diff options
Diffstat (limited to 'arch/x86')
123 files changed, 2306 insertions, 1398 deletions
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 9d16fee6bdb8..1d7122a1883e 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -34,6 +34,7 @@ config X86_64 select SWIOTLB select ARCH_HAS_ELFCORE_COMPAT select ZONE_DMA32 + select EXECMEM if DYNAMIC_FTRACE config FORCE_DYNAMIC_FTRACE def_bool y @@ -84,6 +85,7 @@ config X86 select ARCH_HAS_FORTIFY_SOURCE select ARCH_HAS_GCOV_PROFILE_ALL select ARCH_HAS_KCOV if X86_64 + select ARCH_HAS_KERNEL_FPU_SUPPORT select ARCH_HAS_MEM_ENCRYPT select ARCH_HAS_MEMBARRIER_SYNC_CORE select ARCH_HAS_NMI_SAFE_THIS_CPU_OPS @@ -223,7 +225,7 @@ config X86 select HAVE_EFFICIENT_UNALIGNED_ACCESS select HAVE_EISA select HAVE_EXIT_THREAD - select HAVE_FAST_GUP + select HAVE_GUP_FAST select HAVE_FENTRY if X86_64 || DYNAMIC_FTRACE select HAVE_FTRACE_MCOUNT_RECORD select HAVE_FUNCTION_GRAPH_RETVAL if HAVE_FUNCTION_GRAPH_TRACER diff --git a/arch/x86/Kconfig.debug b/arch/x86/Kconfig.debug index c5d614d28a75..74777a97e394 100644 --- a/arch/x86/Kconfig.debug +++ b/arch/x86/Kconfig.debug @@ -248,6 +248,7 @@ config UNWINDER_ORC config UNWINDER_FRAME_POINTER bool "Frame pointer unwinder" + select ARCH_WANT_FRAME_POINTERS select FRAME_POINTER help This option enables the frame pointer unwinder for unwinding kernel @@ -271,7 +272,3 @@ config UNWINDER_GUESS overhead. endchoice - -config FRAME_POINTER - depends on !UNWINDER_ORC && !UNWINDER_GUESS - bool diff --git a/arch/x86/Makefile b/arch/x86/Makefile index 5ab93fcdd691..801fd85c3ef6 100644 --- a/arch/x86/Makefile +++ b/arch/x86/Makefile @@ -74,6 +74,26 @@ KBUILD_CFLAGS += -mno-sse -mno-mmx -mno-sse2 -mno-3dnow -mno-avx KBUILD_RUSTFLAGS += --target=$(objtree)/scripts/target.json KBUILD_RUSTFLAGS += -Ctarget-feature=-sse,-sse2,-sse3,-ssse3,-sse4.1,-sse4.2,-avx,-avx2 +# +# CFLAGS for compiling floating point code inside the kernel. +# +CC_FLAGS_FPU := -msse -msse2 +ifdef CONFIG_CC_IS_GCC +# Stack alignment mismatch, proceed with caution. +# GCC < 7.1 cannot compile code using `double` and -mpreferred-stack-boundary=3 +# (8B stack alignment). +# See https://gcc.gnu.org/bugzilla/show_bug.cgi?id=53383 +# +# The "-msse" in the first argument is there so that the +# -mpreferred-stack-boundary=3 build error: +# +# -mpreferred-stack-boundary=3 is not between 4 and 12 +# +# can be triggered. Otherwise gcc doesn't complain. +CC_FLAGS_FPU += -mhard-float +CC_FLAGS_FPU += $(call cc-option,-msse -mpreferred-stack-boundary=3,-mpreferred-stack-boundary=4) +endif + ifeq ($(CONFIG_X86_KERNEL_IBT),y) # # Kernel IBT has S_CET.NOTRACK_EN=0, as such the compilers must not generate @@ -258,7 +278,7 @@ drivers-$(CONFIG_PCI) += arch/x86/pci/ # suspend and hibernation support drivers-$(CONFIG_PM) += arch/x86/power/ -drivers-$(CONFIG_FB_CORE) += arch/x86/video/ +drivers-$(CONFIG_VIDEO) += arch/x86/video/ #### # boot loader support. Several targets are kept for legacy purposes diff --git a/arch/x86/boot/Makefile b/arch/x86/boot/Makefile index 3cece19b7473..9cc0ff6e9067 100644 --- a/arch/x86/boot/Makefile +++ b/arch/x86/boot/Makefile @@ -9,19 +9,6 @@ # Changed by many, many contributors over the years. # -# Sanitizer runtimes are unavailable and cannot be linked for early boot code. -KASAN_SANITIZE := n -KCSAN_SANITIZE := n -KMSAN_SANITIZE := n -OBJECT_FILES_NON_STANDARD := y - -# Kernel does not boot with kcov instrumentation here. -# One of the problems observed was insertion of __sanitizer_cov_trace_pc() -# callback into middle of per-cpu data enabling code. Thus the callback observed -# inconsistent state and crashed. We are interested mostly in syscall coverage, -# so boot code is not interesting anyway. -KCOV_INSTRUMENT := n - # If you want to preset the SVGA mode, uncomment the next line and # set SVGA_MODE to whatever number you want. # Set it to -DSVGA_MODE=NORMAL_VGA if you just want the EGA/VGA mode. @@ -69,8 +56,7 @@ KBUILD_CFLAGS := $(REALMODE_CFLAGS) -D_SETUP KBUILD_AFLAGS := $(KBUILD_CFLAGS) -D__ASSEMBLY__ KBUILD_CFLAGS += $(call cc-option,-fmacro-prefix-map=$(srctree)/=) KBUILD_CFLAGS += -fno-asynchronous-unwind-tables -GCOV_PROFILE := n -UBSAN_SANITIZE := n +KBUILD_CFLAGS += $(CONFIG_CC_IMPLICIT_FALLTHROUGH) $(obj)/bzImage: asflags-y := $(SVGA_MODE) @@ -129,7 +115,7 @@ targets += mtools.conf # genimage.sh requires bash, but it also has a bunch of other # external dependencies. quiet_cmd_genimage = GENIMAGE $3 -cmd_genimage = $(BASH) $(srctree)/$(src)/genimage.sh $2 $3 $(obj)/bzImage \ + cmd_genimage = $(BASH) $(src)/genimage.sh $2 $3 $(obj)/bzImage \ $(obj)/mtools.conf '$(FDARGS)' $(FDINITRD) PHONY += bzdisk fdimage fdimage144 fdimage288 hdimage isoimage diff --git a/arch/x86/boot/compressed/Makefile b/arch/x86/boot/compressed/Makefile index e9522c6893be..243ee86cb1b1 100644 --- a/arch/x86/boot/compressed/Makefile +++ b/arch/x86/boot/compressed/Makefile @@ -17,15 +17,6 @@ # (see scripts/Makefile.lib size_append) # compressed vmlinux.bin.all + u32 size of vmlinux.bin.all -# Sanitizer runtimes are unavailable and cannot be linked for early boot code. -KASAN_SANITIZE := n -KCSAN_SANITIZE := n -KMSAN_SANITIZE := n -OBJECT_FILES_NON_STANDARD := y - -# Prevents link failures: __sanitizer_cov_trace_pc() is not linked in. -KCOV_INSTRUMENT := n - targets := vmlinux vmlinux.bin vmlinux.bin.gz vmlinux.bin.bz2 vmlinux.bin.lzma \ vmlinux.bin.xz vmlinux.bin.lzo vmlinux.bin.lz4 vmlinux.bin.zst @@ -59,8 +50,6 @@ KBUILD_CFLAGS += -include $(srctree)/include/linux/hidden.h CFLAGS_sev.o += -I$(objtree)/arch/x86/lib/ KBUILD_AFLAGS := $(KBUILD_CFLAGS) -D__ASSEMBLY__ -GCOV_PROFILE := n -UBSAN_SANITIZE :=n KBUILD_LDFLAGS := -m elf_$(UTS_MACHINE) KBUILD_LDFLAGS += $(call ld-option,--no-ld-generated-unwind-info) diff --git a/arch/x86/boot/printf.c b/arch/x86/boot/printf.c index 1237beeb9540..51dc14b714f6 100644 --- a/arch/x86/boot/printf.c +++ b/arch/x86/boot/printf.c @@ -246,6 +246,7 @@ int vsprintf(char *buf, const char *fmt, va_list args) case 'x': flags |= SMALL; + fallthrough; case 'X': base = 16; break; @@ -253,6 +254,8 @@ int vsprintf(char *buf, const char *fmt, va_list args) case 'd': case 'i': flags |= SIGN; + break; + case 'u': break; diff --git a/arch/x86/crypto/aesni-intel_glue.c b/arch/x86/crypto/aesni-intel_glue.c index 5b25d2a58aeb..ef031655b2d3 100644 --- a/arch/x86/crypto/aesni-intel_glue.c +++ b/arch/x86/crypto/aesni-intel_glue.c @@ -1223,14 +1223,14 @@ DEFINE_XTS_ALG(vaes_avx10_512, "xts-aes-vaes-avx10_512", 800); * implementation with ymm registers (256-bit vectors) will be used instead. */ static const struct x86_cpu_id zmm_exclusion_list[] = { - { .vendor = X86_VENDOR_INTEL, .family = 6, .model = INTEL_FAM6_SKYLAKE_X }, - { .vendor = X86_VENDOR_INTEL, .family = 6, .model = INTEL_FAM6_ICELAKE_X }, - { .vendor = X86_VENDOR_INTEL, .family = 6, .model = INTEL_FAM6_ICELAKE_D }, - { .vendor = X86_VENDOR_INTEL, .family = 6, .model = INTEL_FAM6_ICELAKE }, - { .vendor = X86_VENDOR_INTEL, .family = 6, .model = INTEL_FAM6_ICELAKE_L }, - { .vendor = X86_VENDOR_INTEL, .family = 6, .model = INTEL_FAM6_ICELAKE_NNPI }, - { .vendor = X86_VENDOR_INTEL, .family = 6, .model = INTEL_FAM6_TIGERLAKE_L }, - { .vendor = X86_VENDOR_INTEL, .family = 6, .model = INTEL_FAM6_TIGERLAKE }, + X86_MATCH_VFM(INTEL_SKYLAKE_X, 0), + X86_MATCH_VFM(INTEL_ICELAKE_X, 0), + X86_MATCH_VFM(INTEL_ICELAKE_D, 0), + X86_MATCH_VFM(INTEL_ICELAKE, 0), + X86_MATCH_VFM(INTEL_ICELAKE_L, 0), + X86_MATCH_VFM(INTEL_ICELAKE_NNPI, 0), + X86_MATCH_VFM(INTEL_TIGERLAKE_L, 0), + X86_MATCH_VFM(INTEL_TIGERLAKE, 0), /* Allow Rocket Lake and later, and Sapphire Rapids and later. */ /* Also allow AMD CPUs (starting with Zen 4, the first with AVX-512). */ {}, diff --git a/arch/x86/entry/syscalls/syscall_32.tbl b/arch/x86/entry/syscalls/syscall_32.tbl index 5f8591ce7f25..7fd1f57ad3d3 100644 --- a/arch/x86/entry/syscalls/syscall_32.tbl +++ b/arch/x86/entry/syscalls/syscall_32.tbl @@ -466,3 +466,4 @@ 459 i386 lsm_get_self_attr sys_lsm_get_self_attr 460 i386 lsm_set_self_attr sys_lsm_set_self_attr 461 i386 lsm_list_modules sys_lsm_list_modules +462 i386 mseal sys_mseal diff --git a/arch/x86/entry/syscalls/syscall_64.tbl b/arch/x86/entry/syscalls/syscall_64.tbl index cc78226ffc35..a396f6e6ab5b 100644 --- a/arch/x86/entry/syscalls/syscall_64.tbl +++ b/arch/x86/entry/syscalls/syscall_64.tbl @@ -383,6 +383,7 @@ 459 common lsm_get_self_attr sys_lsm_get_self_attr 460 common lsm_set_self_attr sys_lsm_set_self_attr 461 common lsm_list_modules sys_lsm_list_modules +462 common mseal sys_mseal # # Due to a historical design error, certain syscalls are numbered differently diff --git a/arch/x86/entry/vdso/Makefile b/arch/x86/entry/vdso/Makefile index 3d64bcc403cf..215a1b202a91 100644 --- a/arch/x86/entry/vdso/Makefile +++ b/arch/x86/entry/vdso/Makefile @@ -6,20 +6,6 @@ # Include the generic Makefile to check the built vDSO: include $(srctree)/lib/vdso/Makefile -# Sanitizer runtimes are unavailable and cannot be linked here. -KASAN_SANITIZE := n -KMSAN_SANITIZE_vclock_gettime.o := n -KMSAN_SANITIZE_vdso32/vclock_gettime.o := n -KMSAN_SANITIZE_vgetcpu.o := n -KMSAN_SANITIZE_vdso32/vgetcpu.o := n - -UBSAN_SANITIZE := n -KCSAN_SANITIZE := n -OBJECT_FILES_NON_STANDARD := y - -# Prevents link failures: __sanitizer_cov_trace_pc() is not linked in. -KCOV_INSTRUMENT := n - # Files to link into the vDSO: vobjs-y := vdso-note.o vclock_gettime.o vgetcpu.o vobjs32-y := vdso32/note.o vdso32/system_call.o vdso32/sigreturn.o @@ -28,23 +14,12 @@ vobjs-$(CONFIG_X86_SGX) += vsgx.o # Files to link into the kernel: obj-y += vma.o extable.o -KASAN_SANITIZE_vma.o := y -UBSAN_SANITIZE_vma.o := y -KCSAN_SANITIZE_vma.o := y - -OBJECT_FILES_NON_STANDARD_vma.o := n -OBJECT_FILES_NON_STANDARD_extable.o := n # vDSO images to build: obj-$(CONFIG_X86_64) += vdso-image-64.o obj-$(CONFIG_X86_X32_ABI) += vdso-image-x32.o obj-$(CONFIG_COMPAT_32) += vdso-image-32.o vdso32-setup.o -OBJECT_FILES_NON_STANDARD_vdso-image-32.o := n -OBJECT_FILES_NON_STANDARD_vdso-image-x32.o := n -OBJECT_FILES_NON_STANDARD_vdso-image-64.o := n -OBJECT_FILES_NON_STANDARD_vdso32-setup.o := n - vobjs := $(addprefix $(obj)/, $(vobjs-y)) vobjs32 := $(addprefix $(obj)/, $(vobjs32-y)) @@ -176,11 +151,10 @@ quiet_cmd_vdso = VDSO $@ cmd_vdso = $(LD) -o $@ \ $(VDSO_LDFLAGS) $(VDSO_LDFLAGS_$(filter %.lds,$(^F))) \ -T $(filter %.lds,$^) $(filter %.o,$^) && \ - sh $(srctree)/$(src)/checkundef.sh '$(NM)' '$@' + sh $(src)/checkundef.sh '$(NM)' '$@' VDSO_LDFLAGS = -shared --hash-style=both --build-id=sha1 \ $(call ld-option, --eh-frame-hdr) -Bsymbolic -z noexecstack -GCOV_PROFILE := n quiet_cmd_vdso_and_check = VDSO $@ cmd_vdso_and_check = $(cmd_vdso); $(cmd_vdso_check) diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index 768d1414897f..38c1b1f1deaa 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -5645,18 +5645,11 @@ lbr_is_visible(struct kobject *kobj, struct attribute *attr, int i) static char pmu_name_str[30]; -static ssize_t pmu_name_show(struct device *cdev, - struct device_attribute *attr, - char *buf) -{ - return snprintf(buf, PAGE_SIZE, "%s\n", pmu_name_str); -} - -static DEVICE_ATTR_RO(pmu_name); +static DEVICE_STRING_ATTR_RO(pmu_name, 0444, pmu_name_str); static struct attribute *intel_pmu_caps_attrs[] = { - &dev_attr_pmu_name.attr, - NULL + &dev_attr_pmu_name.attr.attr, + NULL }; static DEVICE_ATTR(allow_tsx_force_abort, 0644, diff --git a/arch/x86/events/intel/cstate.c b/arch/x86/events/intel/cstate.c index 54eb142810fb..9d6e8f13d13a 100644 --- a/arch/x86/events/intel/cstate.c +++ b/arch/x86/events/intel/cstate.c @@ -114,6 +114,7 @@ #include "../perf_event.h" #include "../probe.h" +MODULE_DESCRIPTION("Support for Intel cstate performance events"); MODULE_LICENSE("GPL"); #define DEFINE_CSTATE_FORMAT_ATTR(_var, _name, _format) \ @@ -143,12 +144,6 @@ struct cstate_model { #define SLM_PKG_C6_USE_C7_MSR (1UL << 0) #define KNL_CORE_C6_MSR (1UL << 1) -struct perf_cstate_msr { - u64 msr; - struct perf_pmu_events_attr *attr; -}; - - /* cstate_core PMU */ static struct pmu cstate_core_pmu; static bool has_cstate_core; diff --git a/arch/x86/events/intel/uncore.c b/arch/x86/events/intel/uncore.c index 419c517b8594..c68f5b39952b 100644 --- a/arch/x86/events/intel/uncore.c +++ b/arch/x86/events/intel/uncore.c @@ -34,6 +34,7 @@ static struct event_constraint uncore_constraint_fixed = struct event_constraint uncore_constraint_empty = EVENT_CONSTRAINT(0, 0, 0); +MODULE_DESCRIPTION("Support for Intel uncore performance events"); MODULE_LICENSE("GPL"); int uncore_pcibus_to_dieid(struct pci_bus *bus) diff --git a/arch/x86/events/rapl.c b/arch/x86/events/rapl.c index ca5f687fa420..0c5e7a7c43ac 100644 --- a/arch/x86/events/rapl.c +++ b/arch/x86/events/rapl.c @@ -64,6 +64,7 @@ #include "perf_event.h" #include "probe.h" +MODULE_DESCRIPTION("Support Intel/AMD RAPL energy consumption counters"); MODULE_LICENSE("GPL"); /* @@ -114,8 +115,8 @@ struct rapl_pmu { struct rapl_pmus { struct pmu pmu; - unsigned int maxdie; - struct rapl_pmu *pmus[] __counted_by(maxdie); + unsigned int nr_rapl_pmu; + struct rapl_pmu *pmus[] __counted_by(nr_rapl_pmu); }; enum rapl_unit_quirk { @@ -141,13 +142,13 @@ static struct perf_msr *rapl_msrs; static inline struct rapl_pmu *cpu_to_rapl_pmu(unsigned int cpu) { - unsigned int dieid = topology_logical_die_id(cpu); + unsigned int rapl_pmu_idx = topology_logical_die_id(cpu); /* * The unsigned check also catches the '-1' return value for non * existent mappings in the topology map. */ - return dieid < rapl_pmus->maxdie ? rapl_pmus->pmus[dieid] : NULL; + return rapl_pmu_idx < rapl_pmus->nr_rapl_pmu ? rapl_pmus->pmus[rapl_pmu_idx] : NULL; } static inline u64 rapl_read_counter(struct perf_event *event) @@ -658,7 +659,7 @@ static void cleanup_rapl_pmus(void) { int i; - for (i = 0; i < rapl_pmus->maxdie; i++) + for (i = 0; i < rapl_pmus->nr_rapl_pmu; i++) kfree(rapl_pmus->pmus[i]); kfree(rapl_pmus); } @@ -674,13 +675,13 @@ static const struct attribute_group *rapl_attr_update[] = { static int __init init_rapl_pmus(void) { - int maxdie = topology_max_packages() * topology_max_dies_per_package(); + int nr_rapl_pmu = topology_max_packages() * topology_max_dies_per_package(); - rapl_pmus = kzalloc(struct_size(rapl_pmus, pmus, maxdie), GFP_KERNEL); + rapl_pmus = kzalloc(struct_size(rapl_pmus, pmus, nr_rapl_pmu), GFP_KERNEL); if (!rapl_pmus) return -ENOMEM; - rapl_pmus->maxdie = maxdie; + rapl_pmus->nr_rapl_pmu = nr_rapl_pmu; rapl_pmus->pmu.attr_groups = rapl_attr_groups; rapl_pmus->pmu.attr_update = rapl_attr_update; rapl_pmus->pmu.task_ctx_nr = perf_invalid_context; diff --git a/arch/x86/include/asm/acpi.h b/arch/x86/include/asm/acpi.h index f896eed4516c..5af926c050f0 100644 --- a/arch/x86/include/asm/acpi.h +++ b/arch/x86/include/asm/acpi.h @@ -56,6 +56,8 @@ static inline void disable_acpi(void) extern int acpi_gsi_to_irq(u32 gsi, unsigned int *irq); +extern int acpi_blacklisted(void); + static inline void acpi_noirq_set(void) { acpi_noirq = 1; } static inline void acpi_disable_pci(void) { diff --git a/arch/x86/include/asm/barrier.h b/arch/x86/include/asm/barrier.h index 63bdc6b85219..7b44b3c4cce1 100644 --- a/arch/x86/include/asm/barrier.h +++ b/arch/x86/include/asm/barrier.h @@ -33,20 +33,16 @@ * Returns: * 0 - (index < size) */ -static __always_inline unsigned long array_index_mask_nospec(unsigned long index, - unsigned long size) -{ - unsigned long mask; - - asm volatile ("cmp %1,%2; sbb %0,%0;" - :"=r" (mask) - :"g"(size),"r" (index) - :"cc"); - return mask; -} - -/* Override the default implementation from linux/nospec.h. */ -#define array_index_mask_nospec array_index_mask_nospec +#define array_index_mask_nospec(idx,sz) ({ \ + typeof((idx)+(sz)) __idx = (idx); \ + typeof(__idx) __sz = (sz); \ + unsigned long __mask; \ + asm volatile ("cmp %1,%2; sbb %0,%0" \ + :"=r" (__mask) \ + :ASM_INPUT_G (__sz), \ + "r" (__idx) \ + :"cc"); \ + __mask; }) /* Prevent speculative execution past this barrier. */ #define barrier_nospec() alternative("", "lfence", X86_FEATURE_LFENCE_RDTSC) diff --git a/arch/x86/include/asm/bitops.h b/arch/x86/include/asm/bitops.h index 990eb686ca67..b96d45944c59 100644 --- a/arch/x86/include/asm/bitops.h +++ b/arch/x86/include/asm/bitops.h @@ -250,7 +250,7 @@ static __always_inline unsigned long variable__ffs(unsigned long word) { asm("rep; bsf %1,%0" : "=r" (word) - : "rm" (word)); + : ASM_INPUT_RM (word)); return word; } @@ -297,7 +297,7 @@ static __always_inline unsigned long __fls(unsigned long word) asm("bsr %1,%0" : "=r" (word) - : "rm" (word)); + : ASM_INPUT_RM (word)); return word; } @@ -320,7 +320,7 @@ static __always_inline int variable_ffs(int x) */ asm("bsfl %1,%0" : "=r" (r) - : "rm" (x), "0" (-1)); + : ASM_INPUT_RM (x), "0" (-1)); #elif defined(CONFIG_X86_CMOV) asm("bsfl %1,%0\n\t" "cmovzl %2,%0" @@ -377,7 +377,7 @@ static __always_inline int fls(unsigned int x) */ asm("bsrl %1,%0" : "=r" (r) - : "rm" (x), "0" (-1)); + : ASM_INPUT_RM (x), "0" (-1)); #elif defined(CONFIG_X86_CMOV) asm("bsrl %1,%0\n\t" "cmovzl %2,%0" @@ -416,7 +416,7 @@ static __always_inline int fls64(__u64 x) */ asm("bsrq %1,%q0" : "+r" (bitpos) - : "rm" (x)); + : ASM_INPUT_RM (x)); return bitpos + 1; } #else diff --git a/arch/x86/include/asm/cpu_device_id.h b/arch/x86/include/asm/cpu_device_id.h index 970a232009c3..b6325ee30871 100644 --- a/arch/x86/include/asm/cpu_device_id.h +++ b/arch/x86/include/asm/cpu_device_id.h @@ -53,6 +53,9 @@ #define X86_CENTAUR_FAM6_C7_D 0xd #define X86_CENTAUR_FAM6_NANO 0xf +/* x86_cpu_id::flags */ +#define X86_CPU_ID_FLAG_ENTRY_VALID BIT(0) + #define X86_STEPPINGS(mins, maxs) GENMASK(maxs, mins) /** * X86_MATCH_VENDOR_FAM_MODEL_STEPPINGS_FEATURE - Base macro for CPU matching @@ -79,6 +82,7 @@ .model = _model, \ .steppings = _steppings, \ .feature = _feature, \ + .flags = X86_CPU_ID_FLAG_ENTRY_VALID, \ .driver_data = (unsigned long) _data \ } @@ -89,6 +93,7 @@ .model = _model, \ .steppings = _steppings, \ .feature = _feature, \ + .flags = X86_CPU_ID_FLAG_ENTRY_VALID, \ .driver_data = (unsigned long) _data \ } diff --git a/arch/x86/include/asm/fb.h b/arch/x86/include/asm/fb.h deleted file mode 100644 index c3b9582de7ef..000000000000 --- a/arch/x86/include/asm/fb.h +++ /dev/null @@ -1,19 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _ASM_X86_FB_H -#define _ASM_X86_FB_H - -#include <asm/page.h> - -struct fb_info; - -pgprot_t pgprot_framebuffer(pgprot_t prot, - unsigned long vm_start, unsigned long vm_end, - unsigned long offset); -#define pgprot_framebuffer pgprot_framebuffer - -int fb_is_primary_device(struct fb_info *info); -#define fb_is_primary_device fb_is_primary_device - -#include <asm-generic/fb.h> - -#endif /* _ASM_X86_FB_H */ diff --git a/arch/x86/include/asm/fpu.h b/arch/x86/include/asm/fpu.h new file mode 100644 index 000000000000..b2743fe19339 --- /dev/null +++ b/arch/x86/include/asm/fpu.h @@ -0,0 +1,13 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2023 SiFive + */ + +#ifndef _ASM_X86_FPU_H +#define _ASM_X86_FPU_H + +#include <asm/fpu/api.h> + +#define kernel_fpu_available() true + +#endif /* ! _ASM_X86_FPU_H */ diff --git a/arch/x86/include/asm/fpu/api.h b/arch/x86/include/asm/fpu/api.h index a2be3aefff9f..f86ad3335529 100644 --- a/arch/x86/include/asm/fpu/api.h +++ b/arch/x86/include/asm/fpu/api.h @@ -143,6 +143,9 @@ extern void fpstate_clear_xstate_component(struct fpstate *fps, unsigned int xfe extern u64 xstate_get_guest_group_perm(void); +extern void *get_xsave_addr(struct xregs_state *xsave, int xfeature_nr); + + /* KVM specific functions */ extern bool fpu_alloc_guest_fpstate(struct fpu_guest *gfpu); extern void fpu_free_guest_fpstate(struct fpu_guest *gfpu); diff --git a/arch/x86/include/asm/fpu/types.h b/arch/x86/include/asm/fpu/types.h index ace9aa3b78a3..eb17f31b06d2 100644 --- a/arch/x86/include/asm/fpu/types.h +++ b/arch/x86/include/asm/fpu/types.h @@ -2,8 +2,8 @@ /* * FPU data structures: */ -#ifndef _ASM_X86_FPU_H -#define _ASM_X86_FPU_H +#ifndef _ASM_X86_FPU_TYPES_H +#define _ASM_X86_FPU_TYPES_H #include <asm/page_types.h> @@ -596,4 +596,4 @@ struct fpu_state_config { /* FPU state configuration information */ extern struct fpu_state_config fpu_kernel_cfg, fpu_user_cfg; -#endif /* _ASM_X86_FPU_H */ +#endif /* _ASM_X86_FPU_TYPES_H */ diff --git a/arch/x86/include/asm/inat.h b/arch/x86/include/asm/inat.h index b56c5741581a..53e4015242b4 100644 --- a/arch/x86/include/asm/inat.h +++ b/arch/x86/include/asm/inat.h @@ -35,6 +35,8 @@ #define INAT_PFX_VEX2 13 /* 2-bytes VEX prefix */ #define INAT_PFX_VEX3 14 /* 3-bytes VEX prefix */ #define INAT_PFX_EVEX 15 /* EVEX prefix */ +/* x86-64 REX2 prefix */ +#define INAT_PFX_REX2 16 /* 0xD5 */ #define INAT_LSTPFX_MAX 3 #define INAT_LGCPFX_MAX 11 @@ -50,7 +52,7 @@ /* Legacy prefix */ #define INAT_PFX_OFFS 0 -#define INAT_PFX_BITS 4 +#define INAT_PFX_BITS 5 #define INAT_PFX_MAX ((1 << INAT_PFX_BITS) - 1) #define INAT_PFX_MASK (INAT_PFX_MAX << INAT_PFX_OFFS) /* Escape opcodes */ @@ -77,6 +79,9 @@ #define INAT_VEXOK (1 << (INAT_FLAG_OFFS + 5)) #define INAT_VEXONLY (1 << (INAT_FLAG_OFFS + 6)) #define INAT_EVEXONLY (1 << (INAT_FLAG_OFFS + 7)) +#define INAT_NO_REX2 (1 << (INAT_FLAG_OFFS + 8)) +#define INAT_REX2_VARIANT (1 << (INAT_FLAG_OFFS + 9)) +#define INAT_EVEX_SCALABLE (1 << (INAT_FLAG_OFFS + 10)) /* Attribute making macros for attribute tables */ #define INAT_MAKE_PREFIX(pfx) (pfx << INAT_PFX_OFFS) #define INAT_MAKE_ESCAPE(esc) (esc << INAT_ESC_OFFS) @@ -128,6 +133,11 @@ static inline int inat_is_rex_prefix(insn_attr_t attr) return (attr & INAT_PFX_MASK) == INAT_PFX_REX; } +static inline int inat_is_rex2_prefix(insn_attr_t attr) +{ + return (attr & INAT_PFX_MASK) == INAT_PFX_REX2; +} + static inline int inat_last_prefix_id(insn_attr_t attr) { if ((attr & INAT_PFX_MASK) > INAT_LSTPFX_MAX) @@ -227,4 +237,9 @@ static inline int inat_must_evex(insn_attr_t attr) { return attr & INAT_EVEXONLY; } + +static inline int inat_evex_scalable(insn_attr_t attr) +{ + return attr & INAT_EVEX_SCALABLE; +} #endif diff --git a/arch/x86/include/asm/insn.h b/arch/x86/include/asm/insn.h index 1b29f58f730f..7152ea809e6a 100644 --- a/arch/x86/include/asm/insn.h +++ b/arch/x86/include/asm/insn.h @@ -112,10 +112,15 @@ struct insn { #define X86_SIB_INDEX(sib) (((sib) & 0x38) >> 3) #define X86_SIB_BASE(sib) ((sib) & 0x07) -#define X86_REX_W(rex) ((rex) & 8) -#define X86_REX_R(rex) ((rex) & 4) -#define X86_REX_X(rex) ((rex) & 2) -#define X86_REX_B(rex) ((rex) & 1) +#define X86_REX2_M(rex) ((rex) & 0x80) /* REX2 M0 */ +#define X86_REX2_R(rex) ((rex) & 0x40) /* REX2 R4 */ +#define X86_REX2_X(rex) ((rex) & 0x20) /* REX2 X4 */ +#define X86_REX2_B(rex) ((rex) & 0x10) /* REX2 B4 */ + +#define X86_REX_W(rex) ((rex) & 8) /* REX or REX2 W */ +#define X86_REX_R(rex) ((rex) & 4) /* REX or REX2 R3 */ +#define X86_REX_X(rex) ((rex) & 2) /* REX or REX2 X3 */ +#define X86_REX_B(rex) ((rex) & 1) /* REX or REX2 B3 */ /* VEX bit flags */ #define X86_VEX_W(vex) ((vex) & 0x80) /* VEX3 Byte2 */ @@ -161,6 +166,18 @@ static inline void insn_get_attribute(struct insn *insn) /* Instruction uses RIP-relative addressing */ extern int insn_rip_relative(struct insn *insn); +static inline int insn_is_rex2(struct insn *insn) +{ + if (!insn->prefixes.got) + insn_get_prefixes(insn); + return insn->rex_prefix.nbytes == 2; +} + +static inline insn_byte_t insn_rex2_m_bit(struct insn *insn) +{ + return X86_REX2_M(insn->rex_prefix.bytes[1]); +} + static inline int insn_is_avx(struct insn *insn) { if (!insn->prefixes.got) @@ -198,6 +215,13 @@ static inline insn_byte_t insn_vex_p_bits(struct insn *insn) return X86_VEX_P(insn->vex_prefix.bytes[2]); } +static inline insn_byte_t insn_vex_w_bit(struct insn *insn) +{ + if (insn->vex_prefix.nbytes < 3) + return 0; + return X86_VEX_W(insn->vex_prefix.bytes[2]); +} + /* Get the last prefix id from last prefix or VEX prefix */ static inline int insn_last_prefix_id(struct insn *insn) { diff --git a/arch/x86/include/asm/io.h b/arch/x86/include/asm/io.h index 294cd2a40818..1d60427379c9 100644 --- a/arch/x86/include/asm/io.h +++ b/arch/x86/include/asm/io.h @@ -42,6 +42,7 @@ #include <asm/early_ioremap.h> #include <asm/pgtable_types.h> #include <asm/shared/io.h> +#include <asm/special_insns.h> #define build_mmio_read(name, size, type, reg, barrier) \ static inline type name(const volatile void __iomem *addr) \ @@ -209,6 +210,23 @@ void memset_io(volatile void __iomem *, int, size_t); #define memcpy_toio memcpy_toio #define memset_io memset_io +#ifdef CONFIG_X86_64 +/* + * Commit 0f07496144c2 ("[PATCH] Add faster __iowrite32_copy routine for + * x86_64") says that circa 2006 rep movsl is noticeably faster than a copy + * loop. + */ +static inline void __iowrite32_copy(void __iomem *to, const void *from, + size_t count) +{ + asm volatile("rep ; movsl" + : "=&c"(count), "=&D"(to), "=&S"(from) + : "0"(count), "1"(to), "2"(from) + : "memory"); +} +#define __iowrite32_copy __iowrite32_copy +#endif + /* * ISA space is 'always mapped' on a typical x86 system, no need to * explicitly ioremap() it. The fact that the ISA IO space is mapped diff --git a/arch/x86/include/asm/kexec.h b/arch/x86/include/asm/kexec.h index 91ca9a9ee3a2..ae5482a2f0ca 100644 --- a/arch/x86/include/asm/kexec.h +++ b/arch/x86/include/asm/kexec.h @@ -207,18 +207,11 @@ int arch_kimage_file_post_load_cleanup(struct kimage *image); extern void kdump_nmi_shootdown_cpus(void); #ifdef CONFIG_CRASH_HOTPLUG -void arch_crash_handle_hotplug_event(struct kimage *image); +void arch_crash_handle_hotplug_event(struct kimage *image, void *arg); #define arch_crash_handle_hotplug_event arch_crash_handle_hotplug_event -#ifdef CONFIG_HOTPLUG_CPU -int arch_crash_hotplug_cpu_support(void); -#define crash_hotplug_cpu_support arch_crash_hotplug_cpu_support -#endif - -#ifdef CONFIG_MEMORY_HOTPLUG -int arch_crash_hotplug_memory_support(void); -#define crash_hotplug_memory_support arch_crash_hotplug_memory_support -#endif +int arch_crash_hotplug_support(struct kimage *image, unsigned long kexec_flags); +#define arch_crash_hotplug_support arch_crash_hotplug_support unsigned int arch_crash_get_elfcorehdr_size(void); #define crash_get_elfcorehdr_size arch_crash_get_elfcorehdr_size diff --git a/arch/x86/include/asm/kvm-x86-ops.h b/arch/x86/include/asm/kvm-x86-ops.h index 110d7f29ca9a..5187fcf4b610 100644 --- a/arch/x86/include/asm/kvm-x86-ops.h +++ b/arch/x86/include/asm/kvm-x86-ops.h @@ -121,6 +121,7 @@ KVM_X86_OP(enter_smm) KVM_X86_OP(leave_smm) KVM_X86_OP(enable_smi_window) #endif +KVM_X86_OP_OPTIONAL(dev_get_attr) KVM_X86_OP_OPTIONAL(mem_enc_ioctl) KVM_X86_OP_OPTIONAL(mem_enc_register_region) KVM_X86_OP_OPTIONAL(mem_enc_unregister_region) diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 6efd1497b026..ece45b3f6f20 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -254,28 +254,31 @@ enum x86_intercept_stage; KVM_GUESTDBG_INJECT_DB | \ KVM_GUESTDBG_BLOCKIRQ) +#define PFERR_PRESENT_MASK BIT(0) +#define PFERR_WRITE_MASK BIT(1) +#define PFERR_USER_MASK BIT(2) +#define PFERR_RSVD_MASK BIT(3) +#define PFERR_FETCH_MASK BIT(4) +#define PFERR_PK_MASK BIT(5) +#define PFERR_SGX_MASK BIT(15) +#define PFERR_GUEST_RMP_MASK BIT_ULL(31) +#define PFERR_GUEST_FINAL_MASK BIT_ULL(32) +#define PFERR_GUEST_PAGE_MASK BIT_ULL(33) +#define PFERR_GUEST_ENC_MASK BIT_ULL(34) +#define PFERR_GUEST_SIZEM_MASK BIT_ULL(35) +#define PFERR_GUEST_VMPL_MASK BIT_ULL(36) -#define PFERR_PRESENT_BIT 0 -#define PFERR_WRITE_BIT 1 -#define PFERR_USER_BIT 2 -#define PFERR_RSVD_BIT 3 -#define PFERR_FETCH_BIT 4 -#define PFERR_PK_BIT 5 -#define PFERR_SGX_BIT 15 -#define PFERR_GUEST_FINAL_BIT 32 -#define PFERR_GUEST_PAGE_BIT 33 -#define PFERR_IMPLICIT_ACCESS_BIT 48 - -#define PFERR_PRESENT_MASK BIT(PFERR_PRESENT_BIT) -#define PFERR_WRITE_MASK BIT(PFERR_WRITE_BIT) -#define PFERR_USER_MASK BIT(PFERR_USER_BIT) -#define PFERR_RSVD_MASK BIT(PFERR_RSVD_BIT) -#define PFERR_FETCH_MASK BIT(PFERR_FETCH_BIT) -#define PFERR_PK_MASK BIT(PFERR_PK_BIT) -#define PFERR_SGX_MASK BIT(PFERR_SGX_BIT) -#define PFERR_GUEST_FINAL_MASK BIT_ULL(PFERR_GUEST_FINAL_BIT) -#define PFERR_GUEST_PAGE_MASK BIT_ULL(PFERR_GUEST_PAGE_BIT) -#define PFERR_IMPLICIT_ACCESS BIT_ULL(PFERR_IMPLICIT_ACCESS_BIT) +/* + * IMPLICIT_ACCESS is a KVM-defined flag used to correctly perform SMAP checks + * when emulating instructions that triggers implicit access. + */ +#define PFERR_IMPLICIT_ACCESS BIT_ULL(48) +/* + * PRIVATE_ACCESS is a KVM-defined flag us to indicate that a fault occurred + * when the guest was accessing private memory. + */ +#define PFERR_PRIVATE_ACCESS BIT_ULL(49) +#define PFERR_SYNTHETIC_MASK (PFERR_IMPLICIT_ACCESS | PFERR_PRIVATE_ACCESS) #define PFERR_NESTED_GUEST_PAGE (PFERR_GUEST_PAGE_MASK | \ PFERR_WRITE_MASK | \ @@ -994,9 +997,6 @@ struct kvm_vcpu_arch { u64 msr_kvm_poll_control; - /* set at EPT violation at this point */ - unsigned long exit_qualification; - /* pv related host specific info */ struct { bool pv_unhalted; @@ -1280,12 +1280,14 @@ enum kvm_apicv_inhibit { }; struct kvm_arch { - unsigned long vm_type; unsigned long n_used_mmu_pages; unsigned long n_requested_mmu_pages; unsigned long n_max_mmu_pages; unsigned int indirect_shadow_pages; u8 mmu_valid_gen; + u8 vm_type; + bool has_private_mem; + bool has_protected_state; struct hlist_head mmu_page_hash[KVM_NUM_MMU_PAGES]; struct list_head active_mmu_pages; struct list_head zapped_obsolete_pages; @@ -1312,6 +1314,8 @@ struct kvm_arch { */ spinlock_t mmu_unsync_pages_lock; + u64 shadow_mmio_value; + struct iommu_domain *iommu_domain; bool iommu_noncoherent; #define __KVM_HAVE_ARCH_NONCOHERENT_DMA @@ -1779,6 +1783,7 @@ struct kvm_x86_ops { void (*enable_smi_window)(struct kvm_vcpu *vcpu); #endif + int (*dev_get_attr)(u32 group, u64 attr, u64 *val); int (*mem_enc_ioctl)(struct kvm *kvm, void __user *argp); int (*mem_enc_register_region)(struct kvm *kvm, struct kvm_enc_region *argp); int (*mem_enc_unregister_region)(struct kvm *kvm, struct kvm_enc_region *argp); @@ -1844,6 +1849,7 @@ struct kvm_arch_async_pf { gfn_t gfn; unsigned long cr3; bool direct_map; + u64 error_code; }; extern u32 __read_mostly kvm_nr_uret_msrs; @@ -2140,6 +2146,10 @@ static inline void kvm_clear_apicv_inhibit(struct kvm *kvm, kvm_set_or_clear_apicv_inhibit(kvm, reason, false); } +unsigned long __kvm_emulate_hypercall(struct kvm_vcpu *vcpu, unsigned long nr, + unsigned long a0, unsigned long a1, + unsigned long a2, unsigned long a3, + int op_64_bit, int cpl); int kvm_emulate_hypercall(struct kvm_vcpu *vcpu); int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, u64 error_code, @@ -2153,8 +2163,9 @@ void kvm_mmu_new_pgd(struct kvm_vcpu *vcpu, gpa_t new_pgd); void kvm_configure_mmu(bool enable_tdp, int tdp_forced_root_level, int tdp_max_root_level, int tdp_huge_page_level); + #ifdef CONFIG_KVM_PRIVATE_MEM -#define kvm_arch_has_private_mem(kvm) ((kvm)->arch.vm_type != KVM_X86_DEFAULT_VM) +#define kvm_arch_has_private_mem(kvm) ((kvm)->arch.has_private_mem) #else #define kvm_arch_has_private_mem(kvm) false #endif diff --git a/arch/x86/include/asm/mpspec.h b/arch/x86/include/asm/mpspec.h index c72c7ff78fcd..d593e52e6635 100644 --- a/arch/x86/include/asm/mpspec.h +++ b/arch/x86/include/asm/mpspec.h @@ -16,10 +16,10 @@ extern int pic_mode; * Summit or generic (i.e. installer) kernels need lots of bus entries. * Maximum 256 PCI busses, plus 1 ISA bus in each of 4 cabinets. */ -#if CONFIG_BASE_SMALL == 0 -# define MAX_MP_BUSSES 260 -#else +#ifdef CONFIG_BASE_SMALL # define MAX_MP_BUSSES 32 +#else +# define MAX_MP_BUSSES 260 #endif #define MAX_IRQ_SOURCES 256 diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h index 315535ffb258..65b8e5bb902c 100644 --- a/arch/x86/include/asm/pgtable.h +++ b/arch/x86/include/asm/pgtable.h @@ -234,6 +234,7 @@ static inline unsigned long pmd_pfn(pmd_t pmd) return (pfn & pmd_pfn_mask(pmd)) >> PAGE_SHIFT; } +#define pud_pfn pud_pfn static inline unsigned long pud_pfn(pud_t pud) { phys_addr_t pfn = pud_val(pud); @@ -387,23 +388,7 @@ static inline pte_t pte_wrprotect(pte_t pte) #ifdef CONFIG_HAVE_ARCH_USERFAULTFD_WP static inline int pte_uffd_wp(pte_t pte) { - bool wp = pte_flags(pte) & _PAGE_UFFD_WP; - -#ifdef CONFIG_DEBUG_VM - /* - * Having write bit for wr-protect-marked present ptes is fatal, - * because it means the uffd-wp bit will be ignored and write will - * just go through. - * - * Use any chance of pgtable walking to verify this (e.g., when - * page swapped out or being migrated for all purposes). It means - * something is already wrong. Tell the admin even before the - * process crashes. We also nail it with wrong pgtable setup. - */ - WARN_ON_ONCE(wp && pte_write(pte)); -#endif - - return wp; + return pte_flags(pte) & _PAGE_UFFD_WP; } static