diff options
Diffstat (limited to 'arch/x86/kvm')
39 files changed, 4610 insertions, 2627 deletions
diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig index 840e12583b85..991019d5eee1 100644 --- a/arch/x86/kvm/Kconfig +++ b/arch/x86/kvm/Kconfig @@ -60,13 +60,11 @@ config KVM If unsure, say N. config KVM_INTEL - tristate "KVM for Intel processors support" - depends on KVM - # for perf_guest_get_msrs(): - depends on CPU_SUP_INTEL + tristate "KVM for Intel (and compatible) processors support" + depends on KVM && IA32_FEAT_CTL ---help--- - Provides support for KVM on Intel processors equipped with the VT - extensions. + Provides support for KVM on processors equipped with Intel's VT + extensions, a.k.a. Virtual Machine Extensions (VMX). To compile this as a module, choose M here: the module will be called kvm-intel. diff --git a/arch/x86/kvm/Makefile b/arch/x86/kvm/Makefile index 31ecf7a76d5a..b19ef421084d 100644 --- a/arch/x86/kvm/Makefile +++ b/arch/x86/kvm/Makefile @@ -8,9 +8,9 @@ kvm-y += $(KVM)/kvm_main.o $(KVM)/coalesced_mmio.o \ $(KVM)/eventfd.o $(KVM)/irqchip.o $(KVM)/vfio.o kvm-$(CONFIG_KVM_ASYNC_PF) += $(KVM)/async_pf.o -kvm-y += x86.o mmu.o emulate.o i8259.o irq.o lapic.o \ +kvm-y += x86.o emulate.o i8259.o irq.o lapic.o \ i8254.o ioapic.o irq_comm.o cpuid.o pmu.o mtrr.o \ - hyperv.o page_track.o debugfs.o + hyperv.o debugfs.o mmu/mmu.o mmu/page_track.o kvm-intel-y += vmx/vmx.o vmx/vmenter.o vmx/pmu_intel.o vmx/vmcs12.o vmx/evmcs.o vmx/nested.o kvm-amd-y += svm.o pmu_amd.o diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index 22c2720cd948..b1c469446b07 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -62,7 +62,7 @@ u64 kvm_supported_xcr0(void) return xcr0; } -#define F(x) bit(X86_FEATURE_##x) +#define F feature_bit int kvm_update_cpuid(struct kvm_vcpu *vcpu) { @@ -281,8 +281,9 @@ out: return r; } -static void cpuid_mask(u32 *word, int wordnum) +static __always_inline void cpuid_mask(u32 *word, int wordnum) { + reverse_cpuid_check(wordnum); *word &= boot_cpu_data.x86_capability[wordnum]; } @@ -304,7 +305,13 @@ static void do_host_cpuid(struct kvm_cpuid_entry2 *entry, u32 function, case 7: case 0xb: case 0xd: + case 0xf: + case 0x10: + case 0x12: case 0x14: + case 0x17: + case 0x18: + case 0x1f: case 0x8000001d: entry->flags |= KVM_CPUID_FLAG_SIGNIFCANT_INDEX; break; @@ -346,6 +353,7 @@ static inline void do_cpuid_7_mask(struct kvm_cpuid_entry2 *entry, int index) unsigned f_umip = kvm_x86_ops->umip_emulated() ? F(UMIP) : 0; unsigned f_intel_pt = kvm_x86_ops->pt_supported() ? F(INTEL_PT) : 0; unsigned f_la57; + unsigned f_pku = kvm_x86_ops->pku_supported() ? F(PKU) : 0; /* cpuid 7.0.ebx */ const u32 kvm_cpuid_7_0_ebx_x86_features = @@ -357,10 +365,10 @@ static inline void do_cpuid_7_mask(struct kvm_cpuid_entry2 *entry, int index) /* cpuid 7.0.ecx*/ const u32 kvm_cpuid_7_0_ecx_x86_features = - F(AVX512VBMI) | F(LA57) | F(PKU) | 0 /*OSPKE*/ | + F(AVX512VBMI) | F(LA57) | 0 /*PKU*/ | 0 /*OSPKE*/ | F(RDPID) | F(AVX512_VPOPCNTDQ) | F(UMIP) | F(AVX512_VBMI2) | F(GFNI) | F(VAES) | F(VPCLMULQDQ) | F(AVX512_VNNI) | F(AVX512_BITALG) | - F(CLDEMOTE) | F(MOVDIRI) | F(MOVDIR64B); + F(CLDEMOTE) | F(MOVDIRI) | F(MOVDIR64B) | 0 /*WAITPKG*/; /* cpuid 7.0.edx*/ const u32 kvm_cpuid_7_0_edx_x86_features = @@ -386,12 +394,20 @@ static inline void do_cpuid_7_mask(struct kvm_cpuid_entry2 *entry, int index) /* Set LA57 based on hardware capability. */ entry->ecx |= f_la57; entry->ecx |= f_umip; + entry->ecx |= f_pku; /* PKU is not yet implemented for shadow paging. */ if (!tdp_enabled || !boot_cpu_has(X86_FEATURE_OSPKE)) entry->ecx &= ~F(PKU); entry->edx &= kvm_cpuid_7_0_edx_x86_features; cpuid_mask(&entry->edx, CPUID_7_EDX); + if (boot_cpu_has(X86_FEATURE_IBPB) && boot_cpu_has(X86_FEATURE_IBRS)) + entry->edx |= F(SPEC_CTRL); + if (boot_cpu_has(X86_FEATURE_STIBP)) + entry->edx |= F(INTEL_STIBP); + if (boot_cpu_has(X86_FEATURE_SPEC_CTRL_SSBD) || + boot_cpu_has(X86_FEATURE_AMD_SSBD)) + entry->edx |= F(SPEC_CTRL_SSBD); /* * We emulate ARCH_CAPABILITIES in software even * if the host doesn't support it. @@ -473,6 +489,7 @@ static inline int __do_cpuid_func(struct kvm_cpuid_entry2 *entry, u32 function, /* cpuid 0x80000008.ebx */ const u32 kvm_cpuid_8000_0008_ebx_x86_features = + F(CLZERO) | F(XSAVEERPTR) | F(WBNOINVD) | F(AMD_IBPB) | F(AMD_IBRS) | F(AMD_SSBD) | F(VIRT_SSBD) | F(AMD_SSB_NO) | F(AMD_STIBP) | F(AMD_STIBP_ALWAYS_ON); @@ -491,7 +508,7 @@ static inline int __do_cpuid_func(struct kvm_cpuid_entry2 *entry, u32 function, r = -E2BIG; - if (*nent >= maxnent) + if (WARN_ON(*nent >= maxnent)) goto out; do_host_cpuid(entry, function, 0); @@ -606,16 +623,20 @@ static inline int __do_cpuid_func(struct kvm_cpuid_entry2 *entry, u32 function, */ case 0x1f: case 0xb: { - int i, level_type; + int i; - /* read more entries until level_type is zero */ - for (i = 1; ; ++i) { + /* + * We filled in entry[0] for CPUID(EAX=<function>, + * ECX=00H) above. If its level type (ECX[15:8]) is + * zero, then the leaf is unimplemented, and we're + * done. Otherwise, continue to populate entries + * until the level type (ECX[15:8]) of the previously + * added entry is zero. + */ + for (i = 1; entry[i - 1].ecx & 0xff00; ++i) { if (*nent >= maxnent) goto out; - level_type = entry[i - 1].ecx & 0xff00; - if (!level_type) - break; do_host_cpuid(&entry[i], function, i); ++*nent; } @@ -729,18 +750,24 @@ static inline int __do_cpuid_func(struct kvm_cpuid_entry2 *entry, u32 function, g_phys_as = phys_as; entry->eax = g_phys_as | (virt_as << 8); entry->edx = 0; + entry->ebx &= kvm_cpuid_8000_0008_ebx_x86_features; + cpuid_mask(&entry->ebx, CPUID_8000_0008_EBX); /* - * IBRS, IBPB and VIRT_SSBD aren't necessarily present in - * hardware cpuid + * AMD has separate bits for each SPEC_CTRL bit. + * arch/x86/kernel/cpu/bugs.c is kind enough to + * record that in cpufeatures so use them. */ - if (boot_cpu_has(X86_FEATURE_AMD_IBPB)) + if (boot_cpu_has(X86_FEATURE_IBPB)) entry->ebx |= F(AMD_IBPB); - if (boot_cpu_has(X86_FEATURE_AMD_IBRS)) + if (boot_cpu_has(X86_FEATURE_IBRS)) entry->ebx |= F(AMD_IBRS); - if (boot_cpu_has(X86_FEATURE_VIRT_SSBD)) - entry->ebx |= F(VIRT_SSBD); - entry->ebx &= kvm_cpuid_8000_0008_ebx_x86_features; - cpuid_mask(&entry->ebx, CPUID_8000_0008_EBX); + if (boot_cpu_has(X86_FEATURE_STIBP)) + entry->ebx |= F(AMD_STIBP); + if (boot_cpu_has(X86_FEATURE_SPEC_CTRL_SSBD) || + boot_cpu_has(X86_FEATURE_AMD_SSBD)) + entry->ebx |= F(AMD_SSBD); + if (!boot_cpu_has_bug(X86_BUG_SPEC_STORE_BYPASS)) + entry->ebx |= F(AMD_SSB_NO); /* * The preference is to use SPEC CTRL MSR instead of the * VIRT_SPEC MSR. @@ -756,6 +783,11 @@ static inline int __do_cpuid_func(struct kvm_cpuid_entry2 *entry, u32 function, case 0x8000001a: case 0x8000001e: break; + /* Support memory encryption cpuid if host supports it */ + case 0x8000001F: + if (!boot_cpu_has(X86_FEATURE_SEV)) + entry->eax = entry->ebx = entry->ecx = entry->edx = 0; + break; /*Add support for Centaur's CPUID instruction*/ case 0xC0000000: /*Just support up to 0xC0000004 now*/ @@ -788,14 +820,15 @@ out: static int do_cpuid_func(struct kvm_cpuid_entry2 *entry, u32 func, int *nent, int maxnent, unsigned int type) { + if (*nent >= maxnent) + return -E2BIG; + if (type == KVM_GET_EMULATED_CPUID) return __do_cpuid_func_emulated(entry, func, nent, maxnent); return __do_cpuid_func(entry, func, nent, maxnent); } -#undef F - struct kvm_cpuid_param { u32 func; bool (*qualifier)(const struct kvm_cpuid_param *param); @@ -952,53 +985,72 @@ struct kvm_cpuid_entry2 *kvm_find_cpuid_entry(struct kvm_vcpu *vcpu, EXPORT_SYMBOL_GPL(kvm_find_cpuid_entry); /* - * If no match is found, check whether we exceed the vCPU's limit - * and return the content of the highest valid _standard_ leaf instead. - * This is to satisfy the CPUID specification. + * If the basic or extended CPUID leaf requested is higher than the + * maximum supported basic or extended leaf, respectively, then it is + * out of range. */ -static struct kvm_cpuid_entry2* check_cpuid_limit(struct kvm_vcpu *vcpu, - u32 function, u32 index) +static bool cpuid_function_in_range(struct kvm_vcpu *vcpu, u32 function) { - struct kvm_cpuid_entry2 *maxlevel; - - maxlevel = kvm_find_cpuid_entry(vcpu, function & 0x80000000, 0); - if (!maxlevel || maxlevel->eax >= function) - return NULL; - if (function & 0x80000000) { - maxlevel = kvm_find_cpuid_entry(vcpu, 0, 0); - if (!maxlevel) - return NULL; - } - return kvm_find_cpuid_entry(vcpu, maxlevel->eax, index); + struct kvm_cpuid_entry2 *max; + + max = kvm_find_cpuid_entry(vcpu, function & 0x80000000, 0); + return max && function <= max->eax; } bool kvm_cpuid(struct kvm_vcpu *vcpu, u32 *eax, u32 *ebx, u32 *ecx, u32 *edx, bool check_limit) { u32 function = *eax, index = *ecx; - struct kvm_cpuid_entry2 *best; - bool entry_found = true; - - best = kvm_find_cpuid_entry(vcpu, function, index); - - if (!best) { - entry_found = false; - if (!check_limit) - goto out; + struct kvm_cpuid_entry2 *entry; + struct kvm_cpuid_entry2 *max; + bool found; - best = check_cpuid_limit(vcpu, function, index); + entry = kvm_find_cpuid_entry(vcpu, function, index); + found = entry; + /* + * Intel CPUID semantics treats any query for an out-of-range + * leaf as if the highest basic leaf (i.e. CPUID.0H:EAX) were + * requested. AMD CPUID semantics returns all zeroes for any + * undefined leaf, whether or not the leaf is in range. + */ + if (!entry && check_limit && !guest_cpuid_is_amd(vcpu) && + !cpuid_function_in_range(vcpu, function)) { + max = kvm_find_cpuid_entry(vcpu, 0, 0); + if (max) { + function = max->eax; + entry = kvm_find_cpuid_entry(vcpu, function, index); + } } - -out: - if (best) { - *eax = best->eax; - *ebx = best->ebx; - *ecx = best->ecx; - *edx = best->edx; - } else + if (entry) { + *eax = entry->eax; + *ebx = entry->ebx; + *ecx = entry->ecx; + *edx = entry->edx; + if (function == 7 && index == 0) { + u64 data; + if (!__kvm_get_msr(vcpu, MSR_IA32_TSX_CTRL, &data, true) && + (data & TSX_CTRL_CPUID_CLEAR)) + *ebx &= ~(F(RTM) | F(HLE)); + } + } else { *eax = *ebx = *ecx = *edx = 0; - trace_kvm_cpuid(function, *eax, *ebx, *ecx, *edx, entry_found); - return entry_found; + /* + * When leaf 0BH or 1FH is defined, CL is pass-through + * and EDX is always the x2APIC ID, even for undefined + * subleaves. Index 1 will exist iff the leaf is + * implemented, so we pass through CL iff leaf 1 + * exists. EDX can be copied from any existing index. + */ + if (function == 0xb || function == 0x1f) { + entry = kvm_find_cpuid_entry(vcpu, function, 1); + if (entry) { + *ecx = index & 0xff; + *edx = entry->edx; + } + } + } + trace_kvm_cpuid(function, *eax, *ebx, *ecx, *edx, found); + return found; } EXPORT_SYMBOL_GPL(kvm_cpuid); diff --git a/arch/x86/kvm/cpuid.h b/arch/x86/kvm/cpuid.h index d78a61408243..7366c618aa04 100644 --- a/arch/x86/kvm/cpuid.h +++ b/arch/x86/kvm/cpuid.h @@ -53,15 +53,46 @@ static const struct cpuid_reg reverse_cpuid[] = { [CPUID_7_ECX] = { 7, 0, CPUID_ECX}, [CPUID_8000_0007_EBX] = {0x80000007, 0, CPUID_EBX}, [CPUID_7_EDX] = { 7, 0, CPUID_EDX}, + [CPUID_7_1_EAX] = { 7, 1, CPUID_EAX}, }; -static __always_inline struct cpuid_reg x86_feature_cpuid(unsigned x86_feature) +/* + * Reverse CPUID and its derivatives can only be used for hardware-defined + * feature words, i.e. words whose bits directly correspond to a CPUID leaf. + * Retrieving a feature bit or masking guest CPUID from a Linux-defined word + * is nonsensical as the bit number/mask is an arbitrary software-defined value + * and can't be used by KVM to query/control guest capabilities. And obviously + * the leaf being queried must have an entry in the lookup table. + */ +static __always_inline void reverse_cpuid_check(unsigned x86_leaf) { - unsigned x86_leaf = x86_feature / 32; - + BUILD_BUG_ON(x86_leaf == CPUID_LNX_1); + BUILD_BUG_ON(x86_leaf == CPUID_LNX_2); + BUILD_BUG_ON(x86_leaf == CPUID_LNX_3); + BUILD_BUG_ON(x86_leaf == CPUID_LNX_4); BUILD_BUG_ON(x86_leaf >= ARRAY_SIZE(reverse_cpuid)); BUILD_BUG_ON(reverse_cpuid[x86_leaf].function == 0); +} + +/* + * Retrieve the bit mask from an X86_FEATURE_* definition. Features contain + * the hardware defined bit number (stored in bits 4:0) and a software defined + * "word" (stored in bits 31:5). The word is used to index into arrays of + * bit masks that hold the per-cpu feature capabilities, e.g. this_cpu_has(). + */ +static __always_inline u32 __feature_bit(int x86_feature) +{ + reverse_cpuid_check(x86_feature / 32); + return 1 << (x86_feature & 31); +} +#define feature_bit(name) __feature_bit(X86_FEATURE_##name) + +static __always_inline struct cpuid_reg x86_feature_cpuid(unsigned x86_feature) +{ + unsigned x86_leaf = x86_feature / 32; + + reverse_cpuid_check(x86_leaf); return reverse_cpuid[x86_leaf]; } @@ -93,15 +124,11 @@ static __always_inline bool guest_cpuid_has(struct kvm_vcpu *vcpu, unsigned x86_ { int *reg; - if (x86_feature == X86_FEATURE_XSAVE && - !static_cpu_has(X86_FEATURE_XSAVE)) - return false; - reg = guest_cpuid_get_register(vcpu, x86_feature); if (!reg) return false; - return *reg & bit(x86_feature); + return *reg & __feature_bit(x86_feature); } static __always_inline void guest_cpuid_clear(struct kvm_vcpu *vcpu, unsigned x86_feature) @@ -110,7 +137,7 @@ static __always_inline void guest_cpuid_clear(struct kvm_vcpu *vcpu, unsigned x8 reg = guest_cpuid_get_register(vcpu, x86_feature); if (reg) - *reg &= ~bit(x86_feature); + *reg &= ~__feature_bit(x86_feature); } static inline bool guest_cpuid_is_amd(struct kvm_vcpu *vcpu) diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index 718f7d9afedc..ddbc61984227 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -22,6 +22,7 @@ #include "kvm_cache_regs.h" #include <asm/kvm_emulate.h> #include <linux/stringify.h> +#include <asm/fpu/api.h> #include <asm/debugreg.h> #include <asm/nospec-branch.h> @@ -310,7 +311,9 @@ static void invalidate_registers(struct x86_emulate_ctxt *ctxt) #define ON64(x) #endif -static int fastop(struct x86_emulate_ctxt *ctxt, void (*fop)(struct fastop *)); +typedef void (*fastop_t)(struct fastop *); + +static int fastop(struct x86_emulate_ctxt *ctxt, fastop_t fop); #define __FOP_FUNC(name) \ ".align " __stringify(FASTOP_SIZE) " \n\t" \ @@ -1075,8 +1078,23 @@ static void fetch_register_operand(struct operand *op) } } -static void read_sse_reg(struct x86_emulate_ctxt *ctxt, sse128_t *data, int reg) +static void emulator_get_fpu(void) +{ + fpregs_lock(); + + fpregs_assert_state_consistent(); + if (test_thread_flag(TIF_NEED_FPU_LOAD)) + switch_fpu_return(); +} + +static void emulator_put_fpu(void) +{ + fpregs_unlock(); +} + +static void read_sse_reg(sse128_t *data, int reg) { + emulator_get_fpu(); switch (reg) { case 0: asm("movdqa %%xmm0, %0" : "=m"(*data)); break; case 1: asm("movdqa %%xmm1, %0" : "=m"(*data)); break; @@ -1098,11 +1116,12 @@ static void read_sse_reg(struct x86_emulate_ctxt *ctxt, sse128_t *data, int reg) #endif default: BUG(); } + emulator_put_fpu(); } -static void write_sse_reg(struct x86_emulate_ctxt *ctxt, sse128_t *data, - int reg) +static void write_sse_reg(sse128_t *data, int reg) { + emulator_get_fpu(); switch (reg) { case 0: asm("movdqa %0, %%xmm0" : : "m"(*data)); break; case 1: asm("movdqa %0, %%xmm1" : : "m"(*data)); break; @@ -1124,10 +1143,12 @@ static void write_sse_reg(struct x86_emulate_ctxt *ctxt, sse128_t *data, #endif default: BUG(); } + emulator_put_fpu(); } -static void read_mmx_reg(struct x86_emulate_ctxt *ctxt, u64 *data, int reg) +static void read_mmx_reg(u64 *data, int reg) { + emulator_get_fpu(); switch (reg) { case 0: asm("movq %%mm0, %0" : "=m"(*data)); break; case 1: asm("movq %%mm1, %0" : "=m"(*data)); break; @@ -1139,10 +1160,12 @@ static void read_mmx_reg(struct x86_emulate_ctxt *ctxt, u64 *data, int reg) case 7: asm("movq %%mm7, %0" : "=m"(*data)); break; default: BUG(); } + emulator_put_fpu(); } -static void write_mmx_reg(struct x86_emulate_ctxt *ctxt, u64 *data, int reg) +static void write_mmx_reg(u64 *data, int reg) { + emulator_get_fpu(); switch (reg) { case 0: asm("movq %0, %%mm0" : : "m"(*data)); break; case 1: asm("movq %0, %%mm1" : : "m"(*data)); break; @@ -1154,6 +1177,7 @@ static void write_mmx_reg(struct x86_emulate_ctxt *ctxt, u64 *data, int reg) case 7: asm("movq %0, %%mm7" : : "m"(*data)); break; default: BUG(); } + emulator_put_fpu(); } static int em_fninit(struct x86_emulate_ctxt *ctxt) @@ -1161,7 +1185,9 @@ static int em_fninit(struct x86_emulate_ctxt *ctxt) if (ctxt->ops->get_cr(ctxt, 0) & (X86_CR0_TS | X86_CR0_EM)) return emulate_nm(ctxt); + emulator_get_fpu(); asm volatile("fninit"); + emulator_put_fpu(); return X86EMUL_CONTINUE; } @@ -1172,7 +1198,9 @@ static int em_fnstcw(struct x86_emulate_ctxt *ctxt) if (ctxt->ops->get_cr(ctxt, 0) & (X86_CR0_TS | X86_CR0_EM)) return emulate_nm(ctxt); + emulator_get_fpu(); asm volatile("fnstcw %0": "+m"(fcw)); + emulator_put_fpu(); ctxt->dst.val = fcw; @@ -1186,7 +1214,9 @@ static int em_fnstsw(struct x86_emulate_ctxt *ctxt) if (ctxt->ops->get_cr(ctxt, 0) & (X86_CR0_TS | X86_CR0_EM)) return emulate_nm(ctxt); + emulator_get_fpu(); asm volatile("fnstsw %0": "+m"(fsw)); + emulator_put_fpu(); ctxt->dst.val = fsw; @@ -1205,7 +1235,7 @@ static void decode_register_operand(struct x86_emulate_ctxt *ctxt, op->type = OP_XMM; op->bytes = 16; op->addr.xmm = reg; - read_sse_reg(ctxt, &op->vec_val, reg); + read_sse_reg(&op->vec_val, reg); return; } if (ctxt->d & Mmx) { @@ -1256,7 +1286,7 @@ static int decode_modrm(struct x86_emulate_ctxt *ctxt, op->type = OP_XMM; op->bytes = 16; op->addr.xmm = ctxt->modrm_rm; - read_sse_reg(ctxt, &op->vec_val, ctxt->modrm_rm); + read_sse_reg(&op->vec_val, ctxt->modrm_rm); return rc; } if (ctxt->d & Mmx) { @@ -1833,10 +1863,10 @@ static int writeback(struct x86_emulate_ctxt *ctxt, struct operand *op) op->bytes * op->count); break; case OP_XMM: - write_sse_reg(ctxt, &op->vec_val, op->addr.xmm); + write_sse_reg(&op->vec_val, op->addr.xmm); break; case OP_MM: - write_mmx_reg(ctxt, &op->mm_val, op->addr.mm); + write_mmx_reg(&op->mm_val, op->addr.mm); break; case OP_NONE: /* no writeback */ @@ -2348,12 +2378,7 @@ static int em_lseg(struct x86_emulate_ctxt *ctxt) static int emulator_has_longmode(struct x86_emulate_ctxt *ctxt) { #ifdef CONFIG_X86_64 - u32 eax, ebx, ecx, edx; - - eax = 0x80000001; - ecx = 0; - ctxt->ops->get_cpuid(ctxt, &eax, &ebx, &ecx, &edx, false); - return edx & bit(X86_FEATURE_LM); + return ctxt->ops->guest_has_long_mode(ctxt); #else return false; #endif @@ -2770,11 +2795,10 @@ static int em_syscall(struct x86_emulate_ctxt *ctxt) return emulate_ud(ctxt); ops->get_msr(ctxt, MSR_EFER, &efer); - setup_syscalls_segments(ctxt, &cs, &ss); - if (!(efer & EFER_SCE)) return emulate_ud(ctxt); + setup_syscalls_segments(ctxt, &cs, &ss); ops->get_msr(ctxt, MSR_STAR, &msr_data); msr_data >>= 32; cs_sel = (u16)(msr_data & 0xfffc); @@ -2838,12 +2862,11 @@ static int em_sysenter(struct x86_emulate_ctxt *ctxt) if (ctxt->mode == X86EMUL_MODE_PROT64) return X86EMUL_UNHANDLEABLE; - setup_syscalls_segments(ctxt, &cs, &ss); - ops->get_msr(ctxt, MSR_IA32_SYSENTER_CS, &msr_data); if ((msr_data & 0xfffc) == 0x0) return emulate_gp(ctxt, 0); + setup_syscalls_segments(ctxt, &cs, &ss); ctxt->eflags &= ~(X86_EFLAGS_VM | X86_EFLAGS_IF); cs_sel = (u16)msr_data & ~SEGMENT_RPL_MASK; ss_sel = cs_sel + 8; @@ -3620,18 +3643,11 @@ static int em_mov(struct x86_emulate_ctxt *ctxt) return X86EMUL_CONTINUE; } -#define FFL(x) bit(X86_FEATURE_##x) - static int em_movbe(struct x86_emulate_ctxt *ctxt) { - u32 ebx, ecx, edx, eax = 1; u16 tmp; - /* - * Check MOVBE is set in the guest-visible CPUID leaf. - */ - ctxt->ops->get_cpuid(ctxt, &eax, &ebx, &ecx, &edx, false); - if (!(ecx & FFL(MOVBE))) + if (!ctxt->ops->guest_has_movbe(ctxt)) return emulate_ud(ctxt); switch (ctxt->op_bytes) { @@ -4029,10 +4045,7 @@ static int em_movsxd(struct x86_emulate_ctxt *ctxt) static int check_fxsr(struct x86_emulate_ctxt *ctxt) { - u32 eax = 1, ebx, ecx = 0, edx; - - ctxt->ops->get_cpuid(ctxt, &eax, &ebx, &ecx, &edx, false); - if (!(edx & FFL(FXSR))) + if (!ctxt->ops->guest_has_fxsr(ctxt)) return emulate_ud(ctxt); if (ctxt->ops->get_cr(ctxt, 0) & (X86_CR0_TS | X86_CR0_EM)) @@ -4094,8 +4107,12 @@ static int em_fxsave(struct x86_emulate_ctxt *ctxt) if (rc != X86EMUL_CONTINUE) return rc; + emulator_get_fpu(); + rc = asm_safe("fxsave %[fx]", , [fx] "+m"(fx_state)); + emulator_put_fpu(); + if (rc != X86EMUL_CONTINUE) return rc; @@ -4138,6 +4155,8 @@ static int em_fxrstor(struct x86_emulate_ctxt *ctxt) if (rc != X86EMUL_CONTINUE) return rc; + emulator_get_fpu(); + if (size < __fxstate_size(16)) { rc = fxregs_fixup(&fx_state, size); if (rc != X86EMUL_CONTINUE) @@ -4153,9 +4172,25 @@ static int em_fxrstor(struct x86_emulate_ctxt *ctxt) rc = asm_safe("fxrstor %[fx]", : [fx] "m"(fx_state)); out: + emulator_put_fpu(); + return rc; } +static int em_xsetbv(struct x86_emulate_ctxt *ctxt) +{ + u32 eax, ecx, edx; + + eax = reg_read(ctxt, VCPU_REGS_RAX); + edx = reg_read(ctxt, VCPU_REGS_RDX); + ecx = reg_read(ctxt, VCPU_REGS_RCX); + + if (ctxt->ops->set_xcr(ctxt, ecx, ((u64)edx << 32) | eax)) + return emulate_gp(ctxt, 0); + + return X86EMUL_CONTINUE; +} + static bool valid_cr(int nr) { switch (nr) { @@ -4409,6 +4444,12 @@ static const struct opcode group7_rm1[] = { N, N, N, N, N, N, }; +static const struct opcode group7_rm2[] = { + N, + II(ImplicitOps | Priv, em_xsetbv, xsetbv), + N, N, N, N, N, N, +}; + static const struct opcode group7_rm3[] = { DIP(SrcNone | Prot | Priv, vmrun, check_svme_pa), II(SrcNone | Prot | EmulateOnUD, em_hypercall, vmmcall), @@ -4498,7 +4539,8 @@ static const struct group_dual group7 = { { }, { EXT(0, group7_rm0), EXT(0, group7_rm1), - N, EXT(0, group7_rm3), + EXT(0, group7_rm2), + EXT(0, group7_rm3), II(SrcNone | DstMem | Mov, em_smsw, smsw), N, II(SrcMem16 | Mov | Priv, em_lmsw, lmsw), EXT(0, group7_rm7), @@ -5144,7 +5186,7 @@ int x86_decode_insn(struct x86_emulate_ctxt *ctxt, void *insn, int insn_len) else { rc = __do_insn_fetch_bytes(ctxt, 1); if (rc != X86EMUL_CONTINUE) - return rc; + goto done; } switch (mode) { @@ -5191,16 +5233,28 @@ int x86_decode_insn(struct x86_emulate_ctxt *ctxt, void *insn, int insn_len) ctxt->ad_bytes = def_ad_bytes ^ 6; break; case 0x26: /* ES override */ + has_seg_override = true; + ctxt->seg_override = VCPU_SREG_ES; + break; case 0x2e: /* CS override */ + has_seg_override = true; + ctxt->seg_override = VCPU_SREG_CS; + break; case 0x36: /* SS override */ + has_seg_override = true; + ctxt->seg_override = VCPU_SREG_SS; + break; case 0x3e: /* DS override */ has_seg_override = true; - ctxt->seg_override = (ctxt->b >> 3) & 3; + ctxt->seg_override = VCPU_SREG_DS; break; case 0x64: /* FS override */ + has_seg_override = true; + ctxt->seg_override = VCPU_SREG_FS; + break; case 0x65: /* GS override */ has_seg_override = true; - ctxt->seg_override = ctxt->b & 7; + ctxt->seg_override = VCPU_SREG_GS; break; case 0x40 ... 0x4f: /* REX */ if (mode != X86EMUL_MODE_PROT64) @@ -5284,10 +5338,15 @@ done_prefixes: } break; case Escape: - if (ctxt->modrm > 0xbf) - opcode = opcode.u.esc->high[ctxt->modrm - 0xc0]; - else + if (ctxt->modrm > 0xbf) { + size_t size = ARRAY_SIZE(opcode.u.esc->high); + u32 index = array_index_nospec( + ctxt->modrm - 0xc0, size); + + opcode = opcode.u.esc->high[index]; + } else { opcode = opcode.u.esc->op[(ctxt->modrm >> 3) & 7]; + } break; case InstrDual: if ((ctxt->modrm >> 6) == 3) @@ -5395,6 +5454,8 @@ done_prefixes: ctxt->memopp->addr.mem.ea + ctxt->_eip); done: + if (rc == X86EMUL_PROPAGATE_FAULT) + ctxt->have_exception = true; return (rc != X86EMUL_CONTINUE) ? EMULATION_FAILED : EMULATION_OK; } @@ -5427,7 +5488,9 @@ static int flush_pending_x87_faults(struct x86_emulate_ctxt *ctxt) { int rc; + emulator_get_fpu(); rc = asm_safe("fwait"); + emulator_put_fpu(); if (unlikely(rc != X86EMUL_CONTINUE)) return emulate_exception(ctxt, MF_VECTOR, 0, false); @@ -5435,14 +5498,13 @@ static int flush_pending_x87_faults(struct x86_emulate_ctxt *ctxt) return X86EMUL_CONTINUE; } -static void fetch_possible_mmx_operand(struct x86_emulate_ctxt *ctxt, - struct operand *op) +static void fetch_possible_mmx_operand(struct operand *op) { if (op->type == OP_MM) - read_mmx_reg(ctxt, &op->mm_val, op->addr.mm); + read_mmx_reg(&op->mm_val, op->addr.mm); } -static int fastop(struct x86_emulate_ctxt *ctxt, void (*fop)(struct fastop *)) +static int fastop(struct x86_emulate_ctxt *ctxt, fastop_t fop) { ulong flags = (ctxt->eflags & EFLAGS_MASK) | X86_EFLAGS_IF; @@ -5518,10 +5580,10 @@ int x86_emulate_insn(struct x86_emulate_ctxt *ctxt) * Now that we know the fpu is exception safe, we can fetch * operands from it. */ - fetch_possible_mmx_operand(ctxt, &ctxt->src); - fetch_possible_mmx_operand(ctxt, &ctxt->src2); + fetch_possible_mmx_operand(&ctxt->src); + fetch_possible_mmx_operand(&ctxt->src2); if (!(ctxt->d & Mov)) - fetch_possible_mmx_operand(ctxt, &ctxt->dst); + fetch_possible_mmx_operand(&ctxt->dst); } if (unlikely(emul_flags & X86EMUL_GUEST_MASK) && ctxt->intercept) { @@ -5620,14 +5682,10 @@ special_insn: ctxt->eflags &= ~X86_EFLAGS_RF; if (ctxt->execute) { - if (ctxt->d & Fastop) { - void (*fop)(struct fastop *) = (void *)ctxt->execute; - rc = fastop(ctxt, fop); - if (rc != X86EMUL_CONTINUE) - goto done; - goto writeback; - } - rc = ctxt->execute(ctxt); + if (ctxt->d & Fastop) + rc = fastop(ctxt, (fastop_t)ctxt->execute); + else + rc = ctxt->execute(ctxt); if (rc != X86EMUL_CONTINUE) goto done; goto writeback; diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c index c10a8b10b203..a86fda7a1d03 100644 --- a/arch/x86/kvm/hyperv.c +++ b/arch/x86/kvm/hyperv.c @@ -23,6 +23,7 @@ #include "ioapic.h" #include "hyperv.h" +#include <linux/cpu.h> #include <linux/kvm_host.h> #include <linux/highmem.h> #include <linux/sched/cputime.h> @@ -32,6 +33,7 @@ #include <trace/events/kvm.h> #include "trace.h" +#include "irq.h" #define KVM_HV_MAX_SPARSE_VCPU_SET_BITS DIV_ROUND_UP(KVM_MAX_VCPUS, 64) @@ -645,7 +647,9 @@ static int stimer_notify_direct(struct kvm_vcpu_hv_stimer *stimer) .vector = stimer->config.apic_vector }; - return !kvm_apic_set_irq(vcpu, &irq, NULL); + if (lapic_in_kernel(vcpu)) + return !kvm_apic_set_irq(vcpu, &irq, NULL); + return 0; } static void stimer_expiration(struct kvm_vcpu_hv_stimer *stimer) @@ -772,9 +776,10 @@ int kvm_hv_activate_synic(struct kvm_vcpu *vcpu, bool dont_zero_synic_pages) /* * Hyper-V SynIC auto EOI SINT's are - * not compatible with APICV, so deactivate APICV + * not compatible with APICV, so request + * to deactivate APICV permanently. */ - kvm_vcpu_deactivate_apicv(vcpu); + kvm_request_apicv_update(vcpu->kvm, false, APICV_INHIBIT_REASON_HYPERV); synic->active = true; synic->dont_zero_synic_pages = dont_zero_synic_pages; return 0; @@ -806,11 +811,12 @@ static int kvm_hv_msr_get_crash_data(struct kvm_vcpu *vcpu, u32 index, u64 *pdata) { struct kvm_hv *hv = &vcpu->kvm->arch.hyperv; + size_t size = ARRAY_SIZE(hv->hv_crash_param); - if (WARN_ON_ONCE(index >= ARRAY_SIZE(hv->hv_crash_param))) + if (WARN_ON_ONCE(index >= size)) return -EINVAL; - *pdata = hv->hv_crash_param[index]; + *pdata = hv->hv_crash_param[array_index_nospec(index, size)]; return 0; } @@ -849,11 +855,12 @@ static int kvm_hv_msr_set_crash_data(struct kvm_vcpu *vcpu, u32 index, u64 data) { struct kvm_hv *hv = &vcpu->kvm->arch.hyperv; + size_t size = ARRAY_SIZE(hv->hv_crash_param); - if (WARN_ON_ONCE(index >= ARRAY_SIZE(hv->hv_crash_param))) + if (WARN_ON_ONCE(index >= size)) return -EINVAL; - hv->hv_crash_param[index] = data; + hv->hv_crash_param[array_index_nospec(index, size)] = data; return 0; } @@ -1055,7 +1062,7 @@ static int kvm_hv_set_msr_pw(struct kvm_vcpu *vcpu, u32 msr, u64 data, return 1; break; default: - vcpu_unimpl(vcpu, "Hyper-V uhandled wrmsr: 0x%x data 0x%llx\n", + vcpu_unimpl(vcpu, "Hyper-V unhandled wrmsr: 0x%x data 0x%llx\n", msr, data); return 1; } @@ -1118,7 +1125,7 @@ static int kvm_hv_set_msr(struct kvm_vcpu *vcpu, u32 msr, u64 data, bool host) return 1; /* - * Clear apic_assist portion of f(struct hv_vp_assist_page + * Clear apic_assist portion of struct hv_vp_assist_page * only, there can be valuable data in the rest which needs * to be preserved e.g. on migration. */ @@ -1175,7 +1182,7 @@ static int kvm_hv_set_msr(struct kvm_vcpu *vcpu, u32 msr, u64 data, bool host) return 1; break; default: - vcpu_unimpl(vcpu, "Hyper-V uhandled wrmsr: 0x%x data 0x%llx\n", + vcpu_unimpl(vcpu, "Hyper-V unhandled wrmsr: 0x%x data 0x%llx\n", msr, data); return 1; } @@ -1781,7 +1788,7 @@ int kvm_vm_ioctl_hv_eventfd(struct kvm *kvm, struct kvm_hyperv_eventfd *args) int kvm_vcpu_ioctl_get_hv_cpuid(struct kvm_vcpu *vcpu, struct kvm_cpuid2 *cpuid, struct kvm_cpuid_entry2 __user *entries) { - uint16_t evmcs_ver = kvm_x86_ops->nested_get_evmcs_version(vcpu); + uint16_t evmcs_ver = 0; struct kvm_cpuid_entry2 cpuid_entries[] = { { .function = HYPERV_CPUID_VENDOR_AND_MAX_FUNCTIONS }, { .function = HYPERV_CPUID_INTERFACE }, @@ -1793,6 +1800,9 @@ int kvm_vcpu_ioctl_get_hv_cpuid(struct kvm_vcpu *vcpu, struct kvm_cpuid2 *cpuid, }; int i, nent = ARRAY_SIZE(cpuid_entries); + if (kvm_x86_ops->nested_get_evmcs_version) + evmcs_ver = kvm_x86_ops->nested_get_evmcs_version(vcpu); + /* Skip NESTED_FEATURES if eVMCS is not supported */ if (!evmcs_ver) --nent; @@ -1849,7 +1859,13 @@ int kvm_vcpu_ioctl_get_hv_cpuid(struct kvm_vcpu *vcpu, struct kvm_cpuid2 *cpuid, ent->edx |= HV_FEATURE_FREQUENCY_MSRS_AVAILABLE; ent->edx |= HV_FEATURE_GUEST_CRASH_MSR_AVAILABLE; - ent->edx |= HV_STIMER_DIRECT_MODE_AVAILABLE; + + /* + * Direct Synthetic timers only make sense with in-kernel + * LAPIC + */ + if (lapic_in_kernel(vcpu)) + ent->edx |= HV_STIMER_DIRECT_MODE_AVAILABLE; break; @@ -1861,7 +1877,8 @@ int kvm_vcpu_ioctl_get_hv_cpuid(struct kvm_vcpu *vcpu, struct kvm_cpuid2 *cpuid, ent->eax |= HV_X64_EX_PROCESSOR_MASKS_RECOMMENDED; if (evmcs_ver) ent->eax |= HV_X64_ENLIGHTENED_VMCS_RECOMMENDED; - + if (!cpu_smt_possible()) + ent->eax |= HV_X64_NO_NONARCH_CORESHARING; /* * Default number of spinlock retry attempts, matches * HyperV 2016. diff --git a/arch/x86/kvm/i8254.c b/arch/x86/kvm/i8254.c index 4a6dc54cc12b..b24c606ac04b 100644 --- a/arch/x86/kvm/i8254.c +++ b/arch/x86/kvm/i8254.c @@ -295,12 +295,24 @@ void kvm_pit_set_reinject(struct kvm_pit *pit, bool reinject) if (atomic_read(&ps->reinject) == reinject) return; + /* + * AMD SVM AVIC accelerates EOI write and does not trap. + * This cause in-kernel PIT re-inject mode to fail + * since it checks ps->irq_ack before kvm_set_irq() + * and relies on the ack notifier to timely queue + * the pt->worker work iterm and reinject the missed tick. + * So, deactivate APICv when PIT is in reinject mode. + */ if (reinject) { + kvm_request_apicv_update(kvm, false, + APICV_INHIBIT_REASON_PIT_REINJ); /* The initial state is preserved while ps->reinject == 0. */ kvm_pit_reset_reinject(pit); kvm_register_irq_ack_notifier(kvm, &ps->irq_ack_notifier); kvm_register_irq_mask_notifier(kvm, 0, &pit->mask_notifier); } else { + kvm_request_apicv_update(kvm, true, + APICV_INHIBIT_REASON_PIT_REINJ); kvm_unregister_irq_ack_notifier(kvm, &ps->irq_ack_notifier); kvm_unregister_irq_mask_notifier(kvm, 0, &pit->mask_notifier); } diff --git a/arch/x86/kvm/i8259.c b/arch/x86/kvm/i8259.c index 8b38bb4868a6..629a09ca9860 100644 --- a/arch/x86/kvm/i8259.c +++ b/arch/x86/kvm/i8259.c @@ -460,10 +460,14 @@ static int picdev_write(struct kvm_pic *s, switch (addr) { case 0x20: case 0x21: + pic_lock(s); + pic_ioport_write(&s->pics[0], addr, data); + pic_unlock(s); + break; case 0xa0: case 0xa1: pic_lock(s); - pic_ioport_write(&s->pics[addr >> 7], addr, data); + pic_ioport_write(&s->pics[1], addr, data); pic_unlock(s); break; case 0x4d0: diff --git a/arch/x86/kvm/ioapic.c b/arch/x86/kvm/ioapic.c index d859ae8890d0..7668fed1ce65 100644 --- a/arch/x86/kvm/ioapic.c +++ b/arch/x86/kvm/ioapic.c @@ -36,6 +36,7 @@ #include <linux/io.h> #include <linux/slab.h> #include <linux/export.h> +#include <linux/nospec.h> #include <asm/processor.h> #include <asm/page.h> #include <asm/current.h> @@ -48,6 +49,11 @@ static int ioapic_service(struct kvm_ioapic *vioapic, int irq, bool line_status); +static void kvm_ioapic_update_eoi_one(struct kvm_vcpu *vcpu, + struct kvm_ioapic *ioapic, + int trigger_mode, + int pin); + static unsigned long ioapic_read_indirect(struct kvm_ioapic *ioapic, unsigned long addr, unsigned long length) @@ -68,13 +74,14 @@ static unsigned long ioapic_read_indirect(struct kvm_ioapic *ioapic, default: { u32 redir_index = (ioapic->ioregsel - 0x10) >> 1; - u64 redir_content; + u64 redir_content = ~0ULL; + + if (redir_index < IOAPIC_NUM_PINS) { + u32 index = array_index_nospec( + redir_index, IOAPIC_NUM_PINS); - if (redir_index < IOAPIC_NUM_PINS) - redir_content = - ioapic->redirtbl[redir_index].bits; - else - redir_content = ~0ULL; + redir_content = ioapic->redirtbl[index].bits; + } result = (ioapic->ioregsel & 0x1) ? (redir_content >> 32) & 0xffffffff : @@ -108,8 +115,9 @@ static void __rtc_irq_eoi_tracking_restore_one(struct kvm_vcpu *vcpu) union kvm_ioapic_redirect_entry *e; e = &ioapic->redirtbl[RTC_GSI]; - if (!kvm_apic_match_dest(vcpu, NULL, 0, e->fields.dest_id, - e->fields.dest_mode)) + if (!kvm_apic_match_dest(vcpu, NULL, APIC_DEST_NOSHORT, + e->fields.dest_id, + kvm_lapic_irq_dest_mode(!!e->fields.dest_mode))) return; new_val = kvm_apic_pending_eoi(vcpu, e->fields.vector); @@ -151,10 +159,16 @@ static void kvm_rtc_eoi_tracking_restore_all(struct kvm_ioapic *ioapic) __rtc_irq_eoi_tracking_restore_one(vcpu); } -static void rtc_irq_eoi(struct kvm_ioapic *ioapic, struct kvm_vcpu *vcpu) +static void rtc_irq_eoi(struct kvm_ioapic *ioapic, struct kvm_vcpu *vcpu, + int vector) { - if (test_and_clear_bit(vcpu->vcpu_id, - ioapic->rtc_status.dest_map.map)) { + struct dest_map *dest_map = &ioapic->rtc_status.dest_map; + + /* RTC special handling */ + if (test_bit(vcpu->vcpu_id, dest_map->map) && + (vector == dest_map->vectors[vcpu->vcpu_id]) && + (test_and_clear_bit(vcpu->vcpu_id, + ioapic->rtc_status.dest_map.map))) { --ioapic->rtc_status.pending_eoi; rtc_status_pending_eoi_check_valid(ioapic); } @@ -168,6 +182,31 @@ static bool rtc_irq_check_coalesced(struct kvm_ioapic *ioapic) return false; } +static void ioapic_lazy_update_eoi(struct kvm_ioapic *ioapic, int irq) +{ + int i; + struct kvm_vcpu *vcpu; + union kvm_ioapic_redirect_entry *entry = &ioapic->redirtbl[irq]; + + kvm_for_each_vcpu(i, vcpu, ioapic->kvm) { + if (!kvm_apic_match_dest(vcpu, NULL, APIC_DEST_NOSHORT, + entry->fields.dest_id, + entry->fields.dest_mode) || + kvm_apic_pending_eoi(vcpu, entry->fields.vector)) + continue; + + /* + * If no longer has pending EOI in LAPICs, update + * EOI for this vetor. + */ + rtc_irq_eoi(ioapic, vcpu, entry->fields.vector); + kvm_ioapic_update_eoi_one(vcpu, ioapic, + entry->fields.trig_mode, + irq); + break; + } +} + static int ioapic_set_irq(struct kvm_ioapic *ioapic, unsigned int irq, int irq_level, bool line_status) { @@ -186,9 +225,18 @@ static int ioapic_set_irq(struct kvm_ioapic *ioapic, unsigned int irq, } /* + * AMD SVM AVIC accelerate EOI write and do not trap, + * in-kernel IOAPIC will not be able to receive the EOI. + * In this case, we do lazy update of the pending EOI when + * trying to set IOAPIC irq. + */ + if (kvm_apicv_activated(ioapic->kvm)) + ioapic_lazy_update_eoi(ioapic, irq); + + /* * Return 0 for coalesced interrupts; for edge-triggered interrupts, * this only happens if a previous edge has not been delivered due - * do masking. For level interrupts, the remote_irr field tells + * to masking. For level interrupts, the remote_irr field tells * us if the interrupt is waiting for an EOI. * * RTC is special: it is edge-triggered, but userspace likes to know @@ -250,8 +298,10 @@ void kvm_ioapic_scan_entry(struct kvm_vcpu *vcpu, ulong *ioapic_handled_vectors) if (e->fields.trig_mode == IOAPIC_LEVEL_TRIG || kvm_irq_has_notifier(ioapic->kvm, KVM_IRQCHIP_IOAPIC, index) || index == RTC_GSI) { - if (kvm_apic_match_dest(vcpu, NULL, 0, - e->fields.dest_id, e->fields.dest_mode) || + u16 dm = kvm_lapic_irq_dest_mode(!!e->fields.dest_mode); + + if (kvm_apic_match_dest(vcpu, NULL, APIC_DEST_NOSHORT, + e->fields.dest_id, dm) || kvm_apic_pending_eoi(vcpu, e->fields.vector)) __set_bit(e->fields.vector, ioapic_handled_vectors); @@ -271,8 +321,9 @@ static void ioapic_write_indirect(struct kvm_ioapic *ioapic, u32 val) { unsigned index; bool mask_before, mask_after; - int old_remote_irr, old_delivery_status; union kvm_ioapic_redirect_entry *e; + unsigned long vcpu_bitmap; + int old_remote_irr, old_delivery_status, old_dest_id, old_dest_mode; switch (ioapic->ioregsel) { case IOAPIC_REG_VERSION: @@ -291,11 +342,14 @@ static void ioapic_write_indirect(struct kvm_ioapic *ioapic, u32 val) if (index >= IOAPIC_NUM_PINS) return; + index = array_index_nospec(index, IOAPIC_NUM_PINS); e = &ioapic->redirtbl[index]; mask_before = e->fields.mask; /* Preserve read-only fields */ old_remote_irr = e->fields.remote_irr; old_delivery_status = e->fields.delivery_status; + old_dest_id = e->fields.dest_id; + old_dest_mode = e->fields.dest_mode; if (ioapic->ioregsel & 1) { e->bits &= 0xffffffff; e->bits |= (u64) val << 32; @@ -321,7 +375,37 @@ static void ioapic_write_indirect(struct kvm_ioapic *ioapic, u32 val) if (e->fields.trig_mode == IOAPIC_LEVEL_TRIG && ioapic->irr & (1 << index)) ioapic_service(ioapic, index, false); - kvm_make_scan_ioapic_request(ioapic->kvm); + if (e->fields.delivery_mode == APIC_DM_FIXED) { + struct kvm_lapic_irq irq; + + irq.shorthand = APIC_DEST_NOSHORT; + irq.vector = e->fields.vector; + irq.delivery_mode = e->fields.delivery_mode << 8; + irq.dest_id = e->fields.dest_id; + irq.dest_mode = + kvm_lapic_irq_dest_mode(!!e->fields.dest_mode); + bitmap_zero(&vcpu_bitmap, 16); + kvm_bitmap_or_dest_vcpus(ioapic->kvm, &irq, + &vcpu_bitmap); + if (old_dest_mode != e->fields.dest_mode || + old_dest_id != e->fields.dest_id) { + /* + * Update vcpu_bitmap with vcpus specified in + * the previous request as well. This is done to + * keep ioapic_handled_vectors synchronized. + */ + irq.dest_id = old_dest_id; + irq.dest_mode = + kvm_lapic_irq_dest_mode( + !!e->fields.dest_mode); + kvm_bitmap_or_dest_vcpus(ioapic->kvm, &irq, + &vcpu_bitmap); + } + kvm_make_scan_ioapic_request_mask(ioapic->kvm, + &vcpu_bitmap); + } else { + kvm_make_scan_ioapic_request(ioapic->kvm); + } break; } } @@ -339,11 +423,11 @@ static int ioapic_service(struct kvm_ioapic *ioapic, int irq, bool line_status) irqe.dest_id = entry->fields.dest_id; irqe.vector = entry->fields.vector; - irqe.dest_mode = entry->fields.dest_mode; + irqe.dest_mode = kvm_lapic_irq_dest_mode(!!entry->fields.dest_mode); irqe.trig_mode = entry->fields.trig_mode; irqe.delivery_mode = entry->fields.delivery_mode << 8; irqe.level = 1; - irqe.shorthand = 0; + irqe.shorthand = APIC_DEST_NOSHORT; irqe.msi_redir_hint = false; if (irqe.trig_mode == IOAPIC_EDGE_TRIG) @@ -415,72 +499,68 @@ static void kvm_ioapic_eoi_inject_work(struct work_struct *work) } #define IOAPIC_SUCCESSIVE_IRQ_MAX_COUNT 10000 - -static void __kvm_ioapic_update_eoi(struct kvm_vcpu *vcpu, - struct kvm_ioapic *ioapic, int vector, int trigger_mode) +static void kvm_ioapic_update_eoi_one(struct kvm_vcpu *vcpu, + struct kvm_ioapic *ioapic, + int trigger_mode, + int pin) { - struct dest_map *dest_map = &ioapic->rtc_status.dest_map; struct kvm_lapic *apic = vcpu->arch.apic; - int i; - - /* RTC special handling */ - if (test_bit(vcpu->vcpu_id, dest_map->map) && - vector == dest_map->vectors[vcpu->vcpu_id]) - rtc_irq_eoi(ioapic, vcpu); - - for (i = 0; i < IOAPIC_NUM_PINS; i++) { - union kvm_ioapic_redirect_entry *ent = &ioapic->redirtbl[i]; + union kvm_ioapic_redirect_entry *ent = &ioapic->redirtbl[pin]; - if (ent->fields.vector != vector) - continue; - - /* - * We are dropping lock while calling ack notifiers because ack - * notifier callbacks for assigned devices call into IOAPIC - * recursively. Since remote_irr is cleared only after call - * to notifiers if the same vector will be delivered while lock - * is dropped it will be put into irr and will be delivered - * after ack notifier returns. - */ - spin_unlock(&ioapic->lock); - kvm_notify_acked_irq(ioapic->kvm, KVM_IRQCHIP_IOAPIC, i); - spin_lock(&ioapic->lock); + /* + * We are dropping lock while calling ack notifiers because ack + * notifier callbacks for assigned devices call into IOAPIC + * recursively. Since remote_irr is cleared only after call + * to notifiers if the same vector will be delivered while lock + * is dropped it will be put into irr and will be delivered + * after ack notifier returns. + */ + spin_unlock(&ioapic->lock); + kvm_notify_acked_irq(ioapic->kvm, KVM_IRQCHIP_IOAPIC, pin); + spin_lock(&ioapic->lock); - if (trigger_mode != IOAPIC_LEVEL_TRIG || - kvm_lapic_get_reg(apic, APIC_SPIV) & APIC_SPIV_DIRECTED_EOI) - continue; + if (trigger_mode != IOAPIC_LEVEL_TRIG || + kvm_lapic_get_reg(apic, APIC_SPIV) & APIC_SPIV_DIRECTED_EOI) + return; - ASSERT(ent->fields.trig_mode == IOAPIC_LEVEL_TRIG); - ent->fields.remote_irr = 0; - if (!ent->fields.mask && (ioapic->irr & (1 << i))) { - ++ioapic->irq_eoi[i]; - if (ioapic->irq_eoi[i] == IOAPIC_SUCCESSIVE_IRQ_MAX_COUNT) { - /* - * Real hardware does not deliver the interrupt - * immediately during eoi broadcast, and this - * lets a buggy guest make slow progress - * even if it does not correctly handle a - * level-triggered interrupt. Emulate this - * behavior if we detect an interrupt storm. - */ - schedule_delayed_work(&ioapic->eoi_inject, HZ / 100); - ioapic->irq_eoi[i] = 0; - trace_kvm_ioapic_delayed_eoi_inj(ent->bits); - } else { - ioapic_service(ioapic, i, false); - } + ASSERT(ent->fields.trig_mode == IOAPIC_LEVEL_TRIG); + ent->fields.remote_irr = 0; + if (!ent->fields.mask && (ioapic->irr & (1 << pin))) { + ++ioapic->irq_eoi[pin]; + if (ioapic->irq_eoi[pin] == IOAPIC_SUCCESSIVE_IRQ_MAX_COUNT) { + /* + * Real hardware does not deliver the interrupt + * immediately during eoi broadcast, and this + * lets a buggy guest make slow progress + * even if it does not correctly handle a + * level-triggered interrupt. Emulate this + * behavior if we detect an interrupt storm. + */ + schedule_delayed_work(&ioapic->eoi_inject, HZ / 100); + ioapic->irq_eoi[pin] = 0; + trace_kvm_ioapic_delayed_eoi_inj(ent->bits); } else { - ioapic->irq_eoi[i] = 0; + ioapic_service(ioapic, pin, false); } + } else { + ioapic->irq_eoi[pin] = 0; } } void kvm_ioapic_update_eoi(struct kvm_vcpu *vcpu, int vector, int trigger_mode) { + int i; struct kvm_ioapic *ioapic = vcpu->kvm->arch.vioapic; spin_lock(&ioapic->lock); - __kvm_ioapic_update_eoi(vcpu, ioapic, vector, trigger_mode); + rtc_irq_eoi(ioapic, vcpu, vector); + for (i = 0; i < IOAPIC_NUM_PINS; i++) { + union kvm_ioapic_redirect_entry *ent = &ioapic->redirtbl[i]; + + if (ent->fields.vector != vector) + continue; + kvm_ioapic_update_eoi_one(vcpu, ioapic, trigger_mode, i); + } spin_unlock(&ioapic->lock); } diff --git a/arch/x86/kvm/ioapic.h b/arch/x86/kvm/ioapic.h index ea1a4e0297da..2fb2e3c80724 100644 --- a/arch/x86/kvm/ioapic.h +++ b/arch/x86/kvm/ioapic.h @@ -116,9 +116,6 @@ static inline int ioapic_in_kernel(struct kvm *kvm) } void kvm_rtc_eoi_tracking_restore_one(struct kvm_vcpu *vcpu); -bool kvm_apic_match_dest(struct kvm_vcpu *vcpu, struct kvm_lapic *source, - int short_hand, unsigned int dest, int dest_mode); -int kvm_apic_compare_prio(struct kvm_vcpu *vcpu1, struct kvm_vcpu *vcpu2); void kvm_ioapic_update_eoi(struct kvm_vcpu *vcpu, int vector, int trigger_mode); int kvm_ioapic_init(struct kvm *kvm); @@ -126,9 +123,6 @@ void kvm_ioapic_destroy(struct kvm *kvm); int kvm_ioapic_set_irq(struct kvm_ioapic *ioapic, int irq, int irq_source_id, int level, bool line_status); void kvm_ioapic_clear_all(struct kvm_ioapic *ioapic, int irq_source_id); -int kvm_irq_delivery_to_apic(struct kvm *kvm, struct kvm_lapic *src, - struct kvm_lapic_irq *irq, - struct dest_map *dest_map); void kvm_get_ioapic(struct kvm *kvm, struct kvm_ioapic_state *state); void kvm_set_ioapic(struct kvm *kvm, struct kvm_ioapic_state *state); void kvm_ioapic_scan_entry(struct kvm_vcpu *vcpu, diff --git a/arch/x86/kvm/irq.h b/arch/x86/kvm/irq.h index 7c6233d37c64..f173ab6b407e 100644 --- a/arch/x86/kvm/irq.h +++ b/arch/x86/kvm/irq.h @@ -113,5 +113,8 @@ int apic_has_pending_timer(struct kvm_vcpu *vcpu); int kvm_setup_default_irq_routing(struct kvm *kvm); int kvm_setup_empty_irq_routing(struct kvm *kvm); +int kvm_irq_delivery_to_apic(struct kvm *kvm, struct kvm_lapic *src, + struct kvm_lapic_irq *irq, + struct dest_map *dest_map); #endif diff --git a/arch/x86/kvm/irq_comm.c b/arch/x86/kvm/irq_comm.c index 8ecd48d31800..79afa0bb5f41 100644 --- a/arch/x86/kvm/irq_comm.c +++ b/arch/x86/kvm/irq_comm.c @@ -52,15 +52,15 @@ int kvm_irq_delivery_to_apic(struct kvm *kvm, struct kvm_lapic *src, unsigned long dest_vcpu_bitmap[BITS_TO_LONGS(KVM_MAX_VCPUS)]; unsigned int dest_vcpus = 0; - if (irq->dest_mode == 0 && irq->dest_id == 0xff && - kvm_lowest_prio_delivery(irq)) { + if (kvm_irq_delivery_to_apic_fast(kvm, src, irq, &r, dest_map)) + return r; + + if (irq->dest_mode == APIC_DEST_PHYSICAL && + irq->dest_id == 0xff && kvm_lowest_prio_delivery(irq)) { printk(KERN_INFO "kvm: apic: phys broadcast and lowest prio\n"); irq->delivery_mode = APIC_DM_FIXED; } - if (kvm_irq_delivery_to_apic_fast(kvm, src, irq, &r, dest_map)) - return r; - memset(dest_vcpu_bitmap, 0, sizeof(dest_vcpu_bitmap)); kvm_for_each_vcpu(i, vcpu, kvm) { @@ -114,13 +114,14 @@ void kvm_set_msi_irq(struct kvm *kvm, struct kvm_kernel_irq_routing_entry *e, irq->dest_id |= MSI_ADDR_EXT_DEST_ID(e->msi.address_hi); irq->vector = (e->msi.data & MSI_DATA_VECTOR_MASK) >> MSI_DATA_VECTOR_SHIFT; - irq->dest_mode = (1 << MSI_ADDR_DEST_MODE_SHIFT) & e->msi.address_lo; + irq->dest_mode = kvm_lapic_irq_dest_mode( + !!