diff options
Diffstat (limited to 'arch')
67 files changed, 463 insertions, 258 deletions
diff --git a/arch/arm/boot/dts/am33xx.dtsi b/arch/arm/boot/dts/am33xx.dtsi index 5b213a1e68bb..5e33d0e88f5b 100644 --- a/arch/arm/boot/dts/am33xx.dtsi +++ b/arch/arm/boot/dts/am33xx.dtsi @@ -40,6 +40,9 @@ ethernet1 = &cpsw_emac1; spi0 = &spi0; spi1 = &spi1; + mmc0 = &mmc1; + mmc1 = &mmc2; + mmc2 = &mmc3; }; cpus { diff --git a/arch/arm/boot/dts/at91-sam9x60ek.dts b/arch/arm/boot/dts/at91-sam9x60ek.dts index 73b6b1f89de9..775ceb3acb6c 100644 --- a/arch/arm/boot/dts/at91-sam9x60ek.dts +++ b/arch/arm/boot/dts/at91-sam9x60ek.dts @@ -334,14 +334,6 @@ }; &pinctrl { - atmel,mux-mask = < - /* A B C */ - 0xFFFFFE7F 0xC0E0397F 0xEF00019D /* pioA */ - 0x03FFFFFF 0x02FC7E68 0x00780000 /* pioB */ - 0xffffffff 0xF83FFFFF 0xB800F3FC /* pioC */ - 0x003FFFFF 0x003F8000 0x00000000 /* pioD */ - >; - adc { pinctrl_adc_default: adc_default { atmel,pins = <AT91_PIOB 15 AT91_PERIPH_A AT91_PINCTRL_NONE>; diff --git a/arch/arm/boot/dts/at91-sama5d27_som1.dtsi b/arch/arm/boot/dts/at91-sama5d27_som1.dtsi index 1b1163858b1d..e3251f3e3eaa 100644 --- a/arch/arm/boot/dts/at91-sama5d27_som1.dtsi +++ b/arch/arm/boot/dts/at91-sama5d27_som1.dtsi @@ -84,8 +84,8 @@ pinctrl-0 = <&pinctrl_macb0_default>; phy-mode = "rmii"; - ethernet-phy@0 { - reg = <0x0>; + ethernet-phy@7 { + reg = <0x7>; interrupt-parent = <&pioA>; interrupts = <PIN_PD31 IRQ_TYPE_LEVEL_LOW>; pinctrl-names = "default"; diff --git a/arch/arm/boot/dts/imx6ul-14x14-evk.dtsi b/arch/arm/boot/dts/imx6ul-14x14-evk.dtsi index c593597b2119..5a1e10def6ef 100644 --- a/arch/arm/boot/dts/imx6ul-14x14-evk.dtsi +++ b/arch/arm/boot/dts/imx6ul-14x14-evk.dtsi @@ -210,9 +210,6 @@ micrel,led-mode = <1>; clocks = <&clks IMX6UL_CLK_ENET_REF>; clock-names = "rmii-ref"; - reset-gpios = <&gpio_spi 1 GPIO_ACTIVE_LOW>; - reset-assert-us = <10000>; - reset-deassert-us = <100>; }; @@ -222,9 +219,6 @@ micrel,led-mode = <1>; clocks = <&clks IMX6UL_CLK_ENET2_REF>; clock-names = "rmii-ref"; - reset-gpios = <&gpio_spi 2 GPIO_ACTIVE_LOW>; - reset-assert-us = <10000>; - reset-deassert-us = <100>; }; }; }; @@ -243,6 +237,22 @@ status = "okay"; }; +&gpio_spi { + eth0-phy-hog { + gpio-hog; + gpios = <1 GPIO_ACTIVE_HIGH>; + output-high; + line-name = "eth0-phy"; + }; + + eth1-phy-hog { + gpio-hog; + gpios = <2 GPIO_ACTIVE_HIGH>; + output-high; + line-name = "eth1-phy"; + }; +}; + &i2c1 { clock-frequency = <100000>; pinctrl-names = "default"; diff --git a/arch/arm/boot/dts/imx6ull-myir-mys-6ulx-eval.dts b/arch/arm/boot/dts/imx6ull-myir-mys-6ulx-eval.dts index ecbb2cc5b9ab..79cc45728cd2 100644 --- a/arch/arm/boot/dts/imx6ull-myir-mys-6ulx-eval.dts +++ b/arch/arm/boot/dts/imx6ull-myir-mys-6ulx-eval.dts @@ -14,5 +14,6 @@ }; &gpmi { + fsl,use-minimum-ecc; status = "okay"; }; diff --git a/arch/arm/boot/dts/sam9x60.dtsi b/arch/arm/boot/dts/sam9x60.dtsi index 84066c1298df..ec45ced3cde6 100644 --- a/arch/arm/boot/dts/sam9x60.dtsi +++ b/arch/arm/boot/dts/sam9x60.dtsi @@ -606,6 +606,15 @@ compatible = "microchip,sam9x60-pinctrl", "atmel,at91sam9x5-pinctrl", "atmel,at91rm9200-pinctrl", "simple-bus"; ranges = <0xfffff400 0xfffff400 0x800>; + /* mux-mask corresponding to sam9x60 SoC in TFBGA228L package */ + atmel,mux-mask = < + /* A B C */ + 0xffffffff 0xffe03fff 0xef00019d /* pioA */ + 0x03ffffff 0x02fc7e7f 0x00780000 /* pioB */ + 0xffffffff 0xffffffff 0xf83fffff /* pioC */ + 0x003fffff 0x003f8000 0x00000000 /* pioD */ + >; + pioA: gpio@fffff400 { compatible = "microchip,sam9x60-gpio", "atmel,at91sam9x5-gpio", "atmel,at91rm9200-gpio"; reg = <0xfffff400 0x200>; diff --git a/arch/arm/mach-imx/avic.c b/arch/arm/mach-imx/avic.c index 322caa21bcb3..21bce4049cec 100644 --- a/arch/arm/mach-imx/avic.c +++ b/arch/arm/mach-imx/avic.c @@ -7,6 +7,7 @@ #include <linux/module.h> #include <linux/irq.h> #include <linux/irqdomain.h> +#include <linux/irqchip.h> #include <linux/io.h> #include <linux/of.h> #include <linux/of_address.h> @@ -162,7 +163,7 @@ static void __exception_irq_entry avic_handle_irq(struct pt_regs *regs) * interrupts. It registers the interrupt enable and disable functions * to the kernel for each interrupt source. */ -void __init mxc_init_irq(void __iomem *irqbase) +static void __init mxc_init_irq(void __iomem *irqbase) { struct device_node *np; int irq_base; @@ -220,3 +221,16 @@ void __init mxc_init_irq(void __iomem *irqbase) printk(KERN_INFO "MXC IRQ initialized\n"); } + +static int __init imx_avic_init(struct device_node *node, + struct device_node *parent) +{ + void __iomem *avic_base; + + avic_base = of_iomap(node, 0); + BUG_ON(!avic_base); + mxc_init_irq(avic_base); + return 0; +} + +IRQCHIP_DECLARE(imx_avic, "fsl,avic", imx_avic_init); diff --git a/arch/arm/mach-imx/common.h b/arch/arm/mach-imx/common.h index 2b004cc4f95e..474dedb73bc7 100644 --- a/arch/arm/mach-imx/common.h +++ b/arch/arm/mach-imx/common.h @@ -22,7 +22,6 @@ void mx35_map_io(void); void imx21_init_early(void); void imx31_init_early(void); void imx35_init_early(void); -void mxc_init_irq(void __iomem *); void mx31_init_irq(void); void mx35_init_irq(void); void mxc_set_cpu_type(unsigned int type); diff --git a/arch/arm/mach-imx/mach-imx1.c b/arch/arm/mach-imx/mach-imx1.c index 32df3b8012f9..8eca92d66a2e 100644 --- a/arch/arm/mach-imx/mach-imx1.c +++ b/arch/arm/mach-imx/mach-imx1.c @@ -17,16 +17,6 @@ static void __init imx1_init_early(void) mxc_set_cpu_type(MXC_CPU_MX1); } -static void __init imx1_init_irq(void) -{ - void __iomem *avic_addr; - - avic_addr = ioremap(MX1_AVIC_ADDR, SZ_4K); - WARN_ON(!avic_addr); - - mxc_init_irq(avic_addr); -} - static const char * const imx1_dt_board_compat[] __initconst = { "fsl,imx1", NULL @@ -34,7 +24,6 @@ static const char * const imx1_dt_board_compat[] __initconst = { DT_MACHINE_START(IMX1_DT, "Freescale i.MX1 (Device Tree Support)") .init_early = imx1_init_early, - .init_irq = imx1_init_irq, .dt_compat = imx1_dt_board_compat, .restart = mxc_restart, MACHINE_END diff --git a/arch/arm/mach-imx/mach-imx25.c b/arch/arm/mach-imx/mach-imx25.c index 95de48a1aa7d..51927bd08aef 100644 --- a/arch/arm/mach-imx/mach-imx25.c +++ b/arch/arm/mach-imx/mach-imx25.c @@ -22,17 +22,6 @@ static void __init imx25_dt_init(void) imx_aips_allow_unprivileged_access("fsl,imx25-aips"); } -static void __init mx25_init_irq(void) -{ - struct device_node *np; - void __iomem *avic_base; - - np = of_find_compatible_node(NULL, NULL, "fsl,avic"); - avic_base = of_iomap(np, 0); - BUG_ON(!avic_base); - mxc_init_irq(avic_base); -} - static const char * const imx25_dt_board_compat[] __initconst = { "fsl,imx25", NULL @@ -42,6 +31,5 @@ DT_MACHINE_START(IMX25_DT, "Freescale i.MX25 (Device Tree Support)") .init_early = imx25_init_early, .init_machine = imx25_dt_init, .init_late = imx25_pm_init, - .init_irq = mx25_init_irq, .dt_compat = imx25_dt_board_compat, MACHINE_END diff --git a/arch/arm/mach-imx/mach-imx27.c b/arch/arm/mach-imx/mach-imx27.c index 262422a9c196..e325c9468105 100644 --- a/arch/arm/mach-imx/mach-imx27.c +++ b/arch/arm/mach-imx/mach-imx27.c @@ -56,17 +56,6 @@ static void __init imx27_init_early(void) mxc_set_cpu_type(MXC_CPU_MX27); } -static void __init mx27_init_irq(void) -{ - void __iomem *avic_base; - struct device_node *np; - - np = of_find_compatible_node(NULL, NULL, "fsl,avic"); - avic_base = of_iomap(np, 0); - BUG_ON(!avic_base); - mxc_init_irq(avic_base); -} - static const char * const imx27_dt_board_compat[] __initconst = { "fsl,imx27", NULL @@ -75,7 +64,6 @@ static const char * const imx27_dt_board_compat[] __initconst = { DT_MACHINE_START(IMX27_DT, "Freescale i.MX27 (Device Tree Support)") .map_io = mx27_map_io, .init_early = imx27_init_early, - .init_irq = mx27_init_irq, .init_late = imx27_pm_init, .dt_compat = imx27_dt_board_compat, MACHINE_END diff --git a/arch/arm/mach-imx/mach-imx31.c b/arch/arm/mach-imx/mach-imx31.c index dc69dfe600df..e9a1092b6093 100644 --- a/arch/arm/mach-imx/mach-imx31.c +++ b/arch/arm/mach-imx/mach-imx31.c @@ -14,6 +14,5 @@ static const char * const