RTY_FLG_S, 0); + + roce_set_field(qpc_mask->byte_148_raq, V2_QPC_BYTE_148_RQ_MSN_M, + V2_QPC_BYTE_148_RQ_MSN_S, 0); + roce_set_field(qpc_mask->byte_148_raq, V2_QPC_BYTE_148_RAQ_SYNDROME_M, + V2_QPC_BYTE_148_RAQ_SYNDROME_S, 0); + + roce_set_field(qpc_mask->byte_152_raq, V2_QPC_BYTE_152_RAQ_PSN_M, + V2_QPC_BYTE_152_RAQ_PSN_S, 0); + roce_set_field(qpc_mask->byte_152_raq, + V2_QPC_BYTE_152_RAQ_TRRL_RTY_HEAD_M, + V2_QPC_BYTE_152_RAQ_TRRL_RTY_HEAD_S, 0); + + roce_set_field(qpc_mask->byte_156_raq, V2_QPC_BYTE_156_RAQ_USE_PKTN_M, + V2_QPC_BYTE_156_RAQ_USE_PKTN_S, 0); + + roce_set_field(qpc_mask->byte_160_sq_ci_pi, + V2_QPC_BYTE_160_SQ_PRODUCER_IDX_M, + V2_QPC_BYTE_160_SQ_PRODUCER_IDX_S, 0); + roce_set_field(qpc_mask->byte_160_sq_ci_pi, + V2_QPC_BYTE_160_SQ_CONSUMER_IDX_M, + V2_QPC_BYTE_160_SQ_CONSUMER_IDX_S, 0); + + roce_set_field(context->byte_168_irrl_idx, + V2_QPC_BYTE_168_SQ_SHIFT_BAK_M, + V2_QPC_BYTE_168_SQ_SHIFT_BAK_S, + ilog2((unsigned int)hr_qp->sq.wqe_cnt)); + roce_set_field(qpc_mask->byte_168_irrl_idx, + V2_QPC_BYTE_168_SQ_SHIFT_BAK_M, + V2_QPC_BYTE_168_SQ_SHIFT_BAK_S, 0); + + roce_set_bit(qpc_mask->byte_168_irrl_idx, + V2_QPC_BYTE_168_MSG_RTY_LP_FLG_S, 0); + roce_set_field(qpc_mask->byte_168_irrl_idx, + V2_QPC_BYTE_168_IRRL_IDX_LSB_M, + V2_QPC_BYTE_168_IRRL_IDX_LSB_S, 0); + + roce_set_field(context->byte_172_sq_psn, V2_QPC_BYTE_172_ACK_REQ_FREQ_M, + V2_QPC_BYTE_172_ACK_REQ_FREQ_S, 4); + roce_set_field(qpc_mask->byte_172_sq_psn, + V2_QPC_BYTE_172_ACK_REQ_FREQ_M, + V2_QPC_BYTE_172_ACK_REQ_FREQ_S, 0); + + roce_set_bit(qpc_mask->byte_172_sq_psn, V2_QPC_BYTE_172_MSG_RNR_FLG_S, + 0); + + roce_set_field(qpc_mask->byte_176_msg_pktn, + V2_QPC_BYTE_176_MSG_USE_PKTN_M, + V2_QPC_BYTE_176_MSG_USE_PKTN_S, 0); + roce_set_field(qpc_mask->byte_176_msg_pktn, + V2_QPC_BYTE_176_IRRL_HEAD_PRE_M, + V2_QPC_BYTE_176_IRRL_HEAD_PRE_S, 0); + + roce_set_field(qpc_mask->byte_184_irrl_idx, + V2_QPC_BYTE_184_IRRL_IDX_MSB_M, + V2_QPC_BYTE_184_IRRL_IDX_MSB_S, 0); + + qpc_mask->cur_sge_offset = 0; + + roce_set_field(qpc_mask->byte_192_ext_sge, + V2_QPC_BYTE_192_CUR_SGE_IDX_M, + V2_QPC_BYTE_192_CUR_SGE_IDX_S, 0); + roce_set_field(qpc_mask->byte_192_ext_sge, + V2_QPC_BYTE_192_EXT_SGE_NUM_LEFT_M, + V2_QPC_BYTE_192_EXT_SGE_NUM_LEFT_S, 0); + + roce_set_field(qpc_mask->byte_196_sq_psn, V2_QPC_BYTE_196_IRRL_HEAD_M, + V2_QPC_BYTE_196_IRRL_HEAD_S, 0); + + roce_set_field(qpc_mask->byte_200_sq_max, V2_QPC_BYTE_200_SQ_MAX_IDX_M, + V2_QPC_BYTE_200_SQ_MAX_IDX_S, 0); + roce_set_field(qpc_mask->byte_200_sq_max, + V2_QPC_BYTE_200_LCL_OPERATED_CNT_M, + V2_QPC_BYTE_200_LCL_OPERATED_CNT_S, 0); + + roce_set_bit(qpc_mask->byte_208_irrl, V2_QPC_BYTE_208_PKT_RNR_FLG_S, 0); + roce_set_bit(qpc_mask->byte_208_irrl, V2_QPC_BYTE_208_PKT_RTY_FLG_S, 0); + + roce_set_field(qpc_mask->byte_212_lsn, V2_QPC_BYTE_212_CHECK_FLG_M, + V2_QPC_BYTE_212_CHECK_FLG_S, 0); + + qpc_mask->sq_timer = 0; + + roce_set_field(qpc_mask->byte_220_retry_psn_msn, + V2_QPC_BYTE_220_RETRY_MSG_MSN_M, + V2_QPC_BYTE_220_RETRY_MSG_MSN_S, 0); + roce_set_field(qpc_mask->byte_232_irrl_sge, + V2_QPC_BYTE_232_IRRL_SGE_IDX_M, + V2_QPC_BYTE_232_IRRL_SGE_IDX_S, 0); + + qpc_mask->irrl_cur_sge_offset = 0; + + roce_set_field(qpc_mask->byte_240_irrl_tail, + V2_QPC_BYTE_240_IRRL_TAIL_REAL_M, + V2_QPC_BYTE_240_IRRL_TAIL_REAL_S, 0); + roce_set_field(qpc_mask->byte_240_irrl_tail, + V2_QPC_BYTE_240_IRRL_TAIL_RD_M, + V2_QPC_BYTE_240_IRRL_TAIL_RD_S, 0); + roce_set_field(qpc_mask->byte_240_irrl_tail, + V2_QPC_BYTE_240_RX_ACK_MSN_M, + V2_QPC_BYTE_240_RX_ACK_MSN_S, 0); + + roce_set_field(qpc_mask->byte_248_ack_psn, V2_QPC_BYTE_248_IRRL_PSN_M, + V2_QPC_BYTE_248_IRRL_PSN_S, 0); + roce_set_bit(qpc_mask->byte_248_ack_psn, V2_QPC_BYTE_248_ACK_PSN_ERR_S, + 0); + roce_set_field(qpc_mask->byte_248_ack_psn, + V2_QPC_BYTE_248_ACK_LAST_OPTYPE_M, + V2_QPC_BYTE_248_ACK_LAST_OPTYPE_S, 0); + roce_set_bit(qpc_mask->byte_248_ack_psn, V2_QPC_BYTE_248_IRRL_PSN_VLD_S, + 0); + roce_set_bit(qpc_mask->byte_248_ack_psn, + V2_QPC_BYTE_248_RNR_RETRY_FLAG_S, 0); + roce_set_bit(qpc_mask->byte_248_ack_psn, V2_QPC_BYTE_248_CQ_ERR_IND_S, + 0); + + hr_qp->access_flags = attr->qp_access_flags; + hr_qp->pkey_index = attr->pkey_index; + roce_set_field(context->byte_252_err_txcqn, V2_QPC_BYTE_252_TX_CQN_M, + V2_QPC_BYTE_252_TX_CQN_S, to_hr_cq(ibqp->send_cq)->cqn); + roce_set_field(qpc_mask->byte_252_err_txcqn, V2_QPC_BYTE_252_TX_CQN_M, + V2_QPC_BYTE_252_TX_CQN_S, 0); + + roce_set_field(qpc_mask->byte_252_err_txcqn, V2_QPC_BYTE_252_ERR_TYPE_M, + V2_QPC_BYTE_252_ERR_TYPE_S, 0); + + roce_set_field(qpc_mask->byte_256_sqflush_rqcqe, + V2_QPC_BYTE_256_RQ_CQE_IDX_M, + V2_QPC_BYTE_256_RQ_CQE_IDX_S, 0); + roce_set_field(qpc_mask->byte_256_sqflush_rqcqe, + V2_QPC_BYTE_256_SQ_FLUSH_IDX_M, + V2_QPC_BYTE_256_SQ_FLUSH_IDX_S, 0); +} + +static void modify_qp_init_to_init(struct ib_qp *ibqp, + const struct ib_qp_attr *attr, int attr_mask, + struct hns_roce_v2_qp_context *context, + struct hns_roce_v2_qp_context *qpc_mask) +{ + struct hns_roce_qp *hr_qp = to_hr_qp(ibqp); + + /* + * In v2 engine, software pass context and context mask to hardware + * when modifying qp. If software need modify some fields in context, + * we should set all bits of the relevant fields in context mask to + * 0 at the same time, else set them to 0x1. + */ + roce_set_field(context->byte_4_sqpn_tst, V2_QPC_BYTE_4_TST_M, + V2_QPC_BYTE_4_TST_S, to_hr_qp_type(hr_qp->ibqp.qp_type)); + roce_set_field(qpc_mask->byte_4_sqpn_tst, V2_QPC_BYTE_4_TST_M, + V2_QPC_BYTE_4_TST_S, 0); + + roce_set_field(context->byte_4_sqpn_tst, V2_QPC_BYTE_4_SGE_SHIFT_M, + V2_QPC_BYTE_4_SGE_SHIFT_S, hr_qp->sq.max_gs > 2 ? + ilog2((unsigned int)hr_qp->sge.sge_cnt) : 0); + roce_set_field(qpc_mask->byte_4_sqpn_tst, V2_QPC_BYTE_4_SGE_SHIFT_M, + V2_QPC_BYTE_4_SGE_SHIFT_S, 0); + + if (attr_mask & IB_QP_ACCESS_FLAGS) { + roce_set_bit(context->byte_76_srqn_op_en, V2_QPC_BYTE_76_RRE_S, + !!(attr->qp_access_flags & IB_ACCESS_REMOTE_READ)); + roce_set_bit(qpc_mask->byte_76_srqn_op_en, V2_QPC_BYTE_76_RRE_S, + 0); + + roce_set_bit(context->byte_76_srqn_op_en, V2_QPC_BYTE_76_RWE_S, + !!(attr->qp_access_flags & + IB_ACCESS_REMOTE_WRITE)); + roce_set_bit(qpc_mask->byte_76_srqn_op_en, V2_QPC_BYTE_76_RWE_S, + 0); + + roce_set_bit(context->byte_76_srqn_op_en, V2_QPC_BYTE_76_ATE_S, + !!(attr->qp_access_flags & + IB_ACCESS_REMOTE_ATOMIC)); + roce_set_bit(qpc_mask->byte_76_srqn_op_en, V2_QPC_BYTE_76_ATE_S, + 0); + } else { + roce_set_bit(context->byte_76_srqn_op_en, V2_QPC_BYTE_76_RRE_S, + !!(hr_qp->access_flags & IB_ACCESS_REMOTE_READ)); + roce_set_bit(qpc_mask->byte_76_srqn_op_en, V2_QPC_BYTE_76_RRE_S, + 0); + + roce_set_bit(context->byte_76_srqn_op_en, V2_QPC_BYTE_76_RWE_S, + !!(hr_qp->access_flags & IB_ACCESS_REMOTE_WRITE)); + roce_set_bit(qpc_mask->byte_76_srqn_op_en, V2_QPC_BYTE_76_RWE_S, + 0); + + roce_set_bit(context->byte_76_srqn_op_en, V2_QPC_BYTE_76_ATE_S, + !!(hr_qp->access_flags & IB_ACCESS_REMOTE_ATOMIC)); + roce_set_bit(qpc_mask->byte_76_srqn_op_en, V2_QPC_BYTE_76_ATE_S, + 0); + } + + roce_set_field(context->byte_20_smac_sgid_idx, + V2_QPC_BYTE_20_SQ_SHIFT_M, V2_QPC_BYTE_20_SQ_SHIFT_S, + ilog2((unsigned int)hr_qp->sq.wqe_cnt)); + roce_set_field(qpc_mask->byte_20_smac_sgid_idx, + V2_QPC_BYTE_20_SQ_SHIFT_M, V2_QPC_BYTE_20_SQ_SHIFT_S, 0); + + roce_set_field(context->byte_20_smac_sgid_idx, + V2_QPC_BYTE_20_RQ_SHIFT_M, V2_QPC_BYTE_20_RQ_SHIFT_S, + ilog2((unsigned int)hr_qp->rq.wqe_cnt)); + roce_set_field(qpc_mask->byte_20_smac_sgid_idx, + V2_QPC_BYTE_20_RQ_SHIFT_M, V2_QPC_BYTE_20_RQ_SHIFT_S, 0); + + roce_set_field(context->byte_16_buf_ba_pg_sz, V2_QPC_BYTE_16_PD_M, + V2_QPC_BYTE_16_PD_S, to_hr_pd(ibqp->pd)->pdn); + roce_set_field(qpc_mask->byte_16_buf_ba_pg_sz, V2_QPC_BYTE_16_PD_M, + V2_QPC_BYTE_16_PD_S, 0); + + roce_set_field(context->byte_80_rnr_rx_cqn, V2_QPC_BYTE_80_RX_CQN_M, + V2_QPC_BYTE_80_RX_CQN_S, to_hr_cq(ibqp->recv_cq)->cqn); + roce_set_field(qpc_mask->byte_80_rnr_rx_cqn, V2_QPC_BYTE_80_RX_CQN_M, + V2_QPC_BYTE_80_RX_CQN_S, 0); + + roce_set_field(context->byte_252_err_txcqn, V2_QPC_BYTE_252_TX_CQN_M, + V2_QPC_BYTE_252_TX_CQN_S, to_hr_cq(ibqp->recv_cq)->cqn); + roce_set_field(qpc_mask->byte_252_err_txcqn, V2_QPC_BYTE_252_TX_CQN_M, + V2_QPC_BYTE_252_TX_CQN_S, 0); + + if (ibqp->srq) { + roce_set_bit(context->byte_76_srqn_op_en, + V2_QPC_BYTE_76_SRQ_EN_S, 1); + roce_set_bit(qpc_mask->byte_76_srqn_op_en, + V2_QPC_BYTE_76_SRQ_EN_S, 0); + roce_set_field(context->byte_76_srqn_op_en, + V2_QPC_BYTE_76_SRQN_M, V2_QPC_BYTE_76_SRQN_S, + to_hr_srq(ibqp->srq)->srqn); + roce_set_field(qpc_mask->byte_76_srqn_op_en, + V2_QPC_BYTE_76_SRQN_M, V2_QPC_BYTE_76_SRQN_S, 0); + } + + if (attr_mask & IB_QP_PKEY_INDEX) + context->qkey_xrcd = attr->pkey_index; + else + context->qkey_xrcd = hr_qp->pkey_index; + + roce_set_field(context->byte_4_sqpn_tst, V2_QPC_BYTE_4_SQPN_M, + V2_QPC_BYTE_4_SQPN_S, hr_qp->qpn); + roce_set_field(qpc_mask->byte_4_sqpn_tst, V2_QPC_BYTE_4_SQPN_M, + V2_QPC_BYTE_4_SQPN_S, 0); + + roce_set_field(context->byte_56_dqpn_err, V2_QPC_BYTE_56_DQPN_M, + V2_QPC_BYTE_56_DQPN_S, hr_qp->qpn); + roce_set_field(qpc_mask->byte_56_dqpn_err, V2_QPC_BYTE_56_DQPN_M, + V2_QPC_BYTE_56_DQPN_S, 0); + roce_set_field(context->byte_168_irrl_idx, + V2_QPC_BYTE_168_SQ_SHIFT_BAK_M, + V2_QPC_BYTE_168_SQ_SHIFT_BAK_S, + ilog2((unsigned int)hr_qp->sq.wqe_cnt)); + roce_set_field(qpc_mask->byte_168_irrl_idx, + V2_QPC_BYTE_168_SQ_SHIFT_BAK_M, + V2_QPC_BYTE_168_SQ_SHIFT_BAK_S, 0); +} + +static int modify_qp_init_to_rtr(struct ib_qp *ibqp, + const struct ib_qp_attr *attr, int attr_mask, + struct hns_roce_v2_qp_context *context, + struct hns_roce_v2_qp_context *qpc_mask) +{ + const struct ib_global_route *grh = rdma_ah_read_grh(&attr->ah_attr); + struct hns_roce_dev *hr_dev = to_hr_dev(ibqp->device); + struct hns_roce_qp *hr_qp = to_hr_qp(ibqp); + struct device *dev = hr_dev->dev; + dma_addr_t dma_handle_2; + dma_addr_t dma_handle; + u32 page_size; + u8 port_num; + u64 *mtts_2; + u64 *mtts; + u8 *dmac; + u8 *smac; + int port; + + /* Search qp buf's mtts */ + mtts = hns_roce_table_find(hr_dev, &hr_dev->mr_table.mtt_table, + hr_qp->mtt.first_seg, &dma_handle); + if (!mtts) { + dev_err(dev, "qp buf pa find failed\n"); + return -EINVAL; + } + + /* Search IRRL's mtts */ + mtts_2 = hns_roce_table_find(hr_dev, &hr_dev->qp_table.irrl_table, + hr_qp->qpn, &dma_handle_2); + if (!mtts_2) { + dev_err(dev, "qp irrl_table find failed\n"); + return -EINVAL; + } + + if ((attr_mask & IB_QP_ALT_PATH) || (attr_mask & IB_QP_ACCESS_FLAGS) || + (attr_mask & IB_QP_PKEY_INDEX) || (attr_mask & IB_QP_QKEY)) { + dev_err(dev, "INIT2RTR attr_mask (0x%x) error\n", attr_mask); + return -EINVAL; + } + + dmac = (u8 *)attr->ah_attr.roce.dmac; + context->wqe_sge_ba = (u32)(dma_handle >> 3); + qpc_mask->wqe_sge_ba = 0; + + /* + * In v2 engine, software pass context and context mask to hardware + * when modifying qp. If software need modify some fields in context, + * we should set all bits of the relevant fields in context mask to + * 0 at the same time, else set them to 0x1. + */ + roce_set_field(context->byte_12_sq_hop, V2_QPC_BYTE_12_WQE_SGE_BA_M, + V2_QPC_BYTE_12_WQE_SGE_BA_S, dma_handle >> (32 + 3)); + roce_set_field(qpc_mask->byte_12_sq_hop, V2_QPC_BYTE_12_WQE_SGE_BA_M, + V2_QPC_BYTE_12_WQE_SGE_BA_S, 0); + + roce_set_field(context->byte_12_sq_hop, V2_QPC_BYTE_12_SQ_HOP_NUM_M, + V2_QPC_BYTE_12_SQ_HOP_NUM_S, + hr_dev->caps.mtt_hop_num == HNS_ROCE_HOP_NUM_0 ? + 0 : hr_dev->caps.mtt_hop_num); + roce_set_field(qpc_mask->byte_12_sq_hop, V2_QPC_BYTE_12_SQ_HOP_NUM_M, + V2_QPC_BYTE_12_SQ_HOP_NUM_S, 0); + + roce_set_field(context->byte_20_smac_sgid_idx, + V2_QPC_BYTE_20_SGE_HOP_NUM_M, + V2_QPC_BYTE_20_SGE_HOP_NUM_S, + hr_qp->sq.max_gs > 2 ? hr_dev->caps.mtt_hop_num : 0); + roce_set_field(qpc_mask->byte_20_smac_sgid_idx, + V2_QPC_BYTE_20_SGE_HOP_NUM_M, + V2_QPC_BYTE_20_SGE_HOP_NUM_S, 0); + + roce_set_field(context->byte_20_smac_sgid_idx, + V2_QPC_BYTE_20_RQ_HOP_NUM_M, + V2_QPC_BYTE_20_RQ_HOP_NUM_S, + hr_dev->caps.mtt_hop_num == HNS_ROCE_HOP_NUM_0 ? + 0 : hr_dev->caps.mtt_hop_num); + roce_set_field(qpc_mask->byte_20_smac_sgid_idx, + V2_QPC_BYTE_20_RQ_HOP_NUM_M, + V2_QPC_BYTE_20_RQ_HOP_NUM_S, 0); + + roce_set_field(context->byte_16_buf_ba_pg_sz, + V2_QPC_BYTE_16_WQE_SGE_BA_PG_SZ_M, + V2_QPC_BYTE_16_WQE_SGE_BA_PG_SZ_S, + hr_dev->caps.mtt_ba_pg_sz); + roce_set_field(qpc_mask->byte_16_buf_ba_pg_sz, + V2_QPC_BYTE_16_WQE_SGE_BA_PG_SZ_M, + V2_QPC_BYTE_16_WQE_SGE_BA_PG_SZ_S, 0); + + roce_set_field(context->byte_16_buf_ba_pg_sz, + V2_QPC_BYTE_16_WQE_SGE_BUF_PG_SZ_M, + V2_QPC_BYTE_16_WQE_SGE_BUF_PG_SZ_S, + hr_dev->caps.mtt_buf_pg_sz); + roce_set_field(qpc_mask->byte_16_buf_ba_pg_sz, + V2_QPC_BYTE_16_WQE_SGE_BUF_PG_SZ_M, + V2_QPC_BYTE_16_WQE_SGE_BUF_PG_SZ_S, 0); + + roce_set_field(context->byte_80_rnr_rx_cqn, + V2_QPC_BYTE_80_MIN_RNR_TIME_M, + V2_QPC_BYTE_80_MIN_RNR_TIME_S, attr->min_rnr_timer); + roce_set_field(qpc_mask->byte_80_rnr_rx_cqn, + V2_QPC_BYTE_80_MIN_RNR_TIME_M, + V2_QPC_BYTE_80_MIN_RNR_TIME_S, 0); + + page_size = 1 << (hr_dev->caps.mtt_buf_pg_sz + PAGE_SHIFT); + context->rq_cur_blk_addr = (u32)(mtts[hr_qp->rq.offset / page_size] + >> PAGE_ADDR_SHIFT); + qpc_mask->rq_cur_blk_addr = 0; + + roce_set_field(context->byte_92_srq_info, + V2_QPC_BYTE_92_RQ_CUR_BLK_ADDR_M, + V2_QPC_BYTE_92_RQ_CUR_BLK_ADDR_S, + mtts[hr_qp->rq.offset / page_size] + >> (32 + PAGE_ADDR_SHIFT)); + roce_set_field(qpc_mask->byte_92_srq_info, + V2_QPC_BYTE_92_RQ_CUR_BLK_ADDR_M, + V2_QPC_BYTE_92_RQ_CUR_BLK_ADDR_S, 0); + + context->rq_nxt_blk_addr = (u32)(mtts[hr_qp->rq.offset / page_size + 1] + >> PAGE_ADDR_SHIFT); + qpc_mask->rq_nxt_blk_addr = 0; + + roce_set_field(context->byte_104_rq_sge, + V2_QPC_BYTE_104_RQ_NXT_BLK_ADDR_M, + V2_QPC_BYTE_104_RQ_NXT_BLK_ADDR_S, + mtts[hr_qp->rq.offset / page_size + 1] + >> (32 + PAGE_ADDR_SHIFT)); + roce_set_field(qpc_mask->byte_104_rq_sge, + V2_QPC_BYTE_104_RQ_NXT_BLK_ADDR_M, + V2_QPC_BYTE_104_RQ_NXT_BLK_ADDR_S, 0); + + roce_set_field(context->byte_108_rx_reqepsn, + V2_QPC_BYTE_108_RX_REQ_EPSN_M, + V2_QPC_BYTE_108_RX_REQ_EPSN_S, attr->rq_psn); + roce_set_field(qpc_mask->byte_108_rx_reqepsn, + V2_QPC_BYTE_108_RX_REQ_EPSN_M, + V2_QPC_BYTE_108_RX_REQ_EPSN_S, 0); + + context->irrl_ba = (u32)dma_handle_2; + qpc_mask->irrl_ba = 0; + roce_set_field(context->byte_208_irrl, V2_QPC_BYTE_208_IRRL_BA_M, + V2_QPC_BYTE_208_IRRL_BA_S, + (dma_handle_2 >> 32) & V2_QPC_BYTE_208_IRRL_BA_M); + roce_set_field(qpc_mask->byte_208_irrl, V2_QPC_BYTE_208_IRRL_BA_M, + V2_QPC_BYTE_208_IRRL_BA_S, 0); + + roce_set_bit(context->byte_208_irrl, V2_QPC_BYTE_208_RMT_E2E_S, 1); + roce_set_bit(qpc_mask->byte_208_irrl, V2_QPC_BYTE_208_RMT_E2E_S, 0); + + roce_set_bit(context->byte_252_err_txcqn, V2_QPC_BYTE_252_SIG_TYPE_S, + hr_qp->sq_signal_bits); + roce_set_bit(qpc_mask->byte_252_err_txcqn, V2_QPC_BYTE_252_SIG_TYPE_S, + 0); + + port = (attr_mask & IB_QP_PORT) ? (attr->port_num - 1) : hr_qp->port; + + smac = (u8 *)hr_dev->dev_addr[port]; + /* when dmac equals smac or loop_idc is 1, it should loopback */ + if (ether_addr_equal_unaligned(dmac, smac) || + hr_dev->loop_idc == 0x1) { + roce_set_bit(context->byte_28_at_fl, V2_QPC_BYTE_28_LBI_S, 1); + roce_set_bit(qpc_mask->byte_28_at_fl, V2_QPC_BYTE_28_LBI_S, 0); + } + + roce_set_field(context->byte_140_raq, V2_QPC_BYTE_140_RR_MAX_M, + V2_QPC_BYTE_140_RR_MAX_S, + ilog2((unsigned int)attr->max_dest_rd_atomic)); + roce_set_field(qpc_mask->byte_140_raq, V2_QPC_BYTE_140_RR_MAX_M, + V2_QPC_BYTE_140_RR_MAX_S, 0); + + roce_set_field(context->byte_56_dqpn_err, V2_QPC_BYTE_56_DQPN_M, + V2_QPC_BYTE_56_DQPN_S, attr->dest_qp_num); + roce_set_field(qpc_mask->byte_56_dqpn_err, V2_QPC_BYTE_56_DQPN_M, + V2_QPC_BYTE_56_DQPN_S, 0); + + /* Configure GID index */ + port_num = rdma_ah_get_port_num(&attr->ah_attr); + roce_set_field(context->byte_20_smac_sgid_idx, + V2_QPC_BYTE_20_SGID_IDX_M, + V2_QPC_BYTE_20_SGID_IDX_S, + hns_get_gid_index(hr_dev, port_num - 1, + grh->sgid_index)); + roce_set_field(qpc_mask->byte_20_smac_sgid_idx, + V2_QPC_BYTE_20_SGID_IDX_M, + V2_QPC_BYTE_20_SGID_IDX_S, 0); + memcpy(&(context->dmac), dmac, 4); + roce_set_field(context->byte_52_udpspn_dmac, V2_QPC_BYTE_52_DMAC_M, + V2_QPC_BYTE_52_DMAC_S, *((u16 *)(&dmac[4]))); + qpc_mask->dmac = 0; + roce_set_field(qpc_mask->byte_52_udpspn_dmac, V2_QPC_BYTE_52_DMAC_M, + V2_QPC_BYTE_52_DMAC_S, 0); + + roce_set_field(context->byte_56_dqpn_err, V2_QPC_BYTE_56_LP_PKTN_INI_M, + V2_QPC_BYTE_56_LP_PKTN_INI_S, 4); + roce_set_field(qpc_mask->byte_56_dqpn_err, V2_QPC_BYTE_56_LP_PKTN_INI_M, + V2_QPC_BYTE_56_LP_PKTN_INI_S, 0); + + roce_set_field(context->byte_24_mtu_tc, V2_QPC_BYTE_24_HOP_LIMIT_M, + V2_QPC_BYTE_24_HOP_LIMIT_S, grh->hop_limit); + roce_set_field(qpc_mask->byte_24_mtu_tc, V2_QPC_BYTE_24_HOP_LIMIT_M, + V2_QPC_BYTE_24_HOP_LIMIT_S, 0); + + roce_set_field(context->byte_28_at_fl, V2_QPC_BYTE_28_FL_M, + V2_QPC_BYTE_28_FL_S, grh->flow_label); + roce_set_field(qpc_mask->byte_28_at_fl, V2_QPC_BYTE_28_FL_M, + V2_QPC_BYTE_28_FL_S, 0); + + roce_set_field(context->byte_24_mtu_tc, V2_QPC_BYTE_24_TC_M, + V2_QPC_BYTE_24_TC_S, grh->traffic_class); + roce_set_field(qpc_mask->byte_24_mtu_tc, V2_QPC_BYTE_24_TC_M, + V2_QPC_BYTE_24_TC_S, 0); + + roce_set_field(context->byte_24_mtu_tc, V2_QPC_BYTE_24_MTU_M, + V2_QPC_BYTE_24_MTU_S, attr->path_mtu); + roce_set_field(qpc_mask->byte_24_mtu_tc, V2_QPC_BYTE_24_MTU_M, + V2_QPC_BYTE_24_MTU_S, 0); + + memcpy(context->dgid, grh->dgid.raw, sizeof(grh->dgid.raw)); + memset(qpc_mask->dgid, 0, sizeof(grh->dgid.raw)); + + roce_set_field(context->byte_84_rq_ci_pi, + V2_QPC_BYTE_84_RQ_PRODUCER_IDX_M, + V2_QPC_BYTE_84_RQ_PRODUCER_IDX_S, hr_qp->rq.head); + roce_set_field(qpc_mask->byte_84_rq_ci_pi, + V2_QPC_BYTE_84_RQ_PRODUCER_IDX_M, + V2_QPC_BYTE_84_RQ_PRODUCER_IDX_S, 0); + + roce_set_field(qpc_mask->byte_84_rq_ci_pi, + V2_QPC_BYTE_84_RQ_CONSUMER_IDX_M, + V2_QPC_BYTE_84_RQ_CONSUMER_IDX_S, 0); + roce_set_bit(qpc_mask->byte_108_rx_reqepsn, + V2_QPC_BYTE_108_RX_REQ_PSN_ERR_S, 0); + roce_set_field(qpc_mask->byte_96_rx_reqmsn, V2_QPC_BYTE_96_RX_REQ_MSN_M, + V2_QPC_BYTE_96_RX_REQ_MSN_S, 0); + roce_set_field(qpc_mask->byte_108_rx_reqepsn, + V2_QPC_BYTE_108_RX_REQ_LAST_OPTYPE_M, + V2_QPC_BYTE_108_RX_REQ_LAST_OPTYPE_S, 0); + + context->rq_rnr_timer = 0; + qpc_mask->rq_rnr_timer = 0; + + roce_set_field(context->byte_152_raq, V2_QPC_BYTE_152_RAQ_PSN_M, + V2_QPC_BYTE_152_RAQ_PSN_S, attr->rq_psn - 1); + roce_set_field(qpc_mask->byte_152_raq, V2_QPC_BYTE_152_RAQ_PSN_M, + V2_QPC_BYTE_152_RAQ_PSN_S, 0); + + roce_set_field(qpc_mask->byte_132_trrl, V2_QPC_BYTE_132_TRRL_HEAD_MAX_M, + V2_QPC_BYTE_132_TRRL_HEAD_MAX_S, 0); + roce_set_field(qpc_mask->byte_132_trrl, V2_QPC_BYTE_132_TRRL_TAIL_MAX_M, + V2_QPC_BYTE_132_TRRL_TAIL_MAX_S, 0); + + roce_set_field(context->byte_168_irrl_idx, + V2_QPC_BYTE_168_LP_SGEN_INI_M, + V2_QPC_BYTE_168_LP_SGEN_INI_S, 3); + roce_set_field(qpc_mask->byte_168_irrl_idx, + V2_QPC_BYTE_168_LP_SGEN_INI_M, + V2_QPC_BYTE_168_LP_SGEN_INI_S, 0); + + roce_set_field(context->byte_208_irrl, V2_QPC_BYTE_208_SR_MAX_M, + V2_QPC_BYTE_208_SR_MAX_S, + ilog2((unsigned int)attr->max_rd_atomic)); + roce_set_field(qpc_mask->byte_208_irrl, V2_QPC_BYTE_208_SR_MAX_M, + V2_QPC_BYTE_208_SR_MAX_S, 0); + + roce_set_field(context->byte_28_at_fl, V2_QPC_BYTE_28_SL_M, + V2_QPC_BYTE_28_SL_S, rdma_ah_get_sl(&attr->ah_attr)); + roce_set_field(qpc_mask->byte_28_at_fl, V2_QPC_BYTE_28_SL_M, + V2_QPC_BYTE_28_SL_S, 0); + hr_qp->sl = rdma_ah_get_sl(&attr->ah_attr); + + return 0; +} + +static int modify_qp_rtr_to_rts(struct ib_qp *ibqp, + const struct ib_qp_attr *attr, int attr_mask, + struct hns_roce_v2_qp_context *context, + struct hns_roce_v2_qp_context *qpc_mask) +{ + struct hns_roce_dev *hr_dev = to_hr_dev(ibqp->device); + struct hns_roce_qp *hr_qp = to_hr_qp(ibqp); + struct device *dev = hr_dev->dev; + dma_addr_t dma_handle; + u64 *mtts; + + /* Search qp buf's mtts */ + mtts = hns_roce_table_find(hr_dev, &hr_dev->mr_table.mtt_table, + hr_qp->mtt.first_seg, &dma_handle); + if (!mtts) { + dev_err(dev, "qp buf pa find failed\n"); + return -EINVAL; + } + + /* If exist optional param, return error */ + if ((attr_mask & IB_QP_ALT_PATH) || (attr_mask & IB_QP_ACCESS_FLAGS) || + (attr_mask & IB_QP_QKEY) || (attr_mask & IB_QP_PATH_MIG_STATE) || + (attr_mask & IB_QP_CUR_STATE) || + (attr_mask & IB_QP_MIN_RNR_TIMER)) { + dev_err(dev, "RTR2RTS attr_mask (0x%x)error\n", attr_mask); + return -EINVAL; + } + + /* + * In v2 engine, software pass context and context mask to hardware + * when modifying qp. If software need modify some fields in context, + * we should set all bits of the relevant fields in context mask to + * 0 at the same time, else set them to 0x1. + */ + roce_set_field(context->byte_60_qpst_mapid, + V2_QPC_BYTE_60_RTY_NUM_INI_BAK_M, + V2_QPC_BYTE_60_RTY_NUM_INI_BAK_S, attr->retry_cnt); + roce_set_field(qpc_mask->byte_60_qpst_mapid, + V2_QPC_BYTE_60_RTY_NUM_INI_BAK_M, + V2_QPC_BYTE_60_RTY_NUM_INI_BAK_S, 0); + + context->sq_cur_blk_addr = (u32)(mtts[0] >> PAGE_ADDR_SHIFT); + roce_set_field(context->byte_168_irrl_idx, + V2_QPC_BYTE_168_SQ_CUR_BLK_ADDR_M, + V2_QPC_BYTE_168_SQ_CUR_BLK_ADDR_S, + mtts[0] >> (32 + PAGE_ADDR_SHIFT)); + qpc_mask->sq_cur_blk_addr = 0; + roce_set_field(qpc_mask->byte_168_irrl_idx, + V2_QPC_BYTE_168_SQ_CUR_BLK_ADDR_M, + V2_QPC_BYTE_168_SQ_CUR_BLK_ADDR_S, 0); + + context->rx_sq_cur_blk_addr = (u32)(mtts[0] >> PAGE_ADDR_SHIFT); + roce_set_field(context->byte_232_irrl_sge, + V2_QPC_BYTE_232_RX_SQ_CUR_BLK_ADDR_M, + V2_QPC_BYTE_232_RX_SQ_CUR_BLK_ADDR_S, + mtts[0] >> (32 + PAGE_ADDR_SHIFT)); + qpc_mask->rx_sq_cur_blk_addr = 0; + roce_set_field(qpc_mask->byte_232_irrl_sge, + V2_QPC_BYTE_232_RX_SQ_CUR_BLK_ADDR_M, + V2_QPC_BYTE_232_RX_SQ_CUR_BLK_ADDR_S, 0); + + /* + * Set some fields in context to zero, Because the default values + * of all fields in context are zero, we need not set them to 0 again. + * but we should set the relevant fields of context mask to 0. + */ + roce_set_field(qpc_mask->byte_232_irrl_sge, + V2_QPC_BYTE_232_IRRL_SGE_IDX_M, + V2_QPC_BYTE_232_IRRL_SGE_IDX_S, 0); + + roce_set_field(qpc_mask->byte_240_irrl_tail, + V2_QPC_BYTE_240_RX_ACK_MSN_M, + V2_QPC_BYTE_240_RX_ACK_MSN_S, 0); + + roce_set_field(context->byte_244_rnr_rxack, + V2_QPC_BYTE_244_RX_ACK_EPSN_M, + V2_QPC_BYTE_244_RX_ACK_EPSN_S, attr->sq_psn); + roce_set_field(qpc_mask->byte_244_rnr_rxack, + V2_QPC_BYTE_244_RX_ACK_EPSN_M, + V2_QPC_BYTE_244_RX_ACK_EPSN_S, 0); + + roce_set_field(qpc_mask->byte_248_ack_psn, + V2_QPC_BYTE_248_ACK_LAST_OPTYPE_M, + V2_QPC_BYTE_248_ACK_LAST_OPTYPE_S, 0); + roce_set_bit(qpc_mask->byte_248_ack_psn, + V2_QPC_BYTE_248_IRRL_PSN_VLD_S, 0); + roce_set_field(qpc_mask->byte_248_ack_psn, + V2_QPC_BYTE_248_IRRL_PSN_M, + V2_QPC_BYTE_248_IRRL_PSN_S, 0); + + roce_set_field(qpc_mask->byte_240_irrl_tail, + V2_QPC_BYTE_240_IRRL_TAIL_REAL_M, + V2_QPC_BYTE_240_IRRL_TAIL_REAL_S, 0); + + roce_set_field(context->byte_220_retry_psn_msn, + V2_QPC_BYTE_220_RETRY_MSG_PSN_M, + V2_QPC_BYTE_220_RETRY_MSG_PSN_S, attr->sq_psn); + roce_set_field(qpc_mask->byte_220_retry_psn_msn, + V2_QPC_BYTE_220_RETRY_MSG_PSN_M, + V2_QPC_BYTE_220_RETRY_MSG_PSN_S, 0); + + roce_set_field(context->byte_224_retry_msg, + V2_QPC_BYTE_224_RETRY_MSG_PSN_M, + V2_QPC_BYTE_224_RETRY_MSG_PSN_S, attr->sq_psn >> 16); + roce_set_field(qpc_mask->byte_224_retry_msg, + V2_QPC_BYTE_224_RETRY_MSG_PSN_M, + V2_QPC_BYTE_224_RETRY_MSG_PSN_S, 0); + + roce_set_field(context->byte_224_retry_msg, + V2_QPC_BYTE_224_RETRY_MSG_FPKT_PSN_M, + V2_QPC_BYTE_224_RETRY_MSG_FPKT_PSN_S, attr->sq_psn); + roce_set_field(qpc_mask->byte_224_retry_msg, + V2_QPC_BYTE_224_RETRY_MSG_FPKT_PSN_M, + V2_QPC_BYTE_224_RETRY_MSG_FPKT_PSN_S, 0); + + roce_set_field(qpc_mask->byte_220_retry_psn_msn, + V2_QPC_BYTE_220_RETRY_MSG_MSN_M, + V2_QPC_BYTE_220_RETRY_MSG_MSN_S, 0); + + roce_set_bit(qpc_mask->byte_248_ack_psn, + V2_QPC_BYTE_248_RNR_RETRY_FLAG_S, 0); + + roce_set_field(qpc_mask->byte_212_lsn, V2_QPC_BYTE_212_CHECK_FLG_M, + V2_QPC_BYTE_212_CHECK_FLG_S, 0); + + roce_set_field(context->byte_212_lsn, V2_QPC_BYTE_212_RETRY_CNT_M, + V2_QPC_BYTE_212_RETRY_CNT_S, attr->retry_cnt); + roce_set_field(qpc_mask->byte_212_lsn, V2_QPC_BYTE_212_RETRY_CNT_M, + V2_QPC_BYTE_212_RETRY_CNT_S, 0); + + roce_set_field(context->byte_212_lsn, V2_QPC_BYTE_212_RETRY_NUM_INIT_M, + V2_QPC_BYTE_212_RETRY_NUM_INIT_S, attr->retry_cnt); + roce_set_field(qpc_mask->byte_212_lsn, V2_QPC_BYTE_212_RETRY_NUM_INIT_M, + V2_QPC_BYTE_212_RETRY_NUM_INIT_S, 0); + + roce_set_field(context->byte_244_rnr_rxack, + V2_QPC_BYTE_244_RNR_NUM_INIT_M, + V2_QPC_BYTE_244_RNR_NUM_INIT_S, attr->rnr_retry); + roce_set_field(qpc_mask->byte_244_rnr_rxack, + V2_QPC_BYTE_244_RNR_NUM_INIT_M, + V2_QPC_BYTE_244_RNR_NUM_INIT_S, 0); + + roce_set_field(context->byte_244_rnr_rxack, V2_QPC_BYTE_244_RNR_CNT_M, + V2_QPC_BYTE_244_RNR_CNT_S, attr->rnr_retry); + roce_set_field(qpc_mask->byte_244_rnr_rxack, V2_QPC_BYTE_244_RNR_CNT_M, + V2_QPC_BYTE_244_RNR_CNT_S, 0); + + roce_set_field(context->byte_212_lsn, V2_QPC_BYTE_212_LSN_M, + V2_QPC_BYTE_212_LSN_S, 0x100); + roce_set_field(qpc_mask->byte_212_lsn, V2_QPC_BYTE_212_LSN_M, + V2_QPC_BYTE_212_LSN_S, 0); + + if (attr->timeout < 0xf) + roce_set_field(context->byte_28_at_fl, V2_QPC_BYTE_28_AT_M, + V2_QPC_BYTE_28_AT_S, 0xf); + else + roce_set_field(context->byte_28_at_fl, V2_QPC_BYTE_28_AT_M, + V2_QPC_BYTE_28_AT_S, attr->timeout); + + roce_set_field(qpc_mask->byte_28_at_fl, V2_QPC_BYTE_28_AT_M, + V2_QPC_BYTE_28_AT_S, 0); + + roce_set_field(context->byte_28_at_fl, V2_QPC_BYTE_28_SL_M, + V2_QPC_BYTE_28_SL_S, + rdma_ah_get_sl(&attr->ah_attr)); + roce_set_field(qpc_mask->byte_28_at_fl, V2_QPC_BYTE_28_SL_M, + V2_QPC_BYTE_28_SL_S, 0); + hr_qp->sl = rdma_ah_get_sl(&attr->ah_attr); + + roce_set_field(context->byte_172_sq_psn, V2_QPC_BYTE_172_SQ_CUR_PSN_M, + V2_QPC_BYTE_172_SQ_CUR_PSN_S, attr->sq_psn); + roce_set_field(qpc_mask->byte_172_sq_psn, V2_QPC_BYTE_172_SQ_CUR_PSN_M, + V2_QPC_BYTE_172_SQ_CUR_PSN_S, 0); + + roce_set_field(qpc_mask->byte_196_sq_psn, V2_QPC_BYTE_196_IRRL_HEAD_M, + V2_QPC_BYTE_196_IRRL_HEAD_S, 0); + roce_set_field(context->byte_196_sq_psn, V2_QPC_BYTE_196_SQ_MAX_PSN_M, + V2_QPC_BYTE_196_SQ_MAX_PSN_S, attr->sq_psn); + roce_set_field(qpc_mask->byte_196_sq_psn, V2_QPC_BYTE_196_SQ_MAX_PSN_M, + V2_QPC_BYTE_196_SQ_MAX_PSN_S, 0); + + return 0; +} + +static int hns_roce_v2_modify_qp(struct ib_qp *ibqp, + const struct ib_qp_attr *attr, + int attr_mask, enum ib_qp_state cur_state, + enum ib_qp_state new_state) +{ + struct hns_roce_dev *hr_dev = to_hr_dev(ibqp->device); + struct hns_roce_qp *hr_qp = to_hr_qp(ibqp); + struct hns_roce_v2_qp_context *context; + struct hns_roce_v2_qp_context *qpc_mask; + struct device *dev = hr_dev->dev; + int ret = -EINVAL; + + context = kzalloc(2 * sizeof(*context), GFP_KERNEL); + if (!context) + return -ENOMEM; + + qpc_mask = context + 1; + /* + * In v2 engine, software pass context and context mask to hardware + * when modifying qp. If software need modify some fields in context, + * we should set all bits of the relevant fields in context mask to + * 0 at the same time, else set them to 0x1. + */ + memset(qpc_mask, 0xff, sizeof(*qpc_mask)); + if (cur_state == IB_QPS_RESET && new_state == IB_QPS_INIT) { + modify_qp_reset_to_init(ibqp, attr, context, qpc_mask); + } else if (cur_state == IB_QPS_INIT && new_state == IB_QPS_INIT) { + modify_qp_init_to_init(ibqp, attr, attr_mask, context, + qpc_mask); + } else if (cur_state == IB_QPS_INIT && new_state == IB_QPS_RTR) { + ret = modify_qp_init_to_rtr(ibqp, attr, attr_mask, context, + qpc_mask); + if (ret) + goto out; + } else if (cur_state == IB_QPS_RTR && new_state == IB_QPS_RTS) { + ret = modify_qp_rtr_to_rts(ibqp, attr, attr_mask, context, + qpc_mask); + if (ret) + goto out; + } else if ((cur_state == IB_QPS_RTS && new_state == IB_QPS_RTS) || + (cur_state == IB_QPS_SQE && new_state == IB_QPS_RTS) || + (cur_state == IB_QPS_RTS && new_state == IB_QPS_SQD) || + (cur_state == IB_QPS_SQD && new_state == IB_QPS_SQD) || + (cur_state == IB_QPS_SQD && new_state == IB_QPS_RTS) || + (cur_state == IB_QPS_INIT && new_state == IB_QPS_RESET) || + (cur_state == IB_QPS_RTR && new_state == IB_QPS_RESET) || + (cur_state == IB_QPS_RTS && new_state == IB_QPS_RESET) || + (cur_state == IB_QPS_ERR && new_state == IB_QPS_RESET) || + (cur_state == IB_QPS_INIT && new_state == IB_QPS_ERR) || + (cur_state == IB_QPS_RTR && new_state == IB_QPS_ERR) || + (cur_state == IB_QPS_RTS && new_state == IB_QPS_ERR) || + (cur_state == IB_QPS_SQD && new_state == IB_QPS_ERR) || + (cur_state == IB_QPS_SQE && new_state == IB_QPS_ERR)) { + /* Nothing */ + ; + } else { + dev_err(dev, "Illegal state for QP!\n"); + goto out; + } + + /* Every status migrate must change state */ + roce_set_field(context->byte_60_qpst_mapid, V2_QPC_BYTE_60_QP_ST_M, + V2_QPC_BYTE_60_QP_ST_S, new_state); + roce_set_field(qpc_mask->byte_60_qpst_mapid, V2_QPC_BYTE_60_QP_ST_M, + V2_QPC_BYTE_60_QP_ST_S, 0); + + /* SW pass context to HW */ + ret = hns_roce_v2_qp_modify(hr_dev, &hr_qp->mtt, cur_state, new_state, + context, hr_qp); + if (ret) { + dev_err(dev, "hns_roce_qp_modify failed(%d)\n", ret); + goto out; + } + + hr_qp->state = new_state; + + if (attr_mask & IB_QP_MAX_DEST_RD_ATOMIC) + hr_qp->resp_depth = attr->max_dest_rd_atomic; + if (attr_mask & IB_QP_PORT) { + hr_qp->port = attr->port_num - 1; + hr_qp->phy_port = hr_dev->iboe.phy_port[hr_qp->port]; + } + + if (new_state == IB_QPS_RESET && !ibqp->uobject) { + hns_roce_v2_cq_clean(to_hr_cq(ibqp->recv_cq), hr_qp->qpn, + ibqp->srq ? to_hr_srq(ibqp->srq) : NULL); + if (ibqp->send_cq != ibqp->recv_cq) + hns_roce_v2_cq_clean(to_hr_cq(ibqp->send_cq), + hr_qp->qpn, NULL); + + hr_qp->rq.head = 0; + hr_qp->rq.tail = 0; + hr_qp->sq.head = 0; + hr_qp->sq.tail = 0; + hr_qp->sq_next_wqe = 0; + hr_qp->next_sge = 0; + } + +out: + kfree(context); + return ret; +} + +static inline enum ib_qp_state to_ib_qp_st(enum hns_roce_v2_qp_state state) +{ + switch (state) { + case HNS_ROCE_QP_ST_RST: return IB_QPS_RESET; + case HNS_ROCE_QP_ST_INIT: return IB_QPS_INIT; + case HNS_ROCE_QP_ST_RTR: return IB_QPS_RTR; + case HNS_ROCE_QP_ST_RTS: return IB_QPS_RTS; + case HNS_ROCE_QP_ST_SQ_DRAINING: + case HNS_ROCE_QP_ST_SQD: return IB_QPS_SQD; + case HNS_ROCE_QP_ST_SQER: return IB_QPS_SQE; + case HNS_ROCE_QP_ST_ERR: return IB_QPS_ERR; + default: return -1; + } +} + +static int hns_roce_v2_query_qpc(struct hns_roce_dev *hr_dev, + struct hns_roce_qp *hr_qp, + struct hns_roce_v2_qp_context *hr_context) +{ + struct hns_roce_cmd_mailbox *mailbox; + int ret; + + mailbox = hns_roce_alloc_cmd_mailbox(hr_dev); + if (IS_ERR(mailbox)) + return PTR_ERR(mailbox); + + ret = hns_roce_cmd_mbox(hr_dev, 0, mailbox->dma, hr_qp->qpn, 0, + HNS_ROCE_CMD_QUERY_QPC, + HNS_ROCE_CMD_TIMEOUT_MSECS); + if (ret) { + dev_err(hr_dev->dev, "QUERY QP cmd process error\n"); + goto out; + } + + memcpy(hr_context, mailbox->buf, sizeof(*hr_context)); + +out: + hns_roce_free_cmd_mailbox(hr_dev, mailbox); + return ret; +} + +static int hns_roce_v2_query_qp(struct ib_qp *ibqp, struct ib_qp_attr *qp_attr, + int qp_attr_mask, + struct ib_qp_init_attr *qp_init_attr) +{ + struct hns_roce_dev *hr_dev = to_hr_dev(ibqp->device); + struct hns_roce_qp *hr_qp = to_hr_qp(ibqp); + struct hns_roce_v2_qp_context *context; + struct device *dev = hr_dev->dev; + int tmp_qp_state; + int state; + int ret; + + context = kzalloc(sizeof(*context), GFP_KERNEL); + if (!context) + return -ENOMEM; + + memset(qp_attr, 0, sizeof(*qp_attr)); + memset(qp_init_attr, 0, sizeof(*qp_init_attr)); + + mutex_lock(&hr_qp->mutex); + + if (hr_qp->state == IB_QPS_RESET) { + qp_attr->qp_state = IB_QPS_RESET; + ret = 0; + goto done; + } + + ret = hns_roce_v2_query_qpc(hr_dev, hr_qp, context); + if (ret) { + dev_err(dev, "query qpc error\n"); + ret = -EINVAL; + goto out; + } + + state = roce_get_field(context->byte_60_qpst_mapid, + V2_QPC_BYTE_60_QP_ST_M, V2_QPC_BYTE_60_QP_ST_S); + tmp_qp_state = to_ib_qp_st((enum hns_roce_v2_qp_state)state); + if (tmp_qp_state == -1) { + dev_err(dev, "Illegal ib_qp_state\n"); + ret = -EINVAL; + goto out; + } + hr_qp->state = (u8)tmp_qp_state; + qp_attr->qp_state = (enum ib_qp_state)hr_qp->state; + qp_attr->path_mtu = (enum ib_mtu)roce_get_field(context->byte_24_mtu_tc, + V2_QPC_BYTE_24_MTU_M, + V2_QPC_BYTE_24_MTU_S); + qp_attr->path_mig_state = IB_MIG_ARMED; + qp_attr->ah_attr.type = RDMA_AH_ATTR_TYPE_ROCE; + if (hr_qp->ibqp.qp_type == IB_QPT_UD) + qp_attr->qkey = V2_QKEY_VAL; + + qp_attr->rq_psn = roce_get_field(context->byte_108_rx_reqepsn, + V2_QPC_BYTE_108_RX_REQ_EPSN_M, + V2_QPC_BYTE_108_RX_REQ_EPSN_S); + qp_attr->sq_psn = (u32)roce_get_field(context->byte_172_sq_psn, + V2_QPC_BYTE_172_SQ_CUR_PSN_M, + V2_QPC_BYTE_172_SQ_CUR_PSN_S); + qp_attr->dest_qp_num = (u8)roce_get_field(context->byte_56_dqpn_err, + V2_QPC_BYTE_56_DQPN_M, + V2_QPC_BYTE_56_DQPN_S); + qp_attr->qp_access_flags = ((roce_get_bit(context->byte_76_srqn_op_en, + V2_QPC_BYTE_76_RRE_S)) << 2) | + ((roce_get_bit(context->byte_76_srqn_op_en, + V2_QPC_BYTE_76_RWE_S)) << 1) | + ((roce_get_bit(context->byte_76_srqn_op_en, + V2_QPC_BYTE_76_ATE_S)) << 3); + if (hr_qp->ibqp.qp_type == IB_QPT_RC || + hr_qp->ibqp.qp_type == IB_QPT_UC) { + struct ib_global_route *grh = + rdma_ah_retrieve_grh(&qp_attr->ah_attr); + + rdma_ah_set_sl(&qp_attr->ah_attr, + roce_get_field(context->byte_28_at_fl, + V2_QPC_BYTE_28_SL_M, + V2_QPC_BYTE_28_SL_S)); + grh->flow_label = roce_get_field(context->byte_28_at_fl, + V2_QPC_BYTE_28_FL_M, + V2_QPC_BYTE_28_FL_S); + grh->sgid_index = roce_get_field(context->byte_20_smac_sgid_idx, + V2_QPC_BYTE_20_SGID_IDX_M, + V2_QPC_BYTE_20_SGID_IDX_S); + grh->hop_limit = roce_get_field(context->byte_24_mtu_tc, + V2_QPC_BYTE_24_HOP_LIMIT_M, + V2_QPC_BYTE_24_HOP_LIMIT_S); + grh->traffic_class = roce_get_field(context->byte_24_mtu_tc, + V2_QPC_BYTE_24_TC_M, + V2_QPC_BYTE_24_TC_S); + + memcpy(grh->dgid.raw, context->dgid, sizeof(grh->dgid.raw)); + } + + qp_attr->port_num = hr_qp->port + 1; + qp_attr->sq_draining = 0; + qp_attr->max_rd_atomic = 1 << roce_get_field(context->byte_208_irrl, + V2_QPC_BYTE_208_SR_MAX_M, + V2_QPC_BYTE_208_SR_MAX_S); + qp_attr->max_dest_rd_atomic = 1 << roce_get_field(context->byte_140_raq, + V2_QPC_BYTE_140_RR_MAX_M, + V2_QPC_BYTE_140_RR_MAX_S); + qp_attr->min_rnr_timer = (u8)roce_get_field(context->byte_80_rnr_rx_cqn, + V2_QPC_BYTE_80_MIN_RNR_TIME_M, + V2_QPC_BYTE_80_MIN_RNR_TIME_S); + qp_attr->timeout = (u8)roce_get_field(context->byte_28_at_fl, + V2_QPC_BYTE_28_AT_M, + V2_QPC_BYTE_28_AT_S); + qp_attr->retry_cnt = roce_get_field(context->byte_212_lsn, + V2_QPC_BYTE_212_RETRY_CNT_M, + V2_QPC_BYTE_212_RETRY_CNT_S); + qp_attr->rnr_retry = context->rq_rnr_timer; + +done: + qp_attr->cur_qp_state = qp_attr->qp_state; + qp_attr->cap.max_recv_wr = hr_qp->rq.wqe_cnt; + qp_attr->cap.max_recv_sge = hr_qp->rq.max_gs; + + if (!ibqp->uobject) { + qp_attr->cap.max_send_wr = hr_qp->sq.wqe_cnt; + qp_attr->cap.max_send_sge = hr_qp->sq.max_gs; + } else { + qp_attr->cap.max_send_wr = 0; + qp_attr->cap.max_send_sge = 0; + } + + qp_init_attr->cap = qp_attr->cap; + +out: + mutex_unlock(&hr_qp->mutex); + kfree(context); + return ret; +} + +static int hns_roce_v2_destroy_qp_common(struct hns_roce_dev *hr_dev, + struct hns_roce_qp *hr_qp, + int is_user) +{ + struct hns_roce_cq *send_cq, *recv_cq; + struct device *dev = hr_dev->dev; + int ret; + + if (hr_qp->ibqp.qp_type == IB_QPT_RC && hr_qp->state != IB_QPS_RESET) { + /* Modify qp to reset before destroying qp */ + ret = hns_roce_v2_modify_qp(&hr_qp->ibqp, NULL, 0, + hr_qp->state, IB_QPS_RESET); + if (ret) { + dev_err(dev, "modify QP %06lx to ERR failed.\n", + hr_qp->qpn); + return ret; + } + } + + send_cq = to_hr_cq(hr_qp->ibqp.send_cq); + recv_cq = to_hr_cq(hr_qp->ibqp.recv_cq); + + hns_roce_lock_cqs(send_cq, recv_cq); + + if (!is_user) { + __hns_roce_v2_cq_clean(recv_cq, hr_qp->qpn, hr_qp->ibqp.srq ? + to_hr_srq(hr_qp->ibqp.srq) : NULL); + if (send_cq != recv_cq) + __hns_roce_v2_cq_clean(send_cq, hr_qp->qpn, NULL); + } + + hns_roce_qp_remove(hr_dev, hr_qp); + + hns_roce_unlock_cqs(send_cq, recv_cq); + + hns_roce_qp_free(hr_dev, hr_qp); + + /* Not special_QP, free their QPN */ + if ((hr_qp->ibqp.qp_type == IB_QPT_RC) || + (hr_qp->ibqp.qp_type == IB_QPT_UC) || + (hr_qp->ibqp.qp_type == IB_QPT_UD)) + hns_roce_release_range_qp(hr_dev, hr_qp->qpn, 1); + + hns_roce_mtt_cleanup(hr_dev, &hr_qp->mtt); + + if (is_user) { + ib_umem_release(hr_qp->umem); + } else { + kfree(hr_qp->sq.wrid); + kfree(hr_qp->rq.wrid); + hns_roce_buf_free(hr_dev, hr_qp->buff_size, &hr_qp->hr_buf); + } + + return 0; +} + +static int hns_roce_v2_destroy_qp(struct ib_qp *ibqp) +{ + struct hns_roce_dev *hr_dev = to_hr_dev(ibqp->device); + struct hns_roce_qp *hr_qp = to_hr_qp(ibqp); + int ret; + + ret = hns_roce_v2_destroy_qp_common(hr_dev, hr_qp, !!ibqp->pd->uobject); + if (ret) { + dev_err(hr_dev->dev, "Destroy qp failed(%d)\n", ret); + return ret; + } + + if (hr_qp->ibqp.qp_type == IB_QPT_GSI) + kfree(hr_to_hr_sqp(hr_qp)); + else + kfree(hr_qp); + + return 0; +} + +static int hns_roce_v2_modify_cq(struct ib_cq *cq, u16 cq_count, u16 cq_period) +{ + struct hns_roce_dev *hr_dev = to_hr_dev(cq->device); + struct hns_roce_v2_cq_context *cq_context; + struct hns_roce_cq *hr_cq = to_hr_cq(cq); + struct hns_roce_v2_cq_context *cqc_mask; + struct hns_roce_cmd_mailbox *mailbox; + int ret; + + mailbox = hns_roce_alloc_cmd_mailbox(hr_dev); + if (IS_ERR(mailbox)) + return PTR_ERR(mailbox); + + cq_context = mailbox->buf; + cqc_mask = (struct hns_roce_v2_cq_context *)mailbox->buf + 1; + + memset(cqc_mask, 0xff, sizeof(*cqc_mask)); + + roce_set_field(cq_context->byte_56_cqe_period_maxcnt, + V2_CQC_BYTE_56_CQ_MAX_CNT_M, V2_CQC_BYTE_56_CQ_MAX_CNT_S, + cq_count); + roce_set_field(cqc_mask->byte_56_cqe_period_maxcnt, + V2_CQC_BYTE_56_CQ_MAX_CNT_M, V2_CQC_BYTE_56_CQ_MAX_CNT_S, + 0); + roce_set_field(cq_context->byte_56_cqe_period_maxcnt, + V2_CQC_BYTE_56_CQ_PERIOD_M, V2_CQC_BYTE_56_CQ_PERIOD_S, + cq_period); + roce_set_field(cqc_mask->byte_56_cqe_period_maxcnt, + V2_CQC_BYTE_56_CQ_PERIOD_M, V2_CQC_BYTE_56_CQ_PERIOD_S, + 0); + + ret = hns_roce_cmd_mbox(hr_dev, mailbox->dma, 0, hr_cq->cqn, 1, + HNS_ROCE_CMD_MODIFY_CQC, + HNS_ROCE_CMD_TIMEOUT_MSECS); + hns_roce_free_cmd_mailbox(hr_dev, mailbox); + if (ret) + dev_err(hr_dev->dev, "MODIFY CQ Failed to cmd mailbox.\n"); + + return ret; +} + +static const struct hns_roce_hw hns_roce_hw_v2 = { + .cmq_init = hns_roce_v2_cmq_init, + .cmq_exit = hns_roce_v2_cmq_exit, + .hw_profile = hns_roce_v2_profile, + .post_mbox = hns_roce_v2_post_mbox, + .chk_mbox = hns_roce_v2_chk_mbox, + .set_gid = hns_roce_v2_set_gid, + .set_mac = hns_roce_v2_set_mac, + .write_mtpt = hns_roce_v2_write_mtpt, + .write_cqc = hns_roce_v2_write_cqc, + .set_hem = hns_roce_v2_set_hem, + .clear_hem = hns_roce_v2_clear_hem, + .modify_qp = hns_roce_v2_modify_qp, + .query_qp = hns_roce_v2_query_qp, + .destroy_qp = hns_roce_v2_destroy_qp, + .modify_cq = hns_roce_v2_modify_cq, + .post_send = hns_roce_v2_post_send, + .post_recv = hns_roce_v2_post_recv, + .req_notify_cq = hns_roce_v2_req_notify_cq, + .poll_cq = hns_roce_v2_poll_cq, +}; + +static const struct pci_device_id hns_roce_hw_v2_pci_tbl[] = { + {PCI_VDEVICE(HUAWEI, HNAE3_DEV_ID_25GE_RDMA), 0}, + {PCI_VDEVICE(HUAWEI, HNAE3_DEV_ID_25GE_RDMA_MACSEC), 0}, + {PCI_VDEVICE(HUAWEI, HNAE3_DEV_ID_100G_RDMA_MACSEC), 0}, + /* required last entry */ + {0, } +}; + +static int hns_roce_hw_v2_get_cfg(struct hns_roce_dev *hr_dev, + struct hnae3_handle *handle) +{ + const struct pci_device_id *id; + + id = pci_match_id(hns_roce_hw_v2_pci_tbl, hr_dev->pci_dev); + if (!id) { + dev_err(hr_dev->dev, "device is not compatible!\n"); + return -ENXIO; + } + + hr_dev->hw = &hns_roce_hw_v2; + hr_dev->sdb_offset = ROCEE_DB_SQ_L_0_REG; + hr_dev->odb_offset = hr_dev->sdb_offset; + + /* Get info from NIC driver. */ + hr_dev->reg_base = handle->rinfo.roce_io_base; + hr_dev->caps.num_ports = 1; + hr_dev->iboe.netdevs[0] = handle->rinfo.netdev; + hr_dev->iboe.phy_port[0] = 0; + + /* cmd issue mode: 0 is poll, 1 is event */ + hr_dev->cmd_mod = 0; + hr_dev->loop_idc = 0; + + return 0; +} + +static int hns_roce_hw_v2_init_instance(struct hnae3_handle *handle) +{ + struct hns_roce_dev *hr_dev; + int ret; + + hr_dev = (struct hns_roce_dev *)ib_alloc_device(sizeof(*hr_dev)); + if (!hr_dev) + return -ENOMEM; + + hr_dev->priv = kzalloc(sizeof(struct hns_roce_v2_priv), GFP_KERNEL); + if (!hr_dev->priv) { + ret = -ENOMEM; + goto error_failed_kzalloc; + } + + hr_dev->pci_dev = handle->pdev; + hr_dev->dev = &handle->pdev->dev; + handle->priv = hr_dev; + + ret = hns_roce_hw_v2_get_cfg(hr_dev, handle); + if (ret) { + dev_err(hr_dev->dev, "Get Configuration failed!\n"); + goto error_failed_get_cfg; + } + + ret = hns_roce_init(hr_dev); + if (ret) { + dev_err(hr_dev->dev, "RoCE Engine init failed!\n"); + goto error_failed_get_cfg; + } + + return 0; + +error_failed_get_cfg: + kfree(hr_dev->priv); + +error_failed_kzalloc: + ib_dealloc_device(&hr_dev->ib_dev); + + return ret; +} + +static void hns_roce_hw_v2_uninit_instance(struct hnae3_handle *handle, + bool reset) +{ + struct hns_roce_dev *hr_dev = (struct hns_roce_dev *)handle->priv; + + hns_roce_exit(hr_dev); + kfree(hr_dev->priv); + ib_dealloc_device(&hr_dev->ib_dev); +} + +static const struct hnae3_client_ops hns_roce_hw_v2_ops = { + .init_instance = hns_roce_hw_v2_init_instance, + .uninit_instance = hns_roce_hw_v2_uninit_instance, +}; + +static struct hnae3_client hns_roce_hw_v2_client = { + .name = "hns_roce_hw_v2", + .type = HNAE3_CLIENT_ROCE, + .ops = &hns_roce_hw_v2_ops, +}; + +static int __init hns_roce_hw_v2_init(void) +{ + return hnae3_register_client(&hns_roce_hw_v2_client); +} + +static void __exit hns_roce_hw_v2_exit(void) +{ + hnae3_unregister_client(&hns_roce_hw_v2_client); +} + +module_init(hns_roce_hw_v2_init); +module_exit(hns_roce_hw_v2_exit); + +MODULE_LICENSE("Dual BSD/GPL"); +MODULE_AUTHOR("Wei Hu <xavier.huwei@huawei.com>"); +MODULE_AUTHOR("Lijun Ou <oulijun@huawei.com>"); +MODULE_AUTHOR("Shaobo Xu <xushaobo2@huawei.com>"); +MODULE_DESCRIPTION("Hisilicon Hip08 Family RoCE Driver"); diff --git a/drivers/infiniband/hw/hns/hns_roce_hw_v2.h b/drivers/infiniband/hw/hns/hns_roce_hw_v2.h new file mode 100644 index 000000000000..6106ad1b1322 --- /dev/null +++ b/drivers/infiniband/hw/hns/hns_roce_hw_v2.h @@ -0,0 +1,1167 @@ +/* + * Copyright (c) 2016-2017 Hisilicon Limited. + * + * 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 _HNS_ROCE_HW_V2_H +#define _HNS_ROCE_HW_V2_H + +#include <linux/bitops.h> + +#define HNS_ROCE_VF_QPC_BT_NUM 256 +#define HNS_ROCE_VF_SRQC_BT_NUM 64 +#define HNS_ROCE_VF_CQC_BT_NUM 64 +#define HNS_ROCE_VF_MPT_BT_NUM 64 +#define HNS_ROCE_VF_EQC_NUM 64 +#define HNS_ROCE_VF_SMAC_NUM 32 +#define HNS_ROCE_VF_SGID_NUM 32 +#define HNS_ROCE_VF_SL_NUM 8 + +#define HNS_ROCE_V2_MAX_QP_NUM 0x2000 +#define HNS_ROCE_V2_MAX_WQE_NUM 0x8000 +#define HNS_ROCE_V2_MAX_CQ_NUM 0x8000 +#define HNS_ROCE_V2_MAX_CQE_NUM 0x10000 +#define HNS_ROCE_V2_MAX_RQ_SGE_NUM 0x100 +#define HNS_ROCE_V2_MAX_SQ_SGE_NUM 0xff +#define HNS_ROCE_V2_MAX_SQ_INLINE 0x20 +#define HNS_ROCE_V2_UAR_NUM 256 +#define HNS_ROCE_V2_PHY_UAR_NUM 1 +#define HNS_ROCE_V2_MAX_MTPT_NUM 0x8000 +#define HNS_ROCE_V2_MAX_MTT_SEGS 0x1000000 +#define HNS_ROCE_V2_MAX_CQE_SEGS 0x1000000 +#define HNS_ROCE_V2_MAX_PD_NUM 0x1000000 +#define HNS_ROCE_V2_MAX_QP_INIT_RDMA 128 +#define HNS_ROCE_V2_MAX_QP_DEST_RDMA 128 +#define HNS_ROCE_V2_MAX_SQ_DESC_SZ 64 +#define HNS_ROCE_V2_MAX_RQ_DESC_SZ 16 +#define HNS_ROCE_V2_MAX_SRQ_DESC_SZ 64 +#define HNS_ROCE_V2_QPC_ENTRY_SZ 256 +#define HNS_ROCE_V2_IRRL_ENTRY_SZ 64 +#define HNS_ROCE_V2_CQC_ENTRY_SZ 64 +#define HNS_ROCE_V2_MTPT_ENTRY_SZ 64 +#define HNS_ROCE_V2_MTT_ENTRY_SZ 64 +#define HNS_ROCE_V2_CQE_ENTRY_SIZE 32 +#define HNS_ROCE_V2_PAGE_SIZE_SUPPORTED 0xFFFFF000 +#define HNS_ROCE_V2_MAX_INNER_MTPT_NUM 2 +#define HNS_ROCE_INVALID_LKEY 0x100 +#define HNS_ROCE_CMQ_TX_TIMEOUT 200 + +#define HNS_ROCE_CONTEXT_HOP_NUM 1 +#define HNS_ROCE_MTT_HOP_NUM 1 +#define HNS_ROCE_CQE_HOP_NUM 1 +#define HNS_ROCE_PBL_HOP_NUM 2 + +#define HNS_ROCE_V2_TABLE_CHUNK_SIZE (1 << 18) + +#define HNS_ROCE_CMD_FLAG_IN_VALID_SHIFT 0 +#define HNS_ROCE_CMD_FLAG_OUT_VALID_SHIFT 1 +#define HNS_ROCE_CMD_FLAG_NEXT_SHIFT 2 +#define HNS_ROCE_CMD_FLAG_WR_OR_RD_SHIFT 3 +#define HNS_ROCE_CMD_FLAG_NO_INTR_SHIFT 4 +#define HNS_ROCE_CMD_FLAG_ERR_INTR_SHIFT 5 + +#define HNS_ROCE_CMD_FLAG_IN BIT(HNS_ROCE_CMD_FLAG_IN_VALID_SHIFT) +#define HNS_ROCE_CMD_FLAG_OUT BIT(HNS_ROCE_CMD_FLAG_OUT_VALID_SHIFT) +#define HNS_ROCE_CMD_FLAG_NEXT BIT(HNS_ROCE_CMD_FLAG_NEXT_SHIFT) +#define HNS_ROCE_CMD_FLAG_WR BIT(HNS_ROCE_CMD_FLAG_WR_OR_RD_SHIFT) +#define HNS_ROCE_CMD_FLAG_NO_INTR BIT(HNS_ROCE_CMD_FLAG_NO_INTR_SHIFT) +#define HNS_ROCE_CMD_FLAG_ERR_INTR BIT(HNS_ROCE_CMD_FLAG_ERR_INTR_SHIFT) + +#define HNS_ROCE_CMQ_DESC_NUM_S 3 +#define HNS_ROCE_CMQ_EN_B 16 +#define HNS_ROCE_CMQ_ENABLE BIT(HNS_ROCE_CMQ_EN_B) + +#define check_whether_last_step(hop_num, step_idx) \ + ((step_idx == 0 && hop_num == HNS_ROCE_HOP_NUM_0) || \ + (step_idx == 1 && hop_num == 1) || \ + (step_idx == 2 && hop_num == 2)) + +#define V2_CQ_DB_REQ_NOT_SOL 0 +#define V2_CQ_DB_REQ_NOT 1 + +#define V2_CQ_STATE_VALID 1 +#define V2_QKEY_VAL 0x80010000 + +#define GID_LEN_V2 16 + +#define HNS_ROCE_V2_CQE_QPN_MASK 0x3ffff + +enum { + HNS_ROCE_V2_WQE_OP_SEND = 0x0, + HNS_ROCE_V2_WQE_OP_SEND_WITH_INV = 0x1, + HNS_ROCE_V2_WQE_OP_SEND_WITH_IMM = 0x2, + HNS_ROCE_V2_WQE_OP_RDMA_WRITE = 0x3, + HNS_ROCE_V2_WQE_OP_RDMA_WRITE_WITH_IMM = 0x4, + HNS_ROCE_V2_WQE_OP_RDMA_READ = 0x5, + HNS_ROCE_V2_WQE_OP_ATOM_CMP_AND_SWAP = 0x6, + HNS_ROCE_V2_WQE_OP_ATOM_FETCH_AND_ADD = 0x7, + HNS_ROCE_V2_WQE_OP_ATOM_MSK_CMP_AND_SWAP = 0x8, + HNS_ROCE_V2_WQE_OP_ATOM_MSK_FETCH_AND_ADD = 0x9, + HNS_ROCE_V2_WQE_OP_FAST_REG_PMR = 0xa, + HNS_ROCE_V2_WQE_OP_LOCAL_INV = 0xb, + HNS_ROCE_V2_WQE_OP_BIND_MW_TYPE = 0xc, + HNS_ROCE_V2_WQE_OP_MASK = 0x1f, +}; + +enum { + HNS_ROCE_SQ_OPCODE_SEND = 0x0, + HNS_ROCE_SQ_OPCODE_SEND_WITH_INV = 0x1, + HNS_ROCE_SQ_OPCODE_SEND_WITH_IMM = 0x2, + HNS_ROCE_SQ_OPCODE_RDMA_WRITE = 0x3, + HNS_ROCE_SQ_OPCODE_RDMA_WRITE_WITH_IMM = 0x4, + HNS_ROCE_SQ_OPCODE_RDMA_READ = 0x5, + HNS_ROCE_SQ_OPCODE_ATOMIC_COMP_AND_SWAP = 0x6, + HNS_ROCE_SQ_OPCODE_ATOMIC_FETCH_AND_ADD = 0x7, + HNS_ROCE_SQ_OPCODE_ATOMIC_MASK_COMP_AND_SWAP = 0x8, + HNS_ROCE_SQ_OPCODE_ATOMIC_MASK_FETCH_AND_ADD = 0x9, + HNS_ROCE_SQ_OPCODE_FAST_REG_WR = 0xa, + HNS_ROCE_SQ_OPCODE_LOCAL_INV = 0xb, + HNS_ROCE_SQ_OPCODE_BIND_MW = 0xc, +}; + +enum { + /* rq operations */ + HNS_ROCE_V2_OPCODE_RDMA_WRITE_IMM = 0x0, + HNS_ROCE_V2_OPCODE_SEND = 0x1, + HNS_ROCE_V2_OPCODE_SEND_WITH_IMM = 0x2, + HNS_ROCE_V2_OPCODE_SEND_WITH_INV = 0x3, +}; + +enum { + HNS_ROCE_V2_SQ_DB = 0x0, + HNS_ROCE_V2_RQ_DB = 0x1, + HNS_ROCE_V2_SRQ_DB = 0x2, + HNS_ROCE_V2_CQ_DB_PTR = 0x3, + HNS_ROCE_V2_CQ_DB_NTR = 0x4, +}; + +enum { + HNS_ROCE_CQE_V2_SUCCESS = 0x00, + HNS_ROCE_CQE_V2_LOCAL_LENGTH_ERR = 0x01, + HNS_ROCE_CQE_V2_LOCAL_QP_OP_ERR = 0x02, + HNS_ROCE_CQE_V2_LOCAL_PROT_ERR = 0x04, + HNS_ROCE_CQE_V2_WR_FLUSH_ERR = 0x05, + HNS_ROCE_CQE_V2_MW_BIND_ERR = 0x06, + HNS_ROCE_CQE_V2_BAD_RESP_ERR = 0x10, + HNS_ROCE_CQE_V2_LOCAL_ACCESS_ERR = 0x11, + HNS_ROCE_CQE_V2_REMOTE_INVAL_REQ_ERR = 0x12, + HNS_ROCE_CQE_V2_REMOTE_ACCESS_ERR = 0x13, + HNS_ROCE_CQE_V2_REMOTE_OP_ERR = 0x14, + HNS_ROCE_CQE_V2_TRANSPORT_RETRY_EXC_ERR = 0x15, + HNS_ROCE_CQE_V2_RNR_RETRY_EXC_ERR = 0x16, + HNS_ROCE_CQE_V2_REMOTE_ABORT_ERR = 0x22, + + HNS_ROCE_V2_CQE_STATUS_MASK = 0xff, +}; + +/* CMQ command */ +enum hns_roce_opcode_type { + HNS_ROCE_OPC_QUERY_HW_VER = 0x8000, + HNS_ROCE_OPC_CFG_GLOBAL_PARAM = 0x8001, + HNS_ROCE_OPC_ALLOC_PF_RES = 0x8004, + HNS_ROCE_OPC_QUERY_PF_RES = 0x8400, + HNS_ROCE_OPC_ALLOC_VF_RES = 0x8401, + HNS_ROCE_OPC_CFG_BT_ATTR = 0x8506, +}; + +enum { + TYPE_CRQ, + TYPE_CSQ, +}; + +enum hns_roce_cmd_return_status { + CMD_EXEC_SUCCESS = 0, + CMD_NO_AUTH = 1, + CMD_NOT_EXEC = 2, + CMD_QUEUE_FULL = 3, +}; + +struct hns_roce_v2_cq_context { + u32 byte_4_pg_ceqn; + u32 byte_8_cqn; + u32 cqe_cur_blk_addr; + u32 byte_16_hop_addr; + u32 cqe_nxt_blk_addr; + u32 byte_24_pgsz_addr; + u32 byte_28_cq_pi; + u32 byte_32_cq_ci; + u32 cqe_ba; + u32 byte_40_cqe_ba; + u32 byte_44_db_record; + u32 db_record_addr; + u32 byte_52_cqe_cnt; + u32 byte_56_cqe_period_maxcnt; + u32 cqe_report_timer; + u32 byte_64_se_cqe_idx; +}; +#define V2_CQC_BYTE_4_CQ_ST_S 0 +#define V2_CQC_BYTE_4_CQ_ST_M GENMASK(1, 0) + +#define V2_CQC_BYTE_4_POLL_S 2 + +#define V2_CQC_BYTE_4_SE_S 3 + +#define V2_CQC_BYTE_4_OVER_IGNORE_S 4 + +#define V2_CQC_BYTE_4_COALESCE_S 5 + +#define V2_CQC_BYTE_4_ARM_ST_S 6 +#define V2_CQC_BYTE_4_ARM_ST_M GENMASK(7, 6) + +#define V2_CQC_BYTE_4_SHIFT_S 8 +#define V2_CQC_BYTE_4_SHIFT_M GENMASK(12, 8) + +#define V2_CQC_BYTE_4_CMD_SN_S 13 +#define V2_CQC_BYTE_4_CMD_SN_M GENMASK(14, 13) + +#define V2_CQC_BYTE_4_CEQN_S 15 +#define V2_CQC_BYTE_4_CEQN_M GENMASK(23, 15) + +#define V2_CQC_BYTE_4_PAGE_OFFSET_S 24 +#define V2_CQC_BYTE_4_PAGE_OFFSET_M GENMASK(31, 24) + +#define V2_CQC_BYTE_8_CQN_S 0 +#define V2_CQC_BYTE_8_CQN_M GENMASK(23, 0) + +#define V2_CQC_BYTE_16_CQE_CUR_BLK_ADDR_S 0 +#define V2_CQC_BYTE_16_CQE_CUR_BLK_ADDR_M GENMASK(19, 0) + +#define V2_CQC_BYTE_16_CQE_HOP_NUM_S 30 +#define V2_CQC_BYTE_16_CQE_HOP_NUM_M GENMASK(31, 30) + +#define V2_CQC_BYTE_24_CQE_NXT_BLK_ADDR_S 0 +#define V2_CQC_BYTE_24_CQE_NXT_BLK_ADDR_M GENMASK(19, 0) + +#define V2_CQC_BYTE_24_CQE_BA_PG_SZ_S 24 +#define V2_CQC_BYTE_24_CQE_BA_PG_SZ_M GENMASK(27, 24) + +#define V2_CQC_BYTE_24_CQE_BUF_PG_SZ_S 28 +#define V2_CQC_BYTE_24_CQE_BUF_PG_SZ_M GENMASK(31, 28) + +#define V2_CQC_BYTE_28_CQ_PRODUCER_IDX_S 0 +#define V2_CQC_BYTE_28_CQ_PRODUCER_IDX_M GENMASK(23, 0) + +#define V2_CQC_BYTE_32_CQ_CONSUMER_IDX_S 0 +#define V2_CQC_BYTE_32_CQ_CONSUMER_IDX_M GENMASK(23, 0) + +#define V2_CQC_BYTE_40_CQE_BA_S 0 +#define V2_CQC_BYTE_40_CQE_BA_M GENMASK(28, 0) + +#define V2_CQC_BYTE_44_DB_RECORD_EN_S 0 + +#define V2_CQC_BYTE_52_CQE_CNT_S 0 +#define V2_CQC_BYTE_52_CQE_CNT_M GENMASK(23, 0) + +#define V2_CQC_BYTE_56_CQ_MAX_CNT_S 0 +#define V2_CQC_BYTE_56_CQ_MAX_CNT_M GENMASK(15, 0) + +#define V2_CQC_BYTE_56_CQ_PERIOD_S 16 +#define V2_CQC_BYTE_56_CQ_PERIOD_M GENMASK(31, 16) + +#define V2_CQC_BYTE_64_SE_CQE_IDX_S 0 +#define V2_CQC_BYTE_64_SE_CQE_IDX_M GENMASK(23, 0) + +enum{ + V2_MPT_ST_VALID = 0x1, +}; + +enum hns_roce_v2_qp_state { + HNS_ROCE_QP_ST_RST, + HNS_ROCE_QP_ST_INIT, + HNS_ROCE_QP_ST_RTR, + HNS_ROCE_QP_ST_RTS, + HNS_ROCE_QP_ST_SQER, + HNS_ROCE_QP_ST_SQD, + HNS_ROCE_QP_ST_ERR, + HNS_ROCE_QP_ST_SQ_DRAINING, + HNS_ROCE_QP_NUM_ST +}; + +struct hns_roce_v2_qp_context { + u32 byte_4_sqpn_tst; + u32 wqe_sge_ba; + u32 byte_12_sq_hop; + u32 byte_16_buf_ba_pg_sz; + u32 byte_20_smac_sgid_idx; + u32 byte_24_mtu_tc; + u32 byte_28_at_fl; + u8 dgid[GID_LEN_V2]; + u32 dmac; + u32 byte_52_udpspn_dmac; + u32 byte_56_dqpn_err; + u32 byte_60_qpst_mapid; + u32 qkey_xrcd; + u32 byte_68_rq_db; + u32 rq_db_record_addr; + u32 byte_76_srqn_op_en; + u32 byte_80_rnr_rx_cqn; + u32 byte_84_rq_ci_pi; + u32 rq_cur_blk_addr; + u32 byte_92_srq_info; + u32 byte_96_rx_reqmsn; + u32 rq_nxt_blk_addr; + u32 byte_104_rq_sge; + u32 byte_108_rx_reqepsn; + u32 rq_rnr_timer; + u32 rx_msg_len; + u32 rx_rkey_pkt_info; + u64 rx_va; + u32 byte_132_trrl; + u32 trrl_ba; + u32 byte_140_raq; + u32 byte_144_raq; + u32 byte_148_raq; + u32 byte_152_raq; + u32 byte_156_raq; + u32 byte_160_sq_ci_pi; + u32 sq_cur_blk_addr; + u32 byte_168_irrl_idx; + u32 byte_172_sq_psn; + u32 byte_176_msg_pktn; + u32 sq_cur_sqe_blk_addr; + u32 byte_184_irrl_idx; + u32 cur_sge_offset; + u32 byte_192_ext_sge; + u32 byte_196_sq_psn; + u32 byte_200_sq_max; + u32 irrl_ba; + u32 byte_208_irrl; + u32 byte_212_lsn; + u32 sq_timer; + u32 byte_220_retry_psn_msn; + u32 byte_224_retry_msg; + u32 rx_sq_cur_blk_addr; + u32 byte_232_irrl_sge; + u32 irrl_cur_sge_offset; + u32 byte_240_irrl_tail; + u32 byte_244_rnr_rxack; + u32 byte_248_ack_psn; + u32 byte_252_err_txcqn; + u32 byte_256_sqflush_rqcqe; +}; + +#define V2_QPC_BYTE_4_TST_S 0 +#define V2_QPC_BYTE_4_TST_M GENMASK(2, 0) + +#define V2_QPC_BYTE_4_SGE_SHIFT_S 3 +#define V2_QPC_BYTE_4_SGE_SHIFT_M GENMASK(7, 3) + +#define V2_QPC_BYTE_4_SQPN_S 8 +#define V2_QPC_BYTE_4_SQPN_M GENMASK(31, 8) + +#define V2_QPC_BYTE_12_WQE_SGE_BA_S 0 +#define V2_QPC_BYTE_12_WQE_SGE_BA_M GENMASK(28, 0) + +#define V2_QPC_BYTE_12_SQ_HOP_NUM_S 29 +#define V2_QPC_BYTE_12_SQ_HOP_NUM_M GENMASK(30, 29) + +#define V2_QPC_BYTE_12_RSVD_LKEY_EN_S 31 + +#define V2_QPC_BYTE_16_WQE_SGE_BA_PG_SZ_S 0 +#define V2_QPC_BYTE_16_WQE_SGE_BA_PG_SZ_M GENMASK(3, 0) + +#define V2_QPC_BYTE_16_WQE_SGE_BUF_PG_SZ_S 4 +#define V2_QPC_BYTE_16_WQE_SGE_BUF_PG_SZ_M GENMASK(7, 4) + +#define V2_QPC_BYTE_16_PD_S 8 +#define V2_QPC_BYTE_16_PD_M GENMASK(31, 8) + +#define V2_QPC_BYTE_20_RQ_HOP_NUM_S 0 +#define V2_QPC_BYTE_20_RQ_HOP_NUM_M GENMASK(1, 0) + +#define V2_QPC_BYTE_20_SGE_HOP_NUM_S 2 +#define V2_QPC_BYTE_20_SGE_HOP_NUM_M GENMASK(3, 2) + +#define V2_QPC_BYTE_20_RQWS_S 4 +#define V2_QPC_BYTE_20_RQWS_M GENMASK(7, 4) + +#define V2_QPC_BYTE_20_SQ_SHIFT_S 8 +#define V2_QPC_BYTE_20_SQ_SHIFT_M GENMASK(11, 8) + +#define V2_QPC_BYTE_20_RQ_SHIFT_S 12 +#define V2_QPC_BYTE_20_RQ_SHIFT_M GENMASK(15, 12) + +#define V2_QPC_BYTE_20_SGID_IDX_S 16 +#define V2_QPC_BYTE_20_SGID_IDX_M GENMASK(23, 16) + +#define V2_QPC_BYTE_20_SMAC_IDX_S 24 +#define V2_QPC_BYTE_20_SMAC_IDX_M GENMASK(31, 24) + +#define V2_QPC_BYTE_24_HOP_LIMIT_S 0 +#define V2_QPC_BYTE_24_HOP_LIMIT_M GENMASK(7, 0) + +#define V2_QPC_BYTE_24_TC_S 8 +#define V2_QPC_BYTE_24_TC_M GENMASK(15, 8) + +#define V2_QPC_BYTE_24_VLAN_IDX_S 16 +#define V2_QPC_BYTE_24_VLAN_IDX_M GENMASK(27, 16) + +#define V2_QPC_BYTE_24_MTU_S 28 +#define V2_QPC_BYTE_24_MTU_M GENMASK(31, 28) + +#define V2_QPC_BYTE_28_FL_S 0 +#define V2_QPC_BYTE_28_FL_M GENMASK(19, 0) + +#define V2_QPC_BYTE_28_SL_S 20 +#define V2_QPC_BYTE_28_SL_M GENMASK(23, 20) + +#define V2_QPC_BYTE_28_CNP_TX_FLAG_S 24 + +#define V2_QPC_BYTE_28_CE_FLAG_S 25 + +#define V2_QPC_BYTE_28_LBI_S 26 + +#define V2_QPC_BYTE_28_AT_S 27 +#define V2_QPC_BYTE_28_AT_M GENMASK(31, 27) + +#define V2_QPC_BYTE_52_DMAC_S 0 +#define V2_QPC_BYTE_52_DMAC_M GENMASK(15, 0) + +#define V2_QPC_BYTE_52_UDPSPN_S 16 +#define V2_QPC_BYTE_52_UDPSPN_M GENMASK(31, 16) + +#define V2_QPC_BYTE_56_DQPN_S 0 +#define V2_QPC_BYTE_56_DQPN_M GENMASK(23, 0) + +#define V2_QPC_BYTE_56_SQ_TX_ERR_S 24 +#define V2_QPC_BYTE_56_SQ_RX_ERR_S 25 +#define V2_QPC_BYTE_56_RQ_TX_ERR_S 26 +#define V2_QPC_BYTE_56_RQ_RX_ERR_S 27 + +#define V2_QPC_BYTE_56_LP_PKTN_INI_S 28 +#define V2_QPC_BYTE_56_LP_PKTN_INI_M GENMASK(31, 28) + +#define V2_QPC_BYTE_60_MAPID_S 0 +#define V2_QPC_BYTE_60_MAPID_M GENMASK(12, 0) + +#define V2_QPC_BYTE_60_INNER_MAP_IND_S 13 + +#define V2_QPC_BYTE_60_SQ_MAP_IND_S 14 + +#define V2_QPC_BYTE_60_RQ_MAP_IND_S 15 + +#define V2_QPC_BYTE_60_TEMPID_S 16 +#define V2_QPC_BYTE_60_TEMPID_M GENMASK(22, 16) + +#define V2_QPC_BYTE_60_EXT_MAP_IND_S 23 + +#define V2_QPC_BYTE_60_RTY_NUM_INI_BAK_S 24 +#define V2_QPC_BYTE_60_RTY_NUM_INI_BAK_M GENMASK(26, 24) + +#define V2_QPC_BYTE_60_SQ_RLS_IND_S 27 + +#define V2_QPC_BYTE_60_SQ_EXT_IND_S 28 + +#define V2_QPC_BYTE_60_QP_ST_S 29 +#define V2_QPC_BYTE_60_QP_ST_M GENMASK(31, 29) + +#define V2_QPC_BYTE_68_RQ_RECORD_EN_S 0 + +#define V2_QPC_BYTE_68_RQ_DB_RECORD_ADDR_S 1 +#define V2_QPC_BYTE_68_RQ_DB_RECORD_ADDR_M GENMASK(31, 1) + +#define V2_QPC_BYTE_76_SRQN_S 0 +#define V2_QPC_BYTE_76_SRQN_M GENMASK(23, 0) + +#define V2_QPC_BYTE_76_SRQ_EN_S 24 + +#define V2_QPC_BYTE_76_RRE_S 25 + +#define V2_QPC_BYTE_76_RWE_S 26 + +#define V2_QPC_BYTE_76_ATE_S 27 + +#define V2_QPC_BYTE_76_RQIE_S 28 + +#define V2_QPC_BYTE_80_RX_CQN_S 0 +#define V2_QPC_BYTE_80_RX_CQN_M GENMASK(23, 0) + +#define V2_QPC_BYTE_80_MIN_RNR_TIME_S 27 +#define V2_QPC_BYTE_80_MIN_RNR_TIME_M GENMASK(31, 27) + +#define V2_QPC_BYTE_84_RQ_PRODUCER_IDX_S 0 +#define V2_QPC_BYTE_84_RQ_PRODUCER_IDX_M GENMASK(15, 0) + +#define V2_QPC_BYTE_84_RQ_CONSUMER_IDX_S 16 +#define V2_QPC_BYTE_84_RQ_CONSUMER_IDX_M GENMASK(31, 16) + +#define V2_QPC_BYTE_92_RQ_CUR_BLK_ADDR_S 0 +#define V2_QPC_BYTE_92_RQ_CUR_BLK_ADDR_M GENMASK(19, 0) + +#define V2_QPC_BYTE_92_SRQ_INFO_S 20 +#define V2_QPC_BYTE_92_SRQ_INFO_M GENMASK(31, 20) + +#define V2_QPC_BYTE_96_RX_REQ_MSN_S 0 +#define V2_QPC_BYTE_96_RX_REQ_MSN_M GENMASK(23, 0) + +#define V2_QPC_BYTE_104_RQ_NXT_BLK_ADDR_S 0 +#define V2_QPC_BYTE_104_RQ_NXT_BLK_ADDR_M GENMASK(19, 0) + +#define V2_QPC_BYTE_104_RQ_CUR_WQE_SGE_NUM_S 24 +#define V2_QPC_BYTE_104_RQ_CUR_WQE_SGE_NUM_M GENMASK(31, 24) + +#define V2_QPC_BYTE_108_INV_CREDIT_S 0 + +#define V2_QPC_BYTE_108_RX_REQ_PSN_ERR_S 3 + +#define V2_QPC_BYTE_108_RX_REQ_LAST_OPTYPE_S 4 +#define V2_QPC_BYTE_108_RX_REQ_LAST_OPTYPE_M GENMASK(6, 4) + +#define V2_QPC_BYTE_108_RX_REQ_RNR_S 7 + +#define V2_QPC_BYTE_108_RX_REQ_EPSN_S 8 +#define V2_QPC_BYTE_108_RX_REQ_EPSN_M GENMASK(31, 8) + +#define V2_QPC_BYTE_132_TRRL_HEAD_MAX_S 0 +#define V2_QPC_BYTE_132_TRRL_HEAD_MAX_M GENMASK(7, 0) + +#define V2_QPC_BYTE_132_TRRL_TAIL_MAX_S 8 +#define V2_QPC_BYTE_132_TRRL_TAIL_MAX_M GENMASK(15, 8) + +#define V2_QPC_BYTE_132_TRRL_BA_S 16 +#define V2_QPC_BYTE_132_TRRL_BA_M GENMASK(31, 16) + +#define V2_QPC_BYTE_140_TRRL_BA_S 0 +#define V2_QPC_BYTE_140_TRRL_BA_M GENMASK(11, 0) + +#define V2_QPC_BYTE_140_RR_MAX_S 12 +#define V2_QPC_BYTE_140_RR_MAX_M GENMASK(14, 12) + +#define V2_QPC_BYTE_140_RSVD_RAQ_MAP_S 15 + +#define V2_QPC_BYTE_140_RAQ_TRRL_HEAD_S 16 +#define V2_QPC_BYTE_140_RAQ_TRRL_HEAD_M GENMASK(23, 16) + +#define V2_QPC_BYTE_140_RAQ_TRRL_TAIL_S 24 +#define V2_QPC_BYTE_140_RAQ_TRRL_TAIL_M GENMASK(31, 24) + +#define V2_QPC_BYTE_144_RAQ_RTY_INI_PSN_S 0 +#define V2_QPC_BYTE_144_RAQ_RTY_INI_PSN_M GENMASK(23, 0) + +#define V2_QPC_BYTE_144_RAQ_RTY_INI_IND_S 24 + +#define V2_QPC_BYTE_144_RAQ_CREDIT_S 25 +#define V2_QPC_BYTE_144_RAQ_CREDIT_M GENMASK(29, 25) + +#define V2_QPC_BYTE_144_RESP_RTY_FLG_S 31 + +#define V2_QPC_BYTE_148_RQ_MSN_S 0 +#define V2_QPC_BYTE_148_RQ_MSN_M GENMASK(23, 0) + +#define V2_QPC_BYTE_148_RAQ_SYNDROME_S 24 +#define V2_QPC_BYTE_148_RAQ_SYNDROME_M GENMASK(31, 24) + +#define V2_QPC_BYTE_152_RAQ_PSN_S 8 +#define V2_QPC_BYTE_152_RAQ_PSN_M GENMASK(31, 8) + +#define V2_QPC_BYTE_152_RAQ_TRRL_RTY_HEAD_S 24 +#define V2_QPC_BYTE_152_RAQ_TRRL_RTY_HEAD_M GENMASK(31, 24) + +#define V2_QPC_BYTE_156_RAQ_USE_PKTN_S 0 +#define V2_QPC_BYTE_156_RAQ_USE_PKTN_M GENMASK(23, 0) + +#define V2_QPC_BYTE_160_SQ_PRODUCER_IDX_S 0 +#define V2_QPC_BYTE_160_SQ_PRODUCER_IDX_M GENMASK(15, 0) + +#define V2_QPC_BYTE_160_SQ_CONSUMER_IDX_S 16 +#define V2_QPC_BYTE_160_SQ_CONSUMER_IDX_M GENMASK(31, 16) + +#define V2_QPC_BYTE_168_SQ_CUR_BLK_ADDR_S 0 +#define V2_QPC_BYTE_168_SQ_CUR_BLK_ADDR_M GENMASK(19, 0) + +#define V2_QPC_BYTE_168_MSG_RTY_LP_FLG_S 20 + +#define V2_QPC_BYTE_168_LP_SGEN_INI_S 21 +#define V2_QPC_BYTE_168_LP_SGEN_INI_M GENMASK(23, 21) + +#define V2_QPC_BYTE_168_SQ_SHIFT_BAK_S 24 +#define V2_QPC_BYTE_168_SQ_SHIFT_BAK_M GENMASK(27, 24) + +#define V2_QPC_BYTE_168_IRRL_IDX_LSB_S 28 +#define V2_QPC_BYTE_168_IRRL_IDX_LSB_M GENMASK(31, 28) + +#define V2_QPC_BYTE_172_ACK_REQ_FREQ_S 0 +#define V2_QPC_BYTE_172_ACK_REQ_FREQ_M GENMASK(5, 0) + +#define V2_QPC_BYTE_172_MSG_RNR_FLG_S 6 + +#define V2_QPC_BYTE_172_FRE_S 7 + +#define V2_QPC_BYTE_172_SQ_CUR_PSN_S 8 +#define V2_QPC_BYTE_172_SQ_CUR_PSN_M GENMASK(31, 8) + +#define V2_QPC_BYTE_176_MSG_USE_PKTN_S 0 +#define V2_QPC_BYTE_176_MSG_USE_PKTN_M GENMASK(23, 0) + +#define V2_QPC_BYTE_176_IRRL_HEAD_PRE_S 24 +#define V2_QPC_BYTE_176_IRRL_HEAD_PRE_M GENMASK(31, 24) + +#define V2_QPC_BYTE_184_SQ_CUR_SGE_BLK_ADDR_S 0 +#define V2_QPC_BYTE_184_SQ_CUR_SGE_BLK_ADDR_M GENMASK(19, 0) + +#define V2_QPC_BYTE_184_IRRL_IDX_MSB_S 20 +#define V2_QPC_BYTE_184_IRRL_IDX_MSB_M GENMASK(31, 20) + +#define V2_QPC_BYTE_192_CUR_SGE_IDX_S 0 +#define V2_QPC_BYTE_192_CUR_SGE_IDX_M GENMASK(23, 0) + +#define V2_QPC_BYTE_192_EXT_SGE_NUM_LEFT_S 24 +#define V2_QPC_BYTE_192_EXT_SGE_NUM_LEFT_M GENMASK(31, 24) + +#define V2_QPC_BYTE_196_IRRL_HEAD_S 0 +#define V2_QPC_BYTE_196_IRRL_HEAD_M GENMASK(7, 0) + +#define V2_QPC_BYTE_196_SQ_MAX_PSN_S 8 +#define V2_QPC_BYTE_196_SQ_MAX_PSN_M GENMASK(31, 8) + +#define V2_QPC_BYTE_200_SQ_MAX_IDX_S 0 +#define V2_QPC_BYTE_200_SQ_MAX_IDX_M GENMASK(15, 0) + +#define V2_QPC_BYTE_200_LCL_OPERATED_CNT_S 16 +#define V2_QPC_BYTE_200_LCL_OPERATED_CNT_M GENMASK(31, 16) + +#define V2_QPC_BYTE_208_IRRL_BA_S 0 +#define V2_QPC_BYTE_208_IRRL_BA_M GENMASK(25, 0) + +#define V2_QPC_BYTE_208_PKT_RNR_FLG_S 26 + +#define V2_QPC_BYTE_208_PKT_RTY_FLG_S 27 + +#define V2_QPC_BYTE_208_RMT_E2E_S 28 + +#define V2_QPC_BYTE_208_SR_MAX_S 29 +#define V2_QPC_BYTE_208_SR_MAX_M GENMASK(31, 29) + +#define V2_QPC_BYTE_212_LSN_S 0 +#define V2_QPC_BYTE_212_LSN_M GENMASK(23, 0) + +#define V2_QPC_BYTE_212_RETRY_NUM_INIT_S 24 +#define V2_QPC_BYTE_212_RETRY_NUM_INIT_M GENMASK(26, 24) + +#define V2_QPC_BYTE_212_CHECK_FLG_S 27 +#define V2_QPC_BYTE_212_CHECK_FLG_M GENMASK(28, 27) + +#define V2_QPC_BYTE_212_RETRY_CNT_S 29 +#define V2_QPC_BYTE_212_RETRY_CNT_M GENMASK(31, 29) + +#define V2_QPC_BYTE_220_RETRY_MSG_MSN_S 0 +#define V2_QPC_BYTE_220_RETRY_MSG_MSN_M GENMASK(15, 0) + +#define V2_QPC_BYTE_220_RETRY_MSG_PSN_S 16 +#define V2_QPC_BYTE_220_RETRY_MSG_PSN_M GENMASK(31, 16) + +#define V2_QPC_BYTE_224_RETRY_MSG_PSN_S 0 +#define V2_QPC_BYTE_224_RETRY_MSG_PSN_M GENMASK(7, 0) + +#define V2_QPC_BYTE_224_RETRY_MSG_FPKT_PSN_S 8 +#define V2_QPC_BYTE_224_RETRY_MSG_FPKT_PSN_M GENMASK(31, 8) + +#define V2_QPC_BYTE_232_RX_SQ_CUR_BLK_ADDR_S 0 +#define V2_QPC_BYTE_232_RX_SQ_CUR_BLK_ADDR_M GENMASK(19, 0) + +#define V2_QPC_BYTE_232_IRRL_SGE_IDX_S 20 +#define V2_QPC_BYTE_232_IRRL_SGE_IDX_M GENMASK(28, 20) + +#define V2_QPC_BYTE_240_IRRL_TAIL_REAL_S 0 +#define V2_QPC_BYTE_240_IRRL_TAIL_REAL_M GENMASK(7, 0) + +#define V2_QPC_BYTE_240_IRRL_TAIL_RD_S 8 +#define V2_QPC_BYTE_240_IRRL_TAIL_RD_M GENMASK(15, 8) + +#define V2_QPC_BYTE_240_RX_ACK_MSN_S 16 +#define V2_QPC_BYTE_240_RX_ACK_MSN_M GENMASK(31, 16) + +#define V2_QPC_BYTE_244_RX_ACK_EPSN_S 0 +#define V2_QPC_BYTE_244_RX_ACK_EPSN_M GENMASK(23, 0) + +#define V2_QPC_BYTE_244_RNR_NUM_INIT_S 24 +#define V2_QPC_BYTE_244_RNR_NUM_INIT_M GENMASK(26, 24) + +#define V2_QPC_BYTE_244_RNR_CNT_S 27 +#define V2_QPC_BYTE_244_RNR_CNT_M GENMASK(29, 27) + +#define V2_QPC_BYTE_248_IRRL_PSN_S 0 +#define V2_QPC_BYTE_248_IRRL_PSN_M GENMASK(23, 0) + +#define V2_QPC_BYTE_248_ACK_PSN_ERR_S 24 + +#define V2_QPC_BYTE_248_ACK_LAST_OPTYPE_S 25 +#define V2_QPC_BYTE_248_ACK_LAST_OPTYPE_M GENMASK(26, 25) + +#define V2_QPC_BYTE_248_IRRL_PSN_VLD_S 27 + +#define V2_QPC_BYTE_248_RNR_RETRY_FLAG_S 28 + +#define V2_QPC_BYTE_248_CQ_ERR_IND_S 31 + +#define V2_QPC_BYTE_252_TX_CQN_S 0 +#define V2_QPC_BYTE_252_TX_CQN_M GENMASK(23, 0) + +#define V2_QPC_BYTE_252_SIG_TYPE_S 24 + +#define V2_QPC_BYTE_252_ERR_TYPE_S 25 +#define V2_QPC_BYTE_252_ERR_TYPE_M GENMASK(31, 25) + +#define V2_QPC_BYTE_256_RQ_CQE_IDX_S 0 +#define V2_QPC_BYTE_256_RQ_CQE_IDX_M GENMASK(15, 0) + +#define V2_QPC_BYTE_256_SQ_FLUSH_IDX_S 16 +#define V2_QPC_BYTE_256_SQ_FLUSH_IDX_M GENMASK(31, 16) + +struct hns_roce_v2_cqe { + u32 byte_4; + u32 rkey_immtdata; + u32 byte_12; + u32 byte_16; + u32 byte_cnt; + u32 smac; + u32 byte_28; + u32 byte_32; +}; + +#define V2_CQE_BYTE_4_OPCODE_S 0 +#define V2_CQE_BYTE_4_OPCODE_M GENMASK(4, 0) + +#define V2_CQE_BYTE_4_RQ_INLINE_S 5 + +#define V2_CQE_BYTE_4_S_R_S 6 + +#define V2_CQE_BYTE_4_OWNER_S 7 + +#define V2_CQE_BYTE_4_STATUS_S 8 +#define V2_CQE_BYTE_4_STATUS_M GENMASK(15, 8) + +#define V2_CQE_BYTE_4_WQE_INDX_S 16 +#define V2_CQE_BYTE_4_WQE_INDX_M GENMASK(31, 16) + +#define V2_CQE_BYTE_12_XRC_SRQN_S 0 +#define V2_CQE_BYTE_12_XRC_SRQN_M GENMASK(23, 0) + +#define V2_CQE_BYTE_16_LCL_QPN_S 0 +#define V2_CQE_BYTE_16_LCL_QPN_M GENMASK(23, 0) + +#define V2_CQE_BYTE_16_SUB_STATUS_S 24 +#define V2_CQE_BYTE_16_SUB_STATUS_M GENMASK(31, 24) + +#define V2_CQE_BYTE_28_SMAC_4_S 0 +#define V2_CQE_BYTE_28_SMAC_4_M GENMASK(7, 0) + +#define V2_CQE_BYTE_28_SMAC_5_S 8 +#define V2_CQE_BYTE_28_SMAC_5_M GENMASK(15, 8) + +#define V2_CQE_BYTE_28_PORT_TYPE_S 16 +#define V2_CQE_BYTE_28_PORT_TYPE_M GENMASK(17, 16) + +#define V2_CQE_BYTE_32_RMT_QPN_S 0 +#define V2_CQE_BYTE_32_RMT_QPN_M GENMASK(23, 0) + +#define V2_CQE_BYTE_32_SL_S 24 +#define V2_CQE_BYTE_32_SL_M GENMASK(26, 24) + +#define V2_CQE_BYTE_32_PORTN_S 27 +#define V2_CQE_BYTE_32_PORTN_M GENMASK(29, 27) + +#define V2_CQE_BYTE_32_GRH_S 30 + +#define V2_CQE_BYTE_32_LPK_S 31 + +struct hns_roce_v2_mpt_entry { + __le32 byte_4_pd_hop_st; + __le32 byte_8_mw_cnt_en; + __le32 byte_12_mw_pa; + __le32 bound_lkey; + __le32 len_l; + __le32 len_h; + __le32 lkey; + __le32 va_l; + __le32 va_h; + __le32 pbl_size; + __le32 pbl_ba_l; + __le32 byte_48_mode_ba; + __le32 pa0_l; + __le32 byte_56_pa0_h; + __le32 pa1_l; + __le32 byte_64_buf_pa1; +}; + +#define V2_MPT_BYTE_4_MPT_ST_S 0 +#define V2_MPT_BYTE_4_MPT_ST_M GENMASK(1, 0) + +#define V2_MPT_BYTE_4_PBL_HOP_NUM_S 2 +#define V2_MPT_BYTE_4_PBL_HOP_NUM_M GENMASK(3, 2) + +#define V2_MPT_BYTE_4_PBL_BA_PG_SZ_S 4 +#define V2_MPT_BYTE_4_PBL_BA_PG_SZ_M GENMASK(7, 4) + +#define V2_MPT_BYTE_4_PD_S 8 +#define V2_MPT_BYTE_4_PD_M GENMASK(31, 8) + +#define V2_MPT_BYTE_8_RA_EN_S 0 + +#define V2_MPT_BYTE_8_R_INV_EN_S 1 + +#define V2_MPT_BYTE_8_L_INV_EN_S 2 + +#define V2_MPT_BYTE_8_BIND_EN_S 3 + +#define V2_MPT_BYTE_8_ATOMIC_EN_S 4 + +#define V2_MPT_BYTE_8_RR_EN_S 5 + +#define V2_MPT_BYTE_8_RW_EN_S 6 + +#define V2_MPT_BYTE_8_LW_EN_S 7 + +#define V2_MPT_BYTE_12_PA_S 1 + +#define V2_MPT_BYTE_12_INNER_PA_VLD_S 7 + +#define V2_MPT_BYTE_12_MW_BIND_QPN_S 8 +#define V2_MPT_BYTE_12_MW_BIND_QPN_M GENMASK(31, 8) + +#define V2_MPT_BYTE_48_PBL_BA_H_S 0 +#define V2_MPT_BYTE_48_PBL_BA_H_M GENMASK(28, 0) + +#define V2_MPT_BYTE_48_BLK_MODE_S 29 + +#define V2_MPT_BYTE_56_PA0_H_S 0 +#define V2_MPT_BYTE_56_PA0_H_M GENMASK(25, 0) + +#define V2_MPT_BYTE_64_PA1_H_S 0 +#define V2_MPT_BYTE_64_PA1_H_M GENMASK(25, 0) + +#define V2_MPT_BYTE_64_PBL_BUF_PG_SZ_S 28 +#define V2_MPT_BYTE_64_PBL_BUF_PG_SZ_M GENMASK(31, 28) + +#define V2_DB_BYTE_4_TAG_S 0 +#define V2_DB_BYTE_4_TAG_M GENMASK(23, 0) + +#define V2_DB_BYTE_4_CMD_S 24 +#define V2_DB_BYTE_4_CMD_M GENMASK(27, 24) + +#define V2_DB_PARAMETER_CONS_IDX_S 0 +#define V2_DB_PARAMETER_CONS_IDX_M GENMASK(15, 0) + +#define V2_DB_PARAMETER_SL_S 16 +#define V2_DB_PARAMETER_SL_M GENMASK(18, 16) + +struct hns_roce_v2_cq_db { + u32 byte_4; + u32 parameter; +}; + +#define V2_CQ_DB_BYTE_4_TAG_S 0 +#define V2_CQ_DB_BYTE_4_TAG_M GENMASK(23, 0) + +#define V2_CQ_DB_BYTE_4_CMD_S 24 +#define V2_CQ_DB_BYTE_4_CMD_M GENMASK(27, 24) + +#define V2_CQ_DB_PARAMETER_CONS_IDX_S 0 +#define V2_CQ_DB_PARAMETER_CONS_IDX_M GENMASK(23, 0) + +#define V2_CQ_DB_PARAMETER_CMD_SN_S 25 +#define V2_CQ_DB_PARAMETER_CMD_SN_M GENMASK(26, 25) + +#define V2_CQ_DB_PARAMETER_NOTIFY_S 24 + +struct hns_roce_v2_rc_send_wqe { + u32 byte_4; + u32 msg_len; + u32 inv_key_immtdata; + u32 byte_16; + u32 byte_20; + u32 rkey; + u64 va; +}; + +#define V2_RC_SEND_WQE_BYTE_4_OPCODE_S 0 +#define V2_RC_SEND_WQE_BYTE_4_OPCODE_M GENMASK(4, 0) + +#define V2_RC_SEND_WQE_BYTE_4_OWNER_S 7 + +#define V2_RC_SEND_WQE_BYTE_4_CQE_S 8 + +#define V2_RC_SEND_WQE_BYTE_4_FENCE_S 9 + +#define V2_RC_SEND_WQE_BYTE_4_SO_S 10 + +#define V2_RC_SEND_WQE_BYTE_4_SE_S 11 + +#define V2_RC_SEND_WQE_BYTE_4_INLINE_S 12 + +#define V2_RC_SEND_WQE_BYTE_16_XRC_SRQN_S 0 +#define V2_RC_SEND_WQE_BYTE_16_XRC_SRQN_M GENMASK(23, 0) + +#define V2_RC_SEND_WQE_BYTE_16_SGE_NUM_S 24 +#define V2_RC_SEND_WQE_BYTE_16_SGE_NUM_M GENMASK(31, 24) + +#define V2_RC_SEND_WQE_BYTE_20_MSG_START_SGE_IDX_S 0 +#define V2_RC_SEND_WQE_BYTE_20_MSG_START_SGE_IDX_M GENMASK(23, 0) + +struct hns_roce_v2_wqe_data_seg { + __be32 len; + __be32 lkey; + __be64 addr; +}; + +struct hns_roce_v2_db { + u32 byte_4; + u32 parameter; +}; + +struct hns_roce_query_version { + __le16 rocee_vendor_id; + __le16 rocee_hw_version; + __le32 rsv[5]; +}; + +struct hns_roce_cfg_global_param { + __le32 time_cfg_udp_port; + __le32 rsv[5]; +}; + +#define CFG_GLOBAL_PARAM_DATA_0_ROCEE_TIME_1US_CFG_S 0 +#define CFG_GLOBAL_PARAM_DATA_0_ROCEE_TIME_1US_CFG_M GENMASK(9, 0) + +#define CFG_GLOBAL_PARAM_DATA_0_ROCEE_UDP_PORT_S 16 +#define CFG_GLOBAL_PARAM_DATA_0_ROCEE_UDP_PORT_M GENMASK(31, 16) + +struct hns_roce_pf_res { + __le32 rsv; + __le32 qpc_bt_idx_num; + __le32 srqc_bt_idx_num; + __le32 cqc_bt_idx_num; + __le32 mpt_bt_idx_num; + __le32 eqc_bt_idx_num; +}; + +#define PF_RES_DATA_1_PF_QPC_BT_IDX_S 0 +#define PF_RES_DATA_1_PF_QPC_BT_IDX_M GENMASK(10, 0) + +#define PF_RES_DATA_1_PF_QPC_BT_NUM_S 16 +#define PF_RES_DATA_1_PF_QPC_BT_NUM_M GENMASK(27, 16) + +#define PF_RES_DATA_2_PF_SRQC_BT_IDX_S 0 +#define PF_RES_DATA_2_PF_SRQC_BT_IDX_M GENMASK(8, 0) + +#define PF_RES_DATA_2_PF_SRQC_BT_NUM_S 16 +#define PF_RES_DATA_2_PF_SRQC_BT_NUM_M GENMASK(25, 16) + +#define PF_RES_DATA_3_PF_CQC_BT_IDX_S 0 +#define PF_RES_DATA_3_PF_CQC_BT_IDX_M GENMASK(8, 0) + +#define PF_RES_DATA_3_PF_CQC_BT_NUM_S 16 +#define PF_RES_DATA_3_PF_CQC_BT_NUM_M GENMASK(25, 16) + +#define PF_RES_DATA_4_PF_MPT_BT_IDX_S 0 +#define PF_RES_DATA_4_PF_MPT_BT_IDX_M GENMASK(8, 0) + +#define PF_RES_DATA_4_PF_MPT_BT_NUM_S 16 +#define PF_RES_DATA_4_PF_MPT_BT_NUM_M GENMASK(25, 16) + +#define PF_RES_DATA_5_PF_EQC_BT_IDX_S 0 +#define PF_RES_DATA_5_PF_EQC_BT_IDX_M GENMASK(8, 0) + +#define PF_RES_DATA_5_PF_EQC_BT_NUM_S 16 +#define PF_RES_DATA_5_PF_EQC_BT_NUM_M GENMASK(25, 16) + +struct hns_roce_vf_res_a { + u32 vf_id; + u32 vf_qpc_bt_idx_num; + u32 vf_srqc_bt_idx_num; + u32 vf_cqc_bt_idx_num; + u32 vf_mpt_bt_idx_num; + u32 vf_eqc_bt_idx_num; +}; + +#define VF_RES_A_DATA_1_VF_QPC_BT_IDX_S 0 +#define VF_RES_A_DATA_1_VF_QPC_BT_IDX_M GENMASK(10, 0) + +#define VF_RES_A_DATA_1_VF_QPC_BT_NUM_S 16 +#define VF_RES_A_DATA_1_VF_QPC_BT_NUM_M GENMASK(27, 16) + +#define VF_RES_A_DATA_2_VF_SRQC_BT_IDX_S 0 +#define VF_RES_A_DATA_2_VF_SRQC_BT_IDX_M GENMASK(8, 0) + +#define VF_RES_A_DATA_2_VF_SRQC_BT_NUM_S 16 +#define VF_RES_A_DATA_2_VF_SRQC_BT_NUM_M GENMASK(25, 16) + +#define VF_RES_A_DATA_3_VF_CQC_BT_IDX_S 0 +#define VF_RES_A_DATA_3_VF_CQC_BT_IDX_M GENMASK(8, 0) + +#define VF_RES_A_DATA_3_VF_CQC_BT_NUM_S 16 +#define VF_RES_A_DATA_3_VF_CQC_BT_NUM_M GENMASK(25, 16) + +#define VF_RES_A_DATA_4_VF_MPT_BT_IDX_S 0 +#define VF_RES_A_DATA_4_VF_MPT_BT_IDX_M GENMASK(8, 0) + +#define VF_RES_A_DATA_4_VF_MPT_BT_NUM_S 16 +#define VF_RES_A_DATA_4_VF_MPT_BT_NUM_M GENMASK(25, 16) + +#define VF_RES_A_DATA_5_VF_EQC_IDX_S 0 +#define VF_RES_A_DATA_5_VF_EQC_IDX_M GENMASK(8, 0) + +#define VF_RES_A_DATA_5_VF_EQC_NUM_S 16 +#define VF_RES_A_DATA_5_VF_EQC_NUM_M GENMASK(25, 16) + +struct hns_roce_vf_res_b { + u32 rsv0; + u32 vf_smac_idx_num; + u32 vf_sgid_idx_num; + u32 vf_qid_idx_sl_num; + u32 rsv[2]; +}; + +#define VF_RES_B_DATA_0_VF_ID_S 0 +#define VF_RES_B_DATA_0_VF_ID_M GENMASK(7, 0) + +#define VF_RES_B_DATA_1_VF_SMAC_IDX_S 0 +#define VF_RES_B_DATA_1_VF_SMAC_IDX_M GENMASK(7, 0) + +#define VF_RES_B_DATA_1_VF_SMAC_NUM_S 8 +#define VF_RES_B_DATA_1_VF_SMAC_NUM_M GENMASK(16, 8) + +#define VF_RES_B_DATA_2_VF_SGID_IDX_S 0 +#define VF_RES_B_DATA_2_VF_SGID_IDX_M GENMASK(7, 0) + +#define VF_RES_B_DATA_2_VF_SGID_NUM_S 8 +#define VF_RES_B_DATA_2_VF_SGID_NUM_M GENMASK(16, 8) + +#define VF_RES_B_DATA_3_VF_QID_IDX_S 0 +#define VF_RES_B_DATA_3_VF_QID_IDX_M GENMASK(9, 0) + +#define VF_RES_B_DATA_3_VF_SL_NUM_S 16 +#define VF_RES_B_DATA_3_VF_SL_NUM_M GENMASK(19, 16) + +/* Reg field definition */ +#define ROCEE_VF_SMAC_CFG1_VF_SMAC_H_S 0 +#define ROCEE_VF_SMAC_CFG1_VF_SMAC_H_M GENMASK(15, 0) + +#define ROCEE_VF_SGID_CFG4_SGID_TYPE_S 0 +#define ROCEE_VF_SGID_CFG4_SGID_TYPE_M GENMASK(1, 0) + +struct hns_roce_cfg_bt_attr { + u32 vf_qpc_cfg; + u32 vf_srqc_cfg; + u32 vf_cqc_cfg; + u32 vf_mpt_cfg; + u32 rsv[2]; +}; + +#define CFG_BT_ATTR_DATA_0_VF_QPC_BA_PGSZ_S 0 +#define CFG_BT_ATTR_DATA_0_VF_QPC_BA_PGSZ_M GENMASK(3, 0) + +#define CFG_BT_ATTR_DATA_0_VF_QPC_BUF_PGSZ_S 4 +#define CFG_BT_ATTR_DATA_0_VF_QPC_BUF_PGSZ_M GENMASK(7, 4) + +#define CFG_BT_ATTR_DATA_0_VF_QPC_HOPNUM_S 8 +#define CFG_BT_ATTR_DATA_0_VF_QPC_HOPNUM_M GENMASK(9, 8) + +#define CFG_BT_ATTR_DATA_1_VF_SRQC_BA_PGSZ_S 0 +#define CFG_BT_ATTR_DATA_1_VF_SRQC_BA_PGSZ_M GENMASK(3, 0) + +#define CFG_BT_ATTR_DATA_1_VF_SRQC_BUF_PGSZ_S 4 +#define CFG_BT_ATTR_DATA_1_VF_SRQC_BUF_PGSZ_M GENMASK(7, 4) + +#define CFG_BT_ATTR_DATA_1_VF_SRQC_HOPNUM_S 8 +#define CFG_BT_ATTR_DATA_1_VF_SRQC_HOPNUM_M GENMASK(9, 8) + +#define CFG_BT_ATTR_DATA_2_VF_CQC_BA_PGSZ_S 0 +#define CFG_BT_ATTR_DATA_2_VF_CQC_BA_PGSZ_M GENMASK(3, 0) + +#define CFG_BT_ATTR_DATA_2_VF_CQC_BUF_PGSZ_S 4 +#define CFG_BT_ATTR_DATA_2_VF_CQC_BUF_PGSZ_M GENMASK(7, 4) + +#define CFG_BT_ATTR_DATA_2_VF_CQC_HOPNUM_S 8 +#define CFG_BT_ATTR_DATA_2_VF_CQC_HOPNUM_M GENMASK(9, 8) + +#define CFG_BT_ATTR_DATA_3_VF_MPT_BA_PGSZ_S 0 +#define CFG_BT_ATTR_DATA_3_VF_MPT_BA_PGSZ_M GENMASK(3, 0) + +#define CFG_BT_ATTR_DATA_3_VF_MPT_BUF_PGSZ_S 4 +#define CFG_BT_ATTR_DATA_3_VF_MPT_BUF_PGSZ_M GENMASK(7, 4) + +#define CFG_BT_ATTR_DATA_3_VF_MPT_HOPNUM_S 8 +#define CFG_BT_ATTR_DATA_3_VF_MPT_HOPNUM_M GENMASK(9, 8) + +struct hns_roce_cmq_desc { + u16 opcode; + u16 flag; + u16 retval; + u16 rsv; + u32 data[6]; +}; + +#define ROCEE_VF_MB_CFG0_REG 0x40 +#define ROCEE_VF_MB_STATUS_REG 0x58 + +#define HNS_ROCE_V2_GO_BIT_TIMEOUT_MSECS 10000 + +#define HNS_ROCE_HW_RUN_BIT_SHIFT 31 +#define HNS_ROCE_HW_MB_STATUS_MASK 0xFF + +#define HNS_ROCE_VF_MB4_TAG_MASK 0xFFFFFF00 +#define HNS_ROCE_VF_MB4_TAG_SHIFT 8 + +#define HNS_ROCE_VF_MB4_CMD_MASK 0xFF +#define HNS_ROCE_VF_MB4_CMD_SHIFT 0 + +#define HNS_ROCE_VF_MB5_EVENT_MASK 0x10000 +#define HNS_ROCE_VF_MB5_EVENT_SHIFT 16 + +#define HNS_ROCE_VF_MB5_TOKEN_MASK 0xFFFF +#define HNS_ROCE_VF_MB5_TOKEN_SHIFT 0 + +struct hns_roce_v2_cmq_ring { + dma_addr_t desc_dma_addr; + struct hns_roce_cmq_desc *desc; + u32 head; + u32 tail; + + u16 buf_size; + u16 desc_num; + int next_to_use; + int next_to_clean; + u8 flag; + spinlock_t lock; /* command queue lock */ +}; + +struct hns_roce_v2_cmq { + struct hns_roce_v2_cmq_ring csq; + struct hns_roce_v2_cmq_ring crq; + u16 tx_timeout; + u16 last_status; +}; + +struct hns_roce_v2_priv { + struct hns_roce_v2_cmq cmq; +}; + +#endif diff --git a/drivers/infiniband/hw/hns/hns_roce_main.c b/drivers/infiniband/hw/hns/hns_roce_main.c index d9777b662eba..31120fd5e76b 100644 --- a/drivers/infiniband/hw/hns/hns_roce_main.c +++ b/drivers/infiniband/hw/hns/hns_roce_main.c @@ -57,20 +57,21 @@ int hns_get_gid_index(struct hns_roce_dev *hr_dev, u8 port, int gid_index) { return gid_index * hr_dev->caps.num_ports + port; } +EXPORT_SYMBOL_GPL(hns_get_gid_index); -static void hns_roce_set_mac(struct hns_roce_dev *hr_dev, u8 port, u8 *addr) +static int hns_roce_set_mac(struct hns_roce_dev *hr_dev, u8 port, u8 *addr) { u8 phy_port; u32 i = 0; if (!memcmp(hr_dev->dev_addr[port], addr, MAC_ADDR_OCTET_NUM)) - return; + return 0; for (i = 0; i < MAC_ADDR_OCTET_NUM; i++) hr_dev->dev_addr[port][i] = addr[i]; phy_port = hr_dev->iboe.phy_port[port]; - hr_dev->hw->set_mac(hr_dev, phy_port, addr); + return hr_dev->hw->set_mac(hr_dev, phy_port, addr); } static int hns_roce_add_gid(struct ib_device *device, u8 port_num, @@ -116,8 +117,9 @@ static int hns_roce_del_gid(struct ib_device *device, u8 port_num, static int handle_en_event(struct hns_roce_dev *hr_dev, u8 port, unsigned long event) { - struct device *dev = &hr_dev->pdev->dev; + struct device *dev = hr_dev->dev; struct net_device *netdev; + int ret = 0; netdev = hr_dev->iboe.netdevs[port]; if (!netdev) { @@ -130,7 +132,7 @@ static int handle_en_event(struct hns_roce_dev *hr_dev, u8 port, case NETDEV_CHANGE: case NETDEV_REGISTER: case NETDEV_CHANGEADDR: - hns_roce_set_mac(hr_dev, port, netdev->dev_addr); + ret = hns_roce_set_mac(hr_dev, port, netdev->dev_addr); break; case NETDEV_DOWN: /* @@ -142,7 +144,7 @@ static int handle_en_event(struct hns_roce_dev *hr_dev, u8 port, break; } - return 0; + return ret; } static int hns_roce_netdev_event(struct notifier_block *self, @@ -171,12 +173,17 @@ static int hns_roce_netdev_event(struct notifier_block *self, static int hns_roce_setup_mtu_mac(struct hns_roce_dev *hr_dev) { + int ret; u8 i; for (i = 0; i < hr_dev->caps.num_ports; i++) { - hr_dev->hw->set_mtu(hr_dev, hr_dev->iboe.phy_port[i], - hr_dev->caps.max_mtu); - hns_roce_set_mac(hr_dev, i, hr_dev->iboe.netdevs[i]->dev_addr); + if (hr_dev->hw->set_mtu) + hr_dev->hw->set_mtu(hr_dev, hr_dev->iboe.phy_port[i], + hr_dev->caps.max_mtu); + ret = hns_roce_set_mac(hr_dev, i, + hr_dev->iboe.netdevs[i]->dev_addr); + if (ret) + return ret; } return 0; @@ -200,7 +207,7 @@ static int hns_roce_query_device(struct ib_device *ib_dev, props->max_qp_wr = hr_dev->caps.max_wqes; props->device_cap_flags = IB_DEVICE_PORT_ACTIVE_EVENT | IB_DEVICE_RC_RNR_NAK_GEN; - props->max_sge = hr_dev->caps.max_sq_sg; + props->max_sge = max(hr_dev->caps.max_sq_sg, hr_dev->caps.max_rq_sg); props->max_sge_rd = 1; props->max_cq = hr_dev->caps.num_cqs; props->max_cqe = hr_dev->caps.max_cqes; @@ -238,7 +245,7 @@ static int hns_roce_query_port(struct ib_device *ib_dev, u8 port_num, struct ib_port_attr *props) { struct hns_roce_dev *hr_dev = to_hr_dev(ib_dev); - struct device *dev = &hr_dev->pdev->dev; + struct device *dev = hr_dev->dev; struct net_device *net_dev; unsigned long flags; enum ib_mtu mtu; @@ -379,7 +386,8 @@ static int hns_roce_mmap(struct ib_ucontext *context, to_hr_ucontext(context)->uar.pfn, PAGE_SIZE, vma->vm_page_prot)) return -EAGAIN; - } else if (vma->vm_pgoff == 1 && hr_dev->hw_rev == HNS_ROCE_HW_VER1) { + } else if (vma->vm_pgoff == 1 && hr_dev->tptr_dma_addr && + hr_dev->tptr_size) { /* vm_pgoff: 1 -- TPTR */ if (io_remap_pfn_range(vma, vma->vm_start, hr_dev->tptr_dma_addr >> PAGE_SHIFT, @@ -416,7 +424,6 @@ static void hns_roce_unregister_device(struct hns_roce_dev *hr_dev) { struct hns_roce_ib_iboe *iboe = &hr_dev->iboe; - unregister_inetaddr_notifier(&iboe->nb_inet); unregister_netdevice_notifier(&iboe->nb); ib_unregister_device(&hr_dev->ib_dev); } @@ -426,7 +433,7 @@ static int hns_roce_register_device(struct hns_roce_dev *hr_dev) int ret; struct hns_roce_ib_iboe *iboe = NULL; struct ib_device *ib_dev = NULL; - struct device *dev = &hr_dev->pdev->dev; + struct device *dev = hr_dev->dev; iboe = &hr_dev->iboe; spin_lock_init(&iboe->lock); @@ -492,6 +499,7 @@ static int hns_roce_register_device(struct hns_roce_dev *hr_dev) /* CQ */ ib_dev->create_cq = hns_roce_ib_create_cq; + ib_dev->modify_cq = hr_dev->hw->modify_cq; ib_dev->destroy_cq = hns_roce_ib_destroy_cq; ib_dev->req_notify_cq = hr_dev->hw->req_notify_cq; ib_dev->poll_cq = hr_dev->hw->poll_cq; @@ -531,173 +539,10 @@ error_failed_setup_mtu_mac: return ret; } -static const struct of_device_id hns_roce_of_match[] = { - { .compatible = "hisilicon,hns-roce-v1", .data = &hns_roce_hw_v1, }, - {}, -}; -MODULE_DEVICE_TABLE(of, hns_roce_of_match); - -static const struct acpi_device_id hns_roce_acpi_match[] = { - { "HISI00D1", (kernel_ulong_t)&hns_roce_hw_v1 }, - {}, -}; -MODULE_DEVICE_TABLE(acpi, hns_roce_acpi_match); - -static int hns_roce_node_match(struct device *dev, void *fwnode) -{ - return dev->fwnode == fwnode; -} - -static struct -platform_device *hns_roce_find_pdev(struct fwnode_handle *fwnode) -{ - struct device *dev; - - /* get the 'device'corresponding to matching 'fwnode' */ - dev = bus_find_device(&platform_bus_type, NULL, - fwnode, hns_roce_node_match); - /* get the platform device */ - return dev ? to_platform_device(dev) : NULL; -} - -static int hns_roce_get_cfg(struct hns_roce_dev *hr_dev) -{ - int i; - int ret; - u8 phy_port; - int port_cnt = 0; - struct device *dev = &hr_dev->pdev->dev; - struct device_node *net_node; - struct net_device *netdev = NULL; - struct platform_device *pdev = NULL; - struct resource *res; - - /* check if we are compatible with the underlying SoC */ - if (dev_of_node(dev)) { - const struct of_device_id *of_id; - - of_id = of_match_node(hns_roce_of_match, dev->of_node); - if (!of_id) { - dev_err(dev, "device is not compatible!\n"); - return -ENXIO; - } - hr_dev->hw = (struct hns_roce_hw *)of_id->data; - if (!hr_dev->hw) { - dev_err(dev, "couldn't get H/W specific DT data!\n"); - return -ENXIO; - } - } else if (is_acpi_device_node(dev->fwnode)) { - const struct acpi_device_id *acpi_id; - - acpi_id = acpi_match_device(hns_roce_acpi_match, dev); - if (!acpi_id) { - dev_err(dev, "device is not compatible!\n"); - return -ENXIO; - } - hr_dev->hw = (struct hns_roce_hw *) acpi_id->driver_data; - if (!hr_dev->hw) { - dev_err(dev, "couldn't get H/W specific ACPI data!\n"); - return -ENXIO; - } - } else { - dev_err(dev, "can't read compatibility data from DT or ACPI\n"); - return -ENXIO; - } - - /* get the mapped register base address */ - res = platform_get_resource(hr_dev->pdev, IORESOURCE_MEM, 0); - if (!res) { - dev_err(dev, "memory resource not found!\n"); - return -EINVAL; - } - hr_dev->reg_base = devm_ioremap_resource(dev, res); - if (IS_ERR(hr_dev->reg_base)) - return PTR_ERR(hr_dev->reg_base); - - /* read the node_guid of IB device from the DT or ACPI */ - ret = device_property_read_u8_array(dev, "node-guid", - (u8 *)&hr_dev->ib_dev.node_guid, - GUID_LEN); - if (ret) { - dev_err(dev, "couldn't get node_guid from DT or ACPI!\n"); - return ret; - } - - /* get the RoCE associated ethernet ports or netdevices */ - for (i = 0; i < HNS_ROCE_MAX_PORTS; i++) { - if (dev_of_node(dev)) { - net_node = of_parse_phandle(dev->of_node, "eth-handle", - i); - if (!net_node) - continue; - pdev = of_find_device_by_node(net_node); - } else if (is_acpi_device_node(dev->fwnode)) { - struct acpi_reference_args args; - struct fwnode_handle *fwnode; - - ret = acpi_node_get_property_reference(dev->fwnode, - "eth-handle", - i, &args); - if (ret) - continue; - fwnode = acpi_fwnode_handle(args.adev); - pdev = hns_roce_find_pdev(fwnode); - } else { - dev_err(dev, "cannot read data from DT or ACPI\n"); - return -ENXIO; - } - - if (pdev) { - netdev = platform_get_drvdata(pdev); - phy_port = (u8)i; - if (netdev) { - hr_dev->iboe.netdevs[port_cnt] = netdev; - hr_dev->iboe.phy_port[port_cnt] = phy_port; - } else { - dev_err(dev, "no netdev found with pdev %s\n", - pdev->name); - return -ENODEV; - } - port_cnt++; - } - } - - if (port_cnt == 0) { - dev_err(dev, "unable to get eth-handle for available ports!\n"); - return -EINVAL; - } - - hr_dev->caps.num_ports = port_cnt; - - /* cmd issue mode: 0 is poll, 1 is event */ - hr_dev->cmd_mod = 1; - hr_dev->loop_idc = 0; - - /* read the interrupt names from the DT or ACPI */ - ret = device_property_read_string_array(dev, "interrupt-names", - hr_dev->irq_names, - HNS_ROCE_MAX_IRQ_NUM); - if (ret < 0) { - dev_err(dev, "couldn't get interrupt names from DT or ACPI!\n"); - return ret; - } - - /* fetch the interrupt numbers */ - for (i = 0; i < HNS_ROCE_MAX_IRQ_NUM; i++) { - hr_dev->irq[i] = platform_get_irq(hr_dev->pdev, i); - if (hr_dev->irq[i] <= 0) { - dev_err(dev, "platform get of irq[=%d] failed!\n", i); - return -EINVAL; - } - } - - return 0; -} - static int hns_roce_init_hem(struct hns_roce_dev *hr_dev) { int ret; - struct device *dev = &hr_dev->pdev->dev; + struct device *dev = hr_dev->dev; ret = hns_roce_init_hem_table(hr_dev, &hr_dev->mr_table.mtt_table, HEM_TYPE_MTT, hr_dev->caps.mtt_entry_sz, @@ -707,6 +552,17 @@ static int hns_roce_init_hem(struct hns_roce_dev *hr_dev) return ret; } + if (hns_roce_check_whether_mhop(hr_dev, HEM_TYPE_CQE)) { + ret = hns_roce_init_hem_table(hr_dev, + &hr_dev->mr_table.mtt_cqe_table, + HEM_TYPE_CQE, hr_dev->caps.mtt_entry_sz, + hr_dev->caps.num_cqe_segs, 1); + if (ret) { + dev_err(dev, "Failed to init MTT CQE context memory, aborting.\n"); + goto err_unmap_cqe; + } + } + ret = hns_roce_init_hem_table(hr_dev, &hr_dev->mr_table.mtpt_table, HEM_TYPE_MTPT, hr_dev->caps.mtpt_entry_sz, hr_dev->caps.num_mtpts, 1); @@ -754,6 +610,12 @@ err_unmap_dmpt: err_unmap_mtt: hns_roce_cleanup_hem_table(hr_dev, &hr_dev->mr_table.mtt_table); + if (hns_roce_check_whether_mhop(hr_dev, HEM_TYPE_CQE)) + hns_roce_cleanup_hem_table(hr_dev, + &hr_dev->mr_table.mtt_cqe_table); + +err_unmap_cqe: + hns_roce_cleanup_hem_table(hr_dev, &hr_dev->mr_table.mtt_table); return ret; } @@ -766,7 +628,7 @@ err_unmap_mtt: static int hns_roce_setup_hca(struct hns_roce_dev *hr_dev) { int ret; - struct device *dev = &hr_dev->pdev->dev; + struct device *dev = hr_dev->dev; spin_lock_init(&hr_dev->sm_lock); spin_lock_init(&hr_dev->bt_cmd_lock); @@ -826,56 +688,45 @@ err_uar_table_free: return ret; } -/** - * hns_roce_probe - RoCE driver entrance - * @pdev: pointer to platform device - * Return : int - * - */ -static int hns_roce_probe(struct platform_device *pdev) +int hns_roce_init(struct hns_roce_dev *hr_dev) { int ret; - struct hns_roce_dev *hr_dev; - struct device *dev = &pdev->dev; - - hr_dev = (struct hns_roce_dev *)ib_alloc_device(sizeof(*hr_dev)); - if (!hr_dev) - return -ENOMEM; + struct device *dev = hr_dev->dev; - hr_dev->pdev = pdev; - platform_set_drvdata(pdev, hr_dev); - - if (dma_set_mask_and_coherent(dev, DMA_BIT_MASK(64ULL)) && - dma_set_mask_and_coherent(dev, DMA_BIT_MASK(32ULL))) { - dev_err(dev, "Not usable DMA addressing mode\n"); - ret = -EIO; - goto error_failed_get_cfg; + if (hr_dev->hw->reset) { + ret = hr_dev->hw->reset(hr_dev, true); + if (ret) { + dev_err(dev, "Reset RoCE engine failed!\n"); + return ret; + } } - ret = hns_roce_get_cfg(hr_dev); - if (ret) { - dev_err(dev, "Get Configuration failed!\n"); - goto error_failed_get_cfg; + if (hr_dev->hw->cmq_init) { + ret = hr_dev->hw->cmq_init(hr_dev); + if (ret) { + dev_err(dev, "Init RoCE Command Queue failed!\n"); + goto error_failed_cmq_init; + } } - ret = hr_dev->hw->reset(hr_dev, true); + ret = hr_dev->hw->hw_profile(hr_dev); if (ret) { - dev_err(dev, "Reset RoCE engine failed!\n"); - goto error_failed_get_cfg; + dev_err(dev, "Get RoCE engine profile failed!\n"); + goto error_failed_cmd_init; } - hr_dev->hw->hw_profile(hr_dev); - ret = hns_roce_cmd_init(hr_dev); if (ret) { dev_err(dev, "cmd init failed!\n"); goto error_failed_cmd_init; } - ret = hns_roce_init_eq_table(hr_dev); - if (ret) { - dev_err(dev, "eq init failed!\n"); - goto error_failed_eq_table; + if (hr_dev->cmd_mod) { + ret = hns_roce_init_eq_table(hr_dev); + if (ret) { + dev_err(dev, "eq init failed!\n"); + goto error_failed_eq_table; + } } if (hr_dev->cmd_mod) { @@ -898,10 +749,12 @@ static int hns_roce_probe(struct platform_device *pdev) goto error_failed_setup_hca; } - ret = hr_dev->hw->hw_init(hr_dev); - if (ret) { - dev_err(dev, "hw_init failed!\n"); - goto error_failed_engine_init; + if (hr_dev->hw->hw_init) { + ret = hr_dev->hw->hw_init(hr_dev); + if (ret) { + dev_err(dev, "hw_init failed!\n"); + goto error_failed_engine_init; + } } ret = hns_roce_register_device(hr_dev); @@ -911,7 +764,8 @@ static int hns_roce_probe(struct platform_device *pdev) return 0; error_failed_register_device: - hr_dev->hw->hw_exit(hr_dev); + if (hr_dev->hw->hw_exit) + hr_dev->hw->hw_exit(hr_dev); error_failed_engine_init: hns_roce_cleanup_bitmap(hr_dev); @@ -924,58 +778,47 @@ error_failed_init_hem: hns_roce_cmd_use_polling(hr_dev); error_failed_use_event: - hns_roce_cleanup_eq_table(hr_dev); + if (hr_dev->cmd_mod) + hns_roce_cleanup_eq_table(hr_dev); error_failed_eq_table: hns_roce_cmd_cleanup(hr_dev); error_failed_cmd_init: - ret = hr_dev->hw->reset(hr_dev, false); - if (ret) - dev_err(&hr_dev->pdev->dev, "roce_engine reset fail\n"); + if (hr_dev->hw->cmq_exit) + hr_dev->hw->cmq_exit(hr_dev); -error_failed_get_cfg: - ib_dealloc_device(&hr_dev->ib_dev); +error_failed_cmq_init: + if (hr_dev->hw->reset) { + ret = hr_dev->hw->reset(hr_dev, false); + if (ret) + dev_err(dev, "Dereset RoCE engine failed!\n"); + } return ret; } +EXPORT_SYMBOL_GPL(hns_roce_init); -/** - * hns_roce_remove - remove RoCE device - * @pdev: pointer to platform device - */ -static int hns_roce_remove(struct platform_device *pdev) +void hns_roce_exit(struct hns_roce_dev *hr_dev) { - struct hns_roce_dev *hr_dev = platform_get_drvdata(pdev); - hns_roce_unregister_device(hr_dev); - hr_dev->hw->hw_exit(hr_dev); + if (hr_dev->hw->hw_exit) + hr_dev->hw->hw_exit(hr_dev); hns_roce_cleanup_bitmap(hr_dev); hns_roce_cleanup_hem(hr_dev); if (hr_dev->cmd_mod) hns_roce_cmd_use_polling(hr_dev); - hns_roce_cleanup_eq_table(hr_dev); + if (hr_dev->cmd_mod) + hns_roce_cleanup_eq_table(hr_dev); hns_roce_cmd_cleanup(hr_dev); - hr_dev->hw->reset(hr_dev, false); - - ib_dealloc_device(&hr_dev->ib_dev); - - return 0; + if (hr_dev->hw->cmq_exit) + hr_dev->hw->cmq_exit(hr_dev); + if (hr_dev->hw->reset) + hr_dev->hw->reset(hr_dev, false); } - -static struct platform_driver hns_roce_driver = { - .probe = hns_roce_probe, - .remove = hns_roce_remove, - .driver = { - .name = DRV_NAME, - .of_match_table = hns_roce_of_match, - .acpi_match_table = ACPI_PTR(hns_roce_acpi_match), - }, -}; - -module_platform_driver(hns_roce_driver); +EXPORT_SYMBOL_GPL(hns_roce_exit); MODULE_LICENSE("Dual BSD/GPL"); MODULE_AUTHOR("Wei Hu <xavier.huwei@huawei.com>"); diff --git a/drivers/infiniband/hw/hns/hns_roce_mr.c b/drivers/infiniband/hw/hns/hns_roce_mr.c index e387360e3780..c47a5ee5db17 100644 --- a/drivers/infiniband/hw/hns/hns_roce_mr.c +++ b/drivers/infiniband/hw/hns/hns_roce_mr.c @@ -47,6 +47,7 @@ unsigned long key_to_hw_index(u32 key) { return (key << 24) | (key >> 8); } +EXPORT_SYMBOL_GPL(key_to_hw_index); static int hns_roce_sw2hw_mpt(struct hns_roce_dev *hr_dev, struct hns_roce_cmd_mailbox *mailbox, @@ -65,6 +66,7 @@ int hns_roce_hw2sw_mpt(struct hns_roce_dev *hr_dev, mpt_index, !mailbox, HNS_ROCE_CMD_HW2SW_MPT, HNS_ROCE_CMD_TIMEOUT_MSECS); } +EXPORT_SYMBOL_GPL(hns_roce_hw2sw_mpt); static int hns_roce_buddy_alloc(struct hns_roce_buddy *buddy, int order, unsigned long *seg) @@ -175,18 +177,28 @@ static void hns_roce_buddy_cleanup(struct hns_roce_buddy *buddy) } static int hns_roce_alloc_mtt_range(struct hns_roce_dev *hr_dev, int order, - unsigned long *seg) + unsigned long *seg, u32 mtt_type) { struct hns_roce_mr_table *mr_table = &hr_dev->mr_table; - int ret = 0; + struct hns_roce_hem_table *table; + struct hns_roce_buddy *buddy; + int ret; + + if (mtt_type == MTT_TYPE_WQE) { + buddy = &mr_table->mtt_buddy; + table = &mr_table->mtt_table; + } else { + buddy = &mr_table->mtt_cqe_buddy; + table = &mr_table->mtt_cqe_table; + } - ret = hns_roce_buddy_alloc(&mr_table->mtt_buddy, order, seg); + ret = hns_roce_buddy_alloc(buddy, order, seg); if (ret == -1) return -1; - if (hns_roce_table_get_range(hr_dev, &mr_table->mtt_table, *seg, + if (hns_roce_table_get_range(hr_dev, table, *seg, *seg + (1 << order) - 1)) { - hns_roce_buddy_free(&mr_table->mtt_buddy, *seg, order); + hns_roce_buddy_free(buddy, *seg, order); return -1; } @@ -196,7 +208,7 @@ static int hns_roce_alloc_mtt_range(struct hns_roce_dev *hr_dev, int order, int hns_roce_mtt_init(struct hns_roce_dev *hr_dev, int npages, int page_shift, struct hns_roce_mtt *mtt) { - int ret = 0; + int ret; int i; /* Page num is zero, correspond to DMA memory register */ @@ -215,7 +227,8 @@ int hns_roce_mtt_init(struct hns_roce_dev *hr_dev, int npages, int page_shift, ++mtt->order; /* Allocate MTT entry */ - ret = hns_roce_alloc_mtt_range(hr_dev, mtt->order, &mtt->first_seg); + ret = hns_roce_alloc_mtt_range(hr_dev, mtt->order, &mtt->first_seg, + mtt->mtt_type); if (ret == -1) return -ENOMEM; @@ -229,18 +242,261 @@ void hns_roce_mtt_cleanup(struct hns_roce_dev *hr_dev, struct hns_roce_mtt *mtt) if (mtt->order < 0) return; - hns_roce_buddy_free(&mr_table->mtt_buddy, mtt->first_seg, mtt->order); - hns_roce_table_put_range(hr_dev, &mr_table->mtt_table, mtt->first_seg, - mtt->first_seg + (1 << mtt->order) - 1); + if (mtt->mtt_type == MTT_TYPE_WQE) { + hns_roce_buddy_free(&mr_table->mtt_buddy, mtt->first_seg, + mtt->order); + hns_roce_table_put_range(hr_dev, &mr_table->mtt_table, + mtt->first_seg, + mtt->first_seg + (1 << mtt->order) - 1); + } else { + hns_roce_buddy_free(&mr_table->mtt_cqe_buddy, mtt->first_seg, + mtt->order); + hns_roce_table_put_range(hr_dev, &mr_table->mtt_cqe_table, + mtt->first_seg, + mtt->first_seg + (1 << mtt->order) - 1); + } +} +EXPORT_SYMBOL_GPL(hns_roce_mtt_cleanup); + +static void hns_roce_loop_free(struct hns_roce_dev *hr_dev, + struct hns_roce_mr *mr, int err_loop_index, + int loop_i, int loop_j) +{ + struct device *dev = hr_dev->dev; + u32 mhop_num; + u32 pbl_bt_sz; + u64 bt_idx; + int i, j; + + pbl_bt_sz = 1 << (hr_dev->caps.pbl_ba_pg_sz + PAGE_SHIFT); + mhop_num = hr_dev->caps.pbl_hop_num; + + i = loop_i; + if (mhop_num == 3 && err_loop_index == 2) { + for (; i >= 0; i--) { + dma_free_coherent(dev, pbl_bt_sz, mr->pbl_bt_l1[i], + mr->pbl_l1_dma_addr[i]); + + for (j = 0; j < pbl_bt_sz / 8; j++) { + if (i == loop_i && j >= loop_j) + break; + + bt_idx = i * pbl_bt_sz / 8 + j; + dma_free_coherent(dev, pbl_bt_sz, + mr->pbl_bt_l2[bt_idx], + mr->pbl_l2_dma_addr[bt_idx]); + } + } + } else if (mhop_num == 3 && err_loop_index == 1) { + for (i -= 1; i >= 0; i--) { + dma_free_coherent(dev, pbl_bt_sz, mr->pbl_bt_l1[i], + mr->pbl_l1_dma_addr[i]); + + for (j = 0; j < pbl_bt_sz / 8; j++) { + bt_idx = i * pbl_bt_sz / 8 + j; + dma_free_coherent(dev, pbl_bt_sz, + mr->pbl_bt_l2[bt_idx], + mr->pbl_l2_dma_addr[bt_idx]); + } + } + } else if (mhop_num == 2 && err_loop_index == 1) { + for (i -= 1; i >= 0; i--) + dma_free_coherent(dev, pbl_bt_sz, mr->pbl_bt_l1[i], + mr->pbl_l1_dma_addr[i]); + } else { + dev_warn(dev, "not support: mhop_num=%d, err_loop_index=%d.", + mhop_num, err_loop_index); + return; + } + + dma_free_coherent(dev, pbl_bt_sz, mr->pbl_bt_l0, mr->pbl_l0_dma_addr); + mr->pbl_bt_l0 = NULL; + mr->pbl_l0_dma_addr = 0; +} + +/* PBL multi hop addressing */ +static int hns_roce_mhop_alloc(struct hns_roce_dev *hr_dev, int npages, + struct hns_roce_mr *mr) +{ + struct device *dev = hr_dev->dev; + int mr_alloc_done = 0; + int npages_allocated; + int i = 0, j = 0; + u32 pbl_bt_sz; + u32 mhop_num; + u64 pbl_last_bt_num; + u64 pbl_bt_cnt = 0; + u64 bt_idx; + u64 size; + + mhop_num = hr_dev->caps.pbl_hop_num; + pbl_bt_sz = 1 << (hr_dev->caps.pbl_ba_pg_sz + PAGE_SHIFT); + pbl_last_bt_num = (npages + pbl_bt_sz / 8 - 1) / (pbl_bt_sz / 8); + + if (mhop_num == HNS_ROCE_HOP_NUM_0) + return 0; + + /* hop_num = 1 */ + if (mhop_num == 1) { + if (npages > pbl_bt_sz / 8) { + dev_err(dev, "npages %d is larger than buf_pg_sz!", + npages); + return -EINVAL; + } + mr->pbl_buf = dma_alloc_coherent(dev, npages * 8, + &(mr->pbl_dma_addr), + GFP_KERNEL); + if (!mr->pbl_buf) + return -ENOMEM; + + mr->pbl_size = npages; + mr->pbl_ba = mr->pbl_dma_addr; + mr->pbl_hop_num = hr_dev->caps.pbl_hop_num; + mr->pbl_ba_pg_sz = hr_dev->caps.pbl_ba_pg_sz; + mr->pbl_buf_pg_sz = hr_dev->caps.pbl_buf_pg_sz; + return 0; + } + + mr->pbl_l1_dma_addr = kcalloc(pbl_bt_sz / 8, + sizeof(*mr->pbl_l1_dma_addr), + GFP_KERNEL); + if (!mr->pbl_l1_dma_addr) + return -ENOMEM; + + mr->pbl_bt_l1 = kcalloc(pbl_bt_sz / 8, sizeof(*mr->pbl_bt_l1), + GFP_KERNEL); + if (!mr->pbl_bt_l1) + goto err_kcalloc_bt_l1; + + if (mhop_num == 3) { + mr->pbl_l2_dma_addr = kcalloc(pbl_last_bt_num, + sizeof(*mr->pbl_l2_dma_addr), + GFP_KERNEL); + if (!mr->pbl_l2_dma_addr) + goto err_kcalloc_l2_dma; + + mr->pbl_bt_l2 = kcalloc(pbl_last_bt_num, + sizeof(*mr->pbl_bt_l2), + GFP_KERNEL); + if (!mr->pbl_bt_l2) + goto err_kcalloc_bt_l2; + } + + /* alloc L0 BT */ + mr->pbl_bt_l0 = dma_alloc_coherent(dev, pbl_bt_sz, + &(mr->pbl_l0_dma_addr), + GFP_KERNEL); + if (!mr->pbl_bt_l0) + goto err_dma_alloc_l0; + + if (mhop_num == 2) { + /* alloc L1 BT */ + for (i = 0; i < pbl_bt_sz / 8; i++) { + if (pbl_bt_cnt + 1 < pbl_last_bt_num) { + size = pbl_bt_sz; + } else { + npages_allocated = i * (pbl_bt_sz / 8); + size = (npages - npages_allocated) * 8; + } + mr->pbl_bt_l1[i] = dma_alloc_coherent(dev, size, + &(mr->pbl_l1_dma_addr[i]), + GFP_KERNEL); + if (!mr->pbl_bt_l1[i]) { + hns_roce_loop_free(hr_dev, mr, 1, i, 0); + goto err_dma_alloc_l0; + } + + *(mr->pbl_bt_l0 + i) = mr->pbl_l1_dma_addr[i]; + + pbl_bt_cnt++; + if (pbl_bt_cnt >= pbl_last_bt_num) + break; + } + } else if (mhop_num == 3) { + /* alloc L1, L2 BT */ + for (i = 0; i < pbl_bt_sz / 8; i++) { + mr->pbl_bt_l1[i] = dma_alloc_coherent(dev, pbl_bt_sz, + &(mr->pbl_l1_dma_addr[i]), + GFP_KERNEL); + if (!mr->pbl_bt_l1[i]) { + hns_roce_loop_free(hr_dev, mr, 1, i, 0); + goto err_dma_alloc_l0; + } + + *(mr->pbl_bt_l0 + i) = mr->pbl_l1_dma_addr[i]; + + for (j = 0; j < pbl_bt_sz / 8; j++) { + bt_idx = i * pbl_bt_sz / 8 + j; + + if (pbl_bt_cnt + 1 < pbl_last_bt_num) { + size = pbl_bt_sz; + } else { + npages_allocated = bt_idx * + (pbl_bt_sz / 8); + size = (npages - npages_allocated) * 8; + } + mr->pbl_bt_l2[bt_idx] = dma_alloc_coherent( + dev, size, + &(mr->pbl_l2_dma_addr[bt_idx]), + GFP_KERNEL); + if (!mr->pbl_bt_l2[bt_idx]) { + hns_roce_loop_free(hr_dev, mr, 2, i, j); + goto err_dma_alloc_l0; + } + + *(mr->pbl_bt_l1[i] + j) = + mr->pbl_l2_dma_addr[bt_idx]; + + pbl_bt_cnt++; + if (pbl_bt_cnt >= pbl_last_bt_num) { + mr_alloc_done = 1; + break; + } + } + + if (mr_alloc_done) + break; + } + } + + mr->l0_chunk_last_num = i + 1; + if (mhop_num == 3) + mr->l1_chunk_last_num = j + 1; + + mr->pbl_size = npages; + mr->pbl_ba = mr->pbl_l0_dma_addr; + mr->pbl_hop_num = hr_dev->caps.pbl_hop_num; + mr->pbl_ba_pg_sz = hr_dev->caps.pbl_ba_pg_sz; + mr->pbl_buf_pg_sz = hr_dev->caps.pbl_buf_pg_sz; + + return 0; + +err_dma_alloc_l0: + kfree(mr->pbl_bt_l2); + mr->pbl_bt_l2 = NULL; + +err_kcalloc_bt_l2: + kfree(mr->pbl_l2_dma_addr); + mr->pbl_l2_dma_addr = NULL; + +err_kcalloc_l2_dma: + kfree(mr->pbl_bt_l1); + mr->pbl_bt_l1 = NULL; + +err_kcalloc_bt_l1: + kfree(mr->pbl_l1_dma_addr); + mr->pbl_l1_dma_addr = NULL; + + return -ENOMEM; } static int hns_roce_mr_alloc(struct hns_roce_dev *hr_dev, u32 pd, u64 iova, u64 size, u32 access, int npages, struct hns_roce_mr *mr) { + struct device *dev = hr_dev->dev; unsigned long index = 0; int ret = 0; - struct device *dev = &hr_dev->pdev->dev; /* Allocate a key for mr from mr_table */ ret = hns_roce_bitmap_alloc(&hr_dev->mr_table.mtpt_bitmap, &index); @@ -258,22 +514,117 @@ static int hns_roce_mr_alloc(struct hns_roce_dev *hr_dev, u32 pd, u64 iova, mr->type = MR_TYPE_DMA; mr->pbl_buf = NULL; mr->pbl_dma_addr = 0; + /* PBL multi-hop addressing parameters */ + mr->pbl_bt_l2 = NULL; + mr->pbl_bt_l1 = NULL; + mr->pbl_bt_l0 = NULL; + mr->pbl_l2_dma_addr = NULL; + mr->pbl_l1_dma_addr = NULL; + mr->pbl_l0_dma_addr = 0; } else { mr->type = MR_TYPE_MR; - mr->pbl_buf = dma_alloc_coherent(dev, npages * 8, - &(mr->pbl_dma_addr), - GFP_KERNEL); - if (!mr->pbl_buf) - return -ENOMEM; + if (!hr_dev->caps.pbl_hop_num) { + mr->pbl_buf = dma_alloc_coherent(dev, npages * 8, + &(mr->pbl_dma_addr), + GFP_KERNEL); + if (!mr->pbl_buf) + return -ENOMEM; + } else { + ret = hns_roce_mhop_alloc(hr_dev, npages, mr); + } } - return 0; + return ret; +} + +static void hns_roce_mhop_free(struct hns_roce_dev *hr_dev, + struct hns_roce_mr *mr) +{ + struct device *dev = hr_dev->dev; + int npages_allocated; + int npages; + int i, j; + u32 pbl_bt_sz; + u32 mhop_num; + u64 bt_idx; + + npages = ib_umem_page_count(mr->umem); + pbl_bt_sz = 1 << (hr_dev->caps.pbl_ba_pg_sz + PAGE_SHIFT); + mhop_num = hr_dev->caps.pbl_hop_num; + + if (mhop_num == HNS_ROCE_HOP_NUM_0) + return; + + /* hop_num = 1 */ + if (mhop_num == 1) { + dma_free_coherent(dev, (unsigned int)(npages * 8), + mr->pbl_buf, mr->pbl_dma_addr); + return; + } + + dma_free_coherent(dev, pbl_bt_sz, mr->pbl_bt_l0, + mr->pbl_l0_dma_addr); + + if (mhop_num == 2) { + for (i = 0; i < mr->l0_chunk_last_num; i++) { + if (i == mr->l0_chunk_last_num - 1) { + npages_allocated = i * (pbl_bt_sz / 8); + + dma_free_coherent(dev, + (npages - npages_allocated) * 8, + mr->pbl_bt_l1[i], + mr->pbl_l1_dma_addr[i]); + + break; + } + + dma_free_coherent(dev, pbl_bt_sz, mr->pbl_bt_l1[i], + mr->pbl_l1_dma_addr[i]); + } + } else if (mhop_num == 3) { + for (i = 0; i < mr->l0_chunk_last_num; i++) { + dma_free_coherent(dev, pbl_bt_sz, mr->pbl_bt_l1[i], + mr->pbl_l1_dma_addr[i]); + + for (j = 0; j < pbl_bt_sz / 8; j++) { + bt_idx = i * (pbl_bt_sz / 8) + j; + + if ((i == mr->l0_chunk_last_num - 1) + && j == mr->l1_chunk_last_num - 1) { + npages_allocated = bt_idx * + (pbl_bt_sz / 8); + + dma_free_coherent(dev, + (npages - npages_allocated) * 8, + mr->pbl_bt_l2[bt_idx], + mr->pbl_l2_dma_addr[bt_idx]); + + break; + } + + dma_free_coherent(dev, pbl_bt_sz, + mr->pbl_bt_l2[bt_idx], + mr->pbl_l2_dma_addr[bt_idx]); + } + } + } + + kfree(mr->pbl_bt_l1); + kfree(mr->pbl_l1_dma_addr); + mr->pbl_bt_l1 = NULL; + mr->pbl_l1_dma_addr = NULL; + if (mhop_num == 3) { + kfree(mr->pbl_bt_l2); + kfree(mr->pbl_l2_dma_addr); + mr->pbl_bt_l2 = NULL; + mr->pbl_l2_dma_addr = NULL; + } } static void hns_roce_mr_free(struct hns_roce_dev *hr_dev, struct hns_roce_mr *mr) { - struct device *dev = &hr_dev->pdev->dev; + struct device *dev = hr_dev->dev; int npages = 0; int ret; @@ -286,10 +637,18 @@ static void hns_roce_mr_free(struct hns_roce_dev *hr_dev, if (mr->size != ~0ULL) { npages = ib_umem_page_count(mr->umem); - dma_free_coherent(dev, (unsigned int)(npages * 8), mr->pbl_buf, - mr->pbl_dma_addr); + + if (!hr_dev->caps.pbl_hop_num) + dma_free_coherent(dev, (unsigned int)(npages * 8), + mr->pbl_buf, mr->pbl_dma_addr); + else + hns_roce_mhop_free(hr_dev, mr); } + if (mr->enabled) + hns_roce_table_put(hr_dev, &hr_dev->mr_table.mtpt_table, + key_to_hw_index(mr->key)); + hns_roce_bitmap_free(&hr_dev->mr_table.mtpt_bitmap, key_to_hw_index(mr->key), BITMAP_NO_RR); } @@ -299,7 +658,7 @@ static int hns_roce_mr_enable(struct hns_roce_dev *hr_dev, { int ret; unsigned long mtpt_idx = key_to_hw_index(mr->key); - struct device *dev = &hr_dev->pdev->dev; + struct device *dev = hr_dev->dev; struct hns_roce_cmd_mailbox *mailbox; struct hns_roce_mr_table *mr_table = &hr_dev->mr_table; @@ -345,28 +704,44 @@ static int hns_roce_write_mtt_chunk(struct hns_roce_dev *hr_dev, struct hns_roce_mtt *mtt, u32 start_index, u32 npages, u64 *page_list) { - u32 i = 0; - __le64 *mtts = NULL; + struct hns_roce_hem_table *table; dma_addr_t dma_handle; + __le64 *mtts; u32 s = start_index * sizeof(u64); + u32 bt_page_size; + u32 i; + + if (mtt->mtt_type == MTT_TYPE_WQE) + bt_page_size = 1 << (hr_dev->caps.mtt_ba_pg_sz + PAGE_SHIFT); + else + bt_page_size = 1 << (hr_dev->caps.cqe_ba_pg_sz + PAGE_SHIFT); /* All MTTs must fit in the same page */ - if (start_index / (PAGE_SIZE / sizeof(u64)) != - (start_index + npages - 1) / (PAGE_SIZE / sizeof(u64))) + if (start_index / (bt_page_size / sizeof(u64)) != + (start_index + npages - 1) / (bt_page_size / sizeof(u64))) return -EINVAL; if (start_index & (HNS_ROCE_MTT_ENTRY_PER_SEG - 1)) return -EINVAL; - mtts = hns_roce_table_find(&hr_dev->mr_table.mtt_table, + if (mtt->mtt_type == MTT_TYPE_WQE) + table = &hr_dev->mr_table.mtt_table; + else + table = &hr_dev->mr_table.mtt_cqe_table; + + mtts = hns_roce_table_find(hr_dev, table, mtt->first_seg + s / hr_dev->caps.mtt_entry_sz, &dma_handle); if (!mtts) return -ENOMEM; /* Save page addr, low 12 bits : 0 */ - for (i = 0; i < npages; ++i) - mtts[i] = (cpu_to_le64(page_list[i])) >> PAGE_ADDR_SHIFT; + for (i = 0; i < npages; ++i) { + if (!hr_dev->caps.mtt_hop_num) + mtts[i] = cpu_to_le64(page_list[i] >> PAGE_ADDR_SHIFT); + else + mtts[i] = cpu_to_le64(page_list[i]); + } return 0; } @@ -377,12 +752,18 @@ static int hns_roce_write_mtt(struct hns_roce_dev *hr_dev, { int chunk; int ret; + u32 bt_page_size; if (mtt->order < 0) return -EINVAL; + if (mtt->mtt_type == MTT_TYPE_WQE) + bt_page_size = 1 << (hr_dev->caps.mtt_ba_pg_sz + PAGE_SHIFT); + else + bt_page_size = 1 << (hr_dev->caps.cqe_ba_pg_sz + PAGE_SHIFT); + while (npages > 0) { - chunk = min_t(int, PAGE_SIZE / sizeof(u64), npages); + chunk = min_t(int, bt_page_size / sizeof(u64), npages); ret = hns_roce_write_mtt_chunk(hr_dev, mtt, start_index, chunk, page_list); @@ -400,9 +781,9 @@ static int hns_roce_write_mtt(struct hns_roce_dev *hr_dev, int hns_roce_buf_write_mtt(struct hns_roce_dev *hr_dev, struct hns_roce_mtt *mtt, struct hns_roce_buf *buf) { - u32 i = 0; - int ret = 0; - u64 *page_list = NULL; + u64 *page_list; + int ret; + u32 i; page_list = kmalloc_array(buf->npages, sizeof(*page_list), GFP_KERNEL); if (!page_list) @@ -425,7 +806,7 @@ int hns_roce_buf_write_mtt(struct hns_roce_dev *hr_dev, int hns_roce_init_mr_table(struct hns_roce_dev *hr_dev) { struct hns_roce_mr_table *mr_table = &hr_dev->mr_table; - int ret = 0; + int ret; ret = hns_roce_bitmap_init(&mr_table->mtpt_bitmap, hr_dev->caps.num_mtpts, @@ -439,8 +820,17 @@ int hns_roce_init_mr_table(struct hns_roce_dev *hr_dev) if (ret) goto err_buddy; + if (hns_roce_check_whether_mhop(hr_dev, HEM_TYPE_CQE)) { + ret = hns_roce_buddy_init(&mr_table->mtt_cqe_buddy, + ilog2(hr_dev->caps.num_cqe_segs)); + if (ret) + goto err_buddy_cqe; + } return 0; +err_buddy_cqe: + hns_roce_buddy_cleanup(&mr_table->mtt_buddy); + err_buddy: hns_roce_bitmap_cleanup(&mr_table->mtpt_bitmap); return ret; @@ -451,13 +841,15 @@ void hns_roce_cleanup_mr_table(struct hns_roce_dev *hr_dev) struct hns_roce_mr_table *mr_table = &hr_dev->mr_table; hns_roce_buddy_cleanup(&mr_table->mtt_buddy); + if (hns_roce_check_whether_mhop(hr_dev, HEM_TYPE_CQE)) + hns_roce_buddy_cleanup(&mr_table->mtt_cqe_buddy); hns_roce_bitmap_cleanup(&mr_table->mtpt_bitmap); } struct ib_mr *hns_roce_get_dma_mr(struct ib_pd *pd, int acc) { - int ret = 0; - struct hns_roce_mr *mr = NULL; + struct hns_roce_mr *mr; + int ret; mr = kmalloc(sizeof(*mr), GFP_KERNEL); if (mr == NULL) @@ -489,25 +881,44 @@ err_free: int hns_roce_ib_umem_write_mtt(struct hns_roce_dev *hr_dev, struct hns_roce_mtt *mtt, struct ib_umem *umem) { + struct device *dev = hr_dev->dev; struct scatterlist *sg; + unsigned int order; int i, k, entry; + int npage = 0; int ret = 0; + int len; + u64 page_addr; u64 *pages; + u32 bt_page_size; u32 n; - int len; - pages = (u64 *) __get_free_page(GFP_KERNEL); + order = mtt->mtt_type == MTT_TYPE_WQE ? hr_dev->caps.mtt_ba_pg_sz : + hr_dev->caps.cqe_ba_pg_sz; + bt_page_size = 1 << (order + PAGE_SHIFT); + + pages = (u64 *) __get_free_pages(GFP_KERNEL, order); if (!pages) return -ENOMEM; i = n = 0; for_each_sg(umem->sg_head.sgl, sg, umem->nmap, entry) { - len = sg_dma_len(sg) >> mtt->page_shift; + len = sg_dma_len(sg) >> PAGE_SHIFT; for (k = 0; k < len; ++k) { - pages[i++] = sg_dma_address(sg) + - (k << umem->page_shift); - if (i == PAGE_SIZE / sizeof(u64)) { + page_addr = + sg_dma_address(sg) + (k << umem->page_shift); + if (!(npage % (1 << (mtt->page_shift - PAGE_SHIFT)))) { + if (page_addr & ((1 << mtt->page_shift) - 1)) { + dev_err(dev, "page_addr 0x%llx is not page_shift %d alignment!\n", + page_addr, mtt->page_shift); + ret = -EINVAL; + goto out; + } + pages[i++] = page_addr; + } + npage++; + if (i == bt_page_size / sizeof(u64)) { ret = hns_roce_write_mtt(hr_dev, mtt, n, i, pages); if (ret) @@ -526,16 +937,44 @@ out: return ret; } -static int hns_roce_ib_umem_write_mr(struct hns_roce_mr *mr, +static int hns_roce_ib_umem_write_mr(struct hns_roce_dev *hr_dev, + struct hns_roce_mr *mr, struct ib_umem *umem) { - int i = 0; - int entry; struct scatterlist *sg; + int i = 0, j = 0, k; + int entry; + int len; + u64 page_addr; + u32 pbl_bt_sz; + + if (hr_dev->caps.pbl_hop_num == HNS_ROCE_HOP_NUM_0) + return 0; + pbl_bt_sz = 1 << (hr_dev->caps.pbl_ba_pg_sz + PAGE_SHIFT); for_each_sg(umem->sg_head.sgl, sg, umem->nmap, entry) { - mr->pbl_buf[i] = ((u64)sg_dma_address(sg)) >> 12; - i++; + len = sg_dma_len(sg) >> PAGE_SHIFT; + for (k = 0; k < len; ++k) { + page_addr = sg_dma_address(sg) + + (k << umem->page_shift); + + if (!hr_dev->caps.pbl_hop_num) { + mr->pbl_buf[i++] = page_addr >> 12; + } else if (hr_dev->caps.pbl_hop_num == 1) { + mr->pbl_buf[i++] = page_addr; + } else { + if (hr_dev->caps.pbl_hop_num == 2) + mr->pbl_bt_l1[i][j] = page_addr; + else if (hr_dev->caps.pbl_hop_num == 3) + mr->pbl_bt_l2[i][j] = page_addr; + + j++; + if (j >= (pbl_bt_sz / 8)) { + i++; + j = 0; + } + } + } } /* Memory barrier */ @@ -549,10 +988,12 @@ struct ib_mr *hns_roce_reg_user_mr(struct ib_pd *pd, u64 start, u64 length, struct ib_udata *udata) { struct hns_roce_dev *hr_dev = to_hr_dev(pd->device); - struct device *dev = &hr_dev->pdev->dev; - struct hns_roce_mr *mr = NULL; - int ret = 0; - int n = 0; + struct device *dev = hr_dev->dev; + struct hns_roce_mr *mr; + int bt_size; + int ret; + int n; + int i; mr = kmalloc(sizeof(*mr), GFP_KERNEL); if (!mr) @@ -573,11 +1014,27 @@ struct ib_mr *hns_roce_reg_user_mr(struct ib_pd *pd, u64 start, u64 length, goto err_umem; } - if (n > HNS_ROCE_MAX_MTPT_PBL_NUM) { - dev_err(dev, " MR len %lld err. MR is limited to 4G at most!\n", - length); - ret = -EINVAL; - goto err_umem; + if (!hr_dev->caps.pbl_hop_num) { + if (n > HNS_ROCE_MAX_MTPT_PBL_NUM) { + dev_err(dev, + " MR len %lld err. MR is limited to 4G at most!\n", + length); + ret = -EINVAL; + goto err_umem; + } + } else { + int pbl_size = 1; + + bt_size = (1 << (hr_dev->caps.pbl_ba_pg_sz + PAGE_SHIFT)) / 8; + for (i = 0; i < hr_dev->caps.pbl_hop_num; i++) + pbl_size *= bt_size; + if (n > pbl_size) { + dev_err(dev, + " MR len %lld err. MR page num is limited to %d!\n", + length, pbl_size); + ret = -EINVAL; + goto err_umem; + } } ret = hns_roce_mr_alloc(hr_dev, to_hr_pd(pd)->pdn, virt_addr, length, @@ -585,7 +1042,7 @@ struct ib_mr *hns_roce_reg_user_mr(struct ib_pd *pd, u64 start, u64 length, if (ret) goto err_umem; - ret = hns_roce_ib_umem_write_mr(mr, mr->umem); + ret = hns_roce_ib_umem_write_mr(hr_dev, mr, mr->umem); if (ret) goto err_mr; diff --git a/drivers/infiniband/hw/hns/hns_roce_pd.c b/drivers/infiniband/hw/hns/hns_roce_pd.c index a64500fa1145..bdab2188c04a 100644 --- a/drivers/infiniband/hw/hns/hns_roce_pd.c +++ b/drivers/infiniband/hw/hns/hns_roce_pd.c @@ -31,6 +31,7 @@ */ #include <linux/platform_device.h> +#include <linux/pci.h> #include "hns_roce_device.h" static int hns_roce_pd_alloc(struct hns_roce_dev *hr_dev, unsigned long *pdn) @@ -60,7 +61,7 @@ struct ib_pd *hns_roce_alloc_pd(struct ib_device *ib_dev, struct ib_udata *udata) { struct hns_roce_dev *hr_dev = to_hr_dev(ib_dev); - struct device *dev = &hr_dev->pdev->dev; + struct device *dev = hr_dev->dev; struct hns_roce_pd *pd; int ret; @@ -86,6 +87,7 @@ struct ib_pd *hns_roce_alloc_pd(struct ib_device *ib_dev, return &pd->ibpd; } +EXPORT_SYMBOL_GPL(hns_roce_alloc_pd); int hns_roce_dealloc_pd(struct ib_pd *pd) { @@ -94,6 +96,7 @@ int hns_roce_dealloc_pd(struct ib_pd *pd) return 0; } +EXPORT_SYMBOL_GPL(hns_roce_dealloc_pd); int hns_roce_uar_alloc(struct hns_roce_dev *hr_dev, struct hns_roce_uar *uar) { @@ -109,12 +112,17 @@ int hns_roce_uar_alloc(struct hns_roce_dev *hr_dev, struct hns_roce_uar *uar) uar->index = (uar->index - 1) % (hr_dev->caps.phy_num_uars - 1) + 1; - res = platform_get_resource(hr_dev->pdev, IORESOURCE_MEM, 0); - if (!res) { - dev_err(&hr_dev->pdev->dev, "memory resource not found!\n"); - return -EINVAL; + if (!dev_is_pci(hr_dev->dev)) { + res = platform_get_resource(hr_dev->pdev, IORESOURCE_MEM, 0); + if (!res) { + dev_err(&hr_dev->pdev->dev, "memory resource not found!\n"); + return -EINVAL; + } + uar->pfn = ((res->start) >> PAGE_SHIFT) + uar->index; + } else { + uar->pfn = ((pci_resource_start(hr_dev->pci_dev, 2)) + >> PAGE_SHIFT); } - uar->pfn = ((res->start) >> PAGE_SHIFT) + uar->index; return 0; } diff --git a/drivers/infiniband/hw/hns/hns_roce_qp.c b/drivers/infiniband/hw/hns/hns_roce_qp.c index f5dd21c2d275..b1c9a3768b19 100644 --- a/drivers/infiniband/hw/hns/hns_roce_qp.c +++ b/drivers/infiniband/hw/hns/hns_roce_qp.c @@ -44,7 +44,7 @@ void hns_roce_qp_event(struct hns_roce_dev *hr_dev, u32 qpn, int event_type) { struct hns_roce_qp_table *qp_table = &hr_dev->qp_table; - struct device *dev = &hr_dev->pdev->dev; + struct device *dev = hr_dev->dev; struct hns_roce_qp *qp; spin_lock(&qp_table->lock); @@ -136,6 +136,7 @@ enum hns_roce_qp_state to_hns_roce_state(enum ib_qp_state state) return HNS_ROCE_QP_NUM_STATE; } } +EXPORT_SYMBOL_GPL(to_hns_roce_state); static int hns_roce_gsi_qp_alloc(struct hns_roce_dev *hr_dev, unsigned long qpn, struct hns_roce_qp *hr_qp) @@ -153,7 +154,7 @@ static int hns_roce_gsi_qp_alloc(struct hns_roce_dev *hr_dev, unsigned long qpn, hr_qp->qpn & (hr_dev->caps.num_qps - 1), hr_qp); spin_unlock_irq(&qp_table->lock); if (ret) { - dev_err(&hr_dev->pdev->dev, "QPC radix_tree_insert failed\n"); + dev_err(hr_dev->dev, "QPC radix_tree_insert failed\n"); goto err_put_irrl; } @@ -171,7 +172,7 @@ static int hns_roce_qp_alloc(struct hns_roce_dev *hr_dev, unsigned long qpn, struct hns_roce_qp *hr_qp) { struct hns_roce_qp_table *qp_table = &hr_dev->qp_table; - struct device *dev = &hr_dev->pdev->dev; + struct device *dev = hr_dev->dev; int ret; if (!qpn) @@ -227,6 +228,7 @@ void hns_roce_qp_remove(struct hns_roce_dev *hr_dev, struct hns_roce_qp *hr_qp) hr_qp->qpn & (hr_dev->caps.num_qps - 1)); spin_unlock_irqrestore(&qp_table->lock, flags); } +EXPORT_SYMBOL_GPL(hns_roce_qp_remove); void hns_roce_qp_free(struct hns_roce_dev *hr_dev, struct hns_roce_qp *hr_qp) { @@ -241,6 +243,7 @@ void hns_roce_qp_free(struct hns_roce_dev *hr_dev, struct hns_roce_qp *hr_qp) hns_roce_table_put(hr_dev, &qp_table->qp_table, hr_qp->qpn); } } +EXPORT_SYMBOL_GPL(hns_roce_qp_free); void hns_roce_release_range_qp(struct hns_roce_dev *hr_dev, int base_qpn, int cnt) @@ -252,13 +255,14 @@ void hns_roce_release_range_qp(struct hns_roce_dev *hr_dev, int base_qpn, hns_roce_bitmap_free_range(&qp_table->bitmap, base_qpn, cnt, BITMAP_RR); } +EXPORT_SYMBOL_GPL(hns_roce_release_range_qp); static int hns_roce_set_rq_size(struct hns_roce_dev *hr_dev, struct ib_qp_cap *cap, int is_user, int has_srq, struct hns_roce_qp *hr_qp) { + struct device *dev = hr_dev->dev; u32 max_cnt; - struct device *dev = &hr_dev->pdev->dev; /* Check the validity of QP support capacity */ if (cap->max_recv_wr > hr_dev->caps.max_wqes || @@ -282,20 +286,27 @@ static int hns_roce_set_rq_size(struct hns_roce_dev *hr_dev, return -EINVAL; } - /* In v1 engine, parameter verification procession */ - max_cnt = cap->max_recv_wr > HNS_ROCE_MIN_WQE_NUM ? - cap->max_recv_wr : HNS_ROCE_MIN_WQE_NUM; + if (hr_dev->caps.min_wqes) + max_cnt = max(cap->max_recv_wr, hr_dev->caps.min_wqes); + else + max_cnt = cap->max_recv_wr; + hr_qp->rq.wqe_cnt = roundup_pow_of_two(max_cnt); if ((u32)hr_qp->rq.wqe_cnt > hr_dev->caps.max_wqes) { - dev_err(dev, "hns_roce_set_rq_size rq.wqe_cnt too large\n"); + dev_err(dev, "while setting rq size, rq.wqe_cnt too large\n"); return -EINVAL; } max_cnt = max(1U, cap->max_recv_sge); hr_qp->rq.max_gs = roundup_pow_of_two(max_cnt); - /* WQE is fixed for 64B */ - hr_qp->rq.wqe_shift = ilog2(hr_dev->caps.max_rq_desc_sz); + if (hr_dev->caps.max_rq_sg <= 2) + hr_qp->rq.wqe_shift = + ilog2(hr_dev->caps.max_rq_desc_sz); + else + hr_qp->rq.wqe_shift = + ilog2(hr_dev->caps.max_rq_desc_sz + * hr_qp->rq.max_gs); } cap->max_recv_wr = hr_qp->rq.max_post = hr_qp->rq.wqe_cnt; @@ -305,32 +316,79 @@ static int hns_roce_set_rq_size(struct hns_roce_dev *hr_dev, } static int hns_roce_set_user_sq_size(struct hns_roce_dev *hr_dev, + struct ib_qp_cap *cap, struct hns_roce_qp *hr_qp, struct hns_roce_ib_create_qp *ucmd) { u32 roundup_sq_stride = roundup_pow_of_two(hr_dev->caps.max_sq_desc_sz); u8 max_sq_stride = ilog2(roundup_sq_stride); + u32 page_size; + u32 max_cnt; /* Sanity check SQ size before proceeding */ if ((u32)(1 << ucmd->log_sq_bb_count) > hr_dev->caps.max_wqes || ucmd->log_sq_stride > max_sq_stride || ucmd->log_sq_stride < HNS_ROCE_IB_MIN_SQ_STRIDE) { - dev_err(&hr_dev->pdev->dev, "check SQ size error!\n"); + dev_err(hr_dev->dev, "check SQ size error!\n"); + return -EINVAL; + } + + if (cap->max_send_sge > hr_dev->caps.max_sq_sg) { + dev_err(hr_dev->dev, "SQ sge error! max_send_sge=%d\n", + cap->max_send_sge); return -EINVAL; } hr_qp->sq.wqe_cnt = 1 << ucmd->log_sq_bb_count; hr_qp->sq.wqe_shift = ucmd->log_sq_stride; + max_cnt = max(1U, cap->max_send_sge); + if (hr_dev->caps.max_sq_sg <= 2) + hr_qp->sq.max_gs = roundup_pow_of_two(max_cnt); + else + hr_qp->sq.max_gs = max_cnt; + + if (hr_qp->sq.max_gs > 2) + hr_qp->sge.sge_cnt = roundup_pow_of_two(hr_qp->sq.wqe_cnt * + (hr_qp->sq.max_gs - 2)); + hr_qp->sge.sge_shift = 4; + /* Get buf size, SQ and RQ are aligned to page_szie */ - hr_qp->buff_size = HNS_ROCE_ALOGN_UP((hr_qp->rq.wqe_cnt << + if (hr_dev->caps.max_sq_sg <= 2) { + hr_qp->buff_size = HNS_ROCE_ALOGN_UP((hr_qp->rq.wqe_cnt << hr_qp->rq.wqe_shift), PAGE_SIZE) + - HNS_ROCE_ALOGN_UP((hr_qp->sq.wqe_cnt << + HNS_ROCE_ALOGN_UP((hr_qp->sq.wqe_cnt << hr_qp->sq.wqe_shift), PAGE_SIZE); - hr_qp->sq.offset = 0; - hr_qp->rq.offset = HNS_ROCE_ALOGN_UP((hr_qp->sq.wqe_cnt << + hr_qp->sq.offset = 0; + hr_qp->rq.offset = HNS_ROCE_ALOGN_UP((hr_qp->sq.wqe_cnt << hr_qp->sq.wqe_shift), PAGE_SIZE); + } else { + page_size = 1 << (hr_dev->caps.mtt_buf_pg_sz + PAGE_SHIFT); + hr_qp->buff_size = HNS_ROCE_ALOGN_UP((hr_qp->rq.wqe_cnt << + hr_qp->rq.wqe_shift), page_size) + + HNS_ROCE_ALOGN_UP((hr_qp->sge.sge_cnt << + hr_qp->sge.sge_shift), page_size) + + HNS_ROCE_ALOGN_UP((hr_qp->sq.wqe_cnt << + hr_qp->sq.wqe_shift), page_size); + + hr_qp->sq.offset = 0; + if (hr_qp->sge.sge_cnt) { + hr_qp->sge.offset = HNS_ROCE_ALOGN_UP( + (hr_qp->sq.wqe_cnt << + hr_qp->sq.wqe_shift), + page_size); + hr_qp->rq.offset = hr_qp->sge.offset + + HNS_ROCE_ALOGN_UP((hr_qp->sge.sge_cnt << + hr_qp->sge.sge_shift), + page_size); + } else { + hr_qp->rq.offset = HNS_ROCE_ALOGN_UP( + (hr_qp->sq.wqe_cnt << + hr_qp->sq.wqe_shift), + page_size); + } + } return 0; } @@ -339,13 +397,15 @@ static int hns_roce_set_kernel_sq_size(struct hns_roce_dev *hr_dev, struct ib_qp_cap *cap, struct hns_roce_qp *hr_qp) { - struct device *dev = &hr_dev->pdev->dev; + struct device *dev = hr_dev->dev; + u32 page_size; u32 max_cnt; + int size; if (cap->max_send_wr > hr_dev->caps.max_wqes || cap->max_send_sge > hr_dev->caps.max_sq_sg || cap->max_inline_data > hr_dev->caps.max_sq_inline) { - dev_err(dev, "hns_roce_set_kernel_sq_size error1\n"); + dev_err(dev, "SQ WR or sge or inline data error!\n"); return -EINVAL; } @@ -353,27 +413,46 @@ static int hns_roce_set_kernel_sq_size(struct hns_roce_dev *hr_dev, hr_qp->sq_max_wqes_per_wr = 1; hr_qp->sq_spare_wqes = 0; - /* In v1 engine, parameter verification procession */ - max_cnt = cap->max_send_wr > HNS_ROCE_MIN_WQE_NUM ? - cap->max_send_wr : HNS_ROCE_MIN_WQE_NUM; + if (hr_dev->caps.min_wqes) + max_cnt = max(cap->max_send_wr, hr_dev->caps.min_wqes); + else + max_cnt = cap->max_send_wr; + hr_qp->sq.wqe_cnt = roundup_pow_of_two(max_cnt); if ((u32)hr_qp->sq.wqe_cnt > hr_dev->caps.max_wqes) { - dev_err(dev, "hns_roce_set_kernel_sq_size sq.wqe_cnt too large\n"); + dev_err(dev, "while setting kernel sq size, sq.wqe_cnt too large\n"); return -EINVAL; } /* Get data_seg numbers */ max_cnt = max(1U, cap->max_send_sge); - hr_qp->sq.max_gs = roundup_pow_of_two(max_cnt); + if (hr_dev->caps.max_sq_sg <= 2) + hr_qp->sq.max_gs = roundup_pow_of_two(max_cnt); + else + hr_qp->sq.max_gs = max_cnt; - /* Get buf size, SQ and RQ are aligned to page_szie */ - hr_qp->buff_size = HNS_ROCE_ALOGN_UP((hr_qp->rq.wqe_cnt << - hr_qp->rq.wqe_shift), PAGE_SIZE) + - HNS_ROCE_ALOGN_UP((hr_qp->sq.wqe_cnt << - hr_qp->sq.wqe_shift), PAGE_SIZE); + if (hr_qp->sq.max_gs > 2) { + hr_qp->sge.sge_cnt = roundup_pow_of_two(hr_qp->sq.wqe_cnt * + (hr_qp->sq.max_gs - 2)); + hr_qp->sge.sge_shift = 4; + } + + /* Get buf size, SQ and RQ are aligned to PAGE_SIZE */ + page_size = 1 << (hr_dev->caps.mtt_buf_pg_sz + PAGE_SHIFT); hr_qp->sq.offset = 0; - hr_qp->rq.offset = HNS_ROCE_ALOGN_UP((hr_qp->sq.wqe_cnt << - hr_qp->sq.wqe_shift), PAGE_SIZE); + size = HNS_ROCE_ALOGN_UP(hr_qp->sq.wqe_cnt << hr_qp->sq.wqe_shift, + page_size); + + if (hr_dev->caps.max_sq_sg > 2 && hr_qp->sge.sge_cnt) { + hr_qp->sge.offset = size; + size += HNS_ROCE_ALOGN_UP(hr_qp->sge.sge_cnt << + hr_qp->sge.sge_shift, page_size); + } + + hr_qp->rq.offset = size; + size += HNS_ROCE_ALOGN_UP((hr_qp->rq.wqe_cnt << hr_qp->rq.wqe_shift), + page_size); + hr_qp->buff_size = size; /* Get wr and sge number which send */ cap->max_send_wr = hr_qp->sq.max_post = hr_qp->sq.wqe_cnt; @@ -391,10 +470,12 @@ static int hns_roce_create_qp_common(struct hns_roce_dev *hr_dev, struct ib_udata *udata, unsigned long sqpn, struct hns_roce_qp *hr_qp) { - struct device *dev = &hr_dev->pdev->dev; + struct device *dev = hr_dev->dev; struct hns_roce_ib_create_qp ucmd; unsigned long qpn = 0; int ret = 0; + u32 page_shift; + u32 npages; mutex_init(&hr_qp->mutex); spin_lock_init(&hr_qp->sq.lock); @@ -421,7 +502,8 @@ static int hns_roce_create_qp_common(struct hns_roce_dev *hr_dev, goto err_out; } - ret = hns_roce_set_user_sq_size(hr_dev, hr_qp, &ucmd); + ret = hns_roce_set_user_sq_size(hr_dev, &init_attr->cap, hr_qp, + &ucmd); if (ret) { dev_err(dev, "hns_roce_set_user_sq_size error for create qp\n"); goto err_out; @@ -436,8 +518,21 @@ static int hns_roce_create_qp_common(struct hns_roce_dev *hr_dev, goto err_out; } - ret = hns_roce_mtt_init(hr_dev, ib_umem_page_count(hr_qp->umem), - hr_qp->umem->page_shift, &hr_qp->mtt); + hr_qp->mtt.mtt_type = MTT_TYPE_WQE; + if (hr_dev->caps.mtt_buf_pg_sz) { + npages = (ib_umem_page_count(hr_qp->umem) + + (1 << hr_dev->caps.mtt_buf_pg_sz) - 1) / + (1 << hr_dev->caps.mtt_buf_pg_sz); + page_shift = PAGE_SHIFT + hr_dev->caps.mtt_buf_pg_sz; + ret = hns_roce_mtt_init(hr_dev, npages, + page_shift, + &hr_qp->mtt); + } else { + ret = hns_roce_mtt_init(hr_dev, + ib_umem_page_count(hr_qp->umem), + hr_qp->umem->page_shift, + &hr_qp->mtt); + } if (ret) { dev_err(dev, "hns_roce_mtt_init error for create qp\n"); goto err_buf; @@ -472,20 +567,22 @@ static int hns_roce_create_qp_common(struct hns_roce_dev *hr_dev, } /* QP doorbell register address */ - hr_qp->sq.db_reg_l = hr_dev->reg_base + ROCEE_DB_SQ_L_0_REG + + hr_qp->sq.db_reg_l = hr_dev->reg_base + hr_dev->sdb_offset + DB_REG_OFFSET * hr_dev->priv_uar.index; - hr_qp->rq.db_reg_l = hr_dev->reg_base + - ROCEE_DB_OTHERS_L_0_REG + + hr_qp->rq.db_reg_l = hr_dev->reg_base + hr_dev->odb_offset + DB_REG_OFFSET * hr_dev->priv_uar.index; /* Allocate QP buf */ - if (hns_roce_buf_alloc(hr_dev, hr_qp->buff_size, PAGE_SIZE * 2, - &hr_qp->hr_buf)) { + page_shift = PAGE_SHIFT + hr_dev->caps.mtt_buf_pg_sz; + if (hns_roce_buf_alloc(hr_dev, hr_qp->buff_size, + (1 << page_shift) * 2, + &hr_qp->hr_buf, page_shift)) { dev_err(dev, "hns_roce_buf_alloc error!\n"); ret = -ENOMEM; goto err_out; } + hr_qp->mtt.mtt_type = MTT_TYPE_WQE; /* Write MTT */ ret = hns_roce_mtt_init(hr_dev, hr_qp->hr_buf.npages, hr_qp->hr_buf.page_shift, &hr_qp->mtt); @@ -522,7 +619,9 @@ static int hns_roce_create_qp_common(struct hns_roce_dev *hr_dev, } } - if ((init_attr->qp_type) == IB_QPT_GSI) { + if (init_attr->qp_type == IB_QPT_GSI && + hr_dev->hw_rev == HNS_ROCE_HW_VER1) { + /* In v1 engine, GSI QP context in RoCE engine's register */ ret = hns_roce_gsi_qp_alloc(hr_dev, qpn, hr_qp); if (ret) { dev_err(dev, "hns_roce_qp_alloc failed!