diff options
Diffstat (limited to 'arch')
156 files changed, 1471 insertions, 772 deletions
diff --git a/arch/arc/boot/dts/axc003.dtsi b/arch/arc/boot/dts/axc003.dtsi index cd1edcf4f95e..3434c8131ecd 100644 --- a/arch/arc/boot/dts/axc003.dtsi +++ b/arch/arc/boot/dts/axc003.dtsi @@ -103,11 +103,11 @@ dma-coherent; }; - ehci@40000 { + usb@40000 { dma-coherent; }; - ohci@60000 { + usb@60000 { dma-coherent; }; diff --git a/arch/arc/boot/dts/axc003_idu.dtsi b/arch/arc/boot/dts/axc003_idu.dtsi index 70779386ca79..67556f4b7057 100644 --- a/arch/arc/boot/dts/axc003_idu.dtsi +++ b/arch/arc/boot/dts/axc003_idu.dtsi @@ -110,11 +110,11 @@ dma-coherent; }; - ehci@40000 { + usb@40000 { dma-coherent; }; - ohci@60000 { + usb@60000 { dma-coherent; }; diff --git a/arch/arc/boot/dts/axs10x_mb.dtsi b/arch/arc/boot/dts/axs10x_mb.dtsi index 99d3e7175bf7..b64435385304 100644 --- a/arch/arc/boot/dts/axs10x_mb.dtsi +++ b/arch/arc/boot/dts/axs10x_mb.dtsi @@ -87,13 +87,13 @@ mac-address = [00 00 00 00 00 00]; /* Filled in by U-Boot */ }; - ehci@40000 { + usb@40000 { compatible = "generic-ehci"; reg = < 0x40000 0x100 >; interrupts = < 8 >; }; - ohci@60000 { + usb@60000 { compatible = "generic-ohci"; reg = < 0x60000 0x100 >; interrupts = < 8 >; diff --git a/arch/arc/boot/dts/hsdk.dts b/arch/arc/boot/dts/hsdk.dts index f48ba03e9b5e..6691f4255077 100644 --- a/arch/arc/boot/dts/hsdk.dts +++ b/arch/arc/boot/dts/hsdk.dts @@ -234,7 +234,7 @@ }; }; - ohci@60000 { + usb@60000 { compatible = "snps,hsdk-v1.0-ohci", "generic-ohci"; reg = <0x60000 0x100>; interrupts = <15>; @@ -242,7 +242,7 @@ dma-coherent; }; - ehci@40000 { + usb@40000 { compatible = "snps,hsdk-v1.0-ehci", "generic-ehci"; reg = <0x40000 0x100>; interrupts = <15>; diff --git a/arch/arc/boot/dts/vdk_axs10x_mb.dtsi b/arch/arc/boot/dts/vdk_axs10x_mb.dtsi index cbb179770293..90a412026e64 100644 --- a/arch/arc/boot/dts/vdk_axs10x_mb.dtsi +++ b/arch/arc/boot/dts/vdk_axs10x_mb.dtsi @@ -46,7 +46,7 @@ clock-names = "stmmaceth"; }; - ehci@40000 { + usb@40000 { compatible = "generic-ehci"; reg = < 0x40000 0x100 >; interrupts = < 8 >; diff --git a/arch/arc/configs/axs101_defconfig b/arch/arc/configs/axs101_defconfig index e31a8ebc3ecc..81764160451f 100644 --- a/arch/arc/configs/axs101_defconfig +++ b/arch/arc/configs/axs101_defconfig @@ -35,9 +35,6 @@ CONFIG_IP_PNP=y CONFIG_IP_PNP_DHCP=y CONFIG_IP_PNP_BOOTP=y CONFIG_IP_PNP_RARP=y -# CONFIG_INET_XFRM_MODE_TRANSPORT is not set -# CONFIG_INET_XFRM_MODE_TUNNEL is not set -# CONFIG_INET_XFRM_MODE_BEET is not set # CONFIG_IPV6 is not set CONFIG_DEVTMPFS=y # CONFIG_STANDALONE is not set @@ -99,7 +96,6 @@ CONFIG_NFS_FS=y CONFIG_NFS_V3_ACL=y CONFIG_NLS_CODEPAGE_437=y CONFIG_NLS_ISO8859_1=y -# CONFIG_ENABLE_MUST_CHECK is not set CONFIG_STRIP_ASM_SYMS=y CONFIG_SOFTLOCKUP_DETECTOR=y CONFIG_DEFAULT_HUNG_TASK_TIMEOUT=10 diff --git a/arch/arc/configs/axs103_defconfig b/arch/arc/configs/axs103_defconfig index e0e8567f0d75..d5181275490e 100644 --- a/arch/arc/configs/axs103_defconfig +++ b/arch/arc/configs/axs103_defconfig @@ -34,9 +34,6 @@ CONFIG_IP_PNP=y CONFIG_IP_PNP_DHCP=y CONFIG_IP_PNP_BOOTP=y CONFIG_IP_PNP_RARP=y -# CONFIG_INET_XFRM_MODE_TRANSPORT is not set -# CONFIG_INET_XFRM_MODE_TUNNEL is not set -# CONFIG_INET_XFRM_MODE_BEET is not set # CONFIG_IPV6 is not set CONFIG_DEVTMPFS=y # CONFIG_STANDALONE is not set @@ -97,7 +94,6 @@ CONFIG_NFS_FS=y CONFIG_NFS_V3_ACL=y CONFIG_NLS_CODEPAGE_437=y CONFIG_NLS_ISO8859_1=y -# CONFIG_ENABLE_MUST_CHECK is not set CONFIG_STRIP_ASM_SYMS=y CONFIG_SOFTLOCKUP_DETECTOR=y CONFIG_DEFAULT_HUNG_TASK_TIMEOUT=10 diff --git a/arch/arc/configs/axs103_smp_defconfig b/arch/arc/configs/axs103_smp_defconfig index fcbc952bc75b..2f336d99a8cf 100644 --- a/arch/arc/configs/axs103_smp_defconfig +++ b/arch/arc/configs/axs103_smp_defconfig @@ -35,9 +35,6 @@ CONFIG_IP_PNP=y CONFIG_IP_PNP_DHCP=y CONFIG_IP_PNP_BOOTP=y CONFIG_IP_PNP_RARP=y -# CONFIG_INET_XFRM_MODE_TRANSPORT is not set -# CONFIG_INET_XFRM_MODE_TUNNEL is not set -# CONFIG_INET_XFRM_MODE_BEET is not set # CONFIG_IPV6 is not set CONFIG_DEVTMPFS=y # CONFIG_STANDALONE is not set @@ -100,7 +97,6 @@ CONFIG_NFS_FS=y CONFIG_NFS_V3_ACL=y CONFIG_NLS_CODEPAGE_437=y CONFIG_NLS_ISO8859_1=y -# CONFIG_ENABLE_MUST_CHECK is not set CONFIG_STRIP_ASM_SYMS=y CONFIG_SOFTLOCKUP_DETECTOR=y CONFIG_DEFAULT_HUNG_TASK_TIMEOUT=10 diff --git a/arch/arc/configs/haps_hs_defconfig b/arch/arc/configs/haps_hs_defconfig index d87ad7e88d62..899b2fd5c71d 100644 --- a/arch/arc/configs/haps_hs_defconfig +++ b/arch/arc/configs/haps_hs_defconfig @@ -59,6 +59,5 @@ CONFIG_EXT2_FS_XATTR=y CONFIG_TMPFS=y # CONFIG_MISC_FILESYSTEMS is not set CONFIG_NFS_FS=y -# CONFIG_ENABLE_MUST_CHECK is not set CONFIG_DEBUG_MEMORY_INIT=y # CONFIG_DEBUG_PREEMPT is not set diff --git a/arch/arc/configs/haps_hs_smp_defconfig b/arch/arc/configs/haps_hs_smp_defconfig index 8d82cdb7f86a..0d32aac8069f 100644 --- a/arch/arc/configs/haps_hs_smp_defconfig +++ b/arch/arc/configs/haps_hs_smp_defconfig @@ -59,6 +59,5 @@ CONFIG_EXT2_FS_XATTR=y CONFIG_TMPFS=y # CONFIG_MISC_FILESYSTEMS is not set CONFIG_NFS_FS=y -# CONFIG_ENABLE_MUST_CHECK is not set CONFIG_SOFTLOCKUP_DETECTOR=y # CONFIG_DEBUG_PREEMPT is not set diff --git a/arch/arc/configs/hsdk_defconfig b/arch/arc/configs/hsdk_defconfig index f856b03e0fb5..d18378d2c2a6 100644 --- a/arch/arc/configs/hsdk_defconfig +++ b/arch/arc/configs/hsdk_defconfig @@ -85,7 +85,6 @@ CONFIG_NFS_FS=y CONFIG_NFS_V3_ACL=y CONFIG_NLS_CODEPAGE_437=y CONFIG_NLS_ISO8859_1=y -# CONFIG_ENABLE_MUST_CHECK is not set CONFIG_STRIP_ASM_SYMS=y CONFIG_SOFTLOCKUP_DETECTOR=y CONFIG_DEFAULT_HUNG_TASK_TIMEOUT=10 diff --git a/arch/arc/configs/nsim_700_defconfig b/arch/arc/configs/nsim_700_defconfig index a1ce12bf5b16..3e9829775992 100644 --- a/arch/arc/configs/nsim_700_defconfig +++ b/arch/arc/configs/nsim_700_defconfig @@ -56,5 +56,4 @@ CONFIG_EXT2_FS_XATTR=y CONFIG_TMPFS=y # CONFIG_MISC_FILESYSTEMS is not set CONFIG_NFS_FS=y -# CONFIG_ENABLE_MUST_CHECK is not set # CONFIG_DEBUG_PREEMPT is not set diff --git a/arch/arc/configs/nsimosci_defconfig b/arch/arc/configs/nsimosci_defconfig index ca10f4a2c823..502c87f351c8 100644 --- a/arch/arc/configs/nsimosci_defconfig +++ b/arch/arc/configs/nsimosci_defconfig @@ -65,4 +65,3 @@ CONFIG_TMPFS=y # CONFIG_MISC_FILESYSTEMS is not set CONFIG_NFS_FS=y CONFIG_NFS_V3_ACL=y -# CONFIG_ENABLE_MUST_CHECK is not set diff --git a/arch/arc/configs/nsimosci_hs_defconfig b/arch/arc/configs/nsimosci_hs_defconfig index 31b6ec3683c6..f721cc3997d0 100644 --- a/arch/arc/configs/nsimosci_hs_defconfig +++ b/arch/arc/configs/nsimosci_hs_defconfig @@ -63,4 +63,3 @@ CONFIG_TMPFS=y # CONFIG_MISC_FILESYSTEMS is not set CONFIG_NFS_FS=y CONFIG_NFS_V3_ACL=y -# CONFIG_ENABLE_MUST_CHECK is not set diff --git a/arch/arc/configs/nsimosci_hs_smp_defconfig b/arch/arc/configs/nsimosci_hs_smp_defconfig index 41a0037f48a5..1419fc946a08 100644 --- a/arch/arc/configs/nsimosci_hs_smp_defconfig +++ b/arch/arc/configs/nsimosci_hs_smp_defconfig @@ -26,9 +26,6 @@ CONFIG_UNIX=y CONFIG_UNIX_DIAG=y CONFIG_NET_KEY=y CONFIG_INET=y -# CONFIG_INET_XFRM_MODE_TRANSPORT is not set -# CONFIG_INET_XFRM_MODE_TUNNEL is not set -# CONFIG_INET_XFRM_MODE_BEET is not set # CONFIG_IPV6 is not set # CONFIG_WIRELESS is not set CONFIG_DEVTMPFS=y @@ -37,7 +34,6 @@ CONFIG_DEVTMPFS=y # CONFIG_BLK_DEV is not set CONFIG_NETDEVICES=y # CONFIG_NET_VENDOR_ARC is not set -# CONFIG_NET_CADENCE is not set # CONFIG_NET_VENDOR_BROADCOM is not set CONFIG_EZCHIP_NPS_MANAGEMENT_ENET=y # CONFIG_NET_VENDOR_INTEL is not set @@ -74,5 +70,5 @@ CONFIG_TMPFS=y # CONFIG_MISC_FILESYSTEMS is not set CONFIG_NFS_FS=y CONFIG_NFS_V3_ACL=y -# CONFIG_ENABLE_MUST_CHECK is not set CONFIG_FTRACE=y +# CONFIG_NET_VENDOR_CADENCE is not set diff --git a/arch/arc/configs/tb10x_defconfig b/arch/arc/configs/tb10x_defconfig index 4a94d1684ed6..6f0d2be9d926 100644 --- a/arch/arc/configs/tb10x_defconfig +++ b/arch/arc/configs/tb10x_defconfig @@ -35,15 +35,11 @@ CONFIG_PACKET=y CONFIG_UNIX=y CONFIG_INET=y CONFIG_IP_MULTICAST=y -# CONFIG_INET_XFRM_MODE_TRANSPORT is not set -# CONFIG_INET_XFRM_MODE_TUNNEL is not set -# CONFIG_INET_XFRM_MODE_BEET is not set # CONFIG_INET_DIAG is not set # CONFIG_IPV6 is not set # CONFIG_WIRELESS is not set CONFIG_DEVTMPFS=y CONFIG_NETDEVICES=y -# CONFIG_NET_CADENCE is not set # CONFIG_NET_VENDOR_BROADCOM is not set # CONFIG_NET_VENDOR_INTEL is not set # CONFIG_NET_VENDOR_MARVELL is not set @@ -94,12 +90,11 @@ CONFIG_DEBUG_INFO_DWARF_TOOLCHAIN_DEFAULT=y CONFIG_STRIP_ASM_SYMS=y CONFIG_DEBUG_FS=y CONFIG_HEADERS_INSTALL=y -CONFIG_HEADERS_CHECK=y CONFIG_DEBUG_SECTION_MISMATCH=y CONFIG_MAGIC_SYSRQ=y CONFIG_DEBUG_MEMORY_INIT=y CONFIG_DEBUG_STACKOVERFLOW=y CONFIG_DETECT_HUNG_TASK=y CONFIG_SCHEDSTATS=y -CONFIG_TIMER_STATS=y # CONFIG_CRYPTO_HW is not set +# CONFIG_NET_VENDOR_CADENCE is not set diff --git a/arch/arc/configs/vdk_hs38_defconfig b/arch/arc/configs/vdk_hs38_defconfig index 0c3b21416819..d3ef189c75f8 100644 --- a/arch/arc/configs/vdk_hs38_defconfig +++ b/arch/arc/configs/vdk_hs38_defconfig @@ -58,8 +58,6 @@ CONFIG_SERIAL_OF_PLATFORM=y # CONFIG_HW_RANDOM is not set # CONFIG_HWMON is not set CONFIG_FB=y -CONFIG_ARCPGU_RGB888=y -CONFIG_ARCPGU_DISPTYPE=0 # CONFIG_VGA_CONSOLE is not set CONFIG_FRAMEBUFFER_CONSOLE=y CONFIG_FRAMEBUFFER_CONSOLE_DETECT_PRIMARY=y @@ -87,7 +85,6 @@ CONFIG_NFS_FS=y CONFIG_NFS_V3_ACL=y CONFIG_NLS_CODEPAGE_437=y CONFIG_NLS_ISO8859_1=y -# CONFIG_ENABLE_MUST_CHECK is not set CONFIG_STRIP_ASM_SYMS=y CONFIG_DEBUG_SHIRQ=y CONFIG_SOFTLOCKUP_DETECTOR=y diff --git a/arch/arc/configs/vdk_hs38_smp_defconfig b/arch/arc/configs/vdk_hs38_smp_defconfig index f9ad9d3ee702..944b347025fd 100644 --- a/arch/arc/configs/vdk_hs38_smp_defconfig +++ b/arch/arc/configs/vdk_hs38_smp_defconfig @@ -91,7 +91,6 @@ CONFIG_NFS_FS=y CONFIG_NFS_V3_ACL=y CONFIG_NLS_CODEPAGE_437=y CONFIG_NLS_ISO8859_1=y -# CONFIG_ENABLE_MUST_CHECK is not set CONFIG_STRIP_ASM_SYMS=y CONFIG_DEBUG_SHIRQ=y CONFIG_SOFTLOCKUP_DETECTOR=y diff --git a/arch/arc/include/asm/bitops.h b/arch/arc/include/asm/bitops.h index bdb7e190a294..f5a936496f06 100644 --- a/arch/arc/include/asm/bitops.h +++ b/arch/arc/include/asm/bitops.h @@ -82,7 +82,7 @@ static inline __attribute__ ((const)) int fls(unsigned int x) /* * __fls: Similar to fls, but zero based (0-31) */ -static inline __attribute__ ((const)) int __fls(unsigned long x) +static inline __attribute__ ((const)) unsigned long __fls(unsigned long x) { if (!x) return 0; @@ -131,7 +131,7 @@ static inline __attribute__ ((const)) int fls(unsigned int x) /* * __fls: Similar to fls, but zero based (0-31). Also 0 if no bit set */ -static inline __attribute__ ((const)) int __fls(unsigned long x) +static inline __attribute__ ((const)) unsigned long __fls(unsigned long x) { /* FLS insn has exactly same semantics as the API */ return __builtin_arc_fls(x); diff --git a/arch/arc/include/asm/entry-compact.h b/arch/arc/include/asm/entry-compact.h index 5aab4f93ab8a..67ff06e15cea 100644 --- a/arch/arc/include/asm/entry-compact.h +++ b/arch/arc/include/asm/entry-compact.h @@ -21,7 +21,7 @@ * r25 contains the kernel current task ptr * - Defined Stack Switching Macro to be reused in all intr/excp hdlrs * - Shaved off 11 instructions from RESTORE_ALL_INT1 by using the - * address Write back load ld.ab instead of seperate ld/add instn + * address Write back load ld.ab instead of separate ld/add instn * * Amit Bhor, Sameer Dhavale: Codito Technologies 2004 */ diff --git a/arch/arc/include/asm/io.h b/arch/arc/include/asm/io.h index 8f777d6441a5..80347382a380 100644 --- a/arch/arc/include/asm/io.h +++ b/arch/arc/include/asm/io.h @@ -32,7 +32,7 @@ static inline void ioport_unmap(void __iomem *addr) { } -extern void iounmap(const void __iomem *addr); +extern void iounmap(const volatile void __iomem *addr); /* * io{read,write}{16,32}be() macros diff --git a/arch/arc/include/asm/pgtable-levels.h b/arch/arc/include/asm/pgtable-levels.h index 64ca25d199be..ef68758b69f7 100644 --- a/arch/arc/include/asm/pgtable-levels.h +++ b/arch/arc/include/asm/pgtable-levels.h @@ -161,7 +161,7 @@ #define pmd_pfn(pmd) ((pmd_val(pmd) & PAGE_MASK) >> PAGE_SHIFT) #define pmd_page(pmd) virt_to_page(pmd_page_vaddr(pmd)) #define set_pmd(pmdp, pmd) (*(pmdp) = pmd) -#define pmd_pgtable(pmd) ((pgtable_t) pmd_page_vaddr(pmd)) +#define pmd_pgtable(pmd) ((pgtable_t) pmd_page(pmd)) /* * 4th level paging: pte diff --git a/arch/arc/kernel/smp.c b/arch/arc/kernel/smp.c index ab9e75e90f72..ad93fe6e4b77 100644 --- a/arch/arc/kernel/smp.c +++ b/arch/arc/kernel/smp.c @@ -385,7 +385,7 @@ irqreturn_t do_IPI(int irq, void *dev_id) * API called by platform code to hookup arch-common ISR to their IPI IRQ * * Note: If IPI is provided by platform (vs. say ARC MCIP), their intc setup/map - * function needs to call call irq_set_percpu_devid() for IPI IRQ, otherwise + * function needs to call irq_set_percpu_devid() for IPI IRQ, otherwise * request_percpu_irq() below will fail */ static DEFINE_PER_CPU(int, ipi_dev); diff --git a/arch/arc/mm/cache.c b/arch/arc/mm/cache.c index 5446967ea98d..55c6de138eae 100644 --- a/arch/arc/mm/cache.c +++ b/arch/arc/mm/cache.c @@ -750,7 +750,7 @@ static inline void arc_slc_enable(void) * -In SMP, if hardware caches are coherent * * There's a corollary case, where kernel READs from a userspace mapped page. - * If the U-mapping is not congruent to to K-mapping, former needs flushing. + * If the U-mapping is not congruent to K-mapping, former needs flushing. */ void flush_dcache_page(struct page *page) { @@ -910,7 +910,7 @@ EXPORT_SYMBOL(flush_icache_range); * @vaddr is typically user vaddr (breakpoint) or kernel vaddr (vmalloc) * However in one instance, when called by kprobe (for a breakpt in * builtin kernel code) @vaddr will be paddr only, meaning CDU operation will - * use a paddr to index the cache (despite VIPT). This is fine since since a + * use a paddr to index the cache (despite VIPT). This is fine since a * builtin kernel page will not have any virtual mappings. * kprobe on loadable module will be kernel vaddr. */ diff --git a/arch/arc/mm/ioremap.c b/arch/arc/mm/ioremap.c index 0ee75aca6e10..712c2311daef 100644 --- a/arch/arc/mm/ioremap.c +++ b/arch/arc/mm/ioremap.c @@ -94,7 +94,7 @@ void __iomem *ioremap_prot(phys_addr_t paddr, unsigned long size, EXPORT_SYMBOL(ioremap_prot); -void iounmap(const void __iomem *addr) +void iounmap(const volatile void __iomem *addr) { /* weird double cast to handle phys_addr_t > 32 bits */ if (arc_uncached_addr_space((phys_addr_t)(u32)addr)) diff --git a/arch/arm/boot/dts/imx6q-yapp4-crux.dts b/arch/arm/boot/dts/imx6q-yapp4-crux.dts index 15f4824a5142..bddf3822ebf7 100644 --- a/arch/arm/boot/dts/imx6q-yapp4-crux.dts +++ b/arch/arm/boot/dts/imx6q-yapp4-crux.dts @@ -33,6 +33,10 @@ status = "okay"; }; +®_pu { + regulator-always-on; +}; + ®_usb_h1_vbus { status = "okay"; }; diff --git a/arch/arm/boot/dts/imx6qdl-gw5910.dtsi b/arch/arm/boot/dts/imx6qdl-gw5910.dtsi index 68e5ab2e27e2..6bb4855d13ce 100644 --- a/arch/arm/boot/dts/imx6qdl-gw5910.dtsi +++ b/arch/arm/boot/dts/imx6qdl-gw5910.dtsi @@ -29,7 +29,7 @@ user-pb { label = "user_pb"; - gpios = <&gsc_gpio 0 GPIO_ACTIVE_LOW>; + gpios = <&gsc_gpio 2 GPIO_ACTIVE_LOW>; linux,code = <BTN_0>; }; diff --git a/arch/arm/boot/dts/imx6qdl-gw5913.dtsi b/arch/arm/boot/dts/imx6qdl-gw5913.dtsi index 8e23cec7149e..696427b487f0 100644 --- a/arch/arm/boot/dts/imx6qdl-gw5913.dtsi +++ b/arch/arm/boot/dts/imx6qdl-gw5913.dtsi @@ -26,7 +26,7 @@ user-pb { label = "user_pb"; - gpios = <&gsc_gpio 0 GPIO_ACTIVE_LOW>; + gpios = <&gsc_gpio 2 GPIO_ACTIVE_LOW>; linux,code = <BTN_0>; }; diff --git a/arch/arm/boot/dts/imx6qp-yapp4-crux-plus.dts b/arch/arm/boot/dts/imx6qp-yapp4-crux-plus.dts index cea165f2161a..afaf4a6759d4 100644 --- a/arch/arm/boot/dts/imx6qp-yapp4-crux-plus.dts +++ b/arch/arm/boot/dts/imx6qp-yapp4-crux-plus.dts @@ -33,6 +33,10 @@ status = "okay"; }; +®_pu { + regulator-always-on; +}; + ®_usb_h1_vbus { status = "okay"; }; diff --git a/arch/arm/boot/dts/ste-href.dtsi b/arch/arm/boot/dts/ste-href.dtsi index fbaa0ce46427..8f1bb78fc1e4 100644 --- a/arch/arm/boot/dts/ste-href.dtsi +++ b/arch/arm/boot/dts/ste-href.dtsi @@ -24,6 +24,14 @@ polling-delay = <0>; polling-delay-passive = <0>; thermal-sensors = <&bat_therm>; + + trips { + battery-crit-hi { + temperature = <70000>; + hysteresis = <2000>; + type = "critical"; + }; + }; }; }; diff --git a/arch/arm/boot/dts/ste-snowball.dts b/arch/arm/boot/dts/ste-snowball.dts index 1c9094f24893..e2f0cdacba7d 100644 --- a/arch/arm/boot/dts/ste-snowball.dts +++ b/arch/arm/boot/dts/ste-snowball.dts @@ -28,6 +28,14 @@ polling-delay = <0>; polling-delay-passive = <0>; thermal-sensors = <&bat_therm>; + + trips { + battery-crit-hi { + temperature = <70000>; + hysteresis = <2000>; + type = "critical"; + }; + }; }; }; diff --git a/arch/arm/boot/dts/ste-ux500-samsung-codina-tmo.dts b/arch/arm/boot/dts/ste-ux500-samsung-codina-tmo.dts index d6940e0afa86..27a3ab7e25e1 100644 --- a/arch/arm/boot/dts/ste-ux500-samsung-codina-tmo.dts +++ b/arch/arm/boot/dts/ste-ux500-samsung-codina-tmo.dts @@ -44,6 +44,14 @@ polling-delay = <0>; polling-delay-passive = <0>; thermal-sensors = <&bat_therm>; + + trips { + battery-crit-hi { + temperature = <70000>; + hysteresis = <2000>; + type = "critical"; + }; + }; }; }; diff --git a/arch/arm/boot/dts/ste-ux500-samsung-codina.dts b/arch/arm/boot/dts/ste-ux500-samsung-codina.dts index 5f41256d7f4b..b88f0c07873d 100644 --- a/arch/arm/boot/dts/ste-ux500-samsung-codina.dts +++ b/arch/arm/boot/dts/ste-ux500-samsung-codina.dts @@ -57,6 +57,14 @@ polling-delay = <0>; polling-delay-passive = <0>; thermal-sensors = <&bat_therm>; + + trips { + battery-crit-hi { + temperature = <70000>; + hysteresis = <2000>; + type = "critical"; + }; + }; }; }; diff --git a/arch/arm/boot/dts/ste-ux500-samsung-gavini.dts b/arch/arm/boot/dts/ste-ux500-samsung-gavini.dts index 806da3fc33cd..7231bc745200 100644 --- a/arch/arm/boot/dts/ste-ux500-samsung-gavini.dts +++ b/arch/arm/boot/dts/ste-ux500-samsung-gavini.dts @@ -30,6 +30,14 @@ polling-delay = <0>; polling-delay-passive = <0>; thermal-sensors = <&bat_therm>; + + trips { + battery-crit-hi { + temperature = <70000>; + hysteresis = <2000>; + type = "critical"; + }; + }; }; }; diff --git a/arch/arm/boot/dts/ste-ux500-samsung-golden.dts b/arch/arm/boot/dts/ste-ux500-samsung-golden.dts index b0dce91aff4b..9604695edf53 100644 --- a/arch/arm/boot/dts/ste-ux500-samsung-golden.dts +++ b/arch/arm/boot/dts/ste-ux500-samsung-golden.dts @@ -35,6 +35,14 @@ polling-delay = <0>; polling-delay-passive = <0>; thermal-sensors = <&bat_therm>; + + trips { + battery-crit-hi { + temperature = <70000>; + hysteresis = <2000>; + type = "critical"; + }; + }; }; }; diff --git a/arch/arm/boot/dts/ste-ux500-samsung-janice.dts b/arch/arm/boot/dts/ste-ux500-samsung-janice.dts index ed5c79c3d04b..69387e8754a9 100644 --- a/arch/arm/boot/dts/ste-ux500-samsung-janice.dts +++ b/arch/arm/boot/dts/ste-ux500-samsung-janice.dts @@ -30,6 +30,14 @@ polling-delay = <0>; polling-delay-passive = <0>; thermal-sensors = <&bat_therm>; + + trips { + battery-crit-hi { + temperature = <70000>; + hysteresis = <2000>; + type = "critical"; + }; + }; }; }; diff --git a/arch/arm/boot/dts/ste-ux500-samsung-kyle.dts b/arch/arm/boot/dts/ste-ux500-samsung-kyle.dts index c57676faf181..167846df3104 100644 --- a/arch/arm/boot/dts/ste-ux500-samsung-kyle.dts +++ b/arch/arm/boot/dts/ste-ux500-samsung-kyle.dts @@ -34,6 +34,14 @@ polling-delay = <0>; polling-delay-passive = <0>; thermal-sensors = <&bat_therm>; + + trips { + battery-crit-hi { + temperature = <70000>; + hysteresis = <2000>; + type = "critical"; + }; + }; }; }; diff --git a/arch/arm/boot/dts/ste-ux500-samsung-skomer.dts b/arch/arm/boot/dts/ste-ux500-samsung-skomer.dts index 81b341a5ae45..93e5f5ed888d 100644 --- a/arch/arm/boot/dts/ste-ux500-samsung-skomer.dts +++ b/arch/arm/boot/dts/ste-ux500-samsung-skomer.dts @@ -30,6 +30,14 @@ polling-delay = <0>; polling-delay-passive = <0>; thermal-sensors = <&bat_therm>; + + trips { + battery-crit-hi { + temperature = <70000>; + hysteresis = <2000>; + type = "critical"; + }; + }; }; }; diff --git a/arch/arm64/boot/dts/arm/juno-base.dtsi b/arch/arm64/boot/dts/arm/juno-base.dtsi index 2f27619d8abd..8b4d280b1e7e 100644 --- a/arch/arm64/boot/dts/arm/juno-base.dtsi +++ b/arch/arm64/boot/dts/arm/juno-base.dtsi @@ -751,12 +751,26 @@ polling-delay = <1000>; polling-delay-passive = <100>; thermal-sensors = <&scpi_sensors0 0>; + trips { + pmic_crit0: trip0 { + temperature = <90000>; + hysteresis = <2000>; + type = "critical"; + }; + }; }; soc { polling-delay = <1000>; polling-delay-passive = <100>; thermal-sensors = <&scpi_sensors0 3>; + trips { + soc_crit0: trip0 { + temperature = <80000>; + hysteresis = <2000>; + type = "critical"; + }; + }; }; big_cluster_thermal_zone: big-cluster { diff --git a/arch/arm64/boot/dts/freescale/fsl-ls1088a.dtsi b/arch/arm64/boot/dts/freescale/fsl-ls1088a.dtsi index 421d879013d7..260d045dbd9a 100644 --- a/arch/arm64/boot/dts/freescale/fsl-ls1088a.dtsi +++ b/arch/arm64/boot/dts/freescale/fsl-ls1088a.dtsi @@ -779,6 +779,9 @@ little-endian; #address-cells = <1>; #size-cells = <0>; + clock-frequency = <2500000>; + clocks = <&clockgen QORIQ_CLK_PLATFORM_PLL + QORIQ_CLK_PLL_DIV(1)>; status = "disabled"; }; @@ -788,6 +791,9 @@ little-endian; #address-cells = <1>; #size-cells = <0>; + clock-frequency = <2500000>; + clocks = <&clockgen QORIQ_CLK_PLATFORM_PLL + QORIQ_CLK_PLL_DIV(1)>; status = "disabled"; }; diff --git a/arch/arm64/boot/dts/freescale/fsl-ls208xa.dtsi b/arch/arm64/boot/dts/freescale/fsl-ls208xa.dtsi index f1b9cc8714dc..348d9e3a9125 100644 --- a/arch/arm64/boot/dts/freescale/fsl-ls208xa.dtsi +++ b/arch/arm64/boot/dts/freescale/fsl-ls208xa.dtsi @@ -532,6 +532,9 @@ little-endian; #address-cells = <1>; #size-cells = <0>; + clock-frequency = <2500000>; + clocks = <&clockgen QORIQ_CLK_PLATFORM_PLL + QORIQ_CLK_PLL_DIV(2)>; status = "disabled"; }; @@ -541,6 +544,9 @@ little-endian; #address-cells = <1>; #size-cells = <0>; + clock-frequency = <2500000>; + clocks = <&clockgen QORIQ_CLK_PLATFORM_PLL + QORIQ_CLK_PLL_DIV(2)>; status = "disabled"; }; diff --git a/arch/arm64/boot/dts/freescale/fsl-lx2160a.dtsi b/arch/arm64/boot/dts/freescale/fsl-lx2160a.dtsi index 6680fb2a6dc9..8c76d86cb756 100644 --- a/arch/arm64/boot/dts/freescale/fsl-lx2160a.dtsi +++ b/arch/arm64/boot/dts/freescale/fsl-lx2160a.dtsi @@ -1385,6 +1385,9 @@ #address-cells = <1>; #size-cells = <0>; little-endian; + clock-frequency = <2500000>; + clocks = <&clockgen QORIQ_CLK_PLATFORM_PLL + QORIQ_CLK_PLL_DIV(2)>; status = "disabled"; }; @@ -1395,6 +1398,9 @@ little-endian; #address-cells = <1>; #size-cells = <0>; + clock-frequency = <2500000>; + clocks = <&clockgen QORIQ_CLK_PLATFORM_PLL + QORIQ_CLK_PLL_DIV(2)>; status = "disabled"; }; diff --git a/arch/arm64/boot/dts/freescale/imx8-ss-conn.dtsi b/arch/arm64/boot/dts/freescale/imx8-ss-conn.dtsi index 82a1c4488378..10370d1a6c6d 100644 --- a/arch/arm64/boot/dts/freescale/imx8-ss-conn.