imx31_dt_board_compat[] __initconst = { DT_MACHINE_START(IMX31_DT, "Freescale i.MX31 (Device Tree Support)") .map_io = mx31_map_io, .init_early = imx31_init_early, - .init_irq = mx31_init_irq, .dt_compat = imx31_dt_board_compat, MACHINE_END diff --git a/arch/arm/mach-imx/mach-imx35.c b/arch/arm/mach-imx/mach-imx35.c index ec5c3068715c..0fc08218b77d 100644 --- a/arch/arm/mach-imx/mach-imx35.c +++ b/arch/arm/mach-imx/mach-imx35.c @@ -27,6 +27,5 @@ DT_MACHINE_START(IMX35_DT, "Freescale i.MX35 (Device Tree Support)") .l2c_aux_mask = ~0, .map_io = mx35_map_io, .init_early = imx35_init_early, - .init_irq = mx35_init_irq, .dt_compat = imx35_dt_board_compat, MACHINE_END diff --git a/arch/arm/mach-imx/mm-imx3.c b/arch/arm/mach-imx/mm-imx3.c index 5056438e5b42..28db97289ee8 100644 --- a/arch/arm/mach-imx/mm-imx3.c +++ b/arch/arm/mach-imx/mm-imx3.c @@ -109,18 +109,6 @@ void __init imx31_init_early(void) mx3_ccm_base = of_iomap(np, 0); BUG_ON(!mx3_ccm_base); } - -void __init mx31_init_irq(void) -{ - void __iomem *avic_base; - struct device_node *np; - - np = of_find_compatible_node(NULL, NULL, "fsl,imx31-avic"); - avic_base = of_iomap(np, 0); - BUG_ON(!avic_base); - - mxc_init_irq(avic_base); -} #endif /* ifdef CONFIG_SOC_IMX31 */ #ifdef CONFIG_SOC_IMX35 @@ -158,16 +146,4 @@ void __init imx35_init_early(void) mx3_ccm_base = of_iomap(np, 0); BUG_ON(!mx3_ccm_base); } - -void __init mx35_init_irq(void) -{ - void __iomem *avic_base; - struct device_node *np; - - np = of_find_compatible_node(NULL, NULL, "fsl,imx35-avic"); - avic_base = of_iomap(np, 0); - BUG_ON(!avic_base); - - mxc_init_irq(avic_base); -} #endif /* ifdef CONFIG_SOC_IMX35 */ diff --git a/arch/arm/mach-omap2/sr_device.c b/arch/arm/mach-omap2/sr_device.c index 62df666c2bd0..17b66f0d0dee 100644 --- a/arch/arm/mach-omap2/sr_device.c +++ b/arch/arm/mach-omap2/sr_device.c @@ -88,34 +88,26 @@ static void __init sr_set_nvalues(struct omap_volt_data *volt_data, extern struct omap_sr_data omap_sr_pdata[]; -static int __init sr_dev_init(struct omap_hwmod *oh, void *user) +static int __init sr_init_by_name(const char *name, const char *voltdm) { struct omap_sr_data *sr_data = NULL; struct omap_volt_data *volt_data; - struct omap_smartreflex_dev_attr *sr_dev_attr; static int i; - if (!strncmp(oh->name, "smartreflex_mpu_iva", 20) || - !strncmp(oh->name, "smartreflex_mpu", 16)) + if (!strncmp(name, "smartreflex_mpu_iva", 20) || + !strncmp(name, "smartreflex_mpu", 16)) sr_data = &omap_sr_pdata[OMAP_SR_MPU]; - else if (!strncmp(oh->name, "smartreflex_core", 17)) + else if (!strncmp(name, "smartreflex_core", 17)) sr_data = &omap_sr_pdata[OMAP_SR_CORE]; - else if (!strncmp(oh->name, "smartreflex_iva", 16)) + else if (!strncmp(name, "smartreflex_iva", 16)) sr_data = &omap_sr_pdata[OMAP_SR_IVA]; if (!sr_data) { - pr_err("%s: Unknown instance %s\n", __func__, oh->name); + pr_err("%s: Unknown instance %s\n", __func__, name); return -EINVAL; } - sr_dev_attr = (struct omap_smartreflex_dev_attr *)oh->dev_attr; - if (!sr_dev_attr || !sr_dev_attr->sensor_voltdm_name) { - pr_err("%s: No voltage domain specified for %s. Cannot initialize\n", - __func__, oh->name); - goto exit; - } - - sr_data->name = oh->name; + sr_data->name = name; if (cpu_is_omap343x()) sr_data->ip_type = 1; else @@ -136,10 +128,10 @@ static int __init sr_dev_init(struct omap_hwmod *oh, void *user) } } - sr_data->voltdm = voltdm_lookup(sr_dev_attr->sensor_voltdm_name); + sr_data->voltdm = voltdm_lookup(voltdm); if (!sr_data->voltdm) { pr_err("%s: Unable to get voltage domain pointer for VDD %s\n", - __func__, sr_dev_attr->sensor_voltdm_name); + __func__, voltdm); goto exit; } @@ -160,6 +152,20 @@ exit: return 0; } +static int __init sr_dev_init(struct omap_hwmod *oh, void *user) +{ + struct omap_smartreflex_dev_attr *sr_dev_attr; + + sr_dev_attr = (struct omap_smartreflex_dev_attr *)oh->dev_attr; + if (!sr_dev_attr || !sr_dev_attr->sensor_voltdm_name) { + pr_err("%s: No voltage domain specified for %s. Cannot initialize\n", + __func__, oh->name); + return 0; + } + + return sr_init_by_name(oh->name, sr_dev_attr->sensor_voltdm_name); +} + /* * API to be called from board files to enable smartreflex * autocompensation at init. @@ -169,7 +175,42 @@ void __init omap_enable_smartreflex_on_init(void) sr_enable_on_init = true; } +static const char * const omap4_sr_instances[] = { + "mpu", + "iva", + "core", +}; + +static const char * const dra7_sr_instances[] = { + "mpu", + "core", +}; + int __init omap_devinit_smartreflex(void) { + const char * const *sr_inst; + int i, nr_sr = 0; + + if (soc_is_omap44xx()) { + sr_inst = omap4_sr_instances; + nr_sr = ARRAY_SIZE(omap4_sr_instances); + + } else if (soc_is_dra7xx()) { + sr_inst = dra7_sr_instances; + nr_sr = ARRAY_SIZE(dra7_sr_instances); + } + + if (nr_sr) { + const char *name, *voltdm; + + for (i = 0; i < nr_sr; i++) { + name = kasprintf(GFP_KERNEL, "smartreflex_%s", sr_inst[i]); + voltdm = sr_inst[i]; + sr_init_by_name(name, voltdm); + } + + return 0; + } + return omap_hwmod_for_each_by_class("smartreflex", sr_dev_init, NULL); } diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index 5656e7aacd69..e4e1b6550115 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -810,6 +810,16 @@ config QCOM_FALKOR_ERRATUM_E1041 If unsure, say Y. +config NVIDIA_CARMEL_CNP_ERRATUM + bool "NVIDIA Carmel CNP: CNP on Carmel semantically different than ARM cores" + default y + help + If CNP is enabled on Carmel cores, non-sharable TLBIs on a core will not + invalidate shared TLB entries installed by a different core, as it would + on standard ARM cores. + + If unsure, say Y. + config SOCIONEXT_SYNQUACER_PREITS bool "Socionext Synquacer: Workaround for GICv3 pre-ITS" default y diff --git a/arch/arm64/boot/dts/freescale/fsl-ls1012a.dtsi b/arch/arm64/boot/dts/freescale/fsl-ls1012a.dtsi index 7de6b376d792..9058cfa4980f 100644 --- a/arch/arm64/boot/dts/freescale/fsl-ls1012a.dtsi +++ b/arch/arm64/boot/dts/freescale/fsl-ls1012a.dtsi @@ -198,6 +198,7 @@ ranges = <0x0 0x00 0x1700000 0x100000>; reg = <0x00 0x1700000 0x0 0x100000>; interrupts = <GIC_SPI 75 IRQ_TYPE_LEVEL_HIGH>; + dma-coherent; sec_jr0: jr@10000 { compatible = "fsl,sec-v5.4-job-ring", diff --git a/arch/arm64/boot/dts/freescale/fsl-ls1043a.dtsi b/arch/arm64/boot/dts/freescale/fsl-ls1043a.dtsi index 5a8a1dc4262d..28c51e521cb2 100644 --- a/arch/arm64/boot/dts/freescale/fsl-ls1043a.dtsi +++ b/arch/arm64/boot/dts/freescale/fsl-ls1043a.dtsi @@ -348,6 +348,7 @@ ranges = <0x0 0x00 0x1700000 0x100000>; reg = <0x00 0x1700000 0x0 0x100000>; interrupts = <0 75 0x4>; + dma-coherent; sec_jr0: jr@10000 { compatible = "fsl,sec-v5.4-job-ring", diff --git a/arch/arm64/boot/dts/freescale/fsl-ls1046a.dtsi b/arch/arm64/boot/dts/freescale/fsl-ls1046a.dtsi index 1d6dfd189c7f..39458305e333 100644 --- a/arch/arm64/boot/dts/freescale/fsl-ls1046a.dtsi +++ b/arch/arm64/boot/dts/freescale/fsl-ls1046a.dtsi @@ -354,6 +354,7 @@ ranges = <0x0 0x00 0x1700000 0x100000>; reg = <0x00 0x1700000 0x0 0x100000>; interrupts = <GIC_SPI 75 IRQ_TYPE_LEVEL_HIGH>; + dma-coherent; sec_jr0: jr@10000 { compatible = "fsl,sec-v5.4-job-ring", diff --git a/arch/arm64/boot/dts/freescale/imx8mp-phyboard-pollux-rdk.dts b/arch/arm64/boot/dts/freescale/imx8mp-phyboard-pollux-rdk.dts index 0e1a6d953389..122c95ddad30 100644 --- a/arch/arm64/boot/dts/freescale/imx8mp-phyboard-pollux-rdk.dts +++ b/arch/arm64/boot/dts/freescale/imx8mp-phyboard-pollux-rdk.dts @@ -35,7 +35,7 @@ &i2c2 { clock-frequency = <400000>; - pinctrl-names = "default"; + pinctrl-names = "default", "gpio"; pinctrl-0 = <&pinctrl_i2c2>; pinctrl-1 = <&pinctrl_i2c2_gpio>; sda-gpios = <&gpio5 17 (GPIO_ACTIVE_HIGH | GPIO_OPEN_DRAIN)>; diff --git a/arch/arm64/boot/dts/freescale/imx8mp-phycore-som.dtsi b/arch/arm64/boot/dts/freescale/imx8mp-phycore-som.dtsi index 44a8c2337cee..f3965ec5b31d 100644 --- a/arch/arm64/boot/dts/freescale/imx8mp-phycore-som.