inline pte_t pte_mkuffd_wp(pte_t pte) @@ -1200,7 +1185,6 @@ static inline int pgd_none(pgd_t pgd) extern int direct_gbpages; void init_mem_mapping(void); void early_alloc_pgt_buf(void); -extern void memblock_find_dma_reserve(void); void __init poking_init(void); unsigned long init_memory_mapping(unsigned long start, unsigned long end, pgprot_t prot); diff --git a/arch/x86/include/asm/pgtable_64.h b/arch/x86/include/asm/pgtable_64.h index 7e9db77231ac..3c4407271d08 100644 --- a/arch/x86/include/asm/pgtable_64.h +++ b/arch/x86/include/asm/pgtable_64.h @@ -245,6 +245,7 @@ extern void cleanup_highmap(void); #define HAVE_ARCH_UNMAPPED_AREA #define HAVE_ARCH_UNMAPPED_AREA_TOPDOWN +#define HAVE_ARCH_UNMAPPED_AREA_VMFLAGS #define PAGE_AGP PAGE_KERNEL_NOCACHE #define HAVE_PAGE_AGP 1 diff --git a/arch/x86/include/asm/sev-common.h b/arch/x86/include/asm/sev-common.h index b463fcbd4b90..5a8246dd532f 100644 --- a/arch/x86/include/asm/sev-common.h +++ b/arch/x86/include/asm/sev-common.h @@ -54,8 +54,10 @@ (((unsigned long)fn) << 32)) /* AP Reset Hold */ -#define GHCB_MSR_AP_RESET_HOLD_REQ 0x006 -#define GHCB_MSR_AP_RESET_HOLD_RESP 0x007 +#define GHCB_MSR_AP_RESET_HOLD_REQ 0x006 +#define GHCB_MSR_AP_RESET_HOLD_RESP 0x007 +#define GHCB_MSR_AP_RESET_HOLD_RESULT_POS 12 +#define GHCB_MSR_AP_RESET_HOLD_RESULT_MASK GENMASK_ULL(51, 0) /* GHCB GPA Register */ #define GHCB_MSR_REG_GPA_REQ 0x012 @@ -99,6 +101,8 @@ enum psc_op { /* GHCB Hypervisor Feature Request/Response */ #define GHCB_MSR_HV_FT_REQ 0x080 #define GHCB_MSR_HV_FT_RESP 0x081 +#define GHCB_MSR_HV_FT_POS 12 +#define GHCB_MSR_HV_FT_MASK GENMASK_ULL(51, 0) #define GHCB_MSR_HV_FT_RESP_VAL(v) \ /* GHCBData[63:12] */ \ (((u64)(v) & GENMASK_ULL(63, 12)) >> 12) diff --git a/arch/x86/include/asm/sparsemem.h b/arch/x86/include/asm/sparsemem.h index 1be13b2dfe8b..64df897c0ee3 100644 --- a/arch/x86/include/asm/sparsemem.h +++ b/arch/x86/include/asm/sparsemem.h @@ -37,8 +37,6 @@ extern int phys_to_target_node(phys_addr_t start); #define phys_to_target_node phys_to_target_node extern int memory_add_physaddr_to_nid(u64 start); #define memory_add_physaddr_to_nid memory_add_physaddr_to_nid -extern int numa_fill_memblks(u64 start, u64 end); -#define numa_fill_memblks numa_fill_memblks #endif #endif /* __ASSEMBLY__ */ diff --git a/arch/x86/include/asm/video.h b/arch/x86/include/asm/video.h new file mode 100644 index 000000000000..0950c9535fae --- /dev/null +++ b/arch/x86/include/asm/video.h @@ -0,0 +1,21 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_VIDEO_H +#define _ASM_X86_VIDEO_H + +#include <linux/types.h> + +#include <asm/page.h> + +struct device; + +pgprot_t pgprot_framebuffer(pgprot_t prot, + unsigned long vm_start, unsigned long vm_end, + unsigned long offset); +#define pgprot_framebuffer pgprot_framebuffer + +bool video_is_primary_device(struct device *dev); +#define video_is_primary_device video_is_primary_device + +#include <asm-generic/video.h> + +#endif /* _ASM_X86_VIDEO_H */ diff --git a/arch/x86/include/asm/vmx.h b/arch/x86/include/asm/vmx.h index 4dba17363008..d77a31039f24 100644 --- a/arch/x86/include/asm/vmx.h +++ b/arch/x86/include/asm/vmx.h @@ -71,6 +71,7 @@ #define SECONDARY_EXEC_ENCLS_EXITING VMCS_CONTROL_BIT(ENCLS_EXITING) #define SECONDARY_EXEC_RDSEED_EXITING VMCS_CONTROL_BIT(RDSEED_EXITING) #define SECONDARY_EXEC_ENABLE_PML VMCS_CONTROL_BIT(PAGE_MOD_LOGGING) +#define SECONDARY_EXEC_EPT_VIOLATION_VE VMCS_CONTROL_BIT(EPT_VIOLATION_VE) #define SECONDARY_EXEC_PT_CONCEAL_VMX VMCS_CONTROL_BIT(PT_CONCEAL_VMX) #define SECONDARY_EXEC_ENABLE_XSAVES VMCS_CONTROL_BIT(XSAVES) #define SECONDARY_EXEC_MODE_BASED_EPT_EXEC VMCS_CONTROL_BIT(MODE_BASED_EPT_EXEC) @@ -226,6 +227,8 @@ enum vmcs_field { VMREAD_BITMAP_HIGH = 0x00002027, VMWRITE_BITMAP = 0x00002028, VMWRITE_BITMAP_HIGH = 0x00002029, + VE_INFORMATION_ADDRESS = 0x0000202A, + VE_INFORMATION_ADDRESS_HIGH = 0x0000202B, XSS_EXIT_BITMAP = 0x0000202C, XSS_EXIT_BITMAP_HIGH = 0x0000202D, ENCLS_EXITING_BITMAP = 0x0000202E, @@ -514,6 +517,7 @@ enum vmcs_field { #define VMX_EPT_IPAT_BIT (1ull << 6) #define VMX_EPT_ACCESS_BIT (1ull << 8) #define VMX_EPT_DIRTY_BIT (1ull << 9) +#define VMX_EPT_SUPPRESS_VE_BIT (1ull << 63) #define VMX_EPT_RWX_MASK (VMX_EPT_READABLE_MASK | \ VMX_EPT_WRITABLE_MASK | \ VMX_EPT_EXECUTABLE_MASK) @@ -630,4 +634,13 @@ enum vmx_l1d_flush_state { extern enum vmx_l1d_flush_state l1tf_vmx_mitigation; +struct vmx_ve_information { + u32 exit_reason; + u32 delivery; + u64 exit_qualification; + u64 guest_linear_address; + u64 guest_physical_address; + u16 eptp_index; +}; + #endif diff --git a/arch/x86/include/uapi/asm/kvm.h b/arch/x86/include/uapi/asm/kvm.h index ef11aa4cab42..9fae1b73b529 100644 --- a/arch/x86/include/uapi/asm/kvm.h +++ b/arch/x86/include/uapi/asm/kvm.h @@ -457,8 +457,13 @@ struct kvm_sync_regs { #define KVM_STATE_VMX_PREEMPTION_TIMER_DEADLINE 0x00000001 -/* attributes for system fd (group 0) */ -#define KVM_X86_XCOMP_GUEST_SUPP 0 +/* vendor-independent attributes for system fd (group 0) */ +#define KVM_X86_GRP_SYSTEM 0 +# define KVM_X86_XCOMP_GUEST_SUPP 0 + +/* vendor-specific groups and attributes for system fd */ +#define KVM_X86_GRP_SEV 1 +# define KVM_X86_SEV_VMSA_FEATURES 0 struct kvm_vmx_nested_state_data { __u8 vmcs12[KVM_STATE_NESTED_VMX_VMCS_SIZE]; @@ -689,6 +694,9 @@ enum sev_cmd_id { /* Guest Migration Extension */ KVM_SEV_SEND_CANCEL, + /* Second time is the charm; improved versions of the above ioctls. */ + KVM_SEV_INIT2, + KVM_SEV_NR_MAX, }; @@ -700,6 +708,14 @@ struct kvm_sev_cmd { __u32 sev_fd; }; +struct kvm_sev_init { + __u64 vmsa_features; + __u32 flags; + __u16 ghcb_version; + __u16 pad1; + __u32 pad2[8]; +}; + struct kvm_sev_launch_start { __u32 handle; __u32 policy; @@ -856,5 +872,7 @@ struct kvm_hyperv_eventfd { #define KVM_X86_DEFAULT_VM 0 #define KVM_X86_SW_PROTECTED_VM 1 +#define KVM_X86_SEV_VM 2 +#define KVM_X86_SEV_ES_VM 3 #endif /* _ASM_X86_KVM_H */ diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile index 5d128167e2e2..20a0dd51700a 100644 --- a/arch/x86/kernel/Makefile +++ b/arch/x86/kernel/Makefile @@ -40,7 +40,7 @@ KMSAN_SANITIZE_sev.o := n KCOV_INSTRUMENT_head$(BITS).o := n KCOV_INSTRUMENT_sev.o := n -CFLAGS_irq.o := -I $(srctree)/$(src)/../include/asm/trace +CFLAGS_irq.o := -I $(src)/../include/asm/trace obj-y += head_$(BITS).o obj-y += head$(BITS).o diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c index 7555c15b7183..89de61243272 100644 --- a/arch/x86/kernel/alternative.c +++ b/arch/x86/kernel/alternative.c @@ -372,7 +372,7 @@ static void __apply_relocation(u8 *buf, const u8 * const instr, size_t instrlen, void apply_relocation(u8 *buf, const u8 * const instr, size_t instrlen, u8 *repl, size_t repl_len) { __apply_relocation(buf, instr, instrlen, repl, repl_len); - optimize_nops(instr, buf, repl_len); + optimize_nops(instr, buf, instrlen); } /* Low-level backend functions usable from alternative code replacements. */ diff --git a/arch/x86/kernel/amd_gart_64.c b/arch/x86/kernel/amd_gart_64.c index 2ae98f754e59..c884deca839b 100644 --- a/arch/x86/kernel/amd_gart_64.c +++ b/arch/x86/kernel/amd_gart_64.c @@ -676,7 +676,7 @@ static const struct dma_map_ops gart_dma_ops = { .get_sgtable = dma_common_get_sgtable, .dma_supported = dma_direct_supported, .get_required_mask = dma_direct_get_required_mask, - .alloc_pages = dma_direct_alloc_pages, + .alloc_pages_op = dma_direct_alloc_pages, .free_pages = dma_direct_free_pages, }; diff --git a/arch/x86/kernel/apic/msi.c b/arch/x86/kernel/apic/msi.c index d9651f15ae4f..340769242dea 100644 --- a/arch/x86/kernel/apic/msi.c +++ b/arch/x86/kernel/apic/msi.c @@ -184,7 +184,6 @@ static int x86_msi_prepare(struct irq_domain *domain, struct device *dev, alloc->type = X86_IRQ_ALLOC_TYPE_PCI_MSI; return 0; case DOMAIN_BUS_PCI_DEVICE_MSIX: - case DOMAIN_BUS_PCI_DEVICE_IMS: alloc->type = X86_IRQ_ALLOC_TYPE_PCI_MSIX; return 0; default: @@ -229,10 +228,6 @@ static bool x86_init_dev_msi_info(struct device *dev, struct irq_domain *domain, case DOMAIN_BUS_PCI_DEVICE_MSI: case DOMAIN_BUS_PCI_DEVICE_MSIX: break; - case DOMAIN_BUS_PCI_DEVICE_IMS: - if (!(pops->supported_flags & MSI_FLAG_PCI_IMS)) - return false; - break; default: WARN_ON_ONCE(1); return false; diff --git a/arch/x86/kernel/apic/vector.c b/arch/x86/kernel/apic/vector.c index 9eec52925fa3..557318145038 100644 --- a/arch/x86/kernel/apic/vector.c +++ b/arch/x86/kernel/apic/vector.c @@ -1035,7 +1035,8 @@ static void __vector_schedule_cleanup(struct apic_chip_data *apicd) add_timer_on(&cl->timer, cpu); } } else { - apicd->prev_vector = 0; + pr_warn("IRQ %u schedule cleanup for offline CPU %u\n", apicd->irq, cpu); + free_moved_vector(apicd); } raw_spin_unlock(&vector_lock); } @@ -1072,6 +1073,7 @@ void irq_complete_move(struct irq_cfg *cfg) */ void irq_force_complete_move(struct irq_desc *desc) { + unsigned int cpu = smp_processor_id(); struct apic_chip_data *apicd; struct irq_data *irqd; unsigned int vector; @@ -1096,10 +1098,11 @@ void irq_force_complete_move(struct irq_desc *desc) goto unlock; /* - * If prev_vector is empty, no action required. + * If prev_vector is empty or the descriptor is neither currently + * nor previously on the outgoing CPU no action required. */ vector = apicd->prev_vector; - if (!vector) + if (!vector || (apicd->cpu != cpu && apicd->prev_cpu != cpu)) goto unlock; /* diff --git a/arch/x86/kernel/cpu/Makefile b/arch/x86/kernel/cpu/Makefile index eb4dbcdf41f1..a02bba0ed6b9 100644 --- a/arch/x86/kernel/cpu/Makefile +++ b/arch/x86/kernel/cpu/Makefile @@ -60,7 +60,7 @@ obj-$(CONFIG_ACRN_GUEST) += acrn.o obj-$(CONFIG_DEBUG_FS) += debugfs.o quiet_cmd_mkcapflags = MKCAP $@ - cmd_mkcapflags = $(CONFIG_SHELL) $(srctree)/$(src)/mkcapflags.sh $@ $^ + cmd_mkcapflags = $(CONFIG_SHELL) $(src)/mkcapflags.sh $@ $^ cpufeature = $(src)/../../include/asm/cpufeatures.h vmxfeature = $(src)/../../include/asm/vmxfeatures.h diff --git a/arch/x86/kernel/cpu/match.c b/arch/x86/kernel/cpu/match.c index 8651643bddae..8e7de733320a 100644 --- a/arch/x86/kernel/cpu/match.c +++ b/arch/x86/kernel/cpu/match.c @@ -38,9 +38,7 @@ const struct x86_cpu_id *x86_match_cpu(const struct x86_cpu_id *match) const struct x86_cpu_id *m; struct cpuinfo_x86 *c = &boot_cpu_data; - for (m = match; - m->vendor | m->family | m->model | m->steppings | m->feature; - m++) { + for (m = match; m->flags & X86_CPU_ID_FLAG_ENTRY_VALID; m++) { if (m->vendor != X86_VENDOR_ANY && c->x86_vendor != m->vendor) continue; if (m->family != X86_FAMILY_ANY && c->x86 != m->family) diff --git a/arch/x86/kernel/cpu/sgx/driver.c b/arch/x86/kernel/cpu/sgx/driver.c index 262f5fb18d74..22b65a5f5ec6 100644 --- a/arch/x86/kernel/cpu/sgx/driver.c +++ b/arch/x86/kernel/cpu/sgx/driver.c @@ -113,7 +113,7 @@ static unsigned long sgx_get_unmapped_area(struct file *file, if (flags & MAP_FIXED) return addr; - return current->mm->get_unmapped_area(file, addr, len, pgoff, flags); + return mm_get_unmapped_area(current->mm, file, addr, len, pgoff, flags); } #ifdef CONFIG_COMPAT diff --git a/arch/x86/kernel/cpu/sgx/main.c b/arch/x86/kernel/cpu/sgx/main.c index 166692f2d501..27892e57c4ef 100644 --- a/arch/x86/kernel/cpu/sgx/main.c +++ b/arch/x86/kernel/cpu/sgx/main.c @@ -13,6 +13,7 @@ #include <linux/sched/signal.h> #include <linux/slab.h> #include <linux/sysfs.h> +#include <linux/vmalloc.h> #include <asm/sgx.h> #include "driver.h" #include "encl.h" diff --git a/arch/x86/kernel/cpu/topology.c b/arch/x86/kernel/cpu/topology.c index d17c9b71eb4a..621a151ccf7d 100644 --- a/arch/x86/kernel/cpu/topology.c +++ b/arch/x86/kernel/cpu/topology.c @@ -128,6 +128,9 @@ static void topo_set_cpuids(unsigned int cpu, u32 apic_id, u32 acpi_id) static __init bool check_for_real_bsp(u32 apic_id) { + bool is_bsp = false, has_apic_base = boot_cpu_data.x86 >= 6; + u64 msr; + /* * There is no real good way to detect whether this a kdump() * kernel, but except on the Voyager SMP monstrosity which is not @@ -144,17 +147,61 @@ static __init bool check_for_real_bsp(u32 apic_id) if (topo_info.real_bsp_apic_id != BAD_APICID) return false; + /* + * Check whether the enumeration order is broken by evaluating the + * BSP bit in the APICBASE MSR. If the CPU does not have the + * APICBASE MSR then the BSP detection is not possible and the + * kernel must rely on the firmware enumeration order. + */ + if (has_apic_base) { + rdmsrl(MSR_IA32_APICBASE, msr); + is_bsp = !!(msr & MSR_IA32_APICBASE_BSP); + } + if (apic_id == topo_info.boot_cpu_apic_id) { - topo_info.real_bsp_apic_id = apic_id; - return false; + /* + * If the boot CPU has the APIC BSP bit set then the + * firmware enumeration is agreeing. If the CPU does not + * have the APICBASE MSR then the only choice is to trust + * the enumeration order. + */ + if (is_bsp || !has_apic_base) { + topo_info.real_bsp_apic_id = apic_id; + return false; + } + /* + * If the boot APIC is enumerated first, but the APICBASE + * MSR does not have the BSP bit set, then there is no way + * to discover the real BSP here. Assume a crash kernel and + * limit the number of CPUs to 1 as an INIT to the real BSP + * would reset the machine. + */ + pr_warn("Enumerated BSP APIC %x is not marked in APICBASE MSR\n", apic_id); + pr_warn("Assuming crash kernel. Limiting to one CPU to prevent machine INIT\n"); + set_nr_cpu_ids(1); + goto fwbug; } - pr_warn("Boot CPU APIC ID not the first enumerated APIC ID: %x > %x\n", + pr_warn("Boot CPU APIC ID not the first enumerated APIC ID: %x != %x\n", topo_info.boot_cpu_apic_id, apic_id); + + if (is_bsp) { + /* + * The boot CPU has the APIC BSP bit set. Use it and complain + * about the broken firmware enumeration. + */ + topo_info.real_bsp_apic_id = topo_info.boot_cpu_apic_id; + goto fwbug; + } + pr_warn("Crash kernel detected. Disabling real BSP to prevent machine INIT\n"); topo_info.real_bsp_apic_id = apic_id; return true; + +fwbug: + pr_warn(FW_BUG "APIC enumeration order not specification compliant\n"); + return false; } static unsigned int topo_unit_count(u32 lvlid, enum x86_topology_domains at_level, diff --git a/arch/x86/kernel/crash.c b/arch/x86/kernel/crash.c index e74d0c4286c1..f06501445cd9 100644 --- a/arch/x86/kernel/crash.c +++ b/arch/x86/kernel/crash.c @@ -402,20 +402,26 @@ int crash_load_segments(struct kimage *image) #undef pr_fmt #define pr_fmt(fmt) "crash hp: " fmt -/* These functions provide the value for the sysfs crash_hotplug nodes */ -#ifdef CONFIG_HOTPLUG_CPU -int arch_crash_hotplug_cpu_support(void) +int arch_crash_hotplug_support(struct kimage *image, unsigned long kexec_flags) { - return crash_check_update_elfcorehdr(); -} -#endif -#ifdef CONFIG_MEMORY_HOTPLUG -int arch_crash_hotplug_memory_support(void) -{ - return crash_check_update_elfcorehdr(); -} +#ifdef CONFIG_KEXEC_FILE + if (image->file_mode) + return 1; #endif + /* + * Initially, crash hotplug support for kexec_load was added + * with the KEXEC_UPDATE_ELFCOREHDR flag. Later, this + * functionality was expanded to accommodate multiple kexec + * segment updates, leading to the introduction of the + * KEXEC_CRASH_HOTPLUG_SUPPORT kexec flag bit. Consequently, + * when the kexec tool sends either of these flags, it indicates + * that the required kexec segment (elfcorehdr) is excluded from + * the SHA calculation. + */ + return (kexec_flags & KEXEC_UPDATE_ELFCOREHDR || + kexec_flags & KEXEC_CRASH_HOTPLUG_SUPPORT); +} unsigned int arch_crash_get_elfcorehdr_size(void) { @@ -432,10 +438,12 @@ unsigned int arch_crash_get_elfcorehdr_size(void) /** * arch_crash_handle_hotplug_event() - Handle hotplug elfcorehdr changes * @image: a pointer to kexec_crash_image + * @arg: struct memory_notify handler for memory hotplug case and + * NULL for CPU hotplug case. * * Prepare the new elfcorehdr and replace the existing elfcorehdr. */ -void arch_crash_handle_hotplug_event(struct kimage *image) +void arch_crash_handle_hotplug_event(struct kimage *image, void *arg) { void *elfbuf = NULL, *old_elfcorehdr; unsigned long nr_mem_ranges; diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c index 6276329f5e66..c5a026fee5e0 100644 --- a/arch/x86/kernel/fpu/xstate.c +++ b/arch/x86/kernel/fpu/xstate.c @@ -991,6 +991,7 @@ void *get_xsave_addr(struct xregs_state *xsave, int xfeature_nr) return __raw_xsave_addr(xsave, xfeature_nr); } +EXPORT_SYMBOL_GPL(get_xsave_addr); #ifdef CONFIG_ARCH_HAS_PKEYS diff --git a/arch/x86/kernel/fpu/xstate.h b/arch/x86/kernel/fpu/xstate.h index 19ca623ffa2a..05df04f39628 100644 --- a/arch/x86/kernel/fpu/xstate.h +++ b/arch/x86/kernel/fpu/xstate.h @@ -54,8 +54,6 @@ extern int copy_sigframe_from_user_to_xstate(struct task_struct *tsk, const void extern void fpu__init_cpu_xstate(void); extern void fpu__init_system_xstate(unsigned int legacy_size); -extern void *get_xsave_addr(struct xregs_state *xsave, int xfeature_nr); - static inline u64 xfeatures_mask_supervisor(void) { return fpu_kernel_cfg.max_features & XFEATURE_MASK_SUPERVISOR_SUPPORTED; diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c index 70139d9d2e01..8da0e66ca22d 100644 --- a/arch/x86/kernel/ftrace.c +++ b/arch/x86/kernel/ftrace.c @@ -25,6 +25,7 @@ #include <linux/memory.h> #include <linux/vmalloc.h> #include <linux/set_memory.h> +#include <linux/execmem.h> #include <trace/syscall.h> @@ -260,25 +261,14 @@ void arch_ftrace_update_code(int command) /* Currently only x86_64 supports dynamic trampolines */ #ifdef CONFIG_X86_64 -#ifdef CONFIG_MODULES -#include <linux/moduleloader.h> -/* Module allocation simplifies allocating memory for code */ static inline void *alloc_tramp(unsigned long size) { - return module_alloc(size); + return execmem_alloc(EXECMEM_FTRACE, size); } static inline void tramp_free(void *tramp) { - module_memfree(tramp); + execmem_free(tramp); } -#else -/* Trampolines can only be created if modules are supported */ -static inline void *alloc_tramp(unsigned long size) -{ - return NULL; -} -static inline void tramp_free(void *tramp) { } -#endif /* Defined as markers to the end of the ftrace default trampolines */ extern void ftrace_regs_caller_end(void); diff --git a/arch/x86/kernel/irq_64.c b/arch/x86/kernel/irq_64.c index fe0c859873d1..ade0043ce56e 100644 --- a/arch/x86/kernel/irq_64.c +++ b/arch/x86/kernel/irq_64.c @@ -18,6 +18,7 @@ #include <linux/uaccess.h> #include <linux/smp.h> #include <linux/sched/task_stack.h> +#include <linux/vmalloc.h> #include <asm/cpu_entry_area.h> #include <asm/softirq_stack.h> diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c index d0e49bd7c6f3..72e6a45e7ec2 100644 --- a/arch/x86/kernel/kprobes/core.c +++ b/arch/x86/kernel/kprobes/core.c @@ -40,12 +40,12 @@ #include <linux/kgdb.h> #include <linux/ftrace.h> #include <linux/kasan.h> -#include <linux/moduleloader.h> #include <linux/objtool.h> #include <linux/vmalloc.h> #include <linux/pgtable.h> #include <linux/set_memory.h> #include <linux/cfi.h> +#include <linux/execmem.h> #include <asm/text-patching.h> #include <asm/cacheflush.h> @@ -495,7 +495,7 @@ void *alloc_insn_page(void) { void *page; - page = module_alloc(PAGE_SIZE); + page = execmem_alloc(EXECMEM_KPROBES, PAGE_SIZE); if (!page) return NULL; diff --git a/arch/x86/kernel/kprobes/ftrace.c b/arch/x86/kernel/kprobes/ftrace.c index dd2ec14adb77..15af7e98e161 100644 --- a/arch/x86/kernel/kprobes/ftrace.c +++ b/arch/x86/kernel/kprobes/ftrace.c @@ -21,6 +21,9 @@ void kprobe_ftrace_handler(unsigned long ip, unsigned long parent_ip, struct kprobe_ctlblk *kcb; int bit; + if (unlikely(kprobe_ftrace_disabled)) + return; + bit = ftrace_test_recursion_trylock(ip, parent_ip); if (bit < 0) return; diff --git a/arch/x86/kernel/module.c b/arch/x86/kernel/module.c index e18914c0e38a..837450b6e882 100644 --- a/arch/x86/kernel/module.c +++ b/arch/x86/kernel/module.c @@ -36,57 +36,6 @@ do { \ } while (0) #endif -#ifdef CONFIG_RANDOMIZE_BASE -static unsigned long module_load_offset; - -/* Mutex protects the module_load_offset. */ -static DEFINE_MUTEX(module_kaslr_mutex); - -static unsigned long int get_module_load_offset(void) -{ - if (kaslr_enabled()) { - mutex_lock(&module_kaslr_mutex); - /* - * Calculate the module_load_offset the first time this - * code is called. Once calculated it stays the same until - * reboot. - */ - if (module_load_offset == 0) - module_load_offset = - get_random_u32_inclusive(1, 1024) * PAGE_SIZE; - mutex_unlock(&module_kaslr_mutex); - } - return module_load_offset; -} -#else -static unsigned long int get_module_load_offset(void) -{ - return 0; -} -#endif - -void *module_alloc(unsigned long size) -{ - gfp_t gfp_mask = GFP_KERNEL; - void *p; - - if (PAGE_ALIGN(size) > MODULES_LEN) - return NULL; - - p = __vmalloc_node_range(size, MODULE_ALIGN, - MODULES_VADDR + get_module_load_offset(), - MODULES_END, gfp_mask, PAGE_KERNEL, - VM_FLUSH_RESET_PERMS | VM_DEFER_KMEMLEAK, - NUMA_NO_NODE, __builtin_return_address(0)); - - if (p && (kasan_alloc_module_shadow(p, size, gfp_mask) < 0)) { - vfree(p); - return NULL; - } - - return p; -} - #ifdef CONFIG_X86_32 int apply_relocate(Elf32_Shdr *sechdrs, const char *strtab, diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index 55a1fc332e20..05c5aa951da7 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -1108,8 +1108,6 @@ void __init setup_arch(char **cmdline_p) */ arch_reserve_crashkernel(); - memblock_find_dma_reserve(); - if (!early_xdbc_setup_hardware()) early_xdbc_register_console(); diff --git a/arch/x86/kernel/sys_x86_64.c b/arch/x86/kernel/sys_x86_64.c index cb9fa1d5c66f..01d7cd85ef97 100644 --- a/arch/x86/kernel/sys_x86_64.c +++ b/arch/x86/kernel/sys_x86_64.c @@ -112,13 +112,21 @@ static void find_start_end(unsigned long addr, unsigned long flags, *end = task_size_64bit(addr > DEFAULT_MAP_WINDOW); } +static inline unsigned long stack_guard_placement(vm_flags_t vm_flags) +{ + if (vm_flags & VM_SHADOW_STACK) + return PAGE_SIZE; + + return 0; +} + unsigned long -arch_get_unmapped_area(struct file *filp, unsigned long addr, - unsigned long len, unsigned long pgoff, unsigned long flags) +arch_get_unmapped_area_vmflags(struct file *filp, unsigned long addr, unsigned long len, + unsigned long pgoff, unsigned long flags, vm_flags_t vm_flags) { struct mm_struct *mm = current->mm; struct vm_area_struct *vma; - struct vm_unmapped_area_info info; + struct vm_unmapped_area_info info = {}; unsigned long begin, end; if (flags & MAP_FIXED) @@ -137,12 +145,11 @@ arch_get_unmapped_area(struct file *filp, unsigned long addr, return addr; } - info.flags = 0; info.length = len; info.low_limit = begin; info.high_limit = end; - info.align_mask = 0; info.align_offset = pgoff << PAGE_SHIFT; + info.start_gap = stack_guard_placement(vm_flags); if (filp) { info.align_mask = get_align_mask(); info.align_offset += get_align_bits(); @@ -151,14 +158,14 @@ arch_get_unmapped_area(struct file *filp, unsigned long addr, } unsigned long -arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0, - const unsigned long len, const unsigned long pgoff, - const unsigned long flags) +arch_get_unmapped_area_topdown_vmflags(struct file *filp, unsigned long addr0, + unsigned long len, unsigned long pgoff, + unsigned long flags, vm_flags_t vm_flags) { struct vm_area_struct *vma; struct mm_struct *mm = current->mm; unsigned long addr = addr0; - struct vm_unmapped_area_info info; + struct vm_unmapped_area_info info = {}; /* requested length too big for entire address space */ if (len > TASK_SIZE) @@ -192,6 +199,7 @@ get_unmapped_area: info.low_limit = PAGE_SIZE; info.high_limit = get_mmap_base(0); + info.start_gap = stack_guard_placement(vm_flags); /* * If hint address is above DEFAULT_MAP_WINDOW, look for unmapped area @@ -203,7 +211,6 @@ get_unmapped_area: if (addr > DEFAULT_MAP_WINDOW && !in_32bit_syscall()) info.high_limit += TASK_SIZE_MAX - DEFAULT_MAP_WINDOW; - info.align_mask = 0; info.align_offset = pgoff << PAGE_SHIFT; if (filp) { info.align_mask = get_align_mask(); @@ -223,3 +230,18 @@ bottomup: */ return arch_get_unmapped_area(filp, addr0, len, pgoff, flags); } + +unsigned long +arch_get_unmapped_area(struct file *filp, unsigned long addr, + unsigned long len, unsigned long pgoff, unsigned long flags) +{ + return arch_get_unmapped_area_vmflags(filp, addr, len, pgoff, flags, 0); +} + +unsigned long +arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr, + const unsigned long len, const unsigned long pgoff, + const unsigned long flags) +{ + return arch_get_unmapped_area_topdown_vmflags(filp, addr, len, pgoff, flags, 0); +} diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig index 0ebdd088f28b..d64fb2b3eb69 100644 --- a/arch/x86/kvm/Kconfig +++ b/arch/x86/kvm/Kconfig @@ -95,6 +95,19 @@ config KVM_INTEL To compile this as a module, choose M here: the module will be called kvm-intel. +config KVM_INTEL_PROVE_VE + bool "Check that guests do not receive #VE exceptions" + default KVM_PROVE_MMU || DEBUG_KERNEL + depends on KVM_INTEL + help + + Checks that KVM's page table management code will not incorrectly + let guests receive a virtualization exception. Virtualization + exceptions will be trapped by the hypervisor rather than injected + in the guest. + + If unsure, say N. + config X86_SGX_KVM bool "Software Guard eXtensions (SGX) Virtualization" depends on X86_SGX && KVM_INTEL diff --git a/arch/x86/kvm/Makefile b/arch/x86/kvm/Makefile index addc44fc7187..5494669a055a 100644 --- a/arch/x86/kvm/Makefile +++ b/arch/x86/kvm/Makefile @@ -16,14 +16,15 @@ kvm-$(CONFIG_KVM_XEN) += xen.o kvm-$(CONFIG_KVM_SMM) += smm.o kvm-intel-y += vmx/vmx.o vmx/vmenter.o vmx/pmu_intel.o vmx/vmcs12.o \ - vmx/nested.o vmx/posted_intr.o + vmx/nested.o vmx/posted_intr.o vmx/main.o kvm-intel-$(CONFIG_X86_SGX_KVM) += vmx/sgx.o kvm-intel-$(CONFIG_KVM_HYPERV) += vmx/hyperv.o vmx/hyperv_evmcs.o -kvm-amd-y += svm/svm.o svm/vmenter.o svm/pmu.o svm/nested.o svm/avic.o \ - svm/sev.o -kvm-amd-$(CONFIG_KVM_HYPERV) += svm/hyperv.o +kvm-amd-y += svm/svm.o svm/vmenter.o svm/pmu.o svm/nested.o svm/avic.o + +kvm-amd-$(CONFIG_KVM_AMD_SEV) += svm/sev.o +kvm-amd-$(CONFIG_KVM_HYPERV) += svm/hyperv.o ifdef CONFIG_HYPERV kvm-y += kvm_onhyperv.o diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index 77352a4abd87..f2f2be5d1141 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -772,7 +772,7 @@ void kvm_set_cpu_caps(void) kvm_cpu_cap_mask(CPUID_8000_000A_EDX, 0); kvm_cpu_cap_mask(CPUID_8000_001F_EAX, - 0 /* SME */ | F(SEV) | 0 /* VM_PAGE_FLUSH */ | F(SEV_ES) | + 0 /* SME */ | 0 /* SEV */ | 0 /* VM_PAGE_FLUSH */ | 0 /* SEV_ES */ | F(SME_COHERENT)); kvm_cpu_cap_mask(CPUID_8000_0021_EAX, @@ -1232,9 +1232,22 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function) entry->eax = entry->ebx = entry->ecx = 0; break; case 0x80000008: { - unsigned g_phys_as = (entry->eax >> 16) & 0xff; - unsigned virt_as = max((entry->eax >> 8) & 0xff, 48U); - unsigned phys_as = entry->eax & 0xff; + /* + * GuestPhysAddrSize (EAX[23:16]) is intended for software + * use. + * + * KVM's ABI is to report the effective MAXPHYADDR for the + * guest in PhysAddrSize (phys_as), and the maximum + * *addressable* GPA in GuestPhysAddrSize (g_phys_as). + * + * GuestPhysAddrSize is valid if and only if TDP is enabled, + * in which case the max GPA that can be addressed by KVM may + * be less than the max GPA that can be legally generated by + * the guest, e.g. if MAXPHYADDR>48 but the CPU doesn't + * support 5-level TDP. + */ + unsigned int virt_as = max((entry->eax >> 8) & 0xff, 48U); + unsigned int phys_as, g_phys_as; /* * If TDP (NPT) is disabled use the adjusted host MAXPHYADDR as @@ -1242,16 +1255,24 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function) * reductions in MAXPHYADDR for memory encryption affect shadow * paging, too. * - * If TDP is enabled but an explicit guest MAXPHYADDR is not - * provided, use the raw bare metal MAXPHYADDR as reductions to - * the HPAs do not affect GPAs. + * If TDP is enabled, use the raw bare metal MAXPHYADDR as + * reductions to the HPAs do not affect GPAs. The max + * addressable GPA is the same as the max effective GPA, except + * that it's capped at 48 bits if 5-level TDP isn't supported + * (hardware processes bits 51:48 only when walking the fifth + * level page table). */ - if (!tdp_enabled) - g_phys_as = boot_cpu_data.x86_phys_bits; - else if (!g_phys_as) + if (!tdp_enabled) { + phys_as = boot_cpu_data.x86_phys_bits; + g_phys_as = 0; + } else { + phys_as = entry->eax & 0xff; g_phys_as = phys_as; + if (kvm_mmu_get_max_tdp_level() < 5) + g_phys_as = min(g_phys_as, 48); + } - entry->eax = g_phys_as | (virt_as << 8); + entry->eax = phys_as | (virt_as << 8) | (g_phys_as << 16); entry->ecx &= ~(GENMASK(31, 16) | GENMASK(11, 8)); entry->edx = 0; cpuid_entry_override(entry, CPUID_8000_0008_EBX); diff --git a/arch/x86/kvm/kvm_emulate.h b/arch/x86/kvm/kvm_emulate.h index 5382646162a3..29ea4313e1bb 100644 --- a/arch/x86/kvm/kvm_emulate.h +++ b/arch/x86/kvm/kvm_emulate.h @@ -26,6 +26,7 @@ struct x86_exception { bool nested_page_fault; u64 address; /* cr2 or nested page fault gpa */ u8 async_page_fault; + unsigned long exit_qualification; }; /* diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h index 60f21bb4c27b..2e454316f2a2 100644 --- a/arch/x86/kvm/mmu.h +++ b/arch/x86/kvm/mmu.h @@ -100,6 +100,8 @@ static inline u8 kvm_get_shadow_phys_bits(void) return boot_cpu_data.x86_phys_bits; } +u8 kvm_mmu_get_max_tdp_level(void); + void kvm_mmu_set_mmio_spte_mask(u64 mmio_value, u64 mmio_mask, u64 access_mask); void kvm_mmu_set_me_spte_mask(u64 me_value, u64 me_mask); void kvm_mmu_set_ept_masks(bool has_ad_bits, bool has_exec_only); @@ -213,7 +215,7 @@ static inline u8 permission_fault(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, */ u64 implicit_access = access & PFERR_IMPLICIT_ACCESS; bool not_smap = ((rflags & X86_EFLAGS_AC) | implicit_access) == X86_EFLAGS_AC; - int index = (pfec + (not_smap << PFERR_RSVD_BIT)) >> 1; + int index = (pfec | (not_smap ? PFERR_RSVD_MASK : 0)) >> 1; u32 errcode = PFERR_PRESENT_MASK; bool fault; @@ -234,8 +236,7 @@ static inline u8 permission_fault(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, pkru_bits = (vcpu->arch.pkru >> (pte_pkey * 2)) & 3; /* clear present bit, replace PFEC.RSVD with ACC_USER_MASK. */ - offset = (pfec & ~1) + - ((pte_access & PT_USER_MASK) << (PFERR_RSVD_BIT - PT_USER_SHIFT)); + offset = (pfec & ~1) | ((pte_access & PT_USER_MASK) ? PFERR_RSVD_MASK : 0); pkru_bits &= mmu->pkru_mask >> offset; errcode |= -pkru_bits & PFERR_PK_MASK; diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index db007a4dffa2..662f62dfb2aa 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -432,8 +432,8 @@ static u64 __update_clear_spte_slow(u64 *sptep, u64 spte) * The idea using the light way get the spte on x86_32 guest is from * gup_get_pte (mm/gup.c). * - * An spte tlb flush may be pending, because kvm_set_pte_rmap - * coalesces them and we are running out of the MMU lock. Therefore + * An spte tlb flush may be pending, because they are coalesced and + * we are running out of the MMU lock. Therefore * we need to protect against in-progress updates of the spte. * * Reading the spte while an update is in progress may get the old value @@ -567,9 +567,9 @@ static u64 mmu_spte_clear_track_bits(struct kvm *kvm, u64 *sptep) if (!is_shadow_present_pte(old_spte) || !spte_has_volatile_bits(old_spte)) - __update_clear_spte_fast(sptep, 0ull); + __update_clear_spte_fast(sptep, SHADOW_NONPRESENT_VALUE); else - old_spte = __update_clear_spte_slow(sptep, 0ull); + old_spte = __update_clear_spte_slow(sptep, SHADOW_NONPRESENT_VALUE); if (!is_shadow_present_pte(old_spte)) return old_spte; @@ -603,7 +603,7 @@ static u64 mmu_spte_clear_track_bits(struct kvm *kvm, u64 *sptep) */ static void mmu_spte_clear_no_track(u64 *sptep) { - __update_clear_spte_fast(sptep, 0ull); + __update_clear_spte_fast(sptep, SHADOW_NONPRESENT_VALUE); } static u64 mmu_spte_get_lockless(u64 *sptep) @@ -831,6 +831,15 @@ static void account_shadowed(struct kvm *kvm, struct kvm_mmu_page *sp) gfn_t gfn; kvm->arch.indirect_shadow_pages++; + /* + * Ensure indirect_shadow_pages is elevated prior to re-reading guest + * child PTEs in FNAME(gpte_changed), i.e. guarantee either in-flight + * emulated writes are visible before re-reading guest PTEs, or that + * an emulated write will see the elevated count and acquire mmu_lock + * to update SPTEs. Pairs with the smp_mb() in kvm_mmu_track_write(). + */ + smp_mb(); + gfn = sp->gfn; slots = kvm_memslots_for_spte_role(kvm, sp->role); slot = __gfn_to_memslot(slots, gfn); @@ -1448,49 +1457,11 @@ static bool __kvm_zap_rmap(struct kvm *kvm, struct kvm_rmap_head *rmap_head, } static bool kvm_zap_rmap(struct kvm *kvm, struct kvm_rmap_head *rmap_head, - struct kvm_memory_slot *slot, gfn_t gfn, int level, - pte_t unused) + struct kvm_memory_slot *slot, gfn_t gfn, int level) { return __kvm_zap_rmap(kvm, rmap_head, slot); } -static bool kvm_set_pte_rmap(struct kvm *kvm, struct kvm_rmap_head *rmap_head, - struct kvm_memory_slot *slot, gfn_t gfn, int level, - pte_t pte) -{ - u64 *sptep; - struct rmap_iterator iter; - bool need_flush = false; - u64 new_spte; - kvm_pfn_t new_pfn; - - WARN_ON_ONCE(pte_huge(pte)); - new_pfn = pte_pfn(pte); - -restart: - for_each_rmap_spte(rmap_head, &iter, sptep) { - need_flush = true; - - if (pte_write(pte)) { - kvm_zap_one_rmap_spte(kvm, rmap_head, sptep); - goto restart; - } else { - new_spte = kvm_mmu_changed_pte_notifier_make_spte( - *sptep, new_pfn); - - mmu_spte_clear_track_bits(kvm, sptep); - mmu_spte_set(sptep, new_spte); - } - } - - if (need_flush && kvm_available_flush_remote_tlbs_range()) { - kvm_flush_remote_tlbs_gfn(kvm, gfn, level); - return false; - } - - return need_flush; -} - struct slot_rmap_walk_iterator { /* input fields. */ const struct kvm_memory_slot *slot; @@ -1562,7 +1533,7 @@ static void slot_rmap_walk_next(struct slot_rmap_walk_iterator *iterator) typedef bool (*rmap_handler_t)(struct kvm *kvm, struct kvm_rmap_head *rmap_head, struct kvm_memory_slot *slot, gfn_t gfn, - int level, pte_t pte); + int level); static __always_inline bool kvm_handle_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range, @@ -1574,7 +1545,7 @@ static __always_inline bool kvm_handle_gfn_range(struct kvm *kvm, for_each_slot_rmap_range(range->slot, PG_LEVEL_4K, KVM_MAX_HUGEPAGE_LEVEL, range->start, range->end - 1, &iterator) ret |= handler(kvm, iterator.rmap, range->slot, iterator.gfn, - iterator.level, range->arg.pte); + iterator.level); return ret; } @@ -1596,22 +1567,8 @@ bool kvm_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range) return flush; } -bool kvm_set_spte_gfn(struct kvm *kvm, struct kvm_gfn_range *range) -{ - bool flush = false; - - if (kvm_memslots_have_rmaps(kvm)) - flush = kvm_handle_gfn_range(kvm, range, kvm_set_pte_rmap); - - if (tdp_mmu_enabled) - flush |= kvm_tdp_mmu_set_spte_gfn(kvm, range); - - return flush; -} - static bool kvm_age_rmap(struct kvm *kvm, struct kvm_rmap_head *rmap_head, - struct kvm_memory_slot *slot, gfn_t gfn, int level, - pte_t unused) + struct kvm_memory_slot *slot, gfn_t gfn, int level) { u64 *sptep; struct rmap_iterator iter; @@ -1624,8 +1581,7 @@ static bool kvm_age_rmap(struct kvm *kvm, struct kvm_rmap_head *rmap_head, } static bool kvm_test_age_rmap(struct kvm *kvm, struct kvm_rmap_head *rmap_head, - struct kvm_memory_slot *slot, gfn_t gfn, - int level, pte_t unused) + struct kvm_memory_slot *slot, gfn_t gfn, int level) { u64 *sptep; struct rmap_iterator iter; @@ -1950,7 +1906,8 @@ static bool kvm_sync_page_check(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp) static int kvm_sync_spte(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp, int i) { - if (!sp->spt[i]) + /* sp->spt[i] has initial value of shadow page table allocation */ + if (sp->spt[i] == SHADOW_NONPRESENT_VALUE) return 0; return vcpu->arch.mmu->sync_spte(vcpu, sp, i); @@ -2514,7 +2471,7 @@ static int mmu_page_zap_pte(struct kvm *kvm, struct kvm_mmu_page *sp, return kvm_mmu_prepare_zap_page(kvm, child, invalid_list); } - } else if (is_mmio_spte(pte)) { + } else if (is_mmio_spte(kvm, pte)) { mmu_spte_clear_no_track(spte); } return 0; @@ -3314,9 +3271,19 @@ static int kvm_handle_noslot_fault(struct kvm_vcpu *vcpu, { gva_t gva = fault->is_tdp ? 