diff options
206 files changed, 4139 insertions, 1893 deletions
diff --git a/Documentation/devicetree/bindings/iommu/allwinner,sun50i-h6-iommu.yaml b/Documentation/devicetree/bindings/iommu/allwinner,sun50i-h6-iommu.yaml new file mode 100644 index 000000000000..5e125cf2a88b --- /dev/null +++ b/Documentation/devicetree/bindings/iommu/allwinner,sun50i-h6-iommu.yaml @@ -0,0 +1,61 @@ +# SPDX-License-Identifier: (GPL-2.0 OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/iommu/allwinner,sun50i-h6-iommu.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Allwinner H6 IOMMU Device Tree Bindings + +maintainers: + - Chen-Yu Tsai <wens@csie.org> + - Maxime Ripard <mripard@kernel.org> + +properties: + "#iommu-cells": + const: 1 + description: + The content of the cell is the master ID. + + compatible: + const: allwinner,sun50i-h6-iommu + + reg: + maxItems: 1 + + interrupts: + maxItems: 1 + + clocks: + maxItems: 1 + + resets: + maxItems: 1 + +required: + - "#iommu-cells" + - compatible + - reg + - interrupts + - clocks + - resets + +additionalProperties: false + +examples: + - | + #include <dt-bindings/interrupt-controller/arm-gic.h> + #include <dt-bindings/interrupt-controller/irq.h> + + #include <dt-bindings/clock/sun50i-h6-ccu.h> + #include <dt-bindings/reset/sun50i-h6-ccu.h> + + iommu: iommu@30f0000 { + compatible = "allwinner,sun50i-h6-iommu"; + reg = <0x030f0000 0x10000>; + interrupts = <GIC_SPI 57 IRQ_TYPE_LEVEL_HIGH>; + clocks = <&ccu CLK_BUS_IOMMU>; + resets = <&ccu RST_BUS_IOMMU>; + #iommu-cells = <1>; + }; + +... diff --git a/Documentation/devicetree/bindings/iommu/arm,smmu.yaml b/Documentation/devicetree/bindings/iommu/arm,smmu.yaml index 6515dbe47508..e3ef1c69d132 100644 --- a/Documentation/devicetree/bindings/iommu/arm,smmu.yaml +++ b/Documentation/devicetree/bindings/iommu/arm,smmu.yaml @@ -41,7 +41,9 @@ properties: - const: arm,mmu-500 - const: arm,smmu-v2 - items: - - const: arm,mmu-401 + - enum: + - arm,mmu-400 + - arm,mmu-401 - const: arm,smmu-v1 - enum: - arm,smmu-v1 diff --git a/Documentation/devicetree/bindings/remoteproc/qcom,q6v5.txt b/Documentation/devicetree/bindings/remoteproc/qcom,q6v5.txt index 88dfa3fc15f7..130e50aab741 100644 --- a/Documentation/devicetree/bindings/remoteproc/qcom,q6v5.txt +++ b/Documentation/devicetree/bindings/remoteproc/qcom,q6v5.txt @@ -184,6 +184,9 @@ For the compatible strings below the following phandle references are required: followed by the offset within syscon for conn_box_spare0 register. +The Hexagon node must contain iommus property as described in ../iommu/iommu.txt +on platforms which do not have TrustZone. + = SUBNODES: The Hexagon node must contain two subnodes, named "mba" and "mpss" representing the memory regions used by the Hexagon firmware. Each sub-node must contain: diff --git a/Documentation/process/coding-style.rst b/Documentation/process/coding-style.rst index acb2f1b36350..17a8e584f15f 100644 --- a/Documentation/process/coding-style.rst +++ b/Documentation/process/coding-style.rst @@ -84,15 +84,20 @@ Get a decent editor and don't leave whitespace at the end of lines. Coding style is all about readability and maintainability using commonly available tools. -The limit on the length of lines is 80 columns and this is a strongly -preferred limit. - -Statements longer than 80 columns will be broken into sensible chunks, unless -exceeding 80 columns significantly increases readability and does not hide -information. Descendants are always substantially shorter than the parent and -are placed substantially to the right. The same applies to function headers -with a long argument list. However, never break user-visible strings such as -printk messages, because that breaks the ability to grep for them. +The preferred limit on the length of a single line is 80 columns. + +Statements longer than 80 columns should be broken into sensible chunks, +unless exceeding 80 columns significantly increases readability and does +not hide information. + +Descendants are always substantially shorter than the parent and are +are placed substantially to the right. A very commonly used style +is to align descendants to a function open parenthesis. + +These same rules are applied to function headers with a long argument list. + +However, never break user-visible strings such as printk messages because +that breaks the ability to grep for them. 3) Placing Braces and Spaces @@ -2,7 +2,7 @@ VERSION = 5 PATCHLEVEL = 7 SUBLEVEL = 0 -EXTRAVERSION = -rc7 +EXTRAVERSION = NAME = Kleptomaniac Octopus # *DOCUMENTATION* diff --git a/arch/arm/boot/compressed/vmlinux.lds.S b/arch/arm/boot/compressed/vmlinux.lds.S index b247f399de71..f82b5962d97e 100644 --- a/arch/arm/boot/compressed/vmlinux.lds.S +++ b/arch/arm/boot/compressed/vmlinux.lds.S @@ -42,7 +42,7 @@ SECTIONS } .table : ALIGN(4) { _table_start = .; - LONG(ZIMAGE_MAGIC(2)) + LONG(ZIMAGE_MAGIC(4)) LONG(ZIMAGE_MAGIC(0x5a534c4b)) LONG(ZIMAGE_MAGIC(__piggy_size_addr - _start)) LONG(ZIMAGE_MAGIC(_kernel_bss_size)) diff --git a/arch/arm/boot/dts/am437x-gp-evm.dts b/arch/arm/boot/dts/am437x-gp-evm.dts index 811c8cae315b..d692e3b2812a 100644 --- a/arch/arm/boot/dts/am437x-gp-evm.dts +++ b/arch/arm/boot/dts/am437x-gp-evm.dts @@ -943,7 +943,7 @@ &cpsw_emac0 { phy-handle = <ðphy0>; - phy-mode = "rgmii"; + phy-mode = "rgmii-rxid"; }; &elm { diff --git a/arch/arm/boot/dts/am437x-idk-evm.dts b/arch/arm/boot/dts/am437x-idk-evm.dts index 9f66f96d09c9..a958f9ee4a5a 100644 --- a/arch/arm/boot/dts/am437x-idk-evm.dts +++ b/arch/arm/boot/dts/am437x-idk-evm.dts @@ -504,7 +504,7 @@ &cpsw_emac0 { phy-handle = <ðphy0>; - phy-mode = "rgmii"; + phy-mode = "rgmii-rxid"; }; &rtc { diff --git a/arch/arm/boot/dts/am437x-sk-evm.dts b/arch/arm/boot/dts/am437x-sk-evm.dts index 25222497f828..4d5a7ca2e25d 100644 --- a/arch/arm/boot/dts/am437x-sk-evm.dts +++ b/arch/arm/boot/dts/am437x-sk-evm.dts @@ -833,13 +833,13 @@ &cpsw_emac0 { phy-handle = <ðphy0>; - phy-mode = "rgmii"; + phy-mode = "rgmii-rxid"; dual_emac_res_vlan = <1>; }; &cpsw_emac1 { phy-handle = <ðphy1>; - phy-mode = "rgmii"; + phy-mode = "rgmii-rxid"; dual_emac_res_vlan = <2>; }; diff --git a/arch/arm/boot/dts/am571x-idk.dts b/arch/arm/boot/dts/am571x-idk.dts index 669559c9c95b..c13756fa0f55 100644 --- a/arch/arm/boot/dts/am571x-idk.dts +++ b/arch/arm/boot/dts/am571x-idk.dts @@ -190,13 +190,13 @@ &cpsw_port1 { phy-handle = <ðphy0_sw>; - phy-mode = "rgmii"; + phy-mode = "rgmii-rxid"; ti,dual-emac-pvid = <1>; }; &cpsw_port2 { phy-handle = <ðphy1_sw>; - phy-mode = "rgmii"; + phy-mode = "rgmii-rxid"; ti,dual-emac-pvid = <2>; }; diff --git a/arch/arm/boot/dts/am57xx-beagle-x15-common.dtsi b/arch/arm/boot/dts/am57xx-beagle-x15-common.dtsi index a813a0cf3ff3..565675354de4 100644 --- a/arch/arm/boot/dts/am57xx-beagle-x15-common.dtsi +++ b/arch/arm/boot/dts/am57xx-beagle-x15-common.dtsi @@ -433,13 +433,13 @@ &cpsw_emac0 { phy-handle = <&phy0>; - phy-mode = "rgmii"; + phy-mode = "rgmii-rxid"; dual_emac_res_vlan = <1>; }; &cpsw_emac1 { phy-handle = <&phy1>; - phy-mode = "rgmii"; + phy-mode = "rgmii-rxid"; dual_emac_res_vlan = <2>; }; diff --git a/arch/arm/boot/dts/am57xx-idk-common.dtsi b/arch/arm/boot/dts/am57xx-idk-common.dtsi index aa5e55f98179..a3ff1237d1fa 100644 --- a/arch/arm/boot/dts/am57xx-idk-common.dtsi +++ b/arch/arm/boot/dts/am57xx-idk-common.dtsi @@ -408,13 +408,13 @@ &cpsw_emac0 { phy-handle = <ðphy0>; - phy-mode = "rgmii"; + phy-mode = "rgmii-rxid"; dual_emac_res_vlan = <1>; }; &cpsw_emac1 { phy-handle = <ðphy1>; - phy-mode = "rgmii"; + phy-mode = "rgmii-rxid"; dual_emac_res_vlan = <2>; }; diff --git a/arch/arm/boot/dts/bcm-hr2.dtsi b/arch/arm/boot/dts/bcm-hr2.dtsi index 6142c672811e..5e5f5ca3c86f 100644 --- a/arch/arm/boot/dts/bcm-hr2.dtsi +++ b/arch/arm/boot/dts/bcm-hr2.dtsi @@ -75,7 +75,7 @@ timer@20200 { compatible = "arm,cortex-a9-global-timer"; reg = <0x20200 0x100>; - interrupts = <GIC_PPI 11 IRQ_TYPE_LEVEL_HIGH>; + interrupts = <GIC_PPI 11 IRQ_TYPE_EDGE_RISING>; clocks = <&periph_clk>; }; @@ -83,7 +83,7 @@ compatible = "arm,cortex-a9-twd-timer"; reg = <0x20600 0x20>; interrupts = <GIC_PPI 13 (GIC_CPU_MASK_SIMPLE(1) | - IRQ_TYPE_LEVEL_HIGH)>; + IRQ_TYPE_EDGE_RISING)>; clocks = <&periph_clk>; }; @@ -91,7 +91,7 @@ compatible = "arm,cortex-a9-twd-wdt"; reg = <0x20620 0x20>; interrupts = <GIC_PPI 14 (GIC_CPU_MASK_SIMPLE(1) | - IRQ_TYPE_LEVEL_HIGH)>; + IRQ_TYPE_EDGE_RISING)>; clocks = <&periph_clk>; }; diff --git a/arch/arm/boot/dts/bcm2835-rpi-zero-w.dts b/arch/arm/boot/dts/bcm2835-rpi-zero-w.dts index 4c3f606e5b8d..f65448c01e31 100644 --- a/arch/arm/boot/dts/bcm2835-rpi-zero-w.dts +++ b/arch/arm/boot/dts/bcm2835-rpi-zero-w.dts @@ -24,7 +24,7 @@ leds { act { - gpios = <&gpio 47 GPIO_ACTIVE_HIGH>; + gpios = <&gpio 47 GPIO_ACTIVE_LOW>; }; }; diff --git a/arch/arm/boot/dts/dm814x.dtsi b/arch/arm/boot/dts/dm814x.dtsi index 44ed5a798164..c28ca0540f03 100644 --- a/arch/arm/boot/dts/dm814x.dtsi +++ b/arch/arm/boot/dts/dm814x.dtsi @@ -693,7 +693,7 @@ davinci_mdio: mdio@800 { compatible = "ti,cpsw-mdio", "ti,davinci_mdio"; - clocks = <&alwon_ethernet_clkctrl DM814_ETHERNET_CPGMAC0_CLKCTRL 0>; + clocks = <&cpsw_125mhz_gclk>; clock-names = "fck"; #address-cells = <1>; #size-cells = <0>; diff --git a/arch/arm/boot/dts/imx6q-b450v3.dts b/arch/arm/boot/dts/imx6q-b450v3.dts index 95b8f2d71821..fb0980190aa0 100644 --- a/arch/arm/boot/dts/imx6q-b450v3.dts +++ b/arch/arm/boot/dts/imx6q-b450v3.dts @@ -65,13 +65,6 @@ }; }; -&clks { - assigned-clocks = <&clks IMX6QDL_CLK_LDB_DI0_SEL>, - <&clks IMX6QDL_CLK_LDB_DI1_SEL>; - assigned-clock-parents = <&clks IMX6QDL_CLK_PLL3_USB_OTG>, - <&clks IMX6QDL_CLK_PLL3_USB_OTG>; -}; - &ldb { status = "okay"; diff --git a/arch/arm/boot/dts/imx6q-b650v3.dts b/arch/arm/boot/dts/imx6q-b650v3.dts index 611cb7ae7e55..8f762d9c5ae9 100644 --- a/arch/arm/boot/dts/imx6q-b650v3.dts +++ b/arch/arm/boot/dts/imx6q-b650v3.dts @@ -65,13 +65,6 @@ }; }; -&clks { - assigned-clocks = <&clks IMX6QDL_CLK_LDB_DI0_SEL>, - <&clks IMX6QDL_CLK_LDB_DI1_SEL>; - assigned-clock-parents = <&clks IMX6QDL_CLK_PLL3_USB_OTG>, - <&clks IMX6QDL_CLK_PLL3_USB_OTG>; -}; - &ldb { status = "okay"; diff --git a/arch/arm/boot/dts/imx6q-b850v3.dts b/arch/arm/boot/dts/imx6q-b850v3.dts index e4cb118f88c6..1ea64ecf4291 100644 --- a/arch/arm/boot/dts/imx6q-b850v3.dts +++ b/arch/arm/boot/dts/imx6q-b850v3.dts @@ -53,17 +53,6 @@ }; }; -&clks { - assigned-clocks = <&clks IMX6QDL_CLK_LDB_DI0_SEL>, - <&clks IMX6QDL_CLK_LDB_DI1_SEL>, - <&clks IMX6QDL_CLK_IPU1_DI0_PRE_SEL>, - <&clks IMX6QDL_CLK_IPU2_DI0_PRE_SEL>; - assigned-clock-parents = <&clks IMX6QDL_CLK_PLL5_VIDEO_DIV>, - <&clks IMX6QDL_CLK_PLL5_VIDEO_DIV>, - <&clks IMX6QDL_CLK_PLL2_PFD2_396M>, - <&clks IMX6QDL_CLK_PLL2_PFD2_396M>; -}; - &ldb { fsl,dual-channel; status = "okay"; diff --git a/arch/arm/boot/dts/imx6q-bx50v3.dtsi b/arch/arm/boot/dts/imx6q-bx50v3.dtsi index fa27dcdf06f1..1938b04199c4 100644 --- a/arch/arm/boot/dts/imx6q-bx50v3.dtsi +++ b/arch/arm/boot/dts/imx6q-bx50v3.dtsi @@ -377,3 +377,18 @@ #interrupt-cells = <1>; }; }; + +&clks { + assigned-clocks = <&clks IMX6QDL_CLK_LDB_DI0_SEL>, + <&clks IMX6QDL_CLK_LDB_DI1_SEL>, + <&clks IMX6QDL_CLK_IPU1_DI0_PRE_SEL>, + <&clks IMX6QDL_CLK_IPU1_DI1_PRE_SEL>, + <&clks IMX6QDL_CLK_IPU2_DI0_PRE_SEL>, + <&clks IMX6QDL_CLK_IPU2_DI1_PRE_SEL>; + assigned-clock-parents = <&clks IMX6QDL_CLK_PLL5_VIDEO_DIV>, + <&clks IMX6QDL_CLK_PLL5_VIDEO_DIV>, + <&clks IMX6QDL_CLK_PLL2_PFD0_352M>, + <&clks IMX6QDL_CLK_PLL2_PFD0_352M>, + <&clks IMX6QDL_CLK_PLL2_PFD0_352M>, + <&clks IMX6QDL_CLK_PLL2_PFD0_352M>; +}; diff --git a/arch/arm/boot/dts/mmp3-dell-ariel.dts b/arch/arm/boot/dts/mmp3-dell-ariel.dts index 15449c72c042..b0ec14c42164 100644 --- a/arch/arm/boot/dts/mmp3-dell-ariel.dts +++ b/arch/arm/boot/dts/mmp3-dell-ariel.dts @@ -98,19 +98,19 @@ status = "okay"; }; -&ssp3 { +&ssp1 { status = "okay"; - cs-gpios = <&gpio 46 GPIO_ACTIVE_HIGH>; + cs-gpios = <&gpio 46 GPIO_ACTIVE_LOW>; firmware-flash@0 { - compatible = "st,m25p80", "jedec,spi-nor"; + compatible = "winbond,w25q32", "jedec,spi-nor"; reg = <0>; - spi-max-frequency = <40000000>; + spi-max-frequency = <104000000>; m25p,fast-read; }; }; -&ssp4 { - cs-gpios = <&gpio 56 GPIO_ACTIVE_HIGH>; +&ssp2 { + cs-gpios = <&gpio 56 GPIO_ACTIVE_LOW>; status = "okay"; }; diff --git a/arch/arm/boot/dts/mmp3.dtsi b/arch/arm/boot/dts/mmp3.dtsi index 9b5087a95e73..826f0a577859 100644 --- a/arch/arm/boot/dts/mmp3.dtsi +++ b/arch/arm/boot/dts/mmp3.dtsi @@ -202,8 +202,7 @@ }; hsic_phy0: hsic-phy@f0001800 { - compatible = "marvell,mmp3-hsic-phy", - "usb-nop-xceiv"; + compatible = "marvell,mmp3-hsic-phy"; reg = <0xf0001800 0x40>; #phy-cells = <0>; status = "disabled"; @@ -224,8 +223,7 @@ }; hsic_phy1: hsic-phy@f0002800 { - compatible = "marvell,mmp3-hsic-phy", - "usb-nop-xceiv"; + compatible = "marvell,mmp3-hsic-phy"; reg = <0xf0002800 0x40>; #phy-cells = <0>; status = "disabled"; @@ -531,7 +529,7 @@ }; soc_clocks: clocks@d4050000 { - compatible = "marvell,mmp2-clock"; + compatible = "marvell,mmp3-clock"; reg = <0xd4050000 0x1000>, <0xd4282800 0x400>, <0xd4015000 0x1000>; diff --git a/arch/arm/include/asm/assembler.h b/arch/arm/include/asm/assembler.h index 99929122dad7..3546d294d55f 100644 --- a/arch/arm/include/asm/assembler.h +++ b/arch/arm/include/asm/assembler.h @@ -18,11 +18,11 @@ #endif #include <asm/ptrace.h> -#include <asm/domain.h> #include <asm/opcodes-virt.h> #include <asm/asm-offsets.h> #include <asm/page.h> #include <asm/thread_info.h> +#include <asm/uaccess-asm.h> #define IOMEM(x) (x) @@ -446,79 +446,6 @@ THUMB( orr \reg , \reg , #PSR_T_BIT ) .size \name , . - \name .endm - .macro csdb -#ifdef CONFIG_THUMB2_KERNEL - .inst.w 0xf3af8014 -#else - .inst 0xe320f014 -#endif - .endm - - .macro check_uaccess, addr:req, size:req, limit:req, tmp:req, bad:req -#ifndef CONFIG_CPU_USE_DOMAINS - adds \tmp, \addr, #\size - 1 - sbcscc \tmp, \tmp, \limit - bcs \bad -#ifdef CONFIG_CPU_SPECTRE - movcs \addr, #0 - csdb -#endif -#endif - .endm - - .macro uaccess_mask_range_ptr, addr:req, size:req, limit:req, tmp:req -#ifdef CONFIG_CPU_SPECTRE - sub \tmp, \limit, #1 - subs \tmp, \tmp, \addr @ tmp = limit - 1 - addr - addhs \tmp, \tmp, #1 @ if (tmp >= 0) { - subshs \tmp, \tmp, \size @ tmp = limit - (addr + size) } - movlo \addr, #0 @ if (tmp < 0) addr = NULL - csdb -#endif - .endm - - .macro uaccess_disable, tmp, isb=1 -#ifdef CONFIG_CPU_SW_DOMAIN_PAN - /* - * Whenever we re-enter userspace, the domains should always be - * set appropriately. - */ - mov \tmp, #DACR_UACCESS_DISABLE - mcr p15, 0, \tmp, c3, c0, 0 @ Set domain register - .if \isb - instr_sync - .endif -#endif - .endm - - .macro uaccess_enable, tmp, isb=1 -#ifdef CONFIG_CPU_SW_DOMAIN_PAN - /* - * Whenever we re-enter userspace, the domains should always be - * set appropriately. - */ - mov \tmp, #DACR_UACCESS_ENABLE - mcr p15, 0, \tmp, c3, c0, 0 - .if \isb - instr_sync - .endif -#endif - .endm - - .macro uaccess_save, tmp -#ifdef CONFIG_CPU_SW_DOMAIN_PAN - mrc p15, 0, \tmp, c3, c0, 0 - str \tmp, [sp, #SVC_DACR] -#endif - .endm - - .macro uaccess_restore -#ifdef CONFIG_CPU_SW_DOMAIN_PAN - ldr r0, [sp, #SVC_DACR] - mcr p15, 0, r0, c3, c0, 0 -#endif - .endm - .irp c,,eq,ne,cs,cc,mi,pl,vs,vc,hi,ls,ge,lt,gt,le,hs,lo .macro ret\c, reg #if __LINUX_ARM_ARCH__ < 6 diff --git a/arch/arm/include/asm/uaccess-asm.h b/arch/arm/include/asm/uaccess-asm.h new file mode 100644 index 000000000000..907571fd05c6 --- /dev/null +++ b/arch/arm/include/asm/uaccess-asm.h @@ -0,0 +1,117 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ + +#ifndef __ASM_UACCESS_ASM_H__ +#define __ASM_UACCESS_ASM_H__ + +#include <asm/asm-offsets.h> +#include <asm/domain.h> +#include <asm/memory.h> +#include <asm/thread_info.h> + + .macro csdb +#ifdef CONFIG_THUMB2_KERNEL + .inst.w 0xf3af8014 +#else + .inst 0xe320f014 +#endif + .endm + + .macro check_uaccess, addr:req, size:req, limit:req, tmp:req, bad:req +#ifndef CONFIG_CPU_USE_DOMAINS + adds \tmp, \addr, #\size - 1 + sbcscc \tmp, \tmp, \limit + bcs \bad +#ifdef CONFIG_CPU_SPECTRE + movcs \addr, #0 + csdb +#endif +#endif + .endm + + .macro uaccess_mask_range_ptr, addr:req, size:req, limit:req, tmp:req +#ifdef CONFIG_CPU_SPECTRE + sub \tmp, \limit, #1 + subs \tmp, \tmp, \addr @ tmp = limit - 1 - addr + addhs \tmp, \tmp, #1 @ if (tmp >= 0) { + subshs \tmp, \tmp, \size @ tmp = limit - (addr + size) } + movlo \addr, #0 @ if (tmp < 0) addr = NULL + csdb +#endif + .endm + + .macro uaccess_disable, tmp, isb=1 +#ifdef CONFIG_CPU_SW_DOMAIN_PAN + /* + * Whenever we re-enter userspace, the domains should always be + * set appropriately. + */ + mov \tmp, #DACR_UACCESS_DISABLE + mcr p15, 0, \tmp, c3, c0, 0 @ Set domain register + .if \isb + instr_sync + .endif +#endif + .endm + + .macro uaccess_enable, tmp, isb=1 +#ifdef CONFIG_CPU_SW_DOMAIN_PAN + /* + * Whenever we re-enter userspace, the domains should always be + * set appropriately. + */ + mov \tmp, #DACR_UACCESS_ENABLE + mcr p15, 0, \tmp, c3, c0, 0 + .if \isb + instr_sync + .endif +#endif + .endm + +#if defined(CONFIG_CPU_SW_DOMAIN_PAN) || defined(CONFIG_CPU_USE_DOMAINS) +#define DACR(x...) x +#else +#define DACR(x...) +#endif + + /* + * Save the address limit on entry to a privileged exception. + * + * If we are using the DACR for kernel access by the user accessors + * (CONFIG_CPU_USE_DOMAINS=y), always reset the DACR kernel domain + * back to client mode, whether or not \disable is set. + * + * If we are using SW PAN, set the DACR user domain to no access + * if \disable is set. + */ + .macro uaccess_entry, tsk, tmp0, tmp1, tmp2, disable + ldr \tmp1, [\tsk, #TI_ADDR_LIMIT] + mov \tmp2, #TASK_SIZE + str \tmp2, [\tsk, #TI_ADDR_LIMIT] + DACR( mrc p15, 0, \tmp0, c3, c0, 0) + DACR( str \tmp0, [sp, #SVC_DACR]) + str \tmp1, [sp, #SVC_ADDR_LIMIT] + .if \disable && IS_ENABLED(CONFIG_CPU_SW_DOMAIN_PAN) + /* kernel=client, user=no access */ + mov \tmp2, #DACR_UACCESS_DISABLE + mcr p15, 0, \tmp2, c3, c0, 0 + instr_sync + .elseif IS_ENABLED(CONFIG_CPU_USE_DOMAINS) + /* kernel=client */ + bic \tmp2, \tmp0, #domain_mask(DOMAIN_KERNEL) + orr \tmp2, \tmp2, #domain_val(DOMAIN_KERNEL, DOMAIN_CLIENT) + mcr p15, 0, \tmp2, c3, c0, 0 + instr_sync + .endif + .endm + + /* Restore the user access state previously saved by uaccess_entry */ + .macro uaccess_exit, tsk, tmp0, tmp1 + ldr \tmp1, [sp, #SVC_ADDR_LIMIT] + DACR( ldr \tmp0, [sp, #SVC_DACR]) + str \tmp1, [\tsk, #TI_ADDR_LIMIT] + DACR( mcr p15, 0, \tmp0, c3, c0, 0) + .endm + +#undef DACR + +#endif /* __ASM_UACCESS_ASM_H__ */ diff --git a/arch/arm/kernel/atags_proc.c b/arch/arm/kernel/atags_proc.c index 4247ebf4b893..3c2faf2bd124 100644 --- a/arch/arm/kernel/atags_proc.c +++ b/arch/arm/kernel/atags_proc.c @@ -42,7 +42,7 @@ static int __init init_atags_procfs(void) size_t size; if (tag->hdr.tag != ATAG_CORE) { - pr_info("No ATAGs?"); + pr_info("No ATAGs?\n"); return -EINVAL; } diff --git a/arch/arm/kernel/entry-armv.S b/arch/arm/kernel/entry-armv.S index 77f54830554c..55a47df04773 100644 --- a/arch/arm/kernel/entry-armv.S +++ b/arch/arm/kernel/entry-armv.S @@ -27,6 +27,7 @@ #include <asm/unistd.h> #include <asm/tls.h> #include <asm/system_info.h> +#include <asm/uaccess-asm.h> #include "entry-header.S" #include <asm/entry-macro-multi.S> @@ -179,15 +180,7 @@ ENDPROC(__und_invalid) stmia r7, {r2 - r6} get_thread_info tsk - ldr r0, [tsk, #TI_ADDR_LIMIT] - mov r1, #TASK_SIZE - str r1, [tsk, #TI_ADDR_LIMIT] - str r0, [sp, #SVC_ADDR_LIMIT] - - uaccess_save r0 - .if \uaccess - uaccess_disable r0 - .endif + uaccess_entry tsk, r0, r1, r2, \uaccess .if \trace #ifdef CONFIG_TRACE_IRQFLAGS diff --git a/arch/arm/kernel/entry-header.S b/arch/arm/kernel/entry-header.S index 32051ec5b33f..40db0f9188b6 100644 --- a/arch/arm/kernel/entry-header.S +++ b/arch/arm/kernel/entry-header.S @@ -6,6 +6,7 @@ #include <asm/asm-offsets.h> #include <asm/errno.h> #include <asm/thread_info.h> +#include <asm/uaccess-asm.h> #include <asm/v7m.h> @ Bad Abort numbers @@ -217,9 +218,7 @@ blne trace_hardirqs_off #endif .endif - ldr r1, [sp, #SVC_ADDR_LIMIT] - uaccess_restore - str r1, [tsk, #TI_ADDR_LIMIT] + uaccess_exit tsk, r0, r1 #ifndef CONFIG_THUMB2_KERNEL @ ARM mode SVC restore @@ -263,9 +262,7 @@ @ on the stack remains correct). @ .macro svc_exit_via_fiq - ldr r1, [sp, #SVC_ADDR_LIMIT] - uaccess_restore - str r1, [tsk, #TI_ADDR_LIMIT] + uaccess_exit tsk, r0, r1 #ifndef CONFIG_THUMB2_KERNEL @ ARM mode restore mov r0, sp diff --git a/arch/arm/kernel/ptrace.c b/arch/arm/kernel/ptrace.c index b606cded90cd..4cc6a7eff635 100644 --- a/arch/arm/kernel/ptrace.c +++ b/arch/arm/kernel/ptrace.c @@ -219,8 +219,8 @@ static struct undef_hook arm_break_hook = { }; static struct undef_hook thumb_break_hook = { - .instr_mask = 0xffff, - .instr_val = 0xde01, + .instr_mask = 0xffffffff, + .instr_val = 0x0000de01, .cpsr_mask = PSR_T_BIT, .cpsr_val = PSR_T_BIT, .fn = break_trap, diff --git a/arch/arm64/boot/dts/mediatek/mt8173.dtsi b/arch/arm64/boot/dts/mediatek/mt8173.dtsi index ccb8e88a60c5..d819e44d94a8 100644 --- a/arch/arm64/boot/dts/mediatek/mt8173.dtsi +++ b/arch/arm64/boot/dts/mediatek/mt8173.dtsi @@ -1402,8 +1402,8 @@ "venc_lt_sel"; assigned-clocks = <&topckgen CLK_TOP_VENC_SEL>, <&topckgen CLK_TOP_VENC_LT_SEL>; - assigned-clock-parents = <&topckgen CLK_TOP_VENCPLL_D2>, - <&topckgen CLK_TOP_UNIVPLL1_D2>; + assigned-clock-parents = <&topckgen CLK_TOP_VCODECPLL>, + <&topckgen CLK_TOP_VCODECPLL_370P5>; }; jpegdec: jpegdec@18004000 { diff --git a/arch/arm64/boot/dts/qcom/sdm845-cheza.dtsi b/arch/arm64/boot/dts/qcom/sdm845-cheza.dtsi index 9070be43a309..07081da2c83e 100644 --- a/arch/arm64/boot/dts/qcom/sdm845-cheza.dtsi +++ b/arch/arm64/boot/dts/qcom/sdm845-cheza.dtsi @@ -631,6 +631,11 @@ ap_ts_i2c: &i2c14 { status = "okay"; }; +&mss_pil { + iommus = <&apps_smmu 0x780 0x1>, + <&apps_smmu 0x724 0x3>; +}; + &pm8998_pwrkey { status = "disabled"; }; diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c index 061f60fe452f..bb813d06114a 100644 --- a/arch/arm64/kernel/smp.c +++ b/arch/arm64/kernel/smp.c @@ -176,7 +176,7 @@ int __cpu_up(unsigned int cpu, struct task_struct *idle) panic("CPU%u detected unsupported configuration\n", cpu); } - return ret; + return -EIO; } static void init_gic_priority_masking(void) diff --git a/arch/csky/abiv1/inc/abi/entry.h b/arch/csky/abiv1/inc/abi/entry.h index 61d94ec7dd16..13c23e2c707c 100644 --- a/arch/csky/abiv1/inc/abi/entry.h +++ b/arch/csky/abiv1/inc/abi/entry.h @@ -80,7 +80,6 @@ .endm .macro RESTORE_ALL - psrclr ie ldw lr, (sp, 4) ldw a0, (sp, 8) mtcr a0, epc @@ -175,9 +174,4 @@ movi r6, 0 cpwcr r6, cpcr31 .endm - -.macro ANDI_R3 rx, imm - lsri \rx, 3 - andi \rx, (\imm >> 3) -.endm #endif /* __ASM_CSKY_ENTRY_H */ diff --git a/arch/csky/abiv2/inc/abi/entry.h b/arch/csky/abiv2/inc/abi/entry.h index ab63c41abcca..4fdd6c12e7ff 100644 --- a/arch/csky/abiv2/inc/abi/entry.h +++ b/arch/csky/abiv2/inc/abi/entry.h @@ -13,6 +13,8 @@ #define LSAVE_A1 28 #define LSAVE_A2 32 #define LSAVE_A3 36 +#define LSAVE_A4 40 +#define LSAVE_A5 44 #define KSPTOUSP #define USPTOKSP @@ -63,7 +65,6 @@ .endm .macro RESTORE_ALL - psrclr ie ldw tls, (sp, 0) ldw lr, (sp, 4) ldw a0, (sp, 8) @@ -301,9 +302,4 @@ jmpi 3f /* jump to va */ 3: .endm - -.macro ANDI_R3 rx, imm - lsri \rx, 3 - andi \rx, (\imm >> 3) -.endm #endif /* __ASM_CSKY_ENTRY_H */ diff --git a/arch/csky/include/asm/thread_info.h b/arch/csky/include/asm/thread_info.h index 5c61e84e790f..8980e4e64391 100644 --- a/arch/csky/include/asm/thread_info.h +++ b/arch/csky/include/asm/thread_info.h @@ -81,4 +81,10 @@ static inline struct thread_info *current_thread_info(void) #define _TIF_RESTORE_SIGMASK (1 << TIF_RESTORE_SIGMASK) #define _TIF_SECCOMP (1 << TIF_SECCOMP) +#define _TIF_WORK_MASK (_TIF_NEED_RESCHED | _TIF_SIGPENDING | \ + _TIF_NOTIFY_RESUME | _TIF_UPROBE) + +#define _TIF_SYSCALL_WORK (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT | \ + _TIF_SYSCALL_TRACEPOINT) + #endif /* _ASM_CSKY_THREAD_INFO_H */ diff --git a/arch/csky/kernel/entry.S b/arch/csky/kernel/entry.S index 3760397fdd3d..f13800383a19 100644 --- a/arch/csky/kernel/entry.S +++ b/arch/csky/kernel/entry.S @@ -128,39 +128,41 @@ tlbop_end 1 ENTRY(csky_systemcall) SAVE_ALL TRAP0_SIZE zero_fp -#ifdef CONFIG_RSEQ_DEBUG - mov a0, sp - jbsr rseq_syscall -#endif psrset ee, ie - lrw r11, __NR_syscalls - cmphs syscallid, r11 /* Check nr of syscall */ - bt ret_from_exception + lrw r9, __NR_syscalls + cmphs syscallid, r9 /* Check nr of syscall */ + bt 1f - lrw r13, sys_call_table - ixw r13, syscallid - ldw r11, (r13) - cmpnei r11, 0 + lrw r9, sys_call_table + ixw r9, syscallid + ldw syscallid, (r9) + cmpnei syscallid, 0 bf ret_from_exception mov r9, sp bmaski r10, THREAD_SHIFT andn r9, r10 - ldw r12, (r9, TINFO_FLAGS) - ANDI_R3 r12, (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_TRACEPOINT | _TIF_SYSCALL_AUDIT) - cmpnei r12, 0 + ldw r10, (r9, TINFO_FLAGS) + lrw r9, _TIF_SYSCALL_WORK + and r10, r9 + cmpnei r10, 0 bt csky_syscall_trace #if defined(__CSKYABIV2__) subi sp, 8 stw r5, (sp, 0x4) stw r4, (sp, 0x0) - jsr r11 /* Do system call */ + jsr syscallid /* Do system call */ addi sp, 8 #else - jsr r11 + jsr syscallid #endif stw a0, (sp, LSAVE_A0) /* Save return value */ +1: +#ifdef CONFIG_DEBUG_RSEQ + mov a0, sp + jbsr rseq_syscall +#endif jmpi ret_from_exception csky_syscall_trace: @@ -173,18 +175,23 @@ csky_syscall_trace: ldw a3, (sp, LSAVE_A3) #if defined(__CSKYABIV2__) subi sp, 8 - stw r5, (sp, 0x4) - stw r4, (sp, 0x0) + ldw r9, (sp, LSAVE_A4) + stw r9, (sp, 0x0) + ldw r9, (sp, LSAVE_A5) + stw r9, (sp, 0x4) + jsr syscallid /* Do system call */ + addi sp, 8 #else ldw r6, (sp, LSAVE_A4) ldw r7, (sp, LSAVE_A5) -#endif - jsr r11 /* Do system call */ -#if defined(__CSKYABIV2__) - addi sp, 8 + jsr syscallid /* Do system call */ #endif stw a0, (sp, LSAVE_A0) /* Save return value */ +#ifdef CONFIG_DEBUG_RSEQ + mov a0, sp + jbsr rseq_syscall +#endif mov a0, sp /* right now, sp --> pt_regs */ jbsr syscall_trace_exit br ret_from_exception @@ -200,18 +207,20 @@ ENTRY(ret_from_fork) mov r9, sp bmaski r10, THREAD_SHIFT andn r9, r10 - ldw r12, (r9, TINFO_FLAGS) - ANDI_R3 r12, (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_TRACEPOINT | _TIF_SYSCALL_AUDIT) - cmpnei r12, 0 + ldw r10, (r9, TINFO_FLAGS) + lrw r9, _TIF_SYSCALL_WORK + and r10, r9 + cmpnei r10, 0 bf ret_from_exception mov a0, sp /* sp = pt_regs pointer */ jbsr syscall_trace_exit ret_from_exception: - ld syscallid, (sp, LSAVE_PSR) - btsti syscallid, 31 - bt 1f + psrclr ie + ld r9, (sp, LSAVE_PSR) + btsti r9, 31 + bt 1f /* * Load address of current->thread_info, Then get address of task_struct * Get task_needreshed in task_struct @@ -220,11 +229,24 @@ ret_from_exception: bmaski r10, THREAD_SHIFT andn r9, r10 - ldw r12, (r9, TINFO_FLAGS) - andi r12, (_TIF_SIGPENDING | _TIF_NOTIFY_RESUME | _TIF_NEED_RESCHED | _TIF_UPROBE) - cmpnei r12, 0 + ldw r10, (r9, TINFO_FLAGS) + lrw r9, _TIF_WORK_MASK + and r10, r9 + cmpnei r10, 0 bt exit_work 1: +#ifdef CONFIG_PREEMPTION + mov r9, sp + bmaski r10, THREAD_SHIFT + andn r9, r10 + + ldw r10, (r9, TINFO_PREEMPT) + cmpnei r10, 0 + bt 2f + jbsr preempt_schedule_irq /* irq en/disable is done inside */ +2: +#endif + #ifdef CONFIG_TRACE_IRQFLAGS ld r10, (sp, LSAVE_PSR) btsti r10, 6 @@ -235,14 +257,15 @@ ret_from_exception: RESTORE_ALL exit_work: - lrw syscallid, ret_from_exception - mov lr, syscallid + lrw r9, ret_from_exception + mov lr, r9 - btsti r12, TIF_NEED_RESCHED + btsti r10, TIF_NEED_RESCHED bt work_resched + psrset ie mov a0, sp - mov a1, r12 + mov a1, r10 jmpi do_notify_resume work_resched: @@ -291,34 +314,10 @@ ENTRY(csky_irq) jbsr trace_hardirqs_off #endif -#ifdef CONFIG_PREEMPTION - mov r9, sp /* Get current stack pointer */ - bmaski r10, THREAD_SHIFT - andn r9, r10 /* Get thread_info */ - - /* - * Get task_struct->stack.preempt_count for current, - * and increase 1. - */ - ldw r12, (r9, TINFO_PREEMPT) - addi r12, 1 - stw r12, (r9, TINFO_PREEMPT) -#endif mov a0, sp jbsr csky_do_IRQ -#ifdef CONFIG_PREEMPTION - subi r12, 1 - stw r12, (r9, TINFO_PREEMPT) - cmpnei r12, 0 - bt 2f - ldw r12, (r9, TINFO_FLAGS) - btsti r12, TIF_NEED_RESCHED - bf 2f - jbsr preempt_schedule_irq /* irq en/disable is done inside */ -#endif -2: jmpi ret_from_exception /* diff --git a/arch/ia64/include/asm/device.h b/arch/ia64/include/asm/device.h index 410a769ece95..3eb397415381 100644 --- a/arch/ia64/include/asm/device.h +++ b/arch/ia64/include/asm/device.h @@ -6,7 +6,7 @@ #define _ASM_IA64_DEVICE_H struct dev_archdata { -#ifdef CONFIG_INTEL_IOMMU +#ifdef CONFIG_IOMMU_API void *iommu; /* hook for IOMMU specific extension */ #endif }; diff --git a/arch/parisc/mm/init.c b/arch/parisc/mm/init.c index 5224fb38d766..01d7071b23f7 100644 --- a/arch/parisc/mm/init.c +++ b/arch/parisc/mm/init.c @@ -562,7 +562,7 @@ void __init mem_init(void) > BITS_PER_LONG); high_memory = __va((max_pfn << PAGE_SHIFT)); - set_max_mapnr(page_to_pfn(virt_to_page(high_memory - 1)) + 1); + set_max_mapnr(max_low_pfn); memblock_free_all(); #ifdef CONFIG_PA11 diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index d13b5328ca10..b29d7cb38368 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -126,6 +126,7 @@ config PPC select ARCH_HAS_MMIOWB if PPC64 select ARCH_HAS_PHYS_TO_DMA select ARCH_HAS_PMEM_API + select ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE select ARCH_HAS_PTE_DEVMAP if PPC_BOOK3S_64 select ARCH_HAS_PTE_SPECIAL select ARCH_HAS_MEMBARRIER_CALLBACKS diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile index 1c4385852d3d..244542ae2a91 100644 --- a/arch/powerpc/kernel/Makefile +++ b/arch/powerpc/kernel/Makefile @@ -162,6 +162,9 @@ UBSAN_SANITIZE_kprobes.o := n GCOV_PROFILE_kprobes-ftrace.o := n KCOV_INSTRUMENT_kprobes-ftrace.o := n UBSAN_SANITIZE_kprobes-ftrace.o := n +GCOV_PROFILE_syscall_64.o := n +KCOV_INSTRUMENT_syscall_64.o := n +UBSAN_SANITIZE_syscall_64.o := n UBSAN_SANITIZE_vdso.o := n # Necessary for booting with kcov enabled on book3e machines diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S index b0ad930cbae5..ebeebab74b56 100644 --- a/arch/powerpc/kernel/exceptions-64s.S +++ b/arch/powerpc/kernel/exceptions-64s.S @@ -2411,6 +2411,7 @@ EXC_COMMON_BEGIN(facility_unavailable_common) GEN_COMMON facility_unavailable addi r3,r1,STACK_FRAME_OVERHEAD bl facility_unavailable_exception + REST_NVGPRS(r1) /* instruction emulation may change GPRs */ b interrupt_return GEN_KVM facility_unavailable @@ -2440,6 +2441,7 @@ EXC_COMMON_BEGIN(h_facility_unavailable_common) GEN_COMMON h_facility_unavailable addi r3,r1,STACK_FRAME_OVERHEAD bl facility_unavailable_exception + REST_NVGPRS(r1) /* XXX Shouldn't be necessary in practice */ b interrupt_return GEN_KVM h_facility_unavailable diff --git a/arch/x86/include/asm/device.h b/arch/x86/include/asm/device.h index 7e31f7f1bb06..49bd6cf3eec9 100644 --- a/arch/x86/include/asm/device.h +++ b/arch/x86/include/asm/device.h @@ -3,7 +3,7 @@ #define _ASM_X86_DEVICE_H struct dev_archdata { -#if defined(CONFIG_INTEL_IOMMU) || defined(CONFIG_AMD_IOMMU) +#ifdef CONFIG_IOMMU_API void *iommu; /* hook for IOMMU specific extension */ #endif }; diff --git a/arch/x86/include/asm/dma.h b/arch/x86/include/asm/dma.h index 00f7cf45e699..8e95aa4b0d17 100644 --- a/arch/x86/include/asm/dma.h +++ b/arch/x86/include/asm/dma.h @@ -74,7 +74,7 @@ #define MAX_DMA_PFN ((16UL * 1024 * 1024) >> PAGE_SHIFT) /* 4GB broken PCI/AGP hardware bus master zone */ -#define MAX_DMA32_PFN ((4UL * 1024 * 1024 * 1024) >> PAGE_SHIFT) +#define MAX_DMA32_PFN (1UL << (32 - PAGE_SHIFT)) #ifdef CONFIG_X86_32 /* The maximum address that we can perform a DMA transfer to on this platform */ diff --git a/arch/x86/include/asm/io_bitmap.h b/arch/x86/include/asm/io_bitmap.h index 07344d82e88e..ac1a99ffbd8d 100644 --- a/arch/x86/include/asm/io_bitmap.h +++ b/arch/x86/include/asm/io_bitmap.h @@ -17,7 +17,7 @@ struct task_struct; #ifdef CONFIG_X86_IOPL_IOPERM void io_bitmap_share(struct task_struct *tsk); -void io_bitmap_exit(void); +void io_bitmap_exit(struct task_struct *tsk); void native_tss_update_io_bitmap(void); @@ -29,7 +29,7 @@ void native_tss_update_io_bitmap(void); #else static inline void io_bitmap_share(struct task_struct *tsk) { } -static inline void io_bitmap_exit(void) { } +static inline void io_bitmap_exit(struct task_struct *tsk) { } static inline void tss_update_io_bitmap(void) { } #endif diff --git a/arch/x86/include/uapi/asm/unistd.h b/arch/x86/include/uapi/asm/unistd.h index 196fdd02b8b1..be5e2e747f50 100644 --- a/arch/x86/include/uapi/asm/unistd.h +++ b/arch/x86/include/uapi/asm/unistd.h @@ -2,8 +2,15 @@ #ifndef _UAPI_ASM_X86_UNISTD_H #define _UAPI_ASM_X86_UNISTD_H -/* x32 syscall flag bit */ -#define __X32_SYSCALL_BIT 0x40000000UL +/* + * x32 syscall flag bit. Some user programs expect syscall NR macros + * and __X32_SYSCALL_BIT to have type int, even though syscall numbers + * are, for practical purposes, unsigned long. + * + * Fortunately, expressions like (nr & ~__X32_SYSCALL_BIT) do the right + * thing regardless. + */ +#define __X32_SYSCALL_BIT 0x40000000 #ifndef __KERNEL__ # ifdef __i386__ diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c index 32b153d38748..6a54e83d5589 100644 --- a/arch/x86/kernel/fpu/xstate.c +++ b/arch/x86/kernel/fpu/xstate.c @@ -957,18 +957,31 @@ static inline bool xfeatures_mxcsr_quirk(u64 xfeatures) return true; } -/* - * This is similar to user_regset_copyout(), but will not add offset to - * the source data pointer or increment pos, count, kbuf, and ubuf. - */ -static inline void -__copy_xstate_to_kernel(void *kbuf, const void *data, - unsigned int offset, unsigned int size, unsigned int size_total) +static void fill_gap(unsigned to, void **kbuf, unsigned *pos, unsigned *count) { - if (offset < size_total) { - unsigned int copy = min(size, size_total - offset); + if (*pos < to) { + unsigned size = to - *pos; + + if (size > *count) + size = *count; + memcpy(*kbuf, (void *)&init_fpstate.xsave + *pos, size); + *kbuf += size; + *pos += size; + *count -= size; + } +} - memcpy(kbuf + offset, data, copy); +static void copy_part(unsigned offset, unsigned size, void *from, + void **kbuf, unsigned *pos, unsigned *count) +{ + fill_gap(offset, kbuf, pos, count); + if (size > *count) + size = *count; + if (size) { + memcpy(*kbuf, from, size); + *kbuf += size; + *pos += size; + *count -= size; } } @@ -981,8 +994,9 @@ __copy_xstate_to_kernel(void *kbuf, const void *data, */ int copy_xstate_to_kernel(void *kbuf, struct xregs_state *xsave, unsigned int offset_start, unsigned int size_total) { - unsigned int offset, size; struct xstate_header header; + const unsigned off_mxcsr = offsetof(struct fxregs_state, mxcsr); + unsigned count = size_total; int i; /* @@ -998,46 +1012,42 @@ int copy_xstate_to_kernel(void *kbuf, struct xregs_state *xsave, unsigned int of header.xfeatures = xsave->header.xfeatures; header.xfeatures &= ~XFEATURE_MASK_SUPERVISOR; + if (header.xfeatures & XFEATURE_MASK_FP) + copy_part(0, off_mxcsr, + &xsave->i387, &kbuf, &offset_start, &count); + if (header.xfeatures & (XFEATURE_MASK_SSE | XFEATURE_MASK_YMM)) + copy_part(off_mxcsr, MXCSR_AND_FLAGS_SIZE, + &xsave->i387.mxcsr, &kbuf, &offset_start, &count); + if (header.xfeatures & XFEATURE_MASK_FP) + copy_part(offsetof(struct fxregs_state, st_space), 128, + &xsave->i387.st_space, &kbuf, &offset_start, &count); + if (header.xfeatures & XFEATURE_MASK_SSE) + copy_part(xstate_offsets[XFEATURE_MASK_SSE], 256, + &xsave->i387.xmm_space, &kbuf, &offset_start, &count); + /* + * Fill xsave->i387.sw_reserved value for ptrace frame: + */ + copy_part(offsetof(struct fxregs_state, sw_reserved), 48, + xstate_fx_sw_bytes, &kbuf, &offset_start, &count); /* * Copy xregs_state->header: */ - offset = offsetof(struct xregs_state, header); - size = sizeof(header); - - __copy_xstate_to_kernel(kbuf, &header, offset, size, size_total); + copy_part(offsetof(struct xregs_state, header), sizeof(header), + &header, &kbuf, &offset_start, &count); - for (i = 0; i < XFEATURE_MAX; i++) { + for (i = FIRST_EXTENDED_XFEATURE; i < XFEATURE_MAX; i++) { /* * Copy only in-use xstates: */ if ((header.xfeatures >> i) & 1) { void *src = __raw_xsave_addr(xsave, i); - offset = xstate_offsets[i]; - size = xstate_sizes[i]; - - /* The next component has to fit fully into the output buffer: */ - if (offset + size > size_total) - break; - - __copy_xstate_to_kernel(kbuf, src, offset, size, size_total); + copy_part(xstate_offsets[i], xstate_sizes[i], + src, &kbuf, &offset_start, &count); } } - - if (xfeatures_mxcsr_quirk(header.xfeatures)) { - offset = offsetof(struct fxregs_state, mxcsr); - size = MXCSR_AND_FLAGS_SIZE; - __copy_xstate_to_kernel(kbuf, &xsave->i387.mxcsr, offset, size, size_total); - } - - /* - * Fill xsave->i387.sw_reserved value for ptrace frame: - */ - offset = offsetof(struct fxregs_state, sw_reserved); - size = sizeof(xstate_fx_sw_bytes); - - __copy_xstate_to_kernel(kbuf, xstate_fx_sw_bytes, offset, size, size_total); + fill_gap(size_total, &kbuf, &offset_start, &count); return 0; } diff --git a/arch/x86/kernel/ioport.c b/arch/x86/kernel/ioport.c index a53e7b4a7419..e2fab3ceb09f 100644 --- a/arch/x86/kernel/ioport.c +++ b/arch/x86/kernel/ioport.c @@ -33,15 +33,15 @@ void io_bitmap_share(struct task_struct *tsk) set_tsk_thread_flag(tsk, TIF_IO_BITMAP); } -static void task_update_io_bitmap(void) +static void task_update_io_bitmap(struct task_struct *tsk) { - struct thread_struct *t = ¤t->thread; + struct thread_struct *t = &tsk->thread; if (t->iopl_emul == 3 || t->io_bitmap) { /* TSS update is handled on exit to user space */ - set_thread_flag(TIF_IO_BITMAP); + set_tsk_thread_flag(tsk, TIF_IO_BITMAP); } else { - clear_thread_flag(TIF_IO_BITMAP); + clear_tsk_thread_flag(tsk, TIF_IO_BITMAP); /* Invalidate TSS */ preempt_disable(); tss_update_io_bitmap(); @@ -49,12 +49,12 @@ static void task_update_io_bitmap(void) } } -void io_bitmap_exit(void) +void io_bitmap_exit(struct task_struct *tsk) { - struct io_bitmap *iobm = current->thread.io_bitmap; + struct io_bitmap *iobm = tsk->thread.io_bitmap; - current->thread.io_bitmap = NULL; - task_update_io_bitmap(); + tsk->thread.io_bitmap = NULL; + task_update_io_bitmap(tsk); if (iobm && refcount_dec_and_test(&iobm->refcnt)) kfree(iobm); } @@ -102,7 +102,7 @@ long ksys_ioperm(unsigned long from, unsigned long num, int turn_on) if (!iobm) return -ENOMEM; refcount_set(&iobm->refcnt, 1); - io_bitmap_exit(); + io_bitmap_exit(current); } /* @@ -134,7 +134,7 @@ long ksys_ioperm(unsigned long from, unsigned long num, int turn_on) } /* All permissions dropped? */ if (max_long == UINT_MAX) { - io_bitmap_exit(); + io_bitmap_exit(current); return 0; } @@ -192,7 +192,7 @@ SYSCALL_DEFINE1(iopl, unsigned int, level) } t->iopl_emul = level; - task_update_io_bitmap(); + task_update_io_bitmap(current); return 0; } diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index 9da70b279dad..35638f1c5791 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -96,7 +96,7 @@ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src) } /* - * Free current thread data structures etc.. + * Free thread data structures etc.. */ void exit_thread(struct task_struct *tsk) { @@ -104,7 +104,7 @@ void exit_thread(struct task_struct *tsk) struct fpu *fpu = &t->fpu; if (test_thread_flag(TIF_IO_BITMAP)) - io_bitmap_exit(); + io_bitmap_exit(tsk); free_vm86(t); diff --git a/block/blk-core.c b/block/blk-core.c index 7e4a1da0715e..9bfaee050c82 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -891,14 +891,11 @@ generic_make_request_checks(struct bio *bio) } /* - * Non-mq queues do not honor REQ_NOWAIT, so complete a bio - * with BLK_STS_AGAIN status in order to catch -EAGAIN and - * to give a chance to the caller to repeat request gracefully. + * For a REQ_NOWAIT based request, return -EOPNOTSUPP + * if queue is not a request based queue. */ - if ((bio->bi_opf & REQ_NOWAIT) && !queue_is_mq(q)) { - status = BLK_STS_AGAIN; - goto end_io; - } + if ((bio->bi_opf & REQ_NOWAIT) && !queue_is_mq(q)) + goto not_supported; if (should_fail_bio(bio)) goto end_io; diff --git a/drivers/clk/qcom/Kconfig b/drivers/clk/qcom/Kconfig index 11ec6f466467..abb121f8de52 100644 --- a/drivers/clk/qcom/Kconfig +++ b/drivers/clk/qcom/Kconfig @@ -377,6 +377,7 @@ config SM_GCC_8150 config SM_GCC_8250 tristate "SM8250 Global Clock Controller" + select QCOM_GDSC help Support for the global clock controller on SM8250 devices. Say Y if you want to use peripheral devices such as UART, diff --git a/drivers/clk/qcom/gcc-sm8150.c b/drivers/clk/qcom/gcc-sm8150.c index ef98fdc51755..732bc7c937e6 100644 --- a/drivers/clk/qcom/gcc-sm8150.c +++ b/drivers/clk/qcom/gcc-sm8150.c @@ -76,8 +76,7 @@ static struct clk_alpha_pll_postdiv gpll0_out_even = { .clkr.hw.init = &(struct clk_init_data){ .name = "gpll0_out_even", .parent_data = &(const struct clk_parent_data){ - .fw_name = "bi_tcxo", - .name = "bi_tcxo", + .hw = &gpll0.clkr.hw, }, .num_parents = 1, .ops = &clk_trion_pll_postdiv_ops, diff --git a/drivers/crypto/chelsio/chtls/chtls_io.c b/drivers/crypto/chelsio/chtls/chtls_io.c index dccef3a2908b..e1401d9cc756 100644 --- a/drivers/crypto/chelsio/chtls/chtls_io.c +++ b/drivers/crypto/chelsio/chtls/chtls_io.c @@ -682,7 +682,7 @@ int chtls_push_frames(struct chtls_sock *csk, int comp) make_tx_data_wr(sk, skb, immdlen, len, credits_needed, completion); tp->snd_nxt += len; - tp->lsndtime = tcp_time_stamp(tp); + tp->lsndtime = tcp_jiffies32; if (completion) ULP_SKB_CB(skb)->flags &= ~ULPCB_FLAG_NEED_HDR; } else { diff --git a/drivers/gpio/gpio-bcm-kona.c b/drivers/gpio/gpio-bcm-kona.c index baee8c3f06ad..cf3687a7925f 100644 --- a/drivers/gpio/gpio-bcm-kona.c +++ b/drivers/gpio/gpio-bcm-kona.c @@ -625,7 +625,7 @@ static int bcm_kona_gpio_probe(struct platform_device *pdev) kona_gpio->reg_base = devm_platform_ioremap_resource(pdev, 0); if (IS_ERR(kona_gpio->reg_base)) { - ret = -ENXIO; + ret = PTR_ERR(kona_gpio->reg_base); goto err_irq_domain; } diff --git a/drivers/gpio/gpio-exar.c b/drivers/gpio/gpio-exar.c index da1ef0b1c291..b1accfba017d 100644 --- a/drivers/gpio/gpio-exar.c +++ b/drivers/gpio/gpio-exar.c @@ -148,8 +148,10 @@ static int gpio_exar_probe(struct platform_device *pdev) mutex_init(&exar_gpio->lock); index = ida_simple_get(&ida_index, 0, 0, GFP_KERNEL); - if (index < 0) - goto err_destroy; + if (index < 0) { + ret = index; + goto err_mutex_destroy; + } sprintf(exar_gpio->name, "exar_gpio%d", index); exar_gpio->gpio_chip.label = exar_gpio->name; @@ -176,6 +178,7 @@ static int gpio_exar_probe(struct platform_device *pdev) err_destroy: ida_simple_remove(&ida_index, index); +err_mutex_destroy: mutex_destroy(&exar_gpio->lock); return ret; } diff --git a/drivers/gpio/gpio-mlxbf2.c b/drivers/gpio/gpio-mlxbf2.c index 7b7085050219..da570e63589d 100644 --- a/drivers/gpio/gpio-mlxbf2.c +++ b/drivers/gpio/gpio-mlxbf2.c @@ -127,8 +127,8 @@ static int mlxbf2_gpio_lock_acquire(struct mlxbf2_gpio_context *gs) { u32 arm_gpio_lock_val; - spin_lock(&gs->gc.bgpio_lock); mutex_lock(yu_arm_gpio_lock_param.lock); + spin_lock(&gs->gc.bgpio_lock); arm_gpio_lock_val = readl(yu_arm_gpio_lock_param.io); @@ -136,8 +136,8 @@ static int mlxbf2_gpio_lock_acquire(struct mlxbf2_gpio_context *gs) * When lock active bit[31] is set, ModeX is write enabled */ if (YU_LOCK_ACTIVE_BIT(arm_gpio_lock_val)) { - mutex_unlock(yu_arm_gpio_lock_param.lock); spin_unlock(&gs->gc.bgpio_lock); + mutex_unlock(yu_arm_gpio_lock_param.lock); return -EINVAL; } @@ -152,8 +152,8 @@ static int mlxbf2_gpio_lock_acquire(struct mlxbf2_gpio_context *gs) static void mlxbf2_gpio_lock_release(struct mlxbf2_gpio_context *gs) { writel(YU_ARM_GPIO_LOCK_RELEASE, yu_arm_gpio_lock_param.io); - mutex_unlock(yu_arm_gpio_lock_param.lock); spin_unlock(&gs->gc.bgpio_lock); + mutex_unlock(yu_arm_gpio_lock_param.lock); } /* diff --git a/drivers/gpio/gpio-mvebu.c b/drivers/gpio/gpio-mvebu.c index 3c9f4fb3d5a2..bd65114eb170 100644 --- a/drivers/gpio/gpio-mvebu.c +++ b/drivers/gpio/gpio-mvebu.c @@ -782,6 +782,15 @@ static int mvebu_pwm_probe(struct platform_device *pdev, "marvell,armada-370-gpio")) return 0; + /* + * There are only two sets of PWM configuration registers for + * all the GPIO lines on those SoCs which this driver reserves + * for the first two GPIO chips. So if the resource is missing + * we can't treat it as an error. + */ + if (!platform_get_resource_byname(pdev, IORESOURCE_MEM, "pwm")) + return 0; + if (IS_ERR(mvchip->clk)) return PTR_ERR(mvchip->clk); @@ -804,12 +813,6 @@ static int mvebu_pwm_probe(struct platform_device *pdev, mvchip->mvpwm = mvpwm; mvpwm->mvchip = mvchip; - /* - * There are only two sets of PWM configuration registers for - * all the GPIO lines on those SoCs which this driver reserves - * for the first two GPIO chips. So if the resource is missing - * we can't treat it as an error. - */ mvpwm->membase = devm_platform_ioremap_resource_byname(pdev, "pwm"); if (IS_ERR(mvpwm->membase)) return PTR_ERR(mvpwm->membase); diff --git a/drivers/gpio/gpio-pxa.c b/drivers/gpio/gpio-pxa.c index 1361270ecf8c..0cb6600b8eee 100644 --- a/drivers/gpio/gpio-pxa.c +++ b/drivers/gpio/gpio-pxa.c @@ -660,8 +660,8 @@ static int pxa_gpio_probe(struct platform_device *pdev) pchip->irq1 = irq1; gpio_reg_base = devm_platform_ioremap_resource(pdev, 0); - if (!gpio_reg_base) - return -EINVAL; + if (IS_ERR(gpio_reg_base)) + return PTR_ERR(gpio_reg_base); clk = clk_get(&pdev->dev, NULL); if (IS_ERR(clk)) { diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c index 182136d98b97..c14f0784274a 100644 --- a/drivers/gpio/gpiolib.c +++ b/drivers/gpio/gpiolib.c @@ -729,6 +729,10 @@ static int linehandle_create(struct gpio_device *gdev, void __user *ip) if (ret) goto out_free_descs; } + + atomic_notifier_call_chain(&desc->gdev->notifier, + GPIOLINE_CHANGED_REQUESTED, desc); + dev_dbg(&gdev->dev, "registered chardev handle for line %d\n", offset); } @@ -1083,6 +1087,9 @@ static int lineevent_create(struct gpio_device *gdev, void __user *ip) if (ret) goto out_free_desc; + atomic_notifier_call_chain(&desc->gdev->notifier, + GPIOLINE_CHANGED_REQUESTED, desc); + le->irq = gpiod_to_irq(desc); if (le->irq <= 0) { ret = -ENODEV; @@ -2998,8 +3005,6 @@ static int gpiod_request_commit(struct gpio_desc *desc, const char *label) } done: spin_unlock_irqrestore(&gpio_lock, flags); - atomic_notifier_call_chain(&desc->gdev->notifier, - GPIOLINE_CHANGED_REQUESTED, desc); return ret; } @@ -4215,7 +4220,9 @@ int gpiochip_lock_as_irq(struct gpio_chip *gc, unsigned int offset) } } - if (test_bit(FLAG_IS_OUT, &desc->flags)) { + /* To be valid for IRQ the line needs to be input or open drain */ + if (test_bit(FLAG_IS_OUT, &desc->flags) && + !test_bit(FLAG_OPEN_DRAIN, &desc->flags)) { chip_err(gc, "%s: tried to flag a GPIO set as output for IRQ\n", __func__); @@ -4278,7 +4285,12 @@ void gpiochip_enable_irq(struct gpio_chip *gc, unsigned int offset) if (!IS_ERR(desc) && !WARN_ON(!test_bit(FLAG_USED_AS_IRQ, &desc->flags))) { - WARN_ON(test_bit(FLAG_IS_OUT, &desc->flags)); + /* + * We must not be output when using IRQ UNLESS we are + * open drain. + */ + WARN_ON(test_bit(FLAG_IS_OUT, &desc->flags) && + !test_bit(FLAG_OPEN_DRAIN, &desc->flags)); set_bit(FLAG_IRQ_IS_ENABLED, &desc->flags); } } @@ -4961,6 +4973,9 @@ struct gpio_desc *__must_check gpiod_get_index(struct device *dev, return ERR_PTR(ret); } + atomic_notifier_call_chain(&desc->gdev->notifier, + GPIOLINE_CHANGED_REQUESTED, desc); + return desc; } EXPORT_SYMBOL_GPL(gpiod_get_index); @@ -5026,6 +5041,9 @@ struct gpio_desc *fwnode_get_named_gpiod(struct fwnode_handle *fwnode, return ERR_PTR(ret); } + atomic_notifier_call_chain(&desc->gdev->notifier, + GPIOLINE_CHANGED_REQUESTED, desc); + return desc; } EXPORT_SYMBOL_GPL(fwnode_get_named_gpiod); diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h index 4a3049841086..c24cad3c64ed 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h +++ b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h @@ -1050,7 +1050,7 @@ void kfd_dec_compute_active(struct kfd_dev *dev); /* Check with device cgroup if @kfd device is accessible */ static inline int kfd_devcgroup_check_permission(struct kfd_dev *kfd) { -#if defined(CONFIG_CGROUP_DEVICE) +#if defined(CONFIG_CGROUP_DEVICE) || defined(CONFIG_CGROUP_BPF) struct drm_device *ddev = kfd->ddev; return devcgroup_check_permission(DEVCG_DEV_CHAR, ddev->driver->major, diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c index 28e651b173ab..7fc15b82fe48 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -7880,13 +7880,6 @@ static int dm_update_plane_state(struct dc *dc, return -EINVAL; } - if (new_plane_state->crtc_x <= -new_acrtc->max_cursor_width || - new_plane_state->crtc_y <= -new_acrtc->max_cursor_height) { - DRM_DEBUG_ATOMIC("Bad cursor position %d, %d\n", - new_plane_state->crtc_x, new_plane_state->crtc_y); - return -EINVAL; - } - return 0; } diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c index 82fc3d5b3b2a..416afb99529d 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c +++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c @@ -1684,6 +1684,8 @@ static void delay_cursor_until_vupdate(struct dc *dc, struct pipe_ctx *pipe_ctx) return; /* Stall out until the cursor update completes. */ + if (vupdate_end < vupdate_start) + vupdate_end += stream->timing.v_total; us_vupdate = (vupdate_end - vupdate_start + 1) * us_per_line; udelay(us_to_vupdate + us_vupdate); } diff --git a/drivers/gpu/drm/ingenic/ingenic-drm.c b/drivers/gpu/drm/ingenic/ingenic-drm.c index 1754c0547069..548cc25ea4ab 100644 --- a/drivers/gpu/drm/ingenic/ingenic-drm.c +++ b/drivers/gpu/drm/ingenic/ingenic-drm.c @@ -328,8 +328,8 @@ static int ingenic_drm_crtc_atomic_check(struct drm_crtc *crtc, if (!drm_atomic_crtc_needs_modeset(state)) return 0; - if (state->mode.hdisplay > priv->soc_info->max_height || - state->mode.vdisplay > priv->soc_info->max_width) + if (state->mode.hdisplay > priv->soc_info->max_width || + state->mode.vdisplay > priv->soc_info->max_height) return -EINVAL; rate = clk_round_rate(priv->pix_clk, @@ -474,7 +474,7 @@ static int ingenic_drm_encoder_atomic_check(struct drm_encoder *encoder, static irqreturn_t ingenic_drm_irq_handler(int irq, void *arg) { - struct ingenic_drm *priv = arg; + struct ingenic_drm *priv = drm_device_get_priv(arg); unsigned int state; regmap_read(priv->map, JZ_REG_LCD_STATE, &state); diff --git a/drivers/infiniband/core/rdma_core.c b/drivers/infiniband/core/rdma_core.c index bf8e149d3191..e0a5e897e4b1 100644 --- a/drivers/infiniband/core/rdma_core.c +++ b/drivers/infiniband/core/rdma_core.c @@ -153,9 +153,9 @@ static int uverbs_destroy_uobject(struct ib_uobject *uobj, uobj->context = NULL; /* - * For DESTROY the usecnt is held write locked, the caller is expected - * to put it unlock and put the object when done with it. Only DESTROY - * can remove the IDR handle. + * For DESTROY the usecnt is not changed, the caller is expected to + * manage it via uobj_put_destroy(). Only DESTROY can remove the IDR + * handle. */ if (reason != RDMA_REMOVE_DESTROY) atomic_set(&uobj->usecnt, 0); @@ -187,7 +187,7 @@ static int uverbs_destroy_uobject(struct ib_uobject *uobj, /* * This calls uverbs_destroy_uobject() using the RDMA_REMOVE_DESTROY * sequence. It should only be used from command callbacks. On success the - * caller must pair this with rdma_lookup_put_uobject(LOOKUP_WRITE). This + * caller must pair this with uobj_put_destroy(). This * version requires the caller to have already obtained an * LOOKUP_DESTROY uobject kref. */ @@ -198,6 +198,13 @@ int uobj_destroy(struct ib_uobject *uobj, struct uverbs_attr_bundle *attrs) down_read(&ufile->hw_destroy_rwsem); + /* + * Once the uobject is destroyed by RDMA_REMOVE_DESTROY then it is left + * write locked as the callers put it back with UVERBS_LOOKUP_DESTROY. + * This is because any other concurrent thread can still see the object + * in the xarray due to RCU. Leaving it locked ensures nothing else will + * touch it. + */ ret = uverbs_try_lock_object(uobj, UVERBS_LOOKUP_WRITE); if (ret) goto out_unlock; @@ -216,7 +223,7 @@ out_unlock: /* * uobj_get_destroy destroys the HW object and returns a handle to the uobj * with a NULL object pointer. The caller must pair this with - * uverbs_put_destroy. + * uobj_put_destroy(). */ struct ib_uobject *__uobj_get_destroy(const struct uverbs_api_object *obj, u32 id, struct uverbs_attr_bundle *attrs) @@ -250,8 +257,7 @@ int __uobj_perform_destroy(const struct uverbs_api_object *obj, u32 id, uobj = __uobj_get_destroy(obj, id, attrs); if (IS_ERR(uobj)) return PTR_ERR(uobj); - - rdma_lookup_put_uobject(uobj, UVERBS_LOOKUP_WRITE); + uobj_put_destroy(uobj); return 0; } diff --git a/drivers/infiniband/hw/mlx5/mr.c b/drivers/infiniband/hw/mlx5/mr.c index a401931189b7..44683073be0c 100644 --- a/drivers/infiniband/hw/mlx5/mr.c +++ b/drivers/infiniband/hw/mlx5/mr.c @@ -1439,6 +1439,7 @@ struct ib_mr *mlx5_ib_reg_user_mr(struct ib_pd *pd, u64 start, u64 length, if (is_odp_mr(mr)) { to_ib_umem_odp(mr->umem)->private = mr; + init_waitqueue_head(&mr->q_deferred_work); atomic_set(&mr->num_deferred_work, 0); err = xa_err(xa_store(&dev->odp_mkeys, mlx5_base_mkey(mr->mmkey.key), &mr->mmkey, diff --git a/drivers/infiniband/hw/qib/qib_sysfs.c b/drivers/infiniband/hw/qib/qib_sysfs.c index 568b21eb6ea1..021df0654ba7 100644 --- a/drivers/infiniband/hw/qib/qib_sysfs.c +++ b/drivers/infiniband/hw/qib/qib_sysfs.c @@ -760,7 +760,7 @@ int qib_create_port_files(struct ib_device *ibdev, u8 port_num, qib_dev_err(dd, "Skipping linkcontrol sysfs info, (err %d) port %u\n", ret, port_num); - goto bail; + goto bail_link; } kobject_uevent(&ppd->pport_kobj, KOBJ_ADD); @@ -770,7 +770,7 @@ int qib_create_port_files(struct ib_device *ibdev, u8 port_num, qib_dev_err(dd, "Skipping sl2vl sysfs info, (err %d) port %u\n", ret, port_num); - goto bail_link; + goto bail_sl; } kobject_uevent(&ppd->sl2vl_kobj, KOBJ_ADD); @@ -780,7 +780,7 @@ int qib_create_port_files(struct ib_device *ibdev, u8 port_num, qib_dev_err(dd, "Skipping diag_counters sysfs info, (err %d) port %u\n", ret, port_num); - goto bail_sl; + goto bail_diagc; } kobject_uevent(&ppd->diagc_kobj, KOBJ_ADD); @@ -793,7 +793,7 @@ int qib_create_port_files(struct ib_device *ibdev, u8 port_num, qib_dev_err(dd, "Skipping Congestion Control sysfs info, (err %d) port %u\n", ret, port_num); - goto bail_diagc; + goto bail_cc; } kobject_uevent(&ppd->pport_cc_kobj, KOBJ_ADD); @@ -854,6 +854,7 @@ void qib_verbs_unregister_sysfs(struct qib_devdata *dd) &cc_table_bin_attr); kobject_put(&ppd->pport_cc_kobj); } + kobject_put(&ppd->diagc_kobj); kobject_put(&ppd->sl2vl_kobj); kobject_put(&ppd->pport_kobj); } diff --git a/drivers/infiniband/hw/vmw_pvrdma/pvrdma_main.c b/drivers/infiniband/hw/vmw_pvrdma/pvrdma_main.c index e580ae9cc55a..780fd2dfc07e 100644 --- a/drivers/infiniband/hw/vmw_pvrdma/pvrdma_main.c +++ b/drivers/infiniband/hw/vmw_pvrdma/pvrdma_main.c @@ -829,7 +829,7 @@ static int pvrdma_pci_probe(struct pci_dev *pdev, !(pci_resource_flags(pdev, 1) & IORESOURCE_MEM)) { dev_err(&pdev->dev, "PCI BAR region not MMIO\n"); ret = -ENOMEM; - goto err_free_device; + goto err_disable_pdev; } ret = pci_request_regions(pdev, DRV_NAME); diff --git a/drivers/infiniband/ulp/ipoib/ipoib.h b/drivers/infiniband/ulp/ipoib/ipoib.h index e188a95984b5..9a3379c49541 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib.h +++ b/drivers/infiniband/ulp/ipoib/ipoib.h @@ -377,8 +377,12 @@ struct ipoib_dev_priv { struct ipoib_rx_buf *rx_ring; struct ipoib_tx_buf *tx_ring; + /* cyclic ring variables for managing tx_ring, for UD only */ unsigned int tx_head; unsigned int tx_tail; + /* cyclic ring variables for counting overall outstanding send WRs */ + unsigned int global_tx_head; + unsigned int global_tx_tail; struct ib_sge tx_sge[MAX_SKB_FRAGS + 1]; struct ib_ud_wr tx_wr; struct ib_wc send_wc[MAX_SEND_CQE]; diff --git a/drivers/infiniband/ulp/ipoib/ipoib_cm.c b/drivers/infiniband/ulp/ipoib/ipoib_cm.c index c59e00a0881f..9bf0fa30df28 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_cm.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_cm.c @@ -756,7 +756,8 @@ void ipoib_cm_send(struct net_device *dev, struct sk_buff *skb, struct ipoib_cm_ return; } - if ((priv->tx_head - priv->tx_tail) == ipoib_sendq_size - 1) { + if ((priv->global_tx_head - priv->global_tx_tail) == + ipoib_sendq_size - 1) { ipoib_dbg(priv, "TX ring 0x%x full, stopping kernel net queue\n", tx->qp->qp_num); netif_stop_queue(dev); @@ -786,7 +787,7 @@ void ipoib_cm_send(struct net_device *dev, struct sk_buff *skb, struct ipoib_cm_ } else { netif_trans_update(dev); ++tx->tx_head; - ++priv->tx_head; + ++priv->global_tx_head; } } @@ -820,10 +821,11 @@ void ipoib_cm_handle_tx_wc(struct net_device *dev, struct ib_wc *wc) netif_tx_lock(dev); ++tx->tx_tail; - ++priv->tx_tail; + ++priv->global_tx_tail; if (unlikely(netif_queue_stopped(dev) && - (priv->tx_head - priv->tx_tail) <= ipoib_sendq_size >> 1 && + ((priv->global_tx_head - priv->global_tx_tail) <= + ipoib_sendq_size >> 1) && test_bit(IPOIB_FLAG_ADMIN_UP, &priv->flags))) netif_wake_queue(dev); @@ -1232,8 +1234,9 @@ timeout: dev_kfree_skb_any(tx_req->skb); netif_tx_lock_bh(p->dev); ++p->tx_tail; - ++priv->tx_tail; - if (unlikely(priv->tx_head - priv->tx_tail == ipoib_sendq_size >> 1) && + ++priv->global_tx_tail; + if (unlikely((priv->global_tx_head - priv->global_tx_tail) <= + ipoib_sendq_size >> 1) && netif_queue_stopped(p->dev) && test_bit(IPOIB_FLAG_ADMIN_UP, &priv->flags)) netif_wake_queue(p->dev); diff --git a/drivers/infiniband/ulp/ipoib/ipoib_ib.c b/drivers/infiniband/ulp/ipoib/ipoib_ib.c index c332b4761816..da3c5315bbb5 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_ib.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_ib.c @@ -407,9 +407,11 @@ static void ipoib_ib_handle_tx_wc(struct net_device *dev, struct ib_wc *wc) dev_kfree_skb_any(tx_req->skb); ++priv->tx_tail; + ++priv->global_tx_tail; if (unlikely(netif_queue_stopped(dev) && - ((priv->tx_head - priv->tx_tail) <= ipoib_sendq_size >> 1) && + ((priv->global_tx_head - priv->global_tx_tail) <= + ipoib_sendq_size >> 1) && test_bit(IPOIB_FLAG_ADMIN_UP, &priv->flags))) netif_wake_queue(dev); @@ -634,7 +636,8 @@ int ipoib_send(struct net_device *dev, struct sk_buff *skb, else priv->tx_wr.wr.send_flags &= ~IB_SEND_IP_CSUM; /* increase the tx_head after send success, but use it for queue state */ - if (priv->tx_head - priv->tx_tail == ipoib_sendq_size - 1) { + if ((priv->global_tx_head - priv->global_tx_tail) == + ipoib_sendq_size - 1) { ipoib_dbg(priv, "TX ring full, stopping kernel net queue\n"); netif_stop_queue(dev); } @@ -662,6 +665,7 @@ int ipoib_send(struct net_device *dev, struct sk_buff *skb, rc = priv->tx_head; ++priv->tx_head; + ++priv->global_tx_head; } return rc; } @@ -807,6 +811,7 @@ int ipoib_ib_dev_stop_default(struct net_device *dev) ipoib_dma_unmap_tx(priv, tx_req); dev_kfree_skb_any(tx_req->skb); ++priv->tx_tail; + ++priv->global_tx_tail; } for (i = 0; i < ipoib_recvq_size; ++i) { diff --git a/drivers/infiniband/ulp/ipoib/ipoib_main.c b/drivers/infiniband/ulp/ipoib/ipoib_main.c index 81b8227214f1..ceec24d45185 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_main.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_main.c @@ -1184,9 +1184,11 @@ static void ipoib_timeout(struct net_device *dev, unsigned int txqueue) ipoib_warn(priv, "transmit timeout: latency %d msecs\n", jiffies_to_msecs(jiffies - dev_trans_start(dev))); - ipoib_warn(priv, "queue stopped %d, tx_head %u, tx_tail %u\n", - netif_queue_stopped(dev), - priv->tx_head, priv->tx_tail); + ipoib_warn(priv, + "queue stopped %d, tx_head %u, tx_tail %u, global_tx_head %u, global_tx_tail %u\n", + netif_queue_stopped(dev), priv->tx_head, priv->tx_tail, + priv->global_tx_head, priv->global_tx_tail); + /* XXX reset QP, etc. */ } @@ -1701,7 +1703,7 @@ static int ipoib_dev_init_default(struct net_device *dev) goto out_rx_ring_cleanup; } - /* priv->tx_head, tx_tail & tx_outstanding are already 0 */ + /* priv->tx_head, tx_tail and global_tx_tail/head are already 0 */ if (ipoib_transport_dev_init(dev, priv->ca)) { pr_warn("%s: ipoib_transport_dev_init failed\n", diff --git a/drivers/input/evdev.c b/drivers/input/evdev.c index cb6e3a5f509c..0d57e51b8ba1 100644 --- a/drivers/input/evdev.c +++ b/drivers/input/evdev.c @@ -326,20 +326,6 @@ static int evdev_fasync(int fd, struct file *file, int on) return fasync_helper(fd, file, on, &client->fasync); } -static int evdev_flush(struct file *file, fl_owner_t id) -{ - struct evdev_client *client = file->private_data; - struct evdev *evdev = client->evdev; - - mutex_lock(&evdev->mutex); - - if (evdev->exist && !client->revoked) - input_flush_device(&evdev->handle, file); - - mutex_unlock(&evdev->mutex); - return 0; -} - static void evdev_free(struct device *dev) { struct evdev *evdev = container_of(dev, struct evdev, dev); @@ -453,6 +439,10 @@ static int evdev_release(struct inode *inode, struct file *file) unsigned int i; mutex_lock(&evdev->mutex); + + if (evdev->exist && !client->revoked) + input_flush_device(&evdev->handle, file); + evdev_ungrab(evdev, client); mutex_unlock(&evdev->mutex); @@ -1310,7 +1300,6 @@ static const struct file_operations evdev_fops = { .compat_ioctl = evdev_ioctl_compat, #endif .fasync = evdev_fasync, - .flush = evdev_flush, .llseek = no_llseek, }; diff --git a/drivers/input/joystick/xpad.c b/drivers/input/joystick/xpad.c index 6b40a1c68f9f..c77cdb3b62b5 100644 --- a/drivers/input/joystick/xpad.c +++ b/drivers/input/joystick/xpad.c @@ -459,6 +459,16 @@ static const u8 xboxone_fw2015_init[] = { }; /* + * This packet is required for Xbox One S (0x045e:0x02ea) + * and Xbox One Elite Series 2 (0x045e:0x0b00) pads to + * initialize the controller that was previously used in + * Bluetooth mode. + */ +static const u8 xboxone_s_init[] = { + 0x05, 0x20, 0x00, 0x0f, 0x06 +}; + +/* * This packet is required for the Titanfall 2 Xbox One pads * (0x0e6f:0x0165) to finish initialization and for Hori pads * (0x0f0d:0x0067) to make the analog sticks work. @@ -516,6 +526,8 @@ static const struct xboxone_init_packet xboxone_init_packets[] = { XBOXONE_INIT_PKT(0x0e6f, 0x0165, xboxone_hori_init), XBOXONE_INIT_PKT(0x0f0d, 0x0067, xboxone_hori_init), XBOXONE_INIT_PKT(0x0000, 0x0000, xboxone_fw2015_init), + XBOXONE_INIT_PKT(0x045e, 0x02ea, xboxone_s_init), + XBOXONE_INIT_PKT(0x045e, 0x0b00, xboxone_s_init), XBOXONE_INIT_PKT(0x0e6f, 0x0000, xboxone_pdp_init1), XBOXONE_INIT_PKT(0x0e6f, 0x0000, xboxone_pdp_init2), XBOXONE_INIT_PKT(0x24c6, 0x541a, xboxone_rumblebegin_init), diff --git a/drivers/input/keyboard/applespi.c b/drivers/input/keyboard/applespi.c index d38398526965..14362ebab9a9 100644 --- a/drivers/input/keyboard/applespi.c +++ b/drivers/input/keyboard/applespi.c @@ -186,7 +186,7 @@ struct touchpad_protocol { u8 number_of_fingers; u8 clicked2; u8 unknown3[16]; - struct tp_finger fingers[0]; + struct tp_finger fingers[]; }; /** diff --git a/drivers/input/keyboard/cros_ec_keyb.c b/drivers/input/keyboard/cros_ec_keyb.c index 2b71c5a51f90..fc1793ca2f17 100644 --- a/drivers/input/keyboard/cros_ec_keyb.c +++ b/drivers/input/keyboard/cros_ec_keyb.c @@ -347,18 +347,14 @@ static int cros_ec_keyb_info(struct cros_ec_device *ec_dev, params->info_type = info_type; params->event_type = event_type; - ret = cros_ec_cmd_xfer(ec_dev, msg); - if (ret < 0) { - dev_warn(ec_dev->dev, "Transfer error %d/%d: %d\n", - (int)info_type, (int)event_type, ret); - } else if (msg->result == EC_RES_INVALID_VERSION) { + ret = cros_ec_cmd_xfer_status(ec_dev, msg); + if (ret == -ENOTSUPP) { /* With older ECs we just return 0 for everything */ memset(result, 0, result_size); ret = 0; - } else if (msg->result != EC_RES_SUCCESS) { - dev_warn(ec_dev->dev, "Error getting info %d/%d: %d\n", - (int)info_type, (int)event_type, msg->result); - ret = -EPROTO; + } else if (ret < 0) { + dev_warn(ec_dev->dev, "Transfer error %d/%d: %d\n", + (int)info_type, (int)event_type, ret); } else if (ret != result_size) { dev_warn(ec_dev->dev, "Wrong size %d/%d: %d != %zu\n", (int)info_type, (int)event_type, diff --git a/drivers/input/keyboard/dlink-dir685-touchkeys.c b/drivers/input/keyboard/dlink-dir685-touchkeys.c index b0ead7199c40..a69dcc3bd30c 100644 --- a/drivers/input/keyboard/dlink-dir685-touchkeys.c +++ b/drivers/input/keyboard/dlink-dir685-touchkeys.c @@ -143,7 +143,7 @@ MODULE_DEVICE_TABLE(of, dir685_tk_of_match); static struct i2c_driver dir685_tk_i2c_driver = { .driver = { - .name = "dlin-dir685-touchkeys", + .name = "dlink-dir685-touchkeys", .of_match_table = of_match_ptr(dir685_tk_of_match), }, .probe = dir685_tk_probe, diff --git a/drivers/input/misc/axp20x-pek.c b/drivers/input/misc/axp20x-pek.c index c8f87df93a50..9c6386b2af33 100644 --- a/drivers/input/misc/axp20x-pek.c +++ b/drivers/input/misc/axp20x-pek.c @@ -205,8 +205,11 @@ ATTRIBUTE_GROUPS(axp20x); static irqreturn_t axp20x_pek_irq(int irq, void *pwr) { - struct input_dev *idev = pwr; - struct axp20x_pek *axp20x_pek = input_get_drvdata(idev); + struct axp20x_pek *axp20x_pek = pwr; + struct input_dev *idev = axp20x_pek->input; + + if (!idev) + return IRQ_HANDLED; /* * The power-button is connected to ground so a falling edge (dbf) @@ -225,22 +228,9 @@ static irqreturn_t axp20x_pek_irq(int irq, void *pwr) static int axp20x_pek_probe_input_device(struct axp20x_pek *axp20x_pek, struct platform_device *pdev) { - struct axp20x_dev *axp20x = axp20x_pek->axp20x; struct input_dev *idev; int error; - axp20x_pek->irq_dbr = platform_get_irq_byname(pdev, "PEK_DBR"); - if (axp20x_pek->irq_dbr < 0) - return axp20x_pek->irq_dbr; - axp20x_pek->irq_dbr = regmap_irq_get_virq(axp20x->regmap_irqc, - axp20x_pek->irq_dbr); - - axp20x_pek->irq_dbf = platform_get_irq_byname(pdev, "PEK_DBF"); - if (axp20x_pek->irq_dbf < 0) - return axp20x_pek->irq_dbf; - axp20x_pek->irq_dbf = regmap_irq_get_virq(axp20x->regmap_irqc, - axp20x_pek->irq_dbf); - axp20x_pek->input = devm_input_allocate_device(&pdev->dev); if (!axp20x_pek->input) return -ENOMEM; @@ -255,24 +245,6 @@ static int axp20x_pek_probe_input_device(struct axp20x_pek *axp20x_pek, input_set_drvdata(idev, axp20x_pek); - error = devm_request_any_context_irq(&pdev->dev, axp20x_pek->irq_dbr, - axp20x_pek_irq, 0, - "axp20x-pek-dbr", idev); - if (error < 0) { - dev_err(&pdev->dev, "Failed to request dbr IRQ#%d: %d\n", - axp20x_pek->irq_dbr, error); - return error; - } - - error = devm_request_any_context_irq(&pdev->dev, axp20x_pek->irq_dbf, - axp20x_pek_irq, 0, - "axp20x-pek-dbf", idev); - if (error < 0) { - dev_err(&pdev->dev, "Failed to request dbf IRQ#%d: %d\n", - axp20x_pek->irq_dbf, error); - return error; - } - error = input_register_device(idev); if (error) { dev_err(&pdev->dev, "Can't register input device: %d\n", @@ -280,8 +252,6 @@ static int axp20x_pek_probe_input_device(struct axp20x_pek *axp20x_pek, return error; } - device_init_wakeup(&pdev->dev, true); - return 0; } @@ -339,6 +309,18 @@ static int axp20x_pek_probe(struct platform_device *pdev) axp20x_pek->axp20x = dev_get_drvdata(pdev->dev.parent); + axp20x_pek->irq_dbr = platform_get_irq_byname(pdev, "PEK_DBR"); + if (axp20x_pek->irq_dbr < 0) + return axp20x_pek->irq_dbr; + axp20x_pek->irq_dbr = regmap_irq_get_virq( + axp20x_pek->axp20x->regmap_irqc, axp20x_pek->irq_dbr); + + axp20x_pek->irq_dbf = platform_get_irq_byname(pdev, "PEK_DBF"); + if (axp20x_pek->irq_dbf < 0) + return axp20x_pek->irq_dbf; + axp20x_pek->irq_dbf = regmap_irq_get_virq( + axp20x_pek->axp20x->regmap_irqc, axp20x_pek->irq_dbf); + if (axp20x_pek_should_register_input(axp20x_pek, pdev)) { error = axp20x_pek_probe_input_device(axp20x_pek, pdev); if (error) @@ -347,6 +329,26 @@ static int axp20x_pek_probe(struct platform_device *pdev) axp20x_pek->info = (struct axp20x_info *)match->driver_data; + error = devm_request_any_context_irq(&pdev->dev, axp20x_pek->irq_dbr, + axp20x_pek_irq, 0, + "axp20x-pek-dbr", axp20x_pek); + if (error < 0) { + dev_err(&pdev->dev, "Failed to request dbr IRQ#%d: %d\n", + axp20x_pek->irq_dbr, error); + return error; + } + + error = devm_request_any_context_irq(&pdev->dev, axp20x_pek->irq_dbf, + axp20x_pek_irq, 0, + "axp20x-pek-dbf", axp20x_pek); + if (error < 0) { + dev_err(&pdev->dev, "Failed to request dbf IRQ#%d: %d\n", + axp20x_pek->irq_dbf, error); + return error; + } + + device_init_wakeup(&pdev->dev, true); + platform_set_drvdata(pdev, axp20x_pek); return 0; diff --git a/drivers/input/mouse/synaptics.c b/drivers/input/mouse/synaptics.c index 4d2036209b45..758dae8d6500 100644 --- a/drivers/input/mouse/synaptics.c +++ b/drivers/input/mouse/synaptics.c @@ -170,6 +170,7 @@ static const char * const smbus_pnp_ids[] = { "LEN005b", /* P50 */ "LEN005e", /* T560 */ "LEN006c", /* T470s */ + "LEN007a", /* T470s */ "LEN0071", /* T480 */ "LEN0072", /* X1 Carbon Gen 5 (2017) - Elan/ALPS trackpoint */ "LEN0073", /* X1 Carbon G5 (Elantech) */ diff --git a/drivers/input/rmi4/rmi_driver.c b/drivers/input/rmi4/rmi_driver.c index 190b9974526b..258d5fe3d395 100644 --- a/drivers/input/rmi4/rmi_driver.c +++ b/drivers/input/rmi4/rmi_driver.c @@ -205,7 +205,7 @@ static irqreturn_t rmi_irq_fn(int irq, void *dev_id) if (count) { kfree(attn_data.data); - attn_data.data = NULL; + drvdata->attn_data.data = NULL; } if (!kfifo_is_empty(&drvdata->attn_fifo)) @@ -1210,7 +1210,8 @@ static int rmi_driver_probe(struct device *dev) if (data->input) { rmi_driver_set_input_name(rmi_dev, data->input); if (!rmi_dev->xport->input) { - if (input_register_device(data->input)) { + retval = input_register_device(data->input); + if (retval) { dev_err(dev, "%s: Failed to register input device.\n", __func__); goto err_destroy_functions; diff --git a/drivers/input/serio/i8042-x86ia64io.h b/drivers/input/serio/i8042-x86ia64io.h index 08e919dbeb5d..7e048b557462 100644 --- a/drivers/input/serio/i8042-x86ia64io.h +++ b/drivers/input/serio/i8042-x86ia64io.h @@ -662,6 +662,13 @@ static const struct dmi_system_id __initconst i8042_dmi_reset_table[] = { DMI_MATCH(DMI_PRODUCT_NAME, "P65xRP"), }, }, + { + /* Lenovo ThinkPad Twist S230u */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), + DMI_MATCH(DMI_PRODUCT_NAME, "33474HU"), + }, + }, { } }; diff --git a/drivers/input/touchscreen/elants_i2c.c b/drivers/input/touchscreen/elants_i2c.c index 14c577c16b16..2289f9638116 100644 --- a/drivers/input/touchscreen/elants_i2c.c +++ b/drivers/input/touchscreen/elants_i2c.c @@ -19,6 +19,7 @@ */ +#include <linux/bits.h> #include <linux/module.h> #include <linux/input.h> #include <linux/interrupt.h> @@ -73,6 +74,7 @@ #define FW_POS_STATE 1 #define FW_POS_TOTAL 2 #define FW_POS_XY 3 +#define FW_POS_TOOL_TYPE 33 #define FW_POS_CHECKSUM 34 #define FW_POS_WIDTH 35 #define FW_POS_PRESSURE 45 @@ -842,6 +844,7 @@ static void elants_i2c_mt_event(struct elants_data *ts, u8 *buf) { struct input_dev *input = ts->input; unsigned int n_fingers; + unsigned int tool_type; u16 finger_state; int i; @@ -852,6 +855,10 @@ static void elants_i2c_mt_event(struct elants_data *ts, u8 *buf) dev_dbg(&ts->client->dev, "n_fingers: %u, state: %04x\n", n_fingers, finger_state); + /* Note: all fingers have the same tool type */ + tool_type = buf[FW_POS_TOOL_TYPE] & BIT(0) ? + MT_TOOL_FINGER : MT_TOOL_PALM; + for (i = 0; i < MAX_CONTACT_NUM && n_fingers; i++) { if (finger_state & 1) { unsigned int x, y, p, w; @@ -867,7 +874,7 @@ static void elants_i2c_mt_event(struct elants_data *ts, u8 *buf) i, x, y, p, w); input_mt_slot(input, i); - input_mt_report_slot_state(input, MT_TOOL_FINGER, true); + input_mt_report_slot_state(input, tool_type, true); input_event(input, EV_ABS, ABS_MT_POSITION_X, x); input_event(input, EV_ABS, ABS_MT_POSITION_Y, y); input_event(input, EV_ABS, ABS_MT_PRESSURE, p); @@ -1307,6 +1314,8 @@ static int elants_i2c_probe(struct i2c_client *client, input_set_abs_params(ts->input, ABS_MT_POSITION_Y, 0, ts->y_max, 0, 0); input_set_abs_params(ts->input, ABS_MT_TOUCH_MAJOR, 0, 255, 0, 0); input_set_abs_params(ts->input, ABS_MT_PRESSURE, 0, 255, 0, 0); + input_set_abs_params(ts->input, ABS_MT_TOOL_TYPE, + 0, MT_TOOL_PALM, 0, 0); input_abs_set_res(ts->input, ABS_MT_POSITION_X, ts->x_res); input_abs_set_res(ts->input, ABS_MT_POSITION_Y, ts->y_res); input_abs_set_res(ts->input, ABS_MT_TOUCH_MAJOR, 1); diff --git a/drivers/input/touchscreen/mms114.c b/drivers/input/touchscreen/mms114.c index 69c6d559eeb0..2ef1adaed9af 100644 --- a/drivers/input/touchscreen/mms114.c +++ b/drivers/input/touchscreen/mms114.c @@ -91,15 +91,15 @@ static int __mms114_read_reg(struct mms114_data *data, unsigned int reg, if (reg <= MMS114_MODE_CONTROL && reg + len > MMS114_MODE_CONTROL) BUG(); - /* Write register: use repeated start */ + /* Write register */ xfer[0].addr = client->addr; - xfer[0].flags = I2C_M_TEN | I2C_M_NOSTART; + xfer[0].flags = client->flags & I2C_M_TEN; xfer[0].len = 1; xfer[0].buf = &buf; /* Read data */ xfer[1].addr = client->addr; - xfer[1].flags = I2C_M_RD; + xfer[1].flags = (client->flags & I2C_M_TEN) | I2C_M_RD; xfer[1].len = len; xfer[1].buf = val; @@ -428,10 +428,8 @@ static int mms114_probe(struct i2c_client *client, const void *match_data; int error; - if (!i2c_check_functionality(client->adapter, - I2C_FUNC_PROTOCOL_MANGLING)) { - dev_err(&client->dev, - "Need i2c bus that supports protocol mangling\n"); + if (!i2c_check_functionality(client->adapter, I2C_FUNC_I2C)) { + dev_err(&client->dev, "Not supported I2C adapter\n"); return -ENODEV; } diff --git a/drivers/input/touchscreen/usbtouchscreen.c b/drivers/input/touchscreen/usbtouchscreen.c index 16d70201de4a..397cb1d3f481 100644 --- a/drivers/input/touchscreen/usbtouchscreen.c +++ b/drivers/input/touchscreen/usbtouchscreen.c @@ -182,6 +182,7 @@ static const struct usb_device_id usbtouch_devices[] = { #endif #ifdef CONFIG_TOUCHSCREEN_USB_IRTOUCH + {USB_DEVICE(0x255e, 0x0001), .driver_info = DEVTYPE_IRTOUCH}, {USB_DEVICE(0x595a, 0x0001), .driver_info = DEVTYPE_IRTOUCH}, {USB_DEVICE(0x6615, 0x0001), .driver_info = DEVTYPE_IRTOUCH}, {USB_DEVICE(0x6615, 0x0012), .driver_info = DEVTYPE_IRTOUCH_HIRES}, diff --git a/drivers/iommu/Kconfig b/drivers/iommu/Kconfig index 2ab07ce17abb..aca76383f201 100644 --- a/drivers/iommu/Kconfig +++ b/drivers/iommu/Kconfig @@ -303,6 +303,15 @@ config ROCKCHIP_IOMMU Say Y here if you are using a Rockchip SoC that includes an IOMMU device. +config SUN50I_IOMMU + bool "Allwinner H6 IOMMU Support" + depends on ARCH_SUNXI || COMPILE_TEST + select ARM_DMA_USE_IOMMU + select IOMMU_API + select IOMMU_DMA + help + Support for the IOMMU introduced in the Allwinner H6 SoCs. + config TEGRA_IOMMU_GART bool "Tegra GART IOMMU Support" depends on ARCH_TEGRA_2x_SOC diff --git a/drivers/iommu/Makefile b/drivers/iommu/Makefile index 9f33fdb3bb05..57cf4ba5e27c 100644 --- a/drivers/iommu/Makefile +++ b/drivers/iommu/Makefile @@ -29,6 +29,7 @@ obj-$(CONFIG_MTK_IOMMU_V1) += mtk_iommu_v1.o obj-$(CONFIG_OMAP_IOMMU) += omap-iommu.o obj-$(CONFIG_OMAP_IOMMU_DEBUG) += omap-iommu-debug.o obj-$(CONFIG_ROCKCHIP_IOMMU) += rockchip-iommu.o +obj-$(CONFIG_SUN50I_IOMMU) += sun50i-iommu.o obj-$(CONFIG_TEGRA_IOMMU_GART) += tegra-gart.o obj-$(CONFIG_TEGRA_IOMMU_SMMU) += tegra-smmu.o obj-$(CONFIG_EXYNOS_IOMMU) += exynos-iommu.o diff --git a/drivers/iommu/amd_iommu.c b/drivers/iommu/amd_iommu.c index 7c1884cab91f..311ef7105c6d 100644 --- a/drivers/iommu/amd_iommu.c +++ b/drivers/iommu/amd_iommu.c @@ -307,16 +307,15 @@ static struct iommu_group *acpihid_device_group(struct device *dev) static bool pci_iommuv2_capable(struct pci_dev *pdev) { static const int caps[] = { - PCI_EXT_CAP_ID_ATS, PCI_EXT_CAP_ID_PRI, PCI_EXT_CAP_ID_PASID, }; int i, pos; - if (pci_ats_disabled()) + if (!pci_ats_supported(pdev)) return false; - for (i = 0; i < 3; ++i) { + for (i = 0; i < 2; ++i) { pos = pci_find_ext_capability(pdev, caps[i]); if (pos == 0) return false; @@ -3050,11 +3049,8 @@ int amd_iommu_device_info(struct pci_dev *pdev, memset(info, 0, sizeof(*info)); - if (!pci_ats_disabled()) { - pos = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_ATS); - if (pos) - info->flags |= AMD_IOMMU_DEVICE_FLAG_ATS_SUP; - } + if (pci_ats_supported(pdev)) + info->flags |= AMD_IOMMU_DEVICE_FLAG_ATS_SUP; pos = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_PRI); if (pos) diff --git a/drivers/iommu/arm-smmu-impl.c b/drivers/iommu/arm-smmu-impl.c index 74d97a886e93..c75b9d957b70 100644 --- a/drivers/iommu/arm-smmu-impl.c +++ b/drivers/iommu/arm-smmu-impl.c @@ -150,6 +150,8 @@ static const struct arm_smmu_impl arm_mmu500_impl = { struct arm_smmu_device *arm_smmu_impl_init(struct arm_smmu_device *smmu) { + const struct device_node *np = smmu->dev->of_node; + /* * We will inevitably have to combine model-specific implementation * quirks with platform-specific integration quirks, but everything @@ -166,11 +168,11 @@ struct arm_smmu_device *arm_smmu_impl_init(struct arm_smmu_device *smmu) break; } - if (of_property_read_bool(smmu->dev->of_node, - "calxeda,smmu-secure-config-access")) + if (of_property_read_bool(np, "calxeda,smmu-secure-config-access")) smmu->impl = &calxeda_impl; - if (of_device_is_compatible(smmu->dev->of_node, "qcom,sdm845-smmu-500")) + if (of_device_is_compatible(np, "qcom,sdm845-smmu-500") || + of_device_is_compatible(np, "qcom,sc7180-smmu-500")) return qcom_smmu_impl_init(smmu); return smmu; diff --git a/drivers/iommu/arm-smmu-qcom.c b/drivers/iommu/arm-smmu-qcom.c index 24c071c1d8b0..cf01d0215a39 100644 --- a/drivers/iommu/arm-smmu-qcom.c +++ b/drivers/iommu/arm-smmu-qcom.c @@ -3,6 +3,7 @@ * Copyright (c) 2019, The Linux Foundation. All rights reserved. */ +#include <linux/of_device.h> #include <linux/qcom_scm.h> #include "arm-smmu.h" @@ -11,12 +12,29 @@ struct qcom_smmu { struct arm_smmu_device smmu; }; +static const struct of_device_id qcom_smmu_client_of_match[] = { + { .compatible = "qcom,adreno" }, + { .compatible = "qcom,mdp4" }, + { .compatible = "qcom,mdss" }, + { .compatible = "qcom,sc7180-mdss" }, + { .compatible = "qcom,sc7180-mss-pil" }, + { .compatible = "qcom,sdm845-mdss" }, + { .compatible = "qcom,sdm845-mss-pil" }, + { } +}; + +static int qcom_smmu_def_domain_type(struct device *dev) +{ + const struct of_device_id *match = + of_match_device(qcom_smmu_client_of_match, dev); + + return match ? IOMMU_DOMAIN_IDENTITY : 0; +} + static int qcom_sdm845_smmu500_reset(struct arm_smmu_device *smmu) { int ret; - arm_mmu500_reset(smmu); - /* * To address performance degradation in non-real time clients, * such as USB and UFS, turn off wait-for-safe on sdm845 based boards, @@ -30,8 +48,21 @@ static int qcom_sdm845_smmu500_reset(struct arm_smmu_device *smmu) return ret; } +static int qcom_smmu500_reset(struct arm_smmu_device *smmu) +{ + const struct device_node *np = smmu->dev->of_node; + + arm_mmu500_reset(smmu); + + if (of_device_is_compatible(np, "qcom,sdm845-smmu-500")) + return qcom_sdm845_smmu500_reset(smmu); + + return 0; +} + static const struct arm_smmu_impl qcom_smmu_impl = { - .reset = qcom_sdm845_smmu500_reset, + .def_domain_type = qcom_smmu_def_domain_type, + .reset = qcom_smmu500_reset, }; struct arm_smmu_device *qcom_smmu_impl_init(struct arm_smmu_device *smmu) diff --git a/drivers/iommu/arm-smmu-v3.c b/drivers/iommu/arm-smmu-v3.c index 42e1ee7e5197..f578677a5c41 100644 --- a/drivers/iommu/arm-smmu-v3.c +++ b/drivers/iommu/arm-smmu-v3.c @@ -171,6 +171,8 @@ #define ARM_SMMU_PRIQ_IRQ_CFG1 0xd8 #define ARM_SMMU_PRIQ_IRQ_CFG2 0xdc +#define ARM_SMMU_REG_SZ 0xe00 + /* Common MSI config fields */ #define MSI_CFG0_ADDR_MASK GENMASK_ULL(51, 2) #define MSI_CFG2_SH GENMASK(5, 4) @@ -628,6 +630,7 @@ struct arm_smmu_strtab_cfg { struct arm_smmu_device { struct device *dev; void __iomem *base; + void __iomem *page1; #define ARM_SMMU_FEAT_2_LVL_STRTAB (1 << 0) #define ARM_SMMU_FEAT_2_LVL_CDTAB (1 << 1) @@ -664,7 +667,6 @@ struct arm_smmu_device { #define ARM_SMMU_MAX_ASIDS (1 << 16) unsigned int asid_bits; - DECLARE_BITMAP(asid_map, ARM_SMMU_MAX_ASIDS); #define ARM_SMMU_MAX_VMIDS (1 << 16) unsigned int vmid_bits; @@ -724,6 +726,8 @@ struct arm_smmu_option_prop { const char *prop; }; +static DEFINE_XARRAY_ALLOC1(asid_xa); + static struct arm_smmu_option_prop arm_smmu_options[] = { { ARM_SMMU_OPT_SKIP_PREFETCH, "hisilicon,broken-prefetch-cmd" }, { ARM_SMMU_OPT_PAGE0_REGS_ONLY, "cavium,cn9900-broken-page1-regspace"}, @@ -733,9 +737,8 @@ static struct arm_smmu_option_prop arm_smmu_options[] = { static inline void __iomem *arm_smmu_page1_fixup(unsigned long offset, struct arm_smmu_device *smmu) { - if ((offset > SZ_64K) && - (smmu->options & ARM_SMMU_OPT_PAGE0_REGS_ONLY)) - offset -= SZ_64K; + if (offset > SZ_64K) + return smmu->page1 + offset - SZ_64K; return smmu->base + offset; } @@ -1763,6 +1766,14 @@ static void arm_smmu_free_cd_tables(struct arm_smmu_domain *smmu_domain) cdcfg->cdtab = NULL; } +static void arm_smmu_free_asid(struct arm_smmu_ctx_desc *cd) +{ + if (!cd->asid) + return; + + xa_erase(&asid_xa, cd->asid); +} + /* Stream table manipulation functions */ static void arm_smmu_write_strtab_l1_desc(__le64 *dst, struct arm_smmu_strtab_l1_desc *desc) @@ -2448,10 +2459,9 @@ static void arm_smmu_domain_free(struct iommu_domain *domain) if (smmu_domain->stage == ARM_SMMU_DOMAIN_S1) { struct arm_smmu_s1_cfg *cfg = &smmu_domain->s1_cfg; - if (cfg->cdcfg.cdtab) { + if (cfg->cdcfg.cdtab) arm_smmu_free_cd_tables(smmu_domain); - arm_smmu_bitmap_free(smmu->asid_map, cfg->cd.asid); - } + arm_smmu_free_asid(&cfg->cd); } else { struct arm_smmu_s2_cfg *cfg = &smmu_domain->s2_cfg; if (cfg->vmid) @@ -2466,14 +2476,15 @@ static int arm_smmu_domain_finalise_s1(struct arm_smmu_domain *smmu_domain, struct io_pgtable_cfg *pgtbl_cfg) { int ret; - int asid; + u32 asid; struct arm_smmu_device *smmu = smmu_domain->smmu; struct arm_smmu_s1_cfg *cfg = &smmu_domain->s1_cfg; typeof(&pgtbl_cfg->arm_lpae_s1_cfg.tcr) tcr = &pgtbl_cfg->arm_lpae_s1_cfg.tcr; - asid = arm_smmu_bitmap_alloc(smmu->asid_map, smmu->asid_bits); - if (asid < 0) - return asid; + ret = xa_alloc(&asid_xa, &asid, &cfg->cd, + XA_LIMIT(1, (1 << smmu->asid_bits) - 1), GFP_KERNEL); + if (ret) + return ret; cfg->s1cdmax = master->ssid_bits; @@ -2506,7 +2517,7 @@ static int arm_smmu_domain_finalise_s1(struct arm_smmu_domain *smmu_domain, out_free_cd_tables: arm_smmu_free_cd_tables(smmu_domain); out_free_asid: - arm_smmu_bitmap_free(smmu->asid_map, asid); + arm_smmu_free_asid(&cfg->cd); return ret; } @@ -2652,26 +2663,20 @@ static void arm_smmu_install_ste_for_dev(struct arm_smmu_master *master) } } -#ifdef CONFIG_PCI_ATS static bool arm_smmu_ats_supported(struct arm_smmu_master *master) { - struct pci_dev *pdev; + struct device *dev = master->dev; struct arm_smmu_device *smmu = master->smmu; - struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(master->dev); + struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(dev); - if (!(smmu->features & ARM_SMMU_FEAT_ATS) || !dev_is_pci(master->dev) || - !(fwspec->flags & IOMMU_FWSPEC_PCI_RC_ATS) || pci_ats_disabled()) + if (!(smmu->features & ARM_SMMU_FEAT_ATS)) return false; - pdev = to_pci_dev(master->dev); - return !pdev->untrusted && pdev->ats_cap; -} -#else -static bool arm_smmu_ats_supported(struct arm_smmu_master *master) -{ - return false; + if (!