diff options
Diffstat (limited to 'arch')
276 files changed, 3856 insertions, 2504 deletions
diff --git a/arch/arm/boot/dts/amazon/alpine.dtsi b/arch/arm/boot/dts/amazon/alpine.dtsi index ff68dfb4eb78..90bd12feac01 100644 --- a/arch/arm/boot/dts/amazon/alpine.dtsi +++ b/arch/arm/boot/dts/amazon/alpine.dtsi @@ -167,7 +167,6 @@ msix: msix@fbe00000 { compatible = "al,alpine-msix"; reg = <0x0 0xfbe00000 0x0 0x100000>; - interrupt-controller; msi-controller; al,msi-base-spi = <96>; al,msi-num-spis = <64>; diff --git a/arch/arm/boot/dts/aspeed/aspeed-g4.dtsi b/arch/arm/boot/dts/aspeed/aspeed-g4.dtsi index 530491ae5eb2..857cb26ed6d7 100644 --- a/arch/arm/boot/dts/aspeed/aspeed-g4.dtsi +++ b/arch/arm/boot/dts/aspeed/aspeed-g4.dtsi @@ -466,7 +466,6 @@ i2c0: i2c-bus@40 { #address-cells = <1>; #size-cells = <0>; - #interrupt-cells = <1>; reg = <0x40 0x40>; compatible = "aspeed,ast2400-i2c-bus"; @@ -482,7 +481,6 @@ i2c1: i2c-bus@80 { #address-cells = <1>; #size-cells = <0>; - #interrupt-cells = <1>; reg = <0x80 0x40>; compatible = "aspeed,ast2400-i2c-bus"; @@ -498,7 +496,6 @@ i2c2: i2c-bus@c0 { #address-cells = <1>; #size-cells = <0>; - #interrupt-cells = <1>; reg = <0xc0 0x40>; compatible = "aspeed,ast2400-i2c-bus"; @@ -515,7 +512,6 @@ i2c3: i2c-bus@100 { #address-cells = <1>; #size-cells = <0>; - #interrupt-cells = <1>; reg = <0x100 0x40>; compatible = "aspeed,ast2400-i2c-bus"; @@ -532,7 +528,6 @@ i2c4: i2c-bus@140 { #address-cells = <1>; #size-cells = <0>; - #interrupt-cells = <1>; reg = <0x140 0x40>; compatible = "aspeed,ast2400-i2c-bus"; @@ -549,7 +544,6 @@ i2c5: i2c-bus@180 { #address-cells = <1>; #size-cells = <0>; - #interrupt-cells = <1>; reg = <0x180 0x40>; compatible = "aspeed,ast2400-i2c-bus"; @@ -566,7 +560,6 @@ i2c6: i2c-bus@1c0 { #address-cells = <1>; #size-cells = <0>; - #interrupt-cells = <1>; reg = <0x1c0 0x40>; compatible = "aspeed,ast2400-i2c-bus"; @@ -583,7 +576,6 @@ i2c7: i2c-bus@300 { #address-cells = <1>; #size-cells = <0>; - #interrupt-cells = <1>; reg = <0x300 0x40>; compatible = "aspeed,ast2400-i2c-bus"; @@ -600,7 +592,6 @@ i2c8: i2c-bus@340 { #address-cells = <1>; #size-cells = <0>; - #interrupt-cells = <1>; reg = <0x340 0x40>; compatible = "aspeed,ast2400-i2c-bus"; @@ -617,7 +608,6 @@ i2c9: i2c-bus@380 { #address-cells = <1>; #size-cells = <0>; - #interrupt-cells = <1>; reg = <0x380 0x40>; compatible = "aspeed,ast2400-i2c-bus"; @@ -634,7 +624,6 @@ i2c10: i2c-bus@3c0 { #address-cells = <1>; #size-cells = <0>; - #interrupt-cells = <1>; reg = <0x3c0 0x40>; compatible = "aspeed,ast2400-i2c-bus"; @@ -651,7 +640,6 @@ i2c11: i2c-bus@400 { #address-cells = <1>; #size-cells = <0>; - #interrupt-cells = <1>; reg = <0x400 0x40>; compatible = "aspeed,ast2400-i2c-bus"; @@ -668,7 +656,6 @@ i2c12: i2c-bus@440 { #address-cells = <1>; #size-cells = <0>; - #interrupt-cells = <1>; reg = <0x440 0x40>; compatible = "aspeed,ast2400-i2c-bus"; @@ -685,7 +672,6 @@ i2c13: i2c-bus@480 { #address-cells = <1>; #size-cells = <0>; - #interrupt-cells = <1>; reg = <0x480 0x40>; compatible = "aspeed,ast2400-i2c-bus"; diff --git a/arch/arm/boot/dts/aspeed/aspeed-g5.dtsi b/arch/arm/boot/dts/aspeed/aspeed-g5.dtsi index 04f98d1dbb97..e6f3cf3c721e 100644 --- a/arch/arm/boot/dts/aspeed/aspeed-g5.dtsi +++ b/arch/arm/boot/dts/aspeed/aspeed-g5.dtsi @@ -363,6 +363,7 @@ interrupts = <40>; reg = <0x1e780200 0x0100>; clocks = <&syscon ASPEED_CLK_APB>; + #interrupt-cells = <2>; interrupt-controller; bus-frequency = <12000000>; pinctrl-names = "default"; @@ -594,7 +595,6 @@ i2c0: i2c-bus@40 { #address-cells = <1>; #size-cells = <0>; - #interrupt-cells = <1>; reg = <0x40 0x40>; compatible = "aspeed,ast2500-i2c-bus"; @@ -610,7 +610,6 @@ i2c1: i2c-bus@80 { #address-cells = <1>; #size-cells = <0>; - #interrupt-cells = <1>; reg = <0x80 0x40>; compatible = "aspeed,ast2500-i2c-bus"; @@ -626,7 +625,6 @@ i2c2: i2c-bus@c0 { #address-cells = <1>; #size-cells = <0>; - #interrupt-cells = <1>; reg = <0xc0 0x40>; compatible = "aspeed,ast2500-i2c-bus"; @@ -643,7 +641,6 @@ i2c3: i2c-bus@100 { #address-cells = <1>; #size-cells = <0>; - #interrupt-cells = <1>; reg = <0x100 0x40>; compatible = "aspeed,ast2500-i2c-bus"; @@ -660,7 +657,6 @@ i2c4: i2c-bus@140 { #address-cells = <1>; #size-cells = <0>; - #interrupt-cells = <1>; reg = <0x140 0x40>; compatible = "aspeed,ast2500-i2c-bus"; @@ -677,7 +673,6 @@ i2c5: i2c-bus@180 { #address-cells = <1>; #size-cells = <0>; - #interrupt-cells = <1>; reg = <0x180 0x40>; compatible = "aspeed,ast2500-i2c-bus"; @@ -694,7 +689,6 @@ i2c6: i2c-bus@1c0 { #address-cells = <1>; #size-cells = <0>; - #interrupt-cells = <1>; reg = <0x1c0 0x40>; compatible = "aspeed,ast2500-i2c-bus"; @@ -711,7 +705,6 @@ i2c7: i2c-bus@300 { #address-cells = <1>; #size-cells = <0>; - #interrupt-cells = <1>; reg = <0x300 0x40>; compatible = "aspeed,ast2500-i2c-bus"; @@ -728,7 +721,6 @@ i2c8: i2c-bus@340 { #address-cells = <1>; #size-cells = <0>; - #interrupt-cells = <1>; reg = <0x340 0x40>; compatible = "aspeed,ast2500-i2c-bus"; @@ -745,7 +737,6 @@ i2c9: i2c-bus@380 { #address-cells = <1>; #size-cells = <0>; - #interrupt-cells = <1>; reg = <0x380 0x40>; compatible = "aspeed,ast2500-i2c-bus"; @@ -762,7 +753,6 @@ i2c10: i2c-bus@3c0 { #address-cells = <1>; #size-cells = <0>; - #interrupt-cells = <1>; reg = <0x3c0 0x40>; compatible = "aspeed,ast2500-i2c-bus"; @@ -779,7 +769,6 @@ i2c11: i2c-bus@400 { #address-cells = <1>; #size-cells = <0>; - #interrupt-cells = <1>; reg = <0x400 0x40>; compatible = "aspeed,ast2500-i2c-bus"; @@ -796,7 +785,6 @@ i2c12: i2c-bus@440 { #address-cells = <1>; #size-cells = <0>; - #interrupt-cells = <1>; reg = <0x440 0x40>; compatible = "aspeed,ast2500-i2c-bus"; @@ -813,7 +801,6 @@ i2c13: i2c-bus@480 { #address-cells = <1>; #size-cells = <0>; - #interrupt-cells = <1>; reg = <0x480 0x40>; compatible = "aspeed,ast2500-i2c-bus"; diff --git a/arch/arm/boot/dts/aspeed/aspeed-g6.dtsi b/arch/arm/boot/dts/aspeed/aspeed-g6.dtsi index c4d1faade8be..29f94696d8b1 100644 --- a/arch/arm/boot/dts/aspeed/aspeed-g6.dtsi +++ b/arch/arm/boot/dts/aspeed/aspeed-g6.dtsi @@ -474,6 +474,7 @@ reg = <0x1e780500 0x100>; interrupts = <GIC_SPI 51 IRQ_TYPE_LEVEL_HIGH>; clocks = <&syscon ASPEED_CLK_APB2>; + #interrupt-cells = <2>; interrupt-controller; bus-frequency = <12000000>; pinctrl-names = "default"; @@ -488,6 +489,7 @@ reg = <0x1e780600 0x100>; interrupts = <GIC_SPI 70 IRQ_TYPE_LEVEL_HIGH>; clocks = <&syscon ASPEED_CLK_APB2>; + #interrupt-cells = <2>; interrupt-controller; bus-frequency = <12000000>; pinctrl-names = "default"; @@ -902,7 +904,6 @@ i2c0: i2c-bus@80 { #address-cells = <1>; #size-cells = <0>; - #interrupt-cells = <1>; reg = <0x80 0x80>; compatible = "aspeed,ast2600-i2c-bus"; clocks = <&syscon ASPEED_CLK_APB2>; @@ -917,7 +918,6 @@ i2c1: i2c-bus@100 { #address-cells = <1>; #size-cells = <0>; - #interrupt-cells = <1>; reg = <0x100 0x80>; compatible = "aspeed,ast2600-i2c-bus"; clocks = <&syscon ASPEED_CLK_APB2>; @@ -932,7 +932,6 @@ i2c2: i2c-bus@180 { #address-cells = <1>; #size-cells = <0>; - #interrupt-cells = <1>; reg = <0x180 0x80>; compatible = "aspeed,ast2600-i2c-bus"; clocks = <&syscon ASPEED_CLK_APB2>; @@ -947,7 +946,6 @@ i2c3: i2c-bus@200 { #address-cells = <1>; #size-cells = <0>; - #interrupt-cells = <1>; reg = <0x200 0x80>; compatible = "aspeed,ast2600-i2c-bus"; clocks = <&syscon ASPEED_CLK_APB2>; @@ -962,7 +960,6 @@ i2c4: i2c-bus@280 { #address-cells = <1>; #size-cells = <0>; - #interrupt-cells = <1>; reg = <0x280 0x80>; compatible = "aspeed,ast2600-i2c-bus"; clocks = <&syscon ASPEED_CLK_APB2>; @@ -977,7 +974,6 @@ i2c5: i2c-bus@300 { #address-cells = <1>; #size-cells = <0>; - #interrupt-cells = <1>; reg = <0x300 0x80>; compatible = "aspeed,ast2600-i2c-bus"; clocks = <&syscon ASPEED_CLK_APB2>; @@ -992,7 +988,6 @@ i2c6: i2c-bus@380 { #address-cells = <1>; #size-cells = <0>; - #interrupt-cells = <1>; reg = <0x380 0x80>; compatible = "aspeed,ast2600-i2c-bus"; clocks = <&syscon ASPEED_CLK_APB2>; @@ -1007,7 +1002,6 @@ i2c7: i2c-bus@400 { #address-cells = <1>; #size-cells = <0>; - #interrupt-cells = <1>; reg = <0x400 0x80>; compatible = "aspeed,ast2600-i2c-bus"; clocks = <&syscon ASPEED_CLK_APB2>; @@ -1022,7 +1016,6 @@ i2c8: i2c-bus@480 { #address-cells = <1>; #size-cells = <0>; - #interrupt-cells = <1>; reg = <0x480 0x80>; compatible = "aspeed,ast2600-i2c-bus"; clocks = <&syscon ASPEED_CLK_APB2>; @@ -1037,7 +1030,6 @@ i2c9: i2c-bus@500 { #address-cells = <1>; #size-cells = <0>; - #interrupt-cells = <1>; reg = <0x500 0x80>; compatible = "aspeed,ast2600-i2c-bus"; clocks = <&syscon ASPEED_CLK_APB2>; @@ -1052,7 +1044,6 @@ i2c10: i2c-bus@580 { #address-cells = <1>; #size-cells = <0>; - #interrupt-cells = <1>; reg = <0x580 0x80>; compatible = "aspeed,ast2600-i2c-bus"; clocks = <&syscon ASPEED_CLK_APB2>; @@ -1067,7 +1058,6 @@ i2c11: i2c-bus@600 { #address-cells = <1>; #size-cells = <0>; - #interrupt-cells = <1>; reg = <0x600 0x80>; compatible = "aspeed,ast2600-i2c-bus"; clocks = <&syscon ASPEED_CLK_APB2>; @@ -1082,7 +1072,6 @@ i2c12: i2c-bus@680 { #address-cells = <1>; #size-cells = <0>; - #interrupt-cells = <1>; reg = <0x680 0x80>; compatible = "aspeed,ast2600-i2c-bus"; clocks = <&syscon ASPEED_CLK_APB2>; @@ -1097,7 +1086,6 @@ i2c13: i2c-bus@700 { #address-cells = <1>; #size-cells = <0>; - #interrupt-cells = <1>; reg = <0x700 0x80>; compatible = "aspeed,ast2600-i2c-bus"; clocks = <&syscon ASPEED_CLK_APB2>; @@ -1112,7 +1100,6 @@ i2c14: i2c-bus@780 { #address-cells = <1>; #size-cells = <0>; - #interrupt-cells = <1>; reg = <0x780 0x80>; compatible = "aspeed,ast2600-i2c-bus"; clocks = <&syscon ASPEED_CLK_APB2>; @@ -1127,7 +1114,6 @@ i2c15: i2c-bus@800 { #address-cells = <1>; #size-cells = <0>; - #interrupt-cells = <1>; reg = <0x800 0x80>; compatible = "aspeed,ast2600-i2c-bus"; clocks = <&syscon ASPEED_CLK_APB2>; diff --git a/arch/arm/boot/dts/broadcom/bcm-cygnus.dtsi b/arch/arm/boot/dts/broadcom/bcm-cygnus.dtsi index f9f79ed82518..07ca0d993c9f 100644 --- a/arch/arm/boot/dts/broadcom/bcm-cygnus.dtsi +++ b/arch/arm/boot/dts/broadcom/bcm-cygnus.dtsi @@ -167,6 +167,7 @@ #gpio-cells = <2>; gpio-controller; interrupt-controller; + #interrupt-cells = <2>; interrupt-parent = <&mailbox>; interrupts = <0>; }; @@ -247,6 +248,7 @@ gpio-controller; interrupts = <GIC_SPI 84 IRQ_TYPE_LEVEL_HIGH>; interrupt-controller; + #interrupt-cells = <2>; }; i2c1: i2c@1800b000 { @@ -518,6 +520,7 @@ gpio-controller; interrupt-controller; + #interrupt-cells = <2>; interrupts = <GIC_SPI 174 IRQ_TYPE_LEVEL_HIGH>; gpio-ranges = <&pinctrl 0 42 1>, <&pinctrl 1 44 3>, diff --git a/arch/arm/boot/dts/broadcom/bcm-hr2.dtsi b/arch/arm/boot/dts/broadcom/bcm-hr2.dtsi index 788a6806191a..75545b10ef2f 100644 --- a/arch/arm/boot/dts/broadcom/bcm-hr2.dtsi +++ b/arch/arm/boot/dts/broadcom/bcm-hr2.dtsi @@ -200,6 +200,7 @@ gpio-controller; ngpios = <4>; interrupt-controller; + #interrupt-cells = <2>; interrupts = <GIC_SPI 93 IRQ_TYPE_LEVEL_HIGH>; }; diff --git a/arch/arm/boot/dts/broadcom/bcm-nsp.dtsi b/arch/arm/boot/dts/broadcom/bcm-nsp.dtsi index 9d20ba3b1ffb..6a4482c93167 100644 --- a/arch/arm/boot/dts/broadcom/bcm-nsp.dtsi +++ b/arch/arm/boot/dts/broadcom/bcm-nsp.dtsi @@ -180,6 +180,7 @@ gpio-controller; ngpios = <32>; interrupt-controller; + #interrupt-cells = <2>; interrupts = <GIC_SPI 85 IRQ_TYPE_LEVEL_HIGH>; gpio-ranges = <&pinctrl 0 0 32>; }; @@ -352,6 +353,7 @@ gpio-controller; ngpios = <4>; interrupt-controller; + #interrupt-cells = <2>; interrupts = <GIC_SPI 87 IRQ_TYPE_LEVEL_HIGH>; }; diff --git a/arch/arm/boot/dts/intel/ixp/intel-ixp42x-gateway-7001.dts b/arch/arm/boot/dts/intel/ixp/intel-ixp42x-gateway-7001.dts index 4d70f6afd13a..6d5e69035f94 100644 --- a/arch/arm/boot/dts/intel/ixp/intel-ixp42x-gateway-7001.dts +++ b/arch/arm/boot/dts/intel/ixp/intel-ixp42x-gateway-7001.dts @@ -60,6 +60,8 @@ * We have slots (IDSEL) 1 and 2 with one assigned IRQ * each handling all IRQs. */ + #interrupt-cells = <1>; + interrupt-map-mask = <0xf800 0 0 7>; interrupt-map = /* IDSEL 1 */ <0x0800 0 0 1 &gpio0 11 IRQ_TYPE_LEVEL_LOW>, /* INT A on slot 1 is irq 11 */ diff --git a/arch/arm/boot/dts/intel/ixp/intel-ixp42x-goramo-multilink.dts b/arch/arm/boot/dts/intel/ixp/intel-ixp42x-goramo-multilink.dts index 9ec0169bacf8..5f4c849915db 100644 --- a/arch/arm/boot/dts/intel/ixp/intel-ixp42x-goramo-multilink.dts +++ b/arch/arm/boot/dts/intel/ixp/intel-ixp42x-goramo-multilink.dts @@ -89,6 +89,8 @@ * The slots have Ethernet, Ethernet, NEC and MPCI. * The IDSELs are 11, 12, 13, 14. */ + #interrupt-cells = <1>; + interrupt-map-mask = <0xf800 0 0 7>; interrupt-map = /* IDSEL 11 - Ethernet A */ <0x5800 0 0 1 &gpio0 4 IRQ_TYPE_LEVEL_LOW>, /* INT A on slot 11 is irq 4 */ diff --git a/arch/arm/boot/dts/marvell/kirkwood-l-50.dts b/arch/arm/boot/dts/marvell/kirkwood-l-50.dts index dffb9f84e67c..c841eb8e7fb1 100644 --- a/arch/arm/boot/dts/marvell/kirkwood-l-50.dts +++ b/arch/arm/boot/dts/marvell/kirkwood-l-50.dts @@ -65,6 +65,7 @@ gpio2: gpio-expander@20 { #gpio-cells = <2>; #interrupt-cells = <2>; + interrupt-controller; compatible = "semtech,sx1505q"; reg = <0x20>; @@ -79,6 +80,7 @@ gpio3: gpio-expander@21 { #gpio-cells = <2>; #interrupt-cells = <2>; + interrupt-controller; compatible = "semtech,sx1505q"; reg = <0x21>; diff --git a/arch/arm/boot/dts/nuvoton/nuvoton-wpcm450.dtsi b/arch/arm/boot/dts/nuvoton/nuvoton-wpcm450.dtsi index fd671c7a1e5d..6e1f0f164cb4 100644 --- a/arch/arm/boot/dts/nuvoton/nuvoton-wpcm450.dtsi +++ b/arch/arm/boot/dts/nuvoton/nuvoton-wpcm450.dtsi @@ -120,6 +120,7 @@ interrupts = <2 IRQ_TYPE_LEVEL_HIGH>, <3 IRQ_TYPE_LEVEL_HIGH>, <4 IRQ_TYPE_LEVEL_HIGH>; + #interrupt-cells = <2>; interrupt-controller; }; @@ -128,6 +129,7 @@ gpio-controller; #gpio-cells = <2>; interrupts = <5 IRQ_TYPE_LEVEL_HIGH>; + #interrupt-cells = <2>; interrupt-controller; }; diff --git a/arch/arm/boot/dts/nvidia/tegra30-apalis-v1.1.dtsi b/arch/arm/boot/dts/nvidia/tegra30-apalis-v1.1.dtsi index 1640763fd4af..ff0d684622f7 100644 --- a/arch/arm/boot/dts/nvidia/tegra30-apalis-v1.1.dtsi +++ b/arch/arm/boot/dts/nvidia/tegra30-apalis-v1.1.dtsi @@ -997,7 +997,6 @@ compatible = "st,stmpe811"; reg = <0x41>; irq-gpio = <&gpio TEGRA_GPIO(V, 0) GPIO_ACTIVE_LOW>; - interrupt-controller; id = <0>; blocks = <0x5>; irq-trigger = <0x1>; diff --git a/arch/arm/boot/dts/nvidia/tegra30-apalis.dtsi b/arch/arm/boot/dts/nvidia/tegra30-apalis.dtsi index 3b6fad273cab..d38f1dd38a90 100644 --- a/arch/arm/boot/dts/nvidia/tegra30-apalis.dtsi +++ b/arch/arm/boot/dts/nvidia/tegra30-apalis.dtsi @@ -980,7 +980,6 @@ compatible = "st,stmpe811"; reg = <0x41>; irq-gpio = <&gpio TEGRA_GPIO(V, 0) GPIO_ACTIVE_LOW>; - interrupt-controller; id = <0>; blocks = <0x5>; irq-trigger = <0x1>; diff --git a/arch/arm/boot/dts/nvidia/tegra30-colibri.dtsi b/arch/arm/boot/dts/nvidia/tegra30-colibri.dtsi index 4eb526fe9c55..81c8a5fd92cc 100644 --- a/arch/arm/boot/dts/nvidia/tegra30-colibri.dtsi +++ b/arch/arm/boot/dts/nvidia/tegra30-colibri.dtsi @@ -861,7 +861,6 @@ compatible = "st,stmpe811"; reg = <0x41>; irq-gpio = <&gpio TEGRA_GPIO(V, 0) GPIO_ACTIVE_LOW>; - interrupt-controller; id = <0>; blocks = <0x5>; irq-trigger = <0x1>; diff --git a/arch/arm/boot/dts/nxp/imx/imx6q-b850v3.dts b/arch/arm/boot/dts/nxp/imx/imx6q-b850v3.dts index db8c332df6a1..cad112e05475 100644 --- a/arch/arm/boot/dts/nxp/imx/imx6q-b850v3.dts +++ b/arch/arm/boot/dts/nxp/imx/imx6q-b850v3.dts @@ -227,7 +227,6 @@ #address-cells = <3>; #size-cells = <2>; - #interrupt-cells = <1>; bridge@2,1 { compatible = "pci10b5,8605"; @@ -235,7 +234,6 @@ #address-cells = <3>; #size-cells = <2>; - #interrupt-cells = <1>; /* Intel Corporation I210 Gigabit Network Connection */ ethernet@3,0 { @@ -250,7 +248,6 @@ #address-cells = <3>; #size-cells = <2>; - #interrupt-cells = <1>; /* Intel Corporation I210 Gigabit Network Connection */ switch_nic: ethernet@4,0 { diff --git a/arch/arm/boot/dts/nxp/imx/imx6q-bx50v3.dtsi b/arch/arm/boot/dts/nxp/imx/imx6q-bx50v3.dtsi index 99f4f6ac71d4..c1ae7c47b442 100644 --- a/arch/arm/boot/dts/nxp/imx/imx6q-bx50v3.dtsi +++ b/arch/arm/boot/dts/nxp/imx/imx6q-bx50v3.dtsi @@ -245,6 +245,7 @@ reg = <0x74>; gpio-controller; #gpio-cells = <2>; + #interrupt-cells = <2>; interrupt-controller; interrupt-parent = <&gpio2>; interrupts = <3 IRQ_TYPE_LEVEL_LOW>; @@ -390,7 +391,6 @@ #address-cells = <3>; #size-cells = <2>; - #interrupt-cells = <1>; }; }; diff --git a/arch/arm/boot/dts/nxp/imx/imx6qdl-apalis.dtsi b/arch/arm/boot/dts/nxp/imx/imx6qdl-apalis.dtsi index 2ae93f57fe5a..ea40623d12e5 100644 --- a/arch/arm/boot/dts/nxp/imx/imx6qdl-apalis.dtsi +++ b/arch/arm/boot/dts/nxp/imx/imx6qdl-apalis.dtsi @@ -626,7 +626,6 @@ blocks = <0x5>; id = <0>; interrupts = <10 IRQ_TYPE_LEVEL_LOW>; - interrupt-controller; interrupt-parent = <&gpio4>; irq-trigger = <0x1>; pinctrl-names = "default"; diff --git a/arch/arm/boot/dts/nxp/imx/imx6qdl-colibri.dtsi b/arch/arm/boot/dts/nxp/imx/imx6qdl-colibri.dtsi index 55c90f6393ad..d3a7a6eeb8e0 100644 --- a/arch/arm/boot/dts/nxp/imx/imx6qdl-colibri.dtsi +++ b/arch/arm/boot/dts/nxp/imx/imx6qdl-colibri.dtsi @@ -550,7 +550,6 @@ blocks = <0x5>; interrupts = <20 IRQ_TYPE_LEVEL_LOW>; interrupt-parent = <&gpio6>; - interrupt-controller; id = <0>; irq-trigger = <0x1>; pinctrl-names = "default"; diff --git a/arch/arm/boot/dts/nxp/imx/imx6qdl-emcon.dtsi b/arch/arm/boot/dts/nxp/imx/imx6qdl-emcon.dtsi index a63e73adc1fc..42b2ba23aefc 100644 --- a/arch/arm/boot/dts/nxp/imx/imx6qdl-emcon.dtsi +++ b/arch/arm/boot/dts/nxp/imx/imx6qdl-emcon.dtsi @@ -225,7 +225,6 @@ pinctrl-0 = <&pinctrl_pmic>; interrupt-parent = <&gpio2>; interrupts = <8 IRQ_TYPE_LEVEL_LOW>; - interrupt-controller; onkey { compatible = "dlg,da9063-onkey"; diff --git a/arch/arm/boot/dts/nxp/imx/imx6qdl-phytec-pfla02.dtsi b/arch/arm/boot/dts/nxp/imx/imx6qdl-phytec-pfla02.dtsi index 113974520d54..c0c47adc5866 100644 --- a/arch/arm/boot/dts/nxp/imx/imx6qdl-phytec-pfla02.dtsi +++ b/arch/arm/boot/dts/nxp/imx/imx6qdl-phytec-pfla02.dtsi @@ -124,6 +124,7 @@ reg = <0x58>; interrupt-parent = <&gpio2>; interrupts = <9 IRQ_TYPE_LEVEL_LOW>; /* active-low GPIO2_9 */ + #interrupt-cells = <2>; interrupt-controller; regulators { diff --git a/arch/arm/boot/dts/nxp/imx/imx6qdl-phytec-phycore-som.dtsi b/arch/arm/boot/dts/nxp/imx/imx6qdl-phytec-phycore-som.dtsi index 86b4269e0e01..85e278eb2016 100644 --- a/arch/arm/boot/dts/nxp/imx/imx6qdl-phytec-phycore-som.dtsi +++ b/arch/arm/boot/dts/nxp/imx/imx6qdl-phytec-phycore-som.dtsi @@ -100,6 +100,7 @@ interrupt-parent = <&gpio1>; interrupts = <2 IRQ_TYPE_LEVEL_LOW>; interrupt-controller; + #interrupt-cells = <2>; gpio-controller; #gpio-cells = <2>; diff --git a/arch/arm/boot/dts/nxp/imx/imx7d-pico-dwarf.dts b/arch/arm/boot/dts/nxp/imx/imx7d-pico-dwarf.dts index 12361fcbe24a..1b965652291b 100644 --- a/arch/arm/boot/dts/nxp/imx/imx7d-pico-dwarf.dts +++ b/arch/arm/boot/dts/nxp/imx/imx7d-pico-dwarf.dts @@ -63,6 +63,7 @@ gpio-controller; #gpio-cells = <2>; #interrupt-cells = <2>; + interrupt-controller; reg = <0x25>; }; diff --git a/arch/arm/boot/dts/nxp/imx/imx7s.dtsi b/arch/arm/boot/dts/nxp/imx/imx7s.dtsi index ebf7befcc11e..9c81c6baa2d3 100644 --- a/arch/arm/boot/dts/nxp/imx/imx7s.dtsi +++ b/arch/arm/boot/dts/nxp/imx/imx7s.dtsi @@ -834,16 +834,6 @@ <&clks IMX7D_LCDIF_PIXEL_ROOT_CLK>; clock-names = "pix", "axi"; status = "disabled"; - - port { - #address-cells = <1>; - #size-cells = <0>; - - lcdif_out_mipi_dsi: endpoint@0 { - reg = <0>; - remote-endpoint = <&mipi_dsi_in_lcdif>; - }; - }; }; mipi_csi: mipi-csi@30750000 { @@ -895,22 +885,6 @@ samsung,esc-clock-frequency = <20000000>; samsung,pll-clock-frequency = <24000000>; status = "disabled"; - - ports { - #address-cells = <1>; - #size-cells = <0>; - - port@0 { - reg = <0>; - #address-cells = <1>; - #size-cells = <0>; - - mipi_dsi_in_lcdif: endpoint@0 { - reg = <0>; - remote-endpoint = <&lcdif_out_mipi_dsi>; - }; - }; - }; }; }; diff --git a/arch/arm/boot/dts/nxp/vf/vf610-zii-dev-rev-b.dts b/arch/arm/boot/dts/nxp/vf/vf610-zii-dev-rev-b.dts index b0ed68af0546..029f49be40e3 100644 --- a/arch/arm/boot/dts/nxp/vf/vf610-zii-dev-rev-b.dts +++ b/arch/arm/boot/dts/nxp/vf/vf610-zii-dev-rev-b.dts @@ -338,6 +338,7 @@ reg = <0x22>; gpio-controller; #gpio-cells = <2>; + #interrupt-cells = <2>; interrupt-controller; interrupt-parent = <&gpio3>; interrupts = <2 IRQ_TYPE_LEVEL_LOW>; diff --git a/arch/arm/boot/dts/qcom/qcom-sdx55.dtsi b/arch/arm/boot/dts/qcom/qcom-sdx55.dtsi index 2045fc779f88..27429d0fedfb 100644 --- a/arch/arm/boot/dts/qcom/qcom-sdx55.dtsi +++ b/arch/arm/boot/dts/qcom/qcom-sdx55.dtsi @@ -340,10 +340,10 @@ "msi8"; #interrupt-cells = <1>; interrupt-map-mask = <0 0 0 0x7>; - interrupt-map = <0 0 0 1 &intc 0 0 0 141 IRQ_TYPE_LEVEL_HIGH>, /* int_a */ - <0 0 0 2 &intc 0 0 0 142 IRQ_TYPE_LEVEL_HIGH>, /* int_b */ - <0 0 0 3 &intc 0 0 0 143 IRQ_TYPE_LEVEL_HIGH>, /* int_c */ - <0 0 0 4 &intc 0 0 0 144 IRQ_TYPE_LEVEL_HIGH>; /* int_d */ + interrupt-map = <0 0 0 1 &intc 0 141 IRQ_TYPE_LEVEL_HIGH>, /* int_a */ + <0 0 0 2 &intc 0 142 IRQ_TYPE_LEVEL_HIGH>, /* int_b */ + <0 0 0 3 &intc 0 143 IRQ_TYPE_LEVEL_HIGH>, /* int_c */ + <0 0 0 4 &intc 0 144 IRQ_TYPE_LEVEL_HIGH>; /* int_d */ clocks = <&gcc GCC_PCIE_PIPE_CLK>, <&gcc GCC_PCIE_AUX_CLK>, diff --git a/arch/arm/boot/dts/renesas/r8a7790-lager.dts b/arch/arm/boot/dts/renesas/r8a7790-lager.dts index 2fba4d084001..8590981245a6 100644 --- a/arch/arm/boot/dts/renesas/r8a7790-lager.dts +++ b/arch/arm/boot/dts/renesas/r8a7790-lager.dts @@ -447,6 +447,7 @@ interrupt-parent = <&irqc0>; interrupts = <2 IRQ_TYPE_LEVEL_LOW>; interrupt-controller; + #interrupt-cells = <2>; rtc { compatible = "dlg,da9063-rtc"; diff --git a/arch/arm/boot/dts/renesas/r8a7790-stout.dts b/arch/arm/boot/dts/renesas/r8a7790-stout.dts index f9bc5b4f019d..683f7395fab0 100644 --- a/arch/arm/boot/dts/renesas/r8a7790-stout.dts +++ b/arch/arm/boot/dts/renesas/r8a7790-stout.dts @@ -347,6 +347,7 @@ interrupt-parent = <&irqc0>; interrupts = <2 IRQ_TYPE_LEVEL_LOW>; interrupt-controller; + #interrupt-cells = <2>; onkey { compatible = "dlg,da9063-onkey"; diff --git a/arch/arm/boot/dts/renesas/r8a7791-koelsch.dts b/arch/arm/boot/dts/renesas/r8a7791-koelsch.dts index e9c13bb03772..0efd9f98c75a 100644 --- a/arch/arm/boot/dts/renesas/r8a7791-koelsch.dts +++ b/arch/arm/boot/dts/renesas/r8a7791-koelsch.dts @@ -819,6 +819,7 @@ interrupt-parent = <&irqc0>; interrupts = <2 IRQ_TYPE_LEVEL_LOW>; interrupt-controller; + #interrupt-cells = <2>; rtc { compatible = "dlg,da9063-rtc"; diff --git a/arch/arm/boot/dts/renesas/r8a7791-porter.dts b/arch/arm/boot/dts/renesas/r8a7791-porter.dts index 7e8bc06715f6..93c86e921645 100644 --- a/arch/arm/boot/dts/renesas/r8a7791-porter.dts +++ b/arch/arm/boot/dts/renesas/r8a7791-porter.dts @@ -413,6 +413,7 @@ interrupt-parent = <&irqc0>; interrupts = <2 IRQ_TYPE_LEVEL_LOW>; interrupt-controller; + #interrupt-cells = <2>; watchdog { compatible = "dlg,da9063-watchdog"; diff --git a/arch/arm/boot/dts/renesas/r8a7792-blanche.dts b/arch/arm/boot/dts/renesas/r8a7792-blanche.dts index 4f9838cf97ee..540a9ad28f28 100644 --- a/arch/arm/boot/dts/renesas/r8a7792-blanche.dts +++ b/arch/arm/boot/dts/renesas/r8a7792-blanche.dts @@ -381,6 +381,7 @@ interrupt-parent = <&irqc>; interrupts = <2 IRQ_TYPE_LEVEL_LOW>; interrupt-controller; + #interrupt-cells = <2>; rtc { compatible = "dlg,da9063-rtc"; diff --git a/arch/arm/boot/dts/renesas/r8a7793-gose.dts b/arch/arm/boot/dts/renesas/r8a7793-gose.dts index 1744fdbf9e0c..1ea6c757893b 100644 --- a/arch/arm/boot/dts/renesas/r8a7793-gose.dts +++ b/arch/arm/boot/dts/renesas/r8a7793-gose.dts @@ -759,6 +759,7 @@ interrupt-parent = <&irqc0>; interrupts = <2 IRQ_TYPE_LEVEL_LOW>; interrupt-controller; + #interrupt-cells = <2>; rtc { compatible = "dlg,da9063-rtc"; diff --git a/arch/arm/boot/dts/renesas/r8a7794-alt.dts b/arch/arm/boot/dts/renesas/r8a7794-alt.dts index c0d067df22a0..b5ecafbb2e4d 100644 --- a/arch/arm/boot/dts/renesas/r8a7794-alt.dts +++ b/arch/arm/boot/dts/renesas/r8a7794-alt.dts @@ -453,6 +453,7 @@ interrupt-parent = <&gpio3>; interrupts = <31 IRQ_TYPE_LEVEL_LOW>; interrupt-controller; + #interrupt-cells = <2>; rtc { compatible = "dlg,da9063-rtc"; diff --git a/arch/arm/boot/dts/renesas/r8a7794-silk.dts b/arch/arm/boot/dts/renesas/r8a7794-silk.dts index 43d480a7f3ea..595e074085eb 100644 --- a/arch/arm/boot/dts/renesas/r8a7794-silk.dts +++ b/arch/arm/boot/dts/renesas/r8a7794-silk.dts @@ -439,6 +439,7 @@ interrupt-parent = <&gpio3>; interrupts = <31 IRQ_TYPE_LEVEL_LOW>; interrupt-controller; + #interrupt-cells = <2>; onkey { compatible = "dlg,da9063-onkey"; diff --git a/arch/arm/boot/dts/rockchip/rv1108.dtsi b/arch/arm/boot/dts/rockchip/rv1108.dtsi index abf3006f0a84..f3291f3bbc6f 100644 --- a/arch/arm/boot/dts/rockchip/rv1108.dtsi +++ b/arch/arm/boot/dts/rockchip/rv1108.dtsi @@ -196,7 +196,6 @@ pwm4: pwm@10280000 { compatible = "rockchip,rv1108-pwm", "rockchip,rk3288-pwm"; reg = <0x10280000 0x10>; - interrupts = <GIC_SPI 38 IRQ_TYPE_LEVEL_HIGH>; clocks = <&cru SCLK_PWM>, <&cru PCLK_PWM>; clock-names = "pwm", "pclk"; pinctrl-names = "default"; @@ -208,7 +207,6 @@ pwm5: pwm@10280010 { compatible = "rockchip,rv1108-pwm", "rockchip,rk3288-pwm"; reg = <0x10280010 0x10>; - interrupts = <GIC_SPI 38 IRQ_TYPE_LEVEL_HIGH>; clocks = <&cru SCLK_PWM>, <&cru PCLK_PWM>; clock-names = "pwm", "pclk"; pinctrl-names = "default"; @@ -220,7 +218,6 @@ pwm6: pwm@10280020 { compatible = "rockchip,rv1108-pwm", "rockchip,rk3288-pwm"; reg = <0x10280020 0x10>; - interrupts = <GIC_SPI 38 IRQ_TYPE_LEVEL_HIGH>; clocks = <&cru SCLK_PWM>, <&cru PCLK_PWM>; clock-names = "pwm", "pclk"; pinctrl-names = "default"; @@ -232,7 +229,6 @@ pwm7: pwm@10280030 { compatible = "rockchip,rv1108-pwm", "rockchip,rk3288-pwm"; reg = <0x10280030 0x10>; - interrupts = <GIC_SPI 38 IRQ_TYPE_LEVEL_HIGH>; clocks = <&cru SCLK_PWM>, <&cru PCLK_PWM>; clock-names = "pwm", "pclk"; pinctrl-names = "default"; @@ -386,7 +382,6 @@ pwm0: pwm@20040000 { compatible = "rockchip,rv1108-pwm", "rockchip,rk3288-pwm"; reg = <0x20040000 0x10>; - interrupts = <GIC_SPI 39 IRQ_TYPE_LEVEL_HIGH>; clocks = <&cru SCLK_PWM0_PMU>, <&cru PCLK_PWM0_PMU>; clock-names = "pwm", "pclk"; pinctrl-names = "default"; @@ -398,7 +393,6 @@ pwm1: pwm@20040010 { compatible = "rockchip,rv1108-pwm", "rockchip,rk3288-pwm"; reg = <0x20040010 0x10>; - interrupts = <GIC_SPI 39 IRQ_TYPE_LEVEL_HIGH>; clocks = <&cru SCLK_PWM0_PMU>, <&cru PCLK_PWM0_PMU>; clock-names = "pwm", "pclk"; pinctrl-names = "default"; @@ -410,7 +404,6 @@ pwm2: pwm@20040020 { compatible = "rockchip,rv1108-pwm", "rockchip,rk3288-pwm"; reg = <0x20040020 0x10>; - interrupts = <GIC_SPI 39 IRQ_TYPE_LEVEL_HIGH>; clocks = <&cru SCLK_PWM0_PMU>, <&cru PCLK_PWM0_PMU>; clock-names = "pwm", "pclk"; pinctrl-names = "default"; @@ -422,7 +415,6 @@ pwm3: pwm@20040030 { compatible = "rockchip,rv1108-pwm", "rockchip,rk3288-pwm"; reg = <0x20040030 0x10>; - interrupts = <GIC_SPI 39 IRQ_TYPE_LEVEL_HIGH>; clocks = <&cru SCLK_PWM0_PMU>, <&cru PCLK_PWM0_PMU>; clock-names = "pwm", "pclk"; pinctrl-names = "default"; diff --git a/arch/arm/boot/dts/st/stm32429i-eval.dts b/arch/arm/boot/dts/st/stm32429i-eval.dts index 576235ec3c51..afa417b34b25 100644 --- a/arch/arm/boot/dts/st/stm32429i-eval.dts +++ b/arch/arm/boot/dts/st/stm32429i-eval.dts @@ -222,7 +222,6 @@ reg = <0x42>; interrupts = <8 3>; interrupt-parent = <&gpioi>; - interrupt-controller; wakeup-source; stmpegpio: stmpe_gpio { diff --git a/arch/arm/boot/dts/st/stm32mp157c-dk2.dts b/arch/arm/boot/dts/st/stm32mp157c-dk2.dts index 510cca5acb79..7a701f7ef0c7 100644 --- a/arch/arm/boot/dts/st/stm32mp157c-dk2.dts +++ b/arch/arm/boot/dts/st/stm32mp157c-dk2.dts @@ -64,7 +64,6 @@ reg = <0x38>; interrupts = <2 2>; interrupt-parent = <&gpiof>; - interrupt-controller; touchscreen-size-x = <480>; touchscreen-size-y = <800>; status = "okay"; diff --git a/arch/arm/boot/dts/ti/omap/am5729-beagleboneai.dts b/arch/arm/boot/dts/ti/omap/am5729-beagleboneai.dts index c8e55642f9c6..3e834fc7e370 100644 --- a/arch/arm/boot/dts/ti/omap/am5729-beagleboneai.dts +++ b/arch/arm/boot/dts/ti/omap/am5729-beagleboneai.dts @@ -415,7 +415,6 @@ reg = <0x41>; interrupts = <30 IRQ_TYPE_LEVEL_LOW>; interrupt-parent = <&gpio2>; - interrupt-controller; id = <0>; blocks = <0x5>; irq-trigger = <0x1>; diff --git a/arch/arm/configs/imx_v6_v7_defconfig b/arch/arm/configs/imx_v6_v7_defconfig index 0a90583f9f01..8f9dbe8d9029 100644 --- a/arch/arm/configs/imx_v6_v7_defconfig +++ b/arch/arm/configs/imx_v6_v7_defconfig @@ -297,6 +297,7 @@ CONFIG_FB_MODE_HELPERS=y CONFIG_LCD_CLASS_DEVICE=y CONFIG_LCD_L4F00242T03=y CONFIG_LCD_PLATFORM=y +CONFIG_BACKLIGHT_CLASS_DEVICE=y CONFIG_BACKLIGHT_PWM=y CONFIG_BACKLIGHT_GPIO=y CONFIG_FRAMEBUFFER_CONSOLE=y diff --git a/arch/arm/include/asm/elf.h b/arch/arm/include/asm/elf.h index d68101655b74..9f21e170320f 100644 --- a/arch/arm/include/asm/elf.h +++ b/arch/arm/include/asm/elf.h @@ -4,7 +4,6 @@ #include <asm/auxvec.h> #include <asm/hwcap.h> -#include <asm/vdso_datapage.h> /* * ELF register definitions.. diff --git a/arch/arm/include/asm/vdso_datapage.h b/arch/arm/include/asm/vdso_datapage.h deleted file mode 100644 index bef68f59928d..000000000000 --- a/arch/arm/include/asm/vdso_datapage.h +++ /dev/null @@ -1,26 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * Adapted from arm64 version. - * - * Copyright (C) 2012 ARM Limited - */ -#ifndef __ASM_VDSO_DATAPAGE_H -#define __ASM_VDSO_DATAPAGE_H - -#ifdef __KERNEL__ - -#ifndef __ASSEMBLY__ - -#include <vdso/datapage.h> -#include <asm/page.h> - -union vdso_data_store { - struct vdso_data data[CS_BASES]; - u8 page[PAGE_SIZE]; -}; - -#endif /* !__ASSEMBLY__ */ - -#endif /* __KERNEL__ */ - -#endif /* __ASM_VDSO_DATAPAGE_H */ diff --git a/arch/arm/kernel/asm-offsets.c b/arch/arm/kernel/asm-offsets.c index 219cbc7e5d13..4915662842ff 100644 --- a/arch/arm/kernel/asm-offsets.c +++ b/arch/arm/kernel/asm-offsets.c @@ -21,10 +21,12 @@ #include <asm/mpu.h> #include <asm/procinfo.h> #include <asm/suspend.h> -#include <asm/vdso_datapage.h> #include <asm/hardware/cache-l2x0.h> #include <linux/kbuild.h> #include <linux/arm-smccc.h> + +#include <vdso/datapage.h> + #include "signal.h" /* diff --git a/arch/arm/kernel/vdso.c b/arch/arm/kernel/vdso.c index f297d66a8a76..d499ad461b00 100644 --- a/arch/arm/kernel/vdso.c +++ b/arch/arm/kernel/vdso.c @@ -21,7 +21,6 @@ #include <asm/cacheflush.h> #include <asm/page.h> #include <asm/vdso.h> -#include <asm/vdso_datapage.h> #include <clocksource/arm_arch_timer.h> #include <vdso/helpers.h> #include <vdso/vsyscall.h> @@ -35,9 +34,6 @@ extern char vdso_start[], vdso_end[]; /* Total number of pages needed for the data and text portions of the VDSO. */ unsigned int vdso_total_pages __ro_after_init; -/* - * The VDSO data page. - */ static union vdso_data_store vdso_data_store __page_aligned_data; struct vdso_data *vdso_data = vdso_data_store.data; diff --git a/arch/arm/mach-ep93xx/core.c b/arch/arm/mach-ep93xx/core.c index 71b113976420..8b1ec60a9a46 100644 --- a/arch/arm/mach-ep93xx/core.c +++ b/arch/arm/mach-ep93xx/core.c @@ -339,6 +339,7 @@ static struct gpiod_lookup_table ep93xx_i2c_gpiod_table = { GPIO_ACTIVE_HIGH | GPIO_OPEN_DRAIN), GPIO_LOOKUP_IDX("G", 0, NULL, 1, GPIO_ACTIVE_HIGH | GPIO_OPEN_DRAIN), + { } }, }; diff --git a/arch/arm64/boot/dts/allwinner/Makefile b/arch/arm64/boot/dts/allwinner/Makefile index 91d505b385de..1f1f8d865d0e 100644 --- a/arch/arm64/boot/dts/allwinner/Makefile +++ b/arch/arm64/boot/dts/allwinner/Makefile @@ -42,5 +42,6 @@ dtb-$(CONFIG_ARCH_SUNXI) += sun50i-h616-bigtreetech-cb1-manta.dtb dtb-$(CONFIG_ARCH_SUNXI) += sun50i-h616-bigtreetech-pi.dtb dtb-$(CONFIG_ARCH_SUNXI) += sun50i-h616-orangepi-zero2.dtb dtb-$(CONFIG_ARCH_SUNXI) += sun50i-h616-x96-mate.dtb +dtb-$(CONFIG_ARCH_SUNXI) += sun50i-h618-orangepi-zero2w.dtb dtb-$(CONFIG_ARCH_SUNXI) += sun50i-h618-orangepi-zero3.dtb dtb-$(CONFIG_ARCH_SUNXI) += sun50i-h618-transpeed-8k618-t.dtb diff --git a/arch/arm64/boot/dts/amazon/alpine-v2.dtsi b/arch/arm64/boot/dts/amazon/alpine-v2.dtsi index dccbba6e7f98..dbf2dce8d1d6 100644 --- a/arch/arm64/boot/dts/amazon/alpine-v2.dtsi +++ b/arch/arm64/boot/dts/amazon/alpine-v2.dtsi @@ -145,7 +145,6 @@ msix: msix@fbe00000 { compatible = "al,alpine-msix"; reg = <0x0 0xfbe00000 0x0 0x100000>; - interrupt-controller; msi-controller; al,msi-base-spi = <160>; al,msi-num-spis = <160>; diff --git a/arch/arm64/boot/dts/amazon/alpine-v3.dtsi b/arch/arm64/boot/dts/amazon/alpine-v3.dtsi index 39481d7fd7d4..3ea178acdddf 100644 --- a/arch/arm64/boot/dts/amazon/alpine-v3.dtsi +++ b/arch/arm64/boot/dts/amazon/alpine-v3.dtsi @@ -355,7 +355,6 @@ msix: msix@fbe00000 { compatible = "al,alpine-msix"; reg = <0x0 0xfbe00000 0x0 0x100000>; - interrupt-controller; msi-controller; al,msi-base-spi = <336>; al,msi-num-spis = <959>; diff --git a/arch/arm64/boot/dts/amlogic/amlogic-t7.dtsi b/arch/arm64/boot/dts/amlogic/amlogic-t7.dtsi index a03c7667d2b6..2bfe2c431611 100644 --- a/arch/arm64/boot/dts/amlogic/amlogic-t7.dtsi +++ b/arch/arm64/boot/dts/amlogic/amlogic-t7.dtsi @@ -171,6 +171,16 @@ }; }; + gpio_intc: interrupt-controller@4080 { + compatible = "amlogic,t7-gpio-intc", + "amlogic,meson-gpio-intc"; + reg = <0x0 0x4080 0x0 0x20>; + interrupt-controller; + #interrupt-cells = <2>; + amlogic,channel-interrupts = + <10 11 12 13 14 15 16 17 18 19 20 21>; + }; + uart_a: serial@78000 { compatible = "amlogic,t7-uart", "amlogic,meson-s4-uart"; reg = <0x0 0x78000 0x0 0x18>; diff --git a/arch/arm64/boot/dts/broadcom/northstar2/ns2.dtsi b/arch/arm64/boot/dts/broadcom/northstar2/ns2.dtsi index 9dcd25ec2c04..896d1f33b5b6 100644 --- a/arch/arm64/boot/dts/broadcom/northstar2/ns2.dtsi +++ b/arch/arm64/boot/dts/broadcom/northstar2/ns2.dtsi @@ -586,6 +586,7 @@ #gpio-cells = <2>; gpio-controller; interrupt-controller; + #interrupt-cells = <2>; interrupts = <GIC_SPI 400 IRQ_TYPE_LEVEL_HIGH>; }; diff --git a/arch/arm64/boot/dts/broadcom/stingray/stingray.dtsi b/arch/arm64/boot/dts/broadcom/stingray/stingray.dtsi index f049687d6b96..d8516ec0dae7 100644 --- a/arch/arm64/boot/dts/broadcom/stingray/stingray.dtsi +++ b/arch/arm64/boot/dts/broadcom/stingray/stingray.dtsi @@ -450,6 +450,7 @@ #gpio-cells = <2>; gpio-controller; interrupt-controller; + #interrupt-cells = <2>; interrupts = <GIC_SPI 183 IRQ_TYPE_LEVEL_HIGH>; gpio-ranges = <&pinmux 0 0 16>, <&pinmux 16 71 2>, diff --git a/arch/arm64/boot/dts/freescale/Makefile b/arch/arm64/boot/dts/freescale/Makefile index 2e027675d7bb..2cb0212b63c6 100644 --- a/arch/arm64/boot/dts/freescale/Makefile +++ b/arch/arm64/boot/dts/freescale/Makefile @@ -20,23 +20,41 @@ dtb-$(CONFIG_ARCH_LAYERSCAPE) += fsl-ls1046a-frwy.dtb dtb-$(CONFIG_ARCH_LAYERSCAPE) += fsl-ls1046a-qds.dtb dtb-$(CONFIG_ARCH_LAYERSCAPE) += fsl-ls1046a-rdb.dtb dtb-$(CONFIG_ARCH_LAYERSCAPE) += fsl-ls1046a-tqmls1046a-mbls10xxa.dtb +DTC_FLAGS_fsl-ls1088a-qds := -Wno-interrupt_map dtb-$(CONFIG_ARCH_LAYERSCAPE) += fsl-ls1088a-qds.dtb +DTC_FLAGS_fsl-ls1088a-rdb := -Wno-interrupt_map dtb-$(CONFIG_ARCH_LAYERSCAPE) += fsl-ls1088a-rdb.dtb +DTC_FLAGS_fsl-ls1088a-ten64 := -Wno-interrupt_map dtb-$(CONFIG_ARCH_LAYERSCAPE) += fsl-ls1088a-ten64.dtb +DTC_FLAGS_fsl-ls1088a-tqmls1088a-mbls10xxa := -Wno-interrupt_map dtb-$(CONFIG_ARCH_LAYERSCAPE) += fsl-ls1088a-tqmls1088a-mbls10xxa.dtb +DTC_FLAGS_fsl-ls2080a-qds := -Wno-interrupt_map dtb-$(CONFIG_ARCH_LAYERSCAPE) += fsl-ls2080a-qds.dtb +DTC_FLAGS_fsl-ls2080a-rdb := -Wno-interrupt_map dtb-$(CONFIG_ARCH_LAYERSCAPE) += fsl-ls2080a-rdb.dtb +DTC_FLAGS_fsl-ls2081a-rdb := -Wno-interrupt_map dtb-$(CONFIG_ARCH_LAYERSCAPE) += fsl-ls2081a-rdb.dtb +DTC_FLAGS_fsl-ls2080a-simu := -Wno-interrupt_map dtb-$(CONFIG_ARCH_LAYERSCAPE) += fsl-ls2080a-simu.dtb +DTC_FLAGS_fsl-ls2088a-qds := -Wno-interrupt_map dtb-$(CONFIG_ARCH_LAYERSCAPE) += fsl-ls2088a-qds.dtb +DTC_FLAGS_fsl-ls2088a-rdb := -Wno-interrupt_map dtb-$(CONFIG_ARCH_LAYERSCAPE) += fsl-ls2088a-rdb.dtb +DTC_FLAGS_fsl-lx2160a-bluebox3 := -Wno-interrupt_map dtb-$(CONFIG_ARCH_LAYERSCAPE) += fsl-lx2160a-bluebox3.dtb +DTC_FLAGS_fsl-lx2160a-bluebox3-rev-a := -Wno-interrupt_map dtb-$(CONFIG_ARCH_LAYERSCAPE) += fsl-lx2160a-bluebox3-rev-a.dtb +DTC_FLAGS_fsl-lx2160a-clearfog-cx := -Wno-interrupt_map dtb-$(CONFIG_ARCH_LAYERSCAPE) += fsl-lx2160a-clearfog-cx.dtb +DTC_FLAGS_fsl-lx2160a-honeycomb := -Wno-interrupt_map dtb-$(CONFIG_ARCH_LAYERSCAPE) += fsl-lx2160a-honeycomb.dtb +DTC_FLAGS_fsl-lx2160a-qds := -Wno-interrupt_map dtb-$(CONFIG_ARCH_LAYERSCAPE) += fsl-lx2160a-qds.dtb +DTC_FLAGS_fsl-lx2160a-rdb := -Wno-interrupt_map dtb-$(CONFIG_ARCH_LAYERSCAPE) += fsl-lx2160a-rdb.dtb +DTC_FLAGS_fsl-lx2162a-clearfog := -Wno-interrupt_map dtb-$(CONFIG_ARCH_LAYERSCAPE) += fsl-lx2162a-clearfog.dtb +DTC_FLAGS_fsl-lx2162a-qds := -Wno-interrupt_map dtb-$(CONFIG_ARCH_LAYERSCAPE) += fsl-lx2162a-qds.dtb fsl-ls1028a-qds-13bb-dtbs := fsl-ls1028a-qds.dtb fsl-ls1028a-qds-13bb.dtbo @@ -53,6 +71,7 @@ dtb-$(CONFIG_ARCH_LAYERSCAPE) += fsl-ls1028a-qds-85bb.dtb dtb-$(CONFIG_ARCH_LAYERSCAPE) += fsl-ls1028a-qds-899b.dtb dtb-$(CONFIG_ARCH_LAYERSCAPE) += fsl-ls1028a-qds-9999.dtb +DTC_FLAGS_fsl-lx2160a-tqmlx2160a-mblx2160a := -Wno-interrupt_map fsl-lx2160a-tqmlx2160a-mblx2160a-12-11-x-dtbs := fsl-lx2160a-tqmlx2160a-mblx2160a.dtb \ fsl-lx2160a-tqmlx2160a-mblx2160a_12_x_x.dtbo \ fsl-lx2160a-tqmlx2160a-mblx2160a_x_11_x.dtbo diff --git a/arch/arm64/boot/dts/freescale/imx8mn-var-som-symphony.dts b/arch/arm64/boot/dts/freescale/imx8mn-var-som-symphony.dts index f38ee2266b25..a6b94d1957c9 100644 --- a/arch/arm64/boot/dts/freescale/imx8mn-var-som-symphony.dts +++ b/arch/arm64/boot/dts/freescale/imx8mn-var-som-symphony.dts @@ -128,14 +128,9 @@ pinctrl-0 = <&pinctrl_ptn5150>; status = "okay"; - connector { - compatible = "usb-c-connector"; - label = "USB-C"; - - port { - typec1_dr_sw: endpoint { - remote-endpoint = <&usb1_drd_sw>; - }; + port { + typec1_dr_sw: endpoint { + remote-endpoint = <&usb1_drd_sw>; }; }; }; diff --git a/arch/arm64/boot/dts/freescale/imx8mp-data-modul-edm-sbc.dts b/arch/arm64/boot/dts/freescale/imx8mp-data-modul-edm-sbc.dts index d98a040860a4..5828c9d7821d 100644 --- a/arch/arm64/boot/dts/freescale/imx8mp-data-modul-edm-sbc.dts +++ b/arch/arm64/boot/dts/freescale/imx8mp-data-modul-edm-sbc.dts @@ -486,7 +486,7 @@ &uart4 { pinctrl-names = "default"; pinctrl-0 = <&pinctrl_uart4>; - status = "okay"; + status = "disabled"; }; &usb3_phy0 { diff --git a/arch/arm64/boot/dts/freescale/imx8mp-dhcom-pdk3.dts b/arch/arm64/boot/dts/freescale/imx8mp-dhcom-pdk3.dts index fea67a9282f0..b749e28e5ede 100644 --- a/arch/arm64/boot/dts/freescale/imx8mp-dhcom-pdk3.dts +++ b/arch/arm64/boot/dts/freescale/imx8mp-dhcom-pdk3.dts @@ -175,14 +175,10 @@ pinctrl-names = "default"; pinctrl-0 = <&pinctrl_ptn5150>; - connector { - compatible = "usb-c-connector"; - label = "USB-C"; - - port { - ptn5150_out_ep: endpoint { - remote-endpoint = <&dwc3_0_ep>; - }; + port { + + ptn5150_out_ep: endpoint { + remote-endpoint = <&dwc3_0_ep>; }; }; }; diff --git a/arch/arm64/boot/dts/freescale/imx8mp-dhcom-som.dtsi b/arch/arm64/boot/dts/freescale/imx8mp-dhcom-som.dtsi index 4ae4fdab461e..43f1d45ccc96 100644 --- a/arch/arm64/boot/dts/freescale/imx8mp-dhcom-som.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mp-dhcom-som.dtsi @@ -255,7 +255,7 @@ <&clk IMX8MP_AUDIO_PLL2_OUT>; assigned-clock-parents = <&clk IMX8MP_AUDIO_PLL2_OUT>; assigned-clock-rates = <13000000>, <13000000>, <156000000>; - reset-gpios = <&gpio3 21 GPIO_ACTIVE_HIGH>; + reset-gpios = <&gpio4 1 GPIO_ACTIVE_HIGH>; status = "disabled"; ports { diff --git a/arch/arm64/boot/dts/freescale/imx8mp-tqma8mpql-mba8mpxl.dts b/arch/arm64/boot/dts/freescale/imx8mp-tqma8mpql-mba8mpxl.dts index a2d5d19b2de0..86d3da36e4f3 100644 --- a/arch/arm64/boot/dts/freescale/imx8mp-tqma8mpql-mba8mpxl.dts +++ b/arch/arm64/boot/dts/freescale/imx8mp-tqma8mpql-mba8mpxl.dts @@ -184,6 +184,13 @@ enable-active-high; }; + reg_vcc_1v8: regulator-1v8 { + compatible = "regulator-fixed"; + regulator-name = "VCC_1V8"; + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <1800000>; + }; + reg_vcc_3v3: regulator-3v3 { compatible = "regulator-fixed"; regulator-name = "VCC_3V3"; @@ -480,7 +487,7 @@ clock-names = "mclk"; clocks = <&audio_blk_ctrl IMX8MP_CLK_AUDIOMIX_SAI3_MCLK1>; reset-gpios = <&gpio4 29 GPIO_ACTIVE_LOW>; - iov-supply = <®_vcc_3v3>; + iov-supply = <®_vcc_1v8>; ldoin-supply = <®_vcc_3v3>; }; diff --git a/arch/arm64/boot/dts/freescale/imx8mp.dtsi b/arch/arm64/boot/dts/freescale/imx8mp.dtsi index 76c73daf546b..39a550c1cd26 100644 --- a/arch/arm64/boot/dts/freescale/imx8mp.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mp.dtsi @@ -1820,7 +1820,7 @@ compatible = "fsl,imx8mp-ldb"; reg = <0x5c 0x4>, <0x128 0x4>; reg-names = "ldb", "lvds"; - clocks = <&clk IMX8MP_CLK_MEDIA_LDB>; + clocks = <&clk IMX8MP_CLK_MEDIA_LDB_ROOT>; clock-names = "ldb"; assigned-clocks = <&clk IMX8MP_CLK_MEDIA_LDB>; assigned-clock-parents = <&clk IMX8MP_VIDEO_PLL1_OUT>; diff --git a/arch/arm64/boot/dts/lg/lg1312.dtsi b/arch/arm64/boot/dts/lg/lg1312.dtsi index 48ec4ebec0a8..b864ffa74ea8 100644 --- a/arch/arm64/boot/dts/lg/lg1312.dtsi +++ b/arch/arm64/boot/dts/lg/lg1312.dtsi @@ -126,7 +126,6 @@ amba { #address-cells = <2>; #size-cells = <1>; - #interrupt-cells = <3>; compatible = "simple-bus"; interrupt-parent = <&gic>; diff --git a/arch/arm64/boot/dts/lg/lg1313.dtsi b/arch/arm64/boot/dts/lg/lg1313.dtsi index 3869460aa5dc..996fb39bb50c 100644 --- a/arch/arm64/boot/dts/lg/lg1313.dtsi +++ b/arch/arm64/boot/dts/lg/lg1313.dtsi @@ -126,7 +126,6 @@ amba { #address-cells = <2>; #size-cells = <1>; - #interrupt-cells = <3>; compatible = "simple-bus"; interrupt-parent = <&gic>; diff --git a/arch/arm64/boot/dts/marvell/armada-ap80x.dtsi b/arch/arm64/boot/dts/marvell/armada-ap80x.dtsi index 2c920e22cec2..7ec7c789d87e 100644 --- a/arch/arm64/boot/dts/marvell/armada-ap80x.dtsi +++ b/arch/arm64/boot/dts/marvell/armada-ap80x.dtsi @@ -138,7 +138,6 @@ odmi: odmi@300000 { compatible = "marvell,odmi-controller"; - interrupt-controller; msi-controller; marvell,odmi-frames = <4>; reg = <0x300000 0x4000>, diff --git a/arch/arm64/boot/dts/mediatek/mt8195-demo.dts b/arch/arm64/boot/dts/mediatek/mt8195-demo.dts index 69c7f3954ae5..4127cb84eba4 100644 --- a/arch/arm64/boot/dts/mediatek/mt8195-demo.dts +++ b/arch/arm64/boot/dts/mediatek/mt8195-demo.dts @@ -128,6 +128,7 @@ compatible = "mediatek,mt6360"; reg = <0x34>; interrupt-controller; + #interrupt-cells = <1>; interrupts-extended = <&pio 101 IRQ_TYPE_EDGE_FALLING>; interrupt-names = "IRQB"; diff --git a/arch/arm64/boot/dts/nvidia/tegra234-p3737-0000+p3701-0000.dts b/arch/arm64/boot/dts/nvidia/tegra234-p3737-0000+p3701-0000.dts index ea13c4a7027c..81a82933e350 100644 --- a/arch/arm64/boot/dts/nvidia/tegra234-p3737-0000+p3701-0000.dts +++ b/arch/arm64/boot/dts/nvidia/tegra234-p3737-0000+p3701-0000.dts @@ -175,7 +175,7 @@ status = "okay"; phy-handle = <&mgbe0_phy>; - phy-mode = "usxgmii"; + phy-mode = "10gbase-r"; mdio { #address-cells = <1>; diff --git a/arch/arm64/boot/dts/nvidia/tegra234.dtsi b/arch/arm64/boot/dts/nvidia/tegra234.dtsi index 3f16595d099c..d1bd328892af 100644 --- a/arch/arm64/boot/dts/nvidia/tegra234.dtsi +++ b/arch/arm64/boot/dts/nvidia/tegra234.dtsi @@ -1459,7 +1459,7 @@ <&mc TEGRA234_MEMORY_CLIENT_MGBEAWR &emc>; interconnect-names = "dma-mem", "write"; iommus = <&smmu_niso0 TEGRA234_SID_MGBE>; - power-domains = <&bpmp TEGRA234_POWER_DOMAIN_MGBEA>; + power-domains = <&bpmp TEGRA234_POWER_DOMAIN_MGBEB>; status = "disabled"; }; @@ -1493,7 +1493,7 @@ <&mc TEGRA234_MEMORY_CLIENT_MGBEBWR &emc>; interconnect-names = "dma-mem", "write"; iommus = <&smmu_niso0 TEGRA234_SID_MGBE_VF1>; - power-domains = <&bpmp TEGRA234_POWER_DOMAIN_MGBEB>; + power-domains = <&bpmp TEGRA234_POWER_DOMAIN_MGBEC>; status = "disabled"; }; @@ -1527,7 +1527,7 @@ <&mc TEGRA234_MEMORY_CLIENT_MGBECWR &emc>; interconnect-names = "dma-mem", "write"; iommus = <&smmu_niso0 TEGRA234_SID_MGBE_VF2>; - power-domains = <&bpmp TEGRA234_POWER_DOMAIN_MGBEC>; + power-domains = <&bpmp TEGRA234_POWER_DOMAIN_MGBED>; status = "disabled"; }; diff --git a/arch/arm64/boot/dts/qcom/ipq6018.dtsi b/arch/arm64/boot/dts/qcom/ipq6018.dtsi index 5e1277fea725..61c8fd49c966 100644 --- a/arch/arm64/boot/dts/qcom/ipq6018.dtsi +++ b/arch/arm64/boot/dts/qcom/ipq6018.dtsi @@ -830,10 +830,10 @@ #interrupt-cells = <1>; interrupt-map-mask = <0 0 0 0x7>; - interrupt-map = <0 0 0 1 &intc 0 75 IRQ_TYPE_LEVEL_HIGH>, /* int_a */ - <0 0 0 2 &intc 0 78 IRQ_TYPE_LEVEL_HIGH>, /* int_b */ - <0 0 0 3 &intc 0 79 IRQ_TYPE_LEVEL_HIGH>, /* int_c */ - <0 0 0 4 &intc 0 83 IRQ_TYPE_LEVEL_HIGH>; /* int_d */ + interrupt-map = <0 0 0 1 &intc 0 0 0 75 IRQ_TYPE_LEVEL_HIGH>, /* int_a */ + <0 0 0 2 &intc 0 0 0 78 IRQ_TYPE_LEVEL_HIGH>, /* int_b */ + <0 0 0 3 &intc 0 0 0 79 IRQ_TYPE_LEVEL_HIGH>, /* int_c */ + <0 0 0 4 &intc 0 0 0 83 IRQ_TYPE_LEVEL_HIGH>; /* int_d */ clocks = <&gcc GCC_SYS_NOC_PCIE0_AXI_CLK>, <&gcc GCC_PCIE0_AXI_M_CLK>, diff --git a/arch/arm64/boot/dts/qcom/ipq8074.dtsi b/arch/arm64/boot/dts/qcom/ipq8074.dtsi index cf295bed3299..26441447c866 100644 --- a/arch/arm64/boot/dts/qcom/ipq8074.dtsi +++ b/arch/arm64/boot/dts/qcom/ipq8074.dtsi @@ -814,13 +814,13 @@ interrupt-names = "msi"; #interrupt-cells = <1>; interrupt-map-mask = <0 0 0 0x7>; - interrupt-map = <0 0 0 1 &intc 0 142 + interrupt-map = <0 0 0 1 &intc 0 0 142 IRQ_TYPE_LEVEL_HIGH>, /* int_a */ - <0 0 0 2 &intc 0 143 + <0 0 0 2 &intc 0 0 143 IRQ_TYPE_LEVEL_HIGH>, /* int_b */ - <0 0 0 3 &intc 0 144 + <0 0 0 3 &intc 0 0 144 IRQ_TYPE_LEVEL_HIGH>, /* int_c */ - <0 0 0 4 &intc 0 145 + <0 0 0 4 &intc 0 0 145 IRQ_TYPE_LEVEL_HIGH>; /* int_d */ clocks = <&gcc GCC_SYS_NOC_PCIE1_AXI_CLK>, @@ -876,13 +876,13 @@ interrupt-names = "msi"; #interrupt-cells = <1>; interrupt-map-mask = <0 0 0 0x7>; - interrupt-map = <0 0 0 1 &intc 0 75 + interrupt-map = <0 0 0 1 &intc 0 0 75 IRQ_TYPE_LEVEL_HIGH>, /* int_a */ - <0 0 0 2 &intc 0 78 + <0 0 0 2 &intc 0 0 78 IRQ_TYPE_LEVEL_HIGH>, /* int_b */ - <0 0 0 3 &intc 0 79 + <0 0 0 3 &intc 0 0 79 IRQ_TYPE_LEVEL_HIGH>, /* int_c */ - <0 0 0 4 &intc 0 83 + <0 0 0 4 &intc 0 0 83 IRQ_TYPE_LEVEL_HIGH>; /* int_d */ clocks = <&gcc GCC_SYS_NOC_PCIE0_AXI_CLK>, diff --git a/arch/arm64/boot/dts/qcom/msm8996.dtsi b/arch/arm64/boot/dts/qcom/msm8996.dtsi index 8d41ed261adf..ee6f87c828ae 100644 --- a/arch/arm64/boot/dts/qcom/msm8996.dtsi +++ b/arch/arm64/boot/dts/qcom/msm8996.dtsi @@ -457,25 +457,6 @@ }; }; - mpm: interrupt-controller { - compatible = "qcom,mpm"; - qcom,rpm-msg-ram = <&apss_mpm>; - interrupts = <GIC_SPI 171 IRQ_TYPE_EDGE_RISING>; - mboxes = <&apcs_glb 1>; - interrupt-controller; - #interrupt-cells = <2>; - #power-domain-cells = <0>; - interrupt-parent = <&intc>; - qcom,mpm-pin-count = <96>; - qcom,mpm-pin-map = <2 184>, /* TSENS1 upper_lower_int */ - <52 243>, /* DWC3_PRI ss_phy_irq */ - <79 347>, /* DWC3_PRI hs_phy_irq */ - <80 352>, /* DWC3_SEC hs_phy_irq */ - <81 347>, /* QUSB2_PHY_PRI DP+DM */ - <82 352>, /* QUSB2_PHY_SEC DP+DM */ - <87 326>; /* SPMI */ - }; - psci { compatible = "arm,psci-1.0"; method = "smc"; @@ -765,15 +746,8 @@ }; rpm_msg_ram: sram@68000 { - compatible = "qcom,rpm-msg-ram", "mmio-sram"; + compatible = "qcom,rpm-msg-ram"; reg = <0x00068000 0x6000>; - #address-cells = <1>; - #size-cells = <1>; - ranges = <0 0x00068000 0x7000>; - - apss_mpm: sram@1b8 { - reg = <0x1b8 0x48>; - }; }; qfprom@74000 { @@ -856,8 +830,8 @@ reg = <0x004ad000 0x1000>, /* TM */ <0x004ac000 0x1000>; /* SROT */ #qcom,sensors = <8>; - interrupts-extended = <&mpm 2 IRQ_TYPE_LEVEL_HIGH>, - <&intc GIC_SPI 430 IRQ_TYPE_LEVEL_HIGH>; + interrupts = <GIC_SPI 184 IRQ_TYPE_LEVEL_HIGH>, + <GIC_SPI 430 IRQ_TYPE_LEVEL_HIGH>; interrupt-names = "uplow", "critical"; #thermal-sensor-cells = <1>; }; @@ -1363,7 +1337,6 @@ interrupts = <GIC_SPI 208 IRQ_TYPE_LEVEL_HIGH>; gpio-controller; gpio-ranges = <&tlmm 0 0 150>; - wakeup-parent = <&mpm>; #gpio-cells = <2>; interrupt-controller; #interrupt-cells = <2>; @@ -1891,7 +1864,7 @@ <0x0400a000 0x002100>; reg-names = "core", "chnls", "obsrvr", "intr", "cnfg"; interrupt-names = "periph_irq"; - interrupts-extended = <&mpm 87 IRQ_TYPE_LEVEL_HIGH>; + interrupts = <GIC_SPI 326 IRQ_TYPE_LEVEL_HIGH>; qcom,ee = <0>; qcom,channel = <0>; #address-cells = <2>; @@ -3052,8 +3025,8 @@ #size-cells = <1>; ranges; - interrupts-extended = <&mpm 79 IRQ_TYPE_LEVEL_HIGH>, - <&mpm 52 IRQ_TYPE_LEVEL_HIGH>; + interrupts = <GIC_SPI 347 IRQ_TYPE_LEVEL_HIGH>, + <GIC_SPI 243 IRQ_TYPE_LEVEL_HIGH>; interrupt-names = "hs_phy_irq", "ss_phy_irq"; clocks = <&gcc GCC_SYS_NOC_USB3_AXI_CLK>, diff --git a/arch/arm64/boot/dts/qcom/sc8280xp-crd.dts b/arch/arm64/boot/dts/qcom/sc8280xp-crd.dts index ffc4406422ae..41215567b3ae 100644 --- a/arch/arm64/boot/dts/qcom/sc8280xp-crd.dts +++ b/arch/arm64/boot/dts/qcom/sc8280xp-crd.dts @@ -563,6 +563,8 @@ }; &pcie4 { + max-link-speed = <2>; + perst-gpios = <&tlmm 141 GPIO_ACTIVE_LOW>; wake-gpios = <&tlmm 139 GPIO_ACTIVE_LOW>; diff --git a/arch/arm64/boot/dts/qcom/sc8280xp-lenovo-thinkpad-x13s.dts b/arch/arm64/boot/dts/qcom/sc8280xp-lenovo-thinkpad-x13s.dts index def3976bd5bb..eb657e544961 100644 --- a/arch/arm64/boot/dts/qcom/sc8280xp-lenovo-thinkpad-x13s.dts +++ b/arch/arm64/boot/dts/qcom/sc8280xp-lenovo-thinkpad-x13s.dts @@ -722,6 +722,8 @@ }; &pcie4 { + max-link-speed = <2>; + perst-gpios = <&tlmm 141 GPIO_ACTIVE_LOW>; wake-gpios = <&tlmm 139 GPIO_ACTIVE_LOW>; diff --git a/arch/arm64/boot/dts/qcom/sm6115.dtsi b/arch/arm64/boot/dts/qcom/sm6115.dtsi index 160e098f1075..f9849b8befbf 100644 --- a/arch/arm64/boot/dts/qcom/sm6115.dtsi +++ b/arch/arm64/boot/dts/qcom/sm6115.dtsi @@ -1304,6 +1304,9 @@ &config_noc SLAVE_QUP_0 RPM_ALWAYS_TAG>, <&system_noc MASTER_QUP_0 RPM_ALWAYS_TAG &bimc SLAVE_EBI_CH0 RPM_ALWAYS_TAG>; + interconnect-names = "qup-core", + "qup-config", + "qup-memory"; #address-cells = <1>; #size-cells = <0>; status = "disabled"; diff --git a/arch/arm64/boot/dts/qcom/sm8650-mtp.dts b/arch/arm64/boot/dts/qcom/sm8650-mtp.dts index 9d916edb1c73..be133a3d5cbe 100644 --- a/arch/arm64/boot/dts/qcom/sm8650-mtp.dts +++ b/arch/arm64/boot/dts/qcom/sm8650-mtp.dts @@ -622,7 +622,7 @@ &tlmm { /* Reserved I/Os for NFC */ - gpio-reserved-ranges = <32 8>; + gpio-reserved-ranges = <32 8>, <74 1>; disp0_reset_n_active: disp0-reset-n-active-state { pins = "gpio133"; diff --git a/arch/arm64/boot/dts/qcom/sm8650-qrd.dts b/arch/arm64/boot/dts/qcom/sm8650-qrd.dts index 592a67a47c78..b9151c2ddf2e 100644 --- a/arch/arm64/boot/dts/qcom/sm8650-qrd.dts +++ b/arch/arm64/boot/dts/qcom/sm8650-qrd.dts @@ -659,7 +659,7 @@ &tlmm { /* Reserved I/Os for NFC */ - gpio-reserved-ranges = <32 8>; + gpio-reserved-ranges = <32 8>, <74 1>; bt_default: bt-default-state { bt-en-pins { diff --git a/arch/arm64/boot/dts/renesas/ulcb-kf.dtsi b/arch/arm64/boot/dts/renesas/ulcb-kf.dtsi index 3885ef3454ff..50de17e4fb3f 100644 --- a/arch/arm64/boot/dts/renesas/ulcb-kf.dtsi +++ b/arch/arm64/boot/dts/renesas/ulcb-kf.dtsi @@ -234,6 +234,7 @@ gpio-controller; #gpio-cells = <2>; interrupt-controller; + #interrupt-cells = <2>; interrupt-parent = <&gpio6>; interrupts = <8 IRQ_TYPE_EDGE_FALLING>; @@ -294,6 +295,7 @@ gpio-controller; #gpio-cells = <2>; interrupt-controller; + #interrupt-cells = <2>; interrupt-parent = <&gpio6>; interrupts = <4 IRQ_TYPE_EDGE_FALLING>; }; @@ -314,6 +316,7 @@ gpio-controller; #gpio-cells = <2>; interrupt-controller; + #interrupt-cells = <2>; interrupt-parent = <&gpio7>; interrupts = <3 IRQ_TYPE_EDGE_FALLING>; }; @@ -324,6 +327,7 @@ gpio-controller; #gpio-cells = <2>; interrupt-controller; + #interrupt-cells = <2>; interrupt-parent = <&gpio5>; interrupts = <9 IRQ_TYPE_EDGE_FALLING>; }; diff --git a/arch/arm64/boot/dts/rockchip/px30.dtsi b/arch/arm64/boot/dts/rockchip/px30.dtsi index d0905515399b..9137dd76e72c 100644 --- a/arch/arm64/boot/dts/rockchip/px30.dtsi +++ b/arch/arm64/boot/dts/rockchip/px30.dtsi @@ -631,6 +631,7 @@ clock-names = "spiclk", "apb_pclk"; dmas = <&dmac 12>, <&dmac 13>; dma-names = "tx", "rx"; + num-cs = <2>; pinctrl-names = "default"; pinctrl-0 = <&spi0_clk &spi0_csn &spi0_miso &spi0_mosi>; #address-cells = <1>; @@ -646,6 +647,7 @@ clock-names = "spiclk", "apb_pclk"; dmas = <&dmac 14>, <&dmac 15>; dma-names = "tx", "rx"; + num-cs = <2>; pinctrl-names = "default"; pinctrl-0 = <&spi1_clk &spi1_csn0 &spi1_csn1 &spi1_miso &spi1_mosi>; #address-cells = <1>; diff --git a/arch/arm64/boot/dts/rockchip/rk3328.dtsi b/arch/arm64/boot/dts/rockchip/rk3328.dtsi index fb5dcf6e9327..7b4c15c4a9c3 100644 --- a/arch/arm64/boot/dts/rockchip/rk3328.