0 : fault->addr; + if (fault->is_private) { + kvm_mmu_prepare_memory_fault_exit(vcpu, fault); + return -EFAULT; + } + vcpu_cache_mmio_info(vcpu, gva, fault->gfn, access & shadow_mmio_access_mask); + fault->slot = NULL; + fault->pfn = KVM_PFN_NOSLOT; + fault->map_writable = false; + fault->hva = KVM_HVA_ERR_BAD; + /* * If MMIO caching is disabled, emulate immediately without * touching the shadow page tables as attempting to install an @@ -4196,7 +4163,7 @@ static int handle_mmio_page_fault(struct kvm_vcpu *vcpu, u64 addr, bool direct) if (WARN_ON_ONCE(reserved)) return -EINVAL; - if (is_mmio_spte(spte)) { + if (is_mmio_spte(vcpu->kvm, spte)) { gfn_t gfn = get_mmio_spte_gfn(spte); unsigned int access = get_mmio_spte_access(spte); @@ -4259,24 +4226,28 @@ static u32 alloc_apf_token(struct kvm_vcpu *vcpu) return (vcpu->arch.apf.id++ << 12) | vcpu->vcpu_id; } -static bool kvm_arch_setup_async_pf(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, - gfn_t gfn) +static bool kvm_arch_setup_async_pf(struct kvm_vcpu *vcpu, + struct kvm_page_fault *fault) { struct kvm_arch_async_pf arch; arch.token = alloc_apf_token(vcpu); - arch.gfn = gfn; + arch.gfn = fault->gfn; + arch.error_code = fault->error_code; arch.direct_map = vcpu->arch.mmu->root_role.direct; arch.cr3 = kvm_mmu_get_guest_pgd(vcpu, vcpu->arch.mmu); - return kvm_setup_async_pf(vcpu, cr2_or_gpa, - kvm_vcpu_gfn_to_hva(vcpu, gfn), &arch); + return kvm_setup_async_pf(vcpu, fault->addr, + kvm_vcpu_gfn_to_hva(vcpu, fault->gfn), &arch); } void kvm_arch_async_page_ready(struct kvm_vcpu *vcpu, struct kvm_async_pf *work) { int r; + if (WARN_ON_ONCE(work->arch.error_code & PFERR_PRIVATE_ACCESS)) + return; + if ((vcpu->arch.mmu->root_role.direct != work->arch.direct_map) || work->wakeup_all) return; @@ -4289,7 +4260,7 @@ void kvm_arch_async_page_ready(struct kvm_vcpu *vcpu, struct kvm_async_pf *work) work->arch.cr3 != kvm_mmu_get_guest_pgd(vcpu, vcpu->arch.mmu)) return; - kvm_mmu_do_page_fault(vcpu, work->cr2_or_gpa, 0, true, NULL); + kvm_mmu_do_page_fault(vcpu, work->cr2_or_gpa, work->arch.error_code, true, NULL); } static inline u8 kvm_max_level_for_order(int order) @@ -4309,14 +4280,6 @@ static inline u8 kvm_max_level_for_order(int order) return PG_LEVEL_4K; } -static void kvm_mmu_prepare_memory_fault_exit(struct kvm_vcpu *vcpu, - struct kvm_page_fault *fault) -{ - kvm_prepare_memory_fault_exit(vcpu, fault->gfn << PAGE_SHIFT, - PAGE_SIZE, fault->write, fault->exec, - fault->is_private); -} - static int kvm_faultin_pfn_private(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault) { @@ -4343,48 +4306,15 @@ static int kvm_faultin_pfn_private(struct kvm_vcpu *vcpu, static int __kvm_faultin_pfn(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault) { - struct kvm_memory_slot *slot = fault->slot; bool async; - /* - * Retry the page fault if the gfn hit a memslot that is being deleted - * or moved. This ensures any existing SPTEs for the old memslot will - * be zapped before KVM inserts a new MMIO SPTE for the gfn. - */ - if (slot && (slot->flags & KVM_MEMSLOT_INVALID)) - return RET_PF_RETRY; - - if (!kvm_is_visible_memslot(slot)) { - /* Don't expose private memslots to L2. */ - if (is_guest_mode(vcpu)) { - fault->slot = NULL; - fault->pfn = KVM_PFN_NOSLOT; - fault->map_writable = false; - return RET_PF_CONTINUE; - } - /* - * If the APIC access page exists but is disabled, go directly - * to emulation without caching the MMIO access or creating a - * MMIO SPTE. That way the cache doesn't need to be purged - * when the AVIC is re-enabled. - */ - if (slot && slot->id == APIC_ACCESS_PAGE_PRIVATE_MEMSLOT && - !kvm_apicv_activated(vcpu->kvm)) - return RET_PF_EMULATE; - } - - if (fault->is_private != kvm_mem_is_private(vcpu->kvm, fault->gfn)) { - kvm_mmu_prepare_memory_fault_exit(vcpu, fault); - return -EFAULT; - } - if (fault->is_private) return kvm_faultin_pfn_private(vcpu, fault); async = false; - fault->pfn = __gfn_to_pfn_memslot(slot, fault->gfn, false, false, &async, - fault->write, &fault->map_writable, - &fault->hva); + fault->pfn = __gfn_to_pfn_memslot(fault->slot, fault->gfn, false, false, + &async, fault->write, + &fault->map_writable, &fault->hva); if (!async) return RET_PF_CONTINUE; /* *pfn has correct page already */ @@ -4394,7 +4324,7 @@ static int __kvm_faultin_pfn(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault trace_kvm_async_pf_repeated_fault(fault->addr, fault->gfn); kvm_make_request(KVM_REQ_APF_HALT, vcpu); return RET_PF_RETRY; - } else if (kvm_arch_setup_async_pf(vcpu, fault->addr, fault->gfn)) { + } else if (kvm_arch_setup_async_pf(vcpu, fault)) { return RET_PF_RETRY; } } @@ -4404,17 +4334,72 @@ static int __kvm_faultin_pfn(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault * to wait for IO. Note, gup always bails if it is unable to quickly * get a page and a fatal signal, i.e. SIGKILL, is pending. */ - fault->pfn = __gfn_to_pfn_memslot(slot, fault->gfn, false, true, NULL, - fault->write, &fault->map_writable, - &fault->hva); + fault->pfn = __gfn_to_pfn_memslot(fault->slot, fault->gfn, false, true, + NULL, fault->write, + &fault->map_writable, &fault->hva); return RET_PF_CONTINUE; } static int kvm_faultin_pfn(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault, unsigned int access) { + struct kvm_memory_slot *slot = fault->slot; int ret; + /* + * Note that the mmu_invalidate_seq also serves to detect a concurrent + * change in attributes. is_page_fault_stale() will detect an + * invalidation relate to fault->fn and resume the guest without + * installing a mapping in the page tables. + */ + fault->mmu_seq = vcpu->kvm->mmu_invalidate_seq; + smp_rmb(); + + /* + * Now that we have a snapshot of mmu_invalidate_seq we can check for a + * private vs. shared mismatch. + */ + if (fault->is_private != kvm_mem_is_private(vcpu->kvm, fault->gfn)) { + kvm_mmu_prepare_memory_fault_exit(vcpu, fault); + return -EFAULT; + } + + if (unlikely(!slot)) + return kvm_handle_noslot_fault(vcpu, fault, access); + + /* + * Retry the page fault if the gfn hit a memslot that is being deleted + * or moved. This ensures any existing SPTEs for the old memslot will + * be zapped before KVM inserts a new MMIO SPTE for the gfn. + */ + if (slot->flags & KVM_MEMSLOT_INVALID) + return RET_PF_RETRY; + + if (slot->id == APIC_ACCESS_PAGE_PRIVATE_MEMSLOT) { + /* + * Don't map L1's APIC access page into L2, KVM doesn't support + * using APICv/AVIC to accelerate L2 accesses to L1's APIC, + * i.e. the access needs to be emulated. Emulating access to + * L1's APIC is also correct if L1 is accelerating L2's own + * virtual APIC, but for some reason L1 also maps _L1's_ APIC + * into L2. Note, vcpu_is_mmio_gpa() always treats access to + * the APIC as MMIO. Allow an MMIO SPTE to be created, as KVM + * uses different roots for L1 vs. L2, i.e. there is no danger + * of breaking APICv/AVIC for L1. + */ + if (is_guest_mode(vcpu)) + return kvm_handle_noslot_fault(vcpu, fault, access); + + /* + * If the APIC access page exists but is disabled, go directly + * to emulation without caching the MMIO access or creating a + * MMIO SPTE. That way the cache doesn't need to be purged + * when the AVIC is re-enabled. + */ + if (!kvm_apicv_activated(vcpu->kvm)) + return RET_PF_EMULATE; + } + fault->mmu_seq = vcpu->kvm->mmu_invalidate_seq; smp_rmb(); @@ -4439,8 +4424,7 @@ static int kvm_faultin_pfn(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault, * *guaranteed* to need to retry, i.e. waiting until mmu_lock is held * to detect retry guarantees the worst case latency for the vCPU. */ - if (fault->slot && - mmu_invalidate_retry_gfn_unsafe(vcpu->kvm, fault->mmu_seq, fault->gfn)) + if (mmu_invalidate_retry_gfn_unsafe(vcpu->kvm, fault->mmu_seq, fault->gfn)) return RET_PF_RETRY; ret = __kvm_faultin_pfn(vcpu, fault); @@ -4450,7 +4434,7 @@ static int kvm_faultin_pfn(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault, if (unlikely(is_error_pfn(fault->pfn))) return kvm_handle_error_pfn(vcpu, fault); - if (unlikely(!fault->slot)) + if (WARN_ON_ONCE(!fault->slot || is_noslot_pfn(fault->pfn))) return kvm_handle_noslot_fault(vcpu, fault, access); /* @@ -4561,6 +4545,16 @@ int kvm_handle_page_fault(struct kvm_vcpu *vcpu, u64 error_code, if (WARN_ON_ONCE(fault_address >> 32)) return -EFAULT; #endif + /* + * Legacy #PF exception only have a 32-bit error code. Simply drop the + * upper bits as KVM doesn't use them for #PF (because they are never + * set), and to ensure there are no collisions with KVM-defined bits. + */ + if (WARN_ON_ONCE(error_code >> 32)) + error_code = lower_32_bits(error_code); + + /* Ensure the above sanity check also covers KVM-defined flags. */ + BUILD_BUG_ON(lower_32_bits(PFERR_SYNTHETIC_MASK)); vcpu->arch.l1tf_flush_l1d = true; if (!flags) { @@ -4812,7 +4806,7 @@ EXPORT_SYMBOL_GPL(kvm_mmu_new_pgd); static bool sync_mmio_spte(struct kvm_vcpu *vcpu, u64 *sptep, gfn_t gfn, unsigned int access) { - if (unlikely(is_mmio_spte(*sptep))) { + if (unlikely(is_mmio_spte(vcpu->kvm, *sptep))) { if (gfn != get_mmio_spte_gfn(*sptep)) { mmu_spte_clear_no_track(sptep); return true; @@ -5322,6 +5316,11 @@ static inline int kvm_mmu_get_tdp_level(struct kvm_vcpu *vcpu) return max_tdp_level; } +u8 kvm_mmu_get_max_tdp_level(void) +{ + return tdp_root_level ? tdp_root_level : max_tdp_level; +} + static union kvm_mmu_page_role kvm_calc_tdp_mmu_root_page_role(struct kvm_vcpu *vcpu, union kvm_cpu_role cpu_role) @@ -5802,10 +5801,15 @@ void kvm_mmu_track_write(struct kvm_vcpu *vcpu, gpa_t gpa, const u8 *new, bool flush = false; /* - * If we don't have indirect shadow pages, it means no page is - * write-protected, so we can exit simply. + * When emulating guest writes, ensure the written value is visible to + * any task that is handling page faults before checking whether or not + * KVM is shadowing a guest PTE. This ensures either KVM will create + * the correct SPTE in the page fault handler, or this task will see + * a non-zero indirect_shadow_pages. Pairs with the smp_mb() in + * account_shadowed(). */ - if (!READ_ONCE(vcpu->kvm->arch.indirect_shadow_pages)) + smp_mb(); + if (!vcpu->kvm->arch.indirect_shadow_pages) return; write_lock(&vcpu->kvm->mmu_lock); @@ -5846,30 +5850,35 @@ int noinline kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, u64 err int r, emulation_type = EMULTYPE_PF; bool direct = vcpu->arch.mmu->root_role.direct; - /* - * IMPLICIT_ACCESS is a KVM-defined flag used to correctly perform SMAP - * checks when emulating instructions that triggers implicit access. - * WARN if hardware generates a fault with an error code that collides - * with the KVM-defined value. Clear the flag and continue on, i.e. - * don't terminate the VM, as KVM can't possibly be relying on a flag - * that KVM doesn't know about. - */ - if (WARN_ON_ONCE(error_code & PFERR_IMPLICIT_ACCESS)) - error_code &= ~PFERR_IMPLICIT_ACCESS; - if (WARN_ON_ONCE(!VALID_PAGE(vcpu->arch.mmu->root.hpa))) return RET_PF_RETRY; + /* + * Except for reserved faults (emulated MMIO is shared-only), set the + * PFERR_PRIVATE_ACCESS flag for software-protected VMs based on the gfn's + * current attributes, which are the source of truth for such VMs. Note, + * this wrong for nested MMUs as the GPA is an L2 GPA, but KVM doesn't + * currently supported nested virtualization (among many other things) + * for software-protected VMs. + */ + if (IS_ENABLED(CONFIG_KVM_SW_PROTECTED_VM) && + !(error_code & PFERR_RSVD_MASK) && + vcpu->kvm->arch.vm_type == KVM_X86_SW_PROTECTED_VM && + kvm_mem_is_private(vcpu->kvm, gpa_to_gfn(cr2_or_gpa))) + error_code |= PFERR_PRIVATE_ACCESS; + r = RET_PF_INVALID; if (unlikely(error_code & PFERR_RSVD_MASK)) { + if (WARN_ON_ONCE(error_code & PFERR_PRIVATE_ACCESS)) + return -EFAULT; + r = handle_mmio_page_fault(vcpu, cr2_or_gpa, direct); if (r == RET_PF_EMULATE) goto emulate; } if (r == RET_PF_INVALID) { - r = kvm_mmu_do_page_fault(vcpu, cr2_or_gpa, - lower_32_bits(error_code), false, + r = kvm_mmu_do_page_fault(vcpu, cr2_or_gpa, error_code, false, &emulation_type); if (KVM_BUG_ON(r == RET_PF_INVALID, vcpu->kvm)) return -EIO; @@ -6173,7 +6182,10 @@ int kvm_mmu_create(struct kvm_vcpu *vcpu) vcpu->arch.mmu_page_header_cache.kmem_cache = mmu_page_header_cache; vcpu->arch.mmu_page_header_cache.gfp_zero = __GFP_ZERO; - vcpu->arch.mmu_shadow_page_cache.gfp_zero = __GFP_ZERO; + vcpu->arch.mmu_shadow_page_cache.init_value = + SHADOW_NONPRESENT_VALUE; + if (!vcpu->arch.mmu_shadow_page_cache.init_value) + vcpu->arch.mmu_shadow_page_cache.gfp_zero = __GFP_ZERO; vcpu->arch.mmu = &vcpu->arch.root_mmu; vcpu->arch.walk_mmu = &vcpu->arch.root_mmu; @@ -6316,6 +6328,7 @@ static bool kvm_has_zapped_obsolete_pages(struct kvm *kvm) void kvm_mmu_init_vm(struct kvm *kvm) { + kvm->arch.shadow_mmio_value = shadow_mmio_value; INIT_LIST_HEAD(&kvm->arch.active_mmu_pages); INIT_LIST_HEAD(&kvm->arch.zapped_obsolete_pages); INIT_LIST_HEAD(&kvm->arch.possible_nx_huge_pages); diff --git a/arch/x86/kvm/mmu/mmu_internal.h b/arch/x86/kvm/mmu/mmu_internal.h index 5390a591a571..ce2fcd19ba6b 100644 --- a/arch/x86/kvm/mmu/mmu_internal.h +++ b/arch/x86/kvm/mmu/mmu_internal.h @@ -190,7 +190,7 @@ static inline bool is_nx_huge_page_enabled(struct kvm *kvm) struct kvm_page_fault { /* arguments to kvm_mmu_do_page_fault. */ const gpa_t addr; - const u32 error_code; + const u64 error_code; const bool prefetch; /* Derived from error_code. */ @@ -279,8 +279,16 @@ enum { RET_PF_SPURIOUS, }; +static inline void kvm_mmu_prepare_memory_fault_exit(struct kvm_vcpu *vcpu, + struct kvm_page_fault *fault) +{ + kvm_prepare_memory_fault_exit(vcpu, fault->gfn << PAGE_SHIFT, + PAGE_SIZE, fault->write, fault->exec, + fault->is_private); +} + static inline int kvm_mmu_do_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, - u32 err, bool prefetch, int *emulation_type) + u64 err, bool prefetch, int *emulation_type) { struct kvm_page_fault fault = { .addr = cr2_or_gpa, @@ -298,7 +306,10 @@ static inline int kvm_mmu_do_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, .max_level = KVM_MAX_HUGEPAGE_LEVEL, .req_level = PG_LEVEL_4K, .goal_level = PG_LEVEL_4K, - .is_private = kvm_mem_is_private(vcpu->kvm, cr2_or_gpa >> PAGE_SHIFT), + .is_private = err & PFERR_PRIVATE_ACCESS, + + .pfn = KVM_PFN_ERR_FAULT, + .hva = KVM_HVA_ERR_BAD, }; int r; @@ -320,6 +331,17 @@ static inline int kvm_mmu_do_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, else r = vcpu->arch.mmu->page_fault(vcpu, &fault); + /* + * Not sure what's happening, but punt to userspace and hope that + * they can fix it by changing memory to shared, or they can + * provide a better error. + */ + if (r == RET_PF_EMULATE && fault.is_private) { + pr_warn_ratelimited("kvm: unexpected emulation request on private memory\n"); + kvm_mmu_prepare_memory_fault_exit(vcpu, &fault); + return -EFAULT; + } + if (fault.write_fault_to_shadow_pgtable && emulation_type) *emulation_type |= EMULTYPE_WRITE_PF_TO_SP; diff --git a/arch/x86/kvm/mmu/mmutrace.h b/arch/x86/kvm/mmu/mmutrace.h index ae86820cef69..195d98bc8de8 100644 --- a/arch/x86/kvm/mmu/mmutrace.h +++ b/arch/x86/kvm/mmu/mmutrace.h @@ -260,7 +260,7 @@ TRACE_EVENT( TP_STRUCT__entry( __field(int, vcpu_id) __field(gpa_t, cr2_or_gpa) - __field(u32, error_code) + __field(u64, error_code) __field(u64 *, sptep) __field(u64, old_spte) __field(u64, new_spte) diff --git a/arch/x86/kvm/mmu/page_track.c b/arch/x86/kvm/mmu/page_track.c index f6448284c18e..561c331fd6ec 100644 --- a/arch/x86/kvm/mmu/page_track.c +++ b/arch/x86/kvm/mmu/page_track.c @@ -41,7 +41,7 @@ bool kvm_page_track_write_tracking_enabled(struct kvm *kvm) void kvm_page_track_free_memslot(struct kvm_memory_slot *slot) { - kvfree(slot->arch.gfn_write_track); + vfree(slot->arch.gfn_write_track); slot->arch.gfn_write_track = NULL; } diff --git a/arch/x86/kvm/mmu/paging_tmpl.h b/arch/x86/kvm/mmu/paging_tmpl.h index 4d4e98fe4f35..d3dbcf382ed2 100644 --- a/arch/x86/kvm/mmu/paging_tmpl.h +++ b/arch/x86/kvm/mmu/paging_tmpl.h @@ -497,21 +497,21 @@ error: * The other bits are set to 0. */ if (!(errcode & PFERR_RSVD_MASK)) { - vcpu->arch.exit_qualification &= (EPT_VIOLATION_GVA_IS_VALID | - EPT_VIOLATION_GVA_TRANSLATED); + walker->fault.exit_qualification = 0; + if (write_fault) - vcpu->arch.exit_qualification |= EPT_VIOLATION_ACC_WRITE; + walker->fault.exit_qualification |= EPT_VIOLATION_ACC_WRITE; if (user_fault) - vcpu->arch.exit_qualification |= EPT_VIOLATION_ACC_READ; + walker->fault.exit_qualification |= EPT_VIOLATION_ACC_READ; if (fetch_fault) - vcpu->arch.exit_qualification |= EPT_VIOLATION_ACC_INSTR; + walker->fault.exit_qualification |= EPT_VIOLATION_ACC_INSTR; /* * Note, pte_access holds the raw RWX bits from the EPTE, not * ACC_*_MASK flags! */ - vcpu->arch.exit_qualification |= (pte_access & VMX_EPT_RWX_MASK) << - EPT_VIOLATION_RWX_SHIFT; + walker->fault.exit_qualification |= (pte_access & VMX_EPT_RWX_MASK) << + EPT_VIOLATION_RWX_SHIFT; } #endif walker->fault.address = addr; @@ -911,7 +911,7 @@ static int FNAME(sync_spte)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp, int gpa_t pte_gpa; gfn_t gfn; - if (WARN_ON_ONCE(!sp->spt[i])) + if (WARN_ON_ONCE(sp->spt[i] == SHADOW_NONPRESENT_VALUE)) return 0; first_pte_gpa = FNAME(get_level1_sp_gpa)(sp); @@ -933,13 +933,13 @@ static int FNAME(sync_spte)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp, int return 0; /* - * Drop the SPTE if the new protections would result in a RWX=0 - * SPTE or if the gfn is changing. The RWX=0 case only affects - * EPT with execute-only support, i.e. EPT without an effective - * "present" bit, as all other paging modes will create a - * read-only SPTE if pte_access is zero. + * Drop the SPTE if the new protections result in no effective + * "present" bit or if the gfn is changing. The former case + * only affects EPT with execute-only support with pte_access==0; + * all other paging modes will create a read-only SPTE if + * pte_access is zero. */ - if ((!pte_access && !shadow_present_mask) || + if ((pte_access | shadow_present_mask) == SHADOW_NONPRESENT_VALUE || gfn != kvm_mmu_page_get_gfn(sp, i)) { drop_spte(vcpu->kvm, &sp->spt[i]); return 1; diff --git a/arch/x86/kvm/mmu/spte.c b/arch/x86/kvm/mmu/spte.c index 4a599130e9c9..a5e014d7bc62 100644 --- a/arch/x86/kvm/mmu/spte.c +++ b/arch/x86/kvm/mmu/spte.c @@ -74,10 +74,10 @@ u64 make_mmio_spte(struct kvm_vcpu *vcpu, u64 gfn, unsigned int access) u64 spte = generation_mmio_spte_mask(gen); u64 gpa = gfn << PAGE_SHIFT; - WARN_ON_ONCE(!shadow_mmio_value); + WARN_ON_ONCE(!vcpu->kvm->arch.shadow_mmio_value); access &= shadow_mmio_access_mask; - spte |= shadow_mmio_value | access; + spte |= vcpu->kvm->arch.shadow_mmio_value | access; spte |= gpa | shadow_nonpresent_or_rsvd_mask; spte |= (gpa & shadow_nonpresent_or_rsvd_mask) << SHADOW_NONPRESENT_OR_RSVD_MASK_LEN; @@ -144,19 +144,19 @@ bool make_spte(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp, u64 spte = SPTE_MMU_PRESENT_MASK; bool wrprot = false; - WARN_ON_ONCE(!pte_access && !shadow_present_mask); + /* + * For the EPT case, shadow_present_mask has no RWX bits set if + * exec-only page table entries are supported. In that case, + * ACC_USER_MASK and shadow_user_mask are used to represent + * read access. See FNAME(gpte_access) in paging_tmpl.h. + */ + WARN_ON_ONCE((pte_access | shadow_present_mask) == SHADOW_NONPRESENT_VALUE); if (sp->role.ad_disabled) spte |= SPTE_TDP_AD_DISABLED; else if (kvm_mmu_page_ad_need_write_protect(sp)) spte |= SPTE_TDP_AD_WRPROT_ONLY; - /* - * For the EPT case, shadow_present_mask is 0 if hardware - * supports exec-only page table entries. In that case, - * ACC_USER_MASK and shadow_user_mask are used to represent - * read access. See FNAME(gpte_access) in paging_tmpl.h. - */ spte |= shadow_present_mask; if (!prefetch) spte |= spte_shadow_accessed_mask(spte); @@ -322,22 +322,6 @@ u64 make_nonleaf_spte(u64 *child_pt, bool ad_disabled) return spte; } -u64 kvm_mmu_changed_pte_notifier_make_spte(u64 old_spte, kvm_pfn_t new_pfn) -{ - u64 new_spte; - - new_spte = old_spte & ~SPTE_BASE_ADDR_MASK; - new_spte |= (u64)new_pfn << PAGE_SHIFT; - - new_spte &= ~PT_WRITABLE_MASK; - new_spte &= ~shadow_host_writable_mask; - new_spte &= ~shadow_mmu_writable_mask; - - new_spte = mark_spte_for_access_track(new_spte); - - return new_spte; -} - u64 mark_spte_for_access_track(u64 spte) { if (spte_ad_enabled(spte)) @@ -429,7 +413,9 @@ void kvm_mmu_set_ept_masks(bool has_ad_bits, bool has_exec_only) shadow_dirty_mask = has_ad_bits ? VMX_EPT_DIRTY_BIT : 0ull; shadow_nx_mask = 0ull; shadow_x_mask = VMX_EPT_EXECUTABLE_MASK; - shadow_present_mask = has_exec_only ? 0ull : VMX_EPT_READABLE_MASK; + /* VMX_EPT_SUPPRESS_VE_BIT is needed for W or X violation. */ + shadow_present_mask = + (has_exec_only ? 0ull : VMX_EPT_READABLE_MASK) | VMX_EPT_SUPPRESS_VE_BIT; /* * EPT overrides the host MTRRs, and so KVM must program the desired * memtype directly into the SPTEs. Note, this mask is just the mask @@ -446,7 +432,7 @@ void kvm_mmu_set_ept_masks(bool has_ad_bits, bool has_exec_only) * of an EPT paging-structure entry is 110b (write/execute). */ kvm_mmu_set_mmio_spte_mask(VMX_EPT_MISCONFIG_WX_VALUE, - VMX_EPT_RWX_MASK, 0); + VMX_EPT_RWX_MASK | VMX_EPT_SUPPRESS_VE_BIT, 0); } EXPORT_SYMBOL_GPL(kvm_mmu_set_ept_masks); diff --git a/arch/x86/kvm/mmu/spte.h b/arch/x86/kvm/mmu/spte.h index a129951c9a88..5dd5405fa07a 100644 --- a/arch/x86/kvm/mmu/spte.h +++ b/arch/x86/kvm/mmu/spte.h @@ -149,6 +149,22 @@ static_assert(MMIO_SPTE_GEN_LOW_BITS == 8 && MMIO_SPTE_GEN_HIGH_BITS == 11); #define MMIO_SPTE_GEN_MASK GENMASK_ULL(MMIO_SPTE_GEN_LOW_BITS + MMIO_SPTE_GEN_HIGH_BITS - 1, 0) +/* + * Non-present SPTE value needs to set bit 63 for TDX, in order to suppress + * #VE and get EPT violations on non-present PTEs. We can use the + * same value also without TDX for both VMX and SVM: + * + * For SVM NPT, for non-present spte (bit 0 = 0), other bits are ignored. + * For VMX EPT, bit 63 is ignored if #VE is disabled. (EPT_VIOLATION_VE=0) + * bit 63 is #VE suppress if #VE is enabled. (EPT_VIOLATION_VE=1) + */ +#ifdef CONFIG_X86_64 +#define SHADOW_NONPRESENT_VALUE BIT_ULL(63) +static_assert(!(SHADOW_NONPRESENT_VALUE & SPTE_MMU_PRESENT_MASK)); +#else +#define SHADOW_NONPRESENT_VALUE 0ULL +#endif + extern u64 __read_mostly shadow_host_writable_mask; extern u64 __read_mostly shadow_mmu_writable_mask; extern u64 __read_mostly shadow_nx_mask; @@ -190,11 +206,11 @@ extern u64 __read_mostly shadow_nonpresent_or_rsvd_mask; * * Use a semi-arbitrary value that doesn't set RWX bits, i.e. is not-present on * both AMD and Intel CPUs, and doesn't set PFN bits, i.e. doesn't create a L1TF - * vulnerability. Use only low bits to avoid 64-bit immediates. + * vulnerability. * * Only used by the TDP MMU. */ -#define REMOVED_SPTE 0x5a0ULL +#define REMOVED_SPTE (SHADOW_NONPRESENT_VALUE | 0x5a0ULL) /* Removed SPTEs must not be misconstrued as shadow present PTEs. */ static_assert(!(REMOVED_SPTE & SPTE_MMU_PRESENT_MASK)); @@ -249,9 +265,9 @@ static inline struct kvm_mmu_page *root_to_sp(hpa_t root) return spte_to_child_sp(root); } -static inline bool is_mmio_spte(u64 spte) +static inline bool is_mmio_spte(struct kvm *kvm, u64 spte) { - return (spte & shadow_mmio_mask) == shadow_mmio_value && + return (spte & shadow_mmio_mask) == kvm->arch.shadow_mmio_value && likely(enable_mmio_caching); } @@ -496,8 +512,6 @@ static inline u64 restore_acc_track_spte(u64 spte) return spte; } -u64 kvm_mmu_changed_pte_notifier_make_spte(u64 old_spte, kvm_pfn_t new_pfn); - void __init kvm_mmu_spte_module_init(void); void kvm_mmu_reset_all_pte_masks(void); diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c index 04c1f0957fea..1259dd63defc 100644 --- a/arch/x86/kvm/mmu/tdp_mmu.c +++ b/arch/x86/kvm/mmu/tdp_mmu.c @@ -495,8 +495,8 @@ static void handle_changed_spte(struct kvm *kvm, int as_id, gfn_t gfn, * impact the guest since both the former and current SPTEs * are nonpresent. */ - if (WARN_ON_ONCE(!is_mmio_spte(old_spte) && - !is_mmio_spte(new_spte) && + if (WARN_ON_ONCE(!is_mmio_spte(kvm, old_spte) && + !is_mmio_spte(kvm, new_spte) && !is_removed_spte(new_spte))) pr_err("Unexpected SPTE change! Nonpresent SPTEs\n" "should not be replaced with another,\n" @@ -530,6 +530,31 @@ static void handle_changed_spte(struct kvm *kvm, int as_id, gfn_t gfn, kvm_set_pfn_accessed(spte_to_pfn(old_spte)); } +static inline int __tdp_mmu_set_spte_atomic(struct tdp_iter *iter, u64 new_spte) +{ + u64 *sptep = rcu_dereference(iter->sptep); + + /* + * The caller is responsible for ensuring the old SPTE is not a REMOVED + * SPTE. KVM should never attempt to zap or manipulate a REMOVED SPTE, + * and pre-checking before inserting a new SPTE is advantageous as it + * avoids unnecessary work. + */ + WARN_ON_ONCE(iter->yielded || is_removed_spte(iter->old_spte)); + + /* + * Note, fast_pf_fix_direct_spte() can also modify TDP MMU SPTEs and + * does not hold the mmu_lock. On failure, i.e. if a different logical + * CPU modified the SPTE, try_cmpxchg64() updates iter->old_spte with + * the current value, so the caller operates on fresh data, e.g. if it + * retries tdp_mmu_set_spte_atomic() + */ + if (!try_cmpxchg64(sptep, &iter->old_spte, new_spte)) + return -EBUSY; + + return 0; +} + /* * tdp_mmu_set_spte_atomic - Set a TDP MMU SPTE atomically * and handle the associated bookkeeping. Do not mark the page dirty @@ -551,27 +576,13 @@ static inline int tdp_mmu_set_spte_atomic(struct kvm *kvm, struct tdp_iter *iter, u64 new_spte) { - u64 *sptep = rcu_dereference(iter->sptep); - - /* - * The caller is responsible for ensuring the old SPTE is not a REMOVED - * SPTE. KVM should never attempt to zap or manipulate a REMOVED SPTE, - * and pre-checking before inserting a new SPTE is advantageous as it - * avoids unnecessary work. - */ - WARN_ON_ONCE(iter->yielded || is_removed_spte(iter->old_spte)); + int ret; lockdep_assert_held_read(&kvm->mmu_lock); - /* - * Note, fast_pf_fix_direct_spte() can also modify TDP MMU SPTEs and - * does not hold the mmu_lock. On failure, i.e. if a different logical - * CPU modified the SPTE, try_cmpxchg64() updates iter->old_spte with - * the current value, so the caller operates on fresh data, e.g. if it - * retries tdp_mmu_set_spte_atomic() - */ - if (!try_cmpxchg64(sptep, &iter->old_spte, new_spte)) - return -EBUSY; + ret = __tdp_mmu_set_spte_atomic(iter, new_spte); + if (ret) + return ret; handle_changed_spte(kvm, iter->as_id, iter->gfn, iter->old_spte, new_spte, iter->level, true); @@ -584,13 +595,17 @@ static inline int tdp_mmu_zap_spte_atomic(struct kvm *kvm, { int ret; + lockdep_assert_held_read(&kvm->mmu_lock); + /* - * Freeze the SPTE by setting it to a special, - * non-present value. This will stop other threads from - * immediately installing a present entry in its place - * before the TLBs are flushed. + * Freeze the SPTE by setting it to a special, non-present value. This + * will stop other threads from immediately installing a present entry + * in its place before the TLBs are flushed. + * + * Delay processing of the zapped SPTE until after TLBs are flushed and + * the REMOVED_SPTE is replaced (see below). */ - ret = tdp_mmu_set_spte_atomic(kvm, iter, REMOVED_SPTE); + ret = __tdp_mmu_set_spte_atomic(iter, REMOVED_SPTE); if (ret) return ret; @@ -599,11 +614,19 @@ static inline int tdp_mmu_zap_spte_atomic(struct kvm *kvm, /* * No other thread can overwrite the removed SPTE as they must either * wait on the MMU lock or use tdp_mmu_set_spte_atomic() which will not - * overwrite the special removed SPTE value. No bookkeeping is needed - * here since the SPTE is going from non-present to non-present. Use - * the raw write helper to avoid an unnecessary check on volatile bits. + * overwrite the special removed SPTE value. Use the raw write helper to + * avoid an unnecessary check on volatile bits. */ - __kvm_tdp_mmu_write_spte(iter->sptep, 0); + __kvm_tdp_mmu_write_spte(iter->sptep, SHADOW_NONPRESENT_VALUE); + + /* + * Process the zapped SPTE after flushing TLBs, and after replacing + * REMOVED_SPTE with 0. This minimizes the amount of time vCPUs are + * blocked by the REMOVED_SPTE and reduces contention on the child + * SPTEs. + */ + handle_changed_spte(kvm, iter->as_id, iter->gfn, iter->old_spte, + 0, iter->level, true); return 0; } @@ -740,8 +763,8 @@ retry: continue; if (!shared) - tdp_mmu_iter_set_spte(kvm, &iter, 0); - else if (tdp_mmu_set_spte_atomic(kvm, &iter, 0)) + tdp_mmu_iter_set_spte(kvm, &iter, SHADOW_NONPRESENT_VALUE); + else if (tdp_mmu_set_spte_atomic(kvm, &iter, SHADOW_NONPRESENT_VALUE)) goto retry; } } @@ -808,8 +831,8 @@ bool kvm_tdp_mmu_zap_sp(struct kvm *kvm, struct kvm_mmu_page *sp) if (WARN_ON_ONCE(!is_shadow_present_pte(old_spte))) return false; - tdp_mmu_set_spte(kvm, kvm_mmu_page_as_id(sp), sp->ptep, old_spte, 0, - sp->gfn, sp->role.level + 1); + tdp_mmu_set_spte(kvm, kvm_mmu_page_as_id(sp), sp->ptep, old_spte, + SHADOW_NONPRESENT_VALUE, sp->gfn, sp->role.level + 1); return true; } @@ -843,7 +866,7 @@ static bool tdp_mmu_zap_leafs(struct kvm *kvm, struct kvm_mmu_page *root, !is_last_spte(iter.old_spte, iter.level)) continue; - tdp_mmu_iter_set_spte(kvm, &iter, 