(fwspec->flags & IOMMU_FWSPEC_PCI_RC_ATS)) + return false; + + return dev_is_pci(dev) && pci_ats_supported(to_pci_dev(dev)); } -#endif static void arm_smmu_enable_ats(struct arm_smmu_master *master) { @@ -2986,13 +2991,11 @@ static void arm_smmu_release_device(struct device *dev) { struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(dev); struct arm_smmu_master *master; - struct arm_smmu_device *smmu; if (!fwspec || fwspec->ops != &arm_smmu_ops) return; master = dev_iommu_priv_get(dev); - smmu = master->smmu; arm_smmu_detach_dev(master); arm_smmu_disable_pasid(master); kfree(master); @@ -4003,6 +4006,18 @@ err_reset_pci_ops: __maybe_unused; return err; } +static void __iomem *arm_smmu_ioremap(struct device *dev, resource_size_t start, + resource_size_t size) +{ + struct resource res = { + .flags = IORESOURCE_MEM, + .start = start, + .end = start + size - 1, + }; + + return devm_ioremap_resource(dev, &res); +} + static int arm_smmu_device_probe(struct platform_device *pdev) { int irq, ret; @@ -4038,10 +4053,23 @@ static int arm_smmu_device_probe(struct platform_device *pdev) } ioaddr = res->start; - smmu->base = devm_ioremap_resource(dev, res); + /* + * Don't map the IMPLEMENTATION DEFINED regions, since they may contain + * the PMCG registers which are reserved by the PMU driver. + */ + smmu->base = arm_smmu_ioremap(dev, ioaddr, ARM_SMMU_REG_SZ); if (IS_ERR(smmu->base)) return PTR_ERR(smmu->base); + if (arm_smmu_resource_size(smmu) > SZ_64K) { + smmu->page1 = arm_smmu_ioremap(dev, ioaddr + SZ_64K, + ARM_SMMU_REG_SZ); + if (IS_ERR(smmu->page1)) + return PTR_ERR(smmu->page1); + } else { + smmu->page1 = smmu->base; + } + /* Interrupt lines */ irq = platform_get_irq_byname_optional(pdev, "combined"); diff --git a/drivers/iommu/arm-smmu.c b/drivers/iommu/arm-smmu.c index e622f4e33379..243bc4cb2705 100644 --- a/drivers/iommu/arm-smmu.c +++ b/drivers/iommu/arm-smmu.c @@ -1609,6 +1609,17 @@ static void arm_smmu_get_resv_regions(struct device *dev, iommu_dma_get_resv_regions(dev, head); } +static int arm_smmu_def_domain_type(struct device *dev) +{ + struct arm_smmu_master_cfg *cfg = dev_iommu_priv_get(dev); + const struct arm_smmu_impl *impl = cfg->smmu->impl; + + if (impl && impl->def_domain_type) + return impl->def_domain_type(dev); + + return 0; +} + static struct iommu_ops arm_smmu_ops = { .capable = arm_smmu_capable, .domain_alloc = arm_smmu_domain_alloc, @@ -1627,6 +1638,7 @@ static struct iommu_ops arm_smmu_ops = { .of_xlate = arm_smmu_of_xlate, .get_resv_regions = arm_smmu_get_resv_regions, .put_resv_regions = generic_iommu_put_resv_regions, + .def_domain_type = arm_smmu_def_domain_type, .pgsize_bitmap = -1UL, /* Restricted during device attach */ }; @@ -2244,7 +2256,7 @@ static int arm_smmu_device_remove(struct platform_device *pdev) return -ENODEV; if (!bitmap_empty(smmu->context_map, ARM_SMMU_MAX_CBS)) - dev_err(&pdev->dev, "removing device with active domains!\n"); + dev_notice(&pdev->dev, "disabling translation\n"); arm_smmu_bus_init(NULL); iommu_device_unregister(&smmu->iommu); diff --git a/drivers/iommu/arm-smmu.h b/drivers/iommu/arm-smmu.h index 8d1cd54d82a6..d172c024be61 100644 --- a/drivers/iommu/arm-smmu.h +++ b/drivers/iommu/arm-smmu.h @@ -386,6 +386,7 @@ struct arm_smmu_impl { int (*init_context)(struct arm_smmu_domain *smmu_domain); void (*tlb_sync)(struct arm_smmu_device *smmu, int page, int sync, int status); + int (*def_domain_type)(struct device *dev); }; static inline void __iomem *arm_smmu_page(struct arm_smmu_device *smmu, int n) diff --git a/drivers/iommu/dmar.c b/drivers/iommu/dmar.c index f77dae7ba7d4..60a2970c37ff 100644 --- a/drivers/iommu/dmar.c +++ b/drivers/iommu/dmar.c @@ -963,6 +963,7 @@ static int map_iommu(struct intel_iommu *iommu, u64 phys_addr) warn_invalid_dmar(phys_addr, " returns all ones"); goto unmap; } + iommu->vccap = dmar_readq(iommu->reg + DMAR_VCCAP_REG); /* the registers might be more than one page */ map_size = max_t(int, ecap_max_iotlb_offset(iommu->ecap), @@ -1156,12 +1157,11 @@ static inline void reclaim_free_desc(struct q_inval *qi) } } -static int qi_check_fault(struct intel_iommu *iommu, int index) +static int qi_check_fault(struct intel_iommu *iommu, int index, int wait_index) { u32 fault; int head, tail; struct q_inval *qi = iommu->qi; - int wait_index = (index + 1) % QI_LENGTH; int shift = qi_shift(iommu); if (qi->desc_status[wait_index] == QI_ABORT) @@ -1224,17 +1224,21 @@ static int qi_check_fault(struct intel_iommu *iommu, int index) } /* - * Submit the queued invalidation descriptor to the remapping - * hardware unit and wait for its completion. + * Function to submit invalidation descriptors of all types to the queued + * invalidation interface(QI). Multiple descriptors can be submitted at a + * time, a wait descriptor will be appended to each submission to ensure + * hardware has completed the invalidation before return. Wait descriptors + * can be part of the submission but it will not be polled for completion. */ -int qi_submit_sync(struct qi_desc *desc, struct intel_iommu *iommu) +int qi_submit_sync(struct intel_iommu *iommu, struct qi_desc *desc, + unsigned int count, unsigned long options) { - int rc; struct q_inval *qi = iommu->qi; - int offset, shift, length; struct qi_desc wait_desc; int wait_index, index; unsigned long flags; + int offset, shift; + int rc, i; if (!qi) return 0; @@ -1243,32 +1247,41 @@ restart: rc = 0; raw_spin_lock_irqsave(&qi->q_lock, flags); - while (qi->free_cnt < 3) { + /* + * Check if we have enough empty slots in the queue to submit, + * the calculation is based on: + * # of desc + 1 wait desc + 1 space between head and tail + */ + while (qi->free_cnt < count + 2) { raw_spin_unlock_irqrestore(&qi->q_lock, flags); cpu_relax(); raw_spin_lock_irqsave(&qi->q_lock, flags); } index = qi->free_head; - wait_index = (index + 1) % QI_LENGTH; + wait_index = (index + count) % QI_LENGTH; shift = qi_shift(iommu); - length = 1 << shift; - qi->desc_status[index] = qi->desc_status[wait_index] = QI_IN_USE; + for (i = 0; i < count; i++) { + offset = ((index + i) % QI_LENGTH) << shift; + memcpy(qi->desc + offset, &desc[i], 1 << shift); + qi->desc_status[(index + i) % QI_LENGTH] = QI_IN_USE; + } + qi->desc_status[wait_index] = QI_IN_USE; - offset = index << shift; - memcpy(qi->desc + offset, desc, length); wait_desc.qw0 = QI_IWD_STATUS_DATA(QI_DONE) | QI_IWD_STATUS_WRITE | QI_IWD_TYPE; + if (options & QI_OPT_WAIT_DRAIN) + wait_desc.qw0 |= QI_IWD_PRQ_DRAIN; wait_desc.qw1 = virt_to_phys(&qi->desc_status[wait_index]); wait_desc.qw2 = 0; wait_desc.qw3 = 0; offset = wait_index << shift; - memcpy(qi->desc + offset, &wait_desc, length); + memcpy(qi->desc + offset, &wait_desc, 1 << shift); - qi->free_head = (qi->free_head + 2) % QI_LENGTH; - qi->free_cnt -= 2; + qi->free_head = (qi->free_head + count + 1) % QI_LENGTH; + qi->free_cnt -= count + 1; /* * update the HW tail register indicating the presence of @@ -1284,7 +1297,7 @@ restart: * a deadlock where the interrupt context can wait indefinitely * for free slots in the queue. */ - rc = qi_check_fault(iommu, index); + rc = qi_check_fault(iommu, index, wait_index); if (rc) break; @@ -1293,7 +1306,8 @@ restart: raw_spin_lock(&qi->q_lock); } - qi->desc_status[index] = QI_DONE; + for (i = 0; i < count; i++) + qi->desc_status[(index + i) % QI_LENGTH] = QI_DONE; reclaim_free_desc(qi); raw_spin_unlock_irqrestore(&qi->q_lock, flags); @@ -1317,7 +1331,7 @@ void qi_global_iec(struct intel_iommu *iommu) desc.qw3 = 0; /* should never fail */ - qi_submit_sync(&desc, iommu); + qi_submit_sync(iommu, &desc, 1, 0); } void qi_flush_context(struct intel_iommu *iommu, u16 did, u16 sid, u8 fm, @@ -1331,7 +1345,7 @@ void qi_flush_context(struct intel_iommu *iommu, u16 did, u16 sid, u8 fm, desc.qw2 = 0; desc.qw3 = 0; - qi_submit_sync(&desc, iommu); + qi_submit_sync(iommu, &desc, 1, 0); } void qi_flush_iotlb(struct intel_iommu *iommu, u16 did, u64 addr, @@ -1355,7 +1369,7 @@ void qi_flush_iotlb(struct intel_iommu *iommu, u16 did, u64 addr, desc.qw2 = 0; desc.qw3 = 0; - qi_submit_sync(&desc, iommu); + qi_submit_sync(iommu, &desc, 1, 0); } void qi_flush_dev_iotlb(struct intel_iommu *iommu, u16 sid, u16 pfsid, @@ -1377,7 +1391,7 @@ void qi_flush_dev_iotlb(struct intel_iommu *iommu, u16 sid, u16 pfsid, desc.qw2 = 0; desc.qw3 = 0; - qi_submit_sync(&desc, iommu); + qi_submit_sync(iommu, &desc, 1, 0); } /* PASID-based IOTLB invalidation */ @@ -1418,7 +1432,46 @@ void qi_flush_piotlb(struct intel_iommu *iommu, u16 did, u32 pasid, u64 addr, QI_EIOTLB_AM(mask); } - qi_submit_sync(&desc, iommu); + qi_submit_sync(iommu, &desc, 1, 0); +} + +/* PASID-based device IOTLB Invalidate */ +void qi_flush_dev_iotlb_pasid(struct intel_iommu *iommu, u16 sid, u16 pfsid, + u32 pasid, u16 qdep, u64 addr, + unsigned int size_order, u64 granu) +{ + unsigned long mask = 1UL << (VTD_PAGE_SHIFT + size_order - 1); + struct qi_desc desc = {.qw1 = 0, .qw2 = 0, .qw3 = 0}; + + desc.qw0 = QI_DEV_EIOTLB_PASID(pasid) | QI_DEV_EIOTLB_SID(sid) | + QI_DEV_EIOTLB_QDEP(qdep) | QI_DEIOTLB_TYPE | + QI_DEV_IOTLB_PFSID(pfsid); + desc.qw1 = QI_DEV_EIOTLB_GLOB(granu); + + /* + * If S bit is 0, we only flush a single page. If S bit is set, + * The least significant zero bit indicates the invalidation address + * range. VT-d spec 6.5.2.6. + * e.g. address bit 12[0] indicates 8KB, 13[0] indicates 16KB. + * size order = 0 is PAGE_SIZE 4KB + * Max Invs Pending (MIP) is set to 0 for now until we have DIT in + * ECAP. + */ + desc.qw1 |= addr & ~mask; + if (size_order) + desc.qw1 |= QI_DEV_EIOTLB_SIZE; + + qi_submit_sync(iommu, &desc, 1, 0); +} + +void qi_flush_pasid_cache(struct intel_iommu *iommu, u16 did, + u64 granu, int pasid) +{ + struct qi_desc desc = {.qw1 = 0, .qw2 = 0, .qw3 = 0}; + + desc.qw0 = QI_PC_PASID(pasid) | QI_PC_DID(did) | + QI_PC_GRAN(granu) | QI_PC_TYPE; + qi_submit_sync(iommu, &desc, 1, 0); } /* diff --git a/drivers/iommu/hyperv-iommu.c b/drivers/iommu/hyperv-iommu.c index a386b83e0e34..3c0c67a99c7b 100644 --- a/drivers/iommu/hyperv-iommu.c +++ b/drivers/iommu/hyperv-iommu.c @@ -131,7 +131,7 @@ static int hyperv_irq_remapping_activate(struct irq_domain *domain, return 0; } -static struct irq_domain_ops hyperv_ir_domain_ops = { +static const struct irq_domain_ops hyperv_ir_domain_ops = { .alloc = hyperv_irq_remapping_alloc, .free = hyperv_irq_remapping_free, .activate = hyperv_irq_remapping_activate, diff --git a/drivers/iommu/intel-iommu-debugfs.c b/drivers/iommu/intel-iommu-debugfs.c index 3eb1fe240fb0..cf1ebb98e418 100644 --- a/drivers/iommu/intel-iommu-debugfs.c +++ b/drivers/iommu/intel-iommu-debugfs.c @@ -372,6 +372,66 @@ static int domain_translation_struct_show(struct seq_file *m, void *unused) } DEFINE_SHOW_ATTRIBUTE(domain_translation_struct); +static void invalidation_queue_entry_show(struct seq_file *m, + struct intel_iommu *iommu) +{ + int index, shift = qi_shift(iommu); + struct qi_desc *desc; + int offset; + + if (ecap_smts(iommu->ecap)) + seq_puts(m, "Index\t\tqw0\t\t\tqw1\t\t\tqw2\t\t\tqw3\t\t\tstatus\n"); + else + seq_puts(m, "Index\t\tqw0\t\t\tqw1\t\t\tstatus\n"); + + for (index = 0; index < QI_LENGTH; index++) { + offset = index << shift; + desc = iommu->qi->desc + offset; + if (ecap_smts(iommu->ecap)) + seq_printf(m, "%5d\t%016llx\t%016llx\t%016llx\t%016llx\t%016x\n", + index, desc->qw0, desc->qw1, + desc->qw2, desc->qw3, + iommu->qi->desc_status[index]); + else + seq_printf(m, "%5d\t%016llx\t%016llx\t%016x\n", + index, desc->qw0, desc->qw1, + iommu->qi->desc_status[index]); + } +} + +static int invalidation_queue_show(struct seq_file *m, void *unused) +{ + struct dmar_drhd_unit *drhd; + struct intel_iommu *iommu; + unsigned long flags; + struct q_inval *qi; + int shift; + + rcu_read_lock(); + for_each_active_iommu(iommu, drhd) { + qi = iommu->qi; + shift = qi_shift(iommu); + + if (!qi || !ecap_qis(iommu->ecap)) + continue; + + seq_printf(m, "Invalidation queue on IOMMU: %s\n", iommu->name); + + raw_spin_lock_irqsave(&qi->q_lock, flags); + seq_printf(m, " Base: 0x%llx\tHead: %lld\tTail: %lld\n", + (u64)virt_to_phys(qi->desc), + dmar_readq(iommu->reg + DMAR_IQH_REG) >> shift, + dmar_readq(iommu->reg + DMAR_IQT_REG) >> shift); + invalidation_queue_entry_show(m, iommu); + raw_spin_unlock_irqrestore(&qi->q_lock, flags); + seq_putc(m, '\n'); + } + rcu_read_unlock(); + + return 0; +} +DEFINE_SHOW_ATTRIBUTE(invalidation_queue); + #ifdef CONFIG_IRQ_REMAP static void ir_tbl_remap_entry_show(struct seq_file *m, struct intel_iommu *iommu) @@ -490,6 +550,8 @@ void __init intel_iommu_debugfs_init(void) debugfs_create_file("domain_translation_struct", 0444, intel_iommu_debug, NULL, &domain_translation_struct_fops); + debugfs_create_file("invalidation_queue", 0444, intel_iommu_debug, + NULL, &invalidation_queue_fops); #ifdef CONFIG_IRQ_REMAP debugfs_create_file("ir_translation_struct", 0444, intel_iommu_debug, NULL, &ir_translation_struct_fops); diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c index 34e08fa2ce3a..648a785e078a 100644 --- a/drivers/iommu/intel-iommu.c +++ b/drivers/iommu/intel-iommu.c @@ -296,31 +296,6 @@ static inline void context_clear_entry(struct context_entry *context) static struct dmar_domain *si_domain; static int hw_pass_through = 1; -/* si_domain contains mulitple devices */ -#define DOMAIN_FLAG_STATIC_IDENTITY BIT(0) - -/* - * This is a DMA domain allocated through the iommu domain allocation - * interface. But one or more devices belonging to this domain have - * been chosen to use a private domain. We should avoid to use the - * map/unmap/iova_to_phys APIs on it. - */ -#define DOMAIN_FLAG_LOSE_CHILDREN BIT(1) - -/* - * When VT-d works in the scalable mode, it allows DMA translation to - * happen through either first level or second level page table. This - * bit marks that the DMA translation for the domain goes through the - * first level page table, otherwise, it goes through the second level. - */ -#define DOMAIN_FLAG_USE_FIRST_LEVEL BIT(2) - -/* - * Domain represents a virtual machine which demands iommu nested - * translation mode support. - */ -#define DOMAIN_FLAG_NESTING_MODE BIT(3) - #define for_each_domain_iommu(idx, domain) \ for (idx = 0; idx < g_num_of_iommus; idx++) \ if (domain->iommu_refcnt[idx]) @@ -355,11 +330,6 @@ static void domain_exit(struct dmar_domain *domain); static void domain_remove_dev_info(struct dmar_domain *domain); static void dmar_remove_one_dev_info(struct device *dev); static void __dmar_remove_one_dev_info(struct device_domain_info *info); -static void domain_context_clear(struct intel_iommu *iommu, - struct device *dev); -static int domain_detach_iommu(struct dmar_domain *domain, - struct intel_iommu *iommu); -static bool device_is_rmrr_locked(struct device *dev); static int intel_iommu_attach_device(struct iommu_domain *domain, struct device *dev); static phys_addr_t intel_iommu_iova_to_phys(struct iommu_domain *domain, @@ -395,6 +365,21 @@ EXPORT_SYMBOL_GPL(intel_iommu_gfx_mapped); #define DUMMY_DEVICE_DOMAIN_INFO ((struct device_domain_info *)(-1)) #define DEFER_DEVICE_DOMAIN_INFO ((struct device_domain_info *)(-2)) +struct device_domain_info *get_domain_info(struct device *dev) +{ + struct device_domain_info *info; + + if (!dev) + return NULL; + + info = dev->archdata.iommu; + if (unlikely(info == DUMMY_DEVICE_DOMAIN_INFO || + info == DEFER_DEVICE_DOMAIN_INFO)) + return NULL; + + return info; +} + DEFINE_SPINLOCK(device_domain_lock); static LIST_HEAD(device_domain_list); @@ -446,12 +431,6 @@ static void init_translation_status(struct intel_iommu *iommu) iommu->flags |= VTD_FLAG_TRANS_PRE_ENABLED; } -/* Convert generic 'struct iommu_domain to private struct dmar_domain */ -static struct dmar_domain *to_dmar_domain(struct iommu_domain *dom) -{ - return container_of(dom, struct dmar_domain, domain); -} - static int __init intel_iommu_setup(char *str) { if (!str) @@ -480,8 +459,7 @@ static int __init intel_iommu_setup(char *str) pr_info("Intel-IOMMU: scalable mode supported\n"); intel_iommu_sm = 1; } else if (!strncmp(str, "tboot_noforce", 13)) { - printk(KERN_INFO - "Intel-IOMMU: not forcing on after tboot. This could expose security risk for tboot\n"); + pr_info("Intel-IOMMU: not forcing on after tboot. This could expose security risk for tboot\n"); intel_iommu_tboot_noforce = 1; } else if (!strncmp(str, "nobounce", 8)) { pr_info("Intel-IOMMU: No bounce buffer. This could expose security risks of DMA attacks\n"); @@ -1454,8 +1432,7 @@ static void iommu_enable_dev_iotlb(struct device_domain_info *info) !pci_reset_pri(pdev) && !pci_enable_pri(pdev, 32)) info->pri_enabled = 1; #endif - if (!pdev->untrusted && info->ats_supported && - pci_ats_page_aligned(pdev) && + if (info->ats_supported && pci_ats_page_aligned(pdev) && !pci_enable_ats(pdev, VTD_PAGE_SHIFT)) { info->ats_enabled = 1; domain_update_iotlb(info->domain); @@ -1763,6 +1740,9 @@ static void free_dmar_iommu(struct intel_iommu *iommu) if (ecap_prs(iommu->ecap)) intel_svm_finish_prq(iommu); } + if (ecap_vcs(iommu->ecap) && vccap_pasid(iommu->vccap)) + ioasid_unregister_allocator(&iommu->pasid_allocator); + #endif } @@ -1911,11 +1891,6 @@ static int dmar_init_reserved_ranges(void) return 0; } -static void domain_reserve_special_ranges(struct dmar_domain *domain) -{ - copy_reserved_iova(&reserved_iova_list, &domain->iovad); -} - static inline int guestwidth_to_adjustwidth(int gaw) { int agaw; @@ -1930,65 +1905,6 @@ static inline int guestwidth_to_adjustwidth(int gaw) return agaw; } -static int domain_init(struct dmar_domain *domain, struct intel_iommu *iommu, - int guest_width) -{ - int adjust_width, agaw; - unsigned long sagaw; - int ret; - - init_iova_domain(&domain->iovad, VTD_PAGE_SIZE, IOVA_START_PFN); - - if (!intel_iommu_strict) { - ret = init_iova_flush_queue(&domain->iovad, - iommu_flush_iova, iova_entry_free); - if (ret) - pr_info("iova flush queue initialization failed\n"); - } - - domain_reserve_special_ranges(domain); - - /* calculate AGAW */ - if (guest_width > cap_mgaw(iommu->cap)) - guest_width = cap_mgaw(iommu->cap); - domain->gaw = guest_width; - adjust_width = guestwidth_to_adjustwidth(guest_width); - agaw = width_to_agaw(adjust_width); - sagaw = cap_sagaw(iommu->cap); - if (!test_bit(agaw, &sagaw)) { - /* hardware doesn't support it, choose a bigger one */ - pr_debug("Hardware doesn't support agaw %d\n", agaw); - agaw = find_next_bit(&sagaw, 5, agaw); - if (agaw >= 5) - return -ENODEV; - } - domain->agaw = agaw; - - if (ecap_coherent(iommu->ecap)) - domain->iommu_coherency = 1; - else - domain->iommu_coherency = 0; - - if (ecap_sc_support(iommu->ecap)) - domain->iommu_snooping = 1; - else - domain->iommu_snooping = 0; - - if (intel_iommu_superpage) - domain->iommu_superpage = fls(cap_super_page_val(iommu->cap)); - else - domain->iommu_superpage = 0; - - domain->nid = iommu->node; - - /* always allocate the top pgd */ - domain->pgd = (struct dma_pte *)alloc_pgtable_page(domain->nid); - if (!domain->pgd) - return -ENOMEM; - __iommu_flush_cache(iommu, domain->pgd, PAGE_SIZE); - return 0; -} - static void domain_exit(struct dmar_domain *domain) { @@ -1996,7 +1912,8 @@ static void domain_exit(struct dmar_domain *domain) domain_remove_dev_info(domain); /* destroy iovas */ - put_iova_domain(&domain->iovad); + if (domain->domain.type == IOMMU_DOMAIN_DMA) + put_iova_domain(&domain->iovad); if (domain->pgd) { struct page *freelist; @@ -2518,11 +2435,8 @@ struct dmar_domain *find_domain(struct device *dev) if (unlikely(attach_deferred(dev) || iommu_dummy(dev))) return NULL; - if (dev_is_pci(dev)) - dev = &pci_real_dma_dev(to_pci_dev(dev))->dev; - /* No lock here, assumes no domain exit in normal case */ - info = dev->archdata.iommu; + info = get_domain_info(dev); if (likely(info)) return info->domain; @@ -2545,7 +2459,7 @@ dmar_search_domain_by_dev_info(int segment, int bus, int devfn) struct device_domain_info *info; list_for_each_entry(info, &device_domain_list, global) - if (info->iommu->segment == segment && info->bus == bus && + if (info->segment == segment && info->bus == bus && info->devfn == devfn) return info; @@ -2582,6 +2496,12 @@ static int domain_setup_first_level(struct intel_iommu *iommu, flags); } +static bool dev_is_real_dma_subdevice(struct device *dev) +{ + return dev && dev_is_pci(dev) && + pci_real_dma_dev(to_pci_dev(dev)) != to_pci_dev(dev); +} + static struct dmar_domain *dmar_insert_one_dev_info(struct intel_iommu *iommu, int bus, int devfn, struct device *dev, @@ -2596,8 +2516,18 @@ static struct dmar_domain *dmar_insert_one_dev_info(struct intel_iommu *iommu, if (!info) return NULL; - info->bus = bus; - info->devfn = devfn; + if (!dev_is_real_dma_subdevice(dev)) { + info->bus = bus; + info->devfn = devfn; + info->segment = iommu->segment; + } else { + struct pci_dev *pdev = to_pci_dev(dev); + + info->bus = pdev->bus->number; + info->devfn = pdev->devfn; + info->segment = pci_domain_nr(pdev->bus); + } + info->ats_supported = info->pasid_supported = info->pri_supported = 0; info->ats_enabled = info->pasid_enabled = info->pri_enabled = 0; info->ats_qdep = 0; @@ -2611,10 +2541,8 @@ static struct dmar_domain *dmar_insert_one_dev_info(struct intel_iommu *iommu, if (dev && dev_is_pci(dev)) { struct pci_dev *pdev = to_pci_dev(info->dev); - if (!pdev->untrusted && - !pci_ats_disabled() && - ecap_dev_iotlb_support(iommu->ecap) && - pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_ATS) && + if (ecap_dev_iotlb_support(iommu->ecap) && + pci_ats_supported(pdev) && dmar_find_matched_atsr_unit(pdev)) info->ats_supported = 1; @@ -2637,7 +2565,8 @@ static struct dmar_domain *dmar_insert_one_dev_info(struct intel_iommu *iommu, if (!found) { struct device_domain_info *info2; - info2 = dmar_search_domain_by_dev_info(iommu->segment, bus, devfn); + info2 = dmar_search_domain_by_dev_info(info->segment, info->bus, + info->devfn); if (info2) { found = info2->domain; info2->dev = dev; @@ -2704,108 +2633,10 @@ static struct dmar_domain *dmar_insert_one_dev_info(struct intel_iommu *iommu, return domain; } -static int get_last_alias(struct pci_dev *pdev, u16 alias, void *opaque) -{ - *(u16 *)opaque = alias; - return 0; -} - -static struct dmar_domain *find_or_alloc_domain(struct device *dev, int gaw) -{ - struct device_domain_info *info; - struct dmar_domain *domain = NULL; - struct intel_iommu *iommu; - u16 dma_alias; - unsigned long flags; - u8 bus, devfn; - - iommu = device_to_iommu(dev, &bus, &devfn); - if (!iommu) - return NULL; - - if (dev_is_pci(dev)) { - struct pci_dev *pdev = to_pci_dev(dev); - - pci_for_each_dma_alias(pdev, get_last_alias, &dma_alias); - - spin_lock_irqsave(&device_domain_lock, flags); - info = dmar_search_domain_by_dev_info(pci_domain_nr(pdev->bus), - PCI_BUS_NUM(dma_alias), - dma_alias & 0xff); - if (info) { - iommu = info->iommu; - domain = info->domain; - } - spin_unlock_irqrestore(&device_domain_lock, flags); - - /* DMA alias already has a domain, use it */ - if (info) - goto out; - } - - /* Allocate and initialize new domain for the device */ - domain = alloc_domain(0); - if (!domain) - return NULL; - if (domain_init(domain, iommu, gaw)) { - domain_exit(domain); - return NULL; - } - -out: - return domain; -} - -static struct dmar_domain *set_domain_for_dev(struct device *dev, - struct dmar_domain *domain) -{ - struct intel_iommu *iommu; - struct dmar_domain *tmp; - u16 req_id, dma_alias; - u8 bus, devfn; - - iommu = device_to_iommu(dev, &bus, &devfn); - if (!iommu) - return NULL; - - req_id = ((u16)bus << 8) | devfn; - - if (dev_is_pci(dev)) { - struct pci_dev *pdev = to_pci_dev(dev); - - pci_for_each_dma_alias(pdev, get_last_alias, &dma_alias); - - /* register PCI DMA alias device */ - if (req_id != dma_alias) { - tmp = dmar_insert_one_dev_info(iommu, PCI_BUS_NUM(dma_alias), - dma_alias & 0xff, NULL, domain); - - if (!tmp || tmp != domain) - return tmp; - } - } - - tmp = dmar_insert_one_dev_info(iommu, bus, devfn, dev, domain); - if (!tmp || tmp != domain) - return tmp; - - return domain; -} - static int iommu_domain_identity_map(struct dmar_domain *domain, - unsigned long long start, - unsigned long long end) + unsigned long first_vpfn, + unsigned long last_vpfn) { - unsigned long first_vpfn = start >> VTD_PAGE_SHIFT; - unsigned long last_vpfn = end >> VTD_PAGE_SHIFT; - - if (!reserve_iova(&domain->iovad, dma_to_mm_pfn(first_vpfn), - dma_to_mm_pfn(last_vpfn))) { - pr_err("Reserving iova failed\n"); - return -ENOMEM; - } - - pr_debug("Mapping reserved region %llx-%llx\n", start, end); /* * RMRR range might have overlap with physical memory range, * clear it first @@ -2817,45 +2648,6 @@ static int iommu_domain_identity_map(struct dmar_domain *domain, DMA_PTE_READ|DMA_PTE_WRITE); } -static int domain_prepare_identity_map(struct device *dev, - struct dmar_domain *domain, - unsigned long long start, - unsigned long long end) -{ - /* For _hardware_ passthrough, don't bother. But for software - passthrough, we do it anyway -- it may indicate a memory - range which is reserved in E820, so which didn't get set - up to start with in si_domain */ - if (domain == si_domain && hw_pass_through) { - dev_warn(dev, "Ignoring identity map for HW passthrough [0x%Lx - 0x%Lx]\n", - start, end); - return 0; - } - - dev_info(dev, "Setting identity map [0x%Lx - 0x%Lx]\n", start, end); - - if (end < start) { - WARN(1, "Your BIOS is broken; RMRR ends before it starts!\n" - "BIOS vendor: %s; Ver: %s; Product Version: %s\n", - dmi_get_system_info(DMI_BIOS_VENDOR), - dmi_get_system_info(DMI_BIOS_VERSION), - dmi_get_system_info(DMI_PRODUCT_VERSION)); - return -EIO; - } - - if (end >> agaw_to_width(domain->agaw)) { - WARN(1, "Your BIOS is broken; RMRR exceeds permitted address width (%d bits)\n" - "BIOS vendor: %s; Ver: %s; Product Version: %s\n", - agaw_to_width(domain->agaw), - dmi_get_system_info(DMI_BIOS_VENDOR), - dmi_get_system_info(DMI_BIOS_VERSION), - dmi_get_system_info(DMI_PRODUCT_VERSION)); - return -EIO; - } - - return iommu_domain_identity_map(domain, start, end); -} - static int md_domain_init(struct dmar_domain *domain, int guest_width); static int __init si_domain_init(int hw) @@ -2882,7 +2674,8 @@ static int __init si_domain_init(int hw) for_each_mem_pfn_range(i, nid, &start_pfn, &end_pfn, NULL) { ret = iommu_domain_identity_map(si_domain, - PFN_PHYS(start_pfn), PFN_PHYS(end_pfn)); + mm_to_dma_pfn(start_pfn), + mm_to_dma_pfn(end_pfn)); if (ret) return ret; } @@ -2911,17 +2704,6 @@ static int __init si_domain_init(int hw) return 0; } -static int identity_mapping(struct device *dev) -{ - struct device_domain_info *info; - - info = dev->archdata.iommu; - if (info) - return (info->domain == si_domain); - - return 0; -} - static int domain_add_dev_info(struct dmar_domain *domain, struct device *dev) { struct dmar_domain *ndomain; @@ -3048,31 +2830,6 @@ static int device_def_domain_type(struct device *dev) if ((iommu_identity_mapping & IDENTMAP_GFX) && IS_GFX_DEVICE(pdev)) return IOMMU_DOMAIN_IDENTITY; - - /* - * We want to start off with all devices in the 1:1 domain, and - * take them out later if we find they can't access all of memory. - * - * However, we can't do this for PCI devices behind bridges, - * because all PCI devices behind the same bridge will end up - * with the same source-id on their transactions. - * - * Practically speaking, we can't change things around for these - * devices at run-time, because we can't be sure there'll be no - * DMA transactions in flight for any of their siblings. - * - * So PCI devices (unless they're on the root bus) as well as - * their parent PCI-PCI or PCIe-PCI bridges must be left _out_ of - * the 1:1 domain, just in _case_ one of their siblings turns out - * not to be able to map all of memory. - */ - if (!pci_is_pcie(pdev)) { - if (!pci_is_root_bus(pdev->bus)) - return IOMMU_DOMAIN_DMA; - if (pdev->class >> 8 == PCI_CLASS_BRIDGE_PCI) - return IOMMU_DOMAIN_DMA; - } else if (pci_pcie_type(pdev) == PCI_EXP_TYPE_PCI_BRIDGE) - return IOMMU_DOMAIN_DMA; } return 0; @@ -3297,6 +3054,85 @@ out_unmap: return ret; } +#ifdef CONFIG_INTEL_IOMMU_SVM +static ioasid_t intel_vcmd_ioasid_alloc(ioasid_t min, ioasid_t max, void *data) +{ + struct intel_iommu *iommu = data; + ioasid_t ioasid; + + if (!iommu) + return INVALID_IOASID; + /* + * VT-d virtual command interface always uses the full 20 bit + * PASID range. Host can partition guest PASID range based on + * policies but it is out of guest's control. + */ + if (min < PASID_MIN || max > intel_pasid_max_id) + return INVALID_IOASID; + + if (vcmd_alloc_pasid(iommu, &ioasid)) + return INVALID_IOASID; + + return ioasid; +} + +static void intel_vcmd_ioasid_free(ioasid_t ioasid, void *data) +{ + struct intel_iommu *iommu = data; + + if (!iommu) + return; + /* + * Sanity check the ioasid owner is done at upper layer, e.g. VFIO + * We can only free the PASID when all the devices are unbound. + */ + if (ioasid_find(NULL, ioasid, NULL)) { + pr_alert("Cannot free active IOASID %d\n", ioasid); + return; + } + vcmd_free_pasid(iommu, ioasid); +} + +static void register_pasid_allocator(struct intel_iommu *iommu) +{ + /* + * If we are running in the host, no need for custom allocator + * in that PASIDs are allocated from the host system-wide. + */ + if (!cap_caching_mode(iommu->cap)) + return; + + if (!sm_supported(iommu)) { + pr_warn("VT-d Scalable Mode not enabled, no PASID allocation\n"); + return; + } + + /* + * Register a custom PASID allocator if we are running in a guest, + * guest PASID must be obtained via virtual command interface. + * There can be multiple vIOMMUs in each guest but only one allocator + * is active. All vIOMMU allocators will eventually be calling the same + * host allocator. + */ + if (!ecap_vcs(iommu->ecap) || !vccap_pasid(iommu->vccap)) + return; + + pr_info("Register custom PASID allocator\n"); + iommu->pasid_allocator.alloc = intel_vcmd_ioasid_alloc; + iommu->pasid_allocator.free = intel_vcmd_ioasid_free; + iommu->pasid_allocator.pdata = (void *)iommu; + if (ioasid_register_allocator(&iommu->pasid_allocator)) { + pr_warn("Custom PASID allocator failed, scalable mode disabled\n"); + /* + * Disable scalable mode on this IOMMU if there + * is no custom allocator. Mixing SM capable vIOMMU + * and non-SM vIOMMU are not supported. + */ + intel_iommu_sm = 0; + } +} +#endif + static int __init init_dmars(void) { struct dmar_drhd_unit *drhd; @@ -3414,6 +3250,9 @@ static int __init init_dmars(void) */ for_each_active_iommu(iommu, drhd) { iommu_flush_write_buffer(iommu); +#ifdef CONFIG_INTEL_IOMMU_SVM + register_pasid_allocator(iommu); +#endif iommu_set_root_entry(iommu); iommu->flush.flush_context(iommu, 0, 0, 0, DMA_CCMD_GLOBAL_INVL); iommu->flush.flush_iotlb(iommu, 0, 0, 0, DMA_TLB_GLOBAL_FLUSH); @@ -3531,100 +3370,6 @@ static unsigned long intel_alloc_iova(struct device *dev, return iova_pfn; } -static struct dmar_domain *get_private_domain_for_dev(struct device *dev) -{ - struct dmar_domain *domain, *tmp; - struct dmar_rmrr_unit *rmrr; - struct device *i_dev; - int i, ret; - - /* Device shouldn't be attached by any domains. */ - domain = find_domain(dev); - if (domain) - return NULL; - - domain = find_or_alloc_domain(dev, DEFAULT_DOMAIN_ADDRESS_WIDTH); - if (!domain) - goto out; - - /* We have a new domain - setup possible RMRRs for the device */ - rcu_read_lock(); - for_each_rmrr_units(rmrr) { - for_each_active_dev_scope(rmrr->devices, rmrr->devices_cnt, - i, i_dev) { - if (i_dev != dev) - continue; - - ret = domain_prepare_identity_map(dev, domain, - rmrr->base_address, - rmrr->end_address); - if (ret) - dev_err(dev, "Mapping reserved region failed\n"); - } - } - rcu_read_unlock(); - - tmp = set_domain_for_dev(dev, domain); - if (!tmp || domain != tmp) { - domain_exit(domain); - domain = tmp; - } - -out: - if (!domain) - dev_err(dev, "Allocating domain failed\n"); - else - domain->domain.type = IOMMU_DOMAIN_DMA; - - return domain; -} - -/* Check if the dev needs to go through non-identity map and unmap process.*/ -static bool iommu_need_mapping(struct device *dev) -{ - int ret; - - if (iommu_dummy(dev)) - return false; - - if (unlikely(attach_deferred(dev))) - do_deferred_attach(dev); - - ret = identity_mapping(dev); - if (ret) { - u64 dma_mask = *dev->dma_mask; - - if (dev->coherent_dma_mask && dev->coherent_dma_mask < dma_mask) - dma_mask = dev->coherent_dma_mask; - - if (dma_mask >= dma_direct_get_required_mask(dev)) - return false; - - /* - * 32 bit DMA is removed from si_domain and fall back to - * non-identity mapping. - */ - dmar_remove_one_dev_info(dev); - ret = iommu_request_dma_domain_for_dev(dev); - if (ret) { - struct iommu_domain *domain; - struct dmar_domain *dmar_domain; - - domain = iommu_get_domain_for_dev(dev); - if (domain) { - dmar_domain = to_dmar_domain(domain); - dmar_domain->flags |= DOMAIN_FLAG_LOSE_CHILDREN; - } - dmar_remove_one_dev_info(dev); - get_private_domain_for_dev(dev); - } - - dev_info(dev, "32bit DMA uses non-identity mapping\n"); - } - - return true; -} - static dma_addr_t __intel_map_single(struct device *dev, phys_addr_t paddr, size_t size, int dir, u64 dma_mask) { @@ -3638,6 +3383,9 @@ static dma_addr_t __intel_map_single(struct device *dev, phys_addr_t paddr, BUG_ON(dir == DMA_NONE); + if (unlikely(attach_deferred(dev))) + do_deferred_attach(dev); + domain = find_domain(dev); if (!domain) return DMA_MAPPING_ERROR; @@ -3689,20 +3437,15 @@ static dma_addr_t intel_map_page(struct device *dev, struct page *page, enum dma_data_direction dir, unsigned long attrs) { - if (iommu_need_mapping(dev)) - return __intel_map_single(dev, page_to_phys(page) + offset, - size, dir, *dev->dma_mask); - return dma_direct_map_page(dev, page, offset, size, dir, attrs); + return __intel_map_single(dev, page_to_phys(page) + offset, + size, dir, *dev->dma_mask); } static dma_addr_t intel_map_resource(struct device *dev, phys_addr_t phys_addr, size_t size, enum dma_data_direction dir, unsigned long attrs) { - if (iommu_need_mapping(dev)) - return __intel_map_single(dev, phys_addr, size, dir, - *dev->dma_mask); - return dma_direct_map_resource(dev, phys_addr, size, dir, attrs); + return __intel_map_single(dev, phys_addr, size, dir, *dev->dma_mask); } static void intel_unmap(struct device *dev, dma_addr_t dev_addr, size_t size) @@ -3753,17 +3496,13 @@ static void intel_unmap_page(struct device *dev, dma_addr_t dev_addr, size_t size, enum dma_data_direction dir, unsigned long attrs) { - if (iommu_need_mapping(dev)) - intel_unmap(dev, dev_addr, size); - else - dma_direct_unmap_page(dev, dev_addr, size, dir, attrs); + intel_unmap(dev, dev_addr, size); } static void intel_unmap_resource(struct device *dev, dma_addr_t dev_addr, size_t size, enum dma_data_direction dir, unsigned long attrs) { - if (iommu_need_mapping(dev)) - intel_unmap(dev, dev_addr, size); + intel_unmap(dev, dev_addr, size); } static void *intel_alloc_coherent(struct device *dev, size_t size, @@ -3773,8 +3512,8 @@ static void *intel_alloc_coherent(struct device *dev, size_t size, struct page *page = NULL; int order; - if (!iommu_need_mapping(dev)) - return dma_direct_alloc(dev, size, dma_handle, flags, attrs); + if (unlikely(attach_deferred(dev))) + do_deferred_attach(dev); size = PAGE_ALIGN(size); order = get_order(size); @@ -3809,9 +3548,6 @@ static void intel_free_coherent(struct device *dev, size_t size, void *vaddr, int order; struct page *page = virt_to_page(vaddr); - if (!iommu_need_mapping(dev)) - return dma_direct_free(dev, size, vaddr, dma_handle, attrs); - size = PAGE_ALIGN(size); order = get_order(size); @@ -3829,9 +3565,6 @@ static void intel_unmap_sg(struct device *dev, struct scatterlist *sglist, struct scatterlist *sg; int i; - if (!iommu_need_mapping(dev)) - return dma_direct_unmap_sg(dev, sglist, nelems, dir, attrs); - for_each_sg(sglist, sg, nelems, i) { nrpages += aligned_nrpages(sg_dma_address(sg), sg_dma_len(sg)); } @@ -3855,8 +3588,9 @@ static int intel_map_sg(struct device *dev, struct scatterlist *sglist, int nele struct intel_iommu *iommu; BUG_ON(dir == DMA_NONE); - if (!iommu_need_mapping(dev)) - return dma_direct_map_sg(dev, sglist, nelems, dir, attrs); + + if (unlikely(attach_deferred(dev))) + do_deferred_attach(dev); domain = find_domain(dev); if (!domain) @@ -3903,8 +3637,6 @@ static int intel_map_sg(struct device *dev, struct scatterlist *sglist, int nele static u64 intel_get_required_mask(struct device *dev) { - if (!iommu_need_mapping(dev)) - return dma_direct_get_required_mask(dev); return DMA_BIT_MASK(32); } @@ -4813,58 +4545,37 @@ static int intel_iommu_memory_notifier(struct notifier_block *nb, unsigned long val, void *v) { struct memory_notify *mhp = v; - unsigned long long start, end; - unsigned long start_vpfn, last_vpfn; + unsigned long start_vpfn = mm_to_dma_pfn(mhp->start_pfn); + unsigned long last_vpfn = mm_to_dma_pfn(mhp->start_pfn + + mhp->nr_pages - 1); switch (val) { case MEM_GOING_ONLINE: - start = mhp->start_pfn << PAGE_SHIFT; - end = ((mhp->start_pfn + mhp->nr_pages) << PAGE_SHIFT) - 1; - if (iommu_domain_identity_map(si_domain, start, end)) { - pr_warn("Failed to build identity map for [%llx-%llx]\n", - start, end); + if (iommu_domain_identity_map(si_domain, + start_vpfn, last_vpfn)) { + pr_warn("Failed to build identity map for [%lx-%lx]\n", + start_vpfn, last_vpfn); return NOTIFY_BAD; } break; case MEM_OFFLINE: case MEM_CANCEL_ONLINE: - start_vpfn = mm_to_dma_pfn(mhp->start_pfn); - last_vpfn = mm_to_dma_pfn(mhp->start_pfn + mhp->nr_pages - 1); - while (start_vpfn <= last_vpfn) { - struct iova *iova; + { struct dmar_drhd_unit *drhd; struct intel_iommu *iommu; struct page *freelist; - iova = find_iova(&si_domain->iovad, start_vpfn); - if (iova == NULL) { - pr_debug("Failed get IOVA for PFN %lx\n", - start_vpfn); - break; - } - - iova = split_and_remove_iova(&si_domain->iovad, iova, - start_vpfn, last_vpfn); - if (iova == NULL) { - pr_warn("Failed to split IOVA PFN [%lx-%lx]\n", - start_vpfn, last_vpfn); - return NOTIFY_BAD; - } - - freelist = domain_unmap(si_domain, iova->pfn_lo, - iova->pfn_hi); + freelist = domain_unmap(si_domain, + start_vpfn, last_vpfn); rcu_read_lock(); for_each_active_iommu(iommu, drhd) iommu_flush_iotlb_psi(iommu, si_domain, - iova->pfn_lo, iova_size(iova), + start_vpfn, mhp->nr_pages, !freelist, 0); rcu_read_unlock(); dma_free_pagelist(freelist); - - start_vpfn = iova->pfn_hi + 1; - free_iova_mem(iova); } break; } @@ -4892,8 +4603,9 @@ static void free_all_cpu_cached_iovas(unsigned int cpu) for (did = 0; did < cap_ndoms(iommu->cap); did++) { domain = get_iommu_domain(iommu, (u16)did); - if (!domain) + if (!domain || domain->domain.type != IOMMU_DOMAIN_DMA) continue; + free_cpu_cached_iovas(cpu, &domain->iovad); } } @@ -5186,18 +4898,6 @@ int __init intel_iommu_init(void) } up_write(&dmar_global_lock); -#if defined(CONFIG_X86) && defined(CONFIG_SWIOTLB) - /* - * If the system has no untrusted device or the user has decided - * to disable the bounce page mechanisms, we don't need swiotlb. - * Mark this and the pre-allocated bounce pages will be released - * later. - */ - if (!has_untrusted_dev() || intel_no_bounce) - swiotlb = 0; -#endif - dma_ops = &intel_dma_ops; - init_iommu_pm_ops(); down_read(&dmar_global_lock); @@ -5283,10 +4983,11 @@ static void __dmar_remove_one_dev_info(struct device_domain_info *info) if (info->dev) { if (dev_is_pci(info->dev) && sm_supported(iommu)) intel_pasid_tear_down_entry(iommu, info->dev, - PASID_RID2PASID); + PASID_RID2PASID, false); iommu_disable_dev_iotlb(info); - domain_context_clear(iommu, info->dev); + if (!dev_is_real_dma_subdevice(info->dev)) + domain_context_clear(iommu, info->dev); intel_pasid_free_table(info->dev); } @@ -5296,12 +4997,6 @@ static void __dmar_remove_one_dev_info(struct device_domain_info *info) domain_detach_iommu(domain, iommu); spin_unlock_irqrestore(&iommu->lock, flags); - /* free the private domain */ - if (domain->flags & DOMAIN_FLAG_LOSE_CHILDREN && - !(domain->flags & DOMAIN_FLAG_STATIC_IDENTITY) && - list_empty(&domain->devices)) - domain_exit(info->domain); - free_devinfo_mem(info); } @@ -5311,9 +5006,8 @@ static void dmar_remove_one_dev_info(struct device *dev) unsigned long flags; spin_lock_irqsave(&device_domain_lock, flags); - info = dev->archdata.iommu; - if (info && info != DEFER_DEVICE_DOMAIN_INFO - && info != DUMMY_DEVICE_DOMAIN_INFO) + info = get_domain_info(dev); + if (info) __dmar_remove_one_dev_info(info); spin_unlock_irqrestore(&device_domain_lock, flags); } @@ -5322,9 +5016,6 @@ static int md_domain_init(struct dmar_domain *domain, int guest_width) { int adjust_width; - init_iova_domain(&domain->iovad, VTD_PAGE_SIZE, IOVA_START_PFN); - domain_reserve_special_ranges(domain); - /* calculate AGAW */ domain->gaw = guest_width; adjust_width = guestwidth_to_adjustwidth(guest_width); @@ -5343,11 +5034,21 @@ static int md_domain_init(struct dmar_domain *domain, int guest_width) return 0; } +static void intel_init_iova_domain(struct dmar_domain *dmar_domain) +{ + init_iova_domain(&dmar_domain->iovad, VTD_PAGE_SIZE, IOVA_START_PFN); + copy_reserved_iova(&reserved_iova_list, &dmar_domain->iovad); + + if (!intel_iommu_strict && + init_iova_flush_queue(&dmar_domain->iovad, + iommu_flush_iova, iova_entry_free)) + pr_info("iova flush queue initialization failed\n"); +} + static struct iommu_domain *intel_iommu_domain_alloc(unsigned type) { struct dmar_domain *dmar_domain; struct iommu_domain *domain; - int ret; switch (type) { case IOMMU_DOMAIN_DMA: @@ -5364,13 +5065,8 @@ static struct iommu_domain *intel_iommu_domain_alloc(unsigned type) return NULL; } - if (!intel_iommu_strict && type == IOMMU_DOMAIN_DMA) { - ret = init_iova_flush_queue(&dmar_domain->iovad, - iommu_flush_iova, - iova_entry_free); - if (ret) - pr_info("iova flush queue initialization failed\n"); - } + if (type == IOMMU_DOMAIN_DMA) + intel_init_iova_domain(dmar_domain); domain_update_iommu_cap(dmar_domain); @@ -5403,7 +5099,7 @@ static void intel_iommu_domain_free(struct iommu_domain *domain) static inline bool is_aux_domain(struct device *dev, struct iommu_domain *domain) { - struct device_domain_info *info = dev->archdata.iommu; + struct device_domain_info *info = get_domain_info(dev); return info && info->auxd_enabled && domain->type == IOMMU_DOMAIN_UNMANAGED; @@ -5412,7 +5108,7 @@ is_aux_domain(struct device *dev, struct iommu_domain *domain) static void auxiliary_link_device(struct dmar_domain *domain, struct device *dev) { - struct device_domain_info *info = dev->archdata.iommu; + struct device_domain_info *info = get_domain_info(dev); assert_spin_locked(&device_domain_lock); if (WARN_ON(!info)) @@ -5425,7 +5121,7 @@ static void auxiliary_link_device(struct dmar_domain *domain, static void auxiliary_unlink_device(struct dmar_domain *domain, struct device *dev) { - struct device_domain_info *info = dev->archdata.iommu; + struct device_domain_info *info = get_domain_info(dev); assert_spin_locked(&device_domain_lock); if (WARN_ON(!info)) @@ -5513,13 +5209,13 @@ static void aux_domain_remove_dev(struct dmar_domain *domain, return; spin_lock_irqsave(&device_domain_lock, flags); - info = dev->archdata.iommu; + info = get_domain_info(dev); iommu = info->iommu; auxiliary_unlink_device(domain, dev); spin_lock(&iommu->lock); - intel_pasid_tear_down_entry(iommu, dev, domain->default_pasid); + intel_pasid_tear_down_entry(iommu, dev, domain->default_pasid, false); domain_detach_iommu(domain, iommu); spin_unlock(&iommu->lock); @@ -5626,6 +5322,176 @@ static void intel_iommu_aux_detach_device(struct iommu_domain *domain, aux_domain_remove_dev(to_dmar_domain(domain), dev); } +/* + * 2D array for converting and sanitizing IOMMU generic TLB granularity to + * VT-d granularity. Invalidation is typically included in the unmap operation + * as a result of DMA or VFIO unmap. However, for assigned devices guest + * owns the first level page tables. Invalidations of translation caches in the + * guest are trapped and passed down to the host. + * + * vIOMMU in the guest will only expose first level page tables, therefore + * we do not support IOTLB granularity for request without PASID (second level). + * + * For example, to find the VT-d granularity encoding for IOTLB + * type and page selective granularity within PASID: + * X: indexed by iommu cache type + * Y: indexed by enum iommu_inv_granularity + * [IOMMU_CACHE_INV_TYPE_IOTLB][IOMMU_INV_GRANU_ADDR] + */ + +static const int +inv_type_granu_table[IOMMU_CACHE_INV_TYPE_NR][IOMMU_INV_GRANU_NR] = { + /* + * PASID based IOTLB invalidation: PASID selective (per PASID), + * page selective (address granularity) + */ + {-EINVAL, QI_GRAN_NONG_PASID, QI_GRAN_PSI_PASID}, + /* PASID based dev TLBs */ + {-EINVAL, -EINVAL, QI_DEV_IOTLB_GRAN_PASID_SEL}, + /* PASID cache */ + {-EINVAL, -EINVAL, -EINVAL} +}; + +static inline int to_vtd_granularity(int type, int granu) +{ + return inv_type_granu_table[type][granu]; +} + +static inline u64 to_vtd_size(u64 granu_size, u64 nr_granules) +{ + u64 nr_pages = (granu_size * nr_granules) >> VTD_PAGE_SHIFT; + + /* VT-d size is encoded as 2^size of 4K pages, 0 for 4k, 9 for 2MB, etc. + * IOMMU cache invalidate API passes granu_size in bytes, and number of + * granu size in contiguous memory. + */ + return order_base_2(nr_pages); +} + +#ifdef CONFIG_INTEL_IOMMU_SVM +static int +intel_iommu_sva_invalidate(struct iommu_domain *domain, struct device *dev, + struct iommu_cache_invalidate_info *inv_info) +{ + struct dmar_domain *dmar_domain = to_dmar_domain(domain); + struct device_domain_info *info; + struct intel_iommu *iommu; + unsigned long flags; + int cache_type; + u8 bus, devfn; + u16 did, sid; + int ret = 0; + u64 size = 0; + + if (!inv_info || !dmar_domain || + inv_info->version != IOMMU_CACHE_INVALIDATE_INFO_VERSION_1) + return -EINVAL; + + if (!dev || !dev_is_pci(dev)) + return -ENODEV; + + iommu = device_to_iommu(dev, &bus, &devfn); + if (!iommu) + return -ENODEV; + + if (!