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mp-phycore-som.dtsi @@ -67,7 +67,7 @@ &i2c1 { clock-frequency = <400000>; - pinctrl-names = "default"; + pinctrl-names = "default", "gpio"; pinctrl-0 = <&pinctrl_i2c1>; pinctrl-1 = <&pinctrl_i2c1_gpio>; sda-gpios = <&gpio5 15 (GPIO_ACTIVE_HIGH | GPIO_OPEN_DRAIN)>; diff --git a/arch/arm64/include/asm/checksum.h b/arch/arm64/include/asm/checksum.h index 93a161b3bf3f..dc52b733675d 100644 --- a/arch/arm64/include/asm/checksum.h +++ b/arch/arm64/include/asm/checksum.h @@ -37,7 +37,7 @@ static inline __sum16 ip_fast_csum(const void *iph, unsigned int ihl) } while (--n > 0); sum += ((sum >> 32) | (sum << 32)); - return csum_fold((__force u32)(sum >> 32)); + return csum_fold((__force __wsum)(sum >> 32)); } #define ip_fast_csum ip_fast_csum diff --git a/arch/arm64/include/asm/cpucaps.h b/arch/arm64/include/asm/cpucaps.h index b77d997b173b..c40f2490cd7b 100644 --- a/arch/arm64/include/asm/cpucaps.h +++ b/arch/arm64/include/asm/cpucaps.h @@ -66,7 +66,8 @@ #define ARM64_WORKAROUND_1508412 58 #define ARM64_HAS_LDAPR 59 #define ARM64_KVM_PROTECTED_MODE 60 +#define ARM64_WORKAROUND_NVIDIA_CARMEL_CNP 61 -#define ARM64_NCAPS 61 +#define ARM64_NCAPS 62 #endif /* __ASM_CPUCAPS_H */ diff --git a/arch/arm64/include/asm/kvm_arm.h b/arch/arm64/include/asm/kvm_arm.h index 4e90c2debf70..94d4025acc0b 100644 --- a/arch/arm64/include/asm/kvm_arm.h +++ b/arch/arm64/include/asm/kvm_arm.h @@ -278,6 +278,7 @@ #define CPTR_EL2_DEFAULT CPTR_EL2_RES1 /* Hyp Debug Configuration Register bits */ +#define MDCR_EL2_TTRF (1 << 19) #define MDCR_EL2_TPMS (1 << 14) #define MDCR_EL2_E2PB_MASK (UL(0x3)) #define MDCR_EL2_E2PB_SHIFT (UL(12)) diff --git a/arch/arm64/include/asm/processor.h b/arch/arm64/include/asm/processor.h index ca2cd75d3286..efc10e9041a0 100644 --- a/arch/arm64/include/asm/processor.h +++ b/arch/arm64/include/asm/processor.h @@ -251,6 +251,8 @@ unsigned long get_wchan(struct task_struct *p); extern struct task_struct *cpu_switch_to(struct task_struct *prev, struct task_struct *next); +asmlinkage void arm64_preempt_schedule_irq(void); + #define task_pt_regs(p) \ ((struct pt_regs *)(THREAD_SIZE + task_stack_page(p)) - 1) diff --git a/arch/arm64/include/asm/thread_info.h b/arch/arm64/include/asm/thread_info.h index 9f4e3b266f21..6623c99f0984 100644 --- a/arch/arm64/include/asm/thread_info.h +++ b/arch/arm64/include/asm/thread_info.h @@ -55,6 +55,8 @@ void arch_setup_new_exec(void); #define arch_setup_new_exec arch_setup_new_exec void arch_release_task_struct(struct task_struct *tsk); +int arch_dup_task_struct(struct task_struct *dst, + struct task_struct *src); #endif diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c index 506a1cd37973..e2c20c036442 100644 --- a/arch/arm64/kernel/cpu_errata.c +++ b/arch/arm64/kernel/cpu_errata.c @@ -526,6 +526,14 @@ const struct arm64_cpu_capabilities arm64_errata[] = { 1, 0), }, #endif +#ifdef CONFIG_NVIDIA_CARMEL_CNP_ERRATUM + { + /* NVIDIA Carmel */ + .desc = "NVIDIA Carmel CNP erratum", + .capability = ARM64_WORKAROUND_NVIDIA_CARMEL_CNP, + ERRATA_MIDR_ALL_VERSIONS(MIDR_NVIDIA_CARMEL), + }, +#endif { } }; diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c index 066030717a4c..e5281e1c8f1d 100644 --- a/arch/arm64/kernel/cpufeature.c +++ b/arch/arm64/kernel/cpufeature.c @@ -383,7 +383,6 @@ static const struct arm64_ftr_bits ftr_id_aa64dfr0[] = { * of support. */ S_ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_EXACT, ID_AA64DFR0_PMUVER_SHIFT, 4, 0), - ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_EXACT, ID_AA64DFR0_TRACEVER_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_EXACT, ID_AA64DFR0_DEBUGVER_SHIFT, 4, 0x6), ARM64_FTR_END, }; @@ -1321,7 +1320,10 @@ has_useable_cnp(const struct arm64_cpu_capabilities *entry, int scope) * may share TLB entries with a CPU stuck in the crashed * kernel. */ - if (is_kdump_kernel()) + if (is_kdump_kernel()) + return false; + + if (cpus_have_const_cap(ARM64_WORKAROUND_NVIDIA_CARMEL_CNP)) return false; return has_cpuid_feature(entry, scope); diff --git a/arch/arm64/kernel/cpuinfo.c b/arch/arm64/kernel/cpuinfo.c index 77605aec25fe..51fcf99d5351 100644 --- a/arch/arm64/kernel/cpuinfo.c +++ b/arch/arm64/kernel/cpuinfo.c @@ -353,7 +353,7 @@ static void __cpuinfo_store_cpu(struct cpuinfo_arm64 *info) * with the CLIDR_EL1 fields to avoid triggering false warnings * when there is a mismatch across the CPUs. Keep track of the * effective value of the CTR_EL0 in our internal records for - * acurate sanity check and feature enablement. + * accurate sanity check and feature enablement. */ info->reg_ctr = read_cpuid_effective_cachetype(); info->reg_dczid = read_cpuid(DCZID_EL0); diff --git a/arch/arm64/kernel/crash_dump.c b/arch/arm64/kernel/crash_dump.c index e6e284265f19..58303a9ec32c 100644 --- a/arch/arm64/kernel/crash_dump.c +++ b/arch/arm64/kernel/crash_dump.c @@ -64,5 +64,7 @@ ssize_t copy_oldmem_page(unsigned long pfn, char *buf, ssize_t elfcorehdr_read(char *buf, size_t count, u64 *ppos) { memcpy(buf, phys_to_virt((phys_addr_t)*ppos), count); + *ppos += count; + return count; } diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c index 325c83b1a24d..6e60aa3b5ea9 100644 --- a/arch/arm64/kernel/process.c +++ b/arch/arm64/kernel/process.c @@ -57,6 +57,8 @@ #include <asm/processor.h> #include <asm/pointer_auth.h> #include <asm/stacktrace.h> +#include <asm/switch_to.h> +#include <asm/system_misc.h> #if defined(CONFIG_STACKPROTECTOR) && !defined(CONFIG_STACKPROTECTOR_PER_TASK) #include <linux/stackprotector.h> diff --git a/arch/arm64/kernel/stacktrace.c b/arch/arm64/kernel/stacktrace.c index ad20981dfda4..d55bdfb7789c 100644 --- a/arch/arm64/kernel/stacktrace.c +++ b/arch/arm64/kernel/stacktrace.c @@ -194,8 +194,9 @@ void show_stack(struct task_struct *tsk, unsigned long *sp, const char *loglvl) #ifdef CONFIG_STACKTRACE -void arch_stack_walk(stack_trace_consume_fn consume_entry, void *cookie, - struct task_struct *task, struct pt_regs *regs) +noinline void arch_stack_walk(stack_trace_consume_fn consume_entry, + void *cookie, struct task_struct *task, + struct pt_regs *regs) { struct stackframe frame; @@ -203,8 +204,8 @@ void arch_stack_walk(stack_trace_consume_fn consume_entry, void *cookie, start_backtrace(&frame, regs->regs[29], regs->pc); else if (task == current) start_backtrace(&frame, - (unsigned long)__builtin_frame_address(0), - (unsigned long)arch_stack_walk); + (unsigned long)__builtin_frame_address(1), + (unsigned long)__builtin_return_address(0)); else start_backtrace(&frame, thread_saved_fp(task), thread_saved_pc(task)); diff --git a/arch/arm64/kvm/debug.c b/arch/arm64/kvm/debug.c index 7a7e425616b5..dbc890511631 100644 --- a/arch/arm64/kvm/debug.c +++ b/arch/arm64/kvm/debug.c @@ -89,6 +89,7 @@ void kvm_arm_reset_debug_ptr(struct kvm_vcpu *vcpu) * - Debug ROM Address (MDCR_EL2_TDRA) * - OS related registers (MDCR_EL2_TDOSA) * - Statistical profiler (MDCR_EL2_TPMS/MDCR_EL2_E2PB) + * - Self-hosted Trace Filter controls (MDCR_EL2_TTRF) * * Additionally, KVM only traps guest accesses to the debug registers if * the guest is not actively using them (see the KVM_ARM64_DEBUG_DIRTY @@ -112,6 +113,7 @@ void kvm_arm_setup_debug(struct kvm_vcpu *vcpu) vcpu->arch.mdcr_el2 = __this_cpu_read(mdcr_el2) & MDCR_EL2_HPMN_MASK; vcpu->arch.mdcr_el2 |= (MDCR_EL2_TPM | MDCR_EL2_TPMS | + MDCR_EL2_TTRF | MDCR_EL2_TPMCR | MDCR_EL2_TDRA | MDCR_EL2_TDOSA); diff --git a/arch/arm64/kvm/hyp/vgic-v3-sr.c b/arch/arm64/kvm/hyp/vgic-v3-sr.c index ee3682b9873c..39f8f7f9227c 100644 --- a/arch/arm64/kvm/hyp/vgic-v3-sr.c +++ b/arch/arm64/kvm/hyp/vgic-v3-sr.c @@ -429,6 +429,13 @@ u64 __vgic_v3_get_gic_config(void) if (has_vhe()) flags = local_daif_save(); + /* + * Table 11-2 "Permitted ICC_SRE_ELx.SRE settings" indicates + * that to be able to set ICC_SRE_EL1.SRE to 0, all the + * interrupt overrides must be set. You've got to love this. + */ + sysreg_clear_set(hcr_el2, 0, HCR_AMO | HCR_FMO | HCR_IMO); + isb(); write_gicreg(0, ICC_SRE_EL1); isb(); @@ -436,6 +443,8 @@ u64 __vgic_v3_get_gic_config(void) write_gicreg(sre, ICC_SRE_EL1); isb(); + sysreg_clear_set(hcr_el2, HCR_AMO | HCR_FMO | HCR_IMO, 0); + isb(); if (has_vhe()) local_daif_restore(flags); diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c index 7484ea4f6ba0..5d9550fdb9cf 100644 --- a/arch/arm64/mm/mmu.c +++ b/arch/arm64/mm/mmu.c @@ -1448,6 +1448,22 @@ static void __remove_pgd_mapping(pgd_t *pgdir, unsigned long start, u64 size) struct range arch_get_mappable_range(void) { struct range mhp_range; + u64 start_linear_pa = __pa(_PAGE_OFFSET(vabits_actual)); + u64 end_linear_pa = __pa(PAGE_END - 1); + + if (IS_ENABLED(CONFIG_RANDOMIZE_BASE)) { + /* + * Check for a wrap, it is possible because of randomized linear + * mapping the start physical address is actually bigger than + * the end physical address. In this case set start to zero + * because [0, end_linear_pa] range must still be able to cover + * all addressable physical addresses. + */ + if (start_linear_pa > end_linear_pa) + start_linear_pa = 0; + } + + WARN_ON(start_linear_pa > end_linear_pa); /* * Linear mapping region is the range [PAGE_OFFSET..