\n"); @@ -571,7 +670,7 @@ struct ib_qp *hns_roce_create_qp(struct ib_pd *pd, struct ib_udata *udata) { struct hns_roce_dev *hr_dev = to_hr_dev(pd->device); - struct device *dev = &hr_dev->pdev->dev; + struct device *dev = hr_dev->dev; struct hns_roce_sqp *hr_sqp; struct hns_roce_qp *hr_qp; int ret; @@ -629,6 +728,7 @@ struct ib_qp *hns_roce_create_qp(struct ib_pd *pd, return &hr_qp->ibqp; } +EXPORT_SYMBOL_GPL(hns_roce_create_qp); int to_hr_qp_type(int qp_type) { @@ -647,6 +747,7 @@ int to_hr_qp_type(int qp_type) return transport_type; } +EXPORT_SYMBOL_GPL(to_hr_qp_type); int hns_roce_modify_qp(struct ib_qp *ibqp, struct ib_qp_attr *attr, int attr_mask, struct ib_udata *udata) @@ -654,7 +755,7 @@ int hns_roce_modify_qp(struct ib_qp *ibqp, struct ib_qp_attr *attr, struct hns_roce_dev *hr_dev = to_hr_dev(ibqp->device); struct hns_roce_qp *hr_qp = to_hr_qp(ibqp); enum ib_qp_state cur_state, new_state; - struct device *dev = &hr_dev->pdev->dev; + struct device *dev = hr_dev->dev; int ret = -EINVAL; int p; enum ib_mtu active_mtu; @@ -692,7 +793,10 @@ int hns_roce_modify_qp(struct ib_qp *ibqp, struct ib_qp_attr *attr, p = attr_mask & IB_QP_PORT ? (attr->port_num - 1) : hr_qp->port; active_mtu = iboe_get_mtu(hr_dev->iboe.netdevs[p]->mtu); - if (attr->path_mtu > IB_MTU_2048 || + if ((hr_dev->caps.max_mtu == IB_MTU_4096 && + attr->path_mtu > IB_MTU_4096) || + (hr_dev->caps.max_mtu == IB_MTU_2048 && + attr->path_mtu > IB_MTU_2048) || attr->path_mtu < IB_MTU_256 || attr->path_mtu > active_mtu) { dev_err(dev, "attr path_mtu(%d)invalid while modify qp", @@ -716,9 +820,7 @@ int hns_roce_modify_qp(struct ib_qp *ibqp, struct ib_qp_attr *attr, } if (cur_state == new_state && cur_state == IB_QPS_RESET) { - ret = -EPERM; - dev_err(dev, "cur_state=%d new_state=%d\n", cur_state, - new_state); + ret = 0; goto out; } @@ -745,6 +847,7 @@ void hns_roce_lock_cqs(struct hns_roce_cq *send_cq, struct hns_roce_cq *recv_cq) spin_lock_nested(&send_cq->lock, SINGLE_DEPTH_NESTING); } } +EXPORT_SYMBOL_GPL(hns_roce_lock_cqs); void hns_roce_unlock_cqs(struct hns_roce_cq *send_cq, struct hns_roce_cq *recv_cq) __releases(&send_cq->lock) @@ -761,6 +864,7 @@ void hns_roce_unlock_cqs(struct hns_roce_cq *send_cq, spin_unlock_irq(&recv_cq->lock); } } +EXPORT_SYMBOL_GPL(hns_roce_unlock_cqs); __be32 send_ieth(struct ib_send_wr *wr) { @@ -774,6 +878,7 @@ __be32 send_ieth(struct ib_send_wr *wr) return 0; } } +EXPORT_SYMBOL_GPL(send_ieth); static void *get_wqe(struct hns_roce_qp *hr_qp, int offset) { @@ -785,11 +890,20 @@ void *get_recv_wqe(struct hns_roce_qp *hr_qp, int n) { return get_wqe(hr_qp, hr_qp->rq.offset + (n << hr_qp->rq.wqe_shift)); } +EXPORT_SYMBOL_GPL(get_recv_wqe); void *get_send_wqe(struct hns_roce_qp *hr_qp, int n) { return get_wqe(hr_qp, hr_qp->sq.offset + (n << hr_qp->sq.wqe_shift)); } +EXPORT_SYMBOL_GPL(get_send_wqe); + +void *get_send_extend_sge(struct hns_roce_qp *hr_qp, int n) +{ + return hns_roce_buf_offset(&hr_qp->hr_buf, hr_qp->sge.offset + + (n << hr_qp->sge.sge_shift)); +} +EXPORT_SYMBOL_GPL(get_send_extend_sge); bool hns_roce_wq_overflow(struct hns_roce_wq *hr_wq, int nreq, struct ib_cq *ib_cq) @@ -808,6 +922,7 @@ bool hns_roce_wq_overflow(struct hns_roce_wq *hr_wq, int nreq, return cur + nreq >= hr_wq->max_post; } +EXPORT_SYMBOL_GPL(hns_roce_wq_overflow); int hns_roce_init_qp_table(struct hns_roce_dev *hr_dev) { @@ -823,7 +938,7 @@ int hns_roce_init_qp_table(struct hns_roce_dev *hr_dev) hr_dev->caps.num_qps - 1, SQP_NUM, reserved_from_top); if (ret) { - dev_err(&hr_dev->pdev->dev, "qp bitmap init failed!error=%d\n", + dev_err(hr_dev->dev, "qp bitmap init failed!error=%d\n", ret); return ret; } diff --git a/drivers/infiniband/hw/i40iw/Kconfig b/drivers/infiniband/hw/i40iw/Kconfig index 6e7d27a14061..f6d20ba88c03 100644 --- a/drivers/infiniband/hw/i40iw/Kconfig +++ b/drivers/infiniband/hw/i40iw/Kconfig @@ -1,6 +1,7 @@ config INFINIBAND_I40IW tristate "Intel(R) Ethernet X722 iWARP Driver" depends on INET && I40E + depends on PCI select GENERIC_ALLOCATOR ---help--- Intel(R) Ethernet X722 iWARP Driver diff --git a/drivers/infiniband/hw/i40iw/i40iw.h b/drivers/infiniband/hw/i40iw/i40iw.h index a65e4cbdce2f..4ae9131b6350 100644 --- a/drivers/infiniband/hw/i40iw/i40iw.h +++ b/drivers/infiniband/hw/i40iw/i40iw.h @@ -119,9 +119,6 @@ #define I40IW_CQP_COMPL_SQ_WQE_FLUSHED 3 #define I40IW_CQP_COMPL_RQ_SQ_WQE_FLUSHED 4 -#define I40IW_MTU_TO_MSS 40 -#define I40IW_DEFAULT_MSS 1460 - struct i40iw_cqp_compl_info { u32 op_ret_val; u16 maj_err_code; diff --git a/drivers/infiniband/hw/i40iw/i40iw_cm.c b/drivers/infiniband/hw/i40iw/i40iw_cm.c index 5230dd3c938c..493d6ef3d2d5 100644 --- a/drivers/infiniband/hw/i40iw/i40iw_cm.c +++ b/drivers/infiniband/hw/i40iw/i40iw_cm.c @@ -1188,7 +1188,7 @@ static void i40iw_handle_close_entry(struct i40iw_cm_node *cm_node, u32 rem_node * i40iw_cm_timer_tick - system's timer expired callback * @pass: Pointing to cm_core */ -static void i40iw_cm_timer_tick(unsigned long pass) +static void i40iw_cm_timer_tick(struct timer_list *t) { unsigned long nexttimeout = jiffies + I40IW_LONG_TIME; struct i40iw_cm_node *cm_node; @@ -1196,10 +1196,9 @@ static void i40iw_cm_timer_tick(unsigned long pass) struct list_head *list_core_temp; struct i40iw_sc_vsi *vsi; struct list_head *list_node; - struct i40iw_cm_core *cm_core = (struct i40iw_cm_core *)pass; + struct i40iw_cm_core *cm_core = from_timer(cm_core, t, tcp_timer); u32 settimer = 0; unsigned long timetosend; - struct i40iw_sc_dev *dev; unsigned long flags; struct list_head timer_list; @@ -1267,13 +1266,15 @@ static void i40iw_cm_timer_tick(unsigned long pass) spin_lock_irqsave(&cm_node->retrans_list_lock, flags); goto done; } - cm_node->cm_core->stats_pkt_retrans++; spin_unlock_irqrestore(&cm_node->retrans_list_lock, flags); vsi = &cm_node->iwdev->vsi; - dev = cm_node->dev; - atomic_inc(&send_entry->sqbuf->refcount); - i40iw_puda_send_buf(vsi->ilq, send_entry->sqbuf); + + if (!cm_node->ack_rcvd) { + atomic_inc(&send_entry->sqbuf->refcount); + i40iw_puda_send_buf(vsi->ilq, send_entry->sqbuf); + cm_node->cm_core->stats_pkt_retrans++; + } spin_lock_irqsave(&cm_node->retrans_list_lock, flags); if (send_entry->send_retrans) { send_entry->retranscount--; @@ -1524,8 +1525,8 @@ static bool i40iw_port_in_use(struct i40iw_cm_core *cm_core, u16 port, bool acti break; } } - if (!ret) - clear_bit(port, cm_core->active_side_ports); + if (!ret) + clear_bit(port, cm_core->active_side_ports); spin_unlock_irqrestore(&cm_core->ht_lock, flags); } else { spin_lock_irqsave(&cm_core->listen_list_lock, flags); @@ -2181,6 +2182,7 @@ static struct i40iw_cm_node *i40iw_make_cm_node( cm_node->cm_id = cm_info->cm_id; ether_addr_copy(cm_node->loc_mac, netdev->dev_addr); spin_lock_init(&cm_node->retrans_list_lock); + cm_node->ack_rcvd = false; atomic_set(&cm_node->ref_count, 1); /* associate our parent CM core */ @@ -2191,7 +2193,8 @@ static struct i40iw_cm_node *i40iw_make_cm_node( I40IW_CM_DEFAULT_RCV_WND_SCALED >> I40IW_CM_DEFAULT_RCV_WND_SCALE; ts = current_kernel_time(); cm_node->tcp_cntxt.loc_seq_num = ts.tv_nsec; - cm_node->tcp_cntxt.mss = iwdev->vsi.mss; + cm_node->tcp_cntxt.mss = (cm_node->ipv4) ? (iwdev->vsi.mtu - I40IW_MTU_TO_MSS_IPV4) : + (iwdev->vsi.mtu - I40IW_MTU_TO_MSS_IPV6); cm_node->iwdev = iwdev; cm_node->dev = &iwdev->sc_dev; @@ -2406,6 +2409,7 @@ static void i40iw_handle_rst_pkt(struct i40iw_cm_node *cm_node, case I40IW_CM_STATE_FIN_WAIT1: case I40IW_CM_STATE_LAST_ACK: cm_node->cm_id->rem_ref(cm_node->cm_id); + /* fall through */ case I40IW_CM_STATE_TIME_WAIT: cm_node->state = I40IW_CM_STATE_CLOSED; i40iw_rem_ref_cm_node(cm_node); @@ -2719,7 +2723,10 @@ static int i40iw_handle_ack_pkt(struct i40iw_cm_node *cm_node, cm_node->tcp_cntxt.rem_ack_num = ntohl(tcph->ack_seq); if (datasize) { cm_node->tcp_cntxt.rcv_nxt = inc_sequence + datasize; + cm_node->ack_rcvd = false; i40iw_handle_rcv_mpa(cm_node, rbuf); + } else { + cm_node->ack_rcvd = true; } break; case I40IW_CM_STATE_LISTENING: @@ -3195,8 +3202,7 @@ void i40iw_setup_cm_core(struct i40iw_device *iwdev) INIT_LIST_HEAD(&cm_core->connected_nodes); INIT_LIST_HEAD(&cm_core->listen_nodes); - setup_timer(&cm_core->tcp_timer, i40iw_cm_timer_tick, - (unsigned long)cm_core); + timer_setup(&cm_core->tcp_timer, i40iw_cm_timer_tick, 0); spin_lock_init(&cm_core->ht_lock); spin_lock_init(&cm_core->listen_list_lock); diff --git a/drivers/infiniband/hw/i40iw/i40iw_cm.h b/drivers/infiniband/hw/i40iw/i40iw_cm.h index 45abef76295b..0d5840d2c4fc 100644 --- a/drivers/infiniband/hw/i40iw/i40iw_cm.h +++ b/drivers/infiniband/hw/i40iw/i40iw_cm.h @@ -360,6 +360,7 @@ struct i40iw_cm_node { u8 pdata_buf[IETF_MAX_PRIV_DATA_LEN]; struct i40iw_kmem_info mpa_hdr; + bool ack_rcvd; }; /* structure for client or CM to fill when making CM api calls. */ diff --git a/drivers/infiniband/hw/i40iw/i40iw_ctrl.c b/drivers/infiniband/hw/i40iw/i40iw_ctrl.c index 42ca5346777d..d88c6cf47cf2 100644 --- a/drivers/infiniband/hw/i40iw/i40iw_ctrl.c +++ b/drivers/infiniband/hw/i40iw/i40iw_ctrl.c @@ -348,7 +348,10 @@ void i40iw_change_l2params(struct i40iw_sc_vsi *vsi, struct i40iw_l2params *l2pa u16 qs_handle; int i; - vsi->mss = l2params->mss; + if (vsi->mtu != l2params->mtu) { + vsi->mtu = l2params->mtu; + i40iw_reinitialize_ieq(dev); + } i40iw_fill_qos_list(l2params->qs_handle_list); for (i = 0; i < I40IW_MAX_USER_PRIORITY; i++) { @@ -374,7 +377,7 @@ void i40iw_change_l2params(struct i40iw_sc_vsi *vsi, struct i40iw_l2params *l2pa * i40iw_qp_rem_qos - remove qp from qos lists during destroy qp * @qp: qp to be removed from qos */ -static void i40iw_qp_rem_qos(struct i40iw_sc_qp *qp) +void i40iw_qp_rem_qos(struct i40iw_sc_qp *qp) { struct i40iw_sc_vsi *vsi = qp->vsi; unsigned long flags; @@ -479,6 +482,10 @@ static enum i40iw_status_code i40iw_sc_cqp_init(struct i40iw_sc_cqp *cqp, I40IW_RING_INIT(cqp->sq_ring, cqp->sq_size); cqp->dev->cqp_cmd_stats[OP_REQUESTED_COMMANDS] = 0; cqp->dev->cqp_cmd_stats[OP_COMPLETED_COMMANDS] = 0; + INIT_LIST_HEAD(&cqp->dev->cqp_cmd_head); /* for the cqp commands backlog. */ + + i40iw_wr32(cqp->dev->hw, I40E_PFPE_CQPTAIL, 0); + i40iw_wr32(cqp->dev->hw, I40E_PFPE_CQPDB, 0); i40iw_debug(cqp->dev, I40IW_DEBUG_WQE, "%s: sq_size[%04d] hw_sq_size[%04d] sq_base[%p] sq_pa[%llxh] cqp[%p] polarity[x%04X]\n", @@ -1774,6 +1781,53 @@ static enum i40iw_status_code i40iw_sc_get_next_aeqe(struct i40iw_sc_aeq *aeq, info->iwarp_state = (u8)RS_64(temp, I40IW_AEQE_IWSTATE); info->q2_data_written = (u8)RS_64(temp, I40IW_AEQE_Q2DATA); info->aeqe_overflow = (bool)RS_64(temp, I40IW_AEQE_OVERFLOW); + + switch (info->ae_id) { + case I40IW_AE_PRIV_OPERATION_DENIED: + case I40IW_AE_UDA_XMIT_DGRAM_TOO_LONG: + case I40IW_AE_UDA_XMIT_DGRAM_TOO_SHORT: + case I40IW_AE_BAD_CLOSE: + case I40IW_AE_RDMAP_ROE_BAD_LLP_CLOSE: + case I40IW_AE_RDMA_READ_WHILE_ORD_ZERO: + case I40IW_AE_STAG_ZERO_INVALID: + case I40IW_AE_IB_RREQ_AND_Q1_FULL: + case I40IW_AE_WQE_UNEXPECTED_OPCODE: + case I40IW_AE_DDP_UBE_INVALID_DDP_VERSION: + case I40IW_AE_DDP_UBE_INVALID_MO: + case I40IW_AE_DDP_UBE_INVALID_QN: + case I40IW_AE_DDP_NO_L_BIT: + case I40IW_AE_RDMAP_ROE_INVALID_RDMAP_VERSION: + case I40IW_AE_RDMAP_ROE_UNEXPECTED_OPCODE: + case I40IW_AE_ROE_INVALID_RDMA_READ_REQUEST: + case I40IW_AE_ROE_INVALID_RDMA_WRITE_OR_READ_RESP: + case I40IW_AE_INVALID_ARP_ENTRY: + case I40IW_AE_INVALID_TCP_OPTION_RCVD: + case I40IW_AE_STALE_ARP_ENTRY: + case I40IW_AE_LLP_CLOSE_COMPLETE: + case I40IW_AE_LLP_CONNECTION_RESET: + case I40IW_AE_LLP_FIN_RECEIVED: + case I40IW_AE_LLP_RECEIVED_MPA_CRC_ERROR: + case I40IW_AE_LLP_SEGMENT_TOO_SMALL: + case I40IW_AE_LLP_SYN_RECEIVED: + case I40IW_AE_LLP_TERMINATE_RECEIVED: + case I40IW_AE_LLP_TOO_MANY_RETRIES: + case I40IW_AE_LLP_DOUBT_REACHABILITY: + case I40IW_AE_RESET_SENT: + case I40IW_AE_TERMINATE_SENT: + case I40IW_AE_RESET_NOT_SENT: + case I40IW_AE_LCE_QP_CATASTROPHIC: + case I40IW_AE_QP_SUSPEND_COMPLETE: + info->qp = true; + info->compl_ctx = compl_ctx; + ae_src = I40IW_AE_SOURCE_RSVD; + break; + case I40IW_AE_LCE_CQ_CATASTROPHIC: + info->cq = true; + info->compl_ctx = LS_64_1(compl_ctx, 1); + ae_src = I40IW_AE_SOURCE_RSVD; + break; + } + switch (ae_src) { case I40IW_AE_SOURCE_RQ: case I40IW_AE_SOURCE_RQ_0011: @@ -1807,6 +1861,8 @@ static enum i40iw_status_code i40iw_sc_get_next_aeqe(struct i40iw_sc_aeq *aeq, info->compl_ctx = compl_ctx; info->out_rdrsp = true; break; + case I40IW_AE_SOURCE_RSVD: + /* fallthrough */ default: break; } @@ -2357,7 +2413,6 @@ static enum i40iw_status_code i40iw_sc_qp_init(struct i40iw_sc_qp *qp, qp->rcv_tph_en = info->rcv_tph_en; qp->xmit_tph_en = info->xmit_tph_en; qp->qs_handle = qp->vsi->qos[qp->user_pri].qs_handle; - qp->exception_lan_queue = qp->pd->dev->exception_lan_queue; return 0; } @@ -2399,7 +2454,6 @@ static enum i40iw_status_code i40iw_sc_qp_create( LS_64(qp->qp_type, I40IW_CQPSQ_QP_QPTYPE) | LS_64(qp->virtual_map, I40IW_CQPSQ_QP_VQ) | LS_64(info->cq_num_valid, I40IW_CQPSQ_QP_CQNUMVALID) | - LS_64(info->static_rsrc, I40IW_CQPSQ_QP_STATRSRC) | LS_64(info->arp_cache_idx_valid, I40IW_CQPSQ_QP_ARPTABIDXVALID) | LS_64(info->next_iwarp_state, I40IW_CQPSQ_QP_NEXTIWSTATE) | LS_64(cqp->polarity, I40IW_CQPSQ_WQEVALID); @@ -2462,7 +2516,6 @@ static enum i40iw_status_code i40iw_sc_qp_modify( LS_64(info->cq_num_valid, I40IW_CQPSQ_QP_CQNUMVALID) | LS_64(info->force_loopback, I40IW_CQPSQ_QP_FORCELOOPBACK) | LS_64(qp->qp_type, I40IW_CQPSQ_QP_QPTYPE) | - LS_64(info->static_rsrc, I40IW_CQPSQ_QP_STATRSRC) | LS_64(info->remove_hash_idx, I40IW_CQPSQ_QP_REMOVEHASHENTRY) | LS_64(term_actions, I40IW_CQPSQ_QP_TERMACT) | LS_64(info->reset_tcp_conn, I40IW_CQPSQ_QP_RESETCON) | @@ -2694,7 +2747,7 @@ static enum i40iw_status_code i40iw_sc_qp_setctx( LS_64(qp->sq_tph_val, I40IWQPC_SQTPHVAL) | LS_64(qp->rq_tph_val, I40IWQPC_RQTPHVAL) | LS_64(qp->qs_handle, I40IWQPC_QSHANDLE) | - LS_64(qp->exception_lan_queue, I40IWQPC_EXCEPTION_LAN_QUEUE)); + LS_64(vsi->exception_lan_queue, I40IWQPC_EXCEPTION_LAN_QUEUE)); if (info->iwarp_info_valid) { qw0 |= LS_64(iw->ddp_ver, I40IWQPC_DDP_VER) | @@ -4376,10 +4429,6 @@ static int i40iw_bld_terminate_hdr(struct i40iw_sc_qp *qp, i40iw_setup_termhdr(qp, termhdr, FLUSH_REM_ACCESS_ERR, (LAYER_RDMA << 4) | RDMAP_REMOTE_PROT, RDMAP_TO_WRAP); break; - case I40IW_AE_LLP_RECEIVED_MARKER_AND_LENGTH_FIELDS_DONT_MATCH: - i40iw_setup_termhdr(qp, termhdr, FLUSH_LOC_LEN_ERR, - (LAYER_MPA << 4) | DDP_LLP, MPA_MARKER); - break; case I40IW_AE_LLP_RECEIVED_MPA_CRC_ERROR: i40iw_setup_termhdr(qp, termhdr, FLUSH_GENERAL_ERR, (LAYER_MPA << 4) | DDP_LLP, MPA_CRC); @@ -4395,7 +4444,6 @@ static int i40iw_bld_terminate_hdr(struct i40iw_sc_qp *qp, (LAYER_DDP << 4) | DDP_CATASTROPHIC, DDP_CATASTROPHIC_LOCAL); break; case I40IW_AE_DDP_INVALID_MSN_GAP_IN_MSN: - case I40IW_AE_DDP_INVALID_MSN_RANGE_IS_NOT_VALID: i40iw_setup_termhdr(qp, termhdr, FLUSH_GENERAL_ERR, (LAYER_DDP << 4) | DDP_UNTAGGED_BUFFER, DDP_UNTAGGED_INV_MSN_RANGE); break; @@ -4541,7 +4589,8 @@ void i40iw_sc_vsi_init(struct i40iw_sc_vsi *vsi, struct i40iw_vsi_init_info *inf vsi->dev = info->dev; vsi->back_vsi = info->back_vsi; - vsi->mss = info->params->mss; + vsi->mtu = info->params->mtu; + vsi->exception_lan_queue = info->exception_lan_queue; i40iw_fill_qos_list(info->params->qs_handle_list); for (i = 0; i < I40IW_MAX_USER_PRIORITY; i++) { @@ -4873,6 +4922,7 @@ enum i40iw_status_code i40iw_vsi_stats_init(struct i40iw_sc_vsi *vsi, struct i40 vsi->pestat = info->pestat; vsi->pestat->hw = vsi->dev->hw; + vsi->pestat->vsi = vsi; if (info->stats_initialize) { i40iw_hw_stats_init(vsi->pestat, fcn_id, true); @@ -5018,14 +5068,12 @@ enum i40iw_status_code i40iw_device_init(struct i40iw_sc_dev *dev, u8 db_size; spin_lock_init(&dev->cqp_lock); - INIT_LIST_HEAD(&dev->cqp_cmd_head); /* for the cqp commands backlog. */ i40iw_device_init_uk(&dev->dev_uk); dev->debug_mask = info->debug_mask; dev->hmc_fn_id = info->hmc_fn_id; - dev->exception_lan_queue = info->exception_lan_queue; dev->is_pf = info->is_pf; dev->fpm_query_buf_pa = info->fpm_query_buf_pa; diff --git a/drivers/infiniband/hw/i40iw/i40iw_d.h b/drivers/infiniband/hw/i40iw/i40iw_d.h index 2ebaadbed379..65ec39e3746b 100644 --- a/drivers/infiniband/hw/i40iw/i40iw_d.h +++ b/drivers/infiniband/hw/i40iw/i40iw_d.h @@ -73,6 +73,10 @@ #define I40IW_FIRST_NON_PF_STAT 4 +#define I40IW_MTU_TO_MSS_IPV4 40 +#define I40IW_MTU_TO_MSS_IPV6 60 +#define I40IW_DEFAULT_MTU 1500 + #define LS_64_1(val, bits) ((u64)(uintptr_t)val << bits) #define RS_64_1(val, bits) ((u64)(uintptr_t)val >> bits) #define LS_32_1(val, bits) (u32)(val << bits) @@ -128,6 +132,7 @@ &_ceq->ceqe_base[I40IW_RING_GETCURRENT_TAIL(_ceq->ceq_ring)] \ ) +#define I40IW_AE_SOURCE_RSVD 0x0 #define I40IW_AE_SOURCE_RQ 0x1 #define I40IW_AE_SOURCE_RQ_0011 0x3 @@ -539,9 +544,6 @@ #define I40IW_CQPSQ_QP_MSSCHANGE_SHIFT 52 #define I40IW_CQPSQ_QP_MSSCHANGE_MASK (1ULL << I40IW_CQPSQ_QP_MSSCHANGE_SHIFT) -#define I40IW_CQPSQ_QP_STATRSRC_SHIFT 53 -#define I40IW_CQPSQ_QP_STATRSRC_MASK (1ULL << I40IW_CQPSQ_QP_STATRSRC_SHIFT) - #define I40IW_CQPSQ_QP_IGNOREMWBOUND_SHIFT 54 #define I40IW_CQPSQ_QP_IGNOREMWBOUND_MASK \ (1ULL << I40IW_CQPSQ_QP_IGNOREMWBOUND_SHIFT) @@ -1105,6 +1107,9 @@ #define I40IWQPC_SNDMSS_SHIFT 16 #define I40IWQPC_SNDMSS_MASK (0x3fffUL << I40IWQPC_SNDMSS_SHIFT) +#define I40IW_UDA_QPC_MAXFRAMESIZE_SHIFT 16 +#define I40IW_UDA_QPC_MAXFRAMESIZE_MASK (0x3fffUL << I40IW_UDA_QPC_MAXFRAMESIZE_SHIFT) + #define I40IWQPC_VLANTAG_SHIFT 32 #define I40IWQPC_VLANTAG_MASK (0xffffULL << I40IWQPC_VLANTAG_SHIFT) @@ -1296,8 +1301,13 @@ (0xffffffffULL << I40IWQPC_LOCAL_IPADDR0_SHIFT) /* wqe size considering 32 bytes per wqe*/ -#define I40IWQP_SW_MIN_WQSIZE 4 /* 128 bytes */ -#define I40IWQP_SW_MAX_WQSIZE 2048 /* 2048 bytes */ +#define I40IW_QP_SW_MIN_WQSIZE 4 /*in WRs*/ +#define I40IW_SQ_RSVD 2 +#define I40IW_RQ_RSVD 1 +#define I40IW_MAX_QUANTAS_PER_WR 2 +#define I40IW_QP_SW_MAX_SQ_QUANTAS 2048 +#define I40IW_QP_SW_MAX_RQ_QUANTAS 16384 +#define I40IW_MAX_QP_WRS ((I40IW_QP_SW_MAX_SQ_QUANTAS / I40IW_MAX_QUANTAS_PER_WR) - 1) #define I40IWQP_OP_RDMA_WRITE 0 #define I40IWQP_OP_RDMA_READ 1 @@ -1636,7 +1646,8 @@ enum i40iw_alignment { #define I40IW_AE_AMP_MWBIND_INVALID_BOUNDS 0x0119 #define I40IW_AE_AMP_MWBIND_TO_INVALID_PARENT 0x011a #define I40IW_AE_AMP_MWBIND_BIND_DISABLED 0x011b -#define I40IW_AE_AMP_WQE_INVALID_PARAMETER 0x0130 +#define I40IW_AE_UDA_XMIT_DGRAM_TOO_LONG 0x0132 +#define I40IW_AE_UDA_XMIT_DGRAM_TOO_SHORT 0x0134 #define I40IW_AE_BAD_CLOSE 0x0201 #define I40IW_AE_RDMAP_ROE_BAD_LLP_CLOSE 0x0202 #define I40IW_AE_CQ_OPERATION_ERROR 0x0203 @@ -1644,12 +1655,10 @@ enum i40iw_alignment { #define I40IW_AE_RDMA_READ_WHILE_ORD_ZERO 0x0205 #define I40IW_AE_STAG_ZERO_INVALID 0x0206 #define I40IW_AE_IB_RREQ_AND_Q1_FULL 0x0207 -#define I40IW_AE_SRQ_LIMIT 0x0209 #define I40IW_AE_WQE_UNEXPECTED_OPCODE 0x020a #define I40IW_AE_WQE_INVALID_PARAMETER 0x020b #define I40IW_AE_WQE_LSMM_TOO_LONG 0x0220 #define I40IW_AE_DDP_INVALID_MSN_GAP_IN_MSN 0x0301 -#define I40IW_AE_DDP_INVALID_MSN_RANGE_IS_NOT_VALID 0x0302 #define I40IW_AE_DDP_UBE_DDP_MESSAGE_TOO_LONG_FOR_AVAILABLE_BUFFER 0x0303 #define I40IW_AE_DDP_UBE_INVALID_DDP_VERSION 0x0304 #define I40IW_AE_DDP_UBE_INVALID_MO 0x0305 @@ -1663,12 +1672,10 @@ enum i40iw_alignment { #define I40IW_AE_INVALID_ARP_ENTRY 0x0401 #define I40IW_AE_INVALID_TCP_OPTION_RCVD 0x0402 #define I40IW_AE_STALE_ARP_ENTRY 0x0403 -#define I40IW_AE_INVALID_WQE_LENGTH 0x0404 #define I40IW_AE_INVALID_MAC_ENTRY 0x0405 #define I40IW_AE_LLP_CLOSE_COMPLETE 0x0501 #define I40IW_AE_LLP_CONNECTION_RESET 0x0502 #define I40IW_AE_LLP_FIN_RECEIVED 0x0503 -#define I40IW_AE_LLP_RECEIVED_MARKER_AND_LENGTH_FIELDS_DONT_MATCH 0x0504 #define I40IW_AE_LLP_RECEIVED_MPA_CRC_ERROR 0x0505 #define I40IW_AE_LLP_SEGMENT_TOO_LARGE 0x0506 #define I40IW_AE_LLP_SEGMENT_TOO_SMALL 0x0507 @@ -1685,9 +1692,6 @@ enum i40iw_alignment { #define I40IW_AE_LCE_QP_CATASTROPHIC 0x0700 #define I40IW_AE_LCE_FUNCTION_CATASTROPHIC 0x0701 #define I40IW_AE_LCE_CQ_CATASTROPHIC 0x0702 -#define I40IW_AE_UDA_XMIT_FRAG_SEQ 0x0800 -#define I40IW_AE_UDA_XMIT_DGRAM_TOO_LONG 0x0801 -#define I40IW_AE_UDA_XMIT_IPADDR_MISMATCH 0x0802 #define I40IW_AE_QP_SUSPEND_COMPLETE 0x0900 #define OP_DELETE_LOCAL_MAC_IPADDR_ENTRY 1 diff --git a/drivers/infiniband/hw/i40iw/i40iw_hw.c b/drivers/infiniband/hw/i40iw/i40iw_hw.c index 476867a3f584..e96bdafbcbb3 100644 --- a/drivers/infiniband/hw/i40iw/i40iw_hw.c +++ b/drivers/infiniband/hw/i40iw/i40iw_hw.c @@ -408,8 +408,9 @@ void i40iw_process_aeq(struct i40iw_device *iwdev) case I40IW_AE_LCE_FUNCTION_CATASTROPHIC: case I40IW_AE_LCE_CQ_CATASTROPHIC: case I40IW_AE_UDA_XMIT_DGRAM_TOO_LONG: - case I40IW_AE_UDA_XMIT_IPADDR_MISMATCH: + case I40IW_AE_UDA_XMIT_DGRAM_TOO_SHORT: ctx_info->err_rq_idx_valid = false; + /* fall through */ default: if (!info->sq && ctx_info->err_rq_idx_valid) { ctx_info->err_rq_idx = info->wqe_idx; diff --git a/drivers/infiniband/hw/i40iw/i40iw_main.c b/drivers/infiniband/hw/i40iw/i40iw_main.c index 27590ae21881..e824296713e2 100644 --- a/drivers/infiniband/hw/i40iw/i40iw_main.c +++ b/drivers/infiniband/hw/i40iw/i40iw_main.c @@ -353,6 +353,8 @@ static void i40iw_dele_ceqs(struct i40iw_device *iwdev) i40iw_disable_irq(dev, msix_vec, (void *)iwceq); i40iw_destroy_ceq(iwdev, iwceq); } + + iwdev->sc_dev.ceq_valid = false; } /** @@ -810,17 +812,16 @@ static enum i40iw_status_code i40iw_setup_ceqs(struct i40iw_device *iwdev, i40iw_enable_intr(&iwdev->sc_dev, msix_vec->idx); iwdev->ceqs_count++; } - exit: - if (status) { - if (!iwdev->ceqs_count) { - kfree(iwdev->ceqlist); - iwdev->ceqlist = NULL; - } else { - status = 0; - } + if (status && !iwdev->ceqs_count) { + kfree(iwdev->ceqlist); + iwdev->ceqlist = NULL; + return status; + } else { + iwdev->sc_dev.ceq_valid = true; + return 0; } - return status; + } /** @@ -958,13 +959,13 @@ static enum i40iw_status_code i40iw_initialize_ieq(struct i40iw_device *iwdev) memset(&info, 0, sizeof(info)); info.type = I40IW_PUDA_RSRC_TYPE_IEQ; info.cq_id = 2; - info.qp_id = iwdev->sc_dev.exception_lan_queue; + info.qp_id = iwdev->vsi.exception_lan_queue; info.count = 1; info.pd_id = 2; info.sq_size = 8192; info.rq_size = 8192; - info.buf_size = 2048; - info.tx_buf_cnt = 16384; + info.buf_size = iwdev->vsi.mtu + VLAN_ETH_HLEN; + info.tx_buf_cnt = 4096; status = i40iw_puda_create_rsrc(&iwdev->vsi, &info); if (status) i40iw_pr_err("ieq create fail\n"); @@ -972,6 +973,21 @@ static enum i40iw_status_code i40iw_initialize_ieq(struct i40iw_device *iwdev) } /** + * i40iw_reinitialize_ieq - destroy and re-create ieq + * @dev: iwarp device + */ +void i40iw_reinitialize_ieq(struct i40iw_sc_dev *dev) +{ + struct i40iw_device *iwdev = (struct i40iw_device *)dev->back_dev; + + i40iw_puda_dele_resources(&iwdev->vsi, I40IW_PUDA_RSRC_TYPE_IEQ, false); + if (i40iw_initialize_ieq(iwdev)) { + iwdev->reset = true; + i40iw_request_reset(iwdev); + } +} + +/** * i40iw_hmc_setup - create hmc objects for the device * @iwdev: iwarp device * @@ -1327,8 +1343,8 @@ static enum i40iw_status_code i40iw_initialize_dev(struct i40iw_device *iwdev, info.bar0 = ldev->hw_addr; info.hw = &iwdev->hw; info.debug_mask = debug; - l2params.mss = - (ldev->params.mtu) ? ldev->params.mtu - I40IW_MTU_TO_MSS : I40IW_DEFAULT_MSS; + l2params.mtu = + (ldev->params.mtu) ? ldev->params.mtu : I40IW_DEFAULT_MTU; for (i = 0; i < I40E_CLIENT_MAX_USER_PRIORITY; i++) { qset = ldev->params.qos.prio_qos[i].qs_handle; l2params.qs_handle_list[i] = qset; @@ -1338,7 +1354,6 @@ static enum i40iw_status_code i40iw_initialize_dev(struct i40iw_device *iwdev, iwdev->dcb = true; } i40iw_pr_info("DCB is set/clear = %d\n", iwdev->dcb); - info.exception_lan_queue = 1; info.vchnl_send = i40iw_virtchnl_send; status = i40iw_device_init(&iwdev->sc_dev, &info); @@ -1348,6 +1363,7 @@ static enum i40iw_status_code i40iw_initialize_dev(struct i40iw_device *iwdev, vsi_info.dev = &iwdev->sc_dev; vsi_info.back_vsi = (void *)iwdev; vsi_info.params = &l2params; + vsi_info.exception_lan_queue = 1; i40iw_sc_vsi_init(&iwdev->vsi, &vsi_info); if (dev->is_pf) { @@ -1748,7 +1764,7 @@ static void i40iw_l2param_change(struct i40e_info *ldev, struct i40e_client *cli for (i = 0; i < I40E_CLIENT_MAX_USER_PRIORITY; i++) l2params->qs_handle_list[i] = params->qos.prio_qos[i].qs_handle; - l2params->mss = (params->mtu) ? params->mtu - I40IW_MTU_TO_MSS : iwdev->vsi.mss; + l2params->mtu = (params->mtu) ? params->mtu : iwdev->vsi.mtu; INIT_WORK(&work->work, i40iw_l2params_worker); queue_work(iwdev->param_wq, &work->work); diff --git a/drivers/infiniband/hw/i40iw/i40iw_p.h b/drivers/infiniband/hw/i40iw/i40iw_p.h index 5498ad01c280..11d3a2a72100 100644 --- a/drivers/infiniband/hw/i40iw/i40iw_p.h +++ b/drivers/infiniband/hw/i40iw/i40iw_p.h @@ -86,7 +86,7 @@ void i40iw_sc_vsi_init(struct i40iw_sc_vsi *vsi, struct i40iw_vsi_init_info *inf void i40iw_change_l2params(struct i40iw_sc_vsi *vsi, struct i40iw_l2params *l2params); void i40iw_qp_add_qos(struct i40iw_sc_qp *qp); - +void i40iw_qp_rem_qos(struct i40iw_sc_qp *qp); void i40iw_terminate_send_fin(struct i40iw_sc_qp *qp); void i40iw_terminate_connection(struct i40iw_sc_qp *qp, struct i40iw_aeqe_info *info); @@ -123,5 +123,6 @@ enum i40iw_status_code i40iw_allocate_virt_mem(struct i40iw_hw *hw, enum i40iw_status_code i40iw_free_virt_mem(struct i40iw_hw *hw, struct i40iw_virt_mem *mem); u8 i40iw_get_encoded_wqe_size(u32 wqsize, bool cqpsq); +void i40iw_reinitialize_ieq(struct i40iw_sc_dev *dev); #endif diff --git a/drivers/infiniband/hw/i40iw/i40iw_puda.c b/drivers/infiniband/hw/i40iw/i40iw_puda.c index 59f70676f0e0..796a815b53fd 100644 --- a/drivers/infiniband/hw/i40iw/i40iw_puda.c +++ b/drivers/infiniband/hw/i40iw/i40iw_puda.c @@ -488,7 +488,7 @@ static void i40iw_puda_qp_setctx(struct i40iw_puda_rsrc *rsrc) LS_64(qp->hw_rq_size, I40IWQPC_RQSIZE) | LS_64(qp->hw_sq_size, I40IWQPC_SQSIZE)); - set_64bit_val(qp_ctx, 48, LS_64(1514, I40IWQPC_SNDMSS)); + set_64bit_val(qp_ctx, 48, LS_64(rsrc->buf_size, I40IW_UDA_QPC_MAXFRAMESIZE)); set_64bit_val(qp_ctx, 56, 0); set_64bit_val(qp_ctx, 64, 1); @@ -611,12 +611,14 @@ static enum i40iw_status_code i40iw_puda_qp_create(struct i40iw_puda_rsrc *rsrc) qp->user_pri = 0; i40iw_qp_add_qos(qp); i40iw_puda_qp_setctx(rsrc); - if (rsrc->ceq_valid) + if (rsrc->dev->ceq_valid) ret = i40iw_cqp_qp_create_cmd(rsrc->dev, qp); else ret = i40iw_puda_qp_wqe(rsrc->dev, qp); - if (ret) + if (ret) { + i40iw_qp_rem_qos(qp); i40iw_free_dma_mem(rsrc->dev->hw, &rsrc->qpmem); + } return ret; } @@ -704,7 +706,7 @@ static enum i40iw_status_code i40iw_puda_cq_create(struct i40iw_puda_rsrc *rsrc) ret = dev->iw_priv_cq_ops->cq_init(cq, &info); if (ret) goto error; - if (rsrc->ceq_valid) + if (rsrc->dev->ceq_valid) ret = i40iw_cqp_cq_create_cmd(dev, cq); else ret = i40iw_puda_cq_wqe(dev, cq); @@ -724,7 +726,7 @@ static void i40iw_puda_free_qp(struct i40iw_puda_rsrc *rsrc) struct i40iw_ccq_cqe_info compl_info; struct i40iw_sc_dev *dev = rsrc->dev; - if (rsrc->ceq_valid) { + if (rsrc->dev->ceq_valid) { i40iw_cqp_qp_destroy_cmd(dev, &rsrc->qp); return; } @@ -757,7 +759,7 @@ static void i40iw_puda_free_cq(struct i40iw_puda_rsrc *rsrc) struct i40iw_ccq_cqe_info compl_info; struct i40iw_sc_dev *dev = rsrc->dev; - if (rsrc->ceq_valid) { + if (rsrc->dev->ceq_valid) { i40iw_cqp_cq_destroy_cmd(dev, &rsrc->cq); return; } @@ -813,6 +815,7 @@ void i40iw_puda_dele_resources(struct i40iw_sc_vsi *vsi, switch (rsrc->completion) { case PUDA_HASH_CRC_COMPLETE: i40iw_free_hash_desc(rsrc->hash_desc); + /* fall through */ case PUDA_QP_CREATED: if (!reset) i40iw_puda_free_qp(rsrc); @@ -921,7 +924,6 @@ enum i40iw_status_code i40iw_puda_create_rsrc(struct i40iw_sc_vsi *vsi, rsrc->xmit_complete = i40iw_ieq_tx_compl; } - rsrc->ceq_valid = info->ceq_valid; rsrc->type = info->type; rsrc->sq_wrtrk_array = (struct i40iw_sq_uk_wr_trk_info *)((u8 *)vmem->va + pudasize); rsrc->rq_wrid_array = (u64 *)((u8 *)vmem->va + pudasize + sqwridsize); @@ -1400,7 +1402,8 @@ static void i40iw_ieq_handle_exception(struct i40iw_puda_rsrc *ieq, pfpdu->rcv_nxt = fps; pfpdu->fps = fps; pfpdu->mode = true; - pfpdu->max_fpdu_data = ieq->vsi->mss; + pfpdu->max_fpdu_data = (buf->ipv4) ? (ieq->vsi->mtu - I40IW_MTU_TO_MSS_IPV4) : + (ieq->vsi->mtu - I40IW_MTU_TO_MSS_IPV6); pfpdu->pmode_count++; INIT_LIST_HEAD(rxlist); i40iw_ieq_check_first_buf(buf, fps); diff --git a/drivers/infiniband/hw/i40iw/i40iw_puda.h b/drivers/infiniband/hw/i40iw/i40iw_puda.h index dba05ce7d392..660aa3edae56 100644 --- a/drivers/infiniband/hw/i40iw/i40iw_puda.h +++ b/drivers/infiniband/hw/i40iw/i40iw_puda.h @@ -100,7 +100,6 @@ struct i40iw_puda_rsrc_info { enum puda_resource_type type; /* ILQ or IEQ */ u32 count; u16 pd_id; - bool ceq_valid; u32 cq_id; u32 qp_id; u32 sq_size; @@ -125,7 +124,6 @@ struct i40iw_puda_rsrc { enum puda_resource_type type; u16 buf_size; /*buffer must be max datalen + tcpip hdr + mac */ u16 mss; - bool ceq_valid; u32 cq_id; u32 qp_id; u32 sq_size; diff --git a/drivers/infiniband/hw/i40iw/i40iw_type.h b/drivers/infiniband/hw/i40iw/i40iw_type.h index 63118f6d5ab4..a27d392c92a2 100644 --- a/drivers/infiniband/hw/i40iw/i40iw_type.h +++ b/drivers/infiniband/hw/i40iw/i40iw_type.h @@ -250,6 +250,7 @@ struct i40iw_vsi_pestat { struct i40iw_dev_hw_stats last_read_hw_stats; struct i40iw_dev_hw_stats_offsets hw_stats_offsets; struct timer_list stats_timer; + struct i40iw_sc_vsi *vsi; spinlock_t lock; /* rdma stats lock */ }; @@ -380,7 +381,6 @@ struct i40iw_sc_qp { u8 *q2_buf; u64 qp_compl_ctx; u16 qs_handle; - u16 exception_lan_queue; u16 push_idx; u8 sq_tph_val; u8 rq_tph_val; @@ -459,7 +459,8 @@ struct i40iw_sc_vsi { u32 ieq_count; struct i40iw_virt_mem ieq_mem; struct i40iw_puda_rsrc *ieq; - u16 mss; + u16 exception_lan_queue; + u16 mtu; u8 fcn_id; bool stats_fcn_id_alloc; struct i40iw_qos qos[I40IW_MAX_USER_PRIORITY]; @@ -501,10 +502,10 @@ struct i40iw_sc_dev { struct i40iw_hmc_fpm_misc hmc_fpm_misc; u32 debug_mask; - u16 exception_lan_queue; u8 hmc_fn_id; bool is_pf; bool vchnl_up; + bool ceq_valid; u8 vf_id; wait_queue_head_t vf_reqs; u64 cqp_cmd_stats[OP_SIZE_CQP_STAT_ARRAY]; @@ -534,7 +535,6 @@ struct i40iw_create_qp_info { bool ord_valid; bool tcp_ctx_valid; bool cq_num_valid; - bool static_rsrc; bool arp_cache_idx_valid; }; @@ -546,7 +546,6 @@ struct i40iw_modify_qp_info { bool ord_valid; bool tcp_ctx_valid; bool cq_num_valid; - bool static_rsrc; bool arp_cache_idx_valid; bool reset_tcp_conn; bool remove_hash_idx; @@ -568,13 +567,14 @@ struct i40iw_ccq_cqe_info { struct i40iw_l2params { u16 qs_handle_list[I40IW_MAX_USER_PRIORITY]; - u16 mss; + u16 mtu; }; struct i40iw_vsi_init_info { struct i40iw_sc_dev *dev; void *back_vsi; struct i40iw_l2params *params; + u16 exception_lan_queue; }; struct i40iw_vsi_stats_info { @@ -592,7 +592,6 @@ struct i40iw_device_init_info { struct i40iw_hw *hw; void __iomem *bar0; enum i40iw_status_code (*vchnl_send)(struct i40iw_sc_dev *, u32, u8 *, u16); - u16 exception_lan_queue; u8 hmc_fn_id; bool is_pf; u32 debug_mask; diff --git a/drivers/infiniband/hw/i40iw/i40iw_uk.c b/drivers/infiniband/hw/i40iw/i40iw_uk.c index 0aadb7a0d1aa..3ec5389a81a1 100644 --- a/drivers/infiniband/hw/i40iw/i40iw_uk.c +++ b/drivers/infiniband/hw/i40iw/i40iw_uk.c @@ -821,6 +821,18 @@ static enum i40iw_status_code i40iw_cq_poll_completion(struct i40iw_cq_uk *cq, I40IW_RING_SET_TAIL(qp->rq_ring, array_idx + 1); pring = &qp->rq_ring; } else { + if (qp->first_sq_wq) { + qp->first_sq_wq = false; + if (!wqe_idx && (qp->sq_ring.head == qp->sq_ring.tail)) { + I40IW_RING_MOVE_HEAD_NOCHECK(cq->cq_ring); + I40IW_RING_MOVE_TAIL(cq->cq_ring); + set_64bit_val(cq->shadow_area, 0, + I40IW_RING_GETCURRENT_HEAD(cq->cq_ring)); + memset(info, 0, sizeof(struct i40iw_cq_poll_info)); + return i40iw_cq_poll_completion(cq, info); + } + } + if (info->comp_status != I40IW_COMPL_STATUS_FLUSHED) { info->wr_id = qp->sq_wrtrk_array[wqe_idx].wrid; info->bytes_xfered = qp->sq_wrtrk_array[wqe_idx].wr_len; @@ -882,8 +894,21 @@ exit: } /** + * i40iw_qp_roundup - return round up QP WQ depth + * @wqdepth: WQ depth in quantas to round up + */ +static int i40iw_qp_round_up(u32 wqdepth) +{ + int scount = 1; + + for (wqdepth--; scount <= 16; scount *= 2) + wqdepth |= wqdepth >> scount; + + return ++wqdepth; +} + +/** * i40iw_get_wqe_shift - get shift count for maximum wqe size - * @wqdepth: depth of wq required. * @sge: Maximum Scatter Gather Elements wqe * @inline_data: Maximum inline data size * @shift: Returns the shift needed based on sge @@ -893,22 +918,48 @@ exit: * For 2 or 3 SGEs or inline data <= 48, shift = 1 (wqe size of 64 bytes). * Shift of 2 otherwise (wqe size of 128 bytes). */ -enum i40iw_status_code i40iw_get_wqe_shift(u32 wqdepth, u32 sge, u32 inline_data, u8 *shift) +void i40iw_get_wqe_shift(u32 sge, u32 inline_data, u8 *shift) { - u32 size; - *shift = 0; if (sge > 1 || inline_data > 16) *shift = (sge < 4 && inline_data <= 48) ? 1 : 2; +} - /* check if wqdepth is multiple of 2 or not */ +/* + * i40iw_get_sqdepth - get SQ depth (quantas) + * @sq_size: SQ size + * @shift: shift which determines size of WQE + * @sqdepth: depth of SQ + * + */ +enum i40iw_status_code i40iw_get_sqdepth(u32 sq_size, u8 shift, u32 *sqdepth) +{ + *sqdepth = i40iw_qp_round_up((sq_size << shift) + I40IW_SQ_RSVD); - if ((wqdepth < I40IWQP_SW_MIN_WQSIZE) || (wqdepth & (wqdepth - 1))) + if (*sqdepth < (I40IW_QP_SW_MIN_WQSIZE << shift)) + *sqdepth = I40IW_QP_SW_MIN_WQSIZE << shift; + else if (*sqdepth > I40IW_QP_SW_MAX_SQ_QUANTAS) return I40IW_ERR_INVALID_SIZE; - size = wqdepth << *shift; /* multiple of 32 bytes count */ - if (size > I40IWQP_SW_MAX_WQSIZE) + return 0; +} + +/* + * i40iw_get_rq_depth - get RQ depth (quantas) + * @rq_size: RQ size + * @shift: shift which determines size of WQE + * @rqdepth: depth of RQ + * + */ +enum i40iw_status_code i40iw_get_rqdepth(u32 rq_size, u8 shift, u32 *rqdepth) +{ + *rqdepth = i40iw_qp_round_up((rq_size << shift) + I40IW_RQ_RSVD); + + if (*rqdepth < (I40IW_QP_SW_MIN_WQSIZE << shift)) + *rqdepth = I40IW_QP_SW_MIN_WQSIZE << shift; + else if (*rqdepth > I40IW_QP_SW_MAX_RQ_QUANTAS) return I40IW_ERR_INVALID_SIZE; + return 0; } @@ -962,9 +1013,7 @@ enum i40iw_status_code i40iw_qp_uk_init(struct i40iw_qp_uk *qp, if (info->max_rq_frag_cnt > I40IW_MAX_WQ_FRAGMENT_COUNT) return I40IW_ERR_INVALID_FRAG_COUNT; - ret_code = i40iw_get_wqe_shift(info->sq_size, info->max_sq_frag_cnt, info->max_inline_data, &sqshift); - if (ret_code) - return ret_code; + i40iw_get_wqe_shift(info->max_sq_frag_cnt, info->max_inline_data, &sqshift); qp->sq_base = info->sq; qp->rq_base = info->rq; @@ -988,6 +1037,7 @@ enum i40iw_status_code i40iw_qp_uk_init(struct i40iw_qp_uk *qp, I40IW_RING_MOVE_TAIL(qp->sq_ring); I40IW_RING_MOVE_HEAD(qp->initial_ring, ret_code); qp->swqe_polarity = 1; + qp->first_sq_wq = true; qp->swqe_polarity_deferred = 1; qp->rwqe_polarity = 0; @@ -997,9 +1047,7 @@ enum i40iw_status_code i40iw_qp_uk_init(struct i40iw_qp_uk *qp, I40IW_RING_INIT(qp->rq_ring, qp->rq_size); switch (info->abi_ver) { case 4: - ret_code = i40iw_get_wqe_shift(info->rq_size, info->max_rq_frag_cnt, 0, &rqshift); - if (ret_code) - return ret_code; + i40iw_get_wqe_shift(info->max_rq_frag_cnt, 0, &rqshift); break; case 5: /* fallthrough until next ABI version */ default: diff --git a/drivers/infiniband/hw/i40iw/i40iw_user.h b/drivers/infiniband/hw/i40iw/i40iw_user.h index 84be6f13b9c5..e73efc59a0ab 100644 --- a/drivers/infiniband/hw/i40iw/i40iw_user.h +++ b/drivers/infiniband/hw/i40iw/i40iw_user.h @@ -204,18 +204,6 @@ struct i40iw_post_inline_send { u32 len; }; -struct i40iw_post_send_w_inv { - i40iw_sgl sg_list; - u32 num_sges; - i40iw_stag remote_stag_to_inv; -}; - -struct i40iw_post_inline_send_w_inv { - void *data; - u32 len; - i40iw_stag remote_stag_to_inv; -}; - struct i40iw_rdma_write { i40iw_sgl lo_sg_list; u32 num_lo_sges; @@ -257,9 +245,6 @@ struct i40iw_post_sq_info { bool defer_flag; union { struct i40iw_post_send send; - struct i40iw_post_send send_w_sol; - struct i40iw_post_send_w_inv send_w_inv; - struct i40iw_post_send_w_inv send_w_sol_inv; struct i40iw_rdma_write rdma_write; struct i40iw_rdma_read rdma_read; struct i40iw_rdma_read rdma_read_inv; @@ -267,9 +252,6 @@ struct i40iw_post_sq_info { struct i40iw_inv_local_stag inv_local_stag; struct i40iw_inline_rdma_write inline_rdma_write; struct i40iw_post_inline_send inline_send; - struct i40iw_post_inline_send inline_send_w_sol; - struct i40iw_post_inline_send_w_inv inline_send_w_inv; - struct i40iw_post_inline_send_w_inv inline_send_w_sol_inv; } op; }; @@ -376,6 +358,7 @@ struct i40iw_qp_uk { u8 rwqe_polarity; u8 rq_wqe_size; u8 rq_wqe_size_multiplier; + bool first_sq_wq; bool deferred_flag; }; @@ -442,5 +425,7 @@ enum i40iw_status_code i40iw_fragcnt_to_wqesize_sq(u32 frag_cnt, u8 *wqe_size); enum i40iw_status_code i40iw_fragcnt_to_wqesize_rq(u32 frag_cnt, u8 *wqe_size); enum i40iw_status_code i40iw_inline_data_size_to_wqesize(u32 data_size, u8 *wqe_size); -enum i40iw_status_code i40iw_get_wqe_shift(u32 wqdepth, u32 sge, u32 inline_data, u8 *shift); +void i40iw_get_wqe_shift(u32 sge, u32 inline_data, u8 *shift); +enum i40iw_status_code i40iw_get_sqdepth(u32 sq_size, u8 shift, u32 *sqdepth); +enum i40iw_status_code i40iw_get_rqdepth(u32 rq_size, u8 shift, u32 *rqdepth); #endif diff --git a/drivers/infiniband/hw/i40iw/i40iw_utils.c b/drivers/infiniband/hw/i40iw/i40iw_utils.c index e52dbbb4165e..8845dba7c438 100644 --- a/drivers/infiniband/hw/i40iw/i40iw_utils.c +++ b/drivers/infiniband/hw/i40iw/i40iw_utils.c @@ -168,11 +168,16 @@ int i40iw_inetaddr_event(struct notifier_block *notifier, if (netdev != event_netdev) return NOTIFY_DONE; - if (upper_dev) - local_ipaddr = ntohl( - ((struct in_device *)upper_dev->ip_ptr)->ifa_list->ifa_address); - else + if (upper_dev) { + struct in_device *in; + + rcu_read_lock(); + in = __in_dev_get_rcu(upper_dev); + local_ipaddr = ntohl(in->ifa_list->ifa_address); + rcu_read_unlock(); + } else { local_ipaddr = ntohl(ifa->ifa_address); + } switch (event) { case NETDEV_DOWN: action = I40IW_ARP_DELETE; @@ -870,9 +875,9 @@ void i40iw_terminate_done(struct i40iw_sc_qp *qp, int timeout_occurred) * i40iw_terminate_imeout - timeout happened * @context: points to iwarp qp */ -static void i40iw_terminate_timeout(unsigned long context) +static void i40iw_terminate_timeout(struct timer_list *t) { - struct i40iw_qp *iwqp = (struct i40iw_qp *)context; + struct i40iw_qp *iwqp = from_timer(iwqp, t, terminate_timer); struct i40iw_sc_qp *qp = (struct i40iw_sc_qp *)&iwqp->sc_qp; i40iw_terminate_done(qp, 1); @@ -889,8 +894,7 @@ void i40iw_terminate_start_timer(struct i40iw_sc_qp *qp) iwqp = (struct i40iw_qp *)qp->back_qp; i40iw_add_ref(&iwqp->ibqp); - setup_timer(&iwqp->terminate_timer, i40iw_terminate_timeout, - (unsigned long)iwqp); + timer_setup(&iwqp->terminate_timer, i40iw_terminate_timeout, 0); iwqp->terminate_timer.expires = jiffies + HZ; add_timer(&iwqp->terminate_timer); } @@ -1445,11 +1449,12 @@ enum i40iw_status_code i40iw_puda_get_tcpip_info(struct i40iw_puda_completion_in * i40iw_hw_stats_timeout - Stats timer-handler which updates all HW stats * @vsi: pointer to the vsi structure */ -static void i40iw_hw_stats_timeout(unsigned long vsi) +static void i40iw_hw_stats_timeout(struct timer_list *t) { - struct i40iw_sc_vsi *sc_vsi = (struct i40iw_sc_vsi *)vsi; + struct i40iw_vsi_pestat *pf_devstat = from_timer(pf_devstat, t, + stats_timer); + struct i40iw_sc_vsi *sc_vsi = pf_devstat->vsi; struct i40iw_sc_dev *pf_dev = sc_vsi->dev; - struct i40iw_vsi_pestat *pf_devstat = sc_vsi->pestat; struct i40iw_vsi_pestat *vf_devstat = NULL; u16 iw_vf_idx; unsigned long flags; @@ -1480,8 +1485,7 @@ void i40iw_hw_stats_start_timer(struct i40iw_sc_vsi *vsi) { struct i40iw_vsi_pestat *devstat = vsi->pestat; - setup_timer(&devstat->stats_timer, i40iw_hw_stats_timeout, - (unsigned long)vsi); + timer_setup(&devstat->stats_timer, i40iw_hw_stats_timeout, 0); mod_timer(&devstat->stats_timer, jiffies + msecs_to_jiffies(STATS_TIMER_DELAY)); } diff --git a/drivers/infiniband/hw/i40iw/i40iw_verbs.c b/drivers/infiniband/hw/i40iw/i40iw_verbs.c index 62be0a41ad0b..3c6f3ce88f89 100644 --- a/drivers/infiniband/hw/i40iw/i40iw_verbs.c +++ b/drivers/infiniband/hw/i40iw/i40iw_verbs.c @@ -69,7 +69,7 @@ static int i40iw_query_device(struct ib_device *ibdev, props->hw_ver = (u32)iwdev->sc_dev.hw_rev; props->max_mr_size = I40IW_MAX_OUTBOUND_MESSAGE_SIZE; props->max_qp = iwdev->max_qp - iwdev->used_qps; - props->max_qp_wr = (I40IW_MAX_WQ_ENTRIES >> 2) - 1; + props->max_qp_wr = I40IW_MAX_QP_WRS; props->max_sge = I40IW_MAX_WQ_FRAGMENT_COUNT; props->max_cq = iwdev->max_cq - iwdev->used_cqs; props->max_cqe = iwdev->max_cqe; @@ -381,22 +381,6 @@ static int i40iw_dealloc_pd(struct ib_pd *ibpd) } /** - * i40iw_qp_roundup - return round up qp ring size - * @wr_ring_size: ring size to round up - */ -static int i40iw_qp_roundup(u32 wr_ring_size) -{ - int scount = 1; - - if (wr_ring_size < I40IWQP_SW_MIN_WQSIZE) - wr_ring_size = I40IWQP_SW_MIN_WQSIZE; - - for (wr_ring_size--; scount <= 16; scount *= 2) - wr_ring_size |= wr_ring_size >> scount; - return ++wr_ring_size; -} - -/** * i40iw_get_pbl - Retrieve pbl from a list given a virtual * address * @va: user virtual address @@ -515,21 +499,19 @@ static int i40iw_setup_kmode_qp(struct i40iw_device *iwdev, { struct i40iw_dma_mem *mem = &iwqp->kqp.dma_mem; u32 sqdepth, rqdepth; - u32 sq_size, rq_size; u8 sqshift; u32 size; enum i40iw_status_code status; struct i40iw_qp_uk_init_info *ukinfo = &info->qp_uk_init_info; - sq_size = i40iw_qp_roundup(ukinfo->sq_size + 1); - rq_size = i40iw_qp_roundup(ukinfo->rq_size + 1); - - status = i40iw_get_wqe_shift(sq_size, ukinfo->max_sq_frag_cnt, ukinfo->max_inline_data, &sqshift); + i40iw_get_wqe_shift(ukinfo->max_sq_frag_cnt, ukinfo->max_inline_data, &sqshift); + status = i40iw_get_sqdepth(ukinfo->sq_size, sqshift, &sqdepth); if (status) return -ENOMEM; - sqdepth = sq_size << sqshift; - rqdepth = rq_size << I40IW_MAX_RQ_WQE_SHIFT; + status = i40iw_get_rqdepth(ukinfo->rq_size, I40IW_MAX_RQ_WQE_SHIFT, &rqdepth); + if (status) + return -ENOMEM; size = sqdepth * sizeof(struct i40iw_sq_uk_wr_trk_info) + (rqdepth << 3); iwqp->kqp.wrid_mem = kzalloc(size, GFP_KERNEL); @@ -559,8 +541,8 @@ static int i40iw_setup_kmode_qp(struct i40iw_device *iwdev, ukinfo->shadow_area = ukinfo->rq[rqdepth].elem; info->shadow_area_pa = info->rq_pa + (rqdepth * I40IW_QP_WQE_MIN_SIZE); - ukinfo->sq_size = sq_size; - ukinfo->rq_size = rq_size; + ukinfo->sq_size = sqdepth >> sqshift; + ukinfo->rq_size = rqdepth >> I40IW_MAX_RQ_WQE_SHIFT; ukinfo->qp_id = iwqp->ibqp.qp_num; return 0; } @@ -2204,6 +2186,12 @@ static int i40iw_post_send(struct ib_qp *ibqp, ukqp = &iwqp->sc_qp.qp_uk; spin_lock_irqsave(&iwqp->lock, flags); + + if (iwqp->flush_issued) { + err = -EINVAL; + goto out; + } + while (ib_wr) { inv_stag = false; memset(&info, 0, sizeof(info)); @@ -2346,6 +2334,7 @@ static int i40iw_post_send(struct ib_qp *ibqp, ib_wr = ib_wr->next; } +out: if (err) *bad_wr = ib_wr; else @@ -2378,6 +2367,12 @@ static int i40iw_post_recv(struct ib_qp *ibqp, memset(&post_recv, 0, sizeof(post_recv)); spin_lock_irqsave(&iwqp->lock, flags); + + if (iwqp->flush_issued) { + err = -EINVAL; + goto out; + } + while (ib_wr) { post_recv.num_sges = ib_wr->num_sge; post_recv.wr_id = ib_wr->wr_id; diff --git a/drivers/infiniband/hw/mlx4/ah.c b/drivers/infiniband/hw/mlx4/ah.c index 538c46a73248..6dee4fdc5d67 100644 --- a/drivers/infiniband/hw/mlx4/ah.c +++ b/drivers/infiniband/hw/mlx4/ah.c @@ -92,12 +92,10 @@ static struct ib_ah *create_iboe_ah(struct ib_pd *pd, int ret; memcpy(&in6, grh->dgid.raw, sizeof(in6)); - if (rdma_is_multicast_addr(&in6)) { + if (rdma_is_multicast_addr(&in6)) is_mcast = 1; - rdma_get_mcast_mac(&in6, ah->av.eth.mac); - } else { - memcpy(ah->av.eth.mac, ah_attr->roce.dmac, ETH_ALEN); - } + + memcpy(ah->av.eth.mac, ah_attr->roce.dmac, ETH_ALEN); ret = ib_get_cached_gid(pd->device, rdma_ah_get_port_num(ah_attr), grh->sgid_index, &sgid, &gid_attr); if (ret) diff --git a/drivers/infiniband/hw/mlx4/cq.c b/drivers/infiniband/hw/mlx4/cq.c index cab796341697..6d5f405912dd 100644 --- a/drivers/infiniband/hw/mlx4/cq.c +++ b/drivers/infiniband/hw/mlx4/cq.c @@ -768,11 +768,13 @@ repoll: switch (cqe->owner_sr_opcode & MLX4_CQE_OPCODE_MASK) { case MLX4_OPCODE_RDMA_WRITE_IMM: wc->wc_flags |= IB_WC_WITH_IMM; + /* fall through */ case MLX4_OPCODE_RDMA_WRITE: wc->opcode = IB_WC_RDMA_WRITE; break; case MLX4_OPCODE_SEND_IMM: wc->wc_flags |= IB_WC_WITH_IMM; + /* fall through */ case MLX4_OPCODE_SEND: case MLX4_OPCODE_SEND_INVAL: wc->opcode = IB_WC_SEND; diff --git a/drivers/infiniband/hw/mlx4/mcg.c b/drivers/infiniband/hw/mlx4/mcg.c index 70eb9f917303..81ffc007e0a1 100644 --- a/drivers/infiniband/hw/mlx4/mcg.c +++ b/drivers/infiniband/hw/mlx4/mcg.c @@ -944,6 +944,7 @@ int mlx4_ib_mcg_multiplex_handler(struct ib_device *ibdev, int port, switch (sa_mad->mad_hdr.method) { case IB_MGMT_METHOD_SET: may_create = 1; + /* fall through */ case IB_SA_METHOD_DELETE: req = kzalloc(sizeof *req, GFP_KERNEL); if (!req) diff --git a/drivers/infiniband/hw/mlx5/ah.c b/drivers/infiniband/hw/mlx5/ah.c index 3363e29157f6..fe269f680103 100644 --- a/drivers/infiniband/hw/mlx5/ah.c +++ b/drivers/infiniband/hw/mlx5/ah.c @@ -89,10 +89,6 @@ struct ib_ah *mlx5_ib_create_ah(struct ib_pd *pd, struct rdma_ah_attr *ah_attr, resp.response_length = min_resp_len; - err = ib_resolve_eth_dmac(pd->device, ah_attr); - if (err) - return ERR_PTR(err); - memcpy(resp.dmac, ah_attr->roce.dmac, ETH_ALEN); err = ib_copy_to_udata(udata, &resp, resp.response_length); if (err) diff --git a/drivers/infiniband/hw/mlx5/cq.c b/drivers/infiniband/hw/mlx5/cq.c index 2aa53f427685..01b218a3c277 100644 --- a/drivers/infiniband/hw/mlx5/cq.c +++ b/drivers/infiniband/hw/mlx5/cq.c @@ -124,11 +124,13 @@ static void handle_good_req(struct ib_wc *wc, struct mlx5_cqe64 *cqe, switch (be32_to_cpu(cqe->sop_drop_qpn) >> 24) { case MLX5_OPCODE_RDMA_WRITE_IMM: wc->wc_flags |= IB_WC_WITH_IMM; + /* fall through */ case MLX5_OPCODE_RDMA_WRITE: wc->opcode = IB_WC_RDMA_WRITE; break; case MLX5_OPCODE_SEND_IMM: wc->wc_flags |= IB_WC_WITH_IMM; + /* fall through */ case MLX5_OPCODE_SEND: case MLX5_OPCODE_SEND_INVAL: wc->opcode = IB_WC_SEND; @@ -752,13 +754,13 @@ static int create_cq_user(struct mlx5_ib_dev *dev, struct ib_udata *udata, int err; ucmdlen = udata->inlen < sizeof(ucmd) ? - (sizeof(ucmd) - sizeof(ucmd.reserved)) : sizeof(ucmd); + (sizeof(ucmd) - sizeof(ucmd.flags)) : sizeof(ucmd); if (ib_copy_from_udata(&ucmd, udata, ucmdlen)) return -EFAULT; if (ucmdlen == sizeof(ucmd) && - ucmd.reserved != 0) + (ucmd.flags & ~(MLX5_IB_CREATE_CQ_FLAGS_CQE_128B_PAD))) return -EINVAL; if (ucmd.cqe_size != 64 && ucmd.cqe_size != 128) @@ -802,8 +804,10 @@ static int create_cq_user(struct mlx5_ib_dev *dev, struct ib_udata *udata, *index = to_mucontext(context)->bfregi.sys_pages[0]; if (ucmd.cqe_comp_en == 1) { - if (unlikely((*cqe_size != 64) || - !MLX5_CAP_GEN(dev->mdev, cqe_compression))) { + if (!((*cqe_size == 128 && + MLX5_CAP_GEN(dev->mdev, cqe_compression_128)) || + (*cqe_size == 64 && + MLX5_CAP_GEN(dev->mdev, cqe_compression)))) { err = -EOPNOTSUPP; mlx5_ib_warn(dev, "CQE compression is not supported for size %d!\n", *cqe_size); @@ -826,6 +830,19 @@ static int create_cq_user(struct mlx5_ib_dev *dev, struct ib_udata *udata, ilog2(ucmd.cqe_comp_res_format)); } + if (ucmd.flags & MLX5_IB_CREATE_CQ_FLAGS_CQE_128B_PAD) { + if (*cqe_size != 128 || + !MLX5_CAP_GEN(dev->mdev, cqe_128_always)) { + err = -EOPNOTSUPP; + mlx5_ib_warn(dev, + "CQE padding is not supported for CQE size of %dB!\n", + *cqe_size); + goto err_cqb; + } + + cq->private_flags |= MLX5_IB_CQ_PR_FLAGS_CQE_128_PAD; + } + return 0; err_cqb: @@ -985,7 +1002,10 @@ struct ib_cq *mlx5_ib_create_cq(struct ib_device *ibdev, cq->cqe_size = cqe_size; cqc = MLX5_ADDR_OF(create_cq_in, cqb, cq_context); - MLX5_SET(cqc, cqc, cqe_sz, cqe_sz_to_mlx_sz(cqe_size)); + MLX5_SET(cqc, cqc, cqe_sz, + cqe_sz_to_mlx_sz(cqe_size, + cq->private_flags & + MLX5_IB_CQ_PR_FLAGS_CQE_128_PAD)); MLX5_SET(cqc, cqc, log_cq_size, ilog2(entries)); MLX5_SET(cqc, cqc, uar_page, index); MLX5_SET(cqc, cqc, c_eqn, eqn); @@ -1335,7 +1355,10 @@ int mlx5_ib_resize_cq(struct ib_cq *ibcq, int entries, struct ib_udata *udata) MLX5_SET(cqc, cqc, log_page_size, page_shift - MLX5_ADAPTER_PAGE_SHIFT); - MLX5_SET(cqc, cqc, cqe_sz, cqe_sz_to_mlx_sz(cqe_size)); + MLX5_SET(cqc, cqc, cqe_sz, + cqe_sz_to_mlx_sz(cqe_size, + cq->private_flags & + MLX5_IB_CQ_PR_FLAGS_CQE_128_PAD)); MLX5_SET(cqc, cqc, log_cq_size, ilog2(entries)); MLX5_SET(modify_cq_in, in, op_mod, MLX5_CQ_OPMOD_RESIZE); diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c index 552f7bd4ecc3..260f8be1d0ed 100644 --- a/drivers/infiniband/hw/mlx5/main.c +++ b/drivers/infiniband/hw/mlx5/main.c @@ -824,8 +824,16 @@ static int mlx5_ib_query_device(struct ib_device *ibdev, sizeof(resp.mlx5_ib_support_multi_pkt_send_wqes); } - if (field_avail(typeof(resp), reserved, uhw->outlen)) - resp.response_length += sizeof(resp.reserved); + if (field_avail(typeof(resp), flags, uhw->outlen)) { + resp.response_length += sizeof(resp.flags); + + if (MLX5_CAP_GEN(mdev, cqe_compression_128)) + resp.flags |= + MLX5_IB_QUERY_DEV_RESP_FLAGS_CQE_128B_COMP; + + if (MLX5_CAP_GEN(mdev, cqe_128_always)) + resp.flags |= MLX5_IB_QUERY_DEV_RESP_FLAGS_CQE_128B_PAD; + } if (field_avail(typeof(resp), sw_parsing_caps, uhw->outlen)) { @@ -848,6 +856,36 @@ static int mlx5_ib_query_device(struct ib_device *ibdev, } } + if (field_avail(typeof(resp), striding_rq_caps, uhw->outlen)) { + resp.response_length += sizeof(resp.striding_rq_caps); + if (MLX5_CAP_GEN(mdev, striding_rq)) { + resp.striding_rq_caps.min_single_stride_log_num_of_bytes = + MLX5_MIN_SINGLE_STRIDE_LOG_NUM_BYTES; + resp.striding_rq_caps.max_single_stride_log_num_of_bytes = + MLX5_MAX_SINGLE_STRIDE_LOG_NUM_BYTES; + resp.striding_rq_caps.min_single_wqe_log_num_of_strides = + MLX5_MIN_SINGLE_WQE_LOG_NUM_STRIDES; + resp.striding_rq_caps.max_single_wqe_log_num_of_strides = + MLX5_MAX_SINGLE_WQE_LOG_NUM_STRIDES; + resp.striding_rq_caps.supported_qpts = + BIT(IB_QPT_RAW_PACKET); + } + } + + if (field_avail(typeof(resp), tunnel_offloads_caps, + uhw->outlen)) { + resp.response_length += sizeof(resp.tunnel_offloads_caps); + if (MLX5_CAP_ETH(mdev, tunnel_stateless_vxlan)) + resp.tunnel_offloads_caps |= + MLX5_IB_TUNNELED_OFFLOADS_VXLAN; + if (MLX5_CAP_ETH(mdev, tunnel_stateless_geneve_rx)) + resp.tunnel_offloads_caps |= + MLX5_IB_TUNNELED_OFFLOADS_GENEVE; + if (MLX5_CAP_ETH(mdev, tunnel_stateless_gre)) + resp.tunnel_offloads_caps |= + MLX5_IB_TUNNELED_OFFLOADS_GRE; + } + if (uhw->outlen) { err = ib_copy_to_udata(uhw, &resp, resp.response_length); diff --git a/drivers/infiniband/hw/mlx5/mlx5_ib.h b/drivers/infiniband/hw/mlx5/mlx5_ib.h index 189e80cd6b2f..0a328d6c6494 100644 --- a/drivers/infiniband/hw/mlx5/mlx5_ib.h +++ b/drivers/infiniband/hw/mlx5/mlx5_ib.h @@ -254,8 +254,14 @@ struct mlx5_ib_wq { enum mlx5_ib_wq_flags { MLX5_IB_WQ_FLAGS_DELAY_DROP = 0x1, + MLX5_IB_WQ_FLAGS_STRIDING_RQ = 0x2, }; +#define MLX5_MIN_SINGLE_WQE_LOG_NUM_STRIDES 9 +#define MLX5_MAX_SINGLE_WQE_LOG_NUM_STRIDES 16 +#define MLX5_MIN_SINGLE_STRIDE_LOG_NUM_BYTES 6 +#define MLX5_MAX_SINGLE_STRIDE_LOG_NUM_BYTES 13 + struct mlx5_ib_rwq { struct ib_wq ibwq; struct mlx5_core_qp core_qp; @@ -264,6 +270,9 @@ struct mlx5_ib_rwq { u32 log_rq_size; u32 rq_page_offset; u32 log_page_size; + u32 log_num_strides; + u32 two_byte_shift_en; + u32 single_stride_log_num_of_bytes; struct ib_umem *umem; size_t buf_size; unsigned int page_shift; @@ -389,6 +398,7 @@ struct mlx5_ib_qp { struct list_head cq_send_list; u32 rate_limit; u32 underlay_qpn; + bool tunnel_offload_en; }; struct mlx5_ib_cq_buf { @@ -411,6 +421,8 @@ enum mlx5_ib_qp_flags { MLX5_IB_QP_RSS = 1 << 8, MLX5_IB_QP_CVLAN_STRIPPING = 1 << 9, MLX5_IB_QP_UNDERLAY = 1 << 10, + /* Reserved for PCI_WRITE_PAD = 1 << 11, */ + MLX5_IB_QP_TUNNEL_OFFLOAD = 1 << 12, }; struct mlx5_umr_wr { @@ -435,6 +447,10 @@ struct mlx5_shared_mr_info { struct ib_umem *umem; }; +enum mlx5_ib_cq_pr_flags { + MLX5_IB_CQ_PR_FLAGS_CQE_128_PAD = 1 << 0, +}; + struct mlx5_ib_cq { struct ib_cq ibcq; struct mlx5_core_cq mcq; @@ -457,6 +473,7 @@ struct mlx5_ib_cq { struct list_head wc_list; enum ib_cq_notify_flags notify_flags; struct work_struct notify_work; + u16 private_flags; /* Use mlx5_ib_cq_pr_flags */ }; struct mlx5_ib_wc { diff --git a/drivers/infiniband/hw/mlx5/mr.c b/drivers/infiniband/hw/mlx5/mr.c index 37bbc543847a..9beee9cef137 100644 --- a/drivers/infiniband/hw/mlx5/mr.c +++ b/drivers/infiniband/hw/mlx5/mr.c @@ -1230,13 +1230,13 @@ struct ib_mr *mlx5_ib_reg_user_mr(struct ib_pd *pd, u64 start, u64 length, mr = alloc_mr_from_cache(pd, umem, virt_addr, length, ncont, page_shift, order, access_flags); if (PTR_ERR(mr) == -EAGAIN) { - mlx5_ib_dbg(dev, "cache empty for order %d", order); + mlx5_ib_dbg(dev, "cache empty for order %d\n", order); mr = NULL; } } else if (!MLX5_CAP_GEN(dev->mdev, umr_extended_translation_offset)) { if (access_flags & IB_ACCESS_ON_DEMAND) { err = -EINVAL; - pr_err("Got MR registration for ODP MR > 512MB, not supported for Connect-IB"); + pr_err("Got MR registration for ODP MR > 512MB, not supported for Connect-IB\n"); goto error; } use_umr = false; diff --git a/drivers/infiniband/hw/mlx5/odp.c b/drivers/infiniband/hw/mlx5/odp.c index 3d701c7a4c91..e2197bdda89c 100644 --- a/drivers/infiniband/hw/mlx5/odp.c +++ b/drivers/infiniband/hw/mlx5/odp.c @@ -32,6 +32,7 @@ #include <rdma/ib_umem.h> #include <rdma/ib_umem_odp.h> +#include <linux/kernel.h> #include "mlx5_ib.h" #include "cmd.h" @@ -929,9 +930,8 @@ static int mlx5_ib_mr_initiator_pfault_handler( return -EFAULT; } - if (unlikely(opcode >= sizeof(mlx5_ib_odp_opcode_cap) / - sizeof(mlx5_ib_odp_opcode_cap[0]) || - !(transport_caps & mlx5_ib_odp_opcode_cap[opcode]))) { + if (unlikely(opcode >= ARRAY_SIZE(mlx5_ib_odp_opcode_cap) || + !(transport_caps & mlx5_ib_odp_opcode_cap[opcode]))) { mlx5_ib_err(dev, "ODP fault on QP of an unsupported opcode 0x%x\n", opcode); return -EFAULT; diff --git a/drivers/infiniband/hw/mlx5/qp.c b/drivers/infiniband/hw/mlx5/qp.c index acb79d3a4f1d..9e22dead259a 100644 --- a/drivers/infiniband/hw/mlx5/qp.c +++ b/drivers/infiniband/hw/mlx5/qp.c @@ -1204,8 +1204,16 @@ static void destroy_raw_packet_qp_rq(struct mlx5_ib_dev *dev, mlx5_core_destroy_rq_tracked(dev->mdev, &rq->base.mqp); } +static bool tunnel_offload_supported(struct mlx5_core_dev *dev) +{ + return (MLX5_CAP_ETH(dev, tunnel_stateless_vxlan) || + MLX5_CAP_ETH(dev, tunnel_stateless_gre) || + MLX5_CAP_ETH(dev, tunnel_stateless_geneve_rx)); +} + static int create_raw_packet_qp_tir(struct mlx5_ib_dev *dev, - struct mlx5_ib_rq *rq, u32 tdn) + struct mlx5_ib_rq *rq, u32 tdn, + bool tunnel_offload_en) { u32 *in; void *tirc; @@ -1221,6 +1229,8 @@ static int create_raw_packet_qp_tir(struct mlx5_ib_dev *dev, MLX5_SET(tirc, tirc, disp_type, MLX5_TIRC_DISP_TYPE_DIRECT); MLX5_SET(tirc, tirc, inline_rqn, rq->base.mqp.qpn); MLX5_SET(tirc, tirc, transport_domain, tdn); + if (tunnel_offload_en) + MLX5_SET(tirc, tirc, tunneled_offload_en, 1); err = mlx5_core_create_tir(dev->mdev, in, inlen, &rq->tirn); @@ -1271,7 +1281,8 @@ static int create_raw_packet_qp(struct mlx5_ib_dev *dev, struct mlx5_ib_qp *qp, goto err_destroy_sq; - err = create_raw_packet_qp_tir(dev, rq, tdn); + err = create_raw_packet_qp_tir(dev, rq, tdn, + qp->tunnel_offload_en); if (err) goto err_destroy_rq; } @@ -1358,7 +1369,7 @@ static int create_rss_raw_qp_tir(struct mlx5_ib_dev *dev, struct mlx5_ib_qp *qp, if (udata->outlen < min_resp_len) return -EINVAL; - required_cmd_sz = offsetof(typeof(ucmd), reserved1) + sizeof(ucmd.reserved1); + required_cmd_sz = offsetof(typeof(ucmd), flags) + sizeof(ucmd.flags); if (udata->inlen < required_cmd_sz) { mlx5_ib_dbg(dev, "invalid inlen\n"); return -EINVAL; @@ -1381,8 +1392,20 @@ static int create_rss_raw_qp_tir(struct mlx5_ib_dev *dev, struct mlx5_ib_qp *qp, return -EOPNOTSUPP; } - if (memchr_inv(ucmd.reserved, 0, sizeof(ucmd.reserved)) || ucmd.reserved1) { - mlx5_ib_dbg(dev, "invalid reserved\n"); + if (ucmd.flags & ~MLX5_QP_FLAG_TUNNEL_OFFLOADS) { + mlx5_ib_dbg(dev, "invalid flags\n"); + return -EOPNOTSUPP; + } + + if (ucmd.flags & MLX5_QP_FLAG_TUNNEL_OFFLOADS && + !tunnel_offload_supported(dev->mdev)) { + mlx5_ib_dbg(dev, "tunnel offloads isn't supported\n"); + return -EOPNOTSUPP; + } + + if (ucmd.rx_hash_fields_mask & MLX5_RX_HASH_INNER && + !(ucmd.flags & MLX5_QP_FLAG_TUNNEL_OFFLOADS)) { + mlx5_ib_dbg(dev, "Tunnel offloads must be set for inner RSS\n"); return -EOPNOTSUPP; } @@ -1405,6 +1428,15 @@ static int create_rss_raw_qp_tir(struct mlx5_ib_dev *dev, struct mlx5_ib_qp *qp, MLX5_SET(tirc, tirc, transport_domain, tdn); hfso = MLX5_ADDR_OF(tirc, tirc, rx_hash_field_selector_outer); + + if (ucmd.flags & MLX5_QP_FLAG_TUNNEL_OFFLOADS) + MLX5_SET(tirc, tirc, tunneled_offload_en, 1); + + if (ucmd.rx_hash_fields_mask & MLX5_RX_HASH_INNER) + hfso = MLX5_ADDR_OF(tirc, tirc, rx_hash_field_selector_inner); + else + hfso = MLX5_ADDR_OF(tirc, tirc, rx_hash_field_selector_outer); + switch (ucmd.rx_hash_function) { case MLX5_RX_HASH_FUNC_TOEPLITZ: { @@ -1604,6 +1636,14 @@ static int create_qp_common(struct mlx5_ib_dev *dev, struct ib_pd *pd, qp->wq_sig = !!(ucmd.flags & MLX5_QP_FLAG_SIGNATURE); qp->scat_cqe = !!(ucmd.flags & MLX5_QP_FLAG_SCATTER_CQE); + if (ucmd.flags & MLX5_QP_FLAG_TUNNEL_OFFLOADS) { + if (init_attr->qp_type != IB_QPT_RAW_PACKET || + !tunnel_offload_supported(mdev)) { + mlx5_ib_dbg(dev, "Tunnel offload isn't supported\n"); + return -EOPNOTSUPP; + } + qp->tunnel_offload_en = true; + } if (init_attr->create_flags & IB_QP_CREATE_SOURCE_QPN) { if (init_attr->qp_type != IB_QPT_UD || @@ -3858,7 +3898,6 @@ int mlx5_ib_post_send(struct ib_qp *ibqp, struct ib_send_wr *wr, unsigned long flags; unsigned idx; int err = 0; - int inl = 0; int num_sge; void *seg; int nreq; @@ -4053,6 +4092,7 @@ int mlx5_ib_post_send(struct ib_qp *ibqp, struct ib_send_wr *wr, *bad_wr = wr; goto out; } + /* fall through */ case MLX5_IB_QPT_HW_GSI: set_datagram_seg(seg, wr); seg += sizeof(struct mlx5_wqe_datagram_seg); @@ -4116,7 +4156,6 @@ int mlx5_ib_post_send(struct ib_qp *ibqp, struct ib_send_wr *wr, *bad_wr = wr; goto out; } - inl = 1; size += sz; } else { dpseg = seg; @@ -4707,9 +4746,19 @@ static int create_rq(struct mlx5_ib_rwq *rwq, struct ib_pd *pd, MLX5_SET(rqc, rqc, state, MLX5_RQC_STATE_RST); MLX5_SET(rqc, rqc, flush_in_error_en, 1); wq = MLX5_ADDR_OF(rqc, rqc, wq); - MLX5_SET(wq, wq, wq_type, MLX5_WQ_TYPE_CYCLIC); + MLX5_SET(wq, wq, wq_type, + rwq->create_flags & MLX5_IB_WQ_FLAGS_STRIDING_RQ ? + MLX5_WQ_TYPE_CYCLIC_STRIDING_RQ : MLX5_WQ_TYPE_CYCLIC); MLX5_SET(wq, wq, end_padding_mode, MLX5_WQ_END_PAD_MODE_ALIGN); MLX5_SET(wq, wq, log_wq_stride, rwq->log_rq_stride); + if (rwq->create_flags & MLX5_IB_WQ_FLAGS_STRIDING_RQ) { + MLX5_SET(wq, wq, two_byte_shift_en, rwq->two_byte_shift_en); + MLX5_SET(wq, wq, log_wqe_stride_size, + rwq->single_stride_log_num_of_bytes - + MLX5_MIN_SINGLE_STRIDE_LOG_NUM_BYTES); + MLX5_SET(wq, wq, log_wqe_num_of_strides, rwq->log_num_strides - + MLX5_MIN_SINGLE_WQE_LOG_NUM_STRIDES); + } MLX5_SET(wq, wq, log_wq_sz, rwq->log_rq_size); MLX5_SET(wq, wq, pd, to_mpd(pd)->pdn); MLX5_SET(wq, wq, page_offset, rwq->rq_page_offset); @@ -4791,7 +4840,8 @@ static int prepare_user_rq(struct ib_pd *pd, int err; size_t required_cmd_sz; - required_cmd_sz = offsetof(typeof(ucmd), reserved) + sizeof(ucmd.reserved); + required_cmd_sz = offsetof(typeof(ucmd), single_stride_log_num_of_bytes) + + sizeof(ucmd.single_stride_log_num_of_bytes); if (udata->inlen < required_cmd_sz) { mlx5_ib_dbg(dev, "invalid inlen\n"); return -EINVAL; @@ -4809,14 +4859,39 @@ static int prepare_user_rq(struct ib_pd *pd, return -EFAULT; } - if (ucmd.comp_mask) { + if (ucmd.comp_mask & (~MLX5_IB_CREATE_WQ_STRIDING_RQ)) { mlx5_ib_dbg(dev, "invalid comp mask\n"); return -EOPNOTSUPP; - } - - if (ucmd.reserved) { - mlx5_ib_dbg(dev, "invalid reserved\n"); - return -EOPNOTSUPP; + } else if (ucmd.comp_mask & MLX5_IB_CREATE_WQ_STRIDING_RQ) { + if (!MLX5_CAP_GEN(dev->mdev, striding_rq)) { + mlx5_ib_dbg(dev, "Striding RQ is not supported\n"); + return -EOPNOTSUPP; + } + if ((ucmd.single_stride_log_num_of_bytes < + MLX5_MIN_SINGLE_STRIDE_LOG_NUM_BYTES) || + (ucmd.single_stride_log_num_of_bytes > + MLX5_MAX_SINGLE_STRIDE_LOG_NUM_BYTES)) { + mlx5_ib_dbg(dev, "Invalid log stride size (%u. Range is %u - %u)\n", + ucmd.single_stride_log_num_of_bytes, + MLX5_MIN_SINGLE_STRIDE_LOG_NUM_BYTES, + MLX5_MAX_SINGLE_STRIDE_LOG_NUM_BYTES); + return -EINVAL; + } + if ((ucmd.single_wqe_log_num_of_strides > + MLX5_MAX_SINGLE_WQE_LOG_NUM_STRIDES) || + (ucmd.single_wqe_log_num_of_strides < + MLX5_MIN_SINGLE_WQE_LOG_NUM_STRIDES)) { + mlx5_ib_dbg(dev, "Invalid log num strides (%u. Range is %u - %u)\n", + ucmd.single_wqe_log_num_of_strides, + MLX5_MIN_SINGLE_WQE_LOG_NUM_STRIDES, + MLX5_MAX_SINGLE_WQE_LOG_NUM_STRIDES); + return -EINVAL; + } + rwq->single_stride_log_num_of_bytes = + ucmd.single_stride_log_num_of_bytes; + rwq->log_num_strides = ucmd.single_wqe_log_num_of_strides; + rwq->two_byte_shift_en = !!ucmd.two_byte_shift_en; + rwq->create_flags |= MLX5_IB_WQ_FLAGS_STRIDING_RQ; } err = set_user_rq_size(dev, init_attr, &ucmd, rwq); diff --git a/drivers/infiniband/hw/mthca/mthca_main.c b/drivers/infiniband/hw/mthca/mthca_main.c index e36a9bc52268..f3e80dec1334 100644 --- a/drivers/infiniband/hw/mthca/mthca_main.c +++ b/drivers/infiniband/hw/mthca/mthca_main.c @@ -473,11 +473,11 @@ static int mthca_init_icm(struct mthca_dev *mdev, goto err_unmap_eqp; } - mdev->cq_table.table = mthca_alloc_icm_table(mdev, init_hca->cqc_base, - dev_lim->cqc_entry_sz, - mdev->limits.num_cqs, - mdev->limits.reserved_cqs, - 0, 0); + mdev->cq_table.table = mthca_alloc_icm_table(mdev, init_hca->cqc_base, + dev_lim->cqc_entry_sz, + mdev->limits.num_cqs, + mdev->limits.reserved_cqs, + 0, 0); if (!mdev->cq_table.table) { mthca_err(mdev, "Failed to map CQ context memory, aborting.\n"); err = -ENOMEM; diff --git a/drivers/infiniband/hw/nes/nes.c b/drivers/infiniband/hw/nes/nes.c index 942ca84713c9..42b68aa999fc 100644 --- a/drivers/infiniband/hw/nes/nes.c +++ b/drivers/infiniband/hw/nes/nes.c @@ -178,11 +178,16 @@ static int nes_inetaddr_event(struct notifier_block *notifier, /* fall through */ case NETDEV_CHANGEADDR: /* Add the address to the IP table */ - if (upper_dev) - nesvnic->local_ipaddr = - ((struct in_device *)upper_dev->ip_ptr)->ifa_list->ifa_address; - else + if (upper_dev) { + struct in_device *in; + + rcu_read_lock(); + in = __in_dev_get_rcu(upper_dev); + nesvnic->local_ipaddr = in->ifa_list->ifa_address; + rcu_read_unlock(); + } else { nesvnic->local_ipaddr = ifa->ifa_address; + } nes_write_indexed(nesdev, NES_IDX_DST_IP_ADDR+(0x10*PCI_FUNC(nesdev->pcidev->devfn)), @@ -757,18 +762,18 @@ static void nes_remove(struct pci_dev *pcidev) int netdev_index = 0; unsigned long flags; - if (nesdev->netdev_count) { - netdev = nesdev->netdev[netdev_index]; - if (netdev) { - netif_stop_queue(netdev); - unregister_netdev(netdev); - nes_netdev_destroy(netdev); + if (nesdev->netdev_count) { + netdev = nesdev->netdev[netdev_index]; + if (netdev) { + netif_stop_queue(netdev); + unregister_netdev(netdev); + nes_netdev_destroy(netdev); - nesdev->netdev[netdev_index] = NULL; - nesdev->netdev_count--; - nesdev->nesadapter->netdev_count--; - } + nesdev->netdev[netdev_index] = NULL; + nesdev->netdev_count--; + nesdev->nesadapter->netdev_count--; } + } nes_notifiers_registered--; if (nes_notifiers_registered == 0) { diff --git a/drivers/infiniband/hw/nes/nes.h b/drivers/infiniband/hw/nes/nes.h index 3f9e56e8b379..00c27291dc26 100644 --- a/drivers/infiniband/hw/nes/nes.h +++ b/drivers/infiniband/hw/nes/nes.h @@ -536,7 +536,7 @@ void nes_iwarp_ce_handler(struct nes_device *, struct nes_hw_cq *); int nes_destroy_cqp(struct nes_device *); int nes_nic_cm_xmit(struct sk_buff *, struct net_device *); void nes_recheck_link_status(struct work_struct *work); -void nes_terminate_timeout(unsigned long context); +void nes_terminate_timeout(struct timer_list *t); /* nes_nic.c */ struct net_device *nes_netdev_init(struct nes_device *, void __iomem *); @@ -575,8 +575,8 @@ void nes_put_cqp_request(struct nes_device *nesdev, struct nes_cqp_request *cqp_request); void nes_post_cqp_request(struct nes_device *, struct nes_cqp_request *); int nes_arp_table(struct nes_device *, u32, u8 *, u32); -void nes_mh_fix(unsigned long); -void nes_clc(unsigned long); +void nes_mh_fix(struct timer_list *t); +void nes_clc(struct timer_list *t); void nes_dump_mem(unsigned int, void *, int); u32 nes_crc32(u32, u32, u32, u32, u8 *, u32, u32, u32); diff --git a/drivers/infiniband/hw/nes/nes_cm.c b/drivers/infiniband/hw/nes/nes_cm.c index de4025deaa4a..c56ca2a74df5 100644 --- a/drivers/infiniband/hw/nes/nes_cm.c +++ b/drivers/infiniband/hw/nes/nes_cm.c @@ -840,7 +840,7 @@ static void handle_recv_entry(struct nes_cm_node *cm_node, u32 rem_node) /** * nes_cm_timer_tick */ -static void nes_cm_timer_tick(unsigned long pass) +static void nes_cm_timer_tick(struct timer_list *unused) { unsigned long flags; unsigned long nexttimeout = jiffies + NES_LONG_TIME; @@ -1389,7 +1389,6 @@ static int nes_addr_resolve_neigh(struct nes_vnic *nesvnic, u32 dst_ip, int arpi struct rtable *rt; struct neighbour *neigh; int rc = arpindex; - struct net_device *netdev; struct nes_adapter *nesadapter = nesvnic->nesdev->nesadapter; __be32 dst_ipaddr = htonl(dst_ip); @@ -1400,11 +1399,6 @@ static int nes_addr_resolve_neigh(struct nes_vnic *nesvnic, u32 dst_ip, int arpi return rc; } - if (netif_is_bond_slave(nesvnic->netdev)) - netdev = netdev_master_upper_dev_get(nesvnic->netdev); - else - netdev = nesvnic->netdev; - neigh = dst_neigh_lookup(&rt->dst, &dst_ipaddr); rcu_read_lock(); @@ -1768,6 +1762,7 @@ static void handle_rst_pkt(struct nes_cm_node *cm_node, struct sk_buff *skb, case NES_CM_STATE_FIN_WAIT1: case NES_CM_STATE_LAST_ACK: cm_node->cm_id->rem_ref(cm_node->cm_id); + /* fall through */ case NES_CM_STATE_TIME_WAIT: cm_node->state = NES_CM_STATE_CLOSED; rem_ref_cm_node(cm_node->cm_core, cm_node); @@ -2670,8 +2665,7 @@ static struct nes_cm_core *nes_cm_alloc_core(void) return NULL; INIT_LIST_HEAD(&cm_core->connected_nodes); - init_timer(&cm_core->tcp_timer); - cm_core->tcp_timer.function = nes_cm_timer_tick; + timer_setup(&cm_core->tcp_timer, nes_cm_timer_tick, 0); cm_core->mtu = NES_CM_DEFAULT_MTU; cm_core->state = NES_CM_STATE_INITED; @@ -3074,7 +3068,6 @@ int nes_accept(struct iw_cm_id *cm_id, struct iw_cm_conn_param *conn_param) u32 crc_value; int ret; int passive_state; - struct nes_ib_device *nesibdev; struct ib_mr *ibmr = NULL; struct nes_pd *nespd; u64 tagged_offset; @@ -3157,7 +3150,6 @@ int nes_accept(struct iw_cm_id *cm_id, struct iw_cm_conn_param *conn_param) if (raddr->sin_addr.s_addr != laddr->sin_addr.s_addr) { u64temp = (unsigned long)nesqp; - nesibdev = nesvnic->nesibdev; nespd = nesqp->nespd; tagged_offset = (u64)(unsigned long)*start_buff; ibmr = nes_reg_phys_mr(&nespd->ibpd, diff --git a/drivers/infiniband/hw/nes/nes_hw.c b/drivers/infiniband/hw/nes/nes_hw.c index b0adf65e4bdb..18a7de1c3923 100644 --- a/drivers/infiniband/hw/nes/nes_hw.c +++ b/drivers/infiniband/hw/nes/nes_hw.c @@ -381,6 +381,7 @@ struct nes_adapter *nes_init_adapter(struct nes_device *nesdev, u8 hw_rev) { sizeof nesadapter->pft_mcast_map); /* populate the new nesadapter */ + nesadapter->nesdev = nesdev; nesadapter->devfn = nesdev->pcidev->devfn; nesadapter->bus_number = nesdev->pcidev->bus->number; nesadapter->ref_count = 1; @@ -598,19 +599,15 @@ struct nes_adapter *nes_init_adapter(struct nes_device *nesdev, u8 hw_rev) { } if (nesadapter->hw_rev == NE020_REV) { - init_timer(&nesadapter->mh_timer); - nesadapter->mh_timer.function = nes_mh_fix; + timer_setup(&nesadapter->mh_timer, nes_mh_fix, 0); nesadapter->mh_timer.expires = jiffies + (HZ/5); /* 1 second */ - nesadapter->mh_timer.data = (unsigned long)nesdev; add_timer(&nesadapter->mh_timer); } else { nes_write32(nesdev->regs+NES_INTF_INT_STAT, 0x0f000000); } - init_timer(&nesadapter->lc_timer); - nesadapter->lc_timer.function = nes_clc; + timer_setup(&nesadapter->lc_timer, nes_clc, 0); nesadapter->lc_timer.expires = jiffies + 3600 * HZ; /* 1 hour */ - nesadapter->lc_timer.data = (unsigned long)nesdev; add_timer(&nesadapter->lc_timer); list_add_tail(&nesadapter->list, &nes_adapter_list); @@ -1623,9 +1620,9 @@ static void nes_replenish_nic_rq(struct nes_vnic *nesvnic) /** * nes_rq_wqes_timeout */ -static void nes_rq_wqes_timeout(unsigned long parm) +static void nes_rq_wqes_timeout(struct timer_list *t) { - struct nes_vnic *nesvnic = (struct nes_vnic *)parm; + struct nes_vnic *nesvnic = from_timer(nesvnic, t, rq_wqes_timer); printk("%s: Timer fired.\n", __func__); atomic_set(&nesvnic->rx_skb_timer_running, 0); if (atomic_read(&nesvnic->rx_skbs_needed)) @@ -1849,8 +1846,7 @@ int nes_init_nic_qp(struct nes_device *nesdev, struct net_device *netdev) wqe_count -= counter; nes_write32(nesdev->regs+NES_WQE_ALLOC, (counter << 24) | nesvnic->nic.qp_id); } while (wqe_count); - setup_timer(&nesvnic->rq_wqes_timer, nes_rq_wqes_timeout, - (unsigned long)nesvnic); + timer_setup(&nesvnic->rq_wqes_timer, nes_rq_wqes_timeout, 0); nes_debug(NES_DBG_INIT, "NAPI support Enabled\n"); if (nesdev->nesadapter->et_use_adaptive_rx_coalesce) { @@ -1861,8 +1857,9 @@ int nes_init_nic_qp(struct nes_device *nesdev, struct net_device *netdev) } if ((nesdev->nesadapter->allow_unaligned_fpdus) && (nes_init_mgt_qp(nesdev, netdev, nesvnic))) { - nes_debug(NES_DBG_INIT, "%s: Out of memory for pau nic\n", netdev->name); - nes_destroy_nic_qp(nesvnic); + nes_debug(NES_DBG_INIT, "%s: Out of memory for pau nic\n", + netdev->name); + nes_destroy_nic_qp(nesvnic); return -ENOMEM; } @@ -3474,9 +3471,9 @@ static void nes_terminate_received(struct nes_device *nesdev, } /* Timeout routine in case terminate fails to complete */ -void nes_terminate_timeout(unsigned long context) +void nes_terminate_timeout(struct timer_list *t) { - struct nes_qp *nesqp = (struct nes_qp *)(unsigned long)context; + struct nes_qp *nesqp = from_timer(nesqp, t, terminate_timer); nes_terminate_done(nesqp, 1); } @@ -3631,7 +3628,7 @@ static void nes_process_iwarp_aeqe(struct nes_device *nesdev, aeq_info |= NES_AEQE_AEID_RDMAP_ROE_UNEXPECTED_OPCODE; aeqe->aeqe_words[NES_AEQE_MISC_IDX] = cpu_to_le32(aeq_info); } - + /* fall through */ case NES_AEQE_AEID_RDMAP_ROE_BAD_LLP_CLOSE: case NES_AEQE_AEID_LLP_TOO_MANY_RETRIES: case NES_AEQE_AEID_DDP_UBE_INVALID_MSN_NO_BUFFER_AVAILABLE: diff --git a/drivers/infiniband/hw/nes/nes_hw.h b/drivers/infiniband/hw/nes/nes_hw.h index 1b66ef1e9937..3c56470816a8 100644 --- a/drivers/infiniband/hw/nes/nes_hw.h +++ b/drivers/infiniband/hw/nes/nes_hw.h @@ -1164,6 +1164,7 @@ struct nes_adapter { u8 log_port; /* PCI information */ + struct nes_device *nesdev; unsigned int devfn; unsigned char bus_number; unsigned char OneG_Mode; diff --git a/drivers/infiniband/hw/nes/nes_mgt.c b/drivers/infiniband/hw/nes/nes_mgt.c index 77226cf4ea02..21e0ebd39a05 100644 --- a/drivers/infiniband/hw/nes/nes_mgt.c +++ b/drivers/infiniband/hw/nes/nes_mgt.c @@ -122,9 +122,10 @@ static void nes_replenish_mgt_rq(struct nes_vnic_mgt *mgtvnic) /** * nes_mgt_rq_wqes_timeout */ -static void nes_mgt_rq_wqes_timeout(unsigned long parm) +static void nes_mgt_rq_wqes_timeout(struct timer_list *t) { - struct nes_vnic_mgt *mgtvnic = (struct nes_vnic_mgt *)parm; + struct nes_vnic_mgt *mgtvnic = from_timer(mgtvnic, t, + rq_wqes_timer); atomic_set(&mgtvnic->rx_skb_timer_running, 0); if (atomic_read(&mgtvnic->rx_skbs_needed)) @@ -1040,8 +1041,8 @@ int nes_init_mgt_qp(struct nes_device *nesdev, struct net_device *netdev, struct mgtvnic->mgt.rx_skb[counter] = skb; } - setup_timer(&mgtvnic->rq_wqes_timer, nes_mgt_rq_wqes_timeout, - (unsigned long)mgtvnic); + timer_setup(&mgtvnic->rq_wqes_timer, nes_mgt_rq_wqes_timeout, + 0); wqe_count = NES_MGT_WQ_COUNT - 1; mgtvnic->mgt.rq_head = wqe_count; diff --git a/drivers/infiniband/hw/nes/nes_nic.c b/drivers/infiniband/hw/nes/nes_nic.c index 5921ea3d50ae..0a75164cedea 100644 --- a/drivers/infiniband/hw/nes/nes_nic.c +++ b/drivers/infiniband/hw/nes/nes_nic.c @@ -926,11 +926,10 @@ static void nes_netdev_set_multicast_list(struct net_device *netdev) nesadapter->pft_mcast_map[mc_index] != nesvnic->nic_index && mc_index < max_pft_entries_avaiable) { - nes_debug(NES_DBG_NIC_RX, - "mc_index=%d skipping nic_index=%d, " - "used for=%d \n", mc_index, - nesvnic->nic_index, - nesadapter->pft_mcast_map[mc_index]); + nes_debug(NES_DBG_NIC_RX, + "mc_index=%d skipping nic_index=%d, used for=%d\n", + mc_index, nesvnic->nic_index, + nesadapter->pft_mcast_map[mc_index]); mc_index++; } if (mc_index >= max_pft_entries_avaiable) @@ -1746,8 +1745,7 @@ struct net_device *nes_netdev_init(struct nes_device *nesdev, nesvnic->rdma_enabled = 0; } nesvnic->nic_cq.cq_number = nesvnic->nic.qp_id; - init_timer(&nesvnic->event_timer); - nesvnic->event_timer.function = NULL; + timer_setup(&nesvnic->event_timer, NULL, 0); spin_lock_init(&nesvnic->tx_lock); spin_lock_init(&nesvnic->port_ibevent_lock); nesdev->netdev[nesdev->netdev_count] = netdev; diff --git a/drivers/infiniband/hw/nes/nes_utils.c b/drivers/infiniband/hw/nes/nes_utils.c index 37331e2fdc5f..21b4a8373acf 100644 --- a/drivers/infiniband/hw/nes/nes_utils.c +++ b/drivers/infiniband/hw/nes/nes_utils.c @@ -740,11 +740,11 @@ int nes_arp_table(struct nes_device *nesdev, u32 ip_addr, u8 *mac_addr, u32 acti /** * nes_mh_fix */ -void nes_mh_fix(unsigned long parm) +void nes_mh_fix(struct timer_list *t) { + struct nes_adapter *nesadapter = from_timer(nesadapter, t, mh_timer); + struct nes_device *nesdev = nesadapter->nesdev; unsigned long flags; - struct nes_device *nesdev = (struct nes_device *)parm; - struct nes_adapter *nesadapter = nesdev->nesadapter; struct nes_vnic *nesvnic; u32 used_chunks_tx; u32 temp_used_chunks_tx; @@ -753,7 +753,6 @@ void nes_mh_fix(unsigned long parm) u32 mac_tx_frames_low; u32 mac_tx_frames_high; u32 mac_tx_pauses; - u32 serdes_status; u32 reset_value; u32 tx_control; u32 tx_config; @@ -846,7 +845,7 @@ void nes_mh_fix(unsigned long parm) } nes_write_indexed(nesdev, NES_IDX_ETH_SERDES_COMMON_CONTROL0, 0x00000008); - serdes_status = nes_read_indexed(nesdev, NES_IDX_ETH_SERDES_COMMON_STATUS0); + nes_read_indexed(nesdev, NES_IDX_ETH_SERDES_COMMON_STATUS0); nes_write_indexed(nesdev, NES_IDX_ETH_SERDES_TX_EMP0, 0x000bdef7); nes_write_indexed(nesdev, NES_IDX_ETH_SERDES_TX_DRIVE0, 0x9ce73000); @@ -859,7 +858,7 @@ void nes_mh_fix(unsigned long parm) } else { nes_write_indexed(nesdev, NES_IDX_ETH_SERDES_RX_EQ_CONTROL0, 0xf0042222); } - serdes_status = nes_read_indexed(nesdev, NES_IDX_ETH_SERDES_RX_EQ_STATUS0); + nes_read_indexed(nesdev, NES_IDX_ETH_SERDES_RX_EQ_STATUS0); nes_write_indexed(nesdev, NES_IDX_ETH_SERDES_CDR_CONTROL0, 0x000000ff); nes_write_indexed(nesdev, NES_IDX_MAC_TX_CONTROL, tx_control); @@ -881,17 +880,16 @@ no_mh_work: /** * nes_clc */ -void nes_clc(unsigned long parm) +void nes_clc(struct timer_list *t) { + struct nes_adapter *nesadapter = from_timer(nesadapter, t, lc_timer); unsigned long flags; - struct nes_device *nesdev = (struct nes_device *)parm; - struct nes_adapter *nesadapter = nesdev->nesadapter; spin_lock_irqsave(&nesadapter->phy_lock, flags); - nesadapter->link_interrupt_count[0] = 0; - nesadapter->link_interrupt_count[1] = 0; - nesadapter->link_interrupt_count[2] = 0; - nesadapter->link_interrupt_count[3] = 0; + nesadapter->link_interrupt_count[0] = 0; + nesadapter->link_interrupt_count[1] = 0; + nesadapter->link_interrupt_count[2] = 0; + nesadapter->link_interrupt_count[3] = 0; spin_unlock_irqrestore(&nesadapter->phy_lock, flags); nesadapter->lc_timer.expires = jiffies + 3600 * HZ; /* 1 hour */ diff --git a/drivers/infiniband/hw/nes/nes_verbs.c b/drivers/infiniband/hw/nes/nes_verbs.c index 442b9bdc0f03..db46b7b53fb4 100644 --- a/drivers/infiniband/hw/nes/nes_verbs.c +++ b/drivers/infiniband/hw/nes/nes_verbs.c @@ -1304,8 +1304,7 @@ static struct ib_qp *nes_create_qp(struct ib_pd *ibpd, init_completion(&nesqp->rq_drained); nesqp->sig_all = (init_attr->sq_sig_type == IB_SIGNAL_ALL_WR); - setup_timer(&nesqp->terminate_timer, nes_terminate_timeout, - (unsigned long)nesqp); + timer_setup(&nesqp->terminate_timer, nes_terminate_timeout, 0); /* update the QP table */ nesdev->nesadapter->qp_table[nesqp->hwqp.qp_id-NES_FIRST_QPN] = nesqp; @@ -2865,11 +2864,11 @@ int nes_modify_qp(struct ib_qp *ibqp, struct ib_qp_attr *attr, next_iwarp_state = NES_CQP_QP_IWARP_STATE_ERROR; /* next_iwarp_state = (NES_CQP_QP_IWARP_STATE_TERMINATE | 0x02000000); */ - if (nesqp->hte_added) { - nes_debug(NES_DBG_MOD_QP, "set CQP_QP_DEL_HTE\n"); - next_iwarp_state |= NES_CQP_QP_DEL_HTE; - nesqp->hte_added = 0; - } + if (nesqp->hte_added) { + nes_debug(NES_DBG_MOD_QP, "set CQP_QP_DEL_HTE\n"); + next_iwarp_state |= NES_CQP_QP_DEL_HTE; + nesqp->hte_added = 0; + } if ((nesqp->hw_tcp_state > NES_AEQE_TCP_STATE_CLOSED) && (nesdev->iw_status) && (nesqp->hw_tcp_state != NES_AEQE_TCP_STATE_TIME_WAIT)) { @@ -3560,7 +3559,7 @@ static int nes_poll_cq(struct ib_cq *ibcq, int num_entries, struct ib_wc *entry) entry->byte_len = le32_to_cpu(cqe.cqe_words[NES_CQE_PAYLOAD_LENGTH_IDX]); wrid = ((u64)(le32_to_cpu(nesqp->hwqp.rq_vbase[wqe_index].wqe_words[NES_IWARP_RQ_WQE_COMP_SCRATCH_LOW_IDX]))) | ((u64)(le32_to_cpu(nesqp->hwqp.rq_vbase[wqe_index].wqe_words[NES_IWARP_RQ_WQE_COMP_SCRATCH_HIGH_IDX]))<<32); - entry->opcode = IB_WC_RECV; + entry->opcode = IB_WC_RECV; nesqp->hwqp.rq_tail = (wqe_index+1)&(nesqp->hwqp.rq_size - 1); if ((entry->status != IB_WC_SUCCESS) && (nesqp->hwqp.rq_tail != nesqp->hwqp.rq_head)) { @@ -3788,9 +3787,9 @@ struct nes_ib_device *nes_init_ofa_device(struct net_device *netdev) /** * nes_handle_delayed_event */ -static void nes_handle_delayed_event(unsigned long data) +static void nes_handle_delayed_event(struct timer_list *t) { - struct nes_vnic *nesvnic = (void *) data; + struct nes_vnic *nesvnic = from_timer(nesvnic, t, event_timer); if (nesvnic->delayed_event != nesvnic->last_dispatched_event) { struct ib_event event; @@ -3820,8 +3819,7 @@ void nes_port_ibevent(struct nes_vnic *nesvnic) if (!nesvnic->event_timer.function) { ib_dispatch_event(&event); nesvnic->last_dispatched_event = event.event; - nesvnic->event_timer.function = nes_handle_delayed_event; - nesvnic->event_timer.data = (unsigned long) nesvnic; + nesvnic->event_timer.function = (TIMER_FUNC_TYPE)nes_handle_delayed_event; nesvnic->event_timer.expires = jiffies + NES_EVENT_DELAY; add_timer(&nesvnic->event_timer); } else { diff --git a/drivers/infiniband/hw/ocrdma/ocrdma_ah.c b/drivers/infiniband/hw/ocrdma/ocrdma_ah.c index d0249e463338..dec650930ca6 100644 --- a/drivers/infiniband/hw/ocrdma/ocrdma_ah.c +++ b/drivers/infiniband/hw/ocrdma/ocrdma_ah.c @@ -201,21 +201,6 @@ struct ib_ah *ocrdma_create_ah(struct ib_pd *ibpd, struct rdma_ah_attr *attr, /* Get network header type for this GID */ ah->hdr_type = ib_gid_to_network_type(sgid_attr.gid_type, &sgid); - if ((pd->uctx) && - (!rdma_is_multicast_addr((struct in6_addr *)grh->dgid.raw)) && - (!rdma_link_local_addr((struct in6_addr *)grh->dgid.raw))) { - status = rdma_addr_find_l2_eth_by_grh(&sgid, &grh->dgid, - attr->roce.dmac, - &vlan_tag, - &sgid_attr.ndev->ifindex, - NULL); - if (status) { - pr_err("%s(): Failed to resolve dmac from gid." - "status = %d\n", __func__, status); - goto av_conf_err; - } - } - status = set_av_attr(dev, ah, attr, &sgid, pd->id, &isvlan, vlan_tag); if (status) goto av_conf_err; diff --git a/drivers/infiniband/hw/ocrdma/ocrdma_hw.c b/drivers/infiniband/hw/ocrdma/ocrdma_hw.c index 65b166cc7437..f8c14c7baedb 100644 --- a/drivers/infiniband/hw/ocrdma/ocrdma_hw.c +++ b/drivers/infiniband/hw/ocrdma/ocrdma_hw.c @@ -1093,7 +1093,7 @@ static int ocrdma_mbx_cmd(struct ocrdma_dev *dev, struct ocrdma_mqe *mqe) rsp = &mqe->u.rsp; if (cqe_status || ext_status) { - pr_err("%s() cqe_status=0x%x, ext_status=0x%x,", + pr_err("%s() cqe_status=0x%x, ext_status=0x%x,\n", __func__, cqe_status, ext_status); if (rsp) { /* This is for embedded cmds. */ @@ -3186,8 +3186,8 @@ void ocrdma_eqd_set_task(struct work_struct *work) { struct ocrdma_dev *dev = container_of(work, struct ocrdma_dev, eqd_work.work); - struct ocrdma_eq *eq = 0; - int i, num = 0, status = -EINVAL; + struct ocrdma_eq *eq = NULL; + int i, num = 0; u64 eq_intr; for (i = 0; i < dev->eq_cnt; i++) { @@ -3209,7 +3209,7 @@ void ocrdma_eqd_set_task(struct work_struct *work) } if (num) - status = ocrdma_modify_eqd(dev, &dev->eq_tbl[0], num); + ocrdma_modify_eqd(dev, &dev->eq_tbl[0], num); schedule_delayed_work(&dev->eqd_work, msecs_to_jiffies(1000)); } diff --git a/drivers/infiniband/hw/ocrdma/ocrdma_stats.c b/drivers/infiniband/hw/ocrdma/ocrdma_stats.c index 66056f9a9700..e528d7acb7f6 100644 --- a/drivers/infiniband/hw/ocrdma/ocrdma_stats.c +++ b/drivers/infiniband/hw/ocrdma/ocrdma_stats.c @@ -658,7 +658,7 @@ static ssize_t ocrdma_dbgfs_ops_write(struct file *filp, if (reset) { status = ocrdma_mbx_rdma_stats(dev, true); if (status) { - pr_err("Failed to reset stats = %d", status); + pr_err("Failed to reset stats = %d\n", status); goto err; } } diff --git a/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c b/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c index 27d5e8d9f08d..7866fd8051f6 100644 --- a/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c +++ b/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c @@ -66,9 +66,7 @@ int ocrdma_query_gid(struct ib_device *ibdev, u8 port, int index, union ib_gid *sgid) { int ret; - struct ocrdma_dev *dev; - dev = get_ocrdma_dev(ibdev); memset(sgid, 0, sizeof(*sgid)); if (index >= OCRDMA_MAX_SGID) return -EINVAL; @@ -2247,6 +2245,7 @@ int ocrdma_post_send(struct ib_qp *ibqp, struct ib_send_wr *wr, case IB_WR_SEND_WITH_IMM: hdr->cw |= (OCRDMA_FLAG_IMM << OCRDMA_WQE_FLAGS_SHIFT); hdr->immdt = ntohl(wr->ex.imm_data); + /* fall through */ case IB_WR_SEND: hdr->cw |= (OCRDMA_SEND << OCRDMA_WQE_OPCODE_SHIFT); ocrdma_build_send(qp, hdr, wr); @@ -2260,6 +2259,7 @@ int ocrdma_post_send(struct ib_qp *ibqp, struct ib_send_wr *wr, case IB_WR_RDMA_WRITE_WITH_IMM: hdr->cw |= (OCRDMA_FLAG_IMM << OCRDMA_WQE_FLAGS_SHIFT); hdr->immdt = ntohl(wr->ex.imm_data); + /* fall through */ case IB_WR_RDMA_WRITE: hdr->cw |= (OCRDMA_WRITE << OCRDMA_WQE_OPCODE_SHIFT); status = ocrdma_build_write(qp, hdr, wr); diff --git a/drivers/infiniband/hw/qedr/Kconfig b/drivers/infiniband/hw/qedr/Kconfig index 6c9f3923e838..3feec8dddf41 100644 --- a/drivers/infiniband/hw/qedr/Kconfig +++ b/drivers/infiniband/hw/qedr/Kconfig @@ -1,6 +1,7 @@ config INFINIBAND_QEDR tristate "QLogic RoCE driver" depends on 64BIT && QEDE + depends on PCI select QED_LL2 select QED_RDMA ---help--- diff --git a/drivers/infiniband/hw/qedr/Makefile b/drivers/infiniband/hw/qedr/Makefile index ba7067c77f2f..1c0bc4f78550 100644 --- a/drivers/infiniband/hw/qedr/Makefile +++ b/drivers/infiniband/hw/qedr/Makefile @@ -1,3 +1,3 @@ obj-$(CONFIG_INFINIBAND_QEDR) := qedr.o -qedr-y := main.o verbs.o qedr_cm.o +qedr-y := main.o verbs.o qedr_roce_cm.o qedr_iw_cm.o diff --git a/drivers/infiniband/hw/qedr/main.c b/drivers/infiniband/hw/qedr/main.c index 97d033f51dc9..50812b33291b 100644 --- a/drivers/infiniband/hw/qedr/main.c +++ b/drivers/infiniband/hw/qedr/main.c @@ -33,16 +33,20 @@ #include <rdma/ib_verbs.h> #include <rdma/ib_addr.h> #include <rdma/ib_user_verbs.h> +#include <rdma/iw_cm.h> +#include <rdma/ib_mad.h> #include <linux/netdevice.h> #include <linux/iommu.h> #include <linux/pci.h> #include <net/addrconf.h> +#include <linux/idr.h> #include <linux/qed/qed_chain.h> #include <linux/qed/qed_if.h> #include "qedr.h" #include "verbs.h" #include <rdma/qedr-abi.h> +#include "qedr_iw_cm.h" MODULE_DESCRIPTION("QLogic 40G/100G ROCE Driver"); MODULE_AUTHOR("QLogic Corporation"); @@ -50,8 +54,8 @@ MODULE_LICENSE("Dual BSD/GPL"); #define QEDR_WQ_MULTIPLIER_DFT (3) -void qedr_ib_dispatch_event(struct qedr_dev *dev, u8 port_num, - enum ib_event_type type) +static void qedr_ib_dispatch_event(struct qedr_dev *dev, u8 port_num, + enum ib_event_type type) { struct ib_event ibev; @@ -92,8 +96,84 @@ static struct net_device *qedr_get_netdev(struct ib_device *dev, u8 port_num) return qdev->ndev; } +static int qedr_roce_port_immutable(struct ib_device *ibdev, u8 port_num, + struct ib_port_immutable *immutable) +{ + struct ib_port_attr attr; + int err; + + err = qedr_query_port(ibdev, port_num, &attr); + if (err) + return err; + + immutable->pkey_tbl_len = attr.pkey_tbl_len; + immutable->gid_tbl_len = attr.gid_tbl_len; + immutable->core_cap_flags = RDMA_CORE_PORT_IBA_ROCE | + RDMA_CORE_PORT_IBA_ROCE_UDP_ENCAP; + immutable->max_mad_size = IB_MGMT_MAD_SIZE; + + return 0; +} + +static int qedr_iw_port_immutable(struct ib_device *ibdev, u8 port_num, + struct ib_port_immutable *immutable) +{ + struct ib_port_attr attr; + int err; + + err = qedr_query_port(ibdev, port_num, &attr); + if (err) + return err; + + immutable->pkey_tbl_len = 1; + immutable->gid_tbl_len = 1; + immutable->core_cap_flags = RDMA_CORE_PORT_IWARP; + immutable->max_mad_size = 0; + + return 0; +} + +static int qedr_iw_register_device(struct qedr_dev *dev) +{ + dev->ibdev.node_type = RDMA_NODE_RNIC; + dev->ibdev.query_gid = qedr_iw_query_gid; + + dev->ibdev.get_port_immutable = qedr_iw_port_immutable; + + dev->ibdev.iwcm = kzalloc(sizeof(*dev->ibdev.iwcm), GFP_KERNEL); + if (!dev->ibdev.iwcm) + return -ENOMEM; + + dev->ibdev.iwcm->connect = qedr_iw_connect; + dev->ibdev.iwcm->accept = qedr_iw_accept; + dev->ibdev.iwcm->reject = qedr_iw_reject; + dev->ibdev.iwcm->create_listen = qedr_iw_create_listen; + dev->ibdev.iwcm->destroy_listen = qedr_iw_destroy_listen; + dev->ibdev.iwcm->add_ref = qedr_iw_qp_add_ref; + dev->ibdev.iwcm->rem_ref = qedr_iw_qp_rem_ref; + dev->ibdev.iwcm->get_qp = qedr_iw_get_qp; + + memcpy(dev->ibdev.iwcm->ifname, + dev->ndev->name, sizeof(dev->ibdev.iwcm->ifname)); + + return 0; +} + +static void qedr_roce_register_device(struct qedr_dev *dev) +{ + dev->ibdev.node_type = RDMA_NODE_IB_CA; + dev->ibdev.query_gid = qedr_query_gid; + + dev->ibdev.add_gid = qedr_add_gid; + dev->ibdev.del_gid = qedr_del_gid; + + dev->ibdev.get_port_immutable = qedr_roce_port_immutable; +} + static int qedr_register_device(struct qedr_dev *dev) { + int rc; + strlcpy(dev->ibdev.name, "qedr%d", IB_DEVICE_NAME_MAX); dev->ibdev.node_guid = dev->attr.node_guid; @@ -121,18 +201,21 @@ static int qedr_register_device(struct qedr_dev *dev) QEDR_UVERBS(POST_SEND) | QEDR_UVERBS(POST_RECV); + if (IS_IWARP(dev)) { + rc = qedr_iw_register_device(dev); + if (rc) + return rc; + } else { + qedr_roce_register_device(dev); + } + dev->ibdev.phys_port_cnt = 1; dev->ibdev.num_comp_vectors = dev->num_cnq; - dev->ibdev.node_type = RDMA_NODE_IB_CA; dev->ibdev.query_device = qedr_query_device; dev->ibdev.query_port = qedr_query_port; dev->ibdev.modify_port = qedr_modify_port; - dev->ibdev.query_gid = qedr_query_gid; - dev->ibdev.add_gid = qedr_add_gid; - dev->ibdev.del_gid = qedr_del_gid; - dev->ibdev.alloc_ucontext = qedr_alloc_ucontext; dev->ibdev.dealloc_ucontext = qedr_dealloc_ucontext; dev->ibdev.mmap = qedr_mmap; @@ -166,7 +249,7 @@ static int qedr_register_device(struct qedr_dev *dev) dev->ibdev.post_recv = qedr_post_recv; dev->ibdev.process_mad = qedr_process_mad; - dev->ibdev.get_port_immutable = qedr_port_immutable; + dev->ibdev.get_netdev = qedr_get_netdev; dev->ibdev.dev.parent = &dev->pdev->dev; @@ -217,6 +300,9 @@ static void qedr_free_resources(struct qedr_dev *dev) { int i; + if (IS_IWARP(dev)) + destroy_workqueue(dev->iwarp_wq); + for (i = 0; i < dev->num_cnq; i++) { qedr_free_mem_sb(dev, &dev->sb_array[i], dev->sb_start + i); dev->ops->common->chain_free(dev->cdev, &dev->cnq_array[i].pbl); @@ -241,6 +327,12 @@ static int qedr_alloc_resources(struct qedr_dev *dev) spin_lock_init(&dev->sgid_lock); + if (IS_IWARP(dev)) { + spin_lock_init(&dev->idr_lock); + idr_init(&dev->qpidr); + dev->iwarp_wq = create_singlethread_workqueue("qedr_iwarpq"); + } + /* Allocate Status blocks for CNQ */ dev->sb_array = kcalloc(dev->num_cnq, sizeof(*dev->sb_array), GFP_KERNEL); @@ -597,12 +689,12 @@ static int qedr_set_device_attr(struct qedr_dev *dev) return 0; } -void qedr_unaffiliated_event(void *context, u8 event_code) +static void qedr_unaffiliated_event(void *context, u8 event_code) { pr_err("unaffiliated event not implemented yet\n"); } -void qedr_affiliated_event(void *context, u8 e_code, void *fw_handle) +static void qedr_affiliated_event(void *context, u8 e_code, void *fw_handle) { #define EVENT_TYPE_NOT_DEFINED 0 #define EVENT_TYPE_CQ 1 @@ -716,6 +808,7 @@ static int qedr_init_hw(struct qedr_dev *dev) in_params->events = &events; in_params->cq_mode = QED_RDMA_CQ_MODE_32_BITS; in_params->max_mtu = dev->ndev->mtu; + dev->iwarp_max_mtu = dev->ndev->mtu; ether_addr_copy(&in_params->mac_addr[0], dev->ndev->dev_addr); rc = dev->ops->rdma_init(dev->cdev, in_params); @@ -726,7 +819,7 @@ static int qedr_init_hw(struct qedr_dev *dev) if (rc) goto out; - dev->db_addr = (void *)(uintptr_t)out_params.dpi_addr; + dev->db_addr = (void __iomem *)(uintptr_t)out_params.dpi_addr; dev->db_phys_addr = out_params.dpi_phys_addr; dev->db_size = out_params.dpi_size; dev->dpi = out_params.dpi; @@ -740,7 +833,7 @@ out: return rc; } -void qedr_stop_hw(struct qedr_dev *dev) +static void qedr_stop_hw(struct qedr_dev *dev) { dev->ops->rdma_remove_user(dev->rdma_ctx, dev->dpi); dev->ops->rdma_stop(dev->rdma_ctx); @@ -777,6 +870,7 @@ static struct qedr_dev *qedr_add(struct qed_dev *cdev, struct pci_dev *pdev, goto init_err; dev->user_dpm_enabled = dev_info.user_dpm_enabled; + dev->rdma_type = dev_info.rdma_type; dev->num_hwfns = dev_info.common.num_hwfns; dev->rdma_ctx = dev->ops->rdma_get_rdma_ctx(cdev); diff --git a/drivers/infiniband/hw/qedr/qedr.h b/drivers/infiniband/hw/qedr/qedr.h index 254083b524bd..86d4511e0d75 100644 --- a/drivers/infiniband/hw/qedr/qedr.h +++ b/drivers/infiniband/hw/qedr/qedr.h @@ -33,6 +33,7 @@ #define __QEDR_H__ #include <linux/pci.h> +#include <linux/idr.h> #include <rdma/ib_addr.h> #include <linux/qed/qed_if.h> #include <linux/qed/qed_chain.h> @@ -43,6 +44,8 @@ #define QEDR_NODE_DESC "QLogic 579xx RoCE HCA" #define DP_NAME(dev) ((dev)->ibdev.name) +#define IS_IWARP(_dev) ((_dev)->rdma_type == QED_RDMA_TYPE_IWARP) +#define IS_ROCE(_dev) ((_dev)->rdma_type == QED_RDMA_TYPE_ROCE) #define DP_DEBUG(dev, module, fmt, ...) \ pr_debug("(%s) " module ": " fmt, \ @@ -56,6 +59,7 @@ #define QEDR_MSG_SQ " SQ" #define QEDR_MSG_QP " QP" #define QEDR_MSG_GSI " GSI" +#define QEDR_MSG_IWARP " IW" #define QEDR_CQ_MAGIC_NUMBER (0x11223344) @@ -160,6 +164,11 @@ struct qedr_dev { struct qedr_cq *gsi_sqcq; struct qedr_cq *gsi_rqcq; struct qedr_qp *gsi_qp; + enum qed_rdma_type rdma_type; + spinlock_t idr_lock; /* Protect qpidr data-structure */ + struct idr qpidr; + struct workqueue_struct *iwarp_wq; + u16 iwarp_max_mtu; unsigned long enet_state; @@ -317,6 +326,9 @@ struct qedr_qp_hwq_info { /* DB */ void __iomem *db; union db_prod32 db_data; + + void __iomem *iwarp_db2; + union db_prod32 iwarp_db2_data; }; #define QEDR_INC_SW_IDX(p_info, index) \ @@ -337,7 +349,7 @@ enum qedr_qp_err_bitmap { struct qedr_qp { struct ib_qp ibqp; /* must be first */ struct qedr_dev *dev; - + struct qedr_iw_ep *ep; struct qedr_qp_hwq_info sq; struct qedr_qp_hwq_info rq; @@ -394,6 +406,8 @@ struct qedr_qp { /* Relevant to qps created from user space only (applications) */ struct qedr_userq usq; struct qedr_userq urq; + atomic_t refcnt; + bool destroyed; }; struct qedr_ah { @@ -474,6 +488,21 @@ static inline int qedr_get_dmac(struct qedr_dev *dev, return 0; } +struct qedr_iw_listener { + struct qedr_dev *dev; + struct iw_cm_id *cm_id; + int backlog; + void *qed_handle; +}; + +struct qedr_iw_ep { + struct qedr_dev *dev; + struct iw_cm_id *cm_id; + struct qedr_qp *qp; + void *qed_context; + u8 during_connect; +}; + static inline struct qedr_ucontext *get_qedr_ucontext(struct ib_ucontext *ibucontext) { diff --git a/drivers/infiniband/hw/qedr/qedr_hsi_rdma.h b/drivers/infiniband/hw/qedr/qedr_hsi_rdma.h index 5c98d2055cad..b7587f10e7de 100644 --- a/drivers/infiniband/hw/qedr/qedr_hsi_rdma.h +++ b/drivers/infiniband/hw/qedr/qedr_hsi_rdma.h @@ -655,8 +655,10 @@ struct rdma_sq_rdma_wqe_1st { #define RDMA_SQ_RDMA_WQE_1ST_INLINE_FLG_SHIFT 4 #define RDMA_SQ_RDMA_WQE_1ST_DIF_ON_HOST_FLG_MASK 0x1 #define RDMA_SQ_RDMA_WQE_1ST_DIF_ON_HOST_FLG_SHIFT 5 -#define RDMA_SQ_RDMA_WQE_1ST_RESERVED0_MASK 0x3 -#define RDMA_SQ_RDMA_WQE_1ST_RESERVED0_SHIFT 6 +#define RDMA_SQ_RDMA_WQE_1ST_READ_INV_FLG_MASK 0x1 +#define RDMA_SQ_RDMA_WQE_1ST_READ_INV_FLG_SHIFT 6 +#define RDMA_SQ_RDMA_WQE_1ST_RESERVED0_MASK 0x1 +#define RDMA_SQ_RDMA_WQE_1ST_RESERVED0_SHIFT 7 u8 wqe_size; u8 prev_wqe_size; }; diff --git a/drivers/infiniband/hw/qedr/qedr_iw_cm.c b/drivers/infiniband/hw/qedr/qedr_iw_cm.c new file mode 100644 index 000000000000..478b7317b80a --- /dev/null +++ b/drivers/infiniband/hw/qedr/qedr_iw_cm.c @@ -0,0 +1,749 @@ +/* QLogic qedr NIC Driver + * Copyright (c) 2015-2017 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. + */ +#include <net/ip.h> +#include <net/ipv6.h> +#include <net/udp.h> +#include <net/addrconf.h> +#include <net/route.h> +#include <net/ip6_route.h> +#include <net/flow.h> +#include "qedr.h" +#include "qedr_iw_cm.h" + +static inline void +qedr_fill_sockaddr4(const struct qed_iwarp_cm_info *cm_info, + struct iw_cm_event *event) +{ + struct sockaddr_in *laddr = (struct sockaddr_in *)&event->local_addr; + struct sockaddr_in *raddr = (struct sockaddr_in *)&event->remote_addr; + + laddr->sin_family = AF_INET; + raddr->sin_family = AF_INET; + + laddr->sin_port = htons(cm_info->local_port); + raddr->sin_port = htons(cm_info->remote_port); + + laddr->sin_addr.s_addr = htonl(cm_info->local_ip[0]); + raddr->sin_addr.s_addr = htonl(cm_info->remote_ip[0]); +} + +static inline void +qedr_fill_sockaddr6(const struct qed_iwarp_cm_info *cm_info, + struct iw_cm_event *event) +{ + struct sockaddr_in6 *laddr6 = (struct sockaddr_in6 *)&event->local_addr; + struct sockaddr_in6 *raddr6 = + (struct sockaddr_in6 *)&event->remote_addr; + int i; + + laddr6->sin6_family = AF_INET6; + raddr6->sin6_family = AF_INET6; + + laddr6->sin6_port = htons(cm_info->local_port); + raddr6->sin6_port = htons(cm_info->remote_port); + + for (i = 0; i < 4; i++) { + laddr6->sin6_addr.in6_u.u6_addr32[i] = + htonl(cm_info->local_ip[i]); + raddr6->sin6_addr.in6_u.u6_addr32[i] = + htonl(cm_info->remote_ip[i]); + } +} + +static void +qedr_iw_mpa_request(void *context, struct qed_iwarp_cm_event_params *params) +{ + struct qedr_iw_listener *listener = (struct qedr_iw_listener *)context; + struct qedr_dev *dev = listener->dev; + struct iw_cm_event event; + struct qedr_iw_ep *ep; + + ep = kzalloc(sizeof(*ep), GFP_ATOMIC); + if (!ep) + return; + + ep->dev = dev; + ep->qed_context = params->ep_context; + + memset(&event, 0, sizeof(event)); + event.event = IW_CM_EVENT_CONNECT_REQUEST; + event.status = params->status; + + if (!IS_ENABLED(CONFIG_IPV6) || + params->cm_info->ip_version == QED_TCP_IPV4) + qedr_fill_sockaddr4(params->cm_info, &event); + else + qedr_fill_sockaddr6(params->cm_info, &event); + + event.provider_data = (void *)ep; + event.private_data = (void *)params->cm_info->private_data; + event.private_data_len = (u8)params->cm_info->private_data_len; + event.ord = params->cm_info->ord; + event.ird = params->cm_info->ird; + + listener->cm_id->event_handler(listener->cm_id, &event); +} + +static void +qedr_iw_issue_event(void *context, + struct qed_iwarp_cm_event_params *params, + enum iw_cm_event_type event_type) +{ + struct qedr_iw_ep *ep = (struct qedr_iw_ep *)context; + struct iw_cm_event event; + + memset(&event, 0, sizeof(event)); + event.status = params->status; + event.event = event_type; + + if (params->cm_info) { + event.ird = params->cm_info->ird; + event.ord = params->cm_info->ord; + event.private_data_len = params->cm_info->private_data_len; + event.private_data = (void *)params->cm_info->private_data; + } + + if (ep->cm_id) + ep->cm_id->event_handler(ep->cm_id, &event); +} + +static void +qedr_iw_close_event(void *context, struct qed_iwarp_cm_event_params *params) +{ + struct qedr_iw_ep *ep = (struct qedr_iw_ep *)context; + + if (ep->cm_id) { + qedr_iw_issue_event(context, params, IW_CM_EVENT_CLOSE); + + ep->cm_id->rem_ref(ep->cm_id); + ep->cm_id = NULL; + } +} + +static void +qedr_iw_qp_event(void *context, + struct qed_iwarp_cm_event_params *params, + enum ib_event_type ib_event, char *str) +{ + struct qedr_iw_ep *ep = (struct qedr_iw_ep *)context; + struct qedr_dev *dev = ep->dev; + struct ib_qp *ibqp = &ep->qp->ibqp; + struct ib_event event; + + DP_NOTICE(dev, "QP error received: %s\n", str); + + if (ibqp->event_handler) { + event.event = ib_event; + event.device = ibqp->device; + event.element.qp = ibqp; + ibqp->event_handler(&event, ibqp->qp_context); + } +} + +struct qedr_discon_work { + struct work_struct work; + struct qedr_iw_ep *ep; + enum qed_iwarp_event_type event; + int status; +}; + +static void qedr_iw_disconnect_worker(struct work_struct *work) +{ + struct qedr_discon_work *dwork = + container_of(work, struct qedr_discon_work, work); + struct qed_rdma_modify_qp_in_params qp_params = { 0 }; + struct qedr_iw_ep *ep = dwork->ep; + struct qedr_dev *dev = ep->dev; + struct qedr_qp *qp = ep->qp; + struct iw_cm_event event; + + if (qp->destroyed) { + kfree(dwork); + qedr_iw_qp_rem_ref(&qp->ibqp); + return; + } + + memset(&event, 0, sizeof(event)); + event.status = dwork->status; + event.event = IW_CM_EVENT_DISCONNECT; + + /* Success means graceful disconnect was requested. modifying + * to SQD is translated to graceful disconnect. O/w reset is sent + */ + if (dwork->status) + qp_params.new_state = QED_ROCE_QP_STATE_ERR; + else + qp_params.new_state = QED_ROCE_QP_STATE_SQD; + + kfree(dwork); + + if (ep->cm_id) + ep->cm_id->event_handler(ep->cm_id, &event); + + SET_FIELD(qp_params.modify_flags, + QED_RDMA_MODIFY_QP_VALID_NEW_STATE, 1); + + dev->ops->rdma_modify_qp(dev->rdma_ctx, qp->qed_qp, &qp_params); + + qedr_iw_qp_rem_ref(&qp->ibqp); +} + +static void +qedr_iw_disconnect_event(void *context, + struct qed_iwarp_cm_event_params *params) +{ + struct qedr_discon_work *work; + struct qedr_iw_ep *ep = (struct qedr_iw_ep *)context; + struct qedr_dev *dev = ep->dev; + struct qedr_qp *qp = ep->qp; + + work = kzalloc(sizeof(*work), GFP_ATOMIC); + if (!work) + return; + + qedr_iw_qp_add_ref(&qp->ibqp); + work->ep = ep; + work->event = params->event; + work->status = params->status; + + INIT_WORK(&work->work, qedr_iw_disconnect_worker); + queue_work(dev->iwarp_wq, &work->work); +} + +static void +qedr_iw_passive_complete(void *context, + struct qed_iwarp_cm_event_params *params) +{ + struct qedr_iw_ep *ep = (struct qedr_iw_ep *)context; + struct qedr_dev *dev = ep->dev; + + /* We will only reach the following state if MPA_REJECT was called on + * passive. In this case there will be no associated QP. + */ + if ((params->status == -ECONNREFUSED) && (!ep->qp)) { + DP_DEBUG(dev, QEDR_MSG_IWARP, + "PASSIVE connection refused releasing ep...\n"); + kfree(ep); + return; + } + + qedr_iw_issue_event(context, params, IW_CM_EVENT_ESTABLISHED); + + if (params->status < 0) + qedr_iw_close_event(context, params); +} + +static int +qedr_iw_mpa_reply(void *context, struct qed_iwarp_cm_event_params *params) +{ + struct qedr_iw_ep *ep = (struct qedr_iw_ep *)context; + struct qedr_dev *dev = ep->dev; + struct qed_iwarp_send_rtr_in rtr_in; + + rtr_in.ep_context = params->ep_context; + + return dev->ops->iwarp_send_rtr(dev->rdma_ctx, &rtr_in); +} + +static int +qedr_iw_event_handler(void *context, struct qed_iwarp_cm_event_params *params) +{ + struct qedr_iw_ep *ep = (struct qedr_iw_ep *)context; + struct qedr_dev *dev = ep->dev; + + switch (params->event) { + case QED_IWARP_EVENT_MPA_REQUEST: + qedr_iw_mpa_request(context, params); + break; + case QED_IWARP_EVENT_ACTIVE_MPA_REPLY: + qedr_iw_mpa_reply(context, params); + break; + case QED_IWARP_EVENT_PASSIVE_COMPLETE: + ep->during_connect = 0; + qedr_iw_passive_complete(context, params); + break; + + case QED_IWARP_EVENT_ACTIVE_COMPLETE: + ep->during_connect = 0; + qedr_iw_issue_event(context, + params, + IW_CM_EVENT_CONNECT_REPLY); + if (params->status < 0) { + struct qedr_iw_ep *ep = (struct qedr_iw_ep *)context; + + ep->cm_id->rem_ref(ep->cm_id); + ep->cm_id = NULL; + } + break; + case QED_IWARP_EVENT_DISCONNECT: + qedr_iw_disconnect_event(context, params); + break; + case QED_IWARP_EVENT_CLOSE: + ep->during_connect = 0; + qedr_iw_close_event(context, params); + break; + case QED_IWARP_EVENT_RQ_EMPTY: + qedr_iw_qp_event(context, params, IB_EVENT_QP_FATAL, + "QED_IWARP_EVENT_RQ_EMPTY"); + break; + case QED_IWARP_EVENT_IRQ_FULL: + qedr_iw_qp_event(context, params, IB_EVENT_QP_FATAL, + "QED_IWARP_EVENT_IRQ_FULL"); + break; + case QED_IWARP_EVENT_LLP_TIMEOUT: + qedr_iw_qp_event(context, params, IB_EVENT_QP_FATAL, + "QED_IWARP_EVENT_LLP_TIMEOUT"); + break; + case QED_IWARP_EVENT_REMOTE_PROTECTION_ERROR: + qedr_iw_qp_event(context, params, IB_EVENT_QP_ACCESS_ERR, + "QED_IWARP_EVENT_REMOTE_PROTECTION_ERROR"); + break; + case QED_IWARP_EVENT_CQ_OVERFLOW: + qedr_iw_qp_event(context, params, IB_EVENT_QP_FATAL, + "QED_IWARP_EVENT_CQ_OVERFLOW"); + break; + case QED_IWARP_EVENT_QP_CATASTROPHIC: + qedr_iw_qp_event(context, params, IB_EVENT_QP_FATAL, + "QED_IWARP_EVENT_QP_CATASTROPHIC"); + break; + case QED_IWARP_EVENT_LOCAL_ACCESS_ERROR: + qedr_iw_qp_event(context, params, IB_EVENT_QP_ACCESS_ERR, + "QED_IWARP_EVENT_LOCAL_ACCESS_ERROR"); + break; + case QED_IWARP_EVENT_REMOTE_OPERATION_ERROR: + qedr_iw_qp_event(context, params, IB_EVENT_QP_FATAL, + "QED_IWARP_EVENT_REMOTE_OPERATION_ERROR"); + break; + case QED_IWARP_EVENT_TERMINATE_RECEIVED: + DP_NOTICE(dev, "Got terminate message\n"); + break; + default: + DP_NOTICE(dev, "Unknown event received %d\n", params->event); + break; + }; + return 0; +} + +static u16 qedr_iw_get_vlan_ipv4(struct qedr_dev *dev, u32 *addr) +{ + struct net_device *ndev; + u16 vlan_id = 0; + + ndev = ip_dev_find(&init_net, htonl(addr[0])); + + if (ndev) { + vlan_id = rdma_vlan_dev_vlan_id(ndev); + dev_put(ndev); + } + if (vlan_id == 0xffff) + vlan_id = 0; + return vlan_id; +} + +static u16 qedr_iw_get_vlan_ipv6(u32 *addr) +{ + struct net_device *ndev = NULL; + struct in6_addr laddr6; + u16 vlan_id = 0; + int i; + + if (!IS_ENABLED(CONFIG_IPV6)) + return vlan_id; + + for (i = 0; i < 4; i++) + laddr6.in6_u.u6_addr32[i] = htonl(addr[i]); + + rcu_read_lock(); + for_each_netdev_rcu(&init_net, ndev) { + if (ipv6_chk_addr(&init_net, &laddr6, ndev, 1)) { + vlan_id = rdma_vlan_dev_vlan_id(ndev); + break; + } + } + + rcu_read_unlock(); + if (vlan_id == 0xffff) + vlan_id = 0; + + return vlan_id; +} + +static int +qedr_addr4_resolve(struct qedr_dev *dev, + struct sockaddr_in *src_in, + struct sockaddr_in *dst_in, u8 *dst_mac) +{ + __be32 src_ip = src_in->sin_addr.s_addr; + __be32 dst_ip = dst_in->sin_addr.s_addr; + struct neighbour *neigh = NULL; + struct rtable *rt = NULL; + int rc = 0; + + rt = ip_route_output(&init_net, dst_ip, src_ip, 0, 0); + if (IS_ERR(rt)) { + DP_ERR(dev, "ip_route_output returned error\n"); + return -EINVAL; + } + + neigh = dst_neigh_lookup(&rt->dst, &dst_ip); + + if (neigh) { + rcu_read_lock(); + if (neigh->nud_state & NUD_VALID) { + ether_addr_copy(dst_mac, neigh->ha); + DP_DEBUG(dev, QEDR_MSG_QP, "mac_addr=[%pM]\n", dst_mac); + } else { + neigh_event_send(neigh, NULL); + } + rcu_read_unlock(); + neigh_release(neigh); + } + + ip_rt_put(rt); + + return rc; +} + +static int +qedr_addr6_resolve(struct qedr_dev *dev, + struct sockaddr_in6 *src_in, + struct sockaddr_in6 *dst_in, u8 *dst_mac) +{ + struct neighbour *neigh = NULL; + struct dst_entry *dst; + struct flowi6 fl6; + int rc = 0; + + memset(&fl6, 0, sizeof(fl6)); + fl6.daddr = dst_in->sin6_addr; + fl6.saddr = src_in->sin6_addr; + + dst = ip6_route_output(&init_net, NULL, &fl6); + + if ((!dst) || dst->error) { + if (dst) { + dst_release(dst); + DP_ERR(dev, + "ip6_route_output returned dst->error = %d\n", + dst->error); + } + return -EINVAL; + } + neigh = dst_neigh_lookup(dst, &dst_in); + + if (neigh) { + rcu_read_lock(); + if (neigh->nud_state & NUD_VALID) { + ether_addr_copy(dst_mac, neigh->ha); + DP_DEBUG(dev, QEDR_MSG_QP, "mac_addr=[%pM]\n", dst_mac); + } else { + neigh_event_send(neigh, NULL); + } + rcu_read_unlock(); + neigh_release(neigh); + } + + dst_release(dst); + + return rc; +} + +int qedr_iw_connect(struct iw_cm_id *cm_id, struct iw_cm_conn_param *conn_param) +{ + struct qedr_dev *dev = get_qedr_dev(cm_id->device); + struct qed_iwarp_connect_out out_params; + struct qed_iwarp_connect_in in_params; + struct qed_iwarp_cm_info *cm_info; + struct sockaddr_in6 *laddr6; + struct sockaddr_in6 *raddr6; + struct sockaddr_in *laddr; + struct sockaddr_in *raddr; + struct qedr_iw_ep *ep; + struct qedr_qp *qp; + int rc = 0; + int i; + + qp = idr_find(&dev->qpidr, conn_param->qpn); + + laddr = (struct sockaddr_in *)&cm_id->local_addr; + raddr = (struct sockaddr_in *)&cm_id->remote_addr; + laddr6 = (struct sockaddr_in6 *)&cm_id->local_addr; + raddr6 = (struct sockaddr_in6 *)&cm_id->remote_addr; + + DP_DEBUG(dev, QEDR_MSG_IWARP, + "Connect source address: %pISpc, remote address: %pISpc\n", + &cm_id->local_addr, &cm_id->remote_addr); + + if (!laddr->sin_port || !raddr->sin_port) + return -EINVAL; + + ep = kzalloc(sizeof(*ep), GFP_KERNEL); + if (!ep) + return -ENOMEM; + + ep->dev = dev; + ep->qp = qp; + qp->ep = ep; + cm_id->add_ref(cm_id); + ep->cm_id = cm_id; + + in_params.event_cb = qedr_iw_event_handler; + in_params.cb_context = ep; + + cm_info = &in_params.cm_info; + memset(cm_info->local_ip, 0, sizeof(cm_info->local_ip)); + memset(cm_info->remote_ip, 0, sizeof(cm_info->remote_ip)); + + if (!IS_ENABLED(CONFIG_IPV6) || + cm_id->remote_addr.ss_family == AF_INET) { + cm_info->ip_version = QED_TCP_IPV4; + + cm_info->remote_ip[0] = ntohl(raddr->sin_addr.s_addr); + cm_info->local_ip[0] = ntohl(laddr->sin_addr.s_addr); + cm_info->remote_port = ntohs(raddr->sin_port); + cm_info->local_port = ntohs(laddr->sin_port); + cm_info->vlan = qedr_iw_get_vlan_ipv4(dev, cm_info->local_ip); + + rc = qedr_addr4_resolve(dev, laddr, raddr, + (u8 *)in_params.remote_mac_addr); + + in_params.mss = dev->iwarp_max_mtu - + (sizeof(struct iphdr) + sizeof(struct tcphdr)); + + } else { + in_params.cm_info.ip_version = QED_TCP_IPV6; + + for (i = 0; i < 4; i++) { + cm_info->remote_ip[i] = + ntohl(raddr6->sin6_addr.in6_u.u6_addr32[i]); + cm_info->local_ip[i] = + ntohl(laddr6->sin6_addr.in6_u.u6_addr32[i]); + } + + cm_info->local_port = ntohs(laddr6->sin6_port); + cm_info->remote_port = ntohs(raddr6->sin6_port); + + in_params.mss = dev->iwarp_max_mtu - + (sizeof(struct ipv6hdr) + sizeof(struct tcphdr)); + + cm_info->vlan = qedr_iw_get_vlan_ipv6(cm_info->local_ip); + + rc = qedr_addr6_resolve(dev, laddr6, raddr6, + (u8 *)in_params.remote_mac_addr); + } + if (rc) + goto err; + + DP_DEBUG(dev, QEDR_MSG_IWARP, + "ord = %d ird=%d private_data=%p private_data_len=%d rq_psn=%d\n", + conn_param->ord, conn_param->ird, conn_param->private_data, + conn_param->private_data_len, qp->rq_psn); + + cm_info->ord = conn_param->ord; + cm_info->ird = conn_param->ird; + cm_info->private_data = conn_param->private_data; + cm_info->private_data_len = conn_param->private_data_len; + in_params.qp = qp->qed_qp; + memcpy(in_params.local_mac_addr, dev->ndev->dev_addr, ETH_ALEN); + + ep->during_connect = 1; + rc = dev->ops->iwarp_connect(dev->rdma_ctx, &in_params, &out_params); + if (rc) + goto err; + + return rc; + +err: + cm_id->rem_ref(cm_id); + kfree(ep); + return rc; +} + +int qedr_iw_create_listen(struct iw_cm_id *cm_id, int backlog) +{ + struct qedr_dev *dev = get_qedr_dev(cm_id->device); + struct qedr_iw_listener *listener; + struct qed_iwarp_listen_in iparams; + struct qed_iwarp_listen_out oparams; + struct sockaddr_in *laddr; + struct sockaddr_in6 *laddr6; + int rc; + int i; + + laddr = (struct sockaddr_in *)&cm_id->local_addr; + laddr6 = (struct sockaddr_in6 *)&cm_id->local_addr; + + DP_DEBUG(dev, QEDR_MSG_IWARP, + "Create Listener address: %pISpc\n", &cm_id->local_addr); + + listener = kzalloc(sizeof(*listener), GFP_KERNEL); + if (!listener) + return -ENOMEM; + + listener->dev = dev; + cm_id->add_ref(cm_id); + listener->cm_id = cm_id; + listener->backlog = backlog; + + iparams.cb_context = listener; + iparams.event_cb = qedr_iw_event_handler; + iparams.max_backlog = backlog; + + if (!IS_ENABLED(CONFIG_IPV6) || + cm_id->local_addr.ss_family == AF_INET) { + iparams.ip_version = QED_TCP_IPV4; + memset(iparams.ip_addr, 0, sizeof(iparams.ip_addr)); + + iparams.ip_addr[0] = ntohl(laddr->sin_addr.s_addr); + iparams.port = ntohs(laddr->sin_port); + iparams.vlan = qedr_iw_get_vlan_ipv4(dev, iparams.ip_addr); + } else { + iparams.ip_version = QED_TCP_IPV6; + + for (i = 0; i < 4; i++) { + iparams.ip_addr[i] = + ntohl(laddr6->sin6_addr.in6_u.u6_addr32[i]); + } + + iparams.port = ntohs(laddr6->sin6_port); + + iparams.vlan = qedr_iw_get_vlan_ipv6(iparams.ip_addr); + } + rc = dev->ops->iwarp_create_listen(dev->rdma_ctx, &iparams, &oparams); + if (rc) + goto err; + + listener->qed_handle = oparams.handle; + cm_id->provider_data = listener; + return rc; + +err: + cm_id->rem_ref(cm_id); + kfree(listener); + return rc; +} + +int qedr_iw_destroy_listen(struct iw_cm_id *cm_id) +{ + struct qedr_iw_listener *listener = cm_id->provider_data; + struct qedr_dev *dev = get_qedr_dev(cm_id->device); + int rc = 0; + + if (listener->qed_handle) + rc = dev->ops->iwarp_destroy_listen(dev->rdma_ctx, + listener->qed_handle); + + cm_id->rem_ref(cm_id); + return rc; +} + +int qedr_iw_accept(struct iw_cm_id *cm_id, struct iw_cm_conn_param *conn_param) +{ + struct qedr_iw_ep *ep = (struct qedr_iw_ep *)cm_id->provider_data; + struct qedr_dev *dev = ep->dev; + struct qedr_qp *qp; + struct qed_iwarp_accept_in params; + int rc; + + DP_DEBUG(dev, QEDR_MSG_IWARP, "Accept on qpid=%d\n", conn_param->qpn); + + qp = idr_find(&dev->qpidr, conn_param->qpn); + if (!qp) { + DP_ERR(dev, "Invalid QP number %d\n", conn_param->qpn); + return -EINVAL; + } + + ep->qp = qp; + qp->ep = ep; + cm_id->add_ref(cm_id); + ep->cm_id = cm_id; + + params.ep_context = ep->qed_context; + params.cb_context = ep; + params.qp = ep->qp->qed_qp; + params.private_data = conn_param->private_data; + params.private_data_len = conn_param->private_data_len; + params.ird = conn_param->ird; + params.ord = conn_param->ord; + + ep->during_connect = 1; + rc = dev->ops->iwarp_accept(dev->rdma_ctx, ¶ms); + if (rc) + goto err; + + return rc; +err: + ep->during_connect = 0; + cm_id->rem_ref(cm_id); + return rc; +} + +int qedr_iw_reject(struct iw_cm_id *cm_id, const void *pdata, u8 pdata_len) +{ + struct qedr_iw_ep *ep = (struct qedr_iw_ep *)cm_id->provider_data; + struct qedr_dev *dev = ep->dev; + struct qed_iwarp_reject_in params; + + params.ep_context = ep->qed_context; + params.cb_context = ep; + params.private_data = pdata; + params.private_data_len = pdata_len; + ep->qp = NULL; + + return dev->ops->iwarp_reject(dev->rdma_ctx, ¶ms); +} + +void qedr_iw_qp_add_ref(struct ib_qp *ibqp) +{ + struct qedr_qp *qp = get_qedr_qp(ibqp); + + atomic_inc(&qp->refcnt); +} + +void qedr_iw_qp_rem_ref(struct ib_qp *ibqp) +{ + struct qedr_qp *qp = get_qedr_qp(ibqp); + + if (atomic_dec_and_test(&qp->refcnt)) { + spin_lock_irq(&qp->dev->idr_lock); + idr_remove(&qp->dev->qpidr, qp->qp_id); + spin_unlock_irq(&qp->dev->idr_lock); + kfree(qp); + } +} + +struct ib_qp *qedr_iw_get_qp(struct ib_device *ibdev, int qpn) +{ + struct qedr_dev *dev = get_qedr_dev(ibdev); + + return idr_find(&dev->qpidr, qpn); +} diff --git a/drivers/infiniband/hw/qedr/qedr_iw_cm.h b/drivers/infiniband/hw/qedr/qedr_iw_cm.h new file mode 100644 index 000000000000..08f4b1067e6c --- /dev/null +++ b/drivers/infiniband/hw/qedr/qedr_iw_cm.h @@ -0,0 +1,49 @@ +/* QLogic qed NIC Driver + * Copyright (c) 2015-2017 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. + */ +#include <rdma/iw_cm.h> + +int qedr_iw_connect(struct iw_cm_id *cm_id, + struct iw_cm_conn_param *conn_param); + +int qedr_iw_create_listen(struct iw_cm_id *cm_id, int backlog); + +int qedr_iw_destroy_listen(struct iw_cm_id *cm_id); + +int qedr_iw_accept(struct iw_cm_id *cm_id, struct iw_cm_conn_param *conn_param); + +int qedr_iw_reject(struct iw_cm_id *cm_id, const void *pdata, u8 pdata_len); + +void qedr_iw_qp_add_ref(struct ib_qp *qp); + +void qedr_iw_qp_rem_ref(struct ib_qp *qp); + +struct ib_qp *qedr_iw_get_qp(struct ib_device *dev, int qpn); diff --git a/drivers/infiniband/hw/qedr/qedr_cm.c b/drivers/infiniband/hw/qedr/qedr_roce_cm.c index ad8965397cf7..2bdbb12bfc69 100644 --- a/drivers/infiniband/hw/qedr/qedr_cm.c +++ b/drivers/infiniband/hw/qedr/qedr_roce_cm.c @@ -48,7 +48,7 @@ #include "qedr.h" #include "verbs.h" #include <rdma/qedr-abi.h> -#include "qedr_cm.h" +#include "qedr_roce_cm.h" void qedr_inc_sw_gsi_cons(struct qedr_qp_hwq_info *info) { @@ -64,11 +64,11 @@ void qedr_store_gsi_qp_cq(struct qedr_dev *dev, struct qedr_qp *qp, dev->gsi_qp = qp; } -void qedr_ll2_complete_tx_packet(void *cxt, - u8 connection_handle, - void *cookie, - dma_addr_t first_frag_addr, - bool b_last_fragment, bool b_last_packet) +static void qedr_ll2_complete_tx_packet(void *cxt, u8 connection_handle, + void *cookie, + dma_addr_t first_frag_addr, + bool b_last_fragment, + bool b_last_packet) { struct qedr_dev *dev = (struct qedr_dev *)cxt; struct qed_roce_ll2_packet *pkt = cookie; @@ -93,8 +93,8 @@ void qedr_ll2_complete_tx_packet(void *cxt, (*cq->ibcq.comp_handler) (&cq->ibcq, cq->ibcq.cq_context); } -void qedr_ll2_complete_rx_packet(void *cxt, - struct qed_ll2_comp_rx_data *data) +static void qedr_ll2_complete_rx_packet(void *cxt, + struct qed_ll2_comp_rx_data *data) { struct qedr_dev *dev = (struct qedr_dev *)cxt; struct qedr_cq *cq = dev->gsi_rqcq; @@ -122,10 +122,9 @@ void qedr_ll2_complete_rx_packet(void *cxt, (*cq->ibcq.comp_handler) (&cq->ibcq, cq->ibcq.cq_context); } -void qedr_ll2_release_rx_packet(void *cxt, - u8 connection_handle, - void *cookie, - dma_addr_t rx_buf_addr, bool b_last_packet) +static void qedr_ll2_release_rx_packet(void *cxt, u8 connection_handle, + void *cookie, dma_addr_t rx_buf_addr, + bool b_last_packet) { /* Do nothing... */ } @@ -237,7 +236,7 @@ static int qedr_ll2_post_tx(struct qedr_dev *dev, return 0; } -int qedr_ll2_stop(struct qedr_dev *dev) +static int qedr_ll2_stop(struct qedr_dev *dev) { int rc; @@ -260,8 +259,8 @@ int qedr_ll2_stop(struct qedr_dev *dev) return rc; } -int qedr_ll2_start(struct qedr_dev *dev, - struct ib_qp_init_attr *attrs, struct qedr_qp *qp) +static int qedr_ll2_start(struct qedr_dev *dev, + struct ib_qp_init_attr *attrs, struct qedr_qp *qp) { struct qed_ll2_acquire_data data; struct qed_ll2_cbs cbs; @@ -660,7 +659,7 @@ int qedr_gsi_post_recv(struct ib_qp *ibqp, struct ib_recv_wr *wr, dev->gsi_ll2_handle, wr->sg_list[0].addr, wr->sg_list[0].length, - 0 /* cookie */, + NULL /* cookie */, 1 /* notify_fw */); if (rc) { DP_ERR(dev, diff --git a/drivers/infiniband/hw/qedr/qedr_cm.h b/drivers/infiniband/hw/qedr/qedr_roce_cm.h index a55916323ea9..a55916323ea9 100644 --- a/drivers/infiniband/hw/qedr/qedr_cm.h +++ b/drivers/infiniband/hw/qedr/qedr_roce_cm.h diff --git a/drivers/infiniband/hw/qedr/verbs.c b/drivers/infiniband/hw/qedr/verbs.c index 769ac07c3c8e..b26aa88dab48 100644 --- a/drivers/infiniband/hw/qedr/verbs.c +++ b/drivers/infiniband/hw/qedr/verbs.c @@ -49,7 +49,7 @@ #include "qedr.h" #include "verbs.h" #include <rdma/qedr-abi.h> -#include "qedr_cm.h" +#include "qedr_roce_cm.h" #define DB_ADDR_SHIFT(addr) ((addr) << DB_PWM_ADDR_OFFSET_SHIFT) @@ -70,6 +70,20 @@ int qedr_query_pkey(struct ib_device *ibdev, u8 port, u16 index, u16 *pkey) return 0; } +int qedr_iw_query_gid(struct ib_device *ibdev, u8 port, + int index, union ib_gid *sgid) +{ + struct qedr_dev *dev = get_qedr_dev(ibdev); + + memset(sgid->raw, 0, sizeof(sgid->raw)); + ether_addr_copy(sgid->raw, dev->ndev->dev_addr); + + DP_DEBUG(dev, QEDR_MSG_INIT, "QUERY sgid[%d]=%llx:%llx\n", index, + sgid->global.interface_id, sgid->global.subnet_prefix); + + return 0; +} + int qedr_query_gid(struct ib_device *ibdev, u8 port, int index, union ib_gid *sgid) { @@ -263,8 +277,13 @@ int qedr_query_port(struct ib_device *ibdev, u8 port, struct ib_port_attr *attr) attr->sm_lid = 0; attr->sm_sl = 0; attr->port_cap_flags = IB_PORT_IP_BASED_GIDS; - attr->gid_tbl_len = QEDR_MAX_SGID; - attr->pkey_tbl_len = QEDR_ROCE_PKEY_TABLE_LEN; + if (rdma_protocol_iwarp(&dev->ibdev, 1)) { + attr->gid_tbl_len = 1; + attr->pkey_tbl_len = 1; + } else { + attr->gid_tbl_len = QEDR_MAX_SGID; + attr->pkey_tbl_len = QEDR_ROCE_PKEY_TABLE_LEN; + } attr->bad_pkey_cntr = rdma_port->pkey_bad_counter; attr->qkey_viol_cntr = 0; get_link_speed_and_width(rdma_port->link_speed, @@ -770,7 +789,8 @@ static inline int qedr_init_user_queue(struct ib_ucontext *ib_ctx, struct qedr_dev *dev, struct qedr_userq *q, u64 buf_addr, size_t buf_len, - int access, int dmasync) + int access, int dmasync, + int alloc_and_init) { u32 fw_pages; int rc; @@ -791,19 +811,27 @@ static inline int qedr_init_user_queue(struct ib_ucontext *ib_ctx, if (rc) goto err0; - q->pbl_tbl = qedr_alloc_pbl_tbl(dev, &q->pbl_info, GFP_KERNEL); - if (IS_ERR(q->pbl_tbl)) { - rc = PTR_ERR(q->pbl_tbl); - goto err0; - } - + if (alloc_and_init) { + q->pbl_tbl = qedr_alloc_pbl_tbl(dev, &q->pbl_info, GFP_KERNEL); + if (IS_ERR(q->pbl_tbl)) { + rc = PTR_ERR(q->pbl_tbl); + goto err0; + } qedr_populate_pbls(dev, q->umem, q->pbl_tbl, &q->pbl_info, FW_PAGE_SHIFT); + } else { + q->pbl_tbl = kzalloc(sizeof(*q->pbl_tbl), GFP_KERNEL); + if (!q->pbl_tbl) { + rc = -ENOMEM; + goto err0; + } + } return 0; err0: ib_umem_release(q->umem); + q->umem = NULL; return rc; } @@ -929,7 +957,8 @@ struct ib_cq *qedr_create_cq(struct ib_device *ibdev, cq->cq_type = QEDR_CQ_TYPE_USER; rc = qedr_init_user_queue(ib_ctx, dev, &cq->q, ureq.addr, - ureq.len, IB_ACCESS_LOCAL_WRITE, 1); + ureq.len, IB_ACCESS_LOCAL_WRITE, + 1, 1); if (rc) goto err0; @@ -1222,18 +1251,34 @@ static int qedr_check_qp_attrs(struct ib_pd *ibpd, struct qedr_dev *dev, return 0; } -static void qedr_copy_rq_uresp(struct qedr_create_qp_uresp *uresp, +static void qedr_copy_rq_uresp(struct qedr_dev *dev, + struct qedr_create_qp_uresp *uresp, struct qedr_qp *qp) { - uresp->rq_db_offset = DB_ADDR_SHIFT(DQ_PWM_OFFSET_TCM_ROCE_RQ_PROD); + /* iWARP requires two doorbells per RQ. */ + if (rdma_protocol_iwarp(&dev->ibdev, 1)) { + uresp->rq_db_offset = + DB_ADDR_SHIFT(DQ_PWM_OFFSET_TCM_IWARP_RQ_PROD); + uresp->rq_db2_offset = DB_ADDR_SHIFT(DQ_PWM_OFFSET_TCM_FLAGS); + } else { + uresp->rq_db_offset = + DB_ADDR_SHIFT(DQ_PWM_OFFSET_TCM_ROCE_RQ_PROD); + } + uresp->rq_icid = qp->icid; } -static void qedr_copy_sq_uresp(struct qedr_create_qp_uresp *uresp, +static void qedr_copy_sq_uresp(struct qedr_dev *dev, + struct qedr_create_qp_uresp *uresp, struct qedr_qp *qp) { uresp->sq_db_offset = DB_ADDR_SHIFT(DQ_PWM_OFFSET_XCM_RDMA_SQ_PROD); - uresp->sq_icid = qp->icid + 1; + + /* iWARP uses the same cid for rq and sq */ + if (rdma_protocol_iwarp(&dev->ibdev, 1)) + uresp->sq_icid = qp->icid; + else + uresp->sq_icid = qp->icid + 1; } static int qedr_copy_qp_uresp(struct qedr_dev *dev, @@ -1243,8 +1288,8 @@ static int qedr_copy_qp_uresp(struct qedr_dev *dev, int rc; memset(&uresp, 0, sizeof(uresp)); - qedr_copy_sq_uresp(&uresp, qp); - qedr_copy_rq_uresp(&uresp, qp); + qedr_copy_sq_uresp(dev, &uresp, qp); + qedr_copy_rq_uresp(dev, &uresp, qp); uresp.atomic_supported = dev->atomic_cap != IB_ATOMIC_NONE; uresp.qp_id = qp->qp_id; @@ -1264,6 +1309,7 @@ static void qedr_set_common_qp_params(struct qedr_dev *dev, struct ib_qp_init_attr *attrs) { spin_lock_init(&qp->q_lock); + atomic_set(&qp->refcnt, 1); qp->pd = pd; qp->qp_type = attrs->qp_type; qp->max_inline_data = attrs->cap.max_inline_data; @@ -1334,6 +1380,52 @@ static inline void qedr_qp_user_print(struct qedr_dev *dev, struct qedr_qp *qp) qp->usq.buf_len, qp->urq.buf_addr, qp->urq.buf_len); } +static int qedr_idr_add(struct qedr_dev *dev, void *ptr, u32 id) +{ + int rc; + + if (!rdma_protocol_iwarp(&dev->ibdev, 1)) + return 0; + + idr_preload(GFP_KERNEL); + spin_lock_irq(&dev->idr_lock); + + rc = idr_alloc(&dev->qpidr, ptr, id, id + 1, GFP_ATOMIC); + + spin_unlock_irq(&dev->idr_lock); + idr_preload_end(); + + return rc < 0 ? rc : 0; +} + +static void qedr_idr_remove(struct qedr_dev *dev, u32 id) +{ + if (!rdma_protocol_iwarp(&dev->ibdev, 1)) + return; + + spin_lock_irq(&dev->idr_lock); + idr_remove(&dev->qpidr, id); + spin_unlock_irq(&dev->idr_lock); +} + +static inline void +qedr_iwarp_populate_user_qp(struct qedr_dev *dev, + struct qedr_qp *qp, + struct qed_rdma_create_qp_out_params *out_params) +{ + qp->usq.pbl_tbl->va = out_params->sq_pbl_virt; + qp->usq.pbl_tbl->pa = out_params->sq_pbl_phys; + + qedr_populate_pbls(dev, qp->usq.umem, qp->usq.pbl_tbl, + &qp->usq.pbl_info, FW_PAGE_SHIFT); + + qp->urq.pbl_tbl->va = out_params->rq_pbl_virt; + qp->urq.pbl_tbl->pa = out_params->rq_pbl_phys; + + qedr_populate_pbls(dev, qp->urq.umem, qp->urq.pbl_tbl, + &qp->urq.pbl_info, FW_PAGE_SHIFT); +} + static void qedr_cleanup_user(struct qedr_dev *dev, struct qedr_qp *qp) { if (qp->usq.umem) @@ -1355,12 +1447,11 @@ static int qedr_create_user_qp(struct qedr_dev *dev, struct qed_rdma_create_qp_out_params out_params; struct qedr_pd *pd = get_qedr_pd(ibpd); struct ib_ucontext *ib_ctx = NULL; - struct qedr_ucontext *ctx = NULL; struct qedr_create_qp_ureq ureq; + int alloc_and_init = rdma_protocol_roce(&dev->ibdev, 1); int rc = -EINVAL; ib_ctx = ibpd->uobject->context; - ctx = get_qedr_ucontext(ib_ctx); memset(&ureq, 0, sizeof(ureq)); rc = ib_copy_from_udata(&ureq, udata, sizeof(ureq)); @@ -1371,14 +1462,13 @@ static int qedr_create_user_qp(struct qedr_dev *dev, /* SQ - read access only (0), dma sync not required (0) */ rc = qedr_init_user_queue(ib_ctx, dev, &qp->usq, ureq.sq_addr, - ureq.sq_len, 0, 0); + ureq.sq_len, 0, 0, alloc_and_init); if (rc) return rc; /* RQ - read access only (0), dma sync not required (0) */ rc = qedr_init_user_queue(ib_ctx, dev, &qp->urq, ureq.rq_addr, - ureq.rq_len, 0, 0); - + ureq.rq_len, 0, 0, alloc_and_init); if (rc) return rc; @@ -1399,6 +1489,9 @@ static int qedr_create_user_qp(struct qedr_dev *dev, goto err1; } + if (rdma_protocol_iwarp(&dev->ibdev, 1)) + qedr_iwarp_populate_user_qp(dev, qp, &out_params); + qp->qp_id = out_params.qp_id; qp->icid = out_params.icid; @@ -1419,6 +1512,21 @@ err1: return rc; } +static void qedr_set_iwarp_db_info(struct qedr_dev *dev, struct qedr_qp *qp) +{ + qp->sq.db = dev->db_addr + + DB_ADDR_SHIFT(DQ_PWM_OFFSET_XCM_RDMA_SQ_PROD); + qp->sq.db_data.data.icid = qp->icid; + + qp->rq.db = dev->db_addr + + DB_ADDR_SHIFT(DQ_PWM_OFFSET_TCM_IWARP_RQ_PROD); + qp->rq.db_data.data.icid = qp->icid; + qp->rq.iwarp_db2 = dev->db_addr + + DB_ADDR_SHIFT(DQ_PWM_OFFSET_TCM_FLAGS); + qp->rq.iwarp_db2_data.data.icid = qp->icid; + qp->rq.iwarp_db2_data.data.value = DQ_TCM_IWARP_POST_RQ_CF_CMD; +} + static int qedr_roce_create_kernel_qp(struct qedr_dev *dev, struct qedr_qp *qp, @@ -1465,8 +1573,71 @@ qedr_roce_create_kernel_qp(struct qedr_dev *dev, qp->icid = out_params.icid; qedr_set_roce_db_info(dev, qp); + return rc; +} - return 0; +static int +qedr_iwarp_create_kernel_qp(struct qedr_dev *dev, + struct qedr_qp *qp, + struct qed_rdma_create_qp_in_params *in_params, + u32 n_sq_elems, u32 n_rq_elems) +{ + struct qed_rdma_create_qp_out_params out_params; + struct qed_chain_ext_pbl ext_pbl; + int rc; + + in_params->sq_num_pages = QED_CHAIN_PAGE_CNT(n_sq_elems, + QEDR_SQE_ELEMENT_SIZE, + QED_CHAIN_MODE_PBL); + in_params->rq_num_pages = QED_CHAIN_PAGE_CNT(n_rq_elems, + QEDR_RQE_ELEMENT_SIZE, + QED_CHAIN_MODE_PBL); + + qp->qed_qp = dev->ops->rdma_create_qp(dev->rdma_ctx, + in_params, &out_params); + + if (!qp->qed_qp) + return -EINVAL; + + /* Now we allocate the chain */ + ext_pbl.p_pbl_virt = out_params.sq_pbl_virt; + ext_pbl.p_pbl_phys = out_params.sq_pbl_phys; + + rc = dev->ops->common->chain_alloc(dev->cdev, + QED_CHAIN_USE_TO_PRODUCE, + QED_CHAIN_MODE_PBL, + QED_CHAIN_CNT_TYPE_U32, + n_sq_elems, + QEDR_SQE_ELEMENT_SIZE, + &qp->sq.pbl, &ext_pbl); + + if (rc) + goto err; + + ext_pbl.p_pbl_virt = out_params.rq_pbl_virt; + ext_pbl.p_pbl_phys = out_params.rq_pbl_phys; + + rc = dev->ops->common->chain_alloc(dev->cdev, + QED_CHAIN_USE_TO_CONSUME_PRODUCE, + QED_CHAIN_MODE_PBL, + QED_CHAIN_CNT_TYPE_U32, + n_rq_elems, + QEDR_RQE_ELEMENT_SIZE, + &qp->rq.pbl, &ext_pbl); + + if (rc) + goto err; + + qp->qp_id = out_params.qp_id; + qp->icid = out_params.icid; + + qedr_set_iwarp_db_info(dev, qp); + return rc; + +err: + dev->ops->rdma_destroy_qp(dev->rdma_ctx, qp->qed_qp); + + return rc; } static void qedr_cleanup_kernel(struct qedr_dev *dev, struct qedr_qp *qp) @@ -1541,8 +1712,12 @@ static int qedr_create_kernel_qp(struct qedr_dev *dev, n_rq_elems = qp->rq.max_wr * QEDR_MAX_RQE_ELEMENTS_PER_RQE; - rc = qedr_roce_create_kernel_qp(dev, qp, &in_params, - n_sq_elems, n_rq_elems); + if (rdma_protocol_iwarp(&dev->ibdev, 1)) + rc = qedr_iwarp_create_kernel_qp(dev, qp, &in_params, + n_sq_elems, n_rq_elems); + else + rc = qedr_roce_create_kernel_qp(dev, qp, &in_params, + n_sq_elems, n_rq_elems); if (rc) qedr_cleanup_kernel(dev, qp); @@ -1602,6 +1777,10 @@ struct ib_qp *qedr_create_qp(struct ib_pd *ibpd, qp->ibqp.qp_num = qp->qp_id; + rc = qedr_idr_add(dev, qp, qp->qp_id); + if (rc) + goto err; + return &qp->ibqp; err: @@ -1689,10 +1868,13 @@ static int qedr_update_qp_state(struct qedr_dev *dev, /* Update doorbell (in case post_recv was * done before move to RTR) */ - wmb(); - writel(qp->rq.db_data.raw, qp->rq.db); - /* Make sure write takes effect */ - mmiowb(); + + if (rdma_protocol_roce(&dev->ibdev, 1)) { + wmb(); + writel(qp->rq.db_data.raw, qp->rq.db); + /* Make sure write takes effect */ + mmiowb(); + } break; case QED_ROCE_QP_STATE_ERR: break; @@ -1786,16 +1968,18 @@ int qedr_modify_qp(struct ib_qp *ibqp, struct ib_qp_attr *attr, else new_qp_state = old_qp_state; - if (!ib_modify_qp_is_ok - (old_qp_state, new_qp_state, ibqp->qp_type, attr_mask, - IB_LINK_LAYER_ETHERNET)) { - DP_ERR(dev, - "modify qp: invalid attribute mask=0x%x specified for\n" - "qpn=0x%x of type=0x%x old_qp_state=0x%x, new_qp_state=0x%x\n", - attr_mask, qp->qp_id, ibqp->qp_type, old_qp_state, - new_qp_state); - rc = -EINVAL; - goto err; + if (rdma_protocol_roce(&dev->ibdev, 1)) { + if (!ib_modify_qp_is_ok(old_qp_state, new_qp_state, + ibqp->qp_type, attr_mask, + IB_LINK_LAYER_ETHERNET)) { + DP_ERR(dev, + "modify qp: invalid attribute mask=0x%x specified for\n" + "qpn=0x%x of type=0x%x old_qp_state=0x%x, new_qp_state=0x%x\n", + attr_mask, qp->qp_id, ibqp->qp_type, + old_qp_state, new_qp_state); + rc = -EINVAL; + goto err; + } } /* Translate the masks... */ @@ -2082,7 +2266,7 @@ err: return rc; } -int qedr_free_qp_resources(struct qedr_dev *dev, struct qedr_qp *qp) +static int qedr_free_qp_resources(struct qedr_dev *dev, struct qedr_qp *qp) { int rc = 0; @@ -2111,15 +2295,34 @@ int qedr_destroy_qp(struct ib_qp *ibqp) DP_DEBUG(dev, QEDR_MSG_QP, "destroy qp: destroying %p, qp type=%d\n", qp, qp->qp_type); - if ((qp->state != QED_ROCE_QP_STATE_RESET) && - (qp->state != QED_ROCE_QP_STATE_ERR) && - (qp->state != QED_ROCE_QP_STATE_INIT)) { + if (rdma_protocol_roce(&dev->ibdev, 1)) { + if ((qp->state != QED_ROCE_QP_STATE_RESET) && + (qp->state != QED_ROCE_QP_STATE_ERR) && + (qp->state != QED_ROCE_QP_STATE_INIT)) { - attr.qp_state = IB_QPS_ERR; - attr_mask |= IB_QP_STATE; + attr.qp_state = IB_QPS_ERR; + attr_mask |= IB_QP_STATE; - /* Change the QP state to ERROR */ - qedr_modify_qp(ibqp, &attr, attr_mask, NULL); + /* Change the QP state to ERROR */ + qedr_modify_qp(ibqp, &attr, attr_mask, NULL); + } + } else { + /* Wait for the connect/accept to complete */ + if (qp->ep) { + int wait_count = 1; + + while (qp->ep->during_connect) { + DP_DEBUG(dev, QEDR_MSG_QP, + "Still in during connect/accept\n"); + + msleep(100); + if (wait_count++ > 200) { + DP_NOTICE(dev, + "during connect timeout\n"); + break; + } + } + } } if (qp->qp_type == IB_QPT_GSI) @@ -2127,8 +2330,10 @@ int qedr_destroy_qp(struct ib_qp *ibqp) qedr_free_qp_resources(dev, qp); - kfree(qp); - + if (atomic_dec_and_test(&qp->refcnt)) { + qedr_idr_remove(dev, qp->qp_id); + kfree(qp); + } return rc; } @@ -2395,7 +2600,6 @@ err0: struct ib_mr *qedr_alloc_mr(struct ib_pd *ibpd, enum ib_mr_type mr_type, u32 max_num_sg) { - struct qedr_dev *dev; struct qedr_mr *mr; if (mr_type != IB_MR_TYPE_MEM_REG) @@ -2406,8 +2610,6 @@ struct ib_mr *qedr_alloc_mr(struct ib_pd *ibpd, if (IS_ERR(mr)) return ERR_PTR(-EINVAL); - dev = mr->dev; - return &mr->ibmr; } @@ -2740,6 +2942,7 @@ static enum ib_wc_opcode qedr_ib_to_wc_opcode(enum ib_wr_opcode opcode) case IB_WR_SEND_WITH_INV: return IB_WC_SEND; case IB_WR_RDMA_READ: + case IB_WR_RDMA_READ_WITH_INV: return IB_WC_RDMA_READ; case IB_WR_ATOMIC_CMP_AND_SWP: return IB_WC_COMP_SWAP; @@ -2900,11 +3103,8 @@ static int __qedr_post_send(struct ib_qp *ibqp, struct ib_send_wr *wr, qp->wqe_wr_id[qp->sq.prod].bytes_len = rwqe->length; break; case IB_WR_RDMA_READ_WITH_INV: - DP_ERR(dev, - "RDMA READ WITH INVALIDATE not supported\n"); - *bad_wr = wr; - rc = -EINVAL; - break; + SET_FIELD2(wqe->flags, RDMA_SQ_RDMA_WQE_1ST_READ_INV_FLG, 1); + /* fallthrough -- same is identical to RDMA READ */ case IB_WR_RDMA_READ: wqe->req_type = RDMA_SQ_REQ_TYPE_RDMA_RD; @@ -3014,15 +3214,17 @@ int qedr_post_send(struct ib_qp *ibqp, struct ib_send_wr *wr, spin_lock_irqsave(&qp->q_lock, flags); - if ((qp->state != QED_ROCE_QP_STATE_RTS) && - (qp->state != QED_ROCE_QP_STATE_ERR) && - (qp->state != QED_ROCE_QP_STATE_SQD)) { - spin_unlock_irqrestore(&qp->q_lock, flags); - *bad_wr = wr; - DP_DEBUG(dev, QEDR_MSG_CQ, - "QP in wrong state! QP icid=0x%x state %d\n", - qp->icid, qp->state); - return -EINVAL; + if (rdma_protocol_roce(&dev->ibdev, 1)) { + if ((qp->state != QED_ROCE_QP_STATE_RTS) && + (qp->state != QED_ROCE_QP_STATE_ERR) && + (qp->state != QED_ROCE_QP_STATE_SQD)) { + spin_unlock_irqrestore(&qp->q_lock, flags); + *bad_wr = wr; + DP_DEBUG(dev, QEDR_MSG_CQ, + "QP in wrong state! QP icid=0x%x state %d\n", + qp->icid, qp->state); + return -EINVAL; + } } while (wr) { @@ -3142,6 +3344,11 @@ int qedr_post_recv(struct ib_qp *ibqp, struct ib_recv_wr *wr, /* Make sure write sticks */ mmiowb(); + if (rdma_protocol_iwarp(&dev->ibdev, 1)) { + writel(qp->rq.iwarp_db2_data.raw, qp->rq.iwarp_db2); + mmiowb(); /* for second doorbell */ + } + wr = wr->next; } @@ -3603,23 +3810,3 @@ int qedr_process_mad(struct ib_device *ibdev, int process_mad_flags, mad_hdr->method, mad_hdr->mgmt_class, mad_hdr->status); return IB_MAD_RESULT_SUCCESS; } - -int qedr_port_immutable(struct ib_device *ibdev, u8 port_num, - struct ib_port_immutable *immutable) -{ - struct ib_port_attr attr; - int err; - - immutable->core_cap_flags = RDMA_CORE_PORT_IBA_ROCE | - RDMA_CORE_PORT_IBA_ROCE_UDP_ENCAP; - - err = ib_query_port(ibdev, port_num, &attr); - if (err) - return err; - - immutable->pkey_tbl_len = attr.pkey_tbl_len; - immutable->gid_tbl_len = attr.gid_tbl_len; - immutable->max_mad_size = IB_MGMT_MAD_SIZE; - - return 0; -} diff --git a/drivers/infiniband/hw/qedr/verbs.h b/drivers/infiniband/hw/qedr/verbs.h index 0f8ab49d5a1a..1a94425dea33 100644 --- a/drivers/infiniband/hw/qedr/verbs.h +++ b/drivers/infiniband/hw/qedr/verbs.h @@ -39,6 +39,8 @@ int qedr_modify_port(struct ib_device *, u8 port, int mask, struct ib_port_modify *props); int qedr_query_gid(struct ib_device *, u8 port, int index, union ib_gid *gid); +int qedr_iw_query_gid(struct ib_device *ibdev, u8 port, + int index, union ib_gid *gid); int qedr_query_pkey(struct ib_device *, u8 port, u16 index, u16 *pkey); diff --git a/drivers/infiniband/hw/qib/Kconfig b/drivers/infiniband/hw/qib/Kconfig index e0fdb9201423..cb06314a2ae2 100644 --- a/drivers/infiniband/hw/qib/Kconfig +++ b/drivers/infiniband/hw/qib/Kconfig @@ -1,6 +1,7 @@ config INFINIBAND_QIB tristate "Intel PCIe HCA support" depends on 64BIT && INFINIBAND_RDMAVT + depends on PCI ---help--- This is a low-level driver for Intel PCIe QLE InfiniBand host channel adapters. This driver does not support the Intel diff --git a/drivers/infiniband/hw/qib/qib.h b/drivers/infiniband/hw/qib/qib.h index f9e1c69603a5..092ed8103842 100644 --- a/drivers/infiniband/hw/qib/qib.h +++ b/drivers/infiniband/hw/qib/qib.h @@ -102,18 +102,6 @@ extern const struct pci_error_handlers qib_pci_err_handler; #define QIB_TRAFFIC_ACTIVE_THRESHOLD (2000) /* - * Struct used to indicate which errors are logged in each of the - * error-counters that are logged to EEPROM. A counter is incremented - * _once_ (saturating at 255) for each event with any bits set in - * the error or hwerror register masks below. - */ -#define QIB_EEP_LOG_CNT (4) -struct qib_eep_log_mask { - u64 errs_to_log; - u64 hwerrs_to_log; -}; - -/* * Below contains all data related to a single context (formerly called port). */ @@ -443,14 +431,12 @@ struct qib_irq_notify; #endif struct qib_msix_entry { - int irq; void *arg; #ifdef CONFIG_INFINIBAND_QIB_DCA int dca; int rcv; struct qib_irq_notify *notifier; #endif - char name[MAX_NAME_SIZE]; cpumask_var_t mask; }; @@ -1081,11 +1067,6 @@ struct qib_devdata { /* control high-level access to EEPROM */ struct mutex eep_lock; uint64_t traffic_wds; - /* - * masks for which bits of errs, hwerrs that cause - * each of the counters to increment. - */ - struct qib_eep_log_mask eep_st_masks[QIB_EEP_LOG_CNT]; struct qib_diag_client *diag_client; spinlock_t qib_diag_trans_lock; /* protect diag observer ops */ struct diag_observer_list_elt *diag_observer_list; @@ -1188,7 +1169,7 @@ int qib_set_lid(struct qib_pportdata *, u32, u8); void qib_hol_down(struct qib_pportdata *); void qib_hol_init(struct qib_pportdata *); void qib_hol_up(struct qib_pportdata *); -void qib_hol_event(unsigned long); +void qib_hol_event(struct timer_list *); void qib_disable_after_error(struct qib_devdata *); int qib_set_uevent_bits(struct qib_pportdata *, const int); @@ -1299,10 +1280,9 @@ int qib_twsi_blk_rd(struct qib_devdata *dd, int dev, int addr, void *buffer, int qib_twsi_blk_wr(struct qib_devdata *dd, int dev, int addr, const void *buffer, int len); void qib_get_eeprom_info(struct qib_devdata *); -#define qib_inc_eeprom_err(dd, eidx, incr) void qib_dump_lookup_output_queue(struct qib_devdata *); void qib_force_pio_avail_update(struct qib_devdata *); -void qib_clear_symerror_on_linkup(unsigned long opaque); +void qib_clear_symerror_on_linkup(struct timer_list *t); /* * Set LED override, only the two LSBs have "public" meaning, but @@ -1434,10 +1414,8 @@ int qib_pcie_ddinit(struct qib_devdata *, struct pci_dev *, const struct pci_device_id *); void qib_pcie_ddcleanup(struct qib_devdata *); int qib_pcie_params(struct qib_devdata *dd, u32 minw, u32 *nent); -int qib_reinit_intr(struct qib_devdata *); -void qib_enable_intx(struct qib_devdata *dd); -void qib_nomsi(struct qib_devdata *); -void qib_nomsix(struct qib_devdata *); +void qib_free_irq(struct qib_devdata *dd); +int qib_reinit_intr(struct qib_devdata *dd); void qib_pcie_getcmd(struct qib_devdata *, u16 *, u8 *, u8 *); void qib_pcie_reenable(struct qib_devdata *, u16, u8, u8); /* interrupts for device */ diff --git a/drivers/infiniband/hw/qib/qib_7220.h b/drivers/infiniband/hw/qib/qib_7220.h index a5356cb4252e..9ecaab6232e3 100644 --- a/drivers/infiniband/hw/qib/qib_7220.h +++ b/drivers/infiniband/hw/qib/qib_7220.h @@ -67,7 +67,6 @@ struct qib_chip_specific { u32 lastbuf_for_pio; u32 updthresh; /* current AvailUpdThld */ u32 updthresh_dflt; /* default AvailUpdThld */ - int irq; u8 presets_needed; u8 relock_timer_active; char emsgbuf[128]; @@ -75,6 +74,7 @@ struct qib_chip_specific { char bitsmsgbuf[64]; struct timer_list relock_timer; unsigned int relock_interval; /* in jiffies */ + struct qib_devdata *dd; }; struct qib_chippport_specific { diff --git a/drivers/infiniband/hw/qib/qib_diag.c b/drivers/infiniband/hw/qib/qib_diag.c index 775018b32b0d..a9377eee8734 100644 --- a/drivers/infiniband/hw/qib/qib_diag.c +++ b/drivers/infiniband/hw/qib/qib_diag.c @@ -761,7 +761,6 @@ static ssize_t qib_diag_read(struct file *fp, char __user *data, { struct qib_diag_client *dc = fp->private_data; struct qib_devdata *dd = dc->dd; - void __iomem *kreg_base; ssize_t ret; if (dc->pid != current->pid) { @@ -769,8 +768,6 @@ static ssize_t qib_diag_read(struct file *fp, char __user *data, goto bail; } - kreg_base = dd->kregbase; - if (count == 0) ret = 0; else if ((count % 4) || (*off % 4)) @@ -838,7 +835,6 @@ static ssize_t qib_diag_write(struct file *fp, const char __user *data, { struct qib_diag_client *dc = fp->private_data; struct qib_devdata *dd = dc->dd; - void __iomem *kreg_base; ssize_t ret; if (dc->pid != current->pid) { @@ -846,8 +842,6 @@ static ssize_t qib_diag_write(struct file *fp, const char __user *data, goto bail; } - kreg_base = dd->kregbase; - if (count == 0) ret = 0; else if ((count % 4) || (*off % 4)) diff --git a/drivers/infiniband/hw/qib/qib_driver.c b/drivers/infiniband/hw/qib/qib_driver.c index 719906a9fd51..33d3335385e8 100644 --- a/drivers/infiniband/hw/qib/qib_driver.c +++ b/drivers/infiniband/hw/qib/qib_driver.c @@ -682,9 +682,10 @@ int qib_set_lid(struct qib_pportdata *ppd, u32 lid, u8 lmc) /* Below is "non-zero" to force override, but both actual LEDs are off */ #define LED_OVER_BOTH_OFF (8) -static void qib_run_led_override(unsigned long opaque) +static void qib_run_led_override(struct timer_list *t) { - struct qib_pportdata *ppd = (struct qib_pportdata *)opaque; + struct qib_pportdata *ppd = from_timer(ppd, t, + led_override_timer); struct qib_devdata *dd = ppd->dd; int timeoff; int ph_idx; @@ -735,9 +736,7 @@ void qib_set_led_override(struct qib_pportdata *ppd, unsigned int val) */ if (atomic_inc_return(&ppd->led_override_timer_active) == 1) { /* Need to start timer */ - init_timer(&ppd->led_override_timer); - ppd->led_override_timer.function = qib_run_led_override; - ppd->led_override_timer.data = (unsigned long) ppd; + timer_setup(&ppd->led_override_timer, qib_run_led_override, 0); ppd->led_override_timer.expires = jiffies + 1; add_timer(&ppd->led_override_timer); } else { diff --git a/drivers/infiniband/hw/qib/qib_file_ops.c b/drivers/infiniband/hw/qib/qib_file_ops.c index 9396c1807cc3..2d6a191afec0 100644 --- a/drivers/infiniband/hw/qib/qib_file_ops.c +++ b/drivers/infiniband/hw/qib/qib_file_ops.c @@ -696,15 +696,8 @@ static void qib_clean_part_key(struct qib_ctxtdata *rcd, struct qib_devdata *dd) { int i, j, pchanged = 0; - u64 oldpkey; struct qib_pportdata *ppd = rcd->ppd; - /* for debugging only */ - oldpkey = (u64) ppd->pkeys[0] | - ((u64) ppd->pkeys[1] << 16) | - ((u64) ppd->pkeys[2] << 32) | - ((u64) ppd->pkeys[3] << 48); - for (i = 0; i < ARRAY_SIZE(rcd->pkeys); i++) { if (!rcd->pkeys[i]) continue; @@ -1817,7 +1810,6 @@ static int qib_close(struct inode *in, struct file *fp) struct qib_devdata *dd; unsigned long flags; unsigned ctxt; - pid_t pid; mutex_lock(&qib_mutex); @@ -1859,7 +1851,6 @@ static int qib_close(struct inode *in, struct file *fp) spin_lock_irqsave(&dd->uctxt_lock, flags); ctxt = rcd->ctxt; dd->rcd[ctxt] = NULL; - pid = rcd->pid; rcd->pid = 0; spin_unlock_irqrestore(&dd->uctxt_lock, flags); diff --git a/drivers/infiniband/hw/qib/qib_iba6120.c b/drivers/infiniband/hw/qib/qib_iba6120.c index 3259a60e4f4f..8a15e5c7dd91 100644 --- a/drivers/infiniband/hw/qib/qib_iba6120.c +++ b/drivers/infiniband/hw/qib/qib_iba6120.c @@ -245,7 +245,6 @@ struct qib_chip_specific { u64 iblnkerrsnap; u64 ibcctrl; /* shadow for kr_ibcctrl */ u32 lastlinkrecov; /* link recovery issue */ - int irq; u32 cntrnamelen; u32 portcntrnamelen; u32 ncntrs; @@ -266,6 +265,7 @@ struct qib_chip_specific { u64 rpkts; /* total packets received (sample result) */ u64 xmit_wait; /* # of ticks no data sent (sample result) */ struct timer_list pma_timer; + struct qib_pportdata *ppd; char emsgbuf[128]; char bitsmsgbuf[64]; u8 pma_sample_status; @@ -749,7 +749,6 @@ static void qib_handle_6120_hwerrors(struct qib_devdata *dd, char *msg, u32 bits, ctrl; int isfatal = 0; char *bitsmsg; - int log_idx; hwerrs = qib_read_kreg64(dd, kr_hwerrstatus); if (!hwerrs) @@ -771,11 +770,6 @@ static void qib_handle_6120_hwerrors(struct qib_devdata *dd, char *msg, hwerrs &= dd->cspec->hwerrmask; - /* We log some errors to EEPROM, check if we have any of those. */ - for (log_idx = 0; log_idx < QIB_EEP_LOG_CNT; ++log_idx) - if (hwerrs & dd->eep_st_masks[log_idx].hwerrs_to_log) - qib_inc_eeprom_err(dd, log_idx, 1); - /* * Make sure we get this much out, unless told to be quiet, * or it's occurred within the last 5 seconds. @@ -1005,7 +999,6 @@ static void handle_6120_errors(struct qib_devdata *dd, u64 errs) char *msg; u64 ignore_this_time = 0; u64 iserr = 0; - int log_idx; struct qib_pportdata *ppd = dd->pport; u64 mask; @@ -1016,10 +1009,6 @@ static void handle_6120_errors(struct qib_devdata *dd, u64 errs) /* do these first, they are most important */ if (errs & ERR_MASK(HardwareErr)) qib_handle_6120_hwerrors(dd, msg, sizeof(dd->cspec->emsgbuf)); - else - for (log_idx = 0; log_idx < QIB_EEP_LOG_CNT; ++log_idx) - if (errs & dd->eep_st_masks[log_idx].errs_to_log) - qib_inc_eeprom_err(dd, log_idx, 1); if (errs & ~IB_E_BITSEXTANT) qib_dev_err(dd, @@ -1485,15 +1474,6 @@ static void qib_6120_setup_setextled(struct qib_pportdata *ppd, u32 on) spin_unlock_irqrestore(&dd->cspec->gpio_lock, flags); } -static void qib_6120_free_irq(struct qib_devdata *dd) -{ - if (dd->cspec->irq) { - free_irq(dd->cspec->irq, dd); - dd->cspec->irq = 0; - } - qib_nomsi(dd); -} - /** * qib_6120_setup_cleanup - clean up any per-chip chip-specific stuff * @dd: the qlogic_ib device @@ -1502,7 +1482,7 @@ static void qib_6120_free_irq(struct qib_devdata *dd) */ static void qib_6120_setup_cleanup(struct qib_devdata *dd) { - qib_6120_free_irq(dd); + qib_free_irq(dd); kfree(dd->cspec->cntrs); kfree(dd->cspec->portcntrs); if (dd->cspec->dummy_hdrq) { @@ -1706,6 +1686,8 @@ bail: */ static void qib_setup_6120_interrupt(struct qib_devdata *dd) { + int ret; + /* * If the chip supports added error indication via GPIO pins, * enable interrupts on those bits so the interrupt routine @@ -1719,19 +1701,12 @@ static void qib_setup_6120_interrupt(struct qib_devdata *dd) qib_write_kreg(dd, kr_gpio_mask, dd->cspec->gpio_mask); } - if (!dd->cspec->irq) + ret = pci_request_irq(dd->pcidev, 0, qib_6120intr, NULL, dd, + QIB_DRV_NAME); + if (ret) qib_dev_err(dd, - "irq is 0, BIOS error? Interrupts won't work\n"); - else { - int ret; - - ret = request_irq(dd->cspec->irq, qib_6120intr, 0, - QIB_DRV_NAME, dd); - if (ret) - qib_dev_err(dd, - "Couldn't setup interrupt (irq=%d): %d\n", - dd->cspec->irq, ret); - } + "Couldn't setup interrupt (irq=%d): %d\n", + pci_irq_vector(dd->pcidev, 0), ret); } /** @@ -1929,7 +1904,6 @@ static void qib_6120_put_tid_2(struct qib_devdata *dd, u64 __iomem *tidptr, u32 type, unsigned long pa) { u32 __iomem *tidp32 = (u32 __iomem *)tidptr; - u32 tidx; if (!dd->kregbase) return; @@ -1953,7 +1927,6 @@ static void qib_6120_put_tid_2(struct qib_devdata *dd, u64 __iomem *tidptr, else /* for now, always full 4KB page */ pa |= 2 << 29; } - tidx = tidptr - dd->egrtidbase; writel(pa, tidp32); mmiowb(); } @@ -2647,9 +2620,9 @@ static void qib_chk_6120_errormask(struct qib_devdata *dd) * need traffic_wds done the way it is * called from add_timer */ -static void qib_get_6120_faststats(unsigned long opaque) +static void qib_get_6120_faststats(struct timer_list *t) { - struct qib_devdata *dd = (struct qib_devdata *) opaque; + struct qib_devdata *dd = from_timer(dd, t, stats_timer); struct qib_pportdata *ppd = dd->pport; unsigned long flags; u64 traffic_wds; @@ -2937,10 +2910,10 @@ static int qib_6120_set_loopback(struct qib_pportdata *ppd, const char *what) return ret; } -static void pma_6120_timer(unsigned long data) +static void pma_6120_timer(struct timer_list *t) { - struct qib_pportdata *ppd = (struct qib_pportdata *)data; - struct qib_chip_specific *cs = ppd->dd->cspec; + struct qib_chip_specific *cs = from_timer(cs, t, pma_timer); + struct qib_pportdata *ppd = cs->ppd; struct qib_ibport *ibp = &ppd->ibport_data; unsigned long flags; @@ -3205,6 +3178,7 @@ static int init_6120_variables(struct qib_devdata *dd) dd->num_pports = 1; dd->cspec = (struct qib_chip_specific *)(ppd + dd->num_pports); + dd->cspec->ppd = ppd; ppd->cpspec = NULL; /* not used in this chip */ spin_lock_init(&dd->cspec->kernel_tid_lock); @@ -3242,20 +3216,6 @@ static int init_6120_variables(struct qib_devdata *dd) if (qib_unordered_wc()) dd->flags |= QIB_PIO_FLUSH_WC; - /* - * EEPROM error log 0 is TXE Parity errors. 