(dmar_domain->flags & DOMAIN_FLAG_NESTING_MODE)) + return -EINVAL; + + spin_lock_irqsave(&device_domain_lock, flags); + spin_lock(&iommu->lock); + info = get_domain_info(dev); + if (!info) { + ret = -EINVAL; + goto out_unlock; + } + did = dmar_domain->iommu_did[iommu->seq_id]; + sid = PCI_DEVID(bus, devfn); + + /* Size is only valid in address selective invalidation */ + if (inv_info->granularity != IOMMU_INV_GRANU_PASID) + size = to_vtd_size(inv_info->addr_info.granule_size, + inv_info->addr_info.nb_granules); + + for_each_set_bit(cache_type, + (unsigned long *)&inv_info->cache, + IOMMU_CACHE_INV_TYPE_NR) { + int granu = 0; + u64 pasid = 0; + + granu = to_vtd_granularity(cache_type, inv_info->granularity); + if (granu == -EINVAL) { + pr_err_ratelimited("Invalid cache type and granu combination %d/%d\n", + cache_type, inv_info->granularity); + break; + } + + /* + * PASID is stored in different locations based on the + * granularity. + */ + if (inv_info->granularity == IOMMU_INV_GRANU_PASID && + (inv_info->pasid_info.flags & IOMMU_INV_PASID_FLAGS_PASID)) + pasid = inv_info->pasid_info.pasid; + else if (inv_info->granularity == IOMMU_INV_GRANU_ADDR && + (inv_info->addr_info.flags & IOMMU_INV_ADDR_FLAGS_PASID)) + pasid = inv_info->addr_info.pasid; + + switch (BIT(cache_type)) { + case IOMMU_CACHE_INV_TYPE_IOTLB: + if (inv_info->granularity == IOMMU_INV_GRANU_ADDR && + size && + (inv_info->addr_info.addr & ((BIT(VTD_PAGE_SHIFT + size)) - 1))) { + pr_err_ratelimited("Address out of range, 0x%llx, size order %llu\n", + inv_info->addr_info.addr, size); + ret = -ERANGE; + goto out_unlock; + } + + /* + * If granu is PASID-selective, address is ignored. + * We use npages = -1 to indicate that. + */ + qi_flush_piotlb(iommu, did, pasid, + mm_to_dma_pfn(inv_info->addr_info.addr), + (granu == QI_GRAN_NONG_PASID) ? -1 : 1 << size, + inv_info->addr_info.flags & IOMMU_INV_ADDR_FLAGS_LEAF); + + /* + * Always flush device IOTLB if ATS is enabled. vIOMMU + * in the guest may assume IOTLB flush is inclusive, + * which is more efficient. + */ + if (info->ats_enabled) + qi_flush_dev_iotlb_pasid(iommu, sid, + info->pfsid, pasid, + info->ats_qdep, + inv_info->addr_info.addr, + size, granu); + break; + case IOMMU_CACHE_INV_TYPE_DEV_IOTLB: + if (info->ats_enabled) + qi_flush_dev_iotlb_pasid(iommu, sid, + info->pfsid, pasid, + info->ats_qdep, + inv_info->addr_info.addr, + size, granu); + else + pr_warn_ratelimited("Passdown device IOTLB flush w/o ATS!\n"); + break; + default: + dev_err_ratelimited(dev, "Unsupported IOMMU invalidation type %d\n", + cache_type); + ret = -EINVAL; + } + } +out_unlock: + spin_unlock(&iommu->lock); + spin_unlock_irqrestore(&device_domain_lock, flags); + + return ret; +} +#endif + static int intel_iommu_map(struct iommu_domain *domain, unsigned long iova, phys_addr_t hpa, size_t size, int iommu_prot, gfp_t gfp) @@ -5793,11 +5659,6 @@ static struct iommu_device *intel_iommu_probe_device(struct device *dev) if (translation_pre_enabled(iommu)) dev->archdata.iommu = DEFER_DEVICE_DOMAIN_INFO; - if (device_needs_bounce(dev)) { - dev_info(dev, "Use Intel IOMMU bounce page dma_ops\n"); - set_dma_ops(dev, &bounce_dma_ops); - } - return &iommu->iommu; } @@ -5812,7 +5673,19 @@ static void intel_iommu_release_device(struct device *dev) dmar_remove_one_dev_info(dev); + set_dma_ops(dev, NULL); +} + +static void intel_iommu_probe_finalize(struct device *dev) +{ + struct iommu_domain *domain; + + domain = iommu_get_domain_for_dev(dev); if (device_needs_bounce(dev)) + set_dma_ops(dev, &bounce_dma_ops); + else if (domain && domain->type == IOMMU_DOMAIN_DMA) + set_dma_ops(dev, &intel_dma_ops); + else set_dma_ops(dev, NULL); } @@ -5890,7 +5763,7 @@ int intel_iommu_enable_pasid(struct intel_iommu *iommu, struct device *dev) spin_lock(&iommu->lock); ret = -EINVAL; - info = dev->archdata.iommu; + info = get_domain_info(dev); if (!info || !info->pasid_supported) goto out; @@ -5986,7 +5859,7 @@ static int intel_iommu_enable_auxd(struct device *dev) return -ENODEV; spin_lock_irqsave(&device_domain_lock, flags); - info = dev->archdata.iommu; + info = get_domain_info(dev); info->auxd_enabled = 1; spin_unlock_irqrestore(&device_domain_lock, flags); @@ -5999,7 +5872,7 @@ static int intel_iommu_disable_auxd(struct device *dev) unsigned long flags; spin_lock_irqsave(&device_domain_lock, flags); - info = dev->archdata.iommu; + info = get_domain_info(dev); if (!WARN_ON(!info)) info->auxd_enabled = 0; spin_unlock_irqrestore(&device_domain_lock, flags); @@ -6052,6 +5925,14 @@ intel_iommu_dev_has_feat(struct device *dev, enum iommu_dev_features feat) return !!siov_find_pci_dvsec(to_pci_dev(dev)); } + if (feat == IOMMU_DEV_FEAT_SVA) { + struct device_domain_info *info = get_domain_info(dev); + + return info && (info->iommu->flags & VTD_FLAG_SVM_CAPABLE) && + info->pasid_supported && info->pri_supported && + info->ats_supported; + } + return false; } @@ -6061,6 +5942,16 @@ intel_iommu_dev_enable_feat(struct device *dev, enum iommu_dev_features feat) if (feat == IOMMU_DEV_FEAT_AUX) return intel_iommu_enable_auxd(dev); + if (feat == IOMMU_DEV_FEAT_SVA) { + struct device_domain_info *info = get_domain_info(dev); + + if (!info) + return -EINVAL; + + if (info->iommu->flags & VTD_FLAG_SVM_CAPABLE) + return 0; + } + return -ENODEV; } @@ -6076,7 +5967,7 @@ intel_iommu_dev_disable_feat(struct device *dev, enum iommu_dev_features feat) static bool intel_iommu_dev_feat_enabled(struct device *dev, enum iommu_dev_features feat) { - struct device_domain_info *info = dev->archdata.iommu; + struct device_domain_info *info = get_domain_info(dev); if (feat == IOMMU_DEV_FEAT_AUX) return scalable_mode_support() && info && info->auxd_enabled; @@ -6144,6 +6035,7 @@ const struct iommu_ops intel_iommu_ops = { .unmap = intel_iommu_unmap, .iova_to_phys = intel_iommu_iova_to_phys, .probe_device = intel_iommu_probe_device, + .probe_finalize = intel_iommu_probe_finalize, .release_device = intel_iommu_release_device, .get_resv_regions = intel_iommu_get_resv_regions, .put_resv_regions = generic_iommu_put_resv_regions, @@ -6156,6 +6048,14 @@ const struct iommu_ops intel_iommu_ops = { .is_attach_deferred = intel_iommu_is_attach_deferred, .def_domain_type = device_def_domain_type, .pgsize_bitmap = INTEL_IOMMU_PGSIZES, +#ifdef CONFIG_INTEL_IOMMU_SVM + .cache_invalidate = intel_iommu_sva_invalidate, + .sva_bind_gpasid = intel_svm_bind_gpasid, + .sva_unbind_gpasid = intel_svm_unbind_gpasid, + .sva_bind = intel_svm_bind, + .sva_unbind = intel_svm_unbind, + .sva_get_pasid = intel_svm_get_pasid, +#endif }; static void quirk_iommu_igfx(struct pci_dev *dev) diff --git a/drivers/iommu/intel-pasid.c b/drivers/iommu/intel-pasid.c index 22b30f10b396..c81f0f17c6ba 100644 --- a/drivers/iommu/intel-pasid.c +++ b/drivers/iommu/intel-pasid.c @@ -27,6 +27,63 @@ static DEFINE_SPINLOCK(pasid_lock); u32 intel_pasid_max_id = PASID_MAX; +int vcmd_alloc_pasid(struct intel_iommu *iommu, unsigned int *pasid) +{ + unsigned long flags; + u8 status_code; + int ret = 0; + u64 res; + + raw_spin_lock_irqsave(&iommu->register_lock, flags); + dmar_writeq(iommu->reg + DMAR_VCMD_REG, VCMD_CMD_ALLOC); + IOMMU_WAIT_OP(iommu, DMAR_VCRSP_REG, dmar_readq, + !(res & VCMD_VRSP_IP), res); + raw_spin_unlock_irqrestore(&iommu->register_lock, flags); + + status_code = VCMD_VRSP_SC(res); + switch (status_code) { + case VCMD_VRSP_SC_SUCCESS: + *pasid = VCMD_VRSP_RESULT_PASID(res); + break; + case VCMD_VRSP_SC_NO_PASID_AVAIL: + pr_info("IOMMU: %s: No PASID available\n", iommu->name); + ret = -ENOSPC; + break; + default: + ret = -ENODEV; + pr_warn("IOMMU: %s: Unexpected error code %d\n", + iommu->name, status_code); + } + + return ret; +} + +void vcmd_free_pasid(struct intel_iommu *iommu, unsigned int pasid) +{ + unsigned long flags; + u8 status_code; + u64 res; + + raw_spin_lock_irqsave(&iommu->register_lock, flags); + dmar_writeq(iommu->reg + DMAR_VCMD_REG, + VCMD_CMD_OPERAND(pasid) | VCMD_CMD_FREE); + IOMMU_WAIT_OP(iommu, DMAR_VCRSP_REG, dmar_readq, + !(res & VCMD_VRSP_IP), res); + raw_spin_unlock_irqrestore(&iommu->register_lock, flags); + + status_code = VCMD_VRSP_SC(res); + switch (status_code) { + case VCMD_VRSP_SC_SUCCESS: + break; + case VCMD_VRSP_SC_INVALID_PASID: + pr_info("IOMMU: %s: Invalid PASID\n", iommu->name); + break; + default: + pr_warn("IOMMU: %s: Unexpected error code %d\n", + iommu->name, status_code); + } +} + /* * Per device pasid table management: */ @@ -94,7 +151,7 @@ int intel_pasid_alloc_table(struct device *dev) int size; might_sleep(); - info = dev->archdata.iommu; + info = get_domain_info(dev); if (WARN_ON(!info || !dev_is_pci(dev) || info->pasid_table)) return -EINVAL; @@ -141,7 +198,7 @@ void intel_pasid_free_table(struct device *dev) struct pasid_entry *table; int i, max_pde; - info = dev->archdata.iommu; + info = get_domain_info(dev); if (!info || !dev_is_pci(dev) || !info->pasid_table) return; @@ -167,7 +224,7 @@ struct pasid_table *intel_pasid_get_table(struct device *dev) { struct device_domain_info *info; - info = dev->archdata.iommu; + info = get_domain_info(dev); if (!info) return NULL; @@ -178,7 +235,7 @@ int intel_pasid_get_dev_max_id(struct device *dev) { struct device_domain_info *info; - info = dev->archdata.iommu; + info = get_domain_info(dev); if (!info || !info->pasid_table) return 0; @@ -199,7 +256,7 @@ struct pasid_entry *intel_pasid_get_entry(struct device *dev, int pasid) return NULL; dir = pasid_table->table; - info = dev->archdata.iommu; + info = get_domain_info(dev); dir_index = pasid >> PASID_PDE_SHIFT; index = pasid & PASID_PTE_MASK; @@ -235,7 +292,20 @@ static inline void pasid_clear_entry(struct pasid_entry *pe) WRITE_ONCE(pe->val[7], 0); } -static void intel_pasid_clear_entry(struct device *dev, int pasid) +static inline void pasid_clear_entry_with_fpd(struct pasid_entry *pe) +{ + WRITE_ONCE(pe->val[0], PASID_PTE_FPD); + WRITE_ONCE(pe->val[1], 0); + WRITE_ONCE(pe->val[2], 0); + WRITE_ONCE(pe->val[3], 0); + WRITE_ONCE(pe->val[4], 0); + WRITE_ONCE(pe->val[5], 0); + WRITE_ONCE(pe->val[6], 0); + WRITE_ONCE(pe->val[7], 0); +} + +static void +intel_pasid_clear_entry(struct device *dev, int pasid, bool fault_ignore) { struct pasid_entry *pe; @@ -243,7 +313,10 @@ static void intel_pasid_clear_entry(struct device *dev, int pasid) if (WARN_ON(!pe)) return; - pasid_clear_entry(pe); + if (fault_ignore && pasid_pte_is_present(pe)) + pasid_clear_entry_with_fpd(pe); + else + pasid_clear_entry(pe); } static inline void pasid_set_bits(u64 *ptr, u64 mask, u64 bits) @@ -359,18 +432,29 @@ pasid_set_flpm(struct pasid_entry *pe, u64 value) pasid_set_bits(&pe->val[2], GENMASK_ULL(3, 2), value << 2); } +/* + * Setup the Extended Access Flag Enable (EAFE) field (Bit 135) + * of a scalable mode PASID entry. + */ +static inline void +pasid_set_eafe(struct pasid_entry *pe) +{ + pasid_set_bits(&pe->val[2], 1 << 7, 1 << 7); +} + static void pasid_cache_invalidation_with_pasid(struct intel_iommu *iommu, u16 did, int pasid) { struct qi_desc desc; - desc.qw0 = QI_PC_DID(did) | QI_PC_PASID_SEL | QI_PC_PASID(pasid); + desc.qw0 = QI_PC_DID(did) | QI_PC_GRAN(QI_PC_PASID_SEL) | + QI_PC_PASID(pasid) | QI_PC_TYPE; desc.qw1 = 0; desc.qw2 = 0; desc.qw3 = 0; - qi_submit_sync(&desc, iommu); + qi_submit_sync(iommu, &desc, 1, 0); } static void @@ -384,7 +468,7 @@ iotlb_invalidation_with_pasid(struct intel_iommu *iommu, u16 did, u32 pasid) desc.qw2 = 0; desc.qw3 = 0; - qi_submit_sync(&desc, iommu); + qi_submit_sync(iommu, &desc, 1, 0); } static void @@ -394,7 +478,7 @@ devtlb_invalidation_with_pasid(struct intel_iommu *iommu, struct device_domain_info *info; u16 sid, qdep, pfsid; - info = dev->archdata.iommu; + info = get_domain_info(dev); if (!info || !info->ats_enabled) return; @@ -405,8 +489,8 @@ devtlb_invalidation_with_pasid(struct intel_iommu *iommu, qi_flush_dev_iotlb(iommu, sid, pfsid, qdep, 0, 64 - VTD_PAGE_SHIFT); } -void intel_pasid_tear_down_entry(struct intel_iommu *iommu, - struct device *dev, int pasid) +void intel_pasid_tear_down_entry(struct intel_iommu *iommu, struct device *dev, + int pasid, bool fault_ignore) { struct pasid_entry *pte; u16 did; @@ -416,7 +500,7 @@ void intel_pasid_tear_down_entry(struct intel_iommu *iommu, return; did = pasid_get_domain_id(pte); - intel_pasid_clear_entry(dev, pasid); + intel_pasid_clear_entry(dev, pasid, fault_ignore); if (!ecap_coherent(iommu->ecap)) clflush_cache_range(pte, sizeof(*pte)); @@ -492,7 +576,7 @@ int intel_pasid_setup_first_level(struct intel_iommu *iommu, pasid_set_page_snoop(pte, !!ecap_smpwc(iommu->ecap)); /* Setup Present and PASID Granular Transfer Type: */ - pasid_set_translation_type(pte, 1); + pasid_set_translation_type(pte, PASID_ENTRY_PGTT_FL_ONLY); pasid_set_present(pte); pasid_flush_caches(iommu, pte, pasid, did); @@ -500,6 +584,25 @@ int intel_pasid_setup_first_level(struct intel_iommu *iommu, } /* + * Skip top levels of page tables for iommu which has less agaw + * than default. Unnecessary for PT mode. + */ +static inline int iommu_skip_agaw(struct dmar_domain *domain, + struct intel_iommu *iommu, + struct dma_pte **pgd) +{ + int agaw; + + for (agaw = domain->agaw; agaw > iommu->agaw; agaw--) { + *pgd = phys_to_virt(dma_pte_addr(*pgd)); + if (!dma_pte_present(*pgd)) + return -EINVAL; + } + + return agaw; +} + +/* * Set up the scalable mode pasid entry for second only translation type. */ int intel_pasid_setup_second_level(struct intel_iommu *iommu, @@ -522,17 +625,11 @@ int intel_pasid_setup_second_level(struct intel_iommu *iommu, return -EINVAL; } - /* - * Skip top levels of page tables for iommu which has less agaw - * than default. Unnecessary for PT mode. - */ pgd = domain->pgd; - for (agaw = domain->agaw; agaw > iommu->agaw; agaw--) { - pgd = phys_to_virt(dma_pte_addr(pgd)); - if (!dma_pte_present(pgd)) { - dev_err(dev, "Invalid domain page table\n"); - return -EINVAL; - } + agaw = iommu_skip_agaw(domain, iommu, &pgd); + if (agaw < 0) { + dev_err(dev, "Invalid domain page table\n"); + return -EINVAL; } pgd_val = virt_to_phys(pgd); @@ -548,7 +645,7 @@ int intel_pasid_setup_second_level(struct intel_iommu *iommu, pasid_set_domain_id(pte, did); pasid_set_slptr(pte, pgd_val); pasid_set_address_width(pte, agaw); - pasid_set_translation_type(pte, 2); + pasid_set_translation_type(pte, PASID_ENTRY_PGTT_SL_ONLY); pasid_set_fault_enable(pte); pasid_set_page_snoop(pte, !!ecap_smpwc(iommu->ecap)); @@ -582,7 +679,7 @@ int intel_pasid_setup_pass_through(struct intel_iommu *iommu, pasid_clear_entry(pte); pasid_set_domain_id(pte, did); pasid_set_address_width(pte, iommu->agaw); - pasid_set_translation_type(pte, 4); + pasid_set_translation_type(pte, PASID_ENTRY_PGTT_PT); pasid_set_fault_enable(pte); pasid_set_page_snoop(pte, !!ecap_smpwc(iommu->ecap)); @@ -596,3 +693,161 @@ int intel_pasid_setup_pass_through(struct intel_iommu *iommu, return 0; } + +static int +intel_pasid_setup_bind_data(struct intel_iommu *iommu, struct pasid_entry *pte, + struct iommu_gpasid_bind_data_vtd *pasid_data) +{ + /* + * Not all guest PASID table entry fields are passed down during bind, + * here we only set up the ones that are dependent on guest settings. + * Execution related bits such as NXE, SMEP are not supported. + * Other fields, such as snoop related, are set based on host needs + * regardless of guest settings. + */ + if (pasid_data->flags & IOMMU_SVA_VTD_GPASID_SRE) { + if (!ecap_srs(iommu->ecap)) { + pr_err_ratelimited("No supervisor request support on %s\n", + iommu->name); + return -EINVAL; + } + pasid_set_sre(pte); + } + + if (pasid_data->flags & IOMMU_SVA_VTD_GPASID_EAFE) { + if (!ecap_eafs(iommu->ecap)) { + pr_err_ratelimited("No extended access flag support on %s\n", + iommu->name); + return -EINVAL; + } + pasid_set_eafe(pte); + } + + /* + * Memory type is only applicable to devices inside processor coherent + * domain. Will add MTS support once coherent devices are available. + */ + if (pasid_data->flags & IOMMU_SVA_VTD_GPASID_MTS_MASK) { + pr_warn_ratelimited("No memory type support %s\n", + iommu->name); + return -EINVAL; + } + + return 0; +} + +/** + * intel_pasid_setup_nested() - Set up PASID entry for nested translation. + * This could be used for guest shared virtual address. In this case, the + * first level page tables are used for GVA-GPA translation in the guest, + * second level page tables are used for GPA-HPA translation. + * + * @iommu: IOMMU which the device belong to + * @dev: Device to be set up for translation + * @gpgd: FLPTPTR: First Level Page translation pointer in GPA + * @pasid: PASID to be programmed in the device PASID table + * @pasid_data: Additional PASID info from the guest bind request + * @domain: Domain info for setting up second level page tables + * @addr_width: Address width of the first level (guest) + */ +int intel_pasid_setup_nested(struct intel_iommu *iommu, struct device *dev, + pgd_t *gpgd, int pasid, + struct iommu_gpasid_bind_data_vtd *pasid_data, + struct dmar_domain *domain, int addr_width) +{ + struct pasid_entry *pte; + struct dma_pte *pgd; + int ret = 0; + u64 pgd_val; + int agaw; + u16 did; + + if (!ecap_nest(iommu->ecap)) { + pr_err_ratelimited("IOMMU: %s: No nested translation support\n", + iommu->name); + return -EINVAL; + } + + if (!(domain->flags & DOMAIN_FLAG_NESTING_MODE)) { + pr_err_ratelimited("Domain is not in nesting mode, %x\n", + domain->flags); + return -EINVAL; + } + + pte = intel_pasid_get_entry(dev, pasid); + if (WARN_ON(!pte)) + return -EINVAL; + + /* + * Caller must ensure PASID entry is not in use, i.e. not bind the + * same PASID to the same device twice. + */ + if (pasid_pte_is_present(pte)) + return -EBUSY; + + pasid_clear_entry(pte); + + /* Sanity checking performed by caller to make sure address + * width matching in two dimensions: + * 1. CPU vs. IOMMU + * 2. Guest vs. Host. + */ + switch (addr_width) { +#ifdef CONFIG_X86 + case ADDR_WIDTH_5LEVEL: + if (!cpu_feature_enabled(X86_FEATURE_LA57) || + !cap_5lp_support(iommu->cap)) { + dev_err_ratelimited(dev, + "5-level paging not supported\n"); + return -EINVAL; + } + + pasid_set_flpm(pte, 1); + break; +#endif + case ADDR_WIDTH_4LEVEL: + pasid_set_flpm(pte, 0); + break; + default: + dev_err_ratelimited(dev, "Invalid guest address width %d\n", + addr_width); + return -EINVAL; + } + + /* First level PGD is in GPA, must be supported by the second level */ + if ((uintptr_t)gpgd > domain->max_addr) { + dev_err_ratelimited(dev, + "Guest PGD %lx not supported, max %llx\n", + (uintptr_t)gpgd, domain->max_addr); + return -EINVAL; + } + pasid_set_flptr(pte, (uintptr_t)gpgd); + + ret = intel_pasid_setup_bind_data(iommu, pte, pasid_data); + if (ret) + return ret; + + /* Setup the second level based on the given domain */ + pgd = domain->pgd; + + agaw = iommu_skip_agaw(domain, iommu, &pgd); + if (agaw < 0) { + dev_err_ratelimited(dev, "Invalid domain page table\n"); + return -EINVAL; + } + pgd_val = virt_to_phys(pgd); + pasid_set_slptr(pte, pgd_val); + pasid_set_fault_enable(pte); + + did = domain->iommu_did[iommu->seq_id]; + pasid_set_domain_id(pte, did); + + pasid_set_address_width(pte, agaw); + pasid_set_page_snoop(pte, !!ecap_smpwc(iommu->ecap)); + + pasid_set_translation_type(pte, PASID_ENTRY_PGTT_NESTED); + pasid_set_present(pte); + pasid_flush_caches(iommu, pte, pasid, did); + + return ret; +} diff --git a/drivers/iommu/intel-pasid.h b/drivers/iommu/intel-pasid.h index 92de6df24ccb..c5318d40e0fa 100644 --- a/drivers/iommu/intel-pasid.h +++ b/drivers/iommu/intel-pasid.h @@ -15,6 +15,7 @@ #define PASID_MAX 0x100000 #define PASID_PTE_MASK 0x3F #define PASID_PTE_PRESENT 1 +#define PASID_PTE_FPD 2 #define PDE_PFN_MASK PAGE_MASK #define PASID_PDE_SHIFT 6 #define MAX_NR_PASID_BITS 20 @@ -23,6 +24,16 @@ #define is_pasid_enabled(entry) (((entry)->lo >> 3) & 0x1) #define get_pasid_dir_size(entry) (1 << ((((entry)->lo >> 9) & 0x7) + 7)) +/* Virtual command interface for enlightened pasid management. */ +#define VCMD_CMD_ALLOC 0x1 +#define VCMD_CMD_FREE 0x2 +#define VCMD_VRSP_IP 0x1 +#define VCMD_VRSP_SC(e) (((e) >> 1) & 0x3) +#define VCMD_VRSP_SC_SUCCESS 0 +#define VCMD_VRSP_SC_NO_PASID_AVAIL 1 +#define VCMD_VRSP_SC_INVALID_PASID 1 +#define VCMD_VRSP_RESULT_PASID(e) (((e) >> 8) & 0xfffff) +#define VCMD_CMD_OPERAND(e) ((e) << 8) /* * Domain ID reserved for pasid entries programmed for first-level * only and pass-through transfer modes. @@ -36,6 +47,7 @@ * to vmalloc or even module mappings. */ #define PASID_FLAG_SUPERVISOR_MODE BIT(0) +#define PASID_FLAG_NESTED BIT(1) /* * The PASID_FLAG_FL5LP flag Indicates using 5-level paging for first- @@ -51,6 +63,11 @@ struct pasid_entry { u64 val[8]; }; +#define PASID_ENTRY_PGTT_FL_ONLY (1) +#define PASID_ENTRY_PGTT_SL_ONLY (2) +#define PASID_ENTRY_PGTT_NESTED (3) +#define PASID_ENTRY_PGTT_PT (4) + /* The representative of a PASID table */ struct pasid_table { void *table; /* pasid table pointer */ @@ -99,7 +116,13 @@ int intel_pasid_setup_second_level(struct intel_iommu *iommu, int intel_pasid_setup_pass_through(struct intel_iommu *iommu, struct dmar_domain *domain, struct device *dev, int pasid); +int intel_pasid_setup_nested(struct intel_iommu *iommu, + struct device *dev, pgd_t *pgd, int pasid, + struct iommu_gpasid_bind_data_vtd *pasid_data, + struct dmar_domain *domain, int addr_width); void intel_pasid_tear_down_entry(struct intel_iommu *iommu, - struct device *dev, int pasid); - + struct device *dev, int pasid, + bool fault_ignore); +int vcmd_alloc_pasid(struct intel_iommu *iommu, unsigned int *pasid); +void vcmd_free_pasid(struct intel_iommu *iommu, unsigned int pasid); #endif /* __INTEL_PASID_H */ diff --git a/drivers/iommu/intel-svm.c b/drivers/iommu/intel-svm.c index 2998418f0a38..a035ef911fba 100644 --- a/drivers/iommu/intel-svm.c +++ b/drivers/iommu/intel-svm.c @@ -23,6 +23,7 @@ #include "intel-pasid.h" static irqreturn_t prq_event_thread(int irq, void *d); +static void intel_svm_drain_prq(struct device *dev, int pasid); #define PRQ_ORDER 0 @@ -66,6 +67,8 @@ int intel_svm_enable_prq(struct intel_iommu *iommu) dmar_writeq(iommu->reg + DMAR_PQT_REG, 0ULL); dmar_writeq(iommu->reg + DMAR_PQA_REG, virt_to_phys(iommu->prq) | PRQ_ORDER); + init_completion(&iommu->prq_complete); + return 0; } @@ -138,7 +141,7 @@ static void intel_flush_svm_range_dev (struct intel_svm *svm, struct intel_svm_d } desc.qw2 = 0; desc.qw3 = 0; - qi_submit_sync(&desc, svm->iommu); + qi_submit_sync(svm->iommu, &desc, 1, 0); if (sdev->dev_iotlb) { desc.qw0 = QI_DEV_EIOTLB_PASID(svm->pasid) | @@ -162,7 +165,7 @@ static void intel_flush_svm_range_dev (struct intel_svm *svm, struct intel_svm_d } desc.qw2 = 0; desc.qw3 = 0; - qi_submit_sync(&desc, svm->iommu); + qi_submit_sync(svm->iommu, &desc, 1, 0); } } @@ -206,10 +209,9 @@ static void intel_mm_release(struct mmu_notifier *mn, struct mm_struct *mm) * *has* to handle gracefully without affecting other processes. */ rcu_read_lock(); - list_for_each_entry_rcu(sdev, &svm->devs, list) { - intel_pasid_tear_down_entry(svm->iommu, sdev->dev, svm->pasid); - intel_flush_svm_range_dev(svm, sdev, 0, -1, 0); - } + list_for_each_entry_rcu(sdev, &svm->devs, list) + intel_pasid_tear_down_entry(svm->iommu, sdev->dev, + svm->pasid, true); rcu_read_unlock(); } @@ -226,13 +228,212 @@ static LIST_HEAD(global_svm_list); list_for_each_entry((sdev), &(svm)->devs, list) \ if ((d) != (sdev)->dev) {} else -int intel_svm_bind_mm(struct device *dev, int *pasid, int flags, struct svm_dev_ops *ops) +int intel_svm_bind_gpasid(struct iommu_domain *domain, struct device *dev, + struct iommu_gpasid_bind_data *data) +{ + struct intel_iommu *iommu = intel_svm_device_to_iommu(dev); + struct dmar_domain *dmar_domain; + struct intel_svm_dev *sdev; + struct intel_svm *svm; + int ret = 0; + + if (WARN_ON(!iommu) || !data) + return -EINVAL; + + if (data->version != IOMMU_GPASID_BIND_VERSION_1 || + data->format != IOMMU_PASID_FORMAT_INTEL_VTD) + return -EINVAL; + + if (!dev_is_pci(dev)) + return -ENOTSUPP; + + /* VT-d supports devices with full 20 bit PASIDs only */ + if (pci_max_pasids(to_pci_dev(dev)) != PASID_MAX) + return -EINVAL; + + /* + * We only check host PASID range, we have no knowledge to check + * guest PASID range. + */ + if (data->hpasid <= 0 || data->hpasid >= PASID_MAX) + return -EINVAL; + + dmar_domain = to_dmar_domain(domain); + + mutex_lock(&pasid_mutex); + svm = ioasid_find(NULL, data->hpasid, NULL); + if (IS_ERR(svm)) { + ret = PTR_ERR(svm); + goto out; + } + + if (svm) { + /* + * If we found svm for the PASID, there must be at + * least one device bond, otherwise svm should be freed. + */ + if (WARN_ON(list_empty(&svm->devs))) { + ret = -EINVAL; + goto out; + } + + for_each_svm_dev(sdev, svm, dev) { + /* + * For devices with aux domains, we should allow + * multiple bind calls with the same PASID and pdev. + */ + if (iommu_dev_feature_enabled(dev, + IOMMU_DEV_FEAT_AUX)) { + sdev->users++; + } else { + dev_warn_ratelimited(dev, + "Already bound with PASID %u\n", + svm->pasid); + ret = -EBUSY; + } + goto out; + } + } else { + /* We come here when PASID has never been bond to a device. */ + svm = kzalloc(sizeof(*svm), GFP_KERNEL); + if (!svm) { + ret = -ENOMEM; + goto out; + } + /* REVISIT: upper layer/VFIO can track host process that bind + * the PASID. ioasid_set = mm might be sufficient for vfio to + * check pasid VMM ownership. We can drop the following line + * once VFIO and IOASID set check is in place. + */ + svm->mm = get_task_mm(current); + svm->pasid = data->hpasid; + if (data->flags & IOMMU_SVA_GPASID_VAL) { + svm->gpasid = data->gpasid; + svm->flags |= SVM_FLAG_GUEST_PASID; + } + ioasid_set_data(data->hpasid, svm); + INIT_LIST_HEAD_RCU(&svm->devs); + mmput(svm->mm); + } + sdev = kzalloc(sizeof(*sdev), GFP_KERNEL); + if (!sdev) { + ret = -ENOMEM; + goto out; + } + sdev->dev = dev; + + /* Only count users if device has aux domains */ + if (iommu_dev_feature_enabled(dev, IOMMU_DEV_FEAT_AUX)) + sdev->users = 1; + + /* Set up device context entry for PASID if not enabled already */ + ret = intel_iommu_enable_pasid(iommu, sdev->dev); + if (ret) { + dev_err_ratelimited(dev, "Failed to enable PASID capability\n"); + kfree(sdev); + goto out; + } + + /* + * PASID table is per device for better security. Therefore, for + * each bind of a new device even with an existing PASID, we need to + * call the nested mode setup function here. + */ + spin_lock(&iommu->lock); + ret = intel_pasid_setup_nested(iommu, dev, + (pgd_t *)(uintptr_t)data->gpgd, + data->hpasid, &data->vtd, dmar_domain, + data->addr_width); + spin_unlock(&iommu->lock); + if (ret) { + dev_err_ratelimited(dev, "Failed to set up PASID %llu in nested mode, Err %d\n", + data->hpasid, ret); + /* + * PASID entry should be in cleared state if nested mode + * set up failed. So we only need to clear IOASID tracking + * data such that free call will succeed. + */ + kfree(sdev); + goto out; + } + + svm->flags |= SVM_FLAG_GUEST_MODE; + + init_rcu_head(&sdev->rcu); + list_add_rcu(&sdev->list, &svm->devs); + out: + if (!IS_ERR_OR_NULL(svm) && list_empty(&svm->devs)) { + ioasid_set_data(data->hpasid, NULL); + kfree(svm); + } + + mutex_unlock(&pasid_mutex); + return ret; +} + +int intel_svm_unbind_gpasid(struct device *dev, int pasid) +{ + struct intel_iommu *iommu = intel_svm_device_to_iommu(dev); + struct intel_svm_dev *sdev; + struct intel_svm *svm; + int ret = -EINVAL; + + if (WARN_ON(!iommu)) + return -EINVAL; + + mutex_lock(&pasid_mutex); + svm = ioasid_find(NULL, pasid, NULL); + if (!svm) { + ret = -EINVAL; + goto out; + } + + if (IS_ERR(svm)) { + ret = PTR_ERR(svm); + goto out; + } + + for_each_svm_dev(sdev, svm, dev) { + ret = 0; + if (iommu_dev_feature_enabled(dev, IOMMU_DEV_FEAT_AUX)) + sdev->users--; + if (!sdev->users) { + list_del_rcu(&sdev->list); + intel_pasid_tear_down_entry(iommu, dev, + svm->pasid, false); + intel_svm_drain_prq(dev, svm->pasid); + kfree_rcu(sdev, rcu); + + if (list_empty(&svm->devs)) { + /* + * We do not free the IOASID here in that + * IOMMU driver did not allocate it. + * Unlike native SVM, IOASID for guest use was + * allocated prior to the bind call. + * In any case, if the free call comes before + * the unbind, IOMMU driver will get notified + * and perform cleanup. + */ + ioasid_set_data(pasid, NULL); + kfree(svm); + } + } + break; + } +out: + mutex_unlock(&pasid_mutex); + return ret; +} + +/* Caller must hold pasid_mutex, mm reference */ +static int +intel_svm_bind_mm(struct device *dev, int flags, struct svm_dev_ops *ops, + struct mm_struct *mm, struct intel_svm_dev **sd) { struct intel_iommu *iommu = intel_svm_device_to_iommu(dev); struct device_domain_info *info; struct intel_svm_dev *sdev; struct intel_svm *svm = NULL; - struct mm_struct *mm = NULL; int pasid_max; int ret; @@ -249,16 +450,15 @@ int intel_svm_bind_mm(struct device *dev, int *pasid, int flags, struct svm_dev_ } else pasid_max = 1 << 20; + /* Bind supervisor PASID shuld have mm = NULL */ if (flags & SVM_FLAG_SUPERVISOR_MODE) { - if (!ecap_srs(iommu->ecap)) + if (!ecap_srs(iommu->ecap) || mm) { + pr_err("Supervisor PASID with user provided mm.\n"); return -EINVAL; - } else if (pasid) { - mm = get_task_mm(current); - BUG_ON(!mm); + } } - mutex_lock(&pasid_mutex); - if (pasid && !(flags & SVM_FLAG_PRIVATE_PASID)) { + if (!(flags & SVM_FLAG_PRIVATE_PASID)) { struct intel_svm *t; list_for_each_entry(t, &global_svm_list, list) { @@ -296,19 +496,12 @@ int intel_svm_bind_mm(struct device *dev, int *pasid, int flags, struct svm_dev_ sdev->dev = dev; ret = intel_iommu_enable_pasid(iommu, dev); - if (ret || !pasid) { - /* If they don't actually want to assign a PASID, this is - * just an enabling check/preparation. */ - kfree(sdev); - goto out; - } - - info = dev->archdata.iommu; - if (!info || !info->pasid_supported) { + if (ret) { kfree(sdev); goto out; } + info = get_domain_info(dev); sdev->did = FLPT_DEFAULT_DID; sdev->sid = PCI_DEVID(info->bus, info->devfn); if (info->ats_enabled) { @@ -397,26 +590,24 @@ int intel_svm_bind_mm(struct device *dev, int *pasid, int flags, struct svm_dev_ } } list_add_rcu(&sdev->list, &svm->devs); - - success: - *pasid = svm->pasid; +success: + sdev->pasid = svm->pasid; + sdev->sva.dev = dev; + if (sd) + *sd = sdev; ret = 0; out: - mutex_unlock(&pasid_mutex); - if (mm) - mmput(mm); return ret; } -EXPORT_SYMBOL_GPL(intel_svm_bind_mm); -int intel_svm_unbind_mm(struct device *dev, int pasid) +/* Caller must hold pasid_mutex */ +static int intel_svm_unbind_mm(struct device *dev, int pasid) { struct intel_svm_dev *sdev; struct intel_iommu *iommu; struct intel_svm *svm; int ret = -EINVAL; - mutex_lock(&pasid_mutex); iommu = intel_svm_device_to_iommu(dev); if (!iommu) goto out; @@ -442,8 +633,9 @@ int intel_svm_unbind_mm(struct device *dev, int pasid) * to use. We have a *shared* PASID table, because it's * large and has to be physically contiguous. So it's * hard to be as defensive as we might like. */ - intel_pasid_tear_down_entry(iommu, dev, svm->pasid); - intel_flush_svm_range_dev(svm, sdev, 0, -1, 0); + intel_pasid_tear_down_entry(iommu, dev, + svm->pasid, false); + intel_svm_drain_prq(dev, svm->pasid); kfree_rcu(sdev, rcu); if (list_empty(&svm->devs)) { @@ -462,45 +654,9 @@ int intel_svm_unbind_mm(struct device *dev, int pasid) break; } out: - mutex_unlock(&pasid_mutex); return ret; } -EXPORT_SYMBOL_GPL(intel_svm_unbind_mm); - -int intel_svm_is_pasid_valid(struct device *dev, int pasid) -{ - struct intel_iommu *iommu; - struct intel_svm *svm; - int ret = -EINVAL; - - mutex_lock(&pasid_mutex); - iommu = intel_svm_device_to_iommu(dev); - if (!iommu) - goto out; - - svm = ioasid_find(NULL, pasid, NULL); - if (!svm) - goto out; - - if (IS_ERR(svm)) { - ret = PTR_ERR(svm); - goto out; - } - /* init_mm is used in this case */ - if (!svm->mm) - ret = 1; - else if (atomic_read(&svm->mm->mm_users) > 0) - ret = 1; - else - ret = 0; - - out: - mutex_unlock(&pasid_mutex); - - return ret; -} -EXPORT_SYMBOL_GPL(intel_svm_is_pasid_valid); /* Page request queue descriptor */ struct page_req_dsc { @@ -557,6 +713,93 @@ static bool is_canonical_address(u64 addr) return (((saddr << shift) >> shift) == saddr); } +/** + * intel_svm_drain_prq - Drain page requests and responses for a pasid + * @dev: target device + * @pasid: pasid for draining + * + * Drain all pending page requests and responses related to @pasid in both + * software and hardware. This is supposed to be called after the device + * driver has stopped DMA, the pasid entry has been cleared, and both IOTLB + * and DevTLB have been invalidated. + * + * It waits until all pending page requests for @pasid in the page fault + * queue are completed by the prq handling thread. Then follow the steps + * described in VT-d spec CH7.10 to drain all page requests and page + * responses pending in the hardware. + */ +static void intel_svm_drain_prq(struct device *dev, int pasid) +{ + struct device_domain_info *info; + struct dmar_domain *domain; + struct intel_iommu *iommu; + struct qi_desc desc[3]; + struct pci_dev *pdev; + int head, tail; + u16 sid, did; + int qdep; + + info = get_domain_info(dev); + if (WARN_ON(!info || !dev_is_pci(dev))) + return; + + if (!info->pri_enabled) + return; + + iommu = info->iommu; + domain = info->domain; + pdev = to_pci_dev(dev); + sid = PCI_DEVID(info->bus, info->devfn); + did = domain->iommu_did[iommu->seq_id]; + qdep = pci_ats_queue_depth(pdev); + + /* + * Check and wait until all pending page requests in the queue are + * handled by the prq handling thread. + */ +prq_retry: + reinit_completion(&iommu->prq_complete); + tail = dmar_readq(iommu->reg + DMAR_PQT_REG) & PRQ_RING_MASK; + head = dmar_readq(iommu->reg + DMAR_PQH_REG) & PRQ_RING_MASK; + while (head != tail) { + struct page_req_dsc *req; + + req = &iommu->prq[head / sizeof(*req)]; + if (!req->pasid_present || req->pasid != pasid) { + head = (head + sizeof(*req)) & PRQ_RING_MASK; + continue; + } + + wait_for_completion(&iommu->prq_complete); + goto prq_retry; + } + + /* + * Perform steps described in VT-d spec CH7.10 to drain page + * requests and responses in hardware. + */ + memset(desc, 0, sizeof(desc)); + desc[0].qw0 = QI_IWD_STATUS_DATA(QI_DONE) | + QI_IWD_FENCE | + QI_IWD_TYPE; + desc[1].qw0 = QI_EIOTLB_PASID(pasid) | + QI_EIOTLB_DID(did) | + QI_EIOTLB_GRAN(QI_GRAN_NONG_PASID) | + QI_EIOTLB_TYPE; + desc[2].qw0 = QI_DEV_EIOTLB_PASID(pasid) | + QI_DEV_EIOTLB_SID(sid) | + QI_DEV_EIOTLB_QDEP(qdep) | + QI_DEIOTLB_TYPE | + QI_DEV_IOTLB_PFSID(info->pfsid); +qi_retry: + reinit_completion(&iommu->prq_complete); + qi_submit_sync(iommu, desc, 3, QI_OPT_WAIT_DRAIN); + if (readl(iommu->reg + DMAR_PRS_REG) & DMA_PRS_PRO) { + wait_for_completion(&iommu->prq_complete); + goto qi_retry; + } +} + static irqreturn_t prq_event_thread(int irq, void *d) { struct intel_iommu *iommu = d; @@ -685,12 +928,75 @@ static irqreturn_t prq_event_thread(int irq, void *d) sizeof(req->priv_data)); resp.qw2 = 0; resp.qw3 = 0; - qi_submit_sync(&resp, iommu); + qi_submit_sync(iommu, &resp, 1, 0); } head = (head + sizeof(*req)) & PRQ_RING_MASK; } dmar_writeq(iommu->reg + DMAR_PQH_REG, tail); + /* + * Clear the page request overflow bit and wake up all threads that + * are waiting for the completion of this handling. + */ + if (readl(iommu->reg + DMAR_PRS_REG) & DMA_PRS_PRO) + writel(DMA_PRS_PRO, iommu->reg + DMAR_PRS_REG); + + if (!completion_done(&iommu->prq_complete)) + complete(&iommu->prq_complete); + return IRQ_RETVAL(handled); } + +#define to_intel_svm_dev(handle) container_of(handle, struct intel_svm_dev, sva) +struct iommu_sva * +intel_svm_bind(struct device *dev, struct mm_struct *mm, void *drvdata) +{ + struct iommu_sva *sva = ERR_PTR(-EINVAL); + struct intel_svm_dev *sdev = NULL; + int flags = 0; + int ret; + + /* + * TODO: Consolidate with generic iommu-sva bind after it is merged. + * It will require shared SVM data structures, i.e. combine io_mm + * and intel_svm etc. + */ + if (drvdata) + flags = *(int *)drvdata; + mutex_lock(&pasid_mutex); + ret = intel_svm_bind_mm(dev, flags, NULL, mm, &sdev); + if (ret) + sva = ERR_PTR(ret); + else if (sdev) + sva = &sdev->sva; + else + WARN(!sdev, "SVM bind succeeded with no sdev!\n"); + + mutex_unlock(&pasid_mutex); + + return sva; +} + +void intel_svm_unbind(struct iommu_sva *sva) +{ + struct intel_svm_dev *sdev; + + mutex_lock(&pasid_mutex); + sdev = to_intel_svm_dev(sva); + intel_svm_unbind_mm(sdev->dev, sdev->pasid); + mutex_unlock(&pasid_mutex); +} + +int intel_svm_get_pasid(struct iommu_sva *sva) +{ + struct intel_svm_dev *sdev; + int pasid; + + mutex_lock(&pasid_mutex); + sdev = to_intel_svm_dev(sva); + pasid = sdev->pasid; + mutex_unlock(&pasid_mutex); + + return pasid; +} diff --git a/drivers/iommu/intel_irq_remapping.c b/drivers/iommu/intel_irq_remapping.c index 81e43c1df7ec..a042f123b091 100644 --- a/drivers/iommu/intel_irq_remapping.c +++ b/drivers/iommu/intel_irq_remapping.c @@ -151,7 +151,7 @@ static int qi_flush_iec(struct intel_iommu *iommu, int index, int mask) desc.qw2 = 0; desc.qw3 = 0; - return qi_submit_sync(&desc, iommu); + return qi_submit_sync(iommu, &desc, 1, 0); } static int modify_irte(struct irq_2_iommu *irq_iommu, diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c index 629d209b8e88..b5ea203f6c68 100644 --- a/drivers/iommu/iommu.c +++ b/drivers/iommu/iommu.c @@ -80,7 +80,8 @@ static bool iommu_cmd_line_dma_api(void) return !!