(PAGE_END - 1)] @@ -1455,8 +1471,9 @@ struct range arch_get_mappable_range(void) * range which can be mapped inside this linear mapping range, must * also be derived from its end points. */ - mhp_range.start = __pa(_PAGE_OFFSET(vabits_actual)); - mhp_range.end = __pa(PAGE_END - 1); + mhp_range.start = start_linear_pa; + mhp_range.end = end_linear_pa; + return mhp_range; } diff --git a/arch/ia64/kernel/err_inject.c b/arch/ia64/kernel/err_inject.c index 8b5b8e6bc9d9..dd5bfed52031 100644 --- a/arch/ia64/kernel/err_inject.c +++ b/arch/ia64/kernel/err_inject.c @@ -59,7 +59,7 @@ show_##name(struct device *dev, struct device_attribute *attr, \ char *buf) \ { \ u32 cpu=dev->id; \ - return sprintf(buf, "%lx\n", name[cpu]); \ + return sprintf(buf, "%llx\n", name[cpu]); \ } #define store(name) \ @@ -86,9 +86,9 @@ store_call_start(struct device *dev, struct device_attribute *attr, #ifdef ERR_INJ_DEBUG printk(KERN_DEBUG "pal_mc_err_inject for cpu%d:\n", cpu); - printk(KERN_DEBUG "err_type_info=%lx,\n", err_type_info[cpu]); - printk(KERN_DEBUG "err_struct_info=%lx,\n", err_struct_info[cpu]); - printk(KERN_DEBUG "err_data_buffer=%lx, %lx, %lx.\n", + printk(KERN_DEBUG "err_type_info=%llx,\n", err_type_info[cpu]); + printk(KERN_DEBUG "err_struct_info=%llx,\n", err_struct_info[cpu]); + printk(KERN_DEBUG "err_data_buffer=%llx, %llx, %llx.\n", err_data_buffer[cpu].data1, err_data_buffer[cpu].data2, err_data_buffer[cpu].data3); @@ -117,8 +117,8 @@ store_call_start(struct device *dev, struct device_attribute *attr, #ifdef ERR_INJ_DEBUG printk(KERN_DEBUG "Returns: status=%d,\n", (int)status[cpu]); - printk(KERN_DEBUG "capabilities=%lx,\n", capabilities[cpu]); - printk(KERN_DEBUG "resources=%lx\n", resources[cpu]); + printk(KERN_DEBUG "capabilities=%llx,\n", capabilities[cpu]); + printk(KERN_DEBUG "resources=%llx\n", resources[cpu]); #endif return size; } @@ -131,7 +131,7 @@ show_virtual_to_phys(struct device *dev, struct device_attribute *attr, char *buf) { unsigned int cpu=dev->id; - return sprintf(buf, "%lx\n", phys_addr[cpu]); + return sprintf(buf, "%llx\n", phys_addr[cpu]); } static ssize_t @@ -145,7 +145,7 @@ store_virtual_to_phys(struct device *dev, struct device_attribute *attr, ret = get_user_pages_fast(virt_addr, 1, FOLL_WRITE, NULL); if (ret<=0) { #ifdef ERR_INJ_DEBUG - printk("Virtual address %lx is not existing.\n",virt_addr); + printk("Virtual address %llx is not existing.\n", virt_addr); #endif return -EINVAL; } @@ -163,7 +163,7 @@ show_err_data_buffer(struct device *dev, { unsigned int cpu=dev->id; - return sprintf(buf, "%lx, %lx, %lx\n", + return sprintf(buf, "%llx, %llx, %llx\n", err_data_buffer[cpu].data1, err_data_buffer[cpu].data2, err_data_buffer[cpu].data3); @@ -178,13 +178,13 @@ store_err_data_buffer(struct device *dev, int ret; #ifdef ERR_INJ_DEBUG - printk("write err_data_buffer=[%lx,%lx,%lx] on cpu%d\n", + printk("write err_data_buffer=[%llx,%llx,%llx] on cpu%d\n", err_data_buffer[cpu].data1, err_data_buffer[cpu].data2, err_data_buffer[cpu].data3, cpu); #endif - ret=sscanf(buf, "%lx, %lx, %lx", + ret = sscanf(buf, "%llx, %llx, %llx", &err_data_buffer[cpu].data1, &err_data_buffer[cpu].data2, &err_data_buffer[cpu].data3); diff --git a/arch/ia64/kernel/mca.c b/arch/ia64/kernel/mca.c index d4cae2fc69ca..adf6521525f4 100644 --- a/arch/ia64/kernel/mca.c +++ b/arch/ia64/kernel/mca.c @@ -1824,7 +1824,7 @@ ia64_mca_cpu_init(void *cpu_data) data = mca_bootmem(); first_time = 0; } else - data = (void *)__get_free_pages(GFP_KERNEL, + data = (void *)__get_free_pages(GFP_ATOMIC, get_order(sz)); if (!data) panic("Could not allocate MCA memory for cpu %d\n", diff --git a/arch/mips/kernel/setup.c b/arch/mips/kernel/setup.c index 279be0153f8b..23a140327a0b 100644 --- a/arch/mips/kernel/setup.c +++ b/arch/mips/kernel/setup.c @@ -43,7 +43,7 @@ #include <asm/prom.h> #ifdef CONFIG_MIPS_ELF_APPENDED_DTB -const char __section(".appended_dtb") __appended_dtb[0x100000]; +char __section(".appended_dtb") __appended_dtb[0x100000]; #endif /* CONFIG_MIPS_ELF_APPENDED_DTB */ struct cpuinfo_mips cpu_data[NR_CPUS] __read_mostly; diff --git a/arch/powerpc/platforms/pseries/lpar.c b/arch/powerpc/platforms/pseries/lpar.c index 764170fdb0f7..3805519a6469 100644 --- a/arch/powerpc/platforms/pseries/lpar.c +++ b/arch/powerpc/platforms/pseries/lpar.c @@ -887,7 +887,8 @@ static long pSeries_lpar_hpte_updatepp(unsigned long slot, want_v = hpte_encode_avpn(vpn, psize, ssize); - flags = (newpp & 7) | H_AVPN; + flags = (newpp & (HPTE_R_PP | HPTE_R_N | HPTE_R_KEY_LO)) | H_AVPN; + flags |= (newpp & HPTE_R_KEY_HI) >> 48; if (mmu_has_feature(MMU_FTR_KERNEL_RO)) /* Move pp0 into bit 8 (IBM 55) */ flags |= (newpp & HPTE_R_PP0) >> 55; diff --git a/arch/powerpc/platforms/pseries/mobility.c b/arch/powerpc/platforms/pseries/mobility.c index ea4d6a660e0d..e83e0891272d 100644 --- a/arch/powerpc/platforms/pseries/mobility.c +++ b/arch/powerpc/platforms/pseries/mobility.c @@ -452,12 +452,28 @@ static int do_suspend(void) return ret; } +/** + * struct pseries_suspend_info - State shared between CPUs for join/suspend. + * @counter: Threads are to increment this upon resuming from suspend + * or if an error is received from H_JOIN. The thread which performs + * the first increment (i.e. sets it to 1) is responsible for + * waking the other threads. + * @done: False if join/suspend is in progress. True if the operation is + * complete (successful or not). + */ +struct pseries_suspend_info { + atomic_t counter; + bool done; +}; + static int do_join(void *arg) { - atomic_t *counter = arg; + struct pseries_suspend_info *info = arg; + atomic_t *counter = &info->counter; long hvrc; int ret; +retry: /* Must ensure MSR.EE off for H_JOIN. */ hard_irq_disable(); hvrc = plpar_hcall_norets(H_JOIN); @@ -473,8 +489,20 @@ static int do_join(void *arg) case H_SUCCESS: /* * The suspend is complete and this cpu has received a - * prod. + * prod, or we've received a stray prod from unrelated + * code (e.g. paravirt spinlocks) and we need to join + * again. + * + * This barrier orders the return from H_JOIN above vs + * the load of info->done. It pairs with the barrier + * in the wakeup/prod path below. */ + smp_mb(); + if (READ_ONCE(info->done) == false) { + pr_info_ratelimited("premature return from H_JOIN on CPU %i, retrying", + smp_processor_id()); + goto retry; + } ret = 0; break; case H_BAD_MODE: @@ -488,6 +516,13 @@ static int do_join(void *arg) if (atomic_inc_return(counter) == 1) { pr_info("CPU %u waking all threads\n", smp_processor_id()); + WRITE_ONCE(info->done, true); + /* + * This barrier orders the store to info->done vs subsequent + * H_PRODs to wake the other CPUs. It pairs with the barrier + * in the H_SUCCESS case above. + */ + smp_mb(); prod_others(); } /* @@ -535,11 +570,16 @@ static int pseries_suspend(u64 handle) int ret; while (true) { - atomic_t counter = ATOMIC_INIT(0); + struct pseries_suspend_info info; unsigned long vasi_state; int vasi_err; - ret = stop_machine(do_join, &counter, cpu_online_mask); + info = (struct pseries_suspend_info) { + .counter = ATOMIC_INIT(0), + .done = false, + }; + + ret = stop_machine(do_join, &info, cpu_online_mask); if (ret == 0) break; /* diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig index 87d7b52f278f..0d0cf67359cb 100644 --- a/arch/riscv/Kconfig +++ b/arch/riscv/Kconfig @@ -314,7 +314,7 @@ endchoice # Common NUMA Features config NUMA bool "NUMA Memory Allocation and Scheduler Support" - depends on SMP + depends on SMP && MMU select GENERIC_ARCH_NUMA select OF_NUMA select ARCH_SUPPORTS_NUMA_BALANCING diff --git a/arch/riscv/include/asm/uaccess.h b/arch/riscv/include/asm/uaccess.h index 824b2c9da75b..f944062c9d99 100644 --- a/arch/riscv/include/asm/uaccess.h +++ b/arch/riscv/include/asm/uaccess.h @@ -306,7 +306,9 @@ do { \ * data types like structures or arrays. * * @ptr must have pointer-to-simple-variable type, and @x must be assignable - * to the result of dereferencing @ptr. + * to the result of dereferencing @ptr. The value of @x is copied to avoid + * re-ordering where @x is evaluated inside the block that enables user-space + * access (thus bypassing user space protection if @x is a function). * * Caller must check the pointer with access_ok() before calling this * function. @@ -316,12 +318,13 @@ do { \ #define __put_user(x, ptr) \ ({ \ __typeof__(*(ptr)) __user *__gu_ptr = (ptr); \ + __typeof__(*__gu_ptr) __val = (x); \ long __pu_err = 0; \ \ __chk_user_ptr(__gu_ptr); \ \ __enable_user_access(); \ - __put_user_nocheck(x, __gu_ptr, __pu_err); \ + __put_user_nocheck(__val, __gu_ptr, __pu_err); \ __disable_user_access(); \ \ __pu_err; \ diff --git a/arch/riscv/kernel/entry.S b/arch/riscv/kernel/entry.S index 744f3209c48d..76274a4a1d8e 100644 --- a/arch/riscv/kernel/entry.S +++ b/arch/riscv/kernel/entry.S @@ -447,6 +447,7 @@ ENDPROC(__switch_to) #endif .section ".rodata" + .align LGREG /* Exception vector table */ ENTRY(excp_vect_table) RISCV_PTR do_trap_insn_misaligned diff --git a/arch/riscv/kernel/stacktrace.c b/arch/riscv/kernel/stacktrace.c index 3f893c9d9d85..2b3e0cb90d78 100644 --- a/arch/riscv/kernel/stacktrace.c +++ b/arch/riscv/kernel/stacktrace.c @@ -14,7 +14,7 @@ #include <asm/stacktrace.h> -register const unsigned long sp_in_global __asm__("sp"); +register unsigned long sp_in_global __asm__("sp"); #ifdef CONFIG_FRAME_POINTER diff --git a/arch/riscv/mm/kasan_init.c b/arch/riscv/mm/kasan_init.c index 4f85c6d0ddf8..937d13ce9ab8 100644 --- a/arch/riscv/mm/kasan_init.c +++ b/arch/riscv/mm/kasan_init.c @@ -216,7 +216,7 @@ void __init kasan_init(void) break; kasan_populate(kasan_mem_to_shadow(start), kasan_mem_to_shadow(end)); - }; + } for (i = 0; i < PTRS_PER_PTE; i++) set_pte(&kasan_early_shadow_pte[i], diff --git a/arch/s390/include/asm/vdso/data.h b/arch/s390/include/asm/vdso/data.h index 7b3cdb4a5f48..73ee89142666 100644 --- a/arch/s390/include/asm/vdso/data.h +++ b/arch/s390/include/asm/vdso/data.h @@ -6,7 +6,7 @@ #include <vdso/datapage.h> struct arch_vdso_data { - __u64 tod_steering_delta; + __s64 tod_steering_delta; __u64 tod_steering_end; }; diff --git a/arch/s390/kernel/time.c b/arch/s390/kernel/time.c index 165da961f901..326cb8f75f58 100644 --- a/arch/s390/kernel/time.c +++ b/arch/s390/kernel/time.c @@ -80,10 +80,12 @@ void __init time_early_init(void) { struct ptff_qto qto; struct ptff_qui qui; + int cs; /* Initialize TOD steering parameters */ tod_steering_end = tod_clock_base.tod; - vdso_data->arch_data.tod_steering_end = tod_steering_end; + for (cs = 0; cs < CS_BASES; cs++) + vdso_data[cs].arch_data.tod_steering_end = tod_steering_end; if (!test_facility(28)) return; @@ -366,6 +368,7 @@ static void clock_sync_global(unsigned long delta) { unsigned long now, adj; struct ptff_qto qto; + int cs; /* Fixup the monotonic sched clock. */ tod_clock_base.eitod += delta; @@ -381,7 +384,10 @@ static void clock_sync_global(unsigned long delta) panic("TOD clock sync offset %li is too large to drift\n", tod_steering_delta); tod_steering_end = now + (abs(tod_steering_delta) << 15); - vdso_data->arch_data.tod_steering_end = tod_steering_end; + for (cs = 0; cs < CS_BASES; cs++) { + vdso_data[cs].arch_data.tod_steering_end = tod_steering_end; + vdso_data[cs].arch_data.tod_steering_delta = tod_steering_delta; + } /* Update LPAR offset. */ if (ptff_query(PTFF_QTO) && ptff(&qto, sizeof(qto), PTFF_QTO) == 0) diff --git a/arch/x86/Makefile b/arch/x86/Makefile index 2d6d5a28c3bf..9a85eae37b17 100644 --- a/arch/x86/Makefile +++ b/arch/x86/Makefile @@ -27,7 +27,7 @@ endif REALMODE_CFLAGS := -m16 -g -Os -DDISABLE_BRANCH_PROFILING \ -Wall -Wstrict-prototypes -march=i386 -mregparm=3 \ -fno-strict-aliasing -fomit-frame-pointer -fno-pic \ - -mno-mmx -mno-sse + -mno-mmx -mno-sse $(call cc-option,-fcf-protection=none) REALMODE_CFLAGS += -ffreestanding REALMODE_CFLAGS += -fno-stack-protector diff --git a/arch/x86/include/asm/smp.h b/arch/x86/include/asm/smp.h index c0538f82c9a2..57ef2094af93 100644 --- a/arch/x86/include/asm/smp.h +++ b/arch/x86/include/asm/smp.h @@ -132,6 +132,7 @@ void native_play_dead(void); void play_dead_common(void); void wbinvd_on_cpu(int cpu); int wbinvd_on_all_cpus(void); +bool wakeup_cpu0(void); void native_smp_send_reschedule(int cpu); void native_send_call_func_ipi(const struct cpumask *mask); diff --git a/arch/x86/include/asm/xen/page.h b/arch/x86/include/asm/xen/page.h index 7068e4bb057d..1a162e559753 100644 --- a/arch/x86/include/asm/xen/page.h +++ b/arch/x86/include/asm/xen/page.h @@ -87,18 +87,6 @@ clear_foreign_p2m_mapping(struct gnttab_unmap_grant_ref *unmap_ops, #endif /* - * The maximum amount of extra memory compared to the base size. The - * main scaling factor is the size of struct page. At extreme ratios - * of base:extra, all the base memory can be filled with page - * structures for the extra memory, leaving no space for anything - * else. - * - * 10x seems like a reasonable balance between scaling flexibility and - * leaving a practically usable system. - */ -#define XEN_EXTRA_MEM_RATIO (10) - -/* * Helper functions to write or read unsigned long values to/from * memory, when the access may fault. */ diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c index 7bdc0239a943..14cd3186dc77 100644 --- a/arch/x86/kernel/acpi/boot.c +++ b/arch/x86/kernel/acpi/boot.c @@ -1554,10 +1554,18 @@ void __init acpi_boot_table_init(void) /* * Initialize the ACPI boot-time table parser. */ - if (acpi_table_init()) { + if (acpi_locate_initial_tables()) disable_acpi(); - return; - } + else + acpi_reserve_initial_tables(); +} + +int __init early_acpi_boot_init(void) +{ + if (acpi_disabled) + return 1; + + acpi_table_init_complete(); acpi_table_parse(ACPI_SIG_BOOT, acpi_parse_sbf); @@ -1570,18 +1578,9 @@ void __init acpi_boot_table_init(void) } else { printk(KERN_WARNING PREFIX "Disabling ACPI support\n"); disable_acpi(); - return; + return 1; } } -} - -int __init early_acpi_boot_init(void) -{ - /* - * If acpi_disabled, bail out - */ - if (acpi_disabled) - return 1; /* * Process the Multiple APIC Description Table (MADT), if present diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index d883176ef2ce..5ecd69a48393 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -1045,6 +1045,9 @@ void __init setup_arch(char **cmdline_p) cleanup_highmap(); + /* Look for ACPI tables and reserve memory occupied by them. */ + acpi_boot_table_init(); + memblock_set_current_limit(ISA_END_ADDRESS); e820__memblock_setup(); @@ -1136,11 +1139,6 @@ void __init setup_arch(char **cmdline_p) early_platform_quirks(); - /* - * Parse the ACPI tables for possible boot-time SMP configuration. - */ - acpi_boot_table_init(); - early_acpi_boot_init(); initmem_init(); diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index 02813a7f3a7c..f877150a91da 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -1659,7 +1659,7 @@ void play_dead_common(void) local_irq_disable(); } -static bool wakeup_cpu0(void) +bool wakeup_cpu0(void) { if (smp_processor_id() == 0 && enable_start_cpu0) return true; diff --git a/arch/x86/kvm/Makefile b/arch/x86/kvm/Makefile index 1b4766fe1de2..eafc4d601f25 