1 is RXE Parity. - * 2 is Some Misc, 3 is reserved for future. - */ - dd->eep_st_masks[0].hwerrs_to_log = HWE_MASK(TXEMemParityErr); - - /* Ignore errors in PIO/PBC on systems with unordered write-combining */ - if (qib_unordered_wc()) - dd->eep_st_masks[0].hwerrs_to_log &= ~TXE_PIO_PARITY; - - dd->eep_st_masks[1].hwerrs_to_log = HWE_MASK(RXEMemParityErr); - - dd->eep_st_masks[2].errs_to_log = ERR_MASK(ResetNegated); - ret = qib_init_pportdata(ppd, dd, 0, 1); if (ret) goto bail; @@ -3289,11 +3249,8 @@ static int init_6120_variables(struct qib_devdata *dd) dd->rhdrhead_intr_off = 1ULL << 32; /* setup the stats timer; the add_timer is done at end of init */ - setup_timer(&dd->stats_timer, qib_get_6120_faststats, - (unsigned long)dd); - - setup_timer(&dd->cspec->pma_timer, pma_6120_timer, - (unsigned long)ppd); + timer_setup(&dd->stats_timer, qib_get_6120_faststats, 0); + timer_setup(&dd->cspec->pma_timer, pma_6120_timer, 0); dd->ureg_align = qib_read_kreg32(dd, kr_palign); @@ -3490,7 +3447,7 @@ struct qib_devdata *qib_init_iba6120_funcs(struct pci_dev *pdev, dd->f_bringup_serdes = qib_6120_bringup_serdes; dd->f_cleanup = qib_6120_setup_cleanup; dd->f_clear_tids = qib_6120_clear_tids; - dd->f_free_irq = qib_6120_free_irq; + dd->f_free_irq = qib_free_irq; dd->f_get_base_info = qib_6120_get_base_info; dd->f_get_msgheader = qib_6120_get_msgheader; dd->f_getsendbuf = qib_6120_getsendbuf; @@ -3559,8 +3516,6 @@ struct qib_devdata *qib_init_iba6120_funcs(struct pci_dev *pdev, if (qib_pcie_params(dd, 8, NULL)) qib_dev_err(dd, "Failed to setup PCIe or interrupts; continuing anyway\n"); - dd->cspec->irq = pdev->irq; /* save IRQ */ - /* clear diagctrl register, in case diags were running and crashed */ qib_write_kreg(dd, kr_hwdiagctrl, 0); diff --git a/drivers/infiniband/hw/qib/qib_iba7220.c b/drivers/infiniband/hw/qib/qib_iba7220.c index 04bdd3d487b1..bdff2326731e 100644 --- a/drivers/infiniband/hw/qib/qib_iba7220.c +++ b/drivers/infiniband/hw/qib/qib_iba7220.c @@ -1042,9 +1042,11 @@ done: return iserr; } -static void reenable_7220_chase(unsigned long opaque) +static void reenable_7220_chase(struct timer_list *t) { - struct qib_pportdata *ppd = (struct qib_pportdata *)opaque; + struct qib_chippport_specific *cpspec = from_timer(cpspec, t, + chase_timer); + struct qib_pportdata *ppd = &cpspec->pportdata; ppd->cpspec->chase_timer.expires = 0; qib_set_ib_7220_lstate(ppd, QLOGIC_IB_IBCC_LINKCMD_DOWN, @@ -1094,7 +1096,6 @@ static void handle_7220_errors(struct qib_devdata *dd, u64 errs) char *msg; u64 ignore_this_time = 0; u64 iserr = 0; - int log_idx; struct qib_pportdata *ppd = dd->pport; u64 mask; @@ -1105,10 +1106,6 @@ static void handle_7220_errors(struct qib_devdata *dd, u64 errs) /* do these first, they are most important */ if (errs & ERR_MASK(HardwareErr)) qib_7220_handle_hwerrors(dd, msg, sizeof(dd->cspec->emsgbuf)); - else - for (log_idx = 0; log_idx < QIB_EEP_LOG_CNT; ++log_idx) - if (errs & dd->eep_st_masks[log_idx].errs_to_log) - qib_inc_eeprom_err(dd, log_idx, 1); if (errs & QLOGIC_IB_E_SDMAERRS) sdma_7220_errors(ppd, errs); @@ -1302,7 +1299,6 @@ static void qib_7220_handle_hwerrors(struct qib_devdata *dd, char *msg, u32 bits, ctrl; int isfatal = 0; char *bitsmsg; - int log_idx; hwerrs = qib_read_kreg64(dd, kr_hwerrstatus); if (!hwerrs) @@ -1326,10 +1322,6 @@ static void qib_7220_handle_hwerrors(struct qib_devdata *dd, char *msg, hwerrs &= dd->cspec->hwerrmask; - /* We log some errors to EEPROM, check if we have any of those. */ - for (log_idx = 0; log_idx < QIB_EEP_LOG_CNT; ++log_idx) - if (hwerrs & dd->eep_st_masks[log_idx].hwerrs_to_log) - qib_inc_eeprom_err(dd, log_idx, 1); if (hwerrs & ~(TXEMEMPARITYERR_PIOBUF | TXEMEMPARITYERR_PIOPBC | RXE_PARITY)) qib_devinfo(dd->pcidev, @@ -1663,7 +1655,7 @@ static void qib_7220_quiet_serdes(struct qib_pportdata *ppd) dd->control | QLOGIC_IB_C_FREEZEMODE); ppd->cpspec->chase_end = 0; - if (ppd->cpspec->chase_timer.data) /* if initted */ + if (ppd->cpspec->chase_timer.function) /* if initted */ del_timer_sync(&ppd->cpspec->chase_timer); if (ppd->cpspec->ibsymdelta || ppd->cpspec->iblnkerrdelta || @@ -1780,15 +1772,6 @@ static void qib_setup_7220_setextled(struct qib_pportdata *ppd, u32 on) qib_write_kreg(dd, kr_rcvpktledcnt, ledblink); } -static void qib_7220_free_irq(struct qib_devdata *dd) -{ - if (dd->cspec->irq) { - free_irq(dd->cspec->irq, dd); - dd->cspec->irq = 0; - } - qib_nomsi(dd); -} - /* * qib_setup_7220_cleanup - clean up any per-chip chip-specific stuff * @dd: the qlogic_ib device @@ -1798,7 +1781,7 @@ static void qib_7220_free_irq(struct qib_devdata *dd) */ static void qib_setup_7220_cleanup(struct qib_devdata *dd) { - qib_7220_free_irq(dd); + qib_free_irq(dd); kfree(dd->cspec->cntrs); kfree(dd->cspec->portcntrs); } @@ -2026,20 +2009,14 @@ bail: */ static void qib_setup_7220_interrupt(struct qib_devdata *dd) { - if (!dd->cspec->irq) - qib_dev_err(dd, - "irq is 0, BIOS error? Interrupts won't work\n"); - else { - int ret = request_irq(dd->cspec->irq, qib_7220intr, - dd->msi_lo ? 0 : IRQF_SHARED, - QIB_DRV_NAME, dd); + int ret; - if (ret) - qib_dev_err(dd, - "Couldn't setup %s interrupt (irq=%d): %d\n", - dd->msi_lo ? "MSI" : "INTx", - dd->cspec->irq, ret); - } + ret = pci_request_irq(dd->pcidev, 0, qib_7220intr, NULL, dd, + QIB_DRV_NAME); + if (ret) + qib_dev_err(dd, "Couldn't setup %s interrupt (irq=%d): %d\n", + dd->pcidev->msi_enabled ? "MSI" : "INTx", + pci_irq_vector(dd->pcidev, 0), ret); } /** @@ -3263,9 +3240,9 @@ done: * need traffic_wds done the way it is * called from add_timer */ -static void qib_get_7220_faststats(unsigned long opaque) +static void qib_get_7220_faststats(struct timer_list *t) { - struct qib_devdata *dd = (struct qib_devdata *) opaque; + struct qib_devdata *dd = from_timer(dd, t, stats_timer); struct qib_pportdata *ppd = dd->pport; unsigned long flags; u64 traffic_wds; @@ -3302,16 +3279,12 @@ static int qib_7220_intr_fallback(struct qib_devdata *dd) return 0; qib_devinfo(dd->pcidev, - "MSI interrupt not detected, trying INTx interrupts\n"); - qib_7220_free_irq(dd); - qib_enable_intx(dd); - /* - * Some newer kernels require free_irq before disable_msi, - * and irq can be changed during disable and INTx enable - * and we need to therefore use the pcidev->irq value, - * not our saved MSI value. - */ - dd->cspec->irq = dd->pcidev->irq; + "MSI interrupt not detected, trying INTx interrupts\n"); + + qib_free_irq(dd); + dd->msi_lo = 0; + if (pci_alloc_irq_vectors(dd->pcidev, 1, 1, PCI_IRQ_LEGACY) < 0) + qib_dev_err(dd, "Failed to enable INTx\n"); qib_setup_7220_interrupt(dd); return 1; } @@ -3543,7 +3516,6 @@ static void autoneg_7220_work(struct work_struct *work) { struct qib_pportdata *ppd; struct qib_devdata *dd; - u64 startms; u32 i; unsigned long flags; @@ -3551,8 +3523,6 @@ static void autoneg_7220_work(struct work_struct *work) autoneg_work.work)->pportdata; dd = ppd->dd; - startms = jiffies_to_msecs(jiffies); - /* * Busy wait for this first part, it should be at most a * few hundred usec, since we scheduled ourselves for 2msec. @@ -3997,6 +3967,7 @@ static int qib_init_7220_variables(struct qib_devdata *dd) dd->num_pports = 1; dd->cspec = (struct qib_chip_specific *)(cpspec + dd->num_pports); + dd->cspec->dd = dd; ppd->cpspec = cpspec; spin_lock_init(&dd->cspec->sdepb_lock); @@ -4035,16 +4006,6 @@ static int qib_init_7220_variables(struct qib_devdata *dd) dd->flags |= qib_special_trigger ? QIB_USE_SPCL_TRIG : QIB_HAS_SEND_DMA; - /* - * EEPROM error log 0 is TXE Parity errors. 1 is RXE Parity. - * 2 is Some Misc, 3 is reserved for future. - */ - dd->eep_st_masks[0].hwerrs_to_log = HWE_MASK(TXEMemParityErr); - - dd->eep_st_masks[1].hwerrs_to_log = HWE_MASK(RXEMemParityErr); - - dd->eep_st_masks[2].errs_to_log = ERR_MASK(ResetNegated); - init_waitqueue_head(&cpspec->autoneg_wait); INIT_DELAYED_WORK(&cpspec->autoneg_work, autoneg_7220_work); @@ -4069,8 +4030,7 @@ static int qib_init_7220_variables(struct qib_devdata *dd) if (!qib_mini_init) qib_write_kreg(dd, kr_rcvbthqp, QIB_KD_QP); - setup_timer(&ppd->cpspec->chase_timer, reenable_7220_chase, - (unsigned long)ppd); + timer_setup(&ppd->cpspec->chase_timer, reenable_7220_chase, 0); qib_num_cfg_vls = 1; /* if any 7220's, only one VL */ @@ -4095,9 +4055,7 @@ static int qib_init_7220_variables(struct qib_devdata *dd) dd->rhdrhead_intr_off = 1ULL << 32; /* setup the stats timer; the add_timer is done at end of init */ - init_timer(&dd->stats_timer); - dd->stats_timer.function = qib_get_7220_faststats; - dd->stats_timer.data = (unsigned long) dd; + timer_setup(&dd->stats_timer, qib_get_7220_faststats, 0); dd->stats_timer.expires = jiffies + ACTIVITY_TIMER * HZ; /* @@ -4535,7 +4493,7 @@ struct qib_devdata *qib_init_iba7220_funcs(struct pci_dev *pdev, dd->f_bringup_serdes = qib_7220_bringup_serdes; dd->f_cleanup = qib_setup_7220_cleanup; dd->f_clear_tids = qib_7220_clear_tids; - dd->f_free_irq = qib_7220_free_irq; + dd->f_free_irq = qib_free_irq; dd->f_get_base_info = qib_7220_get_base_info; dd->f_get_msgheader = qib_7220_get_msgheader; dd->f_getsendbuf = qib_7220_getsendbuf; @@ -4618,9 +4576,6 @@ struct qib_devdata *qib_init_iba7220_funcs(struct pci_dev *pdev, qib_dev_err(dd, "Failed to setup PCIe or interrupts; continuing anyway\n"); - /* save IRQ for possible later use */ - dd->cspec->irq = pdev->irq; - if (qib_read_kreg64(dd, kr_hwerrstatus) & QLOGIC_IB_HWE_SERDESPLLFAILED) qib_write_kreg(dd, kr_hwerrclear, diff --git a/drivers/infiniband/hw/qib/qib_iba7322.c b/drivers/infiniband/hw/qib/qib_iba7322.c index 14cadf6d6214..c42549d41c6e 100644 --- a/drivers/infiniband/hw/qib/qib_iba7322.c +++ b/drivers/infiniband/hw/qib/qib_iba7322.c @@ -553,7 +553,6 @@ struct qib_chip_specific { u32 updthresh; /* current AvailUpdThld */ u32 updthresh_dflt; /* default AvailUpdThld */ u32 r1; - int irq; u32 num_msix_entries; u32 sdmabufcnt; u32 lastbuf_for_pio; @@ -756,10 +755,8 @@ static void check_7322_rxe_status(struct qib_pportdata *); static u32 __iomem *qib_7322_getsendbuf(struct qib_pportdata *, u64, u32 *); #ifdef CONFIG_INFINIBAND_QIB_DCA static void qib_setup_dca(struct qib_devdata *dd); -static void setup_dca_notifier(struct qib_devdata *dd, - struct qib_msix_entry *m); -static void reset_dca_notifier(struct qib_devdata *dd, - struct qib_msix_entry *m); +static void setup_dca_notifier(struct qib_devdata *dd, int msixnum); +static void reset_dca_notifier(struct qib_devdata *dd, int msixnum); #endif /** @@ -1647,7 +1644,6 @@ static noinline void handle_7322_errors(struct qib_devdata *dd) u64 iserr = 0; u64 errs; u64 mask; - int log_idx; qib_stats.sps_errints++; errs = qib_read_kreg64(dd, kr_errstatus); @@ -1665,10 +1661,7 @@ static noinline void handle_7322_errors(struct qib_devdata *dd) if (errs & QIB_E_HARDWARE) { *msg = '\0'; qib_7322_handle_hwerrors(dd, msg, sizeof(dd->cspec->emsgbuf)); - } else - for (log_idx = 0; log_idx < QIB_EEP_LOG_CNT; ++log_idx) - if (errs & dd->eep_st_masks[log_idx].errs_to_log) - qib_inc_eeprom_err(dd, log_idx, 1); + } if (errs & QIB_E_SPKTERRS) { qib_disarm_7322_senderrbufs(dd->pport); @@ -1739,9 +1732,10 @@ static void qib_error_tasklet(unsigned long data) qib_write_kreg(dd, kr_errmask, dd->cspec->errormask); } -static void reenable_chase(unsigned long opaque) +static void reenable_chase(struct timer_list *t) { - struct qib_pportdata *ppd = (struct qib_pportdata *)opaque; + struct qib_chippport_specific *cp = from_timer(cp, t, chase_timer); + struct qib_pportdata *ppd = cp->ppd; ppd->cpspec->chase_timer.expires = 0; qib_set_ib_7322_lstate(ppd, QLOGIC_IB_IBCC_LINKCMD_DOWN, @@ -2531,7 +2525,7 @@ static void qib_7322_mini_quiet_serdes(struct qib_pportdata *ppd) cancel_delayed_work_sync(&ppd->cpspec->ipg_work); ppd->cpspec->chase_end = 0; - if (ppd->cpspec->chase_timer.data) /* if initted */ + if (ppd->cpspec->chase_timer.function) /* if initted */ del_timer_sync(&ppd->cpspec->chase_timer); /* @@ -2778,7 +2772,7 @@ static void qib_setup_dca(struct qib_devdata *dd) qib_write_kreg(dd, KREG_IDX(DCACtrlB) + i, cspec->dca_rcvhdr_ctrl[i]); for (i = 0; i < cspec->num_msix_entries; i++) - setup_dca_notifier(dd, &cspec->msix_entries[i]); + setup_dca_notifier(dd, i); } static void qib_irq_notifier_notify(struct irq_affinity_notify *notify, @@ -2820,49 +2814,41 @@ static void qib_irq_notifier_release(struct kref *ref) } #endif -/* - * Disable MSIx interrupt if enabled, call generic MSIx code - * to cleanup, and clear pending MSIx interrupts. - * Used for fallback to INTx, after reset, and when MSIx setup fails. - */ -static void qib_7322_nomsix(struct qib_devdata *dd) +static void qib_7322_free_irq(struct qib_devdata *dd) { u64 intgranted; - int n; + int i; dd->cspec->main_int_mask = ~0ULL; - n = dd->cspec->num_msix_entries; - if (n) { - int i; - dd->cspec->num_msix_entries = 0; - for (i = 0; i < n; i++) { + for (i = 0; i < dd->cspec->num_msix_entries; i++) { + /* only free IRQs that were allocated */ + if (dd->cspec->msix_entries[i].arg) { #ifdef CONFIG_INFINIBAND_QIB_DCA - reset_dca_notifier(dd, &dd->cspec->msix_entries[i]); + reset_dca_notifier(dd, i); #endif - irq_set_affinity_hint( - dd->cspec->msix_entries[i].irq, NULL); + irq_set_affinity_hint(pci_irq_vector(dd->pcidev, i), + NULL); free_cpumask_var(dd->cspec->msix_entries[i].mask); - free_irq(dd->cspec->msix_entries[i].irq, - dd->cspec->msix_entries[i].arg); + pci_free_irq(dd->pcidev, i, + dd->cspec->msix_entries[i].arg); } - qib_nomsix(dd); } + + /* If num_msix_entries was 0, disable the INTx IRQ */ + if (!dd->cspec->num_msix_entries) + pci_free_irq(dd->pcidev, 0, dd); + else + dd->cspec->num_msix_entries = 0; + + pci_free_irq_vectors(dd->pcidev); + /* make sure no MSIx interrupts are left pending */ intgranted = qib_read_kreg64(dd, kr_intgranted); if (intgranted) qib_write_kreg(dd, kr_intgranted, intgranted); } -static void qib_7322_free_irq(struct qib_devdata *dd) -{ - if (dd->cspec->irq) { - free_irq(dd->cspec->irq, dd); - dd->cspec->irq = 0; - } - qib_7322_nomsix(dd); -} - static void qib_setup_7322_cleanup(struct qib_devdata *dd) { int i; @@ -3329,22 +3315,20 @@ static irqreturn_t sdma_cleanup_intr(int irq, void *data) #ifdef CONFIG_INFINIBAND_QIB_DCA -static void reset_dca_notifier(struct qib_devdata *dd, struct qib_msix_entry *m) +static void reset_dca_notifier(struct qib_devdata *dd, int msixnum) { - if (!m->dca) + if (!dd->cspec->msix_entries[msixnum].dca) return; - qib_devinfo(dd->pcidev, - "Disabling notifier on HCA %d irq %d\n", - dd->unit, - m->irq); - irq_set_affinity_notifier( - m->irq, - NULL); - m->notifier = NULL; + + qib_devinfo(dd->pcidev, "Disabling notifier on HCA %d irq %d\n", + dd->unit, pci_irq_vector(dd->pcidev, msixnum)); + irq_set_affinity_notifier(pci_irq_vector(dd->pcidev, msixnum), NULL); + dd->cspec->msix_entries[msixnum].notifier = NULL; } -static void setup_dca_notifier(struct qib_devdata *dd, struct qib_msix_entry *m) +static void setup_dca_notifier(struct qib_devdata *dd, int msixnum) { + struct qib_msix_entry *m = &dd->cspec->msix_entries[msixnum]; struct qib_irq_notify *n; if (!m->dca) @@ -3354,7 +3338,7 @@ static void setup_dca_notifier(struct qib_devdata *dd, struct qib_msix_entry *m) int ret; m->notifier = n; - n->notify.irq = m->irq; + n->notify.irq = pci_irq_vector(dd->pcidev, msixnum); n->notify.notify = qib_irq_notifier_notify; n->notify.release = qib_irq_notifier_release; n->arg = m->arg; @@ -3415,22 +3399,17 @@ static void qib_setup_7322_interrupt(struct qib_devdata *dd, int clearpend) if (!dd->cspec->num_msix_entries) { /* Try to get INTx interrupt */ try_intx: - if (!dd->pcidev->irq) { - qib_dev_err(dd, - "irq is 0, BIOS error? Interrupts won't work\n"); - goto bail; - } - ret = request_irq(dd->pcidev->irq, qib_7322intr, - IRQF_SHARED, QIB_DRV_NAME, dd); + ret = pci_request_irq(dd->pcidev, 0, qib_7322intr, NULL, dd, + QIB_DRV_NAME); if (ret) { - qib_dev_err(dd, + qib_dev_err( + dd, "Couldn't setup INTx interrupt (irq=%d): %d\n", - dd->pcidev->irq, ret); - goto bail; + pci_irq_vector(dd->pcidev, 0), ret); + return; } - dd->cspec->irq = dd->pcidev->irq; dd->cspec->main_int_mask = ~0ULL; - goto bail; + return; } /* Try to get MSIx interrupts */ @@ -3453,15 +3432,10 @@ try_intx: for (i = 0; msixnum < dd->cspec->num_msix_entries; i++) { irq_handler_t handler; void *arg; - u64 val; int lsb, reg, sh; #ifdef CONFIG_INFINIBAND_QIB_DCA int dca = 0; #endif - - dd->cspec->msix_entries[msixnum]. - name[sizeof(dd->cspec->msix_entries[msixnum].name) - 1] - = '\0'; if (i < ARRAY_SIZE(irq_table)) { if (irq_table[i].port) { /* skip if for a non-configured port */ @@ -3475,11 +3449,10 @@ try_intx: #endif lsb = irq_table[i].lsb; handler = irq_table[i].handler; - snprintf(dd->cspec->msix_entries[msixnum].name, - sizeof(dd->cspec->msix_entries[msixnum].name) - - 1, - QIB_DRV_NAME "%d%s", dd->unit, - irq_table[i].name); + ret = pci_request_irq(dd->pcidev, msixnum, handler, + NULL, arg, QIB_DRV_NAME "%d%s", + dd->unit, + irq_table[i].name); } else { unsigned ctxt; @@ -3495,37 +3468,25 @@ try_intx: #endif lsb = QIB_I_RCVAVAIL_LSB + ctxt; handler = qib_7322pintr; - snprintf(dd->cspec->msix_entries[msixnum].name, - sizeof(dd->cspec->msix_entries[msixnum].name) - - 1, - QIB_DRV_NAME "%d (kctx)", dd->unit); + ret = pci_request_irq(dd->pcidev, msixnum, handler, + NULL, arg, + QIB_DRV_NAME "%d (kctx)", + dd->unit); } - dd->cspec->msix_entries[msixnum].irq = pci_irq_vector( - dd->pcidev, msixnum); - if (dd->cspec->msix_entries[msixnum].irq < 0) { - qib_dev_err(dd, - "Couldn't get MSIx irq (vec=%d): %d\n", - msixnum, - dd->cspec->msix_entries[msixnum].irq); - qib_7322_nomsix(dd); - goto try_intx; - } - ret = request_irq(dd->cspec->msix_entries[msixnum].irq, - handler, 0, - dd->cspec->msix_entries[msixnum].name, - arg); if (ret) { /* * Shouldn't happen since the enable said we could * have as many as we are trying to setup here. */ qib_dev_err(dd, - "Couldn't setup MSIx interrupt (vec=%d, irq=%d): %d\n", - msixnum, - dd->cspec->msix_entries[msixnum].irq, - ret); - qib_7322_nomsix(dd); + "Couldn't setup MSIx interrupt (vec=%d, irq=%d): %d\n", + msixnum, + pci_irq_vector(dd->pcidev, msixnum), + ret); + qib_7322_free_irq(dd); + pci_alloc_irq_vectors(dd->pcidev, 1, 1, + PCI_IRQ_LEGACY); goto try_intx; } dd->cspec->msix_entries[msixnum].arg = arg; @@ -3541,8 +3502,8 @@ try_intx: mask &= ~(1ULL << lsb); redirect[reg] |= ((u64) msixnum) << sh; } - val = qib_read_kreg64(dd, 2 * msixnum + 1 + - (QIB_7322_MsixTable_OFFS / sizeof(u64))); + qib_read_kreg64(dd, 2 * msixnum + 1 + + (QIB_7322_MsixTable_OFFS / sizeof(u64))); if (firstcpu < nr_cpu_ids && zalloc_cpumask_var( &dd->cspec->msix_entries[msixnum].mask, @@ -3559,7 +3520,7 @@ try_intx: dd->cspec->msix_entries[msixnum].mask); } irq_set_affinity_hint( - dd->cspec->msix_entries[msixnum].irq, + pci_irq_vector(dd->pcidev, msixnum), dd->cspec->msix_entries[msixnum].mask); } msixnum++; @@ -3570,7 +3531,6 @@ try_intx: dd->cspec->main_int_mask = mask; tasklet_init(&dd->error_tasklet, qib_error_tasklet, (unsigned long)dd); -bail:; } /** @@ -3674,8 +3634,9 @@ static int qib_do_7322_reset(struct qib_devdata *dd) /* no interrupts till re-initted */ qib_7322_set_intr_state(dd, 0); + qib_7322_free_irq(dd); + if (msix_entries) { - qib_7322_nomsix(dd); /* can be up to 512 bytes, too big for stack */ msix_vecsave = kmalloc(2 * dd->cspec->num_msix_entries * sizeof(u64), GFP_KERNEL); @@ -3765,11 +3726,11 @@ static int qib_do_7322_reset(struct qib_devdata *dd) write_7322_init_portregs(&dd->pport[i]); write_7322_initregs(dd); - if (qib_pcie_params(dd, dd->lbus_width, - &dd->cspec->num_msix_entries)) + if (qib_pcie_params(dd, dd->lbus_width, &msix_entries)) qib_dev_err(dd, "Reset failed to setup PCIe or interrupts; continuing anyway\n"); + dd->cspec->num_msix_entries = msix_entries; qib_setup_7322_interrupt(dd, 1); for (i = 0; i < dd->num_pports; ++i) { @@ -5138,9 +5099,9 @@ done: * * called from add_timer */ -static void qib_get_7322_faststats(unsigned long opaque) +static void qib_get_7322_faststats(struct timer_list *t) { - struct qib_devdata *dd = (struct qib_devdata *) opaque; + struct qib_devdata *dd = from_timer(dd, t, stats_timer); struct qib_pportdata *ppd; unsigned long flags; u64 traffic_wds; @@ -5197,8 +5158,9 @@ static int qib_7322_intr_fallback(struct qib_devdata *dd) qib_devinfo(dd->pcidev, "MSIx interrupt not detected, trying INTx interrupts\n"); - qib_7322_nomsix(dd); - qib_enable_intx(dd); + qib_7322_free_irq(dd); + if (pci_alloc_irq_vectors(dd->pcidev, 1, 1, PCI_IRQ_LEGACY) < 0) + qib_dev_err(dd, "Failed to enable INTx\n"); qib_setup_7322_interrupt(dd, 0); return 1; } @@ -5396,16 +5358,11 @@ static void try_7322_autoneg(struct qib_pportdata *ppd) static void autoneg_7322_work(struct work_struct *work) { struct qib_pportdata *ppd; - struct qib_devdata *dd; - u64 startms; u32 i; unsigned long flags; ppd = container_of(work, struct qib_chippport_specific, autoneg_work.work)->ppd; - dd = ppd->dd; - - startms = jiffies_to_msecs(jiffies); /* * Busy wait for this first part, it should be at most a @@ -6614,8 +6571,7 @@ static int qib_init_7322_variables(struct qib_devdata *dd) if (!qib_mini_init) write_7322_init_portregs(ppd); - setup_timer(&cp->chase_timer, reenable_chase, - (unsigned long)ppd); + timer_setup(&cp->chase_timer, reenable_chase, 0); ppd++; } @@ -6641,8 +6597,7 @@ static int qib_init_7322_variables(struct qib_devdata *dd) (u64) rcv_int_count << IBA7322_HDRHEAD_PKTINT_SHIFT; /* setup the stats timer; the add_timer is done at end of init */ - setup_timer(&dd->stats_timer, qib_get_7322_faststats, - (unsigned long)dd); + timer_setup(&dd->stats_timer, qib_get_7322_faststats, 0); dd->ureg_align = 0x10000; /* 64KB alignment */ @@ -7845,13 +7800,12 @@ static void ibsd_wr_allchans(struct qib_pportdata *ppd, int addr, unsigned data, { struct qib_devdata *dd = ppd->dd; int chan; - u32 rbc; for (chan = 0; chan < SERDES_CHANS; ++chan) { ahb_mod(dd, IBSD(ppd->hw_pidx), (chan + (chan >> 1)), addr, data, mask); - rbc = ahb_mod(dd, IBSD(ppd->hw_pidx), (chan + (chan >> 1)), - addr, 0, 0); + ahb_mod(dd, IBSD(ppd->hw_pidx), (chan + (chan >> 1)), addr, + 0, 0); } } diff --git a/drivers/infiniband/hw/qib/qib_init.c b/drivers/infiniband/hw/qib/qib_init.c index c5a4c65636d6..5243ad30dfc0 100644 --- a/drivers/infiniband/hw/qib/qib_init.c +++ b/drivers/infiniband/hw/qib/qib_init.c @@ -93,7 +93,7 @@ unsigned qib_cc_table_size; module_param_named(cc_table_size, qib_cc_table_size, uint, S_IRUGO); MODULE_PARM_DESC(cc_table_size, "Congestion control table entries 0 (CCA disabled - default), min = 128, max = 1984"); -static void verify_interrupt(unsigned long); +static void verify_interrupt(struct timer_list *); static struct idr qib_unit_table; u32 qib_cpulist_count; @@ -233,8 +233,7 @@ int qib_init_pportdata(struct qib_pportdata *ppd, struct qib_devdata *dd, spin_lock_init(&ppd->cc_shadow_lock); init_waitqueue_head(&ppd->state_wait); - setup_timer(&ppd->symerr_clear_timer, qib_clear_symerror_on_linkup, - (unsigned long)ppd); + timer_setup(&ppd->symerr_clear_timer, qib_clear_symerror_on_linkup, 0); ppd->qib_wq = NULL; ppd->ibport_data.pmastats = @@ -428,8 +427,7 @@ static int loadtime_init(struct qib_devdata *dd) qib_get_eeprom_info(dd); /* setup time (don't start yet) to verify we got interrupt */ - setup_timer(&dd->intrchk_timer, verify_interrupt, - (unsigned long)dd); + timer_setup(&dd->intrchk_timer, verify_interrupt, 0); done: return ret; } @@ -493,9 +491,9 @@ static void enable_chip(struct qib_devdata *dd) } } -static void verify_interrupt(unsigned long opaque) +static void verify_interrupt(struct timer_list *t) { - struct qib_devdata *dd = (struct qib_devdata *) opaque; + struct qib_devdata *dd = from_timer(dd, t, intrchk_timer); u64 int_counter; if (!dd) @@ -753,8 +751,7 @@ done: continue; if (dd->flags & QIB_HAS_SEND_DMA) ret = qib_setup_sdma(ppd); - setup_timer(&ppd->hol_timer, qib_hol_event, - (unsigned long)ppd); + timer_setup(&ppd->hol_timer, qib_hol_event, 0); ppd->hol_state = QIB_HOL_UP; } @@ -815,23 +812,19 @@ static void qib_stop_timers(struct qib_devdata *dd) struct qib_pportdata *ppd; int pidx; - if (dd->stats_timer.data) { + if (dd->stats_timer.function) del_timer_sync(&dd->stats_timer); - dd->stats_timer.data = 0; - } - if (dd->intrchk_timer.data) { + if (dd->intrchk_timer.function) del_timer_sync(&dd->intrchk_timer); - dd->intrchk_timer.data = 0; - } for (pidx = 0; pidx < dd->num_pports; ++pidx) { ppd = dd->pport + pidx; - if (ppd->hol_timer.data) + if (ppd->hol_timer.function) del_timer_sync(&ppd->hol_timer); - if (ppd->led_override_timer.data) { + if (ppd->led_override_timer.function) { del_timer_sync(&ppd->led_override_timer); atomic_set(&ppd->led_override_timer_active, 0); } - if (ppd->symerr_clear_timer.data) + if (ppd->symerr_clear_timer.function) del_timer_sync(&ppd->symerr_clear_timer); } } diff --git a/drivers/infiniband/hw/qib/qib_intr.c b/drivers/infiniband/hw/qib/qib_intr.c index a014fd4cd076..65c3b964ad1b 100644 --- a/drivers/infiniband/hw/qib/qib_intr.c +++ b/drivers/infiniband/hw/qib/qib_intr.c @@ -141,7 +141,7 @@ void qib_handle_e_ibstatuschanged(struct qib_pportdata *ppd, u64 ibcs) qib_hol_up(ppd); /* useful only for 6120 now */ *ppd->statusp |= QIB_STATUS_IB_READY | QIB_STATUS_IB_CONF; - qib_clear_symerror_on_linkup((unsigned long)ppd); + qib_clear_symerror_on_linkup(&ppd->symerr_clear_timer); spin_lock_irqsave(&ppd->lflags_lock, flags); ppd->lflags |= QIBL_LINKACTIVE | QIBL_LINKV; ppd->lflags &= ~(QIBL_LINKINIT | @@ -170,9 +170,9 @@ skip_ibchange: signal_ib_event(ppd, ev); } -void qib_clear_symerror_on_linkup(unsigned long opaque) +void qib_clear_symerror_on_linkup(struct timer_list *t) { - struct qib_pportdata *ppd = (struct qib_pportdata *)opaque; + struct qib_pportdata *ppd = from_timer(ppd, t, symerr_clear_timer); if (ppd->lflags & QIBL_LINKACTIVE) return; diff --git a/drivers/infiniband/hw/qib/qib_mad.c b/drivers/infiniband/hw/qib/qib_mad.c index 82d9da9b6997..4845d000c22f 100644 --- a/drivers/infiniband/hw/qib/qib_mad.c +++ b/drivers/infiniband/hw/qib/qib_mad.c @@ -280,7 +280,7 @@ static int subn_get_nodeinfo(struct ib_smp *smp, struct ib_device *ibdev, { struct ib_node_info *nip = (struct ib_node_info *)&smp->data; struct qib_devdata *dd = dd_from_ibdev(ibdev); - u32 vendor, majrev, minrev; + u32 majrev, minrev; unsigned pidx = port - 1; /* IB number port from 1, hdw from 0 */ /* GUID 0 is illegal */ @@ -303,7 +303,6 @@ static int subn_get_nodeinfo(struct ib_smp *smp, struct ib_device *ibdev, minrev = dd->minrev; nip->revision = cpu_to_be32((majrev << 16) | minrev); nip->local_port_num = port; - vendor = dd->vendorid; nip->vendor_id[0] = QIB_SRC_OUI_1; nip->vendor_id[1] = QIB_SRC_OUI_2; nip->vendor_id[2] = QIB_SRC_OUI_3; @@ -434,6 +433,7 @@ static int check_mkey(struct qib_ibport *ibp, struct ib_smp *smp, int mad_flags) /* Bad mkey not a violation below level 2 */ if (ibp->rvp.mkeyprot < 2) break; + /* fall through */ case IB_MGMT_METHOD_SET: case IB_MGMT_METHOD_TRAP_REPRESS: if (ibp->rvp.mkey_violations != 0xFFFF) @@ -2446,9 +2446,9 @@ bail: return ret; } -static void xmit_wait_timer_func(unsigned long opaque) +static void xmit_wait_timer_func(struct timer_list *t) { - struct qib_pportdata *ppd = (struct qib_pportdata *)opaque; + struct qib_pportdata *ppd = from_timer(ppd, t, cong_stats.timer); struct qib_devdata *dd = dd_from_ppd(ppd); unsigned long flags; u8 status; @@ -2478,10 +2478,8 @@ void qib_notify_create_mad_agent(struct rvt_dev_info *rdi, int port_idx) /* Initialize xmit_wait structure */ dd->pport[port_idx].cong_stats.counter = 0; - init_timer(&dd->pport[port_idx].cong_stats.timer); - dd->pport[port_idx].cong_stats.timer.function = xmit_wait_timer_func; - dd->pport[port_idx].cong_stats.timer.data = - (unsigned long)(&dd->pport[port_idx]); + timer_setup(&dd->pport[port_idx].cong_stats.timer, + xmit_wait_timer_func, 0); dd->pport[port_idx].cong_stats.timer.expires = 0; add_timer(&dd->pport[port_idx].cong_stats.timer); } @@ -2492,7 +2490,7 @@ void qib_notify_free_mad_agent(struct rvt_dev_info *rdi, int port_idx) struct qib_devdata *dd = container_of(ibdev, struct qib_devdata, verbs_dev); - if (dd->pport[port_idx].cong_stats.timer.data) + if (dd->pport[port_idx].cong_stats.timer.function) del_timer_sync(&dd->pport[port_idx].cong_stats.timer); if (dd->pport[port_idx].ibport_data.smi_ah) diff --git a/drivers/infiniband/hw/qib/qib_pcie.c b/drivers/infiniband/hw/qib/qib_pcie.c index d90403e31a9d..5ac7b31c346b 100644 --- a/drivers/infiniband/hw/qib/qib_pcie.c +++ b/drivers/infiniband/hw/qib/qib_pcie.c @@ -193,7 +193,7 @@ void qib_pcie_ddcleanup(struct qib_devdata *dd) * chip reset (the kernel PCI infrastructure doesn't yet handle that * correctly. */ -static void qib_msi_setup(struct qib_devdata *dd, int pos) +static void qib_cache_msi_info(struct qib_devdata *dd, int pos) { struct pci_dev *pdev = dd->pcidev; u16 control; @@ -208,64 +208,39 @@ static void qib_msi_setup(struct qib_devdata *dd, int pos) &dd->msi_data); } -static int qib_allocate_irqs(struct qib_devdata *dd, u32 maxvec) -{ - unsigned int flags = PCI_IRQ_LEGACY; - - /* Check our capabilities */ - if (dd->pcidev->msix_cap) { - flags |= PCI_IRQ_MSIX; - } else { - if (dd->pcidev->msi_cap) { - flags |= PCI_IRQ_MSI; - /* Get msi_lo and msi_hi */ - qib_msi_setup(dd, dd->pcidev->msi_cap); - } - } - - if (!(flags & (PCI_IRQ_MSIX | PCI_IRQ_MSI))) - qib_dev_err(dd, "No PCI MSI or MSIx capability!\n"); - - return pci_alloc_irq_vectors(dd->pcidev, 1, maxvec, flags); -} - int qib_pcie_params(struct qib_devdata *dd, u32 minw, u32 *nent) { u16 linkstat, speed; int nvec; int maxvec; - int ret = 0; + unsigned int flags = PCI_IRQ_MSIX | PCI_IRQ_MSI; if (!pci_is_pcie(dd->pcidev)) { qib_dev_err(dd, "Can't find PCI Express capability!\n"); /* set up something... */ dd->lbus_width = 1; dd->lbus_speed = 2500; /* Gen1, 2.5GHz */ - ret = -1; + nvec = -1; goto bail; } + if (dd->flags & QIB_HAS_INTX) + flags |= PCI_IRQ_LEGACY; maxvec = (nent && *nent) ? *nent : 1; - nvec = qib_allocate_irqs(dd, maxvec); - if (nvec < 0) { - ret = nvec; + nvec = pci_alloc_irq_vectors(dd->pcidev, 1, maxvec, flags); + if (nvec < 0) goto bail; - } /* - * If nent exists, make sure to record how many vectors were allocated + * If nent exists, make sure to record how many vectors were allocated. + * If msix_enabled is false, return 0 so the fallback code works + * correctly. */ - if (nent) { - *nent = nvec; + if (nent) + *nent = !dd->pcidev->msix_enabled ? 0 : nvec; - /* - * If we requested (nent) MSIX, but msix_enabled is not set, - * pci_alloc_irq_vectors() enabled INTx. - */ - if (!dd->pcidev->msix_enabled) - qib_dev_err(dd, - "no msix vectors allocated, using INTx\n"); - } + if (dd->pcidev->msi_enabled) + qib_cache_msi_info(dd, dd->pcidev->msi_cap); pcie_capability_read_word(dd->pcidev, PCI_EXP_LNKSTA, &linkstat); /* @@ -306,7 +281,21 @@ bail: /* fill in string, even on errors */ snprintf(dd->lbus_info, sizeof(dd->lbus_info), "PCIe,%uMHz,x%u\n", dd->lbus_speed, dd->lbus_width); - return ret; + return nvec < 0 ? nvec : 0; +} + +/** + * qib_free_irq - Cleanup INTx and MSI interrupts + * @dd: valid pointer to qib dev data + * + * Since cleanup for INTx and MSI interrupts is trivial, have a common + * routine. + * + */ +void qib_free_irq(struct qib_devdata *dd) +{ + pci_free_irq(dd->pcidev, 0, dd); + pci_free_irq_vectors(dd->pcidev); } /* @@ -351,10 +340,10 @@ int qib_reinit_intr(struct qib_devdata *dd) dd->msi_data); ret = 1; bail: - if (!ret && (dd->flags & QIB_HAS_INTX)) { - qib_enable_intx(dd); + qib_free_irq(dd); + + if (!ret && (dd->flags & QIB_HAS_INTX)) ret = 1; - } /* and now set the pci master bit again */ pci_set_master(dd->pcidev); @@ -363,56 +352,6 @@ bail: } /* - * Disable msi interrupt if enabled, and clear msi_lo. - * This is used primarily for the fallback to INTx, but - * is also used in reinit after reset, and during cleanup. - */ -void qib_nomsi(struct qib_devdata *dd) -{ - dd->msi_lo = 0; - pci_free_irq_vectors(dd->pcidev); -} - -/* - * Same as qib_nosmi, but for MSIx. - */ -void qib_nomsix(struct qib_devdata *dd) -{ - pci_free_irq_vectors(dd->pcidev); -} - -/* - * Similar to pci_intx(pdev, 1), except that we make sure - * msi(x) is off. - */ -void qib_enable_intx(struct qib_devdata *dd) -{ - u16 cw, new; - int pos; - struct pci_dev *pdev = dd->pcidev; - - if (pci_alloc_irq_vectors(pdev, 1, 1, PCI_IRQ_LEGACY) < 0) - qib_dev_err(dd, "Failed to enable INTx\n"); - - pos = pdev->msi_cap; - if (pos) { - /* then turn off MSI */ - pci_read_config_word(pdev, pos + PCI_MSI_FLAGS, &cw); - new = cw & ~PCI_MSI_FLAGS_ENABLE; - if (new != cw) - pci_write_config_word(pdev, pos + PCI_MSI_FLAGS, new); - } - pos = pdev->msix_cap; - if (pos) { - /* then turn off MSIx */ - pci_read_config_word(pdev, pos + PCI_MSIX_FLAGS, &cw); - new = cw & ~PCI_MSIX_FLAGS_ENABLE; - if (new != cw) - pci_write_config_word(pdev, pos + PCI_MSIX_FLAGS, new); - } -} - -/* * These two routines are helper routines for the device reset code * to move all the pcie code out of the chip-specific driver code. */ @@ -458,7 +397,6 @@ MODULE_PARM_DESC(pcie_coalesce, "tune PCIe colescing on some Intel chipsets"); */ static void qib_tune_pcie_coalesce(struct qib_devdata *dd) { - int r; struct pci_dev *parent; u16 devid; u32 mask, bits, val; @@ -513,7 +451,7 @@ static void qib_tune_pcie_coalesce(struct qib_devdata *dd) pci_read_config_dword(parent, 0x48, &val); val &= ~mask; val |= bits; - r = pci_write_config_dword(parent, 0x48, val); + pci_write_config_dword(parent, 0x48, val); } /* diff --git a/drivers/infiniband/hw/qib/qib_rc.c b/drivers/infiniband/hw/qib/qib_rc.c index e9a91736b12d..8f5754fb8579 100644 --- a/drivers/infiniband/hw/qib/qib_rc.c +++ b/drivers/infiniband/hw/qib/qib_rc.c @@ -1869,7 +1869,7 @@ send_middle: qp->r_rcv_len = 0; if (opcode == OP(SEND_ONLY)) goto no_immediate_data; - /* FALLTHROUGH for SEND_ONLY_WITH_IMMEDIATE */ + /* fall through -- for SEND_ONLY_WITH_IMMEDIATE */ case OP(SEND_LAST_WITH_IMMEDIATE): send_last_imm: wc.ex.imm_data = ohdr->u.imm_data; diff --git a/drivers/infiniband/hw/qib/qib_sd7220.c b/drivers/infiniband/hw/qib/qib_sd7220.c index c72775f27212..12caf3db8c34 100644 --- a/drivers/infiniband/hw/qib/qib_sd7220.c +++ b/drivers/infiniband/hw/qib/qib_sd7220.c @@ -755,7 +755,6 @@ static int qib_sd7220_ram_xfer(struct qib_devdata *dd, int sdnum, u32 loc, int addr; int ret; unsigned long flags; - const char *op; /* Pick appropriate transaction reg and "Chip select" for this serdes */ switch (sdnum) { @@ -775,7 +774,6 @@ static int qib_sd7220_ram_xfer(struct qib_devdata *dd, int sdnum, u32 loc, return -1; } - op = rd_notwr ? "Rd" : "Wr"; spin_lock_irqsave(&dd->cspec->sdepb_lock, flags); owned = epb_access(dd, sdnum, 1); @@ -1390,11 +1388,11 @@ module_param_named(relock_by_timer, qib_relock_by_timer, uint, S_IWUSR | S_IRUGO); MODULE_PARM_DESC(relock_by_timer, "Allow relock attempt if link not up"); -static void qib_run_relock(unsigned long opaque) +static void qib_run_relock(struct timer_list *t) { - struct qib_devdata *dd = (struct qib_devdata *)opaque; + struct qib_chip_specific *cs = from_timer(cs, t, relock_timer); + struct qib_devdata *dd = cs->dd; struct qib_pportdata *ppd = dd->pport; - struct qib_chip_specific *cs = dd->cspec; int timeoff; /* @@ -1440,9 +1438,7 @@ void set_7220_relock_poll(struct qib_devdata *dd, int ibup) /* If timer has not yet been started, do so. */ if (!cs->relock_timer_active) { cs->relock_timer_active = 1; - init_timer(&cs->relock_timer); - cs->relock_timer.function = qib_run_relock; - cs->relock_timer.data = (unsigned long) dd; + timer_setup(&cs->relock_timer, qib_run_relock, 0); cs->relock_interval = timeout; cs->relock_timer.expires = jiffies + timeout; add_timer(&cs->relock_timer); diff --git a/drivers/infiniband/hw/qib/qib_sdma.c b/drivers/infiniband/hw/qib/qib_sdma.c index 891873b38a1e..c3690bd51582 100644 --- a/drivers/infiniband/hw/qib/qib_sdma.c +++ b/drivers/infiniband/hw/qib/qib_sdma.c @@ -808,7 +808,7 @@ void __qib_sdma_process_event(struct qib_pportdata *ppd, * bringing the link up with traffic active on * 7220, e.g. */ ss->go_s99_running = 1; - /* fall through and start dma engine */ + /* fall through -- and start dma engine */ case qib_sdma_event_e10_go_hw_start: /* This reference means the state machine is started */ sdma_get(&ppd->sdma_state); diff --git a/drivers/infiniband/hw/qib/qib_tx.c b/drivers/infiniband/hw/qib/qib_tx.c index eface3b3dacf..29785eb84646 100644 --- a/drivers/infiniband/hw/qib/qib_tx.c +++ b/drivers/infiniband/hw/qib/qib_tx.c @@ -179,8 +179,6 @@ void qib_disarm_piobufs_set(struct qib_devdata *dd, unsigned long *mask, pppd[i] = NULL; for (i = 0; i < cnt; i++) { - int which; - if (!test_bit(i, mask)) continue; /* @@ -201,9 +199,7 @@ void qib_disarm_piobufs_set(struct qib_devdata *dd, unsigned long *mask, (!test_bit(i << 1, dd->pioavailkernel) && find_ctxt(dd, i))) { __set_bit(i, dd->pio_need_disarm); - which = 0; } else { - which = 1; dd->f_sendctrl(dd->pport, QIB_SENDCTRL_DISARM_BUF(i)); } spin_unlock_irqrestore(&dd->pioavail_lock, flags); @@ -552,9 +548,9 @@ void qib_hol_up(struct qib_pportdata *ppd) /* * This is only called via the timer. */ -void qib_hol_event(unsigned long opaque) +void qib_hol_event(struct timer_list *t) { - struct qib_pportdata *ppd = (struct qib_pportdata *)opaque; + struct qib_pportdata *ppd = from_timer(ppd, t, hol_timer); /* If hardware error, etc, skip. */ if (!(ppd->dd->flags & QIB_INITTED)) diff --git a/drivers/infiniband/hw/qib/qib_verbs.c b/drivers/infiniband/hw/qib/qib_verbs.c index 9d92aeb8d9a1..c55000501582 100644 --- a/drivers/infiniband/hw/qib/qib_verbs.c +++ b/drivers/infiniband/hw/qib/qib_verbs.c @@ -389,9 +389,9 @@ drop: * This is called from a timer to check for QPs * which need kernel memory in order to send a packet. */ -static void mem_timer(unsigned long data) +static void mem_timer(struct timer_list *t) { - struct qib_ibdev *dev = (struct qib_ibdev *) data; + struct qib_ibdev *dev = from_timer(dev, t, mem_timer); struct list_head *list = &dev->memwait; struct rvt_qp *qp = NULL; struct qib_qp_priv *priv = NULL; @@ -701,7 +701,7 @@ void qib_put_txreq(struct qib_verbs_txreq *tx) */ void qib_verbs_sdma_desc_avail(struct qib_pportdata *ppd, unsigned avail) { - struct rvt_qp *qp, *nqp; + struct rvt_qp *qp; struct qib_qp_priv *qpp, *nqpp; struct rvt_qp *qps[20]; struct qib_ibdev *dev; @@ -714,7 +714,6 @@ void qib_verbs_sdma_desc_avail(struct qib_pportdata *ppd, unsigned avail) /* Search wait list for first QP wanting DMA descriptors. */ list_for_each_entry_safe(qpp, nqpp, &dev->dmawait, iowait) { qp = qpp->owner; - nqp = nqpp->owner; if (qp->port_num != ppd->port) continue; if (n == ARRAY_SIZE(qps)) @@ -1532,7 +1531,7 @@ int qib_register_ib_device(struct qib_devdata *dd) init_ibport(ppd + i); /* Only need to initialize non-zero fields. */ - setup_timer(&dev->mem_timer, mem_timer, (unsigned long)dev); + timer_setup(&dev->mem_timer, mem_timer, 0); INIT_LIST_HEAD(&dev->piowait); INIT_LIST_HEAD(&dev->dmawait); diff --git a/drivers/infiniband/hw/usnic/usnic_ib_qp_grp.c b/drivers/infiniband/hw/usnic/usnic_ib_qp_grp.c index 092d4e11a633..912d8ef04352 100644 --- a/drivers/infiniband/hw/usnic/usnic_ib_qp_grp.c +++ b/drivers/infiniband/hw/usnic/usnic_ib_qp_grp.c @@ -392,14 +392,12 @@ int usnic_ib_qp_grp_modify(struct usnic_ib_qp_grp *qp_grp, void *data) { int status = 0; - int vnic_idx; struct ib_event ib_event; enum ib_qp_state old_state; struct usnic_transport_spec *trans_spec; struct usnic_ib_qp_grp_flow *qp_flow; old_state = qp_grp->state; - vnic_idx = usnic_vnic_get_index(qp_grp->vf->vnic); trans_spec = (struct usnic_transport_spec *) data; spin_lock(&qp_grp->lock); diff --git a/drivers/infiniband/hw/usnic/usnic_ib_qp_grp.h b/drivers/infiniband/hw/usnic/usnic_ib_qp_grp.h index b1458be1d402..a8a2314c9531 100644 --- a/drivers/infiniband/hw/usnic/usnic_ib_qp_grp.h +++ b/drivers/infiniband/hw/usnic/usnic_ib_qp_grp.h @@ -84,30 +84,7 @@ struct usnic_ib_qp_grp_flow { char dentry_name[32]; }; -static const struct -usnic_vnic_res_spec min_transport_spec[USNIC_TRANSPORT_MAX] = { - { /*USNIC_TRANSPORT_UNKNOWN*/ - .resources = { - {.type = USNIC_VNIC_RES_TYPE_EOL, .cnt = 0,}, - }, - }, - { /*USNIC_TRANSPORT_ROCE_CUSTOM*/ - .resources = { - {.type = USNIC_VNIC_RES_TYPE_WQ, .cnt = 1,}, - {.type = USNIC_VNIC_RES_TYPE_RQ, .cnt = 1,}, - {.type = USNIC_VNIC_RES_TYPE_CQ, .cnt = 1,}, - {.type = USNIC_VNIC_RES_TYPE_EOL, .cnt = 0,}, - }, - }, - { /*USNIC_TRANSPORT_IPV4_UDP*/ - .resources = { - {.type = USNIC_VNIC_RES_TYPE_WQ, .cnt = 1,}, - {.type = USNIC_VNIC_RES_TYPE_RQ, .cnt = 1,}, - {.type = USNIC_VNIC_RES_TYPE_CQ, .cnt = 1,}, - {.type = USNIC_VNIC_RES_TYPE_EOL, .cnt = 0,}, - }, - }, -}; +extern const struct usnic_vnic_res_spec min_transport_spec[USNIC_TRANSPORT_MAX]; const char *usnic_ib_qp_grp_state_to_string(enum ib_qp_state state); int usnic_ib_qp_grp_dump_hdr(char *buf, int buf_sz); diff --git a/drivers/infiniband/hw/usnic/usnic_ib_sysfs.c b/drivers/infiniband/hw/usnic/usnic_ib_sysfs.c index 32956f9f5715..685ef2293cb8 100644 --- a/drivers/infiniband/hw/usnic/usnic_ib_sysfs.c +++ b/drivers/infiniband/hw/usnic/usnic_ib_sysfs.c @@ -43,6 +43,7 @@ #include "usnic_ib_qp_grp.h" #include "usnic_vnic.h" #include "usnic_ib_verbs.h" +#include "usnic_ib_sysfs.h" #include "usnic_log.h" #include "usnic_ib_sysfs.h" diff --git a/drivers/infiniband/hw/usnic/usnic_ib_verbs.c b/drivers/infiniband/hw/usnic/usnic_ib_verbs.c index e4113ef09315..aa2456a4f9bd 100644 --- a/drivers/infiniband/hw/usnic/usnic_ib_verbs.c +++ b/drivers/infiniband/hw/usnic/usnic_ib_verbs.c @@ -42,6 +42,7 @@ #include "usnic_ib.h" #include "usnic_common_util.h" #include "usnic_ib_qp_grp.h" +#include "usnic_ib_verbs.h" #include "usnic_fwd.h" #include "usnic_log.h" #include "usnic_uiom.h" @@ -50,6 +51,30 @@ #define USNIC_DEFAULT_TRANSPORT USNIC_TRANSPORT_ROCE_CUSTOM +const struct usnic_vnic_res_spec min_transport_spec[USNIC_TRANSPORT_MAX] = { + { /*USNIC_TRANSPORT_UNKNOWN*/ + .resources = { + {.type = USNIC_VNIC_RES_TYPE_EOL, .cnt = 0,}, + }, + }, + { /*USNIC_TRANSPORT_ROCE_CUSTOM*/ + .resources = { + {.type = USNIC_VNIC_RES_TYPE_WQ, .cnt = 1,}, + {.type = USNIC_VNIC_RES_TYPE_RQ, .cnt = 1,}, + {.type = USNIC_VNIC_RES_TYPE_CQ, .cnt = 1,}, + {.type = USNIC_VNIC_RES_TYPE_EOL, .cnt = 0,}, + }, + }, + { /*USNIC_TRANSPORT_IPV4_UDP*/ + .resources = { + {.type = USNIC_VNIC_RES_TYPE_WQ, .cnt = 1,}, + {.type = USNIC_VNIC_RES_TYPE_RQ, .cnt = 1,}, + {.type = USNIC_VNIC_RES_TYPE_CQ, .cnt = 1,}, + {.type = USNIC_VNIC_RES_TYPE_EOL, .cnt = 0,}, + }, + }, +}; + static void usnic_ib_fw_string_to_u64(char *fw_ver_str, u64 *fw_ver) { *fw_ver = *((u64 *)fw_ver_str); diff --git a/drivers/infiniband/sw/rdmavt/Kconfig b/drivers/infiniband/sw/rdmavt/Kconfig index fdd001ce13d8..2b5513da7e83 100644 --- a/drivers/infiniband/sw/rdmavt/Kconfig +++ b/drivers/infiniband/sw/rdmavt/Kconfig @@ -1,6 +1,7 @@ config INFINIBAND_RDMAVT tristate "RDMA verbs transport library" depends on 64BIT + depends on PCI select DMA_VIRT_OPS ---help--- This is a common software verbs provider for RDMA networks. diff --git a/drivers/infiniband/sw/rdmavt/mcast.c b/drivers/infiniband/sw/rdmavt/mcast.c index 1f12b69a0d07..b3a38c5e4cad 100644 --- a/drivers/infiniband/sw/rdmavt/mcast.c +++ b/drivers/infiniband/sw/rdmavt/mcast.c @@ -351,7 +351,7 @@ int rvt_detach_mcast(struct ib_qp *ibqp, union ib_gid *gid, u16 lid) int last = 0; int ret = 0; - if (ibqp->qp_num <= 1 || qp->state == IB_QPS_RESET) + if (ibqp->qp_num <= 1) return -EINVAL; spin_lock_irq(&ibp->lock); diff --git a/drivers/infiniband/sw/rdmavt/qp.c b/drivers/infiniband/sw/rdmavt/qp.c index 22df09ae809e..831f7bd19010 100644 --- a/drivers/infiniband/sw/rdmavt/qp.c +++ b/drivers/infiniband/sw/rdmavt/qp.c @@ -57,7 +57,7 @@ #include "vt.h" #include "trace.h" -static void rvt_rc_timeout(unsigned long arg); +static void rvt_rc_timeout(struct timer_list *t); /* * Convert the AETH RNR timeout code into the number of microseconds. @@ -717,7 +717,6 @@ static void rvt_reset_qp(struct rvt_dev_info *rdi, struct rvt_qp *qp, /* take qp out the hash and wait for it to be unused */ rvt_remove_qp(rdi, qp); - wait_event(qp->wait, !atomic_read(&qp->refcount)); /* grab the lock b/c it was locked at call time */ spin_lock_irq(&qp->r_lock); @@ -807,6 +806,7 @@ struct ib_qp *rvt_create_qp(struct ib_pd *ibpd, if (init_attr->port_num == 0 || init_attr->port_num > ibpd->device->phys_port_cnt) return ERR_PTR(-EINVAL); + /* fall through */ case IB_QPT_UC: case IB_QPT_RC: case IB_QPT_UD: @@ -845,7 +845,7 @@ struct ib_qp *rvt_create_qp(struct ib_pd *ibpd, goto bail_qp; } /* initialize timers needed for rc qp */ - setup_timer(&qp->s_timer, rvt_rc_timeout, (unsigned long)qp); + timer_setup(&qp->s_timer, rvt_rc_timeout, 0); hrtimer_init(&qp->s_rnr_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); qp->s_rnr_timer.function = rvt_rc_rnr_retry; @@ -894,8 +894,6 @@ struct ib_qp *rvt_create_qp(struct ib_pd *ibpd, atomic_set(&qp->refcount, 0); atomic_set(&qp->local_ops_pending, 0); init_waitqueue_head(&qp->wait); - init_timer(&qp->s_timer); - qp->s_timer.data = (unsigned long)qp; INIT_LIST_HEAD(&qp->rspwait); qp->state = IB_QPS_RESET; qp->s_wq = swq; @@ -1443,6 +1441,7 @@ int rvt_destroy_qp(struct ib_qp *ibqp) spin_unlock(&qp->s_hlock); spin_unlock_irq(&qp->r_lock); + wait_event(qp->wait, !atomic_read(&qp->refcount)); /* qpn is now available for use again */ rvt_free_qpn(&rdi->qp_dev->qpn_table, qp->ibqp.qp_num); @@ -2132,9 +2131,9 @@ EXPORT_SYMBOL(rvt_del_timers_sync); /** * This is called from s_timer for missing responses. */ -static void rvt_rc_timeout(unsigned long arg) +static void rvt_rc_timeout(struct timer_list *t) { - struct rvt_qp *qp = (struct rvt_qp *)arg; + struct rvt_qp *qp = from_timer(qp, t, s_timer); struct rvt_dev_info *rdi = ib_to_rvt(qp->ibqp.device); unsigned long flags; diff --git a/drivers/infiniband/sw/rxe/rxe_comp.c b/drivers/infiniband/sw/rxe/rxe_comp.c index 9eb12c2e3c74..6cdc40ed8a9f 100644 --- a/drivers/infiniband/sw/rxe/rxe_comp.c +++ b/drivers/infiniband/sw/rxe/rxe_comp.c @@ -136,9 +136,9 @@ static enum ib_wc_opcode wr_to_wc_opcode(enum ib_wr_opcode opcode) } } -void retransmit_timer(unsigned long data) +void retransmit_timer(struct timer_list *t) { - struct rxe_qp *qp = (struct rxe_qp *)data; + struct rxe_qp *qp = from_timer(qp, t, retrans_timer); if (qp->valid) { qp->comp.timeout = 1; @@ -270,8 +270,8 @@ static inline enum comp_state check_ack(struct rxe_qp *qp, if ((syn & AETH_TYPE_MASK) != AETH_ACK) return COMPST_ERROR; - /* Fall through (IB_OPCODE_RC_RDMA_READ_RESPONSE_MIDDLE - * doesn't have an AETH) + /* fall through */ + /* (IB_OPCODE_RC_RDMA_READ_RESPONSE_MIDDLE doesn't have an AETH) */ case IB_OPCODE_RC_RDMA_READ_RESPONSE_MIDDLE: if (wqe->wr.opcode != IB_WR_RDMA_READ && diff --git a/drivers/infiniband/sw/rxe/rxe_loc.h b/drivers/infiniband/sw/rxe/rxe_loc.h index 77b3ed0df936..d7472a442a2c 100644 --- a/drivers/infiniband/sw/rxe/rxe_loc.h +++ b/drivers/infiniband/sw/rxe/rxe_loc.h @@ -218,8 +218,8 @@ static inline void rxe_advance_resp_resource(struct rxe_qp *qp) qp->resp.res_head = 0; } -void retransmit_timer(unsigned long data); -void rnr_nak_timer(unsigned long data); +void retransmit_timer(struct timer_list *t); +void rnr_nak_timer(struct timer_list *t); /* rxe_srq.c */ #define IB_SRQ_INIT_MASK (~IB_SRQ_LIMIT) diff --git a/drivers/infiniband/sw/rxe/rxe_pool.c b/drivers/infiniband/sw/rxe/rxe_pool.c index c1b5f38f31a5..b4a8acc7bb7d 100644 --- a/drivers/infiniband/sw/rxe/rxe_pool.c +++ b/drivers/infiniband/sw/rxe/rxe_pool.c @@ -394,21 +394,25 @@ void *rxe_alloc(struct rxe_pool *pool) kref_get(&pool->rxe->ref_cnt); - if (atomic_inc_return(&pool->num_elem) > pool->max_elem) { - atomic_dec(&pool->num_elem); - rxe_dev_put(pool->rxe); - rxe_pool_put(pool); - return NULL; - } + if (atomic_inc_return(&pool->num_elem) > pool->max_elem) + goto out_put_pool; elem = kmem_cache_zalloc(pool_cache(pool), (pool->flags & RXE_POOL_ATOMIC) ? GFP_ATOMIC : GFP_KERNEL); + if (!elem) + goto out_put_pool; elem->pool = pool; kref_init(&elem->ref_cnt); return elem; + +out_put_pool: + atomic_dec(&pool->num_elem); + rxe_dev_put(pool->rxe); + rxe_pool_put(pool); + return NULL; } void rxe_elem_release(struct kref *kref) diff --git a/drivers/infiniband/sw/rxe/rxe_qp.c b/drivers/infiniband/sw/rxe/rxe_qp.c index 00bda9380a2e..4469592b839d 100644 --- a/drivers/infiniband/sw/rxe/rxe_qp.c +++ b/drivers/infiniband/sw/rxe/rxe_qp.c @@ -275,8 +275,8 @@ static int rxe_qp_init_req(struct rxe_dev *rxe, struct rxe_qp *qp, qp->qp_timeout_jiffies = 0; /* Can't be set for UD/UC in modify_qp */ if (init->qp_type == IB_QPT_RC) { - setup_timer(&qp->rnr_nak_timer, rnr_nak_timer, (unsigned long)qp); - setup_timer(&qp->retrans_timer, retransmit_timer, (unsigned long)qp); + timer_setup(&qp->rnr_nak_timer, rnr_nak_timer, 0); + timer_setup(&qp->retrans_timer, retransmit_timer, 0); } return 0; } diff --git a/drivers/infiniband/sw/rxe/rxe_req.c b/drivers/infiniband/sw/rxe/rxe_req.c index d84222f9d5d2..26a7f923045b 100644 --- a/drivers/infiniband/sw/rxe/rxe_req.c +++ b/drivers/infiniband/sw/rxe/rxe_req.c @@ -118,9 +118,9 @@ static void req_retry(struct rxe_qp *qp) } } -void rnr_nak_timer(unsigned long data) +void rnr_nak_timer(struct timer_list *t) { - struct rxe_qp *qp = (struct rxe_qp *)data; + struct rxe_qp *qp = from_timer(qp, t, rnr_nak_timer); pr_debug("qp#%d rnr nak timer fired\n", qp_num(qp)); rxe_run_task(&qp->req.task, 1); diff --git a/drivers/infiniband/sw/rxe/rxe_task.c b/drivers/infiniband/sw/rxe/rxe_task.c index ea3810b29273..08f05ac5f5d5 100644 --- a/drivers/infiniband/sw/rxe/rxe_task.c +++ b/drivers/infiniband/sw/rxe/rxe_task.c @@ -71,7 +71,7 @@ void rxe_do_task(unsigned long data) case TASK_STATE_BUSY: task->state = TASK_STATE_ARMED; - /* fall through to */ + /* fall through */ case TASK_STATE_ARMED: spin_unlock_irqrestore(&task->state_lock, flags); return; diff --git a/drivers/infiniband/sw/rxe/rxe_verbs.c b/drivers/infiniband/sw/rxe/rxe_verbs.c index 0b362f49a10a..ff77f4f66970 100644 --- a/drivers/infiniband/sw/rxe/rxe_verbs.c +++ b/drivers/infiniband/sw/rxe/rxe_verbs.c @@ -644,6 +644,7 @@ static void init_send_wr(struct rxe_qp *qp, struct rxe_send_wr *wr, switch (wr->opcode) { case IB_WR_RDMA_WRITE_WITH_IMM: wr->ex.imm_data = ibwr->ex.imm_data; + /* fall through */ case IB_WR_RDMA_READ: case IB_WR_RDMA_WRITE: wr->wr.rdma.remote_addr = rdma_wr(ibwr)->remote_addr; diff --git a/drivers/infiniband/ulp/ipoib/ipoib.h b/drivers/infiniband/ulp/ipoib/ipoib.h index 4a5c7a07a631..8033a006277f 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib.h +++ b/drivers/infiniband/ulp/ipoib/ipoib.h @@ -111,7 +111,7 @@ enum { IPOIB_MCAST_FLAG_BUSY = 2, IPOIB_MCAST_FLAG_ATTACHED = 3, - MAX_SEND_CQE = 16, + MAX_SEND_CQE = 64, IPOIB_CM_COPYBREAK = 256, IPOIB_NON_CHILD = 0, @@ -331,7 +331,8 @@ struct ipoib_dev_priv { struct net_device *dev; - struct napi_struct napi; + struct napi_struct send_napi; + struct napi_struct recv_napi; unsigned long flags; @@ -381,7 +382,6 @@ struct ipoib_dev_priv { unsigned tx_tail; struct ib_sge tx_sge[MAX_SKB_FRAGS + 1]; struct ib_ud_wr tx_wr; - unsigned tx_outstanding; struct ib_wc send_wc[MAX_SEND_CQE]; struct ib_recv_wr rx_wr; @@ -409,7 +409,6 @@ struct ipoib_dev_priv { #endif u64 hca_caps; struct ipoib_ethtool_st ethtool; - struct timer_list poll_timer; unsigned max_send_sge; bool sm_fullmember_sendonly_support; const struct net_device_ops *rn_ops; @@ -476,9 +475,10 @@ extern struct workqueue_struct *ipoib_workqueue; /* functions */ -int ipoib_poll(struct napi_struct *napi, int budget); -void ipoib_ib_completion(struct ib_cq *cq, void *dev_ptr); -void ipoib_send_comp_handler(struct ib_cq *cq, void *dev_ptr); +int ipoib_rx_poll(struct napi_struct *napi, int budget); +int ipoib_tx_poll(struct napi_struct *napi, int budget); +void ipoib_ib_rx_completion(struct ib_cq *cq, void *ctx_ptr); +void ipoib_ib_tx_completion(struct ib_cq *cq, void *ctx_ptr); struct ipoib_ah *ipoib_create_ah(struct net_device *dev, struct ib_pd *pd, struct rdma_ah_attr *attr); @@ -500,7 +500,7 @@ void ipoib_mark_paths_invalid(struct net_device *dev); void ipoib_flush_paths(struct net_device *dev); struct ipoib_dev_priv *ipoib_intf_alloc(struct ib_device *hca, u8 port, const char *format); -void ipoib_ib_tx_timer_func(unsigned long ctx); +void ipoib_ib_tx_timer_func(struct timer_list *t); void ipoib_ib_dev_flush_light(struct work_struct *work); void ipoib_ib_dev_flush_normal(struct work_struct *work); void ipoib_ib_dev_flush_heavy(struct work_struct *work); diff --git a/drivers/infiniband/ulp/ipoib/ipoib_cm.c b/drivers/infiniband/ulp/ipoib/ipoib_cm.c index 7774654c2ccb..87f4bd99cdf7 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_cm.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_cm.c @@ -594,9 +594,9 @@ void ipoib_cm_handle_rx_wc(struct net_device *dev, struct ib_wc *wc) skb = rx_ring[wr_id].skb; if (unlikely(wc->status != IB_WC_SUCCESS)) { - ipoib_dbg(priv, "cm recv error " - "(status=%d, wrid=%d vend_err %x)\n", - wc->status, wr_id, wc->vendor_err); + ipoib_dbg(priv, + "cm recv error (status=%d, wrid=%d vend_err %#x)\n", + wc->status, wr_id, wc->vendor_err); ++dev->stats.rx_dropped; if (has_srq) goto repost; @@ -757,30 +757,35 @@ void ipoib_cm_send(struct net_device *dev, struct sk_buff *skb, struct ipoib_cm_ return; } + if ((priv->tx_head - priv->tx_tail) == ipoib_sendq_size - 1) { + ipoib_dbg(priv, "TX ring 0x%x full, stopping kernel net queue\n", + tx->qp->qp_num); + netif_stop_queue(dev); + } + skb_orphan(skb); skb_dst_drop(skb); + if (netif_queue_stopped(dev)) + if (ib_req_notify_cq(priv->send_cq, IB_CQ_NEXT_COMP | + IB_CQ_REPORT_MISSED_EVENTS)) { + ipoib_warn(priv, "IPoIB/CM:request notify on send CQ failed\n"); + napi_schedule(&priv->send_napi); + } + rc = post_send(priv, tx, tx->tx_head & (ipoib_sendq_size - 1), tx_req); if (unlikely(rc)) { - ipoib_warn(priv, "post_send failed, error %d\n", rc); + ipoib_warn(priv, "IPoIB/CM:post_send failed, error %d\n", rc); ++dev->stats.tx_errors; ipoib_dma_unmap_tx(priv, tx_req); dev_kfree_skb_any(skb); + + if (netif_queue_stopped(dev)) + netif_wake_queue(dev); } else { netif_trans_update(dev); ++tx->tx_head; - - if (++priv->tx_outstanding == ipoib_sendq_size) { - ipoib_dbg(priv, "TX ring 0x%x full, stopping kernel net queue\n", - tx->qp->qp_num); - netif_stop_queue(dev); - rc = ib_req_notify_cq(priv->send_cq, - IB_CQ_NEXT_COMP | IB_CQ_REPORT_MISSED_EVENTS); - if (rc < 0) - ipoib_warn(priv, "request notify on send CQ failed\n"); - else if (rc) - ipoib_send_comp_handler(priv->send_cq, dev); - } + ++priv->tx_head; } } @@ -814,9 +819,11 @@ void ipoib_cm_handle_tx_wc(struct net_device *dev, struct ib_wc *wc) netif_tx_lock(dev); ++tx->tx_tail; - if (unlikely(--priv->tx_outstanding == ipoib_sendq_size >> 1) && - netif_queue_stopped(dev) && - test_bit(IPOIB_FLAG_ADMIN_UP, &priv->flags)) + ++priv->tx_tail; + + if (unlikely(netif_queue_stopped(dev) && + (priv->tx_head - priv->tx_tail) <= ipoib_sendq_size >> 1 && + test_bit(IPOIB_FLAG_ADMIN_UP, &priv->flags))) netif_wake_queue(dev); if (wc->status != IB_WC_SUCCESS && @@ -829,11 +836,11 @@ void ipoib_cm_handle_tx_wc(struct net_device *dev, struct ib_wc *wc) if (wc->status == IB_WC_RNR_RETRY_EXC_ERR || wc->status == IB_WC_RETRY_EXC_ERR) ipoib_dbg(priv, - "%s: failed cm send event (status=%d, wrid=%d vend_err 0x%x)\n", + "%s: failed cm send event (status=%d, wrid=%d vend_err %#x)\n", __func__, wc->status, wr_id, wc->vendor_err); else ipoib_warn(priv, - "%s: failed cm send event (status=%d, wrid=%d vend_err 0x%x)\n", + "%s: failed cm send event (status=%d, wrid=%d vend_err %#x)\n", __func__, wc->status, wr_id, wc->vendor_err); spin_lock_irqsave(&priv->lock, flags); @@ -1045,7 +1052,7 @@ static struct ib_qp *ipoib_cm_create_tx_qp(struct net_device *dev, struct ipoib_ { struct ipoib_dev_priv *priv = ipoib_priv(dev); struct ib_qp_init_attr attr = { - .send_cq = priv->recv_cq, + .send_cq = priv->send_cq, .recv_cq = priv->recv_cq, .srq = priv->cm.srq, .cap.max_send_wr = ipoib_sendq_size, @@ -1219,9 +1226,10 @@ timeout: tx_req = &p->tx_ring[p->tx_tail & (ipoib_sendq_size - 1)]; ipoib_dma_unmap_tx(priv, tx_req); dev_kfree_skb_any(tx_req->skb); - ++p->tx_tail; netif_tx_lock_bh(p->dev); - if (unlikely(--priv->tx_outstanding == ipoib_sendq_size >> 1) && + ++p->tx_tail; + ++priv->tx_tail; + if (unlikely(priv->tx_head - priv->tx_tail == ipoib_sendq_size >> 1) && netif_queue_stopped(p->dev) && test_bit(IPOIB_FLAG_ADMIN_UP, &priv->flags)) netif_wake_queue(p->dev); diff --git a/drivers/infiniband/ulp/ipoib/ipoib_ib.c b/drivers/infiniband/ulp/ipoib/ipoib_ib.c index 6cd61638b441..3b96cdaf9a83 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_ib.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_ib.c @@ -192,8 +192,8 @@ static void ipoib_ib_handle_rx_wc(struct net_device *dev, struct ib_wc *wc) if (unlikely(wc->status != IB_WC_SUCCESS)) { if (wc->status != IB_WC_WR_FLUSH_ERR) - ipoib_warn(priv, "failed recv event " - "(status=%d, wrid=%d vend_err %x)\n", + ipoib_warn(priv, + "failed recv event (status=%d, wrid=%d vend_err %#x)\n", wc->status, wr_id, wc->vendor_err); ipoib_ud_dma_unmap_rx(priv, priv->rx_ring[wr_id].mapping); dev_kfree_skb_any(skb); @@ -264,7 +264,7 @@ static void ipoib_ib_handle_rx_wc(struct net_device *dev, struct ib_wc *wc) likely(wc->wc_flags & IB_WC_IP_CSUM_OK)) skb->ip_summed = CHECKSUM_UNNECESSARY; - napi_gro_receive(&priv->napi, skb); + napi_gro_receive(&priv->recv_napi, skb); repost: if (unlikely(ipoib_ib_post_receive(dev, wr_id))) @@ -406,16 +406,17 @@ static void ipoib_ib_handle_tx_wc(struct net_device *dev, struct ib_wc *wc) dev_kfree_skb_any(tx_req->skb); ++priv->tx_tail; - if (unlikely(--priv->tx_outstanding == ipoib_sendq_size >> 1) && - netif_queue_stopped(dev) && - test_bit(IPOIB_FLAG_ADMIN_UP, &priv->flags)) + + if (unlikely(netif_queue_stopped(dev) && + ((priv->tx_head - priv->tx_tail) <= ipoib_sendq_size >> 1) && + test_bit(IPOIB_FLAG_ADMIN_UP, &priv->flags))) netif_wake_queue(dev); if (wc->status != IB_WC_SUCCESS && wc->status != IB_WC_WR_FLUSH_ERR) { struct ipoib_qp_state_validate *qp_work; - ipoib_warn(priv, "failed send event " - "(status=%d, wrid=%d vend_err %x)\n", + ipoib_warn(priv, + "failed send event (status=%d, wrid=%d vend_err %#x)\n", wc->status, wr_id, wc->vendor_err); qp_work = kzalloc(sizeof(*qp_work), GFP_ATOMIC); if (!qp_work) @@ -430,17 +431,23 @@ static void ipoib_ib_handle_tx_wc(struct net_device *dev, struct ib_wc *wc) static int poll_tx(struct ipoib_dev_priv *priv) { int n, i; + struct ib_wc *wc; n = ib_poll_cq(priv->send_cq, MAX_SEND_CQE, priv->send_wc); - for (i = 0; i < n; ++i) - ipoib_ib_handle_tx_wc(priv->dev, priv->send_wc + i); - + for (i = 0; i < n; ++i) { + wc = priv->send_wc + i; + if (wc->wr_id & IPOIB_OP_CM) + ipoib_cm_handle_tx_wc(priv->dev, priv->send_wc + i); + else + ipoib_ib_handle_tx_wc(priv->dev, priv->send_wc + i); + } return n == MAX_SEND_CQE; } -int ipoib_poll(struct napi_struct *napi, int budget) +int ipoib_rx_poll(struct napi_struct *napi, int budget) { - struct ipoib_dev_priv *priv = container_of(napi, struct ipoib_dev_priv, napi); + struct ipoib_dev_priv *priv = + container_of(napi, struct ipoib_dev_priv, recv_napi); struct net_device *dev = priv->dev; int done; int t; @@ -464,8 +471,9 @@ poll_more: ipoib_cm_handle_rx_wc(dev, wc); else ipoib_ib_handle_rx_wc(dev, wc); - } else - ipoib_cm_handle_tx_wc(priv->dev, wc); + } else { + pr_warn("%s: Got unexpected wqe id\n", __func__); + } } if (n != t) @@ -484,33 +492,47 @@ poll_more: return done; } -void ipoib_ib_completion(struct ib_cq *cq, void *dev_ptr) +int ipoib_tx_poll(struct napi_struct *napi, int budget) { - struct net_device *dev = dev_ptr; - struct ipoib_dev_priv *priv = ipoib_priv(dev); + struct ipoib_dev_priv *priv = container_of(napi, struct ipoib_dev_priv, + send_napi); + struct net_device *dev = priv->dev; + int n, i; + struct ib_wc *wc; - napi_schedule(&priv->napi); -} +poll_more: + n = ib_poll_cq(priv->send_cq, MAX_SEND_CQE, priv->send_wc); -static void drain_tx_cq(struct net_device *dev) -{ - struct ipoib_dev_priv *priv = ipoib_priv(dev); + for (i = 0; i < n; i++) { + wc = priv->send_wc + i; + if (wc->wr_id & IPOIB_OP_CM) + ipoib_cm_handle_tx_wc(dev, wc); + else + ipoib_ib_handle_tx_wc(dev, wc); + } - netif_tx_lock(dev); - while (poll_tx(priv)) - ; /* nothing */ + if (n < budget) { + napi_complete(napi); + if (unlikely(ib_req_notify_cq(priv->send_cq, IB_CQ_NEXT_COMP | + IB_CQ_REPORT_MISSED_EVENTS)) && + napi_reschedule(napi)) + goto poll_more; + } + return n < 0 ? 0 : n; +} - if (netif_queue_stopped(dev)) - mod_timer(&priv->poll_timer, jiffies + 1); +void ipoib_ib_rx_completion(struct ib_cq *cq, void *ctx_ptr) +{ + struct ipoib_dev_priv *priv = ctx_ptr; - netif_tx_unlock(dev); + napi_schedule(&priv->recv_napi); } -void ipoib_send_comp_handler(struct ib_cq *cq, void *dev_ptr) +void ipoib_ib_tx_completion(struct ib_cq *cq, void *ctx_ptr) { - struct ipoib_dev_priv *priv = ipoib_priv(dev_ptr); + struct ipoib_dev_priv *priv = ctx_ptr; - mod_timer(&priv->poll_timer, jiffies); + napi_schedule(&priv->send_napi); } static inline int post_send(struct ipoib_dev_priv *priv, @@ -611,23 +633,25 @@ int ipoib_send(struct net_device *dev, struct sk_buff *skb, priv->tx_wr.wr.send_flags |= IB_SEND_IP_CSUM; else priv->tx_wr.wr.send_flags &= ~IB_SEND_IP_CSUM; - - if (++priv->tx_outstanding == ipoib_sendq_size) { + /* increase the tx_head after send success, but use it for queue state */ + if (priv->tx_head - priv->tx_tail == ipoib_sendq_size - 1) { ipoib_dbg(priv, "TX ring full, stopping kernel net queue\n"); - if (ib_req_notify_cq(priv->send_cq, IB_CQ_NEXT_COMP)) - ipoib_warn(priv, "request notify on send CQ failed\n"); netif_stop_queue(dev); } skb_orphan(skb); skb_dst_drop(skb); + if (netif_queue_stopped(dev)) + if (ib_req_notify_cq(priv->send_cq, IB_CQ_NEXT_COMP | + IB_CQ_REPORT_MISSED_EVENTS)) + ipoib_warn(priv, "request notify on send CQ failed\n"); + rc = post_send(priv, priv->tx_head & (ipoib_sendq_size - 1), address, dqpn, tx_req, phead, hlen); if (unlikely(rc)) { ipoib_warn(priv, "post_send failed, error %d\n", rc); ++dev->stats.tx_errors; - --priv->tx_outstanding; ipoib_dma_unmap_tx(priv, tx_req); dev_kfree_skb_any(skb); if (netif_queue_stopped(dev)) @@ -639,11 +663,6 @@ int ipoib_send(struct net_device *dev, struct sk_buff *skb, rc = priv->tx_head; ++priv->tx_head; } - - if (unlikely(priv->tx_outstanding > MAX_SEND_CQE)) - while (poll_tx(priv)) - ; /* nothing */ - return rc; } @@ -732,6 +751,22 @@ static void check_qp_movement_and_print(struct ipoib_dev_priv *priv, new_state, qp_attr.qp_state); } +static void ipoib_napi_enable(struct net_device *dev) +{ + struct ipoib_dev_priv *priv = ipoib_priv(dev); + + napi_enable(&priv->recv_napi); + napi_enable(&priv->send_napi); +} + +static void ipoib_napi_disable(struct net_device *dev) +{ + struct ipoib_dev_priv *priv = ipoib_priv(dev); + + napi_disable(&priv->recv_napi); + napi_disable(&priv->send_napi); +} + int ipoib_ib_dev_stop_default(struct net_device *dev) { struct ipoib_dev_priv *priv = ipoib_priv(dev); @@ -741,7 +776,7 @@ int ipoib_ib_dev_stop_default(struct net_device *dev) int i; if (test_bit(IPOIB_FLAG_INITIALIZED, &priv->flags)) - napi_disable(&priv->napi); + ipoib_napi_disable(dev); ipoib_cm_dev_stop(dev); @@ -773,7 +808,6 @@ int ipoib_ib_dev_stop_default(struct net_device *dev) ipoib_dma_unmap_tx(priv, tx_req); dev_kfree_skb_any(tx_req->skb); ++priv->tx_tail; - --priv->tx_outstanding; } for (i = 0; i < ipoib_recvq_size; ++i) { @@ -799,7 +833,6 @@ int ipoib_ib_dev_stop_default(struct net_device *dev) ipoib_dbg(priv, "All sends and receives done.\n"); timeout: - del_timer_sync(&priv->poll_timer); qp_attr.qp_state = IB_QPS_RESET; if (ib_modify_qp(priv->qp, &qp_attr, IB_QP_STATE)) ipoib_warn(priv, "Failed to modify QP to RESET state\n"); @@ -821,11 +854,6 @@ int ipoib_ib_dev_stop(struct net_device *dev) return 0; } -void ipoib_ib_tx_timer_func(unsigned long ctx) -{ - drain_tx_cq((struct net_device *)ctx); -} - int ipoib_ib_dev_open_default(struct net_device *dev) { struct ipoib_dev_priv *priv = ipoib_priv(dev); @@ -850,7 +878,7 @@ int ipoib_ib_dev_open_default(struct net_device *dev) } if (!test_bit(IPOIB_FLAG_INITIALIZED, &priv->flags)) - napi_enable(&priv->napi); + ipoib_napi_enable(dev); return 0; out: @@ -893,13 +921,17 @@ dev_stop: void ipoib_pkey_dev_check_presence(struct net_device *dev) { struct ipoib_dev_priv *priv = ipoib_priv(dev); + struct rdma_netdev *rn = netdev_priv(dev); if (!(priv->pkey & 0x7fff) || ib_find_pkey(priv->ca, priv->port, priv->pkey, - &priv->pkey_index)) + &priv->pkey_index)) { clear_bit(IPOIB_PKEY_ASSIGNED, &priv->flags); - else + } else { + if (rn->set_id) + rn->set_id(dev, priv->pkey_index); set_bit(IPOIB_PKEY_ASSIGNED, &priv->flags); + } } void ipoib_ib_dev_up(struct net_device *dev) @@ -961,8 +993,9 @@ void ipoib_drain_cq(struct net_device *dev) ipoib_cm_handle_rx_wc(dev, priv->ibwc + i); else ipoib_ib_handle_rx_wc(dev, priv->ibwc + i); - } else - ipoib_cm_handle_tx_wc(dev, priv->ibwc + i); + } else { + pr_warn("%s: Got unexpected wqe id\n", __func__); + } } } while (n == IPOIB_NUM_WC); @@ -1203,10 +1236,15 @@ static void __ipoib_ib_dev_flush(struct ipoib_dev_priv *priv, ipoib_ib_dev_down(dev); if (level == IPOIB_FLUSH_HEAVY) { + rtnl_lock(); if (test_bit(IPOIB_FLAG_INITIALIZED, &priv->flags)) ipoib_ib_dev_stop(dev); - if (ipoib_ib_dev_open(dev) != 0) + + result = ipoib_ib_dev_open(dev); + rtnl_unlock(); + if (result) return; + if (netif_queue_stopped(dev)) netif_start_queue(dev); } diff --git a/drivers/infiniband/ulp/ipoib/ipoib_main.c b/drivers/infiniband/ulp/ipoib/ipoib_main.c index dcc77014018d..12b7f911f0e5 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_main.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_main.c @@ -51,7 +51,6 @@ #include <net/addrconf.h> #include <linux/inetdevice.h> #include <rdma/ib_cache.h> -#include <linux/pci.h> #define DRV_VERSION "1.0.0" @@ -1617,13 +1616,29 @@ static void ipoib_neigh_hash_uninit(struct net_device *dev) wait_for_completion(&priv->ntbl.deleted); } +static void ipoib_napi_add(struct net_device *dev) +{ + struct ipoib_dev_priv *priv = ipoib_priv(dev); + + netif_napi_add(dev, &priv->recv_napi, ipoib_rx_poll, IPOIB_NUM_WC); + netif_napi_add(dev, &priv->send_napi, ipoib_tx_poll, MAX_SEND_CQE); +} + +static void ipoib_napi_del(struct net_device *dev) +{ + struct ipoib_dev_priv *priv = ipoib_priv(dev); + + netif_napi_del(&priv->recv_napi); + netif_napi_del(&priv->send_napi); +} + static void ipoib_dev_uninit_default(struct net_device *dev) { struct ipoib_dev_priv *priv = ipoib_priv(dev); ipoib_transport_dev_cleanup(dev); - netif_napi_del(&priv->napi); + ipoib_napi_del(dev); ipoib_cm_dev_cleanup(dev); @@ -1638,7 +1653,7 @@ static int ipoib_dev_init_default(struct net_device *dev) { struct ipoib_dev_priv *priv = ipoib_priv(dev); - netif_napi_add(dev, &priv->napi, ipoib_poll, NAPI_POLL_WEIGHT); + ipoib_napi_add(dev); /* Allocate RX/TX "rings" to hold queued skbs */ priv->rx_ring = kzalloc(ipoib_recvq_size * sizeof *priv->rx_ring, @@ -1666,9 +1681,6 @@ static int ipoib_dev_init_default(struct net_device *dev) priv->dev->dev_addr[2] = (priv->qp->qp_num >> 8) & 0xff; priv->dev->dev_addr[3] = (priv->qp->qp_num) & 0xff; - setup_timer(&priv->poll_timer, ipoib_ib_tx_timer_func, - (unsigned long)dev); - return 0; out_tx_ring_cleanup: @@ -1678,7 +1690,7 @@ out_rx_ring_cleanup: kfree(priv->rx_ring); out: - netif_napi_del(&priv->napi); + ipoib_napi_del(dev); return -ENOMEM; } @@ -2314,7 +2326,8 @@ static void ipoib_add_one(struct ib_device *device) } if (!count) { - kfree(dev_list); + pr_err("Failed to init port, removing it\n"); + ipoib_remove_one(device, dev_list); return; } diff --git a/drivers/infiniband/ulp/ipoib/ipoib_verbs.c b/drivers/infiniband/ulp/ipoib/ipoib_verbs.c index bb64baf25309..a1ed25422b72 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_verbs.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_verbs.c @@ -156,7 +156,7 @@ int ipoib_transport_dev_init(struct net_device *dev, struct ib_device *ca) }; struct ib_cq_init_attr cq_attr = {}; - int ret, size; + int ret, size, req_vec; int i; size = ipoib_recvq_size + 1; @@ -171,17 +171,21 @@ int ipoib_transport_dev_init(struct net_device *dev, struct ib_device *ca) if (ret != -ENOSYS) return -ENODEV; + req_vec = (priv->port - 1) * 2; + cq_attr.cqe = size; - priv->recv_cq = ib_create_cq(priv->ca, ipoib_ib_completion, NULL, - dev, &cq_attr); + cq_attr.comp_vector = req_vec % priv->ca->num_comp_vectors; + priv->recv_cq = ib_create_cq(priv->ca, ipoib_ib_rx_completion, NULL, + priv, &cq_attr); if (IS_ERR(priv->recv_cq)) { printk(KERN_WARNING "%s: failed to create receive CQ\n", ca->name); goto out_cm_dev_cleanup; } cq_attr.cqe = ipoib_sendq_size; - priv->send_cq = ib_create_cq(priv->ca, ipoib_send_comp_handler, NULL, - dev, &cq_attr); + cq_attr.comp_vector = (req_vec + 1) % priv->ca->num_comp_vectors; + priv->send_cq = ib_create_cq(priv->ca, ipoib_ib_tx_completion, NULL, + priv, &cq_attr); if (IS_ERR(priv->send_cq)) { printk(KERN_WARNING "%s: failed to create send CQ\n", ca->name); goto out_free_recv_cq; @@ -208,6 +212,9 @@ int ipoib_transport_dev_init(struct net_device *dev, struct ib_device *ca) goto out_free_send_cq; } + if (ib_req_notify_cq(priv->send_cq, IB_CQ_NEXT_COMP)) + goto out_free_send_cq; + for (i = 0; i < MAX_SKB_FRAGS + 1; ++i) priv->tx_sge[i].lkey = priv->pd->local_dma_lkey; diff --git a/drivers/infiniband/ulp/iser/iser_verbs.c b/drivers/infiniband/ulp/iser/iser_verbs.c index 55a73b0ed4c6..56b7240a3fc3 100644 --- a/drivers/infiniband/ulp/iser/iser_verbs.c +++ b/drivers/infiniband/ulp/iser/iser_verbs.c @@ -1146,7 +1146,7 @@ void iser_err_comp(struct ib_wc *wc, const char *type) if (wc->status != IB_WC_WR_FLUSH_ERR) { struct iser_conn *iser_conn = to_iser_conn(wc->qp->qp_context); - iser_err("%s failure: %s (%d) vend_err %x\n", type, + iser_err("%s failure: %s (%d) vend_err %#x\n", type, ib_wc_status_msg(wc->status), wc->status, wc->vendor_err); diff --git a/drivers/infiniband/ulp/isert/ib_isert.c b/drivers/infiniband/ulp/isert/ib_isert.c index ceabdb85df8b..720dfb3a1ac2 100644 --- a/drivers/infiniband/ulp/isert/ib_isert.c +++ b/drivers/infiniband/ulp/isert/ib_isert.c @@ -788,10 +788,11 @@ isert_cma_handler(struct rdma_cm_id *cma_id, struct rdma_cm_event *event) * the rdma cm id */ return 1; - case RDMA_CM_EVENT_REJECTED: /* FALLTHRU */ + case RDMA_CM_EVENT_REJECTED: isert_info("Connection rejected: %s\n", rdma_reject_msg(cma_id, event->status)); - case RDMA_CM_EVENT_UNREACHABLE: /* FALLTHRU */ + /* fall through */ + case RDMA_CM_EVENT_UNREACHABLE: case RDMA_CM_EVENT_CONNECT_ERROR: ret = isert_connect_error(cma_id); break; @@ -1569,9 +1570,7 @@ isert_put_cmd(struct isert_cmd *isert_cmd, bool comp_err) transport_generic_free_cmd(&cmd->se_cmd, 0); break; } - /* - * Fall-through - */ + /* fall through */ default: iscsit_release_cmd(cmd); break; @@ -1749,8 +1748,9 @@ isert_do_control_comp(struct work_struct *work) switch (cmd->i_state) { case ISTATE_SEND_TASKMGTRSP: iscsit_tmr_post_handler(cmd, cmd->conn); - case ISTATE_SEND_REJECT: /* FALLTHRU */ - case ISTATE_SEND_TEXTRSP: /* FALLTHRU */ + /* fall through */ + case ISTATE_SEND_REJECT: + case ISTATE_SEND_TEXTRSP: cmd->i_state = ISTATE_SENT_STATUS; isert_completion_put(&isert_cmd->tx_desc, isert_cmd, ib_dev, false); diff --git a/drivers/infiniband/ulp/opa_vnic/opa_vnic_encap.c b/drivers/infiniband/ulp/opa_vnic/opa_vnic_encap.c index afa938bd26d6..4be3aef40bd2 100644 --- a/drivers/infiniband/ulp/opa_vnic/opa_vnic_encap.c +++ b/drivers/infiniband/ulp/opa_vnic/opa_vnic_encap.c @@ -139,6 +139,7 @@ void opa_vnic_release_mac_tbl(struct opa_vnic_adapter *adapter) rcu_assign_pointer(adapter->mactbl, NULL); synchronize_rcu(); opa_vnic_free_mac_tbl(mactbl); + adapter->info.vport.mac_tbl_digest = 0; mutex_unlock(&adapter->mactbl_lock); } @@ -405,6 +406,42 @@ u8 opa_vnic_get_vl(struct opa_vnic_adapter *adapter, struct sk_buff *skb) return vl; } +/* opa_vnic_get_rc - return the routing control */ +static u8 opa_vnic_get_rc(struct __opa_veswport_info *info, + struct sk_buff *skb) +{ + u8 proto, rout_ctrl; + + switch (vlan_get_protocol(skb)) { + case htons(ETH_P_IPV6): + proto = ipv6_hdr(skb)->nexthdr; + if (proto == IPPROTO_TCP) + rout_ctrl = OPA_VNIC_ENCAP_RC_EXT(info->vesw.rc, + IPV6_TCP); + else if (proto == IPPROTO_UDP) + rout_ctrl = OPA_VNIC_ENCAP_RC_EXT(info->vesw.rc, + IPV6_UDP); + else + rout_ctrl = OPA_VNIC_ENCAP_RC_EXT(info->vesw.rc, IPV6); + break; + case htons(ETH_P_IP): + proto = ip_hdr(skb)->protocol; + if (proto == IPPROTO_TCP) + rout_ctrl = OPA_VNIC_ENCAP_RC_EXT(info->vesw.rc, + IPV4_TCP); + else if (proto == IPPROTO_UDP) + rout_ctrl = OPA_VNIC_ENCAP_RC_EXT(info->vesw.rc, + IPV4_UDP); + else + rout_ctrl = OPA_VNIC_ENCAP_RC_EXT(info->vesw.rc, IPV4); + break; + default: + rout_ctrl = OPA_VNIC_ENCAP_RC_EXT(info->vesw.rc, DEFAULT); + } + + return rout_ctrl; +} + /* opa_vnic_calc_entropy - calculate the packet entropy */ u8 opa_vnic_calc_entropy(struct opa_vnic_adapter *adapter, struct sk_buff *skb) { @@ -447,7 +484,7 @@ void opa_vnic_encap_skb(struct opa_vnic_adapter *adapter, struct sk_buff *skb) { struct __opa_veswport_info *info = &adapter->info; struct opa_vnic_skb_mdata *mdata; - u8 def_port, sc, entropy, *hdr; + u8 def_port, sc, rc, entropy, *hdr; u16 len, l4_hdr; u32 dlid; @@ -458,6 +495,7 @@ void opa_vnic_encap_skb(struct opa_vnic_adapter *adapter, struct sk_buff *skb) len = opa_vnic_wire_length(skb); dlid = opa_vnic_get_dlid(adapter, skb, def_port); sc = opa_vnic_get_sc(info, skb); + rc = opa_vnic_get_rc(info, skb); l4_hdr = info->vesw.vesw_id; mdata = skb_push(skb, sizeof(*mdata)); @@ -470,6 +508,6 @@ void opa_vnic_encap_skb(struct opa_vnic_adapter *adapter, struct sk_buff *skb) } opa_vnic_make_header(hdr, info->vport.encap_slid, dlid, len, - info->vesw.pkey, entropy, sc, 0, + info->vesw.pkey, entropy, sc, rc, OPA_VNIC_L4_ETHR, l4_hdr); } diff --git a/drivers/infiniband/ulp/opa_vnic/opa_vnic_encap.h b/drivers/infiniband/ulp/opa_vnic/opa_vnic_encap.h index 4c434b9dd84c..e4c9bf2ef7e2 100644 --- a/drivers/infiniband/ulp/opa_vnic/opa_vnic_encap.h +++ b/drivers/infiniband/ulp/opa_vnic/opa_vnic_encap.h @@ -103,6 +103,17 @@ #define OPA_VNIC_ETH_LINK_UP 1 #define OPA_VNIC_ETH_LINK_DOWN 2 +/* routing control */ +#define OPA_VNIC_ENCAP_RC_DEFAULT 0 +#define OPA_VNIC_ENCAP_RC_IPV4 4 +#define OPA_VNIC_ENCAP_RC_IPV4_UDP 8 +#define OPA_VNIC_ENCAP_RC_IPV4_TCP 12 +#define OPA_VNIC_ENCAP_RC_IPV6 16 +#define OPA_VNIC_ENCAP_RC_IPV6_TCP 20 +#define OPA_VNIC_ENCAP_RC_IPV6_UDP 24 + +#define OPA_VNIC_ENCAP_RC_EXT(w, b) (((w) >> OPA_VNIC_ENCAP_RC_ ## b) & 0x7) + /** * struct opa_vesw_info - OPA vnic switch information * @fabric_id: 10-bit fabric id @@ -111,8 +122,8 @@ * @pkey: partition key * @u_mcast_dlid: unknown multicast dlid * @u_ucast_dlid: array of unknown unicast dlids - * @eth_mtu: MTUs for each vlan PCP - * @eth_mtu_non_vlan: MTU for non vlan packets + * @rc: routing control + * @eth_mtu: Ethernet MTU */ struct opa_vesw_info { __be16 fabric_id; @@ -128,9 +139,10 @@ struct opa_vesw_info { __be32 u_mcast_dlid; __be32 u_ucast_dlid[OPA_VESW_MAX_NUM_DEF_PORT]; - u8 rsvd3[44]; - __be16 eth_mtu[OPA_VNIC_MAX_NUM_PCP]; - __be16 eth_mtu_non_vlan; + __be32 rc; + + u8 rsvd3[56]; + __be16 eth_mtu; u8 rsvd4[2]; } __packed; diff --git a/drivers/infiniband/ulp/opa_vnic/opa_vnic_internal.h b/drivers/infiniband/ulp/opa_vnic/opa_vnic_internal.h index ca29e6d5aedc..afd95f432262 100644 --- a/drivers/infiniband/ulp/opa_vnic/opa_vnic_internal.h +++ b/drivers/infiniband/ulp/opa_vnic/opa_vnic_internal.h @@ -89,9 +89,10 @@ struct __opa_vesw_info { u32 u_mcast_dlid; u32 u_ucast_dlid[OPA_VESW_MAX_NUM_DEF_PORT]; - u8 rsvd3[44]; - u16 eth_mtu[OPA_VNIC_MAX_NUM_PCP]; - u16 eth_mtu_non_vlan; + u32 rc; + + u8 rsvd3[56]; + u16 eth_mtu; u8 rsvd4[2]; } __packed; diff --git a/drivers/infiniband/ulp/opa_vnic/opa_vnic_netdev.c b/drivers/infiniband/ulp/opa_vnic/opa_vnic_netdev.c index 1a3c25364b64..ce57e0f10289 100644 --- a/drivers/infiniband/ulp/opa_vnic/opa_vnic_netdev.c +++ b/drivers/infiniband/ulp/opa_vnic/opa_vnic_netdev.c @@ -112,6 +112,27 @@ static u16 opa_vnic_select_queue(struct net_device *netdev, struct sk_buff *skb, return rc; } +static void opa_vnic_update_state(struct opa_vnic_adapter *adapter, bool up) +{ + struct __opa_veswport_info *info = &adapter->info; + + mutex_lock(&adapter->lock); + /* Operational state can only be DROP_ALL or FORWARDING */ + if ((info->vport.config_state == OPA_VNIC_STATE_FORWARDING) && up) { + info->vport.oper_state = OPA_VNIC_STATE_FORWARDING; + info->vport.eth_link_status = OPA_VNIC_ETH_LINK_UP; + } else { + info->vport.oper_state = OPA_VNIC_STATE_DROP_ALL; + info->vport.eth_link_status = OPA_VNIC_ETH_LINK_DOWN; + } + + if (info->vport.config_state == OPA_VNIC_STATE_FORWARDING) + netif_dormant_off(adapter->netdev); + else + netif_dormant_on(adapter->netdev); + mutex_unlock(&adapter->lock); +} + /* opa_vnic_process_vema_config - process vema configuration updates */ void opa_vnic_process_vema_config(struct opa_vnic_adapter *adapter) { @@ -130,7 +151,7 @@ void opa_vnic_process_vema_config(struct opa_vnic_adapter *adapter) memcpy(saddr.sa_data, info->vport.base_mac_addr, ARRAY_SIZE(info->vport.base_mac_addr)); mutex_lock(&adapter->lock); - eth_mac_addr(netdev, &saddr); + eth_commit_mac_addr_change(netdev, &saddr); memcpy(adapter->vema_mac_addr, info->vport.base_mac_addr, ETH_ALEN); mutex_unlock(&adapter->lock); @@ -140,7 +161,7 @@ void opa_vnic_process_vema_config(struct opa_vnic_adapter *adapter) /* Handle MTU limit change */ rtnl_lock(); - netdev->max_mtu = max_t(unsigned int, info->vesw.eth_mtu_non_vlan, + netdev->max_mtu = max_t(unsigned int, info->vesw.eth_mtu, netdev->min_mtu); if (netdev->mtu > netdev->max_mtu) dev_set_mtu(netdev, netdev->max_mtu); @@ -164,14 +185,8 @@ void opa_vnic_process_vema_config(struct opa_vnic_adapter *adapter) adapter->flow_tbl[i] = port_count ? port_num[i % port_count] : OPA_VNIC_INVALID_PORT; - /* Operational state can only be DROP_ALL or FORWARDING */ - if (info->vport.config_state == OPA_VNIC_STATE_FORWARDING) { - info->vport.oper_state = OPA_VNIC_STATE_FORWARDING; - netif_dormant_off(netdev); - } else { - info->vport.oper_state = OPA_VNIC_STATE_DROP_ALL; - netif_dormant_on(netdev); - } + /* update state */ + opa_vnic_update_state(adapter, !!(netdev->flags & IFF_UP)); } /* @@ -183,6 +198,7 @@ static inline void opa_vnic_set_pod_values(struct opa_vnic_adapter *adapter) adapter->info.vport.max_smac_ent = OPA_VNIC_MAX_SMAC_LIMIT; adapter->info.vport.config_state = OPA_VNIC_STATE_DROP_ALL; adapter->info.vport.eth_link_status = OPA_VNIC_ETH_LINK_DOWN; + adapter->info.vesw.eth_mtu = ETH_DATA_LEN; } /* opa_vnic_set_mac_addr - change mac address */ @@ -268,8 +284,8 @@ static int opa_netdev_open(struct net_device *netdev) return rc; } - /* Update eth link status and send trap */ - adapter->info.vport.eth_link_status = OPA_VNIC_ETH_LINK_UP; + /* Update status and send trap */ + opa_vnic_update_state(adapter, true); opa_vnic_vema_report_event(adapter, OPA_VESWPORT_TRAP_ETH_LINK_STATUS_CHANGE); return 0; @@ -287,8 +303,8 @@ static int opa_netdev_close(struct net_device *netdev) return rc; } - /* Update eth link status and send trap */ - adapter->info.vport.eth_link_status = OPA_VNIC_ETH_LINK_DOWN; + /* Update status and send trap */ + opa_vnic_update_state(adapter, false); opa_vnic_vema_report_event(adapter, OPA_VESWPORT_TRAP_ETH_LINK_STATUS_CHANGE); return 0; diff --git a/drivers/infiniband/ulp/opa_vnic/opa_vnic_vema.c b/drivers/infiniband/ulp/opa_vnic/opa_vnic_vema.c index 21f0b481edcc..4b615c1451e7 100644 --- a/drivers/infiniband/ulp/opa_vnic/opa_vnic_vema.c +++ b/drivers/infiniband/ulp/opa_vnic/opa_vnic_vema.c @@ -186,6 +186,7 @@ static inline void vema_get_pod_values(struct opa_veswport_info *port_info) cpu_to_be16(OPA_VNIC_MAX_SMAC_LIMIT); port_info->vport.oper_state = OPA_VNIC_STATE_DROP_ALL; port_info->vport.config_state = OPA_VNIC_STATE_DROP_ALL; + port_info->vesw.eth_mtu = cpu_to_be16(ETH_DATA_LEN); } /** diff --git a/drivers/infiniband/ulp/opa_vnic/opa_vnic_vema_iface.c b/drivers/infiniband/ulp/opa_vnic/opa_vnic_vema_iface.c index c2733964379c..868b5aec1537 100644 --- a/drivers/infiniband/ulp/opa_vnic/opa_vnic_vema_iface.c +++ b/drivers/infiniband/ulp/opa_vnic/opa_vnic_vema_iface.c @@ -176,11 +176,10 @@ void opa_vnic_get_vesw_info(struct opa_vnic_adapter *adapter, for (i = 0; i < OPA_VESW_MAX_NUM_DEF_PORT; i++) info->u_ucast_dlid[i] = cpu_to_be32(src->u_ucast_dlid[i]); - memcpy(info->rsvd3, src->rsvd3, ARRAY_SIZE(src->rsvd3)); - for (i = 0; i < OPA_VNIC_MAX_NUM_PCP; i++) - info->eth_mtu[i] = cpu_to_be16(src->eth_mtu[i]); + info->rc = cpu_to_be32(src->rc); - info->eth_mtu_non_vlan = cpu_to_be16(src->eth_mtu_non_vlan); + memcpy(info->rsvd3, src->rsvd3, ARRAY_SIZE(src->rsvd3)); + info->eth_mtu = cpu_to_be16(src->eth_mtu); memcpy(info->rsvd4, src->rsvd4, ARRAY_SIZE(src->rsvd4)); } @@ -211,11 +210,10 @@ void opa_vnic_set_vesw_info(struct opa_vnic_adapter *adapter, for (i = 0; i < OPA_VESW_MAX_NUM_DEF_PORT; i++) dst->u_ucast_dlid[i] = be32_to_cpu(info->u_ucast_dlid[i]); - memcpy(dst->rsvd3, info->rsvd3, ARRAY_SIZE(info->rsvd3)); - for (i = 0; i < OPA_VNIC_MAX_NUM_PCP; i++) - dst->eth_mtu[i] = be16_to_cpu(info->eth_mtu[i]); + dst->rc = be32_to_cpu(info->rc); - dst->eth_mtu_non_vlan = be16_to_cpu(info->eth_mtu_non_vlan); + memcpy(dst->rsvd3, info->rsvd3, ARRAY_SIZE(info->rsvd3)); + dst->eth_mtu = be16_to_cpu(info->eth_mtu); memcpy(dst->rsvd4, info->rsvd4, ARRAY_SIZE(info->rsvd4)); } @@ -348,7 +346,7 @@ void opa_vnic_query_mcast_macs(struct opa_vnic_adapter *adapter, void opa_vnic_query_ucast_macs(struct opa_vnic_adapter *adapter, struct opa_veswport_iface_macs *macs) { - u16 start_idx, tot_macs, num_macs, idx = 0, count = 0; + u16 start_idx, tot_macs, num_macs, idx = 0, count = 0, em_macs = 0; struct netdev_hw_addr *ha; start_idx = be16_to_cpu(macs->start_idx); @@ -359,8 +357,10 @@ void opa_vnic_query_ucast_macs(struct opa_vnic_adapter *adapter, /* Do not include EM specified MAC address */ if (!memcmp(adapter->info.vport.base_mac_addr, ha->addr, - ARRAY_SIZE(adapter->info.vport.base_mac_addr))) + ARRAY_SIZE(adapter->info.vport.base_mac_addr))) { + em_macs++; continue; + } if (start_idx > idx++) continue; @@ -383,7 +383,7 @@ void opa_vnic_query_ucast_macs(struct opa_vnic_adapter *adapter, } tot_macs = netdev_hw_addr_list_count(&adapter->netdev->dev_addrs) + - netdev_uc_count(adapter->netdev); + netdev_uc_count(adapter->netdev) - em_macs; macs->tot_macs_in_lst = cpu_to_be16(tot_macs); macs->num_macs_in_msg = cpu_to_be16(count); macs->gen_count = cpu_to_be16(adapter->info.vport.uc_macs_gen_count); diff --git a/drivers/infiniband/ulp/srp/ib_srp.c b/drivers/infiniband/ulp/srp/ib_srp.c index fa5ccdb3bb2a..972d4b3c5223 100644 --- a/drivers/infiniband/ulp/srp/ib_srp.c +++ b/drivers/infiniband/ulp/srp/ib_srp.c @@ -464,20 +464,20 @@ static struct srp_fr_pool *srp_alloc_fr_pool(struct srp_target_port *target) /** * srp_destroy_qp() - destroy an RDMA queue pair - * @qp: RDMA queue pair. + * @ch: SRP RDMA channel. * * Drain the qp before destroying it. This avoids that the receive * completion handler can access the queue pair while it is * being destroyed. */ -static void srp_destroy_qp(struct srp_rdma_ch *ch, struct ib_qp *qp) +static void srp_destroy_qp(struct srp_rdma_ch *ch) { spin_lock_irq(&ch->lock); ib_process_cq_direct(ch->send_cq, -1); spin_unlock_irq(&ch->lock); - ib_drain_qp(qp); - ib_destroy_qp(qp); + ib_drain_qp(ch->qp); + ib_destroy_qp(ch->qp); } static int srp_create_ch_ib(struct srp_rdma_ch *ch) @@ -550,7 +550,7 @@ static int srp_create_ch_ib(struct srp_rdma_ch *ch) } if (ch->qp) - srp_destroy_qp(ch, ch->qp); + srp_destroy_qp(ch); if (ch->recv_cq) ib_free_cq(ch->recv_cq); if (ch->send_cq) @@ -617,7 +617,7 @@ static void srp_free_ch_ib(struct srp_target_port *target, ib_destroy_fmr_pool(ch->fmr_pool); } - srp_destroy_qp(ch, ch->qp); + srp_destroy_qp(ch); ib_free_cq(ch->send_cq); ib_free_cq(ch->recv_cq); @@ -665,12 +665,19 @@ static void srp_path_rec_completion(int status, static int srp_lookup_path(struct srp_rdma_ch *ch) { struct srp_target_port *target = ch->target; - int ret; + int ret = -ENODEV; ch->path.numb_path = 1; init_completion(&ch->done); + /* + * Avoid that the SCSI host can be removed by srp_remove_target() + * before srp_path_rec_completion() is called. + */ + if (!scsi_host_get(target->scsi_host)) + goto out; + ch->path_query_id = ib_sa_path_rec_get(&srp_sa_client, target->srp_host->srp_dev->dev, target->srp_host->port, @@ -684,18 +691,41 @@ static int srp_lookup_path(struct srp_rdma_ch *ch) GFP_KERNEL, srp_path_rec_completion, ch, &ch->path_query); - if (ch->path_query_id < 0) - return ch->path_query_id; + ret = ch->path_query_id; + if (ret < 0) + goto put; ret = wait_for_completion_interruptible(&ch->done); if (ret < 0) - return ret; + goto put; - if (ch->status < 0) + ret = ch->status; + if (ret < 0) shost_printk(KERN_WARNING, target->scsi_host, PFX "Path record query failed\n"); - return ch->status; +put: + scsi_host_put(target->scsi_host); + +out: + return ret; +} + +static u8 srp_get_subnet_timeout(struct srp_host *host) +{ + struct ib_port_attr attr; + int ret; + u8 subnet_timeout = 18; + + ret = ib_query_port(host->srp_dev->dev, host->port, &attr); + if (ret == 0) + subnet_timeout = attr.subnet_timeout; + + if (unlikely(subnet_timeout < 15)) + pr_warn("%s: subnet timeout %d may cause SRP login to fail.\n", + dev_name(&host->srp_dev->dev->dev), subnet_timeout); + + return subnet_timeout; } static int srp_send_req(struct srp_rdma_ch *ch, bool multich) @@ -706,6 +736,9 @@ static int srp_send_req(struct srp_rdma_ch *ch, bool multich) struct srp_login_req priv; } *req = NULL; int status; + u8 subnet_timeout; + + subnet_timeout = srp_get_subnet_timeout(target->srp_host); req = kzalloc(sizeof *req, GFP_KERNEL); if (!req) @@ -728,8 +761,8 @@ static int srp_send_req(struct srp_rdma_ch *ch, bool multich) * module parameters if anyone cared about setting them. */ req->param.responder_resources = 4; - req->param.remote_cm_response_timeout = 20; - req->param.local_cm_response_timeout = 20; + req->param.remote_cm_response_timeout = subnet_timeout + 2; + req->param.local_cm_response_timeout = subnet_timeout + 2; req->param.retry_count = target->tl_retry_count; req->param.rnr_retry_count = 7; req->param.max_cm_retries = 15; @@ -1279,7 +1312,6 @@ static int srp_map_finish_fmr(struct srp_map_state *state, { struct srp_target_port *target = ch->target; struct srp_device *dev = target->srp_host->srp_dev; - struct ib_pd *pd = target->pd; struct ib_pool_fmr *fmr; u64 io_addr = 0; @@ -1295,9 +1327,9 @@ static int srp_map_finish_fmr(struct srp_map_state *state, if (state->npages == 0) return 0; - if (state->npages == 1 && (pd->flags & IB_PD_UNSAFE_GLOBAL_RKEY)) { + if (state->npages == 1 && target->global_rkey) { srp_map_desc(state, state->base_dma_addr, state->dma_len, - pd->unsafe_global_rkey); + target->global_rkey); goto reset_state; } @@ -1337,7 +1369,6 @@ static int srp_map_finish_fr(struct srp_map_state *state, { struct srp_target_port *target = ch->target; struct srp_device *dev = target->srp_host->srp_dev; - struct ib_pd *pd = target->pd; struct ib_send_wr *bad_wr; struct ib_reg_wr wr; struct srp_fr_desc *desc; @@ -1353,12 +1384,12 @@ static int srp_map_finish_fr(struct srp_map_state *state, WARN_ON_ONCE(!dev->use_fast_reg); - if (sg_nents == 1 && (pd->flags & IB_PD_UNSAFE_GLOBAL_RKEY)) { + if (sg_nents == 1 && target->global_rkey) { unsigned int sg_offset = sg_offset_p ? *sg_offset_p : 0; srp_map_desc(state, sg_dma_address(state->sg) + sg_offset, sg_dma_len(state->sg) - sg_offset, - pd->unsafe_global_rkey); + target->global_rkey); if (sg_offset_p) *sg_offset_p = 0; return 1; @@ -1520,7 +1551,7 @@ static int srp_map_sg_dma(struct srp_map_state *state, struct srp_rdma_ch *ch, for_each_sg(scat, sg, count, i) { srp_map_desc(state, ib_sg_dma_address(dev->dev, sg), ib_sg_dma_len(dev->dev, sg), - target->pd->unsafe_global_rkey); + target->global_rkey); } return 0; @@ -1618,7 +1649,6 @@ static int srp_map_data(struct scsi_cmnd *scmnd, struct srp_rdma_ch *ch, struct srp_request *req) { struct srp_target_port *target = ch->target; - struct ib_pd *pd = target->pd; struct scatterlist *scat; struct srp_cmd *cmd = req->cmd->buf; int len, nents, count, ret; @@ -1654,7 +1684,7 @@ static int srp_map_data(struct scsi_cmnd *scmnd, struct srp_rdma_ch *ch, fmt = SRP_DATA_DESC_DIRECT; len = sizeof (struct srp_cmd) + sizeof (struct srp_direct_buf); - if (count == 1 && (pd->flags & IB_PD_UNSAFE_GLOBAL_RKEY)) { + if (count == 1 && target->global_rkey) { /* * The midlayer only generated a single gather/scatter * entry, or DMA mapping coalesced everything to a @@ -1664,7 +1694,7 @@ static int srp_map_data(struct scsi_cmnd *scmnd, struct srp_rdma_ch *ch, struct srp_direct_buf *buf = (void *) cmd->add_data; buf->va = cpu_to_be64(ib_sg_dma_address(ibdev, scat)); - buf->key = cpu_to_be32(pd->unsafe_global_rkey); + buf->key = cpu_to_be32(target->global_rkey); buf->len = cpu_to_be32(ib_sg_dma_len(ibdev, scat)); req->nmdesc = 0; @@ -1735,14 +1765,14 @@ static int srp_map_data(struct scsi_cmnd *scmnd, struct srp_rdma_ch *ch, memcpy(indirect_hdr->desc_list, req->indirect_desc, count * sizeof (struct srp_direct_buf)); - if (!(pd->flags & IB_PD_UNSAFE_GLOBAL_RKEY)) { + if (!target->global_rkey) { ret = srp_map_idb(ch, req, state.gen.next, state.gen.end, idb_len, &idb_rkey); if (ret < 0) goto unmap; req->nmdesc++; } else { - idb_rkey = cpu_to_be32(pd->unsafe_global_rkey); + idb_rkey = cpu_to_be32(target->global_rkey); } indirect_hdr->table_desc.va = cpu_to_be64(req->indirect_dma_addr); @@ -2403,7 +2433,7 @@ static void srp_cm_rej_handler(struct ib_cm_id *cm_id, switch (event->param.rej_rcvd.reason) { case IB_CM_REJ_PORT_CM_REDIRECT: cpi = event->param.rej_rcvd.ari; - sa_path_set_dlid(&ch->path, htonl(ntohs(cpi->redirect_lid))); + sa_path_set_dlid(&ch->path, ntohs(cpi->redirect_lid)); ch->path.pkey = cpi->redirect_pkey; cm_id->remote_cm_qpn = be32_to_cpu(cpi->redirect_qp) & 0x00ffffff; memcpy(ch->path.dgid.raw, cpi->redirect_gid, 16); @@ -3318,8 +3348,8 @@ static ssize_t srp_create_target(struct device *dev, target->io_class = SRP_REV16A_IB_IO_CLASS; target->scsi_host = target_host; target->srp_host = host; - target->pd = host->srp_dev->pd; target->lkey = host->srp_dev->pd->local_dma_lkey; + target->global_rkey = host->srp_dev->global_rkey; target->cmd_sg_cnt = cmd_sg_entries; target->sg_tablesize = indirect_sg_entries ? : cmd_sg_entries; target->allow_ext_sg = allow_ext_sg; @@ -3638,6 +3668,10 @@ static void srp_add_one(struct ib_device *device) if (IS_ERR(srp_dev->pd)) goto free_dev; + if (flags & IB_PD_UNSAFE_GLOBAL_RKEY) { + srp_dev->global_rkey = srp_dev->pd->unsafe_global_rkey; + WARN_ON_ONCE(srp_dev->global_rkey == 0); + } for (p = rdma_start_port(device); p <= rdma_end_port(device); ++p) { host = srp_add_port(srp_dev, p); diff --git a/drivers/infiniband/ulp/srp/ib_srp.h b/drivers/infiniband/ulp/srp/ib_srp.h index ab9077b81d5a..a814f5ef16f9 100644 --- a/drivers/infiniband/ulp/srp/ib_srp.h +++ b/drivers/infiniband/ulp/srp/ib_srp.h @@ -90,6 +90,7 @@ struct srp_device { struct list_head dev_list; struct ib_device *dev; struct ib_pd *pd; + u32 global_rkey; u64 mr_page_mask; int mr_page_size; int mr_max_size; @@ -179,7 +180,7 @@ struct srp_target_port { spinlock_t lock; /* read only in the hot path */ - struct ib_pd *pd; + u32 global_rkey; struct srp_rdma_ch *ch; u32 ch_count; u32 lkey; diff --git a/drivers/infiniband/ulp/srpt/ib_srpt.c b/drivers/infiniband/ulp/srpt/ib_srpt.c index 9e8e9220f816..304855b9b537 100644 --- a/drivers/infiniband/ulp/srpt/ib_srpt.c +++ b/drivers/infiniband/ulp/srpt/ib_srpt.c @@ -295,6 +295,7 @@ static void srpt_get_ioc(struct srpt_port *sport, u32 slot, { struct srpt_device *sdev = sport->sdev; struct ib_dm_ioc_profile *iocp; + int send_queue_depth; iocp = (struct ib_dm_ioc_profile *)mad->data; @@ -310,6 +311,12 @@ static void srpt_get_ioc(struct srpt_port *sport, u32 slot, return; } + if (sdev->use_srq) + send_queue_depth = sdev->srq_size; + else + send_queue_depth = min(SRPT_RQ_SIZE, + sdev->device->attrs.max_qp_wr); + memset(iocp, 0, sizeof(*iocp)); strcpy(iocp->id_string, SRPT_ID_STRING); iocp->guid = cpu_to_be64(srpt_service_guid); @@ -322,7 +329,7 @@ static void srpt_get_ioc(struct srpt_port *sport, u32 slot, iocp->io_subclass = cpu_to_be16(SRP_IO_SUBCLASS); iocp->protocol = cpu_to_be16(SRP_PROTOCOL); iocp->protocol_version = cpu_to_be16(SRP_PROTOCOL_VERSION); - iocp->send_queue_depth = cpu_to_be16(sdev->srq_size); + iocp->send_queue_depth = cpu_to_be16(send_queue_depth); iocp->rdma_read_depth = 4; iocp->send_size = cpu_to_be32(srp_max_req_size); iocp->rdma_size = cpu_to_be32(min(sport->port_attrib.srp_max_rdma_size, @@ -686,6 +693,9 @@ static void srpt_free_ioctx_ring(struct srpt_ioctx **ioctx_ring, { int i; + if (!ioctx_ring) + return; + for (i = 0; i < ring_size; ++i) srpt_free_ioctx(sdev, ioctx_ring[i], dma_size, dir); kfree(ioctx_ring); @@ -757,7 +767,7 @@ static bool srpt_test_and_set_cmd_state(struct srpt_send_ioctx *ioctx, /** * srpt_post_recv() - Post an IB receive request. */ -static int srpt_post_recv(struct srpt_device *sdev, +static int srpt_post_recv(struct srpt_device *sdev, struct srpt_rdma_ch *ch, struct srpt_recv_ioctx *ioctx) { struct ib_sge list; @@ -766,7 +776,7 @@ static int srpt_post_recv(struct srpt_device *sdev, BUG_ON(!sdev); list.addr = ioctx->ioctx.dma; list.length = srp_max_req_size; - list.lkey = sdev->pd->local_dma_lkey; + list.lkey = sdev->lkey; ioctx->ioctx.cqe.done = srpt_recv_done; wr.wr_cqe = &ioctx->ioctx.cqe; @@ -774,7 +784,10 @@ static int srpt_post_recv(struct srpt_device *sdev, wr.sg_list = &list; wr.num_sge = 1; - return ib_post_srq_recv(sdev->srq, &wr, &bad_wr); + if (sdev->use_srq) + return ib_post_srq_recv(sdev->srq, &wr, &bad_wr); + else + return ib_post_recv(ch->qp, &wr, &bad_wr); } /** @@ -1517,7 +1530,7 @@ static void srpt_handle_new_iu(struct srpt_rdma_ch *ch, break; } - srpt_post_recv(ch->sport->sdev, recv_ioctx); + srpt_post_recv(ch->sport->sdev, ch, recv_ioctx); return; out_wait: @@ -1616,7 +1629,7 @@ static int srpt_create_ch_ib(struct srpt_rdma_ch *ch) struct srpt_device *sdev = sport->sdev; const struct ib_device_attr *attrs = &sdev->device->attrs; u32 srp_sq_size = sport->port_attrib.srp_sq_size; - int ret; + int i, ret; WARN_ON(ch->rq_size < 1); @@ -1640,7 +1653,6 @@ retry: = (void(*)(struct ib_event *, void*))srpt_qp_event; qp_init->send_cq = ch->cq; qp_init->recv_cq = ch->cq; - qp_init->srq = sdev->srq; qp_init->sq_sig_type = IB_SIGNAL_REQ_WR; qp_init->qp_type = IB_QPT_RC; /* @@ -1650,10 +1662,16 @@ retry: * both both, as RDMA contexts will also post completions for the * RDMA READ case. */ - qp_init->cap.max_send_wr = srp_sq_size / 2; + qp_init->cap.max_send_wr = min(srp_sq_size / 2, attrs->max_qp_wr + 0U); qp_init->cap.max_rdma_ctxs = srp_sq_size / 2; qp_init->cap.max_send_sge = min(attrs->max_sge, SRPT_MAX_SG_PER_WQE); qp_init->port_num = ch->sport->port; + if (sdev->use_srq) { + qp_init->srq = sdev->srq; + } else { + qp_init->cap.max_recv_wr = ch->rq_size; + qp_init->cap.max_recv_sge = qp_init->cap.max_send_sge; + } ch->qp = ib_create_qp(sdev->pd, qp_init); if (IS_ERR(ch->qp)) { @@ -1669,6 +1687,10 @@ retry: goto err_destroy_cq; } + if (!sdev->use_srq) + for (i = 0; i < ch->rq_size; i++) + srpt_post_recv(sdev, ch, ch->ioctx_recv_ring[i]); + atomic_set(&ch->sq_wr_avail, qp_init->cap.max_send_wr); pr_debug("%s: max_cqe= %d max_sge= %d sq_size = %d cm_id= %p\n", @@ -1818,6 +1840,10 @@ static void srpt_release_channel_work(struct work_struct *w) ch->sport->sdev, ch->rq_size, ch->rsp_size, DMA_TO_DEVICE); + srpt_free_ioctx_ring((struct srpt_ioctx **)ch->ioctx_recv_ring, + sdev, ch->rq_size, + srp_max_req_size, DMA_FROM_DEVICE); + mutex_lock(&sdev->mutex); list_del_init(&ch->list); if (ch->release_done) @@ -1953,10 +1979,11 @@ static int srpt_cm_req_recv(struct ib_cm_id *cm_id, ch->cm_id = cm_id; cm_id->context = ch; /* - * Avoid QUEUE_FULL conditions by limiting the number of buffers used - * for the SRP protocol to the command queue size. + * ch->rq_size should be at least as large as the initiator queue + * depth to avoid that the initiator driver has to report QUEUE_FULL + * to the SCSI mid-layer. */ - ch->rq_size = SRPT_RQ_SIZE; + ch->rq_size = min(SRPT_RQ_SIZE, sdev->device->attrs.max_qp_wr); spin_lock_init(&ch->spinlock); ch->state = CH_CONNECTING; INIT_LIST_HEAD(&ch->cmd_wait_list); @@ -1974,6 +2001,19 @@ static int srpt_cm_req_recv(struct ib_cm_id *cm_id, ch->ioctx_ring[i]->ch = ch; list_add_tail(&ch->ioctx_ring[i]->free_list, &ch->free_list); } + if (!sdev->use_srq) { + ch->ioctx_recv_ring = (struct srpt_recv_ioctx **) + srpt_alloc_ioctx_ring(ch->sport->sdev, ch->rq_size, + sizeof(*ch->ioctx_recv_ring[0]), + srp_max_req_size, + DMA_FROM_DEVICE); + if (!ch->ioctx_recv_ring) { + pr_err("rejected SRP_LOGIN_REQ because creating a new QP RQ ring failed.\n"); + rej->reason = + cpu_to_be32(SRP_LOGIN_REJ_INSUFFICIENT_RESOURCES); + goto free_ring; + } + } ret = srpt_create_ch_ib(ch); if (ret) { @@ -1981,7 +2021,7 @@ static int srpt_cm_req_recv(struct ib_cm_id *cm_id, SRP_LOGIN_REJ_INSUFFICIENT_RESOURCES); pr_err("rejected SRP_LOGIN_REQ because creating" " a new RDMA channel failed.\n"); - goto free_ring; + goto free_recv_ring; } ret = srpt_ch_qp_rtr(ch, ch->qp); @@ -2072,6 +2112,11 @@ release_channel: destroy_ib: srpt_destroy_ch_ib(ch); +free_recv_ring: + srpt_free_ioctx_ring((struct srpt_ioctx **)ch->ioctx_recv_ring, + ch->sport->sdev, ch->rq_size, + srp_max_req_size, DMA_FROM_DEVICE); + free_ring: srpt_free_ioctx_ring((struct srpt_ioctx **)ch->ioctx_ring, ch->sport->sdev, ch->rq_size, @@ -2342,7 +2387,7 @@ static void srpt_queue_response(struct se_cmd *cmd) sge.addr = ioctx->ioctx.dma; sge.length = resp_len; - sge.lkey = sdev->pd->local_dma_lkey; + sge.lkey = sdev->lkey; ioctx->ioctx.cqe.done = srpt_send_done; send_wr.next = NULL; @@ -2490,6 +2535,8 @@ static void srpt_add_one(struct ib_device *device) if (IS_ERR(sdev->pd)) goto free_dev; + sdev->lkey = sdev->pd->local_dma_lkey; + sdev->srq_size = min(srpt_srq_size, sdev->device->attrs.max_srq_wr); srq_attr.event_handler = srpt_srq_event; @@ -2499,20 +2546,38 @@ static void srpt_add_one(struct ib_device *device) srq_attr.attr.srq_limit = 0; srq_attr.srq_type = IB_SRQT_BASIC; - sdev->srq = ib_create_srq(sdev->pd, &srq_attr); - if (IS_ERR(sdev->srq)) - goto err_pd; + sdev->srq = sdev->port[0].port_attrib.use_srq ? + ib_create_srq(sdev->pd, &srq_attr) : ERR_PTR(-ENOTSUPP); + if (IS_ERR(sdev->srq)) { + pr_debug("ib_create_srq() failed: %ld\n", PTR_ERR(sdev->srq)); + + /* SRQ not supported. */ + sdev->use_srq = false; + } else { + pr_debug("create SRQ #wr= %d max_allow=%d dev= %s\n", + sdev->srq_size, sdev->device->attrs.max_srq_wr, + device->name); + + sdev->use_srq = true; - pr_debug("%s: create SRQ #wr= %d max_allow=%d dev= %s\n", - __func__, sdev->srq_size, sdev->device->attrs.max_srq_wr, - device->name); + sdev->ioctx_ring = (struct srpt_recv_ioctx **) + srpt_alloc_ioctx_ring(sdev, sdev->srq_size, + sizeof(*sdev->ioctx_ring[0]), + srp_max_req_size, + DMA_FROM_DEVICE); + if (!sdev->ioctx_ring) + goto err_pd; + + for (i = 0; i < sdev->srq_size; ++i) + srpt_post_recv(sdev, NULL, sdev->ioctx_ring[i]); + } if (!srpt_service_guid) srpt_service_guid = be64_to_cpu(device->node_guid); sdev->cm_id = ib_create_cm_id(device, srpt_cm_handler, sdev); if (IS_ERR(sdev->cm_id)) - goto err_srq; + goto err_ring; /* print out target login information */ pr_debug("Target login info: id_ext=%016llx,ioc_guid=%016llx," @@ -2532,16 +2597,6 @@ static void srpt_add_one(struct ib_device *device) srpt_event_handler); ib_register_event_handler(&sdev->event_handler); - sdev->ioctx_ring = (struct srpt_recv_ioctx **) - srpt_alloc_ioctx_ring(sdev, sdev->srq_size, - sizeof(*sdev->ioctx_ring[0]), - srp_max_req_size, DMA_FROM_DEVICE); - if (!sdev->ioctx_ring) - goto err_event; - - for (i = 0; i < sdev->srq_size; ++i) - srpt_post_recv(sdev, sdev->ioctx_ring[i]); - WARN_ON(sdev->device->phys_port_cnt > ARRAY_SIZE(sdev->port)); for (i = 1; i <= sdev->device->phys_port_cnt; i++) { @@ -2551,12 +2606,13 @@ static void srpt_add_one(struct ib_device *device) sport->port_attrib.srp_max_rdma_size = DEFAULT_MAX_RDMA_SIZE; sport->port_attrib.srp_max_rsp_size = DEFAULT_MAX_RSP_SIZE; sport->port_attrib.srp_sq_size = DEF_SRPT_SQ_SIZE; + sport->port_attrib.use_srq = false; INIT_WORK(&sport->work, srpt_refresh_port_work); if (srpt_refresh_port(sport)) { pr_err("MAD registration failed for %s-%d.\n", sdev->device->name, i); - goto err_ring; + goto err_event; } } @@ -2569,16 +2625,16 @@ out: pr_debug("added %s.\n", device->name); return; -err_ring: - srpt_free_ioctx_ring((struct srpt_ioctx **)sdev->ioctx_ring, sdev, - sdev->srq_size, srp_max_req_size, - DMA_FROM_DEVICE); err_event: ib_unregister_event_handler(&sdev->event_handler); err_cm: ib_destroy_cm_id(sdev->cm_id); -err_srq: - ib_destroy_srq(sdev->srq); +err_ring: + if (sdev->use_srq) + ib_destroy_srq(sdev->srq); + srpt_free_ioctx_ring((struct srpt_ioctx **)sdev->ioctx_ring, sdev, + sdev->srq_size, srp_max_req_size, + DMA_FROM_DEVICE); err_pd: ib_dealloc_pd(sdev->pd); free_dev: @@ -2622,12 +2678,12 @@ static void srpt_remove_one(struct ib_device *device, void *client_data) spin_unlock(&srpt_dev_lock); srpt_release_sdev(sdev); - ib_destroy_srq(sdev->srq); - ib_dealloc_pd(sdev->pd); - + if (sdev->use_srq) + ib_destroy_srq(sdev->srq); srpt_free_ioctx_ring((struct srpt_ioctx **)sdev->ioctx_ring, sdev, sdev->srq_size, srp_max_req_size, DMA_FROM_DEVICE); - sdev->ioctx_ring = NULL; + ib_dealloc_pd(sdev->pd); + kfree(sdev); } @@ -2777,7 +2833,7 @@ static int srpt_parse_i_port_id(u8 i_port_id[16], const char *name) { const char *p; unsigned len, count, leading_zero_bytes; - int ret, rc; + int ret; p = name; if (strncasecmp(p, "0x", 2) == 0) @@ -2789,10 +2845,9 @@ static int srpt_parse_i_port_id(u8 i_port_id[16], const char *name) count = min(len / 2, 16U); leading_zero_bytes = 16 - count; memset(i_port_id, 0, leading_zero_bytes); - rc = hex2bin(i_port_id + leading_zero_bytes, p, count); - if (rc < 0) - pr_debug("hex2bin failed for srpt_parse_i_port_id: %d\n", rc); - ret = 0; + ret = hex2bin(i_port_id + leading_zero_bytes, p, count); + if (ret < 0) + pr_debug("hex2bin failed for srpt_parse_i_port_id: %d\n", ret); out: return ret; } @@ -2926,14 +2981,43 @@ static ssize_t srpt_tpg_attrib_srp_sq_size_store(struct config_item *item, return count; } +static ssize_t srpt_tpg_attrib_use_srq_show(struct config_item *item, + char *page) +{ + struct se_portal_group *se_tpg = attrib_to_tpg(item); + struct srpt_port *sport = srpt_tpg_to_sport(se_tpg); + + return sprintf(page, "%d\n", sport->port_attrib.use_srq); +} + +static ssize_t srpt_tpg_attrib_use_srq_store(struct config_item *item, + const char *page, size_t count) +{ + struct se_portal_group *se_tpg = attrib_to_tpg(item); + struct srpt_port *sport = srpt_tpg_to_sport(se_tpg); + unsigned long val; + int ret; + + ret = kstrtoul(page, 0, &val); + if (ret < 0) + return ret; + if (val != !!val) + return -EINVAL; + sport->port_attrib.use_srq = val; + + return count; +} + CONFIGFS_ATTR(srpt_tpg_attrib_, srp_max_rdma_size); CONFIGFS_ATTR(srpt_tpg_attrib_, srp_max_rsp_size); CONFIGFS_ATTR(srpt_tpg_attrib_, srp_sq_size); +CONFIGFS_ATTR(srpt_tpg_attrib_, use_srq); static struct configfs_attribute *srpt_tpg_attrib_attrs[] = { &srpt_tpg_attrib_attr_srp_max_rdma_size, &srpt_tpg_attrib_attr_srp_max_rsp_size, &srpt_tpg_attrib_attr_srp_sq_size, + &srpt_tpg_attrib_attr_use_srq, NULL, }; diff --git a/drivers/infiniband/ulp/srpt/ib_srpt.h b/drivers/infiniband/ulp/srpt/ib_srpt.h index 1b817e51b84b..673387d365a3 100644 --- a/drivers/infiniband/ulp/srpt/ib_srpt.h +++ b/drivers/infiniband/ulp/srpt/ib_srpt.h @@ -252,6 +252,7 @@ enum rdma_ch_state { * @free_list: Head of list with free send I/O contexts. * @state: channel state. See also enum rdma_ch_state. * @ioctx_ring: Send ring. + * @ioctx_recv_ring: Receive I/O context ring. * @list: Node for insertion in the srpt_device.rch_list list. * @cmd_wait_list: List of SCSI commands that arrived before the RTU event. This * list contains struct srpt_ioctx elements and is protected @@ -281,6 +282,7 @@ struct srpt_rdma_ch { struct list_head free_list; enum rdma_ch_state state; struct srpt_send_ioctx **ioctx_ring; + struct srpt_recv_ioctx **ioctx_recv_ring; struct list_head list; struct list_head cmd_wait_list; struct se_session *sess; @@ -295,11 +297,13 @@ struct srpt_rdma_ch { * @srp_max_rdma_size: Maximum size of SRP RDMA transfers for new connections. * @srp_max_rsp_size: Maximum size of SRP response messages in bytes. * @srp_sq_size: Shared receive queue (SRQ) size. + * @use_srq: Whether or not to use SRQ. */ struct srpt_port_attrib { u32 srp_max_rdma_size; u32 srp_max_rsp_size; u32 srp_sq_size; + bool use_srq; }; /** @@ -343,10 +347,11 @@ struct srpt_port { * struct srpt_device - Information associated by SRPT with a single HCA. * @device: Backpointer to the struct ib_device managed by the IB core. * @pd: IB protection domain. - * @mr: L_Key (local key) with write access to all local memory. + * @lkey: L_Key (local key) with write access to all local memory. * @srq: Per-HCA SRQ (shared receive queue). * @cm_id: Connection identifier. * @srq_size: SRQ size. + * @use_srq: Whether or not to use SRQ. * @ioctx_ring: Per-HCA SRQ. * @rch_list: Per-device channel list -- see also srpt_rdma_ch.list. * @ch_releaseQ: Enables waiting for removal from rch_list. @@ -358,9 +363,11 @@ struct srpt_port { struct srpt_device { struct ib_device *device; struct ib_pd *pd; + u32 lkey; struct ib_srq *srq; struct ib_cm_id *cm_id; int srq_size; + bool use_srq; struct srpt_recv_ioctx **ioctx_ring; struct list_head rch_list; wait_queue_head_t ch_releaseQ; diff --git a/drivers/iommu/amd_iommu_init.c b/drivers/iommu/amd_iommu_init.c index 382de42b8359..6fe2d0346073 100644 --- a/drivers/iommu/amd_iommu_init.c +++ b/drivers/iommu/amd_iommu_init.c @@ -874,7 +874,7 @@ static bool copy_device_table(void) hi = readl(iommu->mmio_base + MMIO_DEV_TABLE_OFFSET + 4); entry = (((u64) hi) << 32) + lo; if (last_entry && last_entry != entry) { - pr_err("IOMMU:%d should use the same dev table as others!/n", + pr_err("IOMMU:%d should use the same dev table as others!\n", iommu->index); return false; } @@ -882,7 +882,7 @@ static bool copy_device_table(void) old_devtb_size = ((entry & ~PAGE_MASK) + 1) << 12; if (old_devtb_size != dev_table_size) { - pr_err("The device table size of IOMMU:%d is not expected!/n", + pr_err("The device table size of IOMMU:%d is not expected!\n", iommu->index); return false; } @@ -890,7 +890,7 @@ static bool copy_device_table(void) old_devtb_phys = entry & PAGE_MASK; if (old_devtb_phys >= 0x100000000ULL) { - pr_err("The address of old device table is above 4G, not trustworthy!/n"); + pr_err("The address of old device table is above 4G, not trustworthy!\n"); return false; } old_devtb = memremap(old_devtb_phys, dev_table_size, MEMREMAP_WB); @@ -901,7 +901,7 @@ static bool copy_device_table(void) old_dev_tbl_cpy = (void *)__get_free_pages(gfp_flag, get_order(dev_table_size)); if (old_dev_tbl_cpy == NULL) { - pr_err("Failed to allocate memory for copying old device table!/n"); + pr_err("Failed to allocate memory for copying old device table!\n"); return false; } diff --git a/drivers/iommu/io-pgtable-arm-v7s.c b/drivers/iommu/io-pgtable-arm-v7s.c index d665d0dc16e8..6961fc393f0b 100644 --- a/drivers/iommu/io-pgtable-arm-v7s.c +++ b/drivers/iommu/io-pgtable-arm-v7s.c @@ -245,7 +245,7 @@ static void __arm_v7s_free_table(void *table, int lvl, static void __arm_v7s_pte_sync(arm_v7s_iopte *ptep, int num_entries, struct io_pgtable_cfg *cfg) { - if (!