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8-ss-conn.dtsi @@ -38,9 +38,9 @@ conn_subsys: bus@5b000000 { interrupts = <GIC_SPI 232 IRQ_TYPE_LEVEL_HIGH>; reg = <0x5b010000 0x10000>; clocks = <&sdhc0_lpcg IMX_LPCG_CLK_4>, - <&sdhc0_lpcg IMX_LPCG_CLK_5>, - <&sdhc0_lpcg IMX_LPCG_CLK_0>; - clock-names = "ipg", "per", "ahb"; + <&sdhc0_lpcg IMX_LPCG_CLK_0>, + <&sdhc0_lpcg IMX_LPCG_CLK_5>; + clock-names = "ipg", "ahb", "per"; power-domains = <&pd IMX_SC_R_SDHC_0>; status = "disabled"; }; @@ -49,9 +49,9 @@ conn_subsys: bus@5b000000 { interrupts = <GIC_SPI 233 IRQ_TYPE_LEVEL_HIGH>; reg = <0x5b020000 0x10000>; clocks = <&sdhc1_lpcg IMX_LPCG_CLK_4>, - <&sdhc1_lpcg IMX_LPCG_CLK_5>, - <&sdhc1_lpcg IMX_LPCG_CLK_0>; - clock-names = "ipg", "per", "ahb"; + <&sdhc1_lpcg IMX_LPCG_CLK_0>, + <&sdhc1_lpcg IMX_LPCG_CLK_5>; + clock-names = "ipg", "ahb", "per"; power-domains = <&pd IMX_SC_R_SDHC_1>; fsl,tuning-start-tap = <20>; fsl,tuning-step = <2>; @@ -62,9 +62,9 @@ conn_subsys: bus@5b000000 { interrupts = <GIC_SPI 234 IRQ_TYPE_LEVEL_HIGH>; reg = <0x5b030000 0x10000>; clocks = <&sdhc2_lpcg IMX_LPCG_CLK_4>, - <&sdhc2_lpcg IMX_LPCG_CLK_5>, - <&sdhc2_lpcg IMX_LPCG_CLK_0>; - clock-names = "ipg", "per", "ahb"; + <&sdhc2_lpcg IMX_LPCG_CLK_0>, + <&sdhc2_lpcg IMX_LPCG_CLK_5>; + clock-names = "ipg", "ahb", "per"; power-domains = <&pd IMX_SC_R_SDHC_2>; status = "disabled"; }; diff --git a/arch/arm64/boot/dts/freescale/imx8mm-mx8menlo.dts b/arch/arm64/boot/dts/freescale/imx8mm-mx8menlo.dts index 32f6f2f50c10..43e89859c044 100644 --- a/arch/arm64/boot/dts/freescale/imx8mm-mx8menlo.dts +++ b/arch/arm64/boot/dts/freescale/imx8mm-mx8menlo.dts @@ -250,21 +250,21 @@ /* SODIMM 96 */ MX8MM_IOMUXC_SAI1_RXD2_GPIO4_IO4 0x1c4 /* CPLD_D[7] */ - MX8MM_IOMUXC_SAI1_RXD3_GPIO4_IO5 0x1c4 + MX8MM_IOMUXC_SAI1_RXD3_GPIO4_IO5 0x184 /* CPLD_D[6] */ - MX8MM_IOMUXC_SAI1_RXFS_GPIO4_IO0 0x1c4 + MX8MM_IOMUXC_SAI1_RXFS_GPIO4_IO0 0x184 /* CPLD_D[5] */ - MX8MM_IOMUXC_SAI1_TXC_GPIO4_IO11 0x1c4 + MX8MM_IOMUXC_SAI1_TXC_GPIO4_IO11 0x184 /* CPLD_D[4] */ - MX8MM_IOMUXC_SAI1_TXD0_GPIO4_IO12 0x1c4 + MX8MM_IOMUXC_SAI1_TXD0_GPIO4_IO12 0x184 /* CPLD_D[3] */ - MX8MM_IOMUXC_SAI1_TXD1_GPIO4_IO13 0x1c4 + MX8MM_IOMUXC_SAI1_TXD1_GPIO4_IO13 0x184 /* CPLD_D[2] */ - MX8MM_IOMUXC_SAI1_TXD2_GPIO4_IO14 0x1c4 + MX8MM_IOMUXC_SAI1_TXD2_GPIO4_IO14 0x184 /* CPLD_D[1] */ - MX8MM_IOMUXC_SAI1_TXD3_GPIO4_IO15 0x1c4 + MX8MM_IOMUXC_SAI1_TXD3_GPIO4_IO15 0x184 /* CPLD_D[0] */ - MX8MM_IOMUXC_SAI1_TXD4_GPIO4_IO16 0x1c4 + MX8MM_IOMUXC_SAI1_TXD4_GPIO4_IO16 0x184 /* KBD_intK */ MX8MM_IOMUXC_SAI2_MCLK_GPIO4_IO27 0x1c4 /* DISP_reset */ diff --git a/arch/arm64/boot/dts/freescale/imx8mm.dtsi b/arch/arm64/boot/dts/freescale/imx8mm.dtsi index afb90f59c83c..dabd94dc30c4 100644 --- a/arch/arm64/boot/dts/freescale/imx8mm.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mm.dtsi @@ -276,6 +276,7 @@ assigned-clocks = <&clk IMX8MM_CLK_USB_PHY_REF>; assigned-clock-parents = <&clk IMX8MM_SYS_PLL1_100M>; clock-names = "main_clk"; + power-domains = <&pgc_otg1>; }; usbphynop2: usbphynop2 { @@ -285,6 +286,7 @@ assigned-clocks = <&clk IMX8MM_CLK_USB_PHY_REF>; assigned-clock-parents = <&clk IMX8MM_SYS_PLL1_100M>; clock-names = "main_clk"; + power-domains = <&pgc_otg2>; }; soc: soc@0 { @@ -674,13 +676,11 @@ pgc_otg1: power-domain@2 { #power-domain-cells = <0>; reg = <IMX8MM_POWER_DOMAIN_OTG1>; - power-domains = <&pgc_hsiomix>; }; pgc_otg2: power-domain@3 { #power-domain-cells = <0>; reg = <IMX8MM_POWER_DOMAIN_OTG2>; - power-domains = <&pgc_hsiomix>; }; pgc_gpumix: power-domain@4 { @@ -1186,7 +1186,7 @@ assigned-clock-parents = <&clk IMX8MM_SYS_PLL2_500M>; phys = <&usbphynop1>; fsl,usbmisc = <&usbmisc1 0>; - power-domains = <&pgc_otg1>; + power-domains = <&pgc_hsiomix>; status = "disabled"; }; @@ -1206,7 +1206,7 @@ assigned-clock-parents = <&clk IMX8MM_SYS_PLL2_500M>; phys = <&usbphynop2>; fsl,usbmisc = <&usbmisc2 0>; - power-domains = <&pgc_otg2>; + power-domains = <&pgc_hsiomix>; status = "disabled"; }; diff --git a/arch/arm64/boot/dts/freescale/imx8mn.dtsi b/arch/arm64/boot/dts/freescale/imx8mn.dtsi index cb2836bfbd95..ad0b99adf691 100644 --- a/arch/arm64/boot/dts/freescale/imx8mn.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mn.dtsi @@ -662,7 +662,6 @@ pgc_otg1: power-domain@1 { #power-domain-cells = <0>; reg = <IMX8MN_POWER_DOMAIN_OTG1>; - power-domains = <&pgc_hsiomix>; }; pgc_gpumix: power-domain@2 { @@ -1076,7 +1075,7 @@ assigned-clock-parents = <&clk IMX8MN_SYS_PLL2_500M>; phys = <&usbphynop1>; fsl,usbmisc = <&usbmisc1 0>; - power-domains = <&pgc_otg1>; + power-domains = <&pgc_hsiomix>; status = "disabled"; }; @@ -1175,5 +1174,6 @@ assigned-clocks = <&clk IMX8MN_CLK_USB_PHY_REF>; assigned-clock-parents = <&clk IMX8MN_SYS_PLL1_100M>; clock-names = "main_clk"; + power-domains = <&pgc_otg1>; }; }; diff --git a/arch/arm64/boot/dts/freescale/imx8mp-verdin.dtsi b/arch/arm64/boot/dts/freescale/imx8mp-verdin.dtsi index 7b712d1888ea..5dcd1de586b5 100644 --- a/arch/arm64/boot/dts/freescale/imx8mp-verdin.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mp-verdin.dtsi @@ -354,16 +354,6 @@ "SODIMM_82", "SODIMM_70", "SODIMM_72"; - - ctrl-sleep-moci-hog { - gpio-hog; - /* Verdin CTRL_SLEEP_MOCI# (SODIMM 256) */ - gpios = <29 GPIO_ACTIVE_HIGH>; - line-name = "CTRL_SLEEP_MOCI#"; - output-high; - pinctrl-names = "default"; - pinctrl-0 = <&pinctrl_ctrl_sleep_moci>; - }; }; &gpio3 { @@ -432,6 +422,16 @@ "SODIMM_256", "SODIMM_48", "SODIMM_44"; + + ctrl-sleep-moci-hog { + gpio-hog; + /* Verdin CTRL_SLEEP_MOCI# (SODIMM 256) */ + gpios = <29 GPIO_ACTIVE_HIGH>; + line-name = "CTRL_SLEEP_MOCI#"; + output-high; + pinctrl-names = "default"; + pinctrl-0 = <&pinctrl_ctrl_sleep_moci>; + }; }; /* On-module I2C */ diff --git a/arch/arm64/boot/dts/freescale/imx93.dtsi b/arch/arm64/boot/dts/freescale/imx93.dtsi index 3a5713bb4880..0247866fc86b 100644 --- a/arch/arm64/boot/dts/freescale/imx93.dtsi +++ b/arch/arm64/boot/dts/freescale/imx93.dtsi @@ -451,7 +451,7 @@ clocks = <&clk IMX93_CLK_GPIO2_GATE>, <&clk IMX93_CLK_GPIO2_GATE>; clock-names = "gpio", "port"; - gpio-ranges = <&iomuxc 0 32 32>; + gpio-ranges = <&iomuxc 0 4 30>; }; gpio3: gpio@43820080 { @@ -465,7 +465,8 @@ clocks = <&clk IMX93_CLK_GPIO3_GATE>, <&clk IMX93_CLK_GPIO3_GATE>; clock-names = "gpio", "port"; - gpio-ranges = <&iomuxc 0 64 32>; + gpio-ranges = <&iomuxc 0 84 8>, <&iomuxc 8 66 18>, + <&iomuxc 26 34 2>, <&iomuxc 28 0 4>; }; gpio4: gpio@43830080 { @@ -479,7 +480,7 @@ clocks = <&clk IMX93_CLK_GPIO4_GATE>, <&clk IMX93_CLK_GPIO4_GATE>; clock-names = "gpio", "port"; - gpio-ranges = <&iomuxc 0 96 32>; + gpio-ranges = <&iomuxc 0 38 28>, <&iomuxc 28 36 2>; }; gpio1: gpio@47400080 { @@ -493,7 +494,7 @@ clocks = <&clk IMX93_CLK_GPIO1_GATE>, <&clk IMX93_CLK_GPIO1_GATE>; clock-names = "gpio", "port"; - gpio-ranges = <&iomuxc 0 0 32>; + gpio-ranges = <&iomuxc 0 92 16>; }; s4muap: mailbox@47520000 { @@ -501,7 +502,7 @@ reg = <0x47520000 0x10000>; interrupts = <GIC_SPI 31 IRQ_TYPE_LEVEL_HIGH>, <GIC_SPI 30 IRQ_TYPE_LEVEL_HIGH>; - interrupt-names = "txirq", "rxirq"; + interrupt-names = "tx", "rx"; #mbox-cells = <2>; }; diff --git a/arch/arm64/include/asm/efi.h b/arch/arm64/include/asm/efi.h index 439e2bc5d5d8..d6cf535d8352 100644 --- a/arch/arm64/include/asm/efi.h +++ b/arch/arm64/include/asm/efi.h @@ -14,8 +14,16 @@ #ifdef CONFIG_EFI extern void efi_init(void); + +bool efi_runtime_fixup_exception(struct pt_regs *regs, const char *msg); #else #define efi_init() + +static inline +bool efi_runtime_fixup_exception(struct pt_regs *regs, const char *msg) +{ + return false; +} #endif int efi_create_mapping(struct mm_struct *mm, efi_memory_desc_t *md); diff --git a/arch/arm64/include/asm/kvm_pgtable.h b/arch/arm64/include/asm/kvm_pgtable.h index 1b098bd4cd37..3252eb50ecfe 100644 --- a/arch/arm64/include/asm/kvm_pgtable.h +++ b/arch/arm64/include/asm/kvm_pgtable.h @@ -13,6 +13,18 @@ #define KVM_PGTABLE_MAX_LEVELS 4U +/* + * The largest supported block sizes for KVM (no 52-bit PA support): + * - 4K (level 1): 1GB + * - 16K (level 2): 32MB + * - 64K (level 2): 512MB + */ +#ifdef CONFIG_ARM64_4K_PAGES +#define KVM_PGTABLE_MIN_BLOCK_LEVEL 1U +#else +#define KVM_PGTABLE_MIN_BLOCK_LEVEL 2U +#endif + static inline u64 kvm_get_parange(u64 mmfr0) { u64 parange = cpuid_feature_extract_unsigned_field(mmfr0, @@ -58,11 +70,7 @@ static inline u64 kvm_granule_size(u32 level) static inline bool kvm_level_supports_block_mapping(u32 level) { - /* - * Reject invalid block mappings and don't bother with 4TB mappings for - * 52-bit PAs. - */ - return !(level == 0 || (PAGE_SIZE != SZ_4K && level == 1)); + return level >= KVM_PGTABLE_MIN_BLOCK_LEVEL; } /** diff --git a/arch/arm64/include/asm/stage2_pgtable.h b/arch/arm64/include/asm/stage2_pgtable.h index fe341a6578c3..c8dca8ae359c 100644 --- a/arch/arm64/include/asm/stage2_pgtable.h +++ b/arch/arm64/include/asm/stage2_pgtable.h @@ -11,13 +11,6 @@ #include <linux/pgtable.h> /* - * PGDIR_SHIFT determines the size a top-level page table entry can map - * and depends on the number of levels in the page table. Compute the - * PGDIR_SHIFT for a given number of levels. - */ -#define pt_levels_pgdir_shift(lvls) ARM64_HW_PGTABLE_LEVEL_SHIFT(4 - (lvls)) - -/* * The hardware supports concatenation of up to 16 tables at stage2 entry * level and we use the feature whenever possible, which means we resolve 4 * additional bits of address at the entry level. @@ -30,11 +23,6 @@ #define stage2_pgtable_levels(ipa) ARM64_HW_PGTABLE_LEVELS((ipa) - 4) #define kvm_stage2_levels(kvm) VTCR_EL2_LVLS(kvm->arch.vtcr) -/* stage2_pgdir_shift() is the size mapped by top-level stage2 entry for the VM */ -#define stage2_pgdir_shift(kvm) pt_levels_pgdir_shift(kvm_stage2_levels(kvm)) -#define stage2_pgdir_size(kvm) (1ULL << stage2_pgdir_shift(kvm)) -#define stage2_pgdir_mask(kvm) ~(stage2_pgdir_size(kvm) - 1) - /* * kvm_mmmu_cache_min_pages() is the number of pages required to install * a stage-2 translation. We pre-allocate the entry level page table at @@ -42,12 +30,4 @@ */ #define kvm_mmu_cache_min_pages(kvm) (kvm_stage2_levels(kvm) - 1) -static inline phys_addr_t -stage2_pgd_addr_end(struct kvm *kvm, phys_addr_t addr, phys_addr_t end) -{ - phys_addr_t boundary = (addr + stage2_pgdir_size(kvm)) & stage2_pgdir_mask(kvm); - - return (boundary - 1 < end - 1) ? boundary : end; -} - #endif /* __ARM64_S2_PGTABLE_H_ */ diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c index 6062454a9067..b3f37e2209ad 100644 --- a/arch/arm64/kernel/cpufeature.c +++ b/arch/arm64/kernel/cpufeature.c @@ -428,6 +428,30 @@ static const struct arm64_ftr_bits ftr_id_aa64dfr0[] = { ARM64_FTR_END, }; +static const struct arm64_ftr_bits ftr_mvfr0[] = { + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, MVFR0_FPROUND_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, MVFR0_FPSHVEC_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, MVFR0_FPSQRT_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, MVFR0_FPDIVIDE_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, MVFR0_FPTRAP_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, MVFR0_FPDP_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, MVFR0_FPSP_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, MVFR0_SIMD_SHIFT, 4, 0), + ARM64_FTR_END, +}; + +static const struct arm64_ftr_bits ftr_mvfr1[] = { + ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, MVFR1_SIMDFMAC_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, MVFR1_FPHP_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, MVFR1_SIMDHP_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, MVFR1_SIMDSP_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, MVFR1_SIMDINT_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, MVFR1_SIMDLS_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, MVFR1_FPDNAN_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, MVFR1_FPFTZ_SHIFT, 4, 0), + ARM64_FTR_END, +}; + static const struct arm64_ftr_bits ftr_mvfr2[] = { ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, MVFR2_FPMISC_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, MVFR2_SIMDMISC_SHIFT, 4, 0), @@ -458,10 +482,10 @@ static const struct arm64_ftr_bits ftr_id_isar0[] = { static const struct arm64_ftr_bits ftr_id_isar5[] = { ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR5_RDM_SHIFT, 4, 0), - ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR5_CRC32_SHIFT, 4, 0), - ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR5_SHA2_SHIFT, 4, 0), - ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR5_SHA1_SHIFT, 4, 0), - ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR5_AES_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR5_CRC32_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR5_SHA2_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR5_SHA1_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR5_AES_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR5_SEVL_SHIFT, 4, 0), ARM64_FTR_END, }; @@ -574,7 +598,7 @@ static const struct arm64_ftr_bits ftr_smcr[] = { * Common ftr bits for a 32bit register with all hidden, strict * attributes, with 4bit feature fields and a default safe value of * 0. Covers the following 32bit registers: - * id_isar[1-4], id_mmfr[1-3], id_pfr1, mvfr[0-1] + * id_isar[1-3], id_mmfr[1-3] */ static const struct arm64_ftr_bits ftr_generic_32bits[] = { ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, 28, 4, 0), @@ -645,8 +669,8 @@ static const struct __ftr_reg_entry { ARM64_FTR_REG(SYS_ID_ISAR6_EL1, ftr_id_isar6), /* Op1 = 0, CRn = 0, CRm = 3 */ - ARM64_FTR_REG(SYS_MVFR0_EL1, ftr_generic_32bits), - ARM64_FTR_REG(SYS_MVFR1_EL1, ftr_generic_32bits), + ARM64_FTR_REG(SYS_MVFR0_EL1, ftr_mvfr0), + ARM64_FTR_REG(SYS_MVFR1_EL1, ftr_mvfr1), ARM64_FTR_REG(SYS_MVFR2_EL1, ftr_mvfr2), ARM64_FTR_REG(SYS_ID_PFR2_EL1, ftr_id_pfr2), ARM64_FTR_REG(SYS_ID_DFR1_EL1, ftr_id_dfr1), @@ -3339,7 +3363,7 @@ static void __maybe_unused cpu_enable_cnp(struct arm64_cpu_capabilities const *c /* * We emulate only the following system register space. - * Op0 = 0x3, CRn = 0x0, Op1 = 0x0, CRm = [0, 4 - 7] + * Op0 = 0x3, CRn = 0x0, Op1 = 0x0, CRm = [0, 2 - 7] * See Table C5-6 System instruction encodings for System register accesses, * ARMv8 ARM(ARM DDI 0487A.f) for more details. */ @@ -3349,7 +3373,7 @@ static inline bool __attribute_const__ is_emulated(u32 id) sys_reg_CRn(id) == 0x0 && sys_reg_Op1(id) == 0x0 && (sys_reg_CRm(id) == 0 || - ((sys_reg_CRm(id) >= 4) && (sys_reg_CRm(id) <= 7)))); + ((sys_reg_CRm(id) >= 2) && (sys_reg_CRm(id) <= 7)))); } /* diff --git a/arch/arm64/kernel/efi-rt-wrapper.S b/arch/arm64/kernel/efi-rt-wrapper.S index 75691a2641c1..67babd5f04c2 100644 --- a/arch/arm64/kernel/efi-rt-wrapper.S +++ b/arch/arm64/kernel/efi-rt-wrapper.S @@ -6,7 +6,7 @@ #include <linux/linkage.h> SYM_FUNC_START(__efi_rt_asm_wrapper) - stp x29, x30, [sp, #-32]! + stp x29, x30, [sp, #-112]! mov x29, sp /* @@ -17,6 +17,20 @@ SYM_FUNC_START(__efi_rt_asm_wrapper) stp x1, x18, [sp, #16] /* + * Preserve all callee saved registers and record the stack pointer + * value in a per-CPU variable so we can recover from synchronous + * exceptions occurring while running the firmware routines. + */ + stp x19, x20, [sp, #32] + stp x21, x22, [sp, #48] + stp x23, x24, [sp, #64] + stp x25, x26, [sp, #80] + stp x27, x28, [sp, #96] + + adr_this_cpu x8, __efi_rt_asm_recover_sp, x9 + str x29, [x8] + + /* * We are lucky enough that no EFI runtime services take more than * 5 arguments, so all are passed in registers rather than via the * stack. @@ -31,7 +45,7 @@ SYM_FUNC_START(__efi_rt_asm_wrapper) ldp x1, x2, [sp, #16] cmp x2, x18 - ldp x29, x30, [sp], #32 + ldp x29, x30, [sp], #112 b.ne 0f ret 0: @@ -45,3 +59,18 @@ SYM_FUNC_START(__efi_rt_asm_wrapper) mov x18, x2 b efi_handle_corrupted_x18 // tail call SYM_FUNC_END(__efi_rt_asm_wrapper) + +SYM_FUNC_START(__efi_rt_asm_recover) + ldr_this_cpu x8, __efi_rt_asm_recover_sp, x9 + mov sp, x8 + + ldp x0, x18, [sp, #16] + ldp x19, x20, [sp, #32] + ldp x21, x22, [sp, #48] + ldp x23, x24, [sp, #64] + ldp x25, x26, [sp, #80] + ldp x27, x28, [sp, #96] + ldp x29, x30, [sp], #112 + + b efi_handle_runtime_exception +SYM_FUNC_END(__efi_rt_asm_recover) diff --git a/arch/arm64/kernel/efi.c b/arch/arm64/kernel/efi.c index e1be6c429810..8d36e66a6e64 100644 --- a/arch/arm64/kernel/efi.c +++ b/arch/arm64/kernel/efi.c @@ -9,6 +9,7 @@ #include <linux/efi.h> #include <linux/init.h> +#include <linux/percpu.h> #include <asm/efi.h> @@ -128,3 +129,28 @@ asmlinkage efi_status_t efi_handle_corrupted_x18(efi_status_t s, const char *f) pr_err_ratelimited(FW_BUG "register x18 corrupted by EFI %s\n", f); return s; } + +asmlinkage DEFINE_PER_CPU(u64, __efi_rt_asm_recover_sp); + +asmlinkage efi_status_t __efi_rt_asm_recover(void); + +asmlinkage efi_status_t efi_handle_runtime_exception(const char *f) +{ + pr_err(FW_BUG "Synchronous exception occurred in EFI runtime service %s()\n", f); + clear_bit(EFI_RUNTIME_SERVICES, &efi.flags); + return EFI_ABORTED; +} + +bool efi_runtime_fixup_exception(struct pt_regs *regs, const char *msg) +{ + /* Check whether the exception occurred while running the firmware */ + if (current_work() != &efi_rts_work.work || regs->pc >= TASK_SIZE_64) + return false; + + pr_err(FW_BUG "Unable to handle %s in EFI runtime service\n", msg); + add_taint(TAINT_FIRMWARE_WORKAROUND, LOCKDEP_STILL_OK); + dump_stack(); + + regs->pc = (u64)__efi_rt_asm_recover; + return true; +} diff --git a/arch/arm64/kernel/entry-common.c b/arch/arm64/kernel/entry-common.c index 9173fad279af..27369fa1c032 100644 --- a/arch/arm64/kernel/entry-common.c +++ b/arch/arm64/kernel/entry-common.c @@ -329,7 +329,8 @@ static void cortex_a76_erratum_1463225_svc_handler(void) __this_cpu_write(__in_cortex_a76_erratum_1463225_wa, 0); } -static bool cortex_a76_erratum_1463225_debug_handler(struct pt_regs *regs) +static __always_inline bool +cortex_a76_erratum_1463225_debug_handler(struct pt_regs *regs) { if (!__this_cpu_read(__in_cortex_a76_erratum_1463225_wa)) return false; diff --git a/arch/arm64/kernel/entry-ftrace.S b/arch/arm64/kernel/entry-ftrace.S index bd5df50e4643..795344ab4ec4 100644 --- a/arch/arm64/kernel/entry-ftrace.S +++ b/arch/arm64/kernel/entry-ftrace.S @@ -7,6 +7,7 @@ */ #include <linux/linkage.h> +#include <linux/cfi_types.h> #include <asm/asm-offsets.h> #include <asm/assembler.h> #include <asm/ftrace.h> @@ -294,10 +295,14 @@ SYM_FUNC_END(ftrace_graph_caller) #endif /* CONFIG_FUNCTION_GRAPH_TRACER */ #endif /* CONFIG_DYNAMIC_FTRACE_WITH_REGS */ -SYM_FUNC_START(ftrace_stub) +SYM_TYPED_FUNC_START(ftrace_stub) ret SYM_FUNC_END(ftrace_stub) +SYM_TYPED_FUNC_START(ftrace_stub_graph) + ret +SYM_FUNC_END(ftrace_stub_graph) + #ifdef CONFIG_FUNCTION_GRAPH_TRACER /* * void return_to_handler(void) diff --git a/arch/arm64/kvm/hyp/Makefile b/arch/arm64/kvm/hyp/Makefile index 687598e41b21..a38dea6186c9 100644 --- a/arch/arm64/kvm/hyp/Makefile +++ b/arch/arm64/kvm/hyp/Makefile @@ -5,9 +5,6 @@ incdir := $(srctree)/$(src)/include subdir-asflags-y := -I$(incdir) -subdir-ccflags-y := -I$(incdir) \ - -fno-stack-protector \ - -DDISABLE_BRANCH_PROFILING \ - $(DISABLE_STACKLEAK_PLUGIN) +subdir-ccflags-y := -I$(incdir) obj-$(CONFIG_KVM) += vhe/ nvhe/ pgtable.o diff --git a/arch/arm64/kvm/hyp/exception.c b/arch/arm64/kvm/hyp/exception.c index b7557b25ed56..791d3de76771 100644 --- a/arch/arm64/kvm/hyp/exception.c +++ b/arch/arm64/kvm/hyp/exception.c @@ -13,6 +13,7 @@ #include <hyp/adjust_pc.h> #include <linux/kvm_host.h> #include <asm/kvm_emulate.h> +#include <asm/kvm_mmu.h> #if !defined (__KVM_NVHE_HYPERVISOR__) && !defined (__KVM_VHE_HYPERVISOR__) #error Hypervisor code only! @@ -115,7 +116,7 @@ static void enter_exception64(struct kvm_vcpu *vcpu, unsigned long target_mode, new |= (old & PSR_C_BIT); new |= (old & PSR_V_BIT); - if (kvm_has_mte(vcpu->kvm)) + if (kvm_has_mte(kern_hyp_va(vcpu->kvm))) new |= PSR_TCO_BIT; new |= (old & PSR_DIT_BIT); diff --git a/arch/arm64/kvm/hyp/include/hyp/switch.h b/arch/arm64/kvm/hyp/include/hyp/switch.h index 6cbbb6c02f66..3330d1b76bdd 100644 --- a/arch/arm64/kvm/hyp/include/hyp/switch.h +++ b/arch/arm64/kvm/hyp/include/hyp/switch.h @@ -87,6 +87,17 @@ static inline void __activate_traps_common(struct kvm_vcpu *vcpu) vcpu->arch.mdcr_el2_host = read_sysreg(mdcr_el2); write_sysreg(vcpu->arch.mdcr_el2, mdcr_el2); + + if (cpus_have_final_cap(ARM64_SME)) { + sysreg_clear_set_s(SYS_HFGRTR_EL2, + HFGxTR_EL2_nSMPRI_EL1_MASK | + HFGxTR_EL2_nTPIDR2_EL0_MASK, + 0); + sysreg_clear_set_s(SYS_HFGWTR_EL2, + HFGxTR_EL2_nSMPRI_EL1_MASK | + HFGxTR_EL2_nTPIDR2_EL0_MASK, + 0); + } } static inline void __deactivate_traps_common(struct kvm_vcpu *vcpu) @@ -96,6 +107,15 @@ static inline void __deactivate_traps_common(struct kvm_vcpu *vcpu) write_sysreg(0, hstr_el2); if (kvm_arm_support_pmu_v3()) write_sysreg(0, pmuserenr_el0); + + if (cpus_have_final_cap(ARM64_SME)) { + sysreg_clear_set_s(SYS_HFGRTR_EL2, 0, + HFGxTR_EL2_nSMPRI_EL1_MASK | + HFGxTR_EL2_nTPIDR2_EL0_MASK); + sysreg_clear_set_s(SYS_HFGWTR_EL2, 0, + HFGxTR_EL2_nSMPRI_EL1_MASK | + HFGxTR_EL2_nTPIDR2_EL0_MASK); + } } static inline void ___activate_traps(struct kvm_vcpu *vcpu) diff --git a/arch/arm64/kvm/hyp/nvhe/Makefile b/arch/arm64/kvm/hyp/nvhe/Makefile index b5c5119c7396..be0a2bc3e20d 100644 --- a/arch/arm64/kvm/hyp/nvhe/Makefile +++ b/arch/arm64/kvm/hyp/nvhe/Makefile @@ -10,6 +10,9 @@ asflags-y := -D__KVM_NVHE_HYPERVISOR__ -D__DISABLE_EXPORTS # will explode instantly (Words of Marc Zyngier). So introduce a generic flag # __DISABLE_TRACE_MMIO__ to disable MMIO tracing for nVHE KVM. ccflags-y := -D__KVM_NVHE_HYPERVISOR__ -D__DISABLE_EXPORTS -D__DISABLE_TRACE_MMIO__ +ccflags-y += -fno-stack-protector \ + -DDISABLE_BRANCH_PROFILING \ + $(DISABLE_STACKLEAK_PLUGIN) hostprogs := gen-hyprel HOST_EXTRACFLAGS += -I$(objtree)/include @@ -89,6 +92,10 @@ quiet_cmd_hypcopy = HYPCOPY $@ # Remove ftrace, Shadow Call Stack, and CFI CFLAGS. # This is equivalent to the 'notrace', '__noscs', and '__nocfi' annotations. KBUILD_CFLAGS := $(filter-out $(CC_FLAGS_FTRACE) $(CC_FLAGS_SCS) $(CC_FLAGS_CFI), $(KBUILD_CFLAGS)) +# Starting from 13.0.0 llvm emits SHT_REL section '.llvm.call-graph-profile' +# when profile optimization is applied. gen-hyprel does not support SHT_REL and +# causes a build failure. Remove profile optimization flags. +KBUILD_CFLAGS := $(filter-out -fprofile-sample-use=% -fprofile-use=%, $(KBUILD_CFLAGS)) # KVM nVHE code is run at a different exception code with a different map, so # compiler instrumentation that inserts callbacks or checks into the code may diff --git a/arch/arm64/kvm/hyp/nvhe/mem_protect.c b/arch/arm64/kvm/hyp/nvhe/mem_protect.c index 1e78acf9662e..07f9dc9848ef 100644 --- a/arch/arm64/kvm/hyp/nvhe/mem_protect.c +++ b/arch/arm64/kvm/hyp/nvhe/mem_protect.c @@ -516,7 +516,7 @@ static enum pkvm_page_state hyp_get_page_state(kvm_pte_t pte) if (!kvm_pte_valid(pte)) return PKVM_NOPAGE; - return pkvm_getstate(kvm_pgtable_stage2_pte_prot(pte)); + return pkvm_getstate(kvm_pgtable_hyp_pte_prot(pte)); } static int __hyp_check_page_state_range(u64 addr, u64 size, diff --git a/arch/arm64/kvm/hyp/nvhe/switch.c b/arch/arm64/kvm/hyp/nvhe/switch.c index 8e9d49a964be..c2cb46ca4fb6 100644 --- a/arch/arm64/kvm/hyp/nvhe/switch.c +++ b/arch/arm64/kvm/hyp/nvhe/switch.c @@ -55,18 +55,6 @@ static void __activate_traps(struct kvm_vcpu *vcpu) write_sysreg(val, cptr_el2); write_sysreg(__this_cpu_read(kvm_hyp_vector), vbar_el2); - if (cpus_have_final_cap(ARM64_SME)) { - val = read_sysreg_s(SYS_HFGRTR_EL2); - val &= ~(HFGxTR_EL2_nTPIDR2_EL0_MASK | - HFGxTR_EL2_nSMPRI_EL1_MASK); - write_sysreg_s(val, SYS_HFGRTR_EL2); - - val = read_sysreg_s(SYS_HFGWTR_EL2); - val &= ~(HFGxTR_EL2_nTPIDR2_EL0_MASK | - HFGxTR_EL2_nSMPRI_EL1_MASK); - write_sysreg_s(val, SYS_HFGWTR_EL2); - } - if (cpus_have_final_cap(ARM64_WORKAROUND_SPECULATIVE_AT)) { struct kvm_cpu_context *ctxt = &vcpu->arch.ctxt; @@ -110,20 +98,6 @@ static void __deactivate_traps(struct kvm_vcpu *vcpu) write_sysreg(this_cpu_ptr(&kvm_init_params)->hcr_el2, hcr_el2); - if (cpus_have_final_cap(ARM64_SME)) { - u64 val; - - val = read_sysreg_s(SYS_HFGRTR_EL2); - val |= HFGxTR_EL2_nTPIDR2_EL0_MASK | - HFGxTR_EL2_nSMPRI_EL1_MASK; - write_sysreg_s(val, SYS_HFGRTR_EL2); - - val = read_sysreg_s(SYS_HFGWTR_EL2); - val |= HFGxTR_EL2_nTPIDR2_EL0_MASK | - HFGxTR_EL2_nSMPRI_EL1_MASK; - write_sysreg_s(val, SYS_HFGWTR_EL2); - } - cptr = CPTR_EL2_DEFAULT; if (vcpu_has_sve(vcpu) && (vcpu->arch.fp_state == FP_STATE_GUEST_OWNED)) cptr |= CPTR_EL2_TZ; diff --git a/arch/arm64/kvm/hyp/vhe/switch.c b/arch/arm64/kvm/hyp/vhe/switch.c index 7acb87eaa092..1a97391fedd2 100644 --- a/arch/arm64/kvm/hyp/vhe/switch.c +++ b/arch/arm64/kvm/hyp/vhe/switch.c @@ -63,10 +63,6 @@ static void __activate_traps(struct kvm_vcpu *vcpu) __activate_traps_fpsimd32(vcpu); } - if (cpus_have_final_cap(ARM64_SME)) - write_sysreg(read_sysreg(sctlr_el2) & ~SCTLR_ELx_ENTP2, - sctlr_el2); - write_sysreg(val, cpacr_el1); write_sysreg(__this_cpu_read(kvm_hyp_vector), vbar_el1); @@ -88,10 +84,6 @@ static void __deactivate_traps(struct kvm_vcpu *vcpu) */ asm(ALTERNATIVE("nop", "isb", ARM64_WORKAROUND_SPECULATIVE_AT)); - if (cpus_have_final_cap(ARM64_SME)) - write_sysreg(read_sysreg(sctlr_el2) | SCTLR_ELx_ENTP2, - sctlr_el2); - write_sysreg(CPACR_EL1_DEFAULT, cpacr_el1); if (!arm64_kernel_unmapped_at_el0()) diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c index 34c5feed9dc1..60ee3d9f01f8 100644 --- a/arch/arm64/kvm/mmu.c +++ b/arch/arm64/kvm/mmu.c @@ -31,6 +31,13 @@ static phys_addr_t hyp_idmap_vector; static unsigned long io_map_base; +static phys_addr_t stage2_range_addr_end(phys_addr_t addr, phys_addr_t end) +{ + phys_addr_t size = kvm_granule_size(KVM_PGTABLE_MIN_BLOCK_LEVEL); + phys_addr_t boundary = ALIGN_DOWN(addr + size, size); + + return (boundary - 1 < end - 1) ? boundary : end; +} /* * Release kvm_mmu_lock periodically if the memory region is large. Otherwise, @@ -52,7 +59,7 @@ static int stage2_apply_range(struct kvm *kvm, phys_addr_t addr, if (!pgt) return -EINVAL; - next = stage2_pgd_addr_end(kvm, addr, end); + next = stage2_range_addr_end(addr, end); ret = fn(pgt, addr, next - addr); if (ret) break; diff --git a/arch/arm64/kvm/vgic/vgic-its.c b/arch/arm64/kvm/vgic/vgic-its.c index 24d7778d1ce6..733b53055f97 100644 --- a/arch/arm64/kvm/vgic/vgic-its.c +++ b/arch/arm64/kvm/vgic/vgic-its.c @@ -2149,7 +2149,7 @@ static int scan_its_table(struct vgic_its *its, gpa_t base, int size, u32 esz, memset(entry, 0, esz); - while (len > 0) { + while (true) { int next_offset; size_t byte_offset; @@ -2162,6 +2162,9 @@ static int scan_its_table(struct vgic_its *its, gpa_t base, int size, u32 esz, return next_offset; byte_offset = next_offset * esz; + if (byte_offset >= len) + break; + id += next_offset; gpa += byte_offset; len -= byte_offset; diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c index 5b391490e045..3e9cf9826417 100644 --- a/arch/arm64/mm/fault.c +++ b/arch/arm64/mm/fault.c @@ -30,6 +30,7 @@ #include <asm/bug.h> #include <asm/cmpxchg.h> #include <asm/cpufeature.h> +#include <asm/efi.h> #include <asm/exception.h> #include <asm/daifflags.h> #include <asm/debug-monitors.h> @@ -391,6 +392,9 @@ static void __do_kernel_fault(unsigned long addr, unsigned long esr, msg = "paging request"; } + if (efi_runtime_fixup_exception(regs, msg)) + return; + die_kernel_fault(msg, addr, esr, regs); } diff --git a/arch/loongarch/include/asm/processor.h b/arch/loongarch/include/asm/processor.h index 6954dc5d24e9..7184f1dc61f2 100644 --- a/arch/loongarch/include/asm/processor.h +++ b/arch/loongarch/include/asm/processor.h @@ -191,7 +191,7 @@ static inline void flush_thread(void) unsigned long __get_wchan(struct task_struct *p); #define __KSTK_TOS(tsk) ((unsigned long)task_stack_page(tsk) + \ - THREAD_SIZE - 32 - sizeof(struct pt_regs)) + THREAD_SIZE - sizeof(struct pt_regs)) #define task_pt_regs(tsk) ((struct pt_regs *)__KSTK_TOS(tsk)) #define KSTK_EIP(tsk) (task_pt_regs(tsk)->csr_era) #define KSTK_ESP(tsk) (task_pt_regs(tsk)->regs[3]) diff --git a/arch/loongarch/include/asm/ptrace.h b/arch/loongarch/include/asm/ptrace.h index 17838c6b7ccd..59c4608de91d 100644 --- a/arch/loongarch/include/asm/ptrace.h +++ b/arch/loongarch/include/asm/ptrace.h @@ -29,7 +29,7 @@ struct pt_regs { unsigned long csr_euen; unsigned long csr_ecfg; unsigned long csr_estat; - unsigned long __last[0]; + unsigned long __last[]; } __aligned(8); static inline int regs_irqs_disabled(struct pt_regs *regs) @@ -133,7 +133,7 @@ static inline void die_if_kernel(const char *str, struct pt_regs *regs) #define current_pt_regs() \ ({ \ unsigned long sp = (unsigned long)__builtin_frame_address(0); \ - (struct pt_regs *)((sp | (THREAD_SIZE - 1)) + 1 - 32) - 1; \ + (struct pt_regs *)((sp | (THREAD_SIZE - 1)) + 1) - 1; \ }) /* Helpers for working with the user stack pointer */ diff --git a/arch/loongarch/kernel/head.S b/arch/loongarch/kernel/head.S index 97425779ce9f..84970e266658 100644 --- a/arch/loongarch/kernel/head.S +++ b/arch/loongarch/kernel/head.S @@ -84,10 +84,9 @@ SYM_CODE_START(kernel_entry) # kernel entry point la.pcrel tp, init_thread_union /* Set the SP after an empty pt_regs. */ - PTR_LI sp, (_THREAD_SIZE - 32 - PT_SIZE) + PTR_LI sp, (_THREAD_SIZE - PT_SIZE) PTR_ADD sp, sp, tp set_saved_sp sp, t0, t1 - PTR_ADDI sp, sp, -4 * SZREG # init stack pointer bl start_kernel ASM_BUG() diff --git a/arch/loongarch/kernel/process.c b/arch/loongarch/kernel/process.c index 1256e3582475..2526b68f1c0f 100644 --- a/arch/loongarch/kernel/process.c +++ b/arch/loongarch/kernel/process.c @@ -129,7 +129,7 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args) unsigned long clone_flags = args->flags; struct pt_regs *childregs, *regs = current_pt_regs(); - childksp = (unsigned long)task_stack_page(p) + THREAD_SIZE - 32; + childksp = (unsigned long)task_stack_page(p) + THREAD_SIZE; /* set up new TSS. */ childregs = (struct pt_regs *) childksp - 1; @@ -236,7 +236,7 @@ bool in_task_stack(unsigned long stack, struct task_struct *task, struct stack_info *info) { unsigned long begin = (unsigned long)task_stack_page(task); - unsigned long end = begin + THREAD_SIZE - 32; + unsigned long end = begin + THREAD_SIZE; if (stack < begin || stack >= end) return false; diff --git a/arch/loongarch/kernel/switch.S b/arch/loongarch/kernel/switch.S index 43ebbc3990f7..202a163cb32f 100644 --- a/arch/loongarch/kernel/switch.S +++ b/arch/loongarch/kernel/switch.S @@ -26,7 +26,7 @@ SYM_FUNC_START(__switch_to) move tp, a2 cpu_restore_nonscratch a1 - li.w t0, _THREAD_SIZE - 32 + li.w t0, _THREAD_SIZE PTR_ADD t0, t0, tp set_saved_sp t0, t1, t2 diff --git a/arch/loongarch/net/bpf_jit.c b/arch/loongarch/net/bpf_jit.c index 43f0a98efe38..bdcd0c7719a9 100644 --- a/arch/loongarch/net/bpf_jit.c +++ b/arch/loongarch/net/bpf_jit.c @@ -279,6 +279,7 @@ static void emit_atomic(const struct bpf_insn *insn, struct jit_ctx *ctx) const u8 t1 = LOONGARCH_GPR_T1; const u8 t2 = LOONGARCH_GPR_T2; const u8 t3 = LOONGARCH_GPR_T3; + const u8 r0 = regmap[BPF_REG_0]; const u8 src = regmap[insn->src_reg]; const u8 dst = regmap[insn->dst_reg]; const s16 off = insn->off; @@ -359,8 +360,6 @@ static void emit_atomic(const struct bpf_insn *insn, struct jit_ctx *ctx) break; /* r0 = atomic_cmpxchg(dst + off, r0, src); */ case BPF_CMPXCHG: - u8 r0 = regmap[BPF_REG_0]; - move_reg(ctx, t2, r0); if (isdw) { emit_insn(ctx, lld, r0, t1, 0); @@ -390,8 +389,11 @@ static bool is_signed_bpf_cond(u8 cond) static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx, bool extra_pass) { - const bool is32 = BPF_CLASS(insn->code) == BPF_ALU || - BPF_CLASS(insn->code) == BPF_JMP32; + u8 tm = -1; + u64 func_addr; + bool func_addr_fixed; + int i = insn - ctx->prog->insnsi; + int ret, jmp_offset; const u8 code = insn->code; const u8 cond = BPF_OP(code); const u8 t1 = LOONGARCH_GPR_T1; @@ -400,8 +402,8 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx, bool ext const u8 dst = regmap[insn->dst_reg]; const s16 off = insn->off; const s32 imm = insn->imm; - int jmp_offset; - int i = insn - ctx->prog->insnsi; + const u64 imm64 = (u64)(insn + 1)->imm << 32 | (u32)insn->imm; + const bool is32 = BPF_CLASS(insn->code) == BPF_ALU || BPF_CLASS(insn->code) == BPF_JMP32; switch (code) { /* dst = src */ @@ -724,24 +726,23 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx, bool ext case BPF_JMP32 | BPF_JSGE | BPF_K: case BPF_JMP32 | BPF_JSLT | BPF_K: case BPF_JMP32 | BPF_JSLE | BPF_K: - u8 t7 = -1; jmp_offset = bpf2la_offset(i, off, ctx); if (imm) { move_imm(ctx, t1, imm, false); - t7 = t1; + tm = t1; } else { /* If imm is 0, simply use zero register. */ - t7 = LOONGARCH_GPR_ZERO; + tm = LOONGARCH_GPR_ZERO; } move_reg(ctx, t2, dst); if (is_signed_bpf_cond(BPF_OP(code))) { - emit_sext_32(ctx, t7, is32); + emit_sext_32(ctx, tm, is32); emit_sext_32(ctx, t2, is32); } else { - emit_zext_32(ctx, t7, is32); + emit_zext_32(ctx, tm, is32); emit_zext_32(ctx, t2, is32); } - if (emit_cond_jmp(ctx, cond, t2, t7, jmp_offset) < 0) + if (emit_cond_jmp(ctx, cond, t2, tm, jmp_offset) < 0) goto toofar; break; @@ -775,10 +776,6 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx, bool ext /* function call */ case BPF_JMP | BPF_CALL: - int ret; - u64 func_addr; - bool func_addr_fixed; - mark_call(ctx); ret = bpf_jit_get_func_addr(ctx->prog, insn, extra_pass, &func_addr, &func_addr_fixed); @@ -811,8 +808,6 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx, bool ext /* dst = imm64 */ case BPF_LD | BPF_IMM | BPF_DW: - u64 imm64 = (u64)(insn + 1)->imm << 32 | (u32)insn->imm; - move_imm(ctx, dst, imm64, is32); return 1; diff --git a/arch/parisc/include/asm/hardware.h b/arch/parisc/include/asm/hardware.h index 9d3d7737c58b..a005ebc54779 100644 --- a/arch/parisc/include/asm/hardware.h +++ b/arch/parisc/include/asm/hardware.h @@ -10,12 +10,12 @@ #define SVERSION_ANY_ID PA_SVERSION_ANY_ID struct hp_hardware { - unsigned short hw_type:5; /* HPHW_xxx */ - unsigned short hversion; - unsigned long sversion:28; - unsigned short opt; - const char name[80]; /* The hardware description */ -}; + unsigned int hw_type:8; /* HPHW_xxx */ + unsigned int hversion:12; + unsigned int sversion:12; + unsigned char opt; + unsigned char name[59]; /* The hardware description */ +} __packed; struct parisc_device; diff --git a/arch/parisc/include/uapi/asm/pdc.h b/arch/parisc/include/uapi/asm/pdc.h index e794e143ec5f..7a90070136e8 100644 --- a/arch/parisc/include/uapi/asm/pdc.h +++ b/arch/parisc/include/uapi/asm/pdc.h @@ -363,20 +363,25 @@ #if !defined(__ASSEMBLY__) -/* flags of the device_path */ +/* flags for hardware_path */ #define PF_AUTOBOOT 0x80 #define PF_AUTOSEARCH 0x40 #define PF_TIMER 0x0F -struct device_path { /* page 1-69 */ - unsigned char flags; /* flags see above! */ - unsigned char bc[6]; /* bus converter routing info */ - unsigned char mod; - unsigned int layers[6];/* device-specific layer-info */ -} __attribute__((aligned(8))) ; +struct hardware_path { + unsigned char flags; /* see bit definitions below */ + signed char bc[6]; /* Bus Converter routing info to a specific */ + /* I/O adaptor (< 0 means none, > 63 resvd) */ + signed char mod; /* fixed field of specified module */ +}; + +struct pdc_module_path { /* page 1-69 */ + struct hardware_path path; + unsigned int layers[6]; /* device-specific info (ctlr #, unit # ...) */ +} __attribute__((aligned(8))); struct pz_device { - struct device_path dp; /* see above */ + struct pdc_module_path dp; /* see above */ /* struct iomod *hpa; */ unsigned int hpa; /* HPA base address */ /* char *spa; */ @@ -611,21 +616,6 @@ struct pdc_initiator { /* PDC_INITIATOR */ int mode; }; -struct hardware_path { - char flags; /* see bit definitions below */ - char bc[6]; /* Bus Converter routing info to a specific */ - /* I/O adaptor (< 0 means none, > 63 resvd) */ - char mod; /* fixed field of specified module */ -}; - -/* - * Device path specifications used by PDC. - */ -struct pdc_module_path { - struct hardware_path path; - unsigned int layers[6]; /* device-specific info (ctlr #, unit # ...) */ -}; - /* Only used on some pre-PA2.0 boxes */ struct pdc_memory_map { /* PDC_MEMORY_MAP */ unsigned long hpa; /* mod's register set address */ diff --git a/arch/parisc/kernel/drivers.c b/arch/parisc/kernel/drivers.c index d126e78e101a..e7ee0c0c91d3 100644 --- a/arch/parisc/kernel/drivers.c +++ b/arch/parisc/kernel/drivers.c @@ -882,15 +882,13 @@ void __init walk_central_bus(void) &root); } -static void print_parisc_device(struct parisc_device *dev) +static __init void print_parisc_device(struct parisc_device *dev) { - char hw_path[64]; - static int count; + static int count __initdata; - print_pa_hwpath(dev, hw_path); - pr_info("%d. %s at %pap [%s] { %d, 0x%x, 0x%.3x, 0x%.5x }", - ++count, dev->name, &(dev->hpa.start), hw_path, dev->id.hw_type, - dev->id.hversion_rev, dev->id.hversion, dev->id.sversion); + pr_info("%d. %s at %pap { type:%d, hv:%#x, sv:%#x, rev:%#x }", + ++count, dev->name, &(dev->hpa.start), dev->id.hw_type, + dev->id.hversion, dev->id.sversion, dev->id.hversion_rev); if (dev->num_addrs) { int k; @@ -1079,7 +1077,7 @@ static __init int qemu_print_iodc_data(struct device *lin_dev, void *data) -static int print_one_device(struct device * dev, void * data) +static __init int print_one_device(struct device * dev, void * data) { struct parisc_device * pdev = to_parisc_device(dev); diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index 699df27b0e2f..2ca5418457ed 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -147,6 +147,7 @@ config PPC select ARCH_MIGHT_HAVE_PC_SERIO select ARCH_OPTIONAL_KERNEL_RWX if ARCH_HAS_STRICT_KERNEL_RWX select ARCH_OPTIONAL_KERNEL_RWX_DEFAULT + select ARCH_SPLIT_ARG64 if PPC32 select ARCH_STACKWALK select ARCH_SUPPORTS_ATOMIC_RMW select ARCH_SUPPORTS_DEBUG_PAGEALLOC if PPC_BOOK3S || PPC_8xx || 40x @@ -285,7 +286,7 @@ config PPC # config PPC_LONG_DOUBLE_128 - depends on PPC64 + depends on PPC64 && ALTIVEC def_bool $(success,test "$(shell,echo __LONG_DOUBLE_128__ | $(CC) -E -P -)" = 1) config PPC_BARRIER_NOSPEC diff --git a/arch/powerpc/include/asm/book3s/64/tlbflush-hash.h b/arch/powerpc/include/asm/book3s/64/tlbflush-hash.h index fab8332fe1ad..751921f6db46 100644 --- a/arch/powerpc/include/asm/book3s/64/tlbflush-hash.h +++ b/arch/powerpc/include/asm/book3s/64/tlbflush-hash.h @@ -32,6 +32,11 @@ static inline void arch_enter_lazy_mmu_mode(void) if (radix_enabled()) return; + /* + * apply_to_page_range can call us this preempt enabled when + * operating on kernel page tables. + */ + preempt_disable(); batch = this_cpu_ptr(&ppc64_tlb_batch); batch->active = 1; } @@ -47,6 +52,7 @@ static inline void arch_leave_lazy_mmu_mode(void) if (batch->index) __flush_tlb_pending(batch); batch->active = 0; + preempt_enable(); } #define arch_flush_lazy_mmu_mode() do {} while (0) diff --git a/arch/powerpc/include/asm/syscalls.h b/arch/powerpc/include/asm/syscalls.h index a1142496cd58..6d51b007b59e 100644 --- a/arch/powerpc/include/asm/syscalls.h +++ b/arch/powerpc/include/asm/syscalls.h @@ -104,6 +104,13 @@ long sys_ppc_ftruncate64(unsigned int fd, u32 reg4, unsigned long len1, unsigned long len2); long sys_ppc32_fadvise64(int fd, u32 unused, u32 offset1, u32 offset2, size_t len, int advice); +long sys_ppc_sync_file_range2(int fd, unsigned int flags, + unsigned int offset1, + unsigned int offset2, + unsigned int nbytes1, + unsigned int nbytes2); +long sys_ppc_fallocate(int fd, int mode, u32 offset1, u32 offset2, + u32 len1, u32 len2); #endif #ifdef CONFIG_COMPAT long compat_sys_mmap2(unsigned long addr, size_t len, diff --git a/arch/powerpc/kernel/exceptions-64e.S b/arch/powerpc/kernel/exceptions-64e.S index 930e36099015..2f68fb2ee4fc 100644 --- a/arch/powerpc/kernel/exceptions-64e.S +++ b/arch/powerpc/kernel/exceptions-64e.S @@ -813,6 +813,13 @@ kernel_dbg_exc: EXCEPTION_COMMON(0x260) CHECK_NAPPING() addi r3,r1,STACK_FRAME_OVERHEAD + /* + * XXX: Returning from performance_monitor_exception taken as a + * soft-NMI (Linux irqs disabled) may be risky to use interrupt_return + * and could cause bugs in return or elsewhere. That case should just + * restore registers and return. There is a workaround for one known + * problem in interrupt_exit_kernel_prepare(). + */ bl performance_monitor_exception b interrupt_return diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S index 5381a43e50fe..651c36b056bd 100644 --- a/arch/powerpc/kernel/exceptions-64s.S +++ b/arch/powerpc/kernel/exceptions-64s.S @@ -2357,9 +2357,21 @@ EXC_VIRT_END(performance_monitor, 0x4f00, 0x20) EXC_COMMON_BEGIN(performance_monitor_common) GEN_COMMON performance_monitor addi r3,r1,STACK_FRAME_OVERHEAD - bl performance_monitor_exception + lbz r4,PACAIRQSOFTMASK(r13) + cmpdi r4,IRQS_ENABLED + bne 1f + bl performance_monitor_exception_async b interrupt_return_srr +1: + bl performance_monitor_exception_nmi + /* Clear MSR_RI before setting SRR0 and SRR1. */ + li r9,0 + mtmsrd r9,1 + kuap_kernel_restore r9, r10 + + EXCEPTION_RESTORE_REGS hsrr=0 + RFI_TO_KERNEL /** * Interrupt 0xf20 - Vector Unavailable Interrupt. diff --git a/arch/powerpc/kernel/interrupt.c b/arch/powerpc/kernel/interrupt.c index f9db0a172401..fc6631a80527 100644 --- a/arch/powerpc/kernel/interrupt.c +++ b/arch/powerpc/kernel/interrupt.c @@ -374,10 +374,18 @@ notrace unsigned long interrupt_exit_kernel_prepare(struct pt_regs *regs) if (regs_is_unrecoverable(regs)) unrecoverable_exception(regs); /* - * CT_WARN_ON comes here via program_check_exception, - * so avoid recursion. + * CT_WARN_ON comes here via program_check_exception, so avoid + * recursion. + * + * Skip the assertion on PMIs on 64e to work around a problem caused + * by NMI PMIs incorrectly taking this interrupt return path, it's + * possible for this to hit after interrupt exit to user switches + * context to user. See also the comment in the performance monitor + * handler in exceptions-64e.S */ - if (TRAP(regs) != INTERRUPT_PROGRAM) + if (!IS_ENABLED(CONFIG_PPC_BOOK3E_64) && + TRAP(regs) != INTERRUPT_PROGRAM && + TRAP(regs) != INTERRUPT_PERFMON) CT_WARN_ON(ct_state() == CONTEXT_USER); kuap = kuap_get_and_assert_locked(); diff --git a/arch/powerpc/kernel/interrupt_64.S b/arch/powerpc/kernel/interrupt_64.S index 978a173eb339..a019ed6fc839 100644 --- a/arch/powerpc/kernel/interrupt_64.S +++ b/arch/powerpc/kernel/interrupt_64.S @@ -532,15 +532,24 @@ _ASM_NOKPROBE_SYMBOL(interrupt_return_\srr\()_kernel) * Returning to soft-disabled context. * Check if a MUST_HARD_MASK interrupt has become pending, in which * case we need to disable MSR[EE] in the return context. + * + * The MSR[EE] check catches among other things the short incoherency + * in hard_irq_disable() between clearing MSR[EE] and setting + * PACA_IRQ_HARD_DIS. */ ld r12,_MSR(r1) andi. r10,r12,MSR_EE beq .Lfast_kernel_interrupt_return_\srr\() // EE already disabled lbz r11,PACAIRQHAPPENED(r13) andi. r10,r11,PACA_IRQ_MUST_HARD_MASK - beq .Lfast_kernel_interrupt_return_\srr\() // No HARD_MASK pending + bne 1f // HARD_MASK is pending + // No HARD_MASK pending, clear possible HARD_DIS set by interrupt + andi. r11,r11,(~PACA_IRQ_HARD_DIS)@l + stb r11,PACAIRQHAPPENED(r13) + b .Lfast_kernel_interrupt_return_\srr\() + - /* Must clear MSR_EE from _MSR */ +1: /* Must clear MSR_EE from _MSR */ #ifdef CONFIG_PPC_BOOK3S li r10,0 /* Clear valid before changing _MSR */ diff --git a/arch/powerpc/kernel/sys_ppc32.c b/arch/powerpc/kernel/sys_ppc32.c index 1ab4a4d95aba..d451a8229223 100644 --- a/arch/powerpc/kernel/sys_ppc32.c +++ b/arch/powerpc/kernel/sys_ppc32.c @@ -112,7 +112,7 @@ PPC32_SYSCALL_DEFINE6(ppc32_fadvise64, advice); } -COMPAT_SYSCALL_DEFINE6(ppc_sync_file_range2, +PPC32_SYSCALL_DEFINE6(ppc_sync_file_range2, int, fd, unsigned int, flags, unsigned int, offset1, unsigned int, offset2, unsigned int, nbytes1, unsigned int, nbytes2) @@ -122,3 +122,14 @@ COMPAT_SYSCALL_DEFINE6(ppc_sync_file_range2, return ksys_sync_file_range(fd, offset, nbytes, flags); } + +#ifdef CONFIG_PPC32 +SYSCALL_DEFINE6(ppc_fallocate, + int, fd, int, mode, + u32, offset1, u32, offset2, u32, len1, u32, len2) +{ + return ksys_fallocate(fd, mode, + merge_64(offset1, offset2), + merge_64(len1, len2)); +} +#endif diff --git a/arch/powerpc/kernel/syscalls/syscall.tbl b/arch/powerpc/kernel/syscalls/syscall.tbl index e9e0df4f9a61..a0be127475b1 100644 --- a/arch/powerpc/kernel/syscalls/syscall.tbl +++ b/arch/powerpc/kernel/syscalls/syscall.tbl @@ -394,8 +394,11 @@ 305 common signalfd sys_signalfd compat_sys_signalfd 306 common timerfd_create sys_timerfd_create 307 common eventfd sys_eventfd -308 common sync_file_range2 sys_sync_file_range2 compat_sys_ppc_sync_file_range2 -309 nospu fallocate sys_fallocate compat_sys_fallocate +308 32 sync_file_range2 sys_ppc_sync_file_range2 compat_sys_ppc_sync_file_range2 +308 64 sync_file_range2 sys_sync_file_range2 +308 spu sync_file_range2 sys_sync_file_range2 +309 32 fallocate sys_ppc_fallocate compat_sys_fallocate +309 64 fallocate sys_fallocate 310 nospu subpage_prot