diff options
Diffstat (limited to 'arch')
107 files changed, 1776 insertions, 579 deletions
diff --git a/arch/arm64/include/asm/esr.h b/arch/arm64/include/asm/esr.h index a305ce256090..d52a0b269ee8 100644 --- a/arch/arm64/include/asm/esr.h +++ b/arch/arm64/include/asm/esr.h @@ -68,6 +68,7 @@ #define ESR_ELx_EC_MAX (0x3F) #define ESR_ELx_EC_SHIFT (26) +#define ESR_ELx_EC_WIDTH (6) #define ESR_ELx_EC_MASK (UL(0x3F) << ESR_ELx_EC_SHIFT) #define ESR_ELx_EC(esr) (((esr) & ESR_ELx_EC_MASK) >> ESR_ELx_EC_SHIFT) diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h index 4be8486042a7..2a5f7f38006f 100644 --- a/arch/arm64/include/asm/kvm_host.h +++ b/arch/arm64/include/asm/kvm_host.h @@ -584,7 +584,7 @@ struct kvm_vcpu_stat { u64 exits; }; -int kvm_vcpu_preferred_target(struct kvm_vcpu_init *init); +void kvm_vcpu_preferred_target(struct kvm_vcpu_init *init); unsigned long kvm_arm_num_regs(struct kvm_vcpu *vcpu); int kvm_arm_copy_reg_indices(struct kvm_vcpu *vcpu, u64 __user *indices); int kvm_arm_get_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg); diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c index 7de96196ae14..6f3e677d88f1 100644 --- a/arch/arm64/kernel/cpufeature.c +++ b/arch/arm64/kernel/cpufeature.c @@ -2868,6 +2868,7 @@ bool this_cpu_has_cap(unsigned int n) return false; } +EXPORT_SYMBOL_GPL(this_cpu_has_cap); /* * This helper function is used in a narrow window when, diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c index f5490afe1ebf..2f03cbfefe67 100644 --- a/arch/arm64/kvm/arm.c +++ b/arch/arm64/kvm/arm.c @@ -1389,12 +1389,9 @@ long kvm_arch_vm_ioctl(struct file *filp, return kvm_vm_ioctl_set_device_addr(kvm, &dev_addr); } case KVM_ARM_PREFERRED_TARGET: { - int err; struct kvm_vcpu_init init; - err = kvm_vcpu_preferred_target(&init); - if (err) - return err; + kvm_vcpu_preferred_target(&init); if (copy_to_user(argp, &init, sizeof(init))) return -EFAULT; diff --git a/arch/arm64/kvm/guest.c b/arch/arm64/kvm/guest.c index 5ce26bedf23c..e116c7767730 100644 --- a/arch/arm64/kvm/guest.c +++ b/arch/arm64/kvm/guest.c @@ -869,13 +869,10 @@ u32 __attribute_const__ kvm_target_cpu(void) return KVM_ARM_TARGET_GENERIC_V8; } -int kvm_vcpu_preferred_target(struct kvm_vcpu_init *init) +void kvm_vcpu_preferred_target(struct kvm_vcpu_init *init) { u32 target = kvm_target_cpu(); - if (target < 0) - return -ENODEV; - memset(init, 0, sizeof(*init)); /* @@ -885,8 +882,6 @@ int kvm_vcpu_preferred_target(struct kvm_vcpu_init *init) * target type. */ init->target = (__u32)target; - - return 0; } int kvm_arch_vcpu_ioctl_get_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu) diff --git a/arch/arm64/kvm/hyp/hyp-entry.S b/arch/arm64/kvm/hyp/hyp-entry.S index 9aa9b73475c9..b6b6801d96d5 100644 --- a/arch/arm64/kvm/hyp/hyp-entry.S +++ b/arch/arm64/kvm/hyp/hyp-entry.S @@ -44,7 +44,7 @@ el1_sync: // Guest trapped into EL2 mrs x0, esr_el2 - lsr x0, x0, #ESR_ELx_EC_SHIFT + ubfx x0, x0, #ESR_ELx_EC_SHIFT, #ESR_ELx_EC_WIDTH cmp x0, #ESR_ELx_EC_HVC64 ccmp x0, #ESR_ELx_EC_HVC32, #4, ne b.ne el1_trap diff --git a/arch/arm64/kvm/hyp/nvhe/host.S b/arch/arm64/kvm/hyp/nvhe/host.S index 0c6116d34e18..3d613e721a75 100644 --- a/arch/arm64/kvm/hyp/nvhe/host.S +++ b/arch/arm64/kvm/hyp/nvhe/host.S @@ -141,7 +141,7 @@ SYM_FUNC_END(__host_hvc) .L__vect_start\@: stp x0, x1, [sp, #-16]! mrs x0, esr_el2 - lsr x0, x0, #ESR_ELx_EC_SHIFT + ubfx x0, x0, #ESR_ELx_EC_SHIFT, #ESR_ELx_EC_WIDTH cmp x0, #ESR_ELx_EC_HVC64 b.eq __host_hvc b __host_exit diff --git a/arch/arm64/kvm/hyp/nvhe/setup.c b/arch/arm64/kvm/hyp/nvhe/setup.c index 862c7b514e20..578f71798c2e 100644 --- a/arch/arm64/kvm/hyp/nvhe/setup.c +++ b/arch/arm64/kvm/hyp/nvhe/setup.c @@ -178,7 +178,7 @@ static int finalize_host_mappings_walker(u64 addr, u64 end, u32 level, phys = kvm_pte_to_phys(pte); if (!addr_is_memory(phys)) - return 0; + return -EINVAL; /* * Adjust the host stage-2 mappings to match the ownership attributes @@ -207,8 +207,18 @@ static int finalize_host_mappings(void) .cb = finalize_host_mappings_walker, .flags = KVM_PGTABLE_WALK_LEAF, }; + int i, ret; + + for (i = 0; i < hyp_memblock_nr; i++) { + struct memblock_region *reg = &hyp_memory[i]; + u64 start = (u64)hyp_phys_to_virt(reg->base); + + ret = kvm_pgtable_walk(&pkvm_pgtable, start, reg->size, &walker); + if (ret) + return ret; + } - return kvm_pgtable_walk(&pkvm_pgtable, 0, BIT(pkvm_pgtable.ia_bits), &walker); + return 0; } void __noreturn __pkvm_init_finalise(void) diff --git a/arch/arm64/kvm/hyp/nvhe/sys_regs.c b/arch/arm64/kvm/hyp/nvhe/sys_regs.c index 3787ee6fb1a2..792cf6e6ac92 100644 --- a/arch/arm64/kvm/hyp/nvhe/sys_regs.c +++ b/arch/arm64/kvm/hyp/nvhe/sys_regs.c @@ -474,7 +474,7 @@ bool kvm_handle_pvm_sysreg(struct kvm_vcpu *vcpu, u64 *exit_code) return true; } -/** +/* * Handler for protected VM restricted exceptions. * * Inject an undefined exception into the guest and return true to indicate that diff --git a/arch/arm64/mm/kasan_init.c b/arch/arm64/mm/kasan_init.c index ec276f75fa05..c12cd700598f 100644 --- a/arch/arm64/mm/kasan_init.c +++ b/arch/arm64/mm/kasan_init.c @@ -310,7 +310,7 @@ void __init kasan_init(void) kasan_init_depth(); #if defined(CONFIG_KASAN_GENERIC) /* CONFIG_KASAN_SW_TAGS also requires kasan_init_sw_tags(). */ - pr_info("KernelAddressSanitizer initialized\n"); + pr_info("KernelAddressSanitizer initialized (generic)\n"); #endif } diff --git a/arch/m68k/Kconfig.cpu b/arch/m68k/Kconfig.cpu index 277d61a09463..0d00ef5117dc 100644 --- a/arch/m68k/Kconfig.cpu +++ b/arch/m68k/Kconfig.cpu @@ -53,17 +53,6 @@ config M68000 System-On-Chip devices (eg 68328, 68302, etc). It does not contain a paging MMU. -config MCPU32 - bool - select CPU_HAS_NO_BITFIELDS - select CPU_HAS_NO_CAS - select CPU_HAS_NO_UNALIGNED - select CPU_NO_EFFICIENT_FFS - help - The Freescale (was then Motorola) CPU32 is a CPU core that is - based on the 68020 processor. For the most part it is used in - System-On-Chip parts, and does not contain a paging MMU. - config M68020 bool "68020 support" depends on MMU diff --git a/arch/m68k/Kconfig.machine b/arch/m68k/Kconfig.machine index 36fa0c3ef129..eeab4f3e6c19 100644 --- a/arch/m68k/Kconfig.machine +++ b/arch/m68k/Kconfig.machine @@ -203,6 +203,7 @@ config INIT_LCD config MEMORY_RESERVE int "Memory reservation (MiB)" depends on (UCSIMM || UCDIMM) + default 0 help Reserve certain memory regions on 68x328 based boards. diff --git a/arch/m68k/include/asm/bitops.h b/arch/m68k/include/asm/bitops.h index 7b414099e5fc..7b93e1fd8ffa 100644 --- a/arch/m68k/include/asm/bitops.h +++ b/arch/m68k/include/asm/bitops.h @@ -451,7 +451,7 @@ static inline unsigned long ffz(unsigned long word) * generic functions for those. */ #if (defined(__mcfisaaplus__) || defined(__mcfisac__)) && \ - !defined(CONFIG_M68000) && !defined(CONFIG_MCPU32) + !defined(CONFIG_M68000) static inline unsigned long __ffs(unsigned long x) { __asm__ __volatile__ ("bitrev %0; ff1 %0" diff --git a/arch/mips/Kbuild.platforms b/arch/mips/Kbuild.platforms index 2c57994b5217..30193bcf9caa 100644 --- a/arch/mips/Kbuild.platforms +++ b/arch/mips/Kbuild.platforms @@ -37,4 +37,4 @@ platform-$(CONFIG_MACH_TX49XX) += txx9/ platform-$(CONFIG_MACH_VR41XX) += vr41xx/ # include the platform specific files -include $(patsubst %, $(srctree)/arch/mips/%/Platform, $(platform-y)) +include $(patsubst %/, $(srctree)/arch/mips/%/Platform, $(platform-y)) diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig index 86510741d49d..de60ad190057 100644 --- a/arch/mips/Kconfig +++ b/arch/mips/Kconfig @@ -292,6 +292,8 @@ config BMIPS_GENERIC select USB_OHCI_BIG_ENDIAN_DESC if CPU_BIG_ENDIAN select USB_OHCI_BIG_ENDIAN_MMIO if CPU_BIG_ENDIAN select HARDIRQS_SW_RESEND + select HAVE_PCI + select PCI_DRIVERS_GENERIC help Build a generic DT-based kernel image that boots on select BCM33xx cable modem chips, BCM63xx DSL chips, and BCM7xxx set-top @@ -333,6 +335,9 @@ config BCM63XX select SYS_SUPPORTS_32BIT_KERNEL select SYS_SUPPORTS_BIG_ENDIAN select SYS_HAS_EARLY_PRINTK + select SYS_HAS_CPU_BMIPS32_3300 + select SYS_HAS_CPU_BMIPS4350 + select SYS_HAS_CPU_BMIPS4380 select SWAP_IO_SPACE select GPIOLIB select MIPS_L1_CACHE_SHIFT_4 diff --git a/arch/mips/Makefile b/arch/mips/Makefile index e036fc025ccc..ace7f033de07 100644 --- a/arch/mips/Makefile +++ b/arch/mips/Makefile @@ -253,7 +253,9 @@ endif # # Board-dependent options and extra files # +ifdef need-compiler include $(srctree)/arch/mips/Kbuild.platforms +endif ifdef CONFIG_PHYSICAL_START load-y = $(CONFIG_PHYSICAL_START) diff --git a/arch/mips/boot/compressed/.gitignore b/arch/mips/boot/compressed/.gitignore deleted file mode 100644 index d358395614c9..000000000000 --- a/arch/mips/boot/compressed/.gitignore +++ /dev/null @@ -1,3 +0,0 @@ -# SPDX-License-Identifier: GPL-2.0-only -ashldi3.c -bswapsi.c diff --git a/arch/mips/boot/compressed/Makefile b/arch/mips/boot/compressed/Makefile index 3548b3b45269..2861a05c2e0c 100644 --- a/arch/mips/boot/compressed/Makefile +++ b/arch/mips/boot/compressed/Makefile @@ -50,19 +50,9 @@ vmlinuzobjs-$(CONFIG_MIPS_ALCHEMY) += $(obj)/uart-alchemy.o vmlinuzobjs-$(CONFIG_ATH79) += $(obj)/uart-ath79.o endif -extra-y += uart-ath79.c -$(obj)/uart-ath79.c: $(srctree)/arch/mips/ath79/early_printk.c - $(call cmd,shipped) - vmlinuzobjs-$(CONFIG_KERNEL_XZ) += $(obj)/ashldi3.o -extra-y += ashldi3.c -$(obj)/ashldi3.c: $(obj)/%.c: $(srctree)/lib/%.c FORCE - $(call if_changed,shipped) - -extra-y += bswapsi.c -$(obj)/bswapsi.c: $(obj)/%.c: $(srctree)/arch/mips/lib/%.c FORCE - $(call if_changed,shipped) +vmlinuzobjs-$(CONFIG_KERNEL_ZSTD) += $(obj)/bswapdi.o targets := $(notdir $(vmlinuzobjs-y)) diff --git a/arch/mips/boot/compressed/ashldi3.c b/arch/mips/boot/compressed/ashldi3.c new file mode 100644 index 000000000000..f7bf6a7aae31 --- /dev/null +++ b/arch/mips/boot/compressed/ashldi3.c @@ -0,0 +1,2 @@ +// SPDX-License-Identifier: GPL-2.0-only +#include "../../../../lib/ashldi3.c" diff --git a/arch/mips/boot/compressed/bswapdi.c b/arch/mips/boot/compressed/bswapdi.c new file mode 100644 index 000000000000..acb28aebb025 --- /dev/null +++ b/arch/mips/boot/compressed/bswapdi.c @@ -0,0 +1,2 @@ +// SPDX-License-Identifier: GPL-2.0-only +#include "../../lib/bswapdi.c" diff --git a/arch/mips/boot/compressed/bswapsi.c b/arch/mips/boot/compressed/bswapsi.c new file mode 100644 index 000000000000..fdb9c6476904 --- /dev/null +++ b/arch/mips/boot/compressed/bswapsi.c @@ -0,0 +1,2 @@ +// SPDX-License-Identifier: GPL-2.0-only +#include "../../lib/bswapsi.c" diff --git a/arch/mips/boot/compressed/uart-ath79.c b/arch/mips/boot/compressed/uart-ath79.c new file mode 100644 index 000000000000..d686820921be --- /dev/null +++ b/arch/mips/boot/compressed/uart-ath79.c @@ -0,0 +1,2 @@ +// SPDX-License-Identifier: GPL-2.0-only +#include "../../ath79/early_printk.c" diff --git a/arch/mips/configs/bmips_stb_defconfig b/arch/mips/configs/bmips_stb_defconfig index 625bd2d7e685..5956fb95c19f 100644 --- a/arch/mips/configs/bmips_stb_defconfig +++ b/arch/mips/configs/bmips_stb_defconfig @@ -1,6 +1,7 @@ # CONFIG_LOCALVERSION_AUTO is not set # CONFIG_SWAP is not set CONFIG_NO_HZ=y +CONFIG_HZ=1000 CONFIG_BLK_DEV_INITRD=y CONFIG_EXPERT=y # CONFIG_VM_EVENT_COUNTERS is not set @@ -8,17 +9,34 @@ CONFIG_EXPERT=y CONFIG_BMIPS_GENERIC=y CONFIG_CPU_LITTLE_ENDIAN=y CONFIG_HIGHMEM=y +CONFIG_HIGH_RES_TIMERS=y CONFIG_SMP=y CONFIG_NR_CPUS=4 +CONFIG_CC_STACKPROTECTOR_STRONG=y # CONFIG_SECCOMP is not set CONFIG_MIPS_O32_FP64_SUPPORT=y +# CONFIG_RD_GZIP is not set +# CONFIG_RD_BZIP2 is not set +# CONFIG_RD_LZMA is not set +CONFIG_RD_XZ=y +# CONFIG_RD_LZO is not set +# CONFIG_RD_LZ4 is not set +# CONFIG_IOSCHED_DEADLINE is not set +# CONFIG_IOSCHED_CFQ is not set +CONFIG_PCI=y +CONFIG_PCI_MSI=y +CONFIG_PCIEASPM_POWERSAVE=y +CONFIG_PCIEPORTBUS=y +CONFIG_PCIE_BRCMSTB=y CONFIG_CPU_FREQ=y CONFIG_CPU_FREQ_STAT=y +CONFIG_CPU_FREQ_STAT_DETAILS=y +CONFIG_CPU_FREQ_DEFAULT_GOV_PERFORMANCE=y +CONFIG_CPU_FREQ_GOV_PERFORMANCE=y CONFIG_CPU_FREQ_GOV_POWERSAVE=y CONFIG_CPU_FREQ_GOV_USERSPACE=y CONFIG_CPU_FREQ_GOV_ONDEMAND=y CONFIG_CPU_FREQ_GOV_CONSERVATIVE=y -CONFIG_CPU_FREQ_GOV_SCHEDUTIL=y CONFIG_BMIPS_CPUFREQ=y # CONFIG_BLK_DEV_BSG is not set CONFIG_NET=y @@ -32,32 +50,99 @@ CONFIG_INET=y # CONFIG_INET_DIAG is not set CONFIG_CFG80211=y CONFIG_NL80211_TESTMODE=y +CONFIG_WIRELESS=y CONFIG_MAC80211=y +CONFIG_NL80211=y CONFIG_DEVTMPFS=y CONFIG_DEVTMPFS_MOUNT=y # CONFIG_STANDALONE is not set # CONFIG_PREVENT_FIRMWARE_BUILD is not set +CONFIG_BRCMSTB_GISB_ARB=y +CONFIG_MODULES=y +CONFIG_MODULE_FORCE_LOAD=y +CONFIG_MODULE_UNLOAD=y +CONFIG_MODVERSIONS=y +CONFIG_IP_MULTICAST=y +CONFIG_IP_PNP=y +CONFIG_IP_PNP_DHCP=y +CONFIG_IP_PNP_BOOTP=y +CONFIG_IP_PNP_RARP=y +CONFIG_IP_MROUTE=y +CONFIG_IP_PIMSM_V1=y +CONFIG_IP_PIMSM_V2=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_LRO is not set +CONFIG_INET_UDP_DIAG=y +CONFIG_TCP_CONG_ADVANCED=y +CONFIG_TCP_CONG_BIC=y +# CONFIG_TCP_CONG_WESTWOOD is not set +# CONFIG_TCP_CONG_HTCP is not set +# CONFIG_IPV6 is not set +CONFIG_IP_NF_IPTABLES=y +CONFIG_IP_NF_FILTER=y +CONFIG_NETFILTER=y +CONFIG_NETFILTER_XTABLES=y +CONFIG_BRIDGE=y +CONFIG_BRIDGE_NETFILTER=m +CONFIG_BRIDGE_NF_EBTABLES=m +CONFIG_BRIDGE_EBT_BROUTE=m +CONFIG_NET_DSA=y +CONFIG_NET_SWITCHDEV=y +CONFIG_DMA_CMA=y +CONFIG_CMA_ALIGNMENT=12 +CONFIG_SPI=y +CONFIG_SPI_BRCMSTB=y CONFIG_MTD=y +CONFIG_MTD_CMDLINE_PARTS=y +CONFIG_MTD_BLOCK=y CONFIG_MTD_CFI=y +CONFIG_MTD_JEDECPROBE=y CONFIG_MTD_CFI_INTELEXT=y CONFIG_MTD_CFI_AMDSTD=y -CONFIG_MTD_PHYSMAP=y +CONFIG_MTD_CFI_STAA=y +CONFIG_MTD_ROM=y +CONFIG_MTD_ABSENT=y +CONFIG_MTD_PHYSMAP_OF=y +CONFIG_MTD_M25P80=y +CONFIG_MTD_NAND=y +CONFIG_MTD_NAND_BRCMNAND=y +CONFIG_MTD_SPI_NOR=y +# CONFIG_MTD_SPI_NOR_USE_4K_SECTORS is not set +CONFIG_MTD_UBI=y +CONFIG_MTD_UBI_GLUEBI=y +CONFIG_PROC_DEVICETREE=y +CONFIG_BLK_DEV_LOOP=y +CONFIG_BLK_DEV_RAM=y +CONFIG_BLK_DEV_RAM_SIZE=8192 # CONFIG_BLK_DEV is not set CONFIG_SCSI=y CONFIG_BLK_DEV_SD=y +CONFIG_CHR_DEV_SG=y +CONFIG_SCSI_MULTI_LUN=y # CONFIG_SCSI_LOWLEVEL is not set CONFIG_NETDEVICES=y +CONFIG_VLAN_8021Q=y +CONFIG_MACVLAN=y CONFIG_BCMGENET=y CONFIG_USB_USBNET=y -# CONFIG_INPUT is not set +CONFIG_INPUT_EVDEV=y +# CONFIG_INPUT_KEYBOARD is not set +# CONFIG_INPUT_MOUSE is not set +CONFIG_INPUT_MISC=y +CONFIG_INPUT_UINPUT=y # CONFIG_SERIO is not set -# CONFIG_VT is not set +CONFIG_VT=y +CONFIG_VT_HW_CONSOLE_BINDING=y +# CONFIG_DEVKMEM is not set CONFIG_SERIAL_8250=y # CONFIG_SERIAL_8250_DEPRECATED_OPTIONS is not set CONFIG_SERIAL_8250_CONSOLE=y CONFIG_SERIAL_OF_PLATFORM=y # CONFIG_HW_RANDOM is not set CONFIG_POWER_RESET=y +CONFIG_POWER_RESET_BRCMSTB=y CONFIG_POWER_RESET_SYSCON=y CONFIG_POWER_SUPPLY=y # CONFIG_HWMON is not set @@ -69,22 +154,76 @@ CONFIG_USB_OHCI_HCD=y CONFIG_USB_OHCI_HCD_PLATFORM=y CONFIG_USB_STORAGE=y CONFIG_SOC_BRCMSTB=y +CONFIG_MMC=y +CONFIG_MMC_BLOCK_MINORS=16 +CONFIG_MMC_SDHCI=y +CONFIG_MMC_SDHCI_PLTFM=y CONFIG_EXT4_FS=y CONFIG_EXT4_FS_POSIX_ACL=y CONFIG_EXT4_FS_SECURITY=y # CONFIG_DNOTIFY is not set +CONFIG_PROC_KCORE=y +CONFIG_CIFS=y +CONFIG_JBD2_DEBUG=y CONFIG_FUSE_FS=y +CONFIG_FHANDLE=y +CONFIG_CGROUPS=y +CONFIG_CUSE=y +CONFIG_ISO9660_FS=y +CONFIG_JOLIET=y +CONFIG_ZISOFS=y +CONFIG_UDF_FS=y +CONFIG_MSDOS_FS=y CONFIG_VFAT_FS=y -CONFIG_PROC_KCORE=y CONFIG_TMPFS=y +CONFIG_JFFS2_FS=y +CONFIG_UBIFS_FS=y +CONFIG_SQUASHFS=y +CONFIG_SQUASHFS_LZO=y +CONFIG_SQUASHFS_XZ=y CONFIG_NFS_FS=y -CONFIG_CIFS=y +CONFIG_NFS_V3_ACL=y +CONFIG_NFS_V4=y +CONFIG_NFS_V4_1=y +CONFIG_NFS_V4_2=y +CONFIG_ROOT_NFS=y CONFIG_NLS_CODEPAGE_437=y -CONFIG_NLS_ASCII=y CONFIG_NLS_ISO8859_1=y -# CONFIG_CRYPTO_HW is not set CONFIG_PRINTK_TIME=y +CONFIG_DYNAMIC_DEBUG=y +# CONFIG_DEBUG_INFO is not set +# CONFIG_DEBUG_INFO_REDUCED is not set CONFIG_DEBUG_FS=y CONFIG_MAGIC_SYSRQ=y +CONFIG_LOCKUP_DETECTOR=y +CONFIG_DEBUG_USER=y CONFIG_CMDLINE_BOOL=y CONFIG_CMDLINE="earlycon" +# CONFIG_MIPS_CMDLINE_FROM_DTB is not set +CONFIG_MIPS_CMDLINE_DTB_EXTEND=y +# CONFIG_MIPS_CMDLINE_FROM_BOOTLOADER is not set +# CONFIG_CRYPTO_HW is not set +CONFIG_DT_BCM974XX=y +CONFIG_FW_CFE=y +CONFIG_ATA=y +CONFIG_SATA_AHCI_PLATFORM=y +CONFIG_AHCI_BRCMSTB=y +CONFIG_GENERIC_PHY=y +CONFIG_GPIOLIB=y +CONFIG_GPIO_SYSFS=y +CONFIG_PHY_BRCM_USB=y +CONFIG_PHY_BRCM_SATA=y +CONFIG_PM_RUNTIME=y +CONFIG_PM_DEBUG=y +CONFIG_SYSVIPC=y +CONFIG_FUNCTION_GRAPH_TRACER=y +CONFIG_DYNAMIC_FTRACE=y +CONFIG_FUNCTION_TRACER=y +CONFIG_FUNCTION_PROFILER=y +CONFIG_IRQSOFF_TRACER=y +CONFIG_SCHED_TRACER=y +CONFIG_BLK_DEV_IO_TRACE=y +CONFIG_FTRACE_SYSCALLS=y +CONFIG_TRACER_SNAPSHOT=y +CONFIG_TRACER_SNAPSHOT_PER_CPU_SWAP=y +CONFIG_STACK_TRACER=y diff --git a/arch/mips/dec/setup.c b/arch/mips/dec/setup.c index eaad0ed4b523..a8a30bb1dee8 100644 --- a/arch/mips/dec/setup.c +++ b/arch/mips/dec/setup.c @@ -117,21 +117,21 @@ static void __init dec_be_init(void) { switch (mips_machtype) { case MACH_DS23100: /* DS2100/DS3100 Pmin/Pmax */ - board_be_handler = dec_kn01_be_handler; + mips_set_be_handler(dec_kn01_be_handler); busirq_handler = dec_kn01_be_interrupt; busirq_flags |= IRQF_SHARED; dec_kn01_be_init(); break; case MACH_DS5000_1XX: /* DS5000/1xx 3min */ case MACH_DS5000_XX: /* DS5000/xx Maxine */ - board_be_handler = dec_kn02xa_be_handler; + mips_set_be_handler(dec_kn02xa_be_handler); busirq_handler = dec_kn02xa_be_interrupt; dec_kn02xa_be_init(); break; case MACH_DS5000_200: /* DS5000/200 3max */ case