diff options
Diffstat (limited to 'arch')
184 files changed, 3505 insertions, 1912 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/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/kvm/arm.c b/arch/arm64/kvm/arm.c index 94d33e296e10..7b107fa540fa 100644 --- a/arch/arm64/kvm/arm.c +++ b/arch/arm64/kvm/arm.c @@ -2130,6 +2130,11 @@ struct kvm_vcpu *kvm_mpidr_to_vcpu(struct kvm *kvm, unsigned long mpidr) return NULL; } +bool kvm_arch_irqchip_in_kernel(struct kvm *kvm) +{ + return irqchip_in_kernel(kvm); +} + bool kvm_arch_has_irq_bypass(void) { return true; 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/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/irq.h b/arch/arm64/kvm/irq.h deleted file mode 100644 index 0d257de42c10..000000000000 --- a/arch/arm64/kvm/irq.h +++ /dev/null @@ -1,16 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * irq.h: in kernel interrupt controller related definitions - * Copyright (c) 2016 Red Hat, Inc. - * - * This header is included by irqchip.c. However, on ARM, interrupt - * controller declarations are located in include/kvm/arm_vgic.h since - * they are mostly shared between arm and arm64. - */ - -#ifndef __IRQ_H -#define __IRQ_H - -#include <kvm/arm_vgic.h> - -#endif diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c index 60ee3d9f01f8..f154d4a7fae0 100644 --- a/arch/arm64/kvm/mmu.c +++ b/arch/arm64/kvm/mmu.c @@ -1239,7 +1239,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, */ smp_rmb(); - pfn = __gfn_to_pfn_memslot(memslot, gfn, false, NULL, + pfn = __gfn_to_pfn_memslot(memslot, gfn, false, false, NULL, write_fault, &writable, NULL); if (pfn == KVM_PFN_ERR_HWPOISON) { kvm_send_hwpoison_signal(hva, vma_shift); 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/kvm/book3s_64_mmu_hv.c b/arch/powerpc/kvm/book3s_64_mmu_hv.c index e9744b41a226..4939f57b6f6a 100644 --- a/arch/powerpc/kvm/book3s_64_mmu_hv.c +++ b/arch/powerpc/kvm/book3s_64_mmu_hv.c @@ -598,7 +598,7 @@ int kvmppc_book3s_hv_page_fault(struct kvm_vcpu *vcpu, write_ok = true; } else { /* Call KVM generic code to do the slow-path check */ - pfn = __gfn_to_pfn_memslot(memslot, gfn, false, NULL, + pfn = __gfn_to_pfn_memslot(memslot, gfn, false, false, NULL, writing, &write_ok, NULL); if (is_error_noslot_pfn(pfn)) return -EFAULT; diff --git a/arch/powerpc/kvm/book3s_64_mmu_radix.c b/arch/powerpc/kvm/book3s_64_mmu_radix.c index 5d5e12f3bf86..9d3743ca16d5 100644 --- a/arch/powerpc/kvm/book3s_64_mmu_radix.c +++ b/arch/powerpc/kvm/book3s_64_mmu_radix.c @@ -846,7 +846,7 @@ int kvmppc_book3s_instantiate_page(struct kvm_vcpu *vcpu, unsigned long pfn; /* Call KVM generic code to do the slow-path check */ - pfn = __gfn_to_pfn_memslot(memslot, gfn, false, NULL, + pfn = __gfn_to_pfn_memslot(memslot, gfn, false, false, NULL, writing, upgrade_p, NULL); if (is_error_noslot_pfn(pfn)) return -EFAULT; diff --git a/arch/powerpc/kvm/irq.h b/arch/powerpc/kvm/irq.h deleted file mode 100644 index e6463f866abc..000000000000 --- a/arch/powerpc/kvm/irq.h +++ /dev/null @@ -1,22 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef __IRQ_H -#define __IRQ_H - -#include <linux/kvm_host.h> - -static inline int irqchip_in_kernel(struct kvm *kvm) -{ - int ret = 0; - -#ifdef CONFIG_KVM_MPIC - ret = ret || (kvm->arch.mpic != NULL); -#endif -#ifdef CONFIG_KVM_XICS - ret = ret || (kvm->arch.xics != NULL); - ret = ret || (kvm->arch.xive != NULL); -#endif - smp_rmb(); - return ret; -} - -#endif diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c index b850b0efa201..04494a4fb37a 100644 --- a/arch/powerpc/kvm/powerpc.c +++ b/arch/powerpc/kvm/powerpc.c @@ -36,7 +36,6 @@ #include <asm/setup.h> #include "timing.h" -#include "irq.h" #include "../mm/mmu_decl.h" #define CREATE_TRACE_POINTS @@ -2165,10 +2164,25 @@ static int kvm_vm_ioctl_get_pvinfo(struct kvm_ppc_pvinfo *pvinfo) return 0; } +bool kvm_arch_irqchip_in_kernel(struct kvm *kvm) +{ + int ret = 0; + +#ifdef CONFIG_KVM_MPIC + ret = ret || (kvm->arch.mpic != NULL); +#endif +#ifdef CONFIG_KVM_XICS + ret = ret || (kvm->arch.xics != NULL); + ret = ret || (kvm->arch.xive != NULL); +#endif + smp_rmb(); + return ret; +} + int kvm_vm_ioctl_irq_line(struct kvm *kvm, struct kvm_irq_level *irq_event, bool line_status) { - if (!irqchip_in_kernel(kvm)) + if (!kvm_arch_irqchip_in_kernel(kvm)) return -ENXIO; irq_event->status = kvm_set_irq(kvm, KVM_USERSPACE_IRQ_SOURCE_ID, 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/Kconfig b/arch/riscv/Kconfig index 6b48a3ae9843..fa78595a6089 100644 --- a/arch/riscv/Kconfig +++ b/arch/riscv/Kconfig @@ -411,14 +411,16 @@ config RISCV_ISA_SVPBMT If you don't know what to do here, say Y. -config CC_HAS_ZICBOM +config TOOLCHAIN_HAS_ZICBOM bool - default y if 64BIT && $(cc-option,-mabi=lp64 -march=rv64ima_zicbom) - default y if 32BIT && $(cc-option,-mabi=ilp32 -march=rv32ima_zicbom) + default y + depends on !64BIT || $(cc-option,-mabi=lp64 -march=rv64ima_zicbom) + depends on !32BIT || $(cc-option,-mabi=ilp32 -march=rv32ima_zicbom) + depends on LLD_VERSION >= 150000 || LD_VERSION >= 23800 config RISCV_ISA_ZICBOM bool "Zicbom extension support for non-coherent DMA operation" - depends on CC_HAS_ZICBOM + depends on TOOLCHAIN_HAS_ZICBOM depends on !XIP_KERNEL && MMU select RISCV_DMA_NONCOHERENT select RISCV_ALTERNATIVE @@ -433,6 +435,13 @@ config RISCV_ISA_ZICBOM If you don't know what to do here, say Y. +config TOOLCHAIN_HAS_ZIHINTPAUSE + bool + default y + depends on !64BIT || $(cc-option,-mabi=lp64 -march=rv64ima_zihintpause) + depends on !32BIT || $(cc-option,-mabi=ilp32 -march=rv32ima_zihintpause) + depends on LLD_VERSION >= 150000 || LD_VERSION >= 23600 + config FPU bool "FPU support" default y diff --git a/arch/riscv/Makefile b/arch/riscv/Makefile index 1c8ec656e916..0d13b597cb55 100644 --- a/arch/riscv/Makefile +++ b/arch/riscv/Makefile @@ -59,12 +59,10 @@ toolchain-need-zicsr-zifencei := $(call cc-option-yn, -march=$(riscv-march-y)_zi riscv-march-$(toolchain-need-zicsr-zifencei) := $(riscv-march-y)_zicsr_zifencei # Check if the toolchain supports Zicbom extension -toolchain-supports-zicbom := $(call cc-option-yn, -march=$(riscv-march-y)_zicbom) -riscv-march-$(toolchain-supports-zicbom) := $(riscv-march-y)_zicbom +riscv-march-$(CONFIG_TOOLCHAIN_HAS_ZICBOM) := $(riscv-march-y)_zicbom # Check if the toolchain supports Zihintpause extension -toolchain-supports-zihintpause := $(call cc-option-yn, -march=$(riscv-march-y)_zihintpause) -riscv-march-$(toolchain-supports-zihintpause) := $(riscv-march-y)_zihintpause +riscv-march-$(CONFIG_TOOLCHAIN_HAS_ZIHINTPAUSE) := $(riscv-march-y)_zihintpause KBUILD_CFLAGS += -march=$(subst fd,,$(riscv-march-y)) KBUILD_AFLAGS += -march=$(riscv-march-y) diff --git a/arch/riscv/include/asm/jump_label.h b/arch/riscv/include/asm/jump_label.h index 38af2ec7b9bf..6d58bbb5da46 100644 --- a/arch/riscv/include/asm/jump_label.h +++ b/arch/riscv/include/asm/jump_label.h @@ -14,8 +14,8 @@ #define JUMP_LABEL_NOP_SIZE 4 -static __always_inline bool arch_static_branch(struct static_key *key, - bool branch) +static __always_inline bool arch_static_branch(struct static_key * const key, + const bool branch) { asm_volatile_goto( " .option push \n\t" @@ -35,8 +35,8 @@ label: return true; } -static __always_inline bool arch_static_branch_jump(struct static_key *key, - bool branch) +static __always_inline bool arch_static_branch_jump(struct static_key * const key, + const bool branch) { asm_volatile_goto( " .option push \n\t" diff --git a/arch/riscv/include/asm/vdso/processor.h b/arch/riscv/include/asm/vdso/processor.h index 1e4f8b4aef79..fa70cfe507aa 100644 --- a/arch/riscv/include/asm/vdso/processor.h +++ b/arch/riscv/include/asm/vdso/processor.h @@ -21,7 +21,7 @@ static inline void cpu_relax(void) * Reduce instruction retirement. * This assumes the PC changes. */ -#ifdef __riscv_zihintpause +#ifdef CONFIG_TOOLCHAIN_HAS_ZIHINTPAUSE __asm__ __volatile__ ("pause"); #else /* Encoding of the pause instruction */ diff --git a/arch/riscv/kernel/cpu.c b/arch/riscv/kernel/cpu.c index fa427bdcf773..852ecccd8920 100644 --- a/arch/riscv/kernel/cpu.c +++ b/arch/riscv/kernel/cpu.c @@ -213,6 +213,9 @@ static void print_mmu(struct seq_file *f) static void *c_start(struct seq_file *m, loff_t *pos) { + if (*pos == nr_cpu_ids) + return NULL; + *pos = cpumask_next(*pos - 1, cpu_online_mask); if ((*pos) < nr_cpu_ids) return (void *)(uintptr_t)(1 + *pos); diff --git a/arch/riscv/mm/kasan_init.c b/arch/riscv/mm/kasan_init.c index a22e418dbd82..e1226709490f 100644 --- a/arch/riscv/mm/kasan_init.c +++ b/arch/riscv/mm/kasan_init.c @@ -113,6 +113,8 @@ static void __init kasan_populate_pud(pgd_t *pgd, base_pud = pt_ops.get_pud_virt(pfn_to_phys(_pgd_pfn(*pgd))); } else if (pgd_none(*pgd)) { base_pud = memblock_alloc(PTRS_PER_PUD * sizeof(pud_t), PAGE_SIZE); + memcpy(base_pud, (void *)kasan_early_shadow_pud, + sizeof(pud_t) * PTRS_PER_PUD); } else { base_pud = (pud_t *)pgd_page_vaddr(*pgd); if (base_pud == lm_alias(kasan_early_shadow_pud)) { @@ -173,8 +175,11 @@ static void __init kasan_populate_p4d(pgd_t *pgd, base_p4d = pt_ops.get_p4d_virt(pfn_to_phys(_pgd_pfn(*pgd))); } else { base_p4d = (p4d_t *)pgd_page_vaddr(*pgd); - if (base_p4d == lm_alias(kasan_early_shadow_p4d)) + if (base_p4d == lm_alias(kasan_early_shadow_p4d)) { base_p4d = memblock_alloc(PTRS_PER_PUD * sizeof(p4d_t), PAGE_SIZE); + memcpy(base_p4d, (void *)kasan_early_shadow_p4d, + sizeof(p4d_t) * PTRS_PER_P4D); + } } p4dp = base_p4d + p4d_index(vaddr); 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/irq.h b/arch/s390/kvm/irq.h deleted file mode 100644 index 484608c71dd0..000000000000 --- a/arch/s390/kvm/irq.h +++ /dev/null @@ -1,19 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* - * s390 irqchip routines - * - * Copyright IBM Corp. 2014 - * - * Author(s): Cornelia Huck <cornelia.huck@de.ibm.com> - */ -#ifndef __KVM_IRQ_H -#define __KVM_IRQ_H - -#include <linux/kvm_host.h> - -static inline int irqchip_in_kernel(struct kvm *kvm) -{ - return 1; -} - -#endif diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index 8a0c884bf737..e4890e04b210 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -1218,6 +1218,8 @@ 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; @@ -1227,7 +1229,7 @@ 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); @@ -1258,7 +1260,7 @@ 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; } @@ -1270,6 +1272,16 @@ 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); @@ -1284,6 +1296,9 @@ 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; } @@ -4425,13 +4440,6 @@ 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)) @@ -5608,6 +5616,11 @@ vm_fault_t kvm_arch_vcpu_fault(struct kvm_vcpu *vcpu, struct vm_fault *vmf) return VM_FAULT_SIGBUS; } +bool kvm_arch_irqchip_in_kernel(struct kvm *kvm) +{ + return true; +} + /* Section: memory related */ int kvm_arch_prepare_memory_region(struct kvm *kvm, const struct kvm_memory_slot *old, diff --git a/arch/s390/kvm/kvm-s390.h b/arch/s390/kvm/kvm-s390.h index 826754937ae4..d48588c207d8 100644 --- a/arch/s390/kvm/kvm-s390.h +++ b/arch/s390/kvm/kvm-s390.h @@ -367,7 +367,6 @@ 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/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 8259d725054d..4dbde69c423b 100644 --- a/arch/x86/events/intel/lbr.c +++ b/arch/x86/events/intel/lbr.c @@ -1603,10 +1603,8 @@ clear_arch_lbr: * x86_perf_get_lbr - get the LBR records information * * @lbr: the caller's memory to store the LBR records information - * - * Returns: 0 indicates the LBR info has been successfully obtained */ -int x86_perf_get_lbr(struct x86_pmu_lbr *lbr) +void x86_perf_get_lbr(struct x86_pmu_lbr *lbr) { int lbr_fmt = x86_pmu.intel_cap.lbr_format; @@ -1614,8 +1612,6 @@ int x86_perf_get_lbr(struct x86_pmu_lbr *lbr) lbr->from = x86_pmu.lbr_from; lbr->to = x86_pmu.lbr_to; lbr->info = (lbr_fmt == LBR_FORMAT_INFO) ? x86_pmu.lbr_info : 0; - - return 0; } EXPORT_SYMBOL_GPL(x86_perf_get_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/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index b71f4f2ecdd5..1419c4e04d45 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -308,6 +308,9 @@ /* Intel-defined CPU features, CPUID level 0x00000007:1 (EAX), word 12 */ #define X86_FEATURE_AVX_VNNI (12*32+ 4) /* AVX VNNI instructions */ #define X86_FEATURE_AVX512_BF16 (12*32+ 5) /* AVX512 BFLOAT16 instructions */ +#define X86_FEATURE_CMPCCXADD (12*32+ 7) /* "" CMPccXADD instructions */ +#define X86_FEATURE_AMX_FP16 (12*32+21) /* "" AMX fp16 Support */ +#define X86_FEATURE_AVX_IFMA (12*32+23) /* "" Support for VPMADD52[H,L]UQ */ /* AMD-defined CPU features, CPUID level 0x80000008 (EBX), word 13 */ #define X86_FEATURE_CLZERO (13*32+ 0) /* CLZERO instruction */ diff --git a/arch/x86/include/asm/hyperv-tlfs.h b/arch/x86/include/asm/hyperv-tlfs.h index 3089ec352743..e3efaf6e6b62 100644 --- a/arch/x86/include/asm/hyperv-tlfs.h +++ b/arch/x86/include/asm/hyperv-tlfs.h @@ -61,6 +61,8 @@ #define HV_FEATURE_GUEST_CRASH_MSR_AVAILABLE BIT(10) /* Support for debug MSRs available */ #define HV_FEATURE_DEBUG_MSRS_AVAILABLE BIT(11) +/* Support for extended gva ranges for flush hypercalls available */ +#define HV_FEATURE_EXT_GVA_RANGES_FLUSH BIT(14) /* * Support for returning hypercall output block via XMM * registers is available @@ -598,6 +600,41 @@ struct hv_enlightened_vmcs { #define HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL 0xFFFF +/* + * Note, Hyper-V isn't actually stealing bit 28 from Intel, just abusing it by + * pairing it with architecturally impossible exit reasons. Bit 28 is set only + * on SMI exits to a SMI transfer monitor (STM) and if and only if a MTF VM-Exit + * is pending. I.e. it will never be set by hardware for non-SMI exits (there + * are only three), nor will it ever be set unless the VMM is an STM. + */ +#define HV_VMX_SYNTHETIC_EXIT_REASON_TRAP_AFTER_FLUSH 0x10000031 + +/* + * Hyper-V uses the software reserved 32 bytes in VMCB control area to expose + * SVM enlightenments to guests. + */ +struct hv_vmcb_enlightenments { + struct __packed hv_enlightenments_control { + u32 nested_flush_hypercall:1; + u32 msr_bitmap:1; + u32 enlightened_npt_tlb: 1; + u32 reserved:29; + } __packed hv_enlightenments_control; + u32 hv_vp_id; + u64 hv_vm_id; + u64 partition_assist_page; + u64 reserved; +} __packed; + +/* + * Hyper-V uses the software reserved clean bit in VMCB. + */ +#define HV_VMCB_NESTED_ENLIGHTENMENTS 31 + +/* Synthetic VM-Exit */ +#define HV_SVM_EXITCODE_ENL 0xf0000000 +#define HV_SVM_ENL_EXITCODE_TRAP_AFTER_FLUSH (1) + struct hv_partition_assist_pg { u32 tlb_lock_count; }; 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/kvm-x86-ops.h b/arch/x86/include/asm/kvm-x86-ops.h index 82ba4a564e58..abccd51dcfca 100644 --- a/arch/x86/include/asm/kvm-x86-ops.h +++ b/arch/x86/include/asm/kvm-x86-ops.h @@ -110,10 +110,12 @@ KVM_X86_OP_OPTIONAL_RET0(dy_apicv_has_pending_interrupt) KVM_X86_OP_OPTIONAL(set_hv_timer) KVM_X86_OP_OPTIONAL(cancel_hv_timer) KVM_X86_OP(setup_mce) +#ifdef CONFIG_KVM_SMM KVM_X86_OP(smi_allowed) KVM_X86_OP(enter_smm) KVM_X86_OP(leave_smm) KVM_X86_OP(enable_smi_window) +#endif KVM_X86_OP_OPTIONAL(mem_enc_ioctl) KVM_X86_OP_OPTIONAL(mem_enc_register_region) KVM_X86_OP_OPTIONAL(mem_enc_unregister_region) @@ -123,7 +125,7 @@ KVM_X86_OP_OPTIONAL(guest_memory_reclaimed) KVM_X86_OP(get_msr_feature) KVM_X86_OP(can_emulate_instruction) KVM_X86_OP(apic_init_signal_blocked) -KVM_X86_OP_OPTIONAL(enable_direct_tlbflush) +KVM_X86_OP_OPTIONAL(enable_l2_tlb_flush) KVM_X86_OP_OPTIONAL(migrate_timers) KVM_X86_OP(msr_filter_changed) KVM_X86_OP(complete_emulated_msr) diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 7551b6f9c31c..d1013c4f673c 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -25,6 +25,7 @@ #include <linux/clocksource.h> #include <linux/irqbypass.h> #include <linux/hyperv.h> +#include <linux/kfifo.h> #include <asm/apic.h> #include <asm/pvclock-abi.h> @@ -81,7 +82,9 @@ #define KVM_REQ_NMI KVM_ARCH_REQ(9) #define KVM_REQ_PMU KVM_ARCH_REQ(10) #define KVM_REQ_PMI KVM_ARCH_REQ(11) +#ifdef CONFIG_KVM_SMM #define KVM_REQ_SMI KVM_ARCH_REQ(12) +#endif #define KVM_REQ_MASTERCLOCK_UPDATE KVM_ARCH_REQ(13) #define KVM_REQ_MCLOCK_INPROGRESS \ KVM_ARCH_REQ_FLAGS(14, KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP) @@ -108,6 +111,8 @@ KVM_ARCH_REQ_FLAGS(30, KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP) #define KVM_REQ_MMU_FREE_OBSOLETE_ROOTS \ KVM_ARCH_REQ_FLAGS(31, KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP) +#define KVM_REQ_HV_TLB_FLUSH \ + KVM_ARCH_REQ_FLAGS(32, KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP) #define CR0_RESERVED_BITS \ (~(unsigned long)(X86_CR0_PE | X86_CR0_MP | X86_CR0_EM | X86_CR0_TS \ @@ -204,6 +209,7 @@ typedef enum exit_fastpath_completion fastpath_t; struct x86_emulate_ctxt; struct x86_exception; +union kvm_smram; enum x86_intercept; enum x86_intercept_stage; @@ -253,16 +259,16 @@ enum x86_intercept_stage; #define PFERR_GUEST_PAGE_BIT 33 #define PFERR_IMPLICIT_ACCESS_BIT 48 -#define PFERR_PRESENT_MASK (1U << PFERR_PRESENT_BIT) -#define PFERR_WRITE_MASK (1U << PFERR_WRITE_BIT) -#define PFERR_USER_MASK (1U << PFERR_USER_BIT) -#define PFERR_RSVD_MASK (1U << PFERR_RSVD_BIT) -#define PFERR_FETCH_MASK (1U << PFERR_FETCH_BIT) -#define PFERR_PK_MASK (1U << PFERR_PK_BIT) -#define PFERR_SGX_MASK (1U << PFERR_SGX_BIT) -#define PFERR_GUEST_FINAL_MASK (1ULL << PFERR_GUEST_FINAL_BIT) -#define PFERR_GUEST_PAGE_MASK (1ULL << PFERR_GUEST_PAGE_BIT) -#define PFERR_IMPLICIT_ACCESS (1ULL << PFERR_IMPLICIT_ACCESS_BIT) +#define PFERR_PRESENT_MASK BIT(PFERR_PRESENT_BIT) +#define PFERR_WRITE_MASK BIT(PFERR_WRITE_BIT) +#define PFERR_USER_MASK BIT(PFERR_USER_BIT) +#define PFERR_RSVD_MASK BIT(PFERR_RSVD_BIT) +#define PFERR_FETCH_MASK BIT(PFERR_FETCH_BIT) +#define PFERR_PK_MASK BIT(PFERR_PK_BIT) +#define PFERR_SGX_MASK BIT(PFERR_SGX_BIT) +#define PFERR_GUEST_FINAL_MASK BIT_ULL(PFERR_GUEST_FINAL_BIT) +#define PFERR_GUEST_PAGE_MASK BIT_ULL(PFERR_GUEST_PAGE_BIT) +#define PFERR_IMPLICIT_ACCESS BIT_ULL(PFERR_IMPLICIT_ACCESS_BIT) #define PFERR_NESTED_GUEST_PAGE (PFERR_GUEST_PAGE_MASK | \ PFERR_WRITE_MASK | \ @@ -488,20 +494,27 @@ enum pmc_type { struct kvm_pmc { enum pmc_type type; u8 idx; + bool is_paused; + bool intr; u64 counter; + u64 prev_counter; u64 eventsel; struct perf_event *perf_event; struct kvm_vcpu *vcpu; /* + * only for creating or reusing perf_event, * eventsel value for general purpose counters, * ctrl value for fixed counters. */ u64 current_config; - bool is_paused; - 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; @@ -516,10 +529,19 @@ 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); + + /* + * Overlay the bitmap with a 64-bit atomic so that all bits can be + * set in a single access, e.g. to reprogram all counters when the PMU + * filter changes. + */ + union { + DECLARE_BITMAP(reprogram_pmi, X86_PMC_IDX_MAX); + atomic64_t __reprogram_pmi; + }; DECLARE_BITMAP(all_valid_pmc_idx, X86_PMC_IDX_MAX); DECLARE_BITMAP(pmc_in_use, X86_PMC_IDX_MAX); @@ -597,6 +619,29 @@ struct kvm_vcpu_hv_synic { bool dont_zero_synic_pages; }; +/* The maximum number of entries on the TLB flush fifo. */ +#define KVM_HV_TLB_FLUSH_FIFO_SIZE (16) +/* + * Note: the following 'magic' entry is made up by KVM to avoid putting + * anything besides GVA on the TLB flush fifo. It is theoretically possible + * to observe a request to flush 4095 PFNs starting from 0xfffffffffffff000 + * which will look identical. KVM's action to 'flush everything' instead of + * flushing these particular addresses is, however, fully legitimate as + * flushing more than requested is always OK. + */ +#define KVM_HV_TLB_FLUSHALL_ENTRY ((u64)-1) + +enum hv_tlb_flush_fifos { + HV_L1_TLB_FLUSH_FIFO, + HV_L2_TLB_FLUSH_FIFO, + HV_NR_TLB_FLUSH_FIFOS, +}; + +struct kvm_vcpu_hv_tlb_flush_fifo { + spinlock_t write_lock; + DECLARE_KFIFO(entries, u64, KVM_HV_TLB_FLUSH_FIFO_SIZE); +}; + /* Hyper-V per vcpu emulation context */ struct kvm_vcpu_hv { struct kvm_vcpu *vcpu; @@ -618,6 +663,19 @@ struct kvm_vcpu_hv { u32 nested_eax; /* HYPERV_CPUID_NESTED_FEATURES.EAX */ u32 nested_ebx; /* HYPERV_CPUID_NESTED_FEATURES.EBX */ } cpuid_cache; + + struct kvm_vcpu_hv_tlb_flush_fifo tlb_flush_fifo[HV_NR_TLB_FLUSH_FIFOS]; + + /* Preallocated buffer for handling hypercalls passing sparse vCPU set */ + u64 sparse_banks[HV_MAX_SPARSE_VCPU_BANKS]; + + struct hv_vp_assist_page vp_assist_page; + + struct { + u64 pa_page_gpa; + u64 vm_id; + u32 vp_id; + } nested; }; /* Xen HVM per vcpu emulation context */ @@ -1151,7 +1209,18 @@ struct kvm_arch { struct hlist_head mmu_page_hash[KVM_NUM_MMU_PAGES]; struct list_head active_mmu_pages; struct list_head zapped_obsolete_pages; - struct list_head lpage_disallowed_mmu_pages; + /* + * A list of kvm_mmu_page structs that, if zapped, could possibly be + * replaced by an NX huge page. A shadow page is on this list if its + * existence disallows an NX huge page (nx_huge_page_disallowed is set) + * and there are no other conditions that prevent a huge page, e.g. + * the backing host page is huge, dirtly logging is not enabled for its + * memslot, etc... Note, zapping shadow pages on this list doesn't + * guarantee an NX huge page will be created in its stead, e.g. if the + * guest attempts to execute from the region then KVM obviously can't + * create an NX huge page (without hanging the guest). + */ + struct list_head possible_nx_huge_pages; struct kvm_page_track_notifier_node mmu_sp_tracker; struct kvm_page_track_notifier_head track_notifier_head; /* @@ -1267,7 +1336,7 @@ struct kvm_arch { bool sgx_provisioning_allowed; struct kvm_pmu_event_filter __rcu *pmu_event_filter; - struct task_struct *nx_lpage_recovery_thread; + struct task_struct *nx_huge_page_recovery_thread; #ifdef CONFIG_X86_64 /* @@ -1279,6 +1348,9 @@ struct kvm_arch { */ bool tdp_mmu_enabled; + /* The number of TDP MMU pages across all roots. */ + atomic64_t tdp_mmu_pages; + /* * List of kvm_mmu_page structs being used as roots. * All kvm_mmu_page structs in the list should have @@ -1300,20 +1372,12 @@ struct kvm_arch { struct list_head tdp_mmu_roots; /* - * List of kvm_mmu_page structs not being used as roots. - * All kvm_mmu_page structs in the list should have - * tdp_mmu_page set and a tdp_mmu_root_count of 0. - */ - struct list_head tdp_mmu_pages; - - /* * Protects accesses to the following fields when the MMU lock * is held in read mode: * - tdp_mmu_roots (above) - * - tdp_mmu_pages (above) * - the link field of kvm_mmu_page structs used by the TDP MMU - * - lpage_disallowed_mmu_pages - * - the lpage_disallowed_link field of kvm_mmu_page structs used + * - possible_nx_huge_pages; + * - the possible_nx_huge_page_link field of kvm_mmu_page structs used * by the TDP MMU * It is acceptable, but not necessary, to acquire this lock when * the thread holds the MMU lock in write mode. @@ -1607,10 +1671,12 @@ struct kvm_x86_ops { void (*setup_mce)(struct kvm_vcpu *vcpu); +#ifdef CONFIG_KVM_SMM int (*smi_allowed)(struct kvm_vcpu *vcpu, bool for_injection); - int (*enter_smm)(struct kvm_vcpu *vcpu, char *smstate); - int (*leave_smm)(struct kvm_vcpu *vcpu, const char *smstate); + int (*enter_smm)(struct kvm_vcpu *vcpu, union kvm_smram *smram); + int (*leave_smm)(struct kvm_vcpu *vcpu, const union kvm_smram *smram); void (*enable_smi_window)(struct kvm_vcpu *vcpu); +#endif int (*mem_enc_ioctl)(struct kvm *kvm, void __user *argp); int (*mem_enc_register_region)(struct kvm *kvm, struct kvm_enc_region *argp); @@ -1625,7 +1691,7 @@ struct kvm_x86_ops { void *insn, int insn_len); bool (*apic_init_signal_blocked)(struct kvm_vcpu *vcpu); - int (*enable_direct_tlbflush)(struct kvm_vcpu *vcpu); + int (*enable_l2_tlb_flush)(struct kvm_vcpu *vcpu); void (*migrate_timers)(struct kvm_vcpu *vcpu); void (*msr_filter_changed)(struct kvm_vcpu *vcpu); @@ -1658,6 +1724,7 @@ struct kvm_x86_nested_ops { int (*enable_evmcs)(struct kvm_vcpu *vcpu, uint16_t *vmcs_version); uint16_t (*get_evmcs_version)(struct kvm_vcpu *vcpu); + void (*hv_inject_synthetic_vmexit_post_tlb_flush)(struct kvm_vcpu *vcpu); }; struct kvm_x86_init_ops { @@ -1839,6 +1906,7 @@ int kvm_emulate_ap_reset_hold(struct kvm_vcpu *vcpu); int kvm_emulate_wbinvd(struct kvm_vcpu *vcpu); void kvm_get_segment(struct kvm_vcpu *vcpu, struct kvm_segment *var, int seg); +void kvm_set_segment(struct kvm_vcpu *vcpu, struct kvm_segment *var, int seg); int kvm_load_segment_descriptor(struct kvm_vcpu *vcpu, u16 selector, int seg); void kvm_vcpu_deliver_sipi_vector(struct kvm_vcpu *vcpu, u8 vector); @@ -1904,8 +1972,6 @@ void kvm_mmu_free_roots(struct kvm *kvm, struct kvm_mmu *mmu, void kvm_mmu_free_guest_mode_roots(struct kvm *kvm, struct kvm_mmu *mmu); gpa_t kvm_mmu_gva_to_gpa_read(struct kvm_vcpu *vcpu, gva_t gva, struct x86_exception *exception); -gpa_t kvm_mmu_gva_to_gpa_fetch(struct kvm_vcpu *vcpu, gva_t gva, - struct x86_exception *exception); gpa_t kvm_mmu_gva_to_gpa_write(struct kvm_vcpu *vcpu, gva_t gva, struct x86_exception *exception); gpa_t kvm_mmu_gva_to_gpa_system(struct kvm_vcpu *vcpu, gva_t gva, @@ -1989,14 +2055,18 @@ enum { #define HF_NMI_MASK (1 << 3) #define HF_IRET_MASK (1 << 4) #define HF_GUEST_MASK (1 << 5) /* VCPU is in guest-mode */ + +#ifdef CONFIG_KVM_SMM #define HF_SMM_MASK (1 << 6) #define HF_SMM_INSIDE_NMI_MASK (1 << 7) -#define __KVM_VCPU_MULTIPLE_ADDRESS_SPACE -#define KVM_ADDRESS_SPACE_NUM 2 - -#define kvm_arch_vcpu_memslots_id(vcpu) ((vcpu)->arch.hflags & HF_SMM_MASK ? 1 : 0) -#define kvm_memslots_for_spte_role(kvm, role) __kvm_memslots(kvm, (role).smm) +# define __KVM_VCPU_MULTIPLE_ADDRESS_SPACE +# define KVM_ADDRESS_SPACE_NUM 2 +# define kvm_arch_vcpu_memslots_id(vcpu) ((vcpu)->arch.hflags & HF_SMM_MASK ? 