((1 << MSI_ADDR_DEST_MODE_SHIFT) & e->msi.address_lo)); irq->trig_mode = (1 << MSI_DATA_TRIGGER_SHIFT) & e->msi.data; irq->delivery_mode = e->msi.data & 0x700; irq->msi_redir_hint = ((e->msi.address_lo & MSI_ADDR_REDIRECTION_LOWPRI) > 0); irq->level = 1; - irq->shorthand = 0; + irq->shorthand = APIC_DEST_NOSHORT; } EXPORT_SYMBOL_GPL(kvm_set_msi_irq); @@ -416,7 +417,8 @@ void kvm_scan_ioapic_routes(struct kvm_vcpu *vcpu, kvm_set_msi_irq(vcpu->kvm, entry, &irq); - if (irq.level && kvm_apic_match_dest(vcpu, NULL, 0, + if (irq.level && + kvm_apic_match_dest(vcpu, NULL, APIC_DEST_NOSHORT, irq.dest_id, irq.dest_mode)) __set_bit(irq.vector, ioapic_handled_vectors); } diff --git a/arch/x86/kvm/kvm_cache_regs.h b/arch/x86/kvm/kvm_cache_regs.h index 1cc6c47dc77e..58767020de41 100644 --- a/arch/x86/kvm/kvm_cache_regs.h +++ b/arch/x86/kvm/kvm_cache_regs.h @@ -37,22 +37,50 @@ BUILD_KVM_GPR_ACCESSORS(r14, R14) BUILD_KVM_GPR_ACCESSORS(r15, R15) #endif -static inline unsigned long kvm_register_read(struct kvm_vcpu *vcpu, - enum kvm_reg reg) +static inline bool kvm_register_is_available(struct kvm_vcpu *vcpu, + enum kvm_reg reg) { - if (!test_bit(reg, (unsigned long *)&vcpu->arch.regs_avail)) + return test_bit(reg, (unsigned long *)&vcpu->arch.regs_avail); +} + +static inline bool kvm_register_is_dirty(struct kvm_vcpu *vcpu, + enum kvm_reg reg) +{ + return test_bit(reg, (unsigned long *)&vcpu->arch.regs_dirty); +} + +static inline void kvm_register_mark_available(struct kvm_vcpu *vcpu, + enum kvm_reg reg) +{ + __set_bit(reg, (unsigned long *)&vcpu->arch.regs_avail); +} + +static inline void kvm_register_mark_dirty(struct kvm_vcpu *vcpu, + enum kvm_reg reg) +{ + __set_bit(reg, (unsigned long *)&vcpu->arch.regs_avail); + __set_bit(reg, (unsigned long *)&vcpu->arch.regs_dirty); +} + +static inline unsigned long kvm_register_read(struct kvm_vcpu *vcpu, int reg) +{ + if (WARN_ON_ONCE((unsigned int)reg >= NR_VCPU_REGS)) + return 0; + + if (!kvm_register_is_available(vcpu, reg)) kvm_x86_ops->cache_reg(vcpu, reg); return vcpu->arch.regs[reg]; } -static inline void kvm_register_write(struct kvm_vcpu *vcpu, - enum kvm_reg reg, +static inline void kvm_register_write(struct kvm_vcpu *vcpu, int reg, unsigned long val) { + if (WARN_ON_ONCE((unsigned int)reg >= NR_VCPU_REGS)) + return; + vcpu->arch.regs[reg] = val; - __set_bit(reg, (unsigned long *)&vcpu->arch.regs_dirty); - __set_bit(reg, (unsigned long *)&vcpu->arch.regs_avail); + kvm_register_mark_dirty(vcpu, reg); } static inline unsigned long kvm_rip_read(struct kvm_vcpu *vcpu) @@ -79,9 +107,8 @@ static inline u64 kvm_pdptr_read(struct kvm_vcpu *vcpu, int index) { might_sleep(); /* on svm */ - if (!test_bit(VCPU_EXREG_PDPTR, - (unsigned long *)&vcpu->arch.regs_avail)) - kvm_x86_ops->cache_reg(vcpu, (enum kvm_reg)VCPU_EXREG_PDPTR); + if (!kvm_register_is_available(vcpu, VCPU_EXREG_PDPTR)) + kvm_x86_ops->cache_reg(vcpu, VCPU_EXREG_PDPTR); return vcpu->arch.walk_mmu->pdptrs[index]; } @@ -109,8 +136,8 @@ static inline ulong kvm_read_cr4_bits(struct kvm_vcpu *vcpu, ulong mask) static inline ulong kvm_read_cr3(struct kvm_vcpu *vcpu) { - if (!test_bit(VCPU_EXREG_CR3, (ulong *)&vcpu->arch.regs_avail)) - kvm_x86_ops->decache_cr3(vcpu); + if (!kvm_register_is_available(vcpu, VCPU_EXREG_CR3)) + kvm_x86_ops->cache_reg(vcpu, VCPU_EXREG_CR3); return vcpu->arch.cr3; } diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index 685d17c11461..afcd30d44cbb 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -56,17 +56,17 @@ #define APIC_VERSION (0x14UL | ((KVM_APIC_LVT_NUM - 1) << 16)) #define LAPIC_MMIO_LENGTH (1 << 12) /* followed define is not in apicdef.h */ -#define APIC_SHORT_MASK 0xc0000 -#define APIC_DEST_NOSHORT 0x0 -#define APIC_DEST_MASK 0x800 #define MAX_APIC_VECTOR 256 #define APIC_VECTORS_PER_REG 32 #define APIC_BROADCAST 0xFF #define X2APIC_BROADCAST 0xFFFFFFFFul -#define LAPIC_TIMER_ADVANCE_ADJUST_DONE 100 -#define LAPIC_TIMER_ADVANCE_ADJUST_INIT 1000 +static bool lapic_timer_advance_dynamic __read_mostly; +#define LAPIC_TIMER_ADVANCE_ADJUST_MIN 100 /* clock cycles */ +#define LAPIC_TIMER_ADVANCE_ADJUST_MAX 10000 /* clock cycles */ +#define LAPIC_TIMER_ADVANCE_NS_INIT 1000 +#define LAPIC_TIMER_ADVANCE_NS_MAX 5000 /* step-by-step approximation to mitigate fluctuation */ #define LAPIC_TIMER_ADVANCE_ADJUST_STEP 8 @@ -108,11 +108,6 @@ static inline int apic_enabled(struct kvm_lapic *apic) (LVT_MASK | APIC_MODE_MASK | APIC_INPUT_POLARITY | \ APIC_LVT_REMOTE_IRR | APIC_LVT_LEVEL_TRIGGER) -static inline u8 kvm_xapic_id(struct kvm_lapic *apic) -{ - return kvm_lapic_get_reg(apic, APIC_ID) >> 24; -} - static inline u32 kvm_x2apic_id(struct kvm_lapic *apic) { return apic->vcpu->vcpu_id; @@ -216,6 +211,9 @@ static void recalculate_apic_map(struct kvm *kvm) if (!apic_x2apic_mode(apic) && !new->phys_map[xapic_id]) new->phys_map[xapic_id] = apic; + if (!kvm_apic_sw_enabled(apic)) + continue; + ldr = kvm_lapic_get_reg(apic, APIC_LDR); if (apic_x2apic_mode(apic)) { @@ -258,6 +256,8 @@ static inline void apic_set_spiv(struct kvm_lapic *apic, u32 val) static_key_slow_dec_deferred(&apic_sw_disabled); else static_key_slow_inc(&apic_sw_disabled.key); + + recalculate_apic_map(apic->vcpu->kvm); } } @@ -554,60 +554,53 @@ int kvm_apic_set_irq(struct kvm_vcpu *vcpu, struct kvm_lapic_irq *irq, irq->level, irq->trig_mode, dest_map); } +static int __pv_send_ipi(unsigned long *ipi_bitmap, struct kvm_apic_map *map, + struct kvm_lapic_irq *irq, u32 min) +{ + int i, count = 0; + struct kvm_vcpu *vcpu; + + if (min > map->max_apic_id) + return 0; + + for_each_set_bit(i, ipi_bitmap, + min((u32)BITS_PER_LONG, (map->max_apic_id - min + 1))) { + if (map->phys_map[min + i]) { + vcpu = map->phys_map[min + i]->vcpu; + count += kvm_apic_set_irq(vcpu, irq, NULL); + } + } + + return count; +} + int kvm_pv_send_ipi(struct kvm *kvm, unsigned long ipi_bitmap_low, unsigned long ipi_bitmap_high, u32 min, unsigned long icr, int op_64_bit) { - int i; struct kvm_apic_map *map; - struct kvm_vcpu *vcpu; struct kvm_lapic_irq irq = {0}; int cluster_size = op_64_bit ? 64 : 32; - int count = 0; + int count; + + if (icr & (APIC_DEST_MASK | APIC_SHORT_MASK)) + return -KVM_EINVAL; irq.vector = icr & APIC_VECTOR_MASK; irq.delivery_mode = icr & APIC_MODE_MASK; irq.level = (icr & APIC_INT_ASSERT) != 0; irq.trig_mode = icr & APIC_INT_LEVELTRIG; - if (icr & APIC_DEST_MASK) - return -KVM_EINVAL; - if (icr & APIC_SHORT_MASK) - return -KVM_EINVAL; - rcu_read_lock(); map = rcu_dereference(kvm->arch.apic_map); - if (unlikely(!map)) { - count = -EOPNOTSUPP; - goto out; + count = -EOPNOTSUPP; + if (likely(map)) { + count = __pv_send_ipi(&ipi_bitmap_low, map, &irq, min); + min += cluster_size; + count += __pv_send_ipi(&ipi_bitmap_high, map, &irq, min); } - if (min > map->max_apic_id) - goto out; - /* Bits above cluster_size are masked in the caller. */ - for_each_set_bit(i, &ipi_bitmap_low, - min((u32)BITS_PER_LONG, (map->max_apic_id - min + 1))) { - if (map->phys_map[min + i]) { - vcpu = map->phys_map[min + i]->vcpu; - count += kvm_apic_set_irq(vcpu, &irq, NULL); - } - } - - min += cluster_size; - - if (min > map->max_apic_id) - goto out; - - for_each_set_bit(i, &ipi_bitmap_high, - min((u32)BITS_PER_LONG, (map->max_apic_id - min + 1))) { - if (map->phys_map[min + i]) { - vcpu = map->phys_map[min + i]->vcpu; - count += kvm_apic_set_irq(vcpu, &irq, NULL); - } - } - -out: rcu_read_unlock(); return count; } @@ -796,13 +789,13 @@ static u32 kvm_apic_mda(struct kvm_vcpu *vcpu, unsigned int dest_id, } bool kvm_apic_match_dest(struct kvm_vcpu *vcpu, struct kvm_lapic *source, - int short_hand, unsigned int dest, int dest_mode) + int shorthand, unsigned int dest, int dest_mode) { struct kvm_lapic *target = vcpu->arch.apic; u32 mda = kvm_apic_mda(vcpu, dest, source, target); ASSERT(target); - switch (short_hand) { + switch (shorthand) { case APIC_DEST_NOSHORT: if (dest_mode == APIC_DEST_PHYSICAL) return kvm_apic_match_physical_addr(target, mda); @@ -971,12 +964,12 @@ bool kvm_irq_delivery_to_apic_fast(struct kvm *kvm, struct kvm_lapic *src, } /* - * This routine tries to handler interrupts in posted mode, here is how + * This routine tries to handle interrupts in posted mode, here is how * it deals with different cases: * - For single-destination interrupts, handle it in posted mode * - Else if vector hashing is enabled and it is a lowest-priority * interrupt, handle it in posted mode and use the following mechanism - * to find the destinaiton vCPU. + * to find the destination vCPU. * 1. For lowest-priority interrupts, store all the possible * destination vCPUs in an array. * 2. Use "guest vector % max number of destination vCPUs" to find @@ -1087,9 +1080,6 @@ static int __apic_accept_irq(struct kvm_lapic *apic, int delivery_mode, result = 1; /* assumes that there are only KVM_APIC_INIT/SIPI */ apic->pending_events = (1UL << KVM_APIC_INIT); - /* make sure pending_events is visible before sending - * the request */ - smp_wmb(); kvm_make_request(KVM_REQ_EVENT, vcpu); kvm_vcpu_kick(vcpu); } @@ -1121,6 +1111,50 @@ static int __apic_accept_irq(struct kvm_lapic *apic, int delivery_mode, return result; } +/* + * This routine identifies the destination vcpus mask meant to receive the + * IOAPIC interrupts. It either uses kvm_apic_map_get_dest_lapic() to find + * out the destination vcpus array and set the bitmap or it traverses to + * each available vcpu to identify the same. + */ +void kvm_bitmap_or_dest_vcpus(struct kvm *kvm, struct kvm_lapic_irq *irq, + unsigned long *vcpu_bitmap) +{ + struct kvm_lapic **dest_vcpu = NULL; + struct kvm_lapic *src = NULL; + struct kvm_apic_map *map; + struct kvm_vcpu *vcpu; + unsigned long bitmap; + int i, vcpu_idx; + bool ret; + + rcu_read_lock(); + map = rcu_dereference(kvm->arch.apic_map); + + ret = kvm_apic_map_get_dest_lapic(kvm, &src, irq, map, &dest_vcpu, + &bitmap); + if (ret) { + for_each_set_bit(i, &bitmap, 16) { + if (!dest_vcpu[i]) + continue; + vcpu_idx = dest_vcpu[i]->vcpu->vcpu_idx; + __set_bit(vcpu_idx, vcpu_bitmap); + } + } else { + kvm_for_each_vcpu(i, vcpu, kvm) { + if (!kvm_apic_present(vcpu)) + continue; + if (!kvm_apic_match_dest(vcpu, NULL, + irq->shorthand, + irq->dest_id, + irq->dest_mode)) + continue; + __set_bit(i, vcpu_bitmap); + } + } + rcu_read_unlock(); +} + int kvm_apic_compare_prio(struct kvm_vcpu *vcpu1, struct kvm_vcpu *vcpu2) { return vcpu1->arch.apic_arb_prio - vcpu2->arch.apic_arb_prio; @@ -1193,10 +1227,8 @@ void kvm_apic_set_eoi_accelerated(struct kvm_vcpu *vcpu, int vector) } EXPORT_SYMBOL_GPL(kvm_apic_set_eoi_accelerated); -static void apic_send_ipi(struct kvm_lapic *apic) +static void apic_send_ipi(struct kvm_lapic *apic, u32 icr_low, u32 icr_high) { - u32 icr_low = kvm_lapic_get_reg(apic, APIC_ICR); - u32 icr_high = kvm_lapic_get_reg(apic, APIC_ICR2); struct kvm_lapic_irq irq; irq.vector = icr_low & APIC_VECTOR_MASK; @@ -1482,26 +1514,25 @@ static inline void adjust_lapic_timer_advance(struct kvm_vcpu *vcpu, u32 timer_advance_ns = apic->lapic_timer.timer_advance_ns; u64 ns; + /* Do not adjust for tiny fluctuations or large random spikes. */ + if (abs(advance_expire_delta) > LAPIC_TIMER_ADVANCE_ADJUST_MAX || + abs(advance_expire_delta) < LAPIC_TIMER_ADVANCE_ADJUST_MIN) + return; + /* too early */ if (advance_expire_delta < 0) { ns = -advance_expire_delta * 1000000ULL; do_div(ns, vcpu->arch.virtual_tsc_khz); - timer_advance_ns -= min((u32)ns, - timer_advance_ns / LAPIC_TIMER_ADVANCE_ADJUST_STEP); + timer_advance_ns -= ns/LAPIC_TIMER_ADVANCE_ADJUST_STEP; } else { /* too late */ ns = advance_expire_delta * 1000000ULL; do_div(ns, vcpu->arch.virtual_tsc_khz); - timer_advance_ns += min((u32)ns, - timer_advance_ns / LAPIC_TIMER_ADVANCE_ADJUST_STEP); + timer_advance_ns += ns/LAPIC_TIMER_ADVANCE_ADJUST_STEP; } - if (abs(advance_expire_delta) < LAPIC_TIMER_ADVANCE_ADJUST_DONE) - apic->lapic_timer.timer_advance_adjust_done = true; - if (unlikely(timer_advance_ns > 5000)) { - timer_advance_ns = LAPIC_TIMER_ADVANCE_ADJUST_INIT; - apic->lapic_timer.timer_advance_adjust_done = false; - } + if (unlikely(timer_advance_ns > LAPIC_TIMER_ADVANCE_NS_MAX)) + timer_advance_ns = LAPIC_TIMER_ADVANCE_NS_INIT; apic->lapic_timer.timer_advance_ns = timer_advance_ns; } @@ -1521,7 +1552,7 @@ static void __kvm_wait_lapic_expire(struct kvm_vcpu *vcpu) if (guest_tsc < tsc_deadline) __wait_lapic_expire(vcpu, tsc_deadline - guest_tsc); - if (unlikely(!apic->lapic_timer.timer_advance_adjust_done)) + if (lapic_timer_advance_dynamic) adjust_lapic_timer_advance(vcpu, apic->lapic_timer.advance_expire_delta); } @@ -1537,9 +1568,9 @@ static void kvm_apic_inject_pending_timer_irqs(struct kvm_lapic *apic) struct kvm_timer *ktimer = &apic->lapic_timer; kvm_apic_local_deliver(apic, APIC_LVTT); - if (apic_lvtt_tscdeadline(apic)) + if (apic_lvtt_tscdeadline(apic)) { ktimer->tscdeadline = 0; - if (apic_lvtt_oneshot(apic)) { + } else if (apic_lvtt_oneshot(apic)) { ktimer->tscdeadline = 0; ktimer->target_expiration = 0; } @@ -1593,7 +1624,7 @@ static void start_sw_tscdeadline(struct kvm_lapic *apic) likely(ns > apic->lapic_timer.timer_advance_ns)) { expire = ktime_add_ns(now, ns); expire = ktime_sub_ns(expire, ktimer->timer_advance_ns); - hrtimer_start(&ktimer->timer, expire, HRTIMER_MODE_ABS); + hrtimer_start(&ktimer->timer, expire, HRTIMER_MODE_ABS_HARD); } else apic_timer_expired(apic); @@ -1909,8 +1940,9 @@ int kvm_lapic_reg_write(struct kvm_lapic *apic, u32 reg, u32 val) } case APIC_ICR: /* No delay here, so we always clear the pending bit */ - kvm_lapic_set_reg(apic, APIC_ICR, val & ~(1 << 12)); - apic_send_ipi(apic); + val &= ~(1 << 12); + apic_send_ipi(apic, val, kvm_lapic_get_reg(apic, APIC_ICR2)); + kvm_lapic_set_reg(apic, APIC_ICR, val); break; case APIC_ICR2: @@ -1925,15 +1957,20 @@ int kvm_lapic_reg_write(struct kvm_lapic *apic, u32 reg, u32 val) case APIC_LVTTHMR: case APIC_LVTPC: case APIC_LVT1: - case APIC_LVTERR: + case APIC_LVTERR: { /* TODO: Check vector */ + size_t size; + u32 index; + if (!kvm_apic_sw_enabled(apic)) val |= APIC_LVT_MASKED; - - val &= apic_lvt_mask[(reg - APIC_LVTT) >> 4]; + size = ARRAY_SIZE(apic_lvt_mask); + index = array_index_nospec( + (reg - APIC_LVTT) >> 4, size); + val &= apic_lvt_mask[index]; kvm_lapic_set_reg(apic, reg, val); - break; + } case APIC_LVTT: if (!kvm_apic_sw_enabled(apic)) @@ -2147,6 +2184,21 @@ void kvm_lapic_set_base(struct kvm_vcpu *vcpu, u64 value) pr_warn_once("APIC base relocation is unsupported by KVM"); } +void kvm_apic_update_apicv(struct kvm_vcpu *vcpu) +{ + struct kvm_lapic *apic = vcpu->arch.apic; + + if (vcpu->arch.apicv_active) { + /* irr_pending is always true when apicv is activated. */ + apic->irr_pending = true; + apic->isr_count = 1; + } else { + apic->irr_pending = (apic_search_irr(apic) != -1); + apic->isr_count = count_vectors(apic->regs + APIC_ISR); + } +} +EXPORT_SYMBOL_GPL(kvm_apic_update_apicv); + void kvm_lapic_reset(struct kvm_vcpu *vcpu, bool init_event) { struct kvm_lapic *apic = vcpu->arch.apic; @@ -2189,8 +2241,7 @@ void kvm_lapic_reset(struct kvm_vcpu *vcpu, bool init_event) kvm_lapic_set_reg(apic, APIC_ISR + 0x10 * i, 0); kvm_lapic_set_reg(apic, APIC_TMR + 0x10 * i, 0); } - apic->irr_pending = vcpu->arch.apicv_active; - apic->isr_count = vcpu->arch.apicv_active ? 1 : 0; + kvm_apic_update_apicv(vcpu); apic->highest_isr_cache = -1; update_divide_count(apic); atomic_set(&apic->lapic_timer.pending, 0); @@ -2294,17 +2345,16 @@ int kvm_create_lapic(struct kvm_vcpu *vcpu, int timer_advance_ns) apic->vcpu = vcpu; hrtimer_init(&apic->lapic_timer.timer, CLOCK_MONOTONIC, - HRTIMER_MODE_ABS); + HRTIMER_MODE_ABS_HARD); apic->lapic_timer.timer.function = apic_timer_fn; if (timer_advance_ns == -1) { - apic->lapic_timer.timer_advance_ns = LAPIC_TIMER_ADVANCE_ADJUST_INIT; - apic->lapic_timer.timer_advance_adjust_done = false; + apic->lapic_timer.timer_advance_ns = LAPIC_TIMER_ADVANCE_NS_INIT; + lapic_timer_advance_dynamic = true; } else { apic->lapic_timer.timer_advance_ns = timer_advance_ns; - apic->lapic_timer.timer_advance_adjust_done = true; + lapic_timer_advance_dynamic = false; } - /* * APIC is created enabled. This will prevent kvm_lapic_set_base from * thinking that APIC state has changed. @@ -2336,14 +2386,13 @@ int kvm_apic_has_interrupt(struct kvm_vcpu *vcpu) int kvm_apic_accept_pic_intr(struct kvm_vcpu *vcpu) { u32 lvt0 = kvm_lapic_get_reg(vcpu->arch.apic, APIC_LVT0); - int r = 0; if (!kvm_apic_hw_enabled(vcpu->arch.apic)) - r = 1; + return 1; if ((lvt0 & APIC_LVT_MASKED) == 0 && GET_APIC_DELIVERY_MODE(lvt0) == APIC_MODE_EXTINT) - r = 1; - return r; + return 1; + return 0; } void kvm_inject_apic_timer_irqs(struct kvm_vcpu *vcpu) @@ -2449,9 +2498,7 @@ int kvm_apic_set_state(struct kvm_vcpu *vcpu, struct kvm_lapic_state *s) apic_manage_nmi_watchdog(apic, kvm_lapic_get_reg(apic, APIC_LVT0)); update_divide_count(apic); start_apic_timer(apic); - apic->irr_pending = true; - apic->isr_count = vcpu->arch.apicv_active ? - 1 : count_vectors(apic->regs + APIC_ISR); + kvm_apic_update_apicv(vcpu); apic->highest_isr_cache = -1; if (vcpu->arch.apicv_active) { kvm_x86_ops->apicv_post_state_restore(vcpu); @@ -2479,7 +2526,7 @@ void __kvm_migrate_apic_timer(struct kvm_vcpu *vcpu) timer = &vcpu->arch.apic->lapic_timer.timer; if (hrtimer_cancel(timer)) - hrtimer_start_expires(timer, HRTIMER_MODE_ABS); + hrtimer_start_expires(timer, HRTIMER_MODE_ABS_HARD); } /* @@ -2702,11 +2749,14 @@ void kvm_apic_accept_events(struct kvm_vcpu *vcpu) return; /* - * INITs are latched while in SMM. Because an SMM CPU cannot - * be in KVM_MP_STATE_INIT_RECEIVED state, just eat SIPIs - * and delay processing of INIT until the next RSM. + * INITs are latched while CPU is in specific states + * (SMM, VMX non-root mode, SVM with GIF=0). + * Because a CPU cannot be in these states immediately + * after it has processed an INIT signal (and thus in + * KVM_MP_STATE_INIT_RECEIVED state), just eat SIPIs + * and leave the INIT pending. */ - if (is_smm(vcpu)) { + if (kvm_vcpu_latch_init(vcpu)) { WARN_ON_ONCE(vcpu->arch.mp_state == KVM_MP_STATE_INIT_RECEIVED); if (test_bit(KVM_APIC_SIPI, &apic->pending_events)) clear_bit(KVM_APIC_SIPI, &apic->pending_events); diff --git a/arch/x86/kvm/lapic.h b/arch/x86/kvm/lapic.h index 50053d2b8b7b..ec6fbfe325cf 100644 --- a/arch/x86/kvm/lapic.h +++ b/arch/x86/kvm/lapic.h @@ -10,8 +10,9 @@ #define KVM_APIC_SIPI 1 #define KVM_APIC_LVT_NUM 6 -#define KVM_APIC_SHORT_MASK 0xc0000 -#define KVM_APIC_DEST_MASK 0x800 +#define APIC_SHORT_MASK 0xc0000 +#define APIC_DEST_NOSHORT 0x0 +#define APIC_DEST_MASK 0x800 #define APIC_BUS_CYCLE_NS 1 #define APIC_BUS_FREQUENCY (1000000000ULL / APIC_BUS_CYCLE_NS) @@ -35,7 +36,6 @@ struct kvm_timer { s64 advance_expire_delta; atomic_t pending; /* accumulated triggered timers */ bool hv_timer_in_use; - bool timer_advance_adjust_done; }; struct kvm_lapic { @@ -83,14 +83,15 @@ int kvm_lapic_reg_write(struct kvm_lapic *apic, u32 reg, u32 val); int kvm_lapic_reg_read(struct kvm_lapic *apic, u32 offset, int len, void *data); bool kvm_apic_match_dest(struct kvm_vcpu *vcpu, struct kvm_lapic *source, - int short_hand, unsigned int dest, int dest_mode); - + int shorthand, unsigned int dest, int dest_mode); +int kvm_apic_compare_prio(struct kvm_vcpu *vcpu1, struct kvm_vcpu *vcpu2); bool __kvm_apic_update_irr(u32 *pir, void *regs, int *max_irr); bool kvm_apic_update_irr(struct kvm_vcpu *vcpu, u32 *pir, int *max_irr); void kvm_apic_update_ppr(struct kvm_vcpu *vcpu); int kvm_apic_set_irq(struct kvm_vcpu *vcpu, struct kvm_lapic_irq *irq, struct dest_map *dest_map); int kvm_apic_local_deliver(struct kvm_lapic *apic, int lvt_type); +void kvm_apic_update_apicv(struct kvm_vcpu *vcpu); bool kvm_irq_delivery_to_apic_fast(struct kvm *kvm, struct kvm_lapic *src, struct kvm_lapic_irq *irq, int *r, struct dest_map *dest_map); @@ -227,6 +228,9 @@ bool kvm_apic_pending_eoi(struct kvm_vcpu *vcpu, int vector); void kvm_wait_lapic_expire(struct kvm_vcpu *vcpu); +void kvm_bitmap_or_dest_vcpus(struct kvm *kvm, struct kvm_lapic_irq *irq, + unsigned long *vcpu_bitmap); + bool kvm_intr_is_single_vcpu_fast(struct kvm *kvm, struct kvm_lapic_irq *irq, struct kvm_vcpu **dest_vcpu); int kvm_vector_to_index(u32 vector, u32 dest_vcpus, @@ -243,4 +247,9 @@ static inline enum lapic_mode kvm_apic_mode(u64 apic_base) return apic_base & (MSR_IA32_APICBASE_ENABLE | X2APIC_ENABLE); } +static inline u8 kvm_xapic_id(struct kvm_lapic *apic) +{ + return kvm_lapic_get_reg(apic, APIC_ID) >> 24; +} + #endif diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h index 54c2a377795b..a647601c9e1c 100644 --- a/arch/x86/kvm/mmu.h +++ b/arch/x86/kvm/mmu.h @@ -51,7 +51,7 @@ static inline u64 rsvd_bits(int s, int e) return ((1ULL << (e - s + 1)) - 1) << s; } -void kvm_mmu_set_mmio_spte_mask(u64 mmio_mask, u64 mmio_value); +void kvm_mmu_set_mmio_spte_mask(u64 mmio_mask, u64 mmio_value, u64 access_mask); void reset_shadow_zero_bits_mask(struct kvm_vcpu *vcpu, struct kvm_mmu *context); @@ -102,6 +102,19 @@ static inline void kvm_mmu_load_cr3(struct kvm_vcpu *vcpu) kvm_get_active_pcid(vcpu)); } +int kvm_tdp_page_fault(struct kvm_vcpu *vcpu, gpa_t gpa, u32 error_code, + bool prefault); + +static inline int kvm_mmu_do_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, + u32 err, bool prefault) +{ +#ifdef CONFIG_RETPOLINE + if (likely(vcpu->arch.mmu->page_fault == kvm_tdp_page_fault)) + return kvm_tdp_page_fault(vcpu, cr2_or_gpa, err, prefault); +#endif + return vcpu->arch.mmu->page_fault(vcpu, cr2_or_gpa, err, prefault); +} + /* * Currently, we have two sorts of write-protection, a) the first one * write-protects guest page to sync the guest modification, b) another one is @@ -210,4 +223,8 @@ void kvm_mmu_gfn_allow_lpage(struct kvm_memory_slot *slot, gfn_t gfn); bool kvm_mmu_slot_gfn_write_protect(struct kvm *kvm, struct kvm_memory_slot *slot, u64 gfn); int kvm_arch_write_log_dirty(struct kvm_vcpu *vcpu); + +int kvm_mmu_post_init_vm(struct kvm *kvm); +void kvm_mmu_pre_destroy_vm(struct kvm *kvm); + #endif diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu/mmu.c index 24843cf49579..87e9ba27ada1 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -37,9 +37,10 @@ #include <linux/uaccess.h> #include <linux/hash.h> #include <linux/kern_levels.h> +#include <linux/kthread.h> #include <asm/page.h> -#include <asm/pat.h> +#include <asm/memtype.h> #include <asm/cmpxchg.h> #include <asm/e820/api.h> #include <asm/io.h> @@ -47,6 +48,35 @@ #include <asm/kvm_page_track.h> #include "trace.h" +extern bool itlb_multihit_kvm_mitigation; + +static int __read_mostly nx_huge_pages = -1; +#ifdef CONFIG_PREEMPT_RT +/* Recovery can cause latency spikes, disable it for PREEMPT_RT. */ +static uint __read_mostly nx_huge_pages_recovery_ratio = 0; +#else +static uint __read_mostly nx_huge_pages_recovery_ratio = 60; +#endif + +static int set_nx_huge_pages(const char *val, const struct kernel_param *kp); +static int set_nx_huge_pages_recovery_ratio(const char *val, const struct kernel_param *kp); + +static struct kernel_param_ops nx_huge_pages_ops = { + .set = set_nx_huge_pages, + .get = param_get_bool, +}; + +static struct kernel_param_ops nx_huge_pages_recovery_ratio_ops = { + .set = set_nx_huge_pages_recovery_ratio, + .get = param_get_uint, +}; + +module_param_cb(nx_huge_pages, &nx_huge_pages_ops, &nx_huge_pages, 0644); +__MODULE_PARM_TYPE(nx_huge_pages, "bool"); +module_param_cb(nx_huge_pages_recovery_ratio, &nx_huge_pages_recovery_ratio_ops, + &nx_huge_pages_recovery_ratio, 0644); +__MODULE_PARM_TYPE(nx_huge_pages_recovery_ratio, "uint"); + /* * When setting this variable to true it enables Two-Dimensional-Paging * where the hardware walks 2 page tables: @@ -83,7 +113,17 @@ module_param(dbg, bool, 0644); #define PTE_PREFETCH_NUM 8 #define PT_FIRST_AVAIL_BITS_SHIFT 10 -#define PT64_SECOND_AVAIL_BITS_SHIFT 52 +#define PT64_SECOND_AVAIL_BITS_SHIFT 54 + +/* + * The mask used to denote special SPTEs, which can be either MMIO SPTEs or + * Access Tracking SPTEs. + */ +#define SPTE_SPECIAL_MASK (3ULL << 52) +#define SPTE_AD_ENABLED_MASK (0ULL << 52) +#define SPTE_AD_DISABLED_MASK (1ULL << 52) +#define SPTE_AD_WRPROT_ONLY_MASK (2ULL << 52) +#define SPTE_MMIO_MASK (3ULL << 52) #define PT64_LEVEL_BITS 9 @@ -214,16 +254,16 @@ static u64 __read_mostly shadow_accessed_mask; static u64 __read_mostly shadow_dirty_mask; static u64 __read_mostly shadow_mmio_mask; static u64 __read_mostly shadow_mmio_value; +static u64 __read_mostly shadow_mmio_access_mask; static u64 __read_mostly shadow_present_mask; static u64 __read_mostly shadow_me_mask; /* - * SPTEs used by MMUs without A/D bits are marked with shadow_acc_track_value. - * Non-present SPTEs with shadow_acc_track_value set are in place for access - * tracking. + * SPTEs used by MMUs without A/D bits are marked with SPTE_AD_DISABLED_MASK; + * shadow_acc_track_mask is the set of bits to be cleared in non-accessed + * pages. */ static u64 __read_mostly shadow_acc_track_mask; -static const u64 shadow_acc_track_value = SPTE_SPECIAL_MASK; /* * The mask/shift to use for saving the original R/X bits when marking the PTE @@ -299,34 +339,63 @@ static void kvm_flush_remote_tlbs_with_address(struct kvm *kvm, kvm_flush_remote_tlbs_with_range(kvm, &range); } -void kvm_mmu_set_mmio_spte_mask(u64 mmio_mask, u64 mmio_value) +void kvm_mmu_set_mmio_spte_mask(u64 mmio_mask, u64 mmio_value, u64 access_mask) { + BUG_ON((u64)(unsigned)access_mask != access_mask); BUG_ON((mmio_mask & mmio_value) != mmio_value); - shadow_mmio_value = mmio_value | SPTE_SPECIAL_MASK; + shadow_mmio_value = mmio_value | SPTE_MMIO_MASK; shadow_mmio_mask = mmio_mask | SPTE_SPECIAL_MASK; + shadow_mmio_access_mask = access_mask; } EXPORT_SYMBOL_GPL(kvm_mmu_set_mmio_spte_mask); +static bool is_mmio_spte(u64 spte) +{ + return (spte & shadow_mmio_mask) == shadow_mmio_value; +} + static inline bool sp_ad_disabled(struct kvm_mmu_page *sp) { return sp->role.ad_disabled; } +static inline bool kvm_vcpu_ad_need_write_protect(struct kvm_vcpu *vcpu) +{ + /* + * When using the EPT page-modification log, the GPAs in the log + * would come from L2 rather than L1. Therefore, we need to rely + * on write protection to record dirty pages. This also bypasses + * PML, since writes now result in a vmexit. + */ + return vcpu->arch.mmu == &vcpu->arch.guest_mmu; +} + static inline bool spte_ad_enabled(u64 spte) { - MMU_WARN_ON((spte & shadow_mmio_mask) == shadow_mmio_value); - return !(spte & shadow_acc_track_value); + MMU_WARN_ON(is_mmio_spte(spte)); + return (spte & SPTE_SPECIAL_MASK) != SPTE_AD_DISABLED_MASK; +} + +static inline bool spte_ad_need_write_protect(u64 spte) +{ + MMU_WARN_ON(is_mmio_spte(spte)); + return (spte & SPTE_SPECIAL_MASK) != SPTE_AD_ENABLED_MASK; +} + +static bool is_nx_huge_page_enabled(void) +{ + return READ_ONCE(nx_huge_pages); } static inline u64 spte_shadow_accessed_mask(u64 spte) { - MMU_WARN_ON((spte & shadow_mmio_mask) == shadow_mmio_value); + MMU_WARN_ON(is_mmio_spte(spte)); return spte_ad_enabled(spte) ? shadow_accessed_mask : 0; } static inline u64 spte_shadow_dirty_mask(u64 spte) { - MMU_WARN_ON((spte & shadow_mmio_mask) == shadow_mmio_value); + MMU_WARN_ON(is_mmio_spte(spte)); return spte_ad_enabled(spte) ? shadow_dirty_mask : 0; } @@ -349,22 +418,24 @@ static inline bool is_access_track_spte(u64 spte) * requires a full MMU zap). The flag is instead explicitly queried when * checking for MMIO spte cache hits. */ -#define MMIO_SPTE_GEN_MASK GENMASK_ULL(18, 0) +#define MMIO_SPTE_GEN_MASK GENMASK_ULL(17, 0) #define MMIO_SPTE_GEN_LOW_START 3 #define MMIO_SPTE_GEN_LOW_END 11 #define MMIO_SPTE_GEN_LOW_MASK GENMASK_ULL(MMIO_SPTE_GEN_LOW_END, \ MMIO_SPTE_GEN_LOW_START) -#define MMIO_SPTE_GEN_HIGH_START 52 -#define MMIO_SPTE_GEN_HIGH_END 61 +#define MMIO_SPTE_GEN_HIGH_START PT64_SECOND_AVAIL_BITS_SHIFT +#define MMIO_SPTE_GEN_HIGH_END 62 #define MMIO_SPTE_GEN_HIGH_MASK GENMASK_ULL(MMIO_SPTE_GEN_HIGH_END, \ MMIO_SPTE_GEN_HIGH_START) + static u64 generation_mmio_spte_mask(u64 gen) { u64 mask; WARN_ON(gen & ~MMIO_SPTE_GEN_MASK); + BUILD_BUG_ON((MMIO_SPTE_GEN_HIGH_MASK | MMIO_SPTE_GEN_LOW_MASK) & SPTE_SPECIAL_MASK); mask = (gen << MMIO_SPTE_GEN_LOW_START) & MMIO_SPTE_GEN_LOW_MASK; mask |= (gen << MMIO_SPTE_GEN_HIGH_START) & MMIO_SPTE_GEN_HIGH_MASK; @@ -375,35 +446,37 @@ static u64 get_mmio_spte_generation(u64 spte) { u64 gen; - spte &= ~shadow_mmio_mask; - gen = (spte & MMIO_SPTE_GEN_LOW_MASK) >> MMIO_SPTE_GEN_LOW_START; gen |= (spte & MMIO_SPTE_GEN_HIGH_MASK) >> MMIO_SPTE_GEN_HIGH_START; return gen; } -static void mark_mmio_spte(struct kvm_vcpu *vcpu, u64 *sptep, u64 gfn, - unsigned access) +static u64 make_mmio_spte(struct kvm_vcpu *vcpu, u64 gfn, unsigned int access) { + u64 gen = kvm_vcpu_memslots(vcpu)->generation & MMIO_SPTE_GEN_MASK; u64 mask = generation_mmio_spte_mask(gen); u64 gpa = gfn << PAGE_SHIFT; - access &= ACC_WRITE_MASK | ACC_USER_MASK; + access &= shadow_mmio_access_mask; mask |= shadow_mmio_value | access; mask |= gpa | shadow_nonpresent_or_rsvd_mask; mask |= (gpa & shadow_nonpresent_or_rsvd_mask) << shadow_nonpresent_or_rsvd_mask_len; - page_header(__pa(sptep))->mmio_cached = true; - - trace_mark_mmio_spte(sptep, gfn, access, gen); - mmu_spte_set(sptep, mask); + return mask; } -static bool is_mmio_spte(u64 spte) +static void mark_mmio_spte(struct kvm_vcpu *vcpu, u64 *sptep, u64 gfn, + unsigned int access) { - return (spte & shadow_mmio_mask) == shadow_mmio_value; + u64 mask = make_mmio_spte(vcpu, gfn, access); + unsigned int gen = get_mmio_spte_generation(mask); + + access = mask & ACC_ALL; + + trace_mark_mmio_spte(sptep, gfn, access, gen); + mmu_spte_set(sptep, mask); } static gfn_t get_mmio_spte_gfn(u64 spte) @@ -418,12 +491,11 @@ static gfn_t get_mmio_spte_gfn(u64 spte) static unsigned get_mmio_spte_access(u64 spte) { - u64 mask = generation_mmio_spte_mask(MMIO_SPTE_GEN_MASK) | shadow_mmio_mask; - return (spte & ~mask) & ~PAGE_MASK; + return spte & shadow_mmio_access_mask; } static bool set_mmio_spte(struct kvm_vcpu *vcpu, u64 *sptep, gfn_t gfn, - kvm_pfn_t pfn, unsigned access) + kvm_pfn_t pfn, unsigned int access) { if (unlikely(is_noslot_pfn(pfn))) { mark_mmio_spte(vcpu, sptep, gfn, access); @@ -461,7 +533,7 @@ void kvm_mmu_set_mask_ptes(u64 user_mask, u64 accessed_mask, { BUG_ON(!dirty_mask != !accessed_mask); BUG_ON(!accessed_mask && !acc_track_mask); - BUG_ON(acc_track_mask & shadow_acc_track_value); + BUG_ON(acc_track_mask & SPTE_SPECIAL_MASK); shadow_user_mask = user_mask; shadow_accessed_mask = accessed_mask; @@ -477,16 +549,20 @@ EXPORT_SYMBOL_GPL(kvm_mmu_set_mask_ptes); static u8 kvm_get_shadow_phys_bits(void) { /* - * boot_cpu_data.x86_phys_bits is reduced when MKTME is detected - * in CPU detection code, but MKTME treats those reduced bits as - * 'keyID' thus they are not reserved bits. Therefore for MKTME - * we should still return physical address bits reported by CPUID. + * boot_cpu_data.x86_phys_bits is reduced when MKTME or SME are detected + * in CPU detection code, but the processor treats those reduced bits as + * 'keyID' thus they are not reserved bits. Therefore KVM needs to look at + * the physical address bits reported by CPUID. */ - if (!boot_cpu_has(X86_FEATURE_TME) || - WARN_ON_ONCE(boot_cpu_data.extended_cpuid_level < 0x80000008)) - return boot_cpu_data.x86_phys_bits; + if (likely(boot_cpu_data.extended_cpuid_level >= 0x80000008)) + return cpuid_eax(0x80000008) & 0xff; - return cpuid_eax(0x80000008) & 0xff; + /* + * Quite weird to have VMX or SVM but not MAXPHYADDR; probably a VM with + * custom CPUID. Proceed with whatever the kernel found since these features + * aren't virtualizable (SME/SEV also require CPUIDs higher than 0x80000008). + */ + return boot_cpu_data.x86_phys_bits; } static void kvm_mmu_reset_all_pte_masks(void) @@ -1164,6 +1240,17 @@ static void account_shadowed(struct kvm *kvm, struct kvm_mmu_page *sp) kvm_mmu_gfn_disallow_lpage(slot, gfn); } +static void account_huge_nx_page(struct kvm *kvm, struct kvm_mmu_page *sp) +{ + if (sp->lpage_disallowed) + return; + + ++kvm->stat.nx_lpage_splits; + list_add_tail(&sp->lpage_disallowed_link, + &kvm->arch.lpage_disallowed_mmu_pages); + sp->lpage_disallowed = true; +} + static void unaccount_shadowed(struct kvm *kvm, struct kvm_mmu_page *sp) { struct kvm_memslots *slots; @@ -1181,54 +1268,11 @@ static void unaccount_shadowed(struct kvm *kvm, struct kvm_mmu_page *sp) kvm_mmu_gfn_allow_lpage(slot, gfn); } -static bool __mmu_gfn_lpage_is_disallowed(gfn_t gfn, int level, - struct kvm_memory_slot *slot) +static void unaccount_huge_nx_page(struct kvm *kvm, struct kvm_mmu_page *sp) { - struct kvm_lpage_info *linfo; - - if (slot) { - linfo = lpage_info_slot(gfn, slot, level); - return !!linfo->disallow_lpage; - } - - return true; -} - -static bool mmu_gfn_lpage_is_disallowed(struct kvm_vcpu *vcpu, gfn_t gfn, - int level) -{ - struct kvm_memory_slot *slot; - - slot = kvm_vcpu_gfn_to_memslot(vcpu, gfn); - return __mmu_gfn_lpage_is_disallowed(gfn, level, slot); -} - -static int host_mapping_level(struct kvm *kvm, gfn_t gfn) -{ - unsigned long page_size; - int i, ret = 0; - - page_size = kvm_host_page_size(kvm, gfn); - - for (i = PT_PAGE_TABLE_LEVEL; i <= PT_MAX_HUGEPAGE_LEVEL; ++i) { - if (page_size >= KVM_HPAGE_SIZE(i)) - ret = i; - else - break; - } - - return ret; -} - -static inline bool memslot_valid_for_gpte(struct kvm_memory_slot *slot, - bool no_dirty_log) -{ - if (!slot || slot->flags & KVM_MEMSLOT_INVALID) - return false; - if (no_dirty_log && slot->dirty_bitmap) - return false; - - return true; + --kvm->stat.nx_lpage_splits; + sp->lpage_disallowed = false; + list_del(&sp->lpage_disallowed_link); } static struct kvm_memory_slot * @@ -1238,40 +1282,14 @@ gfn_to_memslot_dirty_bitmap(struct kvm_vcpu *vcpu, gfn_t gfn, struct kvm_memory_slot *slot; slot = kvm_vcpu_gfn_to_memslot(vcpu, gfn); - if (!memslot_valid_for_gpte(slot, no_dirty_log)) - slot = NULL; + if (!slot || slot->flags & KVM_MEMSLOT_INVALID) + return NULL; + if (no_dirty_log && slot->dirty_bitmap) + return NULL; return slot; } -static int mapping_level(struct kvm_vcpu *vcpu, gfn_t large_gfn, - bool *force_pt_level) -{ - int host_level, level, max_level; - struct kvm_memory_slot *slot; - - if (unlikely(*force_pt_level)) - return PT_PAGE_TABLE_LEVEL; - - slot = kvm_vcpu_gfn_to_memslot(vcpu, large_gfn); - *force_pt_level = !memslot_valid_for_gpte(slot, true); - if (unlikely(*force_pt_level)) - return PT_PAGE_TABLE_LEVEL; - - host_level = host_mapping_level(vcpu->kvm, large_gfn); - - if (host_level == PT_PAGE_TABLE_LEVEL) - return host_level; - - max_level = min(kvm_x86_ops->get_lpage_level(), host_level); - - for (level = PT_DIRECTORY_LEVEL; level <= max_level; ++level) - if (__mmu_gfn_lpage_is_disallowed(large_gfn, level, slot)) - break; - - return level - 1; -} - /* * About rmap_head encoding: * @@ -1331,7 +1349,7 @@ pte_list_desc_remove_entry(struct kvm_rmap_head *rmap_head, if (j != 0) return; if (!prev_desc && !desc->more) - rmap_head->val = (unsigned long)desc->sptes[0]; + rmap_head->val = 0; else if (prev_desc) prev_desc->more = desc->more; @@ -1446,7 +1464,7 @@ struct rmap_iterator { /* * Iteration must be started by this function. This should also be used after * removing/dropping sptes from the rmap link because in such cases the - * information in the itererator may not be valid. + * information in the iterator may not be valid. * * Returns sptep if found, NULL otherwise. */ @@ -1589,16 +1607,16 @@ static bool spte_clear_dirty(u64 *sptep) rmap_printk("rmap_clear_dirty: spte %p %llx\n", sptep, *sptep); + MMU_WARN_ON(!spte_ad_enabled(spte)); spte &= ~shadow_dirty_mask; - return mmu_spte_update(sptep, spte); } -static bool wrprot_ad_disabled_spte(u64 *sptep) +static bool spte_wrprot_for_clear_dirty(u64 *sptep) { bool was_writable = test_and_clear_bit(PT_WRITABLE_SHIFT, (unsigned long *)sptep); - if (was_writable) + if (was_writable && !spte_ad_enabled(*sptep)) kvm_set_pfn_dirty(spte_to_pfn(*sptep)); return was_writable; @@ -1617,10 +1635,10 @@ static bool __rmap_clear_dirty(struct kvm *kvm, struct kvm_rmap_head *rmap_head) bool flush = false; for_each_rmap_spte(rmap_head, &iter, sptep) - if (spte_ad_enabled(*sptep)) - flush |= spte_clear_dirty(sptep); + if (spte_ad_need_write_protect(*sptep)) + flush |= spte_wrprot_for_clear_dirty(sptep); else - flush |= wrprot_ad_disabled_spte(sptep); + flush |= spte_clear_dirty(sptep); return flush; } @@ -1631,6 +1649,11 @@ static bool spte_set_dirty(u64 *sptep) rmap_printk("rmap_set_dirty: spte %p %llx\n", sptep, *sptep); + /* + * Similar to the !kvm_x86_ops->slot_disable_log_dirty case, + * do not bother adding back write access to pages marked + * SPTE_AD_WRPROT_ONLY_MASK. + */ spte |= shadow_dirty_mask; return mmu_spte_update(sptep, spte); @@ -2095,6 +2118,13 @@ static struct kvm_mmu_page *kvm_mmu_alloc_page(struct kvm_vcpu *vcpu, int direct if (!direct) sp->gfns = mmu_memory_cache_alloc(&vcpu->arch.mmu_page_cache); set_page_private(virt_to_page(sp->spt), (unsigned long)sp); + + /* + * active_mmu_pages must be a FIFO list, as kvm_zap_obsolete_pages() + * depends on valid pages being added to the head of the list. See + * comments in kvm_zap_obsolete_pages(). + */ + sp->mmu_valid_gen = vcpu->kvm->arch.mmu_valid_gen; list_add(&sp->link, &vcpu->kvm->arch.active_mmu_pages); kvm_mod_used_mmu_pages(vcpu->kvm, +1); return sp; @@ -2244,7 +2274,7 @@ static void kvm_mmu_commit_zap_page(struct kvm *kvm, #define for_each_valid_sp(_kvm, _sp, _gfn) \ hlist_for_each_entry(_sp, \ &(_kvm)->arch.mmu_page_hash[kvm_page_table_hashfn(_gfn)], hash_link) \ - if ((_sp)->role.invalid) { \ + if (is_obsolete_sp((_kvm), (_sp))) { \ } else #define for_each_gfn_indirect_valid_sp(_kvm, _sp, _gfn) \ @@ -2301,6 +2331,12 @@ static void kvm_mmu_audit(struct kvm_vcpu *vcpu, int point) { } static void mmu_audit_disable(void) { } #endif +static bool is_obsolete_sp(struct kvm *kvm, struct kvm_mmu_page *sp) +{ + return sp->role.invalid || + unlikely(sp->mmu_valid_gen != kvm->arch.mmu_valid_gen); +} + static bool kvm_sync_page(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp, struct list_head *invalid_list) { @@ -2450,7 +2486,7 @@ static struct kvm_mmu_page *kvm_mmu_get_page(struct kvm_vcpu *vcpu, gva_t gaddr, unsigned level, int direct, - unsigned access) + unsigned int access) { union kvm_mmu_page_role role; unsigned quadrant; @@ -2609,7 +2645,7 @@ static void link_shadow_page(struct kvm_vcpu *vcpu, u64 *sptep, shadow_user_mask | shadow_x_mask | shadow_me_mask; if (sp_ad_disabled(sp)) - spte |= shadow_acc_track_value; + spte |= SPTE_AD_DISABLED_MASK; else spte |= shadow_accessed_mask; @@ -2739,10 +2775,18 @@ static bool __kvm_mmu_prepare_zap_page(struct kvm *kvm, } else { list_move(&sp->link, &kvm->arch.active_mmu_pages); - if (!sp->role.invalid) + /* + * Obsolete pages cannot be used on any vCPUs, see the comment + * in kvm_mmu_zap_all_fast(). Note, is_obsolete_sp() also + * treats invalid shadow pages as being obsolete. + */ + if (!is_obsolete_sp(kvm, sp)) kvm_reload_remote_mmus(kvm); } + if (sp->lpage_disallowed) + unaccount_huge_nx_page(kvm, sp); + sp->role.invalid = 1; return list_unstable; } @@ -2794,6 +2838,26 @@ static bool prepare_zap_oldest_mmu_page(struct kvm *kvm, return kvm_mmu_prepare_zap_page(kvm, sp, invalid_list); } +static int make_mmu_pages_available(struct kvm_vcpu *vcpu) +{ + LIST_HEAD(invalid_list); + + if (likely(kvm_mmu_available_pages(vcpu->kvm) >= KVM_MIN_FREE_MMU_PAGES)) + return 0; + + while (kvm_mmu_available_pages(vcpu->kvm) < KVM_REFILL_PAGES) { + if (!prepare_zap_oldest_mmu_page(vcpu->kvm, &invalid_list)) + break; + + ++vcpu->kvm->stat.mmu_recycled; + } + kvm_mmu_commit_zap_page(vcpu->kvm, &invalid_list); + + if (!kvm_mmu_available_pages(vcpu->kvm)) + return -ENOSPC; + return 0; +} + /* * Changing the number of mmu pages allocated to the vm * Note: if goal_nr_mmu_pages is too small, you will get dead lock @@ -2937,7 +3001,7 @@ static bool kvm_is_mmio_pfn(kvm_pfn_t pfn) #define SET_SPTE_NEED_REMOTE_TLB_FLUSH BIT(1) static int set_spte(struct kvm_vcpu *vcpu, u64 *sptep, - unsigned pte_access, int level, + unsigned int pte_access, int level, gfn_t gfn, kvm_pfn_t pfn, bool speculative, bool can_unsync, bool host_writable) { @@ -2950,7 +3014,9 @@ static int set_spte(struct kvm_vcpu *vcpu, u64 *sptep, sp = page_header(__pa(sptep)); if (sp_ad_disabled(sp)) - spte |= shadow_acc_track_value; + spte |= SPTE_AD_DISABLED_MASK; + else if (kvm_vcpu_ad_need_write_protect(vcpu)) + spte |= SPTE_AD_WRPROT_ONLY_MASK; /* * For the EPT case, shadow_present_mask is 0 if hardware @@ -2962,6 +3028,11 @@ static int set_spte(struct kvm_vcpu *vcpu, u64 *sptep, if (!speculative) spte |= spte_shadow_accessed_mask(spte); + if (level > PT_PAGE_TABLE_LEVEL && (pte_access & ACC_EXEC_MASK) && + is_nx_huge_page_enabled()) { + pte_access &= ~ACC_EXEC_MASK; + } + if (pte_access & ACC_EXEC_MASK) spte |= shadow_x_mask; else @@ -2987,17 +3058,6 @@ static int set_spte(struct kvm_vcpu *vcpu, u64 *sptep, spte |= (u64)pfn << PAGE_SHIFT; if (pte_access & ACC_WRITE_MASK) { - - /* - * Other vcpu creates new sp in the window between - * mapping_level() and acquiring mmu-lock. We can - * allow guest to retry the access, the mapping can - * be fixed if guest refault. - */ - if (level > PT_PAGE_TABLE_LEVEL && - mmu_gfn_lpage_is_disallowed(vcpu, gfn, level)) - goto done; - spte |= PT_WRITABLE_MASK | SPTE_MMU_WRITEABLE; /* @@ -3029,13 +3089,13 @@ static int set_spte(struct kvm_vcpu *vcpu, u64 *sptep, set_pte: if (mmu_spte_update(sptep, spte)) ret |= SET_SPTE_NEED_REMOTE_TLB_FLUSH; -done: return ret; } -static int mmu_set_spte(struct kvm_vcpu *vcpu, u64 *sptep, unsigned pte_access, - int write_fault, int level, gfn_t gfn, kvm_pfn_t pfn, - bool speculative, bool host_writable) +static int mmu_set_spte(struct kvm_vcpu *vcpu, u64 *sptep, + unsigned int pte_access, int write_fault, int level, + gfn_t gfn, kvm_pfn_t pfn, bool speculative, + bool host_writable) { int was_rmapped = 0; int rmap_count; @@ -3117,7 +3177,7 @@ static int direct_pte_prefetch_many(struct kvm_vcpu *vcpu, { struct page *pages[PTE_PREFETCH_NUM]; struct kvm_memory_slot *slot; - unsigned access = sp->role.access; + unsigned int access = sp->role.access; int i, ret; gfn_t gfn; @@ -3182,21 +3242,129 @@ static void direct_pte_prefetch(struct kvm_vcpu *vcpu, u64 *sptep) __direct_pte_prefetch(vcpu, sp, sptep); } +static int host_pfn_mapping_level(struct kvm_vcpu *vcpu, gfn_t gfn, + kvm_pfn_t pfn, struct kvm_memory_slot *slot) +{ + unsigned long hva; + pte_t *pte; + int level; + + BUILD_BUG_ON(PT_PAGE_TABLE_LEVEL != (int)PG_LEVEL_4K || + PT_DIRECTORY_LEVEL != (int)PG_LEVEL_2M || + PT_PDPE_LEVEL != (int)PG_LEVEL_1G); + + if (!PageCompound(pfn_to_page(pfn)) && !kvm_is_zone_device_pfn(pfn)) + return PT_PAGE_TABLE_LEVEL; + + /* + * Note, using the already-retrieved memslot and __gfn_to_hva_memslot() + * is not solely for performance, it's also necessary to avoid the + * "writable" check in __gfn_to_hva_many(), which will always fail on + * read-only memslots due to gfn_to_hva() assuming writes. Earlier + * page fault steps have already verified the guest isn't writing a + * read-only memslot. + */ + hva = __gfn_to_hva_memslot(slot, gfn); + + pte = lookup_address_in_mm(vcpu->kvm->mm, hva, &level); + if (unlikely(!pte)) + return PT_PAGE_TABLE_LEVEL; + + return level; +} + +static int kvm_mmu_hugepage_adjust(struct kvm_vcpu *vcpu, gfn_t gfn, + int max_level, kvm_pfn_t *pfnp) +{ + struct kvm_memory_slot *slot; + struct kvm_lpage_info *linfo; + kvm_pfn_t pfn = *pfnp; + kvm_pfn_t mask; + int level; + + if (unlikely(max_level == PT_PAGE_TABLE_LEVEL)) + return PT_PAGE_TABLE_LEVEL; + + if (is_error_noslot_pfn(pfn) || kvm_is_reserved_pfn(pfn)) + return PT_PAGE_TABLE_LEVEL; + + slot = gfn_to_memslot_dirty_bitmap(vcpu, gfn, true); + if (!slot) + return PT_PAGE_TABLE_LEVEL; + + max_level = min(max_level, kvm_x86_ops->get_lpage_level()); + for ( ; max_level > PT_PAGE_TABLE_LEVEL; max_level--) { + linfo = lpage_info_slot(gfn, slot, max_level); + if (!linfo->disallow_lpage) + break; + } + + if (max_level == PT_PAGE_TABLE_LEVEL) + return PT_PAGE_TABLE_LEVEL; + + level = host_pfn_mapping_level(vcpu, gfn, pfn, slot); + if (level == PT_PAGE_TABLE_LEVEL) + return level; + + level = min(level, max_level); + + /* + * mmu_notifier_retry() was successful and mmu_lock is held, so + * the pmd can't be split from under us. + */ + mask = KVM_PAGES_PER_HPAGE(level) - 1; + VM_BUG_ON((gfn & mask) != (pfn & mask)); + *pfnp = pfn & ~mask; + + return level; +} + +static void disallowed_hugepage_adjust(struct kvm_shadow_walk_iterator it, + gfn_t gfn, kvm_pfn_t *pfnp, int *levelp) +{ + int level = *levelp; + u64 spte = *it.sptep; + + if (it.level == level && level > PT_PAGE_TABLE_LEVEL && + is_nx_huge_page_enabled() && + is_shadow_present_pte(spte) && + !is_large_pte(spte)) { + /* + * A small SPTE exists for this pfn, but FNAME(fetch) + * and __direct_map would like to create a large PTE + * instead: just force them to go down another level, + * patching back for them into pfn the next 9 bits of + * the address. + */ + u64 page_mask = KVM_PAGES_PER_HPAGE(level) - KVM_PAGES_PER_HPAGE(level - 1); + *pfnp |= gfn & page_mask; + (*levelp)--; + } +} + static int __direct_map(struct kvm_vcpu *vcpu, gpa_t gpa, int write, - int map_writable, int level, kvm_pfn_t pfn, - bool prefault) + int map_writable, int max_level, kvm_pfn_t pfn, + bool prefault, bool account_disallowed_nx_lpage) { struct kvm_shadow_walk_iterator it; struct kvm_mmu_page *sp; - int ret; + int level, ret; gfn_t gfn = gpa >> PAGE_SHIFT; gfn_t base_gfn = gfn; - if (!VALID_PAGE(vcpu->arch.mmu->root_hpa)) + if (WARN_ON(!VALID_PAGE(vcpu->arch.mmu->root_hpa))) return RET_PF_RETRY; + level = kvm_mmu_hugepage_adjust(vcpu, gfn, max_level, &pfn); + trace_kvm_mmu_spte_requested(gpa, level, pfn); for_each_shadow_entry(vcpu, gpa, it) { + /* + * We cannot overwrite existing page tables with an NX + * large page, as the leaf could be executable. + */ + disallowed_hugepage_adjust(it, gfn, &pfn, &level); + base_gfn = gfn & ~(KVM_PAGES_PER_HPAGE(it.level) - 1); if (it.level == level) break; @@ -3207,6 +3375,8 @@ static int __direct_map(struct kvm_vcpu *vcpu, gpa_t gpa, int write, it.level - 1, true, ACC_ALL); link_shadow_page(vcpu, it.sptep, sp); + if (account_disallowed_nx_lpage) + account_huge_nx_page(vcpu->kvm, sp); } } @@ -3241,47 +3411,9 @@ static int kvm_handle_bad_page(struct kvm_vcpu *vcpu, gfn_t gfn, kvm_pfn_t pfn) return -EFAULT; } -static void transparent_hugepage_adjust(struct kvm_vcpu *vcpu, - gfn_t gfn, kvm_pfn_t *pfnp, - int *levelp) -{ - kvm_pfn_t pfn = *pfnp; - int level = *levelp; - - /* - * Check if it's a transparent hugepage. If this would be an - * hugetlbfs page, level wouldn't be set to - * PT_PAGE_TABLE_LEVEL and there would be no adjustment done - * here. - */ - if (!is_error_noslot_pfn(pfn) && !kvm_is_reserved_pfn(pfn) && - level == PT_PAGE_TABLE_LEVEL && - PageTransCompoundMap(pfn_to_page(pfn)) && - !mmu_gfn_lpage_is_disallowed(vcpu, gfn, PT_DIRECTORY_LEVEL)) { - unsigned long mask; - /* - * mmu_notifier_retry was successful and we hold the - * mmu_lock here, so the pmd can't become splitting - * from under us, and in turn - * __split_huge_page_refcount() can't run from under - * us and we can safely transfer the refcount from - * PG_tail to PG_head as we switch the pfn to tail to - * head. - */ - *levelp = level = PT_DIRECTORY_LEVEL; - mask = KVM_PAGES_PER_HPAGE(level) - 1; - VM_BUG_ON((gfn & mask) != (pfn & mask)); - if (pfn & mask) { - kvm_release_pfn_clean(pfn); - pfn &= ~mask; - kvm_get_pfn(pfn); - *pfnp = pfn; - } - } -} - static bool handle_abnormal_pfn(struct kvm_vcpu *vcpu, gva_t gva, gfn_t gfn, - kvm_pfn_t pfn, unsigned access, int *ret_val) + kvm_pfn_t pfn, unsigned int access, + int *ret_val) { /* The pfn is invalid, report the error! */ if (unlikely(is_error_pfn(pfn))) { @@ -3290,7 +3422,8 @@ static bool handle_abnormal_pfn(struct kvm_vcpu *vcpu, gva_t gva, gfn_t gfn, } if (unlikely(is_noslot_pfn(pfn))) - vcpu_cache_mmio_info(vcpu, gva, gfn, access); + vcpu_cache_mmio_info(vcpu, gva, gfn, + access & shadow_mmio_access_mask); return false; } @@ -3384,7 +3517,7 @@ static bool is_access_allowed(u32 fault_err_code, u64 spte) * - true: let the vcpu to access on the same address again. * - false: let the real page fault path to fix it. */ -static bool fast_page_fault(struct kvm_vcpu *vcpu, gva_t gva, int level, +static bool fast_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, u32 error_code) { struct kvm_shadow_walk_iterator iterator; @@ -3393,9 +3526,6 @@ static bool fast_page_fault(struct kvm_vcpu *vcpu, gva_t gva, int level, u64 spte = 0ull; uint retry_count = 0; - if (!VALID_PAGE(vcpu->arch.mmu->root_hpa)) - return false; - if (!page_fault_can_be_fast(error_code)) return false; @@ -3404,9 +3534,8 @@ static bool fast_page_fault(struct kvm_vcpu *vcpu, gva_t gva, int level, do { u64 new_spte; - for_each_shadow_entry_lockless(vcpu, gva, iterator, spte) - if (!is_shadow_present_pte(spte) || - iterator.level < level) + for_each_shadow_entry_lockless(vcpu, cr2_or_gpa, iterator, spte) + if (!is_shadow_present_pte(spte)) break; sp = page_header(__pa(iterator.sptep)); @@ -3482,67 +3611,13 @@ static bool fast_page_fault(struct kvm_vcpu *vcpu, gva_t gva, int level, } while (true); - trace_fast_page_fault(vcpu, gva, error_code, iterator.sptep, + trace_fast_page_fault(vcpu, cr2_or_gpa, error_code, iterator.sptep, spte, fault_handled); walk_shadow_page_lockless_end(vcpu); return fault_handled; } -static bool try_async_pf(struct kvm_vcpu *vcpu, bool prefault, gfn_t gfn, - gva_t gva, kvm_pfn_t *pfn, bool write, bool *writable); -static int make_mmu_pages_available(struct kvm_vcpu *vcpu); - -static int nonpaging_map(struct kvm_vcpu *vcpu, gva_t v, u32 error_code, - gfn_t gfn, bool prefault) -{ - int r; - int level; - bool force_pt_level = false; - kvm_pfn_t pfn; - unsigned long mmu_seq; - bool map_writable, write = error_code & PFERR_WRITE_MASK; - - level = mapping_level(vcpu, gfn, &force_pt_level); - if (likely(!force_pt_level)) { - /* - * This path builds a PAE pagetable - so we can map - * 2mb pages at maximum. Therefore check if the level - * is larger than that. - */ - if (level > PT_DIRECTORY_LEVEL) - level = PT_DIRECTORY_LEVEL; - - gfn &= ~(KVM_PAGES_PER_HPAGE(level) - 1); - } - - if (fast_page_fault(vcpu, v, level, error_code)) - return RET_PF_RETRY; - - mmu_seq = vcpu->kvm->mmu_notifier_seq; - smp_rmb(); - - if (try_async_pf(vcpu, prefault, gfn, v, &pfn, write, &map_writable)) - return RET_PF_RETRY; - - if (handle_abnormal_pfn(vcpu, v, gfn, pfn, ACC_ALL, &r)) - return r; - - r = RET_PF_RETRY; - spin_lock(&vcpu->kvm->mmu_lock); - if (mmu_notifier_retry(vcpu->kvm, mmu_seq)) - goto out_unlock; - if (make_mmu_pages_available(vcpu) < 0) - goto out_unlock; - if (likely(!force_pt_level)) - transparent_hugepage_adjust(vcpu, gfn, &pfn, &level); - r = __direct_map(vcpu, v, write, map_writable, level, pfn, prefault); -out_unlock: - spin_unlock(&vcpu->kvm->mmu_lock); - kvm_release_pfn_clean(pfn); - return r; -} - static void mmu_free_root_page(struct kvm *kvm, hpa_t *root_hpa, struct list_head *invalid_list) { @@ -3833,7 +3908,7 @@ void kvm_mmu_sync_roots(struct kvm_vcpu *vcpu) } EXPORT_SYMBOL_GPL(kvm_mmu_sync_roots); -static gpa_t nonpaging_gva_to_gpa(struct kvm_vcpu *vcpu, gva_t vaddr, +static gpa_t nonpaging_gva_to_gpa(struct kvm_vcpu *vcpu, gpa_t vaddr, u32 access, struct x86_exception *exception) { if (exception) @@ -3841,7 +3916,7 @@ static gpa_t nonpaging_gva_to_gpa(struct kvm_vcpu *vcpu, gva_t vaddr, return vaddr; } -static gpa_t nonpaging_gva_to_gpa_nested(struct kvm_vcpu *vcpu, gva_t vaddr, +static gpa_t nonpaging_gva_to_gpa_nested(struct kvm_vcpu *vcpu, gpa_t vaddr, u32 access, struct x86_exception *exception) { @@ -3853,20 +3928,14 @@ static gpa_t nonpaging_gva_to_gpa_nested(struct kvm_vcpu *vcpu, gva_t vaddr, static bool __is_rsvd_bits_set(struct rsvd_bits_validate *rsvd_check, u64 pte, int level) { - int bit7 = (pte >> 7) & 1, low6 = pte & 0x3f; - - return (pte & rsvd_check->rsvd_bits_mask[bit7][level-1]) | - ((rsvd_check->bad_mt_xwr & (1ull << low6)) != 0); -} + int bit7 = (pte >> 7) & 1; -static bool is_rsvd_bits_set(struct kvm_mmu *mmu, u64 gpte, int level) -{ - return __is_rsvd_bits_set(&mmu->guest_rsvd_check, gpte, level); + return pte & rsvd_check->rsvd_bits_mask[bit7][level-1]; } -static bool is_shadow_zero_bits_set(struct kvm_mmu *mmu, u64 spte, int level) +static bool __is_bad_mt_xwr(struct rsvd_bits_validate *rsvd_check, u64 pte) { - return __is_rsvd_bits_set(&mmu->shadow_zero_check, spte, level); + return rsvd_check->bad_mt_xwr & BIT_ULL(pte & 0x3f); } static bool mmio_info_in_cache(struct kvm_vcpu *vcpu, u64 addr, bool direct) @@ -3890,11 +3959,11 @@ walk_shadow_page_get_mmio_spte(struct kvm_vcpu *vcpu, u64 addr, u64 *sptep) { struct kvm_shadow_walk_iterator iterator; u64 sptes[PT64_ROOT_MAX_LEVEL], spte = 0ull; + struct rsvd_bits_validate *rsvd_check; int root, leaf; bool reserved = false; - if (!VALID_PAGE(vcpu->arch.mmu->root_hpa)) - goto exit; + rsvd_check = &vcpu->arch.mmu->shadow_zero_check; walk_shadow_page_lockless_begin(vcpu); @@ -3910,8 +3979,13 @@ walk_shadow_page_get_mmio_spte(struct kvm_vcpu *vcpu, u64 addr, u64 *sptep) if (!is_shadow_present_pte(spte)) break; - reserved |= is_shadow_zero_bits_set(vcpu->arch.mmu, spte, - iterator.level); + /* + * Use a bitwise-OR instead of a logical-OR to aggregate the + * reserved bit and EPT's invalid memtype/XWR checks to avoid + * adding a Jcc in the loop. + */ + reserved |= __is_bad_mt_xwr(rsvd_check, spte) | + __is_rsvd_bits_set(rsvd_check, spte, iterator.level); } walk_shadow_page_lockless_end(vcpu); @@ -3925,7 +3999,7 @@ walk_shadow_page_get_mmio_spte(struct kvm_vcpu *vcpu, u64 addr, u64 *sptep) root--; } } -exit: + *sptep = spte; return reserved; } @@ -3944,7 +4018,7 @@ static int handle_mmio_page_fault(struct kvm_vcpu *vcpu, u64 addr, bool direct) if (is_mmio_spte(spte)) { gfn_t gfn = get_mmio_spte_gfn(spte); - unsigned access = get_mmio_spte_access(spte); + unsigned int access = get_mmio_spte_access(spte); if (!check_mmio_spte(vcpu, spte)) return RET_PF_INVALID; @@ -3989,9 +4063,6 @@ static void shadow_page_table_clear_flood(struct kvm_vcpu *vcpu, gva_t addr) struct kvm_shadow_walk_iterator iterator; u64 spte; - if (!VALID_PAGE(vcpu->arch.mmu->root_hpa)) - return; - walk_shadow_page_lockless_begin(vcpu); for_each_shadow_entry_lockless(vcpu, addr, iterator, spte) { clear_sp_write_flooding_count(iterator.sptep); @@ -4001,29 +4072,8 @@ static void shadow_page_table_clear_flood(struct kvm_vcpu *vcpu, gva_t addr) walk_shadow_page_lockless_end(vcpu); } -static int nonpaging_page_fault(struct kvm_vcpu *vcpu, gva_t gva, - u32 error_code, bool prefault) -{ - gfn_t gfn = gva >> PAGE_SHIFT; - int r; - - pgprintk("%s: gva %lx error %x\n", __func__, gva, error_code); - - if (page_fault_handle_page_track(vcpu, error_code, gfn)) - return RET_PF_EMULATE; - - r = mmu_topup_memory_caches(vcpu); - if (r) - return r; - - MMU_WARN_ON(!VALID_PAGE(vcpu->arch.mmu->root_hpa)); - - - return nonpaging_map(vcpu, gva & PAGE_MASK, - error_code, gfn, prefault); -} - -static int kvm_arch_setup_async_pf(struct kvm_vcpu *vcpu, gva_t gva, gfn_t gfn) +static int kvm_arch_setup_async_pf(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, + gfn_t gfn) { struct kvm_arch_async_pf arch; @@ -4032,11 +4082,13 @@ static int kvm_arch_setup_async_pf(struct kvm_vcpu *vcpu, gva_t gva, gfn_t gfn) arch.direct_map = vcpu->arch.mmu->direct_map; arch.cr3 = vcpu->arch.mmu->get_cr3(vcpu); - return kvm_setup_async_pf(vcpu, gva, kvm_vcpu_gfn_to_hva(vcpu, gfn), &arch); + return kvm_setup_async_pf(vcpu, cr2_or_gpa, + kvm_vcpu_gfn_to_hva(vcpu, gfn), &arch); } static bool try_async_pf(struct kvm_vcpu *vcpu, bool prefault, gfn_t gfn, - gva_t gva, kvm_pfn_t *pfn, bool write, bool *writable) + gpa_t cr2_or_gpa, kvm_pfn_t *pfn, bool write, + bool *writable) { struct kvm_memory_slot *slot; bool async; @@ -4056,12 +4108,12 @@ static bool try_async_pf(struct kvm_vcpu *vcpu, bool prefault, gfn_t gfn, return false; /* *pfn has correct page already */ if (!prefault && kvm_can_do_async_pf(vcpu)) { - trace_kvm_try_async_get_page(gva, gfn); + trace_kvm_try_async_get_page(cr2_or_gpa, gfn); if (kvm_find_async_pf_gfn(vcpu, gfn)) { - trace_kvm_async_pf_doublefault(gva, gfn); + trace_kvm_async_pf_doublefault(cr2_or_gpa, gfn); kvm_make_request(KVM_REQ_APF_HALT, vcpu); return true; - } else if (kvm_arch_setup_async_pf(vcpu, gva, gfn)) + } else if (kvm_arch_setup_async_pf(vcpu, cr2_or_gpa, gfn)) return true; } @@ -4069,11 +4121,77 @@ static bool try_async_pf(struct kvm_vcpu *vcpu, bool prefault, gfn_t gfn, return false; } +static int direct_page_fault(struct kvm_vcpu *vcpu, gpa_t gpa, u32 error_code, + bool prefault, int max_level, bool is_tdp) +{ + bool write = error_code & PFERR_WRITE_MASK; + bool exec = error_code & PFERR_FETCH_MASK; + bool lpage_disallowed = exec && is_nx_huge_page_enabled(); + bool map_writable; + + gfn_t gfn = gpa >> PAGE_SHIFT; + unsigned long mmu_seq; + kvm_pfn_t pfn; + int r; + + if (page_fault_handle_page_track(vcpu, error_code, gfn)) + return RET_PF_EMULATE; + + r = mmu_topup_memory_caches(vcpu); + if (r) + return r; + + if (lpage_disallowed) + max_level = PT_PAGE_TABLE_LEVEL; + + if (fast_page_fault(vcpu, gpa, error_code)) + return RET_PF_RETRY; + + mmu_seq = vcpu->kvm->mmu_notifier_seq; + smp_rmb(); + + if (try_async_pf(vcpu, prefault, gfn, gpa, &pfn, write, &map_writable)) + return RET_PF_RETRY; + + if (handle_abnormal_pfn(vcpu, is_tdp ? 0 : gpa, gfn, pfn, ACC_ALL, &r)) + return r; + + r = RET_PF_RETRY; + spin_lock(&vcpu->kvm->mmu_lock); + if (mmu_notifier_retry(vcpu->kvm, mmu_seq)) + goto out_unlock; + if (make_mmu_pages_available(vcpu) < 0) + goto out_unlock; + r = __direct_map(vcpu, gpa, write, map_writable, max_level, pfn, + prefault, is_tdp && lpage_disallowed); + +out_unlock: + spin_unlock(&vcpu->kvm->mmu_lock); + kvm_release_pfn_clean(pfn); + return r; +} + +static int nonpaging_page_fault(struct kvm_vcpu *vcpu, gpa_t gpa, + u32 error_code, bool prefault) +{ + pgprintk("%s: gva %lx error %x\n", __func__, gpa, error_code); + + /* This path builds a PAE pagetable, we can map 2mb pages at maximum. */ + return direct_page_fault(vcpu, gpa & PAGE_MASK, error_code, prefault, + PT_DIRECTORY_LEVEL, false); +} + int kvm_handle_page_fault(struct kvm_vcpu *vcpu, u64 error_code, u64 fault_address, char *insn, int insn_len) { int r = 1; +#ifndef CONFIG_X86_64 + /* A 64-bit CR2 should be impossible on 32-bit KVM. */ + if (WARN_ON_ONCE(fault_address >> 32)) + return -EFAULT; +#endif + vcpu->arch.l1tf_flush_l1d = true; switch (vcpu->arch.apf.host_apf_reason) { default: @@ -4101,72 +4219,23 @@ int kvm_handle_page_fault(struct kvm_vcpu *vcpu, u64 error_code, } EXPORT_SYMBOL_GPL(kvm_handle_page_fault); -static bool -check_hugepage_cache_consistency(struct kvm_vcpu *vcpu, gfn_t gfn, int level) -{ - int page_num = KVM_PAGES_PER_HPAGE(level); - - gfn &= ~(page_num - 1); - - return kvm_mtrr_check_gfn_range_consistency(vcpu, gfn, page_num); -} - -static int tdp_page_fault(struct kvm_vcpu *vcpu, gva_t gpa, u32 error_code, - bool prefault) +int kvm_tdp_page_fault(struct kvm_vcpu *vcpu, gpa_t gpa, u32 error_code, + bool prefault) { - kvm_pfn_t pfn; - int r; - int level; - bool force_pt_level; - gfn_t gfn = gpa >> PAGE_SHIFT; - unsigned long mmu_seq; - int write = error_code & PFERR_WRITE_MASK; - bool map_writable; + int max_level; - MMU_WARN_ON(!VALID_PAGE(vcpu->arch.mmu->root_hpa)); + for (max_level = PT_MAX_HUGEPAGE_LEVEL; + max_level > PT_PAGE_TABLE_LEVEL; + max_level--) { + int page_num = KVM_PAGES_PER_HPAGE(max_level); + gfn_t base = (gpa >> PAGE_SHIFT) & ~(page_num - 1); - if (page_fault_handle_page_track(vcpu, error_code, gfn)) - return RET_PF_EMULATE; - - r = mmu_topup_memory_caches(vcpu); - if (r) - return r; - - force_pt_level = !check_hugepage_cache_consistency(vcpu, gfn, - PT_DIRECTORY_LEVEL); - level = mapping_level(vcpu, gfn, &force_pt_level); - if (likely(!force_pt_level)) { - if (level > PT_DIRECTORY_LEVEL && - !check_hugepage_cache_consistency(vcpu, gfn, level)) - level = PT_DIRECTORY_LEVEL; - gfn &= ~(KVM_PAGES_PER_HPAGE(level) - 1); + if (kvm_mtrr_check_gfn_range_consistency(vcpu, base, page_num)) + break; } - if (fast_page_fault(vcpu, gpa, level, error_code)) - return RET_PF_RETRY; - - mmu_seq = vcpu->kvm->mmu_notifier_seq; - smp_rmb(); - - if (try_async_pf(vcpu, prefault, gfn, gpa, &pfn, write, &map_writable)) - return RET_PF_RETRY; - - if (handle_abnormal_pfn(vcpu, 0, gfn, pfn, ACC_ALL, &r)) - return r; - - r = RET_PF_RETRY; - spin_lock(&vcpu->kvm->mmu_lock); - if (mmu_notifier_retry(vcpu->kvm, mmu_seq)) - goto out_unlock; - if (make_mmu_pages_available(vcpu) < 0) - goto out_unlock; - if (likely(!force_pt_level)) - transparent_hugepage_adjust(vcpu, gfn, &pfn, &level); - r = __direct_map(vcpu, gpa, write, map_writable, level, pfn, prefault); -out_unlock: - spin_unlock(&vcpu->kvm->mmu_lock); - kvm_release_pfn_clean(pfn); - return r; + return direct_page_fault(vcpu, gpa, error_code, prefault, + max_level, true); } static void nonpaging_init_context(struct kvm_vcpu *vcpu, @@ -4233,10 +4302,17 @@ static bool fast_cr3_switch(struct kvm_vcpu *vcpu, gpa_t new_cr3, return false; if (cached_root_available(vcpu, new_cr3, new_role)) { + /* + * It is possible that the cached previous root page is + * obsolete because of a change in the MMU generation + * number. However, changing the generation number is + * accompanied by KVM_REQ_MMU_RELOAD, which will free + * the root set here and allocate a new one. + */ kvm_make_request(KVM_REQ_LOAD_CR3, vcpu); if (!skip_tlb_flush) { kvm_make_request(KVM_REQ_MMU_SYNC, vcpu); - kvm_x86_ops->tlb_flush(vcpu, true); + kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu); } /* @@ -4286,7 +4362,7 @@ static void inject_page_fault(struct kvm_vcpu *vcpu, } static bool sync_mmio_spte(struct kvm_vcpu *vcpu, u64 *sptep, gfn_t gfn, - unsigned access, int *nr_present) + unsigned int access, int *nr_present) { if (unlikely(is_mmio_spte(*sptep))) { if (gfn != get_mmio_spte_gfn(*sptep)) { @@ -4849,7 +4925,7 @@ static void init_kvm_tdp_mmu(struct kvm_vcpu *vcpu) return; context->mmu_role.as_u64 = new_role.as_u64; - context->page_fault = tdp_page_fault; + context->page_fault = kvm_tdp_page_fault; context->sync_page = nonpaging_sync_page; context->invlpg = nonpaging_invlpg; context->update_pte = nonpaging_update_pte; @@ -5337,50 +5413,31 @@ int kvm_mmu_unprotect_page_virt(struct kvm_vcpu *vcpu, gva_t gva) } EXPORT_SYMBOL_GPL(kvm_mmu_unprotect_page_virt); -static int make_mmu_pages_available(struct kvm_vcpu *vcpu) -{ - LIST_HEAD(invalid_list); - - if (likely(kvm_mmu_available_pages(vcpu->kvm) >= KVM_MIN_FREE_MMU_PAGES)) - return 0; - - while (kvm_mmu_available_pages(vcpu->kvm) < KVM_REFILL_PAGES) { - if (!prepare_zap_oldest_mmu_page(vcpu->kvm, &invalid_list)) - break; - - ++vcpu->kvm->stat.mmu_recycled; - } - kvm_mmu_commit_zap_page(vcpu->kvm, &invalid_list); - - if (!kvm_mmu_available_pages(vcpu->kvm)) - return -ENOSPC; - return 0; -} - -int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gva_t cr2, u64 error_code, +int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, u64 error_code, void *insn, int insn_len) { int r, emulation_type = 0; - enum emulation_result er; bool direct = vcpu->arch.mmu->direct_map; + if (WARN_ON(!VALID_PAGE(vcpu->arch.mmu->root_hpa))) + return RET_PF_RETRY; + /* With shadow page tables, fault_address contains a GVA or nGPA. */ if (vcpu->arch.mmu->direct_map) { vcpu->arch.gpa_available = true; - vcpu->arch.gpa_val = cr2; + vcpu->arch.gpa_val = cr2_or_gpa; } r = RET_PF_INVALID; if (unlikely(error_code & PFERR_RSVD_MASK)) { - r = handle_mmio_page_fault(vcpu, cr2, direct); + r = handle_mmio_page_fault(vcpu, cr2_or_gpa, direct); if (r == RET_PF_EMULATE) goto emulate; } if (r == RET_PF_INVALID) { - r = vcpu->arch.mmu->page_fault(vcpu, cr2, - lower_32_bits(error_code), - false); + r = kvm_mmu_do_page_fault(vcpu, cr2_or_gpa, + lower_32_bits(error_code), false); WARN_ON(r == RET_PF_INVALID); } @@ -5398,7 +5455,7 @@ int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gva_t cr2, u64 error_code, */ if (vcpu->arch.mmu->direct_map && (error_code & PFERR_NESTED_GUEST_PAGE) == PFERR_NESTED_GUEST_PAGE) { - kvm_mmu_unprotect_page(vcpu->kvm, gpa_to_gfn(cr2)); + kvm_mmu_unprotect_page(vcpu->kvm, gpa_to_gfn(cr2_or_gpa)); return 1; } @@ -5413,7 +5470,7 @@ int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gva_t cr2, u64 error_code, * explicitly shadowing L1's page tables, i.e. unprotecting something * for L1 isn't going to magically fix whatever issue cause L2 to fail. */ - if (!mmio_info_in_cache(vcpu, cr2, direct) && !is_guest_mode(vcpu)) + if (!mmio_info_in_cache(vcpu, cr2_or_gpa, direct) && !is_guest_mode(vcpu)) emulation_type = EMULTYPE_ALLOW_RETRY; emulate: /* @@ -5428,19 +5485,8 @@ emulate: return 1; } - er = x86_emulate_instruction(vcpu, cr2, emulation_type, insn, insn_len); - - switch (er) { - case EMULATE_DONE: - return 1; - case EMULATE_USER_EXIT: - ++vcpu->stat.mmio_exits; - /* fall through */ - case EMULATE_FAIL: - return 0; - default: - BUG(); - } + return x86_emulate_instruction(vcpu, cr2_or_gpa, emulation_type, insn, + insn_len); } EXPORT_SYMBOL_GPL(kvm_mmu_page_fault); @@ -5592,13 +5638,13 @@ slot_handle_leaf(struct kvm *kvm, struct kvm_memory_slot *memslot, PT_PAGE_TABLE_LEVEL, lock_flush_tlb); } -static void free_mmu_pages(struct kvm_vcpu *vcpu) +static void free_mmu_pages(struct kvm_mmu *mmu) { - free_page((unsigned long)vcpu->arch.mmu->pae_root); - free_page((unsigned long)vcpu->arch.mmu->lm_root); + free_page((unsigned long)mmu->pae_root); + free_page((unsigned long)mmu->lm_root); } -static int alloc_mmu_pages(struct kvm_vcpu *vcpu) +static int alloc_mmu_pages(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu) { struct page *page; int i; @@ -5619,9 +5665,9 @@ static int alloc_mmu_pages(struct kvm_vcpu *vcpu) if (!page) return -ENOMEM; - vcpu->arch.mmu->pae_root = page_address(page); + mmu->pae_root = page_address(page); for (i = 0; i < 4; ++i) - vcpu->arch.mmu->pae_root[i] = INVALID_PAGE; + mmu->pae_root[i] = INVALID_PAGE; return 0; } @@ -5629,6 +5675,7 @@ static int alloc_mmu_pages(struct kvm_vcpu *vcpu) int kvm_mmu_create(struct kvm_vcpu *vcpu) { uint i; + int ret; vcpu->arch.mmu = &vcpu->arch.root_mmu; vcpu->arch.walk_mmu = &vcpu->arch.root_mmu; @@ -5646,47 +5693,124 @@ int kvm_mmu_create(struct kvm_vcpu *vcpu) vcpu->arch.guest_mmu.prev_roots[i] = KVM_MMU_ROOT_INFO_INVALID; vcpu->arch.nested_mmu.translate_gpa = translate_nested_gpa; - return alloc_mmu_pages(vcpu); -} -static void kvm_mmu_invalidate_zap_pages_in_memslot(struct kvm *kvm, - struct kvm_memory_slot *slot, - struct kvm_page_track_notifier_node *node) -{ - struct kvm_mmu_page *sp; - LIST_HEAD(invalid_list); - unsigned long i; - bool flush; - gfn_t gfn; + ret = alloc_mmu_pages(vcpu, &vcpu->arch.guest_mmu); + if (ret) + return ret; - spin_lock(&kvm->mmu_lock); + ret = alloc_mmu_pages(vcpu, &vcpu->arch.root_mmu); + if (ret) + goto fail_allocate_root; - if (list_empty(&kvm->arch.active_mmu_pages)) - goto out_unlock; + return ret; + fail_allocate_root: + free_mmu_pages(&vcpu->arch.guest_mmu); + return ret; +} - flush = slot_handle_all_level(kvm, slot, kvm_zap_rmapp, false); +#define BATCH_ZAP_PAGES 10 +static void kvm_zap_obsolete_pages(struct kvm *kvm) +{ + struct kvm_mmu_page *sp, *node; + int nr_zapped, batch = 0; - for (i = 0; i < slot->npages; i++) { - gfn = slot->base_gfn + i; +restart: + list_for_each_entry_safe_reverse(sp, node, + &kvm->arch.active_mmu_pages, link) { + /* + * No obsolete valid page exists before a newly created page + * since active_mmu_pages is a FIFO list. + */ + if (!is_obsolete_sp(kvm, sp)) + break; - for_each_valid_sp(kvm, sp, gfn) { - if (sp->gfn != gfn) - continue; + /* + * Skip invalid pages with a non-zero root count, zapping pages + * with a non-zero root count will never succeed, i.e. the page + * will get thrown back on active_mmu_pages and we'll get stuck + * in an infinite loop. + */ + if (sp->role.invalid && sp->root_count) + continue; - kvm_mmu_prepare_zap_page(kvm, sp, &invalid_list); + /* + * No need to flush the TLB since we're only zapping shadow + * pages with an obsolete generation number and all vCPUS have + * loaded a new root, i.e. the shadow pages being zapped cannot + * be in active use by the guest. + */ + if (batch >= BATCH_ZAP_PAGES && + cond_resched_lock(&kvm->mmu_lock)) { + batch = 0; + goto restart; } - if (need_resched() || spin_needbreak(&kvm->mmu_lock)) { - kvm_mmu_remote_flush_or_zap(kvm, &invalid_list, flush); - flush = false; - cond_resched_lock(&kvm->mmu_lock); + + if (__kvm_mmu_prepare_zap_page(kvm, sp, + &kvm->arch.zapped_obsolete_pages, &nr_zapped)) { + batch += nr_zapped; + goto restart; } } - kvm_mmu_remote_flush_or_zap(kvm, &invalid_list, flush); -out_unlock: + /* + * Trigger a remote TLB flush before freeing the page tables to ensure + * KVM is not in the middle of a lockless shadow page table walk, which + * may reference the pages. + */ + kvm_mmu_commit_zap_page(kvm, &kvm->arch.zapped_obsolete_pages); +} + +/* + * Fast invalidate all shadow pages and use lock-break technique + * to zap obsolete pages. + * + * It's required when memslot is being deleted or VM is being + * destroyed, in these cases, we should ensure that KVM MMU does + * not use any resource of the being-deleted slot or all slots + * after calling the function. + */ +static void kvm_mmu_zap_all_fast(struct kvm *kvm) +{ + lockdep_assert_held(&kvm->slots_lock); + + spin_lock(&kvm->mmu_lock); + trace_kvm_mmu_zap_all_fast(kvm); + + /* + * Toggle mmu_valid_gen between '0' and '1'. Because slots_lock is + * held for the entire duration of zapping obsolete pages, it's + * impossible for there to be multiple invalid generations associated + * with *valid* shadow pages at any given time, i.e. there is exactly + * one valid generation and (at most) one invalid generation. + */ + kvm->arch.mmu_valid_gen = kvm->arch.mmu_valid_gen ? 0 : 1; + + /* + * Notify all vcpus to reload its shadow page table and flush TLB. + * Then all vcpus will switch to new shadow page table with the new + * mmu_valid_gen. + * + * Note: we need to do this under the protection of mmu_lock, + * otherwise, vcpu would purge shadow page but miss tlb flush. + */ + kvm_reload_remote_mmus(kvm); + + kvm_zap_obsolete_pages(kvm); spin_unlock(&kvm->mmu_lock); } +static bool kvm_has_zapped_obsolete_pages(struct kvm *kvm) +{ + return unlikely(!list_empty_careful(&kvm->arch.zapped_obsolete_pages)); +} + +static void kvm_mmu_invalidate_zap_pages_in_memslot(struct kvm *kvm, + struct kvm_memory_slot *slot, + struct kvm_page_track_notifier_node *node) +{ + kvm_mmu_zap_all_fast(kvm); +} + void kvm_mmu_init_vm(struct kvm *kvm) { struct kvm_page_track_notifier_node *node = &kvm->arch.mmu_sp_tracker; @@ -5789,9 +5913,9 @@ restart: * the guest, and the guest page table is using 4K page size * mapping if the indirect sp has level = 1. */ - if (sp->role.direct && - !kvm_is_reserved_pfn(pfn) && - PageTransCompoundMap(pfn_to_page(pfn))) { + if (sp->role.direct && !kvm_is_reserved_pfn(pfn) && + (kvm_is_zone_device_pfn(pfn) || + PageCompound(pfn_to_page(pfn)))) { pte_list_remove(rmap_head, sptep); if (kvm_available_flush_tlb_with_range()) @@ -5877,7 +6001,7 @@ void kvm_mmu_slot_set_dirty(struct kvm *kvm, } EXPORT_SYMBOL_GPL(kvm_mmu_slot_set_dirty); -static void __kvm_mmu_zap_all(struct kvm *kvm, bool mmio_only) +void kvm_mmu_zap_all(struct kvm *kvm) { struct kvm_mmu_page *sp, *node; LIST_HEAD(invalid_list); @@ -5886,14 +6010,10 @@ static void __kvm_mmu_zap_all(struct kvm *kvm, bool mmio_only) spin_lock(&kvm->mmu_lock); restart: list_for_each_entry_safe(sp, node, &kvm->arch.active_mmu_pages, link) { - if (mmio_only && !sp->mmio_cached) - continue; if (sp->role.invalid && sp->root_count) continue; - if (__kvm_mmu_prepare_zap_page(kvm, sp, &invalid_list, &ign)) { - WARN_ON_ONCE(mmio_only); + if (__kvm_mmu_prepare_zap_page(kvm, sp, &invalid_list, &ign)) goto restart; - } if (cond_resched_lock(&kvm->mmu_lock)) goto restart; } @@ -5902,11 +6022,6 @@ restart: spin_unlock(&kvm->mmu_lock); } -void kvm_mmu_zap_all(struct kvm *kvm) -{ - return __kvm_mmu_zap_all(kvm, false); -} - void kvm_mmu_invalidate_mmio_sptes(struct kvm *kvm, u64 gen) { WARN_ON(gen & KVM_MEMSLOT_GEN_UPDATE_IN_PROGRESS); @@ -5928,7 +6043,7 @@ void kvm_mmu_invalidate_mmio_sptes(struct kvm *kvm, u64 gen) */ if (unlikely(gen == 0)) { kvm_debug_ratelimited("kvm: zapping shadow pages for mmio generation wraparound\n"); - __kvm_mmu_zap_all(kvm, true); + kvm_mmu_zap_all_fast(kvm); } } @@ -5959,16 +6074,24 @@ mmu_shrink_scan(struct shrinker *shrink, struct shrink_control *sc) * want to shrink a VM that only started to populate its MMU * anyway. */ - if (!kvm->arch.n_used_mmu_pages) + if (!kvm->arch.n_used_mmu_pages && + !kvm_has_zapped_obsolete_pages(kvm)) continue; idx = srcu_read_lock(&kvm->srcu); spin_lock(&kvm->mmu_lock); + if (kvm_has_zapped_obsolete_pages(kvm)) { + kvm_mmu_commit_zap_page(kvm, + &kvm->arch.zapped_obsolete_pages); + goto unlock; + } + if (prepare_zap_oldest_mmu_page(kvm, &invalid_list)) freed++; kvm_mmu_commit_zap_page(kvm, &invalid_list); +unlock: spin_unlock(&kvm->mmu_lock); srcu_read_unlock(&kvm->srcu, idx); @@ -6025,16 +6148,65 @@ static void kvm_set_mmio_spte_mask(void) * If reserved bit is not supported, clear the present bit to disable * mmio page fault. */ - if (IS_ENABLED(CONFIG_X86_64) && shadow_phys_bits == 52) + if (shadow_phys_bits == 52) mask &= ~1ull; - kvm_mmu_set_mmio_spte_mask(mask, mask); + kvm_mmu_set_mmio_spte_mask(mask, mask, ACC_WRITE_MASK | ACC_USER_MASK); +} + +static bool get_nx_auto_mode(void) +{ + /* Return true when CPU has the bug, and mitigations are ON */ + return boot_cpu_has_bug(X86_BUG_ITLB_MULTIHIT) && !cpu_mitigations_off(); +} + +static void __set_nx_huge_pages(bool val) +{ + nx_huge_pages = itlb_multihit_kvm_mitigation = val; +} + +static int set_nx_huge_pages(const char *val, const struct kernel_param *kp) +{ + bool old_val = nx_huge_pages; + bool new_val; + + /* In "auto" mode deploy workaround only if CPU has the bug. */ + if (sysfs_streq(val, "off")) + new_val = 0; + else if (sysfs_streq(val, "force")) + new_val = 1; + else if (sysfs_streq(val, "auto")) + new_val = get_nx_auto_mode(); + else if (strtobool(val, &new_val) < 0) + return -EINVAL; + + __set_nx_huge_pages(new_val); + + if (new_val != old_val) { + struct kvm *kvm; + + mutex_lock(&kvm_lock); + + list_for_each_entry(kvm, &vm_list, vm_list) { + mutex_lock(&kvm->slots_lock); + kvm_mmu_zap_all_fast(kvm); + mutex_unlock(&kvm->slots_lock); + + wake_up_process(kvm->arch.nx_lpage_recovery_thread); + } + mutex_unlock(&kvm_lock); + } + + return 0; } int kvm_mmu_module_init(void) { int ret = -ENOMEM; + if (nx_huge_pages == -1) + __set_nx_huge_pages(get_nx_auto_mode()); + /* * MMU roles use union aliasing which is, generally speaking, an * undefined behavior. However, we supposedly know how compilers behave @@ -6102,7 +6274,8 @@ unsigned long kvm_mmu_calculate_default_mmu_pages(struct kvm *kvm) void kvm_mmu_destroy(struct kvm_vcpu *vcpu) { kvm_mmu_unload(vcpu); - free_mmu_pages(vcpu); + free_mmu_pages(&vcpu->arch.root_mmu); + free_mmu_pages(&vcpu->arch.guest_mmu); mmu_free_memory_caches(vcpu); } @@ -6113,3 +6286,116 @@ void kvm_mmu_module_exit(void) unregister_shrinker(&mmu_shrinker); mmu_audit_disable(); } + +static int set_nx_huge_pages_recovery_ratio(const char *val, const struct kernel_param *kp) +{ + unsigned int old_val; + int err; + + old_val = nx_huge_pages_recovery_ratio; + err = param_set_uint(val, kp); + if (err) + return err; + + if (READ_ONCE(nx_huge_pages) && + !old_val && nx_huge_pages_recovery_ratio) { + struct kvm *kvm; + + mutex_lock(&kvm_lock); + + list_for_each_entry(kvm, &vm_list, vm_list) + wake_up_process(kvm->arch.nx_lpage_recovery_thread); + + mutex_unlock(&kvm_lock); + } + + return err; +} + +static void kvm_recover_nx_lpages(struct kvm *kvm) +{ + int rcu_idx; + struct kvm_mmu_page *sp; + unsigned int ratio; + LIST_HEAD(invalid_list); + ulong to_zap; + + rcu_idx = srcu_read_lock(&kvm->srcu); + spin_lock(&kvm->mmu_lock); + + ratio = READ_ONCE(nx_huge_pages_recovery_ratio); + to_zap = ratio ? DIV_ROUND_UP(kvm->stat.nx_lpage_splits, ratio) : 0; + while (to_zap && !list_empty(&kvm->arch.lpage_disallowed_mmu_pages)) { + /* + * We use a separate list instead of just using active_mmu_pages + * because the number of lpage_disallowed pages is expected to + * be relatively small compared to the total. + */ + sp = list_first_entry(&kvm->arch.lpage_disallowed_mmu_pages, + struct kvm_mmu_page, + lpage_disallowed_link); + WARN_ON_ONCE(!sp->lpage_disallowed); + kvm_mmu_prepare_zap_page(kvm, sp, &invalid_list); + WARN_ON_ONCE(sp->lpage_disallowed); + + if (!--to_zap || need_resched() || spin_needbreak(&kvm->mmu_lock)) { + kvm_mmu_commit_zap_page(kvm, &invalid_list); + if (to_zap) + cond_resched_lock(&kvm->mmu_lock); + } + } + + spin_unlock(&kvm->mmu_lock); + srcu_read_unlock(&kvm->srcu, rcu_idx); +} + +static long get_nx_lpage_recovery_timeout(u64 start_time) +{ + return READ_ONCE(nx_huge_pages) && READ_ONCE(nx_huge_pages_recovery_ratio) + ? start_time + 60 * HZ - get_jiffies_64() + : MAX_SCHEDULE_TIMEOUT; +} + +static int kvm_nx_lpage_recovery_worker(struct kvm *kvm, uintptr_t data) +{ + u64 start_time; + long remaining_time; + + while (true) { + start_time = get_jiffies_64(); + remaining_time = get_nx_lpage_recovery_timeout(start_time); + + set_current_state(TASK_INTERRUPTIBLE); + while (!kthread_should_stop() && remaining_time > 0) { + schedule_timeout(remaining_time); + remaining_time = get_nx_lpage_recovery_timeout(start_time); + set_current_state(TASK_INTERRUPTIBLE); + } + + set_current_state(TASK_RUNNING); + + if (kthread_should_stop()) + return 0; + + kvm_recover_nx_lpages(kvm); + } +} + +int kvm_mmu_post_init_vm(struct kvm *kvm) +{ + int err; + + err = kvm_vm_create_worker_thread(kvm, kvm_nx_lpage_recovery_worker, 0, + "kvm-nx-lpage-recovery", + &kvm->arch.nx_lpage_recovery_thread); + if (!err) + kthread_unpark(kvm->arch.nx_lpage_recovery_thread); + + return err; +} + +void kvm_mmu_pre_destroy_vm(struct kvm *kvm) +{ + if (kvm->arch.nx_lpage_recovery_thread) + kthread_stop(kvm->arch.nx_lpage_recovery_thread); +} diff --git a/arch/x86/kvm/page_track.c b/arch/x86/kvm/mmu/page_track.c index 3521e2d176f2..3521e2d176f2 100644 --- a/arch/x86/kvm/page_track.c +++ b/arch/x86/kvm/mmu/page_track.c diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/mmu/paging_tmpl.h index 7d5cdb3af594..e4c8a4cbf407 100644 --- a/arch/x86/kvm/paging_tmpl.h +++ b/arch/x86/kvm/mmu/paging_tmpl.h @@ -33,7 +33,7 @@ #define PT_GUEST_ACCESSED_SHIFT PT_ACCESSED_SHIFT #define PT_HAVE_ACCESSED_DIRTY(mmu) true #ifdef CONFIG_X86_64 - #define PT_MAX_FULL_LEVELS 4 + #define PT_MAX_FULL_LEVELS PT64_ROOT_MAX_LEVEL #define CMPXCHG cmpxchg #else #define CMPXCHG cmpxchg64 @@ -128,6 +128,21 @@ static inline int FNAME(is_present_gpte)(unsigned long pte) #endif } +static bool FNAME(is_bad_mt_xwr)(struct rsvd_bits_validate *rsvd_check, u64 gpte) +{ +#if PTTYPE != PTTYPE_EPT + return false; +#else + return __is_bad_mt_xwr(rsvd_check, gpte); +#endif +} + +static bool FNAME(is_rsvd_bits_set)(struct kvm_mmu *mmu, u64 gpte, int level) +{ + return __is_rsvd_bits_set(&mmu->guest_rsvd_check, gpte, level) || + FNAME(is_bad_mt_xwr)(&mmu->guest_rsvd_check, gpte); +} + static int FNAME(cmpxchg_gpte)(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, pt_element_t __user *ptep_user, unsigned index, pt_element_t orig_pte, pt_element_t new_pte) @@ -175,9 +190,6 @@ static bool FNAME(prefetch_invalid_gpte)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp, u64 *spte, u64 gpte) { - if (is_rsvd_bits_set(vcpu->arch.mmu, gpte, PT_PAGE_TABLE_LEVEL)) - goto no_present; - if (!FNAME(is_present_gpte)(gpte)) goto no_present; @@ -186,6 +198,9 @@ static bool FNAME(prefetch_invalid_gpte)(struct kvm_vcpu *vcpu, !