diff options
| author | Andrey Konovalov <andrey.konovalov@linaro.org> | 2015-11-04 19:50:07 +0300 |
|---|---|---|
| committer | Andrey Konovalov <andrey.konovalov@linaro.org> | 2015-11-04 19:50:07 +0300 |
| commit | f4845bd61300c2b5013bd4fa28c83975a85069bc (patch) | |
| tree | 974925d5ec1d615a748d37dab2e41c823e38f5c5 | |
| parent | 3985b18650bf2365debb142624f877007b31ada2 (diff) | |
| parent | a852cc89cffb65272be77785b9eb2682e38ed53f (diff) | |
Merge branch 'tracking-ilp32' into merge-linux-linaro-extralinux-linaro-extra-20151104.0linux-linaro-extra
389 files changed, 3692 insertions, 1682 deletions
@@ -59,6 +59,7 @@ James Bottomley <jejb@mulgrave.(none)> James Bottomley <jejb@titanic.il.steeleye.com> James E Wilson <wilson@specifix.com> James Ketrenos <jketreno@io.(none)> +<javier@osg.samsung.com> <javier.martinez@collabora.co.uk> Jean Tourrilhes <jt@hpl.hp.com> Jeff Garzik <jgarzik@pretzel.yyz.us> Jens Axboe <axboe@suse.de> diff --git a/Documentation/arm/OMAP/README b/Documentation/arm/OMAP/README new file mode 100644 index 000000000000..75645c45d14a --- /dev/null +++ b/Documentation/arm/OMAP/README @@ -0,0 +1,7 @@ +This file contains documentation for running mainline +kernel on omaps. + +KERNEL NEW DEPENDENCIES +v4.3+ Update is needed for custom .config files to make sure + CONFIG_REGULATOR_PBIAS is enabled for MMC1 to work + properly. diff --git a/Documentation/arm64/ilp32.txt b/Documentation/arm64/ilp32.txt new file mode 100644 index 000000000000..4f6860b7004a --- /dev/null +++ b/Documentation/arm64/ilp32.txt @@ -0,0 +1,55 @@ +ILP32 AARCH64 SYSCALL ABI +========================= +Written by Andrew Pinski <apinski@cavium.com> +Updated by Philipp Tomsich <philipp.tomsich@theobroma-systems.com> + + +This document describes the ILP32 syscall ABI and where it differs +from the generic linux syscall interface. + +Some structures are changed to reduce the difference in the code path +for both ILP32 and LP64 ABIs for signal handling. + +The following structures have been changed so the layout of the +structures are the same between ILP32 and LP64 ABIs, including: + * sigval_t contains pointers + * sigevent Uses sigval_t which causes it to be the same. Special + handing is needed for reading; in the mq_notify syscall + * sigaction Conversion is handled in the userland (glibc), as the + userland data structures are defined in glibc anyway. + +A number of structures differ between ILP32 and LP64, including: + * timespec uses time_t and suseconds_t + * timeval uses time_t and suseconds_t + * stat uses timespec/time_t + * semid64_ds uses time_t. + * msqid64_ds uses time_t. + * shmid64_ds uses time_t. + * rt_sigframe uses siginfo and ucontext. + * siginfo_t uses clock_t and sigval_t + * ucontext uses stack_t and sigset_t + * fd_set This is done to avoid endian issues between ILP32 and + LP64. Syscalls consuming fd_set use timespec. + * struct msgbuf The specification of 'struct msgbuf' defines the 'mtype' + field as a 'long' (i.e. 32bit for ILP32, but 64bit for + LP64). Functions that operate on 'struct msgbuf' need + to be passed through the compat-syscalls to resolve + this. + * stack_t contains pointers (handled in the compatibility layer) + +Also the syscalls which normally would pass 64bit values as two arguments; +now pass the 64bit value as one argument. Also they have been renamed +(removing the 64 from the name) to avoid confusion. +The list of these LP64 syscalls reused by ILP32 clients is: + * fcntl + * statfs + * fstatfs + * truncate + * ftruncate + * lseek + * sendfile + * newfstatat + * fstat + * mmap + * fadvise64 + diff --git a/Documentation/devicetree/bindings/net/cpsw.txt b/Documentation/devicetree/bindings/net/cpsw.txt index a9df21aaa154..a2cae4eb4a60 100644 --- a/Documentation/devicetree/bindings/net/cpsw.txt +++ b/Documentation/devicetree/bindings/net/cpsw.txt @@ -39,6 +39,7 @@ Required properties: Optional properties: - dual_emac_res_vlan : Specifies VID to be used to segregate the ports - mac-address : See ethernet.txt file in the same directory +- phy-handle : See ethernet.txt file in the same directory Note: "ti,hwmods" field is used to fetch the base address and irq resources from TI, omap hwmod data base during device registration. diff --git a/Documentation/devicetree/bindings/net/smsc-lan87xx.txt b/Documentation/devicetree/bindings/net/smsc-lan87xx.txt new file mode 100644 index 000000000000..974edd5c85cc --- /dev/null +++ b/Documentation/devicetree/bindings/net/smsc-lan87xx.txt @@ -0,0 +1,24 @@ +SMSC LAN87xx Ethernet PHY + +Some boards require special tuning values. Configure them +through an Ethernet OF device node. + +Optional properties: + +- smsc,disable-energy-detect: + If set, do not enable energy detect mode for the SMSC phy. + default: enable energy detect mode + +Examples: +smsc phy with disabled energy detect mode on an am335x based board. +&davinci_mdio { + pinctrl-names = "default", "sleep"; + pinctrl-0 = <&davinci_mdio_default>; + pinctrl-1 = <&davinci_mdio_sleep>; + status = "okay"; + + ethernetphy0: ethernet-phy@0 { + reg = <0>; + smsc,disable-energy-detect; + }; +}; diff --git a/MAINTAINERS b/MAINTAINERS index e957f0ffb4e9..0364e77f102f 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -894,11 +894,12 @@ M: Lennert Buytenhek <kernel@wantstofly.org> L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) S: Maintained -ARM/Allwinner A1X SoC support +ARM/Allwinner sunXi SoC support M: Maxime Ripard <maxime.ripard@free-electrons.com> +M: Chen-Yu Tsai <wens@csie.org> L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) S: Maintained -N: sun[x4567]i +N: sun[x456789]i ARM/Allwinner SoC Clock Support M: Emilio López <emilio@elopez.com.ar> @@ -4427,6 +4428,14 @@ L: linuxppc-dev@lists.ozlabs.org S: Maintained F: drivers/net/ethernet/freescale/ucc_geth* +FREESCALE eTSEC ETHERNET DRIVER (GIANFAR) +M: Claudiu Manoil <claudiu.manoil@freescale.com> +L: netdev@vger.kernel.org +S: Maintained +F: drivers/net/ethernet/freescale/gianfar* +X: drivers/net/ethernet/freescale/gianfar_ptp.c +F: Documentation/devicetree/bindings/net/fsl-tsec-phy.txt + FREESCALE QUICC ENGINE UCC UART DRIVER M: Timur Tabi <timur@tabi.org> L: linuxppc-dev@lists.ozlabs.org @@ -6793,7 +6802,6 @@ F: drivers/scsi/megaraid/ MELLANOX ETHERNET DRIVER (mlx4_en) M: Amir Vadai <amirv@mellanox.com> -M: Ido Shamay <idos@mellanox.com> L: netdev@vger.kernel.org S: Supported W: http://www.mellanox.com @@ -11685,6 +11693,7 @@ F: drivers/tty/serial/zs.* ZSMALLOC COMPRESSED SLAB MEMORY ALLOCATOR M: Minchan Kim <minchan@kernel.org> M: Nitin Gupta <ngupta@vflare.org> +R: Sergey Senozhatsky <sergey.senozhatsky.work@gmail.com> L: linux-mm@kvack.org S: Maintained F: mm/zsmalloc.c @@ -1,7 +1,7 @@ VERSION = 4 PATCHLEVEL = 3 SUBLEVEL = 0 -EXTRAVERSION = -rc6 +EXTRAVERSION = NAME = Blurry Fish Butt # *DOCUMENTATION* diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig index 5a64955e484c..6be62fb1ce75 100644 --- a/arch/arm/Kconfig +++ b/arch/arm/Kconfig @@ -645,6 +645,7 @@ config ARCH_SHMOBILE_LEGACY config ARCH_RPC bool "RiscPC" + depends on MMU select ARCH_ACORN select ARCH_MAY_HAVE_PC_FDC select ARCH_SPARSEMEM_ENABLE diff --git a/arch/arm/boot/dts/am57xx-beagle-x15.dts b/arch/arm/boot/dts/am57xx-beagle-x15.dts index 568adf5efde0..d55e3ea89fda 100644 --- a/arch/arm/boot/dts/am57xx-beagle-x15.dts +++ b/arch/arm/boot/dts/am57xx-beagle-x15.dts @@ -402,11 +402,12 @@ /* SMPS9 unused */ ldo1_reg: ldo1 { - /* VDD_SD */ + /* VDD_SD / VDDSHV8 */ regulator-name = "ldo1"; regulator-min-microvolt = <1800000>; regulator-max-microvolt = <3300000>; regulator-boot-on; + regulator-always-on; }; ldo2_reg: ldo2 { diff --git a/arch/arm/boot/dts/armada-385-db-ap.dts b/arch/arm/boot/dts/armada-385-db-ap.dts index 89f5a95954ed..4047621b137e 100644 --- a/arch/arm/boot/dts/armada-385-db-ap.dts +++ b/arch/arm/boot/dts/armada-385-db-ap.dts @@ -46,7 +46,7 @@ / { model = "Marvell Armada 385 Access Point Development Board"; - compatible = "marvell,a385-db-ap", "marvell,armada385", "marvell,armada38x"; + compatible = "marvell,a385-db-ap", "marvell,armada385", "marvell,armada380"; chosen { stdout-path = "serial1:115200n8"; diff --git a/arch/arm/boot/dts/berlin2q.dtsi b/arch/arm/boot/dts/berlin2q.dtsi index 63a48490e2f9..d4dbd28d348c 100644 --- a/arch/arm/boot/dts/berlin2q.dtsi +++ b/arch/arm/boot/dts/berlin2q.dtsi @@ -152,7 +152,7 @@ }; usb_phy2: phy@a2f400 { - compatible = "marvell,berlin2-usb-phy"; + compatible = "marvell,berlin2cd-usb-phy"; reg = <0xa2f400 0x128>; #phy-cells = <0>; resets = <&chip_rst 0x104 14>; @@ -170,7 +170,7 @@ }; usb_phy0: phy@b74000 { - compatible = "marvell,berlin2-usb-phy"; + compatible = "marvell,berlin2cd-usb-phy"; reg = <0xb74000 0x128>; #phy-cells = <0>; resets = <&chip_rst 0x104 12>; @@ -178,7 +178,7 @@ }; usb_phy1: phy@b78000 { - compatible = "marvell,berlin2-usb-phy"; + compatible = "marvell,berlin2cd-usb-phy"; reg = <0xb78000 0x128>; #phy-cells = <0>; resets = <&chip_rst 0x104 13>; diff --git a/arch/arm/boot/dts/emev2-kzm9d.dts b/arch/arm/boot/dts/emev2-kzm9d.dts index 955c24ee4a8c..8c24975e8f9d 100644 --- a/arch/arm/boot/dts/emev2-kzm9d.dts +++ b/arch/arm/boot/dts/emev2-kzm9d.dts @@ -35,28 +35,28 @@ button@1 { debounce_interval = <50>; - wakeup = <1>; + wakeup-source; label = "DSW2-1"; linux,code = <KEY_1>; gpios = <&gpio0 14 GPIO_ACTIVE_HIGH>; }; button@2 { debounce_interval = <50>; - wakeup = <1>; + wakeup-source; label = "DSW2-2"; linux,code = <KEY_2>; gpios = <&gpio0 15 GPIO_ACTIVE_HIGH>; }; button@3 { debounce_interval = <50>; - wakeup = <1>; + wakeup-source; label = "DSW2-3"; linux,code = <KEY_3>; gpios = <&gpio0 16 GPIO_ACTIVE_HIGH>; }; button@4 { debounce_interval = <50>; - wakeup = <1>; + wakeup-source; label = "DSW2-4"; linux,code = <KEY_4>; gpios = <&gpio0 17 GPIO_ACTIVE_HIGH>; diff --git a/arch/arm/boot/dts/exynos5420-peach-pit.dts b/arch/arm/boot/dts/exynos5420-peach-pit.dts index 8f4d76c5e11c..1b95da79293c 100644 --- a/arch/arm/boot/dts/exynos5420-peach-pit.dts +++ b/arch/arm/boot/dts/exynos5420-peach-pit.dts @@ -915,6 +915,11 @@ }; }; +&pmu_system_controller { + assigned-clocks = <&pmu_system_controller 0>; + assigned-clock-parents = <&clock CLK_FIN_PLL>; +}; + &rtc { status = "okay"; clocks = <&clock CLK_RTC>, <&max77802 MAX77802_CLK_32K_AP>; diff --git a/arch/arm/boot/dts/exynos5800-peach-pi.dts b/arch/arm/boot/dts/exynos5800-peach-pi.dts index 7d5b386b5ae6..8f40c7e549bd 100644 --- a/arch/arm/boot/dts/exynos5800-peach-pi.dts +++ b/arch/arm/boot/dts/exynos5800-peach-pi.dts @@ -878,6 +878,11 @@ }; }; +&pmu_system_controller { + assigned-clocks = <&pmu_system_controller 0>; + assigned-clock-parents = <&clock CLK_FIN_PLL>; +}; + &rtc { status = "okay"; clocks = <&clock CLK_RTC>, <&max77802 MAX77802_CLK_32K_AP>; diff --git a/arch/arm/boot/dts/imx7d.dtsi b/arch/arm/boot/dts/imx7d.dtsi index b738ce0f9d9b..6e444bb873f9 100644 --- a/arch/arm/boot/dts/imx7d.dtsi +++ b/arch/arm/boot/dts/imx7d.dtsi @@ -588,10 +588,10 @@ status = "disabled"; }; - uart2: serial@30870000 { + uart2: serial@30890000 { compatible = "fsl,imx7d-uart", "fsl,imx6q-uart"; - reg = <0x30870000 0x10000>; + reg = <0x30890000 0x10000>; interrupts = <GIC_SPI 27 IRQ_TYPE_LEVEL_HIGH>; clocks = <&clks IMX7D_UART2_ROOT_CLK>, <&clks IMX7D_UART2_ROOT_CLK>; diff --git a/arch/arm/boot/dts/logicpd-torpedo-37xx-devkit.dts b/arch/arm/boot/dts/logicpd-torpedo-37xx-devkit.dts index 91146c318798..5b0430041ec6 100644 --- a/arch/arm/boot/dts/logicpd-torpedo-37xx-devkit.dts +++ b/arch/arm/boot/dts/logicpd-torpedo-37xx-devkit.dts @@ -12,7 +12,7 @@ / { model = "LogicPD Zoom DM3730 Torpedo Development Kit"; - compatible = "logicpd,dm3730-torpedo-devkit", "ti,omap36xx"; + compatible = "logicpd,dm3730-torpedo-devkit", "ti,omap3630", "ti,omap3"; gpio_keys { compatible = "gpio-keys"; diff --git a/arch/arm/boot/dts/meson.dtsi b/arch/arm/boot/dts/meson.dtsi index 548441384d2a..8c77c87660cd 100644 --- a/arch/arm/boot/dts/meson.dtsi +++ b/arch/arm/boot/dts/meson.dtsi @@ -67,7 +67,7 @@ timer@c1109940 { compatible = "amlogic,meson6-timer"; - reg = <0xc1109940 0x14>; + reg = <0xc1109940 0x18>; interrupts = <0 10 1>; }; @@ -80,36 +80,37 @@ wdt: watchdog@c1109900 { compatible = "amlogic,meson6-wdt"; reg = <0xc1109900 0x8>; + interrupts = <0 0 1>; }; uart_AO: serial@c81004c0 { compatible = "amlogic,meson-uart"; - reg = <0xc81004c0 0x14>; + reg = <0xc81004c0 0x18>; interrupts = <0 90 1>; clocks = <&clk81>; status = "disabled"; }; - uart_A: serial@c81084c0 { + uart_A: serial@c11084c0 { compatible = "amlogic,meson-uart"; - reg = <0xc81084c0 0x14>; - interrupts = <0 90 1>; + reg = <0xc11084c0 0x18>; + interrupts = <0 26 1>; clocks = <&clk81>; status = "disabled"; }; - uart_B: serial@c81084dc { + uart_B: serial@c11084dc { compatible = "amlogic,meson-uart"; - reg = <0xc81084dc 0x14>; - interrupts = <0 90 1>; + reg = <0xc11084dc 0x18>; + interrupts = <0 75 1>; clocks = <&clk81>; status = "disabled"; }; - uart_C: serial@c8108700 { + uart_C: serial@c1108700 { compatible = "amlogic,meson-uart"; - reg = <0xc8108700 0x14>; - interrupts = <0 90 1>; + reg = <0xc1108700 0x18>; + interrupts = <0 93 1>; clocks = <&clk81>; status = "disabled"; }; diff --git a/arch/arm/boot/dts/omap3-evm-37xx.dts b/arch/arm/boot/dts/omap3-evm-37xx.dts index 16e8ce350dda..bb339d1648e0 100644 --- a/arch/arm/boot/dts/omap3-evm-37xx.dts +++ b/arch/arm/boot/dts/omap3-evm-37xx.dts @@ -13,7 +13,7 @@ / { model = "TI OMAP37XX EVM (TMDSEVM3730)"; - compatible = "ti,omap3-evm-37xx", "ti,omap36xx"; + compatible = "ti,omap3-evm-37xx", "ti,omap3630", "ti,omap3"; memory { device_type = "memory"; diff --git a/arch/arm/boot/dts/ste-hrefv60plus.dtsi b/arch/arm/boot/dts/ste-hrefv60plus.dtsi index 810cda743b6d..9c2387b34d0c 100644 --- a/arch/arm/boot/dts/ste-hrefv60plus.dtsi +++ b/arch/arm/boot/dts/ste-hrefv60plus.dtsi @@ -56,7 +56,7 @@ /* VMMCI level-shifter enable */ default_hrefv60_cfg2 { pins = "GPIO169_D22"; - ste,config = <&gpio_out_lo>; + ste,config = <&gpio_out_hi>; }; /* VMMCI level-shifter voltage select */ default_hrefv60_cfg3 { diff --git a/arch/arm/boot/dts/ste-snowball.dts b/arch/arm/boot/dts/ste-snowball.dts index 32a5ccb14e7e..e80e42163883 100644 --- a/arch/arm/boot/dts/ste-snowball.dts +++ b/arch/arm/boot/dts/ste-snowball.dts @@ -47,35 +47,35 @@ button@1 { debounce_interval = <50>; - wakeup = <1>; + wakeup-source; linux,code = <2>; label = "userpb"; gpios = <&gpio1 0 0x4>; }; button@2 { debounce_interval = <50>; - wakeup = <1>; + wakeup-source; linux,code = <3>; label = "extkb1"; gpios = <&gpio4 23 0x4>; }; button@3 { debounce_interval = <50>; - wakeup = <1>; + wakeup-source; linux,code = <4>; label = "extkb2"; gpios = <&gpio4 24 0x4>; }; button@4 { debounce_interval = <50>; - wakeup = <1>; + wakeup-source; linux,code = <5>; label = "extkb3"; gpios = <&gpio5 1 0x4>; }; button@5 { debounce_interval = <50>; - wakeup = <1>; + wakeup-source; linux,code = <6>; label = "extkb4"; gpios = <&gpio5 2 0x4>; diff --git a/arch/arm/boot/dts/tegra114.dtsi b/arch/arm/boot/dts/tegra114.dtsi index 9d4f86e9c50a..d845bd1448b5 100644 --- a/arch/arm/boot/dts/tegra114.dtsi +++ b/arch/arm/boot/dts/tegra114.dtsi @@ -234,7 +234,9 @@ gpio-controller; #interrupt-cells = <2>; interrupt-controller; + /* gpio-ranges = <&pinmux 0 0 246>; + */ }; apbmisc@70000800 { diff --git a/arch/arm/boot/dts/tegra124.dtsi b/arch/arm/boot/dts/tegra124.dtsi index 1e204a6de12c..819e2ae2cabe 100644 --- a/arch/arm/boot/dts/tegra124.dtsi +++ b/arch/arm/boot/dts/tegra124.dtsi @@ -258,7 +258,9 @@ gpio-controller; #interrupt-cells = <2>; interrupt-controller; + /* gpio-ranges = <&pinmux 0 0 251>; + */ }; apbdma: dma@0,60020000 { diff --git a/arch/arm/boot/dts/tegra20.dtsi b/arch/arm/boot/dts/tegra20.dtsi index e058709e6d98..969b828505ae 100644 --- a/arch/arm/boot/dts/tegra20.dtsi +++ b/arch/arm/boot/dts/tegra20.dtsi @@ -244,7 +244,9 @@ gpio-controller; #interrupt-cells = <2>; interrupt-controller; + /* gpio-ranges = <&pinmux 0 0 224>; + */ }; apbmisc@70000800 { diff --git a/arch/arm/boot/dts/tegra30.dtsi b/arch/arm/boot/dts/tegra30.dtsi index fe04fb5e155f..c6938ad1b543 100644 --- a/arch/arm/boot/dts/tegra30.dtsi +++ b/arch/arm/boot/dts/tegra30.dtsi @@ -349,7 +349,9 @@ gpio-controller; #interrupt-cells = <2>; interrupt-controller; + /* gpio-ranges = <&pinmux 0 0 248>; + */ }; apbmisc@70000800 { diff --git a/arch/arm/boot/dts/uniphier-ph1-ld6b-ref.dts b/arch/arm/boot/dts/uniphier-ph1-ld6b-ref.dts index 33963acd7e8f..f80f772d99fb 100644 --- a/arch/arm/boot/dts/uniphier-ph1-ld6b-ref.dts +++ b/arch/arm/boot/dts/uniphier-ph1-ld6b-ref.dts @@ -85,7 +85,7 @@ }; ðsc { - interrupts = <0 50 4>; + interrupts = <0 52 4>; }; &serial0 { diff --git a/arch/arm/kvm/Kconfig b/arch/arm/kvm/Kconfig index 210eccadb69a..356970f3b25e 100644 --- a/arch/arm/kvm/Kconfig +++ b/arch/arm/kvm/Kconfig @@ -21,6 +21,7 @@ config KVM depends on MMU && OF select PREEMPT_NOTIFIERS select ANON_INODES + select ARM_GIC select HAVE_KVM_CPU_RELAX_INTERCEPT select HAVE_KVM_ARCH_TLB_FLUSH_ALL select KVM_MMIO diff --git a/arch/arm/kvm/arm.c b/arch/arm/kvm/arm.c index dc017adfddc8..78b286994577 100644 --- a/arch/arm/kvm/arm.c +++ b/arch/arm/kvm/arm.c @@ -1080,7 +1080,7 @@ static int init_hyp_mode(void) */ err = kvm_timer_hyp_init(); if (err) - goto out_free_mappings; + goto out_free_context; #ifndef CONFIG_HOTPLUG_CPU free_boot_hyp_pgd(); diff --git a/arch/arm/mach-exynos/pm_domains.c b/arch/arm/mach-exynos/pm_domains.c index 4a87e86dec45..7c21760f590f 100644 --- a/arch/arm/mach-exynos/pm_domains.c +++ b/arch/arm/mach-exynos/pm_domains.c @@ -200,15 +200,15 @@ no_clk: args.args_count = 0; child_domain = of_genpd_get_from_provider(&args); if (IS_ERR(child_domain)) - goto next_pd; + continue; if (of_parse_phandle_with_args(np, "power-domains", "#power-domain-cells", 0, &args) != 0) - goto next_pd; + continue; parent_domain = of_genpd_get_from_provider(&args); if (IS_ERR(parent_domain)) - goto next_pd; + continue; if (pm_genpd_add_subdomain(parent_domain, child_domain)) pr_warn("%s failed to add subdomain: %s\n", @@ -216,8 +216,6 @@ no_clk: else pr_info("%s has as child subdomain: %s.\n", parent_domain->name, child_domain->name); -next_pd: - of_node_put(np); } return 0; diff --git a/arch/arm/mach-omap2/Kconfig b/arch/arm/mach-omap2/Kconfig index b3a0dff67e3f..33d1460a5639 100644 --- a/arch/arm/mach-omap2/Kconfig +++ b/arch/arm/mach-omap2/Kconfig @@ -49,6 +49,7 @@ config SOC_OMAP5 select OMAP_INTERCONNECT select OMAP_INTERCONNECT_BARRIER select PM_OPP if PM + select ZONE_DMA if ARM_LPAE config SOC_AM33XX bool "TI AM33XX" @@ -78,6 +79,7 @@ config SOC_DRA7XX select OMAP_INTERCONNECT select OMAP_INTERCONNECT_BARRIER select PM_OPP if PM + select ZONE_DMA if ARM_LPAE config ARCH_OMAP2PLUS bool diff --git a/arch/arm/mach-omap2/board-generic.c b/arch/arm/mach-omap2/board-generic.c index 6133eaac685d..fb219a30c10c 100644 --- a/arch/arm/mach-omap2/board-generic.c +++ b/arch/arm/mach-omap2/board-generic.c @@ -106,6 +106,7 @@ DT_MACHINE_START(OMAP3_DT, "Generic OMAP3 (Flattened Device Tree)") MACHINE_END static const char *const omap36xx_boards_compat[] __initconst = { + "ti,omap3630", "ti,omap36xx", NULL, }; @@ -243,6 +244,9 @@ static const char *const omap5_boards_compat[] __initconst = { }; DT_MACHINE_START(OMAP5_DT, "Generic OMAP5 (Flattened Device Tree)") +#if defined(CONFIG_ZONE_DMA) && defined(CONFIG_ARM_LPAE) + .dma_zone_size = SZ_2G, +#endif .reserve = omap_reserve, .smp = smp_ops(omap4_smp_ops), .map_io = omap5_map_io, @@ -288,6 +292,9 @@ static const char *const dra74x_boards_compat[] __initconst = { }; DT_MACHINE_START(DRA74X_DT, "Generic DRA74X (Flattened Device Tree)") +#if defined(CONFIG_ZONE_DMA) && defined(CONFIG_ARM_LPAE) + .dma_zone_size = SZ_2G, +#endif .reserve = omap_reserve, .smp = smp_ops(omap4_smp_ops), .map_io = dra7xx_map_io, @@ -308,6 +315,9 @@ static const char *const dra72x_boards_compat[] __initconst = { }; DT_MACHINE_START(DRA72X_DT, "Generic DRA72X (Flattened Device Tree)") +#if defined(CONFIG_ZONE_DMA) && defined(CONFIG_ARM_LPAE) + .dma_zone_size = SZ_2G, +#endif .reserve = omap_reserve, .map_io = dra7xx_map_io, .init_early = dra7xx_init_early, diff --git a/arch/arm/mach-omap2/pdata-quirks.c b/arch/arm/mach-omap2/pdata-quirks.c index ea56397599c2..1dfe34654c43 100644 --- a/arch/arm/mach-omap2/pdata-quirks.c +++ b/arch/arm/mach-omap2/pdata-quirks.c @@ -559,7 +559,14 @@ static void pdata_quirks_check(struct pdata_init *quirks) void __init pdata_quirks_init(const struct of_device_id *omap_dt_match_table) { - omap_sdrc_init(NULL, NULL); + /* + * We still need this for omap2420 and omap3 PM to work, others are + * using drivers/misc/sram.c already. + */ + if (of_machine_is_compatible("ti,omap2420") || + of_machine_is_compatible("ti,omap3")) + omap_sdrc_init(NULL, NULL); + pdata_quirks_check(auxdata_quirks); of_platform_populate(NULL, omap_dt_match_table, omap_auxdata_lookup, NULL); diff --git a/arch/arm/mach-pxa/pxa3xx.c b/arch/arm/mach-pxa/pxa3xx.c index 06005d3f2ba3..20ce2d386f17 100644 --- a/arch/arm/mach-pxa/pxa3xx.c +++ b/arch/arm/mach-pxa/pxa3xx.c @@ -42,10 +42,6 @@ #define PECR_IS(n) ((1 << ((n) * 2)) << 29) extern void __init pxa_dt_irq_init(int (*fn)(struct irq_data *, unsigned int)); -#ifdef CONFIG_PM - -#define ISRAM_START 0x5c000000 -#define ISRAM_SIZE SZ_256K /* * NAND NFC: DFI bus arbitration subset @@ -54,6 +50,11 @@ extern void __init pxa_dt_irq_init(int (*fn)(struct irq_data *, unsigned int)); #define NDCR_ND_ARB_EN (1 << 12) #define NDCR_ND_ARB_CNTL (1 << 19) +#ifdef CONFIG_PM + +#define ISRAM_START 0x5c000000 +#define ISRAM_SIZE SZ_256K + static void __iomem *sram; static unsigned long wakeup_src; diff --git a/arch/arm/net/bpf_jit_32.c b/arch/arm/net/bpf_jit_32.c index 876060bcceeb..b8efb8cd1f73 100644 --- a/arch/arm/net/bpf_jit_32.c +++ b/arch/arm/net/bpf_jit_32.c @@ -614,6 +614,7 @@ load_common: case BPF_LD | BPF_B | BPF_IND: load_order = 0; load_ind: + update_on_xread(ctx); OP_IMM3(ARM_ADD, r_off, r_X, k, ctx); goto load_common; case BPF_LDX | BPF_IMM: diff --git a/arch/arm/plat-orion/common.c b/arch/arm/plat-orion/common.c index 2235081a04ee..8861c367d061 100644 --- a/arch/arm/plat-orion/common.c +++ b/arch/arm/plat-orion/common.c @@ -495,7 +495,7 @@ void __init orion_ge00_switch_init(struct dsa_platform_data *d, int irq) d->netdev = &orion_ge00.dev; for (i = 0; i < d->nr_chips; i++) - d->chip[i].host_dev = &orion_ge00_shared.dev; + d->chip[i].host_dev = &orion_ge_mvmdio.dev; orion_switch_device.dev.platform_data = d; platform_device_register(&orion_switch_device); diff --git a/arch/arm/vdso/vdsomunge.c b/arch/arm/vdso/vdsomunge.c index aedec81d1198..0cebd98cd88c 100644 --- a/arch/arm/vdso/vdsomunge.c +++ b/arch/arm/vdso/vdsomunge.c @@ -45,7 +45,6 @@ * it does. */ -#include <byteswap.h> #include <elf.h> #include <errno.h> #include <fcntl.h> @@ -59,6 +58,16 @@ #include <sys/types.h> #include <unistd.h> +#define swab16(x) \ + ((((x) & 0x00ff) << 8) | \ + (((x) & 0xff00) >> 8)) + +#define swab32(x) \ + ((((x) & 0x000000ff) << 24) | \ + (((x) & 0x0000ff00) << 8) | \ + (((x) & 0x00ff0000) >> 8) | \ + (((x) & 0xff000000) << 24)) + #if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__ #define HOST_ORDER ELFDATA2LSB #elif __BYTE_ORDER__ == __ORDER_BIG_ENDIAN__ @@ -104,17 +113,17 @@ static void cleanup(void) static Elf32_Word read_elf_word(Elf32_Word word, bool swap) { - return swap ? bswap_32(word) : word; + return swap ? swab32(word) : word; } static Elf32_Half read_elf_half(Elf32_Half half, bool swap) { - return swap ? bswap_16(half) : half; + return swap ? swab16(half) : half; } static void write_elf_word(Elf32_Word val, Elf32_Word *dst, bool swap) { - *dst = swap ? bswap_32(val) : val; + *dst = swap ? swab32(val) : val; } int main(int argc, char **argv) diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index 3aa5028607ae..9cfbabf3f7a5 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -727,6 +727,11 @@ menu "Userspace binary formats" source "fs/Kconfig.binfmt" config COMPAT + def_bool y + depends on AARCH32_EL0 || ARM64_ILP32 + select COMPAT_BINFMT_ELF + +config AARCH32_EL0 bool "Kernel support for 32-bit EL0" depends on !ARM64_64K_PAGES || EXPERT select COMPAT_BINFMT_ELF @@ -745,9 +750,16 @@ config COMPAT If you want to execute 32-bit userspace applications, say Y. +config ARM64_ILP32 + bool "Kernel support for ILP32" + help + This option enables support for AArch64 ILP32 user space. ILP32 + is an ABI where long and pointers are 32bits but it uses the AARCH64 + instruction set. + config SYSVIPC_COMPAT def_bool y - depends on COMPAT && SYSVIPC + depends on AARCH32_EL0 && SYSVIPC endmenu diff --git a/arch/arm64/Makefile b/arch/arm64/Makefile index 6ca213579455..7062ff930c2c 100644 --- a/arch/arm64/Makefile +++ b/arch/arm64/Makefile @@ -30,14 +30,19 @@ KBUILD_CFLAGS += -mgeneral-regs-only $(lseinstr) KBUILD_AFLAGS += $(lseinstr) KBUILD_CFLAGS += -fno-pic +KBUILD_CFLAGS += $(call cc-option,-mabi=lp64) +KBUILD_AFLAGS += $(call cc-option,-mabi=lp64) + ifeq ($(CONFIG_CPU_BIG_ENDIAN), y) KBUILD_CPPFLAGS += -mbig-endian AS += -EB LD += -EB +LDFLAGS += -maarch64linuxb else KBUILD_CPPFLAGS += -mlittle-endian AS += -EL LD += -EL +LDFLAGS += -maarch64linux endif CHECKFLAGS += -D__aarch64__ diff --git a/arch/arm64/boot/dts/arm/juno-motherboard.dtsi b/arch/arm64/boot/dts/arm/juno-motherboard.dtsi index 637e046f0e36..3c386680357e 100644 --- a/arch/arm64/boot/dts/arm/juno-motherboard.dtsi +++ b/arch/arm64/boot/dts/arm/juno-motherboard.dtsi @@ -61,42 +61,42 @@ button@1 { debounce_interval = <50>; - wakeup = <1>; + wakeup-source; linux,code = <116>; label = "POWER"; gpios = <&iofpga_gpio0 0 0x4>; }; button@2 { debounce_interval = <50>; - wakeup = <1>; + wakeup-source; linux,code = <102>; label = "HOME"; gpios = <&iofpga_gpio0 1 0x4>; }; button@3 { debounce_interval = <50>; - wakeup = <1>; + wakeup-source; linux,code = <152>; label = "RLOCK"; gpios = <&iofpga_gpio0 2 0x4>; }; button@4 { debounce_interval = <50>; - wakeup = <1>; + wakeup-source; linux,code = <115>; label = "VOL+"; gpios = <&iofpga_gpio0 3 0x4>; }; button@5 { debounce_interval = <50>; - wakeup = <1>; + wakeup-source; linux,code = <114>; label = "VOL-"; gpios = <&iofpga_gpio0 4 0x4>; }; button@6 { debounce_interval = <50>; - wakeup = <1>; + wakeup-source; linux,code = <99>; label = "NMI"; gpios = <&iofpga_gpio0 5 0x4>; diff --git a/arch/arm64/include/asm/compat.h b/arch/arm64/include/asm/compat.h index 7fbed6919b54..087f21be231c 100644 --- a/arch/arm64/include/asm/compat.h +++ b/arch/arm64/include/asm/compat.h @@ -214,6 +214,9 @@ typedef struct compat_siginfo { } _sifields; } compat_siginfo_t; +/* ILP32 uses the native siginfo and not the compat struct */ +#define COMPAT_USE_NATIVE_SIGINFO !is_a32_compat_task() + #define COMPAT_OFF_T_MAX 0x7fffffff #define COMPAT_LOFF_T_MAX 0x7fffffffffffffffL @@ -299,19 +302,80 @@ struct compat_shmid64_ds { compat_ulong_t __unused5; }; -static inline int is_compat_task(void) +#ifdef CONFIG_AARCH32_EL0 + +static inline int is_a32_compat_task(void) { return test_thread_flag(TIF_32BIT); } -static inline int is_compat_thread(struct thread_info *thread) +static inline int is_a32_compat_thread(struct thread_info *thread) { return test_ti_thread_flag(thread, TIF_32BIT); } +#else + +static inline int is_a32_compat_task(void) +{ + return 0; +} + +static inline int is_a32_compat_thread(struct thread_info *thread) +{ + return 0; +} +#endif + +#ifdef CONFIG_ARM64_ILP32 + +static inline int is_ilp32_compat_task(void) +{ + return test_thread_flag(TIF_32BIT_AARCH64); +} + +static inline int is_ilp32_compat_thread(struct thread_info *thread) +{ + return test_ti_thread_flag(thread, TIF_32BIT_AARCH64); +} + +#else + +static inline int is_ilp32_compat_task(void) +{ + return 0; +} + +static inline int is_ilp32_compat_thread(struct thread_info *thread) +{ + return 0; +} + +#endif + +static inline int is_compat_task(void) +{ + return is_a32_compat_task() || is_ilp32_compat_task(); +} + #else /* !CONFIG_COMPAT */ -static inline int is_compat_thread(struct thread_info *thread) +static inline int is_a32_compat_thread(struct thread_info *thread) +{ + return 0; +} + +static inline int is_a32_compat_task(void) +{ + return 0; +} + +static inline int is_ilp32_compat_thread(struct thread_info *thread) +{ + return 0; +} + +static inline int is_ilp32_compat_task(void) { return 0; } diff --git a/arch/arm64/include/asm/elf.h b/arch/arm64/include/asm/elf.h index faad6df49e5b..3e7956961cc5 100644 --- a/arch/arm64/include/asm/elf.h +++ b/arch/arm64/include/asm/elf.h @@ -134,7 +134,11 @@ typedef struct user_fpsimd_state elf_fpregset_t; */ #define ELF_PLAT_INIT(_r, load_addr) (_r)->regs[0] = 0 -#define SET_PERSONALITY(ex) clear_thread_flag(TIF_32BIT); +#define SET_PERSONALITY(ex) \ +do { \ + clear_thread_flag(TIF_32BIT_AARCH64); \ + clear_thread_flag(TIF_32BIT); \ +} while (0) #define ARCH_DLINFO \ do { \ @@ -149,7 +153,7 @@ extern int arch_setup_additional_pages(struct linux_binprm *bprm, /* 1GB of VA */ #ifdef CONFIG_COMPAT -#define STACK_RND_MASK (test_thread_flag(TIF_32BIT) ? \ +#define STACK_RND_MASK (is_compat_task() ? \ 0x7ff >> (PAGE_SHIFT - 12) : \ 0x3ffff >> (PAGE_SHIFT - 12)) #else @@ -159,30 +163,103 @@ extern int arch_setup_additional_pages(struct linux_binprm *bprm, #ifdef CONFIG_COMPAT #ifdef __AARCH64EB__ -#define COMPAT_ELF_PLATFORM ("v8b") +#define COMPAT_ELF_PLATFORM (is_ilp32_compat_task() ? "aarch64_be:ilp32" : "v8b") #else -#define COMPAT_ELF_PLATFORM ("v8l") +#define COMPAT_ELF_PLATFORM (is_ilp32_compat_task() ? "aarch64:ilp32" : "v8l") #endif #define COMPAT_ELF_ET_DYN_BASE (2 * TASK_SIZE_32 / 3) +extern int aarch32_setup_vectors_page(struct linux_binprm *bprm, + int uses_interp); + +#ifdef CONFIG_AARCH32_EL0 + /* AArch32 registers. */ -#define COMPAT_ELF_NGREG 18 -typedef unsigned int compat_elf_greg_t; -typedef compat_elf_greg_t compat_elf_gregset_t[COMPAT_ELF_NGREG]; +#define COMPAT_A32_ELF_NGREG 18 +typedef unsigned int compat_a32_elf_greg_t; +typedef compat_a32_elf_greg_t compat_a32_elf_gregset_t[COMPAT_A32_ELF_NGREG]; /* AArch32 EABI. */ #define EF_ARM_EABI_MASK 0xff000000 -#define compat_elf_check_arch(x) (((x)->e_machine == EM_ARM) && \ +#define compat_a32_elf_check_arch(x) (((x)->e_machine == EM_ARM) && \ ((x)->e_flags & EF_ARM_EABI_MASK)) #define compat_start_thread compat_start_thread -#define COMPAT_SET_PERSONALITY(ex) set_thread_flag(TIF_32BIT); -#define COMPAT_ARCH_DLINFO -extern int aarch32_setup_vectors_page(struct linux_binprm *bprm, - int uses_interp); -#define compat_arch_setup_additional_pages \ - aarch32_setup_vectors_page +#define COMPAT_A32_SET_PERSONALITY(ex) \ +do { \ + clear_thread_flag(TIF_32BIT_AARCH64); \ + set_thread_flag(TIF_32BIT); \ +} while (0) +#define COMPAT_A32_ARCH_DLINFO do {} while (0) + +#else + +typedef elf_greg_t compat_elf_greg_t; +typedef elf_gregset_t compat_elf_gregset_t; +#define compat_a32_elf_check_arch(x) 0 +#define COMPAT_A32_SET_PERSONALITY(ex) do {} while (0) +#define COMPAT_A32_ARCH_DLINFO do {} while (0) +#endif + +/* If ILP32 is turned on, we want to define the compat_elf_greg_t to the non compat + one and define PR_REG_SIZE/PRSTATUS_SIZE/SET_PR_FPVALID so we pick up the correct + ones for AARCH32. Note also the definition of the macros have to be correct for + LP64 as this file is included in the standard binfmt_elf.c. */ +#ifdef CONFIG_ARM64_ILP32 +typedef elf_greg_t compat_elf_greg_t; +typedef elf_gregset_t compat_elf_gregset_t; +#define PR_REG_SIZE(S) (is_a32_compat_task() ? 72 : 272) +#define PRSTATUS_SIZE(S) (is_a32_compat_task() ? 124 : (is_ilp32_compat_task() ? 352 : 392)) +#define SET_PR_FPVALID(S, V) \ +do { \ + *(int *) (((void *) &((S)->pr_reg)) + PR_REG_SIZE((S)->pr_reg)) = (V); \ +} while (0) +#else +typedef compat_a32_elf_greg_t compat_elf_greg_t; +typedef compat_a32_elf_gregset_t compat_elf_gregset_t; +#endif + +#ifdef CONFIG_ARM64_ILP32 +#define compat_ilp32_elf_check_arch(x) ((x)->e_machine == EM_AARCH64) +#define COMPAT_ILP32_SET_PERSONALITY(ex) \ +do { \ + set_thread_flag(TIF_32BIT_AARCH64); \ + clear_thread_flag(TIF_32BIT); \ +} while (0) +#define COMPAT_ILP32_ARCH_DLINFO \ +do { \ + NEW_AUX_ENT(AT_SYSINFO_EHDR, \ + (elf_addr_t)(long)current->mm->context.vdso); \ +} while (0) +#else +#define compat_ilp32_elf_check_arch(x) 0 +#define COMPAT_ILP32_SET_PERSONALITY(ex) do {} while (0) +#define COMPAT_ILP32_ARCH_DLINFO do {} while (0) +#endif + +#define compat_elf_check_arch(x) (compat_a32_elf_check_arch(x) || compat_ilp32_elf_check_arch(x)) +#define COMPAT_SET_PERSONALITY(ex) \ +do { \ + if (compat_a32_elf_check_arch(&ex)) \ + COMPAT_A32_SET_PERSONALITY(ex); \ + else \ + COMPAT_ILP32_SET_PERSONALITY(ex); \ +} while (0) + +/* ILP32 uses the "LP64-like" vdso pages */ +#define compat_arch_setup_additional_pages \ + (is_a32_compat_task() \ + ? &aarch32_setup_vectors_page \ + : &(arch_setup_additional_pages)) + +#define COMPAT_ARCH_DLINFO \ +do { \ + if (is_a32_compat_task()) \ + COMPAT_A32_ARCH_DLINFO; \ + else \ + COMPAT_ILP32_ARCH_DLINFO; \ +} while (0) #endif /* CONFIG_COMPAT */ diff --git a/arch/arm64/include/asm/fpsimd.h b/arch/arm64/include/asm/fpsimd.h index 50f559f574fe..63b19f128c6c 100644 --- a/arch/arm64/include/asm/fpsimd.h +++ b/arch/arm64/include/asm/fpsimd.h @@ -52,7 +52,7 @@ struct fpsimd_partial_state { }; -#if defined(__KERNEL__) && defined(CONFIG_COMPAT) +#if defined(__KERNEL__) && defined(CONFIG_AARCH32_EL0) /* Masks for extracting the FPSR and FPCR from the FPSCR */ #define VFP_FPSCR_STAT_MASK 0xf800009f #define VFP_FPSCR_CTRL_MASK 0x07f79f00 diff --git a/arch/arm64/include/asm/hwcap.h b/arch/arm64/include/asm/hwcap.h index 0ad735166d9f..1e5361ebf39f 100644 --- a/arch/arm64/include/asm/hwcap.h +++ b/arch/arm64/include/asm/hwcap.h @@ -47,9 +47,17 @@ #define ELF_HWCAP (elf_hwcap) #ifdef CONFIG_COMPAT -#define COMPAT_ELF_HWCAP (compat_elf_hwcap) -#define COMPAT_ELF_HWCAP2 (compat_elf_hwcap2) extern unsigned int compat_elf_hwcap, compat_elf_hwcap2; +#define COMPAT_ELF_HWCAP \ + (is_a32_compat_task() \ + ? compat_elf_hwcap \ + : elf_hwcap) + +#define COMPAT_ELF_HWCAP2 \ + (is_a32_compat_task() \ + ? compat_elf_hwcap2 \ + : 0) + #endif extern unsigned long elf_hwcap; diff --git a/arch/arm64/include/asm/memory.h b/arch/arm64/include/asm/memory.h index 6b4c3ad75a2a..337f8e19d69d 100644 --- a/arch/arm64/include/asm/memory.h +++ b/arch/arm64/include/asm/memory.h @@ -58,7 +58,7 @@ #ifdef CONFIG_COMPAT #define TASK_SIZE_32 UL(0x100000000) -#define TASK_SIZE (test_thread_flag(TIF_32BIT) ? \ +#define TASK_SIZE (is_compat_task() ? \ TASK_SIZE_32 : TASK_SIZE_64) #define TASK_SIZE_OF(tsk) (test_tsk_thread_flag(tsk, TIF_32BIT) ? \ TASK_SIZE_32 : TASK_SIZE_64) diff --git a/arch/arm64/include/asm/processor.h b/arch/arm64/include/asm/processor.h index 98f32355dc97..e244cb4e391c 100644 --- a/arch/arm64/include/asm/processor.h +++ b/arch/arm64/include/asm/processor.h @@ -28,6 +28,7 @@ #ifdef __KERNEL__ #include <linux/string.h> +#include <linux/thread_info.h> #include <asm/fpsimd.h> #include <asm/hw_breakpoint.h> @@ -39,7 +40,7 @@ #define STACK_TOP_MAX TASK_SIZE_64 #ifdef CONFIG_COMPAT #define AARCH32_VECTORS_BASE 0xffff0000 -#define STACK_TOP (test_thread_flag(TIF_32BIT) ? \ +#define STACK_TOP (is_compat_task() ? \ AARCH32_VECTORS_BASE : STACK_TOP_MAX) #else #define STACK_TOP STACK_TOP_MAX @@ -79,7 +80,7 @@ struct cpu_context { struct thread_struct { struct cpu_context cpu_context; /* cpu context */ unsigned long tp_value; /* TLS register */ -#ifdef CONFIG_COMPAT +#ifdef CONFIG_AARCH32_EL0 unsigned long tp2_value; #endif struct fpsimd_state fpsimd_state; @@ -88,11 +89,11 @@ struct thread_struct { struct debug_info debug; /* debugging */ }; -#ifdef CONFIG_COMPAT +#ifdef CONFIG_AARCH32_EL0 #define task_user_tls(t) \ ({ \ unsigned long *__tls; \ - if (is_compat_thread(task_thread_info(t))) \ + if (is_a32_compat_thread(task_thread_info(t))) \ __tls = &(t)->thread.tp2_value; \ else \ __tls = &(t)->thread.tp_value; \ @@ -123,6 +124,15 @@ static inline void start_thread(struct pt_regs *regs, unsigned long pc, static inline void compat_start_thread(struct pt_regs *regs, unsigned long pc, unsigned long sp) { +#ifdef CONFIG_ARM64_ILP32 + /* ILP32 thread are started the same way as LP64 threads. + Note we cannot use is_ilp32_compat_task here as that + would introduce a header depency issue. */ + if (test_thread_flag(TIF_32BIT_AARCH64)) { + start_thread(regs, pc, sp); + return; + } +#endif start_thread_common(regs, pc); regs->pstate = COMPAT_PSR_MODE_USR; if (pc & 1) diff --git a/arch/arm64/include/asm/ptrace.h b/arch/arm64/include/asm/ptrace.h index 536274ed292e..1059b3fcbf46 100644 --- a/arch/arm64/include/asm/ptrace.h +++ b/arch/arm64/include/asm/ptrace.h @@ -120,7 +120,7 @@ struct pt_regs { #define arch_has_single_step() (1) -#ifdef CONFIG_COMPAT +#ifdef CONFIG_AARCH32_EL0 #define compat_thumb_mode(regs) \ (((regs)->pstate & COMPAT_PSR_T_BIT)) #else diff --git a/arch/arm64/include/asm/signal32.h b/arch/arm64/include/asm/signal32.h index eeaa97559bab..70977182fc31 100644 --- a/arch/arm64/include/asm/signal32.h +++ b/arch/arm64/include/asm/signal32.h @@ -20,6 +20,7 @@ #ifdef CONFIG_COMPAT #include <linux/compat.h> +#ifdef CONFIG_AARCH32_EL0 #define AARCH32_KERN_SIGRET_CODE_OFFSET 0x500 extern const compat_ulong_t aarch32_sigret_code[6]; @@ -47,6 +48,24 @@ static inline int compat_setup_rt_frame(int usig, struct ksignal *ksig, sigset_t static inline void compat_setup_restart_syscall(struct pt_regs *regs) { } +#endif /* CONFIG_AARCH32_EL0 */ +#else +static inline void compat_setup_restart_syscall(struct pt_regs *regs) +{ +} + +static inline int compat_setup_rt_frame(int usig, struct ksignal *ksig, sigset_t *set, + struct pt_regs *regs) +{ + return -ENOSYS; +} + +static inline int compat_setup_frame(int usid, struct ksignal *ksig, + sigset_t *set, struct pt_regs *regs) +{ + return -ENOSYS; +} + #endif /* CONFIG_COMPAT */ #endif /* __KERNEL__ */ #endif /* __ASM_SIGNAL32_H */ diff --git a/arch/arm64/include/asm/stat.h b/arch/arm64/include/asm/stat.h index 15e35598ac40..af0427627f59 100644 --- a/arch/arm64/include/asm/stat.h +++ b/arch/arm64/include/asm/stat.h @@ -22,6 +22,7 @@ #include <asm/compat.h> +#ifdef CONFIG_AARCH32_EL0 /* * struct stat64 is needed for compat tasks only. Its definition is different * from the generic struct stat64. @@ -59,3 +60,4 @@ struct stat64 { #endif #endif +#endif diff --git a/arch/arm64/include/asm/thread_info.h b/arch/arm64/include/asm/thread_info.h index dcd06d18a42a..e72de7403a4c 100644 --- a/arch/arm64/include/asm/thread_info.h +++ b/arch/arm64/include/asm/thread_info.h @@ -110,8 +110,9 @@ static inline struct thread_info *current_thread_info(void) #define TIF_FREEZE 19 #define TIF_RESTORE_SIGMASK 20 #define TIF_SINGLESTEP 21 -#define TIF_32BIT 22 /* 32bit process */ +#define TIF_32BIT 22 /* AARCH32 process */ #define TIF_SWITCH_MM 23 /* deferred switch_mm */ +#define TIF_32BIT_AARCH64 24 /* 32 bit process on AArch64(ILP32) */ #define _TIF_SIGPENDING (1 << TIF_SIGPENDING) #define _TIF_NEED_RESCHED (1 << TIF_NEED_RESCHED) diff --git a/arch/arm64/include/asm/unistd.h b/arch/arm64/include/asm/unistd.h index 41e58fe3c041..696e63851790 100644 --- a/arch/arm64/include/asm/unistd.h +++ b/arch/arm64/include/asm/unistd.h @@ -13,20 +13,25 @@ * You should have received a copy of the GNU General Public License * along with this program. If not, see <http://www.gnu.org/licenses/>. */ -#ifdef CONFIG_COMPAT +#ifdef CONFIG_ARM64_ILP32 +#define __ARCH_WANT_COMPAT_SYS_PREADV64 +#define __ARCH_WANT_COMPAT_SYS_PWRITEV64 +#endif +#ifdef CONFIG_AARCH32_EL0 #define __ARCH_WANT_COMPAT_SYS_GETDENTS64 #define __ARCH_WANT_COMPAT_STAT64 #define __ARCH_WANT_SYS_GETHOSTNAME #define __ARCH_WANT_SYS_PAUSE #define __ARCH_WANT_SYS_GETPGRP -#define __ARCH_WANT_SYS_LLSEEK #define __ARCH_WANT_SYS_NICE #define __ARCH_WANT_SYS_SIGPENDING #define __ARCH_WANT_SYS_SIGPROCMASK #define __ARCH_WANT_COMPAT_SYS_SENDFILE #define __ARCH_WANT_SYS_FORK #define __ARCH_WANT_SYS_VFORK +#endif +#ifdef CONFIG_COMPAT /* * Compat syscall numbers used by the AArch64 kernel. */ @@ -37,6 +42,8 @@ #define __NR_compat_sigreturn 119 #define __NR_compat_rt_sigreturn 173 +#define __ARCH_WANT_SYS_LLSEEK + /* * The following SVCs are ARM private. */ diff --git a/arch/arm64/include/uapi/asm/siginfo.h b/arch/arm64/include/uapi/asm/siginfo.h index 5a74a0853db0..d9ac7d46c984 100644 --- a/arch/arm64/include/uapi/asm/siginfo.h +++ b/arch/arm64/include/uapi/asm/siginfo.h @@ -1,5 +1,6 @@ /* * Copyright (C) 2012 ARM Ltd. + * Copyright (C) 2015 Cavium Inc. * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License version 2 as @@ -18,6 +19,26 @@ #define __ARCH_SI_PREAMBLE_SIZE (4 * sizeof(int)) +#ifdef __ILP32__ +# ifdef __AARCH64EB__ +# define __SIGINFO_INNER(type, field) \ + int __pad#field; \ + type field +# else +# define __SIGINFO_INNER(type, field) \ + type field; \ + int __pad#field +# endif + +# undef __SIGINFO_VOIDPOINTER +# define __SIGINFO_VOIDPOINTER(field) \ + __SIGINFO_INNER(void __user*, field) +# undef __SIGINFO_BAND + +# define __SIGINFO_BAND(field) \ + __SIGINFO_INNER(long, field) +#endif + #include <asm-generic/siginfo.h> #endif diff --git a/arch/arm64/include/uapi/asm/signal.h b/arch/arm64/include/uapi/asm/signal.h index 991bf5db2ca1..5053af46f66b 100644 --- a/arch/arm64/include/uapi/asm/signal.h +++ b/arch/arm64/include/uapi/asm/signal.h @@ -22,6 +22,37 @@ #define MINSIGSTKSZ 5120 #define SIGSTKSZ 16384 +/* For ILP32, sigset should be the same size fields as LP64 so use + unsigned long long. */ +#ifdef __ILP32__ +#define __SIGSET_INNER_TYPE __extension__ unsigned long long +#define _NSIG_BPW 64 + +# ifdef __AARCH64EB__ +# define __SIGNAL_INNER(type, field) \ + __extension__ struct { \ + int __pad_##field; \ + type field; \ + } __attribute__((aligned(8))) +# else +# define __SIGNAL_INNER(type, field) \ + __extension__ struct { \ + type field; \ + int __pad_##field; \ + } __attribute__((aligned(8))) +# endif + +# define __SIGACTION_HANDLER(field) \ + __SIGNAL_INNER(__sighandler_t, field) + +#define __SIGACTION_FLAGS(field) \ + __extension__ unsigned long long field + +#define __SIGACTION_RESTORER(field) \ + __SIGNAL_INNER(__sigrestore_t, field) + +#endif + #include <asm-generic/signal.h> #endif diff --git a/arch/arm64/kernel/Makefile b/arch/arm64/kernel/Makefile index 22dc9bc781be..837d7301cbfd 100644 --- a/arch/arm64/kernel/Makefile +++ b/arch/arm64/kernel/Makefile @@ -20,10 +20,12 @@ arm64-obj-y := debug-monitors.o entry.o irq.o fpsimd.o \ cpufeature.o alternative.o cacheinfo.o \ smp.o smp_spin_table.o topology.o -arm64-obj-$(CONFIG_COMPAT) += sys32.o kuser32.o signal32.o \ +arm64-obj-$(CONFIG_AARCH32_EL0) += sys32.o kuser32.o signal32.o \ sys_compat.o entry32.o \ ../../arm/kernel/opcodes.o arm64-obj-$(CONFIG_FUNCTION_TRACER) += ftrace.o entry-ftrace.o +arm64-obj-$(CONFIG_ARM64_ILP32) += sys_ilp32.o +arm64-obj-$(CONFIG_COMPAT) += entry32-common.o arm64-obj-$(CONFIG_MODULES) += arm64ksyms.o module.o arm64-obj-$(CONFIG_PERF_EVENTS) += perf_regs.o perf_callchain.o arm64-obj-$(CONFIG_HW_PERF_EVENTS) += perf_event.o diff --git a/arch/arm64/kernel/armv8_deprecated.c b/arch/arm64/kernel/armv8_deprecated.c index bcee7abac68e..937f5e58a4d3 100644 --- a/arch/arm64/kernel/armv8_deprecated.c +++ b/arch/arm64/kernel/armv8_deprecated.c @@ -284,21 +284,23 @@ static void register_insn_emulation_sysctl(struct ctl_table *table) __asm__ __volatile__( \ ALTERNATIVE("nop", SET_PSTATE_PAN(0), ARM64_HAS_PAN, \ CONFIG_ARM64_PAN) \ - " mov %w2, %w1\n" \ - "0: ldxr"B" %w1, [%3]\n" \ - "1: stxr"B" %w0, %w2, [%3]\n" \ + "0: ldxr"B" %w2, [%3]\n" \ + "1: stxr"B" %w0, %w1, [%3]\n" \ " cbz %w0, 2f\n" \ " mov %w0, %w4\n" \ + " b 3f\n" \ "2:\n" \ + " mov %w1, %w2\n" \ + "3:\n" \ " .pushsection .fixup,\"ax\"\n" \ " .align 2\n" \ - "3: mov %w0, %w5\n" \ - " b 2b\n" \ + "4: mov %w0, %w5\n" \ + " b 3b\n" \ " .popsection" \ " .pushsection __ex_table,\"a\"\n" \ " .align 3\n" \ - " .quad 0b, 3b\n" \ - " .quad 1b, 3b\n" \ + " .quad 0b, 4b\n" \ + " .quad 1b, 4b\n" \ " .popsection\n" \ ALTERNATIVE("nop", SET_PSTATE_PAN(1), ARM64_HAS_PAN, \ CONFIG_ARM64_PAN) \ diff --git a/arch/arm64/kernel/asm-offsets.c b/arch/arm64/kernel/asm-offsets.c index 8d89cf8dae55..e3bcf77f1924 100644 --- a/arch/arm64/kernel/asm-offsets.c +++ b/arch/arm64/kernel/asm-offsets.c @@ -51,7 +51,7 @@ int main(void) DEFINE(S_X7, offsetof(struct pt_regs, regs[7])); DEFINE(S_LR, offsetof(struct pt_regs, regs[30])); DEFINE(S_SP, offsetof(struct pt_regs, sp)); -#ifdef CONFIG_COMPAT +#ifdef CONFIG_AARCH32_EL0 DEFINE(S_COMPAT_SP, offsetof(struct pt_regs, compat_sp)); #endif DEFINE(S_PSTATE, offsetof(struct pt_regs, pstate)); diff --git a/arch/arm64/kernel/efi-stub.c b/arch/arm64/kernel/efi-stub.c index 816120ece6bc..78dfbd34b6bf 100644 --- a/arch/arm64/kernel/efi-stub.c +++ b/arch/arm64/kernel/efi-stub.c @@ -25,10 +25,20 @@ efi_status_t __init handle_kernel_image(efi_system_table_t *sys_table_arg, unsigned long kernel_size, kernel_memsize = 0; unsigned long nr_pages; void *old_image_addr = (void *)*image_addr; + unsigned long preferred_offset; + + /* + * The preferred offset of the kernel Image is TEXT_OFFSET bytes beyond + * a 2 MB aligned base, which itself may be lower than dram_base, as + * long as the resulting offset equals or exceeds it. + */ + preferred_offset = round_down(dram_base, SZ_2M) + TEXT_OFFSET; + if (preferred_offset < dram_base) + preferred_offset += SZ_2M; /* Relocate the image, if required. */ kernel_size = _edata - _text; - if (*image_addr != (dram_base + TEXT_OFFSET)) { + if (*image_addr != preferred_offset) { kernel_memsize = kernel_size + (_end - _edata); /* @@ -42,7 +52,7 @@ efi_status_t __init handle_kernel_image(efi_system_table_t *sys_table_arg, * Mustang), we can still place the kernel at the address * 'dram_base + TEXT_OFFSET'. */ - *image_addr = *reserve_addr = dram_base + TEXT_OFFSET; + *image_addr = *reserve_addr = preferred_offset; nr_pages = round_up(kernel_memsize, EFI_ALLOC_ALIGN) / EFI_PAGE_SIZE; status = efi_call_early(allocate_pages, EFI_ALLOCATE_ADDRESS, diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S index 4306c937b1ff..bcd921a0fbc6 100644 --- a/arch/arm64/kernel/entry.S +++ b/arch/arm64/kernel/entry.S @@ -212,7 +212,7 @@ ENTRY(vectors) ventry el0_fiq_invalid // FIQ 64-bit EL0 ventry el0_error_invalid // Error 64-bit EL0 -#ifdef CONFIG_COMPAT +#ifdef CONFIG_AARCH32_EL0 ventry el0_sync_compat // Synchronous 32-bit EL0 ventry el0_irq_compat // IRQ 32-bit EL0 ventry el0_fiq_invalid_compat // FIQ 32-bit EL0 @@ -252,7 +252,7 @@ el0_error_invalid: inv_entry 0, BAD_ERROR ENDPROC(el0_error_invalid) -#ifdef CONFIG_COMPAT +#ifdef CONFIG_AARCH32_EL0 el0_fiq_invalid_compat: inv_entry 0, BAD_FIQ, 32 ENDPROC(el0_fiq_invalid_compat) @@ -414,7 +414,7 @@ el0_sync: b.ge el0_dbg b el0_inv -#ifdef CONFIG_COMPAT +#ifdef CONFIG_AARCH32_EL0 .align 6 el0_sync_compat: kernel_entry 0, 32 @@ -664,9 +664,13 @@ ENDPROC(ret_from_fork) */ .align 6 el0_svc: - adrp stbl, sys_call_table // load syscall table pointer uxtw scno, w8 // syscall number in w8 mov sc_nr, #__NR_syscalls +#ifdef CONFIG_ARM64_ILP32 + ldr x16, [tsk, #TI_FLAGS] + tbnz x16, #TIF_32BIT_AARCH64, el0_ilp32_svc // We are using ILP32 +#endif + adrp stbl, sys_call_table // load syscall table pointer el0_svc_naked: // compat entry point stp x0, scno, [sp, #S_ORIG_X0] // save the original x0 and syscall number enable_dbg_and_irq @@ -686,6 +690,12 @@ ni_sys: b ret_fast_syscall ENDPROC(el0_svc) +#ifdef CONFIG_ARM64_ILP32 +el0_ilp32_svc: + adrp stbl, sys_call_ilp32_table // load syscall table pointer + b el0_svc_naked +#endif + /* * This is the really slow path. We're going to be doing context * switches, and waiting for our parent to respond. diff --git a/arch/arm64/kernel/entry32-common.S b/arch/arm64/kernel/entry32-common.S new file mode 100644 index 000000000000..2ad59126f8be --- /dev/null +++ b/arch/arm64/kernel/entry32-common.S @@ -0,0 +1,37 @@ +#include <linux/linkage.h> +#include <linux/const.h> + +#include <asm/assembler.h> +#include <asm/asm-offsets.h> +#include <asm/errno.h> +#include <asm/page.h> + +ENTRY(compat_sys_statfs64_wrapper) + mov w3, #84 + cmp w1, #88 + csel w1, w3, w1, eq + b compat_sys_statfs64 +ENDPROC(compat_sys_statfs64_wrapper) + +ENTRY(compat_sys_fstatfs64_wrapper) + mov w3, #84 + cmp w1, #88 + csel w1, w3, w1, eq + b compat_sys_fstatfs64 +ENDPROC(compat_sys_fstatfs64_wrapper) + +/* + * Note: off_4k (w5) is always in units of 4K. If we can't do the + * requested offset because it is not page-aligned, we return -EINVAL. + */ +ENTRY(compat_sys_mmap2_wrapper) +#if PAGE_SHIFT > 12 + tst w5, #~PAGE_MASK >> 12 + b.ne 1f + lsr w5, w5, #PAGE_SHIFT - 12 +#endif + b sys_mmap_pgoff +1: mov x0, #-EINVAL + ret +ENDPROC(compat_sys_mmap2_wrapper) + diff --git a/arch/arm64/kernel/entry32.S b/arch/arm64/kernel/entry32.S index f332d5d1f6b4..802612948fe4 100644 --- a/arch/arm64/kernel/entry32.S +++ b/arch/arm64/kernel/entry32.S @@ -40,35 +40,6 @@ ENTRY(compat_sys_rt_sigreturn_wrapper) b compat_sys_rt_sigreturn ENDPROC(compat_sys_rt_sigreturn_wrapper) -ENTRY(compat_sys_statfs64_wrapper) - mov w3, #84 - cmp w1, #88 - csel w1, w3, w1, eq - b compat_sys_statfs64 -ENDPROC(compat_sys_statfs64_wrapper) - -ENTRY(compat_sys_fstatfs64_wrapper) - mov w3, #84 - cmp w1, #88 - csel w1, w3, w1, eq - b compat_sys_fstatfs64 -ENDPROC(compat_sys_fstatfs64_wrapper) - -/* - * Note: off_4k (w5) is always in units of 4K. If we can't do the - * requested offset because it is not page-aligned, we return -EINVAL. - */ -ENTRY(compat_sys_mmap2_wrapper) -#if PAGE_SHIFT > 12 - tst w5, #~PAGE_MASK >> 12 - b.ne 1f - lsr w5, w5, #PAGE_SHIFT - 12 -#endif - b sys_mmap_pgoff -1: mov x0, #-EINVAL - ret -ENDPROC(compat_sys_mmap2_wrapper) - /* * Wrappers for AArch32 syscalls that either take 64-bit parameters * in registers or that take 32-bit parameters which require sign diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S index 90d09eddd5b2..d11d0b2c87d9 100644 --- a/arch/arm64/kernel/head.S +++ b/arch/arm64/kernel/head.S @@ -519,7 +519,7 @@ CPU_LE( movk x0, #0x30d0, lsl #16 ) // Clear EE and E0E on LE systems mov x0, #0x33ff msr cptr_el2, x0 // Disable copro. traps to EL2 -#ifdef CONFIG_COMPAT +#ifdef CONFIG_AARCH32_EL0 msr hstr_el2, xzr // Disable CP15 traps to EL2 #endif diff --git a/arch/arm64/kernel/hw_breakpoint.c b/arch/arm64/kernel/hw_breakpoint.c index bba85c8f8037..854fc8244b1e 100644 --- a/arch/arm64/kernel/hw_breakpoint.c +++ b/arch/arm64/kernel/hw_breakpoint.c @@ -28,6 +28,7 @@ #include <linux/ptrace.h> #include <linux/smp.h> +#include <asm/compat.h> #include <asm/current.h> #include <asm/debug-monitors.h> #include <asm/hw_breakpoint.h> @@ -420,7 +421,7 @@ static int arch_build_bp_info(struct perf_event *bp) * Watchpoints can be of length 1, 2, 4 or 8 bytes. */ if (info->ctrl.type == ARM_BREAKPOINT_EXECUTE) { - if (is_compat_task()) { + if (is_a32_compat_task()) { if (info->ctrl.len != ARM_BREAKPOINT_LEN_2 && info->ctrl.len != ARM_BREAKPOINT_LEN_4) return -EINVAL; @@ -477,7 +478,7 @@ int arch_validate_hwbkpt_settings(struct perf_event *bp) * AArch32 tasks expect some simple alignment fixups, so emulate * that here. */ - if (is_compat_task()) { + if (is_a32_compat_task()) { if (info->ctrl.len == ARM_BREAKPOINT_LEN_8) alignment_mask = 0x7; else @@ -664,7 +665,7 @@ static int watchpoint_handler(unsigned long addr, unsigned int esr, info = counter_arch_bp(wp); /* AArch32 watchpoints are either 4 or 8 bytes aligned. */ - if (is_compat_task()) { + if (is_a32_compat_task()) { if (info->ctrl.len == ARM_BREAKPOINT_LEN_8) alignment_mask = 0x7; else diff --git a/arch/arm64/kernel/perf_regs.c b/arch/arm64/kernel/perf_regs.c index 3f62b35fb6f1..a79058fe1bb5 100644 --- a/arch/arm64/kernel/perf_regs.c +++ b/arch/arm64/kernel/perf_regs.c @@ -45,7 +45,7 @@ int perf_reg_validate(u64 mask) u64 perf_reg_abi(struct task_struct *task) { - if (is_compat_thread(task_thread_info(task))) + if (is_a32_compat_thread(task_thread_info(task))) return PERF_SAMPLE_REGS_ABI_32; else return PERF_SAMPLE_REGS_ABI_64; diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c index b147e5cb4b25..94125001fd62 100644 --- a/arch/arm64/kernel/process.c +++ b/arch/arm64/kernel/process.c @@ -325,7 +325,7 @@ int copy_thread(unsigned long clone_flags, unsigned long stack_start, asm("mrs %0, tpidr_el0" : "=r" (*task_user_tls(p))); if (stack_start) { - if (is_compat_thread(task_thread_info(p))) + if (is_a32_compat_thread(task_thread_info(p))) childregs->compat_sp = stack_start; /* 16-byte aligned stack mandatory on AArch64 */ else if (stack_start & 15) @@ -362,7 +362,7 @@ static void tls_thread_switch(struct task_struct *next) *task_user_tls(current) = tpidr; tpidr = *task_user_tls(next); - tpidrro = is_compat_thread(task_thread_info(next)) ? + tpidrro = is_a32_compat_thread(task_thread_info(next)) ? next->thread.tp_value : 0; asm( diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c index 1971f491bb90..22d0d5ebf976 100644 --- a/arch/arm64/kernel/ptrace.c +++ b/arch/arm64/kernel/ptrace.c @@ -76,10 +76,10 @@ static void ptrace_hbptriggered(struct perf_event *bp, .si_addr = (void __user *)(bkpt->trigger), }; -#ifdef CONFIG_COMPAT +#ifdef CONFIG_AARCH32_EL0 int i; - if (!is_compat_task()) + if (!is_a32_compat_task()) goto send_sig; for (i = 0; i < ARM_MAX_BRP; ++i) { @@ -651,7 +651,7 @@ static const struct user_regset_view user_aarch64_view = { .regsets = aarch64_regsets, .n = ARRAY_SIZE(aarch64_regsets) }; -#ifdef CONFIG_COMPAT +#ifdef CONFIG_AARCH32_EL0 #include <linux/compat.h> enum compat_regset { @@ -853,9 +853,9 @@ static int compat_tls_set(struct task_struct *target, static const struct user_regset aarch32_regsets[] = { [REGSET_COMPAT_GPR] = { .core_note_type = NT_PRSTATUS, - .n = COMPAT_ELF_NGREG, - .size = sizeof(compat_elf_greg_t), - .align = sizeof(compat_elf_greg_t), + .n = COMPAT_A32_ELF_NGREG, + .size = sizeof(compat_a32_elf_greg_t), + .align = sizeof(compat_a32_elf_greg_t), .get = compat_gpr_get, .set = compat_gpr_set }, @@ -877,7 +877,7 @@ static const struct user_regset_view user_aarch32_view = { static const struct user_regset aarch32_ptrace_regsets[] = { [REGSET_GPR] = { .core_note_type = NT_PRSTATUS, - .n = COMPAT_ELF_NGREG, + .n = COMPAT_A32_ELF_NGREG, .size = sizeof(compat_elf_greg_t), .align = sizeof(compat_elf_greg_t), .get = compat_gpr_get, @@ -946,7 +946,7 @@ static int compat_ptrace_read_user(struct task_struct *tsk, compat_ulong_t off, tmp = tsk->mm->start_data; else if (off == COMPAT_PT_TEXT_END_ADDR) tmp = tsk->mm->end_code; - else if (off < sizeof(compat_elf_gregset_t)) + else if (off < sizeof(compat_a32_elf_gregset_t)) return copy_regset_to_user(tsk, &user_aarch32_view, REGSET_COMPAT_GPR, off, sizeof(compat_ulong_t), ret); @@ -967,7 +967,7 @@ static int compat_ptrace_write_user(struct task_struct *tsk, compat_ulong_t off, if (off & 3 || off >= COMPAT_USER_SZ) return -EIO; - if (off >= sizeof(compat_elf_gregset_t)) + if (off >= sizeof(compat_a32_elf_gregset_t)) return 0; set_fs(KERNEL_DS); @@ -1109,7 +1109,7 @@ static int compat_ptrace_sethbpregs(struct task_struct *tsk, compat_long_t num, } #endif /* CONFIG_HAVE_HW_BREAKPOINT */ -long compat_arch_ptrace(struct task_struct *child, compat_long_t request, +long compat_a32_arch_ptrace(struct task_struct *child, compat_long_t request, compat_ulong_t caddr, compat_ulong_t cdata) { unsigned long addr = caddr; @@ -1130,7 +1130,7 @@ long compat_arch_ptrace(struct task_struct *child, compat_long_t request, ret = copy_regset_to_user(child, &user_aarch32_view, REGSET_COMPAT_GPR, - 0, sizeof(compat_elf_gregset_t), + 0, sizeof(compat_a32_elf_gregset_t), datap); break; @@ -1138,7 +1138,7 @@ long compat_arch_ptrace(struct task_struct *child, compat_long_t request, ret = copy_regset_from_user(child, &user_aarch32_view, REGSET_COMPAT_GPR, - 0, sizeof(compat_elf_gregset_t), + 0, sizeof(compat_a32_elf_gregset_t), datap); break; @@ -1186,20 +1186,33 @@ long compat_arch_ptrace(struct task_struct *child, compat_long_t request, return ret; } -#endif /* CONFIG_COMPAT */ +#else /* !CONFIG_AARCH32_EL0 */ +#define compat_a32_arch_ptrace(child, request, caddr, cdata) (-1) +#endif /* !CONFIG_AARCH32_EL0 */ + +#ifdef CONFIG_COMPAT +long compat_arch_ptrace(struct task_struct *child, compat_long_t request, + compat_ulong_t caddr, compat_ulong_t cdata) +{ + if (is_a32_compat_task()) + return compat_a32_arch_ptrace(child, request, caddr, cdata); + return compat_ptrace_request(child, request, caddr, cdata); +} +#endif + const struct user_regset_view *task_user_regset_view(struct task_struct *task) { -#ifdef CONFIG_COMPAT +#ifdef CONFIG_AARCH32_EL0 /* * Core dumping of 32-bit tasks or compat ptrace requests must use the * user_aarch32_view compatible with arm32. Native ptrace requests on * 32-bit children use an extended user_aarch32_ptrace_view to allow * access to the TLS register. */ - if (is_compat_task()) + if (is_a32_compat_task()) return &user_aarch32_view; - else if (is_compat_thread(task_thread_info(task))) + else if (is_a32_compat_thread(task_thread_info(task))) return &user_aarch32_ptrace_view; #endif return &user_aarch64_view; @@ -1226,7 +1239,7 @@ static void tracehook_report_syscall(struct pt_regs *regs, * A scratch register (ip(r12) on AArch32, x7 on AArch64) is * used to denote syscall entry/exit: */ - regno = (is_compat_task() ? 