100644 --- a/arch/x86/kvm/Makefile +++ b/arch/x86/kvm/Makefile @@ -1,6 +1,6 @@ # SPDX-License-Identifier: GPL-2.0 -ccflags-y += -Iarch/x86/kvm +ccflags-y += -I $(srctree)/arch/x86/kvm ccflags-$(CONFIG_KVM_WERROR) += -Werror ifeq ($(CONFIG_FRAME_POINTER),y) diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index d75524bc8423..486aa94ecf1d 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -5884,6 +5884,7 @@ static void kvm_recover_nx_lpages(struct kvm *kvm) struct kvm_mmu_page *sp; unsigned int ratio; LIST_HEAD(invalid_list); + bool flush = false; ulong to_zap; rcu_idx = srcu_read_lock(&kvm->srcu); @@ -5905,19 +5906,19 @@ static void kvm_recover_nx_lpages(struct kvm *kvm) lpage_disallowed_link); WARN_ON_ONCE(!sp->lpage_disallowed); if (is_tdp_mmu_page(sp)) { - kvm_tdp_mmu_zap_gfn_range(kvm, sp->gfn, - sp->gfn + KVM_PAGES_PER_HPAGE(sp->role.level)); + flush = kvm_tdp_mmu_zap_sp(kvm, sp); } else { kvm_mmu_prepare_zap_page(kvm, sp, &invalid_list); WARN_ON_ONCE(sp->lpage_disallowed); } if (need_resched() || rwlock_needbreak(&kvm->mmu_lock)) { - kvm_mmu_commit_zap_page(kvm, &invalid_list); + kvm_mmu_remote_flush_or_zap(kvm, &invalid_list, flush); cond_resched_rwlock_write(&kvm->mmu_lock); + flush = false; } } - kvm_mmu_commit_zap_page(kvm, &invalid_list); + kvm_mmu_remote_flush_or_zap(kvm, &invalid_list, flush); write_unlock(&kvm->mmu_lock); srcu_read_unlock(&kvm->srcu, rcu_idx); diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c index 462b1f71c77f..018d82e73e31 100644 --- a/arch/x86/kvm/mmu/tdp_mmu.c +++ b/arch/x86/kvm/mmu/tdp_mmu.c @@ -86,7 +86,7 @@ static inline struct kvm_mmu_page *tdp_mmu_next_root(struct kvm *kvm, list_for_each_entry(_root, &_kvm->arch.tdp_mmu_roots, link) static bool zap_gfn_range(struct kvm *kvm, struct kvm_mmu_page *root, - gfn_t start, gfn_t end, bool can_yield); + gfn_t start, gfn_t end, bool can_yield, bool flush); void kvm_tdp_mmu_free_root(struct kvm *kvm, struct kvm_mmu_page *root) { @@ -99,7 +99,7 @@ void kvm_tdp_mmu_free_root(struct kvm *kvm, struct kvm_mmu_page *root) list_del(&root->link); - zap_gfn_range(kvm, root, 0, max_gfn, false); + zap_gfn_range(kvm, root, 0, max_gfn, false, false); free_page((unsigned long)root->spt); kmem_cache_free(mmu_page_header_cache, root); @@ -668,20 +668,21 @@ static inline bool tdp_mmu_iter_cond_resched(struct kvm *kvm, * scheduler needs the CPU or there is contention on the MMU lock. If this * function cannot yield, it will not release the MMU lock or reschedule and * the caller must ensure it does not supply too large a GFN range, or the - * operation can cause a soft lockup. + * operation can cause a soft lockup. Note, in some use cases a flush may be + * required by prior actions. Ensure the pending flush is performed prior to + * yielding. */ static bool zap_gfn_range(struct kvm *kvm, struct kvm_mmu_page *root, - gfn_t start, gfn_t end, bool can_yield) + gfn_t start, gfn_t end, bool can_yield, bool flush) { struct tdp_iter iter; - bool flush_needed = false; rcu_read_lock(); tdp_root_for_each_pte(iter, root, start, end) { if (can_yield && - tdp_mmu_iter_cond_resched(kvm, &iter, flush_needed)) { - flush_needed = false; + tdp_mmu_iter_cond_resched(kvm, &iter, flush)) { + flush = false; continue; } @@ -699,11 +700,11 @@ static bool zap_gfn_range(struct kvm *kvm, struct kvm_mmu_page *root, continue; tdp_mmu_set_spte(kvm, &iter, 0); - flush_needed = true; + flush = true; } rcu_read_unlock(); - return flush_needed; + return flush; } /* @@ -712,13 +713,14 @@ static bool zap_gfn_range(struct kvm *kvm, struct kvm_mmu_page *root, * SPTEs have been cleared and a TLB flush is needed before releasing the * MMU lock. */ -bool kvm_tdp_mmu_zap_gfn_range(struct kvm *kvm, gfn_t start, gfn_t end) +bool __kvm_tdp_mmu_zap_gfn_range(struct kvm *kvm, gfn_t start, gfn_t end, + bool can_yield) { struct kvm_mmu_page *root; bool flush = false; for_each_tdp_mmu_root_yield_safe(kvm, root) - flush |= zap_gfn_range(kvm, root, start, end, true); + flush = zap_gfn_range(kvm, root, start, end, can_yield, flush); return flush; } @@ -930,7 +932,7 @@ static int zap_gfn_range_hva_wrapper(struct kvm *kvm, struct kvm_mmu_page *root, gfn_t start, gfn_t end, unsigned long unused) { - return zap_gfn_range(kvm, root, start, end, false); + return zap_gfn_range(kvm, root, start, end, false, false); } int kvm_tdp_mmu_zap_hva_range(struct kvm *kvm, unsigned long start, diff --git a/arch/x86/kvm/mmu/tdp_mmu.h b/arch/x86/kvm/mmu/tdp_mmu.h index 3b761c111bff..31096ece9b14 100644 --- a/arch/x86/kvm/mmu/tdp_mmu.h +++ b/arch/x86/kvm/mmu/tdp_mmu.h @@ -8,7 +8,29 @@ hpa_t kvm_tdp_mmu_get_vcpu_root_hpa(struct kvm_vcpu *vcpu); void kvm_tdp_mmu_free_root(struct kvm *kvm, struct kvm_mmu_page *root); -bool kvm_tdp_mmu_zap_gfn_range(struct kvm *kvm, gfn_t start, gfn_t end); +bool __kvm_tdp_mmu_zap_gfn_range(struct kvm *kvm, gfn_t start, gfn_t end, + bool can_yield); +static inline bool kvm_tdp_mmu_zap_gfn_range(struct kvm *kvm, gfn_t start, + gfn_t end) +{ + return __kvm_tdp_mmu_zap_gfn_range(kvm, start, end, true); +} +static inline bool kvm_tdp_mmu_zap_sp(struct kvm *kvm, struct kvm_mmu_page *sp) +{ + gfn_t end = sp->gfn + KVM_PAGES_PER_HPAGE(sp->role.level); + + /* + * Don't allow yielding, as the caller may have a flush pending. Note, + * if mmu_lock is held for write, zapping will never yield in this case, + * but explicitly disallow it for safety. The TDP MMU does not yield + * until it has made forward progress (steps sideways), and when zapping + * a single shadow page that it's guaranteed to see (thus the mmu_lock + * requirement), its "step sideways" will always step beyond the bounds + * of the shadow page's gfn range and stop iterating before yielding. + */ + lockdep_assert_held_write(&kvm->mmu_lock); + return __kvm_tdp_mmu_zap_gfn_range(kvm, sp->gfn, end, false); +} void kvm_tdp_mmu_zap_all(struct kvm *kvm); int kvm_tdp_mmu_map(struct kvm_vcpu *vcpu, gpa_t gpa, u32 error_code, diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c index 35891d9a1099..fb204eaa8bb3 100644 --- a/arch/x86/kvm/svm/nested.c +++ b/arch/x86/kvm/svm/nested.c @@ -246,11 +246,18 @@ static bool nested_vmcb_check_controls(struct vmcb_control_area *control) return true; } -static bool nested_vmcb_checks(struct vcpu_svm *svm, struct vmcb *vmcb12) +static bool nested_vmcb_check_save(struct vcpu_svm *svm, struct vmcb *vmcb12) { struct kvm_vcpu *vcpu = &svm->vcpu; bool vmcb12_lma; + /* + * FIXME: these should be done after copying the fields, + * to avoid TOC/TOU races. For these save area checks + * the possible damage is limited since kvm_set_cr0 and + * kvm_set_cr4 handle failure; EFER_SVME is an exception + * so it is force-set later in nested_prepare_vmcb_save. + */ if ((vmcb12->save.efer & EFER_SVME) == 0) return false; @@ -271,7 +278,7 @@ static bool nested_vmcb_checks(struct vcpu_svm *svm, struct vmcb *vmcb12) if (!kvm_is_valid_cr4(&svm->vcpu, vmcb12->save.cr4)) return false; - return nested_vmcb_check_controls(&vmcb12->control); + return true; } static void load_nested_vmcb_control(struct vcpu_svm *svm, @@ -396,7 +403,14 @@ static void nested_prepare_vmcb_save(struct vcpu_svm *svm, struct vmcb *vmcb12) svm->vmcb->save.gdtr = vmcb12->save.gdtr; svm->vmcb->save.idtr = vmcb12->save.idtr; kvm_set_rflags(&svm->vcpu, vmcb12->save.rflags | X86_EFLAGS_FIXED); - svm_set_efer(&svm->vcpu, vmcb12->save.efer); + + /* + * Force-set EFER_SVME even though it is checked earlier on the + * VMCB12, because the guest can flip the bit between the check + * and now. Clearing EFER_SVME would call svm_free_nested. + */ + svm_set_efer(&svm->vcpu, vmcb12->save.efer | EFER_SVME); + svm_set_cr0(&svm->vcpu, vmcb12->save.cr0); svm_set_cr4(&svm->vcpu, vmcb12->save.cr4); svm->vmcb->save.cr2 = svm->vcpu.arch.cr2 = vmcb12->save.cr2; @@ -468,7 +482,6 @@ int enter_svm_guest_mode(struct vcpu_svm *svm, u64 vmcb12_gpa, svm->nested.vmcb12_gpa = vmcb12_gpa; - load_nested_vmcb_control(svm, &vmcb12->control); nested_prepare_vmcb_control(svm); nested_prepare_vmcb_save(svm, vmcb12); @@ -515,7 +528,10 @@ int nested_svm_vmrun(struct vcpu_svm *svm) if (WARN_ON_ONCE(!svm->nested.initialized)) return -EINVAL; - if (!nested_vmcb_checks(svm, vmcb12)) { + load_nested_vmcb_control(svm, &vmcb12->control); + + if (!nested_vmcb_check_save(svm, vmcb12) || + !nested_vmcb_check_controls(&svm->nested.ctl)) { vmcb12->control.exit_code = SVM_EXIT_ERR; vmcb12->control.exit_code_hi = 0; vmcb12->control.exit_info_1 = 0; @@ -1209,6 +1225,8 @@ static int svm_set_nested_state(struct kvm_vcpu *vcpu, */ if (!