MACH_DS5000_2X0: /* DS5000/240 3max+ */ case MACH_DS5900: /* DS5900 bigmax */ - board_be_handler = dec_ecc_be_handler; + mips_set_be_handler(dec_ecc_be_handler); busirq_handler = dec_ecc_be_interrupt; dec_ecc_be_init(); break; diff --git a/arch/mips/include/asm/traps.h b/arch/mips/include/asm/traps.h index b710e76c9c65..15cde638b407 100644 --- a/arch/mips/include/asm/traps.h +++ b/arch/mips/include/asm/traps.h @@ -15,7 +15,7 @@ #define MIPS_BE_FATAL 2 /* treat as an unrecoverable error */ extern void (*board_be_init)(void); -extern int (*board_be_handler)(struct pt_regs *regs, int is_fixup); +void mips_set_be_handler(int (*handler)(struct pt_regs *reg, int is_fixup)); extern void (*board_nmi_handler_setup)(void); extern void (*board_ejtag_handler_setup)(void); diff --git a/arch/mips/kernel/traps.c b/arch/mips/kernel/traps.c index 6f07362de5ce..d26b0fb8ea06 100644 --- a/arch/mips/kernel/traps.c +++ b/arch/mips/kernel/traps.c @@ -103,13 +103,19 @@ extern asmlinkage void handle_reserved(void); extern void tlb_do_page_fault_0(void); void (*board_be_init)(void); -int (*board_be_handler)(struct pt_regs *regs, int is_fixup); +static int (*board_be_handler)(struct pt_regs *regs, int is_fixup); void (*board_nmi_handler_setup)(void); void (*board_ejtag_handler_setup)(void); void (*board_bind_eic_interrupt)(int irq, int regset); void (*board_ebase_setup)(void); void(*board_cache_error_setup)(void); +void mips_set_be_handler(int (*handler)(struct pt_regs *regs, int is_fixup)) +{ + board_be_handler = handler; +} +EXPORT_SYMBOL_GPL(mips_set_be_handler); + static void show_raw_backtrace(unsigned long reg29, const char *loglvl, bool user) { diff --git a/arch/mips/sgi-ip22/ip22-berr.c b/arch/mips/sgi-ip22/ip22-berr.c index dc0110a607a5..afe8a61078e4 100644 --- a/arch/mips/sgi-ip22/ip22-berr.c +++ b/arch/mips/sgi-ip22/ip22-berr.c @@ -112,5 +112,5 @@ static int ip22_be_handler(struct pt_regs *regs, int is_fixup) void __init ip22_be_init(void) { - board_be_handler = ip22_be_handler; + mips_set_be_handler(ip22_be_handler); } diff --git a/arch/mips/sgi-ip22/ip28-berr.c b/arch/mips/sgi-ip22/ip28-berr.c index c61362d9ea95..16ca470deb80 100644 --- a/arch/mips/sgi-ip22/ip28-berr.c +++ b/arch/mips/sgi-ip22/ip28-berr.c @@ -468,7 +468,7 @@ static int ip28_be_handler(struct pt_regs *regs, int is_fixup) void __init ip22_be_init(void) { - board_be_handler = ip28_be_handler; + mips_set_be_handler(ip28_be_handler); } int ip28_show_be_info(struct seq_file *m) diff --git a/arch/mips/sgi-ip27/ip27-berr.c b/arch/mips/sgi-ip27/ip27-berr.c index 5a38ae6bdfa9..923a63a51cda 100644 --- a/arch/mips/sgi-ip27/ip27-berr.c +++ b/arch/mips/sgi-ip27/ip27-berr.c @@ -85,7 +85,7 @@ void __init ip27_be_init(void) int cpu = LOCAL_HUB_L(PI_CPU_NUM); int cpuoff = cpu << 8; - board_be_handler = ip27_be_handler; + mips_set_be_handler(ip27_be_handler); LOCAL_HUB_S(PI_ERR_INT_PEND, cpu ? PI_ERR_CLEAR_ALL_B : PI_ERR_CLEAR_ALL_A); diff --git a/arch/mips/sgi-ip32/ip32-berr.c b/arch/mips/sgi-ip32/ip32-berr.c index c860f95ab7ed..478b63b4c808 100644 --- a/arch/mips/sgi-ip32/ip32-berr.c +++ b/arch/mips/sgi-ip32/ip32-berr.c @@ -34,5 +34,5 @@ static int ip32_be_handler(struct pt_regs *regs, int is_fixup) void __init ip32_be_init(void) { - board_be_handler = ip32_be_handler; + mips_set_be_handler(ip32_be_handler); } diff --git a/arch/mips/sibyte/swarm/setup.c b/arch/mips/sibyte/swarm/setup.c index f07b15dd1c1a..72a31eeeebba 100644 --- a/arch/mips/sibyte/swarm/setup.c +++ b/arch/mips/sibyte/swarm/setup.c @@ -122,7 +122,7 @@ void __init plat_mem_setup(void) #error invalid SiByte board configuration #endif - board_be_handler = swarm_be_handler; + mips_set_be_handler(swarm_be_handler); if (xicor_probe()) swarm_rtc_type = RTC_XICOR; diff --git a/arch/mips/txx9/generic/setup_tx4927.c b/arch/mips/txx9/generic/setup_tx4927.c index 46e9c4101386..63f9725b2eb0 100644 --- a/arch/mips/txx9/generic/setup_tx4927.c +++ b/arch/mips/txx9/generic/setup_tx4927.c @@ -80,7 +80,7 @@ static int tx4927_be_handler(struct pt_regs *regs, int is_fixup) } static void __init tx4927_be_init(void) { - board_be_handler = tx4927_be_handler; + mips_set_be_handler(tx4927_be_handler); } static struct resource tx4927_sdram_resource[4]; diff --git a/arch/mips/txx9/generic/setup_tx4938.c b/arch/mips/txx9/generic/setup_tx4938.c index 17395d5d15ca..ba646548c5f6 100644 --- a/arch/mips/txx9/generic/setup_tx4938.c +++ b/arch/mips/txx9/generic/setup_tx4938.c @@ -82,7 +82,7 @@ static int tx4938_be_handler(struct pt_regs *regs, int is_fixup) } static void __init tx4938_be_init(void) { - board_be_handler = tx4938_be_handler; + mips_set_be_handler(tx4938_be_handler); } static struct resource tx4938_sdram_resource[4]; diff --git a/arch/mips/txx9/generic/setup_tx4939.c b/arch/mips/txx9/generic/setup_tx4939.c index bf8a3cdababf..f5f59b7401a3 100644 --- a/arch/mips/txx9/generic/setup_tx4939.c +++ b/arch/mips/txx9/generic/setup_tx4939.c @@ -86,7 +86,7 @@ static int tx4939_be_handler(struct pt_regs *regs, int is_fixup) } static void __init tx4939_be_init(void) { - board_be_handler = tx4939_be_handler; + mips_set_be_handler(tx4939_be_handler); } static struct resource tx4939_sdram_resource[4]; diff --git a/arch/mips/vdso/Makefile b/arch/mips/vdso/Makefile index 1b2ea34c3d3b..d65f55f67e19 100644 --- a/arch/mips/vdso/Makefile +++ b/arch/mips/vdso/Makefile @@ -57,7 +57,7 @@ endif # VDSO linker flags. ldflags-y := -Bsymbolic --no-undefined -soname=linux-vdso.so.1 \ - $(filter -E%,$(KBUILD_CFLAGS)) -nostdlib -shared \ + $(filter -E%,$(KBUILD_CFLAGS)) -shared \ -G 0 --eh-frame-hdr --hash-style=sysv --build-id=sha1 -T CFLAGS_REMOVE_vdso.o = $(CC_FLAGS_FTRACE) diff --git a/arch/powerpc/kvm/book3s_hv_uvmem.c b/arch/powerpc/kvm/book3s_hv_uvmem.c index a7061ee3b157..28c436df9935 100644 --- a/arch/powerpc/kvm/book3s_hv_uvmem.c +++ b/arch/powerpc/kvm/book3s_hv_uvmem.c @@ -560,7 +560,7 @@ static int __kvmppc_svm_page_out(struct vm_area_struct *vma, gpa, 0, page_shift); if (ret == U_SUCCESS) - *mig.dst = migrate_pfn(pfn) | MIGRATE_PFN_LOCKED; + *mig.dst = migrate_pfn(pfn); else { unlock_page(dpage); __free_page(dpage); @@ -774,7 +774,7 @@ static int kvmppc_svm_page_in(struct vm_area_struct *vma, } } - *mig.dst = migrate_pfn(page_to_pfn(dpage)) | MIGRATE_PFN_LOCKED; + *mig.dst = migrate_pfn(page_to_pfn(dpage)); migrate_vma_pages(&mig); out_finalize: migrate_vma_finalize(&mig); diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig index a34c531be4e7..821252b65f89 100644 --- a/arch/riscv/Kconfig +++ b/arch/riscv/Kconfig @@ -62,6 +62,7 @@ config RISCV select GENERIC_SCHED_CLOCK select GENERIC_SMP_IDLE_THREAD select GENERIC_TIME_VSYSCALL if MMU && 64BIT + select GENERIC_VDSO_TIME_NS if HAVE_GENERIC_VDSO select HAVE_ARCH_AUDITSYSCALL select HAVE_ARCH_JUMP_LABEL if !XIP_KERNEL select HAVE_ARCH_JUMP_LABEL_RELATIVE if !XIP_KERNEL diff --git a/arch/riscv/Makefile b/arch/riscv/Makefile index 7f19b784e649..5927c94302b8 100644 --- a/arch/riscv/Makefile +++ b/arch/riscv/Makefile @@ -136,3 +136,13 @@ zinstall: install-image = Image.gz install zinstall: $(CONFIG_SHELL) $(srctree)/$(boot)/install.sh $(KERNELRELEASE) \ $(boot)/$(install-image) System.map "$(INSTALL_PATH)" + +PHONY += rv32_randconfig +rv32_randconfig: + $(Q)$(MAKE) KCONFIG_ALLCONFIG=$(srctree)/arch/riscv/configs/32-bit.config \ + -f $(srctree)/Makefile randconfig + +PHONY += rv64_randconfig +rv64_randconfig: + $(Q)$(MAKE) KCONFIG_ALLCONFIG=$(srctree)/arch/riscv/configs/64-bit.config \ + -f $(srctree)/Makefile randconfig diff --git a/arch/riscv/boot/dts/microchip/microchip-mpfs-icicle-kit.dts b/arch/riscv/boot/dts/microchip/microchip-mpfs-icicle-kit.dts index b254c60589a1..fc1e5869df1b 100644 --- a/arch/riscv/boot/dts/microchip/microchip-mpfs-icicle-kit.dts +++ b/arch/riscv/boot/dts/microchip/microchip-mpfs-icicle-kit.dts @@ -9,10 +9,8 @@ #define RTCCLK_FREQ 1000000 / { - #address-cells = <2>; - #size-cells = <2>; model = "Microchip PolarFire-SoC Icicle Kit"; - compatible = "microchip,mpfs-icicle-kit"; + compatible = "microchip,mpfs-icicle-kit", "microchip,mpfs"; aliases { ethernet0 = &emac1; @@ -35,9 +33,6 @@ reg = <0x0 0x80000000 0x0 0x40000000>; clocks = <&clkcfg 26>; }; - - soc { - }; }; &serial0 { @@ -56,8 +51,17 @@ status = "okay"; }; -&sdcard { +&mmc { status = "okay"; + + bus-width = <4>; + disable-wp; + cap-sd-highspeed; + card-detect-delay = <200>; + sd-uhs-sdr12; + sd-uhs-sdr25; + sd-uhs-sdr50; + sd-uhs-sdr104; }; &emac0 { diff --git a/arch/riscv/boot/dts/microchip/microchip-mpfs.dtsi b/arch/riscv/boot/dts/microchip/microchip-mpfs.dtsi index 9d2fbbc1f777..c9f6d205d2ba 100644 --- a/arch/riscv/boot/dts/microchip/microchip-mpfs.dtsi +++ b/arch/riscv/boot/dts/microchip/microchip-mpfs.dtsi @@ -6,8 +6,8 @@ / { #address-cells = <2>; #size-cells = <2>; - model = "Microchip MPFS Icicle Kit"; - compatible = "microchip,mpfs-icicle-kit"; + model = "Microchip PolarFire SoC"; + compatible = "microchip,mpfs"; chosen { }; @@ -161,7 +161,7 @@ }; clint@2000000 { - compatible = "sifive,clint0"; + compatible = "sifive,fu540-c000-clint", "sifive,clint0"; reg = <0x0 0x2000000 0x0 0xC000>; interrupts-extended = <&cpu0_intc 3 &cpu0_intc 7 &cpu1_intc 3 &cpu1_intc 7 @@ -172,7 +172,7 @@ plic: interrupt-controller@c000000 { #interrupt-cells = <1>; - compatible = "sifive,plic-1.0.0"; + compatible = "sifive,fu540-c000-plic", "sifive,plic-1.0.0"; reg = <0x0 0xc000000 0x0 0x4000000>; riscv,ndev = <186>; interrupt-controller; @@ -262,39 +262,13 @@ status = "disabled"; }; - emmc: mmc@20008000 { - compatible = "cdns,sd4hc"; + /* Common node entry for emmc/sd */ + mmc: mmc@20008000 { + compatible = "microchip,mpfs-sd4hc", "cdns,sd4hc"; reg = <0x0 0x20008000 0x0 0x1000>; interrupt-parent = <&plic>; interrupts = <88 89>; - pinctrl-names = "default"; clocks = <&clkcfg 6>; - bus-width = <4>; - cap-mmc-highspeed; - mmc-ddr-3_3v; - max-frequency = <200000000>; - non-removable; - no-sd; - no-sdio; - voltage-ranges = <3300 3300>; - status = "disabled"; - }; - - sdcard: sdhc@20008000 { - compatible = "cdns,sd4hc"; - reg = <0x0 0x20008000 0x0 0x1000>; - interrupt-parent = <&plic>; - interrupts = <88>; - pinctrl-names = "default"; - clocks = <&clkcfg 6>; - bus-width = <4>; - disable-wp; - cap-sd-highspeed; - card-detect-delay = <200>; - sd-uhs-sdr12; - sd-uhs-sdr25; - sd-uhs-sdr50; - sd-uhs-sdr104; max-frequency = <200000000>; status = "disabled"; }; diff --git a/arch/riscv/boot/dts/sifive/fu540-c000.dtsi b/arch/riscv/boot/dts/sifive/fu540-c000.dtsi index 7db861053483..0655b5c4201d 100644 --- a/arch/riscv/boot/dts/sifive/fu540-c000.dtsi +++ b/arch/riscv/boot/dts/sifive/fu540-c000.dtsi @@ -141,7 +141,7 @@ ranges; plic0: interrupt-controller@c000000 { #interrupt-cells = <1>; - compatible = "sifive,plic-1.0.0"; + compatible = "sifive,fu540-c000-plic", "sifive,plic-1.0.0"; reg = <0x0 0xc000000 0x0 0x4000000>; riscv,ndev = <53>; interrupt-controller; diff --git a/arch/riscv/boot/dts/sifive/hifive-unleashed-a00.dts b/arch/riscv/boot/dts/sifive/hifive-unleashed-a00.dts index 60846e88ae4b..ba304d4c455c 100644 --- a/arch/riscv/boot/dts/sifive/hifive-unleashed-a00.dts +++ b/arch/riscv/boot/dts/sifive/hifive-unleashed-a00.dts @@ -8,10 +8,9 @@ #define RTCCLK_FREQ 1000000 / { - #address-cells = <2>; - #size-cells = <2>; model = "SiFive HiFive Unleashed A00"; - compatible = "sifive,hifive-unleashed-a00", "sifive,fu540-c000"; + compatible = "sifive,hifive-unleashed-a00", "sifive,fu540-c000", + "sifive,fu540"; chosen { stdout-path = "serial0"; @@ -26,9 +25,6 @@ reg = <0x0 0x80000000 0x2 0x00000000>; }; - soc { - }; - hfclk: hfclk { #clock-cells = <0>; compatible = "fixed-clock"; @@ -63,7 +59,7 @@ &qspi0 { status = "okay"; flash@0 { - compatible = "issi,is25wp256", "jedec,spi-nor"; + compatible = "jedec,spi-nor"; reg = <0>; spi-max-frequency = <50000000>; m25p,fast-read; diff --git a/arch/riscv/boot/dts/sifive/hifive-unmatched-a00.dts b/arch/riscv/boot/dts/sifive/hifive-unmatched-a00.dts index 2e4ea84f27e7..4f66919215f6 100644 --- a/arch/riscv/boot/dts/sifive/hifive-unmatched-a00.dts +++ b/arch/riscv/boot/dts/sifive/hifive-unmatched-a00.dts @@ -8,8 +8,6 @@ #define RTCCLK_FREQ 1000000 / { - #address-cells = <2>; - #size-cells = <2>; model = "SiFive HiFive Unmatched A00"; compatible = "sifive,hifive-unmatched-a00", "sifive,fu740-c000", "sifive,fu740"; @@ -27,9 +25,6 @@ reg = <0x0 0x80000000 0x4 0x00000000>; }; - soc { - }; - hfclk: hfclk { #clock-cells = <0>; compatible = "fixed-clock"; @@ -211,7 +206,7 @@ &qspi0 { status = "okay"; flash@0 { - compatible = "issi,is25wp256", "jedec,spi-nor"; + compatible = "jedec,spi-nor"; reg = <0>; spi-max-frequency = <50000000>; m25p,fast-read; diff --git a/arch/riscv/configs/32-bit.config b/arch/riscv/configs/32-bit.config new file mode 100644 index 000000000000..43f41323b67e --- /dev/null +++ b/arch/riscv/configs/32-bit.config @@ -0,0 +1,2 @@ +CONFIG_ARCH_RV32I=y +CONFIG_32BIT=y diff --git a/arch/riscv/configs/64-bit.config b/arch/riscv/configs/64-bit.config new file mode 100644 index 000000000000..313edc554d84 --- /dev/null +++ b/arch/riscv/configs/64-bit.config @@ -0,0 +1,2 @@ +CONFIG_ARCH_RV64I=y +CONFIG_64BIT=y diff --git a/arch/riscv/configs/defconfig b/arch/riscv/configs/defconfig index 4ebc80315f01..c252fd5706d2 100644 --- a/arch/riscv/configs/defconfig +++ b/arch/riscv/configs/defconfig @@ -72,9 +72,10 @@ CONFIG_GPIOLIB=y CONFIG_GPIO_SIFIVE=y # CONFIG_PTP_1588_CLOCK is not set CONFIG_POWER_RESET=y -CONFIG_DRM=y -CONFIG_DRM_RADEON=y -CONFIG_DRM_VIRTIO_GPU=y +CONFIG_DRM=m +CONFIG_DRM_RADEON=m +CONFIG_DRM_NOUVEAU=m +CONFIG_DRM_VIRTIO_GPU=m CONFIG_FRAMEBUFFER_CONSOLE=y CONFIG_USB=y CONFIG_USB_XHCI_HCD=y diff --git a/arch/riscv/include/asm/page.h b/arch/riscv/include/asm/page.h index 109c97e991a6..b3e5ff0125fe 100644 --- a/arch/riscv/include/asm/page.h +++ b/arch/riscv/include/asm/page.h @@ -157,6 +157,8 @@ extern phys_addr_t __phys_addr_symbol(unsigned long x); #define page_to_bus(page) (page_to_phys(page)) #define phys_to_page(paddr) (pfn_to_page(phys_to_pfn(paddr))) +#define sym_to_pfn(x) __phys_to_pfn(__pa_symbol(x)) + #ifdef CONFIG_FLATMEM #define pfn_valid(pfn) \ (((pfn) >= ARCH_PFN_OFFSET) && (((pfn) - ARCH_PFN_OFFSET) < max_mapnr)) diff --git a/arch/riscv/include/asm/pgtable.h b/arch/riscv/include/asm/pgtable.h index 39b550310ec6..bf204e7c1f74 100644 --- a/arch/riscv/include/asm/pgtable.h +++ b/arch/riscv/include/asm/pgtable.h @@ -75,7 +75,8 @@ #endif #ifdef CONFIG_XIP_KERNEL -#define XIP_OFFSET SZ_8M +#define XIP_OFFSET SZ_32M +#define XIP_OFFSET_MASK (SZ_32M - 1) #else #define XIP_OFFSET 0 #endif @@ -97,7 +98,8 @@ #ifdef CONFIG_XIP_KERNEL #define XIP_FIXUP(addr) ({ \ uintptr_t __a = (uintptr_t)(addr); \ - (__a >= CONFIG_XIP_PHYS_ADDR && __a < CONFIG_XIP_PHYS_ADDR + SZ_16M) ? \ + (__a >= CONFIG_XIP_PHYS_ADDR && \ + __a < CONFIG_XIP_PHYS_ADDR + XIP_OFFSET * 2) ? \ __a - CONFIG_XIP_PHYS_ADDR + CONFIG_PHYS_RAM_BASE - XIP_OFFSET :\ __a; \ }) diff --git a/arch/riscv/include/asm/vdso.h b/arch/riscv/include/asm/vdso.h index 208e31bc5d1c..bc6f75f3a199 100644 --- a/arch/riscv/include/asm/vdso.h +++ b/arch/riscv/include/asm/vdso.h @@ -8,30 +8,19 @@ #ifndef _ASM_RISCV_VDSO_H #define _ASM_RISCV_VDSO_H - -/* - * All systems with an MMU have a VDSO, but systems without an MMU don't - * support shared libraries and therefor don't have one. - */ -#ifdef CONFIG_MMU - -#include <linux/types.h> /* * All systems with an MMU have a VDSO, but systems without an MMU don't * support shared libraries and therefor don't have one. */ #ifdef CONFIG_MMU -#define __VVAR_PAGES 1 +#define __VVAR_PAGES 2 #ifndef __ASSEMBLY__ #include <generated/vdso-offsets.h> #define VDSO_SYMBOL(base, name) \ (void __user *)((unsigned long)(base) + __vdso_##name##_offset) - -#endif /* CONFIG_MMU */ - #endif /* !__ASSEMBLY__ */ #endif /* CONFIG_MMU */ diff --git a/arch/riscv/include/asm/vdso/gettimeofday.h b/arch/riscv/include/asm/vdso/gettimeofday.h index f839f16e0d2a..77d9c2f721c4 100644 --- a/arch/riscv/include/asm/vdso/gettimeofday.h +++ b/arch/riscv/include/asm/vdso/gettimeofday.h @@ -76,6 +76,13 @@ static __always_inline const struct vdso_data *__arch_get_vdso_data(void) return _vdso_data; } +#ifdef CONFIG_TIME_NS +static __always_inline +const struct vdso_data *__arch_get_timens_vdso_data(const struct vdso_data *vd) +{ + return _timens_data; +} +#endif #endif /* !