12 : 7); + regno = (is_a32_compat_task() ? 12 : 7); saved_reg = regs->regs[regno]; regs->regs[regno] = dir; diff --git a/arch/arm64/kernel/signal.c b/arch/arm64/kernel/signal.c index e18c48cb6db1..f12f8a0914e7 100644 --- a/arch/arm64/kernel/signal.c +++ b/arch/arm64/kernel/signal.c @@ -29,6 +29,7 @@ #include <asm/debug-monitors.h> #include <asm/elf.h> #include <asm/cacheflush.h> +#include <asm/compat.h> #include <asm/ucontext.h> #include <asm/unistd.h> #include <asm/fpsimd.h> @@ -276,7 +277,7 @@ static int setup_rt_frame(int usig, struct ksignal *ksig, sigset_t *set, static void setup_restart_syscall(struct pt_regs *regs) { - if (is_compat_task()) + if (is_a32_compat_task()) compat_setup_restart_syscall(regs); else regs->regs[8] = __NR_restart_syscall; @@ -295,7 +296,7 @@ static void handle_signal(struct ksignal *ksig, struct pt_regs *regs) /* * Set up the stack frame */ - if (is_compat_task()) { + if (is_a32_compat_task()) { if (ksig->ka.sa.sa_flags & SA_SIGINFO) ret = compat_setup_rt_frame(usig, ksig, oldset, regs); else @@ -414,3 +415,19 @@ asmlinkage void do_notify_resume(struct pt_regs *regs, fpsimd_restore_current_state(); } + +/* + * Some functions are needed for compat ptrace but we don't define + * them if we don't have AARCH32 support compiled in + */ +#if defined CONFIG_COMPAT && !defined CONFIG_AARCH32_EL0 +int copy_siginfo_to_user32(compat_siginfo_t __user *to, const siginfo_t *from) +{ + return -EFAULT; +} + +int copy_siginfo_from_user32(siginfo_t *to, compat_siginfo_t __user *from) +{ + return -EFAULT; +} +#endif diff --git a/arch/arm64/kernel/stacktrace.c b/arch/arm64/kernel/stacktrace.c index 407991bf79f5..ccb6078ed9f2 100644 --- a/arch/arm64/kernel/stacktrace.c +++ b/arch/arm64/kernel/stacktrace.c @@ -48,11 +48,7 @@ int notrace unwind_frame(struct stackframe *frame) frame->sp = fp + 0x10; frame->fp = *(unsigned long *)(fp); - /* - * -4 here because we care about the PC at time of bl, - * not where the return will go. - */ - frame->pc = *(unsigned long *)(fp + 8) - 4; + frame->pc = *(unsigned long *)(fp + 8); return 0; } diff --git a/arch/arm64/kernel/suspend.c b/arch/arm64/kernel/suspend.c index 8297d502217e..44ca4143b013 100644 --- a/arch/arm64/kernel/suspend.c +++ b/arch/arm64/kernel/suspend.c @@ -80,17 +80,21 @@ int cpu_suspend(unsigned long arg, int (*fn)(unsigned long)) if (ret == 0) { /* * We are resuming from reset with TTBR0_EL1 set to the - * idmap to enable the MMU; restore the active_mm mappings in - * TTBR0_EL1 unless the active_mm == &init_mm, in which case - * the thread entered cpu_suspend with TTBR0_EL1 set to - * reserved TTBR0 page tables and should be restored as such. + * idmap to enable the MMU; set the TTBR0 to the reserved + * page tables to prevent speculative TLB allocations, flush + * the local tlb and set the default tcr_el1.t0sz so that + * the TTBR0 address space set-up is properly restored. + * If the current active_mm != &init_mm we entered cpu_suspend + * with mappings in TTBR0 that must be restored, so we switch + * them back to complete the address space configuration + * restoration before returning. */ - if (mm == &init_mm) - cpu_set_reserved_ttbr0(); - else - cpu_switch_mm(mm->pgd, mm); - + cpu_set_reserved_ttbr0(); flush_tlb_all(); + cpu_set_default_tcr_t0sz(); + + if (mm != &init_mm) + cpu_switch_mm(mm->pgd, mm); /* * Restore per-cpu offset before any kernel diff --git a/arch/arm64/kernel/sys_ilp32.c b/arch/arm64/kernel/sys_ilp32.c new file mode 100644 index 000000000000..889f1d39cab8 --- /dev/null +++ b/arch/arm64/kernel/sys_ilp32.c @@ -0,0 +1,278 @@ +/* + * AArch64- ILP32 specific system calls implementation + * + * Copyright (C) 2015 Cavium Inc. + * Author: Andrew Pinski <apinski@cavium.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 as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +#include <linux/compiler.h> +#include <linux/errno.h> +#include <linux/fs.h> +#include <linux/mm.h> +#include <linux/msg.h> +#include <linux/export.h> +#include <linux/sched.h> +#include <linux/slab.h> +#include <linux/syscalls.h> +#include <linux/compat.h> + +/* + * Wrappers to pass the pt_regs argument. + */ +asmlinkage long sys_rt_sigreturn_wrapper(void); +#define sys_rt_sigreturn sys_rt_sigreturn_wrapper +#define sys_rt_sigsuspend compat_sys_rt_sigsuspend +#define sys_rt_sigaction compat_sys_rt_sigaction +#define sys_rt_sigprocmask compat_sys_rt_sigprocmask +#define sys_rt_sigpending compat_sys_rt_sigpending +#define sys_rt_sigtimedwait compat_sys_rt_sigtimedwait +#define sys_rt_sigqueueinfo compat_sys_rt_sigqueueinfo +#define sys_rt_sigpending compat_sys_rt_sigpending + +/* Using Compat syscalls where necessary */ +#define sys_ioctl compat_sys_ioctl +/* iovec */ +#define sys_readv compat_sys_readv +#define sys_writev compat_sys_writev +#define sys_preadv compat_sys_preadv64 +#define sys_pwritev compat_sys_pwritev64 +#define sys_vmsplice compat_sys_vmsplice +/* robust_list_head */ +#define sys_set_robust_list compat_sys_set_robust_list +#define sys_get_robust_list compat_sys_get_robust_list + +/* kexec_segment */ +#define sys_kexec_load compat_sys_kexec_load + +/* Ptrace has some structures which are different between ILP32 and LP64 */ +#define sys_ptrace compat_sys_ptrace + +/* struct msghdr */ +#define sys_msgctl compat_sys_msgctl +#define sys_recvfrom compat_sys_recvfrom +#define sys_recvmmsg compat_sys_recvmmsg +#define sys_sendmmsg compat_sys_sendmmsg +#define sys_sendmsg compat_sys_sendmsg +#define sys_recvmsg compat_sys_recvmsg +#define sys_msgsnd compat_sys_msgsnd +#define sys_msgrcv compat_sys_msgrcv + +#define sys_setsockopt compat_sys_setsockopt +#define sys_getsockopt compat_sys_getsockopt + +/* Array of pointers */ +#define sys_execve compat_sys_execve +#define sys_move_pages compat_sys_move_pages + +/* iovec */ +#define sys_process_vm_readv compat_sys_process_vm_readv +#define sys_process_vm_writev compat_sys_process_vm_writev + +/* Pointer in struct */ +#define sys_mount compat_sys_mount + +/* NUMA */ +/* unsigned long bitmaps */ +#define sys_get_mempolicy compat_sys_get_mempolicy +#define sys_set_mempolicy compat_sys_set_mempolicy +#define sys_mbind compat_sys_mbind +/* array of pointers */ +/* unsigned long bitmaps */ +#define sys_migrate_pages compat_sys_migrate_pages + +/* Scheduler */ +/* unsigned long bitmaps */ +#define sys_sched_setaffinity compat_sys_sched_setaffinity +#define sys_sched_getaffinity compat_sys_sched_getaffinity + +/* iov usage */ +#define sys_keyctl compat_sys_keyctl + +/* aio */ +/* Pointer to Pointer */ +#define sys_io_setup compat_sys_io_setup +/* Array of pointers */ +#define sys_io_submit compat_sys_io_submit + +#define sys_nanosleep compat_sys_nanosleep + +#define sys_lseek sys_llseek + +#define sys_setitimer compat_sys_setitimer +#define sys_getitimer compat_sys_getitimer + +#define sys_gettimeofday compat_sys_gettimeofday +#define sys_settimeofday compat_sys_settimeofday +#define sys_adjtimex compat_sys_adjtimex + +#define sys_clock_gettime compat_sys_clock_gettime +#define sys_clock_settime compat_sys_clock_settime + +#define sys_timerfd_gettime compat_sys_timerfd_gettime +#define sys_timerfd_settime compat_sys_timerfd_settime +#define sys_utimensat compat_sys_utimensat + +#define sys_getrlimit compat_sys_getrlimit +#define sys_setrlimit compat_sys_setrlimit +#define sys_getrusage compat_sys_getrusage + +#define sys_futex compat_sys_futex +#define sys_get_robust_list compat_sys_get_robust_list +#define sys_set_robust_list compat_sys_set_robust_list + +#define sys_pselect6 compat_sys_pselect6 +#define sys_ppoll compat_sys_ppoll + +asmlinkage long compat_sys_mmap2_wrapper(void); +#define sys_mmap compat_sys_mmap2_wrapper + +asmlinkage long compat_sys_fstatfs64_wrapper(void); +#define sys_fstatfs compat_sys_fstatfs64_wrapper +asmlinkage long compat_sys_statfs64_wrapper(void); +#define sys_statfs compat_sys_statfs64_wrapper + +/* We need to make sure the pointer gets copied correctly. */ +asmlinkage long ilp32_sys_mq_notify(mqd_t mqdes, const struct sigevent __user *u_notification) +{ + struct sigevent __user *p = NULL; + if (u_notification) { + struct sigevent n; + p = compat_alloc_user_space(sizeof(*p)); + if (copy_from_user(&n, u_notification, sizeof(*p))) + return -EFAULT; + if (n.sigev_notify == SIGEV_THREAD) + n.sigev_value.sival_ptr = compat_ptr((uintptr_t)n.sigev_value.sival_ptr); + if (copy_to_user(p, &n, sizeof(*p))) + return -EFAULT; + } + return sys_mq_notify(mqdes, p); +} + +/* sigevent contains sigval_t which is now 64bit always + but need special handling due to padding for SIGEV_THREAD. */ +#define sys_mq_notify ilp32_sys_mq_notify + +/* sigaltstack needs some special handling as the + padding for stack_t might not be non-zero. */ +long ilp32_sys_sigaltstack(const stack_t __user *uss_ptr, + stack_t __user *uoss_ptr) +{ + stack_t uss, uoss; + int ret; + mm_segment_t seg; + + if (uss_ptr) { + if (!access_ok(VERIFY_READ, uss_ptr, sizeof(*uss_ptr))) + return -EFAULT; + if (__get_user(uss.ss_sp, &uss_ptr->ss_sp) | + __get_user(uss.ss_flags, &uss_ptr->ss_flags) | + __get_user(uss.ss_size, &uss_ptr->ss_size)) + return -EFAULT; + /* Zero extend the sp address and the size. */ + uss.ss_sp = (void *)(uintptr_t)(unsigned int)(uintptr_t)uss.ss_sp; + uss.ss_size = (size_t)(unsigned int)uss.ss_size; + } + seg = get_fs(); + set_fs(KERNEL_DS); + /* Note we need to use uoss as we have changed the segment to the + kernel one so passing an user one around is wrong. */ + ret = sys_sigaltstack((stack_t __force __user *) (uss_ptr ? &uss : NULL), + (stack_t __force __user *) &uoss); + set_fs(seg); + if (ret >= 0 && uoss_ptr) { + if (!access_ok(VERIFY_WRITE, uoss_ptr, sizeof(stack_t)) || + __put_user(uoss.ss_sp, &uoss_ptr->ss_sp) || + __put_user(uoss.ss_flags, &uoss_ptr->ss_flags) || + __put_user(uoss.ss_size, &uoss_ptr->ss_size)) + ret = -EFAULT; + } + return ret; +} + +/* sigaltstack needs some special handling as the padding + for stack_t might not be non-zero. */ +#define sys_sigaltstack ilp32_sys_sigaltstack + +/* fs */ + +#define sys_fcntl compat_sys_fcntl + +static long __cp_new_stat64(struct kstat *stat, struct __stat64 __user *statbuf) +{ + struct __stat64 tmp; + + memset(&tmp, 0, sizeof(tmp)); + tmp.st_dev = huge_encode_dev(stat->dev); + tmp.st_rdev = huge_encode_dev(stat->rdev); + + tmp.st_ino = stat->ino; + if (sizeof(tmp.st_ino) < sizeof(stat->ino) && tmp.st_ino != stat->ino) + return -EOVERFLOW; + tmp.st_mode = stat->mode; + tmp.st_nlink = stat->nlink; + tmp.st_uid = from_kuid_munged(current_user_ns(), stat->uid); + tmp.st_gid = from_kgid_munged(current_user_ns(), stat->gid); + tmp.st_atime = stat->atime.tv_sec; + tmp.st_atime_nsec = stat->atime.tv_nsec; + tmp.st_mtime = stat->mtime.tv_sec; + tmp.st_mtime_nsec = stat->mtime.tv_nsec; + tmp.st_ctime = stat->ctime.tv_sec; + tmp.st_ctime_nsec = stat->ctime.tv_nsec; + tmp.st_size = stat->size; + tmp.st_blocks = stat->blocks; + tmp.st_blksize = stat->blksize; + return copy_to_user(statbuf,&tmp,sizeof(tmp)) ? -EFAULT : 0; +} + +long ilp32_sys_fstat64(int fd, struct __stat64 __user * statbuf) +{ + struct kstat stat; + int error = vfs_fstat(fd, &stat); + + if (!error) + error = __cp_new_stat64(&stat, statbuf); + + return error; +} + +#define sys_newfstat ilp32_sys_fstat64 + +long ilp32_sys_fstatat64(int dfd, const char __user * filename, + struct __stat64 __user * statbuf, int flag) +{ + struct kstat stat; + int error; + + error = vfs_fstatat(dfd, filename, &stat, flag); + if (error) + return error; + return __cp_new_stat64(&stat, statbuf); +} + +#define sys_newfstatat ilp32_sys_fstatat64 + +#include <asm/syscall.h> + +#undef __SYSCALL +#define __SYSCALL(nr, sym) [nr] = sym, + +/* + * The sys_call_ilp32_table array must be 4K aligned to be accessible from + * kernel/entry.S. + */ +void *sys_call_ilp32_table[__NR_syscalls] __aligned(4096) = { + [0 ... __NR_syscalls - 1] = sys_ni_syscall, +#include <asm/unistd.h> +}; diff --git a/arch/arm64/kernel/traps.c b/arch/arm64/kernel/traps.c index f93aae5e4307..bc973d078534 100644 --- a/arch/arm64/kernel/traps.c +++ b/arch/arm64/kernel/traps.c @@ -363,9 +363,9 @@ long compat_arm_syscall(struct pt_regs *regs); asmlinkage long do_ni_syscall(struct pt_regs *regs) { -#ifdef CONFIG_COMPAT +#ifdef CONFIG_AARCH32_EL0 long ret; - if (is_compat_task()) { + if (is_a32_compat_task()) { ret = compat_arm_syscall(regs); if (ret != -ENOSYS) return ret; diff --git a/arch/arm64/kernel/vdso.c b/arch/arm64/kernel/vdso.c index 97bc68f4c689..b239b9b2c7bb 100644 --- a/arch/arm64/kernel/vdso.c +++ b/arch/arm64/kernel/vdso.c @@ -49,7 +49,7 @@ static union { } vdso_data_store __page_aligned_data; struct vdso_data *vdso_data = &vdso_data_store.data; -#ifdef CONFIG_COMPAT +#ifdef CONFIG_AARCH32_EL0 /* * Create and map the vectors page for AArch32 tasks. */ @@ -107,7 +107,15 @@ int aarch32_setup_vectors_page(struct linux_binprm *bprm, int uses_interp) return PTR_ERR_OR_ZERO(ret); } -#endif /* CONFIG_COMPAT */ +#else +int aarch32_setup_vectors_page(struct linux_binprm *bprm, int uses_interp) +{ + (void) bprm; + (void) uses_interp; + + return -EINVAL; +} +#endif /* CONFIG_AARCH32_EL0 */ static struct vm_special_mapping vdso_spec[2]; diff --git a/arch/ia64/include/asm/unistd.h b/arch/ia64/include/asm/unistd.h index 99c96a5e6016..db73390568c8 100644 --- a/arch/ia64/include/asm/unistd.h +++ b/arch/ia64/include/asm/unistd.h @@ -11,7 +11,7 @@ -#define NR_syscalls 321 /* length of syscall table */ +#define NR_syscalls 322 /* length of syscall table */ /* * The following defines stop scripts/checksyscalls.sh from complaining about diff --git a/arch/ia64/include/uapi/asm/unistd.h b/arch/ia64/include/uapi/asm/unistd.h index 98e94e19a5a0..9038726e7d26 100644 --- a/arch/ia64/include/uapi/asm/unistd.h +++ b/arch/ia64/include/uapi/asm/unistd.h @@ -334,5 +334,6 @@ #define __NR_execveat 1342 #define __NR_userfaultfd 1343 #define __NR_membarrier 1344 +#define __NR_kcmp 1345 #endif /* _UAPI_ASM_IA64_UNISTD_H */ diff --git a/arch/ia64/kernel/entry.S b/arch/ia64/kernel/entry.S index 37cc7a65cd3e..dcd97f84d065 100644 --- a/arch/ia64/kernel/entry.S +++ b/arch/ia64/kernel/entry.S @@ -1770,5 +1770,6 @@ sys_call_table: data8 sys_execveat data8 sys_userfaultfd data8 sys_membarrier + data8 sys_kcmp // 1345 .org sys_call_table + 8*NR_syscalls // guard against failures to increase NR_syscalls diff --git a/arch/powerpc/include/asm/cache.h b/arch/powerpc/include/asm/cache.h index 0dc42c5082b7..5f8229e24fe6 100644 --- a/arch/powerpc/include/asm/cache.h +++ b/arch/powerpc/include/asm/cache.h @@ -3,7 +3,6 @@ #ifdef __KERNEL__ -#include <asm/reg.h> /* bytes per L1 cache line */ #if defined(CONFIG_8xx) || defined(CONFIG_403GCX) @@ -40,12 +39,6 @@ struct ppc64_caches { }; extern struct ppc64_caches ppc64_caches; - -static inline void logmpp(u64 x) -{ - asm volatile(PPC_LOGMPP(R1) : : "r" (x)); -} - #endif /* __powerpc64__ && ! __ASSEMBLY__ */ #if defined(__ASSEMBLY__) diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h index 827a38d7a9db..887c259556df 100644 --- a/arch/powerpc/include/asm/kvm_host.h +++ b/arch/powerpc/include/asm/kvm_host.h @@ -297,8 +297,6 @@ struct kvmppc_vcore { u32 arch_compat; ulong pcr; ulong dpdes; /* doorbell state (POWER8) */ - void *mpp_buffer; /* Micro Partition Prefetch buffer */ - bool mpp_buffer_is_valid; ulong conferring_threads; }; diff --git a/arch/powerpc/include/asm/ppc-opcode.h b/arch/powerpc/include/asm/ppc-opcode.h index 790f5d1d9a46..7ab04fc59e24 100644 --- a/arch/powerpc/include/asm/ppc-opcode.h +++ b/arch/powerpc/include/asm/ppc-opcode.h @@ -141,7 +141,6 @@ #define PPC_INST_ISEL 0x7c00001e #define PPC_INST_ISEL_MASK 0xfc00003e #define PPC_INST_LDARX 0x7c0000a8 -#define PPC_INST_LOGMPP 0x7c0007e4 #define PPC_INST_LSWI 0x7c0004aa #define PPC_INST_LSWX 0x7c00042a #define PPC_INST_LWARX 0x7c000028 @@ -285,20 +284,6 @@ #define __PPC_EH(eh) 0 #endif -/* POWER8 Micro Partition Prefetch (MPP) parameters */ -/* Address mask is common for LOGMPP instruction and MPPR SPR */ -#define PPC_MPPE_ADDRESS_MASK 0xffffffffc000ULL - -/* Bits 60 and 61 of MPP SPR should be set to one of the following */ -/* Aborting the fetch is indeed setting 00 in the table size bits */ -#define PPC_MPPR_FETCH_ABORT (0x0ULL << 60) -#define PPC_MPPR_FETCH_WHOLE_TABLE (0x2ULL << 60) - -/* Bits 54 and 55 of register for LOGMPP instruction should be set to: */ -#define PPC_LOGMPP_LOG_L2 (0x02ULL << 54) -#define PPC_LOGMPP_LOG_L2L3 (0x01ULL << 54) -#define PPC_LOGMPP_LOG_ABORT (0x03ULL << 54) - /* Deal with instructions that older assemblers aren't aware of */ #define PPC_DCBAL(a, b) stringify_in_c(.long PPC_INST_DCBAL | \ __PPC_RA(a) | __PPC_RB(b)) @@ -307,8 +292,6 @@ #define PPC_LDARX(t, a, b, eh) stringify_in_c(.long PPC_INST_LDARX | \ ___PPC_RT(t) | ___PPC_RA(a) | \ ___PPC_RB(b) | __PPC_EH(eh)) -#define PPC_LOGMPP(b) stringify_in_c(.long PPC_INST_LOGMPP | \ - __PPC_RB(b)) #define PPC_LWARX(t, a, b, eh) stringify_in_c(.long PPC_INST_LWARX | \ ___PPC_RT(t) | ___PPC_RA(a) | \ ___PPC_RB(b) | __PPC_EH(eh)) diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h index aa1cc5f015ee..a908ada8e0a5 100644 --- a/arch/powerpc/include/asm/reg.h +++ b/arch/powerpc/include/asm/reg.h @@ -226,7 +226,6 @@ #define CTRL_TE 0x00c00000 /* thread enable */ #define CTRL_RUNLATCH 0x1 #define SPRN_DAWR 0xB4 -#define SPRN_MPPR 0xB8 /* Micro Partition Prefetch Register */ #define SPRN_RPR 0xBA /* Relative Priority Register */ #define SPRN_CIABR 0xBB #define CIABR_PRIV 0x3 diff --git a/arch/powerpc/kernel/dma.c b/arch/powerpc/kernel/dma.c index 59503ed98e5f..3f1472a78f39 100644 --- a/arch/powerpc/kernel/dma.c +++ b/arch/powerpc/kernel/dma.c @@ -303,7 +303,7 @@ int dma_set_coherent_mask(struct device *dev, u64 mask) dev->coherent_dma_mask = mask; return 0; } -EXPORT_SYMBOL_GPL(dma_set_coherent_mask); +EXPORT_SYMBOL(dma_set_coherent_mask); #define PREALLOC_DMA_DEBUG_ENTRIES (1 << 16) diff --git a/arch/powerpc/kernel/rtas.c b/arch/powerpc/kernel/rtas.c index 84bf934cf748..5a753fae8265 100644 --- a/arch/powerpc/kernel/rtas.c +++ b/arch/powerpc/kernel/rtas.c @@ -1043,6 +1043,9 @@ asmlinkage int ppc_rtas(struct rtas_args __user *uargs) if (!capable(CAP_SYS_ADMIN)) return -EPERM; + if (!rtas.entry) + return -EINVAL; + if (copy_from_user(&args, uargs, 3 * sizeof(u32)) != 0) return -EFAULT; diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c index 228049786888..9c26c5a96ea2 100644 --- a/arch/powerpc/kvm/book3s_hv.c +++ b/arch/powerpc/kvm/book3s_hv.c @@ -36,7 +36,6 @@ #include <asm/reg.h> #include <asm/cputable.h> -#include <asm/cache.h> #include <asm/cacheflush.h> #include <asm/tlbflush.h> #include <asm/uaccess.h> @@ -75,12 +74,6 @@ static DECLARE_BITMAP(default_enabled_hcalls, MAX_HCALL_OPCODE/4 + 1); -#if defined(CONFIG_PPC_64K_PAGES) -#define MPP_BUFFER_ORDER 0 -#elif defined(CONFIG_PPC_4K_PAGES) -#define MPP_BUFFER_ORDER 3 -#endif - static int dynamic_mt_modes = 6; module_param(dynamic_mt_modes, int, S_IRUGO | S_IWUSR); MODULE_PARM_DESC(dynamic_mt_modes, "Set of allowed dynamic micro-threading modes: 0 (= none), 2, 4, or 6 (= 2 or 4)"); @@ -1455,13 +1448,6 @@ static struct kvmppc_vcore *kvmppc_vcore_create(struct kvm *kvm, int core) vcore->kvm = kvm; INIT_LIST_HEAD(&vcore->preempt_list); - vcore->mpp_buffer_is_valid = false; - - if (cpu_has_feature(CPU_FTR_ARCH_207S)) - vcore->mpp_buffer = (void *)__get_free_pages( - GFP_KERNEL|__GFP_ZERO, - MPP_BUFFER_ORDER); - return vcore; } @@ -1894,33 +1880,6 @@ static int on_primary_thread(void) return 1; } -static void kvmppc_start_saving_l2_cache(struct kvmppc_vcore *vc) -{ - phys_addr_t phy_addr, mpp_addr; - - phy_addr = (phys_addr_t)virt_to_phys(vc->mpp_buffer); - mpp_addr = phy_addr & PPC_MPPE_ADDRESS_MASK; - - mtspr(SPRN_MPPR, mpp_addr | PPC_MPPR_FETCH_ABORT); - logmpp(mpp_addr | PPC_LOGMPP_LOG_L2); - - vc->mpp_buffer_is_valid = true; -} - -static void kvmppc_start_restoring_l2_cache(const struct kvmppc_vcore *vc) -{ - phys_addr_t phy_addr, mpp_addr; - - phy_addr = virt_to_phys(vc->mpp_buffer); - mpp_addr = phy_addr & PPC_MPPE_ADDRESS_MASK; - - /* We must abort any in-progress save operations to ensure - * the table is valid so that prefetch engine knows when to - * stop prefetching. */ - logmpp(mpp_addr | PPC_LOGMPP_LOG_ABORT); - mtspr(SPRN_MPPR, mpp_addr | PPC_MPPR_FETCH_WHOLE_TABLE); -} - /* * A list of virtual cores for each physical CPU. * These are vcores that could run but their runner VCPU tasks are @@ -2471,14 +2430,8 @@ static noinline void kvmppc_run_core(struct kvmppc_vcore *vc) srcu_idx = srcu_read_lock(&vc->kvm->srcu); - if (vc->mpp_buffer_is_valid) - kvmppc_start_restoring_l2_cache(vc); - __kvmppc_vcore_entry(); - if (vc->mpp_buffer) - kvmppc_start_saving_l2_cache(vc); - srcu_read_unlock(&vc->kvm->srcu, srcu_idx); spin_lock(&vc->lock); @@ -3073,14 +3026,8 @@ static void kvmppc_free_vcores(struct kvm *kvm) { long int i; - for (i = 0; i < KVM_MAX_VCORES; ++i) { - if (kvm->arch.vcores[i] && kvm->arch.vcores[i]->mpp_buffer) { - struct kvmppc_vcore *vc = kvm->arch.vcores[i]; - free_pages((unsigned long)vc->mpp_buffer, - MPP_BUFFER_ORDER); - } + for (i = 0; i < KVM_MAX_VCORES; ++i) kfree(kvm->arch.vcores[i]); - } kvm->arch.online_vcores = 0; } diff --git a/arch/powerpc/platforms/powernv/smp.c b/arch/powerpc/platforms/powernv/smp.c index 8f70ba681a78..ca264833ee64 100644 --- a/arch/powerpc/platforms/powernv/smp.c +++ b/arch/powerpc/platforms/powernv/smp.c @@ -171,7 +171,26 @@ static void pnv_smp_cpu_kill_self(void) * so clear LPCR:PECE1. We keep PECE2 enabled. */ mtspr(SPRN_LPCR, mfspr(SPRN_LPCR) & ~(u64)LPCR_PECE1); + + /* + * Hard-disable interrupts, and then clear irq_happened flags + * that we can safely ignore while off-line, since they + * are for things for which we do no processing when off-line + * (or in the case of HMI, all the processing we need to do + * is done in lower-level real-mode code). + */ + hard_irq_disable(); + local_paca->irq_happened &= ~(PACA_IRQ_DEC | PACA_IRQ_HMI); + while (!generic_check_cpu_restart(cpu)) { + /* + * Clear IPI flag, since we don't handle IPIs while + * offline, except for those when changing micro-threading + * mode, which are handled explicitly below, and those + * for coming online, which are handled via + * generic_check_cpu_restart() calls. + */ + kvmppc_set_host_ipi(cpu, 0); ppc64_runlatch_off(); @@ -196,20 +215,20 @@ static void pnv_smp_cpu_kill_self(void) * having finished executing in a KVM guest, then srr1 * contains 0. */ - if ((srr1 & wmask) == SRR1_WAKEEE) { + if (((srr1 & wmask) == SRR1_WAKEEE) || + (local_paca->irq_happened & PACA_IRQ_EE)) { icp_native_flush_interrupt(); - local_paca->irq_happened &= PACA_IRQ_HARD_DIS; - smp_mb(); } else if ((srr1 & wmask) == SRR1_WAKEHDBELL) { unsigned long msg = PPC_DBELL_TYPE(PPC_DBELL_SERVER); asm volatile(PPC_MSGCLR(%0) : : "r" (msg)); - kvmppc_set_host_ipi(cpu, 0); } + local_paca->irq_happened &= ~(PACA_IRQ_EE | PACA_IRQ_DBELL); + smp_mb(); if (cpu_core_split_required()) continue; - if (!generic_check_cpu_restart(cpu)) + if (srr1 && !generic_check_cpu_restart(cpu)) DBG("CPU%d Unexpected exit while offline !\n", cpu); } mtspr(SPRN_LPCR, mfspr(SPRN_LPCR) | LPCR_PECE1); diff --git a/arch/um/Makefile b/arch/um/Makefile index 098ab3333e7c..e3abe6f3156d 100644 --- a/arch/um/Makefile +++ b/arch/um/Makefile @@ -70,8 +70,8 @@ KBUILD_AFLAGS += $(ARCH_INCLUDE) USER_CFLAGS = $(patsubst $(KERNEL_DEFINES),,$(patsubst -I%,,$(KBUILD_CFLAGS))) \ $(ARCH_INCLUDE) $(MODE_INCLUDE) $(filter -I%,$(CFLAGS)) \ - -D_FILE_OFFSET_BITS=64 -idirafter include \ - -D__KERNEL__ -D__UM_HOST__ + -D_FILE_OFFSET_BITS=64 -idirafter $(srctree)/include \ + -idirafter $(obj)/include -D__KERNEL__ -D__UM_HOST__ #This will adjust *FLAGS accordingly to the platform. include $(ARCH_DIR)/Makefile-os-$(OS) diff --git a/arch/um/kernel/trap.c b/arch/um/kernel/trap.c index d8a9fce6ee2e..98783dd0fa2e 100644 --- a/arch/um/kernel/trap.c +++ b/arch/um/kernel/trap.c @@ -220,7 +220,7 @@ unsigned long segv(struct faultinfo fi, unsigned long ip, int is_user, show_regs(container_of(regs, struct pt_regs, regs)); panic("Segfault with no mm"); } - else if (!is_user && address < TASK_SIZE) { + else if (!is_user && address > PAGE_SIZE && address < TASK_SIZE) { show_regs(container_of(regs, struct pt_regs, regs)); panic("Kernel tried to access user memory at addr 0x%lx, ip 0x%lx", address, ip); diff --git a/arch/um/os-Linux/helper.c b/arch/um/os-Linux/helper.c index e3ee4a51ef63..3f02d4232812 100644 --- a/arch/um/os-Linux/helper.c +++ b/arch/um/os-Linux/helper.c @@ -96,7 +96,7 @@ int run_helper(void (*pre_exec)(void *), void *pre_data, char **argv) "ret = %d\n", -n); ret = n; } - CATCH_EINTR(waitpid(pid, NULL, __WCLONE)); + CATCH_EINTR(waitpid(pid, NULL, __WALL)); } out_free2: @@ -129,7 +129,7 @@ int run_helper_thread(int (*proc)(void *), void *arg, unsigned int flags, return err; } if (stack_out == NULL) { - CATCH_EINTR(pid = waitpid(pid, &status, __WCLONE)); + CATCH_EINTR(pid = waitpid(pid, &status, __WALL)); if (pid < 0) { err = -errno; printk(UM_KERN_ERR "run_helper_thread - wait failed, " @@ -148,7 +148,7 @@ int run_helper_thread(int (*proc)(void *), void *arg, unsigned int flags, int helper_wait(int pid) { int ret, status; - int wflags = __WCLONE; + int wflags = __WALL; CATCH_EINTR(ret = waitpid(pid, &status, wflags)); if (ret < 0) { diff --git a/arch/x86/boot/compressed/eboot.c b/arch/x86/boot/compressed/eboot.c index ee1b6d346b98..db51c1f27446 100644 --- a/arch/x86/boot/compressed/eboot.c +++ b/arch/x86/boot/compressed/eboot.c @@ -667,6 +667,7 @@ setup_gop32(struct screen_info *si, efi_guid_t *proto, bool conout_found = false; void *dummy = NULL; u32 h = handles[i]; + u32 current_fb_base; status = efi_call_early(handle_protocol, h, proto, (void **)&gop32); @@ -678,7 +679,7 @@ setup_gop32(struct screen_info *si, efi_guid_t *proto, if (status == EFI_SUCCESS) conout_found = true; - status = __gop_query32(gop32, &info, &size, &fb_base); + status = __gop_query32(gop32, &info, &size, ¤t_fb_base); if (status == EFI_SUCCESS && (!first_gop || conout_found)) { /* * Systems that use the UEFI Console Splitter may @@ -692,6 +693,7 @@ setup_gop32(struct screen_info *si, efi_guid_t *proto, pixel_format = info->pixel_format; pixel_info = info->pixel_information; pixels_per_scan_line = info->pixels_per_scan_line; + fb_base = current_fb_base; /* * Once we've found a GOP supporting ConOut, @@ -770,6 +772,7 @@ setup_gop64(struct screen_info *si, efi_guid_t *proto, bool conout_found = false; void *dummy = NULL; u64 h = handles[i]; + u32 current_fb_base; status = efi_call_early(handle_protocol, h, proto, (void **)&gop64); @@ -781,7 +784,7 @@ setup_gop64(struct screen_info *si, efi_guid_t *proto, if (status == EFI_SUCCESS) conout_found = true; - status = __gop_query64(gop64, &info, &size, &fb_base); + status = __gop_query64(gop64, &info, &size, ¤t_fb_base); if (status == EFI_SUCCESS && (!first_gop || conout_found)) { /* * Systems that use the UEFI Console Splitter may @@ -795,6 +798,7 @@ setup_gop64(struct screen_info *si, efi_guid_t *proto, pixel_format = info->pixel_format; pixel_info = info->pixel_information; pixels_per_scan_line = info->pixels_per_scan_line; + fb_base = current_fb_base; /* * Once we've found a GOP supporting ConOut, diff --git a/arch/x86/include/asm/string_64.h b/arch/x86/include/asm/string_64.h index e4661196994e..ff8b9a17dc4b 100644 --- a/arch/x86/include/asm/string_64.h +++ b/arch/x86/include/asm/string_64.h @@ -27,12 +27,11 @@ static __always_inline void *__inline_memcpy(void *to, const void *from, size_t function. */ #define __HAVE_ARCH_MEMCPY 1 +extern void *memcpy(void *to, const void *from, size_t len); extern void *__memcpy(void *to, const void *from, size_t len); #ifndef CONFIG_KMEMCHECK -#if (__GNUC__ == 4 && __GNUC_MINOR__ >= 3) || __GNUC__ > 4 -extern void *memcpy(void *to, const void *from, size_t len); -#else +#if (__GNUC__ == 4 && __GNUC_MINOR__ < 3) || __GNUC__ < 4 #define memcpy(dst, src, len) \ ({ \ size_t __len = (len); \ diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c index 5c60bb162622..4f2821527014 100644 --- a/arch/x86/kernel/apic/io_apic.c +++ b/arch/x86/kernel/apic/io_apic.c @@ -2547,7 +2547,9 @@ void __init setup_ioapic_dest(void) mask = apic->target_cpus(); chip = irq_data_get_irq_chip(idata); - chip->irq_set_affinity(idata, mask, false); + /* Might be lapic_chip for irq 0 */ + if (chip->irq_set_affinity) + chip->irq_set_affinity(idata, mask, false); } } #endif @@ -2907,6 +2909,7 @@ int mp_irqdomain_alloc(struct irq_domain *domain, unsigned int virq, struct irq_data *irq_data; struct mp_chip_data *data; struct irq_alloc_info *info = arg; + unsigned long flags; if (!info || nr_irqs > 1) return -EINVAL; @@ -2939,11 +2942,14 @@ int mp_irqdomain_alloc(struct irq_domain *domain, unsigned int virq, cfg = irqd_cfg(irq_data); add_pin_to_irq_node(data, ioapic_alloc_attr_node(info), ioapic, pin); + + local_irq_save(flags); if (info->ioapic_entry) mp_setup_entry(cfg, data, info->ioapic_entry); mp_register_handler(virq, data->trigger); if (virq < nr_legacy_irqs()) legacy_pic->mask(virq); + local_irq_restore(flags); apic_printk(APIC_VERBOSE, KERN_DEBUG "IOAPIC[%d]: Set routing entry (%d-%d -> 0x%x -> IRQ %d Mode:%i Active:%i Dest:%d)\n", diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c index 1b55de1267cf..cd99433b8ba1 100644 --- a/arch/x86/kernel/pci-dma.c +++ b/arch/x86/kernel/pci-dma.c @@ -131,11 +131,12 @@ void dma_generic_free_coherent(struct device *dev, size_t size, void *vaddr, bool arch_dma_alloc_attrs(struct device **dev, gfp_t *gfp) { + if (!*dev) + *dev = &x86_dma_fallback_dev; + *gfp &= ~(__GFP_DMA | __GFP_HIGHMEM | __GFP_DMA32); *gfp = dma_alloc_coherent_gfp_flags(*dev, *gfp); - if (!*dev) - *dev = &x86_dma_fallback_dev; if (!is_device_dma_capable(*dev)) return false; return true; diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index fe51befb5bf9..57eca132962f 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -71,6 +71,9 @@ static DEFINE_PER_CPU(unsigned char, is_idle); int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src) { memcpy(dst, src, arch_task_struct_size); +#ifdef CONFIG_VM86 + dst->thread.vm86 = NULL; +#endif return fpu__copy(&dst->thread.fpu, &src->thread.fpu); } @@ -537,14 +540,14 @@ unsigned long get_wchan(struct task_struct *p) if (sp < bottom || sp > top) return 0; - fp = READ_ONCE(*(unsigned long *)sp); + fp = READ_ONCE_NOCHECK(*(unsigned long *)sp); do { if (fp < bottom || fp > top) return 0; - ip = READ_ONCE(*(unsigned long *)(fp + sizeof(unsigned long))); + ip = READ_ONCE_NOCHECK(*(unsigned long *)(fp + sizeof(unsigned long))); if (!in_sched_functions(ip)) return ip; - fp = READ_ONCE(*(unsigned long *)fp); + fp = READ_ONCE_NOCHECK(*(unsigned long *)fp); } while (count++ < 16 && p->state != TASK_RUNNING); return 0; } diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index fdb7f2a2d328..a3cccbfc5f77 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -1173,6 +1173,14 @@ void __init setup_arch(char **cmdline_p) clone_pgd_range(initial_page_table + KERNEL_PGD_BOUNDARY, swapper_pg_dir + KERNEL_PGD_BOUNDARY, KERNEL_PGD_PTRS); + + /* + * sync back low identity map too. It is used for example + * in the 32-bit EFI stub. + */ + clone_pgd_range(initial_page_table, + swapper_pg_dir + KERNEL_PGD_BOUNDARY, + KERNEL_PGD_PTRS); #endif tboot_probe(); diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index e0c198e5f920..892ee2e5ecbc 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -509,7 +509,7 @@ void __inquire_remote_apic(int apicid) */ #define UDELAY_10MS_DEFAULT 10000 -static unsigned int init_udelay = UDELAY_10MS_DEFAULT; +static unsigned int init_udelay = INT_MAX; static int __init cpu_init_udelay(char *str) { @@ -522,13 +522,16 @@ early_param("cpu_init_udelay", cpu_init_udelay); static void __init smp_quirk_init_udelay(void) { /* if cmdline changed it from default, leave it alone */ - if (init_udelay != UDELAY_10MS_DEFAULT) + if (init_udelay != INT_MAX) return; /* if modern processor, use no delay */ if (((boot_cpu_data.x86_vendor == X86_VENDOR_INTEL) && (boot_cpu_data.x86 == 6)) || ((boot_cpu_data.x86_vendor == X86_VENDOR_AMD) && (boot_cpu_data.x86 >= 0xF))) init_udelay = 0; + + /* else, use legacy delay */ + init_udelay = UDELAY_10MS_DEFAULT; } /* @@ -657,7 +660,9 @@ wakeup_secondary_cpu_via_init(int phys_apicid, unsigned long start_eip) /* * Give the other CPU some time to accept the IPI. */ - if (init_udelay) + if (init_udelay == 0) + udelay(10); + else udelay(300); pr_debug("Startup point 1\n"); @@ -668,7 +673,9 @@ wakeup_secondary_cpu_via_init(int phys_apicid, unsigned long start_eip) /* * Give the other CPU some time to accept the IPI. */ - if (init_udelay) + if (init_udelay == 0) + udelay(10); + else udelay(200); if (maxlvt > 3) /* Due to the Pentium erratum 3AP. */ diff --git a/arch/x86/um/ldt.c b/arch/x86/um/ldt.c index 9701a4fd7bf2..836a1eb5df43 100644 --- a/arch/x86/um/ldt.c +++ b/arch/x86/um/ldt.c @@ -12,7 +12,10 @@ #include <skas.h> #include <sysdep/tls.h> -extern int modify_ldt(int func, void *ptr, unsigned long bytecount); +static inline int modify_ldt (int func, void *ptr, unsigned long bytecount) +{ + return syscall(__NR_modify_ldt, func, ptr, bytecount); +} static long write_ldt_entry(struct mm_id *mm_idp, int func, struct user_desc *desc, void **addr, int done) diff --git a/block/blk-core.c b/block/blk-core.c index 2eb722d48773..18e92a6645e2 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -576,7 +576,7 @@ void blk_cleanup_queue(struct request_queue *q) q->queue_lock = &q->__queue_lock; spin_unlock_irq(lock); - bdi_destroy(&q->backing_dev_info); + bdi_unregister(&q->backing_dev_info); /* @q is and will stay empty, shutdown and put */ blk_put_queue(q); diff --git a/block/blk-lib.c b/block/blk-lib.c index bd40292e5009..9ebf65379556 100644 --- a/block/blk-lib.c +++ b/block/blk-lib.c @@ -26,13 +26,6 @@ static void bio_batch_end_io(struct bio *bio) bio_put(bio); } -/* - * Ensure that max discard sectors doesn't overflow bi_size and hopefully - * it is of the proper granularity as long as the granularity is a power - * of two. - */ -#define MAX_BIO_SECTORS ((1U << 31) >> 9) - /** * blkdev_issue_discard - queue a discard * @bdev: blockdev to issue discard for @@ -50,6 +43,8 @@ int blkdev_issue_discard(struct block_device *bdev, sector_t sector, DECLARE_COMPLETION_ONSTACK(wait); struct request_queue *q = bdev_get_queue(bdev); int type = REQ_WRITE | REQ_DISCARD; + unsigned int granularity; + int alignment; struct bio_batch bb; struct bio *bio; int ret = 0; @@ -61,6 +56,10 @@ int blkdev_issue_discard(struct block_device *bdev, sector_t sector, if (!blk_queue_discard(q)) return -EOPNOTSUPP; + /* Zero-sector (unknown) and one-sector granularities are the same. */ + granularity = max(q->limits.discard_granularity >> 9, 1U); + alignment = (bdev_discard_alignment(bdev) >> 9) % granularity; + if (flags & BLKDEV_DISCARD_SECURE) { if (!blk_queue_secdiscard(q)) return -EOPNOTSUPP; @@ -74,7 +73,7 @@ int blkdev_issue_discard(struct block_device *bdev, sector_t sector, blk_start_plug(&plug); while (nr_sects) { unsigned int req_sects; - sector_t end_sect; + sector_t end_sect, tmp; bio = bio_alloc(gfp_mask, 1); if (!bio) { @@ -82,8 +81,22 @@ int blkdev_issue_discard(struct block_device *bdev, sector_t sector, break; } - req_sects = min_t(sector_t, nr_sects, MAX_BIO_SECTORS); + /* Make sure bi_size doesn't overflow */ + req_sects = min_t(sector_t, nr_sects, UINT_MAX >> 9); + + /* + * If splitting a request, and the next starting sector would be + * misaligned, stop the discard at the previous aligned sector. + */ end_sect = sector + req_sects; + tmp = end_sect; + if (req_sects < nr_sects && + sector_div(tmp, granularity) != alignment) { + end_sect = end_sect - alignment; + sector_div(end_sect, granularity); + end_sect = end_sect * granularity + alignment; + req_sects = end_sect - sector; + } bio->bi_iter.bi_sector = sector; bio->bi_end_io = bio_batch_end_io; diff --git a/block/blk-mq-tag.c b/block/blk-mq-tag.c index ed96474d75cb..ec2d11915142 100644 --- a/block/blk-mq-tag.c +++ b/block/blk-mq-tag.c @@ -641,6 +641,7 @@ void blk_mq_free_tags(struct blk_mq_tags *tags) { bt_free(&tags->bitmap_tags); bt_free(&tags->breserved_tags); + free_cpumask_var(tags->cpumask); kfree(tags); } diff --git a/block/blk-mq.c b/block/blk-mq.c index 7785ae96267a..85f014327342 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -2296,10 +2296,8 @@ void blk_mq_free_tag_set(struct blk_mq_tag_set *set) int i; for (i = 0; i < set->nr_hw_queues; i++) { - if (set->tags[i]) { + if (set->tags[i]) blk_mq_free_rq_map(set, set->tags[i], i); - free_cpumask_var(set->tags[i]->cpumask); - } } kfree(set->tags); diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c index 3e44a9da2a13..07b42f5ad797 100644 --- a/block/blk-sysfs.c +++ b/block/blk-sysfs.c @@ -540,6 +540,7 @@ static void blk_release_queue(struct kobject *kobj) struct request_queue *q = container_of(kobj, struct request_queue, kobj); + bdi_exit(&q->backing_dev_info); blkcg_exit_queue(q); if (q->elevator) { diff --git a/crypto/ablkcipher.c b/crypto/ablkcipher.c index b788f169cc98..b4ffc5be1a93 100644 --- a/crypto/ablkcipher.c +++ b/crypto/ablkcipher.c @@ -706,7 +706,7 @@ struct crypto_ablkcipher *crypto_alloc_ablkcipher(const char *alg_name, err: if (err != -EAGAIN) break; - if (signal_pending(current)) { + if (fatal_signal_pending(current)) { err = -EINTR; break; } diff --git a/crypto/algapi.c b/crypto/algapi.c index d130b41dbaea..59bf491fe3d8 100644 --- a/crypto/algapi.c +++ b/crypto/algapi.c @@ -345,7 +345,7 @@ static void crypto_wait_for_test(struct crypto_larval *larval) crypto_alg_tested(larval->alg.cra_driver_name, 0); } - err = wait_for_completion_interruptible(&larval->completion); + err = wait_for_completion_killable(&larval->completion); WARN_ON(err); out: diff --git a/crypto/api.c b/crypto/api.c index afe4610afc4b..bbc147cb5dec 100644 --- a/crypto/api.c +++ b/crypto/api.c @@ -172,7 +172,7 @@ static struct crypto_alg *crypto_larval_wait(struct crypto_alg *alg) struct crypto_larval *larval = (void *)alg; long timeout; - timeout = wait_for_completion_interruptible_timeout( + timeout = wait_for_completion_killable_timeout( &larval->completion, 60 * HZ); alg = larval->adult; @@ -445,7 +445,7 @@ struct crypto_tfm *crypto_alloc_base(const char *alg_name, u32 type, u32 mask) err: if (err != -EAGAIN) break; - if (signal_pending(current)) { + if (fatal_signal_pending(current)) { err = -EINTR; break; } @@ -562,7 +562,7 @@ void *crypto_alloc_tfm(const char *alg_name, err: if (err != -EAGAIN) break; - if (signal_pending(current)) { + if (fatal_signal_pending(current)) { err = -EINTR; break; } diff --git a/crypto/crypto_user.c b/crypto/crypto_user.c index d94d99ffe8b9..237f3795cfaa 100644 --- a/crypto/crypto_user.c +++ b/crypto/crypto_user.c @@ -375,7 +375,7 @@ static struct crypto_alg *crypto_user_skcipher_alg(const char *name, u32 type, err = PTR_ERR(alg); if (err != -EAGAIN) break; - if (signal_pending(current)) { + if (fatal_signal_pending(current)) { err = -EINTR; break; } diff --git a/drivers/base/dma-contiguous.c b/drivers/base/dma-contiguous.c index 950fff9ce453..a12ff9863d7e 100644 --- a/drivers/base/dma-contiguous.c +++ b/drivers/base/dma-contiguous.c @@ -187,7 +187,7 @@ int __init dma_contiguous_reserve_area(phys_addr_t size, phys_addr_t base, * global one. Requires architecture specific dev_get_cma_area() helper * function. */ -struct page *dma_alloc_from_contiguous(struct device *dev, int count, +struct page *dma_alloc_from_contiguous(struct device *dev, size_t count, unsigned int align) { if (align > CONFIG_CMA_ALIGNMENT) diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c index 293495a75d3d..1b87623381e2 100644 --- a/drivers/block/nbd.c +++ b/drivers/block/nbd.c @@ -60,6 +60,7 @@ struct nbd_device { bool disconnect; /* a disconnect has been requested by user */ struct timer_list timeout_timer; + spinlock_t tasks_lock; struct task_struct *task_recv; struct task_struct *task_send; @@ -140,21 +141,23 @@ static void sock_shutdown(struct nbd_device *nbd) static void nbd_xmit_timeout(unsigned long arg) { struct nbd_device *nbd = (struct nbd_device *)arg; - struct task_struct *task; + unsigned long flags; if (list_empty(&nbd->queue_head)) return; nbd->disconnect = true; - task = READ_ONCE(nbd->task_recv); - if (task) - force_sig(SIGKILL, task); + spin_lock_irqsave(&nbd->tasks_lock, flags); + + if (nbd->task_recv) + force_sig(SIGKILL, nbd->task_recv); - task = READ_ONCE(nbd->task_send); - if (task) + if (nbd->task_send) force_sig(SIGKILL, nbd->task_send); + spin_unlock_irqrestore(&nbd->tasks_lock, flags); + dev_err(nbd_to_dev(nbd), "Connection timed out, killed receiver and sender, shutting down connection\n"); } @@ -403,17 +406,24 @@ static int nbd_thread_recv(struct nbd_device *nbd) { struct request *req; int ret; + unsigned long flags; BUG_ON(nbd->magic != NBD_MAGIC); sk_set_memalloc(nbd->sock->sk); + spin_lock_irqsave(&nbd->tasks_lock, flags); nbd->task_recv = current; + spin_unlock_irqrestore(&nbd->tasks_lock, flags); ret = device_create_file(disk_to_dev(nbd->disk), &pid_attr); if (ret) { dev_err(disk_to_dev(nbd->disk), "device_create_file failed!\n"); + + spin_lock_irqsave(&nbd->tasks_lock, flags); nbd->task_recv = NULL; + spin_unlock_irqrestore(&nbd->tasks_lock, flags); + return ret; } @@ -429,7 +439,9 @@ static int nbd_thread_recv(struct nbd_device *nbd) device_remove_file(disk_to_dev(nbd->disk), &pid_attr); + spin_lock_irqsave(&nbd->tasks_lock, flags); nbd->task_recv = NULL; + spin_unlock_irqrestore(&nbd->tasks_lock, flags); if (signal_pending(current)) { siginfo_t info; @@ -534,8 +546,11 @@ static int nbd_thread_send(void *data) { struct nbd_device *nbd = data; struct request *req; + unsigned long flags; + spin_lock_irqsave(&nbd->tasks_lock, flags); nbd->task_send = current; + spin_unlock_irqrestore(&nbd->tasks_lock, flags); set_user_nice(current, MIN_NICE); while (!kthread_should_stop() || !list_empty(&nbd->waiting_queue)) { @@ -572,7 +587,15 @@ static int nbd_thread_send(void *data) nbd_handle_req(nbd, req); } + spin_lock_irqsave(&nbd->tasks_lock, flags); nbd->task_send = NULL; + spin_unlock_irqrestore(&nbd->tasks_lock, flags); + + /* Clear maybe pending signals */ + if (signal_pending(current)) { + siginfo_t info; + dequeue_signal_lock(current, ¤t->blocked, &info); + } return 0; } @@ -1052,6 +1075,7 @@ static int __init nbd_init(void) nbd_dev[i].magic = NBD_MAGIC; INIT_LIST_HEAD(&nbd_dev[i].waiting_queue); spin_lock_init(&nbd_dev[i].queue_lock); + spin_lock_init(&nbd_dev[i].tasks_lock); INIT_LIST_HEAD(&nbd_dev[i].queue_head); mutex_init(&nbd_dev[i].tx_lock); init_timer(&nbd_dev[i].timeout_timer); diff --git a/drivers/block/nvme-core.c b/drivers/block/nvme-core.c index 6f04771f1019..ccc0c1f93daa 100644 --- a/drivers/block/nvme-core.c +++ b/drivers/block/nvme-core.c @@ -603,27 +603,31 @@ static void req_completion(struct nvme_queue *nvmeq, void *ctx, struct nvme_iod *iod = ctx; struct request *req = iod_get_private(iod); struct nvme_cmd_info *cmd_rq = blk_mq_rq_to_pdu(req); - u16 status = le16_to_cpup(&cqe->status) >> 1; + bool requeue = false; + int error = 0; if (unlikely(status)) { if (!(status & NVME_SC_DNR || blk_noretry_request(req)) && (jiffies - req->start_time) < req->timeout) { unsigned long flags; + requeue = true; blk_mq_requeue_request(req); spin_lock_irqsave(req->q->queue_lock, flags); if (!blk_queue_stopped(req->q)) blk_mq_kick_requeue_list(req->q); spin_unlock_irqrestore(req->q->queue_lock, flags); - return; + goto release_iod; } if (req->cmd_type == REQ_TYPE_DRV_PRIV) { if (cmd_rq->ctx == CMD_CTX_CANCELLED) - status = -EINTR; + error = -EINTR; + else + error = status; } else { - status = nvme_error_status(status); + error = nvme_error_status(status); } } @@ -635,8 +639,9 @@ static void req_completion(struct nvme_queue *nvmeq, void *ctx, if (cmd_rq->aborted) dev_warn(nvmeq->dev->dev, "completing aborted command with status:%04x\n", - status); + error); +release_iod: if (iod->nents) { dma_unmap_sg(nvmeq->dev->dev, iod->sg, iod->nents, rq_data_dir(req) ? DMA_TO_DEVICE : DMA_FROM_DEVICE); @@ -649,7 +654,8 @@ static void req_completion(struct nvme_queue *nvmeq, void *ctx, } nvme_free_iod(nvmeq->dev, iod); - blk_mq_complete_request(req, status); + if (likely(!requeue)) + blk_mq_complete_request(req, error); } /* length is in bytes. gfp flags indicates whether we may sleep. */ @@ -1804,7 +1810,7 @@ static int nvme_submit_io(struct nvme_ns *ns, struct nvme_user_io __user *uio) length = (io.nblocks + 1) << ns->lba_shift; meta_len = (io.nblocks + 1) * ns->ms; - metadata = (void __user *)(unsigned long)io.metadata; + metadata = (void __user *)(uintptr_t)io.metadata; write = io.opcode & 1; if (ns->ext) { @@ -1844,7 +1850,7 @@ static int nvme_submit_io(struct nvme_ns *ns, struct nvme_user_io __user *uio) c.rw.metadata = cpu_to_le64(meta_dma); status = __nvme_submit_sync_cmd(ns->queue, &c, NULL, - (void __user *)io.addr, length, NULL, 0); + (void __user *)(uintptr_t)io.addr, length, NULL, 0); unmap: if (meta) { if (status == NVME_SC_SUCCESS && !write) { @@ -1886,7 +1892,7 @@ static int nvme_user_cmd(struct nvme_dev *dev, struct nvme_ns *ns, timeout = msecs_to_jiffies(cmd.timeout_ms); status = __nvme_submit_sync_cmd(ns ? ns->queue : dev->admin_q, &c, - NULL, (void __user *)cmd.addr, cmd.data_len, + NULL, (void __user *)(uintptr_t)cmd.addr, cmd.data_len, &cmd.result, timeout); if (status >= 0) { if (put_user(cmd.result, &ucmd->result)) diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c index f5e49b639818..128e7df5b807 100644 --- a/drivers/block/rbd.c +++ b/drivers/block/rbd.c @@ -96,6 +96,8 @@ static int atomic_dec_return_safe(atomic_t *v) #define RBD_MINORS_PER_MAJOR 256 #define RBD_SINGLE_MAJOR_PART_SHIFT 4 +#define RBD_MAX_PARENT_CHAIN_LEN 16 + #define RBD_SNAP_DEV_NAME_PREFIX "snap_" #define RBD_MAX_SNAP_NAME_LEN \ (NAME_MAX - (sizeof (RBD_SNAP_DEV_NAME_PREFIX) - 1)) @@ -426,7 +428,7 @@ static ssize_t rbd_add_single_major(struct bus_type *bus, const char *buf, size_t count); static ssize_t rbd_remove_single_major(struct bus_type *bus, const char *buf, size_t count); -static int rbd_dev_image_probe(struct rbd_device *rbd_dev, bool mapping); +static int rbd_dev_image_probe(struct rbd_device *rbd_dev, int depth); static void rbd_spec_put(struct rbd_spec *spec); static int rbd_dev_id_to_minor(int dev_id) @@ -3778,6 +3780,9 @@ static int rbd_init_disk(struct rbd_device *rbd_dev) blk_queue_max_discard_sectors(q, segment_size / SECTOR_SIZE); q->limits.discard_zeroes_data = 1; + if (!ceph_test_opt(rbd_dev->rbd_client->client, NOCRC)) + q->backing_dev_info.capabilities |= BDI_CAP_STABLE_WRITES; + disk->queue = q; q->queuedata = rbd_dev; @@ -5131,44 +5136,51 @@ out_err: return ret; } -static int rbd_dev_probe_parent(struct rbd_device *rbd_dev) +/* + * @depth is rbd_dev_image_probe() -> rbd_dev_probe_parent() -> + * rbd_dev_image_probe() recursion depth, which means it's also the + * length of the already discovered part of the parent chain. + */ +static int rbd_dev_probe_parent(struct rbd_device *rbd_dev, int depth) { struct rbd_device *parent = NULL; - struct rbd_spec *parent_spec; - struct rbd_client *rbdc; int ret; if (!rbd_dev->parent_spec) return 0; - /* - * We need to pass a reference to the client and the parent - * spec when creating the parent rbd_dev. Images related by - * parent/child relationships always share both. - */ - parent_spec = rbd_spec_get(rbd_dev->parent_spec); - rbdc = __rbd_get_client(rbd_dev->rbd_client); - ret = -ENOMEM; - parent = rbd_dev_create(rbdc, parent_spec, NULL); - if (!parent) + if (++depth > RBD_MAX_PARENT_CHAIN_LEN) { + pr_info("parent chain is too long (%d)\n", depth); + ret = -EINVAL; goto out_err; + } - ret = rbd_dev_image_probe(parent, false); + parent = rbd_dev_create(rbd_dev->rbd_client, rbd_dev->parent_spec, + NULL); + if (!parent) { + ret = -ENOMEM; + goto out_err; + } + + /* + * Images related by parent/child relationships always share + * rbd_client and spec/parent_spec, so bump their refcounts. + */ + __rbd_get_client(rbd_dev->rbd_client); + rbd_spec_get(rbd_dev->parent_spec); + + ret = rbd_dev_image_probe(parent, depth); if (ret < 0) goto out_err; + rbd_dev->parent = parent; atomic_set(&rbd_dev->parent_ref, 1); - return 0; + out_err: - if (parent) { - rbd_dev_unparent(rbd_dev); + rbd_dev_unparent(rbd_dev); + if (parent) rbd_dev_destroy(parent); - } else { - rbd_put_client(rbdc); - rbd_spec_put(parent_spec); - } - return ret; } @@ -5286,7 +5298,7 @@ static void rbd_dev_image_release(struct rbd_device *rbd_dev) * parent), initiate a watch on its header object before using that * object to get detailed information about the rbd image. */ -static int rbd_dev_image_probe(struct rbd_device *rbd_dev, bool mapping) +static int rbd_dev_image_probe(struct rbd_device *rbd_dev, int depth) { int ret; @@ -5304,7 +5316,7 @@ static int rbd_dev_image_probe(struct rbd_device *rbd_dev, bool mapping) if (ret) goto err_out_format; - if (mapping) { + if (!depth) { ret = rbd_dev_header_watch_sync(rbd_dev); if (ret) { if (ret == -ENOENT) @@ -5325,7 +5337,7 @@ static int rbd_dev_image_probe(struct rbd_device *rbd_dev, bool mapping) * Otherwise this is a parent image, identified by pool, image * and snap ids - need to fill in names for those ids. */ - if (mapping) + if (!depth) ret = rbd_spec_fill_snap_id(rbd_dev); else ret = rbd_spec_fill_names(rbd_dev); @@ -5347,12 +5359,12 @@ static int rbd_dev_image_probe(struct rbd_device *rbd_dev, bool mapping) * Need to warn users if this image is the one being * mapped and has a parent. */ - if (mapping && rbd_dev->parent_spec) + if (!depth && rbd_dev->parent_spec) rbd_warn(rbd_dev, "WARNING: kernel layering is EXPERIMENTAL!"); } - ret = rbd_dev_probe_parent(rbd_dev); + ret = rbd_dev_probe_parent(rbd_dev, depth); if (ret) goto err_out_probe; @@ -5363,7 +5375,7 @@ static int rbd_dev_image_probe(struct rbd_device *rbd_dev, bool mapping) err_out_probe: rbd_dev_unprobe(rbd_dev); err_out_watch: - if (mapping) + if (!depth) rbd_dev_header_unwatch_sync(rbd_dev); out_header_name: kfree(rbd_dev->header_name); @@ -5426,7 +5438,7 @@ static ssize_t do_rbd_add(struct bus_type *bus, spec = NULL; /* rbd_dev now owns this */ rbd_opts = NULL; /* rbd_dev now owns this */ - rc = rbd_dev_image_probe(rbd_dev, true); + rc = rbd_dev_image_probe(rbd_dev, 0); if (rc < 0) goto err_out_rbd_dev; diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c index 611170896b8c..a69c02dadec0 100644 --- a/drivers/block/xen-blkfront.c +++ b/drivers/block/xen-blkfront.c @@ -1956,7 +1956,8 @@ static void blkback_changed(struct xenbus_device *dev, break; /* Missed the backend's Closing state -- fallthrough */ case XenbusStateClosing: - blkfront_closing(info); + if (info) + blkfront_closing(info); break; } } diff --git a/drivers/bus/arm-ccn.c b/drivers/bus/arm-ccn.c index 7d9879e166cf..7082c7268845 100644 --- a/drivers/bus/arm-ccn.c +++ b/drivers/bus/arm-ccn.c @@ -1184,11 +1184,12 @@ static int arm_ccn_pmu_cpu_notifier(struct notifier_block *nb, if (!cpumask_test_and_clear_cpu(cpu, &dt->cpu)) break; target = cpumask_any_but(cpu_online_mask, cpu); - if (target < 0) + if (target >= nr_cpu_ids) break; perf_pmu_migrate_context(&dt->pmu, cpu, target); cpumask_set_cpu(target, &dt->cpu); - WARN_ON(irq_set_affinity(ccn->irq, &dt->cpu) != 0); + if (ccn->irq) + WARN_ON(irq_set_affinity(ccn->irq, &dt->cpu) != 0); default: break; } diff --git a/drivers/clk/clkdev.c b/drivers/clk/clkdev.c index c0eaf0973bd2..779b6ff0c7ad 100644 --- a/drivers/clk/clkdev.c +++ b/drivers/clk/clkdev.c @@ -333,7 +333,8 @@ int clk_add_alias(const char *alias, const char *alias_dev_name, if (IS_ERR(r)) return PTR_ERR(r); - l = clkdev_create(r, alias, "%s", alias_dev_name); + l = clkdev_create(r, alias, alias_dev_name ? "%s" : NULL, + alias_dev_name); clk_put(r); return l ? 