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3328.dtsi @@ -488,7 +488,6 @@ pwm3: pwm@ff1b0030 { compatible = "rockchip,rk3328-pwm"; reg = <0x0 0xff1b0030 0x0 0x10>; - interrupts = <GIC_SPI 50 IRQ_TYPE_LEVEL_HIGH>; clocks = <&cru SCLK_PWM>, <&cru PCLK_PWM>; clock-names = "pwm", "pclk"; pinctrl-names = "default"; diff --git a/arch/arm64/boot/dts/rockchip/rk3588-coolpi-cm5-evb.dts b/arch/arm64/boot/dts/rockchip/rk3588-coolpi-cm5-evb.dts index d4c70835e0fe..a4946cdc3bb3 100644 --- a/arch/arm64/boot/dts/rockchip/rk3588-coolpi-cm5-evb.dts +++ b/arch/arm64/boot/dts/rockchip/rk3588-coolpi-cm5-evb.dts @@ -72,7 +72,7 @@ vin-supply = <&vcc3v3_sys>; }; - vcc5v0_usb30_host: vcc5v0-usb30-host-regulator { + vcc5v0_usb_host1: vcc5v0_usb_host2: vcc5v0-usb-host-regulator { compatible = "regulator-fixed"; regulator-name = "vcc5v0_host"; regulator-boot-on; @@ -114,6 +114,7 @@ status = "okay"; }; +/* Standard pcie */ &pcie3x2 { reset-gpios = <&gpio3 RK_PB0 GPIO_ACTIVE_HIGH>; vpcie3v3-supply = <&vcc3v3_sys>; @@ -122,6 +123,7 @@ /* M.2 M-Key ssd */ &pcie3x4 { + num-lanes = <2>; reset-gpios = <&gpio4 RK_PB6 GPIO_ACTIVE_HIGH>; vpcie3v3-supply = <&vcc3v3_sys>; status = "okay"; @@ -188,12 +190,12 @@ }; &u2phy2_host { - phy-supply = <&vcc5v0_usb30_host>; + phy-supply = <&vcc5v0_usb_host1>; status = "okay"; }; &u2phy3_host { - phy-supply = <&vcc5v0_usb30_host>; + phy-supply = <&vcc5v0_usb_host2>; status = "okay"; }; diff --git a/arch/arm64/boot/dts/rockchip/rk3588-coolpi-cm5.dtsi b/arch/arm64/boot/dts/rockchip/rk3588-coolpi-cm5.dtsi index 0b02f4d6e003..cce1c8e83587 100644 --- a/arch/arm64/boot/dts/rockchip/rk3588-coolpi-cm5.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3588-coolpi-cm5.dtsi @@ -16,8 +16,8 @@ aliases { mmc0 = &sdhci; - mmc1 = &sdio; - mmc2 = &sdmmc; + mmc1 = &sdmmc; + mmc2 = &sdio; serial2 = &uart2; }; diff --git a/arch/arm64/boot/dts/rockchip/rk3588-evb1-v10.dts b/arch/arm64/boot/dts/rockchip/rk3588-evb1-v10.dts index ac7c677b0fb9..de30c2632b8e 100644 --- a/arch/arm64/boot/dts/rockchip/rk3588-evb1-v10.dts +++ b/arch/arm64/boot/dts/rockchip/rk3588-evb1-v10.dts @@ -448,6 +448,7 @@ <&rk806_dvs2_null>, <&rk806_dvs3_null>; pinctrl-names = "default"; spi-max-frequency = <1000000>; + system-power-controller; vcc1-supply = <&vcc5v0_sys>; vcc2-supply = <&vcc5v0_sys>; diff --git a/arch/arm64/boot/dts/rockchip/rk3588-jaguar.dts b/arch/arm64/boot/dts/rockchip/rk3588-jaguar.dts index 4ce70fb75a30..39d65002add1 100644 --- a/arch/arm64/boot/dts/rockchip/rk3588-jaguar.dts +++ b/arch/arm64/boot/dts/rockchip/rk3588-jaguar.dts @@ -62,7 +62,6 @@ compatible = "gpio-leds"; pinctrl-names = "default"; pinctrl-0 = <&led1_pin>; - status = "okay"; /* LED1 on PCB */ led-1 { diff --git a/arch/arm64/boot/dts/rockchip/rk3588-nanopc-t6.dts b/arch/arm64/boot/dts/rockchip/rk3588-nanopc-t6.dts index d7722772ecd8..997b516c2533 100644 --- a/arch/arm64/boot/dts/rockchip/rk3588-nanopc-t6.dts +++ b/arch/arm64/boot/dts/rockchip/rk3588-nanopc-t6.dts @@ -189,19 +189,19 @@ cpu-supply = <&vdd_cpu_lit_s0>; }; -&cpu_b0{ +&cpu_b0 { cpu-supply = <&vdd_cpu_big0_s0>; }; -&cpu_b1{ +&cpu_b1 { cpu-supply = <&vdd_cpu_big0_s0>; }; -&cpu_b2{ +&cpu_b2 { cpu-supply = <&vdd_cpu_big1_s0>; }; -&cpu_b3{ +&cpu_b3 { cpu-supply = <&vdd_cpu_big1_s0>; }; diff --git a/arch/arm64/boot/dts/rockchip/rk3588s-coolpi-4b.dts b/arch/arm64/boot/dts/rockchip/rk3588s-coolpi-4b.dts index ef4f058c20ff..e037bf9db75a 100644 --- a/arch/arm64/boot/dts/rockchip/rk3588s-coolpi-4b.dts +++ b/arch/arm64/boot/dts/rockchip/rk3588s-coolpi-4b.dts @@ -19,8 +19,8 @@ aliases { mmc0 = &sdhci; - mmc1 = &sdio; - mmc2 = &sdmmc; + mmc1 = &sdmmc; + mmc2 = &sdio; }; analog-sound { diff --git a/arch/arm64/boot/dts/rockchip/rk3588s-indiedroid-nova.dts b/arch/arm64/boot/dts/rockchip/rk3588s-indiedroid-nova.dts index dc677f29a9c7..3c2278886851 100644 --- a/arch/arm64/boot/dts/rockchip/rk3588s-indiedroid-nova.dts +++ b/arch/arm64/boot/dts/rockchip/rk3588s-indiedroid-nova.dts @@ -195,13 +195,13 @@ &gpio1 { gpio-line-names = /* GPIO1 A0-A7 */ - "HEADER_27_3v3", "HEADER_28_3v3", "", "", + "HEADER_27_3v3", "", "", "", "HEADER_29_1v8", "", "HEADER_7_1v8", "", /* GPIO1 B0-B7 */ "", "HEADER_31_1v8", "HEADER_33_1v8", "", "HEADER_11_1v8", "HEADER_13_1v8", "", "", /* GPIO1 C0-C7 */ - "", "", "", "", + "", "HEADER_28_3v3", "", "", "", "", "", "", /* GPIO1 D0-D7 */ "", "", "", "", @@ -225,11 +225,11 @@ &gpio4 { gpio-line-names = /* GPIO4 A0-A7 */ - "", "", "HEADER_37_3v3", "HEADER_32_3v3", - "HEADER_36_3v3", "", "HEADER_35_3v3", "HEADER_38_3v3", + "", "", "HEADER_37_3v3", "HEADER_8_3v3", + "HEADER_10_3v3", "", "HEADER_32_3v3", "HEADER_35_3v3", /* GPIO4 B0-B7 */ "", "", "", "HEADER_40_3v3", - "HEADER_8_3v3", "HEADER_10_3v3", "", "", + "HEADER_38_3v3", "HEADER_36_3v3", "", "", /* GPIO4 C0-C7 */ "", "", "", "", "", "", "", "", diff --git a/arch/arm64/crypto/aes-neonbs-glue.c b/arch/arm64/crypto/aes-neonbs-glue.c index bac4cabef607..467ac2f768ac 100644 --- a/arch/arm64/crypto/aes-neonbs-glue.c +++ b/arch/arm64/crypto/aes-neonbs-glue.c @@ -227,8 +227,19 @@ static int ctr_encrypt(struct skcipher_request *req) src += blocks * AES_BLOCK_SIZE; } if (nbytes && walk.nbytes == walk.total) { + u8 buf[AES_BLOCK_SIZE]; + u8 *d = dst; + + if (unlikely(nbytes < AES_BLOCK_SIZE)) + src = dst = memcpy(buf + sizeof(buf) - nbytes, + src, nbytes); + neon_aes_ctr_encrypt(dst, src, ctx->enc, ctx->key.rounds, nbytes, walk.iv); + + if (unlikely(nbytes < AES_BLOCK_SIZE)) + memcpy(d, dst, nbytes); + nbytes = 0; } kernel_neon_end(); diff --git a/arch/arm64/include/asm/fpsimd.h b/arch/arm64/include/asm/fpsimd.h index 481d94416d69..b67b89c54e1c 100644 --- a/arch/arm64/include/asm/fpsimd.h +++ b/arch/arm64/include/asm/fpsimd.h @@ -386,6 +386,7 @@ extern void sme_alloc(struct task_struct *task, bool flush); extern unsigned int sme_get_vl(void); extern int sme_set_current_vl(unsigned long arg); extern int sme_get_current_vl(void); +extern void sme_suspend_exit(void); /* * Return how many bytes of memory are required to store the full SME @@ -421,6 +422,7 @@ static inline int sme_max_vl(void) { return 0; } static inline int sme_max_virtualisable_vl(void) { return 0; } static inline int sme_set_current_vl(unsigned long arg) { return -EINVAL; } static inline int sme_get_current_vl(void) { return -EINVAL; } +static inline void sme_suspend_exit(void) { } static inline size_t sme_state_size(struct task_struct const *task) { diff --git a/arch/arm64/include/asm/jump_label.h b/arch/arm64/include/asm/jump_label.h index b360c4c2b5e7..6aafbb789991 100644 --- a/arch/arm64/include/asm/jump_label.h +++ b/arch/arm64/include/asm/jump_label.h @@ -15,10 +15,6 @@ #define JUMP_LABEL_NOP_SIZE AARCH64_INSN_SIZE -/* - * Prefer the constraint "S" to support PIC with GCC. Clang before 19 does not - * support "S" on a symbol with a constant offset, so we use "i" as a fallback. - */ static __always_inline bool arch_static_branch(struct static_key * const key, const bool branch) { @@ -27,9 +23,9 @@ static __always_inline bool arch_static_branch(struct static_key * const key, " .pushsection __jump_table, \"aw\" \n\t" " .align 3 \n\t" " .long 1b - ., %l[l_yes] - . \n\t" - " .quad (%[key] - .) + %[bit0] \n\t" + " .quad %c0 - . \n\t" " .popsection \n\t" - : : [key]"Si"(key), [bit0]"i"(branch) : : l_yes); + : : "i"(&((char *)key)[branch]) : : l_yes); return false; l_yes: @@ -44,9 +40,9 @@ static __always_inline bool arch_static_branch_jump(struct static_key * const ke " .pushsection __jump_table, \"aw\" \n\t" " .align 3 \n\t" " .long 1b - ., %l[l_yes] - . \n\t" - " .quad (%[key] - .) + %[bit0] \n\t" + " .quad %c0 - . \n\t" " .popsection \n\t" - : : [key]"Si"(key), [bit0]"i"(branch) : : l_yes); + : : "i"(&((char *)key)[branch]) : : l_yes); return false; l_yes: diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c index 25ceaee6b025..f27acca550d5 100644 --- a/arch/arm64/kernel/fpsimd.c +++ b/arch/arm64/kernel/fpsimd.c @@ -1311,6 +1311,22 @@ void __init sme_setup(void) get_sme_default_vl()); } +void sme_suspend_exit(void) +{ + u64 smcr = 0; + + if (!system_supports_sme()) + return; + + if (system_supports_fa64()) + smcr |= SMCR_ELx_FA64; + if (system_supports_sme2()) + smcr |= SMCR_ELx_EZT0; + + write_sysreg_s(smcr, SYS_SMCR_EL1); + write_sysreg_s(0, SYS_SMPRI_EL1); +} + #endif /* CONFIG_ARM64_SME */ static void sve_init_regs(void) diff --git a/arch/arm64/kernel/stacktrace.c b/arch/arm64/kernel/stacktrace.c index 7f88028a00c0..b2a60e0bcfd2 100644 --- a/arch/arm64/kernel/stacktrace.c +++ b/arch/arm64/kernel/stacktrace.c @@ -247,7 +247,7 @@ struct kunwind_consume_entry_data { void *cookie; }; -static bool +static __always_inline bool arch_kunwind_consume_entry(const struct kunwind_state *state, void *cookie) { struct kunwind_consume_entry_data *data = cookie; diff --git a/arch/arm64/kernel/suspend.c b/arch/arm64/kernel/suspend.c index eca4d0435211..eaaff94329cd 100644 --- a/arch/arm64/kernel/suspend.c +++ b/arch/arm64/kernel/suspend.c @@ -12,6 +12,7 @@ #include <asm/daifflags.h> #include <asm/debug-monitors.h> #include <asm/exec.h> +#include <asm/fpsimd.h> #include <asm/mte.h> #include <asm/memory.h> #include <asm/mmu_context.h> @@ -80,6 +81,8 @@ void notrace __cpu_suspend_exit(void) */ spectre_v4_enable_mitigation(NULL); + sme_suspend_exit(); + /* Restore additional feature-specific configuration */ ptrauth_suspend_exit(); } diff --git a/arch/arm64/kernel/vdso.c b/arch/arm64/kernel/vdso.c index 5562daf38a22..89b6e7840002 100644 --- a/arch/arm64/kernel/vdso.c +++ b/arch/arm64/kernel/vdso.c @@ -69,10 +69,7 @@ static struct vdso_abi_info vdso_info[] __ro_after_init = { /* * The vDSO data page. */ -static union { - struct vdso_data data[CS_BASES]; - u8 page[PAGE_SIZE]; -} vdso_data_store __page_aligned_data; +static union vdso_data_store vdso_data_store __page_aligned_data; struct vdso_data *vdso_data = vdso_data_store.data; static int vdso_mremap(const struct vm_special_mapping *sm, diff --git a/arch/arm64/kvm/vgic/vgic-its.c b/arch/arm64/kvm/vgic/vgic-its.c index e2764d0ffa9f..28a93074eca1 100644 --- a/arch/arm64/kvm/vgic/vgic-its.c +++ b/arch/arm64/kvm/vgic/vgic-its.c @@ -468,6 +468,9 @@ static int its_sync_lpi_pending_table(struct kvm_vcpu *vcpu) } irq = vgic_get_irq(vcpu->kvm, NULL, intids[i]); + if (!irq) + continue; + raw_spin_lock_irqsave(&irq->irq_lock, flags); irq->pending_latch = pendmask & (1U << bit_nr); vgic_queue_irq_unlock(vcpu->kvm, irq, flags); @@ -1432,6 +1435,8 @@ static int vgic_its_cmd_handle_movall(struct kvm *kvm, struct vgic_its *its, for (i = 0; i < irq_count; i++) { irq = vgic_get_irq(kvm, NULL, intids[i]); + if (!irq) + continue; update_affinity(irq, vcpu2); diff --git a/arch/csky/include/asm/vdso.h b/arch/csky/include/asm/vdso.h index bdce581b5fcb..181a15edafe8 100644 --- a/arch/csky/include/asm/vdso.h +++ b/arch/csky/include/asm/vdso.h @@ -5,11 +5,6 @@ #include <linux/types.h> -#ifndef GENERIC_TIME_VSYSCALL -struct vdso_data { -}; -#endif - /* * The VDSO symbols are mapped into Linux so we can just use regular symbol * addressing to get their offsets in userspace. The symbols are mapped at an diff --git a/arch/csky/kernel/vdso.c b/arch/csky/kernel/vdso.c index 16c20d64d165..2ca886e4a458 100644 --- a/arch/csky/kernel/vdso.c +++ b/arch/csky/kernel/vdso.c @@ -8,25 +8,15 @@ #include <linux/slab.h> #include <asm/page.h> -#ifdef GENERIC_TIME_VSYSCALL #include <vdso/datapage.h> -#else -#include <asm/vdso.h> -#endif extern char vdso_start[], vdso_end[]; static unsigned int vdso_pages; static struct page **vdso_pagelist; -/* - * The vDSO data page. - */ -static union { - struct vdso_data data; - u8 page[PAGE_SIZE]; -} vdso_data_store __page_aligned_data; -struct vdso_data *vdso_data = &vdso_data_store.data; +static union vdso_data_store vdso_data_store __page_aligned_data; +struct vdso_data *vdso_data = vdso_data_store.data; static int __init vdso_init(void) { diff --git a/arch/loongarch/boot/dts/loongson-2k0500-ref.dts b/arch/loongarch/boot/dts/loongson-2k0500-ref.dts index b38071a4d0b0..8aefb0c12672 100644 --- a/arch/loongarch/boot/dts/loongson-2k0500-ref.dts +++ b/arch/loongarch/boot/dts/loongson-2k0500-ref.dts @@ -60,7 +60,7 @@ #address-cells = <1>; #size-cells = <0>; - eeprom@57{ + eeprom@57 { compatible = "atmel,24c16"; reg = <0x57>; pagesize = <16>; diff --git a/arch/loongarch/boot/dts/loongson-2k1000-ref.dts b/arch/loongarch/boot/dts/loongson-2k1000-ref.dts index 132a2d1ea8bc..ed4d32434041 100644 --- a/arch/loongarch/boot/dts/loongson-2k1000-ref.dts +++ b/arch/loongarch/boot/dts/loongson-2k1000-ref.dts @@ -78,7 +78,7 @@ #address-cells = <1>; #size-cells = <0>; - eeprom@57{ + eeprom@57 { compatible = "atmel,24c16"; reg = <0x57>; pagesize = <16>; diff --git a/arch/loongarch/kernel/setup.c b/arch/loongarch/kernel/setup.c index edf2bba80130..634ef17fd38b 100644 --- a/arch/loongarch/kernel/setup.c +++ b/arch/loongarch/kernel/setup.c @@ -357,6 +357,8 @@ void __init platform_init(void) acpi_gbl_use_default_register_widths = false; acpi_boot_table_init(); #endif + + early_init_fdt_scan_reserved_mem(); unflatten_and_copy_device_tree(); #ifdef CONFIG_NUMA @@ -390,8 +392,6 @@ static void __init arch_mem_init(char **cmdline_p) check_kernel_sections_mem(); - early_init_fdt_scan_reserved_mem(); - /* * In order to reduce the possibility of kernel panic when failed to * get IO TLB memory under CONFIG_SWIOTLB, it is better to allocate diff --git a/arch/loongarch/kernel/smp.c b/arch/loongarch/kernel/smp.c index 2b49d30eb7c0..aabee0b280fe 100644 --- a/arch/loongarch/kernel/smp.c +++ b/arch/loongarch/kernel/smp.c @@ -88,6 +88,73 @@ void show_ipi_list(struct seq_file *p, int prec) } } +static inline void set_cpu_core_map(int cpu) +{ + int i; + + cpumask_set_cpu(cpu, &cpu_core_setup_map); + + for_each_cpu(i, &cpu_core_setup_map) { + if (cpu_data[cpu].package == cpu_data[i].package) { + cpumask_set_cpu(i, &cpu_core_map[cpu]); + cpumask_set_cpu(cpu, &cpu_core_map[i]); + } + } +} + +static inline void set_cpu_sibling_map(int cpu) +{ + int i; + + cpumask_set_cpu(cpu, &cpu_sibling_setup_map); + + for_each_cpu(i, &cpu_sibling_setup_map) { + if (cpus_are_siblings(cpu, i)) { + cpumask_set_cpu(i, &cpu_sibling_map[cpu]); + cpumask_set_cpu(cpu, &cpu_sibling_map[i]); + } + } +} + +static inline void clear_cpu_sibling_map(int cpu) +{ + int i; + + for_each_cpu(i, &cpu_sibling_setup_map) { + if (cpus_are_siblings(cpu, i)) { + cpumask_clear_cpu(i, &cpu_sibling_map[cpu]); + cpumask_clear_cpu(cpu, &cpu_sibling_map[i]); + } + } + + cpumask_clear_cpu(cpu, &cpu_sibling_setup_map); +} + +/* + * Calculate a new cpu_foreign_map mask whenever a + * new cpu appears or disappears. + */ +void calculate_cpu_foreign_map(void) +{ + int i, k, core_present; + cpumask_t temp_foreign_map; + + /* Re-calculate the mask */ + cpumask_clear(&temp_foreign_map); + for_each_online_cpu(i) { + core_present = 0; + for_each_cpu(k, &temp_foreign_map) + if (cpus_are_siblings(i, k)) + core_present = 1; + if (!core_present) + cpumask_set_cpu(i, &temp_foreign_map); + } + + for_each_online_cpu(i) + cpumask_andnot(&cpu_foreign_map[i], + &temp_foreign_map, &cpu_sibling_map[i]); +} + /* Send mailbox buffer via Mail_Send */ static void csr_mail_send(uint64_t data, int cpu, int mailbox) { @@ -303,6 +370,7 @@ int loongson_cpu_disable(void) numa_remove_cpu(cpu); #endif set_cpu_online(cpu, false); + clear_cpu_sibling_map(cpu); calculate_cpu_foreign_map(); local_irq_save(flags); irq_migrate_all_off_this_cpu(); @@ -337,6 +405,7 @@ void __noreturn arch_cpu_idle_dead(void) addr = iocsr_read64(LOONGARCH_IOCSR_MBUF0); } while (addr == 0); + local_irq_disable(); init_fn = (void *)TO_CACHE(addr); iocsr_write32(0xffffffff, LOONGARCH_IOCSR_IPI_CLEAR); @@ -379,59 +448,6 @@ static int __init ipi_pm_init(void) core_initcall(ipi_pm_init); #endif -static inline void set_cpu_sibling_map(int cpu) -{ - int i; - - cpumask_set_cpu(cpu, &cpu_sibling_setup_map); - - for_each_cpu(i, &cpu_sibling_setup_map) { - if (cpus_are_siblings(cpu, i)) { - cpumask_set_cpu(i, &cpu_sibling_map[cpu]); - cpumask_set_cpu(cpu, &cpu_sibling_map[i]); - } - } -} - -static inline void set_cpu_core_map(int cpu) -{ - int i; - - cpumask_set_cpu(cpu, &cpu_core_setup_map); - - for_each_cpu(i, &cpu_core_setup_map) { - if (cpu_data[cpu].package == cpu_data[i].package) { - cpumask_set_cpu(i, &cpu_core_map[cpu]); - cpumask_set_cpu(cpu, &cpu_core_map[i]); - } - } -} - -/* - * Calculate a new cpu_foreign_map mask whenever a - * new cpu appears or disappears. - */ -void calculate_cpu_foreign_map(void) -{ - int i, k, core_present; - cpumask_t temp_foreign_map; - - /* Re-calculate the mask */ - cpumask_clear(&temp_foreign_map); - for_each_online_cpu(i) { - core_present = 0; - for_each_cpu(k, &temp_foreign_map) - if (cpus_are_siblings(i, k)) - core_present = 1; - if (!core_present) - cpumask_set_cpu(i, &temp_foreign_map); - } - - for_each_online_cpu(i) - cpumask_andnot(&cpu_foreign_map[i], - &temp_foreign_map, &cpu_sibling_map[i]); -} - /* Preload SMP state for boot cpu */ void smp_prepare_boot_cpu(void) { diff --git a/arch/loongarch/kernel/vdso.c b/arch/loongarch/kernel/vdso.c index 14941e4be66d..90dfccb41c14 100644 --- a/arch/loongarch/kernel/vdso.c +++ b/arch/loongarch/kernel/vdso.c @@ -21,15 +21,13 @@ #include <asm/vdso.h> #include <vdso/helpers.h> #include <vdso/vsyscall.h> +#include <vdso/datapage.h> #include <generated/vdso-offsets.h> extern char vdso_start[], vdso_end[]; /* Kernel-provided data used by the VDSO. */ -static union { - u8 page[PAGE_SIZE]; - struct vdso_data data[CS_BASES]; -} generic_vdso_data __page_aligned_data; +static union vdso_data_store generic_vdso_data __page_aligned_data; static union { u8 page[LOONGARCH_VDSO_DATA_SIZE]; diff --git a/arch/loongarch/kvm/vcpu.c b/arch/loongarch/kvm/vcpu.c index 27701991886d..36106922b5d7 100644 --- a/arch/loongarch/kvm/vcpu.c +++ b/arch/loongarch/kvm/vcpu.c @@ -298,74 +298,73 @@ static int _kvm_setcsr(struct kvm_vcpu *vcpu, unsigned int id, u64 val) return ret; } -static int _kvm_get_cpucfg(int id, u64 *v) +static int _kvm_get_cpucfg_mask(int id, u64 *v) { - int ret = 0; - - if (id < 0 && id >= KVM_MAX_CPUCFG_REGS) + if (id < 0 || id >= KVM_MAX_CPUCFG_REGS) return -EINVAL; switch (id) { case 2: - /* Return CPUCFG2 features which have been supported by KVM */ + /* CPUCFG2 features unconditionally supported by KVM */ *v = CPUCFG2_FP | CPUCFG2_FPSP | CPUCFG2_FPDP | CPUCFG2_FPVERS | CPUCFG2_LLFTP | CPUCFG2_LLFTPREV | CPUCFG2_LAM; /* - * If LSX is supported by CPU, it is also supported by KVM, - * as we implement it. + * For the ISA extensions listed below, if one is supported + * by the host, then it is also supported by KVM. */ if (cpu_has_lsx) *v |= CPUCFG2_LSX; - /* - * if LASX is supported by CPU, it is also supported by KVM, - * as we implement it. - */ if (cpu_has_lasx) *v |= CPUCFG2_LASX; - break; + return 0; default: - ret = -EINVAL; - break; + /* + * No restrictions on other valid CPUCFG IDs' values, but + * CPUCFG data is limited to 32 bits as the LoongArch ISA + * manual says (Volume 1, Section 2.2.10.5 "CPUCFG"). + */ + *v = U32_MAX; + return 0; } - return ret; } static int kvm_check_cpucfg(int id, u64 val) { - u64 mask; - int ret = 0; - - if (id < 0 && id >= KVM_MAX_CPUCFG_REGS) - return -EINVAL; + int ret; + u64 mask = 0; - if (_kvm_get_cpucfg(id, &mask)) + ret = _kvm_get_cpucfg_mask(id, &mask); + if (ret) return ret; + if (val & ~mask) + /* Unsupported features and/or the higher 32 bits should not be set */ + return -EINVAL; + switch (id) { case 2: - /* CPUCFG2 features checking */ - if (val & ~mask) - /* The unsupported features should not be set */ - ret = -EINVAL; - else if (!(val & CPUCFG2_LLFTP)) - /* The LLFTP must be set, as guest must has a constant timer */ - ret = -EINVAL; - else if ((val & CPUCFG2_FP) && (!(val & CPUCFG2_FPSP) || !(val & CPUCFG2_FPDP))) - /* Single and double float point must both be set when enable FP */ - ret = -EINVAL; - else if ((val & CPUCFG2_LSX) && !(val & CPUCFG2_FP)) - /* FP should be set when enable LSX */ - ret = -EINVAL; - else if ((val & CPUCFG2_LASX) && !(val & CPUCFG2_LSX)) - /* LSX, FP should be set when enable LASX, and FP has been checked before. */ - ret = -EINVAL; - break; + if (!(val & CPUCFG2_LLFTP)) + /* Guests must have a constant timer */ + return -EINVAL; + if ((val & CPUCFG2_FP) && (!(val & CPUCFG2_FPSP) || !(val & CPUCFG2_FPDP))) + /* Single and double float point must both be set when FP is enabled */ + return -EINVAL; + if ((val & CPUCFG2_LSX) && !(val & CPUCFG2_FP)) + /* LSX architecturally implies FP but val does not satisfy that */ + return -EINVAL; + if ((val & CPUCFG2_LASX) && !(val & CPUCFG2_LSX)) + /* LASX architecturally implies LSX and FP but val does not satisfy that */ + return -EINVAL; + return 0; default: - break; + /* + * Values for the other CPUCFG IDs are not being further validated + * besides the mask check above. + */ + return 0; } - return ret; } static int kvm_get_one_reg(struct kvm_vcpu *vcpu, @@ -566,7 +565,7 @@ static int kvm_loongarch_get_cpucfg_attr(struct kvm_vcpu *vcpu, uint64_t val; uint64_t __user *uaddr = (uint64_t __user *)attr->addr; - ret = _kvm_get_cpucfg(attr->attr, &val); + ret = _kvm_get_cpucfg_mask(attr->attr, &val); if (ret) return ret; diff --git a/arch/m68k/emu/nfblock.c b/arch/m68k/emu/nfblock.c index a708fbd5a844..642fb80c5c4e 100644 --- a/arch/m68k/emu/nfblock.c +++ b/arch/m68k/emu/nfblock.c @@ -96,6 +96,9 @@ static const struct block_device_operations nfhd_ops = { static int __init nfhd_init_one(int id, u32 blocks, u32 bsize) { + struct queue_limits lim = { + .logical_block_size = bsize, + }; struct nfhd_device *dev; int dev_id = id - NFHD_DEV_OFFSET; int err = -ENOMEM; @@ -117,9 +120,11 @@ static int __init nfhd_init_one(int id, u32 blocks, u32 bsize) dev->bsize = bsize; dev->bshift = ffs(bsize) - 10; - dev->disk = blk_alloc_disk(NUMA_NO_NODE); - if (!dev->disk) + dev->disk = blk_alloc_disk(&lim, NUMA_NO_NODE); + if (IS_ERR(dev->disk)) { + err = PTR_ERR(dev->disk); goto free_dev; + } dev->disk->major = major_num; dev->disk->first_minor = dev_id * 16; @@ -128,7 +133,6 @@ static int __init nfhd_init_one(int id, u32 blocks, u32 bsize) dev->disk->private_data = dev; sprintf(dev->disk->disk_name, "nfhd%u", dev_id); set_capacity(dev->disk, (sector_t)blocks * (bsize / 512)); - blk_queue_logical_block_size(dev->disk->queue, bsize); err = add_disk(dev->disk); if (err) goto out_cleanup_disk; diff --git a/arch/mips/include/asm/vdso.h b/arch/mips/include/asm/vdso.h index cc7b516129a8..afb03d45bcd0 100644 --- a/arch/mips/include/asm/vdso.h +++ b/arch/mips/include/asm/vdso.h @@ -50,9 +50,4 @@ extern struct mips_vdso_image vdso_image_o32; extern struct mips_vdso_image vdso_image_n32; #endif -union mips_vdso_data { - struct vdso_data data[CS_BASES]; - u8 page[PAGE_SIZE]; -}; - #endif /* __ASM_VDSO_H */ diff --git a/arch/mips/kernel/vdso.c b/arch/mips/kernel/vdso.c index f6d40e43f108..dda36fa26307 100644 --- a/arch/mips/kernel/vdso.c +++ b/arch/mips/kernel/vdso.c @@ -24,7 +24,7 @@ #include <vdso/vsyscall.h> /* Kernel-provided data used by the VDSO. */ -static union mips_vdso_data mips_vdso_data __page_aligned_data; +static union vdso_data_store mips_vdso_data __page_aligned_data; struct vdso_data *vdso_data = mips_vdso_data.data; /* diff --git a/arch/parisc/include/asm/kprobes.h b/arch/parisc/include/asm/kprobes.h index 0a175ac87698..0f42f5c8e3b6 100644 --- a/arch/parisc/include/asm/kprobes.h +++ b/arch/parisc/include/asm/kprobes.h @@ -10,9 +10,10 @@ #ifndef _PARISC_KPROBES_H #define _PARISC_KPROBES_H +#include <asm-generic/kprobes.h> + #ifdef CONFIG_KPROBES -#include <asm-generic/kprobes.h> #include <linux/types.h> #include <linux/ptrace.h> #include <linux/notifier.h> diff --git a/arch/parisc/kernel/ftrace.c b/arch/parisc/kernel/ftrace.c index d1defb9ede70..621a4b386ae4 100644 --- a/arch/parisc/kernel/ftrace.c +++ b/arch/parisc/kernel/ftrace.c @@ -78,7 +78,7 @@ asmlinkage void notrace __hot ftrace_function_trampoline(unsigned long parent, #endif } -#ifdef CONFIG_FUNCTION_GRAPH_TRACER +#if defined(CONFIG_DYNAMIC_FTRACE) && defined(CONFIG_FUNCTION_GRAPH_TRACER) int ftrace_enable_ftrace_graph_caller(void) { static_key_enable(&ftrace_graph_enable.key); diff --git a/arch/parisc/kernel/processor.c b/arch/parisc/kernel/processor.c index e95a977ba5f3..bf73562706b2 100644 --- a/arch/parisc/kernel/processor.c +++ b/arch/parisc/kernel/processor.c @@ -172,7 +172,6 @@ static int __init processor_probe(struct parisc_device *dev) p->cpu_num = cpu_info.cpu_num; p->cpu_loc = cpu_info.cpu_loc; - set_cpu_possible(cpuid, true); store_cpu_topology(cpuid); #ifdef CONFIG_SMP @@ -474,13 +473,6 @@ static struct parisc_driver cpu_driver __refdata = { */ void __init processor_init(void) { - unsigned int cpu; - reset_cpu_topology(); - - /* reset possible mask. We will mark those which are possible. */ - for_each_possible_cpu(cpu) - set_cpu_possible(cpu, false); - register_parisc_driver(&cpu_driver); } diff --git a/arch/parisc/kernel/unwind.c b/arch/parisc/kernel/unwind.c index 27ae40a443b8..f7e0fee5ee55 100644 --- a/arch/parisc/kernel/unwind.c +++ b/arch/parisc/kernel/unwind.c @@ -228,10 +228,8 @@ static int unwind_special(struct unwind_frame_info *info, unsigned long pc, int #ifdef CONFIG_IRQSTACKS extern void * const _call_on_stack; #endif /* CONFIG_IRQSTACKS */ - void *ptr; - ptr = dereference_kernel_function_descriptor(&handle_interruption); - if (pc_is_kernel_fn(pc, ptr)) { + if (pc_is_kernel_fn(pc, handle_interruption)) { struct pt_regs *regs = (struct pt_regs *)(info->sp - frame_size - PT_SZ_ALGN); dbg("Unwinding through handle_interruption()\n"); info->prev_sp = regs->gr[30]; @@ -239,13 +237,13 @@ static int unwind_special(struct unwind_frame_info *info, unsigned long pc, int return 1; } - if (pc_is_kernel_fn(pc, ret_from_kernel_thread) || - pc_is_kernel_fn(pc, syscall_exit)) { + if (pc == (unsigned long)&ret_from_kernel_thread || + pc == (unsigned long)&syscall_exit) { info->prev_sp = info->prev_ip = 0; return 1; } - if (pc_is_kernel_fn(pc, intr_return)) { + if (pc == (unsigned long)&intr_return) { struct pt_regs *regs; dbg("Found intr_return()\n"); @@ -257,14 +255,14 @@ static int unwind_special(struct unwind_frame_info *info, unsigned long pc, int } if (pc_is_kernel_fn(pc, _switch_to) || - pc_is_kernel_fn(pc, _switch_to_ret)) { + pc == (unsigned long)&_switch_to_ret) { info->prev_sp = info->sp - CALLEE_SAVE_FRAME_SIZE; info->prev_ip = *(unsigned long *)(info->prev_sp - RP_OFFSET); return 1; } #ifdef CONFIG_IRQSTACKS - if (pc_is_kernel_fn(pc, _call_on_stack)) { + if (pc == (unsigned long)&_call_on_stack) { info->prev_sp = *(unsigned long *)(info->sp - FRAME_SIZE - REG_SZ); info->prev_ip = *(unsigned long *)(info->sp - FRAME_SIZE - RP_OFFSET); return 1; diff --git a/arch/powerpc/include/asm/ppc-pci.h b/arch/powerpc/include/asm/ppc-pci.h index ce2b1b5eebdd..a8b7e8682f5b 100644 --- a/arch/powerpc/include/asm/ppc-pci.h +++ b/arch/powerpc/include/asm/ppc-pci.h @@ -30,6 +30,16 @@ void *pci_traverse_device_nodes(struct device_node *start, void *data); extern void pci_devs_phb_init_dynamic(struct pci_controller *phb); +#if defined(CONFIG_IOMMU_API) && (defined(CONFIG_PPC_PSERIES) || \ + defined(CONFIG_PPC_POWERNV)) +extern void ppc_iommu_register_device(struct pci_controller *phb); +extern void ppc_iommu_unregister_device(struct pci_controller *phb); +#else +static inline void ppc_iommu_register_device(struct pci_controller *phb) { } +static inline void ppc_iommu_unregister_device(struct pci_controller *phb) { } +#endif + + /* From rtas_pci.h */ extern void init_pci_config_tokens (void); extern unsigned long get_phb_buid (struct device_node *); diff --git a/arch/powerpc/include/asm/rtas.h b/arch/powerpc/include/asm/rtas.h index 9bb2210c8d44..065ffd1b2f8a 100644 --- a/arch/powerpc/include/asm/rtas.h +++ b/arch/powerpc/include/asm/rtas.h @@ -69,7 +69,7 @@ enum rtas_function_index { RTAS_FNIDX__IBM_READ_SLOT_RESET_STATE, RTAS_FNIDX__IBM_READ_SLOT_RESET_STATE2, RTAS_FNIDX__IBM_REMOVE_PE_DMA_WINDOW, - RTAS_FNIDX__IBM_RESET_PE_DMA_WINDOWS, + RTAS_FNIDX__IBM_RESET_PE_DMA_WINDOW, RTAS_FNIDX__IBM_SCAN_LOG_DUMP, RTAS_FNIDX__IBM_SET_DYNAMIC_INDICATOR, RTAS_FNIDX__IBM_SET_EEH_OPTION, @@ -164,7 +164,7 @@ typedef struct { #define RTAS_FN_IBM_READ_SLOT_RESET_STATE rtas_fn_handle(RTAS_FNIDX__IBM_READ_SLOT_RESET_STATE) #define RTAS_FN_IBM_READ_SLOT_RESET_STATE2 rtas_fn_handle(RTAS_FNIDX__IBM_READ_SLOT_RESET_STATE2) #define RTAS_FN_IBM_REMOVE_PE_DMA_WINDOW rtas_fn_handle(RTAS_FNIDX__IBM_REMOVE_PE_DMA_WINDOW) -#define RTAS_FN_IBM_RESET_PE_DMA_WINDOWS rtas_fn_handle(RTAS_FNIDX__IBM_RESET_PE_DMA_WINDOWS) +#define RTAS_FN_IBM_RESET_PE_DMA_WINDOW rtas_fn_handle(RTAS_FNIDX__IBM_RESET_PE_DMA_WINDOW) #define RTAS_FN_IBM_SCAN_LOG_DUMP rtas_fn_handle(RTAS_FNIDX__IBM_SCAN_LOG_DUMP) #define RTAS_FN_IBM_SET_DYNAMIC_INDICATOR rtas_fn_handle(RTAS_FNIDX__IBM_SET_DYNAMIC_INDICATOR) #define RTAS_FN_IBM_SET_EEH_OPTION rtas_fn_handle(RTAS_FNIDX__IBM_SET_EEH_OPTION) diff --git a/arch/powerpc/kernel/iommu.c b/arch/powerpc/kernel/iommu.c index a9bebfd56b3b..1185efebf032 100644 --- a/arch/powerpc/kernel/iommu.c +++ b/arch/powerpc/kernel/iommu.c @@ -1360,7 +1360,7 @@ static struct iommu_device *spapr_tce_iommu_probe_device(struct device *dev) struct pci_controller *hose; if (!dev_is_pci(dev)) - return ERR_PTR(-EPERM); + return ERR_PTR(-ENODEV); pdev = to_pci_dev(dev); hose = pdev->bus->sysdata; @@ -1409,6 +1409,21 @@ static const struct attribute_group *spapr_tce_iommu_groups[] = { NULL, }; +void ppc_iommu_register_device(struct pci_controller *phb) +{ + iommu_device_sysfs_add(&phb->iommu, phb->parent, + spapr_tce_iommu_groups, "iommu-phb%04x", + phb->global_number); + iommu_device_register(&phb->iommu, &spapr_tce_iommu_ops, + phb->parent); +} + +void ppc_iommu_unregister_device(struct pci_controller *phb) +{ + iommu_device_unregister(&phb->iommu); + iommu_device_sysfs_remove(&phb->iommu); +} + /* * This registers IOMMU devices of PHBs. This needs to happen * after core_initcall(iommu_init) + postcore_initcall(pci_driver_init) and @@ -1419,11 +1434,7 @@ static int __init spapr_tce_setup_phb_iommus_initcall(void) struct pci_controller *hose; list_for_each_entry(hose, &hose_list, list_node) { - iommu_device_sysfs_add(&hose->iommu, hose->parent, - spapr_tce_iommu_groups, "iommu-phb%04x", - hose->global_number); - iommu_device_register(&hose->iommu, &spapr_tce_iommu_ops, - hose->parent); + ppc_iommu_register_device(hose); } return 0; } diff --git a/arch/powerpc/kernel/rtas.c b/arch/powerpc/kernel/rtas.c index 7e793b503e29..8064d9c3de86 100644 --- a/arch/powerpc/kernel/rtas.c +++ b/arch/powerpc/kernel/rtas.c @@ -375,8 +375,13 @@ static struct rtas_function rtas_function_table[] __ro_after_init = { [RTAS_FNIDX__IBM_REMOVE_PE_DMA_WINDOW] = { .name = "ibm,remove-pe-dma-window", }, - [RTAS_FNIDX__IBM_RESET_PE_DMA_WINDOWS] = { - .name = "ibm,reset-pe-dma-windows", + [RTAS_FNIDX__IBM_RESET_PE_DMA_WINDOW] = { + /* + * Note: PAPR+ v2.13 7.3.31.4.1 spells this as + * "ibm,reset-pe-dma-windows" (plural), but RTAS + * implementations use the singular form in practice. + */ + .name = "ibm,reset-pe-dma-window", }, [RTAS_FNIDX__IBM_SCAN_LOG_DUMP] = { .name = "ibm,scan-log-dump", diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c index 52427fc2a33f..0b921704da45 100644 --- a/arch/powerpc/kvm/book3s_hv.c +++ b/arch/powerpc/kvm/book3s_hv.c @@ -391,6 +391,24 @@ static void kvmppc_set_pvr_hv(struct kvm_vcpu *vcpu, u32 pvr) /* Dummy value used in computing PCR value below */ #define PCR_ARCH_31 (PCR_ARCH_300 << 1) +static inline unsigned long map_pcr_to_cap(unsigned long pcr) +{ + unsigned long cap = 0; + + switch (pcr) { + case PCR_ARCH_300: + cap = H_GUEST_CAP_POWER9; + break; + case PCR_ARCH_31: + cap = H_GUEST_CAP_POWER10; + break; + default: + break; + } + + return cap; +} + static int kvmppc_set_arch_compat(struct kvm_vcpu *vcpu, u32 arch_compat) { unsigned long host_pcr_bit = 0, guest_pcr_bit = 0, cap = 0; @@ -424,11 +442,9 @@ static int kvmppc_set_arch_compat(struct kvm_vcpu *vcpu, u32 arch_compat) break; case PVR_ARCH_300: guest_pcr_bit = PCR_ARCH_300; - cap = H_GUEST_CAP_POWER9; break; case PVR_ARCH_31: guest_pcr_bit = PCR_ARCH_31; - cap = H_GUEST_CAP_POWER10; break; default: return -EINVAL; @@ -440,6 +456,12 @@ static int kvmppc_set_arch_compat(struct kvm_vcpu *vcpu, u32 arch_compat) return -EINVAL; if (kvmhv_on_pseries() && kvmhv_is_nestedv2()) { + /* + * 'arch_compat == 0' would mean the guest should default to + * L1's compatibility. In this case, the guest would pick + * host's PCR and evaluate the corresponding capabilities. + */ + cap = map_pcr_to_cap(guest_pcr_bit); if (!(cap & nested_capabilities)) return -EINVAL; } diff --git a/arch/powerpc/kvm/book3s_hv_nestedv2.c b/arch/powerpc/kvm/book3s_hv_nestedv2.c index 5378eb40b162..8e6f5355f08b 100644 --- a/arch/powerpc/kvm/book3s_hv_nestedv2.c +++ b/arch/powerpc/kvm/book3s_hv_nestedv2.c @@ -138,6 +138,7 @@ static int gs_msg_ops_vcpu_fill_info(struct kvmppc_gs_buff *gsb, vector128 v; int rc, i; u16 iden; + u32 arch_compat = 0; vcpu = gsm->data; @@ -347,8 +348,23 @@ static int gs_msg_ops_vcpu_fill_info(struct kvmppc_gs_buff *gsb, break; } case KVMPPC_GSID_LOGICAL_PVR: - rc = kvmppc_gse_put_u32(gsb, iden, - vcpu->arch.vcore->arch_compat); + /* + * Though 'arch_compat == 0' would mean the default + * compatibility, arch_compat, being a Guest Wide + * Element, cannot be filled with a value of 0 in GSB + * as this would result into a kernel trap. + * Hence, when `arch_compat == 0`, arch_compat should + * default to L1's PVR. + */ + if (!vcpu->arch.vcore->arch_compat) { + if (cpu_has_feature(CPU_FTR_ARCH_31)) + arch_compat = PVR_ARCH_31; + else if (cpu_has_feature(CPU_FTR_ARCH_300)) + arch_compat = PVR_ARCH_300; + } else { + arch_compat = vcpu->arch.vcore->arch_compat; + } + rc = kvmppc_gse_put_u32(gsb, iden, arch_compat); break; } diff --git a/arch/powerpc/platforms/pseries/iommu.c b/arch/powerpc/platforms/pseries/iommu.c index 496e16c588aa..e8c4129697b1 100644 --- a/arch/powerpc/platforms/pseries/iommu.c +++ b/arch/powerpc/platforms/pseries/iommu.c @@ -574,29 +574,6 @@ static void iommu_table_setparms(struct pci_controller *phb, struct iommu_table_ops iommu_table_lpar_multi_ops; -/* - * iommu_table_setparms_lpar - * - * Function: On pSeries LPAR systems, return TCE table info, given a pci bus. - */ -static void iommu_table_setparms_lpar(struct pci_controller *phb, - struct device_node *dn, - struct iommu_table *tbl, - struct iommu_table_group *table_group, - const __be32 *dma_window) -{ - unsigned long offset, size, liobn; - - of_parse_dma_window(dn, dma_window, &liobn, &offset, &size); - - iommu_table_setparms_common(tbl, phb->bus->number, liobn, offset, size, IOMMU_PAGE_SHIFT_4K, NULL, - &iommu_table_lpar_multi_ops); - - - table_group->tce32_start = offset; - table_group->tce32_size = size; -} - struct iommu_table_ops iommu_table_pseries_ops = { .set = tce_build_pSeries, .clear = tce_free_pSeries, @@ -724,26 +701,71 @@ struct iommu_table_ops iommu_table_lpar_multi_ops = { * dynamic 64bit DMA window, walking up the device tree. */ static struct device_node *pci_dma_find(struct device_node *dn, - const __be32 **dma_window) + struct dynamic_dma_window_prop *prop) { - const __be32 *dw = NULL; + const __be32 *default_prop = NULL; + const __be32 *ddw_prop = NULL; + struct device_node *rdn = NULL; + bool default_win = false, ddw_win = false; for ( ; dn && PCI_DN(dn); dn = dn->parent) { - dw = of_get_property(dn, "ibm,dma-window", NULL); - if (dw) { - if (dma_window) - *dma_window = dw; - return dn; + default_prop = of_get_property(dn, "ibm,dma-window", NULL); + if (default_prop) { + rdn = dn; + default_win = true; + } + ddw_prop = of_get_property(dn, DIRECT64_PROPNAME, NULL); + if (ddw_prop) { + rdn = dn; + ddw_win = true; + break; + } + ddw_prop = of_get_property(dn, DMA64_PROPNAME, NULL); + if (ddw_prop) { + rdn = dn; + ddw_win = true; + break; } - dw = of_get_property(dn, DIRECT64_PROPNAME, NULL); - if (dw) - return dn; - dw = of_get_property(dn, DMA64_PROPNAME, NULL); - if (dw) - return dn; + + /* At least found default window, which is the case for normal boot */ + if (default_win) + break; } - return NULL; + /* For PCI devices there will always be a DMA window, either on the device + * or parent bus + */ + WARN_ON(!(default_win | ddw_win)); + + /* caller doesn't want to get DMA window property */ + if (!prop) + return rdn; + + /* parse DMA window property. During normal system boot, only default + * DMA window is passed in OF. But, for kdump, a dedicated adapter might + * have both default and DDW in FDT. In this scenario, DDW takes precedence + * over default window. + */ + if (ddw_win) { + struct dynamic_dma_window_prop *p; + + p = (struct dynamic_dma_window_prop *)ddw_prop; + prop->liobn = p->liobn; + prop->dma_base = p->dma_base; + prop->tce_shift = p->tce_shift; + prop->window_shift = p->window_shift; + } else if (default_win) { + unsigned long offset, size, liobn; + + of_parse_dma_window(rdn, default_prop, &liobn, &offset, &size); + + prop->liobn = cpu_to_be32((u32)liobn); + prop->dma_base = cpu_to_be64(offset); + prop->tce_shift = cpu_to_be32(IOMMU_PAGE_SHIFT_4K); + prop->window_shift = cpu_to_be32(order_base_2(size)); + } + + return rdn; } static void pci_dma_bus_setup_pSeriesLP(struct pci_bus *bus) @@ -751,17 +773,20 @@ static void pci_dma_bus_setup_pSeriesLP(struct pci_bus *bus) struct iommu_table *tbl; struct device_node *dn, *pdn; struct pci_dn *ppci; - const __be32 *dma_window = NULL; + struct dynamic_dma_window_prop prop; dn = pci_bus_to_OF_node(bus); pr_debug("pci_dma_bus_setup_pSeriesLP: setting up bus %pOF\n", dn); - pdn = pci_dma_find(dn, &dma_window); + pdn = pci_dma_find(dn, &prop); - if (dma_window == NULL) - pr_debug(" no ibm,dma-window property !\n"); + /* In PPC architecture, there will always be DMA window on bus or one of the + * parent bus. During reboot, there will be ibm,dma-window property to + * define DMA window. For kdump, there will at least be default window or DDW + * or both. + */ ppci = PCI_DN(pdn); @@ -771,13 +796,24 @@ static void pci_dma_bus_setup_pSeriesLP(struct pci_bus *bus) if (!ppci->table_group) { ppci->table_group = iommu_pseries_alloc_group(ppci->phb->node); tbl = ppci->table_group->tables[0]; - if (dma_window) { - iommu_table_setparms_lpar(ppci->phb, pdn, tbl, - ppci->table_group, dma_window); - if (!iommu_init_table(tbl, ppci->phb->node, 0, 0)) - panic("Failed to initialize iommu table"); - } + iommu_table_setparms_common(tbl, ppci->phb->bus->number, + be32_to_cpu(prop.liobn), + be64_to_cpu(prop.dma_base), + 1ULL << be32_to_cpu(prop.window_shift), + be32_to_cpu(prop.tce_shift), NULL, + &iommu_table_lpar_multi_ops); + + /* Only for normal boot with default window. Doesn't matter even + * if we set these with DDW which is 64bit during kdump, since + * these will not be used during kdump. + */ + ppci->table_group->tce32_start = be64_to_cpu(prop.dma_base); + ppci->table_group->tce32_size = 1 << be32_to_cpu(prop.window_shift); + + if (!iommu_init_table(tbl, ppci->phb->node, 0, 0)) + panic("Failed to initialize iommu table"); + iommu_register_group(ppci->table_group, pci_domain_nr(bus), 0); pr_debug(" created table: %p\n", ppci->table_group); @@ -968,6 +1004,12 @@ static void find_existing_ddw_windows_named(const char *name) continue; } + /* If at the time of system initialization, there are DDWs in OF, + * it means this is during kexec. DDW could be direct or dynamic. + * We will just mark DDWs as "dynamic" since this is kdump path, + * no need to worry about perforance. ddw_list_new_entry() will + * set window->direct = false. + */ window = ddw_list_new_entry(pdn, dma64); if (!window) { of_node_put(pdn); @@ -1524,8 +1566,8 @@ static void pci_dma_dev_setup_pSeriesLP(struct pci_dev *dev) { struct device_node *pdn, *dn; struct iommu_table *tbl; - const __be32 *dma_window = NULL; struct pci_dn *pci; + struct dynamic_dma_window_prop prop; pr_debug("pci_dma_dev_setup_pSeriesLP: %s\n", pci_name(dev)); @@ -1538,7 +1580,7 @@ static void pci_dma_dev_setup_pSeriesLP(struct pci_dev *dev) dn = pci_device_to_OF_node(dev); pr_debug(" node is %pOF\n", dn); - pdn = pci_dma_find(dn, &dma_window); + pdn = pci_dma_find(dn, &prop); if (!pdn || !PCI_DN(pdn)) { printk(KERN_WARNING "pci_dma_dev_setup_pSeriesLP: " "no DMA window found for pci dev=%s dn=%pOF\n", @@ -1551,8 +1593,20 @@ static void pci_dma_dev_setup_pSeriesLP(struct pci_dev *dev) if (!pci->table_group) { pci->table_group = iommu_pseries_alloc_group(pci->phb->node); tbl = pci->table_group->tables[0]; - iommu_table_setparms_lpar(pci->phb, pdn, tbl, - pci->table_group, dma_window); + + iommu_table_setparms_common(tbl, pci->phb->bus->number, + be32_to_cpu(prop.liobn), + be64_to_cpu(prop.dma_base), + 1ULL << be32_to_cpu(prop.window_shift), + be32_to_cpu(prop.tce_shift), NULL, + &iommu_table_lpar_multi_ops); + + /* Only for normal boot with default window. Doesn't matter even + * if we set these with DDW which is 64bit during kdump, since + * these will not be used during kdump. + */ + pci->table_group->tce32_start = be64_to_cpu(prop.dma_base); + pci->table_group->tce32_size = 1 << be32_to_cpu(prop.window_shift); iommu_init_table(tbl, pci->phb->node, 0, 0); iommu_register_group(pci->table_group, diff --git a/arch/powerpc/platforms/pseries/pci_dlpar.c b/arch/powerpc/platforms/pseries/pci_dlpar.c index 4ba824568119..4448386268d9 100644 --- a/arch/powerpc/platforms/pseries/pci_dlpar.c +++ b/arch/powerpc/platforms/pseries/pci_dlpar.c @@ -35,6 +35,8 @@ struct pci_controller *init_phb_dynamic(struct device_node *dn) pseries_msi_allocate_domains(phb); + ppc_iommu_register_device(phb); + /* Create EEH devices for the PHB */ eeh_phb_pe_create(phb); @@ -76,6 +78,8 @@ int remove_phb_dynamic(struct pci_controller *phb) } } + ppc_iommu_unregister_device(phb); + pseries_msi_free_domains(phb); /* Keep a reference so phb isn't freed yet */ diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig index bffbd869a068..e3142ce531a0 100644 --- a/arch/riscv/Kconfig +++ b/arch/riscv/Kconfig @@ -315,7 +315,6 @@ config AS_HAS_OPTION_ARCH # https://reviews.llvm.org/D123515 def_bool y depends on $(as-instr, .option arch$(comma) +m) - depends on !