(save->cr0 & X86_CR0_PG)) goto out_free; + if (!(save->efer & EFER_SVME)) + goto out_free; /* * All checks done, we can enter guest mode. L1 control fields diff --git a/arch/x86/kvm/svm/pmu.c b/arch/x86/kvm/svm/pmu.c index 035da07500e8..fdf587f19c5f 100644 --- a/arch/x86/kvm/svm/pmu.c +++ b/arch/x86/kvm/svm/pmu.c @@ -98,6 +98,8 @@ static enum index msr_to_index(u32 msr) static inline struct kvm_pmc *get_gp_pmc_amd(struct kvm_pmu *pmu, u32 msr, enum pmu_type type) { + struct kvm_vcpu *vcpu = pmu_to_vcpu(pmu); + switch (msr) { case MSR_F15H_PERF_CTL0: case MSR_F15H_PERF_CTL1: @@ -105,6 +107,9 @@ static inline struct kvm_pmc *get_gp_pmc_amd(struct kvm_pmu *pmu, u32 msr, case MSR_F15H_PERF_CTL3: case MSR_F15H_PERF_CTL4: case MSR_F15H_PERF_CTL5: + if (!guest_cpuid_has(vcpu, X86_FEATURE_PERFCTR_CORE)) + return NULL; + fallthrough; case MSR_K7_EVNTSEL0 ... MSR_K7_EVNTSEL3: if (type != PMU_TYPE_EVNTSEL) return NULL; @@ -115,6 +120,9 @@ static inline struct kvm_pmc *get_gp_pmc_amd(struct kvm_pmu *pmu, u32 msr, case MSR_F15H_PERF_CTR3: case MSR_F15H_PERF_CTR4: case MSR_F15H_PERF_CTR5: + if (!guest_cpuid_has(vcpu, X86_FEATURE_PERFCTR_CORE)) + return NULL; + fallthrough; case MSR_K7_PERFCTR0 ... MSR_K7_PERFCTR3: if (type != PMU_TYPE_COUNTER) return NULL; diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index fe806e894212..eca63625aee4 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -271,8 +271,7 @@ static struct kmem_cache *x86_emulator_cache; * When called, it means the previous get/set msr reached an invalid msr. * Return true if we want to ignore/silent this failed msr access. */ -static bool kvm_msr_ignored_check(struct kvm_vcpu *vcpu, u32 msr, - u64 data, bool write) +static bool kvm_msr_ignored_check(u32 msr, u64 data, bool write) { const char *op = write ? "wrmsr" : "rdmsr"; @@ -1445,7 +1444,7 @@ static int do_get_msr_feature(struct kvm_vcpu *vcpu, unsigned index, u64 *data) if (r == KVM_MSR_RET_INVALID) { /* Unconditionally clear the output for simplicity */ *data = 0; - if (kvm_msr_ignored_check(vcpu, index, 0, false)) + if (kvm_msr_ignored_check(index, 0, false)) r = 0; } @@ -1620,7 +1619,7 @@ static int kvm_set_msr_ignored_check(struct kvm_vcpu *vcpu, int ret = __kvm_set_msr(vcpu, index, data, host_initiated); if (ret == KVM_MSR_RET_INVALID) - if (kvm_msr_ignored_check(vcpu, index, data, true)) + if (kvm_msr_ignored_check(index, data, true)) ret = 0; return ret; @@ -1658,7 +1657,7 @@ static int kvm_get_msr_ignored_check(struct kvm_vcpu *vcpu, if (ret == KVM_MSR_RET_INVALID) { /* Unconditionally clear *data for simplicity */ *data = 0; - if (kvm_msr_ignored_check(vcpu, index, 0, false)) + if (kvm_msr_ignored_check(index, 0, false)) ret = 0; } @@ -2329,7 +2328,7 @@ static void kvm_synchronize_tsc(struct kvm_vcpu *vcpu, u64 data) kvm_vcpu_write_tsc_offset(vcpu, offset); raw_spin_unlock_irqrestore(&kvm->arch.tsc_write_lock, flags); - spin_lock(&kvm->arch.pvclock_gtod_sync_lock); + spin_lock_irqsave(&kvm->arch.pvclock_gtod_sync_lock, flags); if (!matched) { kvm->arch.nr_vcpus_matched_tsc = 0; } else if (!already_matched) { @@ -2337,7 +2336,7 @@ static void kvm_synchronize_tsc(struct kvm_vcpu *vcpu, u64 data) } kvm_track_tsc_matching(vcpu); - spin_unlock(&kvm->arch.pvclock_gtod_sync_lock); + spin_unlock_irqrestore(&kvm->arch.pvclock_gtod_sync_lock, flags); } static inline void adjust_tsc_offset_guest(struct kvm_vcpu *vcpu, @@ -2559,13 +2558,16 @@ static void kvm_gen_update_masterclock(struct kvm *kvm) int i; struct kvm_vcpu *vcpu; struct kvm_arch *ka = &kvm->arch; + unsigned long flags; kvm_hv_invalidate_tsc_page(kvm); - spin_lock(&ka->pvclock_gtod_sync_lock); kvm_make_mclock_inprogress_request(kvm); + /* no guest entries from this point */ + spin_lock_irqsave(&ka->pvclock_gtod_sync_lock, flags); pvclock_update_vm_gtod_copy(kvm); + spin_unlock_irqrestore(&ka->pvclock_gtod_sync_lock, flags); kvm_for_each_vcpu(i, vcpu, kvm) kvm_make_request(KVM_REQ_CLOCK_UPDATE, vcpu); @@ -2573,8 +2575,6 @@ static void kvm_gen_update_masterclock(struct kvm *kvm) /* guest entries allowed */ kvm_for_each_vcpu(i, vcpu, kvm) kvm_clear_request(KVM_REQ_MCLOCK_INPROGRESS, vcpu); - - spin_unlock(&ka->pvclock_gtod_sync_lock); #endif } @@ -2582,17 +2582,18 @@ u64 get_kvmclock_ns(struct kvm *kvm) { struct kvm_arch *ka = &kvm->arch; struct pvclock_vcpu_time_info hv_clock; + unsigned long flags; u64 ret; - spin_lock(&ka->pvclock_gtod_sync_lock); + spin_lock_irqsave(&ka->pvclock_gtod_sync_lock, flags); if (!ka->use_master_clock) { - spin_unlock(&ka->pvclock_gtod_sync_lock); + spin_unlock_irqrestore(&ka->pvclock_gtod_sync_lock, flags); return get_kvmclock_base_ns() + ka->kvmclock_offset; } hv_clock.tsc_timestamp = ka->master_cycle_now; hv_clock.system_time = ka->master_kernel_ns + ka->kvmclock_offset; - spin_unlock(&ka->pvclock_gtod_sync_lock); + spin_unlock_irqrestore(&ka->pvclock_gtod_sync_lock, flags); /* both __this_cpu_read() and rdtsc() should be on the same cpu */ get_cpu(); @@ -2686,13 +2687,13 @@ static int kvm_guest_time_update(struct kvm_vcpu *v) * If the host uses TSC clock, then passthrough TSC as stable * to the guest. */ - spin_lock(&ka->pvclock_gtod_sync_lock); + spin_lock_irqsave(&ka->pvclock_gtod_sync_lock, flags); use_master_clock = ka->use_master_clock; if (use_master_clock) { host_tsc = ka->master_cycle_now; kernel_ns = ka->master_kernel_ns; } - spin_unlock(&ka->pvclock_gtod_sync_lock); + spin_unlock_irqrestore(&ka->pvclock_gtod_sync_lock, flags); /* Keep irq disabled to prevent changes to the clock */ local_irq_save(flags); @@ -5726,6 +5727,7 @@ set_pit2_out: } #endif case KVM_SET_CLOCK: { + struct kvm_arch *ka = &kvm->arch; struct kvm_clock_data user_ns; u64 now_ns; @@ -5744,8 +5746,22 @@ set_pit2_out: * pvclock_update_vm_gtod_copy(). */ kvm_gen_update_masterclock(kvm); - now_ns = get_kvmclock_ns(kvm); - kvm->arch.kvmclock_offset += user_ns.clock - now_ns; + + /* + * This pairs with kvm_guest_time_update(): when masterclock is + * in use, we use master_kernel_ns + kvmclock_offset to set + * unsigned 'system_time' so if we use get_kvmclock_ns() (which + * is slightly ahead) here we risk going negative on unsigned + * 'system_time' when 'user_ns.clock' is very small. + */ + spin_lock_irq(&ka->pvclock_gtod_sync_lock); + if (kvm->arch.use_master_clock) + now_ns = ka->master_kernel_ns; + else + now_ns = get_kvmclock_base_ns(); + ka->kvmclock_offset = user_ns.clock - now_ns; + spin_unlock_irq(&ka->pvclock_gtod_sync_lock); + kvm_make_all_cpus_request(kvm, KVM_REQ_CLOCK_UPDATE); break; } @@ -7724,6 +7740,7 @@ static void kvm_hyperv_tsc_notifier(void) struct kvm *kvm; struct kvm_vcpu *vcpu; int cpu; + unsigned long flags; mutex_lock(&kvm_lock); list_for_each_entry(kvm, &vm_list, vm_list) @@ -7739,17 +7756,15 @@ static void kvm_hyperv_tsc_notifier(void) list_for_each_entry(kvm, &vm_list, vm_list) { struct kvm_arch *ka = &kvm->arch; - spin_lock(&ka->pvclock_gtod_sync_lock); - + spin_lock_irqsave(&ka->pvclock_gtod_sync_lock, flags); pvclock_update_vm_gtod_copy(kvm); + spin_unlock_irqrestore(&ka->pvclock_gtod_sync_lock, flags); kvm_for_each_vcpu(cpu, vcpu, kvm) kvm_make_request(KVM_REQ_CLOCK_UPDATE, vcpu); kvm_for_each_vcpu(cpu, vcpu, kvm) kvm_clear_request(KVM_REQ_MCLOCK_INPROGRESS, vcpu); - - spin_unlock(&ka->pvclock_gtod_sync_lock); } mutex_unlock(&kvm_lock); } diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h index 39eb04887141..9035e34aa156 100644 --- a/arch/x86/kvm/x86.h +++ b/arch/x86/kvm/x86.h @@ -250,7 +250,6 @@ static inline bool kvm_vcpu_latch_init(struct