0 : -ENODEV; diff --git a/drivers/clocksource/arm_global_timer.c b/drivers/clocksource/arm_global_timer.c index 29ea50ac366a..a2cb6fae9295 100644 --- a/drivers/clocksource/arm_global_timer.c +++ b/drivers/clocksource/arm_global_timer.c @@ -60,7 +60,7 @@ static struct clock_event_device __percpu *gt_evt; * different to the 32-bit upper value read previously, go back to step 2. * Otherwise the 64-bit timer counter value is correct. */ -static u64 gt_counter_read(void) +static u64 notrace _gt_counter_read(void) { u64 counter; u32 lower; @@ -79,6 +79,11 @@ static u64 gt_counter_read(void) return counter; } +static u64 gt_counter_read(void) +{ + return _gt_counter_read(); +} + /** * To ensure that updates to comparator value register do not set the * Interrupt Status Register proceed as follows: @@ -201,7 +206,7 @@ static struct clocksource gt_clocksource = { #ifdef CONFIG_CLKSRC_ARM_GLOBAL_TIMER_SCHED_CLOCK static u64 notrace gt_sched_clock_read(void) { - return gt_counter_read(); + return _gt_counter_read(); } #endif diff --git a/drivers/clocksource/fsl_ftm_timer.c b/drivers/clocksource/fsl_ftm_timer.c index ef434699c80a..10202f1fdfd7 100644 --- a/drivers/clocksource/fsl_ftm_timer.c +++ b/drivers/clocksource/fsl_ftm_timer.c @@ -118,7 +118,7 @@ static inline void ftm_reset_counter(void __iomem *base) ftm_writel(0x00, base + FTM_CNT); } -static u64 ftm_read_sched_clock(void) +static u64 notrace ftm_read_sched_clock(void) { return ftm_readl(priv->clksrc_base + FTM_CNT); } diff --git a/drivers/clocksource/samsung_pwm_timer.c b/drivers/clocksource/samsung_pwm_timer.c index bc90e13338cc..9502bc4c3f6d 100644 --- a/drivers/clocksource/samsung_pwm_timer.c +++ b/drivers/clocksource/samsung_pwm_timer.c @@ -307,7 +307,7 @@ static void samsung_clocksource_resume(struct clocksource *cs) samsung_time_start(pwm.source_id, true); } -static cycle_t samsung_clocksource_read(struct clocksource *c) +static cycle_t notrace samsung_clocksource_read(struct clocksource *c) { return ~readl_relaxed(pwm.source_reg); } diff --git a/drivers/clocksource/sh_mtu2.c b/drivers/clocksource/sh_mtu2.c index f1985da8113f..53aa7e92a7d7 100644 --- a/drivers/clocksource/sh_mtu2.c +++ b/drivers/clocksource/sh_mtu2.c @@ -280,7 +280,9 @@ static int sh_mtu2_clock_event_shutdown(struct clock_event_device *ced) { struct sh_mtu2_channel *ch = ced_to_sh_mtu2(ced); - sh_mtu2_disable(ch); + if (clockevent_state_periodic(ced)) + sh_mtu2_disable(ch); + return 0; } diff --git a/drivers/clocksource/time-pistachio.c b/drivers/clocksource/time-pistachio.c index 18d4266c2986..bba679900054 100644 --- a/drivers/clocksource/time-pistachio.c +++ b/drivers/clocksource/time-pistachio.c @@ -67,7 +67,8 @@ static inline void gpt_writel(void __iomem *base, u32 value, u32 offset, writel(value, base + 0x20 * gpt_id + offset); } -static cycle_t pistachio_clocksource_read_cycles(struct clocksource *cs) +static cycle_t notrace +pistachio_clocksource_read_cycles(struct clocksource *cs) { struct pistachio_clocksource *pcs = to_pistachio_clocksource(cs); u32 counter, overflw; diff --git a/drivers/clocksource/timer-digicolor.c b/drivers/clocksource/timer-digicolor.c index e73947f0f86d..a536eeb634d8 100644 --- a/drivers/clocksource/timer-digicolor.c +++ b/drivers/clocksource/timer-digicolor.c @@ -143,7 +143,7 @@ static irqreturn_t digicolor_timer_interrupt(int irq, void *dev_id) return IRQ_HANDLED; } -static u64 digicolor_timer_sched_read(void) +static u64 notrace digicolor_timer_sched_read(void) { return ~readl(dc_timer_dev.base + COUNT(TIMER_B)); } diff --git a/drivers/clocksource/timer-prima2.c b/drivers/clocksource/timer-prima2.c index 78de982cc640..2854c663e8b5 100644 --- a/drivers/clocksource/timer-prima2.c +++ b/drivers/clocksource/timer-prima2.c @@ -73,7 +73,7 @@ static irqreturn_t sirfsoc_timer_interrupt(int irq, void *dev_id) } /* read 64-bit timer counter */ -static cycle_t sirfsoc_timer_read(struct clocksource *cs) +static cycle_t notrace sirfsoc_timer_read(struct clocksource *cs) { u64 cycles; diff --git a/drivers/clocksource/vf_pit_timer.c b/drivers/clocksource/vf_pit_timer.c index f07ba9932171..a0e6c68536a1 100644 --- a/drivers/clocksource/vf_pit_timer.c +++ b/drivers/clocksource/vf_pit_timer.c @@ -52,7 +52,7 @@ static inline void pit_irq_acknowledge(void) __raw_writel(PITTFLG_TIF, clkevt_base + PITTFLG); } -static u64 pit_read_sched_clock(void) +static u64 notrace pit_read_sched_clock(void) { return ~__raw_readl(clksrc_base + PITCVAL); } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h index 6647fb26ef25..0d13e6368b96 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h @@ -1654,6 +1654,7 @@ struct amdgpu_pm { u8 fan_max_rpm; /* dpm */ bool dpm_enabled; + bool sysfs_initialized; struct amdgpu_dpm dpm; const struct firmware *fw; /* SMC firmware */ uint32_t fw_version; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c index dc29ed8145c2..6c9e0902a414 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c @@ -184,10 +184,6 @@ int amdgpu_crtc_page_flip(struct drm_crtc *crtc, goto cleanup; } - fence_get(work->excl); - for (i = 0; i < work->shared_count; ++i) - fence_get(work->shared[i]); - amdgpu_bo_get_tiling_flags(new_rbo, &tiling_flags); amdgpu_bo_unreserve(new_rbo); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c index efed11509f4a..22a8c7d3a3ab 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c @@ -294,10 +294,14 @@ static umode_t hwmon_attributes_visible(struct kobject *kobj, struct amdgpu_device *adev = dev_get_drvdata(dev); umode_t effective_mode = attr->mode; - /* Skip limit attributes if DPM is not enabled */ + /* Skip attributes if DPM is not enabled */ if (!adev->pm.dpm_enabled && (attr == &sensor_dev_attr_temp1_crit.dev_attr.attr || - attr == &sensor_dev_attr_temp1_crit_hyst.dev_attr.attr)) + attr == &sensor_dev_attr_temp1_crit_hyst.dev_attr.attr || + attr == &sensor_dev_attr_pwm1.dev_attr.attr || + attr == &sensor_dev_attr_pwm1_enable.dev_attr.attr || + attr == &sensor_dev_attr_pwm1_max.dev_attr.attr || + attr == &sensor_dev_attr_pwm1_min.dev_attr.attr)) return 0; /* Skip fan attributes if fan is not present */ @@ -691,6 +695,9 @@ int amdgpu_pm_sysfs_init(struct amdgpu_device *adev) { int ret; + if (adev->pm.sysfs_initialized) + return 0; + if (adev->pm.funcs->get_temperature == NULL) return 0; adev->pm.int_hwmon_dev = hwmon_device_register_with_groups(adev->dev, @@ -719,6 +726,8 @@ int amdgpu_pm_sysfs_init(struct amdgpu_device *adev) return ret; } + adev->pm.sysfs_initialized = true; + return 0; } diff --git a/drivers/gpu/drm/amd/amdgpu/kv_dpm.c b/drivers/gpu/drm/amd/amdgpu/kv_dpm.c index 9745ed3a9aef..7e9154c7f1db 100644 --- a/drivers/gpu/drm/amd/amdgpu/kv_dpm.c +++ b/drivers/gpu/drm/amd/amdgpu/kv_dpm.c @@ -2997,6 +2997,9 @@ static int kv_dpm_late_init(void *handle) struct amdgpu_device *adev = (struct amdgpu_device *)handle; int ret; + if (!amdgpu_dpm) + return 0; + /* init the sysfs and debugfs files late */ ret = amdgpu_pm_sysfs_init(adev); if (ret) diff --git a/drivers/gpu/drm/drm_crtc.c b/drivers/gpu/drm/drm_crtc.c index 33d877c65ced..8328e7059205 100644 --- a/drivers/gpu/drm/drm_crtc.c +++ b/drivers/gpu/drm/drm_crtc.c @@ -4105,7 +4105,7 @@ drm_property_create_blob(struct drm_device *dev, size_t length, struct drm_property_blob *blob; int ret; - if (!length) + if (!length || length > ULONG_MAX - sizeof(struct drm_property_blob)) return ERR_PTR(-EINVAL); blob = kzalloc(sizeof(struct drm_property_blob)+length, GFP_KERNEL); @@ -4454,7 +4454,7 @@ int drm_mode_createblob_ioctl(struct drm_device *dev, * not associated with any file_priv. */ mutex_lock(&dev->mode_config.blob_lock); out_resp->blob_id = blob->base.id; - list_add_tail(&file_priv->blobs, &blob->head_file); + list_add_tail(&blob->head_file, &file_priv->blobs); mutex_unlock(&dev->mode_config.blob_lock); return 0; diff --git a/drivers/gpu/drm/drm_dp_mst_topology.c b/drivers/gpu/drm/drm_dp_mst_topology.c index 5bca390d9ae2..809959d56d78 100644 --- a/drivers/gpu/drm/drm_dp_mst_topology.c +++ b/drivers/gpu/drm/drm_dp_mst_topology.c @@ -1194,17 +1194,18 @@ static struct drm_dp_mst_branch *drm_dp_get_mst_branch_device(struct drm_dp_mst_ list_for_each_entry(port, &mstb->ports, next) { if (port->port_num == port_num) { - if (!port->mstb) { + mstb = port->mstb; + if (!mstb) { DRM_ERROR("failed to lookup MSTB with lct %d, rad %02x\n", lct, rad[0]); - return NULL; + goto out; } - mstb = port->mstb; break; } } } kref_get(&mstb->kref); +out: mutex_unlock(&mgr->lock); return mstb; } diff --git a/drivers/gpu/drm/i915/i915_gem_shrinker.c b/drivers/gpu/drm/i915/i915_gem_shrinker.c index f6ecbda2c604..674341708033 100644 --- a/drivers/gpu/drm/i915/i915_gem_shrinker.c +++ b/drivers/gpu/drm/i915/i915_gem_shrinker.c @@ -143,7 +143,7 @@ i915_gem_shrink(struct drm_i915_private *dev_priv, } /** - * i915_gem_shrink - Shrink buffer object caches completely + * i915_gem_shrink_all - Shrink buffer object caches completely * @dev_priv: i915 device * * This is a simple wraper around i915_gem_shrink() to aggressively shrink all diff --git a/drivers/gpu/drm/i915/i915_gem_userptr.c b/drivers/gpu/drm/i915/i915_gem_userptr.c index 8fd431bcdfd3..a96b9006a51e 100644 --- a/drivers/gpu/drm/i915/i915_gem_userptr.c +++ b/drivers/gpu/drm/i915/i915_gem_userptr.c @@ -804,7 +804,10 @@ static const struct drm_i915_gem_object_ops i915_gem_userptr_ops = { * Also note, that the object created here is not currently a "first class" * object, in that several ioctls are banned. These are the CPU access * ioctls: mmap(), pwrite and pread. In practice, you are expected to use - * direct access via your pointer rather than use those ioctls. + * direct access via your pointer rather than use those ioctls. Another + * restriction is that we do not allow userptr surfaces to be pinned to the + * hardware and so we reject any attempt to create a framebuffer out of a + * userptr. * * If you think this is a good interface to use to pass GPU memory between * drivers, please use dma-buf instead. In fact, wherever possible use diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c index cf418be7d30a..b2270d576979 100644 --- a/drivers/gpu/drm/i915/intel_display.c +++ b/drivers/gpu/drm/i915/intel_display.c @@ -1724,6 +1724,15 @@ static void i9xx_enable_pll(struct intel_crtc *crtc) I915_READ(DPLL(!crtc->pipe)) | DPLL_DVO_2X_MODE); } + /* + * Apparently we need to have VGA mode enabled prior to changing + * the P1/P2 dividers. Otherwise the DPLL will keep using the old + * dividers, even though the register value does change. + */ + I915_WRITE(reg, 0); + + I915_WRITE(reg, dpll); + /* Wait for the clocks to stabilize. */ POSTING_READ(reg); udelay(150); @@ -14107,6 +14116,11 @@ static int intel_user_framebuffer_create_handle(struct drm_framebuffer *fb, struct intel_framebuffer *intel_fb = to_intel_framebuffer(fb); struct drm_i915_gem_object *obj = intel_fb->obj; + if (obj->userptr.mm) { + DRM_DEBUG("attempting to use a userptr for a framebuffer, denied\n"); + return -EINVAL; + } + return drm_gem_handle_create(file, &obj->base, handle); } @@ -14897,9 +14911,19 @@ static void intel_sanitize_crtc(struct intel_crtc *crtc) /* restore vblank interrupts to correct state */ drm_crtc_vblank_reset(&crtc->base); if (crtc->active) { + struct intel_plane *plane; + drm_calc_timestamping_constants(&crtc->base, &crtc->base.hwmode); update_scanline_offset(crtc); drm_crtc_vblank_on(&crtc->base); + + /* Disable everything but the primary plane */ + for_each_intel_plane_on_crtc(dev, crtc, plane) { + if (plane->base.type == DRM_PLANE_TYPE_PRIMARY) + continue; + + plane->disable_plane(&plane->base, &crtc->base); + } } /* We need to sanitize the plane -> pipe mapping first because this will @@ -15067,38 +15091,25 @@ void i915_redisable_vga(struct drm_device *dev) i915_redisable_vga_power_on(dev); } -static bool primary_get_hw_state(struct intel_crtc *crtc) +static bool primary_get_hw_state(struct intel_plane *plane) { - struct drm_i915_private *dev_priv = crtc->base.dev->dev_private; + struct drm_i915_private *dev_priv = to_i915(plane->base.dev); - return !!(I915_READ(DSPCNTR(crtc->plane)) & DISPLAY_PLANE_ENABLE); + return I915_READ(DSPCNTR(plane->plane)) & DISPLAY_PLANE_ENABLE; } -static void readout_plane_state(struct intel_crtc *crtc, - struct intel_crtc_state *crtc_state) +/* FIXME read out full plane state for all planes */ +static void readout_plane_state(struct intel_crtc *crtc) { - struct intel_plane *p; - struct intel_plane_state *plane_state; - bool active = crtc_state->base.active; - - for_each_intel_plane(crtc->base.dev, p) { - if (crtc->pipe != p->pipe) - continue; - - plane_state = to_intel_plane_state(p->base.state); + struct drm_plane *primary = crtc->base.primary; + struct intel_plane_state *plane_state = + to_intel_plane_state(primary->state); - if (p->base.type == DRM_PLANE_TYPE_PRIMARY) { - plane_state->visible = primary_get_hw_state(crtc); - if (plane_state->visible) - crtc->base.state->plane_mask |= - 1 << drm_plane_index(&p->base); - } else { - if (active) - p->disable_plane(&p->base, &crtc->base); + plane_state->visible = + primary_get_hw_state(to_intel_plane(primary)); - plane_state->visible = false; - } - } + if (plane_state->visible) + crtc->base.state->plane_mask |= 1 << drm_plane_index(primary); } static void intel_modeset_readout_hw_state(struct drm_device *dev) @@ -15121,34 +15132,7 @@ static void intel_modeset_readout_hw_state(struct drm_device *dev) crtc->base.state->active = crtc->active; crtc->base.enabled = crtc->active; - memset(&crtc->base.mode, 0, sizeof(crtc->base.mode)); - if (crtc->base.state->active) { - intel_mode_from_pipe_config(&crtc->base.mode, crtc->config); - intel_mode_from_pipe_config(&crtc->base.state->adjusted_mode, crtc->config); - WARN_ON(drm_atomic_set_mode_for_crtc(crtc->base.state, &crtc->base.mode)); - - /* - * The initial mode needs to be set in order to keep - * the atomic core happy. It wants a valid mode if the - * crtc's enabled, so we do the above call. - * - * At this point some state updated by the connectors - * in their ->detect() callback has not run yet, so - * no recalculation can be done yet. - * - * Even if we could do a recalculation and modeset - * right now it would cause a double modeset if - * fbdev or userspace chooses a different initial mode. - * - * If that happens, someone indicated they wanted a - * mode change, which means it's safe to do a full - * recalculation. - */ - crtc->base.state->mode.private_flags = I915_MODE_FLAG_INHERITED; - } - - crtc->base.hwmode = crtc->config->base.adjusted_mode; - readout_plane_state(crtc, to_intel_crtc_state(crtc->base.state)); + readout_plane_state(crtc); DRM_DEBUG_KMS("[CRTC:%d] hw state readout: %s\n", crtc->base.base.id, @@ -15207,6 +15191,36 @@ static void intel_modeset_readout_hw_state(struct drm_device *dev) connector->base.name, connector->base.encoder ? "enabled" : "disabled"); } + + for_each_intel_crtc(dev, crtc) { + crtc->base.hwmode = crtc->config->base.adjusted_mode; + + memset(&crtc->base.mode, 0, sizeof(crtc->base.mode)); + if (crtc->base.state->active) { + intel_mode_from_pipe_config(&crtc->base.mode, crtc->config); + intel_mode_from_pipe_config(&crtc->base.state->adjusted_mode, crtc->config); + WARN_ON(drm_atomic_set_mode_for_crtc(crtc->base.state, &crtc->base.mode)); + + /* + * The initial mode needs to be set in order to keep + * the atomic core happy. It wants a valid mode if the + * crtc's enabled, so we do the above call. + * + * At this point some state updated by the connectors + * in their ->detect() callback has not run yet, so + * no recalculation can be done yet. + * + * Even if we could do a recalculation and modeset + * right now it would cause a double modeset if + * fbdev or userspace chooses a different initial mode. + * + * If that happens, someone indicated they wanted a + * mode change, which means it's safe to do a full + * recalculation. + */ + crtc->base.state->mode.private_flags = I915_MODE_FLAG_INHERITED; + } + } } /* Scan out the current hw modeset state, diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c index 7412caedcf7f..29dd4488dc49 100644 --- a/drivers/gpu/drm/i915/intel_lrc.c +++ b/drivers/gpu/drm/i915/intel_lrc.c @@ -1659,6 +1659,7 @@ static int gen8_emit_flush_render(struct drm_i915_gem_request *request, if (flush_domains) { flags |= PIPE_CONTROL_RENDER_TARGET_CACHE_FLUSH; flags |= PIPE_CONTROL_DEPTH_CACHE_FLUSH; + flags |= PIPE_CONTROL_FLUSH_ENABLE; } if (invalidate_domains) { diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c index 6e6b8db996ef..61b451fbd09e 100644 --- a/drivers/gpu/drm/i915/intel_ringbuffer.c +++ b/drivers/gpu/drm/i915/intel_ringbuffer.c @@ -347,6 +347,7 @@ gen7_render_ring_flush(struct drm_i915_gem_request *req, if (flush_domains) { flags |= PIPE_CONTROL_RENDER_TARGET_CACHE_FLUSH; flags |= PIPE_CONTROL_DEPTH_CACHE_FLUSH; + flags |= PIPE_CONTROL_FLUSH_ENABLE; } if (invalidate_domains) { flags |= PIPE_CONTROL_TLB_INVALIDATE; @@ -418,6 +419,7 @@ gen8_render_ring_flush(struct drm_i915_gem_request *req, if (flush_domains) { flags |= PIPE_CONTROL_RENDER_TARGET_CACHE_FLUSH; flags |= PIPE_CONTROL_DEPTH_CACHE_FLUSH; + flags |= PIPE_CONTROL_FLUSH_ENABLE; } if (invalidate_domains) { flags |= PIPE_CONTROL_TLB_INVALIDATE; diff --git a/drivers/gpu/drm/nouveau/nouveau_gem.c b/drivers/gpu/drm/nouveau/nouveau_gem.c index 2c9981512d27..41be584147b9 100644 --- a/drivers/gpu/drm/nouveau/nouveau_gem.c +++ b/drivers/gpu/drm/nouveau/nouveau_gem.c @@ -227,11 +227,12 @@ nouveau_gem_info(struct drm_file *file_priv, struct drm_gem_object *gem, struct nouveau_bo *nvbo = nouveau_gem_object(gem); struct nvkm_vma *vma; - if (nvbo->bo.mem.mem_type == TTM_PL_TT) + if (is_power_of_2(nvbo->valid_domains)) + rep->domain = nvbo->valid_domains; + else if (nvbo->bo.mem.mem_type == TTM_PL_TT) rep->domain = NOUVEAU_GEM_DOMAIN_GART; else rep->domain = NOUVEAU_GEM_DOMAIN_VRAM; - rep->offset = nvbo->bo.offset; if (cli->vm) { vma = nouveau_bo_vma_find(nvbo, cli->vm); diff --git a/drivers/gpu/drm/radeon/atombios_encoders.c b/drivers/gpu/drm/radeon/atombios_encoders.c index 65adb9c72377..bb292143997e 100644 --- a/drivers/gpu/drm/radeon/atombios_encoders.c +++ b/drivers/gpu/drm/radeon/atombios_encoders.c @@ -237,6 +237,7 @@ void radeon_atom_backlight_init(struct radeon_encoder *radeon_encoder, backlight_update_status(bd); DRM_INFO("radeon atom DIG backlight initialized\n"); + rdev->mode_info.bl_encoder = radeon_encoder; return; @@ -1624,9 +1625,14 @@ radeon_atom_encoder_dpms_avivo(struct drm_encoder *encoder, int mode) } else atom_execute_table(rdev->mode_info.atom_context, index, (uint32_t *)&args); if (radeon_encoder->devices & (ATOM_DEVICE_LCD_SUPPORT)) { - struct radeon_encoder_atom_dig *dig = radeon_encoder->enc_priv; + if (rdev->mode_info.bl_encoder) { + struct radeon_encoder_atom_dig *dig = radeon_encoder->enc_priv; - atombios_set_backlight_level(radeon_encoder, dig->backlight_level); + atombios_set_backlight_level(radeon_encoder, dig->backlight_level); + } else { + args.ucAction = ATOM_LCD_BLON; + atom_execute_table(rdev->mode_info.atom_context, index, (uint32_t *)&args); + } } break; case DRM_MODE_DPMS_STANDBY: @@ -1706,8 +1712,13 @@ radeon_atom_encoder_dpms_dig(struct drm_encoder *encoder, int mode) if (ASIC_IS_DCE4(rdev)) atombios_dig_encoder_setup(encoder, ATOM_ENCODER_CMD_DP_VIDEO_ON, 0); } - if (radeon_encoder->devices & (ATOM_DEVICE_LCD_SUPPORT)) - atombios_set_backlight_level(radeon_encoder, dig->backlight_level); + if (radeon_encoder->devices & (ATOM_DEVICE_LCD_SUPPORT)) { + if (rdev->mode_info.bl_encoder) + atombios_set_backlight_level(radeon_encoder, dig->backlight_level); + else + atombios_dig_transmitter_setup(encoder, + ATOM_TRANSMITTER_ACTION_LCD_BLON, 0, 0); + } if (ext_encoder) atombios_external_encoder_setup(encoder, ext_encoder, ATOM_ENABLE); break; diff --git a/drivers/gpu/drm/radeon/radeon.h b/drivers/gpu/drm/radeon/radeon.h index f03b7eb15233..b6cbd816537e 100644 --- a/drivers/gpu/drm/radeon/radeon.h +++ b/drivers/gpu/drm/radeon/radeon.h @@ -1658,6 +1658,7 @@ struct radeon_pm { u8 fan_max_rpm; /* dpm */ bool dpm_enabled; + bool sysfs_initialized; struct radeon_dpm dpm; }; diff --git a/drivers/gpu/drm/radeon/radeon_encoders.c b/drivers/gpu/drm/radeon/radeon_encoders.c index ef99917f000d..c6ee80216cf4 100644 --- a/drivers/gpu/drm/radeon/radeon_encoders.c +++ b/drivers/gpu/drm/radeon/radeon_encoders.c @@ -194,7 +194,6 @@ static void radeon_encoder_add_backlight(struct radeon_encoder *radeon_encoder, radeon_atom_backlight_init(radeon_encoder, connector); else radeon_legacy_backlight_init(radeon_encoder, connector); - rdev->mode_info.bl_encoder = radeon_encoder; } } diff --git a/drivers/gpu/drm/radeon/radeon_legacy_encoders.c b/drivers/gpu/drm/radeon/radeon_legacy_encoders.c index 45715307db71..30de43366eae 100644 --- a/drivers/gpu/drm/radeon/radeon_legacy_encoders.c +++ b/drivers/gpu/drm/radeon/radeon_legacy_encoders.c @@ -441,6 +441,7 @@ void radeon_legacy_backlight_init(struct radeon_encoder *radeon_encoder, backlight_update_status(bd); DRM_INFO("radeon legacy LVDS backlight initialized\n"); + rdev->mode_info.bl_encoder = radeon_encoder; return; diff --git a/drivers/gpu/drm/radeon/radeon_pm.c b/drivers/gpu/drm/radeon/radeon_pm.c index 44489cce7458..5feee3b4c557 100644 --- a/drivers/gpu/drm/radeon/radeon_pm.c +++ b/drivers/gpu/drm/radeon/radeon_pm.c @@ -717,10 +717,14 @@ static umode_t hwmon_attributes_visible(struct kobject *kobj, struct radeon_device *rdev = dev_get_drvdata(dev); umode_t effective_mode = attr->mode; - /* Skip limit attributes if DPM is not enabled */ + /* Skip attributes if DPM is not enabled */ if (rdev->pm.pm_method != PM_METHOD_DPM && (attr == &sensor_dev_attr_temp1_crit.dev_attr.attr || - attr == &sensor_dev_attr_temp1_crit_hyst.dev_attr.attr)) + attr == &sensor_dev_attr_temp1_crit_hyst.dev_attr.attr || + attr == &sensor_dev_attr_pwm1.dev_attr.attr || + attr == &sensor_dev_attr_pwm1_enable.dev_attr.attr || + attr == &sensor_dev_attr_pwm1_max.dev_attr.attr || + attr == &sensor_dev_attr_pwm1_min.dev_attr.attr)) return 0; /* Skip fan attributes if fan is not present */ @@ -1524,19 +1528,23 @@ int radeon_pm_late_init(struct radeon_device *rdev) if (rdev->pm.pm_method == PM_METHOD_DPM) { if (rdev->pm.dpm_enabled) { - ret = device_create_file(rdev->dev, &dev_attr_power_dpm_state); - if (ret) - DRM_ERROR("failed to create device file for dpm state\n"); - ret = device_create_file(rdev->dev, &dev_attr_power_dpm_force_performance_level); - if (ret) - DRM_ERROR("failed to create device file for dpm state\n"); - /* XXX: these are noops for dpm but are here for backwards compat */ - ret = device_create_file(rdev->dev, &dev_attr_power_profile); - if (ret) - DRM_ERROR("failed to create device file for power profile\n"); - ret = device_create_file(rdev->dev, &dev_attr_power_method); - if (ret) - DRM_ERROR("failed to create device file for power method\n"); + if (!rdev->pm.sysfs_initialized) { + ret = device_create_file(rdev->dev, &dev_attr_power_dpm_state); + if (ret) + DRM_ERROR("failed to create device file for dpm state\n"); + ret = device_create_file(rdev->dev, &dev_attr_power_dpm_force_performance_level); + if (ret) + DRM_ERROR("failed to create device file for dpm state\n"); + /* XXX: these are noops for dpm but are here for backwards compat */ + ret = device_create_file(rdev->dev, &dev_attr_power_profile); + if (ret) + DRM_ERROR("failed to create device file for power profile\n"); + ret = device_create_file(rdev->dev, &dev_attr_power_method); + if (ret) + DRM_ERROR("failed to create device file for power method\n"); + if (!ret) + rdev->pm.sysfs_initialized = true; + } mutex_lock(&rdev->pm.mutex); ret = radeon_dpm_late_enable(rdev); @@ -1552,7 +1560,8 @@ int radeon_pm_late_init(struct radeon_device *rdev) } } } else { - if (rdev->pm.num_power_states > 1) { + if ((rdev->pm.num_power_states > 1) && + (!rdev->pm.sysfs_initialized)) { /* where's the best place to put these? */ ret = device_create_file(rdev->dev, &dev_attr_power_profile); if (ret) @@ -1560,6 +1569,8 @@ int radeon_pm_late_init(struct radeon_device *rdev) ret = device_create_file(rdev->dev, &dev_attr_power_method); if (ret) DRM_ERROR("failed to create device file for power method\n"); + if (!ret) + rdev->pm.sysfs_initialized = true; } } return ret; diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_cmdbuf.c b/drivers/gpu/drm/vmwgfx/vmwgfx_cmdbuf.c index 8a76821177a6..6377e8151000 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_cmdbuf.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_cmdbuf.c @@ -415,16 +415,16 @@ static void vmw_cmdbuf_ctx_process(struct vmw_cmdbuf_man *man, * * Calls vmw_cmdbuf_ctx_process() on all contexts. If any context has * command buffers left that are not submitted to hardware, Make sure - * IRQ handling is turned on. Otherwise, make sure it's turned off. This - * function may return -EAGAIN to indicate it should be rerun due to - * possibly missed IRQs if IRQs has just been turned on. + * IRQ handling is turned on. Otherwise, make sure it's turned off. */ -static int vmw_cmdbuf_man_process(struct vmw_cmdbuf_man *man) +static void vmw_cmdbuf_man_process(struct vmw_cmdbuf_man *man) { - int notempty = 0; + int notempty; struct vmw_cmdbuf_context *ctx; int i; +retry: + notempty = 0; for_each_cmdbuf_ctx(man, i, ctx) vmw_cmdbuf_ctx_process(man, ctx, ¬empty); @@ -440,10 +440,8 @@ static int vmw_cmdbuf_man_process(struct vmw_cmdbuf_man *man) man->irq_on = true; /* Rerun in case we just missed an irq. */ - return -EAGAIN; + goto retry; } - - return 0; } /** @@ -468,8 +466,7 @@ static void vmw_cmdbuf_ctx_add(struct vmw_cmdbuf_man *man, header->cb_context = cb_context; list_add_tail(&header->list, &man->ctx[cb_context].submitted); - if (vmw_cmdbuf_man_process(man) == -EAGAIN) - vmw_cmdbuf_man_process(man); + vmw_cmdbuf_man_process(man); } /** @@ -488,8 +485,7 @@ static void vmw_cmdbuf_man_tasklet(unsigned long data) struct vmw_cmdbuf_man *man = (struct vmw_cmdbuf_man *) data; spin_lock(&man->lock); - if (vmw_cmdbuf_man_process(man) == -EAGAIN) - (void) vmw_cmdbuf_man_process(man); + vmw_cmdbuf_man_process(man); spin_unlock(&man->lock); } @@ -507,6 +503,7 @@ static void vmw_cmdbuf_work_func(struct work_struct *work) struct vmw_cmdbuf_man *man = container_of(work, struct vmw_cmdbuf_man, work); struct vmw_cmdbuf_header *entry, *next; + uint32_t dummy; bool restart = false; spin_lock_bh(&man->lock); @@ -523,6 +520,8 @@ static void vmw_cmdbuf_work_func(struct work_struct *work) if (restart && vmw_cmdbuf_startstop(man, true)) DRM_ERROR("Failed restarting command buffer context 0.\n"); + /* Send a new fence in case one was removed */ + vmw_fifo_send_fence(man->dev_priv, &dummy); } /** @@ -682,7 +681,7 @@ static bool vmw_cmdbuf_try_alloc(struct vmw_cmdbuf_man *man, DRM_MM_SEARCH_DEFAULT, DRM_MM_CREATE_DEFAULT); if (ret) { - (void) vmw_cmdbuf_man_process(man); + vmw_cmdbuf_man_process(man); ret = drm_mm_insert_node_generic(&man->mm, info->node, info->page_size, 0, 0, DRM_MM_SEARCH_DEFAULT, @@ -1168,7 +1167,14 @@ int vmw_cmdbuf_set_pool_size(struct vmw_cmdbuf_man *man, drm_mm_init(&man->mm, 0, size >> PAGE_SHIFT); man->has_pool = true; - man->default_size = default_size; + + /* + * For now, set the default size to VMW_CMDBUF_INLINE_SIZE to + * prevent deadlocks from happening when vmw_cmdbuf_space_pool() + * needs to wait for space and we block on further command + * submissions to be able to free up space. + */ + man->default_size = VMW_CMDBUF_INLINE_SIZE; DRM_INFO("Using command buffers with %s pool.\n", (man->using_mob) ? "MOB" : "DMA"); diff --git a/drivers/i2c/busses/i2c-mv64xxx.c b/drivers/i2c/busses/i2c-mv64xxx.c index 30059c1df2a3..5801227b97ab 100644 --- a/drivers/i2c/busses/i2c-mv64xxx.c +++ b/drivers/i2c/busses/i2c-mv64xxx.c @@ -669,8 +669,6 @@ mv64xxx_i2c_can_offload(struct mv64xxx_i2c_data *drv_data) struct i2c_msg *msgs = drv_data->msgs; int num = drv_data->num_msgs; - return false; - if (!drv_data->offload_enabled) return false; diff --git a/drivers/i2c/busses/i2c-pnx.c b/drivers/i2c/busses/i2c-pnx.c index e814a36d9b78..6f8b446be5b0 100644 --- a/drivers/i2c/busses/i2c-pnx.c +++ b/drivers/i2c/busses/i2c-pnx.c @@ -600,7 +600,7 @@ static int i2c_pnx_controller_suspend(struct device *dev) { struct i2c_pnx_algo_data *alg_data = dev_get_drvdata(dev); - clk_disable(alg_data->clk); + clk_disable_unprepare(alg_data->clk); return 0; } @@ -609,7 +609,7 @@ static int i2c_pnx_controller_resume(struct device *dev) { struct i2c_pnx_algo_data *alg_data = dev_get_drvdata(dev); - return clk_enable(alg_data->clk); + return clk_prepare_enable(alg_data->clk); } static SIMPLE_DEV_PM_OPS(i2c_pnx_pm, @@ -672,7 +672,7 @@ static int i2c_pnx_probe(struct platform_device *pdev) if (IS_ERR(alg_data->ioaddr)) return PTR_ERR(alg_data->ioaddr); - ret = clk_enable(alg_data->clk); + ret = clk_prepare_enable(alg_data->clk); if (ret) return ret; @@ -726,7 +726,7 @@ static int i2c_pnx_probe(struct platform_device *pdev) return 0; out_clock: - clk_disable(alg_data->clk); + clk_disable_unprepare(alg_data->clk); return ret; } @@ -735,7 +735,7 @@ static int i2c_pnx_remove(struct platform_device *pdev) struct i2c_pnx_algo_data *alg_data = platform_get_drvdata(pdev); i2c_del_adapter(&alg_data->adapter); - clk_disable(alg_data->clk); + clk_disable_unprepare(alg_data->clk); return 0; } diff --git a/drivers/iio/accel/st_accel_core.c b/drivers/iio/accel/st_accel_core.c index ff30f8806880..fb9311110424 100644 --- a/drivers/iio/accel/st_accel_core.c +++ b/drivers/iio/accel/st_accel_core.c @@ -149,8 +149,6 @@ #define ST_ACCEL_4_BDU_MASK 0x40 #define ST_ACCEL_4_DRDY_IRQ_ADDR 0x21 #define ST_ACCEL_4_DRDY_IRQ_INT1_MASK 0x04 -#define ST_ACCEL_4_IG1_EN_ADDR 0x21 -#define ST_ACCEL_4_IG1_EN_MASK 0x08 #define ST_ACCEL_4_MULTIREAD_BIT true /* CUSTOM VALUES FOR SENSOR 5 */ @@ -489,10 +487,6 @@ static const struct st_sensor_settings st_accel_sensors_settings[] = { .drdy_irq = { .addr = ST_ACCEL_4_DRDY_IRQ_ADDR, .mask_int1 = ST_ACCEL_4_DRDY_IRQ_INT1_MASK, - .ig1 = { - .en_addr = ST_ACCEL_4_IG1_EN_ADDR, - .en_mask = ST_ACCEL_4_IG1_EN_MASK, - }, }, .multi_read_bit = ST_ACCEL_4_MULTIREAD_BIT, .bootime = 2, /* guess */ diff --git a/drivers/iio/adc/twl4030-madc.c b/drivers/iio/adc/twl4030-madc.c index ebe415f10640..0c74869a540a 100644 --- a/drivers/iio/adc/twl4030-madc.c +++ b/drivers/iio/adc/twl4030-madc.c @@ -45,13 +45,18 @@ #include <linux/types.h> #include <linux/gfp.h> #include <linux/err.h> +#include <linux/regulator/consumer.h> #include <linux/iio/iio.h> +#define TWL4030_USB_SEL_MADC_MCPC (1<<3) +#define TWL4030_USB_CARKIT_ANA_CTRL 0xBB + /** * struct twl4030_madc_data - a container for madc info * @dev: Pointer to device structure for madc * @lock: Mutex protecting this data structure + * @regulator: Pointer to bias regulator for madc * @requests: Array of request struct corresponding to SW1, SW2 and RT * @use_second_irq: IRQ selection (main or co-processor) * @imr: Interrupt mask register of MADC @@ -60,6 +65,7 @@ struct twl4030_madc_data { struct device *dev; struct mutex lock; /* mutex protecting this data structure */ + struct regulator *usb3v1; struct twl4030_madc_request requests[TWL4030_MADC_NUM_METHODS]; bool use_second_irq; u8 imr; @@ -841,6 +847,32 @@ static int twl4030_madc_probe(struct platform_device *pdev) } twl4030_madc = madc; + /* Configure MADC[3:6] */ + ret = twl_i2c_read_u8(TWL_MODULE_USB, ®val, + TWL4030_USB_CARKIT_ANA_CTRL); + if (ret) { + dev_err(&pdev->dev, "unable to read reg CARKIT_ANA_CTRL 0x%X\n", + TWL4030_USB_CARKIT_ANA_CTRL); + goto err_i2c; + } + regval |= TWL4030_USB_SEL_MADC_MCPC; + ret = twl_i2c_write_u8(TWL_MODULE_USB, regval, + TWL4030_USB_CARKIT_ANA_CTRL); + if (ret) { + dev_err(&pdev->dev, "unable to write reg CARKIT_ANA_CTRL 0x%X\n", + TWL4030_USB_CARKIT_ANA_CTRL); + goto err_i2c; + } + + /* Enable 3v1 bias regulator for MADC[3:6] */ + madc->usb3v1 = devm_regulator_get(madc->dev, "vusb3v1"); + if (IS_ERR(madc->usb3v1)) + return -ENODEV; + + ret = regulator_enable(madc->usb3v1); + if (ret) + dev_err(madc->dev, "could not enable 3v1 bias regulator\n"); + ret = iio_device_register(iio_dev); if (ret) { dev_err(&pdev->dev, "could not register iio device\n"); @@ -866,6 +898,8 @@ static int twl4030_madc_remove(struct platform_device *pdev) twl4030_madc_set_current_generator(madc, 0, 0); twl4030_madc_set_power(madc, 0); + regulator_disable(madc->usb3v1); + return 0; } diff --git a/drivers/infiniband/core/cache.c b/drivers/infiniband/core/cache.c index 8f66c67ff0df..87471ef37198 100644 --- a/drivers/infiniband/core/cache.c +++ b/drivers/infiniband/core/cache.c @@ -508,12 +508,12 @@ void ib_cache_gid_set_default_gid(struct ib_device *ib_dev, u8 port, memset(&gid_attr, 0, sizeof(gid_attr)); gid_attr.ndev = ndev; + mutex_lock(&table->lock); ix = find_gid(table, NULL, NULL, true, GID_ATTR_FIND_MASK_DEFAULT); /* Coudn't find default GID location */ WARN_ON(ix < 0); - mutex_lock(&table->lock); if (!__ib_cache_gid_get(ib_dev, port, ix, ¤t_gid, ¤t_gid_attr) && mode == IB_CACHE_GID_DEFAULT_MODE_SET && diff --git a/drivers/infiniband/core/cm.c b/drivers/infiniband/core/cm.c index ea4db9c1d44f..4f918b929eca 100644 --- a/drivers/infiniband/core/cm.c +++ b/drivers/infiniband/core/cm.c @@ -835,6 +835,11 @@ retest: case IB_CM_SIDR_REQ_RCVD: spin_unlock_irq(&cm_id_priv->lock); cm_reject_sidr_req(cm_id_priv, IB_SIDR_REJECT); + spin_lock_irq(&cm.lock); + if (!RB_EMPTY_NODE(&cm_id_priv->sidr_id_node)) + rb_erase(&cm_id_priv->sidr_id_node, + &cm.remote_sidr_table); + spin_unlock_irq(&cm.lock); break; case IB_CM_REQ_SENT: case IB_CM_MRA_REQ_RCVD: @@ -3172,7 +3177,10 @@ int ib_send_cm_sidr_rep(struct ib_cm_id *cm_id, spin_unlock_irqrestore(&cm_id_priv->lock, flags); spin_lock_irqsave(&cm.lock, flags); - rb_erase(&cm_id_priv->sidr_id_node, &cm.remote_sidr_table); + if (!RB_EMPTY_NODE(&cm_id_priv->sidr_id_node)) { + rb_erase(&cm_id_priv->sidr_id_node, &cm.remote_sidr_table); + RB_CLEAR_NODE(&cm_id_priv->sidr_id_node); + } spin_unlock_irqrestore(&cm.lock, flags); return 0; diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c index 59a2dafc8c57..36b12d560e17 100644 --- a/drivers/infiniband/core/cma.c +++ b/drivers/infiniband/core/cma.c @@ -1067,14 +1067,14 @@ static int cma_save_req_info(const struct ib_cm_event *ib_event, sizeof(req->local_gid)); req->has_gid = true; req->service_id = req_param->primary_path->service_id; - req->pkey = req_param->bth_pkey; + req->pkey = be16_to_cpu(req_param->primary_path->pkey); break; case IB_CM_SIDR_REQ_RECEIVED: req->device = sidr_param->listen_id->device; req->port = sidr_param->port; req->has_gid = false; req->service_id = sidr_param->service_id; - req->pkey = sidr_param->bth_pkey; + req->pkey = sidr_param->pkey; break; default: return -EINVAL; @@ -1324,7 +1324,7 @@ static struct rdma_id_private *cma_id_from_event(struct ib_cm_id *cm_id, bind_list = cma_ps_find(rdma_ps_from_service_id(req.service_id), cma_port_from_service_id(req.service_id)); id_priv = cma_find_listener(bind_list, cm_id, ib_event, &req, *net_dev); - if (IS_ERR(id_priv)) { + if (IS_ERR(id_priv) && *net_dev) { dev_put(*net_dev); *net_dev = NULL; } diff --git a/drivers/infiniband/core/roce_gid_mgmt.c b/drivers/infiniband/core/roce_gid_mgmt.c index 6b24cba1e474..178f98482e13 100644 --- a/drivers/infiniband/core/roce_gid_mgmt.c +++ b/drivers/infiniband/core/roce_gid_mgmt.c @@ -250,25 +250,44 @@ static void enum_netdev_ipv4_ips(struct ib_device *ib_dev, u8 port, struct net_device *ndev) { struct in_device *in_dev; + struct sin_list { + struct list_head list; + struct sockaddr_in ip; + }; + struct sin_list *sin_iter; + struct sin_list *sin_temp; + LIST_HEAD(sin_list); if (ndev->reg_state >= NETREG_UNREGISTERING) return; - in_dev = in_dev_get(ndev); - if (!in_dev) + rcu_read_lock(); + in_dev = __in_dev_get_rcu(ndev); + if (!in_dev) { + rcu_read_unlock(); return; + } for_ifa(in_dev) { - struct sockaddr_in ip; + struct sin_list *entry = kzalloc(sizeof(*entry), GFP_ATOMIC); - ip.sin_family = AF_INET; - ip.sin_addr.s_addr = ifa->ifa_address; - update_gid_ip(GID_ADD, ib_dev, port, ndev, - (struct sockaddr *)&ip); + if (!entry) { + pr_warn("roce_gid_mgmt: couldn't allocate entry for IPv4 update\n"); + continue; + } + entry->ip.sin_family = AF_INET; + entry->ip.sin_addr.s_addr = ifa->ifa_address; + list_add_tail(&entry->list, &sin_list); } endfor_ifa(in_dev); + rcu_read_unlock(); - in_dev_put(in_dev); + list_for_each_entry_safe(sin_iter, sin_temp, &sin_list, list) { + update_gid_ip(GID_ADD, ib_dev, port, ndev, + (struct sockaddr *)&sin_iter->ip); + list_del(&sin_iter->list); + kfree(sin_iter); + } } static void enum_netdev_ipv6_ips(struct ib_device *ib_dev, diff --git a/drivers/infiniband/core/ucma.c b/drivers/infiniband/core/ucma.c index a53fc9b01c69..30467d10df91 100644 --- a/drivers/infiniband/core/ucma.c +++ b/drivers/infiniband/core/ucma.c @@ -1624,11 +1624,16 @@ static int ucma_open(struct inode *inode, struct file *filp) if (!file) return -ENOMEM; + file->close_wq = create_singlethread_workqueue("ucma_close_id"); + if (!file->close_wq) { + kfree(file); + return -ENOMEM; + } + INIT_LIST_HEAD(&file->event_list); INIT_LIST_HEAD(&file->ctx_list); init_waitqueue_head(&file->poll_wait); mutex_init(&file->mut); - file->close_wq = create_singlethread_workqueue("ucma_close_id"); filp->private_data = file; file->filp = filp; diff --git a/drivers/input/mouse/alps.c b/drivers/input/mouse/alps.c index 4d246861d692..41e6cb501e6a 100644 --- a/drivers/input/mouse/alps.c +++ b/drivers/input/mouse/alps.c @@ -100,7 +100,7 @@ static const struct alps_nibble_commands alps_v6_nibble_commands[] = { #define ALPS_FOUR_BUTTONS 0x40 /* 4 direction button present */ #define ALPS_PS2_INTERLEAVED 0x80 /* 3-byte PS/2 packet interleaved with 6-byte ALPS packet */ -#define ALPS_DELL 0x100 /* device is a Dell laptop */ +#define ALPS_STICK_BITS 0x100 /* separate stick button bits */ #define ALPS_BUTTONPAD 0x200 /* device is a clickpad */ static const struct alps_model_info alps_model_data[] = { @@ -159,6 +159,43 @@ static const struct alps_protocol_info alps_v8_protocol_data = { ALPS_PROTO_V8, 0x18, 0x18, 0 }; +/* + * Some v2 models report the stick buttons in separate bits + */ +static const struct dmi_system_id alps_dmi_has_separate_stick_buttons[] = { +#if defined(CONFIG_DMI) && defined(CONFIG_X86) + { + /* Extrapolated from other entries */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), + DMI_MATCH(DMI_PRODUCT_NAME, "Latitude D420"), + }, + }, + { + /* Reported-by: Hans de Bruin <jmdebruin@xmsnet.nl> */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), + DMI_MATCH(DMI_PRODUCT_NAME, "Latitude D430"), + }, + }, + { + /* Reported-by: Hans de Goede <hdegoede@redhat.com> */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), + DMI_MATCH(DMI_PRODUCT_NAME, "Latitude D620"), + }, + }, + { + /* Extrapolated from other entries */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), + DMI_MATCH(DMI_PRODUCT_NAME, "Latitude D630"), + }, + }, +#endif + { } +}; + static void alps_set_abs_params_st(struct alps_data *priv, struct input_dev *dev1); static void alps_set_abs_params_semi_mt(struct alps_data *priv, @@ -253,9 +290,8 @@ static void alps_process_packet_v1_v2(struct psmouse *psmouse) return; } - /* Dell non interleaved V2 dualpoint has separate stick button bits */ - if (priv->proto_version == ALPS_PROTO_V2 && - priv->flags == (ALPS_DELL | ALPS_PASS | ALPS_DUALPOINT)) { + /* Some models have separate stick button bits */ + if (priv->flags & ALPS_STICK_BITS) { left |= packet[0] & 1; right |= packet[0] & 2; middle |= packet[0] & 4; @@ -2552,8 +2588,6 @@ static int alps_set_protocol(struct psmouse *psmouse, priv->byte0 = protocol->byte0; priv->mask0 = protocol->mask0; priv->flags = protocol->flags; - if (dmi_name_in_vendors("Dell")) - priv->flags |= ALPS_DELL; priv->x_max = 2000; priv->y_max = 1400; @@ -2568,6 +2602,8 @@ static int alps_set_protocol(struct psmouse *psmouse, priv->set_abs_params = alps_set_abs_params_st; priv->x_max = 1023; priv->y_max = 767; + if (dmi_check_system(alps_dmi_has_separate_stick_buttons)) + priv->flags |= ALPS_STICK_BITS; break; case ALPS_PROTO_V3: diff --git a/drivers/input/touchscreen/Kconfig b/drivers/input/touchscreen/Kconfig index 600dcceff542..deb14c12ae8b 100644 --- a/drivers/input/touchscreen/Kconfig +++ b/drivers/input/touchscreen/Kconfig @@ -1006,6 +1006,7 @@ config TOUCHSCREEN_SUN4I config TOUCHSCREEN_SUR40 tristate "Samsung SUR40 (Surface 2.0/PixelSense) touchscreen" depends on USB && MEDIA_USB_SUPPORT && HAS_DMA + depends on VIDEO_V4L2 select INPUT_POLLDEV select VIDEOBUF2_DMA_SG help diff --git a/drivers/input/touchscreen/lpc32xx_ts.c b/drivers/input/touchscreen/lpc32xx_ts.c index 24d704cd9f88..7fbb3b0c8571 100644 --- a/drivers/input/touchscreen/lpc32xx_ts.c +++ b/drivers/input/touchscreen/lpc32xx_ts.c @@ -139,14 +139,14 @@ static void lpc32xx_stop_tsc(struct lpc32xx_tsc *tsc) tsc_readl(tsc, LPC32XX_TSC_CON) & ~LPC32XX_TSC_ADCCON_AUTO_EN); - clk_disable(tsc->clk); + clk_disable_unprepare(tsc->clk); } static void lpc32xx_setup_tsc(struct lpc32xx_tsc *tsc) { u32 tmp; - clk_enable(tsc->clk); + clk_prepare_enable(tsc->clk); tmp = tsc_readl(tsc, LPC32XX_TSC_CON) & ~LPC32XX_TSC_ADCCON_POWER_UP; diff --git a/drivers/iommu/amd_iommu.c b/drivers/iommu/amd_iommu.c index 08d2775887f7..532e2a211fe1 100644 --- a/drivers/iommu/amd_iommu.c +++ b/drivers/iommu/amd_iommu.c @@ -1974,8 +1974,8 @@ static void set_dte_entry(u16 devid, struct protection_domain *domain, bool ats) static void clear_dte_entry(u16 devid) { /* remove entry from the device table seen by the hardware */ - amd_iommu_dev_table[devid].data[0] = IOMMU_PTE_P | IOMMU_PTE_TV; - amd_iommu_dev_table[devid].data[1] = 0; + amd_iommu_dev_table[devid].data[0] = IOMMU_PTE_P | IOMMU_PTE_TV; + amd_iommu_dev_table[devid].data[1] &= DTE_FLAG_MASK; amd_iommu_apply_erratum_63(devid); } diff --git a/drivers/iommu/amd_iommu_types.h b/drivers/iommu/amd_iommu_types.h index f65908841be0..c9b64722f623 100644 --- a/drivers/iommu/amd_iommu_types.h +++ b/drivers/iommu/amd_iommu_types.h @@ -295,6 +295,7 @@ #define IOMMU_PTE_IR (1ULL << 61) #define IOMMU_PTE_IW (1ULL << 62) +#define DTE_FLAG_MASK (0x3ffULL << 32) #define DTE_FLAG_IOTLB (0x01UL << 32) #define DTE_FLAG_GV (0x01ULL << 55) #define DTE_GLX_SHIFT (56) diff --git a/drivers/iommu/amd_iommu_v2.c b/drivers/iommu/amd_iommu_v2.c index 1131664b918b..d21d4edf7236 100644 --- a/drivers/iommu/amd_iommu_v2.c +++ b/drivers/iommu/amd_iommu_v2.c @@ -516,6 +516,13 @@ static void do_fault(struct work_struct *work) goto out; } + if (!(vma->vm_flags & (VM_READ | VM_EXEC | VM_WRITE))) { + /* handle_mm_fault would BUG_ON() */ + up_read(&mm->mmap_sem); + handle_fault_error(fault); + goto out; + } + ret = handle_mm_fault(mm, vma, address, write); if (ret & VM_FAULT_ERROR) { /* failed to service fault */ diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c index 35365f046923..d65cf42399e8 100644 --- a/drivers/iommu/intel-iommu.c +++ b/drivers/iommu/intel-iommu.c @@ -2115,15 +2115,19 @@ static int __domain_mapping(struct dmar_domain *domain, unsigned long iov_pfn, return -ENOMEM; /* It is large page*/ if (largepage_lvl > 1) { + unsigned long nr_superpages, end_pfn; + pteval |= DMA_PTE_LARGE_PAGE; lvl_pages = lvl_to_nr_pages(largepage_lvl); + + nr_superpages = sg_res / lvl_pages; + end_pfn = iov_pfn + nr_superpages * lvl_pages - 1; + /* * Ensure that old small page tables are - * removed to make room for superpage, - * if they exist. + * removed to make room for superpage(s). */ - dma_pte_free_pagetable(domain, iov_pfn, - iov_pfn + lvl_pages - 1); + dma_pte_free_pagetable(domain, iov_pfn, end_pfn); } else { pteval &= ~(uint64_t)DMA_PTE_LARGE_PAGE; } diff --git a/drivers/irqchip/irq-armada-370-xp.c b/drivers/irqchip/irq-armada-370-xp.c index 655cb967a1f2..389318a3be82 100644 --- a/drivers/irqchip/irq-armada-370-xp.c +++ b/drivers/irqchip/irq-armada-370-xp.c @@ -317,6 +317,7 @@ static int armada_370_xp_mpic_irq_map(struct irq_domain *h, handle_level_irq); } irq_set_probe(virq); + irq_clear_status_flags(virq, IRQ_NOAUTOEN); return 0; } diff --git a/drivers/irqchip/irq-tegra.c b/drivers/irqchip/irq-tegra.c index 2fd89eb88f3a..fd88e687791a 100644 --- a/drivers/irqchip/irq-tegra.c +++ b/drivers/irqchip/irq-tegra.c @@ -214,6 +214,7 @@ static struct irq_chip tegra_ictlr_chip = { .irq_unmask = tegra_unmask, .irq_retrigger = tegra_retrigger, .irq_set_wake = tegra_set_wake, + .irq_set_type = irq_chip_set_type_parent, .flags = IRQCHIP_MASK_ON_SUSPEND, #ifdef CONFIG_SMP .irq_set_affinity = irq_chip_set_affinity_parent, diff --git a/drivers/isdn/hisax/isdnl2.c b/drivers/isdn/hisax/isdnl2.c index 18accb0a79cc..c53a53f6efb6 100644 --- a/drivers/isdn/hisax/isdnl2.c +++ b/drivers/isdn/hisax/isdnl2.c @@ -1247,7 +1247,7 @@ static void l2_pull_iqueue(struct FsmInst *fi, int event, void *arg) { struct PStack *st = fi->userdata; - struct sk_buff *skb; + struct sk_buff *skb, *nskb; struct Layer2 *l2 = &st->l2; u_char header[MAX_HEADER_LEN]; int i, hdr_space_needed; @@ -1262,14 +1262,10 @@ l2_pull_iqueue(struct FsmInst *fi, int event, void *arg) return; hdr_space_needed = l2headersize(l2, 0); - if (hdr_space_needed > skb_headroom(skb)) { - struct sk_buff *orig_skb = skb; - - skb = skb_realloc_headroom(skb, hdr_space_needed); - if (!skb) { - dev_kfree_skb(orig_skb); - return; - } + nskb = skb_realloc_headroom(skb, hdr_space_needed); + if (!nskb) { + skb_queue_head(&l2->i_queue, skb); + return; } spin_lock_irqsave(&l2->lock, flags); if (test_bit(FLG_MOD128, &l2->flag)) @@ -1282,7 +1278,7 @@ l2_pull_iqueue(struct FsmInst *fi, int event, void *arg) p1); dev_kfree_skb(l2->windowar[p1]); } - l2->windowar[p1] = skb_clone(skb, GFP_ATOMIC); + l2->windowar[p1] = skb; i = sethdraddr(&st->l2, header, CMD); @@ -1295,8 +1291,8 @@ l2_pull_iqueue(struct FsmInst *fi, int event, void *arg) l2->vs = (l2->vs + 1) % 8; } spin_unlock_irqrestore(&l2->lock, flags); - memcpy(skb_push(skb, i), header, i); - st->l2.l2l1(st, PH_PULL | INDICATION, skb); + memcpy(skb_push(nskb, i), header, i); + st->l2.l2l1(st, PH_PULL | INDICATION, nskb); test_and_clear_bit(FLG_ACK_PEND, &st->l2.flag); if (!test_and_set_bit(FLG_T200_RUN, &st->l2.flag)) { FsmDelTimer(&st->l2.t203, 13); diff --git a/drivers/isdn/mISDN/layer2.c b/drivers/isdn/mISDN/layer2.c index 949cabb88f1c..5eb380a25903 100644 --- a/drivers/isdn/mISDN/layer2.c +++ b/drivers/isdn/mISDN/layer2.c @@ -1476,7 +1476,7 @@ static void l2_pull_iqueue(struct FsmInst *fi, int event, void *arg) { struct layer2 *l2 = fi->userdata; - struct sk_buff *skb, *nskb, *oskb; + struct sk_buff *skb, *nskb; u_char header[MAX_L2HEADER_LEN]; u_int i, p1; @@ -1486,48 +1486,34 @@ l2_pull_iqueue(struct FsmInst *fi, int event, void *arg) skb = skb_dequeue(&l2->i_queue); if (!skb) return; - - if (test_bit(FLG_MOD128, &l2->flag)) - p1 = (l2->vs - l2->va) % 128; - else - p1 = (l2->vs - l2->va) % 8; - p1 = (p1 + l2->sow) % l2->window; - if (l2->windowar[p1]) { - printk(KERN_WARNING "%s: l2 try overwrite ack queue entry %d\n", - mISDNDevName4ch(&l2->ch), p1); - dev_kfree_skb(l2->windowar[p1]); - } - l2->windowar[p1] = skb; i = sethdraddr(l2, header, CMD); if (test_bit(FLG_MOD128, &l2->flag)) { header[i++] = l2->vs << 1; header[i++] = l2->vr << 1; + } else + header[i++] = (l2->vr << 5) | (l2->vs << 1); + nskb = skb_realloc_headroom(skb, i); + if (!nskb) { + printk(KERN_WARNING "%s: no headroom(%d) copy for IFrame\n", + mISDNDevName4ch(&l2->ch), i); + skb_queue_head(&l2->i_queue, skb); + return; + } + if (test_bit(FLG_MOD128, &l2->flag)) { + p1 = (l2->vs - l2->va) % 128; l2->vs = (l2->vs + 1) % 128; } else { - header[i++] = (l2->vr << 5) | (l2->vs << 1); + p1 = (l2->vs - l2->va) % 8; l2->vs = (l2->vs + 1) % 8; } - - nskb = skb_clone(skb, GFP_ATOMIC); - p1 = skb_headroom(nskb); - if (p1 >= i) - memcpy(skb_push(nskb, i), header, i); - else { - printk(KERN_WARNING - "%s: L2 pull_iqueue skb header(%d/%d) too short\n", - mISDNDevName4ch(&l2->ch), i, p1); - oskb = nskb; - nskb = mI_alloc_skb(oskb->len + i, GFP_ATOMIC); - if (!nskb) { - dev_kfree_skb(oskb); - printk(KERN_WARNING "%s: no skb mem in %s\n", - mISDNDevName4ch(&l2->ch), __func__); - return; - } - memcpy(skb_put(nskb, i), header, i); - memcpy(skb_put(nskb, oskb->len), oskb->data, oskb->len); - dev_kfree_skb(oskb); + p1 = (p1 + l2->sow) % l2->window; + if (l2->windowar[p1]) { + printk(KERN_WARNING "%s: l2 try overwrite ack queue entry %d\n", + mISDNDevName4ch(&l2->ch), p1); + dev_kfree_skb(l2->windowar[p1]); } + l2->windowar[p1] = skb; + memcpy(skb_push(nskb, i), header, i); l2down(l2, PH_DATA_REQ, l2_newid(l2), nskb); test_and_clear_bit(FLG_ACK_PEND, &l2->flag); if (!test_and_set_bit(FLG_T200_RUN, &l2->flag)) { diff --git a/drivers/md/dm-cache-metadata.c b/drivers/md/dm-cache-metadata.c index 20cc36b01b77..0a17d1b91a81 100644 --- a/drivers/md/dm-cache-metadata.c +++ b/drivers/md/dm-cache-metadata.c @@ -634,10 +634,10 @@ static int __commit_transaction(struct dm_cache_metadata *cmd, disk_super = dm_block_data(sblock); + disk_super->flags = cpu_to_le32(cmd->flags); if (mutator) update_flags(disk_super, mutator); - disk_super->flags = cpu_to_le32(cmd->flags); disk_super->mapping_root = cpu_to_le64(cmd->root); disk_super->hint_root = cpu_to_le64(cmd->hint_root); disk_super->discard_root = cpu_to_le64(cmd->discard_root); diff --git a/drivers/md/md.c b/drivers/md/md.c index c702de18207a..3fe3d04a968a 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -8040,8 +8040,7 @@ static int remove_and_add_spares(struct mddev *mddev, !test_bit(Bitmap_sync, &rdev->flags))) continue; - if (rdev->saved_raid_disk < 0) - rdev->recovery_offset = 0; + rdev->recovery_offset = 0; if (mddev->pers-> hot_add_disk(mddev, rdev) == 0) { if (sysfs_link_rdev(mddev, rdev)) diff --git a/drivers/md/persistent-data/dm-btree-remove.c b/drivers/md/persistent-data/dm-btree-remove.c index 421a36c593e3..2e4c4cb79e4d 100644 --- a/drivers/md/persistent-data/dm-btree-remove.c +++ b/drivers/md/persistent-data/dm-btree-remove.c @@ -301,11 +301,16 @@ static void redistribute3(struct dm_btree_info *info, struct btree_node *parent, { int s; uint32_t max_entries = le32_to_cpu(left->header.max_entries); - unsigned target = (nr_left + nr_center + nr_right) / 3; - BUG_ON(target > max_entries); + unsigned total = nr_left + nr_center + nr_right; + unsigned target_right = total / 3; + unsigned remainder = (target_right * 3) != total; + unsigned target_left = target_right + remainder; + + BUG_ON(target_left > max_entries); + BUG_ON(target_right > max_entries); if (nr_left < nr_right) { - s = nr_left - target; + s = nr_left - target_left; if (s < 0 && nr_center < -s) { /* not enough in central node */ @@ -316,10 +321,10 @@ static void redistribute3(struct dm_btree_info *info, struct btree_node *parent, } else shift(left, center, s); - shift(center, right, target - nr_right); + shift(center, right, target_right - nr_right); } else { - s = target - nr_right; + s = target_right - nr_right; if (s > 0 && nr_center < s) { /* not enough in central node */ shift(center, right, nr_center); @@ -329,7 +334,7 @@ static void redistribute3(struct dm_btree_info *info, struct btree_node *parent, } else shift(center, right, s); - shift(left, center, nr_left - target); + shift(left, center, nr_left - target_left); } *key_ptr(parent, c->index) = center->keys[0]; diff --git a/drivers/md/persistent-data/dm-btree.c b/drivers/md/persistent-data/dm-btree.c index b6cec258cc21..0e09aef43998 100644 --- a/drivers/md/persistent-data/dm-btree.c +++ b/drivers/md/persistent-data/dm-btree.c @@ -523,7 +523,7 @@ static int btree_split_beneath(struct shadow_spine *s, uint64_t key) r = new_block(s->info, &right); if (r < 0) { - /* FIXME: put left */ + unlock_block(s->info, left); return r; } diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c index ddd8a5f572aa..d9d031ede4bf 100644 --- a/drivers/md/raid1.c +++ b/drivers/md/raid1.c @@ -2195,7 +2195,7 @@ static int narrow_write_error(struct r1bio *r1_bio, int i) bio_trim(wbio, sector - r1_bio->sector, sectors); wbio->bi_iter.bi_sector += rdev->data_offset; wbio->bi_bdev = rdev->bdev; - if (submit_bio_wait(WRITE, wbio) == 0) + if (submit_bio_wait(WRITE, wbio) < 0) /* failure! */ ok = rdev_set_badblocks(rdev, sector, sectors, 0) @@ -2258,15 +2258,16 @@ static void handle_write_finished(struct r1conf *conf, struct r1bio *r1_bio) rdev_dec_pending(conf->mirrors[m].rdev, conf->mddev); } - if (test_bit(R1BIO_WriteError, &r1_bio->state)) - close_write(r1_bio); if (fail) { spin_lock_irq(&conf->device_lock); list_add(&r1_bio->retry_list, &conf->bio_end_io_list); spin_unlock_irq(&conf->device_lock); md_wakeup_thread(conf->mddev->thread); - } else + } else { + if (test_bit(R1BIO_WriteError, &r1_bio->state)) + close_write(r1_bio); raid_end_bio_io(r1_bio); + } } static void handle_read_error(struct r1conf *conf, struct r1bio *r1_bio) @@ -2385,6 +2386,10 @@ static void raid1d(struct md_thread *thread) r1_bio = list_first_entry(&tmp, struct r1bio, retry_list); list_del(&r1_bio->retry_list); + if (mddev->degraded) + set_bit(R1BIO_Degraded, &r1_bio->state); + if (test_bit(R1BIO_WriteError, &r1_bio->state)) + close_write(r1_bio); raid_end_bio_io(r1_bio); } } diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c index 9f69dc526f8c..96f365968306 100644 --- a/drivers/md/raid10.c +++ b/drivers/md/raid10.c @@ -39,6 +39,7 @@ * far_copies (stored in second byte of layout) * far_offset (stored in bit 16 of layout ) * use_far_sets (stored in bit 17 of layout ) + * use_far_sets_bugfixed (stored in bit 18 of layout ) * * The data to be stored is divided into chunks using chunksize. Each device * is divided into far_copies sections. In each section, chunks are laid out @@ -1497,6 +1498,8 @@ static void status(struct seq_file *seq, struct mddev *mddev) seq_printf(seq, " %d offset-copies", conf->geo.far_copies); else seq_printf(seq, " %d far-copies", conf->geo.far_copies); + if (conf->geo.far_set_size != conf->geo.raid_disks) + seq_printf(seq, " %d devices per set", conf->geo.far_set_size); } seq_printf(seq, " [%d/%d] [", conf->geo.raid_disks, conf->geo.raid_disks - mddev->degraded); @@ -2467,7 +2470,7 @@ static int narrow_write_error(struct r10bio *r10_bio, int i) choose_data_offset(r10_bio, rdev) + (sector - r10_bio->sector)); wbio->bi_bdev = rdev->bdev; - if (submit_bio_wait(WRITE, wbio) == 0) + if (submit_bio_wait(WRITE, wbio) < 0) /* Failure! */ ok = rdev_set_badblocks(rdev, sector, sectors, 0) @@ -2654,16 +2657,17 @@ static void handle_write_completed(struct r10conf *conf, struct r10bio *r10_bio) rdev_dec_pending(rdev, conf->mddev); } } - if (test_bit(R10BIO_WriteError, - &r10_bio->state)) - close_write(r10_bio); if (fail) { spin_lock_irq(&conf->device_lock); list_add(&r10_bio->retry_list, &conf->bio_end_io_list); spin_unlock_irq(&conf->device_lock); md_wakeup_thread(conf->mddev->thread); - } else + } else { + if (test_bit(R10BIO_WriteError, + &r10_bio->state)) + close_write(r10_bio); raid_end_bio_io(r10_bio); + } } } @@ -2691,6 +2695,12 @@ static void raid10d(struct md_thread *thread) r10_bio = list_first_entry(&tmp, struct r10bio, retry_list); list_del(&r10_bio->retry_list); + if (mddev->degraded) + set_bit(R10BIO_Degraded, &r10_bio->state); + + if (test_bit(R10BIO_WriteError, + &r10_bio->state)) + close_write(r10_bio); raid_end_bio_io(r10_bio); } } @@ -3387,7 +3397,7 @@ static int setup_geo(struct geom *geo, struct mddev *mddev, enum geo_type new) disks = mddev->raid_disks + mddev->delta_disks; break; } - if (layout >> 18) + if (layout >> 19) return -1; if (chunk < (PAGE_SIZE >> 9) || !is_power_of_2(chunk)) @@ -3399,7 +3409,22 @@ static int setup_geo(struct geom *geo, struct mddev *mddev, enum geo_type new) geo->near_copies = nc; geo->far_copies = fc; geo->far_offset = fo; - geo->far_set_size = (layout & (1<<17)) ? disks / fc : disks; + switch (layout >> 17) { + case 0: /* original layout. simple but not always optimal */ + geo->far_set_size = disks; + break; + case 1: /* "improved" layout which was buggy. Hopefully no-one is + * actually using this, but leave code here just in case.