(gpte & PT_GUEST_ACCESSED_MASK)) goto no_present; + if (FNAME(is_rsvd_bits_set)(vcpu->arch.mmu, gpte, PT_PAGE_TABLE_LEVEL)) + goto no_present; + return false; no_present: @@ -291,11 +306,11 @@ static inline unsigned FNAME(gpte_pkeys)(struct kvm_vcpu *vcpu, u64 gpte) } /* - * Fetch a guest pte for a guest virtual address + * Fetch a guest pte for a guest virtual address, or for an L2's GPA. */ static int FNAME(walk_addr_generic)(struct guest_walker *walker, struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, - gva_t addr, u32 access) + gpa_t addr, u32 access) { int ret; pt_element_t pte; @@ -400,7 +415,7 @@ retry_walk: if (unlikely(!FNAME(is_present_gpte)(pte))) goto error; - if (unlikely(is_rsvd_bits_set(mmu, pte, walker->level))) { + if (unlikely(FNAME(is_rsvd_bits_set)(mmu, pte, walker->level))) { errcode = PFERR_RSVD_MASK | PFERR_PRESENT_MASK; goto error; } @@ -496,7 +511,7 @@ error: } static int FNAME(walk_addr)(struct guest_walker *walker, - struct kvm_vcpu *vcpu, gva_t addr, u32 access) + struct kvm_vcpu *vcpu, gpa_t addr, u32 access) { return FNAME(walk_addr_generic)(walker, vcpu, vcpu->arch.mmu, addr, access); @@ -611,16 +626,17 @@ static void FNAME(pte_prefetch)(struct kvm_vcpu *vcpu, struct guest_walker *gw, * If the guest tries to write a write-protected page, we need to * emulate this operation, return 1 to indicate this case. */ -static int FNAME(fetch)(struct kvm_vcpu *vcpu, gva_t addr, +static int FNAME(fetch)(struct kvm_vcpu *vcpu, gpa_t addr, struct guest_walker *gw, - int write_fault, int hlevel, - kvm_pfn_t pfn, bool map_writable, bool prefault) + int write_fault, int max_level, + kvm_pfn_t pfn, bool map_writable, bool prefault, + bool lpage_disallowed) { struct kvm_mmu_page *sp = NULL; struct kvm_shadow_walk_iterator it; unsigned direct_access, access = gw->pt_access; - int top_level, ret; - gfn_t base_gfn; + int top_level, hlevel, ret; + gfn_t base_gfn = gw->gfn; direct_access = gw->pte_access; @@ -636,7 +652,7 @@ static int FNAME(fetch)(struct kvm_vcpu *vcpu, gva_t addr, if (FNAME(gpte_changed)(vcpu, gw, top_level)) goto out_gpte_changed; - if (!VALID_PAGE(vcpu->arch.mmu->root_hpa)) + if (WARN_ON(!VALID_PAGE(vcpu->arch.mmu->root_hpa))) goto out_gpte_changed; for (shadow_walk_init(&it, vcpu, addr); @@ -665,12 +681,19 @@ static int FNAME(fetch)(struct kvm_vcpu *vcpu, gva_t addr, link_shadow_page(vcpu, it.sptep, sp); } - base_gfn = gw->gfn; + hlevel = kvm_mmu_hugepage_adjust(vcpu, gw->gfn, max_level, &pfn); trace_kvm_mmu_spte_requested(addr, gw->level, pfn); for (; shadow_walk_okay(&it); shadow_walk_next(&it)) { clear_sp_write_flooding_count(it.sptep); + + /* + * We cannot overwrite existing page tables with an NX + * large page, as the leaf could be executable. + */ + disallowed_hugepage_adjust(it, gw->gfn, &pfn, &hlevel); + base_gfn = gw->gfn & ~(KVM_PAGES_PER_HPAGE(it.level) - 1); if (it.level == hlevel) break; @@ -683,6 +706,8 @@ static int FNAME(fetch)(struct kvm_vcpu *vcpu, gva_t addr, sp = kvm_mmu_get_page(vcpu, base_gfn, addr, it.level - 1, true, direct_access); link_shadow_page(vcpu, it.sptep, sp); + if (lpage_disallowed) + account_huge_nx_page(vcpu->kvm, sp); } } @@ -750,7 +775,7 @@ FNAME(is_self_change_mapping)(struct kvm_vcpu *vcpu, * Returns: 1 if we need to emulate the instruction, 0 otherwise, or * a negative value on error. */ -static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gva_t addr, u32 error_code, +static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gpa_t addr, u32 error_code, bool prefault) { int write_fault = error_code & PFERR_WRITE_MASK; @@ -758,10 +783,11 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gva_t addr, u32 error_code, struct guest_walker walker; int r; kvm_pfn_t pfn; - int level = PT_PAGE_TABLE_LEVEL; - bool force_pt_level = false; unsigned long mmu_seq; bool map_writable, is_self_change_mapping; + bool lpage_disallowed = (error_code & PFERR_FETCH_MASK) && + is_nx_huge_page_enabled(); + int max_level; pgprintk("%s: addr %lx err %x\n", __func__, addr, error_code); @@ -801,14 +827,10 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gva_t addr, u32 error_code, is_self_change_mapping = FNAME(is_self_change_mapping)(vcpu, &walker, user_fault, &vcpu->arch.write_fault_to_shadow_pgtable); - if (walker.level >= PT_DIRECTORY_LEVEL && !is_self_change_mapping) { - level = mapping_level(vcpu, walker.gfn, &force_pt_level); - if (likely(!force_pt_level)) { - level = min(walker.level, level); - walker.gfn = walker.gfn & ~(KVM_PAGES_PER_HPAGE(level) - 1); - } - } else - force_pt_level = true; + if (lpage_disallowed || is_self_change_mapping) + max_level = PT_PAGE_TABLE_LEVEL; + else + max_level = walker.level; mmu_seq = vcpu->kvm->mmu_notifier_seq; smp_rmb(); @@ -848,10 +870,8 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gva_t addr, u32 error_code, kvm_mmu_audit(vcpu, AUDIT_PRE_PAGE_FAULT); if (make_mmu_pages_available(vcpu) < 0) goto out_unlock; - if (!force_pt_level) - transparent_hugepage_adjust(vcpu, walker.gfn, &pfn, &level); - r = FNAME(fetch)(vcpu, addr, &walker, write_fault, - level, pfn, map_writable, prefault); + r = FNAME(fetch)(vcpu, addr, &walker, write_fault, max_level, pfn, + map_writable, prefault, lpage_disallowed); kvm_mmu_audit(vcpu, AUDIT_POST_PAGE_FAULT); out_unlock: @@ -928,18 +948,19 @@ static void FNAME(invlpg)(struct kvm_vcpu *vcpu, gva_t gva, hpa_t root_hpa) spin_unlock(&vcpu->kvm->mmu_lock); } -static gpa_t FNAME(gva_to_gpa)(struct kvm_vcpu *vcpu, gva_t vaddr, u32 access, +/* Note, @addr is a GPA when gva_to_gpa() translates an L2 GPA to an L1 GPA. */ +static gpa_t FNAME(gva_to_gpa)(struct kvm_vcpu *vcpu, gpa_t addr, u32 access, struct x86_exception *exception) { struct guest_walker walker; gpa_t gpa = UNMAPPED_GVA; int r; - r = FNAME(walk_addr)(&walker, vcpu, vaddr, access); + r = FNAME(walk_addr)(&walker, vcpu, addr, access); if (r) { gpa = gfn_to_gpa(walker.gfn); - gpa |= vaddr & ~PAGE_MASK; + gpa |= addr & ~PAGE_MASK; } else if (exception) *exception = walker.fault; @@ -947,7 +968,8 @@ static gpa_t FNAME(gva_to_gpa)(struct kvm_vcpu *vcpu, gva_t vaddr, u32 access, } #if PTTYPE != PTTYPE_EPT -static gpa_t FNAME(gva_to_gpa_nested)(struct kvm_vcpu *vcpu, gva_t vaddr, +/* Note, gva_to_gpa_nested() is only used to translate L2 GVAs. */ +static gpa_t FNAME(gva_to_gpa_nested)(struct kvm_vcpu *vcpu, gpa_t vaddr, u32 access, struct x86_exception *exception) { @@ -955,6 +977,11 @@ static gpa_t FNAME(gva_to_gpa_nested)(struct kvm_vcpu *vcpu, gva_t vaddr, gpa_t gpa = UNMAPPED_GVA; int r; +#ifndef CONFIG_X86_64 + /* A 64-bit GVA should be impossible on 32-bit KVM. */ + WARN_ON_ONCE(vaddr >> 32); +#endif + r = FNAME(walk_addr_nested)(&walker, vcpu, vaddr, access); if (r) { diff --git a/arch/x86/kvm/mmutrace.h b/arch/x86/kvm/mmutrace.h index d8001b4bca05..3c6522b84ff1 100644 --- a/arch/x86/kvm/mmutrace.h +++ b/arch/x86/kvm/mmutrace.h @@ -8,16 +8,18 @@ #undef TRACE_SYSTEM #define TRACE_SYSTEM kvmmmu -#define KVM_MMU_PAGE_FIELDS \ - __field(__u64, gfn) \ - __field(__u32, role) \ - __field(__u32, root_count) \ +#define KVM_MMU_PAGE_FIELDS \ + __field(__u8, mmu_valid_gen) \ + __field(__u64, gfn) \ + __field(__u32, role) \ + __field(__u32, root_count) \ __field(bool, unsync) -#define KVM_MMU_PAGE_ASSIGN(sp) \ - __entry->gfn = sp->gfn; \ - __entry->role = sp->role.word; \ - __entry->root_count = sp->root_count; \ +#define KVM_MMU_PAGE_ASSIGN(sp) \ + __entry->mmu_valid_gen = sp->mmu_valid_gen; \ + __entry->gfn = sp->gfn; \ + __entry->role = sp->role.word; \ + __entry->root_count = sp->root_count; \ __entry->unsync = sp->unsync; #define KVM_MMU_PAGE_PRINTK() ({ \ @@ -29,8 +31,9 @@ \ role.word = __entry->role; \ \ - trace_seq_printf(p, "sp gfn %llx l%u %u-byte q%u%s %s%s" \ + trace_seq_printf(p, "sp gen %u gfn %llx l%u %u-byte q%u%s %s%s" \ " %snxe %sad root %u %s%c", \ + __entry->mmu_valid_gen, \ __entry->gfn, role.level, \ role.gpte_is_8_bytes ? 8 : 4, \ role.quadrant, \ @@ -246,13 +249,13 @@ TRACE_EVENT( TRACE_EVENT( fast_page_fault, - TP_PROTO(struct kvm_vcpu *vcpu, gva_t gva, u32 error_code, + TP_PROTO(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, u32 error_code, u64 *sptep, u64 old_spte, bool retry), - TP_ARGS(vcpu, gva, error_code, sptep, old_spte, retry), + TP_ARGS(vcpu, cr2_or_gpa, error_code, sptep, old_spte, retry), TP_STRUCT__entry( __field(int, vcpu_id) - __field(gva_t, gva) + __field(gpa_t, cr2_or_gpa) __field(u32, error_code) __field(u64 *, sptep) __field(u64, old_spte) @@ -262,7 +265,7 @@ TRACE_EVENT( TP_fast_assign( __entry->vcpu_id = vcpu->vcpu_id; - __entry->gva = gva; + __entry->cr2_or_gpa = cr2_or_gpa; __entry->error_code = error_code; __entry->sptep = sptep; __entry->old_spte = old_spte; @@ -270,9 +273,9 @@ TRACE_EVENT( __entry->retry = retry; ), - TP_printk("vcpu %d gva %lx error_code %s sptep %p old %#llx" + TP_printk("vcpu %d gva %llx error_code %s sptep %p old %#llx" " new %llx spurious %d fixed %d", __entry->vcpu_id, - __entry->gva, __print_flags(__entry->error_code, "|", + __entry->cr2_or_gpa, __print_flags(__entry->error_code, "|", kvm_mmu_trace_pferr_flags), __entry->sptep, __entry->old_spte, __entry->new_spte, __spte_satisfied(old_spte), __spte_satisfied(new_spte) @@ -280,6 +283,27 @@ TRACE_EVENT( ); TRACE_EVENT( + kvm_mmu_zap_all_fast, + TP_PROTO(struct kvm *kvm), + TP_ARGS(kvm), + + TP_STRUCT__entry( + __field(__u8, mmu_valid_gen) + __field(unsigned int, mmu_used_pages) + ), + + TP_fast_assign( + __entry->mmu_valid_gen = kvm->arch.mmu_valid_gen; + __entry->mmu_used_pages = kvm->arch.n_used_mmu_pages; + ), + + TP_printk("kvm-mmu-valid-gen %u used_pages %x", + __entry->mmu_valid_gen, __entry->mmu_used_pages + ) +); + + +TRACE_EVENT( check_mmio_spte, TP_PROTO(u64 spte, unsigned int kvm_gen, unsigned int spte_gen), TP_ARGS(spte, kvm_gen, spte_gen), diff --git a/arch/x86/kvm/mtrr.c b/arch/x86/kvm/mtrr.c index 25ce3edd1872..7f0059aa30e1 100644 --- a/arch/x86/kvm/mtrr.c +++ b/arch/x86/kvm/mtrr.c @@ -192,11 +192,15 @@ static bool fixed_msr_to_seg_unit(u32 msr, int *seg, int *unit) break; case MSR_MTRRfix16K_80000 ... MSR_MTRRfix16K_A0000: *seg = 1; - *unit = msr - MSR_MTRRfix16K_80000; + *unit = array_index_nospec( + msr - MSR_MTRRfix16K_80000, + MSR_MTRRfix16K_A0000 - MSR_MTRRfix16K_80000 + 1); break; case MSR_MTRRfix4K_C0000 ... MSR_MTRRfix4K_F8000: *seg = 2; - *unit = msr - MSR_MTRRfix4K_C0000; + *unit = array_index_nospec( + msr - MSR_MTRRfix4K_C0000, + MSR_MTRRfix4K_F8000 - MSR_MTRRfix4K_C0000 + 1); break; default: return false; diff --git a/arch/x86/kvm/pmu.c b/arch/x86/kvm/pmu.c index 46875bbd0419..bcc6a73d6628 100644 --- a/arch/x86/kvm/pmu.c +++ b/arch/x86/kvm/pmu.c @@ -62,8 +62,7 @@ static void kvm_perf_overflow(struct perf_event *perf_event, struct kvm_pmc *pmc = perf_event->overflow_handler_context; struct kvm_pmu *pmu = pmc_to_pmu(pmc); - if (!test_and_set_bit(pmc->idx, - (unsigned long *)&pmu->reprogram_pmi)) { + if (!test_and_set_bit(pmc->idx, pmu->reprogram_pmi)) { __set_bit(pmc->idx, (unsigned long *)&pmu->global_status); kvm_make_request(KVM_REQ_PMU, pmc->vcpu); } @@ -76,8 +75,7 @@ static void kvm_perf_overflow_intr(struct perf_event *perf_event, struct kvm_pmc *pmc = perf_event->overflow_handler_context; struct kvm_pmu *pmu = pmc_to_pmu(pmc); - if (!test_and_set_bit(pmc->idx, - (unsigned long *)&pmu->reprogram_pmi)) { + if (!test_and_set_bit(pmc->idx, pmu->reprogram_pmi)) { __set_bit(pmc->idx, (unsigned long *)&pmu->global_status); kvm_make_request(KVM_REQ_PMU, pmc->vcpu); @@ -137,7 +135,37 @@ static void pmc_reprogram_counter(struct kvm_pmc *pmc, u32 type, } pmc->perf_event = event; - clear_bit(pmc->idx, (unsigned long*)&pmc_to_pmu(pmc)->reprogram_pmi); + pmc_to_pmu(pmc)->event_count++; + clear_bit(pmc->idx, pmc_to_pmu(pmc)->reprogram_pmi); +} + +static void pmc_pause_counter(struct kvm_pmc *pmc) +{ + u64 counter = pmc->counter; + + if (!pmc->perf_event) + return; + + /* update counter, reset event value to avoid redundant accumulation */ + counter += perf_event_pause(pmc->perf_event, true); + pmc->counter = counter & pmc_bitmask(pmc); +} + +static bool pmc_resume_counter(struct kvm_pmc *pmc) +{ + if (!pmc->perf_event) + return false; + + /* recalibrate sample period and check if it's accepted by perf core */ + if (perf_event_period(pmc->perf_event, + (-pmc->counter) & pmc_bitmask(pmc))) + return false; + + /* reuse perf_event to serve as pmc_reprogram_counter() does*/ + perf_event_enable(pmc->perf_event); + + clear_bit(pmc->idx, (unsigned long *)&pmc_to_pmu(pmc)->reprogram_pmi); + return true; } void reprogram_gp_counter(struct kvm_pmc *pmc, u64 eventsel) @@ -154,7 +182,7 @@ void reprogram_gp_counter(struct kvm_pmc *pmc, u64 eventsel) pmc->eventsel = eventsel; - pmc_stop_counter(pmc); + pmc_pause_counter(pmc); if (!(eventsel & ARCH_PERFMON_EVENTSEL_ENABLE) || !pmc_is_enabled(pmc)) return; @@ -193,6 +221,12 @@ void reprogram_gp_counter(struct kvm_pmc *pmc, u64 eventsel) if (type == PERF_TYPE_RAW) config = eventsel & X86_RAW_EVENT_MASK; + if (pmc->current_config == eventsel && pmc_resume_counter(pmc)) + return; + + pmc_release_perf_event(pmc); + + pmc->current_config = eventsel; pmc_reprogram_counter(pmc, type, config, !(eventsel & ARCH_PERFMON_EVENTSEL_USR), !(eventsel & ARCH_PERFMON_EVENTSEL_OS), @@ -209,7 +243,7 @@ void reprogram_fixed_counter(struct kvm_pmc *pmc, u8 ctrl, int idx) struct kvm_pmu_event_filter *filter; struct kvm *kvm = pmc->vcpu->kvm; - pmc_stop_counter(pmc); + pmc_pause_counter(pmc); if (!en_field || !pmc_is_enabled(pmc)) return; @@ -224,6 +258,12 @@ void reprogram_fixed_counter(struct kvm_pmc *pmc, u8 ctrl, int idx) return; } + if (pmc->current_config == (u64)ctrl && pmc_resume_counter(pmc)) + return; + + pmc_release_perf_event(pmc); + + pmc->current_config = (u64)ctrl; pmc_reprogram_counter(pmc, PERF_TYPE_HARDWARE, kvm_x86_ops->pmu_ops->find_fixed_event(idx), !(en_field & 0x2), /* exclude user */ @@ -253,27 +293,32 @@ EXPORT_SYMBOL_GPL(reprogram_counter); void kvm_pmu_handle_event(struct kvm_vcpu *vcpu) { struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); - u64 bitmask; int bit; - bitmask = pmu->reprogram_pmi; - - for_each_set_bit(bit, (unsigned long *)&bitmask, X86_PMC_IDX_MAX) { + for_each_set_bit(bit, pmu->reprogram_pmi, X86_PMC_IDX_MAX) { struct kvm_pmc *pmc = kvm_x86_ops->pmu_ops->pmc_idx_to_pmc(pmu, bit); if (unlikely(!pmc || !pmc->perf_event)) { - clear_bit(bit, (unsigned long *)&pmu->reprogram_pmi); + clear_bit(bit, pmu->reprogram_pmi); continue; } reprogram_counter(pmu, bit); } + + /* + * Unused perf_events are only released if the corresponding MSRs + * weren't accessed during the last vCPU time slice. kvm_arch_sched_in + * triggers KVM_REQ_PMU if cleanup is needed. + */ + if (unlikely(pmu->need_cleanup)) + kvm_pmu_cleanup(vcpu); } /* check if idx is a valid index to access PMU */ -int kvm_pmu_is_valid_msr_idx(struct kvm_vcpu *vcpu, unsigned idx) +int kvm_pmu_is_valid_rdpmc_ecx(struct kvm_vcpu *vcpu, unsigned int idx) { - return kvm_x86_ops->pmu_ops->is_valid_msr_idx(vcpu, idx); + return kvm_x86_ops->pmu_ops->is_valid_rdpmc_ecx(vcpu, idx); } bool is_vmware_backdoor_pmc(u32 pmc_idx) @@ -323,7 +368,7 @@ int kvm_pmu_rdpmc(struct kvm_vcpu *vcpu, unsigned idx, u64 *data) if (is_vmware_backdoor_pmc(idx)) return kvm_pmu_rdpmc_vmware(vcpu, idx, data); - pmc = kvm_x86_ops->pmu_ops->msr_idx_to_pmc(vcpu, idx, &mask); + pmc = kvm_x86_ops->pmu_ops->rdpmc_ecx_to_pmc(vcpu, idx, &mask); if (!pmc) return 1; @@ -339,7 +384,17 @@ void kvm_pmu_deliver_pmi(struct kvm_vcpu *vcpu) bool kvm_pmu_is_valid_msr(struct kvm_vcpu *vcpu, u32 msr) { - return kvm_x86_ops->pmu_ops->is_valid_msr(vcpu, msr); + return kvm_x86_ops->pmu_ops->msr_idx_to_pmc(vcpu, msr) || + kvm_x86_ops->pmu_ops->is_valid_msr(vcpu, msr); +} + +static void kvm_pmu_mark_pmc_in_use(struct kvm_vcpu *vcpu, u32 msr) +{ + struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); + struct kvm_pmc *pmc = kvm_x86_ops->pmu_ops->msr_idx_to_pmc(vcpu, msr); + + if (pmc) + __set_bit(pmc->idx, pmu->pmc_in_use); } int kvm_pmu_get_msr(struct kvm_vcpu *vcpu, u32 msr, u64 *data) @@ -349,6 +404,7 @@ int kvm_pmu_get_msr(struct kvm_vcpu *vcpu, u32 msr, u64 *data) int kvm_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) { + kvm_pmu_mark_pmc_in_use(vcpu, msr_info->index); return kvm_x86_ops->pmu_ops->set_msr(vcpu, msr_info); } @@ -376,9 +432,45 @@ void kvm_pmu_init(struct kvm_vcpu *vcpu) memset(pmu, 0, sizeof(*pmu)); kvm_x86_ops->pmu_ops->init(vcpu); init_irq_work(&pmu->irq_work, kvm_pmi_trigger_fn); + pmu->event_count = 0; + pmu->need_cleanup = false; kvm_pmu_refresh(vcpu); } +static inline bool pmc_speculative_in_use(struct kvm_pmc *pmc) +{ + struct kvm_pmu *pmu = pmc_to_pmu(pmc); + + if (pmc_is_fixed(pmc)) + return fixed_ctrl_field(pmu->fixed_ctr_ctrl, + pmc->idx - INTEL_PMC_IDX_FIXED) & 0x3; + + return pmc->eventsel & ARCH_PERFMON_EVENTSEL_ENABLE; +} + +/* Release perf_events for vPMCs that have been unused for a full time slice. */ +void kvm_pmu_cleanup(struct kvm_vcpu *vcpu) +{ + struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); + struct kvm_pmc *pmc = NULL; + DECLARE_BITMAP(bitmask, X86_PMC_IDX_MAX); + int i; + + pmu->need_cleanup = false; + + bitmap_andnot(bitmask, pmu->all_valid_pmc_idx, + pmu->pmc_in_use, X86_PMC_IDX_MAX); + + for_each_set_bit(i, bitmask, X86_PMC_IDX_MAX) { + pmc = kvm_x86_ops->pmu_ops->pmc_idx_to_pmc(pmu, i); + + if (pmc && pmc->perf_event && !pmc_speculative_in_use(pmc)) + pmc_stop_counter(pmc); + } + + bitmap_zero(pmu->pmc_in_use, X86_PMC_IDX_MAX); +} + void kvm_pmu_destroy(struct kvm_vcpu *vcpu) { kvm_pmu_reset(vcpu); @@ -416,8 +508,8 @@ int kvm_vm_ioctl_set_pmu_event_filter(struct kvm *kvm, void __user *argp) *filter = tmp; mutex_lock(&kvm->lock); - rcu_swap_protected(kvm->arch.pmu_event_filter, filter, - mutex_is_locked(&kvm->lock)); + filter = rcu_replace_pointer(kvm->arch.pmu_event_filter, filter, + mutex_is_locked(&kvm->lock)); mutex_unlock(&kvm->lock); synchronize_srcu_expedited(&kvm->srcu); diff --git a/arch/x86/kvm/pmu.h b/arch/x86/kvm/pmu.h index 58265f761c3b..13332984b6d5 100644 --- a/arch/x86/kvm/pmu.h +++ b/arch/x86/kvm/pmu.h @@ -2,6 +2,8 @@ #ifndef __KVM_X86_PMU_H #define __KVM_X86_PMU_H +#include <linux/nospec.h> + #define vcpu_to_pmu(vcpu) (&(vcpu)->arch.pmu) #define pmu_to_vcpu(pmu) (container_of((pmu), struct kvm_vcpu, arch.pmu)) #define pmc_to_pmu(pmc) (&(pmc)->vcpu->arch.pmu) @@ -25,9 +27,10 @@ struct kvm_pmu_ops { unsigned (*find_fixed_event)(int idx); bool (*pmc_is_enabled)(struct kvm_pmc *pmc); struct kvm_pmc *(*pmc_idx_to_pmc)(struct kvm_pmu *pmu, int pmc_idx); - struct kvm_pmc *(*msr_idx_to_pmc)(struct kvm_vcpu *vcpu, unsigned idx, - u64 *mask); - int (*is_valid_msr_idx)(struct kvm_vcpu *vcpu, unsigned idx); + struct kvm_pmc *(*rdpmc_ecx_to_pmc)(struct kvm_vcpu *vcpu, + unsigned int idx, u64 *mask); + struct kvm_pmc *(*msr_idx_to_pmc)(struct kvm_vcpu *vcpu, u32 msr); + int (*is_valid_rdpmc_ecx)(struct kvm_vcpu *vcpu, unsigned int idx); bool (*is_valid_msr)(struct kvm_vcpu *vcpu, u32 msr); int (*get_msr)(struct kvm_vcpu *vcpu, u32 msr, u64 *data); int (*set_msr)(struct kvm_vcpu *vcpu, struct msr_data *msr_info); @@ -55,12 +58,21 @@ static inline u64 pmc_read_counter(struct kvm_pmc *pmc) return counter & pmc_bitmask(pmc); } -static inline void pmc_stop_counter(struct kvm_pmc *pmc) +static inline void pmc_release_perf_event(struct kvm_pmc *pmc) { if (pmc->perf_event) { - pmc->counter = pmc_read_counter(pmc); perf_event_release_kernel(pmc->perf_event); pmc->perf_event = NULL; + pmc->current_config = 0; + pmc_to_pmu(pmc)->event_count--; + } +} + +static inline void pmc_stop_counter(struct kvm_pmc *pmc) +{ + if (pmc->perf_event) { + pmc->counter = pmc_read_counter(pmc); + pmc_release_perf_event(pmc); } } @@ -79,6 +91,12 @@ static inline bool pmc_is_enabled(struct kvm_pmc *pmc) return kvm_x86_ops->pmu_ops->pmc_is_enabled(pmc); } +static inline bool kvm_valid_perf_global_ctrl(struct kvm_pmu *pmu, + u64 data) +{ + return !(pmu->global_ctrl_mask & data); +} + /* returns general purpose PMC with the specified MSR. Note that it can be * used for both PERFCTRn and EVNTSELn; that is why it accepts base as a * paramenter to tell them apart. @@ -86,8 +104,12 @@ static inline bool pmc_is_enabled(struct kvm_pmc *pmc) static inline struct kvm_pmc *get_gp_pmc(struct kvm_pmu *pmu, u32 msr, u32 base) { - if (msr >= base && msr < base + pmu->nr_arch_gp_counters) - return &pmu->gp_counters[msr - base]; + if (msr >= base && msr < base + pmu->nr_arch_gp_counters) { + u32 index = array_index_nospec(msr - base, + pmu->nr_arch_gp_counters); + + return &pmu->gp_counters[index]; + } return NULL; } @@ -97,8 +119,12 @@ static inline struct kvm_pmc *get_fixed_pmc(struct kvm_pmu *pmu, u32 msr) { int base = MSR_CORE_PERF_FIXED_CTR0; - if (msr >= base && msr < base + pmu->nr_arch_fixed_counters) - return &pmu->fixed_counters[msr - base]; + if (msr >= base && msr < base + pmu->nr_arch_fixed_counters) { + u32 index = array_index_nospec(msr - base, + pmu->nr_arch_fixed_counters); + + return &pmu->fixed_counters[index]; + } return NULL; } @@ -110,13 +136,14 @@ void reprogram_counter(struct kvm_pmu *pmu, int pmc_idx); void kvm_pmu_deliver_pmi(struct kvm_vcpu *vcpu); void kvm_pmu_handle_event(struct kvm_vcpu *vcpu); int kvm_pmu_rdpmc(struct kvm_vcpu *vcpu, unsigned pmc, u64 *data); -int kvm_pmu_is_valid_msr_idx(struct kvm_vcpu *vcpu, unsigned idx); +int kvm_pmu_is_valid_rdpmc_ecx(struct kvm_vcpu *vcpu, unsigned int idx); bool kvm_pmu_is_valid_msr(struct kvm_vcpu *vcpu, u32 msr); int kvm_pmu_get_msr(struct kvm_vcpu *vcpu, u32 msr, u64 *data); int kvm_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info); void kvm_pmu_refresh(struct kvm_vcpu *vcpu); void kvm_pmu_reset(struct kvm_vcpu *vcpu); void kvm_pmu_init(struct kvm_vcpu *vcpu); +void kvm_pmu_cleanup(struct kvm_vcpu *vcpu); void kvm_pmu_destroy(struct kvm_vcpu *vcpu); int kvm_vm_ioctl_set_pmu_event_filter(struct kvm *kvm, void __user *argp); diff --git a/arch/x86/kvm/pmu_amd.c b/arch/x86/kvm/pmu_amd.c index c8388389a3b0..ce0b10fe5e2b 100644 --- a/arch/x86/kvm/pmu_amd.c +++ b/arch/x86/kvm/pmu_amd.c @@ -174,7 +174,7 @@ static struct kvm_pmc *amd_pmc_idx_to_pmc(struct kvm_pmu *pmu, int pmc_idx) } /* returns 0 if idx's corresponding MSR exists; otherwise returns 1. */ -static int amd_is_valid_msr_idx(struct kvm_vcpu *vcpu, unsigned idx) +static int amd_is_valid_rdpmc_ecx(struct kvm_vcpu *vcpu, unsigned int idx) { struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); @@ -184,7 +184,8 @@ static int amd_is_valid_msr_idx(struct kvm_vcpu *vcpu, unsigned idx) } /* idx is the ECX register of RDPMC instruction */ -static struct kvm_pmc *amd_msr_idx_to_pmc(struct kvm_vcpu *vcpu, unsigned idx, u64 *mask) +static struct kvm_pmc *amd_rdpmc_ecx_to_pmc(struct kvm_vcpu *vcpu, + unsigned int idx, u64 *mask) { struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); struct kvm_pmc *counters; @@ -199,13 +200,19 @@ static struct kvm_pmc *amd_msr_idx_to_pmc(struct kvm_vcpu *vcpu, unsigned idx, u static bool amd_is_valid_msr(struct kvm_vcpu *vcpu, u32 msr) { + /* All MSRs refer to exactly one PMC, so msr_idx_to_pmc is enough. */ + return false; +} + +static struct kvm_pmc *amd_msr_idx_to_pmc(struct kvm_vcpu *vcpu, u32 msr) +{ struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); - int ret = false; + struct kvm_pmc *pmc; - ret = get_gp_pmc_amd(pmu, msr, PMU_TYPE_COUNTER) || - get_gp_pmc_amd(pmu, msr, PMU_TYPE_EVNTSEL); + pmc = get_gp_pmc_amd(pmu, msr, PMU_TYPE_COUNTER); + pmc = pmc ? pmc : get_gp_pmc_amd(pmu, msr, PMU_TYPE_EVNTSEL); - return ret; + return pmc; } static int amd_pmu_get_msr(struct kvm_vcpu *vcpu, u32 msr, u64 *data) @@ -272,6 +279,7 @@ static void amd_pmu_refresh(struct kvm_vcpu *vcpu) pmu->counter_bitmask[KVM_PMC_FIXED] = 0; pmu->nr_arch_fixed_counters = 0; pmu->global_status = 0; + bitmap_set(pmu->all_valid_pmc_idx, 0, pmu->nr_arch_gp_counters); } static void amd_pmu_init(struct kvm_vcpu *vcpu) @@ -285,6 +293,7 @@ static void amd_pmu_init(struct kvm_vcpu *vcpu) pmu->gp_counters[i].type = KVM_PMC_GP; pmu->gp_counters[i].vcpu = vcpu; pmu->gp_counters[i].idx = i; + pmu->gp_counters[i].current_config = 0; } } @@ -306,8 +315,9 @@ struct kvm_pmu_ops amd_pmu_ops = { .find_fixed_event = amd_find_fixed_event, .pmc_is_enabled = amd_pmc_is_enabled, .pmc_idx_to_pmc = amd_pmc_idx_to_pmc, + .rdpmc_ecx_to_pmc = amd_rdpmc_ecx_to_pmc, .msr_idx_to_pmc = amd_msr_idx_to_pmc, - .is_valid_msr_idx = amd_is_valid_msr_idx, + .is_valid_rdpmc_ecx = amd_is_valid_rdpmc_ecx, .is_valid_msr = amd_is_valid_msr, .get_msr = amd_pmu_get_msr, .set_msr = amd_pmu_set_msr, diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index d685491fce4d..bef0ba35f121 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -38,6 +38,7 @@ #include <linux/file.h> #include <linux/pagemap.h> #include <linux/swap.h> +#include <linux/rwsem.h> #include <asm/apic.h> #include <asm/perf_event.h> @@ -68,10 +69,8 @@ MODULE_DEVICE_TABLE(x86cpu, svm_cpu_id); #define SEG_TYPE_LDT 2 #define SEG_TYPE_BUSY_TSS16 3 -#define SVM_FEATURE_NPT (1 << 0) #define SVM_FEATURE_LBRV (1 << 1) #define SVM_FEATURE_SVML (1 << 2) -#define SVM_FEATURE_NRIP (1 << 3) #define SVM_FEATURE_TSC_RATE (1 << 4) #define SVM_FEATURE_VMCB_CLEAN (1 << 5) #define SVM_FEATURE_FLUSH_ASID (1 << 6) @@ -388,6 +387,8 @@ static u8 rsm_ins_bytes[] = "\x0f\xaa"; static void svm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0); static void svm_flush_tlb(struct kvm_vcpu *vcpu, bool invalidate_gpa); static void svm_complete_interrupts(struct vcpu_svm *svm); +static void svm_toggle_avic_for_irq_window(struct kvm_vcpu *vcpu, bool activate); +static inline void avic_post_state_restore(struct kvm_vcpu *vcpu); static int nested_svm_exit_handled(struct vcpu_svm *svm); static int nested_svm_intercept(struct vcpu_svm *svm); @@ -420,9 +421,13 @@ enum { #define VMCB_AVIC_APIC_BAR_MASK 0xFFFFFFFFFF000ULL +static int sev_flush_asids(void); +static DECLARE_RWSEM(sev_deactivate_lock); +static DEFINE_MUTEX(sev_bitmap_lock); static unsigned int max_sev_asid; static unsigned int min_sev_asid; static unsigned long *sev_asid_bitmap; +static unsigned long *sev_reclaim_asid_bitmap; #define __sme_page_pa(x) __sme_set(page_to_pfn(x) << PAGE_SHIFT) struct enc_region { @@ -736,8 +741,14 @@ static int get_npt_level(struct kvm_vcpu *vcpu) static void svm_set_efer(struct kvm_vcpu *vcpu, u64 efer) { vcpu->arch.efer = efer; - if (!npt_enabled && !(efer & EFER_LMA)) - efer &= ~EFER_LME; + + if (!npt_enabled) { + /* Shadow paging assumes NX to be available. */ + efer |= EFER_NX; + + if (!(efer & EFER_LMA)) + efer &= ~EFER_LME; + } to_svm(vcpu)->vmcb->save.efer = efer | EFER_SVME; mark_dirty(to_svm(vcpu)->vmcb, VMCB_CR); @@ -770,7 +781,7 @@ static void svm_set_interrupt_shadow(struct kvm_vcpu *vcpu, int mask) } -static void skip_emulated_instruction(struct kvm_vcpu *vcpu) +static int skip_emulated_instruction(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); @@ -780,17 +791,17 @@ static void skip_emulated_instruction(struct kvm_vcpu *vcpu) } if (!svm->next_rip) { - if (kvm_emulate_instruction(vcpu, EMULTYPE_SKIP) != - EMULATE_DONE) - printk(KERN_DEBUG "%s: NOP\n", __func__); - return; + if (!kvm_emulate_instruction(vcpu, EMULTYPE_SKIP)) + return 0; + } else { + if (svm->next_rip - kvm_rip_read(vcpu) > MAX_INST_SIZE) + pr_err("%s: ip 0x%lx next 0x%llx\n", + __func__, kvm_rip_read(vcpu), svm->next_rip); + kvm_rip_write(vcpu, svm->next_rip); } - if (svm->next_rip - kvm_rip_read(vcpu) > MAX_INST_SIZE) - printk(KERN_ERR "%s: ip 0x%lx next 0x%llx\n", - __func__, kvm_rip_read(vcpu), svm->next_rip); - - kvm_rip_write(vcpu, svm->next_rip); svm_set_interrupt_shadow(vcpu, 0); + + return 1; } static void svm_queue_exception(struct kvm_vcpu *vcpu) @@ -821,7 +832,7 @@ static void svm_queue_exception(struct kvm_vcpu *vcpu) * raises a fault that is not intercepted. Still better than * failing in all cases. */ - skip_emulated_instruction(&svm->vcpu); + (void)skip_emulated_instruction(&svm->vcpu); rip = kvm_rip_read(&svm->vcpu); svm->int3_rip = rip + svm->vmcb->save.cs.base; svm->int3_injected = rip - old_rip; @@ -1231,11 +1242,15 @@ static __init int sev_hardware_setup(void) /* Minimum ASID value that should be used for SEV guest */ min_sev_asid = cpuid_edx(0x8000001F); - /* Initialize SEV ASID bitmap */ + /* Initialize SEV ASID bitmaps */ sev_asid_bitmap = bitmap_zalloc(max_sev_asid, GFP_KERNEL); if (!sev_asid_bitmap) return 1; + sev_reclaim_asid_bitmap = bitmap_zalloc(max_sev_asid, GFP_KERNEL); + if (!sev_reclaim_asid_bitmap) + return 1; + status = kmalloc(sizeof(*status), GFP_KERNEL); if (!status) return 1; @@ -1269,11 +1284,11 @@ static void grow_ple_window(struct kvm_vcpu *vcpu) pause_filter_count_grow, pause_filter_count_max); - if (control->pause_filter_count != old) + if (control->pause_filter_count != old) { mark_dirty(svm->vmcb, VMCB_INTERCEPTS); - - trace_kvm_ple_window_grow(vcpu->vcpu_id, - control->pause_filter_count, old); + trace_kvm_ple_window_update(vcpu->vcpu_id, + control->pause_filter_count, old); + } } static void shrink_ple_window(struct kvm_vcpu *vcpu) @@ -1287,11 +1302,52 @@ static void shrink_ple_window(struct kvm_vcpu *vcpu) pause_filter_count, pause_filter_count_shrink, pause_filter_count); - if (control->pause_filter_count != old) + if (control->pause_filter_count != old) { mark_dirty(svm->vmcb, VMCB_INTERCEPTS); + trace_kvm_ple_window_update(vcpu->vcpu_id, + control->pause_filter_count, old); + } +} - trace_kvm_ple_window_shrink(vcpu->vcpu_id, - control->pause_filter_count, old); +/* + * The default MMIO mask is a single bit (excluding the present bit), + * which could conflict with the memory encryption bit. Check for + * memory encryption support and override the default MMIO mask if + * memory encryption is enabled. + */ +static __init void svm_adjust_mmio_mask(void) +{ + unsigned int enc_bit, mask_bit; + u64 msr, mask; + + /* If there is no memory encryption support, use existing mask */ + if (cpuid_eax(0x80000000) < 0x8000001f) + return; + + /* If memory encryption is not enabled, use existing mask */ + rdmsrl(MSR_K8_SYSCFG, msr); + if (!(msr & MSR_K8_SYSCFG_MEM_ENCRYPT)) + return; + + enc_bit = cpuid_ebx(0x8000001f) & 0x3f; + mask_bit = boot_cpu_data.x86_phys_bits; + + /* Increment the mask bit if it is the same as the encryption bit */ + if (enc_bit == mask_bit) + mask_bit++; + + /* + * If the mask bit location is below 52, then some bits above the + * physical addressing limit will always be reserved, so use the + * rsvd_bits() function to generate the mask. This mask, along with + * the present bit, will be used to generate a page fault with + * PFER.RSV = 1. + * + * If the mask bit location is 52 (or above), then clear the mask. + */ + mask = (mask_bit < 52) ? rsvd_bits(mask_bit, 51) | PT_PRESENT_MASK : 0; + + kvm_mmu_set_mmio_spte_mask(mask, mask, PT_WRITABLE_MASK | PT_USER_MASK); } static __init int svm_hardware_setup(void) @@ -1348,6 +1404,8 @@ static __init int svm_hardware_setup(void) } } + svm_adjust_mmio_mask(); + for_each_possible_cpu(cpu) { r = svm_cpu_init(cpu); if (r) @@ -1414,8 +1472,12 @@ static __exit void svm_hardware_unsetup(void) { int cpu; - if (svm_sev_enabled()) + if (svm_sev_enabled()) { bitmap_free(sev_asid_bitmap); + bitmap_free(sev_reclaim_asid_bitmap); + + sev_flush_asids(); + } for_each_possible_cpu(cpu) svm_cpu_uninit(cpu); @@ -1485,7 +1547,10 @@ static void avic_init_vmcb(struct vcpu_svm *svm) vmcb->control.avic_logical_id = lpa & AVIC_HPA_MASK; vmcb->control.avic_physical_id = ppa & AVIC_HPA_MASK; vmcb->control.avic_physical_id |= AVIC_MAX_PHYSICAL_ID_COUNT; - vmcb->control.int_ctl |= AVIC_ENABLE_MASK; + if (kvm_apicv_activated(svm->vcpu.kvm)) + vmcb->control.int_ctl |= AVIC_ENABLE_MASK; + else + vmcb->control.int_ctl &= ~AVIC_ENABLE_MASK; } static void init_vmcb(struct vcpu_svm *svm) @@ -1542,6 +1607,7 @@ static void init_vmcb(struct vcpu_svm *svm) set_intercept(svm, INTERCEPT_SKINIT); set_intercept(svm, INTERCEPT_WBINVD); set_intercept(svm, INTERCEPT_XSETBV); + set_intercept(svm, INTERCEPT_RDPRU); set_intercept(svm, INTERCEPT_RSM); if (!kvm_mwait_in_guest(svm->vcpu.kvm)) { @@ -1668,23 +1734,28 @@ static u64 *avic_get_physical_id_entry(struct kvm_vcpu *vcpu, * field of the VMCB. Therefore, we set up the * APIC_ACCESS_PAGE_PRIVATE_MEMSLOT (4KB) here. */ -static int avic_init_access_page(struct kvm_vcpu *vcpu) +static int avic_update_access_page(struct kvm *kvm, bool activate) { - struct kvm *kvm = vcpu->kvm; int ret = 0; mutex_lock(&kvm->slots_lock); - if (kvm->arch.apic_access_page_done) + /* + * During kvm_destroy_vm(), kvm_pit_set_reinject() could trigger + * APICv mode change, which update APIC_ACCESS_PAGE_PRIVATE_MEMSLOT + * memory region. So, we need to ensure that kvm->mm == current->mm. + */ + if ((kvm->arch.apic_access_page_done == activate) || + (kvm->mm != current->mm)) goto out; ret = __x86_set_memory_region(kvm, APIC_ACCESS_PAGE_PRIVATE_MEMSLOT, APIC_DEFAULT_PHYS_BASE, - PAGE_SIZE); + activate ? PAGE_SIZE : 0); if (ret) goto out; - kvm->arch.apic_access_page_done = true; + kvm->arch.apic_access_page_done = activate; out: mutex_unlock(&kvm->slots_lock); return ret; @@ -1692,21 +1763,24 @@ out: static int avic_init_backing_page(struct kvm_vcpu *vcpu) { - int ret; u64 *entry, new_entry; int id = vcpu->vcpu_id; struct vcpu_svm *svm = to_svm(vcpu); - ret = avic_init_access_page(vcpu); - if (ret) - return ret; - if (id >= AVIC_MAX_PHYSICAL_ID_COUNT) return -EINVAL; if (!svm->vcpu.arch.apic->regs) return -EINVAL; + if (kvm_apicv_activated(vcpu->kvm)) { + int ret; + + ret = avic_update_access_page(vcpu->kvm, true); + if (ret) + return ret; + } + svm->avic_backing_page = virt_to_page(svm->vcpu.arch.apic->regs); /* Setting AVIC backing page address in the phy APIC ID table */ @@ -1714,7 +1788,6 @@ static int avic_init_backing_page(struct kvm_vcpu *vcpu) if (!entry) return -EINVAL; - new_entry = READ_ONCE(*entry); new_entry = __sme_set((page_to_phys(svm->avic_backing_page) & AVIC_PHYSICAL_ID_ENTRY_BACKING_PAGE_MASK) | AVIC_PHYSICAL_ID_ENTRY_VALID_MASK); @@ -1725,25 +1798,22 @@ static int avic_init_backing_page(struct kvm_vcpu *vcpu) return 0; } -static void __sev_asid_free(int asid) +static void sev_asid_free(int asid) { struct svm_cpu_data *sd; int cpu, pos; + mutex_lock(&sev_bitmap_lock); + pos = asid - 1; - clear_bit(pos, sev_asid_bitmap); + __set_bit(pos, sev_reclaim_asid_bitmap); for_each_possible_cpu(cpu) { sd = per_cpu(svm_data, cpu); sd->sev_vmcbs[pos] = NULL; } -} - -static void sev_asid_free(struct kvm *kvm) -{ - struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info; - __sev_asid_free(sev->asid); + mutex_unlock(&sev_bitmap_lock); } static void sev_unbind_asid(struct kvm *kvm, unsigned int handle) @@ -1760,10 +1830,12 @@ static void sev_unbind_asid(struct kvm *kvm, unsigned int handle) /* deactivate handle */ data->handle = handle; + + /* Guard DEACTIVATE against WBINVD/DF_FLUSH used in ASID recycling */ + down_read(&sev_deactivate_lock); sev_guest_deactivate(data, NULL); + up_read(&sev_deactivate_lock); - wbinvd_on_all_cpus(); - sev_guest_df_flush(NULL); kfree(data); decommission = kzalloc(sizeof(*decommission), GFP_KERNEL); @@ -1912,7 +1984,7 @@ static void sev_vm_destroy(struct kvm *kvm) mutex_unlock(&kvm->lock); sev_unbind_asid(kvm, sev->handle); - sev_asid_free(kvm); + sev_asid_free(sev->asid); } static void avic_vm_destroy(struct kvm *kvm) @@ -1993,6 +2065,18 @@ free_avic: return err; } +static int svm_vm_init(struct kvm *kvm) +{ + if (avic) { + int ret = avic_vm_init(kvm); + if (ret) + return ret; + } + + kvm_apicv_init(kvm, avic); + return 0; +} + static inline int avic_update_iommu_vcpu_affinity(struct kvm_vcpu *vcpu, int cpu, bool r) { @@ -2091,7 +2175,6 @@ static void svm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) u32 dummy; u32 eax = 1; - vcpu->arch.microcode_version = 0x01000065; svm->spec_ctrl = 0; svm->virt_spec_ctrl = 0; @@ -2128,7 +2211,7 @@ static int avic_init_vcpu(struct vcpu_svm *svm) return ret; } -static struct kvm_vcpu *svm_create_vcpu(struct kvm *kvm, unsigned int id) +static int svm_create_vcpu(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm; struct page *page; @@ -2137,36 +2220,13 @@ static struct kvm_vcpu *svm_create_vcpu(struct kvm *kvm, unsigned int id) struct page *nested_msrpm_pages; int err; - svm = kmem_cache_zalloc(kvm_vcpu_cache, GFP_KERNEL_ACCOUNT); - if (!svm) { - err = -ENOMEM; - goto out; - } - - svm->vcpu.arch.user_fpu = kmem_cache_zalloc(x86_fpu_cache, - GFP_KERNEL_ACCOUNT); - if (!svm->vcpu.arch.user_fpu) { - printk(KERN_ERR "kvm: failed to allocate kvm userspace's fpu\n"); - err = -ENOMEM; - goto free_partial_svm; - } - - svm->vcpu.arch.guest_fpu = kmem_cache_zalloc(x86_fpu_cache, - GFP_KERNEL_ACCOUNT); - if (!svm->vcpu.arch.guest_fpu) { - printk(KERN_ERR "kvm: failed to allocate vcpu's fpu\n"); - err = -ENOMEM; - goto free_user_fpu; - } - - err = kvm_vcpu_init(&svm->vcpu, kvm, id); - if (err) - goto free_svm; + BUILD_BUG_ON(offsetof(struct vcpu_svm, vcpu) != 0); + svm = to_svm(vcpu); err = -ENOMEM; page = alloc_page(GFP_KERNEL_ACCOUNT); if (!page) - goto uninit; + goto out; msrpm_pages = alloc_pages(GFP_KERNEL_ACCOUNT, MSRPM_ALLOC_ORDER); if (!msrpm_pages) @@ -2187,7 +2247,8 @@ static struct kvm_vcpu *svm_create_vcpu(struct kvm *kvm, unsigned int id) /* We initialize this flag to true to make sure that the is_running * bit would be set the first time the vcpu is loaded. */ - svm->avic_is_running = true; + if (irqchip_in_kernel(vcpu->kvm) && kvm_apicv_activated(vcpu->kvm)) + svm->avic_is_running = true; svm->nested.hsave = page_address(hsave_page); @@ -2203,9 +2264,10 @@ static struct kvm_vcpu *svm_create_vcpu(struct kvm *kvm, unsigned int id) svm->asid_generation = 0; init_vmcb(svm); - svm_init_osvw(&svm->vcpu); + svm_init_osvw(vcpu); + vcpu->arch.microcode_version = 0x01000065; - return &svm->vcpu; + return 0; free_page4: __free_page(hsave_page); @@ -2215,16 +2277,8 @@ free_page2: __free_pages(msrpm_pages, MSRPM_ALLOC_ORDER); free_page1: __free_page(page); -uninit: - kvm_vcpu_uninit(&svm->vcpu); -free_svm: - kmem_cache_free(x86_fpu_cache, svm->vcpu.arch.guest_fpu); -free_user_fpu: - kmem_cache_free(x86_fpu_cache, svm->vcpu.arch.user_fpu); -free_partial_svm: - kmem_cache_free(kvm_vcpu_cache, svm); out: - return ERR_PTR(err); + return err; } static void svm_clear_current_vmcb(struct vmcb *vmcb) @@ -2250,10 +2304,6 @@ static void svm_free_vcpu(struct kvm_vcpu *vcpu) __free_pages(virt_to_page(svm->msrpm), MSRPM_ALLOC_ORDER); __free_page(virt_to_page(svm->nested.hsave)); __free_pages(virt_to_page(svm->nested.msrpm), MSRPM_ALLOC_ORDER); - kvm_vcpu_uninit(vcpu); - kmem_cache_free(x86_fpu_cache, svm->vcpu.arch.user_fpu); - kmem_cache_free(x86_fpu_cache, svm->vcpu.arch.guest_fpu); - kmem_cache_free(kvm_vcpu_cache, svm); } static void svm_vcpu_load(struct kvm_vcpu *vcpu, int cpu) @@ -2324,6 +2374,8 @@ static void svm_vcpu_blocking(struct kvm_vcpu *vcpu) static void svm_vcpu_unblocking(struct kvm_vcpu *vcpu) { + if (kvm_check_request(KVM_REQ_APICV_UPDATE, vcpu)) + kvm_vcpu_update_apicv(vcpu); avic_set_running(vcpu, true); } @@ -2363,7 +2415,7 @@ static void svm_cache_reg(struct kvm_vcpu *vcpu, enum kvm_reg reg) load_pdptrs(vcpu, vcpu->arch.walk_mmu, kvm_read_cr3(vcpu)); break; default: - BUG(); + WARN_ON_ONCE(1); } } @@ -2516,10 +2568,6 @@ static void svm_decache_cr0_guest_bits(struct kvm_vcpu *vcpu) { } -static void svm_decache_cr3(struct kvm_vcpu *vcpu) -{ -} - static void svm_decache_cr4_guest_bits(struct kvm_vcpu *vcpu) { } @@ -2769,17 +2817,18 @@ static int gp_interception(struct vcpu_svm *svm) { struct kvm_vcpu *vcpu = &svm->vcpu; u32 error_code = svm->vmcb->control.exit_info_1; - int er; WARN_ON_ONCE(!enable_vmware_backdoor); - er = kvm_emulate_instruction(vcpu, - EMULTYPE_VMWARE | EMULTYPE_NO_UD_ON_FAIL); - if (er == EMULATE_USER_EXIT) - return 0; - else if (er != EMULATE_DONE) + /* + * VMware backdoor emulation on #GP interception only handles IN{S}, + * OUT{S}, and RDPMC, none of which generate a non-zero error code. + */ + if (error_code) { kvm_queue_exception_e(vcpu, GP_VECTOR, error_code); - return 1; + return 1; + } + return kvm_emulate_instruction(vcpu, EMULTYPE_VMWARE_GP); } static bool is_erratum_383(void) @@ -2877,7 +2926,7 @@ static int io_interception(struct vcpu_svm *svm) string = (io_info & SVM_IOIO_STR_MASK) != 0; in = (io_info & SVM_IOIO_TYPE_MASK) != 0; if (string) - return kvm_emulate_instruction(vcpu, 0) == EMULATE_DONE; + return kvm_emulate_instruction(vcpu, 0); port = io_info >> 16; size = (io_info & SVM_IOIO_SIZE_MASK) >> SVM_IOIO_SIZE_SHIFT; @@ -2904,13 +2953,11 @@ static int nop_on_interception(struct vcpu_svm *svm) static int halt_interception(struct vcpu_svm *svm) { - svm->next_rip = kvm_rip_read(&svm->vcpu) + 1; return kvm_emulate_halt(&svm->vcpu); } static int vmmcall_interception(struct vcpu_svm *svm) { - svm->next_rip = kvm_rip_read(&svm->vcpu) + 3; return kvm_emulate_hypercall(&svm->vcpu); } @@ -3589,9 +3636,9 @@ static void enter_svm_guest_mode(struct vcpu_svm *svm, u64 vmcb_gpa, mark_all_dirty(svm->vmcb); } -static bool nested_svm_vmrun(struct vcpu_svm *svm) +static int nested_svm_vmrun(struct vcpu_svm *svm) { - int rc; + int ret; struct vmcb *nested_vmcb; struct vmcb *hsave = svm->nested.hsave; struct vmcb *vmcb = svm->vmcb; @@ -3600,13 +3647,16 @@ static bool nested_svm_vmrun(struct vcpu_svm *svm) vmcb_gpa = svm->vmcb->save.rax; - rc = kvm_vcpu_map(&svm->vcpu, gpa_to_gfn(vmcb_gpa), &map); - if (rc) { - if (rc == -EINVAL) - kvm_inject_gp(&svm->vcpu, 0); - return false; + ret = kvm_vcpu_map(&svm->vcpu, gpa_to_gfn(vmcb_gpa), &map); + if (ret == -EINVAL) { + kvm_inject_gp(&svm->vcpu, 0); + return 1; + } else if (ret) { + return kvm_skip_emulated_instruction(&svm->vcpu); } + ret = kvm_skip_emulated_instruction(&svm->vcpu); + nested_vmcb = map.hva; if (!nested_vmcb_checks(nested_vmcb)) { @@ -3617,7 +3667,7 @@ static bool nested_svm_vmrun(struct vcpu_svm *svm) kvm_vcpu_unmap(&svm->vcpu, &map, true); - return false; + return ret; } trace_kvm_nested_vmrun(svm->vmcb->save.rip, vmcb_gpa, @@ -3661,7 +3711,16 @@ static bool nested_svm_vmrun(struct vcpu_svm *svm) enter_svm_guest_mode(svm, vmcb_gpa, nested_vmcb, &map); - return true; + if (!nested_svm_vmrun_msrpm(svm)) { + svm->vmcb->control.exit_code = SVM_EXIT_ERR; + svm->vmcb->control.exit_code_hi = 0; + svm->vmcb->control.exit_info_1 = 0; + svm->vmcb->control.exit_info_2 = 0; + + nested_svm_vmexit(svm); + } + + return ret; } static void nested_svm_vmloadsave(struct vmcb *from_vmcb, struct vmcb *to_vmcb) @@ -3698,7 +3757,6 @@ static int vmload_interception(struct vcpu_svm *svm) nested_vmcb = map.hva; - svm->next_rip = kvm_rip_read(&svm->vcpu) + 3; ret = kvm_skip_emulated_instruction(&svm->vcpu); nested_svm_vmloadsave(nested_vmcb, svm->vmcb); @@ -3725,7 +3783,6 @@ static int vmsave_interception(struct vcpu_svm *svm) nested_vmcb = map.hva; - svm->next_rip = kvm_rip_read(&svm->vcpu) + 3; ret = kvm_skip_emulated_instruction(&svm->vcpu); nested_svm_vmloadsave(svm->vmcb, nested_vmcb); @@ -3739,27 +3796,7 @@ static int vmrun_interception(struct vcpu_svm *svm) if (nested_svm_check_permissions(svm)) return 1; - /* Save rip after vmrun instruction */ - kvm_rip_write(&svm->vcpu, kvm_rip_read(&svm->vcpu) + 3); - - if (!nested_svm_vmrun(svm)) - return 1; - - if (!nested_svm_vmrun_msrpm(svm)) - goto failed; - - return 1; - -failed: - - svm->vmcb->control.exit_code = SVM_EXIT_ERR; - svm->vmcb->control.exit_code_hi = 0; - svm->vmcb->control.exit_info_1 = 0; - svm->vmcb->control.exit_info_2 = 0; - - nested_svm_vmexit(svm); - - return 1; + return nested_svm_vmrun(svm); } static int stgi_interception(struct vcpu_svm *svm) @@ -3776,7 +3813,6 @@ static int stgi_interception(struct vcpu_svm *svm) if (vgif_enabled(svm)) clr_intercept(svm, INTERCEPT_STGI); - svm->next_rip = kvm_rip_read(&svm->vcpu) + 3; ret = kvm_skip_emulated_instruction(&svm->vcpu); kvm_make_request(KVM_REQ_EVENT, &svm->vcpu); @@ -3792,7 +3828,6 @@ static int clgi_interception(struct vcpu_svm *svm) if (nested_svm_check_permissions(svm)) return 1; - svm->next_rip = kvm_rip_read(&svm->vcpu) + 3; ret = kvm_skip_emulated_instruction(&svm->vcpu); disable_gif(svm); @@ -3817,7 +3852,6 @@ static int invlpga_interception(struct vcpu_svm *svm) /* Let's treat INVLPGA the same as INVLPG (can be optimized!) */ kvm_mmu_invlpg(vcpu, kvm_rax_read(&svm->vcpu)); - svm->next_rip = kvm_rip_read(&svm->vcpu) + 3; return kvm_skip_emulated_instruction(&svm->vcpu); } @@ -3840,13 +3874,18 @@ static int xsetbv_interception(struct vcpu_svm *svm) u32 index = kvm_rcx_read(&svm->vcpu); if (kvm_set_xcr(&svm->vcpu, index, new_bv) == 0) { - svm->next_rip = kvm_rip_read(&svm->vcpu) + 3; return kvm_skip_emulated_instruction(&svm->vcpu); } return 1; } +static int rdpru_interception(struct vcpu_svm *svm) +{ + kvm_queue_exception(&svm->vcpu, UD_VECTOR); + return 1; +} + static int task_switch_interception(struct vcpu_svm *svm) { u16 tss_selector; @@ -3899,25 +3938,20 @@ static int task_switch_interception(struct vcpu_svm *svm) if (reason != TASK_SWITCH_GATE || int_type == SVM_EXITINTINFO_TYPE_SOFT || (int_type == SVM_EXITINTINFO_TYPE_EXEPT && - (int_vec == OF_VECTOR || int_vec == BP_VECTOR))) - skip_emulated_instruction(&svm->vcpu); + (int_vec == OF_VECTOR || int_vec == BP_VECTOR))) { + if (!skip_emulated_instruction(&svm->vcpu)) + return 0; + } if (int_type != SVM_EXITINTINFO_TYPE_SOFT) int_vec = -1; - if (kvm_task_switch(&svm->vcpu, tss_selector, int_vec, reason, - has_error_code, error_code) == EMULATE_FAIL) { - svm->vcpu.run->exit_reason = KVM_EXIT_INTERNAL_ERROR; - svm->vcpu.run->internal.suberror = KVM_INTERNAL_ERROR_EMULATION; - svm->vcpu.run->internal.ndata = 0; - return 0; - } - return 1; + return kvm_task_switch(&svm->vcpu, tss_selector, int_vec, reason, + has_error_code, error_code); } static int cpuid_interception(struct vcpu_svm *svm) { - svm->next_rip = kvm_rip_read(&svm->vcpu) + 2; return kvm_emulate_cpuid(&svm->vcpu); } @@ -3934,7 +3968,7 @@ static int iret_interception(struct vcpu_svm *svm) static int invlpg_interception(struct vcpu_svm *svm) { if (!static_cpu_has(X86_FEATURE_DECODEASSISTS)) - return kvm_emulate_instruction(&svm->vcpu, 0) == EMULATE_DONE; + return kvm_emulate_instruction(&svm->vcpu, 0); kvm_mmu_invlpg(&svm->vcpu, svm->vmcb->control.exit_info_1); return kvm_skip_emulated_instruction(&svm->vcpu); @@ -3942,13 +3976,12 @@ static int invlpg_interception(struct vcpu_svm *svm) static int emulate_on_interception(struct vcpu_svm *svm) { - return kvm_emulate_instruction(&svm->vcpu, 0) == EMULATE_DONE; + return kvm_emulate_instruction(&svm->vcpu, 0); } static int rsm_interception(struct vcpu_svm *svm) { - return kvm_emulate_instruction_from_buffer(&svm->vcpu, - rsm_ins_bytes, 2) == EMULATE_DONE; + return kvm_emulate_instruction_from_buffer(&svm->vcpu, rsm_ins_bytes, 2); } static int rdpmc_interception(struct vcpu_svm *svm) @@ -4192,6 +4225,8 @@ static int svm_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) break; case MSR_IA32_SPEC_CTRL: if (!msr_info->host_initiated && + !guest_cpuid_has(vcpu, X86_FEATURE_SPEC_CTRL) && + !guest_cpuid_has(vcpu, X86_FEATURE_AMD_STIBP) && !guest_cpuid_has(vcpu, X86_FEATURE_AMD_IBRS) && !guest_cpuid_has(vcpu, X86_FEATURE_AMD_SSBD)) return 1; @@ -4233,23 +4268,7 @@ static int svm_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) static int rdmsr_interception(struct vcpu_svm *svm) { - u32 ecx = kvm_rcx_read(&svm->vcpu); - struct msr_data msr_info; - - msr_info.index = ecx; - msr_info.host_initiated = false; - if (svm_get_msr(&svm->vcpu, &msr_info)) { - trace_kvm_msr_read_ex(ecx); - kvm_inject_gp(&svm->vcpu, 0); - return 1; - } else { - trace_kvm_msr_read(ecx, msr_info.data); - - kvm_rax_write(&svm->vcpu, msr_info.data & 0xffffffff); - kvm_rdx_write(&svm->vcpu, msr_info.data >> 32); - svm->next_rip = kvm_rip_read(&svm->vcpu) + 2; - return kvm_skip_emulated_instruction(&svm->vcpu); - } + return kvm_emulate_rdmsr(&svm->vcpu); } static int svm_set_vm_cr(struct kvm_vcpu *vcpu, u64 data) @@ -4293,16 +4312,16 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr) break; case MSR_IA32_SPEC_CTRL: if (!msr->host_initiated && + !guest_cpuid_has(vcpu, X86_FEATURE_SPEC_CTRL) && + !guest_cpuid_has(vcpu, X86_FEATURE_AMD_STIBP) && !guest_cpuid_has(vcpu, X86_FEATURE_AMD_IBRS) && !guest_cpuid_has(vcpu, X86_FEATURE_AMD_SSBD)) return 1; - /* The STIBP bit doesn't fault even if it's not advertised */ - if (data & ~(SPEC_CTRL_IBRS | SPEC_CTRL_STIBP | SPEC_CTRL_SSBD)) + if (data & ~kvm_spec_ctrl_valid_bits(vcpu)) return 1; svm->spec_ctrl = data; - if (!data) break; @@ -4326,13 +4345,12 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr) if (data & ~PRED_CMD_IBPB) return 1; - + if (!boot_cpu_has(X86_FEATURE_AMD_IBPB)) + return 1; if (!data) break; wrmsrl(MSR_IA32_PRED_CMD, PRED_CMD_IBPB); - if (is_guest_mode(vcpu)) - break; set_msr_interception(svm->msrpm, MSR_IA32_PRED_CMD, 0, 1); break; case MSR_AMD64_VIRT_SPEC_CTRL: @@ -4439,23 +4457,7 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr) static int wrmsr_interception(struct vcpu_svm *svm) { - struct msr_data msr; - u32 ecx = kvm_rcx_read(&svm->vcpu); - u64 data = kvm_read_edx_eax(&svm->vcpu); - - msr.data = data; - msr.index = ecx; - msr.host_initiated = false; - - svm->next_rip = kvm_rip_read(&svm->vcpu) + 2; - if (kvm_set_msr(&svm->vcpu, &msr)) { - trace_kvm_msr_write_ex(ecx, data); - kvm_inject_gp(&svm->vcpu, 0); - return 1; - } else { - trace_kvm_msr_write(ecx, data); - return kvm_skip_emulated_instruction(&svm->vcpu); - } + return kvm_emulate_wrmsr(&svm->vcpu); } static int msr_interception(struct vcpu_svm *svm) @@ -4470,6 +4472,14 @@ static int interrupt_window_interception(struct vcpu_svm *svm) { kvm_make_request(KVM_REQ_EVENT, &svm->vcpu); svm_clear_vintr(svm); + + /* + * For AVIC, the only reason to end up here is ExtINTs. + * In this case AVIC was temporarily disabled for + * requesting the IRQ window and we have to re-enable it. + */ + svm_toggle_avic_for_irq_window(&svm->vcpu, true); + svm->vmcb->control.int_ctl &= ~V_IRQ_MASK; mark_dirty(svm->vmcb, VMCB_INTR); ++svm->vcpu.stat.irq_window_exits; @@ -4551,9 +4561,9 @@ static int avic_incomplete_ipi_interception(struct vcpu_svm *svm) */ kvm_for_each_vcpu(i, vcpu, kvm) { bool m = kvm_apic_match_dest(vcpu, apic, - icrl & KVM_APIC_SHORT_MASK, + icrl & APIC_SHORT_MASK, GET_APIC_DEST_FIELD(icrh), - icrl & KVM_APIC_DEST_MASK); + icrl & APIC_DEST_MASK); if (m && !avic_vcpu_is_running(vcpu)) kvm_vcpu_wake_up(vcpu); @@ -4637,6 +4647,7 @@ static int avic_handle_ldr_update(struct kvm_vcpu *vcpu) int ret = 0; struct vcpu_svm *svm = to_svm(vcpu); u32 ldr = kvm_lapic_get_reg(vcpu->arch.apic, APIC_LDR); + u32 id = kvm_xapic_id(vcpu->arch.apic); if (ldr == svm->ldr_reg) return 0; @@ -4644,7 +4655,7 @@ static int avic_handle_ldr_update(struct kvm_vcpu *vcpu) avic_invalidate_logical_id_entry(vcpu); if (ldr) - ret = avic_ldr_write(vcpu, vcpu->vcpu_id, ldr); + ret = avic_ldr_write(vcpu, id, ldr); if (!ret) svm->ldr_reg = ldr; @@ -4656,8 +4667,7 @@ static int avic_handle_apic_id_update(struct kvm_vcpu *vcpu) { u64 *old, *new; struct vcpu_svm *svm = to_svm(vcpu); - u32 apic_id_reg = kvm_lapic_get_reg(vcpu->arch.apic, APIC_ID); - u32 id = (apic_id_reg >> 24) & 0xff; + u32 id = kvm_xapic_id(vcpu->arch.apic); if (vcpu->vcpu_id == id) return 0; @@ -4769,7 +4779,7 @@ static int avic_unaccelerated_access_interception(struct vcpu_svm *svm) ret = avic_unaccel_trap_write(svm); } else { /* Handling Fault */ - ret = (kvm_emulate_instruction(&svm->vcpu, 0) == EMULATE_DONE); + ret = kvm_emulate_instruction(&svm->vcpu, 0); } return ret; @@ -4836,6 +4846,7 @@ static int (*const svm_exit_handlers[])(struct vcpu_svm *svm) = { [SVM_EXIT_MONITOR] = monitor_interception, [SVM_EXIT_MWAIT] = mwait_interception, [SVM_EXIT_XSETBV] = xsetbv_interception, + [SVM_EXIT_RDPRU] = rdpru_interception, [SVM_EXIT_NPF] = npf_interception, [SVM_EXIT_RSM] = rsm_interception, [SVM_EXIT_AVIC_INCOMPLETE_IPI] = avic_incomplete_ipi_interception, @@ -4966,7 +4977,8 @@ static void svm_get_exit_info(struct kvm_vcpu *vcpu, u64 *info1, u64 *info2) *info2 = control->exit_info_2; } -static int handle_exit(struct kvm_vcpu *vcpu) +static int handle_exit(struct kvm_vcpu *vcpu, + enum exit_fastpath_completion exit_fastpath) { struct vcpu_svm *svm = to_svm(vcpu); struct kvm_run *kvm_run = vcpu->run; @@ -5024,13 +5036,33 @@ static int handle_exit(struct kvm_vcpu *vcpu) __func__, svm->vmcb->control.exit_int_info, exit_code); - if (exit_code >= ARRAY_SIZE(svm_exit_handlers) - || !svm_exit_handlers[exit_code]) { - WARN_ONCE(1, "svm: unexpected exit reason 0x%x\n", exit_code); - kvm_queue_exception(vcpu, UD_VECTOR); + if (exit_fastpath == EXIT_FASTPATH_SKIP_EMUL_INS) { + kvm_skip_emulated_instruction(vcpu); return 1; + } else if (exit_code >= ARRAY_SIZE(svm_exit_handlers) + || !svm_exit_handlers[exit_code]) { + vcpu_unimpl(vcpu, "svm: unexpected exit reason 0x%x\n", exit_code); + dump_vmcb(vcpu); + vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR; + vcpu->run->internal.suberror = + KVM_INTERNAL_ERROR_UNEXPECTED_EXIT_REASON; + vcpu->run->internal.ndata = 1; + vcpu->run->internal.data[0] = exit_code; + return 0; } +#ifdef CONFIG_RETPOLINE + if (exit_code == SVM_EXIT_MSR) + return msr_interception(svm); + else if (exit_code == SVM_EXIT_VINTR) + return interrupt_window_interception(svm); + else if (exit_code == SVM_EXIT_INTR) + return intr_interception(svm); + else if (exit_code == SVM_EXIT_HLT) + return halt_interception(svm); + else if (exit_code == SVM_EXIT_NPF) + return npf_interception(svm); +#endif return svm_exit_handlers[exit_code](svm); } @@ -5126,8 +5158,7 @@ static void update_cr8_intercept(struct kvm_vcpu *vcpu, int tpr, int irr) { struct vcpu_svm *svm = to_svm(vcpu); - if (svm_nested_virtualize_tpr(vcpu) || - kvm_vcpu_apicv_active(vcpu)) + if (svm_nested_virtualize_tpr(vcpu)) return; clr_cr_intercept(svm, INTERCEPT_CR8_WRITE); @@ -5144,30 +5175,79 @@ static void svm_set_virtual_apic_mode(struct kvm_vcpu *vcpu) return; } -static bool svm_get_enable_apicv(struct kvm_vcpu *vcpu) +static void svm_hwapic_irr_update(struct kvm_vcpu *vcpu, int max_irr) { - return avic && irqchip_split(vcpu->kvm); } -static void svm_hwapic_irr_update(struct kvm_vcpu *vcpu, int max_irr) +static void svm_hwapic_isr_update(struct kvm_vcpu *vcpu, int max_isr) { } -static void svm_hwapic_isr_update(struct kvm_vcpu *vcpu, int max_isr) +static void svm_toggle_avic_for_irq_window(struct kvm_vcpu *vcpu, bool activate) { + if (!avic || !lapic_in_kernel(vcpu)) + return; + + srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx); + kvm_request_apicv_update(vcpu->kvm, activate, + APICV_INHIBIT_REASON_IRQWIN); + vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu); +} + +static int svm_set_pi_irte_mode(struct kvm_vcpu *vcpu, bool activate) +{ + int ret = 0; + unsigned long flags; + struct amd_svm_iommu_ir *ir; + struct vcpu_svm *svm = to_svm(vcpu); + + if (!kvm_arch_has_assigned_device(vcpu->kvm)) + return 0; + + /* + * Here, we go through the per-vcpu ir_list to update all existing + * interrupt remapping table entry targeting this vcpu. + */ + spin_lock_irqsave(&svm->ir_list_lock, flags); + + if (list_empty(&svm->ir_list)) + goto out; + + list_for_each_entry(ir, &svm->ir_list, node) { + if (activate) + ret = amd_iommu_activate_guest_mode(ir->data); + else + ret = amd_iommu_deactivate_guest_mode(ir->data); + if (ret) + break; + } +out: + spin_unlock_irqrestore(&svm->ir_list_lock, flags); + return ret; } -/* Note: Currently only used by Hyper-V. */ static void svm_refresh_apicv_exec_ctrl(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); struct vmcb *vmcb = svm->vmcb; + bool activated = kvm_vcpu_apicv_active(vcpu); - if (kvm_vcpu_apicv_active(vcpu)) + if (activated) { + /** + * During AVIC temporary deactivation, guest could update + * APIC ID, DFR and LDR registers, which would not be trapped + * by avic_unaccelerated_access_interception(). In this case, + * we need to check and update the AVIC logical APIC ID table + * accordingly before re-activating. + */ + avic_post_state_restore(vcpu); vmcb->control.int_ctl |= AVIC_ENABLE_MASK; - else + } else { vmcb->control.int_ctl &= ~AVIC_ENABLE_MASK; + } mark_dirty(vmcb, VMCB_AVIC); + + svm_set_pi_irte_mode(vcpu, activated); } static void svm_load_eoi_exitmap(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap) @@ -5275,7 +5355,8 @@ get_pi_vcpu_info(struct kvm *kvm, struct kvm_kernel_irq_routing_entry *e, kvm_set_msi_irq(kvm, e, &irq); - if (!kvm_intr_is_single_vcpu(kvm, &irq, &vcpu)) { + if (!kvm_intr_is_single_vcpu(kvm, &irq, &vcpu) || + !kvm_irq_is_postable(&irq)) { pr_debug("SVM: %s: use legacy intr remap mode for irq %u\n", __func__, irq.vector); return -1; @@ -5329,6 +5410,7 @@ static int svm_update_pi_irte(struct kvm *kvm, unsigned int host_irq, * 1. When cannot target interrupt to a specific vcpu. * 2. Unsetting posted interrupt. * 3. APIC virtialization is disabled for the vcpu. + * 4. IRQ has incompatible delivery mode (SMI, INIT, etc) */ if (!get_pi_vcpu_info(kvm, e, &vcpu_info, &svm) && set && kvm_vcpu_apicv_active(&svm->vcpu)) { @@ -5452,9 +5534,6 @@ static void enable_irq_window(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); - if (kvm_vcpu_apicv_active(vcpu)) - return; - /* * In case GIF=0 we can't rely on the CPU to tell us when GIF becomes * 1, because that's a separate STGI/VMRUN intercept. The next time we @@ -5464,6 +5543,13 @@ static void enable_irq_window(struct kvm_vcpu *vcpu) * window under the assumption that the hardware will set the GIF. */ if ((vgif_enabled(svm) || gif_set(svm)) && nested_svm_intr(svm)) { + /* + * IRQ window is not needed when AVIC is enabled, + * unless we have pending ExtINT since it cannot be injected + * via AVIC. In such case, we need to temporarily disable AVIC, + * and fallback to injecting IRQ via V_IRQ. + */ + svm_toggle_avic_for_irq_window(vcpu, false); svm_set_vintr(svm); svm_inject_irq(svm, 0x0); } @@ -5666,7 +5752,7 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu) svm->vmcb->save.cr2 = vcpu->arch.cr2; clgi(); - kvm_load_guest_xcr0(vcpu); + kvm_load_guest_xsave_state(vcpu); if (lapic_in_kernel(vcpu) && vcpu->arch.apic->lapic_timer.timer_advance_ns) @@ -5816,7 +5902,7 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu) if (unlikely(svm->vmcb->control.exit_code == SVM_EXIT_NMI)) kvm_before_interrupt(&svm->vcpu); - kvm_put_guest_xcr0(vcpu); + kvm_load_host_xsave_state(vcpu); stgi(); /* Any pending NMI will happen here */ @@ -5925,6 +6011,10 @@ static void svm_cpuid_update(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); + vcpu->arch.xsaves_enabled = guest_cpuid_has(vcpu, X86_FEATURE_XSAVE) && + boot_cpu_has(X86_FEATURE_XSAVE) && + boot_cpu_has(X86_FEATURE_XSAVES); + /* Update nrips enabled cache */ svm->nrips_enabled = !!guest_cpuid_has(&svm->vcpu, X86_FEATURE_NRIPS); @@ -5932,19 +6022,34 @@ static void svm_cpuid_update(struct kvm_vcpu *vcpu) return; guest_cpuid_clear(vcpu, X86_FEATURE_X2APIC); + + /* + * Currently, AVIC does not work with nested virtualization. + * So, we disable AVIC when cpuid for SVM is set in the L1 guest. + */ + if (nested && guest_cpuid_has(vcpu, X86_FEATURE_SVM)) + kvm_request_apicv_update(vcpu->kvm, false, + APICV_INHIBIT_REASON_NESTED); } +#define F feature_bit + static void svm_set_supported_cpuid(u32 func, struct kvm_cpuid_entry2 *entry) { switch (func) { case 0x1: if (avic) - entry->ecx &= ~bit(X86_FEATURE_X2APIC); + entry->ecx &= ~F(X2APIC); break; case 0x80000001: if (nested) entry->ecx |= (1 << 2); /* Set SVM bit */ break; + case 0x80000008: + if (boot_cpu_has(X86_FEATURE_LS_CFG_SSBD) || + boot_cpu_has(X86_FEATURE_AMD_SSBD)) + entry->ebx |= F(VIRT_SSBD); + break; case 0x8000000A: entry->eax = 1; /* SVM revision 1 */ entry->ebx = 8; /* Lets support 8 ASIDs in case we add proper @@ -5955,18 +6060,11 @@ static void svm_set_supported_cpuid(u32 func, struct kvm_cpuid_entry2 *entry) /* Support next_rip if host supports it */ if (boot_cpu_has(X86_FEATURE_NRIPS)) - entry->edx |= SVM_FEATURE_NRIP; + entry->edx |= F(NRIPS); /* Support NPT for the guest if enabled */ if (npt_enabled) - entry->edx |= SVM_FEATURE_NPT; - - break; - case 0x8000001F: - /* Support memory encryption cpuid if host supports it */ - if (boot_cpu_has(X86_FEATURE_SEV)) - cpuid(0x8000001f, &entry->eax, &entry->ebx, - &entry->ecx, &entry->edx); + entry->edx |= F(NPT); } } @@ -5993,7 +6091,7 @@ static bool svm_mpx_supported(void) static bool svm_xsaves_supported(void) { - return false; + return boot_cpu_has(X86_FEATURE_XSAVES); } static bool svm_umip_emulated(void) @@ -6011,6 +6109,11 @@ static bool svm_has_wbinvd_exit(void) return true; } +static bool svm_pku_supported(void) +{ + return false; +} + #define PRE_EX(exit) { .exit_code = (exit), \ .stage = X86_ICPT_PRE_EXCEPT, } #define POST_EX(exit) { .exit_code = (exit), \ @@ -6068,6 +6171,7 @@ static const struct __x86_intercept { [x86_intercept_ins] = POST_EX(SVM_EXIT_IOIO), [x86_intercept_out] = POST_EX(SVM_EXIT_IOIO), [x86_intercept_outs] = POST_EX(SVM_EXIT_IOIO), + [x86_intercept_xsetbv] = PRE_EX(SVM_EXIT_XSETBV), }; #undef PRE_EX @@ -6195,9 +6299,12 @@ out: return ret; } -static void svm_handle_exit_irqoff(struct kvm_vcpu *vcpu) +static void svm_handle_exit_irqoff(struct kvm_vcpu *vcpu, + enum exit_fastpath_completion *exit_fastpath) { - + if (!is_guest_mode(vcpu) && + to_svm(vcpu)->vmcb->control.exit_code == EXIT_REASON_MSR_WRITE) + *exit_fastpath = handle_fastpath_set_msr_irqoff(vcpu); } static void svm_sched_in(struct kvm_vcpu *vcpu, int cpu) @@ -6294,18 +6401,73 @@ static int enable_smi_window(struct kvm_vcpu *vcpu) return 0; } +static int sev_flush_asids(void) +{ + int ret, error; + + /* + * DEACTIVATE will clear the WBINVD indicator causing DF_FLUSH to fail, + * so it must be guarded. + */ + down_write(&sev_deactivate_lock); + + wbinvd_on_all_cpus(); + ret = sev_guest_df_flush(&error); + + up_write(&sev_deactivate_lock); + + if (ret) + pr_err("SEV: DF_FLUSH failed, ret=%d, error=%#x\n", ret, error); + + return ret; +} + +/* Must be called with the sev_bitmap_lock held */ +static bool __sev_recycle_asids(void) +{ + int pos; + + /* Check if there are any ASIDs to reclaim before performing a flush */ + pos = find_next_bit(sev_reclaim_asid_bitmap, + max_sev_asid, min_sev_asid - 1); + if (pos >= max_sev_asid) + return false; + + if (sev_flush_asids()) + return false; + + bitmap_xor(sev_asid_bitmap, sev_asid_bitmap, sev_reclaim_asid_bitmap, + max_sev_asid); + bitmap_zero(sev_reclaim_asid_bitmap, max_sev_asid); + + return true; +} + static int sev_asid_new(void) { + bool retry = true; int pos; + mutex_lock(&sev_bitmap_lock); + /* * SEV-enabled guest must use asid from min_sev_asid to max_sev_asid. */ +again: pos = find_next_zero_bit(sev_asid_bitmap, max_sev_asid, min_sev_asid - 1); - if (pos >= max_sev_asid) + if (pos >= max_sev_asid) { + if (retry && __sev_recycle_asids()) { + retry = false; + goto again; + } + mutex_unlock(&sev_bitmap_lock); return -EBUSY; + } + + __set_bit(pos, sev_asid_bitmap); + + mutex_unlock(&sev_bitmap_lock); - set_bit(pos, sev_asid_bitmap); return pos + 1; } @@ -6333,7 +6495,7 @@ static int sev_guest_init(struct kvm *kvm, struct kvm_sev_cmd *argp) return 0; e_free: - __sev_asid_free(asid); + sev_asid_free(asid); return ret; } @@ -6343,12 +6505,6 @@ static int sev_bind_asid(struct kvm *kvm, unsigned int handle, int *error) int asid = sev_get_asid(kvm); int ret; - wbinvd_on_all_cpus(); - - ret = sev_guest_df_flush(error); - if (ret) - return ret; - data = kzalloc(sizeof(*data), GFP_KERNEL_ACCOUNT); if (!data) return -ENOMEM; @@ -7129,19 +7285,6 @@ failed: return ret; } -static uint16_t nested_get_evmcs_version(struct kvm_vcpu *vcpu) -{ - /* Not supported */ - return 0; -} - -static int nested_enable_evmcs(struct kvm_vcpu *vcpu, - uint16_t *vmcs_version) -{ - /* Intel-only feature */ - return -ENODEV; -} - static bool svm_need_emulation_on_page_fault(struct kvm_vcpu *vcpu) { unsigned long cr4 = kvm_read_cr4(vcpu); @@ -7200,6 +7343,37 @@ static bool svm_need_emulation_on_page_fault(struct kvm_vcpu *vcpu) return false; } +static bool svm_apic_init_signal_blocked(struct kvm_vcpu *vcpu) +{ + struct vcpu_svm *svm = to_svm(vcpu); + + /* + * TODO: Last condition latch INIT signals on vCPU when + * vCPU is in guest-mode and vmcb12 defines intercept on INIT. + * To properly emulate the INIT intercept, SVM should implement + * kvm_x86_ops->check_nested_events() and call nested_svm_vmexit() + * there if an INIT signal is pending. + */ + return !gif_set(svm) || + (svm->vmcb->control.intercept & (1ULL << INTERCEPT_INIT)); +} + +static bool svm_check_apicv_inhibit_reasons(ulong bit) +{ + ulong supported = BIT(APICV_INHIBIT_REASON_DISABLE) | + BIT(APICV_INHIBIT_REASON_HYPERV) | + BIT(APICV_INHIBIT_REASON_NESTED) | + BIT(APICV_INHIBIT_REASON_IRQWIN) | + BIT(APICV_INHIBIT_REASON_PIT_REINJ); + + return supported & BIT(bit); +} + +static void svm_pre_update_apicv_exec_ctrl(struct kvm *kvm, bool activate) +{ + avic_update_access_page(kvm, activate); +} + static struct kvm_x86_ops svm_x86_ops __ro_after_init = { .cpu_has_kvm_support = has_svm, .disabled_by_bios = is_disabled, @@ -7217,7 +7391,7 @@ static struct kvm_x86_ops svm_x86_ops __ro_after_init = { .vm_alloc = svm_vm_alloc, .vm_free = svm_vm_free, - .vm_init = avic_vm_init, + .vm_init = svm_vm_init, .vm_destroy = svm_vm_destroy, .prepare_guest_switch = svm_prepare_guest_switch, @@ -7236,7 +7410,6 @@ static struct kvm_x86_ops svm_x86_ops __ro_after_init = { .get_cpl = svm_get_cpl, .get_cs_db_l_bits = kvm_get_cs_db_l_bits, .decache_cr0_guest_bits = svm_decache_cr0_guest_bits, - .decache_cr3 = svm_decache_cr3, .decache_cr4_guest_bits = svm_decache_cr4_guest_bits, .set_cr0 = svm_set_cr0, .set_cr3 = svm_set_cr3, @@ -7275,8 +7448,9 @@ static struct kvm_x86_ops svm_x86_ops __ro_after_init = { .enable_irq_window = enable_irq_window, .update_cr8_intercept = update_cr8_intercept, .set_virtual_apic_mode = svm_set_virtual_apic_mode, - .get_enable_apicv = svm_get_enable_apicv, .refresh_apicv_exec_ctrl = svm_refresh_apicv_exec_ctrl, + .check_apicv_inhibit_reasons = svm_check_apicv_inhibit_reasons, + .pre_update_apicv_exec_ctrl = svm_pre_update_apicv_exec_ctrl, .load_eoi_exitmap = svm_load_eoi_exitmap, .hwapic_irr_update = svm_hwapic_irr_update, .hwapic_isr_update = svm_hwapic_isr_update, @@ -7300,6 +7474,7 @@ static struct kvm_x86_ops svm_x86_ops __ro_after_init = { .xsaves_supported = svm_xsaves_supported, .umip_emulated = svm_umip_emulated, .pt_supported = svm_pt_supported, + .pku_supported = svm_pku_supported, .set_supported_cpuid = svm_set_supported_cpuid, @@ -7332,10 +7507,12 @@ static struct kvm_x86_ops svm_x86_ops __ro_after_init = { .mem_enc_reg_region = svm_register_enc_region, .mem_enc_unreg_region = svm_unregister_enc_region, - .nested_enable_evmcs = nested_enable_evmcs, - .nested_get_evmcs_version = nested_get_evmcs_version, + .nested_enable_evmcs = NULL, + .nested_get_evmcs_version = NULL, .need_emulation_on_page_fault = svm_need_emulation_on_page_fault, + + .apic_init_signal_blocked = svm_apic_init_signal_blocked, }; static int __init svm_init(void) diff --git a/arch/x86/kvm/trace.h b/arch/x86/kvm/trace.h index b5c831e79094..f194dd058470 100644 --- a/arch/x86/kvm/trace.h +++ b/arch/x86/kvm/trace.h @@ -232,17 +232,20 @@ TRACE_EVENT(kvm_exit, __field( u32, isa ) __field( u64, info1 ) __field( u64, info2 ) + __field( unsigned int, vcpu_id ) ), TP_fast_assign( __entry->exit_reason = exit_reason; __entry->guest_rip = kvm_rip_read(vcpu); __entry->isa = isa; + __entry->vcpu_id = vcpu->vcpu_id; kvm_x86_ops->get_exit_info(vcpu, &__entry->info1, &__entry->info2); ), - TP_printk("reason %s rip 0x%lx info %llx %llx", + TP_printk("vcpu %u reason %s rip 0x%lx info %llx %llx", + __entry->vcpu_id, (__entry->isa == KVM_ISA_VMX) ? __print_symbolic(__entry->exit_reason, VMX_EXIT_REASONS) : __print_symbolic(__entry->exit_reason, SVM_EXIT_REASONS), @@ -887,36 +890,27 @@ TRACE_EVENT(kvm_pml_full, TP_printk("vcpu %d: PML full", __entry->vcpu_id) ); -TRACE_EVENT(kvm_ple_window, - TP_PROTO(bool grow, unsigned int vcpu_id, int new, int old), - TP_ARGS(grow, vcpu_id, new, old), +TRACE_EVENT(kvm_ple_window_update, + TP_PROTO(unsigned int vcpu_id, unsigned int new, unsigned int old), + TP_ARGS(vcpu_id, new, old), TP_STRUCT__entry( - __field( bool, grow ) __field( unsigned int, vcpu_id ) - __field( int, new ) - __field( int, old ) + __field( unsigned int, new ) + __field( unsigned int, old ) ), TP_fast_assign( - __entry->grow = grow; __entry->vcpu_id = vcpu_id; __entry->new = new; __entry->old = old; ), - TP_printk("vcpu %u: ple_window %d (%s %d)", - __entry->vcpu_id, - __entry->new, - __entry->grow ? "grow" : "shrink", - __entry->old) + TP_printk("vcpu %u old %u new %u (%s)", + __entry->vcpu_id, __entry->old, __entry->new, + __entry->old < __entry->new ? "growed" : "shrinked") ); -#define trace_kvm_ple_window_grow(vcpu_id, new, old) \ - trace_kvm_ple_window(true, vcpu_id, new, old) -#define trace_kvm_ple_window_shrink(vcpu_id, new, old) \ - trace_kvm_ple_window(false, vcpu_id, new, old) - TRACE_EVENT(kvm_pvclock_update, TP_PROTO(unsigned int vcpu_id, struct pvclock_vcpu_time_info *pvclock), TP_ARGS(vcpu_id, pvclock), @@ -1297,6 +1291,25 @@ TRACE_EVENT(kvm_hv_stimer_cleanup, __entry->vcpu_id, __entry->timer_index) ); +TRACE_EVENT(kvm_apicv_update_request, + TP_PROTO(bool activate, unsigned long bit), + TP_ARGS(activate, bit), + + TP_STRUCT__entry( + __field(bool, activate) + __field(unsigned long, bit) + ), + + TP_fast_assign( + __entry->activate = activate; + __entry->bit = bit; + ), + + TP_printk("%s bit=%lu", + __entry->activate ? "activate" : "deactivate", + __entry->bit) +); + /* * Tracepoint for AMD AVIC */ @@ -1320,7 +1333,7 @@ TRACE_EVENT(kvm_avic_incomplete_ipi, __entry->index = index; ), - TP_printk("vcpu=%u, icrh:icrl=%#010x:%08x, id=%u, index=%u\n", + TP_printk("vcpu=%u, icrh:icrl=%#010x:%08x, id=%u, index=%u", __entry->vcpu, __entry->icrh, __entry->icrl, __entry->id, __entry->index) ); @@ -1345,7 +1358,7 @@ TRACE_EVENT(kvm_avic_unaccelerated_access, __entry->vec = vec; ), - TP_printk("vcpu=%u, offset=%#x(%s), %s, %s, vec=%#x\n", + TP_printk("vcpu=%u, offset=%#x(%s), %s, %s, vec=%#x", __entry->vcpu, __entry->offset, __print_symbolic(__entry->offset, kvm_trace_symbol_apic), @@ -1462,6 +1475,46 @@ TRACE_EVENT(kvm_hv_send_ipi_ex, __entry->vector, __entry->format, __entry->valid_bank_mask) ); + +TRACE_EVENT(kvm_pv_tlb_flush, + TP_PROTO(unsigned int vcpu_id, bool need_flush_tlb), + TP_ARGS(vcpu_id, need_flush_tlb), + + TP_STRUCT__entry( + __field( unsigned int, vcpu_id ) + __field( bool, need_flush_tlb ) + ), + + TP_fast_assign( + __entry->vcpu_id = vcpu_id; + __entry->need_flush_tlb = need_flush_tlb; + ), + + TP_printk("vcpu %u need_flush_tlb %s", __entry->vcpu_id, + __entry->need_flush_tlb ? "true" : "false") +); + +/* + * Tracepoint for failed nested VMX VM-Enter. + */ +TRACE_EVENT(kvm_nested_vmenter_failed, + TP_PROTO(const char *msg, u32 err), + TP_ARGS(msg, err), + + TP_STRUCT__entry( + __field(const char *, msg) + __field(u32, err) + ), + + TP_fast_assign( + __entry->msg = msg; + __entry->err = err; + ), + + TP_printk("%s%s", __entry->msg, !__entry->err ? "" : + __print_symbolic(__entry->err, VMX_VMENTER_INSTRUCTION_ERRORS)) +); + #endif /* _TRACE_KVM_H */ #undef TRACE_INCLUDE_PATH diff --git a/arch/x86/kvm/vmx/capabilities.h b/arch/x86/kvm/vmx/capabilities.h index d6664ee3d127..283bdb7071af 100644 --- a/arch/x86/kvm/vmx/capabilities.h +++ b/arch/x86/kvm/vmx/capabilities.h @@ -145,6 +145,11 @@ static inline bool vmx_umip_emulated(void) SECONDARY_EXEC_DESC; } +static inline bool vmx_pku_supported(void) +{ + return boot_cpu_has(X86_FEATURE_PKU); +} + static inline bool cpu_has_vmx_rdtscp(void) { return vmcs_config.cpu_based_2nd_exec_ctrl & @@ -247,6 +252,12 @@ static inline bool vmx_xsaves_supported(void) SECONDARY_EXEC_XSAVES; } +static inline bool vmx_waitpkg_supported(void) +{ + return vmcs_config.cpu_based_2nd_exec_ctrl & + SECONDARY_EXEC_ENABLE_USR_WAIT_PAUSE; +} + static inline bool cpu_has_vmx_tsc_scaling(void) { return vmcs_config.cpu_based_2nd_exec_ctrl & diff --git a/arch/x86/kvm/vmx/evmcs.c b/arch/x86/kvm/vmx/evmcs.c index 72359709cdc1..303813423c3e 100644 --- a/arch/x86/kvm/vmx/evmcs.c +++ b/arch/x86/kvm/vmx/evmcs.c @@ -7,6 +7,7 @@ #include "evmcs.h" #include "vmcs.h" #include "vmx.h" +#include "trace.h" DEFINE_STATIC_KEY_FALSE(enable_evmcs); @@ -346,26 +347,93 @@ uint16_t nested_get_evmcs_version(struct kvm_vcpu *vcpu) return 0; } +void nested_evmcs_filter_control_msr(u32 msr_index, u64 *pdata) +{ + u32 ctl_low = (u32)*pdata; + u32 ctl_high = (u32)(*pdata >> 32); + + /* + * Hyper-V 2016 and 2019 try using these features even when eVMCS + * is enabled but there are no corresponding fields. + */ + switch (msr_index) { + case MSR_IA32_VMX_EXIT_CTLS: + case MSR_IA32_VMX_TRUE_EXIT_CTLS: + ctl_high &= ~VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL; + break; + case MSR_IA32_VMX_ENTRY_CTLS: + case MSR_IA32_VMX_TRUE_ENTRY_CTLS: + ctl_high &= ~VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL; + break; + case MSR_IA32_VMX_PROCBASED_CTLS2: + ctl_high &= ~SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES; + break; + } + + *pdata = ctl_low | ((u64)ctl_high << 32); +} + +int nested_evmcs_check_controls(struct vmcs12 *vmcs12) +{ + int ret = 0; + u32 unsupp_ctl; + + unsupp_ctl = vmcs12->pin_based_vm_exec_control & + EVMCS1_UNSUPPORTED_PINCTRL; + if (unsupp_ctl) { + trace_kvm_nested_vmenter_failed( + "eVMCS: unsupported pin-based VM-execution controls", + unsupp_ctl); + ret = -EINVAL; + } + + unsupp_ctl = vmcs12->secondary_vm_exec_control & + EVMCS1_UNSUPPORTED_2NDEXEC; + if (unsupp_ctl) { + trace_kvm_nested_vmenter_failed( + "eVMCS: unsupported secondary VM-execution controls", + unsupp_ctl); + ret = -EINVAL; + } + + unsupp_ctl = vmcs12->vm_exit_controls & + EVMCS1_UNSUPPORTED_VMEXIT_CTRL; + if (unsupp_ctl) { + trace_kvm_nested_vmenter_failed( + "eVMCS: unsupported VM-exit controls", + unsupp_ctl); + ret = -EINVAL; + } + + unsupp_ctl = vmcs12->vm_entry_controls & + EVMCS1_UNSUPPORTED_VMENTRY_CTRL; + if (unsupp_ctl) { + trace_kvm_nested_vmenter_failed( + "eVMCS: unsupported VM-entry controls", + unsupp_ctl); + ret = -EINVAL; + } + + unsupp_ctl = vmcs12->vm_function_control & EVMCS1_UNSUPPORTED_VMFUNC; + if (unsupp_ctl) { + trace_kvm_nested_vmenter_failed( + "eVMCS: unsupported VM-function controls", + unsupp_ctl); + ret = -EINVAL; + } + + return ret; +} + int nested_enable_evmcs(struct kvm_vcpu *vcpu, uint16_t *vmcs_version) { struct vcpu_vmx *vmx = to_vmx(vcpu); - bool evmcs_already_enabled = vmx->nested.enlightened_vmcs_enabled; vmx->nested.enlightened_vmcs_enabled = true; if (vmcs_version) *vmcs_version = nested_get_evmcs_version(vcpu); - /* We don't support disabling the feature for simplicity. */ - if (evmcs_already_enabled) - return 0; - - vmx->nested.msrs.pinbased_ctls_high &= ~EVMCS1_UNSUPPORTED_PINCTRL; - vmx->nested.msrs.entry_ctls_high &= ~EVMCS1_UNSUPPORTED_VMENTRY_CTRL; - vmx->nested.msrs.exit_ctls_high &= ~EVMCS1_UNSUPPORTED_VMEXIT_CTRL; - vmx->nested.msrs.secondary_ctls_high &= ~EVMCS1_UNSUPPORTED_2NDEXEC; - vmx->nested.msrs.vmfunc_controls &= ~EVMCS1_UNSUPPORTED_VMFUNC; - return 0; } diff --git a/arch/x86/kvm/vmx/evmcs.h b/arch/x86/kvm/vmx/evmcs.h index 39a24eec8884..6de47f2569c9 100644 --- a/arch/x86/kvm/vmx/evmcs.h +++ b/arch/x86/kvm/vmx/evmcs.h @@ -10,6 +10,7 @@ #include "capabilities.h" #include "vmcs.h" +#include "vmcs12.h" struct vmcs_config; @@ -178,6 +179,8 @@ static inline void evmcs_load(u64 phys_addr) struct hv_vp_assist_page *vp_ap = hv_get_vp_assist_page(smp_processor_id()); + if (current_evmcs->hv_enlightenments_control.nested_flush_hypercall) + vp_ap->nested_control.features.directhypercall = 1; vp_ap->current_nested_vmcs = phys_addr; vp_ap->enlighten_vmentry = 1; } @@ -199,5 +202,7 @@ bool nested_enlightened_vmentry(struct kvm_vcpu *vcpu, u64 *evmcs_gpa); uint16_t nested_get_evmcs_version(struct kvm_vcpu *vcpu); int nested_enable_evmcs(struct kvm_vcpu *vcpu, uint16_t *vmcs_version); +void nested_evmcs_filter_control_msr(u32 msr_index, u64 *pdata); +int nested_evmcs_check_controls(struct vmcs12 *vmcs12); #endif /* __KVM_X86_VMX_EVMCS_H */ diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c index ced9fba32598..3589cd3c0fcc 100644 --- a/arch/x86/kvm/vmx/nested.c +++ b/arch/x86/kvm/vmx/nested.c @@ -10,6 +10,7 @@ #include "hyperv.h" #include "mmu.h" #include "nested.h" +#include "pmu.h" #include "trace.h" #include "x86.h" @@ -19,6 +20,14 @@ module_param_named(enable_shadow_vmcs, enable_shadow_vmcs, bool, S_IRUGO); static bool __read_mostly nested_early_check = 0; module_param(nested_early_check, bool, S_IRUGO); +#define CC(consistency_check) \ +({ \ + bool failed = (consistency_check); \ + if (failed) \ + trace_kvm_nested_vmenter_failed(#consistency_check, 0); \ + failed; \ +}) + /* * Hyper-V requires all of these, so mark them as supported even though * they are just treated the same as all-context. @@ -190,6 +199,16 @@ static void nested_vmx_abort(struct kvm_vcpu *vcpu, u32 indicator) pr_debug_ratelimited("kvm: nested vmx abort, indicator %d\n", indicator); } +static inline bool vmx_control_verify(u32 control, u32 low, u32 high) +{ + return fixed_bits_valid(control, low, high); +} + +static inline u64 vmx_control_msr(u32 low, u32 high) +{ + return low | ((u64)high << 32); +} + static void vmx_disable_shadow_vmcs(struct vcpu_vmx *vmx) { secondary_exec_controls_clearbit(vmx, SECONDARY_EXEC_SHADOW_VMCS); @@ -239,7 +258,7 @@ static void free_nested(struct kvm_vcpu *vcpu) vmx->nested.cached_shadow_vmcs12 = NULL; /* Unpin physical memory we referred to in the vmcs02 */ if (vmx->nested.apic_access_page) { - kvm_release_page_dirty(vmx->nested.apic_access_page); + kvm_release_page_clean(vmx->nested.apic_access_page); vmx->nested.apic_access_page = NULL; } kvm_vcpu_unmap(vcpu, &vmx->nested.virtual_apic_map, true); @@ -430,8 +449,8 @@ static int nested_vmx_check_io_bitmap_controls(struct kvm_vcpu *vcpu, if (!nested_cpu_has(vmcs12, CPU_BASED_USE_IO_BITMAPS)) return 0; - if (!page_address_valid(vcpu, vmcs12->io_bitmap_a) || - !page_address_valid(vcpu, vmcs12->io_bitmap_b)) + if (CC(!page_address_valid(vcpu, vmcs12->io_bitmap_a)) || + CC(!page_address_valid(vcpu, vmcs12->io_bitmap_b))) return -EINVAL; return 0; @@ -443,7 +462,7 @@ static int nested_vmx_check_msr_bitmap_controls(struct kvm_vcpu *vcpu, if (!nested_cpu_has(vmcs12, CPU_BASED_USE_MSR_BITMAPS)) return 0; - if (!page_address_valid(vcpu, vmcs12->msr_bitmap)) + if (CC(!page_address_valid(vcpu, vmcs12->msr_bitmap))) return -EINVAL; return 0; @@ -455,7 +474,7 @@ static int nested_vmx_check_tpr_shadow_controls(struct kvm_vcpu *vcpu, if (!nested_cpu_has(vmcs12, CPU_BASED_TPR_SHADOW)) return 0; - if (!page_address_valid(vcpu, vmcs12->virtual_apic_page_addr)) + if (CC(!page_address_valid(vcpu, vmcs12->virtual_apic_page_addr))) return -EINVAL; return 0; @@ -525,7 +544,8 @@ static void nested_vmx_disable_intercept_for_msr(unsigned long *msr_bitmap_l1, } } -static inline void enable_x2apic_msr_intercepts(unsigned long *msr_bitmap) { +static inline void enable_x2apic_msr_intercepts(unsigned long *msr_bitmap) +{ int msr; for (msr = 0x800; msr <= 0x8ff; msr += BITS_PER_LONG) { @@ -688,7 +708,7 @@ static int nested_vmx_check_apic_access_controls(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) { if (nested_cpu_has2(vmcs12, SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES) && - !page_address_valid(vcpu, vmcs12->apic_access_addr)) + CC(!page_address_valid(vcpu, vmcs12->apic_access_addr))) return -EINVAL; else return 0; @@ -707,16 +727,15 @@ static int nested_vmx_check_apicv_controls(struct kvm_vcpu *vcpu, * If virtualize x2apic mode is enabled, * virtualize apic access must be disabled. */ - if (nested_cpu_has_virt_x2apic_mode(vmcs12) && - nested_cpu_has2(vmcs12, SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES)) + if (CC(nested_cpu_has_virt_x2apic_mode(vmcs12) && + nested_cpu_has2(vmcs12, SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES))) return -EINVAL; /* * If virtual interrupt delivery is enabled, * we must exit on external interrupts. */ - if (nested_cpu_has_vid(vmcs12) && - !nested_exit_on_intr(vcpu)) + if (CC(nested_cpu_has_vid(vmcs12) && !nested_exit_on_intr(vcpu))) return -EINVAL; /* @@ -727,15 +746,15 @@ static int nested_vmx_check_apicv_controls(struct kvm_vcpu *vcpu, * bits 5:0 of posted_intr_desc_addr should be zero. */ if (nested_cpu_has_posted_intr(vmcs12) && - (!nested_cpu_has_vid(vmcs12) || - !nested_exit_intr_ack_set(vcpu) || - (vmcs12->posted_intr_nv & 0xff00) || - (vmcs12->posted_intr_desc_addr & 0x3f) || - (vmcs12->posted_intr_desc_addr >> cpuid_maxphyaddr(vcpu)))) + (CC(!nested_cpu_has_vid(vmcs12)) || + CC(!nested_exit_intr_ack_set(vcpu)) || + CC((vmcs12->posted_intr_nv & 0xff00)) || + CC((vmcs12->posted_intr_desc_addr & 0x3f)) || + CC((vmcs12->posted_intr_desc_addr >> cpuid_maxphyaddr(vcpu))))) return -EINVAL; /* tpr shadow is needed by all apicv features. */ - if (!nested_cpu_has(vmcs12, CPU_BASED_TPR_SHADOW)) + if (CC(!nested_cpu_has(vmcs12, CPU_BASED_TPR_SHADOW))) return -EINVAL; return 0; @@ -759,10 +778,12 @@ static int nested_vmx_check_msr_switch(struct kvm_vcpu *vcpu, static int nested_vmx_check_exit_msr_switch_controls(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) { - if (nested_vmx_check_msr_switch(vcpu, vmcs12->vm_exit_msr_load_count, - vmcs12->vm_exit_msr_load_addr) || - nested_vmx_check_msr_switch(vcpu, vmcs12->vm_exit_msr_store_count, - vmcs12->vm_exit_msr_store_addr)) + if (CC(nested_vmx_check_msr_switch(vcpu, + vmcs12->vm_exit_msr_load_count, + vmcs12->vm_exit_msr_load_addr)) || + CC(nested_vmx_check_msr_switch(vcpu, + vmcs12->vm_exit_msr_store_count, + vmcs12->vm_exit_msr_store_addr))) return -EINVAL; return 0; @@ -771,8 +792,9 @@ static int nested_vmx_check_exit_msr_switch_controls(struct kvm_vcpu *vcpu, static int nested_vmx_check_entry_msr_switch_controls(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) { - if (nested_vmx_check_msr_switch(vcpu, vmcs12->vm_entry_msr_load_count, - vmcs12->vm_entry_msr_load_addr)) + if (CC(nested_vmx_check_msr_switch(vcpu, + vmcs12->vm_entry_msr_load_count, + vmcs12->vm_entry_msr_load_addr))) return -EINVAL; return 0; @@ -784,8 +806,8 @@ static int nested_vmx_check_pml_controls(struct kvm_vcpu *vcpu, if (!nested_cpu_has_pml(vmcs12)) return 0; - if (!nested_cpu_has_ept(vmcs12) || - !page_address_valid(vcpu, vmcs12->pml_address)) + if (CC(!nested_cpu_has_ept(vmcs12)) || + CC(!page_address_valid(vcpu, vmcs12->pml_address))) return -EINVAL; return 0; @@ -794,8 +816,8 @@ static int nested_vmx_check_pml_controls(struct kvm_vcpu *vcpu, static int nested_vmx_check_unrestricted_guest_controls(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) { - if (nested_cpu_has2(vmcs12, SECONDARY_EXEC_UNRESTRICTED_GUEST) && - !nested_cpu_has_ept(vmcs12)) + if (CC(nested_cpu_has2(vmcs12, SECONDARY_EXEC_UNRESTRICTED_GUEST) && + !nested_cpu_has_ept(vmcs12))) return -EINVAL; return 0; } @@ -803,8 +825,8 @@ static int nested_vmx_check_unrestricted_guest_controls(struct kvm_vcpu *vcpu, static int nested_vmx_check_mode_based_ept_exec_controls(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) { - if (nested_cpu_has2(vmcs12, SECONDARY_EXEC_MODE_BASED_EPT_EXEC) && - !nested_cpu_has_ept(vmcs12)) + if (CC(nested_cpu_has2(vmcs12, SECONDARY_EXEC_MODE_BASED_EPT_EXEC) && + !nested_cpu_has_ept(vmcs12))) return -EINVAL; return 0; } @@ -815,8 +837,8 @@ static int nested_vmx_check_shadow_vmcs_controls(struct kvm_vcpu *vcpu, if (!nested_cpu_has_shadow_vmcs(vmcs12)) return 0; - if (!page_address_valid(vcpu, vmcs12->vmread_bitmap) || - !page_address_valid(vcpu, vmcs12->vmwrite_bitmap)) + if (CC(!page_address_valid(vcpu, vmcs12->vmread_bitmap)) || + CC(!page_address_valid(vcpu, vmcs12->vmwrite_bitmap))) return -EINVAL; return 0; @@ -826,12 +848,12 @@ static int nested_vmx_msr_check_common(struct kvm_vcpu *vcpu, struct vmx_msr_entry *e) { /* x2APIC MSR accesses are not allowed */ - if (vcpu->arch.apic_base & X2APIC_ENABLE && e->index >> 8 == 0x8) + if (CC(vcpu->arch.apic_base & X2APIC_ENABLE && e->index >> 8 == 0x8)) return -EINVAL; - if (e->index == MSR_IA32_UCODE_WRITE || /* SDM Table 35-2 */ - e->index == MSR_IA32_UCODE_REV) + if (CC(e->index == MSR_IA32_UCODE_WRITE) || /* SDM Table 35-2 */ + CC(e->index == MSR_IA32_UCODE_REV)) return -EINVAL; - if (e->reserved != 0) + if (CC(e->reserved != 0)) return -EINVAL; return 0; } @@ -839,9 +861,9 @@ static int nested_vmx_msr_check_common(struct kvm_vcpu *vcpu, static int nested_vmx_load_msr_check(struct kvm_vcpu *vcpu, struct vmx_msr_entry *e) { - if (e->index == MSR_FS_BASE || - e->index == MSR_GS_BASE || - e->index == MSR_IA32_SMM_MONITOR_CTL || /* SMM is not supported */ + if (CC(e->index == MSR_FS_BASE) || + CC(e->index == MSR_GS_BASE) || + CC(e->index == MSR_IA32_SMM_MONITOR_CTL) || /* SMM is not supported */ nested_vmx_msr_check_common(vcpu, e)) return -EINVAL; return 0; @@ -850,24 +872,40 @@ static int nested_vmx_load_msr_check(struct kvm_vcpu *vcpu, static int nested_vmx_store_msr_check(struct kvm_vcpu *vcpu, struct vmx_msr_entry *e) { - if (e->index == MSR_IA32_SMBASE || /* SMM is not supported */ + if (CC(e->index == MSR_IA32_SMBASE) || /* SMM is not supported */ nested_vmx_msr_check_common(vcpu, e)) return -EINVAL; return 0; } +static u32 nested_vmx_max_atomic_switch_msrs(struct kvm_vcpu *vcpu) +{ + struct vcpu_vmx *vmx = to_vmx(vcpu); + u64 vmx_misc = vmx_control_msr(vmx->nested.msrs.misc_low, + vmx->nested.msrs.misc_high); + + return (vmx_misc_max_msr(vmx_misc) + 1) * VMX_MISC_MSR_LIST_MULTIPLIER; +} + /* * Load guest's/host's msr at nested entry/exit. * return 0 for success, entry index for failure. + * + * One of the failure modes for MSR load/store is when a list exceeds the + * virtual hardware's capacity. To maintain compatibility with hardware inasmuch + * as possible, process all valid entries before failing rather than precheck + * for a capacity violation. */ static u32 nested_vmx_load_msr(struct kvm_vcpu *vcpu, u64 gpa, u32 count) { u32 i; struct vmx_msr_entry e; - struct msr_data msr; + u32 max_msr_list_size = nested_vmx_max_atomic_switch_msrs(vcpu); - msr.host_initiated = false; for (i = 0; i < count; i++) { + if (unlikely(i >= max_msr_list_size)) + goto fail; + if (kvm_vcpu_read_guest(vcpu, gpa + i * sizeof(e), &e, sizeof(e))) { pr_debug_ratelimited( @@ -881,9 +919,7 @@ static u32 nested_vmx_load_msr(struct kvm_vcpu *vcpu, u64 gpa, u32 count) __func__, i, e.index, e.reserved); goto fail; } - msr.index = e.index; - msr.data = e.value; - if (kvm_set_msr(vcpu, &msr)) { + if (kvm_set_msr(vcpu, e.index, e.value)) { pr_debug_ratelimited( "%s cannot write MSR (%u, 0x%x, 0x%llx)\n", __func__, i, e.index, e.value); @@ -895,48 +931,141 @@ fail: return i + 1; } +static bool nested_vmx_get_vmexit_msr_value(struct kvm_vcpu *vcpu, + u32 msr_index, + u64 *data) +{ + struct vcpu_vmx *vmx = to_vmx(vcpu); + + /* + * If the L0 hypervisor stored a more accurate value for the TSC that + * does not include the time taken for emulation of the L2->L1 + * VM-exit in L0, use the more accurate value. + */ + if (msr_index == MSR_IA32_TSC) { + int index = vmx_find_msr_index(&vmx->msr_autostore.guest, + MSR_IA32_TSC); + + if (index >= 0) { + u64 val = vmx->msr_autostore.guest.val[index].value; + + *data = kvm_read_l1_tsc(vcpu, val); + return true; + } + } + + if (kvm_get_msr(vcpu, msr_index, data)) { + pr_debug_ratelimited("%s cannot read MSR (0x%x)\n", __func__, + msr_index); + return false; + } + return true; +} + +static bool read_and_check_msr_entry(struct kvm_vcpu *vcpu, u64 gpa, int i, + struct vmx_msr_entry *e) +{ + if (kvm_vcpu_read_guest(vcpu, + gpa + i * sizeof(*e), + e, 2 * sizeof(u32))) { + pr_debug_ratelimited( + "%s cannot read MSR entry (%u, 0x%08llx)\n", + __func__, i, gpa + i * sizeof(*e)); + return false; + } + if (nested_vmx_store_msr_check(vcpu, e)) { + pr_debug_ratelimited( + "%s check failed (%u, 0x%x, 0x%x)\n", + __func__, i, e->index, e->reserved); + return false; + } + return true; +} + static int nested_vmx_store_msr(struct kvm_vcpu *vcpu, u64 gpa, u32 count) { + u64 data; u32 i; struct vmx_msr_entry e; + u32 max_msr_list_size = nested_vmx_max_atomic_switch_msrs(vcpu); for (i = 0; i < count; i++) { - struct msr_data msr_info; - if (kvm_vcpu_read_guest(vcpu, - gpa + i * sizeof(e), - &e, 2 * sizeof(u32))) { - pr_debug_ratelimited( - "%s cannot read MSR entry (%u, 0x%08llx)\n", - __func__, i, gpa + i * sizeof(e)); + if (unlikely(i >= max_msr_list_size)) return -EINVAL; - } - if (nested_vmx_store_msr_check(vcpu, &e)) { - pr_debug_ratelimited( - "%s check failed (%u, 0x%x, 0x%x)\n", - __func__, i, e.index, e.reserved); + + if (!read_and_check_msr_entry(vcpu, gpa, i, &e)) return -EINVAL; - } - msr_info.host_initiated = false; - msr_info.index = e.index; - if (kvm_get_msr(vcpu, &msr_info)) { - pr_debug_ratelimited( - "%s cannot read MSR (%u, 0x%x)\n", - __func__, i, e.index); + + if (!nested_vmx_get_vmexit_msr_value(vcpu, e.index, &data)) return -EINVAL; - } + if (kvm_vcpu_write_guest(vcpu, gpa + i * sizeof(e) + offsetof(struct vmx_msr_entry, value), - &msr_info.data, sizeof(msr_info.data))) { + &data, sizeof(data))) { pr_debug_ratelimited( "%s cannot write MSR (%u, 0x%x, 0x%llx)\n", - __func__, i, e.index, msr_info.data); + __func__, i, e.index, data); return -EINVAL; } } return 0; } +static bool nested_msr_store_list_has_msr(struct kvm_vcpu *vcpu, u32 msr_index) +{ + struct vmcs12 *vmcs12 = get_vmcs12(vcpu); + u32 count = vmcs12->vm_exit_msr_store_count; + u64 gpa = vmcs12->vm_exit_msr_store_addr; + struct vmx_msr_entry e; + u32 i; + + for (i = 0; i < count; i++) { + if (!read_and_check_msr_entry(vcpu, gpa, i, &e)) + return false; + + if (e.index == msr_index) + return true; + } + return false; +} + +static void prepare_vmx_msr_autostore_list(struct kvm_vcpu *vcpu, + u32 msr_index) +{ + struct vcpu_vmx *vmx = to_vmx(vcpu); + struct vmx_msrs *autostore = &vmx->msr_autostore.guest; + bool in_vmcs12_store_list; + int msr_autostore_index; + bool in_autostore_list; + int last; + + msr_autostore_index = vmx_find_msr_index(autostore, msr_index); + in_autostore_list = msr_autostore_index >= 0; + in_vmcs12_store_list = nested_msr_store_list_has_msr(vcpu, msr_index); + + if (in_vmcs12_store_list && !in_autostore_list) { + if (autostore->nr == NR_LOADSTORE_MSRS) { + /* + * Emulated VMEntry does not fail here. Instead a less + * accurate value will be returned by + * nested_vmx_get_vmexit_msr_value() using kvm_get_msr() + * instead of reading the value from the vmcs02 VMExit + * MSR-store area. + */ + pr_warn_ratelimited( + "Not enough msr entries in msr_autostore. Can't add msr %x\n", + msr_index); + return; + } + last = autostore->nr++; + autostore->val[last].index = msr_index; + } else if (!in_vmcs12_store_list && in_autostore_list) { + last = --autostore->nr; + autostore->val[msr_autostore_index] = autostore->val[last]; + } +} + static bool nested_cr3_valid(struct kvm_vcpu *vcpu, unsigned long val) { unsigned long invalid_mask; @@ -946,16 +1075,16 @@ static bool nested_cr3_valid(struct kvm_vcpu *vcpu, unsigned long val) } /* - * Load guest's/host's cr3 at nested entry/exit. nested_ept is true if we are - * emulating VM entry into a guest with EPT enabled. - * Returns 0 on success, 1 on failure. Invalid state exit qualification code - * is assigned to entry_failure_code on failure. + * Load guest's/host's cr3 at nested entry/exit. @nested_ept is true if we are + * emulating VM-Entry into a guest with EPT enabled. On failure, the expected + * Exit Qualification (for a VM-Entry consistency check VM-Exit) is assigned to + * @entry_failure_code. */ static int nested_vmx_load_cr3(struct kvm_vcpu *vcpu, unsigned long cr3, bool nested_ept, u32 *entry_failure_code) { if (cr3 != kvm_read_cr3(vcpu) || (!nested_ept && pdptrs_changed(vcpu))) { - if (!nested_cr3_valid(vcpu, cr3)) { + if (CC(!nested_cr3_valid(vcpu, cr3))) { *entry_failure_code = ENTRY_FAIL_DEFAULT; return -EINVAL; } @@ -965,7 +1094,7 @@ static int nested_vmx_load_cr3(struct kvm_vcpu *vcpu, unsigned long cr3, bool ne * must not be dereferenced. */ if (is_pae_paging(vcpu) && !nested_ept) { - if (!load_pdptrs(vcpu, vcpu->arch.walk_mmu, cr3)) { + if (CC(!load_pdptrs(vcpu, vcpu->arch.walk_mmu, cr3))) { *entry_failure_code = ENTRY_FAIL_PDPTE; return -EINVAL; } @@ -976,7 +1105,7 @@ static int nested_vmx_load_cr3(struct kvm_vcpu *vcpu, unsigned long cr3, bool ne kvm_mmu_new_cr3(vcpu, cr3, false); vcpu->arch.cr3 = cr3; - __set_bit(VCPU_EXREG_CR3, (ulong *)&vcpu->arch.regs_avail); + kvm_register_mark_available(vcpu, VCPU_EXREG_CR3); kvm_init_mmu(vcpu, false); @@ -988,7 +1117,9 @@ static int nested_vmx_load_cr3(struct kvm_vcpu *vcpu, unsigned long cr3, bool ne * populated by L2 differently than TLB entries populated * by L1. * - * If L1 uses EPT, then TLB entries are tagged with different EPTP. + * If L0 uses EPT, L1 and L2 run with different EPTP because + * guest_mode is part of kvm_mmu_page_role. Thus, TLB entries + * are tagged with different EPTP. * * If L1 uses VPID and we allocated a vpid02, TLB entries are tagged * with different VPID (L1 entries are tagged with vmx->vpid @@ -998,7 +1129,7 @@ static bool nested_has_guest_tlb_tag(struct kvm_vcpu *vcpu) { struct vmcs12 *vmcs12 = get_vmcs12(vcpu); - return nested_cpu_has_ept(vmcs12) || + return enable_ept || (nested_cpu_has_vpid(vmcs12) && to_vmx(vcpu)->nested.vpid02); } @@ -1009,17 +1140,6 @@ static u16 nested_get_vpid02(struct kvm_vcpu *vcpu) return vmx->nested.vpid02 ? vmx->nested.vpid02 : vmx->vpid; } - -static inline bool vmx_control_verify(u32 control, u32 low, u32 high) -{ - return fixed_bits_valid(control, low, high); -} - -static inline u64 vmx_control_msr(u32 low, u32 high) -{ - return low | ((u64)high << 32); -} - static bool is_bitwise_subset(u64 superset, u64 subset, u64 mask) { superset &= mask; @@ -1862,7 +1982,7 @@ static int nested_vmx_handle_enlightened_vmptrld(struct kvm_vcpu *vcpu, } /* - * Clean fields data can't de used on VMLAUNCH and when we switch + * Clean fields data can't be used on VMLAUNCH and when we switch * between different L2 guests as KVM keeps a single VMCS12 per L1. */ if (from_launch || evmcs_gpa_changed) @@ -1993,7 +2113,7 @@ static void prepare_vmcs02_constant_state(struct vcpu_vmx *vmx) * addresses are constant (for vmcs02), the counts can change based * on L2's behavior, e.g. switching to/from long mode. */ - vmcs_write32(VM_EXIT_MSR_STORE_COUNT, 0); + vmcs_write64(VM_EXIT_MSR_STORE_ADDR, __pa(vmx->msr_autostore.guest.val)); vmcs_write64(VM_EXIT_MSR_LOAD_ADDR, __pa(vmx->msr_autoload.host.val)); vmcs_write64(VM_ENTRY_MSR_LOAD_ADDR, __pa(vmx->msr_autoload.guest.val)); @@ -2043,11 +2163,12 @@ static void prepare_vmcs02_early(struct vcpu_vmx *vmx, struct vmcs12 *vmcs12) * EXEC CONTROLS */ exec_control = vmx_exec_control(vmx); /* L0's desires */ - exec_control &= ~CPU_BASED_VIRTUAL_INTR_PENDING; - exec_control &= ~CPU_BASED_VIRTUAL_NMI_PENDING; + exec_control &= ~CPU_BASED_INTR_WINDOW_EXITING; + exec_control &= ~CPU_BASED_NMI_WINDOW_EXITING; exec_control &= ~CPU_BASED_TPR_SHADOW; exec_control |= vmcs12->cpu_based_vm_exec_control; + vmx->nested.l1_tpr_threshold = -1; if (exec_control & CPU_BASED_TPR_SHADOW) vmcs_write32(TPR_THRESHOLD, vmcs12->tpr_threshold); #ifdef CONFIG_X86_64 @@ -2085,6 +2206,7 @@ static void prepare_vmcs02_early(struct vcpu_vmx *vmx, struct vmcs12 *vmcs12) SECONDARY_EXEC_ENABLE_INVPCID | SECONDARY_EXEC_RDTSCP | SECONDARY_EXEC_XSAVES | + SECONDARY_EXEC_ENABLE_USR_WAIT_PAUSE | SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY | SECONDARY_EXEC_APIC_REGISTER_VIRT | SECONDARY_EXEC_ENABLE_VMFUNC); @@ -2259,6 +2381,13 @@ static void prepare_vmcs02_rare(struct vcpu_vmx *vmx, struct vmcs12 *vmcs12) vmcs_write64(EOI_EXIT_BITMAP3, vmcs12->eoi_exit_bitmap3); } + /* + * Make sure the msr_autostore list is up to date before we set the + * count in the vmcs02. + */ + prepare_vmx_msr_autostore_list(&vmx->vcpu, MSR_IA32_TSC); + + vmcs_write32(VM_EXIT_MSR_STORE_COUNT, vmx->msr_autostore.guest.nr); vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, vmx->msr_autoload.host.nr); vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, vmx->msr_autoload.guest.nr); @@ -2355,9 +2484,6 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, if (nested_cpu_has_ept(vmcs12)) nested_ept_init_mmu_context(vcpu); - else if (nested_cpu_has2(vmcs12, - SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES)) - vmx_flush_tlb(vcpu, true); /* * This sets GUEST_CR0 to vmcs12->guest_cr0, possibly modifying those @@ -2392,6 +2518,16 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, entry_failure_code)) return -EINVAL; + /* + * Immediately write vmcs02.GUEST_CR3. It will be propagated to vmcs12 + * on nested VM-Exit, which can occur without actually running L2 and + * thus without hitting vmx_set_cr3(), e.g. if L1 is entering L2 with + * vmcs12.GUEST_ACTIVITYSTATE=HLT, in which case KVM will intercept the + * transition to HLT instead of running L2. + */ + if (enable_ept) + vmcs_writel(GUEST_CR3, vmcs12->guest_cr3); + /* Late preparation of GUEST_PDPTRs now that EFER and CRs are set. */ if (load_guest_pdptrs_vmcs12 && nested_cpu_has_ept(vmcs12) && is_pae_paging(vcpu)) { @@ -2404,6 +2540,11 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, if (!enable_ept) vcpu->arch.walk_mmu->inject_page_fault = vmx_inject_page_fault_nested; + if ((vmcs12->vm_entry_controls & VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL) && + WARN_ON_ONCE(kvm_set_msr(vcpu, MSR_CORE_PERF_GLOBAL_CTRL, + vmcs12->guest_ia32_perf_global_ctrl))) + return -EINVAL; + kvm_rsp_write(vcpu, vmcs12->guest_rsp); kvm_rip_write(vcpu, vmcs12->guest_rip); return 0; @@ -2411,12 +2552,12 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, static int nested_vmx_check_nmi_controls(struct vmcs12 *vmcs12) { - if (!nested_cpu_has_nmi_exiting(vmcs12) && - nested_cpu_has_virtual_nmis(vmcs12)) + if (CC(!nested_cpu_has_nmi_exiting(vmcs12) && + nested_cpu_has_virtual_nmis(vmcs12))) return -EINVAL; - if (!nested_cpu_has_virtual_nmis(vmcs12) && - nested_cpu_has(vmcs12, CPU_BASED_VIRTUAL_NMI_PENDING)) + if (CC(!nested_cpu_has_virtual_nmis(vmcs12) && + nested_cpu_has(vmcs12, CPU_BASED_NMI_WINDOW_EXITING))) return -EINVAL; return 0; @@ -2430,11 +2571,11 @@ static bool valid_ept_address(struct kvm_vcpu *vcpu, u64 address) /* Check for memory type validity */ switch (address & VMX_EPTP_MT_MASK) { case VMX_EPTP_MT_UC: - if (!(vmx->nested.msrs.ept_caps & VMX_EPTP_UC_BIT)) + if (CC(!(vmx->nested.msrs.ept_caps & VMX_EPTP_UC_BIT))) return false; break; case VMX_EPTP_MT_WB: - if (!(vmx->nested.msrs.ept_caps & VMX_EPTP_WB_BIT)) + if (CC(!(vmx->nested.msrs.ept_caps & VMX_EPTP_WB_BIT))) return false; break; default: @@ -2442,16 +2583,16 @@ static bool valid_ept_address(struct kvm_vcpu *vcpu, u64 address) } /* only 4 levels page-walk length are valid */ - if ((address & VMX_EPTP_PWL_MASK) != VMX_EPTP_PWL_4) + if (CC((address & VMX_EPTP_PWL_MASK) != VMX_EPTP_PWL_4)) return false; /* Reserved bits should not be set */ - if (address >> maxphyaddr || ((address >> 7) & 0x1f)) + if (CC(address >> maxphyaddr || ((address >> 7) & 0x1f))) return false; /* AD, if set, should be supported */ if (address & VMX_EPTP_AD_ENABLE_BIT) { - if (!(vmx->nested.msrs.ept_caps & VMX_EPT_AD_BIT)) + if (CC(!(vmx->nested.msrs.ept_caps & VMX_EPT_AD_BIT))) return false; } @@ -2466,21 +2607,21 @@ static int nested_check_vm_execution_controls(struct kvm_vcpu *vcpu, { struct vcpu_vmx *vmx = to_vmx(vcpu); - if (!vmx_control_verify(vmcs12->pin_based_vm_exec_control, - vmx->nested.msrs.pinbased_ctls_low, - vmx->nested.msrs.pinbased_ctls_high) || - !vmx_control_verify(vmcs12->cpu_based_vm_exec_control, - vmx->nested.msrs.procbased_ctls_low, - vmx->nested.msrs.procbased_ctls_high)) + if (CC(!vmx_control_verify(vmcs12->pin_based_vm_exec_control, + vmx->nested.msrs.pinbased_ctls_low, + vmx->nested.msrs.pinbased_ctls_high)) || + CC(!vmx_control_verify(vmcs12->cpu_based_vm_exec_control, + vmx->nested.msrs.procbased_ctls_low, + vmx->nested.msrs.procbased_ctls_high))) return -EINVAL; if (nested_cpu_has(vmcs12, CPU_BASED_ACTIVATE_SECONDARY_CONTROLS) && - !vmx_control_verify(vmcs12->secondary_vm_exec_control, - vmx->nested.msrs.secondary_ctls_low, - vmx->nested.msrs.secondary_ctls_high)) + CC(!vmx_control_verify(vmcs12->secondary_vm_exec_control, + vmx->nested.msrs.secondary_ctls_low, + vmx->nested.msrs.secondary_ctls_high))) return -EINVAL; - if (vmcs12->cr3_target_count > nested_cpu_vmx_misc_cr3_count(vcpu) || + if (CC(vmcs12->cr3_target_count > nested_cpu_vmx_misc_cr3_count(vcpu)) || nested_vmx_check_io_bitmap_controls(vcpu, vmcs12) || nested_vmx_check_msr_bitmap_controls(vcpu, vmcs12) || nested_vmx_check_tpr_shadow_controls(vcpu, vmcs12) || @@ -2491,7 +2632,7 @@ static int nested_check_vm_execution_controls(struct kvm_vcpu *vcpu, nested_vmx_check_unrestricted_guest_controls(vcpu, vmcs12) || nested_vmx_check_mode_based_ept_exec_controls(vcpu, vmcs12) || nested_vmx_check_shadow_vmcs_controls(vcpu, vmcs12) || - (nested_cpu_has_vpid(vmcs12) && !vmcs12->virtual_processor_id)) + CC(nested_cpu_has_vpid(vmcs12) && !vmcs12->virtual_processor_id)) return -EINVAL; if (!nested_cpu_has_preemption_timer(vmcs12) && @@ -2499,17 +2640,17 @@ static int nested_check_vm_execution_controls(struct kvm_vcpu *vcpu, return -EINVAL; if (nested_cpu_has_ept(vmcs12) && - !valid_ept_address(vcpu, vmcs12->ept_pointer)) + CC(!valid_ept_address(vcpu, vmcs12->ept_pointer))) return -EINVAL; if (nested_cpu_has_vmfunc(vmcs12)) { - if (vmcs12->vm_function_control & - ~vmx->nested.msrs.vmfunc_controls) + if (CC(vmcs12->vm_function_control & + ~vmx->nested.msrs.vmfunc_controls)) return -EINVAL; if (nested_cpu_has_eptp_switching(vmcs12)) { - if (!nested_cpu_has_ept(vmcs12) || - !page_address_valid(vcpu, vmcs12->eptp_list_address)) + if (CC(!nested_cpu_has_ept(vmcs12)) || + CC(!page_address_valid(vcpu, vmcs12->eptp_list_address))) return -EINVAL; } } @@ -2525,10 +2666,10 @@ static int nested_check_vm_exit_controls(struct kvm_vcpu *vcpu, { struct vcpu_vmx *vmx = to_vmx(vcpu); - if (!vmx_control_verify(vmcs12->vm_exit_controls, - vmx->nested.msrs.exit_ctls_low, - vmx->nested.msrs.exit_ctls_high) || - nested_vmx_check_exit_msr_switch_controls(vcpu, vmcs12)) + if (CC(!vmx_control_verify(vmcs12->vm_exit_controls, + vmx->nested.msrs.exit_ctls_low, + vmx->nested.msrs.exit_ctls_high)) || + CC(nested_vmx_check_exit_msr_switch_controls(vcpu, vmcs12))) return -EINVAL; return 0; @@ -2542,9 +2683,9 @@ static int nested_check_vm_entry_controls(struct kvm_vcpu *vcpu, { struct vcpu_vmx *vmx = to_vmx(vcpu); - if (!vmx_control_verify(vmcs12->vm_entry_controls, - vmx->nested.msrs.entry_ctls_low, - vmx->nested.msrs.entry_ctls_high)) + if (CC(!vmx_control_verify(vmcs12->vm_entry_controls, + vmx->nested.msrs.entry_ctls_low, + vmx->nested.msrs.entry_ctls_high))) return -EINVAL; /* @@ -2564,31 +2705,31 @@ static int nested_check_vm_entry_controls(struct kvm_vcpu *vcpu, bool prot_mode = !urg || vmcs12->guest_cr0 & X86_CR0_PE; /* VM-entry interruption-info field: interruption type */ - if (intr_type == INTR_TYPE_RESERVED || - (intr_type == INTR_TYPE_OTHER_EVENT && - !nested_cpu_supports_monitor_trap_flag(vcpu))) + if (CC(intr_type == INTR_TYPE_RESERVED) || + CC(intr_type == INTR_TYPE_OTHER_EVENT && + !nested_cpu_supports_monitor_trap_flag(vcpu))) return -EINVAL; /* VM-entry interruption-info field: vector */ - if ((intr_type == INTR_TYPE_NMI_INTR && vector != NMI_VECTOR) || - (intr_type == INTR_TYPE_HARD_EXCEPTION && vector > 31) || - (intr_type == INTR_TYPE_OTHER_EVENT && vector != 0)) + if (CC(intr_type == INTR_TYPE_NMI_INTR && vector != NMI_VECTOR) || + CC(intr_type == INTR_TYPE_HARD_EXCEPTION && vector > 31) || + CC(intr_type == INTR_TYPE_OTHER_EVENT && vector != 0)) return -EINVAL; /* VM-entry interruption-info field: deliver error code */ should_have_error_code = intr_type == INTR_TYPE_HARD_EXCEPTION && prot_mode && x86_exception_has_error_code(vector); - if (has_error_code != should_have_error_code) + if (CC(has_error_code != should_have_error_code)) return -EINVAL; /* VM-entry exception error code */ - if (has_error_code && - vmcs12->vm_entry_exception_error_code & GENMASK(31, 15)) + if (CC(has_error_code && + vmcs12->vm_entry_exception_error_code & GENMASK(31, 16))) return -EINVAL; /* VM-entry interruption-info field: reserved bits */ - if (intr_info & INTR_INFO_RESVD_BITS_MASK) + if (CC(intr_info & INTR_INFO_RESVD_BITS_MASK)) return -EINVAL; /* VM-entry instruction length */ @@ -2596,9 +2737,9 @@ static int nested_check_vm_entry_controls(struct kvm_vcpu *vcpu, case INTR_TYPE_SOFT_EXCEPTION: case INTR_TYPE_SOFT_INTR: case INTR_TYPE_PRIV_SW_EXCEPTION: - if ((vmcs12->vm_entry_instruction_len > 15) || - (vmcs12->vm_entry_instruction_len == 0 && - !nested_cpu_has_zero_length_injection(vcpu))) + if (CC(vmcs12->vm_entry_instruction_len > 15) || + CC(vmcs12->vm_entry_instruction_len == 0 && + CC(!nested_cpu_has_zero_length_injection(vcpu)))) return -EINVAL; } } @@ -2617,6 +2758,9 @@ static int nested_vmx_check_controls(struct kvm_vcpu *vcpu, nested_check_vm_entry_controls(vcpu, vmcs12)) return -EINVAL; + if (to_vmx(vcpu)->nested.enlightened_vmcs_enabled) + return nested_evmcs_check_controls(vmcs12); + return 0; } @@ -2625,43 +2769,62 @@ static int nested_vmx_check_host_state(struct kvm_vcpu *vcpu, { bool ia32e; - if (!nested_host_cr0_valid(vcpu, vmcs12->host_cr0) || - !nested_host_cr4_valid(vcpu, vmcs12->host_cr4) || - !nested_cr3_valid(vcpu, vmcs12->host_cr3)) + if (CC(!nested_host_cr0_valid(vcpu, vmcs12->host_cr0)) || + CC(!nested_host_cr4_valid(vcpu, vmcs12->host_cr4)) || + CC(!nested_cr3_valid(vcpu, vmcs12->host_cr3))) return -EINVAL; - if (is_noncanonical_address(vmcs12->host_ia32_sysenter_esp, vcpu) || - is_noncanonical_address(vmcs12->host_ia32_sysenter_eip, vcpu)) + if (CC(is_noncanonical_address(vmcs12->host_ia32_sysenter_esp, vcpu)) || + CC(is_noncanonical_address(vmcs12->host_ia32_sysenter_eip, vcpu))) return -EINVAL; if ((vmcs12->vm_exit_controls & VM_EXIT_LOAD_IA32_PAT) && - !kvm_pat_valid(vmcs12->host_ia32_pat)) + CC(!kvm_pat_valid(vmcs12->host_ia32_pat))) return -EINVAL; - ia32e = (vmcs12->vm_exit_controls & - VM_EXIT_HOST_ADDR_SPACE_SIZE) != 0; - - if (vmcs12->host_cs_selector & (SEGMENT_RPL_MASK | SEGMENT_TI_MASK) || - vmcs12->host_ss_selector & (SEGMENT_RPL_MASK | SEGMENT_TI_MASK) || - vmcs12->host_ds_selector & (SEGMENT_RPL_MASK | SEGMENT_TI_MASK) || - vmcs12->host_es_selector & (SEGMENT_RPL_MASK | SEGMENT_TI_MASK) || - vmcs12->host_fs_selector & (SEGMENT_RPL_MASK | SEGMENT_TI_MASK) || - vmcs12->host_gs_selector & (SEGMENT_RPL_MASK | SEGMENT_TI_MASK) || - vmcs12->host_tr_selector & (SEGMENT_RPL_MASK | SEGMENT_TI_MASK) || - vmcs12->host_cs_selector == 0 || - vmcs12->host_tr_selector == 0 || - (vmcs12->host_ss_selector == 0 && !ia32e)) + if ((vmcs12->vm_exit_controls & VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL) && + CC(!kvm_valid_perf_global_ctrl(vcpu_to_pmu(vcpu), + vmcs12->host_ia32_perf_global_ctrl))) return -EINVAL; #ifdef CONFIG_X86_64 - if (is_noncanonical_address(vmcs12->host_fs_base, vcpu) || - is_noncanonical_address(vmcs12->host_gs_base, vcpu) || - is_noncanonical_address(vmcs12->host_gdtr_base, vcpu) || - is_noncanonical_address(vmcs12->host_idtr_base, vcpu) || - is_noncanonical_address(vmcs12->host_tr_base, vcpu)) - return -EINVAL; + ia32e = !!(vcpu->arch.efer & EFER_LMA); +#else + ia32e = false; #endif + if (ia32e) { + if (CC(!(vmcs12->vm_exit_controls & VM_EXIT_HOST_ADDR_SPACE_SIZE)) || + CC(!(vmcs12->host_cr4 & X86_CR4_PAE))) + return -EINVAL; + } else { + if (CC(vmcs12->vm_exit_controls & VM_EXIT_HOST_ADDR_SPACE_SIZE) || + CC(vmcs12->vm_entry_controls & VM_ENTRY_IA32E_MODE) || + CC(vmcs12->host_cr4 & X86_CR4_PCIDE) || + CC((vmcs12->host_rip) >> 32)) + return -EINVAL; + } + + if (CC(vmcs12->host_cs_selector & (SEGMENT_RPL_MASK | SEGMENT_TI_MASK)) || + CC(vmcs12->host_ss_selector & (SEGMENT_RPL_MASK | SEGMENT_TI_MASK)) || + CC(vmcs12->host_ds_selector & (SEGMENT_RPL_MASK | SEGMENT_TI_MASK)) || + CC(vmcs12->host_es_selector & (SEGMENT_RPL_MASK | SEGMENT_TI_MASK)) || + CC(vmcs12->host_fs_selector & (SEGMENT_RPL_MASK | SEGMENT_TI_MASK)) || + CC(vmcs12->host_gs_selector & (SEGMENT_RPL_MASK | SEGMENT_TI_MASK)) || + CC(vmcs12->host_tr_selector & (SEGMENT_RPL_MASK | SEGMENT_TI_MASK)) || + CC(vmcs12->host_cs_selector == 0) || + CC(vmcs12->host_tr_selector == 0) || + CC(vmcs12->host_ss_selector == 0 && !ia32e)) + return -EINVAL; + + if (CC(is_noncanonical_address(vmcs12->host_fs_base, vcpu)) || + CC(is_noncanonical_address(vmcs12->host_gs_base, vcpu)) || + CC(is_noncanonical_address(vmcs12->host_gdtr_base, vcpu)) || + CC(is_noncanonical_address(vmcs12->host_idtr_base, vcpu)) || + CC(is_noncanonical_address(vmcs12->host_tr_base, vcpu)) || + CC(is_noncanonical_address(vmcs12->host_rip, vcpu))) + return -EINVAL; + /* * If the load IA32_EFER VM-exit control is 1, bits reserved in the * IA32_EFER MSR must be 0 in the field for that register. In addition, @@ -2669,9 +2832,9 @@ static int nested_vmx_check_host_state(struct kvm_vcpu *vcpu, * the host address-space size VM-exit control. */ if (vmcs12->vm_exit_controls & VM_EXIT_LOAD_IA32_EFER) { - if (!kvm_valid_efer(vcpu, vmcs12->host_ia32_efer) || - ia32e != !!(vmcs12->host_ia32_efer & EFER_LMA) || - ia32e != !!(vmcs12->host_ia32_efer & EFER_LME)) + if (CC(!kvm_valid_efer(vcpu, vmcs12->host_ia32_efer)) || + CC(ia32e != !!(vmcs12->host_ia32_efer & EFER_LMA)) || + CC(ia32e != !!(vmcs12->host_ia32_efer & EFER_LME))) return -EINVAL; } @@ -2688,16 +2851,16 @@ static int nested_vmx_check_vmcs_link_ptr(struct kvm_vcpu *vcpu, if (vmcs12->vmcs_link_pointer == -1ull) return 0; - if (!page_address_valid(vcpu, vmcs12->vmcs_link_pointer)) + if (CC(!page_address_valid(vcpu, vmcs12->vmcs_link_pointer))) return -EINVAL; - if (kvm_vcpu_map(vcpu, gpa_to_gfn(vmcs12->vmcs_link_pointer), &map)) + if (CC(kvm_vcpu_map(vcpu, gpa_to_gfn(vmcs12->vmcs_link_pointer), &map))) return -EINVAL; shadow = map.hva; - if (shadow->hdr.revision_id != VMCS12_REVISION || - shadow->hdr.shadow_vmcs != nested_cpu_has_shadow_vmcs(vmcs12)) + if (CC(shadow->hdr.revision_id != VMCS12_REVISION) || + CC(shadow->hdr.shadow_vmcs != nested_cpu_has_shadow_vmcs(vmcs12))) r = -EINVAL; kvm_vcpu_unmap(vcpu, &map, false); @@ -2709,8 +2872,8 @@ static int nested_vmx_check_vmcs_link_ptr(struct kvm_vcpu *vcpu, */ static int nested_check_guest_non_reg_state(struct vmcs12 *vmcs12) { - if (vmcs12->guest_activity_state != GUEST_ACTIVITY_ACTIVE && - vmcs12->guest_activity_state != GUEST_ACTIVITY_HLT) + if (CC(vmcs12->guest_activity_state != GUEST_ACTIVITY_ACTIVE && + vmcs12->guest_activity_state != GUEST_ACTIVITY_HLT)) return -EINVAL; return 0; @@ -2724,12 +2887,16 @@ static int nested_vmx_check_guest_state(struct kvm_vcpu *vcpu, *exit_qual = ENTRY_FAIL_DEFAULT; - if (!nested_guest_cr0_valid(vcpu, vmcs12->guest_cr0) || - !nested_guest_cr4_valid(vcpu, vmcs12->guest_cr4)) + if (CC(!nested_guest_cr0_valid(vcpu, vmcs12->guest_cr0)) || + CC(!nested_guest_cr4_valid(vcpu, vmcs12->guest_cr4))) + return -EINVAL; + + if ((vmcs12->vm_entry_controls & VM_ENTRY_LOAD_DEBUG_CONTROLS) && + CC(!kvm_dr7_valid(vmcs12->guest_dr7))) return -EINVAL; if ((vmcs12->vm_entry_controls & VM_ENTRY_LOAD_IA32_PAT) && - !kvm_pat_valid(vmcs12->guest_ia32_pat)) + CC(!kvm_pat_valid(vmcs12->guest_ia32_pat))) return -EINVAL; if (nested_vmx_check_vmcs_link_ptr(vcpu, vmcs12)) { @@ -2737,6 +2904,11 @@ static int nested_vmx_check_guest_state(struct kvm_vcpu *vcpu, return -EINVAL; } + if ((vmcs12->vm_entry_controls & VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL) && + CC(!kvm_valid_perf_global_ctrl(vcpu_to_pmu(vcpu), + vmcs12->guest_ia32_perf_global_ctrl))) + return -EINVAL; + /* * If the load IA32_EFER VM-entry control is 1, the following checks * are performed on the field for the IA32_EFER MSR: @@ -2749,16 +2921,16 @@ static int nested_vmx_check_guest_state(struct kvm_vcpu *vcpu, if (to_vmx(vcpu)->nested.nested_run_pending && (vmcs12->vm_entry_controls & VM_ENTRY_LOAD_IA32_EFER)) { ia32e = (vmcs12->vm_entry_controls & VM_ENTRY_IA32E_MODE) != 0; - if (!kvm_valid_efer(vcpu, vmcs12->guest_ia32_efer) || - ia32e != !!(vmcs12->guest_ia32_efer & EFER_LMA) || - ((vmcs12->guest_cr0 & X86_CR0_PG) && - ia32e != !!(vmcs12->guest_ia32_efer & EFER_LME))) + if (CC(!kvm_valid_efer(vcpu, vmcs12->guest_ia32_efer)) || + CC(ia32e != !!(vmcs12->guest_ia32_efer & EFER_LMA)) || + CC(((vmcs12->guest_cr0 & X86_CR0_PG) && + ia32e != !!(vmcs12->guest_ia32_efer & EFER_LME)))) return -EINVAL; } if ((vmcs12->vm_entry_controls & VM_ENTRY_LOAD_BNDCFGS) && - (is_noncanonical_address(vmcs12->guest_bndcfgs & PAGE_MASK, vcpu) || - (vmcs12->guest_bndcfgs & MSR_IA32_BNDCFGS_RSVD))) + (CC(is_noncanonical_address(vmcs12->guest_bndcfgs & PAGE_MASK, vcpu)) || + CC((vmcs12->guest_bndcfgs & MSR_IA32_BNDCFGS_RSVD)))) return -EINVAL; if (nested_check_guest_non_reg_state(vmcs12)) @@ -2841,9 +3013,13 @@ static int nested_vmx_check_vmentry_hw(struct kvm_vcpu *vcpu) vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, vmx->msr_autoload.guest.nr); if (vm_fail) { + u32 error = vmcs_read32(VM_INSTRUCTION_ERROR); + preempt_enable(); - WARN_ON_ONCE(vmcs_read32(VM_INSTRUCTION_ERROR) != - VMXERR_ENTRY_INVALID_CONTROL_FIELD); + + trace_kvm_nested_vmenter_failed( + "early hardware check VM-instruction error: ", error); + WARN_ON_ONCE(error != VMXERR_ENTRY_INVALID_CONTROL_FIELD); return 1; } @@ -2868,10 +3044,7 @@ static int nested_vmx_check_vmentry_hw(struct kvm_vcpu *vcpu) return 0; } -static inline bool nested_vmx_prepare_msr_bitmap(struct kvm_vcpu *vcpu, - struct vmcs12 *vmcs12); - -static void nested_get_vmcs12_pages(struct kvm_vcpu *vcpu) +static bool nested_get_vmcs12_pages(struct kvm_vcpu *vcpu) { struct vmcs12 *vmcs12 = get_vmcs12(vcpu); struct vcpu_vmx *vmx = to_vmx(vcpu); @@ -2887,23 +3060,22 @@ static void nested_get_vmcs12_pages(struct kvm_vcpu *vcpu) * to it so we can release it later. */ if (vmx->nested.apic_access_page) { /* shouldn't happen */ - kvm_release_page_dirty(vmx->nested.apic_access_page); + kvm_release_page_clean(vmx->nested.apic_access_page); vmx->nested.apic_access_page = NULL; } page = kvm_vcpu_gpa_to_page(vcpu, vmcs12->apic_access_addr); - /* - * If translation failed, no matter: This feature asks - * to exit when accessing the given address, and if it - * can never be accessed, this feature won't do - * anything anyway. - */ if (!is_error_page(page)) { vmx->nested.apic_access_page = page; hpa = page_to_phys(vmx->nested.apic_access_page); vmcs_write64(APIC_ACCESS_ADDR, hpa); } else { - secondary_exec_controls_clearbit(vmx, - SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES); + pr_debug_ratelimited("%s: no backing 'struct page' for APIC-access address in vmcs12\n", + __func__); + vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR; + vcpu->run->internal.suberror = + KVM_INTERNAL_ERROR_EMULATION; + vcpu->run->internal.ndata = 0; + return false; } } @@ -2948,6 +3120,7 @@ static void nested_get_vmcs12_pages(struct kvm_vcpu *vcpu) exec_controls_setbit(vmx, CPU_BASED_USE_MSR_BITMAPS); else exec_controls_clearbit(vmx, CPU_BASED_USE_MSR_BITMAPS); + return true; } /* @@ -2986,13 +3159,15 @@ static void load_vmcs12_host_state(struct kvm_vcpu *vcpu, /* * If from_vmentry is false, this is being called from state restore (either RSM * or KVM_SET_NESTED_STATE). Otherwise it's called from vmlaunch/vmresume. -+ * -+ * Returns: -+ * 0 - success, i.e. proceed with actual VMEnter -+ * 1 - consistency check VMExit -+ * -1 - consistency check VMFail + * + * Returns: + * NVMX_ENTRY_SUCCESS: Entered VMX non-root mode + * NVMX_ENTRY_VMFAIL: Consistency check VMFail + * NVMX_ENTRY_VMEXIT: Consistency check VMExit + * NVMX_ENTRY_KVM_INTERNAL_ERROR: KVM internal error */ -int nested_vmx_enter_non_root_mode(struct kvm_vcpu *vcpu, bool from_vmentry) +enum nvmx_vmentry_status nested_vmx_enter_non_root_mode(struct kvm_vcpu *vcpu, + bool from_vmentry) { struct vcpu_vmx *vmx = to_vmx(vcpu); struct vmcs12 *vmcs12 = get_vmcs12(vcpu); @@ -3001,7 +3176,7 @@ int nested_vmx_enter_non_root_mode(struct kvm_vcpu *vcpu, bool from_vmentry) u32 exit_qual; evaluate_pending_interrupts = exec_controls_get(vmx) & - (CPU_BASED_VIRTUAL_INTR_PENDING | CPU_BASED_VIRTUAL_NMI_PENDING); + (CPU_BASED_INTR_WINDOW_EXITING | CPU_BASED_NMI_WINDOW_EXITING); if (likely(!evaluate_pending_interrupts) && kvm_vcpu_apicv_active(vcpu)) evaluate_pending_interrupts |= vmx_has_apicv_interrupt(vcpu); @@ -3035,11 +3210,12 @@ int nested_vmx_enter_non_root_mode(struct kvm_vcpu *vcpu, bool from_vmentry) prepare_vmcs02_early(vmx, vmcs12); if (from_vmentry) { - nested_get_vmcs12_pages(vcpu); + if (unlikely(!nested_get_vmcs12_pages(vcpu))) + return NVMX_VMENTRY_KVM_INTERNAL_ERROR; if (nested_vmx_check_vmentry_hw(vcpu)) { vmx_switch_vmcs(vcpu, &vmx->vmcs01); - return -1; + return NVMX_VMENTRY_VMFAIL; } if (nested_vmx_check_guest_state(vcpu, vmcs12, &exit_qual)) @@ -3047,7 +3223,7 @@ int nested_vmx_enter_non_root_mode(struct kvm_vcpu *vcpu, bool from_vmentry) } enter_guest_mode(vcpu); - if (vmcs12->cpu_based_vm_exec_control & CPU_BASED_USE_TSC_OFFSETING) + if (vmcs12->cpu_based_vm_exec_control & CPU_BASED_USE_TSC_OFFSETTING) vcpu->arch.tsc_offset += vmcs12->tsc_offset; if (prepare_vmcs02(vcpu, vmcs12, &exit_qual)) @@ -3103,7 +3279,7 @@ int nested_vmx_enter_non_root_mode(struct kvm_vcpu *vcpu, bool from_vmentry) * returned as far as L1 is concerned. It will only return (and set * the success flag) when L2 exits (see nested_vmx_vmexit()). */ - return 0; + return NVMX_VMENTRY_SUCCESS; /* * A failed consistency check that leads to a VMExit during L1's @@ -3111,7 +3287,7 @@ int nested_vmx_enter_non_root_mode(struct kvm_vcpu *vcpu, bool from_vmentry) * 26.7 "VM-entry failures during or after loading guest state". */ vmentry_fail_vmexit_guest_mode: - if (vmcs12->cpu_based_vm_exec_control & CPU_BASED_USE_TSC_OFFSETING) + if (vmcs12->cpu_based_vm_exec_control & CPU_BASED_USE_TSC_OFFSETTING) vcpu->arch.tsc_offset -= vmcs12->tsc_offset; leave_guest_mode(vcpu); @@ -3119,14 +3295,14 @@ vmentry_fail_vmexit: vmx_switch_vmcs(vcpu, &vmx->vmcs01); if (!from_vmentry) - return 1; + return NVMX_VMENTRY_VMEXIT; load_vmcs12_host_state(vcpu, vmcs12); vmcs12->vm_exit_reason = exit_reason | VMX_EXIT_REASONS_FAILED_VMENTRY; vmcs12->exit_qualification = exit_qual; if (enable_shadow_vmcs || vmx->nested.hv_evmcs) vmx->nested.need_vmcs12_to_shadow_sync = true; - return 1; + return NVMX_VMENTRY_VMEXIT; } /* @@ -3136,9 +3312,9 @@ vmentry_fail_vmexit: static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch) { struct vmcs12 *vmcs12; + enum nvmx_vmentry_status status; struct vcpu_vmx *vmx = to_vmx(vcpu); u32 interrupt_shadow = vmx_get_interrupt_shadow(vcpu); - int ret; if (!nested_vmx_check_permission(vcpu)) return 1; @@ -3198,13 +3374,9 @@ static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch) * the nested entry. */ vmx->nested.nested_run_pending = 1; - ret = nested_vmx_enter_non_root_mode(vcpu, true); - vmx->nested.nested_run_pending = !ret; - if (ret > 0) - return 1; - else if (ret) - return nested_vmx_failValid(vcpu, - VMXERR_ENTRY_INVALID_CONTROL_FIELD); + status = nested_vmx_enter_non_root_mode(vcpu, true); + if (unlikely(status != NVMX_VMENTRY_SUCCESS)) + goto vmentry_failed; /* Hide L1D cache contents from the nested guest. */ vmx->vcpu.arch.l1tf_flush_l1d = true; @@ -3228,18 +3400,27 @@ static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch) */ if ((vmcs12->guest_activity_state == GUEST_ACTIVITY_HLT) && !(vmcs12->vm_entry_intr_info_field & INTR_INFO_VALID_MASK) && - !(vmcs12->cpu_based_vm_exec_control & CPU_BASED_VIRTUAL_NMI_PENDING) && - !((vmcs12->cpu_based_vm_exec_control & CPU_BASED_VIRTUAL_INTR_PENDING) && + !(vmcs12->cpu_based_vm_exec_control & CPU_BASED_NMI_WINDOW_EXITING) && + !((vmcs12->cpu_based_vm_exec_control & CPU_BASED_INTR_WINDOW_EXITING) && (vmcs12->guest_rflags & X86_EFLAGS_IF))) { vmx->nested.nested_run_pending = 0; return kvm_vcpu_halt(vcpu); } return 1; + +vmentry_failed: + vmx->nested.nested_run_pending = 0; + if (status == NVMX_VMENTRY_KVM_INTERNAL_ERROR) + return 0; + if (status == NVMX_VMENTRY_VMEXIT) + return 1; + WARN_ON_ONCE(status != NVMX_VMENTRY_VMFAIL); + return nested_vmx_failValid(vcpu, VMXERR_ENTRY_INVALID_CONTROL_FIELD); } /* * On a nested exit from L2 to L1, vmcs12.guest_cr0 might not be up-to-date - * because L2 may have changed some cr0 bits directly (CRO_GUEST_HOST_MASK). + * because L2 may have changed some cr0 bits directly (CR0_GUEST_HOST_MASK). * This function returns the new value we should put in vmcs12.guest_cr0. * It's not enough to just return the vmcs02 GUEST_CR0. Rather, * 1. Bits that neither L0 nor L1 trapped, were set directly by L2 and are now @@ -3395,12 +3576,50 @@ static void nested_vmx_inject_exception_vmexit(struct kvm_vcpu *vcpu, nested_vmx_vmexit(vcpu, EXIT_REASON_EXCEPTION_NMI, intr_info, exit_qual); } +/* + * Returns true if a debug trap is pending delivery. + * + * In KVM, debug traps bear an exception payload. As such, the class of a #DB + * exception may be inferred from the presence of an exception payload. + */ +static inline bool vmx_pending_dbg_trap(struct kvm_vcpu *vcpu) +{ + return vcpu->arch.exception.pending && + vcpu->arch.exception.nr == DB_VECTOR && + vcpu->arch.exception.payload; +} + +/* + * Certain VM-exits set the 'pending debug exceptions' field to indicate a + * recognized #DB (data or single-step) that has yet to be delivered. Since KVM + * represents these debug traps with a payload that is said to be compatible + * with the 'pending debug exceptions' field, write the payload to the VMCS + * field if a VM-exit is delivered before the debug trap. + */ +static void nested_vmx_update_pending_dbg(struct kvm_vcpu *vcpu) +{ + if (vmx_pending_dbg_trap(vcpu)) + vmcs_writel(GUEST_PENDING_DBG_EXCEPTIONS, + vcpu->arch.exception.payload); +} + static int vmx_check_nested_events(struct kvm_vcpu *vcpu, bool external_intr) { struct vcpu_vmx *vmx = to_vmx(vcpu); unsigned long exit_qual; bool block_nested_events = vmx->nested.nested_run_pending || kvm_event_needs_reinjection(vcpu); + struct kvm_lapic *apic = vcpu->arch.apic; + + if (lapic_in_kernel(vcpu) && + test_bit(KVM_APIC_INIT, &apic->pending_events)) { + if (block_nested_events) + return -EBUSY; + nested_vmx_update_pending_dbg(vcpu); + clear_bit(KVM_APIC_INIT, &apic->pending_events); + nested_vmx_vmexit(vcpu, EXIT_REASON_INIT_SIGNAL, 0, 0); + return 0; + } if (vcpu->arch.exception.pending && nested_vmx_check_exception(vcpu, &exit_qual)) { @@ -3801,8 +4020,8 @@ static void load_vmcs12_host_state(struct kvm_vcpu *vcpu, vcpu->arch.pat = vmcs12->host_ia32_pat; } if (vmcs12->vm_exit_controls & VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL) - vmcs_write64(GUEST_IA32_PERF_GLOBAL_CTRL, - vmcs12->host_ia32_perf_global_ctrl); + WARN_ON_ONCE(kvm_set_msr(vcpu, MSR_CORE_PERF_GLOBAL_CTRL, + vmcs12->host_ia32_perf_global_ctrl)); /* Set L1 segment info according to Intel SDM 27.5.2 Loading Host Segment and Descriptor-Table Registers */ @@ -3889,7 +4108,6 @@ static void nested_vmx_restore_host_state(struct kvm_vcpu *vcpu) struct vmcs12 *vmcs12 = get_vmcs12(vcpu); struct vcpu_vmx *vmx = to_vmx(vcpu); struct vmx_msr_entry g, h; - struct msr_data msr; gpa_t gpa; u32 i, j; @@ -3922,7 +4140,7 @@ static void nested_vmx_restore_host_state(struct kvm_vcpu *vcpu) nested_ept_uninit_mmu_context(vcpu); vcpu->arch.cr3 = vmcs_readl(GUEST_CR3); - __set_bit(VCPU_EXREG_CR3, (ulong *)&vcpu->arch.regs_avail); + kvm_register_mark_available(vcpu, VCPU_EXREG_CR3); /* * Use ept_save_pdptrs(vcpu) to load the MMU's cached PDPTRs @@ -3949,7 +4167,6 @@ static void nested_vmx_restore_host_state(struct kvm_vcpu *vcpu) * from the guest value. The intent is to stuff host state as * silently as possible, not to fully process the exit load list. */ - msr.host_initiated = false; for (i = 0; i < vmcs12->vm_entry_msr_load_count; i++) { gpa = vmcs12->vm_entry_msr_load_addr + (i * sizeof(g)); if (kvm_vcpu_read_guest(vcpu, gpa, &g, sizeof(g))) { @@ -3979,9 +4196,7 @@ static void nested_vmx_restore_host_state(struct kvm_vcpu *vcpu) goto vmabort; } - msr.index = h.index; - msr.data = h.value; - if (kvm_set_msr(vcpu, &msr)) { + if (kvm_set_msr(vcpu, h.index, h.value)) { pr_debug_ratelimited( "%s WRMSR failed (%u, 0x%x, 0x%llx)\n", __func__, j, h.index, h.value); @@ -4015,7 +4230,7 @@ void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 exit_reason, if (nested_cpu_has_preemption_timer(vmcs12)) hrtimer_cancel(&to_vmx(vcpu)->nested.preemption_timer); - if (vmcs12->cpu_based_vm_exec_control & CPU_BASED_USE_TSC_OFFSETING) + if (vmcs12->cpu_based_vm_exec_control & CPU_BASED_USE_TSC_OFFSETTING) vcpu->arch.tsc_offset -= vmcs12->tsc_offset; if (likely(!vmx->fail)) { @@ -4053,6 +4268,8 @@ void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 exit_reason, vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, vmx->msr_autoload.host.nr); vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, vmx->msr_autoload.guest.nr); vmcs_write64(TSC_OFFSET, vcpu->arch.tsc_offset); + if (vmx->nested.l1_tpr_threshold != -1) + vmcs_write32(TPR_THRESHOLD, vmx->nested.l1_tpr_threshold); if (kvm_has_tsc_control) decache_tsc_multiplier(vmx); @@ -4060,15 +4277,11 @@ void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 exit_reason, if (vmx->nested.change_vmcs01_virtual_apic_mode) { vmx->nested.change_vmcs01_virtual_apic_mode = false; vmx_set_virtual_apic_mode(vcpu); - } else if (!nested_cpu_has_ept(vmcs12) && - nested_cpu_has2(vmcs12, - SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES)) { - vmx_flush_tlb(vcpu, true); } /* Unpin physical memory we referred to in vmcs02 */ if (vmx->nested.apic_access_page) { - kvm_release_page_dirty(vmx->nested.apic_access_page); + kvm_release_page_clean(vmx->nested.apic_access_page); vmx->nested.apic_access_page = NULL; } kvm_vcpu_unmap(vcpu, &vmx->nested.virtual_apic_map, true); @@ -4268,6 +4481,27 @@ int get_vmx_mem_address(struct kvm_vcpu *vcpu, unsigned long exit_qualification, return 0; } +void nested_vmx_pmu_entry_exit_ctls_update(struct kvm_vcpu *vcpu) +{ + struct vcpu_vmx *vmx; + + if (!nested_vmx_allowed(vcpu)) + return; + + vmx = to_vmx(vcpu); + if (kvm_x86_ops->pmu_ops->is_valid_msr(vcpu, MSR_CORE_PERF_GLOBAL_CTRL)) { + vmx->nested.msrs.entry_ctls_high |= + VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL; + vmx->nested.msrs.exit_ctls_high |= + VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL; + } else { + vmx->nested.msrs.entry_ctls_high &= + ~VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL; + vmx->nested.msrs.exit_ctls_high &= + ~VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL; + } +} + static int nested_vmx_get_vmptr(struct kvm_vcpu *vcpu, gpa_t *vmpointer) { gva_t gva; @@ -4375,8 +4609,8 @@ static int handle_vmon(struct kvm_vcpu *vcpu) gpa_t vmptr; uint32_t revision; struct vcpu_vmx *vmx = to_vmx(vcpu); - const u64 VMXON_NEEDED_FEATURES = FEATURE_CONTROL_LOCKED - | FEATURE_CONTROL_VMXON_ENABLED_OUTSIDE_SMX; + const u64 VMXON_NEEDED_FEATURES = FEAT_CTL_LOCKED + | FEAT_CTL_VMX_ENABLED_OUTSIDE_SMX; /* * The Intel VMX Instruction Reference lists a bunch of bits that are @@ -4466,7 +4700,12 @@ static int handle_vmoff(struct kvm_vcpu *vcpu) { if (!nested_vmx_check_permission(vcpu)) return 1; + free_nested(vcpu); + + /* Process a latched INIT during time CPU was in VMX operation */ + kvm_make_request(KVM_REQ_EVENT, vcpu); + return nested_vmx_succeed(vcpu); } @@ -4516,8 +4755,6 @@ static int handle_vmclear(struct kvm_vcpu *vcpu) return nested_vmx_succeed(vcpu); } -static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch); - /* Emulate the VMLAUNCH instruction */ static int handle_vmlaunch(struct kvm_vcpu *vcpu) { @@ -4533,35 +4770,32 @@ static int handle_vmresume(struct kvm_vcpu *vcpu) static int handle_vmread(struct kvm_vcpu *vcpu) { - unsigned long field; - u64 field_value; + struct vmcs12 *vmcs12 = is_guest_mode(vcpu) ? get_shadow_vmcs12(vcpu) + : get_vmcs12(vcpu); unsigned long exit_qualification = vmcs_readl(EXIT_QUALIFICATION); - u32 vmx_instruction_info = vmcs_read32(VMX_INSTRUCTION_INFO); - int len; + u32 instr_info = vmcs_read32(VMX_INSTRUCTION_INFO); + struct vcpu_vmx *vmx = to_vmx(vcpu); + struct x86_exception e; + unsigned long field; + u64 value; gva_t gva = 0; - struct vmcs12 *vmcs12; short offset; + int len; if (!nested_vmx_check_permission(vcpu)) return 1; - if (to_vmx(vcpu)->nested.current_vmptr == -1ull) + /* + * In VMX non-root operation, when the VMCS-link pointer is -1ull, + * any VMREAD sets the ALU flags for VMfailInvalid. + */ + if (vmx->nested.current_vmptr == -1ull || + (is_guest_mode(vcpu) && + get_vmcs12(vcpu)->vmcs_link_pointer == -1ull)) return nested_vmx_failInvalid(vcpu); - if (!is_guest_mode(vcpu)) - vmcs12 = get_vmcs12(vcpu); - else { - /* - * When vmcs->vmcs_link_pointer is -1ull, any VMREAD - * to shadowed-field sets the ALU flags for VMfailInvalid. - */ - if (get_vmcs12(vcpu)->vmcs_link_pointer == -1ull) - return nested_vmx_failInvalid(vcpu); - vmcs12 = get_shadow_vmcs12(vcpu); - } - /* Decode instruction info and find the field to read */ - field = kvm_register_readl(vcpu, (((vmx_instruction_info) >> 28) & 0xf)); + field = kvm_register_readl(vcpu, (((instr_info) >> 28) & 0xf)); offset = vmcs_field_to_offset(field); if (offset < 0) @@ -4571,24 +4805,26 @@ static int handle_vmread(struct kvm_vcpu *vcpu) if (!is_guest_mode(vcpu) && is_vmcs12_ext_field(field)) copy_vmcs02_to_vmcs12_rare(vcpu, vmcs12); - /* Read the field, zero-extended to a u64 field_value */ - field_value = vmcs12_read_any(vmcs12, field, offset); + /* Read the field, zero-extended to a u64 value */ + value = vmcs12_read_any(vmcs12, field, offset); /* * Now copy part of this value to register or memory, as requested. * Note that the number of bits actually copied is 32 or 64 depending * on the guest's mode (32 or 64 bit), not on the given field's length. */ - if (vmx_instruction_info & (1u << 10)) { - kvm_register_writel(vcpu, (((vmx_instruction_info) >> 3) & 0xf), - field_value); + if (instr_info & BIT(10)) { + kvm_register_writel(vcpu, (((instr_info) >> 3) & 0xf), value); } else { len = is_64_bit_mode(vcpu) ? 