(iommu_cmd_line & IOMMU_CMD_LINE_DMA_API); } -static int iommu_alloc_default_domain(struct device *dev); +static int iommu_alloc_default_domain(struct iommu_group *group, + struct device *dev); static struct iommu_domain *__iommu_domain_alloc(struct bus_type *bus, unsigned type); static int __iommu_attach_device(struct iommu_domain *domain, @@ -251,17 +252,17 @@ int iommu_probe_device(struct device *dev) if (ret) goto err_out; + group = iommu_group_get(dev); + if (!group) + goto err_release; + /* * Try to allocate a default domain - needs support from the * IOMMU driver. There are still some drivers which don't * support default domains, so the return value is not yet * checked. */ - iommu_alloc_default_domain(dev); - - group = iommu_group_get(dev); - if (!group) - goto err_release; + iommu_alloc_default_domain(group, dev); if (group->default_domain) ret = __iommu_attach_device(group->default_domain, dev); @@ -586,7 +587,7 @@ struct iommu_group *iommu_group_alloc(void) NULL, "%d", group->id); if (ret) { ida_simple_remove(&iommu_group_ida, group->id); - kfree(group); + kobject_put(&group->kobj); return ERR_PTR(ret); } @@ -1487,15 +1488,11 @@ static int iommu_group_alloc_default_domain(struct bus_type *bus, return 0; } -static int iommu_alloc_default_domain(struct device *dev) +static int iommu_alloc_default_domain(struct iommu_group *group, + struct device *dev) { - struct iommu_group *group; unsigned int type; - group = iommu_group_get(dev); - if (!group) - return -ENODEV; - if (group->default_domain) return 0; @@ -1683,17 +1680,8 @@ static void probe_alloc_default_domain(struct bus_type *bus, static int iommu_group_do_dma_attach(struct device *dev, void *data) { struct iommu_domain *domain = data; - const struct iommu_ops *ops; - int ret; - ret = __iommu_attach_device(domain, dev); - - ops = domain->ops; - - if (ret == 0 && ops->probe_finalize) - ops->probe_finalize(dev); - - return ret; + return __iommu_attach_device(domain, dev); } static int __iommu_group_dma_attach(struct iommu_group *group) @@ -1702,6 +1690,22 @@ static int __iommu_group_dma_attach(struct iommu_group *group) iommu_group_do_dma_attach); } +static int iommu_group_do_probe_finalize(struct device *dev, void *data) +{ + struct iommu_domain *domain = data; + + if (domain->ops->probe_finalize) + domain->ops->probe_finalize(dev); + + return 0; +} + +static void __iommu_group_dma_finalize(struct iommu_group *group) +{ + __iommu_group_for_each_dev(group, group->default_domain, + iommu_group_do_probe_finalize); +} + static int iommu_do_create_direct_mappings(struct device *dev, void *data) { struct iommu_group *group = data; @@ -1754,6 +1758,8 @@ int bus_iommu_probe(struct bus_type *bus) if (ret) break; + + __iommu_group_dma_finalize(group); } return ret; @@ -2541,71 +2547,6 @@ struct iommu_resv_region *iommu_alloc_resv_region(phys_addr_t start, } EXPORT_SYMBOL_GPL(iommu_alloc_resv_region); -static int -request_default_domain_for_dev(struct device *dev, unsigned long type) -{ - struct iommu_domain *domain; - struct iommu_group *group; - int ret; - - /* Device must already be in a group before calling this function */ - group = iommu_group_get(dev); - if (!group) - return -EINVAL; - - mutex_lock(&group->mutex); - - ret = 0; - if (group->default_domain && group->default_domain->type == type) - goto out; - - /* Don't change mappings of existing devices */ - ret = -EBUSY; - if (iommu_group_device_count(group) != 1) - goto out; - - ret = -ENOMEM; - domain = __iommu_domain_alloc(dev->bus, type); - if (!domain) - goto out; - - /* Attach the device to the domain */ - ret = __iommu_attach_group(domain, group); - if (ret) { - iommu_domain_free(domain); - goto out; - } - - /* Make the domain the default for this group */ - if (group->default_domain) - iommu_domain_free(group->default_domain); - group->default_domain = domain; - - iommu_create_device_direct_mappings(group, dev); - - dev_info(dev, "Using iommu %s mapping\n", - type == IOMMU_DOMAIN_DMA ? "dma" : "direct"); - - ret = 0; -out: - mutex_unlock(&group->mutex); - iommu_group_put(group); - - return ret; -} - -/* Request that a device is direct mapped by the IOMMU */ -int iommu_request_dm_for_dev(struct device *dev) -{ - return request_default_domain_for_dev(dev, IOMMU_DOMAIN_IDENTITY); -} - -/* Request that a device can't be direct mapped by the IOMMU */ -int iommu_request_dma_domain_for_dev(struct device *dev) -{ - return request_default_domain_for_dev(dev, IOMMU_DOMAIN_DMA); -} - void iommu_set_default_passthrough(bool cmd_line) { if (cmd_line) @@ -2883,17 +2824,6 @@ void iommu_sva_unbind_device(struct iommu_sva *handle) } EXPORT_SYMBOL_GPL(iommu_sva_unbind_device); -int iommu_sva_set_ops(struct iommu_sva *handle, - const struct iommu_sva_ops *sva_ops) -{ - if (handle->ops && handle->ops != sva_ops) - return -EEXIST; - - handle->ops = sva_ops; - return 0; -} -EXPORT_SYMBOL_GPL(iommu_sva_set_ops); - int iommu_sva_get_pasid(struct iommu_sva *handle) { const struct iommu_ops *ops = handle->dev->bus->iommu_ops; diff --git a/drivers/iommu/msm_iommu.c b/drivers/iommu/msm_iommu.c index 10cd4db0710a..3d8a63555c25 100644 --- a/drivers/iommu/msm_iommu.c +++ b/drivers/iommu/msm_iommu.c @@ -34,7 +34,7 @@ __asm__ __volatile__ ( \ /* bitmap of the page sizes currently supported */ #define MSM_IOMMU_PGSIZES (SZ_4K | SZ_64K | SZ_1M | SZ_16M) -DEFINE_SPINLOCK(msm_iommu_lock); +static DEFINE_SPINLOCK(msm_iommu_lock); static LIST_HEAD(qcom_iommu_devices); static struct iommu_ops msm_iommu_ops; diff --git a/drivers/iommu/mtk_iommu_v1.c b/drivers/iommu/mtk_iommu_v1.c index 7bdd74c7cb9f..c9d79cff4d17 100644 --- a/drivers/iommu/mtk_iommu_v1.c +++ b/drivers/iommu/mtk_iommu_v1.c @@ -265,10 +265,13 @@ static int mtk_iommu_attach_device(struct iommu_domain *domain, { struct mtk_iommu_data *data = dev_iommu_priv_get(dev); struct mtk_iommu_domain *dom = to_mtk_domain(domain); + struct dma_iommu_mapping *mtk_mapping; int ret; - if (!data) - return -ENODEV; + /* Only allow the domain created internally. */ + mtk_mapping = data->dev->archdata.iommu; + if (mtk_mapping->domain != domain) + return 0; if (!data->m4u_dom) { data->m4u_dom = dom; @@ -288,9 +291,6 @@ static void mtk_iommu_detach_device(struct iommu_domain *domain, { struct mtk_iommu_data *data = dev_iommu_priv_get(dev); - if (!data) - return; - mtk_iommu_config(data, dev, false); } @@ -416,6 +416,11 @@ static int mtk_iommu_create_mapping(struct device *dev, return 0; } +static int mtk_iommu_def_domain_type(struct device *dev) +{ + return IOMMU_DOMAIN_UNMANAGED; +} + static struct iommu_device *mtk_iommu_probe_device(struct device *dev) { struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(dev); @@ -464,12 +469,10 @@ static void mtk_iommu_probe_finalize(struct device *dev) static void mtk_iommu_release_device(struct device *dev) { struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(dev); - struct mtk_iommu_data *data; if (!fwspec || fwspec->ops != &mtk_iommu_ops) return; - data = dev_iommu_priv_get(dev); iommu_fwspec_free(dev); } @@ -525,6 +528,7 @@ static const struct iommu_ops mtk_iommu_ops = { .probe_device = mtk_iommu_probe_device, .probe_finalize = mtk_iommu_probe_finalize, .release_device = mtk_iommu_release_device, + .def_domain_type = mtk_iommu_def_domain_type, .device_group = generic_device_group, .pgsize_bitmap = ~0UL << MT2701_IOMMU_PAGE_SHIFT, }; diff --git a/drivers/iommu/omap-iommu.c b/drivers/iommu/omap-iommu.c index 6699fe6d9e06..c8282cc212cb 100644 --- a/drivers/iommu/omap-iommu.c +++ b/drivers/iommu/omap-iommu.c @@ -1236,6 +1236,7 @@ static int omap_iommu_probe(struct platform_device *pdev) goto out_group; iommu_device_set_ops(&obj->iommu, &omap_iommu_ops); + iommu_device_set_fwnode(&obj->iommu, &of->fwnode); err = iommu_device_register(&obj->iommu); if (err) @@ -1726,6 +1727,9 @@ static struct iommu_group *omap_iommu_device_group(struct device *dev) struct omap_iommu_arch_data *arch_data = dev->archdata.iommu; struct iommu_group *group = ERR_PTR(-EINVAL); + if (!arch_data) + return ERR_PTR(-ENODEV); + if (arch_data->iommu_dev) group = iommu_group_ref_get(arch_data->iommu_dev->group); diff --git a/drivers/iommu/sun50i-iommu.c b/drivers/iommu/sun50i-iommu.c new file mode 100644 index 000000000000..fce605e96aa2 --- /dev/null +++ b/drivers/iommu/sun50i-iommu.c @@ -0,0 +1,1023 @@ +// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +// Copyright (C) 2016-2018, Allwinner Technology CO., LTD. +// Copyright (C) 2019-2020, Cerno + +#include <linux/bitfield.h> +#include <linux/bug.h> +#include <linux/clk.h> +#include <linux/device.h> +#include <linux/dma-direction.h> +#include <linux/dma-iommu.h> +#include <linux/dma-mapping.h> +#include <linux/err.h> +#include <linux/errno.h> +#include <linux/interrupt.h> +#include <linux/iommu.h> +#include <linux/iopoll.h> +#include <linux/ioport.h> +#include <linux/log2.h> +#include <linux/module.h> +#include <linux/of_platform.h> +#include <linux/platform_device.h> +#include <linux/pm.h> +#include <linux/pm_runtime.h> +#include <linux/reset.h> +#include <linux/sizes.h> +#include <linux/slab.h> +#include <linux/spinlock.h> +#include <linux/types.h> + +#define IOMMU_RESET_REG 0x010 +#define IOMMU_ENABLE_REG 0x020 +#define IOMMU_ENABLE_ENABLE BIT(0) + +#define IOMMU_BYPASS_REG 0x030 +#define IOMMU_AUTO_GATING_REG 0x040 +#define IOMMU_AUTO_GATING_ENABLE BIT(0) + +#define IOMMU_WBUF_CTRL_REG 0x044 +#define IOMMU_OOO_CTRL_REG 0x048 +#define IOMMU_4KB_BDY_PRT_CTRL_REG 0x04c +#define IOMMU_TTB_REG 0x050 +#define IOMMU_TLB_ENABLE_REG 0x060 +#define IOMMU_TLB_PREFETCH_REG 0x070 +#define IOMMU_TLB_PREFETCH_MASTER_ENABLE(m) BIT(m) + +#define IOMMU_TLB_FLUSH_REG 0x080 +#define IOMMU_TLB_FLUSH_PTW_CACHE BIT(17) +#define IOMMU_TLB_FLUSH_MACRO_TLB BIT(16) +#define IOMMU_TLB_FLUSH_MICRO_TLB(i) (BIT(i) & GENMASK(5, 0)) + +#define IOMMU_TLB_IVLD_ADDR_REG 0x090 +#define IOMMU_TLB_IVLD_ADDR_MASK_REG 0x094 +#define IOMMU_TLB_IVLD_ENABLE_REG 0x098 +#define IOMMU_TLB_IVLD_ENABLE_ENABLE BIT(0) + +#define IOMMU_PC_IVLD_ADDR_REG 0x0a0 +#define IOMMU_PC_IVLD_ENABLE_REG 0x0a8 +#define IOMMU_PC_IVLD_ENABLE_ENABLE BIT(0) + +#define IOMMU_DM_AUT_CTRL_REG(d) (0x0b0 + ((d) / 2) * 4) +#define IOMMU_DM_AUT_CTRL_RD_UNAVAIL(d, m) (1 << (((d & 1) * 16) + ((m) * 2))) +#define IOMMU_DM_AUT_CTRL_WR_UNAVAIL(d, m) (1 << (((d & 1) * 16) + ((m) * 2) + 1)) + +#define IOMMU_DM_AUT_OVWT_REG 0x0d0 +#define IOMMU_INT_ENABLE_REG 0x100 +#define IOMMU_INT_CLR_REG 0x104 +#define IOMMU_INT_STA_REG 0x108 +#define IOMMU_INT_ERR_ADDR_REG(i) (0x110 + (i) * 4) +#define IOMMU_INT_ERR_ADDR_L1_REG 0x130 +#define IOMMU_INT_ERR_ADDR_L2_REG 0x134 +#define IOMMU_INT_ERR_DATA_REG(i) (0x150 + (i) * 4) +#define IOMMU_L1PG_INT_REG 0x0180 +#define IOMMU_L2PG_INT_REG 0x0184 + +#define IOMMU_INT_INVALID_L2PG BIT(17) +#define IOMMU_INT_INVALID_L1PG BIT(16) +#define IOMMU_INT_MASTER_PERMISSION(m) BIT(m) +#define IOMMU_INT_MASTER_MASK (IOMMU_INT_MASTER_PERMISSION(0) | \ + IOMMU_INT_MASTER_PERMISSION(1) | \ + IOMMU_INT_MASTER_PERMISSION(2) | \ + IOMMU_INT_MASTER_PERMISSION(3) | \ + IOMMU_INT_MASTER_PERMISSION(4) | \ + IOMMU_INT_MASTER_PERMISSION(5)) +#define IOMMU_INT_MASK (IOMMU_INT_INVALID_L1PG | \ + IOMMU_INT_INVALID_L2PG | \ + IOMMU_INT_MASTER_MASK) + +#define PT_ENTRY_SIZE sizeof(u32) + +#define NUM_DT_ENTRIES 4096 +#define DT_SIZE (NUM_DT_ENTRIES * PT_ENTRY_SIZE) + +#define NUM_PT_ENTRIES 256 +#define PT_SIZE (NUM_PT_ENTRIES * PT_ENTRY_SIZE) + +struct sun50i_iommu { + struct iommu_device iommu; + + /* Lock to modify the IOMMU registers */ + spinlock_t iommu_lock; + + struct device *dev; + void __iomem *base; + struct reset_control *reset; + struct clk *clk; + + struct iommu_domain *domain; + struct iommu_group *group; + struct kmem_cache *pt_pool; +}; + +struct sun50i_iommu_domain { + struct iommu_domain domain; + + /* Number of devices attached to the domain */ + refcount_t refcnt; + + /* L1 Page Table */ + u32 *dt; + dma_addr_t dt_dma; + + struct sun50i_iommu *iommu; +}; + +static struct sun50i_iommu_domain *to_sun50i_domain(struct iommu_domain *domain) +{ + return container_of(domain, struct sun50i_iommu_domain, domain); +} + +static struct sun50i_iommu *sun50i_iommu_from_dev(struct device *dev) +{ + return dev_iommu_priv_get(dev); +} + +static u32 iommu_read(struct sun50i_iommu *iommu, u32 offset) +{ + return readl(iommu->base + offset); +} + +static void iommu_write(struct sun50i_iommu *iommu, u32 offset, u32 value) +{ + writel(value, iommu->base + offset); +} + +/* + * The Allwinner H6 IOMMU uses a 2-level page table. + * + * The first level is the usual Directory Table (DT), that consists of + * 4096 4-bytes Directory Table Entries (DTE), each pointing to a Page + * Table (PT). + * + * Each PT consits of 256 4-bytes Page Table Entries (PTE), each + * pointing to a 4kB page of physical memory. + * + * The IOMMU supports a single DT, pointed by the IOMMU_TTB_REG + * register that contains its physical address. + */ + +#define SUN50I_IOVA_DTE_MASK GENMASK(31, 20) +#define SUN50I_IOVA_PTE_MASK GENMASK(19, 12) +#define SUN50I_IOVA_PAGE_MASK GENMASK(11, 0) + +static u32 sun50i_iova_get_dte_index(dma_addr_t iova) +{ + return FIELD_GET(SUN50I_IOVA_DTE_MASK, iova); +} + +static u32 sun50i_iova_get_pte_index(dma_addr_t iova) +{ + return FIELD_GET(SUN50I_IOVA_PTE_MASK, iova); +} + +static u32 sun50i_iova_get_page_offset(dma_addr_t iova) +{ + return FIELD_GET(SUN50I_IOVA_PAGE_MASK, iova); +} + +/* + * Each Directory Table Entry has a Page Table address and a valid + * bit: + + * +---------------------+-----------+-+ + * | PT address | Reserved |V| + * +---------------------+-----------+-+ + * 31:10 - Page Table address + * 9:2 - Reserved + * 1:0 - 1 if the entry is valid + */ + +#define SUN50I_DTE_PT_ADDRESS_MASK GENMASK(31, 10) +#define SUN50I_DTE_PT_ATTRS GENMASK(1, 0) +#define SUN50I_DTE_PT_VALID 1 + +static phys_addr_t sun50i_dte_get_pt_address(u32 dte) +{ + return (phys_addr_t)dte & SUN50I_DTE_PT_ADDRESS_MASK; +} + +static bool sun50i_dte_is_pt_valid(u32 dte) +{ + return (dte & SUN50I_DTE_PT_ATTRS) == SUN50I_DTE_PT_VALID; +} + +static u32 sun50i_mk_dte(dma_addr_t pt_dma) +{ + return (pt_dma & SUN50I_DTE_PT_ADDRESS_MASK) | SUN50I_DTE_PT_VALID; +} + +/* + * Each PTE has a Page address, an authority index and a valid bit: + * + * +----------------+-----+-----+-----+---+-----+ + * | Page address | Rsv | ACI | Rsv | V | Rsv | + * +----------------+-----+-----+-----+---+-----+ + * 31:12 - Page address + * 11:8 - Reserved + * 7:4 - Authority Control Index + * 3:2 - Reserved + * 1 - 1 if the entry is valid + * 0 - Reserved + * + * The way permissions work is that the IOMMU has 16 "domains" that + * can be configured to give each masters either read or write + * permissions through the IOMMU_DM_AUT_CTRL_REG registers. The domain + * 0 seems like the default domain, and its permissions in the + * IOMMU_DM_AUT_CTRL_REG are only read-only, so it's not really + * useful to enforce any particular permission. + * + * Each page entry will then have a reference to the domain they are + * affected to, so that we can actually enforce them on a per-page + * basis. + * + * In order to make it work with the IOMMU framework, we will be using + * 4 different domains, starting at 1: RD_WR, RD, WR and NONE + * depending on the permission we want to enforce. Each domain will + * have each master setup in the same way, since the IOMMU framework + * doesn't seem to restrict page access on a per-device basis. And + * then we will use the relevant domain index when generating the page + * table entry depending on the permissions we want to be enforced. + */ + +enum sun50i_iommu_aci { + SUN50I_IOMMU_ACI_DO_NOT_USE = 0, + SUN50I_IOMMU_ACI_NONE, + SUN50I_IOMMU_ACI_RD, + SUN50I_IOMMU_ACI_WR, + SUN50I_IOMMU_ACI_RD_WR, +}; + +#define SUN50I_PTE_PAGE_ADDRESS_MASK GENMASK(31, 12) +#define SUN50I_PTE_ACI_MASK GENMASK(7, 4) +#define SUN50I_PTE_PAGE_VALID BIT(1) + +static phys_addr_t sun50i_pte_get_page_address(u32 pte) +{ + return (phys_addr_t)pte & SUN50I_PTE_PAGE_ADDRESS_MASK; +} + +static enum sun50i_iommu_aci sun50i_get_pte_aci(u32 pte) +{ + return FIELD_GET(SUN50I_PTE_ACI_MASK, pte); +} + +static bool sun50i_pte_is_page_valid(u32 pte) +{ + return pte & SUN50I_PTE_PAGE_VALID; +} + +static u32 sun50i_mk_pte(phys_addr_t page, int prot) +{ + enum sun50i_iommu_aci aci; + u32 flags = 0; + + if (prot & (IOMMU_READ | IOMMU_WRITE)) + aci = SUN50I_IOMMU_ACI_RD_WR; + else if (prot & IOMMU_READ) + aci = SUN50I_IOMMU_ACI_RD; + else if (prot & IOMMU_WRITE) + aci = SUN50I_IOMMU_ACI_WR; + else + aci = SUN50I_IOMMU_ACI_NONE; + + flags |= FIELD_PREP(SUN50I_PTE_ACI_MASK, aci); + page &= SUN50I_PTE_PAGE_ADDRESS_MASK; + return page | flags | SUN50I_PTE_PAGE_VALID; +} + +static void sun50i_table_flush(struct sun50i_iommu_domain *sun50i_domain, + void *vaddr, unsigned int count) +{ + struct sun50i_iommu *iommu = sun50i_domain->iommu; + dma_addr_t dma = virt_to_phys(vaddr); + size_t size = count * PT_ENTRY_SIZE; + + dma_sync_single_for_device(iommu->dev, dma, size, DMA_TO_DEVICE); +} + +static int sun50i_iommu_flush_all_tlb(struct sun50i_iommu *iommu) +{ + u32 reg; + int ret; + + assert_spin_locked(&iommu->iommu_lock); + + iommu_write(iommu, + IOMMU_TLB_FLUSH_REG, + IOMMU_TLB_FLUSH_PTW_CACHE | + IOMMU_TLB_FLUSH_MACRO_TLB | + IOMMU_TLB_FLUSH_MICRO_TLB(5) | + IOMMU_TLB_FLUSH_MICRO_TLB(4) | + IOMMU_TLB_FLUSH_MICRO_TLB(3) | + IOMMU_TLB_FLUSH_MICRO_TLB(2) | + IOMMU_TLB_FLUSH_MICRO_TLB(1) | + IOMMU_TLB_FLUSH_MICRO_TLB(0)); + + ret = readl_poll_timeout(iommu->base + IOMMU_TLB_FLUSH_REG, + reg, !reg, + 1, 2000); + if (ret) + dev_warn(iommu->dev, "TLB Flush timed out!\n"); + + return ret; +} + +static void sun50i_iommu_flush_iotlb_all(struct iommu_domain *domain) +{ + struct sun50i_iommu_domain *sun50i_domain = to_sun50i_domain(domain); + struct sun50i_iommu *iommu = sun50i_domain->iommu; + unsigned long flags; + + /* + * At boot, we'll have a first call into .flush_iotlb_all right after + * .probe_device, and since we link our (single) domain to our iommu in + * the .attach_device callback, we don't have that pointer set. + * + * It shouldn't really be any trouble to ignore it though since we flush + * all caches as part of the device powerup. + */ + if (!iommu) + return; + + spin_lock_irqsave(&iommu->iommu_lock, flags); + sun50i_iommu_flush_all_tlb(iommu); + spin_unlock_irqrestore(&iommu->iommu_lock, flags); +} + +static void sun50i_iommu_iotlb_sync(struct iommu_domain *domain, + struct iommu_iotlb_gather *gather) +{ + sun50i_iommu_flush_iotlb_all(domain); +} + +static int sun50i_iommu_enable(struct sun50i_iommu *iommu) +{ + struct sun50i_iommu_domain *sun50i_domain; + unsigned long flags; + int ret; + + if (!iommu->domain) + return 0; + + sun50i_domain = to_sun50i_domain(iommu->domain); + + ret = reset_control_deassert(iommu->reset); + if (ret) + return ret; + + ret = clk_prepare_enable(iommu->clk); + if (ret) + goto err_reset_assert; + + spin_lock_irqsave(&iommu->iommu_lock, flags); + + iommu_write(iommu, IOMMU_TTB_REG, sun50i_domain->dt_dma); + iommu_write(iommu, IOMMU_TLB_PREFETCH_REG, + IOMMU_TLB_PREFETCH_MASTER_ENABLE(0) | + IOMMU_TLB_PREFETCH_MASTER_ENABLE(1) | + IOMMU_TLB_PREFETCH_MASTER_ENABLE(2) | + IOMMU_TLB_PREFETCH_MASTER_ENABLE(3) | + IOMMU_TLB_PREFETCH_MASTER_ENABLE(4) | + IOMMU_TLB_PREFETCH_MASTER_ENABLE(5)); + iommu_write(iommu, IOMMU_INT_ENABLE_REG, IOMMU_INT_MASK); + iommu_write(iommu, IOMMU_DM_AUT_CTRL_REG(SUN50I_IOMMU_ACI_NONE), + IOMMU_DM_AUT_CTRL_RD_UNAVAIL(SUN50I_IOMMU_ACI_NONE, 0) | + IOMMU_DM_AUT_CTRL_WR_UNAVAIL(SUN50I_IOMMU_ACI_NONE, 0) | + IOMMU_DM_AUT_CTRL_RD_UNAVAIL(SUN50I_IOMMU_ACI_NONE, 1) | + IOMMU_DM_AUT_CTRL_WR_UNAVAIL(SUN50I_IOMMU_ACI_NONE, 1) | + IOMMU_DM_AUT_CTRL_RD_UNAVAIL(SUN50I_IOMMU_ACI_NONE, 2) | + IOMMU_DM_AUT_CTRL_WR_UNAVAIL(SUN50I_IOMMU_ACI_NONE, 2) | + IOMMU_DM_AUT_CTRL_RD_UNAVAIL(SUN50I_IOMMU_ACI_NONE, 3) | + IOMMU_DM_AUT_CTRL_WR_UNAVAIL(SUN50I_IOMMU_ACI_NONE, 3) | + IOMMU_DM_AUT_CTRL_RD_UNAVAIL(SUN50I_IOMMU_ACI_NONE, 4) | + IOMMU_DM_AUT_CTRL_WR_UNAVAIL(SUN50I_IOMMU_ACI_NONE, 4) | + IOMMU_DM_AUT_CTRL_RD_UNAVAIL(SUN50I_IOMMU_ACI_NONE, 5) | + IOMMU_DM_AUT_CTRL_WR_UNAVAIL(SUN50I_IOMMU_ACI_NONE, 5)); + + iommu_write(iommu, IOMMU_DM_AUT_CTRL_REG(SUN50I_IOMMU_ACI_RD), + IOMMU_DM_AUT_CTRL_WR_UNAVAIL(SUN50I_IOMMU_ACI_RD, 0) | + IOMMU_DM_AUT_CTRL_WR_UNAVAIL(SUN50I_IOMMU_ACI_RD, 1) | + IOMMU_DM_AUT_CTRL_WR_UNAVAIL(SUN50I_IOMMU_ACI_RD, 2) | + IOMMU_DM_AUT_CTRL_WR_UNAVAIL(SUN50I_IOMMU_ACI_RD, 3) | + IOMMU_DM_AUT_CTRL_WR_UNAVAIL(SUN50I_IOMMU_ACI_RD, 4) | + IOMMU_DM_AUT_CTRL_WR_UNAVAIL(SUN50I_IOMMU_ACI_RD, 5)); + + iommu_write(iommu, IOMMU_DM_AUT_CTRL_REG(SUN50I_IOMMU_ACI_WR), + IOMMU_DM_AUT_CTRL_RD_UNAVAIL(SUN50I_IOMMU_ACI_WR, 0) | + IOMMU_DM_AUT_CTRL_RD_UNAVAIL(SUN50I_IOMMU_ACI_WR, 1) | + IOMMU_DM_AUT_CTRL_RD_UNAVAIL(SUN50I_IOMMU_ACI_WR, 2) | + IOMMU_DM_AUT_CTRL_RD_UNAVAIL(SUN50I_IOMMU_ACI_WR, 3) | + IOMMU_DM_AUT_CTRL_RD_UNAVAIL(SUN50I_IOMMU_ACI_WR, 4) | + IOMMU_DM_AUT_CTRL_RD_UNAVAIL(SUN50I_IOMMU_ACI_WR, 5)); + + ret = sun50i_iommu_flush_all_tlb(iommu); + if (ret) { + spin_unlock_irqrestore(&iommu->iommu_lock, flags); + goto err_clk_disable; + } + + iommu_write(iommu, IOMMU_AUTO_GATING_REG, IOMMU_AUTO_GATING_ENABLE); + iommu_write(iommu, IOMMU_ENABLE_REG, IOMMU_ENABLE_ENABLE); + + spin_unlock_irqrestore(&iommu->iommu_lock, flags); + + return 0; + +err_clk_disable: + clk_disable_unprepare(iommu->clk); + +err_reset_assert: + reset_control_assert(iommu->reset); + + return ret; +} + +static void sun50i_iommu_disable(struct sun50i_iommu *iommu) +{ + unsigned long flags; + + spin_lock_irqsave(&iommu->iommu_lock, flags); + + iommu_write(iommu, IOMMU_ENABLE_REG, 0); + iommu_write(iommu, IOMMU_TTB_REG, 0); + + spin_unlock_irqrestore(&iommu->iommu_lock, flags); + + clk_disable_unprepare(iommu->clk); + reset_control_assert(iommu->reset); +} + +static void *sun50i_iommu_alloc_page_table(struct sun50i_iommu *iommu, + gfp_t gfp) +{ + dma_addr_t pt_dma; + u32 *page_table; + + page_table = kmem_cache_zalloc(iommu->pt_pool, gfp); + if (!page_table) + return ERR_PTR(-ENOMEM); + + pt_dma = dma_map_single(iommu->dev, page_table, PT_SIZE, DMA_TO_DEVICE); + if (dma_mapping_error(iommu->dev, pt_dma)) { + dev_err(iommu->dev, "Couldn't map L2 Page Table\n"); + kmem_cache_free(iommu->pt_pool, page_table); + return ERR_PTR(-ENOMEM); + } + + /* We rely on the physical address and DMA address being the same */ + WARN_ON(pt_dma != virt_to_phys(page_table)); + + return page_table; +} + +static void sun50i_iommu_free_page_table(struct sun50i_iommu *iommu, + u32 *page_table) +{ + phys_addr_t pt_phys = virt_to_phys(page_table); + + dma_unmap_single(iommu->dev, pt_phys, PT_SIZE, DMA_TO_DEVICE); + kmem_cache_free(iommu->pt_pool, page_table); +} + +static u32 *sun50i_dte_get_page_table(struct sun50i_iommu_domain *sun50i_domain, + dma_addr_t iova, gfp_t gfp) +{ + struct sun50i_iommu *iommu = sun50i_domain->iommu; + u32 *page_table; + u32 *dte_addr; + u32 old_dte; + u32 dte; + + dte_addr = &sun50i_domain->dt[sun50i_iova_get_dte_index(iova)]; + dte = *dte_addr; + if (sun50i_dte_is_pt_valid(dte)) { + phys_addr_t pt_phys = sun50i_dte_get_pt_address(dte); + return (u32 *)phys_to_virt(pt_phys); + } + + page_table = sun50i_iommu_alloc_page_table(iommu, gfp); + if (IS_ERR(page_table)) + return page_table; + + dte = sun50i_mk_dte(virt_to_phys(page_table)); + old_dte = cmpxchg(dte_addr, 0, dte); + if (old_dte) { + phys_addr_t installed_pt_phys = + sun50i_dte_get_pt_address(old_dte); + u32 *installed_pt = phys_to_virt(installed_pt_phys); + u32 *drop_pt = page_table; + + page_table = installed_pt; + dte = old_dte; + sun50i_iommu_free_page_table(iommu, drop_pt); + } + + sun50i_table_flush(sun50i_domain, page_table, PT_SIZE); + sun50i_table_flush(sun50i_domain, dte_addr, 1); + + return page_table; +} + +static int sun50i_iommu_map(struct iommu_domain *domain, unsigned long iova, + phys_addr_t paddr, size_t size, int prot, gfp_t gfp) +{ + struct sun50i_iommu_domain *sun50i_domain = to_sun50i_domain(domain); + struct sun50i_iommu *iommu = sun50i_domain->iommu; + u32 pte_index; + u32 *page_table, *pte_addr; + int ret = 0; + + page_table = sun50i_dte_get_page_table(sun50i_domain, iova, gfp); + if (IS_ERR(page_table)) { + ret = PTR_ERR(page_table); + goto out; + } + + pte_index = sun50i_iova_get_pte_index(iova); + pte_addr = &page_table[pte_index]; + if (unlikely(sun50i_pte_is_page_valid(*pte_addr))) { + phys_addr_t page_phys = sun50i_pte_get_page_address(*pte_addr); + dev_err(iommu->dev, + "iova %pad already mapped to %pa cannot remap to %pa prot: %#x\n", + &iova, &page_phys, &paddr, prot); + ret = -EBUSY; + goto out; + } + + *pte_addr = sun50i_mk_pte(paddr, prot); + sun50i_table_flush(sun50i_domain, pte_addr, 1); + +out: + return ret; +} + +static size_t sun50i_iommu_unmap(struct iommu_domain *domain, unsigned long iova, + size_t size, struct iommu_iotlb_gather *gather) +{ + struct sun50i_iommu_domain *sun50i_domain = to_sun50i_domain(domain); + phys_addr_t pt_phys; + dma_addr_t pte_dma; + u32 *pte_addr; + u32 dte; + + dte = sun50i_domain->dt[sun50i_iova_get_dte_index(iova)]; + if (!sun50i_dte_is_pt_valid(dte)) + return 0; + + pt_phys = sun50i_dte_get_pt_address(dte); + pte_addr = (u32 *)phys_to_virt(pt_phys) + sun50i_iova_get_pte_index(iova); + pte_dma = pt_phys + sun50i_iova_get_pte_index(iova) * PT_ENTRY_SIZE; + + if (!sun50i_pte_is_page_valid(*pte_addr)) + return 0; + + memset(pte_addr, 0, sizeof(*pte_addr)); + sun50i_table_flush(sun50i_domain, pte_addr, 1); + + return SZ_4K; +} + +static phys_addr_t sun50i_iommu_iova_to_phys(struct iommu_domain *domain, + dma_addr_t iova) +{ + struct sun50i_iommu_domain *sun50i_domain = to_sun50i_domain(domain); + phys_addr_t pt_phys; + u32 *page_table; + u32 dte, pte; + + dte = sun50i_domain->dt[sun50i_iova_get_dte_index(iova)]; + if (!sun50i_dte_is_pt_valid(dte)) + return 0; + + pt_phys = sun50i_dte_get_pt_address(dte); + page_table = (u32 *)phys_to_virt(pt_phys); + pte = page_table[sun50i_iova_get_pte_index(iova)]; + if (!sun50i_pte_is_page_valid(pte)) + return 0; + + return sun50i_pte_get_page_address(pte) + + sun50i_iova_get_page_offset(iova); +} + +static struct iommu_domain *sun50i_iommu_domain_alloc(unsigned type) +{ + struct sun50i_iommu_domain *sun50i_domain; + + if (type != IOMMU_DOMAIN_DMA && + type != IOMMU_DOMAIN_IDENTITY && + type != IOMMU_DOMAIN_UNMANAGED) + return NULL; + + sun50i_domain = kzalloc(sizeof(*sun50i_domain), GFP_KERNEL); + if (!sun50i_domain) + return NULL; + + if (type == IOMMU_DOMAIN_DMA && + iommu_get_dma_cookie(&sun50i_domain->domain)) + goto err_free_domain; + + sun50i_domain->dt = (u32 *)__get_free_pages(GFP_KERNEL | __GFP_ZERO, + get_order(DT_SIZE)); + if (!sun50i_domain->dt) + goto err_put_cookie; + + refcount_set(&sun50i_domain->refcnt, 1); + + sun50i_domain->domain.geometry.aperture_start = 0; + sun50i_domain->domain.geometry.aperture_end = DMA_BIT_MASK(32); + sun50i_domain->domain.geometry.force_aperture = true; + + return &sun50i_domain->domain; + +err_put_cookie: + if (type == IOMMU_DOMAIN_DMA) + iommu_put_dma_cookie(&sun50i_domain->domain); + +err_free_domain: + kfree(sun50i_domain); + + return NULL; +} + +static void sun50i_iommu_domain_free(struct iommu_domain *domain) +{ + struct sun50i_iommu_domain *sun50i_domain = to_sun50i_domain(domain); + + free_pages((unsigned long)sun50i_domain->dt, get_order(DT_SIZE)); + sun50i_domain->dt = NULL; + + iommu_put_dma_cookie(domain); + + kfree(sun50i_domain); +} + +static int sun50i_iommu_attach_domain(struct sun50i_iommu *iommu, + struct sun50i_iommu_domain *sun50i_domain) +{ + iommu->domain = &sun50i_domain->domain; + sun50i_domain->iommu = iommu; + + sun50i_domain->dt_dma = dma_map_single(iommu->dev, sun50i_domain->dt, + DT_SIZE, DMA_TO_DEVICE); + if (dma_mapping_error(iommu->dev, sun50i_domain->dt_dma)) { + dev_err(iommu->dev, "Couldn't map L1 Page Table\n"); + return -ENOMEM; + } + + return sun50i_iommu_enable(iommu); +} + +static void sun50i_iommu_detach_domain(struct sun50i_iommu *iommu, + struct sun50i_iommu_domain *sun50i_domain) +{ + unsigned int i; + + for (i = 0; i < NUM_DT_ENTRIES; i++) { + phys_addr_t pt_phys; + u32 *page_table; + u32 *dte_addr; + u32 dte; + + dte_addr = &sun50i_domain->dt[i]; + dte = *dte_addr; + if (!sun50i_dte_is_pt_valid(dte)) + continue; + + memset(dte_addr, 0, sizeof(*dte_addr)); + sun50i_table_flush(sun50i_domain, dte_addr, 1); + + pt_phys = sun50i_dte_get_pt_address(dte); + page_table = phys_to_virt(pt_phys); + sun50i_iommu_free_page_table(iommu, page_table); + } + + + sun50i_iommu_disable(iommu); + + dma_unmap_single(iommu->dev, virt_to_phys(sun50i_domain->dt), + DT_SIZE, DMA_TO_DEVICE); + + iommu->domain = NULL; +} + +static void sun50i_iommu_detach_device(struct iommu_domain *domain, + struct device *dev) +{ + struct sun50i_iommu_domain *sun50i_domain = to_sun50i_domain(domain); + struct sun50i_iommu *iommu = dev_iommu_priv_get(dev); + + dev_dbg(dev, "Detaching from IOMMU domain\n"); + + if (iommu->domain != domain) + return; + + if (refcount_dec_and_test(&sun50i_domain->refcnt)) + sun50i_iommu_detach_domain(iommu, sun50i_domain); +} + +static int sun50i_iommu_attach_device(struct iommu_domain *domain, + struct device *dev) +{ + struct sun50i_iommu_domain *sun50i_domain = to_sun50i_domain(domain); + struct sun50i_iommu *iommu; + + iommu = sun50i_iommu_from_dev(dev); + if (!iommu) + return -ENODEV; + + dev_dbg(dev, "Attaching to IOMMU domain\n"); + + refcount_inc(&sun50i_domain->refcnt); + + if (iommu->domain == domain) + return 0; + + if (iommu->domain) + sun50i_iommu_detach_device(iommu->domain, dev); + + sun50i_iommu_attach_domain(iommu, sun50i_domain); + + return 0; +} + +static struct iommu_device *sun50i_iommu_probe_device(struct device *dev) +{ + struct sun50i_iommu *iommu; + + iommu = sun50i_iommu_from_dev(dev); + if (!iommu) + return ERR_PTR(-ENODEV); + + return &iommu->iommu; +} + +static void sun50i_iommu_release_device(struct device *dev) {} + +static struct iommu_group *sun50i_iommu_device_group(struct device *dev) +{ + struct sun50i_iommu *iommu = sun50i_iommu_from_dev(dev); + + return iommu_group_ref_get(iommu->group); +} + +static int sun50i_iommu_of_xlate(struct device *dev, + struct of_phandle_args *args) +{ + struct platform_device *iommu_pdev = of_find_device_by_node(args->np); + unsigned id = args->args[0]; + + dev_iommu_priv_set(dev, platform_get_drvdata(iommu_pdev)); + + return iommu_fwspec_add_ids(dev, &id, 1); +} + +static const struct iommu_ops sun50i_iommu_ops = { + .pgsize_bitmap = SZ_4K, + .attach_dev = sun50i_iommu_attach_device, + .detach_dev = sun50i_iommu_detach_device, + .device_group = sun50i_iommu_device_group, + .domain_alloc = sun50i_iommu_domain_alloc, + .domain_free = sun50i_iommu_domain_free, + .flush_iotlb_all = sun50i_iommu_flush_iotlb_all, + .iotlb_sync = sun50i_iommu_iotlb_sync, + .iova_to_phys = sun50i_iommu_iova_to_phys, + .map = sun50i_iommu_map, + .of_xlate = sun50i_iommu_of_xlate, + .probe_device = sun50i_iommu_probe_device, + .release_device = sun50i_iommu_release_device, + .unmap = sun50i_iommu_unmap, +}; + +static void sun50i_iommu_report_fault(struct sun50i_iommu *iommu, + unsigned master, phys_addr_t iova, + unsigned prot) +{ + dev_err(iommu->dev, "Page fault for %pad (master %d, dir %s)\n", + &iova, master, (prot == IOMMU_FAULT_WRITE) ? "wr" : "rd"); + + if (iommu->domain) + report_iommu_fault(iommu->domain, iommu->dev, iova, prot); + else + dev_err(iommu->dev, "Page fault while iommu not attached to any domain?\n"); +} + +static phys_addr_t sun50i_iommu_handle_pt_irq(struct sun50i_iommu *iommu, + unsigned addr_reg, + unsigned blame_reg) +{ + phys_addr_t iova; + unsigned master; + u32 blame; + + assert_spin_locked(&iommu->iommu_lock); + + iova = iommu_read(iommu, addr_reg); + blame = iommu_read(iommu, blame_reg); + master = ilog2(blame & IOMMU_INT_MASTER_MASK); + + /* + * If the address is not in the page table, we can't get what + * operation triggered the fault. Assume it's a read + * operation. + */ + sun50i_iommu_report_fault(iommu, master, iova, IOMMU_FAULT_READ); + + return iova; +} + +static phys_addr_t sun50i_iommu_handle_perm_irq(struct sun50i_iommu *iommu) +{ + enum sun50i_iommu_aci aci; + phys_addr_t iova; + unsigned master; + unsigned dir; + u32 blame; + + assert_spin_locked(&iommu->iommu_lock); + + blame = iommu_read(iommu, IOMMU_INT_STA_REG); + master = ilog2(blame & IOMMU_INT_MASTER_MASK); + iova = iommu_read(iommu, IOMMU_INT_ERR_ADDR_REG(master)); + aci = sun50i_get_pte_aci(iommu_read(iommu, + IOMMU_INT_ERR_DATA_REG(master))); + + switch (aci) { + /* + * If we are in the read-only domain, then it means we + * tried to write. + */ + case SUN50I_IOMMU_ACI_RD: + dir = IOMMU_FAULT_WRITE; + break; + + /* + * If we are in the write-only domain, then it means + * we tried to read. + */ + case SUN50I_IOMMU_ACI_WR: + + /* + * If we are in the domain without any permission, we + * can't really tell. Let's default to a read + * operation. + */ + case SUN50I_IOMMU_ACI_NONE: + + /* WTF? */ + case SUN50I_IOMMU_ACI_RD_WR: + default: + dir = IOMMU_FAULT_READ; + break; + } + + /* + * If the address is not in the page table, we can't get what + * operation triggered the fault. Assume it's a read + * operation. + */ + sun50i_iommu_report_fault(iommu, master, iova, dir); + + return iova; +} + +static irqreturn_t sun50i_iommu_irq(int irq, void *dev_id) +{ + struct sun50i_iommu *iommu = dev_id; + phys_addr_t iova; + u32 status; + + spin_lock(&iommu->iommu_lock); + + status = iommu_read(iommu, IOMMU_INT_STA_REG); + if (!(status & IOMMU_INT_MASK)) { + spin_unlock(&iommu->iommu_lock); + return IRQ_NONE; + } + + if (status & IOMMU_INT_INVALID_L2PG) + iova = sun50i_iommu_handle_pt_irq(iommu, + IOMMU_INT_ERR_ADDR_L2_REG, + IOMMU_L2PG_INT_REG); + else if (status & IOMMU_INT_INVALID_L1PG) + iova = sun50i_iommu_handle_pt_irq(iommu, + IOMMU_INT_ERR_ADDR_L1_REG, + IOMMU_L1PG_INT_REG); + else + iova = sun50i_iommu_handle_perm_irq(iommu); + + iommu_write(iommu, IOMMU_INT_CLR_REG, status); + + iommu_write(iommu, IOMMU_RESET_REG, ~status); + iommu_write(iommu, IOMMU_RESET_REG, status); + + spin_unlock(&iommu->iommu_lock); + + return IRQ_HANDLED; +} + +static int sun50i_iommu_probe(struct platform_device *pdev) +{ + struct sun50i_iommu *iommu; + int ret, irq; + + iommu = devm_kzalloc(&pdev->dev, sizeof(*iommu), GFP_KERNEL); + if (!iommu) + return -ENOMEM; + spin_lock_init(&iommu->iommu_lock); + platform_set_drvdata(pdev, iommu); + iommu->dev = &pdev->dev; + + iommu->pt_pool = kmem_cache_create(dev_name(&pdev->dev), + PT_SIZE, PT_SIZE, + SLAB_HWCACHE_ALIGN, + NULL); + if (!iommu->pt_pool) + return -ENOMEM; + + iommu->group = iommu_group_alloc(); + if (IS_ERR(iommu->group)) { + ret = PTR_ERR(iommu->group); + goto err_free_cache; + } + + iommu->base = devm_platform_ioremap_resource(pdev, 0); + if (IS_ERR(iommu->base)) { + ret = PTR_ERR(iommu->base); + goto err_free_group; + } + + irq = platform_get_irq(pdev, 0); + if (irq < 0) { + ret = irq; + goto err_free_group; + } + + iommu->clk = devm_clk_get(&pdev->dev, NULL); + if (IS_ERR(iommu->clk)) { + dev_err(&pdev->dev, "Couldn't get our clock.\n"); + ret = PTR_ERR(iommu->clk); + goto err_free_group; + } + + iommu->reset = devm_reset_control_get(&pdev->dev, NULL); + if (IS_ERR(iommu->reset)) { + dev_err(&pdev->dev, "Couldn't get our reset line.\n"); + ret = PTR_ERR(iommu->reset); + goto err_free_group; + } + + ret = iommu_device_sysfs_add(&iommu->iommu, &pdev->dev, + NULL, dev_name(&pdev->dev)); + if (ret) + goto err_free_group; + + iommu_device_set_ops(&iommu->iommu, &sun50i_iommu_ops); + iommu_device_set_fwnode(&iommu->iommu, &pdev->dev.of_node->fwnode); + + ret = iommu_device_register(&iommu->iommu); + if (ret) + goto err_remove_sysfs; + + ret = devm_request_irq(&pdev->dev, irq, sun50i_iommu_irq, 0, + dev_name(&pdev->dev), iommu); + if (ret < 0) + goto err_unregister; + + bus_set_iommu(&platform_bus_type, &sun50i_iommu_ops); + + return 0; + +err_unregister: + iommu_device_unregister(&iommu->iommu); + +err_remove_sysfs: + iommu_device_sysfs_remove(&iommu->iommu); + +err_free_group: + iommu_group_put(iommu->group); + +err_free_cache: + kmem_cache_destroy(iommu->pt_pool); + + return ret; +} + +static const struct of_device_id sun50i_iommu_dt[] = { + { .compatible = "allwinner,sun50i-h6-iommu", }, + { /* sentinel */ }, +}; +MODULE_DEVICE_TABLE(of, sun50i_iommu_dt); + +static struct platform_driver sun50i_iommu_driver = { + .driver = { + .name = "sun50i-iommu", + .of_match_table = sun50i_iommu_dt, + .suppress_bind_attrs = true, + } +}; +builtin_platform_driver_probe(sun50i_iommu_driver, sun50i_iommu_probe); + +MODULE_DESCRIPTION("Allwinner H6 IOMMU driver"); +MODULE_AUTHOR("Maxime Ripard <maxime@cerno.tech>"); +MODULE_AUTHOR("zhuxianbin <zhuxianbin@allwinnertech.com>"); +MODULE_LICENSE("Dual BSD/GPL"); diff --git a/drivers/misc/uacce/uacce.c b/drivers/misc/uacce/uacce.c index d39307f060bd..107028e77ca3 100644 --- a/drivers/misc/uacce/uacce.c +++ b/drivers/misc/uacce/uacce.c @@ -90,109 +90,39 @@ static long uacce_fops_compat_ioctl(struct file *filep, } #endif -static int uacce_sva_exit(struct device *dev, struct iommu_sva *handle, - void *data) +static int uacce_bind_queue(struct uacce_device *uacce, struct uacce_queue *q) { - struct uacce_mm *uacce_mm = data; - struct uacce_queue *q; - - /* - * No new queue can be added concurrently because no caller can have a - * reference to this mm. But there may be concurrent calls to - * uacce_mm_put(), so we need the lock. - */ - mutex_lock(&uacce_mm->lock); - list_for_each_entry(q, &uacce_mm->queues, list) - uacce_put_queue(q); - uacce_mm->mm = NULL; - mutex_unlock(&uacce_mm->lock); + int pasid; + struct iommu_sva *handle; - return 0; -} - -static struct iommu_sva_ops uacce_sva_ops = { - .mm_exit = uacce_sva_exit, -}; - -static struct uacce_mm *uacce_mm_get(struct uacce_device *uacce, - struct uacce_queue *q, - struct mm_struct *mm) -{ - struct uacce_mm *uacce_mm = NULL; - struct iommu_sva *handle = NULL; - int ret; - - lockdep_assert_held(&uacce->mm_lock); - - list_for_each_entry(uacce_mm, &uacce->mm_list, list) { - if (uacce_mm->mm == mm) { - mutex_lock(&uacce_mm->lock); - list_add(&q->list, &uacce_mm->queues); - mutex_unlock(&uacce_mm->lock); - return uacce_mm; - } - } - - uacce_mm = kzalloc(sizeof(*uacce_mm), GFP_KERNEL); - if (!uacce_mm) - return NULL; + if (!(uacce->flags & UACCE_DEV_SVA)) + return 0; - if (uacce->flags & UACCE_DEV_SVA) { - /* - * Safe to pass an incomplete uacce_mm, since mm_exit cannot - * fire while we hold a reference to the mm. - */ - handle = iommu_sva_bind_device(uacce->parent, mm, uacce_mm); - if (IS_ERR(handle)) - goto err_free; + handle = iommu_sva_bind_device(uacce->parent, current->mm, NULL); + if (IS_ERR(handle)) + return PTR_ERR(handle); - ret = iommu_sva_set_ops(handle, &uacce_sva_ops); - if (ret) - goto err_unbind; - - uacce_mm->pasid = iommu_sva_get_pasid(handle); - if (uacce_mm->pasid == IOMMU_PASID_INVALID) - goto err_unbind; + pasid = iommu_sva_get_pasid(handle); + if (pasid == IOMMU_PASID_INVALID) { + iommu_sva_unbind_device(handle); + return -ENODEV; } - uacce_mm->mm = mm; - uacce_mm->handle = handle; - INIT_LIST_HEAD(&uacce_mm->queues); - mutex_init(&uacce_mm->lock); - list_add(&q->list, &uacce_mm->queues); - list_add(&uacce_mm->list, &uacce->mm_list); - - return uacce_mm; - -err_unbind: - if (handle) - iommu_sva_unbind_device(handle); -err_free: - kfree(uacce_mm); - return NULL; + q->handle = handle; + q->pasid = pasid; + return 0; } -static void uacce_mm_put(struct uacce_queue *q) +static void uacce_unbind_queue(struct uacce_queue *q) { - struct uacce_mm *uacce_mm = q->uacce_mm; - - lockdep_assert_held(&q->uacce->mm_lock); - - mutex_lock(&uacce_mm->lock); - list_del(&q->list); - mutex_unlock(&uacce_mm->lock); - - if (list_empty(&uacce_mm->queues)) { - if (uacce_mm->handle) - iommu_sva_unbind_device(uacce_mm->handle); - list_del(&uacce_mm->list); - kfree(uacce_mm); - } + if (!q->handle) + return; + iommu_sva_unbind_device(q->handle); + q->handle = NULL; } static int uacce_fops_open(struct inode *inode, struct file *filep) { - struct uacce_mm *uacce_mm = NULL; struct uacce_device *uacce; struct uacce_queue *q; int ret = 0; @@ -205,21 +135,16 @@ static int uacce_fops_open(struct inode *inode, struct file *filep) if (!q) return -ENOMEM; - mutex_lock(&uacce->mm_lock); - uacce_mm = uacce_mm_get(uacce, q, current->mm); - mutex_unlock(&uacce->mm_lock); - if (!uacce_mm) { - ret = -ENOMEM; + ret = uacce_bind_queue(uacce, q); + if (ret) goto out_with_mem; - } q->uacce = uacce; - q->uacce_mm = uacce_mm; if (uacce->ops->get_queue) { - ret = uacce->ops->get_queue(uacce, uacce_mm->pasid, q); + ret = uacce->ops->get_queue(uacce, q->pasid, q); if (ret < 0) - goto out_with_mm; + goto out_with_bond; } init_waitqueue_head(&q->wait); @@ -227,12 +152,14 @@ static int uacce_fops_open(struct inode *inode, struct file *filep) uacce->inode = inode; q->state = UACCE_Q_INIT; + mutex_lock(&uacce->queues_lock); + list_add(&q->list, &uacce->queues); + mutex_unlock(&uacce->queues_lock); + return 0; -out_with_mm: - mutex_lock(&uacce->mm_lock); - uacce_mm_put(q); - mutex_unlock(&uacce->mm_lock); +out_with_bond: + uacce_unbind_queue(q); out_with_mem: kfree(q); return ret; @@ -241,14 +168,12 @@ out_with_mem: static int uacce_fops_release(struct inode *inode, struct file *filep) { struct uacce_queue *q = filep->private_data; - struct uacce_device *uacce = q->uacce; + mutex_lock(&q->uacce->queues_lock); + list_del(&q->list); + mutex_unlock(&q->uacce->queues_lock); uacce_put_queue(q); - - mutex_lock(&uacce->mm_lock); - uacce_mm_put(q); - mutex_unlock(&uacce->mm_lock); - + uacce_unbind_queue(q); kfree(q); return 0; @@ -513,8 +438,8 @@ struct uacce_device *uacce_alloc(struct device *parent, if (ret < 0) goto err_with_uacce; - INIT_LIST_HEAD(&uacce->mm_list); - mutex_init(&uacce->mm_lock); + INIT_LIST_HEAD(&uacce->queues); + mutex_init(&uacce->queues_lock); device_initialize(&uacce->dev); uacce->dev.devt = MKDEV(MAJOR(uacce_devt), uacce->dev_id); uacce->dev.class = uacce_class; @@ -561,8 +486,7 @@ EXPORT_SYMBOL_GPL(uacce_register); */ void uacce_remove(struct uacce_device *uacce) { - struct uacce_mm *uacce_mm; - struct uacce_queue *q; + struct uacce_queue *q, *next_q; if (!uacce) return; @@ -574,24 +498,12 @@ void uacce_remove(struct uacce_device *uacce) unmap_mapping_range(uacce->inode->i_mapping, 0, 0, 1); /* ensure no open queue remains */ - mutex_lock(&uacce->mm_lock); - list_for_each_entry(uacce_mm, &uacce->mm_list, list) { - /* - * We don't take the uacce_mm->lock here. Since we hold the - * device's mm_lock, no queue can be added to or removed from - * this uacce_mm. We may run concurrently with mm_exit, but - * uacce_put_queue() is serialized and iommu_sva_unbind_device() - * waits for the lock that mm_exit is holding. - */ - list_for_each_entry(q, &uacce_mm->queues, list) - uacce_put_queue(q); - - if (uacce->flags & UACCE_DEV_SVA) { - iommu_sva_unbind_device(uacce_mm->handle); - uacce_mm->handle = NULL; - } + mutex_lock(&uacce->queues_lock); + list_for_each_entry_safe(q, next_q, &uacce->queues, list) { + uacce_put_queue(q); + uacce_unbind_queue(q); } - mutex_unlock(&uacce->mm_lock); + mutex_unlock(&uacce->queues_lock); /* disable sva now since no opened queues */ if (uacce->flags & UACCE_DEV_SVA) diff --git a/drivers/mmc/core/block.c b/drivers/mmc/core/block.c index c5367e2c8487..7896952de1ac 100644 --- a/drivers/mmc/core/block.c +++ b/drivers/mmc/core/block.c @@ -2484,8 +2484,8 @@ static int mmc_rpmb_chrdev_release(struct inode *inode, struct file *filp) struct mmc_rpmb_data *rpmb = container_of(inode->i_cdev, struct mmc_rpmb_data, chrdev); - put_device(&rpmb->dev); mmc_blk_put(rpmb->md); + put_device(&rpmb->dev); return 0; } diff --git a/drivers/mmc/host/sdhci.c b/drivers/mmc/host/sdhci.c index 3f716466fcfd..e368f2dabf20 100644 --- a/drivers/mmc/host/sdhci.c +++ b/drivers/mmc/host/sdhci.c @@ -4000,9 +4000,6 @@ int sdhci_setup_host(struct sdhci_host *host) mmc_hostname(mmc), host->version); } - if (host->quirks & SDHCI_QUIRK_BROKEN_CQE) - mmc->caps2 &= ~MMC_CAP2_CQE; - if (host->quirks & SDHCI_QUIRK_FORCE_DMA) host->flags |= SDHCI_USE_SDMA; else if (!