*/ + geo->far_set_size = disks/fc; + WARN(geo->far_set_size < fc, + "This RAID10 layout does not provide data safety - please backup and create new array\n"); + break; + case 2: /* "improved" layout fixed to match documentation */ + geo->far_set_size = fc * nc; + break; + default: /* Not a valid layout */ + return -1; + } geo->chunk_mask = chunk - 1; geo->chunk_shift = ffz(~chunk); return nc*fc; diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index 49bb8d3ff9be..45933c160697 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -3499,6 +3499,7 @@ returnbi: } if (!discard_pending && test_bit(R5_Discard, &sh->dev[sh->pd_idx].flags)) { + int hash; clear_bit(R5_Discard, &sh->dev[sh->pd_idx].flags); clear_bit(R5_UPTODATE, &sh->dev[sh->pd_idx].flags); if (sh->qd_idx >= 0) { @@ -3512,16 +3513,17 @@ returnbi: * no updated data, so remove it from hash list and the stripe * will be reinitialized */ - spin_lock_irq(&conf->device_lock); unhash: + hash = sh->hash_lock_index; + spin_lock_irq(conf->hash_locks + hash); remove_hash(sh); + spin_unlock_irq(conf->hash_locks + hash); if (head_sh->batch_head) { sh = list_first_entry(&sh->batch_list, struct stripe_head, batch_list); if (sh != head_sh) goto unhash; } - spin_unlock_irq(&conf->device_lock); sh = head_sh; if (test_bit(STRIPE_SYNC_REQUESTED, &sh->state)) diff --git a/drivers/media/dvb-frontends/horus3a.h b/drivers/media/dvb-frontends/horus3a.h index b055319d532e..c1e2d1834b78 100644 --- a/drivers/media/dvb-frontends/horus3a.h +++ b/drivers/media/dvb-frontends/horus3a.h @@ -46,8 +46,8 @@ extern struct dvb_frontend *horus3a_attach(struct dvb_frontend *fe, const struct horus3a_config *config, struct i2c_adapter *i2c); #else -static inline struct dvb_frontend *horus3a_attach( - const struct cxd2820r_config *config, +static inline struct dvb_frontend *horus3a_attach(struct dvb_frontend *fe, + const struct horus3a_config *config, struct i2c_adapter *i2c) { printk(KERN_WARNING "%s: driver disabled by Kconfig\n", __func__); diff --git a/drivers/media/dvb-frontends/lnbh25.h b/drivers/media/dvb-frontends/lnbh25.h index 69f30e21f6b3..1f329ef05acc 100644 --- a/drivers/media/dvb-frontends/lnbh25.h +++ b/drivers/media/dvb-frontends/lnbh25.h @@ -43,7 +43,7 @@ struct dvb_frontend *lnbh25_attach( struct lnbh25_config *cfg, struct i2c_adapter *i2c); #else -static inline dvb_frontend *lnbh25_attach( +static inline struct dvb_frontend *lnbh25_attach( struct dvb_frontend *fe, struct lnbh25_config *cfg, struct i2c_adapter *i2c) diff --git a/drivers/media/dvb-frontends/m88ds3103.c b/drivers/media/dvb-frontends/m88ds3103.c index ff31e7a01ca9..feeeb70d841e 100644 --- a/drivers/media/dvb-frontends/m88ds3103.c +++ b/drivers/media/dvb-frontends/m88ds3103.c @@ -18,6 +18,27 @@ static struct dvb_frontend_ops m88ds3103_ops; +/* write single register with mask */ +static int m88ds3103_update_bits(struct m88ds3103_dev *dev, + u8 reg, u8 mask, u8 val) +{ + int ret; + u8 tmp; + + /* no need for read if whole reg is written */ + if (mask != 0xff) { + ret = regmap_bulk_read(dev->regmap, reg, &tmp, 1); + if (ret) + return ret; + + val &= mask; + tmp &= ~mask; + val |= tmp; + } + + return regmap_bulk_write(dev->regmap, reg, &val, 1); +} + /* write reg val table using reg addr auto increment */ static int m88ds3103_wr_reg_val_tab(struct m88ds3103_dev *dev, const struct m88ds3103_reg_val *tab, int tab_len) @@ -394,10 +415,10 @@ static int m88ds3103_set_frontend(struct dvb_frontend *fe) u8tmp2 = 0x00; /* 0b00 */ break; } - ret = regmap_update_bits(dev->regmap, 0x22, 0xc0, u8tmp1 << 6); + ret = m88ds3103_update_bits(dev, 0x22, 0xc0, u8tmp1 << 6); if (ret) goto err; - ret = regmap_update_bits(dev->regmap, 0x24, 0xc0, u8tmp2 << 6); + ret = m88ds3103_update_bits(dev, 0x24, 0xc0, u8tmp2 << 6); if (ret) goto err; } @@ -455,13 +476,13 @@ static int m88ds3103_set_frontend(struct dvb_frontend *fe) if (ret) goto err; } - ret = regmap_update_bits(dev->regmap, 0x9d, 0x08, 0x08); + ret = m88ds3103_update_bits(dev, 0x9d, 0x08, 0x08); if (ret) goto err; ret = regmap_write(dev->regmap, 0xf1, 0x01); if (ret) goto err; - ret = regmap_update_bits(dev->regmap, 0x30, 0x80, 0x80); + ret = m88ds3103_update_bits(dev, 0x30, 0x80, 0x80); if (ret) goto err; } @@ -498,7 +519,7 @@ static int m88ds3103_set_frontend(struct dvb_frontend *fe) switch (dev->cfg->ts_mode) { case M88DS3103_TS_SERIAL: case M88DS3103_TS_SERIAL_D7: - ret = regmap_update_bits(dev->regmap, 0x29, 0x20, u8tmp1); + ret = m88ds3103_update_bits(dev, 0x29, 0x20, u8tmp1); if (ret) goto err; u8tmp1 = 0; @@ -567,11 +588,11 @@ static int m88ds3103_set_frontend(struct dvb_frontend *fe) if (ret) goto err; - ret = regmap_update_bits(dev->regmap, 0x4d, 0x02, dev->cfg->spec_inv << 1); + ret = m88ds3103_update_bits(dev, 0x4d, 0x02, dev->cfg->spec_inv << 1); if (ret) goto err; - ret = regmap_update_bits(dev->regmap, 0x30, 0x10, dev->cfg->agc_inv << 4); + ret = m88ds3103_update_bits(dev, 0x30, 0x10, dev->cfg->agc_inv << 4); if (ret) goto err; @@ -625,13 +646,13 @@ static int m88ds3103_init(struct dvb_frontend *fe) dev->warm = false; /* wake up device from sleep */ - ret = regmap_update_bits(dev->regmap, 0x08, 0x01, 0x01); + ret = m88ds3103_update_bits(dev, 0x08, 0x01, 0x01); if (ret) goto err; - ret = regmap_update_bits(dev->regmap, 0x04, 0x01, 0x00); + ret = m88ds3103_update_bits(dev, 0x04, 0x01, 0x00); if (ret) goto err; - ret = regmap_update_bits(dev->regmap, 0x23, 0x10, 0x00); + ret = m88ds3103_update_bits(dev, 0x23, 0x10, 0x00); if (ret) goto err; @@ -749,18 +770,18 @@ static int m88ds3103_sleep(struct dvb_frontend *fe) utmp = 0x29; else utmp = 0x27; - ret = regmap_update_bits(dev->regmap, utmp, 0x01, 0x00); + ret = m88ds3103_update_bits(dev, utmp, 0x01, 0x00); if (ret) goto err; /* sleep */ - ret = regmap_update_bits(dev->regmap, 0x08, 0x01, 0x00); + ret = m88ds3103_update_bits(dev, 0x08, 0x01, 0x00); if (ret) goto err; - ret = regmap_update_bits(dev->regmap, 0x04, 0x01, 0x01); + ret = m88ds3103_update_bits(dev, 0x04, 0x01, 0x01); if (ret) goto err; - ret = regmap_update_bits(dev->regmap, 0x23, 0x10, 0x10); + ret = m88ds3103_update_bits(dev, 0x23, 0x10, 0x10); if (ret) goto err; @@ -992,12 +1013,12 @@ static int m88ds3103_set_tone(struct dvb_frontend *fe, } utmp = tone << 7 | dev->cfg->envelope_mode << 5; - ret = regmap_update_bits(dev->regmap, 0xa2, 0xe0, utmp); + ret = m88ds3103_update_bits(dev, 0xa2, 0xe0, utmp); if (ret) goto err; utmp = 1 << 2; - ret = regmap_update_bits(dev->regmap, 0xa1, reg_a1_mask, utmp); + ret = m88ds3103_update_bits(dev, 0xa1, reg_a1_mask, utmp); if (ret) goto err; @@ -1047,7 +1068,7 @@ static int m88ds3103_set_voltage(struct dvb_frontend *fe, voltage_dis ^= dev->cfg->lnb_en_pol; utmp = voltage_dis << 1 | voltage_sel << 0; - ret = regmap_update_bits(dev->regmap, 0xa2, 0x03, utmp); + ret = m88ds3103_update_bits(dev, 0xa2, 0x03, utmp); if (ret) goto err; @@ -1080,7 +1101,7 @@ static int m88ds3103_diseqc_send_master_cmd(struct dvb_frontend *fe, } utmp = dev->cfg->envelope_mode << 5; - ret = regmap_update_bits(dev->regmap, 0xa2, 0xe0, utmp); + ret = m88ds3103_update_bits(dev, 0xa2, 0xe0, utmp); if (ret) goto err; @@ -1115,12 +1136,12 @@ static int m88ds3103_diseqc_send_master_cmd(struct dvb_frontend *fe, } else { dev_dbg(&client->dev, "diseqc tx timeout\n"); - ret = regmap_update_bits(dev->regmap, 0xa1, 0xc0, 0x40); + ret = m88ds3103_update_bits(dev, 0xa1, 0xc0, 0x40); if (ret) goto err; } - ret = regmap_update_bits(dev->regmap, 0xa2, 0xc0, 0x80); + ret = m88ds3103_update_bits(dev, 0xa2, 0xc0, 0x80); if (ret) goto err; @@ -1152,7 +1173,7 @@ static int m88ds3103_diseqc_send_burst(struct dvb_frontend *fe, } utmp = dev->cfg->envelope_mode << 5; - ret = regmap_update_bits(dev->regmap, 0xa2, 0xe0, utmp); + ret = m88ds3103_update_bits(dev, 0xa2, 0xe0, utmp); if (ret) goto err; @@ -1194,12 +1215,12 @@ static int m88ds3103_diseqc_send_burst(struct dvb_frontend *fe, } else { dev_dbg(&client->dev, "diseqc tx timeout\n"); - ret = regmap_update_bits(dev->regmap, 0xa1, 0xc0, 0x40); + ret = m88ds3103_update_bits(dev, 0xa1, 0xc0, 0x40); if (ret) goto err; } - ret = regmap_update_bits(dev->regmap, 0xa2, 0xc0, 0x80); + ret = m88ds3103_update_bits(dev, 0xa2, 0xc0, 0x80); if (ret) goto err; @@ -1435,13 +1456,13 @@ static int m88ds3103_probe(struct i2c_client *client, goto err_kfree; /* sleep */ - ret = regmap_update_bits(dev->regmap, 0x08, 0x01, 0x00); + ret = m88ds3103_update_bits(dev, 0x08, 0x01, 0x00); if (ret) goto err_kfree; - ret = regmap_update_bits(dev->regmap, 0x04, 0x01, 0x01); + ret = m88ds3103_update_bits(dev, 0x04, 0x01, 0x01); if (ret) goto err_kfree; - ret = regmap_update_bits(dev->regmap, 0x23, 0x10, 0x10); + ret = m88ds3103_update_bits(dev, 0x23, 0x10, 0x10); if (ret) goto err_kfree; diff --git a/drivers/media/dvb-frontends/si2168.c b/drivers/media/dvb-frontends/si2168.c index 81788c5a44d8..821a8f481507 100644 --- a/drivers/media/dvb-frontends/si2168.c +++ b/drivers/media/dvb-frontends/si2168.c @@ -502,6 +502,10 @@ static int si2168_init(struct dvb_frontend *fe) /* firmware is in the new format */ for (remaining = fw->size; remaining > 0; remaining -= 17) { len = fw->data[fw->size - remaining]; + if (len > SI2168_ARGLEN) { + ret = -EINVAL; + break; + } memcpy(cmd.args, &fw->data[(fw->size - remaining) + 1], len); cmd.wlen = len; cmd.rlen = 1; diff --git a/drivers/media/pci/netup_unidvb/netup_unidvb_spi.c b/drivers/media/pci/netup_unidvb/netup_unidvb_spi.c index f55b3276f28d..56773f3893d4 100644 --- a/drivers/media/pci/netup_unidvb/netup_unidvb_spi.c +++ b/drivers/media/pci/netup_unidvb/netup_unidvb_spi.c @@ -80,11 +80,9 @@ irqreturn_t netup_spi_interrupt(struct netup_spi *spi) u16 reg; unsigned long flags; - if (!spi) { - dev_dbg(&spi->master->dev, - "%s(): SPI not initialized\n", __func__); + if (!spi) return IRQ_NONE; - } + spin_lock_irqsave(&spi->lock, flags); reg = readw(&spi->regs->control_stat); if (!(reg & NETUP_SPI_CTRL_IRQ)) { @@ -234,11 +232,9 @@ void netup_spi_release(struct netup_unidvb_dev *ndev) unsigned long flags; struct netup_spi *spi = ndev->spi; - if (!spi) { - dev_dbg(&spi->master->dev, - "%s(): SPI not initialized\n", __func__); + if (!spi) return; - } + spin_lock_irqsave(&spi->lock, flags); reg = readw(&spi->regs->control_stat); writew(reg | NETUP_SPI_CTRL_IRQ, &spi->regs->control_stat); diff --git a/drivers/media/platform/sti/c8sectpfe/c8sectpfe-core.c b/drivers/media/platform/sti/c8sectpfe/c8sectpfe-core.c index 486aef50d99b..f922f2e827bc 100644 --- a/drivers/media/platform/sti/c8sectpfe/c8sectpfe-core.c +++ b/drivers/media/platform/sti/c8sectpfe/c8sectpfe-core.c @@ -1097,7 +1097,7 @@ static int load_slim_core_fw(const struct firmware *fw, void *context) Elf32_Ehdr *ehdr; Elf32_Phdr *phdr; u8 __iomem *dst; - int err, i; + int err = 0, i; if (!fw || !context) return -EINVAL; @@ -1106,7 +1106,7 @@ static int load_slim_core_fw(const struct firmware *fw, void *context) phdr = (Elf32_Phdr *)(fw->data + ehdr->e_phoff); /* go through the available ELF segments */ - for (i = 0; i < ehdr->e_phnum && !err; i++, phdr++) { + for (i = 0; i < ehdr->e_phnum; i++, phdr++) { /* Only consider LOAD segments */ if (phdr->p_type != PT_LOAD) @@ -1192,7 +1192,6 @@ err: static int load_c8sectpfe_fw_step1(struct c8sectpfei *fei) { - int ret; int err; dev_info(fei->dev, "Loading firmware: %s\n", FIRMWARE_MEMDMA); @@ -1207,7 +1206,7 @@ static int load_c8sectpfe_fw_step1(struct c8sectpfei *fei) if (err) { dev_err(fei->dev, "request_firmware_nowait err: %d.\n", err); complete_all(&fei->fw_ack); - return ret; + return err; } return 0; diff --git a/drivers/media/rc/ir-hix5hd2.c b/drivers/media/rc/ir-hix5hd2.c index 1c087cb76815..d0549fba711c 100644 --- a/drivers/media/rc/ir-hix5hd2.c +++ b/drivers/media/rc/ir-hix5hd2.c @@ -257,7 +257,7 @@ static int hix5hd2_ir_probe(struct platform_device *pdev) goto clkerr; if (devm_request_irq(dev, priv->irq, hix5hd2_ir_rx_interrupt, - IRQF_NO_SUSPEND, pdev->name, priv) < 0) { + 0, pdev->name, priv) < 0) { dev_err(dev, "IRQ %d register failed\n", priv->irq); ret = -EINVAL; goto regerr; diff --git a/drivers/media/tuners/si2157.c b/drivers/media/tuners/si2157.c index 507382160e5e..ce157edd45fa 100644 --- a/drivers/media/tuners/si2157.c +++ b/drivers/media/tuners/si2157.c @@ -166,6 +166,10 @@ static int si2157_init(struct dvb_frontend *fe) for (remaining = fw->size; remaining > 0; remaining -= 17) { len = fw->data[fw->size - remaining]; + if (len > SI2157_ARGLEN) { + dev_err(&client->dev, "Bad firmware length\n"); + goto err_release_firmware; + } memcpy(cmd.args, &fw->data[(fw->size - remaining) + 1], len); cmd.wlen = len; cmd.rlen = 1; diff --git a/drivers/media/usb/dvb-usb-v2/rtl28xxu.c b/drivers/media/usb/dvb-usb-v2/rtl28xxu.c index c3cac4c12fb3..197a4f2e54d2 100644 --- a/drivers/media/usb/dvb-usb-v2/rtl28xxu.c +++ b/drivers/media/usb/dvb-usb-v2/rtl28xxu.c @@ -34,6 +34,14 @@ static int rtl28xxu_ctrl_msg(struct dvb_usb_device *d, struct rtl28xxu_req *req) unsigned int pipe; u8 requesttype; + mutex_lock(&d->usb_mutex); + + if (req->size > sizeof(dev->buf)) { + dev_err(&d->intf->dev, "too large message %u\n", req->size); + ret = -EINVAL; + goto err_mutex_unlock; + } + if (req->index & CMD_WR_FLAG) { /* write */ memcpy(dev->buf, req->data, req->size); @@ -50,14 +58,17 @@ static int rtl28xxu_ctrl_msg(struct dvb_usb_device *d, struct rtl28xxu_req *req) dvb_usb_dbg_usb_control_msg(d->udev, 0, requesttype, req->value, req->index, dev->buf, req->size); if (ret < 0) - goto err; + goto err_mutex_unlock; /* read request, copy returned data to return buf */ if (requesttype == (USB_TYPE_VENDOR | USB_DIR_IN)) memcpy(req->data, dev->buf, req->size); + mutex_unlock(&d->usb_mutex); + return 0; -err: +err_mutex_unlock: + mutex_unlock(&d->usb_mutex); dev_dbg(&d->intf->dev, "failed=%d\n", ret); return ret; } diff --git a/drivers/media/usb/dvb-usb-v2/rtl28xxu.h b/drivers/media/usb/dvb-usb-v2/rtl28xxu.h index 9f6115a2ee01..138062960a73 100644 --- a/drivers/media/usb/dvb-usb-v2/rtl28xxu.h +++ b/drivers/media/usb/dvb-usb-v2/rtl28xxu.h @@ -71,7 +71,7 @@ struct rtl28xxu_dev { - u8 buf[28]; + u8 buf[128]; u8 chip_id; u8 tuner; char *tuner_name; diff --git a/drivers/media/v4l2-core/Kconfig b/drivers/media/v4l2-core/Kconfig index 82876a67f144..9beece00869b 100644 --- a/drivers/media/v4l2-core/Kconfig +++ b/drivers/media/v4l2-core/Kconfig @@ -47,7 +47,7 @@ config V4L2_MEM2MEM_DEV # Used by LED subsystem flash drivers config V4L2_FLASH_LED_CLASS tristate "V4L2 flash API for LED flash class devices" - depends on VIDEO_V4L2_SUBDEV_API + depends on VIDEO_V4L2 && VIDEO_V4L2_SUBDEV_API depends on LEDS_CLASS_FLASH ---help--- Say Y here to enable V4L2 flash API support for LED flash diff --git a/drivers/memory/Kconfig b/drivers/memory/Kconfig index c6a644b22af4..6f3154613dc7 100644 --- a/drivers/memory/Kconfig +++ b/drivers/memory/Kconfig @@ -58,12 +58,18 @@ config OMAP_GPMC memory drives like NOR, NAND, OneNAND, SRAM. config OMAP_GPMC_DEBUG - bool + bool "Enable GPMC debug output and skip reset of GPMC during init" depends on OMAP_GPMC help Enables verbose debugging mostly to decode the bootloader provided - timings. Enable this during development to configure devices - connected to the GPMC bus. + timings. To preserve the bootloader provided timings, the reset + of GPMC is skipped during init. Enable this during development to + configure devices connected to the GPMC bus. + + NOTE: In addition to matching the register setup with the bootloader + you also need to match the GPMC FCLK frequency used by the + bootloader or else the GPMC timings won't be identical with the + bootloader timings. config MVEBU_DEVBUS bool "Marvell EBU Device Bus Controller" diff --git a/drivers/memory/omap-gpmc.c b/drivers/memory/omap-gpmc.c index 32ac049f2bc4..6515dfc2b805 100644 --- a/drivers/memory/omap-gpmc.c +++ b/drivers/memory/omap-gpmc.c @@ -696,7 +696,6 @@ int gpmc_cs_set_timings(int cs, const struct gpmc_timings *t, int div; u32 l; - gpmc_cs_show_timings(cs, "before gpmc_cs_set_timings"); div = gpmc_calc_divider(t->sync_clk); if (div < 0) return div; @@ -1988,6 +1987,7 @@ static int gpmc_probe_generic_child(struct platform_device *pdev, if (ret < 0) goto err; + gpmc_cs_show_timings(cs, "before gpmc_cs_program_settings"); ret = gpmc_cs_program_settings(cs, &gpmc_s); if (ret < 0) goto err; diff --git a/drivers/mmc/card/mmc_test.c b/drivers/mmc/card/mmc_test.c index b78cf5d403a3..7fc9174d4619 100644 --- a/drivers/mmc/card/mmc_test.c +++ b/drivers/mmc/card/mmc_test.c @@ -2263,15 +2263,12 @@ static int mmc_test_profile_sglen_r_nonblock_perf(struct mmc_test_card *test) /* * eMMC hardware reset. */ -static int mmc_test_hw_reset(struct mmc_test_card *test) +static int mmc_test_reset(struct mmc_test_card *test) { struct mmc_card *card = test->card; struct mmc_host *host = card->host; int err; - if (!mmc_card_mmc(card) || !mmc_can_reset(card)) - return RESULT_UNSUP_CARD; - err = mmc_hw_reset(host); if (!err) return RESULT_OK; @@ -2605,8 +2602,8 @@ static const struct mmc_test_case mmc_test_cases[] = { }, { - .name = "eMMC hardware reset", - .run = mmc_test_hw_reset, + .name = "Reset test", + .run = mmc_test_reset, }, }; diff --git a/drivers/mmc/core/mmc.c b/drivers/mmc/core/mmc.c index e726903170a8..f6cd995dbe92 100644 --- a/drivers/mmc/core/mmc.c +++ b/drivers/mmc/core/mmc.c @@ -1924,7 +1924,6 @@ EXPORT_SYMBOL(mmc_can_reset); static int mmc_reset(struct mmc_host *host) { struct mmc_card *card = host->card; - u32 status; if (!(host->caps & MMC_CAP_HW_RESET) || !host->ops->hw_reset) return -EOPNOTSUPP; @@ -1937,12 +1936,6 @@ static int mmc_reset(struct mmc_host *host) host->ops->hw_reset(host); - /* If the reset has happened, then a status command will fail */ - if (!mmc_send_status(card, &status)) { - mmc_host_clk_release(host); - return -ENOSYS; - } - /* Set initial state and call mmc_set_ios */ mmc_set_initial_state(host); mmc_host_clk_release(host); diff --git a/drivers/net/can/sja1000/peak_pci.c b/drivers/net/can/sja1000/peak_pci.c index e5fac368068a..131026fbc2d7 100644 --- a/drivers/net/can/sja1000/peak_pci.c +++ b/drivers/net/can/sja1000/peak_pci.c @@ -87,6 +87,7 @@ static const struct pci_device_id peak_pci_tbl[] = { {PEAK_PCI_VENDOR_ID, PEAK_PC_104P_DEVICE_ID, PCI_ANY_ID, PCI_ANY_ID,}, {PEAK_PCI_VENDOR_ID, PEAK_PCI_104E_DEVICE_ID, PCI_ANY_ID, PCI_ANY_ID,}, {PEAK_PCI_VENDOR_ID, PEAK_CPCI_DEVICE_ID, PCI_ANY_ID, PCI_ANY_ID,}, + {PEAK_PCI_VENDOR_ID, PEAK_PCIE_OEM_ID, PCI_ANY_ID, PCI_ANY_ID,}, #ifdef CONFIG_CAN_PEAK_PCIEC {PEAK_PCI_VENDOR_ID, PEAK_PCIEC_DEVICE_ID, PCI_ANY_ID, PCI_ANY_ID,}, {PEAK_PCI_VENDOR_ID, PEAK_PCIEC34_DEVICE_ID, PCI_ANY_ID, PCI_ANY_ID,}, diff --git a/drivers/net/ethernet/allwinner/sun4i-emac.c b/drivers/net/ethernet/allwinner/sun4i-emac.c index 48ce83e443c2..8d50314ac3eb 100644 --- a/drivers/net/ethernet/allwinner/sun4i-emac.c +++ b/drivers/net/ethernet/allwinner/sun4i-emac.c @@ -847,21 +847,25 @@ static int emac_probe(struct platform_device *pdev) if (ndev->irq == -ENXIO) { netdev_err(ndev, "No irq resource\n"); ret = ndev->irq; - goto out; + goto out_iounmap; } db->clk = devm_clk_get(&pdev->dev, NULL); if (IS_ERR(db->clk)) { ret = PTR_ERR(db->clk); - goto out; + goto out_iounmap; } - clk_prepare_enable(db->clk); + ret = clk_prepare_enable(db->clk); + if (ret) { + dev_err(&pdev->dev, "Error couldn't enable clock (%d)\n", ret); + goto out_iounmap; + } ret = sunxi_sram_claim(&pdev->dev); if (ret) { dev_err(&pdev->dev, "Error couldn't map SRAM to device\n"); - goto out; + goto out_clk_disable_unprepare; } db->phy_node = of_parse_phandle(np, "phy", 0); @@ -910,6 +914,10 @@ static int emac_probe(struct platform_device *pdev) out_release_sram: sunxi_sram_release(&pdev->dev); +out_clk_disable_unprepare: + clk_disable_unprepare(db->clk); +out_iounmap: + iounmap(db->membase); out: dev_err(db->dev, "not found (%d).\n", ret); @@ -921,8 +929,12 @@ out: static int emac_remove(struct platform_device *pdev) { struct net_device *ndev = platform_get_drvdata(pdev); + struct emac_board_info *db = netdev_priv(ndev); unregister_netdev(ndev); + sunxi_sram_release(&pdev->dev); + clk_disable_unprepare(db->clk); + iounmap(db->membase); free_netdev(ndev); dev_dbg(&pdev->dev, "released and freed device\n"); diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-debugfs.c b/drivers/net/ethernet/amd/xgbe/xgbe-debugfs.c index 2c063b60db4b..96f485ab612e 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-debugfs.c +++ b/drivers/net/ethernet/amd/xgbe/xgbe-debugfs.c @@ -327,9 +327,13 @@ void xgbe_debugfs_init(struct xgbe_prv_data *pdata) pdata->debugfs_xpcs_reg = 0; buf = kasprintf(GFP_KERNEL, "amd-xgbe-%s", pdata->netdev->name); + if (!buf) + return; + pdata->xgbe_debugfs = debugfs_create_dir(buf, NULL); if (!pdata->xgbe_debugfs) { netdev_err(pdata->netdev, "debugfs_create_dir failed\n"); + kfree(buf); return; } diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-dev.c b/drivers/net/ethernet/amd/xgbe/xgbe-dev.c index a4473d8ff4fa..f672dba345f7 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-dev.c +++ b/drivers/net/ethernet/amd/xgbe/xgbe-dev.c @@ -1595,7 +1595,7 @@ static void xgbe_dev_xmit(struct xgbe_channel *channel) packet->rdesc_count, 1); /* Make sure ownership is written to the descriptor */ - dma_wmb(); + smp_wmb(); ring->cur = cur_index + 1; if (!packet->skb->xmit_more || diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c index aae9d5ecd182..dde0486667e0 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c +++ b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c @@ -1807,6 +1807,7 @@ static int xgbe_tx_poll(struct xgbe_channel *channel) struct netdev_queue *txq; int processed = 0; unsigned int tx_packets = 0, tx_bytes = 0; + unsigned int cur; DBGPR("-->xgbe_tx_poll\n"); @@ -1814,10 +1815,15 @@ static int xgbe_tx_poll(struct xgbe_channel *channel) if (!ring) return 0; + cur = ring->cur; + + /* Be sure we get ring->cur before accessing descriptor data */ + smp_rmb(); + txq = netdev_get_tx_queue(netdev, channel->queue_index); while ((processed < XGBE_TX_DESC_MAX_PROC) && - (ring->dirty != ring->cur)) { + (ring->dirty != cur)) { rdata = XGBE_GET_DESC_DATA(ring, ring->dirty); rdesc = rdata->rdesc; diff --git a/drivers/net/ethernet/broadcom/bcm63xx_enet.c b/drivers/net/ethernet/broadcom/bcm63xx_enet.c index a7f2cc3e485e..4183c2abeeeb 100644 --- a/drivers/net/ethernet/broadcom/bcm63xx_enet.c +++ b/drivers/net/ethernet/broadcom/bcm63xx_enet.c @@ -2049,7 +2049,7 @@ static void swphy_poll_timer(unsigned long data) for (i = 0; i < priv->num_ports; i++) { struct bcm63xx_enetsw_port *port; - int val, j, up, advertise, lpa, lpa2, speed, duplex, media; + int val, j, up, advertise, lpa, speed, duplex, media; int external_phy = bcm_enet_port_is_rgmii(i); u8 override; @@ -2092,22 +2092,27 @@ static void swphy_poll_timer(unsigned long data) lpa = bcmenet_sw_mdio_read(priv, external_phy, port->phy_id, MII_LPA); - lpa2 = bcmenet_sw_mdio_read(priv, external_phy, port->phy_id, - MII_STAT1000); - /* figure out media and duplex from advertise and LPA values */ media = mii_nway_result(lpa & advertise); duplex = (media & ADVERTISE_FULL) ? 1 : 0; - if (lpa2 & LPA_1000FULL) - duplex = 1; - - if (lpa2 & (LPA_1000FULL | LPA_1000HALF)) - speed = 1000; - else { - if (media & (ADVERTISE_100FULL | ADVERTISE_100HALF)) - speed = 100; - else - speed = 10; + + if (media & (ADVERTISE_100FULL | ADVERTISE_100HALF)) + speed = 100; + else + speed = 10; + + if (val & BMSR_ESTATEN) { + advertise = bcmenet_sw_mdio_read(priv, external_phy, + port->phy_id, MII_CTRL1000); + + lpa = bcmenet_sw_mdio_read(priv, external_phy, + port->phy_id, MII_STAT1000); + + if (advertise & (ADVERTISE_1000FULL | ADVERTISE_1000HALF) + && lpa & (LPA_1000FULL | LPA_1000HALF)) { + speed = 1000; + duplex = (lpa & LPA_1000FULL); + } } dev_info(&priv->pdev->dev, diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c index aeb7ce64452e..be628bd9fb18 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c @@ -3351,6 +3351,13 @@ static int bnx2x_set_rss_flags(struct bnx2x *bp, struct ethtool_rxnfc *info) udp_rss_requested = 0; else return -EINVAL; + + if (CHIP_IS_E1x(bp) && udp_rss_requested) { + DP(BNX2X_MSG_ETHTOOL, + "57710, 57711 boards don't support RSS according to UDP 4-tuple\n"); + return -EINVAL; + } + if ((info->flow_type == UDP_V4_FLOW) && (bp->rss_conf_obj.udp_rss_v4 != udp_rss_requested)) { bp->rss_conf_obj.udp_rss_v4 = udp_rss_requested; diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c index 3bc701e4c59e..1805541b4240 100644 --- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c +++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c @@ -1683,6 +1683,24 @@ static void bcmgenet_intr_disable(struct bcmgenet_priv *priv) bcmgenet_intrl2_1_writel(priv, 0, INTRL2_CPU_MASK_CLEAR); } +static void bcmgenet_link_intr_enable(struct bcmgenet_priv *priv) +{ + u32 int0_enable = 0; + + /* Monitor cable plug/unplugged event for internal PHY, external PHY + * and MoCA PHY + */ + if (priv->internal_phy) { + int0_enable |= UMAC_IRQ_LINK_EVENT; + } else if (priv->ext_phy) { + int0_enable |= UMAC_IRQ_LINK_EVENT; + } else if (priv->phy_interface == PHY_INTERFACE_MODE_MOCA) { + if (priv->hw_params->flags & GENET_HAS_MOCA_LINK_DET) + int0_enable |= UMAC_IRQ_LINK_EVENT; + } + bcmgenet_intrl2_0_writel(priv, int0_enable, INTRL2_CPU_MASK_CLEAR); +} + static int init_umac(struct bcmgenet_priv *priv) { struct device *kdev = &priv->pdev->dev; @@ -1723,15 +1741,8 @@ static int init_umac(struct bcmgenet_priv *priv) /* Enable Tx default queue 16 interrupts */ int0_enable |= UMAC_IRQ_TXDMA_DONE; - /* Monitor cable plug/unplugged event for internal PHY */ - if (priv->internal_phy) { - int0_enable |= UMAC_IRQ_LINK_EVENT; - } else if (priv->ext_phy) { - int0_enable |= UMAC_IRQ_LINK_EVENT; - } else if (priv->phy_interface == PHY_INTERFACE_MODE_MOCA) { - if (priv->hw_params->flags & GENET_HAS_MOCA_LINK_DET) - int0_enable |= UMAC_IRQ_LINK_EVENT; - + /* Configure backpressure vectors for MoCA */ + if (priv->phy_interface == PHY_INTERFACE_MODE_MOCA) { reg = bcmgenet_bp_mc_get(priv); reg |= BIT(priv->hw_params->bp_in_en_shift); @@ -2645,6 +2656,9 @@ static void bcmgenet_netif_start(struct net_device *dev) netif_tx_start_all_queues(dev); + /* Monitor link interrupts now */ + bcmgenet_link_intr_enable(priv); + phy_start(priv->phydev); } diff --git a/drivers/net/ethernet/cavium/Kconfig b/drivers/net/ethernet/cavium/Kconfig index 9b35d142f47a..8fb84e69c30e 100644 --- a/drivers/net/ethernet/cavium/Kconfig +++ b/drivers/net/ethernet/cavium/Kconfig @@ -3,7 +3,7 @@ # config NET_VENDOR_CAVIUM - tristate "Cavium ethernet drivers" + bool "Cavium ethernet drivers" depends on PCI default y ---help--- diff --git a/drivers/net/ethernet/cavium/thunder/nic_main.c b/drivers/net/ethernet/cavium/thunder/nic_main.c index b3a5947a2cc0..c561fdcb79a7 100644 --- a/drivers/net/ethernet/cavium/thunder/nic_main.c +++ b/drivers/net/ethernet/cavium/thunder/nic_main.c @@ -22,7 +22,6 @@ struct nicpf { struct pci_dev *pdev; - u8 rev_id; u8 node; unsigned int flags; u8 num_vf_en; /* No of VF enabled */ @@ -44,6 +43,7 @@ struct nicpf { u8 duplex[MAX_LMAC]; u32 speed[MAX_LMAC]; u16 cpi_base[MAX_NUM_VFS_SUPPORTED]; + u16 rssi_base[MAX_NUM_VFS_SUPPORTED]; u16 rss_ind_tbl_size; bool mbx_lock[MAX_NUM_VFS_SUPPORTED]; @@ -54,6 +54,11 @@ struct nicpf { bool irq_allocated[NIC_PF_MSIX_VECTORS]; }; +static inline bool pass1_silicon(struct nicpf *nic) +{ + return nic->pdev->revision < 8; +} + /* Supported devices */ static const struct pci_device_id nic_id_table[] = { { PCI_DEVICE(PCI_VENDOR_ID_CAVIUM, PCI_DEVICE_ID_THUNDER_NIC_PF) }, @@ -117,7 +122,7 @@ static void nic_send_msg_to_vf(struct nicpf *nic, int vf, union nic_mbx *mbx) * when PF writes to MBOX(1), in next revisions when * PF writes to MBOX(0) */ - if (nic->rev_id == 0) { + if (pass1_silicon(nic)) { /* see the comment for nic_reg_write()/nic_reg_read() * functions above */ @@ -305,9 +310,6 @@ static void nic_init_hw(struct nicpf *nic) { int i; - /* Reset NIC, in case the driver is repeatedly inserted and removed */ - nic_reg_write(nic, NIC_PF_SOFT_RESET, 1); - /* Enable NIC HW block */ nic_reg_write(nic, NIC_PF_CFG, 0x3); @@ -395,8 +397,18 @@ static void nic_config_cpi(struct nicpf *nic, struct cpi_cfg_msg *cfg) padd = cpi % 8; /* 3 bits CS out of 6bits DSCP */ /* Leave RSS_SIZE as '0' to disable RSS */ - nic_reg_write(nic, NIC_PF_CPI_0_2047_CFG | (cpi << 3), - (vnic << 24) | (padd << 16) | (rssi_base + rssi)); + if (pass1_silicon(nic)) { + nic_reg_write(nic, NIC_PF_CPI_0_2047_CFG | (cpi << 3), + (vnic << 24) | (padd << 16) | + (rssi_base + rssi)); + } else { + /* Set MPI_ALG to '0' to disable MCAM parsing */ + nic_reg_write(nic, NIC_PF_CPI_0_2047_CFG | (cpi << 3), + (padd << 16)); + /* MPI index is same as CPI if MPI_ALG is not enabled */ + nic_reg_write(nic, NIC_PF_MPI_0_2047_CFG | (cpi << 3), + (vnic << 24) | (rssi_base + rssi)); + } if ((rssi + 1) >= cfg->rq_cnt) continue; @@ -409,6 +421,7 @@ static void nic_config_cpi(struct nicpf *nic, struct cpi_cfg_msg *cfg) rssi = ((cpi - cpi_base) & 0x38) >> 3; } nic->cpi_base[cfg->vf_id] = cpi_base; + nic->rssi_base[cfg->vf_id] = rssi_base; } /* Responsds to VF with its RSS indirection table size */ @@ -434,10 +447,9 @@ static void nic_config_rss(struct nicpf *nic, struct rss_cfg_msg *cfg) { u8 qset, idx = 0; u64 cpi_cfg, cpi_base, rssi_base, rssi; + u64 idx_addr; - cpi_base = nic->cpi_base[cfg->vf_id]; - cpi_cfg = nic_reg_read(nic, NIC_PF_CPI_0_2047_CFG | (cpi_base << 3)); - rssi_base = (cpi_cfg & 0x0FFF) + cfg->tbl_offset; + rssi_base = nic->rssi_base[cfg->vf_id] + cfg->tbl_offset; rssi = rssi_base; qset = cfg->vf_id; @@ -454,9 +466,15 @@ static void nic_config_rss(struct nicpf *nic, struct rss_cfg_msg *cfg) idx++; } + cpi_base = nic->cpi_base[cfg->vf_id]; + if (pass1_silicon(nic)) + idx_addr = NIC_PF_CPI_0_2047_CFG; + else + idx_addr = NIC_PF_MPI_0_2047_CFG; + cpi_cfg = nic_reg_read(nic, idx_addr | (cpi_base << 3)); cpi_cfg &= ~(0xFULL << 20); cpi_cfg |= (cfg->hash_bits << 20); - nic_reg_write(nic, NIC_PF_CPI_0_2047_CFG | (cpi_base << 3), cpi_cfg); + nic_reg_write(nic, idx_addr | (cpi_base << 3), cpi_cfg); } /* 4 level transmit side scheduler configutation @@ -1001,8 +1019,6 @@ static int nic_probe(struct pci_dev *pdev, const struct pci_device_id *ent) goto err_release_regions; } - pci_read_config_byte(pdev, PCI_REVISION_ID, &nic->rev_id); - nic->node = nic_get_node_id(pdev); nic_set_lmac_vf_mapping(nic); diff --git a/drivers/net/ethernet/cavium/thunder/nic_reg.h b/drivers/net/ethernet/cavium/thunder/nic_reg.h index 58197bb2f805..dd536be20193 100644 --- a/drivers/net/ethernet/cavium/thunder/nic_reg.h +++ b/drivers/net/ethernet/cavium/thunder/nic_reg.h @@ -85,7 +85,11 @@ #define NIC_PF_ECC3_DBE_INT_W1S (0x2708) #define NIC_PF_ECC3_DBE_ENA_W1C (0x2710) #define NIC_PF_ECC3_DBE_ENA_W1S (0x2718) +#define NIC_PF_MCAM_0_191_ENA (0x100000) +#define NIC_PF_MCAM_0_191_M_0_5_DATA (0x110000) +#define NIC_PF_MCAM_CTRL (0x120000) #define NIC_PF_CPI_0_2047_CFG (0x200000) +#define NIC_PF_MPI_0_2047_CFG (0x210000) #define NIC_PF_RSSI_0_4097_RQ (0x220000) #define NIC_PF_LMAC_0_7_CFG (0x240000) #define NIC_PF_LMAC_0_7_SW_XOFF (0x242000) diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_main.c b/drivers/net/ethernet/cavium/thunder/nicvf_main.c index b63e579aeb12..a9377727c11c 100644 --- a/drivers/net/ethernet/cavium/thunder/nicvf_main.c +++ b/drivers/net/ethernet/cavium/thunder/nicvf_main.c @@ -29,7 +29,7 @@ static const struct pci_device_id nicvf_id_table[] = { { PCI_DEVICE_SUB(PCI_VENDOR_ID_CAVIUM, PCI_DEVICE_ID_THUNDER_NIC_VF, - PCI_VENDOR_ID_CAVIUM, 0xA11E) }, + PCI_VENDOR_ID_CAVIUM, 0xA134) }, { PCI_DEVICE_SUB(PCI_VENDOR_ID_CAVIUM, PCI_DEVICE_ID_THUNDER_PASS1_NIC_VF, PCI_VENDOR_ID_CAVIUM, 0xA11E) }, diff --git a/drivers/net/ethernet/cavium/thunder/thunder_bgx.c b/drivers/net/ethernet/cavium/thunder/thunder_bgx.c index 574c49278900..180aa9fabf48 100644 --- a/drivers/net/ethernet/cavium/thunder/thunder_bgx.c +++ b/drivers/net/ethernet/cavium/thunder/thunder_bgx.c @@ -977,8 +977,10 @@ static int bgx_init_of_phy(struct bgx *bgx) SET_NETDEV_DEV(&bgx->lmac[lmac].netdev, &bgx->pdev->dev); bgx->lmac[lmac].lmacid = lmac; lmac++; - if (lmac == MAX_LMAC_PER_BGX) + if (lmac == MAX_LMAC_PER_BGX) { + of_node_put(np_child); break; + } } return 0; } diff --git a/drivers/net/ethernet/emulex/benet/be.h b/drivers/net/ethernet/emulex/benet/be.h index 821540913343..d463563e1f70 100644 --- a/drivers/net/ethernet/emulex/benet/be.h +++ b/drivers/net/ethernet/emulex/benet/be.h @@ -592,6 +592,7 @@ struct be_adapter { int be_get_temp_freq; struct be_hwmon hwmon_info; u8 pf_number; + u8 pci_func_num; struct rss_info rss_info; /* Filters for packets that need to be sent to BMC */ u32 bmc_filt_mask; diff --git a/drivers/net/ethernet/emulex/benet/be_cmds.c b/drivers/net/ethernet/emulex/benet/be_cmds.c index eb323913cd39..1795c935ff02 100644 --- a/drivers/net/ethernet/emulex/benet/be_cmds.c +++ b/drivers/net/ethernet/emulex/benet/be_cmds.c @@ -851,8 +851,10 @@ static int be_cmd_notify_wait(struct be_adapter *adapter, return status; dest_wrb = be_cmd_copy(adapter, wrb); - if (!dest_wrb) - return -EBUSY; + if (!dest_wrb) { + status = -EBUSY; + goto unlock; + } if (use_mcc(adapter)) status = be_mcc_notify_wait(adapter); @@ -862,6 +864,7 @@ static int be_cmd_notify_wait(struct be_adapter *adapter, if (!status) memcpy(wrb, dest_wrb, sizeof(*wrb)); +unlock: be_cmd_unlock(adapter); return status; } @@ -1984,6 +1987,8 @@ int be_cmd_rx_filter(struct be_adapter *adapter, u32 flags, u32 value) be_if_cap_flags(adapter)); } flags &= be_if_cap_flags(adapter); + if (!flags) + return -ENOTSUPP; return __be_cmd_rx_filter(adapter, flags, value); } @@ -2887,6 +2892,7 @@ int be_cmd_get_cntl_attributes(struct be_adapter *adapter) if (!status) { attribs = attribs_cmd.va + sizeof(struct be_cmd_resp_hdr); adapter->hba_port_num = attribs->hba_attribs.phy_port; + adapter->pci_func_num = attribs->pci_func_num; serial_num = attribs->hba_attribs.controller_serial_number; for (i = 0; i < CNTL_SERIAL_NUM_WORDS; i++) adapter->serial_num[i] = le32_to_cpu(serial_num[i]) & @@ -3709,7 +3715,6 @@ int be_cmd_get_func_config(struct be_adapter *adapter, struct be_resources *res) status = -EINVAL; goto err; } - adapter->pf_number = desc->pf_num; be_copy_nic_desc(res, desc); } @@ -3721,7 +3726,10 @@ err: return status; } -/* Will use MBOX only if MCCQ has not been created */ +/* Will use MBOX only if MCCQ has not been created + * non-zero domain => a PF is querying this on behalf of a VF + * zero domain => a PF or a VF is querying this for itself + */ int be_cmd_get_profile_config(struct be_adapter *adapter, struct be_resources *res, u8 query, u8 domain) { @@ -3748,10 +3756,15 @@ int be_cmd_get_profile_config(struct be_adapter *adapter, OPCODE_COMMON_GET_PROFILE_CONFIG, cmd.size, &wrb, &cmd); - req->hdr.domain = domain; if (!lancer_chip(adapter)) req->hdr.version = 1; req->type = ACTIVE_PROFILE_TYPE; + /* When a function is querying profile information relating to + * itself hdr.pf_number must be set to it's pci_func_num + 1 + */ + req->hdr.domain = domain; + if (domain == 0) + req->hdr.pf_num = adapter->pci_func_num + 1; /* When QUERY_MODIFIABLE_FIELDS_TYPE bit is set, cmd returns the * descriptors with all bits set to "1" for the fields which can be @@ -3921,12 +3934,16 @@ static void be_fill_vf_res_template(struct be_adapter *adapter, vf_if_cap_flags &= ~(BE_IF_FLAGS_RSS | BE_IF_FLAGS_DEFQ_RSS); } - - nic_vft->cap_flags = cpu_to_le32(vf_if_cap_flags); } else { num_vf_qs = 1; } + if (res_mod.vf_if_cap_flags & BE_IF_FLAGS_VLAN_PROMISCUOUS) { + nic_vft->flags |= BIT(IF_CAPS_FLAGS_VALID_SHIFT); + vf_if_cap_flags &= ~BE_IF_FLAGS_VLAN_PROMISCUOUS; + } + + nic_vft->cap_flags = cpu_to_le32(vf_if_cap_flags); nic_vft->rq_count = cpu_to_le16(num_vf_qs); nic_vft->txq_count = cpu_to_le16(num_vf_qs); nic_vft->rssq_count = cpu_to_le16(num_vf_qs); diff --git a/drivers/net/ethernet/emulex/benet/be_cmds.h b/drivers/net/ethernet/emulex/benet/be_cmds.h index 7d178bdb112e..91155ea74f34 100644 --- a/drivers/net/ethernet/emulex/benet/be_cmds.h +++ b/drivers/net/ethernet/emulex/benet/be_cmds.h @@ -289,7 +289,9 @@ struct be_cmd_req_hdr { u32 timeout; /* dword 1 */ u32 request_length; /* dword 2 */ u8 version; /* dword 3 */ - u8 rsvd[3]; /* dword 3 */ + u8 rsvd1; /* dword 3 */ + u8 pf_num; /* dword 3 */ + u8 rsvd2; /* dword 3 */ }; #define RESP_HDR_INFO_OPCODE_SHIFT 0 /* bits 0 - 7 */ @@ -1652,7 +1654,11 @@ struct mgmt_hba_attribs { struct mgmt_controller_attrib { struct mgmt_hba_attribs hba_attribs; - u32 rsvd0[10]; + u32 rsvd0[2]; + u16 rsvd1; + u8 pci_func_num; + u8 rsvd2; + u32 rsvd3[7]; } __packed; struct be_cmd_req_cntl_attribs { diff --git a/drivers/net/ethernet/emulex/benet/be_main.c b/drivers/net/ethernet/emulex/benet/be_main.c index 7bf51a1a0a77..eb48a977f8da 100644 --- a/drivers/net/ethernet/emulex/benet/be_main.c +++ b/drivers/net/ethernet/emulex/benet/be_main.c @@ -1123,11 +1123,12 @@ static struct sk_buff *be_xmit_workarounds(struct be_adapter *adapter, struct sk_buff *skb, struct be_wrb_params *wrb_params) { - /* Lancer, SH-R ASICs have a bug wherein Packets that are 32 bytes or - * less may cause a transmit stall on that port. So the work-around is - * to pad short packets (<= 32 bytes) to a 36-byte length. + /* Lancer, SH and BE3 in SRIOV mode have a bug wherein + * packets that are 32b or less may cause a transmit stall + * on that port. The workaround is to pad such packets + * (len <= 32 bytes) to a minimum length of 36b. */ - if (unlikely(!BEx_chip(adapter) && skb->len <= 32)) { + if (skb->len <= 32) { if (skb_put_padto(skb, 36)) return NULL; } @@ -4205,10 +4206,6 @@ static int be_get_config(struct be_adapter *adapter) int status, level; u16 profile_id; - status = be_cmd_get_cntl_attributes(adapter); - if (status) - return status; - status = be_cmd_query_fw_cfg(adapter); if (status) return status; @@ -4407,6 +4404,11 @@ static int be_setup(struct be_adapter *adapter) if (!lancer_chip(adapter)) be_cmd_req_native_mode(adapter); + /* Need to invoke this cmd first to get the PCI Function Number */ + status = be_cmd_get_cntl_attributes(adapter); + if (status) + return status; + if (!BE2_chip(adapter) && be_physfn(adapter)) be_alloc_sriov_res(adapter); @@ -4999,7 +5001,15 @@ static bool be_check_ufi_compatibility(struct be_adapter *adapter, return false; } - return (fhdr->asic_type_rev >= adapter->asic_rev); + /* In BE3 FW images the "asic_type_rev" field doesn't track the + * asic_rev of the chips it is compatible with. + * When asic_type_rev is 0 the image is compatible only with + * pre-BE3-R chips (asic_rev < 0x10) + */ + if (BEx_chip(adapter) && fhdr->asic_type_rev == 0) + return adapter->asic_rev < 0x10; + else + return (fhdr->asic_type_rev >= adapter->asic_rev); } static int be_fw_download(struct be_adapter *adapter, const struct firmware* fw) diff --git a/drivers/net/ethernet/freescale/fsl_pq_mdio.c b/drivers/net/ethernet/freescale/fsl_pq_mdio.c index 3c40f6b99224..55c36230e176 100644 --- a/drivers/net/ethernet/freescale/fsl_pq_mdio.c +++ b/drivers/net/ethernet/freescale/fsl_pq_mdio.c @@ -198,11 +198,13 @@ static int fsl_pq_mdio_reset(struct mii_bus *bus) #if defined(CONFIG_GIANFAR) || defined(CONFIG_GIANFAR_MODULE) /* + * Return the TBIPA address, starting from the address + * of the mapped GFAR MDIO registers (struct gfar) * This is mildly evil, but so is our hardware for doing this. * Also, we have to cast back to struct gfar because of * definition weirdness done in gianfar.h. */ -static uint32_t __iomem *get_gfar_tbipa(void __iomem *p) +static uint32_t __iomem *get_gfar_tbipa_from_mdio(void __iomem *p) { struct gfar __iomem *enet_regs = p; @@ -210,6 +212,15 @@ static uint32_t __iomem *get_gfar_tbipa(void __iomem *p) } /* + * Return the TBIPA address, starting from the address + * of the mapped GFAR MII registers (gfar_mii_regs[] within struct gfar) + */ +static uint32_t __iomem *get_gfar_tbipa_from_mii(void __iomem *p) +{ + return get_gfar_tbipa_from_mdio(container_of(p, struct gfar, gfar_mii_regs)); +} + +/* * Return the TBIPAR address for an eTSEC2 node */ static uint32_t __iomem *get_etsec_tbipa(void __iomem *p) @@ -220,11 +231,12 @@ static uint32_t __iomem *get_etsec_tbipa(void __iomem *p) #if defined(CONFIG_UCC_GETH) || defined(CONFIG_UCC_GETH_MODULE) /* - * Return the TBIPAR address for a QE MDIO node + * Return the TBIPAR address for a QE MDIO node, starting from the address + * of the mapped MII registers (struct fsl_pq_mii) */ static uint32_t __iomem *get_ucc_tbipa(void __iomem *p) { - struct fsl_pq_mdio __iomem *mdio = p; + struct fsl_pq_mdio __iomem *mdio = container_of(p, struct fsl_pq_mdio, mii); return &mdio->utbipar; } @@ -300,14 +312,14 @@ static const struct of_device_id fsl_pq_mdio_match[] = { .compatible = "fsl,gianfar-tbi", .data = &(struct fsl_pq_mdio_data) { .mii_offset = 0, - .get_tbipa = get_gfar_tbipa, + .get_tbipa = get_gfar_tbipa_from_mii, }, }, { .compatible = "fsl,gianfar-mdio", .data = &(struct fsl_pq_mdio_data) { .mii_offset = 0, - .get_tbipa = get_gfar_tbipa, + .get_tbipa = get_gfar_tbipa_from_mii, }, }, { @@ -315,7 +327,7 @@ static const struct of_device_id fsl_pq_mdio_match[] = { .compatible = "gianfar", .data = &(struct fsl_pq_mdio_data) { .mii_offset = offsetof(struct fsl_pq_mdio, mii), - .get_tbipa = get_gfar_tbipa, + .get_tbipa = get_gfar_tbipa_from_mdio, }, }, { @@ -445,6 +457,16 @@ static int fsl_pq_mdio_probe(struct platform_device *pdev) tbipa = data->get_tbipa(priv->map); + /* + * Add consistency check to make sure TBI is contained + * within the mapped range (not because we would get a + * segfault, rather to catch bugs in computing TBI + * address). Print error message but continue anyway. + */ + if ((void *)tbipa > priv->map + resource_size(&res) - 4) + dev_err(&pdev->dev, "invalid register map (should be at least 0x%04x to contain TBI address)\n", + ((void *)tbipa - priv->map) + 4); + iowrite32be(be32_to_cpup(prop), tbipa); } } diff --git a/drivers/net/ethernet/freescale/gianfar.c b/drivers/net/ethernet/freescale/gianfar.c index 710715fcb23d..ce38d266f931 100644 --- a/drivers/net/ethernet/freescale/gianfar.c +++ b/drivers/net/ethernet/freescale/gianfar.c @@ -341,7 +341,7 @@ static void gfar_rx_offload_en(struct gfar_private *priv) if (priv->ndev->features & (NETIF_F_RXCSUM | NETIF_F_HW_VLAN_CTAG_RX)) priv->uses_rxfcb = 1; - if (priv->hwts_rx_en) + if (priv->hwts_rx_en || priv->rx_filer_enable) priv->uses_rxfcb = 1; } @@ -351,7 +351,7 @@ static void gfar_mac_rx_config(struct gfar_private *priv) u32 rctrl = 0; if (priv->rx_filer_enable) { - rctrl |= RCTRL_FILREN; + rctrl |= RCTRL_FILREN | RCTRL_PRSDEP_INIT; /* Program the RIR0 reg with the required distribution */ if (priv->poll_mode == GFAR_SQ_POLLING) gfar_write(®s->rir0, DEFAULT_2RXQ_RIR0); @@ -3462,11 +3462,9 @@ static irqreturn_t gfar_error(int irq, void *grp_id) netif_dbg(priv, tx_err, dev, "Transmit Error\n"); } if (events & IEVENT_BSY) { - dev->stats.rx_errors++; + dev->stats.rx_over_errors++; atomic64_inc(&priv->extra_stats.rx_bsy); - gfar_receive(irq, grp_id); - netif_dbg(priv, rx_err, dev, "busy error (rstat: %x)\n", gfar_read(®s->rstat)); } diff --git a/drivers/net/ethernet/freescale/gianfar_ethtool.c b/drivers/net/ethernet/freescale/gianfar_ethtool.c index 6bdc89179b72..a33e4a829601 100644 --- a/drivers/net/ethernet/freescale/gianfar_ethtool.c +++ b/drivers/net/ethernet/freescale/gianfar_ethtool.c @@ -676,14 +676,14 @@ static void ethflow_to_filer_rules (struct gfar_private *priv, u64 ethflow) u32 fcr = 0x0, fpr = FPR_FILER_MASK; if (ethflow & RXH_L2DA) { - fcr = RQFCR_PID_DAH |RQFCR_CMP_NOMATCH | + fcr = RQFCR_PID_DAH | RQFCR_CMP_NOMATCH | RQFCR_HASH | RQFCR_AND | RQFCR_HASHTBL_0; priv->ftp_rqfpr[priv->cur_filer_idx] = fpr; priv->ftp_rqfcr[priv->cur_filer_idx] = fcr; gfar_write_filer(priv, priv->cur_filer_idx, fcr, fpr); priv->cur_filer_idx = priv->cur_filer_idx - 1; - fcr = RQFCR_PID_DAL | RQFCR_AND | RQFCR_CMP_NOMATCH | + fcr = RQFCR_PID_DAL | RQFCR_CMP_NOMATCH | RQFCR_HASH | RQFCR_AND | RQFCR_HASHTBL_0; priv->ftp_rqfpr[priv->cur_filer_idx] = fpr; priv->ftp_rqfcr[priv->cur_filer_idx] = fcr; diff --git a/drivers/net/ethernet/intel/i40e/i40e_adminq.c b/drivers/net/ethernet/intel/i40e/i40e_adminq.c index 62488a67149d..c0e943aecd13 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_adminq.c +++ b/drivers/net/ethernet/intel/i40e/i40e_adminq.c @@ -386,7 +386,6 @@ static i40e_status i40e_init_asq(struct i40e_hw *hw) hw->aq.asq.next_to_use = 0; hw->aq.asq.next_to_clean = 0; - hw->aq.asq.count = hw->aq.num_asq_entries; /* allocate the ring memory */ ret_code = i40e_alloc_adminq_asq_ring(hw); @@ -404,6 +403,7 @@ static i40e_status i40e_init_asq(struct i40e_hw *hw) goto init_adminq_free_rings; /* success! */ + hw->aq.asq.count = hw->aq.num_asq_entries; goto init_adminq_exit; init_adminq_free_rings: @@ -445,7 +445,6 @@ static i40e_status i40e_init_arq(struct i40e_hw *hw) hw->aq.arq.next_to_use = 0; hw->aq.arq.next_to_clean = 0; - hw->aq.arq.count = hw->aq.num_arq_entries; /* allocate the ring memory */ ret_code = i40e_alloc_adminq_arq_ring(hw); @@ -463,6 +462,7 @@ static i40e_status i40e_init_arq(struct i40e_hw *hw) goto init_adminq_free_rings; /* success! */ + hw->aq.arq.count = hw->aq.num_arq_entries; goto init_adminq_exit; init_adminq_free_rings: diff --git a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c index e972b5ecbf0b..13a5d4cf494b 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c +++ b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c @@ -1344,6 +1344,12 @@ static void i40e_get_ethtool_stats(struct net_device *netdev, data[i++] = (i40e_gstrings_veb_stats[j].sizeof_stat == sizeof(u64)) ? *(u64 *)p : *(u32 *)p; } + for (j = 0; j < I40E_MAX_TRAFFIC_CLASS; j++) { + data[i++] = veb->tc_stats.tc_tx_packets[j]; + data[i++] = veb->tc_stats.tc_tx_bytes[j]; + data[i++] = veb->tc_stats.tc_rx_packets[j]; + data[i++] = veb->tc_stats.tc_rx_bytes[j]; + } } for (j = 0; j < I40E_GLOBAL_STATS_LEN; j++) { p = (char *)pf + i40e_gstrings_stats[j].stat_offset; diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index 2fdf978ae6a5..3dd26cdd0bf2 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -7911,6 +7911,7 @@ static int i40e_sw_init(struct i40e_pf *pf) if (pf->hw.func_caps.vmdq) { pf->num_vmdq_vsis = I40E_DEFAULT_NUM_VMDQ_VSI; pf->flags |= I40E_FLAG_VMDQ_ENABLED; + pf->num_vmdq_qps = i40e_default_queues_per_vmdq(pf); } #ifdef I40E_FCOE @@ -8389,6 +8390,7 @@ static int i40e_config_netdev(struct i40e_vsi *vsi) netdev->hw_enc_features |= NETIF_F_IP_CSUM | NETIF_F_GSO_UDP_TUNNEL | + NETIF_F_GSO_GRE | NETIF_F_TSO; netdev->features = NETIF_F_SG | @@ -8396,6 +8398,7 @@ static int i40e_config_netdev(struct i40e_vsi *vsi) NETIF_F_SCTP_CSUM | NETIF_F_HIGHDMA | NETIF_F_GSO_UDP_TUNNEL | + NETIF_F_GSO_GRE | NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_CTAG_RX | NETIF_F_HW_VLAN_CTAG_FILTER | diff --git a/drivers/net/ethernet/intel/i40evf/i40e_adminq.c b/drivers/net/ethernet/intel/i40evf/i40e_adminq.c index 929d47152bf2..a23ebfd5cd25 100644 --- a/drivers/net/ethernet/intel/i40evf/i40e_adminq.c +++ b/drivers/net/ethernet/intel/i40evf/i40e_adminq.c @@ -373,7 +373,6 @@ static i40e_status i40e_init_asq(struct i40e_hw *hw) hw->aq.asq.next_to_use = 0; hw->aq.asq.next_to_clean = 0; - hw->aq.asq.count = hw->aq.num_asq_entries; /* allocate the ring memory */ ret_code = i40e_alloc_adminq_asq_ring(hw); @@ -391,6 +390,7 @@ static i40e_status i40e_init_asq(struct i40e_hw *hw) goto init_adminq_free_rings; /* success! */ + hw->aq.asq.count = hw->aq.num_asq_entries; goto init_adminq_exit; init_adminq_free_rings: @@ -432,7 +432,6 @@ static i40e_status i40e_init_arq(struct i40e_hw *hw) hw->aq.arq.next_to_use = 0; hw->aq.arq.next_to_clean = 0; - hw->aq.arq.count = hw->aq.num_arq_entries; /* allocate the ring memory */ ret_code = i40e_alloc_adminq_arq_ring(hw); @@ -450,6 +449,7 @@ static i40e_status i40e_init_arq(struct i40e_hw *hw) goto init_adminq_free_rings; /* success! */ + hw->aq.arq.count = hw->aq.num_arq_entries; goto init_adminq_exit; init_adminq_free_rings: diff --git a/drivers/net/ethernet/marvell/mv643xx_eth.c b/drivers/net/ethernet/marvell/mv643xx_eth.c index 960169efe636..dfb6d5f79a10 100644 --- a/drivers/net/ethernet/marvell/mv643xx_eth.c +++ b/drivers/net/ethernet/marvell/mv643xx_eth.c @@ -759,11 +759,23 @@ txq_put_data_tso(struct net_device *dev, struct tx_queue *txq, desc->l4i_chk = 0; desc->byte_cnt = length; - desc->buf_ptr = dma_map_single(dev->dev.parent, data, - length, DMA_TO_DEVICE); - if (unlikely(dma_mapping_error(dev->dev.parent, desc->buf_ptr))) { - WARN(1, "dma_map_single failed!\n"); - return -ENOMEM; + + if (length <= 8 && (uintptr_t)data & 0x7) { + /* Copy unaligned small data fragment to TSO header data area */ + memcpy(txq->tso_hdrs + txq->tx_curr_desc * TSO_HEADER_SIZE, + data, length); + desc->buf_ptr = txq->tso_hdrs_dma + + txq->tx_curr_desc * TSO_HEADER_SIZE; + } else { + /* Alignment is okay, map buffer and hand off to hardware */ + txq->tx_desc_mapping[tx_index] = DESC_DMA_MAP_SINGLE; + desc->buf_ptr = dma_map_single(dev->dev.parent, data, + length, DMA_TO_DEVICE); + if (unlikely(dma_mapping_error(dev->dev.parent, + desc->buf_ptr))) { + WARN(1, "dma_map_single failed!\n"); + return -ENOMEM; + } } cmd_sts = BUFFER_OWNED_BY_DMA; @@ -779,7 +791,8 @@ txq_put_data_tso(struct net_device *dev, struct tx_queue *txq, } static inline void -txq_put_hdr_tso(struct sk_buff *skb, struct tx_queue *txq, int length) +txq_put_hdr_tso(struct sk_buff *skb, struct tx_queue *txq, int length, + u32 *first_cmd_sts, bool first_desc) { struct mv643xx_eth_private *mp = txq_to_mp(txq); int hdr_len = skb_transport_offset(skb) + tcp_hdrlen(skb); @@ -788,6 +801,7 @@ txq_put_hdr_tso(struct sk_buff *skb, struct tx_queue *txq, int length) int ret; u32 cmd_csum = 0; u16 l4i_chk = 0; + u32 cmd_sts; tx_index = txq->tx_curr_desc; desc = &txq->tx_desc_area[tx_index]; @@ -803,9 +817,17 @@ txq_put_hdr_tso(struct sk_buff *skb, struct tx_queue *txq, int length) desc->byte_cnt = hdr_len; desc->buf_ptr = txq->tso_hdrs_dma + txq->tx_curr_desc * TSO_HEADER_SIZE; - desc->cmd_sts = cmd_csum | BUFFER_OWNED_BY_DMA | TX_FIRST_DESC | + cmd_sts = cmd_csum | BUFFER_OWNED_BY_DMA | TX_FIRST_DESC | GEN_CRC; + /* Defer updating the first command descriptor until all + * following descriptors have been written. + */ + if (first_desc) + *first_cmd_sts = cmd_sts; + else + desc->cmd_sts = cmd_sts; + txq->tx_curr_desc++; if (txq->tx_curr_desc == txq->tx_ring_size) txq->tx_curr_desc = 0; @@ -819,6 +841,8 @@ static int txq_submit_tso(struct tx_queue *txq, struct sk_buff *skb, int desc_count = 0; struct tso_t tso; int hdr_len = skb_transport_offset(skb) + tcp_hdrlen(skb); + struct tx_desc *first_tx_desc; + u32 first_cmd_sts = 0; /* Count needed descriptors */ if ((txq->tx_desc_count + tso_count_descs(skb)) >= txq->tx_ring_size) { @@ -826,11 +850,14 @@ static int txq_submit_tso(struct tx_queue *txq, struct sk_buff *skb, return -EBUSY; } + first_tx_desc = &txq->tx_desc_area[txq->tx_curr_desc]; + /* Initialize the TSO handler, and prepare the first payload */ tso_start(skb, &tso); total_len = skb->len - hdr_len; while (total_len > 0) { + bool first_desc = (desc_count == 0); char *hdr; data_left = min_t(int, skb_shinfo(skb)->gso_size, total_len); @@ -840,7 +867,8 @@ static int txq_submit_tso(struct tx_queue *txq, struct sk_buff *skb, /* prepare packet headers: MAC + IP + TCP */ hdr = txq->tso_hdrs + txq->tx_curr_desc * TSO_HEADER_SIZE; tso_build_hdr(skb, hdr, &tso, data_left, total_len == 0); - txq_put_hdr_tso(skb, txq, data_left); + txq_put_hdr_tso(skb, txq, data_left, &first_cmd_sts, + first_desc); while (data_left > 0) { int size; @@ -860,6 +888,10 @@ static int txq_submit_tso(struct tx_queue *txq, struct sk_buff *skb, __skb_queue_tail(&txq->tx_skb, skb); skb_tx_timestamp(skb); + /* ensure all other descriptors are written before first cmd_sts */ + wmb(); + first_tx_desc->cmd_sts = first_cmd_sts; + /* clear TX_END status */ mp->work_tx_end &= ~(1 << txq->index); @@ -2785,8 +2817,10 @@ static int mv643xx_eth_shared_of_probe(struct platform_device *pdev) for_each_available_child_of_node(np, pnp) { ret = mv643xx_eth_shared_of_add_port(pdev, pnp); - if (ret) + if (ret) { + of_node_put(pnp); return ret; + } } return 0; } diff --git a/drivers/net/ethernet/mellanox/mlx4/cmd.c b/drivers/net/ethernet/mellanox/mlx4/cmd.c index 0a3202047569..2177e56ed0be 100644 --- a/drivers/net/ethernet/mellanox/mlx4/cmd.c +++ b/drivers/net/ethernet/mellanox/mlx4/cmd.c @@ -2398,7 +2398,7 @@ int mlx4_multi_func_init(struct mlx4_dev *dev) } } - memset(&priv->mfunc.master.cmd_eqe, 0, dev->caps.eqe_size); + memset(&priv->mfunc.master.cmd_eqe, 0, sizeof(struct mlx4_eqe)); priv->mfunc.master.cmd_eqe.type = MLX4_EVENT_TYPE_CMD; INIT_WORK(&priv->mfunc.master.comm_work, mlx4_master_comm_channel); diff --git a/drivers/net/ethernet/mellanox/mlx4/en_tx.c b/drivers/net/ethernet/mellanox/mlx4/en_tx.c index 494e7762fdb1..4421bf5463f6 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_tx.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_tx.c @@ -964,6 +964,8 @@ netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev) tx_desc->ctrl.ins_vlan = MLX4_WQE_CTRL_INS_SVLAN; else if (vlan_proto == ETH_P_8021Q) tx_desc->ctrl.ins_vlan = MLX4_WQE_CTRL_INS_CVLAN; + else + tx_desc->ctrl.ins_vlan = 0; tx_desc->ctrl.fence_size = real_size; diff --git a/drivers/net/ethernet/mellanox/mlx4/eq.c b/drivers/net/ethernet/mellanox/mlx4/eq.c index 8e81e53c370e..603d1c3d3b2e 100644 --- a/drivers/net/ethernet/mellanox/mlx4/eq.c +++ b/drivers/net/ethernet/mellanox/mlx4/eq.c @@ -196,7 +196,7 @@ static void slave_event(struct mlx4_dev *dev, u8 slave, struct mlx4_eqe *eqe) return; } - memcpy(s_eqe, eqe, dev->caps.eqe_size - 1); + memcpy(s_eqe, eqe, sizeof(struct mlx4_eqe) - 1); s_eqe->slave_id = slave; /* ensure all information is written before setting the ownersip bit */ dma_wmb(); @@ -1364,6 +1364,10 @@ int mlx4_test_interrupts(struct mlx4_dev *dev) * and performing a NOP command */ for(i = 0; !err && (i < dev->caps.num_comp_vectors); ++i) { + /* Make sure request_irq was called */ + if (!priv->eq_table.eq[i].have_irq) + continue; + /* Temporary use polling for command completions */ mlx4_cmd_use_polling(dev); diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c index 006757f80988..cc3a9897574c 100644 --- a/drivers/net/ethernet/mellanox/mlx4/main.c +++ b/drivers/net/ethernet/mellanox/mlx4/main.c @@ -2669,14 +2669,11 @@ static void mlx4_enable_msi_x(struct mlx4_dev *dev) if (msi_x) { int nreq = dev->caps.num_ports * num_online_cpus() + 1; - bool shared_ports = false; nreq = min_t(int, dev->caps.num_eqs - dev->caps.reserved_eqs, nreq); - if (nreq > MAX_MSIX) { + if (nreq > MAX_MSIX) nreq = MAX_MSIX; - shared_ports = true; - } entries = kcalloc(nreq, sizeof *entries, GFP_KERNEL); if (!entries) @@ -2699,9 +2696,6 @@ static void mlx4_enable_msi_x(struct mlx4_dev *dev) bitmap_zero(priv->eq_table.eq[MLX4_EQ_ASYNC].actv_ports.ports, dev->caps.num_ports); - if (MLX4_IS_LEGACY_EQ_MODE(dev->caps)) - shared_ports = true; - for (i = 0; i < dev->caps.num_comp_vectors + 1; i++) { if (i == MLX4_EQ_ASYNC) continue; @@ -2709,7 +2703,7 @@ static void mlx4_enable_msi_x(struct mlx4_dev *dev) priv->eq_table.eq[i].irq = entries[i + 1 - !!