$(as-instr, .option arch$(comma) -i) source "arch/riscv/Kconfig.socs" source "arch/riscv/Kconfig.errata" diff --git a/arch/riscv/boot/dts/sifive/hifive-unmatched-a00.dts b/arch/riscv/boot/dts/sifive/hifive-unmatched-a00.dts index 07387f9c135c..72b87b08ab44 100644 --- a/arch/riscv/boot/dts/sifive/hifive-unmatched-a00.dts +++ b/arch/riscv/boot/dts/sifive/hifive-unmatched-a00.dts @@ -123,6 +123,7 @@ interrupt-parent = <&gpio>; interrupts = <1 IRQ_TYPE_LEVEL_LOW>; interrupt-controller; + #interrupt-cells = <2>; onkey { compatible = "dlg,da9063-onkey"; diff --git a/arch/riscv/boot/dts/starfive/jh7100.dtsi b/arch/riscv/boot/dts/starfive/jh7100.dtsi index c216aaecac53..8bcf36d07f3f 100644 --- a/arch/riscv/boot/dts/starfive/jh7100.dtsi +++ b/arch/riscv/boot/dts/starfive/jh7100.dtsi @@ -96,14 +96,14 @@ thermal-sensors = <&sfctemp>; trips { - cpu_alert0 { + cpu-alert0 { /* milliCelsius */ temperature = <75000>; hysteresis = <2000>; type = "passive"; }; - cpu_crit { + cpu-crit { /* milliCelsius */ temperature = <90000>; hysteresis = <2000>; @@ -113,28 +113,28 @@ }; }; - osc_sys: osc_sys { + osc_sys: osc-sys { compatible = "fixed-clock"; #clock-cells = <0>; /* This value must be overridden by the board */ clock-frequency = <0>; }; - osc_aud: osc_aud { + osc_aud: osc-aud { compatible = "fixed-clock"; #clock-cells = <0>; /* This value must be overridden by the board */ clock-frequency = <0>; }; - gmac_rmii_ref: gmac_rmii_ref { + gmac_rmii_ref: gmac-rmii-ref { compatible = "fixed-clock"; #clock-cells = <0>; /* Should be overridden by the board when needed */ clock-frequency = <0>; }; - gmac_gr_mii_rxclk: gmac_gr_mii_rxclk { + gmac_gr_mii_rxclk: gmac-gr-mii-rxclk { compatible = "fixed-clock"; #clock-cells = <0>; /* Should be overridden by the board when needed */ diff --git a/arch/riscv/boot/dts/starfive/jh7110.dtsi b/arch/riscv/boot/dts/starfive/jh7110.dtsi index 45213cdf50dc..74ed3b9264d8 100644 --- a/arch/riscv/boot/dts/starfive/jh7110.dtsi +++ b/arch/riscv/boot/dts/starfive/jh7110.dtsi @@ -237,14 +237,14 @@ }; trips { - cpu_alert0: cpu_alert0 { + cpu_alert0: cpu-alert0 { /* milliCelsius */ temperature = <85000>; hysteresis = <2000>; type = "passive"; }; - cpu_crit { + cpu-crit { /* milliCelsius */ temperature = <100000>; hysteresis = <2000>; diff --git a/arch/riscv/include/asm/csr.h b/arch/riscv/include/asm/csr.h index 510014051f5d..2468c55933cd 100644 --- a/arch/riscv/include/asm/csr.h +++ b/arch/riscv/include/asm/csr.h @@ -424,6 +424,7 @@ # define CSR_STATUS CSR_MSTATUS # define CSR_IE CSR_MIE # define CSR_TVEC CSR_MTVEC +# define CSR_ENVCFG CSR_MENVCFG # define CSR_SCRATCH CSR_MSCRATCH # define CSR_EPC CSR_MEPC # define CSR_CAUSE CSR_MCAUSE @@ -448,6 +449,7 @@ # define CSR_STATUS CSR_SSTATUS # define CSR_IE CSR_SIE # define CSR_TVEC CSR_STVEC +# define CSR_ENVCFG CSR_SENVCFG # define CSR_SCRATCH CSR_SSCRATCH # define CSR_EPC CSR_SEPC # define CSR_CAUSE CSR_SCAUSE diff --git a/arch/riscv/include/asm/ftrace.h b/arch/riscv/include/asm/ftrace.h index 329172122952..15055f9df4da 100644 --- a/arch/riscv/include/asm/ftrace.h +++ b/arch/riscv/include/asm/ftrace.h @@ -25,6 +25,11 @@ #define ARCH_SUPPORTS_FTRACE_OPS 1 #ifndef __ASSEMBLY__ + +extern void *return_address(unsigned int level); + +#define ftrace_return_address(n) return_address(n) + void MCOUNT_NAME(void); static inline unsigned long ftrace_call_adjust(unsigned long addr) { diff --git a/arch/riscv/include/asm/hugetlb.h b/arch/riscv/include/asm/hugetlb.h index 20f9c3ba2341..22deb7a2a6ec 100644 --- a/arch/riscv/include/asm/hugetlb.h +++ b/arch/riscv/include/asm/hugetlb.h @@ -11,8 +11,10 @@ static inline void arch_clear_hugepage_flags(struct page *page) } #define arch_clear_hugepage_flags arch_clear_hugepage_flags +#ifdef CONFIG_ARCH_ENABLE_HUGEPAGE_MIGRATION bool arch_hugetlb_migration_supported(struct hstate *h); #define arch_hugetlb_migration_supported arch_hugetlb_migration_supported +#endif #ifdef CONFIG_RISCV_ISA_SVNAPOT #define __HAVE_ARCH_HUGE_PTE_CLEAR diff --git a/arch/riscv/include/asm/hwcap.h b/arch/riscv/include/asm/hwcap.h index 5340f818746b..1f2d2599c655 100644 --- a/arch/riscv/include/asm/hwcap.h +++ b/arch/riscv/include/asm/hwcap.h @@ -81,6 +81,8 @@ #define RISCV_ISA_EXT_ZTSO 72 #define RISCV_ISA_EXT_ZACAS 73 +#define RISCV_ISA_EXT_XLINUXENVCFG 127 + #define RISCV_ISA_EXT_MAX 128 #define RISCV_ISA_EXT_INVALID U32_MAX diff --git a/arch/riscv/include/asm/pgalloc.h b/arch/riscv/include/asm/pgalloc.h index d169a4f41a2e..c80bb9990d32 100644 --- a/arch/riscv/include/asm/pgalloc.h +++ b/arch/riscv/include/asm/pgalloc.h @@ -95,7 +95,13 @@ static inline void pud_free(struct mm_struct *mm, pud_t *pud) __pud_free(mm, pud); } -#define __pud_free_tlb(tlb, pud, addr) pud_free((tlb)->mm, pud) +#define __pud_free_tlb(tlb, pud, addr) \ +do { \ + if (pgtable_l4_enabled) { \ + pagetable_pud_dtor(virt_to_ptdesc(pud)); \ + tlb_remove_page_ptdesc((tlb), virt_to_ptdesc(pud)); \ + } \ +} while (0) #define p4d_alloc_one p4d_alloc_one static inline p4d_t *p4d_alloc_one(struct mm_struct *mm, unsigned long addr) @@ -124,7 +130,11 @@ static inline void p4d_free(struct mm_struct *mm, p4d_t *p4d) __p4d_free(mm, p4d); } -#define __p4d_free_tlb(tlb, p4d, addr) p4d_free((tlb)->mm, p4d) +#define __p4d_free_tlb(tlb, p4d, addr) \ +do { \ + if (pgtable_l5_enabled) \ + tlb_remove_page_ptdesc((tlb), virt_to_ptdesc(p4d)); \ +} while (0) #endif /* __PAGETABLE_PMD_FOLDED */ static inline void sync_kernel_mappings(pgd_t *pgd) @@ -149,7 +159,11 @@ static inline pgd_t *pgd_alloc(struct mm_struct *mm) #ifndef __PAGETABLE_PMD_FOLDED -#define __pmd_free_tlb(tlb, pmd, addr) pmd_free((tlb)->mm, pmd) +#define __pmd_free_tlb(tlb, pmd, addr) \ +do { \ + pagetable_pmd_dtor(virt_to_ptdesc(pmd)); \ + tlb_remove_page_ptdesc((tlb), virt_to_ptdesc(pmd)); \ +} while (0) #endif /* __PAGETABLE_PMD_FOLDED */ diff --git a/arch/riscv/include/asm/pgtable-64.h b/arch/riscv/include/asm/pgtable-64.h index b42017d76924..b99bd66107a6 100644 --- a/arch/riscv/include/asm/pgtable-64.h +++ b/arch/riscv/include/asm/pgtable-64.h @@ -136,7 +136,7 @@ enum napot_cont_order { * 10010 - IO Strongly-ordered, Non-cacheable, Non-bufferable, Shareable, Non-trustable */ #define _PAGE_PMA_THEAD ((1UL << 62) | (1UL << 61) | (1UL << 60)) -#define _PAGE_NOCACHE_THEAD ((1UL < 61) | (1UL << 60)) +#define _PAGE_NOCACHE_THEAD ((1UL << 61) | (1UL << 60)) #define _PAGE_IO_THEAD ((1UL << 63) | (1UL << 60)) #define _PAGE_MTMASK_THEAD (_PAGE_PMA_THEAD | _PAGE_IO_THEAD | (1UL << 59)) diff --git a/arch/riscv/include/asm/pgtable.h b/arch/riscv/include/asm/pgtable.h index 0c94260b5d0c..6066822e7396 100644 --- a/arch/riscv/include/asm/pgtable.h +++ b/arch/riscv/include/asm/pgtable.h @@ -84,7 +84,7 @@ * Define vmemmap for pfn_to_page & page_to_pfn calls. Needed if kernel * is configured with CONFIG_SPARSEMEM_VMEMMAP enabled. */ -#define vmemmap ((struct page *)VMEMMAP_START) +#define vmemmap ((struct page *)VMEMMAP_START - (phys_ram_base >> PAGE_SHIFT)) #define PCI_IO_SIZE SZ_16M #define PCI_IO_END VMEMMAP_START @@ -439,6 +439,10 @@ static inline pte_t pte_mkhuge(pte_t pte) return pte; } +#define pte_leaf_size(pte) (pte_napot(pte) ? \ + napot_cont_size(napot_cont_order(pte)) :\ + PAGE_SIZE) + #ifdef CONFIG_NUMA_BALANCING /* * See the comment in include/asm-generic/pgtable.h diff --git a/arch/riscv/include/asm/suspend.h b/arch/riscv/include/asm/suspend.h index 02f87867389a..491296a335d0 100644 --- a/arch/riscv/include/asm/suspend.h +++ b/arch/riscv/include/asm/suspend.h @@ -14,6 +14,7 @@ struct suspend_context { struct pt_regs regs; /* Saved and restored by high-level functions */ unsigned long scratch; + unsigned long envcfg; unsigned long tvec; unsigned long ie; #ifdef CONFIG_MMU diff --git a/arch/riscv/include/asm/vmalloc.h b/arch/riscv/include/asm/vmalloc.h index 924d01b56c9a..51f6dfe19745 100644 --- a/arch/riscv/include/asm/vmalloc.h +++ b/arch/riscv/include/asm/vmalloc.h @@ -19,65 +19,6 @@ static inline bool arch_vmap_pmd_supported(pgprot_t prot) return true; } -#ifdef CONFIG_RISCV_ISA_SVNAPOT -#include <linux/pgtable.h> +#endif -#define arch_vmap_pte_range_map_size arch_vmap_pte_range_map_size -static inline unsigned long arch_vmap_pte_range_map_size(unsigned long addr, unsigned long end, - u64 pfn, unsigned int max_page_shift) -{ - unsigned long map_size = PAGE_SIZE; - unsigned long size, order; - - if (!has_svnapot()) - return map_size; - - for_each_napot_order_rev(order) { - if (napot_cont_shift(order) > max_page_shift) - continue; - - size = napot_cont_size(order); - if (end - addr < size) - continue; - - if (!IS_ALIGNED(addr, size)) - continue; - - if (!IS_ALIGNED(PFN_PHYS(pfn), size)) - continue; - - map_size = size; - break; - } - - return map_size; -} - -#define arch_vmap_pte_supported_shift arch_vmap_pte_supported_shift -static inline int arch_vmap_pte_supported_shift(unsigned long size) -{ - int shift = PAGE_SHIFT; - unsigned long order; - - if (!has_svnapot()) - return shift; - - WARN_ON_ONCE(size >= PMD_SIZE); - - for_each_napot_order_rev(order) { - if (napot_cont_size(order) > size) - continue; - - if (!IS_ALIGNED(size, napot_cont_size(order))) - continue; - - shift = napot_cont_shift(order); - break; - } - - return shift; -} - -#endif /* CONFIG_RISCV_ISA_SVNAPOT */ -#endif /* CONFIG_HAVE_ARCH_HUGE_VMAP */ #endif /* _ASM_RISCV_VMALLOC_H */ diff --git a/arch/riscv/kernel/Makefile b/arch/riscv/kernel/Makefile index f71910718053..604d6bf7e476 100644 --- a/arch/riscv/kernel/Makefile +++ b/arch/riscv/kernel/Makefile @@ -7,6 +7,7 @@ ifdef CONFIG_FTRACE CFLAGS_REMOVE_ftrace.o = $(CC_FLAGS_FTRACE) CFLAGS_REMOVE_patch.o = $(CC_FLAGS_FTRACE) CFLAGS_REMOVE_sbi.o = $(CC_FLAGS_FTRACE) +CFLAGS_REMOVE_return_address.o = $(CC_FLAGS_FTRACE) endif CFLAGS_syscall_table.o += $(call cc-option,-Wno-override-init,) CFLAGS_compat_syscall_table.o += $(call cc-option,-Wno-override-init,) @@ -46,6 +47,7 @@ obj-y += irq.o obj-y += process.o obj-y += ptrace.o obj-y += reset.o +obj-y += return_address.o obj-y += setup.o obj-y += signal.o obj-y += syscall_table.o diff --git a/arch/riscv/kernel/cpufeature.c b/arch/riscv/kernel/cpufeature.c index 89920f84d0a3..79a5a35fab96 100644 --- a/arch/riscv/kernel/cpufeature.c +++ b/arch/riscv/kernel/cpufeature.c @@ -24,6 +24,7 @@ #include <asm/hwprobe.h> #include <asm/patch.h> #include <asm/processor.h> +#include <asm/sbi.h> #include <asm/vector.h> #include "copy-unaligned.h" @@ -202,6 +203,16 @@ static const unsigned int riscv_zvbb_exts[] = { }; /* + * While the [ms]envcfg CSRs were not defined until version 1.12 of the RISC-V + * privileged ISA, the existence of the CSRs is implied by any extension which + * specifies [ms]envcfg bit(s). Hence, we define a custom ISA extension for the + * existence of the CSR, and treat it as a subset of those other extensions. + */ +static const unsigned int riscv_xlinuxenvcfg_exts[] = { + RISCV_ISA_EXT_XLINUXENVCFG +}; + +/* * The canonical order of ISA extension names in the ISA string is defined in * chapter 27 of the unprivileged specification. * @@ -250,8 +261,8 @@ const struct riscv_isa_ext_data riscv_isa_ext[] = { __RISCV_ISA_EXT_DATA(c, RISCV_ISA_EXT_c), __RISCV_ISA_EXT_DATA(v, RISCV_ISA_EXT_v), __RISCV_ISA_EXT_DATA(h, RISCV_ISA_EXT_h), - __RISCV_ISA_EXT_DATA(zicbom, RISCV_ISA_EXT_ZICBOM), - __RISCV_ISA_EXT_DATA(zicboz, RISCV_ISA_EXT_ZICBOZ), + __RISCV_ISA_EXT_SUPERSET(zicbom, RISCV_ISA_EXT_ZICBOM, riscv_xlinuxenvcfg_exts), + __RISCV_ISA_EXT_SUPERSET(zicboz, RISCV_ISA_EXT_ZICBOZ, riscv_xlinuxenvcfg_exts), __RISCV_ISA_EXT_DATA(zicntr, RISCV_ISA_EXT_ZICNTR), __RISCV_ISA_EXT_DATA(zicond, RISCV_ISA_EXT_ZICOND), __RISCV_ISA_EXT_DATA(zicsr, RISCV_ISA_EXT_ZICSR), @@ -539,6 +550,20 @@ static void __init riscv_fill_hwcap_from_isa_string(unsigned long *isa2hwcap) } /* + * "V" in ISA strings is ambiguous in practice: it should mean + * just the standard V-1.0 but vendors aren't well behaved. + * Many vendors with T-Head CPU cores which implement the 0.7.1 + * version of the vector specification put "v" into their DTs. + * CPU cores with the ratified spec will contain non-zero + * marchid. + */ + if (acpi_disabled && riscv_cached_mvendorid(cpu) == THEAD_VENDOR_ID && + riscv_cached_marchid(cpu) == 0x0) { + this_hwcap &= ~isa2hwcap[RISCV_ISA_EXT_v]; + clear_bit(RISCV_ISA_EXT_v, isainfo->isa); + } + + /* * All "okay" hart should have same isa. Set HWCAP based on * common capabilities of every "okay" hart, in case they don't * have. @@ -950,7 +975,7 @@ arch_initcall(check_unaligned_access_all_cpus); void riscv_user_isa_enable(void) { if (riscv_cpu_has_extension_unlikely(smp_processor_id(), RISCV_ISA_EXT_ZICBOZ)) - csr_set(CSR_SENVCFG, ENVCFG_CBZE); + csr_set(CSR_ENVCFG, ENVCFG_CBZE); } #ifdef CONFIG_RISCV_ALTERNATIVE diff --git a/arch/riscv/kernel/return_address.c b/arch/riscv/kernel/return_address.c new file mode 100644 index 000000000000..c8115ec8fb30 --- /dev/null +++ b/arch/riscv/kernel/return_address.c @@ -0,0 +1,48 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * This code come from arch/arm64/kernel/return_address.c + * + * Copyright (C) 2023 SiFive. + */ + +#include <linux/export.h> +#include <linux/kprobes.h> +#include <linux/stacktrace.h> + +struct return_address_data { + unsigned int level; + void *addr; +}; + +static bool save_return_addr(void *d, unsigned long pc) +{ + struct return_address_data *data = d; + + if (!data->level) { + data->addr = (void *)pc; + return false; + } + + --data->level; + + return true; +} +NOKPROBE_SYMBOL(save_return_addr); + +noinline void *return_address(unsigned int level) +{ + struct return_address_data data; + + data.level = level + 3; + data.addr = NULL; + + arch_stack_walk(save_return_addr, &data, current, NULL); + + if (!data.level) + return data.addr; + else + return NULL; + +} +EXPORT_SYMBOL_GPL(return_address); +NOKPROBE_SYMBOL(return_address); diff --git a/arch/riscv/kernel/suspend.c b/arch/riscv/kernel/suspend.c index 239509367e42..299795341e8a 100644 --- a/arch/riscv/kernel/suspend.c +++ b/arch/riscv/kernel/suspend.c @@ -15,6 +15,8 @@ void suspend_save_csrs(struct suspend_context *context) { context->scratch = csr_read(CSR_SCRATCH); + if (riscv_cpu_has_extension_unlikely(smp_processor_id(), RISCV_ISA_EXT_XLINUXENVCFG)) + context->envcfg = csr_read(CSR_ENVCFG); context->tvec = csr_read(CSR_TVEC); context->ie = csr_read(CSR_IE); @@ -36,6 +38,8 @@ void suspend_save_csrs(struct suspend_context *context) void suspend_restore_csrs(struct suspend_context *context) { csr_write(CSR_SCRATCH, context->scratch); + if (riscv_cpu_has_extension_unlikely(smp_processor_id(), RISCV_ISA_EXT_XLINUXENVCFG)) + csr_write(CSR_ENVCFG, context->envcfg); csr_write(CSR_TVEC, context->tvec); csr_write(CSR_IE, context->ie); diff --git a/arch/riscv/kernel/vdso.c b/arch/riscv/kernel/vdso.c index 2cf76218a5bd..98315b98256d 100644 --- a/arch/riscv/kernel/vdso.c +++ b/arch/riscv/kernel/vdso.c @@ -30,14 +30,8 @@ enum rv_vdso_map { #define VVAR_SIZE (VVAR_NR_PAGES << PAGE_SHIFT) -/* - * The vDSO data page. - */ -static union { - struct vdso_data data; - u8 page[PAGE_SIZE]; -} vdso_data_store __page_aligned_data; -struct vdso_data *vdso_data = &vdso_data_store.data; +static union vdso_data_store vdso_data_store __page_aligned_data; +struct vdso_data *vdso_data = vdso_data_store.data; struct __vdso_info { const char *name; diff --git a/arch/riscv/mm/hugetlbpage.c b/arch/riscv/mm/hugetlbpage.c index 29c7606414d2..5ef2a6891158 100644 --- a/arch/riscv/mm/hugetlbpage.c +++ b/arch/riscv/mm/hugetlbpage.c @@ -426,10 +426,12 @@ bool __init arch_hugetlb_valid_size(unsigned long size) return __hugetlb_valid_size(size); } +#ifdef CONFIG_ARCH_ENABLE_HUGEPAGE_MIGRATION bool arch_hugetlb_migration_supported(struct hstate *h) { return __hugetlb_valid_size(huge_page_size(h)); } +#endif #ifdef CONFIG_CONTIG_ALLOC static __init int gigantic_pages_init(void) diff --git a/arch/s390/configs/compat.config b/arch/s390/configs/compat.config new file mode 100644 index 000000000000..6fd051453ae8 --- /dev/null +++ b/arch/s390/configs/compat.config @@ -0,0 +1,3 @@ +# Help: Enable compat support +CONFIG_COMPAT=y +CONFIG_COMPAT_32BIT_TIME=y diff --git a/arch/s390/configs/debug_defconfig b/arch/s390/configs/debug_defconfig index cae2dd34fbb4..06756bad5e30 100644 --- a/arch/s390/configs/debug_defconfig +++ b/arch/s390/configs/debug_defconfig @@ -118,7 +118,6 @@ CONFIG_UNIX=y CONFIG_UNIX_DIAG=m CONFIG_XFRM_USER=m CONFIG_NET_KEY=m -CONFIG_SMC=m CONFIG_SMC_DIAG=m CONFIG_INET=y CONFIG_IP_MULTICAST=y @@ -374,6 +373,7 @@ CONFIG_NET_ACT_POLICE=m CONFIG_NET_ACT_GACT=m CONFIG_GACT_PROB=y CONFIG_NET_ACT_MIRRED=m +CONFIG_NET_ACT_IPT=m CONFIG_NET_ACT_NAT=m CONFIG_NET_ACT_PEDIT=m CONFIG_NET_ACT_SIMP=m @@ -436,9 +436,6 @@ CONFIG_SCSI_DH_ALUA=m CONFIG_MD=y CONFIG_BLK_DEV_MD=y # CONFIG_MD_BITMAP_FILE is not set -CONFIG_MD_LINEAR=m -CONFIG_MD_MULTIPATH=m -CONFIG_MD_FAULTY=m CONFIG_MD_CLUSTER=m CONFIG_BCACHE=m CONFIG_BLK_DEV_DM=y @@ -637,7 +634,6 @@ CONFIG_FUSE_FS=y CONFIG_CUSE=m CONFIG_VIRTIO_FS=m CONFIG_OVERLAY_FS=m -CONFIG_NETFS_SUPPORT=m CONFIG_NETFS_STATS=y CONFIG_FSCACHE=y CONFIG_CACHEFILES=m @@ -709,7 +705,6 @@ CONFIG_IMA_DEFAULT_HASH_SHA256=y CONFIG_IMA_WRITE_POLICY=y CONFIG_IMA_APPRAISE=y CONFIG_LSM="yama,loadpin,safesetid,integrity,selinux,smack,tomoyo,apparmor" -CONFIG_INIT_STACK_NONE=y CONFIG_BUG_ON_DATA_CORRUPTION=y CONFIG_CRYPTO_USER=m # CONFIG_CRYPTO_MANAGER_DISABLE_TESTS is not set @@ -739,7 +734,6 @@ CONFIG_CRYPTO_TEA=m CONFIG_CRYPTO_TWOFISH=m CONFIG_CRYPTO_ADIANTUM=m CONFIG_CRYPTO_ARC4=m -CONFIG_CRYPTO_CFB=m CONFIG_CRYPTO_HCTR2=m CONFIG_CRYPTO_KEYWRAP=m CONFIG_CRYPTO_LRW=m @@ -886,4 +880,3 @@ CONFIG_ATOMIC64_SELFTEST=y CONFIG_STRING_SELFTEST=y CONFIG_TEST_BITOPS=m CONFIG_TEST_BPF=m -CONFIG_TEST_LIVEPATCH=m diff --git a/arch/s390/configs/defconfig b/arch/s390/configs/defconfig index 42b988873e54..d33f814f78b2 100644 --- a/arch/s390/configs/defconfig +++ b/arch/s390/configs/defconfig @@ -109,7 +109,6 @@ CONFIG_UNIX=y CONFIG_UNIX_DIAG=m CONFIG_XFRM_USER=m CONFIG_NET_KEY=m -CONFIG_SMC=m CONFIG_SMC_DIAG=m CONFIG_INET=y CONFIG_IP_MULTICAST=y @@ -364,6 +363,7 @@ CONFIG_NET_ACT_POLICE=m CONFIG_NET_ACT_GACT=m CONFIG_GACT_PROB=y CONFIG_NET_ACT_MIRRED=m +CONFIG_NET_ACT_IPT=m CONFIG_NET_ACT_NAT=m CONFIG_NET_ACT_PEDIT=m CONFIG_NET_ACT_SIMP=m @@ -426,9 +426,6 @@ CONFIG_SCSI_DH_ALUA=m CONFIG_MD=y CONFIG_BLK_DEV_MD=y # CONFIG_MD_BITMAP_FILE is not set -CONFIG_MD_LINEAR=m -CONFIG_MD_MULTIPATH=m -CONFIG_MD_FAULTY=m CONFIG_MD_CLUSTER=m CONFIG_BCACHE=m CONFIG_BLK_DEV_DM=y @@ -622,7 +619,6 @@ CONFIG_FUSE_FS=y CONFIG_CUSE=m CONFIG_VIRTIO_FS=m CONFIG_OVERLAY_FS=m -CONFIG_NETFS_SUPPORT=m CONFIG_NETFS_STATS=y CONFIG_FSCACHE=y CONFIG_CACHEFILES=m @@ -693,7 +689,6 @@ CONFIG_IMA_DEFAULT_HASH_SHA256=y CONFIG_IMA_WRITE_POLICY=y CONFIG_IMA_APPRAISE=y CONFIG_LSM="yama,loadpin,safesetid,integrity,selinux,smack,tomoyo,apparmor" -CONFIG_INIT_STACK_NONE=y CONFIG_BUG_ON_DATA_CORRUPTION=y CONFIG_CRYPTO_FIPS=y CONFIG_CRYPTO_USER=m @@ -724,11 +719,9 @@ CONFIG_CRYPTO_TEA=m CONFIG_CRYPTO_TWOFISH=m CONFIG_CRYPTO_ADIANTUM=m CONFIG_CRYPTO_ARC4=m -CONFIG_CRYPTO_CFB=m CONFIG_CRYPTO_HCTR2=m CONFIG_CRYPTO_KEYWRAP=m CONFIG_CRYPTO_LRW=m -CONFIG_CRYPTO_OFB=m CONFIG_CRYPTO_PCBC=m CONFIG_CRYPTO_AEGIS128=m CONFIG_CRYPTO_CHACHA20POLY1305=m @@ -815,4 +808,3 @@ CONFIG_KPROBES_SANITY_TEST=m CONFIG_PERCPU_TEST=m CONFIG_ATOMIC64_SELFTEST=y CONFIG_TEST_BPF=m -CONFIG_TEST_LIVEPATCH=m diff --git a/arch/s390/configs/zfcpdump_defconfig b/arch/s390/configs/zfcpdump_defconfig index 30d2a1687665..c51f3ec4eb28 100644 --- a/arch/s390/configs/zfcpdump_defconfig +++ b/arch/s390/configs/zfcpdump_defconfig @@ -8,6 +8,7 @@ CONFIG_BPF_SYSCALL=y # CONFIG_NET_NS is not set CONFIG_BLK_DEV_INITRD=y CONFIG_CC_OPTIMIZE_FOR_SIZE=y +CONFIG_KEXEC=y CONFIG_CRASH_DUMP=y CONFIG_MARCH_Z13=y CONFIG_NR_CPUS=2 @@ -64,7 +65,6 @@ CONFIG_ZFCP=y # CONFIG_MISC_FILESYSTEMS is not set # CONFIG_NETWORK_FILESYSTEMS is not set CONFIG_LSM="yama,loadpin,safesetid,integrity" -CONFIG_INIT_STACK_NONE=y # CONFIG_ZLIB_DFLTCC is not set CONFIG_XZ_DEC_MICROLZMA=y CONFIG_PRINTK_TIME=y diff --git a/arch/s390/include/asm/vdso/data.h b/arch/s390/include/asm/vdso/data.h index 73ee89142666..0e2b40ef69b0 100644 --- a/arch/s390/include/asm/vdso/data.h +++ b/arch/s390/include/asm/vdso/data.h @@ -3,7 +3,6 @@ #define __S390_ASM_VDSO_DATA_H #include <linux/types.h> -#include <vdso/datapage.h> struct arch_vdso_data { __s64 tod_steering_delta; diff --git a/arch/s390/kernel/vdso.c b/arch/s390/kernel/vdso.c index bbaefd84f15e..a45b3a4c91db 100644 --- a/arch/s390/kernel/vdso.c +++ b/arch/s390/kernel/vdso.c @@ -25,10 +25,7 @@ extern char vdso32_start[], vdso32_end[]; static struct vm_special_mapping vvar_mapping; -static union { - struct vdso_data data[CS_BASES]; - u8 page[PAGE_SIZE]; -} vdso_data_store __page_aligned_data; +static union vdso_data_store vdso_data_store __page_aligned_data; struct vdso_data *vdso_data = vdso_data_store.data; diff --git a/arch/s390/pci/pci.c b/arch/s390/pci/pci.c index 676ac74026a8..52a44e353796 100644 --- a/arch/s390/pci/pci.c +++ b/arch/s390/pci/pci.c @@ -252,7 +252,7 @@ resource_size_t pcibios_align_resource(void *data, const struct resource *res, /* combine single writes by using store-block insn */ void __iowrite64_copy(void __iomem *to, const void *from, size_t count) { - zpci_memcpy_toio(to, from, count); + zpci_memcpy_toio(to, from, count * 8); } void __iomem *ioremap_prot(phys_addr_t phys_addr, size_t size, diff --git a/arch/sparc/Makefile b/arch/sparc/Makefile index 5f6035936131..2a03daa68f28 100644 --- a/arch/sparc/Makefile +++ b/arch/sparc/Makefile @@ -60,7 +60,7 @@ libs-y += arch/sparc/prom/ libs-y += arch/sparc/lib/ drivers-$(CONFIG_PM) += arch/sparc/power/ -drivers-$(CONFIG_FB) += arch/sparc/video/ +drivers-$(CONFIG_FB_CORE) += arch/sparc/video/ boot := arch/sparc/boot diff --git a/arch/sparc/video/Makefile b/arch/sparc/video/Makefile index 6baddbd58e4d..d4d83f1702c6 100644 --- a/arch/sparc/video/Makefile +++ b/arch/sparc/video/Makefile @@ -1,3 +1,3 @@ # SPDX-License-Identifier: GPL-2.0-only -obj-$(CONFIG_FB) += fbdev.o +obj-$(CONFIG_FB_CORE) += fbdev.o diff --git a/arch/um/drivers/ubd_kern.c b/arch/um/drivers/ubd_kern.c index 92ee2697ff39..63fc062add70 100644 --- a/arch/um/drivers/ubd_kern.c +++ b/arch/um/drivers/ubd_kern.c @@ -108,8 +108,6 @@ static inline void ubd_set_bit(__u64 bit, unsigned char *data) static DEFINE_MUTEX(ubd_lock); static DEFINE_MUTEX(ubd_mutex); /* replaces BKL, might not be needed */ -static int ubd_open(struct gendisk *disk, blk_mode_t mode); -static void ubd_release(struct gendisk *disk); static int ubd_ioctl(struct block_device *bdev, blk_mode_t mode, unsigned int cmd, unsigned long arg); static int ubd_getgeo(struct block_device *bdev, struct hd_geometry *geo); @@ -118,16 +116,11 @@ static int ubd_getgeo(struct block_device *bdev, struct hd_geometry *geo); static const struct block_device_operations ubd_blops = { .owner = THIS_MODULE, - .open = ubd_open, - .release = ubd_release, .ioctl = ubd_ioctl, .compat_ioctl = blkdev_compat_ptr_ioctl, .getgeo = ubd_getgeo, }; -/* Protected by ubd_lock */ -static struct gendisk *ubd_gendisk[MAX_DEV]; - #ifdef CONFIG_BLK_DEV_UBD_SYNC #define OPEN_FLAGS ((struct openflags) { .r = 1, .w = 1, .s = 1, .c = 0, \ .cl = 1 }) @@ -155,7 +148,6 @@ struct ubd { * backing or the cow file. */ char *file; char *serial; - int count; int fd; __u64 size; struct openflags boot_openflags; @@ -165,7 +157,7 @@ struct ubd { unsigned no_trim:1; struct cow cow; struct platform_device pdev; - struct request_queue *queue; + struct gendisk *disk; struct blk_mq_tag_set tag_set; spinlock_t lock; }; @@ -181,7 +173,6 @@ struct ubd { #define DEFAULT_UBD { \ .file = NULL, \ .serial = NULL, \ - .count = 0, \ .fd = -1, \ .size = -1, \ .boot_openflags = OPEN_FLAGS, \ @@ -774,8 +765,6 @@ static int ubd_open_dev(struct ubd *ubd_dev) ubd_dev->fd = fd; if(ubd_dev->cow.file != NULL){ - blk_queue_max_hw_sectors(ubd_dev->queue, 8 * sizeof(long)); - err = -ENOMEM; ubd_dev->cow.bitmap = vmalloc(ubd_dev->cow.bitmap_len); if(ubd_dev->cow.bitmap == NULL){ @@ -797,11 +786,6 @@ static int ubd_open_dev(struct ubd *ubd_dev) if(err < 0) goto error; ubd_dev->cow.fd = err; } - if (ubd_dev->no_trim == 0) { - blk_queue_max_discard_sectors(ubd_dev->queue, UBD_MAX_REQUEST); - blk_queue_max_write_zeroes_sectors(ubd_dev->queue, UBD_MAX_REQUEST); - } - blk_queue_flag_set(QUEUE_FLAG_NONROT, ubd_dev->queue); return 0; error: os_close_file(ubd_dev->fd); @@ -851,27 +835,6 @@ static const struct attribute_group *ubd_attr_groups[] = { NULL, }; -static int ubd_disk_register(int major, u64 size, int unit, - struct gendisk *disk) -{ - disk->major = major; - disk->first_minor = unit << UBD_SHIFT; - disk->minors = 1 << UBD_SHIFT; - disk->fops = &ubd_blops; - set_capacity(disk, size / 512); - sprintf(disk->disk_name, "ubd%c", 'a' + unit); - - ubd_devs[unit].pdev.id = unit; - ubd_devs[unit].pdev.name = DRIVER_NAME; - ubd_devs[unit].pdev.dev.release = ubd_device_release; - dev_set_drvdata(&ubd_devs[unit].pdev.dev, &ubd_devs[unit]); - platform_device_register(&ubd_devs[unit].pdev); - - disk->private_data = &ubd_devs[unit]; - disk->queue = ubd_devs[unit].queue; - return device_add_disk(&ubd_devs[unit].pdev.dev, disk, ubd_attr_groups); -} - #define ROUND_BLOCK(n) ((n + (SECTOR_SIZE - 1)) & (-SECTOR_SIZE)) static const struct blk_mq_ops ubd_mq_ops = { @@ -881,18 +844,36 @@ static const struct blk_mq_ops ubd_mq_ops = { static int ubd_add(int n, char **error_out) { struct ubd *ubd_dev = &ubd_devs[n]; + struct queue_limits lim = { + .max_segments = MAX_SG, + .seg_boundary_mask = PAGE_SIZE - 1, + }; struct gendisk *disk; int err = 0; if(ubd_dev->file == NULL) goto out; + if (ubd_dev->cow.file) + lim.max_hw_sectors = 8 * sizeof(long); + if (!ubd_dev->no_trim) { + lim.max_hw_discard_sectors = UBD_MAX_REQUEST; + lim.max_write_zeroes_sectors = UBD_MAX_REQUEST; + } + err = ubd_file_size(ubd_dev, &ubd_dev->size); if(err < 0){ *error_out = "Couldn't determine size of device's file"; goto out; } + err = ubd_open_dev(ubd_dev); + if (err) { + pr_err("ubd%c: Can't open \"%s\": errno = %d\n", + 'a' + n, ubd_dev->file, -err); + goto out; + } + ubd_dev->size = ROUND_BLOCK(ubd_dev->size); ubd_dev->tag_set.ops = &ubd_mq_ops; @@ -904,29 +885,43 @@ static int ubd_add(int n, char **error_out) err = blk_mq_alloc_tag_set(&ubd_dev->tag_set); if (err) - goto out; + goto out_close; - disk = blk_mq_alloc_disk(&ubd_dev->tag_set, ubd_dev); + disk = blk_mq_alloc_disk(&ubd_dev->tag_set, &lim, ubd_dev); if (IS_ERR(disk)) { err = PTR_ERR(disk); goto out_cleanup_tags; } - ubd_dev->queue = disk->queue; - blk_queue_write_cache(ubd_dev->queue, true, false); - blk_queue_max_segments(ubd_dev->queue, MAX_SG); - blk_queue_segment_boundary(ubd_dev->queue, PAGE_SIZE - 1); - err = ubd_disk_register(UBD_MAJOR, ubd_dev->size, n, disk); + blk_queue_flag_set(QUEUE_FLAG_NONROT, disk->queue); + blk_queue_write_cache(disk->queue, true, false); + disk->major = UBD_MAJOR; + disk->first_minor = n << UBD_SHIFT; + disk->minors = 1 << UBD_SHIFT; + disk->fops = &ubd_blops; + set_capacity(disk, ubd_dev->size / 512); + sprintf(disk->disk_name, "ubd%c", 'a' + n); + disk->private_data = ubd_dev; + set_disk_ro(disk, !ubd_dev->openflags.w); + + ubd_dev->pdev.id = n; + ubd_dev->pdev.name = DRIVER_NAME; + ubd_dev->pdev.dev.release = ubd_device_release; + dev_set_drvdata(&ubd_dev->pdev.dev, ubd_dev); + platform_device_register(&ubd_dev->pdev); + + err = device_add_disk(&ubd_dev->pdev.dev, disk, ubd_attr_groups); if (err) goto out_cleanup_disk; - ubd_gendisk[n] = disk; return 0; out_cleanup_disk: put_disk(disk); out_cleanup_tags: blk_mq_free_tag_set(&ubd_dev->tag_set); +out_close: + ubd_close_dev(ubd_dev); out: return err; } @@ -1012,7 +1007,6 @@ static int ubd_id(char **str, int *start_out, int *end_out) static int ubd_remove(int n, char **error_out) { - struct gendisk *disk = ubd_gendisk[n]; struct ubd *ubd_dev; int err = -ENODEV; @@ -1023,15 +1017,15 @@ static int ubd_remove(int n, char **error_out) if(ubd_dev->file == NULL) goto out; - /* you cannot remove a open disk */ - err = -EBUSY; - if(ubd_dev->count > 0) - goto out; + if (ubd_dev->disk) { + /* you cannot remove a open disk */ + err = -EBUSY; + if (disk_openers(ubd_dev->disk)) + goto out; - ubd_gendisk[n] = NULL; - if(disk != NULL){ - del_gendisk(disk); - put_disk(disk); + del_gendisk(ubd_dev->disk); + ubd_close_dev(ubd_dev); + put_disk(ubd_dev->disk); } err = 0; @@ -1153,37 +1147,6 @@ static int __init ubd_driver_init(void){ device_initcall(ubd_driver_init); -static int ubd_open(struct gendisk *disk, blk_mode_t mode) -{ - struct ubd *ubd_dev = disk->private_data; - int err = 0; - - mutex_lock(&ubd_mutex); - if(ubd_dev->count == 0){ - err = ubd_open_dev(ubd_dev); - if(err){ - printk(KERN_ERR "%s: Can't open \"%s\": errno = %d\n", - disk->disk_name, ubd_dev->file, -err); - goto out; - } - } - ubd_dev->count++; - set_disk_ro(disk, !ubd_dev->openflags.w); -out: - mutex_unlock(&ubd_mutex); - return err; -} - -static void ubd_release(struct gendisk *disk) -{ - struct ubd *ubd_dev = disk->private_data; - - mutex_lock(&ubd_mutex); - if(--ubd_dev->count == 0) - ubd_close_dev(ubd_dev); - mutex_unlock(&ubd_mutex); -} - static void cowify_bitmap(__u64 io_offset, int length, unsigned long *cow_mask, __u64 *cow_offset, unsigned long *bitmap, __u64 bitmap_offset, unsigned long *bitmap_words, diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 5edec175b9bf..854ab38a359a 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -496,6 +496,15 @@ config X86_CPU_RESCTRL Say N if unsure. +config X86_FRED + bool "Flexible Return and Event Delivery" + depends on X86_64 + help + When enabled, try to use Flexible Return and Event Delivery + instead of the legacy SYSCALL/SYSENTER/IDT architecture for + ring transitions and exception/interrupt handling if the + system supports. + if X86_32 config X86_BIGSMP bool "Support for big SMP systems with more than 8 CPUs" diff --git a/arch/x86/entry/Makefile b/arch/x86/entry/Makefile index ca2fe186994b..c93e7f5c2a06 100644 --- a/arch/x86/entry/Makefile +++ b/arch/x86/entry/Makefile @@ -18,6 +18,9 @@ obj-y += vdso/ obj-y += vsyscall/ obj-$(CONFIG_PREEMPTION) += thunk_$(BITS).o +CFLAGS_entry_fred.o += -fno-stack-protector +CFLAGS_REMOVE_entry_fred.o += -pg $(CC_FLAGS_FTRACE) +obj-$(CONFIG_X86_FRED) += entry_64_fred.o entry_fred.o + obj-$(CONFIG_IA32_EMULATION) += entry_64_compat.o syscall_32.o obj-$(CONFIG_X86_X32_ABI) += syscall_x32.o - diff --git a/arch/x86/entry/calling.h b/arch/x86/entry/calling.h index 9f1d94790a54..1c3b561528fd 100644 --- a/arch/x86/entry/calling.h +++ b/arch/x86/entry/calling.h @@ -65,7 +65,7 @@ For 32-bit we have the following conventions - kernel is built with * for assembly code: */ -.macro PUSH_REGS rdx=%rdx rcx=%rcx rax=%rax save_ret=0 +.macro PUSH_REGS rdx=%rdx rcx=%rcx rax=%rax save_ret=0 unwind_hint=1 .if \save_ret pushq %rsi /* pt_regs->si */ movq 8(%rsp), %rsi /* temporarily store the return address in %rsi */ @@ -87,14 +87,17 @@ For 32-bit we have the following conventions - kernel is built with pushq %r13 /* pt_regs->r13 */ pushq %r14 /* pt_regs->r14 */ pushq %r15 /* pt_regs->r15 */ + + .if \unwind_hint UNWIND_HINT_REGS + .endif .if \save_ret pushq %rsi /* return address on top of stack */ .endif .endm -.macro CLEAR_REGS +.macro CLEAR_REGS clear_bp=1 /* * Sanitize registers of values that a speculation attack might * otherwise want to exploit. The lower registers are likely clobbered @@ -109,7 +112,9 @@ For 32-bit we have the following conventions - kernel is built with xorl %r10d, %r10d /* nospec r10 */ xorl %r11d, %r11d /* nospec r11 */ xorl %ebx, %ebx /* nospec rbx */ + .if \clear_bp xorl %ebp, %ebp /* nospec rbp */ + .endif xorl %r12d, %r12d /* nospec r12 */ xorl %r13d, %r13d /* nospec r13 */ xorl %r14d, %r14d /* nospec r14 */ @@ -117,9 +122,9 @@ For 32-bit we have the following conventions - kernel is built with .endm -.macro PUSH_AND_CLEAR_REGS rdx=%rdx rcx=%rcx rax=%rax save_ret=0 - PUSH_REGS rdx=\rdx, rcx=\rcx, rax=\rax, save_ret=\save_ret - CLEAR_REGS +.macro PUSH_AND_CLEAR_REGS rdx=%rdx rcx=%rcx rax=%rax save_ret=0 clear_bp=1 unwind_hint=1 + PUSH_REGS rdx=\rdx, rcx=\rcx, rax=\rax, save_ret=\save_ret unwind_hint=\unwind_hint + CLEAR_REGS clear_bp=\clear_bp .endm .macro POP_REGS pop_rdi=1 @@ -239,17 +244,19 @@ For 32-bit we have the following conventions - kernel is built with .Ldone_\@: .endm -.macro RESTORE_CR3 scratch_reg:req save_reg:req +/* Restore CR3 from a kernel context. May restore a user CR3 value. */ +.macro PARANOID_RESTORE_CR3 scratch_reg:req save_reg:req ALTERNATIVE "jmp .Lend_\@", "", X86_FEATURE_PTI - ALTERNATIVE "jmp .Lwrcr3_\@", "", X86_FEATURE_PCID - /* - * KERNEL pages can always resume with NOFLUSH as we do - * explicit flushes. + * If CR3 contained the kernel page tables at the paranoid exception + * entry, then there is nothing to restore as CR3 is not modified while + * handling the exception. */ bt $PTI_USER_PGTABLE_BIT, \save_reg - jnc .Lnoflush_\@ + jnc .Lend_\@ + + ALTERNATIVE "jmp .Lwrcr3_\@", "", X86_FEATURE_PCID /* * Check if there's a pending flush for the user ASID we're @@ -257,20 +264,12 @@ For 32-bit we have the following conventions - kernel is built with */ movq \save_reg, \scratch_reg andq $(0x7FF), \scratch_reg - bt \scratch_reg, THIS_CPU_user_pcid_flush_mask - jnc .Lnoflush_\@ - btr \scratch_reg, THIS_CPU_user_pcid_flush_mask - jmp .Lwrcr3_\@ + jc .Lwrcr3_\@ -.Lnoflush_\@: SET_NOFLUSH_BIT \save_reg .Lwrcr3_\@: - /* - * The CR3 write could be avoided when not changing its value, - * but would require a CR3 read *and* a scratch register. - */ movq \save_reg, %cr3 .Lend_\@: .endm @@ -285,7 +284,7 @@ For 32-bit we have the following conventions - kernel is built with .endm .macro SAVE_AND_SWITCH_TO_KERNEL_CR3 scratch_reg:req save_reg:req .endm -.macro RESTORE_CR3 scratch_reg:req save_reg:req +.macro PARANOID_RESTORE_CR3 scratch_reg:req save_reg:req .endm #endif diff --git a/arch/x86/entry/entry.S b/arch/x86/entry/entry.S index 8c8d38f0cb1d..003379049924 100644 --- a/arch/x86/entry/entry.S +++ b/arch/x86/entry/entry.S @@ -6,6 +6,9 @@ #include <linux/export.h> #include <linux/linkage.h> #include <asm/msr-index.h> +#include <asm/unwind_hints.h> +#include <asm/segment.h> +#include <asm/cache.h> .pushsection .noinstr.text, "ax" @@ -20,3 +23,23 @@ SYM_FUNC_END(entry_ibpb) EXPORT_SYMBOL_GPL(entry_ibpb); .popsection + +/* + * Define the VERW operand that is disguised as entry code so that + * it can be referenced with KPTI enabled. This ensure VERW can be + * used late in exit-to-user path after page tables are switched. + */ +.pushsection .entry.text, "ax" + +.align L1_CACHE_BYTES, 0xcc +SYM_CODE_START_NOALIGN(mds_verw_sel) + UNWIND_HINT_UNDEFINED + ANNOTATE_NOENDBR + .word __KERNEL_DS +.align L1_CACHE_BYTES, 0xcc +SYM_CODE_END(mds_verw_sel); +/* For KVM */ +EXPORT_SYMBOL_GPL(mds_verw_sel); + +.popsection + diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S index c73047bf9f4b..b8be0164385c 100644 --- a/arch/x86/entry/entry_32.S +++ b/arch/x86/entry/entry_32.S @@ -649,10 +649,6 @@ SYM_CODE_START_LOCAL(asm_\cfunc) SYM_CODE_END(asm_\cfunc) .endm -.macro idtentry_sysvec vector cfunc - idtentry \vector asm_\cfunc \cfunc has_error_code=0 -.endm - /* * Include the defines which emit the idt entries which are shared * shared between 32 and 64 bit and emit the __irqentry_text_* markers @@ -885,6 +881,7 @@ SYM_FUNC_START(entry_SYSENTER_32) BUG_IF_WRONG_CR3 no_user_check=1 popfl popl %eax + CLEAR_CPU_BUFFERS /* * Return back to the vDSO, which will pop ecx and edx. @@ -954,6 +951,7 @@ restore_all_switch_stack: /* Restore user state */ RESTORE_REGS pop=4 # skip orig_eax/error_code + CLEAR_CPU_BUFFERS .Lirq_return: /* * ARCH_HAS_MEMBARRIER_SYNC_CORE rely on IRET core serialization @@ -1146,6 +1144,7 @@ SYM_CODE_START(asm_exc_nmi) /* Not on SYSENTER stack. */ call exc_nmi + CLEAR_CPU_BUFFERS jmp .Lnmi_return .Lnmi_from_sysenter_stack: diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S index c40f89ab1b4c..a19ed151a813 100644 --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -161,6 +161,7 @@ syscall_return_via_sysret: SYM_INNER_LABEL(entry_SYSRETQ_unsafe_stack, SYM_L_GLOBAL) ANNOTATE_NOENDBR swapgs + CLEAR_CPU_BUFFERS sysretq SYM_INNER_LABEL(entry_SYSRETQ_end, SYM_L_GLOBAL) ANNOTATE_NOENDBR @@ -247,7 +248,13 @@ SYM_CODE_START(ret_from_fork_asm) * and unwind should work normally. */ UNWIND_HINT_REGS + +#ifdef CONFIG_X86_FRED + ALTERNATIVE "jmp swapgs_restore_regs_and_return_to_usermode", \ + "jmp asm_fred_exit_user", X86_FEATURE_FRED +#else jmp swapgs_restore_regs_and_return_to_usermode +#endif SYM_CODE_END(ret_from_fork_asm) .popsection @@ -370,14 +377,6 @@ SYM_CODE_END(\asmsym) idtentry \vector asm_\cfunc \cfunc has_error_code=1 .endm -/* - * System vectors which invoke their handlers directly and are not - * going through the regular common device interrupt handling code. - */ -.macro idtentry_sysvec vector cfunc - idtentry \vector asm_\cfunc \cfunc has_error_code=0 -.endm - /** * idtentry_mce_db - Macro to generate entry stubs for #MC and #DB * @vector: Vector number @@ -573,6 +572,7 @@ SYM_INNER_LABEL(swapgs_restore_regs_and_return_to_usermode, SYM_L_GLOBAL) .Lswapgs_and_iret: swapgs + CLEAR_CPU_BUFFERS /* Assert that the IRET frame indicates user mode. */ testb $3, 8(%rsp) jnz .Lnative_iret @@ -723,6 +723,8 @@ native_irq_return_ldt: */ popq %rax /* Restore user RAX */ + CLEAR_CPU_BUFFERS + /* * RSP now points to an ordinary IRET frame, except that the page * is read-only and RSP[31:16] are preloaded with the userspace @@ -968,14 +970,14 @@ SYM_CODE_START_LOCAL(paranoid_exit) IBRS_EXIT save_reg=%r15 /* - * The order of operations is important. RESTORE_CR3 requires + * The order of operations is important. PARANOID_RESTORE_CR3 requires * kernel GSBASE. * * NB to anyone to try to optimize this code: this code does * not execute at all for exceptions from user mode. Those * exceptions go through error_return instead. */ - RESTORE_CR3 scratch_reg=%rax save_reg=%r14 + PARANOID_RESTORE_CR3 scratch_reg=%rax save_reg=%r14 /* Handle the three GSBASE cases */ ALTERNATIVE "jmp .Lparanoid_exit_checkgs", "", X86_FEATURE_FSGSBASE @@ -1404,8 +1406,7 @@ end_repeat_nmi: /* Always restore stashed SPEC_CTRL value (see paranoid_entry) */ IBRS_EXIT save_reg=%r15 - /* Always restore stashed CR3 value (see paranoid_entry) */ - RESTORE_CR3 scratch_reg=%r15 save_reg=%r14 + PARANOID_RESTORE_CR3 scratch_reg=%r15 save_reg=%r14 /* * The above invocation of paranoid_entry stored the GSBASE @@ -1450,6 +1451,12 @@ nmi_restore: movq $0, 5*8(%rsp) /* clear "NMI executing" */ /* + * Skip CLEAR_CPU_BUFFERS here, since it only helps in rare cases like + * NMI in kernel after user state is restored. For an unprivileged user + * these conditions are hard to meet. + */ + + /* * iretq reads the "iret" frame and exits the NMI stack in a * single instruction. We are returning to kernel mode, so this * cannot result in a fault. Similarly, we don't need to worry @@ -1466,6 +1473,7 @@ SYM_CODE_START(entry_SYSCALL32_ignore) UNWIND_HINT_END_OF_STACK ENDBR mov $-ENOSYS, %eax + CLEAR_CPU_BUFFERS sysretl SYM_CODE_END(entry_SYSCALL32_ignore) diff --git a/arch/x86/entry/entry_64_compat.S b/arch/x86/entry/entry_64_compat.S index de94e2e84ecc..eabf48c4d4b4 100644 --- a/arch/x86/entry/entry_64_compat.S +++ b/arch/x86/entry/entry_64_compat.S @@ -270,6 +270,7 @@ SYM_INNER_LABEL(entry_SYSRETL_compat_unsafe_stack, SYM_L_GLOBAL) xorl %r9d, %r9d xorl %r10d, %r10d swapgs + CLEAR_CPU_BUFFERS sysretl SYM_INNER_LABEL(entry_SYSRETL_compat_end, SYM_L_GLOBAL) ANNOTATE_NOENDBR diff --git a/arch/x86/entry/entry_64_fred.S b/arch/x86/entry/entry_64_fred.S new file mode 100644 index 000000000000..a02bc6f3d2e6 --- /dev/null +++ b/arch/x86/entry/entry_64_fred.S @@ -0,0 +1,131 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * The actual FRED entry points. + */ + +#include <linux/export.h> + +#include <asm/asm.h> +#include <asm/fred.h> +#include <asm/segment.h> + +#include "calling.h" + + .code64 + .section .noinstr.text, "ax" + +.macro FRED_ENTER + UNWIND_HINT_END_OF_STACK + ENDBR + PUSH_AND_CLEAR_REGS + movq %rsp, %rdi /* %rdi -> pt_regs */ +.endm + +.macro FRED_EXIT + UNWIND_HINT_REGS + POP_REGS +.endm + +/* + * The new RIP value that FRED event delivery establishes is + * IA32_FRED_CONFIG & ~FFFH for events that occur in ring 3. + * Thus the FRED ring 3 entry point must be 4K page aligned. + */ + .align 4096 + +SYM_CODE_START_NOALIGN(asm_fred_entrypoint_user) + FRED_ENTER + call fred_entry_from_user +SYM_INNER_LABEL(asm_fred_exit_user, SYM_L_GLOBAL) + FRED_EXIT +1: ERETU + + _ASM_EXTABLE_TYPE(1b, asm_fred_entrypoint_user, EX_TYPE_ERETU) +SYM_CODE_END(asm_fred_entrypoint_user) + +/* + * The new RIP value that FRED event delivery establishes is + * (IA32_FRED_CONFIG & ~FFFH) + 256 for events that occur in + * ring 0, i.e., asm_fred_entrypoint_user + 256. + */ + .org asm_fred_entrypoint_user + 256, 0xcc +SYM_CODE_START_NOALIGN(asm_fred_entrypoint_kernel) + FRED_ENTER + call fred_entry_from_kernel + FRED_EXIT + ERETS +SYM_CODE_END(asm_fred_entrypoint_kernel) + +#if IS_ENABLED(CONFIG_KVM_INTEL) +SYM_FUNC_START(asm_fred_entry_from_kvm) + push %rbp + mov %rsp, %rbp + + UNWIND_HINT_SAVE + + /* + * Both IRQ and NMI from VMX can be handled on current task stack + * because there is no need to protect from reentrancy and the call + * stack leading to this helper is effectively constant and shallow + * (relatively speaking). Do the same when FRED is active, i.e., no + * need to check current stack level for a stack switch. + * + * Emulate the FRED-defined redzone and stack alignment. + */ + sub $(FRED_CONFIG_REDZONE_AMOUNT << 6), %rsp + and $FRED_STACK_FRAME_RSP_MASK, %rsp + + /* + * Start to push a FRED stack frame, which is always 64 bytes: + * + * +--------+-----------------+ + * | Bytes | Usage | + * +--------+-----------------+ + * | 63:56 | Reserved | + * | 55:48 | Event Data | + * | 47:40 | SS + Event Info | + * | 39:32 | RSP | + * | 31:24 | RFLAGS | + * | 23:16 | CS + Aux Info | + * | 15:8 | RIP | + * | 7:0 | Error Code | + * +--------+-----------------+ + */ + push $0 /* Reserved, must be 0 */ + push $0 /* Event data, 0 for IRQ/NMI */ + push %rdi /* fred_ss handed in by the caller */ + push %rbp + pushf + mov $__KERNEL_CS, %rax + push %rax + + /* + * Unlike the IDT event delivery, FRED _always_ pushes an error code + * after pushing the return RIP, thus the CALL instruction CANNOT be + * used here to push the return RIP, otherwise there is no chance to + * push an error code before invoking the IRQ/NMI handler. + * + * Use LEA to get the return RIP and push it, then push an error code. + */ + lea 1f(%rip), %rax + push %rax /* Return RIP */ + push $0 /* Error code, 0 for IRQ/NMI */ + + PUSH_AND_CLEAR_REGS clear_bp=0 unwind_hint=0 + movq %rsp, %rdi /* %rdi -> pt_regs */ + call __fred_entry_from_kvm /* Call the C entry point */ + POP_REGS + ERETS +1: + /* + * Objtool doesn't understand what ERETS does, this hint tells it that + * yes, we'll reach here and with what stack state. A save/restore pair + * isn't strictly needed, but it's the simplest form. + */ + UNWIND_HINT_RESTORE + pop %rbp + RET + +SYM_FUNC_END(asm_fred_entry_from_kvm) +EXPORT_SYMBOL_GPL(asm_fred_entry_from_kvm); +#endif diff --git a/arch/x86/entry/entry_fred.c b/arch/x86/entry/entry_fred.c new file mode 100644 index 000000000000..ac120cbdaaf2 --- /dev/null +++ b/arch/x86/entry/entry_fred.c @@ -0,0 +1,294 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * The FRED specific kernel/user entry functions which are invoked from + * assembly code and dispatch to the associated handlers. + */ +#include <linux/kernel.h> +#include <linux/kdebug.h> +#include <linux/nospec.h> + +#include <asm/desc.h> +#include <asm/fred.h> +#include <asm/idtentry.h> +#include <asm/syscall.h> +#include <asm/trapnr.h> +#include <asm/traps.h> + +/* FRED EVENT_TYPE_OTHER vector numbers */ +#define FRED_SYSCALL 1 +#define FRED_SYSENTER 2 + +static noinstr void fred_bad_type(struct pt_regs *regs, unsigned long error_code) +{ + irqentry_state_t irq_state = irqentry_nmi_enter(regs); + + instrumentation_begin(); + + /* Panic on events from a high stack level */ + if (regs->fred_cs.sl > 0) { + pr_emerg("PANIC: invalid or fatal FRED event; event type %u " + "vector %u error 0x%lx aux 0x%lx at %04x:%016lx\n", + regs->fred_ss.type, regs->fred_ss.vector, regs->orig_ax, + fred_event_data(regs), regs->cs, regs->ip); + die("invalid or fatal FRED event", regs, regs->orig_ax); + panic("invalid or fatal FRED event"); + } else { + unsigned long flags = oops_begin(); + int sig = SIGKILL; + + pr_alert("BUG: invalid or fatal FRED event; event type %u " + "vector %u error 0x%lx aux 0x%lx at %04x:%016lx\n", + regs->fred_ss.type, regs->fred_ss.vector, regs->orig_ax, + fred_event_data(regs), regs->cs, regs->ip); + + if (__die("Invalid or fatal FRED event", regs, regs->orig_ax)) + sig = 0; + + oops_end(flags, regs, sig); + } + + instrumentation_end(); + irqentry_nmi_exit(regs, irq_state); +} + +static noinstr void fred_intx(struct pt_regs *regs) +{ + switch (regs->fred_ss.vector) { + /* Opcode 0xcd, 0x3, NOT INT3 (opcode 0xcc) */ + case X86_TRAP_BP: + return exc_int3(regs); + + /* Opcode 0xcd, 0x4, NOT INTO (opcode 0xce) */ + case X86_TRAP_OF: + return exc_overflow(regs); + +#ifdef CONFIG_IA32_EMULATION + /* INT80 */ + case IA32_SYSCALL_VECTOR: + if (ia32_enabled()) + return int80_emulation(regs); + fallthrough; +#endif + + default: + return exc_general_protection(regs, 0); + } +} + +static __always_inline void fred_other(struct pt_regs *regs) +{ + /* The compiler can fold these conditions into a single test */ + if (likely(regs->fred_ss.vector == FRED_SYSCALL && regs->fred_ss.lm)) { + regs->orig_ax = regs->ax; + regs->ax = -ENOSYS; + do_syscall_64(regs, regs->orig_ax); + return; + } else if (ia32_enabled() && + likely(regs->fred_ss.vector == FRED_SYSENTER && !regs->fred_ss.lm)) { + regs->orig_ax = regs->ax; + regs->ax = -ENOSYS; + do_fast_syscall_32(regs); + return; + } else { + exc_invalid_op(regs); + return; + } +} + +#define SYSVEC(_vector, _function) [_vector - FIRST_SYSTEM_VECTOR] = fred_sysvec_##_function + +static idtentry_t sysvec_table[NR_SYSTEM_VECTORS] __ro_after_init = { + SYSVEC(ERROR_APIC_VECTOR, error_interrupt), + SYSVEC(SPURIOUS_APIC_VECTOR, spurious_apic_interrupt), + SYSVEC(LOCAL_TIMER_VECTOR, apic_timer_interrupt), + SYSVEC(X86_PLATFORM_IPI_VECTOR, x86_platform_ipi), + + SYSVEC(RESCHEDULE_VECTOR, reschedule_ipi), + SYSVEC(CALL_FUNCTION_SINGLE_VECTOR, call_function_single), + SYSVEC(CALL_FUNCTION_VECTOR, call_function), + SYSVEC(REBOOT_VECTOR, reboot), + + SYSVEC(THRESHOLD_APIC_VECTOR, threshold), + SYSVEC(DEFERRED_ERROR_VECTOR, deferred_error), + SYSVEC(THERMAL_APIC_VECTOR, thermal), + + SYSVEC(IRQ_WORK_VECTOR, irq_work), + + SYSVEC(POSTED_INTR_VECTOR, kvm_posted_intr_ipi), + SYSVEC(POSTED_INTR_WAKEUP_VECTOR, kvm_posted_intr_wakeup_ipi), + SYSVEC(POSTED_INTR_NESTED_VECTOR, kvm_posted_intr_nested_ipi), +}; + +static bool fred_setup_done __initdata; + +void __init fred_install_sysvec(unsigned int sysvec, idtentry_t handler) +{ + if (WARN_ON_ONCE(sysvec < FIRST_SYSTEM_VECTOR)) + return; + + if (WARN_ON_ONCE(fred_setup_done)) + return; + + if (!WARN_ON_ONCE(sysvec_table[sysvec - FIRST_SYSTEM_VECTOR])) + sysvec_table[sysvec - FIRST_SYSTEM_VECTOR] = handler; +} + +static noinstr void fred_handle_spurious_interrupt(struct pt_regs *regs) +{ + spurious_interrupt(regs, regs->fred_ss.vector); +} + +void __init fred_complete_exception_setup(void) +{ + unsigned int vector; + + for (vector = 0; vector < FIRST_EXTERNAL_VECTOR; vector++) + set_bit(vector, system_vectors); + + for (vector = 0; vector < NR_SYSTEM_VECTORS; vector++) { + if (sysvec_table[vector]) + set_bit(vector + FIRST_SYSTEM_VECTOR, system_vectors); + else + sysvec_table[vector] = fred_handle_spurious_interrupt; + } + fred_setup_done = true; +} + +static noinstr void fred_extint(struct pt_regs *regs) +{ + unsigned int vector = regs->fred_ss.vector; + unsigned int index = array_index_nospec(vector - FIRST_SYSTEM_VECTOR, + NR_SYSTEM_VECTORS); + + if (WARN_ON_ONCE(vector < FIRST_EXTERNAL_VECTOR)) + return; + + if (likely(vector >= FIRST_SYSTEM_VECTOR)) { + irqentry_state_t state = irqentry_enter(regs); + + instrumentation_begin(); + sysvec_table[index](regs); + instrumentation_end(); + irqentry_exit(regs, state); + } else { + common_interrupt(regs, vector); + } +} + +static noinstr void fred_hwexc(struct pt_regs *regs, unsigned long error_code) +{ + /* Optimize for #PF. That's the only exception which matters performance wise */ + if (likely(regs->fred_ss.vector == X86_TRAP_PF)) + return exc_page_fault(regs, error_code); + + switch (regs->fred_ss.vector) { + case X86_TRAP_DE: return exc_divide_error(regs); + case X86_TRAP_DB: return fred_exc_debug(regs); + case X86_TRAP_BR: return exc_bounds(regs); + case X86_TRAP_UD: return exc_invalid_op(regs); + case X86_TRAP_NM: return exc_device_not_available(regs); + case X86_TRAP_DF: return exc_double_fault(regs, error_code); + case X86_TRAP_TS: return exc_invalid_tss(regs, error_code); + case X86_TRAP_NP: return exc_segment_not_present(regs, error_code); + case X86_TRAP_SS: return exc_stack_segment(regs, error_code); + case X86_TRAP_GP: return exc_general_protection(regs, error_code); + case X86_TRAP_MF: return exc_coprocessor_error(regs); + case X86_TRAP_AC: return exc_alignment_check(regs, error_code); + case X86_TRAP_XF: return exc_simd_coprocessor_error(regs); + +#ifdef CONFIG_X86_MCE + case X86_TRAP_MC: return fred_exc_machine_check(regs); +#endif +#ifdef CONFIG_INTEL_TDX_GUEST + case X86_TRAP_VE: return exc_virtualization_exception(regs); +#endif +#ifdef CONFIG_X86_CET + case X86_TRAP_CP: return exc_control_protection(regs, error_code); +#endif + default: return fred_bad_type(regs, error_code); + } + +} + +static noinstr void fred_swexc(struct pt_regs *regs, unsigned long error_code) +{ + switch (regs->fred_ss.vector) { + case X86_TRAP_BP: return exc_int3(regs); + case X86_TRAP_OF: return exc_overflow(regs); + default: return fred_bad_type(regs, error_code); + } +} + +__visible noinstr void fred_entry_from_user(struct pt_regs *regs) +{ + unsigned long error_code = regs->orig_ax; + + /* Invalidate orig_ax so that syscall_get_nr() works correctly */ + regs->orig_ax = -1; + + switch (regs->fred_ss.type) { + case EVENT_TYPE_EXTINT: + return fred_extint(regs); + case EVENT_TYPE_NMI: + if (likely(regs->fred_ss.vector == X86_TRAP_NMI)) + return fred_exc_nmi(regs); + break; + case EVENT_TYPE_HWEXC: + return fred_hwexc(regs, error_code); + case EVENT_TYPE_SWINT: + return fred_intx(regs); + case EVENT_TYPE_PRIV_SWEXC: + if (likely(regs->fred_ss.vector == X86_TRAP_DB)) + return fred_exc_debug(regs); + break; + case EVENT_TYPE_SWEXC: + return fred_swexc(regs, error_code); + case EVENT_TYPE_OTHER: + return fred_other(regs); + default: break; + } + + return fred_bad_type(regs, error_code); +} + +__visible noinstr void fred_entry_from_kernel(struct pt_regs *regs) +{ + unsigned long error_code = regs->orig_ax; + + /* Invalidate orig_ax so that syscall_get_nr() works correctly */ + regs->orig_ax = -1; + + switch (regs->fred_ss.type) { + case EVENT_TYPE_EXTINT: + return fred_extint(regs); + case EVENT_TYPE_NMI: + if (likely(regs->fred_ss.vector == X86_TRAP_NMI)) + return fred_exc_nmi(regs); + break; + case EVENT_TYPE_HWEXC: + return fred_hwexc(regs, error_code); + case EVENT_TYPE_PRIV_SWEXC: + if (likely(regs->fred_ss.vector == X86_TRAP_DB)) + return fred_exc_debug(regs); + break; + case EVENT_TYPE_SWEXC: + return fred_swexc(regs, error_code); + default: break; + } + + return fred_bad_type(regs, error_code); +} + +#if IS_ENABLED(CONFIG_KVM_INTEL) +__visible noinstr void __fred_entry_from_kvm(struct pt_regs *regs) +{ + switch (regs->fred_ss.type) { + case EVENT_TYPE_EXTINT: + return fred_extint(regs); + case EVENT_TYPE_NMI: + return fred_exc_nmi(regs); + default: + WARN_ON_ONCE(1); + } +} +#endif diff --git a/arch/x86/entry/vsyscall/vsyscall_64.c b/arch/x86/entry/vsyscall/vsyscall_64.c index e0ca8120aea8..a3c0df11d0e6 100644 --- a/arch/x86/entry/vsyscall/vsyscall_64.c +++ b/arch/x86/entry/vsyscall/vsyscall_64.c @@ -76,7 +76,7 @@ static void warn_bad_vsyscall(const char *level, struct pt_regs *regs, if (!show_unhandled_signals) return; - printk_ratelimited("%s%s[%d] %s ip:%lx cs:%lx sp:%lx ax:%lx si:%lx di:%lx\n", + printk_ratelimited("%s%s[%d] %s ip:%lx cs:%x sp:%lx ax:%lx si:%lx di:%lx\n", level, current->comm, task_pid_nr(current), message, regs->ip, regs->cs, regs->sp, regs->ax, regs->si, regs->di); diff --git a/arch/x86/events/amd/core.c b/arch/x86/events/amd/core.c index 81f6d8275b6b..69a3b02e50bb 100644 --- a/arch/x86/events/amd/core.c +++ b/arch/x86/events/amd/core.c @@ -579,7 +579,7 @@ static void amd_pmu_cpu_starting(int cpu) if (!x86_pmu.amd_nb_constraints) return; - nb_id = topology_die_id(cpu); + nb_id = topology_amd_node_id(cpu); WARN_ON_ONCE(nb_id == BAD_APICID); for_each_online_cpu(i) { diff --git a/arch/x86/events/intel/cstate.c b/arch/x86/events/intel/cstate.c index 4b50a3a9818a..326c8cd5aa2d 100644 --- a/arch/x86/events/intel/cstate.c +++ b/arch/x86/events/intel/cstate.c @@ -834,7 +834,7 @@ static int __init cstate_init(void) } if (has_cstate_pkg) { - if (topology_max_die_per_package() > 1) { + if (topology_max_dies_per_package() > 1) { err = perf_pmu_register(&cstate_pkg_pmu, "cstate_die", -1); } else { diff --git a/arch/x86/events/intel/uncore.c b/arch/x86/events/intel/uncore.c index 7927c0b832fa..258e2cdf28fa 100644 --- a/arch/x86/events/intel/uncore.c +++ b/arch/x86/events/intel/uncore.c @@ -1893,7 +1893,7 @@ static int __init intel_uncore_init(void) return -ENODEV; __uncore_max_dies = - topology_max_packages() * topology_max_die_per_package(); + topology_max_packages() * topology_max_dies_per_package(); id = x86_match_cpu(intel_uncore_match); if (!id) { diff --git a/arch/x86/events/intel/uncore_nhmex.c b/arch/x86/events/intel/uncore_nhmex.c index 56eea2c66cfb..92da8aaa5966 100644 --- a/arch/x86/events/intel/uncore_nhmex.c +++ b/arch/x86/events/intel/uncore_nhmex.c @@ -1221,8 +1221,8 @@ void nhmex_uncore_cpu_init(void) uncore_nhmex = true; else nhmex_uncore_mbox.event_descs = wsmex_uncore_mbox_events; - if (nhmex_uncore_cbox.num_boxes > boot_cpu_data.x86_max_cores) - nhmex_uncore_cbox.num_boxes = boot_cpu_data.x86_max_cores; + if (nhmex_uncore_cbox.num_boxes > topology_num_cores_per_package()) + nhmex_uncore_cbox.num_boxes = topology_num_cores_per_package(); uncore_msr_uncores = nhmex_msr_uncores; } /* end of Nehalem-EX uncore support */ diff --git a/arch/x86/events/intel/uncore_snb.c b/arch/x86/events/intel/uncore_snb.c index 7fd4334e12a1..9462fd9f3b7a 100644 --- a/arch/x86/events/intel/uncore_snb.c +++ b/arch/x86/events/intel/uncore_snb.c @@ -364,8 +364,8 @@ static struct intel_uncore_type *snb_msr_uncores[] = { void snb_uncore_cpu_init(void) { uncore_msr_uncores = snb_msr_uncores; - if (snb_uncore_cbox.num_boxes > boot_cpu_data.x86_max_cores) - snb_uncore_cbox.num_boxes = boot_cpu_data.x86_max_cores; + if (snb_uncore_cbox.num_boxes > topology_num_cores_per_package()) + snb_uncore_cbox.num_boxes = topology_num_cores_per_package(); } static void skl_uncore_msr_init_box(struct intel_uncore_box *box) @@ -428,8 +428,8 @@ static struct intel_uncore_type *skl_msr_uncores[] = { void skl_uncore_cpu_init(void) { uncore_msr_uncores = skl_msr_uncores; - if (skl_uncore_cbox.num_boxes > boot_cpu_data.x86_max_cores) - skl_uncore_cbox.num_boxes = boot_cpu_data.x86_max_cores; + if (skl_uncore_cbox.num_boxes > topology_num_cores_per_package()) + skl_uncore_cbox.num_boxes = topology_num_cores_per_package(); snb_uncore_arb.ops = &skl_uncore_msr_ops; } diff --git a/arch/x86/events/intel/uncore_snbep.c b/arch/x86/events/intel/uncore_snbep.c index a96496bef678..2eaf0f339849 100644 --- a/arch/x86/events/intel/uncore_snbep.c +++ b/arch/x86/events/intel/uncore_snbep.c @@ -1172,8 +1172,8 @@ static struct intel_uncore_type *snbep_msr_uncores[] = { void snbep_uncore_cpu_init(void) { - if (snbep_uncore_cbox.num_boxes > boot_cpu_data.x86_max_cores) - snbep_uncore_cbox.num_boxes = boot_cpu_data.x86_max_cores; + if (snbep_uncore_cbox.num_boxes > topology_num_cores_per_package()) + snbep_uncore_cbox.num_boxes = topology_num_cores_per_package(); uncore_msr_uncores = snbep_msr_uncores; } @@ -1406,7 +1406,7 @@ static int topology_gidnid_map(int nodeid, u32 gidnid) */ for (i = 0; i < 8; i++) { if (nodeid == GIDNIDMAP(gidnid, i)) { - if (topology_max_die_per_package() > 1) + if (topology_max_dies_per_package() > 1) die_id = i; else die_id = topology_phys_to_logical_pkg(i); @@ -1845,8 +1845,8 @@ static struct intel_uncore_type *ivbep_msr_uncores[] = { void ivbep_uncore_cpu_init(void) { - if (ivbep_uncore_cbox.num_boxes > boot_cpu_data.x86_max_cores) - ivbep_uncore_cbox.num_boxes = boot_cpu_data.x86_max_cores; + if (ivbep_uncore_cbox.num_boxes > topology_num_cores_per_package()) + ivbep_uncore_cbox.num_boxes = topology_num_cores_per_package(); uncore_msr_uncores = ivbep_msr_uncores; } @@ -2917,8 +2917,8 @@ static bool hswep_has_limit_sbox(unsigned int device) void hswep_uncore_cpu_init(void) { - if (hswep_uncore_cbox.num_boxes > boot_cpu_data.x86_max_cores) - hswep_uncore_cbox.num_boxes = boot_cpu_data.x86_max_cores; + if (hswep_uncore_cbox.num_boxes > topology_num_cores_per_package()) + hswep_uncore_cbox.num_boxes = topology_num_cores_per_package(); /* Detect 6-8 core systems with only two SBOXes */ if (hswep_has_limit_sbox(HSWEP_PCU_DID)) @@ -3280,8 +3280,8 @@ static struct event_constraint bdx_uncore_pcu_constraints[] = { void bdx_uncore_cpu_init(void) { - if (bdx_uncore_cbox.num_boxes > boot_cpu_data.x86_max_cores) - bdx_uncore_cbox.num_boxes = boot_cpu_data.x86_max_cores; + if (bdx_uncore_cbox.num_boxes > topology_num_cores_per_package()) + bdx_uncore_cbox.num_boxes = topology_num_cores_per_package(); uncore_msr_uncores = bdx_msr_uncores; /* Detect systems with no SBOXes */ diff --git a/arch/x86/events/rapl.c b/arch/x86/events/rapl.c index 8d98d468b976..fb2b1961e5a3 100644 --- a/arch/x86/events/rapl.c +++ b/arch/x86/events/rapl.c @@ -674,7 +674,7 @@ static const struct attribute_group *rapl_attr_update[] = { static int __init init_rapl_pmus(void) { - int maxdie = topology_max_packages() * topology_max_die_per_package(); + int maxdie = topology_max_packages() * topology_max_dies_per_package(); size_t size; size = sizeof(*rapl_pmus) + maxdie * sizeof(struct rapl_pmu *); diff --git a/arch/x86/hyperv/hv_vtl.c b/arch/x86/hyperv/hv_vtl.c index 96e6c51515f5..edd2f35b2a5e 100644 --- a/arch/x86/hyperv/hv_vtl.c +++ b/arch/x86/hyperv/hv_vtl.c @@ -16,6 +16,11 @@ extern struct boot_params boot_params; static struct real_mode_header hv_vtl_real_mode_header; +static bool __init hv_vtl_msi_ext_dest_id(void) +{ + return true; +} + void __init hv_vtl_init_platform(void) { pr_info("Linux runs in Hyper-V Virtual Trust Level\n"); @@ -26,8 +31,9 @@ void __init hv_vtl_init_platform(void) x86_init.timers.timer_init = x86_init_noop; /* Avoid searching for BIOS MP tables */ - x86_init.mpparse.find_smp_config = x86_init_noop; - x86_init.mpparse.get_smp_config = x86_init_uint_noop; + x86_init.mpparse.find_mptable = x86_init_noop; + x86_init.mpparse.early_parse_smp_cfg = x86_init_noop; + x86_init.mpparse.parse_smp_cfg = x86_init_noop; x86_platform.get_wallclock = get_rtc_noop; x86_platform.set_wallclock = set_rtc_noop; @@ -38,6 +44,8 @@ void __init hv_vtl_init_platform(void) x86_platform.legacy.warm_reset = 0; x86_platform.legacy.reserve_bios_regions = 0; x86_platform.legacy.devices.pnpbios = 0; + + x86_init.hyper.msi_ext_dest_id = hv_vtl_msi_ext_dest_id; } static inline u64 hv_vtl_system_desc_base(struct ldttss_desc *desc) diff --git a/arch/x86/hyperv/ivm.c b/arch/x86/hyperv/ivm.c index 7dcbf153ad72..768d73de0d09 100644 --- a/arch/x86/hyperv/ivm.c +++ b/arch/x86/hyperv/ivm.c @@ -15,6 +15,7 @@ #include <asm/io.h> #include <asm/coco.h> #include <asm/mem_encrypt.h> +#include <asm/set_memory.h> #include <asm/mshyperv.h> #include <asm/hypervisor.h> #include <asm/mtrr.h> @@ -503,6 +504,31 @@ static int hv_mark_gpa_visibility(u16 count, const u64 pfn[], } /* + * When transitioning memory between encrypted and decrypted, the caller + * of set_memory_encrypted() or set_memory_decrypted() is responsible for + * ensuring that the memory isn't in use and isn't referenced while the + * transition is in progress. The transition has multiple steps, and the + * memory is in an inconsistent state until all steps are complete. A + * reference while the state is inconsistent could result in an exception + * that can't be cleanly fixed up. + * + * But the Linux kernel load_unaligned_zeropad() mechanism could cause a + * stray reference that can't be prevented by the caller, so Linux has + * specific code to handle this case. But when the #VC and #VE exceptions + * routed to a paravisor, the specific code doesn't work. To avoid this + * problem, mark the pages as "not present" while the transition is in + * progress. If load_unaligned_zeropad() causes a stray reference, a normal + * page fault is generated instead of #VC or #VE, and the page-fault-based + * handlers for load_unaligned_zeropad() resolve the reference. When the + * transition is complete, hv_vtom_set_host_visibility() marks the pages + * as "present" again. + */ +static bool hv_vtom_clear_present(unsigned long kbuffer, int pagecount, bool enc) +{ + return !set_memory_np(kbuffer, pagecount); +} + +/* * hv_vtom_set_host_visibility - Set specified memory visible to host. * * In Isolation VM, all guest memory is encrypted from host and guest @@ -515,16 +541,28 @@ static bool hv_vtom_set_host_visibility(unsigned long kbuffer, int pagecount, bo enum hv_mem_host_visibility visibility = enc ? VMBUS_PAGE_NOT_VISIBLE : VMBUS_PAGE_VISIBLE_READ_WRITE; u64 *pfn_array; + phys_addr_t paddr; + void *vaddr; int ret = 0; bool result = true; int i, pfn; pfn_array = kmalloc(HV_HYP_PAGE_SIZE, GFP_KERNEL); - if (!pfn_array) - return false; + if (!pfn_array) { + result = false; + goto err_set_memory_p; + } for (i = 0, pfn = 0; i < pagecount; i++) { - pfn_array[pfn] = virt_to_hvpfn((void *)kbuffer + i * HV_HYP_PAGE_SIZE); + /* + * Use slow_virt_to_phys() because the PRESENT bit has been + * temporarily cleared in the PTEs. slow_virt_to_phys() works + * without the PRESENT bit while virt_to_hvpfn() or similar + * does not. + */ + vaddr = (void *)kbuffer + (i * HV_HYP_PAGE_SIZE); + paddr = slow_virt_to_phys(vaddr); + pfn_array[pfn] = paddr >> HV_HYP_PAGE_SHIFT; pfn++; if (pfn == HV_MAX_MODIFY_GPA_REP_COUNT || i == pagecount - 1) { @@ -538,14 +576,30 @@ static bool hv_vtom_set_host_visibility(unsigned long kbuffer, int pagecount, bo } } - err_free_pfn_array: +err_free_pfn_array: kfree(pfn_array); + +err_set_memory_p: + /* + * Set the PTE PRESENT bits again to revert what hv_vtom_clear_present() + * did. Do this even if there is an error earlier in this function in + * order to avoid leaving the memory range in a "broken" state. Setting + * the PRESENT bits shouldn't fail, but return an error if it does. + */ + if (set_memory_p(kbuffer, pagecount)) + result = false; + return result; } static bool hv_vtom_tlb_flush_required(bool private) { - return true; + /* + * Since hv_vtom_clear_present() marks the PTEs as "not present" + * and flushes the TLB, they can't be in the TLB. That makes the + * flush controlled by this function redundant, so return "false". + */ + return false; } static bool hv_vtom_cache_flush_required(void) @@ -608,6 +662,7 @@ void __init hv_vtom_init(void) x86_platform.hyper.is_private_mmio = hv_is_private_mmio; x86_platform.guest.enc_cache_flush_required = hv_vtom_cache_flush_required; x86_platform.guest.enc_tlb_flush_required = hv_vtom_tlb_flush_required; + x86_platform.guest.enc_status_change_prepare = hv_vtom_clear_present; x86_platform.guest.enc_status_change_finish = hv_vtom_set_host_visibility; /* Set WB as the default cache mode. */ diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h index 9d159b771dc8..94ce0f7c9d3a 100644 --- a/arch/x86/include/asm/apic.h +++ b/arch/x86/include/asm/apic.h @@ -46,6 +46,10 @@ extern void x86_32_probe_apic(void); static inline void x86_32_probe_apic(void) { } #endif +extern u32 cpuid_to_apicid[]; + +#define CPU_ACPIID_INVALID U32_MAX + #ifdef CONFIG_X86_LOCAL_APIC extern int apic_verbosity; @@ -54,8 +58,6 @@ extern int local_apic_timer_c2_ok; extern bool apic_is_disabled; extern unsigned int lapic_timer_period; -extern u32 cpuid_to_apicid[]; - extern enum apic_intr_mode_id apic_intr_mode; enum apic_intr_mode_id { APIC_PIC, @@ -169,6 +171,14 @@ extern bool apic_needs_pit(void); extern void apic_send_IPI_allbutself(unsigned int vector); +extern void topology_register_apic(u32 apic_id, u32 acpi_id, bool present); +extern void topology_register_boot_apic(u32 apic_id); +extern int topology_hotplug_apic(u32 apic_id, u32 acpi_id); +extern void topology_hotunplug_apic(unsigned int cpu); +extern void topology_apply_cmdline_limits_early(void); +extern void topology_init_possible_cpus(void); +extern void topology_reset_possible_cpus_up(void); + #else /* !CONFIG_X86_LOCAL_APIC */ static inline void lapic_shutdown(void) { } #define local_apic_timer_c2_ok 1 @@ -183,6 +193,8 @@ static inline void apic_intr_mode_init(void) { } static inline void lapic_assign_system_vectors(void) { } static inline void lapic_assign_legacy_vector(unsigned int i, bool r) { } static inline bool apic_needs_pit(void) { return true; } +static inline void topology_apply_cmdline_limits_early(void) { } +static inline void topology_init_possible_cpus(void) { } #endif /* !CONFIG_X86_LOCAL_APIC */ #ifdef CONFIG_X86_X2APIC @@ -289,16 +301,11 @@ struct apic { /* Probe, setup and smpboot functions */ int (*probe)(void); int (*acpi_madt_oem_check)(char *oem_id, char *oem_table_id); - bool (*apic_id_registered)(void); - bool (*check_apicid_used)(physid_mask_t *map, u32 apicid); void (*init_apic_ldr)(void); - void (*ioapic_phys_id_map)(physid_mask_t *phys_map, physid_mask_t *retmap); u32 (*cpu_present_to_apicid)(int mps_cpu); - u32 (*phys_pkg_id)(u32 cpuid_apic, int index_msb); u32 (*get_apic_id)(u32 id); - u32 (*set_apic_id)(u32 apicid); /* wakeup_secondary_cpu */ int (*wakeup_secondary_cpu)(u32 apicid, unsigned long start_eip); @@ -527,7 +534,6 @@ extern int default_apic_id_valid(u32 apicid); extern u32 apic_default_calc_apicid(unsigned int cpu); extern u32 apic_flat_calc_apicid(unsigned int cpu); -extern void default_ioapic_phys_id_map(physid_mask_t *phys_map, physid_mask_t *retmap); extern u32 default_cpu_present_to_apicid(int mps_cpu); void apic_send_nmi_to_offline_cpu(unsigned int cpu); diff --git a/arch/x86/include/asm/asm-prototypes.h b/arch/x86/include/asm/asm-prototypes.h index b1a98fa38828..076bf8dee702 100644 --- a/arch/x86/include/asm/asm-prototypes.h +++ b/arch/x86/include/asm/asm-prototypes.h @@ -12,6 +12,7 @@ #include <asm/special_insns.h> #include <asm/preempt.h> #include <asm/asm.h> +#include <asm/fred.h> #include <asm/gsseg.h> #ifndef CONFIG_X86_CMPXCHG64 diff --git a/arch/x86/include/asm/barrier.h b/arch/x86/include/asm/barrier.h index 0216f63a366b..fe1e7e3cc844 100644 --- a/arch/x86/include/asm/barrier.h +++ b/arch/x86/include/asm/barrier.h @@ -33,7 +33,7 @@ * Returns: * 0 - (index < size) */ -static inline unsigned long array_index_mask_nospec(unsigned long index, +static __always_inline unsigned long array_index_mask_nospec(unsigned long index, unsigned long size) { unsigned long mask; diff --git a/arch/x86/include/asm/cpu.h b/arch/x86/include/asm/cpu.h index f8f9a9b79395..aa30fd8cad7f 100644 --- a/arch/x86/include/asm/cpu.h +++ b/arch/x86/include/asm/cpu.h @@ -9,18 +9,10 @@ #include <linux/percpu.h> #include <asm/ibt.h> -#ifdef CONFIG_SMP - -extern void prefill_possible_map(void); - -#else /* CONFIG_SMP */ - -static inline void prefill_possible_map(void) {} - +#ifndef CONFIG_SMP #define cpu_physical_id(cpu) boot_cpu_physical_apicid #define cpu_acpi_id(cpu) 0 #define safe_smp_processor_id() 0 - #endif /* CONFIG_SMP */ #ifdef CONFIG_HOTPLUG_CPU diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index fdf723b6f6d0..8e371c6cc5f9 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -95,7 +95,7 @@ #define X86_FEATURE_SYSENTER32 ( 3*32+15) /* "" sysenter in IA32 userspace */ #define X86_FEATURE_REP_GOOD ( 3*32+16) /* REP microcode works well */ #define X86_FEATURE_AMD_LBR_V2 ( 3*32+17) /* AMD Last Branch Record Extension Version 2 */ -/* FREE, was #define X86_FEATURE_LFENCE_RDTSC ( 3*32+18) "" LFENCE synchronizes RDTSC */ +#define X86_FEATURE_CLEAR_CPU_BUF ( 3*32+18) /* "" Clear CPU buffers using VERW */ #define X86_FEATURE_ACC_POWER ( 3*32+19) /* AMD Accumulated Power Mechanism */ #define X86_FEATURE_NOPL ( 3*32+20) /* The NOPL (0F 1F) instructions */ #define X86_FEATURE_ALWAYS ( 3*32+21) /* "" Always-present feature */ @@ -324,7 +324,9 @@ #define X86_FEATURE_FZRM (12*32+10) /* "" Fast zero-length REP MOVSB */ #define X86_FEATURE_FSRS (12*32+11) /* "" Fast short REP STOSB */ #define X86_FEATURE_FSRC (12*32+12) /* "" Fast short REP {CMPSB,SCASB} */ +#define X86_FEATURE_FRED (12*32+17) /* Flexible Return and Event Delivery */ #define X86_FEATURE_LKGS (12*32+18) /* "" Load "kernel" (userspace) GS */ +#define X86_FEATURE_WRMSRNS (12*32+19) /* "" Non-serializing WRMSR */ #define X86_FEATURE_AMX_FP16 (12*32+21) /* "" AMX fp16 Support */ #define X86_FEATURE_AVX_IFMA (12*32+23) /* "" Support for VPMADD52[H,L]UQ */ #define X86_FEATURE_LAM (12*32+26) /* Linear Address Masking */ diff --git a/arch/x86/include/asm/cpuid.h b/arch/x86/include/asm/cpuid.h index 9bee3e7bf973..6b122a31da06 100644 --- a/arch/x86/include/asm/cpuid.h +++ b/arch/x86/include/asm/cpuid.h @@ -127,6 +127,42 @@ static inline unsigned int cpuid_edx(unsigned int op) return edx; } +static inline void __cpuid_read(unsigned int leaf, unsigned int subleaf, u32 *regs) +{ + regs[CPUID_EAX] = leaf; + regs[CPUID_ECX] = subleaf; + __cpuid(regs + CPUID_EAX, regs + CPUID_EBX, regs + CPUID_ECX, regs + CPUID_EDX); +} + +#define cpuid_subleaf(leaf, subleaf, regs) { \ + static_assert(sizeof(*(regs)) == 16); \ + __cpuid_read(leaf, subleaf, (u32 *)(regs)); \ +} + +#define cpuid_leaf(leaf, regs) { \ + static_assert(sizeof(*(regs)) == 16); \ + __cpuid_read(leaf, 0, (u32 *)(regs)); \ +} + +static inline void __cpuid_read_reg(unsigned int leaf, unsigned int subleaf, + enum cpuid_regs_idx regidx, u32 *reg) +{ + u32 regs[4]; + + __cpuid_read(leaf, subleaf, regs); + *reg = regs[regidx]; +} + +#define cpuid_subleaf_reg(leaf, subleaf, regidx, reg) { \ + static_assert(sizeof(*(reg)) == 4); \ + __cpuid_read_reg(leaf, subleaf, regidx, (u32 *)(reg)); \ +} + +#define cpuid_leaf_reg(leaf, regidx, reg) { \ + static_assert(sizeof(*(reg)) == 4); \ + __cpuid_read_reg(leaf, 0, regidx, (u32 *)(reg)); \ +} + static __always_inline bool cpuid_function_is_indexed(u32 function) { switch (function) { diff --git a/arch/x86/include/asm/desc.h b/arch/x86/include/asm/desc.h index ab97b22ac04a..ec95fe44fa3a 100644 --- a/arch/x86/include/asm/desc.h +++ b/arch/x86/include/asm/desc.h @@ -402,8 +402,6 @@ static inline void set_desc_limit(struct desc_struct *desc, unsigned long limit) desc->limit1 = (limit >> 16) & 0xf; } -void alloc_intr_gate(unsigned int n, const void *addr); - static inline void init_idt_data(struct idt_data *data, unsigned int n, const void *addr) { diff --git a/arch/x86/include/asm/disabled-features.h b/arch/x86/include/asm/disabled-features.h index 702d93fdd10e..f40b29d3abad 100644 --- a/arch/x86/include/asm/disabled-features.h +++ b/arch/x86/include/asm/disabled-features.h @@ -117,6 +117,12 @@ #define DISABLE_IBT (1 << (X86_FEATURE_IBT & 31)) #endif +#ifdef CONFIG_X86_FRED +# define DISABLE_FRED 0 +#else +# define DISABLE_FRED (1 << (X86_FEATURE_FRED & 31)) +#endif + /* * Make sure to add features to the correct mask */ @@ -133,7 +139,7 @@ #define DISABLED_MASK10 0 #define DISABLED_MASK11 (DISABLE_RETPOLINE|DISABLE_RETHUNK|DISABLE_UNRET| \ DISABLE_CALL_DEPTH_TRACKING|DISABLE_USER_SHSTK) -#define DISABLED_MASK12 (DISABLE_LAM) +#define DISABLED_MASK12 (DISABLE_FRED|DISABLE_LAM) #define DISABLED_MASK13 0 #define DISABLED_MASK14 0 #define DISABLED_MASK15 0 diff --git a/arch/x86/include/asm/entry-common.h b/arch/x86/include/asm/entry-common.h index ce8f50192ae3..7e523bb3d2d3 100644 --- a/arch/x86/include/asm/entry-common.h +++ b/arch/x86/include/asm/entry-common.h @@ -91,7 +91,6 @@ static inline void arch_exit_to_user_mode_prepare(struct pt_regs *regs, static __always_inline void arch_exit_to_user_mode(void) { - mds_user_clear_cpu_buffers(); amd_clear_divider(); } #define arch_exit_to_user_mode arch_exit_to_user_mode diff --git a/arch/x86/include/asm/extable_fixup_types.h b/arch/x86/include/asm/extable_fixup_types.h index fe6312045042..7acf0383be80 100644 --- a/arch/x86/include/asm/extable_fixup_types.h +++ b/arch/x86/include/asm/extable_fixup_types.h @@ -64,6 +64,8 @@ #define EX_TYPE_UCOPY_LEN4 (EX_TYPE_UCOPY_LEN | EX_DATA_IMM(4)) #define EX_TYPE_UCOPY_LEN8 (EX_TYPE_UCOPY_LEN | EX_DATA_IMM(8)) -#define EX_TYPE_ZEROPAD 20 /* longword load with zeropad on fault */ +#define EX_TYPE_ZEROPAD 20 /* longword load with zeropad on fault */ + +#define EX_TYPE_ERETU 21 #endif diff --git a/arch/x86/include/asm/fred.h b/arch/x86/include/asm/fred.h new file mode 100644 index 000000000000..e86c7ba32435 --- /dev/null +++ b/arch/x86/include/asm/fred.h @@ -0,0 +1,97 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Macros for Flexible Return and Event Delivery (FRED) + */ + +#ifndef ASM_X86_FRED_H +#define ASM_X86_FRED_H + +#include <linux/const.h> + +#include <asm/asm.h> +#include <asm/trapnr.h> + +/* + * FRED event return instruction opcodes for ERET{S,U}; supported in + * binutils >= 2.41. + */ +#define ERETS _ASM_BYTES(0xf2,0x0f,0x01,0xca) +#define ERETU _ASM_BYTES(0xf3,0x0f,0x01,0xca) + +/* + * RSP is aligned to a 64-byte boundary before used to push a new stack frame + */ +#define FRED_STACK_FRAME_RSP_MASK _AT(unsigned long, (~0x3f)) + +/* + * Used for the return address for call emulation during code patching, + * and measured in 64-byte cache lines. + */ +#define FRED_CONFIG_REDZONE_AMOUNT 1 +#define FRED_CONFIG_REDZONE (_AT(unsigned long, FRED_CONFIG_REDZONE_AMOUNT) << 6) +#define FRED_CONFIG_INT_STKLVL(l) (_AT(unsigned long, l) << 9) +#define FRED_CONFIG_ENTRYPOINT(p) _AT(unsigned long, (p)) + +#ifndef __ASSEMBLY__ + +#ifdef CONFIG_X86_FRED +#include <linux/kernel.h> + +#include <asm/ptrace.h> + +struct fred_info { + /* Event data: CR2, DR6, ... */ + unsigned long edata; + unsigned long resv; +}; + +/* Full format of the FRED stack frame */ +struct fred_frame { + struct pt_regs regs; + struct fred_info info; +}; + +static __always_inline struct fred_info *fred_info(struct pt_regs *regs) +{ + return &container_of(regs, struct fred_frame, regs)->info; +} + +static __always_inline unsigned long fred_event_data(struct pt_regs *regs) +{ + return fred_info(regs)->edata; +} + +void asm_fred_entrypoint_user(void); +void asm_fred_entrypoint_kernel(void); +void asm_fred_entry_from_kvm(struct fred_ss); + +__visible void fred_entry_from_user(struct pt_regs *regs); +__visible void fred_entry_from_kernel(struct pt_regs *regs); +__visible void __fred_entry_from_kvm(struct pt_regs *regs); + +/* Can be called from noinstr code, thus __always_inline */ +static __always_inline void fred_entry_from_kvm(unsigned int type, unsigned int vector) +{ + struct fred_ss ss = { + .ss =__KERNEL_DS, + .type = type, + .vector = vector, + .nmi = type == EVENT_TYPE_NMI, + .lm = 1, + }; + + asm_fred_entry_from_kvm(ss); +} + +void cpu_init_fred_exceptions(void); +void fred_complete_exception_setup(void); + +#else /* CONFIG_X86_FRED */ +static __always_inline unsigned long fred_event_data(struct pt_regs *regs) { return 0; } +static inline void cpu_init_fred_exceptions(void) { } +static inline void fred_complete_exception_setup(void) { } +static __always_inline void fred_entry_from_kvm(unsigned int type, unsigned int vector) { } +#endif /* CONFIG_X86_FRED */ +#endif /* !__ASSEMBLY__ */ + +#endif /* ASM_X86_FRED_H */ diff --git a/arch/x86/include/asm/hw_irq.h b/arch/x86/include/asm/hw_irq.h index b02c3cd3c0f6..edebf1020e04 100644 --- a/arch/x86/include/asm/hw_irq.h +++ b/arch/x86/include/asm/hw_irq.h @@ -16,8 +16,6 @@ #include <asm/irq_vectors.h> -#define IRQ_MATRIX_BITS NR_VECTORS - #ifndef __ASSEMBLY__ #include <linux/percpu.h> diff --git a/arch/x86/include/asm/ia32.h b/arch/x86/include/asm/ia32.h index c7ef6ea2fa99..4212c00c9708 100644 --- a/arch/x86/include/asm/ia32.h +++ b/arch/x86/include/asm/ia32.h @@ -69,7 +69,7 @@ extern void ia32_pick_mmap_layout(struct mm_struct *mm); extern bool __ia32_enabled; -static inline bool ia32_enabled(void) +static __always_inline bool ia32_enabled(void) { return __ia32_enabled; } @@ -81,7 +81,7 @@ static inline void ia32_disable(void) #else /* !CONFIG_IA32_EMULATION */ -static inline bool ia32_enabled(void) +static __always_inline bool ia32_enabled(void) { return IS_ENABLED(CONFIG_X86_32); } diff --git a/arch/x86/include/asm/idtentry.h b/arch/x86/include/asm/idtentry.h index 13639e57e1f8..47d4c04d103d 100644 --- a/arch/x86/include/asm/idtentry.h +++ b/arch/x86/include/asm/idtentry.h @@ -13,15 +13,18 @@ #include <asm/irq_stack.h> +typedef void (*idtentry_t)(struct pt_regs *regs); + /** * DECLARE_IDTENTRY - Declare functions for simple IDT entry points * No error code pushed by hardware * @vector: Vector number (ignored for C) * @func: Function name of the entry point * - * Declares three functions: + * Declares four functions: * - The ASM entry point: asm_##func * - The XEN PV trap entry point: xen_##func (maybe unused) + * - The C handler called from the FRED event dispatcher (maybe unused) * - The C handler called from the ASM entry point * * Note: This is the C variant of DECLARE_IDTENTRY(). As the name says it @@ -31,6 +34,7 @@ #define DECLARE_IDTENTRY(vector, func) \ asmlinkage void asm_##func(void); \ asmlinkage void xen_asm_##func(void); \ + void fred_##func(struct pt_regs *regs); \ __visible void func(struct pt_regs *regs) /** @@ -138,6 +142,17 @@ static __always_inline void __##func(struct pt_regs *regs, \ __visible noinstr void func(struct pt_regs *regs) /** + * DEFINE_FREDENTRY_RAW - Emit code for raw FRED entry points + * @func: Function name of the entry point + * + * @func is called from the FRED event dispatcher with interrupts disabled. + * + * See @DEFINE_IDTENTRY_RAW for further details. + */ +#define DEFINE_FREDENTRY_RAW(func) \ +noinstr void fred_##func(struct pt_regs *regs) + +/** * DECLARE_IDTENTRY_RAW_ERRORCODE - Declare functions for raw IDT entry points * Error code pushed by hardware * @vector: Vector number (ignored for C) @@ -233,17 +248,27 @@ static noinline void __##func(struct pt_regs *regs, u32 vector) #define DEFINE_IDTENTRY_SYSVEC(func) \ static void __##func(struct pt_regs *regs); \ \ +static __always_inline void instr_##func(struct pt_regs *regs) \ +{ \ + kvm_set_cpu_l1tf_flush_l1d(); \ + run_sysvec_on_irqstack_cond(__##func, regs); \ +} \ + \ __visible noinstr void func(struct pt_regs *regs) \ { \ irqentry_state_t state = irqentry_enter(regs); \ \ instrumentation_begin(); \ - kvm_set_cpu_l1tf_flush_l1d(); \ - run_sysvec_on_irqstack_cond(__##func, regs); \ + instr_##func (regs); \ instrumentation_end(); \ irqentry_exit(regs, state); \ } \ \ +void fred_##func(struct pt_regs *regs) \ +{ \ + instr_##func (regs); \ +} \ + \ static noinline void __##func(struct pt_regs *regs) /** @@ -260,19 +285,29 @@ static noinline void __##func(struct pt_regs *regs) #define DEFINE_IDTENTRY_SYSVEC_SIMPLE(func) \ static __always_inline void __##func(struct pt_regs *regs); \ \ -__visible noinstr void func(struct pt_regs *regs) \ +static __always_inline void instr_##func(struct pt_regs *regs) \ { \ - irqentry_state_t state = irqentry_enter(regs); \ - \ - instrumentation_begin(); \ __irq_enter_raw(); \ kvm_set_cpu_l1tf_flush_l1d(); \ __##func (regs); \ __irq_exit_raw(); \ +} \ + \ +__visible noinstr void func(struct pt_regs *regs) \ +{ \ + irqentry_state_t state = irqentry_enter(regs); \ + \ + instrumentation_begin(); \ + instr_##func (regs); \ instrumentation_end(); \ irqentry_exit(regs, state); \ } \ \ +void fred_##func(struct pt_regs *regs) \ +{ \ + instr_##func (regs); \ +} \ + \ static __always_inline void __##func(struct pt_regs *regs) /** @@ -410,17 +445,35 @@ __visible noinstr void func(struct pt_regs *regs, \ /* C-Code mapping */ #define DECLARE_IDTENTRY_NMI DECLARE_IDTENTRY_RAW #define DEFINE_IDTENTRY_NMI DEFINE_IDTENTRY_RAW +#define DEFINE_FREDENTRY_NMI DEFINE_FREDENTRY_RAW #ifdef CONFIG_X86_64 #define DECLARE_IDTENTRY_MCE DECLARE_IDTENTRY_IST #define DEFINE_IDTENTRY_MCE DEFINE_IDTENTRY_IST #define DEFINE_IDTENTRY_MCE_USER DEFINE_IDTENTRY_NOIST +#define DEFINE_FREDENTRY_MCE DEFINE_FREDENTRY_RAW #define DECLARE_IDTENTRY_DEBUG DECLARE_IDTENTRY_IST #define DEFINE_IDTENTRY_DEBUG DEFINE_IDTENTRY_IST #define DEFINE_IDTENTRY_DEBUG_USER DEFINE_IDTENTRY_NOIST +#define DEFINE_FREDENTRY_DEBUG DEFINE_FREDENTRY_RAW +#endif + +void idt_install_sysvec(unsigned int n, const void *function); + +#ifdef CONFIG_X86_FRED +void fred_install_sysvec(unsigned int vector, const idtentry_t function); +#else +static inline void fred_install_sysvec(unsigned int vector, const idtentry_t function) { } #endif +#define sysvec_install(vector, function) { \ + if (cpu_feature_enabled(X86_FEATURE_FRED)) \ + fred_install_sysvec(vector, function); \ + else \ + idt_install_sysvec(vector, asm_##function); \ +} + #else /* !__ASSEMBLY__ */ /* @@ -447,7 +500,7 @@ __visible noinstr void func(struct pt_regs *regs, \ /* System vector entries */ #define DECLARE_IDTENTRY_SYSVEC(vector, func) \ - idtentry_sysvec vector func + DECLARE_IDTENTRY(vector, func) #ifdef CONFIG_X86_64 # define DECLARE_IDTENTRY_MCE(vector, func) \ @@ -655,23 +708,36 @@ DECLARE_IDTENTRY(RESCHEDULE_VECTOR, sysvec_reschedule_ipi); DECLARE_IDTENTRY_SYSVEC(REBOOT_VECTOR, sysvec_reboot); DECLARE_IDTENTRY_SYSVEC(CALL_FUNCTION_SINGLE_VECTOR, sysvec_call_function_single); DECLARE_IDTENTRY_SYSVEC(CALL_FUNCTION_VECTOR, sysvec_call_function); +#else +# define fred_sysvec_reschedule_ipi NULL +# define fred_sysvec_reboot NULL +# define fred_sysvec_call_function_single NULL +# define fred_sysvec_call_function NULL #endif #ifdef CONFIG_X86_LOCAL_APIC # ifdef CONFIG_X86_MCE_THRESHOLD DECLARE_IDTENTRY_SYSVEC(THRESHOLD_APIC_VECTOR, sysvec_threshold); +# else +# define fred_sysvec_threshold NULL # endif # ifdef CONFIG_X86_MCE_AMD DECLARE_IDTENTRY_SYSVEC(DEFERRED_ERROR_VECTOR, sysvec_deferred_error); +# else +# define fred_sysvec_deferred_error NULL # endif # ifdef CONFIG_X86_THERMAL_VECTOR DECLARE_IDTENTRY_SYSVEC(THERMAL_APIC_VECTOR, sysvec_thermal); +# else +# define fred_sysvec_thermal NULL # endif # ifdef CONFIG_IRQ_WORK DECLARE_IDTENTRY_SYSVEC(IRQ_WORK_VECTOR, sysvec_irq_work); +# else +# define fred_sysvec_irq_work NULL # endif #endif @@ -679,12 +745,16 @@ DECLARE_IDTENTRY_SYSVEC(IRQ_WORK_VECTOR, sysvec_irq_work); DECLARE_IDTENTRY_SYSVEC(POSTED_INTR_VECTOR, sysvec_kvm_posted_intr_ipi); DECLARE_IDTENTRY_SYSVEC(POSTED_INTR_WAKEUP_VECTOR, sysvec_kvm_posted_intr_wakeup_ipi); DECLARE_IDTENTRY_SYSVEC(POSTED_INTR_NESTED_VECTOR, sysvec_kvm_posted_intr_nested_ipi); +#else +# define fred_sysvec_kvm_posted_intr_ipi NULL +# define fred_sysvec_kvm_posted_intr_wakeup_ipi NULL +# define fred_sysvec_kvm_posted_intr_nested_ipi NULL #endif #if IS_ENABLED(CONFIG_HYPERV) DECLARE_IDTENTRY_SYSVEC(HYPERVISOR_CALLBACK_VECTOR, sysvec_hyperv_callback); DECLARE_IDTENTRY_SYSVEC(HYPERV_REENLIGHTENMENT_VECTOR, sysvec_hyperv_reenlightenment); -DECLARE_IDTENTRY_SYSVEC(HYPERV_STIMER0_VECTOR, sysvec_hyperv_stimer0); +DECLARE_IDTENTRY_SYSVEC(HYPERV_STIMER0_VECTOR, sysvec_hyperv_stimer0); #endif #if IS_ENABLED(CONFIG_ACRN_GUEST) diff --git a/arch/x86/include/asm/io_apic.h b/arch/x86/include/asm/io_apic.h index 51c782600e02..0d806513c4b3 100644 --- a/arch/x86/include/asm/io_apic.h +++ b/arch/x86/include/asm/io_apic.h @@ -140,7 +140,6 @@ extern void mask_ioapic_entries(void); extern int restore_ioapic_entries(void); extern void setup_ioapic_ids_from_mpc(void); -extern void setup_ioapic_ids_from_mpc_nocheck(void); extern int mp_find_ioapic(u32 gsi); extern int mp_find_ioapic_pin(int ioapic, u32 gsi); diff --git a/arch/x86/include/asm/kvmclock.h b/arch/x86/include/asm/kvmclock.h index 511b35069187..f163176d6f7f 100644 --- a/arch/x86/include/asm/kvmclock.h +++ b/arch/x86/include/asm/kvmclock.h @@ -4,8 +4,6 @@ #include <linux/percpu.h> -extern struct clocksource kvm_clock; - DECLARE_PER_CPU(struct pvclock_vsyscall_time_info *, hv_clock_per_cpu); static __always_inline struct pvclock_vcpu_time_info *this_cpu_pvti(void) diff --git a/arch/x86/include/asm/mpspec.h b/arch/x86/include/asm/mpspec.h index 4b0f98a8d338..c72c7ff78fcd 100644 --- a/arch/x86/include/asm/mpspec.h +++ b/arch/x86/include/asm/mpspec.h @@ -2,6 +2,7 @@ #ifndef _ASM_X86_MPSPEC_H #define _ASM_X86_MPSPEC_H +#include <linux/types.h> #include <asm/mpspec_def.h> #include <asm/x86_init.h> @@ -46,70 +47,31 @@ extern int smp_found_config; # define smp_found_config 0 #endif -static inline void get_smp_config(void) -{ - x86_init.mpparse.get_smp_config(0); -} - -static inline void early_get_smp_config(void) -{ - x86_init.mpparse.get_smp_config(1); -} - -static inline void find_smp_config(void) -{ - x86_init.mpparse.find_smp_config(); -} - #ifdef CONFIG_X86_MPPARSE extern void e820__memblock_alloc_reserved_mpc_new(void); extern int enable_update_mptable; -extern void default_find_smp_config(void); -extern void default_get_smp_config(unsigned int early); +extern void mpparse_find_mptable(void); +extern void mpparse_parse_early_smp_config(void); +extern void mpparse_parse_smp_config(void); #else static inline void e820__memblock_alloc_reserved_mpc_new(void) { } -#define enable_update_mptable 0 -#define default_find_smp_config x86_init_noop -#define default_get_smp_config x86_init_uint_noop +#define enable_update_mptable 0 +#define mpparse_find_mptable x86_init_noop +#define mpparse_parse_early_smp_config x86_init_noop +#define mpparse_parse_smp_config x86_init_noop #endif -int generic_processor_info(int apicid); +extern DECLARE_BITMAP(phys_cpu_present_map, MAX_LOCAL_APIC); -#define PHYSID_ARRAY_SIZE BITS_TO_LONGS(MAX_LOCAL_APIC) - -struct physid_mask { - unsigned long mask[PHYSID_ARRAY_SIZE]; -}; - -typedef struct physid_mask physid_mask_t; - -#define physid_set(physid, map) set_bit(physid, (map).mask) -#define physid_isset(physid, map) test_bit(physid, (map).mask) - -#define physids_or(dst, src1, src2) \ - bitmap_or((dst).mask, (src1).mask, (src2).mask, MAX_LOCAL_APIC) - -#define physids_clear(map) \ - bitmap_zero((map).mask, MAX_LOCAL_APIC) - -#define physids_empty(map) \ - bitmap_empty((map).mask, MAX_LOCAL_APIC) - -static inline void physids_promote(unsigned long physids, physid_mask_t *map) +static inline void reset_phys_cpu_present_map(u32 apicid) { - physids_clear(*map); - map->mask[0] = physids; + bitmap_zero(phys_cpu_present_map, MAX_LOCAL_APIC); + set_bit(apicid, phys_cpu_present_map); } -static inline void physid_set_mask_of_physid(int physid, physid_mask_t *map) +static inline void copy_phys_cpu_present_map(unsigned long *dst) { - physids_clear(*map); - physid_set(physid, *map); + bitmap_copy(dst, phys_cpu_present_map, MAX_LOCAL_APIC); } -#define PHYSID_MASK_ALL { {[0 ... PHYSID_ARRAY_SIZE-1] = ~0UL} } -#define PHYSID_MASK_NONE { {[0 ... PHYSID_ARRAY_SIZE-1] = 0UL} } - -extern physid_mask_t phys_cpu_present_map; - #endif /* _ASM_X86_MPSPEC_H */ diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index f1bd7b91b3c6..1f9dc9bd13eb 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -36,8 +36,19 @@ #define EFER_FFXSR (1<<_EFER_FFXSR) #define EFER_AUTOIBRS (1<<_EFER_AUTOIBRS) -/* Intel MSRs. Some also available on other CPUs */ +/* FRED MSRs */ +#define MSR_IA32_FRED_RSP0 0x1cc /* Level 0 stack pointer */ +#define MSR_IA32_FRED_RSP1 0x1cd /* Level 1 stack pointer */ +#define MSR_IA32_FRED_RSP2 0x1ce /* Level 2 stack pointer */ +#define MSR_IA32_FRED_RSP3 0x1cf /* Level 3 stack pointer */ +#define MSR_IA32_FRED_STKLVLS 0x1d0 /* Exception stack levels */ +#define MSR_IA32_FRED_SSP0 MSR_IA32_PL0_SSP /* Level 0 shadow stack pointer */ +#define MSR_IA32_FRED_SSP1 0x1d1 /* Level 1 shadow stack pointer */ +#define MSR_IA32_FRED_SSP2 0x1d2 /* Level 2 shadow stack pointer */ +#define MSR_IA32_FRED_SSP3 0x1d3 /* Level 3 shadow stack pointer */ +#define MSR_IA32_FRED_CONFIG 0x1d4 /* Entrypoint and interrupt stack level */ +/* Intel MSRs. Some also available on other CPUs */ #define MSR_TEST_CTRL 0x00000033 #define MSR_TEST_CTRL_SPLIT_LOCK_DETECT_BIT 29 #define MSR_TEST_CTRL_SPLIT_LOCK_DETECT BIT(MSR_TEST_CTRL_SPLIT_LOCK_DETECT_BIT) diff --git a/arch/x86/include/asm/msr.h b/arch/x86/include/asm/msr.h index 65ec1965cd28..c284ff9ebe67 100644 --- a/arch/x86/include/asm/msr.h +++ b/arch/x86/include/asm/msr.h @@ -97,6 +97,19 @@ static __always_inline void __wrmsr(unsigned int msr, u32 low, u32 high) : : "c" (msr), "a"(low), "d" (high) : "memory"); } +/* + * WRMSRNS behaves exactly like WRMSR with the only difference being + * that it is not a serializing instruction by default. + */ +static __always_inline void __wrmsrns(u32 msr, u32 low, u32 high) +{ + /* Instruction opcode for WRMSRNS; supported in binutils >= 2.40. */ + asm volatile("1: .byte 0x0f,0x01,0xc6\n" + "2:\n" + _ASM_EXTABLE_TYPE(1b, 2b, EX_TYPE_WRMSR) + : : "c" (msr), "a"(low), "d" (high)); +} + #define native_rdmsr(msr, val1, val2) \ do { \ u64 __val = __rdmsr((msr)); \ @@ -297,6 +310,11 @@ do { \ #endif /* !CONFIG_PARAVIRT_XXL */ +static __always_inline void wrmsrns(u32 msr, u64 val) +{ + __wrmsrns(msr, val, val >> 32); +} + /* * 64-bit version of wrmsr_safe(): */ diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h index 262e65539f83..ab19c7f1167b 100644 --- a/arch/x86/include/asm/nospec-branch.h +++ b/arch/x86/include/asm/nospec-branch.h @@ -315,6 +315,17 @@ #endif .endm +/* + * Macro to execute VERW instruction that mitigate transient data sampling + * attacks such as MDS. On affected systems a microcode update overloaded VERW + * instruction to also clear the CPU buffers. VERW clobbers CFLAGS.ZF. + * + * Note: Only the memory operand variant of VERW clears the CPU buffers. + */ +.macro CLEAR_CPU_BUFFERS + ALTERNATIVE "", __stringify(verw mds_verw_sel), X86_FEATURE_CLEAR_CPU_BUF +.endm + #else /* __ASSEMBLY__ */ #define ANNOTATE_RETPOLINE_SAFE \ @@ -529,13 +540,14 @@ DECLARE_STATIC_KEY_FALSE(switch_to_cond_stibp); DECLARE_STATIC_KEY_FALSE(switch_mm_cond_ibpb); DECLARE_STATIC_KEY_FALSE(switch_mm_always_ibpb); -DECLARE_STATIC_KEY_FALSE(mds_user_clear); DECLARE_STATIC_KEY_FALSE(mds_idle_clear); DECLARE_STATIC_KEY_FALSE(switch_mm_cond_l1d_flush); DECLARE_STATIC_KEY_FALSE(mmio_stale_data_clear); +extern u16 mds_verw_sel; + #include <asm/segment.h> /** @@ -562,17 +574,6 @@ static __always_inline void mds_clear_cpu_buffers(void) } /** - * mds_user_clear_cpu_buffers - Mitigation for MDS and TAA vulnerability - * - * Clear CPU buffers if the corresponding static key is enabled - */ -static __always_inline void mds_user_clear_cpu_buffers(void) -{ - if (static_branch_likely(&mds_user_clear)) - mds_clear_cpu_buffers(); -} - -/** * mds_idle_clear_cpu_buffers - Mitigation for MDS vulnerability * * Clear CPU buffers if the corresponding static key is enabled diff --git a/arch/x86/include/asm/perf_event_p4.h b/arch/x86/include/asm/perf_event_p4.h index 94de1a05aeba..d65e338b6a5f 100644 --- a/arch/x86/include/asm/perf_event_p4.h +++ b/arch/x86/include/asm/perf_event_p4.h @@ -181,7 +181,7 @@ static inline u64 p4_clear_ht_bit(u64 config) static inline int p4_ht_active(void) { #ifdef CONFIG_SMP - return smp_num_siblings > 1; + return __max_threads_per_core > 1; #endif return 0; } @@ -189,7 +189,7 @@ static inline int p4_ht_active(void) static inline int p4_ht_thread(int cpu) { #ifdef CONFIG_SMP - if (smp_num_siblings == 2) + if (__max_threads_per_core == 2) return cpu != cpumask_first(this_cpu_cpumask_var_ptr(cpu_sibling_map)); #endif return 0; diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index 26620d7642a9..89cf39dbd306 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -100,6 +100,9 @@ struct cpuinfo_topology { u32 logical_pkg_id; u32 logical_die_id; + // AMD Node ID and Nodes per Package info + u32 amd_node_id; + // Cache level topology IDs u32 llc_id; u32 l2c_id; @@ -119,8 +122,6 @@ struct cpuinfo_x86 { #endif __u8 x86_virt_bits; __u8 x86_phys_bits; - /* CPUID returned core id bits: */ - __u8 x86_coreid_bits; /* Max extended CPUID function supported: */ __u32 extended_cpuid_level; /* Maximum supported CPUID level, -1=no CPUID: */ @@ -148,8 +149,6 @@ struct cpuinfo_x86 { unsigned long loops_per_jiffy; /* protected processor identification number */ u64 ppin; - /* cpuid returned max cores value: */ - u16 x86_max_cores; u16 x86_clflush_size; /* number of cores as seen by the OS: */ u16 booted_cores; @@ -664,8 +663,10 @@ static __always_inline void prefetchw(const void *x) #else extern unsigned long __end_init_task[]; -#define INIT_THREAD { \ - .sp = (unsigned long)&__end_init_task - sizeof(struct pt_regs), \ +#define INIT_THREAD { \ + .sp = (unsigned long)&__end_init_task - \ + TOP_OF_KERNEL_STACK_PADDING - \ + sizeof(struct pt_regs), \ } extern unsigned long KSTK_ESP(struct task_struct *task); @@ -704,12 +705,10 @@ static inline u32 per_cpu_l2c_id(unsigned int cpu) } #ifdef CONFIG_CPU_SUP_AMD -extern u32 amd_get_nodes_per_socket(void); extern u32 amd_get_highest_perf(void); extern void amd_clear_divider(void); extern void amd_check_microcode(void); #else -static inline u32 amd_get_nodes_per_socket(void) { return 0; } static inline u32 amd_get_highest_perf(void) { return 0; } static inline void amd_clear_divider(void) { } static inline void amd_check_microcode(void) { } diff --git a/arch/x86/include/asm/prom.h b/arch/x86/include/asm/prom.h index 65dee2420624..043758a2e627 100644 --- a/arch/x86/include/asm/prom.h +++ b/arch/x86/include/asm/prom.h @@ -23,11 +23,11 @@ extern int of_ioapic; extern u64 initial_dtb; extern void add_dtb(u64 data); void x86_of_pci_init(void); -void x86_dtb_init(void); +void x86_dtb_parse_smp_config(void); #else static inline void add_dtb(u64 data) { } static inline void x86_of_pci_init(void) { } -static inline void x86_dtb_init(void) { } +static inline void x86_dtb_parse_smp_config(void) { } #define of_ioapic 0 #endif diff --git a/arch/x86/include/asm/ptrace.h b/arch/x86/include/asm/ptrace.h index f4db78b09c8f..5a83fbd9bc0b 100644 --- a/arch/x86/include/asm/ptrace.h +++ b/arch/x86/include/asm/ptrace.h @@ -56,18 +56,64 @@ struct pt_regs { #else /* __i386__ */ +struct fred_cs { + /* CS selector */ + u64 cs : 16, + /* Stack level at event time */ + sl : 2, + /* IBT in WAIT_FOR_ENDBRANCH state */ + wfe : 1, + : 45; +}; + +struct fred_ss { + /* SS selector */ + u64 ss : 16, + /* STI state */ + sti : 1, + /* Set if syscall, sysenter or INT n */ + swevent : 1, + /* Event is NMI type */ + nmi : 1, + : 13, + /* Event vector */ + vector : 8, + : 8, + /* Event type */ + type : 4, + : 4, + /* Event was incident to enclave execution */ + enclave : 1, + /* CPU was in long mode */ + lm : 1, + /* + * Nested exception during FRED delivery, not set + * for #DF. + */ + nested : 1, + : 1, + /* + * The length of the instruction causing the event. + * Only set for INTO, INT1, INT3, INT n, SYSCALL + * and SYSENTER. 0 otherwise. + */ + insnlen : 4; +}; + struct pt_regs { -/* - * C ABI says these regs are callee-preserved. They aren't saved on kernel entry - * unless syscall needs a complete, fully filled "struct pt_regs". - */ + /* + * C ABI says these regs are callee-preserved. They aren't saved on + * kernel entry unless syscall needs a complete, fully filled + * "struct pt_regs". + */ unsigned long r15; unsigned long r14; unsigned long r13; unsigned long r12; unsigned long bp; unsigned long bx; -/* These regs are callee-clobbered. Always saved on kernel entry. */ + + /* These regs are callee-clobbered. Always saved on kernel entry. */ unsigned long r11; unsigned long r10; unsigned long r9; @@ -77,18 +123,50 @@ struct pt_regs { unsigned long dx; unsigned long si; unsigned long di; -/* - * On syscall entry, this is syscall#. On CPU exception, this is error code. - * On hw interrupt, it's IRQ number: - */ + + /* + * orig_ax is used on entry for: + * - the syscall number (syscall, sysenter, int80) + * - error_code stored by the CPU on traps and exceptions + * - the interrupt number for device interrupts + * + * A FRED stack frame starts here: + * 1) It _always_ includes an error code; + * + * 2) The return frame for ERET[US] starts here, but + * the content of orig_ax is ignored. + */ unsigned long orig_ax; -/* Return frame for iretq */ + + /* The IRETQ return frame starts here */ unsigned long ip; - unsigned long cs; + + union { + /* CS selector */ + u16 cs; + /* The extended 64-bit data slot containing CS */ + u64 csx; + /* The FRED CS extension */ + struct fred_cs fred_cs; + }; + unsigned long flags; unsigned long sp; - unsigned long ss; -/* top of stack page */ + + union { + /* SS selector */ + u16 ss; + /* The extended 64-bit data slot containing SS */ + u64 ssx; + /* The FRED SS extension */ + struct fred_ss fred_ss; + }; + + /* + * Top of stack on IDT systems, while FRED systems have extra fields + * defined above for storing exception related information, e.g. CR2 or + * DR6. + */ }; #endif /* !