sys_subpage_prot 311 32 timerfd_settime sys_timerfd_settime32 311 64 timerfd_settime sys_timerfd_settime diff --git a/arch/powerpc/kvm/Kconfig b/arch/powerpc/kvm/Kconfig index 61cdd782d3c5..a9f57dad6d91 100644 --- a/arch/powerpc/kvm/Kconfig +++ b/arch/powerpc/kvm/Kconfig @@ -51,6 +51,7 @@ config KVM_BOOK3S_HV_POSSIBLE config KVM_BOOK3S_32 tristate "KVM support for PowerPC book3s_32 processors" depends on PPC_BOOK3S_32 && !SMP && !PTE_64BIT + depends on !CONTEXT_TRACKING_USER select KVM select KVM_BOOK3S_32_HANDLER select KVM_BOOK3S_PR_POSSIBLE @@ -105,6 +106,7 @@ config KVM_BOOK3S_64_HV config KVM_BOOK3S_64_PR tristate "KVM support without using hypervisor mode in host" depends on KVM_BOOK3S_64 + depends on !CONTEXT_TRACKING_USER select KVM_BOOK3S_PR_POSSIBLE help Support running guest kernels in virtual machines on processors @@ -190,6 +192,7 @@ config KVM_EXIT_TIMING config KVM_E500V2 bool "KVM support for PowerPC E500v2 processors" depends on PPC_E500 && !PPC_E500MC + depends on !CONTEXT_TRACKING_USER select KVM select KVM_MMIO select MMU_NOTIFIER @@ -205,6 +208,7 @@ config KVM_E500V2 config KVM_E500MC bool "KVM support for PowerPC E500MC/E5500/E6500 processors" depends on PPC_E500MC + depends on !CONTEXT_TRACKING_USER select KVM select KVM_MMIO select KVM_BOOKE_HV diff --git a/arch/powerpc/lib/vmx-helper.c b/arch/powerpc/lib/vmx-helper.c index f76a50291fd7..d491da8d1838 100644 --- a/arch/powerpc/lib/vmx-helper.c +++ b/arch/powerpc/lib/vmx-helper.c @@ -36,7 +36,17 @@ int exit_vmx_usercopy(void) { disable_kernel_altivec(); pagefault_enable(); - preempt_enable(); + preempt_enable_no_resched(); + /* + * Must never explicitly call schedule (including preempt_enable()) + * while in a kuap-unlocked user copy, because the AMR register will + * not be saved and restored across context switch. However preempt + * kernels need to be preempted as soon as possible if need_resched is + * set and we are preemptible. The hack here is to schedule a + * decrementer to fire here and reschedule for us if necessary. + */ + if (IS_ENABLED(CONFIG_PREEMPT) && need_resched()) + set_dec(1); return 0; } diff --git a/arch/powerpc/mm/book3s64/hash_native.c b/arch/powerpc/mm/book3s64/hash_native.c index 623a7b7ab38b..9342e79870df 100644 --- a/arch/powerpc/mm/book3s64/hash_native.c +++ b/arch/powerpc/mm/book3s64/hash_native.c @@ -43,6 +43,29 @@ static DEFINE_RAW_SPINLOCK(native_tlbie_lock); +#ifdef CONFIG_LOCKDEP +static struct lockdep_map hpte_lock_map = + STATIC_LOCKDEP_MAP_INIT("hpte_lock", &hpte_lock_map); + +static void acquire_hpte_lock(void) +{ + lock_map_acquire(&hpte_lock_map); +} + +static void release_hpte_lock(void) +{ + lock_map_release(&hpte_lock_map); +} +#else +static void acquire_hpte_lock(void) +{ +} + +static void release_hpte_lock(void) +{ +} +#endif + static inline unsigned long ___tlbie(unsigned long vpn, int psize, int apsize, int ssize) { @@ -220,6 +243,7 @@ static inline void native_lock_hpte(struct hash_pte *hptep) { unsigned long *word = (unsigned long *)&hptep->v; + acquire_hpte_lock(); while (1) { if (!test_and_set_bit_lock(HPTE_LOCK_BIT, word)) break; @@ -234,6 +258,7 @@ static inline void native_unlock_hpte(struct hash_pte *hptep) { unsigned long *word = (unsigned long *)&hptep->v; + release_hpte_lock(); clear_bit_unlock(HPTE_LOCK_BIT, word); } @@ -243,8 +268,11 @@ static long native_hpte_insert(unsigned long hpte_group, unsigned long vpn, { struct hash_pte *hptep = htab_address + hpte_group; unsigned long hpte_v, hpte_r; + unsigned long flags; int i; + local_irq_save(flags); + if (!(vflags & HPTE_V_BOLTED)) { DBG_LOW(" insert(group=%lx, vpn=%016lx, pa=%016lx," " rflags=%lx, vflags=%lx, psize=%d)\n", @@ -263,8 +291,10 @@ static long native_hpte_insert(unsigned long hpte_group, unsigned long vpn, hptep++; } - if (i == HPTES_PER_GROUP) + if (i == HPTES_PER_GROUP) { + local_irq_restore(flags); return -1; + } hpte_v = hpte_encode_v(vpn, psize, apsize, ssize) | vflags | HPTE_V_VALID; hpte_r = hpte_encode_r(pa, psize, apsize) | rflags; @@ -286,10 +316,13 @@ static long native_hpte_insert(unsigned long hpte_group, unsigned long vpn, * Now set the first dword including the valid bit * NOTE: this also unlocks the hpte */ + release_hpte_lock(); hptep->v = cpu_to_be64(hpte_v); __asm__ __volatile__ ("ptesync" : : : "memory"); + local_irq_restore(flags); + return i | (!!(vflags & HPTE_V_SECONDARY) << 3); } @@ -327,6 +360,7 @@ static long native_hpte_remove(unsigned long hpte_group) return -1; /* Invalidate the hpte. NOTE: this also unlocks it */ + release_hpte_lock(); hptep->v = 0; return i; @@ -339,6 +373,9 @@ static long native_hpte_updatepp(unsigned long slot, unsigned long newpp, struct hash_pte *hptep = htab_address + slot; unsigned long hpte_v, want_v; int ret = 0, local = 0; + unsigned long irqflags; + + local_irq_save(irqflags); want_v = hpte_encode_avpn(vpn, bpsize, ssize); @@ -382,6 +419,8 @@ static long native_hpte_updatepp(unsigned long slot, unsigned long newpp, if (!(flags & HPTE_NOHPTE_UPDATE)) tlbie(vpn, bpsize, apsize, ssize, local); + local_irq_restore(irqflags); + return ret; } @@ -445,6 +484,9 @@ static void native_hpte_updateboltedpp(unsigned long newpp, unsigned long ea, unsigned long vsid; long slot; struct hash_pte *hptep; + unsigned long flags; + + local_irq_save(flags); vsid = get_kernel_vsid(ea, ssize); vpn = hpt_vpn(ea, vsid, ssize); @@ -463,6 +505,8 @@ static void native_hpte_updateboltedpp(unsigned long newpp, unsigned long ea, * actual page size will be same. */ tlbie(vpn, psize, psize, ssize, 0); + + local_irq_restore(flags); } /* @@ -476,6 +520,9 @@ static int native_hpte_removebolted(unsigned long ea, int psize, int ssize) unsigned long vsid; long slot; struct hash_pte *hptep; + unsigned long flags; + + local_irq_save(flags); vsid = get_kernel_vsid(ea, ssize); vpn = hpt_vpn(ea, vsid, ssize); @@ -493,6 +540,9 @@ static int native_hpte_removebolted(unsigned long ea, int psize, int ssize) /* Invalidate the TLB */ tlbie(vpn, psize, psize, ssize, 0); + + local_irq_restore(flags); + return 0; } @@ -517,10 +567,11 @@ static void native_hpte_invalidate(unsigned long slot, unsigned long vpn, /* recheck with locks held */ hpte_v = hpte_get_old_v(hptep); - if (HPTE_V_COMPARE(hpte_v, want_v) && (hpte_v & HPTE_V_VALID)) + if (HPTE_V_COMPARE(hpte_v, want_v) && (hpte_v & HPTE_V_VALID)) { /* Invalidate the hpte. NOTE: this also unlocks it */ + release_hpte_lock(); hptep->v = 0; - else + } else native_unlock_hpte(hptep); } /* @@ -580,10 +631,8 @@ static void native_hugepage_invalidate(unsigned long vsid, hpte_v = hpte_get_old_v(hptep); if (HPTE_V_COMPARE(hpte_v, want_v) && (hpte_v & HPTE_V_VALID)) { - /* - * Invalidate the hpte. NOTE: this also unlocks it - */ - + /* Invalidate the hpte. NOTE: this also unlocks it */ + release_hpte_lock(); hptep->v = 0; } else native_unlock_hpte(hptep); @@ -765,8 +814,10 @@ static void native_flush_hash_range(unsigned long number, int local) if (!HPTE_V_COMPARE(hpte_v, want_v) || !(hpte_v & HPTE_V_VALID)) native_unlock_hpte(hptep); - else + else { + release_hpte_lock(); hptep->v = 0; + } } pte_iterate_hashed_end(); } diff --git a/arch/powerpc/mm/book3s64/hash_pgtable.c b/arch/powerpc/mm/book3s64/hash_pgtable.c index 747492edb75a..51f48984abca 100644 --- a/arch/powerpc/mm/book3s64/hash_pgtable.c +++ b/arch/powerpc/mm/book3s64/hash_pgtable.c @@ -404,7 +404,8 @@ EXPORT_SYMBOL_GPL(hash__has_transparent_hugepage); struct change_memory_parms { unsigned long start, end, newpp; - unsigned int step, nr_cpus, master_cpu; + unsigned int step, nr_cpus; + atomic_t master_cpu; atomic_t cpu_counter; }; @@ -478,7 +479,8 @@ static int change_memory_range_fn(void *data) { struct change_memory_parms *parms = data; - if (parms->master_cpu != smp_processor_id()) + // First CPU goes through, all others wait. + if (atomic_xchg(&parms->master_cpu, 1) == 1) return chmem_secondary_loop(parms); // Wait for all but one CPU (this one) to call-in @@ -516,7 +518,7 @@ static bool hash__change_memory_range(unsigned long start, unsigned long end, chmem_parms.end = end; chmem_parms.step = step; chmem_parms.newpp = newpp; - chmem_parms.master_cpu = smp_processor_id(); + atomic_set(&chmem_parms.master_cpu, 0); cpus_read_lock(); diff --git a/arch/powerpc/mm/book3s64/hash_utils.c b/arch/powerpc/mm/book3s64/hash_utils.c index df008edf7be0..6df4c6d38b66 100644 --- a/arch/powerpc/mm/book3s64/hash_utils.c +++ b/arch/powerpc/mm/book3s64/hash_utils.c @@ -1981,7 +1981,7 @@ repeat: } #if defined(CONFIG_DEBUG_PAGEALLOC) || defined(CONFIG_KFENCE) -static DEFINE_SPINLOCK(linear_map_hash_lock); +static DEFINE_RAW_SPINLOCK(linear_map_hash_lock); static void kernel_map_linear_page(unsigned long vaddr, unsigned long lmi) { @@ -2005,10 +2005,10 @@ static void kernel_map_linear_page(unsigned long vaddr, unsigned long lmi) mmu_linear_psize, mmu_kernel_ssize); BUG_ON (ret < 0); - spin_lock(&linear_map_hash_lock); + raw_spin_lock(&linear_map_hash_lock); BUG_ON(linear_map_hash_slots[lmi] & 0x80); linear_map_hash_slots[lmi] = ret | 0x80; - spin_unlock(&linear_map_hash_lock); + raw_spin_unlock(&linear_map_hash_lock); } static void kernel_unmap_linear_page(unsigned long vaddr, unsigned long lmi) @@ -2018,14 +2018,14 @@ static void kernel_unmap_linear_page(unsigned long vaddr, unsigned long lmi) unsigned long vpn = hpt_vpn(vaddr, vsid, mmu_kernel_ssize); hash = hpt_hash(vpn, PAGE_SHIFT, mmu_kernel_ssize); - spin_lock(&linear_map_hash_lock); + raw_spin_lock(&linear_map_hash_lock); if (!(linear_map_hash_slots[lmi] & 0x80)) { - spin_unlock(&linear_map_hash_lock); + raw_spin_unlock(&linear_map_hash_lock); return; } hidx = linear_map_hash_slots[lmi] & 0x7f; linear_map_hash_slots[lmi] = 0; - spin_unlock(&linear_map_hash_lock); + raw_spin_unlock(&linear_map_hash_lock); if (hidx & _PTEIDX_SECONDARY) hash = ~hash; slot = (hash & htab_hash_mask) * HPTES_PER_GROUP; diff --git a/arch/powerpc/platforms/pseries/lparcfg.c b/arch/powerpc/platforms/pseries/lparcfg.c index 507dc0b5987d..63fd925ccbb8 100644 --- a/arch/powerpc/platforms/pseries/lparcfg.c +++ b/arch/powerpc/platforms/pseries/lparcfg.c @@ -35,6 +35,7 @@ #include <asm/drmem.h> #include "pseries.h" +#include "vas.h" /* pseries_vas_dlpar_cpu() */ /* * This isn't a module but we expose that to userspace @@ -748,6 +749,16 @@ static ssize_t lparcfg_write(struct file *file, const char __user * buf, return -EINVAL; retval = update_ppp(new_entitled_ptr, NULL); + + if (retval == H_SUCCESS || retval == H_CONSTRAINED) { + /* + * The hypervisor assigns VAS resources based + * on entitled capacity for shared mode. + * Reconfig VAS windows based on DLPAR CPU events. + */ + if (pseries_vas_dlpar_cpu() != 0) + retval = H_HARDWARE; + } } else if (!strcmp(kbuf, "capacity_weight")) { char *endp; *new_weight_ptr = (u8) simple_strtoul(tmp, &endp, 10); diff --git a/arch/powerpc/platforms/pseries/vas.c b/arch/powerpc/platforms/pseries/vas.c index 0e0524cbe20c..4ad6e510d405 100644 --- a/arch/powerpc/platforms/pseries/vas.c +++ b/arch/powerpc/platforms/pseries/vas.c @@ -200,17 +200,42 @@ static irqreturn_t pseries_vas_fault_thread_fn(int irq, void *data) struct vas_user_win_ref *tsk_ref; int rc; - rc = h_get_nx_fault(txwin->vas_win.winid, (u64)virt_to_phys(&crb)); - if (!rc) { - tsk_ref = &txwin->vas_win.task_ref; - vas_dump_crb(&crb); - vas_update_csb(&crb, tsk_ref); + while (atomic_read(&txwin->pending_faults)) { + rc = h_get_nx_fault(txwin->vas_win.winid, (u64)virt_to_phys(&crb)); + if (!rc) { + tsk_ref = &txwin->vas_win.task_ref; + vas_dump_crb(&crb); + vas_update_csb(&crb, tsk_ref); + } + atomic_dec(&txwin->pending_faults); } return IRQ_HANDLED; } /* + * irq_default_primary_handler() can be used only with IRQF_ONESHOT + * which disables IRQ before executing the thread handler and enables + * it after. But this disabling interrupt sets the VAS IRQ OFF + * state in the hypervisor. If the NX generates fault interrupt + * during this window, the hypervisor will not deliver this + * interrupt to the LPAR. So use VAS specific IRQ handler instead + * of calling the default primary handler. + */ +static irqreturn_t pseries_vas_irq_handler(int irq, void *data) +{ + struct pseries_vas_window *txwin = data; + + /* + * The thread hanlder will process this interrupt if it is + * already running. + */ + atomic_inc(&txwin->pending_faults); + + return IRQ_WAKE_THREAD; +} + +/* * Allocate window and setup IRQ mapping. */ static int allocate_setup_window(struct pseries_vas_window *txwin, @@ -240,8 +265,9 @@ static int allocate_setup_window(struct pseries_vas_window *txwin, goto out_irq; } - rc = request_threaded_irq(txwin->fault_virq, NULL, - pseries_vas_fault_thread_fn, IRQF_ONESHOT, + rc = request_threaded_irq(txwin->fault_virq, + pseries_vas_irq_handler, + pseries_vas_fault_thread_fn, 0, txwin->name, txwin); if (rc) { pr_err("VAS-Window[%d]: Request IRQ(%u) failed with %d\n", @@ -826,6 +852,25 @@ int vas_reconfig_capabilties(u8 type, int new_nr_creds) mutex_unlock(&vas_pseries_mutex); return rc; } + +int pseries_vas_dlpar_cpu(void) +{ + int new_nr_creds, rc; + + rc = h_query_vas_capabilities(H_QUERY_VAS_CAPABILITIES, + vascaps[VAS_GZIP_DEF_FEAT_TYPE].feat, + (u64)virt_to_phys(&hv_cop_caps)); + if (!rc) { + new_nr_creds = be16_to_cpu(hv_cop_caps.target_lpar_creds); + rc = vas_reconfig_capabilties(VAS_GZIP_DEF_FEAT_TYPE, new_nr_creds); + } + + if (rc) + pr_err("Failed reconfig VAS capabilities with DLPAR\n"); + + return rc; +} + /* * Total number of default credits available (target_credits) * in LPAR depends on number of cores configured. It varies based on @@ -840,7 +885,15 @@ static int pseries_vas_notifier(struct notifier_block *nb, struct of_reconfig_data *rd = data; struct device_node *dn = rd->dn; const __be32 *intserv = NULL; - int new_nr_creds, len, rc = 0; + int len; + + /* + * For shared CPU partition, the hypervisor assigns total credits + * based on entitled core capacity. So updating VAS windows will + * be called from lparcfg_write(). + */ + if (is_shared_processor()) + return NOTIFY_OK; if ((action == OF_RECONFIG_ATTACH_NODE) || (action == OF_RECONFIG_DETACH_NODE)) @@ -852,19 +905,7 @@ static int pseries_vas_notifier(struct notifier_block *nb, if (!intserv) return NOTIFY_OK; - rc = h_query_vas_capabilities(H_QUERY_VAS_CAPABILITIES, - vascaps[VAS_GZIP_DEF_FEAT_TYPE].feat, - (u64)virt_to_phys(&hv_cop_caps)); - if (!rc) { - new_nr_creds = be16_to_cpu(hv_cop_caps.target_lpar_creds); - rc = vas_reconfig_capabilties(VAS_GZIP_DEF_FEAT_TYPE, - new_nr_creds); - } - - if (rc) - pr_err("Failed reconfig VAS capabilities with DLPAR\n"); - - return rc; + return pseries_vas_dlpar_cpu(); } static struct notifier_block pseries_vas_nb = { diff --git a/arch/powerpc/platforms/pseries/vas.h b/arch/powerpc/platforms/pseries/vas.h index 333ffa2f9f42..7115043ec488 100644 --- a/arch/powerpc/platforms/pseries/vas.h +++ b/arch/powerpc/platforms/pseries/vas.h @@ -132,6 +132,7 @@ struct pseries_vas_window { u64 flags; char *name; int fault_virq; + atomic_t pending_faults; /* Number of pending faults */ }; int sysfs_add_vas_caps(struct vas_cop_feat_caps *caps); @@ -140,10 +141,15 @@ int __init sysfs_pseries_vas_init(struct vas_all_caps *vas_caps); #ifdef CONFIG_PPC_VAS int vas_migration_handler(int action); +int pseries_vas_dlpar_cpu(void); #else static inline int vas_migration_handler(int action) { return 0; } +static inline int pseries_vas_dlpar_cpu(void) +{ + return 0; +} #endif #endif /* _VAS_H */ diff --git a/arch/riscv/include/asm/cacheflush.h b/arch/riscv/include/asm/cacheflush.h index 8a5c246b0a21..f6fbe7042f1c 100644 --- a/arch/riscv/include/asm/cacheflush.h +++ b/arch/riscv/include/asm/cacheflush.h @@ -42,16 +42,8 @@ void flush_icache_mm(struct mm_struct *mm, bool local); #endif /* CONFIG_SMP */ -/* - * The T-Head CMO errata internally probe the CBOM block size, but otherwise - * don't depend on Zicbom. - */ extern unsigned int riscv_cbom_block_size; -#ifdef CONFIG_RISCV_ISA_ZICBOM void riscv_init_cbom_blocksize(void); -#else -static inline void riscv_init_cbom_blocksize(void) { } -#endif #ifdef CONFIG_RISCV_DMA_NONCOHERENT void riscv_noncoherent_supported(void); diff --git a/arch/riscv/include/asm/kvm_vcpu_timer.h b/arch/riscv/include/asm/kvm_vcpu_timer.h index 0d8fdb8ec63a..82f7260301da 100644 --- a/arch/riscv/include/asm/kvm_vcpu_timer.h +++ b/arch/riscv/include/asm/kvm_vcpu_timer.h @@ -45,6 +45,7 @@ int kvm_riscv_vcpu_timer_deinit(struct kvm_vcpu *vcpu); int kvm_riscv_vcpu_timer_reset(struct kvm_vcpu *vcpu); void kvm_riscv_vcpu_timer_restore(struct kvm_vcpu *vcpu); void kvm_riscv_guest_timer_init(struct kvm *kvm); +void kvm_riscv_vcpu_timer_sync(struct kvm_vcpu *vcpu); void kvm_riscv_vcpu_timer_save(struct kvm_vcpu *vcpu); bool kvm_riscv_vcpu_timer_pending(struct kvm_vcpu *vcpu); diff --git a/arch/riscv/kvm/vcpu.c b/arch/riscv/kvm/vcpu.c index a032c4f0d600..71ebbc4821f0 100644 --- a/arch/riscv/kvm/vcpu.c +++ b/arch/riscv/kvm/vcpu.c @@ -708,6 +708,9 @@ void kvm_riscv_vcpu_sync_interrupts(struct kvm_vcpu *vcpu) clear_bit(IRQ_VS_SOFT, &v->irqs_pending); } } + + /* Sync-up timer CSRs */ + kvm_riscv_vcpu_timer_sync(vcpu); } int kvm_riscv_vcpu_set_interrupt(struct kvm_vcpu *vcpu, unsigned int irq) diff --git a/arch/riscv/kvm/vcpu_timer.c b/arch/riscv/kvm/vcpu_timer.c index 185f2386a747..ad34519c8a13 100644 --- a/arch/riscv/kvm/vcpu_timer.c +++ b/arch/riscv/kvm/vcpu_timer.c @@ -320,20 +320,33 @@ void kvm_riscv_vcpu_timer_restore(struct kvm_vcpu *vcpu) kvm_riscv_vcpu_timer_unblocking(vcpu); } -void kvm_riscv_vcpu_timer_save(struct kvm_vcpu *vcpu) +void kvm_riscv_vcpu_timer_sync(struct kvm_vcpu *vcpu) { struct kvm_vcpu_timer *t = &vcpu->arch.timer; if (!t->sstc_enabled) return; - t = &vcpu->arch.timer; #if defined(CONFIG_32BIT) t->next_cycles = csr_read(CSR_VSTIMECMP); t->next_cycles |= (u64)csr_read(CSR_VSTIMECMPH) << 32; #else t->next_cycles = csr_read(CSR_VSTIMECMP); #endif +} + +void kvm_riscv_vcpu_timer_save(struct kvm_vcpu *vcpu) +{ + struct kvm_vcpu_timer *t = &vcpu->arch.timer; + + if (!t->sstc_enabled) + return; + + /* + * The vstimecmp CSRs are saved by kvm_riscv_vcpu_timer_sync() + * upon every VM exit so no need to save here. + */ + /* timer should be enabled for the remaining operations */ if (unlikely(!t->init_done)) return; diff --git a/arch/riscv/mm/cacheflush.c b/arch/riscv/mm/cacheflush.c index 6cb7d96ad9c7..57b40a350420 100644 --- a/arch/riscv/mm/cacheflush.c +++ b/arch/riscv/mm/cacheflush.c @@ -3,6 +3,7 @@ * Copyright (C) 2017 SiFive */ +#include <linux/of.h> #include <asm/cacheflush.h> #ifdef CONFIG_SMP @@ -86,3 +87,40 @@ void flush_icache_pte(pte_t pte) flush_icache_all(); } #endif /* CONFIG_MMU */ + +unsigned int riscv_cbom_block_size; +EXPORT_SYMBOL_GPL(riscv_cbom_block_size); + +void riscv_init_cbom_blocksize(void) +{ + struct device_node *node; + unsigned long cbom_hartid; + u32 val, probed_block_size; + int ret; + + probed_block_size = 0; + for_each_of_cpu_node(node) { + unsigned long hartid; + + ret = riscv_of_processor_hartid(node, &hartid); + if (ret) + continue; + + /* set block-size for cbom extension if available */ + ret = of_property_read_u32(node, "riscv,cbom-block-size", &val); + if (ret) + continue; + + if (!probed_block_size) { + probed_block_size = val; + cbom_hartid = hartid; + } else { + if (probed_block_size != val) + pr_warn("cbom-block-size mismatched between harts %lu and %lu\n", + cbom_hartid, hartid); + } + } + + if (probed_block_size) + riscv_cbom_block_size = probed_block_size; +} diff --git a/arch/riscv/mm/dma-noncoherent.c b/arch/riscv/mm/dma-noncoherent.c index b0add983530a..d919efab6eba 100644 --- a/arch/riscv/mm/dma-noncoherent.c +++ b/arch/riscv/mm/dma-noncoherent.c @@ -8,13 +8,8 @@ #include <linux/dma-direct.h> #include <linux/dma-map-ops.h> #include <linux/mm.h> -#include <linux/of.h> -#include <linux/of_device.h> #include <asm/cacheflush.h> -unsigned int riscv_cbom_block_size; -EXPORT_SYMBOL_GPL(riscv_cbom_block_size); - static bool noncoherent_supported; void arch_sync_dma_for_device(phys_addr_t paddr, size_t size, @@ -77,42 +72,6 @@ void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size, dev->dma_coherent = coherent; } -#ifdef CONFIG_RISCV_ISA_ZICBOM -void riscv_init_cbom_blocksize(void) -{ - struct device_node *node; - unsigned long cbom_hartid; - u32 val, probed_block_size; - int ret; - - probed_block_size = 0; - for_each_of_cpu_node(node) { - unsigned long hartid; - - ret = riscv_of_processor_hartid(node, &hartid); - if (ret) - continue; - - /* set block-size for cbom extension if available */ - ret = of_property_read_u32(node, "riscv,cbom-block-size", &val); - if (ret) - continue; - - if (!probed_block_size) { - probed_block_size = val; - cbom_hartid = hartid; - } else { - if (probed_block_size != val) - pr_warn("cbom-block-size mismatched between harts %lu and %lu\n", - cbom_hartid, hartid); - } - } - - if (probed_block_size) - riscv_cbom_block_size = probed_block_size; -} -#endif - void riscv_noncoherent_supported(void) { WARN(!riscv_cbom_block_size, diff --git a/arch/s390/boot/vmlinux.lds.S b/arch/s390/boot/vmlinux.lds.S index af5c6860e0a1..fa9d33b01b85 100644 --- a/arch/s390/boot/vmlinux.lds.S +++ b/arch/s390/boot/vmlinux.lds.S @@ -102,8 +102,17 @@ SECTIONS _compressed_start = .; *(.vmlinux.bin.compressed) _compressed_end = .; - FILL(0xff); - . = ALIGN(4096); + } + +#define SB_TRAILER_SIZE 32 + /* Trailer needed for Secure Boot */ + . += SB_TRAILER_SIZE; /* make sure .sb.trailer does not overwrite the previous section */ + . = ALIGN(4096) - SB_TRAILER_SIZE; + .sb.trailer : { + QUAD(0) + QUAD(0) + QUAD(0) + QUAD(0x000000207a49504c) } _end = .; diff --git a/arch/s390/include/asm/futex.h b/arch/s390/include/asm/futex.h index e08c882dccaa..eaeaeb3ff0be 100644 --- a/arch/s390/include/asm/futex.h +++ b/arch/s390/include/asm/futex.h @@ -17,7 +17,8 @@ "3: jl 1b\n" \ " lhi %0,0\n" \ "4: sacf 768\n" \ - EX_TABLE(0b,4b) EX_TABLE(2b,4b) EX_TABLE(3b,4b) \ + EX_TABLE(0b,4b) EX_TABLE(1b,4b) \ + EX_TABLE(2b,4b) EX_TABLE(3b,4b) \ : "=d" (ret), "=&d" (oldval), "=&d" (newval), \ "=m" (*uaddr) \ : "0" (-EFAULT), "d" (oparg), "a" (uaddr), \ diff --git a/arch/s390/kernel/perf_pai_ext.c b/arch/s390/kernel/perf_pai_ext.c index d5c7c1e30c17..74b53c531e0c 100644 --- a/arch/s390/kernel/perf_pai_ext.c +++ b/arch/s390/kernel/perf_pai_ext.c @@ -459,6 +459,7 @@ static int paiext_push_sample(void) raw.frag.data = cpump->save; raw.size = raw.frag.size; data.raw = &raw; + data.sample_flags |= PERF_SAMPLE_RAW; } overflow = perf_event_overflow(event, &data, ®s); diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index 45d4b8182b07..bc491a73815c 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -1207,6 +1207,8 @@ static int