1 : 0) +# define kvm_memslots_for_spte_role(kvm, role) __kvm_memslots(kvm, (role).smm) +#else +# define kvm_memslots_for_spte_role(kvm, role) __kvm_memslots(kvm, 0) +#endif #define KVM_ARCH_WANT_MMU_NOTIFIER @@ -2084,12 +2154,6 @@ static inline int kvm_cpu_get_apicid(int mps_cpu) #endif } -#define put_smstate(type, buf, offset, val) \ - *(type *)((buf) + (offset) - 0x7e00) = val - -#define GET_SMSTATE(type, buf, offset) \ - (*(type *)((buf) + (offset) - 0x7e00)) - int kvm_cpu_dirty_log_size(void); int memslot_rmap_alloc(struct kvm_memory_slot *slot, unsigned long npages); diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h index 9ac46dbe57d4..5d0f6891ae61 100644 --- a/arch/x86/include/asm/perf_event.h +++ b/arch/x86/include/asm/perf_event.h @@ -543,12 +543,12 @@ static inline void perf_check_microcode(void) { } #if defined(CONFIG_PERF_EVENTS) && defined(CONFIG_CPU_SUP_INTEL) extern struct perf_guest_switch_msr *perf_guest_get_msrs(int *nr, void *data); -extern int x86_perf_get_lbr(struct x86_pmu_lbr *lbr); +extern void x86_perf_get_lbr(struct x86_pmu_lbr *lbr); #else struct perf_guest_switch_msr *perf_guest_get_msrs(int *nr, void *data); -static inline int x86_perf_get_lbr(struct x86_pmu_lbr *lbr) +static inline void x86_perf_get_lbr(struct x86_pmu_lbr *lbr) { - return -1; + memset(lbr, 0, sizeof(*lbr)); } #endif 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/svm.h b/arch/x86/include/asm/svm.h index 0361626841bc..cb1ee53ad3b1 100644 --- a/arch/x86/include/asm/svm.h +++ b/arch/x86/include/asm/svm.h @@ -5,6 +5,8 @@ #include <uapi/asm/svm.h> #include <uapi/asm/kvm.h> +#include <asm/hyperv-tlfs.h> + /* * 32-bit intercept words in the VMCB Control Area, starting * at Byte offset 000h. @@ -161,7 +163,10 @@ struct __attribute__ ((__packed__)) vmcb_control_area { * Offset 0x3e0, 32 bytes reserved * for use by hypervisor/software. */ - u8 reserved_sw[32]; + union { + struct hv_vmcb_enlightenments hv_enlightenments; + u8 reserved_sw[32]; + }; }; @@ -293,12 +298,13 @@ struct vmcb_save_area { struct vmcb_seg ldtr; struct vmcb_seg idtr; struct vmcb_seg tr; - u8 reserved_1[42]; + /* Reserved fields are named following their struct offset */ + u8 reserved_0xa0[42]; u8 vmpl; u8 cpl; - u8 reserved_2[4]; + u8 reserved_0xcc[4]; u64 efer; - u8 reserved_3[112]; + u8 reserved_0xd8[112]; u64 cr4; u64 cr3; u64 cr0; @@ -306,7 +312,7 @@ struct vmcb_save_area { u64 dr6; u64 rflags; u64 rip; - u8 reserved_4[88]; + u8 reserved_0x180[88]; u64 rsp; u64 s_cet; u64 ssp; @@ -321,14 +327,14 @@ struct vmcb_save_area { u64 sysenter_esp; u64 sysenter_eip; u64 cr2; - u8 reserved_5[32]; + u8 reserved_0x248[32]; u64 g_pat; u64 dbgctl; u64 br_from; u64 br_to; u64 last_excp_from; u64 last_excp_to; - u8 reserved_6[72]; + u8 reserved_0x298[72]; u32 spec_ctrl; /* Guest version of SPEC_CTRL at 0x2E0 */ } __packed; @@ -349,12 +355,12 @@ struct sev_es_save_area { u64 vmpl2_ssp; u64 vmpl3_ssp; u64 u_cet; - u8 reserved_1[2]; + u8 reserved_0xc8[2]; u8 vmpl; u8 cpl; - u8 reserved_2[4]; + u8 reserved_0xcc[4]; u64 efer; - u8 reserved_3[104]; + u8 reserved_0xd8[104]; u64 xss; u64 cr4; u64 cr3; @@ -371,7 +377,7 @@ struct sev_es_save_area { u64 dr1_addr_mask; u64 dr2_addr_mask; u64 dr3_addr_mask; - u8 reserved_4[24]; + u8 reserved_0x1c0[24]; u64 rsp; u64 s_cet; u64 ssp; @@ -386,21 +392,21 @@ struct sev_es_save_area { u64 sysenter_esp; u64 sysenter_eip; u64 cr2; - u8 reserved_5[32]; + u8 reserved_0x248[32]; u64 g_pat; u64 dbgctl; u64 br_from; u64 br_to; u64 last_excp_from; u64 last_excp_to; - u8 reserved_7[80]; + u8 reserved_0x298[80]; u32 pkru; - u8 reserved_8[20]; - u64 reserved_9; /* rax already available at 0x01f8 */ + u32 tsc_aux; + u8 reserved_0x2f0[24]; u64 rcx; u64 rdx; u64 rbx; - u64 reserved_10; /* rsp already available at 0x01d8 */ + u64 reserved_0x320; /* rsp already available at 0x01d8 */ u64 rbp; u64 rsi; u64 rdi; @@ -412,7 +418,7 @@ struct sev_es_save_area { u64 r13; u64 r14; u64 r15; - u8 reserved_11[16]; + u8 reserved_0x380[16]; u64 guest_exit_info_1; u64 guest_exit_info_2; u64 guest_exit_int_info; @@ -425,7 +431,7 @@ struct sev_es_save_area { u64 pcpu_id; u64 event_inj; u64 xcr0; - u8 reserved_12[16]; + u8 reserved_0x3f0[16]; /* Floating point area */ u64 x87_dp; @@ -443,23 +449,23 @@ struct sev_es_save_area { } __packed; struct ghcb_save_area { - u8 reserved_1[203]; + u8 reserved_0x0[203]; u8 cpl; - u8 reserved_2[116]; + u8 reserved_0xcc[116]; u64 xss; - u8 reserved_3[24]; + u8 reserved_0x148[24]; u64 dr7; - u8 reserved_4[16]; + u8 reserved_0x168[16]; u64 rip; - u8 reserved_5[88]; + u8 reserved_0x180[88]; u64 rsp; - u8 reserved_6[24]; + u8 reserved_0x1e0[24]; u64 rax; - u8 reserved_7[264]; + u8 reserved_0x200[264]; u64 rcx; u64 rdx; u64 rbx; - u8 reserved_8[8]; + u8 reserved_0x320[8]; u64 rbp; u64 rsi; u64 rdi; @@ -471,12 +477,12 @@ struct ghcb_save_area { u64 r13; u64 r14; u64 r15; - u8 reserved_9[16]; + u8 reserved_0x380[16]; u64 sw_exit_code; u64 sw_exit_info_1; u64 sw_exit_info_2; u64 sw_scratch; - u8 reserved_10[56]; + u8 reserved_0x3b0[56]; u64 xcr0; u8 valid_bitmap[16]; u64 x87_state_gpa; @@ -490,7 +496,7 @@ struct ghcb { u8 shared_buffer[GHCB_SHARED_BUF_SIZE]; - u8 reserved_1[10]; + u8 reserved_0xff0[10]; u16 protocol_version; /* negotiated SEV-ES/GHCB protocol version */ u32 ghcb_usage; } __packed; @@ -502,6 +508,9 @@ struct ghcb { #define EXPECTED_VMCB_CONTROL_AREA_SIZE 1024 #define EXPECTED_GHCB_SIZE PAGE_SIZE +#define BUILD_BUG_RESERVED_OFFSET(x, y) \ + ASSERT_STRUCT_OFFSET(struct x, reserved ## _ ## y, y) + static inline void __unused_size_checks(void) { BUILD_BUG_ON(sizeof(struct vmcb_save_area) != EXPECTED_VMCB_SAVE_AREA_SIZE); @@ -509,6 +518,39 @@ static inline void __unused_size_checks(void) BUILD_BUG_ON(sizeof(struct sev_es_save_area) != EXPECTED_SEV_ES_SAVE_AREA_SIZE); BUILD_BUG_ON(sizeof(struct vmcb_control_area) != EXPECTED_VMCB_CONTROL_AREA_SIZE); BUILD_BUG_ON(sizeof(struct ghcb) != EXPECTED_GHCB_SIZE); + + /* Check offsets of reserved fields */ + + BUILD_BUG_RESERVED_OFFSET(vmcb_save_area, 0xa0); + BUILD_BUG_RESERVED_OFFSET(vmcb_save_area, 0xcc); + BUILD_BUG_RESERVED_OFFSET(vmcb_save_area, 0xd8); + BUILD_BUG_RESERVED_OFFSET(vmcb_save_area, 0x180); + BUILD_BUG_RESERVED_OFFSET(vmcb_save_area, 0x248); + BUILD_BUG_RESERVED_OFFSET(vmcb_save_area, 0x298); + + BUILD_BUG_RESERVED_OFFSET(sev_es_save_area, 0xc8); + BUILD_BUG_RESERVED_OFFSET(sev_es_save_area, 0xcc); + BUILD_BUG_RESERVED_OFFSET(sev_es_save_area, 0xd8); + BUILD_BUG_RESERVED_OFFSET(sev_es_save_area, 0x1c0); + BUILD_BUG_RESERVED_OFFSET(sev_es_save_area, 0x248); + BUILD_BUG_RESERVED_OFFSET(sev_es_save_area, 0x298); + BUILD_BUG_RESERVED_OFFSET(sev_es_save_area, 0x2f0); + BUILD_BUG_RESERVED_OFFSET(sev_es_save_area, 0x320); + BUILD_BUG_RESERVED_OFFSET(sev_es_save_area, 0x380); + BUILD_BUG_RESERVED_OFFSET(sev_es_save_area, 0x3f0); + + BUILD_BUG_RESERVED_OFFSET(ghcb_save_area, 0x0); + BUILD_BUG_RESERVED_OFFSET(ghcb_save_area, 0xcc); + BUILD_BUG_RESERVED_OFFSET(ghcb_save_area, 0x148); + BUILD_BUG_RESERVED_OFFSET(ghcb_save_area, 0x168); + BUILD_BUG_RESERVED_OFFSET(ghcb_save_area, 0x180); + BUILD_BUG_RESERVED_OFFSET(ghcb_save_area, 0x1e0); + BUILD_BUG_RESERVED_OFFSET(ghcb_save_area, 0x200); + BUILD_BUG_RESERVED_OFFSET(ghcb_save_area, 0x320); + BUILD_BUG_RESERVED_OFFSET(ghcb_save_area, 0x380); + BUILD_BUG_RESERVED_OFFSET(ghcb_save_area, 0x3b0); + + BUILD_BUG_RESERVED_OFFSET(ghcb, 0xff0); } struct vmcb { 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/include/uapi/asm/kvm.h b/arch/x86/include/uapi/asm/kvm.h index 46de10a809ec..c6df6b16a088 100644 --- a/arch/x86/include/uapi/asm/kvm.h +++ b/arch/x86/include/uapi/asm/kvm.h @@ -214,6 +214,8 @@ struct kvm_msr_list { struct kvm_msr_filter_range { #define KVM_MSR_FILTER_READ (1 << 0) #define KVM_MSR_FILTER_WRITE (1 << 1) +#define KVM_MSR_FILTER_RANGE_VALID_MASK (KVM_MSR_FILTER_READ | \ + KVM_MSR_FILTER_WRITE) __u32 flags; __u32 nmsrs; /* number of msrs in bitmap */ __u32 base; /* MSR index the bitmap starts at */ @@ -222,8 +224,11 @@ struct kvm_msr_filter_range { #define KVM_MSR_FILTER_MAX_RANGES 16 struct kvm_msr_filter { +#ifndef __KERNEL__ #define KVM_MSR_FILTER_DEFAULT_ALLOW (0 << 0) +#endif #define KVM_MSR_FILTER_DEFAULT_DENY (1 << 0) +#define KVM_MSR_FILTER_VALID_MASK (KVM_MSR_FILTER_DEFAULT_DENY) __u32 flags; struct kvm_msr_filter_range ranges[KVM_MSR_FILTER_MAX_RANGES]; }; 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/kvm.c b/arch/x86/kernel/kvm.c index d4e48b4a438b..cf886f86038a 100644 --- a/arch/x86/kernel/kvm.c +++ b/arch/x86/kernel/kvm.c @@ -349,7 +349,7 @@ static notrace void kvm_guest_apic_eoi_write(u32 reg, u32 val) static void kvm_guest_cpu_init(void) { if (kvm_para_has_feature(KVM_FEATURE_ASYNC_PF_INT) && kvmapf) { - u64 pa = slow_virt_to_phys(this_cpu_ptr(&apf_reason)); + u64 pa; WARN_ON_ONCE(!static_branch_likely(&kvm_async_pf_enabled)); 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/Kconfig b/arch/x86/kvm/Kconfig index 67be7f217e37..fbeaa9ddef59 100644 --- a/arch/x86/kvm/Kconfig +++ b/arch/x86/kvm/Kconfig @@ -118,6 +118,17 @@ config KVM_AMD_SEV Provides support for launching Encrypted VMs (SEV) and Encrypted VMs with Encrypted State (SEV-ES) on AMD processors. +config KVM_SMM + bool "System Management Mode emulation" + default y + depends on KVM + help + Provides support for KVM to emulate System Management Mode (SMM) + in virtual machines. This can be used by the virtual machine + firmware to implement UEFI secure boot. + + If unsure, say Y. + config KVM_XEN bool "Support for Xen hypercall interface" depends on KVM diff --git a/arch/x86/kvm/Makefile b/arch/x86/kvm/Makefile index 30f244b64523..80e3fe184d17 100644 --- a/arch/x86/kvm/Makefile +++ b/arch/x86/kvm/Makefile @@ -20,12 +20,14 @@ endif kvm-$(CONFIG_X86_64) += mmu/tdp_iter.o mmu/tdp_mmu.o kvm-$(CONFIG_KVM_XEN) += xen.o +kvm-$(CONFIG_KVM_SMM) += smm.o kvm-intel-y += vmx/vmx.o vmx/vmenter.o vmx/pmu_intel.o vmx/vmcs12.o \ - vmx/evmcs.o vmx/nested.o vmx/posted_intr.o + vmx/hyperv.o vmx/nested.o vmx/posted_intr.o kvm-intel-$(CONFIG_X86_SGX_KVM) += vmx/sgx.o -kvm-amd-y += svm/svm.o svm/vmenter.o svm/pmu.o svm/nested.o svm/avic.o svm/sev.o +kvm-amd-y += svm/svm.o svm/vmenter.o svm/pmu.o svm/nested.o svm/avic.o \ + svm/sev.o svm/hyperv.o ifdef CONFIG_HYPERV kvm-amd-y += svm/svm_onhyperv.o @@ -34,3 +36,15 @@ 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..723502181a3a 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -62,10 +62,16 @@ u32 xstate_required_size(u64 xstate_bv, bool compacted) * This one is tied to SSB in the user API, and not * visible in /proc/cpuinfo. */ -#define KVM_X86_FEATURE_PSFD (13*32+28) /* Predictive Store Forwarding Disable */ +#define KVM_X86_FEATURE_AMD_PSFD (13*32+28) /* Predictive Store Forwarding Disable */ #define F feature_bit -#define SF(name) (boot_cpu_has(X86_FEATURE_##name) ? F(name) : 0) + +/* Scattered Flag - For features that are scattered by cpufeatures.h. */ +#define SF(name) \ +({ \ + BUILD_BUG_ON(X86_FEATURE_##name >= MAX_CPU_FEATURES); \ + (boot_cpu_has(X86_FEATURE_##name) ? F(name) : 0); \ +}) /* * Magic value used by KVM when querying userspace-provided CPUID entries and @@ -543,9 +549,9 @@ static __always_inline void __kvm_cpu_cap_mask(unsigned int leaf) } static __always_inline -void kvm_cpu_cap_init_scattered(enum kvm_only_cpuid_leafs leaf, u32 mask) +void kvm_cpu_cap_init_kvm_defined(enum kvm_only_cpuid_leafs leaf, u32 mask) { - /* Use kvm_cpu_cap_mask for non-scattered leafs. */ + /* Use kvm_cpu_cap_mask for leafs that aren't KVM-only. */ BUILD_BUG_ON(leaf < NCAPINTS); kvm_cpu_caps[leaf] = mask; @@ -555,7 +561,7 @@ void kvm_cpu_cap_init_scattered(enum kvm_only_cpuid_leafs leaf, u32 mask) static __always_inline void kvm_cpu_cap_mask(enum cpuid_leafs leaf, u32 mask) { - /* Use kvm_cpu_cap_init_scattered for scattered leafs. */ + /* Use kvm_cpu_cap_init_kvm_defined for KVM-only leafs. */ BUILD_BUG_ON(leaf >= NCAPINTS); kvm_cpu_caps[leaf] &= mask; @@ -657,14 +663,19 @@ void kvm_set_cpu_caps(void) kvm_cpu_cap_set(X86_FEATURE_SPEC_CTRL_SSBD); kvm_cpu_cap_mask(CPUID_7_1_EAX, - F(AVX_VNNI) | F(AVX512_BF16) + F(AVX_VNNI) | F(AVX512_BF16) | F(CMPCCXADD) | F(AMX_FP16) | + F(AVX_IFMA) + ); + + kvm_cpu_cap_init_kvm_defined(CPUID_7_1_EDX, + F(AVX_VNNI_INT8) | F(AVX_NE_CONVERT) | F(PREFETCHITI) ); kvm_cpu_cap_mask(CPUID_D_1_EAX, F(XSAVEOPT) | F(XSAVEC) | F(XGETBV1) | F(XSAVES) | f_xfd ); - kvm_cpu_cap_init_scattered(CPUID_12_EAX, + kvm_cpu_cap_init_kvm_defined(CPUID_12_EAX, SF(SGX1) | SF(SGX2) ); @@ -694,7 +705,7 @@ void kvm_set_cpu_caps(void) F(CLZERO) | F(XSAVEERPTR) | F(WBNOINVD) | F(AMD_IBPB) | F(AMD_IBRS) | F(AMD_SSBD) | F(VIRT_SSBD) | F(AMD_SSB_NO) | F(AMD_STIBP) | F(AMD_STIBP_ALWAYS_ON) | - __feature_bit(KVM_X86_FEATURE_PSFD) + __feature_bit(KVM_X86_FEATURE_AMD_PSFD) ); /* @@ -913,9 +924,9 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function) goto out; cpuid_entry_override(entry, CPUID_7_1_EAX); + cpuid_entry_override(entry, CPUID_7_1_EDX); entry->ebx = 0; entry->ecx = 0; - entry->edx = 0; } break; case 0xa: { /* Architectural Performance Monitoring */ @@ -1133,11 +1144,13 @@ 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 +1180,7 @@ 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 +1200,9 @@ 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 +1210,8 @@ 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 +1349,7 @@ 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..5cc3efa0e21c 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -242,37 +242,6 @@ enum x86_transfer_type { X86_TRANSFER_TASK_SWITCH, }; -static ulong reg_read(struct x86_emulate_ctxt *ctxt, unsigned nr) -{ - if (KVM_EMULATOR_BUG_ON(nr >= NR_EMULATOR_GPRS, ctxt)) - nr &= NR_EMULATOR_GPRS - 1; - - if (!(ctxt->regs_valid & (1 << nr))) { - ctxt->regs_valid |= 1 << nr; - ctxt->_regs[nr] = ctxt->ops->read_gpr(ctxt, nr); - } - return ctxt->_regs[nr]; -} - -static ulong *reg_write(struct x86_emulate_ctxt *ctxt, unsigned nr) -{ - if (KVM_EMULATOR_BUG_ON(nr >= NR_EMULATOR_GPRS, ctxt)) - nr &= NR_EMULATOR_GPRS - 1; - - BUILD_BUG_ON(sizeof(ctxt->regs_dirty) * BITS_PER_BYTE < NR_EMULATOR_GPRS); - BUILD_BUG_ON(sizeof(ctxt->regs_valid) * BITS_PER_BYTE < NR_EMULATOR_GPRS); - - ctxt->regs_valid |= 1 << nr; - ctxt->regs_dirty |= 1 << nr; - return &ctxt->_regs[nr]; -} - -static ulong *reg_rmw(struct x86_emulate_ctxt *ctxt, unsigned nr) -{ - reg_read(ctxt, nr); - return reg_write(ctxt, nr); -} - static void writeback_registers(struct x86_emulate_ctxt *ctxt) { unsigned long dirty = ctxt->regs_dirty; @@ -791,8 +760,7 @@ 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 +770,71 @@ 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 +2170,7 @@ 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 +2248,7 @@ 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; @@ -2309,335 +2307,15 @@ static int em_lseg(struct x86_emulate_ctxt *ctxt) return rc; } -static int emulator_has_longmode(struct x86_emulate_ctxt *ctxt) -{ -#ifdef CONFIG_X86_64 - return ctxt->ops->guest_has_long_mode(ctxt); -#else - return false; -#endif -} - -static void rsm_set_desc_flags(struct desc_struct *desc, u32 flags) -{ - desc->g = (flags >> 23) & 1; - desc->d = (flags >> 22) & 1; - desc->l = (flags >> 21) & 1; - desc->avl = (flags >> 20) & 1; - desc->p = (flags >> 15) & 1; - desc->dpl = (flags >> 13) & 3; - desc->s = (flags >> 12) & 1; - desc->type = (flags >> 8) & 15; -} - -static int rsm_load_seg_32(struct x86_emulate_ctxt *ctxt, const char *smstate, - int n) -{ - struct desc_struct desc; - int offset; - u16 selector; - - selector = GET_SMSTATE(u32, smstate, 0x7fa8 + n * 4); - - if (n < 3) - offset = 0x7f84 + n * 12; - else - offset = 0x7f2c + (n - 3) * 12; - - set_desc_base(&desc, GET_SMSTATE(u32, smstate, offset + 8)); - set_desc_limit(&desc, GET_SMSTATE(u32, smstate, offset + 4)); - rsm_set_desc_flags(&desc, GET_SMSTATE(u32, smstate, offset)); - ctxt->ops->set_segment(ctxt, selector, &desc, 0, n); - return X86EMUL_CONTINUE; -} - -#ifdef CONFIG_X86_64 -static int rsm_load_seg_64(struct x86_emulate_ctxt *ctxt, const char *smstate, - int n) -{ - struct desc_struct desc; - int offset; - u16 selector; - u32 base3; - - offset = 0x7e00 + n * 16; - - selector = GET_SMSTATE(u16, smstate, offset); - rsm_set_desc_flags(&desc, GET_SMSTATE(u16, smstate, offset + 2) << 8); - set_desc_limit(&desc, GET_SMSTATE(u32, smstate, offset + 4)); - set_desc_base(&desc, GET_SMSTATE(u32, smstate, offset + 8)); - base3 = GET_SMSTATE(u32, smstate, offset + 12); - - ctxt->ops->set_segment(ctxt, selector, &desc, base3, n); - return X86EMUL_CONTINUE; -} -#endif - -static int rsm_enter_protected_mode(struct x86_emulate_ctxt *ctxt, - u64 cr0, u64 cr3, u64 cr4) -{ - int bad; - u64 pcid; - - /* In order to later set CR4.PCIDE, CR3[11:0] must be zero. */ - pcid = 0; - if (cr4 & X86_CR4_PCIDE) { - pcid = cr3 & 0xfff; - cr3 &= ~0xfff; - } - - bad = ctxt->ops->set_cr(ctxt, 3, cr3); - if (bad) - return X86EMUL_UNHANDLEABLE; - - /* - * First enable PAE, long mode needs it before CR0.PG = 1 is set. - * Then enable protected mode. However, PCID cannot be enabled - * if EFER.LMA=0, so set it separately. - */ - bad = ctxt->ops->set_cr(ctxt, 4, cr4 & ~X86_CR4_PCIDE); - if (bad) - return X86EMUL_UNHANDLEABLE; - - bad = ctxt->ops->set_cr(ctxt, 0, cr0); - if (bad) - return X86EMUL_UNHANDLEABLE; - - if (cr4 & X86_CR4_PCIDE) { - bad = ctxt->ops->set_cr(ctxt, 4, cr4); - if (bad) - return X86EMUL_UNHANDLEABLE; - if (pcid) { - bad = ctxt->ops->set_cr(ctxt, 3, cr3 | pcid); - if (bad) - return X86EMUL_UNHANDLEABLE; - } - - } - - return X86EMUL_CONTINUE; -} - -static int rsm_load_state_32(struct x86_emulate_ctxt *ctxt, - const char *smstate) -{ - struct desc_struct desc; - struct desc_ptr dt; - u16 selector; - u32 val, cr0, cr3, cr4; - int i; - - cr0 = GET_SMSTATE(u32, smstate, 0x7ffc); - cr3 = GET_SMSTATE(u32, smstate, 0x7ff8); - 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++) - *reg_write(ctxt, i) = GET_SMSTATE(u32, smstate, 0x7fd0 + i * 4); - - val = GET_SMSTATE(u32, smstate, 0x7fcc); - - if (ctxt->ops->set_dr(ctxt, 6, val)) - return X86EMUL_UNHANDLEABLE; - - val = GET_SMSTATE(u32, smstate, 0x7fc8); - - if (ctxt->ops->set_dr(ctxt, 7, val)) - return X86EMUL_UNHANDLEABLE; - - selector = GET_SMSTATE(u32, smstate, 0x7fc4); - set_desc_base(&desc, GET_SMSTATE(u32, smstate, 0x7f64)); - set_desc_limit(&desc, GET_SMSTATE(u32, smstate, 0x7f60)); - rsm_set_desc_flags(&desc, GET_SMSTATE(u32, smstate, 0x7f5c)); - ctxt->ops->set_segment(ctxt, selector, &desc, 0, VCPU_SREG_TR); - - selector = GET_SMSTATE(u32, smstate, 0x7fc0); - set_desc_base(&desc, GET_SMSTATE(u32, smstate, 0x7f80)); - set_desc_limit(&desc, GET_SMSTATE(u32, smstate, 0x7f7c)); - rsm_set_desc_flags(&desc, GET_SMSTATE(u32, smstate, 0x7f78)); - ctxt->ops->set_segment(ctxt, selector, &desc, 0, VCPU_SREG_LDTR); - - dt.address = GET_SMSTATE(u32, smstate, 0x7f74); - dt.size = GET_SMSTATE(u32, smstate, 0x7f70); - ctxt->ops->set_gdt(ctxt, &dt); - - dt.address = GET_SMSTATE(u32, smstate, 0x7f58); - dt.size = GET_SMSTATE(u32, smstate, 0x7f54); - ctxt->ops->set_idt(ctxt, &dt); - - for (i = 0; i < 6; i++) { - int r = rsm_load_seg_32(ctxt, smstate, i); - if (r != X86EMUL_CONTINUE) - return r; - } - - cr4 = GET_SMSTATE(u32, smstate, 0x7f14); - - ctxt->ops->set_smbase(ctxt, GET_SMSTATE(u32, smstate, 0x7ef8)); - - return rsm_enter_protected_mode(ctxt, cr0, cr3, cr4); -} - -#ifdef CONFIG_X86_64 -static int rsm_load_state_64(struct x86_emulate_ctxt *ctxt, - const char *smstate) -{ - struct desc_struct desc; - struct desc_ptr dt; - u64 val, cr0, cr3, cr4; - u32 base3; - u16 selector; - int i, r; - - for (i = 0; i < NR_EMULATOR_GPRS; i++) - *reg_write(ctxt, i) = GET_SMSTATE(u64, smstate, 0x7ff8 - i * 8); - - ctxt->_eip = GET_SMSTATE(u64, smstate, 0x7f78); - ctxt->eflags = GET_SMSTATE(u32, smstate, 0x7f70) | X86_EFLAGS_FIXED; - - val = GET_SMSTATE(u64, smstate, 0x7f68); - - if (ctxt->ops->set_dr(ctxt, 6, val)) - return X86EMUL_UNHANDLEABLE; - - val = GET_SMSTATE(u64, smstate, 0x7f60); - - if (ctxt->ops->set_dr(ctxt, 7, val)) - return X86EMUL_UNHANDLEABLE; - - cr0 = GET_SMSTATE(u64, smstate, 0x7f58); - cr3 = GET_SMSTATE(u64, smstate, 0x7f50); - cr4 = GET_SMSTATE(u64, smstate, 0x7f48); - ctxt->ops->set_smbase(ctxt, GET_SMSTATE(u32, smstate, 0x7f00)); - val = GET_SMSTATE(u64, smstate, 0x7ed0); - - if (ctxt->ops->set_msr(ctxt, MSR_EFER, val & ~EFER_LMA)) - return X86EMUL_UNHANDLEABLE; - - selector = GET_SMSTATE(u32, smstate, 0x7e90); - rsm_set_desc_flags(&desc, GET_SMSTATE(u32, smstate, 0x7e92) << 8); - set_desc_limit(&desc, GET_SMSTATE(u32, smstate, 0x7e94)); - set_desc_base(&desc, GET_SMSTATE(u32, smstate, 0x7e98)); - base3 = GET_SMSTATE(u32, smstate, 0x7e9c); - ctxt->ops->set_segment(ctxt, selector, &desc, base3, VCPU_SREG_TR); - - dt.size = GET_SMSTATE(u32, smstate, 0x7e84); - dt.address = GET_SMSTATE(u64, smstate, 0x7e88); - ctxt->ops->set_idt(ctxt, &dt); - - selector = GET_SMSTATE(u32, smstate, 0x7e70); - rsm_set_desc_flags(&desc, GET_SMSTATE(u32, smstate, 0x7e72) << 8); - set_desc_limit(&desc, GET_SMSTATE(u32, smstate, 0x7e74)); - set_desc_base(&desc, GET_SMSTATE(u32, smstate, 0x7e78)); - base3 = GET_SMSTATE(u32, smstate, 0x7e7c); - ctxt->ops->set_segment(ctxt, selector, &desc, base3, VCPU_SREG_LDTR); - - dt.size = GET_SMSTATE(u32, smstate, 0x7e64); - dt.address = GET_SMSTATE(u64, smstate, 0x7e68); - ctxt->ops->set_gdt(ctxt, &dt); - - r = rsm_enter_protected_mode(ctxt, cr0, cr3, cr4); - if (r != X86EMUL_CONTINUE) - return r; - - for (i = 0; i < 6; i++) { - r = rsm_load_seg_64(ctxt, smstate, i); - if (r != X86EMUL_CONTINUE) - return r; - } - - return X86EMUL_CONTINUE; -} -#endif - static int em_rsm(struct x86_emulate_ctxt *ctxt) { - unsigned long cr0, cr4, efer; - char buf[512]; - u64 smbase; - int ret; - if ((ctxt->ops->get_hflags(ctxt) & X86EMUL_SMM_MASK) == 0) return emulate_ud(ctxt); - smbase = ctxt->ops->get_smbase(ctxt); - - ret = ctxt->ops->read_phys(ctxt, smbase + 0xfe00, buf, sizeof(buf)); - if (ret != X86EMUL_CONTINUE) - return X86EMUL_UNHANDLEABLE; - - if ((ctxt->ops->get_hflags(ctxt) & X86EMUL_SMM_INSIDE_NMI_MASK) == 0) - ctxt->ops->set_nmi_mask(ctxt, false); - - ctxt->ops->exiting_smm(ctxt); - - /* - * Get back to real mode, to prepare a safe state in which to load - * CR0/CR3/CR4/EFER. It's all a bit more complicated if the vCPU - * supports long mode. - */ - if (emulator_has_longmode(ctxt)) { - struct desc_struct cs_desc; - - /* Zero CR4.PCIDE before CR0.PG. */ - cr4 = ctxt->ops->get_cr(ctxt, 4); - if (cr4 & X86_CR4_PCIDE) - ctxt->ops->set_cr(ctxt, 4, cr4 & ~X86_CR4_PCIDE); - - /* A 32-bit code segment is required to clear EFER.LMA. */ - memset(&cs_desc, 0, sizeof(cs_desc)); - cs_desc.type = 0xb; - cs_desc.s = cs_desc.g = cs_desc.p = 1; - ctxt->ops->set_segment(ctxt, 0, &cs_desc, 0, VCPU_SREG_CS); - } - - /* For the 64-bit case, this will clear EFER.LMA. */ - cr0 = ctxt->ops->get_cr(ctxt, 0); - if (cr0 & X86_CR0_PE) - ctxt->ops->set_cr(ctxt, 0, cr0 & ~(X86_CR0_PG | X86_CR0_PE)); - - if (emulator_has_longmode(ctxt)) { - /* Clear CR4.PAE before clearing EFER.LME. */ - cr4 = ctxt->ops->get_cr(ctxt, 4); - if (cr4 & X86_CR4_PAE) - ctxt->ops->set_cr(ctxt, 4, cr4 & ~X86_CR4_PAE); - - /* And finally go back to 32-bit mode. */ - efer = 0; - ctxt->ops->set_msr(ctxt, MSR_EFER, efer); - } - - /* - * Give leave_smm() a chance to make ISA-specific changes to the vCPU - * state (e.g. enter guest mode) before loading state from the SMM - * state-save area. - */ - if (ctxt->ops->leave_smm(ctxt, buf)) - goto emulate_shutdown; - -#ifdef CONFIG_X86_64 - if (emulator_has_longmode(ctxt)) - ret = rsm_load_state_64(ctxt, buf); - else -#endif - ret = rsm_load_state_32(ctxt, buf); - - if (ret != X86EMUL_CONTINUE) - goto emulate_shutdown; - - /* - * Note, the ctxt->ops callbacks are responsible for handling side - * effects when writing MSRs and CRs, e.g. MMU context resets, CPUID - * runtime updates, etc... If that changes, e.g. this flow is moved - * out of the emulator to make it look more like enter_smm(), then - * those side effects need to be explicitly handled for both success - * and shutdown. - */ - return X86EMUL_CONTINUE; + if (ctxt->ops->leave_smm(ctxt)) + ctxt->ops->triple_fault(ctxt); -emulate_shutdown: - ctxt->ops->triple_fault(ctxt); - return X86EMUL_CONTINUE; + return emulator_recalc_and_set_mode(ctxt); } static void @@ -2876,6 +2554,7 @@ 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 +3148,7 @@ 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 +3290,25 @@ 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/hyperv.c b/arch/x86/kvm/hyperv.c index 0adf4a437e85..2c7f2a26421e 100644 --- a/arch/x86/kvm/hyperv.c +++ b/arch/x86/kvm/hyperv.c @@ -23,22 +23,25 @@ #include "ioapic.h" #include "cpuid.h" #include "hyperv.h" +#include "mmu.h" #include "xen.h" #include <linux/cpu.h> #include <linux/kvm_host.h> #include <linux/highmem.h> #include <linux/sched/cputime.h> +#include <linux/spinlock.h> #include <linux/eventfd.h> #include <asm/apicdef.h> +#include <asm/mshyperv.h> #include <trace/events/kvm.h> #include "trace.h" #include "irq.h" #include "fpu.h" -#define KVM_HV_MAX_SPARSE_VCPU_SET_BITS DIV_ROUND_UP(KVM_MAX_VCPUS, 64) +#define KVM_HV_MAX_SPARSE_VCPU_SET_BITS DIV_ROUND_UP(KVM_MAX_VCPUS, HV_VCPUS_PER_SPARSE_BANK) static void stimer_mark_pending(struct kvm_vcpu_hv_stimer *stimer, bool vcpu_kick); @@ -897,13 +900,15 @@ bool kvm_hv_assist_page_enabled(struct kvm_vcpu *vcpu) } EXPORT_SYMBOL_GPL(kvm_hv_assist_page_enabled); -bool kvm_hv_get_assist_page(struct kvm_vcpu *vcpu, - struct