__ASSEMBLY__ */ #endif /* __ASM_VDSO_GETTIMEOFDAY_H */ diff --git a/arch/riscv/kernel/head.S b/arch/riscv/kernel/head.S index 25ec50573957..f52f01ecbeea 100644 --- a/arch/riscv/kernel/head.S +++ b/arch/riscv/kernel/head.S @@ -20,10 +20,20 @@ REG_L t0, _xip_fixup add \reg, \reg, t0 .endm +.macro XIP_FIXUP_FLASH_OFFSET reg + la t1, __data_loc + li t0, XIP_OFFSET_MASK + and t1, t1, t0 + li t1, XIP_OFFSET + sub t0, t0, t1 + sub \reg, \reg, t0 +.endm _xip_fixup: .dword CONFIG_PHYS_RAM_BASE - CONFIG_XIP_PHYS_ADDR - XIP_OFFSET #else .macro XIP_FIXUP_OFFSET reg .endm +.macro XIP_FIXUP_FLASH_OFFSET reg +.endm #endif /* CONFIG_XIP_KERNEL */ __HEAD @@ -267,6 +277,7 @@ pmp_done: la a3, hart_lottery mv a2, a3 XIP_FIXUP_OFFSET a2 + XIP_FIXUP_FLASH_OFFSET a3 lw t1, (a3) amoswap.w t0, t1, (a2) /* first time here if hart_lottery in RAM is not set */ @@ -305,6 +316,7 @@ clear_bss_done: XIP_FIXUP_OFFSET sp #ifdef CONFIG_BUILTIN_DTB la a0, __dtb_start + XIP_FIXUP_OFFSET a0 #else mv a0, s1 #endif /* CONFIG_BUILTIN_DTB */ diff --git a/arch/riscv/kernel/reset.c b/arch/riscv/kernel/reset.c index ee5878d968cc..9c842c41684a 100644 --- a/arch/riscv/kernel/reset.c +++ b/arch/riscv/kernel/reset.c @@ -12,7 +12,7 @@ static void default_power_off(void) wait_for_interrupt(); } -void (*pm_power_off)(void) = default_power_off; +void (*pm_power_off)(void) = NULL; EXPORT_SYMBOL(pm_power_off); void machine_restart(char *cmd) @@ -23,10 +23,16 @@ void machine_restart(char *cmd) void machine_halt(void) { - pm_power_off(); + if (pm_power_off != NULL) + pm_power_off(); + else + default_power_off(); } void machine_power_off(void) { - pm_power_off(); + if (pm_power_off != NULL) + pm_power_off(); + else + default_power_off(); } diff --git a/arch/riscv/kernel/vdso.c b/arch/riscv/kernel/vdso.c index b70956d80408..a9436a65161a 100644 --- a/arch/riscv/kernel/vdso.c +++ b/arch/riscv/kernel/vdso.c @@ -13,6 +13,7 @@ #include <linux/err.h> #include <asm/page.h> #include <asm/vdso.h> +#include <linux/time_namespace.h> #ifdef CONFIG_GENERIC_TIME_VSYSCALL #include <vdso/datapage.h> @@ -25,14 +26,12 @@ extern char vdso_start[], vdso_end[]; enum vvar_pages { VVAR_DATA_PAGE_OFFSET, + VVAR_TIMENS_PAGE_OFFSET, VVAR_NR_PAGES, }; #define VVAR_SIZE (VVAR_NR_PAGES << PAGE_SHIFT) -static unsigned int vdso_pages __ro_after_init; -static struct page **vdso_pagelist __ro_after_init; - /* * The vDSO data page. */ @@ -42,83 +41,228 @@ static union { } vdso_data_store __page_aligned_data; struct vdso_data *vdso_data = &vdso_data_store.data; -static int __init vdso_init(void) +struct __vdso_info { + const char *name; + const char *vdso_code_start; + const char *vdso_code_end; + unsigned long vdso_pages; + /* Data Mapping */ + struct vm_special_mapping *dm; + /* Code Mapping */ + struct vm_special_mapping *cm; +}; + +static struct __vdso_info vdso_info __ro_after_init = { + .name = "vdso", + .vdso_code_start = vdso_start, + .vdso_code_end = vdso_end, +}; + +static int vdso_mremap(const struct vm_special_mapping *sm, + struct vm_area_struct *new_vma) +{ + current->mm->context.vdso = (void *)new_vma->vm_start; + + return 0; +} + +static int __init __vdso_init(void) { unsigned int i; + struct page **vdso_pagelist; + unsigned long pfn; - vdso_pages = (vdso_end - vdso_start) >> PAGE_SHIFT; - vdso_pagelist = - kcalloc(vdso_pages + VVAR_NR_PAGES, sizeof(struct page *), GFP_KERNEL); - if (unlikely(vdso_pagelist == NULL)) { - pr_err("vdso: pagelist allocation failed\n"); - return -ENOMEM; + if (memcmp(vdso_info.vdso_code_start, "\177ELF", 4)) { + pr_err("vDSO is not a valid ELF object!\n"); + return -EINVAL; } - for (i = 0; i < vdso_pages; i++) { - struct page *pg; + vdso_info.vdso_pages = ( + vdso_info.vdso_code_end - + vdso_info.vdso_code_start) >> + PAGE_SHIFT; + + vdso_pagelist = kcalloc(vdso_info.vdso_pages, + sizeof(struct page *), + GFP_KERNEL); + if (vdso_pagelist == NULL) + return -ENOMEM; + + /* Grab the vDSO code pages. */ + pfn = sym_to_pfn(vdso_info.vdso_code_start); + + for (i = 0; i < vdso_info.vdso_pages; i++) + vdso_pagelist[i] = pfn_to_page(pfn + i); + + vdso_info.cm->pages = vdso_pagelist; + + return 0; +} + +#ifdef CONFIG_TIME_NS +struct vdso_data *arch_get_vdso_data(void *vvar_page) +{ + return (struct vdso_data *)(vvar_page); +} + +/* + * The vvar mapping contains data for a specific time namespace, so when a task + * changes namespace we must unmap its vvar data for the old namespace. + * Subsequent faults will map in data for the new namespace. + * + * For more details see timens_setup_vdso_data(). + */ +int vdso_join_timens(struct task_struct *task, struct time_namespace *ns) +{ + struct mm_struct *mm = task->mm; + struct vm_area_struct *vma; + + mmap_read_lock(mm); - pg = virt_to_page(vdso_start + (i << PAGE_SHIFT)); - vdso_pagelist[i] = pg; + for (vma = mm->mmap; vma; vma = vma->vm_next) { + unsigned long size = vma->vm_end - vma->vm_start; + + if (vma_is_special_mapping(vma, vdso_info.dm)) + zap_page_range(vma, vma->vm_start, size); } - vdso_pagelist[i] = virt_to_page(vdso_data); + mmap_read_unlock(mm); return 0; } + +static struct page *find_timens_vvar_page(struct vm_area_struct *vma) +{ + if (likely(vma->vm_mm == current->mm)) + return current->nsproxy->time_ns->vvar_page; + + /* + * VM_PFNMAP | VM_IO protect .fault() handler from being called + * through interfaces like /proc/$pid/mem or + * process_vm_{readv,writev}() as long as there's no .access() + * in special_mapping_vmops. + * For more details check_vma_flags() and __access_remote_vm() + */ + WARN(1, "vvar_page accessed remotely"); + + return NULL; +} +#else +static struct page *find_timens_vvar_page(struct vm_area_struct *vma) +{ + return NULL; +} +#endif + +static vm_fault_t vvar_fault(const struct vm_special_mapping *sm, + struct vm_area_struct *vma, struct vm_fault *vmf) +{ + struct page *timens_page = find_timens_vvar_page(vma); + unsigned long pfn; + + switch (vmf->pgoff) { + case VVAR_DATA_PAGE_OFFSET: + if (timens_page) + pfn = page_to_pfn(timens_page); + else + pfn = sym_to_pfn(vdso_data); + break; +#ifdef CONFIG_TIME_NS + case VVAR_TIMENS_PAGE_OFFSET: + /* + * If a task belongs to a time namespace then a namespace + * specific VVAR is mapped with the VVAR_DATA_PAGE_OFFSET and + * the real VVAR page is mapped with the VVAR_TIMENS_PAGE_OFFSET + * offset. + * See also the comment near timens_setup_vdso_data(). + */ + if (!timens_page) + return VM_FAULT_SIGBUS; + pfn = sym_to_pfn(vdso_data); + break; +#endif /* CONFIG_TIME_NS */ + default: + return VM_FAULT_SIGBUS; + } + + return vmf_insert_pfn(vma, vmf->address, pfn); +} + +enum rv_vdso_map { + RV_VDSO_MAP_VVAR, + RV_VDSO_MAP_VDSO, +}; + +static struct vm_special_mapping rv_vdso_maps[] __ro_after_init = { + [RV_VDSO_MAP_VVAR] = { + .name = "[vvar]", + .fault = vvar_fault, + }, + [RV_VDSO_MAP_VDSO] = { + .name = "[vdso]", + .mremap = vdso_mremap, + }, +}; + +static int __init vdso_init(void) +{ + vdso_info.dm = &rv_vdso_maps[RV_VDSO_MAP_VVAR]; + vdso_info.cm = &rv_vdso_maps[RV_VDSO_MAP_VDSO]; + + return __vdso_init(); +} arch_initcall(vdso_init); -int arch_setup_additional_pages(struct linux_binprm *bprm, - int uses_interp) +static int __setup_additional_pages(struct mm_struct *mm, + struct linux_binprm *bprm, + int uses_interp) { - struct mm_struct *mm = current->mm; - unsigned long vdso_base, vdso_len; - int ret; + unsigned long vdso_base, vdso_text_len, vdso_mapping_len; + void *ret; BUILD_BUG_ON(VVAR_NR_PAGES != __VVAR_PAGES); - vdso_len = (vdso_pages + VVAR_NR_PAGES) << PAGE_SHIFT; + vdso_text_len = vdso_info.vdso_pages << PAGE_SHIFT; + /* Be sure to map the data page */ + vdso_mapping_len = vdso_text_len + VVAR_SIZE; - if (mmap_write_lock_killable(mm)) - return -EINTR; - - vdso_base = get_unmapped_area(NULL, 0, vdso_len, 0, 0); + vdso_base = get_unmapped_area(NULL, 0, vdso_mapping_len, 0, 0); if (IS_ERR_VALUE(vdso_base)) { - ret = vdso_base; - goto end; + ret = ERR_PTR(vdso_base); + goto up_fail; } - mm->context.vdso = NULL; - ret = install_special_mapping(mm, vdso_base, VVAR_SIZE, - (VM_READ | VM_MAYREAD), &vdso_pagelist[vdso_pages]); - if (unlikely(ret)) - goto end; + ret = _install_special_mapping(mm, vdso_base, VVAR_SIZE, + (VM_READ | VM_MAYREAD | VM_PFNMAP), vdso_info.dm); + if (IS_ERR(ret)) + goto up_fail; + vdso_base += VVAR_SIZE; + mm->context.vdso = (void *)vdso_base; ret = - install_special_mapping(mm, vdso_base + VVAR_SIZE, - vdso_pages << PAGE_SHIFT, + _install_special_mapping(mm, vdso_base, vdso_text_len, (VM_READ | VM_EXEC | VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC), - vdso_pagelist); + vdso_info.cm); - if (unlikely(ret)) - goto end; + if (IS_ERR(ret)) + goto up_fail; - /* - * Put vDSO base into mm struct. We need to do this before calling - * install_special_mapping or the perf counter mmap tracking code - * will fail to recognise it as a vDSO (since arch_vma_name fails). - */ - mm->context.vdso = (void *)vdso_base + VVAR_SIZE; + return 0; -end: - mmap_write_unlock(mm); - return ret; +up_fail: + mm->context.vdso = NULL; + return PTR_ERR(ret); } -const char *arch_vma_name(struct vm_area_struct *vma) +int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp) { - if (vma->vm_mm && (vma->vm_start == (long)vma->vm_mm->context.vdso)) - return "[vdso]"; - if (vma->vm_mm && (vma->vm_start == - (long)vma->vm_mm->context.vdso - VVAR_SIZE)) - return "[vdso_data]"; - return NULL; + struct mm_struct *mm = current->mm; + int ret; + + if (mmap_write_lock_killable(mm)) + return -EINTR; + + ret = __setup_additional_pages(mm, bprm, uses_interp); + mmap_write_unlock(mm); + + return ret; } diff --git a/arch/riscv/kernel/vdso/vdso.lds.S b/arch/riscv/kernel/vdso/vdso.lds.S index e9111f700af0..01d94aae5bf5 100644 --- a/arch/riscv/kernel/vdso/vdso.lds.S +++ b/arch/riscv/kernel/vdso/vdso.lds.S @@ -10,6 +10,9 @@ OUTPUT_ARCH(riscv) SECTIONS { PROVIDE(_vdso_data = . - __VVAR_PAGES * PAGE_SIZE); +#ifdef CONFIG_TIME_NS + PROVIDE(_timens_data = _vdso_data + PAGE_SIZE); +#endif . = SIZEOF_HEADERS; .hash : { *(.hash) } :text diff --git a/arch/riscv/kernel/vmlinux-xip.lds.S b/arch/riscv/kernel/vmlinux-xip.lds.S index 9c9f35091ef0..f5ed08262139 100644 --- a/arch/riscv/kernel/vmlinux-xip.lds.S +++ b/arch/riscv/kernel/vmlinux-xip.lds.S @@ -64,8 +64,11 @@ SECTIONS /* * From this point, stuff is considered writable and will be copied to RAM */ - __data_loc = ALIGN(16); /* location in file */ - . = LOAD_OFFSET + XIP_OFFSET; /* location in memory */ + __data_loc = ALIGN(PAGE_SIZE); /* location in file */ + . = KERNEL_LINK_ADDR + XIP_OFFSET; /* location in memory */ + +#undef LOAD_OFFSET +#define LOAD_OFFSET (KERNEL_LINK_ADDR + XIP_OFFSET - (__data_loc & XIP_OFFSET_MASK)) _sdata = .; /* Start of data section */ _data = .; @@ -96,7 +99,6 @@ SECTIONS KEEP(*(__soc_builtin_dtb_table)) __soc_builtin_dtb_table_end = .; } - PERCPU_SECTION(L1_CACHE_BYTES) . = ALIGN(8); .alternative : { @@ -122,6 +124,8 @@ SECTIONS BSS_SECTION(PAGE_SIZE, PAGE_SIZE, 0) + PERCPU_SECTION(L1_CACHE_BYTES) + .rel.dyn : AT(ADDR(.rel.dyn) - LOAD_OFFSET) { *(.rel.dyn*) } diff --git a/arch/riscv/mm/context.c b/arch/riscv/mm/context.c index ee3459cb6750..ea54cc0c9106 100644 --- a/arch/riscv/mm/context.c +++ b/arch/riscv/mm/context.c @@ -233,8 +233,10 @@ static int __init asids_init(void) local_flush_tlb_all(); /* Pre-compute ASID details */ - num_asids = 1 << asid_bits; - asid_mask = num_asids - 1; + if (asid_bits) { + num_asids = 1 << asid_bits; + asid_mask = num_asids - 1; + } /* * Use ASID allocator only if number of HW ASIDs are @@ -255,7 +257,7 @@ static int __init asids_init(void) pr_info("ASID allocator using %lu bits (%lu entries)\n", asid_bits, num_asids); } else { - pr_info("ASID allocator disabled\n"); + pr_info("ASID allocator disabled (%lu bits)\n", asid_bits); } return 0; diff --git a/arch/riscv/mm/extable.c b/arch/riscv/mm/extable.c index 18bf338303b6..ddb7d3b99e89 100644 --- a/arch/riscv/mm/extable.c +++ b/arch/riscv/mm/extable.c @@ -11,7 +11,7 @@ #include <linux/module.h> #include <linux/uaccess.h> -#ifdef CONFIG_BPF_JIT +#if defined(CONFIG_BPF_JIT) && defined(CONFIG_ARCH_RV64I) int rv_bpf_fixup_exception(const struct exception_table_entry *ex, struct pt_regs *regs); #endif @@ -23,7 +23,7 @@ int fixup_exception(struct pt_regs *regs) if (!fixup) return 0; -#ifdef CONFIG_BPF_JIT +#if defined(CONFIG_BPF_JIT) && defined(CONFIG_ARCH_RV64I) if (regs->epc >= BPF_JIT_REGION_START && regs->epc < BPF_JIT_REGION_END) return rv_bpf_fixup_exception(fixup, regs); #endif diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c index c0cddf0fc22d..24b2b8044602 100644 --- a/arch/riscv/mm/init.c +++ b/arch/riscv/mm/init.c @@ -41,7 +41,7 @@ phys_addr_t phys_ram_base __ro_after_init; EXPORT_SYMBOL(phys_ram_base); #ifdef CONFIG_XIP_KERNEL -extern char _xiprom[], _exiprom[]; +extern char _xiprom[], _exiprom[], __data_loc; #endif unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)] @@ -454,10 +454,9 @@ static uintptr_t __init best_map_size(phys_addr_t base, phys_addr_t size) /* called from head.S with MMU off */ asmlinkage void __init __copy_data(void) { - void *from = (void *)(&_sdata); - void *end = (void *)(&_end); + void *from = (void *)(&__data_loc); void *to = (void *)CONFIG_PHYS_RAM_BASE; - size_t sz = (size_t)(end - from + 1); + size_t sz = (size_t)((uintptr_t)(&_end) - (uintptr_t)(&_sdata)); memcpy(to, from, sz); } diff --git a/arch/riscv/net/bpf_jit_comp64.c b/arch/riscv/net/bpf_jit_comp64.c index 2ca345c7b0bf..f2a779c7e225 100644 --- a/arch/riscv/net/bpf_jit_comp64.c +++ b/arch/riscv/net/bpf_jit_comp64.c @@ -460,6 +460,8 @@ static int emit_call(bool fixed, u64 addr, struct rv_jit_context *ctx) #define BPF_FIXUP_REG_MASK GENMASK(31, 27) int rv_bpf_fixup_exception(const struct exception_table_entry *ex, + struct pt_regs *regs); +int rv_bpf_fixup_exception(const struct exception_table_entry *ex, struct pt_regs *regs) { off_t offset = FIELD_GET(BPF_FIXUP_OFFSET_MASK, ex->fixup); diff --git a/arch/s390/include/asm/pci.h b/arch/s390/include/asm/pci.h index 6b3c366af78e..90824be5ce9a 100644 --- a/arch/s390/include/asm/pci.h +++ b/arch/s390/include/asm/pci.h @@ -210,9 +210,11 @@ int zpci_deconfigure_device(struct zpci_dev *zdev); void zpci_device_reserved(struct zpci_dev *zdev); bool zpci_is_device_configured(struct zpci_dev *zdev); +int zpci_hot_reset_device(struct zpci_dev *zdev); int zpci_register_ioat(struct zpci_dev *, u8, u64, u64, u64); int zpci_unregister_ioat(struct zpci_dev *, u8); void zpci_remove_reserved_devices(void); +void zpci_update_fh(struct zpci_dev *zdev, u32 fh); /* CLP */ int clp_setup_writeback_mio(void); @@ -294,8 +296,10 @@ void zpci_debug_exit(void); void zpci_debug_init_device(struct zpci_dev *, const char *); void zpci_debug_exit_device(struct zpci_dev *); -/* Error reporting */ +/* Error handling */ int zpci_report_error(struct pci_dev *, struct zpci_report_error_header *); +int zpci_clear_error_state(struct zpci_dev *zdev); +int zpci_reset_load_store_blocked(struct zpci_dev *zdev); #ifdef CONFIG_NUMA diff --git a/arch/s390/kernel/perf_cpum_cf.c b/arch/s390/kernel/perf_cpum_cf.c index 6f431fa9e4d7..ee8707abdb6a 100644 --- a/arch/s390/kernel/perf_cpum_cf.c +++ b/arch/s390/kernel/perf_cpum_cf.c @@ -687,8 +687,10 @@ static void cpumf_pmu_stop(struct perf_event *event, int flags) false); if (cfdiag_diffctr(cpuhw, event->hw.config_base)) cfdiag_push_sample(event, cpuhw); - } else + } else if (cpuhw->flags & PMU_F_RESERVED) { + /* Only update when PMU not hotplugged off */ hw_perf_event_update(event); + } hwc->state |= PERF_HES_UPTODATE; } } diff --git a/arch/s390/pci/pci.c b/arch/s390/pci/pci.c index 872d772b73d2..2f9b78fa82a5 100644 --- a/arch/s390/pci/pci.c +++ b/arch/s390/pci/pci.c @@ -481,6 +481,34 @@ static void zpci_free_iomap(struct zpci_dev *zdev, int entry) spin_unlock(&zpci_iomap_lock); } +static void zpci_do_update_iomap_fh(struct zpci_dev *zdev, u32 fh) +{ + int bar, idx; + + spin_lock(&zpci_iomap_lock); + for (bar = 0; bar < PCI_STD_NUM_BARS; bar++) { + if (!zdev->bars[bar].size) + continue; + idx = zdev->bars[bar].map_idx; + if (!zpci_iomap_start[idx].count) + continue; + WRITE_ONCE(zpci_iomap_start[idx].fh, zdev->fh); + } + spin_unlock(&zpci_iomap_lock); +} + +void zpci_update_fh(struct zpci_dev *zdev, u32 fh) +{ + if (!fh || zdev->fh == fh) + return; + + zdev->fh = fh; + if (zpci_use_mio(zdev)) + return; + if (zdev->has_resources && zdev_enabled(zdev)) + zpci_do_update_iomap_fh(zdev, fh); +} + static struct resource *__alloc_res(struct zpci_dev *zdev, unsigned long start, unsigned long size, unsigned long flags) { @@ -668,7 +696,7 @@ int zpci_enable_device(struct zpci_dev *zdev) if (clp_enable_fh(zdev, &fh, ZPCI_NR_DMA_SPACES)) rc = -EIO; else - zdev->fh = fh; + zpci_update_fh(zdev, fh); return rc; } @@ -679,14 +707,14 @@ int zpci_disable_device(struct zpci_dev *zdev) cc = clp_disable_fh(zdev, &fh); if (!cc) { - zdev->fh = fh; + zpci_update_fh(zdev, fh); } else if (cc == CLP_RC_SETPCIFN_ALRDY) { pr_info("Disabling PCI function %08x had no effect as it was already disabled\n", zdev->fid); /* Function is already disabled - update handle */ rc = clp_refresh_fh(zdev->fid, &fh); if (!rc) { - zdev->fh = fh; + zpci_update_fh(zdev, fh); rc = -EINVAL; } } else { @@ -696,6 +724,65 @@ int zpci_disable_device(struct zpci_dev *zdev) } /** + * zpci_hot_reset_device - perform a reset of the given zPCI function + * @zdev: the slot which should be reset + * + * Performs a low level reset of the zPCI function. The reset is low level in + * the sense that the zPCI function can be reset without detaching it from the + * common PCI subsystem. The reset may be performed while under control of + * either DMA or IOMMU APIs in which case the existing DMA/IOMMU translation + * table is reinstated at the end of the reset. + * + * After the reset the functions internal state is reset to an initial state + * equivalent to its state during boot when first probing a driver. + * Consequently after reset the PCI function requires re-initialization via the + * common PCI code including re-enabling IRQs via pci_alloc_irq_vectors() + * and enabling the function via e.g.pci_enablde_device_flags().The caller + * must guard against concurrent reset attempts. + * + * In most cases this function should not be called directly but through + * pci_reset_function() or pci_reset_bus() which handle the save/restore and + * locking. + * + * Return: 0 on success and an error value