__i386__ */ diff --git a/arch/x86/include/asm/set_memory.h b/arch/x86/include/asm/set_memory.h index a5e89641bd2d..9aee31862b4a 100644 --- a/arch/x86/include/asm/set_memory.h +++ b/arch/x86/include/asm/set_memory.h @@ -47,6 +47,7 @@ int set_memory_uc(unsigned long addr, int numpages); int set_memory_wc(unsigned long addr, int numpages); int set_memory_wb(unsigned long addr, int numpages); int set_memory_np(unsigned long addr, int numpages); +int set_memory_p(unsigned long addr, int numpages); int set_memory_4k(unsigned long addr, int numpages); int set_memory_encrypted(unsigned long addr, int numpages); int set_memory_decrypted(unsigned long addr, int numpages); diff --git a/arch/x86/include/asm/smp.h b/arch/x86/include/asm/smp.h index 4fab2ed454f3..54d6d71e0eca 100644 --- a/arch/x86/include/asm/smp.h +++ b/arch/x86/include/asm/smp.h @@ -8,9 +8,6 @@ #include <asm/current.h> #include <asm/thread_info.h> -extern int smp_num_siblings; -extern unsigned int num_processors; - DECLARE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_sibling_map); DECLARE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_core_map); DECLARE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_die_map); @@ -110,7 +107,6 @@ void cpu_disable_common(void); void native_smp_prepare_boot_cpu(void); void smp_prepare_cpus_common(void); void native_smp_prepare_cpus(unsigned int max_cpus); -void calculate_max_logical_packages(void); void native_smp_cpus_done(unsigned int max_cpus); int common_cpu_up(unsigned int cpunum, struct task_struct *tidle); int native_kick_ap(unsigned int cpu, struct task_struct *tidle); @@ -174,8 +170,6 @@ static inline struct cpumask *cpu_llc_shared_mask(int cpu) } #endif /* CONFIG_SMP */ -extern unsigned disabled_cpus; - #ifdef CONFIG_DEBUG_NMI_SELFTEST extern void nmi_selftest(void); #else diff --git a/arch/x86/include/asm/switch_to.h b/arch/x86/include/asm/switch_to.h index f42dbf17f52b..c3bd0c0758c9 100644 --- a/arch/x86/include/asm/switch_to.h +++ b/arch/x86/include/asm/switch_to.h @@ -70,9 +70,13 @@ static inline void update_task_stack(struct task_struct *task) #ifdef CONFIG_X86_32 this_cpu_write(cpu_tss_rw.x86_tss.sp1, task->thread.sp0); #else - /* Xen PV enters the kernel on the thread stack. */ - if (cpu_feature_enabled(X86_FEATURE_XENPV)) + if (cpu_feature_enabled(X86_FEATURE_FRED)) { + /* WRMSRNS is a baseline feature for FRED. */ + wrmsrns(MSR_IA32_FRED_RSP0, (unsigned long)task_stack_page(task) + THREAD_SIZE); + } else if (cpu_feature_enabled(X86_FEATURE_XENPV)) { + /* Xen PV enters the kernel on the thread stack. */ load_sp0(task_top_of_stack(task)); + } #endif } diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h index d63b02940747..12da7dfd5ef1 100644 --- a/arch/x86/include/asm/thread_info.h +++ b/arch/x86/include/asm/thread_info.h @@ -31,7 +31,9 @@ * In vm86 mode, the hardware frame is much longer still, so add 16 * bytes to make room for the real-mode segments. * - * x86_64 has a fixed-length stack frame. + * x86-64 has a fixed-length stack frame, but it depends on whether + * or not FRED is enabled. Future versions of FRED might make this + * dynamic, but for now it is always 2 words longer. */ #ifdef CONFIG_X86_32 # ifdef CONFIG_VM86 @@ -39,8 +41,12 @@ # else # define TOP_OF_KERNEL_STACK_PADDING 8 # endif -#else -# define TOP_OF_KERNEL_STACK_PADDING 0 +#else /* x86-64 */ +# ifdef CONFIG_X86_FRED +# define TOP_OF_KERNEL_STACK_PADDING (2 * 8) +# else +# define TOP_OF_KERNEL_STACK_PADDING 0 +# endif #endif /* diff --git a/arch/x86/include/asm/topology.h b/arch/x86/include/asm/topology.h index 5f87f6b9b09e..76b1d87f1531 100644 --- a/arch/x86/include/asm/topology.h +++ b/arch/x86/include/asm/topology.h @@ -102,6 +102,35 @@ static inline void setup_node_to_cpumask_map(void) { } #include <asm-generic/topology.h> +/* Topology information */ +enum x86_topology_domains { + TOPO_SMT_DOMAIN, + TOPO_CORE_DOMAIN, + TOPO_MODULE_DOMAIN, + TOPO_TILE_DOMAIN, + TOPO_DIE_DOMAIN, + TOPO_DIEGRP_DOMAIN, + TOPO_PKG_DOMAIN, + TOPO_MAX_DOMAIN, +}; + +struct x86_topology_system { + unsigned int dom_shifts[TOPO_MAX_DOMAIN]; + unsigned int dom_size[TOPO_MAX_DOMAIN]; +}; + +extern struct x86_topology_system x86_topo_system; + +static inline unsigned int topology_get_domain_size(enum x86_topology_domains dom) +{ + return x86_topo_system.dom_size[dom]; +} + +static inline unsigned int topology_get_domain_shift(enum x86_topology_domains dom) +{ + return dom == TOPO_SMT_DOMAIN ? 0 : x86_topo_system.dom_shifts[dom - 1]; +} + extern const struct cpumask *cpu_coregroup_mask(int cpu); extern const struct cpumask *cpu_clustergroup_mask(int cpu); @@ -112,7 +141,42 @@ extern const struct cpumask *cpu_clustergroup_mask(int cpu); #define topology_core_id(cpu) (cpu_data(cpu).topo.core_id) #define topology_ppin(cpu) (cpu_data(cpu).ppin) -extern unsigned int __max_die_per_package; +#define topology_amd_node_id(cpu) (cpu_data(cpu).topo.amd_node_id) + +extern unsigned int __max_dies_per_package; +extern unsigned int __max_logical_packages; +extern unsigned int __max_threads_per_core; +extern unsigned int __num_threads_per_package; +extern unsigned int __num_cores_per_package; + +static inline unsigned int topology_max_packages(void) +{ + return __max_logical_packages; +} + +static inline unsigned int topology_max_dies_per_package(void) +{ + return __max_dies_per_package; +} + +static inline unsigned int topology_num_cores_per_package(void) +{ + return __num_cores_per_package; +} + +static inline unsigned int topology_num_threads_per_package(void) +{ + return __num_threads_per_package; +} + +#ifdef CONFIG_X86_LOCAL_APIC +int topology_get_logical_id(u32 apicid, enum x86_topology_domains at_level); +#else +static inline int topology_get_logical_id(u32 apicid, enum x86_topology_domains at_level) +{ + return 0; +} +#endif #ifdef CONFIG_SMP #define topology_cluster_id(cpu) (cpu_data(cpu).topo.l2c_id) @@ -121,12 +185,11 @@ extern unsigned int __max_die_per_package; #define topology_core_cpumask(cpu) (per_cpu(cpu_core_map, cpu)) #define topology_sibling_cpumask(cpu) (per_cpu(cpu_sibling_map, cpu)) -extern unsigned int __max_logical_packages; -#define topology_max_packages() (__max_logical_packages) -static inline int topology_max_die_per_package(void) +static inline int topology_phys_to_logical_pkg(unsigned int pkg) { - return __max_die_per_package; + return topology_get_logical_id(pkg << x86_topo_system.dom_shifts[TOPO_PKG_DOMAIN], + TOPO_PKG_DOMAIN); } extern int __max_smt_threads; @@ -138,9 +201,12 @@ static inline int topology_max_smt_threads(void) #include <linux/cpu_smt.h> -int topology_update_package_map(unsigned int apicid, unsigned int cpu); -int topology_update_die_map(unsigned int dieid, unsigned int cpu); -int topology_phys_to_logical_pkg(unsigned int pkg); +extern unsigned int __amd_nodes_per_pkg; + +static inline unsigned int topology_amd_nodes_per_pkg(void) +{ + return __amd_nodes_per_pkg; +} extern struct cpumask __cpu_primary_thread_mask; #define cpu_primary_thread_mask ((const struct cpumask *)&__cpu_primary_thread_mask) @@ -153,16 +219,12 @@ static inline bool topology_is_primary_thread(unsigned int cpu) { return cpumask_test_cpu(cpu, cpu_primary_thread_mask); } + #else /* CONFIG_SMP */ -#define topology_max_packages() (1) -static inline int -topology_update_package_map(unsigned int apicid, unsigned int cpu) { return 0; } -static inline int -topology_update_die_map(unsigned int dieid, unsigned int cpu) { return 0; } static inline int topology_phys_to_logical_pkg(unsigned int pkg) { return 0; } -static inline int topology_max_die_per_package(void) { return 1; } static inline int topology_max_smt_threads(void) { return 1; } static inline bool topology_is_primary_thread(unsigned int cpu) { return true; } +static inline unsigned int topology_amd_nodes_per_pkg(void) { return 0; }; #endif /* !CONFIG_SMP */ static inline void arch_fix_phys_package_id(int num, u32 slot) diff --git a/arch/x86/include/asm/trapnr.h b/arch/x86/include/asm/trapnr.h index f5d2325aa0b7..8d1154cdf787 100644 --- a/arch/x86/include/asm/trapnr.h +++ b/arch/x86/include/asm/trapnr.h @@ -2,6 +2,18 @@ #ifndef _ASM_X86_TRAPNR_H #define _ASM_X86_TRAPNR_H +/* + * Event type codes used by FRED, Intel VT-x and AMD SVM + */ +#define EVENT_TYPE_EXTINT 0 // External interrupt +#define EVENT_TYPE_RESERVED 1 +#define EVENT_TYPE_NMI 2 // NMI +#define EVENT_TYPE_HWEXC 3 // Hardware originated traps, exceptions +#define EVENT_TYPE_SWINT 4 // INT n +#define EVENT_TYPE_PRIV_SWEXC 5 // INT1 +#define EVENT_TYPE_SWEXC 6 // INTO, INT3 +#define EVENT_TYPE_OTHER 7 // FRED SYSCALL/SYSENTER, VT-x MTF + /* Interrupts/Exceptions */ #define X86_TRAP_DE 0 /* Divide-by-zero */ diff --git a/arch/x86/include/asm/vmx.h b/arch/x86/include/asm/vmx.h index 0e73616b82f3..4dba17363008 100644 --- a/arch/x86/include/asm/vmx.h +++ b/arch/x86/include/asm/vmx.h @@ -17,6 +17,7 @@ #include <linux/types.h> #include <uapi/asm/vmx.h> +#include <asm/trapnr.h> #include <asm/vmxfeatures.h> #define VMCS_CONTROL_BIT(x) BIT(VMX_FEATURE_##x & 0x1f) @@ -374,14 +375,14 @@ enum vmcs_field { #define VECTORING_INFO_DELIVER_CODE_MASK INTR_INFO_DELIVER_CODE_MASK #define VECTORING_INFO_VALID_MASK INTR_INFO_VALID_MASK -#define INTR_TYPE_EXT_INTR (0 << 8) /* external interrupt */ -#define INTR_TYPE_RESERVED (1 << 8) /* reserved */ -#define INTR_TYPE_NMI_INTR (2 << 8) /* NMI */ -#define INTR_TYPE_HARD_EXCEPTION (3 << 8) /* processor exception */ -#define INTR_TYPE_SOFT_INTR (4 << 8) /* software interrupt */ -#define INTR_TYPE_PRIV_SW_EXCEPTION (5 << 8) /* ICE breakpoint - undocumented */ -#define INTR_TYPE_SOFT_EXCEPTION (6 << 8) /* software exception */ -#define INTR_TYPE_OTHER_EVENT (7 << 8) /* other event */ +#define INTR_TYPE_EXT_INTR (EVENT_TYPE_EXTINT << 8) /* external interrupt */ +#define INTR_TYPE_RESERVED (EVENT_TYPE_RESERVED << 8) /* reserved */ +#define INTR_TYPE_NMI_INTR (EVENT_TYPE_NMI << 8) /* NMI */ +#define INTR_TYPE_HARD_EXCEPTION (EVENT_TYPE_HWEXC << 8) /* processor exception */ +#define INTR_TYPE_SOFT_INTR (EVENT_TYPE_SWINT << 8) /* software interrupt */ +#define INTR_TYPE_PRIV_SW_EXCEPTION (EVENT_TYPE_PRIV_SWEXC << 8) /* ICE breakpoint */ +#define INTR_TYPE_SOFT_EXCEPTION (EVENT_TYPE_SWEXC << 8) /* software exception */ +#define INTR_TYPE_OTHER_EVENT (EVENT_TYPE_OTHER << 8) /* other event */ /* GUEST_INTERRUPTIBILITY_INFO flags. */ #define GUEST_INTR_STATE_STI 0x00000001 diff --git a/arch/x86/include/asm/vsyscall.h b/arch/x86/include/asm/vsyscall.h index ab60a71a8dcb..472f0263dbc6 100644 --- a/arch/x86/include/asm/vsyscall.h +++ b/arch/x86/include/asm/vsyscall.h @@ -4,6 +4,7 @@ #include <linux/seqlock.h> #include <uapi/asm/vsyscall.h> +#include <asm/page_types.h> #ifdef CONFIG_X86_VSYSCALL_EMULATION extern void map_vsyscall(void); @@ -24,4 +25,13 @@ static inline bool emulate_vsyscall(unsigned long error_code, } #endif +/* + * The (legacy) vsyscall page is the long page in the kernel portion + * of the address space that has user-accessible permissions. + */ +static inline bool is_vsyscall_vaddr(unsigned long vaddr) +{ + return unlikely((vaddr & PAGE_MASK) == VSYSCALL_ADDR); +} + #endif /* _ASM_X86_VSYSCALL_H */ diff --git a/arch/x86/include/asm/x86_init.h b/arch/x86/include/asm/x86_init.h index c878616a18b8..9ca624749176 100644 --- a/arch/x86/include/asm/x86_init.h +++ b/arch/x86/include/asm/x86_init.h @@ -15,13 +15,15 @@ struct irq_domain; /** * struct x86_init_mpparse - platform specific mpparse ops * @setup_ioapic_ids: platform specific ioapic id override - * @find_smp_config: find the smp configuration - * @get_smp_config: get the smp configuration + * @find_mptable: Find MPTABLE early to reserve the memory region + * @early_parse_smp_cfg: Parse the SMP configuration data early before initmem_init() + * @parse_smp_cfg: Parse the SMP configuration data */ struct x86_init_mpparse { void (*setup_ioapic_ids)(void); - void (*find_smp_config)(void); - void (*get_smp_config)(unsigned int early); + void (*find_mptable)(void); + void (*early_parse_smp_cfg)(void); + void (*parse_smp_cfg)(void); }; /** diff --git a/arch/x86/include/uapi/asm/processor-flags.h b/arch/x86/include/uapi/asm/processor-flags.h index d898432947ff..f1a4adc78272 100644 --- a/arch/x86/include/uapi/asm/processor-flags.h +++ b/arch/x86/include/uapi/asm/processor-flags.h @@ -139,6 +139,13 @@ #define X86_CR4_LAM_SUP_BIT 28 /* LAM for supervisor pointers */ #define X86_CR4_LAM_SUP _BITUL(X86_CR4_LAM_SUP_BIT) +#ifdef __x86_64__ +#define X86_CR4_FRED_BIT 32 /* enable FRED kernel entry */ +#define X86_CR4_FRED _BITUL(X86_CR4_FRED_BIT) +#else +#define X86_CR4_FRED (0) +#endif + /* * x86-64 Task Priority Register, CR8 */ diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile index 0000325ab98f..0dcbfc1a4c41 100644 --- a/arch/x86/kernel/Makefile +++ b/arch/x86/kernel/Makefile @@ -48,6 +48,7 @@ obj-y += platform-quirks.o obj-y += process_$(BITS).o signal.o signal_$(BITS).o obj-y += traps.o idt.o irq.o irq_$(BITS).o dumpstack_$(BITS).o obj-y += time.o ioport.o dumpstack.o nmi.o +obj-$(CONFIG_X86_FRED) += fred.o obj-$(CONFIG_MODIFY_LDT_SYSCALL) += ldt.o obj-$(CONFIG_X86_KERNEL_IBT) += ibt_selftest.o obj-y += setup.o x86_init.o i8259.o irqinit.o diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c index 85a3ce2a3666..4bf82dbd2a6b 100644 --- a/arch/x86/kernel/acpi/boot.c +++ b/arch/x86/kernel/acpi/boot.c @@ -164,35 +164,6 @@ static int __init acpi_parse_madt(struct acpi_table_header *table) return 0; } -/** - * acpi_register_lapic - register a local apic and generates a logic cpu number - * @id: local apic id to register - * @acpiid: ACPI id to register - * @enabled: this cpu is enabled or not - * - * Returns the logic cpu number which maps to the local apic - */ -static int acpi_register_lapic(int id, u32 acpiid, u8 enabled) -{ - int cpu; - - if (id >= MAX_LOCAL_APIC) { - pr_info("skipped apicid that is too big\n"); - return -EINVAL; - } - - if (!enabled) { - ++disabled_cpus; - return -EINVAL; - } - - cpu = generic_processor_info(id); - if (cpu >= 0) - early_per_cpu(x86_cpu_to_acpiid, cpu) = acpiid; - - return cpu; -} - static bool __init acpi_is_processor_usable(u32 lapic_flags) { if (lapic_flags & ACPI_MADT_ENABLED) @@ -254,7 +225,7 @@ acpi_parse_x2apic(union acpi_subtable_headers *header, const unsigned long end) return 0; } - acpi_register_lapic(apic_id, processor->uid, enabled); + topology_register_apic(apic_id, processor->uid, enabled); #else pr_warn("x2apic entry ignored\n"); #endif @@ -289,9 +260,9 @@ acpi_parse_lapic(union acpi_subtable_headers * header, const unsigned long end) * to not preallocating memory for all NR_CPUS * when we use CPU hotplug. */ - acpi_register_lapic(processor->id, /* APIC ID */ - processor->processor_id, /* ACPI ID */ - processor->lapic_flags & ACPI_MADT_ENABLED); + topology_register_apic(processor->id, /* APIC ID */ + processor->processor_id, /* ACPI ID */ + processor->lapic_flags & ACPI_MADT_ENABLED); has_lapic_cpus = true; return 0; @@ -309,9 +280,9 @@ acpi_parse_sapic(union acpi_subtable_headers *header, const unsigned long end) acpi_table_print_madt_entry(&header->common); - acpi_register_lapic((processor->id << 8) | processor->eid,/* APIC ID */ - processor->processor_id, /* ACPI ID */ - processor->lapic_flags & ACPI_MADT_ENABLED); + topology_register_apic((processor->id << 8) | processor->eid,/* APIC ID */ + processor->processor_id, /* ACPI ID */ + processor->lapic_flags & ACPI_MADT_ENABLED); return 0; } @@ -844,12 +815,10 @@ static int acpi_map_cpu2node(acpi_handle handle, int cpu, int physid) return 0; } -int acpi_map_cpu(acpi_handle handle, phys_cpuid_t physid, u32 acpi_id, - int *pcpu) +int acpi_map_cpu(acpi_handle handle, phys_cpuid_t physid, u32 acpi_id, int *pcpu) { - int cpu; + int cpu = topology_hotplug_apic(physid, acpi_id); - cpu = acpi_register_lapic(physid, acpi_id, ACPI_MADT_ENABLED); if (cpu < 0) { pr_info("Unable to map lapic to logical cpu number\n"); return cpu; @@ -868,15 +837,11 @@ int acpi_unmap_cpu(int cpu) #ifdef CONFIG_ACPI_NUMA set_apicid_to_node(per_cpu(x86_cpu_to_apicid, cpu), NUMA_NO_NODE); #endif - - per_cpu(x86_cpu_to_apicid, cpu) = BAD_APICID; - set_cpu_present(cpu, false); - num_processors--; - - return (0); + topology_hotunplug_apic(cpu); + return 0; } EXPORT_SYMBOL(acpi_unmap_cpu); -#endif /* CONFIG_ACPI_HOTPLUG_CPU */ +#endif /* CONFIG_ACPI_HOTPLUG_CPU */ int acpi_register_ioapic(acpi_handle handle, u64 phys_addr, u32 gsi_base) { diff --git a/arch/x86/kernel/amd_nb.c b/arch/x86/kernel/amd_nb.c index 053f6dcc6b2c..5bf5f9fc5753 100644 --- a/arch/x86/kernel/amd_nb.c +++ b/arch/x86/kernel/amd_nb.c @@ -386,7 +386,7 @@ struct resource *amd_get_mmconfig_range(struct resource *res) int amd_get_subcaches(int cpu) { - struct pci_dev *link = node_to_amd_nb(topology_die_id(cpu))->link; + struct pci_dev *link = node_to_amd_nb(topology_amd_node_id(cpu))->link; unsigned int mask; if (!amd_nb_has_feature(AMD_NB_L3_PARTITIONING)) @@ -400,7 +400,7 @@ int amd_get_subcaches(int cpu) int amd_set_subcaches(int cpu, unsigned long mask) { static unsigned int reset, ban; - struct amd_northbridge *nb = node_to_amd_nb(topology_die_id(cpu)); + struct amd_northbridge *nb = node_to_amd_nb(topology_amd_node_id(cpu)); unsigned int reg; int cuid; diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index 4667bc4b00ab..a42d8a6f7149 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -19,6 +19,7 @@ #include <linux/kernel_stat.h> #include <linux/mc146818rtc.h> #include <linux/acpi_pmtmr.h> +#include <linux/bitmap.h> #include <linux/clockchips.h> #include <linux/interrupt.h> #include <linux/memblock.h> @@ -67,10 +68,6 @@ #include "local.h" -unsigned int num_processors; - -unsigned disabled_cpus; - /* Processor that is doing the boot up */ u32 boot_cpu_physical_apicid __ro_after_init = BAD_APICID; EXPORT_SYMBOL_GPL(boot_cpu_physical_apicid); @@ -78,18 +75,6 @@ EXPORT_SYMBOL_GPL(boot_cpu_physical_apicid); u8 boot_cpu_apic_version __ro_after_init; /* - * Bitmask of physically existing CPUs: - */ -physid_mask_t phys_cpu_present_map; - -/* - * Processor to be disabled specified by kernel parameter - * disable_cpu_apicid=<int>, mostly used for the kdump 2nd kernel to - * avoid undefined behaviour caused by sending INIT from AP to BSP. - */ -static u32 disabled_cpu_apicid __ro_after_init = BAD_APICID; - -/* * This variable controls which CPUs receive external NMIs. By default, * external NMIs are delivered only to the BSP. */ @@ -108,14 +93,6 @@ static inline bool apic_accessible(void) return x2apic_mode || apic_mmio_base; } -/* - * Map cpu index to physical APIC ID - */ -DEFINE_EARLY_PER_CPU_READ_MOSTLY(u32, x86_cpu_to_apicid, BAD_APICID); -DEFINE_EARLY_PER_CPU_READ_MOSTLY(u32, x86_cpu_to_acpiid, U32_MAX); -EXPORT_EARLY_PER_CPU_SYMBOL(x86_cpu_to_apicid); -EXPORT_EARLY_PER_CPU_SYMBOL(x86_cpu_to_acpiid); - #ifdef CONFIG_X86_32 /* Local APIC was disabled by the BIOS and enabled by the kernel */ static int enabled_via_apicbase __ro_after_init; @@ -261,16 +238,6 @@ u64 native_apic_icr_read(void) return icr1 | ((u64)icr2 << 32); } -#ifdef CONFIG_X86_32 -/** - * get_physical_broadcast - Get number of physical broadcast IDs - */ -int get_physical_broadcast(void) -{ - return modern_apic() ? 0xff : 0xf; -} -#endif - /** * lapic_get_maxlvt - get the maximum number of local vector table entries */ @@ -1549,9 +1516,6 @@ static void setup_local_APIC(void) apic_write(APIC_ESR, 0); } #endif - /* Validate that the APIC is registered if required */ - BUG_ON(apic->apic_id_registered && !apic->apic_id_registered()); - /* * Intel recommends to set DFR, LDR and TPR before enabling * an APIC. See e.g. "AP-388 82489DX User's Manual" (Intel @@ -1690,8 +1654,6 @@ void apic_ap_setup(void) end_local_APIC_setup(); } -static __init void cpu_set_boot_apic(void); - static __init void apic_read_boot_cpu_id(bool x2apic) { /* @@ -1706,7 +1668,8 @@ static __init void apic_read_boot_cpu_id(bool x2apic) boot_cpu_physical_apicid = read_apic_id(); boot_cpu_apic_version = GET_APIC_VERSION(apic_read(APIC_LVR)); } - cpu_set_boot_apic(); + topology_register_boot_apic(boot_cpu_physical_apicid); + x86_32_probe_bigsmp_early(); } #ifdef CONFIG_X86_X2APIC @@ -2091,7 +2054,6 @@ void __init init_apic_mappings(void) pr_info("APIC: disable apic facility\n"); apic_disable(); } - num_processors = 1; } } @@ -2305,155 +2267,6 @@ void disconnect_bsp_APIC(int virt_wire_setup) apic_write(APIC_LVT1, value); } -/* - * The number of allocated logical CPU IDs. Since logical CPU IDs are allocated - * contiguously, it equals to current allocated max logical CPU ID plus 1. - * All allocated CPU IDs should be in the [0, nr_logical_cpuids) range, - * so the maximum of nr_logical_cpuids is nr_cpu_ids. - * - * NOTE: Reserve 0 for BSP. - */ -static int nr_logical_cpuids = 1; - -/* - * Used to store mapping between logical CPU IDs and APIC IDs. - */ -u32 cpuid_to_apicid[] = { [0 ... NR_CPUS - 1] = BAD_APICID, }; - -bool arch_match_cpu_phys_id(int cpu, u64 phys_id) -{ - return phys_id == (u64)cpuid_to_apicid[cpu]; -} - -#ifdef CONFIG_SMP -static void cpu_mark_primary_thread(unsigned int cpu, unsigned int apicid) -{ - /* Isolate the SMT bit(s) in the APICID and check for 0 */ - u32 mask = (1U << (fls(smp_num_siblings) - 1)) - 1; - - if (smp_num_siblings == 1 || !(apicid & mask)) - cpumask_set_cpu(cpu, &__cpu_primary_thread_mask); -} - -/* - * Due to the utter mess of CPUID evaluation smp_num_siblings is not valid - * during early boot. Initialize the primary thread mask before SMP - * bringup. - */ -static int __init smp_init_primary_thread_mask(void) -{ - unsigned int cpu; - - /* - * XEN/PV provides either none or useless topology information. - * Pretend that all vCPUs are primary threads. - */ - if (xen_pv_domain()) { - cpumask_copy(&__cpu_primary_thread_mask, cpu_possible_mask); - return 0; - } - - for (cpu = 0; cpu < nr_logical_cpuids; cpu++) - cpu_mark_primary_thread(cpu, cpuid_to_apicid[cpu]); - return 0; -} -early_initcall(smp_init_primary_thread_mask); -#else -static inline void cpu_mark_primary_thread(unsigned int cpu, unsigned int apicid) { } -#endif - -/* - * Should use this API to allocate logical CPU IDs to keep nr_logical_cpuids - * and cpuid_to_apicid[] synchronized. - */ -static int allocate_logical_cpuid(int apicid) -{ - int i; - - /* - * cpuid <-> apicid mapping is persistent, so when a cpu is up, - * check if the kernel has allocated a cpuid for it. - */ - for (i = 0; i < nr_logical_cpuids; i++) { - if (cpuid_to_apicid[i] == apicid) - return i; - } - - /* Allocate a new cpuid. */ - if (nr_logical_cpuids >= nr_cpu_ids) { - WARN_ONCE(1, "APIC: NR_CPUS/possible_cpus limit of %u reached. " - "Processor %d/0x%x and the rest are ignored.\n", - nr_cpu_ids, nr_logical_cpuids, apicid); - return -EINVAL; - } - - cpuid_to_apicid[nr_logical_cpuids] = apicid; - return nr_logical_cpuids++; -} - -static void cpu_update_apic(int cpu, u32 apicid) -{ -#if defined(CONFIG_SMP) || defined(CONFIG_X86_64) - early_per_cpu(x86_cpu_to_apicid, cpu) = apicid; -#endif - set_cpu_possible(cpu, true); - physid_set(apicid, phys_cpu_present_map); - set_cpu_present(cpu, true); - num_processors++; - - if (system_state != SYSTEM_BOOTING) - cpu_mark_primary_thread(cpu, apicid); -} - -static __init void cpu_set_boot_apic(void) -{ - cpuid_to_apicid[0] = boot_cpu_physical_apicid; - cpu_update_apic(0, boot_cpu_physical_apicid); - x86_32_probe_bigsmp_early(); -} - -int generic_processor_info(int apicid) -{ - int cpu, max = nr_cpu_ids; - - /* The boot CPU must be set before MADT/MPTABLE parsing happens */ - if (cpuid_to_apicid[0] == BAD_APICID) - panic("Boot CPU APIC not registered yet\n"); - - if (apicid == boot_cpu_physical_apicid) - return 0; - - if (disabled_cpu_apicid == apicid) { - int thiscpu = num_processors + disabled_cpus; - - pr_warn("APIC: Disabling requested cpu. Processor %d/0x%x ignored.\n", - thiscpu, apicid); - - disabled_cpus++; - return -ENODEV; - } - - if (num_processors >= nr_cpu_ids) { - int thiscpu = max + disabled_cpus; - - pr_warn("APIC: NR_CPUS/possible_cpus limit of %i reached. " - "Processor %d/0x%x ignored.\n", max, thiscpu, apicid); - - disabled_cpus++; - return -EINVAL; - } - - cpu = allocate_logical_cpuid(apicid); - if (cpu < 0) { - disabled_cpus++; - return -EINVAL; - } - - cpu_update_apic(cpu, apicid); - return cpu; -} - - void __irq_msi_compose_msg(struct irq_cfg *cfg, struct msi_msg *msg, bool dmar) { @@ -2496,10 +2309,7 @@ EXPORT_SYMBOL_GPL(x86_msi_msg_get_destid); static void __init apic_bsp_up_setup(void) { -#ifdef CONFIG_X86_64 - apic_write(APIC_ID, apic->set_apic_id(boot_cpu_physical_apicid)); -#endif - physid_set_mask_of_physid(boot_cpu_physical_apicid, &phys_cpu_present_map); + reset_phys_cpu_present_map(boot_cpu_physical_apicid); } /** @@ -2845,15 +2655,6 @@ static int __init lapic_insert_resource(void) */ late_initcall(lapic_insert_resource); -static int __init apic_set_disabled_cpu_apicid(char *arg) -{ - if (!arg || !get_option(&arg, &disabled_cpu_apicid)) - return -EINVAL; - - return 0; -} -early_param("disable_cpu_apicid", apic_set_disabled_cpu_apicid); - static int __init apic_set_extnmi(char *arg) { if (!arg) diff --git a/arch/x86/kernel/apic/apic_common.c b/arch/x86/kernel/apic/apic_common.c index 8a00141073ea..9ef3be866832 100644 --- a/arch/x86/kernel/apic/apic_common.c +++ b/arch/x86/kernel/apic/apic_common.c @@ -18,16 +18,6 @@ u32 apic_flat_calc_apicid(unsigned int cpu) return 1U << cpu; } -bool default_check_apicid_used(physid_mask_t *map, u32 apicid) -{ - return physid_isset(apicid, *map); -} - -void default_ioapic_phys_id_map(physid_mask_t *phys_map, physid_mask_t *retmap) -{ - *retmap = *phys_map; -} - u32 default_cpu_present_to_apicid(int mps_cpu) { if (mps_cpu < nr_cpu_ids && cpu_present(mps_cpu)) @@ -37,11 +27,6 @@ u32 default_cpu_present_to_apicid(int mps_cpu) } EXPORT_SYMBOL_GPL(default_cpu_present_to_apicid); -bool default_apic_id_registered(void) -{ - return physid_isset(read_apic_id(), phys_cpu_present_map); -} - /* * Set up the logical destination ID when the APIC operates in logical * destination mode. diff --git a/arch/x86/kernel/apic/apic_flat_64.c b/arch/x86/kernel/apic/apic_flat_64.c index b295a056a4fc..f37ad3392fec 100644 --- a/arch/x86/kernel/apic/apic_flat_64.c +++ b/arch/x86/kernel/apic/apic_flat_64.c @@ -61,16 +61,6 @@ static u32 flat_get_apic_id(u32 x) return (x >> 24) & 0xFF; } -static u32 set_apic_id(u32 id) -{ - return (id & 0xFF) << 24; -} - -static u32 flat_phys_pkg_id(u32 initial_apic_id, int index_msb) -{ - return initial_apic_id >> index_msb; -} - static int flat_probe(void) { return 1; @@ -80,7 +70,6 @@ static struct apic apic_flat __ro_after_init = { .name = "flat", .probe = flat_probe, .acpi_madt_oem_check = flat_acpi_madt_oem_check, - .apic_id_registered = default_apic_id_registered, .dest_mode_logical = true, @@ -88,11 +77,9 @@ static struct apic apic_flat __ro_after_init = { .init_apic_ldr = default_init_apic_ldr, .cpu_present_to_apicid = default_cpu_present_to_apicid, - .phys_pkg_id = flat_phys_pkg_id, .max_apic_id = 0xFE, .get_apic_id = flat_get_apic_id, - .set_apic_id = set_apic_id, .calc_dest_apicid = apic_flat_calc_apicid, @@ -151,18 +138,15 @@ static struct apic apic_physflat __ro_after_init = { .name = "physical flat", .probe = physflat_probe, .acpi_madt_oem_check = physflat_acpi_madt_oem_check, - .apic_id_registered = default_apic_id_registered, .dest_mode_logical = false, .disable_esr = 0, .cpu_present_to_apicid = default_cpu_present_to_apicid, - .phys_pkg_id = flat_phys_pkg_id, .max_apic_id = 0xFE, .get_apic_id = flat_get_apic_id, - .set_apic_id = set_apic_id, .calc_dest_apicid = apic_default_calc_apicid, diff --git a/arch/x86/kernel/apic/apic_noop.c b/arch/x86/kernel/apic/apic_noop.c index 9f1d553eb48f..b5bb7a2e8340 100644 --- a/arch/x86/kernel/apic/apic_noop.c +++ b/arch/x86/kernel/apic/apic_noop.c @@ -29,7 +29,6 @@ static void noop_send_IPI_self(int vector) { } static void noop_apic_icr_write(u32 low, u32 id) { } static int noop_wakeup_secondary_cpu(u32 apicid, unsigned long start_eip) { return -1; } static u64 noop_apic_icr_read(void) { return 0; } -static u32 noop_phys_pkg_id(u32 cpuid_apic, int index_msb) { return 0; } static u32 noop_get_apic_id(u32 apicid) { return 0; } static void noop_apic_eoi(void) { } @@ -51,12 +50,8 @@ struct apic apic_noop __ro_after_init = { .disable_esr = 0, - .check_apicid_used = default_check_apicid_used, - .ioapic_phys_id_map = default_ioapic_phys_id_map, .cpu_present_to_apicid = default_cpu_present_to_apicid, - .phys_pkg_id = noop_phys_pkg_id, - .max_apic_id = 0xFE, .get_apic_id = noop_get_apic_id, diff --git a/arch/x86/kernel/apic/apic_numachip.c b/arch/x86/kernel/apic/apic_numachip.c index 7d0c51b9d3bc..16410f087b7a 100644 --- a/arch/x86/kernel/apic/apic_numachip.c +++ b/arch/x86/kernel/apic/apic_numachip.c @@ -38,11 +38,6 @@ static u32 numachip1_get_apic_id(u32 x) return id; } -static u32 numachip1_set_apic_id(u32 id) -{ - return (id & 0xff) << 24; -} - static u32 numachip2_get_apic_id(u32 x) { u64 mcfg; @@ -51,16 +46,6 @@ static u32 numachip2_get_apic_id(u32 x) return ((mcfg >> (28 - 8)) & 0xfff00) | (x >> 24); } -static u32 numachip2_set_apic_id(u32 id) -{ - return id << 24; -} - -static u32 numachip_phys_pkg_id(u32 initial_apic_id, int index_msb) -{ - return initial_apic_id >> index_msb; -} - static void numachip1_apic_icr_write(int apicid, unsigned int val) { write_lcsr(CSR_G3_EXT_IRQ_GEN, (apicid << 16) | val); @@ -227,11 +212,9 @@ static const struct apic apic_numachip1 __refconst = { .disable_esr = 0, .cpu_present_to_apicid = default_cpu_present_to_apicid, - .phys_pkg_id = numachip_phys_pkg_id, .max_apic_id = UINT_MAX, .get_apic_id = numachip1_get_apic_id, - .set_apic_id = numachip1_set_apic_id, .calc_dest_apicid = apic_default_calc_apicid, @@ -263,11 +246,9 @@ static const struct apic apic_numachip2 __refconst = { .disable_esr = 0, .cpu_present_to_apicid = default_cpu_present_to_apicid, - .phys_pkg_id = numachip_phys_pkg_id, .max_apic_id = UINT_MAX, .get_apic_id = numachip2_get_apic_id, - .set_apic_id = numachip2_set_apic_id, .calc_dest_apicid = apic_default_calc_apicid, diff --git a/arch/x86/kernel/apic/bigsmp_32.c b/arch/x86/kernel/apic/bigsmp_32.c index 5a0d60b38e6b..9285d500d5b4 100644 --- a/arch/x86/kernel/apic/bigsmp_32.c +++ b/arch/x86/kernel/apic/bigsmp_32.c @@ -18,22 +18,6 @@ static u32 bigsmp_get_apic_id(u32 x) return (x >> 24) & 0xFF; } -static bool bigsmp_check_apicid_used(physid_mask_t *map, u32 apicid) -{ - return false; -} - -static void bigsmp_ioapic_phys_id_map(physid_mask_t *phys_map, physid_mask_t *retmap) -{ - /* For clustered we don't have a good way to do this yet - hack */ - physids_promote(0xFFL, retmap); -} - -static u32 bigsmp_phys_pkg_id(u32 cpuid_apic, int index_msb) -{ - return cpuid_apic >> index_msb; -} - static void bigsmp_send_IPI_allbutself(int vector) { default_send_IPI_mask_allbutself_phys(cpu_online_mask, vector); @@ -84,14 +68,10 @@ static struct apic apic_bigsmp __ro_after_init = { .disable_esr = 1, - .check_apicid_used = bigsmp_check_apicid_used, - .ioapic_phys_id_map = bigsmp_ioapic_phys_id_map, .cpu_present_to_apicid = default_cpu_present_to_apicid, - .phys_pkg_id = bigsmp_phys_pkg_id, .max_apic_id = 0xFE, .get_apic_id = bigsmp_get_apic_id, - .set_apic_id = NULL, .calc_dest_apicid = apic_default_calc_apicid, diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c index 40c7cf180c20..477b740b2f26 100644 --- a/arch/x86/kernel/apic/io_apic.c +++ b/arch/x86/kernel/apic/io_apic.c @@ -1458,20 +1458,20 @@ void restore_boot_irq_mode(void) * * by Matt Domsch <Matt_Domsch@dell.com> Tue Dec 21 12:25:05 CST 1999 */ -void __init setup_ioapic_ids_from_mpc_nocheck(void) +static void __init setup_ioapic_ids_from_mpc_nocheck(void) { + DECLARE_BITMAP(phys_id_present_map, MAX_LOCAL_APIC); + const u32 broadcast_id = 0xF; union IO_APIC_reg_00 reg_00; - physid_mask_t phys_id_present_map; - int ioapic_idx; - int i; unsigned char old_id; unsigned long flags; + int ioapic_idx, i; /* * This is broken; anything with a real cpu count has to * circumvent this idiocy regardless. */ - apic->ioapic_phys_id_map(&phys_cpu_present_map, &phys_id_present_map); + copy_phys_cpu_present_map(phys_id_present_map); /* * Set the IOAPIC ID to the value stored in the MPC table. @@ -1484,11 +1484,10 @@ void __init setup_ioapic_ids_from_mpc_nocheck(void) old_id = mpc_ioapic_id(ioapic_idx); - if (mpc_ioapic_id(ioapic_idx) >= get_physical_broadcast()) { - printk(KERN_ERR "BIOS bug, IO-APIC#%d ID is %d in the MPC table!...\n", - ioapic_idx, mpc_ioapic_id(ioapic_idx)); - printk(KERN_ERR "... fixing up to %d. (tell your hw vendor)\n", - reg_00.bits.ID); + if (mpc_ioapic_id(ioapic_idx) >= broadcast_id) { + pr_err(FW_BUG "IO-APIC#%d ID is %d in the MPC table!...\n", + ioapic_idx, mpc_ioapic_id(ioapic_idx)); + pr_err("... fixing up to %d. (tell your hw vendor)\n", reg_00.bits.ID); ioapics[ioapic_idx].mp_config.apicid = reg_00.bits.ID; } @@ -1497,23 +1496,21 @@ void __init setup_ioapic_ids_from_mpc_nocheck(void) * system must have a unique ID or we get lots of nice * 'stuck on smp_invalidate_needed IPI wait' messages. */ - if (apic->check_apicid_used(&phys_id_present_map, - mpc_ioapic_id(ioapic_idx))) { - printk(KERN_ERR "BIOS bug, IO-APIC#%d ID %d is already used!...\n", - ioapic_idx, mpc_ioapic_id(ioapic_idx)); - for (i = 0; i < get_physical_broadcast(); i++) - if (!physid_isset(i, phys_id_present_map)) + if (test_bit(mpc_ioapic_id(ioapic_idx), phys_id_present_map)) { + pr_err(FW_BUG "IO-APIC#%d ID %d is already used!...\n", + ioapic_idx, mpc_ioapic_id(ioapic_idx)); + for (i = 0; i < broadcast_id; i++) + if (!test_bit(i, phys_id_present_map)) break; - if (i >= get_physical_broadcast()) + if (i >= broadcast_id) panic("Max APIC ID exceeded!\n"); - printk(KERN_ERR "... fixing up to %d. (tell your hw vendor)\n", - i); - physid_set(i, phys_id_present_map); + pr_err("... fixing up to %d. (tell your hw vendor)\n", i); + set_bit(i, phys_id_present_map); ioapics[ioapic_idx].mp_config.apicid = i; } else { apic_printk(APIC_VERBOSE, "Setting %d in the phys_id_present_map\n", mpc_ioapic_id(ioapic_idx)); - physid_set(mpc_ioapic_id(ioapic_idx), phys_id_present_map); + set_bit(mpc_ioapic_id(ioapic_idx), phys_id_present_map); } /* @@ -2209,7 +2206,7 @@ static inline void __init check_timer(void) * 8259A. */ if (pin1 == -1) { - panic_if_irq_remap("BIOS bug: timer not connected to IO-APIC"); + panic_if_irq_remap(FW_BUG "Timer not connected to IO-APIC"); pin1 = pin2; apic1 = apic2; no_pin1 = 1; @@ -2354,7 +2351,7 @@ static int mp_irqdomain_create(int ioapic) fwspec.param_count = 1; fwspec.param[0] = mpc_ioapic_id(ioapic); - parent = irq_find_matching_fwspec(&fwspec, DOMAIN_BUS_ANY); + parent = irq_find_matching_fwspec(&fwspec, DOMAIN_BUS_GENERIC_MSI); if (!parent) { if (!cfg->dev) irq_domain_free_fwnode(fn); @@ -2494,56 +2491,41 @@ unsigned int arch_dynirq_lower_bound(unsigned int from) #ifdef CONFIG_X86_32 static int io_apic_get_unique_id(int ioapic, int apic_id) { + static DECLARE_BITMAP(apic_id_map, MAX_LOCAL_APIC); + const u32 broadcast_id = 0xF; union IO_APIC_reg_00 reg_00; - static physid_mask_t apic_id_map = PHYSID_MASK_NONE; - physid_mask_t tmp; unsigned long flags; int i = 0; - /* - * The P4 platform supports up to 256 APIC IDs on two separate APIC - * buses (one for LAPICs, one for IOAPICs), where predecessors only - * supports up to 16 on one shared APIC bus. - * - * TBD: Expand LAPIC/IOAPIC support on P4-class systems to take full - * advantage of new APIC bus architecture. - */ - - if (physids_empty(apic_id_map)) - apic->ioapic_phys_id_map(&phys_cpu_present_map, &apic_id_map); + /* Initialize the ID map */ + if (bitmap_empty(apic_id_map, MAX_LOCAL_APIC)) + copy_phys_cpu_present_map(apic_id_map); raw_spin_lock_irqsave(&ioapic_lock, flags); reg_00.raw = io_apic_read(ioapic, 0); raw_spin_unlock_irqrestore(&ioapic_lock, flags); - if (apic_id >= get_physical_broadcast()) { - printk(KERN_WARNING "IOAPIC[%d]: Invalid apic_id %d, trying " - "%d\n", ioapic, apic_id, reg_00.bits.ID); + if (apic_id >= broadcast_id) { + pr_warn("IOAPIC[%d]: Invalid apic_id %d, trying %d\n", + ioapic, apic_id, reg_00.bits.ID); apic_id = reg_00.bits.ID; } - /* - * Every APIC in a system must have a unique ID or we get lots of nice - * 'stuck on smp_invalidate_needed IPI wait' messages. - */ - if (apic->check_apicid_used(&apic_id_map, apic_id)) { - - for (i = 0; i < get_physical_broadcast(); i++) { - if (!apic->check_apicid_used(&apic_id_map, i)) + /* Every APIC in a system must have a unique ID */ + if (test_bit(apic_id, apic_id_map)) { + for (i = 0; i < broadcast_id; i++) { + if (!test_bit(i, apic_id_map)) break; } - if (i == get_physical_broadcast()) + if (i == broadcast_id) panic("Max apic_id exceeded!\n"); - printk(KERN_WARNING "IOAPIC[%d]: apic_id %d already used, " - "trying %d\n", ioapic, apic_id, i); - + pr_warn("IOAPIC[%d]: apic_id %d already used, trying %d\n", ioapic, apic_id, i); apic_id = i; } - physid_set_mask_of_physid(apic_id, &tmp); - physids_or(apic_id_map, apic_id_map, tmp); + set_bit(apic_id, apic_id_map); if (reg_00.bits.ID != apic_id) { reg_00.bits.ID = apic_id; @@ -2569,11 +2551,9 @@ static int io_apic_get_unique_id(int ioapic, int apic_id) static u8 io_apic_unique_id(int idx, u8 id) { - if ((boot_cpu_data.x86_vendor == X86_VENDOR_INTEL) && - !APIC_XAPIC(boot_cpu_apic_version)) + if ((boot_cpu_data.x86_vendor == X86_VENDOR_INTEL) && !APIC_XAPIC(boot_cpu_apic_version)) return io_apic_get_unique_id(idx, id); - else - return id; + return id; } #else static u8 io_apic_unique_id(int idx, u8 id) diff --git a/arch/x86/kernel/apic/local.h b/arch/x86/kernel/apic/local.h index 9ea6186ea88c..842fe28496be 100644 --- a/arch/x86/kernel/apic/local.h +++ b/arch/x86/kernel/apic/local.h @@ -16,8 +16,6 @@ /* X2APIC */ void __x2apic_send_IPI_dest(unsigned int apicid, int vector, unsigned int dest); u32 x2apic_get_apic_id(u32 id); -u32 x2apic_set_apic_id(u32 id); -u32 x2apic_phys_pkg_id(u32 initial_apicid, int index_msb); void x2apic_send_IPI_all(int vector); void x2apic_send_IPI_allbutself(int vector); @@ -63,9 +61,6 @@ void default_send_IPI_allbutself(int vector); void default_send_IPI_all(int vector); void default_send_IPI_self(int vector); -bool default_apic_id_registered(void); -bool default_check_apicid_used(physid_mask_t *map, u32 apicid); - #ifdef CONFIG_X86_32 void default_send_IPI_mask_sequence_logical(const struct cpumask *mask, int vector); void default_send_IPI_mask_allbutself_logical(const struct cpumask *mask, int vector); diff --git a/arch/x86/kernel/apic/probe_32.c b/arch/x86/kernel/apic/probe_32.c index c0f78059f06a..f75ee345c02d 100644 --- a/arch/x86/kernel/apic/probe_32.c +++ b/arch/x86/kernel/apic/probe_32.c @@ -18,11 +18,6 @@ #include "local.h" -static u32 default_phys_pkg_id(u32 cpuid_apic, int index_msb) -{ - return cpuid_apic >> index_msb; -} - static u32 default_get_apic_id(u32 x) { unsigned int ver = GET_APIC_VERSION(apic_read(APIC_LVR)); @@ -43,17 +38,13 @@ static struct apic apic_default __ro_after_init = { .name = "default", .probe = probe_default, - .apic_id_registered = default_apic_id_registered, .dest_mode_logical = true, .disable_esr = 0, - .check_apicid_used = default_check_apicid_used, .init_apic_ldr = default_init_apic_ldr, - .ioapic_phys_id_map = default_ioapic_phys_id_map, .cpu_present_to_apicid = default_cpu_present_to_apicid, - .phys_pkg_id = default_phys_pkg_id, .max_apic_id = 0xFE, .get_apic_id = default_get_apic_id, diff --git a/arch/x86/kernel/apic/x2apic_cluster.c b/arch/x86/kernel/apic/x2apic_cluster.c index 28a7d3f2312d..567dbd2fe4b6 100644 --- a/arch/x86/kernel/apic/x2apic_cluster.c +++ b/arch/x86/kernel/apic/x2apic_cluster.c @@ -231,16 +231,12 @@ static struct apic apic_x2apic_cluster __ro_after_init = { .disable_esr = 0, - .check_apicid_used = NULL, .init_apic_ldr = init_x2apic_ldr, - .ioapic_phys_id_map = NULL, .cpu_present_to_apicid = default_cpu_present_to_apicid, - .phys_pkg_id = x2apic_phys_pkg_id, .max_apic_id = UINT_MAX, .x2apic_set_max_apicid = true, .get_apic_id = x2apic_get_apic_id, - .set_apic_id = x2apic_set_apic_id, .calc_dest_apicid = x2apic_calc_apicid, diff --git a/arch/x86/kernel/apic/x2apic_phys.c b/arch/x86/kernel/apic/x2apic_phys.c index 409815a40668..12d4c35547a6 100644 --- a/arch/x86/kernel/apic/x2apic_phys.c +++ b/arch/x86/kernel/apic/x2apic_phys.c @@ -129,16 +129,6 @@ u32 x2apic_get_apic_id(u32 id) return id; } -u32 x2apic_set_apic_id(u32 id) -{ - return id; -} - -u32 x2apic_phys_pkg_id(u32 initial_apicid, int index_msb) -{ - return initial_apicid >> index_msb; -} - static struct apic apic_x2apic_phys __ro_after_init = { .name = "physical x2apic", @@ -150,12 +140,10 @@ static struct apic apic_x2apic_phys __ro_after_init = { .disable_esr = 0, .cpu_present_to_apicid = default_cpu_present_to_apicid, - .phys_pkg_id = x2apic_phys_pkg_id, .max_apic_id = UINT_MAX, .x2apic_set_max_apicid = true, .get_apic_id = x2apic_get_apic_id, - .set_apic_id = x2apic_set_apic_id, .calc_dest_apicid = apic_default_calc_apicid, diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c index f1766b18dcd0..7fef504ca508 100644 --- a/arch/x86/kernel/apic/x2apic_uv_x.c +++ b/arch/x86/kernel/apic/x2apic_uv_x.c @@ -241,54 +241,20 @@ static void __init uv_tsc_check_sync(void) is_uv(UV3) ? sname.s3.field : \ undef) -/* [Copied from arch/x86/kernel/cpu/topology.c:detect_extended_topology()] */ - -#define SMT_LEVEL 0 /* Leaf 0xb SMT level */ -#define INVALID_TYPE 0 /* Leaf 0xb sub-leaf types */ -#define SMT_TYPE 1 -#define CORE_TYPE 2 -#define LEAFB_SUBTYPE(ecx) (((ecx) >> 8) & 0xff) -#define BITS_SHIFT_NEXT_LEVEL(eax) ((eax) & 0x1f) - -static void set_x2apic_bits(void) -{ - unsigned int eax, ebx, ecx, edx, sub_index; - unsigned int sid_shift; - - cpuid(0, &eax, &ebx, &ecx, &edx); - if (eax < 0xb) { - pr_info("UV: CPU does not have CPUID.11\n"); - return; - } - - cpuid_count(0xb, SMT_LEVEL, &eax, &ebx, &ecx, &edx); - if (ebx == 0 || (LEAFB_SUBTYPE(ecx) != SMT_TYPE)) { - pr_info("UV: CPUID.11 not implemented\n"); - return; - } - - sid_shift = BITS_SHIFT_NEXT_LEVEL(eax); - sub_index = 1; - do { - cpuid_count(0xb, sub_index, &eax, &ebx, &ecx, &edx); - if (LEAFB_SUBTYPE(ecx) == CORE_TYPE) { - sid_shift = BITS_SHIFT_NEXT_LEVEL(eax); - break; - } - sub_index++; - } while (LEAFB_SUBTYPE(ecx) != INVALID_TYPE); - - uv_cpuid.apicid_shift = 0; - uv_cpuid.apicid_mask = (~(-1 << sid_shift)); - uv_cpuid.socketid_shift = sid_shift; -} - static void __init early_get_apic_socketid_shift(void) { + unsigned int sid_shift = topology_get_domain_shift(TOPO_PKG_DOMAIN); + if (is_uv2_hub() || is_uv3_hub()) uvh_apicid.v = uv_early_read_mmr(UVH_APICID); - set_x2apic_bits(); + if (sid_shift) { + uv_cpuid.apicid_shift = 0; + uv_cpuid.apicid_mask = (~(-1 << sid_shift)); + uv_cpuid.socketid_shift = sid_shift; + } else { + pr_info("UV: CPU does not have valid CPUID.11\n"); + } pr_info("UV: apicid_shift:%d apicid_mask:0x%x\n", uv_cpuid.apicid_shift, uv_cpuid.apicid_mask); pr_info("UV: socketid_shift:%d pnode_mask:0x%x\n", uv_cpuid.socketid_shift, uv_cpuid.pnode_mask); @@ -779,21 +745,6 @@ static void uv_send_IPI_all(int vector) uv_send_IPI_mask(cpu_online_mask, vector); } -static u32 set_apic_id(u32 id) -{ - return id; -} - -static unsigned int uv_read_apic_id(void) -{ - return x2apic_get_apic_id(apic_read(APIC_ID)); -} - -static u32 uv_phys_pkg_id(u32 initial_apicid, int index_msb) -{ - return uv_read_apic_id() >> index_msb; -} - static int uv_probe(void) { return apic == &apic_x2apic_uv_x; @@ -810,11 +761,9 @@ static struct apic apic_x2apic_uv_x __ro_after_init = { .disable_esr = 0, .cpu_present_to_apicid = default_cpu_present_to_apicid, - .phys_pkg_id = uv_phys_pkg_id, .max_apic_id = UINT_MAX, .get_apic_id = x2apic_get_apic_id, - .set_apic_id = set_apic_id, .calc_dest_apicid = apic_default_calc_apicid, diff --git a/arch/x86/kernel/cpu/Makefile b/arch/x86/kernel/cpu/Makefile index 93eabf544031..eb4dbcdf41f1 100644 --- a/arch/x86/kernel/cpu/Makefile +++ b/arch/x86/kernel/cpu/Makefile @@ -17,7 +17,8 @@ KMSAN_SANITIZE_common.o := n # As above, instrumenting secondary CPU boot code causes boot hangs. KCSAN_SANITIZE_common.o := n -obj-y := cacheinfo.o scattered.o topology.o +obj-y := cacheinfo.o scattered.o +obj-y += topology_common.o topology_ext.o topology_amd.o obj-y += common.o obj-y += rdrand.o obj-y += match.o @@ -25,14 +26,16 @@ obj-y += bugs.o obj-y += aperfmperf.o obj-y += cpuid-deps.o obj-y += umwait.o +obj-y += capflags.o powerflags.o -obj-$(CONFIG_PROC_FS) += proc.o -obj-y += capflags.o powerflags.o +obj-$(CONFIG_X86_LOCAL_APIC) += topology.o -obj-$(CONFIG_IA32_FEAT_CTL) += feat_ctl.o +obj-$(CONFIG_PROC_FS) += proc.o + +obj-$(CONFIG_IA32_FEAT_CTL) += feat_ctl.o ifdef CONFIG_CPU_SUP_INTEL -obj-y += intel.o intel_pconfig.o tsx.o -obj-$(CONFIG_PM) += intel_epb.o +obj-y += intel.o intel_pconfig.o tsx.o +obj-$(CONFIG_PM) += intel_epb.o endif obj-$(CONFIG_CPU_SUP_AMD) += amd.o obj-$(CONFIG_CPU_SUP_HYGON) += hygon.o diff --git a/arch/x86/kernel/cpu/acrn.c b/arch/x86/kernel/cpu/acrn.c index bfeb18fad63f..2c5b51aad91a 100644 --- a/arch/x86/kernel/cpu/acrn.c +++ b/arch/x86/kernel/cpu/acrn.c @@ -26,8 +26,8 @@ static u32 __init acrn_detect(void) static void __init acrn_init_platform(void) { - /* Setup the IDT for ACRN hypervisor callback */ - alloc_intr_gate(HYPERVISOR_CALLBACK_VECTOR, asm_sysvec_acrn_hv_callback); + /* Install system interrupt handler for ACRN hypervisor callback */ + sysvec_install(HYPERVISOR_CALLBACK_VECTOR, sysvec_acrn_hv_callback); x86_platform.calibrate_tsc = acrn_get_tsc_khz; x86_platform.calibrate_cpu = acrn_get_tsc_khz; diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index f3abca334199..9cfd4e99944d 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -27,13 +27,6 @@ #include "cpu.h" -/* - * nodes_per_socket: Stores the number of nodes per socket. - * Refer to Fam15h Models 00-0fh BKDG - CPUID Fn8000_001E_ECX - * Node Identifiers[10:8] - */ -static u32 nodes_per_socket = 1; - static inline int rdmsrl_amd_safe(unsigned msr, unsigned long long *p) { u32 gprs[8] = { 0 }; @@ -300,97 +293,6 @@ static int nearby_node(int apicid) } #endif -/* - * Fix up topo::core_id for pre-F17h systems to be in the - * [0 .. cores_per_node - 1] range. Not really needed but - * kept so as not to break existing setups. - */ -static void legacy_fixup_core_id(struct cpuinfo_x86 *c) -{ - u32 cus_per_node; - - if (c->x86 >= 0x17) - return; - - cus_per_node = c->x86_max_cores / nodes_per_socket; - c->topo.core_id %= cus_per_node; -} - -/* - * Fixup core topology information for - * (1) AMD multi-node processors - * Assumption: Number of cores in each internal node is the same. - * (2) AMD processors supporting compute units - */ -static void amd_get_topology(struct cpuinfo_x86 *c) -{ - /* get information required for multi-node processors */ - if (boot_cpu_has(X86_FEATURE_TOPOEXT)) { - int err; - u32 eax, ebx, ecx, edx; - - cpuid(0x8000001e, &eax, &ebx, &ecx, &edx); - - c->topo.die_id = ecx & 0xff; - - if (c->x86 == 0x15) - c->topo.cu_id = ebx & 0xff; - - if (c->x86 >= 0x17) { - c->topo.core_id = ebx & 0xff; - - if (smp_num_siblings > 1) - c->x86_max_cores /= smp_num_siblings; - } - - /* - * In case leaf B is available, use it to derive - * topology information. - */ - err = detect_extended_topology(c); - if (!err) - c->x86_coreid_bits = get_count_order(c->x86_max_cores); - - cacheinfo_amd_init_llc_id(c); - - } else if (cpu_has(c, X86_FEATURE_NODEID_MSR)) { - u64 value; - - rdmsrl(MSR_FAM10H_NODE_ID, value); - c->topo.die_id = value & 7; - c->topo.llc_id = c->topo.die_id; - } else - return; - - if (nodes_per_socket > 1) { - set_cpu_cap(c, X86_FEATURE_AMD_DCM); - legacy_fixup_core_id(c); - } -} - -/* - * On a AMD dual core setup the lower bits of the APIC id distinguish the cores. - * Assumes number of cores is a power of two. - */ -static void amd_detect_cmp(struct cpuinfo_x86 *c) -{ - unsigned bits; - - bits = c->x86_coreid_bits; - /* Low order bits define the core id (index of core in socket) */ - c->topo.core_id = c->topo.initial_apicid & ((1 << bits)-1); - /* Convert the initial APIC ID into the socket ID */ - c->topo.pkg_id = c->topo.initial_apicid >> bits; - /* use socket ID also for last level cache */ - c->topo.llc_id = c->topo.die_id = c->topo.pkg_id; -} - -u32 amd_get_nodes_per_socket(void) -{ - return nodes_per_socket; -} -EXPORT_SYMBOL_GPL(amd_get_nodes_per_socket); - static void srat_detect_node(struct cpuinfo_x86 *c) { #ifdef CONFIG_NUMA @@ -442,32 +344,6 @@ static void srat_detect_node(struct cpuinfo_x86 *c) #endif } -static void early_init_amd_mc(struct cpuinfo_x86 *c) -{ -#ifdef CONFIG_SMP - unsigned bits, ecx; - - /* Multi core CPU? */ - if (c->extended_cpuid_level < 0x80000008) - return; - - ecx = cpuid_ecx(0x80000008); - - c->x86_max_cores = (ecx & 0xff) + 1; - - /* CPU telling us the core id bits shift? */ - bits = (ecx >> 12) & 0xF; - - /* Otherwise recompute */ - if (bits == 0) { - while ((1 << bits) < c->x86_max_cores) - bits++; - } - - c->x86_coreid_bits = bits; -#endif -} - static void bsp_init_amd(struct cpuinfo_x86 *c) { if (cpu_has(c, X86_FEATURE_CONSTANT_TSC)) { @@ -500,18 +376,6 @@ static void bsp_init_amd(struct cpuinfo_x86 *c) if (cpu_has(c, X86_FEATURE_MWAITX)) use_mwaitx_delay(); - if (boot_cpu_has(X86_FEATURE_TOPOEXT)) { - u32 ecx; - - ecx = cpuid_ecx(0x8000001e); - __max_die_per_package = nodes_per_socket = ((ecx >> 8) & 