0); + tdp_mmu_iter_set_spte(kvm, &iter, SHADOW_NONPRESENT_VALUE); /* * Zappings SPTEs in invalid roots doesn't require a TLB flush, @@ -1028,7 +1051,7 @@ static int tdp_mmu_map_handle_target_level(struct kvm_vcpu *vcpu, } /* If a MMIO SPTE is installed, the MMIO will need to be emulated. */ - if (unlikely(is_mmio_spte(new_spte))) { + if (unlikely(is_mmio_spte(vcpu->kvm, new_spte))) { vcpu->stat.pf_mmio_spte_created++; trace_mark_mmio_spte(rcu_dereference(iter->sptep), iter->gfn, new_spte); @@ -1258,52 +1281,6 @@ bool kvm_tdp_mmu_test_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range) return kvm_tdp_mmu_handle_gfn(kvm, range, test_age_gfn); } -static bool set_spte_gfn(struct kvm *kvm, struct tdp_iter *iter, - struct kvm_gfn_range *range) -{ - u64 new_spte; - - /* Huge pages aren't expected to be modified without first being zapped. */ - WARN_ON_ONCE(pte_huge(range->arg.pte) || range->start + 1 != range->end); - - if (iter->level != PG_LEVEL_4K || - !is_shadow_present_pte(iter->old_spte)) - return false; - - /* - * Note, when changing a read-only SPTE, it's not strictly necessary to - * zero the SPTE before setting the new PFN, but doing so preserves the - * invariant that the PFN of a present * leaf SPTE can never change. - * See handle_changed_spte(). - */ - tdp_mmu_iter_set_spte(kvm, iter, 0); - - if (!pte_write(range->arg.pte)) { - new_spte = kvm_mmu_changed_pte_notifier_make_spte(iter->old_spte, - pte_pfn(range->arg.pte)); - - tdp_mmu_iter_set_spte(kvm, iter, new_spte); - } - - return true; -} - -/* - * Handle the changed_pte MMU notifier for the TDP MMU. - * data is a pointer to the new pte_t mapping the HVA specified by the MMU - * notifier. - * Returns non-zero if a flush is needed before releasing the MMU lock. - */ -bool kvm_tdp_mmu_set_spte_gfn(struct kvm *kvm, struct kvm_gfn_range *range) -{ - /* - * No need to handle the remote TLB flush under RCU protection, the - * target SPTE _must_ be a leaf SPTE, i.e. cannot result in freeing a - * shadow page. See the WARN on pfn_changed in handle_changed_spte(). - */ - return kvm_tdp_mmu_handle_gfn(kvm, range, set_spte_gfn); -} - /* * Remove write access from all SPTEs at or above min_level that map GFNs * [start, end). Returns true if an SPTE has been changed and the TLBs need to diff --git a/arch/x86/kvm/mmu/tdp_mmu.h b/arch/x86/kvm/mmu/tdp_mmu.h index 6e1ea04ca885..58b55e61bd33 100644 --- a/arch/x86/kvm/mmu/tdp_mmu.h +++ b/arch/x86/kvm/mmu/tdp_mmu.h @@ -31,7 +31,6 @@ bool kvm_tdp_mmu_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range, bool flush); bool kvm_tdp_mmu_age_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range); bool kvm_tdp_mmu_test_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range); -bool kvm_tdp_mmu_set_spte_gfn(struct kvm *kvm, struct kvm_gfn_range *range); bool kvm_tdp_mmu_wrprot_slot(struct kvm *kvm, const struct kvm_memory_slot *slot, int min_level); diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c index 759581bb2128..0623cfaa7bb0 100644 --- a/arch/x86/kvm/svm/sev.c +++ b/arch/x86/kvm/svm/sev.c @@ -23,6 +23,7 @@ #include <asm/pkru.h> #include <asm/trapnr.h> #include <asm/fpu/xcr.h> +#include <asm/fpu/xstate.h> #include <asm/debugreg.h> #include "mmu.h" @@ -32,22 +33,12 @@ #include "cpuid.h" #include "trace.h" -#ifndef CONFIG_KVM_AMD_SEV -/* - * When this config is not defined, SEV feature is not supported and APIs in - * this file are not used but this file still gets compiled into the KVM AMD - * module. - * - * We will not have MISC_CG_RES_SEV and MISC_CG_RES_SEV_ES entries in the enum - * misc_res_type {} defined in linux/misc_cgroup.h. - * - * Below macros allow compilation to succeed. - */ -#define MISC_CG_RES_SEV MISC_CG_RES_TYPES -#define MISC_CG_RES_SEV_ES MISC_CG_RES_TYPES -#endif +#define GHCB_VERSION_MAX 2ULL +#define GHCB_VERSION_DEFAULT 2ULL +#define GHCB_VERSION_MIN 1ULL + +#define GHCB_HV_FT_SUPPORTED GHCB_HV_FT_SNP -#ifdef CONFIG_KVM_AMD_SEV /* enable/disable SEV support */ static bool sev_enabled = true; module_param_named(sev, sev_enabled, bool, 0444); @@ -57,13 +48,13 @@ static bool sev_es_enabled = true; module_param_named(sev_es, sev_es_enabled, bool, 0444); /* enable/disable SEV-ES DebugSwap support */ -static bool sev_es_debug_swap_enabled = false; +static bool sev_es_debug_swap_enabled = true; module_param_named(debug_swap, sev_es_debug_swap_enabled, bool, 0444); -#else -#define sev_enabled false -#define sev_es_enabled false -#define sev_es_debug_swap_enabled false -#endif /* CONFIG_KVM_AMD_SEV */ +static u64 sev_supported_vmsa_features; + +#define AP_RESET_HOLD_NONE 0 +#define AP_RESET_HOLD_NAE_EVENT 1 +#define AP_RESET_HOLD_MSR_PROTO 2 static u8 sev_enc_bit; static DECLARE_RWSEM(sev_deactivate_lock); @@ -113,7 +104,15 @@ static int sev_flush_asids(unsigned int min_asid, unsigned int max_asid) static inline bool is_mirroring_enc_context(struct kvm *kvm) { - return !!to_kvm_svm(kvm)->sev_info.enc_context_owner; + return !!to_kvm_sev_info(kvm)->enc_context_owner; +} + +static bool sev_vcpu_has_debug_swap(struct vcpu_svm *svm) +{ + struct kvm_vcpu *vcpu = &svm->vcpu; + struct kvm_sev_info *sev = &to_kvm_svm(vcpu->kvm)->sev_info; + + return sev->vmsa_features & SVM_SEV_FEAT_DEBUG_SWAP; } /* Must be called with the sev_bitmap_lock held */ @@ -251,20 +250,44 @@ static void sev_unbind_asid(struct kvm *kvm, unsigned int handle) sev_decommission(handle); } -static int sev_guest_init(struct kvm *kvm, struct kvm_sev_cmd *argp) +static int __sev_guest_init(struct kvm *kvm, struct kvm_sev_cmd *argp, + struct kvm_sev_init *data, + unsigned long vm_type) { struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info; struct sev_platform_init_args init_args = {0}; + bool es_active = vm_type != KVM_X86_SEV_VM; + u64 valid_vmsa_features = es_active ? sev_supported_vmsa_features : 0; int ret; if (kvm->created_vcpus) return -EINVAL; + if (data->flags) + return -EINVAL; + + if (data->vmsa_features & ~valid_vmsa_features) + return -EINVAL; + + if (data->ghcb_version > GHCB_VERSION_MAX || (!es_active && data->ghcb_version)) + return -EINVAL; + if (unlikely(sev->active)) return -EINVAL; sev->active = true; - sev->es_active = argp->id == KVM_SEV_ES_INIT; + sev->es_active = es_active; + sev->vmsa_features = data->vmsa_features; + sev->ghcb_version = data->ghcb_version; + + /* + * Currently KVM supports the full range of mandatory features defined + * by version 2 of the GHCB protocol, so default to that for SEV-ES + * guests created via KVM_SEV_INIT2. + */ + if (sev->es_active && !sev->ghcb_version) + sev->ghcb_version = GHCB_VERSION_DEFAULT; + ret = sev_asid_new(sev); if (ret) goto e_no_asid; @@ -276,6 +299,7 @@ static int sev_guest_init(struct kvm *kvm, struct kvm_sev_cmd *argp) INIT_LIST_HEAD(&sev->regions_list); INIT_LIST_HEAD(&sev->mirror_vms); + sev->need_init = false; kvm_set_apicv_inhibit(kvm, APICV_INHIBIT_REASON_SEV); @@ -286,11 +310,53 @@ e_free: sev_asid_free(sev); sev->asid = 0; e_no_asid: + sev->vmsa_features = 0; sev->es_active = false; sev->active = false; return ret; } +static int sev_guest_init(struct kvm *kvm, struct kvm_sev_cmd *argp) +{ + struct kvm_sev_init data = { + .vmsa_features = 0, + .ghcb_version = 0, + }; + unsigned long vm_type; + + if (kvm->arch.vm_type != KVM_X86_DEFAULT_VM) + return -EINVAL; + + vm_type = (argp->id == KVM_SEV_INIT ? KVM_X86_SEV_VM : KVM_X86_SEV_ES_VM); + + /* + * KVM_SEV_ES_INIT has been deprecated by KVM_SEV_INIT2, so it will + * continue to only ever support the minimal GHCB protocol version. + */ + if (vm_type == KVM_X86_SEV_ES_VM) + data.ghcb_version = GHCB_VERSION_MIN; + + return __sev_guest_init(kvm, argp, &data, vm_type); +} + +static int sev_guest_init2(struct kvm *kvm, struct kvm_sev_cmd *argp) +{ + struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info; + struct kvm_sev_init data; + + if (!sev->need_init) + return -EINVAL; + + if (kvm->arch.vm_type != KVM_X86_SEV_VM && + kvm->arch.vm_type != KVM_X86_SEV_ES_VM) + return -EINVAL; + + if (copy_from_user(&data, u64_to_user_ptr(argp->data), sizeof(data))) + return -EFAULT; + + return __sev_guest_init(kvm, argp, &data, kvm->arch.vm_type); +} + static int sev_bind_asid(struct kvm *kvm, unsigned int handle, int *error) { unsigned int asid = sev_get_asid(kvm); @@ -339,7 +405,7 @@ static int sev_launch_start(struct kvm *kvm, struct kvm_sev_cmd *argp) if (!sev_guest(kvm)) return -ENOTTY; - if (copy_from_user(¶ms, (void __user *)(uintptr_t)argp->data, sizeof(params))) + if (copy_from_user(¶ms, u64_to_user_ptr(argp->data), sizeof(params))) return -EFAULT; memset(&start, 0, sizeof(start)); @@ -383,7 +449,7 @@ static int sev_launch_start(struct kvm *kvm, struct kvm_sev_cmd *argp) /* return handle to userspace */ params.handle = start.handle; - if (copy_to_user((void __user *)(uintptr_t)argp->data, ¶ms, sizeof(params))) { + if (copy_to_user(u64_to_user_ptr(argp->data), ¶ms, sizeof(params))) { sev_unbind_asid(kvm, start.handle); ret = -EFAULT; goto e_free_session; @@ -522,7 +588,7 @@ static int sev_launch_update_data(struct kvm *kvm, struct kvm_sev_cmd *argp) if (!sev_guest(kvm)) return -ENOTTY; - if (copy_from_user(¶ms, (void __user *)(uintptr_t)argp->data, sizeof(params))) + if (copy_from_user(¶ms, u64_to_user_ptr(argp->data), sizeof(params))) return -EFAULT; vaddr = params.uaddr; @@ -580,7 +646,13 @@ e_unpin: static int sev_es_sync_vmsa(struct vcpu_svm *svm) { + struct kvm_vcpu *vcpu = &svm->vcpu; + struct kvm_sev_info *sev = &to_kvm_svm(vcpu->kvm)->sev_info; struct sev_es_save_area *save = svm->sev_es.vmsa; + struct xregs_state *xsave; + const u8 *s; + u8 *d; + int i; /* Check some debug related fields before encrypting the VMSA */ if (svm->vcpu.guest_debug || (svm->vmcb->save.dr7 & ~DR7_FIXED_1)) @@ -621,10 +693,44 @@ static int sev_es_sync_vmsa(struct vcpu_svm *svm) save->xss = svm->vcpu.arch.ia32_xss; save->dr6 = svm->vcpu.arch.dr6; - if (sev_es_debug_swap_enabled) { - save->sev_features |= SVM_SEV_FEAT_DEBUG_SWAP; - pr_warn_once("Enabling DebugSwap with KVM_SEV_ES_INIT. " - "This will not work starting with Linux 6.10\n"); + save->sev_features = sev->vmsa_features; + + /* + * Skip FPU and AVX setup with KVM_SEV_ES_INIT to avoid + * breaking older measurements. + */ + if (vcpu->kvm->arch.vm_type != KVM_X86_DEFAULT_VM) { + xsave = &vcpu->arch.guest_fpu.fpstate->regs.xsave; + save->x87_dp = xsave->i387.rdp; + save->mxcsr = xsave->i387.mxcsr; + save->x87_ftw = xsave->i387.twd; + save->x87_fsw = xsave->i387.swd; + save->x87_fcw = xsave->i387.cwd; + save->x87_fop = xsave->i387.fop; + save->x87_ds = 0; + save->x87_cs = 0; + save->x87_rip = xsave->i387.rip; + + for (i = 0; i < 8; i++) { + /* + * The format of the x87 save area is undocumented and + * definitely not what you would expect. It consists of + * an 8*8 bytes area with bytes 0-7, and an 8*2 bytes + * area with bytes 8-9 of each register. + */ + d = save->fpreg_x87 + i * 8; + s = ((u8 *)xsave->i387.st_space) + i * 16; + memcpy(d, s, 8); + save->fpreg_x87[64 + i * 2] = s[8]; + save->fpreg_x87[64 + i * 2 + 1] = s[9]; + } + memcpy(save->fpreg_xmm, xsave->i387.xmm_space, 256); + + s = get_xsave_addr(xsave, XFEATURE_YMM); + if (s) + memcpy(save->fpreg_ymm, s, 256); + else + memset(save->fpreg_ymm, 0, 256); } pr_debug("Virtual Machine Save Area (VMSA):\n"); @@ -658,13 +764,20 @@ static int __sev_launch_update_vmsa(struct kvm *kvm, struct kvm_vcpu *vcpu, clflush_cache_range(svm->sev_es.vmsa, PAGE_SIZE); vmsa.reserved = 0; - vmsa.handle = to_kvm_svm(kvm)->sev_info.handle; + vmsa.handle = to_kvm_sev_info(kvm)->handle; 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) return ret; + /* + * SEV-ES guests maintain an encrypted version of their FPU + * state which is restored and saved on VMRUN and VMEXIT. + * Mark vcpu->arch.guest_fpu->fpstate as scratch so it won't + * do xsave/xrstor on it. + */ + fpstate_set_confidential(&vcpu->arch.guest_fpu); vcpu->arch.guest_state_protected = true; return 0; } @@ -695,7 +808,7 @@ static int sev_launch_update_vmsa(struct kvm *kvm, struct kvm_sev_cmd *argp) static int sev_launch_measure(struct kvm *kvm, struct kvm_sev_cmd *argp) { - void __user *measure = (void __user *)(uintptr_t)argp->data; + void __user *measure = u64_to_user_ptr(argp->data); struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info; struct sev_data_launch_measure data; struct kvm_sev_launch_measure params; @@ -715,7 +828,7 @@ static int sev_launch_measure(struct kvm *kvm, struct kvm_sev_cmd *argp) if (!params.len) goto cmd; - p = (void __user *)(uintptr_t)params.uaddr; + p = u64_to_user_ptr(params.uaddr); if (p) { if (params.len > SEV_FW_BLOB_MAX_SIZE) return -EINVAL; @@ -788,7 +901,7 @@ static int sev_guest_status(struct kvm *kvm, struct kvm_sev_cmd *argp) params.state = data.state; params.handle = data.handle; - if (copy_to_user((void __user *)(uintptr_t)argp->data, ¶ms, sizeof(params))) + if (copy_to_user(u64_to_user_ptr(argp->data), ¶ms, sizeof(params))) ret = -EFAULT; return ret; @@ -953,7 +1066,7 @@ static int sev_dbg_crypt(struct kvm *kvm, struct kvm_sev_cmd *argp, bool dec) if (!sev_guest(kvm)) return -ENOTTY; - if (copy_from_user(&debug, (void __user *)(uintptr_t)argp->data, sizeof(debug))) + if (copy_from_user(&debug, u64_to_user_ptr(argp->data), sizeof(debug))) return -EFAULT; if (!debug.len || debug.src_uaddr + debug.len < debug.src_uaddr) @@ -1037,7 +1150,7 @@ static int sev_launch_secret(struct kvm *kvm, struct kvm_sev_cmd *argp) if (!sev_guest(kvm)) return -ENOTTY; - if (copy_from_user(¶ms, (void __user *)(uintptr_t)argp->data, sizeof(params))) + if (copy_from_user(¶ms, u64_to_user_ptr(argp->data), sizeof(params))) return -EFAULT; pages = sev_pin_memory(kvm, params.guest_uaddr, params.guest_len, &n, 1); @@ -1101,7 +1214,7 @@ e_unpin_memory: static int sev_get_attestation_report(struct kvm *kvm, struct kvm_sev_cmd *argp) { - void __user *report = (void __user *)(uintptr_t)argp->data; + void __user *report = u64_to_user_ptr(argp->data); struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info; struct sev_data_attestation_report data; struct kvm_sev_attestation_report params; @@ -1112,7 +1225,7 @@ static int sev_get_attestation_report(struct kvm *kvm, struct kvm_sev_cmd *argp) if (!sev_guest(kvm)) return -ENOTTY; - if (copy_from_user(¶ms, (void __user *)(uintptr_t)argp->data, sizeof(params))) + if (copy_from_user(¶ms, u64_to_user_ptr(argp->data), sizeof(params))) return -EFAULT; memset(&data, 0, sizeof(data)); @@ -1121,7 +1234,7 @@ static int sev_get_attestation_report(struct kvm *kvm, struct kvm_sev_cmd *argp) if (!params.len) goto cmd; - p = (void __user *)(uintptr_t)params.uaddr; + p = u64_to_user_ptr(params.uaddr); if (p) { if (params.len > SEV_FW_BLOB_MAX_SIZE) return -EINVAL; @@ -1174,7 +1287,7 @@ __sev_send_start_query_session_length(struct kvm *kvm, struct kvm_sev_cmd *argp, ret = sev_issue_cmd(kvm, SEV_CMD_SEND_START, &data, &argp->error); params->session_len = data.session_len; - if (copy_to_user((void __user *)(uintptr_t)argp->data, params, + if (copy_to_user(u64_to_user_ptr(argp->data), params, sizeof(struct kvm_sev_send_start))) ret = -EFAULT; @@ -1193,7 +1306,7 @@ static int sev_send_start(struct kvm *kvm, struct kvm_sev_cmd *argp) if (!sev_guest(kvm)) return -ENOTTY; - if (copy_from_user(¶ms, (void __user *)(uintptr_t)argp->data, + if (copy_from_user(¶ms, u64_to_user_ptr(argp->data), sizeof(struct kvm_sev_send_start))) return -EFAULT; @@ -1248,7 +1361,7 @@ static int sev_send_start(struct kvm *kvm, struct kvm_sev_cmd *argp) ret = sev_issue_cmd(kvm, SEV_CMD_SEND_START, &data, &argp->error); - if (!ret && copy_to_user((void __user *)(uintptr_t)params.session_uaddr, + if (!ret && copy_to_user(u64_to_user_ptr(params.session_uaddr), session_data, params.session_len)) { ret = -EFAULT; goto e_free_amd_cert; @@ -1256,7 +1369,7 @@ static int sev_send_start(struct kvm *kvm, struct kvm_sev_cmd *argp) params.policy = data.policy; params.session_len = data.session_len; - if (copy_to_user((void __user *)(uintptr_t)argp->data, ¶ms, + if (copy_to_user(u64_to_user_ptr(argp->data), ¶ms, sizeof(struct kvm_sev_send_start))) ret = -EFAULT; @@ -1287,7 +1400,7 @@ __sev_send_update_data_query_lengths(struct kvm *kvm, struct kvm_sev_cmd *argp, params->hdr_len = data.hdr_len; params->trans_len = data.trans_len; - if (copy_to_user((void __user *)(uintptr_t)argp->data, params, + if (copy_to_user(u64_to_user_ptr(argp->data), params, sizeof(struct kvm_sev_send_update_data))) ret = -EFAULT; @@ -1307,7 +1420,7 @@ static int sev_send_update_data(struct kvm *kvm, struct kvm_sev_cmd *argp) if (!sev_guest(kvm)) return -ENOTTY; - if (copy_from_user(¶ms, (void __user *)(uintptr_t)argp->data, + if (copy_from_user(¶ms, u64_to_user_ptr(argp->data), sizeof(struct kvm_sev_send_update_data))) return -EFAULT; @@ -1358,14 +1471,14 @@ static int sev_send_update_data(struct kvm *kvm, struct kvm_sev_cmd *argp) goto e_free_trans_data; /* copy transport buffer to user space */ - if (copy_to_user((void __user *)(uintptr_t)params.trans_uaddr, + if (copy_to_user(u64_to_user_ptr(params.trans_uaddr), trans_data, params.trans_len)) { ret = -EFAULT; goto e_free_trans_data; } /* Copy packet header to userspace. */ - if (copy_to_user((void __user *)(uintptr_t)params.hdr_uaddr, hdr, + if (copy_to_user(u64_to_user_ptr(params.hdr_uaddr), hdr, params.hdr_len)) ret = -EFAULT; @@ -1417,7 +1530,7 @@ static int sev_receive_start(struct kvm *kvm, struct kvm_sev_cmd *argp) return -ENOTTY; /* Get parameter from the userspace */ - if (copy_from_user(¶ms, (void __user *)(uintptr_t)argp->data, + if (copy_from_user(¶ms, u64_to_user_ptr(argp->data), sizeof(struct kvm_sev_receive_start))) return -EFAULT; @@ -1459,7 +1572,7 @@ static int sev_receive_start(struct kvm *kvm, struct kvm_sev_cmd *argp) } params.handle = start.handle; - if (copy_to_user((void __user *)(uintptr_t)argp->data, + if (copy_to_user(u64_to_user_ptr(argp->data), ¶ms, sizeof(struct kvm_sev_receive_start))) { ret = -EFAULT; sev_unbind_asid(kvm, start.handle); @@ -1490,7 +1603,7 @@ static int sev_receive_update_data(struct kvm *kvm, struct kvm_sev_cmd *argp) if (!sev_guest(kvm)) return -EINVAL; - if (copy_from_user(¶ms, (void __user *)(uintptr_t)argp->data, + if (copy_from_user(¶ms, u64_to_user_ptr(argp->data), sizeof(struct kvm_sev_receive_update_data))) return -EFAULT; @@ -1705,6 +1818,7 @@ static void sev_migrate_from(struct kvm *dst_kvm, struct kvm *src_kvm) dst->pages_locked = src->pages_locked; dst->enc_context_owner = src->enc_context_owner; dst->es_active = src->es_active; + dst->vmsa_features = src->vmsa_features; src->asid = 0; src->active = false; @@ -1812,7 +1926,8 @@ int sev_vm_move_enc_context_from(struct kvm *kvm, unsigned int source_fd) if (ret) goto out_fput; - if (sev_guest(kvm) || !sev_guest(source_kvm)) { + if (kvm->arch.vm_type != source_kvm->arch.vm_type || + sev_guest(kvm) || !sev_guest(source_kvm)) { ret = -EINVAL; goto out_unlock; } @@ -1861,6 +1976,21 @@ out_fput: return ret; } +int sev_dev_get_attr(u32 group, u64 attr, u64 *val) +{ + if (group != KVM_X86_GRP_SEV) + return -ENXIO; + + switch (attr) { + case KVM_X86_SEV_VMSA_FEATURES: + *val = sev_supported_vmsa_features; + return 0; + + default: + return -ENXIO; + } +} + int sev_mem_enc_ioctl(struct kvm *kvm, void __user *argp) { struct kvm_sev_cmd sev_cmd; @@ -1894,6 +2024,9 @@ int sev_mem_enc_ioctl(struct kvm *kvm, void __user *argp) case KVM_SEV_INIT: r = sev_guest_init(kvm, &sev_cmd); break; + case KVM_SEV_INIT2: + r = sev_guest_init2(kvm, &sev_cmd); + break; case KVM_SEV_LAUNCH_START: r = sev_launch_start(kvm, &sev_cmd); break; @@ -2121,6 +2254,7 @@ int sev_vm_copy_enc_context_from(struct kvm *kvm, unsigned int source_fd) mirror_sev->asid = source_sev->asid; mirror_sev->fd = source_sev->fd; mirror_sev->es_active = source_sev->es_active; + mirror_sev->need_init = false; mirror_sev->handle = source_sev->handle; INIT_LIST_HEAD(&mirror_sev->regions_list); INIT_LIST_HEAD(&mirror_sev->mirror_vms); @@ -2186,15 +2320,18 @@ void sev_vm_destroy(struct kvm *kvm) void __init sev_set_cpu_caps(void) { - if (!sev_enabled) - kvm_cpu_cap_clear(X86_FEATURE_SEV); - if (!sev_es_enabled) - kvm_cpu_cap_clear(X86_FEATURE_SEV_ES); + if (sev_enabled) { + kvm_cpu_cap_set(X86_FEATURE_SEV); + kvm_caps.supported_vm_types |= BIT(KVM_X86_SEV_VM); + } + if (sev_es_enabled) { + kvm_cpu_cap_set(X86_FEATURE_SEV_ES); + kvm_caps.supported_vm_types |= BIT(KVM_X86_SEV_ES_VM); + } } void __init sev_hardware_setup(void) { -#ifdef CONFIG_KVM_AMD_SEV unsigned int eax, ebx, ecx, edx, sev_asid_count, sev_es_asid_count; bool sev_es_supported = false; bool sev_supported = false; @@ -2294,7 +2431,10 @@ out: if (!sev_es_enabled || !cpu_feature_enabled(X86_FEATURE_DEBUG_SWAP) || !cpu_feature_enabled(X86_FEATURE_NO_NESTED_DATA_BP)) sev_es_debug_swap_enabled = false; -#endif + + sev_supported_vmsa_features = 0; + if (sev_es_debug_swap_enabled) + sev_supported_vmsa_features |= SVM_SEV_FEAT_DEBUG_SWAP; } void sev_hardware_unsetup(void) @@ -2585,6 +2725,8 @@ static int sev_es_validate_vmgexit(struct vcpu_svm *svm) case SVM_VMGEXIT_AP_HLT_LOOP: case SVM_VMGEXIT_AP_JUMP_TABLE: case SVM_VMGEXIT_UNSUPPORTED_EVENT: + case SVM_VMGEXIT_HV_FEATURES: + case SVM_VMGEXIT_TERM_REQUEST: break; default: reason = GHCB_ERR_INVALID_EVENT; @@ -2615,6 +2757,9 @@ vmgexit_err: void sev_es_unmap_ghcb(struct vcpu_svm *svm) { + /* Clear any indication that the vCPU is in a type of AP Reset Hold */ + svm->sev_es.ap_reset_hold_type = AP_RESET_HOLD_NONE; + if (!svm->sev_es.ghcb) return; @@ -2774,6 +2919,7 @@ static int sev_handle_vmgexit_msr_protocol(struct vcpu_svm *svm) { struct vmcb_control_area *control = &svm->vmcb->control; struct kvm_vcpu *vcpu = &svm->vcpu; + struct kvm_sev_info *sev = &to_kvm_svm(vcpu->kvm)->sev_info; u64 ghcb_info; int ret = 1; @@ -2784,7 +2930,7 @@ static int sev_handle_vmgexit_msr_protocol(struct vcpu_svm *svm) switch (ghcb_info) { case GHCB_MSR_SEV_INFO_REQ: - set_ghcb_msr(svm, GHCB_MSR_SEV_INFO(GHCB_VERSION_MAX, + set_ghcb_msr(svm, GHCB_MSR_SEV_INFO((__u64)sev->ghcb_version, GHCB_VERSION_MIN, sev_enc_bit)); break; @@ -2826,6 +2972,28 @@ static int sev_handle_vmgexit_msr_protocol(struct vcpu_svm *svm) GHCB_MSR_INFO_POS); break; } + case GHCB_MSR_AP_RESET_HOLD_REQ: + svm->sev_es.ap_reset_hold_type = AP_RESET_HOLD_MSR_PROTO; + ret = kvm_emulate_ap_reset_hold(&svm->vcpu); + + /* + * Preset the result to a non-SIPI return and then only set + * the result to non-zero when delivering a SIPI. + */ + set_ghcb_msr_bits(svm, 0, + GHCB_MSR_AP_RESET_HOLD_RESULT_MASK, + GHCB_MSR_AP_RESET_HOLD_RESULT_POS); + + set_ghcb_msr_bits(svm, GHCB_MSR_AP_RESET_HOLD_RESP, + GHCB_MSR_INFO_MASK, + GHCB_MSR_INFO_POS); + break; + case GHCB_MSR_HV_FT_REQ: + set_ghcb_msr_bits(svm, GHCB_HV_FT_SUPPORTED, + GHCB_MSR_HV_FT_MASK, GHCB_MSR_HV_FT_POS); + set_ghcb_msr_bits(svm, GHCB_MSR_HV_FT_RESP, + GHCB_MSR_INFO_MASK, GHCB_MSR_INFO_POS); + break; case GHCB_MSR_TERM_REQ: { u64 reason_set, reason_code; @@ -2925,6 +3093,7 @@ int sev_handle_vmgexit(struct kvm_vcpu *vcpu) ret = 1; break; case SVM_VMGEXIT_AP_HLT_LOOP: + svm->sev_es.ap_reset_hold_type = AP_RESET_HOLD_NAE_EVENT; ret = kvm_emulate_ap_reset_hold(vcpu); break; case SVM_VMGEXIT_AP_JUMP_TABLE: { @@ -2949,6 +3118,19 @@ int sev_handle_vmgexit(struct kvm_vcpu *vcpu) ret = 1; break; } + case SVM_VMGEXIT_HV_FEATURES: + ghcb_set_sw_exit_info_2(svm->sev_es.ghcb, GHCB_HV_FT_SUPPORTED); + + ret = 1; + break; + case SVM_VMGEXIT_TERM_REQUEST: + pr_info("SEV-ES guest requested termination: reason %#llx info %#llx\n", + control->exit_info_1, control->exit_info_2); + vcpu->run->exit_reason = KVM_EXIT_SYSTEM_EVENT; + vcpu->run->system_event.type = KVM_SYSTEM_EVENT_SEV_TERM; + vcpu->run->system_event.ndata = 1; + vcpu->run->system_event.data[0] = control->ghcb_gpa; + break; case SVM_VMGEXIT_UNSUPPORTED_EVENT: vcpu_unimpl(vcpu, "vmgexit: unsupported event - exit_info_1=%#llx, exit_info_2=%#llx\n", @@ -3063,7 +3245,7 @@ static void sev_es_init_vmcb(struct vcpu_svm *svm) svm_set_intercept(svm, TRAP_CR8_WRITE); vmcb->control.intercepts[INTERCEPT_DR] = 0; - if (!sev_es_debug_swap_enabled) { + if (!sev_vcpu_has_debug_swap(svm)) { vmcb_set_intercept(&vmcb->control, INTERCEPT_DR7_READ); vmcb_set_intercept(&vmcb->control, INTERCEPT_DR7_WRITE); recalc_intercepts(svm); @@ -3109,16 +3291,19 @@ void sev_init_vmcb(struct vcpu_svm *svm) void sev_es_vcpu_reset(struct vcpu_svm *svm) { + struct kvm_vcpu *vcpu = &svm->vcpu; + struct kvm_sev_info *sev = &to_kvm_svm(vcpu->kvm)->sev_info; + /* * Set the GHCB MSR value as per the GHCB specification when emulating * vCPU RESET for an SEV-ES guest. */ - set_ghcb_msr(svm, GHCB_MSR_SEV_INFO(GHCB_VERSION_MAX, + set_ghcb_msr(svm, GHCB_MSR_SEV_INFO((__u64)sev->ghcb_version, GHCB_VERSION_MIN, sev_enc_bit)); } -void sev_es_prepare_switch_to_guest(struct sev_es_save_area *hostsa) +void sev_es_prepare_switch_to_guest(struct vcpu_svm *svm, struct sev_es_save_area *hostsa) { /* * All host state for SEV-ES guests is categorized into three swap types @@ -3146,7 +3331,7 @@ void sev_es_prepare_switch_to_guest(struct sev_es_save_area *hostsa) * the CPU (Type-B). If DebugSwap is disabled/unsupported, the CPU both * saves and loads debug registers (Type-A). */ - if (sev_es_debug_swap_enabled) { + if (sev_vcpu_has_debug_swap(svm)) { hostsa->dr0 = native_get_debugreg(0); hostsa->dr1 = native_get_debugreg(1); hostsa->dr2 = native_get_debugreg(2); @@ -3168,15 +3353,31 @@ void sev_vcpu_deliver_sipi_vector(struct kvm_vcpu *vcpu, u8 vector) return; } - /* - * Subsequent SIPI: Return from an AP Reset Hold VMGEXIT, where - * the guest will set the CS and RIP. Set SW_EXIT_INFO_2 to a - * non-zero value. - */ - if (!svm->sev_es.ghcb) - return; + /* Subsequent SIPI */ + switch (svm->sev_es.ap_reset_hold_type) { + case AP_RESET_HOLD_NAE_EVENT: + /* + * Return from an AP Reset Hold VMGEXIT, where the guest will + * set the CS and RIP. Set SW_EXIT_INFO_2 to a non-zero value. + */ + ghcb_set_sw_exit_info_2(svm->sev_es.ghcb, 1); + break; + case AP_RESET_HOLD_MSR_PROTO: + /* + * Return from an AP Reset Hold VMGEXIT, where the guest will + * set the CS and RIP. Set GHCB data field to a non-zero value. + */ + set_ghcb_msr_bits(svm, 1, + GHCB_MSR_AP_RESET_HOLD_RESULT_MASK, + GHCB_MSR_AP_RESET_HOLD_RESULT_POS); - ghcb_set_sw_exit_info_2(svm->sev_es.ghcb, 1); + set_ghcb_msr_bits(svm, GHCB_MSR_AP_RESET_HOLD_RESP, + GHCB_MSR_INFO_MASK, + GHCB_MSR_INFO_POS); + break; + default: + break; + } } struct page *snp_safe_alloc_page(struct kvm_vcpu *vcpu) diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index 9aaf83c8d57d..c8dc25886c16 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -1433,14 +1433,6 @@ static int svm_vcpu_create(struct kvm_vcpu *vcpu) vmsa_page = snp_safe_alloc_page(vcpu); if (!vmsa_page) goto error_free_vmcb_page; - - /* - * SEV-ES guests maintain an encrypted version of their FPU - * state which is restored and saved on VMRUN and VMEXIT. - * Mark vcpu->arch.guest_fpu->fpstate as scratch so it won't - * do xsave/xrstor on it. - */ - fpstate_set_confidential(&vcpu->arch.guest_fpu); } err = avic_init_vcpu(svm); @@ -1525,7 +1517,7 @@ static void svm_prepare_switch_to_guest(struct kvm_vcpu *vcpu) */ vmsave(sd->save_area_pa); if (sev_es_guest(vcpu->kvm)) - sev_es_prepare_switch_to_guest(sev_es_host_save_area(sd)); + sev_es_prepare_switch_to_guest(svm, sev_es_host_save_area(sd)); if (tsc_scaling) __svm_write_tsc_multiplier(vcpu->arch.tsc_scaling_ratio); @@ -2056,6 +2048,15 @@ static int npf_interception(struct kvm_vcpu *vcpu) u64 fault_address = svm->vmcb->control.exit_info_2; u64 error_code = svm->vmcb->control.exit_info_1; + /* + * WARN if hardware generates a fault with an error code that collides + * with KVM-defined sythentic flags. Clear the flags and continue on, + * i.e. don't terminate the VM, as KVM can't possibly be relying on a + * flag that KVM doesn't know about. + */ + if (WARN_ON_ONCE(error_code & PFERR_SYNTHETIC_MASK)) + error_code &= ~PFERR_SYNTHETIC_MASK; + trace_kvm_page_fault(vcpu, fault_address, error_code); return kvm_mmu_page_fault(vcpu, fault_address, error_code, static_cpu_has(X86_FEATURE_DECODEASSISTS) ? @@ -3304,7 +3305,9 @@ static int (*const svm_exit_handlers[])(struct kvm_vcpu *vcpu) = { [SVM_EXIT_RSM] = rsm_interception, [SVM_EXIT_AVIC_INCOMPLETE_IPI] = avic_incomplete_ipi_interception, [SVM_EXIT_AVIC_UNACCELERATED_ACCESS] = avic_unaccelerated_access_interception, +#ifdef CONFIG_KVM_AMD_SEV [SVM_EXIT_VMGEXIT] = sev_handle_vmgexit, +#endif }; static void dump_vmcb(struct kvm_vcpu *vcpu) @@ -4085,6 +4088,9 @@ static void svm_cancel_injection(struct kvm_vcpu *vcpu) static int svm_vcpu_pre_run(struct kvm_vcpu *vcpu) { + if (to_kvm_sev_info(vcpu->kvm)->need_init) + return -EINVAL; + return 1; } @@ -4892,6 +4898,14 @@ static void svm_vm_destroy(struct kvm *kvm) static int svm_vm_init(struct kvm *kvm) { + int type = kvm->arch.vm_type; + + if (type != KVM_X86_DEFAULT_VM && + type != KVM_X86_SW_PROTECTED_VM) { + kvm->arch.has_protected_state = (type == KVM_X86_SEV_ES_VM); + to_kvm_sev_info(kvm)->need_init = true; + } + if (!pause_filter_count || !pause_filter_thresh) kvm->arch.pause_in_guest = true; @@ -5026,6 +5040,8 @@ static struct kvm_x86_ops svm_x86_ops __initdata = { .enable_smi_window = svm_enable_smi_window, #endif +#ifdef CONFIG_KVM_AMD_SEV + .dev_get_attr = sev_dev_get_attr, .mem_enc_ioctl = sev_mem_enc_ioctl, .mem_enc_register_region = sev_mem_enc_register_region, .mem_enc_unregister_region = sev_mem_enc_unregister_region, @@ -5033,7 +5049,7 @@ static struct kvm_x86_ops svm_x86_ops __initdata = { .vm_copy_enc_context_from = sev_vm_copy_enc_context_from, .vm_move_enc_context_from = sev_vm_move_enc_context_from, - +#endif .check_emulate_instruction = svm_check_emulate_instruction, .apic_init_signal_blocked = svm_apic_init_signal_blocked, diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h index 33878efdebc8..be57213cd295 100644 --- a/arch/x86/kvm/svm/svm.h +++ b/arch/x86/kvm/svm/svm.h @@ -79,12 +79,15 @@ enum { struct kvm_sev_info { bool active; /* SEV enabled guest */ bool es_active; /* SEV-ES enabled guest */ + bool need_init; /* waiting for SEV_INIT2 */ unsigned int asid; /* ASID used for this guest */ unsigned int handle; /* SEV firmware handle */ int fd; /* SEV device fd */ unsigned long pages_locked; /* Number of pages locked */ struct list_head regions_list; /* List of registered regions */ u64 ap_jump_table; /* SEV-ES AP Jump Table address */ + u64 vmsa_features; + u16 ghcb_version; /* Highest guest GHCB protocol version allowed */ struct kvm *enc_context_owner; /* Owner of copied encryption context */ struct list_head mirror_vms; /* List of VMs mirroring */ struct list_head mirror_entry; /* Use as a list entry of mirrors */ @@ -197,6 +200,7 @@ struct vcpu_sev_es_state { u8 valid_bitmap[16]; struct kvm_host_map ghcb_map; bool received_first_sipi; + unsigned int ap_reset_hold_type; /* SEV-ES scratch area support */ u64 sw_scratch; @@ -318,6 +322,11 @@ static __always_inline struct kvm_svm *to_kvm_svm(struct kvm *kvm) return container_of(kvm, struct kvm_svm, kvm); } +static __always_inline struct kvm_sev_info *to_kvm_sev_info(struct kvm *kvm) +{ + return &to_kvm_svm(kvm)->sev_info; +} + static __always_inline bool sev_guest(struct kvm *kvm) { #ifdef CONFIG_KVM_AMD_SEV @@ -664,13 +673,16 @@ void avic_refresh_virtual_apic_mode(struct kvm_vcpu *vcpu); /* sev.c */ -#define GHCB_VERSION_MAX 1ULL -#define GHCB_VERSION_MIN 1ULL - - -extern unsigned int max_sev_asid; +void pre_sev_run(struct vcpu_svm *svm, int cpu); +void sev_init_vmcb(struct vcpu_svm *svm); +void sev_vcpu_after_set_cpuid(struct vcpu_svm *svm); +int sev_es_string_io(struct vcpu_svm *svm, int size, unsigned int port, int in); +void sev_es_vcpu_reset(struct vcpu_svm *svm); +void sev_vcpu_deliver_sipi_vector(struct kvm_vcpu *vcpu, u8 vector); +void sev_es_prepare_switch_to_guest(struct vcpu_svm *svm, struct sev_es_save_area *hostsa); +void sev_es_unmap_ghcb(struct vcpu_svm *svm); -void sev_vm_destroy(struct kvm *kvm); +#ifdef CONFIG_KVM_AMD_SEV int sev_mem_enc_ioctl(struct kvm *kvm, void __user *argp); int sev_mem_enc_register_region(struct kvm *kvm, struct kvm_enc_region *range); @@ -679,22 +691,32 @@ int sev_mem_enc_unregister_region(struct kvm *kvm, int sev_vm_copy_enc_context_from(struct kvm *kvm, unsigned int source_fd); int sev_vm_move_enc_context_from(struct kvm *kvm, unsigned int source_fd); void sev_guest_memory_reclaimed(struct kvm *kvm); +int sev_handle_vmgexit(struct kvm_vcpu *vcpu); -void pre_sev_run(struct vcpu_svm *svm, int cpu); +/* These symbols are used in common code and are stubbed below. */ +struct page *snp_safe_alloc_page(struct kvm_vcpu *vcpu); +void sev_free_vcpu(struct kvm_vcpu *vcpu); +void sev_vm_destroy(struct kvm *kvm); void __init sev_set_cpu_caps(void); void __init sev_hardware_setup(void); void sev_hardware_unsetup(void); int sev_cpu_init(struct svm_cpu_data *sd); -void sev_init_vmcb(struct vcpu_svm *svm); -void sev_vcpu_after_set_cpuid(struct vcpu_svm *svm); -void sev_free_vcpu(struct kvm_vcpu *vcpu); -int sev_handle_vmgexit(struct kvm_vcpu *vcpu); -int sev_es_string_io(struct vcpu_svm *svm, int size, unsigned int port, int in); -void sev_es_vcpu_reset(struct vcpu_svm *svm); -void sev_vcpu_deliver_sipi_vector(struct kvm_vcpu *vcpu, u8 vector); -void sev_es_prepare_switch_to_guest(struct sev_es_save_area *hostsa); -void sev_es_unmap_ghcb(struct vcpu_svm *svm); -struct page *snp_safe_alloc_page(struct kvm_vcpu *vcpu); +int sev_dev_get_attr(u32 group, u64 attr, u64 *val); +extern unsigned int max_sev_asid; +#else +static inline struct page *snp_safe_alloc_page(struct kvm_vcpu *vcpu) { + return alloc_page(GFP_KERNEL_ACCOUNT | __GFP_ZERO); +} + +static inline void sev_free_vcpu(struct kvm_vcpu *vcpu) {} +static inline void sev_vm_destroy(struct kvm *kvm) {} +static inline void __init sev_set_cpu_caps(void) {} +static inline void __init sev_hardware_setup(void) {} +static inline void sev_hardware_unsetup(void) {} +static inline int sev_cpu_init(struct svm_cpu_data *sd) { return 0; } +static inline int sev_dev_get_attr(u32 group, u64 attr, u64 *val) { return -ENXIO; } +#define max_sev_asid 0 +#endif /* vmenter.S */ diff --git a/arch/x86/kvm/trace.h b/arch/x86/kvm/trace.h index c6b4b1728006..e19fed438a67 100644 --- a/arch/x86/kvm/trace.h +++ b/arch/x86/kvm/trace.h @@ -1074,7 +1074,7 @@ TRACE_EVENT(kvm_smm_transition, ); /* - * Tracepoint for VT-d posted-interrupts. + * Tracepoint for VT-d posted-interrupts and AMD-Vi Guest Virtual APIC. */ TRACE_EVENT(kvm_pi_irte_update, TP_PROTO(unsigned int host_irq, unsigned int vcpu_id, @@ -1100,7 +1100,7 @@ TRACE_EVENT(kvm_pi_irte_update, __entry->set = set; ), - TP_printk("VT-d PI is %s for irq %u, vcpu %u, gsi: 0x%x, " + TP_printk("PI is %s for irq %u, vcpu %u, gsi: 0x%x, " "gvec: 0x%x, pi_desc_addr: 0x%llx", __entry->set ? "enabled and being updated" : "disabled", __entry->host_irq, @@ -1678,7 +1678,7 @@ TRACE_EVENT(kvm_nested_vmenter_failed, ), TP_fast_assign( - __assign_str(msg, msg); + __assign_str(msg); __entry->err = err; ), diff --git a/arch/x86/kvm/vmx/main.c b/arch/x86/kvm/vmx/main.c new file mode 100644 index 000000000000..d4ed681785fd --- /dev/null +++ b/arch/x86/kvm/vmx/main.c @@ -0,0 +1,167 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <linux/moduleparam.h> + +#include "x86_ops.h" +#include "vmx.h" +#include "nested.h" +#include "pmu.h" +#include "posted_intr.h" + +#define VMX_REQUIRED_APICV_INHIBITS \ + (BIT(APICV_INHIBIT_REASON_DISABLE)| \ + BIT(APICV_INHIBIT_REASON_ABSENT) | \ + BIT(APICV_INHIBIT_REASON_HYPERV) | \ + BIT(APICV_INHIBIT_REASON_BLOCKIRQ) | \ + BIT(APICV_INHIBIT_REASON_PHYSICAL_ID_ALIASED) | \ + BIT(APICV_INHIBIT_REASON_APIC_ID_MODIFIED) | \ + BIT(APICV_INHIBIT_REASON_APIC_BASE_MODIFIED)) + +struct kvm_x86_ops vt_x86_ops __initdata = { + .name = KBUILD_MODNAME, + + .check_processor_compatibility = vmx_check_processor_compat, + + .hardware_unsetup = vmx_hardware_unsetup, + + .hardware_enable = vmx_hardware_enable, + .hardware_disable = vmx_hardware_disable, + .has_emulated_msr = vmx_has_emulated_msr, + + .vm_size = sizeof(struct kvm_vmx), + .vm_init = vmx_vm_init, + .vm_destroy = vmx_vm_destroy, + + .vcpu_precreate = vmx_vcpu_precreate, + .vcpu_create = vmx_vcpu_create, + .vcpu_free = vmx_vcpu_free, + .vcpu_reset = vmx_vcpu_reset, + + .prepare_switch_to_guest = vmx_prepare_switch_to_guest, + .vcpu_load = vmx_vcpu_load, + .vcpu_put = vmx_vcpu_put, + + .update_exception_bitmap = vmx_update_exception_bitmap, + .get_msr_feature = vmx_get_msr_feature, + .get_msr = vmx_get_msr, + .set_msr = vmx_set_msr, + .get_segment_base = vmx_get_segment_base, + .get_segment = vmx_get_segment, + .set_segment = vmx_set_segment, + .get_cpl = vmx_get_cpl, + .get_cs_db_l_bits = vmx_get_cs_db_l_bits, + .is_valid_cr0 = vmx_is_valid_cr0, + .set_cr0 = vmx_set_cr0, + .is_valid_cr4 = vmx_is_valid_cr4, + .set_cr4 = vmx_set_cr4, + .set_efer = vmx_set_efer, + .get_idt = vmx_get_idt, + .set_idt = vmx_set_idt, + .get_gdt = vmx_get_gdt, + .set_gdt = vmx_set_gdt, + .set_dr7 = vmx_set_dr7, + .sync_dirty_debug_regs = vmx_sync_dirty_debug_regs, + .cache_reg = vmx_cache_reg, + .get_rflags = vmx_get_rflags, + .set_rflags = vmx_set_rflags, + .get_if_flag = vmx_get_if_flag, + + .flush_tlb_all = vmx_flush_tlb_all, + .flush_tlb_current = vmx_flush_tlb_current, + .flush_tlb_gva = vmx_flush_tlb_gva, + .flush_tlb_guest = vmx_flush_tlb_guest, + + .vcpu_pre_run = vmx_vcpu_pre_run, + .vcpu_run = vmx_vcpu_run, + .handle_exit = vmx_handle_exit, + .skip_emulated_instruction = vmx_skip_emulated_instruction, + .update_emulated_instruction = vmx_update_emulated_instruction, + .set_interrupt_shadow = vmx_set_interrupt_shadow, + .get_interrupt_shadow = vmx_get_interrupt_shadow, + .patch_hypercall = vmx_patch_hypercall, + .inject_irq = vmx_inject_irq, + .inject_nmi = vmx_inject_nmi, + .inject_exception = vmx_inject_exception, + .cancel_injection = vmx_cancel_injection, + .interrupt_allowed = vmx_interrupt_allowed, + .nmi_allowed = vmx_nmi_allowed, + .get_nmi_mask = vmx_get_nmi_mask, + .set_nmi_mask = vmx_set_nmi_mask, + .enable_nmi_window = vmx_enable_nmi_window, + .enable_irq_window = vmx_enable_irq_window, + .update_cr8_intercept = vmx_update_cr8_intercept, + .set_virtual_apic_mode = vmx_set_virtual_apic_mode, + .set_apic_access_page_addr = vmx_set_apic_access_page_addr, + .refresh_apicv_exec_ctrl = vmx_refresh_apicv_exec_ctrl, + .load_eoi_exitmap = vmx_load_eoi_exitmap, + .apicv_pre_state_restore = vmx_apicv_pre_state_restore, + .required_apicv_inhibits = VMX_REQUIRED_APICV_INHIBITS, + .hwapic_irr_update = vmx_hwapic_irr_update, + .hwapic_isr_update = vmx_hwapic_isr_update, + .guest_apic_has_interrupt = vmx_guest_apic_has_interrupt, + .sync_pir_to_irr = vmx_sync_pir_to_irr, + .deliver_interrupt = vmx_deliver_interrupt, + .dy_apicv_has_pending_interrupt = pi_has_pending_interrupt, + + .set_tss_addr = vmx_set_tss_addr, + .set_identity_map_addr = vmx_set_identity_map_addr, + .get_mt_mask = vmx_get_mt_mask, + + .get_exit_info = vmx_get_exit_info, + + .vcpu_after_set_cpuid = vmx_vcpu_after_set_cpuid, + + .has_wbinvd_exit = cpu_has_vmx_wbinvd_exit, + + .get_l2_tsc_offset = vmx_get_l2_tsc_offset, + .get_l2_tsc_multiplier = vmx_get_l2_tsc_multiplier, + .write_tsc_offset = vmx_write_tsc_offset, + .write_tsc_multiplier = vmx_write_tsc_multiplier, + + .load_mmu_pgd = vmx_load_mmu_pgd, + + .check_intercept = vmx_check_intercept, + .handle_exit_irqoff = vmx_handle_exit_irqoff, + + .sched_in = vmx_sched_in, + + .cpu_dirty_log_size = PML_ENTITY_NUM, + .update_cpu_dirty_logging = vmx_update_cpu_dirty_logging, + + .nested_ops = &vmx_nested_ops, + + .pi_update_irte = vmx_pi_update_irte, + .pi_start_assignment = vmx_pi_start_assignment, + +#ifdef CONFIG_X86_64 + .set_hv_timer = vmx_set_hv_timer, + .cancel_hv_timer = vmx_cancel_hv_timer, +#endif + + .setup_mce = vmx_setup_mce, + +#ifdef CONFIG_KVM_SMM + .smi_allowed = vmx_smi_allowed, + .enter_smm = vmx_enter_smm, + .leave_smm = vmx_leave_smm, + .enable_smi_window = vmx_enable_smi_window, +#endif + + .check_emulate_instruction = vmx_check_emulate_instruction, + .apic_init_signal_blocked = vmx_apic_init_signal_blocked, + .migrate_timers = vmx_migrate_timers, + + .msr_filter_changed = vmx_msr_filter_changed, + .complete_emulated_msr = kvm_complete_insn_gp, + + .vcpu_deliver_sipi_vector = kvm_vcpu_deliver_sipi_vector, + + .get_untagged_addr = vmx_get_untagged_addr, +}; + +struct kvm_x86_init_ops vt_init_ops __initdata = { + .hardware_setup = vmx_hardware_setup, + .handle_intel_pt_intr = NULL, + + .runtime_ops = &vt_x86_ops, + .pmu_ops = &intel_pmu_ops, +}; diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c index d05ddf751491..d5b832126e34 100644 --- a/arch/x86/kvm/vmx/nested.c +++ b/arch/x86/kvm/vmx/nested.c @@ -409,18 +409,40 @@ static void nested_ept_inject_page_fault(struct kvm_vcpu *vcpu, { struct vmcs12 *vmcs12 = get_vmcs12(vcpu); struct vcpu_vmx *vmx = to_vmx(vcpu); + unsigned long exit_qualification; u32 vm_exit_reason; - unsigned long exit_qualification = vcpu->arch.exit_qualification; if (vmx->nested.pml_full) { vm_exit_reason = EXIT_REASON_PML_FULL; vmx->nested.pml_full = false; - exit_qualification &= INTR_INFO_UNBLOCK_NMI; + + /* + * It should be impossible to trigger a nested PML Full VM-Exit + * for anything other than an EPT Violation from L2. KVM *can* + * trigger nEPT page fault injection in response to an EPT + * Misconfig, e.g. if the MMIO SPTE was stale and L1's EPT + * tables also changed, but KVM should not treat EPT Misconfig + * VM-Exits as writes. + */ + WARN_ON_ONCE(vmx->exit_reason.basic != EXIT_REASON_EPT_VIOLATION); + + /* + * PML Full and EPT Violation VM-Exits both use bit 12 to report + * "NMI unblocking due to IRET", i.e. the bit can be propagated + * as-is from the original EXIT_QUALIFICATION. + */ + exit_qualification = vmx_get_exit_qual(vcpu) & INTR_INFO_UNBLOCK_NMI; } else { - if (fault->error_code & PFERR_RSVD_MASK) + if (fault->error_code & PFERR_RSVD_MASK) { vm_exit_reason = EXIT_REASON_EPT_MISCONFIG; - else + exit_qualification = 0; + } else { + exit_qualification = fault->exit_qualification; + exit_qualification |= vmx_get_exit_qual(vcpu) & + (EPT_VIOLATION_GVA_IS_VALID | + EPT_VIOLATION_GVA_TRANSLATED); vm_exit_reason = EXIT_REASON_EPT_VIOLATION; + } /* * Although the caller (kvm_inject_emulated_page_fault) would diff --git a/arch/x86/kvm/vmx/vmcs.h b/arch/x86/kvm/vmx/vmcs.h index 7c1996b433e2..b25625314658 100644 --- a/arch/x86/kvm/vmx/vmcs.h +++ b/arch/x86/kvm/vmx/vmcs.h @@ -140,6 +140,11 @@ static inline bool is_nm_fault(u32 intr_info) return is_exception_n(intr_info, NM_VECTOR); } +static inline bool is_ve_fault(u32 intr_info) +{ + return is_exception_n(intr_info, VE_VECTOR); +} + /* Undocumented: icebp/int1 */ static inline bool is_icebp(u32 intr_info) { diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index becefaf95cab..6051fad5945f 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -68,6 +68,7 @@ #include "vmcs12.h" #include "vmx.h" #include "x86.h" +#include "x86_ops.h" #include "smm.h" #include "vmx_onhyperv.h" #include "posted_intr.h" @@ -531,8 +532,6 @@ static inline void vmx_segment_cache_clear(struct vcpu_vmx *vmx) static unsigned long host_idt_base; #if IS_ENABLED(CONFIG_HYPERV) -static struct kvm_x86_ops vmx_x86_ops __initdata; - static bool __read_mostly enlightened_vmcs = true; module_param(enlightened_vmcs, bool, 0444); @@ -582,9 +581,8 @@ static __init void hv_init_evmcs(void) } if (ms_hyperv.nested_features & HV_X64_NESTED_DIRECT_FLUSH) - vmx_x86_ops.enable_l2_tlb_flush + vt_x86_ops.enable_l2_tlb_flush = hv_enable_l2_tlb_flush; - } else { enlightened_vmcs = false; } @@ -875,6 +873,12 @@ void vmx_update_exception_bitmap(struct kvm_vcpu *vcpu) eb = (1u << PF_VECTOR) | (1u << UD_VECTOR) | (1u << MC_VECTOR) | (1u << DB_VECTOR) | (1u << AC_VECTOR); /* + * #VE isn't used for VMX. To test against unexpected changes + * related to #VE for VMX, intercept unexpected #VE and warn on it. + */ + if (IS_ENABLED(CONFIG_KVM_INTEL_PROVE_VE)) + eb |= 1u << VE_VECTOR; + /* * Guest access to VMware backdoor ports could legitimately * trigger #GP because of TSS I/O permission bitmap. * We intercept those #GP and allow access to them anyway @@ -1478,7 +1482,7 @@ void vmx_vcpu_load_vmcs(struct kvm_vcpu *vcpu, int cpu, * Switches to specified vcpu, until a matching vcpu_put(), but assumes * vcpu mutex is already taken. */ -static void vmx_vcpu_load(struct kvm_vcpu *vcpu, int cpu) +void vmx_vcpu_load(struct kvm_vcpu *vcpu, int cpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); @@ -1489,7 +1493,7 @@ static void vmx_vcpu_load(struct kvm_vcpu *vcpu, int cpu) vmx->host_debugctlmsr = get_debugctlmsr(); } -static void vmx_vcpu_put(struct kvm_vcpu *vcpu) +void vmx_vcpu_put(struct kvm_vcpu *vcpu) { vmx_vcpu_pi_put(vcpu); @@ -1548,7 +1552,7 @@ void vmx_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags) vmx->emulation_required = vmx_emulation_required(vcpu); } -static bool vmx_get_if_flag(struct kvm_vcpu *vcpu) +bool vmx_get_if_flag(struct kvm_vcpu *vcpu) { return vmx_get_rflags(vcpu) & X86_EFLAGS_IF; } @@ -1654,8 +1658,8 @@ static int vmx_rtit_ctl_check(struct kvm_vcpu *vcpu, u64 data) return 0; } -static int vmx_check_emulate_instruction(struct kvm_vcpu *vcpu, int emul_type, - void *insn, int insn_len) +int vmx_check_emulate_instruction(struct kvm_vcpu *vcpu, int emul_type, + void *insn, int insn_len) { /* * Emulation of instructions in SGX enclaves is impossible as RIP does @@ -1739,7 +1743,7 @@ rip_updated: * Recognizes a pending MTF VM-exit and records the nested state for later * delivery. */ -static void vmx_update_emulated_instruction(struct kvm_vcpu *vcpu) +void vmx_update_emulated_instruction(struct kvm_vcpu *vcpu) { struct vmcs12 *vmcs12 = get_vmcs12(vcpu); struct vcpu_vmx *vmx = to_vmx(vcpu); @@ -1770,7 +1774,7 @@ static void vmx_update_emulated_instruction(struct kvm_vcpu *vcpu) } } -static int vmx_skip_emulated_instruction(struct kvm_vcpu *vcpu) +int vmx_skip_emulated_instruction(struct kvm_vcpu *vcpu) { vmx_update_emulated_instruction(vcpu); return skip_emulated_instruction(vcpu); @@ -1789,7 +1793,7 @@ static void vmx_clear_hlt(struct kvm_vcpu *vcpu) vmcs_write32(GUEST_ACTIVITY_STATE, GUEST_ACTIVITY_ACTIVE); } -static void vmx_inject_exception(struct kvm_vcpu *vcpu) +void vmx_inject_exception(struct kvm_vcpu *vcpu) { struct kvm_queued_exception *ex = &vcpu->arch.exception; u32 intr_info = ex->vector | INTR_INFO_VALID_MASK; @@ -1910,12 +1914,12 @@ u64 vmx_get_l2_tsc_multiplier(struct kvm_vcpu *vcpu) return kvm_caps.default_tsc_scaling_ratio; } -static void vmx_write_tsc_offset(struct kvm_vcpu *vcpu) +void vmx_write_tsc_offset(struct kvm_vcpu *vcpu) { vmcs_write64(TSC_OFFSET, vcpu->arch.tsc_offset); } -static void vmx_write_tsc_multiplier(struct kvm_vcpu *vcpu) +void vmx_write_tsc_multiplier(struct kvm_vcpu *vcpu) { vmcs_write64(TSC_MULTIPLIER, vcpu->arch.tsc_scaling_ratio); } @@ -1958,7 +1962,7 @@ static inline bool is_vmx_feature_control_msr_valid(struct vcpu_vmx *vmx, return !(msr->data & ~valid_bits); } -static int vmx_get_msr_feature(struct kvm_msr_entry *msr) +int vmx_get_msr_feature(struct kvm_msr_entry *msr) { switch (msr->index) { case KVM_FIRST_EMULATED_VMX_MSR ... KVM_LAST_EMULATED_VMX_MSR: @@ -1975,7 +1979,7 @@ static int vmx_get_msr_feature(struct kvm_msr_entry *msr) * Returns 0 on success, non-0 otherwise. * Assumes vcpu_load() was already called. */ -static int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) +int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) { struct vcpu_vmx *vmx = to_vmx(vcpu); struct vmx_uret_msr *msr; @@ -2156,7 +2160,7 @@ static u64 vmx_get_supported_debugctl(struct kvm_vcpu *vcpu, bool host_initiated * Returns 0 on success, non-0 otherwise. * Assumes vcpu_load() was already called. */ -static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) +int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) { struct vcpu_vmx *vmx = to_vmx(vcpu); struct vmx_uret_msr *msr; @@ -2459,7 +2463,7 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) return ret; } -static void vmx_cache_reg(struct kvm_vcpu *vcpu, enum kvm_reg reg) +void vmx_cache_reg(struct kvm_vcpu *vcpu, enum kvm_reg reg) { unsigned long guest_owned_bits; @@ -2607,6 +2611,9 @@ static int setup_vmcs_config(struct vmcs_config *vmcs_conf, &_cpu_based_2nd_exec_control)) return -EIO; } + if (!IS_ENABLED(CONFIG_KVM_INTEL_PROVE_VE)) + _cpu_based_2nd_exec_control &= ~SECONDARY_EXEC_EPT_VIOLATION_VE; + #ifndef CONFIG_X86_64 if (!(_cpu_based_2nd_exec_control & SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES)) @@ -2631,6 +2638,7 @@ static int setup_vmcs_config(struct vmcs_config *vmcs_conf, return -EIO; vmx_cap->ept = 0; + _cpu_based_2nd_exec_control &= ~SECONDARY_EXEC_EPT_VIOLATION_VE; } if (!(_cpu_based_2nd_exec_control & SECONDARY_EXEC_ENABLE_VPID) && vmx_cap->vpid) { @@ -2760,7 +2768,7 @@ static bool kvm_is_vmx_supported(void) return supported; } -static int vmx_check_processor_compat(void) +int vmx_check_processor_compat(void) { int cpu = raw_smp_processor_id(); struct vmcs_config vmcs_conf; @@ -2802,7 +2810,7 @@ fault: return -EFAULT; } -static int vmx_hardware_enable(void) +int vmx_hardware_enable(void) { int cpu = raw_smp_processor_id(); u64 phys_addr = __pa(per_cpu(vmxarea, cpu)); @@ -2842,7 +2850,7 @@ static void vmclear_local_loaded_vmcss(void) __loaded_vmcs_clear(v); } -static void vmx_hardware_disable(void) +void vmx_hardware_disable(void) { vmclear_local_loaded_vmcss(); @@ -3156,7 +3164,7 @@ static void exit_lmode(struct kvm_vcpu *vcpu) #endif -static void vmx_flush_tlb_all(struct kvm_vcpu *vcpu) +void vmx_flush_tlb_all(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); @@ -3186,7 +3194,7 @@ static inline int vmx_get_current_vpid(struct kvm_vcpu *vcpu) return to_vmx(vcpu)->vpid; } -static void vmx_flush_tlb_current(struct kvm_vcpu *vcpu) +void vmx_flush_tlb_current(struct kvm_vcpu *vcpu) { struct kvm_mmu *mmu = vcpu->arch.mmu; u64 root_hpa = mmu->root.hpa; @@ -3202,7 +3210,7 @@ static void vmx_flush_tlb_current(struct kvm_vcpu *vcpu) vpid_sync_context(vmx_get_current_vpid(vcpu)); } -static void vmx_flush_tlb_gva(struct kvm_vcpu *vcpu, gva_t addr) +void vmx_flush_tlb_gva(struct kvm_vcpu *vcpu, gva_t addr) { /* * vpid_sync_vcpu_addr() is a nop if vpid==0, see the comment in @@ -3211,7 +3219,7 @@ static void vmx_flush_tlb_gva(struct kvm_vcpu *vcpu, gva_t addr) vpid_sync_vcpu_addr(vmx_get_current_vpid(vcpu), addr); } -static void vmx_flush_tlb_guest(struct kvm_vcpu *vcpu) +void vmx_flush_tlb_guest(struct kvm_vcpu *vcpu) { /* * vpid_sync_context() is a nop if vpid==0, e.g. if enable_vpid==0 or a @@ -3256,7 +3264,7 @@ void ept_save_pdptrs(struct kvm_vcpu *vcpu) #define CR3_EXITING_BITS (CPU_BASED_CR3_LOAD_EXITING | \ CPU_BASED_CR3_STORE_EXITING) -static bool vmx_is_valid_cr0(struct kvm_vcpu *vcpu, unsigned long cr0) +bool vmx_is_valid_cr0(struct kvm_vcpu *vcpu, unsigned long cr0) { if (is_guest_mode(vcpu)) return nested_guest_cr0_valid(vcpu, cr0); @@ -3377,8 +3385,7 @@ u64 construct_eptp(struct kvm_vcpu *vcpu, hpa_t root_hpa, int root_level) return eptp; } -static void vmx_load_mmu_pgd(struct kvm_vcpu *vcpu, hpa_t root_hpa, - int root_level) +void vmx_load_mmu_pgd(struct kvm_vcpu *vcpu, hpa_t root_hpa, int root_level) { struct kvm *kvm = vcpu->kvm; bool update_guest_cr3 = true; @@ -3407,8 +3414,7 @@ static void vmx_load_mmu_pgd(struct kvm_vcpu *vcpu, hpa_t root_hpa, vmcs_writel(GUEST_CR3, guest_cr3); } - -static bool vmx_is_valid_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) +bool vmx_is_valid_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) { /* * We operate under the default treatment of SMM, so VMX cannot be @@ -3524,7 +3530,7 @@ void vmx_get_segment(struct kvm_vcpu *vcpu, struct kvm_segment *var, int seg) var->g = (ar >> 15) & 1; } -static u64 vmx_get_segment_base(struct kvm_vcpu *vcpu, int seg) +u64 vmx_get_segment_base(struct kvm_vcpu *vcpu, int seg) { struct kvm_segment s; @@ -3601,14 +3607,14 @@ void __vmx_set_segment(struct kvm_vcpu *vcpu, struct kvm_segment *var, int seg) vmcs_write32(sf->ar_bytes, vmx_segment_access_rights(var)); } -static void vmx_set_segment(struct kvm_vcpu *vcpu, struct kvm_segment *var, int seg) +void vmx_set_segment(struct kvm_vcpu *vcpu, struct kvm_segment *var, int seg) { __vmx_set_segment(vcpu, var, seg); to_vmx(vcpu)->emulation_required = vmx_emulation_required(vcpu); } -static void vmx_get_cs_db_l_bits(struct kvm_vcpu *vcpu, int *db, int *l) +void vmx_get_cs_db_l_bits(struct kvm_vcpu *vcpu, int *db, int *l) { u32 ar = vmx_read_guest_seg_ar(to_vmx(vcpu), VCPU_SREG_CS); @@ -3616,25 +3622,25 @@ static void vmx_get_cs_db_l_bits(struct kvm_vcpu *vcpu, int *db, int *l) *l = (ar >> 13) & 1; } -static void vmx_get_idt(struct kvm_vcpu *vcpu, struct desc_ptr *dt) +void vmx_get_idt(struct kvm_vcpu *vcpu, struct desc_ptr *dt) { dt->size = vmcs_read32(GUEST_IDTR_LIMIT); dt->address = vmcs_readl(GUEST_IDTR_BASE); } -static void vmx_set_idt(struct kvm_vcpu *vcpu, struct desc_ptr *dt) +void vmx_set_idt(struct kvm_vcpu *vcpu, struct desc_ptr *dt) { vmcs_write32(GUEST_IDTR_LIMIT, dt->size); vmcs_writel(GUEST_IDTR_BASE, dt->address); } -static void vmx_get_gdt(struct kvm_vcpu *vcpu, struct desc_ptr *dt) +void vmx_get_gdt(struct kvm_vcpu *vcpu, struct desc_ptr *dt) { dt->size = vmcs_read32(GUEST_GDTR_LIMIT); dt->address = vmcs_readl(GUEST_GDTR_BASE); } -static void vmx_set_gdt(struct kvm_vcpu *vcpu, struct desc_ptr *dt) +void vmx_set_gdt(struct kvm_vcpu *vcpu, struct desc_ptr *dt) { vmcs_write32(GUEST_GDTR_LIMIT, dt->size); vmcs_writel(GUEST_GDTR_BASE, dt->address); @@ -4102,7 +4108,7 @@ void pt_update_intercept_for_msr(struct kvm_vcpu *vcpu) } } -static bool vmx_guest_apic_has_interrupt(struct kvm_vcpu *vcpu) +bool vmx_guest_apic_has_interrupt(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); void *vapic_page; @@ -4122,7 +4128,7 @@ static bool vmx_guest_apic_has_interrupt(struct kvm_vcpu *vcpu) return ((rvi & 0xf0) > (vppr & 0xf0)); } -static void vmx_msr_filter_changed(struct kvm_vcpu *vcpu) +void vmx_msr_filter_changed(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); u32 i; @@ -4266,8 +4272,8 @@ static int vmx_deliver_posted_interrupt(struct kvm_vcpu *vcpu, int vector) return 0; } -static void vmx_deliver_interrupt(struct kvm_lapic *apic, int delivery_mode, - int trig_mode, int vector) +void vmx_deliver_interrupt(struct kvm_lapic *apic, int delivery_mode, + int trig_mode, int vector) { struct kvm_vcpu *vcpu = apic->vcpu; @@ -4429,7 +4435,7 @@ static u32 vmx_vmexit_ctrl(void) ~(VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL | VM_EXIT_LOAD_IA32_EFER); } -static void vmx_refresh_apicv_exec_ctrl(struct kvm_vcpu *vcpu) +void vmx_refresh_apicv_exec_ctrl(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); @@ -4595,6 +4601,7 @@ static u32 vmx_secondary_exec_control(struct vcpu_vmx *vmx) exec_control &= ~SECONDARY_EXEC_ENABLE_VPID; if (!enable_ept) { exec_control &= ~SECONDARY_EXEC_ENABLE_EPT; + exec_control &= ~SECONDARY_EXEC_EPT_VIOLATION_VE; enable_unrestricted_guest = 0; } if (!enable_unrestricted_guest) @@ -4693,7 +4700,7 @@ static int vmx_alloc_ipiv_pid_table(struct kvm *kvm) return 0; } -static int vmx_vcpu_precreate(struct kvm *kvm) +int vmx_vcpu_precreate(struct kvm *kvm) { return vmx_alloc_ipiv_pid_table(kvm); } @@ -4718,8 +4725,12 @@ static void init_vmcs(struct vcpu_vmx *vmx) exec_controls_set(vmx, vmx_exec_control(vmx)); - if (cpu_has_secondary_exec_ctrls()) + if (cpu_has_secondary_exec_ctrls()) { secondary_exec_controls_set(vmx, vmx_secondary_exec_control(vmx)); + if (vmx->ve_info) + vmcs_write64(VE_INFORMATION_ADDRESS, + __pa(vmx->ve_info)); + } if (cpu_has_tertiary_exec_ctrls()) tertiary_exec_controls_set(vmx, vmx_tertiary_exec_control(vmx)); @@ -4848,7 +4859,7 @@ static void __vmx_vcpu_reset(struct kvm_vcpu *vcpu) __pi_set_sn(&vmx->pi_desc); } -static void vmx_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) +void vmx_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) { struct vcpu_vmx *vmx = to_vmx(vcpu); @@ -4907,12 +4918,12 @@ static void vmx_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) vmx_update_fb_clear_dis(vcpu, vmx); } -static void vmx_enable_irq_window(struct kvm_vcpu *vcpu) +void vmx_enable_irq_window(struct kvm_vcpu *vcpu) { exec_controls_setbit(to_vmx(vcpu), CPU_BASED_INTR_WINDOW_EXITING); } -static void vmx_enable_nmi_window(struct kvm_vcpu *vcpu) +void vmx_enable_nmi_window(struct kvm_vcpu *vcpu) { if (!enable_vnmi || vmcs_read32(GUEST_INTERRUPTIBILITY_INFO) & GUEST_INTR_STATE_STI) { @@ -4923,7 +4934,7 @@ static void vmx_enable_nmi_window(struct kvm_vcpu *vcpu) exec_controls_setbit(to_vmx(vcpu), CPU_BASED_NMI_WINDOW_EXITING); } -static void vmx_inject_irq(struct kvm_vcpu *vcpu, bool reinjected) +void vmx_inject_irq(struct kvm_vcpu *vcpu, bool reinjected) { struct vcpu_vmx *vmx = to_vmx(vcpu); uint32_t intr; @@ -4951,7 +4962,7 @@ static void vmx_inject_irq(struct kvm_vcpu *vcpu, bool reinjected) vmx_clear_hlt(vcpu); } -static void vmx_inject_nmi(struct kvm_vcpu *vcpu) +void vmx_inject_nmi(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); @@ -5029,7 +5040,7 @@ bool vmx_nmi_blocked(struct kvm_vcpu *vcpu) GUEST_INTR_STATE_NMI)); } -static int vmx_nmi_allowed(struct kvm_vcpu *vcpu, bool for_injection) +int vmx_nmi_allowed(struct kvm_vcpu *vcpu, bool for_injection) { if (to_vmx(vcpu)->nested.nested_run_pending) return -EBUSY; @@ -5051,7 +5062,7 @@ bool vmx_interrupt_blocked(struct kvm_vcpu *vcpu) (GUEST_INTR_STATE_STI | GUEST_INTR_STATE_MOV_SS)); } -static int vmx_interrupt_allowed(struct kvm_vcpu *vcpu, bool for_injection) +int vmx_interrupt_allowed(struct kvm_vcpu *vcpu, bool for_injection) { if (to_vmx(vcpu)->nested.nested_run_pending) return -EBUSY; @@ -5066,7 +5077,7 @@ static int vmx_interrupt_allowed(struct kvm_vcpu *vcpu, bool for_injection) return !vmx_interrupt_blocked(vcpu); } -static int vmx_set_tss_addr(struct kvm *kvm, unsigned int addr) +int vmx_set_tss_addr(struct kvm *kvm, unsigned int addr) { void __user *ret; @@ -5086,7 +5097,7 @@ static int vmx_set_tss_addr(struct kvm *kvm, unsigned int addr) return init_rmode_tss(kvm, ret); } -static int vmx_set_identity_map_addr(struct kvm *kvm, u64 ident_addr) +int vmx_set_identity_map_addr(struct kvm *kvm, u64 ident_addr) { to_kvm_vmx(kvm)->ept_identity_map_addr = ident_addr; return 0; @@ -5207,6 +5218,9 @@ static int handle_exception_nmi(struct kvm_vcpu *vcpu) if (is_invalid_opcode(intr_info)) return handle_ud(vcpu); + if (KVM_BUG_ON(is_ve_fault(intr_info), vcpu->kvm)) + return -EIO; + error_code = 0; if (intr_info & INTR_INFO_DELIVER_CODE_MASK) error_code = vmcs_read32(VM_EXIT_INTR_ERROR_CODE); @@ -5372,8 +5386,7 @@ static int handle_io(struct kvm_vcpu *vcpu) return kvm_fast_pio(vcpu, size, port, in); } -static void -vmx_patch_hypercall(struct kvm_vcpu *vcpu, unsigned char *hypercall) +void vmx_patch_hypercall(struct kvm_vcpu *vcpu, unsigned char *hypercall) { /* * Patch in the VMCALL instruction: @@ -5579,7 +5592,7 @@ out: return kvm_complete_insn_gp(vcpu, err); } -static void vmx_sync_dirty_debug_regs(struct kvm_vcpu *vcpu) +void vmx_sync_dirty_debug_regs(struct kvm_vcpu *vcpu) { get_debugreg(vcpu->arch.db[0], 0); get_debugreg(vcpu->arch.db[1], 1); @@ -5598,7 +5611,7 @@ static void vmx_sync_dirty_debug_regs(struct kvm_vcpu *vcpu) set_debugreg(DR6_RESERVED, 6); } -static void vmx_set_dr7(struct kvm_vcpu *vcpu, unsigned long val) +void vmx_set_dr7(struct kvm_vcpu *vcpu, unsigned long val) { vmcs_writel(GUEST_DR7, val); } @@ -5771,8 +5784,6 @@ static int handle_ept_violation(struct kvm_vcpu *vcpu) error_code |= (exit_qualification & EPT_VIOLATION_GVA_TRANSLATED) != 0 ? PFERR_GUEST_FINAL_MASK : PFERR_GUEST_PAGE_MASK; - vcpu->arch.exit_qualification = exit_qualification; - /* * Check that the GPA doesn't exceed physical memory limits, as that is * a guest page fault. We have to emulate the instruction here, because @@ -5869,7 +5880,7 @@ static int handle_invalid_guest_state(struct kvm_vcpu *vcpu) return 1; } -static int vmx_vcpu_pre_run(struct kvm_vcpu *vcpu) +int vmx_vcpu_pre_run(struct kvm_vcpu *vcpu) { if (vmx_emulation_required_with_pending_exception(vcpu)) { kvm_prepare_emulation_failure_exit(vcpu); @@ -6157,9 +6168,8 @@ static int (*kvm_vmx_exit_handlers[])(struct kvm_vcpu *vcpu) = { static const int kvm_vmx_max_exit_handlers = ARRAY_SIZE(kvm_vmx_exit_handlers); -static void vmx_get_exit_info(struct kvm_vcpu *vcpu, u32 *reason, - u64 *info1, u64 *info2, - u32 *intr_info, u32 *error_code) +void vmx_get_exit_info(struct kvm_vcpu *vcpu, u32 *reason, + u64 *info1, u64 *info2, u32 *intr_info, u32 *error_code) { struct vcpu_vmx *vmx = to_vmx(vcpu); @@ -6417,6 +6427,24 @@ void dump_vmcs(struct kvm_vcpu *vcpu) if (secondary_exec_control & SECONDARY_EXEC_ENABLE_VPID) pr_err("Virtual processor ID = 0x%04x\n", vmcs_read16(VIRTUAL_PROCESSOR_ID)); + if (secondary_exec_control & SECONDARY_EXEC_EPT_VIOLATION_VE) { + struct vmx_ve_information *ve_info = vmx->ve_info; + u64 ve_info_pa = vmcs_read64(VE_INFORMATION_ADDRESS); + + /* + * If KVM is dumping the VMCS, then something has gone wrong + * already. Derefencing an address from the VMCS, which could + * very well be corrupted, is a terrible idea. The virtual + * address is known so use it. + */ + pr_err("VE info address = 0x%016llx%s\n", ve_info_pa, + ve_info_pa == __pa(ve_info) ? "" : "(corrupted!)"); + pr_err("ve_info: 0x%08x 0x%08x 0x%016llx 0x%016llx 0x%016llx 0x%04x\n", + ve_info->exit_reason, ve_info->delivery, + ve_info->exit_qualification, + ve_info->guest_linear_address, + ve_info->guest_physical_address, ve_info->eptp_index); + } } /* @@ -6602,7 +6630,7 @@ unexpected_vmexit: return 0; } -static int vmx_handle_exit(struct kvm_vcpu *vcpu, fastpath_t exit_fastpath) +int vmx_handle_exit(struct kvm_vcpu *vcpu, fastpath_t exit_fastpath) { int ret = __vmx_handle_exit(vcpu, exit_fastpath); @@ -6690,7 +6718,7 @@ static noinstr void vmx_l1d_flush(struct kvm_vcpu *vcpu) : "eax", "ebx", "ecx", "edx"); } -static void vmx_update_cr8_intercept(struct kvm_vcpu *vcpu, int tpr, int irr) +void vmx_update_cr8_intercept(struct kvm_vcpu *vcpu, int tpr, int irr) { struct vmcs12 *vmcs12 = get_vmcs12(vcpu); int tpr_threshold; @@ -6760,7 +6788,7 @@ void vmx_set_virtual_apic_mode(struct kvm_vcpu *vcpu) vmx_update_msr_bitmap_x2apic(vcpu); } -static void vmx_set_apic_access_page_addr(struct kvm_vcpu *vcpu) +void vmx_set_apic_access_page_addr(struct kvm_vcpu *vcpu) { const gfn_t gfn = APIC_DEFAULT_PHYS_BASE >> PAGE_SHIFT; struct kvm *kvm = vcpu->kvm; @@ -6829,7 +6857,7 @@ out: kvm_release_pfn_clean(pfn); } -static void vmx_hwapic_isr_update(int max_isr) +void vmx_hwapic_isr_update(int max_isr) { u16 status; u8 old; @@ -6863,7 +6891,7 @@ static void vmx_set_rvi(int vector) } } -static void vmx_hwapic_irr_update(struct kvm_vcpu *vcpu, int max_irr) +void vmx_hwapic_irr_update(struct kvm_vcpu *vcpu, int max_irr) { /* * When running L2, updating RVI is only relevant when @@ -6877,7 +6905,7 @@ static void vmx_hwapic_irr_update(struct kvm_vcpu *vcpu, int max_irr) vmx_set_rvi(max_irr); } -static int vmx_sync_pir_to_irr(struct kvm_vcpu *vcpu) +int vmx_sync_pir_to_irr(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); int max_irr; @@ -6923,7 +6951,7 @@ static int vmx_sync_pir_to_irr(struct kvm_vcpu *vcpu) return max_irr; } -static void vmx_load_eoi_exitmap(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap) +void vmx_load_eoi_exitmap(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap) { if (!kvm_vcpu_apicv_active(vcpu)) return; @@ -6934,7 +6962,7 @@ static void vmx_load_eoi_exitmap(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap) vmcs_write64(EOI_EXIT_BITMAP3, eoi_exit_bitmap[3]); } -static void vmx_apicv_pre_state_restore(struct kvm_vcpu *vcpu) +void vmx_apicv_pre_state_restore(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); @@ -6965,24 +6993,22 @@ static void handle_nm_fault_irqoff(struct kvm_vcpu *vcpu) rdmsrl(MSR_IA32_XFD_ERR, vcpu->arch.guest_fpu.xfd_err); } -static void handle_exception_irqoff(struct vcpu_vmx *vmx) +static void handle_exception_irqoff(struct kvm_vcpu *vcpu, u32 intr_info) { - u32 intr_info = vmx_get_intr_info(&vmx->vcpu); - /* if exit due to PF check for async PF */ if (is_page_fault(intr_info)) - vmx->vcpu.arch.apf.host_apf_flags = kvm_read_and_reset_apf_flags(); + vcpu->arch.apf.host_apf_flags = kvm_read_and_reset_apf_flags(); /* if exit due to NM, handle before interrupts are enabled */ else if (is_nm_fault(intr_info)) - handle_nm_fault_irqoff(&vmx->vcpu); + handle_nm_fault_irqoff(vcpu); /* Handle machine checks before interrupts are enabled */ else if (is_machine_check(intr_info)) kvm_machine_check(); } -static void handle_external_interrupt_irqoff(struct kvm_vcpu *vcpu) +static void handle_external_interrupt_irqoff(struct kvm_vcpu *vcpu, + u32 intr_info) { - u32 intr_info = vmx_get_intr_info(vcpu); unsigned int vector = intr_info & INTR_INFO_VECTOR_MASK; if (KVM_BUG(!is_external_intr(intr_info), vcpu->kvm, @@ -6999,7 +7025,7 @@ static void handle_external_interrupt_irqoff(struct kvm_vcpu *vcpu) vcpu->arch.at_instruction_boundary = true; } -static void vmx_handle_exit_irqoff(struct kvm_vcpu *vcpu) +void vmx_handle_exit_irqoff(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); @@ -7007,16 +7033,16 @@ static void vmx_handle_exit_irqoff(struct kvm_vcpu *vcpu) return; if (vmx->exit_reason.basic == EXIT_REASON_EXTERNAL_INTERRUPT) - handle_external_interrupt_irqoff(vcpu); + handle_external_interrupt_irqoff(vcpu, vmx_get_intr_info(vcpu)); else if (vmx->exit_reason.basic == EXIT_REASON_EXCEPTION_NMI) - handle_exception_irqoff(vmx); + handle_exception_irqoff(vcpu, vmx_get_intr_info(vcpu)); } /* * The kvm parameter can be NULL (module initialization, or invocation before * VM creation). Be sure to check the kvm parameter before using it. */ -static bool vmx_has_emulated_msr(struct kvm *kvm, u32 index) +bool vmx_has_emulated_msr(struct kvm *kvm, u32 index) { switch (index) { case MSR_IA32_SMBASE: @@ -7139,7 +7165,7 @@ static void vmx_complete_interrupts(struct vcpu_vmx *vmx) IDT_VECTORING_ERROR_CODE); } -static void vmx_cancel_injection(struct kvm_vcpu *vcpu) +void vmx_cancel_injection(struct kvm_vcpu *vcpu) { __vmx_complete_interrupts(vcpu, vmcs_read32(VM_ENTRY_INTR_INFO_FIELD), @@ -7309,7 +7335,7 @@ out: guest_state_exit_irqoff(); } -static fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu, bool force_immediate_exit) +fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu, bool force_immediate_exit) { struct vcpu_vmx *vmx = to_vmx(vcpu); unsigned long cr3, cr4; @@ -7464,7 +7490,7 @@ static fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu, bool force_immediate_exit) return vmx_exit_handlers_fastpath(vcpu, force_immediate_exit); } -static void vmx_vcpu_free(struct kvm_vcpu *vcpu) +void vmx_vcpu_free(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); @@ -7473,9 +7499,10 @@ static void vmx_vcpu_free(struct kvm_vcpu *vcpu) free_vpid(vmx->vpid); nested_vmx_free_vcpu(vcpu); free_loaded_vmcs(vmx->loaded_vmcs); + free_page((unsigned long)vmx->ve_info); } -static int vmx_vcpu_create(struct kvm_vcpu *vcpu) +int vmx_vcpu_create(struct kvm_vcpu *vcpu) { struct vmx_uret_msr *tsx_ctrl; struct vcpu_vmx *vmx; @@ -7566,6 +7593,20 @@ static int vmx_vcpu_create(struct kvm_vcpu *vcpu) goto free_vmcs; } + err = -ENOMEM; + if (vmcs_config.cpu_based_2nd_exec_ctrl & SECONDARY_EXEC_EPT_VIOLATION_VE) { + struct page *page; + + BUILD_BUG_ON(sizeof(*vmx->ve_info) > PAGE_SIZE); + + /* ve_info must be page aligned. */ + page = alloc_page(GFP_KERNEL_ACCOUNT | __GFP_ZERO); + if (!page) + goto free_vmcs; + + vmx->ve_info = page_to_virt(page); + } + if (vmx_can_use_ipiv(vcpu)) WRITE_ONCE(to_kvm_vmx(vcpu->kvm)->pid_table[vcpu->vcpu_id], __pa(&vmx->pi_desc) | PID_TABLE_ENTRY_VALID); @@ -7584,7 +7625,7 @@ free_vpid: #define L1TF_MSG_SMT "L1TF CPU bug present and SMT on, data leak possible. See CVE-2018-3646 and https://www.kernel.org/doc/html/latest/admin-guide/hw-vuln/l1tf.html for details.