(i > MLX4_EQ_ASYNC)].vector; - if (shared_ports) { + if (MLX4_IS_LEGACY_EQ_MODE(dev->caps)) { bitmap_fill(priv->eq_table.eq[i].actv_ports.ports, dev->caps.num_ports); /* We don't set affinity hint when there diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_flow_table.c b/drivers/net/ethernet/mellanox/mlx5/core/en_flow_table.c index e71563ce05d1..22d603f78273 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_flow_table.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_flow_table.c @@ -598,6 +598,8 @@ void mlx5e_enable_vlan_filter(struct mlx5e_priv *priv) return; priv->vlan.filter_disabled = false; + if (priv->netdev->flags & IFF_PROMISC) + return; mlx5e_del_vlan_rule(priv, MLX5E_VLAN_RULE_TYPE_ANY_VID, 0); } @@ -607,6 +609,8 @@ void mlx5e_disable_vlan_filter(struct mlx5e_priv *priv) return; priv->vlan.filter_disabled = true; + if (priv->netdev->flags & IFF_PROMISC) + return; mlx5e_add_vlan_rule(priv, MLX5E_VLAN_RULE_TYPE_ANY_VID, 0); } @@ -717,8 +721,12 @@ void mlx5e_set_rx_mode_work(struct work_struct *work) bool enable_broadcast = !ea->broadcast_enabled && broadcast_enabled; bool disable_broadcast = ea->broadcast_enabled && !broadcast_enabled; - if (enable_promisc) + if (enable_promisc) { mlx5e_add_eth_addr_rule(priv, &ea->promisc, MLX5E_PROMISC); + if (!priv->vlan.filter_disabled) + mlx5e_add_vlan_rule(priv, MLX5E_VLAN_RULE_TYPE_ANY_VID, + 0); + } if (enable_allmulti) mlx5e_add_eth_addr_rule(priv, &ea->allmulti, MLX5E_ALLMULTI); if (enable_broadcast) @@ -730,8 +738,12 @@ void mlx5e_set_rx_mode_work(struct work_struct *work) mlx5e_del_eth_addr_from_flow_table(priv, &ea->broadcast); if (disable_allmulti) mlx5e_del_eth_addr_from_flow_table(priv, &ea->allmulti); - if (disable_promisc) + if (disable_promisc) { + if (!priv->vlan.filter_disabled) + mlx5e_del_vlan_rule(priv, MLX5E_VLAN_RULE_TYPE_ANY_VID, + 0); mlx5e_del_eth_addr_from_flow_table(priv, &ea->promisc); + } ea->promisc_enabled = promisc_enabled; ea->allmulti_enabled = allmulti_enabled; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/port.c b/drivers/net/ethernet/mellanox/mlx5/core/port.c index 821caaab9bfb..3b9480fa3403 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/port.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/port.c @@ -311,7 +311,7 @@ static int mlx5_query_port_pvlc(struct mlx5_core_dev *dev, u32 *pvlc, int err; memset(in, 0, sizeof(in)); - MLX5_SET(ptys_reg, in, local_port, local_port); + MLX5_SET(pvlc_reg, in, local_port, local_port); err = mlx5_core_access_reg(dev, in, sizeof(in), pvlc, pvlc_size, MLX5_REG_PVLC, 0, 0); diff --git a/drivers/net/ethernet/mellanox/mlxsw/core.c b/drivers/net/ethernet/mellanox/mlxsw/core.c index dbcaf5df8967..28c19cc1a17c 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/core.c +++ b/drivers/net/ethernet/mellanox/mlxsw/core.c @@ -374,26 +374,31 @@ static int __mlxsw_emad_transmit(struct mlxsw_core *mlxsw_core, int err; int ret; + mlxsw_core->emad.trans_active = true; + err = mlxsw_core_skb_transmit(mlxsw_core->driver_priv, skb, tx_info); if (err) { dev_err(mlxsw_core->bus_info->dev, "Failed to transmit EMAD (tid=%llx)\n", mlxsw_core->emad.tid); dev_kfree_skb(skb); - return err; + goto trans_inactive_out; } - mlxsw_core->emad.trans_active = true; ret = wait_event_timeout(mlxsw_core->emad.wait, !(mlxsw_core->emad.trans_active), msecs_to_jiffies(MLXSW_EMAD_TIMEOUT_MS)); if (!ret) { dev_warn(mlxsw_core->bus_info->dev, "EMAD timed-out (tid=%llx)\n", mlxsw_core->emad.tid); - mlxsw_core->emad.trans_active = false; - return -EIO; + err = -EIO; + goto trans_inactive_out; } return 0; + +trans_inactive_out: + mlxsw_core->emad.trans_active = false; + return err; } static int mlxsw_emad_process_status(struct mlxsw_core *mlxsw_core, diff --git a/drivers/net/ethernet/mellanox/mlxsw/item.h b/drivers/net/ethernet/mellanox/mlxsw/item.h index ffd55d030ce2..36fb1cec53c9 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/item.h +++ b/drivers/net/ethernet/mellanox/mlxsw/item.h @@ -187,6 +187,7 @@ __mlxsw_item_bit_array_offset(struct mlxsw_item *item, u16 index, u8 *shift) { u16 max_index, be_index; u16 offset; /* byte offset inside the array */ + u8 in_byte_index; BUG_ON(index && !item->element_size); if (item->offset % sizeof(u32) != 0 || @@ -199,7 +200,8 @@ __mlxsw_item_bit_array_offset(struct mlxsw_item *item, u16 index, u8 *shift) max_index = (item->size.bytes << 3) / item->element_size - 1; be_index = max_index - index; offset = be_index * item->element_size >> 3; - *shift = index % (BITS_PER_BYTE / item->element_size) << 1; + in_byte_index = index % (BITS_PER_BYTE / item->element_size); + *shift = in_byte_index * item->element_size; return item->offset + offset; } diff --git a/drivers/net/ethernet/mellanox/mlxsw/pci.c b/drivers/net/ethernet/mellanox/mlxsw/pci.c index 462cea31ecbb..cef866c37648 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/pci.c +++ b/drivers/net/ethernet/mellanox/mlxsw/pci.c @@ -1582,11 +1582,11 @@ static int mlxsw_pci_cmd_exec(void *bus_priv, u16 opcode, u8 opcode_mod, if (in_mbox) memcpy(mlxsw_pci->cmd.in_mbox.buf, in_mbox, in_mbox_size); - mlxsw_pci_write32(mlxsw_pci, CIR_IN_PARAM_HI, in_mapaddr >> 32); - mlxsw_pci_write32(mlxsw_pci, CIR_IN_PARAM_LO, in_mapaddr); + mlxsw_pci_write32(mlxsw_pci, CIR_IN_PARAM_HI, upper_32_bits(in_mapaddr)); + mlxsw_pci_write32(mlxsw_pci, CIR_IN_PARAM_LO, lower_32_bits(in_mapaddr)); - mlxsw_pci_write32(mlxsw_pci, CIR_OUT_PARAM_HI, out_mapaddr >> 32); - mlxsw_pci_write32(mlxsw_pci, CIR_OUT_PARAM_LO, out_mapaddr); + mlxsw_pci_write32(mlxsw_pci, CIR_OUT_PARAM_HI, upper_32_bits(out_mapaddr)); + mlxsw_pci_write32(mlxsw_pci, CIR_OUT_PARAM_LO, lower_32_bits(out_mapaddr)); mlxsw_pci_write32(mlxsw_pci, CIR_IN_MODIFIER, in_mod); mlxsw_pci_write32(mlxsw_pci, CIR_TOKEN, 0); diff --git a/drivers/net/ethernet/mellanox/mlxsw/switchx2.c b/drivers/net/ethernet/mellanox/mlxsw/switchx2.c index 3e52ee93438c..62cbbd1ada8d 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/switchx2.c +++ b/drivers/net/ethernet/mellanox/mlxsw/switchx2.c @@ -1069,9 +1069,9 @@ static int mlxsw_sx_port_create(struct mlxsw_sx *mlxsw_sx, u8 local_port) return 0; err_register_netdev: -err_port_admin_status_set: err_port_mac_learning_mode_set: err_port_stp_state_set: +err_port_admin_status_set: err_port_mtu_set: err_port_speed_set: err_port_swid_set: diff --git a/drivers/net/ethernet/nvidia/forcedeth.c b/drivers/net/ethernet/nvidia/forcedeth.c index a41bb5e6b954..75e88f4c1531 100644 --- a/drivers/net/ethernet/nvidia/forcedeth.c +++ b/drivers/net/ethernet/nvidia/forcedeth.c @@ -4076,6 +4076,8 @@ static void nv_do_nic_poll(unsigned long data) struct fe_priv *np = netdev_priv(dev); u8 __iomem *base = get_hwbase(dev); u32 mask = 0; + unsigned long flags; + unsigned int irq = 0; /* * First disable irq(s) and then @@ -4085,25 +4087,27 @@ static void nv_do_nic_poll(unsigned long data) if (!using_multi_irqs(dev)) { if (np->msi_flags & NV_MSI_X_ENABLED) - disable_irq_lockdep(np->msi_x_entry[NV_MSI_X_VECTOR_ALL].vector); + irq = np->msi_x_entry[NV_MSI_X_VECTOR_ALL].vector; else - disable_irq_lockdep(np->pci_dev->irq); + irq = np->pci_dev->irq; mask = np->irqmask; } else { if (np->nic_poll_irq & NVREG_IRQ_RX_ALL) { - disable_irq_lockdep(np->msi_x_entry[NV_MSI_X_VECTOR_RX].vector); + irq = np->msi_x_entry[NV_MSI_X_VECTOR_RX].vector; mask |= NVREG_IRQ_RX_ALL; } if (np->nic_poll_irq & NVREG_IRQ_TX_ALL) { - disable_irq_lockdep(np->msi_x_entry[NV_MSI_X_VECTOR_TX].vector); + irq = np->msi_x_entry[NV_MSI_X_VECTOR_TX].vector; mask |= NVREG_IRQ_TX_ALL; } if (np->nic_poll_irq & NVREG_IRQ_OTHER) { - disable_irq_lockdep(np->msi_x_entry[NV_MSI_X_VECTOR_OTHER].vector); + irq = np->msi_x_entry[NV_MSI_X_VECTOR_OTHER].vector; mask |= NVREG_IRQ_OTHER; } } - /* disable_irq() contains synchronize_irq, thus no irq handler can run now */ + + disable_irq_nosync_lockdep_irqsave(irq, &flags); + synchronize_irq(irq); if (np->recover_error) { np->recover_error = 0; @@ -4156,28 +4160,22 @@ static void nv_do_nic_poll(unsigned long data) nv_nic_irq_optimized(0, dev); else nv_nic_irq(0, dev); - if (np->msi_flags & NV_MSI_X_ENABLED) - enable_irq_lockdep(np->msi_x_entry[NV_MSI_X_VECTOR_ALL].vector); - else - enable_irq_lockdep(np->pci_dev->irq); } else { if (np->nic_poll_irq & NVREG_IRQ_RX_ALL) { np->nic_poll_irq &= ~NVREG_IRQ_RX_ALL; nv_nic_irq_rx(0, dev); - enable_irq_lockdep(np->msi_x_entry[NV_MSI_X_VECTOR_RX].vector); } if (np->nic_poll_irq & NVREG_IRQ_TX_ALL) { np->nic_poll_irq &= ~NVREG_IRQ_TX_ALL; nv_nic_irq_tx(0, dev); - enable_irq_lockdep(np->msi_x_entry[NV_MSI_X_VECTOR_TX].vector); } if (np->nic_poll_irq & NVREG_IRQ_OTHER) { np->nic_poll_irq &= ~NVREG_IRQ_OTHER; nv_nic_irq_other(0, dev); - enable_irq_lockdep(np->msi_x_entry[NV_MSI_X_VECTOR_OTHER].vector); } } + enable_irq_lockdep_irqrestore(irq, &flags); } #ifdef CONFIG_NET_POLL_CONTROLLER diff --git a/drivers/net/ethernet/nxp/lpc_eth.c b/drivers/net/ethernet/nxp/lpc_eth.c index 66fd868152e5..b159ef8303cc 100644 --- a/drivers/net/ethernet/nxp/lpc_eth.c +++ b/drivers/net/ethernet/nxp/lpc_eth.c @@ -476,13 +476,12 @@ static void __lpc_get_mac(struct netdata_local *pldat, u8 *mac) mac[5] = tmp >> 8; } -static void __lpc_eth_clock_enable(struct netdata_local *pldat, - bool enable) +static void __lpc_eth_clock_enable(struct netdata_local *pldat, bool enable) { if (enable) - clk_enable(pldat->clk); + clk_prepare_enable(pldat->clk); else - clk_disable(pldat->clk); + clk_disable_unprepare(pldat->clk); } static void __lpc_params_setup(struct netdata_local *pldat) @@ -1494,7 +1493,7 @@ err_out_free_irq: err_out_iounmap: iounmap(pldat->net_base); err_out_disable_clocks: - clk_disable(pldat->clk); + clk_disable_unprepare(pldat->clk); clk_put(pldat->clk); err_out_free_dev: free_netdev(ndev); @@ -1519,7 +1518,7 @@ static int lpc_eth_drv_remove(struct platform_device *pdev) iounmap(pldat->net_base); mdiobus_unregister(pldat->mii_bus); mdiobus_free(pldat->mii_bus); - clk_disable(pldat->clk); + clk_disable_unprepare(pldat->clk); clk_put(pldat->clk); free_netdev(ndev); @@ -1540,7 +1539,7 @@ static int lpc_eth_drv_suspend(struct platform_device *pdev, if (netif_running(ndev)) { netif_device_detach(ndev); __lpc_eth_shutdown(pldat); - clk_disable(pldat->clk); + clk_disable_unprepare(pldat->clk); /* * Reset again now clock is disable to be sure diff --git a/drivers/net/ethernet/renesas/sh_eth.c b/drivers/net/ethernet/renesas/sh_eth.c index 257ea713b4c1..a484d8beb855 100644 --- a/drivers/net/ethernet/renesas/sh_eth.c +++ b/drivers/net/ethernet/renesas/sh_eth.c @@ -1127,7 +1127,7 @@ static void sh_eth_ring_format(struct net_device *ndev) struct sh_eth_txdesc *txdesc = NULL; int rx_ringsize = sizeof(*rxdesc) * mdp->num_rx_ring; int tx_ringsize = sizeof(*txdesc) * mdp->num_tx_ring; - int skbuff_size = mdp->rx_buf_sz + SH_ETH_RX_ALIGN - 1; + int skbuff_size = mdp->rx_buf_sz + SH_ETH_RX_ALIGN + 32 - 1; dma_addr_t dma_addr; mdp->cur_rx = 0; @@ -1148,8 +1148,8 @@ static void sh_eth_ring_format(struct net_device *ndev) /* RX descriptor */ rxdesc = &mdp->rx_ring[i]; - /* The size of the buffer is a multiple of 16 bytes. */ - rxdesc->buffer_length = ALIGN(mdp->rx_buf_sz, 16); + /* The size of the buffer is a multiple of 32 bytes. */ + rxdesc->buffer_length = ALIGN(mdp->rx_buf_sz, 32); dma_addr = dma_map_single(&ndev->dev, skb->data, rxdesc->buffer_length, DMA_FROM_DEVICE); @@ -1450,7 +1450,7 @@ static int sh_eth_rx(struct net_device *ndev, u32 intr_status, int *quota) struct sk_buff *skb; u16 pkt_len = 0; u32 desc_status; - int skbuff_size = mdp->rx_buf_sz + SH_ETH_RX_ALIGN - 1; + int skbuff_size = mdp->rx_buf_sz + SH_ETH_RX_ALIGN + 32 - 1; dma_addr_t dma_addr; boguscnt = min(boguscnt, *quota); @@ -1506,7 +1506,7 @@ static int sh_eth_rx(struct net_device *ndev, u32 intr_status, int *quota) if (mdp->cd->rpadir) skb_reserve(skb, NET_IP_ALIGN); dma_unmap_single(&ndev->dev, rxdesc->addr, - ALIGN(mdp->rx_buf_sz, 16), + ALIGN(mdp->rx_buf_sz, 32), DMA_FROM_DEVICE); skb_put(skb, pkt_len); skb->protocol = eth_type_trans(skb, ndev); @@ -1524,8 +1524,8 @@ static int sh_eth_rx(struct net_device *ndev, u32 intr_status, int *quota) for (; mdp->cur_rx - mdp->dirty_rx > 0; mdp->dirty_rx++) { entry = mdp->dirty_rx % mdp->num_rx_ring; rxdesc = &mdp->rx_ring[entry]; - /* The size of the buffer is 16 byte boundary. */ - rxdesc->buffer_length = ALIGN(mdp->rx_buf_sz, 16); + /* The size of the buffer is 32 byte boundary. */ + rxdesc->buffer_length = ALIGN(mdp->rx_buf_sz, 32); if (mdp->rx_skbuff[entry] == NULL) { skb = netdev_alloc_skb(ndev, skbuff_size); diff --git a/drivers/net/ethernet/ti/cpsw.c b/drivers/net/ethernet/ti/cpsw.c index 8fc90f1c872c..874fb297e96c 100644 --- a/drivers/net/ethernet/ti/cpsw.c +++ b/drivers/net/ethernet/ti/cpsw.c @@ -30,6 +30,7 @@ #include <linux/delay.h> #include <linux/pm_runtime.h> #include <linux/of.h> +#include <linux/of_mdio.h> #include <linux/of_net.h> #include <linux/of_device.h> #include <linux/if_vlan.h> @@ -365,6 +366,7 @@ struct cpsw_priv { spinlock_t lock; struct platform_device *pdev; struct net_device *ndev; + struct device_node *phy_node; struct napi_struct napi_rx; struct napi_struct napi_tx; struct device *dev; @@ -1145,7 +1147,11 @@ static void cpsw_slave_open(struct cpsw_slave *slave, struct cpsw_priv *priv) cpsw_ale_add_mcast(priv->ale, priv->ndev->broadcast, 1 << slave_port, 0, 0, ALE_MCAST_FWD_2); - slave->phy = phy_connect(priv->ndev, slave->data->phy_id, + if (priv->phy_node) + slave->phy = of_phy_connect(priv->ndev, priv->phy_node, + &cpsw_adjust_link, 0, slave->data->phy_if); + else + slave->phy = phy_connect(priv->ndev, slave->data->phy_id, &cpsw_adjust_link, slave->data->phy_if); if (IS_ERR(slave->phy)) { dev_err(priv->dev, "phy %s not found on slave %d\n", @@ -1934,11 +1940,12 @@ static void cpsw_slave_init(struct cpsw_slave *slave, struct cpsw_priv *priv, slave->port_vlan = data->dual_emac_res_vlan; } -static int cpsw_probe_dt(struct cpsw_platform_data *data, +static int cpsw_probe_dt(struct cpsw_priv *priv, struct platform_device *pdev) { struct device_node *node = pdev->dev.of_node; struct device_node *slave_node; + struct cpsw_platform_data *data = &priv->data; int i = 0, ret; u32 prop; @@ -2029,6 +2036,7 @@ static int cpsw_probe_dt(struct cpsw_platform_data *data, if (strcmp(slave_node->name, "slave")) continue; + priv->phy_node = of_parse_phandle(slave_node, "phy-handle", 0); parp = of_get_property(slave_node, "phy_id", &lenp); if ((parp == NULL) || (lenp != (sizeof(void *) * 2))) { dev_err(&pdev->dev, "Missing slave[%d] phy_id property\n", i); @@ -2044,7 +2052,6 @@ static int cpsw_probe_dt(struct cpsw_platform_data *data, } snprintf(slave_data->phy_id, sizeof(slave_data->phy_id), PHY_ID_FMT, mdio->name, phyid); - slave_data->phy_if = of_get_phy_mode(slave_node); if (slave_data->phy_if < 0) { dev_err(&pdev->dev, "Missing or malformed slave[%d] phy-mode property\n", @@ -2240,7 +2247,7 @@ static int cpsw_probe(struct platform_device *pdev) /* Select default pin state */ pinctrl_pm_select_default_state(&pdev->dev); - if (cpsw_probe_dt(&priv->data, pdev)) { + if (cpsw_probe_dt(priv, pdev)) { dev_err(&pdev->dev, "cpsw: platform data missing\n"); ret = -ENODEV; goto clean_runtime_disable_ret; diff --git a/drivers/net/ethernet/ti/netcp_ethss.c b/drivers/net/ethernet/ti/netcp_ethss.c index 6bff8d82ceab..4e70e7586a09 100644 --- a/drivers/net/ethernet/ti/netcp_ethss.c +++ b/drivers/net/ethernet/ti/netcp_ethss.c @@ -2637,8 +2637,10 @@ static void init_secondary_ports(struct gbe_priv *gbe_dev, mac_phy_link = true; slave->open = true; - if (gbe_dev->num_slaves >= gbe_dev->max_num_slaves) + if (gbe_dev->num_slaves >= gbe_dev->max_num_slaves) { + of_node_put(port); break; + } } /* of_phy_connect() is needed only for MAC-PHY interface */ @@ -3137,8 +3139,10 @@ static int gbe_probe(struct netcp_device *netcp_device, struct device *dev, continue; } gbe_dev->num_slaves++; - if (gbe_dev->num_slaves >= gbe_dev->max_num_slaves) + if (gbe_dev->num_slaves >= gbe_dev->max_num_slaves) { + of_node_put(interface); break; + } } of_node_put(interfaces); diff --git a/drivers/net/ethernet/via/via-rhine.c b/drivers/net/ethernet/via/via-rhine.c index a83263743665..2b7550c43f78 100644 --- a/drivers/net/ethernet/via/via-rhine.c +++ b/drivers/net/ethernet/via/via-rhine.c @@ -2134,10 +2134,11 @@ static int rhine_rx(struct net_device *dev, int limit) } skb_put(skb, pkt_len); - skb->protocol = eth_type_trans(skb, dev); rhine_rx_vlan_tag(skb, desc, data_size); + skb->protocol = eth_type_trans(skb, dev); + netif_receive_skb(skb); u64_stats_update_begin(&rp->rx_stats.syncp); diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c index 8f5c02eed47d..445071c163cb 100644 --- a/drivers/net/geneve.c +++ b/drivers/net/geneve.c @@ -594,14 +594,12 @@ static struct rtable *geneve_get_rt(struct sk_buff *skb, rt = ip_route_output_key(geneve->net, fl4); if (IS_ERR(rt)) { netdev_dbg(dev, "no route to %pI4\n", &fl4->daddr); - dev->stats.tx_carrier_errors++; - return rt; + return ERR_PTR(-ENETUNREACH); } if (rt->dst.dev == dev) { /* is this necessary? */ netdev_dbg(dev, "circular route to %pI4\n", &fl4->daddr); - dev->stats.collisions++; ip_rt_put(rt); - return ERR_PTR(-EINVAL); + return ERR_PTR(-ELOOP); } return rt; } @@ -627,12 +625,12 @@ static netdev_tx_t geneve_xmit(struct sk_buff *skb, struct net_device *dev) struct ip_tunnel_info *info = NULL; struct rtable *rt = NULL; const struct iphdr *iip; /* interior IP header */ + int err = -EINVAL; struct flowi4 fl4; __u8 tos, ttl; __be16 sport; bool udp_csum; __be16 df; - int err; if (geneve->collect_md) { info = skb_tunnel_info(skb); @@ -647,7 +645,7 @@ static netdev_tx_t geneve_xmit(struct sk_buff *skb, struct net_device *dev) rt = geneve_get_rt(skb, dev, &fl4, info); if (IS_ERR(rt)) { netdev_dbg(dev, "no route to %pI4\n", &fl4.daddr); - dev->stats.tx_carrier_errors++; + err = PTR_ERR(rt); goto tx_error; } @@ -699,10 +697,37 @@ static netdev_tx_t geneve_xmit(struct sk_buff *skb, struct net_device *dev) tx_error: dev_kfree_skb(skb); err: - dev->stats.tx_errors++; + if (err == -ELOOP) + dev->stats.collisions++; + else if (err == -ENETUNREACH) + dev->stats.tx_carrier_errors++; + else + dev->stats.tx_errors++; return NETDEV_TX_OK; } +static int geneve_fill_metadata_dst(struct net_device *dev, struct sk_buff *skb) +{ + struct ip_tunnel_info *info = skb_tunnel_info(skb); + struct geneve_dev *geneve = netdev_priv(dev); + struct rtable *rt; + struct flowi4 fl4; + + if (ip_tunnel_info_af(info) != AF_INET) + return -EINVAL; + + rt = geneve_get_rt(skb, dev, &fl4, info); + if (IS_ERR(rt)) + return PTR_ERR(rt); + + ip_rt_put(rt); + info->key.u.ipv4.src = fl4.saddr; + info->key.tp_src = udp_flow_src_port(geneve->net, skb, + 1, USHRT_MAX, true); + info->key.tp_dst = geneve->dst_port; + return 0; +} + static const struct net_device_ops geneve_netdev_ops = { .ndo_init = geneve_init, .ndo_uninit = geneve_uninit, @@ -713,6 +738,7 @@ static const struct net_device_ops geneve_netdev_ops = { .ndo_change_mtu = eth_change_mtu, .ndo_validate_addr = eth_validate_addr, .ndo_set_mac_address = eth_mac_addr, + .ndo_fill_metadata_dst = geneve_fill_metadata_dst, }; static void geneve_get_drvinfo(struct net_device *dev, @@ -870,14 +896,14 @@ static int geneve_newlink(struct net *net, struct net_device *dev, __be16 dst_port = htons(GENEVE_UDP_PORT); __u8 ttl = 0, tos = 0; bool metadata = false; - __be32 rem_addr; - __u32 vni; + __be32 rem_addr = 0; + __u32 vni = 0; - if (!data[IFLA_GENEVE_ID] || !data[IFLA_GENEVE_REMOTE]) - return -EINVAL; + if (data[IFLA_GENEVE_ID]) + vni = nla_get_u32(data[IFLA_GENEVE_ID]); - vni = nla_get_u32(data[IFLA_GENEVE_ID]); - rem_addr = nla_get_in_addr(data[IFLA_GENEVE_REMOTE]); + if (data[IFLA_GENEVE_REMOTE]) + rem_addr = nla_get_in_addr(data[IFLA_GENEVE_REMOTE]); if (data[IFLA_GENEVE_TTL]) ttl = nla_get_u8(data[IFLA_GENEVE_TTL]); diff --git a/drivers/net/macvtap.c b/drivers/net/macvtap.c index 248478c6f6e4..197c93937c2d 100644 --- a/drivers/net/macvtap.c +++ b/drivers/net/macvtap.c @@ -137,7 +137,7 @@ static const struct proto_ops macvtap_socket_ops; #define TUN_OFFLOADS (NETIF_F_HW_CSUM | NETIF_F_TSO_ECN | NETIF_F_TSO | \ NETIF_F_TSO6 | NETIF_F_UFO) #define RX_OFFLOADS (NETIF_F_GRO | NETIF_F_LRO) -#define TAP_FEATURES (NETIF_F_GSO | NETIF_F_SG) +#define TAP_FEATURES (NETIF_F_GSO | NETIF_F_SG | NETIF_F_FRAGLIST) static struct macvlan_dev *macvtap_get_vlan_rcu(const struct net_device *dev) { diff --git a/drivers/net/phy/Kconfig b/drivers/net/phy/Kconfig index c5ad98ace5d0..436972b2a746 100644 --- a/drivers/net/phy/Kconfig +++ b/drivers/net/phy/Kconfig @@ -122,6 +122,11 @@ config MICREL_PHY ---help--- Supports the KSZ9021, VSC8201, KS8001 PHYs. +config DP83848_PHY + tristate "Driver for Texas Instruments DP83848 PHY" + ---help--- + Supports the DP83848 PHY. + config DP83867_PHY tristate "Drivers for Texas Instruments DP83867 Gigabit PHY" ---help--- @@ -168,8 +173,6 @@ config MDIO_OCTEON busses. It is required by the Octeon and ThunderX ethernet device drivers. - If in doubt, say Y. - config MDIO_SUN4I tristate "Allwinner sun4i MDIO interface support" depends on ARCH_SUNXI diff --git a/drivers/net/phy/Makefile b/drivers/net/phy/Makefile index 87f079c4b2c7..b74822463930 100644 --- a/drivers/net/phy/Makefile +++ b/drivers/net/phy/Makefile @@ -24,6 +24,7 @@ obj-$(CONFIG_MDIO_BITBANG) += mdio-bitbang.o obj-$(CONFIG_MDIO_GPIO) += mdio-gpio.o obj-$(CONFIG_NATIONAL_PHY) += national.o obj-$(CONFIG_DP83640_PHY) += dp83640.o +obj-$(CONFIG_DP83848_PHY) += dp83848.o obj-$(CONFIG_DP83867_PHY) += dp83867.o obj-$(CONFIG_STE10XP) += ste10Xp.o obj-$(CONFIG_MICREL_PHY) += micrel.o diff --git a/drivers/net/phy/dp83848.c b/drivers/net/phy/dp83848.c new file mode 100644 index 000000000000..5ce9bef54468 --- /dev/null +++ b/drivers/net/phy/dp83848.c @@ -0,0 +1,99 @@ +/* + * Driver for the Texas Instruments DP83848 PHY + * + * Copyright (C) 2015 Texas Instruments Inc. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + +#include <linux/module.h> +#include <linux/phy.h> + +#define DP83848_PHY_ID 0x20005c90 + +/* Registers */ +#define DP83848_MICR 0x11 +#define DP83848_MISR 0x12 + +/* MICR Register Fields */ +#define DP83848_MICR_INT_OE BIT(0) /* Interrupt Output Enable */ +#define DP83848_MICR_INTEN BIT(1) /* Interrupt Enable */ + +/* MISR Register Fields */ +#define DP83848_MISR_RHF_INT_EN BIT(0) /* Receive Error Counter */ +#define DP83848_MISR_FHF_INT_EN BIT(1) /* False Carrier Counter */ +#define DP83848_MISR_ANC_INT_EN BIT(2) /* Auto-negotiation complete */ +#define DP83848_MISR_DUP_INT_EN BIT(3) /* Duplex Status */ +#define DP83848_MISR_SPD_INT_EN BIT(4) /* Speed status */ +#define DP83848_MISR_LINK_INT_EN BIT(5) /* Link status */ +#define DP83848_MISR_ED_INT_EN BIT(6) /* Energy detect */ +#define DP83848_MISR_LQM_INT_EN BIT(7) /* Link Quality Monitor */ + +static int dp83848_ack_interrupt(struct phy_device *phydev) +{ + int err = phy_read(phydev, DP83848_MISR); + + return err < 0 ? err : 0; +} + +static int dp83848_config_intr(struct phy_device *phydev) +{ + int err; + + if (phydev->interrupts == PHY_INTERRUPT_ENABLED) { + err = phy_write(phydev, DP83848_MICR, + DP83848_MICR_INT_OE | + DP83848_MICR_INTEN); + if (err < 0) + return err; + + return phy_write(phydev, DP83848_MISR, + DP83848_MISR_ANC_INT_EN | + DP83848_MISR_DUP_INT_EN | + DP83848_MISR_SPD_INT_EN | + DP83848_MISR_LINK_INT_EN); + } + + return phy_write(phydev, DP83848_MICR, 0x0); +} + +static struct mdio_device_id __maybe_unused dp83848_tbl[] = { + { DP83848_PHY_ID, 0xfffffff0 }, + { } +}; +MODULE_DEVICE_TABLE(mdio, dp83848_tbl); + +static struct phy_driver dp83848_driver[] = { + { + .phy_id = DP83848_PHY_ID, + .phy_id_mask = 0xfffffff0, + .name = "TI DP83848", + .features = PHY_BASIC_FEATURES, + .flags = PHY_HAS_INTERRUPT, + + .soft_reset = genphy_soft_reset, + .config_init = genphy_config_init, + .suspend = genphy_suspend, + .resume = genphy_resume, + .config_aneg = genphy_config_aneg, + .read_status = genphy_read_status, + + /* IRQ related */ + .ack_interrupt = dp83848_ack_interrupt, + .config_intr = dp83848_config_intr, + + .driver = { .owner = THIS_MODULE, }, + }, +}; +module_phy_driver(dp83848_driver); + +MODULE_DESCRIPTION("Texas Instruments DP83848 PHY driver"); +MODULE_AUTHOR("Andrew F. Davis <afd@ti.com"); +MODULE_LICENSE("GPL"); diff --git a/drivers/net/phy/mdio-mux-mmioreg.c b/drivers/net/phy/mdio-mux-mmioreg.c index 2377c1341172..7fde454fbc4f 100644 --- a/drivers/net/phy/mdio-mux-mmioreg.c +++ b/drivers/net/phy/mdio-mux-mmioreg.c @@ -113,12 +113,14 @@ static int mdio_mux_mmioreg_probe(struct platform_device *pdev) if (!iprop || len != sizeof(uint32_t)) { dev_err(&pdev->dev, "mdio-mux child node %s is " "missing a 'reg' property\n", np2->full_name); + of_node_put(np2); return -ENODEV; } if (be32_to_cpup(iprop) & ~s->mask) { dev_err(&pdev->dev, "mdio-mux child node %s has " "a 'reg' value with unmasked bits\n", np2->full_name); + of_node_put(np2); return -ENODEV; } } diff --git a/drivers/net/phy/mdio-mux.c b/drivers/net/phy/mdio-mux.c index 280c7c311f72..908e8d486342 100644 --- a/drivers/net/phy/mdio-mux.c +++ b/drivers/net/phy/mdio-mux.c @@ -144,6 +144,7 @@ int mdio_mux_init(struct device *dev, dev_err(dev, "Error: Failed to allocate memory for child\n"); ret_val = -ENOMEM; + of_node_put(child_bus_node); break; } cb->bus_number = v; diff --git a/drivers/net/phy/micrel.c b/drivers/net/phy/micrel.c index 499185eaf413..cf6312fafea5 100644 --- a/drivers/net/phy/micrel.c +++ b/drivers/net/phy/micrel.c @@ -514,6 +514,27 @@ static int ksz8873mll_read_status(struct phy_device *phydev) return 0; } +static int ksz9031_read_status(struct phy_device *phydev) +{ + int err; + int regval; + + err = genphy_read_status(phydev); + if (err) + return err; + + /* Make sure the PHY is not broken. Read idle error count, + * and reset the PHY if it is maxed out. + */ + regval = phy_read(phydev, MII_STAT1000); + if ((regval & 0xFF) == 0xFF) { + phy_init_hw(phydev); + phydev->link = 0; + } + + return 0; +} + static int ksz8873mll_config_aneg(struct phy_device *phydev) { return 0; @@ -772,7 +793,7 @@ static struct phy_driver ksphy_driver[] = { .driver_data = &ksz9021_type, .config_init = ksz9031_config_init, .config_aneg = genphy_config_aneg, - .read_status = genphy_read_status, + .read_status = ksz9031_read_status, .ack_interrupt = kszphy_ack_interrupt, .config_intr = kszphy_config_intr, .suspend = genphy_suspend, diff --git a/drivers/net/phy/smsc.c b/drivers/net/phy/smsc.c index 70b08958763a..dc2da8770918 100644 --- a/drivers/net/phy/smsc.c +++ b/drivers/net/phy/smsc.c @@ -43,16 +43,25 @@ static int smsc_phy_ack_interrupt(struct phy_device *phydev) static int smsc_phy_config_init(struct phy_device *phydev) { + int __maybe_unused len; + struct device *dev __maybe_unused = &phydev->dev; + struct device_node *of_node __maybe_unused = dev->of_node; int rc = phy_read(phydev, MII_LAN83C185_CTRL_STATUS); + int enable_energy = 1; if (rc < 0) return rc; - /* Enable energy detect mode for this SMSC Transceivers */ - rc = phy_write(phydev, MII_LAN83C185_CTRL_STATUS, - rc | MII_LAN83C185_EDPWRDOWN); - if (rc < 0) - return rc; + if (of_find_property(of_node, "smsc,disable-energy-detect", &len)) + enable_energy = 0; + + if (enable_energy) { + /* Enable energy detect mode for this SMSC Transceivers */ + rc = phy_write(phydev, MII_LAN83C185_CTRL_STATUS, + rc | MII_LAN83C185_EDPWRDOWN); + if (rc < 0) + return rc; + } return smsc_phy_ack_interrupt(phydev); } diff --git a/drivers/net/ppp/pppoe.c b/drivers/net/ppp/pppoe.c index 3837ae344f63..5e0b43283bce 100644 --- a/drivers/net/ppp/pppoe.c +++ b/drivers/net/ppp/pppoe.c @@ -313,7 +313,6 @@ static void pppoe_flush_dev(struct net_device *dev) if (po->pppoe_dev == dev && sk->sk_state & (PPPOX_CONNECTED | PPPOX_BOUND | PPPOX_ZOMBIE)) { pppox_unbind_sock(sk); - sk->sk_state = PPPOX_ZOMBIE; sk->sk_state_change(sk); po->pppoe_dev = NULL; dev_put(dev); @@ -590,7 +589,7 @@ static int pppoe_release(struct socket *sock) po = pppox_sk(sk); - if (sk->sk_state & (PPPOX_CONNECTED | PPPOX_BOUND | PPPOX_ZOMBIE)) { + if (po->pppoe_dev) { dev_put(po->pppoe_dev); po->pppoe_dev = NULL; } diff --git a/drivers/net/usb/Kconfig b/drivers/net/usb/Kconfig index fbb9325d1f6e..e66805eeffb4 100644 --- a/drivers/net/usb/Kconfig +++ b/drivers/net/usb/Kconfig @@ -164,6 +164,7 @@ config USB_NET_AX8817X * Aten UC210T * ASIX AX88172 * Billionton Systems, USB2AR + * Billionton Systems, GUSB2AM-1G-B * Buffalo LUA-U2-KTX * Corega FEther USB2-TX * D-Link DUB-E100 diff --git a/drivers/net/usb/asix_common.c b/drivers/net/usb/asix_common.c index 75d6f26729a3..079069a060a6 100644 --- a/drivers/net/usb/asix_common.c +++ b/drivers/net/usb/asix_common.c @@ -91,8 +91,10 @@ int asix_rx_fixup_internal(struct usbnet *dev, struct sk_buff *skb, } rx->ax_skb = netdev_alloc_skb_ip_align(dev->net, rx->size); - if (!rx->ax_skb) + if (!rx->ax_skb) { + rx->size = 0; return 0; + } } if (rx->size > dev->net->mtu + ETH_HLEN + VLAN_HLEN) { diff --git a/drivers/net/usb/asix_devices.c b/drivers/net/usb/asix_devices.c index 1173a24feda3..5cabefc23494 100644 --- a/drivers/net/usb/asix_devices.c +++ b/drivers/net/usb/asix_devices.c @@ -959,6 +959,10 @@ static const struct usb_device_id products [] = { USB_DEVICE (0x08dd, 0x90ff), .driver_info = (unsigned long) &ax8817x_info, }, { + // Billionton Systems, GUSB2AM-1G-B + USB_DEVICE(0x08dd, 0x0114), + .driver_info = (unsigned long) &ax88178_info, +}, { // ATEN UC210T USB_DEVICE (0x0557, 0x2009), .driver_info = (unsigned long) &ax8817x_info, diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c index 355842b85ee9..2a7c1be23c4f 100644 --- a/drivers/net/usb/qmi_wwan.c +++ b/drivers/net/usb/qmi_wwan.c @@ -765,6 +765,10 @@ static const struct usb_device_id products[] = { {QMI_FIXED_INTF(0x1199, 0x9056, 8)}, /* Sierra Wireless Modem */ {QMI_FIXED_INTF(0x1199, 0x9057, 8)}, {QMI_FIXED_INTF(0x1199, 0x9061, 8)}, /* Sierra Wireless Modem */ + {QMI_FIXED_INTF(0x1199, 0x9070, 8)}, /* Sierra Wireless MC74xx/EM74xx */ + {QMI_FIXED_INTF(0x1199, 0x9070, 10)}, /* Sierra Wireless MC74xx/EM74xx */ + {QMI_FIXED_INTF(0x1199, 0x9071, 8)}, /* Sierra Wireless MC74xx/EM74xx */ + {QMI_FIXED_INTF(0x1199, 0x9071, 10)}, /* Sierra Wireless MC74xx/EM74xx */ {QMI_FIXED_INTF(0x1bbb, 0x011e, 4)}, /* Telekom Speedstick LTE II (Alcatel One Touch L100V LTE) */ {QMI_FIXED_INTF(0x1bbb, 0x0203, 2)}, /* Alcatel L800MA */ {QMI_FIXED_INTF(0x2357, 0x0201, 4)}, /* TP-LINK HSUPA Modem MA180 */ diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c index bbac1d35ed4e..c1587ece28cf 100644 --- a/drivers/net/vxlan.c +++ b/drivers/net/vxlan.c @@ -2337,6 +2337,46 @@ static int vxlan_change_mtu(struct net_device *dev, int new_mtu) return 0; } +static int egress_ipv4_tun_info(struct net_device *dev, struct sk_buff *skb, + struct ip_tunnel_info *info, + __be16 sport, __be16 dport) +{ + struct vxlan_dev *vxlan = netdev_priv(dev); + struct rtable *rt; + struct flowi4 fl4; + + memset(&fl4, 0, sizeof(fl4)); + fl4.flowi4_tos = RT_TOS(info->key.tos); + fl4.flowi4_mark = skb->mark; + fl4.flowi4_proto = IPPROTO_UDP; + fl4.daddr = info->key.u.ipv4.dst; + + rt = ip_route_output_key(vxlan->net, &fl4); + if (IS_ERR(rt)) + return PTR_ERR(rt); + ip_rt_put(rt); + + info->key.u.ipv4.src = fl4.saddr; + info->key.tp_src = sport; + info->key.tp_dst = dport; + return 0; +} + +static int vxlan_fill_metadata_dst(struct net_device *dev, struct sk_buff *skb) +{ + struct vxlan_dev *vxlan = netdev_priv(dev); + struct ip_tunnel_info *info = skb_tunnel_info(skb); + __be16 sport, dport; + + sport = udp_flow_src_port(dev_net(dev), skb, vxlan->cfg.port_min, + vxlan->cfg.port_max, true); + dport = info->key.tp_dst ? : vxlan->cfg.dst_port; + + if (ip_tunnel_info_af(info) == AF_INET) + return egress_ipv4_tun_info(dev, skb, info, sport, dport); + return -EINVAL; +} + static const struct net_device_ops vxlan_netdev_ops = { .ndo_init = vxlan_init, .ndo_uninit = vxlan_uninit, @@ -2351,6 +2391,7 @@ static const struct net_device_ops vxlan_netdev_ops = { .ndo_fdb_add = vxlan_fdb_add, .ndo_fdb_del = vxlan_fdb_delete, .ndo_fdb_dump = vxlan_fdb_dump, + .ndo_fill_metadata_dst = vxlan_fill_metadata_dst, }; /* Info for udev, that this is a virtual tunnel endpoint */ @@ -2745,11 +2786,10 @@ static int vxlan_newlink(struct net *src_net, struct net_device *dev, struct vxlan_config conf; int err; - if (!data[IFLA_VXLAN_ID]) - return -EINVAL; - memset(&conf, 0, sizeof(conf)); - conf.vni = nla_get_u32(data[IFLA_VXLAN_ID]); + + if (data[IFLA_VXLAN_ID]) + conf.vni = nla_get_u32(data[IFLA_VXLAN_ID]); if (data[IFLA_VXLAN_GROUP]) { conf.remote_ip.sin.sin_addr.s_addr = nla_get_in_addr(data[IFLA_VXLAN_GROUP]); diff --git a/drivers/net/wireless/ath/ath10k/hw.h b/drivers/net/wireless/ath/ath10k/hw.h index 23afcda2de96..678d72af4a9d 100644 --- a/drivers/net/wireless/ath/ath10k/hw.h +++ b/drivers/net/wireless/ath/ath10k/hw.h @@ -337,7 +337,7 @@ enum ath10k_hw_rate_cck { #define TARGET_10X_MAX_FRAG_ENTRIES 0 /* 10.2 parameters */ -#define TARGET_10_2_DMA_BURST_SIZE 1 +#define TARGET_10_2_DMA_BURST_SIZE 0 /* Target specific defines for WMI-TLV firmware */ #define TARGET_TLV_NUM_VDEVS 4 @@ -391,7 +391,7 @@ enum ath10k_hw_rate_cck { #define TARGET_10_4_TX_DBG_LOG_SIZE 1024 #define TARGET_10_4_NUM_WDS_ENTRIES 32 -#define TARGET_10_4_DMA_BURST_SIZE 1 +#define TARGET_10_4_DMA_BURST_SIZE 0 #define TARGET_10_4_MAC_AGGR_DELIM 0 #define TARGET_10_4_RX_SKIP_DEFRAG_TIMEOUT_DUP_DETECTION_CHECK 1 #define TARGET_10_4_VOW_CONFIG 0 diff --git a/drivers/net/wireless/ath/ath6kl/init.c b/drivers/net/wireless/ath/ath6kl/init.c index 6e473fa4b13c..12241b1c57cd 100644 --- a/drivers/net/wireless/ath/ath6kl/init.c +++ b/drivers/net/wireless/ath/ath6kl/init.c @@ -715,6 +715,7 @@ static bool check_device_tree(struct ath6kl *ar) board_filename, ret); continue; } + of_node_put(node); return true; } return false; diff --git a/drivers/net/wireless/ath/ath9k/init.c b/drivers/net/wireless/ath/ath9k/init.c index 57f95f2dca5b..90eb75012e4f 100644 --- a/drivers/net/wireless/ath/ath9k/init.c +++ b/drivers/net/wireless/ath/ath9k/init.c @@ -880,6 +880,7 @@ static void ath9k_set_hw_capab(struct ath_softc *sc, struct ieee80211_hw *hw) hw->max_rate_tries = 10; hw->sta_data_size = sizeof(struct ath_node); hw->vif_data_size = sizeof(struct ath_vif); + hw->extra_tx_headroom = 4; hw->wiphy->available_antennas_rx = BIT(ah->caps.max_rxchains) - 1; hw->wiphy->available_antennas_tx = BIT(ah->caps.max_txchains) - 1; diff --git a/drivers/net/wireless/b43/main.c b/drivers/net/wireless/b43/main.c index 28490702124a..71d3e9adbf3c 100644 --- a/drivers/net/wireless/b43/main.c +++ b/drivers/net/wireless/b43/main.c @@ -120,6 +120,7 @@ MODULE_PARM_DESC(allhwsupport, "Enable support for all hardware (even it if over #ifdef CONFIG_B43_BCMA static const struct bcma_device_id b43_bcma_tbl[] = { BCMA_CORE(BCMA_MANUF_BCM, BCMA_CORE_80211, 0x11, BCMA_ANY_CLASS), + BCMA_CORE(BCMA_MANUF_BCM, BCMA_CORE_80211, 0x15, BCMA_ANY_CLASS), BCMA_CORE(BCMA_MANUF_BCM, BCMA_CORE_80211, 0x17, BCMA_ANY_CLASS), BCMA_CORE(BCMA_MANUF_BCM, BCMA_CORE_80211, 0x18, BCMA_ANY_CLASS), BCMA_CORE(BCMA_MANUF_BCM, BCMA_CORE_80211, 0x1C, BCMA_ANY_CLASS), diff --git a/drivers/net/wireless/iwlwifi/dvm/lib.c b/drivers/net/wireless/iwlwifi/dvm/lib.c index ab45819c1fbb..e18629a16fb0 100644 --- a/drivers/net/wireless/iwlwifi/dvm/lib.c +++ b/drivers/net/wireless/iwlwifi/dvm/lib.c @@ -1020,7 +1020,7 @@ static void iwlagn_wowlan_program_keys(struct ieee80211_hw *hw, u8 *pn = seq.ccmp.pn; ieee80211_get_key_rx_seq(key, i, &seq); - aes_sc->pn = cpu_to_le64( + aes_sc[i].pn = cpu_to_le64( (u64)pn[5] | ((u64)pn[4] << 8) | ((u64)pn[3] << 16) | diff --git a/drivers/net/wireless/iwlwifi/iwl-7000.c b/drivers/net/wireless/iwlwifi/iwl-7000.c index 6951aba620eb..3fb327d5a911 100644 --- a/drivers/net/wireless/iwlwifi/iwl-7000.c +++ b/drivers/net/wireless/iwlwifi/iwl-7000.c @@ -348,6 +348,6 @@ const struct iwl_cfg iwl7265d_n_cfg = { }; MODULE_FIRMWARE(IWL7260_MODULE_FIRMWARE(IWL7260_UCODE_API_OK)); -MODULE_FIRMWARE(IWL3160_MODULE_FIRMWARE(IWL3160_UCODE_API_OK)); +MODULE_FIRMWARE(IWL3160_MODULE_FIRMWARE(IWL7260_UCODE_API_OK)); MODULE_FIRMWARE(IWL7265_MODULE_FIRMWARE(IWL7260_UCODE_API_OK)); MODULE_FIRMWARE(IWL7265D_MODULE_FIRMWARE(IWL7260_UCODE_API_OK)); diff --git a/drivers/net/wireless/iwlwifi/mvm/d3.c b/drivers/net/wireless/iwlwifi/mvm/d3.c index 04264e417c1c..576187611e61 100644 --- a/drivers/net/wireless/iwlwifi/mvm/d3.c +++ b/drivers/net/wireless/iwlwifi/mvm/d3.c @@ -274,18 +274,13 @@ static void iwl_mvm_wowlan_program_keys(struct ieee80211_hw *hw, break; case WLAN_CIPHER_SUITE_CCMP: if (sta) { - u8 *pn = seq.ccmp.pn; + u64 pn64; aes_sc = data->rsc_tsc->all_tsc_rsc.aes.unicast_rsc; aes_tx_sc = &data->rsc_tsc->all_tsc_rsc.aes.tsc; - ieee80211_get_key_tx_seq(key, &seq); - aes_tx_sc->pn = cpu_to_le64((u64)pn[5] | - ((u64)pn[4] << 8) | - ((u64)pn[3] << 16) | - ((u64)pn[2] << 24) | - ((u64)pn[1] << 32) | - ((u64)pn[0] << 40)); + pn64 = atomic64_read(&key->tx_pn); + aes_tx_sc->pn = cpu_to_le64(pn64); } else { aes_sc = data->rsc_tsc->all_tsc_rsc.aes.multicast_rsc; } @@ -298,12 +293,12 @@ static void iwl_mvm_wowlan_program_keys(struct ieee80211_hw *hw, u8 *pn = seq.ccmp.pn; ieee80211_get_key_rx_seq(key, i, &seq); - aes_sc->pn = cpu_to_le64((u64)pn[5] | - ((u64)pn[4] << 8) | - ((u64)pn[3] << 16) | - ((u64)pn[2] << 24) | - ((u64)pn[1] << 32) | - ((u64)pn[0] << 40)); + aes_sc[i].pn = cpu_to_le64((u64)pn[5] | + ((u64)pn[4] << 8) | + ((u64)pn[3] << 16) | + ((u64)pn[2] << 24) | + ((u64)pn[1] << 32) | + ((u64)pn[0] << 40)); } data->use_rsc_tsc = true; break; @@ -1453,15 +1448,15 @@ static void iwl_mvm_d3_update_gtks(struct ieee80211_hw *hw, switch (key->cipher) { case WLAN_CIPHER_SUITE_CCMP: - iwl_mvm_aes_sc_to_seq(&sc->aes.tsc, &seq); iwl_mvm_set_aes_rx_seq(sc->aes.unicast_rsc, key); + atomic64_set(&key->tx_pn, le64_to_cpu(sc->aes.tsc.pn)); break; case WLAN_CIPHER_SUITE_TKIP: iwl_mvm_tkip_sc_to_seq(&sc->tkip.tsc, &seq); iwl_mvm_set_tkip_rx_seq(sc->tkip.unicast_rsc, key); + ieee80211_set_key_tx_seq(key, &seq); break; } - ieee80211_set_key_tx_seq(key, &seq); /* that's it for this key */ return; diff --git a/drivers/net/wireless/iwlwifi/mvm/fw.c b/drivers/net/wireless/iwlwifi/mvm/fw.c index 4a0ce83315bd..5c7f7cc9ffcc 100644 --- a/drivers/net/wireless/iwlwifi/mvm/fw.c +++ b/drivers/net/wireless/iwlwifi/mvm/fw.c @@ -703,7 +703,7 @@ int iwl_run_init_mvm_ucode(struct iwl_mvm *mvm, bool read_nvm) * abort after reading the nvm in case RF Kill is on, we will complete * the init seq later when RF kill will switch to off */ - if (iwl_mvm_is_radio_killed(mvm)) { + if (iwl_mvm_is_radio_hw_killed(mvm)) { IWL_DEBUG_RF_KILL(mvm, "jump over all phy activities due to RF kill\n"); iwl_remove_notification(&mvm->notif_wait, &calib_wait); @@ -736,7 +736,7 @@ int iwl_run_init_mvm_ucode(struct iwl_mvm *mvm, bool read_nvm) ret = iwl_wait_notification(&mvm->notif_wait, &calib_wait, MVM_UCODE_CALIB_TIMEOUT); - if (ret && iwl_mvm_is_radio_killed(mvm)) { + if (ret && iwl_mvm_is_radio_hw_killed(mvm)) { IWL_DEBUG_RF_KILL(mvm, "RFKILL while calibrating.\n"); ret = 1; } diff --git a/drivers/net/wireless/iwlwifi/mvm/mac80211.c b/drivers/net/wireless/iwlwifi/mvm/mac80211.c index aa8c2b7f23c7..7c2944a72470 100644 --- a/drivers/net/wireless/iwlwifi/mvm/mac80211.c +++ b/drivers/net/wireless/iwlwifi/mvm/mac80211.c @@ -2388,6 +2388,7 @@ static void iwl_mvm_stop_ap_ibss(struct ieee80211_hw *hw, iwl_mvm_remove_time_event(mvm, mvmvif, &mvmvif->time_event_data); RCU_INIT_POINTER(mvm->csa_vif, NULL); + mvmvif->csa_countdown = false; } if (rcu_access_pointer(mvm->csa_tx_blocked_vif) == vif) { diff --git a/drivers/net/wireless/iwlwifi/mvm/mvm.h b/drivers/net/wireless/iwlwifi/mvm/mvm.h index b95a07ec9e36..c754051a4cea 100644 --- a/drivers/net/wireless/iwlwifi/mvm/mvm.h +++ b/drivers/net/wireless/iwlwifi/mvm/mvm.h @@ -860,6 +860,11 @@ static inline bool iwl_mvm_is_radio_killed(struct iwl_mvm *mvm) test_bit(IWL_MVM_STATUS_HW_CTKILL, &mvm->status); } +static inline bool iwl_mvm_is_radio_hw_killed(struct iwl_mvm *mvm) +{ + return test_bit(IWL_MVM_STATUS_HW_RFKILL, &mvm->status); +} + /* Must be called with rcu_read_lock() held and it can only be * released when mvmsta is not needed anymore. */ diff --git a/drivers/net/wireless/iwlwifi/mvm/ops.c b/drivers/net/wireless/iwlwifi/mvm/ops.c index a37de3f410a0..f0cb092f980e 100644 --- a/drivers/net/wireless/iwlwifi/mvm/ops.c +++ b/drivers/net/wireless/iwlwifi/mvm/ops.c @@ -590,6 +590,7 @@ iwl_op_mode_mvm_start(struct iwl_trans *trans, const struct iwl_cfg *cfg, ieee80211_unregister_hw(mvm->hw); iwl_mvm_leds_exit(mvm); out_free: + flush_delayed_work(&mvm->fw_dump_wk); iwl_phy_db_free(mvm->phy_db); kfree(mvm->scan_cmd); if (!cfg->no_power_up_nic_in_init || !mvm->nvm_file_name) diff --git a/drivers/net/wireless/iwlwifi/pcie/drv.c b/drivers/net/wireless/iwlwifi/pcie/drv.c index b0825c402c73..644b58bc5226 100644 --- a/drivers/net/wireless/iwlwifi/pcie/drv.c +++ b/drivers/net/wireless/iwlwifi/pcie/drv.c @@ -414,6 +414,11 @@ static const struct pci_device_id iwl_hw_card_ids[] = { {IWL_PCI_DEVICE(0x095A, 0x5590, iwl7265_2ac_cfg)}, {IWL_PCI_DEVICE(0x095B, 0x5290, iwl7265_2ac_cfg)}, {IWL_PCI_DEVICE(0x095A, 0x5490, iwl7265_2ac_cfg)}, + {IWL_PCI_DEVICE(0x095A, 0x5F10, iwl7265_2ac_cfg)}, + {IWL_PCI_DEVICE(0x095B, 0x5212, iwl7265_2ac_cfg)}, + {IWL_PCI_DEVICE(0x095B, 0x520A, iwl7265_2ac_cfg)}, + {IWL_PCI_DEVICE(0x095A, 0x9000, iwl7265_2ac_cfg)}, + {IWL_PCI_DEVICE(0x095A, 0x9400, iwl7265_2ac_cfg)}, /* 8000 Series */ {IWL_PCI_DEVICE(0x24F3, 0x0010, iwl8260_2ac_cfg)}, diff --git a/drivers/net/wireless/rt2x00/rt2800usb.c b/drivers/net/wireless/rt2x00/rt2800usb.c index 5932306084fd..bf9afbf46c1b 100644 --- a/drivers/net/wireless/rt2x00/rt2800usb.c +++ b/drivers/net/wireless/rt2x00/rt2800usb.c @@ -1114,6 +1114,7 @@ static struct usb_device_id rt2800usb_device_table[] = { { USB_DEVICE(0x0db0, 0x871c) }, { USB_DEVICE(0x0db0, 0x899a) }, /* Ovislink */ + { USB_DEVICE(0x1b75, 0x3070) }, { USB_DEVICE(0x1b75, 0x3071) }, { USB_DEVICE(0x1b75, 0x3072) }, { USB_DEVICE(0x1b75, 0xa200) }, diff --git a/drivers/net/wireless/rtlwifi/pci.h b/drivers/net/wireless/rtlwifi/pci.h index d4567d12e07e..5da6703942d9 100644 --- a/drivers/net/wireless/rtlwifi/pci.h +++ b/drivers/net/wireless/rtlwifi/pci.h @@ -247,6 +247,8 @@ struct rtl_pci { /* MSI support */ bool msi_support; bool using_msi; + /* interrupt clear before set */ + bool int_clear; }; struct mp_adapter { diff --git a/drivers/net/wireless/rtlwifi/rtl8821ae/hw.c b/drivers/net/wireless/rtlwifi/rtl8821ae/hw.c index b7f18e2155eb..6e9418ed90c2 100644 --- a/drivers/net/wireless/rtlwifi/rtl8821ae/hw.c +++ b/drivers/net/wireless/rtlwifi/rtl8821ae/hw.c @@ -2253,11 +2253,28 @@ void rtl8821ae_set_qos(struct ieee80211_hw *hw, int aci) } } +static void rtl8821ae_clear_interrupt(struct ieee80211_hw *hw) +{ + struct rtl_priv *rtlpriv = rtl_priv(hw); + u32 tmp = rtl_read_dword(rtlpriv, REG_HISR); + + rtl_write_dword(rtlpriv, REG_HISR, tmp); + + tmp = rtl_read_dword(rtlpriv, REG_HISRE); + rtl_write_dword(rtlpriv, REG_HISRE, tmp); + + tmp = rtl_read_dword(rtlpriv, REG_HSISR); + rtl_write_dword(rtlpriv, REG_HSISR, tmp); +} + void rtl8821ae_enable_interrupt(struct ieee80211_hw *hw) { struct rtl_priv *rtlpriv = rtl_priv(hw); struct rtl_pci *rtlpci = rtl_pcidev(rtl_pcipriv(hw)); + if (!rtlpci->int_clear) + rtl8821ae_clear_interrupt(hw);/*clear it here first*/ + rtl_write_dword(rtlpriv, REG_HIMR, rtlpci->irq_mask[0] & 0xFFFFFFFF); rtl_write_dword(rtlpriv, REG_HIMRE, rtlpci->irq_mask[1] & 0xFFFFFFFF); rtlpci->irq_enabled = true; diff --git a/drivers/net/wireless/rtlwifi/rtl8821ae/sw.c b/drivers/net/wireless/rtlwifi/rtl8821ae/sw.c index a4988121e1ab..8ee141a55bc5 100644 --- a/drivers/net/wireless/rtlwifi/rtl8821ae/sw.c +++ b/drivers/net/wireless/rtlwifi/rtl8821ae/sw.c @@ -96,6 +96,7 @@ int rtl8821ae_init_sw_vars(struct ieee80211_hw *hw) rtl8821ae_bt_reg_init(hw); rtlpci->msi_support = rtlpriv->cfg->mod_params->msi_support; + rtlpci->int_clear = rtlpriv->cfg->mod_params->int_clear; rtlpriv->btcoexist.btc_ops = rtl_btc_get_ops_pointer(); rtlpriv->dm.dm_initialgain_enable = 1; @@ -167,6 +168,7 @@ int rtl8821ae_init_sw_vars(struct ieee80211_hw *hw) rtlpriv->psc.swctrl_lps = rtlpriv->cfg->mod_params->swctrl_lps; rtlpriv->psc.fwctrl_lps = rtlpriv->cfg->mod_params->fwctrl_lps; rtlpci->msi_support = rtlpriv->cfg->mod_params->msi_support; + rtlpci->msi_support = rtlpriv->cfg->mod_params->int_clear; if (rtlpriv->cfg->mod_params->disable_watchdog) pr_info("watchdog disabled\n"); rtlpriv->psc.reg_fwctrl_lps = 3; @@ -308,6 +310,7 @@ static struct rtl_mod_params rtl8821ae_mod_params = { .swctrl_lps = false, .fwctrl_lps = true, .msi_support = true, + .int_clear = true, .debug = DBG_EMERG, .disable_watchdog = 0, }; @@ -437,6 +440,7 @@ module_param_named(fwlps, rtl8821ae_mod_params.fwctrl_lps, bool, 0444); module_param_named(msi, rtl8821ae_mod_params.msi_support, bool, 0444); module_param_named(disable_watchdog, rtl8821ae_mod_params.disable_watchdog, bool, 0444); +module_param_named(int_clear, rtl8821ae_mod_params.int_clear, bool, 0444); MODULE_PARM_DESC(swenc, "Set to 1 for software crypto (default 0)\n"); MODULE_PARM_DESC(ips, "Set to 0 to not use link power save (default 1)\n"); MODULE_PARM_DESC(swlps, "Set to 1 to use SW control power save (default 0)\n"); @@ -444,6 +448,7 @@ MODULE_PARM_DESC(fwlps, "Set to 1 to use FW control power save (default 1)\n"); MODULE_PARM_DESC(msi, "Set to 1 to use MSI interrupts mode (default 1)\n"); MODULE_PARM_DESC(debug, "Set debug level (0-5) (default 0)"); MODULE_PARM_DESC(disable_watchdog, "Set to 1 to disable the watchdog (default 0)\n"); +MODULE_PARM_DESC(int_clear, "Set to 1 to disable interrupt clear before set (default 0)\n"); static SIMPLE_DEV_PM_OPS(rtlwifi_pm_ops, rtl_pci_suspend, rtl_pci_resume); diff --git a/drivers/net/wireless/rtlwifi/wifi.h b/drivers/net/wireless/rtlwifi/wifi.h index b90ca618b123..4544752a2ba8 100644 --- a/drivers/net/wireless/rtlwifi/wifi.h +++ b/drivers/net/wireless/rtlwifi/wifi.h @@ -2249,6 +2249,9 @@ struct rtl_mod_params { /* default 0: 1 means disable */ bool disable_watchdog; + + /* default 0: 1 means do not disable interrupts */ + bool int_clear; }; struct rtl_hal_usbint_cfg { diff --git a/drivers/net/xen-netback/xenbus.c b/drivers/net/xen-netback/xenbus.c index 929a6e7e5ecf..56ebd8267386 100644 --- a/drivers/net/xen-netback/xenbus.c +++ b/drivers/net/xen-netback/xenbus.c @@ -788,6 +788,12 @@ static void connect(struct backend_info *be) /* Use the number of queues requested by the frontend */ be->vif->queues = vzalloc(requested_num_queues * sizeof(struct xenvif_queue)); + if (!be->vif->queues) { + xenbus_dev_fatal(dev, -ENOMEM, + "allocating queues"); + return; + } + be->vif->num_queues = requested_num_queues; be->vif->stalled_queues = requested_num_queues; diff --git a/drivers/net/xen-netfront.c b/drivers/net/xen-netfront.c index f821a97d7827..6febc053a37f 100644 --- a/drivers/net/xen-netfront.c +++ b/drivers/net/xen-netfront.c @@ -1706,19 +1706,19 @@ static void xennet_destroy_queues(struct netfront_info *info) } static int xennet_create_queues(struct netfront_info *info, - unsigned int num_queues) + unsigned int *num_queues) { unsigned int i; int ret; - info->queues = kcalloc(num_queues, sizeof(struct netfront_queue), + info->queues = kcalloc(*num_queues, sizeof(struct netfront_queue), GFP_KERNEL); if (!info->queues) return -ENOMEM; rtnl_lock(); - for (i = 0; i < num_queues; i++) { + for (i = 0; i < *num_queues; i++) { struct netfront_queue *queue = &info->queues[i]; queue->id = i; @@ -1728,7 +1728,7 @@ static int xennet_create_queues(struct netfront_info *info, if (ret < 0) { dev_warn(&info->netdev->dev, "only created %d queues\n", i); - num_queues = i; + *num_queues = i; break; } @@ -1738,11 +1738,11 @@ static int xennet_create_queues(struct netfront_info *info, napi_enable(&queue->napi); } - netif_set_real_num_tx_queues(info->netdev, num_queues); + netif_set_real_num_tx_queues(info->netdev, *num_queues); rtnl_unlock(); - if (num_queues == 0) { + if (*num_queues == 0) { dev_err(&info->netdev->dev, "no queues\n"); return -EINVAL; } @@ -1788,7 +1788,7 @@ static int talk_to_netback(struct xenbus_device *dev, if (info->queues) xennet_destroy_queues(info); - err = xennet_create_queues(info, num_queues); + err = xennet_create_queues(info, &num_queues); if (err < 0) goto destroy_ring; diff --git a/drivers/pci/pci-sysfs.c b/drivers/pci/pci-sysfs.c index 312f23a8429c..92618686604c 100644 --- a/drivers/pci/pci-sysfs.c +++ b/drivers/pci/pci-sysfs.c @@ -216,7 +216,7 @@ static ssize_t numa_node_store(struct device *dev, if (ret) return ret; - if (!node_online(node)) + if (node >= MAX_NUMNODES || !node_online(node)) return -EINVAL; add_taint(TAINT_FIRMWARE_WORKAROUND, LOCKDEP_STILL_OK); diff --git a/drivers/perf/arm_pmu.c b/drivers/perf/arm_pmu.c index 2365a32a595e..be3755c973e9 100644 --- a/drivers/perf/arm_pmu.c +++ b/drivers/perf/arm_pmu.c @@ -823,9 +823,15 @@ static int of_pmu_irq_cfg(struct arm_pmu *pmu) } /* Now look up the logical CPU number */ - for_each_possible_cpu(cpu) - if (dn == of_cpu_device_node_get(cpu)) + for_each_possible_cpu(cpu) { + struct device_node *cpu_dn; + + cpu_dn = of_cpu_device_node_get(cpu); + of_node_put(cpu_dn); + + if (dn == cpu_dn) break; + } if (cpu >= nr_cpu_ids) { pr_warn("Failed to find logical CPU for %s\n", diff --git a/drivers/scsi/mvsas/mv_sas.c b/drivers/scsi/mvsas/mv_sas.c index 454536c49315..9c780740fb82 100644 --- a/drivers/scsi/mvsas/mv_sas.c +++ b/drivers/scsi/mvsas/mv_sas.c @@ -887,6 +887,8 @@ static void mvs_slot_free(struct mvs_info *mvi, u32 rx_desc) static void mvs_slot_task_free(struct mvs_info *mvi, struct sas_task *task, struct mvs_slot_info *slot, u32 slot_idx) { + if (!slot) + return; if (!slot->task) return; if (!sas_protocol_ata(task->task_proto)) diff --git a/drivers/scsi/scsi_dh.c b/drivers/scsi/scsi_dh.c index 0a2168e69bbc..e7649ed3f667 100644 --- a/drivers/scsi/scsi_dh.c +++ b/drivers/scsi/scsi_dh.c @@ -226,16 +226,20 @@ int scsi_dh_add_device(struct scsi_device *sdev) drv = scsi_dh_find_driver(sdev); if (drv) - devinfo = scsi_dh_lookup(drv); + devinfo = __scsi_dh_lookup(drv); if (devinfo) err = scsi_dh_handler_attach(sdev, devinfo); return err; } -void scsi_dh_remove_device(struct scsi_device *sdev) +void scsi_dh_release_device(struct scsi_device *sdev) { if (sdev->handler) scsi_dh_handler_detach(sdev); +} + +void scsi_dh_remove_device(struct scsi_device *sdev) +{ device_remove_file(&sdev->sdev_gendev, &scsi_dh_state_attr); } diff --git a/drivers/scsi/scsi_priv.h b/drivers/scsi/scsi_priv.h index 644bb7339b55..4d01cdb1b348 100644 --- a/drivers/scsi/scsi_priv.h +++ b/drivers/scsi/scsi_priv.h @@ -173,9 +173,11 @@ extern struct async_domain scsi_sd_probe_domain; /* scsi_dh.c */ #ifdef CONFIG_SCSI_DH int scsi_dh_add_device(struct scsi_device *sdev); +void scsi_dh_release_device(struct scsi_device *sdev); void scsi_dh_remove_device(struct scsi_device *sdev); #else static inline int scsi_dh_add_device(struct scsi_device *sdev) { return 0; } +static inline void scsi_dh_release_device(struct scsi_device *sdev) { } static inline void scsi_dh_remove_device(struct scsi_device *sdev) { } #endif diff --git a/drivers/scsi/scsi_sysfs.c b/drivers/scsi/scsi_sysfs.c index b333389f248f..dff8fafb741c 100644 --- a/drivers/scsi/scsi_sysfs.c +++ b/drivers/scsi/scsi_sysfs.c @@ -399,6 +399,8 @@ static void scsi_device_dev_release_usercontext(struct work_struct *work) sdev = container_of(work, struct scsi_device, ew.work); + scsi_dh_release_device(sdev); + parent = sdev->sdev_gendev.parent; spin_lock_irqsave(sdev->host->host_lock, flags); diff --git a/drivers/staging/iio/accel/sca3000_ring.c b/drivers/staging/iio/accel/sca3000_ring.c index 23685e74917e..bd2c69f85949 100644 --- a/drivers/staging/iio/accel/sca3000_ring.c +++ b/drivers/staging/iio/accel/sca3000_ring.c @@ -116,7 +116,7 @@ static int sca3000_read_first_n_hw_rb(struct iio_buffer *r, if (ret) goto error_ret; - for (i = 0; i < num_read; i++) + for (i = 0; i < num_read / sizeof(u16); i++) *(((u16 *)rx) + i) = be16_to_cpup((__be16 *)rx + i); if (copy_to_user(buf, rx, num_read)) diff --git a/drivers/staging/iio/adc/mxs-lradc.c b/drivers/staging/iio/adc/mxs-lradc.c index 3f7715c9968b..47fc00a3f63b 100644 --- a/drivers/staging/iio/adc/mxs-lradc.c +++ b/drivers/staging/iio/adc/mxs-lradc.c @@ -915,11 +915,12 @@ static int mxs_lradc_read_raw(struct iio_dev *iio_dev, case IIO_CHAN_INFO_OFFSET: if (chan->type == IIO_TEMP) { /* The calculated value from the ADC is in Kelvin, we - * want Celsius for hwmon so the offset is - * -272.15 * scale + * want Celsius for hwmon so the offset is -273.15 + * The offset is applied before scaling so it is + * actually -213.15 * 4 / 1.012 = -1079.644268 */ - *val = -1075; - *val2 = 691699; + *val = -1079; + *val2 = 644268; return IIO_VAL_INT_PLUS_MICRO; } diff --git a/drivers/thermal/samsung/exynos_tmu.c b/drivers/thermal/samsung/exynos_tmu.c index 0bae8cc6c23a..ca920b0ecf8f 100644 --- a/drivers/thermal/samsung/exynos_tmu.c +++ b/drivers/thermal/samsung/exynos_tmu.c @@ -932,7 +932,7 @@ static void exynos4412_tmu_set_emulation(struct exynos_tmu_data *data, if (data->soc == SOC_ARCH_EXYNOS5260) emul_con = EXYNOS5260_EMUL_CON; - if (data->soc == SOC_ARCH_EXYNOS5433) + else if (data->soc == SOC_ARCH_EXYNOS5433) emul_con = EXYNOS5433_TMU_EMUL_CON; else if (data->soc == SOC_ARCH_EXYNOS7) emul_con = EXYNOS7_TMU_REG_EMUL_CON; diff --git a/drivers/tty/serial/8250/8250_dma.c b/drivers/tty/serial/8250/8250_dma.c index 21d01a491405..e508939daea3 100644 --- a/drivers/tty/serial/8250/8250_dma.c +++ b/drivers/tty/serial/8250/8250_dma.c @@ -80,10 +80,6 @@ int serial8250_tx_dma(struct uart_8250_port *p) return 0; dma->tx_size = CIRC_CNT_TO_END(xmit->head, xmit->tail, UART_XMIT_SIZE); - if (dma->tx_size < p->port.fifosize) { - ret = -EINVAL; - goto err; - } desc = dmaengine_prep_slave_single(dma->txchan, dma->tx_addr + xmit->tail, diff --git a/drivers/usb/host/xhci-pci.c b/drivers/usb/host/xhci-pci.c index c79d33676672..c47d3e480586 100644 --- a/drivers/usb/host/xhci-pci.c +++ b/drivers/usb/host/xhci-pci.c @@ -147,6 +147,7 @@ static void xhci_pci_quirks(struct device *dev, struct xhci_hcd *xhci) if (pdev->vendor == PCI_VENDOR_ID_INTEL && pdev->device == PCI_DEVICE_ID_INTEL_LYNXPOINT_LP_XHCI) { xhci->quirks |= XHCI_SPURIOUS_REBOOT; + xhci->quirks |= XHCI_SPURIOUS_WAKEUP; } if (pdev->vendor == PCI_VENDOR_ID_INTEL && (pdev->device == PCI_DEVICE_ID_INTEL_SUNRISEPOINT_LP_XHCI || diff --git a/drivers/usb/host/xhci-ring.c b/drivers/usb/host/xhci-ring.c index 43291f93afeb..97ffe3997273 100644 --- a/drivers/usb/host/xhci-ring.c +++ b/drivers/usb/host/xhci-ring.c @@ -2191,6 +2191,10 @@ static int process_bulk_intr_td(struct xhci_hcd *xhci, struct xhci_td *td, } /* Fast path - was this the last TRB in the TD for this URB? */ } else if (event_trb == td->last_trb) { + if (td->urb_length_set && trb_comp_code == COMP_SHORT_TX) + return finish_td(xhci, td, event_trb, event, ep, + status, false); + if (EVENT_TRB_LEN(le32_to_cpu(event->transfer_len)) != 0) { td->urb->actual_length = td->urb->transfer_buffer_length - @@ -2242,6 +2246,12 @@ static int process_bulk_intr_td(struct xhci_hcd *xhci, struct xhci_td *td, td->urb->actual_length += TRB_LEN(le32_to_cpu(cur_trb->generic.field[2])) - EVENT_TRB_LEN(le32_to_cpu(event->transfer_len)); + + if (trb_comp_code == COMP_SHORT_TX) { + xhci_dbg(xhci, "mid bulk/intr SP, wait for last TRB event\n"); + td->urb_length_set = true; + return 0; + } } return finish_td(xhci, td, event_trb, event, ep, status, false); @@ -2274,6 +2284,7 @@ static int handle_tx_event(struct xhci_hcd *xhci, u32 trb_comp_code; int ret = 0; int td_num = 0; + bool handling_skipped_tds = false; slot_id = TRB_TO_SLOT_ID(le32_to_cpu(event->flags)); xdev = xhci->devs[slot_id]; @@ -2410,6 +2421,10 @@ static int handle_tx_event(struct xhci_hcd *xhci, ep->skip = true; xhci_dbg(xhci, "Miss service interval error, set skip flag\n"); goto cleanup; + case COMP_PING_ERR: + ep->skip = true; + xhci_dbg(xhci, "No Ping response error, Skip one Isoc TD\n"); + goto cleanup; default: if (xhci_is_vendor_info_code(xhci, trb_comp_code)) { status = 0; @@ -2546,13 +2561,18 @@ static int handle_tx_event(struct xhci_hcd *xhci, ep, &status); cleanup: + + + handling_skipped_tds = ep->skip && + trb_comp_code != COMP_MISSED_INT && + trb_comp_code != COMP_PING_ERR; + /* - * Do not update event ring dequeue pointer if ep->skip is set. - * Will roll back to continue process missed tds. + * Do not update event ring dequeue pointer if we're in a loop + * processing missed tds. */ - if (trb_comp_code == COMP_MISSED_INT || !ep->skip) { + if (!handling_skipped_tds) inc_deq(xhci, xhci->event_ring); - } if (ret) { urb = td->urb; @@ -2587,7 +2607,7 @@ cleanup: * Process them as short transfer until reach the td pointed by * the event. */ - } while (ep->skip && trb_comp_code != COMP_MISSED_INT); + } while (handling_skipped_tds); return 0; } diff --git a/drivers/usb/musb/omap2430.c b/drivers/usb/musb/omap2430.c index 70f2b8a2e6cf..1bd9232ff76f 100644 --- a/drivers/usb/musb/omap2430.c +++ b/drivers/usb/musb/omap2430.c @@ -391,9 +391,20 @@ static int omap2430_musb_init(struct musb *musb) } musb->isr = omap2430_musb_interrupt; + /* + * Enable runtime PM for musb parent (this driver). We can't + * do it earlier as struct musb is not yet allocated and we + * need to touch the musb registers for runtime PM. + */ + pm_runtime_enable(glue->dev); + status = pm_runtime_get_sync(glue->dev); + if (status < 0) + goto err1; + status = pm_runtime_get_sync(dev); if (status < 0) { dev_err(dev, "pm_runtime_get_sync FAILED %d\n", status); + pm_runtime_put_sync(glue->dev); goto err1; } @@ -426,6 +437,7 @@ static int omap2430_musb_init(struct musb *musb) phy_power_on(musb->phy); pm_runtime_put_noidle(musb->controller); + pm_runtime_put_noidle(glue->dev); return 0; err1: @@ -626,7 +638,11 @@ static int omap2430_probe(struct platform_device *pdev) goto err2; } - pm_runtime_enable(&pdev->dev); + /* + * Note that we cannot enable PM runtime yet for this + * driver as we need struct musb initialized first. + * See omap2430_musb_init above. + */ ret = platform_device_add(musb); if (ret) { @@ -675,11 +691,12 @@ static int omap2430_runtime_resume(struct device *dev) struct omap2430_glue *glue = dev_get_drvdata(dev); struct musb *musb = glue_to_musb(glue); - if (musb) { - omap2430_low_level_init(musb); - musb_writel(musb->mregs, OTG_INTERFSEL, - musb->context.otg_interfsel); - } + if (!musb) + return -EPROBE_DEFER; + + omap2430_low_level_init(musb); + musb_writel(musb->mregs, OTG_INTERFSEL, + musb->context.otg_interfsel); return 0; } diff --git a/drivers/vhost/vhost.h b/drivers/vhost/vhost.h index 4772862b71a7..d3f767448a72 100644 --- a/drivers/vhost/vhost.h +++ b/drivers/vhost/vhost.h @@ -183,10 +183,17 @@ static inline bool vhost_has_feature(struct vhost_virtqueue *vq, int bit) return vq->acked_features & (1ULL << bit); } +#ifdef CONFIG_VHOST_CROSS_ENDIAN_LEGACY static inline bool vhost_is_little_endian(struct vhost_virtqueue *vq) { return vq->is_le; } +#else +static inline bool vhost_is_little_endian(struct vhost_virtqueue *vq) +{ + return virtio_legacy_is_little_endian() || vq->is_le; +} +#endif /* Memory accessors */ static inline u16 vhost16_to_cpu(struct vhost_virtqueue *vq, __virtio16 val) diff --git a/drivers/video/console/fbcon.c b/drivers/video/console/fbcon.c index 1aaf89300621..92f394927f24 100644 --- a/drivers/video/console/fbcon.c +++ b/drivers/video/console/fbcon.c @@ -1093,6 +1093,7 @@ static void fbcon_init(struct vc_data *vc, int init) con_copy_unimap(vc, svc); ops = info->fbcon_par; + ops->cur_blink_jiffies = msecs_to_jiffies(vc->vc_cur_blink_ms); p->con_rotate = initial_rotation; set_blitting_type(vc, info); diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index b823fac91c92..8c6f247ba81d 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -2584,7 +2584,7 @@ static long btrfs_fallocate(struct file *file, int mode, alloc_start); if (ret) goto out; - } else { + } else if (offset + len > inode->i_size) { /* * If we are fallocating from the end of the file onward we * need to zero out the end of the page if i_size lands in the diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index 3e3e6130637f..8d20f3b1cab0 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -4641,7 +4641,7 @@ locked: if (bctl->flags & ~(BTRFS_BALANCE_ARGS_MASK | BTRFS_BALANCE_TYPE_MASK)) { ret = -EINVAL; - goto out_bargs; + goto out_bctl; } do_balance: @@ -4655,12 +4655,15 @@ do_balance: need_unlock = false; ret = btrfs_balance(bctl, bargs); + bctl = NULL; if (arg) { if (copy_to_user(arg, bargs, sizeof(*bargs))) ret = -EFAULT; } +out_bctl: + kfree(bctl); out_bargs: kfree(bargs); out_unlock: diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index 1386709e9c91..ab2877a727b2 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -778,19 +778,24 @@ static void bdi_split_work_to_wbs(struct backing_dev_info *bdi, struct wb_writeback_work *base_work, bool skip_if_busy) { - int next_memcg_id = 0; - struct bdi_writeback *wb; - struct wb_iter iter; + struct bdi_writeback *last_wb = NULL; + struct bdi_writeback *wb = list_entry_rcu(&bdi->wb_list, + struct bdi_writeback, bdi_node); might_sleep(); restart: rcu_read_lock(); - bdi_for_each_wb(wb, bdi, &iter, next_memcg_id) { + list_for_each_entry_continue_rcu(wb, &bdi->wb_list, bdi_node) { DEFINE_WB_COMPLETION_ONSTACK(fallback_work_done); struct wb_writeback_work fallback_work; struct wb_writeback_work *work; long nr_pages; + if (last_wb) { + wb_put(last_wb); + last_wb = NULL; + } + /* SYNC_ALL writes out I_DIRTY_TIME too */ if (!wb_has_dirty_io(wb) && (base_work->sync_mode == WB_SYNC_NONE || @@ -819,12 +824,22 @@ restart: wb_queue_work(wb, work); - next_memcg_id = wb->memcg_css->id + 1; + /* + * Pin @wb so that it stays on @bdi->wb_list. This allows + * continuing iteration from @wb after dropping and + * regrabbing rcu read lock. + */ + wb_get(wb); + last_wb = wb; + rcu_read_unlock(); wb_wait_for_completion(bdi, &fallback_work_done); goto restart; } rcu_read_unlock(); + + if (last_wb) + wb_put(last_wb); } #else /* CONFIG_CGROUP_WRITEBACK */ @@ -1857,12 +1872,11 @@ void wakeup_flusher_threads(long nr_pages, enum wb_reason reason) rcu_read_lock(); list_for_each_entry_rcu(bdi, &bdi_list, bdi_list) { struct bdi_writeback *wb; - struct wb_iter iter; if (!bdi_has_dirty_io(bdi)) continue; - bdi_for_each_wb(wb, bdi, &iter, 0) + list_for_each_entry_rcu(wb, &bdi->wb_list, bdi_node) wb_start_writeback(wb, wb_split_bdi_pages(wb, nr_pages), false, reason); } @@ -1894,11 +1908,10 @@ static void wakeup_dirtytime_writeback(struct work_struct *w) rcu_read_lock(); list_for_each_entry_rcu(bdi, &bdi_list, bdi_list) { struct bdi_writeback *wb; - struct wb_iter iter; - bdi_for_each_wb(wb, bdi, &iter, 0) - if (!list_empty(&bdi->wb.b_dirty_time)) - wb_wakeup(&bdi->wb); + list_for_each_entry_rcu(wb, &bdi->wb_list, bdi_node) + if (!list_empty(&wb->b_dirty_time)) + wb_wakeup(wb); } rcu_read_unlock(); schedule_delayed_work(&dirtytime_work, dirtytime_expire_interval * HZ); diff --git a/fs/ocfs2/dlm/dlmmaster.c b/fs/ocfs2/dlm/dlmmaster.c index ee5aa4daaea0..ce38b4ccc9ab 100644 --- a/fs/ocfs2/dlm/dlmmaster.c +++ b/fs/ocfs2/dlm/dlmmaster.c @@ -1658,12 +1658,13 @@ send_response: if (ret < 0) { mlog(ML_ERROR, "failed to dispatch assert master work\n"); response = DLM_MASTER_RESP_ERROR; + spin_unlock(&res->spinlock); dlm_lockres_put(res); } else { dispatched = 1; __dlm_lockres_grab_inflight_worker(dlm, res); + spin_unlock(&res->spinlock); } - spin_unlock(&res->spinlock); } else { if (res) dlm_lockres_put(res); diff --git a/fs/ocfs2/dlm/dlmrecovery.c b/fs/ocfs2/dlm/dlmrecovery.c index 3d90ad7ff91f..58eaa5c0d387 100644 --- a/fs/ocfs2/dlm/dlmrecovery.c +++ b/fs/ocfs2/dlm/dlmrecovery.c @@ -1723,8 +1723,8 @@ int dlm_master_requery_handler(struct o2net_msg *msg, u32 len, void *data, } else { dispatched = 1; __dlm_lockres_grab_inflight_worker(dlm, res); + spin_unlock(&res->spinlock); } - spin_unlock(&res->spinlock); } else { /* put.. incase we are not the master */ spin_unlock(&res->spinlock); diff --git a/fs/overlayfs/copy_up.c b/fs/overlayfs/copy_up.c index 84d693d37428..871fcb67be97 100644 --- a/fs/overlayfs/copy_up.c +++ b/fs/overlayfs/copy_up.c @@ -81,11 +81,11 @@ static int ovl_copy_up_data(struct path *old, struct path *new, loff_t len) if (len == 0) return 0; - old_file = ovl_path_open(old, O_RDONLY); + old_file = ovl_path_open(old, O_LARGEFILE | O_RDONLY); if (IS_ERR(old_file)) return PTR_ERR(old_file); - new_file = ovl_path_open(new, O_WRONLY); + new_file = ovl_path_open(new, O_LARGEFILE | O_WRONLY); if (IS_ERR(new_file)) { error = PTR_ERR(new_file); goto out_fput; @@ -267,7 +267,7 @@ out: out_cleanup: ovl_cleanup(wdir, newdentry); - goto out; + goto out2; } /* diff --git a/fs/overlayfs/inode.c b/fs/overlayfs/inode.c index d9da5a4e9382..ec0c2a050043 100644 --- a/fs/overlayfs/inode.c +++ b/fs/overlayfs/inode.c @@ -363,6 +363,9 @@ struct inode *ovl_d_select_inode(struct dentry *dentry, unsigned file_flags) ovl_path_upper(dentry, &realpath); } + if (realpath.dentry->d_flags & DCACHE_OP_SELECT_INODE) + return realpath.dentry->d_op->d_select_inode(realpath.dentry, file_flags); + return d_backing_inode(realpath.dentry); } diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c index 79073d68b475..e38ee0fed24a 100644 --- a/fs/overlayfs/super.c +++ b/fs/overlayfs/super.c @@ -544,6 +544,7 @@ static void ovl_put_super(struct super_block *sb) mntput(ufs->upper_mnt); for (i = 0; i < ufs->numlower; i++) mntput(ufs->lower_mnt[i]); + kfree(ufs->lower_mnt); kfree(ufs->config.lowerdir); kfree(ufs->config.upperdir); @@ -1048,6 +1049,7 @@ static int ovl_fill_super(struct super_block *sb, void *data, int silent) oe->lowerstack[i].dentry = stack[i].dentry; oe->lowerstack[i].mnt = ufs->lower_mnt[i]; } + kfree(stack); root_dentry->d_fsdata = oe; diff --git a/include/linux/backing-dev-defs.h b/include/linux/backing-dev-defs.h index a23209b43842..1b4d69f68c33 100644 --- a/include/linux/backing-dev-defs.h +++ b/include/linux/backing-dev-defs.h @@ -116,6 +116,8 @@ struct bdi_writeback { struct list_head work_list; struct delayed_work dwork; /* work item used for writeback */ + struct list_head bdi_node; /* anchored at bdi->wb_list */ + #ifdef CONFIG_CGROUP_WRITEBACK struct percpu_ref refcnt; /* used only for !root wb's */ struct fprop_local_percpu memcg_completions; @@ -150,6 +152,7 @@ struct backing_dev_info { atomic_long_t tot_write_bandwidth; struct bdi_writeback wb; /* the root writeback info for this bdi */ + struct list_head wb_list; /* list of all wbs */ #ifdef CONFIG_CGROUP_WRITEBACK struct radix_tree_root cgwb_tree; /* radix tree of active cgroup wbs */ struct rb_root cgwb_congested_tree; /* their congested states */ diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h index d5eb4ad1c534..c85f74946a8b 100644 --- a/include/linux/backing-dev.h +++ b/include/linux/backing-dev.h @@ -19,13 +19,17 @@ #include <linux/slab.h> int __must_check bdi_init(struct backing_dev_info *bdi); -void bdi_destroy(struct backing_dev_info *bdi); +void bdi_exit(struct backing_dev_info *bdi); __printf(3, 4) int bdi_register(struct backing_dev_info *bdi, struct device *parent, const char *fmt, ...); int bdi_register_dev(struct backing_dev_info *bdi, dev_t dev); +void bdi_unregister(struct backing_dev_info *bdi); + int __must_check bdi_setup_and_register(struct backing_dev_info *, char *); +void bdi_destroy(struct backing_dev_info *bdi); + void wb_start_writeback(struct bdi_writeback *wb, long nr_pages, bool range_cyclic, enum wb_reason reason); void wb_start_background_writeback(struct bdi_writeback *wb); @@ -408,61 +412,6 @@ static inline void unlocked_inode_to_wb_end(struct inode *inode, bool locked) rcu_read_unlock(); } -struct wb_iter { - int start_memcg_id; - struct radix_tree_iter tree_iter; - void **slot; -}; - -static inline struct bdi_writeback *__wb_iter_next(struct wb_iter *iter, - struct backing_dev_info *bdi) -{ - struct radix_tree_iter *titer = &iter->tree_iter; - - WARN_ON_ONCE(!rcu_read_lock_held()); - - if (iter->start_memcg_id >= 0) { - iter->slot = radix_tree_iter_init(titer, iter->start_memcg_id); - iter->start_memcg_id = -1; - } else { - iter->slot = radix_tree_next_slot(iter->slot, titer, 0); - } - - if (!iter->slot) - iter->slot = radix_tree_next_chunk(&bdi->cgwb_tree, titer, 0); - if (iter->slot) - return *iter->slot; - return NULL; -} - -static inline struct bdi_writeback *__wb_iter_init(struct wb_iter *iter, - struct backing_dev_info *bdi, - int start_memcg_id) -{ - iter->start_memcg_id = start_memcg_id; - - if (start_memcg_id) - return __wb_iter_next(iter, bdi); - else - return &bdi->wb; -} - -/** - * bdi_for_each_wb - walk all wb's of a bdi in ascending memcg ID order - * @wb_cur: cursor struct bdi_writeback pointer - * @bdi: bdi to walk wb's of - * @iter: pointer to struct wb_iter to be used as iteration buffer - * @start_memcg_id: memcg ID to start iteration from - * - * Iterate @wb_cur through the wb's (bdi_writeback's) of @bdi in ascending - * memcg ID order starting from @start_memcg_id. @iter is struct wb_iter - * to be used as temp storage during iteration. rcu_read_lock() must be - * held throughout iteration. - */ -#define bdi_for_each_wb(wb_cur, bdi, iter, start_memcg_id) \ - for ((wb_cur) = __wb_iter_init(iter, bdi, start_memcg_id); \ - (wb_cur); (wb_cur) = __wb_iter_next(iter, bdi)) - #else /* CONFIG_CGROUP_WRITEBACK */ static inline bool inode_cgwb_enabled(struct inode *inode) @@ -522,14 +471,6 @@ static inline void wb_blkcg_offline(struct blkcg *blkcg) { } -struct wb_iter { - int next_id; -}; - -#define bdi_for_each_wb(wb_cur, bdi, iter, start_blkcg_id) \ - for ((iter)->next_id = (start_blkcg_id); \ - ({ (wb_cur) = !(iter)->next_id++ ? &(bdi)->wb : NULL; }); ) - static inline int inode_congested(struct inode *inode, int cong_bits) { return wb_congested(&inode_to_bdi(inode)->wb, cong_bits); diff --git a/include/linux/blk-cgroup.h b/include/linux/blk-cgroup.h index 0a5cc7a1109b..c02e669945e9 100644 --- a/include/linux/blk-cgroup.h +++ b/include/linux/blk-cgroup.h @@ -713,9 +713,9 @@ static inline bool blkcg_bio_issue_check(struct request_queue *q, if (!throtl) { blkg = blkg ?: q->root_blkg; - blkg_rwstat_add(&blkg->stat_bytes, bio->bi_flags, + blkg_rwstat_add(&blkg->stat_bytes, bio->bi_rw, bio->bi_iter.bi_size); - blkg_rwstat_add(&blkg->stat_ios, bio->bi_flags, 1); + blkg_rwstat_add(&blkg->stat_ios, bio->bi_rw, 1); } rcu_read_unlock(); diff --git a/include/linux/cma.h b/include/linux/cma.h index f7ef093ec49a..29f9e774ab76 100644 --- a/include/linux/cma.h +++ b/include/linux/cma.h @@ -26,6 +26,6 @@ extern int __init cma_declare_contiguous(phys_addr_t base, extern int cma_init_reserved_mem(phys_addr_t base, phys_addr_t size, unsigned int order_per_bit, struct cma **res_cma); -extern struct page *cma_alloc(struct cma *cma, unsigned int count, unsigned int align); +extern struct page *cma_alloc(struct cma *cma, size_t count, unsigned int align); extern bool cma_release(struct cma *cma, const struct page *pages, unsigned int count); #endif diff --git a/include/linux/compat.h b/include/linux/compat.h index a76c9172b2eb..0a25d9041b8b 100644 --- a/include/linux/compat.h +++ b/include/linux/compat.h @@ -24,6 +24,10 @@ #define COMPAT_USE_64BIT_TIME 0 #endif +#ifndef COMPAT_USE_NATIVE_SIGINFO +#define COMPAT_USE_NATIVE_SIGINFO 0 +#endif + #ifndef __SC_DELOUSE #define __SC_DELOUSE(t,v) ((t)(unsigned long)(v)) #endif diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h index dfaa7b3e9ae9..8efb40e61d6e 100644 --- a/include/linux/compiler-gcc.h +++ b/include/linux/compiler-gcc.h @@ -237,12 +237,25 @@ #define KASAN_ABI_VERSION 3 #endif +#if GCC_VERSION >= 40902 +/* + * Tell the compiler that address safety instrumentation (KASAN) + * should not be applied to that function. + * Conflicts with inlining: https://gcc.gnu.org/bugzilla/show_bug.cgi?id=67368 + */ +#define __no_sanitize_address __attribute__((no_sanitize_address)) +#endif + #endif /* gcc version >= 40000 specific checks */ #if !defined(__noclone) #define __noclone /* not needed */ #endif +#if !defined(__no_sanitize_address) +#define __no_sanitize_address +#endif + /* * A trick to suppress uninitialized variable warning without generating any * code diff --git a/include/linux/compiler.h b/include/linux/compiler.h index c836eb2dc44d..3d7810341b57 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -198,19 +198,45 @@ void ftrace_likely_update(struct ftrace_branch_data *f, int val, int expect); #include <uapi/linux/types.h> -static __always_inline void __read_once_size(const volatile void *p, void *res, int size) +#define __READ_ONCE_SIZE \ +({ \ + switch (size) { \ + case 1: *(__u8 *)res = *(volatile __u8 *)p; break; \ + case 2: *(__u16 *)res = *(volatile __u16 *)p; break; \ + case 4: *(__u32 *)res = *(volatile __u32 *)p; break; \ + case 8: *(__u64 *)res = *(volatile __u64 *)p; break; \ + default: \ + barrier(); \ + __builtin_memcpy((void *)res, (const void *)p, size); \ + barrier(); \ + } \ +}) + +static __always_inline +void __read_once_size(const volatile void *p, void *res, int size) { - switch (size) { - case 1: *(__u8 *)res = *(volatile __u8 *)p; break; - case 2: *(__u16 *)res = *(volatile __u16 *)p; break; - case 4: *(__u32 *)res = *(volatile __u32 *)p; break; - case 8: *(__u64 *)res = *(volatile __u64 *)p; break; - default: - barrier(); - __builtin_memcpy((void *)res, (const void *)p, size); - barrier(); - } + __READ_ONCE_SIZE; +} + +#ifdef CONFIG_KASAN +/* + * This function is not 'inline' because __no_sanitize_address confilcts + * with inlining. Attempt to inline it may cause a build failure. + * https://gcc.gnu.org/bugzilla/show_bug.cgi?id=67368 + * '__maybe_unused' allows us to avoid defined-but-not-used warnings. + */ +static __no_sanitize_address __maybe_unused +void __read_once_size_nocheck(const volatile void *p, void *res, int size) +{ + __READ_ONCE_SIZE; +} +#else +static __always_inline +void __read_once_size_nocheck(const volatile void *p, void *res, int size) +{ + __READ_ONCE_SIZE; } +#endif static __always_inline void __write_once_size(volatile void *p, void *res, int size) { @@ -248,8 +274,22 @@ static __always_inline void __write_once_size(volatile void *p, void *res, int s * required ordering. */ -#define READ_ONCE(x) \ - ({ union { typeof(x) __val; char __c[1]; } __u; __read_once_size(&(x), __u.__c, sizeof(x)); __u.__val; }) +#define __READ_ONCE(x, check) \ +({ \ + union { typeof(x) __val; char __c[1]; } __u; \ + if (check) \ + __read_once_size(&(x), __u.__c, sizeof(x)); \ + else \ + __read_once_size_nocheck(&(x), __u.__c, sizeof(x)); \ + __u.__val; \ +}) +#define READ_ONCE(x) __READ_ONCE(x, 1) + +/* + * Use READ_ONCE_NOCHECK() instead of READ_ONCE() if you need + * to hide memory access from KASAN. + */ +#define READ_ONCE_NOCHECK(x) __READ_ONCE(x, 0) #define WRITE_ONCE(x, val) \ ({ \ diff --git a/include/linux/dma-contiguous.h b/include/linux/dma-contiguous.h index 569bbd039896..fec734df1524 100644 --- a/include/linux/dma-contiguous.h +++ b/include/linux/dma-contiguous.h @@ -111,7 +111,7 @@ static inline int dma_declare_contiguous(struct device *dev, phys_addr_t size, return ret; } -struct page *dma_alloc_from_contiguous(struct device *dev, int count, +struct page *dma_alloc_from_contiguous(struct device *dev, size_t count, unsigned int order); bool dma_release_from_contiguous(struct device *dev, struct page *pages, int count); @@ -144,7 +144,7 @@ int dma_declare_contiguous(struct device *dev, phys_addr_t size, } static inline -struct page *dma_alloc_from_contiguous(struct device *dev, int count, +struct page *dma_alloc_from_contiguous(struct device *dev, size_t count, unsigned int order) { return NULL; diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 6452ff4c463f..3e3318ddfc0e 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -676,8 +676,9 @@ enum { struct list_head *mem_cgroup_cgwb_list(struct mem_cgroup *memcg); struct wb_domain *mem_cgroup_wb_domain(struct bdi_writeback *wb); -void mem_cgroup_wb_stats(struct bdi_writeback *wb, unsigned long *pavail, - unsigned long *pdirty, unsigned long *pwriteback); +void mem_cgroup_wb_stats(struct bdi_writeback *wb, unsigned long *pfilepages, + unsigned long *pheadroom, unsigned long *pdirty, + unsigned long *pwriteback); #else /* CONFIG_CGROUP_WRITEBACK */ @@ -687,7 +688,8 @@ static inline struct wb_domain *mem_cgroup_wb_domain(struct bdi_writeback *wb) } static inline void mem_cgroup_wb_stats(struct bdi_writeback *wb, - unsigned long *pavail, + unsigned long *pfilepages, + unsigned long *pheadroom, unsigned long *pdirty, unsigned long *pwriteback) { diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 2d15e3831440..210d11a75e4f 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1054,6 +1054,10 @@ typedef u16 (*select_queue_fallback_t)(struct net_device *dev, * This function is used to pass protocol port error state information * to the switch driver. The switch driver can react to the proto_down * by doing a phys down on the associated switch port. + * int (*ndo_fill_metadata_dst)(struct net_device *dev, struct sk_buff *skb); + * This function is used to get egress tunnel information for given skb. + * This is useful for retrieving outer tunnel header parameters while + * sampling packet. * */ struct net_device_ops { @@ -1227,6 +1231,8 @@ struct net_device_ops { int (*ndo_get_iflink)(const struct net_device *dev); int (*ndo_change_proto_down)(struct net_device *dev, bool proto_down); + int (*ndo_fill_metadata_dst)(struct net_device *dev, + struct sk_buff *skb); }; /** @@ -2203,6 +2209,7 @@ void dev_add_offload(struct packet_offload *po); void dev_remove_offload(struct packet_offload *po); int dev_get_iflink(const struct net_device *dev); +int dev_fill_metadata_dst(struct net_device *dev, struct sk_buff *skb); struct net_device *__dev_get_by_flags(struct net *net, unsigned short flags, unsigned short mask); struct net_device *dev_get_by_name(struct net *net, const char *name); diff --git a/include/linux/omap-dma.h b/include/linux/omap-dma.h index e5a70132a240..88fa8af2b937 100644 --- a/include/linux/omap-dma.h +++ b/include/linux/omap-dma.h @@ -17,7 +17,7 @@ #include <linux/platform_device.h> -#define INT_DMA_LCD 25 +#define INT_DMA_LCD (NR_IRQS_LEGACY + 25) #define OMAP1_DMA_TOUT_IRQ (1 << 0) #define OMAP_DMA_DROP_IRQ (1 << 1) diff --git a/include/net/af_unix.h b/include/net/af_unix.h index cb1b9bbda332..b36d837c701e 100644 --- a/include/net/af_unix.h +++ b/include/net/af_unix.h @@ -64,7 +64,7 @@ struct unix_sock { struct socket_wq peer_wq; }; -static inline struct unix_sock *unix_sk(struct sock *sk) +static inline struct unix_sock *unix_sk(const struct sock *sk) { return (struct unix_sock *)sk; } diff --git a/include/net/dst_metadata.h b/include/net/dst_metadata.h index af9d5382f6cb..ce009710120c 100644 --- a/include/net/dst_metadata.h +++ b/include/net/dst_metadata.h @@ -60,6 +60,38 @@ static inline struct metadata_dst *tun_rx_dst(int md_size) return tun_dst; } +static inline struct metadata_dst *tun_dst_unclone(struct sk_buff *skb) +{ + struct metadata_dst *md_dst = skb_metadata_dst(skb); + int md_size = md_dst->u.tun_info.options_len; + struct metadata_dst *new_md; + + if (!md_dst) + return ERR_PTR(-EINVAL); + + new_md = metadata_dst_alloc(md_size, GFP_ATOMIC); + if (!new_md) + return ERR_PTR(-ENOMEM); + + memcpy(&new_md->u.tun_info, &md_dst->u.tun_info, + sizeof(struct ip_tunnel_info) + md_size); + skb_dst_drop(skb); + dst_hold(&new_md->dst); + skb_dst_set(skb, &new_md->dst); + return new_md; +} + +static inline struct ip_tunnel_info *skb_tunnel_info_unclone(struct sk_buff *skb) +{ + struct metadata_dst *dst; + + dst = tun_dst_unclone(skb); + if (IS_ERR(dst)) + return NULL; + + return &dst->u.tun_info; +} + static inline struct metadata_dst *ip_tun_rx_dst(struct sk_buff *skb, __be16 flags, __be64 tunnel_id, diff --git a/include/net/inet_timewait_sock.h b/include/net/inet_timewait_sock.h index 186f3a1e1b1f..fc1937698625 100644 --- a/include/net/inet_timewait_sock.h +++ b/include/net/inet_timewait_sock.h @@ -113,12 +113,12 @@ void __inet_twsk_hashdance(struct inet_timewait_sock *tw, struct sock *sk, void __inet_twsk_schedule(struct inet_timewait_sock *tw, int timeo, bool rearm); -static void inline inet_twsk_schedule(struct inet_timewait_sock *tw, int timeo) +static inline void inet_twsk_schedule(struct inet_timewait_sock *tw, int timeo) { __inet_twsk_schedule(tw, timeo, false); } -static void inline inet_twsk_reschedule(struct inet_timewait_sock *tw, int timeo) +static inline void inet_twsk_reschedule(struct inet_timewait_sock *tw, int timeo) { __inet_twsk_schedule(tw, timeo, true); } diff --git a/include/net/sock.h b/include/net/sock.h index 7aa78440559a..e23717013a4e 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -828,6 +828,14 @@ static inline __must_check int sk_add_backlog(struct sock *sk, struct sk_buff *s if (sk_rcvqueues_full(sk, limit)) return -ENOBUFS; + /* + * If the skb was allocated from pfmemalloc reserves, only + * allow SOCK_MEMALLOC sockets to use it as this socket is + * helping free memory + */ + if (skb_pfmemalloc(skb) && !sock_flag(sk, SOCK_MEMALLOC)) + return -ENOMEM; + __sk_add_backlog(sk, skb); sk->sk_backlog.len += skb->truesize; return 0; diff --git a/include/sound/soc.h b/include/sound/soc.h index 884e728b09d9..26ede14597da 100644 --- a/include/sound/soc.h +++ b/include/sound/soc.h @@ -86,7 +86,7 @@ .access = SNDRV_CTL_ELEM_ACCESS_TLV_READ | \ SNDRV_CTL_ELEM_ACCESS_READWRITE, \ .tlv.p = (tlv_array),\ - .info = snd_soc_info_volsw, \ + .info = snd_soc_info_volsw_sx, \ .get = snd_soc_get_volsw_sx,\ .put = snd_soc_put_volsw_sx, \ .private_value = (unsigned long)&(struct soc_mixer_control) \ @@ -156,7 +156,7 @@ .access = SNDRV_CTL_ELEM_ACCESS_TLV_READ | \ SNDRV_CTL_ELEM_ACCESS_READWRITE, \ .tlv.p = (tlv_array), \ - .info = snd_soc_info_volsw, \ + .info = snd_soc_info_volsw_sx, \ .get = snd_soc_get_volsw_sx, \ .put = snd_soc_put_volsw_sx, \ .private_value = (unsigned long)&(struct soc_mixer_control) \ @@ -574,6 +574,8 @@ int snd_soc_put_enum_double(struct snd_kcontrol *kcontrol, struct snd_ctl_elem_value *ucontrol); int snd_soc_info_volsw(struct snd_kcontrol *kcontrol, struct snd_ctl_elem_info *uinfo); +int snd_soc_info_volsw_sx(struct snd_kcontrol *kcontrol, + struct snd_ctl_elem_info *uinfo); #define snd_soc_info_bool_ext snd_ctl_boolean_mono_info int snd_soc_get_volsw(struct snd_kcontrol *kcontrol, struct snd_ctl_elem_value *ucontrol); diff --git a/include/sound/wm8904.h b/include/sound/wm8904.h index 898be3a8db9a..6d8f8fba3341 100644 --- a/include/sound/wm8904.h +++ b/include/sound/wm8904.h @@ -119,7 +119,7 @@ #define WM8904_MIC_REGS 2 #define WM8904_GPIO_REGS 4 #define WM8904_DRC_REGS 4 -#define WM8904_EQ_REGS 25 +#define WM8904_EQ_REGS 24 /** * DRC configurations are specified with a label and a set of register diff --git a/include/uapi/asm-generic/siginfo.h b/include/uapi/asm-generic/siginfo.h index 1e3552037a5a..be640a90071a 100644 --- a/include/uapi/asm-generic/siginfo.h +++ b/include/uapi/asm-generic/siginfo.h @@ -4,9 +4,17 @@ #include <linux/compiler.h> #include <linux/types.h> +#ifndef __SIGINFO_VOIDPOINTER +#define __SIGINFO_VOIDPOINTER(field) void __user *field +#endif + +#ifndef __SIGINFO_BAND +#define __SIGINFO_BAND(field) __ARCH_SI_BAND_T field +#endif + typedef union sigval { int sival_int; - void __user *sival_ptr; + __SIGINFO_VOIDPOINTER(sival_ptr); } sigval_t; /* @@ -86,7 +94,7 @@ typedef struct siginfo { /* SIGILL, SIGFPE, SIGSEGV, SIGBUS */ struct { - void __user *_addr; /* faulting insn/memory ref. */ + __SIGINFO_VOIDPOINTER(_addr); /* faulting insn/memory ref. */ #ifdef __ARCH_SI_TRAPNO int _trapno; /* TRAP # which caused the signal */ #endif @@ -99,13 +107,13 @@ typedef struct siginfo { /* SIGPOLL */ struct { - __ARCH_SI_BAND_T _band; /* POLL_IN, POLL_OUT, POLL_MSG */ + __SIGINFO_BAND(_band); /* POLL_IN, POLL_OUT, POLL_MSG */ int _fd; } _sigpoll; /* SIGSYS */ struct { - void __user *_call_addr; /* calling user insn */ + __SIGINFO_VOIDPOINTER(_call_addr); /* calling user insn */ int _syscall; /* triggering system call number */ unsigned int _arch; /* AUDIT_ARCH_* of syscall */ } _sigsys; @@ -290,6 +298,7 @@ typedef struct sigevent { int _pad[SIGEV_PAD_SIZE]; int _tid; + /* Note these two are handled only in userspace */ struct { void (*_function)(sigval_t); void *_attribute; /* really pthread_attr_t */ diff --git a/include/uapi/asm-generic/signal.h b/include/uapi/asm-generic/signal.h index 3094618d382f..92d8ce318223 100644 --- a/include/uapi/asm-generic/signal.h +++ b/include/uapi/asm-generic/signal.h @@ -4,7 +4,9 @@ #include <linux/types.h> #define _NSIG 64 +#ifndef _NSIG_BPW #define _NSIG_BPW __BITS_PER_LONG +#endif #define _NSIG_WORDS (_NSIG / _NSIG_BPW) #define SIGHUP 1 @@ -85,9 +87,13 @@ #define SIGSTKSZ 8192 #endif +#ifndef __SIGSET_INNER_TYPE +#define __SIGSET_INNER_TYPE unsigned long +#endif + #ifndef __ASSEMBLY__ typedef struct { - unsigned long sig[_NSIG_WORDS]; + __SIGSET_INNER_TYPE sig[_NSIG_WORDS]; } sigset_t; /* not actually used, but required for linux/syscalls.h */ @@ -100,11 +106,24 @@ typedef unsigned long old_sigset_t; #endif #ifndef __KERNEL__ + +#ifndef __SIGACTION_HANDLER +#define __SIGACTION_HANDLER(field) __sighandler_t field +#endif + +#ifndef __SIGACTION_FLAGS +#define __SIGACTION_FLAGS(field) unsigned long field +#endif + +#ifndef __SIGACTION_RESTORER +#define __SIGACTION_RESTORER(field) __sigrestore_t field +#endif + struct sigaction { - __sighandler_t sa_handler; - unsigned long sa_flags; + __SIGACTION_HANDLER(sa_handler); + __SIGACTION_FLAGS(sa_flags); #ifdef SA_RESTORER - __sigrestore_t sa_restorer; + __SIGACTION_RESTORER(sa_restorer); #endif sigset_t sa_mask; /* mask last for extensibility */ }; diff --git a/include/uapi/asm-generic/stat.h b/include/uapi/asm-generic/stat.h index bd8cad21998e..ae81e73c90c1 100644 --- a/include/uapi/asm-generic/stat.h +++ b/include/uapi/asm-generic/stat.h @@ -43,9 +43,7 @@ struct stat { unsigned int __unused5; }; -/* This matches struct stat64 in glibc2.1. Only used for 32 bit. */ -#if __BITS_PER_LONG != 64 || defined(__ARCH_WANT_STAT64) -struct stat64 { +struct __stat64 { unsigned long long st_dev; /* Device. */ unsigned long long st_ino; /* File serial number. */ unsigned int st_mode; /* File mode. */ @@ -67,6 +65,10 @@ struct stat64 { unsigned int __unused4; unsigned int __unused5; }; + +#if __BITS_PER_LONG != 64 || defined(__ARCH_WANT_STAT64) +/* This matches struct stat64 in glibc2.1. Only used for 32 bit. */ +#define stat64 __stat64 #endif #endif /* __ASM_GENERIC_STAT_H */ diff --git a/include/uapi/linux/openvswitch.h b/include/uapi/linux/openvswitch.h index 32e07d8cbaf4..e663627a8ef3 100644 --- a/include/uapi/linux/openvswitch.h +++ b/include/uapi/linux/openvswitch.h @@ -323,10 +323,10 @@ enum ovs_key_attr { OVS_KEY_ATTR_MPLS, /* array of struct ovs_key_mpls. * The implementation may restrict * the accepted length of the array. */ - OVS_KEY_ATTR_CT_STATE, /* u8 bitmask of OVS_CS_F_* */ + OVS_KEY_ATTR_CT_STATE, /* u32 bitmask of OVS_CS_F_* */ OVS_KEY_ATTR_CT_ZONE, /* u16 connection tracking zone. */ OVS_KEY_ATTR_CT_MARK, /* u32 connection tracking mark */ - OVS_KEY_ATTR_CT_LABEL, /* 16-octet connection tracking label */ + OVS_KEY_ATTR_CT_LABELS, /* 16-octet connection tracking label */ #ifdef __KERNEL__ OVS_KEY_ATTR_TUNNEL_INFO, /* struct ip_tunnel_info */ @@ -439,9 +439,9 @@ struct ovs_key_nd { __u8 nd_tll[ETH_ALEN]; }; -#define OVS_CT_LABEL_LEN 16 -struct ovs_key_ct_label { - __u8 ct_label[OVS_CT_LABEL_LEN]; +#define OVS_CT_LABELS_LEN 16 +struct ovs_key_ct_labels { + __u8 ct_labels[OVS_CT_LABELS_LEN]; }; /* OVS_KEY_ATTR_CT_STATE flags */ @@ -449,9 +449,9 @@ struct ovs_key_ct_label { #define OVS_CS_F_ESTABLISHED 0x02 /* Part of an existing connection. */ #define OVS_CS_F_RELATED 0x04 /* Related to an established * connection. */ -#define OVS_CS_F_INVALID 0x20 /* Could not track connection. */ -#define OVS_CS_F_REPLY_DIR 0x40 /* Flow is in the reply direction. */ -#define OVS_CS_F_TRACKED 0x80 /* Conntrack has occurred. */ +#define OVS_CS_F_REPLY_DIR 0x08 /* Flow is in the reply direction. */ +#define OVS_CS_F_INVALID 0x10 /* Could not track connection. */ +#define OVS_CS_F_TRACKED 0x20 /* Conntrack has occurred. */ /** * enum ovs_flow_attr - attributes for %OVS_FLOW_* commands. @@ -618,22 +618,25 @@ struct ovs_action_hash { /** * enum ovs_ct_attr - Attributes for %OVS_ACTION_ATTR_CT action. - * @OVS_CT_ATTR_FLAGS: u32 connection tracking flags. + * @OVS_CT_ATTR_COMMIT: If present, commits the connection to the conntrack + * table. This allows future packets for the same connection to be identified + * as 'established' or 'related'. The flow key for the current packet will + * retain the pre-commit connection state. * @OVS_CT_ATTR_ZONE: u16 connection tracking zone. * @OVS_CT_ATTR_MARK: u32 value followed by u32 mask. For each bit set in the * mask, the corresponding bit in the value is copied to the connection * tracking mark field in the connection. - * @OVS_CT_ATTR_LABEL: %OVS_CT_LABEL_LEN value followed by %OVS_CT_LABEL_LEN + * @OVS_CT_ATTR_LABEL: %OVS_CT_LABELS_LEN value followed by %OVS_CT_LABELS_LEN * mask. For each bit set in the mask, the corresponding bit in the value is * copied to the connection tracking label field in the connection. * @OVS_CT_ATTR_HELPER: variable length string defining conntrack ALG. */ enum ovs_ct_attr { OVS_CT_ATTR_UNSPEC, - OVS_CT_ATTR_FLAGS, /* u8 bitmask of OVS_CT_F_*. */ + OVS_CT_ATTR_COMMIT, /* No argument, commits connection. */ OVS_CT_ATTR_ZONE, /* u16 zone id. */ OVS_CT_ATTR_MARK, /* mark to associate with this connection. */ - OVS_CT_ATTR_LABEL, /* label to associate with this connection. */ + OVS_CT_ATTR_LABELS, /* labels to associate with this connection. */ OVS_CT_ATTR_HELPER, /* netlink helper to assist detection of related connections. */ __OVS_CT_ATTR_MAX @@ -641,14 +644,6 @@ enum ovs_ct_attr { #define OVS_CT_ATTR_MAX (__OVS_CT_ATTR_MAX - 1) -/* - * OVS_CT_ATTR_FLAGS flags - bitmask of %OVS_CT_F_* - * @OVS_CT_F_COMMIT: Commits the flow to the conntrack table. This allows - * future packets for the same connection to be identified as 'established' - * or 'related'. - */ -#define OVS_CT_F_COMMIT 0x01 - /** * enum ovs_action_attr - Action types. * @@ -705,7 +700,7 @@ enum ovs_action_attr { * data immediately followed by a mask. * The data must be zero for the unmasked * bits. */ - OVS_ACTION_ATTR_CT, /* One nested OVS_CT_ATTR_* . */ + OVS_ACTION_ATTR_CT, /* Nested OVS_CT_ATTR_* . */ __OVS_ACTION_ATTR_MAX, /* Nothing past this will be accepted * from userspace. */ diff --git a/include/uapi/linux/rtnetlink.h b/include/uapi/linux/rtnetlink.h index e1eaf85a37c8..5cd55ef2b196 100644 --- a/include/uapi/linux/rtnetlink.h +++ b/include/uapi/linux/rtnetlink.h @@ -160,7 +160,7 @@ struct rtattr { /* Macros to handle rtattributes */ -#define RTA_ALIGNTO 4 +#define RTA_ALIGNTO 4U #define RTA_ALIGN(len) ( ((len)+RTA_ALIGNTO-1) & ~(RTA_ALIGNTO-1) ) #define RTA_OK(rta,len) ((len) >= (int)sizeof(struct rtattr) && \ (rta)->rta_len >= sizeof(struct rtattr) && \ diff --git a/kernel/kmod.c b/kernel/kmod.c index da98d0593de2..0277d1216f80 100644 --- a/kernel/kmod.c +++ b/kernel/kmod.c @@ -327,9 +327,13 @@ static void call_usermodehelper_exec_work(struct work_struct *work) call_usermodehelper_exec_sync(sub_info); } else { pid_t pid; - + /* + * Use CLONE_PARENT to reparent it to kthreadd; we do not + * want to pollute current->children, and we need a parent + * that always ignores SIGCHLD to ensure auto-reaping. + */ pid = kernel_thread(call_usermodehelper_exec_async, sub_info, - SIGCHLD); + CLONE_PARENT | SIGCHLD); if (pid < 0) { sub_info->retval = pid; umh_complete(sub_info); diff --git a/kernel/memremap.c b/kernel/memremap.c index 72b0c66628b6..9d6b55587eaa 100644 --- a/kernel/memremap.c +++ b/kernel/memremap.c @@ -24,6 +24,16 @@ __weak void __iomem *ioremap_cache(resource_size_t offset, unsigned long size) } #endif +static void *try_ram_remap(resource_size_t offset, size_t size) +{ + struct page *page = pfn_to_page(offset >> PAGE_SHIFT); + + /* In the simple case just return the existing linear address */ + if (!PageHighMem(page)) + return __va(offset); + return NULL; /* fallback to ioremap_cache */ +} + /** * memremap() - remap an iomem_resource as cacheable memory * @offset: iomem resource start address @@ -66,8 +76,8 @@ void *memremap(resource_size_t offset, size_t size, unsigned long flags) * the requested range is potentially in "System RAM" */ if (is_ram == REGION_INTERSECTS) - addr = __va(offset); - else + addr = try_ram_remap(offset, size); + if (!addr) addr = ioremap_cache(offset, size); } diff --git a/kernel/module.c b/kernel/module.c index b86b7bf1be38..8f051a106676 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -1063,11 +1063,15 @@ void symbol_put_addr(void *addr) if (core_kernel_text(a)) return; - /* module_text_address is safe here: we're supposed to have reference - * to module from symbol_get, so it can't go away. */ + /* + * Even though we hold a reference on the module; we still need to + * disable preemption in order to safely traverse the data structure. + */ + preempt_disable(); modaddr = __module_text_address(a); BUG_ON(!modaddr); module_put(modaddr); + preempt_enable(); } EXPORT_SYMBOL_GPL(symbol_put_addr); diff --git a/kernel/ptrace.c b/kernel/ptrace.c index 787320de68e0..04799aa638fe 100644 --- a/kernel/ptrace.c +++ b/kernel/ptrace.c @@ -652,7 +652,7 @@ static int ptrace_peek_siginfo(struct task_struct *child, break; #ifdef CONFIG_COMPAT - if (unlikely(is_compat_task())) { + if (unlikely(is_compat_task() && !COMPAT_USE_NATIVE_SIGINFO)) { compat_siginfo_t __user *uinfo = compat_ptr(data); if (copy_siginfo_to_user32(uinfo, &info) || @@ -1140,16 +1140,26 @@ int compat_ptrace_request(struct task_struct *child, compat_long_t request, case PTRACE_GETSIGINFO: ret = ptrace_getsiginfo(child, &siginfo); - if (!ret) - ret = copy_siginfo_to_user32( - (struct compat_siginfo __user *) datap, - &siginfo); + if (!ret) { + if (COMPAT_USE_NATIVE_SIGINFO) + ret = copy_siginfo_to_user( + (struct siginfo __user *) datap, + &siginfo); + else + ret = copy_siginfo_to_user32( + (struct compat_siginfo __user *) datap, + &siginfo); + } break; case PTRACE_SETSIGINFO: memset(&siginfo, 0, sizeof siginfo); - if (copy_siginfo_from_user32( - &siginfo, (struct compat_siginfo __user *) datap)) + if (COMPAT_USE_NATIVE_SIGINFO) + ret = copy_from_user(&siginfo, datap, sizeof(siginfo)); + else + ret = copy_siginfo_from_user32( + &siginfo, (struct compat_siginfo __user *) datap); + if (ret) ret = -EFAULT; else ret = ptrace_setsiginfo(child, &siginfo); diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 4165313da645..04c9fdef00bd 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -2366,8 +2366,15 @@ void wake_up_new_task(struct task_struct *p) trace_sched_wakeup_new(p); check_preempt_curr(rq, p, WF_FORK); #ifdef CONFIG_SMP - if (p->sched_class->task_woken) + if (p->sched_class->task_woken) { + /* + * Nothing relies on rq->lock after this, so its fine to + * drop it. + */ + lockdep_unpin_lock(&rq->lock); p->sched_class->task_woken(rq, p); + lockdep_pin_lock(&rq->lock); + } #endif task_rq_unlock(rq, p, &flags); } @@ -7238,9 +7245,6 @@ void __init sched_init_smp(void) alloc_cpumask_var(&non_isolated_cpus, GFP_KERNEL); alloc_cpumask_var(&fallback_doms, GFP_KERNEL); - /* nohz_full won't take effect without isolating the cpus. */ - tick_nohz_full_add_cpus_to(cpu_isolated_map); - sched_init_numa(); /* diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c index fc8f01083527..8b0a15e285f9 100644 --- a/kernel/sched/deadline.c +++ b/kernel/sched/deadline.c @@ -668,8 +668,15 @@ static enum hrtimer_restart dl_task_timer(struct hrtimer *timer) * Queueing this task back might have overloaded rq, check if we need * to kick someone away. */ - if (has_pushable_dl_tasks(rq)) + if (has_pushable_dl_tasks(rq)) { + /* + * Nothing relies on rq->lock after this, so its safe to drop + * rq->lock. + */ + lockdep_unpin_lock(&rq->lock); push_dl_task(rq); + lockdep_pin_lock(&rq->lock); + } #endif unlock: @@ -1066,8 +1073,9 @@ select_task_rq_dl(struct task_struct *p, int cpu, int sd_flag, int flags) int target = find_later_rq(p); if (target != -1 && - dl_time_before(p->dl.deadline, - cpu_rq(target)->dl.earliest_dl.curr)) + (dl_time_before(p->dl.deadline, + cpu_rq(target)->dl.earliest_dl.curr) || + (cpu_rq(target)->dl.dl_nr_running == 0))) cpu = target; } rcu_read_unlock(); @@ -1417,7 +1425,8 @@ static struct rq *find_lock_later_rq(struct task_struct *task, struct rq *rq) later_rq = cpu_rq(cpu); - if (!dl_time_before(task->dl.deadline, + if (later_rq->dl.dl_nr_running && + !dl_time_before(task->dl.deadline, later_rq->dl.earliest_dl.curr)) { /* * Target rq has tasks of equal or earlier deadline, diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 6e2e3483b1ec..9a5e60fe721a 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -2363,7 +2363,7 @@ static inline long calc_tg_weight(struct task_group *tg, struct cfs_rq *cfs_rq) */ tg_weight = atomic_long_read(&tg->load_avg); tg_weight -= cfs_rq->tg_load_avg_contrib; - tg_weight += cfs_rq_load_avg(cfs_rq); + tg_weight += cfs_rq->load.weight; return tg_weight; } @@ -2373,7 +2373,7 @@ static long calc_cfs_shares(struct cfs_rq *cfs_rq, struct task_group *tg) long tg_weight, load, shares; tg_weight = calc_tg_weight(tg, cfs_rq); - load = cfs_rq_load_avg(cfs_rq); + load = cfs_rq->load.weight; shares = (tg->shares * load); if (tg_weight) @@ -2664,13 +2664,14 @@ static inline u64 cfs_rq_clock_task(struct cfs_rq *cfs_rq); /* Group cfs_rq's load_avg is used for task_h_load and update_cfs_share */ static inline int update_cfs_rq_load_avg(u64 now, struct cfs_rq *cfs_rq) { - int decayed; struct sched_avg *sa = &cfs_rq->avg; + int decayed, removed = 0; if (atomic_long_read(&cfs_rq->removed_load_avg)) { long r = atomic_long_xchg(&cfs_rq->removed_load_avg, 0); sa->load_avg = max_t(long, sa->load_avg - r, 0); sa->load_sum = max_t(s64, sa->load_sum - r * LOAD_AVG_MAX, 0); + removed = 1; } if (atomic_long_read(&cfs_rq->removed_util_avg)) { @@ -2688,7 +2689,7 @@ static inline int update_cfs_rq_load_avg(u64 now, struct cfs_rq *cfs_rq) cfs_rq->load_last_update_time_copy = sa->last_update_time; #endif - return decayed; + return decayed || removed; } /* Update task and its cfs_rq load average */ diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c index 8f177c73ae19..4a2ef5a02fd3 100644 --- a/kernel/sched/idle.c +++ b/kernel/sched/idle.c @@ -57,9 +57,11 @@ static inline int cpu_idle_poll(void) rcu_idle_enter(); trace_cpu_idle_rcuidle(0, smp_processor_id()); local_irq_enable(); + stop_critical_timings(); while (!tif_need_resched() && (cpu_idle_force_poll || tick_check_broadcast_expired())) cpu_relax(); + start_critical_timings(); trace_cpu_idle_rcuidle(PWR_EVENT_EXIT, smp_processor_id()); rcu_idle_exit(); return 1; diff --git a/kernel/trace/trace_stack.c b/kernel/trace/trace_stack.c index b746399ab59c..8abf1ba18085 100644 --- a/kernel/trace/trace_stack.c +++ b/kernel/trace/trace_stack.c @@ -85,9 +85,19 @@ check_stack(unsigned long ip, unsigned long *stack) if (!object_is_on_stack(stack)) return; + /* Can't do this from NMI context (can cause deadlocks) */ + if (in_nmi()) + return; + local_irq_save(flags); arch_spin_lock(&max_stack_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; @@ -169,6 +179,7 @@ check_stack(unsigned long ip, unsigned long *stack) } out: + rcu_irq_exit(); arch_spin_unlock(&max_stack_lock); local_irq_restore(flags); } diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index 6d2596fc1baa..a5ef3d1ca367 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -197,6 +197,7 @@ config ENABLE_MUST_CHECK config FRAME_WARN int "Warn for stack frames larger than (needs gcc 4.4)" range 0 8192 + default 0 if KASAN default 1024 if !64BIT default 2048 if 64BIT help diff --git a/lib/fault-inject.c b/lib/fault-inject.c index f1cdeb024d17..6a823a53e357 100644 --- a/lib/fault-inject.c +++ b/lib/fault-inject.c @@ -44,7 +44,7 @@ static void fail_dump(struct fault_attr *attr) printk(KERN_NOTICE "FAULT_INJECTION: forcing a failure.\n" "name %pd, interval %lu, probability %lu, " "space %d, times %d\n", attr->dname, - attr->probability, attr->interval, + attr->interval, attr->probability, atomic_read(&attr->space), atomic_read(&attr->times)); if (attr->verbose > 1) diff --git a/mm/backing-dev.c b/mm/backing-dev.c index 2df8ddcb0ca0..619984fc07ec 100644 --- a/mm/backing-dev.c +++ b/mm/backing-dev.c @@ -480,6 +480,10 @@ static void cgwb_release_workfn(struct work_struct *work) release_work); struct backing_dev_info *bdi = wb->bdi; + spin_lock_irq(&cgwb_lock); + list_del_rcu(&wb->bdi_node); + spin_unlock_irq(&cgwb_lock); + wb_shutdown(wb); css_put(wb->memcg_css); @@ -575,6 +579,7 @@ static int cgwb_create(struct backing_dev_info *bdi, ret = radix_tree_insert(&bdi->cgwb_tree, memcg_css->id, wb); if (!ret) { atomic_inc(&bdi->usage_cnt); + list_add_tail_rcu(&wb->bdi_node, &bdi->wb_list); list_add(&wb->memcg_node, memcg_cgwb_list); list_add(&wb->blkcg_node, blkcg_cgwb_list); css_get(memcg_css); @@ -676,7 +681,7 @@ static int cgwb_bdi_init(struct backing_dev_info *bdi) static void cgwb_bdi_destroy(struct backing_dev_info *bdi) { struct radix_tree_iter iter; - struct bdi_writeback_congested *congested, *congested_n; + struct rb_node *rbn; void **slot; WARN_ON(test_bit(WB_registered, &bdi->wb.state)); @@ -686,9 +691,11 @@ static void cgwb_bdi_destroy(struct backing_dev_info *bdi) radix_tree_for_each_slot(slot, &bdi->cgwb_tree, &iter, 0) cgwb_kill(*slot); - rbtree_postorder_for_each_entry_safe(congested, congested_n, - &bdi->cgwb_congested_tree, rb_node) { - rb_erase(&congested->rb_node, &bdi->cgwb_congested_tree); + while ((rbn = rb_first(&bdi->cgwb_congested_tree))) { + struct bdi_writeback_congested *congested = + rb_entry(rbn, struct bdi_writeback_congested, rb_node); + + rb_erase(rbn, &bdi->cgwb_congested_tree); congested->bdi = NULL; /* mark @congested unlinked */ } @@ -764,15 +771,22 @@ static void cgwb_bdi_destroy(struct backing_dev_info *bdi) { } int bdi_init(struct backing_dev_info *bdi) { + int ret; + bdi->dev = NULL; bdi->min_ratio = 0; bdi->max_ratio = 100; bdi->max_prop_frac = FPROP_FRAC_BASE; INIT_LIST_HEAD(&bdi->bdi_list); + INIT_LIST_HEAD(&bdi->wb_list); init_waitqueue_head(&bdi->wb_waitq); - return cgwb_bdi_init(bdi); + ret = cgwb_bdi_init(bdi); + + list_add_tail_rcu(&bdi->wb.bdi_node, &bdi->wb_list); + + return ret; } EXPORT_SYMBOL(bdi_init); @@ -823,7 +837,7 @@ static void bdi_remove_from_list(struct backing_dev_info *bdi) synchronize_rcu_expedited(); } -void bdi_destroy(struct backing_dev_info *bdi) +void bdi_unregister(struct backing_dev_info *bdi) { /* make sure nobody finds us on the bdi_list anymore */ bdi_remove_from_list(bdi); @@ -835,9 +849,19 @@ void bdi_destroy(struct backing_dev_info *bdi) device_unregister(bdi->dev); bdi->dev = NULL; } +} +void bdi_exit(struct backing_dev_info *bdi) +{ + WARN_ON_ONCE(bdi->dev); wb_exit(&bdi->wb); } + +void bdi_destroy(struct backing_dev_info *bdi) +{ + bdi_unregister(bdi); + bdi_exit(bdi); +} EXPORT_SYMBOL(bdi_destroy); /* @@ -361,7 +361,7 @@ err: * This function allocates part of contiguous memory on specific * contiguous memory area. */ -struct page *cma_alloc(struct cma *cma, unsigned int count, unsigned int align) +struct page *cma_alloc(struct cma *cma, size_t count, unsigned int align) { unsigned long mask, offset, pfn, start = 0; unsigned long bitmap_maxno, bitmap_no, bitmap_count; @@ -371,7 +371,7 @@ struct page *cma_alloc(struct cma *cma, unsigned int count, unsigned int align) if (!cma || !cma->count) return NULL; - pr_debug("%s(cma %p, count %d, align %d)\n", __func__, (void *)cma, + pr_debug("%s(cma %p, count %zu, align %d)\n", __func__, (void *)cma, count, align); if (!count) diff --git a/mm/filemap.c b/mm/filemap.c index 1cc5467cf36c..327910c2400c 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -2488,6 +2488,11 @@ again: break; } + if (fatal_signal_pending(current)) { + status = -EINTR; + break; + } + status = a_ops->write_begin(file, mapping, pos, bytes, flags, &page, &fsdata); if (unlikely(status < 0)) @@ -2525,10 +2530,6 @@ again: written += copied; balance_dirty_pages_ratelimited(mapping); - if (fatal_signal_pending(current)) { - status = -EINTR; - break; - } } while (iov_iter_count(i)); return written ? written : status; diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 4b06b8db9df2..bbac913f96bc 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -2206,7 +2206,8 @@ static int __collapse_huge_page_isolate(struct vm_area_struct *vma, for (_pte = pte; _pte < pte+HPAGE_PMD_NR; _pte++, address += PAGE_SIZE) { pte_t pteval = *_pte; - if (pte_none(pteval) || is_zero_pfn(pte_pfn(pteval))) { + if (pte_none(pteval) || (pte_present(pteval) && + is_zero_pfn(pte_pfn(pteval)))) { if (!userfaultfd_armed(vma) && ++none_or_zero <= khugepaged_max_ptes_none) continue; diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 9b0fc38aa09a..07c8070d7721 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -3741,44 +3741,43 @@ struct wb_domain *mem_cgroup_wb_domain(struct bdi_writeback *wb) /** * mem_cgroup_wb_stats - retrieve writeback related stats from its memcg * @wb: bdi_writeback in question - * @pavail: out parameter for number of available pages + * @pfilepages: out parameter for number of file pages + * @pheadroom: out parameter for number of allocatable pages according to memcg * @pdirty: out parameter for number of dirty pages * @pwriteback: out parameter for number of pages under writeback * - * Determine the numbers of available, dirty, and writeback pages in @wb's - * memcg. Dirty and writeback are self-explanatory. Available is a bit - * more involved. + * Determine the numbers of file, headroom, dirty, and writeback pages in + * @wb's memcg. File, dirty and writeback are self-explanatory. Headroom + * is a bit more involved. * - * A memcg's headroom is "min(max, high) - used". The available memory is - * calculated as the lowest headroom of itself and the ancestors plus the - * number of pages already being used for file pages. Note that this - * doesn't consider the actual amount of available memory in the system. - * The caller should further cap *@pavail accordingly. + * A memcg's headroom is "min(max, high) - used". In the hierarchy, the + * headroom is calculated as the lowest headroom of itself and the + * ancestors. Note that this doesn't consider the actual amount of + * available memory in the system. The caller should further cap + * *@pheadroom accordingly. */ -void mem_cgroup_wb_stats(struct bdi_writeback *wb, unsigned long *pavail, - unsigned long *pdirty, unsigned long *pwriteback) +void mem_cgroup_wb_stats(struct bdi_writeback *wb, unsigned long *pfilepages, + unsigned long *pheadroom, unsigned long *pdirty, + unsigned long *pwriteback) { struct mem_cgroup *memcg = mem_cgroup_from_css(wb->memcg_css); struct mem_cgroup *parent; - unsigned long head_room = PAGE_COUNTER_MAX; - unsigned long file_pages; *pdirty = mem_cgroup_read_stat(memcg, MEM_CGROUP_STAT_DIRTY); /* this should eventually include NR_UNSTABLE_NFS */ *pwriteback = mem_cgroup_read_stat(memcg, MEM_CGROUP_STAT_WRITEBACK); + *pfilepages = mem_cgroup_nr_lru_pages(memcg, (1 << LRU_INACTIVE_FILE) | + (1 << LRU_ACTIVE_FILE)); + *pheadroom = PAGE_COUNTER_MAX; - file_pages = mem_cgroup_nr_lru_pages(memcg, (1 << LRU_INACTIVE_FILE) | - (1 << LRU_ACTIVE_FILE)); while ((parent = parent_mem_cgroup(memcg))) { unsigned long ceiling = min(memcg->memory.limit, memcg->high); unsigned long used = page_counter_read(&memcg->memory); - head_room = min(head_room, ceiling - min(ceiling, used)); + *pheadroom = min(*pheadroom, ceiling - min(ceiling, used)); memcg = parent; } - - *pavail = file_pages + head_room; } #else /* CONFIG_CGROUP_WRITEBACK */ diff --git a/mm/page-writeback.c b/mm/page-writeback.c index 0a931cdd4f6b..2c90357c34ea 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -145,9 +145,6 @@ struct dirty_throttle_control { unsigned long pos_ratio; }; -#define DTC_INIT_COMMON(__wb) .wb = (__wb), \ - .wb_completions = &(__wb)->completions - /* * Length of period for aging writeout fractions of bdis. This is an * arbitrarily chosen number. The longer the period, the slower fractions will @@ -157,12 +154,16 @@ struct dirty_throttle_control { #ifdef CONFIG_CGROUP_WRITEBACK -#define GDTC_INIT(__wb) .dom = &global_wb_domain, \ - DTC_INIT_COMMON(__wb) +#define GDTC_INIT(__wb) .wb = (__wb), \ + .dom = &global_wb_domain, \ + .wb_completions = &(__wb)->completions + #define GDTC_INIT_NO_WB .dom = &global_wb_domain -#define MDTC_INIT(__wb, __gdtc) .dom = mem_cgroup_wb_domain(__wb), \ - .gdtc = __gdtc, \ - DTC_INIT_COMMON(__wb) + +#define MDTC_INIT(__wb, __gdtc) .wb = (__wb), \ + .dom = mem_cgroup_wb_domain(__wb), \ + .wb_completions = &(__wb)->memcg_completions, \ + .gdtc = __gdtc static bool mdtc_valid(struct dirty_throttle_control *dtc) { @@ -213,7 +214,8 @@ static void wb_min_max_ratio(struct bdi_writeback *wb, #else /* CONFIG_CGROUP_WRITEBACK */ -#define GDTC_INIT(__wb) DTC_INIT_COMMON(__wb) +#define GDTC_INIT(__wb) .wb = (__wb), \ + .wb_completions = &(__wb)->completions #define GDTC_INIT_NO_WB #define MDTC_INIT(__wb, __gdtc) @@ -682,13 +684,19 @@ static unsigned long hard_dirty_limit(struct wb_domain *dom, return max(thresh, dom->dirty_limit); } -/* memory available to a memcg domain is capped by system-wide clean memory */ -static void mdtc_cap_avail(struct