(host->caps & SDHCI_CAN_DO_SDMA)) @@ -4539,6 +4536,12 @@ int __sdhci_add_host(struct sdhci_host *host) struct mmc_host *mmc = host->mmc; int ret; + if ((mmc->caps2 & MMC_CAP2_CQE) && + (host->quirks & SDHCI_QUIRK_BROKEN_CQE)) { + mmc->caps2 &= ~MMC_CAP2_CQE; + mmc->cqe_ops = NULL; + } + host->complete_wq = alloc_workqueue("sdhci", flags, 0); if (!host->complete_wq) return -ENOMEM; diff --git a/drivers/net/bonding/bond_sysfs_slave.c b/drivers/net/bonding/bond_sysfs_slave.c index 007481557191..9b8346638f69 100644 --- a/drivers/net/bonding/bond_sysfs_slave.c +++ b/drivers/net/bonding/bond_sysfs_slave.c @@ -149,8 +149,10 @@ int bond_sysfs_slave_add(struct slave *slave) err = kobject_init_and_add(&slave->kobj, &slave_ktype, &(slave->dev->dev.kobj), "bonding_slave"); - if (err) + if (err) { + kobject_put(&slave->kobj); return err; + } for (a = slave_attrs; *a; ++a) { err = sysfs_create_file(&slave->kobj, &((*a)->attr)); diff --git a/drivers/net/dsa/ocelot/felix.c b/drivers/net/dsa/ocelot/felix.c index e8aae64db1ca..e113269c220a 100644 --- a/drivers/net/dsa/ocelot/felix.c +++ b/drivers/net/dsa/ocelot/felix.c @@ -102,13 +102,17 @@ static void felix_vlan_add(struct dsa_switch *ds, int port, const struct switchdev_obj_port_vlan *vlan) { struct ocelot *ocelot = ds->priv; + u16 flags = vlan->flags; u16 vid; int err; + if (dsa_is_cpu_port(ds, port)) + flags &= ~BRIDGE_VLAN_INFO_UNTAGGED; + for (vid = vlan->vid_begin; vid <= vlan->vid_end; vid++) { err = ocelot_vlan_add(ocelot, port, vid, - vlan->flags & BRIDGE_VLAN_INFO_PVID, - vlan->flags & BRIDGE_VLAN_INFO_UNTAGGED); + flags & BRIDGE_VLAN_INFO_PVID, + flags & BRIDGE_VLAN_INFO_UNTAGGED); if (err) { dev_err(ds->dev, "Failed to add VLAN %d to port %d: %d\n", vid, port, err); diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index d1a83716d934..58e0d9a781e9 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -4176,14 +4176,12 @@ static int bnxt_hwrm_do_send_msg(struct bnxt *bp, void *msg, u32 msg_len, int i, intr_process, rc, tmo_count; struct input *req = msg; u32 *data = msg; - __le32 *resp_len; u8 *valid; u16 cp_ring_id, len = 0; struct hwrm_err_output *resp = bp->hwrm_cmd_resp_addr; u16 max_req_len = BNXT_HWRM_MAX_REQ_LEN; struct hwrm_short_input short_input = {0}; u32 doorbell_offset = BNXT_GRCPF_REG_CHIMP_COMM_TRIGGER; - u8 *resp_addr = (u8 *)bp->hwrm_cmd_resp_addr; u32 bar_offset = BNXT_GRCPF_REG_CHIMP_COMM; u16 dst = BNXT_HWRM_CHNL_CHIMP; @@ -4201,7 +4199,6 @@ static int bnxt_hwrm_do_send_msg(struct bnxt *bp, void *msg, u32 msg_len, bar_offset = BNXT_GRCPF_REG_KONG_COMM; doorbell_offset = BNXT_GRCPF_REG_KONG_COMM_TRIGGER; resp = bp->hwrm_cmd_kong_resp_addr; - resp_addr = (u8 *)bp->hwrm_cmd_kong_resp_addr; } memset(resp, 0, PAGE_SIZE); @@ -4270,7 +4267,6 @@ static int bnxt_hwrm_do_send_msg(struct bnxt *bp, void *msg, u32 msg_len, tmo_count = HWRM_SHORT_TIMEOUT_COUNTER; timeout = timeout - HWRM_SHORT_MIN_TIMEOUT * HWRM_SHORT_TIMEOUT_COUNTER; tmo_count += DIV_ROUND_UP(timeout, HWRM_MIN_TIMEOUT); - resp_len = (__le32 *)(resp_addr + HWRM_RESP_LEN_OFFSET); if (intr_process) { u16 seq_id = bp->hwrm_intr_seq_id; @@ -4298,9 +4294,8 @@ static int bnxt_hwrm_do_send_msg(struct bnxt *bp, void *msg, u32 msg_len, le16_to_cpu(req->req_type)); return -EBUSY; } - len = (le32_to_cpu(*resp_len) & HWRM_RESP_LEN_MASK) >> - HWRM_RESP_LEN_SFT; - valid = resp_addr + len - 1; + len = le16_to_cpu(resp->resp_len); + valid = ((u8 *)resp) + len - 1; } else { int j; @@ -4311,8 +4306,7 @@ static int bnxt_hwrm_do_send_msg(struct bnxt *bp, void *msg, u32 msg_len, */ if (test_bit(BNXT_STATE_FW_FATAL_COND, &bp->state)) return -EBUSY; - len = (le32_to_cpu(*resp_len) & HWRM_RESP_LEN_MASK) >> - HWRM_RESP_LEN_SFT; + len = le16_to_cpu(resp->resp_len); if (len) break; /* on first few passes, just barely sleep */ @@ -4334,7 +4328,7 @@ static int bnxt_hwrm_do_send_msg(struct bnxt *bp, void *msg, u32 msg_len, } /* Last byte of resp contains valid bit */ - valid = resp_addr + len - 1; + valid = ((u8 *)resp) + len - 1; for (j = 0; j < HWRM_VALID_BIT_DELAY_USEC; j++) { /* make sure we read from updated DMA memory */ dma_rmb(); @@ -9310,7 +9304,7 @@ static void __bnxt_close_nic(struct bnxt *bp, bool irq_re_init, bnxt_free_skbs(bp); /* Save ring stats before shutdown */ - if (bp->bnapi) + if (bp->bnapi && irq_re_init) bnxt_get_ring_stats(bp, &bp->net_stats_prev); if (irq_re_init) { bnxt_free_irq(bp); diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h index f6a3250ef1c5..3d39638521d6 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h @@ -656,11 +656,6 @@ struct nqe_cn { #define HWRM_CMD_TIMEOUT (bp->hwrm_cmd_timeout) #define HWRM_RESET_TIMEOUT ((HWRM_CMD_TIMEOUT) * 4) #define HWRM_COREDUMP_TIMEOUT ((HWRM_CMD_TIMEOUT) * 12) -#define HWRM_RESP_ERR_CODE_MASK 0xffff -#define HWRM_RESP_LEN_OFFSET 4 -#define HWRM_RESP_LEN_MASK 0xffff0000 -#define HWRM_RESP_LEN_SFT 16 -#define HWRM_RESP_VALID_MASK 0xff000000 #define BNXT_HWRM_REQ_MAX_SIZE 128 #define BNXT_HWRM_REQS_PER_PAGE (BNXT_PAGE_SIZE / \ BNXT_HWRM_REQ_MAX_SIZE) diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c index 34046a6286e8..360f9a95c1d5 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c @@ -2012,11 +2012,12 @@ int bnxt_flash_package_from_file(struct net_device *dev, const char *filename, bnxt_hwrm_fw_set_time(bp); - if (bnxt_find_nvram_item(dev, BNX_DIR_TYPE_UPDATE, - BNX_DIR_ORDINAL_FIRST, BNX_DIR_EXT_NONE, - &index, &item_len, NULL) != 0) { + rc = bnxt_find_nvram_item(dev, BNX_DIR_TYPE_UPDATE, + BNX_DIR_ORDINAL_FIRST, BNX_DIR_EXT_NONE, + &index, &item_len, NULL); + if (rc) { netdev_err(dev, "PKG update area not created in nvram\n"); - return -ENOBUFS; + return rc; } rc = request_firmware(&fw, filename, &dev->dev); diff --git a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c index 2cd1f8efdfa3..6bfa7575af94 100644 --- a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c +++ b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c @@ -2914,7 +2914,7 @@ static int dpaa_eth_probe(struct platform_device *pdev) } /* Do this here, so we can be verbose early */ - SET_NETDEV_DEV(net_dev, dev); + SET_NETDEV_DEV(net_dev, dev->parent); dev_set_drvdata(dev, net_dev); priv = netdev_priv(net_dev); diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c index 3de549c6c693..197dc5b2c090 100644 --- a/drivers/net/ethernet/ibm/ibmvnic.c +++ b/drivers/net/ethernet/ibm/ibmvnic.c @@ -4678,12 +4678,10 @@ static void ibmvnic_handle_crq(union ibmvnic_crq *crq, dev_err(dev, "Error %ld in VERSION_EXCHG_RSP\n", rc); break; } - dev_info(dev, "Partner protocol version is %d\n", - crq->version_exchange_rsp.version); - if (be16_to_cpu(crq->version_exchange_rsp.version) < - ibmvnic_version) - ibmvnic_version = + ibmvnic_version = be16_to_cpu(crq->version_exchange_rsp.version); + dev_info(dev, "Partner protocol version is %d\n", + ibmvnic_version); send_cap_queries(adapter); break; case QUERY_CAPABILITY_RSP: diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Kconfig b/drivers/net/ethernet/mellanox/mlx5/core/Kconfig index 7d69a3061f17..fd375cbe586e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/Kconfig +++ b/drivers/net/ethernet/mellanox/mlx5/core/Kconfig @@ -80,7 +80,7 @@ config MLX5_ESWITCH config MLX5_TC_CT bool "MLX5 TC connection tracking offload support" - depends on MLX5_CORE_EN && NET_SWITCHDEV && NF_FLOW_TABLE && NET_ACT_CT && NET_TC_SKB_EXT + depends on MLX5_ESWITCH && NF_FLOW_TABLE && NET_ACT_CT && NET_TC_SKB_EXT default y help Say Y here if you want to support offloading connection tracking rules diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h index 59745402747b..0a5aada0f50f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h @@ -1068,10 +1068,12 @@ void mlx5e_deactivate_priv_channels(struct mlx5e_priv *priv); void mlx5e_build_default_indir_rqt(u32 *indirection_rqt, int len, int num_channels); -void mlx5e_set_tx_cq_mode_params(struct mlx5e_params *params, - u8 cq_period_mode); -void mlx5e_set_rx_cq_mode_params(struct mlx5e_params *params, - u8 cq_period_mode); + +void mlx5e_reset_tx_moderation(struct mlx5e_params *params, u8 cq_period_mode); +void mlx5e_reset_rx_moderation(struct mlx5e_params *params, u8 cq_period_mode); +void mlx5e_set_tx_cq_mode_params(struct mlx5e_params *params, u8 cq_period_mode); +void mlx5e_set_rx_cq_mode_params(struct mlx5e_params *params, u8 cq_period_mode); + void mlx5e_set_rq_type(struct mlx5_core_dev *mdev, struct mlx5e_params *params); void mlx5e_init_rq_type_params(struct mlx5_core_dev *mdev, struct mlx5e_params *params); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/port.c b/drivers/net/ethernet/mellanox/mlx5/core/en/port.c index 2c4a670c8ffd..2a8950b3056f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/port.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/port.c @@ -369,17 +369,19 @@ enum mlx5e_fec_supported_link_mode { *_policy = MLX5_GET(pplm_reg, _buf, fec_override_admin_##link); \ } while (0) -#define MLX5E_FEC_OVERRIDE_ADMIN_50G_POLICY(buf, policy, write, link) \ - do { \ - u16 *__policy = &(policy); \ - bool _write = (write); \ - \ - if (_write && *__policy) \ - *__policy = find_first_bit((u_long *)__policy, \ - sizeof(u16) * BITS_PER_BYTE);\ - MLX5E_FEC_OVERRIDE_ADMIN_POLICY(buf, *__policy, _write, link); \ - if (!_write && *__policy) \ - *__policy = 1 << *__policy; \ +#define MLX5E_FEC_OVERRIDE_ADMIN_50G_POLICY(buf, policy, write, link) \ + do { \ + unsigned long policy_long; \ + u16 *__policy = &(policy); \ + bool _write = (write); \ + \ + policy_long = *__policy; \ + if (_write && *__policy) \ + *__policy = find_first_bit(&policy_long, \ + sizeof(policy_long) * BITS_PER_BYTE);\ + MLX5E_FEC_OVERRIDE_ADMIN_POLICY(buf, *__policy, _write, link); \ + if (!_write && *__policy) \ + *__policy = 1 << *__policy; \ } while (0) /* get/set FEC admin field for a given speed */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c index 6d703ddee4e2..bc290ae80a53 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c @@ -527,8 +527,8 @@ int mlx5e_ethtool_set_coalesce(struct mlx5e_priv *priv, struct dim_cq_moder *rx_moder, *tx_moder; struct mlx5_core_dev *mdev = priv->mdev; struct mlx5e_channels new_channels = {}; + bool reset_rx, reset_tx; int err = 0; - bool reset; if (!MLX5_CAP_GEN(mdev, cq_moderation)) return -EOPNOTSUPP; @@ -566,15 +566,28 @@ int mlx5e_ethtool_set_coalesce(struct mlx5e_priv *priv, } /* we are opened */ - reset = (!!coal->use_adaptive_rx_coalesce != priv->channels.params.rx_dim_enabled) || - (!!coal->use_adaptive_tx_coalesce != priv->channels.params.tx_dim_enabled); + reset_rx = !!coal->use_adaptive_rx_coalesce != priv->channels.params.rx_dim_enabled; + reset_tx = !!coal->use_adaptive_tx_coalesce != priv->channels.params.tx_dim_enabled; - if (!reset) { + if (!reset_rx && !reset_tx) { mlx5e_set_priv_channels_coalesce(priv, coal); priv->channels.params = new_channels.params; goto out; } + if (reset_rx) { + u8 mode = MLX5E_GET_PFLAG(&new_channels.params, + MLX5E_PFLAG_RX_CQE_BASED_MODER); + + mlx5e_reset_rx_moderation(&new_channels.params, mode); + } + if (reset_tx) { + u8 mode = MLX5E_GET_PFLAG(&new_channels.params, + MLX5E_PFLAG_TX_CQE_BASED_MODER); + + mlx5e_reset_tx_moderation(&new_channels.params, mode); + } + err = mlx5e_safe_switch_channels(priv, &new_channels, NULL, NULL); out: @@ -665,11 +678,12 @@ static const u32 pplm_fec_2_ethtool_linkmodes[] = { static int get_fec_supported_advertised(struct mlx5_core_dev *dev, struct ethtool_link_ksettings *link_ksettings) { - u_long active_fec = 0; + unsigned long active_fec_long; + u32 active_fec; u32 bitn; int err; - err = mlx5e_get_fec_mode(dev, (u32 *)&active_fec, NULL); + err = mlx5e_get_fec_mode(dev, &active_fec, NULL); if (err) return (err == -EOPNOTSUPP) ? 0 : err; @@ -682,10 +696,11 @@ static int get_fec_supported_advertised(struct mlx5_core_dev *dev, MLX5E_ADVERTISE_SUPPORTED_FEC(MLX5E_FEC_LLRS_272_257_1, ETHTOOL_LINK_MODE_FEC_LLRS_BIT); + active_fec_long = active_fec; /* active fec is a bit set, find out which bit is set and * advertise the corresponding ethtool bit */ - bitn = find_first_bit(&active_fec, sizeof(u32) * BITS_PER_BYTE); + bitn = find_first_bit(&active_fec_long, sizeof(active_fec_long) * BITS_PER_BYTE); if (bitn < ARRAY_SIZE(pplm_fec_2_ethtool_linkmodes)) __set_bit(pplm_fec_2_ethtool_linkmodes[bitn], link_ksettings->link_modes.advertising); @@ -1517,8 +1532,8 @@ static int mlx5e_get_fecparam(struct net_device *netdev, { struct mlx5e_priv *priv = netdev_priv(netdev); struct mlx5_core_dev *mdev = priv->mdev; - u16 fec_configured = 0; - u32 fec_active = 0; + u16 fec_configured; + u32 fec_active; int err; err = mlx5e_get_fec_mode(mdev, &fec_active, &fec_configured); @@ -1526,14 +1541,14 @@ static int mlx5e_get_fecparam(struct net_device *netdev, if (err) return err; - fecparam->active_fec = pplm2ethtool_fec((u_long)fec_active, - sizeof(u32) * BITS_PER_BYTE); + fecparam->active_fec = pplm2ethtool_fec((unsigned long)fec_active, + sizeof(unsigned long) * BITS_PER_BYTE); if (!fecparam->active_fec) return -EOPNOTSUPP; - fecparam->fec = pplm2ethtool_fec((u_long)fec_configured, - sizeof(u16) * BITS_PER_BYTE); + fecparam->fec = pplm2ethtool_fec((unsigned long)fec_configured, + sizeof(unsigned long) * BITS_PER_BYTE); return 0; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index c6b83042d431..bd8d0e096085 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -4716,7 +4716,7 @@ static u8 mlx5_to_net_dim_cq_period_mode(u8 cq_period_mode) DIM_CQ_PERIOD_MODE_START_FROM_EQE; } -void mlx5e_set_tx_cq_mode_params(struct mlx5e_params *params, u8 cq_period_mode) +void mlx5e_reset_tx_moderation(struct mlx5e_params *params, u8 cq_period_mode) { if (params->tx_dim_enabled) { u8 dim_period_mode = mlx5_to_net_dim_cq_period_mode(cq_period_mode); @@ -4725,13 +4725,9 @@ void mlx5e_set_tx_cq_mode_params(struct mlx5e_params *params, u8 cq_period_mode) } else { params->tx_cq_moderation = mlx5e_get_def_tx_moderation(cq_period_mode); } - - MLX5E_SET_PFLAG(params, MLX5E_PFLAG_TX_CQE_BASED_MODER, - params->tx_cq_moderation.cq_period_mode == - MLX5_CQ_PERIOD_MODE_START_FROM_CQE); } -void mlx5e_set_rx_cq_mode_params(struct mlx5e_params *params, u8 cq_period_mode) +void mlx5e_reset_rx_moderation(struct mlx5e_params *params, u8 cq_period_mode) { if (params->rx_dim_enabled) { u8 dim_period_mode = mlx5_to_net_dim_cq_period_mode(cq_period_mode); @@ -4740,7 +4736,19 @@ void mlx5e_set_rx_cq_mode_params(struct mlx5e_params *params, u8 cq_period_mode) } else { params->rx_cq_moderation = mlx5e_get_def_rx_moderation(cq_period_mode); } +} + +void mlx5e_set_tx_cq_mode_params(struct mlx5e_params *params, u8 cq_period_mode) +{ + mlx5e_reset_tx_moderation(params, cq_period_mode); + MLX5E_SET_PFLAG(params, MLX5E_PFLAG_TX_CQE_BASED_MODER, + params->tx_cq_moderation.cq_period_mode == + MLX5_CQ_PERIOD_MODE_START_FROM_CQE); +} +void mlx5e_set_rx_cq_mode_params(struct mlx5e_params *params, u8 cq_period_mode) +{ + mlx5e_reset_rx_moderation(params, cq_period_mode); MLX5E_SET_PFLAG(params, MLX5E_PFLAG_RX_CQE_BASED_MODER, params->rx_cq_moderation.cq_period_mode == MLX5_CQ_PERIOD_MODE_START_FROM_CQE); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index 5bcf95fcdd59..10f705761666 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -2068,7 +2068,7 @@ static int mlx5e_flower_parse_meta(struct net_device *filter_dev, flow_rule_match_meta(rule, &match); if (match.mask->ingress_ifindex != 0xFFFFFFFF) { NL_SET_ERR_MSG_MOD(extack, "Unsupported ingress ifindex mask"); - return -EINVAL; + return -EOPNOTSUPP; } ingress_dev = __dev_get_by_index(dev_net(filter_dev), @@ -2076,13 +2076,13 @@ static int mlx5e_flower_parse_meta(struct net_device *filter_dev, if (!ingress_dev) { NL_SET_ERR_MSG_MOD(extack, "Can't find the ingress port to match on"); - return -EINVAL; + return -ENOENT; } if (ingress_dev != filter_dev) { NL_SET_ERR_MSG_MOD(extack, "Can't match on the ingress filter port"); - return -EINVAL; + return -EOPNOTSUPP; } return 0; @@ -3849,10 +3849,6 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv, if (!mlx5e_is_valid_eswitch_fwd_dev(priv, out_dev)) { NL_SET_ERR_MSG_MOD(extack, "devices are not on same switch HW, can't offload forwarding"); - netdev_warn(priv->netdev, - "devices %s %s not on same switch HW, can't offload forwarding\n", - priv->netdev->name, - out_dev->name); return -EOPNOTSUPP; } @@ -4614,7 +4610,7 @@ void mlx5e_tc_stats_matchall(struct mlx5e_priv *priv, dpkts = cur_stats.rx_packets - rpriv->prev_vf_vport_stats.rx_packets; dbytes = cur_stats.rx_bytes - rpriv->prev_vf_vport_stats.rx_bytes; rpriv->prev_vf_vport_stats = cur_stats; - flow_stats_update(&ma->stats, dpkts, dbytes, jiffies, + flow_stats_update(&ma->stats, dbytes, dpkts, jiffies, FLOW_ACTION_HW_STATS_DELAYED); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index c1618b818f3a..17f818a54090 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -1549,6 +1549,22 @@ static void shutdown(struct pci_dev *pdev) mlx5_pci_disable_device(dev); } +static int mlx5_suspend(struct pci_dev *pdev, pm_message_t state) +{ + struct mlx5_core_dev *dev = pci_get_drvdata(pdev); + + mlx5_unload_one(dev, false); + + return 0; +} + +static int mlx5_resume(struct pci_dev *pdev) +{ + struct mlx5_core_dev *dev = pci_get_drvdata(pdev); + + return mlx5_load_one(dev, false); +} + static const struct pci_device_id mlx5_core_pci_table[] = { { PCI_VDEVICE(MELLANOX, PCI_DEVICE_ID_MELLANOX_CONNECTIB) }, { PCI_VDEVICE(MELLANOX, 0x1012), MLX5_PCI_DEV_IS_VF}, /* Connect-IB VF */ @@ -1592,6 +1608,8 @@ static struct pci_driver mlx5_core_driver = { .id_table = mlx5_core_pci_table, .probe = init_one, .remove = remove_one, + .suspend = mlx5_suspend, + .resume = mlx5_resume, .shutdown = shutdown, .err_handler = &mlx5_err_handler, .sriov_configure = mlx5_core_sriov_configure, diff --git a/drivers/net/ethernet/netronome/nfp/flower/offload.c b/drivers/net/ethernet/netronome/nfp/flower/offload.c index c694dbc239d0..6b60771ccb19 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/offload.c +++ b/drivers/net/ethernet/netronome/nfp/flower/offload.c @@ -1440,7 +1440,8 @@ __nfp_flower_update_merge_stats(struct nfp_app *app, ctx_id = be32_to_cpu(sub_flow->meta.host_ctx_id); priv->stats[ctx_id].pkts += pkts; priv->stats[ctx_id].bytes += bytes; - max_t(u64, priv->stats[ctx_id].used, used); + priv->stats[ctx_id].used = max_t(u64, used, + priv->stats[ctx_id].used); } } diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c index 2a533280b124..29b9c728a65e 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c @@ -3651,7 +3651,7 @@ int qlcnic_83xx_interrupt_test(struct net_device *netdev) ahw->diag_cnt = 0; ret = qlcnic_alloc_mbx_args(&cmd, adapter, QLCNIC_CMD_INTRPT_TEST); if (ret) - goto fail_diag_irq; + goto fail_mbx_args; if (adapter->flags & QLCNIC_MSIX_ENABLED) intrpt_id = ahw->intr_tbl[0].id; @@ -3681,6 +3681,8 @@ int qlcnic_83xx_interrupt_test(struct net_device *netdev) done: qlcnic_free_mbx_args(&cmd); + +fail_mbx_args: qlcnic_83xx_diag_free_res(netdev, drv_sds_rings); fail_diag_irq: diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index 1f319c9cee46..7e9cbfd23530 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -630,7 +630,8 @@ static int stmmac_hwtstamp_set(struct net_device *dev, struct ifreq *ifr) config.rx_filter = HWTSTAMP_FILTER_PTP_V2_EVENT; ptp_v2 = PTP_TCR_TSVER2ENA; snap_type_sel = PTP_TCR_SNAPTYPSEL_1; - ts_event_en = PTP_TCR_TSEVNTENA; + if (priv->synopsys_id != DWMAC_CORE_5_10) + ts_event_en = PTP_TCR_TSEVNTENA; ptp_over_ipv4_udp = PTP_TCR_TSIPV4ENA; ptp_over_ipv6_udp = PTP_TCR_TSIPV6ENA; ptp_over_ethernet = PTP_TCR_TSIPENA; diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c index 4bb8552a00d3..4a2c7355be63 100644 --- a/drivers/net/usb/qmi_wwan.c +++ b/drivers/net/usb/qmi_wwan.c @@ -1324,6 +1324,7 @@ static const struct usb_device_id products[] = { {QMI_FIXED_INTF(0x1bbb, 0x0203, 2)}, /* Alcatel L800MA */ {QMI_FIXED_INTF(0x2357, 0x0201, 4)}, /* TP-LINK HSUPA Modem MA180 */ {QMI_FIXED_INTF(0x2357, 0x9000, 4)}, /* TP-LINK MA260 */ + {QMI_QUIRK_SET_DTR(0x1bc7, 0x1031, 3)}, /* Telit LE910C1-EUX */ {QMI_QUIRK_SET_DTR(0x1bc7, 0x1040, 2)}, /* Telit LE922A */ {QMI_QUIRK_SET_DTR(0x1bc7, 0x1050, 2)}, /* Telit FN980 */ {QMI_FIXED_INTF(0x1bc7, 0x1100, 3)}, /* Telit ME910 */ diff --git a/drivers/nfc/st21nfca/dep.c b/drivers/nfc/st21nfca/dep.c index a1d69f9b2d4a..0b9ca6d20ffa 100644 --- a/drivers/nfc/st21nfca/dep.c +++ b/drivers/nfc/st21nfca/dep.c @@ -173,8 +173,10 @@ static int st21nfca_tm_send_atr_res(struct nfc_hci_dev *hdev, memcpy(atr_res->gbi, atr_req->gbi, gb_len); r = nfc_set_remote_general_bytes(hdev->ndev, atr_res->gbi, gb_len); - if (r < 0) + if (r < 0) { + kfree_skb(skb); return r; + } } info->dep_info.curr_nfc_dep_pni = 0; diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index 3726dc780d15..cc46e250fcac 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -1382,16 +1382,19 @@ static void nvme_disable_admin_queue(struct nvme_dev *dev, bool shutdown) /* * Called only on a device that has been disabled and after all other threads - * that can check this device's completion queues have synced. This is the - * last chance for the driver to see a natural completion before - * nvme_cancel_request() terminates all incomplete requests. + * that can check this device's completion queues have synced, except + * nvme_poll(). This is the last chance for the driver to see a natural + * completion before nvme_cancel_request() terminates all incomplete requests. */ static void nvme_reap_pending_cqes(struct nvme_dev *dev) { int i; - for (i = dev->ctrl.queue_count - 1; i > 0; i--) + for (i = dev->ctrl.queue_count - 1; i > 0; i--) { + spin_lock(&dev->queues[i].cq_poll_lock); nvme_process_cq(&dev->queues[i]); + spin_unlock(&dev->queues[i].cq_poll_lock); + } } static int nvme_cmb_qdepth(struct nvme_dev *dev, int nr_io_queues, diff --git a/drivers/pci/ats.c b/drivers/pci/ats.c index 390e92f2d8d1..b761c1f72f67 100644 --- a/drivers/pci/ats.c +++ b/drivers/pci/ats.c @@ -31,6 +31,22 @@ void pci_ats_init(struct pci_dev *dev) } /** + * pci_ats_supported - check if the device can use ATS + * @dev: the PCI device + * + * Returns true if the device supports ATS and is allowed to use it, false + * otherwise. + */ +bool pci_ats_supported(struct pci_dev *dev) +{ + if (!dev->ats_cap) + return false; + + return (dev->untrusted == 0); +} +EXPORT_SYMBOL_GPL(pci_ats_supported); + +/** * pci_enable_ats - enable the ATS capability * @dev: the PCI device * @ps: the IOMMU page shift @@ -42,7 +58,7 @@ int pci_enable_ats(struct pci_dev *dev, int ps) u16 ctrl; struct pci_dev *pdev; - if (!dev->ats_cap) + if (!pci_ats_supported(dev)) return -EINVAL; if (WARN_ON(dev->ats_enabled)) diff --git a/drivers/soc/mediatek/mtk-cmdq-helper.c b/drivers/soc/mediatek/mtk-cmdq-helper.c index db37144ae98c..87ee9f767b7a 100644 --- a/drivers/soc/mediatek/mtk-cmdq-helper.c +++ b/drivers/soc/mediatek/mtk-cmdq-helper.c @@ -351,7 +351,9 @@ int cmdq_pkt_flush_async(struct cmdq_pkt *pkt, cmdq_async_flush_cb cb, spin_unlock_irqrestore(&client->lock, flags); } - mbox_send_message(client->chan, pkt); + err = mbox_send_message(client->chan, pkt); + if (err < 0) + return err; /* We can send next packet immediately, so just call txdone. */ mbox_client_txdone(client->chan, 0); diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c index 13f25e241ac4..25d489bc9453 100644 --- a/fs/binfmt_elf.c +++ b/fs/binfmt_elf.c @@ -1733,7 +1733,7 @@ static int fill_thread_core_info(struct elf_thread_core_info *t, (!regset->active || regset->active(t->task, regset) > 0)) { int ret; size_t size = regset_size(t->task, regset); - void *data = kmalloc(size, GFP_KERNEL); + void *data = kzalloc(size, GFP_KERNEL); if (unlikely(!data)) return 0; ret = regset->get(t->task, regset, diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c index 5f3aa4d607de..f1acde6fb9a6 100644 --- a/fs/ceph/caps.c +++ b/fs/ceph/caps.c @@ -3991,7 +3991,7 @@ void ceph_handle_caps(struct ceph_mds_session *session, __ceph_queue_cap_release(session, cap); spin_unlock(&session->s_cap_lock); } - goto done; + goto flush_cap_releases; } /* these will work even if we don't have a cap yet */ diff --git a/fs/gfs2/lops.c b/fs/gfs2/lops.c index 48b54ec1c793..cb2a11b458c6 100644 --- a/fs/gfs2/lops.c +++ b/fs/gfs2/lops.c @@ -509,12 +509,12 @@ int gfs2_find_jhead(struct gfs2_jdesc *jd, struct gfs2_log_header_host *head, unsigned int bsize = sdp->sd_sb.sb_bsize, off; unsigned int bsize_shift = sdp->sd_sb.sb_bsize_shift; unsigned int shift = PAGE_SHIFT - bsize_shift; - unsigned int max_bio_size = 2 * 1024 * 1024; + unsigned int max_blocks = 2 * 1024 * 1024 >> bsize_shift; struct gfs2_journal_extent *je; int sz, ret = 0; struct bio *bio = NULL; struct page *page = NULL; - bool bio_chained = false, done = false; + bool done = false; errseq_t since; memset(head, 0, sizeof(*head)); @@ -537,10 +537,7 @@ int gfs2_find_jhead(struct gfs2_jdesc *jd, struct gfs2_log_header_host *head, off = 0; } - if (!bio || (bio_chained && !off) || - bio->bi_iter.bi_size >= max_bio_size) { - /* start new bio */ - } else { + if (bio && (off || block < blocks_submitted + max_blocks)) { sector_t sector = dblock << sdp->sd_fsb2bb_shift; if (bio_end_sector(bio) == sector) { @@ -553,19 +550,17 @@ int gfs2_find_jhead(struct gfs2_jdesc *jd, struct gfs2_log_header_host *head, (PAGE_SIZE - off) >> bsize_shift; bio = gfs2_chain_bio(bio, blocks); - bio_chained = true; goto add_block_to_new_bio; } } if (bio) { - blocks_submitted = block + 1; + blocks_submitted = block; submit_bio(bio); } bio = gfs2_log_alloc_bio(sdp, dblock, gfs2_end_log_read); bio->bi_opf = REQ_OP_READ; - bio_chained = false; add_block_to_new_bio: sz = bio_add_page(bio, page, bsize, off); BUG_ON(sz != bsize); @@ -573,7 +568,7 @@ block_added: off += bsize; if (off == PAGE_SIZE) page = NULL; - if (blocks_submitted < 2 * max_bio_size >> bsize_shift) { + if (blocks_submitted <= blocks_read + max_blocks) { /* Keep at least one bio in flight */ continue; } diff --git a/fs/notify/fanotify/fanotify.c b/fs/notify/fanotify/fanotify.c index 5435a40f82be..c18459cea6f4 100644 --- a/fs/notify/fanotify/fanotify.c +++ b/fs/notify/fanotify/fanotify.c @@ -520,7 +520,7 @@ static int fanotify_handle_event(struct fsnotify_group *group, BUILD_BUG_ON(FAN_OPEN_EXEC != FS_OPEN_EXEC); BUILD_BUG_ON(FAN_OPEN_EXEC_PERM != FS_OPEN_EXEC_PERM); - BUILD_BUG_ON(HWEIGHT32(ALL_FANOTIFY_EVENT_BITS) != 20); + BUILD_BUG_ON(HWEIGHT32(ALL_FANOTIFY_EVENT_BITS) != 19); mask = fanotify_group_event_mask(group, iter_info, mask, data, data_type); diff --git a/fs/xattr.c b/fs/xattr.c index e13265e65871..91608d9bfc6a 100644 --- a/fs/xattr.c +++ b/fs/xattr.c @@ -876,6 +876,9 @@ int simple_xattr_set(struct simple_xattrs *xattrs, const char *name, struct simple_xattr *new_xattr = NULL; int err = 0; + if (removed_size) + *removed_size = -1; + /* value == NULL means remove */ if (value) { new_xattr = simple_xattr_alloc(value, size); @@ -914,9 +917,6 @@ int simple_xattr_set(struct simple_xattrs *xattrs, const char *name, list_add(&new_xattr->list, &xattrs->head); xattr = NULL; } - - if (removed_size) - *removed_size = -1; out: spin_unlock(&xattrs->lock); if (xattr) { diff --git a/include/asm-generic/topology.h b/include/asm-generic/topology.h index 238873739550..5aa8705df87e 100644 --- a/include/asm-generic/topology.h +++ b/include/asm-generic/topology.h @@ -48,7 +48,7 @@ #ifdef CONFIG_NEED_MULTIPLE_NODES #define cpumask_of_node(node) ((node) == 0 ? cpu_online_mask : cpu_none_mask) #else - #define cpumask_of_node(node) ((void)node, cpu_online_mask) + #define cpumask_of_node(node) ((void)(node), cpu_online_mask) #endif #endif #ifndef pcibus_to_node diff --git a/include/linux/device_cgroup.h b/include/linux/device_cgroup.h index fa35b52e0002..9a72214496e5 100644 --- a/include/linux/device_cgroup.h +++ b/include/linux/device_cgroup.h @@ -1,6 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ #include <linux/fs.h> -#include <linux/bpf-cgroup.h> #define DEVCG_ACC_MKNOD 1 #define DEVCG_ACC_READ 2 @@ -11,16 +10,10 @@ #define DEVCG_DEV_CHAR 2 #define DEVCG_DEV_ALL 4 /* this represents all devices */ -#ifdef CONFIG_CGROUP_DEVICE -int devcgroup_check_permission(short type, u32 major, u32 minor, - short access); -#else -static inline int devcgroup_check_permission(short type, u32 major, u32 minor, - short access) -{ return 0; } -#endif #if defined(CONFIG_CGROUP_DEVICE) || defined(CONFIG_CGROUP_BPF) +int devcgroup_check_permission(short type, u32 major, u32 minor, + short access); static inline int devcgroup_inode_permission(struct inode *inode, int mask) { short type, access = 0; @@ -61,6 +54,9 @@ static inline int devcgroup_inode_mknod(int mode, dev_t dev) } #else +static inline int devcgroup_check_permission(short type, u32 major, u32 minor, + short access) +{ return 0; } static inline int devcgroup_inode_permission(struct inode *inode, int mask) { return 0; } static inline int devcgroup_inode_mknod(int mode, dev_t dev) diff --git a/include/linux/fanotify.h b/include/linux/fanotify.h index 3049a6c06d9e..b79fa9bb7359 100644 --- a/include/linux/fanotify.h +++ b/include/linux/fanotify.h @@ -47,8 +47,7 @@ * Directory entry modification events - reported only to directory * where entry is modified and not to a watching parent. */ -#define FANOTIFY_DIRENT_EVENTS (FAN_MOVE | FAN_CREATE | FAN_DELETE | \ - FAN_DIR_MODIFY) +#define FANOTIFY_DIRENT_EVENTS (FAN_MOVE | FAN_CREATE | FAN_DELETE) /* Events that can only be reported with data type FSNOTIFY_EVENT_INODE */ #define FANOTIFY_INODE_EVENTS (FANOTIFY_DIRENT_EVENTS | \ diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index 16268ef1cbcc..5d3e48d02033 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -2047,7 +2047,7 @@ ieee80211_he_ppe_size(u8 ppe_thres_hdr, const u8 *phy_cap_info) } /* HE Operation defines */ -#define IEEE80211_HE_OPERATION_DFLT_PE_DURATION_MASK 0x00000003 +#define IEEE80211_HE_OPERATION_DFLT_PE_DURATION_MASK 0x00000007 #define IEEE80211_HE_OPERATION_TWT_REQUIRED 0x00000008 #define IEEE80211_HE_OPERATION_RTS_THRESHOLD_MASK 0x00003ff0 #define IEEE80211_HE_OPERATION_RTS_THRESHOLD_OFFSET 4 diff --git a/include/linux/input/lm8333.h b/include/linux/input/lm8333.h index 79f918c6e8c5..906da5fc06e0 100644 --- a/include/linux/input/lm8333.h +++ b/include/linux/input/lm8333.h @@ -1,6 +1,6 @@ /* * public include for LM8333 keypad driver - same license as driver - * Copyright (C) 2012 Wolfram Sang, Pengutronix <w.sang@pengutronix.de> + * Copyright (C) 2012 Wolfram Sang, Pengutronix <kernel@pengutronix.de> */ #ifndef _LM8333_H diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h index 980234ae0312..4100bd224f5c 100644 --- a/include/linux/intel-iommu.h +++ b/include/linux/intel-iommu.h @@ -19,6 +19,7 @@ #include <linux/iommu.h> #include <linux/io-64-nonatomic-lo-hi.h> #include <linux/dmar.h> +#include <linux/ioasid.h> #include <asm/cacheflush.h> #include <asm/iommu.h> @@ -42,6 +43,9 @@ #define DMA_FL_PTE_PRESENT BIT_ULL(0) #define DMA_FL_PTE_XD BIT_ULL(63) +#define ADDR_WIDTH_5LEVEL (57) +#define ADDR_WIDTH_4LEVEL (48) + #define CONTEXT_TT_MULTI_LEVEL 0 #define CONTEXT_TT_DEV_IOTLB 1 #define CONTEXT_TT_PASS_THROUGH 2 @@ -166,6 +170,7 @@ #define ecap_smpwc(e) (((e) >> 48) & 0x1) #define ecap_flts(e) (((e) >> 47) & 0x1) #define ecap_slts(e) (((e) >> 46) & 0x1) +#define ecap_vcs(e) (((e) >> 44) & 0x1) #define ecap_smts(e) (((e) >> 43) & 0x1) #define ecap_dit(e) ((e >> 41) & 0x1) #define ecap_pasid(e) ((e >> 40) & 0x1) @@ -191,6 +196,9 @@ #define ecap_max_handle_mask(e) ((e >> 20) & 0xf) #define ecap_sc_support(e) ((e >> 7) & 0x1) /* Snooping Control */ +/* Virtual command interface capability */ +#define vccap_pasid(v) (((v) & DMA_VCS_PAS)) /* PASID allocation */ + /* IOTLB_REG */ #define DMA_TLB_FLUSH_GRANU_OFFSET 60 #define DMA_TLB_GLOBAL_FLUSH (((u64)1) << 60) @@ -284,6 +292,9 @@ /* PRS_REG */ #define DMA_PRS_PPR ((u32)1) +#define DMA_PRS_PRO ((u32)2) + +#define DMA_VCS_PAS ((u64)1) #define IOMMU_WAIT_OP(iommu, offset, op, cond, sts) \ do { \ @@ -324,6 +335,8 @@ enum { #define QI_IWD_STATUS_DATA(d) (((u64)d) << 32) #define QI_IWD_STATUS_WRITE (((u64)1) << 5) +#define QI_IWD_FENCE (((u64)1) << 6) +#define QI_IWD_PRQ_DRAIN (((u64)1) << 7) #define QI_IOTLB_DID(did) (((u64)did) << 16) #define QI_IOTLB_DR(dr) (((u64)dr) << 7) @@ -331,7 +344,7 @@ enum { #define QI_IOTLB_GRAN(gran) (((u64)gran) >> (DMA_TLB_FLUSH_GRANU_OFFSET-4)) #define QI_IOTLB_ADDR(addr) (((u64)addr) & VTD_PAGE_MASK) #define QI_IOTLB_IH(ih) (((u64)ih) << 6) -#define QI_IOTLB_AM(am) (((u8)am)) +#define QI_IOTLB_AM(am) (((u8)am) & 0x3f) #define QI_CC_FM(fm) (((u64)fm) << 48) #define QI_CC_SID(sid) (((u64)sid) << 32) @@ -350,16 +363,21 @@ enum { #define QI_PC_DID(did) (((u64)did) << 16) #define QI_PC_GRAN(gran) (((u64)gran) << 4) -#define QI_PC_ALL_PASIDS (QI_PC_TYPE | QI_PC_GRAN(0)) -#define QI_PC_PASID_SEL (QI_PC_TYPE | QI_PC_GRAN(1)) +/* PASID cache invalidation granu */ +#define QI_PC_ALL_PASIDS 0 +#define QI_PC_PASID_SEL 1 #define QI_EIOTLB_ADDR(addr) ((u64)(addr) & VTD_PAGE_MASK) #define QI_EIOTLB_IH(ih) (((u64)ih) << 6) -#define QI_EIOTLB_AM(am) (((u64)am)) +#define QI_EIOTLB_AM(am) (((u64)am) & 0x3f) #define QI_EIOTLB_PASID(pasid) (((u64)pasid) << 32) #define QI_EIOTLB_DID(did) (((u64)did) << 16) #define QI_EIOTLB_GRAN(gran) (((u64)gran) << 4) +/* QI Dev-IOTLB inv granu */ +#define QI_DEV_IOTLB_GRAN_ALL 1 +#define QI_DEV_IOTLB_GRAN_PASID_SEL 0 + #define QI_DEV_EIOTLB_ADDR(a) ((u64)(a) & VTD_PAGE_MASK) #define QI_DEV_EIOTLB_SIZE (((u64)1) << 11) #define QI_DEV_EIOTLB_GLOB(g) ((u64)g) @@ -480,6 +498,23 @@ struct context_entry { u64 hi; }; +/* si_domain contains mulitple devices */ +#define DOMAIN_FLAG_STATIC_IDENTITY BIT(0) + +/* + * When VT-d works in the scalable mode, it allows DMA translation to + * happen through either first level or second level page table. This + * bit marks that the DMA translation for the domain goes through the + * first level page table, otherwise, it goes through the second level. + */ +#define DOMAIN_FLAG_USE_FIRST_LEVEL BIT(1) + +/* + * Domain represents a virtual machine which demands iommu nested + * translation mode support. + */ +#define DOMAIN_FLAG_NESTING_MODE BIT(2) + struct dmar_domain { int nid; /* node id */ @@ -529,6 +564,7 @@ struct intel_iommu { u64 reg_size; /* size of hw register set */ u64 cap; u64 ecap; + u64 vccap; u32 gcmd; /* Holds TE, EAFL. Don't need SRTP, SFL, WBF */ raw_spinlock_t register_lock; /* protect register handling */ int seq_id; /* sequence id of the iommu */ @@ -549,6 +585,8 @@ struct intel_iommu { #ifdef CONFIG_INTEL_IOMMU_SVM struct page_req_dsc *prq; unsigned char prq_name[16]; /* Name for PRQ interrupt */ + struct completion prq_complete; + struct ioasid_allocator_ops pasid_allocator; /* Custom allocator for PASIDs */ #endif struct q_inval *qi; /* Queued invalidation info */ u32 *iommu_state; /* Store iommu states between suspend and resume.*/ @@ -571,6 +609,7 @@ struct device_domain_info { struct list_head auxiliary_domains; /* auxiliary domains * attached to this device */ + u32 segment; /* PCI segment number */ u8 bus; /* PCI bus number */ u8 devfn; /* PCI devfn number */ u16 pfsid; /* SRIOV physical function source ID */ @@ -595,6 +634,12 @@ static inline void __iommu_flush_cache( clflush_cache_range(addr, size); } +/* Convert generic struct iommu_domain to private struct dmar_domain */ +static inline struct dmar_domain *to_dmar_domain(struct iommu_domain *dom) +{ + return container_of(dom, struct dmar_domain, domain); +} + /* * 0: readable * 1: writable @@ -653,9 +698,23 @@ extern void qi_flush_iotlb(struct intel_iommu *iommu, u16 did, u64 addr, unsigned int size_order, u64 type); extern void qi_flush_dev_iotlb(struct intel_iommu *iommu, u16 sid, u16 pfsid, u16 qdep, u64 addr, unsigned mask); + void qi_flush_piotlb(struct intel_iommu *iommu, u16 did, u32 pasid, u64 addr, unsigned long npages, bool ih); -extern int qi_submit_sync(struct qi_desc *desc, struct intel_iommu *iommu); + +void qi_flush_dev_iotlb_pasid(struct intel_iommu *iommu, u16 sid, u16 pfsid, + u32 pasid, u16 qdep, u64 addr, + unsigned int size_order, u64 granu); +void qi_flush_pasid_cache(struct intel_iommu *iommu, u16 did, u64 granu, + int pasid); + +int qi_submit_sync(struct intel_iommu *iommu, struct qi_desc *desc, + unsigned int count, unsigned long options); +/* + * Options used in qi_submit_sync: + * QI_OPT_WAIT_DRAIN - Wait for PRQ drain completion, spec 6.5.2.8. + */ +#define QI_OPT_WAIT_DRAIN BIT(0) extern int dmar_ir_support(void); @@ -667,12 +726,19 @@ int for_each_device_domain(int (*fn)(struct device_domain_info *info, void iommu_flush_write_buffer(struct intel_iommu *iommu); int intel_iommu_enable_pasid(struct intel_iommu *iommu, struct device *dev); struct dmar_domain *find_domain(struct device *dev); +struct device_domain_info *get_domain_info(struct device *dev); #ifdef CONFIG_INTEL_IOMMU_SVM extern void intel_svm_check(struct intel_iommu *iommu); extern int intel_svm_enable_prq(struct intel_iommu *iommu); extern int intel_svm_finish_prq(struct intel_iommu *iommu); - +int intel_svm_bind_gpasid(struct iommu_domain *domain, struct device *dev, + struct iommu_gpasid_bind_data *data); +int intel_svm_unbind_gpasid(struct device *dev, int pasid); +struct iommu_sva *intel_svm_bind(struct device *dev, struct mm_struct *mm, + void *drvdata); +void intel_svm_unbind(struct iommu_sva *handle); +int intel_svm_get_pasid(struct iommu_sva *handle); struct svm_dev_ops; struct intel_svm_dev { @@ -680,6 +746,8 @@ struct intel_svm_dev { struct rcu_head rcu; struct device *dev; struct svm_dev_ops *ops; + struct iommu_sva sva; + int pasid; int users; u16 did; u16 dev_iotlb:1; @@ -689,9 +757,11 @@ struct intel_svm_dev { struct intel_svm { struct mmu_notifier notifier; struct mm_struct *mm; + struct intel_iommu *iommu; int flags; int pasid; + int gpasid; /* In case that guest PASID is different from host PASID */ struct list_head devs; struct list_head list; }; diff --git a/include/linux/intel-svm.h b/include/linux/intel-svm.h index d7c403d0dd27..c9e7e601950d 100644 --- a/include/linux/intel-svm.h +++ b/include/linux/intel-svm.h @@ -21,7 +21,6 @@ struct svm_dev_ops { #define SVM_REQ_EXEC (1<<1) #define SVM_REQ_PRIV (1<<0) - /* * The SVM_FLAG_PRIVATE_PASID flag requests a PASID which is *not* the "main" * PASID for the current process. Even if a PASID already exists, a new one @@ -44,90 +43,17 @@ struct svm_dev_ops { * do such IOTLB flushes automatically. */ #define SVM_FLAG_SUPERVISOR_MODE (1<<1) - -#ifdef CONFIG_INTEL_IOMMU_SVM - -/** - * intel_svm_bind_mm() - Bind the current process to a PASID - * @dev: Device to be granted access - * @pasid: Address for allocated PASID - * @flags: Flags. Later for requesting supervisor mode, etc. - * @ops: Callbacks to device driver - * - * This function attempts to enable PASID support for the given device. - * If the @pasid argument is non-%NULL, a PASID is allocated for access - * to the MM of the current process. - * - * By using a %NULL value for the @pasid argument, this function can - * be used to simply validate that PASID support is available for the - * given device — i.e. that it is behind an IOMMU which has the - * requisite support, and is enabled. - * - * Page faults are handled transparently by the IOMMU code, and there - * should be no need for the device driver to be involved. If a page - * fault cannot be handled (i.e. is an invalid address rather than - * just needs paging in), then the page request will be completed by - * the core IOMMU code with appropriate status, and the device itself - * can then report the resulting fault to its driver via whatever - * mechanism is appropriate. - * - * Multiple calls from the same process may result in the same PASID - * being re-used. A reference count is kept. - */ -extern int intel_svm_bind_mm(struct device *dev, int *pasid, int flags, - struct svm_dev_ops *ops); - -/** - * intel_svm_unbind_mm() - Unbind a specified PASID - * @dev: Device for which PASID was allocated - * @pasid: PASID value to be unbound - * - * This function allows a PASID to be retired when the device no - * longer requires access to the address space of a given process. - * - * If the use count for the PASID in question reaches zero, the - * PASID is revoked and may no longer be used by hardware. - * - * Device drivers are required to ensure that no access (including - * page requests) is currently outstanding for the PASID in question, - * before calling this function. +/* + * The SVM_FLAG_GUEST_MODE flag is used when a PASID bind is for guest + * processes. Compared to the host bind, the primary differences are: + * 1. mm life cycle management + * 2. fault reporting */ -extern int intel_svm_unbind_mm(struct device *dev, int pasid); - -/** - * intel_svm_is_pasid_valid() - check if pasid is valid - * @dev: Device for which PASID was allocated - * @pasid: PASID value to be checked - * - * This function checks if the specified pasid is still valid. A - * valid pasid means the backing mm is still having a valid user. - * For kernel callers init_mm is always valid. for other mm, if mm->mm_users - * is non-zero, it is valid. - * - * returns -EINVAL if invalid pasid, 0 if pasid ref count is invalid - * 1 if pasid is valid. +#define SVM_FLAG_GUEST_MODE (1<<2) +/* + * The SVM_FLAG_GUEST_PASID flag is used when a guest has its own PASID space, + * which requires guest and host PASID translation at both directions. */ -extern int intel_svm_is_pasid_valid(struct device *dev, int pasid); - -#else /* CONFIG_INTEL_IOMMU_SVM */ - -static inline int intel_svm_bind_mm(struct device *dev, int *pasid, - int flags, struct svm_dev_ops *ops) -{ - return -ENOSYS; -} - -static inline int