7) + 1; - } else if (boot_cpu_has(X86_FEATURE_NODEID_MSR)) { - u64 value; - - rdmsrl(MSR_FAM10H_NODE_ID, value); - __max_die_per_package = nodes_per_socket = ((value >> 3) & 7) + 1; - } - if (!boot_cpu_has(X86_FEATURE_AMD_SSBD) && !boot_cpu_has(X86_FEATURE_VIRT_SSBD) && c->x86 >= 0x15 && c->x86 <= 0x17) { @@ -649,8 +513,6 @@ static void early_init_amd(struct cpuinfo_x86 *c) u64 value; u32 dummy; - early_init_amd_mc(c); - if (c->x86 >= 0xf) set_cpu_cap(c, X86_FEATURE_K8); @@ -730,9 +592,6 @@ static void early_init_amd(struct cpuinfo_x86 *c) } } - if (cpu_has(c, X86_FEATURE_TOPOEXT)) - smp_num_siblings = ((cpuid_ebx(0x8000001e) >> 8) & 0xff) + 1; - if (!cpu_has(c, X86_FEATURE_HYPERVISOR) && !cpu_has(c, X86_FEATURE_IBPB_BRTYPE)) { if (c->x86 == 0x17 && boot_cpu_has(X86_FEATURE_AMD_IBPB)) setup_force_cpu_cap(X86_FEATURE_IBPB_BRTYPE); @@ -969,7 +828,6 @@ static void init_amd_zen_common(void) static void init_amd_zen1(struct cpuinfo_x86 *c) { - init_amd_zen_common(); fix_erratum_1386(c); /* Fix up CPUID bits, but only if not virtualised. */ @@ -1023,7 +881,6 @@ static void zen2_zenbleed_check(struct cpuinfo_x86 *c) static void init_amd_zen2(struct cpuinfo_x86 *c) { - init_amd_zen_common(); init_spectral_chicken(c); fix_erratum_1386(c); zen2_zenbleed_check(c); @@ -1031,8 +888,6 @@ static void init_amd_zen2(struct cpuinfo_x86 *c) static void init_amd_zen3(struct cpuinfo_x86 *c) { - init_amd_zen_common(); - if (!cpu_has(c, X86_FEATURE_HYPERVISOR)) { /* * Zen3 (Fam19 model < 0x10) parts are not susceptible to @@ -1046,15 +901,12 @@ static void init_amd_zen3(struct cpuinfo_x86 *c) static void init_amd_zen4(struct cpuinfo_x86 *c) { - init_amd_zen_common(); - if (!cpu_has(c, X86_FEATURE_HYPERVISOR)) msr_set_bit(MSR_ZEN4_BP_CFG, MSR_ZEN4_BP_CFG_SHARED_BTB_FIX_BIT); } static void init_amd_zen5(struct cpuinfo_x86 *c) { - init_amd_zen_common(); } static void init_amd(struct cpuinfo_x86 *c) @@ -1076,9 +928,6 @@ static void init_amd(struct cpuinfo_x86 *c) if (cpu_has(c, X86_FEATURE_FSRM)) set_cpu_cap(c, X86_FEATURE_FSRS); - /* get apicid instead of initial apic id from cpuid */ - c->topo.apicid = read_apic_id(); - /* K6s reports MCEs but don't actually have all the MSRs */ if (c->x86 < 6) clear_cpu_cap(c, X86_FEATURE_MCE); @@ -1094,6 +943,13 @@ static void init_amd(struct cpuinfo_x86 *c) case 0x16: init_amd_jg(c); break; } + /* + * Save up on some future enablement work and do common Zen + * settings. + */ + if (c->x86 >= 0x17) + init_amd_zen_common(); + if (boot_cpu_has(X86_FEATURE_ZEN1)) init_amd_zen1(c); else if (boot_cpu_has(X86_FEATURE_ZEN2)) @@ -1114,8 +970,6 @@ static void init_amd(struct cpuinfo_x86 *c) cpu_detect_cache_sizes(c); - amd_detect_cmp(c); - amd_get_topology(c); srat_detect_node(c); init_amd_cacheinfo(c); diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index bb0ab8466b91..48d049cd74e7 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -111,9 +111,6 @@ DEFINE_STATIC_KEY_FALSE(switch_mm_cond_ibpb); /* Control unconditional IBPB in switch_mm() */ DEFINE_STATIC_KEY_FALSE(switch_mm_always_ibpb); -/* Control MDS CPU buffer clear before returning to user space */ -DEFINE_STATIC_KEY_FALSE(mds_user_clear); -EXPORT_SYMBOL_GPL(mds_user_clear); /* Control MDS CPU buffer clear before idling (halt, mwait) */ DEFINE_STATIC_KEY_FALSE(mds_idle_clear); EXPORT_SYMBOL_GPL(mds_idle_clear); @@ -252,7 +249,7 @@ static void __init mds_select_mitigation(void) if (!boot_cpu_has(X86_FEATURE_MD_CLEAR)) mds_mitigation = MDS_MITIGATION_VMWERV; - static_branch_enable(&mds_user_clear); + setup_force_cpu_cap(X86_FEATURE_CLEAR_CPU_BUF); if (!boot_cpu_has(X86_BUG_MSBDS_ONLY) && (mds_nosmt || cpu_mitigations_auto_nosmt())) @@ -356,7 +353,7 @@ static void __init taa_select_mitigation(void) * For guests that can't determine whether the correct microcode is * present on host, enable the mitigation for UCODE_NEEDED as well. */ - static_branch_enable(&mds_user_clear); + setup_force_cpu_cap(X86_FEATURE_CLEAR_CPU_BUF); if (taa_nosmt || cpu_mitigations_auto_nosmt()) cpu_smt_disable(false); @@ -424,7 +421,7 @@ static void __init mmio_select_mitigation(void) */ if (boot_cpu_has_bug(X86_BUG_MDS) || (boot_cpu_has_bug(X86_BUG_TAA) && boot_cpu_has(X86_FEATURE_RTM))) - static_branch_enable(&mds_user_clear); + setup_force_cpu_cap(X86_FEATURE_CLEAR_CPU_BUF); else static_branch_enable(&mmio_stale_data_clear); @@ -484,12 +481,12 @@ static void __init md_clear_update_mitigation(void) if (cpu_mitigations_off()) return; - if (!static_key_enabled(&mds_user_clear)) + if (!boot_cpu_has(X86_FEATURE_CLEAR_CPU_BUF)) goto out; /* - * mds_user_clear is now enabled. Update MDS, TAA and MMIO Stale Data - * mitigation, if necessary. + * X86_FEATURE_CLEAR_CPU_BUF is now enabled. Update MDS, TAA and MMIO + * Stale Data mitigation, if necessary. */ if (mds_mitigation == MDS_MITIGATION_OFF && boot_cpu_has_bug(X86_BUG_MDS)) { diff --git a/arch/x86/kernel/cpu/cacheinfo.c b/arch/x86/kernel/cpu/cacheinfo.c index 78afad50a7c0..392d09c936d6 100644 --- a/arch/x86/kernel/cpu/cacheinfo.c +++ b/arch/x86/kernel/cpu/cacheinfo.c @@ -301,7 +301,7 @@ amd_cpuid4(int leaf, union _cpuid4_leaf_eax *eax, eax->split.type = types[leaf]; eax->split.level = levels[leaf]; eax->split.num_threads_sharing = 0; - eax->split.num_cores_on_die = __this_cpu_read(cpu_info.x86_max_cores) - 1; + eax->split.num_cores_on_die = topology_num_cores_per_package(); if (assoc == 0xffff) @@ -595,7 +595,7 @@ static void amd_init_l3_cache(struct _cpuid4_info_regs *this_leaf, int index) if (index < 3) return; - node = topology_die_id(smp_processor_id()); + node = topology_amd_node_id(smp_processor_id()); this_leaf->nb = node_to_amd_nb(node); if (this_leaf->nb && !this_leaf->nb->l3_cache.indices) amd_calc_l3_indices(this_leaf->nb); @@ -661,7 +661,7 @@ static int find_num_cache_leaves(struct cpuinfo_x86 *c) return i; } -void cacheinfo_amd_init_llc_id(struct cpuinfo_x86 *c) +void cacheinfo_amd_init_llc_id(struct cpuinfo_x86 *c, u16 die_id) { /* * We may have multiple LLCs if L3 caches exist, so check if we @@ -672,7 +672,7 @@ void cacheinfo_amd_init_llc_id(struct cpuinfo_x86 *c) if (c->x86 < 0x17) { /* LLC is at the node level. */ - c->topo.llc_id = c->topo.die_id; + c->topo.llc_id = die_id; } else if (c->x86 == 0x17 && c->x86_model <= 0x1F) { /* * LLC is at the core complex level. diff --git a/arch/x86/kernel/cpu/centaur.c b/arch/x86/kernel/cpu/centaur.c index 345f7d905db6..a3b55db35c96 100644 --- a/arch/x86/kernel/cpu/centaur.c +++ b/arch/x86/kernel/cpu/centaur.c @@ -128,10 +128,6 @@ static void init_centaur(struct cpuinfo_x86 *c) #endif early_init_centaur(c); init_intel_cacheinfo(c); - detect_num_cpu_cores(c); -#ifdef CONFIG_X86_32 - detect_ht(c); -#endif if (c->cpuid_level > 9) { unsigned int eax = cpuid_eax(10); diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 0b97bcde70c6..c44e6f0c8972 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -61,6 +61,7 @@ #include <asm/microcode.h> #include <asm/intel-family.h> #include <asm/cpu_device_id.h> +#include <asm/fred.h> #include <asm/uv/uv.h> #include <asm/ia32.h> #include <asm/set_memory.h> @@ -73,8 +74,20 @@ u32 elf_hwcap2 __read_mostly; /* Number of siblings per CPU package */ -int smp_num_siblings = 1; -EXPORT_SYMBOL(smp_num_siblings); +unsigned int __max_threads_per_core __ro_after_init = 1; +EXPORT_SYMBOL(__max_threads_per_core); + +unsigned int __max_dies_per_package __ro_after_init = 1; +EXPORT_SYMBOL(__max_dies_per_package); + +unsigned int __max_logical_packages __ro_after_init = 1; +EXPORT_SYMBOL(__max_logical_packages); + +unsigned int __num_cores_per_package __ro_after_init = 1; +EXPORT_SYMBOL(__num_cores_per_package); + +unsigned int __num_threads_per_package __ro_after_init = 1; +EXPORT_SYMBOL(__num_threads_per_package); static struct ppin_info { int feature; @@ -382,9 +395,8 @@ out: } /* These bits should not change their value after CPU init is finished. */ -static const unsigned long cr4_pinned_mask = - X86_CR4_SMEP | X86_CR4_SMAP | X86_CR4_UMIP | - X86_CR4_FSGSBASE | X86_CR4_CET; +static const unsigned long cr4_pinned_mask = X86_CR4_SMEP | X86_CR4_SMAP | X86_CR4_UMIP | + X86_CR4_FSGSBASE | X86_CR4_CET | X86_CR4_FRED; static DEFINE_STATIC_KEY_FALSE_RO(cr_pinning); static unsigned long cr4_pinned_bits __ro_after_init; @@ -790,19 +802,6 @@ static void get_model_name(struct cpuinfo_x86 *c) *(s + 1) = '\0'; } -void detect_num_cpu_cores(struct cpuinfo_x86 *c) -{ - unsigned int eax, ebx, ecx, edx; - - c->x86_max_cores = 1; - if (!IS_ENABLED(CONFIG_SMP) || c->cpuid_level < 4) - return; - - cpuid_count(4, 0, &eax, &ebx, &ecx, &edx); - if (eax & 0x1f) - c->x86_max_cores = (eax >> 26) + 1; -} - void cpu_detect_cache_sizes(struct cpuinfo_x86 *c) { unsigned int n, dummy, ebx, ecx, edx, l2size; @@ -864,51 +863,6 @@ static void cpu_detect_tlb(struct cpuinfo_x86 *c) tlb_lld_4m[ENTRIES], tlb_lld_1g[ENTRIES]); } -int detect_ht_early(struct cpuinfo_x86 *c) -{ -#ifdef CONFIG_SMP - u32 eax, ebx, ecx, edx; - - if (!cpu_has(c, X86_FEATURE_HT)) - return -1; - - if (cpu_has(c, X86_FEATURE_CMP_LEGACY)) - return -1; - - if (cpu_has(c, X86_FEATURE_XTOPOLOGY)) - return -1; - - cpuid(1, &eax, &ebx, &ecx, &edx); - - smp_num_siblings = (ebx & 0xff0000) >> 16; - if (smp_num_siblings == 1) - pr_info_once("CPU0: Hyper-Threading is disabled\n"); -#endif - return 0; -} - -void detect_ht(struct cpuinfo_x86 *c) -{ -#ifdef CONFIG_SMP - int index_msb, core_bits; - - if (detect_ht_early(c) < 0) - return; - - index_msb = get_count_order(smp_num_siblings); - c->topo.pkg_id = apic->phys_pkg_id(c->topo.initial_apicid, index_msb); - - smp_num_siblings = smp_num_siblings / c->x86_max_cores; - - index_msb = get_count_order(smp_num_siblings); - - core_bits = get_count_order(c->x86_max_cores); - - c->topo.core_id = apic->phys_pkg_id(c->topo.initial_apicid, index_msb) & - ((1 << core_bits) - 1); -#endif -} - static void get_cpu_vendor(struct cpuinfo_x86 *c) { char *v = c->x86_vendor_id; @@ -1589,8 +1543,11 @@ static void __init early_identify_cpu(struct cpuinfo_x86 *c) get_cpu_vendor(c); get_cpu_cap(c); setup_force_cpu_cap(X86_FEATURE_CPUID); + get_cpu_address_sizes(c); cpu_parse_early_param(); + cpu_init_topology(c); + if (this_cpu->c_early_init) this_cpu->c_early_init(c); @@ -1601,10 +1558,10 @@ static void __init early_identify_cpu(struct cpuinfo_x86 *c) this_cpu->c_bsp_init(c); } else { setup_clear_cpu_cap(X86_FEATURE_CPUID); + get_cpu_address_sizes(c); + cpu_init_topology(c); } - get_cpu_address_sizes(c); - setup_force_cpu_cap(X86_FEATURE_ALWAYS); cpu_set_bug_bits(c); @@ -1748,18 +1705,6 @@ static void generic_identify(struct cpuinfo_x86 *c) get_cpu_address_sizes(c); - if (c->cpuid_level >= 0x00000001) { - c->topo.initial_apicid = (cpuid_ebx(1) >> 24) & 0xFF; -#ifdef CONFIG_X86_32 -# ifdef CONFIG_SMP - c->topo.apicid = apic->phys_pkg_id(c->topo.initial_apicid, 0); -# else - c->topo.apicid = c->topo.initial_apicid; -# endif -#endif - c->topo.pkg_id = c->topo.initial_apicid; - } - get_model_name(c); /* Default name */ /* @@ -1781,29 +1726,6 @@ static void generic_identify(struct cpuinfo_x86 *c) } /* - * Validate that ACPI/mptables have the same information about the - * effective APIC id and update the package map. - */ -static void validate_apic_and_package_id(struct cpuinfo_x86 *c) -{ -#ifdef CONFIG_SMP - unsigned int cpu = smp_processor_id(); - u32 apicid; - - apicid = apic->cpu_present_to_apicid(cpu); - - if (apicid != c->topo.apicid) { - pr_err(FW_BUG "CPU%u: APIC id mismatch. Firmware: %x APIC: %x\n", - cpu, apicid, c->topo.initial_apicid); - } - BUG_ON(topology_update_package_map(c->topo.pkg_id, cpu)); - BUG_ON(topology_update_die_map(c->topo.die_id, cpu)); -#else - c->topo.logical_pkg_id = 0; -#endif -} - -/* * This does the hard work of actually picking apart the CPU stuff... */ static void identify_cpu(struct cpuinfo_x86 *c) @@ -1816,11 +1738,6 @@ static void identify_cpu(struct cpuinfo_x86 *c) c->x86_model = c->x86_stepping = 0; /* So far unknown... */ c->x86_vendor_id[0] = '\0'; /* Unset */ c->x86_model_id[0] = '\0'; /* Unset */ - c->x86_max_cores = 1; - c->x86_coreid_bits = 0; - c->topo.cu_id = 0xff; - c->topo.llc_id = BAD_APICID; - c->topo.l2c_id = BAD_APICID; #ifdef CONFIG_X86_64 c->x86_clflush_size = 64; c->x86_phys_bits = 36; @@ -1839,17 +1756,14 @@ static void identify_cpu(struct cpuinfo_x86 *c) generic_identify(c); + cpu_parse_topology(c); + if (this_cpu->c_identify) this_cpu->c_identify(c); /* Clear/Set all flags overridden by options, after probe */ apply_forced_caps(c); -#ifdef CONFIG_X86_64 - c->topo.apicid = apic->phys_pkg_id(c->topo.initial_apicid, 0); -#endif - - /* * Set default APIC and TSC_DEADLINE MSR fencing flag. AMD and * Hygon will clear it in ->c_init() below. @@ -1903,10 +1817,6 @@ static void identify_cpu(struct cpuinfo_x86 *c) c->x86, c->x86_model); } -#ifdef CONFIG_X86_64 - detect_ht(c); -#endif - x86_init_rdrand(c); setup_pku(c); setup_cet(c); @@ -1998,7 +1908,6 @@ void identify_secondary_cpu(struct cpuinfo_x86 *c) #ifdef CONFIG_X86_32 enable_sep_cpu(); #endif - validate_apic_and_package_id(c); x86_spec_ctrl_setup_ap(); update_srbds_msr(); if (boot_cpu_has_bug(X86_BUG_GDS)) @@ -2067,10 +1976,8 @@ static void wrmsrl_cstar(unsigned long val) wrmsrl(MSR_CSTAR, val); } -/* May not be marked __init: used by software suspend */ -void syscall_init(void) +static inline void idt_syscall_init(void) { - wrmsr(MSR_STAR, 0, (__USER32_CS << 16) | __KERNEL_CS); wrmsrl(MSR_LSTAR, (unsigned long)entry_SYSCALL_64); if (ia32_enabled()) { @@ -2104,6 +2011,23 @@ void syscall_init(void) X86_EFLAGS_AC|X86_EFLAGS_ID); } +/* May not be marked __init: used by software suspend */ +void syscall_init(void) +{ + /* The default user and kernel segments */ + wrmsr(MSR_STAR, 0, (__USER32_CS << 16) | __KERNEL_CS); + + /* + * Except the IA32_STAR MSR, there is NO need to setup SYSCALL and + * SYSENTER MSRs for FRED, because FRED uses the ring 3 FRED + * entrypoint for SYSCALL and SYSENTER, and ERETU is the only legit + * instruction to return to ring 3 (both sysexit and sysret cause + * #UD when FRED is enabled). + */ + if (!cpu_feature_enabled(X86_FEATURE_FRED)) + idt_syscall_init(); +} + #else /* CONFIG_X86_64 */ #ifdef CONFIG_STACKPROTECTOR @@ -2207,8 +2131,9 @@ void cpu_init_exception_handling(void) /* paranoid_entry() gets the CPU number from the GDT */ setup_getcpu(cpu); - /* IST vectors need TSS to be set up. */ - tss_setup_ist(tss); + /* For IDT mode, IST vectors need to be set in TSS. */ + if (!cpu_feature_enabled(X86_FEATURE_FRED)) + tss_setup_ist(tss); tss_setup_io_bitmap(tss); set_tss_desc(cpu, &get_cpu_entry_area(cpu)->tss.x86_tss); @@ -2217,8 +2142,10 @@ void cpu_init_exception_handling(void) /* GHCB needs to be setup to handle #VC. */ setup_ghcb(); - /* Finally load the IDT */ - load_current_idt(); + if (cpu_feature_enabled(X86_FEATURE_FRED)) + cpu_init_fred_exceptions(); + else + load_current_idt(); } /* @@ -2347,7 +2274,7 @@ void __init arch_cpu_finalize_init(void) * identify_boot_cpu() initialized SMT support information, let the * core code know. */ - cpu_smt_set_num_threads(smp_num_siblings, smp_num_siblings); + cpu_smt_set_num_threads(__max_threads_per_core, __max_threads_per_core); if (!IS_ENABLED(CONFIG_SMP)) { pr_info("CPU: "); diff --git a/arch/x86/kernel/cpu/cpu.h b/arch/x86/kernel/cpu/cpu.h index 885281ae79a5..ea9e07d57c8d 100644 --- a/arch/x86/kernel/cpu/cpu.h +++ b/arch/x86/kernel/cpu/cpu.h @@ -2,6 +2,11 @@ #ifndef ARCH_X86_CPU_H #define ARCH_X86_CPU_H +#include <asm/cpu.h> +#include <asm/topology.h> + +#include "topology.h" + /* attempt to consolidate cpu attributes */ struct cpu_dev { const char *c_vendor; @@ -71,14 +76,9 @@ extern void init_intel_cacheinfo(struct cpuinfo_x86 *c); extern void init_amd_cacheinfo(struct cpuinfo_x86 *c); extern void init_hygon_cacheinfo(struct cpuinfo_x86 *c); -extern void detect_num_cpu_cores(struct cpuinfo_x86 *c); -extern int detect_extended_topology_early(struct cpuinfo_x86 *c); -extern int detect_extended_topology(struct cpuinfo_x86 *c); -extern int detect_ht_early(struct cpuinfo_x86 *c); -extern void detect_ht(struct cpuinfo_x86 *c); extern void check_null_seg_clears_base(struct cpuinfo_x86 *c); -void cacheinfo_amd_init_llc_id(struct cpuinfo_x86 *c); +void cacheinfo_amd_init_llc_id(struct cpuinfo_x86 *c, u16 die_id); void cacheinfo_hygon_init_llc_id(struct cpuinfo_x86 *c); unsigned int aperfmperf_get_khz(int cpu); @@ -96,4 +96,5 @@ static inline bool spectre_v2_in_eibrs_mode(enum spectre_v2_mitigation mode) mode == SPECTRE_V2_EIBRS_RETPOLINE || mode == SPECTRE_V2_EIBRS_LFENCE; } + #endif /* ARCH_X86_CPU_H */ diff --git a/arch/x86/kernel/cpu/cpuid-deps.c b/arch/x86/kernel/cpu/cpuid-deps.c index e462c1d3800a..b7174209d855 100644 --- a/arch/x86/kernel/cpu/cpuid-deps.c +++ b/arch/x86/kernel/cpu/cpuid-deps.c @@ -82,6 +82,8 @@ static const struct cpuid_dep cpuid_deps[] = { { X86_FEATURE_XFD, X86_FEATURE_XGETBV1 }, { X86_FEATURE_AMX_TILE, X86_FEATURE_XFD }, { X86_FEATURE_SHSTK, X86_FEATURE_XSAVES }, + { X86_FEATURE_FRED, X86_FEATURE_LKGS }, + { X86_FEATURE_FRED, X86_FEATURE_WRMSRNS }, {} }; diff --git a/arch/x86/kernel/cpu/debugfs.c b/arch/x86/kernel/cpu/debugfs.c index 0c179d684b3b..3baf3e435834 100644 --- a/arch/x86/kernel/cpu/debugfs.c +++ b/arch/x86/kernel/cpu/debugfs.c @@ -5,6 +5,8 @@ #include <asm/apic.h> #include <asm/processor.h> +#include "cpu.h" + static int cpu_debug_show(struct seq_file *m, void *p) { unsigned long cpu = (unsigned long)m->private; @@ -24,9 +26,12 @@ static int cpu_debug_show(struct seq_file *m, void *p) seq_printf(m, "logical_die_id: %u\n", c->topo.logical_die_id); seq_printf(m, "llc_id: %u\n", c->topo.llc_id); seq_printf(m, "l2c_id: %u\n", c->topo.l2c_id); - seq_printf(m, "max_cores: %u\n", c->x86_max_cores); - seq_printf(m, "max_die_per_pkg: %u\n", __max_die_per_package); - seq_printf(m, "smp_num_siblings: %u\n", smp_num_siblings); + seq_printf(m, "amd_node_id: %u\n", c->topo.amd_node_id); + seq_printf(m, "amd_nodes_per_pkg: %u\n", topology_amd_nodes_per_pkg()); + seq_printf(m, "num_threads: %u\n", __num_threads_per_package); + seq_printf(m, "num_cores: %u\n", __num_cores_per_package); + seq_printf(m, "max_dies_per_pkg: %u\n", __max_dies_per_package); + seq_printf(m, "max_threads_per_core:%u\n", __max_threads_per_core); return 0; } @@ -42,12 +47,48 @@ static const struct file_operations dfs_cpu_ops = { .release = single_release, }; +static int dom_debug_show(struct seq_file *m, void *p) +{ + static const char *domain_names[TOPO_MAX_DOMAIN] = { + [TOPO_SMT_DOMAIN] = "Thread", + [TOPO_CORE_DOMAIN] = "Core", + [TOPO_MODULE_DOMAIN] = "Module", + [TOPO_TILE_DOMAIN] = "Tile", + [TOPO_DIE_DOMAIN] = "Die", + [TOPO_DIEGRP_DOMAIN] = "DieGrp", + [TOPO_PKG_DOMAIN] = "Package", + }; + unsigned int dom, nthreads = 1; + + for (dom = 0; dom < TOPO_MAX_DOMAIN; dom++) { + nthreads *= x86_topo_system.dom_size[dom]; + seq_printf(m, "domain: %-10s shift: %u dom_size: %5u max_threads: %5u\n", + domain_names[dom], x86_topo_system.dom_shifts[dom], + x86_topo_system.dom_size[dom], nthreads); + } + return 0; +} + +static int dom_debug_open(struct inode *inode, struct file *file) +{ + return single_open(file, dom_debug_show, inode->i_private); +} + +static const struct file_operations dfs_dom_ops = { + .open = dom_debug_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; + static __init int cpu_init_debugfs(void) { struct dentry *dir, *base = debugfs_create_dir("topo", arch_debugfs_dir); unsigned long id; char name[24]; + debugfs_create_file("domains", 0444, base, NULL, &dfs_dom_ops); + dir = debugfs_create_dir("cpus", base); for_each_possible_cpu(id) { sprintf(name, "%lu", id); diff --git a/arch/x86/kernel/cpu/hygon.c b/arch/x86/kernel/cpu/hygon.c index f0cd95502faa..c5191b06f9f2 100644 --- a/arch/x86/kernel/cpu/hygon.c +++ b/arch/x86/kernel/cpu/hygon.c @@ -18,14 +18,6 @@ #include "cpu.h" -#define APICID_SOCKET_ID_BIT 6 - -/* - * nodes_per_socket: Stores the number of nodes per socket. - * Refer to CPUID Fn8000_001E_ECX Node Identifiers[10:8] - */ -static u32 nodes_per_socket = 1; - #ifdef CONFIG_NUMA /* * To workaround broken NUMA config. Read the comment in @@ -49,80 +41,6 @@ static int nearby_node(int apicid) } #endif -static void hygon_get_topology_early(struct cpuinfo_x86 *c) -{ - if (cpu_has(c, X86_FEATURE_TOPOEXT)) - smp_num_siblings = ((cpuid_ebx(0x8000001e) >> 8) & 0xff) + 1; -} - -/* - * Fixup core topology information for - * (1) Hygon multi-node processors - * Assumption: Number of cores in each internal node is the same. - * (2) Hygon processors supporting compute units - */ -static void hygon_get_topology(struct cpuinfo_x86 *c) -{ - /* get information required for multi-node processors */ - if (boot_cpu_has(X86_FEATURE_TOPOEXT)) { - int err; - u32 eax, ebx, ecx, edx; - - cpuid(0x8000001e, &eax, &ebx, &ecx, &edx); - - c->topo.die_id = ecx & 0xff; - - c->topo.core_id = ebx & 0xff; - - if (smp_num_siblings > 1) - c->x86_max_cores /= smp_num_siblings; - - /* - * In case leaf B is available, use it to derive - * topology information. - */ - err = detect_extended_topology(c); - if (!err) - c->x86_coreid_bits = get_count_order(c->x86_max_cores); - - /* - * Socket ID is ApicId[6] for the processors with model <= 0x3 - * when running on host. - */ - if (!boot_cpu_has(X86_FEATURE_HYPERVISOR) && c->x86_model <= 0x3) - c->topo.pkg_id = c->topo.apicid >> APICID_SOCKET_ID_BIT; - - cacheinfo_hygon_init_llc_id(c); - } else if (cpu_has(c, X86_FEATURE_NODEID_MSR)) { - u64 value; - - rdmsrl(MSR_FAM10H_NODE_ID, value); - c->topo.die_id = value & 7; - c->topo.llc_id = c->topo.die_id; - } else - return; - - if (nodes_per_socket > 1) - set_cpu_cap(c, X86_FEATURE_AMD_DCM); -} - -/* - * On Hygon setup the lower bits of the APIC id distinguish the cores. - * Assumes number of cores is a power of two. - */ -static void hygon_detect_cmp(struct cpuinfo_x86 *c) -{ - unsigned int bits; - - bits = c->x86_coreid_bits; - /* Low order bits define the core id (index of core in socket) */ - c->topo.core_id = c->topo.initial_apicid & ((1 << bits)-1); - /* Convert the initial APIC ID into the socket ID */ - c->topo.pkg_id = c->topo.initial_apicid >> bits; - /* Use package ID also for last level cache */ - c->topo.llc_id = c->topo.die_id = c->topo.pkg_id; -} - static void srat_detect_node(struct cpuinfo_x86 *c) { #ifdef CONFIG_NUMA @@ -173,32 +91,6 @@ static void srat_detect_node(struct cpuinfo_x86 *c) #endif } -static void early_init_hygon_mc(struct cpuinfo_x86 *c) -{ -#ifdef CONFIG_SMP - unsigned int bits, ecx; - - /* Multi core CPU? */ - if (c->extended_cpuid_level < 0x80000008) - return; - - ecx = cpuid_ecx(0x80000008); - - c->x86_max_cores = (ecx & 0xff) + 1; - - /* CPU telling us the core id bits shift? */ - bits = (ecx >> 12) & 0xF; - - /* Otherwise recompute */ - if (bits == 0) { - while ((1 << bits) < c->x86_max_cores) - bits++; - } - - c->x86_coreid_bits = bits; -#endif -} - static void bsp_init_hygon(struct cpuinfo_x86 *c) { if (cpu_has(c, X86_FEATURE_CONSTANT_TSC)) { @@ -212,18 +104,6 @@ static void bsp_init_hygon(struct cpuinfo_x86 *c) if (cpu_has(c, X86_FEATURE_MWAITX)) use_mwaitx_delay(); - if (boot_cpu_has(X86_FEATURE_TOPOEXT)) { - u32 ecx; - - ecx = cpuid_ecx(0x8000001e); - __max_die_per_package = nodes_per_socket = ((ecx >> 8) & 7) + 1; - } else if (boot_cpu_has(X86_FEATURE_NODEID_MSR)) { - u64 value; - - rdmsrl(MSR_FAM10H_NODE_ID, value); - __max_die_per_package = nodes_per_socket = ((value >> 3) & 7) + 1; - } - if (!boot_cpu_has(X86_FEATURE_AMD_SSBD) && !boot_cpu_has(X86_FEATURE_VIRT_SSBD)) { /* @@ -242,8 +122,6 @@ static void early_init_hygon(struct cpuinfo_x86 *c) { u32 dummy; - early_init_hygon_mc(c); - set_cpu_cap(c, X86_FEATURE_K8); rdmsr_safe(MSR_AMD64_PATCH_LEVEL, &c->microcode, &dummy); @@ -284,8 +162,6 @@ static void early_init_hygon(struct cpuinfo_x86 *c) * we can set it unconditionally. */ set_cpu_cap(c, X86_FEATURE_VMMCALL); - - hygon_get_topology_early(c); } static void init_hygon(struct cpuinfo_x86 *c) @@ -302,9 +178,6 @@ static void init_hygon(struct cpuinfo_x86 *c) set_cpu_cap(c, X86_FEATURE_REP_GOOD); - /* get apicid instead of initial apic id from cpuid */ - c->topo.apicid = read_apic_id(); - /* * XXX someone from Hygon needs to confirm this DTRT * @@ -316,8 +189,6 @@ static void init_hygon(struct cpuinfo_x86 *c) cpu_detect_cache_sizes(c); - hygon_detect_cmp(c); - hygon_get_topology(c); srat_detect_node(c); init_hygon_cacheinfo(c); diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c index a927a8fc9624..be30d7fa2e66 100644 --- a/arch/x86/kernel/cpu/intel.c +++ b/arch/x86/kernel/cpu/intel.c @@ -184,6 +184,90 @@ static bool bad_spectre_microcode(struct cpuinfo_x86 *c) return false; } +#define MSR_IA32_TME_ACTIVATE 0x982 + +/* Helpers to access TME_ACTIVATE MSR */ +#define TME_ACTIVATE_LOCKED(x) (x & 0x1) +#define TME_ACTIVATE_ENABLED(x) (x & 0x2) + +#define TME_ACTIVATE_POLICY(x) ((x >> 4) & 0xf) /* Bits 7:4 */ +#define TME_ACTIVATE_POLICY_AES_XTS_128 0 + +#define TME_ACTIVATE_KEYID_BITS(x) ((x >> 32) & 0xf) /* Bits 35:32 */ + +#define TME_ACTIVATE_CRYPTO_ALGS(x) ((x >> 48) & 0xffff) /* Bits 63:48 */ +#define TME_ACTIVATE_CRYPTO_AES_XTS_128 1 + +/* Values for mktme_status (SW only construct) */ +#define MKTME_ENABLED 0 +#define MKTME_DISABLED 1 +#define MKTME_UNINITIALIZED 2 +static int mktme_status = MKTME_UNINITIALIZED; + +static void detect_tme_early(struct cpuinfo_x86 *c) +{ + u64 tme_activate, tme_policy, tme_crypto_algs; + int keyid_bits = 0, nr_keyids = 0; + static u64 tme_activate_cpu0 = 0; + + rdmsrl(MSR_IA32_TME_ACTIVATE, tme_activate); + + if (mktme_status != MKTME_UNINITIALIZED) { + if (tme_activate != tme_activate_cpu0) { + /* Broken BIOS? */ + pr_err_once("x86/tme: configuration is inconsistent between CPUs\n"); + pr_err_once("x86/tme: MKTME is not usable\n"); + mktme_status = MKTME_DISABLED; + + /* Proceed. We may need to exclude bits from x86_phys_bits. */ + } + } else { + tme_activate_cpu0 = tme_activate; + } + + if (!TME_ACTIVATE_LOCKED(tme_activate) || !TME_ACTIVATE_ENABLED(tme_activate)) { + pr_info_once("x86/tme: not enabled by BIOS\n"); + mktme_status = MKTME_DISABLED; + return; + } + + if (mktme_status != MKTME_UNINITIALIZED) + goto detect_keyid_bits; + + pr_info("x86/tme: enabled by BIOS\n"); + + tme_policy = TME_ACTIVATE_POLICY(tme_activate); + if (tme_policy != TME_ACTIVATE_POLICY_AES_XTS_128) + pr_warn("x86/tme: Unknown policy is active: %#llx\n", tme_policy); + + tme_crypto_algs = TME_ACTIVATE_CRYPTO_ALGS(tme_activate); + if (!(tme_crypto_algs & TME_ACTIVATE_CRYPTO_AES_XTS_128)) { + pr_err("x86/mktme: No known encryption algorithm is supported: %#llx\n", + tme_crypto_algs); + mktme_status = MKTME_DISABLED; + } +detect_keyid_bits: + keyid_bits = TME_ACTIVATE_KEYID_BITS(tme_activate); + nr_keyids = (1UL << keyid_bits) - 1; + if (nr_keyids) { + pr_info_once("x86/mktme: enabled by BIOS\n"); + pr_info_once("x86/mktme: %d KeyIDs available\n", nr_keyids); + } else { + pr_info_once("x86/mktme: disabled by BIOS\n"); + } + + if (mktme_status == MKTME_UNINITIALIZED) { + /* MKTME is usable */ + mktme_status = MKTME_ENABLED; + } + + /* + * KeyID bits effectively lower the number of physical address + * bits. Update cpuinfo_x86::x86_phys_bits accordingly. + */ + c->x86_phys_bits -= keyid_bits; +} + static void early_init_intel(struct cpuinfo_x86 *c) { u64 misc_enable; @@ -317,11 +401,11 @@ static void early_init_intel(struct cpuinfo_x86 *c) check_memory_type_self_snoop_errata(c); /* - * Get the number of SMT siblings early from the extended topology - * leaf, if available. Otherwise try the legacy SMT detection. + * Adjust the number of physical bits early because it affects the + * valid bits of the MTRR mask registers. */ - if (detect_extended_topology_early(c) < 0) - detect_ht_early(c); + if (cpu_has(c, X86_FEATURE_TME)) + detect_tme_early(c); } static void bsp_init_intel(struct cpuinfo_x86 *c) @@ -482,90 +566,6 @@ static void srat_detect_node(struct cpuinfo_x86 *c) #endif } -#define MSR_IA32_TME_ACTIVATE 0x982 - -/* Helpers to access TME_ACTIVATE MSR */ -#define TME_ACTIVATE_LOCKED(x) (x & 0x1) -#define TME_ACTIVATE_ENABLED(x) (x & 0x2) - -#define TME_ACTIVATE_POLICY(x) ((x >> 4) & 0xf) /* Bits 7:4 */ -#define TME_ACTIVATE_POLICY_AES_XTS_128 0 - -#define TME_ACTIVATE_KEYID_BITS(x) ((x >> 32) & 0xf) /* Bits 35:32 */ - -#define TME_ACTIVATE_CRYPTO_ALGS(x) ((x >> 48) & 0xffff) /* Bits 63:48 */ -#define TME_ACTIVATE_CRYPTO_AES_XTS_128 1 - -/* Values for mktme_status (SW only construct) */ -#define MKTME_ENABLED 0 -#define MKTME_DISABLED 1 -#define MKTME_UNINITIALIZED 2 -static int mktme_status = MKTME_UNINITIALIZED; - -static void detect_tme(struct cpuinfo_x86 *c) -{ - u64 tme_activate, tme_policy, tme_crypto_algs; - int keyid_bits = 0, nr_keyids = 0; - static u64 tme_activate_cpu0 = 0; - - rdmsrl(MSR_IA32_TME_ACTIVATE, tme_activate); - - if (mktme_status != MKTME_UNINITIALIZED) { - if (tme_activate != tme_activate_cpu0) { - /* Broken BIOS? */ - pr_err_once("x86/tme: configuration is inconsistent between CPUs\n"); - pr_err_once("x86/tme: MKTME is not usable\n"); - mktme_status = MKTME_DISABLED; - - /* Proceed. We may need to exclude bits from x86_phys_bits. */ - } - } else { - tme_activate_cpu0 = tme_activate; - } - - if (!TME_ACTIVATE_LOCKED(tme_activate) || !TME_ACTIVATE_ENABLED(tme_activate)) { - pr_info_once("x86/tme: not enabled by BIOS\n"); - mktme_status = MKTME_DISABLED; - return; - } - - if (mktme_status != MKTME_UNINITIALIZED) - goto detect_keyid_bits; - - pr_info("x86/tme: enabled by BIOS\n"); - - tme_policy = TME_ACTIVATE_POLICY(tme_activate); - if (tme_policy != TME_ACTIVATE_POLICY_AES_XTS_128) - pr_warn("x86/tme: Unknown policy is active: %#llx\n", tme_policy); - - tme_crypto_algs = TME_ACTIVATE_CRYPTO_ALGS(tme_activate); - if (!(tme_crypto_algs & TME_ACTIVATE_CRYPTO_AES_XTS_128)) { - pr_err("x86/mktme: No known encryption algorithm is supported: %#llx\n", - tme_crypto_algs); - mktme_status = MKTME_DISABLED; - } -detect_keyid_bits: - keyid_bits = TME_ACTIVATE_KEYID_BITS(tme_activate); - nr_keyids = (1UL << keyid_bits) - 1; - if (nr_keyids) { - pr_info_once("x86/mktme: enabled by BIOS\n"); - pr_info_once("x86/mktme: %d KeyIDs available\n", nr_keyids); - } else { - pr_info_once("x86/mktme: disabled by BIOS\n"); - } - - if (mktme_status == MKTME_UNINITIALIZED) { - /* MKTME is usable */ - mktme_status = MKTME_ENABLED; - } - - /* - * KeyID bits effectively lower the number of physical address - * bits. Update cpuinfo_x86::x86_phys_bits accordingly. - */ - c->x86_phys_bits -= keyid_bits; -} - static void init_cpuid_fault(struct cpuinfo_x86 *c) { u64 msr; @@ -603,24 +603,6 @@ static void init_intel(struct cpuinfo_x86 *c) intel_workarounds(c); - /* - * Detect the extended topology information if available. This - * will reinitialise the initial_apicid which will be used - * in init_intel_cacheinfo() - */ - detect_extended_topology(c); - - if (!cpu_has(c, X86_FEATURE_XTOPOLOGY)) { - /* - * let's use the legacy cpuid vector 0x1 and 0x4 for topology - * detection. - */ - detect_num_cpu_cores(c); -#ifdef CONFIG_X86_32 - detect_ht(c); -#endif - } - init_intel_cacheinfo(c); if (c->cpuid_level > 9) { @@ -702,9 +684,6 @@ static void init_intel(struct cpuinfo_x86 *c) init_ia32_feat_ctl(c); - if (cpu_has(c, X86_FEATURE_TME)) - detect_tme(c); - init_intel_misc_features(c); split_lock_init(); diff --git a/arch/x86/kernel/cpu/mce/amd.c b/arch/x86/kernel/cpu/mce/amd.c index 2b46eb0fdf3a..9a0133ef7e20 100644 --- a/arch/x86/kernel/cpu/mce/amd.c +++ b/arch/x86/kernel/cpu/mce/amd.c @@ -1231,7 +1231,7 @@ static int threshold_create_bank(struct threshold_bank **bp, unsigned int cpu, return -ENODEV; if (is_shared_bank(bank)) { - nb = node_to_amd_nb(topology_die_id(cpu)); + nb = node_to_amd_nb(topology_amd_node_id(cpu)); /* threshold descriptor already initialized on this node? */ if (nb && nb->bank4) { @@ -1335,7 +1335,7 @@ static void threshold_remove_bank(struct threshold_bank *bank) * The last CPU on this node using the shared bank is going * away, remove that bank now. */ - nb = node_to_amd_nb(topology_die_id(smp_processor_id())); + nb = node_to_amd_nb(topology_amd_node_id(smp_processor_id())); nb->bank4 = NULL; } diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c index bc39252bc54f..b5cc557cfc37 100644 --- a/arch/x86/kernel/cpu/mce/core.c +++ b/arch/x86/kernel/cpu/mce/core.c @@ -46,6 +46,7 @@ #include <linux/hardirq.h> #include <linux/kexec.h> +#include <asm/fred.h> #include <asm/intel-family.h> #include <asm/processor.h> #include <asm/traps.h> @@ -2166,6 +2167,31 @@ DEFINE_IDTENTRY_MCE_USER(exc_machine_check) exc_machine_check_user(regs); local_db_restore(dr7); } + +#ifdef CONFIG_X86_FRED +/* + * When occurred on different ring level, i.e., from user or kernel + * context, #MCE needs to be handled on different stack: User #MCE + * on current task stack, while kernel #MCE on a dedicated stack. + * + * This is exactly how FRED event delivery invokes an exception + * handler: ring 3 event on level 0 stack, i.e., current task stack; + * ring 0 event on the #MCE dedicated stack specified in the + * IA32_FRED_STKLVLS MSR. So unlike IDT, the FRED machine check entry + * stub doesn't do stack switch. + */ +DEFINE_FREDENTRY_MCE(exc_machine_check) +{ + unsigned long dr7; + + dr7 = local_db_save(); + if (user_mode(regs)) + exc_machine_check_user(regs); + else + exc_machine_check_kernel(regs); + local_db_restore(dr7); +} +#endif #else /* 32bit unified entry point */ DEFINE_IDTENTRY_RAW(exc_machine_check) @@ -2431,7 +2457,7 @@ static void mce_enable_ce(void *all) __mcheck_cpu_init_timer(); } -static struct bus_type mce_subsys = { +static const struct bus_type mce_subsys = { .name = "machinecheck", .dev_name = "machinecheck", }; diff --git a/arch/x86/kernel/cpu/mce/inject.c b/arch/x86/kernel/cpu/mce/inject.c index 72f0695c3dc1..94953d749475 100644 --- a/arch/x86/kernel/cpu/mce/inject.c +++ b/arch/x86/kernel/cpu/mce/inject.c @@ -430,11 +430,9 @@ static void trigger_thr_int(void *info) static u32 get_nbc_for_node(int node_id) { - struct cpuinfo_x86 *c = &boot_cpu_data; u32 cores_per_node; - cores_per_node = (c->x86_max_cores * smp_num_siblings) / amd_get_nodes_per_socket(); - + cores_per_node = topology_num_threads_per_package() / topology_amd_nodes_per_pkg(); return cores_per_node * node_id; } @@ -543,8 +541,8 @@ static void do_inject(void) if (boot_cpu_has(X86_FEATURE_AMD_DCM) && b == 4 && boot_cpu_data.x86 < 0x17) { - toggle_nb_mca_mst_cpu(topology_die_id(cpu)); - cpu = get_nbc_for_node(topology_die_id(cpu)); + toggle_nb_mca_mst_cpu(topology_amd_node_id(cpu)); + cpu = get_nbc_for_node(topology_amd_node_id(cpu)); } cpus_read_lock(); diff --git a/arch/x86/kernel/cpu/microcode/intel.c b/arch/x86/kernel/cpu/microcode/intel.c index 857e608af641..5f0414452b67 100644 --- a/arch/x86/kernel/cpu/microcode/intel.c +++ b/arch/x86/kernel/cpu/microcode/intel.c @@ -641,7 +641,7 @@ static __init void calc_llc_size_per_core(struct cpuinfo_x86 *c) { u64 llc_size = c->x86_cache_size * 1024ULL; - do_div(llc_size, c->x86_max_cores); + do_div(llc_size, topology_num_cores_per_package()); llc_size_per_core = (unsigned int)llc_size; } diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c index 01fa06dd06b6..45e0e70e238c 100644 --- a/arch/x86/kernel/cpu/mshyperv.c +++ b/arch/x86/kernel/cpu/mshyperv.c @@ -539,19 +539,18 @@ static void __init ms_hyperv_init_platform(void) */ x86_platform.apic_post_init = hyperv_init; hyperv_setup_mmu_ops(); - /* Setup the IDT for hypervisor callback */ - alloc_intr_gate(HYPERVISOR_CALLBACK_VECTOR, asm_sysvec_hyperv_callback); - /* Setup the IDT for reenlightenment notifications */ + /* Install system interrupt handler for hypervisor callback */ + sysvec_install(HYPERVISOR_CALLBACK_VECTOR, sysvec_hyperv_callback); + + /* Install system interrupt handler for reenlightenment notifications */ if (ms_hyperv.features & HV_ACCESS_REENLIGHTENMENT) { - alloc_intr_gate(HYPERV_REENLIGHTENMENT_VECTOR, - asm_sysvec_hyperv_reenlightenment); + sysvec_install(HYPERV_REENLIGHTENMENT_VECTOR, sysvec_hyperv_reenlightenment); } - /* Setup the IDT for stimer0 */ + /* Install system interrupt handler for stimer0 */ if (ms_hyperv.misc_features & HV_STIMER_DIRECT_MODE_AVAILABLE) { - alloc_intr_gate(HYPERV_STIMER0_VECTOR, - asm_sysvec_hyperv_stimer0); + sysvec_install(HYPERV_STIMER0_VECTOR, sysvec_hyperv_stimer0); } # ifdef CONFIG_SMP diff --git a/arch/x86/kernel/cpu/topology.c b/arch/x86/kernel/cpu/topology.c index dc136703566f..3259b1d4fefe 100644 --- a/arch/x86/kernel/cpu/topology.c +++ b/arch/x86/kernel/cpu/topology.c @@ -1,167 +1,510 @@ -// SPDX-License-Identifier: GPL-2.0 +// SPDX-License-Identifier: GPL-2.0-only /* - * Check for extended topology enumeration cpuid leaf 0xb and if it - * exists, use it for populating initial_apicid and cpu topology - * detection. + * CPU/APIC topology + * + * The APIC IDs describe the system topology in multiple domain levels. + * The CPUID topology parser provides the information which part of the + * APIC ID is associated to the individual levels: + * + * [PACKAGE][DIEGRP][DIE][TILE][MODULE][CORE][THREAD] + * + * The root space contains the package (socket) IDs. + * + * Not enumerated levels consume 0 bits space, but conceptually they are + * always represented. If e.g. only CORE and THREAD levels are enumerated + * then the DIE, MODULE and TILE have the same physical ID as the PACKAGE. + * + * If SMT is not supported, then the THREAD domain is still used. It then + * has the same physical ID as the CORE domain and is the only child of + * the core domain. + * + * This allows a unified view on the system independent of the enumerated + * domain levels without requiring any conditionals in the code. */ - +#define pr_fmt(fmt) "CPU topo: " fmt #include <linux/cpu.h> + +#include <xen/xen.h> + #include <asm/apic.h> -#include <asm/memtype.h> -#include <asm/processor.h> +#include <asm/hypervisor.h> +#include <asm/io_apic.h> +#include <asm/mpspec.h> +#include <asm/smp.h> #include "cpu.h" -/* leaf 0xb SMT level */ -#define SMT_LEVEL 0 +/* + * Map cpu index to physical APIC ID + */ +DEFINE_EARLY_PER_CPU_READ_MOSTLY(u32, x86_cpu_to_apicid, BAD_APICID); +DEFINE_EARLY_PER_CPU_READ_MOSTLY(u32, x86_cpu_to_acpiid, CPU_ACPIID_INVALID); +EXPORT_EARLY_PER_CPU_SYMBOL(x86_cpu_to_apicid); +EXPORT_EARLY_PER_CPU_SYMBOL(x86_cpu_to_acpiid); -/* extended topology sub-leaf types */ -#define INVALID_TYPE 0 -#define SMT_TYPE 1 -#define CORE_TYPE 2 -#define DIE_TYPE 5 +/* Bitmap of physically present CPUs. */ +DECLARE_BITMAP(phys_cpu_present_map, MAX_LOCAL_APIC) __read_mostly; -#define LEAFB_SUBTYPE(ecx) (((ecx) >> 8) & 0xff) -#define BITS_SHIFT_NEXT_LEVEL(eax) ((eax) & 0x1f) -#define LEVEL_MAX_SIBLINGS(ebx) ((ebx) & 0xffff) +/* Used for CPU number allocation and parallel CPU bringup */ +u32 cpuid_to_apicid[] __ro_after_init = { [0 ... NR_CPUS - 1] = BAD_APICID, }; + +/* Bitmaps to mark registered APICs at each topology domain */ +static struct { DECLARE_BITMAP(map, MAX_LOCAL_APIC); } apic_maps[TOPO_MAX_DOMAIN] __ro_after_init; + +/* + * Keep track of assigned, disabled and rejected CPUs. Present assigned + * with 1 as CPU #0 is reserved for the boot CPU. + */ +static struct { + unsigned int nr_assigned_cpus; + unsigned int nr_disabled_cpus; + unsigned int nr_rejected_cpus; + u32 boot_cpu_apic_id; + u32 real_bsp_apic_id; +} topo_info __ro_after_init = { + .nr_assigned_cpus = 1, + .boot_cpu_apic_id = BAD_APICID, + .real_bsp_apic_id = BAD_APICID, +}; -unsigned int __max_die_per_package __read_mostly = 1; -EXPORT_SYMBOL(__max_die_per_package); +#define domain_weight(_dom) bitmap_weight(apic_maps[_dom].map, MAX_LOCAL_APIC) + +bool arch_match_cpu_phys_id(int cpu, u64 phys_id) +{ + return phys_id == (u64)cpuid_to_apicid[cpu]; +} #ifdef CONFIG_SMP +static void cpu_mark_primary_thread(unsigned int cpu, unsigned int apicid) +{ + if (!(apicid & (__max_threads_per_core - 1))) + cpumask_set_cpu(cpu, &__cpu_primary_thread_mask); +} +#else +static inline void cpu_mark_primary_thread(unsigned int cpu, unsigned int apicid) { } +#endif + /* - * Check if given CPUID extended topology "leaf" is implemented + * Convert the APIC ID to a domain level ID by masking out the low bits + * below the domain level @dom. */ -static int check_extended_topology_leaf(int leaf) +static inline u32 topo_apicid(u32 apicid, enum x86_topology_domains dom) +{ + if (dom == TOPO_SMT_DOMAIN) + return apicid; + return apicid & (UINT_MAX << x86_topo_system.dom_shifts[dom - 1]); +} + +static int topo_lookup_cpuid(u32 apic_id) { - unsigned int eax, ebx, ecx, edx; + int i; - cpuid_count(leaf, SMT_LEVEL, &eax, &ebx, &ecx, &edx); + /* CPU# to APICID mapping is persistent once it is established */ + for (i = 0; i < topo_info.nr_assigned_cpus; i++) { + if (cpuid_to_apicid[i] == apic_id) + return i; + } + return -ENODEV; +} - if (ebx == 0 || (LEAFB_SUBTYPE(ecx) != SMT_TYPE)) - return -1; +static __init int topo_get_cpunr(u32 apic_id) +{ + int cpu = topo_lookup_cpuid(apic_id); - return 0; + if (cpu >= 0) + return cpu; + + return topo_info.nr_assigned_cpus++; } -/* - * Return best CPUID Extended Topology Leaf supported + +static void topo_set_cpuids(unsigned int cpu, u32 apic_id, u32 acpi_id) +{ +#if defined(CONFIG_SMP) || defined(CONFIG_X86_64) + early_per_cpu(x86_cpu_to_apicid, cpu) = apic_id; + early_per_cpu(x86_cpu_to_acpiid, cpu) = acpi_id; +#endif + set_cpu_possible(cpu, true); + set_cpu_present(cpu, true); +} + +static __init bool check_for_real_bsp(u32 apic_id) +{ + /* + * There is no real good way to detect whether this a kdump() + * kernel, but except on the Voyager SMP monstrosity which is not + * longer supported, the real BSP APIC ID is the first one which is + * enumerated by firmware. That allows to detect whether the boot + * CPU is the real BSP. If it is not, then do not register the APIC + * because sending INIT to the real BSP would reset the whole + * system. + * + * The first APIC ID which is enumerated by firmware is detectable + * because the boot CPU APIC ID is registered before that without + * invoking this code. + */ + if (topo_info.real_bsp_apic_id != BAD_APICID) + return false; + + if (apic_id == topo_info.boot_cpu_apic_id) { + topo_info.real_bsp_apic_id = apic_id; + return false; + } + + pr_warn("Boot CPU APIC ID not the first enumerated APIC ID: %x > %x\n", + topo_info.boot_cpu_apic_id, apic_id); + pr_warn("Crash kernel detected. Disabling real BSP to prevent machine INIT\n"); + + topo_info.real_bsp_apic_id = apic_id; + return true; +} + +static unsigned int topo_unit_count(u32 lvlid, enum x86_topology_domains at_level, + unsigned long *map) +{ + unsigned int id, end, cnt = 0; + + /* Calculate the exclusive end */ + end = lvlid + (1U << x86_topo_system.dom_shifts[at_level]); + + /* Unfortunately there is no bitmap_weight_range() */ + for (id = find_next_bit(map, end, lvlid); id < end; id = find_next_bit(map, end, ++id)) + cnt++; + return cnt; +} + +static __init void topo_register_apic(u32 apic_id, u32 acpi_id, bool present) +{ + int cpu, dom; + + if (present) { + set_bit(apic_id, phys_cpu_present_map); + + /* + * Double registration is valid in case of the boot CPU + * APIC because that is registered before the enumeration + * of the APICs via firmware parsers or VM guest + * mechanisms. + */ + if (apic_id == topo_info.boot_cpu_apic_id) + cpu = 0; + else + cpu = topo_get_cpunr(apic_id); + + cpuid_to_apicid[cpu] = apic_id; + topo_set_cpuids(cpu, apic_id, acpi_id); + } else { + u32 pkgid = topo_apicid(apic_id, TOPO_PKG_DOMAIN); + + /* + * Check for present APICs in the same package when running + * on bare metal. Allow the bogosity in a guest. + */ + if (hypervisor_is_type(X86_HYPER_NATIVE) && + topo_unit_count(pkgid, TOPO_PKG_DOMAIN, phys_cpu_present_map)) { + pr_info_once("Ignoring hot-pluggable APIC ID %x in present package.