(cfg->quirks & IO_PGTABLE_QUIRK_NO_DMA)) + if (cfg->quirks & IO_PGTABLE_QUIRK_NO_DMA) return; dma_sync_single_for_device(cfg->iommu_dev, __arm_v7s_dma_addr(ptep), diff --git a/drivers/iommu/mtk_iommu.c b/drivers/iommu/mtk_iommu.c index bd515be5b380..16d33ac19db0 100644 --- a/drivers/iommu/mtk_iommu.c +++ b/drivers/iommu/mtk_iommu.c @@ -371,7 +371,8 @@ static int mtk_iommu_map(struct iommu_domain *domain, unsigned long iova, int ret; spin_lock_irqsave(&dom->pgtlock, flags); - ret = dom->iop->map(dom->iop, iova, paddr, size, prot); + ret = dom->iop->map(dom->iop, iova, paddr & DMA_BIT_MASK(32), + size, prot); spin_unlock_irqrestore(&dom->pgtlock, flags); return ret; diff --git a/drivers/irqchip/irq-mips-gic.c b/drivers/irqchip/irq-mips-gic.c index 40159ac12ac8..c90976d7e53c 100644 --- a/drivers/irqchip/irq-mips-gic.c +++ b/drivers/irqchip/irq-mips-gic.c @@ -175,14 +175,13 @@ static void gic_mask_irq(struct irq_data *d) static void gic_unmask_irq(struct irq_data *d) { - struct cpumask *affinity = irq_data_get_affinity_mask(d); unsigned int intr = GIC_HWIRQ_TO_SHARED(d->hwirq); unsigned int cpu; write_gic_smask(intr); gic_clear_pcpu_masks(intr); - cpu = cpumask_first_and(affinity, cpu_online_mask); + cpu = cpumask_first(irq_data_get_effective_affinity_mask(d)); set_bit(intr, per_cpu_ptr(pcpu_masks, cpu)); } @@ -420,13 +419,17 @@ static int gic_shared_irq_domain_map(struct irq_domain *d, unsigned int virq, irq_hw_number_t hw, unsigned int cpu) { int intr = GIC_HWIRQ_TO_SHARED(hw); + struct irq_data *data; unsigned long flags; + data = irq_get_irq_data(virq); + spin_lock_irqsave(&gic_lock, flags); write_gic_map_pin(intr, GIC_MAP_PIN_MAP_TO_PIN | gic_cpu_pin); write_gic_map_vp(intr, BIT(mips_cm_vp_id(cpu))); gic_clear_pcpu_masks(intr); set_bit(intr, per_cpu_ptr(pcpu_masks, cpu)); + irq_data_update_effective_affinity(data, cpumask_of(cpu)); spin_unlock_irqrestore(&gic_lock, flags); return 0; @@ -645,7 +648,7 @@ static int __init gic_of_init(struct device_node *node, /* Find the first available CPU vector. */ i = 0; - reserved = (C_SW0 | C_SW1) >> __fls(C_SW0); + reserved = (C_SW0 | C_SW1) >> __ffs(C_SW0); while (!of_property_read_u32_index(node, "mti,reserved-cpu-vectors", i++, &cpu_vec)) reserved |= BIT(cpu_vec); @@ -684,11 +687,11 @@ static int __init gic_of_init(struct device_node *node, gicconfig = read_gic_config(); gic_shared_intrs = gicconfig & GIC_CONFIG_NUMINTERRUPTS; - gic_shared_intrs >>= __fls(GIC_CONFIG_NUMINTERRUPTS); + gic_shared_intrs >>= __ffs(GIC_CONFIG_NUMINTERRUPTS); gic_shared_intrs = (gic_shared_intrs + 1) * 8; gic_vpes = gicconfig & GIC_CONFIG_PVPS; - gic_vpes >>= __fls(GIC_CONFIG_PVPS); + gic_vpes >>= __ffs(GIC_CONFIG_PVPS); gic_vpes = gic_vpes + 1; if (cpu_has_veic) { diff --git a/drivers/leds/leds-as3645a.c b/drivers/leds/leds-as3645a.c index bbbbe0898233..9a257f969300 100644 --- a/drivers/leds/leds-as3645a.c +++ b/drivers/leds/leds-as3645a.c @@ -112,6 +112,10 @@ #define AS_PEAK_mA_TO_REG(a) \ ((min_t(u32, AS_PEAK_mA_MAX, a) - 1250) / 250) +/* LED numbers for Devicetree */ +#define AS_LED_FLASH 0 +#define AS_LED_INDICATOR 1 + enum as_mode { AS_MODE_EXT_TORCH = 0 << AS_CONTROL_MODE_SETTING_SHIFT, AS_MODE_INDICATOR = 1 << AS_CONTROL_MODE_SETTING_SHIFT, @@ -491,10 +495,29 @@ static int as3645a_parse_node(struct as3645a *flash, struct device_node *node) { struct as3645a_config *cfg = &flash->cfg; + struct device_node *child; const char *name; int rval; - flash->flash_node = of_get_child_by_name(node, "flash"); + for_each_child_of_node(node, child) { + u32 id = 0; + + of_property_read_u32(child, "reg", &id); + + switch (id) { + case AS_LED_FLASH: + flash->flash_node = of_node_get(child); + break; + case AS_LED_INDICATOR: + flash->indicator_node = of_node_get(child); + break; + default: + dev_warn(&flash->client->dev, + "unknown LED %u encountered, ignoring\n", id); + break; + } + } + if (!flash->flash_node) { dev_err(&flash->client->dev, "can't find flash node\n"); return -ENODEV; @@ -534,11 +557,10 @@ static int as3645a_parse_node(struct as3645a *flash, of_property_read_u32(flash->flash_node, "voltage-reference", &cfg->voltage_reference); - of_property_read_u32(flash->flash_node, "peak-current-limit", + of_property_read_u32(flash->flash_node, "ams,input-max-microamp", &cfg->peak); cfg->peak = AS_PEAK_mA_TO_REG(cfg->peak); - flash->indicator_node = of_get_child_by_name(node, "indicator"); if (!flash->indicator_node) { dev_warn(&flash->client->dev, "can't find indicator node\n"); @@ -721,6 +743,7 @@ static int as3645a_remove(struct i2c_client *client) as3645a_set_control(flash, AS_MODE_EXT_TORCH, false); v4l2_flash_release(flash->vf); + v4l2_flash_release(flash->vfind); led_classdev_flash_unregister(&flash->fled); led_classdev_unregister(&flash->iled_cdev); diff --git a/drivers/md/bcache/closure.c b/drivers/md/bcache/closure.c index 7d5286b05036..1841d0359bac 100644 --- a/drivers/md/bcache/closure.c +++ b/drivers/md/bcache/closure.c @@ -64,7 +64,7 @@ EXPORT_SYMBOL(closure_put); void __closure_wake_up(struct closure_waitlist *wait_list) { struct llist_node *list; - struct closure *cl; + struct closure *cl, *t; struct llist_node *reverse = NULL; list = llist_del_all(&wait_list->list); @@ -73,7 +73,7 @@ void __closure_wake_up(struct closure_waitlist *wait_list) reverse = llist_reverse_order(list); /* Then do the wakeups */ - llist_for_each_entry(cl, reverse, list) { + llist_for_each_entry_safe(cl, t, reverse, list) { closure_set_waiting(cl, 0); closure_sub(cl, CLOSURE_WAITING + 1); } diff --git a/drivers/md/dm-core.h b/drivers/md/dm-core.h index 24eddbdf2ab4..203144762f36 100644 --- a/drivers/md/dm-core.h +++ b/drivers/md/dm-core.h @@ -149,5 +149,6 @@ static inline bool dm_message_test_buffer_overflow(char *result, unsigned maxlen extern atomic_t dm_global_event_nr; extern wait_queue_head_t dm_global_eventq; +void dm_issue_global_event(void); #endif diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c index a55ffd4f5933..96ab46512e1f 100644 --- a/drivers/md/dm-crypt.c +++ b/drivers/md/dm-crypt.c @@ -2466,6 +2466,7 @@ static int crypt_ctr_cipher_old(struct dm_target *ti, char *cipher_in, char *key kfree(cipher_api); return ret; } + kfree(cipher_api); return 0; bad_mem: @@ -2584,6 +2585,10 @@ static int crypt_ctr_optional(struct dm_target *ti, unsigned int argc, char **ar ti->error = "Invalid feature value for sector_size"; return -EINVAL; } + if (ti->len & ((cc->sector_size >> SECTOR_SHIFT) - 1)) { + ti->error = "Device size is not multiple of sector_size feature"; + return -EINVAL; + } cc->sector_shift = __ffs(cc->sector_size) - SECTOR_SHIFT; } else if (!strcasecmp(opt_string, "iv_large_sectors")) set_bit(CRYPT_IV_LARGE_SECTORS, &cc->cipher_flags); diff --git a/drivers/md/dm-ioctl.c b/drivers/md/dm-ioctl.c index 8756a6850431..e52676fa9832 100644 --- a/drivers/md/dm-ioctl.c +++ b/drivers/md/dm-ioctl.c @@ -477,9 +477,13 @@ static int remove_all(struct file *filp, struct dm_ioctl *param, size_t param_si * Round up the ptr to an 8-byte boundary. */ #define ALIGN_MASK 7 +static inline size_t align_val(size_t val) +{ + return (val + ALIGN_MASK) & ~ALIGN_MASK; +} static inline void *align_ptr(void *ptr) { - return (void *) (((size_t) (ptr + ALIGN_MASK)) & ~ALIGN_MASK); + return (void *)align_val((size_t)ptr); } /* @@ -505,7 +509,7 @@ static int list_devices(struct file *filp, struct dm_ioctl *param, size_t param_ struct hash_cell *hc; size_t len, needed = 0; struct gendisk *disk; - struct dm_name_list *nl, *old_nl = NULL; + struct dm_name_list *orig_nl, *nl, *old_nl = NULL; uint32_t *event_nr; down_write(&_hash_lock); @@ -516,17 +520,15 @@ static int list_devices(struct file *filp, struct dm_ioctl *param, size_t param_ */ for (i = 0; i < NUM_BUCKETS; i++) { list_for_each_entry (hc, _name_buckets + i, name_list) { - needed += sizeof(struct dm_name_list); - needed += strlen(hc->name) + 1; - needed += ALIGN_MASK; - needed += (sizeof(uint32_t) + ALIGN_MASK) & ~ALIGN_MASK; + needed += align_val(offsetof(struct dm_name_list, name) + strlen(hc->name) + 1); + needed += align_val(sizeof(uint32_t)); } } /* * Grab our output buffer. */ - nl = get_result_buffer(param, param_size, &len); + nl = orig_nl = get_result_buffer(param, param_size, &len); if (len < needed) { param->flags |= DM_BUFFER_FULL_FLAG; goto out; @@ -549,11 +551,16 @@ static int list_devices(struct file *filp, struct dm_ioctl *param, size_t param_ strcpy(nl->name, hc->name); old_nl = nl; - event_nr = align_ptr(((void *) (nl + 1)) + strlen(hc->name) + 1); + event_nr = align_ptr(nl->name + strlen(hc->name) + 1); *event_nr = dm_get_event_nr(hc->md); nl = align_ptr(event_nr + 1); } } + /* + * If mismatch happens, security may be compromised due to buffer + * overflow, so it's better to crash. + */ + BUG_ON((char *)nl - (char *)orig_nl != needed); out: up_write(&_hash_lock); @@ -1621,7 +1628,8 @@ static int target_message(struct file *filp, struct dm_ioctl *param, size_t para * which has a variable size, is not used by the function processing * the ioctl. */ -#define IOCTL_FLAGS_NO_PARAMS 1 +#define IOCTL_FLAGS_NO_PARAMS 1 +#define IOCTL_FLAGS_ISSUE_GLOBAL_EVENT 2 /*----------------------------------------------------------------- * Implementation of open/close/ioctl on the special char @@ -1635,12 +1643,12 @@ static ioctl_fn lookup_ioctl(unsigned int cmd, int *ioctl_flags) ioctl_fn fn; } _ioctls[] = { {DM_VERSION_CMD, 0, NULL}, /* version is dealt with elsewhere */ - {DM_REMOVE_ALL_CMD, IOCTL_FLAGS_NO_PARAMS, remove_all}, + {DM_REMOVE_ALL_CMD, IOCTL_FLAGS_NO_PARAMS | IOCTL_FLAGS_ISSUE_GLOBAL_EVENT, remove_all}, {DM_LIST_DEVICES_CMD, 0, list_devices}, - {DM_DEV_CREATE_CMD, IOCTL_FLAGS_NO_PARAMS, dev_create}, - {DM_DEV_REMOVE_CMD, IOCTL_FLAGS_NO_PARAMS, dev_remove}, - {DM_DEV_RENAME_CMD, 0, dev_rename}, + {DM_DEV_CREATE_CMD, IOCTL_FLAGS_NO_PARAMS | IOCTL_FLAGS_ISSUE_GLOBAL_EVENT, dev_create}, + {DM_DEV_REMOVE_CMD, IOCTL_FLAGS_NO_PARAMS | IOCTL_FLAGS_ISSUE_GLOBAL_EVENT, dev_remove}, + {DM_DEV_RENAME_CMD, IOCTL_FLAGS_ISSUE_GLOBAL_EVENT, dev_rename}, {DM_DEV_SUSPEND_CMD, IOCTL_FLAGS_NO_PARAMS, dev_suspend}, {DM_DEV_STATUS_CMD, IOCTL_FLAGS_NO_PARAMS, dev_status}, {DM_DEV_WAIT_CMD, 0, dev_wait}, @@ -1869,6 +1877,9 @@ static int ctl_ioctl(struct file *file, uint command, struct dm_ioctl __user *us unlikely(ioctl_flags & IOCTL_FLAGS_NO_PARAMS)) DMERR("ioctl %d tried to output some data but has IOCTL_FLAGS_NO_PARAMS set", cmd); + if (!r && ioctl_flags & IOCTL_FLAGS_ISSUE_GLOBAL_EVENT) + dm_issue_global_event(); + /* * Copy the results back to userland. */ diff --git a/drivers/md/dm-raid.c b/drivers/md/dm-raid.c index 5bfe285ea9d1..2245d06d2045 100644 --- a/drivers/md/dm-raid.c +++ b/drivers/md/dm-raid.c @@ -3238,7 +3238,7 @@ static int raid_map(struct dm_target *ti, struct bio *bio) if (unlikely(bio_end_sector(bio) > mddev->array_sectors)) return DM_MAPIO_REQUEUE; - mddev->pers->make_request(mddev, bio); + md_handle_request(mddev, bio); return DM_MAPIO_SUBMITTED; } @@ -3297,11 +3297,10 @@ static const char *__raid_dev_status(struct raid_set *rs, struct md_rdev *rdev, static sector_t rs_get_progress(struct raid_set *rs, sector_t resync_max_sectors, bool *array_in_sync) { - sector_t r, recovery_cp, curr_resync_completed; + sector_t r, curr_resync_completed; struct mddev *mddev = &rs->md; curr_resync_completed = mddev->curr_resync_completed ?: mddev->recovery_cp; - recovery_cp = mddev->recovery_cp; *array_in_sync = false; if (rs_is_raid0(rs)) { @@ -3330,9 +3329,11 @@ static sector_t rs_get_progress(struct raid_set *rs, } else if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery)) r = curr_resync_completed; else - r = recovery_cp; + r = mddev->recovery_cp; - if (r == MaxSector) { + if ((r == MaxSector) || + (test_bit(MD_RECOVERY_DONE, &mddev->recovery) && + (mddev->curr_resync_completed == resync_max_sectors))) { /* * Sync complete. */ @@ -3892,7 +3893,7 @@ static void raid_resume(struct dm_target *ti) static struct target_type raid_target = { .name = "raid", - .version = {1, 12, 1}, + .version = {1, 13, 0}, .module = THIS_MODULE, .ctr = raid_ctr, .dtr = raid_dtr, diff --git a/drivers/md/dm.c b/drivers/md/dm.c index 6e54145969c5..4be85324f44d 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -52,6 +52,12 @@ static struct workqueue_struct *deferred_remove_workqueue; atomic_t dm_global_event_nr = ATOMIC_INIT(0); DECLARE_WAIT_QUEUE_HEAD(dm_global_eventq); +void dm_issue_global_event(void) +{ + atomic_inc(&dm_global_event_nr); + wake_up(&dm_global_eventq); +} + /* * One of these is allocated per bio. */ @@ -1865,9 +1871,8 @@ static void event_callback(void *context) dm_send_uevents(&uevents, &disk_to_dev(md->disk)->kobj); atomic_inc(&md->event_nr); - atomic_inc(&dm_global_event_nr); wake_up(&md->eventq); - wake_up(&dm_global_eventq); + dm_issue_global_event(); } /* @@ -2283,6 +2288,7 @@ struct dm_table *dm_swap_table(struct mapped_device *md, struct dm_table *table) } map = __bind(md, table, &limits); + dm_issue_global_event(); out: mutex_unlock(&md->suspend_lock); diff --git a/drivers/md/md.c b/drivers/md/md.c index 08fcaebc61bd..0ff1bbf6c90e 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -266,6 +266,37 @@ static DEFINE_SPINLOCK(all_mddevs_lock); * call has finished, the bio has been linked into some internal structure * and so is visible to ->quiesce(), so we don't need the refcount any more. */ +void md_handle_request(struct mddev *mddev, struct bio *bio) +{ +check_suspended: + rcu_read_lock(); + if (mddev->suspended) { + DEFINE_WAIT(__wait); + for (;;) { + prepare_to_wait(&mddev->sb_wait, &__wait, + TASK_UNINTERRUPTIBLE); + if (!mddev->suspended) + break; + rcu_read_unlock(); + schedule(); + rcu_read_lock(); + } + finish_wait(&mddev->sb_wait, &__wait); + } + atomic_inc(&mddev->active_io); + rcu_read_unlock(); + + if (!mddev->pers->make_request(mddev, bio)) { + atomic_dec(&mddev->active_io); + wake_up(&mddev->sb_wait); + goto check_suspended; + } + + if (atomic_dec_and_test(&mddev->active_io) && mddev->suspended) + wake_up(&mddev->sb_wait); +} +EXPORT_SYMBOL(md_handle_request); + static blk_qc_t md_make_request(struct request_queue *q, struct bio *bio) { const int rw = bio_data_dir(bio); @@ -285,23 +316,6 @@ static blk_qc_t md_make_request(struct request_queue *q, struct bio *bio) bio_endio(bio); return BLK_QC_T_NONE; } -check_suspended: - rcu_read_lock(); - if (mddev->suspended) { - DEFINE_WAIT(__wait); - for (;;) { - prepare_to_wait(&mddev->sb_wait, &__wait, - TASK_UNINTERRUPTIBLE); - if (!mddev->suspended) - break; - rcu_read_unlock(); - schedule(); - rcu_read_lock(); - } - finish_wait(&mddev->sb_wait, &__wait); - } - atomic_inc(&mddev->active_io); - rcu_read_unlock(); /* * save the sectors now since our bio can @@ -310,20 +324,14 @@ check_suspended: sectors = bio_sectors(bio); /* bio could be mergeable after passing to underlayer */ bio->bi_opf &= ~REQ_NOMERGE; - if (!mddev->pers->make_request(mddev, bio)) { - atomic_dec(&mddev->active_io); - wake_up(&mddev->sb_wait); - goto check_suspended; - } + + md_handle_request(mddev, bio); cpu = part_stat_lock(); part_stat_inc(cpu, &mddev->gendisk->part0, ios[rw]); part_stat_add(cpu, &mddev->gendisk->part0, sectors[rw], sectors); part_stat_unlock(); - if (atomic_dec_and_test(&mddev->active_io) && mddev->suspended) - wake_up(&mddev->sb_wait); - return BLK_QC_T_NONE; } @@ -439,16 +447,22 @@ static void md_submit_flush_data(struct work_struct *ws) struct mddev *mddev = container_of(ws, struct mddev, flush_work); struct bio *bio = mddev->flush_bio; + /* + * must reset flush_bio before calling into md_handle_request to avoid a + * deadlock, because other bios passed md_handle_request suspend check + * could wait for this and below md_handle_request could wait for those + * bios because of suspend check + */ + mddev->flush_bio = NULL; + wake_up(&mddev->sb_wait); + if (bio->bi_iter.bi_size == 0) /* an empty barrier - all done */ bio_endio(bio); else { bio->bi_opf &= ~REQ_PREFLUSH; - mddev->pers->make_request(mddev, bio); + md_handle_request(mddev, bio); } - - mddev->flush_bio = NULL; - wake_up(&mddev->sb_wait); } void md_flush_request(struct mddev *mddev, struct bio *bio) diff --git a/drivers/md/md.h b/drivers/md/md.h index 561d22b9a9a8..d8287d3cd1bf 100644 --- a/drivers/md/md.h +++ b/drivers/md/md.h @@ -692,6 +692,7 @@ extern void md_stop_writes(struct mddev *mddev); extern int md_rdev_init(struct md_rdev *rdev); extern void md_rdev_clear(struct md_rdev *rdev); +extern void md_handle_request(struct mddev *mddev, struct bio *bio); extern void mddev_suspend(struct mddev *mddev); extern void mddev_resume(struct mddev *mddev); extern struct bio *bio_alloc_mddev(gfp_t gfp_mask, int nr_iovecs, diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index 076409455b60..928e24a07133 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -6575,14 +6575,17 @@ static ssize_t raid5_store_group_thread_cnt(struct mddev *mddev, const char *page, size_t len) { struct r5conf *conf; - unsigned long new; + unsigned int new; int err; struct r5worker_group *new_groups, *old_groups; int group_cnt, worker_cnt_per_group; if (len >= PAGE_SIZE) return -EINVAL; - if (kstrtoul(page, 10, &new)) + if (kstrtouint(page, 10, &new)) + return -EINVAL; + /* 8192 should be big enough */ + if (new > 8192) return -EINVAL; err = mddev_lock(mddev); diff --git a/drivers/media/rc/ir-sharp-decoder.c b/drivers/media/rc/ir-sharp-decoder.c index ed43a4212479..129b558acc92 100644 --- a/drivers/media/rc/ir-sharp-decoder.c +++ b/drivers/media/rc/ir-sharp-decoder.c @@ -245,5 +245,5 @@ module_init(ir_sharp_decode_init); module_exit(ir_sharp_decode_exit); MODULE_LICENSE("GPL"); -MODULE_AUTHOR("James Hogan <james.hogan@imgtec.com>"); +MODULE_AUTHOR("James Hogan <jhogan@kernel.org>"); MODULE_DESCRIPTION("Sharp IR protocol decoder"); diff --git a/drivers/misc/cxl/cxllib.c b/drivers/misc/cxl/cxllib.c index 5dba23ca2e5f..dc9bc1807fdf 100644 --- a/drivers/misc/cxl/cxllib.c +++ b/drivers/misc/cxl/cxllib.c @@ -219,8 +219,17 @@ int cxllib_handle_fault(struct mm_struct *mm, u64 addr, u64 size, u64 flags) down_read(&mm->mmap_sem); - for (dar = addr; dar < addr + size; dar += page_size) { - if (!vma || dar < vma->vm_start || dar > vma->vm_end) { + vma = find_vma(mm, addr); + if (!vma) { + pr_err("Can't find vma for addr %016llx\n", addr); + rc = -EFAULT; + goto out; + } + /* get the size of the pages allocated */ + page_size = vma_kernel_pagesize(vma); + + for (dar = (addr & ~(page_size - 1)); dar < (addr + size); dar += page_size) { + if (dar < vma->vm_start || dar >= vma->vm_end) { vma = find_vma(mm, addr); if (!vma) { pr_err("Can't find vma for addr %016llx\n", addr); diff --git a/drivers/mmc/core/block.c b/drivers/mmc/core/block.c index 29fc1e662891..2ad7b5c69156 100644 --- a/drivers/mmc/core/block.c +++ b/drivers/mmc/core/block.c @@ -1634,8 +1634,6 @@ static void mmc_blk_data_prep(struct mmc_queue *mq, struct mmc_queue_req *mqrq, } mqrq->areq.mrq = &brq->mrq; - - mmc_queue_bounce_pre(mqrq); } static void mmc_blk_rw_rq_prep(struct mmc_queue_req *mqrq, @@ -1829,7 +1827,6 @@ static void mmc_blk_issue_rw_rq(struct mmc_queue *mq, struct request *new_req) brq = &mq_rq->brq; old_req = mmc_queue_req_to_req(mq_rq); type = rq_data_dir(old_req) == READ ? MMC_BLK_READ : MMC_BLK_WRITE; - mmc_queue_bounce_post(mq_rq); switch (status) { case MMC_BLK_SUCCESS: diff --git a/drivers/mmc/core/mmc.c b/drivers/mmc/core/mmc.c index a7eb623f8daa..36217ad5e9b1 100644 --- a/drivers/mmc/core/mmc.c +++ b/drivers/mmc/core/mmc.c @@ -1286,6 +1286,23 @@ out_err: return err; } +static void mmc_select_driver_type(struct mmc_card *card) +{ + int card_drv_type, drive_strength, drv_type; + + card_drv_type = card->ext_csd.raw_driver_strength | + mmc_driver_type_mask(0); + + drive_strength = mmc_select_drive_strength(card, + card->ext_csd.hs200_max_dtr, + card_drv_type, &drv_type); + + card->drive_strength = drive_strength; + + if (drv_type) + mmc_set_driver_type(card->host, drv_type); +} + static int mmc_select_hs400es(struct mmc_card *card) { struct mmc_host *host = card->host; @@ -1341,6 +1358,8 @@ static int mmc_select_hs400es(struct mmc_card *card) goto out_err; } + mmc_select_driver_type(card); + /* Switch card to HS400 */ val = EXT_CSD_TIMING_HS400 | card->drive_strength << EXT_CSD_DRV_STR_SHIFT; @@ -1374,23 +1393,6 @@ out_err: return err; } -static void mmc_select_driver_type(struct mmc_card *card) -{ - int card_drv_type, drive_strength, drv_type; - - card_drv_type = card->ext_csd.raw_driver_strength | - mmc_driver_type_mask(0); - - drive_strength = mmc_select_drive_strength(card, - card->ext_csd.hs200_max_dtr, - card_drv_type, &drv_type); - - card->drive_strength = drive_strength; - - if (drv_type) - mmc_set_driver_type(card->host, drv_type); -} - /* * For device supporting HS200 mode, the following sequence * should be done before executing the tuning process. diff --git a/drivers/mmc/core/queue.c b/drivers/mmc/core/queue.c index 74c663b1c0a7..0a4e77a5ba33 100644 --- a/drivers/mmc/core/queue.c +++ b/drivers/mmc/core/queue.c @@ -23,8 +23,6 @@ #include "core.h" #include "card.h" -#define MMC_QUEUE_BOUNCESZ 65536 - /* * Prepare a MMC request. This just filters out odd stuff. */ @@ -150,26 +148,6 @@ static void mmc_queue_setup_discard(struct request_queue *q, queue_flag_set_unlocked(QUEUE_FLAG_SECERASE, q); } -static unsigned int mmc_queue_calc_bouncesz(struct mmc_host *host) -{ - unsigned int bouncesz = MMC_QUEUE_BOUNCESZ; - - if (host->max_segs != 1 || (host->caps & MMC_CAP_NO_BOUNCE_BUFF)) - return 0; - - if (bouncesz > host->max_req_size) - bouncesz = host->max_req_size; - if (bouncesz > host->max_seg_size) - bouncesz = host->max_seg_size; - if (bouncesz > host->max_blk_count * 512) - bouncesz = host->max_blk_count * 512; - - if (bouncesz <= 512) - return 0; - - return bouncesz; -} - /** * mmc_init_request() - initialize the MMC-specific per-request data * @q: the request queue @@ -184,26 +162,9 @@ static int mmc_init_request(struct request_queue *q, struct request *req, struct mmc_card *card = mq->card; struct mmc_host *host = card->host; - if (card->bouncesz) { - mq_rq->bounce_buf = kmalloc(card->bouncesz, gfp); - if (!mq_rq->bounce_buf) - return -ENOMEM; - if (card->bouncesz > 512) { - mq_rq->sg = mmc_alloc_sg(1, gfp); - if (!mq_rq->sg) - return -ENOMEM; - mq_rq->bounce_sg = mmc_alloc_sg(card->bouncesz / 512, - gfp); - if (!mq_rq->bounce_sg) - return -ENOMEM; - } - } else { - mq_rq->bounce_buf = NULL; - mq_rq->bounce_sg = NULL; - mq_rq->sg = mmc_alloc_sg(host->max_segs, gfp); - if (!mq_rq->sg) - return -ENOMEM; - } + mq_rq->sg = mmc_alloc_sg(host->max_segs, gfp); + if (!mq_rq->sg) + return -ENOMEM; return 0; } @@ -212,13 +173,6 @@ static void mmc_exit_request(struct request_queue *q, struct request *req) { struct mmc_queue_req *mq_rq = req_to_mmc_queue_req(req); - /* It is OK to kfree(NULL) so this will be smooth */ - kfree(mq_rq->bounce_sg); - mq_rq->bounce_sg = NULL; - - kfree(mq_rq->bounce_buf); - mq_rq->bounce_buf = NULL; - kfree(mq_rq->sg); mq_rq->sg = NULL; } @@ -242,12 +196,6 @@ int mmc_init_queue(struct mmc_queue *mq, struct mmc_card *card, if (mmc_dev(host)->dma_mask && *mmc_dev(host)->dma_mask) limit = (u64)dma_max_pfn(mmc_dev(host)) << PAGE_SHIFT; - /* - * mmc_init_request() depends on card->bouncesz so it must be calculated - * before blk_init_allocated_queue() starts allocating requests. - */ - card->bouncesz = mmc_queue_calc_bouncesz(host); - mq->card = card; mq->queue = blk_alloc_queue(GFP_KERNEL); if (!mq->queue) @@ -271,17 +219,11 @@ int mmc_init_queue(struct mmc_queue *mq, struct mmc_card *card, if (mmc_can_erase(card)) mmc_queue_setup_discard(mq->queue, card); - if (card->bouncesz) { - blk_queue_max_hw_sectors(mq->queue, card->bouncesz / 512); - blk_queue_max_segments(mq->queue, card->bouncesz / 512); - blk_queue_max_segment_size(mq->queue, card->bouncesz); - } else { - blk_queue_bounce_limit(mq->queue, limit); - blk_queue_max_hw_sectors(mq->queue, - min(host->max_blk_count, host->max_req_size / 512)); - blk_queue_max_segments(mq->queue, host->max_segs); - blk_queue_max_segment_size(mq->queue, host->max_seg_size); - } + blk_queue_bounce_limit(mq->queue, limit); + blk_queue_max_hw_sectors(mq->queue, + min(host->max_blk_count, host->max_req_size / 512)); + blk_queue_max_segments(mq->queue, host->max_segs); + blk_queue_max_segment_size(mq->queue, host->max_seg_size); sema_init(&mq->thread_sem, 1); @@ -370,56 +312,7 @@ void mmc_queue_resume(struct mmc_queue *mq) */ unsigned int mmc_queue_map_sg(struct mmc_queue *mq, struct mmc_queue_req *mqrq) { - unsigned int sg_len; - size_t buflen; - struct scatterlist *sg; struct request *req = mmc_queue_req_to_req(mqrq); - int i; - - if (!mqrq->bounce_buf) - return blk_rq_map_sg(mq->queue, req, mqrq->sg); - - sg_len = blk_rq_map_sg(mq->queue, req, mqrq->bounce_sg); - - mqrq->bounce_sg_len = sg_len; - - buflen = 0; - for_each_sg(mqrq->bounce_sg, sg, sg_len, i) - buflen += sg->length; - - sg_init_one(mqrq->sg, mqrq->bounce_buf, buflen); - - return 1; -} - -/* - * If writing, bounce the data to the buffer before the request - * is sent to the host driver - */ -void mmc_queue_bounce_pre(struct mmc_queue_req *mqrq) -{ - if (!mqrq->bounce_buf) - return; - - if (rq_data_dir(mmc_queue_req_to_req(mqrq)) != WRITE) - return; - - sg_copy_to_buffer(mqrq->bounce_sg, mqrq->bounce_sg_len, - mqrq->bounce_buf, mqrq->sg[0].length); -} - -/* - * If reading, bounce the data from the buffer after the request - * has been handled by the host driver - */ -void mmc_queue_bounce_post(struct mmc_queue_req *mqrq) -{ - if (!mqrq->bounce_buf) - return; - - if (rq_data_dir(mmc_queue_req_to_req(mqrq)) != READ) - return; - sg_copy_from_buffer(mqrq->bounce_sg, mqrq->bounce_sg_len, - mqrq->bounce_buf, mqrq->sg[0].length); + return blk_rq_map_sg(mq->queue, req, mqrq->sg); } diff --git a/drivers/mmc/core/queue.h b/drivers/mmc/core/queue.h index 04fc89360a7a..f18d3f656baa 100644 --- a/drivers/mmc/core/queue.h +++ b/drivers/mmc/core/queue.h @@ -49,9 +49,6 @@ enum mmc_drv_op { struct mmc_queue_req { struct mmc_blk_request brq; struct scatterlist *sg; - char *bounce_buf; - struct scatterlist *bounce_sg; - unsigned int bounce_sg_len; struct mmc_async_req areq; enum mmc_drv_op drv_op; int drv_op_result; @@ -81,11 +78,8 @@ extern int mmc_init_queue(struct mmc_queue *, struct mmc_card *, spinlock_t *, extern void mmc_cleanup_queue(struct mmc_queue *); extern void mmc_queue_suspend(struct mmc_queue *); extern void mmc_queue_resume(struct mmc_queue *); - extern unsigned int mmc_queue_map_sg(struct mmc_queue *, struct mmc_queue_req *); -extern void mmc_queue_bounce_pre(struct mmc_queue_req *); -extern void mmc_queue_bounce_post(struct mmc_queue_req *); extern int mmc_access_rpmb(struct mmc_queue *); diff --git a/drivers/mmc/host/cavium.c b/drivers/mmc/host/cavium.c index 27fb625cbcf3..fbd29f00fca0 100644 --- a/drivers/mmc/host/cavium.c +++ b/drivers/mmc/host/cavium.c @@ -1038,7 +1038,7 @@ int cvm_mmc_of_slot_probe(struct device *dev, struct cvm_mmc_host *host) */ mmc->caps |= MMC_CAP_MMC_HIGHSPEED | MMC_CAP_SD_HIGHSPEED | MMC_CAP_ERASE | MMC_CAP_CMD23 | MMC_CAP_POWER_OFF_CARD | - MMC_CAP_3_3V_DDR | MMC_CAP_NO_BOUNCE_BUFF; + MMC_CAP_3_3V_DDR; if (host->use_sg) mmc->max_segs = 16; diff --git a/drivers/mmc/host/meson-gx-mmc.c b/drivers/mmc/host/meson-gx-mmc.c index c885c2d4b904..85745ef179e2 100644 --- a/drivers/mmc/host/meson-gx-mmc.c +++ b/drivers/mmc/host/meson-gx-mmc.c @@ -531,8 +531,7 @@ static int meson_mmc_clk_init(struct meson_host *host) div->shift = __ffs(CLK_DIV_MASK); div->width = __builtin_popcountl(CLK_DIV_MASK); div->hw.init = &init; - div->flags = (CLK_DIVIDER_ONE_BASED | - CLK_DIVIDER_ROUND_CLOSEST); + div->flags = CLK_DIVIDER_ONE_BASED; clk = devm_clk_register(host->dev, &div->hw); if (WARN_ON(IS_ERR(clk))) @@ -717,6 +716,22 @@ static int meson_mmc_clk_phase_tuning(struct mmc_host *mmc, u32 opcode, static int meson_mmc_execute_tuning(struct mmc_host *mmc, u32 opcode) { struct meson_host *host = mmc_priv(mmc); + int ret; + + /* + * If this is the initial tuning, try to get a sane Rx starting + * phase before doing the actual tuning. + */ + if (!mmc->doing_retune) { + ret = meson_mmc_clk_phase_tuning(mmc, opcode, host->rx_clk); + + if (ret) + return ret; + } + + ret = meson_mmc_clk_phase_tuning(mmc, opcode, host->tx_clk); + if (ret) + return ret; return meson_mmc_clk_phase_tuning(mmc, opcode, host->rx_clk); } @@ -746,6 +761,11 @@ static void meson_mmc_set_ios(struct mmc_host *mmc, struct mmc_ios *ios) case MMC_POWER_UP: if (!IS_ERR(mmc->supply.vmmc)) mmc_regulator_set_ocr(mmc, mmc->supply.vmmc, ios->vdd); + + /* Reset phases */ + clk_set_phase(host->rx_clk, 0); + clk_set_phase(host->tx_clk, 270); + break; case MMC_POWER_ON: @@ -759,8 +779,6 @@ static void meson_mmc_set_ios(struct mmc_host *mmc, struct mmc_ios *ios) host->vqmmc_enabled = true; } - /* Reset rx phase */ - clk_set_phase(host->rx_clk, 0); break; } diff --git a/drivers/mmc/host/pxamci.c b/drivers/mmc/host/pxamci.c index 59ab194cb009..c763b404510f 100644 --- a/drivers/mmc/host/pxamci.c +++ b/drivers/mmc/host/pxamci.c @@ -702,11 +702,7 @@ static int pxamci_probe(struct platform_device *pdev) pxamci_init_ocr(host); - /* - * This architecture used to disable bounce buffers through its - * defconfig, now it is done at runtime as a host property. - */ - mmc->caps = MMC_CAP_NO_BOUNCE_BUFF; + mmc->caps = 0; host->cmdat = 0; if (!cpu_is_pxa25x()) { mmc->caps |= MMC_CAP_4_BIT_DATA | MMC_CAP_SDIO_IRQ; diff --git a/drivers/mmc/host/sdhci-pci-core.c b/drivers/mmc/host/sdhci-pci-core.c index bbaddf18a1b3..d0ccc6729fd2 100644 --- a/drivers/mmc/host/sdhci-pci-core.c +++ b/drivers/mmc/host/sdhci-pci-core.c @@ -392,6 +392,7 @@ static const struct sdhci_pci_fixes sdhci_intel_pch_sdio = { enum { INTEL_DSM_FNS = 0, + INTEL_DSM_V18_SWITCH = 3, INTEL_DSM_DRV_STRENGTH = 9, INTEL_DSM_D3_RETUNE = 10, }; @@ -557,6 +558,19 @@ static void intel_hs400_enhanced_strobe(struct mmc_host *mmc, sdhci_writel(host, val, INTEL_HS400_ES_REG); } +static void sdhci_intel_voltage_switch(struct sdhci_host *host) +{ + struct sdhci_pci_slot *slot = sdhci_priv(host); + struct intel_host *intel_host = sdhci_pci_priv(slot); + struct device *dev = &slot->chip->pdev->dev; + u32 result = 0; + int err; + + err = intel_dsm(intel_host, dev, INTEL_DSM_V18_SWITCH, &result); + pr_debug("%s: %s DSM error %d result %u\n", + mmc_hostname(host->mmc), __func__, err, result); +} + static const struct sdhci_ops sdhci_intel_byt_ops = { .set_clock = sdhci_set_clock, .set_power = sdhci_intel_set_power, @@ -565,6 +579,7 @@ static const struct sdhci_ops sdhci_intel_byt_ops = { .reset = sdhci_reset, .set_uhs_signaling = sdhci_set_uhs_signaling, .hw_reset = sdhci_pci_hw_reset, + .voltage_switch = sdhci_intel_voltage_switch, }; static void byt_read_dsm(struct sdhci_pci_slot *slot) diff --git a/drivers/mmc/host/sdhci-xenon.c b/drivers/mmc/host/sdhci-xenon.c index 2eec2e652c53..0842bbc2d7ad 100644 --- a/drivers/mmc/host/sdhci-xenon.c +++ b/drivers/mmc/host/sdhci-xenon.c @@ -466,6 +466,7 @@ static int xenon_probe(struct platform_device *pdev) { struct sdhci_pltfm_host *pltfm_host; struct sdhci_host *host; + struct xenon_priv *priv; int err; host = sdhci_pltfm_init(pdev, &sdhci_xenon_pdata, @@ -474,6 +475,7 @@ static int xenon_probe(struct platform_device *pdev) return PTR_ERR(host); pltfm_host = sdhci_priv(host); + priv = sdhci_pltfm_priv(pltfm_host); /* * Link Xenon specific mmc_host_ops function, @@ -491,9 +493,20 @@ static int xenon_probe(struct platform_device *pdev) if (err) goto free_pltfm; + priv->axi_clk = devm_clk_get(&pdev->dev, "axi"); + if (IS_ERR(priv->axi_clk)) { + err = PTR_ERR(priv->axi_clk); + if (err == -EPROBE_DEFER) + goto err_clk; + } else { + err = clk_prepare_enable(priv->axi_clk); + if (err) + goto err_clk; + } + err = mmc_of_parse(host->mmc); if (err) - goto err_clk; + goto err_clk_axi; sdhci_get_of_property(pdev); @@ -502,11 +515,11 @@ static int xenon_probe(struct platform_device *pdev) /* Xenon specific dt parse */ err = xenon_probe_dt(pdev); if (err) - goto err_clk; + goto err_clk_axi; err = xenon_sdhc_prepare(host); if (err) - goto err_clk; + goto err_clk_axi; pm_runtime_get_noresume(&pdev->dev); pm_runtime_set_active(&pdev->dev); @@ -527,6 +540,8 @@ remove_sdhc: pm_runtime_disable(&pdev->dev); pm_runtime_put_noidle(&pdev->dev); xenon_sdhc_unprepare(host); +err_clk_axi: + clk_disable_unprepare(priv->axi_clk); err_clk: clk_disable_unprepare(pltfm_host->clk); free_pltfm: @@ -538,6 +553,7 @@ static int xenon_remove(struct platform_device *pdev) { struct sdhci_host *host = platform_get_drvdata(pdev); struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host); + struct xenon_priv *priv = sdhci_pltfm_priv(pltfm_host); pm_runtime_get_sync(&pdev->dev); pm_runtime_disable(&pdev->dev); @@ -546,7 +562,7 @@ static int xenon_remove(struct platform_device *pdev) sdhci_remove_host(host, 0); xenon_sdhc_unprepare(host); - + clk_disable_unprepare(priv->axi_clk); clk_disable_unprepare(pltfm_host->clk); sdhci_pltfm_free(pdev); diff --git a/drivers/mmc/host/sdhci-xenon.h b/drivers/mmc/host/sdhci-xenon.h index 2bc0510c0769..9994995c7c56 100644 --- a/drivers/mmc/host/sdhci-xenon.h +++ b/drivers/mmc/host/sdhci-xenon.h @@ -83,6 +83,7 @@ struct xenon_priv { unsigned char bus_width; unsigned char timing; unsigned int clock; + struct clk *axi_clk; int phy_type; /* diff --git a/drivers/mmc/host/tmio_mmc_core.c b/drivers/mmc/host/tmio_mmc_core.c index 12cf8288d663..a7293e186e03 100644 --- a/drivers/mmc/host/tmio_mmc_core.c +++ b/drivers/mmc/host/tmio_mmc_core.c @@ -129,50 +129,6 @@ static int tmio_mmc_next_sg(struct tmio_mmc_host *host) #define CMDREQ_TIMEOUT 5000 -#ifdef CONFIG_MMC_DEBUG - -#define STATUS_TO_TEXT(a, status, i) \ - do { \ - if ((status) & TMIO_STAT_##a) { \ - if ((i)++) \ - printk(KERN_DEBUG " | "); \ - printk(KERN_DEBUG #a); \ - } \ - } while (0) - -static void pr_debug_status(u32 status) -{ - int i = 0; - - pr_debug("status: %08x = ", status); - STATUS_TO_TEXT(CARD_REMOVE, status, i); - STATUS_TO_TEXT(CARD_INSERT, status, i); - STATUS_TO_TEXT(SIGSTATE, status, i); - STATUS_TO_TEXT(WRPROTECT, status, i); - STATUS_TO_TEXT(CARD_REMOVE_A, status, i); - STATUS_TO_TEXT(CARD_INSERT_A, status, i); - STATUS_TO_TEXT(SIGSTATE_A, status, i); - STATUS_TO_TEXT(CMD_IDX_ERR, status, i); - STATUS_TO_TEXT(STOPBIT_ERR, status, i); - STATUS_TO_TEXT(ILL_FUNC, status, i); - STATUS_TO_TEXT(CMD_BUSY, status, i); - STATUS_TO_TEXT(CMDRESPEND, status, i); - STATUS_TO_TEXT(DATAEND, status, i); - STATUS_TO_TEXT(CRCFAIL, status, i); - STATUS_TO_TEXT(DATATIMEOUT, status, i); - STATUS_TO_TEXT(CMDTIMEOUT, status, i); - STATUS_TO_TEXT(RXOVERFLOW, status, i); - STATUS_TO_TEXT(TXUNDERRUN, status, i); - STATUS_TO_TEXT(RXRDY, status, i); - STATUS_TO_TEXT(TXRQ, status, i); - STATUS_TO_TEXT(ILL_ACCESS, status, i); - printk("\n"); -} - -#else -#define pr_debug_status(s) do { } while (0) -#endif - static void tmio_mmc_enable_sdio_irq(struct mmc_host *mmc, int enable) { struct tmio_mmc_host *host = mmc_priv(mmc); @@ -762,9 +718,6 @@ irqreturn_t tmio_mmc_irq(int irq, void *devid) status = sd_ctrl_read16_and_16_as_32(host, CTL_STATUS); ireg = status & TMIO_MASK_IRQ & ~host->sdcard_irq_mask; - pr_debug_status(status); - pr_debug_status(ireg); - /* Clear the status except the interrupt status */ sd_ctrl_write32_as_16_and_16(host, CTL_STATUS, TMIO_MASK_IRQ); diff --git a/drivers/mtd/mtdpart.c b/drivers/mtd/mtdpart.c index 5736b0c90b33..a308e707392d 100644 --- a/drivers/mtd/mtdpart.c +++ b/drivers/mtd/mtdpart.c @@ -581,6 +581,14 @@ static struct mtd_part *allocate_partition(struct mtd_info *parent, slave->mtd.erasesize = parent->erasesize; } + /* + * Slave erasesize might differ from the master one if the master + * exposes several regions with different erasesize. Adjust + * wr_alignment accordingly. + */ + if (!(slave->mtd.flags & MTD_NO_ERASE)) + wr_alignment = slave->mtd.erasesize; + tmp = slave->offset; remainder = do_div(tmp, wr_alignment); if ((slave->mtd.flags & MTD_WRITEABLE) && remainder) { diff --git a/drivers/mtd/nand/atmel/pmecc.c b/drivers/mtd/nand/atmel/pmecc.c index 146af8218314..8268636675ef 100644 --- a/drivers/mtd/nand/atmel/pmecc.c +++ b/drivers/mtd/nand/atmel/pmecc.c @@ -363,7 +363,7 @@ atmel_pmecc_create_user(struct atmel_pmecc *pmecc, size += (req->ecc.strength + 1) * sizeof(u16); /* Reserve space for mu, dmu and delta. */ size = ALIGN(size, sizeof(s32)); - size += (req->ecc.strength + 1) * sizeof(s32); + size += (req->ecc.strength + 1) * sizeof(s32) * 3; user = kzalloc(size, GFP_KERNEL); if (!user) diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c index c6678aa9b4ef..d74c7335c512 100644 --- a/drivers/net/dsa/mv88e6xxx/chip.c +++ b/drivers/net/dsa/mv88e6xxx/chip.c @@ -1100,6 +1100,10 @@ static int mv88e6xxx_port_check_hw_vlan(struct dsa_switch *ds, int port, }; int i, err; + /* DSA and CPU ports have to be members of multiple vlans */ + if (dsa_is_dsa_port(ds, port) || dsa_is_cpu_port(ds, port)) + return 0; + if (!vid_begin) return -EOPNOTSUPP; @@ -3947,7 +3951,9 @@ static void mv88e6xxx_remove(struct mdio_device *mdiodev) if (chip->irq > 0) { if (chip->info->g2_irqs > 0) mv88e6xxx_g2_irq_free(chip); + mutex_lock(&chip->reg_lock); mv88e6xxx_g1_irq_free(chip); + mutex_unlock(&chip->reg_lock); } } diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_cfg.h b/drivers/net/ethernet/aquantia/atlantic/aq_cfg.h index 214986436ece..0fdaaa643073 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_cfg.h +++ b/drivers/net/ethernet/aquantia/atlantic/aq_cfg.h @@ -51,6 +51,10 @@ #define AQ_CFG_SKB_FRAGS_MAX 32U +/* Number of descriptors available in one ring to resume this ring queue + */ +#define AQ_CFG_RESTART_DESC_THRES (AQ_CFG_SKB_FRAGS_MAX * 2) + #define AQ_CFG_NAPI_WEIGHT 64U #define AQ_CFG_MULTICAST_ADDRESS_MAX 32U diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_nic.c b/drivers/net/ethernet/aquantia/atlantic/aq_nic.c index 6ac9e2602d6d..0a5bb4114eb4 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_nic.c +++ b/drivers/net/ethernet/aquantia/atlantic/aq_nic.c @@ -119,6 +119,35 @@ int aq_nic_cfg_start(struct aq_nic_s *self) return 0; } +static int aq_nic_update_link_status(struct aq_nic_s *self) +{ + int err = self->aq_hw_ops.hw_get_link_status(self->aq_hw); + + if (err) + return err; + + if (self->link_status.mbps != self->aq_hw->aq_link_status.mbps) + pr_info("%s: link change old %d new %d\n", + AQ_CFG_DRV_NAME, self->link_status.mbps, + self->aq_hw->aq_link_status.mbps); + + self->link_status = self->aq_hw->aq_link_status; + if (!netif_carrier_ok(self->ndev) && self->link_status.mbps) { + aq_utils_obj_set(&self->header.flags, + AQ_NIC_FLAG_STARTED); + aq_utils_obj_clear(&self->header.flags, + AQ_NIC_LINK_DOWN); + netif_carrier_on(self->ndev); + netif_tx_wake_all_queues(self->ndev); + } + if (netif_carrier_ok(self->ndev) && !self->link_status.mbps) { + netif_carrier_off(self->ndev); + netif_tx_disable(self->ndev); + aq_utils_obj_set(&self->header.flags, AQ_NIC_LINK_DOWN); + } + return 0; +} + static void aq_nic_service_timer_cb(unsigned long param) { struct aq_nic_s *self = (struct aq_nic_s *)param; @@ -131,26 +160,13 @@ static void aq_nic_service_timer_cb(unsigned long param) if (aq_utils_obj_test(&self->header.flags, AQ_NIC_FLAGS_IS_NOT_READY)) goto err_exit; - err = self->aq_hw_ops.hw_get_link_status(self->aq_hw); - if (err < 0) + err = aq_nic_update_link_status(self); + if (err) goto err_exit; - self->link_status = self->aq_hw->aq_link_status; - self->aq_hw_ops.hw_interrupt_moderation_set(self->aq_hw, self->aq_nic_cfg.is_interrupt_moderation); - if (self->link_status.mbps) { - aq_utils_obj_set(&self->header.flags, - AQ_NIC_FLAG_STARTED); - aq_utils_obj_clear(&self->header.flags, - AQ_NIC_LINK_DOWN); - netif_carrier_on(self->ndev); - } else { - netif_carrier_off(self->ndev); - aq_utils_obj_set(&self->header.flags, AQ_NIC_LINK_DOWN); - } - memset(&stats_rx, 0U, sizeof(struct aq_ring_stats_rx_s)); memset(&stats_tx, 0U, sizeof(struct aq_ring_stats_tx_s)); for (i = AQ_DIMOF(self->aq_vec); i--;) { @@ -214,7 +230,6 @@ struct aq_nic_s *aq_nic_alloc_cold(const struct net_device_ops *ndev_ops, SET_NETDEV_DEV(ndev, dev); ndev->if_port = port; - ndev->min_mtu = ETH_MIN_MTU; self->ndev = ndev; self->aq_pci_func = aq_pci_func; @@ -241,7 +256,6 @@ err_exit: int aq_nic_ndev_register(struct aq_nic_s *self) { int err = 0; - unsigned int i = 0U; if (!self->ndev) { err = -EINVAL; @@ -263,8 +277,7 @@ int aq_nic_ndev_register(struct aq_nic_s *self) netif_carrier_off(self->ndev); - for (i = AQ_CFG_VECS_MAX; i--;) - aq_nic_ndev_queue_stop(self, i); + netif_tx_disable(self->ndev); err = register_netdev(self->ndev); if (err < 0) @@ -283,6 +296,7 @@ int aq_nic_ndev_init(struct aq_nic_s *self) self->ndev->features = aq_hw_caps->hw_features; self->ndev->priv_flags = aq_hw_caps->hw_priv_flags; self->ndev->mtu = aq_nic_cfg->mtu - ETH_HLEN; + self->ndev->max_mtu = self->aq_hw_caps.mtu - ETH_FCS_LEN - ETH_HLEN; return 0; } @@ -318,12 +332,8 @@ struct aq_nic_s *aq_nic_alloc_hot(struct net_device *ndev) err = -EINVAL; goto err_exit; } - if (netif_running(ndev)) { - unsigned int i; - - for (i = AQ_CFG_VECS_MAX; i--;) - netif_stop_subqueue(ndev, i); - } + if (netif_running(ndev)) + netif_tx_disable(ndev); for (self->aq_vecs = 0; self->aq_vecs < self->aq_nic_cfg.vecs; self->aq_vecs++) { @@ -383,16 +393,6 @@ err_exit: return err; } -void aq_nic_ndev_queue_start(struct aq_nic_s *self, unsigned int idx) -{ - netif_start_subqueue(self->ndev, idx); -} - -void aq_nic_ndev_queue_stop(struct aq_nic_s *self, unsigned int idx) -{ - netif_stop_subqueue(self->ndev, idx); -} - int aq_nic_start(struct aq_nic_s *self) { struct aq_vec_s *aq_vec = NULL; @@ -451,10 +451,6 @@ int aq_nic_start(struct aq_nic_s *self) goto err_exit; } - for (i = 0U, aq_vec = self->aq_vec[0]; - self->aq_vecs > i; ++i, aq_vec = self->aq_vec[i]) - aq_nic_ndev_queue_start(self, i); - err = netif_set_real_num_tx_queues(self->ndev, self->aq_vecs); if (err < 0) goto err_exit; @@ -463,6 +459,8 @@ int aq_nic_start(struct aq_nic_s *self) if (err < 0) goto err_exit; + netif_tx_start_all_queues(self->ndev); + err_exit: return err; } @@ -475,6 +473,7 @@ static unsigned int aq_nic_map_skb(struct aq_nic_s *self, unsigned int nr_frags = skb_shinfo(skb)->nr_frags; unsigned int frag_count = 0U; unsigned int dx = ring->sw_tail; + struct aq_ring_buff_s *first = NULL; struct aq_ring_buff_s *dx_buff = &ring->buff_ring[dx]; if (unlikely(skb_is_gso(skb))) { @@ -485,6 +484,7 @@ static unsigned int aq_nic_map_skb(struct aq_nic_s *self, dx_buff->len_l4 = tcp_hdrlen(skb); dx_buff->mss = skb_shinfo(skb)->gso_size; dx_buff->is_txc = 1U; + dx_buff->eop_index = 0xffffU; dx_buff->is_ipv6 = (ip_hdr(skb)->version == 6) ? 1U : 0U; @@ -504,6 +504,7 @@ static unsigned int aq_nic_map_skb(struct aq_nic_s *self, if (unlikely(dma_mapping_error(aq_nic_get_dev(self), dx_buff->pa))) goto exit; + first = dx_buff; dx_buff->len_pkt = skb->len; dx_buff->is_sop = 1U; dx_buff->is_mapped = 1U; @@ -532,40 +533,46 @@ static unsigned int aq_nic_map_skb(struct aq_nic_s *self, for (; nr_frags--; ++frag_count) { unsigned int frag_len = 0U; + unsigned int buff_offset = 0U; + unsigned int buff_size = 0U; dma_addr_t frag_pa; skb_frag_t *frag = &skb_shinfo(skb)->frags[frag_count]; frag_len = skb_frag_size(frag); - frag_pa = skb_frag_dma_map(aq_nic_get_dev(self), frag, 0, - frag_len, DMA_TO_DEVICE); - if (unlikely(dma_mapping_error(aq_nic_get_dev(self), frag_pa))) - goto mapping_error; + while (frag_len) { + if (frag_len > AQ_CFG_TX_FRAME_MAX) + buff_size = AQ_CFG_TX_FRAME_MAX; + else + buff_size = frag_len; + + frag_pa = skb_frag_dma_map(aq_nic_get_dev(self), + frag, + buff_offset, + buff_size, + DMA_TO_DEVICE); + + if (unlikely(dma_mapping_error(aq_nic_get_dev(self), + frag_pa))) + goto mapping_error; - while (frag_len > AQ_CFG_TX_FRAME_MAX) { dx = aq_ring_next_dx(ring, dx); dx_buff = &ring->buff_ring[dx]; dx_buff->flags = 0U; - dx_buff->len = AQ_CFG_TX_FRAME_MAX; + dx_buff->len = buff_size; dx_buff->pa = frag_pa; dx_buff->is_mapped = 1U; + dx_buff->eop_index = 0xffffU; + + frag_len -= buff_size; + buff_offset += buff_size; - frag_len -= AQ_CFG_TX_FRAME_MAX; - frag_pa += AQ_CFG_TX_FRAME_MAX; ++ret; } - - dx = aq_ring_next_dx(ring, dx); - dx_buff = &ring->buff_ring[dx]; - - dx_buff->flags = 0U; - dx_buff->len = frag_len; - dx_buff->pa = frag_pa; - dx_buff->is_mapped = 1U; - ++ret; } + first->eop_index = dx; dx_buff->is_eop = 1U; dx_buff->skb = skb; goto exit; @@ -602,7 +609,6 @@ int aq_nic_xmit(struct aq_nic_s *self, struct sk_buff *skb) unsigned int vec = skb->queue_mapping % self->aq_nic_cfg.vecs; unsigned int tc = 0U; int err = NETDEV_TX_OK; - bool is_nic_in_bad_state; frags = skb_shinfo(skb)->nr_frags + 1; @@ -613,13 +619,10 @@ int aq_nic_xmit(struct aq_nic_s *self, struct sk_buff *skb) goto err_exit; } - is_nic_in_bad_state = aq_utils_obj_test(&self->header.flags, - AQ_NIC_FLAGS_IS_NOT_TX_READY) || - (aq_ring_avail_dx(ring) < - AQ_CFG_SKB_FRAGS_MAX); + aq_ring_update_queue_state(ring); - if (is_nic_in_bad_state) { - aq_nic_ndev_queue_stop(self, ring->idx); + /* Above status update may stop the queue. Check this. */ + if (__netif_subqueue_stopped(self->ndev, ring->idx)) { err = NETDEV_TX_BUSY; goto err_exit; } @@ -631,9 +634,6 @@ int aq_nic_xmit(struct aq_nic_s *self, struct sk_buff *skb) ring, frags); if (err >= 0) { - if (aq_ring_avail_dx(ring) < AQ_CFG_SKB_FRAGS_MAX + 1) - aq_nic_ndev_queue_stop(self, ring->idx); - ++ring->stats.tx.packets; ring->stats.tx.bytes += skb->len; } @@ -693,16 +693,9 @@ int aq_nic_set_multicast_list(struct aq_nic_s *self, struct net_device *ndev) int aq_nic_set_mtu(struct aq_nic_s *self, int new_mtu) { - int err = 0; - - if (new_mtu > self->aq_hw_caps.mtu) { - err = -EINVAL; - goto err_exit; - } self->aq_nic_cfg.mtu = new_mtu; -err_exit: - return err; + return 0; } int aq_nic_set_mac(struct aq_nic_s *self, struct net_device *ndev) @@ -905,9 +898,7 @@ int aq_nic_stop(struct aq_nic_s *self) struct aq_vec_s *aq_vec = NULL; unsigned int i = 0U; - for (i = 0U, aq_vec = self->aq_vec[0]; - self->aq_vecs > i; ++i, aq_vec = self->aq_vec[i]) - aq_nic_ndev_queue_stop(self, i); + netif_tx_disable(self->ndev); del_timer_sync(&self->service_timer); diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_nic.h b/drivers/net/ethernet/aquantia/atlantic/aq_nic.h index 7fc2a5ecb2b7..0ddd556ff901 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_nic.h +++ b/drivers/net/ethernet/aquantia/atlantic/aq_nic.h @@ -83,8 +83,6 @@ struct net_device *aq_nic_get_ndev(struct aq_nic_s *self); int aq_nic_init(struct aq_nic_s *self); int aq_nic_cfg_start(struct aq_nic_s *self); int aq_nic_ndev_register(struct aq_nic_s *self); -void aq_nic_ndev_queue_start(struct aq_nic_s *self, unsigned int idx); -void aq_nic_ndev_queue_stop(struct aq_nic_s *self, unsigned int idx); void aq_nic_ndev_free(struct aq_nic_s *self); int aq_nic_start(struct aq_nic_s *self); int aq_nic_xmit(struct aq_nic_s *self, struct sk_buff *skb); diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_ring.c b/drivers/net/ethernet/aquantia/atlantic/aq_ring.c index 4eee1996a825..0654e0c76bc2 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_ring.c +++ b/drivers/net/ethernet/aquantia/atlantic/aq_ring.c @@ -104,6 +104,38 @@ int aq_ring_init(struct aq_ring_s *self) return 0; } +static inline bool aq_ring_dx_in_range(unsigned int h, unsigned int i, + unsigned int t) +{ + return (h < t) ? ((h < i) && (i < t)) : ((h < i) || (i < t)); +} + +void aq_ring_update_queue_state(struct aq_ring_s *ring) +{ + if (aq_ring_avail_dx(ring) <= AQ_CFG_SKB_FRAGS_MAX) + aq_ring_queue_stop(ring); + else if (aq_ring_avail_dx(ring) > AQ_CFG_RESTART_DESC_THRES) + aq_ring_queue_wake(ring); +} + +void aq_ring_queue_wake(struct aq_ring_s *ring) +{ + struct net_device *ndev = aq_nic_get_ndev(ring->aq_nic); + + if (__netif_subqueue_stopped(ndev, ring->idx)) { + netif_wake_subqueue(ndev, ring->idx); + ring->stats.tx.queue_restarts++; + } +} + +void aq_ring_queue_stop(struct aq_ring_s *ring) +{ + struct net_device *ndev = aq_nic_get_ndev(ring->aq_nic); + + if (!__netif_subqueue_stopped(ndev, ring->idx)) + netif_stop_subqueue(ndev, ring->idx); +} + void aq_ring_tx_clean(struct aq_ring_s *self) { struct device *dev = aq_nic_get_dev(self->aq_nic); @@ -113,23 +145,28 @@ void aq_ring_tx_clean(struct aq_ring_s *self) struct aq_ring_buff_s *buff = &self->buff_ring[self->sw_head]; if (likely(buff->is_mapped)) { - if (unlikely(buff->is_sop)) + if (unlikely(buff->is_sop)) { + if (!buff->is_eop && + buff->eop_index != 0xffffU && + (!aq_ring_dx_in_range(self->sw_head, + buff->eop_index, + self->hw_head))) + break; + dma_unmap_single(dev, buff->pa, buff->len, DMA_TO_DEVICE); - else + } else { dma_unmap_page(dev, buff->pa, buff->len, DMA_TO_DEVICE); + } } if (unlikely(buff->is_eop)) dev_kfree_skb_any(buff->skb); - } -} -static inline unsigned int aq_ring_dx_in_range(unsigned int h, unsigned int i, - unsigned int t) -{ - return (h < t) ? ((h < i) && (i < t)) : ((h < i) || (i < t)); + buff->pa = 0U; + buff->eop_index = 0xffffU; + } } #define AQ_SKB_ALIGN SKB_DATA_ALIGN(sizeof(struct skb_shared_info)) diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_ring.h b/drivers/net/ethernet/aquantia/atlantic/aq_ring.h index 782176c5f4f8..5844078764bd 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_ring.h +++ b/drivers/net/ethernet/aquantia/atlantic/aq_ring.h @@ -65,7 +65,7 @@ struct __packed aq_ring_buff_s { }; union { struct { - u32 len:16; + u16 len; u32 is_ip_cso:1; u32 is_udp_cso:1; u32 is_tcp_cso:1; @@ -77,8 +77,10 @@ struct __packed aq_ring_buff_s { u32 is_cleaned:1; u32 is_error:1; u32 rsvd3:6; + u16 eop_index; + u16 rsvd4; }; - u32 flags; + u64 flags; }; }; @@ -94,6 +96,7 @@ struct aq_ring_stats_tx_s { u64 errors; u64 packets; u64 bytes; + u64 queue_restarts; }; union aq_ring_stats_s { @@ -147,6 +150,9 @@ struct aq_ring_s *aq_ring_rx_alloc(struct aq_ring_s *self, int aq_ring_init(struct aq_ring_s *self); void aq_ring_rx_deinit(struct aq_ring_s *self); void aq_ring_free(struct aq_ring_s *self); +void aq_ring_update_queue_state(struct aq_ring_s *ring); +void aq_ring_queue_wake(struct aq_ring_s *ring); +void aq_ring_queue_stop(struct aq_ring_s *ring); void aq_ring_tx_clean(struct aq_ring_s *self); int aq_ring_rx_clean(struct aq_ring_s *self, struct napi_struct *napi, diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_vec.c b/drivers/net/ethernet/aquantia/atlantic/aq_vec.c index ebf588004c46..305ff8ffac2c 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_vec.c +++ b/drivers/net/ethernet/aquantia/atlantic/aq_vec.c @@ -59,12 +59,7 @@ static int aq_vec_poll(struct napi_struct *napi, int budget) if (ring[AQ_VEC_TX_ID].sw_head != ring[AQ_VEC_TX_ID].hw_head) { aq_ring_tx_clean(&ring[AQ_VEC_TX_ID]); - - if (aq_ring_avail_dx(&ring[AQ_VEC_TX_ID]) > - AQ_CFG_SKB_FRAGS_MAX) { - aq_nic_ndev_queue_start(self->aq_nic, - ring[AQ_VEC_TX_ID].idx); - } + aq_ring_update_queue_state(&ring[AQ_VEC_TX_ID]); was_tx_cleaned = true; } @@ -364,6 +359,7 @@ void aq_vec_add_stats(struct aq_vec_s *self, stats_tx->packets += tx->packets; stats_tx->bytes += tx->bytes; stats_tx->errors += tx->errors; + stats_tx->queue_restarts += tx->queue_restarts; } } diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0_internal.h b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0_internal.h index f3957e930340..fcf89e25a773 100644 --- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0_internal.h +++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0_internal.h @@ -16,7 +16,7 @@ #include "../aq_common.h" -#define HW_ATL_B0_MTU_JUMBO (16000U) +#define HW_ATL_B0_MTU_JUMBO 16352U #define HW_ATL_B0_MTU 1514U #define HW_ATL_B0_TX_RINGS 4U diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.c index 4f5ec9a0fbfb..bf734b32e44b 100644 --- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.c +++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.c @@ -351,8 +351,7 @@ int hw_atl_utils_mpi_get_link_status(struct aq_hw_s *self) break; default: - link_status->mbps = 0U; - break; + return -EBUSY; } } diff --git a/drivers/net/ethernet/broadcom/cnic.c b/drivers/net/ethernet/broadcom/cnic.c index cec94bbb2ea5..8bc126a156e8 100644 --- a/drivers/net/ethernet/broadcom/cnic.c +++ b/drivers/net/ethernet/broadcom/cnic.c @@ -1278,7 +1278,7 @@ static int cnic_alloc_bnx2x_resc(struct cnic_dev *dev) ret = cnic_alloc_dma(dev, kwq_16_dma, pages, 0); if (ret) - return -ENOMEM; + goto error; n = CNIC_PAGE_SIZE / CNIC_KWQ16_DATA_SIZE; for (i = 0, j = 0; i < cp->max_cid_space; i++) { diff --git a/drivers/net/ethernet/chelsio/cxgb3/t3cdev.h b/drivers/net/ethernet/chelsio/cxgb3/t3cdev.h index 705713b56636..3c3e6cf6aca6 100644 --- a/drivers/net/ethernet/chelsio/cxgb3/t3cdev.h +++ b/drivers/net/ethernet/chelsio/cxgb3/t3cdev.h @@ -60,7 +60,7 @@ struct t3cdev { int (*ctl)(struct t3cdev *dev, unsigned int req, void *data); void (*neigh_update)(struct t3cdev *dev, struct neighbour *neigh); void *priv; /* driver private data */ - void *l2opt; /* optional layer 2 data */ + void __rcu *l2opt; /* optional layer 2 data */ void *l3opt; /* optional layer 3 data */ void *l4opt; /* optional layer 4 data */ void *ulp; /* ulp stuff */ diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c index e0685e630afe..c1cdbfd83bdb 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c @@ -2652,7 +2652,8 @@ static int hclge_rss_init_hw(struct hclge_dev *hdev) dev_err(&hdev->pdev->dev, "Configure rss tc size failed, invalid TC_SIZE = %d\n", rss_size); - return -EINVAL; + ret = -EINVAL; + goto err; } roundup_size = roundup_pow_of_two(rss_size); diff --git a/drivers/net/ethernet/marvell/mvpp2.c b/drivers/net/ethernet/marvell/mvpp2.c index dd0ee2691c86..9c86cb7cb988 100644 --- a/drivers/net/ethernet/marvell/mvpp2.c +++ b/drivers/net/ethernet/marvell/mvpp2.c @@ -333,7 +333,7 @@ #define MVPP2_GMAC_INBAND_AN_MASK BIT(0) #define MVPP2_GMAC_FLOW_CTRL_MASK GENMASK(2, 1) #define MVPP2_GMAC_PCS_ENABLE_MASK BIT(3) -#define MVPP2_GMAC_PORT_RGMII_MASK BIT(4) +#define MVPP2_GMAC_INTERNAL_CLK_MASK BIT(4) #define MVPP2_GMAC_DISABLE_PADDING BIT(5) #define MVPP2_GMAC_PORT_RESET_MASK BIT(6) #define MVPP2_GMAC_AUTONEG_CONFIG 0xc @@ -676,6 +676,7 @@ enum mvpp2_tag_type { #define MVPP2_PRS_RI_L3_MCAST BIT(15) #define MVPP2_PRS_RI_L3_BCAST (BIT(15) | BIT(16)) #define MVPP2_PRS_RI_IP_FRAG_MASK 0x20000 +#define MVPP2_PRS_RI_IP_FRAG_TRUE BIT(17) #define MVPP2_PRS_RI_UDF3_MASK 0x300000 #define MVPP2_PRS_RI_UDF3_RX_SPECIAL BIT(21) #define MVPP2_PRS_RI_L4_PROTO_MASK 0x1c00000 @@ -792,6 +793,7 @@ struct mvpp2 { struct clk *pp_clk; struct clk *gop_clk; struct clk *mg_clk; + struct clk *axi_clk; /* List of pointers to port structures */ struct mvpp2_port **port_list; @@ -2315,7 +2317,7 @@ static int mvpp2_prs_ip4_proto(struct mvpp2 *priv, unsigned short proto, (proto != IPPROTO_IGMP)) return -EINVAL; - /* Fragmented packet */ + /* Not fragmented packet */ tid = mvpp2_prs_tcam_first_free(priv, MVPP2_PE_FIRST_FREE_TID, MVPP2_PE_LAST_FREE_TID); if (tid < 0) @@ -2334,8 +2336,12 @@ static int mvpp2_prs_ip4_proto(struct mvpp2 *priv, unsigned short proto, MVPP2_PRS_SRAM_OP_SEL_UDF_ADD); mvpp2_prs_sram_ai_update(&pe, MVPP2_PRS_IPV4_DIP_AI_BIT, MVPP2_PRS_IPV4_DIP_AI_BIT); - mvpp2_prs_sram_ri_update(&pe, ri | MVPP2_PRS_RI_IP_FRAG_MASK, - ri_mask | MVPP2_PRS_RI_IP_FRAG_MASK); + mvpp2_prs_sram_ri_update(&pe, ri, ri_mask | MVPP2_PRS_RI_IP_FRAG_MASK); + + mvpp2_prs_tcam_data_byte_set(&pe, 2, 0x00, + MVPP2_PRS_TCAM_PROTO_MASK_L); + mvpp2_prs_tcam_data_byte_set(&pe, 3, 0x00, + MVPP2_PRS_TCAM_PROTO_MASK); mvpp2_prs_tcam_data_byte_set(&pe, 5, proto, MVPP2_PRS_TCAM_PROTO_MASK); mvpp2_prs_tcam_ai_update(&pe, 0, MVPP2_PRS_IPV4_DIP_AI_BIT); @@ -2346,7 +2352,7 @@ static int mvpp2_prs_ip4_proto(struct mvpp2 *priv, unsigned short proto, mvpp2_prs_shadow_set(priv, pe.index, MVPP2_PRS_LU_IP4); mvpp2_prs_hw_write(priv, &pe); - /* Not fragmented packet */ + /* Fragmented packet */ tid = mvpp2_prs_tcam_first_free(priv, MVPP2_PE_FIRST_FREE_TID, MVPP2_PE_LAST_FREE_TID); if (tid < 0) @@ -2358,8 +2364,11 @@ static int mvpp2_prs_ip4_proto(struct mvpp2 *priv, unsigned short proto, pe.sram.word[MVPP2_PRS_SRAM_RI_CTRL_WORD] = 0x0; mvpp2_prs_sram_ri_update(&pe, ri, ri_mask); - mvpp2_prs_tcam_data_byte_set(&pe, 2, 0x00, MVPP2_PRS_TCAM_PROTO_MASK_L); - mvpp2_prs_tcam_data_byte_set(&pe, 3, 0x00, MVPP2_PRS_TCAM_PROTO_MASK); + mvpp2_prs_sram_ri_update(&pe, ri | MVPP2_PRS_RI_IP_FRAG_TRUE, + ri_mask | MVPP2_PRS_RI_IP_FRAG_MASK); + + mvpp2_prs_tcam_data_byte_set(&pe, 2, 0x00, 0x0); + mvpp2_prs_tcam_data_byte_set(&pe, 3, 0x00, 0x0); /* Update shadow table and hw entry */ mvpp2_prs_shadow_set(priv, pe.index, MVPP2_PRS_LU_IP4); @@ -4591,7 +4600,6 @@ static void mvpp2_port_mii_gmac_configure(struct mvpp2_port *port) val |= MVPP2_GMAC_INBAND_AN_MASK | MVPP2_GMAC_PCS_ENABLE_MASK; } else if (phy_interface_mode_is_rgmii(port->phy_interface)) { val &= ~MVPP2_GMAC_PCS_ENABLE_MASK; - val |= MVPP2_GMAC_PORT_RGMII_MASK; } writel(val, port->base + MVPP2_GMAC_CTRL_2_REG); @@ -7496,7 +7504,7 @@ static void mvpp2_port_copy_mac_addr(struct net_device *dev, struct mvpp2 *priv, /* Ports initialization */ static int mvpp2_port_probe(struct platform_device *pdev, struct device_node *port_node, - struct mvpp2 *priv) + struct mvpp2 *priv, int index) { struct device_node *phy_node; struct phy *comphy; @@ -7670,7 +7678,7 @@ static int mvpp2_port_probe(struct platform_device *pdev, } netdev_info(dev, "Using %s mac address %pM\n", mac_from, dev->dev_addr); - priv->port_list[id] = port; + priv->port_list[index] = port; return 0; err_free_port_pcpu: @@ -7963,6 +7971,18 @@ static int mvpp2_probe(struct platform_device *pdev) err = clk_prepare_enable(priv->mg_clk); if (err < 0) goto err_gop_clk; + + priv->axi_clk = devm_clk_get(&pdev->dev, "axi_clk"); + if (IS_ERR(priv->axi_clk)) { + err = PTR_ERR(priv->axi_clk); + if (err == -EPROBE_DEFER) + goto err_gop_clk; + priv->axi_clk = NULL; + } else { + err = clk_prepare_enable(priv->axi_clk); + if (err < 0) + goto err_gop_clk; + } } /* Get system's tclk rate */ @@ -8005,16 +8025,19 @@ static int mvpp2_probe(struct platform_device *pdev) } /* Initialize ports */ + i = 0; for_each_available_child_of_node(dn, port_node) { - err = mvpp2_port_probe(pdev, port_node, priv); + err = mvpp2_port_probe(pdev, port_node, priv, i); if (err < 0) goto err_mg_clk; + i++; } platform_set_drvdata(pdev, priv); return 0; err_mg_clk: + clk_disable_unprepare(priv->axi_clk); if (priv->hw_version == MVPP22) clk_disable_unprepare(priv->mg_clk); err_gop_clk: @@ -8052,6 +8075,7 @@ static int mvpp2_remove(struct platform_device *pdev) aggr_txq->descs_dma); } + clk_disable_unprepare(priv->axi_clk); clk_disable_unprepare(priv->mg_clk); clk_disable_unprepare(priv->pp_clk); clk_disable_unprepare(priv->gop_clk); diff --git a/drivers/net/ethernet/mellanox/mlx4/catas.c b/drivers/net/ethernet/mellanox/mlx4/catas.c index 53daa6ca5d83..e2b6b0cac1ac 100644 --- a/drivers/net/ethernet/mellanox/mlx4/catas.c +++ b/drivers/net/ethernet/mellanox/mlx4/catas.c @@ -231,10 +231,10 @@ static void dump_err_buf(struct mlx4_dev *dev) i, swab32(readl(priv->catas_err.map + i))); } -static void poll_catas(unsigned long dev_ptr) +static void poll_catas(struct timer_list *t) { - struct mlx4_dev *dev = (struct mlx4_dev *) dev_ptr; - struct mlx4_priv *priv = mlx4_priv(dev); + struct mlx4_priv *priv = from_timer(priv, t, catas_err.timer); + struct mlx4_dev *dev = &priv->dev; u32 slave_read; if (mlx4_is_slave(dev)) { @@ -277,7 +277,7 @@ void mlx4_start_catas_poll(struct mlx4_dev *dev) phys_addr_t addr; INIT_LIST_HEAD(&priv->catas_err.list); - init_timer(&priv->catas_err.timer); + timer_setup(&priv->catas_err.timer, poll_catas, 0); priv->catas_err.map = NULL; if (!mlx4_is_slave(dev)) { @@ -293,8 +293,6 @@ void mlx4_start_catas_poll(struct mlx4_dev *dev) } } - priv->catas_err.timer.data = (unsigned long) dev; - priv->catas_err.timer.function = poll_catas; priv->catas_err.timer.expires = round_jiffies(jiffies + MLX4_CATAS_POLL_INTERVAL); add_timer(&priv->catas_err.timer); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Kconfig b/drivers/net/ethernet/mellanox/mlx5/core/Kconfig index fdaef00465d7..25deaa5a534c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/Kconfig +++ b/drivers/net/ethernet/mellanox/mlx5/core/Kconfig @@ -6,6 +6,7 @@ config MLX5_CORE tristate "Mellanox Technologies ConnectX-4 and Connect-IB core driver" depends on MAY_USE_DEVLINK depends on PCI + imply PTP_1588_CLOCK default n ---help--- Core driver for low level functionality of the ConnectX-4 and @@ -29,7 +30,6 @@ config MLX5_CORE_EN bool "Mellanox Technologies ConnectX-4 Ethernet support" depends on NETDEVICES && ETHERNET && INET && PCI && MLX5_CORE depends on IPV6=y || IPV6=n || MLX5_CORE=m - imply PTP_1588_CLOCK default n ---help--- Ethernet support in Mellanox Technologies ConnectX-4 NIC. diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Makefile b/drivers/net/ethernet/mellanox/mlx5/core/Makefile index 87a3099808f3..100fe4ecad9b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/Makefile +++ b/drivers/net/ethernet/mellanox/mlx5/core/Makefile @@ -4,7 +4,7 @@ subdir-ccflags-y += -I$(src) mlx5_core-y := main.o cmd.o debugfs.o fw.o eq.o uar.o pagealloc.o \ health.o mcg.o cq.o srq.o alloc.o qp.o port.o mr.o pd.o \ mad.o transobj.o vport.o sriov.o fs_cmd.o fs_core.o \ - fs_counters.o rl.o lag.o dev.o wq.o lib/gid.o \ + fs_counters.o rl.o lag.o dev.o wq.o lib/gid.o lib/clock.o \ diag/fs_tracepoint.o mlx5_core-$(CONFIG_MLX5_ACCEL) += accel/ipsec.o @@ -13,7 +13,7 @@ mlx5_core-$(CONFIG_MLX5_FPGA) += fpga/cmd.o fpga/core.o fpga/conn.o fpga/sdk.o \ fpga/ipsec.o mlx5_core-$(CONFIG_MLX5_CORE_EN) += en_main.o en_common.o en_fs.o en_ethtool.o \ - en_tx.o en_rx.o en_rx_am.o en_txrx.o en_clock.o vxlan.o \ + en_tx.o en_rx.o en_rx_am.o en_txrx.o vxlan.o \ en_arfs.o en_fs_ethtool.o en_selftest.o mlx5_core-$(CONFIG_MLX5_MPFS) += lib/mpfs.o @@ -22,7 +22,7 @@ mlx5_core-$(CONFIG_MLX5_ESWITCH) += eswitch.o eswitch_offloads.o en_rep.o en_tc. mlx5_core-$(CONFIG_MLX5_CORE_EN_DCB) += en_dcbnl.o -mlx5_core-$(CONFIG_MLX5_CORE_IPOIB) += ipoib/ipoib.o ipoib/ethtool.o +mlx5_core-$(CONFIG_MLX5_CORE_IPOIB) += ipoib/ipoib.o ipoib/ethtool.o ipoib/ipoib_vlan.o mlx5_core-$(CONFIG_MLX5_EN_IPSEC) += en_accel/ipsec.o en_accel/ipsec_rxtx.o \ en_accel/ipsec_stats.o diff --git a/drivers/net/ethernet/mellanox/mlx5/core/diag/fs_tracepoint.h b/drivers/net/ethernet/mellanox/mlx5/core/diag/fs_tracepoint.h index 1e3a6c3e4132..80eef4163f52 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/diag/fs_tracepoint.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/diag/fs_tracepoint.h @@ -139,7 +139,7 @@ TRACE_EVENT(mlx5_fs_del_fg, {MLX5_FLOW_CONTEXT_ACTION_FWD_NEXT_PRIO, "NEXT_PRIO"} TRACE_EVENT(mlx5_fs_set_fte, - TP_PROTO(const struct fs_fte *fte, bool new_fte), + TP_PROTO(const struct fs_fte *fte, int new_fte), TP_ARGS(fte, new_fte), TP_STRUCT__entry( __field(const struct fs_fte *, fte) @@ -149,7 +149,7 @@ TRACE_EVENT(mlx5_fs_set_fte, __field(u32, action) __field(u32, flow_tag) __field(u8, mask_enable) - __field(bool, new_fte) + __field(int, new_fte) __array(u32, mask_outer, MLX5_ST_SZ_DW(fte_match_set_lyr_2_4)) __array(u32, mask_inner, MLX5_ST_SZ_DW(fte_match_set_lyr_2_4)) __array(u32, mask_misc, MLX5_ST_SZ_DW(fte_match_set_misc)) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h index cc13d3dbd366..2059122eb089 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h @@ -267,28 +267,6 @@ struct mlx5e_dcbx { }; #endif -#define MAX_PIN_NUM 8 -struct mlx5e_pps { - u8 pin_caps[MAX_PIN_NUM]; - struct work_struct out_work; - u64 start[MAX_PIN_NUM]; - u8 enabled; -}; - -struct mlx5e_tstamp { - rwlock_t lock; - struct cyclecounter cycles; - struct timecounter clock; - struct hwtstamp_config hwtstamp_config; - u32 nominal_c_mult; - unsigned long overflow_period; - struct delayed_work overflow_work; - struct mlx5_core_dev *mdev; - struct ptp_clock *ptp; - struct ptp_clock_info ptp_info; - struct mlx5e_pps pps_info; -}; - enum { MLX5E_RQ_STATE_ENABLED, MLX5E_RQ_STATE_AM, @@ -375,9 +353,10 @@ struct mlx5e_txqsq { u8 min_inline_mode; u16 edge; struct device *pdev; - struct mlx5e_tstamp *tstamp; __be32 mkey_be; unsigned long state; + struct hwtstamp_config *tstamp; + struct mlx5_clock *clock; /* control path */ struct mlx5_wq_ctrl wq_ctrl; @@ -543,10 +522,11 @@ struct mlx5e_rq { struct mlx5e_channel *channel; struct device *pdev; struct net_device *netdev; - struct mlx5e_tstamp *tstamp; struct mlx5e_rq_stats stats; struct mlx5e_cq cq; struct mlx5e_page_cache page_cache; + struct hwtstamp_config *tstamp; + struct mlx5_clock *clock; mlx5e_fp_handle_rx_cqe handle_rx_cqe; mlx5e_fp_post_rx_wqes post_wqes; @@ -588,7 +568,7 @@ struct mlx5e_channel { /* control */ struct mlx5e_priv *priv; struct mlx5_core_dev *mdev; - struct mlx5e_tstamp *tstamp; + struct hwtstamp_config *tstamp; int ix; }; @@ -789,7 +769,7 @@ struct mlx5e_priv { struct mlx5_core_dev *mdev; struct net_device *netdev; struct mlx5e_stats stats; - struct mlx5e_tstamp tstamp; + struct hwtstamp_config tstamp; u16 q_counter; #ifdef CONFIG_MLX5_CORE_EN_DCB struct mlx5e_dcbx dcbx; @@ -873,12 +853,6 @@ void mlx5e_ethtool_init_steering(struct mlx5e_priv *priv); void mlx5e_ethtool_cleanup_steering(struct mlx5e_priv *priv); void mlx5e_set_rx_mode_work(struct work_struct *work); -void mlx5e_fill_hwstamp(struct mlx5e_tstamp *clock, u64 timestamp, - struct skb_shared_hwtstamps *hwts); -void mlx5e_timestamp_init(struct mlx5e_priv *priv); -void mlx5e_timestamp_cleanup(struct mlx5e_priv *priv); -void mlx5e_pps_event_handler(struct mlx5e_priv *priv, - struct ptp_clock_event *event); int mlx5e_hwstamp_set(struct mlx5e_priv *priv, struct ifreq *ifr); int mlx5e_hwstamp_get(struct mlx5e_priv *priv, struct ifreq *ifr); int mlx5e_modify_rx_cqe_compression_locked(struct mlx5e_priv *priv, bool val); @@ -889,6 +863,7 @@ int mlx5e_vlan_rx_kill_vid(struct net_device *dev, __always_unused __be16 proto, u16 vid); void mlx5e_enable_vlan_filter(struct mlx5e_priv *priv); void mlx5e_disable_vlan_filter(struct mlx5e_priv *priv); +void mlx5e_timestamp_set(struct mlx5e_priv *priv); struct mlx5e_redirect_rqt_param { bool is_rss; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_clock.c b/drivers/net/ethernet/mellanox/mlx5/core/en_clock.c deleted file mode 100644 index 84dd63e74041..000000000000 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_clock.c +++ /dev/null @@ -1,619 +0,0 @@ -/* - * Copyright (c) 2015, Mellanox Technologies. All rights reserved. - * - * This software is available to you under a choice of one of two - * licenses. You may choose to be licensed under the terms of the GNU - * General Public License (GPL) Version 2, available from the file - * COPYING in the main directory of this source tree, or the - * OpenIB.org BSD license below: - * - * Redistribution and use in source and binary forms, with or - * without modification, are permitted provided that the following - * conditions are met: - * - * - Redistributions of source code must retain the above - * copyright notice, this list of conditions and the following - * disclaimer. - * - * - Redistributions in binary form must reproduce the above - * copyright notice, this list of conditions and the following - * disclaimer in the documentation and/or other materials - * provided with the distribution. - * - * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, - * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF - * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND - * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS - * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN - * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN - * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE - * SOFTWARE. - */ - -#include <linux/clocksource.h> -#include "en.h" - -enum { - MLX5E_CYCLES_SHIFT = 23 -}; - -enum { - MLX5E_PIN_MODE_IN = 0x0, - MLX5E_PIN_MODE_OUT = 0x1, -}; - -enum { - MLX5E_OUT_PATTERN_PULSE = 0x0, - MLX5E_OUT_PATTERN_PERIODIC = 0x1, -}; - -enum { - MLX5E_EVENT_MODE_DISABLE = 0x0, - MLX5E_EVENT_MODE_REPETETIVE = 0x1, - MLX5E_EVENT_MODE_ONCE_TILL_ARM = 0x2, -}; - -enum { - MLX5E_MTPPS_FS_ENABLE = BIT(0x0), - MLX5E_MTPPS_FS_PATTERN = BIT(0x2), - MLX5E_MTPPS_FS_PIN_MODE = BIT(0x3), - MLX5E_MTPPS_FS_TIME_STAMP = BIT(0x4), - MLX5E_MTPPS_FS_OUT_PULSE_DURATION = BIT(0x5), - MLX5E_MTPPS_FS_ENH_OUT_PER_ADJ = BIT(0x7), -}; - -void mlx5e_fill_hwstamp(struct mlx5e_tstamp *tstamp, u64 timestamp, - struct skb_shared_hwtstamps *hwts) -{ - u64 nsec; - - read_lock(&tstamp->lock); - nsec = timecounter_cyc2time(&tstamp->clock, timestamp); - read_unlock(&tstamp->lock); - - hwts->hwtstamp = ns_to_ktime(nsec); -} - -static u64 mlx5e_read_internal_timer(const struct cyclecounter *cc) -{ - struct mlx5e_tstamp *tstamp = container_of(cc, struct mlx5e_tstamp, - cycles); - - return mlx5_read_internal_timer(tstamp->mdev) & cc->mask; -} - -static void mlx5e_pps_out(struct work_struct *work) -{ - struct mlx5e_pps *pps_info = container_of(work, struct mlx5e_pps, - out_work); - struct mlx5e_tstamp *tstamp = container_of(pps_info, struct mlx5e_tstamp, - pps_info); - u32 in[MLX5_ST_SZ_DW(mtpps_reg)] = {0}; - unsigned long flags; - int i; - - for (i = 0; i < tstamp->ptp_info.n_pins; i++) { - u64 tstart; - - write_lock_irqsave(&tstamp->lock, flags); - tstart = tstamp->pps_info.start[i]; - tstamp->pps_info.start[i] = 0; - write_unlock_irqrestore(&tstamp->lock, flags); - if (!tstart) - continue; - - MLX5_SET(mtpps_reg, in, pin, i); - MLX5_SET64(mtpps_reg, in, time_stamp, tstart); - MLX5_SET(mtpps_reg, in, field_select, MLX5E_MTPPS_FS_TIME_STAMP); - mlx5_set_mtpps(tstamp->mdev, in, sizeof(in)); - } -} - -static void mlx5e_timestamp_overflow(struct work_struct *work) -{ - struct delayed_work *dwork = to_delayed_work(work); - struct mlx5e_tstamp *tstamp = container_of(dwork, struct mlx5e_tstamp, - overflow_work); - struct mlx5e_priv *priv = container_of(tstamp, struct mlx5e_priv, tstamp); - unsigned long flags; - - write_lock_irqsave(&tstamp->lock, flags); - timecounter_read(&tstamp->clock); - write_unlock_irqrestore(&tstamp->lock, flags); - queue_delayed_work(priv->wq, &tstamp->overflow_work, - msecs_to_jiffies(tstamp->overflow_period * 1000)); -} - -int mlx5e_hwstamp_set(struct mlx5e_priv *priv, struct ifreq *ifr) -{ - struct hwtstamp_config config; - int err; - - if (!MLX5_CAP_GEN(priv->mdev, device_frequency_khz)) - return -EOPNOTSUPP; - - if (copy_from_user(&config, ifr->ifr_data, sizeof(config))) - return -EFAULT; - - /* TX HW timestamp */ - switch (config.tx_type) { - case HWTSTAMP_TX_OFF: - case HWTSTAMP_TX_ON: - break; - default: - return -ERANGE; - } - - mutex_lock(&priv->state_lock); - /* RX HW timestamp */ - switch (config.rx_filter) { - case HWTSTAMP_FILTER_NONE: - /* Reset CQE compression to Admin default */ - mlx5e_modify_rx_cqe_compression_locked(priv, priv->channels.params.rx_cqe_compress_def); - break; - case HWTSTAMP_FILTER_ALL: - case HWTSTAMP_FILTER_SOME: - case HWTSTAMP_FILTER_PTP_V1_L4_EVENT: - case HWTSTAMP_FILTER_PTP_V1_L4_SYNC: - case HWTSTAMP_FILTER_PTP_V1_L4_DELAY_REQ: - case HWTSTAMP_FILTER_PTP_V2_L4_EVENT: - case HWTSTAMP_FILTER_PTP_V2_L4_SYNC: - case HWTSTAMP_FILTER_PTP_V2_L4_DELAY_REQ: - case HWTSTAMP_FILTER_PTP_V2_L2_EVENT: - case HWTSTAMP_FILTER_PTP_V2_L2_SYNC: - case HWTSTAMP_FILTER_PTP_V2_L2_DELAY_REQ: - case HWTSTAMP_FILTER_PTP_V2_EVENT: - case HWTSTAMP_FILTER_PTP_V2_SYNC: - case HWTSTAMP_FILTER_PTP_V2_DELAY_REQ: - case HWTSTAMP_FILTER_NTP_ALL: - /* Disable CQE compression */ - netdev_warn(priv->netdev, "Disabling cqe compression"); - err = mlx5e_modify_rx_cqe_compression_locked(priv, false); - if (err) { - netdev_err(priv->netdev, "Failed disabling cqe compression err=%d\n", err); - mutex_unlock(&priv->state_lock); - return err; - } - config.rx_filter = HWTSTAMP_FILTER_ALL; - break; - default: - mutex_unlock(&priv->state_lock); - return -ERANGE; - } - - memcpy(&priv->tstamp.hwtstamp_config, &config, sizeof(config)); - mutex_unlock(&priv->state_lock); - - return copy_to_user(ifr->ifr_data, &config, - sizeof(config)) ? -EFAULT : 0; -} - -int mlx5e_hwstamp_get(struct mlx5e_priv *priv, struct ifreq *ifr) -{ - struct hwtstamp_config *cfg = &priv->tstamp.hwtstamp_config; - - if (!MLX5_CAP_GEN(priv->mdev, device_frequency_khz)) - return -EOPNOTSUPP; - - return copy_to_user(ifr->ifr_data, cfg, sizeof(*cfg)) ? -EFAULT : 0; -} - -static int mlx5e_ptp_settime(struct ptp_clock_info *ptp, - const struct timespec64 *ts) -{ - struct mlx5e_tstamp *tstamp = container_of(ptp, struct mlx5e_tstamp, - ptp_info); - u64 ns = timespec64_to_ns(ts); - unsigned long flags; - - write_lock_irqsave(&tstamp->lock, flags); - timecounter_init(&tstamp->clock, &tstamp->cycles, ns); - write_unlock_irqrestore(&tstamp->lock, flags); - - return 0; -} - -static int mlx5e_ptp_gettime(struct ptp_clock_info *ptp, - struct timespec64 *ts) -{ - struct mlx5e_tstamp *tstamp = container_of(ptp, struct mlx5e_tstamp, - ptp_info); - u64 ns; - unsigned long flags; - - write_lock_irqsave(&tstamp->lock, flags); - ns = timecounter_read(&tstamp->clock); - write_unlock_irqrestore(&tstamp->lock, flags); - - *ts = ns_to_timespec64(ns); - - return 0; -} - -static int mlx5e_ptp_adjtime(struct ptp_clock_info *ptp, s64 delta) -{ - struct mlx5e_tstamp *tstamp = container_of(ptp, struct mlx5e_tstamp, - ptp_info); - unsigned long flags; - - write_lock_irqsave(&tstamp->lock, flags); - timecounter_adjtime(&tstamp->clock, delta); - write_unlock_irqrestore(&tstamp->lock, flags); - - return 0; -} - -static int mlx5e_ptp_adjfreq(struct ptp_clock_info *ptp, s32 delta) -{ - u64 adj; - u32 diff; - unsigned long flags; - int neg_adj = 0; - struct mlx5e_tstamp *tstamp = container_of(ptp, struct mlx5e_tstamp, - ptp_info); - - if (delta < 0) { - neg_adj = 1; - delta = -delta; - } - - adj = tstamp->nominal_c_mult; - adj *= delta; - diff = div_u64(adj, 1000000000ULL); - - write_lock_irqsave(&tstamp->lock, flags); - timecounter_read(&tstamp->clock); - tstamp->cycles.mult = neg_adj ? tstamp->nominal_c_mult - diff : - tstamp->nominal_c_mult + diff; - write_unlock_irqrestore(&tstamp->lock, flags); - - return 0; -} - -static int mlx5e_extts_configure(struct ptp_clock_info *ptp, - struct ptp_clock_request *rq, - int on) -{ - struct mlx5e_tstamp *tstamp = - container_of(ptp, struct mlx5e_tstamp, ptp_info); - struct mlx5e_priv *priv = - container_of(tstamp, struct mlx5e_priv, tstamp); - u32 in[MLX5_ST_SZ_DW(mtpps_reg)] = {0}; - u32 field_select = 0; - u8 pin_mode = 0; - u8 pattern = 0; - int pin = -1; - int err = 0; - - if (!MLX5_PPS_CAP(priv->mdev)) - return -EOPNOTSUPP; - - if (rq->extts.index >= tstamp->ptp_info.n_pins) - return -EINVAL; - - if (on) { - pin = ptp_find_pin(tstamp->ptp, PTP_PF_EXTTS, rq->extts.index); - if (pin < 0) - return -EBUSY; - pin_mode = MLX5E_PIN_MODE_IN; - pattern = !!(rq->extts.flags & PTP_FALLING_EDGE); - field_select = MLX5E_MTPPS_FS_PIN_MODE | - MLX5E_MTPPS_FS_PATTERN | - MLX5E_MTPPS_FS_ENABLE; - } else { - pin = rq->extts.index; - field_select = MLX5E_MTPPS_FS_ENABLE; - } - - MLX5_SET(mtpps_reg, in, pin, pin); - MLX5_SET(mtpps_reg, in, pin_mode, pin_mode); - MLX5_SET(mtpps_reg, in, pattern, pattern); - MLX5_SET(mtpps_reg, in, enable, on); - MLX5_SET(mtpps_reg, in, field_select, field_select); - - err = mlx5_set_mtpps(priv->mdev, in, sizeof(in)); - if (err) - return err; - - return mlx5_set_mtppse(priv->mdev, pin, 0, - MLX5E_EVENT_MODE_REPETETIVE & on); -} - -static int mlx5e_perout_configure(struct ptp_clock_info *ptp, - struct ptp_clock_request *rq, - int on) -{ - struct mlx5e_tstamp *tstamp = - container_of(ptp, struct mlx5e_tstamp, ptp_info); - struct mlx5e_priv *priv = - container_of(tstamp, struct mlx5e_priv, tstamp); - u32 in[MLX5_ST_SZ_DW(mtpps_reg)] = {0}; - u64 nsec_now, nsec_delta, time_stamp = 0; - u64 cycles_now, cycles_delta; - struct timespec64 ts; - unsigned long flags; - u32 field_select = 0; - u8 pin_mode = 0; - u8 pattern = 0; - int pin = -1; - int err = 0; - s64 ns; - - if (!MLX5_PPS_CAP(priv->mdev)) - return -EOPNOTSUPP; - - if (rq->perout.index >= tstamp->ptp_info.n_pins) - return -EINVAL; - - if (on) { - pin = ptp_find_pin(tstamp->ptp, PTP_PF_PEROUT, - rq->perout.index); - if (pin < 0) - return -EBUSY; - - pin_mode = MLX5E_PIN_MODE_OUT; - pattern = MLX5E_OUT_PATTERN_PERIODIC; - ts.tv_sec = rq->perout.period.sec; - ts.tv_nsec = rq->perout.period.nsec; - ns = timespec64_to_ns(&ts); - - if ((ns >> 1) != 500000000LL) - return -EINVAL; - - ts.tv_sec = rq->perout.start.sec; - ts.tv_nsec = rq->perout.start.nsec; - ns = timespec64_to_ns(&ts); - cycles_now = mlx5_read_internal_timer(tstamp->mdev); - write_lock_irqsave(&tstamp->lock, flags); - nsec_now = timecounter_cyc2time(&tstamp->clock, cycles_now); - nsec_delta = ns - nsec_now; - cycles_delta = div64_u64(nsec_delta << tstamp->cycles.shift, - tstamp->cycles.mult); - write_unlock_irqrestore(&tstamp->lock, flags); - time_stamp = cycles_now + cycles_delta; - field_select = MLX5E_MTPPS_FS_PIN_MODE | - MLX5E_MTPPS_FS_PATTERN | - MLX5E_MTPPS_FS_ENABLE | - MLX5E_MTPPS_FS_TIME_STAMP; - } else { - pin = rq->perout.index; - field_select = MLX5E_MTPPS_FS_ENABLE; - } - - MLX5_SET(mtpps_reg, in, pin, pin); - MLX5_SET(mtpps_reg, in, pin_mode, pin_mode); - MLX5_SET(mtpps_reg, in, pattern, pattern); - MLX5_SET(mtpps_reg, in, enable, on); - MLX5_SET64(mtpps_reg, in, time_stamp, time_stamp); - MLX5_SET(mtpps_reg, in, field_select, field_select); - - err = mlx5_set_mtpps(priv->mdev, in, sizeof(in)); - if (err) - return err; - - return mlx5_set_mtppse(priv->mdev, pin, 0, - MLX5E_EVENT_MODE_REPETETIVE & on); -} - -static int mlx5e_pps_configure(struct ptp_clock_info *ptp, - struct ptp_clock_request *rq, - int on) -{ - struct mlx5e_tstamp *tstamp = - container_of(ptp, struct mlx5e_tstamp, ptp_info); - - tstamp->pps_info.enabled = !!on; - return 0; -} - -static int mlx5e_ptp_enable(struct ptp_clock_info *ptp, - struct ptp_clock_request *rq, - int on) -{ - switch (rq->type) { - case PTP_CLK_REQ_EXTTS: - return mlx5e_extts_configure(ptp, rq, on); - case PTP_CLK_REQ_PEROUT: - return mlx5e_perout_configure(ptp, rq, on); - case PTP_CLK_REQ_PPS: - return mlx5e_pps_configure(ptp, rq, on); - default: - return -EOPNOTSUPP; - } - return 0; -} - -static int mlx5e_ptp_verify(struct ptp_clock_info *ptp, unsigned int pin, - enum ptp_pin_function func, unsigned int chan) -{ - return (func == PTP_PF_PHYSYNC) ? -EOPNOTSUPP : 0; -} - -static const struct ptp_clock_info mlx5e_ptp_clock_info = { - .owner = THIS_MODULE, - .max_adj = 100000000, - .n_alarm = 0, - .n_ext_ts = 0, - .n_per_out = 0, - .n_pins = 0, - .pps = 0, - .adjfreq = mlx5e_ptp_adjfreq, - .adjtime = mlx5e_ptp_adjtime, - .gettime64 = mlx5e_ptp_gettime, - .settime64 = mlx5e_ptp_settime, - .enable = NULL, - .verify = NULL, -}; - -static void mlx5e_timestamp_init_config(struct mlx5e_tstamp *tstamp) -{ - tstamp->hwtstamp_config.tx_type = HWTSTAMP_TX_OFF; - tstamp->hwtstamp_config.rx_filter = HWTSTAMP_FILTER_NONE; -} - -static int mlx5e_init_pin_config(struct mlx5e_tstamp *tstamp) -{ - int i; - - tstamp->ptp_info.pin_config = - kzalloc(sizeof(*tstamp->ptp_info.pin_config) * - tstamp->ptp_info.n_pins, GFP_KERNEL); - if (!tstamp->ptp_info.pin_config) - return -ENOMEM; - tstamp->ptp_info.enable = mlx5e_ptp_enable; - tstamp->ptp_info.verify = mlx5e_ptp_verify; - tstamp->ptp_info.pps = 1; - - for (i = 0; i < tstamp->ptp_info.n_pins; i++) { - snprintf(tstamp->ptp_info.pin_config[i].name, - sizeof(tstamp->ptp_info.pin_config[i].name), - "mlx5_pps%d", i); - tstamp->ptp_info.pin_config[i].index = i; - tstamp->ptp_info.pin_config[i].func = PTP_PF_NONE; - tstamp->ptp_info.pin_config[i].chan = i; - } - - return 0; -} - -static void mlx5e_get_pps_caps(struct mlx5e_priv *priv, - struct mlx5e_tstamp *tstamp) -{ - u32 out[MLX5_ST_SZ_DW(mtpps_reg)] = {0}; - - mlx5_query_mtpps(priv->mdev, out, sizeof(out)); - - tstamp->ptp_info.n_pins = MLX5_GET(mtpps_reg, out, - cap_number_of_pps_pins); - tstamp->ptp_info.n_ext_ts = MLX5_GET(mtpps_reg, out, - cap_max_num_of_pps_in_pins); - tstamp->ptp_info.n_per_out = MLX5_GET(mtpps_reg, out, - cap_max_num_of_pps_out_pins); - - tstamp->pps_info.pin_caps[0] = MLX5_GET(mtpps_reg, out, cap_pin_0_mode); - tstamp->pps_info.pin_caps[1] = MLX5_GET(mtpps_reg, out, cap_pin_1_mode); - tstamp->pps_info.pin_caps[2] = MLX5_GET(mtpps_reg, out, cap_pin_2_mode); - tstamp->pps_info.pin_caps[3] = MLX5_GET(mtpps_reg, out, cap_pin_3_mode); - tstamp->pps_info.pin_caps[4] = MLX5_GET(mtpps_reg, out, cap_pin_4_mode); - tstamp->pps_info.pin_caps[5] = MLX5_GET(mtpps_reg, out, cap_pin_5_mode); - tstamp->pps_info.pin_caps[6] = MLX5_GET(mtpps_reg, out, cap_pin_6_mode); - tstamp->pps_info.pin_caps[7] = MLX5_GET(mtpps_reg, out, cap_pin_7_mode); -} - -void mlx5e_pps_event_handler(struct mlx5e_priv *priv, - struct ptp_clock_event *event) -{ - struct net_device *netdev = priv->netdev; - struct mlx5e_tstamp *tstamp = &priv->tstamp; - struct timespec64 ts; - u64 nsec_now, nsec_delta; - u64 cycles_now, cycles_delta; - int pin = event->index; - s64 ns; - unsigned long flags; - - switch (tstamp->ptp_info.pin_config[pin].func) { - case PTP_PF_EXTTS: - if (tstamp->pps_info.enabled) { - event->type = PTP_CLOCK_PPSUSR; - event->pps_times.ts_real = ns_to_timespec64(event->timestamp); - } else { - event->type = PTP_CLOCK_EXTTS; - } - ptp_clock_event(tstamp->ptp, event); - break; - case PTP_PF_PEROUT: - mlx5e_ptp_gettime(&tstamp->ptp_info, &ts); - cycles_now = mlx5_read_internal_timer(tstamp->mdev); - ts.tv_sec += 1; - ts.tv_nsec = 0; - ns = timespec64_to_ns(&ts); - write_lock_irqsave(&tstamp->lock, flags); - nsec_now = timecounter_cyc2time(&tstamp->clock, cycles_now); - nsec_delta = ns - nsec_now; - cycles_delta = div64_u64(nsec_delta << tstamp->cycles.shift, - tstamp->cycles.mult); - tstamp->pps_info.start[pin] = cycles_now + cycles_delta; - queue_work(priv->wq, &tstamp->pps_info.out_work); - write_unlock_irqrestore(&tstamp->lock, flags); - break; - default: - netdev_err(netdev, "%s: Unhandled event\n", __func__); - } -} - -void mlx5e_timestamp_init(struct mlx5e_priv *priv) -{ - struct mlx5e_tstamp *tstamp = &priv->tstamp; - u64 ns; - u64 frac = 0; - u32 dev_freq; - - mlx5e_timestamp_init_config(tstamp); - dev_freq = MLX5_CAP_GEN(priv->mdev, device_frequency_khz); - if (!dev_freq) { - mlx5_core_warn(priv->mdev, "invalid device_frequency_khz, aborting HW clock init\n"); - return; - } - rwlock_init(&tstamp->lock); - tstamp->cycles.read = mlx5e_read_internal_timer; - tstamp->cycles.shift = MLX5E_CYCLES_SHIFT; - tstamp->cycles.mult = clocksource_khz2mult(dev_freq, - tstamp->cycles.shift); - tstamp->nominal_c_mult = tstamp->cycles.mult; - tstamp->cycles.mask = CLOCKSOURCE_MASK(41); - tstamp->mdev = priv->mdev; - - timecounter_init(&tstamp->clock, &tstamp->cycles, - ktime_to_ns(ktime_get_real())); - - /* Calculate period in seconds to call the overflow watchdog - to make - * sure counter is checked at least once every wrap around. - */ - ns = cyclecounter_cyc2ns(&tstamp->cycles, tstamp->cycles.mask, - frac, &frac); - do_div(ns, NSEC_PER_SEC / 2 / HZ); - tstamp->overflow_period = ns; - - INIT_WORK(&tstamp->pps_info.out_work, mlx5e_pps_out); - INIT_DELAYED_WORK(&tstamp->overflow_work, mlx5e_timestamp_overflow); - if (tstamp->overflow_period) - queue_delayed_work(priv->wq, &tstamp->overflow_work, 0); - else - mlx5_core_warn(priv->mdev, "invalid overflow period, overflow_work is not scheduled\n"); - - /* Configure the PHC */ - tstamp->ptp_info = mlx5e_ptp_clock_info; - snprintf(tstamp->ptp_info.name, 16, "mlx5 ptp"); - - /* Initialize 1PPS data structures */ - if (MLX5_PPS_CAP(priv->mdev)) - mlx5e_get_pps_caps(priv, tstamp); - if (tstamp->ptp_info.n_pins) - mlx5e_init_pin_config(tstamp); - - tstamp->ptp = ptp_clock_register(&tstamp->ptp_info, - &priv->mdev->pdev->dev); - if (IS_ERR(tstamp->ptp)) { - mlx5_core_warn(priv->mdev, "ptp_clock_register failed %ld\n", - PTR_ERR(tstamp->ptp)); - tstamp->ptp = NULL; - } -} - -void mlx5e_timestamp_cleanup(struct mlx5e_priv *priv) -{ - struct mlx5e_tstamp *tstamp = &priv->tstamp; - - if (!MLX5_CAP_GEN(priv->mdev, device_frequency_khz)) - return; - - if (priv->tstamp.ptp) { - ptp_clock_unregister(priv->tstamp.ptp); - priv->tstamp.ptp = NULL; - } - - cancel_work_sync(&tstamp->pps_info.out_work); - cancel_delayed_work_sync(&tstamp->overflow_work); - kfree(tstamp->ptp_info.pin_config); -} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_common.c b/drivers/net/ethernet/mellanox/mlx5/core/en_common.c index ece3fb147e3e..157d02917237 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_common.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_common.c @@ -134,6 +134,7 @@ void mlx5e_destroy_mdev_resources(struct mlx5_core_dev *mdev) mlx5_core_destroy_mkey(mdev, &res->mkey); mlx5_core_dealloc_transport_domain(mdev, res->td.tdn); mlx5_core_dealloc_pd(mdev, res->pdn); + memset(res, 0, sizeof(*res)); } int mlx5e_refresh_tirs(struct mlx5e_priv *priv, bool enable_uc_lb) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c index d12e9fc0d76b..81a112e40fe3 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c @@ -1417,14 +1417,15 @@ static int mlx5e_set_pauseparam(struct net_device *netdev, int mlx5e_ethtool_get_ts_info(struct mlx5e_priv *priv, struct ethtool_ts_info *info) { + struct mlx5_core_dev *mdev = priv->mdev; int ret; ret = ethtool_op_get_ts_info(priv->netdev, info); if (ret) return ret; - info->phc_index = priv->tstamp.ptp ? - ptp_clock_index(priv->tstamp.ptp) : -1; + info->phc_index = mdev->clock.ptp ? + ptp_clock_index(mdev->clock.ptp) : -1; if (!MLX5_CAP_GEN(priv->mdev, device_frequency_khz)) return 0; @@ -1754,7 +1755,7 @@ static int set_pflag_rx_cqe_compress(struct net_device *netdev, if (!MLX5_CAP_GEN(mdev, cqe_compression)) return -EOPNOTSUPP; - if (enable && priv->tstamp.hwtstamp_config.rx_filter != HWTSTAMP_FILTER_NONE) { + if (enable && priv->tstamp.rx_filter != HWTSTAMP_FILTER_NONE) { netdev_err(netdev, "Can't enable cqe compression while timestamping is enabled.\n"); return -EINVAL; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c index f11fd07ac4dd..850cdc980ab5 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c @@ -291,7 +291,7 @@ void mlx5e_enable_vlan_filter(struct mlx5e_priv *priv) priv->fs.vlan.filter_disabled = false; if (priv->netdev->flags & IFF_PROMISC) return; - mlx5e_del_any_vid_rules(priv); + mlx5e_del_vlan_rule(priv, MLX5E_VLAN_RULE_TYPE_ANY_CTAG_VID, 0); } void mlx5e_disable_vlan_filter(struct mlx5e_priv *priv) @@ -302,7 +302,7 @@ void mlx5e_disable_vlan_filter(struct mlx5e_priv *priv) priv->fs.vlan.filter_disabled = true; if (priv->netdev->flags & IFF_PROMISC) return; - mlx5e_add_any_vid_rules(priv); + mlx5e_add_vlan_rule(priv, MLX5E_VLAN_RULE_TYPE_ANY_CTAG_VID, 0); } int mlx5e_vlan_rx_add_vid(struct net_device *dev, __always_unused __be16 proto, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index dfc29720ab77..6df00dd9745a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -184,7 +184,6 @@ static void mlx5e_update_sw_counters(struct mlx5e_priv *priv) struct mlx5e_sw_stats temp, *s = &temp; struct mlx5e_rq_stats *rq_stats; struct mlx5e_sq_stats *sq_stats; - u64 tx_offload_none = 0; int i, j; memset(s, 0, sizeof(*s)); @@ -199,6 +198,7 @@ static void mlx5e_update_sw_counters(struct mlx5e_priv *priv) s->rx_lro_bytes += rq_stats->lro_bytes; s->rx_csum_none += rq_stats->csum_none; s->rx_csum_complete += rq_stats->csum_complete; + s->rx_csum_unnecessary += rq_stats->csum_unnecessary; s->rx_csum_unnecessary_inner += rq_stats->csum_unnecessary_inner; s->rx_xdp_drop += rq_stats->xdp_drop; s->rx_xdp_tx += rq_stats->xdp_tx; @@ -229,14 +229,11 @@ static void mlx5e_update_sw_counters(struct mlx5e_priv *priv) s->tx_queue_dropped += sq_stats->dropped; s->tx_xmit_more += sq_stats->xmit_more; s->tx_csum_partial_inner += sq_stats->csum_partial_inner; - tx_offload_none += sq_stats->csum_none; + s->tx_csum_none += sq_stats->csum_none; + s->tx_csum_partial += sq_stats->csum_partial; } } - /* Update calculated offload counters */ - s->tx_csum_partial = s->tx_packets - tx_offload_none - s->tx_csum_partial_inner; - s->rx_csum_unnecessary = s->rx_packets - s->rx_csum_none - s->rx_csum_complete; - s->link_down_events_phy = MLX5_GET(ppcnt_reg, priv->stats.pport.phy_counters, counter_set.phys_layer_cntrs.link_down_events); @@ -376,8 +373,6 @@ static void mlx5e_async_event(struct mlx5_core_dev *mdev, void *vpriv, enum mlx5_dev_event event, unsigned long param) { struct mlx5e_priv *priv = vpriv; - struct ptp_clock_event ptp_event; - struct mlx5_eqe *eqe = NULL; if (!test_bit(MLX5E_STATE_ASYNC_EVENTS_ENABLED, &priv->state)) return; @@ -387,14 +382,6 @@ static void mlx5e_async_event(struct mlx5_core_dev *mdev, void *vpriv, case MLX5_DEV_EVENT_PORT_DOWN: queue_work(priv->wq, &priv->update_carrier_work); break; - case MLX5_DEV_EVENT_PPS: - eqe = (struct mlx5_eqe *)param; - ptp_event.index = eqe->data.pps.pin; - ptp_event.timestamp = - timecounter_cyc2time(&priv->tstamp.clock, - be64_to_cpu(eqe->data.pps.time_stamp)); - mlx5e_pps_event_handler(vpriv, &ptp_event); - break; default: break; } @@ -588,6 +575,7 @@ static int mlx5e_alloc_rq(struct mlx5e_channel *c, rq->pdev = c->pdev; rq->netdev = c->netdev; rq->tstamp = c->tstamp; + rq->clock = &mdev->clock; rq->channel = c; rq->ix = c->ix; rq->mdev = mdev; @@ -1126,6 +1114,7 @@ static int mlx5e_alloc_txqsq(struct mlx5e_channel *c, sq->pdev = c->pdev; sq->tstamp = c->tstamp; + sq->clock = &mdev->clock; sq->mkey_be = c->mkey_be; sq->channel = c; sq->txq_ix = txq_ix; @@ -2681,6 +2670,12 @@ void mlx5e_switch_priv_channels(struct mlx5e_priv *priv, netif_carrier_on(netdev); } +void mlx5e_timestamp_set(struct mlx5e_priv *priv) +{ + priv->tstamp.tx_type = HWTSTAMP_TX_OFF; + priv->tstamp.rx_filter = HWTSTAMP_FILTER_NONE; +} + int mlx5e_open_locked(struct net_device *netdev) { struct mlx5e_priv *priv = netdev_priv(netdev); @@ -2696,7 +2691,7 @@ int mlx5e_open_locked(struct net_device *netdev) mlx5e_activate_priv_channels(priv); if (priv->profile->update_carrier) priv->profile->update_carrier(priv); - mlx5e_timestamp_init(priv); + mlx5e_timestamp_set(priv); if (priv->profile->update_stats) queue_delayed_work(priv->wq, &priv->update_stats_work, 0); @@ -2734,7 +2729,6 @@ int mlx5e_close_locked(struct net_device *netdev) clear_bit(MLX5E_STATE_OPENED, &priv->state); - mlx5e_timestamp_cleanup(priv); netif_carrier_off(priv->netdev); mlx5e_deactivate_priv_channels(priv); mlx5e_close_channels(&priv->channels); @@ -3333,8 +3327,8 @@ static int mlx5e_handle_feature(struct net_device *netdev, err = feature_handler(netdev, enable); if (err) { - netdev_err(netdev, "%s feature 0x%llx failed err %d\n", - enable ? "Enable" : "Disable", feature, err); + netdev_err(netdev, "%s feature %pNF failed, err %d\n", + enable ? "Enable" : "Disable", &feature, err); return err; } @@ -3406,6 +3400,80 @@ out: return err; } +int mlx5e_hwstamp_set(struct mlx5e_priv *priv, struct ifreq *ifr) +{ + struct hwtstamp_config config; + int err; + + if (!MLX5_CAP_GEN(priv->mdev, device_frequency_khz)) + return -EOPNOTSUPP; + + if (copy_from_user(&config, ifr->ifr_data, sizeof(config))) + return -EFAULT; + + /* TX HW timestamp */ + switch (config.tx_type) { + case HWTSTAMP_TX_OFF: + case HWTSTAMP_TX_ON: + break; + default: + return -ERANGE; + } + + mutex_lock(&priv->state_lock); + /* RX HW timestamp */ + switch (config.rx_filter) { + case HWTSTAMP_FILTER_NONE: + /* Reset CQE compression to Admin default */ + mlx5e_modify_rx_cqe_compression_locked(priv, priv->channels.params.rx_cqe_compress_def); + break; + case HWTSTAMP_FILTER_ALL: + case HWTSTAMP_FILTER_SOME: + case HWTSTAMP_FILTER_PTP_V1_L4_EVENT: + case HWTSTAMP_FILTER_PTP_V1_L4_SYNC: + case HWTSTAMP_FILTER_PTP_V1_L4_DELAY_REQ: + case HWTSTAMP_FILTER_PTP_V2_L4_EVENT: + case HWTSTAMP_FILTER_PTP_V2_L4_SYNC: + case HWTSTAMP_FILTER_PTP_V2_L4_DELAY_REQ: + case HWTSTAMP_FILTER_PTP_V2_L2_EVENT: + case HWTSTAMP_FILTER_PTP_V2_L2_SYNC: + case HWTSTAMP_FILTER_PTP_V2_L2_DELAY_REQ: + case HWTSTAMP_FILTER_PTP_V2_EVENT: + case HWTSTAMP_FILTER_PTP_V2_SYNC: + case HWTSTAMP_FILTER_PTP_V2_DELAY_REQ: + case HWTSTAMP_FILTER_NTP_ALL: + /* Disable CQE compression */ + netdev_warn(priv->netdev, "Disabling cqe compression"); + err = mlx5e_modify_rx_cqe_compression_locked(priv, false); + if (err) { + netdev_err(priv->netdev, "Failed disabling cqe compression err=%d\n", err); + mutex_unlock(&priv->state_lock); + return err; + } + config.rx_filter = HWTSTAMP_FILTER_ALL; + break; + default: + mutex_unlock(&priv->state_lock); + return -ERANGE; + } + + memcpy(&priv->tstamp, &config, sizeof(config)); + mutex_unlock(&priv->state_lock); + + return copy_to_user(ifr->ifr_data, &config, + sizeof(config)) ? -EFAULT : 0; +} + +int mlx5e_hwstamp_get(struct mlx5e_priv *priv, struct ifreq *ifr) +{ + struct hwtstamp_config *cfg = &priv->tstamp; + + if (!MLX5_CAP_GEN(priv->mdev, device_frequency_khz)) + return -EOPNOTSUPP; + + return copy_to_user(ifr->ifr_data, cfg, sizeof(*cfg)) ? -EFAULT : 0; +} + static int mlx5e_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) { struct mlx5e_priv *priv = netdev_priv(dev); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c index f1dd638384d3..2c3f2e9b6983 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c @@ -42,10 +42,11 @@ #include "en_rep.h" #include "ipoib/ipoib.h" #include "en_accel/ipsec_rxtx.h" +#include "lib/clock.h" -static inline bool mlx5e_rx_hw_stamp(struct mlx5e_tstamp *tstamp) +static inline bool mlx5e_rx_hw_stamp(struct hwtstamp_config *config) { - return tstamp->hwtstamp_config.rx_filter == HWTSTAMP_FILTER_ALL; + return config->rx_filter == HWTSTAMP_FILTER_ALL; } static inline void mlx5e_read_cqe_slot(struct mlx5e_cq *cq, u32 cqcc, @@ -627,6 +628,7 @@ static inline void mlx5e_handle_csum(struct net_device *netdev, if (lro) { skb->ip_summed = CHECKSUM_UNNECESSARY; + rq->stats.csum_unnecessary++; return; } @@ -644,7 +646,9 @@ static inline void mlx5e_handle_csum(struct net_device *netdev, skb->csum_level = 1; skb->encapsulation = 1; rq->stats.csum_unnecessary_inner++; + return; } + rq->stats.csum_unnecessary++; return; } csum_none: @@ -658,7 +662,6 @@ static inline void mlx5e_build_rx_skb(struct mlx5_cqe64 *cqe, struct sk_buff *skb) { struct net_device *netdev = rq->netdev; - struct mlx5e_tstamp *tstamp = rq->tstamp; int lro_num_seg; lro_num_seg = be32_to_cpu(cqe->srqn) >> 24; @@ -673,8 +676,9 @@ static inline void mlx5e_build_rx_skb(struct mlx5_cqe64 *cqe, rq->stats.lro_bytes += cqe_bcnt; } - if (unlikely(mlx5e_rx_hw_stamp(tstamp))) - mlx5e_fill_hwstamp(tstamp, get_cqe_ts(cqe), skb_hwtstamps(skb)); + if (unlikely(mlx5e_rx_hw_stamp(rq->tstamp))) + skb_hwtstamps(skb)->hwtstamp = + mlx5_timecounter_cyc2time(rq->clock, get_cqe_ts(cqe)); skb_record_rx_queue(skb, rq->ix); @@ -1159,12 +1163,25 @@ static inline void mlx5i_complete_rx_cqe(struct mlx5e_rq *rq, u32 cqe_bcnt, struct sk_buff *skb) { - struct net_device *netdev = rq->netdev; - struct mlx5e_tstamp *tstamp = rq->tstamp; + struct net_device *netdev; char *pseudo_header; + u32 qpn; u8 *dgid; u8 g; + qpn = be32_to_cpu(cqe->sop_drop_qpn) & 0xffffff; + netdev = mlx5i_pkey_get_netdev(rq->netdev, qpn); + + /* No mapping present, cannot process SKB. This might happen if a child + * interface is going down while having unprocessed CQEs on parent RQ + */ + if (unlikely(!netdev)) { + /* TODO: add drop counters support */ + skb->dev = NULL; + pr_warn_once("Unable to map QPN %u to dev - dropping skb\n", qpn); + return; + } + g = (be32_to_cpu(cqe->flags_rqpn) >> 28) & 3; dgid = skb->data + MLX5_IB_GRH_DGID_OFFSET; if ((!g) || dgid[0] != 0xff) @@ -1185,8 +1202,9 @@ static inline void mlx5i_complete_rx_cqe(struct mlx5e_rq *rq, skb->ip_summed = CHECKSUM_COMPLETE; skb->csum = csum_unfold((__force __sum16)cqe->check_sum); - if (unlikely(mlx5e_rx_hw_stamp(tstamp))) - mlx5e_fill_hwstamp(tstamp, get_cqe_ts(cqe), skb_hwtstamps(skb)); + if (unlikely(mlx5e_rx_hw_stamp(rq->tstamp))) + skb_hwtstamps(skb)->hwtstamp = + mlx5_timecounter_cyc2time(rq->clock, get_cqe_ts(cqe)); skb_record_rx_queue(skb, rq->ix); @@ -1226,6 +1244,10 @@ void mlx5i_handle_rx_cqe(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe) goto wq_free_wqe; mlx5i_complete_rx_cqe(rq, cqe, cqe_bcnt, skb); + if (unlikely(!skb->dev)) { + dev_kfree_skb_any(skb); + goto wq_free_wqe; + } napi_gro_receive(rq->cq.napi, skb); wq_free_wqe: diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h index 6d199ffb1c0b..f8637213afc0 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h @@ -68,6 +68,7 @@ struct mlx5e_sw_stats { u64 rx_xdp_drop; u64 rx_xdp_tx; u64 rx_xdp_tx_full; + u64 tx_csum_none; u64 tx_csum_partial; u64 tx_csum_partial_inner; u64 tx_queue_stopped; @@ -108,6 +109,7 @@ static const struct counter_desc sw_stats_desc[] = { { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xdp_drop) }, { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xdp_tx) }, { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xdp_tx_full) }, + { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_csum_none) }, { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_csum_partial) }, { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_csum_partial_inner) }, { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_queue_stopped) }, @@ -339,6 +341,7 @@ struct mlx5e_rq_stats { u64 packets; u64 bytes; u64 csum_complete; + u64 csum_unnecessary; u64 csum_unnecessary_inner; u64 csum_none; u64 lro_packets; @@ -363,6 +366,7 @@ static const struct counter_desc rq_stats_desc[] = { { MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, packets) }, { MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, bytes) }, { MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, csum_complete) }, + { MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, csum_unnecessary) }, { MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, csum_unnecessary_inner) }, { MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, csum_none) }, { MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, xdp_drop) }, @@ -392,6 +396,7 @@ struct mlx5e_sq_stats { u64 tso_bytes; u64 tso_inner_packets; u64 tso_inner_bytes; + u64 csum_partial; u64 csum_partial_inner; u64 nop; /* less likely accessed in data path */ @@ -408,6 +413,7 @@ static const struct counter_desc sq_stats_desc[] = { { MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, tso_bytes) }, { MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, tso_inner_packets) }, { MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, tso_inner_bytes) }, + { MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, csum_partial) }, { MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, csum_partial_inner) }, { MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, nop) }, { MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, csum_none) }, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index da503e6411da..1aa2028ed995 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -1317,6 +1317,69 @@ static bool csum_offload_supported(struct mlx5e_priv *priv, u32 action, u32 upda return true; } +static bool modify_header_match_supported(struct mlx5_flow_spec *spec, + struct tcf_exts *exts) +{ + const struct tc_action *a; + bool modify_ip_header; + LIST_HEAD(actions); + u8 htype, ip_proto; + void *headers_v; + u16 ethertype; + int nkeys, i; + + headers_v = MLX5_ADDR_OF(fte_match_param, spec->match_value, outer_headers); + ethertype = MLX5_GET(fte_match_set_lyr_2_4, headers_v, ethertype); + + /* for non-IP we only re-write MACs, so we're okay */ + if (ethertype != ETH_P_IP && ethertype != ETH_P_IPV6) + goto out_ok; + + modify_ip_header = false; + tcf_exts_to_list(exts, &actions); + list_for_each_entry(a, &actions, list) { + if (!is_tcf_pedit(a)) + continue; + + nkeys = tcf_pedit_nkeys(a); + for (i = 0; i < nkeys; i++) { + htype = tcf_pedit_htype(a, i); + if (htype == TCA_PEDIT_KEY_EX_HDR_TYPE_IP4 || + htype == TCA_PEDIT_KEY_EX_HDR_TYPE_IP6) { + modify_ip_header = true; + break; + } + } + } + + ip_proto = MLX5_GET(fte_match_set_lyr_2_4, headers_v, ip_protocol); + if (modify_ip_header && ip_proto != IPPROTO_TCP && ip_proto != IPPROTO_UDP) { + pr_info("can't offload re-write of ip proto %d\n", ip_proto); + return false; + } + +out_ok: + return true; +} + +static bool actions_match_supported(struct mlx5e_priv *priv, + struct tcf_exts *exts, + struct mlx5e_tc_flow_parse_attr *parse_attr, + struct mlx5e_tc_flow *flow) +{ + u32 actions; + + if (flow->flags & MLX5E_TC_FLOW_ESWITCH) + actions = flow->esw_attr->action; + else + actions = flow->nic_attr->action; + + if (actions & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR) + return modify_header_match_supported(&parse_attr->spec, exts); + + return true; +} + static int parse_tc_nic_actions(struct mlx5e_priv *priv, struct tcf_exts *exts, struct mlx5e_tc_flow_parse_attr *parse_attr, struct mlx5e_tc_flow *flow) @@ -1378,6 +1441,9 @@ static int parse_tc_nic_actions(struct mlx5e_priv *priv, struct tcf_exts *exts, return -EINVAL; } + if (!actions_match_supported(priv, exts, parse_attr, flow)) + return -EOPNOTSUPP; + return 0; } @@ -1564,7 +1630,7 @@ static int mlx5e_create_encap_header_ipv4(struct mlx5e_priv *priv, break; default: err = -EOPNOTSUPP; - goto out; + goto free_encap; } fl4.flowi4_tos = tun_key->tos; fl4.daddr = tun_key->u.ipv4.dst; @@ -1573,7 +1639,7 @@ static int mlx5e_create_encap_header_ipv4(struct mlx5e_priv *priv, err = mlx5e_route_lookup_ipv4(priv, mirred_dev, &out_dev, &fl4, &n, &ttl); if (err) - goto out; + goto free_encap; /* used by mlx5e_detach_encap to lookup a neigh hash table * entry in the neigh hash table when a user deletes a rule @@ -1590,7 +1656,7 @@ static int mlx5e_create_encap_header_ipv4(struct mlx5e_priv *priv, */ err = mlx5e_rep_encap_entry_attach(netdev_priv(out_dev), e); if (err) - goto out; + goto free_encap; read_lock_bh(&n->lock); nud_state = n->nud_state; @@ -1630,8 +1696,9 @@ static int mlx5e_create_encap_header_ipv4(struct mlx5e_priv *priv, destroy_neigh_entry: mlx5e_rep_encap_entry_detach(netdev_priv(e->out_dev), e); -out: +free_encap: kfree(encap_header); +out: if (n) neigh_release(n); return err; @@ -1668,7 +1735,7 @@ static int mlx5e_create_encap_header_ipv6(struct mlx5e_priv *priv, break; default: err = -EOPNOTSUPP; - goto out; + goto free_encap; } fl6.flowlabel = ip6_make_flowinfo(RT_TOS(tun_key->tos), tun_key->label); @@ -1678,7 +1745,7 @@ static int mlx5e_create_encap_header_ipv6(struct mlx5e_priv *priv, err = mlx5e_route_lookup_ipv6(priv, mirred_dev, &out_dev, &fl6, &n, &ttl); if (err) - goto out; + goto free_encap; /* used by mlx5e_detach_encap to lookup a neigh hash table * entry in the neigh hash table when a user deletes a rule @@ -1695,7 +1762,7 @@ static int mlx5e_create_encap_header_ipv6(struct mlx5e_priv *priv, */ err = mlx5e_rep_encap_entry_attach(netdev_priv(out_dev), e); if (err) - goto out; + goto free_encap; read_lock_bh(&n->lock); nud_state = n->nud_state; @@ -1736,8 +1803,9 @@ static int mlx5e_create_encap_header_ipv6(struct mlx5e_priv *priv, destroy_neigh_entry: mlx5e_rep_encap_entry_detach(netdev_priv(e->out_dev), e); -out: +free_encap: kfree(encap_header); +out: if (n) neigh_release(n); return err; @@ -1791,6 +1859,7 @@ vxlan_encap_offload_err: } } + /* must verify if encap is valid or not */ if (found) goto attach_flow; @@ -1817,6 +1886,8 @@ attach_flow: *encap_dev = e->out_dev; if (e->flags & MLX5_ENCAP_ENTRY_VALID) attr->encap_id = e->encap_id; + else + err = -EAGAIN; return err; @@ -1934,6 +2005,10 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv, struct tcf_exts *exts, return -EINVAL; } + + if (!actions_match_supported(priv, exts, parse_attr, flow)) + return -EOPNOTSUPP; + return err; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c index fee43e40fa16..a7c208a1ad83 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c @@ -35,6 +35,7 @@ #include "en.h" #include "ipoib/ipoib.h" #include "en_accel/ipsec_rxtx.h" +#include "lib/clock.h" #define MLX5E_SQ_NOPS_ROOM MLX5_SEND_WQE_MAX_WQEBBS #define MLX5E_SQ_STOP_ROOM (MLX5_SEND_WQE_MAX_WQEBBS +\ @@ -193,6 +194,7 @@ mlx5e_txwqe_build_eseg_csum(struct mlx5e_txqsq *sq, struct sk_buff *skb, struct sq->stats.csum_partial_inner++; } else { eseg->cs_flags |= MLX5_ETH_WQE_L4_CSUM; + sq->stats.csum_partial++; } } else sq->stats.csum_none++; @@ -451,8 +453,9 @@ bool mlx5e_poll_tx_cq(struct mlx5e_cq *cq, int napi_budget) SKBTX_HW_TSTAMP)) { struct skb_shared_hwtstamps hwts = {}; - mlx5e_fill_hwstamp(sq->tstamp, - get_cqe_ts(cqe), &hwts); + hwts.hwtstamp = + mlx5_timecounter_cyc2time(sq->clock, + get_cqe_ts(cqe)); skb_tstamp_tx(skb, &hwts); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eq.c b/drivers/net/ethernet/mellanox/mlx5/core/eq.c index fc606bfd1d6e..60771865c99c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eq.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eq.c @@ -491,8 +491,7 @@ static irqreturn_t mlx5_eq_int(int irq, void *eq_ptr) break; case MLX5_EVENT_TYPE_PPS_EVENT: - if (dev->event) - dev->event(dev, MLX5_DEV_EVENT_PPS, (unsigned long)eqe); + mlx5_pps_event(dev, eqe); break; case MLX5_EVENT_TYPE_FPGA_ERROR: diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fpga/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/fpga/cmd.c index e37453d838db..c0fd2212e890 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fpga/cmd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fpga/cmd.c @@ -71,11 +71,11 @@ int mlx5_fpga_access_reg(struct mlx5_core_dev *dev, u8 size, u64 addr, return 0; } -int mlx5_fpga_caps(struct mlx5_core_dev *dev, u32 *caps) +int mlx5_fpga_caps(struct mlx5_core_dev *dev) { u32 in[MLX5_ST_SZ_DW(fpga_cap)] = {0}; - return mlx5_core_access_reg(dev, in, sizeof(in), caps, + return mlx5_core_access_reg(dev, in, sizeof(in), dev->caps.fpga, MLX5_ST_SZ_BYTES(fpga_cap), MLX5_REG_FPGA_CAP, 0, 0); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fpga/cmd.h b/drivers/net/ethernet/mellanox/mlx5/core/fpga/cmd.h index 94bdfd47c3f0..d05233c9b4f6 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fpga/cmd.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/fpga/cmd.h @@ -65,7 +65,7 @@ struct mlx5_fpga_qp_counters { u64 rx_total_drop; }; -int mlx5_fpga_caps(struct mlx5_core_dev *dev, u32 *caps); +int mlx5_fpga_caps(struct mlx5_core_dev *dev); int mlx5_fpga_query(struct mlx5_core_dev *dev, struct mlx5_fpga_query *query); int mlx5_fpga_ctrl_op(struct mlx5_core_dev *dev, u8 op); int mlx5_fpga_access_reg(struct mlx5_core_dev *dev, u8 size, u64 addr, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fpga/core.c b/drivers/net/ethernet/mellanox/mlx5/core/fpga/core.c index 9034e9960a76..dc8970346521 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fpga/core.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fpga/core.c @@ -139,8 +139,7 @@ int mlx5_fpga_device_start(struct mlx5_core_dev *mdev) if (err) goto out; - err = mlx5_fpga_caps(fdev->mdev, - fdev->mdev->caps.hca_cur[MLX5_CAP_FPGA]); + err = mlx5_fpga_caps(fdev->mdev); if (err) goto out; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c index e0d0efd903bc..881e2e55840c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c @@ -40,7 +40,8 @@ #include "eswitch.h" int mlx5_cmd_update_root_ft(struct mlx5_core_dev *dev, - struct mlx5_flow_table *ft, u32 underlay_qpn) + struct mlx5_flow_table *ft, u32 underlay_qpn, + bool disconnect) { u32 in[MLX5_ST_SZ_DW(set_flow_table_root_in)] = {0}; u32 out[MLX5_ST_SZ_DW(set_flow_table_root_out)] = {0}; @@ -52,7 +53,15 @@ int mlx5_cmd_update_root_ft(struct mlx5_core_dev *dev, MLX5_SET(set_flow_table_root_in, in, opcode, MLX5_CMD_OP_SET_FLOW_TABLE_ROOT); MLX5_SET(set_flow_table_root_in, in, table_type, ft->type); - MLX5_SET(set_flow_table_root_in, in, table_id, ft->id); + + if (disconnect) { + MLX5_SET(set_flow_table_root_in, in, op_mod, 1); + MLX5_SET(set_flow_table_root_in, in, table_id, 0); + } else { + MLX5_SET(set_flow_table_root_in, in, op_mod, 0); + MLX5_SET(set_flow_table_root_in, in, table_id, ft->id); + } + MLX5_SET(set_flow_table_root_in, in, underlay_qpn, underlay_qpn); if (ft->vport) { MLX5_SET(set_flow_table_root_in, in, vport_number, ft->vport); @@ -293,6 +302,9 @@ static int mlx5_cmd_set_fte(struct mlx5_core_dev *dev, } if (fte->action & MLX5_FLOW_CONTEXT_ACTION_COUNT) { + int max_list_size = BIT(MLX5_CAP_FLOWTABLE_TYPE(dev, + log_max_flow_counter, + ft->type)); int list_size = 0; list_for_each_entry(dst, &fte->node.children, node.list) { @@ -305,12 +317,17 @@ static int mlx5_cmd_set_fte(struct mlx5_core_dev *dev, in_dests += MLX5_ST_SZ_BYTES(dest_format_struct); list_size++; } + if (list_size > max_list_size) { + err = -EINVAL; + goto err_out; + } MLX5_SET(flow_context, in_flow_context, flow_counter_list_size, list_size); } err = mlx5_cmd_exec(dev, in, inlen, out, sizeof(out)); +err_out: kvfree(in); return err; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.h b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.h index c6d7bdf255b6..71e2d0f37ad9 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.h @@ -71,8 +71,8 @@ int mlx5_cmd_delete_fte(struct mlx5_core_dev *dev, unsigned int index); int mlx5_cmd_update_root_ft(struct mlx5_core_dev *dev, - struct mlx5_flow_table *ft, - u32 underlay_qpn); + struct mlx5_flow_table *ft, u32 underlay_qpn, + bool disconnect); int mlx5_cmd_fc_alloc(struct mlx5_core_dev *dev, u32 *id); int mlx5_cmd_fc_free(struct mlx5_core_dev *dev, u32 id); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c index 5a7bea688ec8..f77e496f7053 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c @@ -145,10 +145,10 @@ static struct init_tree_node { } }; -enum fs_i_mutex_lock_class { - FS_MUTEX_GRANDPARENT, - FS_MUTEX_PARENT, - FS_MUTEX_CHILD +enum fs_i_lock_class { + FS_LOCK_GRANDPARENT, + FS_LOCK_PARENT, + FS_LOCK_CHILD }; static const struct rhashtable_params rhash_fte = { @@ -168,10 +168,16 @@ static const struct rhashtable_params rhash_fg = { }; -static void del_rule(struct fs_node *node); -static void del_flow_table(struct fs_node *node); -static void del_flow_group(struct fs_node *node); -static void del_fte(struct fs_node *node); +static void del_hw_flow_table(struct fs_node *node); +static void del_hw_flow_group(struct fs_node *node); +static void del_hw_fte(struct fs_node *node); +static void del_sw_flow_table(struct fs_node *node); +static void del_sw_flow_group(struct fs_node *node); +static void del_sw_fte(struct fs_node *node); +/* Delete rule (destination) is special case that + * requires to lock the FTE for all the deletion process. + */ +static void del_sw_hw_rule(struct fs_node *node); static bool mlx5_flow_dests_cmp(struct mlx5_flow_destination *d1, struct mlx5_flow_destination *d2); static struct mlx5_flow_rule * @@ -179,14 +185,16 @@ find_flow_rule(struct fs_fte *fte, struct mlx5_flow_destination *dest); static void tree_init_node(struct fs_node *node, - unsigned int refcount, - void (*remove_func)(struct fs_node *)) + void (*del_hw_func)(struct fs_node *), + void (*del_sw_func)(struct fs_node *)) { - atomic_set(&node->refcount, refcount); + atomic_set(&node->refcount, 1); INIT_LIST_HEAD(&node->list); INIT_LIST_HEAD(&node->children); - mutex_init(&node->lock); - node->remove_func = remove_func; + init_rwsem(&node->lock); + node->del_hw_func = del_hw_func; + node->del_sw_func = del_sw_func; + node->active = false; } static void tree_add_node(struct fs_node *node, struct fs_node *parent) @@ -202,50 +210,70 @@ static void tree_add_node(struct fs_node *node, struct fs_node *parent) node->root = parent->root; } -static void tree_get_node(struct fs_node *node) +static int tree_get_node(struct fs_node *node) { - atomic_inc(&node->refcount); + return atomic_add_unless(&node->refcount, 1, 0); } -static void nested_lock_ref_node(struct fs_node *node, - enum fs_i_mutex_lock_class class) +static void nested_down_read_ref_node(struct fs_node *node, + enum fs_i_lock_class class) { if (node) { - mutex_lock_nested(&node->lock, class); + down_read_nested(&node->lock, class); atomic_inc(&node->refcount); } } -static void lock_ref_node(struct fs_node *node) +static void nested_down_write_ref_node(struct fs_node *node, + enum fs_i_lock_class class) { if (node) { - mutex_lock(&node->lock); + down_write_nested(&node->lock, class); atomic_inc(&node->refcount); } } -static void unlock_ref_node(struct fs_node *node) +static void down_write_ref_node(struct fs_node *node) { if (node) { - atomic_dec(&node->refcount); - mutex_unlock(&node->lock); + down_write(&node->lock); + atomic_inc(&node->refcount); } } +static void up_read_ref_node(struct fs_node *node) +{ + atomic_dec(&node->refcount); + up_read(&node->lock); +} + +static void up_write_ref_node(struct fs_node *node) +{ + atomic_dec(&node->refcount); + up_write(&node->lock); +} + static void tree_put_node(struct fs_node *node) { struct fs_node *parent_node = node->parent; - lock_ref_node(parent_node); if (atomic_dec_and_test(&node->refcount)) { - if (parent_node) + if (node->del_hw_func) + node->del_hw_func(node); + if (parent_node) { + /* Only root namespace doesn't have parent and we just + * need to free its node. + */ + down_write_ref_node(parent_node); list_del_init(&node->list); - if (node->remove_func) - node->remove_func(node); - kfree(node); + if (node->del_sw_func) + node->del_sw_func(node); + up_write_ref_node(parent_node); + } else { + kfree(node); + } node = NULL; } - unlock_ref_node(parent_node); if (!node && parent_node) tree_put_node(parent_node); } @@ -362,6 +390,15 @@ static struct mlx5_flow_root_namespace *find_root(struct fs_node *node) return container_of(ns, struct mlx5_flow_root_namespace, ns); } +static inline struct mlx5_flow_steering *get_steering(struct fs_node *node) +{ + struct mlx5_flow_root_namespace *root = find_root(node); + + if (root) + return root->dev->priv.steering; + return NULL; +} + static inline struct mlx5_core_dev *get_dev(struct fs_node *node) { struct mlx5_flow_root_namespace *root = find_root(node); @@ -371,26 +408,36 @@ static inline struct mlx5_core_dev *get_dev(struct fs_node *node) return NULL; } -static void del_flow_table(struct fs_node *node) +static void del_hw_flow_table(struct fs_node *node) { struct mlx5_flow_table *ft; struct mlx5_core_dev *dev; - struct fs_prio *prio; int err; fs_get_obj(ft, node); dev = get_dev(&ft->node); - err = mlx5_cmd_destroy_flow_table(dev, ft); - if (err) - mlx5_core_warn(dev, "flow steering can't destroy ft\n"); - ida_destroy(&ft->fte_allocator); + if (node->active) { + err = mlx5_cmd_destroy_flow_table(dev, ft); + if (err) + mlx5_core_warn(dev, "flow steering can't destroy ft\n"); + } +} + +static void del_sw_flow_table(struct fs_node *node) +{ + struct mlx5_flow_table *ft; + struct fs_prio *prio; + + fs_get_obj(ft, node); + rhltable_destroy(&ft->fgs_hash); fs_get_obj(prio, ft->node.parent); prio->num_ft--; + kfree(ft); } -static void del_rule(struct fs_node *node) +static void del_sw_hw_rule(struct fs_node *node) { struct mlx5_flow_rule *rule; struct mlx5_flow_table *ft; @@ -406,7 +453,6 @@ static void del_rule(struct fs_node *node) fs_get_obj(fg, fte->node.parent); fs_get_obj(ft, fg->node.parent); trace_mlx5_fs_del_rule(rule); - list_del(&rule->node.list); if (rule->sw_action == MLX5_FLOW_CONTEXT_ACTION_FWD_NEXT_PRIO) { mutex_lock(&rule->dest_attr.ft->lock); list_del(&rule->next_ft); @@ -434,117 +480,203 @@ out: "%s can't del rule fg id=%d fte_index=%d\n", __func__, fg->id, fte->index); } + kfree(rule); } -static void destroy_fte(struct fs_fte *fte, struct mlx5_flow_group *fg) +static void del_hw_fte(struct fs_node *node) { struct mlx5_flow_table *ft; - int ret; + struct mlx5_flow_group *fg; + struct mlx5_core_dev *dev; + struct fs_fte *fte; + int err; - ret = rhashtable_remove_fast(&fg->ftes_hash, &fte->hash, rhash_fte); - WARN_ON(ret); - fte->status = 0; + fs_get_obj(fte, node); + fs_get_obj(fg, fte->node.parent); fs_get_obj(ft, fg->node.parent); - ida_simple_remove(&ft->fte_allocator, fte->index); + + trace_mlx5_fs_del_fte(fte); + dev = get_dev(&ft->node); + if (node->active) { + err = mlx5_cmd_delete_fte(dev, ft, + fte->index); + if (err) + mlx5_core_warn(dev, + "flow steering can't delete fte in index %d of flow group id %d\n", + fte->index, fg->id); + } } -static void del_fte(struct fs_node *node) +static void del_sw_fte(struct fs_node *node) { - struct mlx5_flow_table *ft; + struct mlx5_flow_steering *steering = get_steering(node); struct mlx5_flow_group *fg; - struct mlx5_core_dev *dev; struct fs_fte *fte; int err; fs_get_obj(fte, node); fs_get_obj(fg, fte->node.parent); - fs_get_obj(ft, fg->node.parent); - trace_mlx5_fs_del_fte(fte); - - dev = get_dev(&ft->node); - err = mlx5_cmd_delete_fte(dev, ft, - fte->index); - if (err) - mlx5_core_warn(dev, - "flow steering can't delete fte in index %d of flow group id %d\n", - fte->index, fg->id); - destroy_fte(fte, fg); + err = rhashtable_remove_fast(&fg->ftes_hash, + &fte->hash, + rhash_fte); + WARN_ON(err); + ida_simple_remove(&fg->fte_allocator, fte->index - fg->start_index); + kmem_cache_free(steering->ftes_cache, fte); } -static void del_flow_group(struct fs_node *node) +static void del_hw_flow_group(struct fs_node *node) { struct mlx5_flow_group *fg; struct mlx5_flow_table *ft; struct mlx5_core_dev *dev; - int err; fs_get_obj(fg, node); fs_get_obj(ft, fg->node.parent); dev = get_dev(&ft->node); trace_mlx5_fs_del_fg(fg); - if (ft->autogroup.active) - ft->autogroup.num_groups--; + if (fg->node.active && mlx5_cmd_destroy_flow_group(dev, ft, fg->id)) + mlx5_core_warn(dev, "flow steering can't destroy fg %d of ft %d\n", + fg->id, ft->id); +} + +static void del_sw_flow_group(struct fs_node *node) +{ + struct mlx5_flow_steering *steering = get_steering(node); + struct mlx5_flow_group *fg; + struct mlx5_flow_table *ft; + int err; + + fs_get_obj(fg, node); + fs_get_obj(ft, fg->node.parent); rhashtable_destroy(&fg->ftes_hash); + ida_destroy(&fg->fte_allocator); + if (ft->autogroup.active) + ft->autogroup.num_groups--; err = rhltable_remove(&ft->fgs_hash, &fg->hash, rhash_fg); WARN_ON(err); - if (mlx5_cmd_destroy_flow_group(dev, ft, fg->id)) - mlx5_core_warn(dev, "flow steering can't destroy fg %d of ft %d\n", - fg->id, ft->id); + kmem_cache_free(steering->fgs_cache, fg); } -static struct fs_fte *alloc_fte(struct mlx5_flow_act *flow_act, +static int insert_fte(struct mlx5_flow_group *fg, struct fs_fte *fte) +{ + int index; + int ret; + + index = ida_simple_get(&fg->fte_allocator, 0, fg->max_ftes, GFP_KERNEL); + if (index < 0) + return index; + + fte->index = index + fg->start_index; + ret = rhashtable_insert_fast(&fg->ftes_hash, + &fte->hash, + rhash_fte); + if (ret) + goto err_ida_remove; + + tree_add_node(&fte->node, &fg->node); + list_add_tail(&fte->node.list, &fg->node.children); + return 0; + +err_ida_remove: + ida_simple_remove(&fg->fte_allocator, index); + return ret; +} + +static struct fs_fte *alloc_fte(struct mlx5_flow_table *ft, u32 *match_value, - unsigned int index) + struct mlx5_flow_act *flow_act) { + struct mlx5_flow_steering *steering = get_steering(&ft->node); struct fs_fte *fte; - fte = kzalloc(sizeof(*fte), GFP_KERNEL); + fte = kmem_cache_zalloc(steering->ftes_cache, GFP_KERNEL); if (!fte) return ERR_PTR(-ENOMEM); memcpy(fte->val, match_value, sizeof(fte->val)); fte->node.type = FS_TYPE_FLOW_ENTRY; fte->flow_tag = flow_act->flow_tag; - fte->index = index; fte->action = flow_act->action; fte->encap_id = flow_act->encap_id; fte->modify_id = flow_act->modify_id; + tree_init_node(&fte->node, del_hw_fte, del_sw_fte); + return fte; } -static struct mlx5_flow_group *alloc_flow_group(u32 *create_fg_in) +static void dealloc_flow_group(struct mlx5_flow_steering *steering, + struct mlx5_flow_group *fg) +{ + rhashtable_destroy(&fg->ftes_hash); + kmem_cache_free(steering->fgs_cache, fg); +} + +static struct mlx5_flow_group *alloc_flow_group(struct mlx5_flow_steering *steering, + u8 match_criteria_enable, + void *match_criteria, + int start_index, + int end_index) { struct mlx5_flow_group *fg; - void *match_criteria = MLX5_ADDR_OF(create_flow_group_in, - create_fg_in, match_criteria); - u8 match_criteria_enable = MLX5_GET(create_flow_group_in, - create_fg_in, - match_criteria_enable); int ret; - fg = kzalloc(sizeof(*fg), GFP_KERNEL); + fg = kmem_cache_zalloc(steering->fgs_cache, GFP_KERNEL); if (!fg) return ERR_PTR(-ENOMEM); ret = rhashtable_init(&fg->ftes_hash, &rhash_fte); if (ret) { - kfree(fg); + kmem_cache_free(steering->fgs_cache, fg); return ERR_PTR(ret); - } +} + ida_init(&fg->fte_allocator); fg->mask.match_criteria_enable = match_criteria_enable; memcpy(&fg->mask.match_criteria, match_criteria, sizeof(fg->mask.match_criteria)); fg->node.type = FS_TYPE_FLOW_GROUP; - fg->start_index = MLX5_GET(create_flow_group_in, create_fg_in, - start_flow_index); - fg->max_ftes = MLX5_GET(create_flow_group_in, create_fg_in, - end_flow_index) - fg->start_index + 1; + fg->start_index = start_index; + fg->max_ftes = end_index - start_index + 1; + + return fg; +} + +static struct mlx5_flow_group *alloc_insert_flow_group(struct mlx5_flow_table *ft, + u8 match_criteria_enable, + void *match_criteria, + int start_index, + int end_index, + struct list_head *prev) +{ + struct mlx5_flow_steering *steering = get_steering(&ft->node); + struct mlx5_flow_group *fg; + int ret; + + fg = alloc_flow_group(steering, match_criteria_enable, match_criteria, + start_index, end_index); + if (IS_ERR(fg)) + return fg; + + /* initialize refcnt, add to parent list */ + ret = rhltable_insert(&ft->fgs_hash, + &fg->hash, + rhash_fg); + if (ret) { + dealloc_flow_group(steering, fg); + return ERR_PTR(ret); + } + + tree_init_node(&fg->node, del_hw_flow_group, del_sw_flow_group); + tree_add_node(&fg->node, &ft->node); + /* Add node to group list */ + list_add(&fg->node.list, prev); + atomic_inc(&ft->node.version); + return fg; } @@ -575,7 +707,6 @@ static struct mlx5_flow_table *alloc_flow_table(int level, u16 vport, int max_ft ft->flags = flags; INIT_LIST_HEAD(&ft->fwd_rules); mutex_init(&ft->lock); - ida_init(&ft->fte_allocator); return ft; } @@ -693,8 +824,10 @@ static int update_root_ft_create(struct mlx5_flow_table *ft, struct fs_prio *prio) { struct mlx5_flow_root_namespace *root = find_root(&prio->node); + struct mlx5_ft_underlay_qp *uqp; int min_level = INT_MAX; int err; + u32 qpn; if (root->root_ft) min_level = root->root_ft->level; @@ -702,10 +835,24 @@ static int update_root_ft_create(struct mlx5_flow_table *ft, struct fs_prio if (ft->level >= min_level) return 0; - err = mlx5_cmd_update_root_ft(root->dev, ft, root->underlay_qpn); + if (list_empty(&root->underlay_qpns)) { + /* Don't set any QPN (zero) in case QPN list is empty */ + qpn = 0; + err = mlx5_cmd_update_root_ft(root->dev, ft, qpn, false); + } else { + list_for_each_entry(uqp, &root->underlay_qpns, list) { + qpn = uqp->qpn; + err = mlx5_cmd_update_root_ft(root->dev, ft, qpn, + false); + if (err) + break; + } + } + if (err) - mlx5_core_warn(root->dev, "Update root flow table of id=%u failed\n", - ft->id); + mlx5_core_warn(root->dev, + "Update root flow table of id(%u) qpn(%d) failed\n", + ft->id, qpn); else root->root_ft = ft; @@ -724,7 +871,7 @@ static int _mlx5_modify_rule_destination(struct mlx5_flow_rule *rule, fs_get_obj(fte, rule->node.parent); if (!