otherwise + */ +int zpci_hot_reset_device(struct zpci_dev *zdev) +{ + int rc; + + zpci_dbg(3, "rst fid:%x, fh:%x\n", zdev->fid, zdev->fh); + if (zdev_enabled(zdev)) { + /* Disables device access, DMAs and IRQs (reset state) */ + rc = zpci_disable_device(zdev); + /* + * Due to a z/VM vs LPAR inconsistency in the error state the + * FH may indicate an enabled device but disable says the + * device is already disabled don't treat it as an error here. + */ + if (rc == -EINVAL) + rc = 0; + if (rc) + return rc; + } + + rc = zpci_enable_device(zdev); + if (rc) + return rc; + + if (zdev->dma_table) + rc = zpci_register_ioat(zdev, 0, zdev->start_dma, zdev->end_dma, + (u64)zdev->dma_table); + else + rc = zpci_dma_init_device(zdev); + if (rc) { + zpci_disable_device(zdev); + return rc; + } + + return 0; +} + +/** * zpci_create_device() - Create a new zpci_dev and add it to the zbus * @fid: Function ID of the device to be created * @fh: Current Function Handle of the device to be created @@ -776,7 +863,7 @@ int zpci_scan_configured_device(struct zpci_dev *zdev, u32 fh) { int rc; - zdev->fh = fh; + zpci_update_fh(zdev, fh); /* the PCI function will be scanned once function 0 appears */ if (!zdev->zbus->bus) return 0; @@ -903,6 +990,59 @@ int zpci_report_error(struct pci_dev *pdev, } EXPORT_SYMBOL(zpci_report_error); +/** + * zpci_clear_error_state() - Clears the zPCI error state of the device + * @zdev: The zdev for which the zPCI error state should be reset + * + * Clear the zPCI error state of the device. If clearing the zPCI error state + * fails the device is left in the error state. In this case it may make sense + * to call zpci_io_perm_failure() on the associated pdev if it exists. + * + * Returns: 0 on success, -EIO otherwise + */ +int zpci_clear_error_state(struct zpci_dev *zdev) +{ + u64 req = ZPCI_CREATE_REQ(zdev->fh, 0, ZPCI_MOD_FC_RESET_ERROR); + struct zpci_fib fib = {0}; + u8 status; + int cc; + + cc = zpci_mod_fc(req, &fib, &status); + if (cc) { + zpci_dbg(3, "ces fid:%x, cc:%d, status:%x\n", zdev->fid, cc, status); + return -EIO; + } + + return 0; +} + +/** + * zpci_reset_load_store_blocked() - Re-enables L/S from error state + * @zdev: The zdev for which to unblock load/store access + * + * Re-enables load/store access for a PCI function in the error state while + * keeping DMA blocked. In this state drivers can poke MMIO space to determine + * if error recovery is possible while catching any rogue DMA access from the + * device. + * + * Returns: 0 on success, -EIO otherwise + */ +int zpci_reset_load_store_blocked(struct zpci_dev *zdev) +{ + u64 req = ZPCI_CREATE_REQ(zdev->fh, 0, ZPCI_MOD_FC_RESET_BLOCK); + struct zpci_fib fib = {0}; + u8 status; + int cc; + + cc = zpci_mod_fc(req, &fib, &status); + if (cc) { + zpci_dbg(3, "rls fid:%x, cc:%d, status:%x\n", zdev->fid, cc, status); + return -EIO; + } + + return 0; +} + static int zpci_mem_init(void) { BUILD_BUG_ON(!is_power_of_2(__alignof__(struct zpci_fmb)) || diff --git a/arch/s390/pci/pci_event.c b/arch/s390/pci/pci_event.c index 6a5bfa9dc1f2..2e3e5b278925 100644 --- a/arch/s390/pci/pci_event.c +++ b/arch/s390/pci/pci_event.c @@ -47,18 +47,223 @@ struct zpci_ccdf_avail { u16 pec; /* PCI event code */ } __packed; +static inline bool ers_result_indicates_abort(pci_ers_result_t ers_res) +{ + switch (ers_res) { + case PCI_ERS_RESULT_CAN_RECOVER: + case PCI_ERS_RESULT_RECOVERED: + case PCI_ERS_RESULT_NEED_RESET: + return false; + default: + return true; + } +} + +static bool is_passed_through(struct zpci_dev *zdev) +{ + return zdev->s390_domain; +} + +static bool is_driver_supported(struct pci_driver *driver) +{ + if (!driver || !driver->err_handler) + return false; + if (!driver->err_handler->error_detected) + return false; + if (!driver->err_handler->slot_reset) + return false; + if (!driver->err_handler->resume) + return false; + return true; +} + +static pci_ers_result_t zpci_event_notify_error_detected(struct pci_dev *pdev, + struct pci_driver *driver) +{ + pci_ers_result_t ers_res = PCI_ERS_RESULT_DISCONNECT; + + ers_res = driver->err_handler->error_detected(pdev, pdev->error_state); + if (ers_result_indicates_abort(ers_res)) + pr_info("%s: Automatic recovery failed after initial reporting\n", pci_name(pdev)); + else if (ers_res == PCI_ERS_RESULT_NEED_RESET) + pr_debug("%s: Driver needs reset to recover\n", pci_name(pdev)); + + return ers_res; +} + +static pci_ers_result_t zpci_event_do_error_state_clear(struct pci_dev *pdev, + struct pci_driver *driver) +{ + pci_ers_result_t ers_res = PCI_ERS_RESULT_DISCONNECT; + struct zpci_dev *zdev = to_zpci(pdev); + int rc; + + pr_info("%s: Unblocking device access for examination\n", pci_name(pdev)); + rc = zpci_reset_load_store_blocked(zdev); + if (rc) { + pr_err("%s: Unblocking device access failed\n", pci_name(pdev)); + /* Let's try a full reset instead */ + return PCI_ERS_RESULT_NEED_RESET; + } + + if (driver->err_handler->mmio_enabled) { + ers_res = driver->err_handler->mmio_enabled(pdev); + if (ers_result_indicates_abort(ers_res)) { + pr_info("%s: Automatic recovery failed after MMIO re-enable\n", + pci_name(pdev)); + return ers_res; + } else if (ers_res == PCI_ERS_RESULT_NEED_RESET) { + pr_debug("%s: Driver needs reset to recover\n", pci_name(pdev)); + return ers_res; + } + } + + pr_debug("%s: Unblocking DMA\n", pci_name(pdev)); + rc = zpci_clear_error_state(zdev); + if (!rc) { + pdev->error_state = pci_channel_io_normal; + } else { + pr_err("%s: Unblocking DMA failed\n", pci_name(pdev)); + /* Let's try a full reset instead */ + return PCI_ERS_RESULT_NEED_RESET; + } + + return ers_res; +} + +static pci_ers_result_t zpci_event_do_reset(struct pci_dev *pdev, + struct pci_driver *driver) +{ + pci_ers_result_t ers_res = PCI_ERS_RESULT_DISCONNECT; + + pr_info("%s: Initiating reset\n", pci_name(pdev)); + if (zpci_hot_reset_device(to_zpci(pdev))) { + pr_err("%s: The reset request failed\n", pci_name(pdev)); + return ers_res; + } + pdev->error_state = pci_channel_io_normal; + ers_res = driver->err_handler->slot_reset(pdev); + if (ers_result_indicates_abort(ers_res)) { + pr_info("%s: Automatic recovery failed after slot reset\n", pci_name(pdev)); + return ers_res; + } + + return ers_res; +} + +/* zpci_event_attempt_error_recovery - Try to recover the given PCI function + * @pdev: PCI function to recover currently in the error state + * + * We follow the scheme outlined in Documentation/PCI/pci-error-recovery.rst. + * With the simplification that recovery always happens per function + * and the platform determines which functions are affected for + * multi-function devices. + */ +static pci_ers_result_t zpci_event_attempt_error_recovery(struct pci_dev *pdev) +{ + pci_ers_result_t ers_res = PCI_ERS_RESULT_DISCONNECT; + struct pci_driver *driver; + + /* + * Ensure that the PCI function is not removed concurrently, no driver + * is unbound or probed and that userspace can't access its + * configuration space while we perform recovery. + */ + pci_dev_lock(pdev); + if (pdev->error_state == pci_channel_io_perm_failure) { + ers_res = PCI_ERS_RESULT_DISCONNECT; + goto out_unlock; + } + pdev->error_state = pci_channel_io_frozen; + + if (is_passed_through(to_zpci(pdev))) { + pr_info("%s: Cannot be recovered in the host because it is a pass-through device\n", + pci_name(pdev)); + goto out_unlock; + } + + driver = to_pci_driver(pdev->dev.driver); + if (!is_driver_supported(driver)) { + if (!driver) + pr_info("%s: Cannot be recovered because no driver is bound to the device\n", + pci_name(pdev)); + else + pr_info("%s: The %s driver bound to the device does not support error recovery\n", + pci_name(pdev), + driver->name); + goto out_unlock; + } + + ers_res = zpci_event_notify_error_detected(pdev, driver); + if (ers_result_indicates_abort(ers_res)) + goto out_unlock; + + if (ers_res == PCI_ERS_RESULT_CAN_RECOVER) { + ers_res = zpci_event_do_error_state_clear(pdev, driver); + if (ers_result_indicates_abort(ers_res)) + goto out_unlock; + } + + if (ers_res == PCI_ERS_RESULT_NEED_RESET) + ers_res = zpci_event_do_reset(pdev, driver); + + if (ers_res != PCI_ERS_RESULT_RECOVERED) { + pr_err("%s: Automatic recovery failed; operator intervention is required\n", + pci_name(pdev)); + goto out_unlock; + } + + pr_info("%s: The device is ready to resume operations\n", pci_name(pdev)); + if (driver->err_handler->resume) + driver->err_handler->resume(pdev); +out_unlock: + pci_dev_unlock(pdev); + + return ers_res; +} + +/* zpci_event_io_failure - Report PCI channel failure state to driver + * @pdev: PCI function for which to report + * @es: PCI channel failure state to report + */ +static void zpci_event_io_failure(struct pci_dev *pdev, pci_channel_state_t es) +{ + struct pci_driver *driver; + + pci_dev_lock(pdev); + pdev->error_state = es; + /** + * While vfio-pci's error_detected callback notifies user-space QEMU + * reacts to this by freezing the guest. In an s390 environment PCI + * errors are rarely fatal so this is overkill. Instead in the future + * we will inject the error event and let the guest recover the device + * itself. + */ + if (is_passed_through(to_zpci(pdev))) + goto out; + driver = to_pci_driver(pdev->dev.driver); + if (driver && driver->err_handler && driver->err_handler->error_detected) + driver->err_handler->error_detected(pdev, pdev->error_state); +out: + pci_dev_unlock(pdev); +} + static void __zpci_event_error(struct zpci_ccdf_err *ccdf) { struct zpci_dev *zdev = get_zdev_by_fid(ccdf->fid); struct pci_dev *pdev = NULL; + pci_ers_result_t ers_res; zpci_dbg(3, "err fid:%x, fh:%x, pec:%x\n", ccdf->fid, ccdf->fh, ccdf->pec); zpci_err("error CCDF:\n"); zpci_err_hex(ccdf, sizeof(*ccdf)); - if (zdev) - pdev = pci_get_slot(zdev->zbus->bus, zdev->devfn); + if (zdev) { + zpci_update_fh(zdev, ccdf->fh); + if (zdev->zbus->bus) + pdev = pci_get_slot(zdev->zbus->bus, zdev->devfn); + } pr_err("%s: Event 0x%x reports an error for PCI function 0x%x\n", pdev ? pci_name(pdev) : "n/a", ccdf->pec, ccdf->fid); @@ -66,7 +271,20 @@ static void __zpci_event_error(struct zpci_ccdf_err *ccdf) if (!pdev) return; - pdev->error_state = pci_channel_io_perm_failure; + switch (ccdf->pec) { + case 0x003a: /* Service Action or Error Recovery Successful */ + ers_res = zpci_event_attempt_error_recovery(pdev); + if (ers_res != PCI_ERS_RESULT_RECOVERED) + zpci_event_io_failure(pdev, pci_channel_io_perm_failure); + break; + default: + /* + * Mark as frozen not permanently failed because the device + * could be subsequently recovered by the platform. + */ + zpci_event_io_failure(pdev, pci_channel_io_frozen); + break; + } pci_dev_put(pdev); } @@ -78,7 +296,7 @@ void zpci_event_error(void *data) static void zpci_event_hard_deconfigured(struct zpci_dev *zdev, u32 fh) { - zdev->fh = fh; + zpci_update_fh(zdev, fh); /* Give the driver a hint that the function is * already unusable. */ @@ -121,7 +339,7 @@ static void __zpci_event_availability(struct zpci_ccdf_avail *ccdf) if (!zdev) zpci_create_device(ccdf->fid, ccdf->fh, ZPCI_FN_STATE_STANDBY); else - zdev->fh = ccdf->fh; + zpci_update_fh(zdev, ccdf->fh); break; case 0x0303: /* Deconfiguration requested */ if (zdev) { @@ -130,7 +348,7 @@ static void __zpci_event_availability(struct zpci_ccdf_avail *ccdf) */ if (zdev->state != ZPCI_FN_STATE_CONFIGURED) break; - zdev->fh = ccdf->fh; + zpci_update_fh(zdev, ccdf->fh); zpci_deconfigure_device(zdev); } break; diff --git a/arch/s390/pci/pci_insn.c b/arch/s390/pci/pci_insn.c index 2e43996159f0..28d863aaafea 100644 --- a/arch/s390/pci/pci_insn.c +++ b/arch/s390/pci/pci_insn.c @@ -163,7 +163,7 @@ static inline int zpci_load_fh(u64 *data, const volatile void __iomem *addr, unsigned long len) { struct zpci_iomap_entry *entry = &zpci_iomap_start[ZPCI_IDX(addr)]; - u64 req = ZPCI_CREATE_REQ(entry->fh, entry->bar, len); + u64 req = ZPCI_CREATE_REQ(READ_ONCE(entry->fh), entry->bar, len); return __zpci_load(data, req, ZPCI_OFFSET(addr)); } @@ -244,7 +244,7 @@ static inline int zpci_store_fh(const volatile void __iomem *addr, u64 data, unsigned long len) { struct zpci_iomap_entry *entry = &zpci_iomap_start[ZPCI_IDX(addr)]; - u64 req = ZPCI_CREATE_REQ(entry->fh, entry->bar, len); + u64 req = ZPCI_CREATE_REQ(READ_ONCE(entry->fh), entry->bar, len); return __zpci_store(data, req, ZPCI_OFFSET(addr)); } diff --git a/arch/s390/pci/pci_irq.c b/arch/s390/pci/pci_irq.c index 3823e159bf74..954bb7a83124 100644 --- a/arch/s390/pci/pci_irq.c +++ b/arch/s390/pci/pci_irq.c @@ -387,6 +387,15 @@ void arch_teardown_msi_irqs(struct pci_dev *pdev) airq_iv_free(zpci_ibv[0], zdev->msi_first_bit, zdev->msi_nr_irqs); } +void arch_restore_msi_irqs(struct pci_dev *pdev) +{ + struct zpci_dev *zdev = to_zpci(pdev); + + if (!zdev->irqs_registered) + zpci_set_irq(zdev); + default_restore_msi_irqs(pdev); +} + static struct airq_struct zpci_airq = { .handler = zpci_floating_irq_handler, .isc = PCI_ISC, diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index 603964408d2d..42cf01ecdd13 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -3048,8 +3048,10 @@ intel_vlbr_constraints(struct perf_event *event) { struct event_constraint *c = &vlbr_constraint; - if (unlikely(constraint_match(c, event->hw.config))) + if (unlikely(constraint_match(c, event->hw.config))) { + event->hw.flags |= c->flags; return c; + } return NULL; } diff --git a/arch/x86/events/intel/lbr.c b/arch/x86/events/intel/lbr.c index 6b72e9b55c69..8043213b75a5 100644 --- a/arch/x86/events/intel/lbr.c +++ b/arch/x86/events/intel/lbr.c @@ -265,6 +265,8 @@ void intel_pmu_lbr_reset(void) cpuc->last_task_ctx = NULL; cpuc->last_log_id = 0; + if (!static_cpu_has(X86_FEATURE_ARCH_LBR) && cpuc->lbr_select) + wrmsrl(MSR_LBR_SELECT, 0); } /* diff --git a/arch/x86/include/asm/fpu/xcr.h b/arch/x86/include/asm/fpu/xcr.h index 79f95d3787e2..9656a5bc6fea 100644 --- a/arch/x86/include/asm/fpu/xcr.h +++ b/arch/x86/include/asm/fpu/xcr.h @@ -3,6 +3,7 @@ #define _ASM_X86_FPU_XCR_H #define XCR_XFEATURE_ENABLED_MASK 0x00000000 +#define XCR_XFEATURE_IN_USE_MASK 0x00000001 static inline u64 xgetbv(u32 index) { @@ -20,4 +21,15 @@ static inline void xsetbv(u32 index, u64 value) asm volatile("xsetbv" :: "a" (eax), "d" (edx), "c" (index)); } +/* + * Return a mask of xfeatures which are currently being tracked + * by the processor as being in the initial configuration. + * + * Callers should check X86_FEATURE_XGETBV1. + */ +static inline u64 xfeatures_in_use(void) +{ + return xgetbv(XCR_XFEATURE_IN_USE_MASK); +} + #endif /* _ASM_X86_FPU_XCR_H */ diff --git a/arch/x86/include/asm/fpu/xstate.h b/arch/x86/include/asm/fpu/xstate.h index 0f8b90ab18c9..cd3dd170e23a 100644 --- a/arch/x86/include/asm/fpu/xstate.h +++ b/arch/x86/include/asm/fpu/xstate.h @@ -92,6 +92,13 @@ #define XFEATURE_MASK_FPSTATE (XFEATURE_MASK_USER_RESTORE | \ XFEATURE_MASK_SUPERVISOR_SUPPORTED) +/* + * Features in this mask have space allocated in the signal frame, but may not + * have that space initialized when the feature is in its init state. + */ +#define XFEATURE_MASK_SIGFRAME_INITOPT (XFEATURE_MASK_XTILE | \ + XFEATURE_MASK_USER_DYNAMIC) + extern u64 xstate_fx_sw_bytes[USER_XSTATE_FX_SW_WORDS]; extern void __init update_regset_xstate_info(unsigned int size, diff --git a/arch/x86/include/asm/intel-family.h b/arch/x86/include/asm/intel-family.h index 27158436f322..5a0bcf8b78d7 100644 --- a/arch/x86/include/asm/intel-family.h +++ b/arch/x86/include/asm/intel-family.h @@ -108,6 +108,8 @@ #define INTEL_FAM6_ALDERLAKE 0x97 /* Golden Cove / Gracemont */ #define INTEL_FAM6_ALDERLAKE_L 0x9A /* Golden Cove / Gracemont */ +#define INTEL_FAM6_RAPTOR_LAKE 0xB7 + /* "Small Core" Processors (Atom) */ #define INTEL_FAM6_ATOM_BONNELL 0x1C /* Diamondville, Pineview */ diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 2acf37cc1991..e5d8700319cc 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -38,7 +38,6 @@ #define __KVM_HAVE_ARCH_VCPU_DEBUGFS #define KVM_MAX_VCPUS 1024 -#define KVM_SOFT_MAX_VCPUS 710 /* * In x86, the VCPU ID corresponds to the APIC ID, and APIC IDs @@ -725,6 +724,7 @@ struct kvm_vcpu_arch { int cpuid_nent; struct kvm_cpuid_entry2 *cpuid_entries; + u32 kvm_cpuid_base; u64 reserved_gpa_bits; int maxphyaddr; @@ -748,7 +748,7 @@ struct kvm_vcpu_arch { u8 preempted; u64 msr_val; u64 last_steal; - struct gfn_to_pfn_cache cache; + struct gfn_to_hva_cache cache; } st; u64 l1_tsc_offset; @@ -1034,6 +1034,7 @@ struct kvm_x86_msr_filter { #define APICV_INHIBIT_REASON_IRQWIN 3 #define APICV_INHIBIT_REASON_PIT_REINJ 4 #define APICV_INHIBIT_REASON_X2APIC 5 +#define APICV_INHIBIT_REASON_BLOCKIRQ 6 struct kvm_arch { unsigned long n_used_mmu_pages; @@ -1476,6 +1477,7 @@ struct kvm_x86_ops { int (*mem_enc_reg_region)(struct kvm *kvm, struct kvm_enc_region *argp); int (*mem_enc_unreg_region)(struct kvm *kvm, struct kvm_enc_region *argp); int (*vm_copy_enc_context_from)(struct kvm *kvm, unsigned int source_fd); + int (*vm_move_enc_context_from)(struct kvm *kvm, unsigned int source_fd); int (*get_msr_feature)(struct kvm_msr_entry *entry); diff --git a/arch/x86/include/asm/kvm_para.h b/arch/x86/include/asm/kvm_para.h index 69299878b200..56935ebb1dfe 100644 --- a/arch/x86/include/asm/kvm_para.h +++ b/arch/x86/include/asm/kvm_para.h @@ -83,6 +83,18 @@ static inline long kvm_hypercall4(unsigned int nr, unsigned long p1, return ret; } +static inline long kvm_sev_hypercall3(unsigned