\n", + apic_id); + topo_info.nr_rejected_cpus++; + return; + } + + topo_info.nr_disabled_cpus++; + } + + /* Register present and possible CPUs in the domain maps */ + for (dom = TOPO_SMT_DOMAIN; dom < TOPO_MAX_DOMAIN; dom++) + set_bit(topo_apicid(apic_id, dom), apic_maps[dom].map); +} + +/** + * topology_register_apic - Register an APIC in early topology maps + * @apic_id: The APIC ID to set up + * @acpi_id: The ACPI ID associated to the APIC + * @present: True if the corresponding CPU is present */ -static int detect_extended_topology_leaf(struct cpuinfo_x86 *c) +void __init topology_register_apic(u32 apic_id, u32 acpi_id, bool present) { - if (c->cpuid_level >= 0x1f) { - if (check_extended_topology_leaf(0x1f) == 0) - return 0x1f; + if (apic_id >= MAX_LOCAL_APIC) { + pr_err_once("APIC ID %x exceeds kernel limit of: %x\n", apic_id, MAX_LOCAL_APIC - 1); + topo_info.nr_rejected_cpus++; + return; + } + + if (check_for_real_bsp(apic_id)) { + topo_info.nr_rejected_cpus++; + return; } - if (c->cpuid_level >= 0xb) { - if (check_extended_topology_leaf(0xb) == 0) - return 0xb; + /* CPU numbers exhausted? */ + if (apic_id != topo_info.boot_cpu_apic_id && topo_info.nr_assigned_cpus >= nr_cpu_ids) { + pr_warn_once("CPU limit of %d reached. Ignoring further CPUs\n", nr_cpu_ids); + topo_info.nr_rejected_cpus++; + return; } - return -1; + topo_register_apic(apic_id, acpi_id, present); +} + +/** + * topology_register_boot_apic - Register the boot CPU APIC + * @apic_id: The APIC ID to set up + * + * Separate so CPU #0 can be assigned + */ +void __init topology_register_boot_apic(u32 apic_id) +{ + WARN_ON_ONCE(topo_info.boot_cpu_apic_id != BAD_APICID); + + topo_info.boot_cpu_apic_id = apic_id; + topo_register_apic(apic_id, CPU_ACPIID_INVALID, true); +} + +/** + * topology_get_logical_id - Retrieve the logical ID at a given topology domain level + * @apicid: The APIC ID for which to lookup the logical ID + * @at_level: The topology domain level to use + * + * @apicid must be a full APIC ID, not the normalized variant. It's valid to have + * all bits below the domain level specified by @at_level to be clear. So both + * real APIC IDs and backshifted normalized APIC IDs work correctly. + * + * Returns: + * - >= 0: The requested logical ID + * - -ERANGE: @apicid is out of range + * - -ENODEV: @apicid is not registered + */ +int topology_get_logical_id(u32 apicid, enum x86_topology_domains at_level) +{ + /* Remove the bits below @at_level to get the proper level ID of @apicid */ + unsigned int lvlid = topo_apicid(apicid, at_level); + + if (lvlid >= MAX_LOCAL_APIC) + return -ERANGE; + if (!test_bit(lvlid, apic_maps[at_level].map)) + return -ENODEV; + /* Get the number of set bits before @lvlid. */ + return bitmap_weight(apic_maps[at_level].map, lvlid); +} +EXPORT_SYMBOL_GPL(topology_get_logical_id); + +/** + * topology_unit_count - Retrieve the count of specified units at a given topology domain level + * @apicid: The APIC ID which specifies the search range + * @which_units: The domain level specifying the units to count + * @at_level: The domain level at which @which_units have to be counted + * + * This returns the number of possible units according to the enumerated + * information. + * + * E.g. topology_count_units(apicid, TOPO_CORE_DOMAIN, TOPO_PKG_DOMAIN) + * counts the number of possible cores in the package to which @apicid + * belongs. + * + * @at_level must obviously be greater than @which_level to produce useful + * results. If @at_level is equal to @which_units the result is + * unsurprisingly 1. If @at_level is less than @which_units the results + * is by definition undefined and the function returns 0. + */ +unsigned int topology_unit_count(u32 apicid, enum x86_topology_domains which_units, + enum x86_topology_domains at_level) +{ + /* Remove the bits below @at_level to get the proper level ID of @apicid */ + unsigned int lvlid = topo_apicid(apicid, at_level); + + if (lvlid >= MAX_LOCAL_APIC) + return 0; + if (!test_bit(lvlid, apic_maps[at_level].map)) + return 0; + if (which_units > at_level) + return 0; + if (which_units == at_level) + return 1; + return topo_unit_count(lvlid, at_level, apic_maps[which_units].map); +} + +#ifdef CONFIG_ACPI_HOTPLUG_CPU +/** + * topology_hotplug_apic - Handle a physical hotplugged APIC after boot + * @apic_id: The APIC ID to set up + * @acpi_id: The ACPI ID associated to the APIC + */ +int topology_hotplug_apic(u32 apic_id, u32 acpi_id) +{ + int cpu; + + if (apic_id >= MAX_LOCAL_APIC) + return -EINVAL; + + /* Reject if the APIC ID was not registered during enumeration. */ + if (!test_bit(apic_id, apic_maps[TOPO_SMT_DOMAIN].map)) + return -ENODEV; + + cpu = topo_lookup_cpuid(apic_id); + if (cpu < 0) + return -ENOSPC; + + set_bit(apic_id, phys_cpu_present_map); + topo_set_cpuids(cpu, apic_id, acpi_id); + cpu_mark_primary_thread(cpu, apic_id); + return cpu; +} + +/** + * topology_hotunplug_apic - Remove a physical hotplugged APIC after boot + * @cpu: The CPU number for which the APIC ID is removed + */ +void topology_hotunplug_apic(unsigned int cpu) +{ + u32 apic_id = cpuid_to_apicid[cpu]; + + if (apic_id == BAD_APICID) + return; + + per_cpu(x86_cpu_to_apicid, cpu) = BAD_APICID; + clear_bit(apic_id, phys_cpu_present_map); + set_cpu_present(cpu, false); } #endif -int detect_extended_topology_early(struct cpuinfo_x86 *c) +#ifdef CONFIG_X86_LOCAL_APIC +static unsigned int max_possible_cpus __initdata = NR_CPUS; + +/** + * topology_apply_cmdline_limits_early - Apply topology command line limits early + * + * Ensure that command line limits are in effect before firmware parsing + * takes place. + */ +void __init topology_apply_cmdline_limits_early(void) { -#ifdef CONFIG_SMP - unsigned int eax, ebx, ecx, edx; - int leaf; + unsigned int possible = nr_cpu_ids; - leaf = detect_extended_topology_leaf(c); - if (leaf < 0) - return -1; + /* 'maxcpus=0' 'nosmp' 'nolapic' 'disableapic' 'noapic' */ + if (!setup_max_cpus || ioapic_is_disabled || apic_is_disabled) + possible = 1; - set_cpu_cap(c, X86_FEATURE_XTOPOLOGY); + /* 'possible_cpus=N' */ + possible = min_t(unsigned int, max_possible_cpus, possible); + + if (possible < nr_cpu_ids) { + pr_info("Limiting to %u possible CPUs\n", possible); + set_nr_cpu_ids(possible); + } +} - cpuid_count(leaf, SMT_LEVEL, &eax, &ebx, &ecx, &edx); +static __init bool restrict_to_up(void) +{ + if (!smp_found_config || ioapic_is_disabled) + return true; /* - * initial apic id, which also represents 32-bit extended x2apic id. + * XEN PV is special as it does not advertise the local APIC + * properly, but provides a fake topology for it so that the + * infrastructure works. So don't apply the restrictions vs. APIC + * here. */ - c->topo.initial_apicid = edx; - smp_num_siblings = max_t(int, smp_num_siblings, LEVEL_MAX_SIBLINGS(ebx)); -#endif - return 0; + if (xen_pv_domain()) + return false; + + return apic_is_disabled; } -/* - * Check for extended topology enumeration cpuid leaf, and if it - * exists, use it for populating initial_apicid and cpu topology - * detection. - */ -int detect_extended_topology(struct cpuinfo_x86 *c) +void __init topology_init_possible_cpus(void) { -#ifdef CONFIG_SMP - unsigned int eax, ebx, ecx, edx, sub_index; - unsigned int ht_mask_width, core_plus_mask_width, die_plus_mask_width; - unsigned int core_select_mask, core_level_siblings; - unsigned int die_select_mask, die_level_siblings; - unsigned int pkg_mask_width; - bool die_level_present = false; - int leaf; - - leaf = detect_extended_topology_leaf(c); - if (leaf < 0) - return -1; + unsigned int assigned = topo_info.nr_assigned_cpus; + unsigned int disabled = topo_info.nr_disabled_cpus; + unsigned int cnta, cntb, cpu, allowed = 1; + unsigned int total = assigned + disabled; + u32 apicid, firstid; + + if (!restrict_to_up()) { + if (WARN_ON_ONCE(assigned > nr_cpu_ids)) { + disabled += assigned - nr_cpu_ids; + assigned = nr_cpu_ids; + } + allowed = min_t(unsigned int, total, nr_cpu_ids); + } + + if (total > allowed) + pr_warn("%u possible CPUs exceed the limit of %u\n", total, allowed); + + assigned = min_t(unsigned int, allowed, assigned); + disabled = allowed - assigned; + topo_info.nr_assigned_cpus = assigned; + topo_info.nr_disabled_cpus = disabled; + + total_cpus = allowed; + set_nr_cpu_ids(allowed); + + cnta = domain_weight(TOPO_PKG_DOMAIN); + cntb = domain_weight(TOPO_DIE_DOMAIN); + __max_logical_packages = cnta; + __max_dies_per_package = 1U << (get_count_order(cntb) - get_count_order(cnta)); + + pr_info("Max. logical packages: %3u\n", cnta); + pr_info("Max. logical dies: %3u\n", cntb); + pr_info("Max. dies per package: %3u\n", __max_dies_per_package); + + cnta = domain_weight(TOPO_CORE_DOMAIN); + cntb = domain_weight(TOPO_SMT_DOMAIN); /* - * Populate HT related information from sub-leaf level 0. + * Can't use order delta here as order(cnta) can be equal + * order(cntb) even if cnta != cntb. */ - cpuid_count(leaf, SMT_LEVEL, &eax, &ebx, &ecx, &edx); - c->topo.initial_apicid = edx; - core_level_siblings = LEVEL_MAX_SIBLINGS(ebx); - smp_num_siblings = max_t(int, smp_num_siblings, LEVEL_MAX_SIBLINGS(ebx)); - core_plus_mask_width = ht_mask_width = BITS_SHIFT_NEXT_LEVEL(eax); - die_level_siblings = LEVEL_MAX_SIBLINGS(ebx); - pkg_mask_width = die_plus_mask_width = BITS_SHIFT_NEXT_LEVEL(eax); - - sub_index = 1; - while (true) { - cpuid_count(leaf, sub_index, &eax, &ebx, &ecx, &edx); + __max_threads_per_core = DIV_ROUND_UP(cntb, cnta); + pr_info("Max. threads per core: %3u\n", __max_threads_per_core); - /* - * Check for the Core type in the implemented sub leaves. - */ - if (LEAFB_SUBTYPE(ecx) == CORE_TYPE) { - core_level_siblings = LEVEL_MAX_SIBLINGS(ebx); - core_plus_mask_width = BITS_SHIFT_NEXT_LEVEL(eax); - die_level_siblings = core_level_siblings; - die_plus_mask_width = BITS_SHIFT_NEXT_LEVEL(eax); - } - if (LEAFB_SUBTYPE(ecx) == DIE_TYPE) { - die_level_present = true; - die_level_siblings = LEVEL_MAX_SIBLINGS(ebx); - die_plus_mask_width = BITS_SHIFT_NEXT_LEVEL(eax); - } + firstid = find_first_bit(apic_maps[TOPO_SMT_DOMAIN].map, MAX_LOCAL_APIC); + __num_cores_per_package = topology_unit_count(firstid, TOPO_CORE_DOMAIN, TOPO_PKG_DOMAIN); + pr_info("Num. cores per package: %3u\n", __num_cores_per_package); + __num_threads_per_package = topology_unit_count(firstid, TOPO_SMT_DOMAIN, TOPO_PKG_DOMAIN); + pr_info("Num. threads per package: %3u\n", __num_threads_per_package); - if (LEAFB_SUBTYPE(ecx) != INVALID_TYPE) - pkg_mask_width = BITS_SHIFT_NEXT_LEVEL(eax); - else - break; + pr_info("Allowing %u present CPUs plus %u hotplug CPUs\n", assigned, disabled); + if (topo_info.nr_rejected_cpus) + pr_info("Rejected CPUs %u\n", topo_info.nr_rejected_cpus); - sub_index++; + init_cpu_present(cpumask_of(0)); + init_cpu_possible(cpumask_of(0)); + + /* Assign CPU numbers to non-present CPUs */ + for (apicid = 0; disabled; disabled--, apicid++) { + apicid = find_next_andnot_bit(apic_maps[TOPO_SMT_DOMAIN].map, phys_cpu_present_map, + MAX_LOCAL_APIC, apicid); + if (apicid >= MAX_LOCAL_APIC) + break; + cpuid_to_apicid[topo_info.nr_assigned_cpus++] = apicid; } - core_select_mask = (~(-1 << pkg_mask_width)) >> ht_mask_width; - die_select_mask = (~(-1 << die_plus_mask_width)) >> - core_plus_mask_width; + for (cpu = 0; cpu < allowed; cpu++) { + apicid = cpuid_to_apicid[cpu]; - c->topo.core_id = apic->phys_pkg_id(c->topo.initial_apicid, - ht_mask_width) & core_select_mask; + set_cpu_possible(cpu, true); - if (die_level_present) { - c->topo.die_id = apic->phys_pkg_id(c->topo.initial_apicid, - core_plus_mask_width) & die_select_mask; + if (apicid == BAD_APICID) + continue; + + cpu_mark_primary_thread(cpu, apicid); + set_cpu_present(cpu, test_bit(apicid, phys_cpu_present_map)); } +} - c->topo.pkg_id = apic->phys_pkg_id(c->topo.initial_apicid, pkg_mask_width); - /* - * Reinit the apicid, now that we have extended initial_apicid. - */ - c->topo.apicid = apic->phys_pkg_id(c->topo.initial_apicid, 0); +/* + * Late SMP disable after sizing CPU masks when APIC/IOAPIC setup failed. + */ +void __init topology_reset_possible_cpus_up(void) +{ + init_cpu_present(cpumask_of(0)); + init_cpu_possible(cpumask_of(0)); - c->x86_max_cores = (core_level_siblings / smp_num_siblings); - __max_die_per_package = (die_level_siblings / core_level_siblings); -#endif + bitmap_zero(phys_cpu_present_map, MAX_LOCAL_APIC); + if (topo_info.boot_cpu_apic_id != BAD_APICID) + set_bit(topo_info.boot_cpu_apic_id, phys_cpu_present_map); +} + +static int __init setup_possible_cpus(char *str) +{ + get_option(&str, &max_possible_cpus); return 0; } +early_param("possible_cpus", setup_possible_cpus); +#endif diff --git a/arch/x86/kernel/cpu/topology.h b/arch/x86/kernel/cpu/topology.h new file mode 100644 index 000000000000..37326297f80c --- /dev/null +++ b/arch/x86/kernel/cpu/topology.h @@ -0,0 +1,67 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef ARCH_X86_TOPOLOGY_H +#define ARCH_X86_TOPOLOGY_H + +struct topo_scan { + struct cpuinfo_x86 *c; + unsigned int dom_shifts[TOPO_MAX_DOMAIN]; + unsigned int dom_ncpus[TOPO_MAX_DOMAIN]; + + /* Legacy CPUID[1]:EBX[23:16] number of logical processors */ + unsigned int ebx1_nproc_shift; + + /* AMD specific node ID which cannot be mapped into APIC space. */ + u16 amd_nodes_per_pkg; + u16 amd_node_id; +}; + +void cpu_init_topology(struct cpuinfo_x86 *c); +void cpu_parse_topology(struct cpuinfo_x86 *c); +void topology_set_dom(struct topo_scan *tscan, enum x86_topology_domains dom, + unsigned int shift, unsigned int ncpus); +bool cpu_parse_topology_ext(struct topo_scan *tscan); +void cpu_parse_topology_amd(struct topo_scan *tscan); +void cpu_topology_fixup_amd(struct topo_scan *tscan); + +static inline u32 topo_shift_apicid(u32 apicid, enum x86_topology_domains dom) +{ + if (dom == TOPO_SMT_DOMAIN) + return apicid; + return apicid >> x86_topo_system.dom_shifts[dom - 1]; +} + +static inline u32 topo_relative_domain_id(u32 apicid, enum x86_topology_domains dom) +{ + if (dom != TOPO_SMT_DOMAIN) + apicid >>= x86_topo_system.dom_shifts[dom - 1]; + return apicid & (x86_topo_system.dom_size[dom] - 1); +} + +static inline u32 topo_domain_mask(enum x86_topology_domains dom) +{ + return (1U << x86_topo_system.dom_shifts[dom]) - 1; +} + +/* + * Update a domain level after the fact without propagating. Used to fixup + * broken CPUID enumerations. + */ +static inline void topology_update_dom(struct topo_scan *tscan, enum x86_topology_domains dom, + unsigned int shift, unsigned int ncpus) +{ + tscan->dom_shifts[dom] = shift; + tscan->dom_ncpus[dom] = ncpus; +} + +#ifdef CONFIG_X86_LOCAL_APIC +unsigned int topology_unit_count(u32 apicid, enum x86_topology_domains which_units, + enum x86_topology_domains at_level); +#else +static inline unsigned int topology_unit_count(u32 apicid, enum x86_topology_domains which_units, + enum x86_topology_domains at_level) +{ + return 1; +} +#endif + +#endif /* ARCH_X86_TOPOLOGY_H */ diff --git a/arch/x86/kernel/cpu/topology_amd.c b/arch/x86/kernel/cpu/topology_amd.c new file mode 100644 index 000000000000..1a8b3ad493af --- /dev/null +++ b/arch/x86/kernel/cpu/topology_amd.c @@ -0,0 +1,183 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <linux/cpu.h> + +#include <asm/apic.h> +#include <asm/memtype.h> +#include <asm/processor.h> + +#include "cpu.h" + +static bool parse_8000_0008(struct topo_scan *tscan) +{ + struct { + // ecx + u32 cpu_nthreads : 8, // Number of physical threads - 1 + : 4, // Reserved + apicid_coreid_len : 4, // Number of thread core ID bits (shift) in APIC ID + perf_tsc_len : 2, // Performance time-stamp counter size + : 14; // Reserved + } ecx; + unsigned int sft; + + if (tscan->c->extended_cpuid_level < 0x80000008) + return false; + + cpuid_leaf_reg(0x80000008, CPUID_ECX, &ecx); + + /* If the thread bits are 0, then get the shift value from ecx.cpu_nthreads */ + sft = ecx.apicid_coreid_len; + if (!sft) + sft = get_count_order(ecx.cpu_nthreads + 1); + + topology_set_dom(tscan, TOPO_SMT_DOMAIN, sft, ecx.cpu_nthreads + 1); + return true; +} + +static void store_node(struct topo_scan *tscan, unsigned int nr_nodes, u16 node_id) +{ + /* + * Starting with Fam 17h the DIE domain could probably be used to + * retrieve the node info on AMD/HYGON. Analysis of CPUID dumps + * suggests it's the topmost bit(s) of the CPU cores area, but + * that's guess work and neither enumerated nor documented. + * + * Up to Fam 16h this does not work at all and the legacy node ID + * has to be used. + */ + tscan->amd_nodes_per_pkg = nr_nodes; + tscan->amd_node_id = node_id; +} + +static bool parse_8000_001e(struct topo_scan *tscan, bool has_0xb) +{ + struct { + // eax + u32 ext_apic_id : 32; // Extended APIC ID + // ebx + u32 core_id : 8, // Unique per-socket logical core unit ID + core_nthreads : 8, // #Threads per core (zero-based) + : 16; // Reserved + // ecx + u32 node_id : 8, // Node (die) ID of invoking logical CPU + nnodes_per_socket : 3, // #nodes in invoking logical CPU's package/socket + : 21; // Reserved + // edx + u32 : 32; // Reserved + } leaf; + + if (!boot_cpu_has(X86_FEATURE_TOPOEXT)) + return false; + + cpuid_leaf(0x8000001e, &leaf); + + tscan->c->topo.initial_apicid = leaf.ext_apic_id; + + /* + * If leaf 0xb is available, then SMT shift is set already. If not + * take it from ecx.threads_per_core and use topo_update_dom() - + * topology_set_dom() would propagate and overwrite the already + * propagated CORE level. + */ + if (!has_0xb) { + unsigned int nthreads = leaf.core_nthreads + 1; + + topology_update_dom(tscan, TOPO_SMT_DOMAIN, get_count_order(nthreads), nthreads); + } + + store_node(tscan, leaf.nnodes_per_socket + 1, leaf.node_id); + + if (tscan->c->x86_vendor == X86_VENDOR_AMD) { + if (tscan->c->x86 == 0x15) + tscan->c->topo.cu_id = leaf.core_id; + + cacheinfo_amd_init_llc_id(tscan->c, leaf.node_id); + } else { + /* + * Package ID is ApicId[6..] on certain Hygon CPUs. See + * commit e0ceeae708ce for explanation. The topology info + * is screwed up: The package shift is always 6 and the + * node ID is bit [4:5]. + */ + if (!boot_cpu_has(X86_FEATURE_HYPERVISOR) && tscan->c->x86_model <= 0x3) { + topology_set_dom(tscan, TOPO_CORE_DOMAIN, 6, + tscan->dom_ncpus[TOPO_CORE_DOMAIN]); + } + cacheinfo_hygon_init_llc_id(tscan->c); + } + return true; +} + +static bool parse_fam10h_node_id(struct topo_scan *tscan) +{ + struct { + union { + u64 node_id : 3, + nodes_per_pkg : 3, + unused : 58; + u64 msr; + }; + } nid; + + if (!boot_cpu_has(X86_FEATURE_NODEID_MSR)) + return false; + + rdmsrl(MSR_FAM10H_NODE_ID, nid.msr); + store_node(tscan, nid.nodes_per_pkg + 1, nid.node_id); + tscan->c->topo.llc_id = nid.node_id; + return true; +} + +static void legacy_set_llc(struct topo_scan *tscan) +{ + unsigned int apicid = tscan->c->topo.initial_apicid; + + /* parse_8000_0008() set everything up except llc_id */ + tscan->c->topo.llc_id = apicid >> tscan->dom_shifts[TOPO_CORE_DOMAIN]; +} + +static void parse_topology_amd(struct topo_scan *tscan) +{ + bool has_0xb = false; + + /* + * If the extended topology leaf 0x8000_001e is available + * try to get SMT and CORE shift from leaf 0xb first, then + * try to get the CORE shift from leaf 0x8000_0008. + */ + if (cpu_feature_enabled(X86_FEATURE_TOPOEXT)) + has_0xb = cpu_parse_topology_ext(tscan); + + if (!has_0xb && !parse_8000_0008(tscan)) + return; + + /* Prefer leaf 0x8000001e if available */ + if (parse_8000_001e(tscan, has_0xb)) + return; + + /* Try the NODEID MSR */ + if (parse_fam10h_node_id(tscan)) + return; + + legacy_set_llc(tscan); +} + +void cpu_parse_topology_amd(struct topo_scan *tscan) +{ + tscan->amd_nodes_per_pkg = 1; + parse_topology_amd(tscan); + + if (tscan->amd_nodes_per_pkg > 1) + set_cpu_cap(tscan->c, X86_FEATURE_AMD_DCM); +} + +void cpu_topology_fixup_amd(struct topo_scan *tscan) +{ + struct cpuinfo_x86 *c = tscan->c; + + /* + * Adjust the core_id relative to the node when there is more than + * one node. + */ + if (tscan->c->x86 < 0x17 && tscan->amd_nodes_per_pkg > 1) + c->topo.core_id %= tscan->dom_ncpus[TOPO_CORE_DOMAIN] / tscan->amd_nodes_per_pkg; +} diff --git a/arch/x86/kernel/cpu/topology_common.c b/arch/x86/kernel/cpu/topology_common.c new file mode 100644 index 000000000000..a50ae8d63d1c --- /dev/null +++ b/arch/x86/kernel/cpu/topology_common.c @@ -0,0 +1,218 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <linux/cpu.h> + +#include <xen/xen.h> + +#include <asm/apic.h> +#include <asm/processor.h> +#include <asm/smp.h> + +#include "cpu.h" + +struct x86_topology_system x86_topo_system __ro_after_init; +EXPORT_SYMBOL_GPL(x86_topo_system); + +unsigned int __amd_nodes_per_pkg __ro_after_init; +EXPORT_SYMBOL_GPL(__amd_nodes_per_pkg); + +void topology_set_dom(struct topo_scan *tscan, enum x86_topology_domains dom, + unsigned int shift, unsigned int ncpus) +{ + topology_update_dom(tscan, dom, shift, ncpus); + + /* Propagate to the upper levels */ + for (dom++; dom < TOPO_MAX_DOMAIN; dom++) { + tscan->dom_shifts[dom] = tscan->dom_shifts[dom - 1]; + tscan->dom_ncpus[dom] = tscan->dom_ncpus[dom - 1]; + } +} + +static unsigned int __maybe_unused parse_num_cores_legacy(struct cpuinfo_x86 *c) +{ + struct { + u32 cache_type : 5, + unused : 21, + ncores : 6; + } eax; + + if (c->cpuid_level < 4) + return 1; + + cpuid_subleaf_reg(4, 0, CPUID_EAX, &eax); + if (!eax.cache_type) + return 1; + + return eax.ncores + 1; +} + +static void parse_legacy(struct topo_scan *tscan) +{ + unsigned int cores, core_shift, smt_shift = 0; + struct cpuinfo_x86 *c = tscan->c; + + cores = parse_num_cores_legacy(c); + core_shift = get_count_order(cores); + + if (cpu_has(c, X86_FEATURE_HT)) { + if (!WARN_ON_ONCE(tscan->ebx1_nproc_shift < core_shift)) + smt_shift = tscan->ebx1_nproc_shift - core_shift; + /* + * The parser expects leaf 0xb/0x1f format, which means + * the number of logical processors at core level is + * counting threads. + */ + core_shift += smt_shift; + cores <<= smt_shift; + } + + topology_set_dom(tscan, TOPO_SMT_DOMAIN, smt_shift, 1U << smt_shift); + topology_set_dom(tscan, TOPO_CORE_DOMAIN, core_shift, cores); +} + +static bool fake_topology(struct topo_scan *tscan) +{ + /* + * Preset the CORE level shift for CPUID less systems and XEN_PV, + * which has useless CPUID information. + */ + topology_set_dom(tscan, TOPO_SMT_DOMAIN, 0, 1); + topology_set_dom(tscan, TOPO_CORE_DOMAIN, 0, 1); + + return tscan->c->cpuid_level < 1; +} + +static void parse_topology(struct topo_scan *tscan, bool early) +{ + const struct cpuinfo_topology topo_defaults = { + .cu_id = 0xff, + .llc_id = BAD_APICID, + .l2c_id = BAD_APICID, + }; + struct cpuinfo_x86 *c = tscan->c; + struct { + u32 unused0 : 16, + nproc : 8, + apicid : 8; + } ebx; + + c->topo = topo_defaults; + + if (fake_topology(tscan)) + return; + + /* Preset Initial APIC ID from CPUID leaf 1 */ + cpuid_leaf_reg(1, CPUID_EBX, &ebx); + c->topo.initial_apicid = ebx.apicid; + + /* + * The initial invocation from early_identify_cpu() happens before + * the APIC is mapped or X2APIC enabled. For establishing the + * topology, that's not required. Use the initial APIC ID. + */ + if (early) + c->topo.apicid = c->topo.initial_apicid; + else + c->topo.apicid = read_apic_id(); + + /* The above is sufficient for UP */ + if (!IS_ENABLED(CONFIG_SMP)) + return; + + tscan->ebx1_nproc_shift = get_count_order(ebx.nproc); + + switch (c->x86_vendor) { + case X86_VENDOR_AMD: + if (IS_ENABLED(CONFIG_CPU_SUP_AMD)) + cpu_parse_topology_amd(tscan); + break; + case X86_VENDOR_CENTAUR: + case X86_VENDOR_ZHAOXIN: + parse_legacy(tscan); + break; + case X86_VENDOR_INTEL: + if (!IS_ENABLED(CONFIG_CPU_SUP_INTEL) || !cpu_parse_topology_ext(tscan)) + parse_legacy(tscan); + break; + case X86_VENDOR_HYGON: + if (IS_ENABLED(CONFIG_CPU_SUP_HYGON)) + cpu_parse_topology_amd(tscan); + break; + } +} + +static void topo_set_ids(struct topo_scan *tscan) +{ + struct cpuinfo_x86 *c = tscan->c; + u32 apicid = c->topo.apicid; + + c->topo.pkg_id = topo_shift_apicid(apicid, TOPO_PKG_DOMAIN); + c->topo.die_id = topo_shift_apicid(apicid, TOPO_DIE_DOMAIN); + + c->topo.logical_pkg_id = topology_get_logical_id(apicid, TOPO_PKG_DOMAIN); + c->topo.logical_die_id = topology_get_logical_id(apicid, TOPO_DIE_DOMAIN); + + /* Package relative core ID */ + c->topo.core_id = (apicid & topo_domain_mask(TOPO_PKG_DOMAIN)) >> + x86_topo_system.dom_shifts[TOPO_SMT_DOMAIN]; + + c->topo.amd_node_id = tscan->amd_node_id; + + if (c->x86_vendor == X86_VENDOR_AMD) + cpu_topology_fixup_amd(tscan); +} + +void cpu_parse_topology(struct cpuinfo_x86 *c) +{ + unsigned int dom, cpu = smp_processor_id(); + struct topo_scan tscan = { .c = c, }; + + parse_topology(&tscan, false); + + if (IS_ENABLED(CONFIG_X86_LOCAL_APIC)) { + if (c->topo.initial_apicid != c->topo.apicid) { + pr_err(FW_BUG "CPU%4u: APIC ID mismatch. CPUID: 0x%04x APIC: 0x%04x\n", + cpu, c->topo.initial_apicid, c->topo.apicid); + } + + if (c->topo.apicid != cpuid_to_apicid[cpu]) { + pr_err(FW_BUG "CPU%4u: APIC ID mismatch. Firmware: 0x%04x APIC: 0x%04x\n", + cpu, cpuid_to_apicid[cpu], c->topo.apicid); + } + } + + for (dom = TOPO_SMT_DOMAIN; dom < TOPO_MAX_DOMAIN; dom++) { + if (tscan.dom_shifts[dom] == x86_topo_system.dom_shifts[dom]) + continue; + pr_err(FW_BUG "CPU%d: Topology domain %u shift %u != %u\n", cpu, dom, + tscan.dom_shifts[dom], x86_topo_system.dom_shifts[dom]); + } + + topo_set_ids(&tscan); +} + +void __init cpu_init_topology(struct cpuinfo_x86 *c) +{ + struct topo_scan tscan = { .c = c, }; + unsigned int dom, sft; + + parse_topology(&tscan, true); + + /* Copy the shift values and calculate the unit sizes. */ + memcpy(x86_topo_system.dom_shifts, tscan.dom_shifts, sizeof(x86_topo_system.dom_shifts)); + + dom = TOPO_SMT_DOMAIN; + x86_topo_system.dom_size[dom] = 1U << x86_topo_system.dom_shifts[dom]; + + for (dom++; dom < TOPO_MAX_DOMAIN; dom++) { + sft = x86_topo_system.dom_shifts[dom] - x86_topo_system.dom_shifts[dom - 1]; + x86_topo_system.dom_size[dom] = 1U << sft; + } + + topo_set_ids(&tscan); + + /* + * AMD systems have Nodes per package which cannot be mapped to + * APIC ID. + */ + __amd_nodes_per_pkg = tscan.amd_nodes_per_pkg; +} diff --git a/arch/x86/kernel/cpu/topology_ext.c b/arch/x86/kernel/cpu/topology_ext.c new file mode 100644 index 000000000000..e477228cd5b2 --- /dev/null +++ b/arch/x86/kernel/cpu/topology_ext.c @@ -0,0 +1,130 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <linux/cpu.h> + +#include <asm/apic.h> +#include <asm/memtype.h> +#include <asm/processor.h> + +#include "cpu.h" + +enum topo_types { + INVALID_TYPE = 0, + SMT_TYPE = 1, + CORE_TYPE = 2, + MAX_TYPE_0B = 3, + MODULE_TYPE = 3, + TILE_TYPE = 4, + DIE_TYPE = 5, + DIEGRP_TYPE = 6, + MAX_TYPE_1F = 7, +}; + +/* + * Use a lookup table for the case that there are future types > 6 which + * describe an intermediate domain level which does not exist today. + */ +static const unsigned int topo_domain_map_0b_1f[MAX_TYPE_1F] = { + [SMT_TYPE] = TOPO_SMT_DOMAIN, + [CORE_TYPE] = TOPO_CORE_DOMAIN, + [MODULE_TYPE] = TOPO_MODULE_DOMAIN, + [TILE_TYPE] = TOPO_TILE_DOMAIN, + [DIE_TYPE] = TOPO_DIE_DOMAIN, + [DIEGRP_TYPE] = TOPO_DIEGRP_DOMAIN, +}; + +static inline bool topo_subleaf(struct topo_scan *tscan, u32 leaf, u32 subleaf, + unsigned int *last_dom) +{ + unsigned int dom, maxtype; + const unsigned int *map; + struct { + // eax + u32 x2apic_shift : 5, // Number of bits to shift APIC ID right + // for the topology ID at the next level + : 27; // Reserved + // ebx + u32 num_processors : 16, // Number of processors at current level + : 16; // Reserved + // ecx + u32 level : 8, // Current topology level. Same as sub leaf number + type : 8, // Level type. If 0, invalid + : 16; // Reserved + // edx + u32 x2apic_id : 32; // X2APIC ID of the current logical processor + } sl; + + switch (leaf) { + case 0x0b: maxtype = MAX_TYPE_0B; map = topo_domain_map_0b_1f; break; + case 0x1f: maxtype = MAX_TYPE_1F; map = topo_domain_map_0b_1f; break; + default: return false; + } + + cpuid_subleaf(leaf, subleaf, &sl); + + if (!sl.num_processors || sl.type == INVALID_TYPE) + return false; + + if (sl.type >= maxtype) { + pr_err_once("Topology: leaf 0x%x:%d Unknown domain type %u\n", + leaf, subleaf, sl.type); + /* + * It really would have been too obvious to make the domain + * type space sparse and leave a few reserved types between + * the points which might change instead of following the + * usual "this can be fixed in software" principle. + */ + dom = *last_dom + 1; + } else { + dom = map[sl.type]; + *last_dom = dom; + } + + if (!dom) { + tscan->c->topo.initial_apicid = sl.x2apic_id; + } else if (tscan->c->topo.initial_apicid != sl.x2apic_id) { + pr_warn_once(FW_BUG "CPUID leaf 0x%x subleaf %d APIC ID mismatch %x != %x\n", + leaf, subleaf, tscan->c->topo.initial_apicid, sl.x2apic_id); + } + + topology_set_dom(tscan, dom, sl.x2apic_shift, sl.num_processors); + return true; +} + +static bool parse_topology_leaf(struct topo_scan *tscan, u32 leaf) +{ + unsigned int last_dom; + u32 subleaf; + + /* Read all available subleafs and populate the levels */ + for (subleaf = 0, last_dom = 0; topo_subleaf(tscan, leaf, subleaf, &last_dom); subleaf++); + + /* If subleaf 0 failed to parse, give up */ + if (!subleaf) + return false; + + /* + * There are machines in the wild which have shift 0 in the subleaf + * 0, but advertise 2 logical processors at that level. They are + * truly SMT. + */ + if (!tscan->dom_shifts[TOPO_SMT_DOMAIN] && tscan->dom_ncpus[TOPO_SMT_DOMAIN] > 1) { + unsigned int sft = get_count_order(tscan->dom_ncpus[TOPO_SMT_DOMAIN]); + + pr_warn_once(FW_BUG "CPUID leaf 0x%x subleaf 0 has shift level 0 but %u CPUs. Fixing it up.\n", + leaf, tscan->dom_ncpus[TOPO_SMT_DOMAIN]); + topology_update_dom(tscan, TOPO_SMT_DOMAIN, sft, tscan->dom_ncpus[TOPO_SMT_DOMAIN]); + } + + set_cpu_cap(tscan->c, X86_FEATURE_XTOPOLOGY); + return true; +} + +bool cpu_parse_topology_ext(struct topo_scan *tscan) +{ + /* Intel: Try leaf 0x1F first. */ + if (tscan->c->cpuid_level >= 0x1f && parse_topology_leaf(tscan, 0x1f)) + return true; + + /* Intel/AMD: Fall back to leaf 0xB if available */ + return tscan->c->cpuid_level >= 0x0b && parse_topology_leaf(tscan, 0x0b); +} diff --git a/arch/x86/kernel/cpu/zhaoxin.c b/arch/x86/kernel/cpu/zhaoxin.c index 415564a6523b..90eba7eb5335 100644 --- a/arch/x86/kernel/cpu/zhaoxin.c +++ b/arch/x86/kernel/cpu/zhaoxin.c @@ -71,10 +71,6 @@ static void init_zhaoxin(struct cpuinfo_x86 *c) { early_init_zhaoxin(c); init_intel_cacheinfo(c); - detect_num_cpu_cores(c); -#ifdef CONFIG_X86_32 - detect_ht(c); -#endif if (c->cpuid_level > 9) { unsigned int eax = cpuid_eax(10); diff --git a/arch/x86/kernel/devicetree.c b/arch/x86/kernel/devicetree.c index afd09924094e..4aeafe63521b 100644 --- a/arch/x86/kernel/devicetree.c +++ b/arch/x86/kernel/devicetree.c @@ -136,7 +136,7 @@ static void __init dtb_cpu_setup(void) pr_warn("%pOF: missing local APIC ID\n", dn); continue; } - generic_processor_info(apic_id); + topology_register_apic(apic_id, CPU_ACPIID_INVALID, true); } } @@ -302,7 +302,7 @@ void __init x86_flattree_get_config(void) } #endif -void __init x86_dtb_init(void) +void __init x86_dtb_parse_smp_config(void) { if (!of_have_populated_dt()) return; diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c index fb8cf953380d..b66f540de054 100644 --- a/arch/x86/kernel/e820.c +++ b/arch/x86/kernel/e820.c @@ -1017,10 +1017,12 @@ void __init e820__reserve_setup_data(void) e820__range_update(pa_data, sizeof(*data)+data->len, E820_TYPE_RAM, E820_TYPE_RESERVED_KERN); /* - * SETUP_EFI and SETUP_IMA are supplied by kexec and do not need - * to be reserved. + * SETUP_EFI, SETUP_IMA and SETUP_RNG_SEED are supplied by + * kexec and do not need to be reserved. */ - if (data->type != SETUP_EFI && data->type != SETUP_IMA) + if (data->type != SETUP_EFI && + data->type != SETUP_IMA && + data->type != SETUP_RNG_SEED) e820__range_update_kexec(pa_data, sizeof(*data) + data->len, E820_TYPE_RAM, E820_TYPE_RESERVED_KERN); diff --git a/arch/x86/kernel/espfix_64.c b/arch/x86/kernel/espfix_64.c index 16f9814c9be0..6726e0473d0b 100644 --- a/arch/x86/kernel/espfix_64.c +++ b/arch/x86/kernel/espfix_64.c @@ -106,6 +106,10 @@ void __init init_espfix_bsp(void) pgd_t *pgd; p4d_t *p4d; + /* FRED systems always restore the full value of %rsp */ + if (cpu_feature_enabled(X86_FEATURE_FRED)) + return; + /* Install the espfix pud into the kernel page directory */ pgd = &init_top_pgt[pgd_index(ESPFIX_BASE_ADDR)]; p4d = p4d_alloc(&init_mm, pgd, ESPFIX_BASE_ADDR); @@ -129,6 +133,10 @@ void init_espfix_ap(int cpu) void *stack_page; pteval_t ptemask; + /* FRED systems always restore the full value of %rsp */ + if (cpu_feature_enabled(X86_FEATURE_FRED)) + return; + /* We only have to do this once... */ if (likely(per_cpu(espfix_stack, cpu))) return; /* Already initialized */ diff --git a/arch/x86/kernel/fred.c b/arch/x86/kernel/fred.c new file mode 100644 index 000000000000..4bcd8791ad96 --- /dev/null +++ b/arch/x86/kernel/fred.c @@ -0,0 +1,59 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#include <linux/kernel.h> + +#include <asm/desc.h> +#include <asm/fred.h> +#include <asm/tlbflush.h> +#include <asm/traps.h> + +/* #DB in the kernel would imply the use of a kernel debugger. */ +#define FRED_DB_STACK_LEVEL 1UL +#define FRED_NMI_STACK_LEVEL 2UL +#define FRED_MC_STACK_LEVEL 2UL +/* + * #DF is the highest level because a #DF means "something went wrong + * *while delivering an exception*." The number of cases for which that + * can happen with FRED is drastically reduced and basically amounts to + * "the stack you pointed me to is broken." Thus, always change stacks + * on #DF, which means it should be at the highest level. + */ +#define FRED_DF_STACK_LEVEL 3UL + +#define FRED_STKLVL(vector, lvl) ((lvl) << (2 * (vector))) + +void cpu_init_fred_exceptions(void) +{ + /* When FRED is enabled by default, remove this log message */ + pr_info("Initialize FRED on CPU%d\n", smp_processor_id()); + + wrmsrl(MSR_IA32_FRED_CONFIG, + /* Reserve for CALL emulation */ + FRED_CONFIG_REDZONE | + FRED_CONFIG_INT_STKLVL(0) | + FRED_CONFIG_ENTRYPOINT(asm_fred_entrypoint_user)); + + /* + * The purpose of separate stacks for NMI, #DB and #MC *in the kernel* + * (remember that user space faults are always taken on stack level 0) + * is to avoid overflowing the kernel stack. + */ + wrmsrl(MSR_IA32_FRED_STKLVLS, + FRED_STKLVL(X86_TRAP_DB, FRED_DB_STACK_LEVEL) | + FRED_STKLVL(X86_TRAP_NMI, FRED_NMI_STACK_LEVEL) | + FRED_STKLVL(X86_TRAP_MC, FRED_MC_STACK_LEVEL) | + FRED_STKLVL(X86_TRAP_DF, FRED_DF_STACK_LEVEL)); + + /* The FRED equivalents to IST stacks... */ + wrmsrl(MSR_IA32_FRED_RSP1, __this_cpu_ist_top_va(DB)); + wrmsrl(MSR_IA32_FRED_RSP2, __this_cpu_ist_top_va(NMI)); + wrmsrl(MSR_IA32_FRED_RSP3, __this_cpu_ist_top_va(DF)); + + /* Enable FRED */ + cr4_set_bits(X86_CR4_FRED); + /* Any further IDT use is a bug */ + idt_invalidate(); + + /* Use int $0x80 for 32-bit system calls in FRED mode */ + setup_clear_cpu_cap(X86_FEATURE_SYSENTER32); + setup_clear_cpu_cap(X86_FEATURE_SYSCALL32); +} diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S index d4918d03efb4..c38e43589046 100644 --- a/arch/x86/kernel/head_64.S +++ b/arch/x86/kernel/head_64.S @@ -26,6 +26,7 @@ #include <asm/apicdef.h> #include <asm/fixmap.h> #include <asm/smp.h> +#include <asm/thread_info.h> /* * We are not able to switch in one step to the final KERNEL ADDRESS SPACE @@ -66,7 +67,7 @@ SYM_CODE_START_NOALIGN(startup_64) mov %rsi, %r15 /* Set up the stack for verify_cpu() */ - leaq (__end_init_task - PTREGS_SIZE)(%rip), %rsp + leaq (__end_init_task - TOP_OF_KERNEL_STACK_PADDING - PTREGS_SIZE)(%rip), %rsp leaq _text(%rip), %rdi diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c index a38d0c93a66e..c96ae8fee95e 100644 --- a/arch/x86/kernel/hpet.c +++ b/arch/x86/kernel/hpet.c @@ -568,7 +568,7 @@ static struct irq_domain *hpet_create_irq_domain(int hpet_id) fwspec.param_count = 1; fwspec.param[0] = hpet_id; - parent = irq_find_matching_fwspec(&fwspec, DOMAIN_BUS_ANY); + parent = irq_find_matching_fwspec(&fwspec, DOMAIN_BUS_GENERIC_MSI); if (!parent) { irq_domain_free_fwnode(fn); kfree(domain_info); diff --git a/arch/x86/kernel/idt.c b/arch/x86/kernel/idt.c index 660b601f1d6c..0cd53fa8c65d 100644 --- a/arch/x86/kernel/idt.c +++ b/arch/x86/kernel/idt.c @@ -337,7 +337,7 @@ void idt_invalidate(void) load_idt(&idt); } -void __init alloc_intr_gate(unsigned int n, const void *addr) +void __init idt_install_sysvec(unsigned int n, const void *function) { if (WARN_ON(n < FIRST_SYSTEM_VECTOR)) return; @@ -346,5 +346,5 @@ void __init alloc_intr_gate(unsigned int n, const void *addr) return; if (!WARN_ON(test_and_set_bit(n, system_vectors))) - set_intr_gate(n, addr); + set_intr_gate(n, function); } diff --git a/arch/x86/kernel/irqinit.c b/arch/x86/kernel/irqinit.c index c683666876f1..f79c5edc0b89 100644 --- a/arch/x86/kernel/irqinit.c +++ b/arch/x86/kernel/irqinit.c @@ -28,6 +28,7 @@ #include <asm/setup.h> #include <asm/i8259.h> #include <asm/traps.h> +#include <asm/fred.h> #include <asm/prom.h> /* @@ -96,7 +97,11 @@ void __init native_init_IRQ(void) /* Execute any quirks before the call gates are initialised: */ x86_init.irqs.pre_vector_init(); - idt_setup_apic_and_irq_gates(); + if (cpu_feature_enabled(X86_FEATURE_FRED)) + fred_complete_exception_setup(); + else + idt_setup_apic_and_irq_gates(); + lapic_assign_system_vectors(); if (!acpi_ioapic && !of_ioapic && nr_legacy_irqs()) { diff --git a/arch/x86/kernel/jailhouse.c b/arch/x86/kernel/jailhouse.c index 578d16fc040f..df337860612d 100644 --- a/arch/x86/kernel/jailhouse.c +++ b/arch/x86/kernel/jailhouse.c @@ -89,7 +89,7 @@ static void __init jailhouse_x2apic_init(void) #endif } -static void __init jailhouse_get_smp_config(unsigned int early) +static void __init jailhouse_parse_smp_config(void) { struct ioapic_domain_cfg ioapic_cfg = { .type = IOAPIC_DOMAIN_STRICT, @@ -102,7 +102,7 @@ static void __init jailhouse_get_smp_config(unsigned int early) register_lapic_address(0xfee00000); for (cpu = 0; cpu < setup_data.v1.num_cpus; cpu++) - generic_processor_info(setup_data.v1.cpu_ids[cpu]); + topology_register_apic(setup_data.v1.cpu_ids[cpu], CPU_ACPIID_INVALID, true); smp_found_config = 1; @@ -201,21 +201,23 @@ static void __init jailhouse_init_platform(void) struct setup_data header; void *mapping; - x86_init.irqs.pre_vector_init = x86_init_noop; - x86_init.timers.timer_init = jailhouse_timer_init; - x86_init.mpparse.get_smp_config = jailhouse_get_smp_config; - x86_init.pci.arch_init = jailhouse_pci_arch_init; + x86_init.irqs.pre_vector_init = x86_init_noop; + x86_init.timers.timer_init = jailhouse_timer_init; + x86_init.mpparse.find_mptable = x86_init_noop; + x86_init.mpparse.early_parse_smp_cfg = x86_init_noop; + x86_init.mpparse.parse_smp_cfg = jailhouse_parse_smp_config; + x86_init.pci.arch_init = jailhouse_pci_arch_init; - x86_platform.calibrate_cpu = jailhouse_get_tsc; - x86_platform.calibrate_tsc = jailhouse_get_tsc; - x86_platform.get_wallclock = jailhouse_get_wallclock; - x86_platform.legacy.rtc = 0; - x86_platform.legacy.warm_reset = 0; - x86_platform.legacy.i8042 = X86_LEGACY_I8042_PLATFORM_ABSENT; + x86_platform.calibrate_cpu = jailhouse_get_tsc; + x86_platform.calibrate_tsc = jailhouse_get_tsc; + x86_platform.get_wallclock = jailhouse_get_wallclock; + x86_platform.legacy.rtc = 0; + x86_platform.legacy.warm_reset = 0; + x86_platform.legacy.i8042 = X86_LEGACY_I8042_PLATFORM_ABSENT; - legacy_pic = &null_legacy_pic; + legacy_pic = &null_legacy_pic; - machine_ops.emergency_restart = jailhouse_no_restart; + machine_ops.emergency_restart = jailhouse_no_restart; while (pa_data) { mapping = early_memremap(pa_data, sizeof(header)); diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c index 428ee74002e1..101a7c1bf200 100644 --- a/arch/x86/kernel/kvm.c +++ b/arch/x86/kernel/kvm.c @@ -830,7 +830,7 @@ static void __init kvm_guest_init(void) if (kvm_para_has_feature(KVM_FEATURE_ASYNC_PF_INT) && kvmapf) { static_branch_enable(&kvm_async_pf_enabled); - alloc_intr_gate(HYPERVISOR_CALLBACK_VECTOR, asm_sysvec_kvm_asyncpf_interrupt); + sysvec_install(HYPERVISOR_CALLBACK_VECTOR, sysvec_kvm_asyncpf_interrupt); } #ifdef CONFIG_SMP diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c index 5bb395551c44..5b2c15214a6b 100644 --- a/arch/x86/kernel/kvmclock.c +++ b/arch/x86/kernel/kvmclock.c @@ -154,15 +154,15 @@ static int kvm_cs_enable(struct clocksource *cs) return 0; } -struct clocksource kvm_clock = { +static struct clocksource kvm_clock = { .name = "kvm-clock", .read = kvm_clock_get_cycles, .rating = 400, .mask = CLOCKSOURCE_MASK(64), .flags = CLOCK_SOURCE_IS_CONTINUOUS, + .id = CSID_X86_KVM_CLK, .enable = kvm_cs_enable, }; -EXPORT_SYMBOL_GPL(kvm_clock); static void kvm_register_clock(char *txt) { diff --git a/arch/x86/kernel/mpparse.c b/arch/x86/kernel/mpparse.c index b223922248e9..1ccd30c8246f 100644 --- a/arch/x86/kernel/mpparse.c +++ b/arch/x86/kernel/mpparse.c @@ -36,6 +36,8 @@ * Checksum an MP configuration block. */ +static unsigned int num_procs __initdata; + static int __init mpf_checksum(unsigned char *mp, int len) { int sum = 0; @@ -50,16 +52,15 @@ static void __init MP_processor_info(struct mpc_cpu *m) { char *bootup_cpu = ""; - if (!(m->cpuflag & CPU_ENABLED)) { - disabled_cpus++; + topology_register_apic(m->apicid, CPU_ACPIID_INVALID, m->cpuflag & CPU_ENABLED); + if (!(m->cpuflag & CPU_ENABLED)) return; - } if (m->cpuflag & CPU_BOOTPROCESSOR) bootup_cpu = " (Bootup-CPU)"; pr_info("Processor #%d%s\n", m->apicid, bootup_cpu); - generic_processor_info(m->apicid); + num_procs++; } #ifdef CONFIG_X86_IO_APIC @@ -236,9 +237,9 @@ static int __init smp_read_mpc(struct mpc_table *mpc, unsigned early) } } - if (!num_processors) + if (!num_procs && !acpi_lapic) pr_err("MPTABLE: no processors registered!\n"); - return num_processors; + return num_procs || acpi_lapic; } #ifdef CONFIG_X86_IO_APIC @@ -473,7 +474,7 @@ static int __init check_physptr(struct mpf_intel *mpf, unsigned int early) /* * Scan the memory blocks for an SMP configuration block. */ -void __init default_get_smp_config(unsigned int early) +static __init void mpparse_get_smp_config(unsigned int early) { struct mpf_intel *mpf; @@ -529,8 +530,8 @@ void __init default_get_smp_config(unsigned int early) } else BUG(); - if (!early) - pr_info("Processors: %d\n", num_processors); + if (!early && !acpi_lapic) + pr_info("Processors: %d\n", num_procs); /* * Only use the first configuration found. */ @@ -538,6 +539,16 @@ out: early_memunmap(mpf, sizeof(*mpf)); } +void __init mpparse_parse_early_smp_config(void) +{ + mpparse_get_smp_config(true); +} + +void __init mpparse_parse_smp_config(void) +{ + mpparse_get_smp_config(false); +} + static void __init smp_reserve_memory(struct mpf_intel *mpf) { memblock_reserve(mpf->physptr, get_mpc_size(mpf->physptr)); @@ -587,7 +598,7 @@ static int __init smp_scan_config(unsigned long base, unsigned long length) return ret; } -void __init default_find_smp_config(void) +void __init mpparse_find_mptable(void) { unsigned int address; diff --git a/arch/x86/kernel/nmi.c b/arch/x86/kernel/nmi.c index 17e955ab69fe..397ef9fcf5e9 100644 --- a/arch/x86/kernel/nmi.c +++ b/arch/x86/kernel/nmi.c @@ -35,6 +35,7 @@ #include <asm/nospec-branch.h> #include <asm/microcode.h> #include <asm/sev.h> +#include <asm/fred.h> #define CREATE_TRACE_POINTS #include <trace/events/nmi.h> @@ -563,9 +564,6 @@ nmi_restart: } if (this_cpu_dec_return(nmi_state)) goto nmi_restart; - - if (user_mode(regs)) - mds_user_clear_cpu_buffers(); } #if IS_ENABLED(CONFIG_KVM_INTEL) @@ -651,6 +649,47 @@ void nmi_backtrace_stall_check(const struct cpumask *btp) #endif +#ifdef CONFIG_X86_FRED +/* + * With FRED, CR2/DR6 is pushed to #PF/#DB stack frame during FRED + * event delivery, i.e., there is no problem of transient states. + * And NMI unblocking only happens when the stack frame indicates + * that so should happen. + * + * Thus, the NMI entry stub for FRED is really straightforward and + * as simple as most exception handlers. As such, #DB is allowed + * during NMI handling. + */ +DEFINE_FREDENTRY_NMI(exc_nmi) +{ + irqentry_state_t irq_state; + + if (arch_cpu_is_offline(smp_processor_id())) { + if (microcode_nmi_handler_enabled()) + microcode_offline_nmi_handler(); + return; + } + + /* + * Save CR2 for eventual restore to cover the case where the NMI + * hits the VMENTER/VMEXIT region where guest CR2 is life. This + * prevents guest state corruption in case that the NMI handler + * takes a page fault. + */ + this_cpu_write(nmi_cr2, read_cr2()); + + irq_state = irqentry_nmi_enter(regs); + + inc_irq_stat(__nmi_count); + default_do_nmi(regs); + + irqentry_nmi_exit(regs, irq_state); + + if (unlikely(this_cpu_read(nmi_cr2) != read_cr2())) + write_cr2(this_cpu_read(nmi_cr2)); +} +#endif + void stop_nmi(void) { ignore_nmis++; diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index ab49ade31b0d..6121c2b42ecf 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -936,7 +936,7 @@ static __cpuidle void mwait_idle(void) void select_idle_routine(const struct cpuinfo_x86 *c) { #ifdef CONFIG_SMP - if (boot_option_idle_override == IDLE_POLL && smp_num_siblings > 1) + if (boot_option_idle_override == IDLE_POLL && __max_threads_per_core > 1) pr_warn_once("WARNING: polling idle and HT enabled, performance may degrade\n"); #endif if (x86_idle_set() || boot_option_idle_override == IDLE_POLL) diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index 33b268747bb7..c075591b7b46 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -56,6 +56,7 @@ #include <asm/resctrl.h> #include <asm/unistd.h> #include <asm/fsgsbase.h> +#include <asm/fred.h> #ifdef CONFIG_IA32_EMULATION /* Not included via unistd.h */ #include <asm/unistd_32_ia32.h> @@ -117,7 +118,7 @@ void __show_regs(struct pt_regs *regs, enum show_regs_mode mode, printk("%sFS: %016lx(%04x) GS:%016lx(%04x) knlGS:%016lx\n", log_lvl, fs, fsindex, gs, gsindex, shadowgs); - printk("%sCS: %04lx DS: %04x ES: %04x CR0: %016lx\n", + printk("%sCS: %04x DS: %04x ES: %04x CR0: %016lx\n", log_lvl, regs->cs, ds, es, cr0); printk("%sCR2: %016lx CR3: %016lx CR4: %016lx\n", log_lvl, cr2, cr3, cr4); @@ -166,7 +167,29 @@ static noinstr unsigned long __rdgsbase_inactive(void) lockdep_assert_irqs_disabled(); - if (!cpu_feature_enabled(X86_FEATURE_XENPV)) { + /* + * SWAPGS is no longer needed thus NOT allowed with FRED because + * FRED transitions ensure that an operating system can _always_ + * operate with its own GS base address: + * - For events that occur in ring 3, FRED event delivery swaps + * the GS base address with the IA32_KERNEL_GS_BASE MSR. + * - ERETU (the FRED transition that returns to ring 3) also swaps + * the GS base address with the IA32_KERNEL_GS_BASE MSR. + * + * And the operating system can still setup the GS segment for a + * user thread without the need of loading a user thread GS with: + * - Using LKGS, available with FRED, to modify other attributes + * of the GS segment without compromising its ability always to + * operate with its own GS base address. + * - Accessing the GS segment base address for a user thread as + * before using RDMSR or WRMSR on the IA32_KERNEL_GS_BASE MSR. + * + * Note, LKGS loads the GS base address into the IA32_KERNEL_GS_BASE + * MSR instead of the GS segment’s descriptor cache. As such, the + * operating system never changes its runtime GS base address. + */ + if (!cpu_feature_enabled(X86_FEATURE_FRED) && + !cpu_feature_enabled(X86_FEATURE_XENPV)) { native_swapgs(); gsbase = rdgsbase(); native_swapgs(); @@ -191,7 +214,8 @@ static noinstr void __wrgsbase_inactive(unsigned long gsbase) { lockdep_assert_irqs_disabled(); - if (!cpu_feature_enabled(X86_FEATURE_XENPV)) { + if (!cpu_feature_enabled(X86_FEATURE_FRED) && + !cpu_feature_enabled(X86_FEATURE_XENPV)) { native_swapgs(); wrgsbase(gsbase); native_swapgs(); @@ -505,7 +529,7 @@ void x86_gsbase_write_task(struct task_struct *task, unsigned long gsbase) static void start_thread_common(struct pt_regs *regs, unsigned long new_ip, unsigned long new_sp, - unsigned int _cs, unsigned int _ss, unsigned int _ds) + u16 _cs, u16 _ss, u16 _ds) { WARN_ON_ONCE(regs != current_pt_regs()); @@ -522,11 +546,36 @@ start_thread_common(struct pt_regs *regs, unsigned long new_ip, loadsegment(ds, _ds); load_gs_index(0); - regs->ip = new_ip; - regs->sp = new_sp; - regs->cs = _cs; - regs->ss = _ss; - regs->flags = X86_EFLAGS_IF; + regs->ip = new_ip; + regs->sp = new_sp; + regs->csx = _cs; + regs->ssx = _ss; + /* + * Allow single-step trap and NMI when starting a new task, thus + * once the new task enters user space, single-step trap and NMI + * are both enabled immediately. + * + * Entering a new task is logically speaking a return from a + * system call (exec, fork, clone, etc.). As such, if ptrace + * enables single stepping a single step exception should be + * allowed to trigger immediately upon entering user space. + * This is not optional. + * + * NMI should *never* be disabled in user space. As such, this + * is an optional, opportunistic way to catch errors. + * + * Paranoia: High-order 48 bits above the lowest 16 bit SS are + * discarded by the legacy IRET instruction on all Intel, AMD, + * and Cyrix/Centaur/VIA CPUs, thus can be set unconditionally, + * even when FRED is not enabled. But we choose the safer side + * to use these bits only when FRED is enabled. + */ + if (cpu_feature_enabled(X86_FEATURE_FRED)) { + regs->fred_ss.swevent = true; + regs->fred_ss.nmi = true; + } + + regs->flags = X86_EFLAGS_IF | X86_EFLAGS_FIXED; } void diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index 84201071dfac..4e320d4d3898 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -970,10 +970,8 @@ void __init setup_arch(char **cmdline_p) high_memory = (void *)__va(max_pfn * PAGE_SIZE - 1) + 1; #endif - /* - * Find and reserve possible boot-time SMP configuration: - */ - find_smp_config(); + /* Find and reserve MPTABLE area */ + x86_init.mpparse.find_mptable(); early_alloc_pgt_buf(); @@ -1090,7 +1088,9 @@ void __init setup_arch(char **cmdline_p) early_platform_quirks(); + /* Some platforms need the APIC registered for NUMA configuration */ early_acpi_boot_init(); + x86_init.mpparse.early_parse_smp_cfg(); x86_flattree_get_config(); @@ -1131,24 +1131,19 @@ void __init setup_arch(char **cmdline_p) early_quirks(); - /* - * Read APIC and some other early information from ACPI tables. - */ - acpi_boot_init(); - x86_dtb_init(); + topology_apply_cmdline_limits_early(); /* - * get boot-time SMP configuration: + * Parse SMP configuration. Try ACPI first and then the platform + * specific parser. */ - get_smp_config(); + acpi_boot_init(); + x86_init.mpparse.parse_smp_cfg(); - /* - * Systems w/o ACPI and mptables might not have it mapped the local - * APIC yet, but prefill_possible_map() might need to access it. - */ + /* Last opportunity to detect and map the local APIC */ init_apic_mappings(); - prefill_possible_map(); + topology_init_possible_cpus(); init_cpu_to_node(); init_gi_nodes(); diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index 3f57ce68a3f1..9c1e1219c28f 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -125,25 +125,6 @@ struct mwait_cpu_dead { */ static DEFINE_PER_CPU_ALIGNED(struct mwait_cpu_dead, mwait_cpu_dead); -/* Logical package management. */ -struct logical_maps { - u32 phys_pkg_id; - u32 phys_die_id; - u32 logical_pkg_id; - u32 logical_die_id; -}; - -/* Temporary workaround until the full topology mechanics is in place */ -static DEFINE_PER_CPU_READ_MOSTLY(struct logical_maps, logical_maps) = { - .phys_pkg_id = U32_MAX, - .phys_die_id = U32_MAX, -}; - -unsigned int __max_logical_packages __read_mostly; -EXPORT_SYMBOL(__max_logical_packages); -static unsigned int logical_packages __read_mostly; -static unsigned int logical_die __read_mostly; - /* Maximum number of SMT threads on any online core */ int __read_mostly __max_smt_threads = 1; @@ -336,103 +317,11 @@ static void notrace start_secondary(void *unused) cpu_startup_entry(CPUHP_AP_ONLINE_IDLE); } -/** - * topology_phys_to_logical_pkg - Map a physical package id to a logical - * @phys_pkg: The physical package id to map - * - * Returns logical package id or -1 if not found - */ -int topology_phys_to_logical_pkg(unsigned int phys_pkg) -{ - int cpu; - - for_each_possible_cpu(cpu) { - if (per_cpu(logical_maps.phys_pkg_id, cpu) == phys_pkg) - return per_cpu(logical_maps.logical_pkg_id, cpu); - } - return -1; -} -EXPORT_SYMBOL(topology_phys_to_logical_pkg); - -/** - * topology_phys_to_logical_die - Map a physical die id to logical - * @die_id: The physical die id to map - * @cur_cpu: The CPU for which the mapping is done - * - * Returns logical die id or -1 if not found - */ -static int topology_phys_to_logical_die(unsigned int