(fte->action & MLX5_FLOW_CONTEXT_ACTION_FWD_DEST)) return -EINVAL; - lock_ref_node(&fte->node); + down_write_ref_node(&fte->node); fs_get_obj(fg, fte->node.parent); fs_get_obj(ft, fg->node.parent); @@ -733,7 +880,7 @@ static int _mlx5_modify_rule_destination(struct mlx5_flow_rule *rule, ft, fg->id, modify_mask, fte); - unlock_ref_node(&fte->node); + up_write_ref_node(&fte->node); return err; } @@ -870,7 +1017,7 @@ static struct mlx5_flow_table *__mlx5_create_flow_table(struct mlx5_flow_namespa goto unlock_root; } - tree_init_node(&ft->node, 1, del_flow_table); + tree_init_node(&ft->node, del_hw_flow_table, del_sw_flow_table); log_table_sz = ft->max_fte ? ilog2(ft->max_fte) : 0; next_ft = find_next_chained_ft(fs_prio); err = mlx5_cmd_create_flow_table(root->dev, ft->vport, ft->op_mod, ft->type, @@ -882,17 +1029,17 @@ static struct mlx5_flow_table *__mlx5_create_flow_table(struct mlx5_flow_namespa err = connect_flow_table(root->dev, ft, fs_prio); if (err) goto destroy_ft; - lock_ref_node(&fs_prio->node); + ft->node.active = true; + down_write_ref_node(&fs_prio->node); tree_add_node(&ft->node, &fs_prio->node); list_add_flow_table(ft, fs_prio); fs_prio->num_ft++; - unlock_ref_node(&fs_prio->node); + up_write_ref_node(&fs_prio->node); mutex_unlock(&root->chain_lock); return ft; destroy_ft: mlx5_cmd_destroy_flow_table(root->dev, ft); free_ft: - ida_destroy(&ft->fte_allocator); kfree(ft); unlock_root: mutex_unlock(&root->chain_lock); @@ -960,54 +1107,6 @@ mlx5_create_auto_grouped_flow_table(struct mlx5_flow_namespace *ns, } EXPORT_SYMBOL(mlx5_create_auto_grouped_flow_table); -/* Flow table should be locked */ -static struct mlx5_flow_group *create_flow_group_common(struct mlx5_flow_table *ft, - u32 *fg_in, - struct list_head - *prev_fg, - bool is_auto_fg) -{ - struct mlx5_flow_group *fg; - struct mlx5_core_dev *dev = get_dev(&ft->node); - int err; - - if (!dev) - return ERR_PTR(-ENODEV); - - fg = alloc_flow_group(fg_in); - if (IS_ERR(fg)) - return fg; - - err = rhltable_insert(&ft->fgs_hash, &fg->hash, rhash_fg); - if (err) - goto err_free_fg; - - err = mlx5_cmd_create_flow_group(dev, ft, fg_in, &fg->id); - if (err) - goto err_remove_fg; - - if (ft->autogroup.active) - ft->autogroup.num_groups++; - /* Add node to tree */ - tree_init_node(&fg->node, !is_auto_fg, del_flow_group); - tree_add_node(&fg->node, &ft->node); - /* Add node to group list */ - list_add(&fg->node.list, prev_fg); - - trace_mlx5_fs_add_fg(fg); - return fg; - -err_remove_fg: - WARN_ON(rhltable_remove(&ft->fgs_hash, - &fg->hash, - rhash_fg)); -err_free_fg: - rhashtable_destroy(&fg->ftes_hash); - kfree(fg); - - return ERR_PTR(err); -} - struct mlx5_flow_group *mlx5_create_flow_group(struct mlx5_flow_table *ft, u32 *fg_in) { @@ -1016,7 +1115,13 @@ struct mlx5_flow_group *mlx5_create_flow_group(struct mlx5_flow_table *ft, u8 match_criteria_enable = MLX5_GET(create_flow_group_in, fg_in, match_criteria_enable); + int start_index = MLX5_GET(create_flow_group_in, fg_in, + start_flow_index); + int end_index = MLX5_GET(create_flow_group_in, fg_in, + end_flow_index); + struct mlx5_core_dev *dev = get_dev(&ft->node); struct mlx5_flow_group *fg; + int err; if (!check_valid_mask(match_criteria_enable, match_criteria)) return ERR_PTR(-EINVAL); @@ -1024,9 +1129,21 @@ struct mlx5_flow_group *mlx5_create_flow_group(struct mlx5_flow_table *ft, if (ft->autogroup.active) return ERR_PTR(-EPERM); - lock_ref_node(&ft->node); - fg = create_flow_group_common(ft, fg_in, ft->node.children.prev, false); - unlock_ref_node(&ft->node); + down_write_ref_node(&ft->node); + fg = alloc_insert_flow_group(ft, match_criteria_enable, match_criteria, + start_index, end_index, + ft->node.children.prev); + up_write_ref_node(&ft->node); + if (IS_ERR(fg)) + return fg; + + err = mlx5_cmd_create_flow_group(dev, ft, fg_in, &fg->id); + if (err) { + tree_put_node(&fg->node); + return ERR_PTR(err); + } + trace_mlx5_fs_add_fg(fg); + fg->node.active = true; return fg; } @@ -1111,7 +1228,7 @@ create_flow_handle(struct fs_fte *fte, /* Add dest to dests list- we need flow tables to be in the * end of the list for forward to next prio rules. */ - tree_init_node(&rule->node, 1, del_rule); + tree_init_node(&rule->node, NULL, del_sw_hw_rule); if (dest && dest[i].type != MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE) list_add(&rule->node.list, &fte->node.children); @@ -1167,7 +1284,9 @@ add_rule_fte(struct fs_fte *fte, if (err) goto free_handle; + fte->node.active = true; fte->status |= FS_FTE_STATUS_EXISTING; + atomic_inc(&fte->node.version); out: return handle; @@ -1177,59 +1296,17 @@ free_handle: return ERR_PTR(err); } -static struct fs_fte *create_fte(struct mlx5_flow_group *fg, - u32 *match_value, - struct mlx5_flow_act *flow_act) -{ - struct mlx5_flow_table *ft; - struct fs_fte *fte; - int index; - int ret; - - fs_get_obj(ft, fg->node.parent); - index = ida_simple_get(&ft->fte_allocator, fg->start_index, - fg->start_index + fg->max_ftes, - GFP_KERNEL); - if (index < 0) - return ERR_PTR(index); - - fte = alloc_fte(flow_act, match_value, index); - if (IS_ERR(fte)) { - ret = PTR_ERR(fte); - goto err_alloc; - } - ret = rhashtable_insert_fast(&fg->ftes_hash, &fte->hash, rhash_fte); - if (ret) - goto err_hash; - - return fte; - -err_hash: - kfree(fte); -err_alloc: - ida_simple_remove(&ft->fte_allocator, index); - return ERR_PTR(ret); -} - -static struct mlx5_flow_group *create_autogroup(struct mlx5_flow_table *ft, - u8 match_criteria_enable, - u32 *match_criteria) +static struct mlx5_flow_group *alloc_auto_flow_group(struct mlx5_flow_table *ft, + struct mlx5_flow_spec *spec) { - int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in); struct list_head *prev = &ft->node.children; - unsigned int candidate_index = 0; struct mlx5_flow_group *fg; - void *match_criteria_addr; + unsigned int candidate_index = 0; unsigned int group_size = 0; - u32 *in; if (!ft->autogroup.active) return ERR_PTR(-ENOENT); - in = kvzalloc(inlen, GFP_KERNEL); - if (!in) - return ERR_PTR(-ENOMEM); - if (ft->autogroup.num_groups < ft->autogroup.required_groups) /* We save place for flow groups in addition to max types */ group_size = ft->max_fte / (ft->autogroup.required_groups + 1); @@ -1247,25 +1324,55 @@ static struct mlx5_flow_group *create_autogroup(struct mlx5_flow_table *ft, prev = &fg->node.list; } - if (candidate_index + group_size > ft->max_fte) { - fg = ERR_PTR(-ENOSPC); + if (candidate_index + group_size > ft->max_fte) + return ERR_PTR(-ENOSPC); + + fg = alloc_insert_flow_group(ft, + spec->match_criteria_enable, + spec->match_criteria, + candidate_index, + candidate_index + group_size - 1, + prev); + if (IS_ERR(fg)) goto out; - } + + ft->autogroup.num_groups++; + +out: + return fg; +} + +static int create_auto_flow_group(struct mlx5_flow_table *ft, + struct mlx5_flow_group *fg) +{ + struct mlx5_core_dev *dev = get_dev(&ft->node); + int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in); + void *match_criteria_addr; + int err; + u32 *in; + + in = kvzalloc(inlen, GFP_KERNEL); + if (!in) + return -ENOMEM; MLX5_SET(create_flow_group_in, in, match_criteria_enable, - match_criteria_enable); - MLX5_SET(create_flow_group_in, in, start_flow_index, candidate_index); - MLX5_SET(create_flow_group_in, in, end_flow_index, candidate_index + - group_size - 1); + fg->mask.match_criteria_enable); + MLX5_SET(create_flow_group_in, in, start_flow_index, fg->start_index); + MLX5_SET(create_flow_group_in, in, end_flow_index, fg->start_index + + fg->max_ftes - 1); match_criteria_addr = MLX5_ADDR_OF(create_flow_group_in, in, match_criteria); - memcpy(match_criteria_addr, match_criteria, - MLX5_ST_SZ_BYTES(fte_match_param)); + memcpy(match_criteria_addr, fg->mask.match_criteria, + sizeof(fg->mask.match_criteria)); + + err = mlx5_cmd_create_flow_group(dev, ft, in, &fg->id); + if (!err) { + fg->node.active = true; + trace_mlx5_fs_add_fg(fg); + } - fg = create_flow_group_common(ft, in, prev, true); -out: kvfree(in); - return fg; + return err; } static bool mlx5_flow_dests_cmp(struct mlx5_flow_destination *d1, @@ -1340,60 +1447,30 @@ static struct mlx5_flow_handle *add_rule_fg(struct mlx5_flow_group *fg, struct fs_fte *fte) { struct mlx5_flow_handle *handle; - struct mlx5_flow_table *ft; + int old_action; int i; + int ret; - if (fte) { - int old_action; - int ret; - - nested_lock_ref_node(&fte->node, FS_MUTEX_CHILD); - ret = check_conflicting_ftes(fte, flow_act); - if (ret) { - handle = ERR_PTR(ret); - goto unlock_fte; - } - - old_action = fte->action; - fte->action |= flow_act->action; - handle = add_rule_fte(fte, fg, dest, dest_num, - old_action != flow_act->action); - if (IS_ERR(handle)) { - fte->action = old_action; - goto unlock_fte; - } else { - trace_mlx5_fs_set_fte(fte, false); - goto add_rules; - } - } - fs_get_obj(ft, fg->node.parent); + ret = check_conflicting_ftes(fte, flow_act); + if (ret) + return ERR_PTR(ret); - fte = create_fte(fg, match_value, flow_act); - if (IS_ERR(fte)) - return (void *)fte; - tree_init_node(&fte->node, 0, del_fte); - nested_lock_ref_node(&fte->node, FS_MUTEX_CHILD); - handle = add_rule_fte(fte, fg, dest, dest_num, false); + old_action = fte->action; + fte->action |= flow_act->action; + handle = add_rule_fte(fte, fg, dest, dest_num, + old_action != flow_act->action); if (IS_ERR(handle)) { - unlock_ref_node(&fte->node); - destroy_fte(fte, fg); - kfree(fte); + fte->action = old_action; return handle; } + trace_mlx5_fs_set_fte(fte, false); - tree_add_node(&fte->node, &fg->node); - /* fte list isn't sorted */ - list_add_tail(&fte->node.list, &fg->node.children); - trace_mlx5_fs_set_fte(fte, true); -add_rules: for (i = 0; i < handle->num_rules; i++) { if (atomic_read(&handle->rule[i]->node.refcount) == 1) { tree_add_node(&handle->rule[i]->node, &fte->node); trace_mlx5_fs_add_rule(handle->rule[i]); } } -unlock_fte: - unlock_ref_node(&fte->node); return handle; } @@ -1441,93 +1518,197 @@ static bool dest_is_valid(struct mlx5_flow_destination *dest, return true; } -static struct mlx5_flow_handle * -try_add_to_existing_fg(struct mlx5_flow_table *ft, - struct mlx5_flow_spec *spec, - struct mlx5_flow_act *flow_act, - struct mlx5_flow_destination *dest, - int dest_num) -{ +struct match_list { + struct list_head list; struct mlx5_flow_group *g; - struct mlx5_flow_handle *rule = ERR_PTR(-ENOENT); +}; + +struct match_list_head { + struct list_head list; + struct match_list first; +}; + +static void free_match_list(struct match_list_head *head) +{ + if (!list_empty(&head->list)) { + struct match_list *iter, *match_tmp; + + list_del(&head->first.list); + tree_put_node(&head->first.g->node); + list_for_each_entry_safe(iter, match_tmp, &head->list, + list) { + tree_put_node(&iter->g->node); + list_del(&iter->list); + kfree(iter); + } + } +} + +static int build_match_list(struct match_list_head *match_head, + struct mlx5_flow_table *ft, + struct mlx5_flow_spec *spec) +{ struct rhlist_head *tmp, *list; - struct match_list { - struct list_head list; - struct mlx5_flow_group *g; - } match_list, *iter; - LIST_HEAD(match_head); + struct mlx5_flow_group *g; + int err = 0; rcu_read_lock(); + INIT_LIST_HEAD(&match_head->list); /* Collect all fgs which has a matching match_criteria */ list = rhltable_lookup(&ft->fgs_hash, spec, rhash_fg); + /* RCU is atomic, we can't execute FW commands here */ rhl_for_each_entry_rcu(g, tmp, list, hash) { struct match_list *curr_match; - if (likely(list_empty(&match_head))) { - match_list.g = g; - list_add_tail(&match_list.list, &match_head); + if (likely(list_empty(&match_head->list))) { + if (!tree_get_node(&g->node)) + continue; + match_head->first.g = g; + list_add_tail(&match_head->first.list, + &match_head->list); continue; } - curr_match = kmalloc(sizeof(*curr_match), GFP_ATOMIC); + curr_match = kmalloc(sizeof(*curr_match), GFP_ATOMIC); if (!curr_match) { - rcu_read_unlock(); - rule = ERR_PTR(-ENOMEM); - goto free_list; + free_match_list(match_head); + err = -ENOMEM; + goto out; + } + if (!tree_get_node(&g->node)) { + kfree(curr_match); + continue; } curr_match->g = g; - list_add_tail(&curr_match->list, &match_head); + list_add_tail(&curr_match->list, &match_head->list); } +out: rcu_read_unlock(); + return err; +} + +static u64 matched_fgs_get_version(struct list_head *match_head) +{ + struct match_list *iter; + u64 version = 0; + + list_for_each_entry(iter, match_head, list) + version += (u64)atomic_read(&iter->g->node.version); + return version; +} +static struct mlx5_flow_handle * +try_add_to_existing_fg(struct mlx5_flow_table *ft, + struct list_head *match_head, + struct mlx5_flow_spec *spec, + struct mlx5_flow_act *flow_act, + struct mlx5_flow_destination *dest, + int dest_num, + int ft_version) +{ + struct mlx5_flow_steering *steering = get_steering(&ft->node); + struct mlx5_flow_group *g; + struct mlx5_flow_handle *rule; + struct match_list *iter; + bool take_write = false; + struct fs_fte *fte; + u64 version; + int err; + + fte = alloc_fte(ft, spec->match_value, flow_act); + if (IS_ERR(fte)) + return ERR_PTR(-ENOMEM); + + list_for_each_entry(iter, match_head, list) { + nested_down_read_ref_node(&iter->g->node, FS_LOCK_PARENT); + ida_pre_get(&iter->g->fte_allocator, GFP_KERNEL); + } + +search_again_locked: + version = matched_fgs_get_version(match_head); /* Try to find a fg that already contains a matching fte */ - list_for_each_entry(iter, &match_head, list) { - struct fs_fte *fte; + list_for_each_entry(iter, match_head, list) { + struct fs_fte *fte_tmp; g = iter->g; - nested_lock_ref_node(&g->node, FS_MUTEX_PARENT); - fte = rhashtable_lookup_fast(&g->ftes_hash, spec->match_value, - rhash_fte); - if (fte) { - rule = add_rule_fg(g, spec->match_value, - flow_act, dest, dest_num, fte); - unlock_ref_node(&g->node); - goto free_list; + fte_tmp = rhashtable_lookup_fast(&g->ftes_hash, spec->match_value, + rhash_fte); + if (!fte_tmp || !tree_get_node(&fte_tmp->node)) + continue; + + nested_down_write_ref_node(&fte_tmp->node, FS_LOCK_CHILD); + if (!take_write) { + list_for_each_entry(iter, match_head, list) + up_read_ref_node(&iter->g->node); + } else { + list_for_each_entry(iter, match_head, list) + up_write_ref_node(&iter->g->node); } - unlock_ref_node(&g->node); + + rule = add_rule_fg(g, spec->match_value, + flow_act, dest, dest_num, fte_tmp); + up_write_ref_node(&fte_tmp->node); + tree_put_node(&fte_tmp->node); + kmem_cache_free(steering->ftes_cache, fte); + return rule; } /* No group with matching fte found. Try to add a new fte to any * matching fg. */ - list_for_each_entry(iter, &match_head, list) { - g = iter->g; - nested_lock_ref_node(&g->node, FS_MUTEX_PARENT); - rule = add_rule_fg(g, spec->match_value, - flow_act, dest, dest_num, NULL); - if (!IS_ERR(rule) || PTR_ERR(rule) != -ENOSPC) { - unlock_ref_node(&g->node); - goto free_list; - } - unlock_ref_node(&g->node); + if (!take_write) { + list_for_each_entry(iter, match_head, list) + up_read_ref_node(&iter->g->node); + list_for_each_entry(iter, match_head, list) + nested_down_write_ref_node(&iter->g->node, + FS_LOCK_PARENT); + take_write = true; } -free_list: - if (!list_empty(&match_head)) { - struct match_list *match_tmp; + /* Check the ft version, for case that new flow group + * was added while the fgs weren't locked + */ + if (atomic_read(&ft->node.version) != ft_version) { + rule = ERR_PTR(-EAGAIN); + goto out; + } - /* The most common case is having one FG. Since we want to - * optimize this case, we save the first on the stack. - * Therefore, no need to free it. - */ - list_del(&list_first_entry(&match_head, typeof(*iter), list)->list); - list_for_each_entry_safe(iter, match_tmp, &match_head, list) { - list_del(&iter->list); - kfree(iter); + /* Check the fgs version, for case the new FTE with the + * same values was added while the fgs weren't locked + */ + if (version != matched_fgs_get_version(match_head)) + goto search_again_locked; + + list_for_each_entry(iter, match_head, list) { + g = iter->g; + + if (!g->node.active) + continue; + err = insert_fte(g, fte); + if (err) { + if (err == -ENOSPC) + continue; + list_for_each_entry(iter, match_head, list) + up_write_ref_node(&iter->g->node); + kmem_cache_free(steering->ftes_cache, fte); + return ERR_PTR(err); } - } + nested_down_write_ref_node(&fte->node, FS_LOCK_CHILD); + list_for_each_entry(iter, match_head, list) + up_write_ref_node(&iter->g->node); + rule = add_rule_fg(g, spec->match_value, + flow_act, dest, dest_num, fte); + up_write_ref_node(&fte->node); + tree_put_node(&fte->node); + return rule; + } + rule = ERR_PTR(-ENOENT); +out: + list_for_each_entry(iter, match_head, list) + up_write_ref_node(&iter->g->node); + kmem_cache_free(steering->ftes_cache, fte); return rule; } @@ -1539,8 +1720,14 @@ _mlx5_add_flow_rules(struct mlx5_flow_table *ft, int dest_num) { + struct mlx5_flow_steering *steering = get_steering(&ft->node); struct mlx5_flow_group *g; struct mlx5_flow_handle *rule; + struct match_list_head match_head; + bool take_write = false; + struct fs_fte *fte; + int version; + int err; int i; if (!check_valid_spec(spec)) @@ -1550,33 +1737,73 @@ _mlx5_add_flow_rules(struct mlx5_flow_table *ft, if (!dest_is_valid(&dest[i], flow_act->action, ft)) return ERR_PTR(-EINVAL); } + nested_down_read_ref_node(&ft->node, FS_LOCK_GRANDPARENT); +search_again_locked: + version = atomic_read(&ft->node.version); + + /* Collect all fgs which has a matching match_criteria */ + err = build_match_list(&match_head, ft, spec); + if (err) + return ERR_PTR(err); - nested_lock_ref_node(&ft->node, FS_MUTEX_GRANDPARENT); - rule = try_add_to_existing_fg(ft, spec, flow_act, dest, dest_num); - if (!IS_ERR(rule)) - goto unlock; + if (!take_write) + up_read_ref_node(&ft->node); - g = create_autogroup(ft, spec->match_criteria_enable, - spec->match_criteria); + rule = try_add_to_existing_fg(ft, &match_head.list, spec, flow_act, dest, + dest_num, version); + free_match_list(&match_head); + if (!IS_ERR(rule) || + (PTR_ERR(rule) != -ENOENT && PTR_ERR(rule) != -EAGAIN)) + return rule; + + if (!take_write) { + nested_down_write_ref_node(&ft->node, FS_LOCK_GRANDPARENT); + take_write = true; + } + + if (PTR_ERR(rule) == -EAGAIN || + version != atomic_read(&ft->node.version)) + goto search_again_locked; + + g = alloc_auto_flow_group(ft, spec); if (IS_ERR(g)) { rule = (void *)g; - goto unlock; + up_write_ref_node(&ft->node); + return rule; } - rule = add_rule_fg(g, spec->match_value, flow_act, dest, - dest_num, NULL); - if (IS_ERR(rule)) { - /* Remove assumes refcount > 0 and autogroup creates a group - * with a refcount = 0. - */ - unlock_ref_node(&ft->node); - tree_get_node(&g->node); - tree_remove_node(&g->node); - return rule; + nested_down_write_ref_node(&g->node, FS_LOCK_PARENT); + up_write_ref_node(&ft->node); + + err = create_auto_flow_group(ft, g); + if (err) + goto err_release_fg; + + fte = alloc_fte(ft, spec->match_value, flow_act); + if (IS_ERR(fte)) { + err = PTR_ERR(fte); + goto err_release_fg; } -unlock: - unlock_ref_node(&ft->node); + + err = insert_fte(g, fte); + if (err) { + kmem_cache_free(steering->ftes_cache, fte); + goto err_release_fg; + } + + nested_down_write_ref_node(&fte->node, FS_LOCK_CHILD); + up_write_ref_node(&g->node); + rule = add_rule_fg(g, spec->match_value, flow_act, dest, + dest_num, fte); + up_write_ref_node(&fte->node); + tree_put_node(&fte->node); + tree_put_node(&g->node); return rule; + +err_release_fg: + up_write_ref_node(&g->node); + tree_put_node(&g->node); + return ERR_PTR(err); } static bool fwd_next_prio_supported(struct mlx5_flow_table *ft) @@ -1661,23 +1888,43 @@ static struct mlx5_flow_table *find_next_ft(struct mlx5_flow_table *ft) static int update_root_ft_destroy(struct mlx5_flow_table *ft) { struct mlx5_flow_root_namespace *root = find_root(&ft->node); + struct mlx5_ft_underlay_qp *uqp; struct mlx5_flow_table *new_root_ft = NULL; + int err = 0; + u32 qpn; if (root->root_ft != ft) return 0; new_root_ft = find_next_ft(ft); - if (new_root_ft) { - int err = mlx5_cmd_update_root_ft(root->dev, new_root_ft, - root->underlay_qpn); - if (err) { - mlx5_core_warn(root->dev, "Update root flow table of id=%u failed\n", - ft->id); - return err; + if (!new_root_ft) { + root->root_ft = NULL; + return 0; + } + + if (list_empty(&root->underlay_qpns)) { + /* Don't set any QPN (zero) in case QPN list is empty */ + qpn = 0; + err = mlx5_cmd_update_root_ft(root->dev, new_root_ft, qpn, + false); + } else { + list_for_each_entry(uqp, &root->underlay_qpns, list) { + qpn = uqp->qpn; + err = mlx5_cmd_update_root_ft(root->dev, new_root_ft, + qpn, false); + if (err) + break; } } - root->root_ft = new_root_ft; + + if (err) + mlx5_core_warn(root->dev, + "Update root flow table of id(%u) qpn(%d) failed\n", + ft->id, qpn); + else + root->root_ft = new_root_ft; + return 0; } @@ -1817,7 +2064,7 @@ static struct fs_prio *fs_create_prio(struct mlx5_flow_namespace *ns, return ERR_PTR(-ENOMEM); fs_prio->node.type = FS_TYPE_PRIO; - tree_init_node(&fs_prio->node, 1, NULL); + tree_init_node(&fs_prio->node, NULL, NULL); tree_add_node(&fs_prio->node, &ns->node); fs_prio->num_levels = num_levels; fs_prio->prio = prio; @@ -1843,7 +2090,7 @@ static struct mlx5_flow_namespace *fs_create_namespace(struct fs_prio *prio) return ERR_PTR(-ENOMEM); fs_init_namespace(ns); - tree_init_node(&ns->node, 1, NULL); + tree_init_node(&ns->node, NULL, NULL); tree_add_node(&ns->node, &prio->node); list_add_tail(&ns->node.list, &prio->node.children); @@ -1965,10 +2212,12 @@ static struct mlx5_flow_root_namespace *create_root_ns(struct mlx5_flow_steering root_ns->dev = steering->dev; root_ns->table_type = table_type; + INIT_LIST_HEAD(&root_ns->underlay_qpns); + ns = &root_ns->ns; fs_init_namespace(ns); mutex_init(&root_ns->chain_lock); - tree_init_node(&ns->node, 1, NULL); + tree_init_node(&ns->node, NULL, NULL); tree_add_node(&ns->node, NULL); return root_ns; @@ -2066,8 +2315,10 @@ static void clean_tree(struct fs_node *node) struct fs_node *iter; struct fs_node *temp; + tree_get_node(node); list_for_each_entry_safe(iter, temp, &node->children, list) clean_tree(iter); + tree_put_node(node); tree_remove_node(node); } } @@ -2091,6 +2342,8 @@ void mlx5_cleanup_fs(struct mlx5_core_dev *dev) cleanup_root_ns(steering->sniffer_rx_root_ns); cleanup_root_ns(steering->sniffer_tx_root_ns); mlx5_cleanup_fc_stats(dev); + kmem_cache_destroy(steering->ftes_cache); + kmem_cache_destroy(steering->fgs_cache); kfree(steering); } @@ -2196,6 +2449,16 @@ int mlx5_init_fs(struct mlx5_core_dev *dev) steering->dev = dev; dev->priv.steering = steering; + steering->fgs_cache = kmem_cache_create("mlx5_fs_fgs", + sizeof(struct mlx5_flow_group), 0, + 0, NULL); + steering->ftes_cache = kmem_cache_create("mlx5_fs_ftes", sizeof(struct fs_fte), 0, + 0, NULL); + if (!steering->ftes_cache || !steering->fgs_cache) { + err = -ENOMEM; + goto err; + } + if ((((MLX5_CAP_GEN(dev, port_type) == MLX5_CAP_PORT_TYPE_ETH) && (MLX5_CAP_GEN(dev, nic_flow_table))) || ((MLX5_CAP_GEN(dev, port_type) == MLX5_CAP_PORT_TYPE_IB) && @@ -2245,17 +2508,76 @@ err: int mlx5_fs_add_rx_underlay_qpn(struct mlx5_core_dev *dev, u32 underlay_qpn) { struct mlx5_flow_root_namespace *root = dev->priv.steering->root_ns; + struct mlx5_ft_underlay_qp *new_uqp; + int err = 0; + + new_uqp = kzalloc(sizeof(*new_uqp), GFP_KERNEL); + if (!new_uqp) + return -ENOMEM; + + mutex_lock(&root->chain_lock); + + if (!root->root_ft) { + err = -EINVAL; + goto update_ft_fail; + } + + err = mlx5_cmd_update_root_ft(dev, root->root_ft, underlay_qpn, false); + if (err) { + mlx5_core_warn(dev, "Failed adding underlay QPN (%u) to root FT err(%d)\n", + underlay_qpn, err); + goto update_ft_fail; + } + + new_uqp->qpn = underlay_qpn; + list_add_tail(&new_uqp->list, &root->underlay_qpns); + + mutex_unlock(&root->chain_lock); - root->underlay_qpn = underlay_qpn; return 0; + +update_ft_fail: + mutex_unlock(&root->chain_lock); + kfree(new_uqp); + return err; } EXPORT_SYMBOL(mlx5_fs_add_rx_underlay_qpn); int mlx5_fs_remove_rx_underlay_qpn(struct mlx5_core_dev *dev, u32 underlay_qpn) { struct mlx5_flow_root_namespace *root = dev->priv.steering->root_ns; + struct mlx5_ft_underlay_qp *uqp; + bool found = false; + int err = 0; + + mutex_lock(&root->chain_lock); + list_for_each_entry(uqp, &root->underlay_qpns, list) { + if (uqp->qpn == underlay_qpn) { + found = true; + break; + } + } + + if (!found) { + mlx5_core_warn(dev, "Failed finding underlay qp (%u) in qpn list\n", + underlay_qpn); + err = -EINVAL; + goto out; + } + + err = mlx5_cmd_update_root_ft(dev, root->root_ft, underlay_qpn, true); + if (err) + mlx5_core_warn(dev, "Failed removing underlay QPN (%u) from root FT err(%d)\n", + underlay_qpn, err); + + list_del(&uqp->list); + mutex_unlock(&root->chain_lock); + kfree(uqp); - root->underlay_qpn = 0; return 0; + +out: + mutex_unlock(&root->chain_lock); + return err; } EXPORT_SYMBOL(mlx5_fs_remove_rx_underlay_qpn); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h index 5509a752f98e..80f6f3c714c8 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h @@ -52,6 +52,7 @@ enum fs_flow_table_type { FS_FT_FDB = 0X4, FS_FT_SNIFFER_RX = 0X5, FS_FT_SNIFFER_TX = 0X6, + FS_FT_MAX_TYPE = FS_FT_SNIFFER_TX, }; enum fs_flow_table_op_mod { @@ -65,6 +66,8 @@ enum fs_fte_status { struct mlx5_flow_steering { struct mlx5_core_dev *dev; + struct kmem_cache *fgs_cache; + struct kmem_cache *ftes_cache; struct mlx5_flow_root_namespace *root_ns; struct mlx5_flow_root_namespace *fdb_root_ns; struct mlx5_flow_root_namespace *esw_egress_root_ns; @@ -80,9 +83,12 @@ struct fs_node { struct fs_node *parent; struct fs_node *root; /* lock the node for writing and traversing */ - struct mutex lock; + struct rw_semaphore lock; atomic_t refcount; - void (*remove_func)(struct fs_node *); + bool active; + void (*del_hw_func)(struct fs_node *); + void (*del_sw_func)(struct fs_node *); + atomic_t version; }; struct mlx5_flow_rule { @@ -119,7 +125,6 @@ struct mlx5_flow_table { /* FWD rules that point on this flow table */ struct list_head fwd_rules; u32 flags; - struct ida fte_allocator; struct rhltable fgs_hash; }; @@ -146,6 +151,11 @@ struct mlx5_fc { struct mlx5_fc_cache cache ____cacheline_aligned_in_smp; }; +struct mlx5_ft_underlay_qp { + struct list_head list; + u32 qpn; +}; + #define MLX5_FTE_MATCH_PARAM_RESERVED reserved_at_600 /* Calculate the fte_match_param length and without the reserved length. * Make sure the reserved field is the last. @@ -199,6 +209,7 @@ struct mlx5_flow_group { struct mlx5_flow_group_mask mask; u32 start_index; u32 max_ftes; + struct ida fte_allocator; u32 id; struct rhashtable ftes_hash; struct rhlist_head hash; @@ -211,7 +222,7 @@ struct mlx5_flow_root_namespace { struct mlx5_flow_table *root_ft; /* Should be held when chaining flow tables */ struct mutex chain_lock; - u32 underlay_qpn; + struct list_head underlay_qpns; }; int mlx5_init_fc_stats(struct mlx5_core_dev *dev); @@ -260,4 +271,14 @@ void mlx5_cleanup_fs(struct mlx5_core_dev *dev); #define fs_for_each_dst(pos, fte) \ fs_list_for_each_entry(pos, &(fte)->node.children) +#define MLX5_CAP_FLOWTABLE_TYPE(mdev, cap, type) ( \ + (type == FS_FT_NIC_RX) ? MLX5_CAP_FLOWTABLE_NIC_RX(mdev, cap) : \ + (type == FS_FT_ESW_EGRESS_ACL) ? MLX5_CAP_ESW_EGRESS_ACL(mdev, cap) : \ + (type == FS_FT_ESW_INGRESS_ACL) ? MLX5_CAP_ESW_INGRESS_ACL(mdev, cap) : \ + (type == FS_FT_FDB) ? MLX5_CAP_ESW_FLOWTABLE_FDB(mdev, cap) : \ + (type == FS_FT_SNIFFER_RX) ? MLX5_CAP_FLOWTABLE_SNIFFER_RX(mdev, cap) : \ + (type == FS_FT_SNIFFER_TX) ? MLX5_CAP_FLOWTABLE_SNIFFER_TX(mdev, cap) : \ + (BUILD_BUG_ON_ZERO(FS_FT_SNIFFER_TX != FS_FT_MAX_TYPE))\ + ) + #endif diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ethtool.c index 43c126c63955..6f338a9219c8 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ethtool.c @@ -250,3 +250,8 @@ const struct ethtool_ops mlx5i_ethtool_ops = { .get_link_ksettings = mlx5i_get_link_ksettings, .get_link = ethtool_op_get_link, }; + +const struct ethtool_ops mlx5i_pkey_ethtool_ops = { + .get_drvinfo = mlx5i_get_drvinfo, + .get_link = ethtool_op_get_link, +}; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c index 85298051a3e4..abf270d7f556 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c @@ -40,8 +40,6 @@ static int mlx5i_open(struct net_device *netdev); static int mlx5i_close(struct net_device *netdev); -static int mlx5i_dev_init(struct net_device *dev); -static void mlx5i_dev_cleanup(struct net_device *dev); static int mlx5i_change_mtu(struct net_device *netdev, int new_mtu); static int mlx5i_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd); @@ -70,10 +68,10 @@ static void mlx5i_build_nic_params(struct mlx5_core_dev *mdev, } /* Called directly after IPoIB netdevice was created to initialize SW structs */ -static void mlx5i_init(struct mlx5_core_dev *mdev, - struct net_device *netdev, - const struct mlx5e_profile *profile, - void *ppriv) +void mlx5i_init(struct mlx5_core_dev *mdev, + struct net_device *netdev, + const struct mlx5e_profile *profile, + void *ppriv) { struct mlx5e_priv *priv = mlx5i_epriv(netdev); @@ -108,11 +106,69 @@ static void mlx5i_cleanup(struct mlx5e_priv *priv) /* Do nothing .. */ } +int mlx5i_init_underlay_qp(struct mlx5e_priv *priv) +{ + struct mlx5_core_dev *mdev = priv->mdev; + struct mlx5i_priv *ipriv = priv->ppriv; + struct mlx5_core_qp *qp = &ipriv->qp; + struct mlx5_qp_context *context; + int ret; + + /* QP states */ + context = kzalloc(sizeof(*context), GFP_KERNEL); + if (!context) + return -ENOMEM; + + context->flags = cpu_to_be32(MLX5_QP_PM_MIGRATED << 11); + context->pri_path.port = 1; + context->pri_path.pkey_index = cpu_to_be16(ipriv->pkey_index); + context->qkey = cpu_to_be32(IB_DEFAULT_Q_KEY); + + ret = mlx5_core_qp_modify(mdev, MLX5_CMD_OP_RST2INIT_QP, 0, context, qp); + if (ret) { + mlx5_core_err(mdev, "Failed to modify qp RST2INIT, err: %d\n", ret); + goto err_qp_modify_to_err; + } + memset(context, 0, sizeof(*context)); + + ret = mlx5_core_qp_modify(mdev, MLX5_CMD_OP_INIT2RTR_QP, 0, context, qp); + if (ret) { + mlx5_core_err(mdev, "Failed to modify qp INIT2RTR, err: %d\n", ret); + goto err_qp_modify_to_err; + } + + ret = mlx5_core_qp_modify(mdev, MLX5_CMD_OP_RTR2RTS_QP, 0, context, qp); + if (ret) { + mlx5_core_err(mdev, "Failed to modify qp RTR2RTS, err: %d\n", ret); + goto err_qp_modify_to_err; + } + + kfree(context); + return 0; + +err_qp_modify_to_err: + mlx5_core_qp_modify(mdev, MLX5_CMD_OP_2ERR_QP, 0, &context, qp); + kfree(context); + return ret; +} + +void mlx5i_uninit_underlay_qp(struct mlx5e_priv *priv) +{ + struct mlx5i_priv *ipriv = priv->ppriv; + struct mlx5_core_dev *mdev = priv->mdev; + struct mlx5_qp_context context; + int err; + + err = mlx5_core_qp_modify(mdev, MLX5_CMD_OP_2RST_QP, 0, &context, + &ipriv->qp); + if (err) + mlx5_core_err(mdev, "Failed to modify qp 2RST, err: %d\n", err); +} + #define MLX5_QP_ENHANCED_ULP_STATELESS_MODE 2 -static int mlx5i_create_underlay_qp(struct mlx5_core_dev *mdev, struct mlx5_core_qp *qp) +int mlx5i_create_underlay_qp(struct mlx5_core_dev *mdev, struct mlx5_core_qp *qp) { - struct mlx5_qp_context *context = NULL; u32 *in = NULL; void *addr_path; int ret = 0; @@ -140,43 +196,12 @@ static int mlx5i_create_underlay_qp(struct mlx5_core_dev *mdev, struct mlx5_core goto out; } - /* QP states */ - context = kzalloc(sizeof(*context), GFP_KERNEL); - if (!context) { - ret = -ENOMEM; - goto out; - } - - context->flags = cpu_to_be32(MLX5_QP_PM_MIGRATED << 11); - context->pri_path.port = 1; - context->qkey = cpu_to_be32(IB_DEFAULT_Q_KEY); - - ret = mlx5_core_qp_modify(mdev, MLX5_CMD_OP_RST2INIT_QP, 0, context, qp); - if (ret) { - mlx5_core_err(mdev, "Failed to modify qp RST2INIT, err: %d\n", ret); - goto out; - } - memset(context, 0, sizeof(*context)); - - ret = mlx5_core_qp_modify(mdev, MLX5_CMD_OP_INIT2RTR_QP, 0, context, qp); - if (ret) { - mlx5_core_err(mdev, "Failed to modify qp INIT2RTR, err: %d\n", ret); - goto out; - } - - ret = mlx5_core_qp_modify(mdev, MLX5_CMD_OP_RTR2RTS_QP, 0, context, qp); - if (ret) { - mlx5_core_err(mdev, "Failed to modify qp RTR2RTS, err: %d\n", ret); - goto out; - } - out: - kfree(context); kvfree(in); return ret; } -static void mlx5i_destroy_underlay_qp(struct mlx5_core_dev *mdev, struct mlx5_core_qp *qp) +void mlx5i_destroy_underlay_qp(struct mlx5_core_dev *mdev, struct mlx5_core_qp *qp) { mlx5_core_destroy_qp(mdev, qp); } @@ -195,10 +220,14 @@ static int mlx5i_init_tx(struct mlx5e_priv *priv) err = mlx5e_create_tis(priv->mdev, 0 /* tc */, ipriv->qp.qpn, &priv->tisn[0]); if (err) { mlx5_core_warn(priv->mdev, "create tis failed, %d\n", err); - return err; + goto err_destroy_underlay_qp; } return 0; + +err_destroy_underlay_qp: + mlx5i_destroy_underlay_qp(priv->mdev, &ipriv->qp); + return err; } static void mlx5i_cleanup_tx(struct mlx5e_priv *priv) @@ -249,7 +278,6 @@ static void mlx5i_destroy_flow_steering(struct mlx5e_priv *priv) static int mlx5i_init_rx(struct mlx5e_priv *priv) { - struct mlx5i_priv *ipriv = priv->ppriv; int err; err = mlx5e_create_indirect_rqt(priv); @@ -268,18 +296,12 @@ static int mlx5i_init_rx(struct mlx5e_priv *priv) if (err) goto err_destroy_indirect_tirs; - err = mlx5_fs_add_rx_underlay_qpn(priv->mdev, ipriv->qp.qpn); - if (err) - goto err_destroy_direct_tirs; - err = mlx5i_create_flow_steering(priv); if (err) - goto err_remove_rx_underlay_qpn; + goto err_destroy_direct_tirs; return 0; -err_remove_rx_underlay_qpn: - mlx5_fs_remove_rx_underlay_qpn(priv->mdev, ipriv->qp.qpn); err_destroy_direct_tirs: mlx5e_destroy_direct_tirs(priv); err_destroy_indirect_tirs: @@ -293,9 +315,6 @@ err_destroy_indirect_rqts: static void mlx5i_cleanup_rx(struct mlx5e_priv *priv) { - struct mlx5i_priv *ipriv = priv->ppriv; - - mlx5_fs_remove_rx_underlay_qpn(priv->mdev, ipriv->qp.qpn); mlx5i_destroy_flow_steering(priv); mlx5e_destroy_direct_tirs(priv); mlx5e_destroy_indirect_tirs(priv); @@ -351,7 +370,7 @@ out: return err; } -static int mlx5i_dev_init(struct net_device *dev) +int mlx5i_dev_init(struct net_device *dev) { struct mlx5e_priv *priv = mlx5i_epriv(dev); struct mlx5i_priv *ipriv = priv->ppriv; @@ -361,6 +380,9 @@ static int mlx5i_dev_init(struct net_device *dev) dev->dev_addr[2] = (ipriv->qp.qpn >> 8) & 0xff; dev->dev_addr[3] = (ipriv->qp.qpn) & 0xff; + /* Add QPN to net-device mapping to HT */ + mlx5i_pkey_add_qpn(dev ,ipriv->qp.qpn); + return 0; } @@ -378,63 +400,84 @@ static int mlx5i_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) } } -static void mlx5i_dev_cleanup(struct net_device *dev) +void mlx5i_dev_cleanup(struct net_device *dev) { struct mlx5e_priv *priv = mlx5i_epriv(dev); - struct mlx5_core_dev *mdev = priv->mdev; - struct mlx5i_priv *ipriv = priv->ppriv; - struct mlx5_qp_context context; + struct mlx5i_priv *ipriv = priv->ppriv; + + mlx5i_uninit_underlay_qp(priv); - /* detach qp from flow-steering by reset it */ - mlx5_core_qp_modify(mdev, MLX5_CMD_OP_2RST_QP, 0, &context, &ipriv->qp); + /* Delete QPN to net-device mapping from HT */ + mlx5i_pkey_del_qpn(dev, ipriv->qp.qpn); } static int mlx5i_open(struct net_device *netdev) { - struct mlx5e_priv *priv = mlx5i_epriv(netdev); + struct mlx5e_priv *epriv = mlx5i_epriv(netdev); + struct mlx5i_priv *ipriv = epriv->ppriv; + struct mlx5_core_dev *mdev = epriv->mdev; int err; - mutex_lock(&priv->state_lock); + mutex_lock(&epriv->state_lock); - set_bit(MLX5E_STATE_OPENED, &priv->state); + set_bit(MLX5E_STATE_OPENED, &epriv->state); - err = mlx5e_open_channels(priv, &priv->channels); - if (err) + err = mlx5i_init_underlay_qp(epriv); + if (err) { + mlx5_core_warn(mdev, "prepare underlay qp state failed, %d\n", err); goto err_clear_state_opened_flag; + } - mlx5e_refresh_tirs(priv, false); - mlx5e_activate_priv_channels(priv); - mlx5e_timestamp_init(priv); + err = mlx5_fs_add_rx_underlay_qpn(mdev, ipriv->qp.qpn); + if (err) { + mlx5_core_warn(mdev, "attach underlay qp to ft failed, %d\n", err); + goto err_reset_qp; + } - mutex_unlock(&priv->state_lock); + err = mlx5e_open_channels(epriv, &epriv->channels); + if (err) + goto err_remove_fs_underlay_qp; + + mlx5e_refresh_tirs(epriv, false); + mlx5e_activate_priv_channels(epriv); + mlx5e_timestamp_set(epriv); + + mutex_unlock(&epriv->state_lock); return 0; +err_remove_fs_underlay_qp: + mlx5_fs_remove_rx_underlay_qpn(mdev, ipriv->qp.qpn); +err_reset_qp: + mlx5i_uninit_underlay_qp(epriv); err_clear_state_opened_flag: - clear_bit(MLX5E_STATE_OPENED, &priv->state); - mutex_unlock(&priv->state_lock); + clear_bit(MLX5E_STATE_OPENED, &epriv->state); + mutex_unlock(&epriv->state_lock); return err; } static int mlx5i_close(struct net_device *netdev) { - struct mlx5e_priv *priv = mlx5i_epriv(netdev); + struct mlx5e_priv *epriv = mlx5i_epriv(netdev); + struct mlx5i_priv *ipriv = epriv->ppriv; + struct mlx5_core_dev *mdev = epriv->mdev; /* May already be CLOSED in case a previous configuration operation * (e.g RX/TX queue size change) that involves close&open failed. */ - mutex_lock(&priv->state_lock); + mutex_lock(&epriv->state_lock); - if (!test_bit(MLX5E_STATE_OPENED, &priv->state)) + if (!test_bit(MLX5E_STATE_OPENED, &epriv->state)) goto unlock; - clear_bit(MLX5E_STATE_OPENED, &priv->state); + clear_bit(MLX5E_STATE_OPENED, &epriv->state); - mlx5e_timestamp_cleanup(priv); - netif_carrier_off(priv->netdev); - mlx5e_deactivate_priv_channels(priv); - mlx5e_close_channels(&priv->channels); + netif_carrier_off(epriv->netdev); + mlx5_fs_remove_rx_underlay_qpn(mdev, ipriv->qp.qpn); + mlx5i_uninit_underlay_qp(epriv); + mlx5e_deactivate_priv_channels(epriv); + mlx5e_close_channels(&epriv->channels);; unlock: - mutex_unlock(&priv->state_lock); + mutex_unlock(&epriv->state_lock); return 0; } @@ -492,6 +535,13 @@ static int mlx5i_xmit(struct net_device *dev, struct sk_buff *skb, return mlx5i_sq_xmit(sq, skb, &mah->av, dqpn, ipriv->qkey); } +static void mlx5i_set_pkey_index(struct net_device *netdev, int id) +{ + struct mlx5i_priv *ipriv = netdev_priv(netdev); + + ipriv->pkey_index = (u16)id; +} + static int mlx5i_check_required_hca_cap(struct mlx5_core_dev *mdev) { if (MLX5_CAP_GEN(mdev, port_type) != MLX5_CAP_PORT_TYPE_IB) @@ -510,12 +560,13 @@ struct net_device *mlx5_rdma_netdev_alloc(struct mlx5_core_dev *mdev, const char *name, void (*setup)(struct net_device *)) { - const struct mlx5e_profile *profile = &mlx5i_nic_profile; - int nch = profile->max_nch(mdev); + const struct mlx5e_profile *profile; struct net_device *netdev; struct mlx5i_priv *ipriv; struct mlx5e_priv *epriv; struct rdma_netdev *rn; + bool sub_interface; + int nch; int err; if (mlx5i_check_required_hca_cap(mdev)) { @@ -523,10 +574,15 @@ struct net_device *mlx5_rdma_netdev_alloc(struct mlx5_core_dev *mdev, return ERR_PTR(-EOPNOTSUPP); } - /* This function should only be called once per mdev */ - err = mlx5e_create_mdev_resources(mdev); - if (err) - return NULL; + /* TODO: Need to find a better way to check if child device*/ + sub_interface = (mdev->mlx5e_res.pdn != 0); + + if (sub_interface) + profile = mlx5i_pkey_get_profile(); + else + profile = &mlx5i_nic_profile; + + nch = profile->max_nch(mdev); netdev = alloc_netdev_mqs(sizeof(struct mlx5i_priv) + sizeof(struct mlx5e_priv), name, NET_NAME_UNKNOWN, @@ -535,7 +591,7 @@ struct net_device *mlx5_rdma_netdev_alloc(struct mlx5_core_dev *mdev, nch); if (!netdev) { mlx5_core_warn(mdev, "alloc_netdev_mqs failed\n"); - goto free_mdev_resources; + return NULL; } ipriv = netdev_priv(netdev); @@ -545,6 +601,20 @@ struct net_device *mlx5_rdma_netdev_alloc(struct mlx5_core_dev *mdev, if (!epriv->wq) goto err_free_netdev; + ipriv->sub_interface = sub_interface; + if (!ipriv->sub_interface) { + err = mlx5i_pkey_qpn_ht_init(netdev); + if (err) { + mlx5_core_warn(mdev, "allocate qpn_to_netdev ht failed\n"); + goto destroy_wq; + } + + /* This should only be called once per mdev */ + err = mlx5e_create_mdev_resources(mdev); + if (err) + goto destroy_ht; + } + profile->init(mdev, netdev, profile, ipriv); mlx5e_attach_netdev(epriv); @@ -556,13 +626,16 @@ struct net_device *mlx5_rdma_netdev_alloc(struct mlx5_core_dev *mdev, rn->send = mlx5i_xmit; rn->attach_mcast = mlx5i_attach_mcast; rn->detach_mcast = mlx5i_detach_mcast; + rn->set_id = mlx5i_set_pkey_index; return netdev; +destroy_ht: + mlx5i_pkey_qpn_ht_cleanup(netdev); +destroy_wq: + destroy_workqueue(epriv->wq); err_free_netdev: free_netdev(netdev); -free_mdev_resources: - mlx5e_destroy_mdev_resources(mdev); return NULL; } @@ -570,14 +643,18 @@ EXPORT_SYMBOL(mlx5_rdma_netdev_alloc); void mlx5_rdma_netdev_free(struct net_device *netdev) { - struct mlx5e_priv *priv = mlx5i_epriv(netdev); + struct mlx5e_priv *priv = mlx5i_epriv(netdev); + struct mlx5i_priv *ipriv = priv->ppriv; const struct mlx5e_profile *profile = priv->profile; mlx5e_detach_netdev(priv); profile->cleanup(priv); destroy_workqueue(priv->wq); - free_netdev(netdev); - mlx5e_destroy_mdev_resources(priv->mdev); + if (!ipriv->sub_interface) { + mlx5i_pkey_qpn_ht_cleanup(netdev); + mlx5e_destroy_mdev_resources(priv->mdev); + } + free_netdev(netdev); } EXPORT_SYMBOL(mlx5_rdma_netdev_free); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.h b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.h index a0f405f520f7..49008022c306 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.h @@ -39,6 +39,7 @@ #define MLX5I_MAX_NUM_TC 1 extern const struct ethtool_ops mlx5i_ethtool_ops; +extern const struct ethtool_ops mlx5i_pkey_ethtool_ops; #define MLX5_IB_GRH_BYTES 40 #define MLX5_IPOIB_ENCAP_LEN 4 @@ -49,10 +50,45 @@ extern const struct ethtool_ops mlx5i_ethtool_ops; struct mlx5i_priv { struct rdma_netdev rn; /* keep this first */ struct mlx5_core_qp qp; + bool sub_interface; u32 qkey; + u16 pkey_index; + struct mlx5i_pkey_qpn_ht *qpn_htbl; char *mlx5e_priv[0]; }; +/* Underlay QP create/destroy functions */ +int mlx5i_create_underlay_qp(struct mlx5_core_dev *mdev, struct mlx5_core_qp *qp); +void mlx5i_destroy_underlay_qp(struct mlx5_core_dev *mdev, struct mlx5_core_qp *qp); + +/* Underlay QP state modification init/uninit functions */ +int mlx5i_init_underlay_qp(struct mlx5e_priv *priv); +void mlx5i_uninit_underlay_qp(struct mlx5e_priv *priv); + +/* Allocate/Free underlay QPN to net-device hash table */ +int mlx5i_pkey_qpn_ht_init(struct net_device *netdev); +void mlx5i_pkey_qpn_ht_cleanup(struct net_device *netdev); + +/* Add/Remove an underlay QPN to net-device mapping to/from the hash table */ +int mlx5i_pkey_add_qpn(struct net_device *netdev, u32 qpn); +int mlx5i_pkey_del_qpn(struct net_device *netdev, u32 qpn); + +/* Get the net-device corresponding to the given underlay QPN */ +struct net_device *mlx5i_pkey_get_netdev(struct net_device *netdev, u32 qpn); + +/* Shared ndo functionts */ +int mlx5i_dev_init(struct net_device *dev); +void mlx5i_dev_cleanup(struct net_device *dev); + +/* Parent profile functions */ +void mlx5i_init(struct mlx5_core_dev *mdev, + struct net_device *netdev, + const struct mlx5e_profile *profile, + void *ppriv); + +/* Get child interface nic profile */ +const struct mlx5e_profile *mlx5i_pkey_get_profile(void); + /* Extract mlx5e_priv from IPoIB netdev */ #define mlx5i_epriv(netdev) ((void *)(((struct mlx5i_priv *)netdev_priv(netdev))->mlx5e_priv)) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib_vlan.c b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib_vlan.c new file mode 100644 index 000000000000..531b02cc979b --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib_vlan.c @@ -0,0 +1,350 @@ +/* + * Copyright (c) 2017, Mellanox Technologies. All rights reserved. + * + * This software is available to you under a choice of one of two + * licenses. You may choose to be licensed under the terms of the GNU + * General Public License (GPL) Version 2, available from the file + * COPYING in the main directory of this source tree, or the + * OpenIB.org BSD license below: + * + * Redistribution and use in source and binary forms, with or + * without modification, are permitted provided that the following + * conditions are met: + * + * - Redistributions of source code must retain the above + * copyright notice, this list of conditions and the following + * disclaimer. + * + * - Redistributions in binary form must reproduce the above + * copyright notice, this list of conditions and the following + * disclaimer in the documentation and/or other materials + * provided with the distribution. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND + * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS + * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN + * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN + * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE + * SOFTWARE. + */ + +#include <linux/hash.h> +#include "ipoib.h" + +#define MLX5I_MAX_LOG_PKEY_SUP 7 + +struct qpn_to_netdev { + struct net_device *netdev; + struct hlist_node hlist; + u32 underlay_qpn; +}; + +struct mlx5i_pkey_qpn_ht { + struct hlist_head buckets[1 << MLX5I_MAX_LOG_PKEY_SUP]; + spinlock_t ht_lock; /* Synchronise with NAPI */ +}; + +int mlx5i_pkey_qpn_ht_init(struct net_device *netdev) +{ + struct mlx5i_priv *ipriv = netdev_priv(netdev); + struct mlx5i_pkey_qpn_ht *qpn_htbl; + + qpn_htbl = kzalloc(sizeof(*qpn_htbl), GFP_KERNEL); + if (!qpn_htbl) + return -ENOMEM; + + ipriv->qpn_htbl = qpn_htbl; + spin_lock_init(&qpn_htbl->ht_lock); + + return 0; +} + +void mlx5i_pkey_qpn_ht_cleanup(struct net_device *netdev) +{ + struct mlx5i_priv *ipriv = netdev_priv(netdev); + + kfree(ipriv->qpn_htbl); +} + +static struct qpn_to_netdev *mlx5i_find_qpn_to_netdev_node(struct hlist_head *buckets, + u32 qpn) +{ + struct hlist_head *h = &buckets[hash_32(qpn, MLX5I_MAX_LOG_PKEY_SUP)]; + struct qpn_to_netdev *node; + + hlist_for_each_entry(node, h, hlist) { + if (node->underlay_qpn == qpn) + return node; + } + + return NULL; +} + +int mlx5i_pkey_add_qpn(struct net_device *netdev, u32 qpn) +{ + struct mlx5i_priv *ipriv = netdev_priv(netdev); + struct mlx5i_pkey_qpn_ht *ht = ipriv->qpn_htbl; + u8 key = hash_32(qpn, MLX5I_MAX_LOG_PKEY_SUP); + struct qpn_to_netdev *new_node; + + new_node = kzalloc(sizeof(*new_node), GFP_KERNEL); + if (!new_node) + return -ENOMEM; + + new_node->netdev = netdev; + new_node->underlay_qpn = qpn; + spin_lock_bh(&ht->ht_lock); + hlist_add_head(&new_node->hlist, &ht->buckets[key]); + spin_unlock_bh(&ht->ht_lock); + + return 0; +} + +int mlx5i_pkey_del_qpn(struct net_device *netdev, u32 qpn) +{ + struct mlx5e_priv *epriv = mlx5i_epriv(netdev); + struct mlx5i_priv *ipriv = epriv->ppriv; + struct mlx5i_pkey_qpn_ht *ht = ipriv->qpn_htbl; + struct qpn_to_netdev *node; + + node = mlx5i_find_qpn_to_netdev_node(ht->buckets, qpn); + if (!node) { + mlx5_core_warn(epriv->mdev, "QPN to netdev delete from HT failed\n"); + return -EINVAL; + } + + spin_lock_bh(&ht->ht_lock); + hlist_del_init(&node->hlist); + spin_unlock_bh(&ht->ht_lock); + kfree(node); + + return 0; +} + +struct net_device *mlx5i_pkey_get_netdev(struct net_device *netdev, u32 qpn) +{ + struct mlx5i_priv *ipriv = netdev_priv(netdev); + struct qpn_to_netdev *node; + + node = mlx5i_find_qpn_to_netdev_node(ipriv->qpn_htbl->buckets, qpn); + if (!node) + return NULL; + + return node->netdev; +} + +static int mlx5i_pkey_open(struct net_device *netdev); +static int mlx5i_pkey_close(struct net_device *netdev); +static int mlx5i_pkey_dev_init(struct net_device *dev); +static void mlx5i_pkey_dev_cleanup(struct net_device *netdev); +static int mlx5i_pkey_change_mtu(struct net_device *netdev, int new_mtu); + +static const struct net_device_ops mlx5i_pkey_netdev_ops = { + .ndo_open = mlx5i_pkey_open, + .ndo_stop = mlx5i_pkey_close, + .ndo_init = mlx5i_pkey_dev_init, + .ndo_uninit = mlx5i_pkey_dev_cleanup, + .ndo_change_mtu = mlx5i_pkey_change_mtu, +}; + +/* Child NDOs */ +static int mlx5i_pkey_dev_init(struct net_device *dev) +{ + struct mlx5e_priv *priv = mlx5i_epriv(dev); + struct mlx5i_priv *ipriv, *parent_ipriv; + struct net_device *parent_dev; + int parent_ifindex; + + ipriv = priv->ppriv; + + /* Get QPN to netdevice hash table from parent */ + parent_ifindex = dev->netdev_ops->ndo_get_iflink(dev); + parent_dev = dev_get_by_index(dev_net(dev), parent_ifindex); + if (!parent_dev) { + mlx5_core_warn(priv->mdev, "failed to get parent device\n"); + return -EINVAL; + } + + parent_ipriv = netdev_priv(parent_dev); + ipriv->qpn_htbl = parent_ipriv->qpn_htbl; + dev_put(parent_dev); + + return mlx5i_dev_init(dev); +} + +static void mlx5i_pkey_dev_cleanup(struct net_device *netdev) +{ + return mlx5i_dev_cleanup(netdev); +} + +static int mlx5i_pkey_open(struct net_device *netdev) +{ + struct mlx5e_priv *epriv = mlx5i_epriv(netdev); + struct mlx5i_priv *ipriv = epriv->ppriv; + struct mlx5_core_dev *mdev = epriv->mdev; + int err; + + mutex_lock(&epriv->state_lock); + + set_bit(MLX5E_STATE_OPENED, &epriv->state); + + err = mlx5i_init_underlay_qp(epriv); + if (err) { + mlx5_core_warn(mdev, "prepare child underlay qp state failed, %d\n", err); + goto err_release_lock; + } + + err = mlx5_fs_add_rx_underlay_qpn(mdev, ipriv->qp.qpn); + if (err) { + mlx5_core_warn(mdev, "attach child underlay qp to ft failed, %d\n", err); + goto err_unint_underlay_qp; + } + + err = mlx5e_create_tis(mdev, 0 /* tc */, ipriv->qp.qpn, &epriv->tisn[0]); + if (err) { + mlx5_core_warn(mdev, "create child tis failed, %d\n", err); + goto err_remove_rx_uderlay_qp; + } + + err = mlx5e_open_channels(epriv, &epriv->channels); + if (err) { + mlx5_core_warn(mdev, "opening child channels failed, %d\n", err); + goto err_clear_state_opened_flag; + } + mlx5e_refresh_tirs(epriv, false); + mlx5e_activate_priv_channels(epriv); + mutex_unlock(&epriv->state_lock); + + return 0; + +err_clear_state_opened_flag: + mlx5e_destroy_tis(mdev, epriv->tisn[0]); +err_remove_rx_uderlay_qp: + mlx5_fs_remove_rx_underlay_qpn(mdev, ipriv->qp.qpn); +err_unint_underlay_qp: + mlx5i_uninit_underlay_qp(epriv); +err_release_lock: + clear_bit(MLX5E_STATE_OPENED, &epriv->state); + mutex_unlock(&epriv->state_lock); + return err; +} + +static int mlx5i_pkey_close(struct net_device *netdev) +{ + struct mlx5e_priv *priv = mlx5i_epriv(netdev); + struct mlx5i_priv *ipriv = priv->ppriv; + struct mlx5_core_dev *mdev = priv->mdev; + + mutex_lock(&priv->state_lock); + + if (!test_bit(MLX5E_STATE_OPENED, &priv->state)) + goto unlock; + + clear_bit(MLX5E_STATE_OPENED, &priv->state); + + netif_carrier_off(priv->netdev); + mlx5_fs_remove_rx_underlay_qpn(mdev, ipriv->qp.qpn); + mlx5i_uninit_underlay_qp(priv); + mlx5e_deactivate_priv_channels(priv); + mlx5e_close_channels(&priv->channels); + mlx5e_destroy_tis(mdev, priv->tisn[0]); +unlock: + mutex_unlock(&priv->state_lock); + return 0; +} + +static int mlx5i_pkey_change_mtu(struct net_device *netdev, int new_mtu) +{ + struct mlx5e_priv *priv = mlx5i_epriv(netdev); + + mutex_lock(&priv->state_lock); + netdev->mtu = new_mtu; + mutex_unlock(&priv->state_lock); + + return 0; +} + +/* Called directly after IPoIB netdevice was created to initialize SW structs */ +static void mlx5i_pkey_init(struct mlx5_core_dev *mdev, + struct net_device *netdev, + const struct mlx5e_profile *profile, + void *ppriv) +{ + struct mlx5e_priv *priv = mlx5i_epriv(netdev); + + mlx5i_init(mdev, netdev, profile, ppriv); + + /* Override parent ndo */ + netdev->netdev_ops = &mlx5i_pkey_netdev_ops; + + /* Set child limited ethtool support */ + netdev->ethtool_ops = &mlx5i_pkey_ethtool_ops; + + /* Use dummy rqs */ + priv->channels.params.log_rq_size = MLX5E_PARAMS_MINIMUM_LOG_RQ_SIZE; +} + +/* Called directly before IPoIB netdevice is destroyed to cleanup SW structs */ +static void mlx5i_pkey_cleanup(struct mlx5e_priv *priv) +{ + /* Do nothing .. */ +} + +static int mlx5i_pkey_init_tx(struct mlx5e_priv *priv) +{ + struct mlx5i_priv *ipriv = priv->ppriv; + int err; + + err = mlx5i_create_underlay_qp(priv->mdev, &ipriv->qp); + if (err) { + mlx5_core_warn(priv->mdev, "create child underlay QP failed, %d\n", err); + return err; + } + + return 0; +} + +static void mlx5i_pkey_cleanup_tx(struct mlx5e_priv *priv) +{ + struct mlx5i_priv *ipriv = priv->ppriv; + + mlx5i_destroy_underlay_qp(priv->mdev, &ipriv->qp); +} + +static int mlx5i_pkey_init_rx(struct mlx5e_priv *priv) +{ + /* Since the rx resources are shared between child and parent, the + * parent interface is taking care of rx resource allocation and init + */ + return 0; +} + +static void mlx5i_pkey_cleanup_rx(struct mlx5e_priv *priv) +{ + /* Since the rx resources are shared between child and parent, the + * parent interface is taking care of rx resource free and de-init + */ +} + +static const struct mlx5e_profile mlx5i_pkey_nic_profile = { + .init = mlx5i_pkey_init, + .cleanup = mlx5i_pkey_cleanup, + .init_tx = mlx5i_pkey_init_tx, + .cleanup_tx = mlx5i_pkey_cleanup_tx, + .init_rx = mlx5i_pkey_init_rx, + .cleanup_rx = mlx5i_pkey_cleanup_rx, + .enable = NULL, + .disable = NULL, + .update_stats = NULL, + .max_nch = mlx5e_get_max_num_channels, + .rx_handlers.handle_rx_cqe = mlx5i_handle_rx_cqe, + .rx_handlers.handle_rx_cqe_mpwqe = NULL, /* Not supported */ + .max_tc = MLX5I_MAX_NUM_TC, +}; + +const struct mlx5e_profile *mlx5i_pkey_get_profile(void) +{ + return &mlx5i_pkey_nic_profile; +} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c new file mode 100644 index 000000000000..fa8aed62b231 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c @@ -0,0 +1,525 @@ +/* + * Copyright (c) 2015, Mellanox Technologies. All rights reserved. + * + * This software is available to you under a choice of one of two + * licenses. You may choose to be licensed under the terms of the GNU + * General Public License (GPL) Version 2, available from the file + * COPYING in the main directory of this source tree, or the + * OpenIB.org BSD license below: + * + * Redistribution and use in source and binary forms, with or + * without modification, are permitted provided that the following + * conditions are met: + * + * - Redistributions of source code must retain the above + * copyright notice, this list of conditions and the following + * disclaimer. + * + * - Redistributions in binary form must reproduce the above + * copyright notice, this list of conditions and the following + * disclaimer in the documentation and/or other materials + * provided with the distribution. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND + * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS + * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN + * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN + * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE + * SOFTWARE. + */ + +#include <linux/clocksource.h> +#include "en.h" + +enum { + MLX5_CYCLES_SHIFT = 23 +}; + +enum { + MLX5_PIN_MODE_IN = 0x0, + MLX5_PIN_MODE_OUT = 0x1, +}; + +enum { + MLX5_OUT_PATTERN_PULSE = 0x0, + MLX5_OUT_PATTERN_PERIODIC = 0x1, +}; + +enum { + MLX5_EVENT_MODE_DISABLE = 0x0, + MLX5_EVENT_MODE_REPETETIVE = 0x1, + MLX5_EVENT_MODE_ONCE_TILL_ARM = 0x2, +}; + +enum { + MLX5_MTPPS_FS_ENABLE = BIT(0x0), + MLX5_MTPPS_FS_PATTERN = BIT(0x2), + MLX5_MTPPS_FS_PIN_MODE = BIT(0x3), + MLX5_MTPPS_FS_TIME_STAMP = BIT(0x4), + MLX5_MTPPS_FS_OUT_PULSE_DURATION = BIT(0x5), + MLX5_MTPPS_FS_ENH_OUT_PER_ADJ = BIT(0x7), +}; + +static u64 read_internal_timer(const struct cyclecounter *cc) +{ + struct mlx5_clock *clock = container_of(cc, struct mlx5_clock, cycles); + struct mlx5_core_dev *mdev = container_of(clock, struct mlx5_core_dev, + clock); + + return mlx5_read_internal_timer(mdev) & cc->mask; +} + +static void mlx5_pps_out(struct work_struct *work) +{ + struct mlx5_pps *pps_info = container_of(work, struct mlx5_pps, + out_work); + struct mlx5_clock *clock = container_of(pps_info, struct mlx5_clock, + pps_info); + struct mlx5_core_dev *mdev = container_of(clock, struct mlx5_core_dev, + clock); + u32 in[MLX5_ST_SZ_DW(mtpps_reg)] = {0}; + unsigned long flags; + int i; + + for (i = 0; i < clock->ptp_info.n_pins; i++) { + u64 tstart; + + write_lock_irqsave(&clock->lock, flags); + tstart = clock->pps_info.start[i]; + clock->pps_info.start[i] = 0; + write_unlock_irqrestore(&clock->lock, flags); + if (!tstart) + continue; + + MLX5_SET(mtpps_reg, in, pin, i); + MLX5_SET64(mtpps_reg, in, time_stamp, tstart); + MLX5_SET(mtpps_reg, in, field_select, MLX5_MTPPS_FS_TIME_STAMP); + mlx5_set_mtpps(mdev, in, sizeof(in)); + } +} + +static void mlx5_timestamp_overflow(struct work_struct *work) +{ + struct delayed_work *dwork = to_delayed_work(work); + struct mlx5_clock *clock = container_of(dwork, struct mlx5_clock, + overflow_work); + unsigned long flags; + + write_lock_irqsave(&clock->lock, flags); + timecounter_read(&clock->tc); + write_unlock_irqrestore(&clock->lock, flags); + schedule_delayed_work(&clock->overflow_work, clock->overflow_period); +} + +static int mlx5_ptp_settime(struct ptp_clock_info *ptp, + const struct timespec64 *ts) +{ + struct mlx5_clock *clock = container_of(ptp, struct mlx5_clock, + ptp_info); + u64 ns = timespec64_to_ns(ts); + unsigned long flags; + + write_lock_irqsave(&clock->lock, flags); + timecounter_init(&clock->tc, &clock->cycles, ns); + write_unlock_irqrestore(&clock->lock, flags); + + return 0; +} + +static int mlx5_ptp_gettime(struct ptp_clock_info *ptp, struct timespec64 *ts) +{ + struct mlx5_clock *clock = container_of(ptp, struct mlx5_clock, + ptp_info); + u64 ns; + unsigned long flags; + + write_lock_irqsave(&clock->lock, flags); + ns = timecounter_read(&clock->tc); + write_unlock_irqrestore(&clock->lock, flags); + + *ts = ns_to_timespec64(ns); + + return 0; +} + +static int mlx5_ptp_adjtime(struct ptp_clock_info *ptp, s64 delta) +{ + struct mlx5_clock *clock = container_of(ptp, struct mlx5_clock, + ptp_info); + unsigned long flags; + + write_lock_irqsave(&clock->lock, flags); + timecounter_adjtime(&clock->tc, delta); + write_unlock_irqrestore(&clock->lock, flags); + + return 0; +} + +static int mlx5_ptp_adjfreq(struct ptp_clock_info *ptp, s32 delta) +{ + u64 adj; + u32 diff; + unsigned long flags; + int neg_adj = 0; + struct mlx5_clock *clock = container_of(ptp, struct mlx5_clock, + ptp_info); + + if (delta < 0) { + neg_adj = 1; + delta = -delta; + } + + adj = clock->nominal_c_mult; + adj *= delta; + diff = div_u64(adj, 1000000000ULL); + + write_lock_irqsave(&clock->lock, flags); + timecounter_read(&clock->tc); + clock->cycles.mult = neg_adj ? clock->nominal_c_mult - diff : + clock->nominal_c_mult + diff; + write_unlock_irqrestore(&clock->lock, flags); + + return 0; +} + +static int mlx5_extts_configure(struct ptp_clock_info *ptp, + struct ptp_clock_request *rq, + int on) +{ + struct mlx5_clock *clock = + container_of(ptp, struct mlx5_clock, ptp_info); + struct mlx5_core_dev *mdev = + container_of(clock, struct mlx5_core_dev, clock); + u32 in[MLX5_ST_SZ_DW(mtpps_reg)] = {0}; + u32 field_select = 0; + u8 pin_mode = 0; + u8 pattern = 0; + int pin = -1; + int err = 0; + + if (!MLX5_PPS_CAP(mdev)) + return -EOPNOTSUPP; + + if (rq->extts.index >= clock->ptp_info.n_pins) + return -EINVAL; + + if (on) { + pin = ptp_find_pin(clock->ptp, PTP_PF_EXTTS, rq->extts.index); + if (pin < 0) + return -EBUSY; + pin_mode = MLX5_PIN_MODE_IN; + pattern = !!(rq->extts.flags & PTP_FALLING_EDGE); + field_select = MLX5_MTPPS_FS_PIN_MODE | + MLX5_MTPPS_FS_PATTERN | + MLX5_MTPPS_FS_ENABLE; + } else { + pin = rq->extts.index; + field_select = MLX5_MTPPS_FS_ENABLE; + } + + MLX5_SET(mtpps_reg, in, pin, pin); + MLX5_SET(mtpps_reg, in, pin_mode, pin_mode); + MLX5_SET(mtpps_reg, in, pattern, pattern); + MLX5_SET(mtpps_reg, in, enable, on); + MLX5_SET(mtpps_reg, in, field_select, field_select); + + err = mlx5_set_mtpps(mdev, in, sizeof(in)); + if (err) + return err; + + return mlx5_set_mtppse(mdev, pin, 0, + MLX5_EVENT_MODE_REPETETIVE & on); +} + +static int mlx5_perout_configure(struct ptp_clock_info *ptp, + struct ptp_clock_request *rq, + int on) +{ + struct mlx5_clock *clock = + container_of(ptp, struct mlx5_clock, ptp_info); + struct mlx5_core_dev *mdev = + container_of(clock, struct mlx5_core_dev, clock); + u32 in[MLX5_ST_SZ_DW(mtpps_reg)] = {0}; + u64 nsec_now, nsec_delta, time_stamp = 0; + u64 cycles_now, cycles_delta; + struct timespec64 ts; + unsigned long flags; + u32 field_select = 0; + u8 pin_mode = 0; + u8 pattern = 0; + int pin = -1; + int err = 0; + s64 ns; + + if (!MLX5_PPS_CAP(mdev)) + return -EOPNOTSUPP; + + if (rq->perout.index >= clock->ptp_info.n_pins) + return -EINVAL; + + if (on) { + pin = ptp_find_pin(clock->ptp, PTP_PF_PEROUT, + rq->perout.index); + if (pin < 0) + return -EBUSY; + + pin_mode = MLX5_PIN_MODE_OUT; + pattern = MLX5_OUT_PATTERN_PERIODIC; + ts.tv_sec = rq->perout.period.sec; + ts.tv_nsec = rq->perout.period.nsec; + ns = timespec64_to_ns(&ts); + + if ((ns >> 1) != 500000000LL) + return -EINVAL; + + ts.tv_sec = rq->perout.start.sec; + ts.tv_nsec = rq->perout.start.nsec; + ns = timespec64_to_ns(&ts); + cycles_now = mlx5_read_internal_timer(mdev); + write_lock_irqsave(&clock->lock, flags); + nsec_now = timecounter_cyc2time(&clock->tc, cycles_now); + nsec_delta = ns - nsec_now; + cycles_delta = div64_u64(nsec_delta << clock->cycles.shift, + clock->cycles.mult); + write_unlock_irqrestore(&clock->lock, flags); + time_stamp = cycles_now + cycles_delta; + field_select = MLX5_MTPPS_FS_PIN_MODE | + MLX5_MTPPS_FS_PATTERN | + MLX5_MTPPS_FS_ENABLE | + MLX5_MTPPS_FS_TIME_STAMP; + } else { + pin = rq->perout.index; + field_select = MLX5_MTPPS_FS_ENABLE; + } + + MLX5_SET(mtpps_reg, in, pin, pin); + MLX5_SET(mtpps_reg, in, pin_mode, pin_mode); + MLX5_SET(mtpps_reg, in, pattern, pattern); + MLX5_SET(mtpps_reg, in, enable, on); + MLX5_SET64(mtpps_reg, in, time_stamp, time_stamp); + MLX5_SET(mtpps_reg, in, field_select, field_select); + + err = mlx5_set_mtpps(mdev, in, sizeof(in)); + if (err) + return err; + + return mlx5_set_mtppse(mdev, pin, 0, + MLX5_EVENT_MODE_REPETETIVE & on); +} + +static int mlx5_pps_configure(struct ptp_clock_info *ptp, + struct ptp_clock_request *rq, + int on) +{ + struct mlx5_clock *clock = + container_of(ptp, struct mlx5_clock, ptp_info); + + clock->pps_info.enabled = !!on; + return 0; +} + +static int mlx5_ptp_enable(struct ptp_clock_info *ptp, + struct ptp_clock_request *rq, + int on) +{ + switch (rq->type) { + case PTP_CLK_REQ_EXTTS: + return mlx5_extts_configure(ptp, rq, on); + case PTP_CLK_REQ_PEROUT: + return mlx5_perout_configure(ptp, rq, on); + case PTP_CLK_REQ_PPS: + return mlx5_pps_configure(ptp, rq, on); + default: + return -EOPNOTSUPP; + } + return 0; +} + +static int mlx5_ptp_verify(struct ptp_clock_info *ptp, unsigned int pin, + enum ptp_pin_function func, unsigned int chan) +{ + return (func == PTP_PF_PHYSYNC) ? -EOPNOTSUPP : 0; +} + +static const struct ptp_clock_info mlx5_ptp_clock_info = { + .owner = THIS_MODULE, + .name = "mlx5_p2p", + .max_adj = 100000000, + .n_alarm = 0, + .n_ext_ts = 0, + .n_per_out = 0, + .n_pins = 0, + .pps = 0, + .adjfreq = mlx5_ptp_adjfreq, + .adjtime = mlx5_ptp_adjtime, + .gettime64 = mlx5_ptp_gettime, + .settime64 = mlx5_ptp_settime, + .enable = NULL, + .verify = NULL, +}; + +static int mlx5_init_pin_config(struct mlx5_clock *clock) +{ + int i; + + clock->ptp_info.pin_config = + kzalloc(sizeof(*clock->ptp_info.pin_config) * + clock->ptp_info.n_pins, GFP_KERNEL); + if (!clock->ptp_info.pin_config) + return -ENOMEM; + clock->ptp_info.enable = mlx5_ptp_enable; + clock->ptp_info.verify = mlx5_ptp_verify; + clock->ptp_info.pps = 1; + + for (i = 0; i < clock->ptp_info.n_pins; i++) { + snprintf(clock->ptp_info.pin_config[i].name, + sizeof(clock->ptp_info.pin_config[i].name), + "mlx5_pps%d", i); + clock->ptp_info.pin_config[i].index = i; + clock->ptp_info.pin_config[i].func = PTP_PF_NONE; + clock->ptp_info.pin_config[i].chan = i; + } + + return 0; +} + +static void mlx5_get_pps_caps(struct mlx5_core_dev *mdev) +{ + struct mlx5_clock *clock = &mdev->clock; + u32 out[MLX5_ST_SZ_DW(mtpps_reg)] = {0}; + + mlx5_query_mtpps(mdev, out, sizeof(out)); + + clock->ptp_info.n_pins = MLX5_GET(mtpps_reg, out, + cap_number_of_pps_pins); + clock->ptp_info.n_ext_ts = MLX5_GET(mtpps_reg, out, + cap_max_num_of_pps_in_pins); + clock->ptp_info.n_per_out = MLX5_GET(mtpps_reg, out, + cap_max_num_of_pps_out_pins); + + clock->pps_info.pin_caps[0] = MLX5_GET(mtpps_reg, out, cap_pin_0_mode); + clock->pps_info.pin_caps[1] = MLX5_GET(mtpps_reg, out, cap_pin_1_mode); + clock->pps_info.pin_caps[2] = MLX5_GET(mtpps_reg, out, cap_pin_2_mode); + clock->pps_info.pin_caps[3] = MLX5_GET(mtpps_reg, out, cap_pin_3_mode); + clock->pps_info.pin_caps[4] = MLX5_GET(mtpps_reg, out, cap_pin_4_mode); + clock->pps_info.pin_caps[5] = MLX5_GET(mtpps_reg, out, cap_pin_5_mode); + clock->pps_info.pin_caps[6] = MLX5_GET(mtpps_reg, out, cap_pin_6_mode); + clock->pps_info.pin_caps[7] = MLX5_GET(mtpps_reg, out, cap_pin_7_mode); +} + +void mlx5_pps_event(struct mlx5_core_dev *mdev, + struct mlx5_eqe *eqe) +{ + struct mlx5_clock *clock = &mdev->clock; + struct ptp_clock_event ptp_event; + struct timespec64 ts; + u64 nsec_now, nsec_delta; + u64 cycles_now, cycles_delta; + int pin = eqe->data.pps.pin; + s64 ns; + unsigned long flags; + + switch (clock->ptp_info.pin_config[pin].func) { + case PTP_PF_EXTTS: + if (clock->pps_info.enabled) { + ptp_event.type = PTP_CLOCK_PPSUSR; + ptp_event.pps_times.ts_real = ns_to_timespec64(eqe->data.pps.time_stamp); + } else { + ptp_event.type = PTP_CLOCK_EXTTS; + } + ptp_clock_event(clock->ptp, &ptp_event); + break; + case PTP_PF_PEROUT: + mlx5_ptp_gettime(&clock->ptp_info, &ts); + cycles_now = mlx5_read_internal_timer(mdev); + ts.tv_sec += 1; + ts.tv_nsec = 0; + ns = timespec64_to_ns(&ts); + write_lock_irqsave(&clock->lock, flags); + nsec_now = timecounter_cyc2time(&clock->tc, cycles_now); + nsec_delta = ns - nsec_now; + cycles_delta = div64_u64(nsec_delta << clock->cycles.shift, + clock->cycles.mult); + clock->pps_info.start[pin] = cycles_now + cycles_delta; + schedule_work(&clock->pps_info.out_work); + write_unlock_irqrestore(&clock->lock, flags); + break; + default: + mlx5_core_err(mdev, " Unhandled event\n"); + } +} + +void mlx5_init_clock(struct mlx5_core_dev *mdev) +{ + struct mlx5_clock *clock = &mdev->clock; + u64 ns; + u64 frac = 0; + u32 dev_freq; + + dev_freq = MLX5_CAP_GEN(mdev, device_frequency_khz); + if (!dev_freq) { + mlx5_core_warn(mdev, "invalid device_frequency_khz, aborting HW clock init\n"); + return; + } + rwlock_init(&clock->lock); + clock->cycles.read = read_internal_timer; + clock->cycles.shift = MLX5_CYCLES_SHIFT; + clock->cycles.mult = clocksource_khz2mult(dev_freq, + clock->cycles.shift); + clock->nominal_c_mult = clock->cycles.mult; + clock->cycles.mask = CLOCKSOURCE_MASK(41); + + timecounter_init(&clock->tc, &clock->cycles, + ktime_to_ns(ktime_get_real())); + + /* Calculate period in seconds to call the overflow watchdog - to make + * sure counter is checked at least once every wrap around. + */ + ns = cyclecounter_cyc2ns(&clock->cycles, clock->cycles.mask, + frac, &frac); + do_div(ns, NSEC_PER_SEC / 2 / HZ); + clock->overflow_period = ns; + + INIT_WORK(&clock->pps_info.out_work, mlx5_pps_out); + INIT_DELAYED_WORK(&clock->overflow_work, mlx5_timestamp_overflow); + if (clock->overflow_period) + schedule_delayed_work(&clock->overflow_work, 0); + else + mlx5_core_warn(mdev, "invalid overflow period, overflow_work is not scheduled\n"); + + /* Configure the PHC */ + clock->ptp_info = mlx5_ptp_clock_info; + + /* Initialize 1PPS data structures */ + if (MLX5_PPS_CAP(mdev)) + mlx5_get_pps_caps(mdev); + if (clock->ptp_info.n_pins) + mlx5_init_pin_config(clock); + + clock->ptp = ptp_clock_register(&clock->ptp_info, + &mdev->pdev->dev); + if (IS_ERR(clock->ptp)) { + mlx5_core_warn(mdev, "ptp_clock_register failed %ld\n", + PTR_ERR(clock->ptp)); + clock->ptp = NULL; + } +} + +void mlx5_cleanup_clock(struct mlx5_core_dev *mdev) +{ + struct mlx5_clock *clock = &mdev->clock; + + if (!MLX5_CAP_GEN(mdev, device_frequency_khz)) + return; + + if (clock->ptp) { + ptp_clock_unregister(clock->ptp); + clock->ptp = NULL; + } + + cancel_work_sync(&clock->pps_info.out_work); + cancel_delayed_work_sync(&clock->overflow_work); + kfree(clock->ptp_info.pin_config); +} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.h b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.h new file mode 100644 index 000000000000..a8eecedd46c2 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.h @@ -0,0 +1,51 @@ +/* + * Copyright (c) 2017, Mellanox Technologies, Ltd. All rights reserved. + * + * This software is available to you under a choice of one of two + * licenses. You may choose to be licensed under the terms of the GNU + * General Public License (GPL) Version 2, available from the file + * COPYING in the main directory of this source tree, or the + * OpenIB.org BSD license below: + * + * Redistribution and use in source and binary forms, with or + * without modification, are permitted provided that the following + * conditions are met: + * + * - Redistributions of source code must retain the above + * copyright notice, this list of conditions and the following + * disclaimer. + * + * - Redistributions in binary form must reproduce the above + * copyright notice, this list of conditions and the following + * disclaimer in the documentation and/or other materials + * provided with the distribution. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND + * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS + * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN + * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN + * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE + * SOFTWARE. + */ + +#ifndef __LIB_CLOCK_H__ +#define __LIB_CLOCK_H__ + +void mlx5_init_clock(struct mlx5_core_dev *mdev); +void mlx5_cleanup_clock(struct mlx5_core_dev *mdev); + +static inline ktime_t mlx5_timecounter_cyc2time(struct mlx5_clock *clock, + u64 timestamp) +{ + u64 nsec; + + read_lock(&clock->lock); + nsec = timecounter_cyc2time(&clock->tc, timestamp); + read_unlock(&clock->lock); + + return ns_to_ktime(nsec); +} + +#endif diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index 0d2c8dcd6eae..ecbe9fad22d8 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -59,6 +59,7 @@ #include "lib/mlx5.h" #include "fpga/core.h" #include "accel/ipsec.h" +#include "lib/clock.h" MODULE_AUTHOR("Eli Cohen <eli@mellanox.com>"); MODULE_DESCRIPTION("Mellanox Connect-IB, ConnectX-4 core driver"); @@ -889,6 +890,8 @@ static int mlx5_init_once(struct mlx5_core_dev *dev, struct mlx5_priv *priv) mlx5_init_reserved_gids(dev); + mlx5_init_clock(dev); + err = mlx5_init_rl_table(dev); if (err) { dev_err(&pdev->dev, "Failed to init rate limiting\n"); @@ -949,6 +952,7 @@ static void mlx5_cleanup_once(struct mlx5_core_dev *dev) mlx5_eswitch_cleanup(dev->priv.eswitch); mlx5_mpfs_cleanup(dev); mlx5_cleanup_rl_table(dev); + mlx5_cleanup_clock(dev); mlx5_cleanup_reserved_gids(dev); mlx5_cleanup_mkey_table(dev); mlx5_cleanup_srq_table(dev); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h index b7c2900b75f9..8f00de2fe283 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h @@ -93,6 +93,7 @@ void mlx5_core_event(struct mlx5_core_dev *dev, enum mlx5_dev_event event, unsigned long param); void mlx5_core_page_fault(struct mlx5_core_dev *dev, struct mlx5_pagefault *pfault); +void mlx5_pps_event(struct mlx5_core_dev *dev, struct mlx5_eqe *eqe); void mlx5_port_module_event(struct mlx5_core_dev *dev, struct mlx5_eqe *eqe); void mlx5_enter_error_state(struct mlx5_core_dev *dev, bool force); void mlx5_disable_device(struct mlx5_core_dev *dev); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sriov.c b/drivers/net/ethernet/mellanox/mlx5/core/sriov.c index 6c48e9959b65..2a8b529ce6dd 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/sriov.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/sriov.c @@ -109,7 +109,7 @@ static int mlx5_device_enable_sriov(struct mlx5_core_dev *dev, int num_vfs) mlx5_core_warn(dev, "failed to restore VF %d settings, err %d\n", vf, err); - continue; + continue; } } mlx5_core_dbg(dev, "successfully enabled VF* %d\n", vf); diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c index 2cfb3f5d092d..032089efc1a0 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c @@ -2723,6 +2723,7 @@ static void mlxsw_sp_nexthop_type_fini(struct mlxsw_sp *mlxsw_sp, mlxsw_sp_nexthop_rif_fini(nh); break; case MLXSW_SP_NEXTHOP_TYPE_IPIP: + mlxsw_sp_nexthop_rif_fini(nh); mlxsw_sp_nexthop_ipip_fini(mlxsw_sp, nh); break; } @@ -2742,7 +2743,11 @@ static int mlxsw_sp_nexthop4_type_init(struct mlxsw_sp *mlxsw_sp, router->ipip_ops_arr[ipipt]->can_offload(mlxsw_sp, dev, MLXSW_SP_L3_PROTO_IPV4)) { nh->type = MLXSW_SP_NEXTHOP_TYPE_IPIP; - return mlxsw_sp_nexthop_ipip_init(mlxsw_sp, ipipt, nh, dev); + err = mlxsw_sp_nexthop_ipip_init(mlxsw_sp, ipipt, nh, dev); + if (err) + return err; + mlxsw_sp_nexthop_rif_init(nh, &nh->ipip_entry->ol_lb->common); + return 0; } nh->type = MLXSW_SP_NEXTHOP_TYPE_ETH; @@ -4009,7 +4014,11 @@ static int mlxsw_sp_nexthop6_type_init(struct mlxsw_sp *mlxsw_sp, router->ipip_ops_arr[ipipt]->can_offload(mlxsw_sp, dev, MLXSW_SP_L3_PROTO_IPV6)) { nh->type = MLXSW_SP_NEXTHOP_TYPE_IPIP; - return mlxsw_sp_nexthop_ipip_init(mlxsw_sp, ipipt, nh, dev); + err = mlxsw_sp_nexthop_ipip_init(mlxsw_sp, ipipt, nh, dev); + if (err) + return err; + mlxsw_sp_nexthop_rif_init(nh, &nh->ipip_entry->ol_lb->common); + return 0; } nh->type = MLXSW_SP_NEXTHOP_TYPE_ETH; @@ -5068,6 +5077,7 @@ mlxsw_sp_rif_create(struct mlxsw_sp *mlxsw_sp, vr = mlxsw_sp_vr_get(mlxsw_sp, tb_id ? : RT_TABLE_MAIN); if (IS_ERR(vr)) return ERR_CAST(vr); + vr->rif_count++; err = mlxsw_sp_rif_index_alloc(mlxsw_sp, &rif_index); if (err) @@ -5099,7 +5109,6 @@ mlxsw_sp_rif_create(struct mlxsw_sp *mlxsw_sp, mlxsw_sp_rif_counters_alloc(rif); mlxsw_sp->router->rifs[rif_index] = rif; - vr->rif_count++; return rif; @@ -5110,6 +5119,7 @@ err_fid_get: kfree(rif); err_rif_alloc: err_rif_index_alloc: + vr->rif_count--; mlxsw_sp_vr_put(vr); return ERR_PTR(err); } @@ -5124,7 +5134,6 @@ void mlxsw_sp_rif_destroy(struct mlxsw_sp_rif *rif) mlxsw_sp_router_rif_gone_sync(mlxsw_sp, rif); vr = &mlxsw_sp->router->vrs[rif->vr_id]; - vr->rif_count--; mlxsw_sp->router->rifs[rif->rif_index] = NULL; mlxsw_sp_rif_counters_free(rif); ops->deconfigure(rif); @@ -5132,6 +5141,7 @@ void mlxsw_sp_rif_destroy(struct mlxsw_sp_rif *rif) /* Loopback RIFs are not associated with a FID. */ mlxsw_sp_fid_put(fid); kfree(rif); + vr->rif_count--; mlxsw_sp_vr_put(vr); } diff --git a/drivers/net/ethernet/qualcomm/emac/emac-mac.c b/drivers/net/ethernet/qualcomm/emac/emac-mac.c index 0ea3ca09c689..3ed9033e56db 100644 --- a/drivers/net/ethernet/qualcomm/emac/emac-mac.c +++ b/drivers/net/ethernet/qualcomm/emac/emac-mac.c @@ -898,7 +898,8 @@ static void emac_mac_rx_descs_refill(struct emac_adapter *adpt, curr_rxbuf->dma_addr = dma_map_single(adpt->netdev->dev.parent, skb->data, - curr_rxbuf->length, DMA_FROM_DEVICE); + adpt->rxbuf_size, DMA_FROM_DEVICE); + ret = dma_mapping_error(adpt->netdev->dev.parent, curr_rxbuf->dma_addr); if (ret) { diff --git a/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c b/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c index 98f22551eb45..1e33aea59f50 100644 --- a/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c +++ b/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c @@ -51,10 +51,7 @@ struct rmnet_walk_data { static int rmnet_is_real_dev_registered(const struct net_device *real_dev) { - rx_handler_func_t *rx_handler; - - rx_handler = rcu_dereference(real_dev->rx_handler); - return (rx_handler == rmnet_rx_handler); + return rcu_access_pointer(real_dev->rx_handler) == rmnet_rx_handler; } /* Needs rtnl lock */ diff --git a/drivers/net/ethernet/rocker/rocker_tlv.h b/drivers/net/ethernet/rocker/rocker_tlv.h index a63ef82e7c72..dfae3c9d57c6 100644 --- a/drivers/net/ethernet/rocker/rocker_tlv.h +++ b/drivers/net/ethernet/rocker/rocker_tlv.h @@ -139,40 +139,52 @@ rocker_tlv_start(struct rocker_desc_info *desc_info) int rocker_tlv_put(struct rocker_desc_info *desc_info, int attrtype, int attrlen, const void *data); -static inline int rocker_tlv_put_u8(struct rocker_desc_info *desc_info, - int attrtype, u8 value) +static inline int +rocker_tlv_put_u8(struct rocker_desc_info *desc_info, int attrtype, u8 value) { - return rocker_tlv_put(desc_info, attrtype, sizeof(u8), &value); + u8 tmp = value; /* work around GCC PR81715 */ + + return rocker_tlv_put(desc_info, attrtype, sizeof(u8), &tmp); } -static inline int rocker_tlv_put_u16(struct rocker_desc_info *desc_info, - int attrtype, u16 value) +static inline int +rocker_tlv_put_u16(struct rocker_desc_info *desc_info, int attrtype, u16 value) { - return rocker_tlv_put(desc_info, attrtype, sizeof(u16), &value); + u16 tmp = value; + + return rocker_tlv_put(desc_info, attrtype, sizeof(u16), &tmp); } -static inline int rocker_tlv_put_be16(struct rocker_desc_info *desc_info, - int attrtype, __be16 value) +static inline int +rocker_tlv_put_be16(struct rocker_desc_info *desc_info, int attrtype, __be16 value) { - return rocker_tlv_put(desc_info, attrtype, sizeof(__be16), &value); + __be16 tmp = value; + + return rocker_tlv_put(desc_info, attrtype, sizeof(__be16), &tmp); } -static inline int rocker_tlv_put_u32(struct rocker_desc_info *desc_info, - int attrtype, u32 value) +static inline int +rocker_tlv_put_u32(struct rocker_desc_info *desc_info, int attrtype, u32 value) { - return rocker_tlv_put(desc_info, attrtype, sizeof(u32), &value); + u32 tmp = value; + + return rocker_tlv_put(desc_info, attrtype, sizeof(u32), &tmp); } -static inline int rocker_tlv_put_be32(struct rocker_desc_info *desc_info, - int attrtype, __be32 value) +static inline int +rocker_tlv_put_be32(struct rocker_desc_info *desc_info, int attrtype, __be32 value) { - return rocker_tlv_put(desc_info, attrtype, sizeof(__be32), &value); + __be32 tmp = value; + + return rocker_tlv_put(desc_info, attrtype, sizeof(__be32), &tmp); } -static inline int rocker_tlv_put_u64(struct rocker_desc_info *desc_info, - int attrtype, u64 value) +static inline int +rocker_tlv_put_u64(struct rocker_desc_info *desc_info, int attrtype, u64 value) { - return rocker_tlv_put(desc_info, attrtype, sizeof(u64), &value); + u64 tmp = value; + + return rocker_tlv_put(desc_info, attrtype, sizeof(u64), &tmp); } static inline struct rocker_tlv * 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 dd6a2f9791cc..5efef8001edf 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-dwc-qos-eth.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-dwc-qos-eth.c @@ -511,6 +511,7 @@ static struct platform_driver dwc_eth_dwmac_driver = { .remove = dwc_eth_dwmac_remove, .driver = { .name = "dwc-eth-dwmac", + .pm = &stmmac_pltfr_pm_ops, .of_match_table = dwc_eth_dwmac_match, }, }; diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c index 99823f54696a..13133b30b575 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c @@ -83,6 +83,117 @@ struct rk_priv_data { (((tx) ? soc##_GMAC_TXCLK_DLY_ENABLE : soc##_GMAC_TXCLK_DLY_DISABLE) | \ ((rx) ? soc##_GMAC_RXCLK_DLY_ENABLE : soc##_GMAC_RXCLK_DLY_DISABLE)) +#define RK3128_GRF_MAC_CON0 0x0168 +#define RK3128_GRF_MAC_CON1 0x016c + +/* RK3128_GRF_MAC_CON0 */ +#define RK3128_GMAC_TXCLK_DLY_ENABLE GRF_BIT(14) +#define RK3128_GMAC_TXCLK_DLY_DISABLE GRF_CLR_BIT(14) +#define RK3128_GMAC_RXCLK_DLY_ENABLE GRF_BIT(15) +#define RK3128_GMAC_RXCLK_DLY_DISABLE GRF_CLR_BIT(15) +#define RK3128_GMAC_CLK_RX_DL_CFG(val) HIWORD_UPDATE(val, 0x7F, 7) +#define RK3128_GMAC_CLK_TX_DL_CFG(val) HIWORD_UPDATE(val, 0x7F, 0) + +/* RK3128_GRF_MAC_CON1 */ +#define RK3128_GMAC_PHY_INTF_SEL_RGMII \ + (GRF_BIT(6) | GRF_CLR_BIT(7) | GRF_CLR_BIT(8)) +#define RK3128_GMAC_PHY_INTF_SEL_RMII \ + (GRF_CLR_BIT(6) | GRF_CLR_BIT(7) | GRF_BIT(8)) +#define RK3128_GMAC_FLOW_CTRL GRF_BIT(9) +#define RK3128_GMAC_FLOW_CTRL_CLR GRF_CLR_BIT(9) +#define RK3128_GMAC_SPEED_10M GRF_CLR_BIT(10) +#define RK3128_GMAC_SPEED_100M GRF_BIT(10) +#define RK3128_GMAC_RMII_CLK_25M GRF_BIT(11) +#define RK3128_GMAC_RMII_CLK_2_5M GRF_CLR_BIT(11) +#define RK3128_GMAC_CLK_125M (GRF_CLR_BIT(12) | GRF_CLR_BIT(13)) +#define RK3128_GMAC_CLK_25M (GRF_BIT(12) | GRF_BIT(13)) +#define RK3128_GMAC_CLK_2_5M (GRF_CLR_BIT(12) | GRF_BIT(13)) +#define RK3128_GMAC_RMII_MODE GRF_BIT(14) +#define RK3128_GMAC_RMII_MODE_CLR GRF_CLR_BIT(14) + +static void rk3128_set_to_rgmii(struct rk_priv_data *bsp_priv, + int tx_delay, int rx_delay) +{ + struct device *dev = &bsp_priv->pdev->dev; + + if (IS_ERR(bsp_priv->grf)) { + dev_err(dev, "Missing rockchip,grf property\n"); + return; + } + + regmap_write(bsp_priv->grf, RK3128_GRF_MAC_CON1, + RK3128_GMAC_PHY_INTF_SEL_RGMII | + RK3128_GMAC_RMII_MODE_CLR); + regmap_write(bsp_priv->grf, RK3128_GRF_MAC_CON0, + DELAY_ENABLE(RK3128, tx_delay, rx_delay) | + RK3128_GMAC_CLK_RX_DL_CFG(rx_delay) | + RK3128_GMAC_CLK_TX_DL_CFG(tx_delay)); +} + +static void rk3128_set_to_rmii(struct rk_priv_data *bsp_priv) +{ + struct device *dev = &bsp_priv->pdev->dev; + + if (IS_ERR(bsp_priv->grf)) { + dev_err(dev, "Missing rockchip,grf property\n"); + return; + } + + regmap_write(bsp_priv->grf, RK3128_GRF_MAC_CON1, + RK3128_GMAC_PHY_INTF_SEL_RMII | RK3128_GMAC_RMII_MODE); +} + +static void rk3128_set_rgmii_speed(struct rk_priv_data *bsp_priv, int speed) +{ + struct device *dev = &bsp_priv->pdev->dev; + + if (IS_ERR(bsp_priv->grf)) { + dev_err(dev, "Missing rockchip,grf property\n"); + return; + } + + if (speed == 10) + regmap_write(bsp_priv->grf, RK3128_GRF_MAC_CON1, + RK3128_GMAC_CLK_2_5M); + else if (speed == 100) + regmap_write(bsp_priv->grf, RK3128_GRF_MAC_CON1, + RK3128_GMAC_CLK_25M); + else if (speed == 1000) + regmap_write(bsp_priv->grf, RK3128_GRF_MAC_CON1, + RK3128_GMAC_CLK_125M); + else + dev_err(dev, "unknown speed value for RGMII! speed=%d", speed); +} + +static void rk3128_set_rmii_speed(struct rk_priv_data *bsp_priv, int speed) +{ + struct device *dev = &bsp_priv->pdev->dev; + + if (IS_ERR(bsp_priv->grf)) { + dev_err(dev, "Missing rockchip,grf property\n"); + return; + } + + if (speed == 10) { + regmap_write(bsp_priv->grf, RK3128_GRF_MAC_CON1, + RK3128_GMAC_RMII_CLK_2_5M | + RK3128_GMAC_SPEED_10M); + } else if (speed == 100) { + regmap_write(bsp_priv->grf, RK3128_GRF_MAC_CON1, + RK3128_GMAC_RMII_CLK_25M | + RK3128_GMAC_SPEED_100M); + } else { + dev_err(dev, "unknown speed value for RMII! speed=%d", speed); + } +} + +static const struct rk_gmac_ops rk3128_ops = { + .set_to_rgmii = rk3128_set_to_rgmii, + .set_to_rmii = rk3128_set_to_rmii, + .set_rgmii_speed = rk3128_set_rgmii_speed, + .set_rmii_speed = rk3128_set_rmii_speed, +}; + #define RK3228_GRF_MAC_CON0 0x0900 #define RK3228_GRF_MAC_CON1 0x0904 @@ -1313,6 +1424,7 @@ static int rk_gmac_resume(struct device *dev) static SIMPLE_DEV_PM_OPS(rk_gmac_pm_ops, rk_gmac_suspend, rk_gmac_resume); static const struct of_device_id rk_gmac_dwmac_match[] = { + { .compatible = "rockchip,rk3128-gmac", .data = &rk3128_ops }, { .compatible = "rockchip,rk3228-gmac", .data = &rk3228_ops }, { .compatible = "rockchip,rk3288-gmac", .data = &rk3288_ops }, { .compatible = "rockchip,rk3328-gmac", .data = &rk3328_ops }, diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c index c4407e8e39a3..2f7d7ec59962 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c @@ -296,6 +296,7 @@ static void dwmac4_pmt(struct mac_device_info *hw, unsigned long mode) { void __iomem *ioaddr = hw->pcsr; unsigned int pmt = 0; + u32 config; if (mode & WAKE_MAGIC) { pr_debug("GMAC: WOL Magic frame\n"); @@ -306,6 +307,12 @@ static void dwmac4_pmt(struct mac_device_info *hw, unsigned long mode) pmt |= power_down | global_unicast | wake_up_frame_en; } + if (pmt) { + /* The receiver must be enabled for WOL before powering down */ + config = readl(ioaddr + GMAC_CONFIG); + config |= GMAC_CONFIG_RE; + writel(config, ioaddr + GMAC_CONFIG); + } writel(pmt, ioaddr + GMAC_PMT); } diff --git a/drivers/net/ppp/ppp_generic.c b/drivers/net/ppp/ppp_generic.c index a404552555d4..c3f77e3b7819 100644 --- a/drivers/net/ppp/ppp_generic.c +++ b/drivers/net/ppp/ppp_generic.c @@ -120,7 +120,7 @@ struct ppp { int n_channels; /* how many channels are attached 54 */ spinlock_t rlock; /* lock for receive side 58 */ spinlock_t wlock; /* lock for transmit side 5c */ - int *xmit_recursion __percpu; /* xmit recursion detect */ + int __percpu *xmit_recursion; /* xmit recursion detect */ int mru; /* max receive unit 60 */ unsigned int flags; /* control bits 64 */ unsigned int xstate; /* transmit state bits 68 */ diff --git a/drivers/net/tun.c b/drivers/net/tun.c index 3c9985f29950..5ce580f413b9 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -1496,11 +1496,13 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile, switch (tun->flags & TUN_TYPE_MASK) { case IFF_TUN: if (tun->flags & IFF_NO_PI) { - switch (skb->data[0] & 0xf0) { - case 0x40: + u8 ip_version = skb->len ? (skb->data[0] >> 4) : 0; + + switch (ip_version) { + case 4: pi.proto = htons(ETH_P_IP); break; - case 0x60: + case 6: pi.proto = htons(ETH_P_IPV6); break; default: diff --git a/drivers/net/usb/cdc_ether.c b/drivers/net/usb/cdc_ether.c index 8ab281b478f2..29c7e2ec0dcb 100644 --- a/drivers/net/usb/cdc_ether.c +++ b/drivers/net/usb/cdc_ether.c @@ -54,11 +54,19 @@ static int is_wireless_rndis(struct usb_interface_descriptor *desc) desc->bInterfaceProtocol == 3); } +static int is_novatel_rndis(struct usb_interface_descriptor *desc) +{ + return (desc->bInterfaceClass == USB_CLASS_MISC && + desc->bInterfaceSubClass == 4 && + desc->bInterfaceProtocol == 1); +} + #else #define is_rndis(desc) 0 #define is_activesync(desc) 0 #define is_wireless_rndis(desc) 0 +#define is_novatel_rndis(desc) 0 #endif @@ -150,7 +158,8 @@ int usbnet_generic_cdc_bind(struct usbnet *dev, struct usb_interface *intf) */ rndis = (is_rndis(&intf->cur_altsetting->desc) || is_activesync(&intf->cur_altsetting->desc) || - is_wireless_rndis(&intf->cur_altsetting->desc)); + is_wireless_rndis(&intf->cur_altsetting->desc) || + is_novatel_rndis(&intf->cur_altsetting->desc)); memset(info, 0, sizeof(*info)); info->control = intf; @@ -547,6 +556,7 @@ static const struct driver_info wwan_info = { #define REALTEK_VENDOR_ID 0x0bda #define SAMSUNG_VENDOR_ID 0x04e8 #define LENOVO_VENDOR_ID 0x17ef +#define LINKSYS_VENDOR_ID 0x13b1 #define NVIDIA_VENDOR_ID 0x0955 #define HP_VENDOR_ID 0x03f0 #define MICROSOFT_VENDOR_ID 0x045e @@ -737,6 +747,15 @@ static const struct usb_device_id products[] = { .driver_info = 0, }, +#if IS_ENABLED(CONFIG_USB_RTL8152) +/* Linksys USB3GIGV1 Ethernet Adapter */ +{ + USB_DEVICE_AND_INTERFACE_INFO(LINKSYS_VENDOR_ID, 0x0041, USB_CLASS_COMM, + USB_CDC_SUBCLASS_ETHERNET, USB_CDC_PROTO_NONE), + .driver_info = 0, +}, +#endif + /* ThinkPad USB-C Dock (based on Realtek RTL8153) */ { USB_DEVICE_AND_INTERFACE_INFO(LENOVO_VENDOR_ID, 0x3062, USB_CLASS_COMM, diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c index ceb78e2ea4f0..941ece08ba78 100644 --- a/drivers/net/usb/r8152.c +++ b/drivers/net/usb/r8152.c @@ -613,6 +613,7 @@ enum rtl8152_flags { #define VENDOR_ID_MICROSOFT 0x045e #define VENDOR_ID_SAMSUNG 0x04e8 #define VENDOR_ID_LENOVO 0x17ef +#define VENDOR_ID_LINKSYS 0x13b1 #define VENDOR_ID_NVIDIA 0x0955 #define MCU_TYPE_PLA 0x0100 @@ -5316,6 +5317,7 @@ static const struct usb_device_id rtl8152_table[] = { {REALTEK_USB_DEVICE(VENDOR_ID_LENOVO, 0x7205)}, {REALTEK_USB_DEVICE(VENDOR_ID_LENOVO, 0x720c)}, {REALTEK_USB_DEVICE(VENDOR_ID_LENOVO, 0x7214)}, + {REALTEK_USB_DEVICE(VENDOR_ID_LINKSYS, 0x0041)}, {REALTEK_USB_DEVICE(VENDOR_ID_NVIDIA, 0x09ff)}, {} }; diff --git a/drivers/net/usb/rndis_host.c b/drivers/net/usb/rndis_host.c index a151f267aebb..b807c91abe1d 100644 --- a/drivers/net/usb/rndis_host.c +++ b/drivers/net/usb/rndis_host.c @@ -632,6 +632,10 @@ static const struct usb_device_id products [] = { /* RNDIS for tethering */ USB_INTERFACE_INFO(USB_CLASS_WIRELESS_CONTROLLER, 1, 3), .driver_info = (unsigned long) &rndis_info, +}, { + /* Novatel Verizon USB730L */ + USB_INTERFACE_INFO(USB_CLASS_MISC, 4, 1), + .driver_info = (unsigned long) &rndis_info, }, { }, // END }; diff --git a/drivers/net/wireless/ath/ath10k/pci.c b/drivers/net/wireless/ath/ath10k/pci.c index bc1633945a56..195dafb98131 100644 --- a/drivers/net/wireless/ath/ath10k/pci.c +++ b/drivers/net/wireless/ath/ath10k/pci.c @@ -3396,9 +3396,7 @@ static void ath10k_pci_remove(struct pci_dev *pdev) MODULE_DEVICE_TABLE(pci, ath10k_pci_id_table); -#ifdef CONFIG_PM - -static int ath10k_pci_pm_suspend(struct device *dev) +static __maybe_unused int ath10k_pci_pm_suspend(struct device *dev) { struct ath10k *ar = dev_get_drvdata(dev); int ret; @@ -3414,7 +3412,7 @@ static int ath10k_pci_pm_suspend(struct device *dev) return ret; } -static int ath10k_pci_pm_resume(struct device *dev) +static __maybe_unused int ath10k_pci_pm_resume(struct device *dev) { struct ath10k *ar = dev_get_drvdata(dev); int ret; @@ -3433,7 +3431,6 @@ static int ath10k_pci_pm_resume(struct device *dev) static SIMPLE_DEV_PM_OPS(ath10k_pci_pm_ops, ath10k_pci_pm_suspend, ath10k_pci_pm_resume); -#endif static struct pci_driver ath10k_pci_driver = { .name = "ath10k_pci", diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c index aaed4ab503ad..4157c90ad973 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c @@ -980,7 +980,7 @@ static void brcmf_escan_prep(struct brcmf_cfg80211_info *cfg, eth_broadcast_addr(params_le->bssid); params_le->bss_type = DOT11_BSSTYPE_ANY; - params_le->scan_type = 0; + params_le->scan_type = BRCMF_SCANTYPE_ACTIVE; params_le->channel_num = 0; params_le->nprobes = cpu_to_le32(-1); params_le->active_time = cpu_to_le32(-1); @@ -988,12 +988,9 @@ static void brcmf_escan_prep(struct brcmf_cfg80211_info *cfg, params_le->home_time = cpu_to_le32(-1); memset(¶ms_le->ssid_le, 0, sizeof(params_le->ssid_le)); - /* if request is null exit so it will be all channel broadcast scan */ - if (!request) - return; - n_ssids = request->n_ssids; n_channels = request->n_channels; + /* Copy channel array if applicable */ brcmf_dbg(SCAN, "### List of channelspecs to scan ### %d\n", n_channels); @@ -1030,16 +1027,8 @@ static void brcmf_escan_prep(struct brcmf_cfg80211_info *cfg, ptr += sizeof(ssid_le); } } else { - brcmf_dbg(SCAN, "Broadcast scan %p\n", request->ssids); - if ((request->ssids) && request->ssids->ssid_len) { - brcmf_dbg(SCAN, "SSID %s len=%d\n", - params_le->ssid_le.SSID, - request->ssids->ssid_len); - params_le->ssid_le.SSID_len = - cpu_to_le32(request->ssids->ssid_len); - memcpy(¶ms_le->ssid_le.SSID, request->ssids->ssid, - request->ssids->ssid_len); - } + brcmf_dbg(SCAN, "Performing passive scan\n"); + params_le->scan_type = BRCMF_SCANTYPE_PASSIVE; } /* Adding mask to channel numbers */ params_le->channel_num = @@ -3162,6 +3151,7 @@ brcmf_cfg80211_escan_handler(struct brcmf_if *ifp, struct brcmf_cfg80211_info *cfg = ifp->drvr->config; s32 status; struct brcmf_escan_result_le *escan_result_le; + u32 escan_buflen; struct brcmf_bss_info_le *bss_info_le; struct brcmf_bss_info_le *bss = NULL; u32 bi_length; @@ -3181,11 +3171,23 @@ brcmf_cfg80211_escan_handler(struct brcmf_if *ifp, if (status == BRCMF_E_STATUS_PARTIAL) { brcmf_dbg(SCAN, "ESCAN Partial result\n"); + if (e->datalen < sizeof(*escan_result_le)) { + brcmf_err("invalid event data length\n"); + goto exit; + } escan_result_le = (struct brcmf_escan_result_le *) data; if (!escan_result_le) { brcmf_err("Invalid escan result (NULL pointer)\n"); goto exit; } + escan_buflen = le32_to_cpu(escan_result_le->buflen); + if (escan_buflen > BRCMF_ESCAN_BUF_SIZE || + escan_buflen > e->datalen || + escan_buflen < sizeof(*escan_result_le)) { + brcmf_err("Invalid escan buffer length: %d\n", + escan_buflen); + goto exit; + } if (le16_to_cpu(escan_result_le->bss_count) != 1) { brcmf_err("Invalid bss_count %d: ignoring\n", escan_result_le->bss_count); @@ -3202,9 +3204,8 @@ brcmf_cfg80211_escan_handler(struct brcmf_if *ifp, } bi_length = le32_to_cpu(bss_info_le->length); - if (bi_length != (le32_to_cpu(escan_result_le->buflen) - - WL_ESCAN_RESULTS_FIXED_SIZE)) { - brcmf_err("Invalid bss_info length %d: ignoring\n", + if (bi_length != escan_buflen - WL_ESCAN_RESULTS_FIXED_SIZE) { + brcmf_err("Ignoring invalid bss_info length: %d\n", bi_length); goto exit; } diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fwil_types.h b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fwil_types.h index 8391989b1882..e0d22fedb2b4 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fwil_types.h +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fwil_types.h @@ -45,6 +45,11 @@ #define BRCMF_SCAN_PARAMS_COUNT_MASK 0x0000ffff #define BRCMF_SCAN_PARAMS_NSSID_SHIFT 16 +/* scan type definitions */ +#define BRCMF_SCANTYPE_DEFAULT 0xFF +#define BRCMF_SCANTYPE_ACTIVE 0 +#define BRCMF_SCANTYPE_PASSIVE 1 + #define BRCMF_WSEC_MAX_PSK_LEN 32 #define BRCMF_WSEC_PASSPHRASE BIT(0) diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/d3.c b/drivers/net/wireless/intel/iwlwifi/mvm/d3.c index 5de19ea10575..b205a7bfb828 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/d3.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/d3.c @@ -2167,7 +2167,7 @@ out: * 1. We are not using a unified image * 2. We are using a unified image but had an error while exiting D3 */ - set_bit(IWL_MVM_STATUS_IN_HW_RESTART, &mvm->status); + set_bit(IWL_MVM_STATUS_HW_RESTART_REQUESTED, &mvm->status); set_bit(IWL_MVM_STATUS_D3_RECONFIG, &mvm->status); /* * When switching images we return 1, which causes mac80211 diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c index 15f2d826bb4b..3bcaa82f59b2 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c @@ -1546,6 +1546,11 @@ static void iwl_mvm_mc_iface_iterator(void *_data, u8 *mac, struct iwl_mvm_mc_iter_data *data = _data; struct iwl_mvm *mvm = data->mvm; struct iwl_mcast_filter_cmd *cmd = mvm->mcast_filter_cmd; + struct iwl_host_cmd hcmd = { + .id = MCAST_FILTER_CMD, + .flags = CMD_ASYNC, + .dataflags[0] = IWL_HCMD_DFL_NOCOPY, + }; int ret, len; /* if we don't have free ports, mcast frames will be dropped */ @@ -1560,7 +1565,10 @@ static void iwl_mvm_mc_iface_iterator(void *_data, u8 *mac, memcpy(cmd->bssid, vif->bss_conf.bssid, ETH_ALEN); len = roundup(sizeof(*cmd) + cmd->count * ETH_ALEN, 4); - ret = iwl_mvm_send_cmd_pdu(mvm, MCAST_FILTER_CMD, CMD_ASYNC, len, cmd); + hcmd.len[0] = len; + hcmd.data[0] = cmd; + + ret = iwl_mvm_send_cmd(mvm, &hcmd); if (ret) IWL_ERR(mvm, "mcast filter cmd error. ret=%d\n", ret); } @@ -1635,6 +1643,12 @@ static void iwl_mvm_configure_filter(struct ieee80211_hw *hw, if (!cmd) goto out; + if (changed_flags & FIF_ALLMULTI) + cmd->pass_all = !!(*total_flags & FIF_ALLMULTI); + + if (cmd->pass_all) + cmd->count = 0; + iwl_mvm_recalc_multicast(mvm); out: mutex_unlock(&mvm->mutex); @@ -2563,7 +2577,7 @@ static void iwl_mvm_purge_deferred_tx_frames(struct iwl_mvm *mvm, * queues, so we should never get a second deferred * frame for the RA/TID. */ - iwl_mvm_start_mac_queues(mvm, info->hw_queue); + iwl_mvm_start_mac_queues(mvm, BIT(info->hw_queue)); ieee80211_free_txskb(mvm->hw, skb); } } @@ -3975,6 +3989,43 @@ out_unlock: return ret; } +static void iwl_mvm_flush_no_vif(struct iwl_mvm *mvm, u32 queues, bool drop) +{ + if (drop) { + if (iwl_mvm_has_new_tx_api(mvm)) + /* TODO new tx api */ + WARN_ONCE(1, + "Need to implement flush TX queue\n"); + else + iwl_mvm_flush_tx_path(mvm, + iwl_mvm_flushable_queues(mvm) & queues, + 0); + } else { + if (iwl_mvm_has_new_tx_api(mvm)) { + struct ieee80211_sta *sta; + int i; + + mutex_lock(&mvm->mutex); + + for (i = 0; i < ARRAY_SIZE(mvm->fw_id_to_mac_id); i++) { + sta = rcu_dereference_protected( + mvm->fw_id_to_mac_id[i], + lockdep_is_held(&mvm->mutex)); + if (IS_ERR_OR_NULL(sta)) + continue; + + iwl_mvm_wait_sta_queues_empty(mvm, + iwl_mvm_sta_from_mac80211(sta)); + } + + mutex_unlock(&mvm->mutex); + } else { + iwl_trans_wait_tx_queues_empty(mvm->trans, + queues); + } + } +} + static void iwl_mvm_mac_flush(struct ieee80211_hw *hw, struct ieee80211_vif *vif, u32 queues, bool drop) { @@ -3985,7 +4036,12 @@ static void iwl_mvm_mac_flush(struct ieee80211_hw *hw, int i; u32 msk = 0; - if (!vif || vif->type != NL80211_IFTYPE_STATION) + if (!vif) { + iwl_mvm_flush_no_vif(mvm, queues, drop); + return; + } + + if (vif->type != NL80211_IFTYPE_STATION) return; /* Make sure we're done with the deferred traffic before flushing */ diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/rs.c b/drivers/net/wireless/intel/iwlwifi/mvm/rs.c index ba7bd049d3d4..0fe723ca844e 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/rs.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/rs.c @@ -661,7 +661,8 @@ static void rs_tl_turn_on_agg(struct iwl_mvm *mvm, struct iwl_mvm_sta *mvmsta, (lq_sta->tx_agg_tid_en & BIT(tid)) && (tid_data->tx_count_last >= IWL_MVM_RS_AGG_START_THRESHOLD)) { IWL_DEBUG_RATE(mvm, "try to aggregate tid %d\n", tid); - rs_tl_turn_on_agg_for_tid(mvm, lq_sta, tid, sta); + if (rs_tl_turn_on_agg_for_tid(mvm, lq_sta, tid, sta) == 0) + tid_data->state = IWL_AGG_QUEUED; } } diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c b/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c index 67ffd9774712..77f77bc5d083 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c @@ -672,11 +672,12 @@ static bool iwl_mvm_reorder(struct iwl_mvm *mvm, * If there was a significant jump in the nssn - adjust. * If the SN is smaller than the NSSN it might need to first go into * the reorder buffer, in which case we just release up to it and the - * rest of the function will take of storing it and releasing up to the - * nssn + * rest of the function will take care of storing it and releasing up to + * the nssn */ if (!iwl_mvm_is_sn_less(nssn, buffer->head_sn + buffer->buf_size, - buffer->buf_size)) { + buffer->buf_size) || + !ieee80211_sn_less(sn, buffer->head_sn + buffer->buf_size)) { u16 min_sn = ieee80211_sn_less(sn, nssn) ? sn : nssn; iwl_mvm_release_frames(mvm, sta, napi, buffer, min_sn); diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/scan.c b/drivers/net/wireless/intel/iwlwifi/mvm/scan.c index 50983615dce6..774122fed454 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/scan.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/scan.c @@ -555,7 +555,7 @@ static int iwl_mvm_lmac_scan_abort(struct iwl_mvm *mvm) struct iwl_host_cmd cmd = { .id = SCAN_OFFLOAD_ABORT_CMD, }; - u32 status; + u32 status = CAN_ABORT_STATUS; ret = iwl_mvm_send_cmd_status(mvm, &cmd, &status); if (ret) diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/sta.c b/drivers/net/wireless/intel/iwlwifi/mvm/sta.c index 411a2055dc45..c4a343534c5e 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/sta.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/sta.c @@ -1285,7 +1285,7 @@ static int iwl_mvm_add_int_sta_common(struct iwl_mvm *mvm, { struct iwl_mvm_add_sta_cmd cmd; int ret; - u32 status; + u32 status = ADD_STA_SUCCESS; lockdep_assert_held(&mvm->mutex); @@ -2385,8 +2385,10 @@ int iwl_mvm_sta_tx_agg_start(struct iwl_mvm *mvm, struct ieee80211_vif *vif, if (WARN_ON_ONCE(tid >= IWL_MAX_TID_COUNT)) return -EINVAL; - if (mvmsta->tid_data[tid].state != IWL_AGG_OFF) { - IWL_ERR(mvm, "Start AGG when state is not IWL_AGG_OFF %d!\n", + if (mvmsta->tid_data[tid].state != IWL_AGG_QUEUED && + mvmsta->tid_data[tid].state != IWL_AGG_OFF) { + IWL_ERR(mvm, + "Start AGG when state is not IWL_AGG_QUEUED or IWL_AGG_OFF %d!\n", mvmsta->tid_data[tid].state); return -ENXIO; } diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/sta.h b/drivers/net/wireless/intel/iwlwifi/mvm/sta.h index d13893806513..aedabe101cf0 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/sta.h +++ b/drivers/net/wireless/intel/iwlwifi/mvm/sta.h @@ -281,6 +281,7 @@ struct iwl_mvm_vif; * These states relate to a specific RA / TID. * * @IWL_AGG_OFF: aggregation is not used + * @IWL_AGG_QUEUED: aggregation start work has been queued * @IWL_AGG_STARTING: aggregation are starting (between start and oper) * @IWL_AGG_ON: aggregation session is up * @IWL_EMPTYING_HW_QUEUE_ADDBA: establishing a BA session - waiting for the @@ -290,6 +291,7 @@ struct iwl_mvm_vif; */ enum iwl_mvm_agg_state { IWL_AGG_OFF = 0, + IWL_AGG_QUEUED, IWL_AGG_STARTING, IWL_AGG_ON, IWL_EMPTYING_HW_QUEUE_ADDBA, diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/tt.c b/drivers/net/wireless/intel/iwlwifi/mvm/tt.c index 8876c2abc440..4d907f60bce9 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/tt.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/tt.c @@ -529,6 +529,7 @@ int iwl_mvm_ctdp_command(struct iwl_mvm *mvm, u32 op, u32 state) lockdep_assert_held(&mvm->mutex); + status = 0; ret = iwl_mvm_send_cmd_pdu_status(mvm, WIDE_ID(PHY_OPS_GROUP, CTDP_CONFIG_CMD), sizeof(cmd), &cmd, &status); diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/tx.c b/drivers/net/wireless/intel/iwlwifi/mvm/tx.c index 172b5e63d3fb..6f2e2af23219 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/tx.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/tx.c @@ -564,8 +564,8 @@ static int iwl_mvm_get_ctrl_vif_queue(struct iwl_mvm *mvm, case NL80211_IFTYPE_AP: case NL80211_IFTYPE_ADHOC: /* - * Handle legacy hostapd as well, where station will be added - * only just before sending the association response. + * Non-bufferable frames use the broadcast station, thus they + * use the probe queue. * Also take care of the case where we send a deauth to a * station that we don't have, or similarly an association * response (with non-success status) for a station we can't @@ -573,9 +573,9 @@ static int iwl_mvm_get_ctrl_vif_queue(struct iwl_mvm *mvm, * Also, disassociate frames might happen, particular with * reason 7 ("Class 3 frame received from nonassociated STA"). */ - if (ieee80211_is_probe_resp(fc) || ieee80211_is_auth(fc) || - ieee80211_is_deauth(fc) || ieee80211_is_assoc_resp(fc) || - ieee80211_is_disassoc(fc)) + if (ieee80211_is_mgmt(fc) && + (!ieee80211_is_bufferable_mmpdu(fc) || + ieee80211_is_deauth(fc) || ieee80211_is_disassoc(fc))) return mvm->probe_queue; if (info->hw_queue == info->control.vif->cab_queue) return mvmvif->cab_queue; diff --git a/drivers/net/wireless/quantenna/qtnfmac/cfg80211.c b/drivers/net/wireless/quantenna/qtnfmac/cfg80211.c index 856fa6e8327e..a450bc6bc774 100644 --- a/drivers/net/wireless/quantenna/qtnfmac/cfg80211.c +++ b/drivers/net/wireless/quantenna/qtnfmac/cfg80211.c @@ -115,6 +115,8 @@ int qtnf_del_virtual_intf(struct wiphy *wiphy, struct wireless_dev *wdev) vif = qtnf_netdev_get_priv(wdev->netdev); + qtnf_scan_done(vif->mac, true); + if (qtnf_cmd_send_del_intf(vif)) pr_err("VIF%u.%u: failed to delete VIF\n", vif->mac->macid, vif->vifid); @@ -335,6 +337,8 @@ static int qtnf_stop_ap(struct wiphy *wiphy, struct net_device *dev) struct qtnf_vif *vif = qtnf_netdev_get_priv(dev); int ret; + qtnf_scan_done(vif->mac, true); + ret = qtnf_cmd_send_stop_ap(vif); if (ret) { pr_err("VIF%u.%u: failed to stop AP operation in FW\n", @@ -570,8 +574,6 @@ qtnf_del_station(struct wiphy *wiphy, struct net_device *dev, !qtnf_sta_list_lookup(&vif->sta_list, params->mac)) return 0; - qtnf_scan_done(vif->mac, true); - ret = qtnf_cmd_send_del_sta(vif, params); if (ret) pr_err("VIF%u.%u: failed to delete STA %pM\n", @@ -1134,8 +1136,9 @@ void qtnf_virtual_intf_cleanup(struct net_device *ndev) } vif->sta_state = QTNF_STA_DISCONNECTED; - qtnf_scan_done(mac, true); } + + qtnf_scan_done(mac, true); } void qtnf_cfg80211_vif_reset(struct qtnf_vif *vif) diff --git a/drivers/net/wireless/quantenna/qtnfmac/cfg80211.h b/drivers/net/wireless/quantenna/qtnfmac/cfg80211.h index 6a4af52522b8..66db26613b1f 100644 --- a/drivers/net/wireless/quantenna/qtnfmac/cfg80211.h +++ b/drivers/net/wireless/quantenna/qtnfmac/cfg80211.h @@ -34,6 +34,9 @@ static inline void qtnf_scan_done(struct qtnf_wmac *mac, bool aborted) .aborted = aborted, }; + if (timer_pending(&mac->scan_timeout)) + del_timer_sync(&mac->scan_timeout); + mutex_lock(&mac->mac_lock); if (mac->scan_req) { diff --git a/drivers/net/wireless/quantenna/qtnfmac/event.c b/drivers/net/wireless/quantenna/qtnfmac/event.c index 0fc2814eafad..43d2e7fd6e02 100644 --- a/drivers/net/wireless/quantenna/qtnfmac/event.c +++ b/drivers/net/wireless/quantenna/qtnfmac/event.c @@ -345,8 +345,6 @@ qtnf_event_handle_scan_complete(struct qtnf_wmac *mac, return -EINVAL; } - if (timer_pending(&mac->scan_timeout)) - del_timer_sync(&mac->scan_timeout); qtnf_scan_done(mac, le32_to_cpu(status->flags) & QLINK_SCAN_ABORTED); return 0; diff --git a/drivers/net/wireless/quantenna/qtnfmac/pearl/pcie.c b/drivers/net/wireless/quantenna/qtnfmac/pearl/pcie.c index 502e72b7cdcc..69131965a298 100644 --- a/drivers/net/wireless/quantenna/qtnfmac/pearl/pcie.c +++ b/drivers/net/wireless/quantenna/qtnfmac/pearl/pcie.c @@ -661,14 +661,18 @@ static int qtnf_pcie_data_tx(struct qtnf_bus *bus, struct sk_buff *skb) struct qtnf_pcie_bus_priv *priv = (void *)get_bus_priv(bus); dma_addr_t txbd_paddr, skb_paddr; struct qtnf_tx_bd *txbd; + unsigned long flags; int len, i; u32 info; int ret = 0; + spin_lock_irqsave(&priv->tx0_lock, flags); + if (!qtnf_tx_queue_ready(priv)) { if (skb->dev) netif_stop_queue(skb->dev); + spin_unlock_irqrestore(&priv->tx0_lock, flags); return NETDEV_TX_BUSY; } @@ -717,8 +721,10 @@ tx_done: dev_kfree_skb_any(skb); } - qtnf_pcie_data_tx_reclaim(priv); priv->tx_done_count++; + spin_unlock_irqrestore(&priv->tx0_lock, flags); + + qtnf_pcie_data_tx_reclaim(priv); return NETDEV_TX_OK; } @@ -1247,6 +1253,7 @@ static int qtnf_pcie_probe(struct pci_dev *pdev, const struct pci_device_id *id) strcpy(bus->fwname, QTN_PCI_PEARL_FW_NAME); init_completion(&bus->request_firmware_complete); mutex_init(&bus->bus_lock); + spin_lock_init(&pcie_priv->tx0_lock); spin_lock_init(&pcie_priv->irq_lock); spin_lock_init(&pcie_priv->tx_reclaim_lock); diff --git a/drivers/net/wireless/quantenna/qtnfmac/pearl/pcie_bus_priv.h b/drivers/net/wireless/quantenna/qtnfmac/pearl/pcie_bus_priv.h index e76a23716ee0..86ac1ccedb52 100644 --- a/drivers/net/wireless/quantenna/qtnfmac/pearl/pcie_bus_priv.h +++ b/drivers/net/wireless/quantenna/qtnfmac/pearl/pcie_bus_priv.h @@ -34,6 +34,8 @@ struct qtnf_pcie_bus_priv { /* lock for tx reclaim operations */ spinlock_t tx_reclaim_lock; + /* lock for tx0 operations */ + spinlock_t tx0_lock; u8 msi_enabled; int mps; diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index acc816b67582..5a14cc7f28ee 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -134,8 +134,6 @@ static inline bool nvme_req_needs_retry(struct request *req) return false; if (nvme_req(req)->status & NVME_SC_DNR) return false; - if (jiffies - req->start_time >= req->timeout) - return false; if (nvme_req(req)->retries >= nvme_max_retries) return false; return true; @@ -2138,7 +2136,7 @@ static umode_t nvme_ns_attrs_are_visible(struct kobject *kobj, struct nvme_ns *ns = nvme_get_ns_from_dev(dev); if (a == &dev_attr_uuid.attr) { - if (uuid_is_null(&ns->uuid) || + if (uuid_is_null(&ns->uuid) && !memchr_inv(ns->nguid, 0, sizeof(ns->nguid))) return 0; } @@ -2590,7 +2588,7 @@ static void nvme_async_event_work(struct work_struct *work) container_of(work, struct nvme_ctrl, async_event_work); spin_lock_irq(&ctrl->lock); - while (ctrl->event_limit > 0) { + while (ctrl->state == NVME_CTRL_LIVE && ctrl->event_limit > 0) { int aer_idx = --ctrl->event_limit; spin_unlock_irq(&ctrl->lock); @@ -2677,7 +2675,8 @@ void nvme_complete_async_event(struct nvme_ctrl *ctrl, __le16 status, /*FALLTHRU*/ case NVME_SC_ABORT_REQ: ++ctrl->event_limit; - queue_work(nvme_wq, &ctrl->async_event_work); + if (ctrl->state == NVME_CTRL_LIVE) + queue_work(nvme_wq, &ctrl->async_event_work); break; default: break; @@ -2692,7 +2691,7 @@ void nvme_complete_async_event(struct nvme_ctrl *ctrl, __le16 status, nvme_queue_scan(ctrl); break; case NVME_AER_NOTICE_FW_ACT_STARTING: - schedule_work(&ctrl->fw_act_work); + queue_work(nvme_wq, &ctrl->fw_act_work); break; default: dev_warn(ctrl->device, "async event result %08x\n", result); diff --git a/drivers/nvme/host/fabrics.c b/drivers/nvme/host/fabrics.c index 47307752dc65..555c976cc2ee 100644 --- a/drivers/nvme/host/fabrics.c +++ b/drivers/nvme/host/fabrics.c @@ -565,6 +565,7 @@ static int nvmf_parse_options(struct nvmf_ctrl_options *opts, opts->queue_size = NVMF_DEF_QUEUE_SIZE; opts->nr_io_queues = num_online_cpus(); opts->reconnect_delay = NVMF_DEF_RECONNECT_DELAY; + opts->kato = NVME_DEFAULT_KATO; options = o = kstrdup(buf, GFP_KERNEL); if (!options) @@ -655,21 +656,22 @@ static int nvmf_parse_options(struct nvmf_ctrl_options *opts, goto out; } - if (opts->discovery_nqn) { - pr_err("Discovery controllers cannot accept keep_alive_tmo != 0\n"); - ret = -EINVAL; - goto out; - } - if (token < 0) { pr_err("Invalid keep_alive_tmo %d\n", token); ret = -EINVAL; goto out; - } else if (token == 0) { + } else if (token == 0 && !opts->discovery_nqn) { /* Allowed for debug */ pr_warn("keep_alive_tmo 0 won't execute keep alives!!!\n"); } opts->kato = token; + + if (opts->discovery_nqn && opts->kato) { + pr_err("Discovery controllers cannot accept KATO != 0\n"); + ret = -EINVAL; + goto out; + } + break; case NVMF_OPT_CTRL_LOSS_TMO: if (match_int(args, &token)) { @@ -762,8 +764,6 @@ static int nvmf_parse_options(struct nvmf_ctrl_options *opts, uuid_copy(&opts->host->id, &hostid); out: - if (!opts->discovery_nqn && !opts->kato) - opts->kato = NVME_DEFAULT_KATO; kfree(options); return ret; } diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c index d2e882c0f496..af075e998944 100644 --- a/drivers/nvme/host/fc.c +++ b/drivers/nvme/host/fc.c @@ -1376,7 +1376,7 @@ nvme_fc_fcpio_done(struct nvmefc_fcp_req *req) if (atomic_read(&op->state) == FCPOP_STATE_ABORTED) status = cpu_to_le16((NVME_SC_ABORT_REQ | NVME_SC_DNR) << 1); else if (freq->status) - status = cpu_to_le16(NVME_SC_FC_TRANSPORT_ERROR << 1); + status = cpu_to_le16(NVME_SC_INTERNAL << 1); /* * For the linux implementation, if we have an unsuccesful @@ -1404,7 +1404,7 @@ nvme_fc_fcpio_done(struct nvmefc_fcp_req *req) */ if (freq->transferred_length != be32_to_cpu(op->cmd_iu.data_len)) { - status = cpu_to_le16(NVME_SC_FC_TRANSPORT_ERROR << 1); + status = cpu_to_le16(NVME_SC_INTERNAL << 1); goto done; } result.u64 = 0; @@ -1421,7 +1421,7 @@ nvme_fc_fcpio_done(struct nvmefc_fcp_req *req) freq->transferred_length || op->rsp_iu.status_code || sqe->common.command_id != cqe->command_id)) { - status = cpu_to_le16(NVME_SC_FC_TRANSPORT_ERROR << 1); + status = cpu_to_le16(NVME_SC_INTERNAL << 1); goto done; } result = cqe->result; @@ -1429,7 +1429,7 @@ nvme_fc_fcpio_done(struct nvmefc_fcp_req *req) break; default: - status = cpu_to_le16(NVME_SC_FC_TRANSPORT_ERROR << 1); + status = cpu_to_le16(NVME_SC_INTERNAL << 1); goto done; } @@ -1989,16 +1989,17 @@ nvme_fc_start_fcp_op(struct nvme_fc_ctrl *ctrl, struct nvme_fc_queue *queue, * as well as those by FC-NVME spec. */ WARN_ON_ONCE(sqe->common.metadata); - WARN_ON_ONCE(sqe->common.dptr.prp1); - WARN_ON_ONCE(sqe->common.dptr.prp2); sqe->common.flags |= NVME_CMD_SGL_METABUF; /* - * format SQE DPTR field per FC-NVME rules - * type=data block descr; subtype=offset; - * offset is currently 0. + * format SQE DPTR field per FC-NVME rules: + * type=0x5 Transport SGL Data Block Descriptor + * subtype=0xA Transport-specific value + * address=0 + * length=length of the data series */ - sqe->rw.dptr.sgl.type = NVME_SGL_FMT_OFFSET; + sqe->rw.dptr.sgl.type = (NVME_TRANSPORT_SGL_DATA_DESC << 4) | + NVME_SGL_FMT_TRANSPORT_A; sqe->rw.dptr.sgl.length = cpu_to_le32(data_len); sqe->rw.dptr.sgl.addr = 0; diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index 4a2121335f48..3f5a04c586ce 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -24,6 +24,7 @@ #include <linux/mm.h> #include <linux/module.h> #include <linux/mutex.h> +#include <linux/once.h> #include <linux/pci.h> #include <linux/poison.h> #include <linux/t10-pi.h> @@ -93,7 +94,7 @@ struct nvme_dev { struct mutex shutdown_lock; bool subsystem; void __iomem *cmb; - dma_addr_t cmb_dma_addr; + pci_bus_addr_t cmb_bus_addr; u64 cmb_size; u32 cmbsz; u32 cmbloc; @@ -540,6 +541,20 @@ static void nvme_dif_complete(u32 p, u32 v, struct t10_pi_tuple *pi) } #endif +static void nvme_print_sgl(struct scatterlist *sgl, int nents) +{ + int i; + struct scatterlist *sg; + + for_each_sg(sgl, sg, nents, i) { + dma_addr_t phys = sg_phys(sg); + pr_warn("sg[%d] phys_addr:%pad offset:%d length:%d " + "dma_address:%pad dma_length:%d\n", + i, &phys, sg->offset, sg->length, &sg_dma_address(sg), + sg_dma_len(sg)); + } +} + static blk_status_t nvme_setup_prps(struct nvme_dev *dev, struct request *req) { struct nvme_iod *iod = blk_mq_rq_to_pdu(req); @@ -622,19 +637,10 @@ static blk_status_t nvme_setup_prps(struct nvme_dev *dev, struct request *req) return BLK_STS_OK; bad_sgl: - if (WARN_ONCE(1, "Invalid SGL for payload:%d nents:%d\n", - blk_rq_payload_bytes(req), iod->nents)) { - for_each_sg(iod->sg, sg, iod->nents, i) { - dma_addr_t phys = sg_phys(sg); - pr_warn("sg[%d] phys_addr:%pad offset:%d length:%d " - "dma_address:%pad dma_length:%d\n", i, &phys, - sg->offset, sg->length, - &sg_dma_address(sg), - sg_dma_len(sg)); - } - } + WARN(DO_ONCE(nvme_print_sgl, iod->sg, iod->nents), + "Invalid SGL for payload:%d nents:%d\n", + blk_rq_payload_bytes(req), iod->nents); return BLK_STS_IOERR; - } static blk_status_t nvme_map_data(struct nvme_dev *dev, struct request *req, @@ -1220,7 +1226,7 @@ static int nvme_alloc_sq_cmds(struct nvme_dev *dev, struct nvme_queue *nvmeq, if (qid && dev->cmb && use_cmb_sqes && NVME_CMB_SQS(dev->cmbsz)) { unsigned offset = (qid - 1) * roundup(SQ_SIZE(depth), dev->ctrl.page_size); - nvmeq->sq_dma_addr = dev->cmb_dma_addr + offset; + nvmeq->sq_dma_addr = dev->cmb_bus_addr + offset; nvmeq->sq_cmds_io = dev->cmb + offset; } else { nvmeq->sq_cmds = dma_alloc_coherent(dev->dev, SQ_SIZE(depth), @@ -1313,11 +1319,11 @@ static int nvme_create_queue(struct nvme_queue *nvmeq, int qid) if (result < 0) goto release_cq; + nvme_init_queue(nvmeq, qid); result = queue_request_irq(nvmeq); if (result < 0) goto release_sq; - nvme_init_queue(nvmeq, qid); return result; release_sq: @@ -1464,6 +1470,7 @@ static int nvme_pci_configure_admin_queue(struct nvme_dev *dev) return result; nvmeq->cq_vector = 0; + nvme_init_queue(nvmeq, 0); result = queue_request_irq(nvmeq); if (result) { nvmeq->cq_vector = -1; @@ -1520,7 +1527,7 @@ static void __iomem *nvme_map_cmb(struct nvme_dev *dev) resource_size_t bar_size; struct pci_dev *pdev = to_pci_dev(dev->dev); void __iomem *cmb; - dma_addr_t dma_addr; + int bar; dev->cmbsz = readl(dev->bar + NVME_REG_CMBSZ); if (!(NVME_CMB_SZ(dev->cmbsz))) @@ -1533,7 +1540,8 @@ static void __iomem *nvme_map_cmb(struct nvme_dev *dev) szu = (u64)1 << (12 + 4 * NVME_CMB_SZU(dev->cmbsz)); size = szu * NVME_CMB_SZ(dev->cmbsz); offset = szu * NVME_CMB_OFST(dev->cmbloc); - bar_size = pci_resource_len(pdev, NVME_CMB_BIR(dev->cmbloc)); + bar = NVME_CMB_BIR(dev->cmbloc); + bar_size = pci_resource_len(pdev, bar); if (offset > bar_size) return NULL; @@ -1546,12 +1554,11 @@ static void __iomem *nvme_map_cmb(struct nvme_dev *dev) if (size > bar_size - offset) size = bar_size - offset; - dma_addr = pci_resource_start(pdev, NVME_CMB_BIR(dev->cmbloc)) + offset; - cmb = ioremap_wc(dma_addr, size); + cmb = ioremap_wc(pci_resource_start(pdev, bar) + offset, size); if (!cmb) return NULL; - dev->cmb_dma_addr = dma_addr; + dev->cmb_bus_addr = pci_bus_address(pdev, bar) + offset; dev->cmb_size = size; return cmb; } @@ -2156,7 +2163,6 @@ static void nvme_reset_work(struct work_struct *work) if (result) goto out; - nvme_init_queue(dev->queues[0], 0); result = nvme_alloc_admin_tags(dev); if (result) goto out; diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c index 58983000964b..92a03ff5fb4d 100644 --- a/drivers/nvme/host/rdma.c +++ b/drivers/nvme/host/rdma.c @@ -942,7 +942,12 @@ static void nvme_rdma_reconnect_ctrl_work(struct work_struct *work) } changed = nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_LIVE); - WARN_ON_ONCE(!changed); + if (!changed) { + /* state change failure is ok if we're in DELETING state */ + WARN_ON_ONCE(ctrl->ctrl.state != NVME_CTRL_DELETING); + return; + } + ctrl->ctrl.nr_reconnects = 0; nvme_start_ctrl(&ctrl->ctrl); @@ -962,7 +967,7 @@ static void nvme_rdma_error_recovery_work(struct work_struct *work) struct nvme_rdma_ctrl *ctrl = container_of(work, struct nvme_rdma_ctrl, err_work); - nvme_stop_ctrl(&ctrl->ctrl); + nvme_stop_keep_alive(&ctrl->ctrl); if (ctrl->ctrl.queue_count > 1) { nvme_stop_queues(&ctrl->ctrl); diff --git a/drivers/nvme/target/core.c b/drivers/nvme/target/core.c index 7c23eaf8e563..1b208beeef50 100644 --- a/drivers/nvme/target/core.c +++ b/drivers/nvme/target/core.c @@ -390,10 +390,10 @@ static void __nvmet_req_complete(struct nvmet_req *req, u16 status) if (status) nvmet_set_status(req, status); - /* XXX: need to fill in something useful for sq_head */ - req->rsp->sq_head = 0; - if (likely(req->sq)) /* may happen during early failure */ - req->rsp->sq_id = cpu_to_le16(req->sq->qid); + if (req->sq->size) + req->sq->sqhd = (req->sq->sqhd + 1) % req->sq->size; + req->rsp->sq_head = cpu_to_le16(req->sq->sqhd); + req->rsp->sq_id = cpu_to_le16(req->sq->qid); req->rsp->command_id = req->cmd->common.command_id; if (req->ns) @@ -420,6 +420,7 @@ void nvmet_cq_setup(struct nvmet_ctrl *ctrl, struct nvmet_cq *cq, void nvmet_sq_setup(struct nvmet_ctrl *ctrl, struct nvmet_sq *sq, u16 qid, u16 size) { + sq->sqhd = 0; sq->qid = qid; sq->size = size; diff --git a/drivers/nvme/target/fabrics-cmd.c b/drivers/nvme/target/fabrics-cmd.c index 859a66725291..db3bf6b8bf9e 100644 --- a/drivers/nvme/target/fabrics-cmd.c +++ b/drivers/nvme/target/fabrics-cmd.c @@ -109,9 +109,14 @@ static u16 nvmet_install_queue(struct nvmet_ctrl *ctrl, struct nvmet_req *req) pr_warn("queue already connected!\n"); return NVME_SC_CONNECT_CTRL_BUSY | NVME_SC_DNR; } + if (!sqsize) { + pr_warn("queue size zero!\n"); + return NVME_SC_CONNECT_INVALID_PARAM | NVME_SC_DNR; + } - nvmet_cq_setup(ctrl, req->cq, qid, sqsize); - nvmet_sq_setup(ctrl, req->sq, qid, sqsize); + /* note: convert queue size from 0's-based value to 1's-based value */ + nvmet_cq_setup(ctrl, req->cq, qid, sqsize + 1); + nvmet_sq_setup(ctrl, req->sq, qid, sqsize + 1); return 0; } diff --git a/drivers/nvme/target/fc.c b/drivers/nvme/target/fc.c index 421e43bf1dd7..58e010bdda3e 100644 --- a/drivers/nvme/target/fc.c +++ b/drivers/nvme/target/fc.c @@ -148,7 +148,7 @@ struct nvmet_fc_tgt_assoc { u32 a_id; struct nvmet_fc_tgtport *tgtport; struct list_head a_list; - struct nvmet_fc_tgt_queue *queues[NVMET_NR_QUEUES]; + struct nvmet_fc_tgt_queue *queues[NVMET_NR_QUEUES + 1]; struct kref ref; }; @@ -608,7 +608,7 @@ nvmet_fc_alloc_target_queue(struct nvmet_fc_tgt_assoc *assoc, unsigned long flags; int ret; - if (qid >= NVMET_NR_QUEUES) + if (qid > NVMET_NR_QUEUES) return NULL; queue = kzalloc((sizeof(*queue) + @@ -783,6 +783,9 @@ nvmet_fc_find_target_queue(struct nvmet_fc_tgtport *tgtport, u16 qid = nvmet_fc_getqueueid(connection_id); unsigned long flags; + if (qid > NVMET_NR_QUEUES) + return NULL; + spin_lock_irqsave(&tgtport->lock, flags); list_for_each_entry(assoc, &tgtport->assoc_list, a_list) { if (association_id == assoc->association_id) { @@ -888,7 +891,7 @@ nvmet_fc_delete_target_assoc(struct nvmet_fc_tgt_assoc *assoc) int i; spin_lock_irqsave(&tgtport->lock, flags); - for (i = NVMET_NR_QUEUES - 1; i >= 0; i--) { + for (i = NVMET_NR_QUEUES; i >= 0; i--) { queue = assoc->queues[i]; if (queue) { if (!nvmet_fc_tgt_q_get(queue)) @@ -1910,8 +1913,7 @@ nvmet_fc_transfer_fcp_data(struct nvmet_fc_tgtport *tgtport, spin_lock_irqsave(&fod->flock, flags); fod->writedataactive = false; spin_unlock_irqrestore(&fod->flock, flags); - nvmet_req_complete(&fod->req, - NVME_SC_FC_TRANSPORT_ERROR); + nvmet_req_complete(&fod->req, NVME_SC_INTERNAL); } else /* NVMET_FCOP_READDATA or NVMET_FCOP_READDATA_RSP */ { fcpreq->fcp_error = ret; fcpreq->transferred_length = 0; @@ -1929,8 +1931,7 @@ __nvmet_fc_fod_op_abort(struct nvmet_fc_fcp_iod *fod, bool abort) /* if in the middle of an io and we need to tear down */ if (abort) { if (fcpreq->op == NVMET_FCOP_WRITEDATA) { - nvmet_req_complete(&fod->req, - NVME_SC_FC_TRANSPORT_ERROR); + nvmet_req_complete(&fod->req, NVME_SC_INTERNAL); return true; } @@ -1968,8 +1969,7 @@ nvmet_fc_fod_op_done(struct nvmet_fc_fcp_iod *fod) fod->abort = true; spin_unlock(&fod->flock); - nvmet_req_complete(&fod->req, - NVME_SC_FC_TRANSPORT_ERROR); + nvmet_req_complete(&fod->req, NVME_SC_INTERNAL); return; } @@ -2533,13 +2533,17 @@ nvmet_fc_remove_port(struct nvmet_port *port) { struct nvmet_fc_tgtport *tgtport = port->priv; unsigned long flags; + bool matched = false; spin_lock_irqsave(&nvmet_fc_tgtlock, flags); if (tgtport->port == port) { - nvmet_fc_tgtport_put(tgtport); + matched = true; tgtport->port = NULL; } spin_unlock_irqrestore(&nvmet_fc_tgtlock, flags); + + if (matched) + nvmet_fc_tgtport_put(tgtport); } static struct nvmet_fabrics_ops nvmet_fc_tgt_fcp_ops = { diff --git a/drivers/nvme/target/fcloop.c b/drivers/nvme/target/fcloop.c index 1cb9847ec261..7b75d9de55ab 100644 --- a/drivers/nvme/target/fcloop.c +++ b/drivers/nvme/target/fcloop.c @@ -224,8 +224,6 @@ struct fcloop_nport { struct fcloop_lport *lport; struct list_head nport_list; struct kref ref; - struct completion rport_unreg_done; - struct completion tport_unreg_done; u64 node_name; u64 port_name; u32 port_role; @@ -576,7 +574,7 @@ fcloop_tgt_fcp_abort(struct nvmet_fc_target_port *tgtport, tfcp_req->aborted = true; spin_unlock(&tfcp_req->reqlock); - tfcp_req->status = NVME_SC_FC_TRANSPORT_ABORTED; + tfcp_req->status = NVME_SC_INTERNAL; /* * nothing more to do. If io wasn't active, the transport should @@ -631,6 +629,32 @@ fcloop_fcp_abort(struct nvme_fc_local_port *localport, } static void +fcloop_nport_free(struct kref *ref) +{ + struct fcloop_nport *nport = + container_of(ref, struct fcloop_nport, ref); + unsigned long flags; + + spin_lock_irqsave(&fcloop_lock, flags); + list_del(&nport->nport_list); + spin_unlock_irqrestore(&fcloop_lock, flags); + + kfree(nport); +} + +static void +fcloop_nport_put(struct fcloop_nport *nport) +{ + kref_put(&nport->ref, fcloop_nport_free); +} + +static int +fcloop_nport_get(struct fcloop_nport *nport) +{ + return kref_get_unless_zero(&nport->ref); +} + +static void fcloop_localport_delete(struct nvme_fc_local_port *localport) { struct fcloop_lport *lport = localport->private; @@ -644,8 +668,7 @@ fcloop_remoteport_delete(struct nvme_fc_remote_port *remoteport) { struct fcloop_rport *rport = remoteport->private; - /* release any threads waiting for the unreg to complete */ - complete(&rport->nport->rport_unreg_done); + fcloop_nport_put(rport->nport); } static void @@ -653,8 +676,7 @@ fcloop_targetport_delete(struct nvmet_fc_target_port *targetport) { struct fcloop_tport *tport = targetport->private; - /* release any threads waiting for the unreg to complete */ - complete(&tport->nport->tport_unreg_done); + fcloop_nport_put(tport->nport); } #define FCLOOP_HW_QUEUES 4 @@ -722,6 +744,7 @@ fcloop_create_local_port(struct device *dev, struct device_attribute *attr, goto out_free_opts; } + memset(&pinfo, 0, sizeof(pinfo)); pinfo.node_name = opts->wwnn; pinfo.port_name = opts->wwpn; pinfo.port_role = opts->roles; @@ -804,32 +827,6 @@ fcloop_delete_local_port(struct device *dev, struct device_attribute *attr, return ret ? ret : count; } -static void -fcloop_nport_free(struct kref *ref) -{ - struct fcloop_nport *nport = - container_of(ref, struct fcloop_nport, ref); - unsigned long flags; - - spin_lock_irqsave(&fcloop_lock, flags); - list_del(&nport->nport_list); - spin_unlock_irqrestore(&fcloop_lock, flags); - - kfree(nport); -} - -static void -fcloop_nport_put(struct fcloop_nport *nport) -{ - kref_put(&nport->ref, fcloop_nport_free); -} - -static int -fcloop_nport_get(struct fcloop_nport *nport) -{ - return kref_get_unless_zero(&nport->ref); -} - static struct fcloop_nport * fcloop_alloc_nport(const char *buf, size_t count, bool remoteport) { @@ -938,6 +935,7 @@ fcloop_create_remote_port(struct device *dev, struct device_attribute *attr, if (!nport) return -EIO; + memset(&pinfo, 0, sizeof(pinfo)); pinfo.node_name = nport->node_name; pinfo.port_name = nport->port_name; pinfo.port_role = nport->port_role; @@ -979,24 +977,12 @@ __unlink_remote_port(struct fcloop_nport *nport) } static int -__wait_remoteport_unreg(struct fcloop_nport *nport, struct fcloop_rport *rport) +__remoteport_unreg(struct fcloop_nport *nport, struct fcloop_rport *rport) { - int ret; - if (!rport) return -EALREADY; - init_completion(&nport->rport_unreg_done); - - ret = nvme_fc_unregister_remoteport(rport->remoteport); - if (ret) - return ret; - - wait_for_completion(&nport->rport_unreg_done); - - fcloop_nport_put(nport); - - return ret; + return nvme_fc_unregister_remoteport(rport->remoteport); } static ssize_t @@ -1029,7 +1015,7 @@ fcloop_delete_remote_port(struct device *dev, struct device_attribute *attr, if (!nport) return -ENOENT; - ret = __wait_remoteport_unreg(nport, rport); + ret = __remoteport_unreg(nport, rport); return ret ? ret : count; } @@ -1086,24 +1072,12 @@ __unlink_target_port(struct fcloop_nport *nport) } static int -__wait_targetport_unreg(struct fcloop_nport *nport, struct fcloop_tport *tport) +__targetport_unreg(struct fcloop_nport *nport, struct fcloop_tport *tport) { - int ret; - if (!tport) return -EALREADY; - init_completion(&nport->tport_unreg_done); - - ret = nvmet_fc_unregister_targetport(tport->targetport); - if (ret) - return ret; - - wait_for_completion(&nport->tport_unreg_done); - - fcloop_nport_put(nport); - - return ret; + return nvmet_fc_unregister_targetport(tport->targetport); } static ssize_t @@ -1136,7 +1110,7 @@ fcloop_delete_target_port(struct device *dev, struct device_attribute *attr, if (!nport) return -ENOENT; - ret = __wait_targetport_unreg(nport, tport); + ret = __targetport_unreg(nport, tport); return ret ? ret : count; } @@ -1223,11 +1197,11 @@ static void __exit fcloop_exit(void) spin_unlock_irqrestore(&fcloop_lock, flags); - ret = __wait_targetport_unreg(nport, tport); + ret = __targetport_unreg(nport, tport); if (ret) pr_warn("%s: Failed deleting target port\n", __func__); - ret = __wait_remoteport_unreg(nport, rport); + ret = __remoteport_unreg(nport, rport); if (ret) pr_warn("%s: Failed deleting remote port\n", __func__); diff --git a/drivers/nvme/target/nvmet.h b/drivers/nvme/target/nvmet.h index 7d261ab894f4..7b8e20adf760 100644 --- a/drivers/nvme/target/nvmet.h +++ b/drivers/nvme/target/nvmet.h @@ -74,6 +74,7 @@ struct nvmet_sq { struct percpu_ref ref; u16 qid; u16 size; + u16 sqhd; struct completion free_done; struct completion confirm_done; }; diff --git a/drivers/nvmem/core.c b/drivers/nvmem/core.c index de54c7f5048a..d12e5de78e70 100644 --- a/drivers/nvmem/core.c +++ b/drivers/nvmem/core.c @@ -135,7 +135,7 @@ static ssize_t bin_attr_nvmem_write(struct file *filp, struct kobject *kobj, /* Stop the user from writing */ if (pos >= nvmem->size) - return 0; + return -EFBIG; if (count < nvmem->word_size) return -EINVAL; @@ -789,6 +789,7 @@ struct nvmem_cell *of_nvmem_cell_get(struct device_node *np, return ERR_PTR(-EINVAL); nvmem = __nvmem_device_get(nvmem_np, NULL, NULL); + of_node_put(nvmem_np); if (IS_ERR(nvmem)) return ERR_CAST(nvmem); diff --git a/drivers/pci/pci-sysfs.c b/drivers/pci/pci-sysfs.c index 1eecfa301f7f..8e075ea2743e 100644 --- a/drivers/pci/pci-sysfs.c +++ b/drivers/pci/pci-sysfs.c @@ -686,7 +686,7 @@ static ssize_t driver_override_store(struct device *dev, const char *buf, size_t count) { struct pci_dev *pdev = to_pci_dev(dev); - char *driver_override, *old = pdev->driver_override, *cp; + char *driver_override, *old, *cp; /* We need to keep extra room for a newline */ if (count >= (PAGE_SIZE - 1)) @@ -700,12 +700,15 @@ static ssize_t driver_override_store(struct device *dev, if (cp) *cp = '\0'; + device_lock(dev); + old = pdev->driver_override; if (strlen(driver_override)) { pdev->driver_override = driver_override; } else { kfree(driver_override); pdev->driver_override = NULL; } + device_unlock(dev); kfree(old); @@ -716,8 +719,12 @@ static ssize_t driver_override_show(struct device *dev, struct device_attribute *attr, char *buf) { struct pci_dev *pdev = to_pci_dev(dev); + ssize_t len; - return snprintf(buf, PAGE_SIZE, "%s\n", pdev->driver_override); + device_lock(dev); + len = snprintf(buf, PAGE_SIZE, "%s\n", pdev->driver_override); + device_unlock(dev); + return len; } static DEVICE_ATTR_RW(driver_override); diff --git a/drivers/platform/x86/fujitsu-laptop.c b/drivers/platform/x86/fujitsu-laptop.c index 85de30f93a9c..56a8195096a2 100644 --- a/drivers/platform/x86/fujitsu-laptop.c +++ b/drivers/platform/x86/fujitsu-laptop.c @@ -254,10 +254,12 @@ static int bl_update_status(struct backlight_device *b) { struct acpi_device *device = bl_get_data(b); - if (b->props.power == FB_BLANK_POWERDOWN) - call_fext_func(fext, FUNC_BACKLIGHT, 0x1, 0x4, 0x3); - else - call_fext_func(fext, FUNC_BACKLIGHT, 0x1, 0x4, 0x0); + if (fext) { + if (b->props.power == FB_BLANK_POWERDOWN) + call_fext_func(fext, FUNC_BACKLIGHT, 0x1, 0x4, 0x3); + else + call_fext_func(fext, FUNC_BACKLIGHT, 0x1, 0x4, 0x0); + } return set_lcd_level(device, b->props.brightness); } diff --git a/drivers/rapidio/devices/tsi721.c b/drivers/rapidio/devices/tsi721.c index 315a4be8dc1e..9a68914100ad 100644 --- a/drivers/rapidio/devices/tsi721.c +++ b/drivers/rapidio/devices/tsi721.c @@ -51,6 +51,8 @@ module_param(mbox_sel, byte, S_IRUGO); MODULE_PARM_DESC(mbox_sel, "RIO Messaging MBOX Selection Mask (default: 0x0f = all)"); +static DEFINE_SPINLOCK(tsi721_maint_lock); + static void tsi721_omsg_handler(struct tsi721_device *priv, int ch); static void tsi721_imsg_handler(struct tsi721_device *priv, int ch); @@ -124,12 +126,15 @@ static int tsi721_maint_dma(struct tsi721_device *priv, u32 sys_size, void __iomem *regs = priv->regs + TSI721_DMAC_BASE(priv->mdma.ch_id); struct tsi721_dma_desc *bd_ptr; u32 rd_count, swr_ptr, ch_stat; + unsigned long flags; int i, err = 0; u32 op = do_wr ? MAINT_WR : MAINT_RD; if (offset > (RIO_MAINT_SPACE_SZ - len) || (len != sizeof(u32))) return -EINVAL; + spin_lock_irqsave(&tsi721_maint_lock, flags); + bd_ptr = priv->mdma.bd_base; rd_count = ioread32(regs + TSI721_DMAC_DRDCNT); @@ -197,7 +202,9 @@ static int tsi721_maint_dma(struct tsi721_device *priv, u32 sys_size, */ swr_ptr = ioread32(regs + TSI721_DMAC_DSWP); iowrite32(swr_ptr, regs + TSI721_DMAC_DSRP); + err_out: + spin_unlock_irqrestore(&tsi721_maint_lock, flags); return err; } diff --git a/drivers/rapidio/rio-access.c b/drivers/rapidio/rio-access.c index a3824baca2e5..3ee9af83b638 100644 --- a/drivers/rapidio/rio-access.c +++ b/drivers/rapidio/rio-access.c @@ -14,16 +14,8 @@ #include <linux/module.h> /* - * These interrupt-safe spinlocks protect all accesses to RIO - * configuration space and doorbell access. - */ -static DEFINE_SPINLOCK(rio_config_lock); -static DEFINE_SPINLOCK(rio_doorbell_lock); - -/* * Wrappers for all RIO configuration access functions. They just check - * alignment, do locking and call the low-level functions pointed to - * by rio_mport->ops. + * alignment and call the low-level functions pointed to by rio_mport->ops. */ #define RIO_8_BAD 0 @@ -44,13 +36,10 @@ int __rio_local_read_config_##size \ (struct rio_mport *mport, u32 offset, type *value) \ { \ int res; \ - unsigned long flags; \ u32 data = 0; \ if (RIO_##size##_BAD) return RIO_BAD_SIZE; \ - spin_lock_irqsave(&rio_config_lock, flags); \ res = mport->ops->lcread(mport, mport->id, offset, len, &data); \ *value = (type)data; \ - spin_unlock_irqrestore(&rio_config_lock, flags); \ return res; \ } @@ -67,13 +56,8 @@ int __rio_local_read_config_##size \ int __rio_local_write_config_##size \ (struct rio_mport *mport, u32 offset, type value) \ { \ - int res; \ - unsigned long flags; \ if (RIO_##size##_BAD) return RIO_BAD_SIZE; \ - spin_lock_irqsave(&rio_config_lock, flags); \ - res = mport->ops->lcwrite(mport, mport->id, offset, len, value);\ - spin_unlock_irqrestore(&rio_config_lock, flags); \ - return res; \ + return mport->ops->lcwrite(mport, mport->id, offset, len, value);\ } RIO_LOP_READ(8, u8, 1) @@ -104,13 +88,10 @@ int rio_mport_read_config_##size \ (struct rio_mport *mport, u16 destid, u8 hopcount, u32 offset, type *value) \ { \ int res; \ - unsigned long flags; \ u32 data = 0; \ if (RIO_##size##_BAD) return RIO_BAD_SIZE; \ - spin_lock_irqsave(&rio_config_lock, flags); \ res = mport->ops->cread(mport, mport->id, destid, hopcount, offset, len, &data); \ *value = (type)data; \ - spin_unlock_irqrestore(&rio_config_lock, flags); \ return res; \ } @@ -127,13 +108,9 @@ int rio_mport_read_config_##size \ int rio_mport_write_config_##size \ (struct rio_mport *mport, u16 destid, u8 hopcount, u32 offset, type value) \ { \ - int res; \ - unsigned long flags; \ if (RIO_##size##_BAD) return RIO_BAD_SIZE; \ - spin_lock_irqsave(&rio_config_lock, flags); \ - res = mport->ops->cwrite(mport, mport->id, destid, hopcount, offset, len, value); \ - spin_unlock_irqrestore(&rio_config_lock, flags); \ - return res; \ + return mport->ops->cwrite(mport, mport->id, destid, hopcount, \ + offset, len, value); \ } RIO_OP_READ(8, u8, 1) @@ -162,14 +139,7 @@ EXPORT_SYMBOL_GPL(rio_mport_write_config_32); */ int rio_mport_send_doorbell(struct rio_mport *mport, u16 destid, u16 data) { - int res; - unsigned long flags; - - spin_lock_irqsave(&rio_doorbell_lock, flags); - res = mport->ops->dsend(mport, mport->id, destid, data); - spin_unlock_irqrestore(&rio_doorbell_lock, flags); - - return res; + return mport->ops->dsend(mport, mport->id, destid, data); } EXPORT_SYMBOL_GPL(rio_mport_send_doorbell); diff --git a/drivers/reset/Kconfig b/drivers/reset/Kconfig index e0c393214264..e2baecbb9dd3 100644 --- a/drivers/reset/Kconfig +++ b/drivers/reset/Kconfig @@ -34,11 +34,12 @@ config RESET_BERLIN help This enables the reset controller driver for Marvell Berlin SoCs. -config RESET_HSDK_V1 - bool "HSDK v1 Reset Driver" - default n +config RESET_HSDK + bool "Synopsys HSDK Reset Driver" + depends on HAS_IOMEM + depends on ARC_SOC_HSDK || COMPILE_TEST help - This enables the reset controller driver for HSDK v1. + This enables the reset controller driver for HSDK board. config RESET_IMX7 bool "i.MX7 Reset Driver" if COMPILE_TEST diff --git a/drivers/reset/Makefile b/drivers/reset/Makefile index d368367110e5..af1c15c330b3 100644 --- a/drivers/reset/Makefile +++ b/drivers/reset/Makefile @@ -5,7 +5,7 @@ obj-$(CONFIG_ARCH_TEGRA) += tegra/ obj-$(CONFIG_RESET_A10SR) += reset-a10sr.o obj-$(CONFIG_RESET_ATH79) += reset-ath79.o obj-$(CONFIG_RESET_BERLIN) += reset-berlin.o -obj-$(CONFIG_RESET_HSDK_V1) += reset-hsdk-v1.o +obj-$(CONFIG_RESET_HSDK) += reset-hsdk.o obj-$(CONFIG_RESET_IMX7) += reset-imx7.o obj-$(CONFIG_RESET_LANTIQ) += reset-lantiq.o obj-$(CONFIG_RESET_LPC18XX) += reset-lpc18xx.o diff --git a/drivers/reset/reset-hsdk-v1.c b/drivers/reset/reset-hsdk.c index bca13e4bf622..8bce391c6943 100644 --- a/drivers/reset/reset-hsdk-v1.c +++ b/drivers/reset/reset-hsdk.c @@ -1,7 +1,7 @@ /* * Copyright (C) 2017 Synopsys. * - * Synopsys HSDKv1 SDP reset driver. + * Synopsys HSDK Development platform reset driver. * * This file is licensed under the terms of the GNU General Public * License version 2. This program is licensed "as is" without any @@ -18,9 +18,9 @@ #include <linux/slab.h> #include <linux/types.h> -#define to_hsdkv1_rst(p) container_of((p), struct hsdkv1_rst, rcdev) +#define to_hsdk_rst(p) container_of((p), struct hsdk_rst, rcdev) -struct hsdkv1_rst { +struct hsdk_rst { void __iomem *regs_ctl; void __iomem *regs_rst; spinlock_t lock; @@ -49,12 +49,12 @@ static const u32 rst_map[] = { #define CGU_IP_SW_RESET_RESET BIT(0) #define SW_RESET_TIMEOUT 10000 -static void hsdkv1_reset_config(struct hsdkv1_rst *rst, unsigned long id) +static void hsdk_reset_config(struct hsdk_rst *rst, unsigned long id) { writel(rst_map[id], rst->regs_ctl + CGU_SYS_RST_CTRL); } -static int hsdkv1_reset_do(struct hsdkv1_rst *rst) +static int hsdk_reset_do(struct hsdk_rst *rst) { u32 reg; @@ -69,28 +69,28 @@ static int hsdkv1_reset_do(struct hsdkv1_rst *rst) !(reg & CGU_IP_SW_RESET_RESET), 5, SW_RESET_TIMEOUT); } -static int hsdkv1_reset_reset(struct reset_controller_dev *rcdev, +static int hsdk_reset_reset(struct reset_controller_dev *rcdev, unsigned long id) { - struct hsdkv1_rst *rst = to_hsdkv1_rst(rcdev); + struct hsdk_rst *rst = to_hsdk_rst(rcdev); unsigned long flags; int ret; spin_lock_irqsave(&rst->lock, flags); - hsdkv1_reset_config(rst, id); - ret = hsdkv1_reset_do(rst); + hsdk_reset_config(rst, id); + ret = hsdk_reset_do(rst); spin_unlock_irqrestore(&rst->lock, flags); return ret; } -static const struct reset_control_ops hsdkv1_reset_ops = { - .reset = hsdkv1_reset_reset, +static const struct reset_control_ops hsdk_reset_ops = { + .reset = hsdk_reset_reset, }; -static int hsdkv1_reset_probe(struct platform_device *pdev) +static int hsdk_reset_probe(struct platform_device *pdev) { - struct hsdkv1_rst *rst; + struct hsdk_rst *rst; struct resource *mem; rst = devm_kzalloc(&pdev->dev, sizeof(*rst), GFP_KERNEL); @@ -110,7 +110,7 @@ static int hsdkv1_reset_probe(struct platform_device *pdev) spin_lock_init(&rst->lock); rst->rcdev.owner = THIS_MODULE; - rst->rcdev.ops = &hsdkv1_reset_ops; + rst->rcdev.ops = &hsdk_reset_ops; rst->rcdev.of_node = pdev->dev.of_node; rst->rcdev.nr_resets = HSDK_MAX_RESETS; rst->rcdev.of_reset_n_cells = 1; @@ -118,20 +118,20 @@ static int hsdkv1_reset_probe(struct platform_device *pdev) return reset_controller_register(&rst->rcdev); } -static const struct of_device_id hsdkv1_reset_dt_match[] = { - { .compatible = "snps,hsdk-v1.0-reset" }, +static const struct of_device_id hsdk_reset_dt_match[] = { + { .compatible = "snps,hsdk-reset" }, { }, }; -static struct platform_driver hsdkv1_reset_driver = { - .probe = hsdkv1_reset_probe, +static struct platform_driver hsdk_reset_driver = { + .probe = hsdk_reset_probe, .driver = { - .name = "hsdk-v1.0-reset", - .of_match_table = hsdkv1_reset_dt_match, + .name = "hsdk-reset", + .of_match_table = hsdk_reset_dt_match, }, }; -builtin_platform_driver(hsdkv1_reset_driver); +builtin_platform_driver(hsdk_reset_driver); MODULE_AUTHOR("Eugeniy Paltsev <Eugeniy.Paltsev@synopsys.com>"); -MODULE_DESCRIPTION("Synopsys HSDKv1 SDP reset driver"); +MODULE_DESCRIPTION("Synopsys HSDK SDP reset driver"); MODULE_LICENSE("GPL v2"); diff --git a/drivers/scsi/aacraid/aachba.c b/drivers/scsi/aacraid/aachba.c index a64285ab0728..af3e4d3f9735 100644 --- a/drivers/scsi/aacraid/aachba.c +++ b/drivers/scsi/aacraid/aachba.c @@ -699,13 +699,13 @@ static void _aac_probe_container1(void * context, struct fib * fibptr) int status; dresp = (struct aac_mount *) fib_data(fibptr); - if (!(fibptr->dev->supplement_adapter_info.supported_options2 & - AAC_OPTION_VARIABLE_BLOCK_SIZE)) + if (!aac_supports_2T(fibptr->dev)) { dresp->mnt[0].capacityhigh = 0; - if ((le32_to_cpu(dresp->status) != ST_OK) || - (le32_to_cpu(dresp->mnt[0].vol) != CT_NONE)) { - _aac_probe_container2(context, fibptr); - return; + if ((le32_to_cpu(dresp->status) == ST_OK) && + (le32_to_cpu(dresp->mnt[0].vol) != CT_NONE)) { + _aac_probe_container2(context, fibptr); + return; + } } scsicmd = (struct scsi_cmnd *) context; diff --git a/drivers/scsi/aacraid/aacraid.h b/drivers/scsi/aacraid/aacraid.h index 92fabf2b0c24..403a639574e5 100644 --- a/drivers/scsi/aacraid/aacraid.h +++ b/drivers/scsi/aacraid/aacraid.h @@ -2701,6 +2701,11 @@ static inline int aac_is_src(struct aac_dev *dev) return 0; } +static inline int aac_supports_2T(struct aac_dev *dev) +{ + return (dev->adapter_info.options & AAC_OPT_NEW_COMM_64); +} + char * get_container_type(unsigned type); extern int numacb; extern char aac_driver_version[]; diff --git a/drivers/scsi/aacraid/linit.c b/drivers/scsi/aacraid/linit.c index 87cc4a93e637..62beb2596466 100644 --- a/drivers/scsi/aacraid/linit.c +++ b/drivers/scsi/aacraid/linit.c @@ -906,12 +906,14 @@ static int aac_eh_dev_reset(struct scsi_cmnd *cmd) bus = aac_logical_to_phys(scmd_channel(cmd)); cid = scmd_id(cmd); - info = &aac->hba_map[bus][cid]; - if (bus >= AAC_MAX_BUSES || cid >= AAC_MAX_TARGETS || - info->devtype != AAC_DEVTYPE_NATIVE_RAW) + + if (bus >= AAC_MAX_BUSES || cid >= AAC_MAX_TARGETS) return FAILED; - if (info->reset_state > 0) + info = &aac->hba_map[bus][cid]; + + if (info->devtype != AAC_DEVTYPE_NATIVE_RAW && + info->reset_state > 0) return FAILED; pr_err("%s: Host adapter reset request. SCSI hang ?\n", @@ -962,12 +964,14 @@ static int aac_eh_target_reset(struct scsi_cmnd *cmd) bus = aac_logical_to_phys(scmd_channel(cmd)); cid = scmd_id(cmd); - info = &aac->hba_map[bus][cid]; - if (bus >= AAC_MAX_BUSES || cid >= AAC_MAX_TARGETS || - info->devtype != AAC_DEVTYPE_NATIVE_RAW) + + if (bus >= AAC_MAX_BUSES || cid >= AAC_MAX_TARGETS) return FAILED; - if (info->reset_state > 0) + info = &aac->hba_map[bus][cid]; + + if (info->devtype != AAC_DEVTYPE_NATIVE_RAW && + info->reset_state > 0) return FAILED; pr_err("%s: Host adapter reset request. SCSI hang ?