int nr, unsigned long p1, + unsigned long p2, unsigned long p3) +{ + long ret; + + asm volatile("vmmcall" + : "=a"(ret) + : "a"(nr), "b"(p1), "c"(p2), "d"(p3) + : "memory"); + return ret; +} + #ifdef CONFIG_KVM_GUEST void kvmclock_init(void); void kvmclock_disable(void); diff --git a/arch/x86/include/asm/mem_encrypt.h b/arch/x86/include/asm/mem_encrypt.h index 2d4f5c17d79c..e2c6f433ed10 100644 --- a/arch/x86/include/asm/mem_encrypt.h +++ b/arch/x86/include/asm/mem_encrypt.h @@ -44,6 +44,8 @@ void __init sme_enable(struct boot_params *bp); int __init early_set_memory_decrypted(unsigned long vaddr, unsigned long size); int __init early_set_memory_encrypted(unsigned long vaddr, unsigned long size); +void __init early_set_mem_enc_dec_hypercall(unsigned long vaddr, int npages, + bool enc); void __init mem_encrypt_free_decrypted_mem(void); @@ -78,6 +80,8 @@ static inline int __init early_set_memory_decrypted(unsigned long vaddr, unsigned long size) { return 0; } static inline int __init early_set_memory_encrypted(unsigned long vaddr, unsigned long size) { return 0; } +static inline void __init +early_set_mem_enc_dec_hypercall(unsigned long vaddr, int npages, bool enc) {} static inline void mem_encrypt_free_decrypted_mem(void) { } diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h index cebec95a7124..21c4a694ca11 100644 --- a/arch/x86/include/asm/paravirt.h +++ b/arch/x86/include/asm/paravirt.h @@ -97,6 +97,12 @@ static inline void paravirt_arch_exit_mmap(struct mm_struct *mm) PVOP_VCALL1(mmu.exit_mmap, mm); } +static inline void notify_page_enc_status_changed(unsigned long pfn, + int npages, bool enc) +{ + PVOP_VCALL3(mmu.notify_page_enc_status_changed, pfn, npages, enc); +} + #ifdef CONFIG_PARAVIRT_XXL static inline void load_sp0(unsigned long sp0) { diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h index fc1151e77569..a69012e1903f 100644 --- a/arch/x86/include/asm/paravirt_types.h +++ b/arch/x86/include/asm/paravirt_types.h @@ -168,6 +168,7 @@ struct pv_mmu_ops { /* Hook for intercepting the destruction of an mm_struct. */ void (*exit_mmap)(struct mm_struct *mm); + void (*notify_page_enc_status_changed)(unsigned long pfn, int npages, bool enc); #ifdef CONFIG_PARAVIRT_XXL struct paravirt_callee_save read_cr2; diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index 191878a65c61..355d38c0cf60 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -806,11 +806,14 @@ static inline u32 amd_get_nodes_per_socket(void) { return 0; } static inline u32 amd_get_highest_perf(void) { return 0; } #endif +#define for_each_possible_hypervisor_cpuid_base(function) \ + for (function = 0x40000000; function < 0x40010000; function += 0x100) + static inline uint32_t hypervisor_cpuid_base(const char *sig, uint32_t leaves) { uint32_t base, eax, signature[3]; - for (base = 0x40000000; base < 0x40010000; base += 0x100) { + for_each_possible_hypervisor_cpuid_base(base) { cpuid(base, &eax, &signature[0], &signature[1], &signature[2]); if (!memcmp(sig, signature, 12) && diff --git a/arch/x86/include/asm/set_memory.h b/arch/x86/include/asm/set_memory.h index 43fa081a1adb..872617542bbc 100644 --- a/arch/x86/include/asm/set_memory.h +++ b/arch/x86/include/asm/set_memory.h @@ -83,6 +83,7 @@ int set_pages_rw(struct page *page, int numpages); int set_direct_map_invalid_noflush(struct page *page); int set_direct_map_default_noflush(struct page *page); bool kernel_page_present(struct page *page); +void notify_range_enc_status_changed(unsigned long vaddr, int npages, bool enc); extern int kernel_set_to_readonly; diff --git a/arch/x86/include/asm/smp.h b/arch/x86/include/asm/smp.h index 08b0e90623ad..81a0211a372d 100644 --- a/arch/x86/include/asm/smp.h +++ b/arch/x86/include/asm/smp.h @@ -126,6 +126,7 @@ static inline void arch_send_call_function_ipi_mask(const struct cpumask *mask) void cpu_disable_common(void); void native_smp_prepare_boot_cpu(void); +void smp_prepare_cpus_common(void); void native_smp_prepare_cpus(unsigned int max_cpus); void calculate_max_logical_packages(void); void native_smp_cpus_done(unsigned int max_cpus); diff --git a/arch/x86/include/uapi/asm/kvm_para.h b/arch/x86/include/uapi/asm/kvm_para.h index 5146bbab84d4..6e64b27b2c1e 100644 --- a/arch/x86/include/uapi/asm/kvm_para.h +++ b/arch/x86/include/uapi/asm/kvm_para.h @@ -8,6 +8,7 @@ * should be used to determine that a VM is running under KVM. */ #define KVM_CPUID_SIGNATURE 0x40000000 +#define KVM_SIGNATURE "KVMKVMKVM\0\0\0" /* This CPUID returns two feature bitmaps in eax, edx. Before enabling * a particular paravirtualization, the appropriate feature bit should diff --git a/arch/x86/kernel/cpu/cpuid-deps.c b/arch/x86/kernel/cpu/cpuid-deps.c index cb2fdd130aae..c881bcafba7d 100644 --- a/arch/x86/kernel/cpu/cpuid-deps.c +++ b/arch/x86/kernel/cpu/cpuid-deps.c @@ -76,6 +76,7 @@ static const struct cpuid_dep cpuid_deps[] = { { X86_FEATURE_SGX1, X86_FEATURE_SGX }, { X86_FEATURE_SGX2, X86_FEATURE_SGX1 }, { X86_FEATURE_XFD, X86_FEATURE_XSAVES }, + { X86_FEATURE_XFD, X86_FEATURE_XGETBV1 }, { X86_FEATURE_AMX_TILE, X86_FEATURE_XFD }, {} }; diff --git a/arch/x86/kernel/cpu/mce/intel.c b/arch/x86/kernel/cpu/mce/intel.c index acfd5d9f93c6..bb9a46a804bf 100644 --- a/arch/x86/kernel/cpu/mce/intel.c +++ b/arch/x86/kernel/cpu/mce/intel.c @@ -547,12 +547,13 @@ bool intel_filter_mce(struct mce *m) { struct cpuinfo_x86 *c = &boot_cpu_data; - /* MCE errata HSD131, HSM142, HSW131, BDM48, and HSM142 */ + /* MCE errata HSD131, HSM142, HSW131, BDM48, HSM142 and SKX37 */ if ((c->x86 == 6) && ((c->x86_model == INTEL_FAM6_HASWELL) || (c->x86_model == INTEL_FAM6_HASWELL_L) || (c->x86_model == INTEL_FAM6_BROADWELL) || - (c->x86_model == INTEL_FAM6_HASWELL_G)) && + (c->x86_model == INTEL_FAM6_HASWELL_G) || + (c->x86_model == INTEL_FAM6_SKYLAKE_X)) && (m->bank == 0) && ((m->status & 0xa0000000ffffffff) == 0x80000000000f0005)) return true; diff --git a/arch/x86/kernel/fpu/xstate.h b/arch/x86/kernel/fpu/xstate.h index e18210dff88c..86ea7c0fa2f6 100644 --- a/arch/x86/kernel/fpu/xstate.h +++ b/arch/x86/kernel/fpu/xstate.h @@ -4,6 +4,7 @@ #include <asm/cpufeature.h> #include <asm/fpu/xstate.h> +#include <asm/fpu/xcr.h> #ifdef CONFIG_X86_64 DECLARE_PER_CPU(u64, xfd_state); @@ -199,6 +200,32 @@ static inline void os_xrstor_supervisor(struct fpstate *fpstate) } /* + * XSAVE itself always writes all requested xfeatures. Removing features + * from the request bitmap reduces the features which are written. + * Generate a mask of features which must be written to a sigframe. The + * unset features can be optimized away and not written. + * + * This optimization is user-visible. Only use for states where + * uninitialized sigframe contents are tolerable, like dynamic features. + * + * Users of buffers produced with this optimization must check XSTATE_BV + * to determine which features have been optimized out. + */ +static inline u64 xfeatures_need_sigframe_write(void) +{ + u64 xfeaures_to_write; + + /* In-use features must be written: */ + xfeaures_to_write = xfeatures_in_use(); + + /* Also write all non-optimizable sigframe features: */ + xfeaures_to_write |= XFEATURE_MASK_USER_SUPPORTED & + ~XFEATURE_MASK_SIGFRAME_INITOPT; + + return xfeaures_to_write; +} + +/* * Save xstate to user space xsave area. * * We don't use modified optimization because xrstor/xrstors might track @@ -220,10 +247,16 @@ static inline int xsave_to_user_sigframe(struct xregs_state __user *buf) */ struct fpstate *fpstate = current->thread.fpu.fpstate; u64 mask = fpstate->user_xfeatures; - u32 lmask = mask; - u32 hmask = mask >> 32; + u32 lmask; + u32 hmask; int err; + /* Optimize away writing unnecessary xfeatures: */ + if (fpu_state_size_dynamic()) + mask &= xfeatures_need_sigframe_write(); + + lmask = mask; + hmask = mask >> 32; xfd_validate_state(fpstate, mask, false); stac(); diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c index 8863d1941f1b..59abbdad7729 100644 --- a/arch/x86/kernel/kvm.c +++ b/arch/x86/kernel/kvm.c @@ -28,6 +28,7 @@ #include <linux/swait.h> #include <linux/syscore_ops.h> #include <linux/cc_platform.h> +#include <linux/efi.h> #include <asm/timer.h> #include <asm/cpu.h> #include <asm/traps.h> @@ -41,6 +42,7 @@ #include <asm/ptrace.h> #include <asm/reboot.h> #include <asm/svm.h> +#include <asm/e820/api.h> DEFINE_STATIC_KEY_FALSE(kvm_async_pf_enabled); @@ -434,6 +436,8 @@ static void kvm_guest_cpu_offline(bool shutdown) kvm_disable_steal_time(); if (kvm_para_has_feature(KVM_FEATURE_PV_EOI)) wrmsrl(MSR_KVM_PV_EOI_EN, 0); + if (kvm_para_has_feature(KVM_FEATURE_MIGRATION_CONTROL)) + wrmsrl(MSR_KVM_MIGRATION_CONTROL, 0); kvm_pv_disable_apf(); if (!shutdown) apf_task_wake_all(); @@ -548,6 +552,55 @@ static void kvm_send_ipi_mask_allbutself(const struct cpumask *mask, int vector) __send_ipi_mask(local_mask, vector); } +static int __init setup_efi_kvm_sev_migration(void) +{ + efi_char16_t efi_sev_live_migration_enabled[] = L"SevLiveMigrationEnabled"; + efi_guid_t efi_variable_guid = AMD_SEV_MEM_ENCRYPT_GUID; + efi_status_t status; + unsigned long size; + bool enabled; + + if (!cc_platform_has(CC_ATTR_GUEST_MEM_ENCRYPT) || + !kvm_para_has_feature(KVM_FEATURE_MIGRATION_CONTROL)) + return 0; + + if (!efi_enabled(EFI_BOOT)) + return 0; + + if (!efi_enabled(EFI_RUNTIME_SERVICES)) { + pr_info("%s : EFI runtime services are not enabled\n", __func__); + return 0; + } + + size = sizeof(enabled); + + /* Get variable contents into buffer */ + status = efi.get_variable(efi_sev_live_migration_enabled, + &efi_variable_guid, NULL, &size, &enabled); + + if (status == EFI_NOT_FOUND) { + pr_info("%s : EFI live migration variable not found\n", __func__); + return 0; + } + + if (status != EFI_SUCCESS) { + pr_info("%s : EFI variable retrieval failed\n", __func__); + return 0; + } + + if (enabled == 0) { + pr_info("%s: live migration disabled in EFI\n", __func__); + return 0; + } + + pr_info("%s : live migration enabled in EFI\n", __func__); + wrmsrl(MSR_KVM_MIGRATION_CONTROL, KVM_MIGRATION_READY); + + return 1; +} + +late_initcall(setup_efi_kvm_sev_migration); + /* * Set the IPI entry points */ @@ -756,7 +809,7 @@ static noinline uint32_t __kvm_cpuid_base(void) return 0; /* So we don't blow up on old processors */ if (boot_cpu_has(X86_FEATURE_HYPERVISOR)) - return hypervisor_cpuid_base("KVMKVMKVM\0\0\0", 0); + return hypervisor_cpuid_base(KVM_SIGNATURE, 0); return 0; } @@ -806,8 +859,62 @@ static bool __init kvm_msi_ext_dest_id(void) return kvm_para_has_feature(KVM_FEATURE_MSI_EXT_DEST_ID); } +static void kvm_sev_hc_page_enc_status(unsigned long pfn, int npages, bool enc) +{ + kvm_sev_hypercall3(KVM_HC_MAP_GPA_RANGE, pfn << PAGE_SHIFT, npages, + KVM_MAP_GPA_RANGE_ENC_STAT(enc) | KVM_MAP_GPA_RANGE_PAGE_SZ_4K); +} + static void __init kvm_init_platform(void) { + if (cc_platform_has(CC_ATTR_GUEST_MEM_ENCRYPT) && + kvm_para_has_feature(KVM_FEATURE_MIGRATION_CONTROL)) { + unsigned long nr_pages; + int i; + + pv_ops.mmu.notify_page_enc_status_changed = + kvm_sev_hc_page_enc_status; + + /* + * Reset the host's shared pages list related to kernel + * specific page encryption status settings before we load a + * new kernel by kexec. Reset the page encryption status + * during early boot intead of just before kexec to avoid SMP + * races during kvm_pv_guest_cpu_reboot(). + * NOTE: We cannot reset the complete shared pages list + * here as we need to retain the UEFI/OVMF firmware + * specific settings. + */ + + for (i = 0; i < e820_table->nr_entries; i++) { + struct e820_entry *entry = &e820_table->entries[i]; + + if (entry->type != E820_TYPE_RAM) + continue; + + nr_pages = DIV_ROUND_UP(entry->size, PAGE_SIZE); + + kvm_sev_hypercall3(KVM_HC_MAP_GPA_RANGE, entry->addr, + nr_pages, + KVM_MAP_GPA_RANGE_ENCRYPTED | KVM_MAP_GPA_RANGE_PAGE_SZ_4K); + } + + /* + * Ensure that _bss_decrypted section is marked as decrypted in the + * shared pages list. + */ + nr_pages = DIV_ROUND_UP(__end_bss_decrypted - __start_bss_decrypted, + PAGE_SIZE); + early_set_mem_enc_dec_hypercall((unsigned long)__start_bss_decrypted, + nr_pages, 0); + + /* + * If not booted using EFI, enable Live migration support. + */ + if (!efi_enabled(EFI_BOOT)) + wrmsrl(MSR_KVM_MIGRATION_CONTROL, + KVM_MIGRATION_READY); + } kvmclock_init(); x86_platform.apic_post_init = kvm_apic_init; } diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c index 7157c2df3bc2..7f7636aac620 100644 --- a/arch/x86/kernel/paravirt.c +++ b/arch/x86/kernel/paravirt.c @@ -337,6 +337,7 @@ struct paravirt_patch_template pv_ops = { (void (*)(struct mmu_gather *, void *))tlb_remove_page, .mmu.exit_mmap = paravirt_nop, + .mmu.notify_page_enc_status_changed = paravirt_nop, #ifdef CONFIG_PARAVIRT_XXL .mmu.read_cr2 = __PV_IS_CALLEE_SAVE(pv_native_read_cr2), diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index 8241927addff..ac2909f0cab3 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -1350,12 +1350,7 @@ static void __init smp_get_logical_apicid(void) cpu0_logical_apicid = GET_APIC_LOGICAL_ID(apic_read(APIC_LDR)); } -/* - * Prepare for SMP bootup. - * @max_cpus: configured maximum number of CPUs, It is a legacy parameter - * for common interface support. - */ -void __init native_smp_prepare_cpus(unsigned int max_cpus) +void __init smp_prepare_cpus_common(void) { unsigned int i; @@ -1386,6 +1381,17 @@ void __init native_smp_prepare_cpus(unsigned int max_cpus) set_sched_topology(x86_topology); set_cpu_sibling_map(0); +} + +/* + * Prepare for SMP bootup. + * @max_cpus: configured maximum number of CPUs, It is a legacy parameter + * for common interface support. + */ +void __init native_smp_prepare_cpus(unsigned int max_cpus) +{ + smp_prepare_cpus_common(); + init_freq_invariance(false, false); smp_sanity_check(); diff --git a/arch/x86/kernel/vm86_32.c b/arch/x86/kernel/vm86_32.c index f14f69d7aa3c..cce1c89cb7df 100644 --- a/arch/x86/kernel/vm86_32.c +++ b/arch/x86/kernel/vm86_32.c @@ -106,7 +106,7 @@ void save_v86_state(struct kernel_vm86_regs *regs, int retval) */ local_irq_enable(); - BUG_ON(!vm86 || !vm86->user_vm86); + BUG_ON(!vm86); set_flags(regs->pt.flags, VEFLAGS, X86_EFLAGS_VIF | vm86->veflags_mask); user = vm86->user_vm86; diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index 2d70edb0f323..e19dabf1848b 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -99,11 +99,45 @@ static int kvm_check_cpuid(struct kvm_cpuid_entry2 *entries, int nent) return 0; } -void kvm_update_pv_runtime(struct kvm_vcpu *vcpu) +static void kvm_update_kvm_cpuid_base(struct kvm_vcpu *vcpu) { - struct kvm_cpuid_entry2 *best; + u32 function; + struct kvm_cpuid_entry2 *entry; + + vcpu->arch.kvm_cpuid_base = 0; + + for_each_possible_hypervisor_cpuid_base(function) { + entry = kvm_find_cpuid_entry(vcpu, function, 0); - best = kvm_find_cpuid_entry(vcpu, KVM_CPUID_FEATURES, 0); + if (entry) { + u32 signature[3]; + + signature[0] = entry->ebx; + signature[1] = entry->ecx; + signature[2] = entry->edx; + + BUILD_BUG_ON(sizeof(signature) > sizeof(KVM_SIGNATURE)); + if (!memcmp(signature, KVM_SIGNATURE, sizeof(signature))) { + vcpu->arch.kvm_cpuid_base = function; + break; + } + } + } +} + +struct kvm_cpuid_entry2 *kvm_find_kvm_cpuid_features(struct kvm_vcpu *vcpu) +{ + u32 base = vcpu->arch.kvm_cpuid_base; + + if (!base) + return NULL; + + return kvm_find_cpuid_entry(vcpu, base | KVM_CPUID_FEATURES, 0); +} + +void kvm_update_pv_runtime(struct kvm_vcpu *vcpu) +{ + struct kvm_cpuid_entry2 *best = kvm_find_kvm_cpuid_features(vcpu); /* * save the feature bitmap to avoid cpuid lookup for every PV @@ -142,7 +176,7 @@ void kvm_update_cpuid_runtime(struct kvm_vcpu *vcpu) cpuid_entry_has(best, X86_FEATURE_XSAVEC))) best->ebx = xstate_required_size(vcpu->arch.xcr0, true); - best = kvm_find_cpuid_entry(vcpu, KVM_CPUID_FEATURES, 0); + best = kvm_find_kvm_cpuid_features(vcpu); if (kvm_hlt_in_guest(vcpu->kvm) && best && (best->eax & (1 << KVM_FEATURE_PV_UNHALT))) best->eax &= ~(1 << KVM_FEATURE_PV_UNHALT); @@ -239,6 +273,26 @@ u64 kvm_vcpu_reserved_gpa_bits_raw(struct kvm_vcpu *vcpu) return rsvd_bits(cpuid_maxphyaddr(vcpu), 63); } +static int kvm_set_cpuid(struct kvm_vcpu *vcpu, struct kvm_cpuid_entry2 *e2, + int nent) +{ + int r; + + r = kvm_check_cpuid(e2, nent); + if (r) + return r; + + kvfree(vcpu->arch.cpuid_entries); + vcpu->arch.cpuid_entries = e2; + vcpu->arch.cpuid_nent = nent; + + kvm_update_kvm_cpuid_base(vcpu); + kvm_update_cpuid_runtime(vcpu); + kvm_vcpu_after_set_cpuid(vcpu); + + return 0; +} + /* when an old userspace process fills a new kernel module */ int kvm_vcpu_ioctl_set_cpuid(struct kvm_vcpu *vcpu, struct kvm_cpuid *cpuid, @@ -275,18 +329,9 @@ int kvm_vcpu_ioctl_set_cpuid(struct kvm_vcpu *vcpu, e2[i].padding[2] = 0; } - r = kvm_check_cpuid(e2, cpuid->nent); - if (r) { + r = kvm_set_cpuid(vcpu, e2, cpuid->nent); + if (r) kvfree(e2); - goto out_free_cpuid; - } - - kvfree(vcpu->arch.cpuid_entries); - vcpu->arch.cpuid_entries = e2; - vcpu->arch.cpuid_nent = cpuid->nent; - - kvm_update_cpuid_runtime(vcpu); - kvm_vcpu_after_set_cpuid(vcpu); out_free_cpuid: kvfree(e); @@ -310,20 +355,11 @@ int kvm_vcpu_ioctl_set_cpuid2(struct kvm_vcpu *vcpu, return PTR_ERR(e2); } - r = kvm_check_cpuid(e2, cpuid->nent); - if (r) { + r = kvm_set_cpuid(vcpu, e2, cpuid->nent); + if (r) kvfree(e2); - return r; - } - kvfree(vcpu->arch.cpuid_entries); - vcpu->arch.cpuid_entries = e2; - vcpu->arch.cpuid_nent = cpuid->nent; - - kvm_update_cpuid_runtime(vcpu); - kvm_vcpu_after_set_cpuid(vcpu); - - return 0; + return r; } int kvm_vcpu_ioctl_get_cpuid2(struct kvm_vcpu *vcpu, @@ -871,8 +907,7 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function) } break; case KVM_CPUID_SIGNATURE: { - static const char signature[12] = "KVMKVMKVM\0\0"; - const u32 *sigptr = (const u32 *)signature; + const u32 *sigptr = (const u32 *)KVM_SIGNATURE; entry->eax = KVM_CPUID_FEATURES; entry->ebx = sigptr[0]; entry->ecx = sigptr[1]; diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c index 4f15c0165c05..4a555f32885a 100644 --- a/arch/x86/kvm/hyperv.c +++ b/arch/x86/kvm/hyperv.c @@ -1472,7 +1472,7 @@ static int kvm_hv_set_msr(struct kvm_vcpu *vcpu, u32 msr, u64 data, bool host) if (!