hv_vp_assist_page *assist_page) +int kvm_hv_get_assist_page(struct kvm_vcpu *vcpu) { - if (!kvm_hv_assist_page_enabled(vcpu)) - return false; - return !kvm_read_guest_cached(vcpu->kvm, &vcpu->arch.pv_eoi.data, - assist_page, sizeof(*assist_page)); + struct kvm_vcpu_hv *hv_vcpu = to_hv_vcpu(vcpu); + + if (!hv_vcpu || !kvm_hv_assist_page_enabled(vcpu)) + return -EFAULT; + + return kvm_read_guest_cached(vcpu->kvm, &vcpu->arch.pv_eoi.data, + &hv_vcpu->vp_assist_page, sizeof(struct hv_vp_assist_page)); } EXPORT_SYMBOL_GPL(kvm_hv_get_assist_page); @@ -954,6 +959,11 @@ int kvm_hv_vcpu_init(struct kvm_vcpu *vcpu) hv_vcpu->vp_index = vcpu->vcpu_idx; + for (i = 0; i < HV_NR_TLB_FLUSH_FIFOS; i++) { + INIT_KFIFO(hv_vcpu->tlb_flush_fifo[i].entries); + spin_lock_init(&hv_vcpu->tlb_flush_fifo[i].write_lock); + } + return 0; } @@ -1736,6 +1746,28 @@ static void sparse_set_to_vcpu_mask(struct kvm *kvm, u64 *sparse_banks, } } +static bool hv_is_vp_in_sparse_set(u32 vp_id, u64 valid_bank_mask, u64 sparse_banks[]) +{ + int valid_bit_nr = vp_id / HV_VCPUS_PER_SPARSE_BANK; + unsigned long sbank; + + if (!test_bit(valid_bit_nr, (unsigned long *)&valid_bank_mask)) + return false; + + /* + * The index into the sparse bank is the number of preceding bits in + * the valid mask. Optimize for VMs with <64 vCPUs by skipping the + * fancy math if there can't possibly be preceding bits. + */ + if (valid_bit_nr) + sbank = hweight64(valid_bank_mask & GENMASK_ULL(valid_bit_nr - 1, 0)); + else + sbank = 0; + + return test_bit(vp_id % HV_VCPUS_PER_SPARSE_BANK, + (unsigned long *)&sparse_banks[sbank]); +} + struct kvm_hv_hcall { u64 param; u64 ingpa; @@ -1749,57 +1781,173 @@ struct kvm_hv_hcall { sse128_t xmm[HV_HYPERCALL_MAX_XMM_REGISTERS]; }; -static u64 kvm_get_sparse_vp_set(struct kvm *kvm, struct kvm_hv_hcall *hc, - int consumed_xmm_halves, - u64 *sparse_banks, gpa_t offset) -{ - u16 var_cnt; - int i; - - if (hc->var_cnt > 64) - return -EINVAL; - /* Ignore banks that cannot possibly contain a legal VP index. */ - var_cnt = min_t(u16, hc->var_cnt, KVM_HV_MAX_SPARSE_VCPU_SET_BITS); +static int kvm_hv_get_hc_data(struct kvm *kvm, struct kvm_hv_hcall *hc, + u16 orig_cnt, u16 cnt_cap, u64 *data, + int consumed_xmm_halves, gpa_t offset) +{ + /* + * Preserve the original count when ignoring entries via a "cap", KVM + * still needs to validate the guest input (though the non-XMM path + * punts on the checks). + */ + u16 cnt = min(orig_cnt, cnt_cap); + int i, j; if (hc->fast) { /* * Each XMM holds two sparse banks, but do not count halves that * have already been consumed for hypercall parameters. */ - if (hc->var_cnt > 2 * HV_HYPERCALL_MAX_XMM_REGISTERS - consumed_xmm_halves) + if (orig_cnt > 2 * HV_HYPERCALL_MAX_XMM_REGISTERS - consumed_xmm_halves) return HV_STATUS_INVALID_HYPERCALL_INPUT; - for (i = 0; i < var_cnt; i++) { - int j = i + consumed_xmm_halves; + + for (i = 0; i < cnt; i++) { + j = i + consumed_xmm_halves; if (j % 2) - sparse_banks[i] = sse128_hi(hc->xmm[j / 2]); + data[i] = sse128_hi(hc->xmm[j / 2]); else - sparse_banks[i] = sse128_lo(hc->xmm[j / 2]); + data[i] = sse128_lo(hc->xmm[j / 2]); } return 0; } - return kvm_read_guest(kvm, hc->ingpa + offset, sparse_banks, - var_cnt * sizeof(*sparse_banks)); + return kvm_read_guest(kvm, hc->ingpa + offset, data, + cnt * sizeof(*data)); +} + +static u64 kvm_get_sparse_vp_set(struct kvm *kvm, struct kvm_hv_hcall *hc, + u64 *sparse_banks, int consumed_xmm_halves, + gpa_t offset) +{ + if (hc->var_cnt > HV_MAX_SPARSE_VCPU_BANKS) + return -EINVAL; + + /* Cap var_cnt to ignore banks that cannot contain a legal VP index. */ + return kvm_hv_get_hc_data(kvm, hc, hc->var_cnt, KVM_HV_MAX_SPARSE_VCPU_SET_BITS, + sparse_banks, consumed_xmm_halves, offset); +} + +static int kvm_hv_get_tlb_flush_entries(struct kvm *kvm, struct kvm_hv_hcall *hc, u64 entries[], + int consumed_xmm_halves, gpa_t offset) +{ + return kvm_hv_get_hc_data(kvm, hc, hc->rep_cnt, hc->rep_cnt, + entries, consumed_xmm_halves, offset); +} + +static void hv_tlb_flush_enqueue(struct kvm_vcpu *vcpu, + struct kvm_vcpu_hv_tlb_flush_fifo *tlb_flush_fifo, + u64 *entries, int count) +{ + struct kvm_vcpu_hv *hv_vcpu = to_hv_vcpu(vcpu); + u64 flush_all_entry = KVM_HV_TLB_FLUSHALL_ENTRY; + + if (!hv_vcpu) + return; + + spin_lock(&tlb_flush_fifo->write_lock); + + /* + * All entries should fit on the fifo leaving one free for 'flush all' + * entry in case another request comes in. In case there's not enough + * space, just put 'flush all' entry there. + */ + if (count && entries && count < kfifo_avail(&tlb_flush_fifo->entries)) { + WARN_ON(kfifo_in(&tlb_flush_fifo->entries, entries, count) != count); + goto out_unlock; + } + + /* + * Note: full fifo always contains 'flush all' entry, no need to check the + * return value. + */ + kfifo_in(&tlb_flush_fifo->entries, &flush_all_entry, 1); + +out_unlock: + spin_unlock(&tlb_flush_fifo->write_lock); +} + +int kvm_hv_vcpu_flush_tlb(struct kvm_vcpu *vcpu) +{ + struct kvm_vcpu_hv_tlb_flush_fifo *tlb_flush_fifo; + struct kvm_vcpu_hv *hv_vcpu = to_hv_vcpu(vcpu); + u64 entries[KVM_HV_TLB_FLUSH_FIFO_SIZE]; + int i, j, count; + gva_t gva; + + if (!tdp_enabled || !hv_vcpu) + return -EINVAL; + + tlb_flush_fifo = kvm_hv_get_tlb_flush_fifo(vcpu, is_guest_mode(vcpu)); + + count = kfifo_out(&tlb_flush_fifo->entries, entries, KVM_HV_TLB_FLUSH_FIFO_SIZE); + + for (i = 0; i < count; i++) { + if (entries[i] == KVM_HV_TLB_FLUSHALL_ENTRY) + goto out_flush_all; + + /* + * Lower 12 bits of 'address' encode the number of additional + * pages to flush. + */ + gva = entries[i] & PAGE_MASK; + for (j = 0; j < (entries[i] & ~PAGE_MASK) + 1; j++) + static_call(kvm_x86_flush_tlb_gva)(vcpu, gva + j * PAGE_SIZE); + + ++vcpu->stat.tlb_flush; + } + return 0; + +out_flush_all: + kfifo_reset_out(&tlb_flush_fifo->entries); + + /* Fall back to full flush. */ + return -ENOSPC; } static u64 kvm_hv_flush_tlb(struct kvm_vcpu *vcpu, struct kvm_hv_hcall *hc) { + struct kvm_vcpu_hv *hv_vcpu = to_hv_vcpu(vcpu); + u64 *sparse_banks = hv_vcpu->sparse_banks; struct kvm *kvm = vcpu->kvm; struct hv_tlb_flush_ex flush_ex; struct hv_tlb_flush flush; DECLARE_BITMAP(vcpu_mask, KVM_MAX_VCPUS); + struct kvm_vcpu_hv_tlb_flush_fifo *tlb_flush_fifo; + /* + * Normally, there can be no more than 'KVM_HV_TLB_FLUSH_FIFO_SIZE' + * entries on the TLB flush fifo. The last entry, however, needs to be + * always left free for 'flush all' entry which gets placed when + * there is not enough space to put all the requested entries. + */ + u64 __tlb_flush_entries[KVM_HV_TLB_FLUSH_FIFO_SIZE - 1]; + u64 *tlb_flush_entries; u64 valid_bank_mask; - u64 sparse_banks[KVM_HV_MAX_SPARSE_VCPU_SET_BITS]; + struct kvm_vcpu *v; + unsigned long i; bool all_cpus; + int consumed_xmm_halves = 0; + gpa_t data_offset; /* - * The Hyper-V TLFS doesn't allow more than 64 sparse banks, e.g. the - * valid mask is a u64. Fail the build if KVM's max allowed number of - * vCPUs (>4096) would exceed this limit, KVM will additional changes - * for Hyper-V support to avoid setting the guest up to fail. + * The Hyper-V TLFS doesn't allow more than HV_MAX_SPARSE_VCPU_BANKS + * sparse banks. Fail the build if KVM's max allowed number of + * vCPUs (>4096) exceeds this limit. */ - BUILD_BUG_ON(KVM_HV_MAX_SPARSE_VCPU_SET_BITS > 64); + BUILD_BUG_ON(KVM_HV_MAX_SPARSE_VCPU_SET_BITS > HV_MAX_SPARSE_VCPU_BANKS); + + /* + * 'Slow' hypercall's first parameter is the address in guest's memory + * where hypercall parameters are placed. This is either a GPA or a + * nested GPA when KVM is handling the call from L2 ('direct' TLB + * flush). Translate the address here so the memory can be uniformly + * read with kvm_read_guest(). + */ + if (!hc->fast && is_guest_mode(vcpu)) { + hc->ingpa = translate_nested_gpa(vcpu, hc->ingpa, 0, NULL); + if (unlikely(hc->ingpa == INVALID_GPA)) + return HV_STATUS_INVALID_HYPERCALL_INPUT; + } if (hc->code == HVCALL_FLUSH_VIRTUAL_ADDRESS_LIST || hc->code == HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE) { @@ -1807,14 +1955,17 @@ static u64 kvm_hv_flush_tlb(struct kvm_vcpu *vcpu, struct kvm_hv_hcall *hc) flush.address_space = hc->ingpa; flush.flags = hc->outgpa; flush.processor_mask = sse128_lo(hc->xmm[0]); + consumed_xmm_halves = 1; } else { if (unlikely(kvm_read_guest(kvm, hc->ingpa, &flush, sizeof(flush)))) return HV_STATUS_INVALID_HYPERCALL_INPUT; + data_offset = sizeof(flush); } trace_kvm_hv_flush_tlb(flush.processor_mask, - flush.address_space, flush.flags); + flush.address_space, flush.flags, + is_guest_mode(vcpu)); valid_bank_mask = BIT_ULL(0); sparse_banks[0] = flush.processor_mask; @@ -1834,16 +1985,18 @@ static u64 kvm_hv_flush_tlb(struct kvm_vcpu *vcpu, struct kvm_hv_hcall *hc) flush_ex.flags = hc->outgpa; memcpy(&flush_ex.hv_vp_set, &hc->xmm[0], sizeof(hc->xmm[0])); + consumed_xmm_halves = 2; } else { if (unlikely(kvm_read_guest(kvm, hc->ingpa, &flush_ex, sizeof(flush_ex)))) return HV_STATUS_INVALID_HYPERCALL_INPUT; + data_offset = sizeof(flush_ex); } trace_kvm_hv_flush_tlb_ex(flush_ex.hv_vp_set.valid_bank_mask, flush_ex.hv_vp_set.format, flush_ex.address_space, - flush_ex.flags); + flush_ex.flags, is_guest_mode(vcpu)); valid_bank_mask = flush_ex.hv_vp_set.valid_bank_mask; all_cpus = flush_ex.hv_vp_set.format != @@ -1852,29 +2005,95 @@ static u64 kvm_hv_flush_tlb(struct kvm_vcpu *vcpu, struct kvm_hv_hcall *hc) if (hc->var_cnt != hweight64(valid_bank_mask)) return HV_STATUS_INVALID_HYPERCALL_INPUT; - if (all_cpus) - goto do_flush; + if (!all_cpus) { + if (!hc->var_cnt) + goto ret_success; - if (!hc->var_cnt) - goto ret_success; + if (kvm_get_sparse_vp_set(kvm, hc, sparse_banks, + consumed_xmm_halves, data_offset)) + return HV_STATUS_INVALID_HYPERCALL_INPUT; + } - if (kvm_get_sparse_vp_set(kvm, hc, 2, sparse_banks, - offsetof(struct hv_tlb_flush_ex, - hv_vp_set.bank_contents))) + /* + * Hyper-V TLFS doesn't explicitly forbid non-empty sparse vCPU + * banks (and, thus, non-zero 'var_cnt') for the 'all vCPUs' + * case (HV_GENERIC_SET_ALL). Always adjust data_offset and + * consumed_xmm_halves to make sure TLB flush entries are read + * from the correct offset. + */ + data_offset += hc->var_cnt * sizeof(sparse_banks[0]); + consumed_xmm_halves += hc->var_cnt; + } + + if (hc->code == HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE || + hc->code == HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE_EX || + hc->rep_cnt > ARRAY_SIZE(__tlb_flush_entries)) { + tlb_flush_entries = NULL; + } else { + if (kvm_hv_get_tlb_flush_entries(kvm, hc, __tlb_flush_entries, + consumed_xmm_halves, data_offset)) return HV_STATUS_INVALID_HYPERCALL_INPUT; + tlb_flush_entries = __tlb_flush_entries; } -do_flush: /* * vcpu->arch.cr3 may not be up-to-date for running vCPUs so we can't * analyze it here, flush TLB regardless of the specified address space. */ - if (all_cpus) { - kvm_make_all_cpus_request(kvm, KVM_REQ_TLB_FLUSH_GUEST); - } else { + if (all_cpus && !is_guest_mode(vcpu)) { + kvm_for_each_vcpu(i, v, kvm) { + tlb_flush_fifo = kvm_hv_get_tlb_flush_fifo(v, false); + hv_tlb_flush_enqueue(v, tlb_flush_fifo, + tlb_flush_entries, hc->rep_cnt); + } + + kvm_make_all_cpus_request(kvm, KVM_REQ_HV_TLB_FLUSH); + } else if (!is_guest_mode(vcpu)) { sparse_set_to_vcpu_mask(kvm, sparse_banks, valid_bank_mask, vcpu_mask); - kvm_make_vcpus_request_mask(kvm, KVM_REQ_TLB_FLUSH_GUEST, vcpu_mask); + for_each_set_bit(i, vcpu_mask, KVM_MAX_VCPUS) { + v = kvm_get_vcpu(kvm, i); + if (!v) + continue; + tlb_flush_fifo = kvm_hv_get_tlb_flush_fifo(v, false); + hv_tlb_flush_enqueue(v, tlb_flush_fifo, + tlb_flush_entries, hc->rep_cnt); + } + + kvm_make_vcpus_request_mask(kvm, KVM_REQ_HV_TLB_FLUSH, vcpu_mask); + } else { + struct kvm_vcpu_hv *hv_v; + + bitmap_zero(vcpu_mask, KVM_MAX_VCPUS); + + kvm_for_each_vcpu(i, v, kvm) { + hv_v = to_hv_vcpu(v); + + /* + * The following check races with nested vCPUs entering/exiting + * and/or migrating between L1's vCPUs, however the only case when + * KVM *must* flush the TLB is when the target L2 vCPU keeps + * running on the same L1 vCPU from the moment of the request until + * kvm_hv_flush_tlb() returns. TLB is fully flushed in all other + * cases, e.g. when the target L2 vCPU migrates to a different L1 + * vCPU or when the corresponding L1 vCPU temporary switches to a + * different L2 vCPU while the request is being processed. + */ + if (!hv_v || hv_v->nested.vm_id != hv_vcpu->nested.vm_id) + continue; + + if (!all_cpus && + !hv_is_vp_in_sparse_set(hv_v->nested.vp_id, valid_bank_mask, + sparse_banks)) + continue; + + __set_bit(i, vcpu_mask); + tlb_flush_fifo = kvm_hv_get_tlb_flush_fifo(v, true); + hv_tlb_flush_enqueue(v, tlb_flush_fifo, + tlb_flush_entries, hc->rep_cnt); + } + + kvm_make_vcpus_request_mask(kvm, KVM_REQ_HV_TLB_FLUSH, vcpu_mask); } ret_success: @@ -1883,8 +2102,8 @@ ret_success: ((u64)hc->rep_cnt << HV_HYPERCALL_REP_COMP_OFFSET); } -static void kvm_send_ipi_to_many(struct kvm *kvm, u32 vector, - unsigned long *vcpu_bitmap) +static void kvm_hv_send_ipi_to_many(struct kvm *kvm, u32 vector, + u64 *sparse_banks, u64 valid_bank_mask) { struct kvm_lapic_irq irq = { .delivery_mode = APIC_DM_FIXED, @@ -1894,7 +2113,9 @@ static void kvm_send_ipi_to_many(struct kvm *kvm, u32 vector, unsigned long i; kvm_for_each_vcpu(i, vcpu, kvm) { - if (vcpu_bitmap && !test_bit(i, vcpu_bitmap)) + if (sparse_banks && + !hv_is_vp_in_sparse_set(kvm_hv_get_vpindex(vcpu), + valid_bank_mask, sparse_banks)) continue; /* We fail only when APIC is disabled */ @@ -1904,12 +2125,12 @@ static void kvm_send_ipi_to_many(struct kvm *kvm, u32 vector, static u64 kvm_hv_send_ipi(struct kvm_vcpu *vcpu, struct kvm_hv_hcall *hc) { + struct kvm_vcpu_hv *hv_vcpu = to_hv_vcpu(vcpu); + u64 *sparse_banks = hv_vcpu->sparse_banks; struct kvm *kvm = vcpu->kvm; struct hv_send_ipi_ex send_ipi_ex; struct hv_send_ipi send_ipi; - DECLARE_BITMAP(vcpu_mask, KVM_MAX_VCPUS); u64 valid_bank_mask; - u64 sparse_banks[KVM_HV_MAX_SPARSE_VCPU_SET_BITS]; u32 vector; bool all_cpus; @@ -1959,7 +2180,7 @@ static u64 kvm_hv_send_ipi(struct kvm_vcpu *vcpu, struct kvm_hv_hcall *hc) if (!hc->var_cnt) goto ret_success; - if (kvm_get_sparse_vp_set(kvm, hc, 1, sparse_banks, + if (kvm_get_sparse_vp_set(kvm, hc, sparse_banks, 1, offsetof(struct hv_send_ipi_ex, vp_set.bank_contents))) return HV_STATUS_INVALID_HYPERCALL_INPUT; @@ -1969,13 +2190,10 @@ check_and_send_ipi: if ((vector < HV_IPI_LOW_VECTOR) || (vector > HV_IPI_HIGH_VECTOR)) return HV_STATUS_INVALID_HYPERCALL_INPUT; - if (all_cpus) { - kvm_send_ipi_to_many(kvm, vector, NULL); - } else { - sparse_set_to_vcpu_mask(kvm, sparse_banks, valid_bank_mask, vcpu_mask); - - kvm_send_ipi_to_many(kvm, vector, vcpu_mask); - } + if (all_cpus) + kvm_hv_send_ipi_to_many(kvm, vector, NULL, 0); + else + kvm_hv_send_ipi_to_many(kvm, vector, sparse_banks, valid_bank_mask); ret_success: return HV_STATUS_SUCCESS; @@ -2062,10 +2280,25 @@ static void kvm_hv_hypercall_set_result(struct kvm_vcpu *vcpu, u64 result) static int kvm_hv_hypercall_complete(struct kvm_vcpu *vcpu, u64 result) { + u32 tlb_lock_count = 0; + int ret; + + if (hv_result_success(result) && is_guest_mode(vcpu) && + kvm_hv_is_tlb_flush_hcall(vcpu) && + kvm_read_guest(vcpu->kvm, to_hv_vcpu(vcpu)->nested.pa_page_gpa, + &tlb_lock_count, sizeof(tlb_lock_count))) + result = HV_STATUS_INVALID_HYPERCALL_INPUT; + trace_kvm_hv_hypercall_done(result); kvm_hv_hypercall_set_result(vcpu, result); ++vcpu->stat.hypercalls; - return kvm_skip_emulated_instruction(vcpu); + + ret = kvm_skip_emulated_instruction(vcpu); + + if (tlb_lock_count) + kvm_x86_ops.nested_ops->hv_inject_synthetic_vmexit_post_tlb_flush(vcpu); + + return ret; } static int kvm_hv_hypercall_complete_userspace(struct kvm_vcpu *vcpu) @@ -2502,6 +2735,7 @@ int kvm_get_hv_cpuid(struct kvm_vcpu *vcpu, struct kvm_cpuid2 *cpuid, ent->ebx |= HV_DEBUGGING; ent->edx |= HV_X64_GUEST_DEBUGGING_AVAILABLE; ent->edx |= HV_FEATURE_DEBUG_MSRS_AVAILABLE; + ent->edx |= HV_FEATURE_EXT_GVA_RANGES_FLUSH; /* * Direct Synthetic timers only make sense with in-kernel @@ -2545,6 +2779,7 @@ int kvm_get_hv_cpuid(struct kvm_vcpu *vcpu, struct kvm_cpuid2 *cpuid, case HYPERV_CPUID_NESTED_FEATURES: ent->eax = evmcs_ver; + ent->eax |= HV_X64_NESTED_DIRECT_FLUSH; ent->eax |= HV_X64_NESTED_MSR_BITMAP; ent->ebx |= HV_X64_NESTED_EVMCS1_PERF_GLOBAL_CTRL; break; diff --git a/arch/x86/kvm/hyperv.h b/arch/x86/kvm/hyperv.h index 1030b1b50552..9f96414a31c5 100644 --- a/arch/x86/kvm/hyperv.h +++ b/arch/x86/kvm/hyperv.h @@ -22,6 +22,7 @@ #define __ARCH_X86_KVM_HYPERV_H__ #include <linux/kvm_host.h> +#include "x86.h" /* "Hv#1" signature */ #define HYPERV_CPUID_SIGNATURE_EAX 0x31237648 @@ -107,8 +108,7 @@ int kvm_hv_activate_synic(struct kvm_vcpu *vcpu, bool dont_zero_synic_pages); void kvm_hv_vcpu_uninit(struct kvm_vcpu *vcpu); bool kvm_hv_assist_page_enabled(struct kvm_vcpu *vcpu); -bool kvm_hv_get_assist_page(struct kvm_vcpu *vcpu, - struct hv_vp_assist_page *assist_page); +int kvm_hv_get_assist_page(struct kvm_vcpu *vcpu); static inline struct kvm_vcpu_hv_stimer *to_hv_stimer(struct kvm_vcpu *vcpu, int timer_index) @@ -151,4 +151,64 @@ int kvm_vm_ioctl_hv_eventfd(struct kvm *kvm, struct kvm_hyperv_eventfd *args); int kvm_get_hv_cpuid(struct kvm_vcpu *vcpu, struct kvm_cpuid2 *cpuid, struct kvm_cpuid_entry2 __user *entries); +static inline struct kvm_vcpu_hv_tlb_flush_fifo *kvm_hv_get_tlb_flush_fifo(struct kvm_vcpu *vcpu, + bool is_guest_mode) +{ + struct kvm_vcpu_hv *hv_vcpu = to_hv_vcpu(vcpu); + int i = is_guest_mode ? HV_L2_TLB_FLUSH_FIFO : + HV_L1_TLB_FLUSH_FIFO; + + return &hv_vcpu->tlb_flush_fifo[i]; +} + +static inline void kvm_hv_vcpu_purge_flush_tlb(struct kvm_vcpu *vcpu) +{ + struct kvm_vcpu_hv_tlb_flush_fifo *tlb_flush_fifo; + + if (!to_hv_vcpu(vcpu) || !kvm_check_request(KVM_REQ_HV_TLB_FLUSH, vcpu)) + return; + + tlb_flush_fifo = kvm_hv_get_tlb_flush_fifo(vcpu, is_guest_mode(vcpu)); + + kfifo_reset_out(&tlb_flush_fifo->entries); +} + +static inline bool guest_hv_cpuid_has_l2_tlb_flush(struct kvm_vcpu *vcpu) +{ + struct kvm_vcpu_hv *hv_vcpu = to_hv_vcpu(vcpu); + + return hv_vcpu && + (hv_vcpu->cpuid_cache.nested_eax & HV_X64_NESTED_DIRECT_FLUSH); +} + +static inline bool kvm_hv_is_tlb_flush_hcall(struct kvm_vcpu *vcpu) +{ + struct kvm_vcpu_hv *hv_vcpu = to_hv_vcpu(vcpu); + u16 code; + + if (!hv_vcpu) + return false; + + code = is_64_bit_hypercall(vcpu) ? kvm_rcx_read(vcpu) : + kvm_rax_read(vcpu); + + return (code == HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE || + code == HVCALL_FLUSH_VIRTUAL_ADDRESS_LIST || + code == HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE_EX || + code == HVCALL_FLUSH_VIRTUAL_ADDRESS_LIST_EX); +} + +static inline int kvm_hv_verify_vp_assist(struct kvm_vcpu *vcpu) +{ + if (!to_hv_vcpu(vcpu)) + return 0; + + if (!kvm_hv_assist_page_enabled(vcpu)) + return 0; + + return kvm_hv_get_assist_page(vcpu); +} + +int kvm_hv_vcpu_flush_tlb(struct kvm_vcpu *vcpu); + #endif diff --git a/arch/x86/kvm/irq.c b/arch/x86/kvm/irq.c index f371f1292ca3..d8d50558f165 100644 --- a/arch/x86/kvm/irq.c +++ b/arch/x86/kvm/irq.c @@ -165,3 +165,8 @@ bool kvm_arch_irqfd_allowed(struct kvm *kvm, struct kvm_irqfd *args) return resample ? irqchip_kernel(kvm) : irqchip_in_kernel(kvm); } + +bool kvm_arch_irqchip_in_kernel(struct kvm *kvm) +{ + return irqchip_in_kernel(kvm); +} 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/kvm_cache_regs.h b/arch/x86/kvm/kvm_cache_regs.h index 3febc342360c..c09174f73a34 100644 --- a/arch/x86/kvm/kvm_cache_regs.h +++ b/arch/x86/kvm/kvm_cache_regs.h @@ -200,9 +200,4 @@ static inline bool is_guest_mode(struct kvm_vcpu *vcpu) return vcpu->arch.hflags & HF_GUEST_MASK; } -static inline bool is_smm(struct kvm_vcpu *vcpu) -{ - return vcpu->arch.hflags & HF_SMM_MASK; -} - #endif diff --git a/arch/x86/kvm/kvm_emulate.h b/arch/x86/kvm/kvm_emulate.h index 89246446d6aa..2d9662be8333 100644 --- a/arch/x86/kvm/kvm_emulate.h +++ b/arch/x86/kvm/kvm_emulate.h @@ -117,16 +117,6 @@ struct x86_emulate_ops { struct x86_exception *fault, bool system); /* - * read_phys: Read bytes of standard (non-emulated/special) memory. - * Used for descriptor reading. - * @addr: [IN ] Physical address from which to read. - * @val: [OUT] Value read from memory. - * @bytes: [IN ] Number of bytes to read from memory. - */ - int (*read_phys)(struct x86_emulate_ctxt *ctxt, unsigned long addr, - void *val, unsigned int bytes); - - /* * write_std: Write bytes of standard (non-emulated/special) memory. * Used for descriptor writing. * @addr: [IN ] Linear address to which to write. @@ -209,11 +199,8 @@ struct x86_emulate_ops { int (*cpl)(struct x86_emulate_ctxt *ctxt); void (*get_dr)(struct x86_emulate_ctxt *ctxt, int dr, ulong *dest); int (*set_dr)(struct x86_emulate_ctxt *ctxt, int dr, ulong value); - u64 (*get_smbase)(struct x86_emulate_ctxt *ctxt); - void (*set_smbase)(struct x86_emulate_ctxt *ctxt, u64 smbase); int (*set_msr_with_filter)(struct x86_emulate_ctxt *ctxt, u32 msr_index, u64 data); int (*get_msr_with_filter)(struct x86_emulate_ctxt *ctxt, u32 msr_index, u64 *pdata); - int (*set_msr)(struct x86_emulate_ctxt *ctxt, u32 msr_index, u64 data); int (*get_msr)(struct x86_emulate_ctxt *ctxt, u32 msr_index, u64 *pdata); int (*check_pmc)(struct x86_emulate_ctxt *ctxt, u32 pmc); int (*read_pmc)(struct x86_emulate_ctxt *ctxt, u32 pmc, u64 *pdata); @@ -234,8 +221,7 @@ struct x86_emulate_ops { void (*set_nmi_mask)(struct x86_emulate_ctxt *ctxt, bool masked); unsigned (*get_hflags)(struct x86_emulate_ctxt *ctxt); - void (*exiting_smm)(struct x86_emulate_ctxt *ctxt); - int (*leave_smm)(struct x86_emulate_ctxt *ctxt, const char *smstate); + int (*leave_smm)(struct x86_emulate_ctxt *ctxt); void (*triple_fault)(struct x86_emulate_ctxt *ctxt); int (*set_xcr)(struct x86_emulate_ctxt *ctxt, u32 index, u64 xcr); }; @@ -292,7 +278,6 @@ enum x86emul_mode { /* These match some of the HF_* flags defined in kvm_host.h */ #define X86EMUL_GUEST_MASK (1 << 5) /* VCPU is in guest-mode */ #define X86EMUL_SMM_MASK (1 << 6) -#define X86EMUL_SMM_INSIDE_NMI_MASK (1 << 7) /* * fastop functions are declared as taking a never-defined fastop parameter, @@ -526,4 +511,35 @@ void emulator_invalidate_register_cache(struct x86_emulate_ctxt *ctxt); void emulator_writeback_register_cache(struct x86_emulate_ctxt *ctxt); bool emulator_can_use_gpa(struct x86_emulate_ctxt *ctxt); +static inline ulong reg_read(struct x86_emulate_ctxt *ctxt, unsigned nr) +{ + if (KVM_EMULATOR_BUG_ON(nr >= NR_EMULATOR_GPRS, ctxt)) + nr &= NR_EMULATOR_GPRS - 1; + + if (!