\n", diff --git a/drivers/scsi/aacraid/src.c b/drivers/scsi/aacraid/src.c index 48c2b2b34b72..0c9361c87ec8 100644 --- a/drivers/scsi/aacraid/src.c +++ b/drivers/scsi/aacraid/src.c @@ -740,6 +740,8 @@ static void aac_send_iop_reset(struct aac_dev *dev) aac_set_intx_mode(dev); src_writel(dev, MUnit.IDR, IOP_SRC_RESET_MASK); + + msleep(5000); } static void aac_send_hardware_soft_reset(struct aac_dev *dev) diff --git a/drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.c b/drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.c index 785fb42f6650..2799a6b08f73 100644 --- a/drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.c +++ b/drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.c @@ -3767,7 +3767,7 @@ static int ibmvscsis_write_pending(struct se_cmd *se_cmd) */ if ((vscsi->flags & (CLIENT_FAILED | RESPONSE_Q_DOWN))) { pr_err("write_pending failed since: %d\n", vscsi->flags); - return 0; + return -EIO; } rc = srp_transfer_data(cmd, &vio_iu(iue)->srp.cmd, ibmvscsis_rdma, diff --git a/drivers/scsi/libiscsi.c b/drivers/scsi/libiscsi.c index bd4605a34f54..c62e8d111fd9 100644 --- a/drivers/scsi/libiscsi.c +++ b/drivers/scsi/libiscsi.c @@ -2851,9 +2851,6 @@ EXPORT_SYMBOL_GPL(iscsi_session_setup); /** * iscsi_session_teardown - destroy session, host, and cls_session * @cls_session: iscsi session - * - * The driver must have called iscsi_remove_session before - * calling this. */ void iscsi_session_teardown(struct iscsi_cls_session *cls_session) { @@ -2863,6 +2860,8 @@ void iscsi_session_teardown(struct iscsi_cls_session *cls_session) iscsi_pool_free(&session->cmdpool); + iscsi_remove_session(cls_session); + kfree(session->password); kfree(session->password_in); kfree(session->username); @@ -2877,7 +2876,8 @@ void iscsi_session_teardown(struct iscsi_cls_session *cls_session) kfree(session->portal_type); kfree(session->discovery_parent_type); - iscsi_destroy_session(cls_session); + iscsi_free_session(cls_session); + iscsi_host_dec_session_cnt(shost); module_put(owner); } diff --git a/drivers/scsi/lpfc/lpfc_init.c b/drivers/scsi/lpfc/lpfc_init.c index 7e7ae786121b..100bc4c8798d 100644 --- a/drivers/scsi/lpfc/lpfc_init.c +++ b/drivers/scsi/lpfc/lpfc_init.c @@ -6131,6 +6131,7 @@ lpfc_sli4_driver_resource_setup(struct lpfc_hba *phba) "Extents and RPI headers enabled.\n"); } mempool_free(mboxq, phba->mbox_mem_pool); + rc = -EIO; goto out_free_bsmbx; } diff --git a/drivers/scsi/lpfc/lpfc_nvme.c b/drivers/scsi/lpfc/lpfc_nvme.c index 79ba3ce063a4..23bdb1ca106e 100644 --- a/drivers/scsi/lpfc/lpfc_nvme.c +++ b/drivers/scsi/lpfc/lpfc_nvme.c @@ -884,7 +884,7 @@ out_err: wcqe->total_data_placed); nCmd->transferred_length = 0; nCmd->rcv_rsplen = 0; - nCmd->status = NVME_SC_FC_TRANSPORT_ERROR; + nCmd->status = NVME_SC_INTERNAL; } } diff --git a/drivers/scsi/qla2xxx/qla_nvme.c b/drivers/scsi/qla2xxx/qla_nvme.c index 1f59e7a74c7b..6b33a1f24f56 100644 --- a/drivers/scsi/qla2xxx/qla_nvme.c +++ b/drivers/scsi/qla2xxx/qla_nvme.c @@ -180,7 +180,7 @@ static void qla_nvme_sp_done(void *ptr, int res) goto rel; if (unlikely(res == QLA_FUNCTION_FAILED)) - fd->status = NVME_SC_FC_TRANSPORT_ERROR; + fd->status = NVME_SC_INTERNAL; else fd->status = 0; diff --git a/drivers/scsi/scsi_error.c b/drivers/scsi/scsi_error.c index 38942050b265..dab876c65473 100644 --- a/drivers/scsi/scsi_error.c +++ b/drivers/scsi/scsi_error.c @@ -580,7 +580,8 @@ int scsi_check_sense(struct scsi_cmnd *scmd) if (sshdr.asc == 0x20 || /* Invalid command operation code */ sshdr.asc == 0x21 || /* Logical block address out of range */ sshdr.asc == 0x24 || /* Invalid field in cdb */ - sshdr.asc == 0x26) { /* Parameter value invalid */ + sshdr.asc == 0x26 || /* Parameter value invalid */ + sshdr.asc == 0x27) { /* Write protected */ set_host_byte(scmd, DID_TARGET_FAILURE); } return SUCCESS; diff --git a/drivers/scsi/scsi_scan.c b/drivers/scsi/scsi_scan.c index e7818afeda2b..15590a063ad9 100644 --- a/drivers/scsi/scsi_scan.c +++ b/drivers/scsi/scsi_scan.c @@ -956,6 +956,9 @@ static int scsi_add_lun(struct scsi_device *sdev, unsigned char *inq_result, if (*bflags & BLIST_NO_DIF) sdev->no_dif = 1; + if (*bflags & BLIST_UNMAP_LIMIT_WS) + sdev->unmap_limit_for_ws = 1; + sdev->eh_timeout = SCSI_DEFAULT_EH_TIMEOUT; if (*bflags & BLIST_TRY_VPD_PAGES) diff --git a/drivers/scsi/scsi_transport_fc.c b/drivers/scsi/scsi_transport_fc.c index ba9d70f8a6a1..cbd4495d0ff9 100644 --- a/drivers/scsi/scsi_transport_fc.c +++ b/drivers/scsi/scsi_transport_fc.c @@ -2739,7 +2739,8 @@ fc_remote_port_add(struct Scsi_Host *shost, int channel, list_for_each_entry(rport, &fc_host->rports, peers) { - if ((rport->port_state == FC_PORTSTATE_BLOCKED) && + if ((rport->port_state == FC_PORTSTATE_BLOCKED || + rport->port_state == FC_PORTSTATE_NOTPRESENT) && (rport->channel == channel)) { switch (fc_host->tgtid_bind_type) { @@ -2876,7 +2877,6 @@ fc_remote_port_add(struct Scsi_Host *shost, int channel, memcpy(&rport->port_name, &ids->port_name, sizeof(rport->port_name)); rport->port_id = ids->port_id; - rport->roles = ids->roles; rport->port_state = FC_PORTSTATE_ONLINE; rport->flags &= ~FC_RPORT_FAST_FAIL_TIMEDOUT; @@ -2885,15 +2885,7 @@ fc_remote_port_add(struct Scsi_Host *shost, int channel, fci->f->dd_fcrport_size); spin_unlock_irqrestore(shost->host_lock, flags); - if (ids->roles & FC_PORT_ROLE_FCP_TARGET) { - scsi_target_unblock(&rport->dev, SDEV_RUNNING); - - /* initiate a scan of the target */ - spin_lock_irqsave(shost->host_lock, flags); - rport->flags |= FC_RPORT_SCAN_PENDING; - scsi_queue_work(shost, &rport->scan_work); - spin_unlock_irqrestore(shost->host_lock, flags); - } + fc_remote_port_rolechg(rport, ids->roles); return rport; } } diff --git a/drivers/scsi/scsi_transport_iscsi.c b/drivers/scsi/scsi_transport_iscsi.c index 8934f19bce8e..7404d26895f5 100644 --- a/drivers/scsi/scsi_transport_iscsi.c +++ b/drivers/scsi/scsi_transport_iscsi.c @@ -2211,22 +2211,6 @@ void iscsi_free_session(struct iscsi_cls_session *session) EXPORT_SYMBOL_GPL(iscsi_free_session); /** - * iscsi_destroy_session - destroy iscsi session - * @session: iscsi_session - * - * Can be called by a LLD or iscsi_transport. There must not be - * any running connections. - */ -int iscsi_destroy_session(struct iscsi_cls_session *session) -{ - iscsi_remove_session(session); - ISCSI_DBG_TRANS_SESSION(session, "Completing session destruction\n"); - iscsi_free_session(session); - return 0; -} -EXPORT_SYMBOL_GPL(iscsi_destroy_session); - -/** * iscsi_create_conn - create iscsi class connection * @session: iscsi cls session * @dd_size: private driver data size @@ -3689,7 +3673,7 @@ iscsi_if_rx(struct sk_buff *skb) uint32_t group; nlh = nlmsg_hdr(skb); - if (nlh->nlmsg_len < sizeof(*nlh) || + if (nlh->nlmsg_len < sizeof(*nlh) + sizeof(*ev) || skb->len < nlh->nlmsg_len) { break; } diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c index fb9f8b5f4673..d175c5c5ccf8 100644 --- a/drivers/scsi/sd.c +++ b/drivers/scsi/sd.c @@ -715,13 +715,21 @@ static void sd_config_discard(struct scsi_disk *sdkp, unsigned int mode) break; case SD_LBP_WS16: - max_blocks = min_not_zero(sdkp->max_ws_blocks, - (u32)SD_MAX_WS16_BLOCKS); + if (sdkp->device->unmap_limit_for_ws) + max_blocks = sdkp->max_unmap_blocks; + else + max_blocks = sdkp->max_ws_blocks; + + max_blocks = min_not_zero(max_blocks, (u32)SD_MAX_WS16_BLOCKS); break; case SD_LBP_WS10: - max_blocks = min_not_zero(sdkp->max_ws_blocks, - (u32)SD_MAX_WS10_BLOCKS); + if (sdkp->device->unmap_limit_for_ws) + max_blocks = sdkp->max_unmap_blocks; + else + max_blocks = sdkp->max_ws_blocks; + + max_blocks = min_not_zero(max_blocks, (u32)SD_MAX_WS10_BLOCKS); break; case SD_LBP_ZERO: @@ -3099,8 +3107,6 @@ static int sd_revalidate_disk(struct gendisk *disk) sd_read_security(sdkp, buffer); } - sdkp->first_scan = 0; - /* * We now have all cache related info, determine how we deal * with flush requests. @@ -3115,7 +3121,7 @@ static int sd_revalidate_disk(struct gendisk *disk) q->limits.max_dev_sectors = logical_to_sectors(sdp, dev_max); /* - * Use the device's preferred I/O size for reads and writes + * Determine the device's preferred I/O size for reads and writes * unless the reported value is unreasonably small, large, or * garbage. */ @@ -3129,8 +3135,19 @@ static int sd_revalidate_disk(struct gendisk *disk) rw_max = min_not_zero(logical_to_sectors(sdp, dev_max), (sector_t)BLK_DEF_MAX_SECTORS); - /* Combine with controller limits */ - q->limits.max_sectors = min(rw_max, queue_max_hw_sectors(q)); + /* Do not exceed controller limit */ + rw_max = min(rw_max, queue_max_hw_sectors(q)); + + /* + * Only update max_sectors if previously unset or if the current value + * exceeds the capabilities of the hardware. + */ + if (sdkp->first_scan || + q->limits.max_sectors > q->limits.max_dev_sectors || + q->limits.max_sectors > q->limits.max_hw_sectors) + q->limits.max_sectors = rw_max; + + sdkp->first_scan = 0; set_capacity(disk, logical_to_sectors(sdp, sdkp->capacity)); sd_config_write_same(sdkp); diff --git a/drivers/staging/iio/adc/ad7192.c b/drivers/staging/iio/adc/ad7192.c index d11c6de9c777..6150d2780e22 100644 --- a/drivers/staging/iio/adc/ad7192.c +++ b/drivers/staging/iio/adc/ad7192.c @@ -223,11 +223,9 @@ static int ad7192_setup(struct ad7192_state *st, struct iio_dev *indio_dev = spi_get_drvdata(st->sd.spi); unsigned long long scale_uv; int i, ret, id; - u8 ones[6]; /* reset the serial interface */ - memset(&ones, 0xFF, 6); - ret = spi_write(st->sd.spi, &ones, 6); + ret = ad_sd_reset(&st->sd, 48); if (ret < 0) goto out; usleep_range(500, 1000); /* Wait for at least 500us */ diff --git a/drivers/staging/lustre/lnet/Kconfig b/drivers/staging/lustre/lnet/Kconfig index 2b5930150cda..6bcb53d0c6f4 100644 --- a/drivers/staging/lustre/lnet/Kconfig +++ b/drivers/staging/lustre/lnet/Kconfig @@ -34,7 +34,7 @@ config LNET_SELFTEST config LNET_XPRT_IB tristate "LNET infiniband support" - depends on LNET && INFINIBAND && INFINIBAND_ADDR_TRANS + depends on LNET && PCI && INFINIBAND && INFINIBAND_ADDR_TRANS default LNET && INFINIBAND help This option allows the LNET users to use infiniband as an diff --git a/drivers/staging/mt29f_spinand/mt29f_spinand.c b/drivers/staging/mt29f_spinand/mt29f_spinand.c index 13eaf16ecd16..87595c594b12 100644 --- a/drivers/staging/mt29f_spinand/mt29f_spinand.c +++ b/drivers/staging/mt29f_spinand/mt29f_spinand.c @@ -496,8 +496,12 @@ static int spinand_program_page(struct spi_device *spi_nand, if (!wbuf) return -ENOMEM; - enable_read_hw_ecc = 0; - spinand_read_page(spi_nand, page_id, 0, CACHE_BUF, wbuf); + enable_read_hw_ecc = 1; + retval = spinand_read_page(spi_nand, page_id, 0, CACHE_BUF, wbuf); + if (retval < 0) { + dev_err(&spi_nand->dev, "ecc error on read page!!!\n"); + return retval; + } for (i = offset, j = 0; i < len; i++, j++) wbuf[i] &= buf[j]; diff --git a/drivers/staging/pi433/rf69.c b/drivers/staging/pi433/rf69.c index c4b1b218ea38..290b419aa9dd 100644 --- a/drivers/staging/pi433/rf69.c +++ b/drivers/staging/pi433/rf69.c @@ -570,12 +570,6 @@ int rf69_set_dio_mapping(struct spi_device *spi, u8 DIONumber, u8 value) dev_dbg(&spi->dev, "set: DIO mapping"); #endif - // check DIO number - if (DIONumber > 5) { - dev_dbg(&spi->dev, "set: illegal input param"); - return -EINVAL; - } - switch (DIONumber) { case 0: mask=MASK_DIO0; shift=SHIFT_DIO0; regaddr=REG_DIOMAPPING1; break; case 1: mask=MASK_DIO1; shift=SHIFT_DIO1; regaddr=REG_DIOMAPPING1; break; @@ -583,6 +577,9 @@ int rf69_set_dio_mapping(struct spi_device *spi, u8 DIONumber, u8 value) case 3: mask=MASK_DIO3; shift=SHIFT_DIO3; regaddr=REG_DIOMAPPING1; break; case 4: mask=MASK_DIO4; shift=SHIFT_DIO4; regaddr=REG_DIOMAPPING2; break; case 5: mask=MASK_DIO5; shift=SHIFT_DIO5; regaddr=REG_DIOMAPPING2; break; + default: + dev_dbg(&spi->dev, "set: illegal input param"); + return -EINVAL; } // read reg diff --git a/drivers/staging/rtl8723bs/core/rtw_mlme.c b/drivers/staging/rtl8723bs/core/rtw_mlme.c index 6b778206a1a3..cb8a95aabd6c 100644 --- a/drivers/staging/rtl8723bs/core/rtw_mlme.c +++ b/drivers/staging/rtl8723bs/core/rtw_mlme.c @@ -119,9 +119,8 @@ void rtw_free_mlme_priv_ie_data(struct mlme_priv *pmlmepriv) void _rtw_free_mlme_priv(struct mlme_priv *pmlmepriv) { - rtw_free_mlme_priv_ie_data(pmlmepriv); - if (pmlmepriv) { + rtw_free_mlme_priv_ie_data(pmlmepriv); if (pmlmepriv->free_bss_buf) { vfree(pmlmepriv->free_bss_buf); } diff --git a/drivers/staging/rtl8723bs/os_dep/rtw_proc.c b/drivers/staging/rtl8723bs/os_dep/rtw_proc.c index 92277457aba4..ce1dd6f9036f 100644 --- a/drivers/staging/rtl8723bs/os_dep/rtw_proc.c +++ b/drivers/staging/rtl8723bs/os_dep/rtw_proc.c @@ -311,6 +311,8 @@ static ssize_t proc_set_cam(struct file *file, const char __user *buffer, size_t if (num < 2) return count; + if (id >= TOTAL_CAM_ENTRY) + return -EINVAL; if (strcmp("c", cmd) == 0) { _clear_cam_entry(adapter, id); diff --git a/drivers/staging/rtlwifi/halmac/halmac_88xx/halmac_api_88xx.c b/drivers/staging/rtlwifi/halmac/halmac_88xx/halmac_api_88xx.c index 5f84526cb5b5..edbf6af1c8b7 100644 --- a/drivers/staging/rtlwifi/halmac/halmac_88xx/halmac_api_88xx.c +++ b/drivers/staging/rtlwifi/halmac/halmac_88xx/halmac_api_88xx.c @@ -2901,11 +2901,11 @@ halmac_update_datapack_88xx(struct halmac_adapter *halmac_adapter, if (halmac_adapter->fw_version.h2c_version < 4) return HALMAC_RET_FW_NO_SUPPORT; + driver_adapter = halmac_adapter->driver_adapter; + HALMAC_RT_TRACE(driver_adapter, HALMAC_MSG_H2C, DBG_DMESG, "[TRACE]%s ==========>\n", __func__); - driver_adapter = halmac_adapter->driver_adapter; - HALMAC_RT_TRACE(driver_adapter, HALMAC_MSG_H2C, DBG_DMESG, "[TRACE]%s <==========\n", __func__); diff --git a/drivers/staging/rtlwifi/halmac/halmac_88xx/halmac_func_88xx.c b/drivers/staging/rtlwifi/halmac/halmac_88xx/halmac_func_88xx.c index f33024e4d853..544f638ed3ef 100644 --- a/drivers/staging/rtlwifi/halmac/halmac_88xx/halmac_func_88xx.c +++ b/drivers/staging/rtlwifi/halmac/halmac_88xx/halmac_func_88xx.c @@ -1618,10 +1618,11 @@ halmac_send_h2c_set_pwr_mode_88xx(struct halmac_adapter *halmac_adapter, void *driver_adapter = NULL; enum halmac_ret_status status = HALMAC_RET_SUCCESS; + driver_adapter = halmac_adapter->driver_adapter; + HALMAC_RT_TRACE(driver_adapter, HALMAC_MSG_H2C, DBG_DMESG, "%s!!\n", __func__); - driver_adapter = halmac_adapter->driver_adapter; h2c_header = h2c_buff; h2c_cmd = h2c_header + HALMAC_H2C_CMD_HDR_SIZE_88XX; @@ -1713,10 +1714,11 @@ halmac_media_status_rpt_88xx(struct halmac_adapter *halmac_adapter, u8 op_mode, void *driver_adapter = NULL; enum halmac_ret_status status = HALMAC_RET_SUCCESS; + driver_adapter = halmac_adapter->driver_adapter; + HALMAC_RT_TRACE(driver_adapter, HALMAC_MSG_H2C, DBG_DMESG, "halmac_send_h2c_set_pwr_mode_88xx!!\n"); - driver_adapter = halmac_adapter->driver_adapter; h2c_header = H2c_buff; h2c_cmd = h2c_header + HALMAC_H2C_CMD_HDR_SIZE_88XX; @@ -2143,10 +2145,11 @@ halmac_func_ctrl_ch_switch_88xx(struct halmac_adapter *halmac_adapter, enum halmac_cmd_process_status *process_status = &halmac_adapter->halmac_state.scan_state_set.process_status; + driver_adapter = halmac_adapter->driver_adapter; + HALMAC_RT_TRACE(driver_adapter, HALMAC_MSG_H2C, DBG_DMESG, "halmac_ctrl_ch_switch!!\n"); - driver_adapter = halmac_adapter->driver_adapter; halmac_api = (struct halmac_api *)halmac_adapter->halmac_api; if (halmac_transition_scan_state_88xx( @@ -2276,15 +2279,13 @@ enum halmac_ret_status halmac_send_h2c_update_bcn_parse_info_88xx( { u8 h2c_buff[HALMAC_H2C_CMD_SIZE_88XX] = {0}; u16 h2c_seq_mum = 0; - void *driver_adapter = NULL; + void *driver_adapter = halmac_adapter->driver_adapter; struct halmac_h2c_header_info h2c_header_info; enum halmac_ret_status status = HALMAC_RET_SUCCESS; HALMAC_RT_TRACE(driver_adapter, HALMAC_MSG_H2C, DBG_DMESG, "%s!!\n", __func__); - driver_adapter = halmac_adapter->driver_adapter; - UPDATE_BEACON_PARSING_INFO_SET_FUNC_EN(h2c_buff, bcn_ie_info->func_en); UPDATE_BEACON_PARSING_INFO_SET_SIZE_TH(h2c_buff, bcn_ie_info->size_th); UPDATE_BEACON_PARSING_INFO_SET_TIMEOUT(h2c_buff, bcn_ie_info->timeout); diff --git a/drivers/staging/speakup/main.c b/drivers/staging/speakup/main.c index 67956e24779c..56f7be6af1f6 100644 --- a/drivers/staging/speakup/main.c +++ b/drivers/staging/speakup/main.c @@ -1376,6 +1376,8 @@ static void reset_highlight_buffers(struct vc_data *); static int read_all_key; +static int in_keyboard_notifier; + static void start_read_all_timer(struct vc_data *vc, int command); enum { @@ -1408,7 +1410,10 @@ static void read_all_doc(struct vc_data *vc) cursor_track = read_all_mode; spk_reset_index_count(0); if (get_sentence_buf(vc, 0) == -1) { - kbd_fakekey2(vc, RA_DOWN_ARROW); + del_timer(&cursor_timer); + if (!in_keyboard_notifier) + speakup_fake_down_arrow(); + start_read_all_timer(vc, RA_DOWN_ARROW); } else { say_sentence_num(0, 0); synth_insert_next_index(0); @@ -2212,8 +2217,10 @@ static int keyboard_notifier_call(struct notifier_block *nb, int ret = NOTIFY_OK; static int keycode; /* to hold the current keycode */ + in_keyboard_notifier = 1; + if (vc->vc_mode == KD_GRAPHICS) - return ret; + goto out; /* * First, determine whether we are handling a fake keypress on @@ -2225,7 +2232,7 @@ static int keyboard_notifier_call(struct notifier_block *nb, */ if (speakup_fake_key_pressed()) - return ret; + goto out; switch (code) { case KBD_KEYCODE: @@ -2266,6 +2273,8 @@ static int keyboard_notifier_call(struct notifier_block *nb, break; } } +out: + in_keyboard_notifier = 0; return ret; } diff --git a/drivers/staging/unisys/visorbus/visorchipset.c b/drivers/staging/unisys/visorbus/visorchipset.c index 74cce4f1a7bd..27ecf6fb49fd 100644 --- a/drivers/staging/unisys/visorbus/visorchipset.c +++ b/drivers/staging/unisys/visorbus/visorchipset.c @@ -1826,7 +1826,7 @@ static __init int visorutil_spar_detect(void) return 0; } -static int init_unisys(void) +static int __init init_unisys(void) { int result; @@ -1841,7 +1841,7 @@ static int init_unisys(void) return 0; }; -static void exit_unisys(void) +static void __exit exit_unisys(void) { acpi_bus_unregister_driver(&unisys_acpi_driver); } diff --git a/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_2835_arm.c b/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_2835_arm.c index 0159ca4407d8..be08849175ea 100644 --- a/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_2835_arm.c +++ b/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_2835_arm.c @@ -612,18 +612,20 @@ free_pagelist(struct vchiq_pagelist_info *pagelistinfo, if (head_bytes > actual) head_bytes = actual; - memcpy((char *)page_address(pages[0]) + + memcpy((char *)kmap(pages[0]) + pagelist->offset, fragments, head_bytes); + kunmap(pages[0]); } if ((actual >= 0) && (head_bytes < actual) && (tail_bytes != 0)) { - memcpy((char *)page_address(pages[num_pages - 1]) + + memcpy((char *)kmap(pages[num_pages - 1]) + ((pagelist->offset + actual) & (PAGE_SIZE - 1) & ~(g_cache_line_size - 1)), fragments + g_cache_line_size, tail_bytes); + kunmap(pages[num_pages - 1]); } down(&g_free_fragments_mutex); diff --git a/drivers/tty/mxser.c b/drivers/tty/mxser.c index 1c0c9553bc05..7dd38047ba23 100644 --- a/drivers/tty/mxser.c +++ b/drivers/tty/mxser.c @@ -246,11 +246,11 @@ struct mxser_port { unsigned char err_shadow; struct async_icount icount; /* kernel counters for 4 input interrupts */ - int timeout; + unsigned int timeout; int read_status_mask; int ignore_status_mask; - int xmit_fifo_size; + unsigned int xmit_fifo_size; int xmit_head; int xmit_tail; int xmit_cnt; @@ -572,8 +572,9 @@ static void mxser_dtr_rts(struct tty_port *port, int on) static int mxser_set_baud(struct tty_struct *tty, long newspd) { struct mxser_port *info = tty->driver_data; - int quot = 0, baud; + unsigned int quot = 0, baud; unsigned char cval; + u64 timeout; if (!info->ioaddr) return -1; @@ -594,8 +595,13 @@ static int mxser_set_baud(struct tty_struct *tty, long newspd) quot = 0; } - info->timeout = ((info->xmit_fifo_size * HZ * 10 * quot) / info->baud_base); - info->timeout += HZ / 50; /* Add .02 seconds of slop */ + /* + * worst case (128 * 1000 * 10 * 18432) needs 35 bits, so divide in the + * u64 domain + */ + timeout = (u64)info->xmit_fifo_size * HZ * 10 * quot; + do_div(timeout, info->baud_base); + info->timeout = timeout + HZ / 50; /* Add .02 seconds of slop */ if (quot) { info->MCR |= UART_MCR_DTR; diff --git a/drivers/tty/serial/bcm63xx_uart.c b/drivers/tty/serial/bcm63xx_uart.c index 583c9a0c7ecc..8c48c3784831 100644 --- a/drivers/tty/serial/bcm63xx_uart.c +++ b/drivers/tty/serial/bcm63xx_uart.c @@ -507,9 +507,14 @@ static void bcm_uart_set_termios(struct uart_port *port, { unsigned int ctl, baud, quot, ier; unsigned long flags; + int tries; spin_lock_irqsave(&port->lock, flags); + /* Drain the hot tub fully before we power it off for the winter. */ + for (tries = 3; !bcm_uart_tx_empty(port) && tries; tries--) + mdelay(10); + /* disable uart while changing speed */ bcm_uart_disable(port); bcm_uart_flush(port); diff --git a/drivers/tty/serial/fsl_lpuart.c b/drivers/tty/serial/fsl_lpuart.c index 849c1f9991ce..f0252184291e 100644 --- a/drivers/tty/serial/fsl_lpuart.c +++ b/drivers/tty/serial/fsl_lpuart.c @@ -1276,7 +1276,6 @@ static void rx_dma_timer_init(struct lpuart_port *sport) static int lpuart_startup(struct uart_port *port) { struct lpuart_port *sport = container_of(port, struct lpuart_port, port); - int ret; unsigned long flags; unsigned char temp; @@ -1291,11 +1290,6 @@ static int lpuart_startup(struct uart_port *port) sport->rxfifo_size = 0x1 << (((temp >> UARTPFIFO_RXSIZE_OFF) & UARTPFIFO_FIFOSIZE_MASK) + 1); - ret = devm_request_irq(port->dev, port->irq, lpuart_int, 0, - DRIVER_NAME, sport); - if (ret) - return ret; - spin_lock_irqsave(&sport->port.lock, flags); lpuart_setup_watermark(sport); @@ -1333,7 +1327,6 @@ static int lpuart_startup(struct uart_port *port) static int lpuart32_startup(struct uart_port *port) { struct lpuart_port *sport = container_of(port, struct lpuart_port, port); - int ret; unsigned long flags; unsigned long temp; @@ -1346,11 +1339,6 @@ static int lpuart32_startup(struct uart_port *port) sport->rxfifo_size = 0x1 << (((temp >> UARTFIFO_RXSIZE_OFF) & UARTFIFO_FIFOSIZE_MASK) - 1); - ret = devm_request_irq(port->dev, port->irq, lpuart32_int, 0, - DRIVER_NAME, sport); - if (ret) - return ret; - spin_lock_irqsave(&sport->port.lock, flags); lpuart32_setup_watermark(sport); @@ -1380,8 +1368,6 @@ static void lpuart_shutdown(struct uart_port *port) spin_unlock_irqrestore(&port->lock, flags); - devm_free_irq(port->dev, port->irq, sport); - if (sport->lpuart_dma_rx_use) { del_timer_sync(&sport->lpuart_timer); lpuart_dma_rx_free(&sport->port); @@ -1400,7 +1386,6 @@ static void lpuart_shutdown(struct uart_port *port) static void lpuart32_shutdown(struct uart_port *port) { - struct lpuart_port *sport = container_of(port, struct lpuart_port, port); unsigned long temp; unsigned long flags; @@ -1413,8 +1398,6 @@ static void lpuart32_shutdown(struct uart_port *port) lpuart32_write(port, temp, UARTCTRL); spin_unlock_irqrestore(&port->lock, flags); - - devm_free_irq(port->dev, port->irq, sport); } static void @@ -2212,16 +2195,22 @@ static int lpuart_probe(struct platform_device *pdev) platform_set_drvdata(pdev, &sport->port); - if (lpuart_is_32(sport)) + if (lpuart_is_32(sport)) { lpuart_reg.cons = LPUART32_CONSOLE; - else + ret = devm_request_irq(&pdev->dev, sport->port.irq, lpuart32_int, 0, + DRIVER_NAME, sport); + } else { lpuart_reg.cons = LPUART_CONSOLE; + ret = devm_request_irq(&pdev->dev, sport->port.irq, lpuart_int, 0, + DRIVER_NAME, sport); + } + + if (ret) + goto failed_irq_request; ret = uart_add_one_port(&lpuart_reg, &sport->port); - if (ret) { - clk_disable_unprepare(sport->clk); - return ret; - } + if (ret) + goto failed_attach_port; sport->dma_tx_chan = dma_request_slave_channel(sport->port.dev, "tx"); if (!sport->dma_tx_chan) @@ -2240,6 +2229,11 @@ static int lpuart_probe(struct platform_device *pdev) } return 0; + +failed_attach_port: +failed_irq_request: + clk_disable_unprepare(sport->clk); + return ret; } static int lpuart_remove(struct platform_device *pdev) diff --git a/drivers/tty/serial/sccnxp.c b/drivers/tty/serial/sccnxp.c index cdd2f942317c..b9c7a904c1ea 100644 --- a/drivers/tty/serial/sccnxp.c +++ b/drivers/tty/serial/sccnxp.c @@ -889,7 +889,16 @@ static int sccnxp_probe(struct platform_device *pdev) goto err_out; uartclk = 0; } else { - clk_prepare_enable(clk); + ret = clk_prepare_enable(clk); + if (ret) + goto err_out; + + ret = devm_add_action_or_reset(&pdev->dev, + (void(*)(void *))clk_disable_unprepare, + clk); + if (ret) + goto err_out; + uartclk = clk_get_rate(clk); } @@ -988,7 +997,7 @@ static int sccnxp_probe(struct platform_device *pdev) uart_unregister_driver(&s->uart); err_out: if (!IS_ERR(s->regulator)) - return regulator_disable(s->regulator); + regulator_disable(s->regulator); return ret; } diff --git a/drivers/usb/class/cdc-wdm.c b/drivers/usb/class/cdc-wdm.c index 5aacea1978a5..3e865dbf878c 100644 --- a/drivers/usb/class/cdc-wdm.c +++ b/drivers/usb/class/cdc-wdm.c @@ -190,8 +190,10 @@ static void wdm_in_callback(struct urb *urb) /* * only set a new error if there is no previous error. * Errors are only cleared during read/open + * Avoid propagating -EPIPE (stall) to userspace since it is + * better handled as an empty read */ - if (desc->rerr == 0) + if (desc->rerr == 0 && status != -EPIPE) desc->rerr = status; if (length + desc->length > desc->wMaxCommand) { diff --git a/drivers/usb/core/config.c b/drivers/usb/core/config.c index 4be52c602e9b..68b54bd88d1e 100644 --- a/drivers/usb/core/config.c +++ b/drivers/usb/core/config.c @@ -643,15 +643,23 @@ static int usb_parse_configuration(struct usb_device *dev, int cfgidx, } else if (header->bDescriptorType == USB_DT_INTERFACE_ASSOCIATION) { + struct usb_interface_assoc_descriptor *d; + + d = (struct usb_interface_assoc_descriptor *)header; + if (d->bLength < USB_DT_INTERFACE_ASSOCIATION_SIZE) { + dev_warn(ddev, + "config %d has an invalid interface association descriptor of length %d, skipping\n", + cfgno, d->bLength); + continue; + } + if (iad_num == USB_MAXIADS) { dev_warn(ddev, "found more Interface " "Association Descriptors " "than allocated for in " "configuration %d\n", cfgno); } else { - config->intf_assoc[iad_num] = - (struct usb_interface_assoc_descriptor - *)header; + config->intf_assoc[iad_num] = d; iad_num++; } @@ -852,7 +860,7 @@ int usb_get_configuration(struct usb_device *dev) } if (dev->quirks & USB_QUIRK_DELAY_INIT) - msleep(100); + msleep(200); result = usb_get_descriptor(dev, USB_DT_CONFIG, cfgno, bigbuffer, length); diff --git a/drivers/usb/core/devio.c b/drivers/usb/core/devio.c index 318bb3b96687..4664e543cf2f 100644 --- a/drivers/usb/core/devio.c +++ b/drivers/usb/core/devio.c @@ -140,6 +140,9 @@ module_param(usbfs_memory_mb, uint, 0644); MODULE_PARM_DESC(usbfs_memory_mb, "maximum MB allowed for usbfs buffers (0 = no limit)"); +/* Hard limit, necessary to avoid arithmetic overflow */ +#define USBFS_XFER_MAX (UINT_MAX / 2 - 1000000) + static atomic64_t usbfs_memory_usage; /* Total memory currently allocated */ /* Check whether it's okay to allocate more memory for a transfer */ @@ -1460,6 +1463,8 @@ static int proc_do_submiturb(struct usb_dev_state *ps, struct usbdevfs_urb *uurb USBDEVFS_URB_ZERO_PACKET | USBDEVFS_URB_NO_INTERRUPT)) return -EINVAL; + if ((unsigned int)uurb->buffer_length >= USBFS_XFER_MAX) + return -EINVAL; if (uurb->buffer_length > 0 && !uurb->buffer) return -EINVAL; if (!(uurb->type == USBDEVFS_URB_TYPE_CONTROL && @@ -1571,7 +1576,11 @@ static int proc_do_submiturb(struct usb_dev_state *ps, struct usbdevfs_urb *uurb totlen += isopkt[u].length; } u *= sizeof(struct usb_iso_packet_descriptor); - uurb->buffer_length = totlen; + if (totlen <= uurb->buffer_length) + uurb->buffer_length = totlen; + else + WARN_ONCE(1, "uurb->buffer_length is too short %d vs %d", + totlen, uurb->buffer_length); break; default: diff --git a/drivers/usb/core/hub.c b/drivers/usb/core/hub.c index 41eaf0b52518..b5c733613823 100644 --- a/drivers/usb/core/hub.c +++ b/drivers/usb/core/hub.c @@ -4838,7 +4838,7 @@ static void hub_port_connect(struct usb_hub *hub, int port1, u16 portstatus, goto loop; if (udev->quirks & USB_QUIRK_DELAY_INIT) - msleep(1000); + msleep(2000); /* consecutive bus-powered hubs aren't reliable; they can * violate the voltage drop budget. if the new child has diff --git a/drivers/usb/core/message.c b/drivers/usb/core/message.c index 4c38ea41ae96..371a07d874a3 100644 --- a/drivers/usb/core/message.c +++ b/drivers/usb/core/message.c @@ -2069,6 +2069,10 @@ int cdc_parse_cdc_header(struct usb_cdc_parsed_header *hdr, elength = 1; goto next_desc; } + if ((buflen < elength) || (elength < 3)) { + dev_err(&intf->dev, "invalid descriptor buffer length\n"); + break; + } if (buffer[1] != USB_DT_CS_INTERFACE) { dev_err(&intf->dev, "skipping garbage\n"); goto next_desc; diff --git a/drivers/usb/dwc3/dwc3-of-simple.c b/drivers/usb/dwc3/dwc3-of-simple.c index 4cef7d4f9cd0..a26d1fde0f5e 100644 --- a/drivers/usb/dwc3/dwc3-of-simple.c +++ b/drivers/usb/dwc3/dwc3-of-simple.c @@ -177,6 +177,7 @@ static const struct of_device_id of_dwc3_simple_match[] = { { .compatible = "rockchip,rk3399-dwc3" }, { .compatible = "xlnx,zynqmp-dwc3" }, { .compatible = "cavium,octeon-7130-usb-uctl" }, + { .compatible = "sprd,sc9860-dwc3" }, { /* Sentinel */ } }; MODULE_DEVICE_TABLE(of, of_dwc3_simple_match); diff --git a/drivers/usb/dwc3/ep0.c b/drivers/usb/dwc3/ep0.c index 827e376bfa97..75e6cb044eb2 100644 --- a/drivers/usb/dwc3/ep0.c +++ b/drivers/usb/dwc3/ep0.c @@ -990,6 +990,8 @@ static void __dwc3_ep0_do_control_data(struct dwc3 *dwc, DWC3_TRBCTL_CONTROL_DATA, true); + req->trb = &dwc->ep0_trb[dep->trb_enqueue - 1]; + /* Now prepare one extra TRB to align transfer size */ dwc3_ep0_prepare_one_trb(dep, dwc->bounce_addr, maxpacket - rem, @@ -1015,6 +1017,8 @@ static void __dwc3_ep0_do_control_data(struct dwc3 *dwc, DWC3_TRBCTL_CONTROL_DATA, true); + req->trb = &dwc->ep0_trb[dep->trb_enqueue - 1]; + /* Now prepare one extra TRB to align transfer size */ dwc3_ep0_prepare_one_trb(dep, dwc->bounce_addr, 0, DWC3_TRBCTL_CONTROL_DATA, @@ -1029,6 +1033,9 @@ static void __dwc3_ep0_do_control_data(struct dwc3 *dwc, dwc3_ep0_prepare_one_trb(dep, req->request.dma, req->request.length, DWC3_TRBCTL_CONTROL_DATA, false); + + req->trb = &dwc->ep0_trb[dep->trb_enqueue]; + ret = dwc3_ep0_start_trans(dep); } diff --git a/drivers/usb/gadget/function/f_fs.c b/drivers/usb/gadget/function/f_fs.c index 9990944a7245..8b342587f8ad 100644 --- a/drivers/usb/gadget/function/f_fs.c +++ b/drivers/usb/gadget/function/f_fs.c @@ -46,7 +46,8 @@ static void ffs_data_get(struct ffs_data *ffs); static void ffs_data_put(struct ffs_data *ffs); /* Creates new ffs_data object. */ -static struct ffs_data *__must_check ffs_data_new(void) __attribute__((malloc)); +static struct ffs_data *__must_check ffs_data_new(const char *dev_name) + __attribute__((malloc)); /* Opened counter handling. */ static void ffs_data_opened(struct ffs_data *ffs); @@ -780,11 +781,12 @@ static void ffs_epfile_async_io_complete(struct usb_ep *_ep, struct usb_request *req) { struct ffs_io_data *io_data = req->context; + struct ffs_data *ffs = io_data->ffs; ENTER(); INIT_WORK(&io_data->work, ffs_user_copy_worker); - schedule_work(&io_data->work); + queue_work(ffs->io_completion_wq, &io_data->work); } static void __ffs_epfile_read_buffer_free(struct ffs_epfile *epfile) @@ -1500,7 +1502,7 @@ ffs_fs_mount(struct file_system_type *t, int flags, if (unlikely(ret < 0)) return ERR_PTR(ret); - ffs = ffs_data_new(); + ffs = ffs_data_new(dev_name); if (unlikely(!ffs)) return ERR_PTR(-ENOMEM); ffs->file_perms = data.perms; @@ -1610,6 +1612,7 @@ static void ffs_data_put(struct ffs_data *ffs) BUG_ON(waitqueue_active(&ffs->ev.waitq) || waitqueue_active(&ffs->ep0req_completion.wait) || waitqueue_active(&ffs->wait)); + destroy_workqueue(ffs->io_completion_wq); kfree(ffs->dev_name); kfree(ffs); } @@ -1642,7 +1645,7 @@ static void ffs_data_closed(struct ffs_data *ffs) ffs_data_put(ffs); } -static struct ffs_data *ffs_data_new(void) +static struct ffs_data *ffs_data_new(const char *dev_name) { struct ffs_data *ffs = kzalloc(sizeof *ffs, GFP_KERNEL); if (unlikely(!ffs)) @@ -1650,6 +1653,12 @@ static struct ffs_data *ffs_data_new(void) ENTER(); + ffs->io_completion_wq = alloc_ordered_workqueue("%s", 0, dev_name); + if (!ffs->io_completion_wq) { + kfree(ffs); + return NULL; + } + refcount_set(&ffs->ref, 1); atomic_set(&ffs->opened, 0); ffs->state = FFS_READ_DESCRIPTORS; diff --git a/drivers/usb/gadget/function/f_mass_storage.c b/drivers/usb/gadget/function/f_mass_storage.c index d6bd0244b008..5153e29870c3 100644 --- a/drivers/usb/gadget/function/f_mass_storage.c +++ b/drivers/usb/gadget/function/f_mass_storage.c @@ -307,8 +307,6 @@ struct fsg_common { struct completion thread_notifier; struct task_struct *thread_task; - /* Callback functions. */ - const struct fsg_operations *ops; /* Gadget's private data. */ void *private_data; @@ -2438,6 +2436,7 @@ static void handle_exception(struct fsg_common *common) static int fsg_main_thread(void *common_) { struct fsg_common *common = common_; + int i; /* * Allow the thread to be killed by a signal, but set the signal mask @@ -2476,21 +2475,16 @@ static int fsg_main_thread(void *common_) common->thread_task = NULL; spin_unlock_irq(&common->lock); - if (!common->ops || !common->ops->thread_exits - || common->ops->thread_exits(common) < 0) { - int i; + /* Eject media from all LUNs */ - down_write(&common->filesem); - for (i = 0; i < ARRAY_SIZE(common->luns); i++) { - struct fsg_lun *curlun = common->luns[i]; - if (!curlun || !fsg_lun_is_open(curlun)) - continue; + down_write(&common->filesem); + for (i = 0; i < ARRAY_SIZE(common->luns); i++) { + struct fsg_lun *curlun = common->luns[i]; + if (curlun && fsg_lun_is_open(curlun)) fsg_lun_close(curlun); - curlun->unit_attention_data = SS_MEDIUM_NOT_PRESENT; - } - up_write(&common->filesem); } + up_write(&common->filesem); /* Let fsg_unbind() know the thread has exited */ complete_and_exit(&common->thread_notifier, 0); @@ -2681,13 +2675,6 @@ void fsg_common_remove_luns(struct fsg_common *common) } EXPORT_SYMBOL_GPL(fsg_common_remove_luns); -void fsg_common_set_ops(struct fsg_common *common, - const struct fsg_operations *ops) -{ - common->ops = ops; -} -EXPORT_SYMBOL_GPL(fsg_common_set_ops); - void fsg_common_free_buffers(struct fsg_common *common) { _fsg_common_free_buffers(common->buffhds, common->fsg_num_buffers); diff --git a/drivers/usb/gadget/function/f_mass_storage.h b/drivers/usb/gadget/function/f_mass_storage.h index d3902313b8ac..dc05ca0c4359 100644 --- a/drivers/usb/gadget/function/f_mass_storage.h +++ b/drivers/usb/gadget/function/f_mass_storage.h @@ -60,17 +60,6 @@ struct fsg_module_parameters { struct fsg_common; /* FSF callback functions */ -struct fsg_operations { - /* - * Callback function to call when thread exits. If no - * callback is set or it returns value lower then zero MSF - * will force eject all LUNs it operates on (including those - * marked as non-removable or with prevent_medium_removal flag - * set). - */ - int (*thread_exits)(struct fsg_common *common); -}; - struct fsg_lun_opts { struct config_group group; struct fsg_lun *lun; @@ -142,9 +131,6 @@ void fsg_common_remove_lun(struct fsg_lun *lun); void fsg_common_remove_luns(struct fsg_common *common); -void fsg_common_set_ops(struct fsg_common *common, - const struct fsg_operations *ops); - int fsg_common_create_lun(struct fsg_common *common, struct fsg_lun_config *cfg, unsigned int id, const char *name, const char **name_pfx); diff --git a/drivers/usb/gadget/function/f_printer.c b/drivers/usb/gadget/function/f_printer.c index 8df244fc9d80..ea0da35a44e2 100644 --- a/drivers/usb/gadget/function/f_printer.c +++ b/drivers/usb/gadget/function/f_printer.c @@ -555,6 +555,7 @@ printer_write(struct file *fd, const char __user *buf, size_t len, loff_t *ptr) size_t size; /* Amount of data in a TX request. */ size_t bytes_copied = 0; struct usb_request *req; + int value; DBG(dev, "printer_write trying to send %d bytes\n", (int)len); @@ -634,7 +635,11 @@ printer_write(struct file *fd, const char __user *buf, size_t len, loff_t *ptr) return -EAGAIN; } - if (usb_ep_queue(dev->in_ep, req, GFP_ATOMIC)) { + /* here, we unlock, and only unlock, to avoid deadlock. */ + spin_unlock(&dev->lock); + value = usb_ep_queue(dev->in_ep, req, GFP_ATOMIC); + spin_lock(&dev->lock); + if (value) { list_add(&req->list, &dev->tx_reqs); spin_unlock_irqrestore(&dev->lock, flags); mutex_unlock(&dev->lock_printer_io); diff --git a/drivers/usb/gadget/function/u_fs.h b/drivers/usb/gadget/function/u_fs.h index 540f1c48c1a8..79f70ebf85dc 100644 --- a/drivers/usb/gadget/function/u_fs.h +++ b/drivers/usb/gadget/function/u_fs.h @@ -279,6 +279,7 @@ struct ffs_data { } file_perms; struct eventfd_ctx *ffs_eventfd; + struct workqueue_struct *io_completion_wq; bool no_disconnect; struct work_struct reset_work; diff --git a/drivers/usb/gadget/legacy/inode.c b/drivers/usb/gadget/legacy/inode.c index 684900fcfe24..5c28bee327e1 100644 --- a/drivers/usb/gadget/legacy/inode.c +++ b/drivers/usb/gadget/legacy/inode.c @@ -28,7 +28,7 @@ #include <linux/aio.h> #include <linux/uio.h> #include <linux/refcount.h> - +#include <linux/delay.h> #include <linux/device.h> #include <linux/moduleparam.h> @@ -116,6 +116,7 @@ enum ep0_state { struct dev_data { spinlock_t lock; refcount_t count; + int udc_usage; enum ep0_state state; /* P: lock */ struct usb_gadgetfs_event event [N_EVENT]; unsigned ev_next; @@ -513,9 +514,9 @@ static void ep_aio_complete(struct usb_ep *ep, struct usb_request *req) INIT_WORK(&priv->work, ep_user_copy_worker); schedule_work(&priv->work); } - spin_unlock(&epdata->dev->lock); usb_ep_free_request(ep, req); + spin_unlock(&epdata->dev->lock); put_ep(epdata); } @@ -939,9 +940,11 @@ ep0_read (struct file *fd, char __user *buf, size_t len, loff_t *ptr) struct usb_request *req = dev->req; if ((retval = setup_req (ep, req, 0)) == 0) { + ++dev->udc_usage; spin_unlock_irq (&dev->lock); retval = usb_ep_queue (ep, req, GFP_KERNEL); spin_lock_irq (&dev->lock); + --dev->udc_usage; } dev->state = STATE_DEV_CONNECTED; @@ -983,11 +986,14 @@ ep0_read (struct file *fd, char __user *buf, size_t len, loff_t *ptr) retval = -EIO; else { len = min (len, (size_t)dev->req->actual); -// FIXME don't call this with the spinlock held ... + ++dev->udc_usage; + spin_unlock_irq(&dev->lock); if (copy_to_user (buf, dev->req->buf, len)) retval = -EFAULT; else retval = len; + spin_lock_irq(&dev->lock); + --dev->udc_usage; clean_req (dev->gadget->ep0, dev->req); /* NOTE userspace can't yet choose to stall */ } @@ -1131,6 +1137,7 @@ ep0_write (struct file *fd, const char __user *buf, size_t len, loff_t *ptr) retval = setup_req (dev->gadget->ep0, dev->req, len); if (retval == 0) { dev->state = STATE_DEV_CONNECTED; + ++dev->udc_usage; spin_unlock_irq (&dev->lock); if (copy_from_user (dev->req->buf, buf, len)) retval = -EFAULT; @@ -1142,6 +1149,7 @@ ep0_write (struct file *fd, const char __user *buf, size_t len, loff_t *ptr) GFP_KERNEL); } spin_lock_irq(&dev->lock); + --dev->udc_usage; if (retval < 0) { clean_req (dev->gadget->ep0, dev->req); } else @@ -1243,9 +1251,21 @@ static long dev_ioctl (struct file *fd, unsigned code, unsigned long value) struct usb_gadget *gadget = dev->gadget; long ret = -ENOTTY; - if (gadget->ops->ioctl) + spin_lock_irq(&dev->lock); + if (dev->state == STATE_DEV_OPENED || + dev->state == STATE_DEV_UNBOUND) { + /* Not bound to a UDC */ + } else if (gadget->ops->ioctl) { + ++dev->udc_usage; + spin_unlock_irq(&dev->lock); + ret = gadget->ops->ioctl (gadget, code, value); + spin_lock_irq(&dev->lock); + --dev->udc_usage; + } + spin_unlock_irq(&dev->lock); + return ret; } @@ -1463,10 +1483,12 @@ delegate: if (value < 0) break; + ++dev->udc_usage; spin_unlock (&dev->lock); value = usb_ep_queue (gadget->ep0, dev->req, GFP_KERNEL); spin_lock (&dev->lock); + --dev->udc_usage; if (value < 0) { clean_req (gadget->ep0, dev->req); break; @@ -1490,8 +1512,12 @@ delegate: req->length = value; req->zero = value < w_length; + ++dev->udc_usage; spin_unlock (&dev->lock); value = usb_ep_queue (gadget->ep0, req, GFP_KERNEL); + spin_lock(&dev->lock); + --dev->udc_usage; + spin_unlock(&dev->lock); if (value < 0) { DBG (dev, "ep_queue --> %d\n", value); req->status = 0; @@ -1518,21 +1544,24 @@ static void destroy_ep_files (struct dev_data *dev) /* break link to FS */ ep = list_first_entry (&dev->epfiles, struct ep_data, epfiles); list_del_init (&ep->epfiles); + spin_unlock_irq (&dev->lock); + dentry = ep->dentry; ep->dentry = NULL; parent = d_inode(dentry->d_parent); /* break link to controller */ + mutex_lock(&ep->lock); if (ep->state == STATE_EP_ENABLED) (void) usb_ep_disable (ep->ep); ep->state = STATE_EP_UNBOUND; usb_ep_free_request (ep->ep, ep->req); ep->ep = NULL; + mutex_unlock(&ep->lock); + wake_up (&ep->wait); put_ep (ep); - spin_unlock_irq (&dev->lock); - /* break link to dcache */ inode_lock(parent); d_delete (dentry); @@ -1603,6 +1632,11 @@ gadgetfs_unbind (struct usb_gadget *gadget) spin_lock_irq (&dev->lock); dev->state = STATE_DEV_UNBOUND; + while (dev->udc_usage > 0) { + spin_unlock_irq(&dev->lock); + usleep_range(1000, 2000); + spin_lock_irq(&dev->lock); + } spin_unlock_irq (&dev->lock); destroy_ep_files (dev); diff --git a/drivers/usb/gadget/legacy/mass_storage.c b/drivers/usb/gadget/legacy/mass_storage.c index e99ab57ee3e5..fcba59782f26 100644 --- a/drivers/usb/gadget/legacy/mass_storage.c +++ b/drivers/usb/gadget/legacy/mass_storage.c @@ -107,15 +107,6 @@ static unsigned int fsg_num_buffers = CONFIG_USB_GADGET_STORAGE_NUM_BUFFERS; FSG_MODULE_PARAMETERS(/* no prefix */, mod_data); -static unsigned long msg_registered; -static void msg_cleanup(void); - -static int msg_thread_exits(struct fsg_common *common) -{ - msg_cleanup(); - return 0; -} - static int msg_do_config(struct usb_configuration *c) { struct fsg_opts *opts; @@ -154,9 +145,6 @@ static struct usb_configuration msg_config_driver = { static int msg_bind(struct usb_composite_dev *cdev) { - static const struct fsg_operations ops = { - .thread_exits = msg_thread_exits, - }; struct fsg_opts *opts; struct fsg_config config; int status; @@ -173,8 +161,6 @@ static int msg_bind(struct usb_composite_dev *cdev) if (status) goto fail; - fsg_common_set_ops(opts->common, &ops); - status = fsg_common_set_cdev(opts->common, cdev, config.can_stall); if (status) goto fail_set_cdev; @@ -256,18 +242,12 @@ MODULE_LICENSE("GPL"); static int __init msg_init(void) { - int ret; - - ret = usb_composite_probe(&msg_driver); - set_bit(0, &msg_registered); - - return ret; + return usb_composite_probe(&msg_driver); } module_init(msg_init); -static void msg_cleanup(void) +static void __exit msg_cleanup(void) { - if (test_and_clear_bit(0, &msg_registered)) - usb_composite_unregister(&msg_driver); + usb_composite_unregister(&msg_driver); } module_exit(msg_cleanup); diff --git a/drivers/usb/gadget/udc/Kconfig b/drivers/usb/gadget/udc/Kconfig index 7cd5c969fcbe..1e9567091d86 100644 --- a/drivers/usb/gadget/udc/Kconfig +++ b/drivers/usb/gadget/udc/Kconfig @@ -273,6 +273,7 @@ config USB_SNP_CORE config USB_SNP_UDC_PLAT tristate "Synopsys USB 2.0 Device controller" depends on USB_GADGET && OF && HAS_DMA + depends on EXTCON || EXTCON=n select USB_GADGET_DUALSPEED select USB_SNP_CORE default ARCH_BCM_IPROC diff --git a/drivers/usb/gadget/udc/atmel_usba_udc.c b/drivers/usb/gadget/udc/atmel_usba_udc.c index 98d71400f8a1..a884c022df7a 100644 --- a/drivers/usb/gadget/udc/atmel_usba_udc.c +++ b/drivers/usb/gadget/udc/atmel_usba_udc.c @@ -29,6 +29,8 @@ #include <linux/of_gpio.h> #include "atmel_usba_udc.h" +#define USBA_VBUS_IRQFLAGS (IRQF_ONESHOT \ + | IRQF_TRIGGER_FALLING | IRQF_TRIGGER_RISING) #ifdef CONFIG_USB_GADGET_DEBUG_FS #include <linux/debugfs.h> @@ -2361,7 +2363,7 @@ static int usba_udc_probe(struct platform_device *pdev) IRQ_NOAUTOEN); ret = devm_request_threaded_irq(&pdev->dev, gpio_to_irq(udc->vbus_pin), NULL, - usba_vbus_irq_thread, IRQF_ONESHOT, + usba_vbus_irq_thread, USBA_VBUS_IRQFLAGS, "atmel_usba_udc", udc); if (ret) { udc->vbus_pin = -ENODEV; diff --git a/drivers/usb/gadget/udc/core.c b/drivers/usb/gadget/udc/core.c index 75c51ca4ee0f..d41d07aae0ce 100644 --- a/drivers/usb/gadget/udc/core.c +++ b/drivers/usb/gadget/udc/core.c @@ -1320,8 +1320,7 @@ static int udc_bind_to_driver(struct usb_udc *udc, struct usb_gadget_driver *dri udc->dev.driver = &driver->driver; udc->gadget->dev.driver = &driver->driver; - if (driver->max_speed < udc->gadget->max_speed) - usb_gadget_udc_set_speed(udc, driver->max_speed); + usb_gadget_udc_set_speed(udc, driver->max_speed); ret = driver->bind(udc->gadget, driver); if (ret) diff --git a/drivers/usb/gadget/udc/dummy_hcd.c b/drivers/usb/gadget/udc/dummy_hcd.c index a030d7923d7d..b17618a55f1b 100644 --- a/drivers/usb/gadget/udc/dummy_hcd.c +++ b/drivers/usb/gadget/udc/dummy_hcd.c @@ -237,6 +237,8 @@ struct dummy_hcd { struct usb_device *udev; struct list_head urbp_list; + struct urbp *next_frame_urbp; + u32 stream_en_ep; u8 num_stream[30 / 2]; @@ -253,11 +255,13 @@ struct dummy { */ struct dummy_ep ep[DUMMY_ENDPOINTS]; int address; + int callback_usage; struct usb_gadget gadget; struct usb_gadget_driver *driver; struct dummy_request fifo_req; u8 fifo_buf[FIFO_SIZE]; u16 devstatus; + unsigned ints_enabled:1; unsigned udc_suspended:1; unsigned pullup:1; @@ -375,11 +379,10 @@ static void set_link_state_by_speed(struct dummy_hcd *dum_hcd) USB_PORT_STAT_CONNECTION) == 0) dum_hcd->port_status |= (USB_PORT_STAT_C_CONNECTION << 16); - if ((dum_hcd->port_status & - USB_PORT_STAT_ENABLE) == 1 && - (dum_hcd->port_status & - USB_SS_PORT_LS_U0) == 1 && - dum_hcd->rh_state != DUMMY_RH_SUSPENDED) + if ((dum_hcd->port_status & USB_PORT_STAT_ENABLE) && + (dum_hcd->port_status & + USB_PORT_STAT_LINK_STATE) == USB_SS_PORT_LS_U0 && + dum_hcd->rh_state != DUMMY_RH_SUSPENDED) dum_hcd->active = 1; } } else { @@ -440,18 +443,27 @@ static void set_link_state(struct dummy_hcd *dum_hcd) (~dum_hcd->old_status) & dum_hcd->port_status; /* Report reset and disconnect events to the driver */ - if (dum->driver && (disconnect || reset)) { + if (dum->ints_enabled && (disconnect || reset)) { stop_activity(dum); + ++dum->callback_usage; + spin_unlock(&dum->lock); if (reset) usb_gadget_udc_reset(&dum->gadget, dum->driver); else dum->driver->disconnect(&dum->gadget); + spin_lock(&dum->lock); + --dum->callback_usage; } - } else if (dum_hcd->active != dum_hcd->old_active) { + } else if (dum_hcd->active != dum_hcd->old_active && + dum->ints_enabled) { + ++dum->callback_usage; + spin_unlock(&dum->lock); if (dum_hcd->old_active && dum->driver->suspend) dum->driver->suspend(&dum->gadget); else if (!dum_hcd->old_active && dum->driver->resume) dum->driver->resume(&dum->gadget); + spin_lock(&dum->lock); + --dum->callback_usage; } dum_hcd->old_status = dum_hcd->port_status; @@ -972,8 +984,11 @@ static int dummy_udc_start(struct usb_gadget *g, * can't enumerate without help from the driver we're binding. */ + spin_lock_irq(&dum->lock); dum->devstatus = 0; dum->driver = driver; + dum->ints_enabled = 1; + spin_unlock_irq(&dum->lock); return 0; } @@ -984,6 +999,16 @@ static int dummy_udc_stop(struct usb_gadget *g) struct dummy *dum = dum_hcd->dum; spin_lock_irq(&dum->lock); + dum->ints_enabled = 0; + stop_activity(dum); + + /* emulate synchronize_irq(): wait for callbacks to finish */ + while (dum->callback_usage > 0) { + spin_unlock_irq(&dum->lock); + usleep_range(1000, 2000); + spin_lock_irq(&dum->lock); + } + dum->driver = NULL; spin_unlock_irq(&dum->lock); @@ -1037,7 +1062,12 @@ static int dummy_udc_probe(struct platform_device *pdev) 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; + if (mod_data.is_super_speed) + dum->gadget.max_speed = USB_SPEED_SUPER; + else if (mod_data.is_high_speed) + dum->gadget.max_speed = USB_SPEED_HIGH; + else + dum->gadget.max_speed = USB_SPEED_FULL; dum->gadget.dev.parent = &pdev->dev; init_dummy_udc_hw(dum); @@ -1246,6 +1276,8 @@ static int dummy_urb_enqueue( list_add_tail(&urbp->urbp_list, &dum_hcd->urbp_list); urb->hcpriv = urbp; + if (!dum_hcd->next_frame_urbp) + dum_hcd->next_frame_urbp = urbp; if (usb_pipetype(urb->pipe) == PIPE_CONTROL) urb->error_count = 1; /* mark as a new urb */ @@ -1521,6 +1553,8 @@ static struct dummy_ep *find_endpoint(struct dummy *dum, u8 address) if (!is_active((dum->gadget.speed == USB_SPEED_SUPER ? dum->ss_hcd : dum->hs_hcd))) return NULL; + if (!dum->ints_enabled) + return NULL; if ((address & ~USB_DIR_IN) == 0) return &dum->ep[0]; for (i = 1; i < DUMMY_ENDPOINTS; i++) { @@ -1762,6 +1796,7 @@ static void dummy_timer(unsigned long _dum_hcd) spin_unlock_irqrestore(&dum->lock, flags); return; } + dum_hcd->next_frame_urbp = NULL; for (i = 0; i < DUMMY_ENDPOINTS; i++) { if (!ep_info[i].name) @@ -1778,6 +1813,10 @@ restart: int type; int status = -EINPROGRESS; + /* stop when we reach URBs queued after the timer interrupt */ + if (urbp == dum_hcd->next_frame_urbp) + break; + urb = urbp->urb; if (urb->unlinked) goto return_urb; @@ -1857,10 +1896,12 @@ restart: * until setup() returns; no reentrancy issues etc. */ if (value > 0) { + ++dum->callback_usage; spin_unlock(&dum->lock); value = dum->driver->setup(&dum->gadget, &setup); spin_lock(&dum->lock); + --dum->callback_usage; if (value >= 0) { /* no delays (max 64KB data stage) */ @@ -2561,8 +2602,6 @@ static struct hc_driver dummy_hcd = { .product_desc = "Dummy host controller", .hcd_priv_size = sizeof(struct dummy_hcd), - .flags = HCD_USB3 | HCD_SHARED, - .reset = dummy_setup, .start = dummy_start, .stop = dummy_stop, @@ -2591,8 +2630,12 @@ static int dummy_hcd_probe(struct platform_device *pdev) dev_info(&pdev->dev, "%s, driver " DRIVER_VERSION "\n", driver_desc); dum = *((void **)dev_get_platdata(&pdev->dev)); - if (!mod_data.is_super_speed) + if (mod_data.is_super_speed) + dummy_hcd.flags = HCD_USB3 | HCD_SHARED; + else if (mod_data.is_high_speed) dummy_hcd.flags = HCD_USB2; + else + dummy_hcd.flags = HCD_USB11; hs_hcd = usb_create_hcd(&dummy_hcd, &pdev->dev, dev_name(&pdev->dev)); if (!hs_hcd) return -ENOMEM; diff --git a/drivers/usb/gadget/udc/renesas_usb3.c b/drivers/usb/gadget/udc/renesas_usb3.c index df37c1e6e9d5..63a206122058 100644 --- a/drivers/usb/gadget/udc/renesas_usb3.c +++ b/drivers/usb/gadget/udc/renesas_usb3.c @@ -1038,7 +1038,7 @@ static int usb3_write_pipe(struct renesas_usb3_ep *usb3_ep, usb3_ep->ep.maxpacket); u8 *buf = usb3_req->req.buf + usb3_req->req.actual; u32 tmp = 0; - bool is_last; + bool is_last = !len ? true : false; if (usb3_wait_pipe_status(usb3_ep, PX_STA_BUFSTS) < 0) return -EBUSY; @@ -1059,7 +1059,8 @@ static int usb3_write_pipe(struct renesas_usb3_ep *usb3_ep, usb3_write(usb3, tmp, fifo_reg); } - is_last = usb3_is_transfer_complete(usb3_ep, usb3_req); + if (!is_last) + is_last = usb3_is_transfer_complete(usb3_ep, usb3_req); /* Send the data */ usb3_set_px_con_send(usb3_ep, len, is_last); @@ -1150,7 +1151,8 @@ static void usb3_start_pipe0(struct renesas_usb3_ep *usb3_ep, usb3_set_p0_con_for_ctrl_read_data(usb3); } else { usb3_clear_bit(usb3, P0_MOD_DIR, USB3_P0_MOD); - usb3_set_p0_con_for_ctrl_write_data(usb3); + if (usb3_req->req.length) + usb3_set_p0_con_for_ctrl_write_data(usb3); } usb3_p0_xfer(usb3_ep, usb3_req); @@ -2053,7 +2055,16 @@ static u32 usb3_calc_ramarea(int ram_size) static u32 usb3_calc_rammap_val(struct renesas_usb3_ep *usb3_ep, const struct usb_endpoint_descriptor *desc) { - return usb3_ep->rammap_val | PN_RAMMAP_MPKT(usb_endpoint_maxp(desc)); + int i; + const u32 max_packet_array[] = {8, 16, 32, 64, 512}; + u32 mpkt = PN_RAMMAP_MPKT(1024); + + for (i = 0; i < ARRAY_SIZE(max_packet_array); i++) { + if (usb_endpoint_maxp(desc) <= max_packet_array[i]) + mpkt = PN_RAMMAP_MPKT(max_packet_array[i]); + } + + return usb3_ep->rammap_val | mpkt; } static int usb3_enable_pipe_n(struct renesas_usb3_ep *usb3_ep, diff --git a/drivers/usb/host/pci-quirks.c b/drivers/usb/host/pci-quirks.c index 658d9d1f9ea3..6dda3623a276 100644 --- a/drivers/usb/host/pci-quirks.c +++ b/drivers/usb/host/pci-quirks.c @@ -447,7 +447,7 @@ static int usb_asmedia_wait_write(struct pci_dev *pdev) if ((value & ASMT_CONTROL_WRITE_BIT) == 0) return 0; - usleep_range(40, 60); + udelay(50); } dev_warn(&pdev->dev, "%s: check_write_ready timeout", __func__); @@ -1022,7 +1022,7 @@ EXPORT_SYMBOL_GPL(usb_disable_xhci_ports); * * Takes care of the handoff between the Pre-OS (i.e. BIOS) and the OS. * It signals to the BIOS that the OS wants control of the host controller, - * and then waits 5 seconds for the BIOS to hand over control. + * and then waits 1 second for the BIOS to hand over control. * If we timeout, assume the BIOS is broken and take control anyway. */ static void quirk_usb_handoff_xhci(struct pci_dev *pdev) @@ -1069,9 +1069,9 @@ static void quirk_usb_handoff_xhci(struct pci_dev *pdev) if (val & XHCI_HC_BIOS_OWNED) { writel(val | XHCI_HC_OS_OWNED, base + ext_cap_offset); - /* Wait for 5 seconds with 10 microsecond polling interval */ + /* Wait for 1 second with 10 microsecond polling interval */ timeout = handshake(base + ext_cap_offset, XHCI_HC_BIOS_OWNED, - 0, 5000, 10); + 0, 1000000, 10); /* Assume a buggy BIOS and take HC ownership anyway */ if (timeout) { @@ -1100,7 +1100,7 @@ hc_init: * operational or runtime registers. Wait 5 seconds and no more. */ timeout = handshake(op_reg_base + XHCI_STS_OFFSET, XHCI_STS_CNR, 0, - 5000, 10); + 5000000, 10); /* Assume a buggy HC and start HC initialization anyway */ if (timeout) { val = readl(op_reg_base + XHCI_STS_OFFSET); diff --git a/drivers/usb/host/xhci-hub.c b/drivers/usb/host/xhci-hub.c index ad89a6d4111b..da9158f171cb 100644 --- a/drivers/usb/host/xhci-hub.c +++ b/drivers/usb/host/xhci-hub.c @@ -112,7 +112,7 @@ static int xhci_create_usb3_bos_desc(struct xhci_hcd *xhci, char *buf, /* If PSI table exists, add the custom speed attributes from it */ if (usb3_1 && xhci->usb3_rhub.psi_count) { - u32 ssp_cap_base, bm_attrib, psi; + u32 ssp_cap_base, bm_attrib, psi, psi_mant, psi_exp; int offset; ssp_cap_base = USB_DT_BOS_SIZE + USB_DT_USB_SS_CAP_SIZE; @@ -139,6 +139,15 @@ static int xhci_create_usb3_bos_desc(struct xhci_hcd *xhci, char *buf, for (i = 0; i < xhci->usb3_rhub.psi_count; i++) { psi = xhci->usb3_rhub.psi[i]; psi &= ~USB_SSP_SUBLINK_SPEED_RSVD; + psi_exp = XHCI_EXT_PORT_PSIE(psi); + psi_mant = XHCI_EXT_PORT_PSIM(psi); + + /* Shift to Gbps and set SSP Link BIT(14) if 10Gpbs */ + for (; psi_exp < 3; psi_exp++) + psi_mant /= 1000; + if (psi_mant >= 10) + psi |= BIT(14); + if ((psi & PLT_MASK) == PLT_SYM) { /* Symmetric, create SSA RX and TX from one PSI entry */ put_unaligned_le32(psi, &buf[offset]); @@ -1506,9 +1515,6 @@ int xhci_bus_suspend(struct usb_hcd *hcd) t2 |= PORT_WKOC_E | PORT_WKCONN_E; t2 &= ~PORT_WKDISC_E; } - if ((xhci->quirks & XHCI_U2_DISABLE_WAKE) && - (hcd->speed < HCD_USB3)) - t2 &= ~PORT_WAKE_BITS; } else t2 &= ~PORT_WAKE_BITS; diff --git a/drivers/usb/host/xhci-pci.c b/drivers/usb/host/xhci-pci.c index 8071c8fdd15e..76f392954733 100644 --- a/drivers/usb/host/xhci-pci.c +++ b/drivers/usb/host/xhci-pci.c @@ -54,11 +54,6 @@ #define PCI_DEVICE_ID_INTEL_APL_XHCI 0x5aa8 #define PCI_DEVICE_ID_INTEL_DNV_XHCI 0x19d0 -#define PCI_DEVICE_ID_AMD_PROMONTORYA_4 0x43b9 -#define PCI_DEVICE_ID_AMD_PROMONTORYA_3 0x43ba -#define PCI_DEVICE_ID_AMD_PROMONTORYA_2 0x43bb -#define PCI_DEVICE_ID_AMD_PROMONTORYA_1 0x43bc - #define PCI_DEVICE_ID_ASMEDIA_1042A_XHCI 0x1142 static const char hcd_name[] = "xhci_hcd"; @@ -142,13 +137,6 @@ static void xhci_pci_quirks(struct device *dev, struct xhci_hcd *xhci) if (pdev->vendor == PCI_VENDOR_ID_AMD) xhci->quirks |= XHCI_TRUST_TX_LENGTH; - if ((pdev->vendor == PCI_VENDOR_ID_AMD) && - ((pdev->device == PCI_DEVICE_ID_AMD_PROMONTORYA_4) || - (pdev->device == PCI_DEVICE_ID_AMD_PROMONTORYA_3) || - (pdev->device == PCI_DEVICE_ID_AMD_PROMONTORYA_2) || - (pdev->device == PCI_DEVICE_ID_AMD_PROMONTORYA_1))) - xhci->quirks |= XHCI_U2_DISABLE_WAKE; - if (pdev->vendor == PCI_VENDOR_ID_INTEL) { xhci->quirks |= XHCI_LPM_SUPPORT; xhci->quirks |= XHCI_INTEL_HOST; diff --git a/drivers/usb/host/xhci-plat.c b/drivers/usb/host/xhci-plat.c index 163bafde709f..1cb6eaef4ae1 100644 --- a/drivers/usb/host/xhci-plat.c +++ b/drivers/usb/host/xhci-plat.c @@ -178,14 +178,18 @@ static int xhci_plat_probe(struct platform_device *pdev) * 2. xhci_plat is child of a device from firmware (dwc3-plat) * 3. xhci_plat is grandchild of a pci device (dwc3-pci) */ - sysdev = &pdev->dev; - if (sysdev->parent && !sysdev->of_node && sysdev->parent->of_node) - sysdev = sysdev->parent; + for (sysdev = &pdev->dev; sysdev; sysdev = sysdev->parent) { + if (is_of_node(sysdev->fwnode) || + is_acpi_device_node(sysdev->fwnode)) + break; #ifdef CONFIG_PCI - else if (sysdev->parent && sysdev->parent->parent && - sysdev->parent->parent->bus == &pci_bus_type) - sysdev = sysdev->parent->parent; + else if (sysdev->bus == &pci_bus_type) + break; #endif + } + + if (!sysdev) + sysdev = &pdev->dev; /* Try to set 64-bit DMA first */ if (WARN_ON(!sysdev->dma_mask)) diff --git a/drivers/usb/host/xhci.c b/drivers/usb/host/xhci.c index b2ff1ff1a02f..ee198ea47f49 100644 --- a/drivers/usb/host/xhci.c +++ b/drivers/usb/host/xhci.c @@ -1703,7 +1703,8 @@ static int xhci_add_endpoint(struct usb_hcd *hcd, struct usb_device *udev, if (xhci->quirks & XHCI_MTK_HOST) { ret = xhci_mtk_add_ep_quirk(hcd, udev, ep); if (ret < 0) { - xhci_free_endpoint_ring(xhci, virt_dev, ep_index); + xhci_ring_free(xhci, virt_dev->eps[ep_index].new_ring); + virt_dev->eps[ep_index].new_ring = NULL; return ret; } } diff --git a/drivers/usb/host/xhci.h b/drivers/usb/host/xhci.h index 2abaa4d6d39d..2b48aa4f6b76 100644 --- a/drivers/usb/host/xhci.h +++ b/drivers/usb/host/xhci.h @@ -735,6 +735,8 @@ struct xhci_ep_ctx { #define EP_MAXPSTREAMS(p) (((p) << 10) & EP_MAXPSTREAMS_MASK) /* Endpoint is set up with a Linear Stream Array (vs. Secondary Stream Array) */ #define EP_HAS_LSA (1 << 15) +/* hosts with LEC=1 use bits 31:24 as ESIT high bits. */ +#define CTX_TO_MAX_ESIT_PAYLOAD_HI(p) (((p) >> 24) & 0xff) /* ep_info2 bitmasks */ /* @@ -1681,7 +1683,7 @@ struct xhci_bus_state { static inline unsigned int hcd_index(struct usb_hcd *hcd) { - if (hcd->speed == HCD_USB3) + if (hcd->speed >= HCD_USB3) return 0; else return 1; @@ -1826,7 +1828,7 @@ struct xhci_hcd { /* For controller with a broken Port Disable implementation */ #define XHCI_BROKEN_PORT_PED (1 << 25) #define XHCI_LIMIT_ENDPOINT_INTERVAL_7 (1 << 26) -#define XHCI_U2_DISABLE_WAKE (1 << 27) +/* Reserved. It was XHCI_U2_DISABLE_WAKE */ #define XHCI_ASMEDIA_MODIFY_FLOWCONTROL (1 << 28) unsigned int num_active_eps; @@ -2540,8 +2542,8 @@ static inline const char *xhci_decode_ep_context(u32 info, u32 info2, u64 deq, u8 lsa; u8 hid; - esit = EP_MAX_ESIT_PAYLOAD_HI(info) << 16 | - EP_MAX_ESIT_PAYLOAD_LO(tx_info); + esit = CTX_TO_MAX_ESIT_PAYLOAD_HI(info) << 16 | + CTX_TO_MAX_ESIT_PAYLOAD(tx_info); ep_state = info & EP_STATE_MASK; max_pstr = info & EP_MAXPSTREAMS_MASK; diff --git a/drivers/usb/renesas_usbhs/fifo.c b/drivers/usb/renesas_usbhs/fifo.c index d1af831f43eb..68f26904c316 100644 --- a/drivers/usb/renesas_usbhs/fifo.c +++ b/drivers/usb/renesas_usbhs/fifo.c @@ -282,11 +282,26 @@ static void usbhsf_fifo_clear(struct usbhs_pipe *pipe, struct usbhs_fifo *fifo) { struct usbhs_priv *priv = usbhs_pipe_to_priv(pipe); + int ret = 0; - if (!usbhs_pipe_is_dcp(pipe)) - usbhsf_fifo_barrier(priv, fifo); + if (!usbhs_pipe_is_dcp(pipe)) { + /* + * This driver checks the pipe condition first to avoid -EBUSY + * from usbhsf_fifo_barrier() with about 10 msec delay in + * the interrupt handler if the pipe is RX direction and empty. + */ + if (usbhs_pipe_is_dir_in(pipe)) + ret = usbhs_pipe_is_accessible(pipe); + if (!ret) + ret = usbhsf_fifo_barrier(priv, fifo); + } - usbhs_write(priv, fifo->ctr, BCLR); + /* + * if non-DCP pipe, this driver should set BCLR when + * usbhsf_fifo_barrier() returns 0. + */ + if (!ret) + usbhs_write(priv, fifo->ctr, BCLR); } static int usbhsf_fifo_rcv_len(struct usbhs_priv *priv, diff --git a/drivers/usb/storage/transport.c b/drivers/usb/storage/transport.c index 1a59f335b063..a3ccb899df60 100644 --- a/drivers/usb/storage/transport.c +++ b/drivers/usb/storage/transport.c @@ -834,13 +834,25 @@ Retry_Sense: if (result == USB_STOR_TRANSPORT_GOOD) { srb->result = SAM_STAT_GOOD; srb->sense_buffer[0] = 0x0; + } + + /* + * ATA-passthru commands use sense data to report + * the command completion status, and often devices + * return Check Condition status when nothing is + * wrong. + */ + else if (srb->cmnd[0] == ATA_16 || + srb->cmnd[0] == ATA_12) { + /* leave the data alone */ + } /* * If there was a problem, report an unspecified * hardware error to prevent the higher layers from * entering an infinite retry loop. */ - } else { + else { srb->result = DID_ERROR << 16; if ((sshdr.response_code & 0x72) == 0x72) srb->sense_buffer[1] = HARDWARE_ERROR; diff --git a/drivers/usb/storage/uas-detect.h b/drivers/usb/storage/uas-detect.h index f58caa9e6a27..a155cd02bce2 100644 --- a/drivers/usb/storage/uas-detect.h +++ b/drivers/usb/storage/uas-detect.h @@ -9,7 +9,8 @@ static int uas_is_interface(struct usb_host_interface *intf) intf->desc.bInterfaceProtocol == USB_PR_UAS); } -static int uas_find_uas_alt_setting(struct usb_interface *intf) +static struct usb_host_interface *uas_find_uas_alt_setting( + struct usb_interface *intf) { int i; @@ -17,10 +18,10 @@ static int uas_find_uas_alt_setting(struct usb_interface *intf) struct usb_host_interface *alt = &intf->altsetting[i]; if (uas_is_interface(alt)) - return alt->desc.bAlternateSetting; + return alt; } - return -ENODEV; + return NULL; } static int uas_find_endpoints(struct usb_host_interface *alt, @@ -58,14 +59,14 @@ static int uas_use_uas_driver(struct usb_interface *intf, struct usb_device *udev = interface_to_usbdev(intf); struct usb_hcd *hcd = bus_to_hcd(udev->bus); unsigned long flags = id->driver_info; - int r, alt; - + struct usb_host_interface *alt; + int r; alt = uas_find_uas_alt_setting(intf); - if (alt < 0) + if (!alt) return 0; - r = uas_find_endpoints(&intf->altsetting[alt], eps); + r = uas_find_endpoints(alt, eps); if (r < 0) return 0; diff --git a/drivers/usb/storage/uas.c b/drivers/usb/storage/uas.c index cfb1e3bbd434..63cf981ed81c 100644 --- a/drivers/usb/storage/uas.c +++ b/drivers/usb/storage/uas.c @@ -873,14 +873,14 @@ MODULE_DEVICE_TABLE(usb, uas_usb_ids); static int uas_switch_interface(struct usb_device *udev, struct usb_interface *intf) { - int alt; + struct usb_host_interface *alt; alt = uas_find_uas_alt_setting(intf); - if (alt < 0) - return alt; + if (!alt) + return -ENODEV; - return usb_set_interface(udev, - intf->altsetting[0].desc.bInterfaceNumber, alt); + return usb_set_interface(udev, alt->desc.bInterfaceNumber, + alt->desc.bAlternateSetting); } static int uas_configure_endpoints(struct uas_dev_info *devinfo) diff --git a/drivers/usb/storage/unusual_devs.h b/drivers/usb/storage/unusual_devs.h index 5a70c33ef0e0..eb06d88b41d6 100644 --- a/drivers/usb/storage/unusual_devs.h +++ b/drivers/usb/storage/unusual_devs.h @@ -1459,6 +1459,13 @@ UNUSUAL_DEV( 0x0bc2, 0x3010, 0x0000, 0x0000, USB_SC_DEVICE, USB_PR_DEVICE, NULL, US_FL_SANE_SENSE ), +/* Reported by Kris Lindgren <kris.lindgren@gmail.com> */ +UNUSUAL_DEV( 0x0bc2, 0x3332, 0x0000, 0x9999, + "Seagate", + "External", + USB_SC_DEVICE, USB_PR_DEVICE, NULL, + US_FL_NO_WP_DETECT ), + UNUSUAL_DEV( 0x0d49, 0x7310, 0x0000, 0x9999, "Maxtor", "USB to SATA", diff --git a/drivers/uwb/hwa-rc.c b/drivers/uwb/hwa-rc.c index 35a1e777b449..9a53912bdfe9 100644 --- a/drivers/uwb/hwa-rc.c +++ b/drivers/uwb/hwa-rc.c @@ -825,6 +825,8 @@ static int hwarc_probe(struct usb_interface *iface, if (iface->cur_altsetting->desc.bNumEndpoints < 1) return -ENODEV; + if (!usb_endpoint_xfer_int(&iface->cur_altsetting->endpoint[0].desc)) + return -ENODEV; result = -ENOMEM; uwb_rc = uwb_rc_alloc(); diff --git a/drivers/uwb/uwbd.c b/drivers/uwb/uwbd.c index 01c20a260a8b..39dd4ef53c77 100644 --- a/drivers/uwb/uwbd.c +++ b/drivers/uwb/uwbd.c @@ -302,18 +302,22 @@ static int uwbd(void *param) /** Start the UWB daemon */ void uwbd_start(struct uwb_rc *rc) { - rc->uwbd.task = kthread_run(uwbd, rc, "uwbd"); - if (rc->uwbd.task == NULL) + struct task_struct *task = kthread_run(uwbd, rc, "uwbd"); + if (IS_ERR(task)) { + rc->uwbd.task = NULL; printk(KERN_ERR "UWB: Cannot start management daemon; " "UWB won't work\n"); - else + } else { + rc->uwbd.task = task; rc->uwbd.pid = rc->uwbd.task->pid; + } } /* Stop the UWB daemon and free any unprocessed events */ void uwbd_stop(struct uwb_rc *rc) { - kthread_stop(rc->uwbd.task); + if (rc->uwbd.task) + kthread_stop(rc->uwbd.task); uwbd_flush(rc); } diff --git a/drivers/xen/xen-pciback/conf_space_header.c b/drivers/xen/xen-pciback/conf_space_header.c index 5fbfd9cfb6d6..5b3d57fc82d3 100644 --- a/drivers/xen/xen-pciback/conf_space_header.c +++ b/drivers/xen/xen-pciback/conf_space_header.c @@ -169,6 +169,9 @@ static int rom_write(struct pci_dev *dev, int offset, u32 value, void *data) static int bar_write(struct pci_dev *dev, int offset, u32 value, void *data) { struct pci_bar_info *bar = data; + unsigned int pos = (offset - PCI_BASE_ADDRESS_0) / 4; + const struct resource *res = dev->resource; + u32 mask; if (unlikely(!bar)) { pr_warn(DRV_NAME ": driver data not found for %s\n", @@ -179,7 +182,13 @@ static int bar_write(struct pci_dev *dev, int offset, u32 value, void *data) /* A write to obtain the length must happen as a 32-bit write. * This does not (yet) support writing individual bytes */ - if (value == ~0) + if (res[pos].flags & IORESOURCE_IO) + mask = ~PCI_BASE_ADDRESS_IO_MASK; + else if (pos && (res[pos - 1].flags & IORESOURCE_MEM_64)) + mask = 0; + else + mask = ~PCI_BASE_ADDRESS_MEM_MASK; + if ((value | mask) == ~0U) bar->which = 1; else { u32 tmpval; diff --git a/fs/binfmt_misc.c b/fs/binfmt_misc.c index ce7181ea60fa..2a46762def31 100644 --- a/fs/binfmt_misc.c +++ b/fs/binfmt_misc.c @@ -54,7 +54,7 @@ typedef struct { int size; /* size of magic/mask */ char *magic; /* magic or filename extension */ char *mask; /* mask, NULL for exact match */ - char *interpreter; /* filename of interpreter */ + const char *interpreter; /* filename of interpreter */ char *name; struct dentry *dentry; struct file *interp_file; @@ -131,27 +131,26 @@ static int load_misc_binary(struct linux_binprm *bprm) { Node *fmt; struct file *interp_file = NULL; - char iname[BINPRM_BUF_SIZE]; - const char *iname_addr = iname; int retval; int fd_binary = -1; retval = -ENOEXEC; if (!enabled) - goto ret; + return retval; /* to keep locking time low, we copy the interpreter string */ read_lock(&entries_lock); fmt = check_file(bprm); if (fmt) - strlcpy(iname, fmt->interpreter, BINPRM_BUF_SIZE); + dget(fmt->dentry); read_unlock(&entries_lock); if (!fmt) - goto ret; + return retval; /* Need to be able to load the file after exec */ + retval = -ENOENT; if (bprm->interp_flags & BINPRM_FLAGS_PATH_INACCESSIBLE) - return -ENOENT; + goto ret; if (!(fmt->flags & MISC_FMT_PRESERVE_ARGV0)) { retval = remove_arg_zero(bprm); @@ -195,22 +194,22 @@ static int load_misc_binary(struct linux_binprm *bprm) bprm->argc++; /* add the interp as argv[0] */ - retval = copy_strings_kernel(1, &iname_addr, bprm); + retval = copy_strings_kernel(1, &fmt->interpreter, bprm); if (retval < 0) goto error; bprm->argc++; /* Update interp in case binfmt_script needs it. */ - retval = bprm_change_interp(iname, bprm); + retval = bprm_change_interp(fmt->interpreter, bprm); if (retval < 0) goto error; - if (fmt->flags & MISC_FMT_OPEN_FILE && fmt->interp_file) { + if (fmt->flags & MISC_FMT_OPEN_FILE) { interp_file = filp_clone_open(fmt->interp_file); if (!IS_ERR(interp_file)) deny_write_access(interp_file); } else { - interp_file = open_exec(iname); + interp_file = open_exec(fmt->interpreter); } retval = PTR_ERR(interp_file); if (IS_ERR(interp_file)) @@ -238,6 +237,7 @@ static int load_misc_binary(struct linux_binprm *bprm) goto error; ret: + dput(fmt->dentry); return retval; error: if (fd_binary > 0) @@ -594,8 +594,13 @@ static struct inode *bm_get_inode(struct super_block *sb, int mode) static void bm_evict_inode(struct inode *inode) { + Node *e = inode->i_private; + + if (e->flags & MISC_FMT_OPEN_FILE) + filp_close(e->interp_file, NULL); + clear_inode(inode); - kfree(inode->i_private); + kfree(e); } static void kill_node(Node *e) @@ -603,24 +608,14 @@ static void kill_node(Node *e) struct dentry *dentry; write_lock(&entries_lock); - dentry = e->dentry; - if (dentry) { - list_del_init(&e->list); - e->dentry = NULL; - } + list_del_init(&e->list); write_unlock(&entries_lock); - if ((e->flags & MISC_FMT_OPEN_FILE) && e->interp_file) { - filp_close(e->interp_file, NULL); - e->interp_file = NULL; - } - - if (dentry) { - drop_nlink(d_inode(dentry)); - d_drop(dentry); - dput(dentry); - simple_release_fs(&bm_mnt, &entry_count); - } + dentry = e->dentry; + drop_nlink(d_inode(dentry)); + d_drop(dentry); + dput(dentry); + simple_release_fs(&bm_mnt, &entry_count); } /* /<entry> */ @@ -665,7 +660,8 @@ static ssize_t bm_entry_write(struct file *file, const char __user *buffer, root = file_inode(file)->i_sb->s_root; inode_lock(d_inode(root)); - kill_node(e); + if (!list_empty(&e->list)) + kill_node(e); inode_unlock(d_inode(root)); break; @@ -794,7 +790,7 @@ static ssize_t bm_status_write(struct file *file, const char __user *buffer, inode_lock(d_inode(root)); while (!list_empty(&entries)) - kill_node(list_entry(entries.next, Node, list)); + kill_node(list_first_entry(&entries, Node, list)); inode_unlock(d_inode(root)); break; diff --git a/fs/binfmt_script.c b/fs/binfmt_script.c index afdf4e3cafc2..7cde3f46ad26 100644 --- a/fs/binfmt_script.c +++ b/fs/binfmt_script.c @@ -19,7 +19,6 @@ static int load_script(struct linux_binprm *bprm) const char *i_arg, *i_name; char *cp; struct file *file; - char interp[BINPRM_BUF_SIZE]; int retval; if ((bprm->buf[0] != '#') || (bprm->buf[1] != '!')) @@ -55,7 +54,7 @@ static int load_script(struct linux_binprm *bprm) break; } for (cp = bprm->buf+2; (*cp == ' ') || (*cp == '\t'); cp++); - if (*cp == '\0') + if (*cp == '\0') return -ENOEXEC; /* No interpreter name found */ i_name = cp; i_arg = NULL; @@ -65,7 +64,6 @@ static int load_script(struct linux_binprm *bprm) *cp++ = '\0'; if (*cp) i_arg = cp; - strcpy (interp, i_name); /* * OK, we've parsed out the interpreter name and * (optional) argument. @@ -80,24 +78,27 @@ static int load_script(struct linux_binprm *bprm) if (retval) return retval; retval = copy_strings_kernel(1, &bprm->interp, bprm); - if (retval < 0) return retval; + if (retval < 0) + return retval; bprm->argc++; if (i_arg) { retval = copy_strings_kernel(1, &i_arg, bprm); - if (retval < 0) return retval; + if (retval < 0) + return retval; bprm->argc++; } retval = copy_strings_kernel(1, &i_name, bprm); - if (retval) return retval; + if (retval) + return retval; bprm->argc++; - retval = bprm_change_interp(interp, bprm); + retval = bprm_change_interp(i_name, bprm); if (retval < 0) return retval; /* * OK, now restart the process with the interpreter's dentry. */ - file = open_exec(interp); + file = open_exec(i_name); if (IS_ERR(file)) return PTR_ERR(file); diff --git a/fs/btrfs/compression.c b/fs/btrfs/compression.c index b51d23f5cafa..280384bf34f1 100644 --- a/fs/btrfs/compression.c +++ b/fs/btrfs/compression.c @@ -107,7 +107,8 @@ static void end_compressed_bio_read(struct bio *bio) struct inode *inode; struct page *page; unsigned long index; - int ret; + unsigned int mirror = btrfs_io_bio(bio)->mirror_num; + int ret = 0; if (bio->bi_status) cb->errors = 1; @@ -118,6 +119,21 @@ static void end_compressed_bio_read(struct bio *bio) if (!refcount_dec_and_test(&cb->pending_bios)) goto out; + /* + * Record the correct mirror_num in cb->orig_bio so that + * read-repair can work properly. + */ + ASSERT(btrfs_io_bio(cb->orig_bio)); + btrfs_io_bio(cb->orig_bio)->mirror_num = mirror; + cb->mirror_num = mirror; + + /* + * Some IO in this cb have failed, just skip checksum as there + * is no way it could be correct. + */ + if (cb->errors == 1) + goto csum_failed; + inode = cb->inode; ret = check_compressed_csum(BTRFS_I(inode), cb, (u64)bio->bi_iter.bi_sector << 9); diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index 5a8933da39a7..8fc690384c58 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -709,7 +709,6 @@ struct btrfs_delayed_root; #define BTRFS_FS_OPEN 5 #define BTRFS_FS_QUOTA_ENABLED 6 #define BTRFS_FS_QUOTA_ENABLING 7 -#define BTRFS_FS_QUOTA_DISABLING 8 #define BTRFS_FS_UPDATE_UUID_TREE_GEN 9 #define BTRFS_FS_CREATING_FREE_SPACE_TREE 10 #define BTRFS_FS_BTREE_ERR 11 @@ -723,7 +722,7 @@ struct btrfs_delayed_root; * Indicate that a whole-filesystem exclusive operation is running * (device replace, resize, device add/delete, balance) */ -#define BTRFS_FS_EXCL_OP 14 +#define BTRFS_FS_EXCL_OP 16 struct btrfs_fs_info { u8 fsid[BTRFS_FSID_SIZE]; diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 487bbe4fb3c6..dfdab849037b 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -3643,7 +3643,14 @@ int write_all_supers(struct btrfs_fs_info *fs_info, int max_mirrors) u64 flags; do_barriers = !btrfs_test_opt(fs_info, NOBARRIER); - backup_super_roots(fs_info); + + /* + * max_mirrors == 0 indicates we're from commit_transaction, + * not from fsync where the tree roots in fs_info have not + * been consistent on disk. + */ + if (max_mirrors == 0) + backup_super_roots(fs_info); sb = fs_info->super_for_commit; dev_item = &sb->dev_item; diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index 3e5bb0cdd3cd..970190cd347e 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -2801,7 +2801,7 @@ static int submit_extent_page(unsigned int opf, struct extent_io_tree *tree, } } - bio = btrfs_bio_alloc(bdev, sector << 9); + bio = btrfs_bio_alloc(bdev, (u64)sector << 9); bio_add_page(bio, page, page_size, offset); bio->bi_end_io = end_io_func; bio->bi_private = tree; @@ -3471,8 +3471,7 @@ static int __extent_writepage(struct page *page, struct writeback_control *wbc, unsigned int write_flags = 0; unsigned long nr_written = 0; - if (wbc->sync_mode == WB_SYNC_ALL) - write_flags = REQ_SYNC; + write_flags = wbc_to_write_flags(wbc); trace___extent_writepage(page, inode, wbc); @@ -3718,7 +3717,7 @@ static noinline_for_stack int write_one_eb(struct extent_buffer *eb, unsigned long i, num_pages; unsigned long bio_flags = 0; unsigned long start, end; - unsigned int write_flags = (epd->sync_io ? REQ_SYNC : 0) | REQ_META; + unsigned int write_flags = wbc_to_write_flags(wbc) | REQ_META; int ret = 0; clear_bit(EXTENT_BUFFER_WRITE_ERR, &eb->bflags); @@ -4063,9 +4062,6 @@ static void flush_epd_write_bio(struct extent_page_data *epd) if (epd->bio) { int ret; - bio_set_op_attrs(epd->bio, REQ_OP_WRITE, - epd->sync_io ? REQ_SYNC : 0); - ret = submit_one_bio(epd->bio, 0, epd->bio_flags); BUG_ON(ret < 0); /* -ENOMEM */ epd->bio = NULL; diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 128f3e58634f..d94e3f68b9b1 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -135,6 +135,18 @@ static inline void btrfs_cleanup_ordered_extents(struct inode *inode, const u64 offset, const u64 bytes) { + unsigned long index = offset >> PAGE_SHIFT; + unsigned long end_index = (offset + bytes - 1) >> PAGE_SHIFT; + struct page *page; + + while (index <= end_index) { + page = find_get_page(inode->i_mapping, index); + index++; + if (!page) + continue; + ClearPagePrivate2(page); + put_page(page); + } return __endio_write_update_ordered(inode, offset + PAGE_SIZE, bytes - PAGE_SIZE, false); } @@ -8357,11 +8369,8 @@ static void btrfs_endio_direct_read(struct bio *bio) struct btrfs_io_bio *io_bio = btrfs_io_bio(bio); blk_status_t err = bio->bi_status; - if (dip->flags & BTRFS_DIO_ORIG_BIO_SUBMITTED) { + if (dip->flags & BTRFS_DIO_ORIG_BIO_SUBMITTED) err = btrfs_subio_endio_read(inode, io_bio, err); - if (!err) - bio->bi_status = 0; - } unlock_extent(&BTRFS_I(inode)->io_tree, dip->logical_offset, dip->logical_offset + dip->bytes - 1); @@ -8369,7 +8378,7 @@ static void btrfs_endio_direct_read(struct bio *bio) kfree(dip); - dio_bio->bi_status = bio->bi_status; + dio_bio->bi_status = err; dio_end_io(dio_bio); if (io_bio->end_io) @@ -8387,6 +8396,7 @@ static void __endio_write_update_ordered(struct inode *inode, btrfs_work_func_t func; u64 ordered_offset = offset; u64 ordered_bytes = bytes; + u64 last_offset; int ret; if (btrfs_is_free_space_inode(BTRFS_I(inode))) { @@ -8398,6 +8408,7 @@ static void __endio_write_update_ordered(struct inode *inode, } again: + last_offset = ordered_offset; ret = btrfs_dec_test_first_ordered_pending(inode, &ordered, &ordered_offset, ordered_bytes, @@ -8409,6 +8420,12 @@ again: btrfs_queue_work(wq, &ordered->work); out_test: /* + * If btrfs_dec_test_ordered_pending does not find any ordered extent + * in the range, we can exit. + */ + if (ordered_offset == last_offset) + return; + /* * our bio might span multiple ordered extents. If we haven't * completed the accounting for the whole dio, go back and try again */ diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index d6715c2bcdc4..6c7a49faf4e0 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -2773,9 +2773,9 @@ static long btrfs_ioctl_fs_info(struct btrfs_fs_info *fs_info, } mutex_unlock(&fs_devices->device_list_mutex); - fi_args->nodesize = fs_info->super_copy->nodesize; - fi_args->sectorsize = fs_info->super_copy->sectorsize; - fi_args->clone_alignment = fs_info->super_copy->sectorsize; + fi_args->nodesize = fs_info->nodesize; + fi_args->sectorsize = fs_info->sectorsize; + fi_args->clone_alignment = fs_info->sectorsize; if (copy_to_user(arg, fi_args, sizeof(*fi_args))) ret = -EFAULT; @@ -3032,7 +3032,7 @@ static int btrfs_cmp_data_prepare(struct inode *src, u64 loff, out: if (ret) btrfs_cmp_data_free(cmp); - return 0; + return ret; } static int btrfs_cmp_data(u64 len, struct cmp_pages *cmp) @@ -4061,6 +4061,10 @@ static long btrfs_ioctl_default_subvol(struct file *file, void __user *argp) ret = PTR_ERR(new_root); goto out; } + if (!is_fstree(new_root->objectid)) { + ret = -ENOENT; + goto out; + } path = btrfs_alloc_path(); if (!path) { diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c index 5c8b61c86e61..e172d4843eae 100644 --- a/fs/btrfs/qgroup.c +++ b/fs/btrfs/qgroup.c @@ -807,7 +807,6 @@ static int btrfs_clean_quota_tree(struct btrfs_trans_handle *trans, } ret = 0; out: - set_bit(BTRFS_FS_QUOTA_DISABLING, &root->fs_info->flags); btrfs_free_path(path); return ret; } @@ -953,7 +952,6 @@ int btrfs_quota_disable(struct btrfs_trans_handle *trans, if (!fs_info->quota_root) goto out; clear_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags); - set_bit(BTRFS_FS_QUOTA_DISABLING, &fs_info->flags); btrfs_qgroup_wait_for_completion(fs_info, false); spin_lock(&fs_info->qgroup_lock); quota_root = fs_info->quota_root; @@ -1307,6 +1305,8 @@ int btrfs_remove_qgroup(struct btrfs_trans_handle *trans, } } ret = del_qgroup_item(trans, quota_root, qgroupid); + if (ret && ret != -ENOENT) + goto out; while (!list_empty(&qgroup->groups)) { list = list_first_entry(&qgroup->groups, @@ -2086,8 +2086,6 @@ int btrfs_run_qgroups(struct btrfs_trans_handle *trans, if (test_and_clear_bit(BTRFS_FS_QUOTA_ENABLING, &fs_info->flags)) set_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags); - if (test_and_clear_bit(BTRFS_FS_QUOTA_DISABLING, &fs_info->flags)) - clear_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags); spin_lock(&fs_info->qgroup_lock); while (!list_empty(&fs_info->dirty_qgroups)) { diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c index 3a49a3c2fca4..9841faef08ea 100644 --- a/fs/btrfs/relocation.c +++ b/fs/btrfs/relocation.c @@ -2400,11 +2400,11 @@ void free_reloc_roots(struct list_head *list) while (!list_empty(list)) { reloc_root = list_entry(list->next, struct btrfs_root, root_list); + __del_reloc_root(reloc_root); free_extent_buffer(reloc_root->node); free_extent_buffer(reloc_root->commit_root); reloc_root->node = NULL; reloc_root->commit_root = NULL; - __del_reloc_root(reloc_root); } } diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c index 32b043ef8ac9..8fd195cfe81b 100644 --- a/fs/btrfs/send.c +++ b/fs/btrfs/send.c @@ -2630,7 +2630,7 @@ static int send_create_inode(struct send_ctx *sctx, u64 ino) } else { btrfs_warn(sctx->send_root->fs_info, "unexpected inode type %o", (int)(mode & S_IFMT)); - ret = -ENOTSUPP; + ret = -EOPNOTSUPP; goto out; } diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index ad7f4bab640b..c800d067fcbf 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -4181,6 +4181,7 @@ static int btrfs_log_changed_extents(struct btrfs_trans_handle *trans, struct extent_map *em, *n; struct list_head extents; struct extent_map_tree *tree = &inode->extent_tree; + u64 logged_start, logged_end; u64 test_gen; int ret = 0; int num = 0; @@ -4190,10 +4191,11 @@ static int btrfs_log_changed_extents(struct btrfs_trans_handle *trans, down_write(&inode->dio_sem); write_lock(&tree->lock); test_gen = root->fs_info->last_trans_committed; + logged_start = start; + logged_end = end; list_for_each_entry_safe(em, n, &tree->modified_extents, list) { list_del_init(&em->list); - /* * Just an arbitrary number, this can be really CPU intensive * once we start getting a lot of extents, and really once we @@ -4208,6 +4210,12 @@ static int btrfs_log_changed_extents(struct btrfs_trans_handle *trans, if (em->generation <= test_gen) continue; + + if (em->start < logged_start) + logged_start = em->start; + if ((em->start + em->len - 1) > logged_end) + logged_end = em->start + em->len - 1; + /* Need a ref to keep it from getting evicted from cache */ refcount_inc(&em->refs); set_bit(EXTENT_FLAG_LOGGING, &em->flags); @@ -4216,7 +4224,7 @@ static int btrfs_log_changed_extents(struct btrfs_trans_handle *trans, } list_sort(NULL, &extents, extent_cmp); - btrfs_get_logged_extents(inode, logged_list, start, end); + btrfs_get_logged_extents(inode, logged_list, logged_start, logged_end); /* * Some ordered extents started by fsync might have completed * before we could collect them into the list logged_list, which diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index 0e8f16c305df..b39737568c22 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -6166,7 +6166,7 @@ blk_status_t btrfs_map_bio(struct btrfs_fs_info *fs_info, struct bio *bio, map_length = length; btrfs_bio_counter_inc_blocked(fs_info); - ret = __btrfs_map_block(fs_info, bio_op(bio), logical, + ret = __btrfs_map_block(fs_info, btrfs_op(bio), logical, &map_length, &bbio, mirror_num, 1); if (ret) { btrfs_bio_counter_dec(fs_info); diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c index 84edfc60d87a..f23c820daaed 100644 --- a/fs/ceph/mds_client.c +++ b/fs/ceph/mds_client.c @@ -734,12 +734,13 @@ static int __choose_mds(struct ceph_mds_client *mdsc, inode = req->r_inode; ihold(inode); } else { - /* req->r_dentry is non-null for LSSNAP request. - * fall-thru */ - WARN_ON_ONCE(!req->r_dentry); + /* req->r_dentry is non-null for LSSNAP request */ + rcu_read_lock(); + inode = get_nonsnap_parent(req->r_dentry); + rcu_read_unlock(); + dout("__choose_mds using snapdir's parent %p\n", inode); } - } - if (!inode && req->r_dentry) { + } else if (req->r_dentry) { /* ignore race with rename; old or new d_parent is okay */ struct dentry *parent; struct inode *dir; diff --git a/fs/ceph/snap.c b/fs/ceph/snap.c index 1ffc8b426c1c..7fc0b850c352 100644 --- a/fs/ceph/snap.c +++ b/fs/ceph/snap.c @@ -374,12 +374,10 @@ static int build_snap_context(struct ceph_snap_realm *realm, realm->ino, realm, snapc, snapc->seq, (unsigned int) snapc->num_snaps); - if (realm->cached_context) { - ceph_put_snap_context(realm->cached_context); - /* queue realm for cap_snap creation */ - list_add_tail(&realm->dirty_item, dirty_realms); - } + ceph_put_snap_context(realm->cached_context); realm->cached_context = snapc; + /* queue realm for cap_snap creation */ + list_add_tail(&realm->dirty_item, dirty_realms); return 0; fail: diff --git a/fs/direct-io.c b/fs/direct-io.c index 5fa2211e49ae..62cf812ed0e5 100644 --- a/fs/direct-io.c +++ b/fs/direct-io.c @@ -229,6 +229,7 @@ static ssize_t dio_complete(struct dio *dio, ssize_t ret, bool is_async) { loff_t offset = dio->iocb->ki_pos; ssize_t transferred = 0; + int err; /* * AIO submission can race with bio completion to get here while @@ -258,8 +259,22 @@ static ssize_t dio_complete(struct dio *dio, ssize_t ret, bool is_async) if (ret == 0) ret = transferred; + /* + * 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 + * of the write was an mmap'ed region of the file we're writing. Either + * one is a pretty crazy thing to do, so we don't support it 100%. If + * this invalidation fails, tough, the write still worked... + */ + if (ret > 0 && dio->op == REQ_OP_WRITE && + dio->inode->i_mapping->nrpages) { + err = invalidate_inode_pages2_range(dio->inode->i_mapping, + offset >> PAGE_SHIFT, + (offset + ret - 1) >> PAGE_SHIFT); + WARN_ON_ONCE(err); + } + if (dio->end_io) { - int err; // XXX: ki_pos?? err = dio->end_io(dio->iocb, offset, ret, dio->private); @@ -304,6 +319,7 @@ static void dio_bio_end_aio(struct bio *bio) struct dio *dio = bio->bi_private; unsigned long remaining; unsigned long flags; + bool defer_completion = false; /* cleanup the bio */ dio_bio_complete(dio, bio); @@ -315,7 +331,19 @@ static void dio_bio_end_aio(struct bio *bio) spin_unlock_irqrestore(&dio->bio_lock, flags); if (remaining == 0) { - if (dio->result && dio->defer_completion) { + /* + * Defer completion when defer_completion is set or + * when the inode has pages mapped and this is AIO write. + * We need to invalidate those pages because there is a + * chance they contain stale data in the case buffered IO + * went in between AIO submission and completion into the + * same region. + */ + if (dio->result) + defer_completion = dio->defer_completion || + (dio->op == REQ_OP_WRITE && + dio->inode->i_mapping->nrpages); + if (defer_completion) { INIT_WORK(&dio->complete_work, dio_aio_complete_work); queue_work(dio->inode->i_sb->s_dio_done_wq, &dio->complete_work); @@ -1210,10 +1238,19 @@ do_blockdev_direct_IO(struct kiocb *iocb, struct inode *inode, * For AIO O_(D)SYNC writes we need to defer completions to a workqueue * so that we can call ->fsync. */ - if (dio->is_async && iov_iter_rw(iter) == WRITE && - ((iocb->ki_filp->f_flags & O_DSYNC) || - IS_SYNC(iocb->ki_filp->f_mapping->host))) { - retval = dio_set_defer_completion(dio); + if (dio->is_async && iov_iter_rw(iter) == WRITE) { + retval = 0; + if ((iocb->ki_filp->f_flags & O_DSYNC) || + IS_SYNC(iocb->ki_filp->f_mapping->host)) + retval = dio_set_defer_completion(dio); + else if (!dio->inode->i_sb->s_dio_done_wq) { + /* + * In case of AIO write racing with buffered read we + * need to defer completion. We can't decide this now, + * however the workqueue needs to be initialized here. + */ + retval = sb_init_dio_done_wq(dio->inode->i_sb); + } if (retval) { /* * We grab i_mutex only for reads so we don't have diff --git a/fs/exec.c b/fs/exec.c index ac34d9724684..5470d3c1892a 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -1410,7 +1410,7 @@ static void free_bprm(struct linux_binprm *bprm) kfree(bprm); } -int bprm_change_interp(char *interp, struct linux_binprm *bprm) +int bprm_change_interp(const char *interp, struct linux_binprm *bprm) { /* If a binfmt changed the interp, free it first. */ if (bprm->interp != bprm->filename) diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c index 98e845b7841b..11066d8647d2 100644 --- a/fs/gfs2/glock.c +++ b/fs/gfs2/glock.c @@ -1945,13 +1945,9 @@ static void *gfs2_glock_seq_start(struct seq_file *seq, loff_t *pos) { struct gfs2_glock_iter *gi = seq->private; loff_t n = *pos; - int ret; - - if (gi->last_pos <= *pos) - n = (*pos - gi->last_pos); - ret = rhashtable_walk_start(&gi->hti); - if (ret) + rhashtable_walk_enter(&gl_hash_table, &gi->hti); + if (rhashtable_walk_start(&gi->hti) != 0) return NULL; do { @@ -1959,6 +1955,7 @@ static void *gfs2_glock_seq_start(struct seq_file *seq, loff_t *pos) } while (gi->gl && n--); gi->last_pos = *pos; + return gi->gl; } @@ -1970,6 +1967,7 @@ static void *gfs2_glock_seq_next(struct seq_file *seq, void *iter_ptr, (*pos)++; gi->last_pos = *pos; gfs2_glock_iter_next(gi); + return gi->gl; } @@ -1980,6 +1978,7 @@ static void gfs2_glock_seq_stop(struct seq_file *seq, void *iter_ptr) gi->gl = NULL; rhashtable_walk_stop(&gi->hti); + rhashtable_walk_exit(&gi->hti); } static int gfs2_glock_seq_show(struct seq_file *seq, void *iter_ptr) @@ -2042,12 +2041,10 @@ static int __gfs2_glocks_open(struct inode *inode, struct file *file, struct gfs2_glock_iter *gi = seq->private; gi->sdp = inode->i_private; - gi->last_pos = 0; seq->buf = kmalloc(GFS2_SEQ_GOODSIZE, GFP_KERNEL | __GFP_NOWARN); if (seq->buf) seq->size = GFS2_SEQ_GOODSIZE; gi->gl = NULL; - rhashtable_walk_enter(&gl_hash_table, &gi->hti); } return ret; } @@ -2063,7 +2060,6 @@ static int gfs2_glocks_release(struct inode *inode, struct file *file) struct gfs2_glock_iter *gi = seq->private; gi->gl = NULL; - rhashtable_walk_exit(&gi->hti); return seq_release_private(inode, file); } diff --git a/fs/iomap.c b/fs/iomap.c index 269b24a01f32..be61cf742b5e 100644 --- a/fs/iomap.c +++ b/fs/iomap.c @@ -713,8 +713,24 @@ struct iomap_dio { static ssize_t iomap_dio_complete(struct iomap_dio *dio) { struct kiocb *iocb = dio->iocb; + struct inode *inode = file_inode(iocb->ki_filp); ssize_t ret; + /* + * 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 + * of the write was an mmap'ed region of the file we're writing. Either + * one is a pretty crazy thing to do, so we don't support it 100%. If + * this invalidation fails, tough, the write still worked... + */ + if (!dio->error && + (dio->flags & IOMAP_DIO_WRITE) && inode->i_mapping->nrpages) { + ret = invalidate_inode_pages2_range(inode->i_mapping, + iocb->ki_pos >> PAGE_SHIFT, + (iocb->ki_pos + dio->size - 1) >> PAGE_SHIFT); + WARN_ON_ONCE(ret); + } + if (dio->end_io) { ret = dio->end_io(iocb, dio->error ? dio->error : dio->size, @@ -993,6 +1009,13 @@ iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter, WARN_ON_ONCE(ret); ret = 0; + if (iov_iter_rw(iter) == WRITE && !is_sync_kiocb(iocb) && + !inode->i_sb->s_dio_done_wq) { + ret = sb_init_dio_done_wq(inode->i_sb); + if (ret < 0) + goto out_free_dio; + } + inode_dio_begin(inode); blk_start_plug(&plug); @@ -1015,13 +1038,6 @@ iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter, if (ret < 0) iomap_dio_set_error(dio, ret); - if (ret >= 0 && iov_iter_rw(iter) == WRITE && !is_sync_kiocb(iocb) && - !inode->i_sb->s_dio_done_wq) { - ret = sb_init_dio_done_wq(inode->i_sb); - if (ret < 0) - iomap_dio_set_error(dio, ret); - } - if (!atomic_dec_and_test(&dio->ref)) { if (!is_sync_kiocb(iocb)) return -EIOCBQUEUED; @@ -1042,19 +1058,6 @@ iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter, 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 - * of the write was an mmap'ed region of the file we're writing. Either - * one is a pretty crazy thing to do, so we don't support it 100%. If - * this invalidation fails, tough, the write still worked... - */ - if (iov_iter_rw(iter) == WRITE) { - int err = invalidate_inode_pages2_range(mapping, - start >> PAGE_SHIFT, end >> PAGE_SHIFT); - WARN_ON_ONCE(err); - } - return ret; out_free_dio: diff --git a/fs/isofs/inode.c b/fs/isofs/inode.c index db692f554158..447a24d77b89 100644 --- a/fs/isofs/inode.c +++ b/fs/isofs/inode.c @@ -514,9 +514,11 @@ static int isofs_show_options(struct seq_file *m, struct dentry *root) if (sbi->s_fmode != ISOFS_INVALID_MODE) seq_printf(m, ",fmode=%o", sbi->s_fmode); +#ifdef CONFIG_JOLIET if (sbi->s_nls_iocharset && strcmp(sbi->s_nls_iocharset->charset, CONFIG_NLS_DEFAULT) != 0) seq_printf(m, ",iocharset=%s", sbi->s_nls_iocharset->charset); +#endif return 0; } diff --git a/fs/namespace.c b/fs/namespace.c index 54059b142d6b..3b601f115b6c 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -468,7 +468,9 @@ static inline int may_write_real(struct file *file) /* File refers to upper, writable layer? */ upperdentry = d_real(dentry, NULL, 0, D_REAL_UPPER); - if (upperdentry && file_inode(file) == d_inode(upperdentry)) + if (upperdentry && + (file_inode(file) == d_inode(upperdentry) || + file_inode(file) == d_inode(dentry))) return 0; /* Lower layer: can't write to real file, sorry... */ diff --git a/fs/overlayfs/copy_up.c b/fs/overlayfs/copy_up.c index aad97b30d5e6..c441f9387a1b 100644 --- a/fs/overlayfs/copy_up.c +++ b/fs/overlayfs/copy_up.c @@ -561,10 +561,8 @@ static int ovl_do_copy_up(struct ovl_copy_up_ctx *c) c->tmpfile = true; err = ovl_copy_up_locked(c); } else { - err = -EIO; - if (lock_rename(c->workdir, c->destdir) != NULL) { - pr_err("overlayfs: failed to lock workdir+upperdir\n"); - } else { + err = ovl_lock_rename_workdir(c->workdir, c->destdir); + if (!err) { err = ovl_copy_up_locked(c); unlock_rename(c->workdir, c->destdir); } diff --git a/fs/overlayfs/dir.c b/fs/overlayfs/dir.c index 3309b1912241..cc961a3bd3bd 100644 --- a/fs/overlayfs/dir.c +++ b/fs/overlayfs/dir.c @@ -216,26 +216,6 @@ out_unlock: return err; } -static int ovl_lock_rename_workdir(struct dentry *workdir, - struct dentry *upperdir) -{ - /* Workdir should not be the same as upperdir */ - if (workdir == upperdir) - goto err; - - /* Workdir should not be subdir of upperdir and vice versa */ - if (lock_rename(workdir, upperdir) != NULL) - goto err_unlock; - - return 0; - -err_unlock: - unlock_rename(workdir, upperdir); -err: - pr_err("overlayfs: failed to lock workdir+upperdir\n"); - return -EIO; -} - static struct dentry *ovl_clear_empty(struct dentry *dentry, struct list_head *list) { diff --git a/fs/overlayfs/namei.c b/fs/overlayfs/namei.c index c3addd1114f1..654bea1a5ac9 100644 --- a/fs/overlayfs/namei.c +++ b/fs/overlayfs/namei.c @@ -506,6 +506,7 @@ static struct dentry *ovl_lookup_index(struct dentry *dentry, index = lookup_one_len_unlocked(name.name, ofs->indexdir, name.len); if (IS_ERR(index)) { + err = PTR_ERR(index); pr_warn_ratelimited("overlayfs: failed inode index lookup (ino=%lu, key=%*s, err=%i);\n" "overlayfs: mount with '-o index=off' to disable inodes index.\n", d_inode(origin)->i_ino, name.len, name.name, diff --git a/fs/overlayfs/overlayfs.h b/fs/overlayfs/overlayfs.h index d4e8c1a08fb0..c706a6f99928 100644 --- a/fs/overlayfs/overlayfs.h +++ b/fs/overlayfs/overlayfs.h @@ -235,6 +235,7 @@ bool ovl_inuse_trylock(struct dentry *dentry); void ovl_inuse_unlock(struct dentry *dentry); int ovl_nlink_start(struct dentry *dentry, bool *locked); void ovl_nlink_end(struct dentry *dentry, bool locked); +int ovl_lock_rename_workdir(struct dentry *workdir, struct dentry *upperdir); static inline bool ovl_is_impuredir(struct dentry *dentry) { diff --git a/fs/overlayfs/ovl_entry.h b/fs/overlayfs/ovl_entry.h index 878a750986dd..25d9b5adcd42 100644 --- a/fs/overlayfs/ovl_entry.h +++ b/fs/overlayfs/ovl_entry.h @@ -37,6 +37,9 @@ struct ovl_fs { bool noxattr; /* sb common to all layers */ struct super_block *same_sb; + /* Did we take the inuse lock? */ + bool upperdir_locked; + bool workdir_locked; }; /* private information held for every overlayfs dentry */ diff --git a/fs/overlayfs/readdir.c b/fs/overlayfs/readdir.c index 62e9b22a2077..0f85ee9c3268 100644 --- a/fs/overlayfs/readdir.c +++ b/fs/overlayfs/readdir.c @@ -988,6 +988,7 @@ int ovl_indexdir_cleanup(struct dentry *dentry, struct vfsmount *mnt, struct path *lowerstack, unsigned int numlower) { int err; + struct dentry *index = NULL; struct inode *dir = dentry->d_inode; struct path path = { .mnt = mnt, .dentry = dentry }; LIST_HEAD(list); @@ -1007,8 +1008,6 @@ int ovl_indexdir_cleanup(struct dentry *dentry, struct vfsmount *mnt, inode_lock_nested(dir, I_MUTEX_PARENT); list_for_each_entry(p, &list, l_node) { - struct dentry *index; - if (p->name[0] == '.') { if (p->len == 1) continue; @@ -1018,6 +1017,7 @@ int ovl_indexdir_cleanup(struct dentry *dentry, struct vfsmount *mnt, index = lookup_one_len(p->name, dentry, p->len); if (IS_ERR(index)) { err = PTR_ERR(index); + index = NULL; break; } err = ovl_verify_index(index, lowerstack, numlower); @@ -1029,7 +1029,9 @@ int ovl_indexdir_cleanup(struct dentry *dentry, struct vfsmount *mnt, break; } dput(index); + index = NULL; } + dput(index); inode_unlock(dir); out: ovl_cache_free(&list); diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c index fd5ea4facc62..092d150643c1 100644 --- a/fs/overlayfs/super.c +++ b/fs/overlayfs/super.c @@ -211,9 +211,10 @@ static void ovl_put_super(struct super_block *sb) dput(ufs->indexdir); dput(ufs->workdir); - ovl_inuse_unlock(ufs->workbasedir); + if (ufs->workdir_locked) + ovl_inuse_unlock(ufs->workbasedir); dput(ufs->workbasedir); - if (ufs->upper_mnt) + if (ufs->upper_mnt && ufs->upperdir_locked) ovl_inuse_unlock(ufs->upper_mnt->mnt_root); mntput(ufs->upper_mnt); for (i = 0; i < ufs->numlower; i++) @@ -881,9 +882,13 @@ static int ovl_fill_super(struct super_block *sb, void *data, int silent) goto out_put_upperpath; err = -EBUSY; - if (!ovl_inuse_trylock(upperpath.dentry)) { - pr_err("overlayfs: upperdir is in-use by another mount\n"); + if (ovl_inuse_trylock(upperpath.dentry)) { + ufs->upperdir_locked = true; + } else if (ufs->config.index) { + pr_err("overlayfs: upperdir is in-use by another mount, mount with '-o index=off' to override exclusive upperdir protection.\n"); goto out_put_upperpath; + } else { + pr_warn("overlayfs: upperdir is in-use by another mount, accessing files from both mounts will result in undefined behavior.\n"); } err = ovl_mount_dir(ufs->config.workdir, &workpath); @@ -901,9 +906,13 @@ static int ovl_fill_super(struct super_block *sb, void *data, int silent) } err = -EBUSY; - if (!ovl_inuse_trylock(workpath.dentry)) { - pr_err("overlayfs: workdir is in-use by another mount\n"); + if (ovl_inuse_trylock(workpath.dentry)) { + ufs->workdir_locked = true; + } else if (ufs->config.index) { + pr_err("overlayfs: workdir is in-use by another mount, mount with '-o index=off' to override exclusive workdir protection.\n"); goto out_put_workpath; + } else { + pr_warn("overlayfs: workdir is in-use by another mount, accessing files from both mounts will result in undefined behavior.\n"); } ufs->workbasedir = workpath.dentry; @@ -1156,11 +1165,13 @@ out_put_lowerpath: out_free_lowertmp: kfree(lowertmp); out_unlock_workdentry: - ovl_inuse_unlock(workpath.dentry); + if (ufs->workdir_locked) + ovl_inuse_unlock(workpath.dentry); out_put_workpath: path_put(&workpath); out_unlock_upperdentry: - ovl_inuse_unlock(upperpath.dentry); + if (ufs->upperdir_locked) + ovl_inuse_unlock(upperpath.dentry); out_put_upperpath: path_put(&upperpath); out_free_config: diff --git a/fs/overlayfs/util.c b/fs/overlayfs/util.c index 117794582f9f..b9b239fa5cfd 100644 --- a/fs/overlayfs/util.c +++ b/fs/overlayfs/util.c @@ -430,7 +430,7 @@ void ovl_inuse_unlock(struct dentry *dentry) } } -/* Called must hold OVL_I(inode)->oi_lock */ +/* Caller must hold OVL_I(inode)->lock */ static void ovl_cleanup_index(struct dentry *dentry) { struct inode *dir = ovl_indexdir(dentry->d_sb)->d_inode; @@ -469,6 +469,9 @@ static void ovl_cleanup_index(struct dentry *dentry) err = PTR_ERR(index); if (!IS_ERR(index)) err = ovl_cleanup(dir, index); + else + index = NULL; + inode_unlock(dir); if (err) goto fail; @@ -557,3 +560,22 @@ void ovl_nlink_end(struct dentry *dentry, bool locked) mutex_unlock(&OVL_I(d_inode(dentry))->lock); } } + +int ovl_lock_rename_workdir(struct dentry *workdir, struct dentry *upperdir) +{ + /* Workdir should not be the same as upperdir */ + if (workdir == upperdir) + goto err; + + /* Workdir should not be subdir of upperdir and vice versa */ + if (lock_rename(workdir, upperdir) != NULL) + goto err_unlock; + + return 0; + +err_unlock: + unlock_rename(workdir, upperdir); +err: + pr_err("overlayfs: failed to lock workdir+upperdir\n"); + return -EIO; +} diff --git a/fs/proc/array.c b/fs/proc/array.c index 525157ca25cb..77a8eacbe032 100644 --- a/fs/proc/array.c +++ b/fs/proc/array.c @@ -119,30 +119,25 @@ static inline void task_name(struct seq_file *m, struct task_struct *p) * simple bit tests. */ static const char * const task_state_array[] = { - "R (running)", /* 0 */ - "S (sleeping)", /* 1 */ - "D (disk sleep)", /* 2 */ - "T (stopped)", /* 4 */ - "t (tracing stop)", /* 8 */ - "X (dead)", /* 16 */ - "Z (zombie)", /* 32 */ + + /* states in TASK_REPORT: */ + "R (running)", /* 0x00 */ + "S (sleeping)", /* 0x01 */ + "D (disk sleep)", /* 0x02 */ + "T (stopped)", /* 0x04 */ + "t (tracing stop)", /* 0x08 */ + "X (dead)", /* 0x10 */ + "Z (zombie)", /* 0x20 */ + "P (parked)", /* 0x40 */ + + /* states beyond TASK_REPORT: */ + "I (idle)", /* 0x80 */ }; static inline const char *get_task_state(struct task_struct *tsk) { - unsigned int state = (tsk->state | tsk->exit_state) & TASK_REPORT; - - /* - * Parked tasks do not run; they sit in __kthread_parkme(). - * Without this check, we would report them as running, which is - * clearly wrong, so we report them as sleeping instead. - */ - if (tsk->state == TASK_PARKED) - state = TASK_INTERRUPTIBLE; - - BUILD_BUG_ON(1 + ilog2(TASK_REPORT) != ARRAY_SIZE(task_state_array)-1); - - return task_state_array[fls(state)]; + BUILD_BUG_ON(1 + ilog2(TASK_REPORT_MAX) != ARRAY_SIZE(task_state_array)); + return task_state_array[__get_task_state(tsk)]; } static inline int get_task_umask(struct task_struct *tsk) diff --git a/fs/quota/dquot.c b/fs/quota/dquot.c index 8381db9db6d9..50b0556a124f 100644 --- a/fs/quota/dquot.c +++ b/fs/quota/dquot.c @@ -1980,7 +1980,9 @@ int __dquot_transfer(struct inode *inode, struct dquot **transfer_to) ret = dquot_add_space(transfer_to[cnt], cur_space, rsv_space, 0, &warn_to[cnt]); if (ret) { + spin_lock(&transfer_to[cnt]->dq_dqb_lock); dquot_decr_inodes(transfer_to[cnt], inode_usage); + spin_unlock(&transfer_to[cnt]->dq_dqb_lock); goto over_quota; } } diff --git a/fs/quota/quota_v2.c b/fs/quota/quota_v2.c index c0187cda2c1e..a73e5b34db41 100644 --- a/fs/quota/quota_v2.c +++ b/fs/quota/quota_v2.c @@ -328,12 +328,16 @@ static int v2_write_dquot(struct dquot *dquot) if (!dquot->dq_off) { alloc = true; down_write(&dqopt->dqio_sem); + } else { + down_read(&dqopt->dqio_sem); } ret = qtree_write_dquot( sb_dqinfo(dquot->dq_sb, dquot->dq_id.type)->dqi_priv, dquot); if (alloc) up_write(&dqopt->dqio_sem); + else + up_read(&dqopt->dqio_sem); return ret; } diff --git a/fs/read_write.c b/fs/read_write.c index a2b9a47235c5..f0d4b16873e8 100644 --- a/fs/read_write.c +++ b/fs/read_write.c @@ -112,7 +112,7 @@ generic_file_llseek_size(struct file *file, loff_t offset, int whence, * In the generic case the entire file is data, so as long as * offset isn't at the end of the file then the offset is data. */ - if (offset >= eof) + if ((unsigned long long)offset >= eof) return -ENXIO; break; case SEEK_HOLE: @@ -120,7 +120,7 @@ generic_file_llseek_size(struct file *file, loff_t offset, int whence, * There is a virtual hole at the end of the file, so as long as * offset isn't i_size or larger, return i_size. */ - if (offset >= eof) + if ((unsigned long long)offset >= eof) return -ENXIO; offset = eof; break; diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c index ef4b48d1ea42..1c713fd5b3e6 100644 --- a/fs/userfaultfd.c +++ b/fs/userfaultfd.c @@ -588,6 +588,12 @@ static void userfaultfd_event_wait_completion(struct userfaultfd_ctx *ctx, break; if (ACCESS_ONCE(ctx->released) || fatal_signal_pending(current)) { + /* + * &ewq->wq may be queued in fork_event, but + * __remove_wait_queue ignores the head + * parameter. It would be a problem if it + * didn't. + */ __remove_wait_queue(&ctx->event_wqh, &ewq->wq); if (ewq->msg.event == UFFD_EVENT_FORK) { struct userfaultfd_ctx *new; @@ -1061,6 +1067,12 @@ static ssize_t userfaultfd_ctx_read(struct userfaultfd_ctx *ctx, int no_wait, (unsigned long) uwq->msg.arg.reserved.reserved1; list_move(&uwq->wq.entry, &fork_event); + /* + * fork_nctx can be freed as soon as + * we drop the lock, unless we take a + * reference on it. + */ + userfaultfd_ctx_get(fork_nctx); spin_unlock(&ctx->event_wqh.lock); ret = 0; break; @@ -1091,19 +1103,53 @@ static ssize_t userfaultfd_ctx_read(struct userfaultfd_ctx *ctx, int no_wait, if (!ret && msg->event == UFFD_EVENT_FORK) { ret = resolve_userfault_fork(ctx, fork_nctx, msg); + spin_lock(&ctx->event_wqh.lock); + if (!list_empty(&fork_event)) { + /* + * The fork thread didn't abort, so we can + * drop the temporary refcount. + */ + userfaultfd_ctx_put(fork_nctx); + + uwq = list_first_entry(&fork_event, + typeof(*uwq), + wq.entry); + /* + * If fork_event list wasn't empty and in turn + * the event wasn't already released by fork + * (the event is allocated on fork kernel + * stack), put the event back to its place in + * the event_wq. fork_event head will be freed + * as soon as we return so the event cannot + * stay queued there no matter the current + * "ret" value. + */ + list_del(&uwq->wq.entry); + __add_wait_queue(&ctx->event_wqh, &uwq->wq); - if (!ret) { - spin_lock(&ctx->event_wqh.lock); - if (!list_empty(&fork_event)) { - uwq = list_first_entry(&fork_event, - typeof(*uwq), - wq.entry); - list_del(&uwq->wq.entry); - __add_wait_queue(&ctx->event_wqh, &uwq->wq); + /* + * Leave the event in the waitqueue and report + * error to userland if we failed to resolve + * the userfault fork. + */ + if (likely(!ret)) userfaultfd_event_complete(ctx, uwq); - } - spin_unlock(&ctx->event_wqh.lock); + } else { + /* + * Here the fork thread aborted and the + * refcount from the fork thread on fork_nctx + * has already been released. We still hold + * the reference we took before releasing the + * lock above. If resolve_userfault_fork + * failed we've to drop it because the + * fork_nctx has to be freed in such case. If + * it succeeded we'll hold it because the new + * uffd references it. + */ + if (ret) + userfaultfd_ctx_put(fork_nctx); } + spin_unlock(&ctx->event_wqh.lock); } return ret; diff --git a/fs/xattr.c b/fs/xattr.c index 4424f7fecf14..61cd28ba25f3 100644 --- a/fs/xattr.c +++ b/fs/xattr.c @@ -250,7 +250,7 @@ xattr_getsecurity(struct inode *inode, const char *name, void *value, } memcpy(value, buffer, len); out: - security_release_secctx(buffer, len); + kfree(buffer); out_noalloc: return len; } diff --git a/fs/xfs/libxfs/xfs_ag_resv.c b/fs/xfs/libxfs/xfs_ag_resv.c index b008ff3250eb..df3e600835e8 100644 --- a/fs/xfs/libxfs/xfs_ag_resv.c +++ b/fs/xfs/libxfs/xfs_ag_resv.c @@ -156,7 +156,8 @@ __xfs_ag_resv_free( trace_xfs_ag_resv_free(pag, type, 0); resv = xfs_perag_resv(pag, type); - pag->pag_mount->m_ag_max_usable += resv->ar_asked; + if (pag->pag_agno == 0) + pag->pag_mount->m_ag_max_usable += resv->ar_asked; /* * AGFL blocks are always considered "free", so whatever * was reserved at mount time must be given back at umount. @@ -216,7 +217,14 @@ __xfs_ag_resv_init( return error; } - mp->m_ag_max_usable -= ask; + /* + * Reduce the maximum per-AG allocation length by however much we're + * trying to reserve for an AG. Since this is a filesystem-wide + * counter, we only make the adjustment for AG 0. This assumes that + * there aren't any AGs hungrier for per-AG reservation than AG 0. + */ + if (pag->pag_agno == 0) + mp->m_ag_max_usable -= ask; resv = xfs_perag_resv(pag, type); resv->ar_asked = ask; diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c index 459f4b4f08fe..044a363119be 100644 --- a/fs/xfs/libxfs/xfs_bmap.c +++ b/fs/xfs/libxfs/xfs_bmap.c @@ -49,7 +49,6 @@ #include "xfs_rmap.h" #include "xfs_ag_resv.h" #include "xfs_refcount.h" -#include "xfs_rmap_btree.h" #include "xfs_icache.h" @@ -192,12 +191,8 @@ xfs_bmap_worst_indlen( int maxrecs; /* maximum record count at this level */ xfs_mount_t *mp; /* mount structure */ xfs_filblks_t rval; /* return value */ - xfs_filblks_t orig_len; mp = ip->i_mount; - - /* Calculate the worst-case size of the bmbt. */ - orig_len = len; maxrecs = mp->m_bmap_dmxr[0]; for (level = 0, rval = 0; level < XFS_BM_MAXLEVELS(mp, XFS_DATA_FORK); @@ -205,20 +200,12 @@ xfs_bmap_worst_indlen( len += maxrecs - 1; do_div(len, maxrecs); rval += len; - if (len == 1) { - rval += XFS_BM_MAXLEVELS(mp, XFS_DATA_FORK) - + if (len == 1) + return rval + XFS_BM_MAXLEVELS(mp, XFS_DATA_FORK) - level - 1; - break; - } if (level == 0) maxrecs = mp->m_bmap_dmxr[1]; } - - /* Calculate the worst-case size of the rmapbt. */ - if (xfs_sb_version_hasrmapbt(&mp->m_sb)) - rval += 1 + xfs_rmapbt_calc_size(mp, orig_len) + - mp->m_rmap_maxlevels; - return rval; } diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c index 29172609f2a3..f18e5932aec4 100644 --- a/fs/xfs/xfs_aops.c +++ b/fs/xfs/xfs_aops.c @@ -343,7 +343,8 @@ xfs_end_io( error = xfs_reflink_end_cow(ip, offset, size); break; case XFS_IO_UNWRITTEN: - error = xfs_iomap_write_unwritten(ip, offset, size); + /* writeback should never update isize */ + error = xfs_iomap_write_unwritten(ip, offset, size, false); break; default: ASSERT(!xfs_ioend_is_append(ioend) || ioend->io_append_trans); diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c index cd9a5400ba4f..e9db7fc95b70 100644 --- a/fs/xfs/xfs_bmap_util.c +++ b/fs/xfs/xfs_bmap_util.c @@ -1459,7 +1459,19 @@ xfs_shift_file_space( return error; /* - * The extent shiting code works on extent granularity. So, if + * Clean out anything hanging around in the cow fork now that + * we've flushed all the dirty data out to disk to avoid having + * CoW extents at the wrong offsets. + */ + if (xfs_is_reflink_inode(ip)) { + error = xfs_reflink_cancel_cow_range(ip, offset, NULLFILEOFF, + true); + if (error) + return error; + } + + /* + * The extent shifting code works on extent granularity. So, if * stop_fsb is not the starting block of extent, we need to split * the extent at stop_fsb. */ @@ -2110,11 +2122,31 @@ xfs_swap_extents( ip->i_d.di_flags2 |= tip->i_d.di_flags2 & XFS_DIFLAG2_REFLINK; tip->i_d.di_flags2 &= ~XFS_DIFLAG2_REFLINK; tip->i_d.di_flags2 |= f & XFS_DIFLAG2_REFLINK; + } + + /* Swap the cow forks. */ + if (xfs_sb_version_hasreflink(&mp->m_sb)) { + xfs_extnum_t extnum; + + ASSERT(ip->i_cformat == XFS_DINODE_FMT_EXTENTS); + ASSERT(tip->i_cformat == XFS_DINODE_FMT_EXTENTS); + + extnum = ip->i_cnextents; + ip->i_cnextents = tip->i_cnextents; + tip->i_cnextents = extnum; + cowfp = ip->i_cowfp; ip->i_cowfp = tip->i_cowfp; tip->i_cowfp = cowfp; - xfs_inode_set_cowblocks_tag(ip); - xfs_inode_set_cowblocks_tag(tip); + + if (ip->i_cowfp && ip->i_cnextents) + xfs_inode_set_cowblocks_tag(ip); + else + xfs_inode_clear_cowblocks_tag(ip); + if (tip->i_cowfp && tip->i_cnextents) + xfs_inode_set_cowblocks_tag(tip); + else + xfs_inode_clear_cowblocks_tag(tip); } xfs_trans_log_inode(tp, ip, src_log_flags); diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c index da14658da310..2f97c12ca75e 100644 --- a/fs/xfs/xfs_buf.c +++ b/fs/xfs/xfs_buf.c @@ -1258,8 +1258,6 @@ xfs_buf_ioapply_map( int size; int offset; - total_nr_pages = bp->b_page_count; - /* skip the pages in the buffer before the start offset */ page_index = 0; offset = *buf_offset; diff --git a/fs/xfs/xfs_error.c b/fs/xfs/xfs_error.c index bd786a9ac2c3..eaf86f55b7f2 100644 --- a/fs/xfs/xfs_error.c +++ b/fs/xfs/xfs_error.c @@ -347,7 +347,7 @@ xfs_verifier_error( { struct xfs_mount *mp = bp->b_target->bt_mount; - xfs_alert(mp, "Metadata %s detected at %pF, %s block 0x%llx", + xfs_alert(mp, "Metadata %s detected at %pS, %s block 0x%llx", bp->b_error == -EFSBADCRC ? "CRC error" : "corruption", __return_address, bp->b_ops->name, bp->b_bn); diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c index ebdd0bd2b261..309e26c9dddb 100644 --- a/fs/xfs/xfs_file.c +++ b/fs/xfs/xfs_file.c @@ -58,7 +58,7 @@ xfs_zero_range( xfs_off_t count, bool *did_zero) { - return iomap_zero_range(VFS_I(ip), pos, count, NULL, &xfs_iomap_ops); + return iomap_zero_range(VFS_I(ip), pos, count, did_zero, &xfs_iomap_ops); } int @@ -377,8 +377,6 @@ restart: */ spin_lock(&ip->i_flags_lock); if (iocb->ki_pos > i_size_read(inode)) { - bool zero = false; - spin_unlock(&ip->i_flags_lock); if (!drained_dio) { if (*iolock == XFS_IOLOCK_SHARED) { @@ -399,7 +397,7 @@ restart: drained_dio = true; goto restart; } - error = xfs_zero_eof(ip, iocb->ki_pos, i_size_read(inode), &zero); + error = xfs_zero_eof(ip, iocb->ki_pos, i_size_read(inode), NULL); if (error) return error; } else @@ -436,7 +434,6 @@ xfs_dio_write_end_io( struct inode *inode = file_inode(iocb->ki_filp); struct xfs_inode *ip = XFS_I(inode); loff_t offset = iocb->ki_pos; - bool update_size = false; int error = 0; trace_xfs_end_io_direct_write(ip, offset, size); @@ -447,6 +444,21 @@ xfs_dio_write_end_io( if (size <= 0) return size; + if (flags & IOMAP_DIO_COW) { + error = xfs_reflink_end_cow(ip, offset, size); + if (error) + return error; + } + + /* + * Unwritten conversion updates the in-core isize after extent + * conversion but before updating the on-disk size. Updating isize any + * earlier allows a racing dio read to find unwritten extents before + * they are converted. + */ + if (flags & IOMAP_DIO_UNWRITTEN) + return xfs_iomap_write_unwritten(ip, offset, size, true); + /* * We need to update the in-core inode size here so that we don't end up * with the on-disk inode size being outside the in-core inode size. We @@ -461,20 +473,11 @@ xfs_dio_write_end_io( spin_lock(&ip->i_flags_lock); if (offset + size > i_size_read(inode)) { i_size_write(inode, offset + size); - update_size = true; - } - spin_unlock(&ip->i_flags_lock); - - if (flags & IOMAP_DIO_COW) { - error = xfs_reflink_end_cow(ip, offset, size); - if (error) - return error; - } - - if (flags & IOMAP_DIO_UNWRITTEN) - error = xfs_iomap_write_unwritten(ip, offset, size); - else if (update_size) + spin_unlock(&ip->i_flags_lock); error = xfs_setfilesize(ip, offset, size); + } else { + spin_unlock(&ip->i_flags_lock); + } return error; } diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c index 5599dda4727a..4ec5b7f45401 100644 --- a/fs/xfs/xfs_inode.c +++ b/fs/xfs/xfs_inode.c @@ -1624,10 +1624,12 @@ xfs_itruncate_extents( goto out; /* - * Clear the reflink flag if we truncated everything. + * Clear the reflink flag if there are no data fork blocks and + * there are no extents staged in the cow fork. */ - if (ip->i_d.di_nblocks == 0 && xfs_is_reflink_inode(ip)) { - ip->i_d.di_flags2 &= ~XFS_DIFLAG2_REFLINK; + if (xfs_is_reflink_inode(ip) && ip->i_cnextents == 0) { + if (ip->i_d.di_nblocks == 0) + ip->i_d.di_flags2 &= ~XFS_DIFLAG2_REFLINK; xfs_inode_clear_cowblocks_tag(ip); } diff --git a/fs/xfs/xfs_inode_item.c b/fs/xfs/xfs_inode_item.c index 6d0f74ec31e8..a705f34b58fa 100644 --- a/fs/xfs/xfs_inode_item.c +++ b/fs/xfs/xfs_inode_item.c @@ -745,7 +745,7 @@ xfs_iflush_done( */ iip = INODE_ITEM(blip); if ((iip->ili_logged && blip->li_lsn == iip->ili_flush_lsn) || - lip->li_flags & XFS_LI_FAILED) + (blip->li_flags & XFS_LI_FAILED)) need_ail++; blip = next; diff --git a/fs/xfs/xfs_ioctl.c b/fs/xfs/xfs_ioctl.c index 5049e8ab6e30..aa75389be8cf 100644 --- a/fs/xfs/xfs_ioctl.c +++ b/fs/xfs/xfs_ioctl.c @@ -1088,6 +1088,7 @@ xfs_ioctl_setattr_dax_invalidate( int *join_flags) { struct inode *inode = VFS_I(ip); + struct super_block *sb = inode->i_sb; int error; *join_flags = 0; @@ -1100,7 +1101,7 @@ xfs_ioctl_setattr_dax_invalidate( if (fa->fsx_xflags & FS_XFLAG_DAX) { if (!