\n" #define L1TF_MSG_L1D "L1TF CPU bug present and virtualization mitigation disabled, data leak possible. See CVE-2018-3646 and https://www.kernel.org/doc/html/latest/admin-guide/hw-vuln/l1tf.html for details.\n" -static int vmx_vm_init(struct kvm *kvm) +int vmx_vm_init(struct kvm *kvm) { if (!ple_gap) kvm->arch.pause_in_guest = true; @@ -7615,7 +7656,7 @@ static int vmx_vm_init(struct kvm *kvm) return 0; } -static u8 vmx_get_mt_mask(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio) +u8 vmx_get_mt_mask(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio) { /* We wanted to honor guest CD/MTRR/PAT, but doing so could result in * memory aliases with conflicting memory types and sometimes MCEs. @@ -7787,7 +7828,7 @@ static void update_intel_pt_cfg(struct kvm_vcpu *vcpu) vmx->pt_desc.ctl_bitmask &= ~(0xfULL << (32 + i * 4)); } -static void vmx_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu) +void vmx_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); @@ -8002,10 +8043,10 @@ static int vmx_check_intercept_io(struct kvm_vcpu *vcpu, return intercept ? X86EMUL_UNHANDLEABLE : X86EMUL_CONTINUE; } -static int vmx_check_intercept(struct kvm_vcpu *vcpu, - struct x86_instruction_info *info, - enum x86_intercept_stage stage, - struct x86_exception *exception) +int vmx_check_intercept(struct kvm_vcpu *vcpu, + struct x86_instruction_info *info, + enum x86_intercept_stage stage, + struct x86_exception *exception) { struct vmcs12 *vmcs12 = get_vmcs12(vcpu); @@ -8085,8 +8126,8 @@ static inline int u64_shl_div_u64(u64 a, unsigned int shift, return 0; } -static int vmx_set_hv_timer(struct kvm_vcpu *vcpu, u64 guest_deadline_tsc, - bool *expired) +int vmx_set_hv_timer(struct kvm_vcpu *vcpu, u64 guest_deadline_tsc, + bool *expired) { struct vcpu_vmx *vmx; u64 tscl, guest_tscl, delta_tsc, lapic_timer_advance_cycles; @@ -8125,13 +8166,13 @@ static int vmx_set_hv_timer(struct kvm_vcpu *vcpu, u64 guest_deadline_tsc, return 0; } -static void vmx_cancel_hv_timer(struct kvm_vcpu *vcpu) +void vmx_cancel_hv_timer(struct kvm_vcpu *vcpu) { to_vmx(vcpu)->hv_deadline_tsc = -1; } #endif -static void vmx_sched_in(struct kvm_vcpu *vcpu, int cpu) +void vmx_sched_in(struct kvm_vcpu *vcpu, int cpu) { if (!kvm_pause_in_guest(vcpu->kvm)) shrink_ple_window(vcpu); @@ -8160,7 +8201,7 @@ void vmx_update_cpu_dirty_logging(struct kvm_vcpu *vcpu) secondary_exec_controls_clearbit(vmx, SECONDARY_EXEC_ENABLE_PML); } -static void vmx_setup_mce(struct kvm_vcpu *vcpu) +void vmx_setup_mce(struct kvm_vcpu *vcpu) { if (vcpu->arch.mcg_cap & MCG_LMCE_P) to_vmx(vcpu)->msr_ia32_feature_control_valid_bits |= @@ -8171,7 +8212,7 @@ static void vmx_setup_mce(struct kvm_vcpu *vcpu) } #ifdef CONFIG_KVM_SMM -static int vmx_smi_allowed(struct kvm_vcpu *vcpu, bool for_injection) +int vmx_smi_allowed(struct kvm_vcpu *vcpu, bool for_injection) { /* we need a nested vmexit to enter SMM, postpone if run is pending */ if (to_vmx(vcpu)->nested.nested_run_pending) @@ -8179,7 +8220,7 @@ static int vmx_smi_allowed(struct kvm_vcpu *vcpu, bool for_injection) return !is_smm(vcpu); } -static int vmx_enter_smm(struct kvm_vcpu *vcpu, union kvm_smram *smram) +int vmx_enter_smm(struct kvm_vcpu *vcpu, union kvm_smram *smram) { struct vcpu_vmx *vmx = to_vmx(vcpu); @@ -8200,7 +8241,7 @@ static int vmx_enter_smm(struct kvm_vcpu *vcpu, union kvm_smram *smram) return 0; } -static int vmx_leave_smm(struct kvm_vcpu *vcpu, const union kvm_smram *smram) +int vmx_leave_smm(struct kvm_vcpu *vcpu, const union kvm_smram *smram) { struct vcpu_vmx *vmx = to_vmx(vcpu); int ret; @@ -8221,18 +8262,18 @@ static int vmx_leave_smm(struct kvm_vcpu *vcpu, const union kvm_smram *smram) return 0; } -static void vmx_enable_smi_window(struct kvm_vcpu *vcpu) +void vmx_enable_smi_window(struct kvm_vcpu *vcpu) { /* RSM will cause a vmexit anyway. */ } #endif -static bool vmx_apic_init_signal_blocked(struct kvm_vcpu *vcpu) +bool vmx_apic_init_signal_blocked(struct kvm_vcpu *vcpu) { return to_vmx(vcpu)->nested.vmxon && !is_guest_mode(vcpu); } -static void vmx_migrate_timers(struct kvm_vcpu *vcpu) +void vmx_migrate_timers(struct kvm_vcpu *vcpu) { if (is_guest_mode(vcpu)) { struct hrtimer *timer = &to_vmx(vcpu)->nested.preemption_timer; @@ -8242,7 +8283,7 @@ static void vmx_migrate_timers(struct kvm_vcpu *vcpu) } } -static void vmx_hardware_unsetup(void) +void vmx_hardware_unsetup(void) { kvm_set_posted_intr_wakeup_handler(NULL); @@ -8252,18 +8293,7 @@ static void vmx_hardware_unsetup(void) free_kvm_area(); } -#define VMX_REQUIRED_APICV_INHIBITS \ -( \ - BIT(APICV_INHIBIT_REASON_DISABLE)| \ - BIT(APICV_INHIBIT_REASON_ABSENT) | \ - BIT(APICV_INHIBIT_REASON_HYPERV) | \ - BIT(APICV_INHIBIT_REASON_BLOCKIRQ) | \ - BIT(APICV_INHIBIT_REASON_PHYSICAL_ID_ALIASED) | \ - BIT(APICV_INHIBIT_REASON_APIC_ID_MODIFIED) | \ - BIT(APICV_INHIBIT_REASON_APIC_BASE_MODIFIED) \ -) - -static void vmx_vm_destroy(struct kvm *kvm) +void vmx_vm_destroy(struct kvm *kvm) { struct kvm_vmx *kvm_vmx = to_kvm_vmx(kvm); @@ -8314,148 +8344,6 @@ gva_t vmx_get_untagged_addr(struct kvm_vcpu *vcpu, gva_t gva, unsigned int flags return (sign_extend64(gva, lam_bit) & ~BIT_ULL(63)) | (gva & BIT_ULL(63)); } -static struct kvm_x86_ops vmx_x86_ops __initdata = { - .name = KBUILD_MODNAME, - - .check_processor_compatibility = vmx_check_processor_compat, - - .hardware_unsetup = vmx_hardware_unsetup, - - .hardware_enable = vmx_hardware_enable, - .hardware_disable = vmx_hardware_disable, - .has_emulated_msr = vmx_has_emulated_msr, - - .vm_size = sizeof(struct kvm_vmx), - .vm_init = vmx_vm_init, - .vm_destroy = vmx_vm_destroy, - - .vcpu_precreate = vmx_vcpu_precreate, - .vcpu_create = vmx_vcpu_create, - .vcpu_free = vmx_vcpu_free, - .vcpu_reset = vmx_vcpu_reset, - - .prepare_switch_to_guest = vmx_prepare_switch_to_guest, - .vcpu_load = vmx_vcpu_load, - .vcpu_put = vmx_vcpu_put, - - .update_exception_bitmap = vmx_update_exception_bitmap, - .get_msr_feature = vmx_get_msr_feature, - .get_msr = vmx_get_msr, - .set_msr = vmx_set_msr, - .get_segment_base = vmx_get_segment_base, - .get_segment = vmx_get_segment, - .set_segment = vmx_set_segment, - .get_cpl = vmx_get_cpl, - .get_cs_db_l_bits = vmx_get_cs_db_l_bits, - .is_valid_cr0 = vmx_is_valid_cr0, - .set_cr0 = vmx_set_cr0, - .is_valid_cr4 = vmx_is_valid_cr4, - .set_cr4 = vmx_set_cr4, - .set_efer = vmx_set_efer, - .get_idt = vmx_get_idt, - .set_idt = vmx_set_idt, - .get_gdt = vmx_get_gdt, - .set_gdt = vmx_set_gdt, - .set_dr7 = vmx_set_dr7, - .sync_dirty_debug_regs = vmx_sync_dirty_debug_regs, - .cache_reg = vmx_cache_reg, - .get_rflags = vmx_get_rflags, - .set_rflags = vmx_set_rflags, - .get_if_flag = vmx_get_if_flag, - - .flush_tlb_all = vmx_flush_tlb_all, - .flush_tlb_current = vmx_flush_tlb_current, - .flush_tlb_gva = vmx_flush_tlb_gva, - .flush_tlb_guest = vmx_flush_tlb_guest, - - .vcpu_pre_run = vmx_vcpu_pre_run, - .vcpu_run = vmx_vcpu_run, - .handle_exit = vmx_handle_exit, - .skip_emulated_instruction = vmx_skip_emulated_instruction, - .update_emulated_instruction = vmx_update_emulated_instruction, - .set_interrupt_shadow = vmx_set_interrupt_shadow, - .get_interrupt_shadow = vmx_get_interrupt_shadow, - .patch_hypercall = vmx_patch_hypercall, - .inject_irq = vmx_inject_irq, - .inject_nmi = vmx_inject_nmi, - .inject_exception = vmx_inject_exception, - .cancel_injection = vmx_cancel_injection, - .interrupt_allowed = vmx_interrupt_allowed, - .nmi_allowed = vmx_nmi_allowed, - .get_nmi_mask = vmx_get_nmi_mask, - .set_nmi_mask = vmx_set_nmi_mask, - .enable_nmi_window = vmx_enable_nmi_window, - .enable_irq_window = vmx_enable_irq_window, - .update_cr8_intercept = vmx_update_cr8_intercept, - .set_virtual_apic_mode = vmx_set_virtual_apic_mode, - .set_apic_access_page_addr = vmx_set_apic_access_page_addr, - .refresh_apicv_exec_ctrl = vmx_refresh_apicv_exec_ctrl, - .load_eoi_exitmap = vmx_load_eoi_exitmap, - .apicv_pre_state_restore = vmx_apicv_pre_state_restore, - .required_apicv_inhibits = VMX_REQUIRED_APICV_INHIBITS, - .hwapic_irr_update = vmx_hwapic_irr_update, - .hwapic_isr_update = vmx_hwapic_isr_update, - .guest_apic_has_interrupt = vmx_guest_apic_has_interrupt, - .sync_pir_to_irr = vmx_sync_pir_to_irr, - .deliver_interrupt = vmx_deliver_interrupt, - .dy_apicv_has_pending_interrupt = pi_has_pending_interrupt, - - .set_tss_addr = vmx_set_tss_addr, - .set_identity_map_addr = vmx_set_identity_map_addr, - .get_mt_mask = vmx_get_mt_mask, - - .get_exit_info = vmx_get_exit_info, - - .vcpu_after_set_cpuid = vmx_vcpu_after_set_cpuid, - - .has_wbinvd_exit = cpu_has_vmx_wbinvd_exit, - - .get_l2_tsc_offset = vmx_get_l2_tsc_offset, - .get_l2_tsc_multiplier = vmx_get_l2_tsc_multiplier, - .write_tsc_offset = vmx_write_tsc_offset, - .write_tsc_multiplier = vmx_write_tsc_multiplier, - - .load_mmu_pgd = vmx_load_mmu_pgd, - - .check_intercept = vmx_check_intercept, - .handle_exit_irqoff = vmx_handle_exit_irqoff, - - .sched_in = vmx_sched_in, - - .cpu_dirty_log_size = PML_ENTITY_NUM, - .update_cpu_dirty_logging = vmx_update_cpu_dirty_logging, - - .nested_ops = &vmx_nested_ops, - - .pi_update_irte = vmx_pi_update_irte, - .pi_start_assignment = vmx_pi_start_assignment, - -#ifdef CONFIG_X86_64 - .set_hv_timer = vmx_set_hv_timer, - .cancel_hv_timer = vmx_cancel_hv_timer, -#endif - - .setup_mce = vmx_setup_mce, - -#ifdef CONFIG_KVM_SMM - .smi_allowed = vmx_smi_allowed, - .enter_smm = vmx_enter_smm, - .leave_smm = vmx_leave_smm, - .enable_smi_window = vmx_enable_smi_window, -#endif - - .check_emulate_instruction = vmx_check_emulate_instruction, - .apic_init_signal_blocked = vmx_apic_init_signal_blocked, - .migrate_timers = vmx_migrate_timers, - - .msr_filter_changed = vmx_msr_filter_changed, - .complete_emulated_msr = kvm_complete_insn_gp, - - .vcpu_deliver_sipi_vector = kvm_vcpu_deliver_sipi_vector, - - .get_untagged_addr = vmx_get_untagged_addr, -}; - static unsigned int vmx_handle_intel_pt_intr(void) { struct kvm_vcpu *vcpu = kvm_get_running_vcpu(); @@ -8521,9 +8409,7 @@ static void __init vmx_setup_me_spte_mask(void) kvm_mmu_set_me_spte_mask(0, me_mask); } -static struct kvm_x86_init_ops vmx_init_ops __initdata; - -static __init int hardware_setup(void) +__init int vmx_hardware_setup(void) { unsigned long host_bndcfgs; struct desc_ptr dt; @@ -8592,16 +8478,16 @@ static __init int hardware_setup(void) * using the APIC_ACCESS_ADDR VMCS field. */ if (!flexpriority_enabled) - vmx_x86_ops.set_apic_access_page_addr = NULL; + vt_x86_ops.set_apic_access_page_addr = NULL; if (!cpu_has_vmx_tpr_shadow()) - vmx_x86_ops.update_cr8_intercept = NULL; + vt_x86_ops.update_cr8_intercept = NULL; #if IS_ENABLED(CONFIG_HYPERV) if (ms_hyperv.nested_features & HV_X64_NESTED_GUEST_MAPPING_FLUSH && enable_ept) { - vmx_x86_ops.flush_remote_tlbs = hv_flush_remote_tlbs; - vmx_x86_ops.flush_remote_tlbs_range = hv_flush_remote_tlbs_range; + vt_x86_ops.flush_remote_tlbs = hv_flush_remote_tlbs; + vt_x86_ops.flush_remote_tlbs_range = hv_flush_remote_tlbs_range; } #endif @@ -8616,7 +8502,7 @@ static __init int hardware_setup(void) if (!cpu_has_vmx_apicv()) enable_apicv = 0; if (!enable_apicv) - vmx_x86_ops.sync_pir_to_irr = NULL; + vt_x86_ops.sync_pir_to_irr = NULL; if (!enable_apicv || !cpu_has_vmx_ipiv()) enable_ipiv = false; @@ -8652,7 +8538,7 @@ static __init int hardware_setup(void) enable_pml = 0; if (!enable_pml) - vmx_x86_ops.cpu_dirty_log_size = 0; + vt_x86_ops.cpu_dirty_log_size = 0; if (!cpu_has_vmx_preemption_timer()) enable_preemption_timer = false; @@ -8677,8 +8563,8 @@ static __init int hardware_setup(void) } if (!enable_preemption_timer) { - vmx_x86_ops.set_hv_timer = NULL; - vmx_x86_ops.cancel_hv_timer = NULL; + vt_x86_ops.set_hv_timer = NULL; + vt_x86_ops.cancel_hv_timer = NULL; } kvm_caps.supported_mce_cap |= MCG_LMCE_P; @@ -8689,9 +8575,9 @@ static __init int hardware_setup(void) if (!enable_ept || !enable_pmu || !cpu_has_vmx_intel_pt()) pt_mode = PT_MODE_SYSTEM; if (pt_mode == PT_MODE_HOST_GUEST) - vmx_init_ops.handle_intel_pt_intr = vmx_handle_intel_pt_intr; + vt_init_ops.handle_intel_pt_intr = vmx_handle_intel_pt_intr; else - vmx_init_ops.handle_intel_pt_intr = NULL; + vt_init_ops.handle_intel_pt_intr = NULL; setup_default_sgx_lepubkeyhash(); @@ -8714,14 +8600,6 @@ static __init int hardware_setup(void) return r; } -static struct kvm_x86_init_ops vmx_init_ops __initdata = { - .hardware_setup = hardware_setup, - .handle_intel_pt_intr = NULL, - - .runtime_ops = &vmx_x86_ops, - .pmu_ops = &intel_pmu_ops, -}; - static void vmx_cleanup_l1d_flush(void) { if (vmx_l1d_flush_pages) { @@ -8763,7 +8641,7 @@ static int __init vmx_init(void) */ hv_init_evmcs(); - r = kvm_x86_vendor_init(&vmx_init_ops); + r = kvm_x86_vendor_init(&vt_init_ops); if (r) return r; diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h index 7e483366b31e..7b64e271a931 100644 --- a/arch/x86/kvm/vmx/vmx.h +++ b/arch/x86/kvm/vmx/vmx.h @@ -365,6 +365,9 @@ struct vcpu_vmx { DECLARE_BITMAP(read, MAX_POSSIBLE_PASSTHROUGH_MSRS); DECLARE_BITMAP(write, MAX_POSSIBLE_PASSTHROUGH_MSRS); } shadow_msr_intercept; + + /* ve_info must be page aligned. */ + struct vmx_ve_information *ve_info; }; struct kvm_vmx { @@ -577,7 +580,8 @@ static inline u8 vmx_get_rvi(void) SECONDARY_EXEC_ENABLE_VMFUNC | \ SECONDARY_EXEC_BUS_LOCK_DETECTION | \ SECONDARY_EXEC_NOTIFY_VM_EXITING | \ - SECONDARY_EXEC_ENCLS_EXITING) + SECONDARY_EXEC_ENCLS_EXITING | \ + SECONDARY_EXEC_EPT_VIOLATION_VE) #define KVM_REQUIRED_VMX_TERTIARY_VM_EXEC_CONTROL 0 #define KVM_OPTIONAL_VMX_TERTIARY_VM_EXEC_CONTROL \ diff --git a/arch/x86/kvm/vmx/x86_ops.h b/arch/x86/kvm/vmx/x86_ops.h new file mode 100644 index 000000000000..502704596c83 --- /dev/null +++ b/arch/x86/kvm/vmx/x86_ops.h @@ -0,0 +1,124 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __KVM_X86_VMX_X86_OPS_H +#define __KVM_X86_VMX_X86_OPS_H + +#include <linux/kvm_host.h> + +#include "x86.h" + +__init int vmx_hardware_setup(void); + +extern struct kvm_x86_ops vt_x86_ops __initdata; +extern struct kvm_x86_init_ops vt_init_ops __initdata; + +void vmx_hardware_unsetup(void); +int vmx_check_processor_compat(void); +int vmx_hardware_enable(void); +void vmx_hardware_disable(void); +int vmx_vm_init(struct kvm *kvm); +void vmx_vm_destroy(struct kvm *kvm); +int vmx_vcpu_precreate(struct kvm *kvm); +int vmx_vcpu_create(struct kvm_vcpu *vcpu); +int vmx_vcpu_pre_run(struct kvm_vcpu *vcpu); +fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu, bool force_immediate_exit); +void vmx_vcpu_free(struct kvm_vcpu *vcpu); +void vmx_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event); +void vmx_vcpu_load(struct kvm_vcpu *vcpu, int cpu); +void vmx_vcpu_put(struct kvm_vcpu *vcpu); +int vmx_handle_exit(struct kvm_vcpu *vcpu, fastpath_t exit_fastpath); +void vmx_handle_exit_irqoff(struct kvm_vcpu *vcpu); +int vmx_skip_emulated_instruction(struct kvm_vcpu *vcpu); +void vmx_update_emulated_instruction(struct kvm_vcpu *vcpu); +int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info); +#ifdef CONFIG_KVM_SMM +int vmx_smi_allowed(struct kvm_vcpu *vcpu, bool for_injection); +int vmx_enter_smm(struct kvm_vcpu *vcpu, union kvm_smram *smram); +int vmx_leave_smm(struct kvm_vcpu *vcpu, const union kvm_smram *smram); +void vmx_enable_smi_window(struct kvm_vcpu *vcpu); +#endif +int vmx_check_emulate_instruction(struct kvm_vcpu *vcpu, int emul_type, + void *insn, int insn_len); +int vmx_check_intercept(struct kvm_vcpu *vcpu, + struct x86_instruction_info *info, + enum x86_intercept_stage stage, + struct x86_exception *exception); +bool vmx_apic_init_signal_blocked(struct kvm_vcpu *vcpu); +void vmx_migrate_timers(struct kvm_vcpu *vcpu); +void vmx_set_virtual_apic_mode(struct kvm_vcpu *vcpu); +void vmx_apicv_pre_state_restore(struct kvm_vcpu *vcpu); +bool vmx_check_apicv_inhibit_reasons(enum kvm_apicv_inhibit reason); +void vmx_hwapic_irr_update(struct kvm_vcpu *vcpu, int max_irr); +void vmx_hwapic_isr_update(int max_isr); +bool vmx_guest_apic_has_interrupt(struct kvm_vcpu *vcpu); +int vmx_sync_pir_to_irr(struct kvm_vcpu *vcpu); +void vmx_deliver_interrupt(struct kvm_lapic *apic, int delivery_mode, + int trig_mode, int vector); +void vmx_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu); +bool vmx_has_emulated_msr(struct kvm *kvm, u32 index); +void vmx_msr_filter_changed(struct kvm_vcpu *vcpu); +void vmx_prepare_switch_to_guest(struct kvm_vcpu *vcpu); +void vmx_update_exception_bitmap(struct kvm_vcpu *vcpu); +int vmx_get_msr_feature(struct kvm_msr_entry *msr); +int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info); +u64 vmx_get_segment_base(struct kvm_vcpu *vcpu, int seg); +void vmx_get_segment(struct kvm_vcpu *vcpu, struct kvm_segment *var, int seg); +void vmx_set_segment(struct kvm_vcpu *vcpu, struct kvm_segment *var, int seg); +int vmx_get_cpl(struct kvm_vcpu *vcpu); +void vmx_get_cs_db_l_bits(struct kvm_vcpu *vcpu, int *db, int *l); +bool vmx_is_valid_cr0(struct kvm_vcpu *vcpu, unsigned long cr0); +void vmx_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0); +void vmx_load_mmu_pgd(struct kvm_vcpu *vcpu, hpa_t root_hpa, int root_level); +void vmx_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4); +bool vmx_is_valid_cr4(struct kvm_vcpu *vcpu, unsigned long cr4); +int vmx_set_efer(struct kvm_vcpu *vcpu, u64 efer); +void vmx_get_idt(struct kvm_vcpu *vcpu, struct desc_ptr *dt); +void vmx_set_idt(struct kvm_vcpu *vcpu, struct desc_ptr *dt); +void vmx_get_gdt(struct kvm_vcpu *vcpu, struct desc_ptr *dt); +void vmx_set_gdt(struct kvm_vcpu *vcpu, struct desc_ptr *dt); +void vmx_set_dr7(struct kvm_vcpu *vcpu, unsigned long val); +void vmx_sync_dirty_debug_regs(struct kvm_vcpu *vcpu); +void vmx_cache_reg(struct kvm_vcpu *vcpu, enum kvm_reg reg); +unsigned long vmx_get_rflags(struct kvm_vcpu *vcpu); +void vmx_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags); +bool vmx_get_if_flag(struct kvm_vcpu *vcpu); +void vmx_flush_tlb_all(struct kvm_vcpu *vcpu); +void vmx_flush_tlb_current(struct kvm_vcpu *vcpu); +void vmx_flush_tlb_gva(struct kvm_vcpu *vcpu, gva_t addr); +void vmx_flush_tlb_guest(struct kvm_vcpu *vcpu); +void vmx_set_interrupt_shadow(struct kvm_vcpu *vcpu, int mask); +u32 vmx_get_interrupt_shadow(struct kvm_vcpu *vcpu); +void vmx_patch_hypercall(struct kvm_vcpu *vcpu, unsigned char *hypercall); +void vmx_inject_irq(struct kvm_vcpu *vcpu, bool reinjected); +void vmx_inject_nmi(struct kvm_vcpu *vcpu); +void vmx_inject_exception(struct kvm_vcpu *vcpu); +void vmx_cancel_injection(struct kvm_vcpu *vcpu); +int vmx_interrupt_allowed(struct kvm_vcpu *vcpu, bool for_injection); +int vmx_nmi_allowed(struct kvm_vcpu *vcpu, bool for_injection); +bool vmx_get_nmi_mask(struct kvm_vcpu *vcpu); +void vmx_set_nmi_mask(struct kvm_vcpu *vcpu, bool masked); +void vmx_enable_nmi_window(struct kvm_vcpu *vcpu); +void vmx_enable_irq_window(struct kvm_vcpu *vcpu); +void vmx_update_cr8_intercept(struct kvm_vcpu *vcpu, int tpr, int irr); +void vmx_set_apic_access_page_addr(struct kvm_vcpu *vcpu); +void vmx_refresh_apicv_exec_ctrl(struct kvm_vcpu *vcpu); +void vmx_load_eoi_exitmap(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap); +int vmx_set_tss_addr(struct kvm *kvm, unsigned int addr); +int vmx_set_identity_map_addr(struct kvm *kvm, u64 ident_addr); +u8 vmx_get_mt_mask(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio); +void vmx_get_exit_info(struct kvm_vcpu *vcpu, u32 *reason, + u64 *info1, u64 *info2, u32 *intr_info, u32 *error_code); +u64 vmx_get_l2_tsc_offset(struct kvm_vcpu *vcpu); +u64 vmx_get_l2_tsc_multiplier(struct kvm_vcpu *vcpu); +void vmx_write_tsc_offset(struct kvm_vcpu *vcpu); +void vmx_write_tsc_multiplier(struct kvm_vcpu *vcpu); +void vmx_request_immediate_exit(struct kvm_vcpu *vcpu); +void vmx_sched_in(struct kvm_vcpu *vcpu, int cpu); +void vmx_update_cpu_dirty_logging(struct kvm_vcpu *vcpu); +#ifdef CONFIG_X86_64 +int vmx_set_hv_timer(struct kvm_vcpu *vcpu, u64 guest_deadline_tsc, + bool *expired); +void vmx_cancel_hv_timer(struct kvm_vcpu *vcpu); +#endif +void vmx_setup_mce(struct kvm_vcpu *vcpu); + +#endif /* __KVM_X86_VMX_X86_OPS_H */ diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 91478b769af0..082ac6d95a3a 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -92,9 +92,12 @@ #define MAX_IO_MSRS 256 #define KVM_MAX_MCE_BANKS 32 -struct kvm_caps kvm_caps __read_mostly = { - .supported_mce_cap = MCG_CTL_P | MCG_SER_P, -}; +/* + * Note, kvm_caps fields should *never* have default values, all fields must be + * recomputed from scratch during vendor module load, e.g. to account for a + * vendor module being reloaded with different module parameters. + */ +struct kvm_caps kvm_caps __read_mostly; EXPORT_SYMBOL_GPL(kvm_caps); #define ERR_PTR_USR(e) ((void __user *)ERR_PTR(e)) @@ -2230,16 +2233,13 @@ static int do_set_msr(struct kvm_vcpu *vcpu, unsigned index, u64 *data) /* * Disallow writes to immutable feature MSRs after KVM_RUN. KVM does * not support modifying the guest vCPU model on the fly, e.g. changing - * the nVMX capabilities while L2 is running is nonsensical. Ignore + * the nVMX capabilities while L2 is running is nonsensical. Allow * writes of the same value, e.g. to allow userspace to blindly stuff * all MSRs when emulating RESET. */ - if (kvm_vcpu_has_run(vcpu) && kvm_is_immutable_feature_msr(index)) { - if (do_get_msr(vcpu, index, &val) || *data != val) - return -EINVAL; - - return 0; - } + if (kvm_vcpu_has_run(vcpu) && kvm_is_immutable_feature_msr(index) && + (do_get_msr(vcpu, index, &val) || *data != val)) + return -EINVAL; return kvm_set_msr_ignored_check(vcpu, index, *data, true); } @@ -4629,9 +4629,7 @@ static int kvm_ioctl_get_supported_hv_cpuid(struct kvm_vcpu *vcpu, static bool kvm_is_vm_type_supported(unsigned long type) { - return type == KVM_X86_DEFAULT_VM || - (type == KVM_X86_SW_PROTECTED_VM && - IS_ENABLED(CONFIG_KVM_SW_PROTECTED_VM) && tdp_mmu_enabled); + return type < 32 && (kvm_caps.supported_vm_types & BIT(type)); } int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) @@ -4832,9 +4830,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) r = kvm_caps.has_notify_vmexit; break; case KVM_CAP_VM_TYPES: - r = BIT(KVM_X86_DEFAULT_VM); - if (kvm_is_vm_type_supported(KVM_X86_SW_PROTECTED_VM)) - r |= BIT(KVM_X86_SW_PROTECTED_VM); + r = kvm_caps.supported_vm_types; break; default: break; @@ -4842,46 +4838,44 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) return r; } -static inline void __user *kvm_get_attr_addr(struct kvm_device_attr *attr) +static int __kvm_x86_dev_get_attr(struct kvm_device_attr *attr, u64 *val) { - void __user *uaddr = (void __user*)(unsigned long)attr->addr; - - if ((u64)(unsigned long)uaddr != attr->addr) - return ERR_PTR_USR(-EFAULT); - return uaddr; -} - -static int kvm_x86_dev_get_attr(struct kvm_device_attr *attr) -{ - u64 __user *uaddr = kvm_get_attr_addr(attr); - - if (attr->group) + if (attr->group) { + if (kvm_x86_ops.dev_get_attr) + return static_call(kvm_x86_dev_get_attr)(attr->group, attr->attr, val); return -ENXIO; - - if (IS_ERR(uaddr)) - return PTR_ERR(uaddr); + } switch (attr->attr) { case KVM_X86_XCOMP_GUEST_SUPP: - if (put_user(kvm_caps.supported_xcr0, uaddr)) - return -EFAULT; + *val = kvm_caps.supported_xcr0; return 0; default: return -ENXIO; } } +static int kvm_x86_dev_get_attr(struct kvm_device_attr *attr) +{ + u64 __user *uaddr = u64_to_user_ptr(attr->addr); + int r; + u64 val; + + r = __kvm_x86_dev_get_attr(attr, &val); + if (r < 0) + return r; + + if (put_user(val, uaddr)) + return -EFAULT; + + return 0; +} + static int kvm_x86_dev_has_attr(struct kvm_device_attr *attr) { - if (attr->group) - return -ENXIO; + u64 val; - switch (attr->attr) { - case KVM_X86_XCOMP_GUEST_SUPP: - return 0; - default: - return -ENXIO; - } + return __kvm_x86_dev_get_attr(attr, &val); } long kvm_arch_dev_ioctl(struct file *filp, @@ -5557,11 +5551,15 @@ static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu, return 0; } -static void kvm_vcpu_ioctl_x86_get_debugregs(struct kvm_vcpu *vcpu, - struct kvm_debugregs *dbgregs) +static int kvm_vcpu_ioctl_x86_get_debugregs(struct kvm_vcpu *vcpu, + struct kvm_debugregs *dbgregs) { unsigned int i; + if (vcpu->kvm->arch.has_protected_state && + vcpu->arch.guest_state_protected) + return -EINVAL; + memset(dbgregs, 0, sizeof(*dbgregs)); BUILD_BUG_ON(ARRAY_SIZE(vcpu->arch.db) != ARRAY_SIZE(dbgregs->db)); @@ -5570,6 +5568,7 @@ static void kvm_vcpu_ioctl_x86_get_debugregs(struct kvm_vcpu *vcpu, dbgregs->dr6 = vcpu->arch.dr6; dbgregs->dr7 = vcpu->arch.dr7; + return 0; } static int kvm_vcpu_ioctl_x86_set_debugregs(struct kvm_vcpu *vcpu, @@ -5577,6 +5576,10 @@ static int kvm_vcpu_ioctl_x86_set_debugregs(struct kvm_vcpu *vcpu, { unsigned int i; + if (vcpu->kvm->arch.has_protected_state && + vcpu->arch.guest_state_protected) + return -EINVAL; + if (dbgregs->flags) return -EINVAL; @@ -5597,8 +5600,8 @@ static int kvm_vcpu_ioctl_x86_set_debugregs(struct kvm_vcpu *vcpu, } -static void kvm_vcpu_ioctl_x86_get_xsave2(struct kvm_vcpu *vcpu, - u8 *state, unsigned int size) +static int kvm_vcpu_ioctl_x86_get_xsave2(struct kvm_vcpu *vcpu, + u8 *state, unsigned int size) { /* * Only copy state for features that are enabled for the guest. The @@ -5616,24 +5619,25 @@ static void kvm_vcpu_ioctl_x86_get_xsave2(struct kvm_vcpu *vcpu, XFEATURE_MASK_FPSSE; if (fpstate_is_confidential(&vcpu->arch.guest_fpu)) - return; + return vcpu->kvm->arch.has_protected_state ? -EINVAL : 0; fpu_copy_guest_fpstate_to_uabi(&vcpu->arch.guest_fpu, state, size, supported_xcr0, vcpu->arch.pkru); + return 0; } -static void kvm_vcpu_ioctl_x86_get_xsave(struct kvm_vcpu *vcpu, - struct kvm_xsave *guest_xsave) +static int kvm_vcpu_ioctl_x86_get_xsave(struct kvm_vcpu *vcpu, + struct kvm_xsave *guest_xsave) { - kvm_vcpu_ioctl_x86_get_xsave2(vcpu, (void *)guest_xsave->region, - sizeof(guest_xsave->region)); + return kvm_vcpu_ioctl_x86_get_xsave2(vcpu, (void *)guest_xsave->region, + sizeof(guest_xsave->region)); } static int kvm_vcpu_ioctl_x86_set_xsave(struct kvm_vcpu *vcpu, struct kvm_xsave *guest_xsave) { if (fpstate_is_confidential(&vcpu->arch.guest_fpu)) - return 0; + return vcpu->kvm->arch.has_protected_state ? -EINVAL : 0; return fpu_copy_uabi_to_guest_fpstate(&vcpu->arch.guest_fpu, guest_xsave->region, @@ -5641,18 +5645,23 @@ static int kvm_vcpu_ioctl_x86_set_xsave(struct kvm_vcpu *vcpu, &vcpu->arch.pkru); } -static void kvm_vcpu_ioctl_x86_get_xcrs(struct kvm_vcpu *vcpu, - struct kvm_xcrs *guest_xcrs) +static int kvm_vcpu_ioctl_x86_get_xcrs(struct kvm_vcpu *vcpu, + struct kvm_xcrs *guest_xcrs) { + if (vcpu->kvm->arch.has_protected_state && + vcpu->arch.guest_state_protected) + return -EINVAL; + if (!boot_cpu_has(X86_FEATURE_XSAVE)) { guest_xcrs->nr_xcrs = 0; - return; + return 0; } guest_xcrs->nr_xcrs = 1; guest_xcrs->flags = 0; guest_xcrs->xcrs[0].xcr = XCR_XFEATURE_ENABLED_MASK; guest_xcrs->xcrs[0].value = vcpu->arch.xcr0; + return 0; } static int kvm_vcpu_ioctl_x86_set_xcrs(struct kvm_vcpu *vcpu, @@ -5660,6 +5669,10 @@ static int kvm_vcpu_ioctl_x86_set_xcrs(struct kvm_vcpu *vcpu, { int i, r = 0; + if (vcpu->kvm->arch.has_protected_state && + vcpu->arch.guest_state_protected) + return -EINVAL; + if (!boot_cpu_has(X86_FEATURE_XSAVE)) return -EINVAL; @@ -5712,12 +5725,9 @@ static int kvm_arch_tsc_has_attr(struct kvm_vcpu *vcpu, static int kvm_arch_tsc_get_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr) { - u64 __user *uaddr = kvm_get_attr_addr(attr); + u64 __user *uaddr = u64_to_user_ptr(attr->addr); int r; - if (IS_ERR(uaddr)) - return PTR_ERR(uaddr); - switch (attr->attr) { case KVM_VCPU_TSC_OFFSET: r = -EFAULT; @@ -5735,13 +5745,10 @@ static int kvm_arch_tsc_get_attr(struct kvm_vcpu *vcpu, static int kvm_arch_tsc_set_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr) { - u64 __user *uaddr = kvm_get_attr_addr(attr); + u64 __user *uaddr = u64_to_user_ptr(attr->addr); struct kvm *kvm = vcpu->kvm; int r; - if (IS_ERR(uaddr)) - return PTR_ERR(uaddr); - switch (attr->attr) { case KVM_VCPU_TSC_OFFSET: { u64 offset, tsc, ns; @@ -6048,7 +6055,9 @@ long kvm_arch_vcpu_ioctl(struct file *filp, case KVM_GET_DEBUGREGS: { struct kvm_debugregs dbgregs; - kvm_vcpu_ioctl_x86_get_debugregs(vcpu, &dbgregs); + r = kvm_vcpu_ioctl_x86_get_debugregs(vcpu, &dbgregs); + if (r < 0) + break; r = -EFAULT; if (copy_to_user(argp, &dbgregs, @@ -6078,7 +6087,9 @@ long kvm_arch_vcpu_ioctl(struct file *filp, if (!u.xsave) break; - kvm_vcpu_ioctl_x86_get_xsave(vcpu, u.xsave); + r = kvm_vcpu_ioctl_x86_get_xsave(vcpu, u.xsave); + if (r < 0) + break; r = -EFAULT; if (copy_to_user(argp, u.xsave, sizeof(struct kvm_xsave))) @@ -6107,7 +6118,9 @@ long kvm_arch_vcpu_ioctl(struct file *filp, if (!u.xsave) break; - kvm_vcpu_ioctl_x86_get_xsave2(vcpu, u.buffer, size); + r = kvm_vcpu_ioctl_x86_get_xsave2(vcpu, u.buffer, size); + if (r < 0) + break; r = -EFAULT; if (copy_to_user(argp, u.xsave, size)) @@ -6123,7 +6136,9 @@ long kvm_arch_vcpu_ioctl(struct file *filp, if (!u.xcrs) break; - kvm_vcpu_ioctl_x86_get_xcrs(vcpu, u.xcrs); + r = kvm_vcpu_ioctl_x86_get_xcrs(vcpu, u.xcrs); + if (r < 0) + break; r = -EFAULT; if (copy_to_user(argp, u.xcrs, @@ -6267,6 +6282,11 @@ long kvm_arch_vcpu_ioctl(struct file *filp, } #endif case KVM_GET_SREGS2: { + r = -EINVAL; + if (vcpu->kvm->arch.has_protected_state && + vcpu->arch.guest_state_protected) + goto out; + u.sregs2 = kzalloc(sizeof(struct kvm_sregs2), GFP_KERNEL); r = -ENOMEM; if (!u.sregs2) @@ -6279,6 +6299,11 @@ long kvm_arch_vcpu_ioctl(struct file *filp, break; } case KVM_SET_SREGS2: { + r = -EINVAL; + if (vcpu->kvm->arch.has_protected_state && + vcpu->arch.guest_state_protected) + goto out; + u.sregs2 = memdup_user(argp, sizeof(struct kvm_sregs2)); if (IS_ERR(u.sregs2)) { r = PTR_ERR(u.sregs2); @@ -9732,6 +9757,8 @@ int kvm_x86_vendor_init(struct kvm_x86_init_ops *ops) return -EIO; } + memset(&kvm_caps, 0, sizeof(kvm_caps)); + x86_emulator_cache = kvm_alloc_emulator_cache(); if (!x86_emulator_cache) { pr_err("failed to allocate cache for x86 emulator\n"); @@ -9750,6 +9777,9 @@ int kvm_x86_vendor_init(struct kvm_x86_init_ops *ops) if (r) goto