(ctxt->regs_valid & (1 << nr))) { + ctxt->regs_valid |= 1 << nr; + ctxt->_regs[nr] = ctxt->ops->read_gpr(ctxt, nr); + } + return ctxt->_regs[nr]; +} + +static inline ulong *reg_write(struct x86_emulate_ctxt *ctxt, unsigned nr) +{ + if (KVM_EMULATOR_BUG_ON(nr >= NR_EMULATOR_GPRS, ctxt)) + nr &= NR_EMULATOR_GPRS - 1; + + BUILD_BUG_ON(sizeof(ctxt->regs_dirty) * BITS_PER_BYTE < NR_EMULATOR_GPRS); + BUILD_BUG_ON(sizeof(ctxt->regs_valid) * BITS_PER_BYTE < NR_EMULATOR_GPRS); + + ctxt->regs_valid |= 1 << nr; + ctxt->regs_dirty |= 1 << nr; + return &ctxt->_regs[nr]; +} + +static inline ulong *reg_rmw(struct x86_emulate_ctxt *ctxt, unsigned nr) +{ + reg_read(ctxt, nr); + return reg_write(ctxt, nr); +} + #endif /* _ASM_X86_KVM_X86_EMULATE_H */ diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index d7639d126e6c..1bb63746e991 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -42,6 +42,7 @@ #include "x86.h" #include "cpuid.h" #include "hyperv.h" +#include "smm.h" #ifndef CONFIG_X86_64 #define mod_64(x, y) ((x) - (y) * div64_u64(x, y)) @@ -1170,9 +1171,10 @@ static int __apic_accept_irq(struct kvm_lapic *apic, int delivery_mode, break; case APIC_DM_SMI: - result = 1; - kvm_make_request(KVM_REQ_SMI, vcpu); - kvm_vcpu_kick(vcpu); + if (!kvm_inject_smi(vcpu)) { + kvm_vcpu_kick(vcpu); + result = 1; + } break; case APIC_DM_NMI: diff --git a/arch/x86/kvm/lapic.h b/arch/x86/kvm/lapic.h index a5ac4a5a5179..28e3769066e2 100644 --- a/arch/x86/kvm/lapic.h +++ b/arch/x86/kvm/lapic.h @@ -7,7 +7,7 @@ #include <linux/kvm_host.h> #include "hyperv.h" -#include "kvm_cache_regs.h" +#include "smm.h" #define KVM_APIC_INIT 0 #define KVM_APIC_SIPI 1 diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index 6f81539061d6..4736d7849c60 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -22,6 +22,7 @@ #include "tdp_mmu.h" #include "x86.h" #include "kvm_cache_regs.h" +#include "smm.h" #include "kvm_emulate.h" #include "cpuid.h" #include "spte.h" @@ -802,15 +803,31 @@ static void account_shadowed(struct kvm *kvm, struct kvm_mmu_page *sp) kvm_flush_remote_tlbs_with_address(kvm, gfn, 1); } -void account_huge_nx_page(struct kvm *kvm, struct kvm_mmu_page *sp) +void track_possible_nx_huge_page(struct kvm *kvm, struct kvm_mmu_page *sp) { - if (sp->lpage_disallowed) + /* + * If it's possible to replace the shadow page with an NX huge page, + * i.e. if the shadow page is the only thing currently preventing KVM + * from using a huge page, add the shadow page to the list of "to be + * zapped for NX recovery" pages. Note, the shadow page can already be + * on the list if KVM is reusing an existing shadow page, i.e. if KVM + * links a shadow page at multiple points. + */ + if (!list_empty(&sp->possible_nx_huge_page_link)) return; ++kvm->stat.nx_lpage_splits; - list_add_tail(&sp->lpage_disallowed_link, - &kvm->arch.lpage_disallowed_mmu_pages); - sp->lpage_disallowed = true; + list_add_tail(&sp->possible_nx_huge_page_link, + &kvm->arch.possible_nx_huge_pages); +} + +static void account_nx_huge_page(struct kvm *kvm, struct kvm_mmu_page *sp, + bool nx_huge_page_possible) +{ + sp->nx_huge_page_disallowed = true; + + if (nx_huge_page_possible) + track_possible_nx_huge_page(kvm, sp); } static void unaccount_shadowed(struct kvm *kvm, struct kvm_mmu_page *sp) @@ -830,11 +847,20 @@ static void unaccount_shadowed(struct kvm *kvm, struct kvm_mmu_page *sp) kvm_mmu_gfn_allow_lpage(slot, gfn); } -void unaccount_huge_nx_page(struct kvm *kvm, struct kvm_mmu_page *sp) +void untrack_possible_nx_huge_page(struct kvm *kvm, struct kvm_mmu_page *sp) { + if (list_empty(&sp->possible_nx_huge_page_link)) + return; + --kvm->stat.nx_lpage_splits; - sp->lpage_disallowed = false; - list_del(&sp->lpage_disallowed_link); + list_del_init(&sp->possible_nx_huge_page_link); +} + +static void unaccount_nx_huge_page(struct kvm *kvm, struct kvm_mmu_page *sp) +{ + sp->nx_huge_page_disallowed = false; + + untrack_possible_nx_huge_page(kvm, sp); } static struct kvm_memory_slot * @@ -1645,7 +1671,7 @@ static int is_empty_shadow_page(u64 *spt) u64 *pos; u64 *end; - for (pos = spt, end = pos + PAGE_SIZE / sizeof(u64); pos != end; pos++) + for (pos = spt, end = pos + SPTE_ENT_PER_PAGE; pos != end; pos++) if (is_shadow_present_pte(*pos)) { printk(KERN_ERR "%s: %p %llx\n", __func__, pos, *pos); @@ -1793,7 +1819,7 @@ static int __mmu_unsync_walk(struct kvm_mmu_page *sp, continue; } - child = to_shadow_page(ent & SPTE_BASE_ADDR_MASK); + child = spte_to_child_sp(ent); if (child->unsync_children) { if (mmu_pages_add(pvec, child, i)) @@ -1894,7 +1920,7 @@ static bool is_obsolete_sp(struct kvm *kvm, struct kvm_mmu_page *sp) if (sp->role.invalid) return true; - /* TDP MMU pages due not use the MMU generation. */ + /* TDP MMU pages do not use the MMU generation. */ return !sp->tdp_mmu_page && unlikely(sp->mmu_valid_gen != kvm->arch.mmu_valid_gen); } @@ -2129,6 +2155,8 @@ static struct kvm_mmu_page *kvm_mmu_alloc_shadow_page(struct kvm *kvm, set_page_private(virt_to_page(sp->spt), (unsigned long)sp); + INIT_LIST_HEAD(&sp->possible_nx_huge_page_link); + /* * active_mmu_pages must be a FIFO list, as kvm_zap_obsolete_pages() * depends on valid pages being added to the head of the list. See @@ -2350,7 +2378,7 @@ static void validate_direct_spte(struct kvm_vcpu *vcpu, u64 *sptep, * so we should update the spte at this point to get * a new sp with the correct access. */ - child = to_shadow_page(*sptep & SPTE_BASE_ADDR_MASK); + child = spte_to_child_sp(*sptep); if (child->role.access == direct_access) return; @@ -2371,7 +2399,7 @@ static int mmu_page_zap_pte(struct kvm *kvm, struct kvm_mmu_page *sp, if (is_last_spte(pte, sp->role.level)) { drop_spte(kvm, spte); } else { - child = to_shadow_page(pte & SPTE_BASE_ADDR_MASK); + child = spte_to_child_sp(pte); drop_parent_pte(child, spte); /* @@ -2486,8 +2514,8 @@ static bool __kvm_mmu_prepare_zap_page(struct kvm *kvm, zapped_root = !is_obsolete_sp(kvm, sp); } - if (sp->lpage_disallowed) - unaccount_huge_nx_page(kvm, sp); + if (sp->nx_huge_page_disallowed) + unaccount_nx_huge_page(kvm, sp); sp->role.invalid = 1; @@ -2810,7 +2838,7 @@ static int mmu_set_spte(struct kvm_vcpu *vcpu, struct kvm_memory_slot *slot, struct kvm_mmu_page *child; u64 pte = *sptep; - child = to_shadow_page(pte & SPTE_BASE_ADDR_MASK); + child = spte_to_child_sp(pte); drop_parent_pte(child, sptep); flush = true; } else if (pfn != spte_to_pfn(*sptep)) { @@ -3084,7 +3112,8 @@ void disallowed_hugepage_adjust(struct kvm_page_fault *fault, u64 spte, int cur_ if (cur_level > PG_LEVEL_4K && cur_level == fault->goal_level && is_shadow_present_pte(spte) && - !is_large_pte(spte)) { + !is_large_pte(spte) && + spte_to_child_sp(spte)->nx_huge_page_disallowed) { /* * A small SPTE exists for this pfn, but FNAME(fetch) * and __direct_map would like to create a large PTE @@ -3126,9 +3155,9 @@ static int __direct_map(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault) continue; link_shadow_page(vcpu, it.sptep, sp); - if (fault->is_tdp && fault->huge_page_disallowed && - fault->req_level >= it.level) - account_huge_nx_page(vcpu->kvm, sp); + if (fault->huge_page_disallowed) + account_nx_huge_page(vcpu->kvm, sp, + fault->req_level >= it.level); } if (WARN_ON_ONCE(it.level != fault->goal_level)) @@ -3148,8 +3177,13 @@ static void kvm_send_hwpoison_signal(unsigned long address, struct task_struct * send_sig_mceerr(BUS_MCEERR_AR, (void __user *)address, PAGE_SHIFT, tsk); } -static int kvm_handle_bad_page(struct kvm_vcpu *vcpu, gfn_t gfn, kvm_pfn_t pfn) +static int kvm_handle_error_pfn(struct kvm_vcpu *vcpu, gfn_t gfn, kvm_pfn_t pfn) { + if (is_sigpending_pfn(pfn)) { + kvm_handle_signal_exit(vcpu); + return -EINTR; + } + /* * Do not cache the mmio info caused by writing the readonly gfn * into the spte otherwise read access on readonly gfn also can @@ -3171,7 +3205,7 @@ static int handle_abnormal_pfn(struct kvm_vcpu *vcpu, struct kvm_page_fault *fau { /* The pfn is invalid, report the error! */ if (unlikely(is_error_pfn(fault->pfn))) - return kvm_handle_bad_page(vcpu, fault->gfn, fault->pfn); + return kvm_handle_error_pfn(vcpu, fault->gfn, fault->pfn); if (unlikely(!fault->slot)) { gva_t gva = fault->is_tdp ? 0 : fault->addr; @@ -3422,7 +3456,11 @@ static void mmu_free_root_page(struct kvm *kvm, hpa_t *root_hpa, if (!VALID_PAGE(*root_hpa)) return; - sp = to_shadow_page(*root_hpa & SPTE_BASE_ADDR_MASK); + /* + * The "root" may be a special root, e.g. a PAE entry, treat it as a + * SPTE to ensure any non-PA bits are dropped. + */ + sp = spte_to_child_sp(*root_hpa); if (WARN_ON(!sp)) return; @@ -3907,8 +3945,7 @@ void kvm_mmu_sync_roots(struct kvm_vcpu *vcpu) hpa_t root = vcpu->arch.mmu->pae_root[i]; if (IS_VALID_PAE_ROOT(root)) { - root &= SPTE_BASE_ADDR_MASK; - sp = to_shadow_page(root); + sp = spte_to_child_sp(root); mmu_sync_children(vcpu, sp, true); } } @@ -4169,7 +4206,7 @@ static int kvm_faultin_pfn(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault) } async = false; - fault->pfn = __gfn_to_pfn_memslot(slot, fault->gfn, false, &async, + fault->pfn = __gfn_to_pfn_memslot(slot, fault->gfn, false, false, &async, fault->write, &fault->map_writable, &fault->hva); if (!async) @@ -4186,7 +4223,12 @@ static int kvm_faultin_pfn(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault) } } - fault->pfn = __gfn_to_pfn_memslot(slot, fault->gfn, false, NULL, + /* + * Allow gup to bail on pending non-fatal signals when it's also allowed + * to wait for IO. Note, gup always bails if it is unable to quickly + * get a page and a fatal signal, i.e. SIGKILL, is pending. + */ + fault->pfn = __gfn_to_pfn_memslot(slot, fault->gfn, false, true, NULL, fault->write, &fault->map_writable, &fault->hva); return RET_PF_CONTINUE; @@ -5971,7 +6013,7 @@ int kvm_mmu_init_vm(struct kvm *kvm) INIT_LIST_HEAD(&kvm->arch.active_mmu_pages); INIT_LIST_HEAD(&kvm->arch.zapped_obsolete_pages); - INIT_LIST_HEAD(&kvm->arch.lpage_disallowed_mmu_pages); + INIT_LIST_HEAD(&kvm->arch.possible_nx_huge_pages); spin_lock_init(&kvm->arch.mmu_unsync_pages_lock); r = kvm_mmu_init_tdp_mmu(kvm); @@ -6656,7 +6698,7 @@ static int set_nx_huge_pages(const char *val, const struct kernel_param *kp) kvm_mmu_zap_all_fast(kvm); mutex_unlock(&kvm->slots_lock); - wake_up_process(kvm->arch.nx_lpage_recovery_thread); + wake_up_process(kvm->arch.nx_huge_page_recovery_thread); } mutex_unlock(&kvm_lock); } @@ -6788,7 +6830,7 @@ static int set_nx_huge_pages_recovery_param(const char *val, const struct kernel mutex_lock(&kvm_lock); list_for_each_entry(kvm, &vm_list, vm_list) - wake_up_process(kvm->arch.nx_lpage_recovery_thread); + wake_up_process(kvm->arch.nx_huge_page_recovery_thread); mutex_unlock(&kvm_lock); } @@ -6796,9 +6838,10 @@ static int set_nx_huge_pages_recovery_param(const char *val, const struct kernel return err; } -static void kvm_recover_nx_lpages(struct kvm *kvm) +static void kvm_recover_nx_huge_pages(struct kvm *kvm) { unsigned long nx_lpage_splits = kvm->stat.nx_lpage_splits; + struct kvm_memory_slot *slot; int rcu_idx; struct kvm_mmu_page *sp; unsigned int ratio; @@ -6819,24 +6862,55 @@ static void kvm_recover_nx_lpages(struct kvm *kvm) ratio = READ_ONCE(nx_huge_pages_recovery_ratio); to_zap = ratio ? DIV_ROUND_UP(nx_lpage_splits, ratio) : 0; for ( ; to_zap; --to_zap) { - if (list_empty(&kvm->arch.lpage_disallowed_mmu_pages)) + if (list_empty(&kvm->arch.possible_nx_huge_pages)) break; /* * We use a separate list instead of just using active_mmu_pages - * because the number of lpage_disallowed pages is expected to - * be relatively small compared to the total. + * because the number of shadow pages that be replaced with an + * NX huge page is expected to be relatively small compared to + * the total number of shadow pages. And because the TDP MMU + * doesn't use active_mmu_pages. */ - sp = list_first_entry(&kvm->arch.lpage_disallowed_mmu_pages, + sp = list_first_entry(&kvm->arch.possible_nx_huge_pages, struct kvm_mmu_page, - lpage_disallowed_link); - WARN_ON_ONCE(!sp->lpage_disallowed); - if (is_tdp_mmu_page(sp)) { + possible_nx_huge_page_link); + WARN_ON_ONCE(!sp->nx_huge_page_disallowed); + WARN_ON_ONCE(!sp->role.direct); + + /* + * Unaccount and do not attempt to recover any NX Huge Pages + * that are being dirty tracked, as they would just be faulted + * back in as 4KiB pages. The NX Huge Pages in this slot will be + * recovered, along with all the other huge pages in the slot, + * when dirty logging is disabled. + * + * Since gfn_to_memslot() is relatively expensive, it helps to + * skip it if it the test cannot possibly return true. On the + * other hand, if any memslot has logging enabled, chances are + * good that all of them do, in which case unaccount_nx_huge_page() + * is much cheaper than zapping the page. + * + * If a memslot update is in progress, reading an incorrect value + * of kvm->nr_memslots_dirty_logging is not a problem: if it is + * becoming zero, gfn_to_memslot() will be done unnecessarily; if + * it is becoming nonzero, the page will be zapped unnecessarily. + * Either way, this only affects efficiency in racy situations, + * and not correctness. + */ + slot = NULL; + if (atomic_read(&kvm->nr_memslots_dirty_logging)) { + slot = gfn_to_memslot(kvm, sp->gfn); + WARN_ON_ONCE(!slot); + } + + if (slot && kvm_slot_dirty_track_enabled(slot)) + unaccount_nx_huge_page(kvm, sp); + else if (is_tdp_mmu_page(sp)) flush |= kvm_tdp_mmu_zap_sp(kvm, sp); - } else { + else kvm_mmu_prepare_zap_page(kvm, sp, &invalid_list); - WARN_ON_ONCE(sp->lpage_disallowed); - } + WARN_ON_ONCE(sp->nx_huge_page_disallowed); if (need_resched() || rwlock_needbreak(&kvm->mmu_lock)) { kvm_mmu_remote_flush_or_zap(kvm, &invalid_list, flush); @@ -6856,7 +6930,7 @@ static void kvm_recover_nx_lpages(struct kvm *kvm) srcu_read_unlock(&kvm->srcu, rcu_idx); } -static long get_nx_lpage_recovery_timeout(u64 start_time) +static long get_nx_huge_page_recovery_timeout(u64 start_time) { bool enabled; uint period; @@ -6867,19 +6941,19 @@ static long get_nx_lpage_recovery_timeout(u64 start_time) : MAX_SCHEDULE_TIMEOUT; } -static int kvm_nx_lpage_recovery_worker(struct kvm *kvm, uintptr_t data) +static int kvm_nx_huge_page_recovery_worker(struct kvm *kvm, uintptr_t data) { u64 start_time; long remaining_time; while (true) { start_time = get_jiffies_64(); - remaining_time = get_nx_lpage_recovery_timeout(start_time); + remaining_time = get_nx_huge_page_recovery_timeout(start_time); set_current_state(TASK_INTERRUPTIBLE); while (!kthread_should_stop() && remaining_time > 0) { schedule_timeout(remaining_time); - remaining_time = get_nx_lpage_recovery_timeout(start_time); + remaining_time = get_nx_huge_page_recovery_timeout(start_time); set_current_state(TASK_INTERRUPTIBLE); } @@ -6888,7 +6962,7 @@ static int kvm_nx_lpage_recovery_worker(struct kvm *kvm, uintptr_t data) if (kthread_should_stop()) return 0; - kvm_recover_nx_lpages(kvm); + kvm_recover_nx_huge_pages(kvm); } } @@ -6896,17 +6970,17 @@ int kvm_mmu_post_init_vm(struct kvm *kvm) { int err; - err = kvm_vm_create_worker_thread(kvm, kvm_nx_lpage_recovery_worker, 0, + err = kvm_vm_create_worker_thread(kvm, kvm_nx_huge_page_recovery_worker, 0, "kvm-nx-lpage-recovery", - &kvm->arch.nx_lpage_recovery_thread); + &kvm->arch.nx_huge_page_recovery_thread); if (!err) - kthread_unpark(kvm->arch.nx_lpage_recovery_thread); + kthread_unpark(kvm->arch.nx_huge_page_recovery_thread); return err; } void kvm_mmu_pre_destroy_vm(struct kvm *kvm) { - if (kvm->arch.nx_lpage_recovery_thread) - kthread_stop(kvm->arch.nx_lpage_recovery_thread); + if (kvm->arch.nx_huge_page_recovery_thread) + kthread_stop(kvm->arch.nx_huge_page_recovery_thread); } diff --git a/arch/x86/kvm/mmu/mmu_internal.h b/arch/x86/kvm/mmu/mmu_internal.h index 582def531d4d..dbaf6755c5a7 100644 --- a/arch/x86/kvm/mmu/mmu_internal.h +++ b/arch/x86/kvm/mmu/mmu_internal.h @@ -57,7 +57,13 @@ struct kvm_mmu_page { bool tdp_mmu_page; bool unsync; u8 mmu_valid_gen; - bool lpage_disallowed; /* Can't be replaced by an equiv large page */ + + /* + * The shadow page can't be replaced by an equivalent huge page + * because it is being used to map an executable page in the guest + * and the NX huge page mitigation is enabled. + */ + bool nx_huge_page_disallowed; /* * The following two entries are used to key the shadow page in the @@ -100,7 +106,14 @@ struct kvm_mmu_page { }; }; - struct list_head lpage_disallowed_link; + /* + * Tracks shadow pages that, if zapped, would allow KVM to create an NX + * huge page. A shadow page will have nx_huge_page_disallowed set but + * not be on the list if a huge page is disallowed for other reasons, + * e.g. because KVM is shadowing a PTE at the same gfn, the memslot + * isn't properly aligned, etc... + */ + struct list_head possible_nx_huge_page_link; #ifdef CONFIG_X86_32 /* * Used out of the mmu-lock to avoid reading spte values while an @@ -120,18 +133,6 @@ struct kvm_mmu_page { extern struct kmem_cache *mmu_page_header_cache; -static inline struct kvm_mmu_page *to_shadow_page(hpa_t shadow_page) -{ - struct page *page = pfn_to_page(shadow_page >> PAGE_SHIFT); - - return (struct kvm_mmu_page *)page_private(page); -} - -static inline struct kvm_mmu_page *sptep_to_sp(u64 *sptep) -{ - return to_shadow_page(__pa(sptep)); -} - static inline int kvm_mmu_role_as_id(union kvm_mmu_page_role role) { return role.smm ? 1 : 0; @@ -315,7 +316,7 @@ void disallowed_hugepage_adjust(struct kvm_page_fault *fault, u64 spte, int cur_ void *mmu_memory_cache_alloc(struct kvm_mmu_memory_cache *mc); -void account_huge_nx_page(struct kvm *kvm, struct kvm_mmu_page *sp); -void unaccount_huge_nx_page(struct kvm *kvm, struct kvm_mmu_page *sp); +void track_possible_nx_huge_page(struct kvm *kvm, struct kvm_mmu_page *sp); +void untrack_possible_nx_huge_page(struct kvm *kvm, struct kvm_mmu_page *sp); #endif /* __KVM_X86_MMU_INTERNAL_H */ diff --git a/arch/x86/kvm/mmu/paging_tmpl.h b/arch/x86/kvm/mmu/paging_tmpl.h index 5ab5f94dcb6f..0f6455072055 100644 --- a/arch/x86/kvm/mmu/paging_tmpl.h +++ b/arch/x86/kvm/mmu/paging_tmpl.h @@ -713,9 +713,9 @@ static int FNAME(fetch)(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault, continue; link_shadow_page(vcpu, it.sptep, sp); - if (fault->huge_page_disallowed && - fault->req_level >= it.level) - account_huge_nx_page(vcpu->kvm, sp); + if (fault->huge_page_disallowed) + account_nx_huge_page(vcpu->kvm, sp, + fault->req_level >= it.level); } if (WARN_ON_ONCE(it.level != fault->goal_level)) diff --git a/arch/x86/kvm/mmu/spte.c b/arch/x86/kvm/mmu/spte.c index 2e08b2a45361..c0fd7e049b4e 100644 --- a/arch/x86/kvm/mmu/spte.c +++ b/arch/x86/kvm/mmu/spte.c @@ -161,6 +161,18 @@ bool make_spte(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp, if (!prefetch) spte |= spte_shadow_accessed_mask(spte); + /* + * For simplicity, enforce the NX huge page mitigation even if not + * strictly necessary. KVM could ignore the mitigation if paging is + * disabled in the guest, as the guest doesn't have an page tables to + * abuse. But to safely ignore the mitigation, KVM would have to + * ensure a new MMU is loaded (or all shadow pages zapped) when CR0.PG + * is toggled on, and that's a net negative for performance when TDP is + * enabled. When TDP is disabled, KVM will always switch to a new MMU + * when CR0.PG is toggled, but leveraging that to ignore the mitigation + * would tie make_spte() further to vCPU/MMU state, and add complexity + * just to optimize a mode that is anything but performance critical. + */ if (level > PG_LEVEL_4K && (pte_access & ACC_EXEC_MASK) && is_nx_huge_page_enabled(vcpu->kvm)) { pte_access &= ~ACC_EXEC_MASK; diff --git a/arch/x86/kvm/mmu/spte.h b/arch/x86/kvm/mmu/spte.h index 7670c13ce251..1f03701b943a 100644 --- a/arch/x86/kvm/mmu/spte.h +++ b/arch/x86/kvm/mmu/spte.h @@ -188,7 +188,7 @@ extern u64 __read_mostly shadow_nonpresent_or_rsvd_mask; * should not modify the SPTE. * * Use a semi-arbitrary value that doesn't set RWX bits, i.e. is not-present on - * bot AMD and Intel CPUs, and doesn't set PFN bits, i.e. doesn't create a L1TF + * both AMD and Intel CPUs, and doesn't set PFN bits, i.e. doesn't create a L1TF * vulnerability. Use only low bits to avoid 64-bit immediates. * * Only used by the TDP MMU. @@ -219,6 +219,23 @@ static inline int spte_index(u64 *sptep) */ extern u64 __read_mostly shadow_nonpresent_or_rsvd_lower_gfn_mask; +static inline struct kvm_mmu_page *to_shadow_page(hpa_t shadow_page) +{ + struct page *page = pfn_to_page((shadow_page) >> PAGE_SHIFT); + + return (struct kvm_mmu_page *)page_private(page); +} + +static inline struct kvm_mmu_page *spte_to_child_sp(u64 spte) +{ + return to_shadow_page(spte & SPTE_BASE_ADDR_MASK); +} + +static inline struct kvm_mmu_page *sptep_to_sp(u64 *sptep) +{ + return to_shadow_page(__pa(sptep)); +} + static inline bool is_mmio_spte(u64 spte) { return (spte & shadow_mmio_mask) == shadow_mmio_value && diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c index 672f0432d777..771210ce5181 100644 --- a/arch/x86/kvm/mmu/tdp_mmu.c +++ b/arch/x86/kvm/mmu/tdp_mmu.c @@ -29,7 +29,6 @@ int kvm_mmu_init_tdp_mmu(struct kvm *kvm) kvm->arch.tdp_mmu_enabled = true; INIT_LIST_HEAD(&kvm->arch.tdp_mmu_roots); spin_lock_init(&kvm->arch.tdp_mmu_pages_lock); - INIT_LIST_HEAD(&kvm->arch.tdp_mmu_pages); kvm->arch.tdp_mmu_zap_wq = wq; return 1; } @@ -54,7 +53,7 @@ void kvm_mmu_uninit_tdp_mmu(struct kvm *kvm) /* Also waits for any queued work items. */ destroy_workqueue(kvm->arch.tdp_mmu_zap_wq); - WARN_ON(!list_empty(&kvm->arch.tdp_mmu_pages)); + WARN_ON(atomic64_read(&kvm->arch.tdp_mmu_pages)); WARN_ON(!list_empty(&kvm->arch.tdp_mmu_roots)); /* @@ -284,6 +283,8 @@ static struct kvm_mmu_page *tdp_mmu_alloc_sp(struct kvm_vcpu *vcpu) static void tdp_mmu_init_sp(struct kvm_mmu_page *sp, tdp_ptep_t sptep, gfn_t gfn, union kvm_mmu_page_role role) { + INIT_LIST_HEAD(&sp->possible_nx_huge_page_link); + set_page_private(virt_to_page(sp->spt), (unsigned long)sp); sp->role = role; @@ -375,11 +376,13 @@ static void handle_changed_spte_dirty_log(struct kvm *kvm, int as_id, gfn_t gfn, static void tdp_account_mmu_page(struct kvm *kvm, struct kvm_mmu_page *sp) { kvm_account_pgtable_pages((void *)sp->spt, +1); + atomic64_inc(&kvm->arch.tdp_mmu_pages); } static void tdp_unaccount_mmu_page(struct kvm *kvm, struct kvm_mmu_page *sp) { kvm_account_pgtable_pages((void *)sp->spt, -1); + atomic64_dec(&kvm->arch.tdp_mmu_pages); } /** @@ -395,14 +398,17 @@ static void tdp_mmu_unlink_sp(struct kvm *kvm, struct kvm_mmu_page *sp, bool shared) { tdp_unaccount_mmu_page(kvm, sp); + + if (!sp->nx_huge_page_disallowed) + return; + if (shared) spin_lock(&kvm->arch.tdp_mmu_pages_lock); else lockdep_assert_held_write(&kvm->mmu_lock); - list_del(&sp->link); - if (sp->lpage_disallowed) - unaccount_huge_nx_page(kvm, sp); + sp->nx_huge_page_disallowed = false; + untrack_possible_nx_huge_page(kvm, sp); if (shared) spin_unlock(&kvm->arch.tdp_mmu_pages_lock); @@ -1116,16 +1122,13 @@ static int tdp_mmu_map_handle_target_level(struct kvm_vcpu *vcpu, * @kvm: kvm instance * @iter: a tdp_iter instance currently on the SPTE that should be set * @sp: The new TDP page table to install. - * @account_nx: True if this page table is being installed to split a - * non-executable huge page. * @shared: This operation is running under the MMU lock in read mode. * * Returns: 0 if the new page table was installed. Non-0 if the page table * could not be installed (e.g. the atomic compare-exchange failed). */ static int tdp_mmu_link_sp(struct kvm *kvm, struct tdp_iter *iter, - struct kvm_mmu_page *sp, bool account_nx, - bool shared) + struct kvm_mmu_page *sp, bool shared) { u64 spte = make_nonleaf_spte(sp->spt, !kvm_ad_enabled()); int ret = 0; @@ -1138,16 +1141,14 @@ static int tdp_mmu_link_sp(struct kvm *kvm, struct tdp_iter *iter, tdp_mmu_set_spte(kvm, iter, spte); } - spin_lock(&kvm->arch.tdp_mmu_pages_lock); - list_add(&sp->link, &kvm->arch.tdp_mmu_pages); - if (account_nx) - account_huge_nx_page(kvm, sp); - spin_unlock(&kvm->arch.tdp_mmu_pages_lock); tdp_account_mmu_page(kvm, sp); return 0; } +static int tdp_mmu_split_huge_page(struct kvm *kvm, struct tdp_iter *iter, + struct kvm_mmu_page *sp, bool shared); + /* * Handle a TDP page fault (NPT/EPT violation/misconfiguration) by installing * page tables and SPTEs to translate the faulting guest physical address. @@ -1155,9 +1156,10 @@ static int tdp_mmu_link_sp(struct kvm *kvm, struct tdp_iter *iter, int kvm_tdp_mmu_map(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault) { struct kvm_mmu *mmu = vcpu->arch.mmu; + struct kvm *kvm = vcpu->kvm; struct tdp_iter iter; struct kvm_mmu_page *sp; - int ret; + int ret = RET_PF_RETRY; kvm_mmu_hugepage_adjust(vcpu, fault); @@ -1166,6 +1168,8 @@ int kvm_tdp_mmu_map(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault) rcu_read_lock(); tdp_mmu_for_each_pte(iter, mmu, fault->gfn, fault->gfn + 1) { + int r; + if (fault->nx_huge_page_workaround_enabled) disallowed_hugepage_adjust(fault, iter.old_spte, iter.level); @@ -1173,57 +1177,52 @@ int kvm_tdp_mmu_map(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault) break; /* - * If there is an SPTE mapping a large page at a higher level - * than the target, that SPTE must be cleared and replaced - * with a non-leaf SPTE. + * If SPTE has been frozen by another thread, just give up and + * retry, avoiding unnecessary page table allocation and free. */ - if (is_shadow_present_pte(iter.old_spte) && - is_large_pte(iter.old_spte)) { - if (tdp_mmu_zap_spte_atomic(vcpu->kvm, &iter)) - break; + if (is_removed_spte(iter.old_spte)) + goto retry; - /* - * The iter must explicitly re-read the spte here - * because the new value informs the !present - * path below. - */ - iter.old_spte = kvm_tdp_mmu_read_spte(iter.sptep); - } + /* Step down into the lower level page table if it exists. */ + if (is_shadow_present_pte(iter.old_spte) && + !is_large_pte(iter.old_spte)) + continue; - if (!is_shadow_present_pte(iter.old_spte)) { - bool account_nx = fault->huge_page_disallowed && - fault->req_level >= iter.level; + /* + * The SPTE is either non-present or points to a huge page that + * needs to be split. + */ + sp = tdp_mmu_alloc_sp(vcpu); + tdp_mmu_init_child_sp(sp, &iter); - /* - * If SPTE has been frozen by another thread, just - * give up and retry, avoiding unnecessary page table - * allocation and free. - */ - if (is_removed_spte(iter.old_spte)) - break; + sp->nx_huge_page_disallowed = fault->huge_page_disallowed; - sp = tdp_mmu_alloc_sp(vcpu); - tdp_mmu_init_child_sp(sp, &iter); + if (is_shadow_present_pte(iter.old_spte)) + r = tdp_mmu_split_huge_page(kvm, &iter, sp, true); + else + r = tdp_mmu_link_sp(kvm, &iter, sp, true); - if (tdp_mmu_link_sp(vcpu->kvm, &iter, sp, account_nx, true)) { - tdp_mmu_free_sp(sp); - break; - } + /* + * Also force the guest to retry the access if the upper level SPTEs + * aren't in place. + */ + if (r) { + tdp_mmu_free_sp(sp); + goto retry; } - } - /* - * Force the guest to retry the access if the upper level SPTEs aren't - * in place, or if the target leaf SPTE is frozen by another CPU. - */ - if (iter.level != fault->goal_level || is_removed_spte(iter.old_spte)) { - rcu_read_unlock(); - return RET_PF_RETRY; + if (fault->huge_page_disallowed && + fault->req_level >= iter.level) { + spin_lock(&kvm->arch.tdp_mmu_pages_lock); + track_possible_nx_huge_page(kvm, sp); + spin_unlock(&kvm->arch.tdp_mmu_pages_lock); + } } ret = tdp_mmu_map_handle_target_level(vcpu, fault, &iter); - rcu_read_unlock(); +retry: + rcu_read_unlock(); return ret; } @@ -1472,6 +1471,7 @@ static struct kvm_mmu_page *tdp_mmu_alloc_sp_for_split(struct kvm *kvm, return sp; } +/* Note, the caller is responsible for initializing @sp. */ static int tdp_mmu_split_huge_page(struct kvm *kvm, struct tdp_iter *iter, struct kvm_mmu_page *sp, bool shared) { @@ -1479,8 +1479,6 @@ static int tdp_mmu_split_huge_page(struct kvm *kvm, struct tdp_iter *iter, const int level = iter->level; int ret, i; - tdp_mmu_init_child_sp(sp, iter); - /* * No need for atomics when writing to sp->spt since the page table has * not been linked in yet and thus is not reachable from any other CPU. @@ -1496,7 +1494,7 @@ static int tdp_mmu_split_huge_page(struct kvm *kvm, struct tdp_iter *iter, * correctness standpoint since the translation will be the same either * way. */ - ret = tdp_mmu_link_sp(kvm, iter, sp, false, shared); + ret = tdp_mmu_link_sp(kvm, iter, sp, shared); if (ret) goto out; @@ -1556,6 +1554,8 @@ retry: continue; } + tdp_mmu_init_child_sp(sp, &iter); + if (tdp_mmu_split_huge_page(kvm, &iter, sp, shared)) goto retry; diff --git a/arch/x86/kvm/mmu/tdp_mmu.h b/arch/x86/kvm/mmu/tdp_mmu.h index c163f7cc23ca..d3714200b932 100644 --- a/arch/x86/kvm/mmu/tdp_mmu.h +++ b/arch/x86/kvm/mmu/tdp_mmu.h @@ -5,6 +5,8 @@ #include <linux/kvm_host.h> +#include "spte.h" + hpa_t kvm_tdp_mmu_get_vcpu_root_hpa(struct kvm_vcpu *vcpu); __must_check static inline bool kvm_tdp_mmu_get_root(struct kvm_mmu_page *root) diff --git a/arch/x86/kvm/pmu.c b/arch/x86/kvm/pmu.c index d9b9a0f0db17..684393c22105 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 @@ -101,10 +101,6 @@ static inline void __kvm_perf_overflow(struct kvm_pmc *pmc, bool in_pmi) struct kvm_pmu *pmu = pmc_to_pmu(pmc); bool skip_pmi = false; - /* Ignore counters that have been reprogrammed already. */ - if (test_and_set_bit(pmc->idx, pmu->reprogram_pmi)) - return; - if (pmc->perf_event && pmc->perf_event->attr.precise_ip) { if (!in_pmi) { /* @@ -122,7 +118,6 @@ static inline void __kvm_perf_overflow(struct kvm_pmc *pmc, bool in_pmi) } else { __set_bit(pmc->idx, (unsigned long *)&pmu->global_status); } - kvm_make_request(KVM_REQ_PMU, pmc->vcpu); if (!pmc->intr || skip_pmi) return; @@ -147,12 +142,22 @@ static void kvm_perf_overflow(struct perf_event *perf_event, { struct kvm_pmc *pmc = perf_event->overflow_handler_context; + /* + * Ignore overflow events for counters that are scheduled to be + * reprogrammed, e.g. if a PMI for the previous event races with KVM's + * handling of a related guest WRMSR. + */ + if (test_and_set_bit(pmc->idx, pmc_to_pmu(pmc)->reprogram_pmi)) + return; + __kvm_perf_overflow(pmc, true); + + kvm_make_request(KVM_REQ_PMU, pmc->vcpu); } -static void pmc_reprogram_counter(struct kvm_pmc *pmc, u32 type, - u64 config, bool exclude_user, - bool exclude_kernel, bool intr) +static int pmc_reprogram_counter(struct kvm_pmc *pmc, u32 type, u64 config, + bool exclude_user, bool exclude_kernel, + bool intr) { struct kvm_pmu *pmu = pmc_to_pmu(pmc); struct perf_event *event; @@ -204,14 +209,14 @@ static void pmc_reprogram_counter(struct kvm_pmc *pmc, u32 type, if (IS_ERR(event)) { pr_debug_ratelimited("kvm_pmu: event creation failed %ld for pmc->idx = %d\n", PTR_ERR(event), pmc->idx); - return; + return PTR_ERR(event); } pmc->perf_event = event; pmc_to_pmu(pmc)->event_count++; - clear_bit(pmc->idx, pmc_to_pmu(pmc)->reprogram_pmi); pmc->is_paused = false; pmc->intr = intr || pebs; + return 0; } static void pmc_pause_counter(struct kvm_pmc *pmc) @@ -245,7 +250,6 @@ static bool pmc_resume_counter(struct kvm_pmc *pmc) perf_event_enable(pmc->perf_event); pmc->is_paused = false; - clear_bit(pmc->idx, (unsigned long *)&pmc_to_pmu(pmc)->reprogram_pmi); return true; } @@ -293,7 +297,7 @@ out: return allow_event; } -void reprogram_counter(struct kvm_pmc *pmc) +static void reprogram_counter(struct kvm_pmc *pmc) { struct kvm_pmu *pmu = pmc_to_pmu(pmc); u64 eventsel = pmc->eventsel; @@ -303,10 +307,13 @@ void reprogram_counter(struct kvm_pmc *pmc) pmc_pause_counter(pmc); if (!pmc_speculative_in_use(pmc) || !pmc_is_enabled(pmc)) - return; + goto reprogram_complete; if (!check_pmu_event_filter(pmc)) - return; + goto reprogram_complete; + + if (pmc->counter < pmc->prev_counter) + __kvm_perf_overflow(pmc, false); if (eventsel & ARCH_PERFMON_EVENTSEL_PIN_CONTROL) printk_once("kvm pmu: pin control bit is ignored\n"); @@ -324,18 +331,29 @@ void reprogram_counter(struct kvm_pmc *pmc) } if (pmc->current_config == new_config && pmc_resume_counter(pmc)) - return; + goto reprogram_complete; pmc_release_perf_event(pmc); pmc->current_config = new_config; - pmc_reprogram_counter(pmc, PERF_TYPE_RAW, - (eventsel & pmu->raw_event_mask), - !