(S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode))) return -EINVAL; - if (ip->i_mount->m_sb.sb_blocksize != PAGE_SIZE) + if (bdev_dax_supported(sb, sb->s_blocksize) < 0) return -EINVAL; } diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c index a1909bc064e9..f179bdf1644d 100644 --- a/fs/xfs/xfs_iomap.c +++ b/fs/xfs/xfs_iomap.c @@ -829,7 +829,8 @@ int xfs_iomap_write_unwritten( xfs_inode_t *ip, xfs_off_t offset, - xfs_off_t count) + xfs_off_t count, + bool update_isize) { xfs_mount_t *mp = ip->i_mount; xfs_fileoff_t offset_fsb; @@ -840,6 +841,7 @@ xfs_iomap_write_unwritten( xfs_trans_t *tp; xfs_bmbt_irec_t imap; struct xfs_defer_ops dfops; + struct inode *inode = VFS_I(ip); xfs_fsize_t i_size; uint resblks; int error; @@ -899,7 +901,8 @@ xfs_iomap_write_unwritten( i_size = XFS_FSB_TO_B(mp, offset_fsb + count_fsb); if (i_size > offset + count) i_size = offset + count; - + if (update_isize && i_size > i_size_read(inode)) + i_size_write(inode, i_size); i_size = xfs_new_eof(ip, i_size); if (i_size) { ip->i_d.di_size = i_size; diff --git a/fs/xfs/xfs_iomap.h b/fs/xfs/xfs_iomap.h index 00db3ecea084..ee535065c5d0 100644 --- a/fs/xfs/xfs_iomap.h +++ b/fs/xfs/xfs_iomap.h @@ -27,7 +27,7 @@ int xfs_iomap_write_direct(struct xfs_inode *, xfs_off_t, size_t, struct xfs_bmbt_irec *, int); int xfs_iomap_write_allocate(struct xfs_inode *, int, xfs_off_t, struct xfs_bmbt_irec *); -int xfs_iomap_write_unwritten(struct xfs_inode *, xfs_off_t, xfs_off_t); +int xfs_iomap_write_unwritten(struct xfs_inode *, xfs_off_t, xfs_off_t, bool); void xfs_bmbt_to_iomap(struct xfs_inode *, struct iomap *, struct xfs_bmbt_irec *); diff --git a/fs/xfs/xfs_pnfs.c b/fs/xfs/xfs_pnfs.c index 2f2dc3c09ad0..4246876df7b7 100644 --- a/fs/xfs/xfs_pnfs.c +++ b/fs/xfs/xfs_pnfs.c @@ -274,7 +274,7 @@ xfs_fs_commit_blocks( (end - 1) >> PAGE_SHIFT); WARN_ON_ONCE(error); - error = xfs_iomap_write_unwritten(ip, start, length); + error = xfs_iomap_write_unwritten(ip, start, length, false); if (error) goto out_drop_iolock; } diff --git a/fs/xfs/xfs_reflink.c b/fs/xfs/xfs_reflink.c index 3246815c24d6..37e603bf1591 100644 --- a/fs/xfs/xfs_reflink.c +++ b/fs/xfs/xfs_reflink.c @@ -736,7 +736,13 @@ xfs_reflink_end_cow( /* If there is a hole at end_fsb - 1 go to the previous extent */ if (!xfs_iext_lookup_extent(ip, ifp, end_fsb - 1, &idx, &got) || got.br_startoff > end_fsb) { - ASSERT(idx > 0); + /* + * In case of racing, overlapping AIO writes no COW extents + * might be left by the time I/O completes for the loser of + * the race. In that case we are done. + */ + if (idx <= 0) + goto out_cancel; xfs_iext_get_extent(ifp, --idx, &got); } @@ -809,6 +815,7 @@ next_extent: out_defer: xfs_defer_cancel(&dfops); +out_cancel: xfs_trans_cancel(tp); xfs_iunlock(ip, XFS_ILOCK_EXCL); out: diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c index c996f4ae4a5f..584cf2d573ba 100644 --- a/fs/xfs/xfs_super.c +++ b/fs/xfs/xfs_super.c @@ -1654,6 +1654,16 @@ xfs_fs_fill_super( "DAX and reflink have not been tested together!"); } + if (mp->m_flags & XFS_MOUNT_DISCARD) { + struct request_queue *q = bdev_get_queue(sb->s_bdev); + + if (!blk_queue_discard(q)) { + xfs_warn(mp, "mounting with \"discard\" option, but " + "the device does not support discard"); + mp->m_flags &= ~XFS_MOUNT_DISCARD; + } + } + if (xfs_sb_version_hasrmapbt(&mp->m_sb)) { if (mp->m_sb.sb_rblocks) { xfs_alert(mp, diff --git a/include/asm-generic/percpu.h b/include/asm-generic/percpu.h index 0504ef8f3aa3..976f8ac26665 100644 --- a/include/asm-generic/percpu.h +++ b/include/asm-generic/percpu.h @@ -115,15 +115,35 @@ do { \ (__ret); \ }) -#define this_cpu_generic_read(pcp) \ +#define __this_cpu_generic_read_nopreempt(pcp) \ ({ \ typeof(pcp) __ret; \ preempt_disable_notrace(); \ - __ret = raw_cpu_generic_read(pcp); \ + __ret = READ_ONCE(*raw_cpu_ptr(&(pcp))); \ preempt_enable_notrace(); \ __ret; \ }) +#define __this_cpu_generic_read_noirq(pcp) \ +({ \ + typeof(pcp) __ret; \ + unsigned long __flags; \ + raw_local_irq_save(__flags); \ + __ret = raw_cpu_generic_read(pcp); \ + raw_local_irq_restore(__flags); \ + __ret; \ +}) + +#define this_cpu_generic_read(pcp) \ +({ \ + typeof(pcp) __ret; \ + if (__native_word(pcp)) \ + __ret = __this_cpu_generic_read_nopreempt(pcp); \ + else \ + __ret = __this_cpu_generic_read_noirq(pcp); \ + __ret; \ +}) + #define this_cpu_generic_to_op(pcp, val, op) \ do { \ unsigned long __flags; \ diff --git a/include/dt-bindings/reset/snps,hsdk-reset.h b/include/dt-bindings/reset/snps,hsdk-reset.h new file mode 100644 index 000000000000..e1a643e4bc91 --- /dev/null +++ b/include/dt-bindings/reset/snps,hsdk-reset.h @@ -0,0 +1,17 @@ +/** + * This header provides index for the HSDK reset controller. + */ +#ifndef _DT_BINDINGS_RESET_CONTROLLER_SNPS_HSDK +#define _DT_BINDINGS_RESET_CONTROLLER_SNPS_HSDK + +#define HSDK_APB_RESET 0 +#define HSDK_AXI_RESET 1 +#define HSDK_ETH_RESET 2 +#define HSDK_USB_RESET 3 +#define HSDK_SDIO_RESET 4 +#define HSDK_HDMI_RESET 5 +#define HSDK_GFX_RESET 6 +#define HSDK_DMAC_RESET 7 +#define HSDK_EBI_RESET 8 + +#endif /*_DT_BINDINGS_RESET_CONTROLLER_SNPS_HSDK*/ diff --git a/include/dt-bindings/reset/snps,hsdk-v1-reset.h b/include/dt-bindings/reset/snps,hsdk-v1-reset.h deleted file mode 100644 index d898c89b7123..000000000000 --- a/include/dt-bindings/reset/snps,hsdk-v1-reset.h +++ /dev/null @@ -1,17 +0,0 @@ -/** - * This header provides index for the HSDK v1 reset controller. - */ -#ifndef _DT_BINDINGS_RESET_CONTROLLER_HSDK_V1 -#define _DT_BINDINGS_RESET_CONTROLLER_HSDK_V1 - -#define HSDK_V1_APB_RESET 0 -#define HSDK_V1_AXI_RESET 1 -#define HSDK_V1_ETH_RESET 2 -#define HSDK_V1_USB_RESET 3 -#define HSDK_V1_SDIO_RESET 4 -#define HSDK_V1_HDMI_RESET 5 -#define HSDK_V1_GFX_RESET 6 -#define HSDK_V1_DMAC_RESET 7 -#define HSDK_V1_EBI_RESET 8 - -#endif /*_DT_BINDINGS_RESET_CONTROLLER_HSDK_V1*/ diff --git a/include/linux/binfmts.h b/include/linux/binfmts.h index fb44d6180ca0..18d05b5491f3 100644 --- a/include/linux/binfmts.h +++ b/include/linux/binfmts.h @@ -131,7 +131,7 @@ extern int setup_arg_pages(struct linux_binprm * bprm, int executable_stack); extern int transfer_args_to_stack(struct linux_binprm *bprm, unsigned long *sp_location); -extern int bprm_change_interp(char *interp, struct linux_binprm *bprm); +extern int bprm_change_interp(const char *interp, struct linux_binprm *bprm); extern int copy_strings_kernel(int argc, const char *const *argv, struct linux_binprm *bprm); extern int prepare_bprm_creds(struct linux_binprm *bprm); diff --git a/include/linux/bitfield.h b/include/linux/bitfield.h index 8b9d6fff002d..f2deb71958b2 100644 --- a/include/linux/bitfield.h +++ b/include/linux/bitfield.h @@ -92,7 +92,7 @@ /** * FIELD_GET() - extract a bitfield element * @_mask: shifted mask defining the field's length and position - * @_reg: 32bit value of entire bitfield + * @_reg: value of entire bitfield * * FIELD_GET() extracts the field specified by @_mask from the * bitfield passed in as @_reg by masking and shifting it down. diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 460294bb0fa5..02fa42d24b52 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -551,6 +551,7 @@ struct request_queue { int node; #ifdef CONFIG_BLK_DEV_IO_TRACE struct blk_trace *blk_trace; + struct mutex blk_trace_mutex; #endif /* * for flush operations diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index f24bfb2b9a2d..6d508767e144 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -3,8 +3,27 @@ #include <linux/types.h> +/* + * CPU-up CPU-down + * + * BP AP BP AP + * + * OFFLINE OFFLINE + * | ^ + * v | + * BRINGUP_CPU->AP_OFFLINE BRINGUP_CPU <- AP_IDLE_DEAD (idle thread/play_dead) + * | AP_OFFLINE + * v (IRQ-off) ,---------------^ + * AP_ONLNE | (stop_machine) + * | TEARDOWN_CPU <- AP_ONLINE_IDLE + * | ^ + * v | + * AP_ACTIVE AP_ACTIVE + */ + enum cpuhp_state { - CPUHP_OFFLINE, + CPUHP_INVALID = -1, + CPUHP_OFFLINE = 0, CPUHP_CREATE_THREADS, CPUHP_PERF_PREPARE, CPUHP_PERF_X86_PREPARE, diff --git a/include/linux/device.h b/include/linux/device.h index 1d2607923a24..66fe271c2544 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -307,8 +307,6 @@ struct driver_attribute { size_t count); }; -#define DRIVER_ATTR(_name, _mode, _show, _store) \ - struct driver_attribute driver_attr_##_name = __ATTR(_name, _mode, _show, _store) #define DRIVER_ATTR_RW(_name) \ struct driver_attribute driver_attr_##_name = __ATTR_RW(_name) #define DRIVER_ATTR_RO(_name) \ diff --git a/include/linux/fs.h b/include/linux/fs.h index 339e73742e73..13dab191a23e 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -403,7 +403,7 @@ struct address_space { unsigned long flags; /* error bits */ spinlock_t private_lock; /* for use by the address_space */ gfp_t gfp_mask; /* implicit gfp mask for allocations */ - struct list_head private_list; /* ditto */ + struct list_head private_list; /* for use by the address_space */ void *private_data; /* ditto */ errseq_t wb_err; } __attribute__((aligned(sizeof(long)))) __randomize_layout; diff --git a/include/linux/iio/adc/ad_sigma_delta.h b/include/linux/iio/adc/ad_sigma_delta.h index 5ba430cc9a87..1fc7abd28b0b 100644 --- a/include/linux/iio/adc/ad_sigma_delta.h +++ b/include/linux/iio/adc/ad_sigma_delta.h @@ -111,6 +111,9 @@ int ad_sd_write_reg(struct ad_sigma_delta *sigma_delta, unsigned int reg, int ad_sd_read_reg(struct ad_sigma_delta *sigma_delta, unsigned int reg, unsigned int size, unsigned int *val); +int ad_sd_reset(struct ad_sigma_delta *sigma_delta, + unsigned int reset_length); + int ad_sigma_delta_single_conversion(struct iio_dev *indio_dev, const struct iio_chan_spec *chan, int *val); int ad_sd_calibrate_all(struct ad_sigma_delta *sigma_delta, diff --git a/include/linux/iommu.h b/include/linux/iommu.h index a7f2ac689d29..41b8c5757859 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -167,11 +167,11 @@ struct iommu_resv_region { * @map: map a physically contiguous memory region to an iommu domain * @unmap: unmap a physically contiguous memory region from an iommu domain * @map_sg: map a scatter-gather list of physically contiguous memory chunks + * to an iommu domain * @flush_tlb_all: Synchronously flush all hardware TLBs for this domain * @tlb_range_add: Add a given iova range to the flush queue for this domain * @tlb_sync: Flush all queued ranges from the hardware TLBs and empty flush * queue - * to an iommu domain * @iova_to_phys: translate iova to physical address * @add_device: add device to iommu grouping * @remove_device: remove device from iommu grouping diff --git a/include/linux/key.h b/include/linux/key.h index 044114185120..e315e16b6ff8 100644 --- a/include/linux/key.h +++ b/include/linux/key.h @@ -187,6 +187,7 @@ struct key { #define KEY_FLAG_BUILTIN 8 /* set if key is built in to the kernel */ #define KEY_FLAG_ROOT_CAN_INVAL 9 /* set if key can be invalidated by root without permission */ #define KEY_FLAG_KEEP 10 /* set if key should not be removed */ +#define KEY_FLAG_UID_KEYRING 11 /* set if key is a user or user session keyring */ /* the key type and key description string * - the desc is used to match a key against search criteria @@ -243,6 +244,7 @@ extern struct key *key_alloc(struct key_type *type, #define KEY_ALLOC_NOT_IN_QUOTA 0x0002 /* not in quota */ #define KEY_ALLOC_BUILT_IN 0x0004 /* Key is built into kernel */ #define KEY_ALLOC_BYPASS_RESTRICTION 0x0008 /* Override the check on restricted keyrings */ +#define KEY_ALLOC_UID_KEYRING 0x0010 /* allocating a user or user session keyring */ extern void key_revoke(struct key *key); extern void key_invalidate(struct key *key); diff --git a/include/linux/mlx5/cq.h b/include/linux/mlx5/cq.h index 95898847c7d4..cc718e245b1e 100644 --- a/include/linux/mlx5/cq.h +++ b/include/linux/mlx5/cq.h @@ -125,11 +125,13 @@ struct mlx5_cq_modify_params { enum { CQE_SIZE_64 = 0, CQE_SIZE_128 = 1, + CQE_SIZE_128_PAD = 2, }; -static inline int cqe_sz_to_mlx_sz(u8 size) +static inline int cqe_sz_to_mlx_sz(u8 size, int padding_128_en) { - return size == 64 ? CQE_SIZE_64 : CQE_SIZE_128; + return padding_128_en ? CQE_SIZE_128_PAD : + size == 64 ? CQE_SIZE_64 : CQE_SIZE_128; } static inline void mlx5_cq_set_ci(struct mlx5_core_cq *cq) diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h index eaf4ad209c8f..e32dbc4934db 100644 --- a/include/linux/mlx5/device.h +++ b/include/linux/mlx5/device.h @@ -980,7 +980,6 @@ enum mlx5_cap_type { MLX5_CAP_RESERVED, MLX5_CAP_VECTOR_CALC, MLX5_CAP_QOS, - MLX5_CAP_FPGA, /* NUM OF CAP Types */ MLX5_CAP_NUM }; @@ -1110,10 +1109,10 @@ enum mlx5_mcam_feature_groups { MLX5_GET(mcam_reg, (mdev)->caps.mcam, mng_feature_cap_mask.enhanced_features.fld) #define MLX5_CAP_FPGA(mdev, cap) \ - MLX5_GET(fpga_cap, (mdev)->caps.hca_cur[MLX5_CAP_FPGA], cap) + MLX5_GET(fpga_cap, (mdev)->caps.fpga, cap) #define MLX5_CAP64_FPGA(mdev, cap) \ - MLX5_GET64(fpga_cap, (mdev)->caps.hca_cur[MLX5_CAP_FPGA], cap) + MLX5_GET64(fpga_cap, (mdev)->caps.fpga, cap) enum { MLX5_CMD_STAT_OK = 0x0, diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 02ff700e4f30..08c77b7e59cb 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -49,6 +49,8 @@ #include <linux/mlx5/device.h> #include <linux/mlx5/doorbell.h> #include <linux/mlx5/srq.h> +#include <linux/timecounter.h> +#include <linux/ptp_clock_kernel.h> enum { MLX5_BOARD_ID_LEN = 64, @@ -760,6 +762,27 @@ struct mlx5_rsvd_gids { struct ida ida; }; +#define MAX_PIN_NUM 8 +struct mlx5_pps { + u8 pin_caps[MAX_PIN_NUM]; + struct work_struct out_work; + u64 start[MAX_PIN_NUM]; + u8 enabled; +}; + +struct mlx5_clock { + rwlock_t lock; + struct cyclecounter cycles; + struct timecounter tc; + struct hwtstamp_config hwtstamp_config; + u32 nominal_c_mult; + unsigned long overflow_period; + struct delayed_work overflow_work; + struct ptp_clock *ptp; + struct ptp_clock_info ptp_info; + struct mlx5_pps pps_info; +}; + struct mlx5_core_dev { struct pci_dev *pdev; /* sync pci state */ @@ -774,6 +797,7 @@ struct mlx5_core_dev { u32 hca_max[MLX5_CAP_NUM][MLX5_UN_SZ_DW(hca_cap_union)]; u32 pcam[MLX5_ST_SZ_DW(pcam_reg)]; u32 mcam[MLX5_ST_SZ_DW(mcam_reg)]; + u32 fpga[MLX5_ST_SZ_DW(fpga_cap)]; } caps; phys_addr_t iseg_base; struct mlx5_init_seg __iomem *iseg; @@ -799,6 +823,7 @@ struct mlx5_core_dev { #ifdef CONFIG_RFS_ACCEL struct cpu_rmap *rmap; #endif + struct mlx5_clock clock; }; struct mlx5_db { diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index a528b35a022e..d4c29c183d28 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -327,7 +327,8 @@ struct mlx5_ifc_flow_table_prop_layout_bits { u8 reserved_at_80[0x18]; u8 log_max_destination[0x8]; - u8 reserved_at_a0[0x18]; + u8 log_max_flow_counter[0x8]; + u8 reserved_at_a8[0x10]; u8 log_max_flow[0x8]; u8 reserved_at_c0[0x40]; @@ -613,7 +614,9 @@ struct mlx5_ifc_per_protocol_networking_offload_caps_bits { u8 swp[0x1]; u8 swp_csum[0x1]; u8 swp_lso[0x1]; - u8 reserved_at_23[0x1d]; + u8 reserved_at_23[0x1b]; + u8 max_geneve_opt_len[0x1]; + u8 tunnel_stateless_geneve_rx[0x1]; u8 reserved_at_40[0x10]; u8 lro_min_mss_size[0x10]; @@ -743,6 +746,7 @@ enum { MLX5_WQ_TYPE_LINKED_LIST = 0x0, MLX5_WQ_TYPE_CYCLIC = 0x1, MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ = 0x2, + MLX5_WQ_TYPE_CYCLIC_STRIDING_RQ = 0x3, }; enum { @@ -1045,7 +1049,9 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 num_of_uars_per_page[0x20]; u8 reserved_at_540[0x40]; - u8 reserved_at_580[0x3f]; + u8 reserved_at_580[0x3d]; + u8 cqe_128_always[0x1]; + u8 cqe_compression_128[0x1]; u8 cqe_compression[0x1]; u8 cqe_compression_timeout[0x10]; diff --git a/include/linux/mm.h b/include/linux/mm.h index f8c10d336e42..065d99deb847 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -240,7 +240,7 @@ extern unsigned int kobjsize(const void *objp); #if defined(CONFIG_X86_INTEL_MPX) /* MPX specific bounds table or bounds directory */ -# define VM_MPX VM_HIGH_ARCH_BIT_4 +# define VM_MPX VM_HIGH_ARCH_4 #else # define VM_MPX VM_NONE #endif diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h index f3f2d07feb2a..9a43763a68ad 100644 --- a/include/linux/mmc/host.h +++ b/include/linux/mmc/host.h @@ -316,7 +316,7 @@ struct mmc_host { #define MMC_CAP_UHS_SDR50 (1 << 18) /* Host supports UHS SDR50 mode */ #define MMC_CAP_UHS_SDR104 (1 << 19) /* Host supports UHS SDR104 mode */ #define MMC_CAP_UHS_DDR50 (1 << 20) /* Host supports UHS DDR50 mode */ -#define MMC_CAP_NO_BOUNCE_BUFF (1 << 21) /* Disable bounce buffers on host */ +/* (1 << 21) is free for reuse */ #define MMC_CAP_DRIVER_TYPE_A (1 << 23) /* Host supports Driver Type A */ #define MMC_CAP_DRIVER_TYPE_C (1 << 24) /* Host supports Driver Type C */ #define MMC_CAP_DRIVER_TYPE_D (1 << 25) /* Host supports Driver Type D */ diff --git a/include/linux/mmu_notifier.h b/include/linux/mmu_notifier.h index 7b2e31b1745a..6866e8126982 100644 --- a/include/linux/mmu_notifier.h +++ b/include/linux/mmu_notifier.h @@ -400,6 +400,11 @@ extern void mmu_notifier_synchronize(void); #else /* CONFIG_MMU_NOTIFIER */ +static inline int mm_has_notifiers(struct mm_struct *mm) +{ + return 0; +} + static inline void mmu_notifier_release(struct mm_struct *mm) { } diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 356a814e7c8e..c8f89417740b 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -1094,8 +1094,14 @@ static inline unsigned long early_pfn_to_nid(unsigned long pfn) #error Allocator MAX_ORDER exceeds SECTION_SIZE #endif -#define pfn_to_section_nr(pfn) ((pfn) >> PFN_SECTION_SHIFT) -#define section_nr_to_pfn(sec) ((sec) << PFN_SECTION_SHIFT) +static inline unsigned long pfn_to_section_nr(unsigned long pfn) +{ + return pfn >> PFN_SECTION_SHIFT; +} +static inline unsigned long section_nr_to_pfn(unsigned long sec) +{ + return sec << PFN_SECTION_SHIFT; +} #define SECTION_ALIGN_UP(pfn) (((pfn) + PAGES_PER_SECTION - 1) & PAGE_SECTION_MASK) #define SECTION_ALIGN_DOWN(pfn) ((pfn) & PAGE_SECTION_MASK) diff --git a/include/linux/nmi.h b/include/linux/nmi.h index a36abe2da13e..27e249ed7c5c 100644 --- a/include/linux/nmi.h +++ b/include/linux/nmi.h @@ -12,11 +12,31 @@ #ifdef CONFIG_LOCKUP_DETECTOR void lockup_detector_init(void); +void lockup_detector_soft_poweroff(void); +void lockup_detector_cleanup(void); +bool is_hardlockup(void); + +extern int watchdog_user_enabled; +extern int nmi_watchdog_user_enabled; +extern int soft_watchdog_user_enabled; +extern int watchdog_thresh; +extern unsigned long watchdog_enabled; + +extern struct cpumask watchdog_cpumask; +extern unsigned long *watchdog_cpumask_bits; +#ifdef CONFIG_SMP +extern int sysctl_softlockup_all_cpu_backtrace; +extern int sysctl_hardlockup_all_cpu_backtrace; #else -static inline void lockup_detector_init(void) -{ -} -#endif +#define sysctl_softlockup_all_cpu_backtrace 0 +#define sysctl_hardlockup_all_cpu_backtrace 0 +#endif /* !CONFIG_SMP */ + +#else /* CONFIG_LOCKUP_DETECTOR */ +static inline void lockup_detector_init(void) { } +static inline void lockup_detector_soft_poweroff(void) { } +static inline void lockup_detector_cleanup(void) { } +#endif /* !CONFIG_LOCKUP_DETECTOR */ #ifdef CONFIG_SOFTLOCKUP_DETECTOR extern void touch_softlockup_watchdog_sched(void); @@ -24,29 +44,17 @@ extern void touch_softlockup_watchdog(void); extern void touch_softlockup_watchdog_sync(void); extern void touch_all_softlockup_watchdogs(void); extern unsigned int softlockup_panic; -extern int soft_watchdog_enabled; -extern atomic_t watchdog_park_in_progress; #else -static inline void touch_softlockup_watchdog_sched(void) -{ -} -static inline void touch_softlockup_watchdog(void) -{ -} -static inline void touch_softlockup_watchdog_sync(void) -{ -} -static inline void touch_all_softlockup_watchdogs(void) -{ -} +static inline void touch_softlockup_watchdog_sched(void) { } +static inline void touch_softlockup_watchdog(void) { } +static inline void touch_softlockup_watchdog_sync(void) { } +static inline void touch_all_softlockup_watchdogs(void) { } #endif #ifdef CONFIG_DETECT_HUNG_TASK void reset_hung_task_detector(void); #else -static inline void reset_hung_task_detector(void) -{ -} +static inline void reset_hung_task_detector(void) { } #endif /* @@ -54,12 +62,12 @@ static inline void reset_hung_task_detector(void) * 'watchdog_enabled' variable. Each lockup detector has its dedicated bit - * bit 0 for the hard lockup detector and bit 1 for the soft lockup detector. * - * 'watchdog_user_enabled', 'nmi_watchdog_enabled' and 'soft_watchdog_enabled' - * are variables that are only used as an 'interface' between the parameters - * in /proc/sys/kernel and the internal state bits in 'watchdog_enabled'. The - * 'watchdog_thresh' variable is handled differently because its value is not - * boolean, and the lockup detectors are 'suspended' while 'watchdog_thresh' - * is equal zero. + * 'watchdog_user_enabled', 'nmi_watchdog_user_enabled' and + * 'soft_watchdog_user_enabled' are variables that are only used as an + * 'interface' between the parameters in /proc/sys/kernel and the internal + * state bits in 'watchdog_enabled'. The 'watchdog_thresh' variable is + * handled differently because its value is not boolean, and the lockup + * detectors are 'suspended' while 'watchdog_thresh' is equal zero. */ #define NMI_WATCHDOG_ENABLED_BIT 0 #define SOFT_WATCHDOG_ENABLED_BIT 1 @@ -73,17 +81,41 @@ extern unsigned int hardlockup_panic; static inline void hardlockup_detector_disable(void) {} #endif +#if defined(CONFIG_HAVE_NMI_WATCHDOG) || defined(CONFIG_HARDLOCKUP_DETECTOR) +# define NMI_WATCHDOG_SYSCTL_PERM 0644 +#else +# define NMI_WATCHDOG_SYSCTL_PERM 0444 +#endif + #if defined(CONFIG_HARDLOCKUP_DETECTOR_PERF) extern void arch_touch_nmi_watchdog(void); +extern void hardlockup_detector_perf_stop(void); +extern void hardlockup_detector_perf_restart(void); +extern void hardlockup_detector_perf_disable(void); +extern void hardlockup_detector_perf_enable(void); +extern void hardlockup_detector_perf_cleanup(void); +extern int hardlockup_detector_perf_init(void); #else -#if !defined(CONFIG_HAVE_NMI_WATCHDOG) +static inline void hardlockup_detector_perf_stop(void) { } +static inline void hardlockup_detector_perf_restart(void) { } +static inline void hardlockup_detector_perf_disable(void) { } +static inline void hardlockup_detector_perf_enable(void) { } +static inline void hardlockup_detector_perf_cleanup(void) { } +# if !defined(CONFIG_HAVE_NMI_WATCHDOG) +static inline int hardlockup_detector_perf_init(void) { return -ENODEV; } static inline void arch_touch_nmi_watchdog(void) {} +# else +static inline int hardlockup_detector_perf_init(void) { return 0; } +# endif #endif -#endif + +void watchdog_nmi_stop(void); +void watchdog_nmi_start(void); +int watchdog_nmi_probe(void); /** * touch_nmi_watchdog - restart NMI watchdog timeout. - * + * * If the architecture supports the NMI watchdog, touch_nmi_watchdog() * may be used to reset the timeout - for code which intentionally * disables interrupts for a long time. This call is stateless. @@ -153,22 +185,6 @@ static inline bool trigger_single_cpu_backtrace(int cpu) u64 hw_nmi_get_sample_period(int watchdog_thresh); #endif -#ifdef CONFIG_LOCKUP_DETECTOR -extern int nmi_watchdog_enabled; -extern int watchdog_user_enabled; -extern int watchdog_thresh; -extern unsigned long watchdog_enabled; -extern struct cpumask watchdog_cpumask; -extern unsigned long *watchdog_cpumask_bits; -extern int __read_mostly watchdog_suspended; -#ifdef CONFIG_SMP -extern int sysctl_softlockup_all_cpu_backtrace; -extern int sysctl_hardlockup_all_cpu_backtrace; -#else -#define sysctl_softlockup_all_cpu_backtrace 0 -#define sysctl_hardlockup_all_cpu_backtrace 0 -#endif - #if defined(CONFIG_HARDLOCKUP_CHECK_TIMESTAMP) && \ defined(CONFIG_HARDLOCKUP_DETECTOR) void watchdog_update_hrtimer_threshold(u64 period); @@ -176,7 +192,6 @@ void watchdog_update_hrtimer_threshold(u64 period); static inline void watchdog_update_hrtimer_threshold(u64 period) { } #endif -extern bool is_hardlockup(void); struct ctl_table; extern int proc_watchdog(struct ctl_table *, int , void __user *, size_t *, loff_t *); @@ -188,18 +203,6 @@ extern int proc_watchdog_thresh(struct ctl_table *, int , void __user *, size_t *, loff_t *); extern int proc_watchdog_cpumask(struct ctl_table *, int, void __user *, size_t *, loff_t *); -extern int lockup_detector_suspend(void); -extern void lockup_detector_resume(void); -#else -static inline int lockup_detector_suspend(void) -{ - return 0; -} - -static inline void lockup_detector_resume(void) -{ -} -#endif #ifdef CONFIG_HAVE_ACPI_APEI_NMI #include <asm/nmi.h> diff --git a/include/linux/nvme-fc-driver.h b/include/linux/nvme-fc-driver.h index 9c5cb4480806..a726f96010d5 100644 --- a/include/linux/nvme-fc-driver.h +++ b/include/linux/nvme-fc-driver.h @@ -346,11 +346,6 @@ struct nvme_fc_remote_port { * indicating an FC transport Aborted status. * Entrypoint is Mandatory. * - * @defer_rcv: Called by the transport to signal the LLLD that it has - * begun processing of a previously received NVME CMD IU. The LLDD - * is now free to re-use the rcv buffer associated with the - * nvmefc_tgt_fcp_req. - * * @max_hw_queues: indicates the maximum number of hw queues the LLDD * supports for cpu affinitization. * Value is Mandatory. Must be at least 1. @@ -806,11 +801,19 @@ struct nvmet_fc_target_port { * outstanding operation (if there was one) to complete, then will * call the fcp_req_release() callback to return the command's * exchange context back to the LLDD. + * Entrypoint is Mandatory. * * @fcp_req_release: Called by the transport to return a nvmefc_tgt_fcp_req * to the LLDD after all operations on the fcp operation are complete. * This may be due to the command completing or upon completion of * abort cleanup. + * Entrypoint is Mandatory. + * + * @defer_rcv: Called by the transport to signal the LLLD that it has + * begun processing of a previously received NVME CMD IU. The LLDD + * is now free to re-use the rcv buffer associated with the + * nvmefc_tgt_fcp_req. + * Entrypoint is Optional. * * @max_hw_queues: indicates the maximum number of hw queues the LLDD * supports for cpu affinitization. diff --git a/include/linux/nvme.h b/include/linux/nvme.h index 87723c86f136..9310ce77d8e1 100644 --- a/include/linux/nvme.h +++ b/include/linux/nvme.h @@ -471,12 +471,14 @@ enum nvme_opcode { * * @NVME_SGL_FMT_ADDRESS: absolute address of the data block * @NVME_SGL_FMT_OFFSET: relative offset of the in-capsule data block + * @NVME_SGL_FMT_TRANSPORT_A: transport defined format, value 0xA * @NVME_SGL_FMT_INVALIDATE: RDMA transport specific remote invalidation * request subtype */ enum { NVME_SGL_FMT_ADDRESS = 0x00, NVME_SGL_FMT_OFFSET = 0x01, + NVME_SGL_FMT_TRANSPORT_A = 0x0A, NVME_SGL_FMT_INVALIDATE = 0x0f, }; @@ -490,12 +492,16 @@ enum { * * For struct nvme_keyed_sgl_desc: * @NVME_KEY_SGL_FMT_DATA_DESC: keyed data block descriptor + * + * Transport-specific SGL types: + * @NVME_TRANSPORT_SGL_DATA_DESC: Transport SGL data dlock descriptor */ enum { NVME_SGL_FMT_DATA_DESC = 0x00, NVME_SGL_FMT_SEG_DESC = 0x02, NVME_SGL_FMT_LAST_SEG_DESC = 0x03, NVME_KEY_SGL_FMT_DATA_DESC = 0x04, + NVME_TRANSPORT_SGL_DATA_DESC = 0x05, }; struct nvme_sgl_desc { @@ -1127,19 +1133,6 @@ enum { NVME_SC_UNWRITTEN_BLOCK = 0x287, NVME_SC_DNR = 0x4000, - - - /* - * FC Transport-specific error status values for NVME commands - * - * Transport-specific status code values must be in the range 0xB0..0xBF - */ - - /* Generic FC failure - catchall */ - NVME_SC_FC_TRANSPORT_ERROR = 0x00B0, - - /* I/O failure due to FC ABTS'd */ - NVME_SC_FC_TRANSPORT_ABORTED = 0x00B1, }; struct nvme_completion { diff --git a/include/linux/pci.h b/include/linux/pci.h index f68c58a93dd0..f4f8ee5a7362 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1685,6 +1685,8 @@ static inline int pci_get_new_domain_nr(void) { return -ENOSYS; } #define dev_is_pci(d) (false) #define dev_is_pf(d) (false) +static inline bool pci_acs_enabled(struct pci_dev *pdev, u16 acs_flags) +{ return false; } #endif /* CONFIG_PCI */ /* Include architecture-dependent settings and functions */ diff --git a/include/linux/sched.h b/include/linux/sched.h index 92fb8dd5a9e4..26a7df4e558c 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -65,25 +65,23 @@ struct task_group; */ /* Used in tsk->state: */ -#define TASK_RUNNING 0 -#define TASK_INTERRUPTIBLE 1 -#define TASK_UNINTERRUPTIBLE 2 -#define __TASK_STOPPED 4 -#define __TASK_TRACED 8 +#define TASK_RUNNING 0x0000 +#define TASK_INTERRUPTIBLE 0x0001 +#define TASK_UNINTERRUPTIBLE 0x0002 +#define __TASK_STOPPED 0x0004 +#define __TASK_TRACED 0x0008 /* Used in tsk->exit_state: */ -#define EXIT_DEAD 16 -#define EXIT_ZOMBIE 32 +#define EXIT_DEAD 0x0010 +#define EXIT_ZOMBIE 0x0020 #define EXIT_TRACE (EXIT_ZOMBIE | EXIT_DEAD) /* Used in tsk->state again: */ -#define TASK_DEAD 64 -#define TASK_WAKEKILL 128 -#define TASK_WAKING 256 -#define TASK_PARKED 512 -#define TASK_NOLOAD 1024 -#define TASK_NEW 2048 -#define TASK_STATE_MAX 4096 - -#define TASK_STATE_TO_CHAR_STR "RSDTtXZxKWPNn" +#define TASK_PARKED 0x0040 +#define TASK_DEAD 0x0080 +#define TASK_WAKEKILL 0x0100 +#define TASK_WAKING 0x0200 +#define TASK_NOLOAD 0x0400 +#define TASK_NEW 0x0800 +#define TASK_STATE_MAX 0x1000 /* Convenience macros for the sake of set_current_state: */ #define TASK_KILLABLE (TASK_WAKEKILL | TASK_UNINTERRUPTIBLE) @@ -99,7 +97,8 @@ struct task_group; /* get_task_state(): */ #define TASK_REPORT (TASK_RUNNING | TASK_INTERRUPTIBLE | \ TASK_UNINTERRUPTIBLE | __TASK_STOPPED | \ - __TASK_TRACED | EXIT_ZOMBIE | EXIT_DEAD) + __TASK_TRACED | EXIT_DEAD | EXIT_ZOMBIE | \ + TASK_PARKED) #define task_is_traced(task) ((task->state & __TASK_TRACED) != 0) @@ -1243,17 +1242,34 @@ static inline pid_t task_pgrp_nr(struct task_struct *tsk) return task_pgrp_nr_ns(tsk, &init_pid_ns); } -static inline char task_state_to_char(struct task_struct *task) +#define TASK_REPORT_IDLE (TASK_REPORT + 1) +#define TASK_REPORT_MAX (TASK_REPORT_IDLE << 1) + +static inline unsigned int __get_task_state(struct task_struct *tsk) +{ + unsigned int tsk_state = READ_ONCE(tsk->state); + unsigned int state = (tsk_state | tsk->exit_state) & TASK_REPORT; + + BUILD_BUG_ON_NOT_POWER_OF_2(TASK_REPORT_MAX); + + if (tsk_state == TASK_IDLE) + state = TASK_REPORT_IDLE; + + return fls(state); +} + +static inline char __task_state_to_char(unsigned int state) { - const char stat_nam[] = TASK_STATE_TO_CHAR_STR; - unsigned long state = task->state; + static const char state_char[] = "RSDTtXZPI"; - state = state ? __ffs(state) + 1 : 0; + BUILD_BUG_ON(1 + ilog2(TASK_REPORT_MAX) != sizeof(state_char) - 1); - /* Make sure the string lines up properly with the number of task states: */ - BUILD_BUG_ON(sizeof(TASK_STATE_TO_CHAR_STR)-1 != ilog2(TASK_STATE_MAX)+1); + return state_char[state]; +} - return state < sizeof(stat_nam) - 1 ? stat_nam[state] : '?'; +static inline char task_state_to_char(struct task_struct *tsk) +{ + return __task_state_to_char(__get_task_state(tsk)); } /** diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h index 3a19c253bdb1..ae53e413fb13 100644 --- a/include/linux/sched/mm.h +++ b/include/linux/sched/mm.h @@ -84,6 +84,12 @@ static inline bool mmget_not_zero(struct mm_struct *mm) /* mmput gets rid of the mappings and all user-space */ extern void mmput(struct mm_struct *); +#ifdef CONFIG_MMU +/* same as above but performs the slow path from the async context. Can + * be called from the atomic context as well + */ +void mmput_async(struct mm_struct *); +#endif /* Grab a reference to a task's mm, if it is not already going away */ extern struct mm_struct *get_task_mm(struct task_struct *task); diff --git a/include/linux/smpboot.h b/include/linux/smpboot.h index 12910cf19869..c149aa7bedf3 100644 --- a/include/linux/smpboot.h +++ b/include/linux/smpboot.h @@ -55,7 +55,7 @@ smpboot_register_percpu_thread(struct smp_hotplug_thread *plug_thread) } void smpboot_unregister_percpu_thread(struct smp_hotplug_thread *plug_thread); -int smpboot_update_cpumask_percpu_thread(struct smp_hotplug_thread *plug_thread, - const struct cpumask *); +void smpboot_update_cpumask_percpu_thread(struct smp_hotplug_thread *plug_thread, + const struct cpumask *); #endif diff --git a/include/linux/timer.h b/include/linux/timer.h index e6789b8757d5..6383c528b148 100644 --- a/include/linux/timer.h +++ b/include/linux/timer.h @@ -168,6 +168,20 @@ static inline void init_timer_on_stack_key(struct timer_list *timer, #define setup_pinned_deferrable_timer_on_stack(timer, fn, data) \ __setup_timer_on_stack((timer), (fn), (data), TIMER_DEFERRABLE | TIMER_PINNED) +#define TIMER_DATA_TYPE unsigned long +#define TIMER_FUNC_TYPE void (*)(TIMER_DATA_TYPE) + +static inline void timer_setup(struct timer_list *timer, + void (*callback)(struct timer_list *), + unsigned int flags) +{ + __setup_timer(timer, (TIMER_FUNC_TYPE)callback, + (TIMER_DATA_TYPE)timer, flags); +} + +#define from_timer(var, callback_timer, timer_fieldname) \ + container_of(callback_timer, typeof(*var), timer_fieldname) + /** * timer_pending - is a timer pending? * @timer: the timer in question diff --git a/include/net/netlink.h b/include/net/netlink.h index e51cf5f81597..14c289393071 100644 --- a/include/net/netlink.h +++ b/include/net/netlink.h @@ -773,7 +773,10 @@ static inline int nla_parse_nested(struct nlattr *tb[], int maxtype, */ static inline int nla_put_u8(struct sk_buff *skb, int attrtype, u8 value) { - return nla_put(skb, attrtype, sizeof(u8), &value); + /* temporary variables to work around GCC PR81715 with asan-stack=1 */ + u8 tmp = value; + + return nla_put(skb, attrtype, sizeof(u8), &tmp); } /** @@ -784,7 +787,9 @@ static inline int nla_put_u8(struct sk_buff *skb, int attrtype, u8 value) */ static inline int nla_put_u16(struct sk_buff *skb, int attrtype, u16 value) { - return nla_put(skb, attrtype, sizeof(u16), &value); + u16 tmp = value; + + return nla_put(skb, attrtype, sizeof(u16), &tmp); } /** @@ -795,7 +800,9 @@ static inline int nla_put_u16(struct sk_buff *skb, int attrtype, u16 value) */ static inline int nla_put_be16(struct sk_buff *skb, int attrtype, __be16 value) { - return nla_put(skb, attrtype, sizeof(__be16), &value); + __be16 tmp = value; + + return nla_put(skb, attrtype, sizeof(__be16), &tmp); } /** @@ -806,7 +813,9 @@ static inline int nla_put_be16(struct sk_buff *skb, int attrtype, __be16 value) */ static inline int nla_put_net16(struct sk_buff *skb, int attrtype, __be16 value) { - return nla_put_be16(skb, attrtype | NLA_F_NET_BYTEORDER, value); + __be16 tmp = value; + + return nla_put_be16(skb, attrtype | NLA_F_NET_BYTEORDER, tmp); } /** @@ -817,7 +826,9 @@ static inline int nla_put_net16(struct sk_buff *skb, int attrtype, __be16 value) */ static inline int nla_put_le16(struct sk_buff *skb, int attrtype, __le16 value) { - return nla_put(skb, attrtype, sizeof(__le16), &value); + __le16 tmp = value; + + return nla_put(skb, attrtype, sizeof(__le16), &tmp); } /** @@ -828,7 +839,9 @@ static inline int nla_put_le16(struct sk_buff *skb, int attrtype, __le16 value) */ static inline int nla_put_u32(struct sk_buff *skb, int attrtype, u32 value) { - return nla_put(skb, attrtype, sizeof(u32), &value); + u32 tmp = value; + + return nla_put(skb, attrtype, sizeof(u32), &tmp); } /** @@ -839,7 +852,9 @@ static inline int nla_put_u32(struct sk_buff *skb, int attrtype, u32 value) */ static inline int nla_put_be32(struct sk_buff *skb, int attrtype, __be32 value) { - return nla_put(skb, attrtype, sizeof(__be32), &value); + __be32 tmp = value; + + return nla_put(skb, attrtype, sizeof(__be32), &tmp); } /** @@ -850,7 +865,9 @@ static inline int nla_put_be32(struct sk_buff *skb, int attrtype, __be32 value) */ static inline int nla_put_net32(struct sk_buff *skb, int attrtype, __be32 value) { - return nla_put_be32(skb, attrtype | NLA_F_NET_BYTEORDER, value); + __be32 tmp = value; + + return nla_put_be32(skb, attrtype | NLA_F_NET_BYTEORDER, tmp); } /** @@ -861,7 +878,9 @@ static inline int nla_put_net32(struct sk_buff *skb, int attrtype, __be32 value) */ static inline int nla_put_le32(struct sk_buff *skb, int attrtype, __le32 value) { - return nla_put(skb, attrtype, sizeof(__le32), &value); + __le32 tmp = value; + + return nla_put(skb, attrtype, sizeof(__le32), &tmp); } /** @@ -874,7 +893,9 @@ static inline int nla_put_le32(struct sk_buff *skb, int attrtype, __le32 value) static inline int nla_put_u64_64bit(struct sk_buff *skb, int attrtype, u64 value, int padattr) { - return nla_put_64bit(skb, attrtype, sizeof(u64), &value, padattr); + u64 tmp = value; + + return nla_put_64bit(skb, attrtype, sizeof(u64), &tmp, padattr); } /** @@ -887,7 +908,9 @@ static inline int nla_put_u64_64bit(struct sk_buff *skb, int attrtype, static inline int nla_put_be64(struct sk_buff *skb, int attrtype, __be64 value, int padattr) { - return nla_put_64bit(skb, attrtype, sizeof(__be64), &value, padattr); + __be64 tmp = value; + + return nla_put_64bit(skb, attrtype, sizeof(__be64), &tmp, padattr); } /** @@ -900,7 +923,9 @@ static inline int nla_put_be64(struct sk_buff *skb, int attrtype, __be64 value, static inline int nla_put_net64(struct sk_buff *skb, int attrtype, __be64 value, int padattr) { - return nla_put_be64(skb, attrtype | NLA_F_NET_BYTEORDER, value, + __be64 tmp = value; + + return nla_put_be64(skb, attrtype | NLA_F_NET_BYTEORDER, tmp, padattr); } @@ -914,7 +939,9 @@ static inline int nla_put_net64(struct sk_buff *skb, int attrtype, __be64 value, static inline int nla_put_le64(struct sk_buff *skb, int attrtype, __le64 value, int padattr) { - return nla_put_64bit(skb, attrtype, sizeof(__le64), &value, padattr); + __le64 tmp = value; + + return nla_put_64bit(skb, attrtype, sizeof(__le64), &tmp, padattr); } /** @@ -925,7 +952,9 @@ static inline int nla_put_le64(struct sk_buff *skb, int attrtype, __le64 value, */ static inline int nla_put_s8(struct sk_buff *skb, int attrtype, s8 value) { - return nla_put(skb, attrtype, sizeof(s8), &value); + s8 tmp = value; + + return nla_put(skb, attrtype, sizeof(s8), &tmp); } /** @@ -936,7 +965,9 @@ static inline int nla_put_s8(struct sk_buff *skb, int attrtype, s8 value) */ static inline int nla_put_s16(struct sk_buff *skb, int attrtype, s16 value) { - return nla_put(skb, attrtype, sizeof(s16), &value); + s16 tmp = value; + + return nla_put(skb, attrtype, sizeof(s16), &tmp); } /** @@ -947,7 +978,9 @@ static inline int nla_put_s16(struct sk_buff *skb, int attrtype, s16 value) */ static inline int nla_put_s32(struct sk_buff *skb, int attrtype, s32 value) { - return nla_put(skb, attrtype, sizeof(s32), &value); + s32 tmp = value; + + return nla_put(skb, attrtype, sizeof(s32), &tmp); } /** @@ -960,7 +993,9 @@ static inline int nla_put_s32(struct sk_buff *skb, int attrtype, s32 value) static inline int nla_put_s64(struct sk_buff *skb, int attrtype, s64 value, int padattr) { - return nla_put_64bit(skb, attrtype, sizeof(s64), &value, padattr); + s64 tmp = value; + + return nla_put_64bit(skb, attrtype, sizeof(s64), &tmp, padattr); } /** @@ -1010,7 +1045,9 @@ static inline int nla_put_msecs(struct sk_buff *skb, int attrtype, static inline int nla_put_in_addr(struct sk_buff *skb, int attrtype, __be32 addr) { - return nla_put_be32(skb, attrtype, addr); + __be32 tmp = addr; + + return nla_put_be32(skb, attrtype, tmp); } /** diff --git a/include/net/protocol.h b/include/net/protocol.h index 65ba335b0e7e..4fc75f7ae23b 100644 --- a/include/net/protocol.h +++ b/include/net/protocol.h @@ -39,8 +39,8 @@ /* This is used to register protocols. */ struct net_protocol { - void (*early_demux)(struct sk_buff *skb); - void (*early_demux_handler)(struct sk_buff *skb); + int (*early_demux)(struct sk_buff *skb); + int (*early_demux_handler)(struct sk_buff *skb); int (*handler)(struct sk_buff *skb); void (*err_handler)(struct sk_buff *skb, u32 info); unsigned int no_policy:1, diff --git a/include/net/route.h b/include/net/route.h index 57dfc6850d37..d538e6db1afe 100644 --- a/include/net/route.h +++ b/include/net/route.h @@ -175,7 +175,9 @@ static inline struct rtable *ip_route_output_gre(struct net *net, struct flowi4 fl4->fl4_gre_key = gre_key; return ip_route_output_key(net, fl4); } - +int ip_mc_validate_source(struct sk_buff *skb, __be32 daddr, __be32 saddr, + u8 tos, struct net_device *dev, + struct in_device *in_dev, u32 *itag); int ip_route_input_noref(struct sk_buff *skb, __be32 dst, __be32 src, u8 tos, struct net_device *devin); int ip_route_input_rcu(struct sk_buff *skb, __be32 dst, __be32 src, diff --git a/include/net/tcp.h b/include/net/tcp.h index 3bc910a9bfc6..89974c5286d8 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -345,7 +345,7 @@ void tcp_v4_err(struct sk_buff *skb, u32); void tcp_shutdown(struct sock *sk, int how); -void tcp_v4_early_demux(struct sk_buff *skb); +int tcp_v4_early_demux(struct sk_buff *skb); int tcp_v4_rcv(struct sk_buff *skb); int tcp_v4_tw_remember_stamp(struct inet_timewait_sock *tw); diff --git a/include/net/udp.h b/include/net/udp.h index 12dfbfe2e2d7..6c759c8594e2 100644 --- a/include/net/udp.h +++ b/include/net/udp.h @@ -259,7 +259,7 @@ static inline struct sk_buff *skb_recv_udp(struct sock *sk, unsigned int flags, return __skb_recv_udp(sk, flags, noblock, &peeked, &off, err); } -void udp_v4_early_demux(struct sk_buff *skb); +int udp_v4_early_demux(struct sk_buff *skb); bool udp_sk_rx_dst_set(struct sock *sk, struct dst_entry *dst); int udp_get_port(struct sock *sk, unsigned short snum, int (*saddr_cmp)(const struct sock *, diff --git a/include/rdma/ib_addr.h b/include/rdma/ib_addr.h index ec5008cf5d51..b2a10c762304 100644 --- a/include/rdma/ib_addr.h +++ b/include/rdma/ib_addr.h @@ -245,10 +245,11 @@ static inline void rdma_addr_set_dgid(struct rdma_dev_addr *dev_addr, union ib_g static inline enum ib_mtu iboe_get_mtu(int mtu) { /* - * reduce IB headers from effective IBoE MTU. 28 stands for - * atomic header which is the biggest possible header after BTH + * Reduce IB headers from effective IBoE MTU. */ - mtu = mtu - IB_GRH_BYTES - IB_BTH_BYTES - 28; + mtu = mtu - (IB_GRH_BYTES + IB_UDP_BYTES + IB_BTH_BYTES + + IB_EXT_XRC_BYTES + IB_EXT_ATOMICETH_BYTES + + IB_ICRC_BYTES); if (mtu >= ib_mtu_enum_to_int(IB_MTU_4096)) return IB_MTU_4096; @@ -305,12 +306,12 @@ static inline void rdma_get_ll_mac(struct in6_addr *addr, u8 *mac) static inline int rdma_is_multicast_addr(struct in6_addr *addr) { - u32 ipv4_addr; + __be32 ipv4_addr; if (addr->s6_addr[0] == 0xff) return 1; - memcpy(&ipv4_addr, addr->s6_addr + 12, 4); + ipv4_addr = addr->s6_addr32[3]; return (ipv6_addr_v4mapped(addr) && ipv4_is_multicast(ipv4_addr)); } diff --git a/include/rdma/ib_pack.h b/include/rdma/ib_pack.h index 36655899ee02..7ea1382ad0e5 100644 --- a/include/rdma/ib_pack.h +++ b/include/rdma/ib_pack.h @@ -37,14 +37,17 @@ #include <uapi/linux/if_ether.h> enum { - IB_LRH_BYTES = 8, - IB_ETH_BYTES = 14, - IB_VLAN_BYTES = 4, - IB_GRH_BYTES = 40, - IB_IP4_BYTES = 20, - IB_UDP_BYTES = 8, - IB_BTH_BYTES = 12, - IB_DETH_BYTES = 8 + IB_LRH_BYTES = 8, + IB_ETH_BYTES = 14, + IB_VLAN_BYTES = 4, + IB_GRH_BYTES = 40, + IB_IP4_BYTES = 20, + IB_UDP_BYTES = 8, + IB_BTH_BYTES = 12, + IB_DETH_BYTES = 8, + IB_EXT_ATOMICETH_BYTES = 28, + IB_EXT_XRC_BYTES = 4, + IB_ICRC_BYTES = 4 }; struct ib_field { diff --git a/include/rdma/ib_sa.h b/include/rdma/ib_sa.h index 355b81f4242d..1f7f604db5aa 100644 --- a/include/rdma/ib_sa.h +++ b/include/rdma/ib_sa.h @@ -590,20 +590,20 @@ static inline bool sa_path_is_roce(struct sa_path_rec *rec) (rec->rec_type == SA_PATH_REC_TYPE_ROCE_V2)); } -static inline void sa_path_set_slid(struct sa_path_rec *rec, __be32 slid) +static inline void sa_path_set_slid(struct sa_path_rec *rec, u32 slid) { if (rec->rec_type == SA_PATH_REC_TYPE_IB) - rec->ib.slid = htons(ntohl(slid)); + rec->ib.slid = cpu_to_be16(slid); else if (rec->rec_type == SA_PATH_REC_TYPE_OPA) - rec->opa.slid = slid; + rec->opa.slid = cpu_to_be32(slid); } -static inline void sa_path_set_dlid(struct sa_path_rec *rec, __be32 dlid) +static inline void sa_path_set_dlid(struct sa_path_rec *rec, u32 dlid) { if (rec->rec_type == SA_PATH_REC_TYPE_IB) - rec->ib.dlid = htons(ntohl(dlid)); + rec->ib.dlid = cpu_to_be16(dlid); else if (rec->rec_type == SA_PATH_REC_TYPE_OPA) - rec->opa.dlid = dlid; + rec->opa.dlid = cpu_to_be32(dlid); } static inline void sa_path_set_raw_traffic(struct sa_path_rec *rec, diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h index e8608b2dc844..9810e4568635 100644 --- a/include/rdma/ib_verbs.h +++ b/include/rdma/ib_verbs.h @@ -2858,6 +2858,21 @@ void ib_dealloc_pd(struct ib_pd *pd); struct ib_ah *rdma_create_ah(struct ib_pd *pd, struct rdma_ah_attr *ah_attr); /** + * rdma_create_user_ah - Creates an address handle for the given address vector. + * It resolves destination mac address for ah attribute of RoCE type. + * @pd: The protection domain associated with the address handle. + * @ah_attr: The attributes of the address vector. + * @udata: pointer to user's input output buffer information need by + * provider driver. + * + * It returns 0 on success and returns appropriate error code on error. + * The address handle is used to reference a local or global destination + * in all UD QP post sends. + */ +struct ib_ah *rdma_create_user_ah(struct ib_pd *pd, + struct rdma_ah_attr *ah_attr, + struct ib_udata *udata); +/** * ib_get_gids_from_rdma_hdr - Get sgid and dgid from GRH or IPv4 header * work completion. * @hdr: the L3 header to parse @@ -3607,8 +3622,6 @@ void ib_drain_rq(struct ib_qp *qp); void ib_drain_sq(struct ib_qp *qp); void ib_drain_qp(struct ib_qp *qp); -int ib_resolve_eth_dmac(struct ib_device *device, - struct rdma_ah_attr *ah_attr); int ib_get_eth_speed(struct ib_device *dev, u8 port_num, u8 *speed, u8 *width); static inline u8 *rdma_ah_retrieve_dmac(struct rdma_ah_attr *attr) diff --git a/include/rdma/opa_addr.h b/include/rdma/opa_addr.h index e6e90f18e6d5..f68fca296631 100644 --- a/include/rdma/opa_addr.h +++ b/include/rdma/opa_addr.h @@ -97,15 +97,15 @@ static inline u32 opa_get_lid_from_gid(const union ib_gid *gid) * @dlid: The DLID * @slid: The SLID */ -static inline bool opa_is_extended_lid(u32 dlid, u32 slid) +static inline bool opa_is_extended_lid(__be32 dlid, __be32 slid) { if ((be32_to_cpu(dlid) >= be16_to_cpu(IB_MULTICAST_LID_BASE)) || (be32_to_cpu(slid) >= be16_to_cpu(IB_MULTICAST_LID_BASE))) return true; - else - return false; + + return false; } /* Get multicast lid base */ diff --git a/include/rdma/rdmavt_qp.h b/include/rdma/rdmavt_qp.h index 0eed3d8752fa..89ab88c342b6 100644 --- a/include/rdma/rdmavt_qp.h +++ b/include/rdma/rdmavt_qp.h @@ -282,7 +282,6 @@ struct rvt_qp { u32 remote_qpn; u32 qkey; /* QKEY for this QP (for UD or RD) */ u32 s_size; /* send work queue size */ - u32 s_ahgpsn; /* set to the psn in the copy of the header */ u16 pmtu; /* decoded from path_mtu */ u8 log_pmtu; /* shift for pmtu */ @@ -344,7 +343,6 @@ struct rvt_qp { struct rvt_swqe *s_wqe; struct rvt_sge_state s_sge; /* current send request data */ struct rvt_mregion *s_rdma_mr; - u32 s_cur_size; /* size of send packet in bytes */ u32 s_len; /* total length of s_sge */ u32 s_rdma_read_len; /* total length of s_rdma_read_sge */ u32 s_last_psn; /* last response PSN processed */ @@ -358,8 +356,10 @@ struct rvt_qp { u32 s_acked; /* last un-ACK'ed entry */ u32 s_last; /* last completed entry */ u32 s_lsn; /* limit sequence number (credit) */ - u16 s_hdrwords; /* size of s_hdr in 32 bit words */ + u32 s_ahgpsn; /* set to the psn in the copy of the header */ + u16 s_cur_size; /* size of send packet in bytes */ u16 s_rdma_ack_cnt; + u8 s_hdrwords; /* size of s_hdr in 32 bit words */ s8 s_ahgidx; u8 s_state; /* opcode of last packet sent */ u8 s_ack_state; /* opcode of packet to ACK */ diff --git a/include/scsi/scsi_device.h b/include/scsi/scsi_device.h index 82e93ee94708..67c5a9f223f7 100644 --- a/include/scsi/scsi_device.h +++ b/include/scsi/scsi_device.h @@ -192,6 +192,7 @@ struct scsi_device { unsigned no_dif:1; /* T10 PI (DIF) should be disabled */ unsigned broken_fua:1; /* Don't set FUA bit */ unsigned lun_in_cdb:1; /* Store LUN bits in CDB[1] */ + unsigned unmap_limit_for_ws:1; /* Use the UNMAP limit for WRITE SAME */ atomic_t disk_events_disable_depth; /* disable depth for disk events */ diff --git a/include/scsi/scsi_devinfo.h b/include/scsi/scsi_devinfo.h index 9592570e092a..36b03013d629 100644 --- a/include/scsi/scsi_devinfo.h +++ b/include/scsi/scsi_devinfo.h @@ -29,5 +29,6 @@ #define BLIST_TRY_VPD_PAGES 0x10000000 /* Attempt to read VPD pages */ #define BLIST_NO_RSOC 0x20000000 /* don't try to issue RSOC */ #define BLIST_MAX_1024 0x40000000 /* maximum 1024 sector cdb length */ +#define BLIST_UNMAP_LIMIT_WS 0x80000000 /* Use UNMAP limit for WRITE SAME */ #endif diff --git a/include/scsi/scsi_transport_iscsi.h b/include/scsi/scsi_transport_iscsi.h index 6183d20a01fb..b266d2a3bcb1 100644 --- a/include/scsi/scsi_transport_iscsi.h +++ b/include/scsi/scsi_transport_iscsi.h @@ -434,7 +434,6 @@ extern struct iscsi_cls_session *iscsi_create_session(struct Scsi_Host *shost, unsigned int target_id); extern void iscsi_remove_session(struct iscsi_cls_session *session); extern void iscsi_free_session(struct iscsi_cls_session *session); -extern int iscsi_destroy_session(struct iscsi_cls_session *session); extern struct iscsi_cls_conn *iscsi_create_conn(struct iscsi_cls_session *sess, int dd_size, uint32_t cid); extern int iscsi_destroy_conn(struct iscsi_cls_conn *conn); diff --git a/include/sound/hda_verbs.h b/include/sound/hda_verbs.h index d0509db6d0ec..f89cd5ee1c7a 100644 --- a/include/sound/hda_verbs.h +++ b/include/sound/hda_verbs.h @@ -95,6 +95,7 @@ enum { #define AC_VERB_SET_EAPD_BTLENABLE 0x70c #define AC_VERB_SET_DIGI_CONVERT_1 0x70d #define AC_VERB_SET_DIGI_CONVERT_2 0x70e +#define AC_VERB_SET_DIGI_CONVERT_3 0x73e #define AC_VERB_SET_VOLUME_KNOB_CONTROL 0x70f #define AC_VERB_SET_GPIO_DATA 0x715 #define AC_VERB_SET_GPIO_MASK 0x716 diff --git a/include/trace/events/sched.h b/include/trace/events/sched.h index ae1409ffe99a..3c8b7f625670 100644 --- a/include/trace/events/sched.h +++ b/include/trace/events/sched.h @@ -114,7 +114,10 @@ static inline long __trace_sched_switch_state(bool preempt, struct task_struct * * Preemption ignores task state, therefore preempted tasks are always * RUNNING (we will not have dequeued if state != RUNNING). */ - return preempt ? TASK_RUNNING | TASK_STATE_MAX : p->state; + if (preempt) + return TASK_STATE_MAX; + + return __get_task_state(p); } #endif /* CREATE_TRACE_POINTS */ @@ -152,12 +155,14 @@ TRACE_EVENT(sched_switch, TP_printk("prev_comm=%s prev_pid=%d prev_prio=%d prev_state=%s%s ==> next_comm=%s next_pid=%d next_prio=%d", __entry->prev_comm, __entry->prev_pid, __entry->prev_prio, - __entry->prev_state & (TASK_STATE_MAX-1) ? - __print_flags(__entry->prev_state & (TASK_STATE_MAX-1), "|", - { 1, "S"} , { 2, "D" }, { 4, "T" }, { 8, "t" }, - { 16, "Z" }, { 32, "X" }, { 64, "x" }, - { 128, "K" }, { 256, "W" }, { 512, "P" }, - { 1024, "N" }) : "R", + + (__entry->prev_state & (TASK_REPORT_MAX - 1)) ? + __print_flags(__entry->prev_state & (TASK_REPORT_MAX - 1), "|", + { 0x01, "S" }, { 0x02, "D" }, { 0x04, "T" }, + { 0x08, "t" }, { 0x10, "X" }, { 0x20, "Z" }, + { 0x40, "P" }, { 0x80, "I" }) : + "R", + __entry->prev_state & TASK_STATE_MAX ? "+" : "", __entry->next_comm, __entry->next_pid, __entry->next_prio) ); diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 43ab5c402f98..f90860d1f897 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -312,7 +312,7 @@ union bpf_attr { * jump into another BPF program * @ctx: context pointer passed to next program * @prog_array_map: pointer to map which type is BPF_MAP_TYPE_PROG_ARRAY - * @index: index inside array that selects specific program to run + * @index: 32-bit index inside array that selects specific program to run * Return: 0 on success or negative error * * int bpf_clone_redirect(skb, ifindex, flags) diff --git a/include/uapi/linux/dm-ioctl.h b/include/uapi/linux/dm-ioctl.h index 412c06a624c8..ccaea525340b 100644 --- a/include/uapi/linux/dm-ioctl.h +++ b/include/uapi/linux/dm-ioctl.h @@ -269,9 +269,9 @@ enum { #define DM_DEV_SET_GEOMETRY _IOWR(DM_IOCTL, DM_DEV_SET_GEOMETRY_CMD, struct dm_ioctl) #define DM_VERSION_MAJOR 4 -#define DM_VERSION_MINOR 36 +#define DM_VERSION_MINOR 37 #define DM_VERSION_PATCHLEVEL 0 -#define DM_VERSION_EXTRA "-ioctl (2017-06-09)" +#define DM_VERSION_EXTRA "-ioctl (2017-09-20)" /* Status bits */ #define DM_READONLY_FLAG (1 << 0) /* In/Out */ diff --git a/include/uapi/linux/usb/ch9.h b/include/uapi/linux/usb/ch9.h index ce1169af39d7..2a5d63040a0b 100644 --- a/include/uapi/linux/usb/ch9.h +++ b/include/uapi/linux/usb/ch9.h @@ -780,6 +780,7 @@ struct usb_interface_assoc_descriptor { __u8 iFunction; } __attribute__ ((packed)); +#define USB_DT_INTERFACE_ASSOCIATION_SIZE 8 /*-------------------------------------------------------------------------*/ diff --git a/include/uapi/rdma/mlx5-abi.h b/include/uapi/rdma/mlx5-abi.h index 1791bf123ba9..442b46b74a3a 100644 --- a/include/uapi/rdma/mlx5-abi.h +++ b/include/uapi/rdma/mlx5-abi.h @@ -39,6 +39,7 @@ enum { MLX5_QP_FLAG_SIGNATURE = 1 << 0, MLX5_QP_FLAG_SCATTER_CQE = 1 << 1, + MLX5_QP_FLAG_TUNNEL_OFFLOADS = 1 << 2, }; enum { @@ -190,6 +191,31 @@ struct mlx5_ib_sw_parsing_caps { __u32 supported_qpts; }; +struct mlx5_ib_striding_rq_caps { + __u32 min_single_stride_log_num_of_bytes; + __u32 max_single_stride_log_num_of_bytes; + __u32 min_single_wqe_log_num_of_strides; + __u32 max_single_wqe_log_num_of_strides; + + /* Corresponding bit will be set if qp type from + * 'enum ib_qp_type' is supported, e.g. + * supported_qpts |= 1 << IB_QPT_RAW_PACKET + */ + __u32 supported_qpts; +}; + +enum mlx5_ib_query_dev_resp_flags { + /* Support 128B CQE compression */ + MLX5_IB_QUERY_DEV_RESP_FLAGS_CQE_128B_COMP = 1 << 0, + MLX5_IB_QUERY_DEV_RESP_FLAGS_CQE_128B_PAD = 1 << 1, +}; + +enum mlx5_ib_tunnel_offloads { + MLX5_IB_TUNNELED_OFFLOADS_VXLAN = 1 << 0, + MLX5_IB_TUNNELED_OFFLOADS_GRE = 1 << 1, + MLX5_IB_TUNNELED_OFFLOADS_GENEVE = 1 << 2 +}; + struct mlx5_ib_query_device_resp { __u32 comp_mask; __u32 response_length; @@ -198,8 +224,15 @@ struct mlx5_ib_query_device_resp { struct mlx5_ib_cqe_comp_caps cqe_comp_caps; struct mlx5_packet_pacing_caps packet_pacing_caps; __u32 mlx5_ib_support_multi_pkt_send_wqes; - __u32 reserved; + __u32 flags; /* Use enum mlx5_ib_query_dev_resp_flags */ struct mlx5_ib_sw_parsing_caps sw_parsing_caps; + struct mlx5_ib_striding_rq_caps striding_rq_caps; + __u32 tunnel_offloads_caps; /* enum mlx5_ib_tunnel_offloads */ + __u32 reserved; +}; + +enum mlx5_ib_create_cq_flags { + MLX5_IB_CREATE_CQ_FLAGS_CQE_128B_PAD = 1 << 0, }; struct mlx5_ib_create_cq { @@ -208,7 +241,7 @@ struct mlx5_ib_create_cq { __u32 cqe_size; __u8 cqe_comp_en; __u8 cqe_comp_res_format; - __u16 reserved; /* explicit padding (optional on i386) */ + __u16 flags; }; struct mlx5_ib_create_cq_resp { @@ -270,7 +303,9 @@ enum mlx5_rx_hash_fields { MLX5_RX_HASH_SRC_PORT_TCP = 1 << 4, MLX5_RX_HASH_DST_PORT_TCP = 1 << 5, MLX5_RX_HASH_SRC_PORT_UDP = 1 << 6, - MLX5_RX_HASH_DST_PORT_UDP = 1 << 7 + MLX5_RX_HASH_DST_PORT_UDP = 1 << 7, + /* Save bits for future fields */ + MLX5_RX_HASH_INNER = 1 << 31 }; struct mlx5_ib_create_qp_rss { @@ -280,7 +315,7 @@ struct mlx5_ib_create_qp_rss { __u8 reserved[6]; __u8 rx_hash_key[128]; /* valid only for Toeplitz */ __u32 comp_mask; - __u32 reserved1; + __u32 flags; }; struct mlx5_ib_create_qp_resp { @@ -294,6 +329,10 @@ struct mlx5_ib_alloc_mw { __u16 reserved2; }; +enum mlx5_ib_create_wq_mask { + MLX5_IB_CREATE_WQ_STRIDING_RQ = (1 << 0), +}; + struct mlx5_ib_create_wq { __u64 buf_addr; __u64 db_addr; @@ -302,7 +341,9 @@ struct mlx5_ib_create_wq { __u32 user_index; __u32 flags; __u32 comp_mask; - __u32 reserved; + __u32 single_stride_log_num_of_bytes; + __u32 single_wqe_log_num_of_strides; + __u32 two_byte_shift_en; }; struct mlx5_ib_create_ah_resp { diff --git a/ipc/shm.c b/ipc/shm.c index 1e2b1692ba2c..badac463e2c8 100644 --- a/ipc/shm.c +++ b/ipc/shm.c @@ -1154,7 +1154,7 @@ static int put_compat_shm_info(struct shm_info *ip, info.shm_swp = ip->shm_swp; info.swap_attempts = ip->swap_attempts; info.swap_successes = ip->swap_successes; - return copy_to_user(up, &info, sizeof(info)); + return copy_to_user(uip, &info, sizeof(info)); } static int copy_compat_shmid_to_user(void __user *buf, struct shmid64_ds *in, diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index 917cc04a0a94..7b62df86be1d 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -1022,7 +1022,7 @@ select_insn: struct bpf_map *map = (struct bpf_map *) (unsigned long) BPF_R2; struct bpf_array *array = container_of(map, struct bpf_array, map); struct bpf_prog *prog; - u64 index = BPF_R3; + u32 index = BPF_R3; if (unlikely(index >= array->map.max_entries)) goto out; diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index d6551cd45238..44857278eb8a 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -2311,6 +2311,14 @@ out_release_tset: list_del_init(&cset->mg_node); } spin_unlock_irq(&css_set_lock); + + /* + * Re-initialize the cgroup_taskset structure in case it is reused + * again in another cgroup_migrate_add_task()/cgroup_migrate_execute() + * iteration. + */ + tset->nr_tasks = 0; + tset->csets = &tset->src_csets; return ret; } diff --git a/kernel/cpu.c b/kernel/cpu.c index acf5308fad51..d851df22f5c5 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -24,6 +24,7 @@ #include <linux/lockdep.h> #include <linux/tick.h> #include <linux/irq.h> +#include <linux/nmi.h> #include <linux/smpboot.h> #include <linux/relay.h> #include <linux/slab.h> @@ -46,11 +47,13 @@ * @bringup: Single callback bringup or teardown selector * @cb_state: The state for a single callback (install/uninstall) * @result: Result of the operation - * @done: Signal completion to the issuer of the task + * @done_up: Signal completion to the issuer of the task for cpu-up + * @done_down: Signal completion to the issuer of the task for cpu-down */ struct cpuhp_cpu_state { enum cpuhp_state state; enum cpuhp_state target; + enum cpuhp_state fail; #ifdef CONFIG_SMP struct task_struct *thread; bool should_run; @@ -58,18 +61,39 @@ struct cpuhp_cpu_state { bool single; bool bringup; struct hlist_node *node; + struct hlist_node *last; enum cpuhp_state cb_state; int result; - struct completion done; + struct completion done_up; + struct completion done_down; #endif }; -static DEFINE_PER_CPU(struct cpuhp_cpu_state, cpuhp_state); +static DEFINE_PER_CPU(struct cpuhp_cpu_state, cpuhp_state) = { + .fail = CPUHP_INVALID, +}; #if defined(CONFIG_LOCKDEP) && defined(CONFIG_SMP) -static struct lock_class_key cpuhp_state_key; -static struct lockdep_map cpuhp_state_lock_map = - STATIC_LOCKDEP_MAP_INIT("cpuhp_state", &cpuhp_state_key); +static struct lockdep_map cpuhp_state_up_map = + STATIC_LOCKDEP_MAP_INIT("cpuhp_state-up", &cpuhp_state_up_map); +static struct lockdep_map cpuhp_state_down_map = + STATIC_LOCKDEP_MAP_INIT("cpuhp_state-down", &cpuhp_state_down_map); + + +static void inline cpuhp_lock_acquire(bool bringup) +{ + lock_map_acquire(bringup ? &cpuhp_state_up_map : &cpuhp_state_down_map); +} + +static void inline cpuhp_lock_release(bool bringup) +{ + lock_map_release(bringup ? &cpuhp_state_up_map : &cpuhp_state_down_map); +} +#else + +static void inline cpuhp_lock_acquire(bool bringup) { } +static void inline cpuhp_lock_release(bool bringup) { } + #endif /** @@ -123,13 +147,16 @@ static struct cpuhp_step *cpuhp_get_step(enum cpuhp_state state) /** * cpuhp_invoke_callback _ Invoke the callbacks for a given state * @cpu: The cpu for which the callback should be invoked - * @step: The step in the state machine + * @state: The state to do callbacks for * @bringup: True if the bringup callback should be invoked + * @node: For multi-instance, do a single entry callback for install/remove + * @lastp: For multi-instance rollback, remember how far we got * * Called from cpu hotplug and from the state register machinery. */ static int cpuhp_invoke_callback(unsigned int cpu, enum cpuhp_state state, - bool bringup, struct hlist_node *node) + bool bringup, struct hlist_node *node, + struct hlist_node **lastp) { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); struct cpuhp_step *step = cpuhp_get_step(state); @@ -137,7 +164,17 @@ static int cpuhp_invoke_callback(unsigned int cpu, enum cpuhp_state state, int (*cb)(unsigned int cpu); int ret, cnt; + if (st->fail == state) { + st->fail = CPUHP_INVALID; + + if (!(bringup ? step->startup.single : step->teardown.single)) + return 0; + + return -EAGAIN; + } + if (!step->multi_instance) { + WARN_ON_ONCE(lastp && *lastp); cb = bringup ? step->startup.single : step->teardown.single; if (!cb) return 0; @@ -152,6 +189,7 @@ static int cpuhp_invoke_callback(unsigned int cpu, enum cpuhp_state state, /* Single invocation for instance add/remove */ if (node) { + WARN_ON_ONCE(lastp && *lastp); trace_cpuhp_multi_enter(cpu, st->target, state, cbm, node); ret = cbm(cpu, node); trace_cpuhp_exit(cpu, st->state, state, ret); @@ -161,13 +199,23 @@ static int cpuhp_invoke_callback(unsigned int cpu, enum cpuhp_state state, /* State transition. Invoke on all instances */ cnt = 0; hlist_for_each(node, &step->list) { + if (lastp && node == *lastp) + break; + trace_cpuhp_multi_enter(cpu, st->target, state, cbm, node); ret = cbm(cpu, node); trace_cpuhp_exit(cpu, st->state, state, ret); - if (ret) - goto err; + if (ret) { + if (!lastp) + goto err; + + *lastp = node; + return ret; + } cnt++; } + if (lastp) + *lastp = NULL; return 0; err: /* Rollback the instances if one failed */ @@ -178,12 +226,39 @@ err: hlist_for_each(node, &step->list) { if (!cnt--) break; - cbm(cpu, node); + + trace_cpuhp_multi_enter(cpu, st->target, state, cbm, node); + ret = cbm(cpu, node); + trace_cpuhp_exit(cpu, st->state, state, ret); + /* + * Rollback must not fail, + */ + WARN_ON_ONCE(ret); } return ret; } #ifdef CONFIG_SMP +static inline void wait_for_ap_thread(struct cpuhp_cpu_state *st, bool bringup) +{ + struct completion *done = bringup ? &st->done_up : &st->done_down; + wait_for_completion(done); +} + +static inline void complete_ap_thread(struct cpuhp_cpu_state *st, bool bringup) +{ + struct completion *done = bringup ? &st->done_up : &st->done_down; + complete(done); +} + +/* + * The former STARTING/DYING states, ran with IRQs disabled and must not fail. + */ +static bool cpuhp_is_atomic_state(enum cpuhp_state state) +{ + return CPUHP_AP_IDLE_DEAD <= state && state < CPUHP_AP_ONLINE; +} + /* Serializes the updates to cpu_online_mask, cpu_present_mask */ static DEFINE_MUTEX(cpu_add_remove_lock); bool cpuhp_tasks_frozen; @@ -271,14 +346,79 @@ void cpu_hotplug_enable(void) EXPORT_SYMBOL_GPL(cpu_hotplug_enable); #endif /* CONFIG_HOTPLUG_CPU */ -static void __cpuhp_kick_ap_work(struct cpuhp_cpu_state *st); +static inline enum cpuhp_state +cpuhp_set_state(struct cpuhp_cpu_state *st, enum cpuhp_state target) +{ + enum cpuhp_state prev_state = st->state; + + st->rollback = false; + st->last = NULL; + + st->target = target; + st->single = false; + st->bringup = st->state < target; + + return prev_state; +} + +static inline void +cpuhp_reset_state(struct cpuhp_cpu_state *st, enum cpuhp_state prev_state) +{ + st->rollback = true; + + /* + * If we have st->last we need to undo partial multi_instance of this + * state first. Otherwise start undo at the previous state. + */ + if (!st->last) { + if (st->bringup) + st->state--; + else + st->state++; + } + + st->target = prev_state; + st->bringup = !st->bringup; +} + +/* Regular hotplug invocation of the AP hotplug thread */ +static void __cpuhp_kick_ap(struct cpuhp_cpu_state *st) +{ + if (!st->single && st->state == st->target) + return; + + st->result = 0; + /* + * Make sure the above stores are visible before should_run becomes + * true. Paired with the mb() above in cpuhp_thread_fun() + */ + smp_mb(); + st->should_run = true; + wake_up_process(st->thread); + wait_for_ap_thread(st, st->bringup); +} + +static int cpuhp_kick_ap(struct cpuhp_cpu_state *st, enum cpuhp_state target) +{ + enum cpuhp_state prev_state; + int ret; + + prev_state = cpuhp_set_state(st, target); + __cpuhp_kick_ap(st); + if ((ret = st->result)) { + cpuhp_reset_state(st, prev_state); + __cpuhp_kick_ap(st); + } + + return ret; +} static int bringup_wait_for_ap(unsigned int cpu) { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); /* Wait for the CPU to reach CPUHP_AP_ONLINE_IDLE */ - wait_for_completion(&st->done); + wait_for_ap_thread(st, true); if (WARN_ON_ONCE((!cpu_online(cpu)))) return -ECANCELED; @@ -286,12 +426,10 @@ static int bringup_wait_for_ap(unsigned int cpu) stop_machine_unpark(cpu); kthread_unpark(st->thread); - /* Should we go further up ? */ - if (st->target > CPUHP_AP_ONLINE_IDLE) { - __cpuhp_kick_ap_work(st); - wait_for_completion(&st->done); - } - return st->result; + if (st->target <= CPUHP_AP_ONLINE_IDLE) + return 0; + + return cpuhp_kick_ap(st, st->target); } static int bringup_cpu(unsigned int cpu) @@ -317,32 +455,6 @@ static int bringup_cpu(unsigned int cpu) /* * Hotplug state machine related functions */ -static void undo_cpu_down(unsigned int cpu, struct cpuhp_cpu_state *st) -{ - for (st->state++; st->state < st->target; st->state++) { - struct cpuhp_step *step = cpuhp_get_step(st->state); - - if (!step->skip_onerr) - cpuhp_invoke_callback(cpu, st->state, true, NULL); - } -} - -static int cpuhp_down_callbacks(unsigned int cpu, struct cpuhp_cpu_state *st, - enum cpuhp_state target) -{ - enum cpuhp_state prev_state = st->state; - int ret = 0; - - for (; st->state > target; st->state--) { - ret = cpuhp_invoke_callback(cpu, st->state, false, NULL); - if (ret) { - st->target = prev_state; - undo_cpu_down(cpu, st); - break; - } - } - return ret; -} static void undo_cpu_up(unsigned int cpu, struct cpuhp_cpu_state *st) { @@ -350,7 +462,7 @@ static void undo_cpu_up(unsigned int cpu, struct cpuhp_cpu_state *st) struct cpuhp_step *step = cpuhp_get_step(st->state); if (!step->skip_onerr) - cpuhp_invoke_callback(cpu, st->state, false, NULL); + cpuhp_invoke_callback(cpu, st->state, false, NULL, NULL); } } @@ -362,7 +474,7 @@ static int cpuhp_up_callbacks(unsigned int cpu, struct cpuhp_cpu_state *st, while (st->state < target) { st->state++; - ret = cpuhp_invoke_callback(cpu, st->state, true, NULL); + ret = cpuhp_invoke_callback(cpu, st->state, true, NULL, NULL); if (ret) { st->target = prev_state; undo_cpu_up(cpu, st); @@ -379,7 +491,8 @@ static void cpuhp_create(unsigned int cpu) { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); - init_completion(&st->done); + init_completion(&st->done_up); + init_completion(&st->done_down); } static int cpuhp_should_run(unsigned int cpu) @@ -389,69 +502,90 @@ static int cpuhp_should_run(unsigned int cpu) return st->should_run; } -/* Execute the teardown callbacks. Used to be CPU_DOWN_PREPARE */ -static int cpuhp_ap_offline(unsigned int cpu, struct cpuhp_cpu_state *st) -{ - enum cpuhp_state target = max((int)st->target, CPUHP_TEARDOWN_CPU); - - return cpuhp_down_callbacks(cpu, st, target); -} - -/* Execute the online startup callbacks. Used to be CPU_ONLINE */ -static int cpuhp_ap_online(unsigned int cpu, struct cpuhp_cpu_state *st) -{ - return cpuhp_up_callbacks(cpu, st, st->target); -} - /* * Execute teardown/startup callbacks on the plugged cpu. Also used to invoke * callbacks when a state gets [un]installed at runtime. + * + * Each invocation of this function by the smpboot thread does a single AP + * state callback. + * + * It has 3 modes of operation: + * - single: runs st->cb_state + * - up: runs ++st->state, while st->state < st->target + * - down: runs st->state--, while st->state > st->target + * + * When complete or on error, should_run is cleared and the completion is fired. */ static void cpuhp_thread_fun(unsigned int cpu) { struct cpuhp_cpu_state *st = this_cpu_ptr(&cpuhp_state); - int ret = 0; + bool bringup = st->bringup; + enum cpuhp_state state; /* - * Paired with the mb() in cpuhp_kick_ap_work and - * cpuhp_invoke_ap_callback, so the work set is consistent visible. + * ACQUIRE for the cpuhp_should_run() load of ->should_run. Ensures + * that if we see ->should_run we also see the rest of the state. */ smp_mb(); - if (!st->should_run) + + if (WARN_ON_ONCE(!st->should_run)) return; - st->should_run = false; + cpuhp_lock_acquire(bringup); - lock_map_acquire(&cpuhp_state_lock_map); - /* Single callback invocation for [un]install ? */ if (st->single) { - if (st->cb_state < CPUHP_AP_ONLINE) { - local_irq_disable(); - ret = cpuhp_invoke_callback(cpu, st->cb_state, - st->bringup, st->node); - local_irq_enable(); + state = st->cb_state; + st->should_run = false; + } else { + if (bringup) { + st->state++; + state = st->state; + st->should_run = (st->state < st->target); + WARN_ON_ONCE(st->state > st->target); } else { - ret = cpuhp_invoke_callback(cpu, st->cb_state, - st->bringup, st->node); + state = st->state; + st->state--; + st->should_run = (st->state > st->target); + WARN_ON_ONCE(st->state < st->target); } - } else if (st->rollback) { - BUG_ON(st->state < CPUHP_AP_ONLINE_IDLE); + } + + WARN_ON_ONCE(!cpuhp_is_ap_state(state)); + + if (st->rollback) { + struct cpuhp_step *step = cpuhp_get_step(state); + if (step->skip_onerr) + goto next; + } + + if (cpuhp_is_atomic_state(state)) { + local_irq_disable(); + st->result = cpuhp_invoke_callback(cpu, state, bringup, st->node, &st->last); + local_irq_enable(); - undo_cpu_down(cpu, st); - st->rollback = false; + /* + * STARTING/DYING must not fail! + */ + WARN_ON_ONCE(st->result); } else { - /* Cannot happen .... */ - BUG_ON(st->state < CPUHP_AP_ONLINE_IDLE); - - /* Regular hotplug work */ - if (st->state < st->target) - ret = cpuhp_ap_online(cpu, st); - else if (st->state > st->target) - ret = cpuhp_ap_offline(cpu, st); + st->result = cpuhp_invoke_callback(cpu, state, bringup, st->node, &st->last); + } + + if (st->result) { + /* + * If we fail on a rollback, we're up a creek without no + * paddle, no way forward, no way back. We loose, thanks for + * playing. + */ + WARN_ON_ONCE(st->rollback); + st->should_run = false; } - lock_map_release(&cpuhp_state_lock_map); - st->result = ret; - complete(&st->done); + +next: + cpuhp_lock_release(bringup); + + if (!st->should_run) + complete_ap_thread(st, bringup); } /* Invoke a single callback on a remote cpu */ @@ -460,62 +594,64 @@ cpuhp_invoke_ap_callback(int cpu, enum cpuhp_state state, bool bringup, struct hlist_node *node) { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); + int ret; if (!cpu_online(cpu)) return 0; - lock_map_acquire(&cpuhp_state_lock_map); - lock_map_release(&cpuhp_state_lock_map); + cpuhp_lock_acquire(false); + cpuhp_lock_release(false); + + cpuhp_lock_acquire(true); + cpuhp_lock_release(true); /* * If we are up and running, use the hotplug thread. For early calls * we invoke the thread function directly. */ if (!st->thread) - return cpuhp_invoke_callback(cpu, state, bringup, node); + return cpuhp_invoke_callback(cpu, state, bringup, node, NULL); + + st->rollback = false; + st->last = NULL; + st->node = node; + st->bringup = bringup; st->cb_state = state; st->single = true; - st->bringup = bringup; - st->node = node; - /* - * Make sure the above stores are visible before should_run becomes - * true. Paired with the mb() above in cpuhp_thread_fun() - */ - smp_mb(); - st->should_run = true; - wake_up_process(st->thread); - wait_for_completion(&st->done); - return st->result; -} + __cpuhp_kick_ap(st); -/* Regular hotplug invocation of the AP hotplug thread */ -static void __cpuhp_kick_ap_work(struct cpuhp_cpu_state *st) -{ - st->result = 0; - st->single = false; /* - * Make sure the above stores are visible before should_run becomes - * true. Paired with the mb() above in cpuhp_thread_fun() + * If we failed and did a partial, do a rollback. */ - smp_mb(); - st->should_run = true; - wake_up_process(st->thread); + if ((ret = st->result) && st->last) { + st->rollback = true; + st->bringup = !bringup; + + __cpuhp_kick_ap(st); + } + + return ret; } static int cpuhp_kick_ap_work(unsigned int cpu) { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); - enum cpuhp_state state = st->state; + enum cpuhp_state prev_state = st->state; + int ret; + + cpuhp_lock_acquire(false); + cpuhp_lock_release(false); - trace_cpuhp_enter(cpu, st->target, state, cpuhp_kick_ap_work); - lock_map_acquire(&cpuhp_state_lock_map); - lock_map_release(&cpuhp_state_lock_map); - __cpuhp_kick_ap_work(st); - wait_for_completion(&st->done); - trace_cpuhp_exit(cpu, st->state, state, st->result); - return st->result; + cpuhp_lock_acquire(true); + cpuhp_lock_release(true); + + trace_cpuhp_enter(cpu, st->target, prev_state, cpuhp_kick_ap_work); + ret = cpuhp_kick_ap(st, st->target); + trace_cpuhp_exit(cpu, st->state, prev_state, ret); + + return ret; } static struct smp_hotplug_thread cpuhp_threads = { @@ -581,6 +717,7 @@ static int take_cpu_down(void *_param) struct cpuhp_cpu_state *st = this_cpu_ptr(&cpuhp_state); enum cpuhp_state target = max((int)st->target, CPUHP_AP_OFFLINE); int err, cpu = smp_processor_id(); + int ret; /* Ensure this CPU doesn't handle any more interrupts. */ err = __cpu_disable(); @@ -594,8 +731,13 @@ static int take_cpu_down(void *_param) WARN_ON(st->state != CPUHP_TEARDOWN_CPU); st->state--; /* Invoke the former CPU_DYING callbacks */ - for (; st->state > target; st->state--) - cpuhp_invoke_callback(cpu, st->state, false, NULL); + for (; st->state > target; st->state--) { + ret = cpuhp_invoke_callback(cpu, st->state, false, NULL, NULL); + /* + * DYING must not fail! + */ + WARN_ON_ONCE(ret); + } /* Give up timekeeping duties */ tick_handover_do_timer(); @@ -639,7 +781,7 @@ static int takedown_cpu(unsigned int cpu) * * Wait for the stop thread to go away. */ - wait_for_completion(&st->done); + wait_for_ap_thread(st, false); BUG_ON(st->state != CPUHP_AP_IDLE_DEAD); /* Interrupts are moved away from the dying cpu, reenable alloc/free */ @@ -658,7 +800,7 @@ static void cpuhp_complete_idle_dead(void *arg) { struct cpuhp_cpu_state *st = arg; - complete(&st->done); + complete_ap_thread(st, false); } void cpuhp_report_idle_dead(void) @@ -676,11 +818,32 @@ void cpuhp_report_idle_dead(void) cpuhp_complete_idle_dead, st, 0); } -#else -#define takedown_cpu NULL -#endif +static void undo_cpu_down(unsigned int cpu, struct cpuhp_cpu_state *st) +{ + for (st->state++; st->state < st->target; st->state++) { + struct cpuhp_step *step = cpuhp_get_step(st->state); -#ifdef CONFIG_HOTPLUG_CPU + if (!step->skip_onerr) + cpuhp_invoke_callback(cpu, st->state, true, NULL, NULL); + } +} + +static int cpuhp_down_callbacks(unsigned int cpu, struct cpuhp_cpu_state *st, + enum cpuhp_state target) +{ + enum cpuhp_state prev_state = st->state; + int ret = 0; + + for (; st->state > target; st->state--) { + ret = cpuhp_invoke_callback(cpu, st->state, false, NULL, NULL); + if (ret) { + st->target = prev_state; + undo_cpu_down(cpu, st); + break; + } + } + return ret; +} /* Requires cpu_add_remove_lock to be held */ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen, @@ -699,13 +862,13 @@ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen, cpuhp_tasks_frozen = tasks_frozen; - prev_state = st->state; - st->target = target; + prev_state = cpuhp_set_state(st, target); /* * If the current CPU state is in the range of the AP hotplug thread, * then we need to kick the thread. */ if (st->state > CPUHP_TEARDOWN_CPU) { + st->target = max((int)target, CPUHP_TEARDOWN_CPU); ret = cpuhp_kick_ap_work(cpu); /* * The AP side has done the error rollback already. Just @@ -720,6 +883,8 @@ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen, */ if (st->state > CPUHP_TEARDOWN_CPU) goto out; + + st->target = target; } /* * The AP brought itself down to CPUHP_TEARDOWN_CPU. So we need @@ -727,13 +892,17 @@ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen, */ ret = cpuhp_down_callbacks(cpu, st, target); if (ret && st->state > CPUHP_TEARDOWN_CPU && st->state < prev_state) { - st->target = prev_state; - st->rollback = true; - cpuhp_kick_ap_work(cpu); + cpuhp_reset_state(st, prev_state); + __cpuhp_kick_ap(st); } out: cpus_write_unlock(); + /* + * Do post unplug cleanup. This is still protected against + * concurrent CPU hotplug via cpu_add_remove_lock. + */ + lockup_detector_cleanup(); return ret; } @@ -754,11 +923,15 @@ out: cpu_maps_update_done(); return err; } + int cpu_down(unsigned int cpu) { return do_cpu_down(cpu, CPUHP_OFFLINE); } EXPORT_SYMBOL(cpu_down); + +#else +#define takedown_cpu NULL #endif /*CONFIG_HOTPLUG_CPU*/ /** @@ -772,11 +945,16 @@ void notify_cpu_starting(unsigned int cpu) { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); enum cpuhp_state target = min((int)st->target, CPUHP_AP_ONLINE); + int ret; rcu_cpu_starting(cpu); /* Enables RCU usage on this CPU. */ while (st->state < target) { st->state++; - cpuhp_invoke_callback(cpu, st->state, true, NULL); + ret = cpuhp_invoke_callback(cpu, st->state, true, NULL, NULL); + /* + * STARTING must not fail! + */ + WARN_ON_ONCE(ret); } } @@ -794,7 +972,7 @@ void cpuhp_online_idle(enum cpuhp_state state) return; st->state = CPUHP_AP_ONLINE_IDLE; - complete(&st->done); + complete_ap_thread(st, true); } /* Requires cpu_add_remove_lock to be held */ @@ -829,7 +1007,7 @@ static int _cpu_up(unsigned int cpu, int tasks_frozen, enum cpuhp_state target) cpuhp_tasks_frozen = tasks_frozen; - st->target = target; + cpuhp_set_state(st, target); /* * If the current CPU state is in the range of the AP hotplug thread, * then we need to kick the thread once more. @@ -1296,6 +1474,10 @@ static int cpuhp_issue_call(int cpu, enum cpuhp_state state, bool bringup, struct cpuhp_step *sp = cpuhp_get_step(state); int ret; + /* + * If there's nothing to do, we done. + * Relies on the union for multi_instance. + */ if ((bringup && !sp->startup.single) || (!bringup && !sp->teardown.single)) return 0; @@ -1307,9 +1489,9 @@ static int cpuhp_issue_call(int cpu, enum cpuhp_state state, bool bringup, if (cpuhp_is_ap_state(state)) ret = cpuhp_invoke_ap_callback(cpu, state, bringup, node); else - ret = cpuhp_invoke_callback(cpu, state, bringup, node); + ret = cpuhp_invoke_callback(cpu, state, bringup, node, NULL); #else - ret = cpuhp_invoke_callback(cpu, state, bringup, node); + ret = cpuhp_invoke_callback(cpu, state, bringup, node, NULL); #endif BUG_ON(ret && !bringup); return ret; @@ -1641,9 +1823,55 @@ static ssize_t show_cpuhp_target(struct device *dev, } static DEVICE_ATTR(target, 0644, show_cpuhp_target, write_cpuhp_target); + +static ssize_t write_cpuhp_fail(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) +{ + struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, dev->id); + struct cpuhp_step *sp; + int fail, ret; + + ret = kstrtoint(buf, 10, &fail); + if (ret) + return ret; + + /* + * Cannot fail STARTING/DYING callbacks. + */ + if (cpuhp_is_atomic_state(fail)) + return -EINVAL; + + /* + * Cannot fail anything that doesn't have callbacks. + */ + mutex_lock(&cpuhp_state_mutex); + sp = cpuhp_get_step(fail); + if (!sp->startup.single && !sp->teardown.single) + ret = -EINVAL; + mutex_unlock(&cpuhp_state_mutex); + if (ret) + return ret; + + st->fail = fail; + + return count; +} + +static ssize_t show_cpuhp_fail(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, dev->id); + + return sprintf(buf, "%d\n", st->fail); +} + +static DEVICE_ATTR(fail, 0644, show_cpuhp_fail, write_cpuhp_fail); + static struct attribute *cpuhp_cpu_attrs[] = { &dev_attr_state.attr, &dev_attr_target.attr, + &dev_attr_fail.attr, NULL }; diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c index af71a84e12ee..f684d8e5fa2b 100644 --- a/kernel/events/ring_buffer.c +++ b/kernel/events/ring_buffer.c @@ -412,6 +412,19 @@ err: return NULL; } +static bool __always_inline rb_need_aux_wakeup(struct ring_buffer *rb) +{ + if (rb->aux_overwrite) + return false; + + if (rb->aux_head - rb->aux_wakeup >= rb->aux_watermark) { + rb->aux_wakeup = rounddown(rb->aux_head, rb->aux_watermark); + return true; + } + + return false; +} + /* * Commit the data written by hardware into the ring buffer by adjusting * aux_head and posting a PERF_RECORD_AUX into the perf buffer. It is the @@ -451,10 +464,8 @@ void perf_aux_output_end(struct perf_output_handle *handle, unsigned long size) } rb->user_page->aux_head = rb->aux_head; - if (rb->aux_head - rb->aux_wakeup >= rb->aux_watermark) { + if (rb_need_aux_wakeup(rb)) wakeup = true; - rb->aux_wakeup = rounddown(rb->aux_head, rb->aux_watermark); - } if (wakeup) { if (handle->aux_flags & PERF_AUX_FLAG_TRUNCATED) @@ -484,9 +495,8 @@ int perf_aux_output_skip(struct perf_output_handle *handle, unsigned long size) rb->aux_head += size; rb->user_page->aux_head = rb->aux_head; - if (rb->aux_head - rb->aux_wakeup >= rb->aux_watermark) { + if (rb_need_aux_wakeup(rb)) { perf_output_wakeup(handle); - rb->aux_wakeup = rounddown(rb->aux_head, rb->aux_watermark); handle->wakeup = rb->aux_wakeup + rb->aux_watermark; } diff --git a/kernel/exit.c b/kernel/exit.c index 3481ababd06a..f2cd53e92147 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -1600,12 +1600,10 @@ SYSCALL_DEFINE5(waitid, int, which, pid_t, upid, struct siginfo __user *, struct waitid_info info = {.status = 0}; long err = kernel_waitid(which, upid, &info, options, ru ? &r : NULL); int signo = 0; + if (err > 0) { signo = SIGCHLD; err = 0; - } - - if (!err) { if (ru && copy_to_user(ru, &r, sizeof(struct rusage))) return -EFAULT; } @@ -1723,16 +1721,15 @@ COMPAT_SYSCALL_DEFINE5(waitid, if (err > 0) { signo = SIGCHLD; err = 0; - } - - if (!err && uru) { - /* kernel_waitid() overwrites everything in ru */ - if (COMPAT_USE_64BIT_TIME) - err = copy_to_user(uru, &ru, sizeof(ru)); - else - err = put_compat_rusage(&ru, uru); - if (err) - return -EFAULT; + if (uru) { + /* kernel_waitid() overwrites everything in ru */ + if (COMPAT_USE_64BIT_TIME) + err = copy_to_user(uru, &ru, sizeof(ru)); + else + err = put_compat_rusage(&ru, uru); + if (err) + return -EFAULT; + } } if (!infop) diff --git a/kernel/extable.c b/kernel/extable.c index 38c2412401a1..9aa1cc41ecf7 100644 --- a/kernel/extable.c +++ b/kernel/extable.c @@ -102,15 +102,7 @@ int core_kernel_data(unsigned long addr) int __kernel_text_address(unsigned long addr) { - if (core_kernel_text(addr)) - return 1; - if (is_module_text_address(addr)) - return 1; - if (is_ftrace_trampoline(addr)) - return 1; - if (is_kprobe_optinsn_slot(addr) || is_kprobe_insn_slot(addr)) - return 1; - if (is_bpf_text_address(addr)) + if (kernel_text_address(addr)) return 1; /* * There might be init symbols in saved stacktraces. @@ -127,17 +119,42 @@ int __kernel_text_address(unsigned long addr) int kernel_text_address(unsigned long addr) { + bool no_rcu; + int ret = 1; + if (core_kernel_text(addr)) return 1; + + /* + * If a stack dump happens while RCU is not watching, then + * RCU needs to be notified that it requires to start + * watching again. This can happen either by tracing that + * triggers a stack trace, or a WARN() that happens during + * coming back from idle, or cpu on or offlining. + * + * is_module_text_address() as well as the kprobe slots + * and is_bpf_text_address() require RCU to be watching. + */ + no_rcu = !rcu_is_watching(); + + /* Treat this like an NMI as it can happen anywhere */ + if (no_rcu) + rcu_nmi_enter(); + if (is_module_text_address(addr)) - return 1; + goto out; if (is_ftrace_trampoline(addr)) - return 1; + goto out; if (is_kprobe_optinsn_slot(addr) || is_kprobe_insn_slot(addr)) - return 1; + goto out; if (is_bpf_text_address(addr)) - return 1; - return 0; + goto out; + ret = 0; +out: + if (no_rcu) + rcu_nmi_exit(); + + return ret; } /* diff --git a/kernel/fork.c b/kernel/fork.c index 10646182440f..e702cb9ffbd8 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -946,6 +946,24 @@ void mmput(struct mm_struct *mm) } EXPORT_SYMBOL_GPL(mmput); +#ifdef CONFIG_MMU +static void mmput_async_fn(struct work_struct *work) +{ + struct mm_struct *mm = container_of(work, struct mm_struct, + async_put_work); + + __mmput(mm); +} + +void mmput_async(struct mm_struct *mm) +{ + if (atomic_dec_and_test(&mm->mm_users)) { + INIT_WORK(&mm->async_put_work, mmput_async_fn); + schedule_work(&mm->async_put_work); + } +} +#endif + /** * set_mm_exe_file - change a reference to the mm's executable file * diff --git a/kernel/futex.c b/kernel/futex.c index 3d38eaf05492..0518a0bfc746 100644 --- a/kernel/futex.c +++ b/kernel/futex.c @@ -821,8 +821,6 @@ static void get_pi_state(struct futex_pi_state *pi_state) /* * Drops a reference to the pi_state object and frees or caches it * when the last reference is gone. - * - * Must be called with the hb lock held. */ static void put_pi_state(struct futex_pi_state *pi_state) { @@ -837,16 +835,22 @@ static void put_pi_state(struct futex_pi_state *pi_state) * and has cleaned up the pi_state already */ if (pi_state->owner) { - raw_spin_lock_irq(&pi_state->owner->pi_lock); - list_del_init(&pi_state->list); - raw_spin_unlock_irq(&pi_state->owner->pi_lock); + struct task_struct *owner; - rt_mutex_proxy_unlock(&pi_state->pi_mutex, pi_state->owner); + raw_spin_lock_irq(&pi_state->pi_mutex.wait_lock); + owner = pi_state->owner; + if (owner) { + raw_spin_lock(&owner->pi_lock); + list_del_init(&pi_state->list); + raw_spin_unlock(&owner->pi_lock); + } + rt_mutex_proxy_unlock(&pi_state->pi_mutex, owner); + raw_spin_unlock_irq(&pi_state->pi_mutex.wait_lock); } - if (current->pi_state_cache) + if (current->pi_state_cache) { kfree(pi_state); - else { + } else { /* * pi_state->list is already empty. * clear pi_state->owner. @@ -907,13 +911,14 @@ void exit_pi_state_list(struct task_struct *curr) raw_spin_unlock_irq(&curr->pi_lock); spin_lock(&hb->lock); - - raw_spin_lock_irq(&curr->pi_lock); + raw_spin_lock_irq(&pi_state->pi_mutex.wait_lock); + raw_spin_lock(&curr->pi_lock); /* * We dropped the pi-lock, so re-check whether this * task still owns the PI-state: */ if (head->next != next) { + raw_spin_unlock(&pi_state->pi_mutex.wait_lock); spin_unlock(&hb->lock); continue; } @@ -922,9 +927,10 @@ void exit_pi_state_list(struct task_struct *curr) WARN_ON(list_empty(&pi_state->list)); list_del_init(&pi_state->list); pi_state->owner = NULL; - raw_spin_unlock_irq(&curr->pi_lock); + raw_spin_unlock(&curr->pi_lock); get_pi_state(pi_state); + raw_spin_unlock_irq(&pi_state->pi_mutex.wait_lock); spin_unlock(&hb->lock); rt_mutex_futex_unlock(&pi_state->pi_mutex); @@ -1208,6 +1214,10 @@ static int attach_to_pi_owner(u32 uval, union futex_key *key, WARN_ON(!list_empty(&pi_state->list)); list_add(&pi_state->list, &p->pi_state_list); + /* + * Assignment without holding pi_state->pi_mutex.wait_lock is safe + * because there is no concurrency as the object is not published yet. + */ pi_state->owner = p; raw_spin_unlock_irq(&p->pi_lock); @@ -2878,6 +2888,7 @@ retry: raw_spin_lock_irq(&pi_state->pi_mutex.wait_lock); spin_unlock(&hb->lock); + /* drops pi_state->pi_mutex.wait_lock */ ret = wake_futex_pi(uaddr, uval, pi_state); put_pi_state(pi_state); diff --git a/kernel/irq/generic-chip.c b/kernel/irq/generic-chip.c index f7086b78ad6e..5270a54b9fa4 100644 --- a/kernel/irq/generic-chip.c +++ b/kernel/irq/generic-chip.c @@ -322,7 +322,6 @@ int __irq_alloc_domain_generic_chips(struct irq_domain *d, int irqs_per_chip, /* Calc pointer to the next generic chip */ tmp += sizeof(*gc) + num_ct * sizeof(struct irq_chip_type); } - d->name = name; return 0; } EXPORT_SYMBOL_GPL(__irq_alloc_domain_generic_chips); diff --git a/kernel/irq/irqdomain.c b/kernel/irq/irqdomain.c index e84b7056bb08..ac4644e92b49 100644 --- a/kernel/irq/irqdomain.c +++ b/kernel/irq/irqdomain.c @@ -945,7 +945,7 @@ static int virq_debug_show(struct seq_file *m, void *private) struct irq_desc *desc; struct irq_domain *domain; struct radix_tree_iter iter; - void **slot; + void __rcu **slot; int i; seq_printf(m, " %-16s %-6s %-10s %-10s %s\n", @@ -1453,7 +1453,7 @@ out_free_desc: /* The irq_data was moved, fix the revmap to refer to the new location */ static void irq_domain_fix_revmap(struct irq_data *d) { - void **slot; + void __rcu **slot; if (d->hwirq < d->domain->revmap_size) return; /* Not using radix tree. */ diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c index 573dc52b0806..d00132b5c325 100644 --- a/kernel/irq/manage.c +++ b/kernel/irq/manage.c @@ -1643,6 +1643,10 @@ const void *free_irq(unsigned int irq, void *dev_id) #endif action = __free_irq(irq, dev_id); + + if (!action) + return NULL; + devname = action->name; kfree(action); return devname; diff --git a/kernel/kcmp.c b/kernel/kcmp.c index ea34ed8bb952..055bb2962a0b 100644 --- a/kernel/kcmp.c +++ b/kernel/kcmp.c @@ -131,7 +131,7 @@ static int kcmp_epoll_target(struct task_struct *task1, if (filp_epoll) { filp_tgt = get_epoll_tfile_raw_ptr(filp_epoll, slot.tfd, slot.toff); fput(filp_epoll); - } else + } if (IS_ERR(filp_tgt)) return PTR_ERR(filp_tgt); diff --git a/kernel/locking/rwsem-xadd.c b/kernel/locking/rwsem-xadd.c index 02f660666ab8..1fefe6dcafd7 100644 --- a/kernel/locking/rwsem-xadd.c +++ b/kernel/locking/rwsem-xadd.c @@ -613,6 +613,33 @@ struct rw_semaphore *rwsem_wake(struct rw_semaphore *sem) DEFINE_WAKE_Q(wake_q); /* + * __rwsem_down_write_failed_common(sem) + * rwsem_optimistic_spin(sem) + * osq_unlock(sem->osq) + * ... + * atomic_long_add_return(&sem->count) + * + * - VS - + * + * __up_write() + * if (atomic_long_sub_return_release(&sem->count) < 0) + * rwsem_wake(sem) + * osq_is_locked(&sem->osq) + * + * And __up_write() must observe !osq_is_locked() when it observes the + * atomic_long_add_return() in order to not miss a wakeup. + * + * This boils down to: + * + * [S.rel] X = 1 [RmW] r0 = (Y += 0) + * MB RMB + * [RmW] Y += 1 [L] r1 = X + * + * exists (r0=1 /\ r1=0) + */ + smp_rmb(); + + /* * If a spinner is present, it is not necessary to do the wakeup. * Try to do wakeup only if the trylock succeeds to minimize * spinlock contention which may introduce too much delay in the diff --git a/kernel/memremap.c b/kernel/memremap.c index 6bcbfbf1a8fd..403ab9cdb949 100644 --- a/kernel/memremap.c +++ b/kernel/memremap.c @@ -350,7 +350,7 @@ void *devm_memremap_pages(struct device *dev, struct resource *res, pgprot_t pgprot = PAGE_KERNEL; struct dev_pagemap *pgmap; struct page_map *page_map; - int error, nid, is_ram; + int error, nid, is_ram, i = 0; align_start = res->start & ~(SECTION_SIZE - 1); align_size = ALIGN(res->start + resource_size(res), SECTION_SIZE) @@ -448,6 +448,8 @@ void *devm_memremap_pages(struct device *dev, struct resource *res, list_del(&page->lru); page->pgmap = pgmap; percpu_ref_get(ref); + if (!(++i % 1024)) + cond_resched(); } devres_add(dev, page_map); return __va(res->start); diff --git a/kernel/params.c b/kernel/params.c index 60b2d8101355..cc9108c2a1fd 100644 --- a/kernel/params.c +++ b/kernel/params.c @@ -224,7 +224,7 @@ char *parse_args(const char *doing, } \ int param_get_##name(char *buffer, const struct kernel_param *kp) \ { \ - return scnprintf(buffer, PAGE_SIZE, format, \ + return scnprintf(buffer, PAGE_SIZE, format "\n", \ *((type *)kp->arg)); \ } \ const struct kernel_param_ops param_ops_##name = { \ @@ -236,14 +236,14 @@ char *parse_args(const char *doing, EXPORT_SYMBOL(param_ops_##name) -STANDARD_PARAM_DEF(byte, unsigned char, "%hhu", kstrtou8); -STANDARD_PARAM_DEF(short, short, "%hi", kstrtos16); -STANDARD_PARAM_DEF(ushort, unsigned short, "%hu", kstrtou16); -STANDARD_PARAM_DEF(int, int, "%i", kstrtoint); -STANDARD_PARAM_DEF(uint, unsigned int, "%u", kstrtouint); -STANDARD_PARAM_DEF(long, long, "%li", kstrtol); -STANDARD_PARAM_DEF(ulong, unsigned long, "%lu", kstrtoul); -STANDARD_PARAM_DEF(ullong, unsigned long long, "%llu", kstrtoull); +STANDARD_PARAM_DEF(byte, unsigned char, "%hhu", kstrtou8); +STANDARD_PARAM_DEF(short, short, "%hi", kstrtos16); +STANDARD_PARAM_DEF(ushort, unsigned short, "%hu", kstrtou16); +STANDARD_PARAM_DEF(int, int, "%i", kstrtoint); +STANDARD_PARAM_DEF(uint, unsigned int, "%u", kstrtouint); +STANDARD_PARAM_DEF(long, long, "%li", kstrtol); +STANDARD_PARAM_DEF(ulong, unsigned long, "%lu", kstrtoul); +STANDARD_PARAM_DEF(ullong, unsigned long long, "%llu", kstrtoull); int param_set_charp(const char *val, const struct kernel_param *kp) { @@ -270,7 +270,7 @@ EXPORT_SYMBOL(param_set_charp); int param_get_charp(char *buffer, const struct kernel_param *kp) { - return scnprintf(buffer, PAGE_SIZE, "%s", *((char **)kp->arg)); + return scnprintf(buffer, PAGE_SIZE, "%s\n", *((char **)kp->arg)); } EXPORT_SYMBOL(param_get_charp); @@ -301,7 +301,7 @@ EXPORT_SYMBOL(param_set_bool); int param_get_bool(char *buffer, const struct kernel_param *kp) { /* Y and N chosen as being relatively non-coder friendly */ - return sprintf(buffer, "%c", *(bool *)kp->arg ? 'Y' : 'N'); + return sprintf(buffer, "%c\n", *(bool *)kp->arg ? 'Y' : 'N'); } EXPORT_SYMBOL(param_get_bool); @@ -360,7 +360,7 @@ EXPORT_SYMBOL(param_set_invbool); int param_get_invbool(char *buffer, const struct kernel_param *kp) { - return sprintf(buffer, "%c", (*(bool *)kp->arg) ? 'N' : 'Y'); + return sprintf(buffer, "%c\n", (*(bool *)kp->arg) ? 'N' : 'Y'); } EXPORT_SYMBOL(param_get_invbool); @@ -460,8 +460,9 @@ static int param_array_get(char *buffer, const struct kernel_param *kp) struct kernel_param p = *kp; for (i = off = 0; i < (arr->num ? *arr->num : arr->max); i++) { + /* Replace \n with comma */ if (i) - buffer[off++] = ','; + buffer[off - 1] = ','; p.arg = arr->elem + arr->elemsize * i; check_kparam_locked(p.mod); ret = arr->ops->get(buffer + off, &p); @@ -507,7 +508,7 @@ EXPORT_SYMBOL(param_set_copystring); int param_get_string(char *buffer, const struct kernel_param *kp) { const struct kparam_string *kps = kp->str; - return strlcpy(buffer, kps->string, kps->maxlen); + return scnprintf(buffer, PAGE_SIZE, "%s\n", kps->string); } EXPORT_SYMBOL(param_get_string); @@ -549,10 +550,6 @@ static ssize_t param_attr_show(struct module_attribute *mattr, kernel_param_lock(mk->mod); count = attribute->param->ops->get(buf, attribute->param); kernel_param_unlock(mk->mod); - if (count > 0) { - strcat(buf, "\n"); - ++count; - } return count; } @@ -600,7 +597,7 @@ EXPORT_SYMBOL(kernel_param_unlock); /* * add_sysfs_param - add a parameter to sysfs * @mk: struct module_kobject - * @kparam: the actual parameter definition to add to sysfs + * @kp: the actual parameter definition to add to sysfs * @name: name of parameter * * Create a kobject if for a (per-module) parameter if mp NULL, and diff --git a/kernel/power/suspend.c b/kernel/power/suspend.c index 3e2b4f519009..ccd2d20e6b06 100644 --- a/kernel/power/suspend.c +++ b/kernel/power/suspend.c @@ -120,22 +120,26 @@ static void s2idle_loop(void) * frozen processes + suspended devices + idle processors. * Thus s2idle_enter() should be called right after * all devices have been suspended. + * + * Wakeups during the noirq suspend of devices may be spurious, + * so prevent them from terminating the loop right away. */ error = dpm_noirq_suspend_devices(PMSG_SUSPEND); if (!error) s2idle_enter(); + else if (error == -EBUSY && pm_wakeup_pending()) + error = 0; - dpm_noirq_resume_devices(PMSG_RESUME); - if (error && (error != -EBUSY || !pm_wakeup_pending())) { - dpm_noirq_end(); - break; - } - - if (s2idle_ops && s2idle_ops->wake) + if (!error && s2idle_ops && s2idle_ops->wake) s2idle_ops->wake(); + dpm_noirq_resume_devices(PMSG_RESUME); + dpm_noirq_end(); + if (error) + break; + if (s2idle_ops && s2idle_ops->sync) s2idle_ops->sync(); diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index 1250e4bd4b85..b0ad62b0e7b8 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -882,6 +882,11 @@ void rcu_irq_exit(void) RCU_LOCKDEP_WARN(!irqs_disabled(), "rcu_irq_exit() invoked with irqs enabled!!!"); rdtp = this_cpu_ptr(&rcu_dynticks); + + /* Page faults can happen in NMI handlers, so check... */ + if (rdtp->dynticks_nmi_nesting) + return; + WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) && rdtp->dynticks_nesting < 1); if (rdtp->dynticks_nesting <= 1) { @@ -1015,6 +1020,11 @@ void rcu_irq_enter(void) RCU_LOCKDEP_WARN(!irqs_disabled(), "rcu_irq_enter() invoked with irqs enabled!!!"); rdtp = this_cpu_ptr(&rcu_dynticks); + + /* Page faults can happen in NMI handlers, so check... */ + if (rdtp->dynticks_nmi_nesting) + return; + oldval = rdtp->dynticks_nesting; rdtp->dynticks_nesting++; WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) && diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 18a6966567da..d17c5da523a0 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -5166,6 +5166,28 @@ void sched_show_task(struct task_struct *p) put_task_stack(p); } +static inline bool +state_filter_match(unsigned long state_filter, struct task_struct *p) +{ + /* no filter, everything matches */ + if (!state_filter) + return true; + + /* filter, but doesn't match */ + if (!(p->state & state_filter)) + return false; + + /* + * When looking for TASK_UNINTERRUPTIBLE skip TASK_IDLE (allows + * TASK_KILLABLE). + */ + if (state_filter == TASK_UNINTERRUPTIBLE && p->state == TASK_IDLE) + return false; + + return true; +} + + void show_state_filter(unsigned long state_filter) { struct task_struct *g, *p; @@ -5188,7 +5210,7 @@ void show_state_filter(unsigned long state_filter) */ touch_nmi_watchdog(); touch_all_softlockup_watchdogs(); - if (!state_filter || (p->state & state_filter)) + if (state_filter_match(state_filter, p)) sched_show_task(p); } diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c index 01217fb5a5de..2f93e4a2d9f6 100644 --- a/kernel/sched/debug.c +++ b/kernel/sched/debug.c @@ -466,8 +466,6 @@ static char *task_group_path(struct task_group *tg) } #endif -static const char stat_nam[] = TASK_STATE_TO_CHAR_STR; - static void print_task(struct seq_file *m, struct rq *rq, struct task_struct *p) { diff --git a/kernel/seccomp.c b/kernel/seccomp.c index c24579dfa7a1..bb3a38005b9c 100644 --- a/kernel/seccomp.c +++ b/kernel/seccomp.c @@ -473,14 +473,19 @@ static long seccomp_attach_filter(unsigned int flags, return 0; } +void __get_seccomp_filter(struct seccomp_filter *filter) +{ + /* Reference count is bounded by the number of total processes. */ + refcount_inc(&filter->usage); +} + /* get_seccomp_filter - increments the reference count of the filter on @tsk */ void get_seccomp_filter(struct task_struct *tsk) { struct seccomp_filter *orig = tsk->seccomp.filter; if (!orig) return; - /* Reference count is bounded by the number of total processes. */ - refcount_inc(&orig->usage); + __get_seccomp_filter(orig); } static inline void seccomp_filter_free(struct seccomp_filter *filter) @@ -491,10 +496,8 @@ static inline void seccomp_filter_free(struct seccomp_filter *filter) } } -/* put_seccomp_filter - decrements the ref count of tsk->seccomp.filter */ -void put_seccomp_filter(struct task_struct *tsk) +static void __put_seccomp_filter(struct seccomp_filter *orig) { - struct seccomp_filter *orig = tsk->seccomp.filter; /* Clean up single-reference branches iteratively. */ while (orig && refcount_dec_and_test(&orig->usage)) { struct seccomp_filter *freeme = orig; @@ -503,6 +506,12 @@ void put_seccomp_filter(struct task_struct *tsk) } } +/* put_seccomp_filter - decrements the ref count of tsk->seccomp.filter */ +void put_seccomp_filter(struct task_struct *tsk) +{ + __put_seccomp_filter(tsk->seccomp.filter); +} + static void seccomp_init_siginfo(siginfo_t *info, int syscall, int reason) { memset(info, 0, sizeof(*info)); @@ -1025,13 +1034,13 @@ long seccomp_get_filter(struct task_struct *task, unsigned long filter_off, if (!data) goto out; - get_seccomp_filter(task); + __get_seccomp_filter(filter); spin_unlock_irq(&task->sighand->siglock); if (copy_to_user(data, fprog->filter, bpf_classic_proglen(fprog))) ret = -EFAULT; - put_seccomp_filter(task); + __put_seccomp_filter(filter); return ret; out: diff --git a/kernel/smpboot.c b/kernel/smpboot.c index 1d71c051a951..5043e7433f4b 100644 --- a/kernel/smpboot.c +++ b/kernel/smpboot.c @@ -344,39 +344,30 @@ EXPORT_SYMBOL_GPL(smpboot_unregister_percpu_thread); * by the client, but only by calling this function. * This function can only be called on a registered smp_hotplug_thread. */ -int smpboot_update_cpumask_percpu_thread(struct smp_hotplug_thread *plug_thread, - const struct cpumask *new) +void smpboot_update_cpumask_percpu_thread(struct smp_hotplug_thread *plug_thread, + const struct cpumask *new) { struct cpumask *old = plug_thread->cpumask; - cpumask_var_t tmp; + static struct cpumask tmp; unsigned int cpu; - if (!alloc_cpumask_var(&tmp, GFP_KERNEL)) - return -ENOMEM; - - get_online_cpus(); + lockdep_assert_cpus_held(); mutex_lock(&smpboot_threads_lock); /* Park threads that were exclusively enabled on the old mask. */ - cpumask_andnot(tmp, old, new); - for_each_cpu_and(cpu, tmp, cpu_online_mask) + cpumask_andnot(&tmp, old, new); + for_each_cpu_and(cpu, &tmp, cpu_online_mask) smpboot_park_thread(plug_thread, cpu); /* Unpark threads that are exclusively enabled on the new mask. */ - cpumask_andnot(tmp, new, old); - for_each_cpu_and(cpu, tmp, cpu_online_mask) + cpumask_andnot(&tmp, new, old); + for_each_cpu_and(cpu, &tmp, cpu_online_mask) smpboot_unpark_thread(plug_thread, cpu); cpumask_copy(old, new); mutex_unlock(&smpboot_threads_lock); - put_online_cpus(); - - free_cpumask_var(tmp); - - return 0; } -EXPORT_SYMBOL_GPL(smpboot_update_cpumask_percpu_thread); static DEFINE_PER_CPU(atomic_t, cpu_hotplug_state) = ATOMIC_INIT(CPU_POST_DEAD); diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 6648fbbb8157..d9c31bc2eaea 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -367,7 +367,8 @@ static struct ctl_table kern_table[] = { .data = &sysctl_sched_time_avg, .maxlen = sizeof(unsigned int), .mode = 0644, - .proc_handler = proc_dointvec, + .proc_handler = proc_dointvec_minmax, + .extra1 = &one, }, #ifdef CONFIG_SCHEDSTATS { @@ -871,9 +872,9 @@ static struct ctl_table kern_table[] = { #if defined(CONFIG_LOCKUP_DETECTOR) { .procname = "watchdog", - .data = &watchdog_user_enabled, - .maxlen = sizeof (int), - .mode = 0644, + .data = &watchdog_user_enabled, + .maxlen = sizeof(int), + .mode = 0644, .proc_handler = proc_watchdog, .extra1 = &zero, .extra2 = &one, @@ -889,16 +890,12 @@ static struct ctl_table kern_table[] = { }, { .procname = "nmi_watchdog", - .data = &nmi_watchdog_enabled, - .maxlen = sizeof (int), - .mode = 0644, + .data = &nmi_watchdog_user_enabled, + .maxlen = sizeof(int), + .mode = NMI_WATCHDOG_SYSCTL_PERM, .proc_handler = proc_nmi_watchdog, .extra1 = &zero, -#if defined(CONFIG_HAVE_NMI_WATCHDOG) || defined(CONFIG_HARDLOCKUP_DETECTOR) .extra2 = &one, -#else - .extra2 = &zero, -#endif }, { .procname = "watchdog_cpumask", @@ -910,9 +907,9 @@ static struct ctl_table kern_table[] = { #ifdef CONFIG_SOFTLOCKUP_DETECTOR { .procname = "soft_watchdog", - .data = &soft_watchdog_enabled, - .maxlen = sizeof (int), - .mode = 0644, + .data = &soft_watchdog_user_enabled, + .maxlen = sizeof(int), + .mode = 0644, .proc_handler = proc_soft_watchdog, .extra1 = &zero, .extra2 = &one, @@ -2187,8 +2184,6 @@ static int do_proc_douintvec_conv(unsigned long *lvalp, if (write) { if (*lvalp > UINT_MAX) return -EINVAL; - if (*lvalp > UINT_MAX) - return -EINVAL; *valp = *lvalp; } else { unsigned int val = *valp; diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c index 2a685b45b73b..45a3928544ce 100644 --- a/kernel/trace/blktrace.c +++ b/kernel/trace/blktrace.c @@ -648,6 +648,12 @@ int blk_trace_startstop(struct request_queue *q, int start) } EXPORT_SYMBOL_GPL(blk_trace_startstop); +/* + * When reading or writing the blktrace sysfs files, the references to the + * opened sysfs or device files should prevent the underlying block device + * from being removed. So no further delete protection is really needed. + */ + /** * blk_trace_ioctl: - handle the ioctls associated with tracing * @bdev: the block device @@ -665,7 +671,7 @@ int blk_trace_ioctl(struct block_device *bdev, unsigned cmd, char __user *arg) if (!q) return -ENXIO; - mutex_lock(&bdev->bd_mutex); + mutex_lock(&q->blk_trace_mutex); switch (cmd) { case BLKTRACESETUP: @@ -691,7 +697,7 @@ int blk_trace_ioctl(struct block_device *bdev, unsigned cmd, char __user *arg) break; } - mutex_unlock(&bdev->bd_mutex); + mutex_unlock(&q->blk_trace_mutex); return ret; } @@ -1727,7 +1733,7 @@ static ssize_t sysfs_blk_trace_attr_show(struct device *dev, if (q == NULL) goto out_bdput; - mutex_lock(&bdev->bd_mutex); + mutex_lock(&q->blk_trace_mutex); if (attr == &dev_attr_enable) { ret = sprintf(buf, "%u\n", !!q->blk_trace); @@ -1746,7 +1752,7 @@ static ssize_t sysfs_blk_trace_attr_show(struct device *dev, ret = sprintf(buf, "%llu\n", q->blk_trace->end_lba); out_unlock_bdev: - mutex_unlock(&bdev->bd_mutex); + mutex_unlock(&q->blk_trace_mutex); out_bdput: bdput(bdev); out: @@ -1788,7 +1794,7 @@ static ssize_t sysfs_blk_trace_attr_store(struct device *dev, if (q == NULL) goto out_bdput; - mutex_lock(&bdev->bd_mutex); + mutex_lock(&q->blk_trace_mutex); if (attr == &dev_attr_enable) { if (value) @@ -1814,7 +1820,7 @@ static ssize_t sysfs_blk_trace_attr_store(struct device *dev, } out_unlock_bdev: - mutex_unlock(&bdev->bd_mutex); + mutex_unlock(&q->blk_trace_mutex); out_bdput: bdput(bdev); out: diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 6abfafd7f173..8319e09e15b9 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -4954,9 +4954,6 @@ static char ftrace_graph_buf[FTRACE_FILTER_SIZE] __initdata; static char ftrace_graph_notrace_buf[FTRACE_FILTER_SIZE] __initdata; static int ftrace_graph_set_hash(struct ftrace_hash *hash, char *buffer); -static unsigned long save_global_trampoline; -static unsigned long save_global_flags; - static int __init set_graph_function(char *str) { strlcpy(ftrace_graph_buf, str, FTRACE_FILTER_SIZE); @@ -6808,17 +6805,6 @@ void unregister_ftrace_graph(void) unregister_pm_notifier(&ftrace_suspend_notifier); unregister_trace_sched_switch(ftrace_graph_probe_sched_switch, NULL); -#ifdef CONFIG_DYNAMIC_FTRACE - /* - * Function graph does not allocate the trampoline, but - * other global_ops do. We need to reset the ALLOC_TRAMP flag - * if one was used. - */ - global_ops.trampoline = save_global_trampoline; - if (save_global_flags & FTRACE_OPS_FL_ALLOC_TRAMP) - global_ops.flags |= FTRACE_OPS_FL_ALLOC_TRAMP; -#endif - out: mutex_unlock(&ftrace_lock); } diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c index bac629af2285..c738e764e2a5 100644 --- a/kernel/trace/trace_output.c +++ b/kernel/trace/trace_output.c @@ -656,15 +656,6 @@ int trace_print_lat_context(struct trace_iterator *iter) return !trace_seq_has_overflowed(s); } -static const char state_to_char[] = TASK_STATE_TO_CHAR_STR; - -static int task_state_char(unsigned long state) -{ - int bit = state ? __ffs(state) + 1 : 0; - - return bit < sizeof(state_to_char) - 1 ? state_to_char[bit] : '?'; -} - /** * ftrace_find_event - find a registered event * @type: the type of event to look for @@ -930,8 +921,8 @@ static enum print_line_t trace_ctxwake_print(struct trace_iterator *iter, trace_assign_type(field, iter->ent); - T = task_state_char(field->next_state); - S = task_state_char(field->prev_state); + T = __task_state_to_char(field->next_state); + S = __task_state_to_char(field->prev_state); trace_find_cmdline(field->next_pid, comm); trace_seq_printf(&iter->seq, " %5d:%3d:%c %s [%03d] %5d:%3d:%c %s\n", @@ -966,8 +957,8 @@ static int trace_ctxwake_raw(struct trace_iterator *iter, char S) trace_assign_type(field, iter->ent); if (!S) - S = task_state_char(field->prev_state); - T = task_state_char(field->next_state); + S = __task_state_to_char(field->prev_state); + T = __task_state_to_char(field->next_state); trace_seq_printf(&iter->seq, "%d %d %c %d %d %d %c\n", field->prev_pid, field->prev_prio, @@ -1002,8 +993,8 @@ static int trace_ctxwake_hex(struct trace_iterator *iter, char S) trace_assign_type(field, iter->ent); if (!S) - S = task_state_char(field->prev_state); - T = task_state_char(field->next_state); + S = __task_state_to_char(field->prev_state); + T = __task_state_to_char(field->next_state); SEQ_PUT_HEX_FIELD(s, field->prev_pid); SEQ_PUT_HEX_FIELD(s, field->prev_prio); diff --git a/kernel/trace/trace_sched_wakeup.c b/kernel/trace/trace_sched_wakeup.c index ddec53b67646..0c331978b1a6 100644 --- a/kernel/trace/trace_sched_wakeup.c +++ b/kernel/trace/trace_sched_wakeup.c @@ -397,10 +397,10 @@ tracing_sched_switch_trace(struct trace_array *tr, entry = ring_buffer_event_data(event); entry->prev_pid = prev->pid; entry->prev_prio = prev->prio; - entry->prev_state = prev->state; + entry->prev_state = __get_task_state(prev); entry->next_pid = next->pid; entry->next_prio = next->prio; - entry->next_state = next->state; + entry->next_state = __get_task_state(next); entry->next_cpu = task_cpu(next); if (!call_filter_check_discard(call, entry, buffer, event)) @@ -425,10 +425,10 @@ tracing_sched_wakeup_trace(struct trace_array *tr, entry = ring_buffer_event_data(event); entry->prev_pid = curr->pid; entry->prev_prio = curr->prio; - entry->prev_state = curr->state; + entry->prev_state = __get_task_state(curr); entry->next_pid = wakee->pid; entry->next_prio = wakee->prio; - entry->next_state = wakee->state; + entry->next_state = __get_task_state(wakee); entry->next_cpu = task_cpu(wakee); if (!call_filter_check_discard(call, entry, buffer, event)) diff --git a/kernel/trace/trace_stack.c b/kernel/trace/trace_stack.c index a4df67cbc711..49cb41412eec 100644 --- a/kernel/trace/trace_stack.c +++ b/kernel/trace/trace_stack.c @@ -96,23 +96,9 @@ check_stack(unsigned long ip, unsigned long *stack) if (in_nmi()) return; - /* - * There's a slight chance that we are tracing inside the - * RCU infrastructure, and rcu_irq_enter() will not work - * as expected. - */ - if (unlikely(rcu_irq_enter_disabled())) - return; - local_irq_save(flags); arch_spin_lock(&stack_trace_max_lock); - /* - * RCU may not be watching, make it see us. - * The stack trace code uses rcu_sched. - */ - rcu_irq_enter(); - /* In case another CPU set the tracer_frame on us */ if (unlikely(!frame_size)) this_size -= tracer_frame; @@ -205,7 +191,6 @@ check_stack(unsigned long ip, unsigned long *stack) } out: - rcu_irq_exit(); arch_spin_unlock(&stack_trace_max_lock); local_irq_restore(flags); } diff --git a/kernel/watchdog.c b/kernel/watchdog.c index f5d52024f6b7..6bcb854909c0 100644 --- a/kernel/watchdog.c +++ b/kernel/watchdog.c @@ -29,20 +29,29 @@ #include <linux/kvm_para.h> #include <linux/kthread.h> -/* Watchdog configuration */ -static DEFINE_MUTEX(watchdog_proc_mutex); - -int __read_mostly nmi_watchdog_enabled; +static DEFINE_MUTEX(watchdog_mutex); #if defined(CONFIG_HARDLOCKUP_DETECTOR) || defined(CONFIG_HAVE_NMI_WATCHDOG) -unsigned long __read_mostly watchdog_enabled = SOFT_WATCHDOG_ENABLED | - NMI_WATCHDOG_ENABLED; +# define WATCHDOG_DEFAULT (SOFT_WATCHDOG_ENABLED | NMI_WATCHDOG_ENABLED) +# define NMI_WATCHDOG_DEFAULT 1 #else -unsigned long __read_mostly watchdog_enabled = SOFT_WATCHDOG_ENABLED; +# define WATCHDOG_DEFAULT (SOFT_WATCHDOG_ENABLED) +# define NMI_WATCHDOG_DEFAULT 0 #endif +unsigned long __read_mostly watchdog_enabled; +int __read_mostly watchdog_user_enabled = 1; +int __read_mostly nmi_watchdog_user_enabled = NMI_WATCHDOG_DEFAULT; +int __read_mostly soft_watchdog_user_enabled = 1; +int __read_mostly watchdog_thresh = 10; +int __read_mostly nmi_watchdog_available; + +struct cpumask watchdog_allowed_mask __read_mostly; + +struct cpumask watchdog_cpumask __read_mostly; +unsigned long *watchdog_cpumask_bits = cpumask_bits(&watchdog_cpumask); + #ifdef CONFIG_HARDLOCKUP_DETECTOR -/* boot commands */ /* * Should we panic when a soft-lockup or hard-lockup occurs: */ @@ -56,9 +65,9 @@ unsigned int __read_mostly hardlockup_panic = * kernel command line parameters are parsed, because otherwise it is not * possible to override this in hardlockup_panic_setup(). */ -void hardlockup_detector_disable(void) +void __init hardlockup_detector_disable(void) { - watchdog_enabled &= ~NMI_WATCHDOG_ENABLED; + nmi_watchdog_user_enabled = 0; } static int __init hardlockup_panic_setup(char *str) @@ -68,48 +77,24 @@ static int __init hardlockup_panic_setup(char *str) else if (!strncmp(str, "nopanic", 7)) hardlockup_panic = 0; else if (!strncmp(str, "0", 1)) - watchdog_enabled &= ~NMI_WATCHDOG_ENABLED; + nmi_watchdog_user_enabled = 0; else if (!strncmp(str, "1", 1)) - watchdog_enabled |= NMI_WATCHDOG_ENABLED; + nmi_watchdog_user_enabled = 1; return 1; } __setup("nmi_watchdog=", hardlockup_panic_setup); -#endif - -#ifdef CONFIG_SOFTLOCKUP_DETECTOR -int __read_mostly soft_watchdog_enabled; -#endif - -int __read_mostly watchdog_user_enabled; -int __read_mostly watchdog_thresh = 10; - -#ifdef CONFIG_SMP -int __read_mostly sysctl_softlockup_all_cpu_backtrace; +# ifdef CONFIG_SMP int __read_mostly sysctl_hardlockup_all_cpu_backtrace; -#endif -struct cpumask watchdog_cpumask __read_mostly; -unsigned long *watchdog_cpumask_bits = cpumask_bits(&watchdog_cpumask); -/* - * The 'watchdog_running' variable is set to 1 when the watchdog threads - * are registered/started and is set to 0 when the watchdog threads are - * unregistered/stopped, so it is an indicator whether the threads exist. - */ -static int __read_mostly watchdog_running; -/* - * If a subsystem has a need to deactivate the watchdog temporarily, it - * can use the suspend/resume interface to achieve this. The content of - * the 'watchdog_suspended' variable reflects this state. Existing threads - * are parked/unparked by the lockup_detector_{suspend|resume} functions - * (see comment blocks pertaining to those functions for further details). - * - * 'watchdog_suspended' also prevents threads from being registered/started - * or unregistered/stopped via parameters in /proc/sys/kernel, so the state - * of 'watchdog_running' cannot change while the watchdog is deactivated - * temporarily (see related code in 'proc' handlers). - */ -int __read_mostly watchdog_suspended; +static int __init hardlockup_all_cpu_backtrace_setup(char *str) +{ + sysctl_hardlockup_all_cpu_backtrace = !!simple_strtol(str, NULL, 0); + return 1; +} +__setup("hardlockup_all_cpu_backtrace=", hardlockup_all_cpu_backtrace_setup); +# endif /* CONFIG_SMP */ +#endif /* CONFIG_HARDLOCKUP_DETECTOR */ /* * These functions can be overridden if an architecture implements its @@ -121,36 +106,68 @@ int __read_mostly watchdog_suspended; */ int __weak watchdog_nmi_enable(unsigned int cpu) { + hardlockup_detector_perf_enable(); return 0; } + void __weak watchdog_nmi_disable(unsigned int cpu) { + hardlockup_detector_perf_disable(); } -/* - * watchdog_nmi_reconfigure can be implemented to be notified after any - * watchdog configuration change. The arch hardlockup watchdog should - * respond to the following variables: - * - nmi_watchdog_enabled +/* Return 0, if a NMI watchdog is available. Error code otherwise */ +int __weak __init watchdog_nmi_probe(void) +{ + return hardlockup_detector_perf_init(); +} + +/** + * watchdog_nmi_stop - Stop the watchdog for reconfiguration + * + * The reconfiguration steps are: + * watchdog_nmi_stop(); + * update_variables(); + * watchdog_nmi_start(); + */ +void __weak watchdog_nmi_stop(void) { } + +/** + * watchdog_nmi_start - Start the watchdog after reconfiguration + * + * Counterpart to watchdog_nmi_stop(). + * + * The following variables have been updated in update_variables() and + * contain the currently valid configuration: + * - watchdog_enabled * - watchdog_thresh * - watchdog_cpumask - * - sysctl_hardlockup_all_cpu_backtrace - * - hardlockup_panic - * - watchdog_suspended */ -void __weak watchdog_nmi_reconfigure(void) +void __weak watchdog_nmi_start(void) { } + +/** + * lockup_detector_update_enable - Update the sysctl enable bit + * + * Caller needs to make sure that the NMI/perf watchdogs are off, so this + * can't race with watchdog_nmi_disable(). + */ +static void lockup_detector_update_enable(void) { + watchdog_enabled = 0; + if (!watchdog_user_enabled) + return; + if (nmi_watchdog_available && nmi_watchdog_user_enabled) + watchdog_enabled |= NMI_WATCHDOG_ENABLED; + if (soft_watchdog_user_enabled) + watchdog_enabled |= SOFT_WATCHDOG_ENABLED; } - #ifdef CONFIG_SOFTLOCKUP_DETECTOR -/* Helper for online, unparked cpus. */ -#define for_each_watchdog_cpu(cpu) \ - for_each_cpu_and((cpu), cpu_online_mask, &watchdog_cpumask) - -atomic_t watchdog_park_in_progress = ATOMIC_INIT(0); +/* Global variables, exported for sysctl */ +unsigned int __read_mostly softlockup_panic = + CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC_VALUE; +static bool softlockup_threads_initialized __read_mostly; static u64 __read_mostly sample_period; static DEFINE_PER_CPU(unsigned long, watchdog_touch_ts); @@ -164,50 +181,40 @@ static DEFINE_PER_CPU(struct task_struct *, softlockup_task_ptr_saved); static DEFINE_PER_CPU(unsigned long, hrtimer_interrupts_saved); static unsigned long soft_lockup_nmi_warn; -unsigned int __read_mostly softlockup_panic = - CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC_VALUE; - static int __init softlockup_panic_setup(char *str) { softlockup_panic = simple_strtoul(str, NULL, 0); - return 1; } __setup("softlockup_panic=", softlockup_panic_setup); static int __init nowatchdog_setup(char *str) { - watchdog_enabled = 0; + watchdog_user_enabled = 0; return 1; } __setup("nowatchdog", nowatchdog_setup); static int __init nosoftlockup_setup(char *str) { - watchdog_enabled &= ~SOFT_WATCHDOG_ENABLED; + soft_watchdog_user_enabled = 0; return 1; } __setup("nosoftlockup", nosoftlockup_setup); #ifdef CONFIG_SMP +int __read_mostly sysctl_softlockup_all_cpu_backtrace; + static int __init softlockup_all_cpu_backtrace_setup(char *str) { - sysctl_softlockup_all_cpu_backtrace = - !!simple_strtol(str, NULL, 0); + sysctl_softlockup_all_cpu_backtrace = !!simple_strtol(str, NULL, 0); return 1; } __setup("softlockup_all_cpu_backtrace=", softlockup_all_cpu_backtrace_setup); -#ifdef CONFIG_HARDLOCKUP_DETECTOR -static int __init hardlockup_all_cpu_backtrace_setup(char *str) -{ - sysctl_hardlockup_all_cpu_backtrace = - !!simple_strtol(str, NULL, 0); - return 1; -} -__setup("hardlockup_all_cpu_backtrace=", hardlockup_all_cpu_backtrace_setup); -#endif #endif +static void __lockup_detector_cleanup(void); + /* * Hard-lockup warnings should be triggered after just a few seconds. Soft- * lockups can have false positives under extreme conditions. So we generally @@ -278,11 +285,15 @@ void touch_all_softlockup_watchdogs(void) int cpu; /* - * this is done lockless - * do we care if a 0 races with a timestamp? - * all it means is the softlock check starts one cycle later + * watchdog_mutex cannpt be taken here, as this might be called + * from (soft)interrupt context, so the access to + * watchdog_allowed_cpumask might race with a concurrent update. + * + * The watchdog time stamp can race against a concurrent real + * update as well, the only side effect might be a cycle delay for + * the softlockup check. */ - for_each_watchdog_cpu(cpu) + for_each_cpu(cpu, &watchdog_allowed_mask) per_cpu(watchdog_touch_ts, cpu) = 0; wq_watchdog_touch(-1); } @@ -322,9 +333,6 @@ static void watchdog_interrupt_count(void) __this_cpu_inc(hrtimer_interrupts); } -static int watchdog_enable_all_cpus(void); -static void watchdog_disable_all_cpus(void); - /* watchdog kicker functions */ static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer) { @@ -333,7 +341,7 @@ static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer) int duration; int softlockup_all_cpu_backtrace = sysctl_softlockup_all_cpu_backtrace; - if (atomic_read(&watchdog_park_in_progress) != 0) + if (!watchdog_enabled) return HRTIMER_NORESTART; /* kick the hardlockup detector */ @@ -447,32 +455,38 @@ static void watchdog_set_prio(unsigned int policy, unsigned int prio) static void watchdog_enable(unsigned int cpu) { - struct hrtimer *hrtimer = raw_cpu_ptr(&watchdog_hrtimer); + struct hrtimer *hrtimer = this_cpu_ptr(&watchdog_hrtimer); - /* kick off the timer for the hardlockup detector */ + /* + * Start the timer first to prevent the NMI watchdog triggering + * before the timer has a chance to fire. + */ hrtimer_init(hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); hrtimer->function = watchdog_timer_fn; - - /* Enable the perf event */ - watchdog_nmi_enable(cpu); - - /* done here because hrtimer_start can only pin to smp_processor_id() */ hrtimer_start(hrtimer, ns_to_ktime(sample_period), HRTIMER_MODE_REL_PINNED); - /* initialize timestamp */ - watchdog_set_prio(SCHED_FIFO, MAX_RT_PRIO - 1); + /* Initialize timestamp */ __touch_watchdog(); + /* Enable the perf event */ + if (watchdog_enabled & NMI_WATCHDOG_ENABLED) + watchdog_nmi_enable(cpu); + + watchdog_set_prio(SCHED_FIFO, MAX_RT_PRIO - 1); } static void watchdog_disable(unsigned int cpu) { - struct hrtimer *hrtimer = raw_cpu_ptr(&watchdog_hrtimer); + struct hrtimer *hrtimer = this_cpu_ptr(&watchdog_hrtimer); watchdog_set_prio(SCHED_NORMAL, 0); - hrtimer_cancel(hrtimer); - /* disable the perf event */ + /* + * Disable the perf event first. That prevents that a large delay + * between disabling the timer and disabling the perf event causes + * the perf NMI to detect a false positive. + */ watchdog_nmi_disable(cpu); + hrtimer_cancel(hrtimer); } static void watchdog_cleanup(unsigned int cpu, bool online) @@ -499,21 +513,6 @@ static void watchdog(unsigned int cpu) __this_cpu_write(soft_lockup_hrtimer_cnt, __this_cpu_read(hrtimer_interrupts)); __touch_watchdog(); - - /* - * watchdog_nmi_enable() clears the NMI_WATCHDOG_ENABLED bit in the - * failure path. Check for failures that can occur asynchronously - - * for example, when CPUs are on-lined - and shut down the hardware - * perf event on each CPU accordingly. - * - * The only non-obvious place this bit can be cleared is through - * watchdog_nmi_enable(), so a pr_info() is placed there. Placing a - * pr_info here would be too noisy as it would result in a message - * every few seconds if the hardlockup was disabled but the softlockup - * enabled. - */ - if (!(watchdog_enabled & NMI_WATCHDOG_ENABLED)) - watchdog_nmi_disable(cpu); } static struct smp_hotplug_thread watchdog_threads = { @@ -527,295 +526,174 @@ static struct smp_hotplug_thread watchdog_threads = { .unpark = watchdog_enable, }; -/* - * park all watchdog threads that are specified in 'watchdog_cpumask' - * - * This function returns an error if kthread_park() of a watchdog thread - * fails. In this situation, the watchdog threads of some CPUs can already - * be parked and the watchdog threads of other CPUs can still be runnable. - * Callers are expected to handle this special condition as appropriate in - * their context. - * - * This function may only be called in a context that is protected against - * races with CPU hotplug - for example, via get_online_cpus(). - */ -static int watchdog_park_threads(void) +static void softlockup_update_smpboot_threads(void) { - int cpu, ret = 0; + lockdep_assert_held(&watchdog_mutex); - atomic_set(&watchdog_park_in_progress, 1); + if (!softlockup_threads_initialized) + return; - for_each_watchdog_cpu(cpu) { - ret = kthread_park(per_cpu(softlockup_watchdog, cpu)); - if (ret) - break; - } - - atomic_set(&watchdog_park_in_progress, 0); - - return ret; + smpboot_update_cpumask_percpu_thread(&watchdog_threads, + &watchdog_allowed_mask); } -/* - * unpark all watchdog threads that are specified in 'watchdog_cpumask' - * - * This function may only be called in a context that is protected against - * races with CPU hotplug - for example, via get_online_cpus(). - */ -static void watchdog_unpark_threads(void) +/* Temporarily park all watchdog threads */ +static void softlockup_park_all_threads(void) { - int cpu; - - for_each_watchdog_cpu(cpu) - kthread_unpark(per_cpu(softlockup_watchdog, cpu)); + cpumask_clear(&watchdog_allowed_mask); + softlockup_update_smpboot_threads(); } -static int update_watchdog_all_cpus(void) +/* Unpark enabled threads */ +static void softlockup_unpark_threads(void) { - int ret; - - ret = watchdog_park_threads(); - if (ret) - return ret; - - watchdog_unpark_threads(); - - return 0; + cpumask_copy(&watchdog_allowed_mask, &watchdog_cpumask); + softlockup_update_smpboot_threads(); } -static int watchdog_enable_all_cpus(void) +static void lockup_detector_reconfigure(void) { - int err = 0; - - if (!watchdog_running) { - err = smpboot_register_percpu_thread_cpumask(&watchdog_threads, - &watchdog_cpumask); - if (err) - pr_err("Failed to create watchdog threads, disabled\n"); - else - watchdog_running = 1; - } else { - /* - * Enable/disable the lockup detectors or - * change the sample period 'on the fly'. - */ - err = update_watchdog_all_cpus(); - - if (err) { - watchdog_disable_all_cpus(); - pr_err("Failed to update lockup detectors, disabled\n"); - } - } - - if (err) - watchdog_enabled = 0; - - return err; + cpus_read_lock(); + watchdog_nmi_stop(); + softlockup_park_all_threads(); + set_sample_period(); + lockup_detector_update_enable(); + if (watchdog_enabled && watchdog_thresh) + softlockup_unpark_threads(); + watchdog_nmi_start(); + cpus_read_unlock(); + /* + * Must be called outside the cpus locked section to prevent + * recursive locking in the perf code. + */ + __lockup_detector_cleanup(); } -static void watchdog_disable_all_cpus(void) +/* + * Create the watchdog thread infrastructure and configure the detector(s). + * + * The threads are not unparked as watchdog_allowed_mask is empty. When + * the threads are sucessfully initialized, take the proper locks and + * unpark the threads in the watchdog_cpumask if the watchdog is enabled. + */ +static __init void lockup_detector_setup(void) { - if (watchdog_running) { - watchdog_running = 0; - smpboot_unregister_percpu_thread(&watchdog_threads); - } -} + int ret; -#ifdef CONFIG_SYSCTL -static int watchdog_update_cpus(void) -{ - return smpboot_update_cpumask_percpu_thread( - &watchdog_threads, &watchdog_cpumask); -} -#endif + /* + * If sysctl is off and watchdog got disabled on the command line, + * nothing to do here. + */ + lockup_detector_update_enable(); -#else /* SOFTLOCKUP */ -static int watchdog_park_threads(void) -{ - return 0; -} + if (!IS_ENABLED(CONFIG_SYSCTL) && + !(watchdog_enabled && watchdog_thresh)) + return; -static void watchdog_unpark_threads(void) -{ -} + ret = smpboot_register_percpu_thread_cpumask(&watchdog_threads, + &watchdog_allowed_mask); + if (ret) { + pr_err("Failed to initialize soft lockup detector threads\n"); + return; + } -static int watchdog_enable_all_cpus(void) -{ - return 0; + mutex_lock(&watchdog_mutex); + softlockup_threads_initialized = true; + lockup_detector_reconfigure(); + mutex_unlock(&watchdog_mutex); } -static void watchdog_disable_all_cpus(void) +#else /* CONFIG_SOFTLOCKUP_DETECTOR */ +static inline int watchdog_park_threads(void) { return 0; } +static inline void watchdog_unpark_threads(void) { } +static inline int watchdog_enable_all_cpus(void) { return 0; } +static inline void watchdog_disable_all_cpus(void) { } +static void lockup_detector_reconfigure(void) { + cpus_read_lock(); + watchdog_nmi_stop(); + lockup_detector_update_enable(); + watchdog_nmi_start(); + cpus_read_unlock(); } - -#ifdef CONFIG_SYSCTL -static int watchdog_update_cpus(void) +static inline void lockup_detector_setup(void) { - return 0; + lockup_detector_reconfigure(); } -#endif +#endif /* !CONFIG_SOFTLOCKUP_DETECTOR */ -static void set_sample_period(void) +static void __lockup_detector_cleanup(void) { + lockdep_assert_held(&watchdog_mutex); + hardlockup_detector_perf_cleanup(); } -#endif /* SOFTLOCKUP */ -/* - * Suspend the hard and soft lockup detector by parking the watchdog threads. +/** + * lockup_detector_cleanup - Cleanup after cpu hotplug or sysctl changes + * + * Caller must not hold the cpu hotplug rwsem. */ -int lockup_detector_suspend(void) +void lockup_detector_cleanup(void) { - int ret = 0; - - get_online_cpus(); - mutex_lock(&watchdog_proc_mutex); - /* - * Multiple suspend requests can be active in parallel (counted by - * the 'watchdog_suspended' variable). If the watchdog threads are - * running, the first caller takes care that they will be parked. - * The state of 'watchdog_running' cannot change while a suspend - * request is active (see related code in 'proc' handlers). - */ - if (watchdog_running && !watchdog_suspended) - ret = watchdog_park_threads(); - - if (ret == 0) - watchdog_suspended++; - else { - watchdog_disable_all_cpus(); - pr_err("Failed to suspend lockup detectors, disabled\n"); - watchdog_enabled = 0; - } - - watchdog_nmi_reconfigure(); - - mutex_unlock(&watchdog_proc_mutex); - - return ret; + mutex_lock(&watchdog_mutex); + __lockup_detector_cleanup(); + mutex_unlock(&watchdog_mutex); } -/* - * Resume the hard and soft lockup detector by unparking the watchdog threads. +/** + * lockup_detector_soft_poweroff - Interface to stop lockup detector(s) + * + * Special interface for parisc. It prevents lockup detector warnings from + * the default pm_poweroff() function which busy loops forever. */ -void lockup_detector_resume(void) +void lockup_detector_soft_poweroff(void) { - mutex_lock(&watchdog_proc_mutex); - - watchdog_suspended--; - /* - * The watchdog threads are unparked if they were previously running - * and if there is no more active suspend request. - */ - if (watchdog_running && !watchdog_suspended) - watchdog_unpark_threads(); - - watchdog_nmi_reconfigure(); - - mutex_unlock(&watchdog_proc_mutex); - put_online_cpus(); + watchdog_enabled = 0; } #ifdef CONFIG_SYSCTL -/* - * Update the run state of the lockup detectors. - */ -static int proc_watchdog_update(void) +/* Propagate any changes to the watchdog threads */ +static void proc_watchdog_update(void) { - int err = 0; - - /* - * Watchdog threads won't be started if they are already active. - * The 'watchdog_running' variable in watchdog_*_all_cpus() takes - * care of this. If those threads are already active, the sample - * period will be updated and the lockup detectors will be enabled - * or disabled 'on the fly'. - */ - if (watchdog_enabled && watchdog_thresh) - err = watchdog_enable_all_cpus(); - else - watchdog_disable_all_cpus(); - - watchdog_nmi_reconfigure(); - - return err; - + /* Remove impossible cpus to keep sysctl output clean. */ + cpumask_and(&watchdog_cpumask, &watchdog_cpumask, cpu_possible_mask); + lockup_detector_reconfigure(); } /* * common function for watchdog, nmi_watchdog and soft_watchdog parameter * - * caller | table->data points to | 'which' contains the flag(s) - * -------------------|-----------------------|----------------------------- - * proc_watchdog | watchdog_user_enabled | NMI_WATCHDOG_ENABLED or'ed - * | | with SOFT_WATCHDOG_ENABLED - * -------------------|-----------------------|----------------------------- - * proc_nmi_watchdog | nmi_watchdog_enabled | NMI_WATCHDOG_ENABLED - * -------------------|-----------------------|----------------------------- - * proc_soft_watchdog | soft_watchdog_enabled | SOFT_WATCHDOG_ENABLED + * caller | table->data points to | 'which' + * -------------------|----------------------------|-------------------------- + * proc_watchdog | watchdog_user_enabled | NMI_WATCHDOG_ENABLED | + * | | SOFT_WATCHDOG_ENABLED + * -------------------|----------------------------|-------------------------- + * proc_nmi_watchdog | nmi_watchdog_user_enabled | NMI_WATCHDOG_ENABLED + * -------------------|----------------------------|-------------------------- + * proc_soft_watchdog | soft_watchdog_user_enabled | SOFT_WATCHDOG_ENABLED */ static int proc_watchdog_common(int which, struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { - int err, old, new; - int *watchdog_param = (int *)table->data; + int err, old, *param = table->data; - get_online_cpus(); - mutex_lock(&watchdog_proc_mutex); + mutex_lock(&watchdog_mutex); - if (watchdog_suspended) { - /* no parameter changes allowed while watchdog is suspended */ - err = -EAGAIN; - goto out; - } - - /* - * If the parameter is being read return the state of the corresponding - * bit(s) in 'watchdog_enabled', else update 'watchdog_enabled' and the - * run state of the lockup detectors. - */ if (!write) { - *watchdog_param = (watchdog_enabled & which) != 0; + /* + * On read synchronize the userspace interface. This is a + * racy snapshot. + */ + *param = (watchdog_enabled & which) != 0; err = proc_dointvec_minmax(table, write, buffer, lenp, ppos); } else { + old = READ_ONCE(*param); err = proc_dointvec_minmax(table, write, buffer, lenp, ppos); - if (err) - goto out; - - /* - * There is a race window between fetching the current value - * from 'watchdog_enabled' and storing the new value. During - * this race window, watchdog_nmi_enable() can sneak in and - * clear the NMI_WATCHDOG_ENABLED bit in 'watchdog_enabled'. - * The 'cmpxchg' detects this race and the loop retries. - */ - do { - old = watchdog_enabled; - /* - * If the parameter value is not zero set the - * corresponding bit(s), else clear it(them). - */ - if (*watchdog_param) - new = old | which; - else - new = old & ~which; - } while (cmpxchg(&watchdog_enabled, old, new) != old); - - /* - * Update the run state of the lockup detectors. There is _no_ - * need to check the value returned by proc_watchdog_update() - * and to restore the previous value of 'watchdog_enabled' as - * both lockup detectors are disabled if proc_watchdog_update() - * returns an error. - */ - if (old == new) - goto out; - - err = proc_watchdog_update(); + if (!err && old != READ_ONCE(*param)) + proc_watchdog_update(); } -out: - mutex_unlock(&watchdog_proc_mutex); - put_online_cpus(); + mutex_unlock(&watchdog_mutex); return err; } @@ -835,6 +713,8 @@ int proc_watchdog(struct ctl_table *table, int write, int proc_nmi_watchdog(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { + if (!nmi_watchdog_available && write) + return -ENOTSUPP; return proc_watchdog_common(NMI_WATCHDOG_ENABLED, table, write, buffer, lenp, ppos); } @@ -855,39 +735,17 @@ int proc_soft_watchdog(struct ctl_table *table, int write, int proc_watchdog_thresh(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { - int err, old, new; - - get_online_cpus(); - mutex_lock(&watchdog_proc_mutex); + int err, old; - if (watchdog_suspended) { - /* no parameter changes allowed while watchdog is suspended */ - err = -EAGAIN; - goto out; - } + mutex_lock(&watchdog_mutex); - old = ACCESS_ONCE(watchdog_thresh); + old = READ_ONCE(watchdog_thresh); err = proc_dointvec_minmax(table, write, buffer, lenp, ppos); - if (err || !write) - goto out; - - /* - * Update the sample period. Restore on failure. - */ - new = ACCESS_ONCE(watchdog_thresh); - if (old == new) - goto out; + if (!err && write && old != READ_ONCE(watchdog_thresh)) + proc_watchdog_update(); - set_sample_period(); - err = proc_watchdog_update(); - if (err) { - watchdog_thresh = old; - set_sample_period(); - } -out: - mutex_unlock(&watchdog_proc_mutex); - put_online_cpus(); + mutex_unlock(&watchdog_mutex); return err; } @@ -902,45 +760,19 @@ int proc_watchdog_cpumask(struct ctl_table *table, int write, { int err; - get_online_cpus(); - mutex_lock(&watchdog_proc_mutex); - - if (watchdog_suspended) { - /* no parameter changes allowed while watchdog is suspended */ - err = -EAGAIN; - goto out; - } + mutex_lock(&watchdog_mutex); err = proc_do_large_bitmap(table, write, buffer, lenp, ppos); - if (!err && write) { - /* Remove impossible cpus to keep sysctl output cleaner. */ - cpumask_and(&watchdog_cpumask, &watchdog_cpumask, - cpu_possible_mask); - - if (watchdog_running) { - /* - * Failure would be due to being unable to allocate - * a temporary cpumask, so we are likely not in a - * position to do much else to make things better. - */ - if (watchdog_update_cpus() != 0) - pr_err("cpumask update failed\n"); - } + if (!err && write) + proc_watchdog_update(); - watchdog_nmi_reconfigure(); - } -out: - mutex_unlock(&watchdog_proc_mutex); - put_online_cpus(); + mutex_unlock(&watchdog_mutex); return err; } - #endif /* CONFIG_SYSCTL */ void __init lockup_detector_init(void) { - set_sample_period(); - #ifdef CONFIG_NO_HZ_FULL if (tick_nohz_full_enabled()) { pr_info("Disabling watchdog on nohz_full cores by default\n"); @@ -951,6 +783,7 @@ void __init lockup_detector_init(void) cpumask_copy(&watchdog_cpumask, cpu_possible_mask); #endif - if (watchdog_enabled) - watchdog_enable_all_cpus(); + if (!watchdog_nmi_probe()) + nmi_watchdog_available = true; + lockup_detector_setup(); } diff --git a/kernel/watchdog_hld.c b/kernel/watchdog_hld.c index 3a09ea1b1d3d..71a62ceacdc8 100644 --- a/kernel/watchdog_hld.c +++ b/kernel/watchdog_hld.c @@ -21,8 +21,10 @@ static DEFINE_PER_CPU(bool, hard_watchdog_warn); static DEFINE_PER_CPU(bool, watchdog_nmi_touch); static DEFINE_PER_CPU(struct perf_event *, watchdog_ev); +static struct cpumask dead_events_mask; static unsigned long hardlockup_allcpu_dumped; +static unsigned int watchdog_cpus; void arch_touch_nmi_watchdog(void) { @@ -103,15 +105,12 @@ static struct perf_event_attr wd_hw_attr = { /* Callback function for perf event subsystem */ static void watchdog_overflow_callback(struct perf_event *event, - struct perf_sample_data *data, - struct pt_regs *regs) + struct perf_sample_data *data, + struct pt_regs *regs) { /* Ensure the watchdog never gets throttled */ event->hw.interrupts = 0; - if (atomic_read(&watchdog_park_in_progress) != 0) - return; - if (__this_cpu_read(watchdog_nmi_touch) == true) { __this_cpu_write(watchdog_nmi_touch, false); return; @@ -160,104 +159,131 @@ static void watchdog_overflow_callback(struct perf_event *event, return; } -/* - * People like the simple clean cpu node info on boot. - * Reduce the watchdog noise by only printing messages - * that are different from what cpu0 displayed. - */ -static unsigned long firstcpu_err; -static atomic_t watchdog_cpus; - -int watchdog_nmi_enable(unsigned int cpu) +static int hardlockup_detector_event_create(void) { + unsigned int cpu = smp_processor_id(); struct perf_event_attr *wd_attr; - struct perf_event *event = per_cpu(watchdog_ev, cpu); - int firstcpu = 0; - - /* nothing to do if the hard lockup detector is disabled */ - if (!(watchdog_enabled & NMI_WATCHDOG_ENABLED)) - goto out; - - /* is it already setup and enabled? */ - if (event && event->state > PERF_EVENT_STATE_OFF) - goto out; - - /* it is setup but not enabled */ - if (event != NULL) - goto out_enable; - - if (atomic_inc_return(&watchdog_cpus) == 1) - firstcpu = 1; + struct perf_event *evt; wd_attr = &wd_hw_attr; wd_attr->sample_period = hw_nmi_get_sample_period(watchdog_thresh); /* Try to register using hardware perf events */ - event = perf_event_create_kernel_counter(wd_attr, cpu, NULL, watchdog_overflow_callback, NULL); + evt = perf_event_create_kernel_counter(wd_attr, cpu, NULL, + watchdog_overflow_callback, NULL); + if (IS_ERR(evt)) { + pr_info("Perf event create on CPU %d failed with %ld\n", cpu, + PTR_ERR(evt)); + return PTR_ERR(evt); + } + this_cpu_write(watchdog_ev, evt); + return 0; +} - /* save the first cpu's error for future comparision */ - if (firstcpu && IS_ERR(event)) - firstcpu_err = PTR_ERR(event); +/** + * hardlockup_detector_perf_enable - Enable the local event + */ +void hardlockup_detector_perf_enable(void) +{ + if (hardlockup_detector_event_create()) + return; - if (!IS_ERR(event)) { - /* only print for the first cpu initialized */ - if (firstcpu || firstcpu_err) - pr_info("enabled on all CPUs, permanently consumes one hw-PMU counter.\n"); - goto out_save; - } + if (!watchdog_cpus++) + pr_info("Enabled. Permanently consumes one hw-PMU counter.\n"); - /* - * Disable the hard lockup detector if _any_ CPU fails to set up - * set up the hardware perf event. The watchdog() function checks - * the NMI_WATCHDOG_ENABLED bit periodically. - * - * The barriers are for syncing up watchdog_enabled across all the - * cpus, as clear_bit() does not use barriers. - */ - smp_mb__before_atomic(); - clear_bit(NMI_WATCHDOG_ENABLED_BIT, &watchdog_enabled); - smp_mb__after_atomic(); - - /* skip displaying the same error again */ - if (!firstcpu && (PTR_ERR(event) == firstcpu_err)) - return PTR_ERR(event); - - /* vary the KERN level based on the returned errno */ - if (PTR_ERR(event) == -EOPNOTSUPP) - pr_info("disabled (cpu%i): not supported (no LAPIC?)\n", cpu); - else if (PTR_ERR(event) == -ENOENT) - pr_warn("disabled (cpu%i): hardware events not enabled\n", - cpu); - else - pr_err("disabled (cpu%i): unable to create perf event: %ld\n", - cpu, PTR_ERR(event)); - - pr_info("Shutting down hard lockup detector on all cpus\n"); - - return PTR_ERR(event); - - /* success path */ -out_save: - per_cpu(watchdog_ev, cpu) = event; -out_enable: - perf_event_enable(per_cpu(watchdog_ev, cpu)); -out: - return 0; + perf_event_enable(this_cpu_read(watchdog_ev)); } -void watchdog_nmi_disable(unsigned int cpu) +/** + * hardlockup_detector_perf_disable - Disable the local event + */ +void hardlockup_detector_perf_disable(void) { - struct perf_event *event = per_cpu(watchdog_ev, cpu); + struct perf_event *event = this_cpu_read(watchdog_ev); if (event) { perf_event_disable(event); + cpumask_set_cpu(smp_processor_id(), &dead_events_mask); + watchdog_cpus--; + } +} + +/** + * hardlockup_detector_perf_cleanup - Cleanup disabled events and destroy them + * + * Called from lockup_detector_cleanup(). Serialized by the caller. + */ +void hardlockup_detector_perf_cleanup(void) +{ + int cpu; + + for_each_cpu(cpu, &dead_events_mask) { + struct perf_event *event = per_cpu(watchdog_ev, cpu); + + /* + * Required because for_each_cpu() reports unconditionally + * CPU0 as set on UP kernels. Sigh. + */ + if (event) + perf_event_release_kernel(event); per_cpu(watchdog_ev, cpu) = NULL; + } + cpumask_clear(&dead_events_mask); +} + +/** + * hardlockup_detector_perf_stop - Globally stop watchdog events + * + * Special interface for x86 to handle the perf HT bug. + */ +void __init hardlockup_detector_perf_stop(void) +{ + int cpu; + + lockdep_assert_cpus_held(); + + for_each_online_cpu(cpu) { + struct perf_event *event = per_cpu(watchdog_ev, cpu); + + if (event) + perf_event_disable(event); + } +} - /* should be in cleanup, but blocks oprofile */ - perf_event_release_kernel(event); +/** + * hardlockup_detector_perf_restart - Globally restart watchdog events + * + * Special interface for x86 to handle the perf HT bug. + */ +void __init hardlockup_detector_perf_restart(void) +{ + int cpu; + + lockdep_assert_cpus_held(); + + if (!