die_id, unsigned int cur_cpu) -{ - int cpu, proc_id = cpu_data(cur_cpu).topo.pkg_id; - - for_each_possible_cpu(cpu) { - if (per_cpu(logical_maps.phys_pkg_id, cpu) == proc_id && - per_cpu(logical_maps.phys_die_id, cpu) == die_id) - return per_cpu(logical_maps.logical_die_id, cpu); - } - return -1; -} - -/** - * topology_update_package_map - Update the physical to logical package map - * @pkg: The physical package id as retrieved via CPUID - * @cpu: The cpu for which this is updated - */ -int topology_update_package_map(unsigned int pkg, unsigned int cpu) -{ - int new; - - /* Already available somewhere? */ - new = topology_phys_to_logical_pkg(pkg); - if (new >= 0) - goto found; - - new = logical_packages++; - if (new != pkg) { - pr_info("CPU %u Converting physical %u to logical package %u\n", - cpu, pkg, new); - } -found: - per_cpu(logical_maps.phys_pkg_id, cpu) = pkg; - per_cpu(logical_maps.logical_pkg_id, cpu) = new; - cpu_data(cpu).topo.logical_pkg_id = new; - return 0; -} -/** - * topology_update_die_map - Update the physical to logical die map - * @die: The die id as retrieved via CPUID - * @cpu: The cpu for which this is updated - */ -int topology_update_die_map(unsigned int die, unsigned int cpu) -{ - int new; - - /* Already available somewhere? */ - new = topology_phys_to_logical_die(die, cpu); - if (new >= 0) - goto found; - - new = logical_die++; - if (new != die) { - pr_info("CPU %u Converting physical %u to logical die %u\n", - cpu, die, new); - } -found: - per_cpu(logical_maps.phys_die_id, cpu) = die; - per_cpu(logical_maps.logical_die_id, cpu) = new; - cpu_data(cpu).topo.logical_die_id = new; - return 0; -} - static void __init smp_store_boot_cpu_info(void) { - int id = 0; /* CPU 0 */ - struct cpuinfo_x86 *c = &cpu_data(id); + struct cpuinfo_x86 *c = &cpu_data(0); *c = boot_cpu_data; - c->cpu_index = id; - topology_update_package_map(c->topo.pkg_id, id); - topology_update_die_map(c->topo.die_id, id); c->initialized = true; } @@ -488,6 +377,7 @@ static bool match_smt(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o) if (c->topo.pkg_id == o->topo.pkg_id && c->topo.die_id == o->topo.die_id && + c->topo.amd_node_id == o->topo.amd_node_id && per_cpu_llc_id(cpu1) == per_cpu_llc_id(cpu2)) { if (c->topo.core_id == o->topo.core_id) return topology_sane(c, o, "smt"); @@ -509,10 +399,13 @@ static bool match_smt(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o) static bool match_die(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o) { - if (c->topo.pkg_id == o->topo.pkg_id && - c->topo.die_id == o->topo.die_id) - return true; - return false; + if (c->topo.pkg_id != o->topo.pkg_id || c->topo.die_id != o->topo.die_id) + return false; + + if (cpu_feature_enabled(X86_FEATURE_TOPOEXT) && topology_amd_nodes_per_pkg() > 1) + return c->topo.amd_node_id == o->topo.amd_node_id; + + return true; } static bool match_l2c(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o) @@ -670,8 +563,8 @@ static void __init build_sched_topology(void) void set_cpu_sibling_map(int cpu) { - bool has_smt = smp_num_siblings > 1; - bool has_mp = has_smt || boot_cpu_data.x86_max_cores > 1; + bool has_smt = __max_threads_per_core > 1; + bool has_mp = has_smt || topology_num_cores_per_package() > 1; struct cpuinfo_x86 *c = &cpu_data(cpu); struct cpuinfo_x86 *o; int i, threads; @@ -1068,9 +961,13 @@ int native_kick_ap(unsigned int cpu, struct task_struct *tidle) pr_debug("++++++++++++++++++++=_---CPU UP %u\n", cpu); - if (apicid == BAD_APICID || !physid_isset(apicid, phys_cpu_present_map) || - !apic_id_valid(apicid)) { - pr_err("%s: bad cpu %d\n", __func__, cpu); + if (apicid == BAD_APICID || !apic_id_valid(apicid)) { + pr_err("CPU %u has invalid APIC ID %x. Aborting bringup\n", cpu, apicid); + return -EINVAL; + } + + if (!test_bit(apicid, phys_cpu_present_map)) { + pr_err("CPU %u APIC ID %x is not present. Aborting bringup\n", cpu, apicid); return -EINVAL; } @@ -1139,14 +1036,8 @@ static __init void disable_smp(void) pr_info("SMP disabled\n"); disable_ioapic_support(); + topology_reset_possible_cpus_up(); - init_cpu_present(cpumask_of(0)); - init_cpu_possible(cpumask_of(0)); - - if (smp_found_config) - physid_set_mask_of_physid(boot_cpu_physical_apicid, &phys_cpu_present_map); - else - physid_set_mask_of_physid(0, &phys_cpu_present_map); cpumask_set_cpu(0, topology_sibling_cpumask(0)); cpumask_set_cpu(0, topology_core_cpumask(0)); cpumask_set_cpu(0, topology_die_cpumask(0)); @@ -1265,102 +1156,16 @@ void __init native_smp_prepare_boot_cpu(void) native_pv_lock_init(); } -void __init calculate_max_logical_packages(void) -{ - int ncpus; - - /* - * Today neither Intel nor AMD support heterogeneous systems so - * extrapolate the boot cpu's data to all packages. - */ - ncpus = cpu_data(0).booted_cores * topology_max_smt_threads(); - __max_logical_packages = DIV_ROUND_UP(total_cpus, ncpus); - pr_info("Max logical packages: %u\n", __max_logical_packages); -} - void __init native_smp_cpus_done(unsigned int max_cpus) { pr_debug("Boot done\n"); - calculate_max_logical_packages(); build_sched_topology(); nmi_selftest(); impress_friends(); cache_aps_init(); } -static int __initdata setup_possible_cpus = -1; -static int __init _setup_possible_cpus(char *str) -{ - get_option(&str, &setup_possible_cpus); - return 0; -} -early_param("possible_cpus", _setup_possible_cpus); - - -/* - * cpu_possible_mask should be static, it cannot change as cpu's - * are onlined, or offlined. The reason is per-cpu data-structures - * are allocated by some modules at init time, and don't expect to - * do this dynamically on cpu arrival/departure. - * cpu_present_mask on the other hand can change dynamically. - * In case when cpu_hotplug is not compiled, then we resort to current - * behaviour, which is cpu_possible == cpu_present. - * - Ashok Raj - * - * Three ways to find out the number of additional hotplug CPUs: - * - If the BIOS specified disabled CPUs in ACPI/mptables use that. - * - The user can overwrite it with possible_cpus=NUM - * - Otherwise don't reserve additional CPUs. - * We do this because additional CPUs waste a lot of memory. - * -AK - */ -__init void prefill_possible_map(void) -{ - int i, possible; - - i = setup_max_cpus ?: 1; - if (setup_possible_cpus == -1) { - possible = num_processors; -#ifdef CONFIG_HOTPLUG_CPU - if (setup_max_cpus) - possible += disabled_cpus; -#else - if (possible > i) - possible = i; -#endif - } else - possible = setup_possible_cpus; - - total_cpus = max_t(int, possible, num_processors + disabled_cpus); - - /* nr_cpu_ids could be reduced via nr_cpus= */ - if (possible > nr_cpu_ids) { - pr_warn("%d Processors exceeds NR_CPUS limit of %u\n", - possible, nr_cpu_ids); - possible = nr_cpu_ids; - } - -#ifdef CONFIG_HOTPLUG_CPU - if (!setup_max_cpus) -#endif - if (possible > i) { - pr_warn("%d Processors exceeds max_cpus limit of %u\n", - possible, setup_max_cpus); - possible = i; - } - - set_nr_cpu_ids(possible); - - pr_info("Allowing %d CPUs, %d hotplug CPUs\n", - possible, max_t(int, possible - num_processors, 0)); - - reset_cpu_possible_mask(); - - for (i = 0; i < possible; i++) - set_cpu_possible(i, true); -} - /* correctly size the local cpu masks */ void __init setup_cpu_local_masks(void) { diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index c3b2f863acf0..6cb31df3d5ff 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -51,6 +51,7 @@ #include <asm/ftrace.h> #include <asm/traps.h> #include <asm/desc.h> +#include <asm/fred.h> #include <asm/fpu/api.h> #include <asm/cpu.h> #include <asm/cpu_entry_area.h> @@ -935,8 +936,7 @@ static bool notify_debug(struct pt_regs *regs, unsigned long *dr6) return false; } -static __always_inline void exc_debug_kernel(struct pt_regs *regs, - unsigned long dr6) +static noinstr void exc_debug_kernel(struct pt_regs *regs, unsigned long dr6) { /* * Disable breakpoints during exception handling; recursive exceptions @@ -948,6 +948,11 @@ static __always_inline void exc_debug_kernel(struct pt_regs *regs, * * Entry text is excluded for HW_BP_X and cpu_entry_area, which * includes the entry stack is excluded for everything. + * + * For FRED, nested #DB should just work fine. But when a watchpoint or + * breakpoint is set in the code path which is executed by #DB handler, + * it results in an endless recursion and stack overflow. Thus we stay + * with the IDT approach, i.e., save DR7 and disable #DB. */ unsigned long dr7 = local_db_save(); irqentry_state_t irq_state = irqentry_nmi_enter(regs); @@ -977,7 +982,8 @@ static __always_inline void exc_debug_kernel(struct pt_regs *regs, * Catch SYSENTER with TF set and clear DR_STEP. If this hit a * watchpoint at the same time then that will still be handled. */ - if ((dr6 & DR_STEP) && is_sysenter_singlestep(regs)) + if (!cpu_feature_enabled(X86_FEATURE_FRED) && + (dr6 & DR_STEP) && is_sysenter_singlestep(regs)) dr6 &= ~DR_STEP; /* @@ -1009,8 +1015,7 @@ out: local_db_restore(dr7); } -static __always_inline void exc_debug_user(struct pt_regs *regs, - unsigned long dr6) +static noinstr void exc_debug_user(struct pt_regs *regs, unsigned long dr6) { bool icebp; @@ -1094,6 +1099,34 @@ DEFINE_IDTENTRY_DEBUG_USER(exc_debug) { exc_debug_user(regs, debug_read_clear_dr6()); } + +#ifdef CONFIG_X86_FRED +/* + * When occurred on different ring level, i.e., from user or kernel + * context, #DB needs to be handled on different stack: User #DB on + * current task stack, while kernel #DB on a dedicated stack. + * + * This is exactly how FRED event delivery invokes an exception + * handler: ring 3 event on level 0 stack, i.e., current task stack; + * ring 0 event on the #DB dedicated stack specified in the + * IA32_FRED_STKLVLS MSR. So unlike IDT, the FRED debug exception + * entry stub doesn't do stack switch. + */ +DEFINE_FREDENTRY_DEBUG(exc_debug) +{ + /* + * FRED #DB stores DR6 on the stack in the format which + * debug_read_clear_dr6() returns for the IDT entry points. + */ + unsigned long dr6 = fred_event_data(regs); + + if (user_mode(regs)) + exc_debug_user(regs, dr6); + else + exc_debug_kernel(regs, dr6); +} +#endif /* CONFIG_X86_FRED */ + #else /* 32 bit does not have separate entry points. */ DEFINE_IDTENTRY_RAW(exc_debug) @@ -1369,8 +1402,34 @@ DEFINE_IDTENTRY_SW(iret_error) } #endif +/* Do not enable FRED by default yet. */ +static bool enable_fred __ro_after_init = false; + +#ifdef CONFIG_X86_FRED +static int __init fred_setup(char *str) +{ + if (!str) + return -EINVAL; + + if (!cpu_feature_enabled(X86_FEATURE_FRED)) + return 0; + + if (!strcmp(str, "on")) + enable_fred = true; + else if (!strcmp(str, "off")) + enable_fred = false; + else + pr_warn("invalid FRED option: 'fred=%s'\n", str); + return 0; +} +early_param("fred", fred_setup); +#endif + void __init trap_init(void) { + if (cpu_feature_enabled(X86_FEATURE_FRED) && !enable_fred) + setup_clear_cpu_cap(X86_FEATURE_FRED); + /* Init cpu_entry_area before IST entries are set up */ setup_cpu_entry_areas(); @@ -1379,7 +1438,10 @@ void __init trap_init(void) /* Initialize TSS before setting up traps so ISTs work */ cpu_init_exception_handling(); + /* Setup traps as cpu_init() might #GP */ - idt_setup_traps(); + if (!cpu_feature_enabled(X86_FEATURE_FRED)) + idt_setup_traps(); + cpu_init(); } diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c index 15f97c0abc9d..5a69a49acc96 100644 --- a/arch/x86/kernel/tsc.c +++ b/arch/x86/kernel/tsc.c @@ -53,7 +53,7 @@ static int __read_mostly tsc_force_recalibrate; static u32 art_to_tsc_numerator; static u32 art_to_tsc_denominator; static u64 art_to_tsc_offset; -static struct clocksource *art_related_clocksource; +static bool have_art; struct cyc2ns { struct cyc2ns_data data[2]; /* 0 + 2*16 = 32 */ @@ -652,7 +652,7 @@ success: } /** - * native_calibrate_tsc + * native_calibrate_tsc - determine TSC frequency * Determine TSC frequency via CPUID, else return 0. */ unsigned long native_calibrate_tsc(void) @@ -1168,6 +1168,7 @@ static struct clocksource clocksource_tsc_early = { .mask = CLOCKSOURCE_MASK(64), .flags = CLOCK_SOURCE_IS_CONTINUOUS | CLOCK_SOURCE_MUST_VERIFY, + .id = CSID_X86_TSC_EARLY, .vdso_clock_mode = VDSO_CLOCKMODE_TSC, .enable = tsc_cs_enable, .resume = tsc_resume, @@ -1190,6 +1191,7 @@ static struct clocksource clocksource_tsc = { CLOCK_SOURCE_VALID_FOR_HRES | CLOCK_SOURCE_MUST_VERIFY | CLOCK_SOURCE_VERIFY_PERCPU, + .id = CSID_X86_TSC, .vdso_clock_mode = VDSO_CLOCKMODE_TSC, .enable = tsc_cs_enable, .resume = tsc_resume, @@ -1309,8 +1311,10 @@ struct system_counterval_t convert_art_to_tsc(u64 art) do_div(tmp, art_to_tsc_denominator); res += tmp + art_to_tsc_offset; - return (struct system_counterval_t) {.cs = art_related_clocksource, - .cycles = res}; + return (struct system_counterval_t) { + .cs_id = have_art ? CSID_X86_TSC : CSID_GENERIC, + .cycles = res, + }; } EXPORT_SYMBOL(convert_art_to_tsc); @@ -1327,12 +1331,10 @@ EXPORT_SYMBOL(convert_art_to_tsc); * that this flag is set before conversion to TSC is attempted. * * Return: - * struct system_counterval_t - system counter value with the pointer to the - * corresponding clocksource - * @cycles: System counter value - * @cs: Clocksource corresponding to system counter value. Used - * by timekeeping code to verify comparability of two cycle - * values. + * struct system_counterval_t - system counter value with the ID of the + * corresponding clocksource: + * cycles: System counter value + * cs_id: The clocksource ID for validating comparability */ struct system_counterval_t convert_art_ns_to_tsc(u64 art_ns) @@ -1347,8 +1349,10 @@ struct system_counterval_t convert_art_ns_to_tsc(u64 art_ns) do_div(tmp, USEC_PER_SEC); res += tmp; - return (struct system_counterval_t) { .cs = art_related_clocksource, - .cycles = res}; + return (struct system_counterval_t) { + .cs_id = have_art ? CSID_X86_TSC : CSID_GENERIC, + .cycles = res, + }; } EXPORT_SYMBOL(convert_art_ns_to_tsc); @@ -1357,7 +1361,7 @@ static void tsc_refine_calibration_work(struct work_struct *work); static DECLARE_DELAYED_WORK(tsc_irqwork, tsc_refine_calibration_work); /** * tsc_refine_calibration_work - Further refine tsc freq calibration - * @work - ignored. + * @work: ignored. * * This functions uses delayed work over a period of a * second to further refine the TSC freq value. Since this is @@ -1455,7 +1459,7 @@ out: goto unreg; if (boot_cpu_has(X86_FEATURE_ART)) - art_related_clocksource = &clocksource_tsc; + have_art = true; clocksource_register_khz(&clocksource_tsc, tsc_khz); unreg: clocksource_unregister(&clocksource_tsc_early); @@ -1481,7 +1485,7 @@ static int __init init_tsc_clocksource(void) */ if (boot_cpu_has(X86_FEATURE_TSC_KNOWN_FREQ)) { if (boot_cpu_has(X86_FEATURE_ART)) - art_related_clocksource = &clocksource_tsc; + have_art = true; clocksource_register_khz(&clocksource_tsc, tsc_khz); clocksource_unregister(&clocksource_tsc_early); diff --git a/arch/x86/kernel/vsmp_64.c b/arch/x86/kernel/vsmp_64.c index d3fc01770558..73511332bb67 100644 --- a/arch/x86/kernel/vsmp_64.c +++ b/arch/x86/kernel/vsmp_64.c @@ -127,25 +127,12 @@ static void __init vsmp_cap_cpus(void) #endif } -static u32 apicid_phys_pkg_id(u32 initial_apic_id, int index_msb) -{ - return read_apic_id() >> index_msb; -} - -static void vsmp_apic_post_init(void) -{ - /* need to update phys_pkg_id */ - apic->phys_pkg_id = apicid_phys_pkg_id; -} - void __init vsmp_init(void) { detect_vsmp_box(); if (!is_vsmp_box()) return; - x86_platform.apic_post_init = vsmp_apic_post_init; - vsmp_cap_cpus(); set_vsmp_ctl(); diff --git a/arch/x86/kernel/x86_init.c b/arch/x86/kernel/x86_init.c index a37ebd3b4773..a42830dc151b 100644 --- a/arch/x86/kernel/x86_init.c +++ b/arch/x86/kernel/x86_init.c @@ -70,8 +70,9 @@ struct x86_init_ops x86_init __initdata = { .mpparse = { .setup_ioapic_ids = x86_init_noop, - .find_smp_config = default_find_smp_config, - .get_smp_config = default_get_smp_config, + .find_mptable = mpparse_find_mptable, + .early_parse_smp_cfg = mpparse_parse_early_smp_config, + .parse_smp_cfg = mpparse_parse_smp_config, }, .irqs = { diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig index 87e3da7b0439..65ed14b6540b 100644 --- a/arch/x86/kvm/Kconfig +++ b/arch/x86/kvm/Kconfig @@ -80,9 +80,10 @@ config KVM_SW_PROTECTED_VM depends on KVM && X86_64 select KVM_GENERIC_PRIVATE_MEM help - Enable support for KVM software-protected VMs. Currently "protected" - means the VM can be backed with memory provided by - KVM_CREATE_GUEST_MEMFD. + Enable support for KVM software-protected VMs. Currently, software- + protected VMs are purely a development and testing vehicle for + KVM_CREATE_GUEST_MEMFD. Attempting to run a "real" VM workload as a + software-protected VM will fail miserably. If unsure, say "N". diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index 2d6cdeab1f8a..0544700ca50b 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -4405,6 +4405,31 @@ static int kvm_faultin_pfn(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault, fault->mmu_seq = vcpu->kvm->mmu_invalidate_seq; smp_rmb(); + /* + * Check for a relevant mmu_notifier invalidation event before getting + * the pfn from the primary MMU, and before acquiring mmu_lock. + * + * For mmu_lock, if there is an in-progress invalidation and the kernel + * allows preemption, the invalidation task may drop mmu_lock and yield + * in response to mmu_lock being contended, which is *very* counter- + * productive as this vCPU can't actually make forward progress until + * the invalidation completes. + * + * Retrying now can also avoid unnessary lock contention in the primary + * MMU, as the primary MMU doesn't necessarily hold a single lock for + * the duration of the invalidation, i.e. faulting in a conflicting pfn + * can cause the invalidation to take longer by holding locks that are + * needed to complete the invalidation. + * + * Do the pre-check even for non-preemtible kernels, i.e. even if KVM + * will never yield mmu_lock in response to contention, as this vCPU is + * *guaranteed* to need to retry, i.e. waiting until mmu_lock is held + * to detect retry guarantees the worst case latency for the vCPU. + */ + if (fault->slot && + mmu_invalidate_retry_gfn_unsafe(vcpu->kvm, fault->mmu_seq, fault->gfn)) + return RET_PF_RETRY; + ret = __kvm_faultin_pfn(vcpu, fault); if (ret != RET_PF_CONTINUE) return ret; @@ -4415,6 +4440,18 @@ static int kvm_faultin_pfn(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault, if (unlikely(!fault->slot)) return kvm_handle_noslot_fault(vcpu, fault, access); + /* + * Check again for a relevant mmu_notifier invalidation event purely to + * avoid contending mmu_lock. Most invalidations will be detected by + * the previous check, but checking is extremely cheap relative to the + * overall cost of failing to detect the invalidation until after + * mmu_lock is acquired. + */ + if (mmu_invalidate_retry_gfn_unsafe(vcpu->kvm, fault->mmu_seq, fault->gfn)) { + kvm_release_pfn_clean(fault->pfn); + return RET_PF_RETRY; + } + return RET_PF_CONTINUE; } @@ -4442,6 +4479,11 @@ static bool is_page_fault_stale(struct kvm_vcpu *vcpu, if (!sp && kvm_test_request(KVM_REQ_MMU_FREE_OBSOLETE_ROOTS, vcpu)) return true; + /* + * Check for a relevant mmu_notifier invalidation event one last time + * now that mmu_lock is held, as the "unsafe" checks performed without + * holding mmu_lock can get false negatives. + */ return fault->slot && mmu_invalidate_retry_gfn(vcpu->kvm, fault->mmu_seq, fault->gfn); } diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c index f760106c31f8..a8ce5226b3b5 100644 --- a/arch/x86/kvm/svm/sev.c +++ b/arch/x86/kvm/svm/sev.c @@ -57,7 +57,7 @@ static bool sev_es_enabled = true; module_param_named(sev_es, sev_es_enabled, bool, 0444); /* enable/disable SEV-ES DebugSwap support */ -static bool sev_es_debug_swap_enabled = true; +static bool sev_es_debug_swap_enabled = false; module_param_named(debug_swap, sev_es_debug_swap_enabled, bool, 0444); #else #define sev_enabled false @@ -612,8 +612,11 @@ static int sev_es_sync_vmsa(struct vcpu_svm *svm) save->xss = svm->vcpu.arch.ia32_xss; save->dr6 = svm->vcpu.arch.dr6; - if (sev_es_debug_swap_enabled) + if (sev_es_debug_swap_enabled) { save->sev_features |= SVM_SEV_FEAT_DEBUG_SWAP; + pr_warn_once("Enabling DebugSwap with KVM_SEV_ES_INIT. " + "This will not work starting with Linux 6.10\n"); + } pr_debug("Virtual Machine Save Area (VMSA):\n"); print_hex_dump_debug("", DUMP_PREFIX_NONE, 16, 1, save, sizeof(*save), false); @@ -1975,20 +1978,22 @@ int sev_mem_enc_register_region(struct kvm *kvm, goto e_free; } - region->uaddr = range->addr; - region->size = range->size; - - list_add_tail(®ion->list, &sev->regions_list); - mutex_unlock(&kvm->lock); - /* * The guest may change the memory encryption attribute from C=0 -> C=1 * or vice versa for this memory range. Lets make sure caches are * flushed to ensure that guest data gets written into memory with - * correct C-bit. + * correct C-bit. Note, this must be done before dropping kvm->lock, + * as region and its array of pages can be freed by a different task + * once kvm->lock is released. */ sev_clflush_pages(region->pages, region->npages); + region->uaddr = range->addr; + region->size = range->size; + + list_add_tail(®ion->list, &sev->regions_list); + mutex_unlock(&kvm->lock); + return ret; e_free: diff --git a/arch/x86/kvm/vmx/run_flags.h b/arch/x86/kvm/vmx/run_flags.h index edc3f16cc189..6a9bfdfbb6e5 100644 --- a/arch/x86/kvm/vmx/run_flags.h +++ b/arch/x86/kvm/vmx/run_flags.h @@ -2,7 +2,10 @@ #ifndef __KVM_X86_VMX_RUN_FLAGS_H #define __KVM_X86_VMX_RUN_FLAGS_H -#define VMX_RUN_VMRESUME (1 << 0) -#define VMX_RUN_SAVE_SPEC_CTRL (1 << 1) +#define VMX_RUN_VMRESUME_SHIFT 0 +#define VMX_RUN_SAVE_SPEC_CTRL_SHIFT 1 + +#define VMX_RUN_VMRESUME BIT(VMX_RUN_VMRESUME_SHIFT) +#define VMX_RUN_SAVE_SPEC_CTRL BIT(VMX_RUN_SAVE_SPEC_CTRL_SHIFT) #endif /* __KVM_X86_VMX_RUN_FLAGS_H */ diff --git a/arch/x86/kvm/vmx/vmenter.S b/arch/x86/kvm/vmx/vmenter.S index 906ecd001511..2bfbf758d061 100644 --- a/arch/x86/kvm/vmx/vmenter.S +++ b/arch/x86/kvm/vmx/vmenter.S @@ -139,7 +139,7 @@ SYM_FUNC_START(__vmx_vcpu_run) mov (%_ASM_SP), %_ASM_AX /* Check if vmlaunch or vmresume is needed */ - test $VMX_RUN_VMRESUME, %ebx + bt $VMX_RUN_VMRESUME_SHIFT, %ebx /* Load guest registers. Don't clobber flags. */ mov VCPU_RCX(%_ASM_AX), %_ASM_CX @@ -161,8 +161,11 @@ SYM_FUNC_START(__vmx_vcpu_run) /* Load guest RAX. This kills the @regs pointer! */ mov VCPU_RAX(%_ASM_AX), %_ASM_AX - /* Check EFLAGS.ZF from 'test VMX_RUN_VMRESUME' above */ - jz .Lvmlaunch + /* Clobbers EFLAGS.ZF */ + CLEAR_CPU_BUFFERS + + /* Check EFLAGS.CF from the VMX_RUN_VMRESUME bit test above. */ + jnc .Lvmlaunch /* * After a successful VMRESUME/VMLAUNCH, control flow "magically" diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index 1111d9d08903..5b8fae9c1f82 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -38,6 +38,7 @@ #include <asm/desc.h> #include <asm/fpu/api.h> #include <asm/fpu/xstate.h> +#include <asm/fred.h> #include <asm/idtentry.h> #include <asm/io.h> #include <asm/irq_remapping.h> @@ -388,7 +389,16 @@ static __always_inline void vmx_enable_fb_clear(struct vcpu_vmx *vmx) static void vmx_update_fb_clear_dis(struct kvm_vcpu *vcpu, struct vcpu_vmx *vmx) { - vmx->disable_fb_clear = (host_arch_capabilities & ARCH_CAP_FB_CLEAR_CTRL) && + /* + * Disable VERW's behavior of clearing CPU buffers for the guest if the + * CPU isn't affected by MDS/TAA, and the host hasn't forcefully enabled + * the mitigation. Disabling the clearing behavior provides a + * performance boost for guests that aren't aware that manually clearing + * CPU buffers is unnecessary, at the cost of MSR accesses on VM-Entry + * and VM-Exit. + */ + vmx->disable_fb_clear = !cpu_feature_enabled(X86_FEATURE_CLEAR_CPU_BUF) && + (host_arch_capabilities & ARCH_CAP_FB_CLEAR_CTRL) && !boot_cpu_has_bug(X86_BUG_MDS) && !boot_cpu_has_bug(X86_BUG_TAA); @@ -6960,14 +6970,16 @@ static void handle_external_interrupt_irqoff(struct kvm_vcpu *vcpu) { u32 intr_info = vmx_get_intr_info(vcpu); unsigned int vector = intr_info & INTR_INFO_VECTOR_MASK; - gate_desc *desc = (gate_desc *)host_idt_base + vector; if (KVM_BUG(!is_external_intr(intr_info), vcpu->kvm, "unexpected VM-Exit interrupt info: 0x%x", intr_info)) return; kvm_before_interrupt(vcpu, KVM_HANDLING_IRQ); - vmx_do_interrupt_irqoff(gate_offset(desc)); + if (cpu_feature_enabled(X86_FEATURE_FRED)) + fred_entry_from_kvm(EVENT_TYPE_EXTINT, vector); + else + vmx_do_interrupt_irqoff(gate_offset((gate_desc *)host_idt_base + vector)); kvm_after_interrupt(vcpu); vcpu->arch.at_instruction_boundary = true; @@ -7224,11 +7236,14 @@ static noinstr void vmx_vcpu_enter_exit(struct kvm_vcpu *vcpu, guest_state_enter_irqoff(); - /* L1D Flush includes CPU buffer clear to mitigate MDS */ + /* + * L1D Flush includes CPU buffer clear to mitigate MDS, but VERW + * mitigation for MDS is done late in VMentry and is still + * executed in spite of L1D Flush. This is because an extra VERW + * should not matter much after the big hammer L1D Flush. + */ if (static_branch_unlikely(&vmx_l1d_should_flush)) vmx_l1d_flush(vcpu); - else if (static_branch_unlikely(&mds_user_clear)) - mds_clear_cpu_buffers(); else if (static_branch_unlikely(&mmio_stale_data_clear) && kvm_arch_has_assigned_device(vcpu->kvm)) mds_clear_cpu_buffers(); @@ -7260,7 +7275,10 @@ static noinstr void vmx_vcpu_enter_exit(struct kvm_vcpu *vcpu, if ((u16)vmx->exit_reason.basic == EXIT_REASON_EXCEPTION_NMI && is_nmi(vmx_get_intr_info(vcpu))) { kvm_before_interrupt(vcpu, KVM_HANDLING_NMI); - vmx_do_nmi_irqoff(); + if (cpu_feature_enabled(X86_FEATURE_FRED)) + fred_entry_from_kvm(EVENT_TYPE_NMI, NMI_VECTOR); + else + vmx_do_nmi_irqoff(); kvm_after_interrupt(vcpu); } diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 48a61d283406..e02cc710f56d 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -4580,7 +4580,7 @@ static bool kvm_is_vm_type_supported(unsigned long type) { return type == KVM_X86_DEFAULT_VM || (type == KVM_X86_SW_PROTECTED_VM && - IS_ENABLED(CONFIG_KVM_SW_PROTECTED_VM) && tdp_enabled); + IS_ENABLED(CONFIG_KVM_SW_PROTECTED_VM) && tdp_mmu_enabled); } int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) @@ -8007,6 +8007,16 @@ static int emulator_cmpxchg_emulated(struct x86_emulate_ctxt *ctxt, if (r < 0) return X86EMUL_UNHANDLEABLE; + + /* + * Mark the page dirty _before_ checking whether or not the CMPXCHG was + * successful, as the old value is written back on failure. Note, for + * live migration, this is unnecessarily conservative as CMPXCHG writes + * back the original value and the access is atomic, but KVM's ABI is + * that all writes are dirty logged, regardless of the value written. + */ + kvm_vcpu_mark_page_dirty(vcpu, gpa_to_gfn(gpa)); + if (r) return X86EMUL_CMPXCHG_FAILED; diff --git a/arch/x86/lib/x86-opcode-map.txt b/arch/x86/lib/x86-opcode-map.txt index 5168ee0360b2..12af572201a2 100644 --- a/arch/x86/lib/x86-opcode-map.txt +++ b/arch/x86/lib/x86-opcode-map.txt @@ -1051,8 +1051,8 @@ GrpTable: Grp6 EndTable GrpTable: Grp7 -0: SGDT Ms | VMCALL (001),(11B) | VMLAUNCH (010),(11B) | VMRESUME (011),(11B) | VMXOFF (100),(11B) | PCONFIG (101),(11B) | ENCLV (000),(11B) -1: SIDT Ms | MONITOR (000),(11B) | MWAIT (001),(11B) | CLAC (010),(11B) | STAC (011),(11B) | ENCLS (111),(11B) +0: SGDT Ms | VMCALL (001),(11B) | VMLAUNCH (010),(11B) | VMRESUME (011),(11B) | VMXOFF (100),(11B) | PCONFIG (101),(11B) | ENCLV (000),(11B) | WRMSRNS (110),(11B) +1: SIDT Ms | MONITOR (000),(11B) | MWAIT (001),(11B) | CLAC (010),(11B) | STAC (011),(11B) | ENCLS (111),(11B) | ERETU (F3),(010),(11B) | ERETS (F2),(010),(11B) 2: LGDT Ms | XGETBV (000),(11B) | XSETBV (001),(11B) | VMFUNC (100),(11B) | XEND (101)(11B) | XTEST (110)(11B) | ENCLU (111),(11B) 3: LIDT Ms 4: SMSW Mw/Rv diff --git a/arch/x86/mm/amdtopology.c b/arch/x86/mm/amdtopology.c index b3ca7d23e4b0..9332b36a1091 100644 --- a/arch/x86/mm/amdtopology.c +++ b/arch/x86/mm/amdtopology.c @@ -54,13 +54,11 @@ static __init int find_northbridge(void) int __init amd_numa_init(void) { - u64 start = PFN_PHYS(0); + unsigned int numnodes, cores, apicid; + u64 prevbase, start = PFN_PHYS(0); u64 end = PFN_PHYS(max_pfn); - unsigned numnodes; - u64 prevbase; - int i, j, nb; u32 nodeid, reg; - unsigned int bits, cores, apicid_base; + int i, j, nb; if (!early_pci_allowed()) return -EINVAL; @@ -158,26 +156,18 @@ int __init amd_numa_init(void) return -ENOENT; /* - * We seem to have valid NUMA configuration. Map apicids to nodes - * using the coreid bits from early_identify_cpu. + * We seem to have valid NUMA configuration. Map apicids to nodes + * using the size of the core domain in the APIC space. */ - bits = boot_cpu_data.x86_coreid_bits; - cores = 1 << bits; - apicid_base = 0; + cores = topology_get_domain_size(TOPO_CORE_DOMAIN); - /* - * get boot-time SMP configuration: - */ - early_get_smp_config(); + apicid = boot_cpu_physical_apicid; + if (apicid > 0) + pr_info("BSP APIC ID: %02x\n", apicid); - if (boot_cpu_physical_apicid > 0) { - pr_info("BSP APIC ID: %02x\n", boot_cpu_physical_apicid); - apicid_base = boot_cpu_physical_apicid; + for_each_node_mask(i, numa_nodes_parsed) { + for (j = 0; j < cores; j++, apicid++) + set_apicid_to_node(apicid, i); } - - for_each_node_mask(i, numa_nodes_parsed) - for (j = apicid_base; j < cores + apicid_base; j++) - set_apicid_to_node((i << bits) + j, i); - return 0; } diff --git a/arch/x86/mm/extable.c b/arch/x86/mm/extable.c index 271dcb2deabc..b522933bfa56 100644 --- a/arch/x86/mm/extable.c +++ b/arch/x86/mm/extable.c @@ -6,6 +6,7 @@ #include <xen/xen.h> #include <asm/fpu/api.h> +#include <asm/fred.h> #include <asm/sev.h> #include <asm/traps.h> #include <asm/kdebug.h> @@ -223,6 +224,79 @@ static bool ex_handler_ucopy_len(const struct exception_table_entry *fixup, return ex_handler_uaccess(fixup, regs, trapnr, fault_address); } +#ifdef CONFIG_X86_FRED +static bool ex_handler_eretu(const struct exception_table_entry *fixup, + struct pt_regs *regs, unsigned long error_code) +{ + struct pt_regs *uregs = (struct pt_regs *)(regs->sp - offsetof(struct pt_regs, orig_ax)); + unsigned short ss = uregs->ss; + unsigned short cs = uregs->cs; + + /* + * Move the NMI bit from the invalid stack frame, which caused ERETU + * to fault, to the fault handler's stack frame, thus to unblock NMI + * with the fault handler's ERETS instruction ASAP if NMI is blocked. + */ + regs->fred_ss.nmi = uregs->fred_ss.nmi; + + /* + * Sync event information to uregs, i.e., the ERETU return frame, but + * is it safe to write to the ERETU return frame which is just above + * current event stack frame? + * + * The RSP used by FRED to push a stack frame is not the value in %rsp, + * it is calculated from %rsp with the following 2 steps: + * 1) RSP = %rsp - (IA32_FRED_CONFIG & 0x1c0) // Reserve N*64 bytes + * 2) RSP = RSP & ~0x3f // Align to a 64-byte cache line + * when an event delivery doesn't trigger a stack level change. + * + * Here is an example with N*64 (N=1) bytes reserved: + * + * 64-byte cache line ==> ______________ + * |___Reserved___| + * |__Event_data__| + * |_____SS_______| + * |_____RSP______| + * |_____FLAGS____| + * |_____CS_______| + * |_____IP_______| + * 64-byte cache line ==> |__Error_code__| <== ERETU return frame + * |______________| + * |______________| + * |______________| + * |______________| + * |______________| + * |______________| + * |______________| + * 64-byte cache line ==> |______________| <== RSP after step 1) and 2) + * |___Reserved___| + * |__Event_data__| + * |_____SS_______| + * |_____RSP______| + * |_____FLAGS____| + * |_____CS_______| + * |_____IP_______| + * 64-byte cache line ==> |__Error_code__| <== ERETS return frame + * + * Thus a new FRED stack frame will always be pushed below a previous + * FRED stack frame ((N*64) bytes may be reserved between), and it is + * safe to write to a previous FRED stack frame as they never overlap. + */ + fred_info(uregs)->edata = fred_event_data(regs); + uregs->ssx = regs->ssx; + uregs->fred_ss.ss = ss; + /* The NMI bit was moved away above */ + uregs->fred_ss.nmi = 0; + uregs->csx = regs->csx; + uregs->fred_cs.sl = 0; + uregs->fred_cs.wfe = 0; + uregs->cs = cs; + uregs->orig_ax = error_code; + + return ex_handler_default(fixup, regs); +} +#endif + int ex_get_fixup_type(unsigned long ip) { const struct exception_table_entry *e = search_exception_tables(ip); @@ -300,6 +374,10 @@ int fixup_exception(struct pt_regs *regs, int trapnr, unsigned long error_code, return ex_handler_ucopy_len(e, regs, trapnr, fault_addr, reg, imm); case EX_TYPE_ZEROPAD: return ex_handler_zeropad(e, regs, fault_addr); +#ifdef CONFIG_X86_FRED + case EX_TYPE_ERETU: + return ex_handler_eretu(e, regs, error_code); +#endif } BUG(); } diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index 679b09cfe241..e1ac86396446 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -34,6 +34,7 @@ #include <asm/kvm_para.h> /* kvm_handle_async_pf */ #include <asm/vdso.h> /* fixup_vdso_exception() */ #include <asm/irq_stack.h> +#include <asm/fred.h> #define CREATE_TRACE_POINTS #include <asm/trace/exceptions.h> @@ -798,15 +799,6 @@ show_signal_msg(struct pt_regs *regs, unsigned long error_code, show_opcodes(regs, loglvl); } -/* - * The (legacy) vsyscall page is the long page in the kernel portion - * of the address space that has user-accessible permissions. - */ -static bool is_vsyscall_vaddr(unsigned long vaddr) -{ - return unlikely((vaddr & PAGE_MASK) == VSYSCALL_ADDR); -} - static void __bad_area_nosemaphore(struct pt_regs *regs, unsigned long error_code, unsigned long address, u32 pkey, int si_code) @@ -1518,8 +1510,10 @@ handle_page_fault(struct pt_regs *regs, unsigned long error_code, DEFINE_IDTENTRY_RAW_ERRORCODE(exc_page_fault) { - unsigned long address = read_cr2(); irqentry_state_t state; + unsigned long address; + + address = cpu_feature_enabled(X86_FEATURE_FRED) ? fred_event_data(regs) : read_cr2(); prefetchw(¤t->mm->mmap_lock); diff --git a/arch/x86/mm/maccess.c b/arch/x86/mm/maccess.c index 6993f026adec..42115ac079cf 100644 --- a/arch/x86/mm/maccess.c +++ b/arch/x86/mm/maccess.c @@ -3,6 +3,8 @@ #include <linux/uaccess.h> #include <linux/kernel.h> +#include <asm/vsyscall.h> + #ifdef CONFIG_X86_64 bool copy_from_kernel_nofault_allowed(const void *unsafe_src, size_t size) { @@ -16,6 +18,14 @@ bool copy_from_kernel_nofault_allowed(const void *unsafe_src, size_t size) return false; /* + * Reading from the vsyscall page may cause an unhandled fault in + * certain cases. Though it is at an address above TASK_SIZE_MAX, it is + * usually considered as a user space address. + */ + if (is_vsyscall_vaddr(vaddr)) + return false; + + /* * Allow everything during early boot before 'x86_virt_bits' * is initialized. Needed for instruction decoding in early * exception handlers. diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c index adc497b93f03..65e9a6e391c0 100644 --- a/arch/x86/mm/numa.c +++ b/arch/x86/mm/numa.c @@ -934,7 +934,7 @@ static int __init cmp_memblk(const void *a, const void *b) const struct numa_memblk *ma = *(const struct numa_memblk **)a; const struct numa_memblk *mb = *(const struct numa_memblk **)b; - return ma->start - mb->start; + return (ma->start > mb->start) - (ma->start < mb->start); } static struct numa_memblk *numa_memblk_list[NR_NODE_MEMBLKS] __initdata; @@ -944,14 +944,12 @@ static struct numa_memblk *numa_memblk_list[NR_NODE_MEMBLKS] __initdata; * @start: address to begin fill * @end: address to end fill * - * Find and extend numa_meminfo memblks to cover the @start-@end - * physical address range, such that the first memblk includes - * @start, the last memblk includes @end, and any gaps in between - * are filled. + * Find and extend numa_meminfo memblks to cover the physical + * address range @start-@end * * RETURNS: * 0 : Success - * NUMA_NO_MEMBLK : No memblk exists in @start-@end range + * NUMA_NO_MEMBLK : No memblks exist in address range @start-@end */ int __init numa_fill_memblks(u64 start, u64 end) @@ -963,17 +961,14 @@ int __init numa_fill_memblks(u64 start, u64 end) /* * Create a list of pointers to numa_meminfo memblks that - * overlap start, end. Exclude (start == bi->end) since - * end addresses in both a CFMWS range and a memblk range - * are exclusive. - * - * This list of pointers is used to make in-place changes - * that fill out the numa_meminfo memblks. + * overlap start, end. The list is used to make in-place + * changes that fill out the numa_meminfo memblks. */ for (int i = 0; i < mi->nr_blks; i++) { struct numa_memblk *bi = &mi->blk[i]; - if (start < bi->end && end >= bi->start) { + if (memblock_addrs_overlap(start, end - start, bi->start, + bi->end - bi->start)) { blk[count] = &mi->blk[i]; count++; } diff --git a/arch/x86/mm/pat/set_memory.c b/arch/x86/mm/pat/set_memory.c index e9b448d1b1b7..102880404046 100644 --- a/arch/x86/mm/pat/set_memory.c +++ b/arch/x86/mm/pat/set_memory.c @@ -755,10 +755,14 @@ pmd_t *lookup_pmd_address(unsigned long address) * areas on 32-bit NUMA systems. The percpu areas can * end up in this kind of memory, for instance. * - * This could be optimized, but it is only intended to be - * used at initialization time, and keeping it - * unoptimized should increase the testing coverage for - * the more obscure platforms. + * Note that as long as the PTEs are well-formed with correct PFNs, this + * works without checking the PRESENT bit in the leaf PTE. This is unlike + * the similar vmalloc_to_page() and derivatives. Callers may depend on + * this behavior. + * + * This could be optimized, but it is only used in paths that are not perf + * sensitive, and keeping it unoptimized should increase the testing coverage + * for the more obscure platforms. */ phys_addr_t slow_virt_to_phys(void *__virt_addr) { @@ -2041,17 +2045,12 @@ int set_mce_nospec(unsigned long pfn) return rc; } -static int set_memory_p(unsigned long *addr, int numpages) -{ - return change_page_attr_set(addr, numpages, __pgprot(_PAGE_PRESENT), 0); -} - /* Restore full speculative operation to the pfn. */ int clear_mce_nospec(unsigned long pfn) { unsigned long addr = (unsigned long) pfn_to_kaddr(pfn); - return set_memory_p(&addr, 1); + return set_memory_p(addr, 1); } EXPORT_SYMBOL_GPL(clear_mce_nospec); #endif /* CONFIG_X86_64 */ @@ -2104,6 +2103,11 @@ int set_memory_np_noalias(unsigned long addr, int numpages) CPA_NO_CHECK_ALIAS, NULL); } +int set_memory_p(unsigned long addr, int numpages) +{ + return change_page_attr_set(&addr, numpages, __pgprot(_PAGE_PRESENT), 0); +} + int set_memory_4k(unsigned long addr, int numpages) { return change_page_attr_set_clr(&addr, numpages, __pgprot(0), diff --git a/arch/x86/platform/ce4100/ce4100.c b/arch/x86/platform/ce4100/ce4100.c index 40745664d92f..f32451bdcfdd 100644 --- a/arch/x86/platform/ce4100/ce4100.c +++ b/arch/x86/platform/ce4100/ce4100.c @@ -135,13 +135,13 @@ static void sdv_pci_init(void) */ void __init x86_ce4100_early_setup(void) { - x86_init.oem.arch_setup = sdv_arch_setup; - x86_init.resources.probe_roms = x86_init_noop; - x86_init.mpparse.get_smp_config = x86_init_uint_noop; - x86_init.mpparse.find_smp_config = x86_init_noop; - x86_init.mpparse.setup_ioapic_ids = setup_ioapic_ids_from_mpc_nocheck; - x86_init.pci.init = ce4100_pci_init; - x86_init.pci.init_irq = sdv_pci_init; + x86_init.oem.arch_setup = sdv_arch_setup; + x86_init.resources.probe_roms = x86_init_noop; + x86_init.mpparse.find_mptable = x86_init_noop; + x86_init.mpparse.early_parse_smp_cfg = x86_init_noop; + x86_init.mpparse.parse_smp_cfg = x86_dtb_parse_smp_config; + x86_init.pci.init = ce4100_pci_init; + x86_init.pci.init_irq = sdv_pci_init; /* * By default, the reboot method is ACPI which is supported by the diff --git a/arch/x86/platform/intel-mid/intel-mid.c b/arch/x86/platform/intel-mid/intel-mid.c index f4592dc7a1c1..7be71c2cdc83 100644 --- a/arch/x86/platform/intel-mid/intel-mid.c +++ b/arch/x86/platform/intel-mid/intel-mid.c @@ -118,7 +118,8 @@ void __init x86_intel_mid_early_setup(void) machine_ops.emergency_restart = intel_mid_reboot; /* Avoid searching for BIOS MP tables */ - x86_init.mpparse.find_smp_config = x86_init_noop; - x86_init.mpparse.get_smp_config = x86_init_uint_noop; + x86_init.mpparse.find_mptable = x86_init_noop; + x86_init.mpparse.early_parse_smp_cfg = x86_init_noop; + x86_init.mpparse.parse_smp_cfg = x86_init_noop; set_bit(MP_BUS_ISA, mp_bus_not_pci); } diff --git a/arch/x86/xen/apic.c b/arch/x86/xen/apic.c index 9dd5490b3318..8b045dd25196 100644 --- a/arch/x86/xen/apic.c +++ b/arch/x86/xen/apic.c @@ -33,12 +33,6 @@ static unsigned int xen_io_apic_read(unsigned apic, unsigned reg) return 0xfd; } -static u32 xen_set_apic_id(u32 x) -{ - WARN_ON(1); - return x; -} - static u32 xen_get_apic_id(u32 x) { return ((x)>>24) & 0xFFu; @@ -49,20 +43,20 @@ static u32 xen_apic_read(u32 reg) struct xen_platform_op op = { .cmd = XENPF_get_cpuinfo, .interface_version = XENPF_INTERFACE_VERSION, - .u.pcpu_info.xen_cpuid = 0, }; - int ret; - - /* Shouldn't need this as APIC is turned off for PV, and we only - * get called on the bootup processor. But just in case. */ - if (!xen_initial_domain() || smp_processor_id()) - return 0; + int ret, cpu; if (reg == APIC_LVR) return 0x14; if (reg != APIC_ID) return 0; + cpu = smp_processor_id(); + if (!xen_initial_domain()) + return cpu ? cpuid_to_apicid[cpu] << 24 : 0; + + op.u.pcpu_info.xen_cpuid = cpu; + ret = HYPERVISOR_platform_op(&op); if (ret) op.u.pcpu_info.apic_id = BAD_APICID; @@ -110,11 +104,6 @@ static int xen_madt_oem_check(char *oem_id, char *oem_table_id) return xen_pv_domain(); } -static u32 xen_phys_pkg_id(u32 initial_apic_id, int index_msb) -{ - return initial_apic_id >> index_msb; -} - static u32 xen_cpu_present_to_apicid(int cpu) { if (cpu_present(cpu)) @@ -133,11 +122,9 @@ static struct apic xen_pv_apic __ro_after_init = { .disable_esr = 0, .cpu_present_to_apicid = xen_cpu_present_to_apicid, - .phys_pkg_id = xen_phys_pkg_id, /* detect_ht */ .max_apic_id = UINT_MAX, .get_apic_id = xen_get_apic_id, - .set_apic_id = xen_set_apic_id, .calc_dest_apicid = apic_flat_calc_apicid, diff --git a/arch/x86/xen/enlighten_hvm.c b/arch/x86/xen/enlighten_hvm.c index 3f8c34707c50..99a68fa71dbe 100644 --- a/arch/x86/xen/enlighten_hvm.c +++ b/arch/x86/xen/enlighten_hvm.c @@ -168,7 +168,7 @@ static int xen_cpu_up_prepare_hvm(unsigned int cpu) */ xen_uninit_lock_cpu(cpu); - if (cpu_acpi_id(cpu) != U32_MAX) + if (cpu_acpi_id(cpu) != CPU_ACPIID_INVALID) per_cpu(xen_vcpu_id, cpu) = cpu_acpi_id(cpu); else per_cpu(xen_vcpu_id, cpu) = cpu; diff --git a/arch/x86/xen/enlighten_pv.c b/arch/x86/xen/enlighten_pv.c index aeb33e0a3f76..ace2eb054053 100644 --- a/arch/x86/xen/enlighten_pv.c +++ b/arch/x86/xen/enlighten_pv.c @@ -200,6 +200,9 @@ static void __init xen_pv_init_platform(void) xen_set_mtrr_data(); else mtrr_overwrite_state(NULL, 0, MTRR_TYPE_WRBACK); + + /* Adjust nr_cpu_ids before "enumeration" happens */ + xen_smp_count_cpus(); } static void __init xen_pv_guest_late_init(void) diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c index 1fb9a1644d94..935771726f9c 100644 --- a/arch/x86/xen/smp.c +++ b/arch/x86/xen/smp.c @@ -135,8 +135,6 @@ void __init xen_smp_cpus_done(unsigned int max_cpus) { if (xen_hvm_domain()) native_smp_cpus_done(max_cpus); - else - calculate_max_logical_packages(); } void xen_smp_send_reschedule(int cpu) diff --git a/arch/x86/xen/smp.h b/arch/x86/xen/smp.h index c20cbb14c82b..b8efdbc693f7 100644 --- a/arch/x86/xen/smp.h +++ b/arch/x86/xen/smp.h @@ -19,6 +19,7 @@ extern void xen_smp_intr_free(unsigned int cpu); int xen_smp_intr_init_pv(unsigned int cpu); void xen_smp_intr_free_pv(unsigned int cpu); +void xen_smp_count_cpus(void); void xen_smp_cpus_done(unsigned int max_cpus); void xen_smp_send_reschedule(int cpu); @@ -44,6 +45,7 @@ static inline int xen_smp_intr_init_pv(unsigned int cpu) return 0; } static inline void xen_smp_intr_free_pv(unsigned int cpu) {} +static inline void xen_smp_count_cpus(void) { } #endif /* CONFIG_SMP */ #endif diff --git a/arch/x86/xen/smp_pv.c b/arch/x86/xen/smp_pv.c index a0f07bbfcd6e..27d1a5b7f571 100644 --- a/arch/x86/xen/smp_pv.c +++ b/arch/x86/xen/smp_pv.c @@ -29,6 +29,7 @@ #include <asm/idtentry.h> #include <asm/desc.h> #include <asm/cpu.h> +#include <asm/apic.h> #include <asm/io_apic.h> #include <xen/interface/xen.h> @@ -73,7 +74,6 @@ static void cpu_bringup(void) } cpu = smp_processor_id(); smp_store_cpu_info(cpu); - cpu_data(cpu).x86_max_cores = 1; set_cpu_sibling_map(cpu); speculative_store_bypass_ht_init(); @@ -149,39 +149,16 @@ int xen_smp_intr_init_pv(unsigned int cpu) return rc; } -static void __init _get_smp_config(unsigned int early) +static void __init xen_pv_smp_config(void) { - int i, rc; - unsigned int subtract = 0; - - if (early) - return; - - num_processors = 0; - disabled_cpus = 0; - for (i = 0; i < nr_cpu_ids; i++) { - rc = HYPERVISOR_vcpu_op(VCPUOP_is_up, i, NULL); - if (rc >= 0) { - num_processors++; - set_cpu_possible(i, true); - } else { - set_cpu_possible(i, false); - set_cpu_present(i, false); - subtract++; - } - } -#ifdef CONFIG_HOTPLUG_CPU - /* This is akin to using 'nr_cpus' on the Linux command line. - * Which is OK as when we use 'dom0_max_vcpus=X' we can only - * have up to X, while nr_cpu_ids is greater than X. This - * normally is not a problem, except when CPU hotplugging - * is involved and then there might be more than X CPUs - * in the guest - which will not work as there is no - * hypercall to expand the max number of VCPUs an already - * running guest has. So cap it up to X. */ - if (subtract) - set_nr_cpu_ids(nr_cpu_ids - subtract); -#endif + u32 apicid = 0; + int i; + + topology_register_boot_apic(apicid++); + + for (i = 1; i < nr_cpu_ids; i++) + topology_register_apic(apicid++, CPU_ACPIID_INVALID, true); + /* Pretend to be a proper enumerated system */ smp_found_config = 1; } @@ -224,8 +201,6 @@ static void __init xen_pv_smp_prepare_cpus(unsigned int max_cpus) smp_prepare_cpus_common(); - cpu_data(0).x86_max_cores = 1; - speculative_store_bypass_ht_init(); xen_pmu_init(0); @@ -434,6 +409,20 @@ static irqreturn_t xen_irq_work_interrupt(int irq, void *dev_id) return IRQ_HANDLED; } +void __init xen_smp_count_cpus(void) +{ + unsigned int cpus; + + for (cpus = 0; cpus < nr_cpu_ids; cpus++) { + if (HYPERVISOR_vcpu_op(VCPUOP_is_up, cpus, NULL) < 0) + break; + } + + pr_info("Xen PV: Detected %u vCPUS\n", cpus); + if (cpus < nr_cpu_ids) + set_nr_cpu_ids(cpus); +} + static const struct smp_ops xen_smp_ops __initconst = { .smp_prepare_boot_cpu = xen_pv_smp_prepare_boot_cpu, .smp_prepare_cpus = xen_pv_smp_prepare_cpus, @@ -458,6 +447,12 @@ void __init xen_smp_init(void) smp_ops = xen_smp_ops; /* Avoid searching for BIOS MP tables */ - x86_init.mpparse.find_smp_config = x86_init_noop; - x86_init.mpparse.get_smp_config = _get_smp_config; + x86_init.mpparse.find_mptable = x86_init_noop; + x86_init.mpparse.early_parse_smp_cfg = x86_init_noop; + + /* XEN/PV Dom0 has halfways sane topology information via CPUID/MADT */ + if (xen_initial_domain()) + x86_init.mpparse.parse_smp_cfg = x86_init_noop; + else + x86_init.mpparse.parse_smp_cfg = xen_pv_smp_config; } diff --git a/arch/x86/xen/xen-head.S b/arch/x86/xen/xen-head.S index a0ea285878db..04101b984f24 100644 --- a/arch/x86/xen/xen-head.S +++ b/arch/x86/xen/xen-head.S @@ -49,7 +49,7 @@ SYM_CODE_START(startup_xen) ANNOTATE_NOENDBR cld - leaq (__end_init_task - PTREGS_SIZE)(%rip), %rsp + leaq (__end_init_task - TOP_OF_KERNEL_STACK_PADDING - PTREGS_SIZE)(%rip), %rsp /* Set up %gs. * diff --git a/arch/xtensa/platforms/iss/simdisk.c b/arch/xtensa/platforms/iss/simdisk.c index 178cf96ca10a..defc67909a9c 100644 --- a/arch/xtensa/platforms/iss/simdisk.c +++ b/arch/xtensa/platforms/iss/simdisk.c @@ -264,16 +264,18 @@ static int __init simdisk_setup(struct simdisk *dev, int which, struct proc_dir_entry *procdir) { char tmp[2] = { '0' + which, 0 }; - int err = -ENOMEM; + int err; dev->fd = -1; dev->filename = NULL; spin_lock_init(&dev->lock); dev->users = 0; - dev->gd = blk_alloc_disk(NUMA_NO_NODE); - if (!dev->gd) + dev->gd = blk_alloc_disk(NULL, NUMA_NO_NODE); + if (IS_ERR(dev->gd)) { + err = PTR_ERR(dev->gd); goto out; + } dev->gd->major = simdisk_major; dev->gd->first_minor = which; dev->gd->minors = SIMDISK_MINORS; |