(eventsel & ARCH_PERFMON_EVENTSEL_USR), - !(eventsel & ARCH_PERFMON_EVENTSEL_OS), - eventsel & ARCH_PERFMON_EVENTSEL_INT); + + /* + * If reprogramming fails, e.g. due to contention, leave the counter's + * regprogram bit set, i.e. opportunistically try again on the next PMU + * refresh. Don't make a new request as doing so can stall the guest + * if reprogramming repeatedly fails. + */ + if (pmc_reprogram_counter(pmc, PERF_TYPE_RAW, + (eventsel & pmu->raw_event_mask), + !(eventsel & ARCH_PERFMON_EVENTSEL_USR), + !(eventsel & ARCH_PERFMON_EVENTSEL_OS), + eventsel & ARCH_PERFMON_EVENTSEL_INT)) + return; + +reprogram_complete: + clear_bit(pmc->idx, (unsigned long *)&pmc_to_pmu(pmc)->reprogram_pmi); + pmc->prev_counter = 0; } -EXPORT_SYMBOL_GPL(reprogram_counter); void kvm_pmu_handle_event(struct kvm_vcpu *vcpu) { @@ -345,10 +363,11 @@ void kvm_pmu_handle_event(struct kvm_vcpu *vcpu) for_each_set_bit(bit, pmu->reprogram_pmi, X86_PMC_IDX_MAX) { struct kvm_pmc *pmc = static_call(kvm_x86_pmu_pmc_idx_to_pmc)(pmu, bit); - if (unlikely(!pmc || !pmc->perf_event)) { + if (unlikely(!pmc)) { clear_bit(bit, pmu->reprogram_pmi); continue; } + reprogram_counter(pmc); } @@ -522,14 +541,9 @@ void kvm_pmu_destroy(struct kvm_vcpu *vcpu) static void kvm_pmu_incr_counter(struct kvm_pmc *pmc) { - u64 prev_count; - - prev_count = pmc->counter; + pmc->prev_counter = pmc->counter; pmc->counter = (pmc->counter + 1) & pmc_bitmask(pmc); - - reprogram_counter(pmc); - if (pmc->counter < prev_count) - __kvm_perf_overflow(pmc, false); + kvm_pmu_request_counter_reprogam(pmc); } static inline bool eventsel_match_perf_hw_id(struct kvm_pmc *pmc, @@ -542,12 +556,15 @@ static inline bool eventsel_match_perf_hw_id(struct kvm_pmc *pmc, static inline bool cpl_is_matched(struct kvm_pmc *pmc) { bool select_os, select_user; - u64 config = pmc->current_config; + u64 config; if (pmc_is_gp(pmc)) { + config = pmc->eventsel; select_os = config & ARCH_PERFMON_EVENTSEL_OS; select_user = config & ARCH_PERFMON_EVENTSEL_USR; } else { + config = fixed_ctrl_field(pmc_to_pmu(pmc)->fixed_ctr_ctrl, + pmc->idx - INTEL_PMC_IDX_FIXED); select_os = config & 0x1; select_user = config & 0x2; } @@ -577,6 +594,8 @@ EXPORT_SYMBOL_GPL(kvm_pmu_trigger_event); int kvm_vm_ioctl_set_pmu_event_filter(struct kvm *kvm, void __user *argp) { struct kvm_pmu_event_filter tmp, *filter; + struct kvm_vcpu *vcpu; + unsigned long i; size_t size; int r; @@ -613,9 +632,18 @@ int kvm_vm_ioctl_set_pmu_event_filter(struct kvm *kvm, void __user *argp) mutex_lock(&kvm->lock); filter = rcu_replace_pointer(kvm->arch.pmu_event_filter, filter, mutex_is_locked(&kvm->lock)); + synchronize_srcu_expedited(&kvm->srcu); + + BUILD_BUG_ON(sizeof(((struct kvm_pmu *)0)->reprogram_pmi) > + sizeof(((struct kvm_pmu *)0)->__reprogram_pmi)); + + kvm_for_each_vcpu(i, vcpu, kvm) + atomic64_set(&vcpu_to_pmu(vcpu)->__reprogram_pmi, -1ull); + + kvm_make_all_cpus_request(kvm, KVM_REQ_PMU); + mutex_unlock(&kvm->lock); - synchronize_srcu_expedited(&kvm->srcu); r = 0; cleanup: kfree(filter); diff --git a/arch/x86/kvm/pmu.h b/arch/x86/kvm/pmu.h index 5cc5721f260b..85ff3c0588ba 100644 --- a/arch/x86/kvm/pmu.h +++ b/arch/x86/kvm/pmu.h @@ -183,7 +183,11 @@ static inline void kvm_init_pmu_capability(void) KVM_PMC_MAX_FIXED); } -void reprogram_counter(struct kvm_pmc *pmc); +static inline void kvm_pmu_request_counter_reprogam(struct kvm_pmc *pmc) +{ + set_bit(pmc->idx, pmc_to_pmu(pmc)->reprogram_pmi); + kvm_make_request(KVM_REQ_PMU, pmc->vcpu); +} void kvm_pmu_deliver_pmi(struct kvm_vcpu *vcpu); void kvm_pmu_handle_event(struct kvm_vcpu *vcpu); diff --git a/arch/x86/kvm/reverse_cpuid.h b/arch/x86/kvm/reverse_cpuid.h index a19d473d0184..203fdad07bae 100644 --- a/arch/x86/kvm/reverse_cpuid.h +++ b/arch/x86/kvm/reverse_cpuid.h @@ -7,23 +7,41 @@ #include <asm/cpufeatures.h> /* - * Hardware-defined CPUID leafs that are scattered in the kernel, but need to - * be directly used by KVM. Note, these word values conflict with the kernel's - * "bug" caps, but KVM doesn't use those. + * Hardware-defined CPUID leafs that are either scattered by the kernel or are + * unknown to the kernel, but need to be directly used by KVM. Note, these + * word values conflict with the kernel's "bug" caps, but KVM doesn't use those. */ enum kvm_only_cpuid_leafs { CPUID_12_EAX = NCAPINTS, + CPUID_7_1_EDX, NR_KVM_CPU_CAPS, NKVMCAPINTS = NR_KVM_CPU_CAPS - NCAPINTS, }; +/* + * Define a KVM-only feature flag. + * + * For features that are scattered by cpufeatures.h, __feature_translate() also + * needs to be updated to translate the kernel-defined feature into the + * KVM-defined feature. + * + * For features that are 100% KVM-only, i.e. not defined by cpufeatures.h, + * forego the intermediate KVM_X86_FEATURE and directly define X86_FEATURE_* so + * that X86_FEATURE_* can be used in KVM. No __feature_translate() handling is + * needed in this case. + */ #define KVM_X86_FEATURE(w, f) ((w)*32 + (f)) /* Intel-defined SGX sub-features, CPUID level 0x12 (EAX). */ #define KVM_X86_FEATURE_SGX1 KVM_X86_FEATURE(CPUID_12_EAX, 0) #define KVM_X86_FEATURE_SGX2 KVM_X86_FEATURE(CPUID_12_EAX, 1) +/* Intel-defined sub-features, CPUID level 0x00000007:1 (EDX) */ +#define X86_FEATURE_AVX_VNNI_INT8 KVM_X86_FEATURE(CPUID_7_1_EDX, 4) +#define X86_FEATURE_AVX_NE_CONVERT KVM_X86_FEATURE(CPUID_7_1_EDX, 5) +#define X86_FEATURE_PREFETCHITI KVM_X86_FEATURE(CPUID_7_1_EDX, 14) + struct cpuid_reg { u32 function; u32 index; @@ -48,6 +66,7 @@ static const struct cpuid_reg reverse_cpuid[] = { [CPUID_7_1_EAX] = { 7, 1, CPUID_EAX}, [CPUID_12_EAX] = {0x00000012, 0, CPUID_EAX}, [CPUID_8000_001F_EAX] = {0x8000001f, 0, CPUID_EAX}, + [CPUID_7_1_EDX] = { 7, 1, CPUID_EDX}, }; /* diff --git a/arch/x86/kvm/smm.c b/arch/x86/kvm/smm.c new file mode 100644 index 000000000000..a9c1c2af8d94 --- /dev/null +++ b/arch/x86/kvm/smm.c @@ -0,0 +1,649 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#include <linux/kvm_host.h> +#include "x86.h" +#include "kvm_cache_regs.h" +#include "kvm_emulate.h" +#include "smm.h" +#include "cpuid.h" +#include "trace.h" + +#define CHECK_SMRAM32_OFFSET(field, offset) \ + ASSERT_STRUCT_OFFSET(struct kvm_smram_state_32, field, offset - 0xFE00) + +#define CHECK_SMRAM64_OFFSET(field, offset) \ + ASSERT_STRUCT_OFFSET(struct kvm_smram_state_64, field, offset - 0xFE00) + +static void check_smram_offsets(void) +{ + /* 32 bit SMRAM image */ + CHECK_SMRAM32_OFFSET(reserved1, 0xFE00); + CHECK_SMRAM32_OFFSET(smbase, 0xFEF8); + CHECK_SMRAM32_OFFSET(smm_revision, 0xFEFC); + CHECK_SMRAM32_OFFSET(io_inst_restart, 0xFF00); + CHECK_SMRAM32_OFFSET(auto_hlt_restart, 0xFF02); + CHECK_SMRAM32_OFFSET(io_restart_rdi, 0xFF04); + CHECK_SMRAM32_OFFSET(io_restart_rcx, 0xFF08); + CHECK_SMRAM32_OFFSET(io_restart_rsi, 0xFF0C); + CHECK_SMRAM32_OFFSET(io_restart_rip, 0xFF10); + CHECK_SMRAM32_OFFSET(cr4, 0xFF14); + CHECK_SMRAM32_OFFSET(reserved2, 0xFF18); + CHECK_SMRAM32_OFFSET(int_shadow, 0xFF1A); + CHECK_SMRAM32_OFFSET(reserved3, 0xFF1B); + CHECK_SMRAM32_OFFSET(ds, 0xFF2C); + CHECK_SMRAM32_OFFSET(fs, 0xFF38); + CHECK_SMRAM32_OFFSET(gs, 0xFF44); + CHECK_SMRAM32_OFFSET(idtr, 0xFF50); + CHECK_SMRAM32_OFFSET(tr, 0xFF5C); + CHECK_SMRAM32_OFFSET(gdtr, 0xFF6C); + CHECK_SMRAM32_OFFSET(ldtr, 0xFF78); + CHECK_SMRAM32_OFFSET(es, 0xFF84); + CHECK_SMRAM32_OFFSET(cs, 0xFF90); + CHECK_SMRAM32_OFFSET(ss, 0xFF9C); + CHECK_SMRAM32_OFFSET(es_sel, 0xFFA8); + CHECK_SMRAM32_OFFSET(cs_sel, 0xFFAC); + CHECK_SMRAM32_OFFSET(ss_sel, 0xFFB0); + CHECK_SMRAM32_OFFSET(ds_sel, 0xFFB4); + CHECK_SMRAM32_OFFSET(fs_sel, 0xFFB8); + CHECK_SMRAM32_OFFSET(gs_sel, 0xFFBC); + CHECK_SMRAM32_OFFSET(ldtr_sel, 0xFFC0); + CHECK_SMRAM32_OFFSET(tr_sel, 0xFFC4); + CHECK_SMRAM32_OFFSET(dr7, 0xFFC8); + CHECK_SMRAM32_OFFSET(dr6, 0xFFCC); + CHECK_SMRAM32_OFFSET(gprs, 0xFFD0); + CHECK_SMRAM32_OFFSET(eip, 0xFFF0); + CHECK_SMRAM32_OFFSET(eflags, 0xFFF4); + CHECK_SMRAM32_OFFSET(cr3, 0xFFF8); + CHECK_SMRAM32_OFFSET(cr0, 0xFFFC); + + /* 64 bit SMRAM image */ + CHECK_SMRAM64_OFFSET(es, 0xFE00); + CHECK_SMRAM64_OFFSET(cs, 0xFE10); + CHECK_SMRAM64_OFFSET(ss, 0xFE20); + CHECK_SMRAM64_OFFSET(ds, 0xFE30); + CHECK_SMRAM64_OFFSET(fs, 0xFE40); + CHECK_SMRAM64_OFFSET(gs, 0xFE50); + CHECK_SMRAM64_OFFSET(gdtr, 0xFE60); + CHECK_SMRAM64_OFFSET(ldtr, 0xFE70); + CHECK_SMRAM64_OFFSET(idtr, 0xFE80); + CHECK_SMRAM64_OFFSET(tr, 0xFE90); + CHECK_SMRAM64_OFFSET(io_restart_rip, 0xFEA0); + CHECK_SMRAM64_OFFSET(io_restart_rcx, 0xFEA8); + CHECK_SMRAM64_OFFSET(io_restart_rsi, 0xFEB0); + CHECK_SMRAM64_OFFSET(io_restart_rdi, 0xFEB8); + CHECK_SMRAM64_OFFSET(io_restart_dword, 0xFEC0); + CHECK_SMRAM64_OFFSET(reserved1, 0xFEC4); + CHECK_SMRAM64_OFFSET(io_inst_restart, 0xFEC8); + CHECK_SMRAM64_OFFSET(auto_hlt_restart, 0xFEC9); + CHECK_SMRAM64_OFFSET(amd_nmi_mask, 0xFECA); + CHECK_SMRAM64_OFFSET(int_shadow, 0xFECB); + CHECK_SMRAM64_OFFSET(reserved2, 0xFECC); + CHECK_SMRAM64_OFFSET(efer, 0xFED0); + CHECK_SMRAM64_OFFSET(svm_guest_flag, 0xFED8); + CHECK_SMRAM64_OFFSET(svm_guest_vmcb_gpa, 0xFEE0); + CHECK_SMRAM64_OFFSET(svm_guest_virtual_int, 0xFEE8); + CHECK_SMRAM64_OFFSET(reserved3, 0xFEF0); + CHECK_SMRAM64_OFFSET(smm_revison, 0xFEFC); + CHECK_SMRAM64_OFFSET(smbase, 0xFF00); + CHECK_SMRAM64_OFFSET(reserved4, 0xFF04); + CHECK_SMRAM64_OFFSET(ssp, 0xFF18); + CHECK_SMRAM64_OFFSET(svm_guest_pat, 0xFF20); + CHECK_SMRAM64_OFFSET(svm_host_efer, 0xFF28); + CHECK_SMRAM64_OFFSET(svm_host_cr4, 0xFF30); + CHECK_SMRAM64_OFFSET(svm_host_cr3, 0xFF38); + CHECK_SMRAM64_OFFSET(svm_host_cr0, 0xFF40); + CHECK_SMRAM64_OFFSET(cr4, 0xFF48); + CHECK_SMRAM64_OFFSET(cr3, 0xFF50); + CHECK_SMRAM64_OFFSET(cr0, 0xFF58); + CHECK_SMRAM64_OFFSET(dr7, 0xFF60); + CHECK_SMRAM64_OFFSET(dr6, 0xFF68); + CHECK_SMRAM64_OFFSET(rflags, 0xFF70); + CHECK_SMRAM64_OFFSET(rip, 0xFF78); + CHECK_SMRAM64_OFFSET(gprs, 0xFF80); + + BUILD_BUG_ON(sizeof(union kvm_smram) != 512); +} + +#undef CHECK_SMRAM64_OFFSET +#undef CHECK_SMRAM32_OFFSET + + +void kvm_smm_changed(struct kvm_vcpu *vcpu, bool entering_smm) +{ + BUILD_BUG_ON(HF_SMM_MASK != X86EMUL_SMM_MASK); + + trace_kvm_smm_transition(vcpu->vcpu_id, vcpu->arch.smbase, entering_smm); + + if (entering_smm) { + vcpu->arch.hflags |= HF_SMM_MASK; + } else { + vcpu->arch.hflags &= ~(HF_SMM_MASK | HF_SMM_INSIDE_NMI_MASK); + + /* Process a latched INIT or SMI, if any. */ + kvm_make_request(KVM_REQ_EVENT, vcpu); + + /* + * Even if KVM_SET_SREGS2 loaded PDPTRs out of band, + * on SMM exit we still need to reload them from + * guest memory + */ + vcpu->arch.pdptrs_from_userspace = false; + } + + kvm_mmu_reset_context(vcpu); +} + +void process_smi(struct kvm_vcpu *vcpu) +{ + vcpu->arch.smi_pending = true; + kvm_make_request(KVM_REQ_EVENT, vcpu); +} + +static u32 enter_smm_get_segment_flags(struct kvm_segment *seg) +{ + u32 flags = 0; + flags |= seg->g << 23; + flags |= seg->db << 22; + flags |= seg->l << 21; + flags |= seg->avl << 20; + flags |= seg->present << 15; + flags |= seg->dpl << 13; + flags |= seg->s << 12; + flags |= seg->type << 8; + return flags; +} + +static void enter_smm_save_seg_32(struct kvm_vcpu *vcpu, + struct kvm_smm_seg_state_32 *state, + u32 *selector, int n) +{ + struct kvm_segment seg; + + kvm_get_segment(vcpu, &seg, n); + *selector = seg.selector; + state->base = seg.base; + state->limit = seg.limit; + state->flags = enter_smm_get_segment_flags(&seg); +} + +#ifdef CONFIG_X86_64 +static void enter_smm_save_seg_64(struct kvm_vcpu *vcpu, + struct kvm_smm_seg_state_64 *state, + int n) +{ + struct kvm_segment seg; + + kvm_get_segment(vcpu, &seg, n); + state->selector = seg.selector; + state->attributes = enter_smm_get_segment_flags(&seg) >> 8; + state->limit = seg.limit; + state->base = seg.base; +} +#endif + +static void enter_smm_save_state_32(struct kvm_vcpu *vcpu, + struct kvm_smram_state_32 *smram) +{ + struct desc_ptr dt; + unsigned long val; + int i; + + smram->cr0 = kvm_read_cr0(vcpu); + smram->cr3 = kvm_read_cr3(vcpu); + smram->eflags = kvm_get_rflags(vcpu); + smram->eip = kvm_rip_read(vcpu); + + for (i = 0; i < 8; i++) + smram->gprs[i] = kvm_register_read_raw(vcpu, i); + + kvm_get_dr(vcpu, 6, &val); + smram->dr6 = (u32)val; + kvm_get_dr(vcpu, 7, &val); + smram->dr7 = (u32)val; + + enter_smm_save_seg_32(vcpu, &smram->tr, &smram->tr_sel, VCPU_SREG_TR); + enter_smm_save_seg_32(vcpu, &smram->ldtr, &smram->ldtr_sel, VCPU_SREG_LDTR); + + static_call(kvm_x86_get_gdt)(vcpu, &dt); + smram->gdtr.base = dt.address; + smram->gdtr.limit = dt.size; + + static_call(kvm_x86_get_idt)(vcpu, &dt); + smram->idtr.base = dt.address; + smram->idtr.limit = dt.size; + + enter_smm_save_seg_32(vcpu, &smram->es, &smram->es_sel, VCPU_SREG_ES); + enter_smm_save_seg_32(vcpu, &smram->cs, &smram->cs_sel, VCPU_SREG_CS); + enter_smm_save_seg_32(vcpu, &smram->ss, &smram->ss_sel, VCPU_SREG_SS); + + enter_smm_save_seg_32(vcpu, &smram->ds, &smram->ds_sel, VCPU_SREG_DS); + enter_smm_save_seg_32(vcpu, &smram->fs, &smram->fs_sel, VCPU_SREG_FS); + enter_smm_save_seg_32(vcpu, &smram->gs, &smram->gs_sel, VCPU_SREG_GS); + + smram->cr4 = kvm_read_cr4(vcpu); + smram->smm_revision = 0x00020000; + smram->smbase = vcpu->arch.smbase; + + smram->int_shadow = static_call(kvm_x86_get_interrupt_shadow)(vcpu); +} + +#ifdef CONFIG_X86_64 +static void enter_smm_save_state_64(struct kvm_vcpu *vcpu, + struct kvm_smram_state_64 *smram) +{ + struct desc_ptr dt; + unsigned long val; + int i; + + for (i = 0; i < 16; i++) + smram->gprs[15 - i] = kvm_register_read_raw(vcpu, i); + + smram->rip = kvm_rip_read(vcpu); + smram->rflags = kvm_get_rflags(vcpu); + + + kvm_get_dr(vcpu, 6, &val); + smram->dr6 = val; + kvm_get_dr(vcpu, 7, &val); + smram->dr7 = val; + + smram->cr0 = kvm_read_cr0(vcpu); + smram->cr3 = kvm_read_cr3(vcpu); + smram->cr4 = kvm_read_cr4(vcpu); + + smram->smbase = vcpu->arch.smbase; + smram->smm_revison = 0x00020064; + + smram->efer = vcpu->arch.efer; + + enter_smm_save_seg_64(vcpu, &smram->tr, VCPU_SREG_TR); + + static_call(kvm_x86_get_idt)(vcpu, &dt); + smram->idtr.limit = dt.size; + smram->idtr.base = dt.address; + + enter_smm_save_seg_64(vcpu, &smram->ldtr, VCPU_SREG_LDTR); + + static_call(kvm_x86_get_gdt)(vcpu, &dt); + smram->gdtr.limit = dt.size; + smram->gdtr.base = dt.address; + + enter_smm_save_seg_64(vcpu, &smram->es, VCPU_SREG_ES); + enter_smm_save_seg_64(vcpu, &smram->cs, VCPU_SREG_CS); + enter_smm_save_seg_64(vcpu, &smram->ss, VCPU_SREG_SS); + enter_smm_save_seg_64(vcpu, &smram->ds, VCPU_SREG_DS); + enter_smm_save_seg_64(vcpu, &smram->fs, VCPU_SREG_FS); + enter_smm_save_seg_64(vcpu, &smram->gs, VCPU_SREG_GS); + + smram->int_shadow = static_call(kvm_x86_get_interrupt_shadow)(vcpu); +} +#endif + +void enter_smm(struct kvm_vcpu *vcpu) +{ + struct kvm_segment cs, ds; + struct desc_ptr dt; + unsigned long cr0; + union kvm_smram smram; + + check_smram_offsets(); + + memset(smram.bytes, 0, sizeof(smram.bytes)); + +#ifdef CONFIG_X86_64 + if (guest_cpuid_has(vcpu, X86_FEATURE_LM)) + enter_smm_save_state_64(vcpu, &smram.smram64); + else +#endif + enter_smm_save_state_32(vcpu, &smram.smram32); + + /* + * Give enter_smm() a chance to make ISA-specific changes to the vCPU + * state (e.g. leave guest mode) after we've saved the state into the + * SMM state-save area. + * + * Kill the VM in the unlikely case of failure, because the VM + * can be in undefined state in this case. + */ + if (static_call(kvm_x86_enter_smm)(vcpu, &smram)) + goto error; + + kvm_smm_changed(vcpu, true); + + if (kvm_vcpu_write_guest(vcpu, vcpu->arch.smbase + 0xfe00, &smram, sizeof(smram))) + goto error; + + if (static_call(kvm_x86_get_nmi_mask)(vcpu)) + vcpu->arch.hflags |= HF_SMM_INSIDE_NMI_MASK; + else + static_call(kvm_x86_set_nmi_mask)(vcpu, true); + + kvm_set_rflags(vcpu, X86_EFLAGS_FIXED); + kvm_rip_write(vcpu, 0x8000); + + static_call(kvm_x86_set_interrupt_shadow)(vcpu, 0); + + cr0 = vcpu->arch.cr0 & ~(X86_CR0_PE | X86_CR0_EM | X86_CR0_TS | X86_CR0_PG); + static_call(kvm_x86_set_cr0)(vcpu, cr0); + vcpu->arch.cr0 = cr0; + + static_call(kvm_x86_set_cr4)(vcpu, 0); + + /* Undocumented: IDT limit is set to zero on entry to SMM. */ + dt.address = dt.size = 0; + static_call(kvm_x86_set_idt)(vcpu, &dt); + + if (WARN_ON_ONCE(kvm_set_dr(vcpu, 7, DR7_FIXED_1))) + goto error; + + cs.selector = (vcpu->arch.smbase >> 4) & 0xffff; + cs.base = vcpu->arch.smbase; + + ds.selector = 0; + ds.base = 0; + + cs.limit = ds.limit = 0xffffffff; + cs.type = ds.type = 0x3; + cs.dpl = ds.dpl = 0; + cs.db = ds.db = 0; + cs.s = ds.s = 1; + cs.l = ds.l = 0; + cs.g = ds.g = 1; + cs.avl = ds.avl = 0; + cs.present = ds.present = 1; + cs.unusable = ds.unusable = 0; + cs.padding = ds.padding = 0; + + kvm_set_segment(vcpu, &cs, VCPU_SREG_CS); + kvm_set_segment(vcpu, &ds, VCPU_SREG_DS); + kvm_set_segment(vcpu, &ds, VCPU_SREG_ES); + kvm_set_segment(vcpu, &ds, VCPU_SREG_FS); + kvm_set_segment(vcpu, &ds, VCPU_SREG_GS); + kvm_set_segment(vcpu, &ds, VCPU_SREG_SS); + +#ifdef CONFIG_X86_64 + if (guest_cpuid_has(vcpu, X86_FEATURE_LM)) + if (static_call(kvm_x86_set_efer)(vcpu, 0)) + goto error; +#endif + + kvm_update_cpuid_runtime(vcpu); + kvm_mmu_reset_context(vcpu); + return; +error: + kvm_vm_dead(vcpu->kvm); +} + +static void rsm_set_desc_flags(struct kvm_segment *desc, u32 flags) +{ + desc->g = (flags >> 23) & 1; + desc->db = (flags >> 22) & 1; + desc->l = (flags >> 21) & 1; + desc->avl = (flags >> 20) & 1; + desc->present = (flags >> 15) & 1; + desc->dpl = (flags >> 13) & 3; + desc->s = (flags >> 12) & 1; + desc->type = (flags >> 8) & 15; + + desc->unusable = !desc->present; + desc->padding = 0; +} + +static int rsm_load_seg_32(struct kvm_vcpu *vcpu, + const struct kvm_smm_seg_state_32 *state, + u16 selector, int n) +{ + struct kvm_segment desc; + + desc.selector = selector; + desc.base = state->base; + desc.limit = state->limit; + rsm_set_desc_flags(&desc, state->flags); + kvm_set_segment(vcpu, &desc, n); + return X86EMUL_CONTINUE; +} + +#ifdef CONFIG_X86_64 + +static int rsm_load_seg_64(struct kvm_vcpu *vcpu, + const struct kvm_smm_seg_state_64 *state, + int n) +{ + struct kvm_segment desc; + + desc.selector = state->selector; + rsm_set_desc_flags(&desc, state->attributes << 8); + desc.limit = state->limit; + desc.base = state->base; + kvm_set_segment(vcpu, &desc, n); + return X86EMUL_CONTINUE; +} +#endif + +static int rsm_enter_protected_mode(struct kvm_vcpu *vcpu, + u64 cr0, u64 cr3, u64 cr4) +{ + int bad; + u64 pcid; + + /* In order to later set CR4.PCIDE, CR3[11:0] must be zero. */ + pcid = 0; + if (cr4 & X86_CR4_PCIDE) { + pcid = cr3 & 0xfff; + cr3 &= ~0xfff; + } + + bad = kvm_set_cr3(vcpu, cr3); + if (bad) + return X86EMUL_UNHANDLEABLE; + + /* + * First enable PAE, long mode needs it before CR0.PG = 1 is set. + * Then enable protected mode. However, PCID cannot be enabled + * if EFER.LMA=0, so set it separately. + */ + bad = kvm_set_cr4(vcpu, cr4 & ~X86_CR4_PCIDE); + if (bad) + return X86EMUL_UNHANDLEABLE; + + bad = kvm_set_cr0(vcpu, cr0); + if (bad) + return X86EMUL_UNHANDLEABLE; + + if (cr4 & X86_CR4_PCIDE) { + bad = kvm_set_cr4(vcpu, cr4); + if (bad) + return X86EMUL_UNHANDLEABLE; + if (pcid) { + bad = kvm_set_cr3(vcpu, cr3 | pcid); + if (bad) + return X86EMUL_UNHANDLEABLE; + } + + } + + return X86EMUL_CONTINUE; +} + +static int rsm_load_state_32(struct x86_emulate_ctxt *ctxt, + const struct kvm_smram_state_32 *smstate) +{ + struct kvm_vcpu *vcpu = ctxt->vcpu; + struct desc_ptr dt; + int i, r; + + ctxt->eflags = smstate->eflags | X86_EFLAGS_FIXED; + ctxt->_eip = smstate->eip; + + for (i = 0; i < 8; i++) + *reg_write(ctxt, i) = smstate->gprs[i]; + + if (kvm_set_dr(vcpu, 6, smstate->dr6)) + return X86EMUL_UNHANDLEABLE; + if (kvm_set_dr(vcpu, 7, smstate->dr7)) + return X86EMUL_UNHANDLEABLE; + + rsm_load_seg_32(vcpu, &smstate->tr, smstate->tr_sel, VCPU_SREG_TR); + rsm_load_seg_32(vcpu, &smstate->ldtr, smstate->ldtr_sel, VCPU_SREG_LDTR); + + dt.address = smstate->gdtr.base; + dt.size = smstate->gdtr.limit; + static_call(kvm_x86_set_gdt)(vcpu, &dt); + + dt.address = smstate->idtr.base; + dt.size = smstate->idtr.limit; + static_call(kvm_x86_set_idt)(vcpu, &dt); + + rsm_load_seg_32(vcpu, &smstate->es, smstate->es_sel, VCPU_SREG_ES); + rsm_load_seg_32(vcpu, &smstate->cs, smstate->cs_sel, VCPU_SREG_CS); + rsm_load_seg_32(vcpu, &smstate->ss, smstate->ss_sel, VCPU_SREG_SS); + + rsm_load_seg_32(vcpu, &smstate->ds, smstate->ds_sel, VCPU_SREG_DS); + rsm_load_seg_32(vcpu, &smstate->fs, smstate->fs_sel, VCPU_SREG_FS); + rsm_load_seg_32(vcpu, &smstate->gs, smstate->gs_sel, VCPU_SREG_GS); + + vcpu->arch.smbase = smstate->smbase; + + r = rsm_enter_protected_mode(vcpu, smstate->cr0, + smstate->cr3, smstate->cr4); + + if (r != X86EMUL_CONTINUE) + return r; + + static_call(kvm_x86_set_interrupt_shadow)(vcpu, 0); + ctxt->interruptibility = (u8)smstate->int_shadow; + + return r; +} + +#ifdef CONFIG_X86_64 +static int rsm_load_state_64(struct x86_emulate_ctxt *ctxt, + const struct kvm_smram_state_64 *smstate) +{ + struct kvm_vcpu *vcpu = ctxt->vcpu; + struct desc_ptr dt; + int i, r; + + for (i = 0; i < 16; i++) + *reg_write(ctxt, i) = smstate->gprs[15 - i]; + + ctxt->_eip = smstate->rip; + ctxt->eflags = smstate->rflags | X86_EFLAGS_FIXED; + + if (kvm_set_dr(vcpu, 6, smstate->dr6)) + return X86EMUL_UNHANDLEABLE; + if (kvm_set_dr(vcpu, 7, smstate->dr7)) + return X86EMUL_UNHANDLEABLE; + + vcpu->arch.smbase = smstate->smbase; + + if (kvm_set_msr(vcpu, MSR_EFER, smstate->efer & ~EFER_LMA)) + return X86EMUL_UNHANDLEABLE; + + rsm_load_seg_64(vcpu, &smstate->tr, VCPU_SREG_TR); + + dt.size = smstate->idtr.limit; + dt.address = smstate->idtr.base; + static_call(kvm_x86_set_idt)(vcpu, &dt); + + rsm_load_seg_64(vcpu, &smstate->ldtr, VCPU_SREG_LDTR); + + dt.size = smstate->gdtr.limit; + dt.address = smstate->gdtr.base; + static_call(kvm_x86_set_gdt)(vcpu, &dt); + + r = rsm_enter_protected_mode(vcpu, smstate->cr0, smstate->cr3, smstate->cr4); + if (r != X86EMUL_CONTINUE) + return r; + + rsm_load_seg_64(vcpu, &smstate->es, VCPU_SREG_ES); + rsm_load_seg_64(vcpu, &smstate->cs, VCPU_SREG_CS); + rsm_load_seg_64(vcpu, &smstate->ss, VCPU_SREG_SS); + rsm_load_seg_64(vcpu, &smstate->ds, VCPU_SREG_DS); + rsm_load_seg_64(vcpu, &smstate->fs, VCPU_SREG_FS); + rsm_load_seg_64(vcpu, &smstate->gs, VCPU_SREG_GS); + + static_call(kvm_x86_set_interrupt_shadow)(vcpu, 