kvm_s390_vm_get_migration(struct kvm *kvm, return 0; } +static void __kvm_s390_set_tod_clock(struct kvm *kvm, const struct kvm_s390_vm_tod_clock *gtod); + static int kvm_s390_set_tod_ext(struct kvm *kvm, struct kvm_device_attr *attr) { struct kvm_s390_vm_tod_clock gtod; @@ -1216,7 +1218,7 @@ static int kvm_s390_set_tod_ext(struct kvm *kvm, struct kvm_device_attr *attr) if (!test_kvm_facility(kvm, 139) && gtod.epoch_idx) return -EINVAL; - kvm_s390_set_tod_clock(kvm, >od); + __kvm_s390_set_tod_clock(kvm, >od); VM_EVENT(kvm, 3, "SET: TOD extension: 0x%x, TOD base: 0x%llx", gtod.epoch_idx, gtod.tod); @@ -1247,7 +1249,7 @@ static int kvm_s390_set_tod_low(struct kvm *kvm, struct kvm_device_attr *attr) sizeof(gtod.tod))) return -EFAULT; - kvm_s390_set_tod_clock(kvm, >od); + __kvm_s390_set_tod_clock(kvm, >od); VM_EVENT(kvm, 3, "SET: TOD base: 0x%llx", gtod.tod); return 0; } @@ -1259,6 +1261,16 @@ static int kvm_s390_set_tod(struct kvm *kvm, struct kvm_device_attr *attr) if (attr->flags) return -EINVAL; + mutex_lock(&kvm->lock); + /* + * For protected guests, the TOD is managed by the ultravisor, so trying + * to change it will never bring the expected results. + */ + if (kvm_s390_pv_is_protected(kvm)) { + ret = -EOPNOTSUPP; + goto out_unlock; + } + switch (attr->attr) { case KVM_S390_VM_TOD_EXT: ret = kvm_s390_set_tod_ext(kvm, attr); @@ -1273,6 +1285,9 @@ static int kvm_s390_set_tod(struct kvm *kvm, struct kvm_device_attr *attr) ret = -ENXIO; break; } + +out_unlock: + mutex_unlock(&kvm->lock); return ret; } @@ -4377,13 +4392,6 @@ static void __kvm_s390_set_tod_clock(struct kvm *kvm, const struct kvm_s390_vm_t preempt_enable(); } -void kvm_s390_set_tod_clock(struct kvm *kvm, const struct kvm_s390_vm_tod_clock *gtod) -{ - mutex_lock(&kvm->lock); - __kvm_s390_set_tod_clock(kvm, gtod); - mutex_unlock(&kvm->lock); -} - int kvm_s390_try_set_tod_clock(struct kvm *kvm, const struct kvm_s390_vm_tod_clock *gtod) { if (!mutex_trylock(&kvm->lock)) diff --git a/arch/s390/kvm/kvm-s390.h b/arch/s390/kvm/kvm-s390.h index f6fd668f887e..4755492dfabc 100644 --- a/arch/s390/kvm/kvm-s390.h +++ b/arch/s390/kvm/kvm-s390.h @@ -363,7 +363,6 @@ int kvm_s390_handle_sigp(struct kvm_vcpu *vcpu); int kvm_s390_handle_sigp_pei(struct kvm_vcpu *vcpu); /* implemented in kvm-s390.c */ -void kvm_s390_set_tod_clock(struct kvm *kvm, const struct kvm_s390_vm_tod_clock *gtod); int kvm_s390_try_set_tod_clock(struct kvm *kvm, const struct kvm_s390_vm_tod_clock *gtod); long kvm_arch_fault_in_page(struct kvm_vcpu *vcpu, gpa_t gpa, int writable); int kvm_s390_store_status_unloaded(struct kvm_vcpu *vcpu, unsigned long addr); diff --git a/arch/s390/kvm/pci.c b/arch/s390/kvm/pci.c index c50c1645c0ae..ded1af2ddae9 100644 --- a/arch/s390/kvm/pci.c +++ b/arch/s390/kvm/pci.c @@ -126,7 +126,7 @@ int kvm_s390_pci_aen_init(u8 nisc) return -EPERM; mutex_lock(&aift->aift_lock); - aift->kzdev = kcalloc(ZPCI_NR_DEVICES, sizeof(struct kvm_zdev), + aift->kzdev = kcalloc(ZPCI_NR_DEVICES, sizeof(struct kvm_zdev *), GFP_KERNEL); if (!aift->kzdev) { rc = -ENOMEM; diff --git a/arch/s390/lib/uaccess.c b/arch/s390/lib/uaccess.c index 58033dfcb6d4..720036fb1924 100644 --- a/arch/s390/lib/uaccess.c +++ b/arch/s390/lib/uaccess.c @@ -157,7 +157,7 @@ unsigned long __clear_user(void __user *to, unsigned long size) asm volatile( " lr 0,%[spec]\n" "0: mvcos 0(%1),0(%4),%0\n" - " jz 4f\n" + "6: jz 4f\n" "1: algr %0,%2\n" " slgr %1,%2\n" " j 0b\n" @@ -167,11 +167,11 @@ unsigned long __clear_user(void __user *to, unsigned long size) " clgr %0,%3\n" /* copy crosses next page boundary? */ " jnh 5f\n" "3: mvcos 0(%1),0(%4),%3\n" - " slgr %0,%3\n" + "7: slgr %0,%3\n" " j 5f\n" "4: slgr %0,%0\n" "5:\n" - EX_TABLE(0b,2b) EX_TABLE(3b,5b) + EX_TABLE(0b,2b) EX_TABLE(6b,2b) EX_TABLE(3b,5b) EX_TABLE(7b,5b) : "+a" (size), "+a" (to), "+a" (tmp1), "=a" (tmp2) : "a" (empty_zero_page), [spec] "d" (spec.val) : "cc", "memory", "0"); diff --git a/arch/s390/pci/pci_mmio.c b/arch/s390/pci/pci_mmio.c index 080c88620723..588089332931 100644 --- a/arch/s390/pci/pci_mmio.c +++ b/arch/s390/pci/pci_mmio.c @@ -64,7 +64,7 @@ static inline int __pcistg_mio_inuser( asm volatile ( " sacf 256\n" "0: llgc %[tmp],0(%[src])\n" - " sllg %[val],%[val],8\n" + "4: sllg %[val],%[val],8\n" " aghi %[src],1\n" " ogr %[val],%[tmp]\n" " brctg %[cnt],0b\n" @@ -72,7 +72,7 @@ static inline int __pcistg_mio_inuser( "2: ipm %[cc]\n" " srl %[cc],28\n" "3: sacf 768\n" - EX_TABLE(0b, 3b) EX_TABLE(1b, 3b) EX_TABLE(2b, 3b) + EX_TABLE(0b, 3b) EX_TABLE(4b, 3b) EX_TABLE(1b, 3b) EX_TABLE(2b, 3b) : [src] "+a" (src), [cnt] "+d" (cnt), [val] "+d" (val), [tmp] "=d" (tmp), @@ -215,10 +215,10 @@ static inline int __pcilg_mio_inuser( "2: ahi %[shift],-8\n" " srlg %[tmp],%[val],0(%[shift])\n" "3: stc %[tmp],0(%[dst])\n" - " aghi %[dst],1\n" + "5: aghi %[dst],1\n" " brctg %[cnt],2b\n" "4: sacf 768\n" - EX_TABLE(0b, 4b) EX_TABLE(1b, 4b) EX_TABLE(3b, 4b) + EX_TABLE(0b, 4b) EX_TABLE(1b, 4b) EX_TABLE(3b, 4b) EX_TABLE(5b, 4b) : [ioaddr_len] "+&d" (ioaddr_len.pair), [cc] "+d" (cc), [val] "=d" (val), diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 6d1879ef933a..67745ceab0db 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -1973,7 +1973,6 @@ config EFI config EFI_STUB bool "EFI stub support" depends on EFI - depends on $(cc-option,-mabi=ms) || X86_32 select RELOCATABLE help This kernel feature allows a bzImage to be loaded directly diff --git a/arch/x86/coco/tdx/tdx.c b/arch/x86/coco/tdx/tdx.c index 928dcf7a20d9..b8998cf0508a 100644 --- a/arch/x86/coco/tdx/tdx.c +++ b/arch/x86/coco/tdx/tdx.c @@ -34,6 +34,8 @@ #define VE_GET_PORT_NUM(e) ((e) >> 16) #define VE_IS_IO_STRING(e) ((e) & BIT(4)) +#define ATTR_SEPT_VE_DISABLE BIT(28) + /* * Wrapper for standard use of __tdx_hypercall with no output aside from * return code. @@ -98,10 +100,11 @@ static inline void tdx_module_call(u64 fn, u64 rcx, u64 rdx, u64 r8, u64 r9, panic("TDCALL %lld failed (Buggy TDX module!)\n", fn); } -static u64 get_cc_mask(void) +static void tdx_parse_tdinfo(u64 *cc_mask) { struct tdx_module_output out; unsigned int gpa_width; + u64 td_attr; /* * TDINFO TDX module call is used to get the TD execution environment @@ -109,19 +112,27 @@ static u64 get_cc_mask(void) * information, etc. More details about the ABI can be found in TDX * Guest-Host-Communication Interface (GHCI), section 2.4.2 TDCALL * [TDG.VP.INFO]. + */ + tdx_module_call(TDX_GET_INFO, 0, 0, 0, 0, &out); + + /* + * The highest bit of a guest physical address is the "sharing" bit. + * Set it for shared pages and clear it for private pages. * * The GPA width that comes out of this call is critical. TDX guests * can not meaningfully run without it. */ - tdx_module_call(TDX_GET_INFO, 0, 0, 0, 0, &out); - gpa_width = out.rcx & GENMASK(5, 0); + *cc_mask = BIT_ULL(gpa_width - 1); /* - * The highest bit of a guest physical address is the "sharing" bit. - * Set it for shared pages and clear it for private pages. + * The kernel can not handle #VE's when accessing normal kernel + * memory. Ensure that no #VE will be delivered for accesses to + * TD-private memory. Only VMM-shared memory (MMIO) will #VE. */ - return BIT_ULL(gpa_width - 1); + td_attr = out.rdx; + if (!(td_attr & ATTR_SEPT_VE_DISABLE)) + panic("TD misconfiguration: SEPT_VE_DISABLE attibute must be set.\n"); } /* @@ -758,7 +769,7 @@ void __init tdx_early_init(void) setup_force_cpu_cap(X86_FEATURE_TDX_GUEST); cc_set_vendor(CC_VENDOR_INTEL); - cc_mask = get_cc_mask(); + tdx_parse_tdinfo(&cc_mask); cc_set_mask(cc_mask); /* diff --git a/arch/x86/crypto/polyval-clmulni_glue.c b/arch/x86/crypto/polyval-clmulni_glue.c index b7664d018851..8fa58b0f3cb3 100644 --- a/arch/x86/crypto/polyval-clmulni_glue.c +++ b/arch/x86/crypto/polyval-clmulni_glue.c @@ -27,13 +27,17 @@ #include <asm/cpu_device_id.h> #include <asm/simd.h> +#define POLYVAL_ALIGN 16 +#define POLYVAL_ALIGN_ATTR __aligned(POLYVAL_ALIGN) +#define POLYVAL_ALIGN_EXTRA ((POLYVAL_ALIGN - 1) & ~(CRYPTO_MINALIGN - 1)) +#define POLYVAL_CTX_SIZE (sizeof(struct polyval_tfm_ctx) + POLYVAL_ALIGN_EXTRA) #define NUM_KEY_POWERS 8 struct polyval_tfm_ctx { /* * These powers must be in the order h^8, ..., h^1. */ - u8 key_powers[NUM_KEY_POWERS][POLYVAL_BLOCK_SIZE]; + u8 key_powers[NUM_KEY_POWERS][POLYVAL_BLOCK_SIZE] POLYVAL_ALIGN_ATTR; }; struct polyval_desc_ctx { @@ -45,6 +49,11 @@ asmlinkage void clmul_polyval_update(const struct polyval_tfm_ctx *keys, const u8 *in, size_t nblocks, u8 *accumulator); asmlinkage void clmul_polyval_mul(u8 *op1, const u8 *op2); +static inline struct polyval_tfm_ctx *polyval_tfm_ctx(struct crypto_shash *tfm) +{ + return PTR_ALIGN(crypto_shash_ctx(tfm), POLYVAL_ALIGN); +} + static void internal_polyval_update(const struct polyval_tfm_ctx *keys, const u8 *in, size_t nblocks, u8 *accumulator) { @@ -72,7 +81,7 @@ static void internal_polyval_mul(u8 *op1, const u8 *op2) static int polyval_x86_setkey(struct crypto_shash *tfm, const u8 *key, unsigned int keylen) { - struct polyval_tfm_ctx *tctx = crypto_shash_ctx(tfm); + struct polyval_tfm_ctx *tctx = polyval_tfm_ctx(tfm); int i; if (keylen != POLYVAL_BLOCK_SIZE) @@ -102,7 +111,7 @@ static int polyval_x86_update(struct shash_desc *desc, const u8 *src, unsigned int srclen) { struct polyval_desc_ctx *dctx = shash_desc_ctx(desc); - const struct polyval_tfm_ctx *tctx = crypto_shash_ctx(desc->tfm); + const struct polyval_tfm_ctx *tctx = polyval_tfm_ctx(desc->tfm); u8 *pos; unsigned int nblocks; unsigned int n; @@ -143,7 +152,7 @@ static int polyval_x86_update(struct shash_desc *desc, static int polyval_x86_final(struct shash_desc *desc, u8 *dst) { struct polyval_desc_ctx *dctx = shash_desc_ctx(desc); - const struct polyval_tfm_ctx *tctx = crypto_shash_ctx(desc->tfm); + const struct polyval_tfm_ctx *tctx = polyval_tfm_ctx(desc->tfm); if (dctx->bytes) { internal_polyval_mul(dctx->buffer, @@ -167,7 +176,7 @@ static struct shash_alg polyval_alg = { .cra_driver_name = "polyval-clmulni", .cra_priority = 200, .cra_blocksize = POLYVAL_BLOCK_SIZE, - .cra_ctxsize = sizeof(struct polyval_tfm_ctx), + .cra_ctxsize = POLYVAL_CTX_SIZE, .cra_module = THIS_MODULE, }, }; diff --git a/arch/x86/events/amd/ibs.c b/arch/x86/events/amd/ibs.c index 3271735f0070..4cb710efbdd9 100644 --- a/arch/x86/events/amd/ibs.c +++ b/arch/x86/events/amd/ibs.c @@ -801,7 +801,7 @@ static void perf_ibs_get_mem_lvl(union ibs_op_data2 *op_data2, /* Extension Memory */ if (ibs_caps & IBS_CAPS_ZEN4 && ibs_data_src == IBS_DATA_SRC_EXT_EXT_MEM) { - data_src->mem_lvl_num = PERF_MEM_LVLNUM_EXTN_MEM; + data_src->mem_lvl_num = PERF_MEM_LVLNUM_CXL; if (op_data2->rmt_node) { data_src->mem_remote = PERF_MEM_REMOTE_REMOTE; /* IBS doesn't provide Remote socket detail */ diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index a646a5f9a235..1b92bf05fd65 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -4911,6 +4911,7 @@ static const struct x86_cpu_desc isolation_ucodes[] = { INTEL_CPU_DESC(INTEL_FAM6_SKYLAKE_X, 5, 0x00000000), INTEL_CPU_DESC(INTEL_FAM6_SKYLAKE_X, 6, 0x00000000), INTEL_CPU_DESC(INTEL_FAM6_SKYLAKE_X, 7, 0x00000000), + INTEL_CPU_DESC(INTEL_FAM6_SKYLAKE_X, 11, 0x00000000), INTEL_CPU_DESC(INTEL_FAM6_SKYLAKE_L, 3, 0x0000007c), INTEL_CPU_DESC(INTEL_FAM6_SKYLAKE, 3, 0x0000007c), INTEL_CPU_DESC(INTEL_FAM6_KABYLAKE, 9, 0x0000004e), diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c index 7839507b3844..446d2833efa7 100644 --- a/arch/x86/events/intel/ds.c +++ b/arch/x86/events/intel/ds.c @@ -982,8 +982,13 @@ struct event_constraint intel_icl_pebs_event_constraints[] = { INTEL_FLAGS_UEVENT_CONSTRAINT(0x0400, 0x800000000ULL), /* SLOTS */ INTEL_PLD_CONSTRAINT(0x1cd, 0xff), /* MEM_TRANS_RETIRED.LOAD_LATENCY */ - INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x1d0, 0xf), /* MEM_INST_RETIRED.LOAD */ - INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_ST(0x2d0, 0xf), /* MEM_INST_RETIRED.STORE */ + INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x11d0, 0xf), /* MEM_INST_RETIRED.STLB_MISS_LOADS */ + INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_ST(0x12d0, 0xf), /* MEM_INST_RETIRED.STLB_MISS_STORES */ + INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x21d0, 0xf), /* MEM_INST_RETIRED.LOCK_LOADS */ + INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x41d0, 0xf), /* MEM_INST_RETIRED.SPLIT_LOADS */ + INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_ST(0x42d0, 0xf), /* MEM_INST_RETIRED.SPLIT_STORES */ + INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x81d0, 0xf), /* MEM_INST_RETIRED.ALL_LOADS */ + INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_ST(0x82d0, 0xf), /* MEM_INST_RETIRED.ALL_STORES */ INTEL_FLAGS_EVENT_CONSTRAINT_DATALA_LD_RANGE(0xd1, 0xd4, 0xf), /* MEM_LOAD_*_RETIRED.* */ @@ -1004,8 +1009,13 @@ struct event_constraint intel_spr_pebs_event_constraints[] = { INTEL_FLAGS_EVENT_CONSTRAINT(0xc0, 0xfe), INTEL_PLD_CONSTRAINT(0x1cd, 0xfe), INTEL_PSD_CONSTRAINT(0x2cd, 0x1), - INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x1d0, 0xf), - INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_ST(0x2d0, 0xf), + INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x11d0, 0xf), /* MEM_INST_RETIRED.STLB_MISS_LOADS */ + INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_ST(0x12d0, 0xf), /* MEM_INST_RETIRED.STLB_MISS_STORES */ + INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x21d0, 0xf), /* MEM_INST_RETIRED.LOCK_LOADS */ + INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x41d0, 0xf), /* MEM_INST_RETIRED.SPLIT_LOADS */ + INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_ST(0x42d0, 0xf), /* MEM_INST_RETIRED.SPLIT_STORES */ + INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x81d0, 0xf), /* MEM_INST_RETIRED.ALL_LOADS */ + INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_ST(0x82d0, 0xf), /* MEM_INST_RETIRED.ALL_STORES */ INTEL_FLAGS_EVENT_CONSTRAINT_DATALA_LD_RANGE(0xd1, 0xd4, 0xf), diff --git a/arch/x86/events/intel/lbr.c b/arch/x86/events/intel/lbr.c index 4fce1a4226e3..8259d725054d 100644 --- a/arch/x86/events/intel/lbr.c +++ b/arch/x86/events/intel/lbr.c @@ -1596,7 +1596,7 @@ void __init intel_pmu_arch_lbr_init(void) return; clear_arch_lbr: - clear_cpu_cap(&boot_cpu_data, X86_FEATURE_ARCH_LBR); + setup_clear_cpu_cap(X86_FEATURE_ARCH_LBR); } /** diff --git a/arch/x86/events/rapl.c b/arch/x86/events/rapl.c index 77e3a47af5ad..a829492bca4c 100644 --- a/arch/x86/events/rapl.c +++ b/arch/x86/events/rapl.c @@ -619,12 +619,8 @@ static int rapl_check_hw_unit(struct rapl_model *rm) case RAPL_UNIT_QUIRK_INTEL_HSW: rapl_hw_unit[PERF_RAPL_RAM] = 16; break; - /* - * SPR shares the same DRAM domain energy unit as HSW, plus it - * also has a fixed energy unit for Psys domain. - */ + /* SPR uses a fixed energy unit for Psys domain. */ case RAPL_UNIT_QUIRK_INTEL_SPR: - rapl_hw_unit[PERF_RAPL_RAM] = 16; rapl_hw_unit[PERF_RAPL_PSYS] = 0; break; default: @@ -806,7 +802,11 @@ static const struct x86_cpu_id rapl_model_match[] __initconst = { X86_MATCH_INTEL_FAM6_MODEL(COMETLAKE, &model_skl), X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE, &model_skl), X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE_L, &model_skl), + X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE_N, &model_skl), X86_MATCH_INTEL_FAM6_MODEL(SAPPHIRERAPIDS_X, &model_spr), + X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE, &model_skl), + X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE_P, &model_skl), + X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE_S, &model_skl), {}, }; MODULE_DEVICE_TABLE(x86cpu, rapl_model_match); diff --git a/arch/x86/hyperv/hv_init.c b/arch/x86/hyperv/hv_init.c index 29774126e931..f49bc3ec76e6 100644 --- a/arch/x86/hyperv/hv_init.c +++ b/arch/x86/hyperv/hv_init.c @@ -444,7 +444,7 @@ void __init hyperv_init(void) if (hv_root_partition) { struct page *pg; - void *src, *dst; + void *src; /* * For the root partition, the hypervisor will set up its @@ -459,13 +459,11 @@ void __init hyperv_init(void) wrmsrl(HV_X64_MSR_HYPERCALL, hypercall_msr.as_uint64); pg = vmalloc_to_page(hv_hypercall_pg); - dst = kmap_local_page(pg); src = memremap(hypercall_msr.guest_physical_address << PAGE_SHIFT, PAGE_SIZE, MEMREMAP_WB); - BUG_ON(!(src && dst)); - memcpy(dst, src, HV_HYP_PAGE_SIZE); + BUG_ON(!src); + memcpy_to_page(pg, 0, src, HV_HYP_PAGE_SIZE); memunmap(src); - kunmap_local(dst); } else { hypercall_msr.guest_physical_address = vmalloc_to_pfn(hv_hypercall_pg); wrmsrl(HV_X64_MSR_HYPERCALL, hypercall_msr.as_uint64); @@ -537,6 +535,7 @@ common_free: void hyperv_cleanup(void) { union hv_x64_msr_hypercall_contents hypercall_msr; + union hv_reference_tsc_msr tsc_msr; unregister_syscore_ops(&hv_syscore_ops); @@ -552,12 +551,14 @@ void hyperv_cleanup(void) hv_hypercall_pg = NULL; /* Reset the hypercall page */ - hypercall_msr.as_uint64 = 0; - wrmsrl(HV_X64_MSR_HYPERCALL, hypercall_msr.as_uint64); + hypercall_msr.as_uint64 = hv_get_register(HV_X64_MSR_HYPERCALL); + hypercall_msr.enable = 0; + hv_set_register(HV_X64_MSR_HYPERCALL, hypercall_msr.as_uint64); /* Reset the TSC page */ - hypercall_msr.as_uint64 = 0; - wrmsrl(HV_X64_MSR_REFERENCE_TSC, hypercall_msr.as_uint64); + tsc_msr.as_uint64 = hv_get_register(HV_X64_MSR_REFERENCE_TSC); + tsc_msr.enable = 0; + hv_set_register(HV_X64_MSR_REFERENCE_TSC, tsc_msr.as_uint64); } void hyperv_report_panic(struct pt_regs *regs, long err, bool in_die) diff --git a/arch/x86/include/asm/intel-family.h b/arch/x86/include/asm/intel-family.h index 5d75fe229342..347707d459c6 100644 --- a/arch/x86/include/asm/intel-family.h +++ b/arch/x86/include/asm/intel-family.h @@ -107,6 +107,11 @@ #define INTEL_FAM6_SAPPHIRERAPIDS_X 0x8F /* Golden Cove */ +#define INTEL_FAM6_EMERALDRAPIDS_X 0xCF + +#define INTEL_FAM6_GRANITERAPIDS_X 0xAD +#define INTEL_FAM6_GRANITERAPIDS_D 0xAE + #define INTEL_FAM6_ALDERLAKE 0x97 /* Golden Cove / Gracemont */ #define INTEL_FAM6_ALDERLAKE_L 0x9A /* Golden Cove / Gracemont */ #define INTEL_FAM6_ALDERLAKE_N 0xBE @@ -118,7 +123,7 @@ #define INTEL_FAM6_METEORLAKE 0xAC #define INTEL_FAM6_METEORLAKE_L 0xAA -/* "Small Core" Processors (Atom) */ +/* "Small Core" Processors (Atom/E-Core) */ #define INTEL_FAM6_ATOM_BONNELL 0x1C /* Diamondville, Pineview */ #define INTEL_FAM6_ATOM_BONNELL_MID 0x26 /* Silverthorne, Lincroft */ @@ -145,6 +150,10 @@ #define INTEL_FAM6_ATOM_TREMONT 0x96 /* Elkhart Lake */ #define INTEL_FAM6_ATOM_TREMONT_L 0x9C /* Jasper Lake */ +#define INTEL_FAM6_SIERRAFOREST_X 0xAF + +#define INTEL_FAM6_GRANDRIDGE 0xB6 + /* Xeon Phi */ #define INTEL_FAM6_XEON_PHI_KNL 0x57 /* Knights Landing */ diff --git a/arch/x86/include/asm/iommu.h b/arch/x86/include/asm/iommu.h index 0bef44d30a27..2fd52b65deac 100644 --- a/arch/x86/include/asm/iommu.h +++ b/arch/x86/include/asm/iommu.h @@ -25,8 +25,10 @@ arch_rmrr_sanity_check(struct acpi_dmar_reserved_memory *rmrr) { u64 start = rmrr->base_address; u64 end = rmrr->end_address + 1; + int entry_type; - if (e820__mapped_all(start, end, E820_TYPE_RESERVED)) + entry_type = e820__get_entry_type(start, end); + if (entry_type == E820_TYPE_RESERVED || entry_type == E820_TYPE_NVS) return 0; pr_err(FW_BUG "No firmware reserved region can cover this RMRR [%#018Lx-%#018Lx], contact BIOS vendor for fixes\n", diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 7551b6f9c31c..f05ebaa26f0f 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -501,7 +501,12 @@ struct kvm_pmc { bool intr; }; +/* More counters may conflict with other existing Architectural MSRs */ +#define KVM_INTEL_PMC_MAX_GENERIC 8 +#define MSR_ARCH_PERFMON_PERFCTR_MAX (MSR_ARCH_PERFMON_PERFCTR0 + KVM_INTEL_PMC_MAX_GENERIC - 1) +#define MSR_ARCH_PERFMON_EVENTSEL_MAX (MSR_ARCH_PERFMON_EVENTSEL0 + KVM_INTEL_PMC_MAX_GENERIC - 1) #define KVM_PMC_MAX_FIXED 3 +#define KVM_AMD_PMC_MAX_GENERIC 6 struct kvm_pmu { unsigned nr_arch_gp_counters; unsigned nr_arch_fixed_counters; @@ -516,7 +521,7 @@ struct kvm_pmu { u64 reserved_bits; u64 raw_event_mask; u8 version; - struct kvm_pmc gp_counters[INTEL_PMC_MAX_GENERIC]; + struct kvm_pmc gp_counters[KVM_INTEL_PMC_MAX_GENERIC]; struct kvm_pmc fixed_counters[KVM_PMC_MAX_FIXED]; struct irq_work irq_work; DECLARE_BITMAP(reprogram_pmi, X86_PMC_IDX_MAX); diff --git a/arch/x86/include/asm/spec-ctrl.h b/arch/x86/include/asm/spec-ctrl.h index 5393babc0598..cb0386fc4dc3 100644 --- a/arch/x86/include/asm/spec-ctrl.h +++ b/arch/x86/include/asm/spec-ctrl.h @@ -13,7 +13,7 @@ * Takes the guest view of SPEC_CTRL MSR as a parameter and also * the guest's version of VIRT_SPEC_CTRL, if emulated. */ -extern void x86_virt_spec_ctrl(u64 guest_spec_ctrl, u64 guest_virt_spec_ctrl, bool guest); +extern void x86_virt_spec_ctrl(u64 guest_virt_spec_ctrl, bool guest); /** * x86_spec_ctrl_set_guest - Set speculation control registers for the guest @@ -24,9 +24,9 @@ extern void x86_virt_spec_ctrl(u64 guest_spec_ctrl, u64 guest_virt_spec_ctrl, bo * Avoids writing to the MSR if the content/bits are the same */ static inline -void x86_spec_ctrl_set_guest(u64 guest_spec_ctrl, u64 guest_virt_spec_ctrl) +void x86_spec_ctrl_set_guest(u64 guest_virt_spec_ctrl) { - x86_virt_spec_ctrl(guest_spec_ctrl, guest_virt_spec_ctrl, true); + x86_virt_spec_ctrl(guest_virt_spec_ctrl, true); } /** @@ -38,9 +38,9 @@ void x86_spec_ctrl_set_guest(u64 guest_spec_ctrl, u64 guest_virt_spec_ctrl) * Avoids writing to the MSR if the content/bits are the same */ static inline -void x86_spec_ctrl_restore_host(u64 guest_spec_ctrl, u64 guest_virt_spec_ctrl) +void x86_spec_ctrl_restore_host(u64 guest_virt_spec_ctrl) { - x86_virt_spec_ctrl(guest_spec_ctrl, guest_virt_spec_ctrl, false); + x86_virt_spec_ctrl(guest_virt_spec_ctrl, false); } /* AMD specific Speculative Store Bypass MSR data */ diff --git a/arch/x86/include/asm/string_64.h b/arch/x86/include/asm/string_64.h index 3b87d889b6e1..888731ccf1f6 100644 --- a/arch/x86/include/asm/string_64.h +++ b/arch/x86/include/asm/string_64.h @@ -10,10 +10,13 @@ /* Even with __builtin_ the compiler may decide to use the out of line function. */ +#if defined(__SANITIZE_MEMORY__) && defined(__NO_FORTIFY) +#include <linux/kmsan_string.h> +#endif + #define __HAVE_ARCH_MEMCPY 1 -#if defined(__SANITIZE_MEMORY__) +#if defined(__SANITIZE_MEMORY__) && defined(__NO_FORTIFY) #undef memcpy -void *__msan_memcpy(void *dst, const void *src, size_t size); #define memcpy __msan_memcpy #else extern void *memcpy(void *to, const void *from, size_t len); @@ -21,7 +24,7 @@ extern void *memcpy(void *to, const void *from, size_t len); extern void *__memcpy(void *to, const void *from, size_t len); #define __HAVE_ARCH_MEMSET -#if defined(__SANITIZE_MEMORY__) +#if defined(__SANITIZE_MEMORY__) && defined(__NO_FORTIFY) extern void *__msan_memset(void *s, int