intel_svm_unbind_mm(struct device *dev, int pasid) -{ - BUG(); -} - -static inline int intel_svm_is_pasid_valid(struct device *dev, int pasid) -{ - return -EINVAL; -} -#endif /* CONFIG_INTEL_IOMMU_SVM */ - -#define intel_svm_available(dev) (!intel_svm_bind_mm((dev), NULL, 0, NULL)) +#define SVM_FLAG_GUEST_PASID (1<<3) #endif /* __INTEL_SVM_H__ */ diff --git a/include/linux/iommu.h b/include/linux/iommu.h index 7cfd2dddb49d..4e3cd32f5b37 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -53,8 +53,6 @@ struct iommu_fault_event; typedef int (*iommu_fault_handler_t)(struct iommu_domain *, struct device *, unsigned long, int, void *); -typedef int (*iommu_mm_exit_handler_t)(struct device *dev, struct iommu_sva *, - void *); typedef int (*iommu_dev_fault_handler_t)(struct iommu_fault *, void *); struct iommu_domain_geometry { @@ -171,25 +169,6 @@ enum iommu_dev_features { #define IOMMU_PASID_INVALID (-1U) -/** - * struct iommu_sva_ops - device driver callbacks for an SVA context - * - * @mm_exit: called when the mm is about to be torn down by exit_mmap. After - * @mm_exit returns, the device must not issue any more transaction - * with the PASID given as argument. - * - * The @mm_exit handler is allowed to sleep. Be careful about the - * locks taken in @mm_exit, because they might lead to deadlocks if - * they are also held when dropping references to the mm. Consider the - * following call chain: - * mutex_lock(A); mmput(mm) -> exit_mm() -> @mm_exit() -> mutex_lock(A) - * Using mmput_async() prevents this scenario. - * - */ -struct iommu_sva_ops { - iommu_mm_exit_handler_t mm_exit; -}; - #ifdef CONFIG_IOMMU_API /** @@ -482,8 +461,6 @@ extern void iommu_get_resv_regions(struct device *dev, struct list_head *list); extern void iommu_put_resv_regions(struct device *dev, struct list_head *list); extern void generic_iommu_put_resv_regions(struct device *dev, struct list_head *list); -extern int iommu_request_dm_for_dev(struct device *dev); -extern int iommu_request_dma_domain_for_dev(struct device *dev); extern void iommu_set_default_passthrough(bool cmd_line); extern void iommu_set_default_translated(bool cmd_line); extern bool iommu_default_passthrough(void); @@ -616,7 +593,6 @@ struct iommu_fwspec { */ struct iommu_sva { struct device *dev; - const struct iommu_sva_ops *ops; }; int iommu_fwspec_init(struct device *dev, struct fwnode_handle *iommu_fwnode, @@ -664,8 +640,6 @@ struct iommu_sva *iommu_sva_bind_device(struct device *dev, struct mm_struct *mm, void *drvdata); void iommu_sva_unbind_device(struct iommu_sva *handle); -int iommu_sva_set_ops(struct iommu_sva *handle, - const struct iommu_sva_ops *ops); int iommu_sva_get_pasid(struct iommu_sva *handle); #else /* CONFIG_IOMMU_API */ @@ -804,16 +778,6 @@ static inline int iommu_get_group_resv_regions(struct iommu_group *group, return -ENODEV; } -static inline int iommu_request_dm_for_dev(struct device *dev) -{ - return -ENODEV; -} - -static inline int iommu_request_dma_domain_for_dev(struct device *dev) -{ - return -ENODEV; -} - static inline void iommu_set_default_passthrough(bool cmd_line) { } @@ -1069,12 +1033,6 @@ static inline void iommu_sva_unbind_device(struct iommu_sva *handle) { } -static inline int iommu_sva_set_ops(struct iommu_sva *handle, - const struct iommu_sva_ops *ops) -{ - return -EINVAL; -} - static inline int iommu_sva_get_pasid(struct iommu_sva *handle) { return IOMMU_PASID_INVALID; diff --git a/include/linux/mm.h b/include/linux/mm.h index 5a323422d783..f3fe7371855c 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -782,6 +782,11 @@ static inline void *kvcalloc(size_t n, size_t size, gfp_t flags) extern void kvfree(const void *addr); +/* + * Mapcount of compound page as a whole, does not include mapped sub-pages. + * + * Must be called only for compound pages or any their tail sub-pages. + */ static inline int compound_mapcount(struct page *page) { VM_BUG_ON_PAGE(!PageCompound(page), page); @@ -801,10 +806,16 @@ static inline void page_mapcount_reset(struct page *page) int __page_mapcount(struct page *page); +/* + * Mapcount of 0-order page; when compound sub-page, includes + * compound_mapcount(). + * + * Result is undefined for pages which cannot be mapped into userspace. + * For example SLAB or special types of pages. See function page_has_type(). + * They use this place in struct page differently. + */ static inline int page_mapcount(struct page *page) { - VM_BUG_ON_PAGE(PageSlab(page), page); - if (unlikely(PageCompound(page))) return __page_mapcount(page); return atomic_read(&page->_mapcount) + 1; diff --git a/include/linux/netfilter/nf_conntrack_pptp.h b/include/linux/netfilter/nf_conntrack_pptp.h index fcc409de31a4..a28aa289afdc 100644 --- a/include/linux/netfilter/nf_conntrack_pptp.h +++ b/include/linux/netfilter/nf_conntrack_pptp.h @@ -10,7 +10,7 @@ #include <net/netfilter/nf_conntrack_expect.h> #include <uapi/linux/netfilter/nf_conntrack_tuple_common.h> -extern const char *const pptp_msg_name[]; +const char *pptp_msg_name(u_int16_t msg); /* state of the control session */ enum pptp_ctrlsess_state { diff --git a/include/linux/pci-ats.h b/include/linux/pci-ats.h index d08f0869f121..f75c307f346d 100644 --- a/include/linux/pci-ats.h +++ b/include/linux/pci-ats.h @@ -6,11 +6,14 @@ #ifdef CONFIG_PCI_ATS /* Address Translation Service */ +bool pci_ats_supported(struct pci_dev *dev); int pci_enable_ats(struct pci_dev *dev, int ps); void pci_disable_ats(struct pci_dev *dev); int pci_ats_queue_depth(struct pci_dev *dev); int pci_ats_page_aligned(struct pci_dev *dev); #else /* CONFIG_PCI_ATS */ +static inline bool pci_ats_supported(struct pci_dev *d) +{ return false; } static inline int pci_enable_ats(struct pci_dev *d, int ps) { return -ENODEV; } static inline void pci_disable_ats(struct pci_dev *d) { } diff --git a/include/linux/uacce.h b/include/linux/uacce.h index 0e215e6d0534..454c2f6672d7 100644 --- a/include/linux/uacce.h +++ b/include/linux/uacce.h @@ -68,19 +68,21 @@ enum uacce_q_state { * @uacce: pointer to uacce * @priv: private pointer * @wait: wait queue head - * @list: index into uacce_mm - * @uacce_mm: the corresponding mm + * @list: index into uacce queues list * @qfrs: pointer of qfr regions * @state: queue state machine + * @pasid: pasid associated to the mm + * @handle: iommu_sva handle returned by iommu_sva_bind_device() */ struct uacce_queue { struct uacce_device *uacce; void *priv; wait_queue_head_t wait; struct list_head list; - struct uacce_mm *uacce_mm; struct uacce_qfile_region *qfrs[UACCE_MAX_REGION]; enum uacce_q_state state; + int pasid; + struct iommu_sva *handle; }; /** @@ -96,8 +98,8 @@ struct uacce_queue { * @cdev: cdev of the uacce * @dev: dev of the uacce * @priv: private pointer of the uacce - * @mm_list: list head of uacce_mm->list - * @mm_lock: lock for mm_list + * @queues: list of queues + * @queues_lock: lock for queues list * @inode: core vfs */ struct uacce_device { @@ -112,27 +114,9 @@ struct uacce_device { struct cdev *cdev; struct device dev; void *priv; - struct list_head mm_list; - struct mutex mm_lock; - struct inode *inode; -}; - -/** - * struct uacce_mm - keep track of queues bound to a process - * @list: index into uacce_device - * @queues: list of queues - * @mm: the mm struct - * @lock: protects the list of queues - * @pasid: pasid of the uacce_mm - * @handle: iommu_sva handle return from iommu_sva_bind_device - */ -struct uacce_mm { - struct list_head list; struct list_head queues; - struct mm_struct *mm; - struct mutex lock; - int pasid; - struct iommu_sva *handle; + struct mutex queues_lock; + struct inode *inode; }; #if IS_ENABLED(CONFIG_UACCE) diff --git a/include/linux/virtio_net.h b/include/linux/virtio_net.h index 6f6ade63b04c..e8a924eeea3d 100644 --- a/include/linux/virtio_net.h +++ b/include/linux/virtio_net.h @@ -31,6 +31,7 @@ static inline int virtio_net_hdr_to_skb(struct sk_buff *skb, { unsigned int gso_type = 0; unsigned int thlen = 0; + unsigned int p_off = 0; unsigned int ip_proto; if (hdr->gso_type != VIRTIO_NET_HDR_GSO_NONE) { @@ -68,7 +69,8 @@ static inline int virtio_net_hdr_to_skb(struct sk_buff *skb, if (!skb_partial_csum_set(skb, start, off)) return -EINVAL; - if (skb_transport_offset(skb) + thlen > skb_headlen(skb)) + p_off = skb_transport_offset(skb) + thlen; + if (p_off > skb_headlen(skb)) return -EINVAL; } else { /* gso packets without NEEDS_CSUM do not set transport_offset. @@ -92,23 +94,32 @@ retry: return -EINVAL; } - if (keys.control.thoff + thlen > skb_headlen(skb) || + p_off = keys.control.thoff + thlen; + if (p_off > skb_headlen(skb) || keys.basic.ip_proto != ip_proto) return -EINVAL; skb_set_transport_header(skb, keys.control.thoff); + } else if (gso_type) { + p_off = thlen; + if (p_off > skb_headlen(skb)) + return -EINVAL; } } if (hdr->gso_type != VIRTIO_NET_HDR_GSO_NONE) { u16 gso_size = __virtio16_to_cpu(little_endian, hdr->gso_size); + struct skb_shared_info *shinfo = skb_shinfo(skb); - skb_shinfo(skb)->gso_size = gso_size; - skb_shinfo(skb)->gso_type = gso_type; + /* Too small packets are not really GSO ones. */ + if (skb->len - p_off > gso_size) { + shinfo->gso_size = gso_size; + shinfo->gso_type = gso_type; - /* Header must be checked, and gso_segs computed. */ - skb_shinfo(skb)->gso_type |= SKB_GSO_DODGY; - skb_shinfo(skb)->gso_segs = 0; + /* Header must be checked, and gso_segs computed. */ + shinfo->gso_type |= SKB_GSO_DODGY; + shinfo->gso_segs = 0; + } } return 0; diff --git a/include/net/espintcp.h b/include/net/espintcp.h index dd7026a00066..0335bbd76552 100644 --- a/include/net/espintcp.h +++ b/include/net/espintcp.h @@ -25,6 +25,7 @@ struct espintcp_ctx { struct espintcp_msg partial; void (*saved_data_ready)(struct sock *sk); void (*saved_write_space)(struct sock *sk); + void (*saved_destruct)(struct sock *sk); struct work_struct work; bool tx_running; }; diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h index b219a8fe0950..2ec062aaa978 100644 --- a/include/net/ip_fib.h +++ b/include/net/ip_fib.h @@ -447,6 +447,16 @@ static inline int fib_num_tclassid_users(struct net *net) #endif int fib_unmerge(struct net *net); +static inline bool nhc_l3mdev_matches_dev(const struct fib_nh_common *nhc, +const struct net_device *dev) +{ + if (nhc->nhc_dev == dev || + l3mdev_master_ifindex_rcu(nhc->nhc_dev) == dev->ifindex) + return true; + + return false; +} + /* Exported by fib_semantics.c */ int ip_fib_check_default(__be32 gw, struct net_device *dev); int fib_sync_down_dev(struct net_device *dev, unsigned long event, bool force); @@ -479,6 +489,8 @@ void fib_nh_common_release(struct fib_nh_common *nhc); void fib_alias_hw_flags_set(struct net *net, const struct fib_rt_info *fri); void fib_trie_init(void); struct fib_table *fib_trie_table(u32 id, struct fib_table *alias); +bool fib_lookup_good_nhc(const struct fib_nh_common *nhc, int fib_flags, + const struct flowi4 *flp); static inline void fib_combine_itag(u32 *itag, const struct fib_result *res) { diff --git a/include/net/nexthop.h b/include/net/nexthop.h index c440ccc861fc..8c9f1a718859 100644 --- a/include/net/nexthop.h +++ b/include/net/nexthop.h @@ -70,6 +70,7 @@ struct nh_grp_entry { }; struct nh_group { + struct nh_group *spare; /* spare group for removals */ u16 num_nh; bool mpath; bool has_v4; @@ -136,21 +137,20 @@ static inline unsigned int nexthop_num_path(const struct nexthop *nh) { unsigned int rc = 1; - if (nexthop_is_multipath(nh)) { + if (nh->is_group) { struct nh_group *nh_grp; nh_grp = rcu_dereference_rtnl(nh->nh_grp); - rc = nh_grp->num_nh; + if (nh_grp->mpath) + rc = nh_grp->num_nh; } return rc; } static inline -struct nexthop *nexthop_mpath_select(const struct nexthop *nh, int nhsel) +struct nexthop *nexthop_mpath_select(const struct nh_group *nhg, int nhsel) { - const struct nh_group *nhg = rcu_dereference_rtnl(nh->nh_grp); - /* for_nexthops macros in fib_semantics.c grabs a pointer to * the nexthop before checking nhsel */ @@ -185,12 +185,14 @@ static inline bool nexthop_is_blackhole(const struct nexthop *nh) { const struct nh_info *nhi; - if (nexthop_is_multipath(nh)) { - if (nexthop_num_path(nh) > 1) - return false; - nh = nexthop_mpath_select(nh, 0); - if (!nh) + if (nh->is_group) { + struct nh_group *nh_grp; + + nh_grp = rcu_dereference_rtnl(nh->nh_grp); + if (nh_grp->num_nh > 1) return false; + + nh = nh_grp->nh_entries[0].nh; } nhi = rcu_dereference_rtnl(nh->nh_info); @@ -216,16 +218,79 @@ struct fib_nh_common *nexthop_fib_nhc(struct nexthop *nh, int nhsel) BUILD_BUG_ON(offsetof(struct fib_nh, nh_common) != 0); BUILD_BUG_ON(offsetof(struct fib6_nh, nh_common) != 0); - if (nexthop_is_multipath(nh)) { - nh = nexthop_mpath_select(nh, nhsel); - if (!nh) - return NULL; + if (nh->is_group) { + struct nh_group *nh_grp; + + nh_grp = rcu_dereference_rtnl(nh->nh_grp); + if (nh_grp->mpath) { + nh = nexthop_mpath_select(nh_grp, nhsel); + if (!nh) + return NULL; + } } nhi = rcu_dereference_rtnl(nh->nh_info); return &nhi->fib_nhc; } +/* called from fib_table_lookup with rcu_lock */ +static inline +struct fib_nh_common *nexthop_get_nhc_lookup(const struct nexthop *nh, + int fib_flags, + const struct flowi4 *flp, + int *nhsel) +{ + struct nh_info *nhi; + + if (nh->is_group) { + struct nh_group *nhg = rcu_dereference(nh->nh_grp); + int i; + + for (i = 0; i < nhg->num_nh; i++) { + struct nexthop *nhe = nhg->nh_entries[i].nh; + + nhi = rcu_dereference(nhe->nh_info); + if (fib_lookup_good_nhc(&nhi->fib_nhc, fib_flags, flp)) { + *nhsel = i; + return &nhi->fib_nhc; + } + } + } else { + nhi = rcu_dereference(nh->nh_info); + if (fib_lookup_good_nhc(&nhi->fib_nhc, fib_flags, flp)) { + *nhsel = 0; + return &nhi->fib_nhc; + } + } + + return NULL; +} + +static inline bool nexthop_uses_dev(const struct nexthop *nh, + const struct net_device *dev) +{ + struct nh_info *nhi; + + if (nh->is_group) { + struct nh_group *nhg = rcu_dereference(nh->nh_grp); + int i; + + for (i = 0; i < nhg->num_nh; i++) { + struct nexthop *nhe = nhg->nh_entries[i].nh; + + nhi = rcu_dereference(nhe->nh_info); + if (nhc_l3mdev_matches_dev(&nhi->fib_nhc, dev)) + return true; + } + } else { + nhi = rcu_dereference(nh->nh_info); + if (nhc_l3mdev_matches_dev(&nhi->fib_nhc, dev)) + return true; + } + + return false; +} + static inline unsigned int fib_info_num_path(const struct fib_info *fi) { if (unlikely(fi->nh)) @@ -263,8 +328,11 @@ static inline struct fib6_nh *nexthop_fib6_nh(struct nexthop *nh) { struct nh_info *nhi; - if (nexthop_is_multipath(nh)) { - nh = nexthop_mpath_select(nh, 0); + if (nh->is_group) { + struct nh_group *nh_grp; + + nh_grp = rcu_dereference_rtnl(nh->nh_grp); + nh = nexthop_mpath_select(nh_grp, 0); if (!nh) return NULL; } diff --git a/include/net/tls.h b/include/net/tls.h index bf9eb4823933..18cd4f418464 100644 --- a/include/net/tls.h +++ b/include/net/tls.h @@ -135,6 +135,8 @@ struct tls_sw_context_tx { struct tls_rec *open_rec; struct list_head tx_list; atomic_t encrypt_pending; + /* protect crypto_wait with encrypt_pending */ + spinlock_t encrypt_compl_lock; int async_notify; u8 async_capable:1; @@ -155,6 +157,8 @@ struct tls_sw_context_rx { u8 async_capable:1; u8 decrypted:1; atomic_t decrypt_pending; + /* protect crypto_wait with decrypt_pending*/ + spinlock_t decrypt_compl_lock; bool async_notify; }; diff --git a/include/rdma/uverbs_std_types.h b/include/rdma/uverbs_std_types.h index 1b28ce1aba07..325fdaa3bb66 100644 --- a/include/rdma/uverbs_std_types.h +++ b/include/rdma/uverbs_std_types.h @@ -88,7 +88,7 @@ struct ib_uobject *__uobj_get_destroy(const struct uverbs_api_object *obj, static inline void uobj_put_destroy(struct ib_uobject *uobj) { - rdma_lookup_put_uobject(uobj, UVERBS_LOOKUP_WRITE); + rdma_lookup_put_uobject(uobj, UVERBS_LOOKUP_DESTROY); } static inline void uobj_put_read(struct ib_uobject *uobj) diff --git a/include/uapi/linux/iommu.h b/include/uapi/linux/iommu.h index 4ad3496e5c43..e907b7091a46 100644 --- a/include/uapi/linux/iommu.h +++ b/include/uapi/linux/iommu.h @@ -285,6 +285,11 @@ struct iommu_gpasid_bind_data_vtd { __u32 emt; }; +#define IOMMU_SVA_VTD_GPASID_MTS_MASK (IOMMU_SVA_VTD_GPASID_CD | \ + IOMMU_SVA_VTD_GPASID_EMTE | \ + IOMMU_SVA_VTD_GPASID_PCD | \ + IOMMU_SVA_VTD_GPASID_PWT) + /** * struct iommu_gpasid_bind_data - Information about device and guest PASID binding * @version: Version of this data structure diff --git a/include/uapi/linux/xfrm.h b/include/uapi/linux/xfrm.h index 5f3b9fec7b5f..ff7cfdc6cb44 100644 --- a/include/uapi/linux/xfrm.h +++ b/include/uapi/linux/xfrm.h @@ -304,7 +304,7 @@ enum xfrm_attr_type_t { XFRMA_PROTO, /* __u8 */ XFRMA_ADDRESS_FILTER, /* struct xfrm_address_filter */ XFRMA_PAD, - XFRMA_OFFLOAD_DEV, /* struct xfrm_state_offload */ + XFRMA_OFFLOAD_DEV, /* struct xfrm_user_offload */ XFRMA_SET_MARK, /* __u32 */ XFRMA_SET_MARK_MASK, /* __u32 */ XFRMA_IF_ID, /* __u32 */ diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 8d7ee40e2748..efe14cf24bc6 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -1168,14 +1168,14 @@ static void __reg_assign_32_into_64(struct bpf_reg_state *reg) * but must be positive otherwise set to worse case bounds * and refine later from tnum. */ - if (reg->s32_min_value > 0) - reg->smin_value = reg->s32_min_value; - else - reg->smin_value = 0; - if (reg->s32_max_value > 0) + if (reg->s32_min_value >= 0 && reg->s32_max_value >= 0) reg->smax_value = reg->s32_max_value; else reg->smax_value = U32_MAX; + if (reg->s32_min_value >= 0) + reg->smin_value = reg->s32_min_value; + else + reg->smin_value = 0; } static void __reg_combine_32_into_64(struct bpf_reg_state *reg) @@ -10428,22 +10428,13 @@ static int check_struct_ops_btf_id(struct bpf_verifier_env *env) } #define SECURITY_PREFIX "security_" -static int check_attach_modify_return(struct bpf_verifier_env *env) +static int check_attach_modify_return(struct bpf_prog *prog, unsigned long addr) { - struct bpf_prog *prog = env->prog; - unsigned long addr = (unsigned long) prog->aux->trampoline->func.addr; - - /* This is expected to be cleaned up in the future with the KRSI effort - * introducing the LSM_HOOK macro for cleaning up lsm_hooks.h. - */ if (within_error_injection_list(addr) || !strncmp(SECURITY_PREFIX, prog->aux->attach_func_name, sizeof(SECURITY_PREFIX) - 1)) return 0; - verbose(env, "fmod_ret attach_btf_id %u (%s) is not modifiable\n", - prog->aux->attach_btf_id, prog->aux->attach_func_name); - return -EINVAL; } @@ -10654,11 +10645,18 @@ static int check_attach_btf_id(struct bpf_verifier_env *env) goto out; } } + + if (prog->expected_attach_type == BPF_MODIFY_RETURN) { + ret = check_attach_modify_return(prog, addr); + if (ret) + verbose(env, "%s() is not modifiable\n", + prog->aux->attach_func_name); + } + + if (ret) + goto out; tr->func.addr = (void *)addr; prog->aux->trampoline = tr; - - if (prog->expected_attach_type == BPF_MODIFY_RETURN) - ret = check_attach_modify_return(env); out: mutex_unlock(&tr->mutex); if (ret) diff --git a/kernel/cgroup/rstat.c b/kernel/cgroup/rstat.c index 6f87352f8219..41ca996568df 100644 --- a/kernel/cgroup/rstat.c +++ b/kernel/cgroup/rstat.c @@ -33,12 +33,9 @@ void cgroup_rstat_updated(struct cgroup *cgrp, int cpu) return; /* - * Paired with the one in cgroup_rstat_cpu_pop_updated(). Either we - * see NULL updated_next or they see our updated stat. - */ - smp_mb(); - - /* + * Speculative already-on-list test. This may race leading to + * temporary inaccuracies, which is fine. + * * Because @parent's updated_children is terminated with @parent * instead of NULL, we can tell whether @cgrp is on the list by * testing the next pointer for NULL. @@ -134,13 +131,6 @@ static struct cgroup *cgroup_rstat_cpu_pop_updated(struct cgroup *pos, *nextp = rstatc->updated_next; rstatc->updated_next = NULL; - /* - * Paired with the one in cgroup_rstat_cpu_updated(). - * Either they see NULL updated_next or we see their - * updated stat. - */ - smp_mb(); - return pos; } diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 538ba5d94e99..da3e5b54715b 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -2908,7 +2908,7 @@ static void task_tick_numa(struct rq *rq, struct task_struct *curr) /* * We don't care about NUMA placement if we don't have memory. */ - if (!curr->mm || (curr->flags & PF_EXITING) || work->next != work) + if ((curr->flags & (PF_EXITING | PF_KTHREAD)) || work->next != work) return; /* diff --git a/mm/khugepaged.c b/mm/khugepaged.c index 99d77ffb79c2..cd280afb246e 100644 --- a/mm/khugepaged.c +++ b/mm/khugepaged.c @@ -1692,6 +1692,7 @@ static void collapse_file(struct mm_struct *mm, if (page_has_private(page) && !try_to_release_page(page, GFP_KERNEL)) { result = SCAN_PAGE_HAS_PRIVATE; + putback_lru_page(page); goto out_unlock; } diff --git a/mm/z3fold.c b/mm/z3fold.c index 8c3bb5e508b8..460b0feced26 100644 --- a/mm/z3fold.c +++ b/mm/z3fold.c @@ -43,6 +43,7 @@ #include <linux/spinlock.h> #include <linux/zpool.h> #include <linux/magic.h> +#include <linux/kmemleak.h> /* * NCHUNKS_ORDER determines the internal allocation granularity, effectively @@ -215,6 +216,8 @@ static inline struct z3fold_buddy_slots *alloc_slots(struct z3fold_pool *pool, (gfp & ~(__GFP_HIGHMEM | __GFP_MOVABLE))); if (slots) { + /* It will be freed separately in free_handle(). */ + kmemleak_not_leak(slots); memset(slots->slot, 0, sizeof(slots->slot)); slots->pool = (unsigned long)pool; rwlock_init(&slots->lock); diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c index ad12fe3fca8c..83490bf73a13 100644 --- a/net/bridge/br_multicast.c +++ b/net/bridge/br_multicast.c @@ -2413,7 +2413,8 @@ void br_multicast_uninit_stats(struct net_bridge *br) free_percpu(br->mcast_stats); } -static void mcast_stats_add_dir(u64 *dst, u64 *src) +/* noinline for https://bugs.llvm.org/show_bug.cgi?id=45802#c9 */ +static noinline_for_stack void mcast_stats_add_dir(u64 *dst, u64 *src) { dst[BR_MCAST_DIR_RX] += src[BR_MCAST_DIR_RX]; dst[BR_MCAST_DIR_TX] += src[BR_MCAST_DIR_TX]; diff --git a/net/bridge/netfilter/nft_reject_bridge.c b/net/bridge/netfilter/nft_reject_bridge.c index b325b569e761..f48cf4cfb80f 100644 --- a/net/bridge/netfilter/nft_reject_bridge.c +++ b/net/bridge/netfilter/nft_reject_bridge.c @@ -31,6 +31,12 @@ static void nft_reject_br_push_etherhdr(struct sk_buff *oldskb, ether_addr_copy(eth->h_dest, eth_hdr(oldskb)->h_source); eth->h_proto = eth_hdr(oldskb)->h_proto; skb_pull(nskb, ETH_HLEN); + + if (skb_vlan_tag_present(oldskb)) { + u16 vid = skb_vlan_tag_get(oldskb); + + __vlan_hwaccel_put_tag(nskb, oldskb->vlan_proto, vid); + } } static int nft_bridge_iphdr_validate(struct sk_buff *skb) diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c index 998e26b75a78..1d4973f8cd7a 100644 --- a/net/ceph/osd_client.c +++ b/net/ceph/osd_client.c @@ -3649,7 +3649,9 @@ static void handle_reply(struct ceph_osd *osd, struct ceph_msg *msg) * supported. */ req->r_t.target_oloc.pool = m.redirect.oloc.pool; - req->r_flags |= CEPH_OSD_FLAG_REDIRECTED; + req->r_flags |= CEPH_OSD_FLAG_REDIRECTED | + CEPH_OSD_FLAG_IGNORE_OVERLAY | + CEPH_OSD_FLAG_IGNORE_CACHE; req->r_tid = 0; __submit_request(req, false); goto out_unlock_osdc; diff --git a/net/core/neighbour.c b/net/core/neighbour.c index 116139233d57..dbe0c6ead773 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -1082,8 +1082,8 @@ static void neigh_timer_handler(struct timer_list *t) } if (neigh->nud_state & NUD_IN_TIMER) { - if (time_before(next, jiffies + HZ/2)) - next = jiffies + HZ/2; + if (time_before(next, jiffies + HZ/100)) + next = jiffies + HZ/100; if (!mod_timer(&neigh->timer, next)) neigh_hold(neigh); } diff --git a/net/dsa/slave.c b/net/dsa/slave.c index 62f4ee3da172..d3bcb9afa795 100644 --- a/net/dsa/slave.c +++ b/net/dsa/slave.c @@ -1736,6 +1736,7 @@ int dsa_slave_create(struct dsa_port *port) if (ds->ops->port_vlan_add && ds->ops->port_vlan_del) slave_dev->features |= NETIF_F_HW_VLAN_CTAG_FILTER; slave_dev->hw_features |= NETIF_F_HW_TC; + slave_dev->features |= NETIF_F_LLTX; slave_dev->ethtool_ops = &dsa_slave_ethtool_ops; if (!IS_ERR_OR_NULL(port->mac)) ether_addr_copy(slave_dev->dev_addr, port->mac); diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index c0dd561aa190..5267b6b191eb 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -276,6 +276,7 @@ static struct in_device *inetdev_init(struct net_device *dev) err = devinet_sysctl_register(in_dev); if (err) { in_dev->dead = 1; + neigh_parms_release(&arp_tbl, in_dev->arp_parms); in_dev_put(in_dev); in_dev = NULL; goto out; diff --git a/net/ipv4/esp4_offload.c b/net/ipv4/esp4_offload.c index 731022cff600..d14133eac476 100644 --- a/net/ipv4/esp4_offload.c +++ b/net/ipv4/esp4_offload.c @@ -63,10 +63,8 @@ static struct sk_buff *esp4_gro_receive(struct list_head *head, sp->olen++; xo = xfrm_offload(skb); - if (!xo) { - xfrm_state_put(x); + if (!xo) goto out_reset; - } } xo->flags |= XFRM_GRO; @@ -139,19 +137,27 @@ static struct sk_buff *xfrm4_beet_gso_segment(struct xfrm_state *x, struct xfrm_offload *xo = xfrm_offload(skb); struct sk_buff *segs = ERR_PTR(-EINVAL); const struct net_offload *ops; - int proto = xo->proto; + u8 proto = xo->proto; skb->transport_header += x->props.header_len; - if (proto == IPPROTO_BEETPH) { - struct ip_beet_phdr *ph = (struct ip_beet_phdr *)skb->data; + if (x->sel.family != AF_INET6) { + if (proto == IPPROTO_BEETPH) { + struct ip_beet_phdr *ph = + (struct ip_beet_phdr *)skb->data; + + skb->transport_header += ph->hdrlen * 8; + proto = ph->nexthdr; + } else { + skb->transport_header -= IPV4_BEET_PHMAXLEN; + } + } else { + __be16 frag; - skb->transport_header += ph->hdrlen * 8; - proto = ph->nexthdr; - } else if (x->sel.family != AF_INET6) { - skb->transport_header -= IPV4_BEET_PHMAXLEN; - } else if (proto == IPPROTO_TCP) { - skb_shinfo(skb)->gso_type |= SKB_GSO_TCPV4; + skb->transport_header += + ipv6_skip_exthdr(skb, 0, &proto, &frag); + if (proto == IPPROTO_TCP) + skb_shinfo(skb)->gso_type |= SKB_GSO_TCPV4; } __skb_pull(skb, skb_transport_offset(skb)); diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index 1bf9da3a75f9..41079490a118 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -309,17 +309,18 @@ bool fib_info_nh_uses_dev(struct fib_info *fi, const struct net_device *dev) { bool dev_match = false; #ifdef CONFIG_IP_ROUTE_MULTIPATH - int ret; + if (unlikely(fi->nh)) { + dev_match = nexthop_uses_dev(fi->nh, dev); + } else { + int ret; - for (ret = 0; ret < fib_info_num_path(fi); ret++) { - const struct fib_nh_common *nhc = fib_info_nhc(fi, ret); + for (ret = 0; ret < fib_info_num_path(fi); ret++) { + const struct fib_nh_common *nhc = fib_info_nhc(fi, ret); - if (nhc->nhc_dev == dev) { - dev_match = true; - break; - } else if (l3mdev_master_ifindex_rcu(nhc->nhc_dev) == dev->ifindex) { - dev_match = true; - break; + if (nhc_l3mdev_matches_dev(nhc, dev)) { + dev_match = true; + break; + } } } #else diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index 4f334b425538..248f1c1959a6 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -1371,6 +1371,26 @@ static inline t_key prefix_mismatch(t_key key, struct key_vector *n) return (key ^ prefix) & (prefix | -prefix); } +bool fib_lookup_good_nhc(const struct fib_nh_common *nhc, int fib_flags, + const struct flowi4 *flp) +{ + if (nhc->nhc_flags & RTNH_F_DEAD) + return false; + + if (ip_ignore_linkdown(nhc->nhc_dev) && + nhc->nhc_flags & RTNH_F_LINKDOWN && + !(fib_flags & FIB_LOOKUP_IGNORE_LINKSTATE)) + return false; + + if (!(flp->flowi4_flags & FLOWI_FLAG_SKIP_NH_OIF)) { + if (flp->flowi4_oif && + flp->flowi4_oif != nhc->nhc_oif) + return false; + } + + return true; +} + /* should be called with rcu_read_lock */ int fib_table_lookup(struct fib_table *tb, const struct flowi4 *flp, struct fib_result *res, int fib_flags) @@ -1503,6 +1523,7 @@ found: /* Step 3: Process the leaf, if that fails fall back to backtracing */ hlist_for_each_entry_rcu(fa, &n->leaf, fa_list) { struct fib_info *fi = fa->fa_info; + struct fib_nh_common *nhc; int nhsel, err; if ((BITS_PER_LONG > KEYLENGTH) || (fa->fa_slen < KEYLENGTH)) { @@ -1528,26 +1549,25 @@ out_reject: if (fi->fib_flags & RTNH_F_DEAD) continue; - if (unlikely(fi->nh && nexthop_is_blackhole(fi->nh))) { - err = fib_props[RTN_BLACKHOLE].error; - goto out_reject; + if (unlikely(fi->nh)) { + if (nexthop_is_blackhole(fi->nh)) { + err = fib_props[RTN_BLACKHOLE].error; + goto out_reject; + } + + nhc = nexthop_get_nhc_lookup(fi->nh, fib_flags, flp, + &nhsel); + if (nhc) + goto set_result; + goto miss; } for (nhsel = 0; nhsel < fib_info_num_path(fi); nhsel++) { - struct fib_nh_common *nhc = fib_info_nhc(fi, nhsel); + nhc = fib_info_nhc(fi, nhsel); - if (nhc->nhc_flags & RTNH_F_DEAD) + if (!fib_lookup_good_nhc(nhc, fib_flags, flp)) continue; - if (ip_ignore_linkdown(nhc->nhc_dev) && - nhc->nhc_flags & RTNH_F_LINKDOWN && - !(fib_flags & FIB_LOOKUP_IGNORE_LINKSTATE)) - continue; - if (!(flp->flowi4_flags & FLOWI_FLAG_SKIP_NH_OIF)) { - if (flp->flowi4_oif && - flp->flowi4_oif != nhc->nhc_oif) - continue; - } - +set_result: if (!(fib_flags & FIB_LOOKUP_NOREF)) refcount_inc(&fi->fib_clntref); @@ -1568,6 +1588,7 @@ out_reject: return err; } } +miss: #ifdef CONFIG_IP_FIB_TRIE_STATS this_cpu_inc(stats->semantic_match_miss); #endif diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c index 1b4e6f298648..1dda7c155c48 100644 --- a/net/ipv4/ip_vti.c +++ b/net/ipv4/ip_vti.c @@ -93,7 +93,28 @@ static int vti_rcv_proto(struct sk_buff *skb) static int vti_rcv_tunnel(struct sk_buff *skb) { - return vti_rcv(skb, ip_hdr(skb)->saddr, true); + struct ip_tunnel_net *itn = net_generic(dev_net(skb->dev), vti_net_id); + const struct iphdr *iph = ip_hdr(skb); + struct ip_tunnel *tunnel; + + tunnel = ip_tunnel_lookup(itn, skb->dev->ifindex, TUNNEL_NO_KEY, + iph->saddr, iph->daddr, 0); + if (tunnel) { + struct tnl_ptk_info tpi = { + .proto = htons(ETH_P_IP), + }; + + if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb)) + goto drop; + if (iptunnel_pull_header(skb, 0, tpi.proto, false)) + goto drop; + return ip_tunnel_rcv(tunnel, skb, &tpi, NULL, false); + } + + return -EINVAL; +drop: + kfree_skb(skb); + return 0; } static int vti_rcv_cb(struct sk_buff *skb, int err) diff --git a/net/ipv4/netfilter/nf_nat_pptp.c b/net/ipv4/netfilter/nf_nat_pptp.c index 3c25a467b3ef..7afde8828b4c 100644 --- a/net/ipv4/netfilter/nf_nat_pptp.c +++ b/net/ipv4/netfilter/nf_nat_pptp.c @@ -166,8 +166,7 @@ pptp_outbound_pkt(struct sk_buff *skb, break; default: pr_debug("unknown outbound packet 0x%04x:%s\n", msg, - msg <= PPTP_MSG_MAX ? pptp_msg_name[msg] : - pptp_msg_name[0]); + pptp_msg_name(msg)); fallthrough; case PPTP_SET_LINK_INFO: /* only need to NAT in case PAC is behind NAT box */ @@ -268,9 +267,7 @@ pptp_inbound_pkt(struct sk_buff *skb, pcid_off = offsetof(union pptp_ctrl_union, setlink.peersCallID); break; default: - pr_debug("unknown inbound packet %s\n", - msg <= PPTP_MSG_MAX ? pptp_msg_name[msg] : - pptp_msg_name[0]); + pr_debug("unknown inbound packet %s\n", pptp_msg_name(msg)); fallthrough; case PPTP_START_SESSION_REQUEST: case PPTP_START_SESSION_REPLY: diff --git a/net/ipv4/nexthop.c b/net/ipv4/nexthop.c index 715e14475220..563f71bcb2d7 100644 --- a/net/ipv4/nexthop.c +++ b/net/ipv4/nexthop.c @@ -63,9 +63,16 @@ static void nexthop_free_mpath(struct nexthop *nh) int i; nhg = rcu_dereference_raw(nh->nh_grp); - for (i = 0; i < nhg->num_nh; ++i) - WARN_ON(nhg->nh_entries[i].nh); + for (i = 0; i < nhg->num_nh; ++i) { + struct nh_grp_entry *nhge = &nhg->nh_entries[i]; + + WARN_ON(!list_empty(&nhge->nh_list)); + nexthop_put(nhge->nh); + } + + WARN_ON(nhg->spare == nhg); + kfree(nhg->spare); kfree(nhg); } @@ -694,41 +701,56 @@ static void nh_group_rebalance(struct nh_group *nhg) } } -static void remove_nh_grp_entry(struct nh_grp_entry *nhge, - struct nh_group *nhg, +static void remove_nh_grp_entry(struct net *net, struct nh_grp_entry *nhge, struct nl_info *nlinfo) { + struct nh_grp_entry *nhges, *new_nhges; + struct nexthop *nhp = nhge->nh_parent; struct nexthop *nh = nhge->nh; - struct nh_grp_entry *nhges; - bool found = false; - int i; + struct nh_group *nhg, *newg; + int i, j; WARN_ON(!nh); - nhges = nhg->nh_entries; - for (i = 0; i < nhg->num_nh; ++i) { - if (found) { - nhges[i-1].nh = nhges[i].nh; - nhges[i-1].weight = nhges[i].weight; - list_del(&nhges[i].nh_list); - list_add(&nhges[i-1].nh_list, &nhges[i-1].nh->grp_list); - } else if (nhg->nh_entries[i].nh == nh) { - found = true; - } - } + nhg = rtnl_dereference(nhp->nh_grp); + newg = nhg->spare; - if (WARN_ON(!found)) + /* last entry, keep it visible and remove the parent */ + if (nhg->num_nh == 1) { + remove_nexthop(net, nhp, nlinfo); return; + } + + newg->has_v4 = nhg->has_v4; + newg->mpath = nhg->mpath; + newg->num_nh = nhg->num_nh; - nhg->num_nh--; - nhg->nh_entries[nhg->num_nh].nh = NULL; + /* copy old entries to new except the one getting removed */ + nhges = nhg->nh_entries; + new_nhges = newg->nh_entries; + for (i = 0, j = 0; i < nhg->num_nh; ++i) { + /* current nexthop getting removed */ + if (nhg->nh_entries[i].nh == nh) { + newg->num_nh--; + continue; + } - nh_group_rebalance(nhg); + list_del(&nhges[i].nh_list); + new_nhges[j].nh_parent = nhges[i].nh_parent; + new_nhges[j].nh = nhges[i].nh; + new_nhges[j].weight = nhges[i].weight; + list_add(&new_nhges[j].nh_list, &new_nhges[j].nh->grp_list); + j++; + } - nexthop_put(nh); + nh_group_rebalance(newg); + rcu_assign_pointer(nhp->nh_grp, newg); + + list_del(&nhge->nh_list); + nexthop_put(nhge->nh); if (nlinfo) - nexthop_notify(RTM_NEWNEXTHOP, nhge->nh_parent, nlinfo); + nexthop_notify(RTM_NEWNEXTHOP, nhp, nlinfo); } static void remove_nexthop_from_groups(struct net *net, struct nexthop *nh, @@ -736,17 +758,11 @@ static void remove_nexthop_from_groups(struct net *net, struct nexthop *nh, { struct nh_grp_entry *nhge, *tmp; - list_for_each_entry_safe(nhge, tmp, &nh->grp_list, nh_list) { - struct nh_group *nhg; - - list_del(&nhge->nh_list); - nhg = rtnl_dereference(nhge->nh_parent->nh_grp); - remove_nh_grp_entry(nhge, nhg, nlinfo); + list_for_each_entry_safe(nhge, tmp, &nh->grp_list, nh_list) + remove_nh_grp_entry(net, nhge, nlinfo); - /* if this group has no more entries then remove it */ - if (!nhg->num_nh) - remove_nexthop(net, nhge->nh_parent, nlinfo); - } + /* make sure all see the newly published array before releasing rtnl */ + synchronize_rcu(); } static void remove_nexthop_group(struct nexthop *nh, struct nl_info *nlinfo) @@ -760,10 +776,7 @@ static void remove_nexthop_group(struct nexthop *nh, struct nl_info *nlinfo) if (WARN_ON(!nhge->nh)) continue; - list_del(&nhge->nh_list); - nexthop_put(nhge->nh); - nhge->nh = NULL; - nhg->num_nh--; + list_del_init(&nhge->nh_list); } } @@ -1086,6 +1099,7 @@ static struct nexthop *nexthop_create_group(struct net *net, { struct nlattr *grps_attr = cfg->nh_grp; struct nexthop_grp *entry = nla_data(grps_attr); + u16 num_nh = nla_len(grps_attr) / sizeof(*entry); struct nh_group *nhg; struct nexthop *nh; int i; @@ -1096,12 +1110,21 @@ static struct nexthop *nexthop_create_group(struct net *net, nh->is_group = 1; - nhg = nexthop_grp_alloc(nla_len(grps_attr) / sizeof(*entry)); + nhg = nexthop_grp_alloc(num_nh); if (!nhg) { kfree(nh); return ERR_PTR(-ENOMEM); } + /* spare group used for removals */ + nhg->spare = nexthop_grp_alloc(num_nh); + if (!nhg) { + kfree(nhg); + kfree(nh); + return NULL; + } + nhg->spare->spare = nhg; + for (i = 0; i < nhg->num_nh; ++i) { struct nexthop *nhe; struct nh_info *nhi; @@ -1133,6 +1156,7 @@ out_no_nh: for (; i >= 0; --i) nexthop_put(nhg->nh_entries[i].nh); + kfree(nhg->spare); kfree(nhg); kfree(nh); diff --git a/net/ipv6/esp6_offload.c b/net/ipv6/esp6_offload.c index 8eab2c869d61..ab0eea336c70 100644 --- a/net/ipv6/esp6_offload.c +++ b/net/ipv6/esp6_offload.c @@ -85,10 +85,8 @@ static struct sk_buff *esp6_gro_receive(struct list_head *head, sp->olen++; xo = xfrm_offload(skb); - if (!xo) { - xfrm_state_put(x); + if (!xo) goto out_reset; - } } xo->flags |= XFRM_GRO; @@ -123,9 +121,16 @@ static void esp6_gso_encap(struct xfrm_state *x, struct sk_buff *skb) struct ip_esp_hdr *esph; struct ipv6hdr *iph = ipv6_hdr(skb); struct xfrm_offload *xo = xfrm_offload(skb); - int proto = iph->nexthdr; + u8 proto = iph->nexthdr; skb_push(skb, -skb_network_offset(skb)); + + if (x->outer_mode.encap == XFRM_MODE_TRANSPORT) { + __be16 frag; + + ipv6_skip_exthdr(skb, sizeof(struct ipv6hdr), &proto, &frag); + } + esph = ip_esp_hdr(skb); *skb_mac_header(skb) = IPPROTO_ESP; @@ -166,23 +171,31 @@ static struct sk_buff *xfrm6_beet_gso_segment(struct xfrm_state *x, struct xfrm_offload *xo = xfrm_offload(skb); struct sk_buff *segs = ERR_PTR(-EINVAL); const struct net_offload *ops; - int proto = xo->proto; + u8 proto = xo->proto; skb->transport_header += x->props.header_len; - if (proto == IPPROTO_BEETPH) { - struct ip_beet_phdr *ph = (struct ip_beet_phdr *)skb->data; - - skb->transport_header += ph->hdrlen * 8; - proto = ph->nexthdr; - } - if (x->sel.family != AF_INET6) { skb->transport_header -= (sizeof(struct ipv6hdr) - sizeof(struct iphdr)); + if (proto == IPPROTO_BEETPH) { + struct ip_beet_phdr *ph = + (struct ip_beet_phdr *)skb->data; + + skb->transport_header += ph->hdrlen * 8; + proto = ph->nexthdr; + } else { + skb->transport_header -= IPV4_BEET_PHMAXLEN; + } + if (proto == IPPROTO_TCP) skb_shinfo(skb)->gso_type |= SKB_GSO_TCPV6; + } else { + __be16 frag; + + skb->transport_header += + ipv6_skip_exthdr(skb, 0, &proto, &frag); } __skb_pull(skb, skb_transport_offset(skb)); diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c index fcb53ed1c4fb..6d7ef78c88af 100644 --- a/net/l2tp/l2tp_core.c +++ b/net/l2tp/l2tp_core.c @@ -1458,6 +1458,9 @@ static int l2tp_validate_socket(const struct sock *sk, const struct net *net, if (sk->sk_type != SOCK_DGRAM) return -EPROTONOSUPPORT; + if (sk->sk_family != PF_INET && sk->sk_family != PF_INET6) + return -EPROTONOSUPPORT; + if ((encap == L2TP_ENCAPTYPE_UDP && sk->sk_protocol != IPPROTO_UDP) || (encap == L2TP_ENCAPTYPE_IP && sk->sk_protocol != IPPROTO_L2TP)) return -EPROTONOSUPPORT; diff --git a/net/l2tp/l2tp_ip.c b/net/l2tp/l2tp_ip.c index 0d7c887a2b75..955662a6dee7 100644 --- a/net/l2tp/l2tp_ip.c +++ b/net/l2tp/l2tp_ip.c @@ -20,7 +20,6 @@ #include <net/icmp.h> #include <net/udp.h> #include <net/inet_common.h> -#include <net/inet_hashtables.h> #include <net/tcp_states.h> #include <net/protocol.h> #include <net/xfrm.h> @@ -209,15 +208,31 @@ discard: return 0; } -static int l2tp_ip_open(struct sock *sk) +static int l2tp_ip_hash(struct sock *sk) { - /* Prevent autobind. We don't have ports. */ - inet_sk(sk)->inet_num = IPPROTO_L2TP; + if (sk_unhashed(sk)) { + write_lock_bh(&l2tp_ip_lock); + sk_add_node(sk, &l2tp_ip_table); + write_unlock_bh(&l2tp_ip_lock); + } + return 0; +} +static void l2tp_ip_unhash(struct sock *sk) +{ + if (sk_unhashed(sk)) + return; write_lock_bh(&l2tp_ip_lock); - sk_add_node(sk, &l2tp_ip_table); + sk_del_node_init(sk); write_unlock_bh(&l2tp_ip_lock); +} + +static int l2tp_ip_open(struct sock *sk) +{ + /* Prevent autobind. We don't have ports. */ + inet_sk(sk)->inet_num = IPPROTO_L2TP; + l2tp_ip_hash(sk); return 0; } @@ -594,8 +609,8 @@ static struct proto l2tp_ip_prot = { .sendmsg = l2tp_ip_sendmsg, .recvmsg = l2tp_ip_recvmsg, .backlog_rcv = l2tp_ip_backlog_recv, - .hash = inet_hash, - .unhash = inet_unhash, + .hash = l2tp_ip_hash, + .unhash = l2tp_ip_unhash, .obj_size = sizeof(struct l2tp_ip_sock), #ifdef CONFIG_COMPAT .compat_setsockopt = compat_ip_setsockopt, diff --git a/net/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c index d148766f40d1..0fa694bd3f6a 100644 --- a/net/l2tp/l2tp_ip6.c +++ b/net/l2tp/l2tp_ip6.c @@ -20,8 +20,6 @@ #include <net/icmp.h> #include <net/udp.h> #include <net/inet_common.h> -#include <net/inet_hashtables.h> -#include <net/inet6_hashtables.h> #include <net/tcp_states.h> #include <net/protocol.h> #include <net/xfrm.h> @@ -222,15 +220,31 @@ discard: return 0; } -static int l2tp_ip6_open(struct sock *sk) +static int l2tp_ip6_hash(struct sock *sk) { - /* Prevent autobind. We don't have ports. */ - inet_sk(sk)->inet_num = IPPROTO_L2TP; + if (sk_unhashed(sk)) { + write_lock_bh(&l2tp_ip6_lock); + sk_add_node(sk, &l2tp_ip6_table); + write_unlock_bh(&l2tp_ip6_lock); + } + return 0; +} +static void l2tp_ip6_unhash(struct sock *sk) +{ + if (sk_unhashed(sk)) + return; write_lock_bh(&l2tp_ip6_lock); - sk_add_node(sk, &l2tp_ip6_table); + sk_del_node_init(sk); write_unlock_bh(&l2tp_ip6_lock); +} + +static int l2tp_ip6_open(struct sock *sk) +{ + /* Prevent autobind. We don't have ports. */ + inet_sk(sk)->inet_num = IPPROTO_L2TP; + l2tp_ip6_hash(sk); return 0; } @@ -728,8 +742,8 @@ static struct proto l2tp_ip6_prot = { .sendmsg = l2tp_ip6_sendmsg, .recvmsg = l2tp_ip6_recvmsg, .backlog_rcv = l2tp_ip6_backlog_recv, - .hash = inet6_hash, - .unhash = inet_unhash, + .hash = l2tp_ip6_hash, + .unhash = l2tp_ip6_unhash, .obj_size = sizeof(struct l2tp_ip6_sock), #ifdef CONFIG_COMPAT .compat_setsockopt = compat_ipv6_setsockopt, diff --git a/net/mac80211/mesh_hwmp.c b/net/mac80211/mesh_hwmp.c index 38a0383dfbcf..aa5150929996 100644 --- a/net/mac80211/mesh_hwmp.c +++ b/net/mac80211/mesh_hwmp.c @@ -1103,7 +1103,14 @@ void mesh_path_start_discovery(struct ieee80211_sub_if_data *sdata) mesh_path_sel_frame_tx(MPATH_PREQ, 0, sdata->vif.addr, ifmsh->sn, target_flags, mpath->dst, mpath->sn, da, 0, ttl, lifetime, 0, ifmsh->preq_id++, sdata); + + spin_lock_bh(&mpath->state_lock); + if (mpath->flags & MESH_PATH_DELETED) { + spin_unlock_bh(&mpath->state_lock); + goto enddiscovery; + } mod_timer(&mpath->timer, jiffies + mpath->discovery_timeout); + spin_unlock_bh(&mpath->state_lock); enddiscovery: rcu_read_unlock(); diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index 32ea8d35489a..34dd0e278a82 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -954,7 +954,8 @@ fallback: pr_debug("block timeout %ld", timeo); mptcp_wait_data(sk, &timeo); - if (unlikely(__mptcp_tcp_fallback(msk))) + ssock = __mptcp_tcp_fallback(msk); + if (unlikely(ssock)) goto fallback; } @@ -1262,11 +1263,14 @@ static void mptcp_close(struct sock *sk, long timeout) lock_sock(sk); - mptcp_token_destroy(msk->token); inet_sk_state_store(sk, TCP_CLOSE); - __mptcp_flush_join_list(msk); - + /* be sure to always acquire the join list lock, to sync vs + * mptcp_finish_join(). + */ + spin_lock_bh(&msk->join_list_lock); + list_splice_tail_init(&msk->join_list, &msk->conn_list); + spin_unlock_bh(&msk->join_list_lock); list_splice_init(&msk->conn_list, &conn_list); data_fin_tx_seq = msk->write_seq; @@ -1456,6 +1460,7 @@ static void mptcp_destroy(struct sock *sk) { struct mptcp_sock *msk = mptcp_sk(sk); + mptcp_token_destroy(msk->token); if (msk->cached_ext) __skb_ext_put(msk->cached_ext); @@ -1622,22 +1627,30 @@ bool mptcp_finish_join(struct sock *sk) if (!msk->pm.server_side) return true; - /* passive connection, attach to msk socket */ + if (!mptcp_pm_allow_new_subflow(msk)) + return false; + + /* active connections are already on conn_list, and we can't acquire + * msk lock here. + * use the join list lock as synchronization point and double-check + * msk status to avoid racing with mptcp_close() + */ + spin_lock_bh(&msk->join_list_lock); + ret = inet_sk_state_load(parent) == TCP_ESTABLISHED; + if (ret && !WARN_ON_ONCE(!list_empty(&subflow->node))) + list_add_tail(&subflow->node, &msk->join_list); + spin_unlock_bh(&msk->join_list_lock); + if (!ret) + return false; + + /* attach to msk socket only after we are sure he will deal with us + * at close time + */ parent_sock = READ_ONCE(parent->sk_socket); if (parent_sock && !sk->sk_socket) mptcp_sock_graft(sk, parent_sock); - - ret = mptcp_pm_allow_new_subflow(msk); - if (ret) { - subflow->map_seq = msk->ack_seq; - - /* active connections are already on conn_list */ - spin_lock_bh(&msk->join_list_lock); - if (!WARN_ON_ONCE(!list_empty(&subflow->node))) - list_add_tail(&subflow->node, &msk->join_list); - spin_unlock_bh(&msk->join_list_lock); - } - return ret; + subflow->map_seq = msk->ack_seq; + return true; } bool mptcp_sk_is_subflow(const struct sock *sk) @@ -1711,6 +1724,14 @@ static int mptcp_stream_connect(struct socket *sock, struct sockaddr *uaddr, int err; lock_sock(sock->sk); + if (sock->state != SS_UNCONNECTED && msk->subflow) { + /* pending connection or invalid state, let existing subflow + * cope with that + */ + ssock = msk->subflow; + goto do_connect; + } + ssock = __mptcp_socket_create(msk, TCP_SYN_SENT); if (IS_ERR(ssock)) { err = PTR_ERR(ssock); @@ -1725,9 +1746,17 @@ static int mptcp_stream_connect(struct socket *sock, struct sockaddr *uaddr, mptcp_subflow_ctx(ssock->sk)->request_mptcp = 0; #endif +do_connect: err = ssock->ops->connect(ssock, uaddr, addr_len, flags); - inet_sk_state_store(sock->sk, inet_sk_state_load(ssock->sk)); - mptcp_copy_inaddrs(sock->sk, ssock->sk); + sock->state = ssock->state; + + /* on successful connect, the msk state will be moved to established by + * subflow_finish_connect() + */ + if (!err || err == EINPROGRESS) + mptcp_copy_inaddrs(sock->sk, ssock->sk); + else + inet_sk_state_store(sock->sk, inet_sk_state_load(ssock->sk)); unlock: release_sock(sock->sk); diff --git a/net/netfilter/ipset/ip_set_list_set.c b/net/netfilter/ipset/ip_set_list_set.c index cd747c0962fd..5a67f7966574 100644 --- a/net/netfilter/ipset/ip_set_list_set.c +++ b/net/netfilter/ipset/ip_set_list_set.c @@ -59,7 +59,7 @@ list_set_ktest(struct ip_set *set, const struct sk_buff *skb, /* Don't lookup sub-counters at all */ opt->cmdflags &= ~IPSET_FLAG_MATCH_COUNTERS; if (opt->cmdflags & IPSET_FLAG_SKIP_SUBCOUNTER_UPDATE) - opt->cmdflags &= ~IPSET_FLAG_SKIP_COUNTER_UPDATE; + opt->cmdflags |= IPSET_FLAG_SKIP_COUNTER_UPDATE; list_for_each_entry_rcu(e, &map->members, list) { ret = ip_set_test(e->id, skb, par, opt); if (ret <= 0) diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index 1d57b95d3481..bb72ca5f3999 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -2016,22 +2016,18 @@ static void nf_conntrack_attach(struct sk_buff *nskb, const struct sk_buff *skb) nf_conntrack_get(skb_nfct(nskb)); } -static int nf_conntrack_update(struct net *net, struct sk_buff *skb) +static int __nf_conntrack_update(struct net *net, struct sk_buff *skb, + struct nf_conn *ct, + enum ip_conntrack_info ctinfo) { struct nf_conntrack_tuple_hash *h; struct nf_conntrack_tuple tuple; - enum ip_conntrack_info ctinfo; struct nf_nat_hook *nat_hook; unsigned int status; - struct nf_conn *ct; int dataoff; u16 l3num; u8 l4num; - ct = nf_ct_get(skb, &ctinfo); - if (!ct || nf_ct_is_confirmed(ct)) - return 0; - l3num = nf_ct_l3num(ct); dataoff = get_l4proto(skb, skb_network_offset(skb), l3num, &l4num); @@ -2088,6 +2084,76 @@ static int nf_conntrack_update(struct net *net, struct sk_buff *skb) return 0; } +/* This packet is coming from userspace via nf_queue, complete the packet + * processing after the helper invocation in nf_confirm(). + */ +static int nf_confirm_cthelper(struct sk_buff *skb, struct nf_conn *ct, + enum ip_conntrack_info ctinfo) +{ + const struct nf_conntrack_helper *helper; + const struct nf_conn_help *help; + int protoff; + + help = nfct_help(ct); + if (!help) + return 0; + + helper = rcu_dereference(help->helper); + if (!