0); + ctxt->interruptibility = (u8)smstate->int_shadow; + + return X86EMUL_CONTINUE; +} +#endif + +int emulator_leave_smm(struct x86_emulate_ctxt *ctxt) +{ + struct kvm_vcpu *vcpu = ctxt->vcpu; + unsigned long cr0; + union kvm_smram smram; + u64 smbase; + int ret; + + smbase = vcpu->arch.smbase; + + ret = kvm_vcpu_read_guest(vcpu, smbase + 0xfe00, smram.bytes, sizeof(smram)); + if (ret < 0) + return X86EMUL_UNHANDLEABLE; + + if ((vcpu->arch.hflags & HF_SMM_INSIDE_NMI_MASK) == 0) + static_call(kvm_x86_set_nmi_mask)(vcpu, false); + + kvm_smm_changed(vcpu, false); + + /* + * Get back to real mode, to prepare a safe state in which to load + * CR0/CR3/CR4/EFER. It's all a bit more complicated if the vCPU + * supports long mode. + */ +#ifdef CONFIG_X86_64 + if (guest_cpuid_has(vcpu, X86_FEATURE_LM)) { + struct kvm_segment cs_desc; + unsigned long cr4; + + /* Zero CR4.PCIDE before CR0.PG. */ + cr4 = kvm_read_cr4(vcpu); + if (cr4 & X86_CR4_PCIDE) + kvm_set_cr4(vcpu, cr4 & ~X86_CR4_PCIDE); + + /* A 32-bit code segment is required to clear EFER.LMA. */ + memset(&cs_desc, 0, sizeof(cs_desc)); + cs_desc.type = 0xb; + cs_desc.s = cs_desc.g = cs_desc.present = 1; + kvm_set_segment(vcpu, &cs_desc, VCPU_SREG_CS); + } +#endif + + /* For the 64-bit case, this will clear EFER.LMA. */ + cr0 = kvm_read_cr0(vcpu); + if (cr0 & X86_CR0_PE) + kvm_set_cr0(vcpu, cr0 & ~(X86_CR0_PG | X86_CR0_PE)); + +#ifdef CONFIG_X86_64 + if (guest_cpuid_has(vcpu, X86_FEATURE_LM)) { + unsigned long cr4, efer; + + /* Clear CR4.PAE before clearing EFER.LME. */ + cr4 = kvm_read_cr4(vcpu); + if (cr4 & X86_CR4_PAE) + kvm_set_cr4(vcpu, cr4 & ~X86_CR4_PAE); + + /* And finally go back to 32-bit mode. */ + efer = 0; + kvm_set_msr(vcpu, MSR_EFER, efer); + } +#endif + + /* + * Give leave_smm() a chance to make ISA-specific changes to the vCPU + * state (e.g. enter guest mode) before loading state from the SMM + * state-save area. + */ + if (static_call(kvm_x86_leave_smm)(vcpu, &smram)) + return X86EMUL_UNHANDLEABLE; + +#ifdef CONFIG_X86_64 + if (guest_cpuid_has(vcpu, X86_FEATURE_LM)) + return rsm_load_state_64(ctxt, &smram.smram64); + else +#endif + return rsm_load_state_32(ctxt, &smram.smram32); +} diff --git a/arch/x86/kvm/smm.h b/arch/x86/kvm/smm.h new file mode 100644 index 000000000000..a1cf2ac5bd78 --- /dev/null +++ b/arch/x86/kvm/smm.h @@ -0,0 +1,168 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef ASM_KVM_SMM_H +#define ASM_KVM_SMM_H + +#include <linux/build_bug.h> + +#ifdef CONFIG_KVM_SMM + + +/* + * 32 bit KVM's emulated SMM layout. Based on Intel P6 layout + * (https://www.sandpile.org/x86/smm.htm). + */ + +struct kvm_smm_seg_state_32 { + u32 flags; + u32 limit; + u32 base; +} __packed; + +struct kvm_smram_state_32 { + u32 reserved1[62]; + u32 smbase; + u32 smm_revision; + u16 io_inst_restart; + u16 auto_hlt_restart; + u32 io_restart_rdi; + u32 io_restart_rcx; + u32 io_restart_rsi; + u32 io_restart_rip; + u32 cr4; + + /* A20M#, CPL, shutdown and other reserved/undocumented fields */ + u16 reserved2; + u8 int_shadow; /* KVM extension */ + u8 reserved3[17]; + + struct kvm_smm_seg_state_32 ds; + struct kvm_smm_seg_state_32 fs; + struct kvm_smm_seg_state_32 gs; + struct kvm_smm_seg_state_32 idtr; /* IDTR has only base and limit */ + struct kvm_smm_seg_state_32 tr; + u32 reserved; + struct kvm_smm_seg_state_32 gdtr; /* GDTR has only base and limit */ + struct kvm_smm_seg_state_32 ldtr; + struct kvm_smm_seg_state_32 es; + struct kvm_smm_seg_state_32 cs; + struct kvm_smm_seg_state_32 ss; + + u32 es_sel; + u32 cs_sel; + u32 ss_sel; + u32 ds_sel; + u32 fs_sel; + u32 gs_sel; + u32 ldtr_sel; + u32 tr_sel; + + u32 dr7; + u32 dr6; + u32 gprs[8]; /* GPRS in the "natural" X86 order (EAX/ECX/EDX.../EDI) */ + u32 eip; + u32 eflags; + u32 cr3; + u32 cr0; +} __packed; + + +/* 64 bit KVM's emulated SMM layout. Based on AMD64 layout */ + +struct kvm_smm_seg_state_64 { + u16 selector; + u16 attributes; + u32 limit; + u64 base; +}; + +struct kvm_smram_state_64 { + + struct kvm_smm_seg_state_64 es; + struct kvm_smm_seg_state_64 cs; + struct kvm_smm_seg_state_64 ss; + struct kvm_smm_seg_state_64 ds; + struct kvm_smm_seg_state_64 fs; + struct kvm_smm_seg_state_64 gs; + struct kvm_smm_seg_state_64 gdtr; /* GDTR has only base and limit*/ + struct kvm_smm_seg_state_64 ldtr; + struct kvm_smm_seg_state_64 idtr; /* IDTR has only base and limit*/ + struct kvm_smm_seg_state_64 tr; + + /* I/O restart and auto halt restart are not implemented by KVM */ + u64 io_restart_rip; + u64 io_restart_rcx; + u64 io_restart_rsi; + u64 io_restart_rdi; + u32 io_restart_dword; + u32 reserved1; + u8 io_inst_restart; + u8 auto_hlt_restart; + u8 amd_nmi_mask; /* Documented in AMD BKDG as NMI mask, not used by KVM */ + u8 int_shadow; + u32 reserved2; + + u64 efer; + + /* + * Two fields below are implemented on AMD only, to store + * SVM guest vmcb address if the #SMI was received while in the guest mode. + */ + u64 svm_guest_flag; + u64 svm_guest_vmcb_gpa; + u64 svm_guest_virtual_int; /* unknown purpose, not implemented */ + + u32 reserved3[3]; + u32 smm_revison; + u32 smbase; + u32 reserved4[5]; + + /* ssp and svm_* fields below are not implemented by KVM */ + u64 ssp; + u64 svm_guest_pat; + u64 svm_host_efer; + u64 svm_host_cr4; + u64 svm_host_cr3; + u64 svm_host_cr0; + + u64 cr4; + u64 cr3; + u64 cr0; + u64 dr7; + u64 dr6; + u64 rflags; + u64 rip; + u64 gprs[16]; /* GPRS in a reversed "natural" X86 order (R15/R14/../RCX/RAX.) */ +}; + +union kvm_smram { + struct kvm_smram_state_64 smram64; + struct kvm_smram_state_32 smram32; + u8 bytes[512]; +}; + +static inline int kvm_inject_smi(struct kvm_vcpu *vcpu) +{ + kvm_make_request(KVM_REQ_SMI, vcpu); + return 0; +} + +static inline bool is_smm(struct kvm_vcpu *vcpu) +{ + return vcpu->arch.hflags & HF_SMM_MASK; +} + +void kvm_smm_changed(struct kvm_vcpu *vcpu, bool in_smm); +void enter_smm(struct kvm_vcpu *vcpu); +int emulator_leave_smm(struct x86_emulate_ctxt *ctxt); +void process_smi(struct kvm_vcpu *vcpu); +#else +static inline int kvm_inject_smi(struct kvm_vcpu *vcpu) { return -ENOTTY; } +static inline bool is_smm(struct kvm_vcpu *vcpu) { return false; } + +/* + * emulator_leave_smm is used as a function pointer, so the + * stub is defined in x86.c. + */ +#endif + +#endif diff --git a/arch/x86/kvm/svm/hyperv.c b/arch/x86/kvm/svm/hyperv.c new file mode 100644 index 000000000000..088f6429b24c --- /dev/null +++ b/arch/x86/kvm/svm/hyperv.c @@ -0,0 +1,18 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * AMD SVM specific code for Hyper-V on KVM. + * + * Copyright 2022 Red Hat, Inc. and/or its affiliates. + */ +#include "hyperv.h" + +void svm_hv_inject_synthetic_vmexit_post_tlb_flush(struct kvm_vcpu *vcpu) +{ + struct vcpu_svm *svm = to_svm(vcpu); + + svm->vmcb->control.exit_code = HV_SVM_EXITCODE_ENL; + svm->vmcb->control.exit_code_hi = 0; + svm->vmcb->control.exit_info_1 = HV_SVM_ENL_EXITCODE_TRAP_AFTER_FLUSH; + svm->vmcb->control.exit_info_2 = 0; + nested_svm_vmexit(svm); +} diff --git a/arch/x86/kvm/svm/hyperv.h b/arch/x86/kvm/svm/hyperv.h index 7d6d97968fb9..02f4784b5d44 100644 --- a/arch/x86/kvm/svm/hyperv.h +++ b/arch/x86/kvm/svm/hyperv.h @@ -9,27 +9,37 @@ #include <asm/mshyperv.h> #include "../hyperv.h" +#include "svm.h" -/* - * Hyper-V uses the software reserved 32 bytes in VMCB - * control area to expose SVM enlightenments to guests. - */ -struct hv_enlightenments { - struct __packed hv_enlightenments_control { - u32 nested_flush_hypercall:1; - u32 msr_bitmap:1; - u32 enlightened_npt_tlb: 1; - u32 reserved:29; - } __packed hv_enlightenments_control; - u32 hv_vp_id; - u64 hv_vm_id; - u64 partition_assist_page; - u64 reserved; -} __packed; +static inline void nested_svm_hv_update_vm_vp_ids(struct kvm_vcpu *vcpu) +{ + struct vcpu_svm *svm = to_svm(vcpu); + struct hv_vmcb_enlightenments *hve = &svm->nested.ctl.hv_enlightenments; + struct kvm_vcpu_hv *hv_vcpu = to_hv_vcpu(vcpu); -/* - * Hyper-V uses the software reserved clean bit in VMCB - */ -#define VMCB_HV_NESTED_ENLIGHTENMENTS VMCB_SW + if (!hv_vcpu) + return; + + hv_vcpu->nested.pa_page_gpa = hve->partition_assist_page; + hv_vcpu->nested.vm_id = hve->hv_vm_id; + hv_vcpu->nested.vp_id = hve->hv_vp_id; +} + +static inline bool nested_svm_l2_tlb_flush_enabled(struct kvm_vcpu *vcpu) +{ + struct vcpu_svm *svm = to_svm(vcpu); + struct hv_vmcb_enlightenments *hve = &svm->nested.ctl.hv_enlightenments; + struct kvm_vcpu_hv *hv_vcpu = to_hv_vcpu(vcpu); + + if (!hv_vcpu) + return false; + + if (!hve->hv_enlightenments_control.nested_flush_hypercall) + return false; + + return hv_vcpu->vp_assist_page.nested_control.features.directhypercall; +} + +void svm_hv_inject_synthetic_vmexit_post_tlb_flush(struct kvm_vcpu *vcpu); #endif /* __ARCH_X86_KVM_SVM_HYPERV_H__ */ diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c index 4c620999d230..bc9cd7086fa9 100644 --- a/arch/x86/kvm/svm/nested.c +++ b/arch/x86/kvm/svm/nested.c @@ -25,6 +25,7 @@ #include "trace.h" #include "mmu.h" #include "x86.h" +#include "smm.h" #include "cpuid.h" #include "lapic.h" #include "svm.h" @@ -149,8 +150,12 @@ void recalc_intercepts(struct vcpu_svm *svm) vmcb_clr_intercept(c, INTERCEPT_VINTR); } - /* We don't want to see VMMCALLs from a nested guest */ - vmcb_clr_intercept(c, INTERCEPT_VMMCALL); + /* + * We want to see VMMCALLs from a nested guest only when Hyper-V L2 TLB + * flush feature is enabled. + */ + if (!nested_svm_l2_tlb_flush_enabled(&svm->vcpu)) + vmcb_clr_intercept(c, INTERCEPT_VMMCALL); for (i = 0; i < MAX_INTERCEPT; i++) c->intercepts[i] |= g->intercepts[i]; @@ -179,8 +184,7 @@ void recalc_intercepts(struct vcpu_svm *svm) */ static bool nested_svm_vmrun_msrpm(struct vcpu_svm *svm) { - struct hv_enlightenments *hve = - (struct hv_enlightenments *)svm->nested.ctl.reserved_sw; + struct hv_vmcb_enlightenments *hve = &svm->nested.ctl.hv_enlightenments; int i; /* @@ -194,7 +198,7 @@ static bool nested_svm_vmrun_msrpm(struct vcpu_svm *svm) if (!svm->nested.force_msr_bitmap_recalc && kvm_hv_hypercall_enabled(&svm->vcpu) && hve->hv_enlightenments_control.msr_bitmap && - (svm->nested.ctl.clean & BIT(VMCB_HV_NESTED_ENLIGHTENMENTS))) + (svm->nested.ctl.clean & BIT(HV_VMCB_NESTED_ENLIGHTENMENTS))) goto set_msrpm_base_pa; if (!(vmcb12_is_intercept(&svm->nested.ctl, INTERCEPT_MSR_PROT))) @@ -369,8 +373,8 @@ void __nested_copy_vmcb_control_to_cache(struct kvm_vcpu *vcpu, /* Hyper-V extensions (Enlightened VMCB) */ if (kvm_hv_hypercall_enabled(vcpu)) { to->clean = from->clean; - memcpy(to->reserved_sw, from->reserved_sw, - sizeof(struct hv_enlightenments)); + memcpy(&to->hv_enlightenments, &from->hv_enlightenments, + sizeof(to->hv_enlightenments)); } } @@ -474,6 +478,15 @@ static void nested_save_pending_event_to_vmcb12(struct vcpu_svm *svm, static void nested_svm_transition_tlb_flush(struct kvm_vcpu *vcpu) { /* + * KVM_REQ_HV_TLB_FLUSH flushes entries from either L1's VP_ID or + * L2's VP_ID upon request from the guest. Make sure we check for + * pending entries in the right FIFO upon L1/L2 transition as these + * requests are put by other vCPUs asynchronously. + */ + if (to_hv_vcpu(vcpu) && npt_enabled) + kvm_make_request(KVM_REQ_HV_TLB_FLUSH, vcpu); + + /* * TODO: optimize unconditional TLB flush/MMU sync. A partial list of * things to fix before this can be conditional: * @@ -800,6 +813,8 @@ int enter_svm_guest_mode(struct kvm_vcpu *vcpu, u64 vmcb12_gpa, if (kvm_vcpu_apicv_active(vcpu)) kvm_make_request(KVM_REQ_APICV_UPDATE, vcpu); + nested_svm_hv_update_vm_vp_ids(vcpu); + return 0; } @@ -822,6 +837,13 @@ int nested_svm_vmrun(struct kvm_vcpu *vcpu) return 1; } + /* This fails when VP assist page is enabled but the supplied GPA is bogus */ + ret = kvm_hv_verify_vp_assist(vcpu); + if (ret) { + kvm_inject_gp(vcpu, 0); + return ret; + } + vmcb12_gpa = svm->vmcb->save.rax; ret = kvm_vcpu_map(vcpu, gpa_to_gfn(vmcb12_gpa), &map); if (ret == -EINVAL) { @@ -1091,6 +1113,12 @@ int nested_svm_vmexit(struct vcpu_svm *svm) static void nested_svm_triple_fault(struct kvm_vcpu *vcpu) { + struct vcpu_svm *svm = to_svm(vcpu); + + if (!vmcb12_is_intercept(&svm->nested.ctl, INTERCEPT_SHUTDOWN)) + return; + + kvm_clear_request(KVM_REQ_TRIPLE_FAULT, vcpu); nested_svm_simple_vmexit(to_svm(vcpu), SVM_EXIT_SHUTDOWN); } @@ -1125,6 +1153,9 @@ void svm_free_nested(struct vcpu_svm *svm) if (!svm->nested.initialized) return; + if (WARN_ON_ONCE(svm->vmcb != svm->vmcb01.ptr)) + svm_switch_vmcb(svm, &svm->vmcb01); + svm_vcpu_free_msrpm(svm->nested.msrpm); svm->nested.msrpm = NULL; @@ -1143,9 +1174,6 @@ void svm_free_nested(struct vcpu_svm *svm) svm->nested.initialized = false; } -/* - * Forcibly leave nested mode in order to be able to reset the VCPU later on. - */ void svm_leave_nested(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); @@ -1377,6 +1405,7 @@ static int svm_check_nested_events(struct kvm_vcpu *vcpu) return 0; } +#ifdef CONFIG_KVM_SMM if (vcpu->arch.smi_pending && !svm_smi_blocked(vcpu)) { if (block_nested_events) return -EBUSY; @@ -1385,6 +1414,7 @@ static int svm_check_nested_events(struct kvm_vcpu *vcpu) nested_svm_simple_vmexit(svm, SVM_EXIT_SMI); return 0; } +#endif if (vcpu->arch.nmi_pending && !svm_nmi_blocked(vcpu)) { if (block_nested_events) @@ -1411,6 +1441,7 @@ static int svm_check_nested_events(struct kvm_vcpu *vcpu) int nested_svm_exit_special(struct vcpu_svm *svm) { u32 exit_code = svm->vmcb->control.exit_code; + struct kvm_vcpu *vcpu = &svm->vcpu; switch (exit_code) { case SVM_EXIT_INTR: @@ -1429,6 +1460,13 @@ int nested_svm_exit_special(struct vcpu_svm *svm) return NESTED_EXIT_HOST; break; } + case SVM_EXIT_VMMCALL: + /* Hyper-V L2 TLB flush hypercall is handled by L0 */ + if (guest_hv_cpuid_has_l2_tlb_flush(vcpu) && + nested_svm_l2_tlb_flush_enabled(vcpu) && + kvm_hv_is_tlb_flush_hcall(vcpu)) + return NESTED_EXIT_HOST; + break; default: break; } @@ -1479,7 +1517,7 @@ static void nested_copy_vmcb_cache_to_control(struct vmcb_control_area *dst, dst->virt_ext = from->virt_ext; dst->pause_filter_count = from->pause_filter_count; dst->pause_filter_thresh = from->pause_filter_thresh; - /* 'clean' and 'reserved_sw' are not changed by KVM */ + /* 'clean' and 'hv_enlightenments' are not changed by KVM */ } static int svm_get_nested_state(struct kvm_vcpu *vcpu, @@ -1709,6 +1747,9 @@ static bool svm_get_nested_state_pages(struct kvm_vcpu *vcpu) return false; } + if (kvm_hv_verify_vp_assist(vcpu)) + return false; + return true; } @@ -1720,4 +1761,5 @@ struct kvm_x86_nested_ops svm_nested_ops = { .get_nested_state_pages = svm_get_nested_state_pages, .get_state = svm_get_nested_state, .set_state = svm_set_nested_state, + .hv_inject_synthetic_vmexit_post_tlb_flush = svm_hv_inject_synthetic_vmexit_post_tlb_flush, }; diff --git a/arch/x86/kvm/svm/pmu.c b/arch/x86/kvm/svm/pmu.c index b68956299fa8..0e313fbae055 100644 --- a/arch/x86/kvm/svm/pmu.c +++ b/arch/x86/kvm/svm/pmu.c @@ -159,7 +159,7 @@ static int amd_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) data &= ~pmu->reserved_bits; if (data != pmc->eventsel) { pmc->eventsel = data; - reprogram_counter(pmc); + kvm_pmu_request_counter_reprogam(pmc); } return 0; } @@ -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; @@ -207,11 +208,11 @@ 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); - pmc->counter = pmc->eventsel = 0; + pmc->counter = pmc->prev_counter = pmc->eventsel = 0; } } diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c index 28064060413a..69dbf17f0d6a 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 */ @@ -2648,7 +2648,7 @@ static int setup_vmgexit_scratch(struct vcpu_svm *svm, bool sync, u64 len) ghcb_scratch_beg = control->ghcb_gpa + offsetof(struct ghcb, shared_buffer); ghcb_scratch_end = control->ghcb_gpa + - offsetof(struct ghcb, reserved_1); + offsetof(struct ghcb, reserved_0xff0); /* * If the scratch area begins within the GHCB, it must be diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index 58f0077d9357..91352d692845 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -6,6 +6,7 @@ #include "mmu.h" #include "kvm_cache_regs.h" #include "x86.h" +#include "smm.h" #include "cpuid.h" #include "pmu.h" @@ -245,7 +246,7 @@ 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 @@ -346,12 +347,6 @@ int svm_set_efer(struct kvm_vcpu *vcpu, u64 efer) return 0; } -static int is_external_interrupt(u32 info) -{ - info &= SVM_EVTINJ_TYPE_MASK | SVM_EVTINJ_VALID; - return info == (SVM_EVTINJ_VALID | SVM_EVTINJ_TYPE_INTR); -} - static u32 svm_get_interrupt_shadow(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); @@ -581,12 +576,7 @@ 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 +587,7 @@ 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 +636,37 @@ 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 +715,15 @@ 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 +1419,7 @@ 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) @@ -1439,6 +1433,7 @@ static void svm_vcpu_free(struct kvm_vcpu *vcpu) */ svm_clear_current_vmcb(svm->vmcb); + svm_leave_nested(vcpu); svm_free_nested(svm); sev_free_vcpu(vcpu); @@ -1450,7 +1445,7 @@ 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 +1457,7 @@ 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 +1482,7 @@ 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; @@ -2714,8 +2709,6 @@ static int svm_get_msr_feature(struct kvm_msr_entry *msr) if (boot_cpu_has(X86_FEATURE_LFENCE_RDTSC)) msr->data |= MSR_F10H_DECFG_LFENCE_SERIALIZE; break; - case MSR_IA32_PERF_CAPABILITIES: - return 0; default: return KVM_MSR_RET_INVALID; } @@ -3426,15 +3419,6 @@ static int svm_handle_exit(struct kvm_vcpu *vcpu, fastpath_t exit_fastpath) return 0; } - if (is_external_interrupt(svm->vmcb->control.exit_int_info) && - exit_code != SVM_EXIT_EXCP_BASE + PF_VECTOR && - exit_code != SVM_EXIT_NPF && exit_code != SVM_EXIT_TASK_SWITCH && - exit_code != SVM_EXIT_INTR && exit_code != SVM_EXIT_NMI) - printk(KERN_ERR "%s: unexpected exit_int_info 0x%x " - "exit_code 0x%x\n", - __func__, svm->vmcb->control.exit_int_info, - exit_code); - if (exit_fastpath != EXIT_FASTPATH_NONE) return 1; @@ -3443,7 +3427,7 @@ 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 +3435,7 @@ 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); /* @@ -3739,6 +3723,13 @@ static void svm_flush_tlb_current(struct kvm_vcpu *vcpu) struct vcpu_svm *svm = to_svm(vcpu); /* + * Unlike VMX, SVM doesn't provide a way to flush only NPT TLB entries. + * A TLB flush for the current ASID flushes both "host" and "guest" TLB + * entries, and thus is a superset of Hyper-V's fine grained flushing. + */ + kvm_hv_vcpu_purge_flush_tlb(vcpu); + + /* * Flush only the current ASID even if the TLB flush was invoked via * kvm_flush_remote_tlbs(). Although flushing remote TLBs requires all * ASIDs to be flushed, KVM uses a single ASID for L1 and L2, and @@ -3911,30 +3902,16 @@ 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 +3919,7 @@ 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 +3976,15 @@ 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; @@ -4149,6 +4108,8 @@ static bool svm_has_emulated_msr(struct kvm *kvm, u32 index) case MSR_IA32_VMX_BASIC ... MSR_IA32_VMX_VMFUNC: return false; case MSR_IA32_SMBASE: + if (!IS_ENABLED(CONFIG_KVM_SMM)) + return false; /* SEV-ES guests do not support SMM, so report false */ if (kvm && sev_es_guest(kvm)) return false; @@ -4405,6 +4366,7 @@ static void svm_setup_mce(struct kvm_vcpu *vcpu) vcpu->arch.mcg_cap &= 0x1ff; } +#ifdef CONFIG_KVM_SMM bool svm_smi_blocked(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); @@ -4432,7 +4394,7 @@ static int svm_smi_allowed(struct kvm_vcpu *vcpu, bool for_injection) return 1; } -static int svm_enter_smm(struct kvm_vcpu *vcpu, char *smstate) +static int svm_enter_smm(struct kvm_vcpu *vcpu, union kvm_smram *smram) { struct vcpu_svm *svm = to_svm(vcpu); struct kvm_host_map map_save; @@ -4441,10 +4403,16 @@ static int svm_enter_smm(struct kvm_vcpu *vcpu, char *smstate) if (!is_guest_mode(vcpu)) return 0; - /* FED8h - SVM Guest */ - put_smstate(u64, smstate, 0x7ed8, 1); - /* FEE0h - SVM Guest VMCB Physical Address */ - put_smstate(u64, smstate, 0x7ee0, svm->nested.vmcb12_gpa); + /* + * 32-bit SMRAM format doesn't preserve EFER and SVM state. Userspace is + * responsible for ensuring nested SVM and SMIs are mutually exclusive. + */ + + if (!guest_cpuid_has(vcpu, X86_FEATURE_LM)) + return 1; + + smram->smram64.svm_guest_flag = 1; + smram->smram64.svm_guest_vmcb_gpa = svm->nested.vmcb12_gpa; svm->vmcb->save.rax = vcpu->arch.regs[VCPU_REGS_RAX]; svm->vmcb->save.rsp = vcpu->arch.regs[VCPU_REGS_RSP]; @@ -4466,8 +4434,7 @@ static int svm_enter_smm(struct kvm_vcpu *vcpu, char *smstate) * that, see svm_prepare_switch_to_guest()) which must be * preserved. */ - if (kvm_vcpu_map(vcpu, gpa_to_gfn(svm->nested.hsave_msr), - &map_save) == -EINVAL) + if (kvm_vcpu_map(vcpu, gpa_to_gfn(svm->nested.hsave_msr), &map_save)) return 1; BUILD_BUG_ON(offsetof(struct vmcb, save) != 0x400); @@ -4479,34 +4446,33 @@ static int svm_enter_smm(struct kvm_vcpu *vcpu, char *smstate) return 0; } -static int svm_leave_smm(struct kvm_vcpu *vcpu, const char *smstate) +static int svm_leave_smm(struct kvm_vcpu *vcpu, const union kvm_smram *smram) { struct vcpu_svm *svm = to_svm(vcpu); struct kvm_host_map map, map_save; - u64 saved_efer, vmcb12_gpa; struct vmcb *vmcb12; int ret; + const struct kvm_smram_state_64 *smram64 = &smram->smram64; + if (!guest_cpuid_has(vcpu, X86_FEATURE_LM)) return 0; /* Non-zero if SMI arrived while vCPU was in guest mode. */ - if (!GET_SMSTATE(u64, smstate, 0x7ed8)) + if (!smram64->svm_guest_flag) return 0; if (!guest_cpuid_has(vcpu, X86_FEATURE_SVM)) return 1; - saved_efer = GET_SMSTATE(u64, smstate, 0x7ed0); - if (!(saved_efer & EFER_SVME)) + if (!(smram64->efer & EFER_SVME)) return 1; - vmcb12_gpa = GET_SMSTATE(u64, smstate, 0x7ee0); - if (kvm_vcpu_map(vcpu, gpa_to_gfn(vmcb12_gpa), &map) == -EINVAL) + if (kvm_vcpu_map(vcpu, gpa_to_gfn(smram64->svm_guest_vmcb_gpa), &map)) return 1; ret = 1; - if (kvm_vcpu_map(vcpu, gpa_to_gfn(svm->nested.hsave_msr), &map_save) == -EINVAL) + if (kvm_vcpu_map(vcpu, gpa_to_gfn(svm->nested.hsave_msr), &map_save)) goto unmap_map; if (svm_allocate_nested(svm)) @@ -4528,7 +4494,7 @@ static int svm_leave_smm(struct kvm_vcpu *vcpu, const char *smstate) vmcb12 = map.hva; nested_copy_vmcb_control_to_cache(svm, &vmcb12->control); nested_copy_vmcb_save_to_cache(svm, &vmcb12->save); - ret = enter_svm_guest_mode(vcpu, vmcb12_gpa, vmcb12, false); + ret = enter_svm_guest_mode(vcpu, smram64->svm_guest_vmcb_gpa, vmcb12, false); if (ret) goto unmap_save; @@ -4554,6 +4520,7 @@ static void svm_enable_smi_window(struct kvm_vcpu *vcpu) /* We must be in SMM; RSM will cause a vmexit anyway. */ } } +#endif static bool svm_can_emulate_instruction(struct kvm_vcpu *vcpu, int emul_type, void *insn, int insn_len) @@ -4829,10 +4796,12 @@ static struct kvm_x86_ops svm_x86_ops __initdata = { .pi_update_irte = avic_pi_update_irte, .setup_mce = svm_setup_mce, +#ifdef CONFIG_KVM_SMM .smi_allowed = svm_smi_allowed, .enter_smm = svm_enter_smm, .leave_smm = svm_leave_smm, .enable_smi_window = svm_enable_smi_window, +#endif .mem_enc_ioctl = sev_mem_enc_ioctl, .mem_enc_register_region = sev_mem_enc_register_region, @@ -4898,6 +4867,7 @@ static __init void svm_set_cpu_caps(void) { kvm_set_cpu_caps(); + kvm_caps.supported_perf_cap = 0; kvm_caps.supported_xss = 0; /* CPUID 0x80000001 and 0x8000000A (SVM features) */ diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h index 6a7686bf6900..4826e6cc611b 100644 --- a/arch/x86/kvm/svm/svm.h +++ b/arch/x86/kvm/svm/svm.h @@ -151,7 +151,10 @@ struct vmcb_ctrl_area_cached { u64 nested_cr3; u64 virt_ext; u32 clean; - u8 reserved_sw[32]; + union { + struct hv_vmcb_enlightenments hv_enlightenments; + u8 reserved_sw[32]; + }; }; struct svm_nested_state { @@ -209,7 +212,6 @@ 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 +283,6 @@ struct vcpu_svm { }; struct svm_cpu_data { - int cpu; - u64 asid_generation; u32 max_asid; u32 next_asid; @@ -290,13 +290,15 @@ 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 +685,7 @@ 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_onhyperv.c b/arch/x86/kvm/svm/svm_onhyperv.c index 8cdc62c74a96..26a89d0da93e 100644 --- a/arch/x86/kvm/svm/svm_onhyperv.c +++ b/arch/x86/kvm/svm/svm_onhyperv.c @@ -14,9 +14,9 @@ #include "kvm_onhyperv.h" #include "svm_onhyperv.h" -int svm_hv_enable_direct_tlbflush(struct kvm_vcpu *vcpu) +int svm_hv_enable_l2_tlb_flush(struct kvm_vcpu *vcpu) { - struct hv_enlightenments *hve; + struct hv_vmcb_enlightenments *hve; struct hv_partition_assist_pg **p_hv_pa_pg = &to_kvm_hv(vcpu->kvm)->hv_pa_pg; @@ -26,13 +26,13 @@ int svm_hv_enable_direct_tlbflush(struct kvm_vcpu *vcpu) if (!