8 : 4; if (get_vmx_mem_address(vcpu, exit_qualification, - vmx_instruction_info, true, len, &gva)) + instr_info, true, len, &gva)) return 1; /* _system ok, nested_vmx_check_permission has verified cpl=0 */ - kvm_write_guest_virt_system(vcpu, gva, &field_value, len, NULL); + if (kvm_write_guest_virt_system(vcpu, gva, &value, len, &e)) { + kvm_inject_page_fault(vcpu, &e); + return 1; + } } return nested_vmx_succeed(vcpu); @@ -4620,46 +4856,58 @@ static bool is_shadow_field_ro(unsigned long field) static int handle_vmwrite(struct kvm_vcpu *vcpu) { + struct vmcs12 *vmcs12 = is_guest_mode(vcpu) ? get_shadow_vmcs12(vcpu) + : get_vmcs12(vcpu); + unsigned long exit_qualification = vmcs_readl(EXIT_QUALIFICATION); + u32 instr_info = vmcs_read32(VMX_INSTRUCTION_INFO); + struct vcpu_vmx *vmx = to_vmx(vcpu); + struct x86_exception e; unsigned long field; - int len; + short offset; gva_t gva; - struct vcpu_vmx *vmx = to_vmx(vcpu); - unsigned long exit_qualification = vmcs_readl(EXIT_QUALIFICATION); - u32 vmx_instruction_info = vmcs_read32(VMX_INSTRUCTION_INFO); + int len; - /* The value to write might be 32 or 64 bits, depending on L1's long + /* + * The value to write might be 32 or 64 bits, depending on L1's long * mode, and eventually we need to write that into a field of several * possible lengths. The code below first zero-extends the value to 64 - * bit (field_value), and then copies only the appropriate number of + * bit (value), and then copies only the appropriate number of * bits into the vmcs12 field. */ - u64 field_value = 0; - struct x86_exception e; - struct vmcs12 *vmcs12; - short offset; + u64 value = 0; if (!nested_vmx_check_permission(vcpu)) return 1; - if (vmx->nested.current_vmptr == -1ull) + /* + * In VMX non-root operation, when the VMCS-link pointer is -1ull, + * any VMWRITE sets the ALU flags for VMfailInvalid. + */ + if (vmx->nested.current_vmptr == -1ull || + (is_guest_mode(vcpu) && + get_vmcs12(vcpu)->vmcs_link_pointer == -1ull)) return nested_vmx_failInvalid(vcpu); - if (vmx_instruction_info & (1u << 10)) - field_value = kvm_register_readl(vcpu, - (((vmx_instruction_info) >> 3) & 0xf)); + if (instr_info & BIT(10)) + value = kvm_register_readl(vcpu, (((instr_info) >> 3) & 0xf)); else { len = is_64_bit_mode(vcpu) ? 8 : 4; if (get_vmx_mem_address(vcpu, exit_qualification, - vmx_instruction_info, false, len, &gva)) + instr_info, false, len, &gva)) return 1; - if (kvm_read_guest_virt(vcpu, gva, &field_value, len, &e)) { + if (kvm_read_guest_virt(vcpu, gva, &value, len, &e)) { kvm_inject_page_fault(vcpu, &e); return 1; } } + field = kvm_register_readl(vcpu, (((instr_info) >> 28) & 0xf)); + + offset = vmcs_field_to_offset(field); + if (offset < 0) + return nested_vmx_failValid(vcpu, + VMXERR_UNSUPPORTED_VMCS_COMPONENT); - field = kvm_register_readl(vcpu, (((vmx_instruction_info) >> 28) & 0xf)); /* * If the vCPU supports "VMWRITE to any supported field in the * VMCS," then the "read-only" fields are actually read/write. @@ -4669,29 +4917,12 @@ static int handle_vmwrite(struct kvm_vcpu *vcpu) return nested_vmx_failValid(vcpu, VMXERR_VMWRITE_READ_ONLY_VMCS_COMPONENT); - if (!is_guest_mode(vcpu)) { - vmcs12 = get_vmcs12(vcpu); - - /* - * Ensure vmcs12 is up-to-date before any VMWRITE that dirties - * vmcs12, else we may crush a field or consume a stale value. - */ - if (!is_shadow_field_rw(field)) - copy_vmcs02_to_vmcs12_rare(vcpu, vmcs12); - } else { - /* - * When vmcs->vmcs_link_pointer is -1ull, any VMWRITE - * to shadowed-field sets the ALU flags for VMfailInvalid. - */ - if (get_vmcs12(vcpu)->vmcs_link_pointer == -1ull) - return nested_vmx_failInvalid(vcpu); - vmcs12 = get_shadow_vmcs12(vcpu); - } - - offset = vmcs_field_to_offset(field); - if (offset < 0) - return nested_vmx_failValid(vcpu, - VMXERR_UNSUPPORTED_VMCS_COMPONENT); + /* + * Ensure vmcs12 is up-to-date before any VMWRITE that dirties + * vmcs12, else we may crush a field or consume a stale value. + */ + if (!is_guest_mode(vcpu) && !is_shadow_field_rw(field)) + copy_vmcs02_to_vmcs12_rare(vcpu, vmcs12); /* * Some Intel CPUs intentionally drop the reserved bits of the AR byte @@ -4702,9 +4933,9 @@ static int handle_vmwrite(struct kvm_vcpu *vcpu) * the stripped down value, L2 sees the full value as stored by KVM). */ if (field >= GUEST_ES_AR_BYTES && field <= GUEST_TR_AR_BYTES) - field_value &= 0x1f0ff; + value &= 0x1f0ff; - vmcs12_write_any(vmcs12, field, offset, field_value); + vmcs12_write_any(vmcs12, field, offset, value); /* * Do not track vmcs12 dirty-state if in guest-mode as we actually @@ -4721,7 +4952,7 @@ static int handle_vmwrite(struct kvm_vcpu *vcpu) preempt_disable(); vmcs_load(vmx->vmcs01.shadow_vmcs); - __vmcs_writel(field, field_value); + __vmcs_writel(field, value); vmcs_clear(vmx->vmcs01.shadow_vmcs); vmcs_load(vmx->loaded_vmcs->vmcs); @@ -5259,8 +5490,9 @@ bool nested_vmx_exit_reflected(struct kvm_vcpu *vcpu, u32 exit_reason) return false; if (unlikely(vmx->fail)) { - pr_info_ratelimited("%s failed vm entry %x\n", __func__, - vmcs_read32(VM_INSTRUCTION_ERROR)); + trace_kvm_nested_vmenter_failed( + "hardware VM-instruction error: ", + vmcs_read32(VM_INSTRUCTION_ERROR)); return true; } @@ -5303,10 +5535,10 @@ bool nested_vmx_exit_reflected(struct kvm_vcpu *vcpu, u32 exit_reason) return false; case EXIT_REASON_TRIPLE_FAULT: return true; - case EXIT_REASON_PENDING_INTERRUPT: - return nested_cpu_has(vmcs12, CPU_BASED_VIRTUAL_INTR_PENDING); + case EXIT_REASON_INTERRUPT_WINDOW: + return nested_cpu_has(vmcs12, CPU_BASED_INTR_WINDOW_EXITING); case EXIT_REASON_NMI_WINDOW: - return nested_cpu_has(vmcs12, CPU_BASED_VIRTUAL_NMI_PENDING); + return nested_cpu_has(vmcs12, CPU_BASED_NMI_WINDOW_EXITING); case EXIT_REASON_TASK_SWITCH: return true; case EXIT_REASON_CPUID: @@ -5420,6 +5652,10 @@ bool nested_vmx_exit_reflected(struct kvm_vcpu *vcpu, u32 exit_reason) case EXIT_REASON_ENCLS: /* SGX is never exposed to L1 */ return false; + case EXIT_REASON_UMWAIT: + case EXIT_REASON_TPAUSE: + return nested_cpu_has2(vmcs12, + SECONDARY_EXEC_ENABLE_USR_WAIT_PAUSE); default: return true; } @@ -5695,7 +5931,7 @@ error_guest_mode: return ret; } -void nested_vmx_vcpu_setup(void) +void nested_vmx_set_vmcs_shadowing_bitmap(void) { if (enable_shadow_vmcs) { vmcs_write64(VMREAD_BITMAP, __pa(vmx_vmread_bitmap)); @@ -5790,8 +6026,8 @@ void nested_vmx_setup_ctls_msrs(struct nested_vmx_msrs *msrs, u32 ept_caps, msrs->procbased_ctls_low = CPU_BASED_ALWAYSON_WITHOUT_TRUE_MSR; msrs->procbased_ctls_high &= - CPU_BASED_VIRTUAL_INTR_PENDING | - CPU_BASED_VIRTUAL_NMI_PENDING | CPU_BASED_USE_TSC_OFFSETING | + CPU_BASED_INTR_WINDOW_EXITING | + CPU_BASED_NMI_WINDOW_EXITING | CPU_BASED_USE_TSC_OFFSETTING | CPU_BASED_HLT_EXITING | CPU_BASED_INVLPG_EXITING | CPU_BASED_MWAIT_EXITING | CPU_BASED_CR3_LOAD_EXITING | CPU_BASED_CR3_STORE_EXITING | @@ -5976,23 +6212,23 @@ __init int nested_vmx_hardware_setup(int (*exit_handlers[])(struct kvm_vcpu *)) init_vmcs_shadow_fields(); } - exit_handlers[EXIT_REASON_VMCLEAR] = handle_vmclear, - exit_handlers[EXIT_REASON_VMLAUNCH] = handle_vmlaunch, - exit_handlers[EXIT_REASON_VMPTRLD] = handle_vmptrld, - exit_handlers[EXIT_REASON_VMPTRST] = handle_vmptrst, - exit_handlers[EXIT_REASON_VMREAD] = handle_vmread, - exit_handlers[EXIT_REASON_VMRESUME] = handle_vmresume, - exit_handlers[EXIT_REASON_VMWRITE] = handle_vmwrite, - exit_handlers[EXIT_REASON_VMOFF] = handle_vmoff, - exit_handlers[EXIT_REASON_VMON] = handle_vmon, - exit_handlers[EXIT_REASON_INVEPT] = handle_invept, - exit_handlers[EXIT_REASON_INVVPID] = handle_invvpid, - exit_handlers[EXIT_REASON_VMFUNC] = handle_vmfunc, + exit_handlers[EXIT_REASON_VMCLEAR] = handle_vmclear; + exit_handlers[EXIT_REASON_VMLAUNCH] = handle_vmlaunch; + exit_handlers[EXIT_REASON_VMPTRLD] = handle_vmptrld; + exit_handlers[EXIT_REASON_VMPTRST] = handle_vmptrst; + exit_handlers[EXIT_REASON_VMREAD] = handle_vmread; + exit_handlers[EXIT_REASON_VMRESUME] = handle_vmresume; + exit_handlers[EXIT_REASON_VMWRITE] = handle_vmwrite; + exit_handlers[EXIT_REASON_VMOFF] = handle_vmoff; + exit_handlers[EXIT_REASON_VMON] = handle_vmon; + exit_handlers[EXIT_REASON_INVEPT] = handle_invept; + exit_handlers[EXIT_REASON_INVVPID] = handle_invvpid; + exit_handlers[EXIT_REASON_VMFUNC] = handle_vmfunc; kvm_x86_ops->check_nested_events = vmx_check_nested_events; kvm_x86_ops->get_nested_state = vmx_get_nested_state; kvm_x86_ops->set_nested_state = vmx_set_nested_state; - kvm_x86_ops->get_vmcs12_pages = nested_get_vmcs12_pages, + kvm_x86_ops->get_vmcs12_pages = nested_get_vmcs12_pages; kvm_x86_ops->nested_enable_evmcs = nested_enable_evmcs; kvm_x86_ops->nested_get_evmcs_version = nested_get_evmcs_version; diff --git a/arch/x86/kvm/vmx/nested.h b/arch/x86/kvm/vmx/nested.h index 187d39bf0bf1..fc874d4ead0f 100644 --- a/arch/x86/kvm/vmx/nested.h +++ b/arch/x86/kvm/vmx/nested.h @@ -6,14 +6,25 @@ #include "vmcs12.h" #include "vmx.h" +/* + * Status returned by nested_vmx_enter_non_root_mode(): + */ +enum nvmx_vmentry_status { + NVMX_VMENTRY_SUCCESS, /* Entered VMX non-root mode */ + NVMX_VMENTRY_VMFAIL, /* Consistency check VMFail */ + NVMX_VMENTRY_VMEXIT, /* Consistency check VMExit */ + NVMX_VMENTRY_KVM_INTERNAL_ERROR,/* KVM internal error */ +}; + void vmx_leave_nested(struct kvm_vcpu *vcpu); void nested_vmx_setup_ctls_msrs(struct nested_vmx_msrs *msrs, u32 ept_caps, bool apicv); void nested_vmx_hardware_unsetup(void); __init int nested_vmx_hardware_setup(int (*exit_handlers[])(struct kvm_vcpu *)); -void nested_vmx_vcpu_setup(void); +void nested_vmx_set_vmcs_shadowing_bitmap(void); void nested_vmx_free_vcpu(struct kvm_vcpu *vcpu); -int nested_vmx_enter_non_root_mode(struct kvm_vcpu *vcpu, bool from_vmentry); +enum nvmx_vmentry_status nested_vmx_enter_non_root_mode(struct kvm_vcpu *vcpu, + bool from_vmentry); bool nested_vmx_exit_reflected(struct kvm_vcpu *vcpu, u32 exit_reason); void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 exit_reason, u32 exit_intr_info, unsigned long exit_qualification); @@ -22,6 +33,7 @@ int vmx_set_vmx_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 data); int vmx_get_vmx_msr(struct nested_vmx_msrs *msrs, u32 msr_index, u64 *pdata); int get_vmx_mem_address(struct kvm_vcpu *vcpu, unsigned long exit_qualification, u32 vmx_instruction_info, bool wr, int len, gva_t *ret); +void nested_vmx_pmu_entry_exit_ctls_update(struct kvm_vcpu *vcpu); static inline struct vmcs12 *get_vmcs12(struct kvm_vcpu *vcpu) { @@ -245,7 +257,7 @@ static inline bool fixed_bits_valid(u64 val, u64 fixed0, u64 fixed1) return ((val & fixed1) | fixed0) == val; } -static bool nested_guest_cr0_valid(struct kvm_vcpu *vcpu, unsigned long val) +static inline bool nested_guest_cr0_valid(struct kvm_vcpu *vcpu, unsigned long val) { u64 fixed0 = to_vmx(vcpu)->nested.msrs.cr0_fixed0; u64 fixed1 = to_vmx(vcpu)->nested.msrs.cr0_fixed1; @@ -259,7 +271,7 @@ static bool nested_guest_cr0_valid(struct kvm_vcpu *vcpu, unsigned long val) return fixed_bits_valid(val, fixed0, fixed1); } -static bool nested_host_cr0_valid(struct kvm_vcpu *vcpu, unsigned long val) +static inline bool nested_host_cr0_valid(struct kvm_vcpu *vcpu, unsigned long val) { u64 fixed0 = to_vmx(vcpu)->nested.msrs.cr0_fixed0; u64 fixed1 = to_vmx(vcpu)->nested.msrs.cr0_fixed1; @@ -267,7 +279,7 @@ static bool nested_host_cr0_valid(struct kvm_vcpu *vcpu, unsigned long val) return fixed_bits_valid(val, fixed0, fixed1); } -static bool nested_cr4_valid(struct kvm_vcpu *vcpu, unsigned long val) +static inline bool nested_cr4_valid(struct kvm_vcpu *vcpu, unsigned long val) { u64 fixed0 = to_vmx(vcpu)->nested.msrs.cr4_fixed0; u64 fixed1 = to_vmx(vcpu)->nested.msrs.cr4_fixed1; diff --git a/arch/x86/kvm/vmx/ops.h b/arch/x86/kvm/vmx/ops.h index 2200fb698dd0..45eaedee2ac0 100644 --- a/arch/x86/kvm/vmx/ops.h +++ b/arch/x86/kvm/vmx/ops.h @@ -11,8 +11,13 @@ #include "vmcs.h" #define __ex(x) __kvm_handle_fault_on_reboot(x) -#define __ex_clear(x, reg) \ - ____kvm_handle_fault_on_reboot(x, "xor " reg ", " reg) + +asmlinkage void vmread_error(unsigned long field, bool fault); +void vmwrite_error(unsigned long field, unsigned long value); +void vmclear_error(struct vmcs *vmcs, u64 phys_addr); +void vmptrld_error(struct vmcs *vmcs, u64 phys_addr); +void invvpid_error(unsigned long ext, u16 vpid, gva_t gva); +void invept_error(unsigned long ext, u64 eptp, gpa_t gpa); static __always_inline void vmcs_check16(unsigned long field) { @@ -62,8 +67,22 @@ static __always_inline unsigned long __vmcs_readl(unsigned long field) { unsigned long value; - asm volatile (__ex_clear("vmread %1, %0", "%k0") - : "=r"(value) : "r"(field)); + asm volatile("1: vmread %2, %1\n\t" + ".byte 0x3e\n\t" /* branch taken hint */ + "ja 3f\n\t" + "mov %2, %%" _ASM_ARG1 "\n\t" + "xor %%" _ASM_ARG2 ", %%" _ASM_ARG2 "\n\t" + "2: call vmread_error\n\t" + "xor %k1, %k1\n\t" + "3:\n\t" + + ".pushsection .fixup, \"ax\"\n\t" + "4: mov %2, %%" _ASM_ARG1 "\n\t" + "mov $1, %%" _ASM_ARG2 "\n\t" + "jmp 2b\n\t" + ".popsection\n\t" + _ASM_EXTABLE(1b, 4b) + : ASM_CALL_CONSTRAINT, "=r"(value) : "r"(field) : "cc"); return value; } @@ -103,21 +122,39 @@ static __always_inline unsigned long vmcs_readl(unsigned long field) return __vmcs_readl(field); } -static noinline void vmwrite_error(unsigned long field, unsigned long value) -{ - printk(KERN_ERR "vmwrite error: reg %lx value %lx (err %d)\n", - field, value, vmcs_read32(VM_INSTRUCTION_ERROR)); - dump_stack(); -} +#define vmx_asm1(insn, op1, error_args...) \ +do { \ + asm_volatile_goto("1: " __stringify(insn) " %0\n\t" \ + ".byte 0x2e\n\t" /* branch not taken hint */ \ + "jna %l[error]\n\t" \ + _ASM_EXTABLE(1b, %l[fault]) \ + : : op1 : "cc" : error, fault); \ + return; \ +error: \ + insn##_error(error_args); \ + return; \ +fault: \ + kvm_spurious_fault(); \ +} while (0) + +#define vmx_asm2(insn, op1, op2, error_args...) \ +do { \ + asm_volatile_goto("1: " __stringify(insn) " %1, %0\n\t" \ + ".byte 0x2e\n\t" /* branch not taken hint */ \ + "jna %l[error]\n\t" \ + _ASM_EXTABLE(1b, %l[fault]) \ + : : op1, op2 : "cc" : error, fault); \ + return; \ +error: \ + insn##_error(error_args); \ + return; \ +fault: \ + kvm_spurious_fault(); \ +} while (0) static __always_inline void __vmcs_writel(unsigned long field, unsigned long value) { - bool error; - - asm volatile (__ex("vmwrite %2, %1") CC_SET(na) - : CC_OUT(na) (error) : "r"(field), "rm"(value)); - if (unlikely(error)) - vmwrite_error(field, value); + vmx_asm2(vmwrite, "r"(field), "rm"(value), field, value); } static __always_inline void vmcs_write16(unsigned long field, u16 value) @@ -182,28 +219,18 @@ static __always_inline void vmcs_set_bits(unsigned long field, u32 mask) static inline void vmcs_clear(struct vmcs *vmcs) { u64 phys_addr = __pa(vmcs); - bool error; - asm volatile (__ex("vmclear %1") CC_SET(na) - : CC_OUT(na) (error) : "m"(phys_addr)); - if (unlikely(error)) - printk(KERN_ERR "kvm: vmclear fail: %p/%llx\n", - vmcs, phys_addr); + vmx_asm1(vmclear, "m"(phys_addr), vmcs, phys_addr); } static inline void vmcs_load(struct vmcs *vmcs) { u64 phys_addr = __pa(vmcs); - bool error; if (static_branch_unlikely(&enable_evmcs)) return evmcs_load(phys_addr); - asm volatile (__ex("vmptrld %1") CC_SET(na) - : CC_OUT(na) (error) : "m"(phys_addr)); - if (unlikely(error)) - printk(KERN_ERR "kvm: vmptrld %p/%llx failed\n", - vmcs, phys_addr); + vmx_asm1(vmptrld, "m"(phys_addr), vmcs, phys_addr); } static inline void __invvpid(unsigned long ext, u16 vpid, gva_t gva) @@ -213,11 +240,8 @@ static inline void __invvpid(unsigned long ext, u16 vpid, gva_t gva) u64 rsvd : 48; u64 gva; } operand = { vpid, 0, gva }; - bool error; - asm volatile (__ex("invvpid %2, %1") CC_SET(na) - : CC_OUT(na) (error) : "r"(ext), "m"(operand)); - BUG_ON(error); + vmx_asm2(invvpid, "r"(ext), "m"(operand), ext, vpid, gva); } static inline void __invept(unsigned long ext, u64 eptp, gpa_t gpa) @@ -225,11 +249,8 @@ static inline void __invept(unsigned long ext, u64 eptp, gpa_t gpa) struct { u64 eptp, gpa; } operand = {eptp, gpa}; - bool error; - asm volatile (__ex("invept %2, %1") CC_SET(na) - : CC_OUT(na) (error) : "r"(ext), "m"(operand)); - BUG_ON(error); + vmx_asm2(invept, "r"(ext), "m"(operand), ext, eptp, gpa); } static inline bool vpid_sync_vcpu_addr(int vpid, gva_t addr) diff --git a/arch/x86/kvm/vmx/pmu_intel.c b/arch/x86/kvm/vmx/pmu_intel.c index 4dea0e0e7e39..fd21cdb10b79 100644 --- a/arch/x86/kvm/vmx/pmu_intel.c +++ b/arch/x86/kvm/vmx/pmu_intel.c @@ -15,6 +15,7 @@ #include "x86.h" #include "cpuid.h" #include "lapic.h" +#include "nested.h" #include "pmu.h" static struct kvm_event_hw_type_mapping intel_arch_events[] = { @@ -46,6 +47,7 @@ static void reprogram_fixed_counters(struct kvm_pmu *pmu, u64 data) if (old_ctrl == new_ctrl) continue; + __set_bit(INTEL_PMC_IDX_FIXED + i, pmu->pmc_in_use); reprogram_fixed_counter(pmc, new_ctrl, i); } @@ -84,10 +86,14 @@ static unsigned intel_find_arch_event(struct kvm_pmu *pmu, static unsigned intel_find_fixed_event(int idx) { - if (idx >= ARRAY_SIZE(fixed_pmc_events)) + u32 event; + size_t size = ARRAY_SIZE(fixed_pmc_events); + + if (idx >= size) return PERF_COUNT_HW_MAX; - return intel_arch_events[fixed_pmc_events[idx]].event_type; + event = fixed_pmc_events[array_index_nospec(idx, size)]; + return intel_arch_events[event].event_type; } /* check if a PMC is enabled by comparing it with globl_ctrl bits. */ @@ -111,7 +117,7 @@ static struct kvm_pmc *intel_pmc_idx_to_pmc(struct kvm_pmu *pmu, int pmc_idx) } /* returns 0 if idx's corresponding MSR exists; otherwise returns 1. */ -static int intel_is_valid_msr_idx(struct kvm_vcpu *vcpu, unsigned idx) +static int intel_is_valid_rdpmc_ecx(struct kvm_vcpu *vcpu, unsigned int idx) { struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); bool fixed = idx & (1u << 30); @@ -122,22 +128,26 @@ static int intel_is_valid_msr_idx(struct kvm_vcpu *vcpu, unsigned idx) (fixed && idx >= pmu->nr_arch_fixed_counters); } -static struct kvm_pmc *intel_msr_idx_to_pmc(struct kvm_vcpu *vcpu, - unsigned idx, u64 *mask) +static struct kvm_pmc *intel_rdpmc_ecx_to_pmc(struct kvm_vcpu *vcpu, + unsigned int idx, u64 *mask) { struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); bool fixed = idx & (1u << 30); struct kvm_pmc *counters; + unsigned int num_counters; idx &= ~(3u << 30); - if (!fixed && idx >= pmu->nr_arch_gp_counters) - return NULL; - if (fixed && idx >= pmu->nr_arch_fixed_counters) + if (fixed) { + counters = pmu->fixed_counters; + num_counters = pmu->nr_arch_fixed_counters; + } else { + counters = pmu->gp_counters; + num_counters = pmu->nr_arch_gp_counters; + } + if (idx >= num_counters) return NULL; - counters = fixed ? pmu->fixed_counters : pmu->gp_counters; *mask &= pmu->counter_bitmask[fixed ? KVM_PMC_FIXED : KVM_PMC_GP]; - - return &counters[idx]; + return &counters[array_index_nospec(idx, num_counters)]; } static bool intel_is_valid_msr(struct kvm_vcpu *vcpu, u32 msr) @@ -162,6 +172,18 @@ static bool intel_is_valid_msr(struct kvm_vcpu *vcpu, u32 msr) return ret; } +static struct kvm_pmc *intel_msr_idx_to_pmc(struct kvm_vcpu *vcpu, u32 msr) +{ + struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); + struct kvm_pmc *pmc; + + pmc = get_fixed_pmc(pmu, msr); + pmc = pmc ? pmc : get_gp_pmc(pmu, msr, MSR_P6_EVNTSEL0); + pmc = pmc ? pmc : get_gp_pmc(pmu, msr, MSR_IA32_PERFCTR0); + + return pmc; +} + static int intel_pmu_get_msr(struct kvm_vcpu *vcpu, u32 msr, u64 *data) { struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); @@ -223,7 +245,7 @@ static int intel_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) case MSR_CORE_PERF_GLOBAL_CTRL: if (pmu->global_ctrl == data) return 0; - if (!(data & pmu->global_ctrl_mask)) { + if (kvm_valid_perf_global_ctrl(pmu, data)) { global_ctrl_changed(pmu, data); return 0; } @@ -238,13 +260,12 @@ static int intel_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) break; default: if ((pmc = get_gp_pmc(pmu, msr, MSR_IA32_PERFCTR0))) { - if (msr_info->host_initiated) - pmc->counter = data; - else - pmc->counter = (s32)data; + if (!msr_info->host_initiated) + data = (s64)(s32)data; + pmc->counter += data - pmc_read_counter(pmc); return 0; } else if ((pmc = get_fixed_pmc(pmu, msr))) { - pmc->counter = data; + pmc->counter += data - pmc_read_counter(pmc); return 0; } else if ((pmc = get_gp_pmc(pmu, msr, MSR_P6_EVNTSEL0))) { if (data == pmc->eventsel) @@ -262,6 +283,7 @@ static int intel_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) static void intel_pmu_refresh(struct kvm_vcpu *vcpu) { struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); + struct x86_pmu_capability x86_pmu; struct kvm_cpuid_entry2 *entry; union cpuid10_eax eax; union cpuid10_edx edx; @@ -283,8 +305,10 @@ static void intel_pmu_refresh(struct kvm_vcpu *vcpu) if (!pmu->version) return; + perf_get_x86_pmu_capability(&x86_pmu); + pmu->nr_arch_gp_counters = min_t(int, eax.split.num_counters, - INTEL_PMC_MAX_GENERIC); + x86_pmu.num_counters_gp); pmu->counter_bitmask[KVM_PMC_GP] = ((u64)1 << eax.split.bit_width) - 1; pmu->available_event_types = ~entry->ebx & ((1ull << eax.split.mask_length) - 1); @@ -294,7 +318,7 @@ static void intel_pmu_refresh(struct kvm_vcpu *vcpu) } else { pmu->nr_arch_fixed_counters = min_t(int, edx.split.num_counters_fixed, - INTEL_PMC_MAX_FIXED); + x86_pmu.num_counters_fixed); pmu->counter_bitmask[KVM_PMC_FIXED] = ((u64)1 << edx.split.bit_width_fixed) - 1; } @@ -314,6 +338,13 @@ static void intel_pmu_refresh(struct kvm_vcpu *vcpu) (boot_cpu_has(X86_FEATURE_HLE) || boot_cpu_has(X86_FEATURE_RTM)) && (entry->ebx & (X86_FEATURE_HLE|X86_FEATURE_RTM))) pmu->reserved_bits ^= HSW_IN_TX|HSW_IN_TX_CHECKPOINTED; + + bitmap_set(pmu->all_valid_pmc_idx, + 0, pmu->nr_arch_gp_counters); + bitmap_set(pmu->all_valid_pmc_idx, + INTEL_PMC_MAX_GENERIC, pmu->nr_arch_fixed_counters); + + nested_vmx_pmu_entry_exit_ctls_update(vcpu); } static void intel_pmu_init(struct kvm_vcpu *vcpu) @@ -325,12 +356,14 @@ static void intel_pmu_init(struct kvm_vcpu *vcpu) pmu->gp_counters[i].type = KVM_PMC_GP; pmu->gp_counters[i].vcpu = vcpu; pmu->gp_counters[i].idx = i; + pmu->gp_counters[i].current_config = 0; } for (i = 0; i < INTEL_PMC_MAX_FIXED; i++) { pmu->fixed_counters[i].type = KVM_PMC_FIXED; pmu->fixed_counters[i].vcpu = vcpu; pmu->fixed_counters[i].idx = i + INTEL_PMC_IDX_FIXED; + pmu->fixed_counters[i].current_config = 0; } } @@ -363,8 +396,9 @@ struct kvm_pmu_ops intel_pmu_ops = { .find_fixed_event = intel_find_fixed_event, .pmc_is_enabled = intel_pmc_is_enabled, .pmc_idx_to_pmc = intel_pmc_idx_to_pmc, + .rdpmc_ecx_to_pmc = intel_rdpmc_ecx_to_pmc, .msr_idx_to_pmc = intel_msr_idx_to_pmc, - .is_valid_msr_idx = intel_is_valid_msr_idx, + .is_valid_rdpmc_ecx = intel_is_valid_rdpmc_ecx, .is_valid_msr = intel_is_valid_msr, .get_msr = intel_pmu_get_msr, .set_msr = intel_pmu_set_msr, diff --git a/arch/x86/kvm/vmx/vmcs_shadow_fields.h b/arch/x86/kvm/vmx/vmcs_shadow_fields.h index eb1ecd16fd22..cad128d1657b 100644 --- a/arch/x86/kvm/vmx/vmcs_shadow_fields.h +++ b/arch/x86/kvm/vmx/vmcs_shadow_fields.h @@ -23,12 +23,12 @@ BUILD_BUG_ON(1) * * When adding or removing fields here, note that shadowed * fields must always be synced by prepare_vmcs02, not just - * prepare_vmcs02_full. + * prepare_vmcs02_rare. */ /* * Keeping the fields ordered by size is an attempt at improving - * branch prediction in vmcs_read_any and vmcs_write_any. + * branch prediction in vmcs12_read_any and vmcs12_write_any. */ /* 16-bits */ diff --git a/arch/x86/kvm/vmx/vmenter.S b/arch/x86/kvm/vmx/vmenter.S index 4010d519eb8c..81ada2ce99e7 100644 --- a/arch/x86/kvm/vmx/vmenter.S +++ b/arch/x86/kvm/vmx/vmenter.S @@ -43,7 +43,7 @@ * they VM-Fail, whereas a successful VM-Enter + VM-Exit will jump * to vmx_vmexit. */ -ENTRY(vmx_vmenter) +SYM_FUNC_START(vmx_vmenter) /* EFLAGS.ZF is set if VMCS.LAUNCHED == 0 */ je 2f @@ -65,7 +65,7 @@ ENTRY(vmx_vmenter) _ASM_EXTABLE(1b, 5b) _ASM_EXTABLE(2b, 5b) -ENDPROC(vmx_vmenter) +SYM_FUNC_END(vmx_vmenter) /** * vmx_vmexit - Handle a VMX VM-Exit @@ -77,7 +77,7 @@ ENDPROC(vmx_vmenter) * here after hardware loads the host's state, i.e. this is the destination * referred to by VMCS.HOST_RIP. */ -ENTRY(vmx_vmexit) +SYM_FUNC_START(vmx_vmexit) #ifdef CONFIG_RETPOLINE ALTERNATIVE "jmp .Lvmexit_skip_rsb", "", X86_FEATURE_RETPOLINE /* Preserve guest's RAX, it's used to stuff the RSB. */ @@ -90,18 +90,18 @@ ENTRY(vmx_vmexit) .Lvmexit_skip_rsb: #endif ret -ENDPROC(vmx_vmexit) +SYM_FUNC_END(vmx_vmexit) /** * __vmx_vcpu_run - Run a vCPU via a transition to VMX guest mode - * @vmx: struct vcpu_vmx * + * @vmx: struct vcpu_vmx * (forwarded to vmx_update_host_rsp) * @regs: unsigned long * (to guest registers) * @launched: %true if the VMCS has been launched * * Returns: * 0 on VM-Exit, 1 on VM-Fail */ -ENTRY(__vmx_vcpu_run) +SYM_FUNC_START(__vmx_vcpu_run) push %_ASM_BP mov %_ASM_SP, %_ASM_BP #ifdef CONFIG_X86_64 @@ -151,7 +151,7 @@ ENTRY(__vmx_vcpu_run) mov VCPU_R14(%_ASM_AX), %r14 mov VCPU_R15(%_ASM_AX), %r15 #endif - /* Load guest RAX. This kills the vmx_vcpu pointer! */ + /* Load guest RAX. This kills the @regs pointer! */ mov VCPU_RAX(%_ASM_AX), %_ASM_AX /* Enter guest mode */ @@ -233,4 +233,4 @@ ENTRY(__vmx_vcpu_run) /* VM-Fail. Out-of-line to avoid a taken Jcc after VM-Exit. */ 2: mov $1, %eax jmp 1b -ENDPROC(__vmx_vcpu_run) +SYM_FUNC_END(__vmx_vcpu_run) diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index 42ed3faa6af8..3be25ecae145 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -106,8 +106,6 @@ module_param(enable_apicv, bool, S_IRUGO); static bool __read_mostly nested = 1; module_param(nested, bool, S_IRUGO); -static u64 __read_mostly host_xss; - bool __read_mostly enable_pml = 1; module_param_named(pml, enable_pml, bool, S_IRUGO); @@ -209,6 +207,11 @@ static int vmx_setup_l1d_flush(enum vmx_l1d_flush_state l1tf) struct page *page; unsigned int i; + if (!boot_cpu_has_bug(X86_BUG_L1TF)) { + l1tf_vmx_mitigation = VMENTER_L1D_FLUSH_NOT_REQUIRED; + return 0; + } + if (!enable_ept) { l1tf_vmx_mitigation = VMENTER_L1D_FLUSH_EPT_DISABLED; return 0; @@ -343,6 +346,48 @@ static __always_inline void vmx_disable_intercept_for_msr(unsigned long *msr_bit void vmx_vmexit(void); +#define vmx_insn_failed(fmt...) \ +do { \ + WARN_ONCE(1, fmt); \ + pr_warn_ratelimited(fmt); \ +} while (0) + +asmlinkage void vmread_error(unsigned long field, bool fault) +{ + if (fault) + kvm_spurious_fault(); + else + vmx_insn_failed("kvm: vmread failed: field=%lx\n", field); +} + +noinline void vmwrite_error(unsigned long field, unsigned long value) +{ + vmx_insn_failed("kvm: vmwrite failed: field=%lx val=%lx err=%d\n", + field, value, vmcs_read32(VM_INSTRUCTION_ERROR)); +} + +noinline void vmclear_error(struct vmcs *vmcs, u64 phys_addr) +{ + vmx_insn_failed("kvm: vmclear failed: %p/%llx\n", vmcs, phys_addr); +} + +noinline void vmptrld_error(struct vmcs *vmcs, u64 phys_addr) +{ + vmx_insn_failed("kvm: vmptrld failed: %p/%llx\n", vmcs, phys_addr); +} + +noinline void invvpid_error(unsigned long ext, u16 vpid, gva_t gva) +{ + vmx_insn_failed("kvm: invvpid failed: ext=0x%lx vpid=%u gva=0x%lx\n", + ext, vpid, gva); +} + +noinline void invept_error(unsigned long ext, u64 eptp, gpa_t gpa) +{ + vmx_insn_failed("kvm: invept failed: ext=0x%lx eptp=%llx gpa=0x%llx\n", + ext, eptp, gpa); +} + static DEFINE_PER_CPU(struct vmcs *, vmxarea); DEFINE_PER_CPU(struct vmcs *, current_vmcs); /* @@ -403,6 +448,7 @@ const u32 vmx_msr_index[] = { MSR_SYSCALL_MASK, MSR_LSTAR, MSR_CSTAR, #endif MSR_EFER, MSR_TSC_AUX, MSR_STAR, + MSR_IA32_TSX_CTRL, }; #if IS_ENABLED(CONFIG_HYPERV) @@ -486,6 +532,31 @@ static int hv_remote_flush_tlb(struct kvm *kvm) return hv_remote_flush_tlb_with_range(kvm, NULL); } +static int hv_enable_direct_tlbflush(struct kvm_vcpu *vcpu) +{ + struct hv_enlightened_vmcs *evmcs; + struct hv_partition_assist_pg **p_hv_pa_pg = + &vcpu->kvm->arch.hyperv.hv_pa_pg; + /* + * Synthetic VM-Exit is not enabled in current code and so All + * evmcs in singe VM shares same assist page. + */ + if (!*p_hv_pa_pg) + *p_hv_pa_pg = kzalloc(PAGE_SIZE, GFP_KERNEL); + + if (!*p_hv_pa_pg) + return -ENOMEM; + + evmcs = (struct hv_enlightened_vmcs *)to_vmx(vcpu)->loaded_vmcs->vmcs; + + evmcs->partition_assist_page = + __pa(*p_hv_pa_pg); + evmcs->hv_vm_id = (unsigned long)vcpu->kvm; + evmcs->hv_enlightenments_control.nested_flush_hypercall = 1; + + return 0; +} + #endif /* IS_ENABLED(CONFIG_HYPERV) */ /* @@ -566,6 +637,23 @@ struct shared_msr_entry *find_msr_entry(struct vcpu_vmx *vmx, u32 msr) return NULL; } +static int vmx_set_guest_msr(struct vcpu_vmx *vmx, struct shared_msr_entry *msr, u64 data) +{ + int ret = 0; + + u64 old_msr_data = msr->data; + msr->data = data; + if (msr - vmx->guest_msrs < vmx->save_nmsrs) { + preempt_disable(); + ret = kvm_set_shared_msr(msr->index, msr->data, + msr->mask); + preempt_enable(); + if (ret) + msr->data = old_msr_data; + } + return ret; +} + void loaded_vmcs_init(struct loaded_vmcs *loaded_vmcs) { vmcs_clear(loaded_vmcs->vmcs); @@ -654,8 +742,8 @@ static bool vmx_segment_cache_test_set(struct vcpu_vmx *vmx, unsigned seg, bool ret; u32 mask = 1 << (seg * SEG_FIELD_NR + field); - if (!(vmx->vcpu.arch.regs_avail & (1 << VCPU_EXREG_SEGMENTS))) { - vmx->vcpu.arch.regs_avail |= (1 << VCPU_EXREG_SEGMENTS); + if (!kvm_register_is_available(&vmx->vcpu, VCPU_EXREG_SEGMENTS)) { + kvm_register_mark_available(&vmx->vcpu, VCPU_EXREG_SEGMENTS); vmx->segment_cache.bitmask = 0; } ret = vmx->segment_cache.bitmask & mask; @@ -763,7 +851,7 @@ static void clear_atomic_switch_msr_special(struct vcpu_vmx *vmx, vm_exit_controls_clearbit(vmx, exit); } -static int find_msr(struct vmx_msrs *m, unsigned int msr) +int vmx_find_msr_index(struct vmx_msrs *m, u32 msr) { unsigned int i; @@ -797,7 +885,7 @@ static void clear_atomic_switch_msr(struct vcpu_vmx *vmx, unsigned msr) } break; } - i = find_msr(&m->guest, msr); + i = vmx_find_msr_index(&m->guest, msr); if (i < 0) goto skip_guest; --m->guest.nr; @@ -805,7 +893,7 @@ static void clear_atomic_switch_msr(struct vcpu_vmx *vmx, unsigned msr) vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, m->guest.nr); skip_guest: - i = find_msr(&m->host, msr); + i = vmx_find_msr_index(&m->host, msr); if (i < 0) return; @@ -864,12 +952,12 @@ static void add_atomic_switch_msr(struct vcpu_vmx *vmx, unsigned msr, wrmsrl(MSR_IA32_PEBS_ENABLE, 0); } - i = find_msr(&m->guest, msr); + i = vmx_find_msr_index(&m->guest, msr); if (!entry_only) - j = find_msr(&m->host, msr); + j = vmx_find_msr_index(&m->host, msr); - if ((i < 0 && m->guest.nr == NR_AUTOLOAD_MSRS) || - (j < 0 && m->host.nr == NR_AUTOLOAD_MSRS)) { + if ((i < 0 && m->guest.nr == NR_LOADSTORE_MSRS) || + (j < 0 && m->host.nr == NR_LOADSTORE_MSRS)) { printk_once(KERN_WARNING "Not enough msr switch entries. " "Can't add msr %x\n", msr); return; @@ -897,17 +985,9 @@ static bool update_transition_efer(struct vcpu_vmx *vmx, int efer_offset) u64 guest_efer = vmx->vcpu.arch.efer; u64 ignore_bits = 0; - if (!enable_ept) { - /* - * NX is needed to handle CR0.WP=1, CR4.SMEP=1. Testing - * host CPUID is more efficient than testing guest CPUID - * or CR4. Host SMEP is anyway a requirement for guest SMEP. - */ - if (boot_cpu_has(X86_FEATURE_SMEP)) - guest_efer |= EFER_NX; - else if (!(guest_efer & EFER_NX)) - ignore_bits |= EFER_NX; - } + /* Shadow paging assumes NX to be available. */ + if (!enable_ept) + guest_efer |= EFER_NX; /* * LMA and LME handled by hardware; SCE meaningless outside long mode. @@ -977,6 +1057,12 @@ static unsigned long segment_base(u16 selector) } #endif +static inline bool pt_can_write_msr(struct vcpu_vmx *vmx) +{ + return (pt_mode == PT_MODE_HOST_GUEST) && + !(vmx->pt_desc.guest.ctl & RTIT_CTL_TRACEEN); +} + static inline void pt_load_msr(struct pt_ctx *ctx, u32 addr_range) { u32 i; @@ -1204,6 +1290,18 @@ static void vmx_vcpu_pi_load(struct kvm_vcpu *vcpu, int cpu) if (!pi_test_sn(pi_desc) && vcpu->cpu == cpu) return; + /* + * If the 'nv' field is POSTED_INTR_WAKEUP_VECTOR, do not change + * PI.NDST: pi_post_block is the one expected to change PID.NDST and the + * wakeup handler expects the vCPU to be on the blocked_vcpu_list that + * matches PI.NDST. Otherwise, a vcpu may not be able to be woken up + * correctly. + */ + if (pi_desc->nv == POSTED_INTR_WAKEUP_VECTOR || vcpu->cpu == cpu) { + pi_clear_sn(pi_desc); + goto after_clear_sn; + } + /* The full case. */ do { old.control = new.control = pi_desc->control; @@ -1219,6 +1317,8 @@ static void vmx_vcpu_pi_load(struct kvm_vcpu *vcpu, int cpu) } while (cmpxchg64(&pi_desc->control, old.control, new.control) != old.control); +after_clear_sn: + /* * Clear SN before reading the bitmap. The VT-d firmware * writes the bitmap and reads SN atomically (5.2.3 in the @@ -1227,7 +1327,7 @@ static void vmx_vcpu_pi_load(struct kvm_vcpu *vcpu, int cpu) */ smp_mb__after_atomic(); - if (!bitmap_empty((unsigned long *)pi_desc->pir, NR_VECTORS)) + if (!pi_is_pir_empty(pi_desc)) pi_set_on(pi_desc); } @@ -1274,14 +1374,6 @@ void vmx_vcpu_load_vmcs(struct kvm_vcpu *vcpu, int cpu) (unsigned long)&get_cpu_entry_area(cpu)->tss.x86_tss); vmcs_writel(HOST_GDTR_BASE, (unsigned long)gdt); /* 22.2.4 */ - /* - * VM exits change the host TR limit to 0x67 after a VM - * exit. This is okay, since 0x67 covers everything except - * the IO bitmap and have have code to handle the IO bitmap - * being lost after a VM exit. - */ - BUILD_BUG_ON(IO_BITMAP_OFFSET - 1 != 0x67); - rdmsrl(MSR_IA32_SYSENTER_ESP, sysenter_esp); vmcs_writel(HOST_IA32_SYSENTER_ESP, sysenter_esp); /* 22.2.3 */ @@ -1336,39 +1428,46 @@ static bool emulation_required(struct kvm_vcpu *vcpu) return emulate_invalid_guest_state && !guest_state_valid(vcpu); } -static void vmx_decache_cr0_guest_bits(struct kvm_vcpu *vcpu); - unsigned long vmx_get_rflags(struct kvm_vcpu *vcpu) { + struct vcpu_vmx *vmx = to_vmx(vcpu); unsigned long rflags, save_rflags; - if (!test_bit(VCPU_EXREG_RFLAGS, (ulong *)&vcpu->arch.regs_avail)) { - __set_bit(VCPU_EXREG_RFLAGS, (ulong *)&vcpu->arch.regs_avail); + if (!kvm_register_is_available(vcpu, VCPU_EXREG_RFLAGS)) { + kvm_register_mark_available(vcpu, VCPU_EXREG_RFLAGS); rflags = vmcs_readl(GUEST_RFLAGS); - if (to_vmx(vcpu)->rmode.vm86_active) { + if (vmx->rmode.vm86_active) { rflags &= RMODE_GUEST_OWNED_EFLAGS_BITS; - save_rflags = to_vmx(vcpu)->rmode.save_rflags; + save_rflags = vmx->rmode.save_rflags; rflags |= save_rflags & ~RMODE_GUEST_OWNED_EFLAGS_BITS; } - to_vmx(vcpu)->rflags = rflags; + vmx->rflags = rflags; } - return to_vmx(vcpu)->rflags; + return vmx->rflags; } void vmx_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags) { - unsigned long old_rflags = vmx_get_rflags(vcpu); + struct vcpu_vmx *vmx = to_vmx(vcpu); + unsigned long old_rflags; - __set_bit(VCPU_EXREG_RFLAGS, (ulong *)&vcpu->arch.regs_avail); - to_vmx(vcpu)->rflags = rflags; - if (to_vmx(vcpu)->rmode.vm86_active) { - to_vmx(vcpu)->rmode.save_rflags = rflags; + if (enable_unrestricted_guest) { + kvm_register_mark_available(vcpu, VCPU_EXREG_RFLAGS); + vmx->rflags = rflags; + vmcs_writel(GUEST_RFLAGS, rflags); + return; + } + + old_rflags = vmx_get_rflags(vcpu); + vmx->rflags = rflags; + if (vmx->rmode.vm86_active) { + vmx->rmode.save_rflags = rflags; rflags |= X86_EFLAGS_IOPL | X86_EFLAGS_VM; } vmcs_writel(GUEST_RFLAGS, rflags); - if ((old_rflags ^ to_vmx(vcpu)->rflags) & X86_EFLAGS_VM) - to_vmx(vcpu)->emulation_required = emulation_required(vcpu); + if ((old_rflags ^ vmx->rflags) & X86_EFLAGS_VM) + vmx->emulation_required = emulation_required(vcpu); } u32 vmx_get_interrupt_shadow(struct kvm_vcpu *vcpu) @@ -1472,17 +1571,32 @@ static int vmx_rtit_ctl_check(struct kvm_vcpu *vcpu, u64 data) return 0; } - -static void skip_emulated_instruction(struct kvm_vcpu *vcpu) +static int skip_emulated_instruction(struct kvm_vcpu *vcpu) { unsigned long rip; - rip = kvm_rip_read(vcpu); - rip += vmcs_read32(VM_EXIT_INSTRUCTION_LEN); - kvm_rip_write(vcpu, rip); + /* + * Using VMCS.VM_EXIT_INSTRUCTION_LEN on EPT misconfig depends on + * undefined behavior: Intel's SDM doesn't mandate the VMCS field be + * set when EPT misconfig occurs. In practice, real hardware updates + * VM_EXIT_INSTRUCTION_LEN on EPT misconfig, but other hypervisors + * (namely Hyper-V) don't set it due to it being undefined behavior, + * i.e. we end up advancing IP with some random value. + */ + if (!static_cpu_has(X86_FEATURE_HYPERVISOR) || + to_vmx(vcpu)->exit_reason != EXIT_REASON_EPT_MISCONFIG) { + rip = kvm_rip_read(vcpu); + rip += vmcs_read32(VM_EXIT_INSTRUCTION_LEN); + kvm_rip_write(vcpu, rip); + } else { + if (!kvm_emulate_instruction(vcpu, EMULTYPE_SKIP)) + return 0; + } /* skipping an emulated instruction also counts */ vmx_set_interrupt_shadow(vcpu, 0); + + return 1; } static void vmx_clear_hlt(struct kvm_vcpu *vcpu) @@ -1517,8 +1631,7 @@ static void vmx_queue_exception(struct kvm_vcpu *vcpu) int inc_eip = 0; if (kvm_exception_is_soft(nr)) inc_eip = vcpu->arch.event_exit_inst_len; - if (kvm_inject_realmode_interrupt(vcpu, nr, inc_eip) != EMULATE_DONE) - kvm_make_request(KVM_REQ_TRIPLE_FAULT, vcpu); + kvm_inject_realmode_interrupt(vcpu, nr, inc_eip); return; } @@ -1591,6 +1704,9 @@ static void setup_msrs(struct vcpu_vmx *vmx) index = __find_msr_index(vmx, MSR_TSC_AUX); if (index >= 0 && guest_cpuid_has(&vmx->vcpu, X86_FEATURE_RDTSCP)) move_msr_up(vmx, index, save_nmsrs++); + index = __find_msr_index(vmx, MSR_IA32_TSX_CTRL); + if (index >= 0) + move_msr_up(vmx, index, save_nmsrs++); vmx->save_nmsrs = save_nmsrs; vmx->guest_msrs_ready = false; @@ -1604,7 +1720,7 @@ static u64 vmx_read_l1_tsc_offset(struct kvm_vcpu *vcpu) struct vmcs12 *vmcs12 = get_vmcs12(vcpu); if (is_guest_mode(vcpu) && - (vmcs12->cpu_based_vm_exec_control & CPU_BASED_USE_TSC_OFFSETING)) + (vmcs12->cpu_based_vm_exec_control & CPU_BASED_USE_TSC_OFFSETTING)) return vcpu->arch.tsc_offset - vmcs12->tsc_offset; return vcpu->arch.tsc_offset; @@ -1622,7 +1738,7 @@ static u64 vmx_write_l1_tsc_offset(struct kvm_vcpu *vcpu, u64 offset) * to the newly set TSC to get L2's TSC. */ if (is_guest_mode(vcpu) && - (vmcs12->cpu_based_vm_exec_control & CPU_BASED_USE_TSC_OFFSETING)) + (vmcs12->cpu_based_vm_exec_control & CPU_BASED_USE_TSC_OFFSETTING)) g_tsc_offset = vmcs12->tsc_offset; trace_kvm_write_tsc_offset(vcpu->vcpu_id, @@ -1661,8 +1777,6 @@ static int vmx_get_msr_feature(struct kvm_msr_entry *msr) default: return 1; } - - return 0; } /* @@ -1690,6 +1804,17 @@ static int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) #endif case MSR_EFER: return kvm_get_msr_common(vcpu, msr_info); + case MSR_IA32_TSX_CTRL: + if (!msr_info->host_initiated && + !(vcpu->arch.arch_capabilities & ARCH_CAP_TSX_CTRL_MSR)) + return 1; + goto find_shared_msr; + case MSR_IA32_UMWAIT_CONTROL: + if (!msr_info->host_initiated && !vmx_has_waitpkg(vmx)) + return 1; + + msr_info->data = vmx->msr_ia32_umwait_control; + break; case MSR_IA32_SPEC_CTRL: if (!msr_info->host_initiated && !guest_cpuid_has(vcpu, X86_FEATURE_SPEC_CTRL)) @@ -1716,25 +1841,29 @@ static int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) case MSR_IA32_MCG_EXT_CTL: if (!msr_info->host_initiated && !(vmx->msr_ia32_feature_control & - FEATURE_CONTROL_LMCE)) + FEAT_CTL_LMCE_ENABLED)) return 1; msr_info->data = vcpu->arch.mcg_ext_ctl; break; - case MSR_IA32_FEATURE_CONTROL: + case MSR_IA32_FEAT_CTL: msr_info->data = vmx->msr_ia32_feature_control; break; case MSR_IA32_VMX_BASIC ... MSR_IA32_VMX_VMFUNC: if (!nested_vmx_allowed(vcpu)) return 1; - return vmx_get_vmx_msr(&vmx->nested.msrs, msr_info->index, - &msr_info->data); - case MSR_IA32_XSS: - if (!vmx_xsaves_supported() || - (!msr_info->host_initiated && - !