(data & HV_X64_MSR_VP_ASSIST_PAGE_ENABLE)) { hv_vcpu->hv_vapic = data; - if (kvm_lapic_enable_pv_eoi(vcpu, 0, 0)) + if (kvm_lapic_set_pv_eoi(vcpu, 0, 0)) return 1; break; } @@ -1490,7 +1490,7 @@ static int kvm_hv_set_msr(struct kvm_vcpu *vcpu, u32 msr, u64 data, bool host) return 1; hv_vcpu->hv_vapic = data; kvm_vcpu_mark_page_dirty(vcpu, gfn); - if (kvm_lapic_enable_pv_eoi(vcpu, + if (kvm_lapic_set_pv_eoi(vcpu, gfn_to_gpa(gfn) | KVM_MSR_ENABLED, sizeof(struct hv_vp_assist_page))) return 1; diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index d6ac32f3f650..759952dd1222 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -2856,25 +2856,30 @@ int kvm_hv_vapic_msr_read(struct kvm_vcpu *vcpu, u32 reg, u64 *data) return 0; } -int kvm_lapic_enable_pv_eoi(struct kvm_vcpu *vcpu, u64 data, unsigned long len) +int kvm_lapic_set_pv_eoi(struct kvm_vcpu *vcpu, u64 data, unsigned long len) { u64 addr = data & ~KVM_MSR_ENABLED; struct gfn_to_hva_cache *ghc = &vcpu->arch.pv_eoi.data; unsigned long new_len; + int ret; if (!IS_ALIGNED(addr, 4)) return 1; - vcpu->arch.pv_eoi.msr_val = data; - if (!pv_eoi_enabled(vcpu)) - return 0; + if (data & KVM_MSR_ENABLED) { + if (addr == ghc->gpa && len <= ghc->len) + new_len = ghc->len; + else + new_len = len; - if (addr == ghc->gpa && len <= ghc->len) - new_len = ghc->len; - else - new_len = len; + ret = kvm_gfn_to_hva_cache_init(vcpu->kvm, ghc, addr, new_len); + if (ret) + return ret; + } + + vcpu->arch.pv_eoi.msr_val = data; - return kvm_gfn_to_hva_cache_init(vcpu->kvm, ghc, addr, new_len); + return 0; } int kvm_apic_accept_events(struct kvm_vcpu *vcpu) diff --git a/arch/x86/kvm/lapic.h b/arch/x86/kvm/lapic.h index d7c25d0c1354..2b44e533fc8d 100644 --- a/arch/x86/kvm/lapic.h +++ b/arch/x86/kvm/lapic.h @@ -127,7 +127,7 @@ int kvm_x2apic_msr_read(struct kvm_vcpu *vcpu, u32 msr, u64 *data); int kvm_hv_vapic_msr_write(struct kvm_vcpu *vcpu, u32 msr, u64 data); int kvm_hv_vapic_msr_read(struct kvm_vcpu *vcpu, u32 msr, u64 *data); -int kvm_lapic_enable_pv_eoi(struct kvm_vcpu *vcpu, u64 data, unsigned long len); +int kvm_lapic_set_pv_eoi(struct kvm_vcpu *vcpu, u64 data, unsigned long len); void kvm_lapic_exit(void); #define VEC_POS(v) ((v) & (32 - 1)) diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index 323b5057d08f..33794379949e 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -3191,17 +3191,17 @@ static int fast_page_fault(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault) new_spte |= PT_WRITABLE_MASK; /* - * Do not fix write-permission on the large spte. Since - * we only dirty the first page into the dirty-bitmap in + * Do not fix write-permission on the large spte when + * dirty logging is enabled. Since we only dirty the + * first page into the dirty-bitmap in * fast_pf_fix_direct_spte(), other pages are missed * if its slot has dirty logging enabled. * * Instead, we let the slow page fault path create a * normal spte to fix the access. - * - * See the comments in kvm_arch_commit_memory_region(). */ - if (sp->role.level > PG_LEVEL_4K) + if (sp->role.level > PG_LEVEL_4K && + kvm_slot_dirty_track_enabled(fault->slot)) break; } diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c index 7c5dd83e52de..a54c3491af42 100644 --- a/arch/x86/kvm/mmu/tdp_mmu.c +++ b/arch/x86/kvm/mmu/tdp_mmu.c @@ -897,7 +897,7 @@ static int tdp_mmu_map_handle_target_level(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault, struct tdp_iter *iter) { - struct kvm_mmu_page *sp = sptep_to_sp(iter->sptep); + struct kvm_mmu_page *sp = sptep_to_sp(rcu_dereference(iter->sptep)); u64 new_spte; int ret = RET_PF_FIXED; bool wrprot = false; diff --git a/arch/x86/kvm/pmu.c b/arch/x86/kvm/pmu.c index 0772bad9165c..09873f6488f7 100644 --- a/arch/x86/kvm/pmu.c +++ b/arch/x86/kvm/pmu.c @@ -319,7 +319,7 @@ void kvm_pmu_handle_event(struct kvm_vcpu *vcpu) } /* check if idx is a valid index to access PMU */ -int kvm_pmu_is_valid_rdpmc_ecx(struct kvm_vcpu *vcpu, unsigned int idx) +bool kvm_pmu_is_valid_rdpmc_ecx(struct kvm_vcpu *vcpu, unsigned int idx) { return kvm_x86_ops.pmu_ops->is_valid_rdpmc_ecx(vcpu, idx); } diff --git a/arch/x86/kvm/pmu.h b/arch/x86/kvm/pmu.h index 0e4f2b1fa9fb..59d6b76203d5 100644 --- a/arch/x86/kvm/pmu.h +++ b/arch/x86/kvm/pmu.h @@ -32,7 +32,7 @@ struct kvm_pmu_ops { struct kvm_pmc *(*rdpmc_ecx_to_pmc)(struct kvm_vcpu *vcpu, unsigned int idx, u64 *mask); struct kvm_pmc *(*msr_idx_to_pmc)(struct kvm_vcpu *vcpu, u32 msr); - int (*is_valid_rdpmc_ecx)(struct kvm_vcpu *vcpu, unsigned int idx); + bool (*is_valid_rdpmc_ecx)(struct kvm_vcpu *vcpu, unsigned int idx); bool (*is_valid_msr)(struct kvm_vcpu *vcpu, u32 msr); int (*get_msr)(struct kvm_vcpu *vcpu, struct msr_data *msr_info); int (*set_msr)(struct kvm_vcpu *vcpu, struct msr_data *msr_info); @@ -149,7 +149,7 @@ void reprogram_counter(struct kvm_pmu *pmu, int pmc_idx); void kvm_pmu_deliver_pmi(struct kvm_vcpu *vcpu); void kvm_pmu_handle_event(struct kvm_vcpu *vcpu); int kvm_pmu_rdpmc(struct kvm_vcpu *vcpu, unsigned pmc, u64 *data); -int kvm_pmu_is_valid_rdpmc_ecx(struct kvm_vcpu *vcpu, unsigned int idx); +bool kvm_pmu_is_valid_rdpmc_ecx(struct kvm_vcpu *vcpu, unsigned int idx); bool kvm_pmu_is_valid_msr(struct kvm_vcpu *vcpu, u32 msr); int kvm_pmu_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info); int kvm_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info); diff --git a/arch/x86/kvm/svm/avic.c b/arch/x86/kvm/svm/avic.c index 8052d92069e0..affc0ea98d30 100644 --- a/arch/x86/kvm/svm/avic.c +++ b/arch/x86/kvm/svm/avic.c @@ -904,7 +904,8 @@ bool svm_check_apicv_inhibit_reasons(ulong bit) BIT(APICV_INHIBIT_REASON_NESTED) | BIT(APICV_INHIBIT_REASON_IRQWIN) | BIT(APICV_INHIBIT_REASON_PIT_REINJ) | - BIT(APICV_INHIBIT_REASON_X2APIC); + BIT(APICV_INHIBIT_REASON_X2APIC) | + BIT(APICV_INHIBIT_REASON_BLOCKIRQ); return supported & BIT(bit); } diff --git a/arch/x86/kvm/svm/pmu.c b/arch/x86/kvm/svm/pmu.c index fdf587f19c5f..871c426ec389 100644 --- a/arch/x86/kvm/svm/pmu.c +++ b/arch/x86/kvm/svm/pmu.c @@ -181,14 +181,13 @@ static struct kvm_pmc *amd_pmc_idx_to_pmc(struct kvm_pmu *pmu, int pmc_idx) return get_gp_pmc_amd(pmu, base + pmc_idx, PMU_TYPE_COUNTER); } -/* returns 0 if idx's corresponding MSR exists; otherwise returns 1. */ -static int amd_is_valid_rdpmc_ecx(struct kvm_vcpu *vcpu, unsigned int idx) +static bool amd_is_valid_rdpmc_ecx(struct kvm_vcpu *vcpu, unsigned int idx) { struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); idx &= ~(3u << 30); - return (idx >= pmu->nr_arch_gp_counters); + return idx < pmu->nr_arch_gp_counters; } /* idx is the ECX register of RDPMC instruction */ diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c index 1964b9a174be..902c52a8dd0c 100644 --- a/arch/x86/kvm/svm/sev.c +++ b/arch/x86/kvm/svm/sev.c @@ -120,16 +120,26 @@ static bool __sev_recycle_asids(int min_asid, int max_asid) return true; } +static int sev_misc_cg_try_charge(struct kvm_sev_info *sev) +{ + enum misc_res_type type = sev->es_active ? MISC_CG_RES_SEV_ES : MISC_CG_RES_SEV; + return misc_cg_try_charge(type, sev->misc_cg, 1); +} + +static void sev_misc_cg_uncharge(struct kvm_sev_info *sev) +{ + enum misc_res_type type = sev->es_active ? MISC_CG_RES_SEV_ES : MISC_CG_RES_SEV; + misc_cg_uncharge(type, sev->misc_cg, 1); +} + static int sev_asid_new(struct kvm_sev_info *sev) { int asid, min_asid, max_asid, ret; bool retry = true; - enum misc_res_type type; - type = sev->es_active ? MISC_CG_RES_SEV_ES : MISC_CG_RES_SEV; WARN_ON(sev->misc_cg); sev->misc_cg = get_current_misc_cg(); - ret = misc_cg_try_charge(type, sev->misc_cg, 1); + ret = sev_misc_cg_try_charge(sev); if (ret) { put_misc_cg(sev->misc_cg); sev->misc_cg = NULL; @@ -162,7 +172,7 @@ again: return asid; e_uncharge: - misc_cg_uncharge(type, sev->misc_cg, 1); + sev_misc_cg_uncharge(sev); put_misc_cg(sev->misc_cg); sev->misc_cg = NULL; return ret; @@ -179,7 +189,6 @@ static void sev_asid_free(struct kvm_sev_info *sev) { struct svm_cpu_data *sd; int cpu; - enum misc_res_type type; mutex_lock(&sev_bitmap_lock); @@ -192,8 +201,7 @@ static void sev_asid_free(struct kvm_sev_info *sev) mutex_unlock(&sev_bitmap_lock); - type = sev->es_active ? MISC_CG_RES_SEV_ES : MISC_CG_RES_SEV; - misc_cg_uncharge(type, sev->misc_cg, 1); + sev_misc_cg_uncharge(sev); put_misc_cg(sev->misc_cg); sev->misc_cg = NULL; } @@ -590,7 +598,7 @@ static int sev_es_sync_vmsa(struct vcpu_svm *svm) * traditional VMSA as it has been built so far (in prep * for LAUNCH_UPDATE_VMSA) to be the initial SEV-ES state. */ - memcpy(svm->vmsa, save, sizeof(*save)); + memcpy(svm->sev_es.vmsa, save, sizeof(*save)); return 0; } @@ -612,11 +620,11 @@ static int __sev_launch_update_vmsa(struct kvm *kvm, struct kvm_vcpu *vcpu, * the VMSA memory content (i.e it will write the same memory region * with the guest's key), so invalidate it first. */ - clflush_cache_range(svm->vmsa, PAGE_SIZE); + clflush_cache_range(svm->sev_es.vmsa, PAGE_SIZE); vmsa.reserved = 0; vmsa.handle = to_kvm_svm(kvm)->sev_info.handle; - vmsa.address = __sme_pa(svm->vmsa); + vmsa.address = __sme_pa(svm->sev_es.vmsa); vmsa.len = PAGE_SIZE; ret = sev_issue_cmd(kvm, SEV_CMD_LAUNCH_UPDATE_VMSA, &vmsa, error); if (ret) @@ -1536,6 +1544,201 @@ static bool cmd_allowed_from_miror(u32 cmd_id) return false; } +static int sev_lock_for_migration(struct kvm *kvm) +{ + struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info; + + /* + * Bail if this VM is already involved in a migration to avoid deadlock + * between two VMs trying to migrate to/from each other. + */ + if (atomic_cmpxchg_acquire(&sev->migration_in_progress, 0, 1)) + return -EBUSY; + + mutex_lock(&kvm->lock); + + return 0; +} + +static void sev_unlock_after_migration(struct kvm *kvm) +{ + struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info; + + mutex_unlock(&kvm->lock); + atomic_set_release(&sev->migration_in_progress, 0); +} + + +static int sev_lock_vcpus_for_migration(struct kvm *kvm) +{ + struct kvm_vcpu *vcpu; + int i, j; + + kvm_for_each_vcpu(i, vcpu, kvm) { + if (mutex_lock_killable(&vcpu->mutex)) + goto out_unlock; + } + + return 0; + +out_unlock: + kvm_for_each_vcpu(j, vcpu, kvm) { + if (i == j) + break; + + mutex_unlock(&vcpu->mutex); + } + return -EINTR; +} + +static void sev_unlock_vcpus_for_migration(struct kvm *kvm) +{ + struct kvm_vcpu *vcpu; + int i; + + kvm_for_each_vcpu(i, vcpu, kvm) { + mutex_unlock(&vcpu->mutex); + } +} + +static void sev_migrate_from(struct kvm_sev_info *dst, + struct kvm_sev_info *src) +{ + dst->active = true; + dst->asid = src->asid; + dst->handle = src->handle; + dst->pages_locked = src->pages_locked; + + src->asid = 0; + src->active = false; + src->handle = 0; + src->pages_locked = 0; + + INIT_LIST_HEAD(&dst->regions_list); + list_replace_init(&src->regions_list, &dst->regions_list); +} + +static int sev_es_migrate_from(struct kvm *dst, struct kvm *src) +{ + int i; + struct kvm_vcpu *dst_vcpu, *src_vcpu; + struct vcpu_svm *dst_svm, *src_svm; + + if (atomic_read(&src->online_vcpus) != atomic_read(&dst->online_vcpus)) + return -EINVAL; + + kvm_for_each_vcpu(i, src_vcpu, src) { + if (!src_vcpu->arch.guest_state_protected) + return -EINVAL; + } + + kvm_for_each_vcpu(i, src_vcpu, src) { + src_svm = to_svm(src_vcpu); + dst_vcpu = kvm_get_vcpu(dst, i); + dst_svm = to_svm(dst_vcpu); + + /* + * Transfer VMSA and GHCB state to the destination. Nullify and + * clear source fields as appropriate, the state now belongs to + * the destination. + */ + memcpy(&dst_svm->sev_es, &src_svm->sev_es, sizeof(src_svm->sev_es)); + dst_svm->vmcb->control.ghcb_gpa = src_svm->vmcb->control.ghcb_gpa; + dst_svm->vmcb->control.vmsa_pa = src_svm->vmcb->control.vmsa_pa; + dst_vcpu->arch.guest_state_protected = true; + + memset(&src_svm->sev_es, 0, sizeof(src_svm->sev_es)); + src_svm->vmcb->control.ghcb_gpa = INVALID_PAGE; + src_svm->vmcb->control.vmsa_pa = INVALID_PAGE; + src_vcpu->arch.guest_state_protected = false; + } + to_kvm_svm(src)->sev_info.es_active = false; + to_kvm_svm(dst)->sev_info.es_active = true; + + return 0; +} + +int svm_vm_migrate_from(struct kvm *kvm, unsigned int source_fd) +{ + struct kvm_sev_info *dst_sev = &to_kvm_svm(kvm)->sev_info; + struct kvm_sev_info *src_sev, *cg_cleanup_sev; + struct file *source_kvm_file; + struct kvm *source_kvm; + bool charged = false; + int ret; + + ret = sev_lock_for_migration(kvm); + if (ret) + return ret; + + if (sev_guest(kvm)) { + ret = -EINVAL; + goto out_unlock; + } + + source_kvm_file = fget(source_fd); + if (!file_is_kvm(source_kvm_file)) { + ret = -EBADF; + goto out_fput; + } + + source_kvm = source_kvm_file->private_data; + ret = sev_lock_for_migration(source_kvm); + if (ret) + goto out_fput; + + if (!sev_guest(source_kvm)) { + ret = -EINVAL; + goto out_source; + } + + src_sev = &to_kvm_svm(source_kvm)->sev_info; + dst_sev->misc_cg = get_current_misc_cg(); + cg_cleanup_sev = dst_sev; + if (dst_sev->misc_cg != src_sev->misc_cg) { + ret = sev_misc_cg_try_charge(dst_sev); + if (ret) + goto out_dst_cgroup; + charged = true; + } + + ret = sev_lock_vcpus_for_migration(kvm); + if (ret) + goto out_dst_cgroup; + ret = sev_lock_vcpus_for_migration(source_kvm); + if (ret) + goto out_dst_vcpu; + + if (sev_es_guest(source_kvm)) { + ret = sev_es_migrate_from(kvm, source_kvm); + if (ret) + goto out_source_vcpu; + } + sev_migrate_from(dst_sev, src_sev); + kvm_vm_dead(source_kvm); + cg_cleanup_sev = src_sev; + ret = 0; + +out_source_vcpu: + sev_unlock_vcpus_for_migration(source_kvm); +out_dst_vcpu: + sev_unlock_vcpus_for_migration(kvm); +out_dst_cgroup: + /* Operates on the source on success, on the destination on failure. */ + if (charged) + sev_misc_cg_uncharge(cg_cleanup_sev); + put_misc_cg(cg_cleanup_sev->misc_cg); + cg_cleanup_sev->misc_cg = NULL; +out_source: + sev_unlock_after_migration(source_kvm); +out_fput: + if (source_kvm_file) + fput(source_kvm_file); +out_unlock: + sev_unlock_after_migration(kvm); + return ret; +} + int svm_mem_enc_op(struct kvm *kvm, void __user *argp) { struct kvm_sev_cmd sev_cmd; @@ -2038,16 +2241,16 @@ void sev_free_vcpu(struct kvm_vcpu *vcpu) svm = to_svm(vcpu); if (vcpu->arch.guest_state_protected) - sev_flush_guest_memory(svm, svm->vmsa, PAGE_SIZE); - __free_page(virt_to_page(svm->vmsa)); + sev_flush_guest_memory(svm, svm->sev_es.vmsa, PAGE_SIZE); + __free_page(virt_to_page(svm->sev_es.vmsa)); - if (svm->ghcb_sa_free) - kfree(svm->ghcb_sa); + if (svm->sev_es.ghcb_sa_free) + kfree(svm->sev_es.ghcb_sa); } static void dump_ghcb(struct vcpu_svm *svm) { - struct ghcb *ghcb = svm->ghcb; + struct ghcb *ghcb = svm->sev_es.ghcb; unsigned int nbits; /* Re-use the dump_invalid_vmcb module parameter */ @@ -2073,7 +2276,7 @@ static void dump_ghcb(struct vcpu_svm *svm) static void sev_es_sync_to_ghcb(struct vcpu_svm *svm) { struct kvm_vcpu *vcpu = &svm->vcpu; - struct ghcb *ghcb = svm->ghcb; + struct ghcb *ghcb = svm->sev_es.ghcb; /* * The GHCB protocol so far allows for the following data @@ -2093,7 +2296,7 @@ static void sev_es_sync_from_ghcb(struct vcpu_svm *svm) { struct vmcb_control_area *control = &svm->vmcb->control; struct kvm_vcpu *vcpu = &svm->vcpu; - struct ghcb *ghcb = svm->ghcb; + struct ghcb *ghcb = svm->sev_es.ghcb; u64 exit_code; /* @@ -2140,7 +2343,7 @@ static int sev_es_validate_vmgexit(struct vcpu_svm *svm) struct ghcb *ghcb; u64 exit_code = 0; - ghcb = svm->ghcb; + ghcb = svm->sev_es.ghcb; /* Only GHCB Usage code 0 is supported */ if (ghcb->ghcb_usage) @@ -2258,33 +2461,34 @@ vmgexit_err: void sev_es_unmap_ghcb(struct vcpu_svm *svm) { - if (!svm->ghcb) + if (!svm->sev_es.ghcb) return; - if (svm->ghcb_sa_free) { + if (svm->sev_es.ghcb_sa_free) { /* * The scratch area lives outside the GHCB, so there is a * buffer that, depending on the operation performed, may * need to be synced, then freed. */ - if (svm->ghcb_sa_sync) { + if (svm->sev_es.ghcb_sa_sync) { kvm_write_guest(svm->vcpu.kvm, - ghcb_get_sw_scratch(svm->ghcb), - svm->ghcb_sa, svm->ghcb_sa_len); - svm->ghcb_sa_sync = false; + ghcb_get_sw_scratch(svm->sev_es.ghcb), + svm->sev_es.ghcb_sa, + svm->sev_es.ghcb_sa_len); + svm->sev_es.ghcb_sa_sync = false; } - kfree(svm->ghcb_sa); - svm->ghcb_sa = NULL; - svm->ghcb_sa_free = false; + kfree(svm->sev_es.ghcb_sa); + svm->sev_es.ghcb_sa = NULL; + svm->sev_es.ghcb_sa_free = false; } - trace_kvm_vmgexit_exit(svm->vcpu.vcpu_id, svm->ghcb); + trace_kvm_vmgexit_exit(svm->vcpu.vcpu_id, svm->sev_es.ghcb); sev_es_sync_to_ghcb(svm); - kvm_vcpu_unmap(&svm->vcpu, &svm->ghcb_map, true); - svm->ghcb = NULL; + kvm_vcpu_unmap(&svm->vcpu, &svm->sev_es.ghcb_map, true); + svm->sev_es.ghcb = NULL; } void pre_sev_run(struct vcpu_svm *svm, int cpu) @@ -2314,7 +2518,7 @@ void pre_sev_run(struct vcpu_svm *svm, int cpu) static bool setup_vmgexit_scratch(struct vcpu_svm *svm, bool sync, u64 len) { struct vmcb_control_area *control = &svm->vmcb->control; - struct ghcb *ghcb = svm->ghcb; + struct ghcb *ghcb = svm->sev_es.ghcb; u64 ghcb_scratch_beg, ghcb_scratch_end; u64 scratch_gpa_beg, scratch_gpa_end; void *scratch_va; @@ -2350,7 +2554,7 @@ static bool setup_vmgexit_scratch(struct vcpu_svm *svm, bool sync, u64 len) return false; } - scratch_va = (void *)svm->ghcb; + scratch_va = (void *)svm->sev_es.ghcb; scratch_va += (scratch_gpa_beg - control->ghcb_gpa); } else { /* @@ -2380,12 +2584,12 @@ static bool setup_vmgexit_scratch(struct vcpu_svm *svm, bool sync, u64 len) * the vCPU next time (i.e. a read was requested so the data * must be written back to the guest memory). */ - svm->ghcb_sa_sync = sync; - svm->ghcb_sa_free = true; + svm->sev_es.ghcb_sa_sync = sync; + svm->sev_es.ghcb_sa_free = true; } - svm->ghcb_sa = scratch_va; - svm->ghcb_sa_len = len; + svm->sev_es.ghcb_sa = scratch_va; + svm->sev_es.ghcb_sa_len = len; return true; } @@ -2504,15 +2708,15 @@ int sev_handle_vmgexit(struct kvm_vcpu *vcpu) return -EINVAL; } - if (kvm_vcpu_map(vcpu, ghcb_gpa >> PAGE_SHIFT, &svm->ghcb_map)) { + if (kvm_vcpu_map(vcpu, ghcb_gpa >> PAGE_SHIFT, &svm->sev_es.ghcb_map)) { /* Unable to map GHCB from guest */ vcpu_unimpl(vcpu, "vmgexit: error mapping GHCB [%#llx] from guest\n", ghcb_gpa); return -EINVAL; } - svm->ghcb = svm->ghcb_map.hva; - ghcb = svm->ghcb_map.hva; + svm->sev_es.ghcb = svm->sev_es.ghcb_map.hva; + ghcb = svm->sev_es.ghcb_map.hva; trace_kvm_vmgexit_enter(vcpu->vcpu_id, ghcb); @@ -2535,7 +2739,7 @@ int sev_handle_vmgexit(struct kvm_vcpu *vcpu) ret = kvm_sev_es_mmio_read(vcpu, control->exit_info_1, control->exit_info_2, - svm->ghcb_sa); + svm->sev_es.ghcb_sa); break; case SVM_VMGEXIT_MMIO_WRITE: if (!setup_vmgexit_scratch(svm, false, control->exit_info_2)) @@ -2544,7 +2748,7 @@ int sev_handle_vmgexit(struct kvm_vcpu *vcpu) ret = kvm_sev_es_mmio_write(vcpu, control->exit_info_1, control->exit_info_2, - svm->ghcb_sa); + svm->sev_es.ghcb_sa); break; case SVM_VMGEXIT_NMI_COMPLETE: ret = svm_invoke_exit_handler(vcpu, SVM_EXIT_IRET); @@ -2604,7 +2808,8 @@ int sev_es_string_io(struct vcpu_svm *svm, int size, unsigned int port, int in) if (!setup_vmgexit_scratch(svm, in, bytes)) return -EINVAL; - return kvm_sev_es_string_io(&svm->vcpu, size, port, svm->ghcb_sa, count, in); + return kvm_sev_es_string_io(&svm->vcpu, size, port, svm->sev_es.ghcb_sa, + count, in); } void sev_es_init_vmcb(struct vcpu_svm *svm) @@ -2619,7 +2824,7 @@ void sev_es_init_vmcb(struct vcpu_svm *svm) * VMCB page. Do not include the encryption mask on the VMSA physical * address since hardware will access it using the guest key. */ - svm->vmcb->control.vmsa_pa = __pa(svm->vmsa); + svm->vmcb->control.vmsa_pa = __pa(svm->sev_es.vmsa); /* Can't intercept CR register access, HV can't modify CR registers */ svm_clr_intercept(svm, INTERCEPT_CR0_READ); @@ -2691,8 +2896,8 @@ void sev_vcpu_deliver_sipi_vector(struct kvm_vcpu *vcpu, u8 vector) struct vcpu_svm *svm = to_svm(vcpu); /* First SIPI: Use the values as initially set by the VMM */ - if (!svm->received_first_sipi) { - svm->received_first_sipi = true; + if (!svm->sev_es.received_first_sipi) { + svm->sev_es.received_first_sipi = true; return; } @@ -2701,8 +2906,8 @@ void sev_vcpu_deliver_sipi_vector(struct kvm_vcpu *vcpu, u8 vector) * the guest will set the CS and RIP. Set SW_EXIT_INFO_2 to a * non-zero value. */ - if (!svm->ghcb) + if (!svm->sev_es.ghcb) return; - ghcb_set_sw_exit_info_2(svm->ghcb, 1); + ghcb_set_sw_exit_info_2(svm->sev_es.ghcb, 1); } diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index b36ca4e476c2..5630c241d5f6 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -1452,7 +1452,7 @@ static int svm_create_vcpu(struct kvm_vcpu *vcpu) svm_switch_vmcb(svm, &svm->vmcb01); if (vmsa_page) - svm->vmsa = page_address(vmsa_page); + svm->sev_es.vmsa = page_address(vmsa_page); svm->guest_state_loaded = false; @@ -2835,11 +2835,11 @@ static int svm_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) static int svm_complete_emulated_msr(struct kvm_vcpu *vcpu, int err) { struct vcpu_svm *svm = to_svm(vcpu); - if (!err || !sev_es_guest(vcpu->kvm) || WARN_ON_ONCE(!svm->ghcb)) + if (!err || !sev_es_guest(vcpu->kvm) || WARN_ON_ONCE(!svm->sev_es.ghcb)) return kvm_complete_insn_gp(vcpu, err); - ghcb_set_sw_exit_info_1(svm->ghcb, 1); - ghcb_set_sw_exit_info_2(svm->ghcb, + ghcb_set_sw_exit_info_1(svm->sev_es.ghcb, 1); + ghcb_set_sw_exit_info_2(svm->sev_es.ghcb, X86_TRAP_GP | SVM_EVTINJ_TYPE_EXEPT | SVM_EVTINJ_VALID); @@ -3121,11 +3121,6 @@ static int invpcid_interception(struct kvm_vcpu *vcpu) type = svm->vmcb->control.exit_info_2; gva = svm->vmcb->control.exit_info_1; - if (type > 3) { - kvm_inject_gp(vcpu, 0); - return 1; - } - return kvm_handle_invpcid(vcpu, type, gva); } @@ -4701,6 +4696,7 @@ static struct kvm_x86_ops svm_x86_ops __initdata = { .mem_enc_unreg_region = svm_unregister_enc_region, .vm_copy_enc_context_from = svm_vm_copy_asid_from, + .vm_move_enc_context_from = svm_vm_migrate_from, .can_emulate_instruction = svm_can_emulate_instruction, diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h index 5e9510d4574e..437e68504e66 100644 --- a/arch/x86/kvm/svm/svm.h +++ b/arch/x86/kvm/svm/svm.h @@ -80,6 +80,7 @@ struct kvm_sev_info { u64 ap_jump_table; /* SEV-ES AP Jump Table address */ struct kvm *enc_context_owner; /* Owner of copied encryption context */ struct misc_cg *misc_cg; /* For misc cgroup accounting */ + atomic_t migration_in_progress; }; struct kvm_svm { @@ -123,6 +124,20 @@ struct svm_nested_state { bool initialized; }; +struct vcpu_sev_es_state { + /* SEV-ES support */ + struct vmcb_save_area *vmsa; + struct ghcb *ghcb; + struct kvm_host_map ghcb_map; + bool received_first_sipi; + + /* SEV-ES scratch area support */ + void *ghcb_sa; + u32 ghcb_sa_len; + bool ghcb_sa_sync; + bool ghcb_sa_free; +}; + struct vcpu_svm { struct kvm_vcpu vcpu; /* vmcb always points at current_vmcb->ptr, it's purely a shorthand. */ @@ -186,17 +201,7 @@ struct vcpu_svm { DECLARE_BITMAP(write, MAX_DIRECT_ACCESS_MSRS); } shadow_msr_intercept; - /* SEV-ES support */ - struct vmcb_save_area *vmsa; - struct ghcb *ghcb; - struct kvm_host_map ghcb_map; - bool received_first_sipi; - - /* SEV-ES scratch area support */ - void *ghcb_sa; - u32 ghcb_sa_len; - bool ghcb_sa_sync; - bool ghcb_sa_free; + struct vcpu_sev_es_state sev_es; bool guest_state_loaded; }; @@ -558,6 +563,7 @@ int svm_register_enc_region(struct kvm *kvm, int svm_unregister_enc_region(struct kvm *kvm, struct kvm_enc_region *range); int svm_vm_copy_asid_from(struct kvm *kvm, unsigned int source_fd); +int svm_vm_migrate_from(struct kvm *kvm, unsigned int source_fd); void pre_sev_run(struct vcpu_svm *svm, int cpu); void __init sev_set_cpu_caps(void); void __init sev_hardware_setup(void); diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c index b4ee5e9f9e20..b213ca966d41 100644 --- a/arch/x86/kvm/vmx/nested.c +++ b/arch/x86/kvm/vmx/nested.c @@ -525,67 +525,19 @@ static int nested_vmx_check_tpr_shadow_controls(struct kvm_vcpu *vcpu, } /* - * Check if MSR is intercepted for L01 MSR bitmap. + * For x2APIC MSRs, ignore the vmcs01 bitmap. L1 can enable x2APIC without L1 + * itself utilizing x2APIC. All MSRs were previously set to be intercepted, + * only the "disable intercept" case needs to be handled. */ -static bool msr_write_intercepted_l01(struct kvm_vcpu *vcpu, u32 msr) +static void nested_vmx_disable_intercept_for_x2apic_msr(unsigned long *msr_bitmap_l1, + unsigned long *msr_bitmap_l0, + u32 msr, int type) { - unsigned long *msr_bitmap; - int f = sizeof(unsigned long); + if (type & MSR_TYPE_R && !vmx_test_msr_bitmap_read(msr_bitmap_l1, msr)) + vmx_clear_msr_bitmap_read(msr_bitmap_l0, msr); - if (!cpu_has_vmx_msr_bitmap()) - return true; - - msr_bitmap = to_vmx(vcpu)->vmcs01.msr_bitmap; - - if (msr <= 0x1fff) { - return !!test_bit(msr, msr_bitmap + 0x800 / f); - } else if ((msr >= 0xc0000000) && (msr <= 0xc0001fff)) { - msr &= 0x1fff; - return !!test_bit(msr, msr_bitmap + 0xc00 / f); - } - - return true; -} - -/* - * If a msr is allowed by L0, we should check whether it is allowed by L1. - * The corresponding bit will be cleared unless both of L0 and L1 allow it. - */ -static void nested_vmx_disable_intercept_for_msr(unsigned long *msr_bitmap_l1, - unsigned long *msr_bitmap_nested, - u32 msr, int type) -{ - int f = sizeof(unsigned long); - - /* - * See Intel PRM Vol. 3, 20.6.9 (MSR-Bitmap Address). Early manuals - * have the write-low and read-high bitmap offsets the wrong way round. - * We can control MSRs 0x00000000-0x00001fff and 0xc0000000-0xc0001fff. - */ - if (msr <= 0x1fff) { - if (type & MSR_TYPE_R && - !test_bit(msr, msr_bitmap_l1 + 0x000 / f)) - /* read-low */ - __clear_bit(msr, msr_bitmap_nested + 0x000 / f); - - if (type & MSR_TYPE_W && - !test_bit(msr, msr_bitmap_l1 + 0x800 / f)) - /* write-low */ - __clear_bit(msr, msr_bitmap_nested + 0x800 / f); - - } else if ((msr >= 0xc0000000) && (msr <= 0xc0001fff)) { - msr &= 0x1fff; - if (type & MSR_TYPE_R && - !test_bit(msr, msr_bitmap_l1 + 0x400 / f)) - /* read-high */ - __clear_bit(msr, msr_bitmap_nested + 0x400 / f); - - if (type & MSR_TYPE_W && - !test_bit(msr, msr_bitmap_l1 + 0xc00 / f)) - /* write-high */ - __clear_bit(msr, msr_bitmap_nested + 0xc00 / f); - - } + if (type & MSR_TYPE_W && !vmx_test_msr_bitmap_write(msr_bitmap_l1, msr)) + vmx_clear_msr_bitmap_write(msr_bitmap_l0, msr); } static inline void enable_x2apic_msr_intercepts(unsigned long *msr_bitmap) @@ -600,6 +552,34 @@ static inline void enable_x2apic_msr_intercepts(unsigned long *msr_bitmap) } } +#define BUILD_NVMX_MSR_INTERCEPT_HELPER(rw) \ +static inline \ +void nested_vmx_set_msr_##rw##_intercept(struct vcpu_vmx *vmx, \ + unsigned long *msr_bitmap_l1, \ + unsigned long *msr_bitmap_l0, u32 msr) \ +{ \ + if (vmx_test_msr_bitmap_##rw(vmx->vmcs01.msr_bitmap, msr) || \ + vmx_test_msr_bitmap_##rw(msr_bitmap_l1, msr)) \ + vmx_set_msr_bitmap_##rw(msr_bitmap_l0, msr); \ + else \ + vmx_clear_msr_bitmap_##rw(msr_bitmap_l0, msr); \ +} +BUILD_NVMX_MSR_INTERCEPT_HELPER(read) +BUILD_NVMX_MSR_INTERCEPT_HELPER(write) + +static inline void nested_vmx_set_intercept_for_msr(struct vcpu_vmx *vmx, + unsigned long *msr_bitmap_l1, + unsigned long *msr_bitmap_l0, + u32 msr, int types) +{ + if (types & MSR_TYPE_R) + nested_vmx_set_msr_read_intercept(vmx, msr_bitmap_l1, + msr_bitmap_l0, msr); + if (types & MSR_TYPE_W) + nested_vmx_set_msr_write_intercept(vmx, msr_bitmap_l1, + msr_bitmap_l0, msr); +} + /* * Merge L0's and L1's MSR bitmap, return false to indicate that * we do not use the hardware. @@ -607,10 +587,11 @@ static inline void enable_x2apic_msr_intercepts(unsigned long *msr_bitmap) static inline bool nested_vmx_prepare_msr_bitmap(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) { + struct vcpu_vmx *vmx = to_vmx(vcpu); int msr; unsigned long *msr_bitmap_l1; - unsigned long *msr_bitmap_l0 = to_vmx(vcpu)->nested.vmcs02.msr_bitmap; - struct kvm_host_map *map = &to_vmx(vcpu)->nested.msr_bitmap_map; + unsigned long *msr_bitmap_l0 = vmx->nested.vmcs02.msr_bitmap; + struct kvm_host_map *map = &vmx->nested.msr_bitmap_map; /* Nothing to do if the MSR bitmap is not in use. */ if (!cpu_has_vmx_msr_bitmap() || @@ -625,7 +606,7 @@ static inline bool nested_vmx_prepare_msr_bitmap(struct kvm_vcpu *vcpu, /* * To keep the control flow simple, pay eight 8-byte writes (sixteen * 4-byte writes on 32-bit systems) up front to enable intercepts for - * the x2APIC MSR range and selectively disable them below. + * the x2APIC MSR range and selectively toggle those relevant to L2. */ enable_x2apic_msr_intercepts(msr_bitmap_l0); @@ -644,61 +625,44 @@ static inline bool nested_vmx_prepare_msr_bitmap(struct kvm_vcpu *vcpu, } } - nested_vmx_disable_intercept_for_msr( + nested_vmx_disable_intercept_for_x2apic_msr( msr_bitmap_l1, msr_bitmap_l0, X2APIC_MSR(APIC_TASKPRI), MSR_TYPE_R | MSR_TYPE_W); if (nested_cpu_has_vid(vmcs12)) { - nested_vmx_disable_intercept_for_msr( + nested_vmx_disable_intercept_for_x2apic_msr( msr_bitmap_l1, msr_bitmap_l0, X2APIC_MSR(APIC_EOI), MSR_TYPE_W); - nested_vmx_disable_intercept_for_msr( + nested_vmx_disable_intercept_for_x2apic_msr( msr_bitmap_l1, msr_bitmap_l0, X2APIC_MSR(APIC_SELF_IPI), MSR_TYPE_W); } } - /* KVM unconditionally exposes the FS/GS base MSRs to L1. */ + /* + * Always check vmcs01's bitmap to honor userspace MSR filters and any + * other runtime changes to vmcs01's bitmap, e.g. dynamic pass-through. + */ #ifdef CONFIG_X86_64 - nested_vmx_disable_intercept_for_msr(msr_bitmap_l1, msr_bitmap_l0, - MSR_FS_BASE, MSR_TYPE_RW); + nested_vmx_set_intercept_for_msr(vmx, msr_bitmap_l1, msr_bitmap_l0, + MSR_FS_BASE, MSR_TYPE_RW); - nested_vmx_disable_intercept_for_msr(msr_bitmap_l1, msr_bitmap_l0, - MSR_GS_BASE, MSR_TYPE_RW); + nested_vmx_set_intercept_for_msr(vmx, msr_bitmap_l1, msr_bitmap_l0, + MSR_GS_BASE, MSR_TYPE_RW); - nested_vmx_disable_intercept_for_msr(msr_bitmap_l1, msr_bitmap_l0, - MSR_KERNEL_GS_BASE, MSR_TYPE_RW); + nested_vmx_set_intercept_for_msr(vmx, msr_bitmap_l1, msr_bitmap_l0, + MSR_KERNEL_GS_BASE, MSR_TYPE_RW); #endif + nested_vmx_set_intercept_for_msr(vmx, msr_bitmap_l1, msr_bitmap_l0, + MSR_IA32_SPEC_CTRL, MSR_TYPE_RW); - /* - * Checking the L0->L1 bitmap is trying to verify two things: - * - * 1. L0 gave a permission to L1 to actually passthrough the MSR. This - * ensures that we do not accidentally generate an L02 MSR bitmap - * from the L12 MSR bitmap that is too permissive. - * 2. That L1 or L2s have actually used the MSR. This avoids - * unnecessarily merging of the bitmap if the MSR is unused. This - * works properly because we only update the L01 MSR bitmap lazily. - * So even if L0 should pass L1 these MSRs, the L01 bitmap is only - * updated to reflect this when L1 (or its L2s) actually write to - * the MSR. - */ - if (!msr_write_intercepted_l01(vcpu, MSR_IA32_SPEC_CTRL)) - nested_vmx_disable_intercept_for_msr( - msr_bitmap_l1, msr_bitmap_l0, - MSR_IA32_SPEC_CTRL, - MSR_TYPE_R | MSR_TYPE_W); - - if (!msr_write_intercepted_l01(vcpu, MSR_IA32_PRED_CMD)) - nested_vmx_disable_intercept_for_msr( - msr_bitmap_l1, msr_bitmap_l0, - MSR_IA32_PRED_CMD, - MSR_TYPE_W); + nested_vmx_set_intercept_for_msr(vmx, msr_bitmap_l1, msr_bitmap_l0, + MSR_IA32_PRED_CMD, MSR_TYPE_W); - kvm_vcpu_unmap(vcpu, &to_vmx(vcpu)->nested.msr_bitmap_map, false); + kvm_vcpu_unmap(vcpu, &vmx->nested.msr_bitmap_map, false); return true; } @@ -5379,7 +5343,7 @@ static int handle_invept(struct kvm_vcpu *vcpu) struct { u64 eptp, gpa; } operand; - int i, r; + int i, r, gpr_index; if (!(vmx->nested.msrs.secondary_ctls_high & SECONDARY_EXEC_ENABLE_EPT) || @@ -5392,7 +5356,8 @@ static int handle_invept(struct kvm_vcpu *vcpu) return 1; vmx_instruction_info = vmcs_read32(VMX_INSTRUCTION_INFO); - type = kvm_register_read(vcpu, (vmx_instruction_info >> 28) & 0xf); + gpr_index = vmx_get_instr_info_reg2(vmx_instruction_info); + type = kvm_register_read(vcpu, gpr_index); types = (vmx->nested.msrs.ept_caps >> VMX_EPT_EXTENT_SHIFT) & 6; @@ -5459,7 +5424,7 @@ static int handle_invvpid(struct kvm_vcpu *vcpu) u64 gla; } operand; u16 vpid02; - int r; + int r, gpr_index; if (!(vmx->nested.msrs.secondary_ctls_high & SECONDARY_EXEC_ENABLE_VPID) || @@ -5472,7 +5437,8 @@ static int handle_invvpid(struct kvm_vcpu *vcpu) return 1; vmx_instruction_info = vmcs_read32(VMX_INSTRUCTION_INFO); - type = kvm_register_read(vcpu, (vmx_instruction_info >> 28) & 0xf); + gpr_index = vmx_get_instr_info_reg2(vmx_instruction_info); + type = kvm_register_read(vcpu, gpr_index); types = (vmx->nested.msrs.vpid_caps & VMX_VPID_EXTENT_SUPPORTED_MASK) >> 8; diff --git a/arch/x86/kvm/vmx/pmu_intel.c b/arch/x86/kvm/vmx/pmu_intel.c index b8e0d21b7c8a..1b7456b2177b 100644 --- a/arch/x86/kvm/vmx/pmu_intel.c +++ b/arch/x86/kvm/vmx/pmu_intel.c @@ -118,16 +118,15 @@ static struct kvm_pmc *intel_pmc_idx_to_pmc(struct kvm_pmu *pmu, int pmc_idx) } } -/* returns 0 if idx's corresponding MSR exists; otherwise returns 1. */ -static int intel_is_valid_rdpmc_ecx(struct kvm_vcpu *vcpu, unsigned int idx) +static bool intel_is_valid_rdpmc_ecx(struct kvm_vcpu *vcpu, unsigned int idx) { struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); bool fixed = idx & (1u << 30); idx &= ~(3u << 30); - return (!fixed && idx >= pmu->nr_arch_gp_counters) || - (fixed && idx >= pmu->nr_arch_fixed_counters); + return fixed ? idx < pmu->nr_arch_fixed_counters + : idx < pmu->nr_arch_gp_counters; } static struct kvm_pmc *intel_rdpmc_ecx_to_pmc(struct kvm_vcpu *vcpu, diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index 76861b66bbcf..ba66c171d951 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -769,24 +769,13 @@ void vmx_update_exception_bitmap(struct kvm_vcpu *vcpu) /* * Check if MSR is intercepted for currently loaded MSR bitmap. */ -static bool msr_write_intercepted(struct kvm_vcpu *vcpu, u32 msr) +static bool msr_write_intercepted(struct vcpu_vmx *vmx, u32 msr) { - unsigned long *msr_bitmap; - int f = sizeof(unsigned long); - - if (!cpu_has_vmx_msr_bitmap()) + if (!