*p_hv_pa_pg) return -ENOMEM; - hve = (struct hv_enlightenments *)to_svm(vcpu)->vmcb->control.reserved_sw; + hve = &to_svm(vcpu)->vmcb->control.hv_enlightenments; hve->partition_assist_page = __pa(*p_hv_pa_pg); hve->hv_vm_id = (unsigned long)vcpu->kvm; if (!hve->hv_enlightenments_control.nested_flush_hypercall) { hve->hv_enlightenments_control.nested_flush_hypercall = 1; - vmcb_mark_dirty(to_svm(vcpu)->vmcb, VMCB_HV_NESTED_ENLIGHTENMENTS); + vmcb_mark_dirty(to_svm(vcpu)->vmcb, HV_VMCB_NESTED_ENLIGHTENMENTS); } return 0; diff --git a/arch/x86/kvm/svm/svm_onhyperv.h b/arch/x86/kvm/svm/svm_onhyperv.h index e2fc59380465..45faf84476ce 100644 --- a/arch/x86/kvm/svm/svm_onhyperv.h +++ b/arch/x86/kvm/svm/svm_onhyperv.h @@ -13,12 +13,14 @@ static struct kvm_x86_ops svm_x86_ops; -int svm_hv_enable_direct_tlbflush(struct kvm_vcpu *vcpu); +int svm_hv_enable_l2_tlb_flush(struct kvm_vcpu *vcpu); static inline void svm_hv_init_vmcb(struct vmcb *vmcb) { - struct hv_enlightenments *hve = - (struct hv_enlightenments *)vmcb->control.reserved_sw; + struct hv_vmcb_enlightenments *hve = &vmcb->control.hv_enlightenments; + + BUILD_BUG_ON(sizeof(vmcb->control.hv_enlightenments) != + sizeof(vmcb->control.reserved_sw)); if (npt_enabled && ms_hyperv.nested_features & HV_X64_NESTED_ENLIGHTENED_TLB) @@ -51,8 +53,8 @@ static inline void svm_hv_hardware_setup(void) vp_ap->nested_control.features.directhypercall = 1; } - svm_x86_ops.enable_direct_tlbflush = - svm_hv_enable_direct_tlbflush; + svm_x86_ops.enable_l2_tlb_flush = + svm_hv_enable_l2_tlb_flush; } } @@ -60,23 +62,20 @@ static inline void svm_hv_vmcb_dirty_nested_enlightenments( struct kvm_vcpu *vcpu) { struct vmcb *vmcb = to_svm(vcpu)->vmcb; - struct hv_enlightenments *hve = - (struct hv_enlightenments *)vmcb->control.reserved_sw; + struct hv_vmcb_enlightenments *hve = &vmcb->control.hv_enlightenments; if (hve->hv_enlightenments_control.msr_bitmap) - vmcb_mark_dirty(vmcb, VMCB_HV_NESTED_ENLIGHTENMENTS); + vmcb_mark_dirty(vmcb, HV_VMCB_NESTED_ENLIGHTENMENTS); } -static inline void svm_hv_update_vp_id(struct vmcb *vmcb, - struct kvm_vcpu *vcpu) +static inline void svm_hv_update_vp_id(struct vmcb *vmcb, struct kvm_vcpu *vcpu) { - struct hv_enlightenments *hve = - (struct hv_enlightenments *)vmcb->control.reserved_sw; + struct hv_vmcb_enlightenments *hve = &vmcb->control.hv_enlightenments; u32 vp_index = kvm_hv_get_vpindex(vcpu); if (hve->hv_vp_id != vp_index) { hve->hv_vp_id = vp_index; - vmcb_mark_dirty(vmcb, VMCB_HV_NESTED_ENLIGHTENMENTS); + vmcb_mark_dirty(vmcb, HV_VMCB_NESTED_ENLIGHTENMENTS); } } #else 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/trace.h b/arch/x86/kvm/trace.h index bc25589ad588..83843379813e 100644 --- a/arch/x86/kvm/trace.h +++ b/arch/x86/kvm/trace.h @@ -113,12 +113,13 @@ TRACE_EVENT(kvm_hv_hypercall_done, * Tracepoint for Xen hypercall. */ TRACE_EVENT(kvm_xen_hypercall, - TP_PROTO(unsigned long nr, unsigned long a0, unsigned long a1, - unsigned long a2, unsigned long a3, unsigned long a4, - unsigned long a5), - TP_ARGS(nr, a0, a1, a2, a3, a4, a5), + TP_PROTO(u8 cpl, unsigned long nr, + unsigned long a0, unsigned long a1, unsigned long a2, + unsigned long a3, unsigned long a4, unsigned long a5), + TP_ARGS(cpl, nr, a0, a1, a2, a3, a4, a5), TP_STRUCT__entry( + __field(u8, cpl) __field(unsigned long, nr) __field(unsigned long, a0) __field(unsigned long, a1) @@ -129,6 +130,7 @@ TRACE_EVENT(kvm_xen_hypercall, ), TP_fast_assign( + __entry->cpl = cpl; __entry->nr = nr; __entry->a0 = a0; __entry->a1 = a1; @@ -138,8 +140,9 @@ TRACE_EVENT(kvm_xen_hypercall, __entry->a4 = a5; ), - TP_printk("nr 0x%lx a0 0x%lx a1 0x%lx a2 0x%lx a3 0x%lx a4 0x%lx a5 %lx", - __entry->nr, __entry->a0, __entry->a1, __entry->a2, + TP_printk("cpl %d nr 0x%lx a0 0x%lx a1 0x%lx a2 0x%lx a3 0x%lx a4 0x%lx a5 %lx", + __entry->cpl, __entry->nr, + __entry->a0, __entry->a1, __entry->a2, __entry->a3, __entry->a4, __entry->a5) ); @@ -1547,38 +1550,41 @@ TRACE_EVENT(kvm_hv_timer_state, * Tracepoint for kvm_hv_flush_tlb. */ TRACE_EVENT(kvm_hv_flush_tlb, - TP_PROTO(u64 processor_mask, u64 address_space, u64 flags), - TP_ARGS(processor_mask, address_space, flags), + TP_PROTO(u64 processor_mask, u64 address_space, u64 flags, bool guest_mode), + TP_ARGS(processor_mask, address_space, flags, guest_mode), TP_STRUCT__entry( __field(u64, processor_mask) __field(u64, address_space) __field(u64, flags) + __field(bool, guest_mode) ), TP_fast_assign( __entry->processor_mask = processor_mask; __entry->address_space = address_space; __entry->flags = flags; + __entry->guest_mode = guest_mode; ), - TP_printk("processor_mask 0x%llx address_space 0x%llx flags 0x%llx", + TP_printk("processor_mask 0x%llx address_space 0x%llx flags 0x%llx %s", __entry->processor_mask, __entry->address_space, - __entry->flags) + __entry->flags, __entry->guest_mode ? "(L2)" : "") ); /* * Tracepoint for kvm_hv_flush_tlb_ex. */ TRACE_EVENT(kvm_hv_flush_tlb_ex, - TP_PROTO(u64 valid_bank_mask, u64 format, u64 address_space, u64 flags), - TP_ARGS(valid_bank_mask, format, address_space, flags), + TP_PROTO(u64 valid_bank_mask, u64 format, u64 address_space, u64 flags, bool guest_mode), + TP_ARGS(valid_bank_mask, format, address_space, flags, guest_mode), TP_STRUCT__entry( __field(u64, valid_bank_mask) __field(u64, format) __field(u64, address_space) __field(u64, flags) + __field(bool, guest_mode) ), TP_fast_assign( @@ -1586,12 +1592,14 @@ TRACE_EVENT(kvm_hv_flush_tlb_ex, __entry->format = format; __entry->address_space = address_space; __entry->flags = flags; + __entry->guest_mode = guest_mode; ), TP_printk("valid_bank_mask 0x%llx format 0x%llx " - "address_space 0x%llx flags 0x%llx", + "address_space 0x%llx flags 0x%llx %s", __entry->valid_bank_mask, __entry->format, - __entry->address_space, __entry->flags) + __entry->address_space, __entry->flags, + __entry->guest_mode ? "(L2)" : "") ); /* diff --git a/arch/x86/kvm/vmx/capabilities.h b/arch/x86/kvm/vmx/capabilities.h index 87c4e46daf37..cd2ac9536c99 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 @@ -397,41 +395,6 @@ static inline bool vmx_pebs_supported(void) return boot_cpu_has(X86_FEATURE_PEBS) && kvm_pmu_cap.pebs_ept; } -static inline u64 vmx_get_perf_capabilities(void) -{ - u64 perf_cap = PMU_CAP_FW_WRITES; - u64 host_perf_cap = 0; - - if (!enable_pmu) - return 0; - - 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 (vmx_pebs_supported()) { - perf_cap |= host_perf_cap & PERF_CAP_PEBS_MASK; - if ((perf_cap & PERF_CAP_PEBS_FORMAT) < 4) - perf_cap &= ~PERF_CAP_PEBS_BASELINE; - } - - 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/evmcs.c b/arch/x86/kvm/vmx/hyperv.c index d8b23c96d627..ae03d1fe0355 100644 --- a/arch/x86/kvm/vmx/evmcs.c +++ b/arch/x86/kvm/vmx/hyperv.c @@ -3,9 +3,9 @@ #include <linux/errno.h> #include <linux/smp.h> -#include "../hyperv.h" #include "../cpuid.h" -#include "evmcs.h" +#include "hyperv.h" +#include "nested.h" #include "vmcs.h" #include "vmx.h" #include "trace.h" @@ -322,24 +322,17 @@ const struct evmcs_field vmcs_field_to_evmcs_1[] = { }; const unsigned int nr_evmcs_1_fields = ARRAY_SIZE(vmcs_field_to_evmcs_1); -bool nested_enlightened_vmentry(struct kvm_vcpu *vcpu, u64 *evmcs_gpa) +u64 nested_get_evmptr(struct kvm_vcpu *vcpu) { - struct hv_vp_assist_page assist_page; - - *evmcs_gpa = -1ull; - - if (unlikely(!kvm_hv_get_assist_page(vcpu, &assist_page))) - return false; - - if (unlikely(!assist_page.enlighten_vmentry)) - return false; + struct kvm_vcpu_hv *hv_vcpu = to_hv_vcpu(vcpu); - if (unlikely(!evmptr_is_valid(assist_page.current_nested_vmcs))) - return false; + if (unlikely(kvm_hv_get_assist_page(vcpu))) + return EVMPTR_INVALID; - *evmcs_gpa = assist_page.current_nested_vmcs; + if (unlikely(!hv_vcpu->vp_assist_page.enlighten_vmentry)) + return EVMPTR_INVALID; - return true; + return hv_vcpu->vp_assist_page.current_nested_vmcs; } uint16_t nested_get_evmcs_version(struct kvm_vcpu *vcpu) @@ -507,3 +500,23 @@ int nested_enable_evmcs(struct kvm_vcpu *vcpu, return 0; } + +bool nested_evmcs_l2_tlb_flush_enabled(struct kvm_vcpu *vcpu) +{ + struct kvm_vcpu_hv *hv_vcpu = to_hv_vcpu(vcpu); + struct vcpu_vmx *vmx = to_vmx(vcpu); + struct hv_enlightened_vmcs *evmcs = vmx->nested.hv_evmcs; + + if (!hv_vcpu || !evmcs) + return false; + + if (!evmcs->hv_enlightenments_control.nested_flush_hypercall) + return false; + + return hv_vcpu->vp_assist_page.nested_control.features.directhypercall; +} + +void vmx_hv_inject_synthetic_vmexit_post_tlb_flush(struct kvm_vcpu *vcpu) +{ + nested_vmx_vmexit(vcpu, HV_VMX_SYNTHETIC_EXIT_REASON_TRAP_AFTER_FLUSH, 0, 0); +} diff --git a/arch/x86/kvm/vmx/evmcs.h b/arch/x86/kvm/vmx/hyperv.h index 6f746ef3c038..571e7929d14e 100644 --- a/arch/x86/kvm/vmx/evmcs.h +++ b/arch/x86/kvm/vmx/hyperv.h @@ -1,6 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0 */ -#ifndef __KVM_X86_VMX_EVMCS_H -#define __KVM_X86_VMX_EVMCS_H +#ifndef __KVM_X86_VMX_HYPERV_H +#define __KVM_X86_VMX_HYPERV_H #include <linux/jump_label.h> @@ -8,6 +8,8 @@ #include <asm/mshyperv.h> #include <asm/vmx.h> +#include "../hyperv.h" + #include "capabilities.h" #include "vmcs.h" #include "vmcs12.h" @@ -235,11 +237,13 @@ enum nested_evmptrld_status { EVMPTRLD_ERROR, }; -bool nested_enlightened_vmentry(struct kvm_vcpu *vcpu, u64 *evmcs_gpa); +u64 nested_get_evmptr(struct kvm_vcpu *vcpu); uint16_t nested_get_evmcs_version(struct kvm_vcpu *vcpu); int nested_enable_evmcs(struct kvm_vcpu *vcpu, uint16_t *vmcs_version); void nested_evmcs_filter_control_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 *pdata); int nested_evmcs_check_controls(struct vmcs12 *vmcs12); +bool nested_evmcs_l2_tlb_flush_enabled(struct kvm_vcpu *vcpu); +void vmx_hv_inject_synthetic_vmexit_post_tlb_flush(struct kvm_vcpu *vcpu); -#endif /* __KVM_X86_VMX_EVMCS_H */ +#endif /* __KVM_X86_VMX_HYPERV_H */ diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c index 0c62352dda6a..b28be793de29 100644 --- a/arch/x86/kvm/vmx/nested.c +++ b/arch/x86/kvm/vmx/nested.c @@ -7,7 +7,6 @@ #include <asm/mmu_context.h> #include "cpuid.h" -#include "evmcs.h" #include "hyperv.h" #include "mmu.h" #include "nested.h" @@ -16,6 +15,7 @@ #include "trace.h" #include "vmx.h" #include "x86.h" +#include "smm.h" static bool __read_mostly enable_shadow_vmcs = 1; module_param_named(enable_shadow_vmcs, enable_shadow_vmcs, bool, S_IRUGO); @@ -225,6 +225,7 @@ static void vmx_disable_shadow_vmcs(struct vcpu_vmx *vmx) static inline void nested_release_evmcs(struct kvm_vcpu *vcpu) { + struct kvm_vcpu_hv *hv_vcpu = to_hv_vcpu(vcpu); struct vcpu_vmx *vmx = to_vmx(vcpu); if (evmptr_is_valid(vmx->nested.hv_evmcs_vmptr)) { @@ -233,6 +234,12 @@ static inline void nested_release_evmcs(struct kvm_vcpu *vcpu) } vmx->nested.hv_evmcs_vmptr = EVMPTR_INVALID; + + if (hv_vcpu) { + hv_vcpu->nested.pa_page_gpa = INVALID_GPA; + hv_vcpu->nested.vm_id = 0; + hv_vcpu->nested.vp_id = 0; + } } static void vmx_sync_vmcs_host_state(struct vcpu_vmx *vmx, @@ -1126,6 +1133,15 @@ static void nested_vmx_transition_tlb_flush(struct kvm_vcpu *vcpu, struct vcpu_vmx *vmx = to_vmx(vcpu); /* + * KVM_REQ_HV_TLB_FLUSH flushes entries from either L1's VP_ID or + * L2's VP_ID upon request from the guest. Make sure we check for + * pending entries in the right FIFO upon L1/L2 transition as these + * requests are put by other vCPUs asynchronously. + */ + if (to_hv_vcpu(vcpu) && enable_ept) + kvm_make_request(KVM_REQ_HV_TLB_FLUSH, vcpu); + + /* * If vmcs12 doesn't use VPID, L1 expects linear and combined mappings * for *all* contexts to be flushed on VM-Enter/VM-Exit, i.e. it's a * full TLB flush from the guest's perspective. This is required even @@ -1557,12 +1573,20 @@ static void copy_enlightened_to_vmcs12(struct vcpu_vmx *vmx, u32 hv_clean_fields { struct vmcs12 *vmcs12 = vmx->nested.cached_vmcs12; struct hv_enlightened_vmcs *evmcs = vmx->nested.hv_evmcs; + struct kvm_vcpu_hv *hv_vcpu = to_hv_vcpu(&vmx->vcpu); /* HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE */ vmcs12->tpr_threshold = evmcs->tpr_threshold; vmcs12->guest_rip = evmcs->guest_rip; if (unlikely(!(hv_clean_fields & + HV_VMX_ENLIGHTENED_CLEAN_FIELD_ENLIGHTENMENTSCONTROL))) { + hv_vcpu->nested.pa_page_gpa = evmcs->partition_assist_page; + hv_vcpu->nested.vm_id = evmcs->hv_vm_id; + hv_vcpu->nested.vp_id = evmcs->hv_vp_id; + } + + if (unlikely(!(hv_clean_fields & HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_BASIC))) { vmcs12->guest_rsp = evmcs->guest_rsp; vmcs12->guest_rflags = evmcs->guest_rflags; @@ -1977,7 +2001,8 @@ static enum nested_evmptrld_status nested_vmx_handle_enlightened_vmptrld( if (likely(!guest_cpuid_has_evmcs(vcpu))) return EVMPTRLD_DISABLED; - if (!nested_enlightened_vmentry(vcpu, &evmcs_gpa)) { + evmcs_gpa = nested_get_evmptr(vcpu); + if (!evmptr_is_valid(evmcs_gpa)) { nested_release_evmcs(vcpu); return EVMPTRLD_DISABLED; } @@ -3251,6 +3276,12 @@ static bool nested_get_vmcs12_pages(struct kvm_vcpu *vcpu) static bool vmx_get_nested_state_pages(struct kvm_vcpu *vcpu) { + /* + * Note: nested_get_evmcs_page() also updates 'vp_assist_page' copy + * in 'struct kvm_vcpu_hv' in case eVMCS is in use, this is mandatory + * to make nested_evmcs_l2_tlb_flush_enabled() work correctly post + * migration. + */ if (!nested_get_evmcs_page(vcpu)) { pr_debug_ratelimited("%s: enlightened vmptrld failed\n", __func__); @@ -4854,6 +4885,7 @@ void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 vm_exit_reason, static void nested_vmx_triple_fault(struct kvm_vcpu *vcpu) { + kvm_clear_request(KVM_REQ_TRIPLE_FAULT, vcpu); nested_vmx_vmexit(vcpu, EXIT_REASON_TRIPLE_FAULT, 0, 0); } @@ -5205,7 +5237,6 @@ static int handle_vmclear(struct kvm_vcpu *vcpu) struct vcpu_vmx *vmx = to_vmx(vcpu); u32 zero = 0; gpa_t vmptr; - u64 evmcs_gpa; int r; if (!nested_vmx_check_permission(vcpu)) @@ -5231,7 +5262,7 @@ static int handle_vmclear(struct kvm_vcpu *vcpu) * vmx->nested.hv_evmcs but this shouldn't be a problem. */ if (likely(!guest_cpuid_has_evmcs(vcpu) || - !nested_enlightened_vmentry(vcpu, &evmcs_gpa))) { + !evmptr_is_valid(nested_get_evmptr(vcpu)))) { if (vmptr == vmx->nested.current_vmptr) nested_release_vmcs12(vcpu); @@ -6128,6 +6159,11 @@ static bool nested_vmx_l0_wants_exit(struct kvm_vcpu *vcpu, * Handle L2's bus locks in L0 directly. */ return true; + case EXIT_REASON_VMCALL: + /* Hyper-V L2 TLB flush hypercall is handled by L0 */ + return guest_hv_cpuid_has_l2_tlb_flush(vcpu) && + nested_evmcs_l2_tlb_flush_enabled(vcpu) && + kvm_hv_is_tlb_flush_hcall(vcpu); default: break; } @@ -6440,9 +6476,6 @@ out: return kvm_state.size; } -/* - * Forcibly leave nested mode in order to be able to reset the VCPU later on. - */ void vmx_leave_nested(struct kvm_vcpu *vcpu) { if (is_guest_mode(vcpu)) { @@ -6982,4 +7015,5 @@ struct kvm_x86_nested_ops vmx_nested_ops = { .write_log_dirty = nested_vmx_write_pml_buffer, .enable_evmcs = nested_enable_evmcs, .get_evmcs_version = nested_get_evmcs_version, + .hv_inject_synthetic_vmexit_post_tlb_flush = vmx_hv_inject_synthetic_vmexit_post_tlb_flush, }; diff --git a/arch/x86/kvm/vmx/pmu_intel.c b/arch/x86/kvm/vmx/pmu_intel.c index 25b70a85bef5..e5cec07ca8d9 100644 --- a/arch/x86/kvm/vmx/pmu_intel.c +++ b/arch/x86/kvm/vmx/pmu_intel.c @@ -52,7 +52,7 @@ static void reprogram_fixed_counters(struct kvm_pmu *pmu, u64 data) pmc = get_fixed_pmc(pmu, MSR_CORE_PERF_FIXED_CTR0 + i); __set_bit(INTEL_PMC_IDX_FIXED + i, pmu->pmc_in_use); - reprogram_counter(pmc); + kvm_pmu_request_counter_reprogam(pmc); } } @@ -76,7 +76,7 @@ static void reprogram_counters(struct kvm_pmu *pmu, u64 diff) for_each_set_bit(bit, (unsigned long *)&diff, X86_PMC_IDX_MAX) { pmc = intel_pmc_idx_to_pmc(pmu, bit); if (pmc) - reprogram_counter(pmc); + kvm_pmu_request_counter_reprogam(pmc); } } @@ -477,7 +477,7 @@ static int intel_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) reserved_bits ^= HSW_IN_TX_CHECKPOINTED; if (!(data & reserved_bits)) { pmc->eventsel = data; - reprogram_counter(pmc); + kvm_pmu_request_counter_reprogam(pmc); return 0; } } else if (intel_pmu_handle_lbr_msrs_access(vcpu, msr_info, false)) @@ -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; @@ -631,7 +631,6 @@ static void intel_pmu_init(struct kvm_vcpu *vcpu) pmu->fixed_counters[i].current_config = 0; } - vcpu->arch.perf_capabilities = vmx_get_perf_capabilities(); lbr_desc->records.nr = 0; lbr_desc->event = NULL; lbr_desc->msr_passthrough = false; @@ -643,18 +642,18 @@ 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); - pmc->counter = pmc->eventsel = 0; + pmc->counter = pmc->prev_counter = pmc->eventsel = 0; } for (i = 0; i < KVM_PMC_MAX_FIXED; i++) { pmc = &pmu->fixed_counters[i]; pmc_stop_counter(pmc); - pmc->counter = 0; + pmc->counter = pmc->prev_counter = 0; } pmu->fixed_ctr_ctrl = pmu->global_ctrl = pmu->global_status = 0; diff --git a/arch/x86/kvm/vmx/vmcs12.h b/arch/x86/kvm/vmx/vmcs12.h index 746129ddd5ae..01936013428b 100644 --- a/arch/x86/kvm/vmx/vmcs12.h +++ b/arch/x86/kvm/vmx/vmcs12.h @@ -208,9 +208,8 @@ struct __packed vmcs12 { /* * For save/restore compatibility, the vmcs12 field offsets must not change. */ -#define CHECK_OFFSET(field, loc) \ - BUILD_BUG_ON_MSG(offsetof(struct vmcs12, field) != (loc), \ - "Offset of " #field " in struct vmcs12 has changed.") +#define CHECK_OFFSET(field, loc) \ + ASSERT_STRUCT_OFFSET(struct vmcs12, field, loc) static inline void vmx_check_vmcs12_offsets(void) { 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..cea8c07f5229 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -51,7 +51,6 @@ #include "capabilities.h" #include "cpuid.h" -#include "evmcs.h" #include "hyperv.h" #include "kvm_onhyperv.h" #include "irq.h" @@ -66,6 +65,7 @@ #include "vmcs12.h" #include "vmx.h" #include "x86.h" +#include "smm.h" MODULE_AUTHOR("Qumranet"); MODULE_LICENSE("GPL"); @@ -526,7 +526,7 @@ static unsigned long host_idt_base; static bool __read_mostly enlightened_vmcs = true; module_param(enlightened_vmcs, bool, 0444); -static int hv_enable_direct_tlbflush(struct kvm_vcpu *vcpu) +static int hv_enable_l2_tlb_flush(struct kvm_vcpu *vcpu) { struct hv_enlightened_vmcs *evmcs; struct hv_partition_assist_pg **p_hv_pa_pg = @@ -1849,9 +1849,6 @@ static int vmx_get_msr_feature(struct kvm_msr_entry *msr) if (!nested) return 1; return vmx_get_vmx_msr(&vmcs_config.nested, msr->index, &msr->data); - case MSR_IA32_PERF_CAPABILITIES: - msr->data = vmx_get_perf_capabilities(); - return 0; default: return KVM_MSR_RET_INVALID; } @@ -2021,15 +2018,17 @@ 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 ((kvm_caps.supported_perf_cap & PMU_CAP_LBR_FMT) && + (host_initiated || intel_pmu_lbr_is_enabled(vcpu))) + debugctl |= DEBUGCTLMSR_LBR | DEBUGCTLMSR_FREEZE_LBRS_ON_PMI; return debugctl; } @@ -2103,7 +2102,9 @@ 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", @@ -2338,14 +2339,14 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) return 1; if (data & PMU_CAP_LBR_FMT) { if ((data & PMU_CAP_LBR_FMT) != - (vmx_get_perf_capabilities() & PMU_CAP_LBR_FMT)) + (kvm_caps.supported_perf_cap & PMU_CAP_LBR_FMT)) return 1; if (!cpuid_model_is_consistent(vcpu)) return 1; } if (data & PERF_CAP_PEBS_FORMAT) { if ((data & PERF_CAP_PEBS_MASK) != - (vmx_get_perf_capabilities() & PERF_CAP_PEBS_MASK)) + (kvm_caps.supported_perf_cap & PERF_CAP_PEBS_MASK)) return 1; if (!guest_cpuid_has(vcpu, X86_FEATURE_DS)) return 1; @@ -6840,6 +6841,8 @@ static bool vmx_has_emulated_msr(struct kvm *kvm, u32 index) { switch (index) { case MSR_IA32_SMBASE: + if (!IS_ENABLED(CONFIG_KVM_SMM)) + return false; /* * We cannot do SMM unless we can run the guest in big * real mode. @@ -7665,6 +7668,31 @@ static void vmx_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu) vmx_update_exception_bitmap(vcpu); } +static 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) + return 0; + + if (boot_cpu_has(X86_FEATURE_PDCM)) + rdmsrl(MSR_IA32_PERF_CAPABILITIES, host_perf_cap); + + x86_perf_get_lbr(&lbr); + if (lbr.nr) + perf_cap |= host_perf_cap & PMU_CAP_LBR_FMT; + + if (vmx_pebs_supported()) { + perf_cap |= host_perf_cap & PERF_CAP_PEBS_MASK; + if ((perf_cap & PERF_CAP_PEBS_FORMAT) < 4) + perf_cap &= ~PERF_CAP_PEBS_BASELINE; + } + + return perf_cap; +} + static __init void vmx_set_cpu_caps(void) { kvm_set_cpu_caps(); @@ -7687,6 +7715,7 @@ static __init void vmx_set_cpu_caps(void) if (!enable_pmu) kvm_cpu_cap_clear(X86_FEATURE_PDCM); + kvm_caps.supported_perf_cap = vmx_get_perf_capabilities(); if (!enable_sgx) { kvm_cpu_cap_clear(X86_FEATURE_SGX); @@ -7902,6 +7931,7 @@ static void vmx_setup_mce(struct kvm_vcpu *vcpu) ~FEAT_CTL_LMCE_ENABLED; } +#ifdef CONFIG_KVM_SMM static int vmx_smi_allowed(struct kvm_vcpu *vcpu, bool for_injection) { /* we need a nested vmexit to enter SMM, postpone if run is pending */ @@ -7910,7 +7940,7 @@ static int vmx_smi_allowed(struct kvm_vcpu *vcpu, bool for_injection) return !is_smm(vcpu); } -static int vmx_enter_smm(struct kvm_vcpu *vcpu, char *smstate) +static int vmx_enter_smm(struct kvm_vcpu *vcpu, union kvm_smram *smram) { struct vcpu_vmx *vmx = to_vmx(vcpu); @@ -7931,7 +7961,7 @@ static int vmx_enter_smm(struct kvm_vcpu *vcpu, char *smstate) return 0; } -static int vmx_leave_smm(struct kvm_vcpu *vcpu, const char *smstate) +static int vmx_leave_smm(struct kvm_vcpu *vcpu, const union kvm_smram *smram) { struct vcpu_vmx *vmx = to_vmx(vcpu); int ret; @@ -7956,6 +7986,7 @@ static void vmx_enable_smi_window(struct kvm_vcpu *vcpu) { /* RSM will cause a vmexit anyway. */ } +#endif static bool vmx_apic_init_signal_blocked(struct kvm_vcpu *vcpu) { @@ -8123,10 +8154,12 @@ static struct kvm_x86_ops vmx_x86_ops __initdata = { .setup_mce = vmx_setup_mce, +#ifdef CONFIG_KVM_SMM .smi_allowed = vmx_smi_allowed, .enter_smm = vmx_enter_smm, .leave_smm = vmx_leave_smm, .enable_smi_window = vmx_enable_smi_window, +#endif .can_emulate_instruction = vmx_can_emulate_instruction, .apic_init_signal_blocked = vmx_apic_init_signal_blocked, @@ -8263,6 +8296,11 @@ 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 @@ -8481,8 +8519,8 @@ static int __init vmx_init(void) } if (ms_hyperv.nested_features & HV_X64_NESTED_DIRECT_FLUSH) - vmx_x86_ops.enable_direct_tlbflush - = hv_enable_direct_tlbflush; + vmx_x86_ops.enable_l2_tlb_flush + = hv_enable_l2_tlb_flush; } else { enlightened_vmcs = false; diff --git a/arch/x86/kvm/vmx/vmx_ops.h b/arch/x86/kvm/vmx/vmx_ops.h index ec268df83ed6..f6f23c7397dc 100644 --- a/arch/x86/kvm/vmx/vmx_ops.h +++ b/arch/x86/kvm/vmx/vmx_ops.h @@ -6,7 +6,7 @@ #include <asm/vmx.h> -#include "evmcs.h" +#include "hyperv.h" #include "vmcs.h" #include "../x86.h" diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 9cf1ba865562..72ac6bf05c8b 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -30,6 +30,7 @@ #include "hyperv.h" #include "lapic.h" #include "xen.h" +#include "smm.h" #include <linux/clocksource.h> #include <linux/interrupt.h> @@ -119,8 +120,6 @@ static u64 __read_mostly cr4_reserved_bits = CR4_RESERVED_BITS; static void update_cr8_intercept(struct kvm_vcpu *vcpu); static void process_nmi(struct kvm_vcpu *vcpu); -static void process_smi(struct kvm_vcpu *vcpu); -static void enter_smm(struct kvm_vcpu *vcpu); static void __kvm_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags); static void store_regs(struct kvm_vcpu *vcpu); static int sync_regs(struct kvm_vcpu *vcpu); @@ -628,6 +627,12 @@ static void kvm_queue_exception_vmexit(struct kvm_vcpu *vcpu, unsigned int vecto ex->payload = payload; } +/* Forcibly leave the nested mode in cases like a vCPU reset */ +static void kvm_leave_nested(struct kvm_vcpu *vcpu) +{ + kvm_x86_ops.nested_ops->leave_nested(vcpu); +} + static void kvm_multiple_exception(struct kvm_vcpu *vcpu, unsigned nr, bool has_error, u32 error_code, bool has_payload, unsigned long payload, bool reinject) @@ -1438,32 +1443,27 @@ 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, }; @@ -1653,6 +1653,9 @@ static int kvm_get_msr_feature(struct kvm_msr_entry *msr) case MSR_IA32_ARCH_CAPABILITIES: msr->data = kvm_get_arch_capabilities(); break; + case MSR_IA32_PERF_CAPABILITIES: + msr->data = kvm_caps.supported_perf_cap; + break; case MSR_IA32_UCODE_REV: rdmsrl_safe(msr->index, &msr->data); break; @@ -2315,11 +2318,11 @@ 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 +3391,7 @@ 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; } @@ -3396,6 +3399,9 @@ static void kvm_vcpu_flush_tlb_all(struct kvm_vcpu *vcpu) { ++vcpu->stat.tlb_flush; static_call(kvm_x86_flush_tlb_all)(vcpu); + + /* Flushing all ASIDs flushes the current ASID... */ + kvm_clear_request(KVM_REQ_TLB_FLUSH_CURRENT, vcpu); } static void kvm_vcpu_flush_tlb_guest(struct kvm_vcpu *vcpu) @@ -3414,6 +3420,12 @@ static void kvm_vcpu_flush_tlb_guest(struct kvm_vcpu *vcpu) } static_call(kvm_x86_flush_tlb_guest)(vcpu); + + /* + * Flushing all "guest" TLB is always a superset of Hyper-V's fine + * grained flushing. + */ + kvm_hv_vcpu_purge_flush_tlb(vcpu); } @@ -3565,20 +3577,15 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) return 1; vcpu->arch.arch_capabilities = data; break; - case MSR_IA32_PERF_CAPABILITIES: { - struct kvm_msr_entry msr_ent = {.index = msr, .data = 0}; - + case MSR_IA32_PERF_CAPABILITIES: if (!msr_info->host_initiated) return 1; - if (kvm_get_msr_feature(&msr_ent)) - return 1; - if (data & ~msr_ent.data) + if (data & ~kvm_caps.supported_perf_cap) return 1; vcpu->arch.perf_capabilities = data; kvm_pmu_refresh(vcpu); return 0; - } case MSR_EFER: return set_efer(vcpu, msr_info); case MSR_K7_HWCR: @@ -3650,7 +3657,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) break; } case MSR_IA32_SMBASE: - if (!msr_info->host_initiated) + if (!IS_ENABLED(CONFIG_KVM_SMM) || !msr_info->host_initiated) return 1; vcpu->arch.smbase = data; break; @@ -4066,7 +4073,7 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) msr_info->data = vcpu->arch.ia32_misc_enable_msr; break; case MSR_IA32_SMBASE: - if (!msr_info->host_initiated) + if (!IS_ENABLED(CONFIG_KVM_SMM) || !msr_info->host_initiated) return 1; msr_info->data = vcpu->arch.smbase; break; @@ -4440,6 +4447,9 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) r |= KVM_X86_DISABLE_EXITS_MWAIT; break; case KVM_CAP_X86_SMM: + if (!IS_ENABLED(CONFIG_KVM_SMM)) + break; + /* SMBASE is usually relocated above 1M on modern chipsets, * and SMM handlers might indeed rely on 4G segment limits, * so do not report SMM to be available if real mode is @@ -4480,7 +4490,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) kvm_x86_ops.nested_ops->get_state(NULL, NULL, 0) : 0; break; case KVM_CAP_HYPERV_DIRECT_TLBFLUSH: - r = kvm_x86_ops.enable_direct_tlbflush != NULL; + r = kvm_x86_ops.enable_l2_tlb_flush != NULL; break; case KVM_CAP_HYPERV_ENLIGHTENED_VMCS: r = kvm_x86_ops.nested_ops->enable_evmcs != NULL; @@ -4896,13 +4906,6 @@ static int kvm_vcpu_ioctl_nmi(struct kvm_vcpu *vcpu) return 0; } -static int kvm_vcpu_ioctl_smi(struct kvm_vcpu *vcpu) -{ - kvm_make_request(KVM_REQ_SMI, vcpu); - - return 0; -} - static int vcpu_ioctl_tpr_access_reporting(struct kvm_vcpu *vcpu, struct kvm_tpr_access_ctl *tac) { @@ -5038,8 +5041,10 @@ static void kvm_vcpu_ioctl_x86_get_vcpu_events(struct kvm_vcpu *vcpu, process_nmi(vcpu); +#ifdef CONFIG_KVM_SMM if (kvm_check_request(KVM_REQ_SMI, vcpu)) process_smi(vcpu); +#endif /* * KVM's ABI only allows for one exception to be migrated. Luckily, @@ -5067,16 +5072,15 @@ static void kvm_vcpu_ioctl_x86_get_vcpu_events(struct kvm_vcpu *vcpu, ex->pending && ex->has_payload) kvm_deliver_exception_payload(vcpu, ex); + memset(events, 0, sizeof(*events)); + /* * The API doesn't provide the instruction length for software * exceptions, so don't report them. As long as the guest RIP * isn't advanced, we should expect to encounter the exception * again. */ - if (kvm_exception_is_soft(ex->vector)) { - events->exception.injected = 0; - events->exception.pending = 0; - } else { + if (!kvm_exception_is_soft(ex->vector)) { events->exception.injected = ex->injected; events->exception.pending = ex->pending; /* @@ -5096,20 +5100,20 @@ static void kvm_vcpu_ioctl_x86_get_vcpu_events(struct kvm_vcpu *vcpu, events->interrupt.injected = vcpu->arch.interrupt.injected && !vcpu->arch.interrupt.soft; events->interrupt.nr = vcpu->arch.interrupt.nr; - events->interrupt.soft = 0; events->interrupt.shadow = static_call(kvm_x86_get_interrupt_shadow)(vcpu); events->nmi.injected = vcpu->arch.nmi_injected; events->nmi.pending = vcpu->arch.nmi_pending != 0; events->nmi.masked = static_call(kvm_x86_get_nmi_mask)(vcpu); - events->nmi.pad = 0; - events->sipi_vector = 0; /* never valid when reporting to user space */ + /* events->sipi_vector is never valid when reporting to user space */ +#ifdef CONFIG_KVM_SMM events->smi.smm = is_smm(vcpu); events->smi.pending = vcpu->arch.smi_pending; events->smi.smm_inside_nmi = !!