dirty_throttle_control *mdtc) +/* + * Memory which can be further allocated to a memcg domain is capped by + * system-wide clean memory excluding the amount being used in the domain. + */ +static void mdtc_calc_avail(struct dirty_throttle_control *mdtc, + unsigned long filepages, unsigned long headroom) { struct dirty_throttle_control *gdtc = mdtc_gdtc(mdtc); - unsigned long clean = gdtc->avail - min(gdtc->avail, gdtc->dirty); + unsigned long clean = filepages - min(filepages, mdtc->dirty); + unsigned long global_clean = gdtc->avail - min(gdtc->avail, gdtc->dirty); + unsigned long other_clean = global_clean - min(global_clean, clean); - mdtc->avail = min(mdtc->avail, clean); + mdtc->avail = filepages + min(headroom, other_clean); } /** @@ -1562,16 +1570,16 @@ static void balance_dirty_pages(struct address_space *mapping, } if (mdtc) { - unsigned long writeback; + unsigned long filepages, headroom, writeback; /* * If @wb belongs to !root memcg, repeat the same * basic calculations for the memcg domain. */ - mem_cgroup_wb_stats(wb, &mdtc->avail, &mdtc->dirty, - &writeback); - mdtc_cap_avail(mdtc); + mem_cgroup_wb_stats(wb, &filepages, &headroom, + &mdtc->dirty, &writeback); mdtc->dirty += writeback; + mdtc_calc_avail(mdtc, filepages, headroom); domain_dirty_limits(mdtc); @@ -1893,10 +1901,11 @@ bool wb_over_bg_thresh(struct bdi_writeback *wb) return true; if (mdtc) { - unsigned long writeback; + unsigned long filepages, headroom, writeback; - mem_cgroup_wb_stats(wb, &mdtc->avail, &mdtc->dirty, &writeback); - mdtc_cap_avail(mdtc); + mem_cgroup_wb_stats(wb, &filepages, &headroom, &mdtc->dirty, + &writeback); + mdtc_calc_avail(mdtc, filepages, headroom); domain_dirty_limits(mdtc); /* ditto, ignore writeback */ if (mdtc->dirty > mdtc->bg_thresh) @@ -1956,7 +1965,6 @@ void laptop_mode_timer_fn(unsigned long data) int nr_pages = global_page_state(NR_FILE_DIRTY) + global_page_state(NR_UNSTABLE_NFS); struct bdi_writeback *wb; - struct wb_iter iter; /* * We want to write everything out, not just down to the dirty @@ -1965,10 +1973,12 @@ void laptop_mode_timer_fn(unsigned long data) if (!bdi_has_dirty_io(&q->backing_dev_info)) return; - bdi_for_each_wb(wb, &q->backing_dev_info, &iter, 0) + rcu_read_lock(); + list_for_each_entry_rcu(wb, &q->backing_dev_info.wb_list, bdi_node) if (wb_has_dirty_io(wb)) wb_start_writeback(wb, nr_pages, true, WB_REASON_LAPTOP_TIMER); + rcu_read_unlock(); } /* diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c index b4548c739a64..2dda439c8cb8 100644 --- a/net/bluetooth/hci_conn.c +++ b/net/bluetooth/hci_conn.c @@ -91,10 +91,50 @@ static void hci_connect_le_scan_cleanup(struct hci_conn *conn) * autoconnect action, remove them completely. If they are, just unmark * them as waiting for connection, by clearing explicit_connect field. */ - if (params->auto_connect == HCI_AUTO_CONN_EXPLICIT) + params->explicit_connect = false; + + list_del_init(¶ms->action); + + switch (params->auto_connect) { + case HCI_AUTO_CONN_EXPLICIT: hci_conn_params_del(conn->hdev, bdaddr, bdaddr_type); - else - params->explicit_connect = false; + /* return instead of break to avoid duplicate scan update */ + return; + case HCI_AUTO_CONN_DIRECT: + case HCI_AUTO_CONN_ALWAYS: + list_add(¶ms->action, &conn->hdev->pend_le_conns); + break; + case HCI_AUTO_CONN_REPORT: + list_add(¶ms->action, &conn->hdev->pend_le_reports); + break; + default: + break; + } + + hci_update_background_scan(conn->hdev); +} + +static void hci_conn_cleanup(struct hci_conn *conn) +{ + struct hci_dev *hdev = conn->hdev; + + if (test_bit(HCI_CONN_PARAM_REMOVAL_PEND, &conn->flags)) + hci_conn_params_del(conn->hdev, &conn->dst, conn->dst_type); + + hci_chan_list_flush(conn); + + hci_conn_hash_del(hdev, conn); + + if (hdev->notify) + hdev->notify(hdev, HCI_NOTIFY_CONN_DEL); + + hci_conn_del_sysfs(conn); + + debugfs_remove_recursive(conn->debugfs); + + hci_dev_put(hdev); + + hci_conn_put(conn); } /* This function requires the caller holds hdev->lock */ @@ -102,8 +142,13 @@ static void hci_connect_le_scan_remove(struct hci_conn *conn) { hci_connect_le_scan_cleanup(conn); - hci_conn_hash_del(conn->hdev, conn); - hci_update_background_scan(conn->hdev); + /* We can't call hci_conn_del here since that would deadlock + * with trying to call cancel_delayed_work_sync(&conn->disc_work). + * Instead, call just hci_conn_cleanup() which contains the bare + * minimum cleanup operations needed for a connection in this + * state. + */ + hci_conn_cleanup(conn); } static void hci_acl_create_connection(struct hci_conn *conn) @@ -581,27 +626,17 @@ int hci_conn_del(struct hci_conn *conn) } } - hci_chan_list_flush(conn); - if (conn->amp_mgr) amp_mgr_put(conn->amp_mgr); - hci_conn_hash_del(hdev, conn); - if (hdev->notify) - hdev->notify(hdev, HCI_NOTIFY_CONN_DEL); - skb_queue_purge(&conn->data_q); - hci_conn_del_sysfs(conn); - - debugfs_remove_recursive(conn->debugfs); - - if (test_bit(HCI_CONN_PARAM_REMOVAL_PEND, &conn->flags)) - hci_conn_params_del(conn->hdev, &conn->dst, conn->dst_type); - - hci_dev_put(hdev); - - hci_conn_put(conn); + /* Remove the connection from the list and cleanup its remaining + * state. This is a separate function since for some cases like + * BT_CONNECT_SCAN we *only* want the cleanup part without the + * rest of hci_conn_del. + */ + hci_conn_cleanup(conn); return 0; } @@ -973,15 +1008,23 @@ static int hci_explicit_conn_params_set(struct hci_request *req, if (is_connected(hdev, addr, addr_type)) return -EISCONN; - params = hci_conn_params_add(hdev, addr, addr_type); - if (!params) - return -EIO; + params = hci_conn_params_lookup(hdev, addr, addr_type); + if (!params) { + params = hci_conn_params_add(hdev, addr, addr_type); + if (!params) + return -ENOMEM; - /* If we created new params, or existing params were marked as disabled, - * mark them to be used just once to connect. - */ - if (params->auto_connect == HCI_AUTO_CONN_DISABLED) { + /* If we created new params, mark them to be deleted in + * hci_connect_le_scan_cleanup. It's different case than + * existing disabled params, those will stay after cleanup. + */ params->auto_connect = HCI_AUTO_CONN_EXPLICIT; + } + + /* We're trying to connect, so make sure params are at pend_le_conns */ + if (params->auto_connect == HCI_AUTO_CONN_DISABLED || + params->auto_connect == HCI_AUTO_CONN_REPORT || + params->auto_connect == HCI_AUTO_CONN_EXPLICIT) { list_del_init(¶ms->action); list_add(¶ms->action, &hdev->pend_le_conns); } diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c index adcbc74c2432..e837539452fb 100644 --- a/net/bluetooth/hci_core.c +++ b/net/bluetooth/hci_core.c @@ -2861,13 +2861,6 @@ struct hci_conn_params *hci_explicit_connect_lookup(struct hci_dev *hdev, return param; } - list_for_each_entry(param, &hdev->pend_le_reports, action) { - if (bacmp(¶m->addr, addr) == 0 && - param->addr_type == addr_type && - param->explicit_connect) - return param; - } - return NULL; } diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c index 186041866315..bc31099d3b5b 100644 --- a/net/bluetooth/hci_event.c +++ b/net/bluetooth/hci_event.c @@ -55,7 +55,12 @@ static void hci_cc_inquiry_cancel(struct hci_dev *hdev, struct sk_buff *skb) wake_up_bit(&hdev->flags, HCI_INQUIRY); hci_dev_lock(hdev); - hci_discovery_set_state(hdev, DISCOVERY_STOPPED); + /* Set discovery state to stopped if we're not doing LE active + * scanning. + */ + if (!hci_dev_test_flag(hdev, HCI_LE_SCAN) || + hdev->le_scan_type != LE_SCAN_ACTIVE) + hci_discovery_set_state(hdev, DISCOVERY_STOPPED); hci_dev_unlock(hdev); hci_conn_check_pending(hdev); @@ -4648,8 +4653,8 @@ static struct hci_conn *check_pending_le_conn(struct hci_dev *hdev, /* If we're not connectable only connect devices that we have in * our pend_le_conns list. */ - params = hci_explicit_connect_lookup(hdev, addr, addr_type); - + params = hci_pend_le_action_lookup(&hdev->pend_le_conns, addr, + addr_type); if (!params) return NULL; diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c index ccaf5a436d8f..c4fe2fee753f 100644 --- a/net/bluetooth/mgmt.c +++ b/net/bluetooth/mgmt.c @@ -3545,6 +3545,7 @@ static int pair_device(struct sock *sk, struct hci_dev *hdev, void *data, auth_type); } else { u8 addr_type; + struct hci_conn_params *p; /* Convert from L2CAP channel address type to HCI address type */ @@ -3562,7 +3563,10 @@ static int pair_device(struct sock *sk, struct hci_dev *hdev, void *data, * If connection parameters already exist, then they * will be kept and this function does nothing. */ - hci_conn_params_add(hdev, &cp->addr.bdaddr, addr_type); + p = hci_conn_params_add(hdev, &cp->addr.bdaddr, addr_type); + + if (p->auto_connect == HCI_AUTO_CONN_EXPLICIT) + p->auto_connect = HCI_AUTO_CONN_DISABLED; conn = hci_connect_le_scan(hdev, &cp->addr.bdaddr, addr_type, sec_level, @@ -6117,14 +6121,21 @@ static int hci_conn_params_set(struct hci_request *req, bdaddr_t *addr, __hci_update_background_scan(req); break; case HCI_AUTO_CONN_REPORT: - list_add(¶ms->action, &hdev->pend_le_reports); + if (params->explicit_connect) + list_add(¶ms->action, &hdev->pend_le_conns); + else + list_add(¶ms->action, &hdev->pend_le_reports); __hci_update_background_scan(req); break; case HCI_AUTO_CONN_DIRECT: case HCI_AUTO_CONN_ALWAYS: if (!is_connected(hdev, addr, addr_type)) { list_add(¶ms->action, &hdev->pend_le_conns); - __hci_update_background_scan(req); + /* If we are in scan phase of connecting, we were + * already added to pend_le_conns and scanning. + */ + if (params->auto_connect != HCI_AUTO_CONN_EXPLICIT) + __hci_update_background_scan(req); } break; } @@ -6379,7 +6390,8 @@ static int remove_device(struct sock *sk, struct hci_dev *hdev, goto unlock; } - if (params->auto_connect == HCI_AUTO_CONN_DISABLED) { + if (params->auto_connect == HCI_AUTO_CONN_DISABLED || + params->auto_connect == HCI_AUTO_CONN_EXPLICIT) { err = cmd->cmd_complete(cmd, MGMT_STATUS_INVALID_PARAMS); mgmt_pending_remove(cmd); @@ -6415,6 +6427,10 @@ static int remove_device(struct sock *sk, struct hci_dev *hdev, if (p->auto_connect == HCI_AUTO_CONN_DISABLED) continue; device_removed(sk, hdev, &p->addr, p->addr_type); + if (p->explicit_connect) { + p->auto_connect = HCI_AUTO_CONN_EXPLICIT; + continue; + } list_del(&p->action); list_del(&p->list); kfree(p); diff --git a/net/core/dev.c b/net/core/dev.c index 6bb6470f5b7b..c14748d051e7 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -99,6 +99,7 @@ #include <linux/rtnetlink.h> #include <linux/stat.h> #include <net/dst.h> +#include <net/dst_metadata.h> #include <net/pkt_sched.h> #include <net/checksum.h> #include <net/xfrm.h> @@ -682,6 +683,32 @@ int dev_get_iflink(const struct net_device *dev) EXPORT_SYMBOL(dev_get_iflink); /** + * dev_fill_metadata_dst - Retrieve tunnel egress information. + * @dev: targeted interface + * @skb: The packet. + * + * For better visibility of tunnel traffic OVS needs to retrieve + * egress tunnel information for a packet. Following API allows + * user to get this info. + */ +int dev_fill_metadata_dst(struct net_device *dev, struct sk_buff *skb) +{ + struct ip_tunnel_info *info; + + if (!dev->netdev_ops || !dev->netdev_ops->ndo_fill_metadata_dst) + return -EINVAL; + + info = skb_tunnel_info_unclone(skb); + if (!info) + return -ENOMEM; + if (unlikely(!(info->mode & IP_TUNNEL_INFO_TX))) + return -EINVAL; + + return dev->netdev_ops->ndo_fill_metadata_dst(dev, skb); +} +EXPORT_SYMBOL_GPL(dev_fill_metadata_dst); + +/** * __dev_get_by_name - find a device by its name * @net: the applicable net namespace * @name: name to find diff --git a/net/core/ethtool.c b/net/core/ethtool.c index b495ab1797fa..29edf74846fc 100644 --- a/net/core/ethtool.c +++ b/net/core/ethtool.c @@ -1284,7 +1284,7 @@ static int ethtool_get_strings(struct net_device *dev, void __user *useraddr) gstrings.len = ret; - data = kmalloc(gstrings.len * ETH_GSTRING_LEN, GFP_USER); + data = kcalloc(gstrings.len, ETH_GSTRING_LEN, GFP_USER); if (!data) return -ENOMEM; diff --git a/net/core/filter.c b/net/core/filter.c index 05a04ea87172..bb18c3680001 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -1415,6 +1415,7 @@ static u64 bpf_clone_redirect(u64 r1, u64 ifindex, u64 flags, u64 r4, u64 r5) return dev_forward_skb(dev, skb2); skb2->dev = dev; + skb_sender_cpu_clear(skb2); return dev_queue_xmit(skb2); } @@ -1854,9 +1855,13 @@ int sk_get_filter(struct sock *sk, struct sock_filter __user *ubuf, goto out; /* We're copying the filter that has been originally attached, - * so no conversion/decode needed anymore. + * so no conversion/decode needed anymore. eBPF programs that + * have no original program cannot be dumped through this. */ + ret = -EACCES; fprog = filter->prog->orig_prog; + if (!fprog) + goto out; ret = fprog->len; if (!len) diff --git a/net/dsa/dsa.c b/net/dsa/dsa.c index c59fa5d9c22c..adb5325f4934 100644 --- a/net/dsa/dsa.c +++ b/net/dsa/dsa.c @@ -22,6 +22,7 @@ #include <linux/of_platform.h> #include <linux/of_net.h> #include <linux/sysfs.h> +#include <linux/phy_fixed.h> #include "dsa_priv.h" char dsa_driver_version[] = "0.1"; @@ -305,7 +306,7 @@ static int dsa_switch_setup_one(struct dsa_switch *ds, struct device *parent) if (ret < 0) goto out; - ds->slave_mii_bus = mdiobus_alloc(); + ds->slave_mii_bus = devm_mdiobus_alloc(parent); if (ds->slave_mii_bus == NULL) { ret = -ENOMEM; goto out; @@ -314,7 +315,7 @@ static int dsa_switch_setup_one(struct dsa_switch *ds, struct device *parent) ret = mdiobus_register(ds->slave_mii_bus); if (ret < 0) - goto out_free; + goto out; /* @@ -367,10 +368,7 @@ static int dsa_switch_setup_one(struct dsa_switch *ds, struct device *parent) return ret; -out_free: - mdiobus_free(ds->slave_mii_bus); out: - kfree(ds); return ret; } @@ -400,7 +398,7 @@ dsa_switch_setup(struct dsa_switch_tree *dst, int index, /* * Allocate and initialise switch state. */ - ds = kzalloc(sizeof(*ds) + drv->priv_size, GFP_KERNEL); + ds = devm_kzalloc(parent, sizeof(*ds) + drv->priv_size, GFP_KERNEL); if (ds == NULL) return ERR_PTR(-ENOMEM); @@ -420,10 +418,47 @@ dsa_switch_setup(struct dsa_switch_tree *dst, int index, static void dsa_switch_destroy(struct dsa_switch *ds) { + struct device_node *port_dn; + struct phy_device *phydev; + struct dsa_chip_data *cd = ds->pd; + int port; + #ifdef CONFIG_NET_DSA_HWMON if (ds->hwmon_dev) hwmon_device_unregister(ds->hwmon_dev); #endif + + /* Disable configuration of the CPU and DSA ports */ + for (port = 0; port < DSA_MAX_PORTS; port++) { + if (!(dsa_is_cpu_port(ds, port) || dsa_is_dsa_port(ds, port))) + continue; + + port_dn = cd->port_dn[port]; + if (of_phy_is_fixed_link(port_dn)) { + phydev = of_phy_find_device(port_dn); + if (phydev) { + int addr = phydev->addr; + + phy_device_free(phydev); + of_node_put(port_dn); + fixed_phy_del(addr); + } + } + } + + /* Destroy network devices for physical switch ports. */ + for (port = 0; port < DSA_MAX_PORTS; port++) { + if (!(ds->phys_port_mask & (1 << port))) + continue; + + if (!ds->ports[port]) + continue; + + unregister_netdev(ds->ports[port]); + free_netdev(ds->ports[port]); + } + + mdiobus_unregister(ds->slave_mii_bus); } #ifdef CONFIG_PM_SLEEP @@ -802,10 +837,11 @@ static inline void dsa_of_remove(struct device *dev) } #endif -static void dsa_setup_dst(struct dsa_switch_tree *dst, struct net_device *dev, - struct device *parent, struct dsa_platform_data *pd) +static int dsa_setup_dst(struct dsa_switch_tree *dst, struct net_device *dev, + struct device *parent, struct dsa_platform_data *pd) { int i; + unsigned configured = 0; dst->pd = pd; dst->master_netdev = dev; @@ -825,9 +861,17 @@ static void dsa_setup_dst(struct dsa_switch_tree *dst, struct net_device *dev, dst->ds[i] = ds; if (ds->drv->poll_link != NULL) dst->link_poll_needed = 1; + + ++configured; } /* + * If no switch was found, exit cleanly + */ + if (!configured) + return -EPROBE_DEFER; + + /* * If we use a tagging format that doesn't have an ethertype * field, make sure that all packets from this point on get * sent to the tag format's receive function. @@ -843,6 +887,8 @@ static void dsa_setup_dst(struct dsa_switch_tree *dst, struct net_device *dev, dst->link_poll_timer.expires = round_jiffies(jiffies + HZ); add_timer(&dst->link_poll_timer); } + + return 0; } static int dsa_probe(struct platform_device *pdev) @@ -883,7 +929,7 @@ static int dsa_probe(struct platform_device *pdev) goto out; } - dst = kzalloc(sizeof(*dst), GFP_KERNEL); + dst = devm_kzalloc(&pdev->dev, sizeof(*dst), GFP_KERNEL); if (dst == NULL) { dev_put(dev); ret = -ENOMEM; @@ -892,7 +938,9 @@ static int dsa_probe(struct platform_device *pdev) platform_set_drvdata(pdev, dst); - dsa_setup_dst(dst, dev, &pdev->dev, pd); + ret = dsa_setup_dst(dst, dev, &pdev->dev, pd); + if (ret) + goto out; return 0; @@ -914,7 +962,7 @@ static void dsa_remove_dst(struct dsa_switch_tree *dst) for (i = 0; i < dst->pd->nr_chips; i++) { struct dsa_switch *ds = dst->ds[i]; - if (ds != NULL) + if (ds) dsa_switch_destroy(ds); } } diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c index f03db8b7abee..0c9c3482e419 100644 --- a/net/ipv4/arp.c +++ b/net/ipv4/arp.c @@ -312,7 +312,7 @@ static void arp_send_dst(int type, int ptype, __be32 dest_ip, if (!skb) return; - skb_dst_set(skb, dst); + skb_dst_set(skb, dst_clone(dst)); arp_xmit(skb); } @@ -384,7 +384,7 @@ static void arp_solicit(struct neighbour *neigh, struct sk_buff *skb) } if (skb && !(dev->priv_flags & IFF_XMIT_DST_RELEASE)) - dst = dst_clone(skb_dst(skb)); + dst = skb_dst(skb); arp_send_dst(ARPOP_REQUEST, ETH_P_ARP, target, dev, saddr, dst_hw, dev->dev_addr, NULL, dst); } @@ -811,7 +811,7 @@ static int arp_process(struct sock *sk, struct sk_buff *skb) } else { pneigh_enqueue(&arp_tbl, in_dev->arp_parms, skb); - return 0; + goto out_free_dst; } goto out; } @@ -865,6 +865,8 @@ static int arp_process(struct sock *sk, struct sk_buff *skb) out: consume_skb(skb); +out_free_dst: + dst_release(reply_dst); return 0; } diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index 6c2af797f2f9..744e5936c10d 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -1569,7 +1569,7 @@ static struct key_vector *leaf_walk_rcu(struct key_vector **tn, t_key key) do { /* record parent and next child index */ pn = n; - cindex = key ? get_index(key, pn) : 0; + cindex = (key > pn->key) ? get_index(key, pn) : 0; if (cindex >> pn->bits) break; diff --git a/net/ipv4/gre_offload.c b/net/ipv4/gre_offload.c index 5aa46d4b44ef..5a8ee3282550 100644 --- a/net/ipv4/gre_offload.c +++ b/net/ipv4/gre_offload.c @@ -36,7 +36,8 @@ static struct sk_buff *gre_gso_segment(struct sk_buff *skb, SKB_GSO_TCP_ECN | SKB_GSO_GRE | SKB_GSO_GRE_CSUM | - SKB_GSO_IPIP))) + SKB_GSO_IPIP | + SKB_GSO_SIT))) goto out; if (!skb->encapsulation) diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index c73345f0fefc..09f5301cb586 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -577,21 +577,22 @@ EXPORT_SYMBOL(inet_rtx_syn_ack); static bool reqsk_queue_unlink(struct request_sock_queue *queue, struct request_sock *req) { - struct listen_sock *lopt = queue->listen_opt; struct request_sock **prev; + struct listen_sock *lopt; bool found = false; spin_lock(&queue->syn_wait_lock); - - for (prev = &lopt->syn_table[req->rsk_hash]; *prev != NULL; - prev = &(*prev)->dl_next) { - if (*prev == req) { - *prev = req->dl_next; - found = true; - break; + lopt = queue->listen_opt; + if (lopt) { + for (prev = &lopt->syn_table[req->rsk_hash]; *prev != NULL; + prev = &(*prev)->dl_next) { + if (*prev == req) { + *prev = req->dl_next; + found = true; + break; + } } } - spin_unlock(&queue->syn_wait_lock); if (timer_pending(&req->rsk_timer) && del_timer_sync(&req->rsk_timer)) reqsk_put(req); diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index bd0679d90519..614521437e30 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -498,10 +498,26 @@ static struct sk_buff *gre_handle_offloads(struct sk_buff *skb, csum ? SKB_GSO_GRE_CSUM : SKB_GSO_GRE); } +static struct rtable *gre_get_rt(struct sk_buff *skb, + struct net_device *dev, + struct flowi4 *fl, + const struct ip_tunnel_key *key) +{ + struct net *net = dev_net(dev); + + memset(fl, 0, sizeof(*fl)); + fl->daddr = key->u.ipv4.dst; + fl->saddr = key->u.ipv4.src; + fl->flowi4_tos = RT_TOS(key->tos); + fl->flowi4_mark = skb->mark; + fl->flowi4_proto = IPPROTO_GRE; + + return ip_route_output_key(net, fl); +} + static void gre_fb_xmit(struct sk_buff *skb, struct net_device *dev) { struct ip_tunnel_info *tun_info; - struct net *net = dev_net(dev); const struct ip_tunnel_key *key; struct flowi4 fl; struct rtable *rt; @@ -516,14 +532,7 @@ static void gre_fb_xmit(struct sk_buff *skb, struct net_device *dev) goto err_free_skb; key = &tun_info->key; - memset(&fl, 0, sizeof(fl)); - fl.daddr = key->u.ipv4.dst; - fl.saddr = key->u.ipv4.src; - fl.flowi4_tos = RT_TOS(key->tos); - fl.flowi4_mark = skb->mark; - fl.flowi4_proto = IPPROTO_GRE; - - rt = ip_route_output_key(net, &fl); + rt = gre_get_rt(skb, dev, &fl, key); if (IS_ERR(rt)) goto err_free_skb; @@ -566,6 +575,24 @@ err_free_skb: dev->stats.tx_dropped++; } +static int gre_fill_metadata_dst(struct net_device *dev, struct sk_buff *skb) +{ + struct ip_tunnel_info *info = skb_tunnel_info(skb); + struct rtable *rt; + struct flowi4 fl4; + + if (ip_tunnel_info_af(info) != AF_INET) + return -EINVAL; + + rt = gre_get_rt(skb, dev, &fl4, &info->key); + if (IS_ERR(rt)) + return PTR_ERR(rt); + + ip_rt_put(rt); + info->key.u.ipv4.src = fl4.saddr; + return 0; +} + static netdev_tx_t ipgre_xmit(struct sk_buff *skb, struct net_device *dev) { @@ -1023,6 +1050,7 @@ static const struct net_device_ops gre_tap_netdev_ops = { .ndo_change_mtu = ip_tunnel_change_mtu, .ndo_get_stats64 = ip_tunnel_get_stats64, .ndo_get_iflink = ip_tunnel_get_iflink, + .ndo_fill_metadata_dst = gre_fill_metadata_dst, }; static void ipgre_tap_setup(struct net_device *dev) diff --git a/net/ipv4/netfilter/Kconfig b/net/ipv4/netfilter/Kconfig index 690d27d3f2f9..a35584176535 100644 --- a/net/ipv4/netfilter/Kconfig +++ b/net/ipv4/netfilter/Kconfig @@ -75,6 +75,7 @@ endif # NF_TABLES config NF_DUP_IPV4 tristate "Netfilter IPv4 packet duplication to alternate destination" + depends on !NF_CONNTRACK || NF_CONNTRACK help This option enables the nf_dup_ipv4 core, which duplicates an IPv4 packet to be rerouted to another destination. diff --git a/net/ipv4/netfilter/ipt_rpfilter.c b/net/ipv4/netfilter/ipt_rpfilter.c index 8618fd150c96..c4ffc9de1654 100644 --- a/net/ipv4/netfilter/ipt_rpfilter.c +++ b/net/ipv4/netfilter/ipt_rpfilter.c @@ -61,9 +61,7 @@ static bool rpfilter_lookup_reverse(struct flowi4 *fl4, if (FIB_RES_DEV(res) == dev) dev_match = true; #endif - if (dev_match || flags & XT_RPFILTER_LOOSE) - return FIB_RES_NH(res).nh_scope <= RT_SCOPE_HOST; - return dev_match; + return dev_match || flags & XT_RPFILTER_LOOSE; } static bool rpfilter_is_local(const struct sk_buff *skb) diff --git a/net/ipv4/tcp_dctcp.c b/net/ipv4/tcp_dctcp.c index 7092a61c4dc8..7e538f71f5fb 100644 --- a/net/ipv4/tcp_dctcp.c +++ b/net/ipv4/tcp_dctcp.c @@ -209,7 +209,7 @@ static void dctcp_update_alpha(struct sock *sk, u32 flags) /* alpha = (1 - g) * alpha + g * F */ - alpha -= alpha >> dctcp_shift_g; + alpha -= min_not_zero(alpha, alpha >> dctcp_shift_g); if (bytes_ecn) { /* If dctcp_shift_g == 1, a 32bit value would overflow * after 8 Mbytes. diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index ecfb74de0980..0f29a94723ae 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -3405,7 +3405,7 @@ static int tcp_xmit_probe_skb(struct sock *sk, int urgent, int mib) */ tcp_init_nondata_skb(skb, tp->snd_una - !urgent, TCPHDR_ACK); skb_mstamp_get(&skb->skb_mstamp); - NET_INC_STATS_BH(sock_net(sk), mib); + NET_INC_STATS(sock_net(sk), mib); return tcp_transmit_skb(sk, skb, 0, GFP_ATOMIC); } diff --git a/net/ipv4/xfrm4_output.c b/net/ipv4/xfrm4_output.c index 2878dbfffeb7..41a261355662 100644 --- a/net/ipv4/xfrm4_output.c +++ b/net/ipv4/xfrm4_output.c @@ -30,6 +30,8 @@ static int xfrm4_tunnel_check_size(struct sk_buff *skb) mtu = dst_mtu(skb_dst(skb)); if (skb->len > mtu) { + skb->protocol = htons(ETH_P_IP); + if (skb->sk) xfrm_local_error(skb, mtu); else diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index cb6fca279464..6947dcd773ef 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -3147,6 +3147,8 @@ static void addrconf_gre_config(struct net_device *dev) } addrconf_addr_gen(idev, true); + if (dev->flags & IFF_POINTOPOINT) + addrconf_add_mroute(dev); } #endif diff --git a/net/ipv6/fib6_rules.c b/net/ipv6/fib6_rules.c index 9f777ec59a59..ed33abf57abd 100644 --- a/net/ipv6/fib6_rules.c +++ b/net/ipv6/fib6_rules.c @@ -32,6 +32,7 @@ struct fib6_rule { struct dst_entry *fib6_rule_lookup(struct net *net, struct flowi6 *fl6, int flags, pol_lookup_t lookup) { + struct rt6_info *rt; struct fib_lookup_arg arg = { .lookup_ptr = lookup, .flags = FIB_LOOKUP_NOREF, @@ -40,11 +41,21 @@ struct dst_entry *fib6_rule_lookup(struct net *net, struct flowi6 *fl6, fib_rules_lookup(net->ipv6.fib6_rules_ops, flowi6_to_flowi(fl6), flags, &arg); - if (arg.result) - return arg.result; + rt = arg.result; - dst_hold(&net->ipv6.ip6_null_entry->dst); - return &net->ipv6.ip6_null_entry->dst; + if (!rt) { + dst_hold(&net->ipv6.ip6_null_entry->dst); + return &net->ipv6.ip6_null_entry->dst; + } + + if (rt->rt6i_flags & RTF_REJECT && + rt->dst.error == -EAGAIN) { + ip6_rt_put(rt); + rt = net->ipv6.ip6_null_entry; + dst_hold(&rt->dst); + } + + return &rt->dst; } static int fib6_rule_action(struct fib_rule *rule, struct flowi *flp, diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index 7d2e0023c72d..6cedc62b2abb 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -285,7 +285,17 @@ struct fib6_table *fib6_get_table(struct net *net, u32 id) struct dst_entry *fib6_rule_lookup(struct net *net, struct flowi6 *fl6, int flags, pol_lookup_t lookup) { - return (struct dst_entry *) lookup(net, net->ipv6.fib6_main_tbl, fl6, flags); + struct rt6_info *rt; + + rt = lookup(net, net->ipv6.fib6_main_tbl, fl6, flags); + if (rt->rt6i_flags & RTF_REJECT && + rt->dst.error == -EAGAIN) { + ip6_rt_put(rt); + rt = net->ipv6.ip6_null_entry; + dst_hold(&rt->dst); + } + + return &rt->dst; } static void __net_init fib6_tables_init(struct net *net) diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 92b1aa38f121..f84ec4e9b2de 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -376,6 +376,9 @@ int ip6_forward(struct sk_buff *skb) if (skb->pkt_type != PACKET_HOST) goto drop; + if (unlikely(skb->sk)) + goto drop; + if (skb_warn_if_lro(skb)) goto drop; @@ -581,6 +584,8 @@ int ip6_fragment(struct sock *sk, struct sk_buff *skb, if (np->frag_size) mtu = np->frag_size; } + if (mtu < hlen + sizeof(struct frag_hdr) + 8) + goto fail_toobig; mtu -= hlen + sizeof(struct frag_hdr); frag_id = ipv6_select_ident(net, &ipv6_hdr(skb)->daddr, @@ -874,7 +879,8 @@ static struct dst_entry *ip6_sk_dst_check(struct sock *sk, #ifdef CONFIG_IPV6_SUBTREES ip6_rt_check(&rt->rt6i_src, &fl6->saddr, np->saddr_cache) || #endif - (fl6->flowi6_oif && fl6->flowi6_oif != dst->dev->ifindex)) { + (!(fl6->flowi6_flags & FLOWI_FLAG_SKIP_NH_OIF) && + (fl6->flowi6_oif && fl6->flowi6_oif != dst->dev->ifindex))) { dst_release(dst); dst = NULL; } diff --git a/net/ipv6/netfilter/Kconfig b/net/ipv6/netfilter/Kconfig index 96833e4b3193..f6a024e141e5 100644 --- a/net/ipv6/netfilter/Kconfig +++ b/net/ipv6/netfilter/Kconfig @@ -58,6 +58,7 @@ endif # NF_TABLES config NF_DUP_IPV6 tristate "Netfilter IPv6 packet duplication to alternate destination" + depends on !NF_CONNTRACK || NF_CONNTRACK help This option enables the nf_dup_ipv6 core, which duplicates an IPv6 packet to be rerouted to another destination. diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c index 701cd2bae0a9..c7196ad1d69f 100644 --- a/net/ipv6/netfilter/nf_conntrack_reasm.c +++ b/net/ipv6/netfilter/nf_conntrack_reasm.c @@ -646,6 +646,7 @@ void nf_ct_frag6_consume_orig(struct sk_buff *skb) s = s2; } } +EXPORT_SYMBOL_GPL(nf_ct_frag6_consume_orig); static int nf_ct_net_init(struct net *net) { diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 391895caf08b..ed4aef72ba6d 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -141,6 +141,9 @@ static void rt6_uncached_list_flush_dev(struct net *net, struct net_device *dev) struct net_device *loopback_dev = net->loopback_dev; int cpu; + if (dev == loopback_dev) + return; + for_each_possible_cpu(cpu) { struct uncached_list *ul = per_cpu_ptr(&rt6_uncached_list, cpu); struct rt6_info *rt; @@ -150,14 +153,12 @@ static void rt6_uncached_list_flush_dev(struct net *net, struct net_device *dev) struct inet6_dev *rt_idev = rt->rt6i_idev; struct net_device *rt_dev = rt->dst.dev; - if (rt_idev && (rt_idev->dev == dev || !dev) && - rt_idev->dev != loopback_dev) { + if (rt_idev->dev == dev) { rt->rt6i_idev = in6_dev_get(loopback_dev); in6_dev_put(rt_idev); } - if (rt_dev && (rt_dev == dev || !dev) && - rt_dev != loopback_dev) { + if (rt_dev == dev) { rt->dst.dev = loopback_dev; dev_hold(rt->dst.dev); dev_put(rt_dev); @@ -246,12 +247,6 @@ static void ip6_rt_blackhole_redirect(struct dst_entry *dst, struct sock *sk, { } -static u32 *ip6_rt_blackhole_cow_metrics(struct dst_entry *dst, - unsigned long old) -{ - return NULL; -} - static struct dst_ops ip6_dst_blackhole_ops = { .family = AF_INET6, .destroy = ip6_dst_destroy, @@ -260,7 +255,7 @@ static struct dst_ops ip6_dst_blackhole_ops = { .default_advmss = ip6_default_advmss, .update_pmtu = ip6_rt_blackhole_update_pmtu, .redirect = ip6_rt_blackhole_redirect, - .cow_metrics = ip6_rt_blackhole_cow_metrics, + .cow_metrics = dst_cow_metrics_generic, .neigh_lookup = ip6_neigh_lookup, }; @@ -317,6 +312,15 @@ static const struct rt6_info ip6_blk_hole_entry_template = { #endif +static void rt6_info_init(struct rt6_info *rt) +{ + struct dst_entry *dst = &rt->dst; + + memset(dst + 1, 0, sizeof(*rt) - sizeof(*dst)); + INIT_LIST_HEAD(&rt->rt6i_siblings); + INIT_LIST_HEAD(&rt->rt6i_uncached); +} + /* allocate dst with ip6_dst_ops */ static struct rt6_info *__ip6_dst_alloc(struct net *net, struct net_device *dev, @@ -325,13 +329,9 @@ static struct rt6_info *__ip6_dst_alloc(struct net *net, struct rt6_info *rt = dst_alloc(&net->ipv6.ip6_dst_ops, dev, 0, DST_OBSOLETE_FORCE_CHK, flags); - if (rt) { - struct dst_entry *dst = &rt->dst; + if (rt) + rt6_info_init(rt); - memset(dst + 1, 0, sizeof(*rt) - sizeof(*dst)); - INIT_LIST_HEAD(&rt->rt6i_siblings); - INIT_LIST_HEAD(&rt->rt6i_uncached); - } return rt; } @@ -1064,6 +1064,9 @@ static struct rt6_info *ip6_pol_route(struct net *net, struct fib6_table *table, fn = fib6_lookup(&table->tb6_root, &fl6->daddr, &fl6->saddr); saved_fn = fn; + if (fl6->flowi6_flags & FLOWI_FLAG_SKIP_NH_OIF) + oif = 0; + redo_rt6_select: rt = rt6_select(fn, oif, strict); if (rt->rt6i_nsiblings) @@ -1186,14 +1189,16 @@ struct dst_entry *ip6_route_output(struct net *net, const struct sock *sk, struct flowi6 *fl6) { int flags = 0; + bool any_src; fl6->flowi6_iif = LOOPBACK_IFINDEX; + any_src = ipv6_addr_any(&fl6->saddr); if ((sk && sk->sk_bound_dev_if) || rt6_need_strict(&fl6->daddr) || - fl6->flowi6_oif) + (fl6->flowi6_oif && any_src)) flags |= RT6_LOOKUP_F_IFACE; - if (!ipv6_addr_any(&fl6->saddr)) + if (!any_src) flags |= RT6_LOOKUP_F_HAS_SADDR; else if (sk) flags |= rt6_srcprefs2flags(inet6_sk(sk)->srcprefs); @@ -1209,24 +1214,20 @@ struct dst_entry *ip6_blackhole_route(struct net *net, struct dst_entry *dst_ori rt = dst_alloc(&ip6_dst_blackhole_ops, ort->dst.dev, 1, DST_OBSOLETE_NONE, 0); if (rt) { - new = &rt->dst; - - memset(new + 1, 0, sizeof(*rt) - sizeof(*new)); + rt6_info_init(rt); + new = &rt->dst; new->__use = 1; new->input = dst_discard; new->output = dst_discard_sk; - if (dst_metrics_read_only(&ort->dst)) - new->_metrics = ort->dst._metrics; - else - dst_copy_metrics(new, &ort->dst); + dst_copy_metrics(new, &ort->dst); rt->rt6i_idev = ort->rt6i_idev; if (rt->rt6i_idev) in6_dev_hold(rt->rt6i_idev); rt->rt6i_gateway = ort->rt6i_gateway; - rt->rt6i_flags = ort->rt6i_flags; + rt->rt6i_flags = ort->rt6i_flags & ~RTF_PCPU; rt->rt6i_metric = 0; memcpy(&rt->rt6i_dst, &ort->rt6i_dst, sizeof(struct rt6key)); @@ -2609,7 +2610,8 @@ void rt6_ifdown(struct net *net, struct net_device *dev) fib6_clean_all(net, fib6_ifdown, &adn); icmp6_clean_all(fib6_ifdown, &adn); - rt6_uncached_list_flush_dev(net, dev); + if (dev) + rt6_uncached_list_flush_dev(net, dev); } struct rt6_mtu_change_arg { diff --git a/net/ipv6/xfrm6_output.c b/net/ipv6/xfrm6_output.c index 09c76a7b474d..e15feb7b413d 100644 --- a/net/ipv6/xfrm6_output.c +++ b/net/ipv6/xfrm6_output.c @@ -79,6 +79,7 @@ static int xfrm6_tunnel_check_size(struct sk_buff *skb) if (!skb->ignore_df && skb->len > mtu) { skb->dev = dst->dev; + skb->protocol = htons(ETH_P_IPV6); if (xfrm6_local_dontfrag(skb)) xfrm6_local_rxpmtu(skb, mtu); @@ -136,6 +137,7 @@ static int __xfrm6_output(struct sock *sk, struct sk_buff *skb) struct dst_entry *dst = skb_dst(skb); struct xfrm_state *x = dst->xfrm; int mtu; + bool toobig; #ifdef CONFIG_NETFILTER if (!x) { @@ -144,25 +146,29 @@ static int __xfrm6_output(struct sock *sk, struct sk_buff *skb) } #endif + if (x->props.mode != XFRM_MODE_TUNNEL) + goto skip_frag; + if (skb->protocol == htons(ETH_P_IPV6)) mtu = ip6_skb_dst_mtu(skb); else mtu = dst_mtu(skb_dst(skb)); - if (skb->len > mtu && xfrm6_local_dontfrag(skb)) { + toobig = skb->len > mtu && !skb_is_gso(skb); + + if (toobig && xfrm6_local_dontfrag(skb)) { xfrm6_local_rxpmtu(skb, mtu); return -EMSGSIZE; - } else if (!skb->ignore_df && skb->len > mtu && skb->sk) { + } else if (!skb->ignore_df && toobig && skb->sk) { xfrm_local_error(skb, mtu); return -EMSGSIZE; } - if (x->props.mode == XFRM_MODE_TUNNEL && - ((skb->len > mtu && !skb_is_gso(skb)) || - dst_allfrag(skb_dst(skb)))) { + if (toobig || dst_allfrag(skb_dst(skb))) return ip6_fragment(sk, skb, x->outer_mode->afinfo->output_finish); - } + +skip_frag: return x->outer_mode->afinfo->output_finish(sk, skb); } diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c index 30caa289c5db..da55e0c85bb8 100644 --- a/net/ipv6/xfrm6_policy.c +++ b/net/ipv6/xfrm6_policy.c @@ -37,6 +37,7 @@ static struct dst_entry *xfrm6_dst_lookup(struct net *net, int tos, int oif, memset(&fl6, 0, sizeof(fl6)); fl6.flowi6_oif = oif; + fl6.flowi6_flags = FLOWI_FLAG_SKIP_NH_OIF; memcpy(&fl6.daddr, daddr, sizeof(fl6.daddr)); if (saddr) memcpy(&fl6.saddr, saddr, sizeof(fl6.saddr)); @@ -178,7 +179,8 @@ _decode_session6(struct sk_buff *skb, struct flowi *fl, int reverse) return; case IPPROTO_ICMPV6: - if (!onlyproto && pskb_may_pull(skb, nh + offset + 2 - skb->data)) { + if (!onlyproto && (nh + offset + 2 < skb->data || + pskb_may_pull(skb, nh + offset + 2 - skb->data))) { u8 *icmp; nh = skb_network_header(skb); @@ -192,7 +194,8 @@ _decode_session6(struct sk_buff *skb, struct flowi *fl, int reverse) #if IS_ENABLED(CONFIG_IPV6_MIP6) case IPPROTO_MH: offset += ipv6_optlen(exthdr); - if (!onlyproto && pskb_may_pull(skb, nh + offset + 3 - skb->data)) { + if (!onlyproto && (nh + offset + 3 < skb->data || + pskb_may_pull(skb, nh + offset + 3 - skb->data))) { struct ip6_mh *mh; nh = skb_network_header(skb); diff --git a/net/irda/irlmp.c b/net/irda/irlmp.c index a26c401ef4a4..43964594aa12 100644 --- a/net/irda/irlmp.c +++ b/net/irda/irlmp.c @@ -1839,7 +1839,7 @@ static void *irlmp_seq_hb_idx(struct irlmp_iter_state *iter, loff_t *off) for (element = hashbin_get_first(iter->hashbin); element != NULL; element = hashbin_get_next(iter->hashbin)) { - if (!off || *off-- == 0) { + if (!off || (*off)-- == 0) { /* NB: hashbin left locked */ return element; } diff --git a/net/key/af_key.c b/net/key/af_key.c index 83a70688784b..f9c9ecb0cdd3 100644 --- a/net/key/af_key.c +++ b/net/key/af_key.c @@ -261,7 +261,7 @@ static int pfkey_broadcast(struct sk_buff *skb, err2 = pfkey_broadcast_one(skb, &skb2, GFP_ATOMIC, sk); - /* Error is cleare after succecful sending to at least one + /* Error is cleared after successful sending to at least one * registered KM */ if ((broadcast_flags & BROADCAST_REGISTERED) && err) err = err2; diff --git a/net/mac80211/debugfs.c b/net/mac80211/debugfs.c index ced6bf3be8d6..1560c8482bcb 100644 --- a/net/mac80211/debugfs.c +++ b/net/mac80211/debugfs.c @@ -149,7 +149,7 @@ static ssize_t hwflags_read(struct file *file, char __user *user_buf, for (i = 0; i < NUM_IEEE80211_HW_FLAGS; i++) { if (test_bit(i, local->hw.flags)) - pos += scnprintf(pos, end - pos, "%s", + pos += scnprintf(pos, end - pos, "%s\n", hw_flag_names[i]); } diff --git a/net/mac80211/status.c b/net/mac80211/status.c index 8ba583243509..3ed7ddfbf8e8 100644 --- a/net/mac80211/status.c +++ b/net/mac80211/status.c @@ -101,6 +101,7 @@ static void ieee80211_handle_filtered_frame(struct ieee80211_local *local, * when it wakes up for the next time. */ set_sta_flag(sta, WLAN_STA_CLEAR_PS_FILT); + ieee80211_clear_fast_xmit(sta); /* * This code races in the following way: diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c index 84e0e8c7fb23..7892eb8ed4c8 100644 --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -1218,8 +1218,10 @@ ieee80211_tx_prepare(struct ieee80211_sub_if_data *sdata, if (!tx->sta) info->flags |= IEEE80211_TX_CTL_CLEAR_PS_FILT; - else if (test_and_clear_sta_flag(tx->sta, WLAN_STA_CLEAR_PS_FILT)) + else if (test_and_clear_sta_flag(tx->sta, WLAN_STA_CLEAR_PS_FILT)) { info->flags |= IEEE80211_TX_CTL_CLEAR_PS_FILT; + ieee80211_check_fast_xmit(tx->sta); + } info->flags |= IEEE80211_TX_CTL_FIRST_FRAGMENT; @@ -2451,7 +2453,8 @@ void ieee80211_check_fast_xmit(struct sta_info *sta) if (test_sta_flag(sta, WLAN_STA_PS_STA) || test_sta_flag(sta, WLAN_STA_PS_DRIVER) || - test_sta_flag(sta, WLAN_STA_PS_DELIVER)) + test_sta_flag(sta, WLAN_STA_PS_DELIVER) || + test_sta_flag(sta, WLAN_STA_CLEAR_PS_FILT)) goto out; if (sdata->noack_map) diff --git a/net/netfilter/core.c b/net/netfilter/core.c index 8e47f8113495..21a085686dc1 100644 --- a/net/netfilter/core.c +++ b/net/netfilter/core.c @@ -152,6 +152,8 @@ void nf_unregister_net_hook(struct net *net, const struct nf_hook_ops *reg) #endif synchronize_net(); nf_queue_nf_hook_drop(net, &entry->ops); + /* other cpu might still process nfqueue verdict that used reg */ + synchronize_net(); kfree(entry); } EXPORT_SYMBOL(nf_unregister_net_hook); diff --git a/net/netfilter/ipset/ip_set_list_set.c b/net/netfilter/ipset/ip_set_list_set.c index a1fe5377a2b3..5a30ce6e8c90 100644 --- a/net/netfilter/ipset/ip_set_list_set.c +++ b/net/netfilter/ipset/ip_set_list_set.c @@ -297,7 +297,7 @@ list_set_uadd(struct ip_set *set, void *value, const struct ip_set_ext *ext, ip_set_timeout_expired(ext_timeout(n, set)))) n = NULL; - e = kzalloc(set->dsize, GFP_KERNEL); + e = kzalloc(set->dsize, GFP_ATOMIC); if (!e) return -ENOMEM; e->id = d->id; diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index 8f060d7f9a0e..fafe33bdb619 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -2371,7 +2371,7 @@ static int netlink_getsockopt(struct socket *sock, int level, int optname, int pos, idx, shift; err = 0; - netlink_table_grab(); + netlink_lock_table(); for (pos = 0; pos * 8 < nlk->ngroups; pos += sizeof(u32)) { if (len - pos < sizeof(u32)) break; @@ -2386,7 +2386,7 @@ static int netlink_getsockopt(struct socket *sock, int level, int optname, } if (put_user(ALIGN(nlk->ngroups / 8, sizeof(u32)), optlen)) err = -EFAULT; - netlink_table_ungrab(); + netlink_unlock_table(); break; } case NETLINK_CAP_ACK: @@ -2785,6 +2785,7 @@ static int netlink_dump(struct sock *sk) struct sk_buff *skb = NULL; struct nlmsghdr *nlh; int len, err = -ENOBUFS; + int alloc_min_size; int alloc_size; mutex_lock(nlk->cb_mutex); @@ -2793,9 +2794,6 @@ static int netlink_dump(struct sock *sk) goto errout_skb; } - cb = &nlk->cb; - alloc_size = max_t(int, cb->min_dump_alloc, NLMSG_GOODSIZE); - if (!netlink_rx_is_mmaped(sk) && atomic_read(&sk->sk_rmem_alloc) >= sk->sk_rcvbuf) goto errout_skb; @@ -2805,23 +2803,35 @@ static int netlink_dump(struct sock *sk) * to reduce number of system calls on dump operations, if user * ever provided a big enough buffer. */ - if (alloc_size < nlk->max_recvmsg_len) { - skb = netlink_alloc_skb(sk, - nlk->max_recvmsg_len, - nlk->portid, + cb = &nlk->cb; + alloc_min_size = max_t(int, cb->min_dump_alloc, NLMSG_GOODSIZE); + + if (alloc_min_size < nlk->max_recvmsg_len) { + alloc_size = nlk->max_recvmsg_len; + skb = netlink_alloc_skb(sk, alloc_size, nlk->portid, GFP_KERNEL | __GFP_NOWARN | __GFP_NORETRY); - /* available room should be exact amount to avoid MSG_TRUNC */ - if (skb) - skb_reserve(skb, skb_tailroom(skb) - - nlk->max_recvmsg_len); } - if (!skb) + if (!skb) { + alloc_size = alloc_min_size; skb = netlink_alloc_skb(sk, alloc_size, nlk->portid, GFP_KERNEL); + } if (!skb) goto errout_skb; + + /* Trim skb to allocated size. User is expected to provide buffer as + * large as max(min_dump_alloc, 16KiB (mac_recvmsg_len capped at + * netlink_recvmsg())). dump will pack as many smaller messages as + * could fit within the allocated skb. skb is typically allocated + * with larger space than required (could be as much as near 2x the + * requested size with align to next power of 2 approach). Allowing + * dump to use the excess space makes it difficult for a user to have a + * reasonable static buffer based on the expected largest dump of a + * single netdev. The outcome is MSG_TRUNC error. + */ + skb_reserve(skb, skb_tailroom(skb) - alloc_size); netlink_skb_set_owner_r(skb, sk); len = cb->dump(skb, cb); diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c index 315f5330b6e5..dba635d086b2 100644 --- a/net/openvswitch/actions.c +++ b/net/openvswitch/actions.c @@ -684,7 +684,7 @@ static void ovs_fragment(struct vport *vport, struct sk_buff *skb, u16 mru, { if (skb_network_offset(skb) > MAX_L2_LEN) { OVS_NLERR(1, "L2 header too long to fragment"); - return; + goto err; } if (ethertype == htons(ETH_P_IP)) { @@ -708,8 +708,7 @@ static void ovs_fragment(struct vport *vport, struct sk_buff *skb, u16 mru, struct rt6_info ovs_rt; if (!v6ops) { - kfree_skb(skb); - return; + goto err; } prepare_frag(vport, skb); @@ -728,8 +727,12 @@ static void ovs_fragment(struct vport *vport, struct sk_buff *skb, u16 mru, WARN_ONCE(1, "Failed fragment ->%s: eth=%04x, MRU=%d, MTU=%d.", ovs_vport_name(vport), ntohs(ethertype), mru, vport->dev->mtu); - kfree_skb(skb); + goto err; } + + return; +err: + kfree_skb(skb); } static void do_output(struct datapath *dp, struct sk_buff *skb, int out_port, @@ -765,7 +768,6 @@ static int output_userspace(struct datapath *dp, struct sk_buff *skb, struct sw_flow_key *key, const struct nlattr *attr, const struct nlattr *actions, int actions_len) { - struct ip_tunnel_info info; struct dp_upcall_info upcall; const struct nlattr *a; int rem; @@ -793,11 +795,9 @@ static int output_userspace(struct datapath *dp, struct sk_buff *skb, if (vport) { int err; - upcall.egress_tun_info = &info; - err = ovs_vport_get_egress_tun_info(vport, skb, - &upcall); - if (err) - upcall.egress_tun_info = NULL; + err = dev_fill_metadata_dst(vport->dev, skb); + if (!err) + upcall.egress_tun_info = skb_tunnel_info(skb); } break; @@ -968,7 +968,7 @@ static int execute_masked_set_action(struct sk_buff *skb, case OVS_KEY_ATTR_CT_STATE: case OVS_KEY_ATTR_CT_ZONE: case OVS_KEY_ATTR_CT_MARK: - case OVS_KEY_ATTR_CT_LABEL: + case OVS_KEY_ATTR_CT_LABELS: err = -EINVAL; break; } @@ -1099,12 +1099,18 @@ static int do_execute_actions(struct datapath *dp, struct sk_buff *skb, break; case OVS_ACTION_ATTR_CT: + if (!is_flow_key_valid(key)) { + err = ovs_flow_key_update(skb, key); + if (err) + return err; + } + err = ovs_ct_execute(ovs_dp_get_net(dp), skb, key, nla_data(a)); /* Hide stolen IP fragments from user space. */ - if (err == -EINPROGRESS) - return 0; + if (err) + return err == -EINPROGRESS ? 0 : err; break; } diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c index 002a755fa07e..50095820edb7 100644 --- a/net/openvswitch/conntrack.c +++ b/net/openvswitch/conntrack.c @@ -37,9 +37,9 @@ struct md_mark { }; /* Metadata label for masked write to conntrack label. */ -struct md_label { - struct ovs_key_ct_label value; - struct ovs_key_ct_label mask; +struct md_labels { + struct ovs_key_ct_labels value; + struct ovs_key_ct_labels mask; }; /* Conntrack action context for execution. */ @@ -47,10 +47,10 @@ struct ovs_conntrack_info { struct nf_conntrack_helper *helper; struct nf_conntrack_zone zone; struct nf_conn *ct; - u32 flags; + u8 commit : 1; u16 family; struct md_mark mark; - struct md_label label; + struct md_labels labels; }; static u16 key_to_nfproto(const struct sw_flow_key *key) @@ -109,21 +109,21 @@ static u32 ovs_ct_get_mark(const struct nf_conn *ct) #endif } -static void ovs_ct_get_label(const struct nf_conn *ct, - struct ovs_key_ct_label *label) +static void ovs_ct_get_labels(const struct nf_conn *ct, + struct ovs_key_ct_labels *labels) { struct nf_conn_labels *cl = ct ? nf_ct_labels_find(ct) : NULL; if (cl) { size_t len = cl->words * sizeof(long); - if (len > OVS_CT_LABEL_LEN) - len = OVS_CT_LABEL_LEN; - else if (len < OVS_CT_LABEL_LEN) - memset(label, 0, OVS_CT_LABEL_LEN); - memcpy(label, cl->bits, len); + if (len > OVS_CT_LABELS_LEN) + len = OVS_CT_LABELS_LEN; + else if (len < OVS_CT_LABELS_LEN) + memset(labels, 0, OVS_CT_LABELS_LEN); + memcpy(labels, cl->bits, len); } else { - memset(label, 0, OVS_CT_LABEL_LEN); + memset(labels, 0, OVS_CT_LABELS_LEN); } } @@ -134,7 +134,7 @@ static void __ovs_ct_update_key(struct sw_flow_key *key, u8 state, key->ct.state = state; key->ct.zone = zone->id; key->ct.mark = ovs_ct_get_mark(ct); - ovs_ct_get_label(ct, &key->ct.label); + ovs_ct_get_labels(ct, &key->ct.labels); } /* Update 'key' based on skb->nfct. If 'post_ct' is true, then OVS has @@ -151,6 +151,8 @@ static void ovs_ct_update_key(const struct sk_buff *skb, ct = nf_ct_get(skb, &ctinfo); if (ct) { state = ovs_ct_get_state(ctinfo); + if (!nf_ct_is_confirmed(ct)) + state |= OVS_CS_F_NEW; if (ct->master) state |= OVS_CS_F_RELATED; zone = nf_ct_zone(ct); @@ -167,7 +169,7 @@ void ovs_ct_fill_key(const struct sk_buff *skb, struct sw_flow_key *key) int ovs_ct_put_key(const struct sw_flow_key *key, struct sk_buff *skb) { - if (nla_put_u8(skb, OVS_KEY_ATTR_CT_STATE, key->ct.state)) + if (nla_put_u32(skb, OVS_KEY_ATTR_CT_STATE, key->ct.state)) return -EMSGSIZE; if (IS_ENABLED(CONFIG_NF_CONNTRACK_ZONES) && @@ -179,8 +181,8 @@ int ovs_ct_put_key(const struct sw_flow_key *key, struct sk_buff *skb) return -EMSGSIZE; if (IS_ENABLED(CONFIG_NF_CONNTRACK_LABELS) && - nla_put(skb, OVS_KEY_ATTR_CT_LABEL, sizeof(key->ct.label), - &key->ct.label)) + nla_put(skb, OVS_KEY_ATTR_CT_LABELS, sizeof(key->ct.labels), + &key->ct.labels)) return -EMSGSIZE; return 0; @@ -213,18 +215,15 @@ static int ovs_ct_set_mark(struct sk_buff *skb, struct sw_flow_key *key, #endif } -static int ovs_ct_set_label(struct sk_buff *skb, struct sw_flow_key *key, - const struct ovs_key_ct_label *label, - const struct ovs_key_ct_label *mask) +static int ovs_ct_set_labels(struct sk_buff *skb, struct sw_flow_key *key, + const struct ovs_key_ct_labels *labels, + const struct ovs_key_ct_labels *mask) { enum ip_conntrack_info ctinfo; struct nf_conn_labels *cl; struct nf_conn *ct; int err; - if (!IS_ENABLED(CONFIG_NF_CONNTRACK_LABELS)) - return -ENOTSUPP; - /* The connection could be invalid, in which case set_label is no-op.