out_free_percpu; + kvm_caps.supported_vm_types = BIT(KVM_X86_DEFAULT_VM); + kvm_caps.supported_mce_cap = MCG_CTL_P | MCG_SER_P; + if (boot_cpu_has(X86_FEATURE_XSAVE)) { host_xcr0 = xgetbv(XCR_XFEATURE_ENABLED_MASK); kvm_caps.supported_xcr0 = host_xcr0 & KVM_SUPPORTED_XCR0; @@ -9795,6 +9825,9 @@ int kvm_x86_vendor_init(struct kvm_x86_init_ops *ops) kvm_register_perf_callbacks(ops->handle_intel_pt_intr); + if (IS_ENABLED(CONFIG_KVM_SW_PROTECTED_VM) && tdp_mmu_enabled) + kvm_caps.supported_vm_types |= BIT(KVM_X86_SW_PROTECTED_VM); + if (!kvm_cpu_cap_has(X86_FEATURE_XSAVES)) kvm_caps.supported_xss = 0; @@ -9995,15 +10028,12 @@ static void set_or_clear_apicv_inhibit(unsigned long *inhibits, static void kvm_apicv_init(struct kvm *kvm) { - unsigned long *inhibits = &kvm->arch.apicv_inhibit_reasons; + enum kvm_apicv_inhibit reason = enable_apicv ? APICV_INHIBIT_REASON_ABSENT : + APICV_INHIBIT_REASON_DISABLE; - init_rwsem(&kvm->arch.apicv_update_lock); - - set_or_clear_apicv_inhibit(inhibits, APICV_INHIBIT_REASON_ABSENT, true); + set_or_clear_apicv_inhibit(&kvm->arch.apicv_inhibit_reasons, reason, true); - if (!enable_apicv) - set_or_clear_apicv_inhibit(inhibits, - APICV_INHIBIT_REASON_DISABLE, true); + init_rwsem(&kvm->arch.apicv_update_lock); } static void kvm_sched_yield(struct kvm_vcpu *vcpu, unsigned long dest_id) @@ -10051,26 +10081,15 @@ static int complete_hypercall_exit(struct kvm_vcpu *vcpu) return kvm_skip_emulated_instruction(vcpu); } -int kvm_emulate_hypercall(struct kvm_vcpu *vcpu) +unsigned long __kvm_emulate_hypercall(struct kvm_vcpu *vcpu, unsigned long nr, + unsigned long a0, unsigned long a1, + unsigned long a2, unsigned long a3, + int op_64_bit, int cpl) { - unsigned long nr, a0, a1, a2, a3, ret; - int op_64_bit; - - if (kvm_xen_hypercall_enabled(vcpu->kvm)) - return kvm_xen_hypercall(vcpu); - - if (kvm_hv_hypercall_enabled(vcpu)) - return kvm_hv_hypercall(vcpu); - - nr = kvm_rax_read(vcpu); - a0 = kvm_rbx_read(vcpu); - a1 = kvm_rcx_read(vcpu); - a2 = kvm_rdx_read(vcpu); - a3 = kvm_rsi_read(vcpu); + unsigned long ret; trace_kvm_hypercall(nr, a0, a1, a2, a3); - op_64_bit = is_64_bit_hypercall(vcpu); if (!op_64_bit) { nr &= 0xFFFFFFFF; a0 &= 0xFFFFFFFF; @@ -10079,7 +10098,7 @@ int kvm_emulate_hypercall(struct kvm_vcpu *vcpu) a3 &= 0xFFFFFFFF; } - if (static_call(kvm_x86_get_cpl)(vcpu) != 0) { + if (cpl) { ret = -KVM_EPERM; goto out; } @@ -10140,18 +10159,49 @@ int kvm_emulate_hypercall(struct kvm_vcpu *vcpu) WARN_ON_ONCE(vcpu->run->hypercall.flags & KVM_EXIT_HYPERCALL_MBZ); vcpu->arch.complete_userspace_io = complete_hypercall_exit; + /* stat is incremented on completion. */ return 0; } default: ret = -KVM_ENOSYS; break; } + out: + ++vcpu->stat.hypercalls; + return ret; +} +EXPORT_SYMBOL_GPL(__kvm_emulate_hypercall); + +int kvm_emulate_hypercall(struct kvm_vcpu *vcpu) +{ + unsigned long nr, a0, a1, a2, a3, ret; + int op_64_bit; + int cpl; + + if (kvm_xen_hypercall_enabled(vcpu->kvm)) + return kvm_xen_hypercall(vcpu); + + if (kvm_hv_hypercall_enabled(vcpu)) + return kvm_hv_hypercall(vcpu); + + nr = kvm_rax_read(vcpu); + a0 = kvm_rbx_read(vcpu); + a1 = kvm_rcx_read(vcpu); + a2 = kvm_rdx_read(vcpu); + a3 = kvm_rsi_read(vcpu); + op_64_bit = is_64_bit_hypercall(vcpu); + cpl = static_call(kvm_x86_get_cpl)(vcpu); + + ret = __kvm_emulate_hypercall(vcpu, nr, a0, a1, a2, a3, op_64_bit, cpl); + if (nr == KVM_HC_MAP_GPA_RANGE && !ret) + /* MAP_GPA tosses the request to the user space. */ + return 0; + if (!op_64_bit) ret = (u32)ret; kvm_rax_write(vcpu, ret); - ++vcpu->stat.hypercalls; return kvm_skip_emulated_instruction(vcpu); } EXPORT_SYMBOL_GPL(kvm_emulate_hypercall); @@ -11486,6 +11536,10 @@ static void __get_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs) int kvm_arch_vcpu_ioctl_get_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs) { + if (vcpu->kvm->arch.has_protected_state && + vcpu->arch.guest_state_protected) + return -EINVAL; + vcpu_load(vcpu); __get_regs(vcpu, regs); vcpu_put(vcpu); @@ -11527,6 +11581,10 @@ static void __set_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs) int kvm_arch_vcpu_ioctl_set_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs) { + if (vcpu->kvm->arch.has_protected_state && + vcpu->arch.guest_state_protected) + return -EINVAL; + vcpu_load(vcpu); __set_regs(vcpu, regs); vcpu_put(vcpu); @@ -11599,6 +11657,10 @@ static void __get_sregs2(struct kvm_vcpu *vcpu, struct kvm_sregs2 *sregs2) int kvm_arch_vcpu_ioctl_get_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs) { + if (vcpu->kvm->arch.has_protected_state && + vcpu->arch.guest_state_protected) + return -EINVAL; + vcpu_load(vcpu); __get_sregs(vcpu, sregs); vcpu_put(vcpu); @@ -11866,6 +11928,10 @@ int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu, { int ret; + if (vcpu->kvm->arch.has_protected_state && + vcpu->arch.guest_state_protected) + return -EINVAL; + vcpu_load(vcpu); ret = __set_sregs(vcpu, sregs); vcpu_put(vcpu); @@ -11983,7 +12049,7 @@ int kvm_arch_vcpu_ioctl_get_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu) struct fxregs_state *fxsave; if (fpstate_is_confidential(&vcpu->arch.guest_fpu)) - return 0; + return vcpu->kvm->arch.has_protected_state ? -EINVAL : 0; vcpu_load(vcpu); @@ -12006,7 +12072,7 @@ int kvm_arch_vcpu_ioctl_set_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu) struct fxregs_state *fxsave; if (fpstate_is_confidential(&vcpu->arch.guest_fpu)) - return 0; + return vcpu->kvm->arch.has_protected_state ? -EINVAL : 0; vcpu_load(vcpu); @@ -12532,6 +12598,8 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) return -EINVAL; kvm->arch.vm_type = type; + kvm->arch.has_private_mem = + (type == KVM_X86_SW_PROTECTED_VM); ret = kvm_page_track_init(kvm); if (ret) @@ -12731,7 +12799,7 @@ static void memslot_rmap_free(struct kvm_memory_slot *slot) int i; for (i = 0; i < KVM_NR_PAGE_SIZES; ++i) { - kvfree(slot->arch.rmap[i]); + vfree(slot->arch.rmap[i]); slot->arch.rmap[i] = NULL; } } @@ -12743,7 +12811,7 @@ void kvm_arch_free_memslot(struct kvm *kvm, struct kvm_memory_slot *slot) memslot_rmap_free(slot); for (i = 1; i < KVM_NR_PAGE_SIZES; ++i) { - kvfree(slot->arch.lpage_info[i - 1]); + vfree(slot->arch.lpage_info[i - 1]); slot->arch.lpage_info[i - 1] = NULL; } @@ -12835,7 +12903,7 @@ out_free: memslot_rmap_free(slot); for (i = 1; i < KVM_NR_PAGE_SIZES; ++i) { - kvfree(slot->arch.lpage_info[i - 1]); + vfree(slot->arch.lpage_info[i - 1]); slot->arch.lpage_info[i - 1] = NULL; } return -ENOMEM; diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h index a8b71803777b..d80a4c6b5a38 100644 --- a/arch/x86/kvm/x86.h +++ b/arch/x86/kvm/x86.h @@ -24,6 +24,8 @@ struct kvm_caps { bool has_bus_lock_exit; /* notify VM exit supported? */ bool has_notify_vmexit; + /* bit mask of VM types */ + u32 supported_vm_types; u64 supported_mce_cap; u64 supported_xcr0; diff --git a/arch/x86/lib/Makefile b/arch/x86/lib/Makefile index 6da73513f026..98583a9dbab3 100644 --- a/arch/x86/lib/Makefile +++ b/arch/x86/lib/Makefile @@ -53,7 +53,6 @@ ifneq ($(CONFIG_X86_CMPXCHG64),y) lib-y += atomic64_386_32.o endif else - obj-y += iomap_copy_64.o ifneq ($(CONFIG_GENERIC_CSUM),y) lib-y += csum-partial_64.o csum-copy_64.o csum-wrappers_64.o endif diff --git a/arch/x86/lib/copy_mc.c b/arch/x86/lib/copy_mc.c index 6e8b7e600def..97e88e58567b 100644 --- a/arch/x86/lib/copy_mc.c +++ b/arch/x86/lib/copy_mc.c @@ -4,6 +4,7 @@ #include <linux/jump_label.h> #include <linux/uaccess.h> #include <linux/export.h> +#include <linux/instrumented.h> #include <linux/string.h> #include <linux/types.h> @@ -61,10 +62,20 @@ unsigned long copy_mc_enhanced_fast_string(void *dst, const void *src, unsigned */ unsigned long __must_check copy_mc_to_kernel(void *dst, const void *src, unsigned len) { - if (copy_mc_fragile_enabled) - return copy_mc_fragile(dst, src, len); - if (static_cpu_has(X86_FEATURE_ERMS)) - return copy_mc_enhanced_fast_string(dst, src, len); + unsigned long ret; + + if (copy_mc_fragile_enabled) { + instrument_memcpy_before(dst, src, len); + ret = copy_mc_fragile(dst, src, len); + instrument_memcpy_after(dst, src, len, ret); + return ret; + } + if (static_cpu_has(X86_FEATURE_ERMS)) { + instrument_memcpy_before(dst, src, len); + ret = copy_mc_enhanced_fast_string(dst, src, len); + instrument_memcpy_after(dst, src, len, ret); + return ret; + } memcpy(dst, src, len); return 0; } @@ -75,6 +86,7 @@ unsigned long __must_check copy_mc_to_user(void __user *dst, const void *src, un unsigned long ret; if (copy_mc_fragile_enabled) { + instrument_copy_to_user(dst, src, len); __uaccess_begin(); ret = copy_mc_fragile((__force void *)dst, src, len); __uaccess_end(); @@ -82,6 +94,7 @@ unsigned long __must_check copy_mc_to_user(void __user *dst, const void *src, un } if (static_cpu_has(X86_FEATURE_ERMS)) { + instrument_copy_to_user(dst, src, len); __uaccess_begin(); ret = copy_mc_enhanced_fast_string((__force void *)dst, src, len); __uaccess_end(); diff --git a/arch/x86/lib/insn.c b/arch/x86/lib/insn.c index 1bb155a0955b..5952ab41c60f 100644 --- a/arch/x86/lib/insn.c +++ b/arch/x86/lib/insn.c @@ -185,6 +185,17 @@ found: if (X86_REX_W(b)) /* REX.W overrides opnd_size */ insn->opnd_bytes = 8; + } else if (inat_is_rex2_prefix(attr)) { + insn_set_byte(&insn->rex_prefix, 0, b); + b = peek_nbyte_next(insn_byte_t, insn, 1); + insn_set_byte(&insn->rex_prefix, 1, b); + insn->rex_prefix.nbytes = 2; + insn->next_byte += 2; + if (X86_REX_W(b)) + /* REX.W overrides opnd_size */ + insn->opnd_bytes = 8; + insn->rex_prefix.got = 1; + goto vex_end; } } insn->rex_prefix.got = 1; @@ -283,6 +294,10 @@ int insn_get_opcode(struct insn *insn) m = insn_vex_m_bits(insn); p = insn_vex_p_bits(insn); insn->attr = inat_get_avx_attribute(op, m, p); + /* SCALABLE EVEX uses p bits to encode operand size */ + if (inat_evex_scalable(insn->attr) && !insn_vex_w_bit(insn) && + p == INAT_PFX_OPNDSZ) + insn->opnd_bytes = 2; if ((inat_must_evex(insn->attr) && !insn_is_evex(insn)) || (!inat_accept_vex(insn->attr) && !inat_is_group(insn->attr))) { @@ -294,6 +309,20 @@ int insn_get_opcode(struct insn *insn) goto end; } + /* Check if there is REX2 prefix or not */ + if (insn_is_rex2(insn)) { + if (insn_rex2_m_bit(insn)) { + /* map 1 is escape 0x0f */ + insn_attr_t esc_attr = inat_get_opcode_attribute(0x0f); + + pfx_id = insn_last_prefix_id(insn); + insn->attr = inat_get_escape_attribute(op, pfx_id, esc_attr); + } else { + insn->attr = inat_get_opcode_attribute(op); + } + goto end; + } + insn->attr = inat_get_opcode_attribute(op); while (inat_is_escape(insn->attr)) { /* Get escaped opcode */ diff --git a/arch/x86/lib/iomap_copy_64.S b/arch/x86/lib/iomap_copy_64.S deleted file mode 100644 index 6ff2f56cb0f7..000000000000 --- a/arch/x86/lib/iomap_copy_64.S +++ /dev/null @@ -1,15 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * Copyright 2006 PathScale, Inc. All Rights Reserved. - */ - -#include <linux/linkage.h> - -/* - * override generic version in lib/iomap_copy.c - */ -SYM_FUNC_START(__iowrite32_copy) - movl %edx,%ecx - rep movsl - RET -SYM_FUNC_END(__iowrite32_copy) diff --git a/arch/x86/lib/x86-opcode-map.txt b/arch/x86/lib/x86-opcode-map.txt index 12af572201a2..caedb3ef6688 100644 --- a/arch/x86/lib/x86-opcode-map.txt +++ b/arch/x86/lib/x86-opcode-map.txt @@ -23,6 +23,7 @@ # # AVX Superscripts # (ev): this opcode requires EVEX prefix. +# (es): this opcode requires EVEX prefix and is SCALABALE. # (evo): this opcode is changed by EVEX prefix (EVEX opcode) # (v): this opcode requires VEX prefix. # (v1): this opcode only supports 128bit VEX. @@ -33,6 +34,10 @@ # - (F2): the last prefix is 0xF2 # - (!F3) : the last prefix is not 0xF3 (including non-last prefix case) # - (66&F2): Both 0x66 and 0xF2 prefixes are specified. +# +# REX2 Prefix +# - (!REX2): REX2 is not allowed +# - (REX2): REX2 variant e.g. JMPABS Table: one byte opcode Referrer: @@ -148,7 +153,7 @@ AVXcode: 65: SEG=GS (Prefix) 66: Operand-Size (Prefix) 67: Address-Size (Prefix) -68: PUSH Iz (d64) +68: PUSH Iz 69: IMUL Gv,Ev,Iz 6a: PUSH Ib (d64) 6b: IMUL Gv,Ev,Ib @@ -157,22 +162,22 @@ AVXcode: 6e: OUTS/OUTSB DX,Xb 6f: OUTS/OUTSW/OUTSD DX,Xz # 0x70 - 0x7f -70: JO Jb -71: JNO Jb -72: JB/JNAE/JC Jb -73: JNB/JAE/JNC Jb -74: JZ/JE Jb -75: JNZ/JNE Jb -76: JBE/JNA Jb -77: JNBE/JA Jb -78: JS Jb -79: JNS Jb -7a: JP/JPE Jb -7b: JNP/JPO Jb -7c: JL/JNGE Jb -7d: JNL/JGE Jb -7e: JLE/JNG Jb -7f: JNLE/JG Jb +70: JO Jb (!REX2) +71: JNO Jb (!REX2) +72: JB/JNAE/JC Jb (!REX2) +73: JNB/JAE/JNC Jb (!REX2) +74: JZ/JE Jb (!REX2) +75: JNZ/JNE Jb (!REX2) +76: JBE/JNA Jb (!REX2) +77: JNBE/JA Jb (!REX2) +78: JS Jb (!REX2) +79: JNS Jb (!REX2) +7a: JP/JPE Jb (!REX2) +7b: JNP/JPO Jb (!REX2) +7c: JL/JNGE Jb (!REX2) +7d: JNL/JGE Jb (!REX2) +7e: JLE/JNG Jb (!REX2) +7f: JNLE/JG Jb (!REX2) # 0x80 - 0x8f 80: Grp1 Eb,Ib (1A) 81: Grp1 Ev,Iz (1A) @@ -208,24 +213,24 @@ AVXcode: 9e: SAHF 9f: LAHF # 0xa0 - 0xaf -a0: MOV AL,Ob -a1: MOV rAX,Ov -a2: MOV Ob,AL -a3: MOV Ov,rAX -a4: MOVS/B Yb,Xb -a5: MOVS/W/D/Q Yv,Xv -a6: CMPS/B Xb,Yb -a7: CMPS/W/D Xv,Yv -a8: TEST AL,Ib -a9: TEST rAX,Iz -aa: STOS/B Yb,AL -ab: STOS/W/D/Q Yv,rAX -ac: LODS/B AL,Xb -ad: LODS/W/D/Q rAX,Xv -ae: SCAS/B AL,Yb +a0: MOV AL,Ob (!REX2) +a1: MOV rAX,Ov (!REX2) | JMPABS O (REX2),(o64) +a2: MOV Ob,AL (!REX2) +a3: MOV Ov,rAX (!REX2) +a4: MOVS/B Yb,Xb (!REX2) +a5: MOVS/W/D/Q Yv,Xv (!REX2) +a6: CMPS/B Xb,Yb (!REX2) +a7: CMPS/W/D Xv,Yv (!REX2) +a8: TEST AL,Ib (!REX2) +a9: TEST rAX,Iz (!REX2) +aa: STOS/B Yb,AL (!REX2) +ab: STOS/W/D/Q Yv,rAX (!REX2) +ac: LODS/B AL,Xb (!REX2) +ad: LODS/W/D/Q rAX,Xv (!REX2) +ae: SCAS/B AL,Yb (!REX2) # Note: The May 2011 Intel manual shows Xv for the second parameter of the # next instruction but Yv is correct -af: SCAS/W/D/Q rAX,Yv +af: SCAS/W/D/Q rAX,Yv (!REX2) # 0xb0 - 0xbf b0: MOV AL/R8L,Ib b1: MOV CL/R9L,Ib @@ -266,7 +271,7 @@ d1: Grp2 Ev,1 (1A) d2: Grp2 Eb,CL (1A) d3: Grp2 Ev,CL (1A) d4: AAM Ib (i64) -d5: AAD Ib (i64) +d5: AAD Ib (i64) | REX2 (Prefix),(o64) d6: d7: XLAT/XLATB d8: ESC @@ -281,26 +286,26 @@ df: ESC # Note: "forced64" is Intel CPU behavior: they ignore 0x66 prefix # in 64-bit mode. AMD CPUs accept 0x66 prefix, it causes RIP truncation # to 16 bits. In 32-bit mode, 0x66 is accepted by both Intel and AMD. -e0: LOOPNE/LOOPNZ Jb (f64) -e1: LOOPE/LOOPZ Jb (f64) -e2: LOOP Jb (f64) -e3: JrCXZ Jb (f64) -e4: IN AL,Ib -e5: IN eAX,Ib -e6: OUT Ib,AL -e7: OUT Ib,eAX +e0: LOOPNE/LOOPNZ Jb (f64) (!REX2) +e1: LOOPE/LOOPZ Jb (f64) (!REX2) +e2: LOOP Jb (f64) (!REX2) +e3: JrCXZ Jb (f64) (!REX2) +e4: IN AL,Ib (!REX2) +e5: IN eAX,Ib (!REX2) +e6: OUT Ib,AL (!REX2) +e7: OUT Ib,eAX (!REX2) # With 0x66 prefix in 64-bit mode, for AMD CPUs immediate offset # in "near" jumps and calls is 16-bit. For CALL, # push of return address is 16-bit wide, RSP is decremented by 2 # but is not truncated to 16 bits, unlike RIP. -e8: CALL Jz (f64) -e9: JMP-near Jz (f64) -ea: JMP-far Ap (i64) -eb: JMP-short Jb (f64) -ec: IN AL,DX -ed: IN eAX,DX -ee: OUT DX,AL -ef: OUT DX,eAX +e8: CALL Jz (f64) (!REX2) +e9: JMP-near Jz (f64) (!REX2) +ea: JMP-far Ap (i64) (!REX2) +eb: JMP-short Jb (f64) (!REX2) +ec: IN AL,DX (!REX2) +ed: IN eAX,DX (!REX2) +ee: OUT DX,AL (!REX2) +ef: OUT DX,eAX (!REX2) # 0xf0 - 0xff f0: LOCK (Prefix) f1: @@ -386,14 +391,14 @@ AVXcode: 1 2e: vucomiss Vss,Wss (v1) | vucomisd Vsd,Wsd (66),(v1) 2f: vcomiss Vss,Wss (v1) | vcomisd Vsd,Wsd (66),(v1) # 0x0f 0x30-0x3f -30: WRMSR -31: RDTSC -32: RDMSR -33: RDPMC -34: SYSENTER -35: SYSEXIT +30: WRMSR (!REX2) +31: RDTSC (!REX2) +32: RDMSR (!REX2) +33: RDPMC (!REX2) +34: SYSENTER (!REX2) +35: SYSEXIT (!REX2) 36: -37: GETSEC +37: GETSEC (!REX2) 38: escape # 3-byte escape 1 39: 3a: escape # 3-byte escape 2 @@ -473,22 +478,22 @@ AVXcode: 1 7f: movq Qq,Pq | vmovdqa Wx,Vx (66) | vmovdqa32/64 Wx,Vx (66),(evo) | vmovdqu Wx,Vx (F3) | vmovdqu32/64 Wx,Vx (F3),(evo) | vmovdqu8/16 Wx,Vx (F2),(ev) # 0x0f 0x80-0x8f # Note: "forced64" is Intel CPU behavior (see comment about CALL insn). -80: JO Jz (f64) -81: JNO Jz (f64) -82: JB/JC/JNAE Jz (f64) -83: JAE/JNB/JNC Jz (f64) -84: JE/JZ Jz (f64) -85: JNE/JNZ Jz (f64) -86: JBE/JNA Jz (f64) -87: JA/JNBE Jz (f64) -88: JS Jz (f64) -89: JNS Jz (f64) -8a: JP/JPE Jz (f64) -8b: JNP/JPO Jz (f64) -8c: JL/JNGE Jz (f64) -8d: JNL/JGE Jz (f64) -8e: JLE/JNG Jz (f64) -8f: JNLE/JG Jz (f64) +80: JO Jz (f64) (!REX2) +81: JNO Jz (f64) (!REX2) +82: JB/JC/JNAE Jz (f64) (!REX2) +83: JAE/JNB/JNC Jz (f64) (!REX2) +84: JE/JZ Jz (f64) (!REX2) +85: JNE/JNZ Jz (f64) (!REX2) +86: JBE/JNA Jz (f64) (!REX2) +87: JA/JNBE Jz (f64) (!REX2) +88: JS Jz (f64) (!REX2) +89: JNS Jz (f64) (!REX2) +8a: JP/JPE Jz (f64) (!REX2) +8b: JNP/JPO Jz (f64) (!REX2) +8c: JL/JNGE Jz (f64) (!REX2) +8d: JNL/JGE Jz (f64) (!REX2) +8e: JLE/JNG Jz (f64) (!REX2) +8f: JNLE/JG Jz (f64) (!REX2) # 0x0f 0x90-0x9f 90: SETO Eb | kmovw/q Vk,Wk | kmovb/d Vk,Wk (66) 91: SETNO Eb | kmovw/q Mv,Vk | kmovb/d Mv,Vk (66) @@ -698,17 +703,17 @@ AVXcode: 2 4d: vrcp14ss/d Vsd,Hpd,Wsd (66),(ev) 4e: vrsqrt14ps/d Vpd,Wpd (66),(ev) 4f: vrsqrt14ss/d Vsd,Hsd,Wsd (66),(ev) -50: vpdpbusd Vx,Hx,Wx (66),(ev) -51: vpdpbusds Vx,Hx,Wx (66),(ev) -52: vdpbf16ps Vx,Hx,Wx (F3),(ev) | vpdpwssd Vx,Hx,Wx (66),(ev) | vp4dpwssd Vdqq,Hdqq,Wdq (F2),(ev) -53: vpdpwssds Vx,Hx,Wx (66),(ev) | vp4dpwssds Vdqq,Hdqq,Wdq (F2),(ev) +50: vpdpbusd Vx,Hx,Wx (66) | vpdpbssd Vx,Hx,Wx (F2),(v) | vpdpbsud Vx,Hx,Wx (F3),(v) | vpdpbuud Vx,Hx,Wx (v) +51: vpdpbusds Vx,Hx,Wx (66) | vpdpbssds Vx,Hx,Wx (F2),(v) | vpdpbsuds Vx,Hx,Wx (F3),(v) | vpdpbuuds Vx,Hx,Wx (v) +52: vdpbf16ps Vx,Hx,Wx (F3),(ev) | vpdpwssd Vx,Hx,Wx (66) | vp4dpwssd Vdqq,Hdqq,Wdq (F2),(ev) +53: vpdpwssds Vx,Hx,Wx (66) | vp4dpwssds Vdqq,Hdqq,Wdq (F2),(ev) 54: vpopcntb/w Vx,Wx (66),(ev) 55: vpopcntd/q Vx,Wx (66),(ev) 58: vpbroadcastd Vx,Wx (66),(v) 59: vpbroadcastq Vx,Wx (66),(v) | vbroadcasti32x2 Vx,Wx (66),(evo) 5a: vbroadcasti128 Vqq,Mdq (66),(v) | vbroadcasti32x4/64x2 Vx,Wx (66),(evo) 5b: vbroadcasti32x8/64x4 Vqq,Mdq (66),(ev) -5c: TDPBF16PS Vt,Wt,Ht (F3),(v1) +5c: TDPBF16PS Vt,Wt,Ht (F3),(v1) | TDPFP16PS Vt,Wt,Ht (F2),(v1),(o64) # Skip 0x5d 5e: TDPBSSD Vt,Wt,Ht (F2),(v1) | TDPBSUD Vt,Wt,Ht (F3),(v1) | TDPBUSD Vt,Wt,Ht (66),(v1) | TDPBUUD Vt,Wt,Ht (v1) # Skip 0x5f-0x61 @@ -718,10 +723,12 @@ AVXcode: 2 65: vblendmps/d Vx,Hx,Wx (66),(ev) 66: vpblendmb/w Vx,Hx,Wx (66),(ev) 68: vp2intersectd/q Kx,Hx,Wx (F2),(ev) -# Skip 0x69-0x6f +# Skip 0x69-0x6b +6c: TCMMIMFP16PS Vt,Wt,Ht (66),(v1),(o64) | TCMMRLFP16PS Vt,Wt,Ht (v1),(o64) +# Skip 0x6d-0x6f 70: vpshldvw Vx,Hx,Wx (66),(ev) 71: vpshldvd/q Vx,Hx,Wx (66),(ev) -72: vcvtne2ps2bf16 Vx,Hx,Wx (F2),(ev) | vcvtneps2bf16 Vx,Wx (F3),(ev) | vpshrdvw Vx,Hx,Wx (66),(ev) +72: vcvtne2ps2bf16 Vx,Hx,Wx (F2),(ev) | vcvtneps2bf16 Vx,Wx (F3) | vpshrdvw Vx,Hx,Wx (66),(ev) 73: vpshrdvd/q Vx,Hx,Wx (66),(ev) 75: vpermi2b/w Vx,Hx,Wx (66),(ev) 76: vpermi2d/q Vx,Hx,Wx (66),(ev) @@ -777,8 +784,10 @@ ac: vfnmadd213ps/d Vx,Hx,Wx (66),(v) ad: vfnmadd213ss/d Vx,Hx,Wx (66),(v),(v1) ae: vfnmsub213ps/d Vx,Hx,Wx (66),(v) af: vfnmsub213ss/d Vx,Hx,Wx (66),(v),(v1) -b4: vpmadd52luq Vx,Hx,Wx (66),(ev) -b5: vpmadd52huq Vx,Hx,Wx (66),(ev) +b0: vcvtneebf162ps Vx,Mx (F3),(!11B),(v) | vcvtneeph2ps Vx,Mx (66),(!11B),(v) | vcvtneobf162ps Vx,Mx (F2),(!11B),(v) | vcvtneoph2ps Vx,Mx (!11B),(v) +b1: vbcstnebf162ps Vx,Mw (F3),(!11B),(v) | vbcstnesh2ps Vx,Mw (66),(!11B),(v) +b4: vpmadd52luq Vx,Hx,Wx (66) +b5: vpmadd52huq Vx,Hx,Wx (66) b6: vfmaddsub231ps/d Vx,Hx,Wx (66),(v) b7: vfmsubadd231ps/d Vx,Hx,Wx (66),(v) b8: vfmadd231ps/d Vx,Hx,Wx (66),(v) @@ -796,15 +805,35 @@ c7: Grp19 (1A) c8: sha1nexte Vdq,Wdq | vexp2ps/d Vx,Wx (66),(ev) c9: sha1msg1 Vdq,Wdq ca: sha1msg2 Vdq,Wdq | vrcp28ps/d Vx,Wx (66),(ev) -cb: sha256rnds2 Vdq,Wdq | vrcp28ss/d Vx,Hx,Wx (66),(ev) -cc: sha256msg1 Vdq,Wdq | vrsqrt28ps/d Vx,Wx (66),(ev) -cd: sha256msg2 Vdq,Wdq | vrsqrt28ss/d Vx,Hx,Wx (66),(ev) +cb: sha256rnds2 Vdq,Wdq | vrcp28ss/d Vx,Hx,Wx (66),(ev) | vsha512rnds2 Vqq,Hqq,Udq (F2),(11B),(v) +cc: sha256msg1 Vdq,Wdq | vrsqrt28ps/d Vx,Wx (66),(ev) | vsha512msg1 Vqq,Udq (F2),(11B),(v) +cd: sha256msg2 Vdq,Wdq | vrsqrt28ss/d Vx,Hx,Wx (66),(ev) | vsha512msg2 Vqq,Uqq (F2),(11B),(v) cf: vgf2p8mulb Vx,Wx (66) +d2: vpdpwsud Vx,Hx,Wx (F3),(v) | vpdpwusd Vx,Hx,Wx (66),(v) | vpdpwuud Vx,Hx,Wx (v) +d3: vpdpwsuds Vx,Hx,Wx (F3),(v) | vpdpwusds Vx,Hx,Wx (66),(v) | vpdpwuuds Vx,Hx,Wx (v) +d8: AESENCWIDE128KL Qpi (F3),(000),(00B) | AESENCWIDE256KL Qpi (F3),(000),(10B) | AESDECWIDE128KL Qpi (F3),(000),(01B) | AESDECWIDE256KL Qpi (F3),(000),(11B) +da: vsm3msg1 Vdq,Hdq,Udq (v1) | vsm3msg2 Vdq,Hdq,Udq (66),(v1) | vsm4key4 Vx,Hx,Wx (F3),(v) | vsm4rnds4 Vx,Hx,Wx (F2),(v) db: VAESIMC Vdq,Wdq (66),(v1) -dc: vaesenc Vx,Hx,Wx (66) -dd: vaesenclast Vx,Hx,Wx (66) -de: vaesdec Vx,Hx,Wx (66) -df: vaesdeclast Vx,Hx,Wx (66) +dc: vaesenc Vx,Hx,Wx (66) | LOADIWKEY Vx,Hx (F3) | AESENC128KL Vpd,Qpi (F3) +dd: vaesenclast Vx,Hx,Wx (66) | AESDEC128KL Vpd,Qpi (F3) +de: vaesdec Vx,Hx,Wx (66) | AESENC256KL Vpd,Qpi (F3) +df: vaesdeclast Vx,Hx,Wx (66) | AESDEC256KL Vpd,Qpi (F3) +e0: CMPOXADD My,Gy,By (66),(v1),(o64) +e1: CMPNOXADD My,Gy,By (66),(v1),(o64) +e2: CMPBXADD My,Gy,By (66),(v1),(o64) +e3: CMPNBXADD My,Gy,By (66),(v1),(o64) +e4: CMPZXADD My,Gy,By (66),(v1),(o64) +e5: CMPNZXADD My,Gy,By (66),(v1),(o64) +e6: CMPBEXADD My,Gy,By (66),(v1),(o64) +e7: CMPNBEXADD My,Gy,By (66),(v1),(o64) +e8: CMPSXADD My,Gy,By (66),(v1),(o64) +e9: CMPNSXADD My,Gy,By (66),(v1),(o64) +ea: CMPPXADD My,Gy,By (66),(v1),(o64) +eb: CMPNPXADD My,Gy,By (66),(v1),(o64) +ec: CMPLXADD My,Gy,By (66),(v1),(o64) +ed: CMPNLXADD My,Gy,By (66),(v1),(o64) +ee: CMPLEXADD My,Gy,By (66),(v1),(o64) +ef: CMPNLEXADD My,Gy,By (66),(v1),(o64) f0: MOVBE Gy,My | MOVBE Gw,Mw (66) | CRC32 Gd,Eb (F2) | CRC32 Gd,Eb (66&F2) f1: MOVBE My,Gy | MOVBE Mw,Gw (66) | CRC32 Gd,Ey (F2) | CRC32 Gd,Ew (66&F2) f2: ANDN Gy,By,Ey (v) @@ -812,8 +841,11 @@ f3: Grp17 (1A) f5: BZHI Gy,Ey,By (v) | PEXT Gy,By,Ey (F3),(v) | PDEP Gy,By,Ey (F2),(v) | WRUSSD/Q My,Gy (66) f6: ADCX Gy,Ey (66) | ADOX Gy,Ey (F3) | MULX By,Gy,rDX,Ey (F2),(v) | WRSSD/Q My,Gy f7: BEXTR Gy,Ey,By (v) | SHLX Gy,Ey,By (66),(v) | SARX Gy,Ey,By (F3),(v) | SHRX Gy,Ey,By (F2),(v) -f8: MOVDIR64B Gv,Mdqq (66) | ENQCMD Gv,Mdqq (F2) | ENQCMDS Gv,Mdqq (F3) +f8: MOVDIR64B Gv,Mdqq (66) | ENQCMD Gv,Mdqq (F2) | ENQCMDS Gv,Mdqq (F3) | URDMSR Rq,Gq (F2),(11B) | UWRMSR Gq,Rq (F3),(11B) f9: MOVDIRI My,Gy +fa: ENCODEKEY128 Ew,Ew (F3) +fb: ENCODEKEY256 Ew,Ew (F3) +fc: AADD My,Gy | AAND My,Gy (66) | AOR My,Gy (F2) | AXOR My,Gy (F3) EndTable Table: 3-byte opcode 2 (0x0f 0x3a) @@ -893,10 +925,103 @@ c2: vcmpph Vx,Hx,Wx,Ib (ev) | vcmpsh Vx,Hx,Wx,Ib (F3),(ev) cc: sha1rnds4 Vdq,Wdq,Ib ce: vgf2p8affineqb Vx,Wx,Ib (66) cf: vgf2p8affineinvqb Vx,Wx,Ib (66) +de: vsm3rnds2 Vdq,Hdq,Wdq,Ib (66),(v1) df: VAESKEYGEN Vdq,Wdq,Ib (66),(v1) f0: RORX Gy,Ey,Ib (F2),(v) | HRESET Gv,Ib (F3),(000),(11B) EndTable +Table: EVEX map 4 +Referrer: +AVXcode: 4 +00: ADD Eb,Gb (ev) +01: ADD Ev,Gv (es) | ADD Ev,Gv (66),(es) +02: ADD Gb,Eb (ev) +03: ADD Gv,Ev (es) | ADD Gv,Ev (66),(es) +08: OR Eb,Gb (ev) +09: OR Ev,Gv (es) | OR Ev,Gv (66),(es) +0a: OR Gb,Eb (ev) +0b: OR Gv,Ev (es) | OR Gv,Ev (66),(es) +10: ADC Eb,Gb (ev) +11: ADC Ev,Gv (es) | ADC Ev,Gv (66),(es) +12: ADC Gb,Eb (ev) +13: ADC Gv,Ev (es) | ADC Gv,Ev (66),(es) +18: SBB Eb,Gb (ev) +19: SBB Ev,Gv (es) | SBB Ev,Gv (66),(es) +1a: SBB Gb,Eb (ev) +1b: SBB Gv,Ev (es) | SBB Gv,Ev (66),(es) +20: AND Eb,Gb (ev) +21: AND Ev,Gv (es) | AND Ev,Gv (66),(es) +22: AND Gb,Eb (ev) +23: AND Gv,Ev (es) | AND Gv,Ev (66),(es) +24: SHLD Ev,Gv,Ib (es) | SHLD Ev,Gv,Ib (66),(es) +28: SUB Eb,Gb (ev) +29: SUB Ev,Gv (es) | SUB Ev,Gv (66),(es) +2a: SUB Gb,Eb (ev) +2b: SUB Gv,Ev (es) | SUB Gv,Ev (66),(es) +2c: SHRD Ev,Gv,Ib (es) | SHRD Ev,Gv,Ib (66),(es) +30: XOR Eb,Gb (ev) +31: XOR Ev,Gv (es) | XOR Ev,Gv (66),(es) +32: XOR Gb,Eb (ev) +33: XOR Gv,Ev (es) | XOR Gv,Ev (66),(es) +# CCMPSCC instructions are: CCOMB, CCOMBE, CCOMF, CCOML, CCOMLE, CCOMNB, CCOMNBE, CCOMNL, CCOMNLE, +# CCOMNO, CCOMNS, CCOMNZ, CCOMO, CCOMS, CCOMT, CCOMZ +38: CCMPSCC Eb,Gb (ev) +39: CCMPSCC Ev,Gv (es) | CCMPSCC Ev,Gv (66),(es) +3a: CCMPSCC Gv,Ev (ev) +3b: CCMPSCC Gv,Ev (es) | CCMPSCC Gv,Ev (66),(es) +40: CMOVO Gv,Ev (es) | CMOVO Gv,Ev (66),(es) | CFCMOVO Ev,Ev (es) | CFCMOVO Ev,Ev (66),(es) | SETO Eb (F2),(ev) +41: CMOVNO Gv,Ev (es) | CMOVNO Gv,Ev (66),(es) | CFCMOVNO Ev,Ev (es) | CFCMOVNO Ev,Ev (66),(es) | SETNO Eb (F2),(ev) +42: CMOVB Gv,Ev (es) | CMOVB Gv,Ev (66),(es) | CFCMOVB Ev,Ev (es) | CFCMOVB Ev,Ev (66),(es) | SETB Eb (F2),(ev) +43: CMOVNB Gv,Ev (es) | CMOVNB Gv,Ev (66),(es) | CFCMOVNB Ev,Ev (es) | CFCMOVNB Ev,Ev (66),(es) | SETNB Eb (F2),(ev) +44: CMOVZ Gv,Ev (es) | CMOVZ Gv,Ev (66),(es) | CFCMOVZ Ev,Ev (es) | CFCMOVZ Ev,Ev (66),(es) | SETZ Eb (F2),(ev) +45: CMOVNZ Gv,Ev (es) | CMOVNZ Gv,Ev (66),(es) | CFCMOVNZ Ev,Ev (es) | CFCMOVNZ Ev,Ev (66),(es) | SETNZ Eb (F2),(ev) +46: CMOVBE Gv,Ev (es) | CMOVBE Gv,Ev (66),(es) | CFCMOVBE Ev,Ev (es) | CFCMOVBE Ev,Ev (66),(es) | SETBE Eb (F2),(ev) +47: CMOVNBE Gv,Ev (es) | CMOVNBE Gv,Ev (66),(es) | CFCMOVNBE Ev,Ev (es) | CFCMOVNBE Ev,Ev (66),(es) | SETNBE Eb (F2),(ev) +48: CMOVS Gv,Ev (es) | CMOVS Gv,Ev (66),(es) | CFCMOVS Ev,Ev (es) | CFCMOVS Ev,Ev (66),(es) | SETS Eb (F2),(ev) +49: CMOVNS Gv,Ev (es) | CMOVNS Gv,Ev (66),(es) | CFCMOVNS Ev,Ev (es) | CFCMOVNS Ev,Ev (66),(es) | SETNS Eb (F2),(ev) +4a: CMOVP Gv,Ev (es) | CMOVP Gv,Ev (66),(es) | CFCMOVP Ev,Ev (es) | CFCMOVP Ev,Ev (66),(es) | SETP Eb (F2),(ev) +4b: CMOVNP Gv,Ev (es) | CMOVNP Gv,Ev (66),(es) | CFCMOVNP Ev,Ev (es) | CFCMOVNP Ev,Ev (66),(es) | SETNP Eb (F2),(ev) +4c: CMOVL Gv,Ev (es) | CMOVL Gv,Ev (66),(es) | CFCMOVL Ev,Ev (es) | CFCMOVL Ev,Ev (66),(es) | SETL Eb (F2),(ev) +4d: CMOVNL Gv,Ev (es) | CMOVNL Gv,Ev (66),(es) | CFCMOVNL Ev,Ev (es) | CFCMOVNL Ev,Ev (66),(es) | SETNL Eb (F2),(ev) +4e: CMOVLE Gv,Ev (es) | CMOVLE Gv,Ev (66),(es) | CFCMOVLE Ev,Ev (es) | CFCMOVLE Ev,Ev (66),(es) | SETLE Eb (F2),(ev) +4f: CMOVNLE Gv,Ev (es) | CMOVNLE Gv,Ev (66),(es) | CFCMOVNLE Ev,Ev (es) | CFCMOVNLE Ev,Ev (66),(es) | SETNLE Eb (F2),(ev) +60: MOVBE Gv,Ev (es) | MOVBE Gv,Ev (66),(es) +61: MOVBE Ev,Gv (es) | MOVBE Ev,Gv (66),(es) +65: WRUSSD Md,Gd (66),(ev) | WRUSSQ Mq,Gq (66),(ev) +66: ADCX Gy,Ey (66),(ev) | ADOX Gy,Ey (F3),(ev) | WRSSD Md,Gd (ev) | WRSSQ Mq,Gq (66),(ev) +69: IMUL Gv,Ev,Iz (es) | IMUL Gv,Ev,Iz (66),(es) +6b: IMUL Gv,Ev,Ib (es) | IMUL Gv,Ev,Ib (66),(es) +80: Grp1 Eb,Ib (1A),(ev) +81: Grp1 Ev,Iz (1A),(es) +83: Grp1 Ev,Ib (1A),(es) +# CTESTSCC instructions are: CTESTB, CTESTBE, CTESTF, CTESTL, CTESTLE, CTESTNB, CTESTNBE, CTESTNL, +# CTESTNLE, CTESTNO, CTESTNS, CTESTNZ, CTESTO, CTESTS, CTESTT, CTESTZ +84: CTESTSCC (ev) +85: CTESTSCC (es) | CTESTSCC (66),(es) +88: POPCNT Gv,Ev (es) | POPCNT Gv,Ev (66),(es) +8f: POP2 Bq,Rq (000),(11B),(ev) +a5: SHLD Ev,Gv,CL (es) | SHLD Ev,Gv,CL (66),(es) +ad: SHRD Ev,Gv,CL (es) | SHRD Ev,Gv,CL (66),(es) +af: IMUL Gv,Ev (es) | IMUL Gv,Ev (66),(es) +c0: Grp2 Eb,Ib (1A),(ev) +c1: Grp2 Ev,Ib (1A),(es) +d0: Grp2 Eb,1 (1A),(ev) +d1: Grp2 Ev,1 (1A),(es) +d2: Grp2 Eb,CL (1A),(ev) +d3: Grp2 Ev,CL (1A),(es) +f0: CRC32 Gy,Eb (es) | INVEPT Gq,Mdq (F3),(ev) +f1: CRC32 Gy,Ey (es) | CRC32 Gy,Ey (66),(es) | INVVPID Gy,Mdq (F3),(ev) +f2: INVPCID Gy,Mdq (F3),(ev) +f4: TZCNT Gv,Ev (es) | TZCNT Gv,Ev (66),(es) +f5: LZCNT Gv,Ev (es) | LZCNT Gv,Ev (66),(es) +f6: Grp3_1 Eb (1A),(ev) +f7: Grp3_2 Ev (1A),(es) +f8: MOVDIR64B Gv,Mdqq (66),(ev) | ENQCMD Gv,Mdqq (F2),(ev) | ENQCMDS Gv,Mdqq (F3),(ev) | URDMSR Rq,Gq (F2),(11B),(ev) | UWRMSR Gq,Rq (F3),(11B),(ev) +f9: MOVDIRI My,Gy (ev) +fe: Grp4 (1A),(ev) +ff: Grp5 (1A),(es) | PUSH2 Bq,Rq (110),(11B),(ev) +EndTable + Table: EVEX map 5 Referrer: AVXcode: 5 @@ -975,6 +1100,12 @@ d6: vfcmulcph Vx,Hx,Wx (F2),(ev) | vfmulcph Vx,Hx,Wx (F3),(ev) d7: vfcmulcsh Vx,Hx,Wx (F2),(ev) | vfmulcsh Vx,Hx,Wx (F3),(ev) EndTable +Table: VEX map 7 +Referrer: +AVXcode: 7 +f8: URDMSR Rq,Id (F2),(v1),(11B) | UWRMSR Id,Rq (F3),(v1),(11B) +EndTable + GrpTable: Grp1 0: ADD 1: OR @@ -1051,7 +1182,7 @@ GrpTable: Grp6 EndTable GrpTable: Grp7 -0: SGDT Ms | VMCALL (001),(11B) | VMLAUNCH (010),(11B) | VMRESUME (011),(11B) | VMXOFF (100),(11B) | PCONFIG (101),(11B) | ENCLV (000),(11B) | WRMSRNS (110),(11B) +0: SGDT Ms | VMCALL (001),(11B) | VMLAUNCH (010),(11B) | VMRESUME (011),(11B) | VMXOFF (100),(11B) | PCONFIG (101),(11B) | ENCLV (000),(11B) | WRMSRNS (110),(11B) | RDMSRLIST (F2),(110),(11B) | WRMSRLIST (F3),(110),(11B) | PBNDKB (111),(11B) 1: SIDT Ms | MONITOR (000),(11B) | MWAIT (001),(11B) | CLAC (010),(11B) | STAC (011),(11B) | ENCLS (111),(11B) | ERETU (F3),(010),(11B) | ERETS (F2),(010),(11B) 2: LGDT Ms | XGETBV (000),(11B) | XSETBV (001),(11B) | VMFUNC (100),(11B) | XEND (101)(11B) | XTEST (110)(11B) | ENCLU (111),(11B) 3: LIDT Ms @@ -1137,6 +1268,8 @@ GrpTable: Grp16 1: prefetch T0 2: prefetch T1 3: prefetch T2 +6: prefetch IT1 +7: prefetch IT0 EndTable GrpTable: Grp17 diff --git a/arch/x86/mm/Makefile b/arch/x86/mm/Makefile index 428048e73bd2..8d3a00e5c528 100644 --- a/arch/x86/mm/Makefile +++ b/arch/x86/mm/Makefile @@ -34,7 +34,7 @@ obj-y += pat/ CFLAGS_physaddr.o := -fno-stack-protector CFLAGS_mem_encrypt_identity.o := -fno-stack-protector -CFLAGS_fault.o := -I $(srctree)/$(src)/../include/asm/trace +CFLAGS_fault.o := -I $(src)/../include/asm/trace obj-$(CONFIG_X86_32) += pgtable_32.o iomap_32.o diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index f26ecabc9424..e6c469b323cc 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -20,6 +20,7 @@ #include <linux/efi.h> /* efi_crash_gracefully_on_page_fault()*/ #include <linux/mm_types.h> #include <linux/mm.h> /* find_and_lock_vma() */ +#include <linux/vmalloc.h> #include <asm/cpufeature.h> /* boot_cpu_has, ... */ #include <asm/traps.h> /* dotraplinkage, ... */ @@ -835,14 +836,17 @@ bad_area_nosemaphore(struct pt_regs *regs, unsigned long error_code, static void __bad_area(struct pt_regs *regs, unsigned long error_code, - unsigned long address, u32 pkey, int si_code) + unsigned long address, struct mm_struct *mm, + struct vm_area_struct *vma, u32 pkey, int si_code) { - struct mm_struct *mm = current->mm; /* * Something tried to access memory that isn't in our memory map.. * Fix it, but check if it's kernel or user first.. */ - mmap_read_unlock(mm); + if (mm) + mmap_read_unlock(mm); + else + vma_end_read(vma); __bad_area_nosemaphore(regs, error_code, address, pkey, si_code); } @@ -866,7 +870,8 @@ static inline bool bad_area_access_from_pkeys(unsigned long error_code, static noinline void bad_area_access_error(struct pt_regs *regs, unsigned long error_code, - unsigned long address, struct vm_area_struct *vma) + unsigned long address, struct mm_struct *mm, + struct vm_area_struct *vma) { /* * This OSPKE check is not strictly necessary at runtime. @@ -896,9 +901,9 @@ bad_area_access_error(struct pt_regs *regs, unsigned long error_code, */ u32 pkey = vma_pkey(vma); - __bad_area(regs, error_code, address, pkey, SEGV_PKUERR); + __bad_area(regs, error_code, address, mm, vma, pkey, SEGV_PKUERR); } else { - __bad_area(regs, error_code, address, 0, SEGV_ACCERR); + __bad_area(regs, error_code, address, mm, vma, 0, SEGV_ACCERR); } } @@ -1326,8 +1331,9 @@ void do_user_addr_fault(struct pt_regs *regs, goto lock_mmap; if (unlikely(access_error(error_code, vma))) { - vma_end_read(vma); - goto lock_mmap; + bad_area_access_error(regs, error_code, address, NULL, vma); + count_vm_vma_lock_event(VMA_LOCK_SUCCESS); + return; } fault = handle_mm_fault(vma, address, flags | FAULT_FLAG_VMA_LOCK, regs); if (!