c, size_t n); #undef memset #define memset __msan_memset @@ -67,7 +70,7 @@ static inline void *memset64(uint64_t *s, uint64_t v, size_t n) } #define __HAVE_ARCH_MEMMOVE -#if defined(__SANITIZE_MEMORY__) +#if defined(__SANITIZE_MEMORY__) && defined(__NO_FORTIFY) #undef memmove void *__msan_memmove(void *dest, const void *src, size_t len); #define memmove __msan_memmove diff --git a/arch/x86/include/asm/syscall_wrapper.h b/arch/x86/include/asm/syscall_wrapper.h index 59358d1bf880..fd2669b1cb2d 100644 --- a/arch/x86/include/asm/syscall_wrapper.h +++ b/arch/x86/include/asm/syscall_wrapper.h @@ -6,7 +6,7 @@ #ifndef _ASM_X86_SYSCALL_WRAPPER_H #define _ASM_X86_SYSCALL_WRAPPER_H -struct pt_regs; +#include <asm/ptrace.h> extern long __x64_sys_ni_syscall(const struct pt_regs *regs); extern long __ia32_sys_ni_syscall(const struct pt_regs *regs); diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h index 8bc614cfe21b..1cc756eafa44 100644 --- a/arch/x86/include/asm/uaccess.h +++ b/arch/x86/include/asm/uaccess.h @@ -254,24 +254,25 @@ extern void __put_user_nocheck_8(void); #define __put_user_size(x, ptr, size, label) \ do { \ __typeof__(*(ptr)) __x = (x); /* eval x once */ \ - __chk_user_ptr(ptr); \ + __typeof__(ptr) __ptr = (ptr); /* eval ptr once */ \ + __chk_user_ptr(__ptr); \ switch (size) { \ case 1: \ - __put_user_goto(__x, ptr, "b", "iq", label); \ + __put_user_goto(__x, __ptr, "b", "iq", label); \ break; \ case 2: \ - __put_user_goto(__x, ptr, "w", "ir", label); \ + __put_user_goto(__x, __ptr, "w", "ir", label); \ break; \ case 4: \ - __put_user_goto(__x, ptr, "l", "ir", label); \ + __put_user_goto(__x, __ptr, "l", "ir", label); \ break; \ case 8: \ - __put_user_goto_u64(__x, ptr, label); \ + __put_user_goto_u64(__x, __ptr, label); \ break; \ default: \ __put_user_bad(); \ } \ - instrument_put_user(__x, ptr, size); \ + instrument_put_user(__x, __ptr, size); \ } while (0) #ifdef CONFIG_CC_HAS_ASM_GOTO_OUTPUT diff --git a/arch/x86/kernel/asm-offsets.c b/arch/x86/kernel/asm-offsets.c index cb50589a7102..437308004ef2 100644 --- a/arch/x86/kernel/asm-offsets.c +++ b/arch/x86/kernel/asm-offsets.c @@ -19,7 +19,6 @@ #include <asm/suspend.h> #include <asm/tlbflush.h> #include <asm/tdx.h> -#include "../kvm/vmx/vmx.h" #ifdef CONFIG_XEN #include <xen/interface/xen.h> @@ -108,9 +107,4 @@ static void __used common(void) OFFSET(TSS_sp0, tss_struct, x86_tss.sp0); OFFSET(TSS_sp1, tss_struct, x86_tss.sp1); OFFSET(TSS_sp2, tss_struct, x86_tss.sp2); - - if (IS_ENABLED(CONFIG_KVM_INTEL)) { - BLANK(); - OFFSET(VMX_spec_ctrl, vcpu_vmx, spec_ctrl); - } } diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index da7c361f47e0..3e3230cccaa7 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -196,22 +196,15 @@ void __init check_bugs(void) } /* - * NOTE: This function is *only* called for SVM. VMX spec_ctrl handling is - * done in vmenter.S. + * NOTE: This function is *only* called for SVM, since Intel uses + * MSR_IA32_SPEC_CTRL for SSBD. */ void -x86_virt_spec_ctrl(u64 guest_spec_ctrl, u64 guest_virt_spec_ctrl, bool setguest) +x86_virt_spec_ctrl(u64 guest_virt_spec_ctrl, bool setguest) { - u64 msrval, guestval = guest_spec_ctrl, hostval = spec_ctrl_current(); + u64 guestval, hostval; struct thread_info *ti = current_thread_info(); - if (static_cpu_has(X86_FEATURE_MSR_SPEC_CTRL)) { - if (hostval != guestval) { - msrval = setguest ? guestval : hostval; - wrmsrl(MSR_IA32_SPEC_CTRL, msrval); - } - } - /* * If SSBD is not handled in MSR_SPEC_CTRL on AMD, update * MSR_AMD64_L2_CFG or MSR_VIRT_SPEC_CTRL if supported. diff --git a/arch/x86/kernel/cpu/microcode/amd.c b/arch/x86/kernel/cpu/microcode/amd.c index e7410e98fc1f..3a35dec3ec55 100644 --- a/arch/x86/kernel/cpu/microcode/amd.c +++ b/arch/x86/kernel/cpu/microcode/amd.c @@ -440,7 +440,13 @@ apply_microcode_early_amd(u32 cpuid_1_eax, void *ucode, size_t size, bool save_p return ret; native_rdmsr(MSR_AMD64_PATCH_LEVEL, rev, dummy); - if (rev >= mc->hdr.patch_id) + + /* + * Allow application of the same revision to pick up SMT-specific + * changes even if the revision of the other SMT thread is already + * up-to-date. + */ + if (rev > mc->hdr.patch_id) return ret; if (!__apply_microcode_amd(mc)) { @@ -528,8 +534,12 @@ void load_ucode_amd_ap(unsigned int cpuid_1_eax) native_rdmsr(MSR_AMD64_PATCH_LEVEL, rev, dummy); - /* Check whether we have saved a new patch already: */ - if (*new_rev && rev < mc->hdr.patch_id) { + /* + * Check whether a new patch has been saved already. Also, allow application of + * the same revision in order to pick up SMT-thread-specific configuration even + * if the sibling SMT thread already has an up-to-date revision. + */ + if (*new_rev && rev <= mc->hdr.patch_id) { if (!__apply_microcode_amd(mc)) { *new_rev = mc->hdr.patch_id; return; diff --git a/arch/x86/kernel/cpu/resctrl/core.c b/arch/x86/kernel/cpu/resctrl/core.c index de62b0b87ced..3266ea36667c 100644 --- a/arch/x86/kernel/cpu/resctrl/core.c +++ b/arch/x86/kernel/cpu/resctrl/core.c @@ -66,9 +66,6 @@ struct rdt_hw_resource rdt_resources_all[] = { .rid = RDT_RESOURCE_L3, .name = "L3", .cache_level = 3, - .cache = { - .min_cbm_bits = 1, - }, .domains = domain_init(RDT_RESOURCE_L3), .parse_ctrlval = parse_cbm, .format_str = "%d=%0*x", @@ -83,9 +80,6 @@ struct rdt_hw_resource rdt_resources_all[] = { .rid = RDT_RESOURCE_L2, .name = "L2", .cache_level = 2, - .cache = { - .min_cbm_bits = 1, - }, .domains = domain_init(RDT_RESOURCE_L2), .parse_ctrlval = parse_cbm, .format_str = "%d=%0*x", @@ -836,6 +830,7 @@ static __init void rdt_init_res_defs_intel(void) r->cache.arch_has_sparse_bitmaps = false; r->cache.arch_has_empty_bitmaps = false; r->cache.arch_has_per_cpu_cfg = false; + r->cache.min_cbm_bits = 1; } else if (r->rid == RDT_RESOURCE_MBA) { hw_res->msr_base = MSR_IA32_MBA_THRTL_BASE; hw_res->msr_update = mba_wrmsr_intel; @@ -856,6 +851,7 @@ static __init void rdt_init_res_defs_amd(void) r->cache.arch_has_sparse_bitmaps = true; r->cache.arch_has_empty_bitmaps = true; r->cache.arch_has_per_cpu_cfg = true; + r->cache.min_cbm_bits = 0; } else if (r->rid == RDT_RESOURCE_MBA) { hw_res->msr_base = MSR_IA32_MBA_BW_BASE; hw_res->msr_update = mba_wrmsr_amd; diff --git a/arch/x86/kernel/cpu/topology.c b/arch/x86/kernel/cpu/topology.c index 132a2de44d2f..5e868b62a7c4 100644 --- a/arch/x86/kernel/cpu/topology.c +++ b/arch/x86/kernel/cpu/topology.c @@ -96,6 +96,7 @@ int detect_extended_topology(struct cpuinfo_x86 *c) 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; @@ -111,10 +112,10 @@ int detect_extended_topology(struct cpuinfo_x86 *c) core_level_siblings = 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); - die_plus_mask_width = BITS_SHIFT_NEXT_LEVEL(eax); + pkg_mask_width = die_plus_mask_width = BITS_SHIFT_NEXT_LEVEL(eax); sub_index = 1; - do { + while (true) { cpuid_count(leaf, sub_index, &eax, &ebx, &ecx, &edx); /* @@ -132,10 +133,15 @@ int detect_extended_topology(struct cpuinfo_x86 *c) die_plus_mask_width = BITS_SHIFT_NEXT_LEVEL(eax); } + if (LEAFB_SUBTYPE(ecx) != INVALID_TYPE) + pkg_mask_width = BITS_SHIFT_NEXT_LEVEL(eax); + else + break; + sub_index++; - } while (LEAFB_SUBTYPE(ecx) != INVALID_TYPE); + } - core_select_mask = (~(-1 << core_plus_mask_width)) >> ht_mask_width; + core_select_mask = (~(-1 << pkg_mask_width)) >> ht_mask_width; die_select_mask = (~(-1 << die_plus_mask_width)) >> core_plus_mask_width; @@ -148,7 +154,7 @@ int detect_extended_topology(struct cpuinfo_x86 *c) } c->phys_proc_id = apic->phys_pkg_id(c->initial_apicid, - die_plus_mask_width); + pkg_mask_width); /* * Reinit the apicid, now that we have extended initial_apicid. */ diff --git a/arch/x86/kernel/fpu/init.c b/arch/x86/kernel/fpu/init.c index 621f4b6cac4a..8946f89761cc 100644 --- a/arch/x86/kernel/fpu/init.c +++ b/arch/x86/kernel/fpu/init.c @@ -210,13 +210,6 @@ static void __init fpu__init_system_xstate_size_legacy(void) fpstate_reset(¤t->thread.fpu); } -static void __init fpu__init_init_fpstate(void) -{ - /* Bring init_fpstate size and features up to date */ - init_fpstate.size = fpu_kernel_cfg.max_size; - init_fpstate.xfeatures = fpu_kernel_cfg.max_features; -} - /* * Called on the boot CPU once per system bootup, to set up the initial * FPU state that is later cloned into all processes: @@ -236,5 +229,4 @@ void __init fpu__init_system(struct cpuinfo_x86 *c) fpu__init_system_xstate_size_legacy(); fpu__init_system_xstate(fpu_kernel_cfg.max_size); fpu__init_task_struct_size(); - fpu__init_init_fpstate(); } diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c index c8340156bfd2..59e543b95a3c 100644 --- a/arch/x86/kernel/fpu/xstate.c +++ b/arch/x86/kernel/fpu/xstate.c @@ -360,7 +360,7 @@ static void __init setup_init_fpu_buf(void) print_xstate_features(); - xstate_init_xcomp_bv(&init_fpstate.regs.xsave, fpu_kernel_cfg.max_features); + xstate_init_xcomp_bv(&init_fpstate.regs.xsave, init_fpstate.xfeatures); /* * Init all the features state with header.xfeatures being 0x0 @@ -678,20 +678,6 @@ static unsigned int __init get_xsave_size_user(void) return ebx; } -/* - * Will the runtime-enumerated 'xstate_size' fit in the init - * task's statically-allocated buffer? - */ -static bool __init is_supported_xstate_size(unsigned int test_xstate_size) -{ - if (test_xstate_size <= sizeof(init_fpstate.regs)) - return true; - - pr_warn("x86/fpu: xstate buffer too small (%zu < %d), disabling xsave\n", - sizeof(init_fpstate.regs), test_xstate_size); - return false; -} - static int __init init_xstate_size(void) { /* Recompute the context size for enabled features: */ @@ -717,10 +703,6 @@ static int __init init_xstate_size(void) kernel_default_size = xstate_calculate_size(fpu_kernel_cfg.default_features, compacted); - /* Ensure we have the space to store all default enabled features. */ - if (!is_supported_xstate_size(kernel_default_size)) - return -EINVAL; - if (!paranoid_xstate_size_valid(kernel_size)) return -EINVAL; @@ -875,6 +857,19 @@ void __init fpu__init_system_xstate(unsigned int legacy_size) update_regset_xstate_info(fpu_user_cfg.max_size, fpu_user_cfg.max_features); + /* + * init_fpstate excludes dynamic states as they are large but init + * state is zero. + */ + init_fpstate.size = fpu_kernel_cfg.default_size; + init_fpstate.xfeatures = fpu_kernel_cfg.default_features; + + if (init_fpstate.size > sizeof(init_fpstate.regs)) { + pr_warn("x86/fpu: init_fpstate buffer too small (%zu < %d), disabling XSAVE\n", + sizeof(init_fpstate.regs), init_fpstate.size); + goto out_disable; + } + setup_init_fpu_buf(); /* @@ -1130,6 +1125,15 @@ void __copy_xstate_to_uabi_buf(struct membuf to, struct fpstate *fpstate, */ mask = fpstate->user_xfeatures; + /* + * Dynamic features are not present in init_fpstate. When they are + * in an all zeros init state, remove those from 'mask' to zero + * those features in the user buffer instead of retrieving them + * from init_fpstate. + */ + if (fpu_state_size_dynamic()) + mask &= (header.xfeatures | xinit->header.xcomp_bv); + for_each_extended_xfeature(i, mask) { /* * If there was a feature or alignment gap, zero the space diff --git a/arch/x86/kernel/ftrace_64.S b/arch/x86/kernel/ftrace_64.S index dfeb227de561..2a4be92fd144 100644 --- a/arch/x86/kernel/ftrace_64.S +++ b/arch/x86/kernel/ftrace_64.S @@ -4,6 +4,7 @@ */ #include <linux/linkage.h> +#include <linux/cfi_types.h> #include <asm/ptrace.h> #include <asm/ftrace.h> #include <asm/export.h> @@ -129,6 +130,14 @@ .endm +SYM_TYPED_FUNC_START(ftrace_stub) + RET +SYM_FUNC_END(ftrace_stub) + +SYM_TYPED_FUNC_START(ftrace_stub_graph) + RET +SYM_FUNC_END(ftrace_stub_graph) + #ifdef CONFIG_DYNAMIC_FTRACE SYM_FUNC_START(__fentry__) @@ -172,21 +181,10 @@ SYM_INNER_LABEL(ftrace_call, SYM_L_GLOBAL) */ SYM_INNER_LABEL(ftrace_caller_end, SYM_L_GLOBAL) ANNOTATE_NOENDBR - - jmp ftrace_epilogue + RET SYM_FUNC_END(ftrace_caller); STACK_FRAME_NON_STANDARD_FP(ftrace_caller) -SYM_FUNC_START(ftrace_epilogue) -/* - * This is weak to keep gas from relaxing the jumps. - */ -SYM_INNER_LABEL_ALIGN(ftrace_stub, SYM_L_WEAK) - UNWIND_HINT_FUNC - ENDBR - RET -SYM_FUNC_END(ftrace_epilogue) - SYM_FUNC_START(ftrace_regs_caller) /* Save the current flags before any operations that can change them */ pushfq @@ -262,14 +260,11 @@ SYM_INNER_LABEL(ftrace_regs_caller_jmp, SYM_L_GLOBAL) popfq /* - * As this jmp to ftrace_epilogue can be a short jump - * it must not be copied into the trampoline. - * The trampoline will add the code to jump - * to the return. + * The trampoline will add the return. */ SYM_INNER_LABEL(ftrace_regs_caller_end, SYM_L_GLOBAL) ANNOTATE_NOENDBR - jmp ftrace_epilogue + RET /* Swap the flags with orig_rax */ 1: movq MCOUNT_REG_SIZE(%rsp), %rdi @@ -280,7 +275,7 @@ SYM_INNER_LABEL(ftrace_regs_caller_end, SYM_L_GLOBAL) /* Restore flags */ popfq UNWIND_HINT_FUNC - jmp ftrace_epilogue + RET SYM_FUNC_END(ftrace_regs_caller) STACK_FRAME_NON_STANDARD_FP(ftrace_regs_caller) @@ -291,9 +286,6 @@ STACK_FRAME_NON_STANDARD_FP(ftrace_regs_caller) SYM_FUNC_START(__fentry__) cmpq $ftrace_stub, ftrace_trace_function jnz trace - -SYM_INNER_LABEL(ftrace_stub, SYM_L_GLOBAL) - ENDBR RET trace: diff --git a/arch/x86/kernel/unwind_orc.c b/arch/x86/kernel/unwind_orc.c index 0ea57da92940..c059820dfaea 100644 --- a/arch/x86/kernel/unwind_orc.c +++ b/arch/x86/kernel/unwind_orc.c @@ -713,7 +713,7 @@ void __unwind_start(struct unwind_state *state, struct task_struct *task, /* Otherwise, skip ahead to the user-specified starting frame: */ while (!unwind_done(state) && (!on_stack(&state->stack_info, first_frame, sizeof(long)) || - state->sp < (unsigned long)first_frame)) + state->sp <= (unsigned long)first_frame)) unwind_next_frame(state); return; diff --git a/arch/x86/kvm/.gitignore b/arch/x86/kvm/.gitignore new file mode 100644 index 000000000000..615d6ff35c00 --- /dev/null +++ b/arch/x86/kvm/.gitignore @@ -0,0 +1,2 @@ +/kvm-asm-offsets.s +/kvm-asm-offsets.h diff --git a/arch/x86/kvm/Makefile b/arch/x86/kvm/Makefile index 30f244b64523..f453a0f96e24 100644 --- a/arch/x86/kvm/Makefile +++ b/arch/x86/kvm/Makefile @@ -34,3 +34,15 @@ endif obj-$(CONFIG_KVM) += kvm.o obj-$(CONFIG_KVM_INTEL) += kvm-intel.o obj-$(CONFIG_KVM_AMD) += kvm-amd.o + +AFLAGS_svm/vmenter.o := -iquote $(obj) +$(obj)/svm/vmenter.o: $(obj)/kvm-asm-offsets.h + +AFLAGS_vmx/vmenter.o := -iquote $(obj) +$(obj)/vmx/vmenter.o: $(obj)/kvm-asm-offsets.h + +$(obj)/kvm-asm-offsets.h: $(obj)/kvm-asm-offsets.s FORCE + $(call filechk,offsets,__KVM_ASM_OFFSETS_H__) + +targets += kvm-asm-offsets.s +clean-files += kvm-asm-offsets.h diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index 7065462378e2..62bc7a01cecc 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -1133,11 +1133,13 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function) entry->eax = max(entry->eax, 0x80000021); break; case 0x80000001: + entry->ebx &= ~GENMASK(27, 16); cpuid_entry_override(entry, CPUID_8000_0001_EDX); cpuid_entry_override(entry, CPUID_8000_0001_ECX); break; case 0x80000006: - /* L2 cache and TLB: pass through host info. */ + /* Drop reserved bits, pass host L2 cache and TLB info. */ + entry->edx &= ~GENMASK(17, 16); break; case 0x80000007: /* Advanced power management */ /* invariant TSC is CPUID.80000007H:EDX[8] */ @@ -1167,6 +1169,7 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function) g_phys_as = phys_as; entry->eax = g_phys_as | (virt_as << 8); + entry->ecx &= ~(GENMASK(31, 16) | GENMASK(11, 8)); entry->edx = 0; cpuid_entry_override(entry, CPUID_8000_0008_EBX); break; @@ -1186,6 +1189,9 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function) entry->ecx = entry->edx = 0; break; case 0x8000001a: + entry->eax &= GENMASK(2, 0); + entry->ebx = entry->ecx = entry->edx = 0; + break; case 0x8000001e: break; case 0x8000001F: @@ -1193,7 +1199,8 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function) entry->eax = entry->ebx = entry->ecx = entry->edx = 0; } else { cpuid_entry_override(entry, CPUID_8000_001F_EAX); - + /* Clear NumVMPL since KVM does not support VMPL. */ + entry->ebx &= ~GENMASK(31, 12); /* * Enumerate '0' for "PA bits reduction", the adjusted * MAXPHYADDR is enumerated directly (see 0x80000008). @@ -1331,7 +1338,7 @@ int kvm_dev_ioctl_get_cpuid(struct kvm_cpuid2 *cpuid, if (sanity_check_entries(entries, cpuid->nent, type)) return -EINVAL; - array.entries = kvcalloc(sizeof(struct kvm_cpuid_entry2), cpuid->nent, GFP_KERNEL); + array.entries = kvcalloc(cpuid->nent, sizeof(struct kvm_cpuid_entry2), GFP_KERNEL); if (!array.entries) return -ENOMEM; diff --git a/arch/x86/kvm/debugfs.c b/arch/x86/kvm/debugfs.c index cfed36aba2f7..c1390357126a 100644 --- a/arch/x86/kvm/debugfs.c +++ b/arch/x86/kvm/debugfs.c @@ -158,11 +158,16 @@ out: static int kvm_mmu_rmaps_stat_open(struct inode *inode, struct file *file) { struct kvm *kvm = inode->i_private; + int r; if (!kvm_get_kvm_safe(kvm)) return -ENOENT; - return single_open(file, kvm_mmu_rmaps_stat_show, kvm); + r = single_open(file, kvm_mmu_rmaps_stat_show, kvm); + if (r < 0) + kvm_put_kvm(kvm); + + return r; } static int kvm_mmu_rmaps_stat_release(struct inode *inode, struct file *file) diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index 3b27622d4642..4a43261d25a2 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -791,8 +791,7 @@ static int linearize(struct x86_emulate_ctxt *ctxt, ctxt->mode, linear); } -static inline int assign_eip(struct x86_emulate_ctxt *ctxt, ulong dst, - enum x86emul_mode mode) +static inline int assign_eip(struct x86_emulate_ctxt *ctxt, ulong dst) { ulong linear; int rc; @@ -802,41 +801,71 @@ static inline int assign_eip(struct x86_emulate_ctxt *ctxt, ulong dst, if (ctxt->op_bytes != sizeof(unsigned long)) addr.ea = dst & ((1UL << (ctxt->op_bytes << 3)) - 1); - rc = __linearize(ctxt, addr, &max_size, 1, false, true, mode, &linear); + rc = __linearize(ctxt, addr, &max_size, 1, false, true, ctxt->mode, &linear); if (rc == X86EMUL_CONTINUE) ctxt->_eip = addr.ea; return rc; } +static inline int emulator_recalc_and_set_mode(struct x86_emulate_ctxt *ctxt) +{ + u64 efer; + struct desc_struct cs; + u16 selector; + u32 base3; + + ctxt->ops->get_msr(ctxt, MSR_EFER, &efer); + + if (!(ctxt->ops->get_cr(ctxt, 0) & X86_CR0_PE)) { + /* Real mode. cpu must not have long mode active */ + if (efer & EFER_LMA) + return X86EMUL_UNHANDLEABLE; + ctxt->mode = X86EMUL_MODE_REAL; + return X86EMUL_CONTINUE; + } + + if (ctxt->eflags & X86_EFLAGS_VM) { + /* Protected/VM86 mode. cpu must not have long mode active */ + if (efer & EFER_LMA) + return X86EMUL_UNHANDLEABLE; + ctxt->mode = X86EMUL_MODE_VM86; + return X86EMUL_CONTINUE; + } + + if (!ctxt->ops->get_segment(ctxt, &selector, &cs, &base3, VCPU_SREG_CS)) + return X86EMUL_UNHANDLEABLE; + + if (efer & EFER_LMA) { + if (cs.l) { + /* Proper long mode */ + ctxt->mode = X86EMUL_MODE_PROT64; + } else if (cs.d) { + /* 32 bit compatibility mode*/ + ctxt->mode = X86EMUL_MODE_PROT32; + } else { + ctxt->mode = X86EMUL_MODE_PROT16; + } + } else { + /* Legacy 32 bit / 16 bit mode */ + ctxt->mode = cs.d ? X86EMUL_MODE_PROT32 : X86EMUL_MODE_PROT16; + } + + return X86EMUL_CONTINUE; +} + static inline int assign_eip_near(struct x86_emulate_ctxt *ctxt, ulong dst) { - return assign_eip(ctxt, dst, ctxt->mode); + return assign_eip(ctxt, dst); } -static int assign_eip_far(struct x86_emulate_ctxt *ctxt, ulong dst, - const struct desc_struct *cs_desc) +static int assign_eip_far(struct x86_emulate_ctxt *ctxt, ulong dst) { - enum x86emul_mode mode = ctxt->mode; - int rc; + int rc = emulator_recalc_and_set_mode(ctxt); -#ifdef CONFIG_X86_64 - if (ctxt->mode >= X86EMUL_MODE_PROT16) { - if (cs_desc->l) { - u64 efer = 0; + if (rc != X86EMUL_CONTINUE) + return rc; - ctxt->ops->get_msr(ctxt, MSR_EFER, &efer); - if (efer & EFER_LMA) - mode = X86EMUL_MODE_PROT64; - } else - mode = X86EMUL_MODE_PROT32; /* temporary value */ - } -#endif - if (mode == X86EMUL_MODE_PROT16 || mode == X86EMUL_MODE_PROT32) - mode = cs_desc->d ? X86EMUL_MODE_PROT32 : X86EMUL_MODE_PROT16; - rc = assign_eip(ctxt, dst, mode); - if (rc == X86EMUL_CONTINUE) - ctxt->mode = mode; - return rc; + return assign_eip(ctxt, dst); } static inline int jmp_rel(struct x86_emulate_ctxt *ctxt, int rel) @@ -2172,7 +2201,7 @@ static int em_jmp_far(struct x86_emulate_ctxt *ctxt) if (rc != X86EMUL_CONTINUE) return rc; - rc = assign_eip_far(ctxt, ctxt->src.val, &new_desc); + rc = assign_eip_far(ctxt, ctxt->src.val); /* Error handling is not implemented. */ if (rc != X86EMUL_CONTINUE) return X86EMUL_UNHANDLEABLE; @@ -2250,7 +2279,7 @@ static int em_ret_far(struct x86_emulate_ctxt *ctxt) &new_desc); if (rc != X86EMUL_CONTINUE) return rc; - rc = assign_eip_far(ctxt, eip, &new_desc); + rc = assign_eip_far(ctxt, eip); /* Error handling is not implemented. */ if (rc != X86EMUL_CONTINUE) return X86EMUL_UNHANDLEABLE; @@ -2432,7 +2461,7 @@ static int rsm_load_state_32(struct x86_emulate_ctxt *ctxt, ctxt->eflags = GET_SMSTATE(u32, smstate, 0x7ff4) | X86_EFLAGS_FIXED; ctxt->_eip = GET_SMSTATE(u32, smstate, 0x7ff0); - for (i = 0; i < NR_EMULATOR_GPRS; i++) + for (i = 0; i < 8; i++) *reg_write(ctxt, i) = GET_SMSTATE(u32, smstate, 0x7fd0 + i * 4); val = GET_SMSTATE(u32, smstate, 0x7fcc); @@ -2489,7 +2518,7 @@ static int rsm_load_state_64(struct x86_emulate_ctxt *ctxt, u16 selector; int i, r; - for (i = 0; i < NR_EMULATOR_GPRS; i++) + for (i = 0; i < 16; i++) *reg_write(ctxt, i) = GET_SMSTATE(u64, smstate, 0x7ff8 - i * 8); ctxt->_eip = GET_SMSTATE(u64, smstate, 0x7f78); @@ -2633,7 +2662,7 @@ static int em_rsm(struct x86_emulate_ctxt *ctxt) * those side effects need to be explicitly handled for both success * and shutdown. */ - return X86EMUL_CONTINUE; + return emulator_recalc_and_set_mode(ctxt); emulate_shutdown: ctxt->ops->triple_fault(ctxt); @@ -2876,6 +2905,7 @@ static int em_sysexit(struct x86_emulate_ctxt *ctxt) ops->set_segment(ctxt, ss_sel, &ss, 0, VCPU_SREG_SS); ctxt->_eip = rdx; + ctxt->mode = usermode; *reg_write(ctxt, VCPU_REGS_RSP) = rcx; return X86EMUL_CONTINUE; @@ -3469,7 +3499,7 @@ static int em_call_far(struct x86_emulate_ctxt *ctxt) if (rc != X86EMUL_CONTINUE) return rc; - rc = assign_eip_far(ctxt, ctxt->src.val, &new_desc); + rc = assign_eip_far(ctxt, ctxt->src.val); if (rc != X86EMUL_CONTINUE) goto fail; @@ -3611,11 +3641,25 @@ static int em_movbe(struct x86_emulate_ctxt *ctxt) static int em_cr_write(struct x86_emulate_ctxt *ctxt) { - if (ctxt->ops->set_cr(ctxt, ctxt->modrm_reg, ctxt->src.val)) + int cr_num = ctxt->modrm_reg; + int r; + + if (ctxt->ops->set_cr(ctxt, cr_num, ctxt->src.val)) return emulate_gp(ctxt, 0); /* Disable writeback. */ ctxt->dst.type = OP_NONE; + + if (cr_num == 0) { + /* + * CR0 write might have updated CR0.PE and/or CR0.PG + * which