*/ ct = nf_ct_get(skb, &ctinfo); if (!ct) @@ -235,15 +234,15 @@ static int ovs_ct_set_label(struct sk_buff *skb, struct sw_flow_key *key, nf_ct_labels_ext_add(ct); cl = nf_ct_labels_find(ct); } - if (!cl || cl->words * sizeof(long) < OVS_CT_LABEL_LEN) + if (!cl || cl->words * sizeof(long) < OVS_CT_LABELS_LEN) return -ENOSPC; - err = nf_connlabels_replace(ct, (u32 *)label, (u32 *)mask, - OVS_CT_LABEL_LEN / sizeof(u32)); + err = nf_connlabels_replace(ct, (u32 *)labels, (u32 *)mask, + OVS_CT_LABELS_LEN / sizeof(u32)); if (err) return err; - ovs_ct_get_label(ct, &key->ct.label); + ovs_ct_get_labels(ct, &key->ct.labels); return 0; } @@ -294,6 +293,9 @@ static int ovs_ct_helper(struct sk_buff *skb, u16 proto) return helper->help(skb, protoff, ct, ctinfo); } +/* Returns 0 on success, -EINPROGRESS if 'skb' is stolen, or other nonzero + * value if 'skb' is freed. + */ static int handle_fragments(struct net *net, struct sw_flow_key *key, u16 zone, struct sk_buff *skb) { @@ -309,8 +311,8 @@ static int handle_fragments(struct net *net, struct sw_flow_key *key, return err; ovs_cb.mru = IPCB(skb)->frag_max_size; - } else if (key->eth.type == htons(ETH_P_IPV6)) { #if IS_ENABLED(CONFIG_NF_DEFRAG_IPV6) + } else if (key->eth.type == htons(ETH_P_IPV6)) { enum ip6_defrag_users user = IP6_DEFRAG_CONNTRACK_IN + zone; struct sk_buff *reasm; @@ -319,17 +321,25 @@ static int handle_fragments(struct net *net, struct sw_flow_key *key, if (!reasm) return -EINPROGRESS; - if (skb == reasm) + if (skb == reasm) { + kfree_skb(skb); return -EINVAL; + } + + /* Don't free 'skb' even though it is one of the original + * fragments, as we're going to morph it into the head. + */ + skb_get(skb); + nf_ct_frag6_consume_orig(reasm); key->ip.proto = ipv6_hdr(reasm)->nexthdr; skb_morph(skb, reasm); + skb->next = reasm->next; consume_skb(reasm); ovs_cb.mru = IP6CB(skb)->frag_max_size; -#else - return -EPFNOSUPPORT; #endif } else { + kfree_skb(skb); return -EPFNOSUPPORT; } @@ -377,7 +387,7 @@ static bool skb_nfct_cached(const struct net *net, const struct sk_buff *skb, return true; } -static int __ovs_ct_lookup(struct net *net, const struct sw_flow_key *key, +static int __ovs_ct_lookup(struct net *net, struct sw_flow_key *key, const struct ovs_conntrack_info *info, struct sk_buff *skb) { @@ -408,6 +418,8 @@ static int __ovs_ct_lookup(struct net *net, const struct sw_flow_key *key, } } + ovs_ct_update_key(skb, key, true); + return 0; } @@ -430,8 +442,6 @@ static int ovs_ct_lookup(struct net *net, struct sw_flow_key *key, err = __ovs_ct_lookup(net, key, info, skb); if (err) return err; - - ovs_ct_update_key(skb, key, true); } return 0; @@ -460,22 +470,23 @@ static int ovs_ct_commit(struct net *net, struct sw_flow_key *key, if (nf_conntrack_confirm(skb) != NF_ACCEPT) return -EINVAL; - ovs_ct_update_key(skb, key, true); - return 0; } -static bool label_nonzero(const struct ovs_key_ct_label *label) +static bool labels_nonzero(const struct ovs_key_ct_labels *labels) { size_t i; - for (i = 0; i < sizeof(*label); i++) - if (label->ct_label[i]) + for (i = 0; i < sizeof(*labels); i++) + if (labels->ct_labels[i]) return true; return false; } +/* Returns 0 on success, -EINPROGRESS if 'skb' is stolen, or other nonzero + * value if 'skb' is freed. + */ int ovs_ct_execute(struct net *net, struct sk_buff *skb, struct sw_flow_key *key, const struct ovs_conntrack_info *info) @@ -493,7 +504,7 @@ int ovs_ct_execute(struct net *net, struct sk_buff *skb, return err; } - if (info->flags & OVS_CT_F_COMMIT) + if (info->commit) err = ovs_ct_commit(net, key, info, skb); else err = ovs_ct_lookup(net, key, info, skb); @@ -506,11 +517,13 @@ int ovs_ct_execute(struct net *net, struct sk_buff *skb, if (err) goto err; } - if (label_nonzero(&info->label.mask)) - err = ovs_ct_set_label(skb, key, &info->label.value, - &info->label.mask); + if (labels_nonzero(&info->labels.mask)) + err = ovs_ct_set_labels(skb, key, &info->labels.value, + &info->labels.mask); err: skb_push(skb, nh_ofs); + if (err) + kfree_skb(skb); return err; } @@ -539,14 +552,13 @@ static int ovs_ct_add_helper(struct ovs_conntrack_info *info, const char *name, } static const struct ovs_ct_len_tbl ovs_ct_attr_lens[OVS_CT_ATTR_MAX + 1] = { - [OVS_CT_ATTR_FLAGS] = { .minlen = sizeof(u32), - .maxlen = sizeof(u32) }, + [OVS_CT_ATTR_COMMIT] = { .minlen = 0, .maxlen = 0 }, [OVS_CT_ATTR_ZONE] = { .minlen = sizeof(u16), .maxlen = sizeof(u16) }, [OVS_CT_ATTR_MARK] = { .minlen = sizeof(struct md_mark), .maxlen = sizeof(struct md_mark) }, - [OVS_CT_ATTR_LABEL] = { .minlen = sizeof(struct md_label), - .maxlen = sizeof(struct md_label) }, + [OVS_CT_ATTR_LABELS] = { .minlen = sizeof(struct md_labels), + .maxlen = sizeof(struct md_labels) }, [OVS_CT_ATTR_HELPER] = { .minlen = 1, .maxlen = NF_CT_HELPER_NAME_LEN } }; @@ -576,8 +588,8 @@ static int parse_ct(const struct nlattr *attr, struct ovs_conntrack_info *info, } switch (type) { - case OVS_CT_ATTR_FLAGS: - info->flags = nla_get_u32(a); + case OVS_CT_ATTR_COMMIT: + info->commit = true; break; #ifdef CONFIG_NF_CONNTRACK_ZONES case OVS_CT_ATTR_ZONE: @@ -588,15 +600,23 @@ static int parse_ct(const struct nlattr *attr, struct ovs_conntrack_info *info, case OVS_CT_ATTR_MARK: { struct md_mark *mark = nla_data(a); + if (!mark->mask) { + OVS_NLERR(log, "ct_mark mask cannot be 0"); + return -EINVAL; + } info->mark = *mark; break; } #endif #ifdef CONFIG_NF_CONNTRACK_LABELS - case OVS_CT_ATTR_LABEL: { - struct md_label *label = nla_data(a); + case OVS_CT_ATTR_LABELS: { + struct md_labels *labels = nla_data(a); - info->label = *label; + if (!labels_nonzero(&labels->mask)) { + OVS_NLERR(log, "ct_labels mask cannot be 0"); + return -EINVAL; + } + info->labels = *labels; break; } #endif @@ -633,7 +653,7 @@ bool ovs_ct_verify(struct net *net, enum ovs_key_attr attr) attr == OVS_KEY_ATTR_CT_MARK) return true; if (IS_ENABLED(CONFIG_NF_CONNTRACK_LABELS) && - attr == OVS_KEY_ATTR_CT_LABEL) { + attr == OVS_KEY_ATTR_CT_LABELS) { struct ovs_net *ovs_net = net_generic(net, ovs_net_id); return ovs_net->xt_label; @@ -701,18 +721,19 @@ int ovs_ct_action_to_attr(const struct ovs_conntrack_info *ct_info, if (!start) return -EMSGSIZE; - if (nla_put_u32(skb, OVS_CT_ATTR_FLAGS, ct_info->flags)) + if (ct_info->commit && nla_put_flag(skb, OVS_CT_ATTR_COMMIT)) return -EMSGSIZE; if (IS_ENABLED(CONFIG_NF_CONNTRACK_ZONES) && nla_put_u16(skb, OVS_CT_ATTR_ZONE, ct_info->zone.id)) return -EMSGSIZE; - if (IS_ENABLED(CONFIG_NF_CONNTRACK_MARK) && + if (IS_ENABLED(CONFIG_NF_CONNTRACK_MARK) && ct_info->mark.mask && nla_put(skb, OVS_CT_ATTR_MARK, sizeof(ct_info->mark), &ct_info->mark)) return -EMSGSIZE; if (IS_ENABLED(CONFIG_NF_CONNTRACK_LABELS) && - nla_put(skb, OVS_CT_ATTR_LABEL, sizeof(ct_info->label), - &ct_info->label)) + labels_nonzero(&ct_info->labels.mask) && + nla_put(skb, OVS_CT_ATTR_LABELS, sizeof(ct_info->labels), + &ct_info->labels)) return -EMSGSIZE; if (ct_info->helper) { if (nla_put_string(skb, OVS_CT_ATTR_HELPER, @@ -737,7 +758,7 @@ void ovs_ct_free_action(const struct nlattr *a) void ovs_ct_init(struct net *net) { - unsigned int n_bits = sizeof(struct ovs_key_ct_label) * BITS_PER_BYTE; + unsigned int n_bits = sizeof(struct ovs_key_ct_labels) * BITS_PER_BYTE; struct ovs_net *ovs_net = net_generic(net, ovs_net_id); if (nf_connlabels_get(net, n_bits)) { diff --git a/net/openvswitch/conntrack.h b/net/openvswitch/conntrack.h index 43f5dd7a5577..a7544f405c16 100644 --- a/net/openvswitch/conntrack.h +++ b/net/openvswitch/conntrack.h @@ -34,6 +34,10 @@ int ovs_ct_execute(struct net *, struct sk_buff *, struct sw_flow_key *, void ovs_ct_fill_key(const struct sk_buff *skb, struct sw_flow_key *key); int ovs_ct_put_key(const struct sw_flow_key *key, struct sk_buff *skb); void ovs_ct_free_action(const struct nlattr *a); + +#define CT_SUPPORTED_MASK (OVS_CS_F_NEW | OVS_CS_F_ESTABLISHED | \ + OVS_CS_F_RELATED | OVS_CS_F_REPLY_DIR | \ + OVS_CS_F_INVALID | OVS_CS_F_TRACKED) #else #include <linux/errno.h> @@ -63,6 +67,7 @@ static inline int ovs_ct_execute(struct net *net, struct sk_buff *skb, struct sw_flow_key *key, const struct ovs_conntrack_info *info) { + kfree_skb(skb); return -ENOTSUPP; } @@ -72,7 +77,7 @@ static inline void ovs_ct_fill_key(const struct sk_buff *skb, key->ct.state = 0; key->ct.zone = 0; key->ct.mark = 0; - memset(&key->ct.label, 0, sizeof(key->ct.label)); + memset(&key->ct.labels, 0, sizeof(key->ct.labels)); } static inline int ovs_ct_put_key(const struct sw_flow_key *key, @@ -82,5 +87,7 @@ static inline int ovs_ct_put_key(const struct sw_flow_key *key, } static inline void ovs_ct_free_action(const struct nlattr *a) { } + +#define CT_SUPPORTED_MASK 0 #endif /* CONFIG_NF_CONNTRACK */ #endif /* ovs_conntrack.h */ diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c index b816ff871528..c5d08ee37730 100644 --- a/net/openvswitch/datapath.c +++ b/net/openvswitch/datapath.c @@ -490,9 +490,8 @@ static int queue_userspace_packet(struct datapath *dp, struct sk_buff *skb, if (upcall_info->egress_tun_info) { nla = nla_nest_start(user_skb, OVS_PACKET_ATTR_EGRESS_TUN_KEY); - err = ovs_nla_put_egress_tunnel_key(user_skb, - upcall_info->egress_tun_info, - upcall_info->egress_tun_opts); + err = ovs_nla_put_tunnel_info(user_skb, + upcall_info->egress_tun_info); BUG_ON(err); nla_nest_end(user_skb, nla); } diff --git a/net/openvswitch/datapath.h b/net/openvswitch/datapath.h index f88038a99f44..67bdecd9fdc1 100644 --- a/net/openvswitch/datapath.h +++ b/net/openvswitch/datapath.h @@ -117,7 +117,6 @@ struct ovs_skb_cb { */ struct dp_upcall_info { struct ip_tunnel_info *egress_tun_info; - const void *egress_tun_opts; const struct nlattr *userdata; const struct nlattr *actions; int actions_len; diff --git a/net/openvswitch/flow.h b/net/openvswitch/flow.h index fe527d2dd4b7..8cfa15a08668 100644 --- a/net/openvswitch/flow.h +++ b/net/openvswitch/flow.h @@ -116,7 +116,7 @@ struct sw_flow_key { u16 zone; u32 mark; u8 state; - struct ovs_key_ct_label label; + struct ovs_key_ct_labels labels; } ct; } __aligned(BITS_PER_LONG/8); /* Ensure that we can do comparisons as longs. */ diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c index 5c030a4d7338..38536c137c54 100644 --- a/net/openvswitch/flow_netlink.c +++ b/net/openvswitch/flow_netlink.c @@ -291,10 +291,10 @@ size_t ovs_key_attr_size(void) + nla_total_size(4) /* OVS_KEY_ATTR_SKB_MARK */ + nla_total_size(4) /* OVS_KEY_ATTR_DP_HASH */ + nla_total_size(4) /* OVS_KEY_ATTR_RECIRC_ID */ - + nla_total_size(1) /* OVS_KEY_ATTR_CT_STATE */ + + nla_total_size(4) /* OVS_KEY_ATTR_CT_STATE */ + nla_total_size(2) /* OVS_KEY_ATTR_CT_ZONE */ + nla_total_size(4) /* OVS_KEY_ATTR_CT_MARK */ - + nla_total_size(16) /* OVS_KEY_ATTR_CT_LABEL */ + + nla_total_size(16) /* OVS_KEY_ATTR_CT_LABELS */ + nla_total_size(12) /* OVS_KEY_ATTR_ETHERNET */ + nla_total_size(2) /* OVS_KEY_ATTR_ETHERTYPE */ + nla_total_size(4) /* OVS_KEY_ATTR_VLAN */ @@ -349,10 +349,10 @@ static const struct ovs_len_tbl ovs_key_lens[OVS_KEY_ATTR_MAX + 1] = { [OVS_KEY_ATTR_TUNNEL] = { .len = OVS_ATTR_NESTED, .next = ovs_tunnel_key_lens, }, [OVS_KEY_ATTR_MPLS] = { .len = sizeof(struct ovs_key_mpls) }, - [OVS_KEY_ATTR_CT_STATE] = { .len = sizeof(u8) }, + [OVS_KEY_ATTR_CT_STATE] = { .len = sizeof(u32) }, [OVS_KEY_ATTR_CT_ZONE] = { .len = sizeof(u16) }, [OVS_KEY_ATTR_CT_MARK] = { .len = sizeof(u32) }, - [OVS_KEY_ATTR_CT_LABEL] = { .len = sizeof(struct ovs_key_ct_label) }, + [OVS_KEY_ATTR_CT_LABELS] = { .len = sizeof(struct ovs_key_ct_labels) }, }; static bool check_attr_len(unsigned int attr_len, unsigned int expected_len) @@ -717,7 +717,7 @@ static int __ipv4_tun_to_nlattr(struct sk_buff *skb, if ((output->tun_flags & TUNNEL_OAM) && nla_put_flag(skb, OVS_TUNNEL_KEY_ATTR_OAM)) return -EMSGSIZE; - if (tun_opts) { + if (swkey_tun_opts_len) { if (output->tun_flags & TUNNEL_GENEVE_OPT && nla_put(skb, OVS_TUNNEL_KEY_ATTR_GENEVE_OPTS, swkey_tun_opts_len, tun_opts)) @@ -749,13 +749,12 @@ static int ipv4_tun_to_nlattr(struct sk_buff *skb, return 0; } -int ovs_nla_put_egress_tunnel_key(struct sk_buff *skb, - const struct ip_tunnel_info *egress_tun_info, - const void *egress_tun_opts) +int ovs_nla_put_tunnel_info(struct sk_buff *skb, + struct ip_tunnel_info *tun_info) { - return __ipv4_tun_to_nlattr(skb, &egress_tun_info->key, - egress_tun_opts, - egress_tun_info->options_len); + return __ipv4_tun_to_nlattr(skb, &tun_info->key, + ip_tunnel_info_opts(tun_info), + tun_info->options_len); } static int metadata_from_nlattrs(struct net *net, struct sw_flow_match *match, @@ -814,7 +813,13 @@ static int metadata_from_nlattrs(struct net *net, struct sw_flow_match *match, if (*attrs & (1 << OVS_KEY_ATTR_CT_STATE) && ovs_ct_verify(net, OVS_KEY_ATTR_CT_STATE)) { - u8 ct_state = nla_get_u8(a[OVS_KEY_ATTR_CT_STATE]); + u32 ct_state = nla_get_u32(a[OVS_KEY_ATTR_CT_STATE]); + + if (ct_state & ~CT_SUPPORTED_MASK) { + OVS_NLERR(log, "ct_state flags %08x unsupported", + ct_state); + return -EINVAL; + } SW_FLOW_KEY_PUT(match, ct.state, ct_state, is_mask); *attrs &= ~(1ULL << OVS_KEY_ATTR_CT_STATE); @@ -833,14 +838,14 @@ static int metadata_from_nlattrs(struct net *net, struct sw_flow_match *match, SW_FLOW_KEY_PUT(match, ct.mark, mark, is_mask); *attrs &= ~(1ULL << OVS_KEY_ATTR_CT_MARK); } - if (*attrs & (1 << OVS_KEY_ATTR_CT_LABEL) && - ovs_ct_verify(net, OVS_KEY_ATTR_CT_LABEL)) { - const struct ovs_key_ct_label *cl; + if (*attrs & (1 << OVS_KEY_ATTR_CT_LABELS) && + ovs_ct_verify(net, OVS_KEY_ATTR_CT_LABELS)) { + const struct ovs_key_ct_labels *cl; - cl = nla_data(a[OVS_KEY_ATTR_CT_LABEL]); - SW_FLOW_KEY_MEMCPY(match, ct.label, cl->ct_label, + cl = nla_data(a[OVS_KEY_ATTR_CT_LABELS]); + SW_FLOW_KEY_MEMCPY(match, ct.labels, cl->ct_labels, sizeof(*cl), is_mask); - *attrs &= ~(1ULL << OVS_KEY_ATTR_CT_LABEL); + *attrs &= ~(1ULL << OVS_KEY_ATTR_CT_LABELS); } return 0; } @@ -1093,6 +1098,9 @@ static void nlattr_set(struct nlattr *attr, u8 val, } else { memset(nla_data(nla), val, nla_len(nla)); } + + if (nla_type(nla) == OVS_KEY_ATTR_CT_STATE) + *(u32 *)nla_data(nla) &= CT_SUPPORTED_MASK; } } @@ -1973,7 +1981,7 @@ static int validate_set(const struct nlattr *a, case OVS_KEY_ATTR_PRIORITY: case OVS_KEY_ATTR_SKB_MARK: case OVS_KEY_ATTR_CT_MARK: - case OVS_KEY_ATTR_CT_LABEL: + case OVS_KEY_ATTR_CT_LABELS: case OVS_KEY_ATTR_ETHERNET: break; @@ -2374,10 +2382,7 @@ static int set_action_to_attr(const struct nlattr *a, struct sk_buff *skb) if (!start) return -EMSGSIZE; - err = ipv4_tun_to_nlattr(skb, &tun_info->key, - tun_info->options_len ? - ip_tunnel_info_opts(tun_info) : NULL, - tun_info->options_len); + err = ovs_nla_put_tunnel_info(skb, tun_info); if (err) return err; nla_nest_end(skb, start); diff --git a/net/openvswitch/flow_netlink.h b/net/openvswitch/flow_netlink.h index 6ca3f0baf449..47dd142eca1c 100644 --- a/net/openvswitch/flow_netlink.h +++ b/net/openvswitch/flow_netlink.h @@ -55,9 +55,9 @@ int ovs_nla_put_mask(const struct sw_flow *flow, struct sk_buff *skb); int ovs_nla_get_match(struct net *, struct sw_flow_match *, const struct nlattr *key, const struct nlattr *mask, bool log); -int ovs_nla_put_egress_tunnel_key(struct sk_buff *, - const struct ip_tunnel_info *, - const void *egress_tun_opts); + +int ovs_nla_put_tunnel_info(struct sk_buff *skb, + struct ip_tunnel_info *tun_info); bool ovs_nla_get_ufid(struct sw_flow_id *, const struct nlattr *, bool log); int ovs_nla_get_identifier(struct sw_flow_id *sfid, const struct nlattr *ufid, diff --git a/net/openvswitch/flow_table.c b/net/openvswitch/flow_table.c index f2ea83ba4763..c7f74aab34b9 100644 --- a/net/openvswitch/flow_table.c +++ b/net/openvswitch/flow_table.c @@ -93,7 +93,8 @@ struct sw_flow *ovs_flow_alloc(void) /* Initialize the default stat node. */ stats = kmem_cache_alloc_node(flow_stats_cache, - GFP_KERNEL | __GFP_ZERO, 0); + GFP_KERNEL | __GFP_ZERO, + node_online(0) ? 0 : NUMA_NO_NODE); if (!stats) goto err; diff --git a/net/openvswitch/vport-geneve.c b/net/openvswitch/vport-geneve.c index 2735e9c4a3b8..5f8aaaaa0785 100644 --- a/net/openvswitch/vport-geneve.c +++ b/net/openvswitch/vport-geneve.c @@ -52,18 +52,6 @@ static int geneve_get_options(const struct vport *vport, return 0; } -static int geneve_get_egress_tun_info(struct vport *vport, struct sk_buff *skb, - struct dp_upcall_info *upcall) -{ - struct geneve_port *geneve_port = geneve_vport(vport); - struct net *net = ovs_dp_get_net(vport->dp); - __be16 dport = htons(geneve_port->port_no); - __be16 sport = udp_flow_src_port(net, skb, 1, USHRT_MAX, true); - - return ovs_tunnel_get_egress_info(upcall, ovs_dp_get_net(vport->dp), - skb, IPPROTO_UDP, sport, dport); -} - static struct vport *geneve_tnl_create(const struct vport_parms *parms) { struct net *net = ovs_dp_get_net(parms->dp); @@ -130,7 +118,6 @@ static struct vport_ops ovs_geneve_vport_ops = { .get_options = geneve_get_options, .send = ovs_netdev_send, .owner = THIS_MODULE, - .get_egress_tun_info = geneve_get_egress_tun_info, }; static int __init ovs_geneve_tnl_init(void) diff --git a/net/openvswitch/vport-gre.c b/net/openvswitch/vport-gre.c index 4d24481669c9..64225bf5eb40 100644 --- a/net/openvswitch/vport-gre.c +++ b/net/openvswitch/vport-gre.c @@ -84,18 +84,10 @@ static struct vport *gre_create(const struct vport_parms *parms) return ovs_netdev_link(vport, parms->name); } -static int gre_get_egress_tun_info(struct vport *vport, struct sk_buff *skb, - struct dp_upcall_info *upcall) -{ - return ovs_tunnel_get_egress_info(upcall, ovs_dp_get_net(vport->dp), - skb, IPPROTO_GRE, 0, 0); -} - static struct vport_ops ovs_gre_vport_ops = { .type = OVS_VPORT_TYPE_GRE, .create = gre_create, .send = ovs_netdev_send, - .get_egress_tun_info = gre_get_egress_tun_info, .destroy = ovs_netdev_tunnel_destroy, .owner = THIS_MODULE, }; diff --git a/net/openvswitch/vport-internal_dev.c b/net/openvswitch/vport-internal_dev.c index 388b8a6bf112..b3934126daa8 100644 --- a/net/openvswitch/vport-internal_dev.c +++ b/net/openvswitch/vport-internal_dev.c @@ -106,12 +106,45 @@ static void internal_dev_destructor(struct net_device *dev) free_netdev(dev); } +static struct rtnl_link_stats64 * +internal_get_stats(struct net_device *dev, struct rtnl_link_stats64 *stats) +{ + int i; + + memset(stats, 0, sizeof(*stats)); + stats->rx_errors = dev->stats.rx_errors; + stats->tx_errors = dev->stats.tx_errors; + stats->tx_dropped = dev->stats.tx_dropped; + stats->rx_dropped = dev->stats.rx_dropped; + + for_each_possible_cpu(i) { + const struct pcpu_sw_netstats *percpu_stats; + struct pcpu_sw_netstats local_stats; + unsigned int start; + + percpu_stats = per_cpu_ptr(dev->tstats, i); + + do { + start = u64_stats_fetch_begin_irq(&percpu_stats->syncp); + local_stats = *percpu_stats; + } while (u64_stats_fetch_retry_irq(&percpu_stats->syncp, start)); + + stats->rx_bytes += local_stats.rx_bytes; + stats->rx_packets += local_stats.rx_packets; + stats->tx_bytes += local_stats.tx_bytes; + stats->tx_packets += local_stats.tx_packets; + } + + return stats; +} + static const struct net_device_ops internal_dev_netdev_ops = { .ndo_open = internal_dev_open, .ndo_stop = internal_dev_stop, .ndo_start_xmit = internal_dev_xmit, .ndo_set_mac_address = eth_mac_addr, .ndo_change_mtu = internal_dev_change_mtu, + .ndo_get_stats64 = internal_get_stats, }; static struct rtnl_link_ops internal_dev_link_ops __read_mostly = { @@ -161,6 +194,11 @@ static struct vport *internal_dev_create(const struct vport_parms *parms) err = -ENOMEM; goto error_free_vport; } + vport->dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats); + if (!vport->dev->tstats) { + err = -ENOMEM; + goto error_free_netdev; + } dev_net_set(vport->dev, ovs_dp_get_net(vport->dp)); internal_dev = internal_dev_priv(vport->dev); @@ -173,7 +211,7 @@ static struct vport *internal_dev_create(const struct vport_parms *parms) rtnl_lock(); err = register_netdevice(vport->dev); if (err) - goto error_free_netdev; + goto error_unlock; dev_set_promiscuity(vport->dev, 1); rtnl_unlock(); @@ -181,8 +219,10 @@ static struct vport *internal_dev_create(const struct vport_parms *parms) return vport; -error_free_netdev: +error_unlock: rtnl_unlock(); + free_percpu(vport->dev->tstats); +error_free_netdev: free_netdev(vport->dev); error_free_vport: ovs_vport_free(vport); @@ -198,7 +238,7 @@ static void internal_dev_destroy(struct vport *vport) /* unregister_netdevice() waits for an RCU grace period. */ unregister_netdevice(vport->dev); - + free_percpu(vport->dev->tstats); rtnl_unlock(); } diff --git a/net/openvswitch/vport-vxlan.c b/net/openvswitch/vport-vxlan.c index c11413d5075f..e1c9c0888037 100644 --- a/net/openvswitch/vport-vxlan.c +++ b/net/openvswitch/vport-vxlan.c @@ -146,31 +146,12 @@ static struct vport *vxlan_create(const struct vport_parms *parms) return ovs_netdev_link(vport, parms->name); } -static int vxlan_get_egress_tun_info(struct vport *vport, struct sk_buff *skb, - struct dp_upcall_info *upcall) -{ - struct vxlan_dev *vxlan = netdev_priv(vport->dev); - struct net *net = ovs_dp_get_net(vport->dp); - __be16 dst_port = vxlan_dev_dst_port(vxlan); - __be16 src_port; - int port_min; - int port_max; - - inet_get_local_port_range(net, &port_min, &port_max); - src_port = udp_flow_src_port(net, skb, 0, 0, true); - - return ovs_tunnel_get_egress_info(upcall, net, - skb, IPPROTO_UDP, - src_port, dst_port); -} - static struct vport_ops ovs_vxlan_netdev_vport_ops = { .type = OVS_VPORT_TYPE_VXLAN, .create = vxlan_create, .destroy = ovs_netdev_tunnel_destroy, .get_options = vxlan_get_options, .send = ovs_netdev_send, - .get_egress_tun_info = vxlan_get_egress_tun_info, }; static int __init ovs_vxlan_tnl_init(void) diff --git a/net/openvswitch/vport.c b/net/openvswitch/vport.c index dc81dc619aa2..320c765ce44a 100644 --- a/net/openvswitch/vport.c +++ b/net/openvswitch/vport.c @@ -280,35 +280,19 @@ void ovs_vport_del(struct vport *vport) */ void ovs_vport_get_stats(struct vport *vport, struct ovs_vport_stats *stats) { - struct net_device *dev = vport->dev; - int i; - - memset(stats, 0, sizeof(*stats)); - stats->rx_errors = dev->stats.rx_errors; - stats->tx_errors = dev->stats.tx_errors; - stats->tx_dropped = dev->stats.tx_dropped; - stats->rx_dropped = dev->stats.rx_dropped; - - stats->rx_dropped += atomic_long_read(&dev->rx_dropped); - stats->tx_dropped += atomic_long_read(&dev->tx_dropped); - - for_each_possible_cpu(i) { - const struct pcpu_sw_netstats *percpu_stats; - struct pcpu_sw_netstats local_stats; - unsigned int start; - - percpu_stats = per_cpu_ptr(dev->tstats, i); - - do { - start = u64_stats_fetch_begin_irq(&percpu_stats->syncp); - local_stats = *percpu_stats; - } while (u64_stats_fetch_retry_irq(&percpu_stats->syncp, start)); - - stats->rx_bytes += local_stats.rx_bytes; - stats->rx_packets += local_stats.rx_packets; - stats->tx_bytes += local_stats.tx_bytes; - stats->tx_packets += local_stats.tx_packets; - } + const struct rtnl_link_stats64 *dev_stats; + struct rtnl_link_stats64 temp; + + dev_stats = dev_get_stats(vport->dev, &temp); + stats->rx_errors = dev_stats->rx_errors; + stats->tx_errors = dev_stats->tx_errors; + stats->tx_dropped = dev_stats->tx_dropped; + stats->rx_dropped = dev_stats->rx_dropped; + + stats->rx_bytes = dev_stats->rx_bytes; + stats->rx_packets = dev_stats->rx_packets; + stats->tx_bytes = dev_stats->tx_bytes; + stats->tx_packets = dev_stats->tx_packets; } /** @@ -460,6 +444,15 @@ int ovs_vport_receive(struct vport *vport, struct sk_buff *skb, OVS_CB(skb)->input_vport = vport; OVS_CB(skb)->mru = 0; + if (unlikely(dev_net(skb->dev) != ovs_dp_get_net(vport->dp))) { + u32 mark; + + mark = skb->mark; + skb_scrub_packet(skb, true); + skb->mark = mark; + tun_info = NULL; + } + /* Extract flow from 'skb' into 'key'. */ error = ovs_flow_key_extract(tun_info, skb, &key); if (unlikely(error)) { @@ -486,61 +479,3 @@ void ovs_vport_deferred_free(struct vport *vport) call_rcu(&vport->rcu, free_vport_rcu); } EXPORT_SYMBOL_GPL(ovs_vport_deferred_free); - -int ovs_tunnel_get_egress_info(struct dp_upcall_info *upcall, - struct net *net, - struct sk_buff *skb, - u8 ipproto, - __be16 tp_src, - __be16 tp_dst) -{ - struct ip_tunnel_info *egress_tun_info = upcall->egress_tun_info; - const struct ip_tunnel_info *tun_info = skb_tunnel_info(skb); - const struct ip_tunnel_key *tun_key; - u32 skb_mark = skb->mark; - struct rtable *rt; - struct flowi4 fl; - - if (unlikely(!tun_info)) - return -EINVAL; - if (ip_tunnel_info_af(tun_info) != AF_INET) - return -EINVAL; - - tun_key = &tun_info->key; - - /* Route lookup to get srouce IP address. - * The process may need to be changed if the corresponding process - * in vports ops changed. - */ - rt = ovs_tunnel_route_lookup(net, tun_key, skb_mark, &fl, ipproto); - if (IS_ERR(rt)) - return PTR_ERR(rt); - - ip_rt_put(rt); - - /* Generate egress_tun_info based on tun_info, - * saddr, tp_src and tp_dst - */ - ip_tunnel_key_init(&egress_tun_info->key, - fl.saddr, tun_key->u.ipv4.dst, - tun_key->tos, - tun_key->ttl, - tp_src, tp_dst, - tun_key->tun_id, - tun_key->tun_flags); - egress_tun_info->options_len = tun_info->options_len; - egress_tun_info->mode = tun_info->mode; - upcall->egress_tun_opts = ip_tunnel_info_opts(egress_tun_info); - return 0; -} -EXPORT_SYMBOL_GPL(ovs_tunnel_get_egress_info); - -int ovs_vport_get_egress_tun_info(struct vport *vport, struct sk_buff *skb, - struct dp_upcall_info *upcall) -{ - /* get_egress_tun_info() is only implemented on tunnel ports. */ - if (unlikely(!vport->ops->get_egress_tun_info)) - return -EINVAL; - - return vport->ops->get_egress_tun_info(vport, skb, upcall); -} diff --git a/net/openvswitch/vport.h b/net/openvswitch/vport.h index a413f3ae6a7b..d341ad6f3afe 100644 --- a/net/openvswitch/vport.h +++ b/net/openvswitch/vport.h @@ -27,7 +27,6 @@ #include <linux/skbuff.h> #include <linux/spinlock.h> #include <linux/u64_stats_sync.h> -#include <net/route.h> #include "datapath.h" @@ -53,16 +52,6 @@ int ovs_vport_set_upcall_portids(struct vport *, const struct nlattr *pids); int ovs_vport_get_upcall_portids(const struct vport *, struct sk_buff *); u32 ovs_vport_find_upcall_portid(const struct vport *, struct sk_buff *); -int ovs_tunnel_get_egress_info(struct dp_upcall_info *upcall, - struct net *net, - struct sk_buff *, - u8 ipproto, - __be16 tp_src, - __be16 tp_dst); - -int ovs_vport_get_egress_tun_info(struct vport *vport, struct sk_buff *skb, - struct dp_upcall_info *upcall); - /** * struct vport_portids - array of netlink portids of a vport. * must be protected by rcu. @@ -140,8 +129,6 @@ struct vport_parms { * have any configuration. * @send: Send a packet on the device. * zero for dropped packets or negative for error. - * @get_egress_tun_info: Get the egress tunnel 5-tuple and other info for - * a packet. */ struct vport_ops { enum ovs_vport_type type; @@ -154,9 +141,6 @@ struct vport_ops { int (*get_options)(const struct vport *, struct sk_buff *); void (*send)(struct vport *, struct sk_buff *); - int (*get_egress_tun_info)(struct vport *, struct sk_buff *, - struct dp_upcall_info *upcall); - struct module *owner; struct list_head list; }; @@ -215,25 +199,6 @@ static inline const char *ovs_vport_name(struct vport *vport) int ovs_vport_ops_register(struct vport_ops *ops); void ovs_vport_ops_unregister(struct vport_ops *ops); -static inline struct rtable *ovs_tunnel_route_lookup(struct net *net, - const struct ip_tunnel_key *key, - u32 mark, - struct flowi4 *fl, - u8 protocol) -{ - struct rtable *rt; - - memset(fl, 0, sizeof(*fl)); - fl->daddr = key->u.ipv4.dst; - fl->saddr = key->u.ipv4.src; - fl->flowi4_tos = RT_TOS(key->tos); - fl->flowi4_mark = mark; - fl->flowi4_proto = protocol; - - rt = ip_route_output_key(net, fl); - return rt; -} - static inline void ovs_vport_send(struct vport *vport, struct sk_buff *skb) { vport->ops->send(vport, skb); diff --git a/net/rds/tcp_recv.c b/net/rds/tcp_recv.c index fbc5ef88bc0e..27a992154804 100644 --- a/net/rds/tcp_recv.c +++ b/net/rds/tcp_recv.c @@ -214,8 +214,15 @@ static int rds_tcp_data_recv(read_descriptor_t *desc, struct sk_buff *skb, } to_copy = min(tc->t_tinc_data_rem, left); - pskb_pull(clone, offset); - pskb_trim(clone, to_copy); + if (!pskb_pull(clone, offset) || + pskb_trim(clone, to_copy)) { + pr_warn("rds_tcp_data_recv: pull/trim failed " + "left %zu data_rem %zu skb_len %d\n", + left, tc->t_tinc_data_rem, skb->len); + kfree_skb(clone); + desc->error = -ENOMEM; + goto out; + } skb_queue_tail(&tinc->ti_skb_list, clone); rdsdebug("skb %p data %p len %d off %u to_copy %zu -> " diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c index 2d1be4a760fd..32fcdecdb9e2 100644 --- a/net/sched/act_mirred.c +++ b/net/sched/act_mirred.c @@ -31,13 +31,17 @@ #define MIRRED_TAB_MASK 7 static LIST_HEAD(mirred_list); +static DEFINE_SPINLOCK(mirred_list_lock); static void tcf_mirred_release(struct tc_action *a, int bind) { struct tcf_mirred *m = to_mirred(a); struct net_device *dev = rcu_dereference_protected(m->tcfm_dev, 1); + /* We could be called either in a RCU callback or with RTNL lock held. */ + spin_lock_bh(&mirred_list_lock); list_del(&m->tcfm_list); + spin_unlock_bh(&mirred_list_lock); if (dev) dev_put(dev); } @@ -103,10 +107,10 @@ static int tcf_mirred_init(struct net *net, struct nlattr *nla, } else { if (bind) return 0; - if (!ovr) { - tcf_hash_release(a, bind); + + tcf_hash_release(a, bind); + if (!ovr) return -EEXIST; - } } m = to_mirred(a); @@ -123,7 +127,9 @@ static int tcf_mirred_init(struct net *net, struct nlattr *nla, } if (ret == ACT_P_CREATED) { + spin_lock_bh(&mirred_list_lock); list_add(&m->tcfm_list, &mirred_list); + spin_unlock_bh(&mirred_list_lock); tcf_hash_insert(a); } @@ -173,6 +179,7 @@ static int tcf_mirred(struct sk_buff *skb, const struct tc_action *a, skb2->skb_iif = skb->dev->ifindex; skb2->dev = dev; + skb_sender_cpu_clear(skb2); err = dev_queue_xmit(skb2); if (err) { @@ -221,7 +228,8 @@ static int mirred_device_event(struct notifier_block *unused, struct tcf_mirred *m; ASSERT_RTNL(); - if (event == NETDEV_UNREGISTER) + if (event == NETDEV_UNREGISTER) { + spin_lock_bh(&mirred_list_lock); list_for_each_entry(m, &mirred_list, tcfm_list) { if (rcu_access_pointer(m->tcfm_dev) == dev) { dev_put(dev); @@ -231,6 +239,8 @@ static int mirred_device_event(struct notifier_block *unused, RCU_INIT_POINTER(m->tcfm_dev, NULL); } } + spin_unlock_bh(&mirred_list_lock); + } return NOTIFY_DONE; } diff --git a/net/sched/sch_hhf.c b/net/sched/sch_hhf.c index 9d15cb6b8cb1..86b04e31e60b 100644 --- a/net/sched/sch_hhf.c +++ b/net/sched/sch_hhf.c @@ -368,6 +368,15 @@ static unsigned int hhf_drop(struct Qdisc *sch) return bucket - q->buckets; } +static unsigned int hhf_qdisc_drop(struct Qdisc *sch) +{ + unsigned int prev_backlog; + + prev_backlog = sch->qstats.backlog; + hhf_drop(sch); + return prev_backlog - sch->qstats.backlog; +} + static int hhf_enqueue(struct sk_buff *skb, struct Qdisc *sch) { struct hhf_sched_data *q = qdisc_priv(sch); @@ -696,7 +705,7 @@ static struct Qdisc_ops hhf_qdisc_ops __read_mostly = { .enqueue = hhf_enqueue, .dequeue = hhf_dequeue, .peek = qdisc_peek_dequeued, - .drop = hhf_drop, + .drop = hhf_qdisc_drop, .init = hhf_init, .reset = hhf_reset, .destroy = hhf_destroy, diff --git a/net/switchdev/switchdev.c b/net/switchdev/switchdev.c index fda38f830a10..77f5d17e2612 100644 --- a/net/switchdev/switchdev.c +++ b/net/switchdev/switchdev.c @@ -16,6 +16,7 @@ #include <linux/notifier.h> #include <linux/netdevice.h> #include <linux/if_bridge.h> +#include <linux/if_vlan.h> #include <net/ip_fib.h> #include <net/switchdev.h> @@ -634,6 +635,8 @@ static int switchdev_port_br_afspec(struct net_device *dev, if (nla_len(attr) != sizeof(struct bridge_vlan_info)) return -EINVAL; vinfo = nla_data(attr); + if (!vinfo->vid || vinfo->vid >= VLAN_VID_MASK) + return -EINVAL; vlan->flags = vinfo->flags; if (vinfo->flags & BRIDGE_VLAN_INFO_RANGE_BEGIN) { if (vlan->vid_begin) diff --git a/net/sysctl_net.c b/net/sysctl_net.c index e7000be321b0..ed98c1fc3de1 100644 --- a/net/sysctl_net.c +++ b/net/sysctl_net.c @@ -94,10 +94,14 @@ __init int net_sysctl_init(void) goto out; ret = register_pernet_subsys(&sysctl_pernet_ops); if (ret) - goto out; + goto out1; register_sysctl_root(&net_sysctl_root); out: return ret; +out1: + unregister_sysctl_table(net_header); + net_header = NULL; + goto out; } struct ctl_table_header *register_net_sysctl(struct net *net, diff --git a/net/tipc/bcast.c b/net/tipc/bcast.c index 41042de3ae9b..eadba62afa85 100644 --- a/net/tipc/bcast.c +++ b/net/tipc/bcast.c @@ -42,7 +42,8 @@ #include "core.h" #define MAX_PKT_DEFAULT_MCAST 1500 /* bcast link max packet size (fixed) */ -#define BCLINK_WIN_DEFAULT 20 /* bcast link window size (default) */ +#define BCLINK_WIN_DEFAULT 50 /* bcast link window size (default) */ +#define BCLINK_WIN_MIN 32 /* bcast minimum link window size */ const char tipc_bclink_name[] = "broadcast-link"; @@ -908,9 +909,10 @@ int tipc_bclink_set_queue_limits(struct net *net, u32 limit) if (!bcl) return -ENOPROTOOPT; - if ((limit < TIPC_MIN_LINK_WIN) || (limit > TIPC_MAX_LINK_WIN)) + if (limit < BCLINK_WIN_MIN) + limit = BCLINK_WIN_MIN; + if (limit > TIPC_MAX_LINK_WIN) return -EINVAL; - tipc_bclink_lock(net); tipc_link_set_queue_limits(bcl, limit); tipc_bclink_unlock(net); diff --git a/net/tipc/msg.c b/net/tipc/msg.c index c5ac436235e0..5f73450159df 100644 --- a/net/tipc/msg.c +++ b/net/tipc/msg.c @@ -121,7 +121,7 @@ int tipc_buf_append(struct sk_buff **headbuf, struct sk_buff **buf) { struct sk_buff *head = *headbuf; struct sk_buff *frag = *buf; - struct sk_buff *tail; + struct sk_buff *tail = NULL; struct tipc_msg *msg; u32 fragid; int delta; @@ -141,9 +141,15 @@ int tipc_buf_append(struct sk_buff **headbuf, struct sk_buff **buf) if (unlikely(skb_unclone(frag, GFP_ATOMIC))) goto err; head = *headbuf = frag; - skb_frag_list_init(head); - TIPC_SKB_CB(head)->tail = NULL; *buf = NULL; + TIPC_SKB_CB(head)->tail = NULL; + if (skb_is_nonlinear(head)) { + skb_walk_frags(head, tail) { + TIPC_SKB_CB(head)->tail = tail; + } + } else { + skb_frag_list_init(head); + } return 0; } diff --git a/net/tipc/msg.h b/net/tipc/msg.h index a82c5848d4bc..5351a3f97e8e 100644 --- a/net/tipc/msg.h +++ b/net/tipc/msg.h @@ -357,7 +357,7 @@ static inline u32 msg_importance(struct tipc_msg *m) if (likely((usr <= TIPC_CRITICAL_IMPORTANCE) && !msg_errcode(m))) return usr; if ((usr == MSG_FRAGMENTER) || (usr == MSG_BUNDLER)) - return msg_bits(m, 5, 13, 0x7); + return msg_bits(m, 9, 0, 0x7); return TIPC_SYSTEM_IMPORTANCE; } @@ -366,7 +366,7 @@ static inline void msg_set_importance(struct tipc_msg *m, u32 i) int usr = msg_user(m); if (likely((usr == MSG_FRAGMENTER) || (usr == MSG_BUNDLER))) - msg_set_bits(m, 5, 13, 0x7, i); + msg_set_bits(m, 9, 0, 0x7, i); else if (i < TIPC_SYSTEM_IMPORTANCE) msg_set_user(m, i); else diff --git a/net/tipc/node.c b/net/tipc/node.c index 703875fd6cde..2c32a83037a3 100644 --- a/net/tipc/node.c +++ b/net/tipc/node.c @@ -1116,7 +1116,7 @@ static bool tipc_node_check_state(struct tipc_node *n, struct sk_buff *skb, } /* Ignore duplicate packets */ - if (less(oseqno, rcv_nxt)) + if ((usr != LINK_PROTOCOL) && less(oseqno, rcv_nxt)) return true; /* Initiate or update failover mode if applicable */ @@ -1146,8 +1146,8 @@ static bool tipc_node_check_state(struct tipc_node *n, struct sk_buff *skb, if (!pl || !tipc_link_is_up(pl)) return true; - /* Initiate or update synch mode if applicable */ - if ((usr == TUNNEL_PROTOCOL) && (mtyp == SYNCH_MSG)) { + /* Initiate synch mode if applicable */ + if ((usr == TUNNEL_PROTOCOL) && (mtyp == SYNCH_MSG) && (oseqno == 1)) { syncpt = iseqno + exp_pkts - 1; if (!tipc_link_is_up(l)) { tipc_link_fsm_evt(l, LINK_ESTABLISH_EVT); diff --git a/net/tipc/udp_media.c b/net/tipc/udp_media.c index c170d3138953..6e648d90297a 100644 --- a/net/tipc/udp_media.c +++ b/net/tipc/udp_media.c @@ -52,6 +52,8 @@ /* IANA assigned UDP port */ #define UDP_PORT_DEFAULT 6118 +#define UDP_MIN_HEADROOM 28 + static const struct nla_policy tipc_nl_udp_policy[TIPC_NLA_UDP_MAX + 1] = { [TIPC_NLA_UDP_UNSPEC] = {.type = NLA_UNSPEC}, [TIPC_NLA_UDP_LOCAL] = {.type = NLA_BINARY, @@ -156,6 +158,9 @@ static int tipc_udp_send_msg(struct net *net, struct sk_buff *skb, struct sk_buff *clone; struct rtable *rt; + if (skb_headroom(skb) < UDP_MIN_HEADROOM) + pskb_expand_head(skb, UDP_MIN_HEADROOM, 0, GFP_ATOMIC); + clone = skb_clone(skb, GFP_ATOMIC); skb_set_inner_protocol(clone, htons(ETH_P_TIPC)); ub = rcu_dereference_rtnl(b->media_ptr); diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index ef31b40ad550..94f658235fb4 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -2064,6 +2064,11 @@ static int unix_stream_read_generic(struct unix_stream_read_state *state) goto out; } + if (flags & MSG_PEEK) + skip = sk_peek_offset(sk, flags); + else + skip = 0; + do { int chunk; struct sk_buff *skb, *last; @@ -2112,7 +2117,6 @@ unlock: break; } - skip = sk_peek_offset(sk, flags); while (skip >= unix_skb_len(skb)) { skip -= unix_skb_len(skb); last = skb; @@ -2179,14 +2183,12 @@ unlock: if (UNIXCB(skb).fp) scm.fp = scm_fp_dup(UNIXCB(skb).fp); - if (skip) { - sk_peek_offset_fwd(sk, chunk); - skip -= chunk; - } + sk_peek_offset_fwd(sk, chunk); if (UNIXCB(skb).fp) break; + skip = 0; last = skb; last_len = skb->len; unix_state_lock(sk); diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c index df5fc6b340f1..00e8a349aabc 100644 --- a/net/vmw_vsock/af_vsock.c +++ b/net/vmw_vsock/af_vsock.c @@ -1948,13 +1948,13 @@ int __vsock_core_init(const struct vsock_transport *t, struct module *owner) err = misc_register(&vsock_device); if (err) { pr_err("Failed to register misc device\n"); - return -ENOENT; + goto err_reset_transport; } err = proto_register(&vsock_proto, 1); /* we want our slab */ if (err) { pr_err("Cannot register vsock protocol\n"); - goto err_misc_deregister; + goto err_deregister_misc; } err = sock_register(&vsock_family_ops); @@ -1969,8 +1969,9 @@ int __vsock_core_init(const struct vsock_transport *t, struct module *owner) err_unregister_proto: proto_unregister(&vsock_proto); -err_misc_deregister: +err_deregister_misc: misc_deregister(&vsock_device); +err_reset_transport: transport = NULL; err_busy: mutex_unlock(&vsock_register_mutex); diff --git a/net/vmw_vsock/vmci_transport.c b/net/vmw_vsock/vmci_transport.c index 1f63daff3965..7555cad83a75 100644 --- a/net/vmw_vsock/vmci_transport.c +++ b/net/vmw_vsock/vmci_transport.c @@ -40,13 +40,11 @@ static int vmci_transport_recv_dgram_cb(void *data, struct vmci_datagram *dg); static int vmci_transport_recv_stream_cb(void *data, struct vmci_datagram *dg); -static void vmci_transport_peer_attach_cb(u32 sub_id, - const struct vmci_event_data *ed, - void *client_data); static void vmci_transport_peer_detach_cb(u32 sub_id, const struct vmci_event_data *ed, void *client_data); static void vmci_transport_recv_pkt_work(struct work_struct *work); +static void vmci_transport_cleanup(struct work_struct *work); static int vmci_transport_recv_listen(struct sock *sk, struct vmci_transport_packet *pkt); static int vmci_transport_recv_connecting_server( @@ -75,6 +73,10 @@ struct vmci_transport_recv_pkt_info { struct vmci_transport_packet pkt; }; +static LIST_HEAD(vmci_transport_cleanup_list); +static DEFINE_SPINLOCK(vmci_transport_cleanup_lock); +static DECLARE_WORK(vmci_transport_cleanup_work, vmci_transport_cleanup); + static struct vmci_handle vmci_transport_stream_handle = { VMCI_INVALID_ID, VMCI_INVALID_ID }; static u32 vmci_transport_qp_resumed_sub_id = VMCI_INVALID_ID; @@ -791,44 +793,6 @@ out: return err; } -static void vmci_transport_peer_attach_cb(u32 sub_id, - const struct vmci_event_data *e_data, - void *client_data) -{ - struct sock *sk = client_data; - const struct vmci_event_payload_qp *e_payload; - struct vsock_sock *vsk; - - e_payload = vmci_event_data_const_payload(e_data); - - vsk = vsock_sk(sk); - - /* We don't ask for delayed CBs when we subscribe to this event (we - * pass 0 as flags to vmci_event_subscribe()). VMCI makes no - * guarantees in that case about what context we might be running in, - * so it could be BH or process, blockable or non-blockable. So we - * need to account for all possible contexts here. - */ - local_bh_disable(); - bh_lock_sock(sk); - - /* XXX This is lame, we should provide a way to lookup sockets by - * qp_handle. - */ - if (vmci_handle_is_equal(vmci_trans(vsk)->qp_handle, - e_payload->handle)) { - /* XXX This doesn't do anything, but in the future we may want - * to set a flag here to verify the attach really did occur and - * we weren't just sent a datagram claiming it was. - */ - goto out; - } - -out: - bh_unlock_sock(sk); - local_bh_enable(); -} - static void vmci_transport_handle_detach(struct sock *sk) { struct vsock_sock *vsk; @@ -871,28 +835,38 @@ static void vmci_transport_peer_detach_cb(u32 sub_id, const struct vmci_event_data *e_data, void *client_data) { - struct sock *sk = client_data; + struct vmci_transport *trans = client_data; const struct vmci_event_payload_qp *e_payload; - struct vsock_sock *vsk; e_payload = vmci_event_data_const_payload(e_data); - vsk = vsock_sk(sk); - if (vmci_handle_is_invalid(e_payload->handle)) - return; - - /* Same rules for locking as for peer_attach_cb(). */ - local_bh_disable(); - bh_lock_sock(sk); /* XXX This is lame, we should provide a way to lookup sockets by * qp_handle. */ - if (vmci_handle_is_equal(vmci_trans(vsk)->qp_handle, - e_payload->handle)) - vmci_transport_handle_detach(sk); + if (vmci_handle_is_invalid(e_payload->handle) || + vmci_handle_is_equal(trans->qp_handle, e_payload->handle)) + return; - bh_unlock_sock(sk); - local_bh_enable(); + /* We don't ask for delayed CBs when we subscribe to this event (we + * pass 0 as flags to vmci_event_subscribe()). VMCI makes no + * guarantees in that case about what context we might be running in, + * so it could be BH or process, blockable or non-blockable. So we + * need to account for all possible contexts here. + */ + spin_lock_bh(&trans->lock); + if (!trans->sk) + goto out; + + /* Apart from here, trans->lock is only grabbed as part of sk destruct, + * where trans->sk isn't locked. + */ + bh_lock_sock(trans->sk); + + vmci_transport_handle_detach(trans->sk); + + bh_unlock_sock(trans->sk); + out: + spin_unlock_bh(&trans->lock); } static void vmci_transport_qp_resumed_cb(u32 sub_id, @@ -1181,7 +1155,7 @@ vmci_transport_recv_connecting_server(struct sock *listener, */ err = vmci_event_subscribe(VMCI_EVENT_QP_PEER_DETACH, vmci_transport_peer_detach_cb, - pending, &detach_sub_id); + vmci_trans(vpending), &detach_sub_id); if (err < VMCI_SUCCESS) { vmci_transport_send_reset(pending, pkt); err = vmci_transport_error_to_vsock_error(err); @@ -1321,7 +1295,6 @@ vmci_transport_recv_connecting_client(struct sock *sk, || vmci_trans(vsk)->qpair || vmci_trans(vsk)->produce_size != 0 || vmci_trans(vsk)->consume_size != 0 - || vmci_trans(vsk)->attach_sub_id != VMCI_INVALID_ID || vmci_trans(vsk)->detach_sub_id != VMCI_INVALID_ID) { skerr = EPROTO; err = -EINVAL; @@ -1389,7 +1362,6 @@ static int vmci_transport_recv_connecting_client_negotiate( struct vsock_sock *vsk; struct vmci_handle handle; struct vmci_qp *qpair; - u32 attach_sub_id; u32 detach_sub_id; bool is_local; u32 flags; @@ -1399,7 +1371,6 @@ static int vmci_transport_recv_connecting_client_negotiate( vsk = vsock_sk(sk); handle = VMCI_INVALID_HANDLE; - attach_sub_id = VMCI_INVALID_ID; detach_sub_id = VMCI_INVALID_ID; /* If we have gotten here then we should be past the point where old @@ -1444,23 +1415,15 @@ static int vmci_transport_recv_connecting_client_negotiate( goto destroy; } - /* Subscribe to attach and detach events first. + /* Subscribe to detach events first. * * XXX We attach once for each queue pair created for now so it is easy * to find the socket (it's provided), but later we should only * subscribe once and add a way to lookup sockets by queue pair handle. */ - err = vmci_event_subscribe(VMCI_EVENT_QP_PEER_ATTACH, - vmci_transport_peer_attach_cb, - sk, &attach_sub_id); - if (err < VMCI_SUCCESS) { - err = vmci_transport_error_to_vsock_error(err); - goto destroy; - } - err = vmci_event_subscribe(VMCI_EVENT_QP_PEER_DETACH, vmci_transport_peer_detach_cb, - sk, &detach_sub_id); + vmci_trans(vsk), &detach_sub_id); if (err < VMCI_SUCCESS) { err = vmci_transport_error_to_vsock_error(err); goto destroy; @@ -1496,7 +1459,6 @@ static int vmci_transport_recv_connecting_client_negotiate( vmci_trans(vsk)->produce_size = vmci_trans(vsk)->consume_size = pkt->u.size; - vmci_trans(vsk)->attach_sub_id = attach_sub_id; vmci_trans(vsk)->detach_sub_id = detach_sub_id; vmci_trans(vsk)->notify_ops->process_negotiate(sk); @@ -1504,9 +1466,6 @@ static int vmci_transport_recv_connecting_client_negotiate( return 0; destroy: - if (attach_sub_id != VMCI_INVALID_ID) - vmci_event_unsubscribe(attach_sub_id); - if (detach_sub_id != VMCI_INVALID_ID) vmci_event_unsubscribe(detach_sub_id); @@ -1607,9 +1566,11 @@ static int vmci_transport_socket_init(struct vsock_sock *vsk, vmci_trans(vsk)->qp_handle = VMCI_INVALID_HANDLE; vmci_trans(vsk)->qpair = NULL; vmci_trans(vsk)->produce_size = vmci_trans(vsk)->consume_size = 0; - vmci_trans(vsk)->attach_sub_id = vmci_trans(vsk)->detach_sub_id = - VMCI_INVALID_ID; + vmci_trans(vsk)->detach_sub_id = VMCI_INVALID_ID; vmci_trans(vsk)->notify_ops = NULL; + INIT_LIST_HEAD(&vmci_trans(vsk)->elem); + vmci_trans(vsk)->sk = &vsk->sk; + spin_lock_init(&vmci_trans(vsk)->lock); if (psk) { vmci_trans(vsk)->queue_pair_size = vmci_trans(psk)->queue_pair_size; @@ -1629,29 +1590,57 @@ static int vmci_transport_socket_init(struct vsock_sock *vsk, return 0; } -static void vmci_transport_destruct(struct vsock_sock *vsk) +static void vmci_transport_free_resources(struct list_head *transport_list) { - if (vmci_trans(vsk)->attach_sub_id != VMCI_INVALID_ID) { - vmci_event_unsubscribe(vmci_trans(vsk)->attach_sub_id); - vmci_trans(vsk)->attach_sub_id = VMCI_INVALID_ID; - } + while (!list_empty(transport_list)) { + struct vmci_transport *transport = + list_first_entry(transport_list, struct vmci_transport, + elem); + list_del(&transport->elem); - if (vmci_trans(vsk)->detach_sub_id != VMCI_INVALID_ID) { - vmci_event_unsubscribe(vmci_trans(vsk)->detach_sub_id); - vmci_trans(vsk)->detach_sub_id = VMCI_INVALID_ID; - } + if (transport->detach_sub_id != VMCI_INVALID_ID) { + vmci_event_unsubscribe(transport->detach_sub_id); + transport->detach_sub_id = VMCI_INVALID_ID; + } - if (!vmci_handle_is_invalid(vmci_trans(vsk)->qp_handle)) { - vmci_qpair_detach(&vmci_trans(vsk)->qpair); - vmci_trans(vsk)->qp_handle = VMCI_INVALID_HANDLE; - vmci_trans(vsk)->produce_size = 0; - vmci_trans(vsk)->consume_size = 0; + if (!vmci_handle_is_invalid(transport->qp_handle)) { + vmci_qpair_detach(&transport->qpair); + transport->qp_handle = VMCI_INVALID_HANDLE; + transport->produce_size = 0; + transport->consume_size = 0; + } + + kfree(transport); } +} + +static void vmci_transport_cleanup(struct work_struct *work) +{ + LIST_HEAD(pending); + + spin_lock_bh(&vmci_transport_cleanup_lock); + list_replace_init(&vmci_transport_cleanup_list, &pending); + spin_unlock_bh(&vmci_transport_cleanup_lock); + vmci_transport_free_resources(&pending); +} + +static void vmci_transport_destruct(struct vsock_sock *vsk) +{ + /* Ensure that the detach callback doesn't use the sk/vsk + * we are about to destruct. + */ + spin_lock_bh(&vmci_trans(vsk)->lock); + vmci_trans(vsk)->sk = NULL; + spin_unlock_bh(&vmci_trans(vsk)->lock); if (vmci_trans(vsk)->notify_ops) vmci_trans(vsk)->notify_ops->socket_destruct(vsk); - kfree(vsk->trans); + spin_lock_bh(&vmci_transport_cleanup_lock); + list_add(&vmci_trans(vsk)->elem, &vmci_transport_cleanup_list); + spin_unlock_bh(&vmci_transport_cleanup_lock); + schedule_work(&vmci_transport_cleanup_work); + vsk->trans = NULL; } @@ -2146,6 +2135,9 @@ module_init(vmci_transport_init); static void __exit vmci_transport_exit(void) { + cancel_work_sync(&vmci_transport_cleanup_work); + vmci_transport_free_resources(&vmci_transport_cleanup_list); + if (!vmci_handle_is_invalid(vmci_transport_stream_handle)) { if (vmci_datagram_destroy_handle( vmci_transport_stream_handle) != VMCI_SUCCESS) @@ -2164,6 +2156,7 @@ module_exit(vmci_transport_exit); MODULE_AUTHOR("VMware, Inc."); MODULE_DESCRIPTION("VMCI transport for Virtual Sockets"); +MODULE_VERSION("1.0.2.0-k"); MODULE_LICENSE("GPL v2"); MODULE_ALIAS("vmware_vsock"); MODULE_ALIAS_NETPROTO(PF_VSOCK); diff --git a/net/vmw_vsock/vmci_transport.h b/net/vmw_vsock/vmci_transport.h index ce6c9623d5f0..2ad46f39649f 100644 --- a/net/vmw_vsock/vmci_transport.h +++ b/net/vmw_vsock/vmci_transport.h @@ -119,10 +119,12 @@ struct vmci_transport { u64 queue_pair_size; u64 queue_pair_min_size; u64 queue_pair_max_size; - u32 attach_sub_id; u32 detach_sub_id; union vmci_transport_notify notify; struct vmci_transport_notify_ops *notify_ops; + struct list_head elem; + struct sock *sk; + spinlock_t lock; /* protects sk. */ }; int vmci_transport_register(void); diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index a8de9e300200..24e06a2377f6 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -1928,8 +1928,10 @@ static int xfrm_new_ae(struct sk_buff *skb, struct nlmsghdr *nlh, struct nlattr *rp = attrs[XFRMA_REPLAY_VAL]; struct nlattr *re = attrs[XFRMA_REPLAY_ESN_VAL]; struct nlattr *lt = attrs[XFRMA_LTIME_VAL]; + struct nlattr *et = attrs[XFRMA_ETIMER_THRESH]; + struct nlattr *rt = attrs[XFRMA_REPLAY_THRESH]; - if (!lt && !rp && !re) + if (!lt && !rp && !re && !et && !rt) return err; /* pedantic mode - thou shalt sayeth replaceth */ diff --git a/samples/bpf/bpf_helpers.h b/samples/bpf/bpf_helpers.h index 3a44d3a272af..af44e564d6dd 100644 --- a/samples/bpf/bpf_helpers.h +++ b/samples/bpf/bpf_helpers.h @@ -86,5 +86,17 @@ static int (*bpf_l4_csum_replace)(void *ctx, int off, int from, int to, int flag #define PT_REGS_RC(x) ((x)->gprs[2]) #define PT_REGS_SP(x) ((x)->gprs[15]) +#elif defined(__aarch64__) + +#define PT_REGS_PARM1(x) ((x)->regs[0]) +#define PT_REGS_PARM2(x) ((x)->regs[1]) +#define PT_REGS_PARM3(x) ((x)->regs[2]) +#define PT_REGS_PARM4(x) ((x)->regs[3]) +#define PT_REGS_PARM5(x) ((x)->regs[4]) +#define PT_REGS_RET(x) ((x)->regs[30]) +#define PT_REGS_FP(x) ((x)->regs[29]) /* Works only with CONFIG_FRAME_POINTER */ +#define PT_REGS_RC(x) ((x)->regs[0]) +#define PT_REGS_SP(x) ((x)->sp) + #endif #endif diff --git a/security/keys/gc.c b/security/keys/gc.c index 39eac1fd5706..addf060399e0 100644 --- a/security/keys/gc.c +++ b/security/keys/gc.c @@ -134,8 +134,10 @@ static noinline void key_gc_unused_keys(struct list_head *keys) kdebug("- %u", key->serial); key_check(key); - /* Throw away the key data */ - if (key->type->destroy) + /* Throw away the key data if the key is instantiated */ + if (test_bit(KEY_FLAG_INSTANTIATED, &key->flags) && + !test_bit(KEY_FLAG_NEGATIVE, &key->flags) && + key->type->destroy) key->type->destroy(key); security_key_free(key); diff --git a/security/keys/request_key.c b/security/keys/request_key.c index 486ef6fa393b..0d6253124278 100644 --- a/security/keys/request_key.c +++ b/security/keys/request_key.c @@ -440,6 +440,9 @@ static struct key *construct_key_and_link(struct keyring_search_context *ctx, kenter(""); + if (ctx->index_key.type == &key_type_keyring) + return ERR_PTR(-EPERM); + user = key_user_lookup(current_fsuid()); if (!user) return ERR_PTR(-ENOMEM); diff --git a/sound/hda/ext/hdac_ext_bus.c b/sound/hda/ext/hdac_ext_bus.c index 4449d1a99089..2433f7c81472 100644 --- a/sound/hda/ext/hdac_ext_bus.c +++ b/sound/hda/ext/hdac_ext_bus.c @@ -19,6 +19,7 @@ #include <linux/module.h> #include <linux/slab.h> +#include <linux/io.h> #include <sound/hdaudio_ext.h> MODULE_DESCRIPTION("HDA extended core"); diff --git a/sound/pci/hda/hda_codec.c b/sound/pci/hda/hda_codec.c index 37f43a1b34ef..a249d5486889 100644 --- a/sound/pci/hda/hda_codec.c +++ b/sound/pci/hda/hda_codec.c @@ -3367,10 +3367,8 @@ int snd_hda_codec_build_pcms(struct hda_codec *codec) int dev, err; err = snd_hda_codec_parse_pcms(codec); - if (err < 0) { - snd_hda_codec_reset(codec); + if (err < 0) return err; - } /* attach a new PCM streams */ list_for_each_entry(cpcm, &codec->pcm_list_head, list) { diff --git a/sound/pci/hda/patch_conexant.c b/sound/pci/hda/patch_conexant.c index ca03c40609fc..2f0ec7c45fc7 100644 --- a/sound/pci/hda/patch_conexant.c +++ b/sound/pci/hda/patch_conexant.c @@ -819,6 +819,7 @@ static const struct snd_pci_quirk cxt5066_fixups[] = { SND_PCI_QUIRK(0x17aa, 0x21da, "Lenovo X220", CXT_PINCFG_LENOVO_TP410), SND_PCI_QUIRK(0x17aa, 0x21db, "Lenovo X220-tablet", CXT_PINCFG_LENOVO_TP410), SND_PCI_QUIRK(0x17aa, 0x38af, "Lenovo IdeaPad Z560", CXT_FIXUP_MUTE_LED_EAPD), + SND_PCI_QUIRK(0x17aa, 0x390b, "Lenovo G50-80", CXT_FIXUP_STEREO_DMIC), SND_PCI_QUIRK(0x17aa, 0x3975, "Lenovo U300s", CXT_FIXUP_STEREO_DMIC), SND_PCI_QUIRK(0x17aa, 0x3977, "Lenovo IdeaPad U310", CXT_FIXUP_STEREO_DMIC), SND_PCI_QUIRK(0x17aa, 0x397b, "Lenovo S205", CXT_FIXUP_STEREO_DMIC), diff --git a/sound/soc/codecs/rt298.c b/sound/soc/codecs/rt298.c index 3c2f0f8d6266..f823eb502367 100644 --- a/sound/soc/codecs/rt298.c +++ b/sound/soc/codecs/rt298.c @@ -50,24 +50,24 @@ struct rt298_priv { }; static struct reg_default rt298_index_def[] = { - { 0x01, 0xaaaa }, - { 0x02, 0x8aaa }, + { 0x01, 0xa5a8 }, + { 0x02, 0x8e95 }, { 0x03, 0x0002 }, - { 0x04, 0xaf01 }, - { 0x08, 0x000d }, - { 0x09, 0xd810 }, - { 0x0a, 0x0120 }, + { 0x04, 0xaf67 }, + { 0x08, 0x200f }, + { 0x09, 0xd010 }, + { 0x0a, 0x0100 }, { 0x0b, 0x0000 }, { 0x0d, 0x2800 }, - { 0x0f, 0x0000 }, - { 0x19, 0x0a17 }, + { 0x0f, 0x0022 }, + { 0x19, 0x0217 }, { 0x20, 0x0020 }, { 0x33, 0x0208 }, { 0x46, 0x0300 }, - { 0x49, 0x0004 }, - { 0x4f, 0x50e9 }, - { 0x50, 0x2000 }, - { 0x63, 0x2902 }, + { 0x49, 0x4004 }, + { 0x4f, 0x50c9 }, + { 0x50, 0x3000 }, + { 0x63, 0x1b02 }, { 0x67, 0x1111 }, { 0x68, 0x1016 }, { 0x69, 0x273f }, @@ -1214,7 +1214,7 @@ static int rt298_i2c_probe(struct i2c_client *i2c, mdelay(10); if (!rt298->pdata.gpio2_en) - regmap_write(rt298->regmap, RT298_SET_DMIC2_DEFAULT, 0x4000); + regmap_write(rt298->regmap, RT298_SET_DMIC2_DEFAULT, 0x40); else regmap_write(rt298->regmap, RT298_SET_DMIC2_DEFAULT, 0); diff --git a/sound/soc/codecs/wm8962.c b/sound/soc/codecs/wm8962.c index 2fbc6ef8cbdb..39ebd7bf4f53 100644 --- a/sound/soc/codecs/wm8962.c +++ b/sound/soc/codecs/wm8962.c @@ -3808,6 +3808,8 @@ static int wm8962_runtime_resume(struct device *dev) wm8962_reset(wm8962); + regcache_mark_dirty(wm8962->regmap); + /* SYSCLK defaults to on; make sure it is off so we can safely * write to registers if the device is declocked. */ diff --git a/sound/soc/soc-ops.c b/sound/soc/soc-ops.c index 100d92b5b77e..05977ae1ff2a 100644 --- a/sound/soc/soc-ops.c +++ b/sound/soc/soc-ops.c @@ -207,6 +207,34 @@ int snd_soc_info_volsw(struct snd_kcontrol *kcontrol, EXPORT_SYMBOL_GPL(snd_soc_info_volsw); /** + * snd_soc_info_volsw_sx - Mixer info callback for SX TLV controls + * @kcontrol: mixer control + * @uinfo: control element information + * + * Callback to provide information about a single mixer control, or a double + * mixer control that spans 2 registers of the SX TLV type. SX TLV controls + * have a range that represents both positive and negative values either side + * of zero but without a sign bit. + * + * Returns 0 for success. + */ +int snd_soc_info_volsw_sx(struct snd_kcontrol *kcontrol, + struct snd_ctl_elem_info *uinfo) +{ + struct soc_mixer_control *mc = + (struct soc_mixer_control *)kcontrol->private_value; + + snd_soc_info_volsw(kcontrol, uinfo); + /* Max represents the number of levels in an SX control not the + * maximum value, so add the minimum value back on + */ + uinfo->value.integer.max += mc->min; + + return 0; +} +EXPORT_SYMBOL_GPL(snd_soc_info_volsw_sx); + +/** * snd_soc_get_volsw - single mixer get callback * @kcontrol: mixer control * @ucontrol: control element information diff --git a/tools/testing/selftests/x86/entry_from_vm86.c b/tools/testing/selftests/x86/entry_from_vm86.c index 421c607a8856..d075ea0e5ca1 100644 --- a/tools/testing/selftests/x86/entry_from_vm86.c +++ b/tools/testing/selftests/x86/entry_from_vm86.c @@ -230,5 +230,9 @@ int main(void) } clearhandler(SIGSEGV); + /* Make sure nothing explodes if we fork. */ + if (fork() > 0) + return 0; + return (nerrs == 0 ? 0 : 1); } diff --git a/virt/kvm/arm/arch_timer.c b/virt/kvm/arm/arch_timer.c index 48c6e1ac6827..b9d3a32cbc04 100644 --- a/virt/kvm/arm/arch_timer.c +++ b/virt/kvm/arm/arch_timer.c @@ -137,6 +137,8 @@ bool kvm_timer_should_fire(struct kvm_vcpu *vcpu) void kvm_timer_flush_hwstate(struct kvm_vcpu *vcpu) { struct arch_timer_cpu *timer = &vcpu->arch.timer_cpu; + bool phys_active; + int ret; /* * We're about to run this vcpu again, so there is no need to @@ -151,6 +153,23 @@ void kvm_timer_flush_hwstate(struct kvm_vcpu *vcpu) */ if (kvm_timer_should_fire(vcpu)) kvm_timer_inject_irq(vcpu); + + /* + * We keep track of whether the edge-triggered interrupt has been + * signalled to the vgic/guest, and if so, we mask the interrupt and + * the physical distributor to prevent the timer from raising a + * physical interrupt whenever we run a guest, preventing forward + * VCPU progress. + */ + if (kvm_vgic_get_phys_irq_active(timer->map)) + phys_active = true; + else + phys_active = false; + + ret = irq_set_irqchip_state(timer->map->irq, + IRQCHIP_STATE_ACTIVE, + phys_active); + WARN_ON(ret); } /** diff --git a/virt/kvm/arm/vgic.c b/virt/kvm/arm/vgic.c index 6bd1c9bf7ae7..66c66165e712 100644 --- a/virt/kvm/arm/vgic.c +++ b/virt/kvm/arm/vgic.c @@ -531,6 +531,34 @@ bool vgic_handle_set_pending_reg(struct kvm *kvm, return false; } +/* + * If a mapped interrupt's state has been modified by the guest such that it + * is no longer active or pending, without it have gone through the sync path, + * then the map->active field must be cleared so the interrupt can be taken + * again. + */ +static void vgic_handle_clear_mapped_irq(struct kvm_vcpu *vcpu) +{ + struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu; + struct list_head *root; + struct irq_phys_map_entry *entry; + struct irq_phys_map *map; + + rcu_read_lock(); + + /* Check for PPIs */ + root = &vgic_cpu->irq_phys_map_list; + list_for_each_entry_rcu(entry, root, entry) { + map = &entry->map; + + if (!vgic_dist_irq_is_pending(vcpu, map->virt_irq) && + !vgic_irq_is_active(vcpu, map->virt_irq)) + map->active = false; + } + + rcu_read_unlock(); +} + bool vgic_handle_clear_pending_reg(struct kvm *kvm, struct kvm_exit_mmio *mmio, phys_addr_t offset, int vcpu_id) @@ -561,6 +589,7 @@ bool vgic_handle_clear_pending_reg(struct kvm *kvm, vcpu_id, offset); vgic_reg_access(mmio, reg, offset, mode); + vgic_handle_clear_mapped_irq(kvm_get_vcpu(kvm, vcpu_id)); vgic_update_state(kvm); return true; } @@ -598,6 +627,7 @@ bool vgic_handle_clear_active_reg(struct kvm *kvm, ACCESS_READ_VALUE | ACCESS_WRITE_CLEARBIT); if (mmio->is_write) { + vgic_handle_clear_mapped_irq(kvm_get_vcpu(kvm, vcpu_id)); vgic_update_state(kvm); return true; } @@ -982,6 +1012,12 @@ static int compute_pending_for_cpu(struct kvm_vcpu *vcpu) pend_percpu = vcpu->arch.vgic_cpu.pending_percpu; pend_shared = vcpu->arch.vgic_cpu.pending_shared; + if (!dist->enabled) { + bitmap_zero(pend_percpu, VGIC_NR_PRIVATE_IRQS); + bitmap_zero(pend_shared, nr_shared); + return 0; + } + pending = vgic_bitmap_get_cpu_map(&dist->irq_pending, vcpu_id); enabled = vgic_bitmap_get_cpu_map(&dist->irq_enabled, vcpu_id); bitmap_and(pend_percpu, pending, enabled, VGIC_NR_PRIVATE_IRQS); @@ -1009,11 +1045,6 @@ void vgic_update_state(struct kvm *kvm) struct kvm_vcpu *vcpu; int c; - if (!dist->enabled) { - set_bit(0, dist->irq_pending_on_cpu); - return; - } - kvm_for_each_vcpu(c, vcpu, kvm) { if (compute_pending_for_cpu(vcpu)) set_bit(c, dist->irq_pending_on_cpu); @@ -1092,6 +1123,15 @@ static void vgic_retire_lr(int lr_nr, int irq, struct kvm_vcpu *vcpu) struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu; struct vgic_lr vlr = vgic_get_lr(vcpu, lr_nr); + /* + * We must transfer the pending state back to the distributor before + * retiring the LR, otherwise we may loose edge-triggered interrupts. + */ + if (vlr.state & LR_STATE_PENDING) { + vgic_dist_irq_set_pending(vcpu, irq); + vlr.hwirq = 0; + } + vlr.state = 0; vgic_set_lr(vcpu, lr_nr, vlr); clear_bit(lr_nr, vgic_cpu->lr_used); @@ -1132,7 +1172,8 @@ static void vgic_queue_irq_to_lr(struct kvm_vcpu *vcpu, int irq, kvm_debug("Set active, clear distributor: 0x%x\n", vlr.state); vgic_irq_clear_active(vcpu, irq); vgic_update_state(vcpu->kvm); - } else if (vgic_dist_irq_is_pending(vcpu, irq)) { + } else { + WARN_ON(!vgic_dist_irq_is_pending(vcpu, irq)); vlr.state |= LR_STATE_PENDING; kvm_debug("Set pending: 0x%x\n", vlr.state); } @@ -1240,7 +1281,7 @@ static void __kvm_vgic_flush_hwstate(struct kvm_vcpu *vcpu) struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu; struct vgic_dist *dist = &vcpu->kvm->arch.vgic; unsigned long *pa_percpu, *pa_shared; - int i, vcpu_id, lr, ret; + int i, vcpu_id; int overflow = 0; int nr_shared = vgic_nr_shared_irqs(dist); @@ -1295,31 +1336,6 @@ epilog: */ clear_bit(vcpu_id, dist->irq_pending_on_cpu); } - - for (lr = 0; lr < vgic->nr_lr; lr++) { - struct vgic_lr vlr; - - if (!test_bit(lr, vgic_cpu->lr_used)) - continue; - - vlr = vgic_get_lr(vcpu, lr); - - /* - * If we have a mapping, and the virtual interrupt is - * presented to the guest (as pending or active), then we must - * set the state to active in the physical world. See - * Documentation/virtual/kvm/arm/vgic-mapped-irqs.txt. - */ - if (vlr.state & LR_HW) { - struct irq_phys_map *map; - map = vgic_irq_map_search(vcpu, vlr.irq); - - ret = irq_set_irqchip_state(map->irq, - IRQCHIP_STATE_ACTIVE, - true); - WARN_ON(ret); - } - } } static bool vgic_process_maintenance(struct kvm_vcpu *vcpu) @@ -1421,7 +1437,7 @@ static int vgic_sync_hwirq(struct kvm_vcpu *vcpu, struct vgic_lr vlr) return 0; map = vgic_irq_map_search(vcpu, vlr.irq); - BUG_ON(!map || !map->active); + BUG_ON(!map); ret = irq_get_irqchip_state(map->irq, IRQCHIP_STATE_ACTIVE, @@ -1429,13 +1445,8 @@ static int vgic_sync_hwirq(struct kvm_vcpu *vcpu, struct vgic_lr vlr) WARN_ON(ret); - if (map->active) { - ret = irq_set_irqchip_state(map->irq, - IRQCHIP_STATE_ACTIVE, - false); - WARN_ON(ret); + if (map->active) return 0; - } return 1; } @@ -1607,8 +1618,12 @@ static int vgic_update_irq_pending(struct kvm *kvm, int cpuid, } else { if (level_triggered) { vgic_dist_irq_clear_level(vcpu, irq_num); - if (!vgic_dist_irq_soft_pend(vcpu, irq_num)) + if (!vgic_dist_irq_soft_pend(vcpu, irq_num)) { vgic_dist_irq_clear_pending(vcpu, irq_num); + vgic_cpu_irq_clear(vcpu, irq_num); + if (!compute_pending_for_cpu(vcpu)) + clear_bit(cpuid, dist->irq_pending_on_cpu); + } } ret = false; |