(fault & (VM_FAULT_RETRY | VM_FAULT_COMPLETED))) @@ -1363,7 +1369,7 @@ retry: * we can handle it.. */ if (unlikely(access_error(error_code, vma))) { - bad_area_access_error(regs, error_code, address, vma); + bad_area_access_error(regs, error_code, address, mm, vma); return; } diff --git a/arch/x86/mm/hugetlbpage.c b/arch/x86/mm/hugetlbpage.c index 5804bbae4f01..807a5859a3c4 100644 --- a/arch/x86/mm/hugetlbpage.c +++ b/arch/x86/mm/hugetlbpage.c @@ -19,41 +19,14 @@ #include <asm/tlbflush.h> #include <asm/elf.h> -/* - * pmd_huge() returns 1 if @pmd is hugetlb related entry, that is normal - * hugetlb entry or non-present (migration or hwpoisoned) hugetlb entry. - * Otherwise, returns 0. - */ -int pmd_huge(pmd_t pmd) -{ - return !pmd_none(pmd) && - (pmd_val(pmd) & (_PAGE_PRESENT|_PAGE_PSE)) != _PAGE_PRESENT; -} - -/* - * pud_huge() returns 1 if @pud is hugetlb related entry, that is normal - * hugetlb entry or non-present (migration or hwpoisoned) hugetlb entry. - * Otherwise, returns 0. - */ -int pud_huge(pud_t pud) -{ -#if CONFIG_PGTABLE_LEVELS > 2 - return !pud_none(pud) && - (pud_val(pud) & (_PAGE_PRESENT|_PAGE_PSE)) != _PAGE_PRESENT; -#else - return 0; -#endif -} - #ifdef CONFIG_HUGETLB_PAGE static unsigned long hugetlb_get_unmapped_area_bottomup(struct file *file, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags) { struct hstate *h = hstate_file(file); - struct vm_unmapped_area_info info; + struct vm_unmapped_area_info info = {}; - info.flags = 0; info.length = len; info.low_limit = get_mmap_base(1); @@ -65,7 +38,6 @@ static unsigned long hugetlb_get_unmapped_area_bottomup(struct file *file, task_size_32bit() : task_size_64bit(addr > DEFAULT_MAP_WINDOW); info.align_mask = PAGE_MASK & ~huge_page_mask(h); - info.align_offset = 0; return vm_unmapped_area(&info); } @@ -74,7 +46,7 @@ static unsigned long hugetlb_get_unmapped_area_topdown(struct file *file, unsigned long pgoff, unsigned long flags) { struct hstate *h = hstate_file(file); - struct vm_unmapped_area_info info; + struct vm_unmapped_area_info info = {}; info.flags = VM_UNMAPPED_AREA_TOPDOWN; info.length = len; @@ -89,7 +61,6 @@ static unsigned long hugetlb_get_unmapped_area_topdown(struct file *file, info.high_limit += TASK_SIZE_MAX - DEFAULT_MAP_WINDOW; info.align_mask = PAGE_MASK & ~huge_page_mask(h); - info.align_offset = 0; addr = vm_unmapped_area(&info); /* @@ -141,7 +112,7 @@ hugetlb_get_unmapped_area(struct file *file, unsigned long addr, } get_unmapped_area: - if (mm->get_unmapped_area == arch_get_unmapped_area) + if (!test_bit(MMF_TOPDOWN, &mm->flags)) return hugetlb_get_unmapped_area_bottomup(file, addr, len, pgoff, flags); else diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c index 6b43b6480354..eb503f53c319 100644 --- a/arch/x86/mm/init.c +++ b/arch/x86/mm/init.c @@ -7,6 +7,7 @@ #include <linux/swapops.h> #include <linux/kmemleak.h> #include <linux/sched/task.h> +#include <linux/execmem.h> #include <asm/set_memory.h> #include <asm/cpu_device_id.h> @@ -986,53 +987,6 @@ void __init free_initrd_mem(unsigned long start, unsigned long end) } #endif -/* - * Calculate the precise size of the DMA zone (first 16 MB of RAM), - * and pass it to the MM layer - to help it set zone watermarks more - * accurately. - * - * Done on 64-bit systems only for the time being, although 32-bit systems - * might benefit from this as well. - */ -void __init memblock_find_dma_reserve(void) -{ -#ifdef CONFIG_X86_64 - u64 nr_pages = 0, nr_free_pages = 0; - unsigned long start_pfn, end_pfn; - phys_addr_t start_addr, end_addr; - int i; - u64 u; - - /* - * Iterate over all memory ranges (free and reserved ones alike), - * to calculate the total number of pages in the first 16 MB of RAM: - */ - nr_pages = 0; - for_each_mem_pfn_range(i, MAX_NUMNODES, &start_pfn, &end_pfn, NULL) { - start_pfn = min(start_pfn, MAX_DMA_PFN); - end_pfn = min(end_pfn, MAX_DMA_PFN); - - nr_pages += end_pfn - start_pfn; - } - - /* - * Iterate over free memory ranges to calculate the number of free - * pages in the DMA zone, while not counting potential partial - * pages at the beginning or the end of the range: - */ - nr_free_pages = 0; - for_each_free_mem_range(u, NUMA_NO_NODE, MEMBLOCK_NONE, &start_addr, &end_addr, NULL) { - start_pfn = min_t(unsigned long, PFN_UP(start_addr), MAX_DMA_PFN); - end_pfn = min_t(unsigned long, PFN_DOWN(end_addr), MAX_DMA_PFN); - - if (start_pfn < end_pfn) - nr_free_pages += end_pfn - start_pfn; - } - - set_dma_reserve(nr_pages - nr_free_pages); -#endif -} - void __init zone_sizes_init(void) { unsigned long max_zone_pfns[MAX_NR_ZONES]; @@ -1095,3 +1049,31 @@ unsigned long arch_max_swapfile_size(void) return pages; } #endif + +#ifdef CONFIG_EXECMEM +static struct execmem_info execmem_info __ro_after_init; + +struct execmem_info __init *execmem_arch_setup(void) +{ + unsigned long start, offset = 0; + + if (kaslr_enabled()) + offset = get_random_u32_inclusive(1, 1024) * PAGE_SIZE; + + start = MODULES_VADDR + offset; + + execmem_info = (struct execmem_info){ + .ranges = { + [EXECMEM_DEFAULT] = { + .flags = EXECMEM_KASAN_SHADOW, + .start = start, + .end = MODULES_END, + .pgprot = PAGE_KERNEL, + .alignment = MODULE_ALIGN, + }, + }, + }; + + return &execmem_info; +} +#endif /* CONFIG_EXECMEM */ diff --git a/arch/x86/mm/mmap.c b/arch/x86/mm/mmap.c index c90c20904a60..a2cabb1c81e1 100644 --- a/arch/x86/mm/mmap.c +++ b/arch/x86/mm/mmap.c @@ -129,9 +129,9 @@ static void arch_pick_mmap_base(unsigned long *base, unsigned long *legacy_base, void arch_pick_mmap_layout(struct mm_struct *mm, struct rlimit *rlim_stack) { if (mmap_is_legacy()) - mm->get_unmapped_area = arch_get_unmapped_area; + clear_bit(MMF_TOPDOWN, &mm->flags); else - mm->get_unmapped_area = arch_get_unmapped_area_topdown; + set_bit(MMF_TOPDOWN, &mm->flags); arch_pick_mmap_base(&mm->mmap_base, &mm->mmap_legacy_base, arch_rnd(mmap64_rnd_bits), task_size_64bit(0), diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c index 65e9a6e391c0..ce84ba86e69e 100644 --- a/arch/x86/mm/numa.c +++ b/arch/x86/mm/numa.c @@ -929,6 +929,8 @@ int memory_add_physaddr_to_nid(u64 start) } EXPORT_SYMBOL_GPL(memory_add_physaddr_to_nid); +#endif + static int __init cmp_memblk(const void *a, const void *b) { const struct numa_memblk *ma = *(const struct numa_memblk **)a; @@ -1001,5 +1003,3 @@ int __init numa_fill_memblks(u64 start, u64 end) } return 0; } - -#endif diff --git a/arch/x86/mm/numa_32.c b/arch/x86/mm/numa_32.c index 025fd7ea5d69..65fda406e6f2 100644 --- a/arch/x86/mm/numa_32.c +++ b/arch/x86/mm/numa_32.c @@ -24,6 +24,7 @@ #include <linux/memblock.h> #include <linux/init.h> +#include <linux/vmalloc.h> #include <asm/pgtable_areas.h> #include "numa_internal.h" diff --git a/arch/x86/mm/pat/memtype.c b/arch/x86/mm/pat/memtype.c index 36b603d0cdde..bdc2a240c2aa 100644 --- a/arch/x86/mm/pat/memtype.c +++ b/arch/x86/mm/pat/memtype.c @@ -39,6 +39,7 @@ #include <linux/pfn_t.h> #include <linux/slab.h> #include <linux/mm.h> +#include <linux/highmem.h> #include <linux/fs.h> #include <linux/rbtree.h> @@ -947,6 +948,29 @@ static void free_pfn_range(u64 paddr, unsigned long size) memtype_free(paddr, paddr + size); } +static int follow_phys(struct vm_area_struct *vma, unsigned long *prot, + resource_size_t *phys) +{ + pte_t *ptep, pte; + spinlock_t *ptl; + + if (follow_pte(vma, vma->vm_start, &ptep, &ptl)) + return -EINVAL; + + pte = ptep_get(ptep); + + /* Never return PFNs of anon folios in COW mappings. */ + if (vm_normal_folio(vma, vma->vm_start, pte)) { + pte_unmap_unlock(ptep, ptl); + return -EINVAL; + } + + *prot = pgprot_val(pte_pgprot(pte)); + *phys = (resource_size_t)pte_pfn(pte) << PAGE_SHIFT; + pte_unmap_unlock(ptep, ptl); + return 0; +} + static int get_pat_info(struct vm_area_struct *vma, resource_size_t *paddr, pgprot_t *pgprot) { @@ -964,7 +988,7 @@ static int get_pat_info(struct vm_area_struct *vma, resource_size_t *paddr, * detect the PFN. If we need the cachemode as well, we're out of luck * for now and have to fail fork(). */ - if (!follow_phys(vma, vma->vm_start, 0, &prot, paddr)) { + if (!follow_phys(vma, &prot, paddr)) { if (pgprot) *pgprot = __pgprot(prot); return 0; diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c index d007591b8059..93e54ba91fbf 100644 --- a/arch/x86/mm/pgtable.c +++ b/arch/x86/mm/pgtable.c @@ -631,6 +631,8 @@ int pmdp_clear_flush_young(struct vm_area_struct *vma, pmd_t pmdp_invalidate_ad(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp) { + VM_WARN_ON_ONCE(!pmd_present(*pmdp)); + /* * No flush is necessary. Once an invalid PTE is established, the PTE's * access and dirty bits cannot be updated. @@ -731,7 +733,7 @@ int pud_set_huge(pud_t *pud, phys_addr_t addr, pgprot_t prot) return 0; /* Bail out if we are we on a populated non-leaf entry: */ - if (pud_present(*pud) && !pud_huge(*pud)) + if (pud_present(*pud) && !pud_leaf(*pud)) return 0; set_pte((pte_t *)pud, pfn_pte( @@ -760,7 +762,7 @@ int pmd_set_huge(pmd_t *pmd, phys_addr_t addr, pgprot_t prot) } /* Bail out if we are we on a populated non-leaf entry: */ - if (pmd_present(*pmd) && !pmd_huge(*pmd)) + if (pmd_present(*pmd) && !pmd_leaf(*pmd)) return 0; set_pte((pte_t *)pmd, pfn_pte( diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c index 59cbc94b6e69..5159c7a22922 100644 --- a/arch/x86/net/bpf_jit_comp.c +++ b/arch/x86/net/bpf_jit_comp.c @@ -816,9 +816,10 @@ done: static void emit_mov_imm64(u8 **pprog, u32 dst_reg, const u32 imm32_hi, const u32 imm32_lo) { + u64 imm64 = ((u64)imm32_hi << 32) | (u32)imm32_lo; u8 *prog = *pprog; - if (is_uimm32(((u64)imm32_hi << 32) | (u32)imm32_lo)) { + if (is_uimm32(imm64)) { /* * For emitting plain u32, where sign bit must not be * propagated LLVM tends to load imm64 over mov32 @@ -826,6 +827,8 @@ static void emit_mov_imm64(u8 **pprog, u32 dst_reg, * 'mov %eax, imm32' instead. */ emit_mov_imm32(&prog, false, dst_reg, imm32_lo); + } else if (is_simm32(imm64)) { + emit_mov_imm32(&prog, true, dst_reg, imm32_lo); } else { /* movabsq rax, imm64 */ EMIT2(add_1mod(0x48, dst_reg), add_1reg(0xB8, dst_reg)); @@ -1169,6 +1172,54 @@ static int emit_atomic(u8 **pprog, u8 atomic_op, return 0; } +static int emit_atomic_index(u8 **pprog, u8 atomic_op, u32 size, + u32 dst_reg, u32 src_reg, u32 index_reg, int off) +{ + u8 *prog = *pprog; + + EMIT1(0xF0); /* lock prefix */ + switch (size) { + case BPF_W: + EMIT1(add_3mod(0x40, dst_reg, src_reg, index_reg)); + break; + case BPF_DW: + EMIT1(add_3mod(0x48, dst_reg, src_reg, index_reg)); + break; + default: + pr_err("bpf_jit: 1 and 2 byte atomics are not supported\n"); + return -EFAULT; + } + + /* emit opcode */ + switch (atomic_op) { + case BPF_ADD: + case BPF_AND: + case BPF_OR: + case BPF_XOR: + /* lock *(u32/u64*)(dst_reg + idx_reg + off) <op>= src_reg */ + EMIT1(simple_alu_opcodes[atomic_op]); + break; + case BPF_ADD | BPF_FETCH: + /* src_reg = atomic_fetch_add(dst_reg + idx_reg + off, src_reg); */ + EMIT2(0x0F, 0xC1); + break; + case BPF_XCHG: + /* src_reg = atomic_xchg(dst_reg + idx_reg + off, src_reg); */ + EMIT1(0x87); + break; + case BPF_CMPXCHG: + /* r0 = atomic_cmpxchg(dst_reg + idx_reg + off, r0, src_reg); */ + EMIT2(0x0F, 0xB1); + break; + default: + pr_err("bpf_jit: unknown atomic opcode %02x\n", atomic_op); + return -EFAULT; + } + emit_insn_suffix_SIB(&prog, dst_reg, src_reg, index_reg, off); + *pprog = prog; + return 0; +} + #define DONT_CLEAR 1 bool ex_handler_bpf(const struct exception_table_entry *x, struct pt_regs *regs) @@ -1351,8 +1402,7 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, u8 *rw_image break; case BPF_ALU64 | BPF_MOV | BPF_X: - if (insn->off == BPF_ADDR_SPACE_CAST && - insn->imm == 1U << 16) { + if (insn_is_cast_user(insn)) { if (dst_reg != src_reg) /* 32-bit mov */ emit_mov_reg(&prog, false, dst_reg, src_reg); @@ -1383,6 +1433,16 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, u8 *rw_image maybe_emit_mod(&prog, AUX_REG, dst_reg, true); EMIT3(0x0F, 0x44, add_2reg(0xC0, AUX_REG, dst_reg)); break; + } else if (insn_is_mov_percpu_addr(insn)) { + /* mov <dst>, <src> (if necessary) */ + EMIT_mov(dst_reg, src_reg); +#ifdef CONFIG_SMP + /* add <dst>, gs:[<off>] */ + EMIT2(0x65, add_1mod(0x48, dst_reg)); + EMIT3(0x03, add_2reg(0x04, 0, dst_reg), 0x25); + EMIT((u32)(unsigned long)&this_cpu_off, 4); +#endif + break; } fallthrough; case BPF_ALU | BPF_MOV | BPF_X: @@ -1963,6 +2023,15 @@ populate_extable: return err; break; + case BPF_STX | BPF_PROBE_ATOMIC | BPF_W: + case BPF_STX | BPF_PROBE_ATOMIC | BPF_DW: + start_of_ldx = prog; + err = emit_atomic_index(&prog, insn->imm, BPF_SIZE(insn->code), + dst_reg, src_reg, X86_REG_R12, insn->off); + if (err) + return err; + goto populate_extable; + /* call */ case BPF_JMP | BPF_CALL: { u8 *ip = image + addrs[i - 1]; @@ -2994,12 +3063,9 @@ void arch_free_bpf_trampoline(void *image, unsigned int size) bpf_prog_pack_free(image, size); } -void arch_protect_bpf_trampoline(void *image, unsigned int size) -{ -} - -void arch_unprotect_bpf_trampoline(void *image, unsigned int size) +int arch_protect_bpf_trampoline(void *image, unsigned int size) { + return 0; } int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *image_end, @@ -3359,6 +3425,11 @@ bool bpf_jit_supports_subprog_tailcalls(void) return true; } +bool bpf_jit_supports_percpu_insn(void) +{ + return true; +} + void bpf_jit_free(struct bpf_prog *prog) { if (prog->jited) { @@ -3462,6 +3533,21 @@ bool bpf_jit_supports_arena(void) return true; } +bool bpf_jit_supports_insn(struct bpf_insn *insn, bool in_arena) +{ + if (!in_arena) + return true; + switch (insn->code) { + case BPF_STX | BPF_ATOMIC | BPF_W: + case BPF_STX | BPF_ATOMIC | BPF_DW: + if (insn->imm == (BPF_AND | BPF_FETCH) || + insn->imm == (BPF_OR | BPF_FETCH) || + insn->imm == (BPF_XOR | BPF_FETCH)) + return false; + } + return true; +} + bool bpf_jit_supports_ptr_xchg(void) { return true; diff --git a/arch/x86/net/bpf_jit_comp32.c b/arch/x86/net/bpf_jit_comp32.c index c10083a8e68e..de0f9e5f9f73 100644 --- a/arch/x86/net/bpf_jit_comp32.c +++ b/arch/x86/net/bpf_jit_comp32.c @@ -2600,8 +2600,7 @@ out_image: if (bpf_jit_enable > 1) bpf_jit_dump(prog->len, proglen, pass + 1, image); - if (image) { - bpf_jit_binary_lock_ro(header); + if (image && !bpf_jit_binary_lock_ro(header)) { prog->bpf_func = (void *)image; prog->jited = 1; prog->jited_len = proglen; diff --git a/arch/x86/pci/mmconfig-shared.c b/arch/x86/pci/mmconfig-shared.c index 0cc9520666ef..39255f0eb14d 100644 --- a/arch/x86/pci/mmconfig-shared.c +++ b/arch/x86/pci/mmconfig-shared.c @@ -518,7 +518,34 @@ static bool __ref pci_mmcfg_reserved(struct device *dev, { struct resource *conflict; - if (!early && !acpi_disabled) { + if (early) { + + /* + * Don't try to do this check unless configuration type 1 + * is available. How about type 2? + */ + + /* + * 946f2ee5c731 ("Check that MCFG points to an e820 + * reserved area") added this E820 check in 2006 to work + * around BIOS defects. + * + * Per PCI Firmware r3.3, sec 4.1.2, ECAM space must be + * reserved by a PNP0C02 resource, but it need not be + * mentioned in E820. Before the ACPI interpreter is + * available, we can't check for PNP0C02 resources, so + * there's no reliable way to verify the region in this + * early check. Keep it only for the old machines that + * motivated 946f2ee5c731. + */ + if (dmi_get_bios_year() < 2016 && raw_pci_ops) + return is_mmconf_reserved(e820__mapped_all, cfg, dev, + "E820 entry"); + + return true; + } + + if (!acpi_disabled) { if (is_mmconf_reserved(is_acpi_reserved, cfg, dev, "ACPI motherboard resource")) return true; @@ -551,16 +578,7 @@ static bool __ref pci_mmcfg_reserved(struct device *dev, * For MCFG information constructed from hotpluggable host bridge's * _CBA method, just assume it's reserved. */ - if (pci_mmcfg_running_state) - return true; - - /* Don't try to do this check unless configuration - type 1 is available. how about type 2 ?*/ - if (raw_pci_ops) - return is_mmconf_reserved(e820__mapped_all, cfg, dev, - "E820 entry"); - - return false; + return pci_mmcfg_running_state; } static void __init pci_mmcfg_reject_broken(int early) diff --git a/arch/x86/pci/olpc.c b/arch/x86/pci/olpc.c index f3aab76e357a..4b18c6404363 100644 --- a/arch/x86/pci/olpc.c +++ b/arch/x86/pci/olpc.c @@ -154,9 +154,6 @@ static const uint32_t ehci_hdr[] = { /* dev f function 4 - devfn = 7d */ 0x0, 0x40, 0x0, 0x40a, /* CapPtr INT-D, IRQA */ 0xc8020001, 0x0, 0x0, 0x0, /* Capabilities - 40 is R/O, 44 is mask 8103 (power control) */ -#if 0 - 0x1, 0x40080000, 0x0, 0x0, /* EECP - see EHCI spec section 2.1.7 */ -#endif 0x01000001, 0x0, 0x0, 0x0, /* EECP - see EHCI spec section 2.1.7 */ 0x2020, 0x0, 0x0, 0x0, /* (EHCI page 8) 60 SBRN (R/O), 61 FLADJ (R/W), PORTWAKECAP */ diff --git a/arch/x86/purgatory/Makefile b/arch/x86/purgatory/Makefile index a18591f6e6d9..ebdfd7b84feb 100644 --- a/arch/x86/purgatory/Makefile +++ b/arch/x86/purgatory/Makefile @@ -1,5 +1,4 @@ # SPDX-License-Identifier: GPL-2.0 -OBJECT_FILES_NON_STANDARD := y purgatory-y := purgatory.o stack.o setup-x86_$(BITS).o sha256.o entry64.o string.o @@ -30,14 +29,6 @@ LDFLAGS_purgatory.ro := -r $(PURGATORY_LDFLAGS) LDFLAGS_purgatory.chk := $(PURGATORY_LDFLAGS) targets += purgatory.ro purgatory.chk -# Sanitizer, etc. runtimes are unavailable and cannot be linked here. -GCOV_PROFILE := n -KASAN_SANITIZE := n -UBSAN_SANITIZE := n -KCSAN_SANITIZE := n -KMSAN_SANITIZE := n -KCOV_INSTRUMENT := n - # These are adjustments to the compiler flags used for objects that # make up the standalone purgatory.ro diff --git a/arch/x86/realmode/rm/Makefile b/arch/x86/realmode/rm/Makefile index f614009d3e4e..a0fb39abc5c8 100644 --- a/arch/x86/realmode/rm/Makefile +++ b/arch/x86/realmode/rm/Makefile @@ -7,15 +7,6 @@ # # -# Sanitizer runtimes are unavailable and cannot be linked here. -KASAN_SANITIZE := n -KCSAN_SANITIZE := n -KMSAN_SANITIZE := n -OBJECT_FILES_NON_STANDARD := y - -# Prevents link failures: __sanitizer_cov_trace_pc() is not linked in. -KCOV_INSTRUMENT := n - always-y := realmode.bin realmode.relocs wakeup-objs := wakeup_asm.o wakemain.o video-mode.o @@ -76,5 +67,3 @@ KBUILD_CFLAGS := $(REALMODE_CFLAGS) -D_SETUP -D_WAKEUP \ -I$(srctree)/arch/x86/boot KBUILD_AFLAGS := $(KBUILD_CFLAGS) -D__ASSEMBLY__ KBUILD_CFLAGS += -fno-asynchronous-unwind-tables -GCOV_PROFILE := n -UBSAN_SANITIZE := n diff --git a/arch/x86/tools/gen-insn-attr-x86.awk b/arch/x86/tools/gen-insn-attr-x86.awk index af38469afd14..5770c8097f32 100644 --- a/arch/x86/tools/gen-insn-attr-x86.awk +++ b/arch/x86/tools/gen-insn-attr-x86.awk @@ -64,7 +64,9 @@ BEGIN { modrm_expr = "^([CDEGMNPQRSUVW/][a-z]+|NTA|T[012])" force64_expr = "\\([df]64\\)" - rex_expr = "^REX(\\.[XRWB]+)*" + rex_expr = "^((REX(\\.[XRWB]+)+)|(REX$))" + rex2_expr = "\\(REX2\\)" + no_rex2_expr = "\\(!REX2\\)" fpu_expr = "^ESC" # TODO lprefix1_expr = "\\((66|!F3)\\)" @@ -81,6 +83,8 @@ BEGIN { vexonly_expr = "\\(v\\)" # All opcodes with (ev) superscript supports *only* EVEX prefix evexonly_expr = "\\(ev\\)" + # (es) is the same as (ev) but also "SCALABLE" i.e. W and pp determine operand size + evex_scalable_expr = "\\(es\\)" prefix_expr = "\\(Prefix\\)" prefix_num["Operand-Size"] = "INAT_PFX_OPNDSZ" @@ -99,6 +103,7 @@ BEGIN { prefix_num["VEX+1byte"] = "INAT_PFX_VEX2" prefix_num["VEX+2byte"] = "INAT_PFX_VEX3" prefix_num["EVEX"] = "INAT_PFX_EVEX" + prefix_num["REX2"] = "INAT_PFX_REX2" clear_vars() } @@ -314,6 +319,10 @@ function convert_operands(count,opnd, i,j,imm,mod) if (match(ext, force64_expr)) flags = add_flags(flags, "INAT_FORCE64") + # check REX2 not allowed + if (match(ext, no_rex2_expr)) + flags = add_flags(flags, "INAT_NO_REX2") + # check REX prefix if (match(opcode, rex_expr)) flags = add_flags(flags, "INAT_MAKE_PREFIX(INAT_PFX_REX)") @@ -325,6 +334,8 @@ function convert_operands(count,opnd, i,j,imm,mod) # check VEX codes if (match(ext, evexonly_expr)) flags = add_flags(flags, "INAT_VEXOK | INAT_EVEXONLY") + else if (match(ext, evex_scalable_expr)) + flags = add_flags(flags, "INAT_VEXOK | INAT_EVEXONLY | INAT_EVEX_SCALABLE") else if (match(ext, vexonly_expr)) flags = add_flags(flags, "INAT_VEXOK | INAT_VEXONLY") else if (match(ext, vexok_expr) || match(opcode, vexok_opcode_expr)) @@ -351,6 +362,8 @@ function convert_operands(count,opnd, i,j,imm,mod) lptable3[idx] = add_flags(lptable3[idx],flags) variant = "INAT_VARIANT" } + if (match(ext, rex2_expr)) + table[idx] = add_flags(table[idx], "INAT_REX2_VARIANT") if (!match(ext, lprefix_expr)){ table[idx] = add_flags(table[idx],flags) } diff --git a/arch/x86/um/asm/ptrace.h b/arch/x86/um/asm/ptrace.h index 83822fd42204..2fef3da55533 100644 --- a/arch/x86/um/asm/ptrace.h +++ b/arch/x86/um/asm/ptrace.h @@ -54,6 +54,8 @@ extern int ptrace_get_thread_area(struct task_struct *child, int idx, extern int ptrace_set_thread_area(struct task_struct *child, int idx, struct user_desc __user *user_desc); +extern int arch_switch_tls(struct task_struct *to); + #else #define PT_REGS_R8(r) UPT_R8(&(r)->regs) @@ -83,5 +85,9 @@ extern long arch_prctl(struct task_struct *task, int option, unsigned long __user *addr); #endif + #define user_stack_pointer(regs) PT_REGS_SP(regs) + +extern void arch_switch_to(struct task_struct *to); + #endif /* __UM_X86_PTRACE_H */ diff --git a/arch/x86/um/bugs_32.c b/arch/x86/um/bugs_32.c index 33daff4dade4..d29929efcc07 100644 --- a/arch/x86/um/bugs_32.c +++ b/arch/x86/um/bugs_32.c @@ -3,6 +3,7 @@ * Licensed under the GPL */ +#include <arch.h> #include <signal.h> #include <kern_util.h> #include <longjmp.h> diff --git a/arch/x86/um/bugs_64.c b/arch/x86/um/bugs_64.c index 8cc8256c698d..b01295e8a676 100644 --- a/arch/x86/um/bugs_64.c +++ b/arch/x86/um/bugs_64.c @@ -4,6 +4,7 @@ * Licensed under the GPL */ +#include <arch.h> #include <sysdep/ptrace.h> void arch_check_bugs(void) diff --git a/arch/x86/um/elfcore.c b/arch/x86/um/elfcore.c index 650cdbbdaf45..ef50662fc40d 100644 --- a/arch/x86/um/elfcore.c +++ b/arch/x86/um/elfcore.c @@ -1,5 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 #include <linux/elf.h> +#include <linux/elfcore.h> #include <linux/coredump.h> #include <linux/fs.h> #include <linux/mm.h> diff --git a/arch/x86/um/fault.c b/arch/x86/um/fault.c index 84ac7f7b0257..0dde4d613a87 100644 --- a/arch/x86/um/fault.c +++ b/arch/x86/um/fault.c @@ -3,6 +3,7 @@ * Licensed under the GPL */ +#include <arch.h> #include <sysdep/ptrace.h> /* These two are from asm-um/uaccess.h and linux/module.h, check them. */ diff --git a/arch/x86/um/os-Linux/mcontext.c b/arch/x86/um/os-Linux/mcontext.c index 49c3744cac37..e80ab7d28117 100644 --- a/arch/x86/um/os-Linux/mcontext.c +++ b/arch/x86/um/os-Linux/mcontext.c @@ -3,6 +3,7 @@ #define __FRAME_OFFSETS #include <asm/ptrace.h> #include <sysdep/ptrace.h> +#include <sysdep/mcontext.h> void get_regs_from_mc(struct uml_pt_regs *regs, mcontext_t *mc) { diff --git a/arch/x86/um/os-Linux/registers.c b/arch/x86/um/os-Linux/registers.c index df8f4b4bf98b..f3638dd09cec 100644 --- a/arch/x86/um/os-Linux/registers.c +++ b/arch/x86/um/os-Linux/registers.c @@ -17,7 +17,7 @@ #include <linux/elf.h> #include <registers.h> -int have_xstate_support; +static int have_xstate_support; int save_i387_registers(int pid, unsigned long *fp_regs) { diff --git a/arch/x86/um/os-Linux/tls.c b/arch/x86/um/os-Linux/tls.c index 3e1b1bf6acbc..eed9efe29ade 100644 --- a/arch/x86/um/os-Linux/tls.c +++ b/arch/x86/um/os-Linux/tls.c @@ -6,6 +6,7 @@ #include <sys/syscall.h> #include <unistd.h> +#include <os.h> #include <sysdep/tls.h> #ifndef PTRACE_GET_THREAD_AREA diff --git a/arch/x86/um/ptrace_32.c b/arch/x86/um/ptrace_32.c index 7f1abde2c84b..b0a71c6cdc6e 100644 --- a/arch/x86/um/ptrace_32.c +++ b/arch/x86/um/ptrace_32.c @@ -10,8 +10,6 @@ #include <registers.h> #include <skas.h> -extern int arch_switch_tls(struct task_struct *to); - void arch_switch_to(struct task_struct *to) { int err = arch_switch_tls(to); diff --git a/arch/x86/um/shared/sysdep/archsetjmp.h b/arch/x86/um/shared/sysdep/archsetjmp.h index 166cedbab926..8c81d1a604a9 100644 --- a/arch/x86/um/shared/sysdep/archsetjmp.h +++ b/arch/x86/um/shared/sysdep/archsetjmp.h @@ -1,6 +1,13 @@ /* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __X86_UM_SYSDEP_ARCHSETJMP_H +#define __X86_UM_SYSDEP_ARCHSETJMP_H + #ifdef __i386__ #include "archsetjmp_32.h" #else #include "archsetjmp_64.h" #endif + +unsigned long get_thread_reg(int reg, jmp_buf *buf); + +#endif /* __X86_UM_SYSDEP_ARCHSETJMP_H */ diff --git a/arch/x86/um/shared/sysdep/kernel-offsets.h b/arch/x86/um/shared/sysdep/kernel-offsets.h index a004bffb7b8d..48de3a71f845 100644 --- a/arch/x86/um/shared/sysdep/kernel-offsets.h +++ b/arch/x86/um/shared/sysdep/kernel-offsets.h @@ -6,6 +6,9 @@ #include <linux/kbuild.h> #include <asm/mman.h> +/* workaround for a warning with -Wmissing-prototypes */ +void foo(void); + void foo(void) { #include <common-offsets.h> diff --git a/arch/x86/um/signal.c b/arch/x86/um/signal.c index 263e1d08f216..2cc8c2309022 100644 --- a/arch/x86/um/signal.c +++ b/arch/x86/um/signal.c @@ -8,6 +8,7 @@ #include <linux/personality.h> #include <linux/ptrace.h> #include <linux/kernel.h> +#include <linux/syscalls.h> #include <asm/unistd.h> #include <linux/uaccess.h> #include <asm/ucontext.h> @@ -155,7 +156,7 @@ static int copy_sc_from_user(struct pt_regs *regs, struct sigcontext __user *from) { struct sigcontext sc; - int err, pid; + int err; /* Always make any pending restarted system calls return -EINTR */ current->restart_block.fn = do_no_restart_syscall; @@ -201,10 +202,10 @@ static int copy_sc_from_user(struct pt_regs *regs, #undef GETREG - pid = userspace_pid[current_thread_info()->cpu]; #ifdef CONFIG_X86_32 if (have_fpx_regs) { struct user_fxsr_struct fpx; + int pid = userspace_pid[current_thread_info()->cpu]; err = copy_from_user(&fpx, &((struct _fpstate __user *)sc.fpstate)->_fxsr_env[0], @@ -240,7 +241,7 @@ static int copy_sc_to_user(struct sigcontext __user *to, { struct sigcontext sc; struct faultinfo * fi = ¤t->thread.arch.faultinfo; - int err, pid; + int err; memset(&sc, 0, sizeof(struct sigcontext)); #define PUTREG(regno, regname) sc.regname = regs->regs.gp[HOST_##regno] @@ -288,10 +289,9 @@ static int copy_sc_to_user(struct sigcontext __user *to, if (err) return 1; - pid = userspace_pid[current_thread_info()->cpu]; - #ifdef CONFIG_X86_32 if (have_fpx_regs) { + int pid = userspace_pid[current_thread_info()->cpu]; struct user_fxsr_struct fpx; err = save_fpx_registers(pid, (unsigned long *) &fpx); @@ -450,7 +450,7 @@ int setup_signal_stack_si(unsigned long stack_top, struct ksignal *ksig, return 0; } -long sys_sigreturn(void) +SYSCALL_DEFINE0(sigreturn) { unsigned long sp = PT_REGS_SP(¤t->thread.regs); struct sigframe __user *frame = (struct sigframe __user *)(sp - 8); @@ -557,7 +557,7 @@ int setup_signal_stack_si(unsigned long stack_top, struct ksignal *ksig, } #endif -long sys_rt_sigreturn(void) +SYSCALL_DEFINE0(rt_sigreturn) { unsigned long sp = PT_REGS_SP(¤t->thread.regs); struct rt_sigframe __user *frame = diff --git a/arch/x86/um/tls_32.c b/arch/x86/um/tls_32.c index 66162eafd8e8..d301deee041f 100644 --- a/arch/x86/um/tls_32.c +++ b/arch/x86/um/tls_32.c @@ -20,7 +20,7 @@ static int host_supports_tls = -1; int host_gdt_entry_tls_min; -int do_set_thread_area(struct user_desc *info) +static int do_set_thread_area(struct user_desc *info) { int ret; u32 cpu; @@ -36,22 +36,6 @@ int do_set_thread_area(struct user_desc *info) return ret; } -int do_get_thread_area(struct user_desc *info) -{ - int ret; - u32 cpu; - - cpu = get_cpu(); - ret = os_get_thread_area(info, userspace_pid[cpu]); - put_cpu(); - - if (ret) - printk(KERN_ERR "PTRACE_GET_THREAD_AREA failed, err = %d, " - "index = %d\n", ret, info->entry_number); - - return ret; -} - /* * sys_get_thread_area: get a yet unused TLS descriptor index. * XXX: Consider leaving one free slot for glibc usage at first place. This must @@ -231,7 +215,6 @@ out: return ret; } -/* XXX: use do_get_thread_area to read the host value? I'm not at all sure! */ static int get_tls_entry(struct task_struct *task, struct user_desc *info, int idx) { diff --git a/arch/x86/um/user-offsets.c b/arch/x86/um/user-offsets.c index e54a9814ccf1..1c77d9946199 100644 --- a/arch/x86/um/user-offsets.c +++ b/arch/x86/um/user-offsets.c @@ -14,6 +14,9 @@ COMMENT(#val " / sizeof(unsigned long)"); \ DEFINE(sym, val / sizeof(unsigned long)) +/* workaround for a warning with -Wmissing-prototypes */ +void foo(void); + void foo(void) { #ifdef __i386__ diff --git a/arch/x86/um/vdso/Makefile b/arch/x86/um/vdso/Makefile index b86d634730b2..6a77ea6434ff 100644 --- a/arch/x86/um/vdso/Makefile +++ b/arch/x86/um/vdso/Makefile @@ -3,12 +3,6 @@ # Building vDSO images for x86. # -# do not instrument on vdso because KASAN is not compatible with user mode -KASAN_SANITIZE := n - -# Prevents link failures: __sanitizer_cov_trace_pc() is not linked in. -KCOV_INSTRUMENT := n - VDSO64-y := y vdso-install-$(VDSO64-y) += vdso.so @@ -63,7 +57,6 @@ quiet_cmd_vdso = VDSO $@ cmd_vdso = $(CC) -nostdlib -o $@ \ $(CC_FLAGS_LTO) $(VDSO_LDFLAGS) $(VDSO_LDFLAGS_$(filter %.lds,$(^F))) \ -Wl,-T,$(filter %.lds,$^) $(filter %.o,$^) && \ - sh $(srctree)/$(src)/checkundef.sh '$(NM)' '$@' + sh $(src)/checkundef.sh '$(NM)' '$@' VDSO_LDFLAGS = -fPIC -shared -Wl,--hash-style=sysv -z noexecstack -GCOV_PROFILE := n diff --git a/arch/x86/um/vdso/um_vdso.c b/arch/x86/um/vdso/um_vdso.c index ff0f3b4b6c45..cbae2584124f 100644 --- a/arch/x86/um/vdso/um_vdso.c +++ b/arch/x86/um/vdso/um_vdso.c @@ -13,6 +13,12 @@ #include <linux/getcpu.h> #include <asm/unistd.h> +/* workaround for -Wmissing-prototypes warnings */ +int __vdso_clock_gettime(clockid_t clock, struct __kernel_old_timespec *ts); +int __vdso_gettimeofday(struct __kernel_old_timeval *tv, struct timezone *tz); +__kernel_old_time_t __vdso_time(__kernel_old_time_t *t); +long __vdso_getcpu(unsigned int *cpu, unsigned int *node, struct getcpu_cache *unused); + int __vdso_clock_gettime(clockid_t clock, struct __kernel_old_timespec *ts) { long ret; @@ -54,7 +60,7 @@ __kernel_old_time_t __vdso_time(__kernel_old_time_t *t) __kernel_old_time_t time(__kernel_old_time_t *t) __attribute__((weak, alias("__vdso_time"))); long -__vdso_getcpu(unsigned *cpu, unsigned *node, struct getcpu_cache *unused) +__vdso_getcpu(unsigned int *cpu, unsigned int *node, struct getcpu_cache *unused) { /* * UML does not support SMP, we can cheat here. :) @@ -68,5 +74,5 @@ __vdso_getcpu(unsigned *cpu, unsigned *node, struct getcpu_cache *unused) return 0; } -long getcpu(unsigned *cpu, unsigned *node, struct getcpu_cache *tcache) +long getcpu(unsigned int *cpu, unsigned int *node, struct getcpu_cache *tcache) __attribute__((weak, alias("__vdso_getcpu"))); diff --git a/arch/x86/video/Makefile b/arch/x86/video/Makefile index 5ebe48752ffc..dcfbe7a5912c 100644 --- a/arch/x86/video/Makefile +++ b/arch/x86/video/Makefile @@ -1,2 +1,3 @@ # SPDX-License-Identifier: GPL-2.0-only -obj-$(CONFIG_FB_CORE) += fbdev.o + +obj-y += video-common.o diff --git a/arch/x86/video/fbdev.c b/arch/x86/video/video-common.c index 1dd6528cc947..81fc97a2a837 100644 --- a/arch/x86/video/fbdev.c +++ b/arch/x86/video/video-common.c @@ -7,11 +7,11 @@ * */ -#include <linux/fb.h> #include <linux/module.h> #include <linux/pci.h> #include <linux/vgaarb.h> -#include <asm/fb.h> + +#include <asm/video.h> pgprot_t pgprot_framebuffer(pgprot_t prot, unsigned long vm_start, unsigned long vm_end, @@ -25,20 +25,17 @@ pgprot_t pgprot_framebuffer(pgprot_t prot, } EXPORT_SYMBOL(pgprot_framebuffer); -int fb_is_primary_device(struct fb_info *info) +bool video_is_primary_device(struct device *dev) { - struct device *device = info->device; - struct pci_dev *pci_dev; + struct pci_dev *pdev; - if (!device || !dev_is_pci(device)) - return 0; + if (!dev_is_pci(dev)) + return false; - pci_dev = to_pci_dev(device); + pdev = to_pci_dev(dev); - if (pci_dev == vga_default_device()) - return 1; - return 0; + return (pdev == vga_default_device()); } -EXPORT_SYMBOL(fb_is_primary_device); +EXPORT_SYMBOL(video_is_primary_device); MODULE_LICENSE("GPL"); diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c index 5f3a69f6ec34..0305485edcd3 100644 --- a/arch/x86/xen/enlighten.c +++ b/arch/x86/xen/enlighten.c @@ -379,3 +379,36 @@ void __init xen_add_extra_mem(unsigned long start_pfn, unsigned long n_pfns) memblock_reserve(PFN_PHYS(start_pfn), PFN_PHYS(n_pfns)); } + +#ifdef CONFIG_XEN_UNPOPULATED_ALLOC +int __init arch_xen_unpopulated_init(struct resource **res) +{ + unsigned int i; + + if (!xen_domain()) + return -ENODEV; + + /* Must be set strictly before calling xen_free_unpopulated_pages(). */ + *res = &iomem_resource; + + /* + * Initialize with pages from the extra memory regions (see + * arch/x86/xen/setup.c). + */ + for (i = 0; i < XEN_EXTRA_MEM_MAX_REGIONS; i++) { + unsigned int j; + + for (j = 0; j < xen_extra_mem[i].n_pfns; j++) { + struct page *pg = + pfn_to_page(xen_extra_mem[i].start_pfn + j); + + xen_free_unpopulated_pages(1, &pg); + } + + /* Zero so region is not also added to the balloon driver. */ + xen_extra_mem[i].n_pfns = 0; + } + + return 0; +} +#endif diff --git a/arch/x86/xen/p2m.c b/arch/x86/xen/p2m.c index 9bdc3b656b2c..99918beccd80 100644 --- a/arch/x86/xen/p2m.c +++ b/arch/x86/xen/p2m.c @@ -555,7 +555,6 @@ int xen_alloc_p2m_entry(unsigned long pfn) /* Separately check the mid mfn level */ unsigned long missing_mfn; unsigned long mid_mfn_mfn; - unsigned long old_mfn; mid_mfn = alloc_p2m_page(); if (!mid_mfn) @@ -565,12 +564,12 @@ int xen_alloc_p2m_entry(unsigned long pfn) missing_mfn = virt_to_mfn(p2m_mid_missing_mfn); mid_mfn_mfn = virt_to_mfn(mid_mfn); - old_mfn = cmpxchg(top_mfn_p, missing_mfn, mid_mfn_mfn); - if (old_mfn != missing_mfn) { - free_p2m_page(mid_mfn); - mid_mfn = mfn_to_virt(old_mfn); - } else { + /* try_cmpxchg() updates missing_mfn on failure. */ + if (try_cmpxchg(top_mfn_p, &missing_mfn, mid_mfn_mfn)) { p2m_top_mfn_p[topidx] = mid_mfn; + } else { + free_p2m_page(mid_mfn); + mid_mfn = mfn_to_virt(missing_mfn); } } } else { |