(helper->flags & NF_CT_HELPER_F_USERSPACE)) + return 0; + + switch (nf_ct_l3num(ct)) { + case NFPROTO_IPV4: + protoff = skb_network_offset(skb) + ip_hdrlen(skb); + break; +#if IS_ENABLED(CONFIG_IPV6) + case NFPROTO_IPV6: { + __be16 frag_off; + u8 pnum; + + pnum = ipv6_hdr(skb)->nexthdr; + protoff = ipv6_skip_exthdr(skb, sizeof(struct ipv6hdr), &pnum, + &frag_off); + if (protoff < 0 || (frag_off & htons(~0x7)) != 0) + return 0; + break; + } +#endif + default: + return 0; + } + + if (test_bit(IPS_SEQ_ADJUST_BIT, &ct->status) && + !nf_is_loopback_packet(skb)) { + if (!nf_ct_seq_adjust(skb, ct, ctinfo, protoff)) { + NF_CT_STAT_INC_ATOMIC(nf_ct_net(ct), drop); + return -1; + } + } + + /* We've seen it coming out the other side: confirm it */ + return nf_conntrack_confirm(skb) == NF_DROP ? - 1 : 0; +} + +static int nf_conntrack_update(struct net *net, struct sk_buff *skb) +{ + enum ip_conntrack_info ctinfo; + struct nf_conn *ct; + int err; + + ct = nf_ct_get(skb, &ctinfo); + if (!ct) + return 0; + + if (!nf_ct_is_confirmed(ct)) { + err = __nf_conntrack_update(net, skb, ct, ctinfo); + if (err < 0) + return err; + } + + return nf_confirm_cthelper(skb, ct, ctinfo); +} + static bool nf_conntrack_get_tuple_skb(struct nf_conntrack_tuple *dst_tuple, const struct sk_buff *skb) { diff --git a/net/netfilter/nf_conntrack_pptp.c b/net/netfilter/nf_conntrack_pptp.c index a971183f11af..1f44d523b512 100644 --- a/net/netfilter/nf_conntrack_pptp.c +++ b/net/netfilter/nf_conntrack_pptp.c @@ -72,24 +72,32 @@ EXPORT_SYMBOL_GPL(nf_nat_pptp_hook_expectfn); #if defined(DEBUG) || defined(CONFIG_DYNAMIC_DEBUG) /* PptpControlMessageType names */ -const char *const pptp_msg_name[] = { - "UNKNOWN_MESSAGE", - "START_SESSION_REQUEST", - "START_SESSION_REPLY", - "STOP_SESSION_REQUEST", - "STOP_SESSION_REPLY", - "ECHO_REQUEST", - "ECHO_REPLY", - "OUT_CALL_REQUEST", - "OUT_CALL_REPLY", - "IN_CALL_REQUEST", - "IN_CALL_REPLY", - "IN_CALL_CONNECT", - "CALL_CLEAR_REQUEST", - "CALL_DISCONNECT_NOTIFY", - "WAN_ERROR_NOTIFY", - "SET_LINK_INFO" +static const char *const pptp_msg_name_array[PPTP_MSG_MAX + 1] = { + [0] = "UNKNOWN_MESSAGE", + [PPTP_START_SESSION_REQUEST] = "START_SESSION_REQUEST", + [PPTP_START_SESSION_REPLY] = "START_SESSION_REPLY", + [PPTP_STOP_SESSION_REQUEST] = "STOP_SESSION_REQUEST", + [PPTP_STOP_SESSION_REPLY] = "STOP_SESSION_REPLY", + [PPTP_ECHO_REQUEST] = "ECHO_REQUEST", + [PPTP_ECHO_REPLY] = "ECHO_REPLY", + [PPTP_OUT_CALL_REQUEST] = "OUT_CALL_REQUEST", + [PPTP_OUT_CALL_REPLY] = "OUT_CALL_REPLY", + [PPTP_IN_CALL_REQUEST] = "IN_CALL_REQUEST", + [PPTP_IN_CALL_REPLY] = "IN_CALL_REPLY", + [PPTP_IN_CALL_CONNECT] = "IN_CALL_CONNECT", + [PPTP_CALL_CLEAR_REQUEST] = "CALL_CLEAR_REQUEST", + [PPTP_CALL_DISCONNECT_NOTIFY] = "CALL_DISCONNECT_NOTIFY", + [PPTP_WAN_ERROR_NOTIFY] = "WAN_ERROR_NOTIFY", + [PPTP_SET_LINK_INFO] = "SET_LINK_INFO" }; + +const char *pptp_msg_name(u_int16_t msg) +{ + if (msg > PPTP_MSG_MAX) + return pptp_msg_name_array[0]; + + return pptp_msg_name_array[msg]; +} EXPORT_SYMBOL(pptp_msg_name); #endif @@ -276,7 +284,7 @@ pptp_inbound_pkt(struct sk_buff *skb, unsigned int protoff, typeof(nf_nat_pptp_hook_inbound) nf_nat_pptp_inbound; msg = ntohs(ctlh->messageType); - pr_debug("inbound control message %s\n", pptp_msg_name[msg]); + pr_debug("inbound control message %s\n", pptp_msg_name(msg)); switch (msg) { case PPTP_START_SESSION_REPLY: @@ -311,7 +319,7 @@ pptp_inbound_pkt(struct sk_buff *skb, unsigned int protoff, pcid = pptpReq->ocack.peersCallID; if (info->pns_call_id != pcid) goto invalid; - pr_debug("%s, CID=%X, PCID=%X\n", pptp_msg_name[msg], + pr_debug("%s, CID=%X, PCID=%X\n", pptp_msg_name(msg), ntohs(cid), ntohs(pcid)); if (pptpReq->ocack.resultCode == PPTP_OUTCALL_CONNECT) { @@ -328,7 +336,7 @@ pptp_inbound_pkt(struct sk_buff *skb, unsigned int protoff, goto invalid; cid = pptpReq->icreq.callID; - pr_debug("%s, CID=%X\n", pptp_msg_name[msg], ntohs(cid)); + pr_debug("%s, CID=%X\n", pptp_msg_name(msg), ntohs(cid)); info->cstate = PPTP_CALL_IN_REQ; info->pac_call_id = cid; break; @@ -347,7 +355,7 @@ pptp_inbound_pkt(struct sk_buff *skb, unsigned int protoff, if (info->pns_call_id != pcid) goto invalid; - pr_debug("%s, PCID=%X\n", pptp_msg_name[msg], ntohs(pcid)); + pr_debug("%s, PCID=%X\n", pptp_msg_name(msg), ntohs(pcid)); info->cstate = PPTP_CALL_IN_CONF; /* we expect a GRE connection from PAC to PNS */ @@ -357,7 +365,7 @@ pptp_inbound_pkt(struct sk_buff *skb, unsigned int protoff, case PPTP_CALL_DISCONNECT_NOTIFY: /* server confirms disconnect */ cid = pptpReq->disc.callID; - pr_debug("%s, CID=%X\n", pptp_msg_name[msg], ntohs(cid)); + pr_debug("%s, CID=%X\n", pptp_msg_name(msg), ntohs(cid)); info->cstate = PPTP_CALL_NONE; /* untrack this call id, unexpect GRE packets */ @@ -384,7 +392,7 @@ pptp_inbound_pkt(struct sk_buff *skb, unsigned int protoff, invalid: pr_debug("invalid %s: type=%d cid=%u pcid=%u " "cstate=%d sstate=%d pns_cid=%u pac_cid=%u\n", - msg <= PPTP_MSG_MAX ? pptp_msg_name[msg] : pptp_msg_name[0], + pptp_msg_name(msg), msg, ntohs(cid), ntohs(pcid), info->cstate, info->sstate, ntohs(info->pns_call_id), ntohs(info->pac_call_id)); return NF_ACCEPT; @@ -404,7 +412,7 @@ pptp_outbound_pkt(struct sk_buff *skb, unsigned int protoff, typeof(nf_nat_pptp_hook_outbound) nf_nat_pptp_outbound; msg = ntohs(ctlh->messageType); - pr_debug("outbound control message %s\n", pptp_msg_name[msg]); + pr_debug("outbound control message %s\n", pptp_msg_name(msg)); switch (msg) { case PPTP_START_SESSION_REQUEST: @@ -426,7 +434,7 @@ pptp_outbound_pkt(struct sk_buff *skb, unsigned int protoff, info->cstate = PPTP_CALL_OUT_REQ; /* track PNS call id */ cid = pptpReq->ocreq.callID; - pr_debug("%s, CID=%X\n", pptp_msg_name[msg], ntohs(cid)); + pr_debug("%s, CID=%X\n", pptp_msg_name(msg), ntohs(cid)); info->pns_call_id = cid; break; @@ -440,7 +448,7 @@ pptp_outbound_pkt(struct sk_buff *skb, unsigned int protoff, pcid = pptpReq->icack.peersCallID; if (info->pac_call_id != pcid) goto invalid; - pr_debug("%s, CID=%X PCID=%X\n", pptp_msg_name[msg], + pr_debug("%s, CID=%X PCID=%X\n", pptp_msg_name(msg), ntohs(cid), ntohs(pcid)); if (pptpReq->icack.resultCode == PPTP_INCALL_ACCEPT) { @@ -480,7 +488,7 @@ pptp_outbound_pkt(struct sk_buff *skb, unsigned int protoff, invalid: pr_debug("invalid %s: type=%d cid=%u pcid=%u " "cstate=%d sstate=%d pns_cid=%u pac_cid=%u\n", - msg <= PPTP_MSG_MAX ? pptp_msg_name[msg] : pptp_msg_name[0], + pptp_msg_name(msg), msg, ntohs(cid), ntohs(pcid), info->cstate, info->sstate, ntohs(info->pns_call_id), ntohs(info->pac_call_id)); return NF_ACCEPT; diff --git a/net/netfilter/nfnetlink_cthelper.c b/net/netfilter/nfnetlink_cthelper.c index a5f294aa8e4c..5b0d0a77379c 100644 --- a/net/netfilter/nfnetlink_cthelper.c +++ b/net/netfilter/nfnetlink_cthelper.c @@ -103,7 +103,7 @@ nfnl_cthelper_from_nlattr(struct nlattr *attr, struct nf_conn *ct) if (help->helper->data_len == 0) return -EINVAL; - nla_memcpy(help->data, nla_data(attr), sizeof(help->data)); + nla_memcpy(help->data, attr, sizeof(help->data)); return 0; } @@ -240,6 +240,7 @@ nfnl_cthelper_create(const struct nlattr * const tb[], ret = -ENOMEM; goto err2; } + helper->data_len = size; helper->flags |= NF_CT_HELPER_F_USERSPACE; memcpy(&helper->tuple, tuple, sizeof(struct nf_conntrack_tuple)); diff --git a/net/qrtr/ns.c b/net/qrtr/ns.c index e7d0fe3f4330..c5b3202a14ca 100644 --- a/net/qrtr/ns.c +++ b/net/qrtr/ns.c @@ -712,6 +712,10 @@ void qrtr_ns_init(void) goto err_sock; } + qrtr_ns.workqueue = alloc_workqueue("qrtr_ns_handler", WQ_UNBOUND, 1); + if (!qrtr_ns.workqueue) + goto err_sock; + qrtr_ns.sock->sk->sk_data_ready = qrtr_ns_data_ready; sq.sq_port = QRTR_PORT_CTRL; @@ -720,17 +724,13 @@ void qrtr_ns_init(void) ret = kernel_bind(qrtr_ns.sock, (struct sockaddr *)&sq, sizeof(sq)); if (ret < 0) { pr_err("failed to bind to socket\n"); - goto err_sock; + goto err_wq; } qrtr_ns.bcast_sq.sq_family = AF_QIPCRTR; qrtr_ns.bcast_sq.sq_node = QRTR_NODE_BCAST; qrtr_ns.bcast_sq.sq_port = QRTR_PORT_CTRL; - qrtr_ns.workqueue = alloc_workqueue("qrtr_ns_handler", WQ_UNBOUND, 1); - if (!qrtr_ns.workqueue) - goto err_sock; - ret = say_hello(&qrtr_ns.bcast_sq); if (ret < 0) goto err_wq; diff --git a/net/sched/act_ct.c b/net/sched/act_ct.c index 1a766393be62..20577355235a 100644 --- a/net/sched/act_ct.c +++ b/net/sched/act_ct.c @@ -199,6 +199,9 @@ static int tcf_ct_flow_table_add_action_nat(struct net *net, const struct nf_conntrack_tuple *tuple = &ct->tuplehash[dir].tuple; struct nf_conntrack_tuple target; + if (!(ct->status & IPS_NAT_MASK)) + return 0; + nf_ct_invert_tuple(&target, &ct->tuplehash[!dir].tuple); switch (tuple->src.l3num) { diff --git a/net/sched/sch_fq_pie.c b/net/sched/sch_fq_pie.c index a9da8776bf5b..fb760cee824e 100644 --- a/net/sched/sch_fq_pie.c +++ b/net/sched/sch_fq_pie.c @@ -297,9 +297,9 @@ static int fq_pie_change(struct Qdisc *sch, struct nlattr *opt, goto flow_error; } q->flows_cnt = nla_get_u32(tb[TCA_FQ_PIE_FLOWS]); - if (!q->flows_cnt || q->flows_cnt > 65536) { + if (!q->flows_cnt || q->flows_cnt >= 65536) { NL_SET_ERR_MSG_MOD(extack, - "Number of flows must be < 65536"); + "Number of flows must range in [1..65535]"); goto flow_error; } } diff --git a/net/sctp/Kconfig b/net/sctp/Kconfig index 6e2eb1dd64ed..68934438ee19 100644 --- a/net/sctp/Kconfig +++ b/net/sctp/Kconfig @@ -31,7 +31,7 @@ menuconfig IP_SCTP homing at either or both ends of an association." To compile this protocol support as a module, choose M here: the - module will be called sctp. Debug messages are handeled by the + module will be called sctp. Debug messages are handled by the kernel's dynamic debugging framework. If in doubt, say N. diff --git a/net/sctp/ulpevent.c b/net/sctp/ulpevent.c index c82dbdcf13f2..77d5c36a8991 100644 --- a/net/sctp/ulpevent.c +++ b/net/sctp/ulpevent.c @@ -343,6 +343,9 @@ void sctp_ulpevent_nofity_peer_addr_change(struct sctp_transport *transport, struct sockaddr_storage addr; struct sctp_ulpevent *event; + if (asoc->state < SCTP_STATE_ESTABLISHED) + return; + memset(&addr, 0, sizeof(struct sockaddr_storage)); memcpy(&addr, &transport->ipaddr, transport->af_specific->sockaddr_len); diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c index 2d399b6c4075..8c2763eb6aae 100644 --- a/net/tls/tls_sw.c +++ b/net/tls/tls_sw.c @@ -206,10 +206,12 @@ static void tls_decrypt_done(struct crypto_async_request *req, int err) kfree(aead_req); + spin_lock_bh(&ctx->decrypt_compl_lock); pending = atomic_dec_return(&ctx->decrypt_pending); - if (!pending && READ_ONCE(ctx->async_notify)) + if (!pending && ctx->async_notify) complete(&ctx->async_wait.completion); + spin_unlock_bh(&ctx->decrypt_compl_lock); } static int tls_do_decryption(struct sock *sk, @@ -467,10 +469,12 @@ static void tls_encrypt_done(struct crypto_async_request *req, int err) ready = true; } + spin_lock_bh(&ctx->encrypt_compl_lock); pending = atomic_dec_return(&ctx->encrypt_pending); - if (!pending && READ_ONCE(ctx->async_notify)) + if (!pending && ctx->async_notify) complete(&ctx->async_wait.completion); + spin_unlock_bh(&ctx->encrypt_compl_lock); if (!ready) return; @@ -929,6 +933,7 @@ int tls_sw_sendmsg(struct sock *sk, struct msghdr *msg, size_t size) int num_zc = 0; int orig_size; int ret = 0; + int pending; if (msg->msg_flags & ~(MSG_MORE | MSG_DONTWAIT | MSG_NOSIGNAL)) return -EOPNOTSUPP; @@ -1095,13 +1100,19 @@ trim_sgl: goto send_end; } else if (num_zc) { /* Wait for pending encryptions to get completed */ - smp_store_mb(ctx->async_notify, true); + spin_lock_bh(&ctx->encrypt_compl_lock); + ctx->async_notify = true; - if (atomic_read(&ctx->encrypt_pending)) + pending = atomic_read(&ctx->encrypt_pending); + spin_unlock_bh(&ctx->encrypt_compl_lock); + if (pending) crypto_wait_req(-EINPROGRESS, &ctx->async_wait); else reinit_completion(&ctx->async_wait.completion); + /* There can be no concurrent accesses, since we have no + * pending encrypt operations + */ WRITE_ONCE(ctx->async_notify, false); if (ctx->async_wait.err) { @@ -1732,6 +1743,7 @@ int tls_sw_recvmsg(struct sock *sk, bool is_kvec = iov_iter_is_kvec(&msg->msg_iter); bool is_peek = flags & MSG_PEEK; int num_async = 0; + int pending; flags |= nonblock; @@ -1894,8 +1906,11 @@ pick_next_record: recv_end: if (num_async) { /* Wait for all previously submitted records to be decrypted */ - smp_store_mb(ctx->async_notify, true); - if (atomic_read(&ctx->decrypt_pending)) { + spin_lock_bh(&ctx->decrypt_compl_lock); + ctx->async_notify = true; + pending = atomic_read(&ctx->decrypt_pending); + spin_unlock_bh(&ctx->decrypt_compl_lock); + if (pending) { err = crypto_wait_req(-EINPROGRESS, &ctx->async_wait); if (err) { /* one of async decrypt failed */ @@ -1907,6 +1922,10 @@ recv_end: } else { reinit_completion(&ctx->async_wait.completion); } + + /* There can be no concurrent accesses, since we have no + * pending decrypt operations + */ WRITE_ONCE(ctx->async_notify, false); /* Drain records from the rx_list & copy if required */ @@ -2293,6 +2312,7 @@ int tls_set_sw_offload(struct sock *sk, struct tls_context *ctx, int tx) if (tx) { crypto_init_wait(&sw_ctx_tx->async_wait); + spin_lock_init(&sw_ctx_tx->encrypt_compl_lock); crypto_info = &ctx->crypto_send.info; cctx = &ctx->tx; aead = &sw_ctx_tx->aead_send; @@ -2301,6 +2321,7 @@ int tls_set_sw_offload(struct sock *sk, struct tls_context *ctx, int tx) sw_ctx_tx->tx_work.sk = sk; } else { crypto_init_wait(&sw_ctx_rx->async_wait); + spin_lock_init(&sw_ctx_rx->decrypt_compl_lock); crypto_info = &ctx->crypto_recv.info; cctx = &ctx->rx; skb_queue_head_init(&sw_ctx_rx->rx_list); diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c index a5f28708e0e7..626bf9044418 100644 --- a/net/vmw_vsock/af_vsock.c +++ b/net/vmw_vsock/af_vsock.c @@ -1408,7 +1408,7 @@ static int vsock_accept(struct socket *sock, struct socket *newsock, int flags, /* Wait for children sockets to appear; these are the new sockets * created upon connection establishment. */ - timeout = sock_sndtimeo(listener, flags & O_NONBLOCK); + timeout = sock_rcvtimeo(listener, flags & O_NONBLOCK); prepare_to_wait(sk_sleep(listener), &wait, TASK_INTERRUPTIBLE); while ((connected = vsock_dequeue_accept(listener)) == NULL && diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c index 69efc891885f..0edda1edf988 100644 --- a/net/vmw_vsock/virtio_transport_common.c +++ b/net/vmw_vsock/virtio_transport_common.c @@ -1132,6 +1132,14 @@ void virtio_transport_recv_pkt(struct virtio_transport *t, lock_sock(sk); + /* Check if sk has been released before lock_sock */ + if (sk->sk_shutdown == SHUTDOWN_MASK) { + (void)virtio_transport_reset_no_sock(t, pkt); + release_sock(sk); + sock_put(sk); + goto free_pkt; + } + /* Update CID in case it has changed after a transport reset event */ vsk->local_addr.svm_cid = dst.svm_cid; diff --git a/net/wireless/core.c b/net/wireless/core.c index 341402b4f178..ce024440fa51 100644 --- a/net/wireless/core.c +++ b/net/wireless/core.c @@ -142,7 +142,7 @@ int cfg80211_dev_rename(struct cfg80211_registered_device *rdev, if (result) return result; - if (rdev->wiphy.debugfsdir) + if (!IS_ERR_OR_NULL(rdev->wiphy.debugfsdir)) debugfs_rename(rdev->wiphy.debugfsdir->d_parent, rdev->wiphy.debugfsdir, rdev->wiphy.debugfsdir->d_parent, newname); diff --git a/net/xdp/xdp_umem.c b/net/xdp/xdp_umem.c index ed7a6060f73c..3889bd9aec46 100644 --- a/net/xdp/xdp_umem.c +++ b/net/xdp/xdp_umem.c @@ -341,8 +341,8 @@ static int xdp_umem_reg(struct xdp_umem *umem, struct xdp_umem_reg *mr) { bool unaligned_chunks = mr->flags & XDP_UMEM_UNALIGNED_CHUNK_FLAG; u32 chunk_size = mr->chunk_size, headroom = mr->headroom; + u64 npgs, addr = mr->addr, size = mr->len; unsigned int chunks, chunks_per_page; - u64 addr = mr->addr, size = mr->len; int err; if (chunk_size < XDP_UMEM_MIN_CHUNK_SIZE || chunk_size > PAGE_SIZE) { @@ -372,6 +372,10 @@ static int xdp_umem_reg(struct xdp_umem *umem, struct xdp_umem_reg *mr) if ((addr + size) < addr) return -EINVAL; + npgs = div_u64(size, PAGE_SIZE); + if (npgs > U32_MAX) + return -EINVAL; + chunks = (unsigned int)div_u64(size, chunk_size); if (chunks == 0) return -EINVAL; @@ -391,7 +395,7 @@ static int xdp_umem_reg(struct xdp_umem *umem, struct xdp_umem_reg *mr) umem->size = size; umem->headroom = headroom; umem->chunk_size_nohr = chunk_size - headroom; - umem->npgs = size / PAGE_SIZE; + umem->npgs = (u32)npgs; umem->pgs = NULL; umem->user = NULL; umem->flags = mr->flags; diff --git a/net/xfrm/espintcp.c b/net/xfrm/espintcp.c index 037ea156d2f9..5a0ff665b71a 100644 --- a/net/xfrm/espintcp.c +++ b/net/xfrm/espintcp.c @@ -379,6 +379,7 @@ static void espintcp_destruct(struct sock *sk) { struct espintcp_ctx *ctx = espintcp_getctx(sk); + ctx->saved_destruct(sk); kfree(ctx); } @@ -419,6 +420,7 @@ static int espintcp_init_sk(struct sock *sk) sk->sk_socket->ops = &espintcp_ops; ctx->saved_data_ready = sk->sk_data_ready; ctx->saved_write_space = sk->sk_write_space; + ctx->saved_destruct = sk->sk_destruct; sk->sk_data_ready = espintcp_data_ready; sk->sk_write_space = espintcp_write_space; sk->sk_destruct = espintcp_destruct; diff --git a/net/xfrm/xfrm_device.c b/net/xfrm/xfrm_device.c index 6cc7f7f1dd68..f50d1f97cf8e 100644 --- a/net/xfrm/xfrm_device.c +++ b/net/xfrm/xfrm_device.c @@ -25,12 +25,10 @@ static void __xfrm_transport_prep(struct xfrm_state *x, struct sk_buff *skb, struct xfrm_offload *xo = xfrm_offload(skb); skb_reset_mac_len(skb); - pskb_pull(skb, skb->mac_len + hsize + x->props.header_len); - - if (xo->flags & XFRM_GSO_SEGMENT) { - skb_reset_transport_header(skb); + if (xo->flags & XFRM_GSO_SEGMENT) skb->transport_header -= x->props.header_len; - } + + pskb_pull(skb, skb_transport_offset(skb) + x->props.header_len); } static void __xfrm_mode_tunnel_prep(struct xfrm_state *x, struct sk_buff *skb, diff --git a/net/xfrm/xfrm_input.c b/net/xfrm/xfrm_input.c index aa35f23c4912..8a202c44f89a 100644 --- a/net/xfrm/xfrm_input.c +++ b/net/xfrm/xfrm_input.c @@ -644,7 +644,7 @@ resume: dev_put(skb->dev); spin_lock(&x->lock); - if (nexthdr <= 0) { + if (nexthdr < 0) { if (nexthdr == -EBADMSG) { xfrm_audit_state_icvfail(x, skb, x->type->proto); diff --git a/net/xfrm/xfrm_interface.c b/net/xfrm/xfrm_interface.c index 3361e3ac5714..1e115cbf21d3 100644 --- a/net/xfrm/xfrm_interface.c +++ b/net/xfrm/xfrm_interface.c @@ -750,7 +750,28 @@ static struct rtnl_link_ops xfrmi_link_ops __read_mostly = { .get_link_net = xfrmi_get_link_net, }; +static void __net_exit xfrmi_exit_batch_net(struct list_head *net_exit_list) +{ + struct net *net; + LIST_HEAD(list); + + rtnl_lock(); + list_for_each_entry(net, net_exit_list, exit_list) { + struct xfrmi_net *xfrmn = net_generic(net, xfrmi_net_id); + struct xfrm_if __rcu **xip; + struct xfrm_if *xi; + + for (xip = &xfrmn->xfrmi[0]; + (xi = rtnl_dereference(*xip)) != NULL; + xip = &xi->next) + unregister_netdevice_queue(xi->dev, &list); + } + unregister_netdevice_many(&list); + rtnl_unlock(); +} + static struct pernet_operations xfrmi_net_ops = { + .exit_batch = xfrmi_exit_batch_net, .id = &xfrmi_net_id, .size = sizeof(struct xfrmi_net), }; diff --git a/net/xfrm/xfrm_output.c b/net/xfrm/xfrm_output.c index 2fd3d990d992..69c4900db817 100644 --- a/net/xfrm/xfrm_output.c +++ b/net/xfrm/xfrm_output.c @@ -583,18 +583,20 @@ int xfrm_output(struct sock *sk, struct sk_buff *skb) xfrm_state_hold(x); if (skb_is_gso(skb)) { - skb_shinfo(skb)->gso_type |= SKB_GSO_ESP; + if (skb->inner_protocol) + return xfrm_output_gso(net, sk, skb); - return xfrm_output2(net, sk, skb); + skb_shinfo(skb)->gso_type |= SKB_GSO_ESP; + goto out; } if (x->xso.dev && x->xso.dev->features & NETIF_F_HW_ESP_TX_CSUM) goto out; + } else { + if (skb_is_gso(skb)) + return xfrm_output_gso(net, sk, skb); } - if (skb_is_gso(skb)) - return xfrm_output_gso(net, sk, skb); - if (skb->ip_summed == CHECKSUM_PARTIAL) { err = skb_checksum_help(skb); if (err) { @@ -640,7 +642,8 @@ void xfrm_local_error(struct sk_buff *skb, int mtu) if (skb->protocol == htons(ETH_P_IP)) proto = AF_INET; - else if (skb->protocol == htons(ETH_P_IPV6)) + else if (skb->protocol == htons(ETH_P_IPV6) && + skb->sk->sk_family == AF_INET6) proto = AF_INET6; else return; diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index 297b2fdb3c29..564aa6492e7c 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -1436,12 +1436,7 @@ static void xfrm_policy_requeue(struct xfrm_policy *old, static bool xfrm_policy_mark_match(struct xfrm_policy *policy, struct xfrm_policy *pol) { - u32 mark = policy->mark.v & policy->mark.m; - - if (policy->mark.v == pol->mark.v && policy->mark.m == pol->mark.m) - return true; - - if ((mark & pol->mark.m) == pol->mark.v && + if (policy->mark.v == pol->mark.v && policy->priority == pol->priority) return true; diff --git a/scripts/checkpatch.pl b/scripts/checkpatch.pl index eac40f0abd56..b83be177edf0 100755 --- a/scripts/checkpatch.pl +++ b/scripts/checkpatch.pl @@ -51,7 +51,7 @@ my %ignore_type = (); my @ignore = (); my $help = 0; my $configuration_file = ".checkpatch.conf"; -my $max_line_length = 80; +my $max_line_length = 100; my $ignore_perl_version = 0; my $minimum_perl_version = 5.10.0; my $min_conf_desc_length = 4; @@ -97,9 +97,11 @@ Options: --types TYPE(,TYPE2...) show only these comma separated message types --ignore TYPE(,TYPE2...) ignore various comma separated message types --show-types show the specific message type in the output - --max-line-length=n set the maximum line length, if exceeded, warn + --max-line-length=n set the maximum line length, (default $max_line_length) + if exceeded, warn on patches + requires --strict for use with --file --min-conf-desc-length=n set the min description length, if shorter, warn - --tab-size=n set the number of spaces for tab (default 8) + --tab-size=n set the number of spaces for tab (default $tabsize) --root=PATH PATH to the kernel tree root --no-summary suppress the per-file summary --mailback only produce a report in case of warnings/errors @@ -3240,8 +3242,10 @@ sub process { if ($msg_type ne "" && (show_type("LONG_LINE") || show_type($msg_type))) { - WARN($msg_type, - "line over $max_line_length characters\n" . $herecurr); + my $msg_level = \&WARN; + $msg_level = \&CHK if ($file); + &{$msg_level}($msg_type, + "line length of $length exceeds $max_line_length columns\n" . $herecurr); } } diff --git a/security/Makefile b/security/Makefile index 22e73a3482bd..3baf435de541 100644 --- a/security/Makefile +++ b/security/Makefile @@ -30,7 +30,7 @@ obj-$(CONFIG_SECURITY_YAMA) += yama/ obj-$(CONFIG_SECURITY_LOADPIN) += loadpin/ obj-$(CONFIG_SECURITY_SAFESETID) += safesetid/ obj-$(CONFIG_SECURITY_LOCKDOWN_LSM) += lockdown/ -obj-$(CONFIG_CGROUP_DEVICE) += device_cgroup.o +obj-$(CONFIG_CGROUPS) += device_cgroup.o obj-$(CONFIG_BPF_LSM) += bpf/ # Object integrity file lists diff --git a/security/commoncap.c b/security/commoncap.c index f4ee0ae106b2..0ca31c8bc0b1 100644 --- a/security/commoncap.c +++ b/security/commoncap.c @@ -812,6 +812,7 @@ int cap_bprm_set_creds(struct linux_binprm *bprm) int ret; kuid_t root_uid; + new->cap_ambient = old->cap_ambient; if (WARN_ON(!cap_ambient_invariant_ok(old))) return -EPERM; diff --git a/security/device_cgroup.c b/security/device_cgroup.c index 7d0f8f7431ff..43ab0ad45c1b 100644 --- a/security/device_cgroup.c +++ b/security/device_cgroup.c @@ -15,6 +15,8 @@ #include <linux/rcupdate.h> #include <linux/mutex.h> +#ifdef CONFIG_CGROUP_DEVICE + static DEFINE_MUTEX(devcgroup_mutex); enum devcg_behavior { @@ -792,7 +794,7 @@ struct cgroup_subsys devices_cgrp_subsys = { }; /** - * __devcgroup_check_permission - checks if an inode operation is permitted + * devcgroup_legacy_check_permission - checks if an inode operation is permitted * @dev_cgroup: the dev cgroup to be tested against * @type: device type * @major: device major number @@ -801,7 +803,7 @@ struct cgroup_subsys devices_cgrp_subsys = { * * returns 0 on success, -EPERM case the operation is not permitted */ -static int __devcgroup_check_permission(short type, u32 major, u32 minor, +static int devcgroup_legacy_check_permission(short type, u32 major, u32 minor, short access) { struct dev_cgroup *dev_cgroup; @@ -825,6 +827,10 @@ static int __devcgroup_check_permission(short type, u32 major, u32 minor, return 0; } +#endif /* CONFIG_CGROUP_DEVICE */ + +#if defined(CONFIG_CGROUP_DEVICE) || defined(CONFIG_CGROUP_BPF) + int devcgroup_check_permission(short type, u32 major, u32 minor, short access) { int rc = BPF_CGROUP_RUN_PROG_DEVICE_CGROUP(type, major, minor, access); @@ -832,6 +838,13 @@ int devcgroup_check_permission(short type, u32 major, u32 minor, short access) if (rc) return -EPERM; - return __devcgroup_check_permission(type, major, minor, access); + #ifdef CONFIG_CGROUP_DEVICE + return devcgroup_legacy_check_permission(type, major, minor, access); + + #else /* CONFIG_CGROUP_DEVICE */ + return 0; + + #endif /* CONFIG_CGROUP_DEVICE */ } EXPORT_SYMBOL(devcgroup_check_permission); +#endif /* defined(CONFIG_CGROUP_DEVICE) || defined(CONFIG_CGROUP_BPF) */ diff --git a/sound/core/hwdep.c b/sound/core/hwdep.c index b412d3b3d5ff..21edb8ac95eb 100644 --- a/sound/core/hwdep.c +++ b/sound/core/hwdep.c @@ -216,12 +216,12 @@ static int snd_hwdep_dsp_load(struct snd_hwdep *hw, if (info.index >= 32) return -EINVAL; /* check whether the dsp was already loaded */ - if (hw->dsp_loaded & (1 << info.index)) + if (hw->dsp_loaded & (1u << info.index)) return -EBUSY; err = hw->ops.dsp_load(hw, &info); if (err < 0) return err; - hw->dsp_loaded |= (1 << info.index); + hw->dsp_loaded |= (1u << info.index); return 0; } diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index 041d2a32059b..e62d58872b6e 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -384,6 +384,7 @@ static void alc_fill_eapd_coef(struct hda_codec *codec) case 0x10ec0282: case 0x10ec0283: case 0x10ec0286: + case 0x10ec0287: case 0x10ec0288: case 0x10ec0285: case 0x10ec0298: @@ -5484,18 +5485,9 @@ static void alc_fixup_tpt470_dock(struct hda_codec *codec, { 0x19, 0x21a11010 }, /* dock mic */ { } }; - /* Assure the speaker pin to be coupled with DAC NID 0x03; otherwise - * the speaker output becomes too low by some reason on Thinkpads with - * ALC298 codec - */ - static const hda_nid_t preferred_pairs[] = { - 0x14, 0x03, 0x17, 0x02, 0x21, 0x02, - 0 - }; struct alc_spec *spec = codec->spec; if (action == HDA_FIXUP_ACT_PRE_PROBE) { - spec->gen.preferred_dacs = preferred_pairs; spec->parse_flags = HDA_PINCFG_NO_HP_FIXUP; snd_hda_apply_pincfgs(codec, pincfgs); } else if (action == HDA_FIXUP_ACT_INIT) { @@ -5508,6 +5500,23 @@ static void alc_fixup_tpt470_dock(struct hda_codec *codec, } } +static void alc_fixup_tpt470_dacs(struct hda_codec *codec, + const struct hda_fixup *fix, int action) +{ + /* Assure the speaker pin to be coupled with DAC NID 0x03; otherwise + * the speaker output becomes too low by some reason on Thinkpads with + * ALC298 codec + */ + static const hda_nid_t preferred_pairs[] = { + 0x14, 0x03, 0x17, 0x02, 0x21, 0x02, + 0 + }; + struct alc_spec *spec = codec->spec; + + if (action == HDA_FIXUP_ACT_PRE_PROBE) + spec->gen.preferred_dacs = preferred_pairs; +} + static void alc_shutup_dell_xps13(struct hda_codec *codec) { struct alc_spec *spec = codec->spec; @@ -6063,6 +6072,7 @@ enum { ALC700_FIXUP_INTEL_REFERENCE, ALC274_FIXUP_DELL_BIND_DACS, ALC274_FIXUP_DELL_AIO_LINEOUT_VERB, + ALC298_FIXUP_TPT470_DOCK_FIX, ALC298_FIXUP_TPT470_DOCK, ALC255_FIXUP_DUMMY_LINEOUT_VERB, ALC255_FIXUP_DELL_HEADSET_MIC, @@ -6994,12 +7004,18 @@ static const struct hda_fixup alc269_fixups[] = { .chained = true, .chain_id = ALC274_FIXUP_DELL_BIND_DACS }, - [ALC298_FIXUP_TPT470_DOCK] = { + [ALC298_FIXUP_TPT470_DOCK_FIX] = { .type = HDA_FIXUP_FUNC, .v.func = alc_fixup_tpt470_dock, .chained = true, .chain_id = ALC293_FIXUP_LENOVO_SPK_NOISE }, + [ALC298_FIXUP_TPT470_DOCK] = { + .type = HDA_FIXUP_FUNC, + .v.func = alc_fixup_tpt470_dacs, + .chained = true, + .chain_id = ALC298_FIXUP_TPT470_DOCK_FIX + }, [ALC255_FIXUP_DUMMY_LINEOUT_VERB] = { .type = HDA_FIXUP_PINS, .v.pins = (const struct hda_pintbl[]) { @@ -7638,6 +7654,7 @@ static const struct hda_model_fixup alc269_fixup_models[] = { {.id = ALC292_FIXUP_TPT440_DOCK, .name = "tpt440-dock"}, {.id = ALC292_FIXUP_TPT440, .name = "tpt440"}, {.id = ALC292_FIXUP_TPT460, .name = "tpt460"}, + {.id = ALC298_FIXUP_TPT470_DOCK_FIX, .name = "tpt470-dock-fix"}, {.id = ALC298_FIXUP_TPT470_DOCK, .name = "tpt470-dock"}, {.id = ALC233_FIXUP_LENOVO_MULTI_CODECS, .name = "dual-codecs"}, {.id = ALC700_FIXUP_INTEL_REFERENCE, .name = "alc700-ref"}, @@ -8276,6 +8293,7 @@ static int patch_alc269(struct hda_codec *codec) case 0x10ec0215: case 0x10ec0245: case 0x10ec0285: + case 0x10ec0287: case 0x10ec0289: spec->codec_variant = ALC269_TYPE_ALC215; spec->shutup = alc225_shutup; @@ -9554,6 +9572,7 @@ static const struct hda_device_id snd_hda_id_realtek[] = { HDA_CODEC_ENTRY(0x10ec0284, "ALC284", patch_alc269), HDA_CODEC_ENTRY(0x10ec0285, "ALC285", patch_alc269), HDA_CODEC_ENTRY(0x10ec0286, "ALC286", patch_alc269), + HDA_CODEC_ENTRY(0x10ec0287, "ALC287", patch_alc269), HDA_CODEC_ENTRY(0x10ec0288, "ALC288", patch_alc269), HDA_CODEC_ENTRY(0x10ec0289, "ALC289", patch_alc269), HDA_CODEC_ENTRY(0x10ec0290, "ALC290", patch_alc269), diff --git a/sound/usb/mixer.c b/sound/usb/mixer.c index a88d7854513b..15769f266790 100644 --- a/sound/usb/mixer.c +++ b/sound/usb/mixer.c @@ -1182,6 +1182,14 @@ static void volume_control_quirks(struct usb_mixer_elem_info *cval, cval->res = 384; } break; + case USB_ID(0x0495, 0x3042): /* ESS Technology Asus USB DAC */ + if ((strstr(kctl->id.name, "Playback Volume") != NULL) || + strstr(kctl->id.name, "Capture Volume") != NULL) { + cval->min >>= 8; + cval->max = 0; + cval->res = 1; + } + break; } } diff --git a/sound/usb/mixer_maps.c b/sound/usb/mixer_maps.c index bfdc6ad52785..9af7aa93f6fa 100644 --- a/sound/usb/mixer_maps.c +++ b/sound/usb/mixer_maps.c @@ -397,6 +397,21 @@ static const struct usbmix_connector_map trx40_mobo_connector_map[] = { {} }; +/* Rear panel + front mic on Gigabyte TRX40 Aorus Master with ALC1220-VB */ +static const struct usbmix_name_map aorus_master_alc1220vb_map[] = { + { 17, NULL }, /* OT, IEC958?, disabled */ + { 19, NULL, 12 }, /* FU, Input Gain Pad - broken response, disabled */ + { 16, "Line Out" }, /* OT */ + { 22, "Line Out Playback" }, /* FU */ + { 7, "Line" }, /* IT */ + { 19, "Line Capture" }, /* FU */ + { 8, "Mic" }, /* IT */ + { 20, "Mic Capture" }, /* FU */ + { 9, "Front Mic" }, /* IT */ + { 21, "Front Mic Capture" }, /* FU */ + {} +}; + /* * Control map entries */ @@ -526,6 +541,10 @@ static const struct usbmix_ctl_map usbmix_ctl_maps[] = { .id = USB_ID(0x1b1c, 0x0a42), .map = corsair_virtuoso_map, }, + { /* Gigabyte TRX40 Aorus Master (rear panel + front mic) */ + .id = USB_ID(0x0414, 0xa001), + .map = aorus_master_alc1220vb_map, + }, { /* Gigabyte TRX40 Aorus Pro WiFi */ .id = USB_ID(0x0414, 0xa002), .map = trx40_mobo_map, diff --git a/sound/usb/quirks-table.h b/sound/usb/quirks-table.h index 6313c30f5c85..eb89902a83be 100644 --- a/sound/usb/quirks-table.h +++ b/sound/usb/quirks-table.h @@ -3566,4 +3566,29 @@ ALC1220_VB_DESKTOP(0x0db0, 0x543d), /* MSI TRX40 */ ALC1220_VB_DESKTOP(0x26ce, 0x0a01), /* Asrock TRX40 Creator */ #undef ALC1220_VB_DESKTOP +/* Two entries for Gigabyte TRX40 Aorus Master: + * TRX40 Aorus Master has two USB-audio devices, one for the front headphone + * with ESS SABRE9218 DAC chip, while another for the rest I/O (the rear + * panel and the front mic) with Realtek ALC1220-VB. + * Here we provide two distinct names for making UCM profiles easier. + */ +{ + USB_DEVICE(0x0414, 0xa000), + .driver_info = (unsigned long) & (const struct snd_usb_audio_quirk) { + .vendor_name = "Gigabyte", + .product_name = "Aorus Master Front Headphone", + .profile_name = "Gigabyte-Aorus-Master-Front-Headphone", + .ifnum = QUIRK_NO_INTERFACE + } +}, +{ + USB_DEVICE(0x0414, 0xa001), + .driver_info = (unsigned long) & (const struct snd_usb_audio_quirk) { + .vendor_name = "Gigabyte", + .product_name = "Aorus Master Main Audio", + .profile_name = "Gigabyte-Aorus-Master-Main-Audio", + .ifnum = QUIRK_NO_INTERFACE + } +}, + #undef USB_DEVICE_VENDOR_SPEC diff --git a/tools/arch/x86/include/uapi/asm/unistd.h b/tools/arch/x86/include/uapi/asm/unistd.h index 196fdd02b8b1..30d7d04d72d6 100644 --- a/tools/arch/x86/include/uapi/asm/unistd.h +++ b/tools/arch/x86/include/uapi/asm/unistd.h @@ -3,7 +3,7 @@ #define _UAPI_ASM_X86_UNISTD_H /* x32 syscall flag bit */ -#define __X32_SYSCALL_BIT 0x40000000UL +#define __X32_SYSCALL_BIT 0x40000000 #ifndef __KERNEL__ # ifdef __i386__ diff --git a/tools/testing/selftests/bpf/verifier/bounds.c b/tools/testing/selftests/bpf/verifier/bounds.c index a253a064e6e0..58f4aa593b1b 100644 --- a/tools/testing/selftests/bpf/verifier/bounds.c +++ b/tools/testing/selftests/bpf/verifier/bounds.c @@ -238,7 +238,7 @@ BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), BPF_LD_MAP_FD(BPF_REG_1, 0), BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem), - BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 9), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 8), /* r1 = [0x00, 0xff] */ BPF_LDX_MEM(BPF_B, BPF_REG_1, BPF_REG_0, 0), BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 0xffffff80 >> 1), @@ -253,10 +253,6 @@ * [0xffff'ffff'0000'0080, 0xffff'ffff'ffff'ffff] */ BPF_ALU64_IMM(BPF_SUB, BPF_REG_1, 0xffffff80 >> 1), - /* r1 = 0 or - * [0x00ff'ffff'ff00'0000, 0x00ff'ffff'ffff'ffff] - */ - BPF_ALU64_IMM(BPF_RSH, BPF_REG_1, 8), /* error on OOB pointer computation */ BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1), /* exit */ @@ -265,8 +261,10 @@ }, .fixup_map_hash_8b = { 3 }, /* not actually fully unbounded, but the bound is very high */ - .errstr = "value 72057594021150720 makes map_value pointer be out of bounds", - .result = REJECT + .errstr_unpriv = "R1 has unknown scalar with mixed signed bounds, pointer arithmetic with it prohibited for !root", + .result_unpriv = REJECT, + .errstr = "value -4294967168 makes map_value pointer be out of bounds", + .result = REJECT, }, { "bounds check after truncation of boundary-crossing range (2)", @@ -276,7 +274,7 @@ BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), BPF_LD_MAP_FD(BPF_REG_1, 0), BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem), - BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 9), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 8), /* r1 = [0x00, 0xff] */ BPF_LDX_MEM(BPF_B, BPF_REG_1, BPF_REG_0, 0), BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 0xffffff80 >> 1), @@ -293,10 +291,6 @@ * [0xffff'ffff'0000'0080, 0xffff'ffff'ffff'ffff] */ BPF_ALU64_IMM(BPF_SUB, BPF_REG_1, 0xffffff80 >> 1), - /* r1 = 0 or - * [0x00ff'ffff'ff00'0000, 0x00ff'ffff'ffff'ffff] - */ - BPF_ALU64_IMM(BPF_RSH, BPF_REG_1, 8), /* error on OOB pointer computation */ BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1), /* exit */ @@ -305,8 +299,10 @@ }, .fixup_map_hash_8b = { 3 }, /* not actually fully unbounded, but the bound is very high */ - .errstr = "value 72057594021150720 makes map_value pointer be out of bounds", - .result = REJECT + .errstr_unpriv = "R1 has unknown scalar with mixed signed bounds, pointer arithmetic with it prohibited for !root", + .result_unpriv = REJECT, + .errstr = "value -4294967168 makes map_value pointer be out of bounds", + .result = REJECT, }, { "bounds check after wrapping 32-bit addition", @@ -539,3 +535,25 @@ }, .result = ACCEPT }, +{ + "assigning 32bit bounds to 64bit for wA = 0, wB = wA", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_8, BPF_REG_1, + offsetof(struct __sk_buff, data_end)), + BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_1, + offsetof(struct __sk_buff, data)), + BPF_MOV32_IMM(BPF_REG_9, 0), + BPF_MOV32_REG(BPF_REG_2, BPF_REG_9), + BPF_MOV64_REG(BPF_REG_6, BPF_REG_7), + BPF_ALU64_REG(BPF_ADD, BPF_REG_6, BPF_REG_2), + BPF_MOV64_REG(BPF_REG_3, BPF_REG_6), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_3, 8), + BPF_JMP_REG(BPF_JGT, BPF_REG_3, BPF_REG_8, 1), + BPF_LDX_MEM(BPF_W, BPF_REG_5, BPF_REG_6, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .result = ACCEPT, + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, +}, diff --git a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/fq_pie.json b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/fq_pie.json new file mode 100644 index 000000000000..1cda2e11b3ad --- /dev/null +++ b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/fq_pie.json @@ -0,0 +1,21 @@ +[ + { + "id": "83be", + "name": "Create FQ-PIE with invalid number of flows", + "category": [ + "qdisc", + "fq_pie" + ], + "setup": [ + "$IP link add dev $DUMMY type dummy || /bin/true" + ], + "cmdUnderTest": "$TC qdisc add dev $DUMMY root fq_pie flows 65536", + "expExitCode": "2", + "verifyCmd": "$TC qdisc show dev $DUMMY", + "matchPattern": "qdisc", + "matchCount": "0", + "teardown": [ + "$IP link del dev $DUMMY" + ] + } +] |