can affect the cpu's execution mode. + */ + r = emulator_recalc_and_set_mode(ctxt); + if (r != X86EMUL_CONTINUE) + return r; + } + return X86EMUL_CONTINUE; } diff --git a/arch/x86/kvm/kvm-asm-offsets.c b/arch/x86/kvm/kvm-asm-offsets.c new file mode 100644 index 000000000000..24a710d37323 --- /dev/null +++ b/arch/x86/kvm/kvm-asm-offsets.c @@ -0,0 +1,29 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Generate definitions needed by assembly language modules. + * This code generates raw asm output which is post-processed to extract + * and format the required data. + */ +#define COMPILE_OFFSETS + +#include <linux/kbuild.h> +#include "vmx/vmx.h" +#include "svm/svm.h" + +static void __used common(void) +{ + if (IS_ENABLED(CONFIG_KVM_AMD)) { + BLANK(); + OFFSET(SVM_vcpu_arch_regs, vcpu_svm, vcpu.arch.regs); + OFFSET(SVM_current_vmcb, vcpu_svm, current_vmcb); + OFFSET(SVM_spec_ctrl, vcpu_svm, spec_ctrl); + OFFSET(SVM_vmcb01, vcpu_svm, vmcb01); + OFFSET(KVM_VMCB_pa, kvm_vmcb_info, pa); + OFFSET(SD_save_area_pa, svm_cpu_data, save_area_pa); + } + + if (IS_ENABLED(CONFIG_KVM_INTEL)) { + BLANK(); + OFFSET(VMX_spec_ctrl, vcpu_vmx, spec_ctrl); + } +} diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index 6f81539061d6..1ccb769f62af 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -6056,7 +6056,7 @@ void kvm_zap_gfn_range(struct kvm *kvm, gfn_t gfn_start, gfn_t gfn_end) write_lock(&kvm->mmu_lock); - kvm_mmu_invalidate_begin(kvm, gfn_start, gfn_end); + kvm_mmu_invalidate_begin(kvm, 0, -1ul); flush = kvm_rmap_zap_gfn_range(kvm, gfn_start, gfn_end); @@ -6070,7 +6070,7 @@ void kvm_zap_gfn_range(struct kvm *kvm, gfn_t gfn_start, gfn_t gfn_end) kvm_flush_remote_tlbs_with_address(kvm, gfn_start, gfn_end - gfn_start); - kvm_mmu_invalidate_end(kvm, gfn_start, gfn_end); + kvm_mmu_invalidate_end(kvm, 0, -1ul); write_unlock(&kvm->mmu_lock); } diff --git a/arch/x86/kvm/pmu.c b/arch/x86/kvm/pmu.c index d9b9a0f0db17..de1fd7369736 100644 --- a/arch/x86/kvm/pmu.c +++ b/arch/x86/kvm/pmu.c @@ -56,7 +56,7 @@ static const struct x86_cpu_id vmx_icl_pebs_cpu[] = { * code. Each pmc, stored in kvm_pmc.idx field, is unique across * all perf counters (both gp and fixed). The mapping relationship * between pmc and perf counters is as the following: - * * Intel: [0 .. INTEL_PMC_MAX_GENERIC-1] <=> gp counters + * * Intel: [0 .. KVM_INTEL_PMC_MAX_GENERIC-1] <=> gp counters * [INTEL_PMC_IDX_FIXED .. INTEL_PMC_IDX_FIXED + 2] <=> fixed * * AMD: [0 .. AMD64_NUM_COUNTERS-1] and, for families 15H * and later, [0 .. AMD64_NUM_COUNTERS_CORE-1] <=> gp counters diff --git a/arch/x86/kvm/svm/pmu.c b/arch/x86/kvm/svm/pmu.c index b68956299fa8..9d65cd095691 100644 --- a/arch/x86/kvm/svm/pmu.c +++ b/arch/x86/kvm/svm/pmu.c @@ -192,9 +192,10 @@ static void amd_pmu_init(struct kvm_vcpu *vcpu) struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); int i; - BUILD_BUG_ON(AMD64_NUM_COUNTERS_CORE > INTEL_PMC_MAX_GENERIC); + BUILD_BUG_ON(KVM_AMD_PMC_MAX_GENERIC > AMD64_NUM_COUNTERS_CORE); + BUILD_BUG_ON(KVM_AMD_PMC_MAX_GENERIC > INTEL_PMC_MAX_GENERIC); - for (i = 0; i < AMD64_NUM_COUNTERS_CORE ; i++) { + for (i = 0; i < KVM_AMD_PMC_MAX_GENERIC ; i++) { pmu->gp_counters[i].type = KVM_PMC_GP; pmu->gp_counters[i].vcpu = vcpu; pmu->gp_counters[i].idx = i; @@ -207,7 +208,7 @@ static void amd_pmu_reset(struct kvm_vcpu *vcpu) struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); int i; - for (i = 0; i < AMD64_NUM_COUNTERS_CORE; i++) { + for (i = 0; i < KVM_AMD_PMC_MAX_GENERIC; i++) { struct kvm_pmc *pmc = &pmu->gp_counters[i]; pmc_stop_counter(pmc); diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c index 28064060413a..efaaef2b7ae1 100644 --- a/arch/x86/kvm/svm/sev.c +++ b/arch/x86/kvm/svm/sev.c @@ -196,7 +196,7 @@ static void sev_asid_free(struct kvm_sev_info *sev) __set_bit(sev->asid, sev_reclaim_asid_bitmap); for_each_possible_cpu(cpu) { - sd = per_cpu(svm_data, cpu); + sd = per_cpu_ptr(&svm_data, cpu); sd->sev_vmcbs[sev->asid] = NULL; } @@ -605,7 +605,7 @@ static int sev_es_sync_vmsa(struct vcpu_svm *svm) save->dr6 = svm->vcpu.arch.dr6; pr_debug("Virtual Machine Save Area (VMSA):\n"); - print_hex_dump(KERN_CONT, "", DUMP_PREFIX_NONE, 16, 1, save, sizeof(*save), false); + print_hex_dump_debug("", DUMP_PREFIX_NONE, 16, 1, save, sizeof(*save), false); return 0; } @@ -2600,7 +2600,7 @@ void sev_es_unmap_ghcb(struct vcpu_svm *svm) void pre_sev_run(struct vcpu_svm *svm, int cpu) { - struct svm_cpu_data *sd = per_cpu(svm_data, cpu); + struct svm_cpu_data *sd = per_cpu_ptr(&svm_data, cpu); int asid = sev_get_asid(svm->vcpu.kvm); /* Assign the asid allocated with this SEV guest */ diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index 58f0077d9357..9f88c8e6766e 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -245,7 +245,7 @@ struct kvm_ldttss_desc { u32 zero1; } __attribute__((packed)); -DEFINE_PER_CPU(struct svm_cpu_data *, svm_data); +DEFINE_PER_CPU(struct svm_cpu_data, svm_data); /* * Only MSR_TSC_AUX is switched via the user return hook. EFER is switched via @@ -581,12 +581,7 @@ static int svm_hardware_enable(void) pr_err("%s: err EOPNOTSUPP on %d\n", __func__, me); return -EINVAL; } - sd = per_cpu(svm_data, me); - if (!sd) { - pr_err("%s: svm_data is NULL on %d\n", __func__, me); - return -EINVAL; - } - + sd = per_cpu_ptr(&svm_data, me); sd->asid_generation = 1; sd->max_asid = cpuid_ebx(SVM_CPUID_FUNC) - 1; sd->next_asid = sd->max_asid + 1; @@ -597,7 +592,7 @@ static int svm_hardware_enable(void) wrmsrl(MSR_EFER, efer | EFER_SVME); - wrmsrl(MSR_VM_HSAVE_PA, __sme_page_pa(sd->save_area)); + wrmsrl(MSR_VM_HSAVE_PA, sd->save_area_pa); if (static_cpu_has(X86_FEATURE_TSCRATEMSR)) { /* @@ -646,42 +641,37 @@ static int svm_hardware_enable(void) static void svm_cpu_uninit(int cpu) { - struct svm_cpu_data *sd = per_cpu(svm_data, cpu); + struct svm_cpu_data *sd = per_cpu_ptr(&svm_data, cpu); - if (!sd) + if (!sd->save_area) return; - per_cpu(svm_data, cpu) = NULL; kfree(sd->sev_vmcbs); __free_page(sd->save_area); - kfree(sd); + sd->save_area_pa = 0; + sd->save_area = NULL; } static int svm_cpu_init(int cpu) { - struct svm_cpu_data *sd; + struct svm_cpu_data *sd = per_cpu_ptr(&svm_data, cpu); int ret = -ENOMEM; - sd = kzalloc(sizeof(struct svm_cpu_data), GFP_KERNEL); - if (!sd) - return ret; - sd->cpu = cpu; + memset(sd, 0, sizeof(struct svm_cpu_data)); sd->save_area = alloc_page(GFP_KERNEL | __GFP_ZERO); if (!sd->save_area) - goto free_cpu_data; + return ret; ret = sev_cpu_init(sd); if (ret) goto free_save_area; - per_cpu(svm_data, cpu) = sd; - + sd->save_area_pa = __sme_page_pa(sd->save_area); return 0; free_save_area: __free_page(sd->save_area); -free_cpu_data: - kfree(sd); + sd->save_area = NULL; return ret; } @@ -730,6 +720,15 @@ static bool msr_write_intercepted(struct kvm_vcpu *vcpu, u32 msr) u32 offset; u32 *msrpm; + /* + * For non-nested case: + * If the L01 MSR bitmap does not intercept the MSR, then we need to + * save it. + * + * For nested case: + * If the L02 MSR bitmap does not intercept the MSR, then we need to + * save it. + */ msrpm = is_guest_mode(vcpu) ? to_svm(vcpu)->nested.msrpm: to_svm(vcpu)->msrpm; @@ -1425,7 +1424,7 @@ static void svm_clear_current_vmcb(struct vmcb *vmcb) int i; for_each_online_cpu(i) - cmpxchg(&per_cpu(svm_data, i)->current_vmcb, vmcb, NULL); + cmpxchg(per_cpu_ptr(&svm_data.current_vmcb, i), vmcb, NULL); } static void svm_vcpu_free(struct kvm_vcpu *vcpu) @@ -1450,7 +1449,7 @@ static void svm_vcpu_free(struct kvm_vcpu *vcpu) static void svm_prepare_switch_to_guest(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); - struct svm_cpu_data *sd = per_cpu(svm_data, vcpu->cpu); + struct svm_cpu_data *sd = per_cpu_ptr(&svm_data, vcpu->cpu); if (sev_es_guest(vcpu->kvm)) sev_es_unmap_ghcb(svm); @@ -1462,7 +1461,7 @@ static void svm_prepare_switch_to_guest(struct kvm_vcpu *vcpu) * Save additional host state that will be restored on VMEXIT (sev-es) * or subsequent vmload of host save area. */ - vmsave(__sme_page_pa(sd->save_area)); + vmsave(sd->save_area_pa); if (sev_es_guest(vcpu->kvm)) { struct sev_es_save_area *hostsa; hostsa = (struct sev_es_save_area *)(page_address(sd->save_area) + 0x400); @@ -1487,7 +1486,7 @@ static void svm_prepare_host_switch(struct kvm_vcpu *vcpu) static void svm_vcpu_load(struct kvm_vcpu *vcpu, int cpu) { struct vcpu_svm *svm = to_svm(vcpu); - struct svm_cpu_data *sd = per_cpu(svm_data, cpu); + struct svm_cpu_data *sd = per_cpu_ptr(&svm_data, cpu); if (sd->current_vmcb != svm->vmcb) { sd->current_vmcb = svm->vmcb; @@ -3443,7 +3442,7 @@ static int svm_handle_exit(struct kvm_vcpu *vcpu, fastpath_t exit_fastpath) static void reload_tss(struct kvm_vcpu *vcpu) { - struct svm_cpu_data *sd = per_cpu(svm_data, vcpu->cpu); + struct svm_cpu_data *sd = per_cpu_ptr(&svm_data, vcpu->cpu); sd->tss_desc->type = 9; /* available 32/64-bit TSS */ load_TR_desc(); @@ -3451,7 +3450,7 @@ static void reload_tss(struct kvm_vcpu *vcpu) static void pre_svm_run(struct kvm_vcpu *vcpu) { - struct svm_cpu_data *sd = per_cpu(svm_data, vcpu->cpu); + struct svm_cpu_data *sd = per_cpu_ptr(&svm_data, vcpu->cpu); struct vcpu_svm *svm = to_svm(vcpu); /* @@ -3911,30 +3910,16 @@ static fastpath_t svm_exit_handlers_fastpath(struct kvm_vcpu *vcpu) return EXIT_FASTPATH_NONE; } -static noinstr void svm_vcpu_enter_exit(struct kvm_vcpu *vcpu) +static noinstr void svm_vcpu_enter_exit(struct kvm_vcpu *vcpu, bool spec_ctrl_intercepted) { struct vcpu_svm *svm = to_svm(vcpu); - unsigned long vmcb_pa = svm->current_vmcb->pa; guest_state_enter_irqoff(); - if (sev_es_guest(vcpu->kvm)) { - __svm_sev_es_vcpu_run(vmcb_pa); - } else { - struct svm_cpu_data *sd = per_cpu(svm_data, vcpu->cpu); - - /* - * Use a single vmcb (vmcb01 because it's always valid) for - * context switching guest state via VMLOAD/VMSAVE, that way - * the state doesn't need to be copied between vmcb01 and - * vmcb02 when switching vmcbs for nested virtualization. - */ - vmload(svm->vmcb01.pa); - __svm_vcpu_run(vmcb_pa, (unsigned long *)&vcpu->arch.regs); - vmsave(svm->vmcb01.pa); - - vmload(__sme_page_pa(sd->save_area)); - } + if (sev_es_guest(vcpu->kvm)) + __svm_sev_es_vcpu_run(svm, spec_ctrl_intercepted); + else + __svm_vcpu_run(svm, spec_ctrl_intercepted); guest_state_exit_irqoff(); } @@ -3942,6 +3927,7 @@ static noinstr void svm_vcpu_enter_exit(struct kvm_vcpu *vcpu) static __no_kcsan fastpath_t svm_vcpu_run(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); + bool spec_ctrl_intercepted = msr_write_intercepted(vcpu, MSR_IA32_SPEC_CTRL); trace_kvm_entry(vcpu); @@ -3998,34 +3984,15 @@ static __no_kcsan fastpath_t svm_vcpu_run(struct kvm_vcpu *vcpu) * being speculatively taken. */ if (!static_cpu_has(X86_FEATURE_V_SPEC_CTRL)) - x86_spec_ctrl_set_guest(svm->spec_ctrl, svm->virt_spec_ctrl); + x86_spec_ctrl_set_guest(svm->virt_spec_ctrl); - svm_vcpu_enter_exit(vcpu); - - /* - * We do not use IBRS in the kernel. If this vCPU has used the - * SPEC_CTRL MSR it may have left it on; save the value and - * turn it off. This is much more efficient than blindly adding - * it to the atomic save/restore list. Especially as the former - * (Saving guest MSRs on vmexit) doesn't even exist in KVM. - * - * For non-nested case: - * If the L01 MSR bitmap does not intercept the MSR, then we need to - * save it. - * - * For nested case: - * If the L02 MSR bitmap does not intercept the MSR, then we need to - * save it. - */ - if (!static_cpu_has(X86_FEATURE_V_SPEC_CTRL) && - unlikely(!msr_write_intercepted(vcpu, MSR_IA32_SPEC_CTRL))) - svm->spec_ctrl = native_read_msr(MSR_IA32_SPEC_CTRL); + svm_vcpu_enter_exit(vcpu, spec_ctrl_intercepted); if (!sev_es_guest(vcpu->kvm)) reload_tss(vcpu); if (!static_cpu_has(X86_FEATURE_V_SPEC_CTRL)) - x86_spec_ctrl_restore_host(svm->spec_ctrl, svm->virt_spec_ctrl); + x86_spec_ctrl_restore_host(svm->virt_spec_ctrl); if (!sev_es_guest(vcpu->kvm)) { vcpu->arch.cr2 = svm->vmcb->save.cr2; diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h index 6a7686bf6900..199a2ecef1ce 100644 --- a/arch/x86/kvm/svm/svm.h +++ b/arch/x86/kvm/svm/svm.h @@ -209,7 +209,6 @@ struct vcpu_svm { struct vmcb *vmcb; struct kvm_vmcb_info vmcb01; struct kvm_vmcb_info *current_vmcb; - struct svm_cpu_data *svm_data; u32 asid; u32 sysenter_esp_hi; u32 sysenter_eip_hi; @@ -281,8 +280,6 @@ struct vcpu_svm { }; struct svm_cpu_data { - int cpu; - u64 asid_generation; u32 max_asid; u32 next_asid; @@ -290,13 +287,15 @@ struct svm_cpu_data { struct kvm_ldttss_desc *tss_desc; struct page *save_area; + unsigned long save_area_pa; + struct vmcb *current_vmcb; /* index = sev_asid, value = vmcb pointer */ struct vmcb **sev_vmcbs; }; -DECLARE_PER_CPU(struct svm_cpu_data *, svm_data); +DECLARE_PER_CPU(struct svm_cpu_data, svm_data); void recalc_intercepts(struct vcpu_svm *svm); @@ -683,7 +682,7 @@ void sev_es_unmap_ghcb(struct vcpu_svm *svm); /* vmenter.S */ -void __svm_sev_es_vcpu_run(unsigned long vmcb_pa); -void __svm_vcpu_run(unsigned long vmcb_pa, unsigned long *regs); +void __svm_sev_es_vcpu_run(struct vcpu_svm *svm, bool spec_ctrl_intercepted); +void __svm_vcpu_run(struct vcpu_svm *svm, bool spec_ctrl_intercepted); #endif diff --git a/arch/x86/kvm/svm/svm_ops.h b/arch/x86/kvm/svm/svm_ops.h index 9430d6437c9f..36c8af87a707 100644 --- a/arch/x86/kvm/svm/svm_ops.h +++ b/arch/x86/kvm/svm/svm_ops.h @@ -61,9 +61,4 @@ static __always_inline void vmsave(unsigned long pa) svm_asm1(vmsave, "a" (pa), "memory"); } -static __always_inline void vmload(unsigned long pa) -{ - svm_asm1(vmload, "a" (pa), "memory"); -} - #endif /* __KVM_X86_SVM_OPS_H */ diff --git a/arch/x86/kvm/svm/vmenter.S b/arch/x86/kvm/svm/vmenter.S index 723f8534986c..34367dc203f2 100644 --- a/arch/x86/kvm/svm/vmenter.S +++ b/arch/x86/kvm/svm/vmenter.S @@ -4,35 +4,97 @@ #include <asm/bitsperlong.h> #include <asm/kvm_vcpu_regs.h> #include <asm/nospec-branch.h> +#include "kvm-asm-offsets.h" #define WORD_SIZE (BITS_PER_LONG / 8) /* Intentionally omit RAX as it's context switched by hardware */ -#define VCPU_RCX __VCPU_REGS_RCX * WORD_SIZE -#define VCPU_RDX __VCPU_REGS_RDX * WORD_SIZE -#define VCPU_RBX __VCPU_REGS_RBX * WORD_SIZE +#define VCPU_RCX (SVM_vcpu_arch_regs + __VCPU_REGS_RCX * WORD_SIZE) +#define VCPU_RDX (SVM_vcpu_arch_regs + __VCPU_REGS_RDX * WORD_SIZE) +#define VCPU_RBX (SVM_vcpu_arch_regs + __VCPU_REGS_RBX * WORD_SIZE) /* Intentionally omit RSP as it's context switched by hardware */ -#define VCPU_RBP __VCPU_REGS_RBP * WORD_SIZE -#define VCPU_RSI __VCPU_REGS_RSI * WORD_SIZE -#define VCPU_RDI __VCPU_REGS_RDI * WORD_SIZE +#define VCPU_RBP (SVM_vcpu_arch_regs + __VCPU_REGS_RBP * WORD_SIZE) +#define VCPU_RSI (SVM_vcpu_arch_regs + __VCPU_REGS_RSI * WORD_SIZE) +#define VCPU_RDI (SVM_vcpu_arch_regs + __VCPU_REGS_RDI * WORD_SIZE) #ifdef CONFIG_X86_64 -#define VCPU_R8 __VCPU_REGS_R8 * WORD_SIZE -#define VCPU_R9 __VCPU_REGS_R9 * WORD_SIZE -#define VCPU_R10 __VCPU_REGS_R10 * WORD_SIZE -#define VCPU_R11 __VCPU_REGS_R11 * WORD_SIZE -#define VCPU_R12 __VCPU_REGS_R12 * WORD_SIZE -#define VCPU_R13 __VCPU_REGS_R13 * WORD_SIZE -#define VCPU_R14 __VCPU_REGS_R14 * WORD_SIZE -#define VCPU_R15 __VCPU_REGS_R15 * WORD_SIZE +#define VCPU_R8 (SVM_vcpu_arch_regs + __VCPU_REGS_R8 * WORD_SIZE) +#define VCPU_R9 (SVM_vcpu_arch_regs + __VCPU_REGS_R9 * WORD_SIZE) +#define VCPU_R10 (SVM_vcpu_arch_regs + __VCPU_REGS_R10 * WORD_SIZE) +#define VCPU_R11 (SVM_vcpu_arch_regs + __VCPU_REGS_R11 * WORD_SIZE) +#define VCPU_R12 (SVM_vcpu_arch_regs + __VCPU_REGS_R12 * WORD_SIZE) +#define VCPU_R13 (SVM_vcpu_arch_regs + __VCPU_REGS_R13 * WORD_SIZE) +#define VCPU_R14 (SVM_vcpu_arch_regs + __VCPU_REGS_R14 * WORD_SIZE) +#define VCPU_R15 (SVM_vcpu_arch_regs + __VCPU_REGS_R15 * WORD_SIZE) #endif +#define SVM_vmcb01_pa (SVM_vmcb01 + KVM_VMCB_pa) + .section .noinstr.text, "ax" +.macro RESTORE_GUEST_SPEC_CTRL + /* No need to do anything if SPEC_CTRL is unset or V_SPEC_CTRL is set */ + ALTERNATIVE_2 "", \ + "jmp 800f", X86_FEATURE_MSR_SPEC_CTRL, \ + "", X86_FEATURE_V_SPEC_CTRL +801: +.endm +.macro RESTORE_GUEST_SPEC_CTRL_BODY +800: + /* + * SPEC_CTRL handling: if the guest's SPEC_CTRL value differs from the + * host's, write the MSR. This is kept out-of-line so that the common + * case does not have to jump. + * + * IMPORTANT: To avoid RSB underflow attacks and any other nastiness, + * there must not be any returns or indirect branches between this code + * and vmentry. + */ + movl SVM_spec_ctrl(%_ASM_DI), %eax + cmp PER_CPU_VAR(x86_spec_ctrl_current), %eax + je 801b + mov $MSR_IA32_SPEC_CTRL, %ecx + xor %edx, %edx + wrmsr + jmp 801b +.endm + +.macro RESTORE_HOST_SPEC_CTRL + /* No need to do anything if SPEC_CTRL is unset or V_SPEC_CTRL is set */ + ALTERNATIVE_2 "", \ + "jmp 900f", X86_FEATURE_MSR_SPEC_CTRL, \ + "", X86_FEATURE_V_SPEC_CTRL +901: +.endm +.macro RESTORE_HOST_SPEC_CTRL_BODY +900: + /* Same for after vmexit. */ + mov $MSR_IA32_SPEC_CTRL, %ecx + + /* + * Load the value that the guest had written into MSR_IA32_SPEC_CTRL, + * if it was not intercepted during guest execution. + */ + cmpb $0, (%_ASM_SP) + jnz 998f + rdmsr + movl %eax, SVM_spec_ctrl(%_ASM_DI) +998: + + /* Now restore the host value of the MSR if different from the guest's. */ + movl PER_CPU_VAR(x86_spec_ctrl_current), %eax + cmp SVM_spec_ctrl(%_ASM_DI), %eax + je 901b + xor %edx, %edx + wrmsr + jmp 901b +.endm + + /** * __svm_vcpu_run - Run a vCPU via a transition to SVM guest mode - * @vmcb_pa: unsigned long - * @regs: unsigned long * (to guest registers) + * @svm: struct vcpu_svm * + * @spec_ctrl_intercepted: bool */ SYM_FUNC_START(__svm_vcpu_run) push %_ASM_BP @@ -47,49 +109,71 @@ SYM_FUNC_START(__svm_vcpu_run) #endif push %_ASM_BX - /* Save @regs. */ + /* + * Save variables needed after vmexit on the stack, in inverse + * order compared to when they are needed. + */ + + /* Accessed directly from the stack in RESTORE_HOST_SPEC_CTRL. */ push %_ASM_ARG2 - /* Save @vmcb. */ + /* Needed to restore access to percpu variables. */ + __ASM_SIZE(push) PER_CPU_VAR(svm_data + SD_save_area_pa) + + /* Finally save @svm. */ push %_ASM_ARG1 - /* Move @regs to RAX. */ - mov %_ASM_ARG2, %_ASM_AX +.ifnc _ASM_ARG1, _ASM_DI + /* + * Stash @svm in RDI early. On 32-bit, arguments are in RAX, RCX + * and RDX which are clobbered by RESTORE_GUEST_SPEC_CTRL. + */ + mov %_ASM_ARG1, %_ASM_DI +.endif + + /* Clobbers RAX, RCX, RDX. */ + RESTORE_GUEST_SPEC_CTRL + + /* + * Use a single vmcb (vmcb01 because it's always valid) for + * context switching guest state via VMLOAD/VMSAVE, that way + * the state doesn't need to be copied between vmcb01 and + * vmcb02 when switching vmcbs for nested virtualization. + */ + mov SVM_vmcb01_pa(%_ASM_DI), %_ASM_AX +1: vmload %_ASM_AX +2: + + /* Get svm->current_vmcb->pa into RAX. */ + mov SVM_current_vmcb(%_ASM_DI), %_ASM_AX + mov KVM_VMCB_pa(%_ASM_AX), %_ASM_AX /* Load guest registers. */ - mov VCPU_RCX(%_ASM_AX), %_ASM_CX - mov VCPU_RDX(%_ASM_AX), %_ASM_DX - mov VCPU_RBX(%_ASM_AX), %_ASM_BX - mov VCPU_RBP(%_ASM_AX), %_ASM_BP - mov VCPU_RSI(%_ASM_AX), %_ASM_SI - mov VCPU_RDI(%_ASM_AX), %_ASM_DI + mov VCPU_RCX(%_ASM_DI), %_ASM_CX + mov VCPU_RDX(%_ASM_DI), %_ASM_DX + mov VCPU_RBX(%_ASM_DI), %_ASM_BX + mov VCPU_RBP(%_ASM_DI), %_ASM_BP + mov VCPU_RSI(%_ASM_DI), %_ASM_SI #ifdef CONFIG_X86_64 - mov VCPU_R8 (%_ASM_AX), %r8 - mov VCPU_R9 (%_ASM_AX), %r9 - mov VCPU_R10(%_ASM_AX), %r10 - mov VCPU_R11(%_ASM_AX), %r11 - mov VCPU_R12(%_ASM_AX), %r12 - mov VCPU_R13(%_ASM_AX), %r13 - mov VCPU_R14(%_ASM_AX), %r14 - mov VCPU_R15(%_ASM_AX), %r15 + mov VCPU_R8 (%_ASM_DI), %r8 + mov VCPU_R9 (%_ASM_DI), %r9 + mov VCPU_R10(%_ASM_DI), %r10 + mov VCPU_R11(%_ASM_DI), %r11 + mov VCPU_R12(%_ASM_DI), %r12 + mov VCPU_R13(%_ASM_DI), %r13 + mov VCPU_R14(%_ASM_DI), %r14 + mov VCPU_R15(%_ASM_DI), %r15 #endif - - /* "POP" @vmcb to RAX. */ - pop %_ASM_AX + mov VCPU_RDI(%_ASM_DI), %_ASM_DI /* Enter guest mode */ sti -1: vmrun %_ASM_AX - -2: cli - -#ifdef CONFIG_RETPOLINE - /* IMPORTANT: Stuff the RSB immediately after VM-Exit, before RET! */ - FILL_RETURN_BUFFER %_ASM_AX, RSB_CLEAR_LOOPS, X86_FEATURE_RETPOLINE -#endif +3: vmrun %_ASM_AX +4: + cli - /* "POP" @regs to RAX. */ + /* Pop @svm to RAX while it's the only available register. */ pop %_ASM_AX /* Save all guest registers. */ @@ -110,6 +194,26 @@ SYM_FUNC_START(__svm_vcpu_run) mov %r15, VCPU_R15(%_ASM_AX) #endif + /* @svm can stay in RDI from now on. */ + mov %_ASM_AX, %_ASM_DI + + mov SVM_vmcb01_pa(%_ASM_DI), %_ASM_AX +5: vmsave %_ASM_AX +6: + + /* Restores GSBASE among other things, allowing access to percpu data. */ + pop %_ASM_AX +7: vmload %_ASM_AX +8: + +#ifdef CONFIG_RETPOLINE + /* IMPORTANT: Stuff the RSB immediately after VM-Exit, before RET! */ + FILL_RETURN_BUFFER %_ASM_AX, RSB_CLEAR_LOOPS, X86_FEATURE_RETPOLINE +#endif + + /* Clobbers RAX, RCX, RDX. */ + RESTORE_HOST_SPEC_CTRL + /* * Mitigate RETBleed for AMD/Hygon Zen uarch. RET should be * untrained as soon as we exit the VM and are back to the @@ -145,6 +249,9 @@ SYM_FUNC_START(__svm_vcpu_run) xor %r15d, %r15d #endif + /* "Pop" @spec_ctrl_intercepted. */ + pop %_ASM_BX + pop %_ASM_BX #ifdef CONFIG_X86_64 @@ -159,17 +266,33 @@ SYM_FUNC_START(__svm_vcpu_run) pop %_ASM_BP RET -3: cmpb $0, kvm_rebooting + RESTORE_GUEST_SPEC_CTRL_BODY + RESTORE_HOST_SPEC_CTRL_BODY + +10: cmpb $0, kvm_rebooting jne 2b ud2 +30: cmpb $0, kvm_rebooting + jne 4b + ud2 +50: cmpb $0, kvm_rebooting + jne 6b + ud2 +70: cmpb $0, kvm_rebooting + jne 8b + ud2 - _ASM_EXTABLE(1b, 3b) + _ASM_EXTABLE(1b, 10b) + _ASM_EXTABLE(3b, 30b) + _ASM_EXTABLE(5b, 50b) + _ASM_EXTABLE(7b, 70b) SYM_FUNC_END(__svm_vcpu_run) /** * __svm_sev_es_vcpu_run - Run a SEV-ES vCPU via a transition to SVM guest mode - * @vmcb_pa: unsigned long + * @svm: struct vcpu_svm * + * @spec_ctrl_intercepted: bool */ SYM_FUNC_START(__svm_sev_es_vcpu_run) push %_ASM_BP @@ -184,8 +307,31 @@ SYM_FUNC_START(__svm_sev_es_vcpu_run) #endif push %_ASM_BX - /* Move @vmcb to RAX. */ - mov %_ASM_ARG1, %_ASM_AX + /* + * Save variables needed after vmexit on the stack, in inverse + * order compared to when they are needed. + */ + + /* Accessed directly from the stack in RESTORE_HOST_SPEC_CTRL. */ + push %_ASM_ARG2 + + /* Save @svm. */ + push %_ASM_ARG1 + +.ifnc _ASM_ARG1, _ASM_DI + /* + * Stash @svm in RDI early. On 32-bit, arguments are in RAX, RCX + * and RDX which are clobbered by RESTORE_GUEST_SPEC_CTRL. + */ + mov %_ASM_ARG1, %_ASM_DI +.endif + + /* Clobbers RAX, RCX, RDX. */ + RESTORE_GUEST_SPEC_CTRL + + /* Get svm->current_vmcb->pa into RAX. */ + mov SVM_current_vmcb(%_ASM_DI), %_ASM_AX + mov KVM_VMCB_pa(%_ASM_AX), %_ASM_AX /* Enter guest mode */ sti @@ -194,11 +340,17 @@ SYM_FUNC_START(__svm_sev_es_vcpu_run) 2: cli + /* Pop @svm to RDI, guest