(exec_controls_get(vmx) & CPU_BASED_USE_MSR_BITMAPS)) return true; - msr_bitmap = to_vmx(vcpu)->loaded_vmcs->msr_bitmap; - - if (msr <= 0x1fff) { - return !!test_bit(msr, msr_bitmap + 0x800 / f); - } else if ((msr >= 0xc0000000) && (msr <= 0xc0001fff)) { - msr &= 0x1fff; - return !!test_bit(msr, msr_bitmap + 0xc00 / f); - } - - return true; + return vmx_test_msr_bitmap_write(vmx->loaded_vmcs->msr_bitmap, + MSR_IA32_SPEC_CTRL); } static void clear_atomic_switch_msr_special(struct vcpu_vmx *vmx, @@ -3697,46 +3686,6 @@ void free_vpid(int vpid) spin_unlock(&vmx_vpid_lock); } -static void vmx_clear_msr_bitmap_read(ulong *msr_bitmap, u32 msr) -{ - int f = sizeof(unsigned long); - - if (msr <= 0x1fff) - __clear_bit(msr, msr_bitmap + 0x000 / f); - else if ((msr >= 0xc0000000) && (msr <= 0xc0001fff)) - __clear_bit(msr & 0x1fff, msr_bitmap + 0x400 / f); -} - -static void vmx_clear_msr_bitmap_write(ulong *msr_bitmap, u32 msr) -{ - int f = sizeof(unsigned long); - - if (msr <= 0x1fff) - __clear_bit(msr, msr_bitmap + 0x800 / f); - else if ((msr >= 0xc0000000) && (msr <= 0xc0001fff)) - __clear_bit(msr & 0x1fff, msr_bitmap + 0xc00 / f); -} - -static void vmx_set_msr_bitmap_read(ulong *msr_bitmap, u32 msr) -{ - int f = sizeof(unsigned long); - - if (msr <= 0x1fff) - __set_bit(msr, msr_bitmap + 0x000 / f); - else if ((msr >= 0xc0000000) && (msr <= 0xc0001fff)) - __set_bit(msr & 0x1fff, msr_bitmap + 0x400 / f); -} - -static void vmx_set_msr_bitmap_write(ulong *msr_bitmap, u32 msr) -{ - int f = sizeof(unsigned long); - - if (msr <= 0x1fff) - __set_bit(msr, msr_bitmap + 0x800 / f); - else if ((msr >= 0xc0000000) && (msr <= 0xc0001fff)) - __set_bit(msr & 0x1fff, msr_bitmap + 0xc00 / f); -} - void vmx_disable_intercept_for_msr(struct kvm_vcpu *vcpu, u32 msr, int type) { struct vcpu_vmx *vmx = to_vmx(vcpu); @@ -5494,6 +5443,7 @@ static int handle_invpcid(struct kvm_vcpu *vcpu) u64 pcid; u64 gla; } operand; + int gpr_index; if (!guest_cpuid_has(vcpu, X86_FEATURE_INVPCID)) { kvm_queue_exception(vcpu, UD_VECTOR); @@ -5501,12 +5451,8 @@ static int handle_invpcid(struct kvm_vcpu *vcpu) } vmx_instruction_info = vmcs_read32(VMX_INSTRUCTION_INFO); - type = kvm_register_read(vcpu, (vmx_instruction_info >> 28) & 0xf); - - if (type > 3) { - kvm_inject_gp(vcpu, 0); - return 1; - } + gpr_index = vmx_get_instr_info_reg2(vmx_instruction_info); + type = kvm_register_read(vcpu, gpr_index); /* According to the Intel instruction reference, the memory operand * is read even if it isn't needed (e.g., for type==all) @@ -6749,7 +6695,7 @@ static fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu) * If the L02 MSR bitmap does not intercept the MSR, then we need to * save it. */ - if (unlikely(!msr_write_intercepted(vcpu, MSR_IA32_SPEC_CTRL))) + if (unlikely(!msr_write_intercepted(vmx, MSR_IA32_SPEC_CTRL))) vmx->spec_ctrl = native_read_msr(MSR_IA32_SPEC_CTRL); x86_spec_ctrl_restore_host(vmx->spec_ctrl, 0); @@ -7563,7 +7509,8 @@ static void hardware_unsetup(void) static bool vmx_check_apicv_inhibit_reasons(ulong bit) { ulong supported = BIT(APICV_INHIBIT_REASON_DISABLE) | - BIT(APICV_INHIBIT_REASON_HYPERV); + BIT(APICV_INHIBIT_REASON_HYPERV) | + BIT(APICV_INHIBIT_REASON_BLOCKIRQ); return supported & BIT(bit); } diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h index e7db42e3b0ce..a4ead6023133 100644 --- a/arch/x86/kvm/vmx/vmx.h +++ b/arch/x86/kvm/vmx/vmx.h @@ -400,6 +400,34 @@ static inline void vmx_set_intercept_for_msr(struct kvm_vcpu *vcpu, u32 msr, void vmx_update_cpu_dirty_logging(struct kvm_vcpu *vcpu); +/* + * Note, early Intel manuals have the write-low and read-high bitmap offsets + * the wrong way round. The bitmaps control MSRs 0x00000000-0x00001fff and + * 0xc0000000-0xc0001fff. The former (low) uses bytes 0-0x3ff for reads and + * 0x800-0xbff for writes. The latter (high) uses 0x400-0x7ff for reads and + * 0xc00-0xfff for writes. MSRs not covered by either of the ranges always + * VM-Exit. + */ +#define __BUILD_VMX_MSR_BITMAP_HELPER(rtype, action, bitop, access, base) \ +static inline rtype vmx_##action##_msr_bitmap_##access(unsigned long *bitmap, \ + u32 msr) \ +{ \ + int f = sizeof(unsigned long); \ + \ + if (msr <= 0x1fff) \ + return bitop##_bit(msr, bitmap + base / f); \ + else if ((msr >= 0xc0000000) && (msr <= 0xc0001fff)) \ + return bitop##_bit(msr & 0x1fff, bitmap + (base + 0x400) / f); \ + return (rtype)true; \ +} +#define BUILD_VMX_MSR_BITMAP_HELPERS(ret_type, action, bitop) \ + __BUILD_VMX_MSR_BITMAP_HELPER(ret_type, action, bitop, read, 0x0) \ + __BUILD_VMX_MSR_BITMAP_HELPER(ret_type, action, bitop, write, 0x800) + +BUILD_VMX_MSR_BITMAP_HELPERS(bool, test, test) +BUILD_VMX_MSR_BITMAP_HELPERS(void, clear, __clear) +BUILD_VMX_MSR_BITMAP_HELPERS(void, set, __set) + static inline u8 vmx_get_rvi(void) { return vmcs_read16(GUEST_INTR_STATUS) & 0xff; @@ -522,4 +550,9 @@ static inline bool vmx_guest_state_valid(struct kvm_vcpu *vcpu) void dump_vmcs(struct kvm_vcpu *vcpu); +static inline int vmx_get_instr_info_reg2(u32 vmx_instr_info) +{ + return (vmx_instr_info >> 28) & 0xf; +} + #endif /* __KVM_X86_VMX_H */ diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index c1c4e2b05a63..dc7eb5fddfd3 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -3260,8 +3260,11 @@ static void kvm_vcpu_flush_tlb_guest(struct kvm_vcpu *vcpu) static void record_steal_time(struct kvm_vcpu *vcpu) { - struct kvm_host_map map; - struct kvm_steal_time *st; + struct gfn_to_hva_cache *ghc = &vcpu->arch.st.cache; + struct kvm_steal_time __user *st; + struct kvm_memslots *slots; + u64 steal; + u32 version; if (kvm_xen_msr_enabled(vcpu->kvm)) { kvm_xen_runstate_set_running(vcpu); @@ -3271,47 +3274,86 @@ static void record_steal_time(struct kvm_vcpu *vcpu) if (!(vcpu->arch.st.msr_val & KVM_MSR_ENABLED)) return; - /* -EAGAIN is returned in atomic context so we can just return. */ - if (kvm_map_gfn(vcpu, vcpu->arch.st.msr_val >> PAGE_SHIFT, - &map, &vcpu->arch.st.cache, false)) + if (WARN_ON_ONCE(current->mm != vcpu->kvm->mm)) return; - st = map.hva + - offset_in_page(vcpu->arch.st.msr_val & KVM_STEAL_VALID_BITS); + slots = kvm_memslots(vcpu->kvm); + + if (unlikely(slots->generation != ghc->generation || + kvm_is_error_hva(ghc->hva) || !ghc->memslot)) { + gfn_t gfn = vcpu->arch.st.msr_val & KVM_STEAL_VALID_BITS; + + /* We rely on the fact that it fits in a single page. */ + BUILD_BUG_ON((sizeof(*st) - 1) & KVM_STEAL_VALID_BITS); + + if (kvm_gfn_to_hva_cache_init(vcpu->kvm, ghc, gfn, sizeof(*st)) || + kvm_is_error_hva(ghc->hva) || !ghc->memslot) + return; + } + st = (struct kvm_steal_time __user *)ghc->hva; /* * Doing a TLB flush here, on the guest's behalf, can avoid * expensive IPIs. */ if (guest_pv_has(vcpu, KVM_FEATURE_PV_TLB_FLUSH)) { - u8 st_preempted = xchg(&st->preempted, 0); + u8 st_preempted = 0; + int err = -EFAULT; + + if (!user_access_begin(st, sizeof(*st))) + return; + + asm volatile("1: xchgb %0, %2\n" + "xor %1, %1\n" + "2:\n" + _ASM_EXTABLE_UA(1b, 2b) + : "+r" (st_preempted), + "+&r" (err) + : "m" (st->preempted)); + if (err) + goto out; + + user_access_end(); + + vcpu->arch.st.preempted = 0; trace_kvm_pv_tlb_flush(vcpu->vcpu_id, st_preempted & KVM_VCPU_FLUSH_TLB); if (st_preempted & KVM_VCPU_FLUSH_TLB) kvm_vcpu_flush_tlb_guest(vcpu); + + if (!user_access_begin(st, sizeof(*st))) + goto dirty; } else { - st->preempted = 0; - } + if (!user_access_begin(st, sizeof(*st))) + return; - vcpu->arch.st.preempted = 0; + unsafe_put_user(0, &st->preempted, out); + vcpu->arch.st.preempted = 0; + } - if (st->version & 1) - st->version += 1; /* first time write, random junk */ + unsafe_get_user(version, &st->version, out); + if (version & 1) + version += 1; /* first time write, random junk */ - st->version += 1; + version += 1; + unsafe_put_user(version, &st->version, out); smp_wmb(); - st->steal += current->sched_info.run_delay - + unsafe_get_user(steal, &st->steal, out); + steal += current->sched_info.run_delay - vcpu->arch.st.last_steal; vcpu->arch.st.last_steal = current->sched_info.run_delay; + unsafe_put_user(steal, &st->steal, out); - smp_wmb(); - - st->version += 1; + version += 1; + unsafe_put_user(version, &st->version, out); - kvm_unmap_gfn(vcpu, &map, &vcpu->arch.st.cache, true, false); + out: + user_access_end(); + dirty: + mark_page_dirty_in_slot(vcpu->kvm, ghc->memslot, gpa_to_gfn(ghc->gpa)); } int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) @@ -3517,7 +3559,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) if (!guest_pv_has(vcpu, KVM_FEATURE_PV_EOI)) return 1; - if (kvm_lapic_enable_pv_eoi(vcpu, data, sizeof(u8))) + if (kvm_lapic_set_pv_eoi(vcpu, data, sizeof(u8))) return 1; break; @@ -4137,7 +4179,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) r = !static_call(kvm_x86_cpu_has_accelerated_tpr)(); break; case KVM_CAP_NR_VCPUS: - r = KVM_SOFT_MAX_VCPUS; + r = num_online_cpus(); break; case KVM_CAP_MAX_VCPUS: r = KVM_MAX_VCPUS; @@ -4351,8 +4393,10 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu) static void kvm_steal_time_set_preempted(struct kvm_vcpu *vcpu) { - struct kvm_host_map map; - struct kvm_steal_time *st; + struct gfn_to_hva_cache *ghc = &vcpu->arch.st.cache; + struct kvm_steal_time __user *st; + struct kvm_memslots *slots; + static const u8 preempted = KVM_VCPU_PREEMPTED; if (!(vcpu->arch.st.msr_val & KVM_MSR_ENABLED)) return; @@ -4360,16 +4404,23 @@ static void kvm_steal_time_set_preempted(struct kvm_vcpu *vcpu) if (vcpu->arch.st.preempted) return; - if (kvm_map_gfn(vcpu, vcpu->arch.st.msr_val >> PAGE_SHIFT, &map, - &vcpu->arch.st.cache, true)) + /* This happens on process exit */ + if (unlikely(current->mm != vcpu->kvm->mm)) return; - st = map.hva + - offset_in_page(vcpu->arch.st.msr_val & KVM_STEAL_VALID_BITS); + slots = kvm_memslots(vcpu->kvm); + + if (unlikely(slots->generation != ghc->generation || + kvm_is_error_hva(ghc->hva) || !ghc->memslot)) + return; - st->preempted = vcpu->arch.st.preempted = KVM_VCPU_PREEMPTED; + st = (struct kvm_steal_time __user *)ghc->hva; + BUILD_BUG_ON(sizeof(st->preempted) != sizeof(preempted)); - kvm_unmap_gfn(vcpu, &map, &vcpu->arch.st.cache, true, true); + if (!copy_to_user_nofault(&st->preempted, &preempted, sizeof(preempted))) + vcpu->arch.st.preempted = KVM_VCPU_PREEMPTED; + + mark_page_dirty_in_slot(vcpu->kvm, ghc->memslot, gpa_to_gfn(ghc->gpa)); } void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu) @@ -5728,6 +5779,12 @@ split_irqchip_unlock: if (kvm_x86_ops.vm_copy_enc_context_from) r = kvm_x86_ops.vm_copy_enc_context_from(kvm, cap->args[0]); return r; + case KVM_CAP_VM_MOVE_ENC_CONTEXT_FROM: + r = -EINVAL; + if (kvm_x86_ops.vm_move_enc_context_from) + r = kvm_x86_ops.vm_move_enc_context_from( + kvm, cap->args[0]); + return r; case KVM_CAP_EXIT_HYPERCALL: if (cap->args[0] & ~KVM_EXIT_HYPERCALL_VALID_MASK) { r = -EINVAL; @@ -7328,7 +7385,9 @@ static void emulator_set_smbase(struct x86_emulate_ctxt *ctxt, u64 smbase) static int emulator_check_pmc(struct x86_emulate_ctxt *ctxt, u32 pmc) { - return kvm_pmu_is_valid_rdpmc_ecx(emul_to_vcpu(ctxt), pmc); + if (kvm_pmu_is_valid_rdpmc_ecx(emul_to_vcpu(ctxt), pmc)) + return 0; + return -EINVAL; } static int emulator_read_pmc(struct x86_emulate_ctxt *ctxt, @@ -9552,7 +9611,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) } if (kvm_request_pending(vcpu)) { - if (kvm_check_request(KVM_REQ_VM_BUGGED, vcpu)) { + if (kvm_check_request(KVM_REQ_VM_DEAD, vcpu)) { r = -EIO; goto out; } @@ -10564,6 +10623,24 @@ int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu, return ret; } +static void kvm_arch_vcpu_guestdbg_update_apicv_inhibit(struct kvm *kvm) +{ + bool inhibit = false; + struct kvm_vcpu *vcpu; + int i; + + down_write(&kvm->arch.apicv_update_lock); + + kvm_for_each_vcpu(i, vcpu, kvm) { + if (vcpu->guest_debug & KVM_GUESTDBG_BLOCKIRQ) { + inhibit = true; + break; + } + } + __kvm_request_apicv_update(kvm, !inhibit, APICV_INHIBIT_REASON_BLOCKIRQ); + up_write(&kvm->arch.apicv_update_lock); +} + int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu, struct kvm_guest_debug *dbg) { @@ -10616,6 +10693,8 @@ int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu, static_call(kvm_x86_update_exception_bitmap)(vcpu); + kvm_arch_vcpu_guestdbg_update_apicv_inhibit(vcpu->kvm); + r = 0; out: @@ -10859,11 +10938,8 @@ void kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu) void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu) { - struct gfn_to_pfn_cache *cache = &vcpu->arch.st.cache; int idx; - kvm_release_pfn(cache->pfn, cache->dirty, cache); - kvmclock_reset(vcpu); static_call(kvm_x86_vcpu_free)(vcpu); @@ -12275,7 +12351,8 @@ int kvm_handle_invpcid(struct kvm_vcpu *vcpu, unsigned long type, gva_t gva) return kvm_skip_emulated_instruction(vcpu); default: - BUG(); /* We have already checked above that type <= 3 */ + kvm_inject_gp(vcpu, 0); + return 1; } } EXPORT_SYMBOL_GPL(kvm_handle_invpcid); diff --git a/arch/x86/mm/mem_encrypt.c b/arch/x86/mm/mem_encrypt.c index 23d54b810f08..35487305d8af 100644 --- a/arch/x86/mm/mem_encrypt.c +++ b/arch/x86/mm/mem_encrypt.c @@ -229,28 +229,75 @@ void __init sev_setup_arch(void) swiotlb_adjust_size(size); } -static void __init __set_clr_pte_enc(pte_t *kpte, int level, bool enc) +static unsigned long pg_level_to_pfn(int level, pte_t *kpte, pgprot_t *ret_prot) { - pgprot_t old_prot, new_prot; - unsigned long pfn, pa, size; - pte_t new_pte; + unsigned long pfn = 0; + pgprot_t prot; switch (level) { case PG_LEVEL_4K: pfn = pte_pfn(*kpte); - old_prot = pte_pgprot(*kpte); + prot = pte_pgprot(*kpte); break; case PG_LEVEL_2M: pfn = pmd_pfn(*(pmd_t *)kpte); - old_prot = pmd_pgprot(*(pmd_t *)kpte); + prot = pmd_pgprot(*(pmd_t *)kpte); break; case PG_LEVEL_1G: pfn = pud_pfn(*(pud_t *)kpte); - old_prot = pud_pgprot(*(pud_t *)kpte); + prot = pud_pgprot(*(pud_t *)kpte); break; default: - return; + WARN_ONCE(1, "Invalid level for kpte\n"); + return 0; + } + + if (ret_prot) + *ret_prot = prot; + + return pfn; +} + +void notify_range_enc_status_changed(unsigned long vaddr, int npages, bool enc) +{ +#ifdef CONFIG_PARAVIRT + unsigned long sz = npages << PAGE_SHIFT; + unsigned long vaddr_end = vaddr + sz; + + while (vaddr < vaddr_end) { + int psize, pmask, level; + unsigned long pfn; + pte_t *kpte; + + kpte = lookup_address(vaddr, &level); + if (!kpte || pte_none(*kpte)) { + WARN_ONCE(1, "kpte lookup for vaddr\n"); + return; + } + + pfn = pg_level_to_pfn(level, kpte, NULL); + if (!pfn) + continue; + + psize = page_level_size(level); + pmask = page_level_mask(level); + + notify_page_enc_status_changed(pfn, psize >> PAGE_SHIFT, enc); + + vaddr = (vaddr & pmask) + psize; } +#endif +} + +static void __init __set_clr_pte_enc(pte_t *kpte, int level, bool enc) +{ + pgprot_t old_prot, new_prot; + unsigned long pfn, pa, size; + pte_t new_pte; + + pfn = pg_level_to_pfn(level, kpte, &old_prot); + if (!pfn) + return; new_prot = old_prot; if (enc) @@ -286,12 +333,13 @@ static void __init __set_clr_pte_enc(pte_t *kpte, int level, bool enc) static int __init early_set_memory_enc_dec(unsigned long vaddr, unsigned long size, bool enc) { - unsigned long vaddr_end, vaddr_next; + unsigned long vaddr_end, vaddr_next, start; unsigned long psize, pmask; int split_page_size_mask; int level, ret; pte_t *kpte; + start = vaddr; vaddr_next = vaddr; vaddr_end = vaddr + size; @@ -346,6 +394,7 @@ static int __init early_set_memory_enc_dec(unsigned long vaddr, ret = 0; + notify_range_enc_status_changed(start, PAGE_ALIGN(size) >> PAGE_SHIFT, enc); out: __flush_tlb_all(); return ret; @@ -361,6 +410,11 @@ int __init early_set_memory_encrypted(unsigned long vaddr, unsigned long size) return early_set_memory_enc_dec(vaddr, size, true); } +void __init early_set_mem_enc_dec_hypercall(unsigned long vaddr, int npages, bool enc) +{ + notify_range_enc_status_changed(vaddr, npages, enc); +} + /* Override for DMA direct allocation check - ARCH_HAS_FORCE_DMA_UNENCRYPTED */ bool force_dma_unencrypted(struct device *dev) { diff --git a/arch/x86/mm/pat/set_memory.c b/arch/x86/mm/pat/set_memory.c index 934dc5b2df36..b4072115c8ef 100644 --- a/arch/x86/mm/pat/set_memory.c +++ b/arch/x86/mm/pat/set_memory.c @@ -2023,6 +2023,12 @@ static int __set_memory_enc_pgtable(unsigned long addr, int numpages, bool enc) */ cpa_flush(&cpa, 0); + /* + * Notify hypervisor that a given memory range is mapped encrypted + * or decrypted. + */ + notify_range_enc_status_changed(addr, numpages, enc); + return ret; } diff --git a/arch/x86/xen/smp_pv.c b/arch/x86/xen/smp_pv.c index 9e55bcbfcd33..6a8f3b53ab83 100644 --- a/arch/x86/xen/smp_pv.c +++ b/arch/x86/xen/smp_pv.c @@ -225,7 +225,6 @@ static void __init xen_pv_smp_prepare_boot_cpu(void) static void __init xen_pv_smp_prepare_cpus(unsigned int max_cpus) { unsigned cpu; - unsigned int i; if (skip_ioapic_setup) { char *m = (max_cpus == 0) ? @@ -238,16 +237,9 @@ static void __init xen_pv_smp_prepare_cpus(unsigned int max_cpus) } xen_init_lock_cpu(0); - smp_store_boot_cpu_info(); - cpu_data(0).x86_max_cores = 1; + smp_prepare_cpus_common(); - for_each_possible_cpu(i) { - zalloc_cpumask_var(&per_cpu(cpu_sibling_map, i), GFP_KERNEL); - zalloc_cpumask_var(&per_cpu(cpu_core_map, i), GFP_KERNEL); - zalloc_cpumask_var(&per_cpu(cpu_die_map, i), GFP_KERNEL); - zalloc_cpumask_var(&per_cpu(cpu_llc_shared_map, i), GFP_KERNEL); - } - set_cpu_sibling_map(0); + cpu_data(0).x86_max_cores = 1; speculative_store_bypass_ht_init(); |