(watchdog_enabled & NMI_WATCHDOG_ENABLED)) + return; + + for_each_online_cpu(cpu) { + struct perf_event *event = per_cpu(watchdog_ev, cpu); + + if (event) + perf_event_enable(event); + } +} + +/** + * hardlockup_detector_perf_init - Probe whether NMI event is available at all + */ +int __init hardlockup_detector_perf_init(void) +{ + int ret = hardlockup_detector_event_create(); - /* watchdog_nmi_enable() expects this to be zero initially. */ - if (atomic_dec_and_test(&watchdog_cpus)) - firstcpu_err = 0; + if (ret) { + pr_info("Perf NMI watchdog permanently disabled\n"); + } else { + perf_event_release_kernel(this_cpu_read(watchdog_ev)); + this_cpu_write(watchdog_ev, NULL); } + return ret; } diff --git a/lib/idr.c b/lib/idr.c index f9adf4805fd7..edd9b2be1651 100644 --- a/lib/idr.c +++ b/lib/idr.c @@ -146,8 +146,8 @@ EXPORT_SYMBOL(idr_get_next_ext); * idr_alloc() and idr_remove() (as long as the ID being removed is not * the one being replaced!). * - * Returns: 0 on success. %-ENOENT indicates that @id was not found. - * %-EINVAL indicates that @id or @ptr were not valid. + * Returns: the old value on success. %-ENOENT indicates that @id was not + * found. %-EINVAL indicates that @id or @ptr were not valid. */ void *idr_replace(struct idr *idr, void *ptr, int id) { diff --git a/lib/kobject_uevent.c b/lib/kobject_uevent.c index e590523ea476..f237a09a5862 100644 --- a/lib/kobject_uevent.c +++ b/lib/kobject_uevent.c @@ -294,6 +294,26 @@ static void cleanup_uevent_env(struct subprocess_info *info) } #endif +static void zap_modalias_env(struct kobj_uevent_env *env) +{ + static const char modalias_prefix[] = "MODALIAS="; + int i; + + for (i = 0; i < env->envp_idx;) { + if (strncmp(env->envp[i], modalias_prefix, + sizeof(modalias_prefix) - 1)) { + i++; + continue; + } + + if (i != env->envp_idx - 1) + memmove(&env->envp[i], &env->envp[i + 1], + sizeof(env->envp[i]) * env->envp_idx - 1); + + env->envp_idx--; + } +} + /** * kobject_uevent_env - send an uevent with environmental data * @@ -409,16 +429,29 @@ int kobject_uevent_env(struct kobject *kobj, enum kobject_action action, } } - /* - * Mark "add" and "remove" events in the object to ensure proper - * events to userspace during automatic cleanup. If the object did - * send an "add" event, "remove" will automatically generated by - * the core, if not already done by the caller. - */ - if (action == KOBJ_ADD) + switch (action) { + case KOBJ_ADD: + /* + * Mark "add" event so we can make sure we deliver "remove" + * event to userspace during automatic cleanup. If + * the object did send an "add" event, "remove" will + * automatically generated by the core, if not already done + * by the caller. + */ kobj->state_add_uevent_sent = 1; - else if (action == KOBJ_REMOVE) + break; + + case KOBJ_REMOVE: kobj->state_remove_uevent_sent = 1; + break; + + case KOBJ_UNBIND: + zap_modalias_env(env); + break; + + default: + break; + } mutex_lock(&uevent_sock_mutex); /* we will send an event, so request a new sequence number */ diff --git a/lib/lz4/lz4_decompress.c b/lib/lz4/lz4_decompress.c index bd3574312b82..141734d255e4 100644 --- a/lib/lz4/lz4_decompress.c +++ b/lib/lz4/lz4_decompress.c @@ -85,8 +85,8 @@ static FORCE_INLINE int LZ4_decompress_generic( const BYTE * const lowLimit = lowPrefix - dictSize; const BYTE * const dictEnd = (const BYTE *)dictStart + dictSize; - const unsigned int dec32table[] = { 0, 1, 2, 1, 4, 4, 4, 4 }; - const int dec64table[] = { 0, 0, 0, -1, 0, 1, 2, 3 }; + static const unsigned int dec32table[] = { 0, 1, 2, 1, 4, 4, 4, 4 }; + static const int dec64table[] = { 0, 0, 0, -1, 0, 1, 2, 3 }; const int safeDecode = (endOnInput == endOnInputSize); const int checkOffset = ((safeDecode) && (dictSize < (int)(64 * KB))); diff --git a/lib/ratelimit.c b/lib/ratelimit.c index 08f8043cac61..d01f47135239 100644 --- a/lib/ratelimit.c +++ b/lib/ratelimit.c @@ -48,7 +48,9 @@ int ___ratelimit(struct ratelimit_state *rs, const char *func) if (time_is_before_jiffies(rs->begin + rs->interval)) { if (rs->missed) { if (!(rs->flags & RATELIMIT_MSG_ON_RELEASE)) { - pr_warn("%s: %d callbacks suppressed\n", func, rs->missed); + printk_deferred(KERN_WARNING + "%s: %d callbacks suppressed\n", + func, rs->missed); rs->missed = 0; } } diff --git a/mm/compaction.c b/mm/compaction.c index fb548e4c7bd4..03d31a875341 100644 --- a/mm/compaction.c +++ b/mm/compaction.c @@ -1999,17 +1999,14 @@ void wakeup_kcompactd(pg_data_t *pgdat, int order, int classzone_idx) if (pgdat->kcompactd_max_order < order) pgdat->kcompactd_max_order = order; - /* - * Pairs with implicit barrier in wait_event_freezable() - * such that wakeups are not missed in the lockless - * waitqueue_active() call. - */ - smp_acquire__after_ctrl_dep(); - if (pgdat->kcompactd_classzone_idx > classzone_idx) pgdat->kcompactd_classzone_idx = classzone_idx; - if (!waitqueue_active(&pgdat->kcompactd_wait)) + /* + * Pairs with implicit barrier in wait_event_freezable() + * such that wakeups are not missed. + */ + if (!wq_has_sleeper(&pgdat->kcompactd_wait)) return; if (!kcompactd_node_suitable(pgdat)) diff --git a/mm/filemap.c b/mm/filemap.c index 870971e20967..594d73fef8b4 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -620,6 +620,14 @@ int file_check_and_advance_wb_err(struct file *file) trace_file_check_and_advance_wb_err(file, old); spin_unlock(&file->f_lock); } + + /* + * We're mostly using this function as a drop in replacement for + * filemap_check_errors. Clear AS_EIO/AS_ENOSPC to emulate the effect + * that the legacy code would have had on these flags. + */ + clear_bit(AS_EIO, &mapping->flags); + clear_bit(AS_ENOSPC, &mapping->flags); return err; } EXPORT_SYMBOL(file_check_and_advance_wb_err); @@ -2926,9 +2934,15 @@ generic_file_direct_write(struct kiocb *iocb, struct iov_iter *from) * we're writing. Either one is a pretty crazy thing to do, * so we don't support it 100%. If this invalidation * fails, tough, the write still worked... + * + * Most of the time we do not need this since dio_complete() will do + * the invalidation for us. However there are some file systems that + * do not end up with dio_complete() being called, so let's not break + * them by removing it completely */ - invalidate_inode_pages2_range(mapping, - pos >> PAGE_SHIFT, end); + if (mapping->nrpages) + invalidate_inode_pages2_range(mapping, + pos >> PAGE_SHIFT, end); if (written > 0) { pos += written; @@ -1990,6 +1990,7 @@ static void stable_tree_append(struct rmap_item *rmap_item, */ static void cmp_and_merge_page(struct page *page, struct rmap_item *rmap_item) { + struct mm_struct *mm = rmap_item->mm; struct rmap_item *tree_rmap_item; struct page *tree_page = NULL; struct stable_node *stable_node; @@ -2062,9 +2063,11 @@ static void cmp_and_merge_page(struct page *page, struct rmap_item *rmap_item) if (ksm_use_zero_pages && (checksum == zero_checksum)) { struct vm_area_struct *vma; - vma = find_mergeable_vma(rmap_item->mm, rmap_item->address); + down_read(&mm->mmap_sem); + vma = find_mergeable_vma(mm, rmap_item->address); err = try_to_merge_one_page(vma, page, ZERO_PAGE(rmap_item->address)); + up_read(&mm->mmap_sem); /* * In case of failure, the page was not really empty, so we * need to continue. Otherwise we're done. diff --git a/mm/list_lru.c b/mm/list_lru.c index 7a40fa2be858..f141f0c80ff3 100644 --- a/mm/list_lru.c +++ b/mm/list_lru.c @@ -325,12 +325,12 @@ static int memcg_init_list_lru_node(struct list_lru_node *nlru) { int size = memcg_nr_cache_ids; - nlru->memcg_lrus = kmalloc(size * sizeof(void *), GFP_KERNEL); + nlru->memcg_lrus = kvmalloc(size * sizeof(void *), GFP_KERNEL); if (!nlru->memcg_lrus) return -ENOMEM; if (__memcg_init_list_lru_node(nlru->memcg_lrus, 0, size)) { - kfree(nlru->memcg_lrus); + kvfree(nlru->memcg_lrus); return -ENOMEM; } @@ -340,7 +340,7 @@ static int memcg_init_list_lru_node(struct list_lru_node *nlru) static void memcg_destroy_list_lru_node(struct list_lru_node *nlru) { __memcg_destroy_list_lru_node(nlru->memcg_lrus, 0, memcg_nr_cache_ids); - kfree(nlru->memcg_lrus); + kvfree(nlru->memcg_lrus); } static int memcg_update_list_lru_node(struct list_lru_node *nlru, @@ -351,12 +351,12 @@ static int memcg_update_list_lru_node(struct list_lru_node *nlru, BUG_ON(old_size > new_size); old = nlru->memcg_lrus; - new = kmalloc(new_size * sizeof(void *), GFP_KERNEL); + new = kvmalloc(new_size * sizeof(void *), GFP_KERNEL); if (!new) return -ENOMEM; if (__memcg_init_list_lru_node(new, old_size, new_size)) { - kfree(new); + kvfree(new); return -ENOMEM; } @@ -373,7 +373,7 @@ static int memcg_update_list_lru_node(struct list_lru_node *nlru, nlru->memcg_lrus = new; spin_unlock_irq(&nlru->lock); - kfree(old); + kvfree(old); return 0; } diff --git a/mm/madvise.c b/mm/madvise.c index 21261ff0466f..25bade36e9ca 100644 --- a/mm/madvise.c +++ b/mm/madvise.c @@ -625,18 +625,26 @@ static int madvise_inject_error(int behavior, { struct page *page; struct zone *zone; + unsigned int order; if (!capable(CAP_SYS_ADMIN)) return -EPERM; - for (; start < end; start += PAGE_SIZE << - compound_order(compound_head(page))) { + + for (; start < end; start += PAGE_SIZE << order) { int ret; ret = get_user_pages_fast(start, 1, 0, &page); if (ret != 1) return ret; + /* + * When soft offlining hugepages, after migrating the page + * we dissolve it, therefore in the second loop "page" will + * no longer be a compound page, and order will be 0. + */ + order = compound_order(compound_head(page)); + if (PageHWPoison(page)) { put_page(page); continue; diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 15af3da5af02..d5f3a62887cf 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -1777,6 +1777,10 @@ static void drain_local_stock(struct work_struct *dummy) struct memcg_stock_pcp *stock; unsigned long flags; + /* + * The only protection from memory hotplug vs. drain_stock races is + * that we always operate on local CPU stock here with IRQ disabled + */ local_irq_save(flags); stock = this_cpu_ptr(&memcg_stock); @@ -1821,27 +1825,33 @@ static void drain_all_stock(struct mem_cgroup *root_memcg) /* If someone's already draining, avoid adding running more workers. */ if (!mutex_trylock(&percpu_charge_mutex)) return; - /* Notify other cpus that system-wide "drain" is running */ - get_online_cpus(); + /* + * Notify other cpus that system-wide "drain" is running + * We do not care about races with the cpu hotplug because cpu down + * as well as workers from this path always operate on the local + * per-cpu data. CPU up doesn't touch memcg_stock at all. + */ curcpu = get_cpu(); for_each_online_cpu(cpu) { struct memcg_stock_pcp *stock = &per_cpu(memcg_stock, cpu); struct mem_cgroup *memcg; memcg = stock->cached; - if (!memcg || !stock->nr_pages) + if (!memcg || !stock->nr_pages || !css_tryget(&memcg->css)) continue; - if (!mem_cgroup_is_descendant(memcg, root_memcg)) + if (!mem_cgroup_is_descendant(memcg, root_memcg)) { + css_put(&memcg->css); continue; + } if (!test_and_set_bit(FLUSHING_CACHED_CHARGE, &stock->flags)) { if (cpu == curcpu) drain_local_stock(&stock->work); else schedule_work_on(cpu, &stock->work); } + css_put(&memcg->css); } put_cpu(); - put_online_cpus(); mutex_unlock(&percpu_charge_mutex); } @@ -5648,7 +5658,8 @@ static void uncharge_batch(const struct uncharge_gather *ug) static void uncharge_page(struct page *page, struct uncharge_gather *ug) { VM_BUG_ON_PAGE(PageLRU(page), page); - VM_BUG_ON_PAGE(!PageHWPoison(page) && page_count(page), page); + VM_BUG_ON_PAGE(page_count(page) && !is_zone_device_page(page) && + !PageHWPoison(page) , page); if (!page->mem_cgroup) return; diff --git a/mm/memory.c b/mm/memory.c index ec4e15494901..a728bed16c20 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -845,7 +845,7 @@ struct page *_vm_normal_page(struct vm_area_struct *vma, unsigned long addr, * vm_normal_page() so that we do not have to special case all * call site of vm_normal_page(). */ - if (likely(pfn < highest_memmap_pfn)) { + if (likely(pfn <= highest_memmap_pfn)) { struct page *page = pfn_to_page(pfn); if (is_device_public_page(page)) { diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index e882cb6da994..d4b5f29906b9 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -328,6 +328,7 @@ int __ref __add_pages(int nid, unsigned long phys_start_pfn, if (err && (err != -EEXIST)) break; err = 0; + cond_resched(); } vmemmap_populate_print_last(); out: @@ -337,7 +338,7 @@ EXPORT_SYMBOL_GPL(__add_pages); #ifdef CONFIG_MEMORY_HOTREMOVE /* find the smallest valid pfn in the range [start_pfn, end_pfn) */ -static int find_smallest_section_pfn(int nid, struct zone *zone, +static unsigned long find_smallest_section_pfn(int nid, struct zone *zone, unsigned long start_pfn, unsigned long end_pfn) { @@ -362,7 +363,7 @@ static int find_smallest_section_pfn(int nid, struct zone *zone, } /* find the biggest valid pfn in the range [start_pfn, end_pfn). */ -static int find_biggest_section_pfn(int nid, struct zone *zone, +static unsigned long find_biggest_section_pfn(int nid, struct zone *zone, unsigned long start_pfn, unsigned long end_pfn) { @@ -550,7 +551,7 @@ static int __remove_section(struct zone *zone, struct mem_section *ms, return ret; scn_nr = __section_nr(ms); - start_pfn = section_nr_to_pfn(scn_nr); + start_pfn = section_nr_to_pfn((unsigned long)scn_nr); __remove_zone(zone, start_pfn); sparse_remove_one_section(zone, ms, map_offset); diff --git a/mm/oom_kill.c b/mm/oom_kill.c index 99736e026712..dee0f75c3013 100644 --- a/mm/oom_kill.c +++ b/mm/oom_kill.c @@ -40,6 +40,7 @@ #include <linux/ratelimit.h> #include <linux/kthread.h> #include <linux/init.h> +#include <linux/mmu_notifier.h> #include <asm/tlb.h> #include "internal.h" @@ -495,6 +496,21 @@ static bool __oom_reap_task_mm(struct task_struct *tsk, struct mm_struct *mm) } /* + * If the mm has notifiers then we would need to invalidate them around + * unmap_page_range and that is risky because notifiers can sleep and + * what they do is basically undeterministic. So let's have a short + * sleep to give the oom victim some more time. + * TODO: we really want to get rid of this ugly hack and make sure that + * notifiers cannot block for unbounded amount of time and add + * mmu_notifier_invalidate_range_{start,end} around unmap_page_range + */ + if (mm_has_notifiers(mm)) { + up_read(&mm->mmap_sem); + schedule_timeout_idle(HZ); + goto unlock_oom; + } + + /* * MMF_OOM_SKIP is set by exit_mmap when the OOM reaper can't * work on the mm anymore. The check for MMF_OOM_SKIP must run * under mmap_sem for reading because it serializes against the diff --git a/mm/page_alloc.c b/mm/page_alloc.c index c841af88836a..77e4d3c5c57b 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -1190,7 +1190,7 @@ static void __meminit __init_single_pfn(unsigned long pfn, unsigned long zone, } #ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT -static void init_reserved_page(unsigned long pfn) +static void __meminit init_reserved_page(unsigned long pfn) { pg_data_t *pgdat; int nid, zid; @@ -5367,6 +5367,7 @@ not_early: __init_single_page(page, pfn, zone, nid); set_pageblock_migratetype(page, MIGRATE_MOVABLE); + cond_resched(); } else { __init_single_pfn(pfn, zone, nid); } diff --git a/mm/percpu-stats.c b/mm/percpu-stats.c index 6142484e88f7..7a58460bfd27 100644 --- a/mm/percpu-stats.c +++ b/mm/percpu-stats.c @@ -73,7 +73,7 @@ static void chunk_map_stats(struct seq_file *m, struct pcpu_chunk *chunk, last_alloc + 1 : 0; as_len = 0; - start = chunk->start_offset; + start = chunk->start_offset / PCPU_MIN_ALLOC_SIZE; /* * If a bit is set in the allocation map, the bound_map identifies diff --git a/mm/percpu.c b/mm/percpu.c index 59d44d61f5f1..aa121cef76de 100644 --- a/mm/percpu.c +++ b/mm/percpu.c @@ -353,6 +353,8 @@ static void pcpu_next_md_free_region(struct pcpu_chunk *chunk, int *bit_off, block->contig_hint_start); return; } + /* reset to satisfy the second predicate above */ + block_off = 0; *bits = block->right_free; *bit_off = (i + 1) * PCPU_BITMAP_BLOCK_BITS - block->right_free; @@ -407,6 +409,8 @@ static void pcpu_next_fit_region(struct pcpu_chunk *chunk, int alloc_bits, *bit_off = pcpu_block_off_to_off(i, block->first_free); return; } + /* reset to satisfy the second predicate above */ + block_off = 0; *bit_off = ALIGN(PCPU_BITMAP_BLOCK_BITS - block->right_free, align); diff --git a/mm/rodata_test.c b/mm/rodata_test.c index 6bb4deb12e78..d908c8769b48 100644 --- a/mm/rodata_test.c +++ b/mm/rodata_test.c @@ -14,7 +14,7 @@ #include <linux/uaccess.h> #include <asm/sections.h> -const int rodata_test_data = 0xC3; +static const int rodata_test_data = 0xC3; void rodata_test(void) { diff --git a/mm/slab_common.c b/mm/slab_common.c index 904a83be82de..80164599ca5d 100644 --- a/mm/slab_common.c +++ b/mm/slab_common.c @@ -165,9 +165,9 @@ static int init_memcg_params(struct kmem_cache *s, if (!memcg_nr_cache_ids) return 0; - arr = kzalloc(sizeof(struct memcg_cache_array) + - memcg_nr_cache_ids * sizeof(void *), - GFP_KERNEL); + arr = kvzalloc(sizeof(struct memcg_cache_array) + + memcg_nr_cache_ids * sizeof(void *), + GFP_KERNEL); if (!arr) return -ENOMEM; @@ -178,15 +178,23 @@ static int init_memcg_params(struct kmem_cache *s, static void destroy_memcg_params(struct kmem_cache *s) { if (is_root_cache(s)) - kfree(rcu_access_pointer(s->memcg_params.memcg_caches)); + kvfree(rcu_access_pointer(s->memcg_params.memcg_caches)); +} + +static void free_memcg_params(struct rcu_head *rcu) +{ + struct memcg_cache_array *old; + + old = container_of(rcu, struct memcg_cache_array, rcu); + kvfree(old); } static int update_memcg_params(struct kmem_cache *s, int new_array_size) { struct memcg_cache_array *old, *new; - new = kzalloc(sizeof(struct memcg_cache_array) + - new_array_size * sizeof(void *), GFP_KERNEL); + new = kvzalloc(sizeof(struct memcg_cache_array) + + new_array_size * sizeof(void *), GFP_KERNEL); if (!new) return -ENOMEM; @@ -198,7 +206,7 @@ static int update_memcg_params(struct kmem_cache *s, int new_array_size) rcu_assign_pointer(s->memcg_params.memcg_caches, new); if (old) - kfree_rcu(old, rcu); + call_rcu(&old->rcu, free_memcg_params); return 0; } diff --git a/mm/swap.c b/mm/swap.c index 9295ae960d66..a77d68f2c1b6 100644 --- a/mm/swap.c +++ b/mm/swap.c @@ -575,7 +575,7 @@ static void lru_lazyfree_fn(struct page *page, struct lruvec *lruvec, void *arg) { if (PageLRU(page) && PageAnon(page) && PageSwapBacked(page) && - !PageUnevictable(page)) { + !PageSwapCache(page) && !PageUnevictable(page)) { bool active = PageActive(page); del_page_from_lru_list(page, lruvec, @@ -665,7 +665,7 @@ void deactivate_file_page(struct page *page) void mark_page_lazyfree(struct page *page) { if (PageLRU(page) && PageAnon(page) && PageSwapBacked(page) && - !PageUnevictable(page)) { + !PageSwapCache(page) && !PageUnevictable(page)) { struct pagevec *pvec = &get_cpu_var(lru_lazyfree_pvecs); get_page(page); diff --git a/mm/swap_state.c b/mm/swap_state.c index 71ce2d1ccbf7..ed91091d1e68 100644 --- a/mm/swap_state.c +++ b/mm/swap_state.c @@ -242,6 +242,17 @@ int add_to_swap(struct page *page) * clear SWAP_HAS_CACHE flag. */ goto fail; + /* + * Normally the page will be dirtied in unmap because its pte should be + * dirty. A special case is MADV_FREE page. The page'e pte could have + * dirty bit cleared but the page's SwapBacked bit is still set because + * clearing the dirty bit and SwapBacked bit has no lock protected. For + * such page, unmap will not set dirty bit for it, so page reclaim will + * not write the page out. This can cause data corruption when the page + * is swap in later. Always setting the dirty bit for the page solves + * the problem. + */ + set_page_dirty(page); return 1; diff --git a/mm/z3fold.c b/mm/z3fold.c index 486550df32be..b2ba2ba585f3 100644 --- a/mm/z3fold.c +++ b/mm/z3fold.c @@ -250,6 +250,7 @@ static void __release_z3fold_page(struct z3fold_header *zhdr, bool locked) WARN_ON(!list_empty(&zhdr->buddy)); set_bit(PAGE_STALE, &page->private); + clear_bit(NEEDS_COMPACTING, &page->private); spin_lock(&pool->lock); if (!list_empty(&page->lru)) list_del(&page->lru); @@ -303,7 +304,6 @@ static void free_pages_work(struct work_struct *w) list_del(&zhdr->buddy); if (WARN_ON(!test_bit(PAGE_STALE, &page->private))) continue; - clear_bit(NEEDS_COMPACTING, &page->private); spin_unlock(&pool->stale_lock); cancel_work_sync(&zhdr->work); free_z3fold_page(page); @@ -624,10 +624,8 @@ lookup: * stale pages list. cancel_work_sync() can sleep so we must make * sure it won't be called in case we're in atomic context. */ - if (zhdr && (can_sleep || !work_pending(&zhdr->work) || - !unlikely(work_busy(&zhdr->work)))) { + if (zhdr && (can_sleep || !work_pending(&zhdr->work))) { list_del(&zhdr->buddy); - clear_bit(NEEDS_COMPACTING, &page->private); spin_unlock(&pool->stale_lock); if (can_sleep) cancel_work_sync(&zhdr->work); @@ -875,16 +873,18 @@ static int z3fold_reclaim_page(struct z3fold_pool *pool, unsigned int retries) goto next; } next: + spin_lock(&pool->lock); if (test_bit(PAGE_HEADLESS, &page->private)) { if (ret == 0) { + spin_unlock(&pool->lock); free_z3fold_page(page); return 0; } } else if (kref_put(&zhdr->refcount, release_z3fold_page)) { atomic64_dec(&pool->pages_nr); + spin_unlock(&pool->lock); return 0; } - spin_lock(&pool->lock); /* * Add to the beginning of LRU. diff --git a/net/8021q/vlan_core.c b/net/8021q/vlan_core.c index e2ed69850489..0bc31de9071a 100644 --- a/net/8021q/vlan_core.c +++ b/net/8021q/vlan_core.c @@ -21,6 +21,12 @@ bool vlan_do_receive(struct sk_buff **skbp) if (unlikely(!skb)) return false; + if (unlikely(!(vlan_dev->flags & IFF_UP))) { + kfree_skb(skb); + *skbp = NULL; + return false; + } + skb->dev = vlan_dev; if (unlikely(skb->pkt_type == PACKET_OTHERHOST)) { /* Our lower layer thinks this is not local, let's make sure. diff --git a/net/bluetooth/Kconfig b/net/bluetooth/Kconfig index c18115d22f00..db82a40875e8 100644 --- a/net/bluetooth/Kconfig +++ b/net/bluetooth/Kconfig @@ -126,14 +126,4 @@ config BT_DEBUGFS Provide extensive information about internal Bluetooth states in debugfs. -config BT_LEGACY_IOCTL - bool "Enable legacy ioctl interfaces" - depends on BT && BT_BREDR - default y - help - Enable support for legacy ioctl interfaces. This is only needed - for old and deprecated applications using direct ioctl calls for - controller management. Since Linux 3.4 all configuration and - setup is done via mgmt interface and this is no longer needed. - source "drivers/bluetooth/Kconfig" diff --git a/net/bluetooth/hci_sock.c b/net/bluetooth/hci_sock.c index 0bad296fe0af..65d734c165bd 100644 --- a/net/bluetooth/hci_sock.c +++ b/net/bluetooth/hci_sock.c @@ -878,7 +878,6 @@ static int hci_sock_release(struct socket *sock) return 0; } -#ifdef CONFIG_BT_LEGACY_IOCTL static int hci_sock_blacklist_add(struct hci_dev *hdev, void __user *arg) { bdaddr_t bdaddr; @@ -1050,7 +1049,6 @@ done: release_sock(sk); return err; } -#endif static int hci_sock_bind(struct socket *sock, struct sockaddr *addr, int addr_len) @@ -1971,11 +1969,7 @@ static const struct proto_ops hci_sock_ops = { .getname = hci_sock_getname, .sendmsg = hci_sock_sendmsg, .recvmsg = hci_sock_recvmsg, -#ifdef CONFIG_BT_LEGACY_IOCTL .ioctl = hci_sock_ioctl, -#else - .ioctl = sock_no_ioctl, -#endif .poll = datagram_poll, .listen = sock_no_listen, .shutdown = sock_no_shutdown, diff --git a/net/core/filter.c b/net/core/filter.c index 82edad58d066..74b8c91fb5f4 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -989,10 +989,14 @@ static bool __sk_filter_charge(struct sock *sk, struct sk_filter *fp) bool sk_filter_charge(struct sock *sk, struct sk_filter *fp) { - bool ret = __sk_filter_charge(sk, fp); - if (ret) - refcount_inc(&fp->refcnt); - return ret; + if (!refcount_inc_not_zero(&fp->refcnt)) + return false; + + if (!__sk_filter_charge(sk, fp)) { + sk_filter_release(fp); + return false; + } + return true; } static struct bpf_prog *bpf_migrate_filter(struct bpf_prog *fp) diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index a78fd61da0ec..d4bcdcc68e92 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -3854,6 +3854,9 @@ static int rtnl_fill_statsinfo(struct sk_buff *skb, struct net_device *dev, return -EMSGSIZE; ifsm = nlmsg_data(nlh); + ifsm->family = PF_UNSPEC; + ifsm->pad1 = 0; + ifsm->pad2 = 0; ifsm->ifindex = dev->ifindex; ifsm->filter_mask = filter_mask; diff --git a/net/core/sock.c b/net/core/sock.c index 9b7b6bbb2a23..23953b741a41 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -1654,6 +1654,8 @@ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority) sock_copy(newsk, sk); + newsk->sk_prot_creator = sk->sk_prot; + /* SANITY */ if (likely(newsk->sk_net_refcnt)) get_net(sock_net(newsk)); @@ -1682,13 +1684,16 @@ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority) sock_reset_flag(newsk, SOCK_DONE); - filter = rcu_dereference_protected(newsk->sk_filter, 1); + rcu_read_lock(); + filter = rcu_dereference(sk->sk_filter); if (filter != NULL) /* though it's an empty new sock, the charging may fail * if sysctl_optmem_max was changed between creation of * original socket and cloning */ is_charged = sk_filter_charge(newsk, filter); + RCU_INIT_POINTER(newsk->sk_filter, filter); + rcu_read_unlock(); if (unlikely(!is_charged || xfrm_sk_clone_policy(newsk, sk))) { /* We need to make sure that we don't uncharge the new diff --git a/net/dsa/slave.c b/net/dsa/slave.c index 2afa99506f8b..865e29e62bad 100644 --- a/net/dsa/slave.c +++ b/net/dsa/slave.c @@ -1301,28 +1301,33 @@ int dsa_slave_create(struct dsa_port *port, const char *name) p->old_duplex = -1; port->netdev = slave_dev; - ret = register_netdev(slave_dev); - if (ret) { - netdev_err(master, "error %d registering interface %s\n", - ret, slave_dev->name); - port->netdev = NULL; - free_percpu(p->stats64); - free_netdev(slave_dev); - return ret; - } netif_carrier_off(slave_dev); ret = dsa_slave_phy_setup(p, slave_dev); if (ret) { netdev_err(master, "error %d setting up slave phy\n", ret); - unregister_netdev(slave_dev); - free_percpu(p->stats64); - free_netdev(slave_dev); - return ret; + goto out_free; + } + + ret = register_netdev(slave_dev); + if (ret) { + netdev_err(master, "error %d registering interface %s\n", + ret, slave_dev->name); + goto out_phy; } return 0; + +out_phy: + phy_disconnect(p->phy); + if (of_phy_is_fixed_link(p->dp->dn)) + of_phy_deregister_fixed_link(p->dp->dn); +out_free: + free_percpu(p->stats64); + free_netdev(slave_dev); + port->netdev = NULL; + return ret; } void dsa_slave_destroy(struct net_device *slave_dev) diff --git a/net/ipv4/inetpeer.c b/net/ipv4/inetpeer.c index e7eb590c86ce..b20c8ac64081 100644 --- a/net/ipv4/inetpeer.c +++ b/net/ipv4/inetpeer.c @@ -128,9 +128,9 @@ static struct inet_peer *lookup(const struct inetpeer_addr *daddr, break; } if (cmp == -1) - pp = &(*pp)->rb_left; + pp = &next->rb_left; else - pp = &(*pp)->rb_right; + pp = &next->rb_right; } *parent_p = parent; *pp_p = pp; diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index 0162fb955b33..467e44d7587d 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -259,7 +259,6 @@ static int erspan_rcv(struct sk_buff *skb, struct tnl_ptk_info *tpi, struct ip_tunnel *tunnel; struct erspanhdr *ershdr; const struct iphdr *iph; - __be32 session_id; __be32 index; int len; @@ -275,8 +274,7 @@ static int erspan_rcv(struct sk_buff *skb, struct tnl_ptk_info *tpi, /* The original GRE header does not have key field, * Use ERSPAN 10-bit session ID as key. */ - session_id = cpu_to_be32(ntohs(ershdr->session_id)); - tpi->key = session_id; + tpi->key = cpu_to_be32(ntohs(ershdr->session_id) & ID_MASK); index = ershdr->md.index; tunnel = ip_tunnel_lookup(itn, skb->dev->ifindex, tpi->flags | TUNNEL_KEY, @@ -733,7 +731,7 @@ static netdev_tx_t erspan_xmit(struct sk_buff *skb, if (skb_cow_head(skb, dev->needed_headroom)) goto free_skb; - if (skb->len > dev->mtu) { + if (skb->len - dev->hard_header_len > dev->mtu) { pskb_trim(skb, dev->mtu); truncate = true; } @@ -1223,6 +1221,7 @@ static int gre_tap_init(struct net_device *dev) { __gre_tunnel_init(dev); dev->priv_flags |= IFF_LIVE_ADDR_CHANGE; + netif_keep_dst(dev); return ip_tunnel_init(dev); } @@ -1246,13 +1245,16 @@ static int erspan_tunnel_init(struct net_device *dev) tunnel->tun_hlen = 8; tunnel->parms.iph.protocol = IPPROTO_GRE; - t_hlen = tunnel->hlen + sizeof(struct iphdr) + sizeof(struct erspanhdr); + tunnel->hlen = tunnel->tun_hlen + tunnel->encap_hlen + + sizeof(struct erspanhdr); + t_hlen = tunnel->hlen + sizeof(struct iphdr); dev->needed_headroom = LL_MAX_HEADER + t_hlen + 4; dev->mtu = ETH_DATA_LEN - t_hlen - 4; dev->features |= GRE_FEATURES; dev->hw_features |= GRE_FEATURES; dev->priv_flags |= IFF_LIVE_ADDR_CHANGE; + netif_keep_dst(dev); return ip_tunnel_init(dev); } diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c index fa2dc8f692c6..57fc13c6ab2b 100644 --- a/net/ipv4/ip_input.c +++ b/net/ipv4/ip_input.c @@ -311,9 +311,10 @@ drop: static int ip_rcv_finish(struct net *net, struct sock *sk, struct sk_buff *skb) { const struct iphdr *iph = ip_hdr(skb); - struct rtable *rt; + int (*edemux)(struct sk_buff *skb); struct net_device *dev = skb->dev; - void (*edemux)(struct sk_buff *skb); + struct rtable *rt; + int err; /* if ingress device is enslaved to an L3 master device pass the * skb to its handler for processing @@ -331,7 +332,9 @@ static int ip_rcv_finish(struct net *net, struct sock *sk, struct sk_buff *skb) ipprot = rcu_dereference(inet_protos[protocol]); if (ipprot && (edemux = READ_ONCE(ipprot->early_demux))) { - edemux(skb); + err = edemux(skb); + if (unlikely(err)) + goto drop_error; /* must reload iph, skb->head might have changed */ iph = ip_hdr(skb); } @@ -342,13 +345,10 @@ static int ip_rcv_finish(struct net *net, struct sock *sk, struct sk_buff *skb) * how the packet travels inside Linux networking. */ if (!skb_valid_dst(skb)) { - int err = ip_route_input_noref(skb, iph->daddr, iph->saddr, - iph->tos, dev); - if (unlikely(err)) { - if (err == -EXDEV) - __NET_INC_STATS(net, LINUX_MIB_IPRPFILTER); - goto drop; - } + err = ip_route_input_noref(skb, iph->daddr, iph->saddr, + iph->tos, dev); + if (unlikely(err)) + goto drop_error; } #ifdef CONFIG_IP_ROUTE_CLASSID @@ -399,6 +399,11 @@ static int ip_rcv_finish(struct net *net, struct sock *sk, struct sk_buff *skb) drop: kfree_skb(skb); return NET_RX_DROP; + +drop_error: + if (err == -EXDEV) + __NET_INC_STATS(net, LINUX_MIB_IPRPFILTER); + goto drop; } /* diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c index 5ed63d250950..89453cf62158 100644 --- a/net/ipv4/ip_vti.c +++ b/net/ipv4/ip_vti.c @@ -168,6 +168,7 @@ static netdev_tx_t vti_xmit(struct sk_buff *skb, struct net_device *dev, struct ip_tunnel_parm *parms = &tunnel->parms; struct dst_entry *dst = skb_dst(skb); struct net_device *tdev; /* Device to other host */ + int pkt_len = skb->len; int err; int mtu; @@ -229,7 +230,7 @@ static netdev_tx_t vti_xmit(struct sk_buff *skb, struct net_device *dev, err = dst_output(tunnel->net, skb->sk, skb); if (net_xmit_eval(err) == 0) - err = skb->len; + err = pkt_len; iptunnel_xmit_stats(dev, err); return NETDEV_TX_OK; diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 94d4cd2d5ea4..ac6fde5d45f1 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -1520,43 +1520,56 @@ struct rtable *rt_dst_alloc(struct net_device *dev, EXPORT_SYMBOL(rt_dst_alloc); /* called in rcu_read_lock() section */ -static int ip_route_input_mc(struct sk_buff *skb, __be32 daddr, __be32 saddr, - u8 tos, struct net_device *dev, int our) +int ip_mc_validate_source(struct sk_buff *skb, __be32 daddr, __be32 saddr, + u8 tos, struct net_device *dev, + struct in_device *in_dev, u32 *itag) { - struct rtable *rth; - struct in_device *in_dev = __in_dev_get_rcu(dev); - unsigned int flags = RTCF_MULTICAST; - u32 itag = 0; int err; /* Primary sanity checks. */ - if (!in_dev) return -EINVAL; if (ipv4_is_multicast(saddr) || ipv4_is_lbcast(saddr) || skb->protocol != htons(ETH_P_IP)) - goto e_inval; + return -EINVAL; if (ipv4_is_loopback(saddr) && !IN_DEV_ROUTE_LOCALNET(in_dev)) - goto e_inval; + return -EINVAL; if (ipv4_is_zeronet(saddr)) { if (!ipv4_is_local_multicast(daddr)) - goto e_inval; + return -EINVAL; } else { err = fib_validate_source(skb, saddr, 0, tos, 0, dev, - in_dev, &itag); + in_dev, itag); if (err < 0) - goto e_err; + return err; } + return 0; +} + +/* called in rcu_read_lock() section */ +static int ip_route_input_mc(struct sk_buff *skb, __be32 daddr, __be32 saddr, + u8 tos, struct net_device *dev, int our) +{ + struct in_device *in_dev = __in_dev_get_rcu(dev); + unsigned int flags = RTCF_MULTICAST; + struct rtable *rth; + u32 itag = 0; + int err; + + err = ip_mc_validate_source(skb, daddr, saddr, tos, dev, in_dev, &itag); + if (err) + return err; + if (our) flags |= RTCF_LOCAL; rth = rt_dst_alloc(dev_net(dev)->loopback_dev, flags, RTN_MULTICAST, IN_DEV_CONF_GET(in_dev, NOPOLICY), false, false); if (!rth) - goto e_nobufs; + return -ENOBUFS; #ifdef CONFIG_IP_ROUTE_CLASSID rth->dst.tclassid = itag; @@ -1572,13 +1585,6 @@ static int ip_route_input_mc(struct sk_buff *skb, __be32 daddr, __be32 saddr, skb_dst_set(skb, &rth->dst); return 0; - -e_nobufs: - return -ENOBUFS; -e_inval: - return -EINVAL; -e_err: - return err; } diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index d9416b5162bc..85164d4d3e53 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -1503,23 +1503,23 @@ csum_err: } EXPORT_SYMBOL(tcp_v4_do_rcv); -void tcp_v4_early_demux(struct sk_buff *skb) +int tcp_v4_early_demux(struct sk_buff *skb) { const struct iphdr *iph; const struct tcphdr *th; struct sock *sk; if (skb->pkt_type != PACKET_HOST) - return; + return 0; if (!pskb_may_pull(skb, skb_transport_offset(skb) + sizeof(struct tcphdr))) - return; + return 0; iph = ip_hdr(skb); th = tcp_hdr(skb); if (th->doff < sizeof(struct tcphdr) / 4) - return; + return 0; sk = __inet_lookup_established(dev_net(skb->dev), &tcp_hashinfo, iph->saddr, th->source, @@ -1538,6 +1538,7 @@ void tcp_v4_early_demux(struct sk_buff *skb) skb_dst_set_noref(skb, dst); } } + return 0; } bool tcp_add_backlog(struct sock *sk, struct sk_buff *skb) diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index ef29df8648e4..5676237d2b0f 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -2221,9 +2221,10 @@ static struct sock *__udp4_lib_demux_lookup(struct net *net, return NULL; } -void udp_v4_early_demux(struct sk_buff *skb) +int udp_v4_early_demux(struct sk_buff *skb) { struct net *net = dev_net(skb->dev); + struct in_device *in_dev = NULL; const struct iphdr *iph; const struct udphdr *uh; struct sock *sk = NULL; @@ -2234,24 +2235,24 @@ void udp_v4_early_demux(struct sk_buff *skb) /* validate the packet */ if (!pskb_may_pull(skb, skb_transport_offset(skb) + sizeof(struct udphdr))) - return; + return 0; iph = ip_hdr(skb); uh = udp_hdr(skb); if (skb->pkt_type == PACKET_BROADCAST || skb->pkt_type == PACKET_MULTICAST) { - struct in_device *in_dev = __in_dev_get_rcu(skb->dev); + in_dev = __in_dev_get_rcu(skb->dev); if (!in_dev) - return; + return 0; /* we are supposed to accept bcast packets */ if (skb->pkt_type == PACKET_MULTICAST) { ours = ip_check_mc_rcu(in_dev, iph->daddr, iph->saddr, iph->protocol); if (!ours) - return; + return 0; } sk = __udp4_lib_mcast_demux_lookup(net, uh->dest, iph->daddr, @@ -2263,7 +2264,7 @@ void udp_v4_early_demux(struct sk_buff *skb) } if (!sk || !refcount_inc_not_zero(&sk->sk_refcnt)) - return; + return 0; skb->sk = sk; skb->destructor = sock_efree; @@ -2272,12 +2273,23 @@ void udp_v4_early_demux(struct sk_buff *skb) if (dst) dst = dst_check(dst, 0); if (dst) { + u32 itag = 0; + /* set noref for now. * any place which wants to hold dst has to call * dst_hold_safe() */ skb_dst_set_noref(skb, dst); + + /* for unconnected multicast sockets we need to validate + * the source on each packet + */ + if (!inet_sk(sk)->inet_daddr && in_dev) + return ip_mc_validate_source(skb, iph->daddr, + iph->saddr, iph->tos, + skb->dev, in_dev, &itag); } + return 0; } int udp_rcv(struct sk_buff *skb) diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index 20f66f4c9460..1602b491b281 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -1311,6 +1311,7 @@ static void ip6gre_tap_setup(struct net_device *dev) dev->features |= NETIF_F_NETNS_LOCAL; dev->priv_flags &= ~IFF_TX_SKB_SHARING; dev->priv_flags |= IFF_LIVE_ADDR_CHANGE; + netif_keep_dst(dev); } static bool ip6gre_netlink_encap_parms(struct nlattr *data[], diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index f2f21c24915f..a1c24443cd9e 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -1043,6 +1043,7 @@ int ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev, __u8 dsfield, struct dst_entry *dst = NULL, *ndst = NULL; struct net_device *tdev; int mtu; + unsigned int eth_hlen = t->dev->type == ARPHRD_ETHER ? ETH_HLEN : 0; unsigned int psh_hlen = sizeof(struct ipv6hdr) + t->encap_hlen; unsigned int max_headroom = psh_hlen; bool use_cache = false; @@ -1124,7 +1125,7 @@ route_lookup: t->parms.name); goto tx_err_dst_release; } - mtu = dst_mtu(dst) - psh_hlen - t->tun_hlen; + mtu = dst_mtu(dst) - eth_hlen - psh_hlen - t->tun_hlen; if (encap_limit >= 0) { max_headroom += 8; mtu -= 8; @@ -1133,7 +1134,7 @@ route_lookup: mtu = IPV6_MIN_MTU; if (skb_dst(skb) && !t->parms.collect_md) skb_dst(skb)->ops->update_pmtu(skb_dst(skb), NULL, skb, mtu); - if (skb->len - t->tun_hlen > mtu && !skb_is_gso(skb)) { + if (skb->len - t->tun_hlen - eth_hlen > mtu && !skb_is_gso(skb)) { *pmtu = mtu; err = -EMSGSIZE; goto tx_err_dst_release; diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c index 79444a4bfd6d..bcdc2d557de1 100644 --- a/net/ipv6/ip6_vti.c +++ b/net/ipv6/ip6_vti.c @@ -445,6 +445,7 @@ vti6_xmit(struct sk_buff *skb, struct net_device *dev, struct flowi *fl) struct dst_entry *dst = skb_dst(skb); struct net_device *tdev; struct xfrm_state *x; + int pkt_len = skb->len; int err = -1; int mtu; @@ -502,7 +503,7 @@ vti6_xmit(struct sk_buff *skb, struct net_device *dev, struct flowi *fl) struct pcpu_sw_netstats *tstats = this_cpu_ptr(dev->tstats); u64_stats_update_begin(&tstats->syncp); - tstats->tx_bytes += skb->len; + tstats->tx_bytes += pkt_len; tstats->tx_packets++; u64_stats_update_end(&tstats->syncp); } else { diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c index ee485df73ccd..02d61101b108 100644 --- a/net/l2tp/l2tp_core.c +++ b/net/l2tp/l2tp_core.c @@ -1314,6 +1314,9 @@ again: hlist_del_init(&session->hlist); + if (test_and_set_bit(0, &session->dead)) + goto again; + if (session->ref != NULL) (*session->ref)(session); @@ -1685,14 +1688,12 @@ EXPORT_SYMBOL_GPL(l2tp_tunnel_create); /* This function is used by the netlink TUNNEL_DELETE command. */ -int l2tp_tunnel_delete(struct l2tp_tunnel *tunnel) +void l2tp_tunnel_delete(struct l2tp_tunnel *tunnel) { - l2tp_tunnel_inc_refcount(tunnel); - if (false == queue_work(l2tp_wq, &tunnel->del_work)) { - l2tp_tunnel_dec_refcount(tunnel); - return 1; + if (!test_and_set_bit(0, &tunnel->dead)) { + l2tp_tunnel_inc_refcount(tunnel); + queue_work(l2tp_wq, &tunnel->del_work); } - return 0; } EXPORT_SYMBOL_GPL(l2tp_tunnel_delete); @@ -1750,6 +1751,9 @@ EXPORT_SYMBOL_GPL(__l2tp_session_unhash); */ int l2tp_session_delete(struct l2tp_session *session) { + if (test_and_set_bit(0, &session->dead)) + return 0; + if (session->ref) (*session->ref)(session); __l2tp_session_unhash(session); diff --git a/net/l2tp/l2tp_core.h b/net/l2tp/l2tp_core.h index a305e0c5925a..67c79d9b5c6c 100644 --- a/net/l2tp/l2tp_core.h +++ b/net/l2tp/l2tp_core.h @@ -76,6 +76,7 @@ struct l2tp_session_cfg { struct l2tp_session { int magic; /* should be * L2TP_SESSION_MAGIC */ + long dead; struct l2tp_tunnel *tunnel; /* back pointer to tunnel * context */ @@ -160,6 +161,9 @@ struct l2tp_tunnel_cfg { struct l2tp_tunnel { int magic; /* Should be L2TP_TUNNEL_MAGIC */ + + unsigned long dead; + struct rcu_head rcu; rwlock_t hlist_lock; /* protect session_hlist */ bool acpt_newsess; /* Indicates whether this @@ -254,7 +258,7 @@ int l2tp_tunnel_create(struct net *net, int fd, int version, u32 tunnel_id, u32 peer_tunnel_id, struct l2tp_tunnel_cfg *cfg, struct l2tp_tunnel **tunnelp); void l2tp_tunnel_closeall(struct l2tp_tunnel *tunnel); -int l2tp_tunnel_delete(struct l2tp_tunnel *tunnel); +void l2tp_tunnel_delete(struct l2tp_tunnel *tunnel); struct l2tp_session *l2tp_session_create(int priv_size, struct l2tp_tunnel *tunnel, u32 session_id, u32 peer_session_id, diff --git a/net/l2tp/l2tp_eth.c b/net/l2tp/l2tp_eth.c index 87da9ef61860..014a7bc2a872 100644 --- a/net/l2tp/l2tp_eth.c +++ b/net/l2tp/l2tp_eth.c @@ -44,7 +44,6 @@ struct l2tp_eth { struct net_device *dev; struct sock *tunnel_sock; struct l2tp_session *session; - struct list_head list; atomic_long_t tx_bytes; atomic_long_t tx_packets; atomic_long_t tx_dropped; @@ -58,17 +57,6 @@ struct l2tp_eth_sess { struct net_device *dev; }; -/* per-net private data for this module */ -static unsigned int l2tp_eth_net_id; -struct l2tp_eth_net { - struct list_head l2tp_eth_dev_list; - spinlock_t l2tp_eth_lock; -}; - -static inline struct l2tp_eth_net *l2tp_eth_pernet(struct net *net) -{ - return net_generic(net, l2tp_eth_net_id); -} static int l2tp_eth_dev_init(struct net_device *dev) { @@ -84,12 +72,6 @@ static int l2tp_eth_dev_init(struct net_device *dev) static void l2tp_eth_dev_uninit(struct net_device *dev) { - struct l2tp_eth *priv = netdev_priv(dev); - struct l2tp_eth_net *pn = l2tp_eth_pernet(dev_net(dev)); - - spin_lock(&pn->l2tp_eth_lock); - list_del_init(&priv->list); - spin_unlock(&pn->l2tp_eth_lock); dev_put(dev); } @@ -273,7 +255,6 @@ static int l2tp_eth_create(struct net *net, struct l2tp_tunnel *tunnel, struct l2tp_eth *priv; struct l2tp_eth_sess *spriv; int rc; - struct l2tp_eth_net *pn; if (cfg->ifname) { strlcpy(name, cfg->ifname, IFNAMSIZ); @@ -305,7 +286,6 @@ static int l2tp_eth_create(struct net *net, struct l2tp_tunnel *tunnel, priv = netdev_priv(dev); priv->dev = dev; priv->session = session; - INIT_LIST_HEAD(&priv->list); priv->tunnel_sock = tunnel->sock; session->recv_skb = l2tp_eth_dev_recv; @@ -326,10 +306,6 @@ static int l2tp_eth_create(struct net *net, struct l2tp_tunnel *tunnel, strlcpy(session->ifname, dev->name, IFNAMSIZ); dev_hold(dev); - pn = l2tp_eth_pernet(dev_net(dev)); - spin_lock(&pn->l2tp_eth_lock); - list_add(&priv->list, &pn->l2tp_eth_dev_list); - spin_unlock(&pn->l2tp_eth_lock); return 0; @@ -342,22 +318,6 @@ out: return rc; } -static __net_init int l2tp_eth_init_net(struct net *net) -{ - struct l2tp_eth_net *pn = net_generic(net, l2tp_eth_net_id); - - INIT_LIST_HEAD(&pn->l2tp_eth_dev_list); - spin_lock_init(&pn->l2tp_eth_lock); - - return 0; -} - -static struct pernet_operations l2tp_eth_net_ops = { - .init = l2tp_eth_init_net, - .id = &l2tp_eth_net_id, - .size = sizeof(struct l2tp_eth_net), -}; - static const struct l2tp_nl_cmd_ops l2tp_eth_nl_cmd_ops = { .session_create = l2tp_eth_create, @@ -371,25 +331,18 @@ static int __init l2tp_eth_init(void) err = l2tp_nl_register_ops(L2TP_PWTYPE_ETH, &l2tp_eth_nl_cmd_ops); if (err) - goto out; - - err = register_pernet_device(&l2tp_eth_net_ops); - if (err) - goto out_unreg; + goto err; pr_info("L2TP ethernet pseudowire support (L2TPv3)\n"); return 0; -out_unreg: - l2tp_nl_unregister_ops(L2TP_PWTYPE_ETH); -out: +err: return err; } static void __exit l2tp_eth_exit(void) { - unregister_pernet_device(&l2tp_eth_net_ops); l2tp_nl_unregister_ops(L2TP_PWTYPE_ETH); } diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c index 50e3ee9a9d61..bc6e8bfc5be4 100644 --- a/net/l2tp/l2tp_ppp.c +++ b/net/l2tp/l2tp_ppp.c @@ -437,11 +437,11 @@ static void pppol2tp_session_close(struct l2tp_session *session) BUG_ON(session->magic != L2TP_SESSION_MAGIC); - if (sock) { + if (sock) inet_shutdown(sock, SEND_SHUTDOWN); - /* Don't let the session go away before our socket does */ - l2tp_session_inc_refcount(session); - } + + /* Don't let the session go away before our socket does */ + l2tp_session_inc_refcount(session); } /* Really kill the session socket. (Called from sock_put() if diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index 327807731b44..94c11cf0459d 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -2270,10 +2270,13 @@ int __netlink_dump_start(struct sock *ssk, struct sk_buff *skb, mutex_unlock(nlk->cb_mutex); + ret = 0; if (cb->start) - cb->start(cb); + ret = cb->start(cb); + + if (!ret) + ret = netlink_dump(sk); - ret = netlink_dump(sk); sock_put(sk); if (ret) diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index d288f52c53f7..bec01a3daf5b 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -2840,6 +2840,7 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len) struct virtio_net_hdr vnet_hdr = { 0 }; int offset = 0; struct packet_sock *po = pkt_sk(sk); + bool has_vnet_hdr = false; int hlen, tlen, linear; int extra_len = 0; @@ -2883,6 +2884,7 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len) err = packet_snd_vnet_parse(msg, &len, &vnet_hdr); if (err) goto out_unlock; + has_vnet_hdr = true; } if (unlikely(sock_flag(sk, SOCK_NOFCS))) { @@ -2941,7 +2943,7 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len) skb->priority = sk->sk_priority; skb->mark = sockc.mark; - if (po->has_vnet_hdr) { + if (has_vnet_hdr) { err = virtio_net_hdr_to_skb(skb, &vnet_hdr, vio_le()); if (err) goto out_free; @@ -3069,13 +3071,15 @@ static int packet_do_bind(struct sock *sk, const char *name, int ifindex, int ret = 0; bool unlisted = false; - if (po->fanout) - return -EINVAL; - lock_sock(sk); spin_lock(&po->bind_lock); rcu_read_lock(); + if (po->fanout) { + ret = -EINVAL; + goto out_unlock; + } + if (name) { dev = dev_get_by_name_rcu(sock_net(sk), name); if (!dev) { diff --git a/net/sctp/sctp_diag.c b/net/sctp/sctp_diag.c index 22ed01a76b19..a72a7d925d46 100644 --- a/net/sctp/sctp_diag.c +++ b/net/sctp/sctp_diag.c @@ -463,6 +463,7 @@ static void sctp_diag_dump(struct sk_buff *skb, struct netlink_callback *cb, .r = r, .net_admin = netlink_net_capable(cb->skb, CAP_NET_ADMIN), }; + int pos = cb->args[2]; /* eps hashtable dumps * args: @@ -493,7 +494,8 @@ skip: goto done; sctp_for_each_transport(sctp_sock_filter, sctp_sock_dump, - net, (int *)&cb->args[2], &commp); + net, &pos, &commp); + cb->args[2] = pos; done: cb->args[1] = cb->args[4]; diff --git a/net/tipc/msg.c b/net/tipc/msg.c index 6ef379f004ac..121e59a1d0e7 100644 --- a/net/tipc/msg.c +++ b/net/tipc/msg.c @@ -551,7 +551,7 @@ bool tipc_msg_lookup_dest(struct net *net, struct sk_buff *skb, int *err) return false; if (msg_errcode(msg)) return false; - *err = -TIPC_ERR_NO_NAME; + *err = TIPC_ERR_NO_NAME; if (skb_linearize(skb)) return false; msg = buf_msg(skb); diff --git a/scripts/Makefile.build b/scripts/Makefile.build index 2e3a10e79ca9..061d0c3a420a 100644 --- a/scripts/Makefile.build +++ b/scripts/Makefile.build @@ -265,6 +265,8 @@ objtool_args += --no-fp endif ifdef CONFIG_GCOV_KERNEL objtool_args += --no-unreachable +else +objtool_args += $(call cc-ifversion, -lt, 0405, --no-unreachable) endif # 'OBJECT_FILES_NON_STANDARD := y': skip objtool checking for a directory diff --git a/scripts/checkpatch.pl b/scripts/checkpatch.pl index dd2c262aebbf..8b80bac055e4 100755 --- a/scripts/checkpatch.pl +++ b/scripts/checkpatch.pl @@ -6390,7 +6390,7 @@ sub process { exit(0); } - if (!$is_patch && $file !~ /cover-letter\.patch$/) { + if (!$is_patch && $filename !~ /cover-letter\.patch$/) { ERROR("NOT_UNIFIED_DIFF", "Does not appear to be a unified-diff format patch\n"); } diff --git a/scripts/spelling.txt b/scripts/spelling.txt index 400ef35169c5..aa0cc49ad1ad 100644 --- a/scripts/spelling.txt +++ b/scripts/spelling.txt @@ -53,6 +53,7 @@ acumulator||accumulator adapater||adapter addional||additional additionaly||additionally +additonal||additional addres||address adddress||address addreses||addresses @@ -67,6 +68,8 @@ adviced||advised afecting||affecting againt||against agaist||against +aggreataon||aggregation +aggreation||aggregation albumns||albums alegorical||allegorical algined||aligned @@ -80,6 +83,8 @@ aligment||alignment alignement||alignment allign||align alligned||aligned +alllocate||allocate +alloated||allocated allocatote||allocate allocatrd||allocated allocte||allocate @@ -171,6 +176,7 @@ availale||available availavility||availability availble||available availiable||available +availible||available avalable||available avaliable||available aysnc||async @@ -203,6 +209,7 @@ broadcat||broadcast cacluated||calculated caculation||calculation calender||calendar +calescing||coalescing calle||called callibration||calibration calucate||calculate @@ -210,6 +217,7 @@ calulate||calculate cancelation||cancellation cancle||cancel capabilites||capabilities +capabilty||capability capabitilies||capabilities capatibilities||capabilities capapbilities||capabilities @@ -302,6 +310,7 @@ containts||contains contaisn||contains contant||contact contence||contents +continious||continuous continous||continuous continously||continuously continueing||continuing @@ -393,6 +402,7 @@ differrence||difference diffrent||different diffrentiate||differentiate difinition||definition +dimesions||dimensions diplay||display direectly||directly disassocation||disassociation @@ -449,6 +459,7 @@ equiped||equipped equivelant||equivalent equivilant||equivalent eror||error +errorr||error estbalishment||establishment etsablishment||establishment etsbalishment||establishment @@ -481,6 +492,7 @@ failied||failed faillure||failure failue||failure failuer||failure +failng||failing faireness||fairness falied||failed faliure||failure @@ -493,6 +505,7 @@ fetaure||feature fetaures||features fileystem||filesystem fimware||firmware +firware||firmware finanize||finalize findn||find finilizes||finalizes @@ -502,6 +515,7 @@ folloing||following followign||following followings||following follwing||following +fonud||found forseeable||foreseeable forse||force fortan||fortran @@ -532,6 +546,7 @@ grabing||grabbing grahical||graphical grahpical||graphical grapic||graphic +grranted||granted guage||gauge guarenteed||guaranteed guarentee||guarantee @@ -543,6 +558,7 @@ happend||happened harware||hardware heirarchically||hierarchically helpfull||helpful +hybernate||hibernate hierachy||hierarchy hierarchie||hierarchy howver||however @@ -565,16 +581,19 @@ implemenation||implementation implementaiton||implementation implementated||implemented implemention||implementation +implementd||implemented implemetation||implementation implemntation||implementation implentation||implementation implmentation||implementation implmenting||implementing +incative||inactive incomming||incoming incompatabilities||incompatibilities incompatable||incompatible inconsistant||inconsistent increas||increase +incremeted||incremented incrment||increment indendation||indentation indended||intended @@ -619,6 +638,7 @@ interger||integer intermittant||intermittent internel||internal interoprability||interoperability +interuupt||interrupt interrface||interface interrrupt||interrupt interrup||interrupt @@ -638,8 +658,10 @@ intrrupt||interrupt intterrupt||interrupt intuative||intuitive invaid||invalid +invald||invalid invalde||invalid invalide||invalid +invalidiate||invalidate invalud||invalid invididual||individual invokation||invocation @@ -713,6 +735,7 @@ misformed||malformed mispelled||misspelled mispelt||misspelt mising||missing +mismactch||mismatch missmanaged||mismanaged missmatch||mismatch miximum||maximum @@ -731,6 +754,7 @@ multidimensionnal||multidimensional multple||multiple mumber||number muticast||multicast +mutilcast||multicast mutiple||multiple mutli||multi nams||names @@ -834,6 +858,7 @@ posible||possible positon||position possibilites||possibilities powerfull||powerful +preample||preamble preapre||prepare preceeded||preceded preceeding||preceding @@ -1059,6 +1084,7 @@ sturcture||structure subdirectoires||subdirectories suble||subtle substract||subtract +submition||submission succesfully||successfully succesful||successful successed||succeeded @@ -1078,6 +1104,7 @@ suppoted||supported suppported||supported suppport||support supress||suppress +surpressed||suppressed surpresses||suppresses susbsystem||subsystem suspeneded||suspended @@ -1091,6 +1118,7 @@ swithced||switched swithcing||switching swithed||switched swithing||switching +swtich||switch symetric||symmetric synax||syntax synchonized||synchronized @@ -1111,7 +1139,9 @@ therfore||therefore thier||their threds||threads threshhold||threshold +thresold||threshold throught||through +troughput||throughput thses||these tiggered||triggered tipically||typically @@ -1120,6 +1150,7 @@ tmis||this torerable||tolerable tramsmitted||transmitted tramsmit||transmit +tranasction||transaction tranfer||transfer transciever||transceiver transferd||transferred @@ -1133,6 +1164,7 @@ trasmission||transmission treshold||threshold trigerring||triggering trun||turn +tunning||tuning ture||true tyep||type udpate||update @@ -1199,6 +1231,7 @@ visiters||visitors vitual||virtual wakeus||wakeups wating||waiting +wiat||wait wether||whether whataver||whatever whcih||which diff --git a/security/keys/Kconfig b/security/keys/Kconfig index a7a23b5541f8..91eafada3164 100644 --- a/security/keys/Kconfig +++ b/security/keys/Kconfig @@ -45,10 +45,8 @@ config BIG_KEYS bool "Large payload keys" depends on KEYS depends on TMPFS - depends on (CRYPTO_ANSI_CPRNG = y || CRYPTO_DRBG = y) select CRYPTO_AES - select CRYPTO_ECB - select CRYPTO_RNG + select CRYPTO_GCM help This option provides support for holding large keys within the kernel (for example Kerberos ticket caches). The data may be stored out to diff --git a/security/keys/big_key.c b/security/keys/big_key.c index 6acb00f6f22c..e607830b6154 100644 --- a/security/keys/big_key.c +++ b/security/keys/big_key.c @@ -1,5 +1,6 @@ /* Large capacity key type * + * Copyright (C) 2017 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved. * Copyright (C) 2013 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) * @@ -16,10 +17,10 @@ #include <linux/shmem_fs.h> #include <linux/err.h> #include <linux/scatterlist.h> +#include <linux/random.h> #include <keys/user-type.h> #include <keys/big_key-type.h> -#include <crypto/rng.h> -#include <crypto/skcipher.h> +#include <crypto/aead.h> /* * Layout of key payload words. @@ -49,7 +50,12 @@ enum big_key_op { /* * Key size for big_key data encryption */ -#define ENC_KEY_SIZE 16 +#define ENC_KEY_SIZE 32 + +/* + * Authentication tag length + */ +#define ENC_AUTHTAG_SIZE 16 /* * big_key defined keys take an arbitrary string as the description and an @@ -64,57 +70,62 @@ struct key_type key_type_big_key = { .destroy = big_key_destroy, .describe = big_key_describe, .read = big_key_read, + /* no ->update(); don't add it without changing big_key_crypt() nonce */ }; /* - * Crypto names for big_key data encryption + * Crypto names for big_key data authenticated encryption */ -static const char big_key_rng_name[] = "stdrng"; -static const char big_key_alg_name[] = "ecb(aes)"; +static const char big_key_alg_name[] = "gcm(aes)"; /* - * Crypto algorithms for big_key data encryption + * Crypto algorithms for big_key data authenticated encryption */ -static struct crypto_rng *big_key_rng; -static struct crypto_skcipher *big_key_skcipher; +static struct crypto_aead *big_key_aead; /* - * Generate random key to encrypt big_key data + * Since changing the key affects the entire object, we need a mutex. */ -static inline int big_key_gen_enckey(u8 *key) -{ - return crypto_rng_get_bytes(big_key_rng, key, ENC_KEY_SIZE); -} +static DEFINE_MUTEX(big_key_aead_lock); /* * Encrypt/decrypt big_key data */ static int big_key_crypt(enum big_key_op op, u8 *data, size_t datalen, u8 *key) { - int ret = -EINVAL; + int ret; struct scatterlist sgio; - SKCIPHER_REQUEST_ON_STACK(req, big_key_skcipher); - - if (crypto_skcipher_setkey(big_key_skcipher, key, ENC_KEY_SIZE)) { + struct aead_request *aead_req; + /* We always use a zero nonce. The reason we can get away with this is + * because we're using a different randomly generated key for every + * different encryption. Notably, too, key_type_big_key doesn't define + * an .update function, so there's no chance we'll wind up reusing the + * key to encrypt updated data. Simply put: one key, one encryption. + */ + u8 zero_nonce[crypto_aead_ivsize(big_key_aead)]; + + aead_req = aead_request_alloc(big_key_aead, GFP_KERNEL); + if (!aead_req) + return -ENOMEM; + + memset(zero_nonce, 0, sizeof(zero_nonce)); + sg_init_one(&sgio, data, datalen + (op == BIG_KEY_ENC ? ENC_AUTHTAG_SIZE : 0)); + aead_request_set_crypt(aead_req, &sgio, &sgio, datalen, zero_nonce); + aead_request_set_callback(aead_req, CRYPTO_TFM_REQ_MAY_SLEEP, NULL, NULL); + aead_request_set_ad(aead_req, 0); + + mutex_lock(&big_key_aead_lock); + if (crypto_aead_setkey(big_key_aead, key, ENC_KEY_SIZE)) { ret = -EAGAIN; goto error; } - - skcipher_request_set_tfm(req, big_key_skcipher); - skcipher_request_set_callback(req, CRYPTO_TFM_REQ_MAY_SLEEP, - NULL, NULL); - - sg_init_one(&sgio, data, datalen); - skcipher_request_set_crypt(req, &sgio, &sgio, datalen, NULL); - if (op == BIG_KEY_ENC) - ret = crypto_skcipher_encrypt(req); + ret = crypto_aead_encrypt(aead_req); else - ret = crypto_skcipher_decrypt(req); - - skcipher_request_zero(req); - + ret = crypto_aead_decrypt(aead_req); error: + mutex_unlock(&big_key_aead_lock); + aead_request_free(aead_req); return ret; } @@ -146,16 +157,13 @@ int big_key_preparse(struct key_preparsed_payload *prep) * * File content is stored encrypted with randomly generated key. */ - size_t enclen = ALIGN(datalen, crypto_skcipher_blocksize(big_key_skcipher)); + size_t enclen = datalen + ENC_AUTHTAG_SIZE; loff_t pos = 0; - /* prepare aligned data to encrypt */ data = kmalloc(enclen, GFP_KERNEL); if (!data) return -ENOMEM; - memcpy(data, prep->data, datalen); - memset(data + datalen, 0x00, enclen - datalen); /* generate random key */ enckey = kmalloc(ENC_KEY_SIZE, GFP_KERNEL); @@ -163,13 +171,12 @@ int big_key_preparse(struct key_preparsed_payload *prep) ret = -ENOMEM; goto error; } - - ret = big_key_gen_enckey(enckey); - if (ret) + ret = get_random_bytes_wait(enckey, ENC_KEY_SIZE); + if (unlikely(ret)) goto err_enckey; /* encrypt aligned data */ - ret = big_key_crypt(BIG_KEY_ENC, data, enclen, enckey); + ret = big_key_crypt(BIG_KEY_ENC, data, datalen, enckey); if (ret) goto err_enckey; @@ -195,7 +202,7 @@ int big_key_preparse(struct key_preparsed_payload *prep) *path = file->f_path; path_get(path); fput(file); - kfree(data); + kzfree(data); } else { /* Just store the data in a buffer */ void *data = kmalloc(datalen, GFP_KERNEL); @@ -211,9 +218,9 @@ int big_key_preparse(struct key_preparsed_payload *prep) err_fput: fput(file); err_enckey: - kfree(enckey); + kzfree(enckey); error: - kfree(data); + kzfree(data); return ret; } @@ -227,7 +234,7 @@ void big_key_free_preparse(struct key_preparsed_payload *prep) path_put(path); } - kfree(prep->payload.data[big_key_data]); + kzfree(prep->payload.data[big_key_data]); } /* @@ -259,7 +266,7 @@ void big_key_destroy(struct key *key) path->mnt = NULL; path->dentry = NULL; } - kfree(key->payload.data[big_key_data]); + kzfree(key->payload.data[big_key_data]); key->payload.data[big_key_data] = NULL; } @@ -295,7 +302,7 @@ long big_key_read(const struct key *key, char __user *buffer, size_t buflen) struct file *file; u8 *data; u8 *enckey = (u8 *)key->payload.data[big_key_data]; - size_t enclen = ALIGN(datalen, crypto_skcipher_blocksize(big_key_skcipher)); + size_t enclen = datalen + ENC_AUTHTAG_SIZE; loff_t pos = 0; data = kmalloc(enclen, GFP_KERNEL); @@ -328,7 +335,7 @@ long big_key_read(const struct key *key, char __user *buffer, size_t buflen) err_fput: fput(file); error: - kfree(data); + kzfree(data); } else { ret = datalen; if (copy_to_user(buffer, key->payload.data[big_key_data], @@ -344,47 +351,31 @@ error: */ static int __init big_key_init(void) { - struct crypto_skcipher *cipher; - struct crypto_rng *rng; int ret; - rng = crypto_alloc_rng(big_key_rng_name, 0, 0); - if (IS_ERR(rng)) { - pr_err("Can't alloc rng: %ld\n", PTR_ERR(rng)); - return PTR_ERR(rng); - } - - big_key_rng = rng; - - /* seed RNG */ - ret = crypto_rng_reset(rng, NULL, crypto_rng_seedsize(rng)); - if (ret) { - pr_err("Can't reset rng: %d\n", ret); - goto error_rng; - } - /* init block cipher */ - cipher = crypto_alloc_skcipher(big_key_alg_name, 0, CRYPTO_ALG_ASYNC); - if (IS_ERR(cipher)) { - ret = PTR_ERR(cipher); + big_key_aead = crypto_alloc_aead(big_key_alg_name, 0, CRYPTO_ALG_ASYNC); + if (IS_ERR(big_key_aead)) { + ret = PTR_ERR(big_key_aead); pr_err("Can't alloc crypto: %d\n", ret); - goto error_rng; + return ret; + } + ret = crypto_aead_setauthsize(big_key_aead, ENC_AUTHTAG_SIZE); + if (ret < 0) { + pr_err("Can't set crypto auth tag len: %d\n", ret); + goto free_aead; } - - big_key_skcipher = cipher; ret = register_key_type(&key_type_big_key); if (ret < 0) { pr_err("Can't register type: %d\n", ret); - goto error_cipher; + goto free_aead; } return 0; -error_cipher: - crypto_free_skcipher(big_key_skcipher); -error_rng: - crypto_free_rng(big_key_rng); +free_aead: + crypto_free_aead(big_key_aead); return ret; } diff --git a/security/keys/internal.h b/security/keys/internal.h index 1c02c6547038..503adbae7b0d 100644 --- a/security/keys/internal.h +++ b/security/keys/internal.h @@ -141,7 +141,7 @@ extern key_ref_t keyring_search_aux(key_ref_t keyring_ref, extern key_ref_t search_my_process_keyrings(struct keyring_search_context *ctx); extern key_ref_t search_process_keyrings(struct keyring_search_context *ctx); -extern struct key *find_keyring_by_name(const char *name, bool skip_perm_check); +extern struct key *find_keyring_by_name(const char *name, bool uid_keyring); extern int install_user_keyrings(void); extern int install_thread_keyring_to_cred(struct cred *); diff --git a/security/keys/key.c b/security/keys/key.c index 83da68d98b40..eb914a838840 100644 --- a/security/keys/key.c +++ b/security/keys/key.c @@ -54,10 +54,10 @@ void __key_check(const struct key *key) struct key_user *key_user_lookup(kuid_t uid) { struct key_user *candidate = NULL, *user; - struct rb_node *parent = NULL; - struct rb_node **p; + struct rb_node *parent, **p; try_again: + parent = NULL; p = &key_user_tree.rb_node; spin_lock(&key_user_lock); @@ -302,6 +302,8 @@ struct key *key_alloc(struct key_type *type, const char *desc, key->flags |= 1 << KEY_FLAG_IN_QUOTA; if (flags & KEY_ALLOC_BUILT_IN) key->flags |= 1 << KEY_FLAG_BUILTIN; + if (flags & KEY_ALLOC_UID_KEYRING) + key->flags |= 1 << KEY_FLAG_UID_KEYRING; #ifdef KEY_DEBUGGING key->magic = KEY_DEBUG_MAGIC; diff --git a/security/keys/keyctl.c b/security/keys/keyctl.c index ab0b337c84b4..365ff85d7e27 100644 --- a/security/keys/keyctl.c +++ b/security/keys/keyctl.c @@ -766,12 +766,17 @@ long keyctl_read_key(key_serial_t keyid, char __user *buffer, size_t buflen) key = key_ref_to_ptr(key_ref); + if (test_bit(KEY_FLAG_NEGATIVE, &key->flags)) { + ret = -ENOKEY; + goto error2; + } + /* see if we can read it directly */ ret = key_permission(key_ref, KEY_NEED_READ); if (ret == 0) goto can_read_key; if (ret != -EACCES) - goto error; + goto error2; /* we can't; see if it's searchable from this process's keyrings * - we automatically take account of the fact that it may be @@ -1406,11 +1411,9 @@ long keyctl_assume_authority(key_serial_t id) } ret = keyctl_change_reqkey_auth(authkey); - if (ret < 0) - goto error; + if (ret == 0) + ret = authkey->serial; key_put(authkey); - - ret = authkey->serial; error: return ret; } diff --git a/security/keys/keyring.c b/security/keys/keyring.c index de81793f9920..4fa82a8a9c0e 100644 --- a/security/keys/keyring.c +++ b/security/keys/keyring.c @@ -423,7 +423,7 @@ static void keyring_describe(const struct key *keyring, struct seq_file *m) } struct keyring_read_iterator_context { - size_t qty; + size_t buflen; size_t count; key_serial_t __user *buffer; }; @@ -435,9 +435,9 @@ static int keyring_read_iterator(const void *object, void *data) int ret; kenter("{%s,%d},,{%zu/%zu}", - key->type->name, key->serial, ctx->count, ctx->qty); + key->type->name, key->serial, ctx->count, ctx->buflen); - if (ctx->count >= ctx->qty) + if (ctx->count >= ctx->buflen) return 1; ret = put_user(key->serial, ctx->buffer); @@ -472,16 +472,12 @@ static long keyring_read(const struct key *keyring, return 0; /* Calculate how much data we could return */ - ctx.qty = nr_keys * sizeof(key_serial_t); - if (!buffer || !buflen) - return ctx.qty; - - if (buflen > ctx.qty) - ctx.qty = buflen; + return nr_keys * sizeof(key_serial_t); /* Copy the IDs of the subscribed keys into the buffer */ ctx.buffer = (key_serial_t __user *)buffer; + ctx.buflen = buflen; ctx.count = 0; ret = assoc_array_iterate(&keyring->keys, keyring_read_iterator, &ctx); if (ret < 0) { @@ -1101,15 +1097,15 @@ found: /* * Find a keyring with the specified name. * - * All named keyrings in the current user namespace are searched, provided they - * grant Search permission directly to the caller (unless this check is - * skipped). Keyrings whose usage points have reached zero or who have been - * revoked are skipped. + * Only keyrings that have nonzero refcount, are not revoked, and are owned by a + * user in the current user namespace are considered. If @uid_keyring is %true, + * the keyring additionally must have been allocated as a user or user session + * keyring; otherwise, it must grant Search permission directly to the caller. * * Returns a pointer to the keyring with the keyring's refcount having being * incremented on success. -ENOKEY is returned if a key could not be found. */ -struct key *find_keyring_by_name(const char *name, bool skip_perm_check) +struct key *find_keyring_by_name(const char *name, bool uid_keyring) { struct key *keyring; int bucket; @@ -1137,10 +1133,15 @@ struct key *find_keyring_by_name(const char *name, bool skip_perm_check) if (strcmp(keyring->description, name) != 0) continue; - if (!skip_perm_check && - key_permission(make_key_ref(keyring, 0), - KEY_NEED_SEARCH) < 0) - continue; + if (uid_keyring) { + if (!test_bit(KEY_FLAG_UID_KEYRING, + &keyring->flags)) + continue; + } else { + if (key_permission(make_key_ref(keyring, 0), + KEY_NEED_SEARCH) < 0) + continue; + } /* we've got a match but we might end up racing with * key_cleanup() if the keyring is currently 'dead' diff --git a/security/keys/proc.c b/security/keys/proc.c index bf08d02b6646..de834309d100 100644 --- a/security/keys/proc.c +++ b/security/keys/proc.c @@ -187,7 +187,7 @@ static int proc_keys_show(struct seq_file *m, void *v) struct keyring_search_context ctx = { .index_key.type = key->type, .index_key.description = key->description, - .cred = current_cred(), + .cred = m->file->f_cred, .match_data.cmp = lookup_user_key_possessed, .match_data.raw_data = key, .match_data.lookup_type = KEYRING_SEARCH_LOOKUP_DIRECT, @@ -207,11 +207,7 @@ static int proc_keys_show(struct seq_file *m, void *v) } } - /* check whether the current task is allowed to view the key (assuming - * non-possession) - * - the caller holds a spinlock, and thus the RCU read lock, making our - * access to __current_cred() safe - */ + /* check whether the current task is allowed to view the key */ rc = key_task_permission(key_ref, ctx.cred, KEY_NEED_VIEW); if (rc < 0) return 0; diff --git a/security/keys/process_keys.c b/security/keys/process_keys.c index 86bced9fdbdf..293d3598153b 100644 --- a/security/keys/process_keys.c +++ b/security/keys/process_keys.c @@ -77,7 +77,8 @@ int install_user_keyrings(void) if (IS_ERR(uid_keyring)) { uid_keyring = keyring_alloc(buf, user->uid, INVALID_GID, cred, user_keyring_perm, - KEY_ALLOC_IN_QUOTA, + KEY_ALLOC_UID_KEYRING | + KEY_ALLOC_IN_QUOTA, NULL, NULL); if (IS_ERR(uid_keyring)) { ret = PTR_ERR(uid_keyring); @@ -94,7 +95,8 @@ int install_user_keyrings(void) session_keyring = keyring_alloc(buf, user->uid, INVALID_GID, cred, user_keyring_perm, - KEY_ALLOC_IN_QUOTA, + KEY_ALLOC_UID_KEYRING | + KEY_ALLOC_IN_QUOTA, NULL, NULL); if (IS_ERR(session_keyring)) { ret = PTR_ERR(session_keyring); diff --git a/security/keys/request_key_auth.c b/security/keys/request_key_auth.c index afe9d22ab361..6ebf1af8fce9 100644 --- a/security/keys/request_key_auth.c +++ b/security/keys/request_key_auth.c @@ -120,6 +120,18 @@ static void request_key_auth_revoke(struct key *key) } } +static void free_request_key_auth(struct request_key_auth *rka) +{ + if (!rka) + return; + key_put(rka->target_key); + key_put(rka->dest_keyring); + if (rka->cred) + put_cred(rka->cred); + kfree(rka->callout_info); + kfree(rka); +} + /* * Destroy an instantiation authorisation token key. */ @@ -129,15 +141,7 @@ static void request_key_auth_destroy(struct key *key) kenter("{%d}", key->serial); - if (rka->cred) { - put_cred(rka->cred); - rka->cred = NULL; - } - - key_put(rka->target_key); - key_put(rka->dest_keyring); - kfree(rka->callout_info); - kfree(rka); + free_request_key_auth(rka); } /* @@ -151,22 +155,18 @@ struct key *request_key_auth_new(struct key *target, const void *callout_info, const struct cred *cred = current->cred; struct key *authkey = NULL; char desc[20]; - int ret; + int ret = -ENOMEM; kenter("%d,", target->serial); /* allocate a auth record */ - rka = kmalloc(sizeof(*rka), GFP_KERNEL); - if (!rka) { - kleave(" = -ENOMEM"); - return ERR_PTR(-ENOMEM); - } - rka->callout_info = kmalloc(callout_len, GFP_KERNEL); - if (!rka->callout_info) { - kleave(" = -ENOMEM"); - kfree(rka); - return ERR_PTR(-ENOMEM); - } + rka = kzalloc(sizeof(*rka), GFP_KERNEL); + if (!rka) + goto error; + rka->callout_info = kmemdup(callout_info, callout_len, GFP_KERNEL); + if (!rka->callout_info) + goto error_free_rka; + rka->callout_len = callout_len; /* see if the calling process is already servicing the key request of * another process */ @@ -176,8 +176,12 @@ struct key *request_key_auth_new(struct key *target, const void *callout_info, /* if the auth key has been revoked, then the key we're * servicing is already instantiated */ - if (test_bit(KEY_FLAG_REVOKED, &cred->request_key_auth->flags)) - goto auth_key_revoked; + if (test_bit(KEY_FLAG_REVOKED, + &cred->request_key_auth->flags)) { + up_read(&cred->request_key_auth->sem); + ret = -EKEYREVOKED; + goto error_free_rka; + } irka = cred->request_key_auth->payload.data[0]; rka->cred = get_cred(irka->cred); @@ -193,8 +197,6 @@ struct key *request_key_auth_new(struct key *target, const void *callout_info, rka->target_key = key_get(target); rka->dest_keyring = key_get(dest_keyring); - memcpy(rka->callout_info, callout_info, callout_len); - rka->callout_len = callout_len; /* allocate the auth key */ sprintf(desc, "%x", target->serial); @@ -205,32 +207,22 @@ struct key *request_key_auth_new(struct key *target, const void *callout_info, KEY_USR_VIEW, KEY_ALLOC_NOT_IN_QUOTA, NULL); if (IS_ERR(authkey)) { ret = PTR_ERR(authkey); - goto error_alloc; + goto error_free_rka; } /* construct the auth key */ ret = key_instantiate_and_link(authkey, rka, 0, NULL, NULL); if (ret < 0) - goto error_inst; + goto error_put_authkey; kleave(" = {%d,%d}", authkey->serial, refcount_read(&authkey->usage)); return authkey; -auth_key_revoked: - up_read(&cred->request_key_auth->sem); - kfree(rka->callout_info); - kfree(rka); - kleave("= -EKEYREVOKED"); - return ERR_PTR(-EKEYREVOKED); - -error_inst: - key_revoke(authkey); +error_put_authkey: key_put(authkey); -error_alloc: - key_put(rka->target_key); - key_put(rka->dest_keyring); - kfree(rka->callout_info); - kfree(rka); +error_free_rka: + free_request_key_auth(rka); +error: kleave("= %d", ret); return ERR_PTR(ret); } diff --git a/security/smack/smack_lsm.c b/security/smack/smack_lsm.c index 319add31b4a4..286171a16ed2 100644 --- a/security/smack/smack_lsm.c +++ b/security/smack/smack_lsm.c @@ -1473,7 +1473,7 @@ static int smack_inode_removexattr(struct dentry *dentry, const char *name) * @inode: the object * @name: attribute name * @buffer: where to put the result - * @alloc: unused + * @alloc: duplicate memory * * Returns the size of the attribute or an error code */ @@ -1486,43 +1486,38 @@ static int smack_inode_getsecurity(struct inode *inode, struct super_block *sbp; struct inode *ip = (struct inode *)inode; struct smack_known *isp; - int ilen; - int rc = 0; - if (strcmp(name, XATTR_SMACK_SUFFIX) == 0) { + if (strcmp(name, XATTR_SMACK_SUFFIX) == 0) isp = smk_of_inode(inode); - ilen = strlen(isp->smk_known); - *buffer = isp->smk_known; - return ilen; - } + else { + /* + * The rest of the Smack xattrs are only on sockets. + */ + sbp = ip->i_sb; + if (sbp->s_magic != SOCKFS_MAGIC) + return -EOPNOTSUPP; - /* - * The rest of the Smack xattrs are only on sockets. - */ - sbp = ip->i_sb; - if (sbp->s_magic != SOCKFS_MAGIC) - return -EOPNOTSUPP; + sock = SOCKET_I(ip); + if (sock == NULL || sock->sk == NULL) + return -EOPNOTSUPP; - sock = SOCKET_I(ip); - if (sock == NULL || sock->sk == NULL) - return -EOPNOTSUPP; - - ssp = sock->sk->sk_security; + ssp = sock->sk->sk_security; - if (strcmp(name, XATTR_SMACK_IPIN) == 0) - isp = ssp->smk_in; - else if (strcmp(name, XATTR_SMACK_IPOUT) == 0) - isp = ssp->smk_out; - else - return -EOPNOTSUPP; + if (strcmp(name, XATTR_SMACK_IPIN) == 0) + isp = ssp->smk_in; + else if (strcmp(name, XATTR_SMACK_IPOUT) == 0) + isp = ssp->smk_out; + else + return -EOPNOTSUPP; + } - ilen = strlen(isp->smk_known); - if (rc == 0) { - *buffer = isp->smk_known; - rc = ilen; + if (alloc) { + *buffer = kstrdup(isp->smk_known, GFP_KERNEL); + if (*buffer == NULL) + return -ENOMEM; } - return rc; + return strlen(isp->smk_known); } diff --git a/sound/core/compress_offload.c b/sound/core/compress_offload.c index fec1dfdb14ad..4490a699030b 100644 --- a/sound/core/compress_offload.c +++ b/sound/core/compress_offload.c @@ -948,14 +948,13 @@ static const struct file_operations snd_compr_file_ops = { static int snd_compress_dev_register(struct snd_device *device) { int ret = -EINVAL; - char str[16]; struct snd_compr *compr; if (snd_BUG_ON(!device || !device->device_data)) return -EBADFD; compr = device->device_data; - pr_debug("reg %s for device %s, direction %d\n", str, compr->name, + pr_debug("reg device %s, direction %d\n", compr->name, compr->direction); /* register compressed device */ ret = snd_register_device(SNDRV_DEVICE_TYPE_COMPRESS, diff --git a/sound/core/pcm_compat.c b/sound/core/pcm_compat.c index 3a1cc7b97e46..b719d0bd833e 100644 --- a/sound/core/pcm_compat.c +++ b/sound/core/pcm_compat.c @@ -547,6 +547,7 @@ struct snd_pcm_mmap_status_x32 { u32 pad2; /* alignment */ struct timespec tstamp; s32 suspended_state; + s32 pad3; struct timespec audio_tstamp; } __packed; diff --git a/sound/pci/asihpi/hpioctl.c b/sound/pci/asihpi/hpioctl.c index 7e3aa50b21f9..5badd08e1d69 100644 --- a/sound/pci/asihpi/hpioctl.c +++ b/sound/pci/asihpi/hpioctl.c @@ -103,6 +103,7 @@ long asihpi_hpi_ioctl(struct file *file, unsigned int cmd, unsigned long arg) void __user *puhr; union hpi_message_buffer_v1 *hm; union hpi_response_buffer_v1 *hr; + u16 msg_size; u16 res_max_size; u32 uncopied_bytes; int err = 0; @@ -127,22 +128,25 @@ long asihpi_hpi_ioctl(struct file *file, unsigned int cmd, unsigned long arg) } /* Now read the message size and data from user space. */ - if (get_user(hm->h.size, (u16 __user *)puhm)) { + if (get_user(msg_size, (u16 __user *)puhm)) { err = -EFAULT; goto out; } - if (hm->h.size > sizeof(*hm)) - hm->h.size = sizeof(*hm); + if (msg_size > sizeof(*hm)) + msg_size = sizeof(*hm); /* printk(KERN_INFO "message size %d\n", hm->h.wSize); */ - uncopied_bytes = copy_from_user(hm, puhm, hm->h.size); + uncopied_bytes = copy_from_user(hm, puhm, msg_size); if (uncopied_bytes) { HPI_DEBUG_LOG(ERROR, "uncopied bytes %d\n", uncopied_bytes); err = -EFAULT; goto out; } + /* Override h.size in case it is changed between two userspace fetches */ + hm->h.size = msg_size; + if (get_user(res_max_size, (u16 __user *)puhr)) { err = -EFAULT; goto out; diff --git a/sound/pci/echoaudio/echoaudio.c b/sound/pci/echoaudio/echoaudio.c index 7326695bca33..d68f99e076a8 100644 --- a/sound/pci/echoaudio/echoaudio.c +++ b/sound/pci/echoaudio/echoaudio.c @@ -1272,11 +1272,11 @@ static int snd_echo_mixer_info(struct snd_kcontrol *kcontrol, chip = snd_kcontrol_chip(kcontrol); uinfo->type = SNDRV_CTL_ELEM_TYPE_INTEGER; + uinfo->count = 1; uinfo->value.integer.min = ECHOGAIN_MINOUT; uinfo->value.integer.max = ECHOGAIN_MAXOUT; uinfo->dimen.d[0] = num_busses_out(chip); uinfo->dimen.d[1] = num_busses_in(chip); - uinfo->count = uinfo->dimen.d[0] * uinfo->dimen.d[1]; return 0; } @@ -1344,11 +1344,11 @@ static int snd_echo_vmixer_info(struct snd_kcontrol *kcontrol, chip = snd_kcontrol_chip(kcontrol); uinfo->type = SNDRV_CTL_ELEM_TYPE_INTEGER; + uinfo->count = 1; uinfo->value.integer.min = ECHOGAIN_MINOUT; uinfo->value.integer.max = ECHOGAIN_MAXOUT; uinfo->dimen.d[0] = num_busses_out(chip); uinfo->dimen.d[1] = num_pipes_out(chip); - uinfo->count = uinfo->dimen.d[0] * uinfo->dimen.d[1]; return 0; } @@ -1728,6 +1728,7 @@ static int snd_echo_vumeters_info(struct snd_kcontrol *kcontrol, struct snd_ctl_elem_info *uinfo) { uinfo->type = SNDRV_CTL_ELEM_TYPE_INTEGER; + uinfo->count = 96; uinfo->value.integer.min = ECHOGAIN_MINOUT; uinfo->value.integer.max = 0; #ifdef ECHOCARD_HAS_VMIXER @@ -1737,7 +1738,6 @@ static int snd_echo_vumeters_info(struct snd_kcontrol *kcontrol, #endif uinfo->dimen.d[1] = 16; /* 16 channels */ uinfo->dimen.d[2] = 2; /* 0=level, 1=peak */ - uinfo->count = uinfo->dimen.d[0] * uinfo->dimen.d[1] * uinfo->dimen.d[2]; return 0; } diff --git a/sound/pci/hda/patch_hdmi.c b/sound/pci/hda/patch_hdmi.c index 2b64fabd5faa..c19c81d230bd 100644 --- a/sound/pci/hda/patch_hdmi.c +++ b/sound/pci/hda/patch_hdmi.c @@ -906,6 +906,7 @@ static int hdmi_setup_stream(struct hda_codec *codec, hda_nid_t cvt_nid, hda_nid_t pin_nid, u32 stream_tag, int format) { struct hdmi_spec *spec = codec->spec; + unsigned int param; int err; err = spec->ops.pin_hbr_setup(codec, pin_nid, is_hbr_format(format)); @@ -915,6 +916,26 @@ static int hdmi_setup_stream(struct hda_codec *codec, hda_nid_t cvt_nid, return err; } + if (is_haswell_plus(codec)) { + + /* + * on recent platforms IEC Coding Type is required for HBR + * support, read current Digital Converter settings and set + * ICT bitfield if needed. + */ + param = snd_hda_codec_read(codec, cvt_nid, 0, + AC_VERB_GET_DIGI_CONVERT_1, 0); + + param = (param >> 16) & ~(AC_DIG3_ICT); + + /* on recent platforms ICT mode is required for HBR support */ + if (is_hbr_format(format)) + param |= 0x1; + + snd_hda_codec_write(codec, cvt_nid, 0, + AC_VERB_SET_DIGI_CONVERT_3, param); + } + snd_hda_codec_setup_stream(codec, cvt_nid, stream_tag, 0, format); return 0; } diff --git a/sound/usb/card.c b/sound/usb/card.c index 3dc36d913550..23d1d23aefec 100644 --- a/sound/usb/card.c +++ b/sound/usb/card.c @@ -221,6 +221,7 @@ static int snd_usb_create_streams(struct snd_usb_audio *chip, int ctrlif) struct usb_interface_descriptor *altsd; void *control_header; int i, protocol; + int rest_bytes; /* find audiocontrol interface */ host_iface = &usb_ifnum_to_if(dev, ctrlif)->altsetting[0]; @@ -235,6 +236,15 @@ static int snd_usb_create_streams(struct snd_usb_audio *chip, int ctrlif) return -EINVAL; } + rest_bytes = (void *)(host_iface->extra + host_iface->extralen) - + control_header; + + /* just to be sure -- this shouldn't hit at all */ + if (rest_bytes <= 0) { + dev_err(&dev->dev, "invalid control header\n"); + return -EINVAL; + } + switch (protocol) { default: dev_warn(&dev->dev, @@ -245,11 +255,21 @@ static int snd_usb_create_streams(struct snd_usb_audio *chip, int ctrlif) case UAC_VERSION_1: { struct uac1_ac_header_descriptor *h1 = control_header; + if (rest_bytes < sizeof(*h1)) { + dev_err(&dev->dev, "too short v1 buffer descriptor\n"); + return -EINVAL; + } + if (!h1->bInCollection) { dev_info(&dev->dev, "skipping empty audio interface (v1)\n"); return -EINVAL; } + if (rest_bytes < h1->bLength) { + dev_err(&dev->dev, "invalid buffer length (v1)\n"); + return -EINVAL; + } + if (h1->bLength < sizeof(*h1) + h1->bInCollection) { dev_err(&dev->dev, "invalid UAC_HEADER (v1)\n"); return -EINVAL; diff --git a/sound/usb/quirks.c b/sound/usb/quirks.c index 913552078285..b8cb57aeec77 100644 --- a/sound/usb/quirks.c +++ b/sound/usb/quirks.c @@ -1137,6 +1137,8 @@ bool snd_usb_get_sample_rate_quirk(struct snd_usb_audio *chip) case USB_ID(0x047F, 0x02F7): /* Plantronics BT-600 */ case USB_ID(0x047F, 0x0415): /* Plantronics BT-300 */ case USB_ID(0x047F, 0xAA05): /* Plantronics DA45 */ + case USB_ID(0x047F, 0xC022): /* Plantronics C310 */ + case USB_ID(0x047F, 0xC036): /* Plantronics C520-M */ case USB_ID(0x04D8, 0xFEEA): /* Benchmark DAC1 Pre */ case USB_ID(0x0556, 0x0014): /* Phoenix Audio TMX320VC */ case USB_ID(0x05A3, 0x9420): /* ELP HD USB Camera */ diff --git a/sound/usb/usx2y/usb_stream.c b/sound/usb/usx2y/usb_stream.c index 4dab49080700..e229abd21652 100644 --- a/sound/usb/usx2y/usb_stream.c +++ b/sound/usb/usx2y/usb_stream.c @@ -191,7 +191,8 @@ struct usb_stream *usb_stream_new(struct usb_stream_kernel *sk, } pg = get_order(read_size); - sk->s = (void *) __get_free_pages(GFP_KERNEL|__GFP_COMP|__GFP_ZERO, pg); + sk->s = (void *) __get_free_pages(GFP_KERNEL|__GFP_COMP|__GFP_ZERO| + __GFP_NOWARN, pg); if (!sk->s) { snd_printk(KERN_WARNING "couldn't __get_free_pages()\n"); goto out; @@ -211,7 +212,8 @@ struct usb_stream *usb_stream_new(struct usb_stream_kernel *sk, pg = get_order(write_size); sk->write_page = - (void *)__get_free_pages(GFP_KERNEL|__GFP_COMP|__GFP_ZERO, pg); + (void *)__get_free_pages(GFP_KERNEL|__GFP_COMP|__GFP_ZERO| + __GFP_NOWARN, pg); if (!sk->write_page) { snd_printk(KERN_WARNING "couldn't __get_free_pages()\n"); usb_stream_free(sk); diff --git a/tools/arch/s390/include/uapi/asm/kvm.h b/tools/arch/s390/include/uapi/asm/kvm.h index 69d09c39bbcd..cd7359e23d86 100644 --- a/tools/arch/s390/include/uapi/asm/kvm.h +++ b/tools/arch/s390/include/uapi/asm/kvm.h @@ -88,6 +88,12 @@ struct kvm_s390_io_adapter_req { /* kvm attributes for KVM_S390_VM_TOD */ #define KVM_S390_VM_TOD_LOW 0 #define KVM_S390_VM_TOD_HIGH 1 +#define KVM_S390_VM_TOD_EXT 2 + +struct kvm_s390_vm_tod_clock { + __u8 epoch_idx; + __u64 tod; +}; /* kvm attributes for KVM_S390_VM_CPU_MODEL */ /* processor related attributes are r/w */ diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h index 8ea315a11fe0..2519c6c801c9 100644 --- a/tools/arch/x86/include/asm/cpufeatures.h +++ b/tools/arch/x86/include/asm/cpufeatures.h @@ -196,6 +196,7 @@ #define X86_FEATURE_HW_PSTATE ( 7*32+ 8) /* AMD HW-PState */ #define X86_FEATURE_PROC_FEEDBACK ( 7*32+ 9) /* AMD ProcFeedbackInterface */ +#define X86_FEATURE_SME ( 7*32+10) /* AMD Secure Memory Encryption */ #define X86_FEATURE_INTEL_PPIN ( 7*32+14) /* Intel Processor Inventory Number */ #define X86_FEATURE_INTEL_PT ( 7*32+15) /* Intel Processor Trace */ @@ -287,6 +288,7 @@ #define X86_FEATURE_PFTHRESHOLD (15*32+12) /* pause filter threshold */ #define X86_FEATURE_AVIC (15*32+13) /* Virtual Interrupt Controller */ #define X86_FEATURE_V_VMSAVE_VMLOAD (15*32+15) /* Virtual VMSAVE VMLOAD */ +#define X86_FEATURE_VGIF (15*32+16) /* Virtual GIF */ /* Intel-defined CPU features, CPUID level 0x00000007:0 (ecx), word 16 */ #define X86_FEATURE_AVX512VBMI (16*32+ 1) /* AVX512 Vector Bit Manipulation instructions*/ diff --git a/tools/arch/x86/include/asm/disabled-features.h b/tools/arch/x86/include/asm/disabled-features.h index 5dff775af7cd..c10c9128f54e 100644 --- a/tools/arch/x86/include/asm/disabled-features.h +++ b/tools/arch/x86/include/asm/disabled-features.h @@ -21,11 +21,13 @@ # define DISABLE_K6_MTRR (1<<(X86_FEATURE_K6_MTRR & 31)) # define DISABLE_CYRIX_ARR (1<<(X86_FEATURE_CYRIX_ARR & 31)) # define DISABLE_CENTAUR_MCR (1<<(X86_FEATURE_CENTAUR_MCR & 31)) +# define DISABLE_PCID 0 #else # define DISABLE_VME 0 # define DISABLE_K6_MTRR 0 # define DISABLE_CYRIX_ARR 0 # define DISABLE_CENTAUR_MCR 0 +# define DISABLE_PCID (1<<(X86_FEATURE_PCID & 31)) #endif /* CONFIG_X86_64 */ #ifdef CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS @@ -49,7 +51,7 @@ #define DISABLED_MASK1 0 #define DISABLED_MASK2 0 #define DISABLED_MASK3 (DISABLE_CYRIX_ARR|DISABLE_CENTAUR_MCR|DISABLE_K6_MTRR) -#define DISABLED_MASK4 0 +#define DISABLED_MASK4 (DISABLE_PCID) #define DISABLED_MASK5 0 #define DISABLED_MASK6 0 #define DISABLED_MASK7 0 diff --git a/tools/include/asm-generic/hugetlb_encode.h b/tools/include/asm-generic/hugetlb_encode.h new file mode 100644 index 000000000000..e4732d3c2998 --- /dev/null +++ b/tools/include/asm-generic/hugetlb_encode.h @@ -0,0 +1,34 @@ +#ifndef _ASM_GENERIC_HUGETLB_ENCODE_H_ +#define _ASM_GENERIC_HUGETLB_ENCODE_H_ + +/* + * Several system calls take a flag to request "hugetlb" huge pages. + * Without further specification, these system calls will use the + * system's default huge page size. If a system supports multiple + * huge page sizes, the desired huge page size can be specified in + * bits [26:31] of the flag arguments. The value in these 6 bits + * will encode the log2 of the huge page size. + * + * The following definitions are associated with this huge page size + * encoding in flag arguments. System call specific header files + * that use this encoding should include this file. They can then + * provide definitions based on these with their own specific prefix. + * for example: + * #define MAP_HUGE_SHIFT HUGETLB_FLAG_ENCODE_SHIFT + */ + +#define HUGETLB_FLAG_ENCODE_SHIFT 26 +#define HUGETLB_FLAG_ENCODE_MASK 0x3f + +#define HUGETLB_FLAG_ENCODE_64KB (16 << HUGETLB_FLAG_ENCODE_SHIFT) +#define HUGETLB_FLAG_ENCODE_512KB (19 << HUGETLB_FLAG_ENCODE_SHIFT) +#define HUGETLB_FLAG_ENCODE_1MB (20 << HUGETLB_FLAG_ENCODE_SHIFT) +#define HUGETLB_FLAG_ENCODE_2MB (21 << HUGETLB_FLAG_ENCODE_SHIFT) +#define HUGETLB_FLAG_ENCODE_8MB (23 << HUGETLB_FLAG_ENCODE_SHIFT) +#define HUGETLB_FLAG_ENCODE_16MB (24 << HUGETLB_FLAG_ENCODE_SHIFT) +#define HUGETLB_FLAG_ENCODE_256MB (28 << HUGETLB_FLAG_ENCODE_SHIFT) +#define HUGETLB_FLAG_ENCODE_1GB (30 << HUGETLB_FLAG_ENCODE_SHIFT) +#define HUGETLB_FLAG_ENCODE_2GB (31 << HUGETLB_FLAG_ENCODE_SHIFT) +#define HUGETLB_FLAG_ENCODE_16GB (34 << HUGETLB_FLAG_ENCODE_SHIFT) + +#endif /* _ASM_GENERIC_HUGETLB_ENCODE_H_ */ diff --git a/tools/include/uapi/asm-generic/mman-common.h b/tools/include/uapi/asm-generic/mman-common.h index 8c27db0c5c08..203268f9231e 100644 --- a/tools/include/uapi/asm-generic/mman-common.h +++ b/tools/include/uapi/asm-generic/mman-common.h @@ -58,20 +58,12 @@ overrides the coredump filter bits */ #define MADV_DODUMP 17 /* Clear the MADV_DONTDUMP flag */ +#define MADV_WIPEONFORK 18 /* Zero memory on fork, child only */ +#define MADV_KEEPONFORK 19 /* Undo MADV_WIPEONFORK */ + /* compatibility flags */ #define MAP_FILE 0 -/* - * When MAP_HUGETLB is set bits [26:31] encode the log2 of the huge page size. - * This gives us 6 bits, which is enough until someone invents 128 bit address - * spaces. - * - * Assume these are all power of twos. - * When 0 use the default page size. - */ -#define MAP_HUGE_SHIFT 26 -#define MAP_HUGE_MASK 0x3f - #define PKEY_DISABLE_ACCESS 0x1 #define PKEY_DISABLE_WRITE 0x2 #define PKEY_ACCESS_MASK (PKEY_DISABLE_ACCESS |\ diff --git a/tools/include/uapi/drm/drm.h b/tools/include/uapi/drm/drm.h index 101593ab10ac..97677cd6964d 100644 --- a/tools/include/uapi/drm/drm.h +++ b/tools/include/uapi/drm/drm.h @@ -700,6 +700,7 @@ struct drm_prime_handle { struct drm_syncobj_create { __u32 handle; +#define DRM_SYNCOBJ_CREATE_SIGNALED (1 << 0) __u32 flags; }; @@ -718,6 +719,24 @@ struct drm_syncobj_handle { __u32 pad; }; +#define DRM_SYNCOBJ_WAIT_FLAGS_WAIT_ALL (1 << 0) +#define DRM_SYNCOBJ_WAIT_FLAGS_WAIT_FOR_SUBMIT (1 << 1) +struct drm_syncobj_wait { + __u64 handles; + /* absolute timeout */ + __s64 timeout_nsec; + __u32 count_handles; + __u32 flags; + __u32 first_signaled; /* only valid when not waiting all */ + __u32 pad; +}; + +struct drm_syncobj_array { + __u64 handles; + __u32 count_handles; + __u32 pad; +}; + #if defined(__cplusplus) } #endif @@ -840,6 +859,9 @@ extern "C" { #define DRM_IOCTL_SYNCOBJ_DESTROY DRM_IOWR(0xC0, struct drm_syncobj_destroy) #define DRM_IOCTL_SYNCOBJ_HANDLE_TO_FD DRM_IOWR(0xC1, struct drm_syncobj_handle) #define DRM_IOCTL_SYNCOBJ_FD_TO_HANDLE DRM_IOWR(0xC2, struct drm_syncobj_handle) +#define DRM_IOCTL_SYNCOBJ_WAIT DRM_IOWR(0xC3, struct drm_syncobj_wait) +#define DRM_IOCTL_SYNCOBJ_RESET DRM_IOWR(0xC4, struct drm_syncobj_array) +#define DRM_IOCTL_SYNCOBJ_SIGNAL DRM_IOWR(0xC5, struct drm_syncobj_array) /** * Device specific ioctls should only be in their respective headers diff --git a/tools/include/uapi/drm/i915_drm.h b/tools/include/uapi/drm/i915_drm.h index 7ccbd6a2bbe0..6598fb76d2c2 100644 --- a/tools/include/uapi/drm/i915_drm.h +++ b/tools/include/uapi/drm/i915_drm.h @@ -260,6 +260,8 @@ typedef struct _drm_i915_sarea { #define DRM_I915_GEM_CONTEXT_GETPARAM 0x34 #define DRM_I915_GEM_CONTEXT_SETPARAM 0x35 #define DRM_I915_PERF_OPEN 0x36 +#define DRM_I915_PERF_ADD_CONFIG 0x37 +#define DRM_I915_PERF_REMOVE_CONFIG 0x38 #define DRM_IOCTL_I915_INIT DRM_IOW( DRM_COMMAND_BASE + DRM_I915_INIT, drm_i915_init_t) #define DRM_IOCTL_I915_FLUSH DRM_IO ( DRM_COMMAND_BASE + DRM_I915_FLUSH) @@ -315,6 +317,8 @@ typedef struct _drm_i915_sarea { #define DRM_IOCTL_I915_GEM_CONTEXT_GETPARAM DRM_IOWR (DRM_COMMAND_BASE + DRM_I915_GEM_CONTEXT_GETPARAM, struct drm_i915_gem_context_param) #define DRM_IOCTL_I915_GEM_CONTEXT_SETPARAM DRM_IOWR (DRM_COMMAND_BASE + DRM_I915_GEM_CONTEXT_SETPARAM, struct drm_i915_gem_context_param) #define DRM_IOCTL_I915_PERF_OPEN DRM_IOW(DRM_COMMAND_BASE + DRM_I915_PERF_OPEN, struct drm_i915_perf_open_param) +#define DRM_IOCTL_I915_PERF_ADD_CONFIG DRM_IOW(DRM_COMMAND_BASE + DRM_I915_PERF_ADD_CONFIG, struct drm_i915_perf_oa_config) +#define DRM_IOCTL_I915_PERF_REMOVE_CONFIG DRM_IOW(DRM_COMMAND_BASE + DRM_I915_PERF_REMOVE_CONFIG, __u64) /* Allow drivers to submit batchbuffers directly to hardware, relying * on the security mechanisms provided by hardware. @@ -431,6 +435,11 @@ typedef struct drm_i915_irq_wait { */ #define I915_PARAM_HAS_EXEC_BATCH_FIRST 48 +/* Query whether DRM_I915_GEM_EXECBUFFER2 supports supplying an array of + * drm_i915_gem_exec_fence structures. See I915_EXEC_FENCE_ARRAY. + */ +#define I915_PARAM_HAS_EXEC_FENCE_ARRAY 49 + typedef struct drm_i915_getparam { __s32 param; /* @@ -812,6 +821,17 @@ struct drm_i915_gem_exec_object2 { __u64 rsvd2; }; +struct drm_i915_gem_exec_fence { + /** + * User's handle for a drm_syncobj to wait on or signal. + */ + __u32 handle; + +#define I915_EXEC_FENCE_WAIT (1<<0) +#define I915_EXEC_FENCE_SIGNAL (1<<1) + __u32 flags; +}; + struct drm_i915_gem_execbuffer2 { /** * List of gem_exec_object2 structs @@ -826,7 +846,11 @@ struct drm_i915_gem_execbuffer2 { __u32 DR1; __u32 DR4; __u32 num_cliprects; - /** This is a struct drm_clip_rect *cliprects */ + /** + * This is a struct drm_clip_rect *cliprects if I915_EXEC_FENCE_ARRAY + * is not set. If I915_EXEC_FENCE_ARRAY is set, then this is a + * struct drm_i915_gem_exec_fence *fences. + */ __u64 cliprects_ptr; #define I915_EXEC_RING_MASK (7<<0) #define I915_EXEC_DEFAULT (0<<0) @@ -927,7 +951,14 @@ struct drm_i915_gem_execbuffer2 { * element). */ #define I915_EXEC_BATCH_FIRST (1<<18) -#define __I915_EXEC_UNKNOWN_FLAGS (-(I915_EXEC_BATCH_FIRST<<1)) + +/* Setting I915_FENCE_ARRAY implies that num_cliprects and cliprects_ptr + * define an array of i915_gem_exec_fence structures which specify a set of + * dma fences to wait upon or signal. + */ +#define I915_EXEC_FENCE_ARRAY (1<<19) + +#define __I915_EXEC_UNKNOWN_FLAGS (-(I915_EXEC_FENCE_ARRAY<<1)) #define I915_EXEC_CONTEXT_ID_MASK (0xffffffff) #define i915_execbuffer2_set_context_id(eb2, context) \ @@ -1467,6 +1498,22 @@ enum drm_i915_perf_record_type { DRM_I915_PERF_RECORD_MAX /* non-ABI */ }; +/** + * Structure to upload perf dynamic configuration into the kernel. + */ +struct drm_i915_perf_oa_config { + /** String formatted like "%08x-%04x-%04x-%04x-%012x" */ + char uuid[36]; + + __u32 n_mux_regs; + __u32 n_boolean_regs; + __u32 n_flex_regs; + + __u64 __user mux_regs_ptr; + __u64 __user boolean_regs_ptr; + __u64 __user flex_regs_ptr; +}; + #if defined(__cplusplus) } #endif diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 461811e57140..43ab5c402f98 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -143,12 +143,6 @@ enum bpf_attach_type { #define MAX_BPF_ATTACH_TYPE __MAX_BPF_ATTACH_TYPE -enum bpf_sockmap_flags { - BPF_SOCKMAP_UNSPEC, - BPF_SOCKMAP_STRPARSER, - __MAX_BPF_SOCKMAP_FLAG -}; - /* If BPF_F_ALLOW_OVERRIDE flag is used in BPF_PROG_ATTACH command * to the given target_fd cgroup the descendent cgroup will be able to * override effective bpf program that was inherited from this cgroup @@ -368,9 +362,20 @@ union bpf_attr { * int bpf_redirect(ifindex, flags) * redirect to another netdev * @ifindex: ifindex of the net device - * @flags: bit 0 - if set, redirect to ingress instead of egress - * other bits - reserved - * Return: TC_ACT_REDIRECT + * @flags: + * cls_bpf: + * bit 0 - if set, redirect to ingress instead of egress + * other bits - reserved + * xdp_bpf: + * all bits - reserved + * Return: cls_bpf: TC_ACT_REDIRECT on success or TC_ACT_SHOT on error + * xdp_bfp: XDP_REDIRECT on success or XDP_ABORT on error + * int bpf_redirect_map(map, key, flags) + * redirect to endpoint in map + * @map: pointer to dev map + * @key: index in map to lookup + * @flags: -- + * Return: XDP_REDIRECT on success or XDP_ABORT on error * * u32 bpf_get_route_realm(skb) * retrieve a dst's tclassid @@ -632,7 +637,7 @@ union bpf_attr { FN(skb_adjust_room), \ FN(redirect_map), \ FN(sk_redirect_map), \ - FN(sock_map_update), + FN(sock_map_update), \ /* integer value in 'imm' field of BPF_CALL instruction selects which helper * function eBPF program intends to call @@ -753,20 +758,23 @@ struct bpf_sock { __u32 family; __u32 type; __u32 protocol; + __u32 mark; + __u32 priority; }; #define XDP_PACKET_HEADROOM 256 /* User return codes for XDP prog type. * A valid XDP program must return one of these defined values. All other - * return codes are reserved for future use. Unknown return codes will result - * in packet drop. + * return codes are reserved for future use. Unknown return codes will + * result in packet drops and a warning via bpf_warn_invalid_xdp_action(). */ enum xdp_action { XDP_ABORTED = 0, XDP_DROP, XDP_PASS, XDP_TX, + XDP_REDIRECT, }; /* user accessible metadata for XDP packet hook diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h index 6cd63c18708a..838887587411 100644 --- a/tools/include/uapi/linux/kvm.h +++ b/tools/include/uapi/linux/kvm.h @@ -711,7 +711,8 @@ struct kvm_ppc_one_seg_page_size { struct kvm_ppc_smmu_info { __u64 flags; __u32 slb_size; - __u32 pad; + __u16 data_keys; /* # storage keys supported for data */ + __u16 instr_keys; /* # storage keys supported for instructions */ struct kvm_ppc_one_seg_page_size sps[KVM_PPC_PAGE_SIZES_MAX_SZ]; }; diff --git a/tools/include/uapi/linux/mman.h b/tools/include/uapi/linux/mman.h index 81d8edf11789..a937480d7cd3 100644 --- a/tools/include/uapi/linux/mman.h +++ b/tools/include/uapi/linux/mman.h @@ -1,7 +1,8 @@ #ifndef _UAPI_LINUX_MMAN_H #define _UAPI_LINUX_MMAN_H -#include <uapi/asm/mman.h> +#include <asm/mman.h> +#include <asm-generic/hugetlb_encode.h> #define MREMAP_MAYMOVE 1 #define MREMAP_FIXED 2 @@ -10,4 +11,25 @@ #define OVERCOMMIT_ALWAYS 1 #define OVERCOMMIT_NEVER 2 +/* + * Huge page size encoding when MAP_HUGETLB is specified, and a huge page + * size other than the default is desired. See hugetlb_encode.h. + * All known huge page size encodings are provided here. It is the + * responsibility of the application to know which sizes are supported on + * the running system. See mmap(2) man page for details. + */ +#define MAP_HUGE_SHIFT HUGETLB_FLAG_ENCODE_SHIFT +#define MAP_HUGE_MASK HUGETLB_FLAG_ENCODE_MASK + +#define MAP_HUGE_64KB HUGETLB_FLAG_ENCODE_64KB +#define MAP_HUGE_512KB HUGETLB_FLAG_ENCODE_512KB +#define MAP_HUGE_1MB HUGETLB_FLAG_ENCODE_1MB +#define MAP_HUGE_2MB HUGETLB_FLAG_ENCODE_2MB +#define MAP_HUGE_8MB HUGETLB_FLAG_ENCODE_8MB +#define MAP_HUGE_16MB HUGETLB_FLAG_ENCODE_16MB +#define MAP_HUGE_256MB HUGETLB_FLAG_ENCODE_256MB +#define MAP_HUGE_1GB HUGETLB_FLAG_ENCODE_1GB +#define MAP_HUGE_2GB HUGETLB_FLAG_ENCODE_2GB +#define MAP_HUGE_16GB HUGETLB_FLAG_ENCODE_16GB + #endif /* _UAPI_LINUX_MMAN_H */ diff --git a/tools/objtool/arch/x86/decode.c b/tools/objtool/arch/x86/decode.c index 0f22768c0d4d..34a579f806e3 100644 --- a/tools/objtool/arch/x86/decode.c +++ b/tools/objtool/arch/x86/decode.c @@ -284,11 +284,16 @@ int arch_decode_instruction(struct elf *elf, struct section *sec, case 0x8d: if (sib == 0x24 && rex_w && !rex_b && !rex_x) { - /* lea disp(%rsp), reg */ *type = INSN_STACK; - op->src.type = OP_SRC_ADD; + if (!insn.displacement.value) { + /* lea (%rsp), reg */ + op->src.type = OP_SRC_REG; + } else { + /* lea disp(%rsp), reg */ + op->src.type = OP_SRC_ADD; + op->src.offset = insn.displacement.value; + } op->src.reg = CFI_SP; - op->src.offset = insn.displacement.value; op->dest.type = OP_DEST_REG; op->dest.reg = op_to_cfi_reg[modrm_reg][rex_r]; diff --git a/tools/perf/MANIFEST b/tools/perf/MANIFEST index 62072822dc85..627b7cada144 100644 --- a/tools/perf/MANIFEST +++ b/tools/perf/MANIFEST @@ -1,34 +1,8 @@ tools/perf -tools/arch/alpha/include/asm/barrier.h -tools/arch/arm/include/asm/barrier.h -tools/arch/arm64/include/asm/barrier.h -tools/arch/ia64/include/asm/barrier.h -tools/arch/mips/include/asm/barrier.h -tools/arch/powerpc/include/asm/barrier.h -tools/arch/s390/include/asm/barrier.h -tools/arch/sh/include/asm/barrier.h -tools/arch/sparc/include/asm/barrier.h -tools/arch/sparc/include/asm/barrier_32.h -tools/arch/sparc/include/asm/barrier_64.h -tools/arch/tile/include/asm/barrier.h -tools/arch/x86/include/asm/barrier.h -tools/arch/x86/include/asm/cmpxchg.h -tools/arch/x86/include/asm/cpufeatures.h -tools/arch/x86/include/asm/disabled-features.h -tools/arch/x86/include/asm/required-features.h -tools/arch/x86/include/uapi/asm/svm.h -tools/arch/x86/include/uapi/asm/vmx.h -tools/arch/x86/include/uapi/asm/kvm.h -tools/arch/x86/include/uapi/asm/kvm_perf.h -tools/arch/x86/lib/memcpy_64.S -tools/arch/x86/lib/memset_64.S -tools/arch/s390/include/uapi/asm/kvm_perf.h -tools/arch/s390/include/uapi/asm/sie.h -tools/arch/xtensa/include/asm/barrier.h +tools/arch tools/scripts tools/build -tools/arch/x86/include/asm/atomic.h -tools/arch/x86/include/asm/rmwcc.h +tools/include tools/lib/traceevent tools/lib/api tools/lib/bpf @@ -42,60 +16,3 @@ tools/lib/find_bit.c tools/lib/bitmap.c tools/lib/str_error_r.c tools/lib/vsprintf.c -tools/include/asm/alternative-asm.h -tools/include/asm/atomic.h -tools/include/asm/barrier.h -tools/include/asm/bug.h -tools/include/asm-generic/atomic-gcc.h -tools/include/asm-generic/barrier.h -tools/include/asm-generic/bitops/arch_hweight.h -tools/include/asm-generic/bitops/atomic.h -tools/include/asm-generic/bitops/const_hweight.h -tools/include/asm-generic/bitops/__ffs.h -tools/include/asm-generic/bitops/__ffz.h -tools/include/asm-generic/bitops/__fls.h -tools/include/asm-generic/bitops/find.h -tools/include/asm-generic/bitops/fls64.h -tools/include/asm-generic/bitops/fls.h -tools/include/asm-generic/bitops/hweight.h -tools/include/asm-generic/bitops.h -tools/include/linux/atomic.h -tools/include/linux/bitops.h -tools/include/linux/compiler.h -tools/include/linux/compiler-gcc.h -tools/include/linux/coresight-pmu.h -tools/include/linux/bug.h -tools/include/linux/filter.h -tools/include/linux/hash.h -tools/include/linux/kernel.h -tools/include/linux/list.h -tools/include/linux/log2.h -tools/include/uapi/asm-generic/fcntl.h -tools/include/uapi/asm-generic/ioctls.h -tools/include/uapi/asm-generic/mman-common.h -tools/include/uapi/asm-generic/mman.h -tools/include/uapi/drm/drm.h -tools/include/uapi/drm/i915_drm.h -tools/include/uapi/linux/bpf.h -tools/include/uapi/linux/bpf_common.h -tools/include/uapi/linux/fcntl.h -tools/include/uapi/linux/hw_breakpoint.h -tools/include/uapi/linux/kvm.h -tools/include/uapi/linux/mman.h -tools/include/uapi/linux/perf_event.h -tools/include/uapi/linux/sched.h -tools/include/uapi/linux/stat.h -tools/include/uapi/linux/vhost.h -tools/include/uapi/sound/asound.h -tools/include/linux/poison.h -tools/include/linux/rbtree.h -tools/include/linux/rbtree_augmented.h -tools/include/linux/refcount.h -tools/include/linux/string.h -tools/include/linux/stringify.h -tools/include/linux/types.h -tools/include/linux/err.h -tools/include/linux/bitmap.h -tools/include/linux/time64.h -tools/arch/*/include/uapi/asm/mman.h -tools/arch/*/include/uapi/asm/perf_regs.h diff --git a/tools/perf/arch/s390/util/Build b/tools/perf/arch/s390/util/Build index bd518b623d7a..5bd7b9260cc0 100644 --- a/tools/perf/arch/s390/util/Build +++ b/tools/perf/arch/s390/util/Build @@ -1,5 +1,4 @@ libperf-y += header.o -libperf-y += sym-handling.o libperf-y += kvm-stat.o libperf-$(CONFIG_DWARF) += dwarf-regs.o diff --git a/tools/perf/arch/s390/util/sym-handling.c b/tools/perf/arch/s390/util/sym-handling.c deleted file mode 100644 index e103f6e46afe..000000000000 --- a/tools/perf/arch/s390/util/sym-handling.c +++ /dev/null @@ -1,29 +0,0 @@ -/* - * Architecture specific ELF symbol handling and relocation mapping. - * - * Copyright 2017 IBM Corp. - * Author(s): Thomas Richter <tmricht@linux.vnet.ibm.com> - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License (version 2 only) - * as published by the Free Software Foundation. - */ - -#include "symbol.h" - -#ifdef HAVE_LIBELF_SUPPORT -bool elf__needs_adjust_symbols(GElf_Ehdr ehdr) -{ - if (ehdr.e_type == ET_EXEC) - return false; - return ehdr.e_type == ET_REL || ehdr.e_type == ET_DYN; -} - -void arch__adjust_sym_map_offset(GElf_Sym *sym, - GElf_Shdr *shdr __maybe_unused, - struct map *map) -{ - if (map->type == MAP__FUNCTION) - sym->st_value += map->start; -} -#endif diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c index 510b513e0f01..be09d77cade0 100644 --- a/tools/perf/util/callchain.c +++ b/tools/perf/util/callchain.c @@ -65,8 +65,6 @@ static int parse_callchain_mode(const char *value) callchain_param.mode = CHAIN_FOLDED; return 0; } - - pr_err("Invalid callchain mode: %s\n", value); return -1; } @@ -82,8 +80,6 @@ static int parse_callchain_order(const char *value) callchain_param.order_set = true; return 0; } - - pr_err("Invalid callchain order: %s\n", value); return -1; } @@ -105,8 +101,6 @@ static int parse_callchain_sort_key(const char *value) callchain_param.branch_callstack = 1; return 0; } - - pr_err("Invalid callchain sort key: %s\n", value); return -1; } @@ -124,8 +118,6 @@ static int parse_callchain_value(const char *value) callchain_param.value = CCVAL_COUNT; return 0; } - - pr_err("Invalid callchain config key: %s\n", value); return -1; } @@ -319,12 +311,27 @@ int perf_callchain_config(const char *var, const char *value) return ret; } - if (!strcmp(var, "print-type")) - return parse_callchain_mode(value); - if (!strcmp(var, "order")) - return parse_callchain_order(value); - if (!strcmp(var, "sort-key")) - return parse_callchain_sort_key(value); + if (!strcmp(var, "print-type")){ + int ret; + ret = parse_callchain_mode(value); + if (ret == -1) + pr_err("Invalid callchain mode: %s\n", value); + return ret; + } + if (!strcmp(var, "order")){ + int ret; + ret = parse_callchain_order(value); + if (ret == -1) + pr_err("Invalid callchain order: %s\n", value); + return ret; + } + if (!strcmp(var, "sort-key")){ + int ret; + ret = parse_callchain_sort_key(value); + if (ret == -1) + pr_err("Invalid callchain sort key: %s\n", value); + return ret; + } if (!strcmp(var, "threshold")) { callchain_param.min_percent = strtod(value, &endptr); if (value == endptr) { diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index 4bb89373eb52..0dccdb89572c 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -271,12 +271,17 @@ struct perf_evsel *perf_evsel__new_idx(struct perf_event_attr *attr, int idx) return evsel; } +static bool perf_event_can_profile_kernel(void) +{ + return geteuid() == 0 || perf_event_paranoid() == -1; +} + struct perf_evsel *perf_evsel__new_cycles(bool precise) { struct perf_event_attr attr = { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_CPU_CYCLES, - .exclude_kernel = geteuid() != 0, + .exclude_kernel = !perf_event_can_profile_kernel(), }; struct perf_evsel *evsel; diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c index 5c39f420111e..9cf781f0d8a2 100644 --- a/tools/perf/util/symbol-elf.c +++ b/tools/perf/util/symbol-elf.c @@ -810,12 +810,6 @@ static u64 ref_reloc(struct kmap *kmap) void __weak arch__sym_update(struct symbol *s __maybe_unused, GElf_Sym *sym __maybe_unused) { } -void __weak arch__adjust_sym_map_offset(GElf_Sym *sym, GElf_Shdr *shdr, - struct map *map __maybe_unused) -{ - sym->st_value -= shdr->sh_addr - shdr->sh_offset; -} - int dso__load_sym(struct dso *dso, struct map *map, struct symsrc *syms_ss, struct symsrc *runtime_ss, int kmodule) { @@ -996,7 +990,7 @@ int dso__load_sym(struct dso *dso, struct map *map, struct symsrc *syms_ss, /* Adjust symbol to map to file offset */ if (adjust_kernel_syms) - arch__adjust_sym_map_offset(&sym, &shdr, map); + sym.st_value -= shdr.sh_addr - shdr.sh_offset; if (strcmp(section_name, (curr_dso->short_name + diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h index 2bd6a1f01a1c..aad99e7e179b 100644 --- a/tools/perf/util/symbol.h +++ b/tools/perf/util/symbol.h @@ -344,9 +344,6 @@ int setup_intlist(struct intlist **list, const char *list_str, #ifdef HAVE_LIBELF_SUPPORT bool elf__needs_adjust_symbols(GElf_Ehdr ehdr); void arch__sym_update(struct symbol *s, GElf_Sym *sym); -void arch__adjust_sym_map_offset(GElf_Sym *sym, - GElf_Shdr *shdr __maybe_unused, - struct map *map __maybe_unused); #endif #define SYMBOL_A 0 diff --git a/tools/perf/util/syscalltbl.c b/tools/perf/util/syscalltbl.c index 19e5db90394c..6eea7cff3d4e 100644 --- a/tools/perf/util/syscalltbl.c +++ b/tools/perf/util/syscalltbl.c @@ -15,9 +15,9 @@ #include "syscalltbl.h" #include <stdlib.h> +#include <linux/compiler.h> #ifdef HAVE_SYSCALL_TABLE -#include <linux/compiler.h> #include <string.h> #include "string2.h" #include "util.h" diff --git a/tools/testing/selftests/Makefile b/tools/testing/selftests/Makefile index 26ce4f7168be..ff805643b5f7 100644 --- a/tools/testing/selftests/Makefile +++ b/tools/testing/selftests/Makefile @@ -52,6 +52,10 @@ override LDFLAGS = override MAKEFLAGS = endif +ifneq ($(KBUILD_SRC),) +override LDFLAGS = +endif + BUILD := $(O) ifndef BUILD BUILD := $(KBUILD_OUTPUT) @@ -62,32 +66,32 @@ endif export BUILD all: - for TARGET in $(TARGETS); do \ + @for TARGET in $(TARGETS); do \ BUILD_TARGET=$$BUILD/$$TARGET; \ mkdir $$BUILD_TARGET -p; \ make OUTPUT=$$BUILD_TARGET -C $$TARGET;\ done; run_tests: all - for TARGET in $(TARGETS); do \ + @for TARGET in $(TARGETS); do \ BUILD_TARGET=$$BUILD/$$TARGET; \ make OUTPUT=$$BUILD_TARGET -C $$TARGET run_tests;\ done; hotplug: - for TARGET in $(TARGETS_HOTPLUG); do \ + @for TARGET in $(TARGETS_HOTPLUG); do \ BUILD_TARGET=$$BUILD/$$TARGET; \ make OUTPUT=$$BUILD_TARGET -C $$TARGET;\ done; run_hotplug: hotplug - for TARGET in $(TARGETS_HOTPLUG); do \ + @for TARGET in $(TARGETS_HOTPLUG); do \ BUILD_TARGET=$$BUILD/$$TARGET; \ make OUTPUT=$$BUILD_TARGET -C $$TARGET run_full_test;\ done; clean_hotplug: - for TARGET in $(TARGETS_HOTPLUG); do \ + @for TARGET in $(TARGETS_HOTPLUG); do \ BUILD_TARGET=$$BUILD/$$TARGET; \ make OUTPUT=$$BUILD_TARGET -C $$TARGET clean;\ done; @@ -103,7 +107,7 @@ install: ifdef INSTALL_PATH @# Ask all targets to install their files mkdir -p $(INSTALL_PATH) - for TARGET in $(TARGETS); do \ + @for TARGET in $(TARGETS); do \ BUILD_TARGET=$$BUILD/$$TARGET; \ make OUTPUT=$$BUILD_TARGET -C $$TARGET INSTALL_PATH=$(INSTALL_PATH)/$$TARGET install; \ done; @@ -128,7 +132,7 @@ else endif clean: - for TARGET in $(TARGETS); do \ + @for TARGET in $(TARGETS); do \ BUILD_TARGET=$$BUILD/$$TARGET; \ make OUTPUT=$$BUILD_TARGET -C $$TARGET clean;\ done; diff --git a/tools/testing/selftests/bpf/bpf_util.h b/tools/testing/selftests/bpf/bpf_util.h index 20ecbaa0d85d..6c53a8906eff 100644 --- a/tools/testing/selftests/bpf/bpf_util.h +++ b/tools/testing/selftests/bpf/bpf_util.h @@ -12,6 +12,7 @@ static inline unsigned int bpf_num_possible_cpus(void) unsigned int start, end, possible_cpus = 0; char buff[128]; FILE *fp; + int n; fp = fopen(fcpu, "r"); if (!fp) { @@ -20,17 +21,17 @@ static inline unsigned int bpf_num_possible_cpus(void) } while (fgets(buff, sizeof(buff), fp)) { - if (sscanf(buff, "%u-%u", &start, &end) == 2) { - possible_cpus = start == 0 ? end + 1 : 0; - break; + n = sscanf(buff, "%u-%u", &start, &end); + if (n == 0) { + printf("Failed to retrieve # possible CPUs!\n"); + exit(1); + } else if (n == 1) { + end = start; } + possible_cpus = start == 0 ? end + 1 : 0; + break; } - fclose(fp); - if (!possible_cpus) { - printf("Failed to retrieve # possible CPUs!\n"); - exit(1); - } return possible_cpus; } diff --git a/tools/testing/selftests/breakpoints/Makefile b/tools/testing/selftests/breakpoints/Makefile index 6b214b7b10fb..247b0a1899d7 100644 --- a/tools/testing/selftests/breakpoints/Makefile +++ b/tools/testing/selftests/breakpoints/Makefile @@ -2,14 +2,14 @@ uname_M := $(shell uname -m 2>/dev/null || echo not) ARCH ?= $(shell echo $(uname_M) | sed -e s/i.86/x86/ -e s/x86_64/x86/) +TEST_GEN_PROGS := step_after_suspend_test + ifeq ($(ARCH),x86) -TEST_GEN_PROGS := breakpoint_test +TEST_GEN_PROGS += breakpoint_test endif ifneq (,$(filter $(ARCH),aarch64 arm64)) -TEST_GEN_PROGS := breakpoint_test_arm64 +TEST_GEN_PROGS += breakpoint_test_arm64 endif -TEST_GEN_PROGS += step_after_suspend_test - include ../lib.mk diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/multiple_kprobes.tc b/tools/testing/selftests/ftrace/test.d/kprobe/multiple_kprobes.tc index 2a1cb9908746..a4fd4c851a5b 100644 --- a/tools/testing/selftests/ftrace/test.d/kprobe/multiple_kprobes.tc +++ b/tools/testing/selftests/ftrace/test.d/kprobe/multiple_kprobes.tc @@ -1,6 +1,8 @@ #!/bin/sh # description: Register/unregister many kprobe events +[ -f kprobe_events ] || exit_unsupported # this is configurable + # ftrace fentry skip size depends on the machine architecture. # Currently HAVE_KPROBES_ON_FTRACE defined on x86 and powerpc64le case `uname -m` in diff --git a/tools/testing/selftests/futex/Makefile b/tools/testing/selftests/futex/Makefile index 7c647f619d63..f0c0369ccb79 100644 --- a/tools/testing/selftests/futex/Makefile +++ b/tools/testing/selftests/futex/Makefile @@ -7,14 +7,17 @@ TEST_PROGS := run.sh include ../lib.mk all: - for DIR in $(SUBDIRS); do \ + @for DIR in $(SUBDIRS); do \ BUILD_TARGET=$(OUTPUT)/$$DIR; \ mkdir $$BUILD_TARGET -p; \ make OUTPUT=$$BUILD_TARGET -C $$DIR $@;\ + if [ -e $$DIR/$(TEST_PROGS) ]; then + rsync -a $$DIR/$(TEST_PROGS) $$BUILD_TARGET/; + fi done override define RUN_TESTS - $(OUTPUT)/run.sh + @cd $(OUTPUT); ./run.sh endef override define INSTALL_RULE @@ -33,7 +36,7 @@ override define EMIT_TESTS endef override define CLEAN - for DIR in $(SUBDIRS); do \ + @for DIR in $(SUBDIRS); do \ BUILD_TARGET=$(OUTPUT)/$$DIR; \ mkdir $$BUILD_TARGET -p; \ make OUTPUT=$$BUILD_TARGET -C $$DIR $@;\ diff --git a/tools/testing/selftests/intel_pstate/Makefile b/tools/testing/selftests/intel_pstate/Makefile index 849a90ffe8dd..a97e24edde39 100644 --- a/tools/testing/selftests/intel_pstate/Makefile +++ b/tools/testing/selftests/intel_pstate/Makefile @@ -1,7 +1,9 @@ CFLAGS := $(CFLAGS) -Wall -D_GNU_SOURCE LDLIBS := $(LDLIBS) -lm +ifeq (,$(filter $(ARCH),x86)) TEST_GEN_FILES := msr aperf +endif TEST_PROGS := run.sh diff --git a/tools/testing/selftests/intel_pstate/run.sh b/tools/testing/selftests/intel_pstate/run.sh index 7868c106b8b1..d3ab48f91cd6 100755 --- a/tools/testing/selftests/intel_pstate/run.sh +++ b/tools/testing/selftests/intel_pstate/run.sh @@ -29,13 +29,12 @@ EVALUATE_ONLY=0 -max_cpus=$(($(nproc)-1)) +if ! uname -m | sed -e s/i.86/x86/ -e s/x86_64/x86/ | grep -q x86; then + echo "$0 # Skipped: Test can only run on x86 architectures." + exit 0 +fi -# compile programs -gcc aperf.c -Wall -D_GNU_SOURCE -o aperf -lm -[ $? -ne 0 ] && echo "Problem compiling aperf.c." && exit 1 -gcc -o msr msr.c -lm -[ $? -ne 0 ] && echo "Problem compiling msr.c." && exit 1 +max_cpus=$(($(nproc)-1)) function run_test () { diff --git a/tools/testing/selftests/lib.mk b/tools/testing/selftests/lib.mk index 693616651da5..f65886af7c0c 100644 --- a/tools/testing/selftests/lib.mk +++ b/tools/testing/selftests/lib.mk @@ -6,7 +6,14 @@ ifeq (0,$(MAKELEVEL)) OUTPUT := $(shell pwd) endif +# The following are built by lib.mk common compile rules. +# TEST_CUSTOM_PROGS should be used by tests that require +# custom build rule and prevent common build rule use. +# TEST_PROGS are for test shell scripts. +# TEST_CUSTOM_PROGS and TEST_PROGS will be run by common run_tests +# and install targets. Common clean doesn't touch them. TEST_GEN_PROGS := $(patsubst %,$(OUTPUT)/%,$(TEST_GEN_PROGS)) +TEST_GEN_PROGS_EXTENDED := $(patsubst %,$(OUTPUT)/%,$(TEST_GEN_PROGS_EXTENDED)) TEST_GEN_FILES := $(patsubst %,$(OUTPUT)/%,$(TEST_GEN_FILES)) all: $(TEST_GEN_PROGS) $(TEST_GEN_PROGS_EXTENDED) $(TEST_GEN_FILES) @@ -20,17 +27,28 @@ define RUN_TESTS test_num=`echo $$test_num+1 | bc`; \ echo "selftests: $$BASENAME_TEST"; \ echo "========================================"; \ - if [ ! -x $$BASENAME_TEST ]; then \ + if [ ! -x $$TEST ]; then \ echo "selftests: Warning: file $$BASENAME_TEST is not executable, correct this.";\ echo "not ok 1..$$test_num selftests: $$BASENAME_TEST [FAIL]"; \ else \ - cd `dirname $$TEST` > /dev/null; (./$$BASENAME_TEST && echo "ok 1..$$test_num selftests: $$BASENAME_TEST [PASS]") || echo "not ok 1..$$test_num selftests: $$BASENAME_TEST [FAIL]"; cd - > /dev/null;\ + cd `dirname $$TEST` > /dev/null; (./$$BASENAME_TEST > /tmp/$$BASENAME_TEST 2>&1 && echo "ok 1..$$test_num selftests: $$BASENAME_TEST [PASS]") || echo "not ok 1..$$test_num selftests: $$BASENAME_TEST [FAIL]"; cd - > /dev/null;\ fi; \ done; endef run_tests: all - $(call RUN_TESTS, $(TEST_GEN_PROGS) $(TEST_PROGS)) +ifneq ($(KBUILD_SRC),) + @if [ "X$(TEST_PROGS) $(TEST_PROGS_EXTENDED) $(TEST_FILES)" != "X" ]; then + @rsync -aq $(TEST_PROGS) $(TEST_PROGS_EXTENDED) $(TEST_FILES) $(OUTPUT) + fi + @if [ "X$(TEST_PROGS)" != "X" ]; then + $(call RUN_TESTS, $(TEST_GEN_PROGS) $(TEST_CUSTOM_PROGS) $(OUTPUT)/$(TEST_PROGS)) + else + $(call RUN_TESTS, $(TEST_GEN_PROGS) $(TEST_CUSTOM_PROGS)) + fi +else + $(call RUN_TESTS, $(TEST_GEN_PROGS) $(TEST_CUSTOM_PROGS) $(TEST_PROGS)) +endif define INSTALL_RULE @if [ "X$(TEST_PROGS)$(TEST_PROGS_EXTENDED)$(TEST_FILES)" != "X" ]; then \ @@ -38,10 +56,10 @@ define INSTALL_RULE echo "rsync -a $(TEST_PROGS) $(TEST_PROGS_EXTENDED) $(TEST_FILES) $(INSTALL_PATH)/"; \ rsync -a $(TEST_PROGS) $(TEST_PROGS_EXTENDED) $(TEST_FILES) $(INSTALL_PATH)/; \ fi - @if [ "X$(TEST_GEN_PROGS)$(TEST_GEN_PROGS_EXTENDED)$(TEST_GEN_FILES)" != "X" ]; then \ + @if [ "X$(TEST_GEN_PROGS)$(TEST_CUSTOM_PROGS)$(TEST_GEN_PROGS_EXTENDED)$(TEST_GEN_FILES)" != "X" ]; then \ mkdir -p ${INSTALL_PATH}; \ - echo "rsync -a $(TEST_GEN_PROGS) $(TEST_GEN_PROGS_EXTENDED) $(TEST_GEN_FILES) $(INSTALL_PATH)/"; \ - rsync -a $(TEST_GEN_PROGS) $(TEST_GEN_PROGS_EXTENDED) $(TEST_GEN_FILES) $(INSTALL_PATH)/; \ + echo "rsync -a $(TEST_GEN_PROGS) $(TEST_CUSTOM_PROGS) $(TEST_GEN_PROGS_EXTENDED) $(TEST_GEN_FILES) $(INSTALL_PATH)/"; \ + rsync -a $(TEST_GEN_PROGS) $(TEST_CUSTOM_PROGS) $(TEST_GEN_PROGS_EXTENDED) $(TEST_GEN_FILES) $(INSTALL_PATH)/; \ fi endef @@ -53,15 +71,20 @@ else endif define EMIT_TESTS - @for TEST in $(TEST_GEN_PROGS) $(TEST_PROGS); do \ + @for TEST in $(TEST_GEN_PROGS) $(TEST_CUSTOM_PROGS) $(TEST_PROGS); do \ BASENAME_TEST=`basename $$TEST`; \ - echo "(./$$BASENAME_TEST && echo \"selftests: $$BASENAME_TEST [PASS]\") || echo \"selftests: $$BASENAME_TEST [FAIL]\""; \ + echo "(./$$BASENAME_TEST > /tmp/$$BASENAME_TEST 2>&1 && echo \"selftests: $$BASENAME_TEST [PASS]\") || echo \"selftests: $$BASENAME_TEST [FAIL]\""; \ done; endef emit_tests: $(EMIT_TESTS) +# define if isn't already. It is undefined in make O= case. +ifeq ($(RM),) +RM := rm -f +endif + define CLEAN $(RM) -r $(TEST_GEN_PROGS) $(TEST_GEN_PROGS_EXTENDED) $(TEST_GEN_FILES) $(EXTRA_CLEAN) endef @@ -69,6 +92,15 @@ endef clean: $(CLEAN) +# When make O= with kselftest target from main level +# the following aren't defined. +# +ifneq ($(KBUILD_SRC),) +LINK.c = $(CC) $(CFLAGS) $(CPPFLAGS) $(LDFLAGS) $(TARGET_ARCH) +COMPILE.S = $(CC) $(ASFLAGS) $(CPPFLAGS) $(TARGET_ARCH) -c +LINK.S = $(CC) $(ASFLAGS) $(CPPFLAGS) $(LDFLAGS) $(TARGET_ARCH) +endif + $(OUTPUT)/%:%.c $(LINK.c) $^ $(LDLIBS) -o $@ diff --git a/tools/testing/selftests/memfd/run_tests.sh b/tools/testing/selftests/memfd/run_tests.sh index daabb350697c..daabb350697c 100644..100755 --- a/tools/testing/selftests/memfd/run_tests.sh +++ b/tools/testing/selftests/memfd/run_tests.sh diff --git a/tools/testing/selftests/mqueue/Makefile b/tools/testing/selftests/mqueue/Makefile index 79a664aeb8d7..0f5e347b068d 100644 --- a/tools/testing/selftests/mqueue/Makefile +++ b/tools/testing/selftests/mqueue/Makefile @@ -5,8 +5,8 @@ TEST_GEN_PROGS := mq_open_tests mq_perf_tests include ../lib.mk override define RUN_TESTS - @./mq_open_tests /test1 || echo "selftests: mq_open_tests [FAIL]" - @./mq_perf_tests || echo "selftests: mq_perf_tests [FAIL]" + $(OUTPUT)/mq_open_tests /test1 || echo "selftests: mq_open_tests [FAIL]" + $(OUTPUT)//mq_perf_tests || echo "selftests: mq_perf_tests [FAIL]" endef override define EMIT_TESTS diff --git a/tools/testing/selftests/net/.gitignore b/tools/testing/selftests/net/.gitignore index 9801253e4802..c612d6e38c62 100644 --- a/tools/testing/selftests/net/.gitignore +++ b/tools/testing/selftests/net/.gitignore @@ -6,3 +6,4 @@ reuseport_bpf reuseport_bpf_cpu reuseport_bpf_numa reuseport_dualstack +reuseaddr_conflict diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile index de1f5772b878..d86bca991f45 100644 --- a/tools/testing/selftests/net/Makefile +++ b/tools/testing/selftests/net/Makefile @@ -5,9 +5,9 @@ CFLAGS += -I../../../../usr/include/ TEST_PROGS := run_netsocktests run_afpackettests test_bpf.sh netdevice.sh rtnetlink.sh TEST_GEN_FILES = socket -TEST_GEN_FILES += psock_fanout psock_tpacket -TEST_GEN_FILES += reuseport_bpf reuseport_bpf_cpu reuseport_bpf_numa -TEST_GEN_FILES += reuseport_dualstack msg_zerocopy +TEST_GEN_FILES += psock_fanout psock_tpacket msg_zerocopy +TEST_GEN_PROGS = reuseport_bpf reuseport_bpf_cpu reuseport_bpf_numa +TEST_GEN_PROGS += reuseport_dualstack reuseaddr_conflict include ../lib.mk diff --git a/tools/testing/selftests/net/msg_zerocopy.c b/tools/testing/selftests/net/msg_zerocopy.c index 40232af5b023..3ab6ec403905 100644 --- a/tools/testing/selftests/net/msg_zerocopy.c +++ b/tools/testing/selftests/net/msg_zerocopy.c @@ -55,7 +55,7 @@ #include <unistd.h> #ifndef SO_EE_ORIGIN_ZEROCOPY -#define SO_EE_ORIGIN_ZEROCOPY SO_EE_ORIGIN_UPAGE +#define SO_EE_ORIGIN_ZEROCOPY 5 #endif #ifndef SO_ZEROCOPY diff --git a/tools/testing/selftests/net/netdevice.sh b/tools/testing/selftests/net/netdevice.sh index 4e00568d70c2..90cb903c3381 100755 --- a/tools/testing/selftests/net/netdevice.sh +++ b/tools/testing/selftests/net/netdevice.sh @@ -178,7 +178,7 @@ if [ "$(id -u)" -ne 0 ];then exit 0 fi -ip -Version 2>/dev/null >/dev/null +ip link show 2>/dev/null >/dev/null if [ $? -ne 0 ];then echo "SKIP: Could not run test without the ip tool" exit 0 diff --git a/tools/testing/selftests/net/reuseaddr_conflict.c b/tools/testing/selftests/net/reuseaddr_conflict.c new file mode 100644 index 000000000000..7c5b12664b03 --- /dev/null +++ b/tools/testing/selftests/net/reuseaddr_conflict.c @@ -0,0 +1,114 @@ +/* + * Test for the regression introduced by + * + * b9470c27607b ("inet: kill smallest_size and smallest_port") + * + * If we open an ipv4 socket on a port with reuseaddr we shouldn't reset the tb + * when we open the ipv6 conterpart, which is what was happening previously. + */ +#include <errno.h> +#include <error.h> +#include <arpa/inet.h> +#include <netinet/in.h> +#include <stdbool.h> +#include <stdio.h> +#include <sys/socket.h> +#include <sys/types.h> +#include <unistd.h> + +#define PORT 9999 + +int open_port(int ipv6, int any) +{ + int fd = -1; + int reuseaddr = 1; + int v6only = 1; + int addrlen; + int ret = -1; + struct sockaddr *addr; + int family = ipv6 ? AF_INET6 : AF_INET; + + struct sockaddr_in6 addr6 = { + .sin6_family = AF_INET6, + .sin6_port = htons(PORT), + .sin6_addr = in6addr_any + }; + struct sockaddr_in addr4 = { + .sin_family = AF_INET, + .sin_port = htons(PORT), + .sin_addr.s_addr = any ? htonl(INADDR_ANY) : inet_addr("127.0.0.1"), + }; + + + if (ipv6) { + addr = (struct sockaddr*)&addr6; + addrlen = sizeof(addr6); + } else { + addr = (struct sockaddr*)&addr4; + addrlen = sizeof(addr4); + } + + if ((fd = socket(family, SOCK_STREAM, IPPROTO_TCP)) < 0) { + perror("socket"); + goto out; + } + + if (ipv6 && setsockopt(fd, IPPROTO_IPV6, IPV6_V6ONLY, (void*)&v6only, + sizeof(v6only)) < 0) { + perror("setsockopt IPV6_V6ONLY"); + goto out; + } + + if (setsockopt(fd, SOL_SOCKET, SO_REUSEADDR, &reuseaddr, + sizeof(reuseaddr)) < 0) { + perror("setsockopt SO_REUSEADDR"); + goto out; + } + + if (bind(fd, addr, addrlen) < 0) { + perror("bind"); + goto out; + } + + if (any) + return fd; + + if (listen(fd, 1) < 0) { + perror("listen"); + goto out; + } + return fd; +out: + close(fd); + return ret; +} + +int main(void) +{ + int listenfd; + int fd1, fd2; + + fprintf(stderr, "Opening 127.0.0.1:%d\n", PORT); + listenfd = open_port(0, 0); + if (listenfd < 0) + error(1, errno, "Couldn't open listen socket"); + fprintf(stderr, "Opening INADDR_ANY:%d\n", PORT); + fd1 = open_port(0, 1); + if (fd1 >= 0) + error(1, 0, "Was allowed to create an ipv4 reuseport on a already bound non-reuseport socket"); + fprintf(stderr, "Opening in6addr_any:%d\n", PORT); + fd1 = open_port(1, 1); + if (fd1 < 0) + error(1, errno, "Couldn't open ipv6 reuseport"); + fprintf(stderr, "Opening INADDR_ANY:%d\n", PORT); + fd2 = open_port(0, 1); + if (fd2 >= 0) + error(1, 0, "Was allowed to create an ipv4 reuseport on a already bound non-reuseport socket"); + close(fd1); + fprintf(stderr, "Opening INADDR_ANY:%d after closing ipv6 socket\n", PORT); + fd1 = open_port(0, 1); + if (fd1 >= 0) + error(1, 0, "Was allowed to create an ipv4 reuseport on an already bound non-reuseport socket with no ipv6"); + fprintf(stderr, "Success"); + return 0; +} diff --git a/tools/testing/selftests/seccomp/seccomp_bpf.c b/tools/testing/selftests/seccomp/seccomp_bpf.c index 67c3e2764303..24dbf634e2dd 100644 --- a/tools/testing/selftests/seccomp/seccomp_bpf.c +++ b/tools/testing/selftests/seccomp/seccomp_bpf.c @@ -6,10 +6,18 @@ */ #include <sys/types.h> -#include <asm/siginfo.h> -#define __have_siginfo_t 1 -#define __have_sigval_t 1 -#define __have_sigevent_t 1 + +/* + * glibc 2.26 and later have SIGSYS in siginfo_t. Before that, + * we need to use the kernel's siginfo.h file and trick glibc + * into accepting it. + */ +#if !__GLIBC_PREREQ(2, 26) +# include <asm/siginfo.h> +# define __have_siginfo_t 1 +# define __have_sigval_t 1 +# define __have_sigevent_t 1 +#endif #include <errno.h> #include <linux/filter.h> @@ -884,7 +892,7 @@ TEST_F_SIGNAL(TRAP, ign, SIGSYS) syscall(__NR_getpid); } -static struct siginfo TRAP_info; +static siginfo_t TRAP_info; static volatile int TRAP_nr; static void TRAP_action(int nr, siginfo_t *info, void *void_context) { diff --git a/tools/testing/selftests/sigaltstack/sas.c b/tools/testing/selftests/sigaltstack/sas.c index 7d406c3973ba..97bb150837df 100644 --- a/tools/testing/selftests/sigaltstack/sas.c +++ b/tools/testing/selftests/sigaltstack/sas.c @@ -39,7 +39,11 @@ void my_usr1(int sig, siginfo_t *si, void *u) stack_t stk; struct stk_data *p; +#if __s390x__ + register unsigned long sp asm("%15"); +#else register unsigned long sp asm("sp"); +#endif if (sp < (unsigned long)sstack || sp >= (unsigned long)sstack + SIGSTKSZ) { diff --git a/tools/testing/selftests/sync/Makefile b/tools/testing/selftests/sync/Makefile index 4981c6b6d050..8e04d0afcbd7 100644 --- a/tools/testing/selftests/sync/Makefile +++ b/tools/testing/selftests/sync/Makefile @@ -2,12 +2,16 @@ CFLAGS += -O2 -g -std=gnu89 -pthread -Wall -Wextra CFLAGS += -I../../../../usr/include/ LDFLAGS += -pthread -TEST_PROGS = sync_test - -all: $(TEST_PROGS) +.PHONY: all clean include ../lib.mk +# lib.mk TEST_CUSTOM_PROGS var is for custom tests that need special +# build rules. lib.mk will run and install them. + +TEST_CUSTOM_PROGS := $(OUTPUT)/sync_test +all: $(TEST_CUSTOM_PROGS) + OBJS = sync_test.o sync.o TESTS += sync_alloc.o @@ -18,6 +22,16 @@ TESTS += sync_stress_parallelism.o TESTS += sync_stress_consumer.o TESTS += sync_stress_merge.o -sync_test: $(OBJS) $(TESTS) +OBJS := $(patsubst %,$(OUTPUT)/%,$(OBJS)) +TESTS := $(patsubst %,$(OUTPUT)/%,$(TESTS)) + +$(TEST_CUSTOM_PROGS): $(TESTS) $(OBJS) + $(CC) -o $(TEST_CUSTOM_PROGS) $(OBJS) $(TESTS) $(CFLAGS) $(LDFLAGS) + +$(OBJS): $(OUTPUT)/%.o: %.c + $(CC) -c $^ -o $@ + +$(TESTS): $(OUTPUT)/%.o: %.c + $(CC) -c $^ -o $@ -EXTRA_CLEAN := sync_test $(OBJS) $(TESTS) +EXTRA_CLEAN := $(TEST_CUSTOM_PROGS) $(OBJS) $(TESTS) diff --git a/tools/testing/selftests/timers/set-timer-lat.c b/tools/testing/selftests/timers/set-timer-lat.c index 9c92b7bd5641..50da45437daa 100644 --- a/tools/testing/selftests/timers/set-timer-lat.c +++ b/tools/testing/selftests/timers/set-timer-lat.c @@ -143,7 +143,8 @@ int setup_timer(int clock_id, int flags, int interval, timer_t *tm1) printf("%-22s %s missing CAP_WAKE_ALARM? : [UNSUPPORTED]\n", clockstring(clock_id), flags ? "ABSTIME":"RELTIME"); - return 0; + /* Indicate timer isn't set, so caller doesn't wait */ + return 1; } printf("%s - timer_create() failed\n", clockstring(clock_id)); return -1; @@ -213,8 +214,9 @@ int do_timer(int clock_id, int flags) int err; err = setup_timer(clock_id, flags, interval, &tm1); + /* Unsupported case - return 0 to not fail the test */ if (err) - return err; + return err == 1 ? 0 : err; while (alarmcount < 5) sleep(1); @@ -228,18 +230,17 @@ int do_timer_oneshot(int clock_id, int flags) timer_t tm1; const int interval = 0; struct timeval timeout; - fd_set fds; int err; err = setup_timer(clock_id, flags, interval, &tm1); + /* Unsupported case - return 0 to not fail the test */ if (err) - return err; + return err == 1 ? 0 : err; memset(&timeout, 0, sizeof(timeout)); timeout.tv_sec = 5; - FD_ZERO(&fds); do { - err = select(FD_SETSIZE, &fds, NULL, NULL, &timeout); + err = select(0, NULL, NULL, NULL, &timeout); } while (err == -1 && errno == EINTR); timer_delete(tm1); diff --git a/tools/testing/selftests/watchdog/Makefile b/tools/testing/selftests/watchdog/Makefile index f863c664e3d1..ee068511fd0b 100644 --- a/tools/testing/selftests/watchdog/Makefile +++ b/tools/testing/selftests/watchdog/Makefile @@ -1,8 +1,3 @@ -TEST_PROGS := watchdog-test - -all: $(TEST_PROGS) +TEST_GEN_PROGS := watchdog-test include ../lib.mk - -clean: - rm -fr $(TEST_PROGS) |