(vcpu->arch.hflags & HF_SMM_INSIDE_NMI_MASK); +#endif events->smi.latched_init = kvm_lapic_latched_init(vcpu); events->flags = (KVM_VCPUEVENT_VALID_NMI_PENDING @@ -5121,12 +5125,8 @@ static void kvm_vcpu_ioctl_x86_get_vcpu_events(struct kvm_vcpu *vcpu, events->triple_fault.pending = kvm_test_request(KVM_REQ_TRIPLE_FAULT, vcpu); events->flags |= KVM_VCPUEVENT_VALID_TRIPLE_FAULT; } - - memset(&events->reserved, 0, sizeof(events->reserved)); } -static void kvm_smm_changed(struct kvm_vcpu *vcpu, bool entering_smm); - static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu, struct kvm_vcpu_events *events) { @@ -5199,8 +5199,9 @@ static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu, vcpu->arch.apic->sipi_vector = events->sipi_vector; if (events->flags & KVM_VCPUEVENT_VALID_SMM) { +#ifdef CONFIG_KVM_SMM if (!!(vcpu->arch.hflags & HF_SMM_MASK) != events->smi.smm) { - kvm_x86_ops.nested_ops->leave_nested(vcpu); + kvm_leave_nested(vcpu); kvm_smm_changed(vcpu, events->smi.smm); } @@ -5213,6 +5214,12 @@ static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu, vcpu->arch.hflags &= ~HF_SMM_INSIDE_NMI_MASK; } +#else + if (events->smi.smm || events->smi.pending || + events->smi.smm_inside_nmi) + return -EINVAL; +#endif + if (lapic_in_kernel(vcpu)) { if (events->smi.latched_init) set_bit(KVM_APIC_INIT, &vcpu->arch.apic->pending_events); @@ -5496,10 +5503,10 @@ static int kvm_vcpu_ioctl_enable_cap(struct kvm_vcpu *vcpu, } return r; case KVM_CAP_HYPERV_DIRECT_TLBFLUSH: - if (!kvm_x86_ops.enable_direct_tlbflush) + if (!kvm_x86_ops.enable_l2_tlb_flush) return -ENOTTY; - return static_call(kvm_x86_enable_direct_tlbflush)(vcpu); + return static_call(kvm_x86_enable_l2_tlb_flush)(vcpu); case KVM_CAP_HYPERV_ENFORCE_CPUID: return kvm_hv_set_enforce_cpuid(vcpu, cap->args[0]); @@ -5579,7 +5586,7 @@ long kvm_arch_vcpu_ioctl(struct file *filp, break; } case KVM_SMI: { - r = kvm_vcpu_ioctl_smi(vcpu); + r = kvm_inject_smi(vcpu); break; } case KVM_SET_CPUID: { @@ -6238,9 +6245,7 @@ split_irqchip_unlock: break; case KVM_CAP_X86_USER_SPACE_MSR: r = -EINVAL; - if (cap->args[0] & ~(KVM_MSR_EXIT_REASON_INVAL | - KVM_MSR_EXIT_REASON_UNKNOWN | - KVM_MSR_EXIT_REASON_FILTER)) + if (cap->args[0] & ~KVM_MSR_EXIT_REASON_VALID_MASK) break; kvm->arch.user_space_msr_mask = cap->args[0]; r = 0; @@ -6417,7 +6422,7 @@ static int kvm_add_msr_filter(struct kvm_x86_msr_filter *msr_filter, if (!user_range->nmsrs) return 0; - if (user_range->flags & ~(KVM_MSR_FILTER_READ | KVM_MSR_FILTER_WRITE)) + if (user_range->flags & ~KVM_MSR_FILTER_RANGE_VALID_MASK) return -EINVAL; if (!user_range->flags) @@ -6451,7 +6456,7 @@ static int kvm_vm_ioctl_set_msr_filter(struct kvm *kvm, int r = 0; u32 i; - if (filter->flags & ~KVM_MSR_FILTER_DEFAULT_DENY) + if (filter->flags & ~KVM_MSR_FILTER_VALID_MASK) return -EINVAL; for (i = 0; i < ARRAY_SIZE(filter->ranges); i++) @@ -7041,14 +7046,14 @@ 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: @@ -7124,8 +7129,8 @@ static int vcpu_mmio_read(struct kvm_vcpu *vcpu, gpa_t addr, int len, void *v) return handled; } -static void kvm_set_segment(struct kvm_vcpu *vcpu, - struct kvm_segment *var, int seg) +void kvm_set_segment(struct kvm_vcpu *vcpu, + struct kvm_segment *var, int seg) { static_call(kvm_x86_set_segment)(vcpu, var, seg); } @@ -7161,16 +7166,6 @@ gpa_t kvm_mmu_gva_to_gpa_read(struct kvm_vcpu *vcpu, gva_t gva, } EXPORT_SYMBOL_GPL(kvm_mmu_gva_to_gpa_read); - gpa_t kvm_mmu_gva_to_gpa_fetch(struct kvm_vcpu *vcpu, gva_t gva, - struct x86_exception *exception) -{ - struct kvm_mmu *mmu = vcpu->arch.walk_mmu; - - u64 access = (static_call(kvm_x86_get_cpl)(vcpu) == 3) ? PFERR_USER_MASK : 0; - access |= PFERR_FETCH_MASK; - return mmu->gva_to_gpa(vcpu, mmu, gva, access, exception); -} - gpa_t kvm_mmu_gva_to_gpa_write(struct kvm_vcpu *vcpu, gva_t gva, struct x86_exception *exception) { @@ -7283,15 +7278,6 @@ static int emulator_read_std(struct x86_emulate_ctxt *ctxt, return kvm_read_guest_virt_helper(addr, val, bytes, vcpu, access, exception); } -static int kvm_read_guest_phys_system(struct x86_emulate_ctxt *ctxt, - unsigned long addr, void *val, unsigned int bytes) -{ - struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt); - int r = kvm_vcpu_read_guest(vcpu, addr, val, bytes); - - return r < 0 ? X86EMUL_IO_NEEDED : X86EMUL_CONTINUE; -} - static int kvm_write_guest_virt_helper(gva_t addr, void *val, unsigned int bytes, struct kvm_vcpu *vcpu, u64 access, struct x86_exception *exception) @@ -8083,26 +8069,6 @@ static int emulator_get_msr(struct x86_emulate_ctxt *ctxt, return kvm_get_msr(emul_to_vcpu(ctxt), msr_index, pdata); } -static int emulator_set_msr(struct x86_emulate_ctxt *ctxt, - u32 msr_index, u64 data) -{ - return kvm_set_msr(emul_to_vcpu(ctxt), msr_index, data); -} - -static u64 emulator_get_smbase(struct x86_emulate_ctxt *ctxt) -{ - struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt); - - return vcpu->arch.smbase; -} - -static void emulator_set_smbase(struct x86_emulate_ctxt *ctxt, u64 smbase) -{ - struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt); - - vcpu->arch.smbase = smbase; -} - static int emulator_check_pmc(struct x86_emulate_ctxt *ctxt, u32 pmc) { @@ -8177,18 +8143,13 @@ static unsigned emulator_get_hflags(struct x86_emulate_ctxt *ctxt) return emul_to_vcpu(ctxt)->arch.hflags; } -static void emulator_exiting_smm(struct x86_emulate_ctxt *ctxt) -{ - struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt); - - kvm_smm_changed(vcpu, false); -} - -static int emulator_leave_smm(struct x86_emulate_ctxt *ctxt, - const char *smstate) +#ifndef CONFIG_KVM_SMM +static int emulator_leave_smm(struct x86_emulate_ctxt *ctxt) { - return static_call(kvm_x86_leave_smm)(emul_to_vcpu(ctxt), smstate); + WARN_ON_ONCE(1); + return X86EMUL_UNHANDLEABLE; } +#endif static void emulator_triple_fault(struct x86_emulate_ctxt *ctxt) { @@ -8214,7 +8175,6 @@ static const struct x86_emulate_ops emulate_ops = { .write_gpr = emulator_write_gpr, .read_std = emulator_read_std, .write_std = emulator_write_std, - .read_phys = kvm_read_guest_phys_system, .fetch = kvm_fetch_guest_virt, .read_emulated = emulator_read_emulated, .write_emulated = emulator_write_emulated, @@ -8234,11 +8194,8 @@ static const struct x86_emulate_ops emulate_ops = { .cpl = emulator_get_cpl, .get_dr = emulator_get_dr, .set_dr = emulator_set_dr, - .get_smbase = emulator_get_smbase, - .set_smbase = emulator_set_smbase, .set_msr_with_filter = emulator_set_msr_with_filter, .get_msr_with_filter = emulator_get_msr_with_filter, - .set_msr = emulator_set_msr, .get_msr = emulator_get_msr, .check_pmc = emulator_check_pmc, .read_pmc = emulator_read_pmc, @@ -8253,7 +8210,6 @@ static const struct x86_emulate_ops emulate_ops = { .guest_has_rdpid = emulator_guest_has_rdpid, .set_nmi_mask = emulator_set_nmi_mask, .get_hflags = emulator_get_hflags, - .exiting_smm = emulator_exiting_smm, .leave_smm = emulator_leave_smm, .triple_fault = emulator_triple_fault, .set_xcr = emulator_set_xcr, @@ -8326,8 +8282,6 @@ static void init_emulate_ctxt(struct kvm_vcpu *vcpu) cs_db ? X86EMUL_MODE_PROT32 : X86EMUL_MODE_PROT16; BUILD_BUG_ON(HF_GUEST_MASK != X86EMUL_GUEST_MASK); - BUILD_BUG_ON(HF_SMM_MASK != X86EMUL_SMM_MASK); - BUILD_BUG_ON(HF_SMM_INSIDE_NMI_MASK != X86EMUL_SMM_INSIDE_NMI_MASK); ctxt->interruptibility = 0; ctxt->have_exception = false; @@ -8586,29 +8540,6 @@ static bool retry_instruction(struct x86_emulate_ctxt *ctxt, static int complete_emulated_mmio(struct kvm_vcpu *vcpu); static int complete_emulated_pio(struct kvm_vcpu *vcpu); -static void kvm_smm_changed(struct kvm_vcpu *vcpu, bool entering_smm) -{ - trace_kvm_smm_transition(vcpu->vcpu_id, vcpu->arch.smbase, entering_smm); - - if (entering_smm) { - vcpu->arch.hflags |= HF_SMM_MASK; - } else { - vcpu->arch.hflags &= ~(HF_SMM_MASK | HF_SMM_INSIDE_NMI_MASK); - - /* Process a latched INIT or SMI, if any. */ - kvm_make_request(KVM_REQ_EVENT, vcpu); - - /* - * Even if KVM_SET_SREGS2 loaded PDPTRs out of band, - * on SMM exit we still need to reload them from - * guest memory - */ - vcpu->arch.pdptrs_from_userspace = false; - } - - kvm_mmu_reset_context(vcpu); -} - static int kvm_vcpu_check_hw_bp(unsigned long addr, u32 type, u32 dr7, unsigned long *db) { @@ -9810,7 +9741,7 @@ static void update_cr8_intercept(struct kvm_vcpu *vcpu) int kvm_check_nested_events(struct kvm_vcpu *vcpu) { - if (kvm_check_request(KVM_REQ_TRIPLE_FAULT, vcpu)) { + if (kvm_test_request(KVM_REQ_TRIPLE_FAULT, vcpu)) { kvm_x86_ops.nested_ops->triple_fault(vcpu); return 1; } @@ -9998,6 +9929,7 @@ static int kvm_check_and_inject_events(struct kvm_vcpu *vcpu, * in order to make progress and get back here for another iteration. * The kvm_x86_ops hooks communicate this by returning -EBUSY. */ +#ifdef CONFIG_KVM_SMM if (vcpu->arch.smi_pending) { r = can_inject ? static_call(kvm_x86_smi_allowed)(vcpu, true) : -EBUSY; if (r < 0) @@ -10010,6 +9942,7 @@ static int kvm_check_and_inject_events(struct kvm_vcpu *vcpu, } else static_call(kvm_x86_enable_smi_window)(vcpu); } +#endif if (vcpu->arch.nmi_pending) { r = can_inject ? static_call(kvm_x86_nmi_allowed)(vcpu, true) : -EBUSY; @@ -10044,7 +9977,20 @@ 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: @@ -10072,246 +10018,6 @@ static void process_nmi(struct kvm_vcpu *vcpu) kvm_make_request(KVM_REQ_EVENT, vcpu); } -static u32 enter_smm_get_segment_flags(struct kvm_segment *seg) -{ - u32 flags = 0; - flags |= seg->g << 23; - flags |= seg->db << 22; - flags |= seg->l << 21; - flags |= seg->avl << 20; - flags |= seg->present << 15; - flags |= seg->dpl << 13; - flags |= seg->s << 12; - flags |= seg->type << 8; - return flags; -} - -static void enter_smm_save_seg_32(struct kvm_vcpu *vcpu, char *buf, int n) -{ - struct kvm_segment seg; - int offset; - - kvm_get_segment(vcpu, &seg, n); - put_smstate(u32, buf, 0x7fa8 + n * 4, seg.selector); - - if (n < 3) - offset = 0x7f84 + n * 12; - else - offset = 0x7f2c + (n - 3) * 12; - - put_smstate(u32, buf, offset + 8, seg.base); - put_smstate(u32, buf, offset + 4, seg.limit); - put_smstate(u32, buf, offset, enter_smm_get_segment_flags(&seg)); -} - -#ifdef CONFIG_X86_64 -static void enter_smm_save_seg_64(struct kvm_vcpu *vcpu, char *buf, int n) -{ - struct kvm_segment seg; - int offset; - u16 flags; - - kvm_get_segment(vcpu, &seg, n); - offset = 0x7e00 + n * 16; - - flags = enter_smm_get_segment_flags(&seg) >> 8; - put_smstate(u16, buf, offset, seg.selector); - put_smstate(u16, buf, offset + 2, flags); - put_smstate(u32, buf, offset + 4, seg.limit); - put_smstate(u64, buf, offset + 8, seg.base); -} -#endif - -static void enter_smm_save_state_32(struct kvm_vcpu *vcpu, char *buf) -{ - struct desc_ptr dt; - struct kvm_segment seg; - unsigned long val; - int i; - - put_smstate(u32, buf, 0x7ffc, kvm_read_cr0(vcpu)); - put_smstate(u32, buf, 0x7ff8, kvm_read_cr3(vcpu)); - put_smstate(u32, buf, 0x7ff4, kvm_get_rflags(vcpu)); - put_smstate(u32, buf, 0x7ff0, kvm_rip_read(vcpu)); - - for (i = 0; i < 8; i++) - put_smstate(u32, buf, 0x7fd0 + i * 4, kvm_register_read_raw(vcpu, i)); - - kvm_get_dr(vcpu, 6, &val); - put_smstate(u32, buf, 0x7fcc, (u32)val); - kvm_get_dr(vcpu, 7, &val); - put_smstate(u32, buf, 0x7fc8, (u32)val); - - kvm_get_segment(vcpu, &seg, VCPU_SREG_TR); - put_smstate(u32, buf, 0x7fc4, seg.selector); - put_smstate(u32, buf, 0x7f64, seg.base); - put_smstate(u32, buf, 0x7f60, seg.limit); - put_smstate(u32, buf, 0x7f5c, enter_smm_get_segment_flags(&seg)); - - kvm_get_segment(vcpu, &seg, VCPU_SREG_LDTR); - put_smstate(u32, buf, 0x7fc0, seg.selector); - put_smstate(u32, buf, 0x7f80, seg.base); - put_smstate(u32, buf, 0x7f7c, seg.limit); - put_smstate(u32, buf, 0x7f78, enter_smm_get_segment_flags(&seg)); - - static_call(kvm_x86_get_gdt)(vcpu, &dt); - put_smstate(u32, buf, 0x7f74, dt.address); - put_smstate(u32, buf, 0x7f70, dt.size); - - static_call(kvm_x86_get_idt)(vcpu, &dt); - put_smstate(u32, buf, 0x7f58, dt.address); - put_smstate(u32, buf, 0x7f54, dt.size); - - for (i = 0; i < 6; i++) - enter_smm_save_seg_32(vcpu, buf, i); - - put_smstate(u32, buf, 0x7f14, kvm_read_cr4(vcpu)); - - /* revision id */ - put_smstate(u32, buf, 0x7efc, 0x00020000); - put_smstate(u32, buf, 0x7ef8, vcpu->arch.smbase); -} - -#ifdef CONFIG_X86_64 -static void enter_smm_save_state_64(struct kvm_vcpu *vcpu, char *buf) -{ - struct desc_ptr dt; - struct kvm_segment seg; - unsigned long val; - int i; - - for (i = 0; i < 16; i++) - put_smstate(u64, buf, 0x7ff8 - i * 8, kvm_register_read_raw(vcpu, i)); - - put_smstate(u64, buf, 0x7f78, kvm_rip_read(vcpu)); - put_smstate(u32, buf, 0x7f70, kvm_get_rflags(vcpu)); - - kvm_get_dr(vcpu, 6, &val); - put_smstate(u64, buf, 0x7f68, val); - kvm_get_dr(vcpu, 7, &val); - put_smstate(u64, buf, 0x7f60, val); - - put_smstate(u64, buf, 0x7f58, kvm_read_cr0(vcpu)); - put_smstate(u64, buf, 0x7f50, kvm_read_cr3(vcpu)); - put_smstate(u64, buf, 0x7f48, kvm_read_cr4(vcpu)); - - put_smstate(u32, buf, 0x7f00, vcpu->arch.smbase); - - /* revision id */ - put_smstate(u32, buf, 0x7efc, 0x00020064); - - put_smstate(u64, buf, 0x7ed0, vcpu->arch.efer); - - kvm_get_segment(vcpu, &seg, VCPU_SREG_TR); - put_smstate(u16, buf, 0x7e90, seg.selector); - put_smstate(u16, buf, 0x7e92, enter_smm_get_segment_flags(&seg) >> 8); - put_smstate(u32, buf, 0x7e94, seg.limit); - put_smstate(u64, buf, 0x7e98, seg.base); - - static_call(kvm_x86_get_idt)(vcpu, &dt); - put_smstate(u32, buf, 0x7e84, dt.size); - put_smstate(u64, buf, 0x7e88, dt.address); - - kvm_get_segment(vcpu, &seg, VCPU_SREG_LDTR); - put_smstate(u16, buf, 0x7e70, seg.selector); - put_smstate(u16, buf, 0x7e72, enter_smm_get_segment_flags(&seg) >> 8); - put_smstate(u32, buf, 0x7e74, seg.limit); - put_smstate(u64, buf, 0x7e78, seg.base); - - static_call(kvm_x86_get_gdt)(vcpu, &dt); - put_smstate(u32, buf, 0x7e64, dt.size); - put_smstate(u64, buf, 0x7e68, dt.address); - - for (i = 0; i < 6; i++) - enter_smm_save_seg_64(vcpu, buf, i); -} -#endif - -static void enter_smm(struct kvm_vcpu *vcpu) -{ - struct kvm_segment cs, ds; - struct desc_ptr dt; - unsigned long cr0; - char buf[512]; - - memset(buf, 0, 512); -#ifdef CONFIG_X86_64 - if (guest_cpuid_has(vcpu, X86_FEATURE_LM)) - enter_smm_save_state_64(vcpu, buf); - else -#endif - enter_smm_save_state_32(vcpu, buf); - - /* - * Give enter_smm() a chance to make ISA-specific changes to the vCPU - * state (e.g. leave guest mode) after we've saved the state into the - * SMM state-save area. - */ - static_call(kvm_x86_enter_smm)(vcpu, buf); - - kvm_smm_changed(vcpu, true); - kvm_vcpu_write_guest(vcpu, vcpu->arch.smbase + 0xfe00, buf, sizeof(buf)); - - if (static_call(kvm_x86_get_nmi_mask)(vcpu)) - vcpu->arch.hflags |= HF_SMM_INSIDE_NMI_MASK; - else - static_call(kvm_x86_set_nmi_mask)(vcpu, true); - - kvm_set_rflags(vcpu, X86_EFLAGS_FIXED); - kvm_rip_write(vcpu, 0x8000); - - cr0 = vcpu->arch.cr0 & ~(X86_CR0_PE | X86_CR0_EM | X86_CR0_TS | X86_CR0_PG); - static_call(kvm_x86_set_cr0)(vcpu, cr0); - vcpu->arch.cr0 = cr0; - - static_call(kvm_x86_set_cr4)(vcpu, 0); - - /* Undocumented: IDT limit is set to zero on entry to SMM. */ - dt.address = dt.size = 0; - static_call(kvm_x86_set_idt)(vcpu, &dt); - - kvm_set_dr(vcpu, 7, DR7_FIXED_1); - - cs.selector = (vcpu->arch.smbase >> 4) & 0xffff; - cs.base = vcpu->arch.smbase; - - ds.selector = 0; - ds.base = 0; - - cs.limit = ds.limit = 0xffffffff; - cs.type = ds.type = 0x3; - cs.dpl = ds.dpl = 0; - cs.db = ds.db = 0; - cs.s = ds.s = 1; - cs.l = ds.l = 0; - cs.g = ds.g = 1; - cs.avl = ds.avl = 0; - cs.present = ds.present = 1; - cs.unusable = ds.unusable = 0; - cs.padding = ds.padding = 0; - - kvm_set_segment(vcpu, &cs, VCPU_SREG_CS); - kvm_set_segment(vcpu, &ds, VCPU_SREG_DS); - kvm_set_segment(vcpu, &ds, VCPU_SREG_ES); - kvm_set_segment(vcpu, &ds, VCPU_SREG_FS); - kvm_set_segment(vcpu, &ds, VCPU_SREG_GS); - kvm_set_segment(vcpu, &ds, VCPU_SREG_SS); - -#ifdef CONFIG_X86_64 - if (guest_cpuid_has(vcpu, X86_FEATURE_LM)) - static_call(kvm_x86_set_efer)(vcpu, 0); -#endif - - kvm_update_cpuid_runtime(vcpu); - kvm_mmu_reset_context(vcpu); -} - -static void process_smi(struct kvm_vcpu *vcpu) -{ - vcpu->arch.smi_pending = true; - kvm_make_request(KVM_REQ_EVENT, vcpu); -} - void kvm_make_scan_ioapic_request_mask(struct kvm *kvm, unsigned long *vcpu_bitmap) { @@ -10391,7 +10097,10 @@ 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; @@ -10536,28 +10245,42 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) kvm_mmu_sync_roots(vcpu); if (kvm_check_request(KVM_REQ_LOAD_MMU_PGD, vcpu)) kvm_mmu_load_pgd(vcpu); - if (kvm_check_request(KVM_REQ_TLB_FLUSH, vcpu)) { + + /* + * Note, the order matters here, as flushing "all" TLB entries + * also flushes the "current" TLB entries, i.e. servicing the + * flush "all" will clear any request to flush "current". + */ + if (kvm_check_request(KVM_REQ_TLB_FLUSH, vcpu)) kvm_vcpu_flush_tlb_all(vcpu); - /* Flushing all ASIDs flushes the current ASID... */ - kvm_clear_request(KVM_REQ_TLB_FLUSH_CURRENT, vcpu); - } kvm_service_local_tlb_flush_requests(vcpu); + /* + * Fall back to a "full" guest flush if Hyper-V's precise + * flushing fails. Note, Hyper-V's flushing is per-vCPU, but + * the flushes are considered "remote" and not "local" because + * the requests can be initiated from other vCPUs. + */ + if (kvm_check_request(KVM_REQ_HV_TLB_FLUSH, vcpu) && + kvm_hv_vcpu_flush_tlb(vcpu)) + kvm_vcpu_flush_tlb_guest(vcpu); + if (kvm_check_request(KVM_REQ_REPORT_TPR_ACCESS, vcpu)) { vcpu->run->exit_reason = KVM_EXIT_TPR_ACCESS; r = 0; goto out; } - if (kvm_check_request(KVM_REQ_TRIPLE_FAULT, vcpu)) { - if (is_guest_mode(vcpu)) { + if (kvm_test_request(KVM_REQ_TRIPLE_FAULT, vcpu)) { + if (is_guest_mode(vcpu)) kvm_x86_ops.nested_ops->triple_fault(vcpu); - } else { + + if (kvm_check_request(KVM_REQ_TRIPLE_FAULT, vcpu)) { vcpu->run->exit_reason = KVM_EXIT_SHUTDOWN; vcpu->mmio_needed = 0; r = 0; - goto out; } + goto out; } if (kvm_check_request(KVM_REQ_APF_HALT, vcpu)) { /* Page is swapped out. Do synthetic halt */ @@ -10567,8 +10290,10 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) } if (kvm_check_request(KVM_REQ_STEAL_UPDATE, vcpu)) record_steal_time(vcpu); +#ifdef CONFIG_KVM_SMM if (kvm_check_request(KVM_REQ_SMI, vcpu)) process_smi(vcpu); +#endif if (kvm_check_request(KVM_REQ_NMI, vcpu)) process_nmi(vcpu); if (kvm_check_request(KVM_REQ_PMU, vcpu)) @@ -11816,6 +11541,8 @@ 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 @@ -11880,6 +11607,8 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu) vcpu->arch.pat = MSR_IA32_CR_PAT_DEFAULT; kvm_async_pf_hash_reset(vcpu); + + vcpu->arch.perf_capabilities = kvm_caps.supported_perf_cap; kvm_pmu_init(vcpu); vcpu->arch.pending_external_vector = -1; @@ -11984,8 +11713,18 @@ void kvm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) WARN_ON_ONCE(!init_event && (old_cr0 || kvm_read_cr3(vcpu) || kvm_read_cr4(vcpu))); + /* + * SVM doesn't unconditionally VM-Exit on INIT and SHUTDOWN, thus it's + * possible to INIT the vCPU while L2 is active. Force the vCPU back + * into L1 as EFER.SVME is cleared on INIT (along with all other EFER + * bits), i.e. virtualization is disabled. + */ + if (is_guest_mode(vcpu)) + kvm_leave_nested(vcpu); + kvm_lapic_reset(vcpu, init_event); + WARN_ON_ONCE(is_guest_mode(vcpu) || is_smm(vcpu)); vcpu->arch.hflags = 0; vcpu->arch.smi_pending = 0; @@ -12879,10 +12618,12 @@ static inline bool kvm_vcpu_has_events(struct kvm_vcpu *vcpu) static_call(kvm_x86_nmi_allowed)(vcpu, false))) return true; +#ifdef CONFIG_KVM_SMM if (kvm_test_request(KVM_REQ_SMI, vcpu) || (vcpu->arch.smi_pending && static_call(kvm_x86_smi_allowed)(vcpu, false))) return true; +#endif if (kvm_arch_interrupt_allowed(vcpu) && (kvm_cpu_has_interrupt(vcpu) || @@ -12923,7 +12664,9 @@ bool kvm_arch_dy_runnable(struct kvm_vcpu *vcpu) return true; if (kvm_test_request(KVM_REQ_NMI, vcpu) || +#ifdef CONFIG_KVM_SMM kvm_test_request(KVM_REQ_SMI, vcpu) || +#endif kvm_test_request(KVM_REQ_EVENT, vcpu)) return true; diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h index 829d3134c1eb..9de72586f406 100644 --- a/arch/x86/kvm/x86.h +++ b/arch/x86/kvm/x86.h @@ -27,6 +27,7 @@ struct kvm_caps { u64 supported_mce_cap; u64 supported_xcr0; u64 supported_xss; + u64 supported_perf_cap; }; void kvm_spurious_fault(void); diff --git a/arch/x86/kvm/xen.c b/arch/x86/kvm/xen.c index 93c628d3e3a9..4b8e9628fbf5 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: @@ -955,6 +954,14 @@ static int kvm_xen_hypercall_complete_userspace(struct kvm_vcpu *vcpu) return kvm_xen_hypercall_set_result(vcpu, run->xen.u.hcall.result); } +static inline int max_evtchn_port(struct kvm *kvm) +{ + if (IS_ENABLED(CONFIG_64BIT) && kvm->arch.xen.long_mode) + return EVTCHN_2L_NR_CHANNELS; + else + return COMPAT_EVTCHN_2L_NR_CHANNELS; +} + static bool wait_pending_event(struct kvm_vcpu *vcpu, int nr_ports, evtchn_port_t *ports) { @@ -1043,6 +1050,10 @@ static bool kvm_xen_schedop_poll(struct kvm_vcpu *vcpu, bool longmode, *r = -EFAULT; goto out; } + if (ports[i] >= max_evtchn_port(vcpu->kvm)) { + *r = -EINVAL; + goto out; + } } if (sched_poll.nr_ports == 1) @@ -1216,6 +1227,7 @@ int kvm_xen_hypercall(struct kvm_vcpu *vcpu) bool longmode; u64 input, params[6], r = -ENOSYS; bool handled = false; + u8 cpl; input = (u64)kvm_register_read(vcpu, VCPU_REGS_RAX); @@ -1243,9 +1255,17 @@ int kvm_xen_hypercall(struct kvm_vcpu *vcpu) params[5] = (u64)kvm_r9_read(vcpu); } #endif - trace_kvm_xen_hypercall(input, params[0], params[1], params[2], + cpl = static_call(kvm_x86_get_cpl)(vcpu); + trace_kvm_xen_hypercall(cpl, input, params[0], params[1], params[2], params[3], params[4], params[5]); + /* + * Only allow hypercall acceleration for CPL0. The rare hypercalls that + * are permitted in guest userspace can be handled by the VMM. + */ + if (unlikely(cpl > 0)) + goto handle_in_userspace; + switch (input) { case __HYPERVISOR_xen_version: if (params[0] == XENVER_version && vcpu->kvm->arch.xen.xen_version) { @@ -1280,10 +1300,11 @@ int kvm_xen_hypercall(struct kvm_vcpu *vcpu) if (handled) return kvm_xen_hypercall_set_result(vcpu, r); +handle_in_userspace: vcpu->run->exit_reason = KVM_EXIT_XEN; vcpu->run->xen.type = KVM_EXIT_XEN_HCALL; vcpu->run->xen.u.hcall.longmode = longmode; - vcpu->run->xen.u.hcall.cpl = static_call(kvm_x86_get_cpl)(vcpu); + vcpu->run->xen.u.hcall.cpl = cpl; vcpu->run->xen.u.hcall.input = input; vcpu->run->xen.u.hcall.params[0] = params[0]; vcpu->run->xen.u.hcall.params[1] = params[1]; @@ -1298,14 +1319,6 @@ int kvm_xen_hypercall(struct kvm_vcpu *vcpu) return 0; } -static inline int max_evtchn_port(struct kvm *kvm) -{ - if (IS_ENABLED(CONFIG_64BIT) && kvm->arch.xen.long_mode) - return EVTCHN_2L_NR_CHANNELS; - else - return COMPAT_EVTCHN_2L_NR_CHANNELS; -} - static void kvm_xen_check_poller(struct kvm_vcpu *vcpu, int port) { int poll_evtchn = vcpu->arch.xen.poll_evtchn; @@ -1667,18 +1680,18 @@ 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 +1731,7 @@ static int kvm_xen_eventfd_assign(struct kvm *kvm, out: if (eventfd) eventfd_ctx_put(eventfd); +out_noeventfd: kfree(evtchnfd); return ret; } @@ -1816,7 +1830,12 @@ 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 +1843,17 @@ 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 +1861,7 @@ 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) |