registers have been saved already. */ + pop %_ASM_DI + #ifdef CONFIG_RETPOLINE /* IMPORTANT: Stuff the RSB immediately after VM-Exit, before RET! */ FILL_RETURN_BUFFER %_ASM_AX, RSB_CLEAR_LOOPS, X86_FEATURE_RETPOLINE #endif + /* Clobbers RAX, RCX, RDX. */ + RESTORE_HOST_SPEC_CTRL + /* * Mitigate RETBleed for AMD/Hygon Zen uarch. RET should be * untrained as soon as we exit the VM and are back to the @@ -208,6 +360,9 @@ SYM_FUNC_START(__svm_sev_es_vcpu_run) */ UNTRAIN_RET + /* "Pop" @spec_ctrl_intercepted. */ + pop %_ASM_BX + pop %_ASM_BX #ifdef CONFIG_X86_64 @@ -222,6 +377,9 @@ SYM_FUNC_START(__svm_sev_es_vcpu_run) pop %_ASM_BP RET + RESTORE_GUEST_SPEC_CTRL_BODY + RESTORE_HOST_SPEC_CTRL_BODY + 3: cmpb $0, kvm_rebooting jne 2b ud2 diff --git a/arch/x86/kvm/vmx/capabilities.h b/arch/x86/kvm/vmx/capabilities.h index 87c4e46daf37..07254314f3dd 100644 --- a/arch/x86/kvm/vmx/capabilities.h +++ b/arch/x86/kvm/vmx/capabilities.h @@ -24,8 +24,6 @@ extern int __read_mostly pt_mode; #define PMU_CAP_FW_WRITES (1ULL << 13) #define PMU_CAP_LBR_FMT 0x3f -#define DEBUGCTLMSR_LBR_MASK (DEBUGCTLMSR_LBR | DEBUGCTLMSR_FREEZE_LBRS_ON_PMI) - struct nested_vmx_msrs { /* * We only store the "true" versions of the VMX capability MSRs. We @@ -400,6 +398,7 @@ static inline bool vmx_pebs_supported(void) static inline u64 vmx_get_perf_capabilities(void) { u64 perf_cap = PMU_CAP_FW_WRITES; + struct x86_pmu_lbr lbr; u64 host_perf_cap = 0; if (!enable_pmu) @@ -408,7 +407,8 @@ static inline u64 vmx_get_perf_capabilities(void) if (boot_cpu_has(X86_FEATURE_PDCM)) rdmsrl(MSR_IA32_PERF_CAPABILITIES, host_perf_cap); - perf_cap |= host_perf_cap & PMU_CAP_LBR_FMT; + if (x86_perf_get_lbr(&lbr) >= 0 && lbr.nr) + perf_cap |= host_perf_cap & PMU_CAP_LBR_FMT; if (vmx_pebs_supported()) { perf_cap |= host_perf_cap & PERF_CAP_PEBS_MASK; @@ -419,19 +419,6 @@ static inline u64 vmx_get_perf_capabilities(void) return perf_cap; } -static inline u64 vmx_supported_debugctl(void) -{ - u64 debugctl = 0; - - if (boot_cpu_has(X86_FEATURE_BUS_LOCK_DETECT)) - debugctl |= DEBUGCTLMSR_BUS_LOCK_DETECT; - - if (vmx_get_perf_capabilities() & PMU_CAP_LBR_FMT) - debugctl |= DEBUGCTLMSR_LBR_MASK; - - return debugctl; -} - static inline bool cpu_has_notify_vmexit(void) { return vmcs_config.cpu_based_2nd_exec_ctrl & diff --git a/arch/x86/kvm/vmx/pmu_intel.c b/arch/x86/kvm/vmx/pmu_intel.c index 25b70a85bef5..10b33da9bd05 100644 --- a/arch/x86/kvm/vmx/pmu_intel.c +++ b/arch/x86/kvm/vmx/pmu_intel.c @@ -617,7 +617,7 @@ static void intel_pmu_init(struct kvm_vcpu *vcpu) struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); struct lbr_desc *lbr_desc = vcpu_to_lbr_desc(vcpu); - for (i = 0; i < INTEL_PMC_MAX_GENERIC; i++) { + for (i = 0; i < KVM_INTEL_PMC_MAX_GENERIC; i++) { pmu->gp_counters[i].type = KVM_PMC_GP; pmu->gp_counters[i].vcpu = vcpu; pmu->gp_counters[i].idx = i; @@ -643,7 +643,7 @@ static void intel_pmu_reset(struct kvm_vcpu *vcpu) struct kvm_pmc *pmc = NULL; int i; - for (i = 0; i < INTEL_PMC_MAX_GENERIC; i++) { + for (i = 0; i < KVM_INTEL_PMC_MAX_GENERIC; i++) { pmc = &pmu->gp_counters[i]; pmc_stop_counter(pmc); diff --git a/arch/x86/kvm/vmx/vmenter.S b/arch/x86/kvm/vmx/vmenter.S index 8477d8bdd69c..0b5db4de4d09 100644 --- a/arch/x86/kvm/vmx/vmenter.S +++ b/arch/x86/kvm/vmx/vmenter.S @@ -1,12 +1,12 @@ /* SPDX-License-Identifier: GPL-2.0 */ #include <linux/linkage.h> #include <asm/asm.h> -#include <asm/asm-offsets.h> #include <asm/bitsperlong.h> #include <asm/kvm_vcpu_regs.h> #include <asm/nospec-branch.h> #include <asm/percpu.h> #include <asm/segment.h> +#include "kvm-asm-offsets.h" #include "run_flags.h" #define WORD_SIZE (BITS_PER_LONG / 8) diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index 9dba04b6b019..63247c57c72c 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -2021,15 +2021,17 @@ static u64 nested_vmx_truncate_sysenter_addr(struct kvm_vcpu *vcpu, return (unsigned long)data; } -static u64 vcpu_supported_debugctl(struct kvm_vcpu *vcpu) +static u64 vmx_get_supported_debugctl(struct kvm_vcpu *vcpu, bool host_initiated) { - u64 debugctl = vmx_supported_debugctl(); + u64 debugctl = 0; - if (!intel_pmu_lbr_is_enabled(vcpu)) - debugctl &= ~DEBUGCTLMSR_LBR_MASK; + if (boot_cpu_has(X86_FEATURE_BUS_LOCK_DETECT) && + (host_initiated || guest_cpuid_has(vcpu, X86_FEATURE_BUS_LOCK_DETECT))) + debugctl |= DEBUGCTLMSR_BUS_LOCK_DETECT; - if (!guest_cpuid_has(vcpu, X86_FEATURE_BUS_LOCK_DETECT)) - debugctl &= ~DEBUGCTLMSR_BUS_LOCK_DETECT; + if ((vmx_get_perf_capabilities() & PMU_CAP_LBR_FMT) && + (host_initiated || intel_pmu_lbr_is_enabled(vcpu))) + debugctl |= DEBUGCTLMSR_LBR | DEBUGCTLMSR_FREEZE_LBRS_ON_PMI; return debugctl; } @@ -2103,7 +2105,9 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) vmcs_writel(GUEST_SYSENTER_ESP, data); break; case MSR_IA32_DEBUGCTLMSR: { - u64 invalid = data & ~vcpu_supported_debugctl(vcpu); + u64 invalid; + + invalid = data & ~vmx_get_supported_debugctl(vcpu, msr_info->host_initiated); if (invalid & (DEBUGCTLMSR_BTF|DEBUGCTLMSR_LBR)) { if (report_ignored_msrs) vcpu_unimpl(vcpu, "%s: BTF|LBR in IA32_DEBUGCTLMSR 0x%llx, nop\n", @@ -8263,6 +8267,11 @@ static __init int hardware_setup(void) if (!cpu_has_virtual_nmis()) enable_vnmi = 0; +#ifdef CONFIG_X86_SGX_KVM + if (!cpu_has_vmx_encls_vmexit()) + enable_sgx = false; +#endif + /* * set_apic_access_page_addr() is used to reload apic access * page upon invalidation. No need to do anything if not diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 4bd5f8a751de..ecea83f0da49 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -1438,32 +1438,27 @@ static const u32 msrs_to_save_all[] = { MSR_ARCH_PERFMON_FIXED_CTR0 + 2, MSR_CORE_PERF_FIXED_CTR_CTRL, MSR_CORE_PERF_GLOBAL_STATUS, MSR_CORE_PERF_GLOBAL_CTRL, MSR_CORE_PERF_GLOBAL_OVF_CTRL, + MSR_IA32_PEBS_ENABLE, MSR_IA32_DS_AREA, MSR_PEBS_DATA_CFG, + + /* This part of MSRs should match KVM_INTEL_PMC_MAX_GENERIC. */ MSR_ARCH_PERFMON_PERFCTR0, MSR_ARCH_PERFMON_PERFCTR1, MSR_ARCH_PERFMON_PERFCTR0 + 2, MSR_ARCH_PERFMON_PERFCTR0 + 3, MSR_ARCH_PERFMON_PERFCTR0 + 4, MSR_ARCH_PERFMON_PERFCTR0 + 5, MSR_ARCH_PERFMON_PERFCTR0 + 6, MSR_ARCH_PERFMON_PERFCTR0 + 7, - MSR_ARCH_PERFMON_PERFCTR0 + 8, MSR_ARCH_PERFMON_PERFCTR0 + 9, - MSR_ARCH_PERFMON_PERFCTR0 + 10, MSR_ARCH_PERFMON_PERFCTR0 + 11, - MSR_ARCH_PERFMON_PERFCTR0 + 12, MSR_ARCH_PERFMON_PERFCTR0 + 13, - MSR_ARCH_PERFMON_PERFCTR0 + 14, MSR_ARCH_PERFMON_PERFCTR0 + 15, - MSR_ARCH_PERFMON_PERFCTR0 + 16, MSR_ARCH_PERFMON_PERFCTR0 + 17, MSR_ARCH_PERFMON_EVENTSEL0, MSR_ARCH_PERFMON_EVENTSEL1, MSR_ARCH_PERFMON_EVENTSEL0 + 2, MSR_ARCH_PERFMON_EVENTSEL0 + 3, MSR_ARCH_PERFMON_EVENTSEL0 + 4, MSR_ARCH_PERFMON_EVENTSEL0 + 5, MSR_ARCH_PERFMON_EVENTSEL0 + 6, MSR_ARCH_PERFMON_EVENTSEL0 + 7, - MSR_ARCH_PERFMON_EVENTSEL0 + 8, MSR_ARCH_PERFMON_EVENTSEL0 + 9, - MSR_ARCH_PERFMON_EVENTSEL0 + 10, MSR_ARCH_PERFMON_EVENTSEL0 + 11, - MSR_ARCH_PERFMON_EVENTSEL0 + 12, MSR_ARCH_PERFMON_EVENTSEL0 + 13, - MSR_ARCH_PERFMON_EVENTSEL0 + 14, MSR_ARCH_PERFMON_EVENTSEL0 + 15, - MSR_ARCH_PERFMON_EVENTSEL0 + 16, MSR_ARCH_PERFMON_EVENTSEL0 + 17, - MSR_IA32_PEBS_ENABLE, MSR_IA32_DS_AREA, MSR_PEBS_DATA_CFG, MSR_K7_EVNTSEL0, MSR_K7_EVNTSEL1, MSR_K7_EVNTSEL2, MSR_K7_EVNTSEL3, MSR_K7_PERFCTR0, MSR_K7_PERFCTR1, MSR_K7_PERFCTR2, MSR_K7_PERFCTR3, + + /* This part of MSRs should match KVM_AMD_PMC_MAX_GENERIC. */ MSR_F15H_PERF_CTL0, MSR_F15H_PERF_CTL1, MSR_F15H_PERF_CTL2, MSR_F15H_PERF_CTL3, MSR_F15H_PERF_CTL4, MSR_F15H_PERF_CTL5, MSR_F15H_PERF_CTR0, MSR_F15H_PERF_CTR1, MSR_F15H_PERF_CTR2, MSR_F15H_PERF_CTR3, MSR_F15H_PERF_CTR4, MSR_F15H_PERF_CTR5, + MSR_IA32_XFD, MSR_IA32_XFD_ERR, }; @@ -2315,11 +2310,11 @@ static void kvm_write_system_time(struct kvm_vcpu *vcpu, gpa_t system_time, /* we verify if the enable bit is set... */ if (system_time & 1) { - kvm_gfn_to_pfn_cache_init(vcpu->kvm, &vcpu->arch.pv_time, vcpu, - KVM_HOST_USES_PFN, system_time & ~1ULL, - sizeof(struct pvclock_vcpu_time_info)); + kvm_gpc_activate(vcpu->kvm, &vcpu->arch.pv_time, vcpu, + KVM_HOST_USES_PFN, system_time & ~1ULL, + sizeof(struct pvclock_vcpu_time_info)); } else { - kvm_gfn_to_pfn_cache_destroy(vcpu->kvm, &vcpu->arch.pv_time); + kvm_gpc_deactivate(vcpu->kvm, &vcpu->arch.pv_time); } return; @@ -3388,7 +3383,7 @@ static int kvm_pv_enable_async_pf_int(struct kvm_vcpu *vcpu, u64 data) static void kvmclock_reset(struct kvm_vcpu *vcpu) { - kvm_gfn_to_pfn_cache_destroy(vcpu->kvm, &vcpu->arch.pv_time); + kvm_gpc_deactivate(vcpu->kvm, &vcpu->arch.pv_time); vcpu->arch.time = 0; } @@ -6442,26 +6437,22 @@ static int kvm_add_msr_filter(struct kvm_x86_msr_filter *msr_filter, return 0; } -static int kvm_vm_ioctl_set_msr_filter(struct kvm *kvm, void __user *argp) +static int kvm_vm_ioctl_set_msr_filter(struct kvm *kvm, + struct kvm_msr_filter *filter) { - struct kvm_msr_filter __user *user_msr_filter = argp; struct kvm_x86_msr_filter *new_filter, *old_filter; - struct kvm_msr_filter filter; bool default_allow; bool empty = true; int r = 0; u32 i; - if (copy_from_user(&filter, user_msr_filter, sizeof(filter))) - return -EFAULT; - - if (filter.flags & ~KVM_MSR_FILTER_DEFAULT_DENY) + if (filter->flags & ~KVM_MSR_FILTER_DEFAULT_DENY) return -EINVAL; - for (i = 0; i < ARRAY_SIZE(filter.ranges); i++) - empty &= !filter.ranges[i].nmsrs; + for (i = 0; i < ARRAY_SIZE(filter->ranges); i++) + empty &= !filter->ranges[i].nmsrs; - default_allow = !(filter.flags & KVM_MSR_FILTER_DEFAULT_DENY); + default_allow = !(filter->flags & KVM_MSR_FILTER_DEFAULT_DENY); if (empty && !default_allow) return -EINVAL; @@ -6469,8 +6460,8 @@ static int kvm_vm_ioctl_set_msr_filter(struct kvm *kvm, void __user *argp) if (!new_filter) return -ENOMEM; - for (i = 0; i < ARRAY_SIZE(filter.ranges); i++) { - r = kvm_add_msr_filter(new_filter, &filter.ranges[i]); + for (i = 0; i < ARRAY_SIZE(filter->ranges); i++) { + r = kvm_add_msr_filter(new_filter, &filter->ranges[i]); if (r) { kvm_free_msr_filter(new_filter); return r; @@ -6493,6 +6484,62 @@ static int kvm_vm_ioctl_set_msr_filter(struct kvm *kvm, void __user *argp) return 0; } +#ifdef CONFIG_KVM_COMPAT +/* for KVM_X86_SET_MSR_FILTER */ +struct kvm_msr_filter_range_compat { + __u32 flags; + __u32 nmsrs; + __u32 base; + __u32 bitmap; +}; + +struct kvm_msr_filter_compat { + __u32 flags; + struct kvm_msr_filter_range_compat ranges[KVM_MSR_FILTER_MAX_RANGES]; +}; + +#define KVM_X86_SET_MSR_FILTER_COMPAT _IOW(KVMIO, 0xc6, struct kvm_msr_filter_compat) + +long kvm_arch_vm_compat_ioctl(struct file *filp, unsigned int ioctl, + unsigned long arg) +{ + void __user *argp = (void __user *)arg; + struct kvm *kvm = filp->private_data; + long r = -ENOTTY; + + switch (ioctl) { + case KVM_X86_SET_MSR_FILTER_COMPAT: { + struct kvm_msr_filter __user *user_msr_filter = argp; + struct kvm_msr_filter_compat filter_compat; + struct kvm_msr_filter filter; + int i; + + if (copy_from_user(&filter_compat, user_msr_filter, + sizeof(filter_compat))) + return -EFAULT; + + filter.flags = filter_compat.flags; + for (i = 0; i < ARRAY_SIZE(filter.ranges); i++) { + struct kvm_msr_filter_range_compat *cr; + + cr = &filter_compat.ranges[i]; + filter.ranges[i] = (struct kvm_msr_filter_range) { + .flags = cr->flags, + .nmsrs = cr->nmsrs, + .base = cr->base, + .bitmap = (__u8 *)(ulong)cr->bitmap, + }; + } + + r = kvm_vm_ioctl_set_msr_filter(kvm, &filter); + break; + } + } + + return r; +} +#endif + #ifdef CONFIG_HAVE_KVM_PM_NOTIFIER static int kvm_arch_suspend_notifier(struct kvm *kvm) { @@ -6915,9 +6962,16 @@ set_pit2_out: case KVM_SET_PMU_EVENT_FILTER: r = kvm_vm_ioctl_set_pmu_event_filter(kvm, argp); break; - case KVM_X86_SET_MSR_FILTER: - r = kvm_vm_ioctl_set_msr_filter(kvm, argp); + case KVM_X86_SET_MSR_FILTER: { + struct kvm_msr_filter __user *user_msr_filter = argp; + struct kvm_msr_filter filter; + + if (copy_from_user(&filter, user_msr_filter, sizeof(filter))) + return -EFAULT; + + r = kvm_vm_ioctl_set_msr_filter(kvm, &filter); break; + } default: r = -ENOTTY; } @@ -6982,14 +7036,14 @@ static void kvm_init_msr_list(void) intel_pt_validate_hw_cap(PT_CAP_num_address_ranges) * 2) continue; break; - case MSR_ARCH_PERFMON_PERFCTR0 ... MSR_ARCH_PERFMON_PERFCTR0 + 17: + case MSR_ARCH_PERFMON_PERFCTR0 ... MSR_ARCH_PERFMON_PERFCTR_MAX: if (msrs_to_save_all[i] - MSR_ARCH_PERFMON_PERFCTR0 >= - min(INTEL_PMC_MAX_GENERIC, kvm_pmu_cap.num_counters_gp)) + min(KVM_INTEL_PMC_MAX_GENERIC, kvm_pmu_cap.num_counters_gp)) continue; break; - case MSR_ARCH_PERFMON_EVENTSEL0 ... MSR_ARCH_PERFMON_EVENTSEL0 + 17: + case MSR_ARCH_PERFMON_EVENTSEL0 ... MSR_ARCH_PERFMON_EVENTSEL_MAX: if (msrs_to_save_all[i] - MSR_ARCH_PERFMON_EVENTSEL0 >= - min(INTEL_PMC_MAX_GENERIC, kvm_pmu_cap.num_counters_gp)) + min(KVM_INTEL_PMC_MAX_GENERIC, kvm_pmu_cap.num_counters_gp)) continue; break; case MSR_IA32_XFD: @@ -9985,7 +10039,20 @@ static int kvm_check_and_inject_events(struct kvm_vcpu *vcpu, kvm_x86_ops.nested_ops->has_events(vcpu)) *req_immediate_exit = true; - WARN_ON(kvm_is_exception_pending(vcpu)); + /* + * KVM must never queue a new exception while injecting an event; KVM + * is done emulating and should only propagate the to-be-injected event + * to the VMCS/VMCB. Queueing a new exception can put the vCPU into an + * infinite loop as KVM will bail from VM-Enter to inject the pending + * exception and start the cycle all over. + * + * Exempt triple faults as they have special handling and won't put the + * vCPU into an infinite loop. Triple fault can be queued when running + * VMX without unrestricted guest, as that requires KVM to emulate Real + * Mode events (see kvm_inject_realmode_interrupt()). + */ + WARN_ON_ONCE(vcpu->arch.exception.pending || + vcpu->arch.exception_vmexit.pending); return 0; out: @@ -10332,7 +10399,10 @@ void __kvm_set_or_clear_apicv_inhibit(struct kvm *kvm, kvm->arch.apicv_inhibit_reasons = new; if (new) { unsigned long gfn = gpa_to_gfn(APIC_DEFAULT_PHYS_BASE); + int idx = srcu_read_lock(&kvm->srcu); + kvm_zap_gfn_range(kvm, gfn, gfn+1); + srcu_read_unlock(&kvm->srcu, idx); } } else { kvm->arch.apicv_inhibit_reasons = new; @@ -11757,6 +11827,8 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu) vcpu->arch.regs_avail = ~0; vcpu->arch.regs_dirty = ~0; + kvm_gpc_init(&vcpu->arch.pv_time); + if (!irqchip_in_kernel(vcpu->kvm) || kvm_vcpu_is_reset_bsp(vcpu)) vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE; else diff --git a/arch/x86/kvm/xen.c b/arch/x86/kvm/xen.c index 93c628d3e3a9..2dae413bd62a 100644 --- a/arch/x86/kvm/xen.c +++ b/arch/x86/kvm/xen.c @@ -42,13 +42,13 @@ static int kvm_xen_shared_info_init(struct kvm *kvm, gfn_t gfn) int idx = srcu_read_lock(&kvm->srcu); if (gfn == GPA_INVALID) { - kvm_gfn_to_pfn_cache_destroy(kvm, gpc); + kvm_gpc_deactivate(kvm, gpc); goto out; } do { - ret = kvm_gfn_to_pfn_cache_init(kvm, gpc, NULL, KVM_HOST_USES_PFN, - gpa, PAGE_SIZE); + ret = kvm_gpc_activate(kvm, gpc, NULL, KVM_HOST_USES_PFN, gpa, + PAGE_SIZE); if (ret) goto out; @@ -554,15 +554,15 @@ int kvm_xen_vcpu_set_attr(struct kvm_vcpu *vcpu, struct kvm_xen_vcpu_attr *data) offsetof(struct compat_vcpu_info, time)); if (data->u.gpa == GPA_INVALID) { - kvm_gfn_to_pfn_cache_destroy(vcpu->kvm, &vcpu->arch.xen.vcpu_info_cache); + kvm_gpc_deactivate(vcpu->kvm, &vcpu->arch.xen.vcpu_info_cache); r = 0; break; } - r = kvm_gfn_to_pfn_cache_init(vcpu->kvm, - &vcpu->arch.xen.vcpu_info_cache, - NULL, KVM_HOST_USES_PFN, data->u.gpa, - sizeof(struct vcpu_info)); + r = kvm_gpc_activate(vcpu->kvm, + &vcpu->arch.xen.vcpu_info_cache, NULL, + KVM_HOST_USES_PFN, data->u.gpa, + sizeof(struct vcpu_info)); if (!r) kvm_make_request(KVM_REQ_CLOCK_UPDATE, vcpu); @@ -570,16 +570,16 @@ int kvm_xen_vcpu_set_attr(struct kvm_vcpu *vcpu, struct kvm_xen_vcpu_attr *data) case KVM_XEN_VCPU_ATTR_TYPE_VCPU_TIME_INFO: if (data->u.gpa == GPA_INVALID) { - kvm_gfn_to_pfn_cache_destroy(vcpu->kvm, - &vcpu->arch.xen.vcpu_time_info_cache); + kvm_gpc_deactivate(vcpu->kvm, + &vcpu->arch.xen.vcpu_time_info_cache); r = 0; break; } - r = kvm_gfn_to_pfn_cache_init(vcpu->kvm, - &vcpu->arch.xen.vcpu_time_info_cache, - NULL, KVM_HOST_USES_PFN, data->u.gpa, - sizeof(struct pvclock_vcpu_time_info)); + r = kvm_gpc_activate(vcpu->kvm, + &vcpu->arch.xen.vcpu_time_info_cache, + NULL, KVM_HOST_USES_PFN, data->u.gpa, + sizeof(struct pvclock_vcpu_time_info)); if (!r) kvm_make_request(KVM_REQ_CLOCK_UPDATE, vcpu); break; @@ -590,16 +590,15 @@ int kvm_xen_vcpu_set_attr(struct kvm_vcpu *vcpu, struct kvm_xen_vcpu_attr *data) break; } if (data->u.gpa == GPA_INVALID) { - kvm_gfn_to_pfn_cache_destroy(vcpu->kvm, - &vcpu->arch.xen.runstate_cache); + kvm_gpc_deactivate(vcpu->kvm, + &vcpu->arch.xen.runstate_cache); r = 0; break; } - r = kvm_gfn_to_pfn_cache_init(vcpu->kvm, - &vcpu->arch.xen.runstate_cache, - NULL, KVM_HOST_USES_PFN, data->u.gpa, - sizeof(struct vcpu_runstate_info)); + r = kvm_gpc_activate(vcpu->kvm, &vcpu->arch.xen.runstate_cache, + NULL, KVM_HOST_USES_PFN, data->u.gpa, + sizeof(struct vcpu_runstate_info)); break; case KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_CURRENT: @@ -1667,18 +1666,18 @@ static int kvm_xen_eventfd_assign(struct kvm *kvm, case EVTCHNSTAT_ipi: /* IPI must map back to the same port# */ if (data->u.evtchn.deliver.port.port != data->u.evtchn.send_port) - goto out; /* -EINVAL */ + goto out_noeventfd; /* -EINVAL */ break; case EVTCHNSTAT_interdomain: if (data->u.evtchn.deliver.port.port) { if (data->u.evtchn.deliver.port.port >= max_evtchn_port(kvm)) - goto out; /* -EINVAL */ + goto out_noeventfd; /* -EINVAL */ } else { eventfd = eventfd_ctx_fdget(data->u.evtchn.deliver.eventfd.fd); if (IS_ERR(eventfd)) { ret = PTR_ERR(eventfd); - goto out; + goto out_noeventfd; } } break; @@ -1718,6 +1717,7 @@ static int kvm_xen_eventfd_assign(struct kvm *kvm, out: if (eventfd) eventfd_ctx_put(eventfd); +out_noeventfd: kfree(evtchnfd); return ret; } @@ -1816,7 +1816,12 @@ void kvm_xen_init_vcpu(struct kvm_vcpu *vcpu) { vcpu->arch.xen.vcpu_id = vcpu->vcpu_idx; vcpu->arch.xen.poll_evtchn = 0; + timer_setup(&vcpu->arch.xen.poll_timer, cancel_evtchn_poll, 0); + + kvm_gpc_init(&vcpu->arch.xen.runstate_cache); + kvm_gpc_init(&vcpu->arch.xen.vcpu_info_cache); + kvm_gpc_init(&vcpu->arch.xen.vcpu_time_info_cache); } void kvm_xen_destroy_vcpu(struct kvm_vcpu *vcpu) @@ -1824,18 +1829,17 @@ void kvm_xen_destroy_vcpu(struct kvm_vcpu *vcpu) if (kvm_xen_timer_enabled(vcpu)) kvm_xen_stop_timer(vcpu); - kvm_gfn_to_pfn_cache_destroy(vcpu->kvm, - &vcpu->arch.xen.runstate_cache); - kvm_gfn_to_pfn_cache_destroy(vcpu->kvm, - &vcpu->arch.xen.vcpu_info_cache); - kvm_gfn_to_pfn_cache_destroy(vcpu->kvm, - &vcpu->arch.xen.vcpu_time_info_cache); + kvm_gpc_deactivate(vcpu->kvm, &vcpu->arch.xen.runstate_cache); + kvm_gpc_deactivate(vcpu->kvm, &vcpu->arch.xen.vcpu_info_cache); + kvm_gpc_deactivate(vcpu->kvm, &vcpu->arch.xen.vcpu_time_info_cache); + del_timer_sync(&vcpu->arch.xen.poll_timer); } void kvm_xen_init_vm(struct kvm *kvm) { idr_init(&kvm->arch.xen.evtchn_ports); + kvm_gpc_init(&kvm->arch.xen.shinfo_cache); } void kvm_xen_destroy_vm(struct kvm *kvm) @@ -1843,7 +1847,7 @@ void kvm_xen_destroy_vm(struct kvm *kvm) struct evtchnfd *evtchnfd; int i; - kvm_gfn_to_pfn_cache_destroy(kvm, &kvm->arch.xen.shinfo_cache); + kvm_gpc_deactivate(kvm, &kvm->arch.xen.shinfo_cache); idr_for_each_entry(&kvm->arch.xen.evtchn_ports, evtchnfd, i) { if (!evtchnfd->deliver.port.port) diff --git a/arch/x86/mm/pat/set_memory.c b/arch/x86/mm/pat/set_memory.c index 97342c42dda8..2e5a045731de 100644 --- a/arch/x86/mm/pat/set_memory.c +++ b/arch/x86/mm/pat/set_memory.c @@ -587,6 +587,10 @@ static inline pgprot_t verify_rwx(pgprot_t old, pgprot_t new, unsigned long star { unsigned long end; + /* Kernel text is rw at boot up */ + if (system_state == SYSTEM_BOOTING) + return new; + /* * 32-bit has some unfixable W+X issues, like EFI code * and writeable data being in the same page. Disable diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c index 99620428ad78..00127abd89ee 100644 --- a/arch/x86/net/bpf_jit_comp.c +++ b/arch/x86/net/bpf_jit_comp.c @@ -11,6 +11,7 @@ #include <linux/bpf.h> #include <linux/memory.h> #include <linux/sort.h> +#include <linux/init.h> #include <asm/extable.h> #include <asm/set_memory.h> #include <asm/nospec-branch.h> @@ -388,6 +389,18 @@ out: return ret; } +int __init bpf_arch_init_dispatcher_early(void *ip) +{ + const u8 *nop_insn = x86_nops[5]; + + if (is_endbr(*(u32 *)ip)) + ip += ENDBR_INSN_SIZE; + + if (memcmp(ip, nop_insn, X86_PATCH_SIZE)) + text_poke_early(ip, nop_insn, X86_PATCH_SIZE); + return 0; +} + int bpf_arch_text_poke(void *ip, enum bpf_text_poke_type t, void *old_addr, void *new_addr) { diff --git a/arch/x86/purgatory/Makefile b/arch/x86/purgatory/Makefile index 58a200dc762d..17f09dc26381 100644 --- a/arch/x86/purgatory/Makefile +++ b/arch/x86/purgatory/Makefile @@ -26,6 +26,7 @@ GCOV_PROFILE := n KASAN_SANITIZE := n UBSAN_SANITIZE := n KCSAN_SANITIZE := n +KMSAN_SANITIZE := n KCOV_INSTRUMENT := n # These are adjustments to the compiler flags used for objects that diff --git a/arch/x86/xen/pmu.c b/arch/x86/xen/pmu.c index 68aff1382872..246d67dab510 100644 --- a/arch/x86/xen/pmu.c +++ b/arch/x86/xen/pmu.c @@ -302,7 +302,7 @@ static bool xen_amd_pmu_emulate(unsigned int msr, u64 *val, bool is_read) static bool pmu_msr_chk_emulated(unsigned int msr, uint64_t *val, bool is_read, bool *emul) { - int type, index; + int type, index = 0; if (is_amd_pmu_msr(msr)) *emul = xen_amd_pmu_emulate(msr, val, is_read); diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c index cfa99e8f054b..4f4309500559 100644 --- a/arch/x86/xen/setup.c +++ b/arch/x86/xen/setup.c @@ -910,17 +910,9 @@ static int register_callback(unsigned type, const void *func) void xen_enable_sysenter(void) { - int ret; - unsigned sysenter_feature; - - sysenter_feature = X86_FEATURE_SYSENTER32; - - if (!boot_cpu_has(sysenter_feature)) - return; - - ret = register_callback(CALLBACKTYPE_sysenter, xen_entry_SYSENTER_compat); - if(ret != 0) - setup_clear_cpu_cap(sysenter_feature); + if (cpu_feature_enabled(X86_FEATURE_SYSENTER32) && + register_callback(CALLBACKTYPE_sysenter, xen_entry_SYSENTER_compat)) + setup_clear_cpu_cap(X86_FEATURE_SYSENTER32); } void xen_enable_syscall(void) @@ -934,12 +926,9 @@ void xen_enable_syscall(void) mechanism for syscalls. */ } - if (boot_cpu_has(X86_FEATURE_SYSCALL32)) { - ret = register_callback(CALLBACKTYPE_syscall32, - xen_entry_SYSCALL_compat); - if (ret != 0) - setup_clear_cpu_cap(X86_FEATURE_SYSCALL32); - } + if (cpu_feature_enabled(X86_FEATURE_SYSCALL32) && + register_callback(CALLBACKTYPE_syscall32, xen_entry_SYSCALL_compat)) + setup_clear_cpu_cap(X86_FEATURE_SYSCALL32); } static void __init xen_pvmmu_arch_setup(void) |