kvm_vcpu *vcpu) void kvm_write_wall_clock(struct kvm *kvm, gpa_t wall_clock, int sec_hi_ofs); void kvm_inject_realmode_interrupt(struct kvm_vcpu *vcpu, int irq, int inc_eip); -void kvm_write_tsc(struct kvm_vcpu *vcpu, struct msr_data *msr); u64 get_kvmclock_ns(struct kvm *kvm); int kvm_read_guest_virt(struct kvm_vcpu *vcpu, diff --git a/arch/x86/mm/mem_encrypt.c b/arch/x86/mm/mem_encrypt.c index 4b01f7dbaf30..ae78cef79980 100644 --- a/arch/x86/mm/mem_encrypt.c +++ b/arch/x86/mm/mem_encrypt.c @@ -262,7 +262,7 @@ static void __init __set_clr_pte_enc(pte_t *kpte, int level, bool enc) if (pgprot_val(old_prot) == pgprot_val(new_prot)) return; - pa = pfn << page_level_shift(level); + pa = pfn << PAGE_SHIFT; size = page_level_size(level); /* diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c index 6926d0ca6c71..b35fc8023884 100644 --- a/arch/x86/net/bpf_jit_comp.c +++ b/arch/x86/net/bpf_jit_comp.c @@ -1936,7 +1936,7 @@ static int invoke_bpf_mod_ret(const struct btf_func_model *m, u8 **pprog, * add rsp, 8 // skip eth_type_trans's frame * ret // return to its caller */ -int arch_prepare_bpf_trampoline(void *image, void *image_end, +int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *image_end, const struct btf_func_model *m, u32 flags, struct bpf_tramp_progs *tprogs, void *orig_call) @@ -1975,6 +1975,15 @@ int arch_prepare_bpf_trampoline(void *image, void *image_end, save_regs(m, &prog, nr_args, stack_size); + if (flags & BPF_TRAMP_F_CALL_ORIG) { + /* arg1: mov rdi, im */ + emit_mov_imm64(&prog, BPF_REG_1, (long) im >> 32, (u32) (long) im); + if (emit_call(&prog, __bpf_tramp_enter, prog)) { + ret = -EINVAL; + goto cleanup; + } + } + if (fentry->nr_progs) if (invoke_bpf(m, &prog, fentry, stack_size)) return -EINVAL; @@ -1993,8 +2002,7 @@ int arch_prepare_bpf_trampoline(void *image, void *image_end, } if (flags & BPF_TRAMP_F_CALL_ORIG) { - if (fentry->nr_progs || fmod_ret->nr_progs) - restore_regs(m, &prog, nr_args, stack_size); + restore_regs(m, &prog, nr_args, stack_size); /* call original function */ if (emit_call(&prog, orig_call, prog)) { @@ -2003,6 +2011,9 @@ int arch_prepare_bpf_trampoline(void *image, void *image_end, } /* remember return value in a stack for bpf prog to access */ emit_stx(&prog, BPF_DW, BPF_REG_FP, BPF_REG_0, -8); + im->ip_after_call = prog; + memcpy(prog, ideal_nops[NOP_ATOMIC5], X86_PATCH_SIZE); + prog += X86_PATCH_SIZE; } if (fmod_ret->nr_progs) { @@ -2033,9 +2044,17 @@ int arch_prepare_bpf_trampoline(void *image, void *image_end, * the return value is only updated on the stack and still needs to be * restored to R0. */ - if (flags & BPF_TRAMP_F_CALL_ORIG) + if (flags & BPF_TRAMP_F_CALL_ORIG) { + im->ip_epilogue = prog; + /* arg1: mov rdi, im */ + emit_mov_imm64(&prog, BPF_REG_1, (long) im >> 32, (u32) (long) im); + if (emit_call(&prog, __bpf_tramp_exit, prog)) { + ret = -EINVAL; + goto cleanup; + } /* restore original return value back into RAX */ emit_ldx(&prog, BPF_DW, BPF_REG_0, BPF_REG_FP, -8); + } EMIT1(0x5B); /* pop rbx */ EMIT1(0xC9); /* leave */ @@ -2225,7 +2244,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog) padding = true; goto skip_init_addrs; } - addrs = kmalloc_array(prog->len + 1, sizeof(*addrs), GFP_KERNEL); + addrs = kvmalloc_array(prog->len + 1, sizeof(*addrs), GFP_KERNEL); if (!addrs) { prog = orig_prog; goto out_addrs; @@ -2317,7 +2336,7 @@ out_image: if (image) bpf_prog_fill_jited_linfo(prog, addrs + 1); out_addrs: - kfree(addrs); + kvfree(addrs); kfree(jit_data); prog->aux->jit_data = NULL; } diff --git a/arch/x86/xen/p2m.c b/arch/x86/xen/p2m.c index 17d80f751fcb..ac06ca32e9ef 100644 --- a/arch/x86/xen/p2m.c +++ b/arch/x86/xen/p2m.c @@ -98,8 +98,8 @@ EXPORT_SYMBOL_GPL(xen_p2m_size); unsigned long xen_max_p2m_pfn __read_mostly; EXPORT_SYMBOL_GPL(xen_max_p2m_pfn); -#ifdef CONFIG_XEN_BALLOON_MEMORY_HOTPLUG_LIMIT -#define P2M_LIMIT CONFIG_XEN_BALLOON_MEMORY_HOTPLUG_LIMIT +#ifdef CONFIG_XEN_MEMORY_HOTPLUG_LIMIT +#define P2M_LIMIT CONFIG_XEN_MEMORY_HOTPLUG_LIMIT #else #define P2M_LIMIT 0 #endif @@ -416,9 +416,6 @@ void __init xen_vmalloc_p2m_tree(void) xen_p2m_last_pfn = xen_max_p2m_pfn; p2m_limit = (phys_addr_t)P2M_LIMIT * 1024 * 1024 * 1024 / PAGE_SIZE; - if (!p2m_limit && IS_ENABLED(CONFIG_XEN_UNPOPULATED_ALLOC)) - p2m_limit = xen_start_info->nr_pages * XEN_EXTRA_MEM_RATIO; - vm.flags = VM_ALLOC; vm.size = ALIGN(sizeof(unsigned long) * max(xen_max_p2m_pfn, p2m_limit), PMD_SIZE * PMDS_PER_MID_PAGE); diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c index 1a3b75652fa4..8bfc10330107 100644 --- a/arch/x86/xen/setup.c +++ b/arch/x86/xen/setup.c @@ -59,6 +59,18 @@ static struct { } xen_remap_buf __initdata __aligned(PAGE_SIZE); static unsigned long xen_remap_mfn __initdata = INVALID_P2M_ENTRY; +/* + * The maximum amount of extra memory compared to the base size. The + * main scaling factor is the size of struct page. At extreme ratios + * of base:extra, all the base memory can be filled with page + * structures for the extra memory, leaving no space for anything + * else. + * + * 10x seems like a reasonable balance between scaling flexibility and + * leaving a practically usable system. + */ +#define EXTRA_MEM_RATIO (10) + static bool xen_512gb_limit __initdata = IS_ENABLED(CONFIG_XEN_512GB); static void __init xen_parse_512gb(void) @@ -778,13 +790,13 @@ char * __init xen_memory_setup(void) extra_pages += max_pages - max_pfn; /* - * Clamp the amount of extra memory to a XEN_EXTRA_MEM_RATIO + * Clamp the amount of extra memory to a EXTRA_MEM_RATIO * factor the base size. * * Make sure we have no memory above max_pages, as this area * isn't handled by the p2m management. */ - extra_pages = min3(XEN_EXTRA_MEM_RATIO * min(max_pfn, PFN_DOWN(MAXMEM)), + extra_pages = min3(EXTRA_MEM_RATIO * min(max_pfn, PFN_DOWN(MAXMEM)), extra_pages, max_pages - max_pfn); i = 0; addr = xen_e820_table.entries[0].addr; diff --git a/arch/xtensa/kernel/coprocessor.S b/arch/xtensa/kernel/coprocessor.S index c426b846beef..45cc0ae0af6f 100644 --- a/arch/xtensa/kernel/coprocessor.S +++ b/arch/xtensa/kernel/coprocessor.S @@ -100,37 +100,6 @@ LOAD_CP_REGS_TAB(7) /* - * coprocessor_flush(struct thread_info*, index) - * a2 a3 - * - * Save coprocessor registers for coprocessor 'index'. - * The register values are saved to or loaded from the coprocessor area - * inside the task_info structure. - * - * Note that this function doesn't update the coprocessor_owner information! - * - */ - -ENTRY(coprocessor_flush) - - /* reserve 4 bytes on stack to save a0 */ - abi_entry(4) - - s32i a0, a1, 0 - movi a0, .Lsave_cp_regs_jump_table - addx8 a3, a3, a0 - l32i a4, a3, 4 - l32i a3, a3, 0 - add a2, a2, a4 - beqz a3, 1f - callx0 a3 -1: l32i a0, a1, 0 - - abi_ret(4) - -ENDPROC(coprocessor_flush) - -/* * Entry condition: * * a0: trashed, original value saved on stack (PT_AREG0) @@ -245,6 +214,39 @@ ENTRY(fast_coprocessor) ENDPROC(fast_coprocessor) + .text + +/* + * coprocessor_flush(struct thread_info*, index) + * a2 a3 + * + * Save coprocessor registers for coprocessor 'index'. + * The register values are saved to or loaded from the coprocessor area + * inside the task_info structure. + * + * Note that this function doesn't update the coprocessor_owner information! + * + */ + +ENTRY(coprocessor_flush) + + /* reserve 4 bytes on stack to save a0 */ + abi_entry(4) + + s32i a0, a1, 0 + movi a0, .Lsave_cp_regs_jump_table + addx8 a3, a3, a0 + l32i a4, a3, 4 + l32i a3, a3, 0 + add a2, a2, a4 + beqz a3, 1f + callx0 a3 +1: l32i a0, a1, 0 + + abi_ret(4) + +ENDPROC(coprocessor_flush) + .data ENTRY(coprocessor_owner) diff --git a/arch/xtensa/mm/fault.c b/arch/xtensa/mm/fault.c index 7666408ce12a..95a74890c7e9 100644 --- a/arch/xtensa/mm/fault.c +++ b/arch/xtensa/mm/fault.c @@ -112,8 +112,11 @@ good_area: */ fault = handle_mm_fault(vma, address, flags, regs); - if (fault_signal_pending(fault, regs)) + if (fault_signal_pending(fault, regs)) { + if (!user_mode(regs)) + goto bad_page_fault; return; + } if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) |