(guest_cpuid_has(vcpu, X86_FEATURE_XSAVE) && - guest_cpuid_has(vcpu, X86_FEATURE_XSAVES)))) + if (vmx_get_vmx_msr(&vmx->nested.msrs, msr_info->index, + &msr_info->data)) return 1; - msr_info->data = vcpu->arch.ia32_xss; + /* + * Enlightened VMCS v1 doesn't have certain fields, but buggy + * Hyper-V versions are still trying to use corresponding + * features when they are exposed. Filter out the essential + * minimum. + */ + if (!msr_info->host_initiated && + vmx->nested.enlightened_vmcs_enabled) + nested_evmcs_filter_control_msr(msr_info->index, + &msr_info->data); break; case MSR_IA32_RTIT_CTL: if (pt_mode != PT_MODE_HOST_GUEST) @@ -1786,8 +1915,9 @@ static int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) if (!msr_info->host_initiated && !guest_cpuid_has(vcpu, X86_FEATURE_RDTSCP)) return 1; - /* Else, falls through */ + goto find_shared_msr; default: + find_shared_msr: msr = find_msr_entry(vmx, msr_info->index); if (msr) { msr_info->data = msr->data; @@ -1800,7 +1930,7 @@ static int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) } /* - * Writes msr value into into the appropriate "register". + * Writes msr value into the appropriate "register". * Returns 0 on success, non-0 otherwise. * Assumes vcpu_load() was already called. */ @@ -1863,17 +1993,25 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) return 1; vmcs_write64(GUEST_BNDCFGS, data); break; + case MSR_IA32_UMWAIT_CONTROL: + if (!msr_info->host_initiated && !vmx_has_waitpkg(vmx)) + return 1; + + /* The reserved bit 1 and non-32 bit [63:32] should be zero */ + if (data & (BIT_ULL(1) | GENMASK_ULL(63, 32))) + return 1; + + vmx->msr_ia32_umwait_control = data; + break; case MSR_IA32_SPEC_CTRL: if (!msr_info->host_initiated && !guest_cpuid_has(vcpu, X86_FEATURE_SPEC_CTRL)) return 1; - /* The STIBP bit doesn't fault even if it's not advertised */ - if (data & ~(SPEC_CTRL_IBRS | SPEC_CTRL_STIBP | SPEC_CTRL_SSBD)) + if (data & ~kvm_spec_ctrl_valid_bits(vcpu)) return 1; vmx->spec_ctrl = data; - if (!data) break; @@ -1884,7 +2022,7 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) * * For nested: * The handling of the MSR bitmap for L2 guests is done in - * nested_vmx_merge_msr_bitmap. We should not touch the + * nested_vmx_prepare_msr_bitmap. We should not touch the * vmcs02.msr_bitmap here since it gets completely overwritten * in the merging. We update the vmcs01 here for L1 as well * since it will end up touching the MSR anyway now. @@ -1893,6 +2031,13 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) MSR_IA32_SPEC_CTRL, MSR_TYPE_RW); break; + case MSR_IA32_TSX_CTRL: + if (!msr_info->host_initiated && + !(vcpu->arch.arch_capabilities & ARCH_CAP_TSX_CTRL_MSR)) + return 1; + if (data & ~(TSX_CTRL_RTM_DISABLE | TSX_CTRL_CPUID_CLEAR)) + return 1; + goto find_shared_msr; case MSR_IA32_PRED_CMD: if (!msr_info->host_initiated && !guest_cpuid_has(vcpu, X86_FEATURE_SPEC_CTRL)) @@ -1900,7 +2045,8 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) if (data & ~PRED_CMD_IBPB) return 1; - + if (!boot_cpu_has(X86_FEATURE_SPEC_CTRL)) + return 1; if (!data) break; @@ -1913,7 +2059,7 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) * * For nested: * The handling of the MSR bitmap for L2 guests is done in - * nested_vmx_merge_msr_bitmap. We should not touch the + * nested_vmx_prepare_msr_bitmap. We should not touch the * vmcs02.msr_bitmap here since it gets completely overwritten * in the merging. */ @@ -1941,15 +2087,15 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) case MSR_IA32_MCG_EXT_CTL: if ((!msr_info->host_initiated && !(to_vmx(vcpu)->msr_ia32_feature_control & - FEATURE_CONTROL_LMCE)) || + FEAT_CTL_LMCE_ENABLED)) || (data & ~MCG_EXT_CTL_LMCE_EN)) return 1; vcpu->arch.mcg_ext_ctl = data; break; - case MSR_IA32_FEATURE_CONTROL: + case MSR_IA32_FEAT_CTL: if (!vmx_feature_control_msr_valid(vcpu, data) || (to_vmx(vcpu)->msr_ia32_feature_control & - FEATURE_CONTROL_LOCKED && !msr_info->host_initiated)) + FEAT_CTL_LOCKED && !msr_info->host_initiated)) return 1; vmx->msr_ia32_feature_control = data; if (msr_info->host_initiated && data == 0) @@ -1961,25 +2107,6 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) if (!nested_vmx_allowed(vcpu)) return 1; return vmx_set_vmx_msr(vcpu, msr_index, data); - case MSR_IA32_XSS: - if (!vmx_xsaves_supported() || - (!msr_info->host_initiated && - !(guest_cpuid_has(vcpu, X86_FEATURE_XSAVE) && - guest_cpuid_has(vcpu, X86_FEATURE_XSAVES)))) - return 1; - /* - * The only supported bit as of Skylake is bit 8, but - * it is not supported on KVM. - */ - if (data != 0) - return 1; - vcpu->arch.ia32_xss = data; - if (vcpu->arch.ia32_xss != host_xss) - add_atomic_switch_msr(vmx, MSR_IA32_XSS, - vcpu->arch.ia32_xss, host_xss, false); - else - clear_atomic_switch_msr(vmx, MSR_IA32_XSS); - break; case MSR_IA32_RTIT_CTL: if ((pt_mode != PT_MODE_HOST_GUEST) || vmx_rtit_ctl_check(vcpu, data) || @@ -1990,47 +2117,50 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) pt_update_intercept_for_msr(vmx); break; case MSR_IA32_RTIT_STATUS: - if ((pt_mode != PT_MODE_HOST_GUEST) || - (vmx->pt_desc.guest.ctl & RTIT_CTL_TRACEEN) || - (data & MSR_IA32_RTIT_STATUS_MASK)) + if (!pt_can_write_msr(vmx)) + return 1; + if (data & MSR_IA32_RTIT_STATUS_MASK) return 1; vmx->pt_desc.guest.status = data; break; case MSR_IA32_RTIT_CR3_MATCH: - if ((pt_mode != PT_MODE_HOST_GUEST) || - (vmx->pt_desc.guest.ctl & RTIT_CTL_TRACEEN) || - !intel_pt_validate_cap(vmx->pt_desc.caps, - PT_CAP_cr3_filtering)) + if (!pt_can_write_msr(vmx)) + return 1; + if (!intel_pt_validate_cap(vmx->pt_desc.caps, + PT_CAP_cr3_filtering)) return 1; vmx->pt_desc.guest.cr3_match = data; break; case MSR_IA32_RTIT_OUTPUT_BASE: - if ((pt_mode != PT_MODE_HOST_GUEST) || - (vmx->pt_desc.guest.ctl & RTIT_CTL_TRACEEN) || - (!intel_pt_validate_cap(vmx->pt_desc.caps, - PT_CAP_topa_output) && - !intel_pt_validate_cap(vmx->pt_desc.caps, - PT_CAP_single_range_output)) || - (data & MSR_IA32_RTIT_OUTPUT_BASE_MASK)) + if (!pt_can_write_msr(vmx)) + return 1; + if (!intel_pt_validate_cap(vmx->pt_desc.caps, + PT_CAP_topa_output) && + !intel_pt_validate_cap(vmx->pt_desc.caps, + PT_CAP_single_range_output)) + return 1; + if (data & MSR_IA32_RTIT_OUTPUT_BASE_MASK) return 1; vmx->pt_desc.guest.output_base = data; break; case MSR_IA32_RTIT_OUTPUT_MASK: - if ((pt_mode != PT_MODE_HOST_GUEST) || - (vmx->pt_desc.guest.ctl & RTIT_CTL_TRACEEN) || - (!intel_pt_validate_cap(vmx->pt_desc.caps, - PT_CAP_topa_output) && - !intel_pt_validate_cap(vmx->pt_desc.caps, - PT_CAP_single_range_output))) + if (!pt_can_write_msr(vmx)) + return 1; + if (!intel_pt_validate_cap(vmx->pt_desc.caps, + PT_CAP_topa_output) && + !intel_pt_validate_cap(vmx->pt_desc.caps, + PT_CAP_single_range_output)) return 1; vmx->pt_desc.guest.output_mask = data; break; case MSR_IA32_RTIT_ADDR0_A ... MSR_IA32_RTIT_ADDR3_B: + if (!pt_can_write_msr(vmx)) + return 1; index = msr_info->index - MSR_IA32_RTIT_ADDR0_A; - if ((pt_mode != PT_MODE_HOST_GUEST) || - (vmx->pt_desc.guest.ctl & RTIT_CTL_TRACEEN) || - (index >= 2 * intel_pt_validate_cap(vmx->pt_desc.caps, - PT_CAP_num_address_ranges))) + if (index >= 2 * intel_pt_validate_cap(vmx->pt_desc.caps, + PT_CAP_num_address_ranges)) + return 1; + if (is_noncanonical_address(data, vcpu)) return 1; if (index % 2) vmx->pt_desc.guest.addr_b[index / 2] = data; @@ -2044,23 +2174,15 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) /* Check reserved bit, higher 32 bits should be zero */ if ((data >> 32) != 0) return 1; - /* Else, falls through */ + goto find_shared_msr; + default: + find_shared_msr: msr = find_msr_entry(vmx, msr_index); - if (msr) { - u64 old_msr_data = msr->data; - msr->data = data; - if (msr - vmx->guest_msrs < vmx->save_nmsrs) { - preempt_disable(); - ret = kvm_set_shared_msr(msr->index, msr->data, - msr->mask); - preempt_enable(); - if (ret) - msr->data = old_msr_data; - } - break; - } - ret = kvm_set_msr_common(vcpu, msr_info); + if (msr) + ret = vmx_set_guest_msr(vmx, msr, data); + else + ret = kvm_set_msr_common(vcpu, msr_info); } return ret; @@ -2068,7 +2190,8 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) static void vmx_cache_reg(struct kvm_vcpu *vcpu, enum kvm_reg reg) { - __set_bit(reg, (unsigned long *)&vcpu->arch.regs_avail); + kvm_register_mark_available(vcpu, reg); + switch (reg) { case VCPU_REGS_RSP: vcpu->arch.regs[VCPU_REGS_RSP] = vmcs_readl(GUEST_RSP); @@ -2080,7 +2203,12 @@ static void vmx_cache_reg(struct kvm_vcpu *vcpu, enum kvm_reg reg) if (enable_ept) ept_save_pdptrs(vcpu); break; + case VCPU_EXREG_CR3: + if (enable_unrestricted_guest || (enable_ept && is_paging(vcpu))) + vcpu->arch.cr3 = vmcs_readl(GUEST_CR3); + break; default: + WARN_ON_ONCE(1); break; } } @@ -2092,29 +2220,8 @@ static __init int cpu_has_kvm_support(void) static __init int vmx_disabled_by_bios(void) { - u64 msr; - - rdmsrl(MSR_IA32_FEATURE_CONTROL, msr); - if (msr & FEATURE_CONTROL_LOCKED) { - /* launched w/ TXT and VMX disabled */ - if (!(msr & FEATURE_CONTROL_VMXON_ENABLED_INSIDE_SMX) - && tboot_enabled()) - return 1; - /* launched w/o TXT and VMX only enabled w/ TXT */ - if (!(msr & FEATURE_CONTROL_VMXON_ENABLED_OUTSIDE_SMX) - && (msr & FEATURE_CONTROL_VMXON_ENABLED_INSIDE_SMX) - && !tboot_enabled()) { - printk(KERN_WARNING "kvm: disable TXT in the BIOS or " - "activate TXT before enabling KVM\n"); - return 1; - } - /* launched w/o TXT and VMX disabled */ - if (!(msr & FEATURE_CONTROL_VMXON_ENABLED_OUTSIDE_SMX) - && !tboot_enabled()) - return 1; - } - - return 0; + return !boot_cpu_has(X86_FEATURE_MSR_IA32_FEAT_CTL) || + !boot_cpu_has(X86_FEATURE_VMX); } static void kvm_cpu_vmxon(u64 addr) @@ -2129,7 +2236,6 @@ static int hardware_enable(void) { int cpu = raw_smp_processor_id(); u64 phys_addr = __pa(per_cpu(vmxarea, cpu)); - u64 old, test_bits; if (cr4_read_shadow() & X86_CR4_VMXE) return -EBUSY; @@ -2157,17 +2263,6 @@ static int hardware_enable(void) */ crash_enable_local_vmclear(cpu); - rdmsrl(MSR_IA32_FEATURE_CONTROL, old); - - test_bits = FEATURE_CONTROL_LOCKED; - test_bits |= FEATURE_CONTROL_VMXON_ENABLED_OUTSIDE_SMX; - if (tboot_enabled()) - test_bits |= FEATURE_CONTROL_VMXON_ENABLED_INSIDE_SMX; - - if ((old & test_bits) != test_bits) { - /* enable and lock */ - wrmsrl(MSR_IA32_FEATURE_CONTROL, old | test_bits); - } kvm_cpu_vmxon(phys_addr); if (enable_ept) ept_sync_global(); @@ -2243,7 +2338,7 @@ static __init int setup_vmcs_config(struct vmcs_config *vmcs_conf, CPU_BASED_CR3_STORE_EXITING | CPU_BASED_UNCOND_IO_EXITING | CPU_BASED_MOV_DR_EXITING | - CPU_BASED_USE_TSC_OFFSETING | + CPU_BASED_USE_TSC_OFFSETTING | CPU_BASED_MWAIT_EXITING | CPU_BASED_MONITOR_EXITING | CPU_BASED_INVLPG_EXITING | @@ -2280,6 +2375,7 @@ static __init int setup_vmcs_config(struct vmcs_config *vmcs_conf, SECONDARY_EXEC_RDRAND_EXITING | SECONDARY_EXEC_ENABLE_PML | SECONDARY_EXEC_TSC_SCALING | + SECONDARY_EXEC_ENABLE_USR_WAIT_PAUSE | SECONDARY_EXEC_PT_USE_GPA | SECONDARY_EXEC_PT_CONCEAL_VMX | SECONDARY_EXEC_ENABLE_VMFUNC | @@ -2577,8 +2673,6 @@ static void enter_pmode(struct kvm_vcpu *vcpu) vmx->rmode.vm86_active = 0; - vmx_segment_cache_clear(vmx); - vmx_set_segment(vcpu, &vmx->rmode.segs[VCPU_SREG_TR], VCPU_SREG_TR); flags = vmcs_readl(GUEST_RFLAGS); @@ -2750,13 +2844,6 @@ static void vmx_decache_cr0_guest_bits(struct kvm_vcpu *vcpu) vcpu->arch.cr0 |= vmcs_readl(GUEST_CR0) & cr0_guest_owned_bits; } -static void vmx_decache_cr3(struct kvm_vcpu *vcpu) -{ - if (enable_unrestricted_guest || (enable_ept && is_paging(vcpu))) - vcpu->arch.cr3 = vmcs_readl(GUEST_CR3); - __set_bit(VCPU_EXREG_CR3, (ulong *)&vcpu->arch.regs_avail); -} - static void vmx_decache_cr4_guest_bits(struct kvm_vcpu *vcpu) { ulong cr4_guest_owned_bits = vcpu->arch.cr4_guest_owned_bits; @@ -2769,8 +2856,7 @@ static void ept_load_pdptrs(struct kvm_vcpu *vcpu) { struct kvm_mmu *mmu = vcpu->arch.walk_mmu; - if (!test_bit(VCPU_EXREG_PDPTR, - (unsigned long *)&vcpu->arch.regs_dirty)) + if (!kvm_register_is_dirty(vcpu, VCPU_EXREG_PDPTR)) return; if (is_pae_paging(vcpu)) { @@ -2792,10 +2878,7 @@ void ept_save_pdptrs(struct kvm_vcpu *vcpu) mmu->pdptrs[3] = vmcs_read64(GUEST_PDPTR3); } - __set_bit(VCPU_EXREG_PDPTR, - (unsigned long *)&vcpu->arch.regs_avail); - __set_bit(VCPU_EXREG_PDPTR, - (unsigned long *)&vcpu->arch.regs_dirty); + kvm_register_mark_dirty(vcpu, VCPU_EXREG_PDPTR); } static void ept_update_paging_mode_cr0(unsigned long *hw_cr0, @@ -2804,8 +2887,8 @@ static void ept_update_paging_mode_cr0(unsigned long *hw_cr0, { struct vcpu_vmx *vmx = to_vmx(vcpu); - if (!test_bit(VCPU_EXREG_CR3, (ulong *)&vcpu->arch.regs_avail)) - vmx_decache_cr3(vcpu); + if (!kvm_register_is_available(vcpu, VCPU_EXREG_CR3)) + vmx_cache_reg(vcpu, VCPU_EXREG_CR3); if (!(cr0 & X86_CR0_PG)) { /* From paging/starting to nonpaging */ exec_controls_setbit(vmx, CPU_BASED_CR3_LOAD_EXITING | @@ -2864,6 +2947,9 @@ void vmx_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0) static int get_ept_level(struct kvm_vcpu *vcpu) { + /* Nested EPT currently only supports 4-level walks. */ + if (is_guest_mode(vcpu) && nested_cpu_has_ept(get_vmcs12(vcpu))) + return 4; if (cpu_has_vmx_ept_5levels() && (cpuid_maxphyaddr(vcpu) > 48)) return 5; return 4; @@ -2886,6 +2972,7 @@ u64 construct_eptp(struct kvm_vcpu *vcpu, unsigned long root_hpa) void vmx_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3) { struct kvm *kvm = vcpu->kvm; + bool update_guest_cr3 = true; unsigned long guest_cr3; u64 eptp; @@ -2902,15 +2989,20 @@ void vmx_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3) spin_unlock(&to_kvm_vmx(kvm)->ept_pointer_lock); } - if (enable_unrestricted_guest || is_paging(vcpu) || - is_guest_mode(vcpu)) - guest_cr3 = kvm_read_cr3(vcpu); - else + /* Loading vmcs02.GUEST_CR3 is handled by nested VM-Enter. */ + if (is_guest_mode(vcpu)) + update_guest_cr3 = false; + else if (!enable_unrestricted_guest && !is_paging(vcpu)) guest_cr3 = to_kvm_vmx(kvm)->ept_identity_map_addr; + else if (test_bit(VCPU_EXREG_CR3, (ulong *)&vcpu->arch.regs_avail)) + guest_cr3 = vcpu->arch.cr3; + else /* vmcs01.GUEST_CR3 is already up-to-date. */ + update_guest_cr3 = false; ept_load_pdptrs(vcpu); } - vmcs_writel(GUEST_CR3, guest_cr3); + if (update_guest_cr3) + vmcs_writel(GUEST_CR3, guest_cr3); } int vmx_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) @@ -3369,7 +3461,7 @@ out: static int init_rmode_identity_map(struct kvm *kvm) { struct kvm_vmx *kvm_vmx = to_kvm_vmx(kvm); - int i, idx, r = 0; + int i, r = 0; kvm_pfn_t identity_map_pfn; u32 tmp; @@ -3377,7 +3469,7 @@ static int init_rmode_identity_map(struct kvm *kvm) mutex_lock(&kvm->slots_lock); if (likely(kvm_vmx->ept_identity_pagetable_done)) - goto out2; + goto out; if (!kvm_vmx->ept_identity_map_addr) kvm_vmx->ept_identity_map_addr = VMX_EPT_IDENTITY_PAGETABLE_ADDR; @@ -3386,9 +3478,8 @@ static int init_rmode_identity_map(struct kvm *kvm) r = __x86_set_memory_region(kvm, IDENTITY_PAGETABLE_PRIVATE_MEMSLOT, kvm_vmx->ept_identity_map_addr, PAGE_SIZE); if (r < 0) - goto out2; + goto out; - idx = srcu_read_lock(&kvm->srcu); r = kvm_clear_guest_page(kvm, identity_map_pfn, 0, PAGE_SIZE); if (r < 0) goto out; @@ -3404,9 +3495,6 @@ static int init_rmode_identity_map(struct kvm *kvm) kvm_vmx->ept_identity_pagetable_done = true; out: - srcu_read_unlock(&kvm->srcu, idx); - -out2: mutex_unlock(&kvm->slots_lock); return r; } @@ -3644,11 +3732,6 @@ void pt_update_intercept_for_msr(struct vcpu_vmx *vmx) } } -static bool vmx_get_enable_apicv(struct kvm_vcpu *vcpu) -{ - return enable_apicv; -} - static bool vmx_guest_apic_has_interrupt(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); @@ -3934,9 +4017,12 @@ static void vmx_compute_secondary_exec_control(struct vcpu_vmx *vmx) if (vmx_xsaves_supported()) { /* Exposing XSAVES only when XSAVE is exposed */ bool xsaves_enabled = + boot_cpu_has(X86_FEATURE_XSAVE) && guest_cpuid_has(vcpu, X86_FEATURE_XSAVE) && guest_cpuid_has(vcpu, X86_FEATURE_XSAVES); + vcpu->arch.xsaves_enabled = xsaves_enabled; + if (!xsaves_enabled) exec_control &= ~SECONDARY_EXEC_XSAVES; @@ -4016,6 +4102,23 @@ static void vmx_compute_secondary_exec_control(struct vcpu_vmx *vmx) } } + if (vmx_waitpkg_supported()) { + bool waitpkg_enabled = + guest_cpuid_has(vcpu, X86_FEATURE_WAITPKG); + + if (!waitpkg_enabled) + exec_control &= ~SECONDARY_EXEC_ENABLE_USR_WAIT_PAUSE; + + if (nested) { + if (waitpkg_enabled) + vmx->nested.msrs.secondary_ctls_high |= + SECONDARY_EXEC_ENABLE_USR_WAIT_PAUSE; + else + vmx->nested.msrs.secondary_ctls_high &= + ~SECONDARY_EXEC_ENABLE_USR_WAIT_PAUSE; + } + } + vmx->secondary_exec_control = exec_control; } @@ -4026,20 +4129,19 @@ static void ept_set_mmio_spte_mask(void) * of an EPT paging-structure entry is 110b (write/execute). */ kvm_mmu_set_mmio_spte_mask(VMX_EPT_RWX_MASK, - VMX_EPT_MISCONFIG_WX_VALUE); + VMX_EPT_MISCONFIG_WX_VALUE, 0); } #define VMX_XSS_EXIT_BITMAP 0 /* - * Sets up the vmcs for emulated real mode. + * Noting that the initialization of Guest-state Area of VMCS is in + * vmx_vcpu_reset(). */ -static void vmx_vcpu_setup(struct vcpu_vmx *vmx) +static void init_vmcs(struct vcpu_vmx *vmx) { - int i; - if (nested) - nested_vmx_vcpu_setup(); + nested_vmx_set_vmcs_shadowing_bitmap(); if (cpu_has_vmx_msr_bitmap()) vmcs_write64(MSR_BITMAP, __pa(vmx->vmcs01.msr_bitmap)); @@ -4048,7 +4150,6 @@ static void vmx_vcpu_setup(struct vcpu_vmx *vmx) /* Control */ pin_controls_set(vmx, vmx_pin_based_exec_ctrl(vmx)); - vmx->hv_deadline_tsc = -1; exec_controls_set(vmx, vmx_exec_control(vmx)); @@ -4097,21 +4198,6 @@ static void vmx_vcpu_setup(struct vcpu_vmx *vmx) if (vmcs_config.vmentry_ctrl & VM_ENTRY_LOAD_IA32_PAT) vmcs_write64(GUEST_IA32_PAT, vmx->vcpu.arch.pat); - for (i = 0; i < ARRAY_SIZE(vmx_msr_index); ++i) { - u32 index = vmx_msr_index[i]; - u32 data_low, data_high; - int j = vmx->nmsrs; - - if (rdmsr_safe(index, &data_low, &data_high) < 0) - continue; - if (wrmsr_safe(index, data_low, data_high) < 0) - continue; - vmx->guest_msrs[j].index = i; - vmx->guest_msrs[j].data = 0; - vmx->guest_msrs[j].mask = -1ull; - ++vmx->nmsrs; - } - vm_exit_controls_set(vmx, vmx_vmexit_ctrl()); /* 22.2.1, 20.8.1 */ @@ -4122,6 +4208,9 @@ static void vmx_vcpu_setup(struct vcpu_vmx *vmx) set_cr4_guest_host_mask(vmx); + if (vmx->vpid != 0) + vmcs_write16(VIRTUAL_PROCESSOR_ID, vmx->vpid); + if (vmx_xsaves_supported()) vmcs_write64(XSS_EXIT_BITMAP, VMX_XSS_EXIT_BITMAP); @@ -4150,8 +4239,10 @@ static void vmx_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) vmx->rmode.vm86_active = 0; vmx->spec_ctrl = 0; - vcpu->arch.microcode_version = 0x100000000ULL; + vmx->msr_ia32_umwait_control = 0; + vmx->vcpu.arch.regs[VCPU_REGS_RDX] = get_rdx_init_val(); + vmx->hv_deadline_tsc = -1; kvm_set_cr8(vcpu, 0); if (!init_event) { @@ -4221,9 +4312,6 @@ static void vmx_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) kvm_make_request(KVM_REQ_APIC_PAGE_RELOAD, vcpu); - if (vmx->vpid != 0) - vmcs_write16(VIRTUAL_PROCESSOR_ID, vmx->vpid); - cr0 = X86_CR0_NW | X86_CR0_CD | X86_CR0_ET; vmx->vcpu.arch.cr0 = cr0; vmx_set_cr0(vcpu, cr0); /* enter rmode */ @@ -4239,7 +4327,7 @@ static void vmx_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) static void enable_irq_window(struct kvm_vcpu *vcpu) { - exec_controls_setbit(to_vmx(vcpu), CPU_BASED_VIRTUAL_INTR_PENDING); + exec_controls_setbit(to_vmx(vcpu), CPU_BASED_INTR_WINDOW_EXITING); } static void enable_nmi_window(struct kvm_vcpu *vcpu) @@ -4250,7 +4338,7 @@ static void enable_nmi_window(struct kvm_vcpu *vcpu) return; } - exec_controls_setbit(to_vmx(vcpu), CPU_BASED_VIRTUAL_NMI_PENDING); + exec_controls_setbit(to_vmx(vcpu), CPU_BASED_NMI_WINDOW_EXITING); } static void vmx_inject_irq(struct kvm_vcpu *vcpu) @@ -4266,8 +4354,7 @@ static void vmx_inject_irq(struct kvm_vcpu *vcpu) int inc_eip = 0; if (vcpu->arch.interrupt.soft) inc_eip = vcpu->arch.event_exit_inst_len; - if (kvm_inject_realmode_interrupt(vcpu, irq, inc_eip) != EMULATE_DONE) - kvm_make_request(KVM_REQ_TRIPLE_FAULT, vcpu); + kvm_inject_realmode_interrupt(vcpu, irq, inc_eip); return; } intr = irq | INTR_INFO_VALID_MASK; @@ -4303,8 +4390,7 @@ static void vmx_inject_nmi(struct kvm_vcpu *vcpu) vmx->loaded_vmcs->nmi_known_unmasked = false; if (vmx->rmode.vm86_active) { - if (kvm_inject_realmode_interrupt(vcpu, NMI_VECTOR, 0) != EMULATE_DONE) - kvm_make_request(KVM_REQ_TRIPLE_FAULT, vcpu); + kvm_inject_realmode_interrupt(vcpu, NMI_VECTOR, 0); return; } @@ -4377,8 +4463,11 @@ static int vmx_set_tss_addr(struct kvm *kvm, unsigned int addr) if (enable_unrestricted_guest) return 0; - ret = x86_set_memory_region(kvm, TSS_PRIVATE_MEMSLOT, addr, - PAGE_SIZE * 3); + mutex_lock(&kvm->slots_lock); + ret = __x86_set_memory_region(kvm, TSS_PRIVATE_MEMSLOT, addr, + PAGE_SIZE * 3); + mutex_unlock(&kvm->slots_lock); + if (ret) return ret; to_kvm_vmx(kvm)->tss_addr = addr; @@ -4431,7 +4520,7 @@ static int handle_rmode_exception(struct kvm_vcpu *vcpu, * Cause the #SS fault with 0 error code in VM86 mode. */ if (((vec == GP_VECTOR) || (vec == SS_VECTOR)) && err_code == 0) { - if (kvm_emulate_instruction(vcpu, 0) == EMULATE_DONE) { + if (kvm_emulate_instruction(vcpu, 0)) { if (vcpu->arch.halt_request) { vcpu->arch.halt_request = 0; return kvm_vcpu_halt(vcpu); @@ -4482,7 +4571,6 @@ static int handle_exception_nmi(struct kvm_vcpu *vcpu) u32 intr_info, ex_no, error_code; unsigned long cr2, rip, dr6; u32 vect_info; - enum emulation_result er; vect_info = vmx->idt_vectoring_info; intr_info = vmx->exit_intr_info; @@ -4499,13 +4587,17 @@ static int handle_exception_nmi(struct kvm_vcpu *vcpu) if (!vmx->rmode.vm86_active && is_gp_fault(intr_info)) { WARN_ON_ONCE(!enable_vmware_backdoor); - er = kvm_emulate_instruction(vcpu, - EMULTYPE_VMWARE | EMULTYPE_NO_UD_ON_FAIL); - if (er == EMULATE_USER_EXIT) - return 0; - else if (er != EMULATE_DONE) + + /* + * VMware backdoor emulation on #GP interception only handles + * IN{S}, OUT{S}, and RDPMC, none of which generate a non-zero + * error code on #GP. + */ + if (error_code) { kvm_queue_exception_e(vcpu, GP_VECTOR, error_code); - return 1; + return 1; + } + return kvm_emulate_instruction(vcpu, EMULTYPE_VMWARE_GP); } /* @@ -4547,7 +4639,7 @@ static int handle_exception_nmi(struct kvm_vcpu *vcpu) vcpu->arch.dr6 &= ~DR_TRAP_BITS; vcpu->arch.dr6 |= dr6 | DR6_RTM; if (is_icebp(intr_info)) - skip_emulated_instruction(vcpu); + WARN_ON(!skip_emulated_instruction(vcpu)); kvm_queue_exception(vcpu, DB_VECTOR); return 1; @@ -4577,7 +4669,7 @@ static int handle_exception_nmi(struct kvm_vcpu *vcpu) return 0; } -static int handle_external_interrupt(struct kvm_vcpu *vcpu) +static __always_inline int handle_external_interrupt(struct kvm_vcpu *vcpu) { ++vcpu->stat.irq_exits; return 1; @@ -4602,7 +4694,7 @@ static int handle_io(struct kvm_vcpu *vcpu) ++vcpu->stat.io_exits; if (string) - return kvm_emulate_instruction(vcpu, 0) == EMULATE_DONE; + return kvm_emulate_instruction(vcpu, 0); port = exit_qualification >> 16; size = (exit_qualification & 7) + 1; @@ -4676,7 +4768,7 @@ static int handle_set_cr4(struct kvm_vcpu *vcpu, unsigned long val) static int handle_desc(struct kvm_vcpu *vcpu) { WARN_ON(!(vcpu->arch.cr4 & X86_CR4_UMIP)); - return kvm_emulate_instruction(vcpu, 0) == EMULATE_DONE; + return kvm_emulate_instruction(vcpu, 0); } static int handle_cr(struct kvm_vcpu *vcpu) @@ -4849,50 +4941,6 @@ static void vmx_set_dr7(struct kvm_vcpu *vcpu, unsigned long val) vmcs_writel(GUEST_DR7, val); } -static int handle_cpuid(struct kvm_vcpu *vcpu) -{ - return kvm_emulate_cpuid(vcpu); -} - -static int handle_rdmsr(struct kvm_vcpu *vcpu) -{ - u32 ecx = kvm_rcx_read(vcpu); - struct msr_data msr_info; - - msr_info.index = ecx; - msr_info.host_initiated = false; - if (vmx_get_msr(vcpu, &msr_info)) { - trace_kvm_msr_read_ex(ecx); - kvm_inject_gp(vcpu, 0); - return 1; - } - - trace_kvm_msr_read(ecx, msr_info.data); - - kvm_rax_write(vcpu, msr_info.data & -1u); - kvm_rdx_write(vcpu, (msr_info.data >> 32) & -1u); - return kvm_skip_emulated_instruction(vcpu); -} - -static int handle_wrmsr(struct kvm_vcpu *vcpu) -{ - struct msr_data msr; - u32 ecx = kvm_rcx_read(vcpu); - u64 data = kvm_read_edx_eax(vcpu); - - msr.data = data; - msr.index = ecx; - msr.host_initiated = false; - if (kvm_set_msr(vcpu, &msr) != 0) { - trace_kvm_msr_write_ex(ecx, data); - kvm_inject_gp(vcpu, 0); - return 1; - } - - trace_kvm_msr_write(ecx, data); - return kvm_skip_emulated_instruction(vcpu); -} - static int handle_tpr_below_threshold(struct kvm_vcpu *vcpu) { kvm_apic_update_ppr(vcpu); @@ -4901,7 +4949,7 @@ static int handle_tpr_below_threshold(struct kvm_vcpu *vcpu) static int handle_interrupt_window(struct kvm_vcpu *vcpu) { - exec_controls_clearbit(to_vmx(vcpu), CPU_BASED_VIRTUAL_INTR_PENDING); + exec_controls_clearbit(to_vmx(vcpu), CPU_BASED_INTR_WINDOW_EXITING); kvm_make_request(KVM_REQ_EVENT, vcpu); @@ -4909,11 +4957,6 @@ static int handle_interrupt_window(struct kvm_vcpu *vcpu) return 1; } -static int handle_halt(struct kvm_vcpu *vcpu) -{ - return kvm_emulate_halt(vcpu); -} - static int handle_vmcall(struct kvm_vcpu *vcpu) { return kvm_emulate_hypercall(vcpu); @@ -4921,7 +4964,7 @@ static int handle_vmcall(struct kvm_vcpu *vcpu) static int handle_invd(struct kvm_vcpu *vcpu) { - return kvm_emulate_instruction(vcpu, 0) == EMULATE_DONE; + return kvm_emulate_instruction(vcpu, 0); } static int handle_invlpg(struct kvm_vcpu *vcpu) @@ -4955,20 +4998,6 @@ static int handle_xsetbv(struct kvm_vcpu *vcpu) return 1; } -static int handle_xsaves(struct kvm_vcpu *vcpu) -{ - kvm_skip_emulated_instruction(vcpu); - WARN(1, "this should never happen\n"); - return 1; -} - -static int handle_xrstors(struct kvm_vcpu *vcpu) -{ - kvm_skip_emulated_instruction(vcpu); - WARN(1, "this should never happen\n"); - return 1; -} - static int handle_apic_access(struct kvm_vcpu *vcpu) { if (likely(fasteoi)) { @@ -4988,7 +5017,7 @@ static int handle_apic_access(struct kvm_vcpu *vcpu) return kvm_skip_emulated_instruction(vcpu); } } - return kvm_emulate_instruction(vcpu, 0) == EMULATE_DONE; + return kvm_emulate_instruction(vcpu, 0); } static int handle_apic_eoi_induced(struct kvm_vcpu *vcpu) @@ -5057,23 +5086,15 @@ static int handle_task_switch(struct kvm_vcpu *vcpu) if (!idt_v || (type != INTR_TYPE_HARD_EXCEPTION && type != INTR_TYPE_EXT_INTR && type != INTR_TYPE_NMI_INTR)) - skip_emulated_instruction(vcpu); - - if (kvm_task_switch(vcpu, tss_selector, - type == INTR_TYPE_SOFT_INTR ? idt_index : -1, reason, - has_error_code, error_code) == EMULATE_FAIL) { - vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR; - vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_EMULATION; - vcpu->run->internal.ndata = 0; - return 0; - } + WARN_ON(!skip_emulated_instruction(vcpu)); /* * TODO: What about debug traps on tss switch? * Are we supposed to inject them and update dr6? */ - - return 1; + return kvm_task_switch(vcpu, tss_selector, + type == INTR_TYPE_SOFT_INTR ? idt_index : -1, + reason, has_error_code, error_code); } static int handle_ept_violation(struct kvm_vcpu *vcpu) @@ -5132,21 +5153,7 @@ static int handle_ept_misconfig(struct kvm_vcpu *vcpu) if (!is_guest_mode(vcpu) && !kvm_io_bus_write(vcpu, KVM_FAST_MMIO_BUS, gpa, 0, NULL)) { trace_kvm_fast_mmio(gpa); - /* - * Doing kvm_skip_emulated_instruction() depends on undefined - * behavior: Intel's manual doesn't mandate - * VM_EXIT_INSTRUCTION_LEN to be set in VMCS when EPT MISCONFIG - * occurs and while on real hardware it was observed to be set, - * other hypervisors (namely Hyper-V) don't set it, we end up - * advancing IP with some random value. Disable fast mmio when - * running nested and keep it for real hardware in hope that - * VM_EXIT_INSTRUCTION_LEN will always be set correctly. - */ - if (!static_cpu_has(X86_FEATURE_HYPERVISOR)) - return kvm_skip_emulated_instruction(vcpu); - else - return kvm_emulate_instruction(vcpu, EMULTYPE_SKIP) == - EMULATE_DONE; + return kvm_skip_emulated_instruction(vcpu); } return kvm_mmu_page_fault(vcpu, gpa, PFERR_RSVD_MASK, NULL, 0); @@ -5155,7 +5162,7 @@ static int handle_ept_misconfig(struct kvm_vcpu *vcpu) static int handle_nmi_window(struct kvm_vcpu *vcpu) { WARN_ON_ONCE(!enable_vnmi); - exec_controls_clearbit(to_vmx(vcpu), CPU_BASED_VIRTUAL_NMI_PENDING); + exec_controls_clearbit(to_vmx(vcpu), CPU_BASED_NMI_WINDOW_EXITING); ++vcpu->stat.nmi_window_exits; kvm_make_request(KVM_REQ_EVENT, vcpu); @@ -5165,8 +5172,6 @@ static int handle_nmi_window(struct kvm_vcpu *vcpu) static int handle_invalid_guest_state(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); - enum emulation_result err = EMULATE_DONE; - int ret = 1; bool intr_window_requested; unsigned count = 130; @@ -5178,7 +5183,7 @@ static int handle_invalid_guest_state(struct kvm_vcpu *vcpu) WARN_ON_ONCE(vmx->emulation_required && vmx->nested.nested_run_pending); intr_window_requested = exec_controls_get(vmx) & - CPU_BASED_VIRTUAL_INTR_PENDING; + CPU_BASED_INTR_WINDOW_EXITING; while (vmx->emulation_required && count-- != 0) { if (intr_window_requested && vmx_interrupt_allowed(vcpu)) @@ -5187,71 +5192,67 @@ static int handle_invalid_guest_state(struct kvm_vcpu *vcpu) if (kvm_test_request(KVM_REQ_EVENT, vcpu)) return 1; - err = kvm_emulate_instruction(vcpu, 0); - - if (err == EMULATE_USER_EXIT) { - ++vcpu->stat.mmio_exits; - ret = 0; - goto out; - } - - if (err != EMULATE_DONE) - goto emulation_error; + if (!kvm_emulate_instruction(vcpu, 0)) + return 0; if (vmx->emulation_required && !vmx->rmode.vm86_active && - vcpu->arch.exception.pending) - goto emulation_error; + vcpu->arch.exception.pending) { + vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR; + vcpu->run->internal.suberror = + KVM_INTERNAL_ERROR_EMULATION; + vcpu->run->internal.ndata = 0; + return 0; + } if (vcpu->arch.halt_request) { vcpu->arch.halt_request = 0; - ret = kvm_vcpu_halt(vcpu); - goto out; + return kvm_vcpu_halt(vcpu); } + /* + * Note, return 1 and not 0, vcpu_run() is responsible for + * morphing the pending signal into the proper return code. + */ if (signal_pending(current)) - goto out; + return 1; + if (need_resched()) schedule(); } -out: - return ret; - -emulation_error: - vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR; - vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_EMULATION; - vcpu->run->internal.ndata = 0; - return 0; + return 1; } static void grow_ple_window(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); - int old = vmx->ple_window; + unsigned int old = vmx->ple_window; vmx->ple_window = __grow_ple_window(old, ple_window, ple_window_grow, ple_window_max); - if (vmx->ple_window != old) + if (vmx->ple_window != old) { vmx->ple_window_dirty = true; - - trace_kvm_ple_window_grow(vcpu->vcpu_id, vmx->ple_window, old); + trace_kvm_ple_window_update(vcpu->vcpu_id, + vmx->ple_window, old); + } } static void shrink_ple_window(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); - int old = vmx->ple_window; + unsigned int old = vmx->ple_window; vmx->ple_window = __shrink_ple_window(old, ple_window, ple_window_shrink, ple_window); - if (vmx->ple_window != old) + if (vmx->ple_window != old) { vmx->ple_window_dirty = true; - - trace_kvm_ple_window_shrink(vcpu->vcpu_id, vmx->ple_window, old); + trace_kvm_ple_window_update(vcpu->vcpu_id, + vmx->ple_window, old); + } } /* @@ -5503,11 +5504,11 @@ static int (*kvm_vmx_exit_handlers[])(struct kvm_vcpu *vcpu) = { [EXIT_REASON_IO_INSTRUCTION] = handle_io, [EXIT_REASON_CR_ACCESS] = handle_cr, [EXIT_REASON_DR_ACCESS] = handle_dr, - [EXIT_REASON_CPUID] = handle_cpuid, - [EXIT_REASON_MSR_READ] = handle_rdmsr, - [EXIT_REASON_MSR_WRITE] = handle_wrmsr, - [EXIT_REASON_PENDING_INTERRUPT] = handle_interrupt_window, - [EXIT_REASON_HLT] = handle_halt, + [EXIT_REASON_CPUID] = kvm_emulate_cpuid, + [EXIT_REASON_MSR_READ] = kvm_emulate_rdmsr, + [EXIT_REASON_MSR_WRITE] = kvm_emulate_wrmsr, + [EXIT_REASON_INTERRUPT_WINDOW] = handle_interrupt_window, + [EXIT_REASON_HLT] = kvm_emulate_halt, [EXIT_REASON_INVD] = handle_invd, [EXIT_REASON_INVLPG] = handle_invlpg, [EXIT_REASON_RDPMC] = handle_rdpmc, @@ -5541,8 +5542,6 @@ static int (*kvm_vmx_exit_handlers[])(struct kvm_vcpu *vcpu) = { [EXIT_REASON_INVVPID] = handle_vmx_instruction, [EXIT_REASON_RDRAND] = handle_invalid_op, [EXIT_REASON_RDSEED] = handle_invalid_op, - [EXIT_REASON_XSAVES] = handle_xsaves, - [EXIT_REASON_XRSTORS] = handle_xrstors, [EXIT_REASON_PML_FULL] = handle_pml_full, [EXIT_REASON_INVPCID] = handle_invpcid, [EXIT_REASON_VMFUNC] = handle_vmx_instruction, @@ -5795,7 +5794,8 @@ void dump_vmcs(void) * The guest has exited. See if we can fix it or if we need userspace * assistance. */ -static int vmx_handle_exit(struct kvm_vcpu *vcpu) +static int vmx_handle_exit(struct kvm_vcpu *vcpu, + enum exit_fastpath_completion exit_fastpath) { struct vcpu_vmx *vmx = to_vmx(vcpu); u32 exit_reason = vmx->exit_reason; @@ -5881,15 +5881,44 @@ static int vmx_handle_exit(struct kvm_vcpu *vcpu) } } - if (exit_reason < kvm_vmx_max_exit_handlers - && kvm_vmx_exit_handlers[exit_reason]) - return kvm_vmx_exit_handlers[exit_reason](vcpu); - else { - vcpu_unimpl(vcpu, "vmx: unexpected exit reason 0x%x\n", - exit_reason); - kvm_queue_exception(vcpu, UD_VECTOR); + if (exit_fastpath == EXIT_FASTPATH_SKIP_EMUL_INS) { + kvm_skip_emulated_instruction(vcpu); return 1; } + + if (exit_reason >= kvm_vmx_max_exit_handlers) + goto unexpected_vmexit; +#ifdef CONFIG_RETPOLINE + if (exit_reason == EXIT_REASON_MSR_WRITE) + return kvm_emulate_wrmsr(vcpu); + else if (exit_reason == EXIT_REASON_PREEMPTION_TIMER) + return handle_preemption_timer(vcpu); + else if (exit_reason == EXIT_REASON_INTERRUPT_WINDOW) + return handle_interrupt_window(vcpu); + else if (exit_reason == EXIT_REASON_EXTERNAL_INTERRUPT) + return handle_external_interrupt(vcpu); + else if (exit_reason == EXIT_REASON_HLT) + return kvm_emulate_halt(vcpu); + else if (exit_reason == EXIT_REASON_EPT_MISCONFIG) + return handle_ept_misconfig(vcpu); +#endif + + exit_reason = array_index_nospec(exit_reason, + kvm_vmx_max_exit_handlers); + if (!kvm_vmx_exit_handlers[exit_reason]) + goto unexpected_vmexit; + + return kvm_vmx_exit_handlers[exit_reason](vcpu); + +unexpected_vmexit: + vcpu_unimpl(vcpu, "vmx: unexpected exit reason 0x%x\n", exit_reason); + dump_vmcs(); + vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR; + vcpu->run->internal.suberror = + KVM_INTERNAL_ERROR_UNEXPECTED_EXIT_REASON; + vcpu->run->internal.ndata = 1; + vcpu->run->internal.data[0] = exit_reason; + return 0; } /* @@ -5965,17 +5994,17 @@ static void vmx_l1d_flush(struct kvm_vcpu *vcpu) static void update_cr8_intercept(struct kvm_vcpu *vcpu, int tpr, int irr) { struct vmcs12 *vmcs12 = get_vmcs12(vcpu); + int tpr_threshold; if (is_guest_mode(vcpu) && nested_cpu_has(vmcs12, CPU_BASED_TPR_SHADOW)) return; - if (irr == -1 || tpr < irr) { - vmcs_write32(TPR_THRESHOLD, 0); - return; - } - - vmcs_write32(TPR_THRESHOLD, irr); + tpr_threshold = (irr == -1 || tpr < irr) ? 0 : irr; + if (is_guest_mode(vcpu)) + to_vmx(vcpu)->nested.l1_tpr_threshold = tpr_threshold; + else + vmcs_write32(TPR_THRESHOLD, tpr_threshold); } void vmx_set_virtual_apic_mode(struct kvm_vcpu *vcpu) @@ -6089,7 +6118,7 @@ static int vmx_sync_pir_to_irr(struct kvm_vcpu *vcpu) if (pi_test_on(&vmx->pi_desc)) { pi_clear_on(&vmx->pi_desc); /* - * IOMMU can write to PIR.ON, so the barrier matters even on UP. + * IOMMU can write to PID.ON, so the barrier matters even on UP. * But on x86 this is just a compiler barrier anyway. */ smp_mb__after_atomic(); @@ -6119,7 +6148,10 @@ static int vmx_sync_pir_to_irr(struct kvm_vcpu *vcpu) static bool vmx_dy_apicv_has_pending_interrupt(struct kvm_vcpu *vcpu) { - return pi_test_on(vcpu_to_pi_desc(vcpu)); + struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu); + + return pi_test_on(pi_desc) || + (pi_test_sn(pi_desc) && !pi_is_pir_empty(pi_desc)); } static void vmx_load_eoi_exitmap(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap) @@ -6207,7 +6239,8 @@ static void handle_external_interrupt_irqoff(struct kvm_vcpu *vcpu) } STACK_FRAME_NON_STANDARD(handle_external_interrupt_irqoff); -static void vmx_handle_exit_irqoff(struct kvm_vcpu *vcpu) +static void vmx_handle_exit_irqoff(struct kvm_vcpu *vcpu, + enum exit_fastpath_completion *exit_fastpath) { struct vcpu_vmx *vmx = to_vmx(vcpu); @@ -6215,6 +6248,9 @@ static void vmx_handle_exit_irqoff(struct kvm_vcpu *vcpu) handle_external_interrupt_irqoff(vcpu); else if (vmx->exit_reason == EXIT_REASON_EXCEPTION_NMI) handle_exception_nmi_irqoff(vmx); + else if (!is_guest_mode(vcpu) && + vmx->exit_reason == EXIT_REASON_MSR_WRITE) + *exit_fastpath = handle_fastpath_set_msr_irqoff(vcpu); } static bool vmx_has_emulated_msr(int index) @@ -6373,6 +6409,23 @@ static void atomic_switch_perf_msrs(struct vcpu_vmx *vmx) msrs[i].host, false); } +static void atomic_switch_umwait_control_msr(struct vcpu_vmx *vmx) +{ + u32 host_umwait_control; + + if (!vmx_has_waitpkg(vmx)) + return; + + host_umwait_control = get_umwait_control_msr(); + + if (vmx->msr_ia32_umwait_control != host_umwait_control) + add_atomic_switch_msr(vmx, MSR_IA32_UMWAIT_CONTROL, + vmx->msr_ia32_umwait_control, + host_umwait_control, false); + else + clear_atomic_switch_msr(vmx, MSR_IA32_UMWAIT_CONTROL); +} + static void vmx_update_hv_timer(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); @@ -6432,9 +6485,9 @@ static void vmx_vcpu_run(struct kvm_vcpu *vcpu) if (vmx->nested.need_vmcs12_to_shadow_sync) nested_sync_vmcs12_to_shadow(vcpu); - if (test_bit(VCPU_REGS_RSP, (unsigned long *)&vcpu->arch.regs_dirty)) + if (kvm_register_is_dirty(vcpu, VCPU_REGS_RSP)) vmcs_writel(GUEST_RSP, vcpu->arch.regs[VCPU_REGS_RSP]); - if (test_bit(VCPU_REGS_RIP, (unsigned long *)&vcpu->arch.regs_dirty)) + if (kvm_register_is_dirty(vcpu, VCPU_REGS_RIP)) vmcs_writel(GUEST_RIP, vcpu->arch.regs[VCPU_REGS_RIP]); cr3 = __get_current_cr3_fast(); @@ -6457,7 +6510,7 @@ static void vmx_vcpu_run(struct kvm_vcpu *vcpu) if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP) vmx_set_interrupt_shadow(vcpu, 0); - kvm_load_guest_xcr0(vcpu); + kvm_load_guest_xsave_state(vcpu); if (static_cpu_has(X86_FEATURE_PKU) && kvm_read_cr4_bits(vcpu, X86_CR4_PKE) && @@ -6467,6 +6520,7 @@ static void vmx_vcpu_run(struct kvm_vcpu *vcpu) pt_guest_enter(vmx); atomic_switch_perf_msrs(vmx); + atomic_switch_umwait_control_msr(vmx); if (enable_preemption_timer) vmx_update_hv_timer(vcpu); @@ -6522,6 +6576,9 @@ static void vmx_vcpu_run(struct kvm_vcpu *vcpu) current_evmcs->hv_clean_fields |= HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL; + if (static_branch_unlikely(&enable_evmcs)) + current_evmcs->hv_vp_id = vcpu->arch.hyperv.vp_index; + /* MSR_IA32_DEBUGCTLMSR is zeroed on vmexit. Restore it if needed */ if (vmx->host_debugctlmsr) update_debugctlmsr(vmx->host_debugctlmsr); @@ -6560,7 +6617,7 @@ static void vmx_vcpu_run(struct kvm_vcpu *vcpu) __write_pkru(vmx->host_pkru); } - kvm_put_guest_xcr0(vcpu); + kvm_load_host_xsave_state(vcpu); vmx->nested.nested_run_pending = 0; vmx->idt_vectoring_info = 0; @@ -6589,6 +6646,7 @@ static struct kvm *vmx_vm_alloc(void) static void vmx_vm_free(struct kvm *kvm) { + kfree(kvm->arch.hyperv.hv_pa_pg); vfree(to_kvm_vmx(kvm)); } @@ -6601,70 +6659,66 @@ static void vmx_free_vcpu(struct kvm_vcpu *vcpu) free_vpid(vmx->vpid); nested_vmx_free_vcpu(vcpu); free_loaded_vmcs(vmx->loaded_vmcs); - kfree(vmx->guest_msrs); - kvm_vcpu_uninit(vcpu); - kmem_cache_free(x86_fpu_cache, vmx->vcpu.arch.user_fpu); - kmem_cache_free(x86_fpu_cache, vmx->vcpu.arch.guest_fpu); - kmem_cache_free(kvm_vcpu_cache, vmx); } -static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id) +static int vmx_create_vcpu(struct kvm_vcpu *vcpu) { - int err; struct vcpu_vmx *vmx; unsigned long *msr_bitmap; - int cpu; - - vmx = kmem_cache_zalloc(kvm_vcpu_cache, GFP_KERNEL_ACCOUNT); - if (!vmx) - return ERR_PTR(-ENOMEM); + int i, cpu, err; - vmx->vcpu.arch.user_fpu = kmem_cache_zalloc(x86_fpu_cache, - GFP_KERNEL_ACCOUNT); - if (!vmx->vcpu.arch.user_fpu) { - printk(KERN_ERR "kvm: failed to allocate kvm userspace's fpu\n"); - err = -ENOMEM; - goto free_partial_vcpu; - } + BUILD_BUG_ON(offsetof(struct vcpu_vmx, vcpu) != 0); + vmx = to_vmx(vcpu); - vmx->vcpu.arch.guest_fpu = kmem_cache_zalloc(x86_fpu_cache, - GFP_KERNEL_ACCOUNT); - if (!vmx->vcpu.arch.guest_fpu) { - printk(KERN_ERR "kvm: failed to allocate vcpu's fpu\n"); - err = -ENOMEM; - goto free_user_fpu; - } + err = -ENOMEM; vmx->vpid = allocate_vpid(); - err = kvm_vcpu_init(&vmx->vcpu, kvm, id); - if (err) - goto free_vcpu; - - err = -ENOMEM; - /* * If PML is turned on, failure on enabling PML just results in failure * of creating the vcpu, therefore we can simplify PML logic (by * avoiding dealing with cases, such as enabling PML partially on vcpus - * for the guest, etc. + * for the guest), etc. */ if (enable_pml) { vmx->pml_pg = alloc_page(GFP_KERNEL_ACCOUNT | __GFP_ZERO); if (!vmx->pml_pg) - goto uninit_vcpu; + goto free_vpid; } - vmx->guest_msrs = kmalloc(PAGE_SIZE, GFP_KERNEL_ACCOUNT); - BUILD_BUG_ON(ARRAY_SIZE(vmx_msr_index) * sizeof(vmx->guest_msrs[0]) - > PAGE_SIZE); + BUILD_BUG_ON(ARRAY_SIZE(vmx_msr_index) != NR_SHARED_MSRS); - if (!vmx->guest_msrs) - goto free_pml; + for (i = 0; i < ARRAY_SIZE(vmx_msr_index); ++i) { + u32 index = vmx_msr_index[i]; + u32 data_low, data_high; + int j = vmx->nmsrs; + + if (rdmsr_safe(index, &data_low, &data_high) < 0) + continue; + if (wrmsr_safe(index, data_low, data_high) < 0) + continue; + + vmx->guest_msrs[j].index = i; + vmx->guest_msrs[j].data = 0; + switch (index) { + case MSR_IA32_TSX_CTRL: + /* + * No need to pass TSX_CTRL_CPUID_CLEAR through, so + * let's avoid changing CPUID bits under the host + * kernel's feet. + */ + vmx->guest_msrs[j].mask = ~(u64)TSX_CTRL_CPUID_CLEAR; + break; + default: + vmx->guest_msrs[j].mask = -1ull; + break; + } + ++vmx->nmsrs; + } err = alloc_loaded_vmcs(&vmx->vmcs01); if (err < 0) - goto free_msrs; + goto free_pml; msr_bitmap = vmx->vmcs01.msr_bitmap; vmx_disable_intercept_for_msr(msr_bitmap, MSR_IA32_TSC, MSR_TYPE_R); @@ -6674,7 +6728,7 @@ static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id) vmx_disable_intercept_for_msr(msr_bitmap, MSR_IA32_SYSENTER_CS, MSR_TYPE_RW); vmx_disable_intercept_for_msr(msr_bitmap, MSR_IA32_SYSENTER_ESP, MSR_TYPE_RW); vmx_disable_intercept_for_msr(msr_bitmap, MSR_IA32_SYSENTER_EIP, MSR_TYPE_RW); - if (kvm_cstate_in_guest(kvm)) { + if (kvm_cstate_in_guest(vcpu->kvm)) { vmx_disable_intercept_for_msr(msr_bitmap, MSR_CORE_C1_RES, MSR_TYPE_R); vmx_disable_intercept_for_msr(msr_bitmap, MSR_CORE_C3_RESIDENCY, MSR_TYPE_R); vmx_disable_intercept_for_msr(msr_bitmap, MSR_CORE_C6_RESIDENCY, MSR_TYPE_R); @@ -6684,19 +6738,19 @@ static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id) vmx->loaded_vmcs = &vmx->vmcs01; cpu = get_cpu(); - vmx_vcpu_load(&vmx->vcpu, cpu); - vmx->vcpu.cpu = cpu; - vmx_vcpu_setup(vmx); - vmx_vcpu_put(&vmx->vcpu); + vmx_vcpu_load(vcpu, cpu); + vcpu->cpu = cpu; + init_vmcs(vmx); + vmx_vcpu_put(vcpu); put_cpu(); - if (cpu_need_virtualize_apic_accesses(&vmx->vcpu)) { - err = alloc_apic_access_page(kvm); + if (cpu_need_virtualize_apic_accesses(vcpu)) { + err = alloc_apic_access_page(vcpu->kvm); if (err) goto free_vmcs; } if (enable_ept && !enable_unrestricted_guest) { - err = init_rmode_identity_map(kvm); + err = init_rmode_identity_map(vcpu->kvm); if (err) goto free_vmcs; } @@ -6704,14 +6758,15 @@ static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id) if (nested) nested_vmx_setup_ctls_msrs(&vmx->nested.msrs, vmx_capability.ept, - kvm_vcpu_apicv_active(&vmx->vcpu)); + kvm_vcpu_apicv_active(vcpu)); else memset(&vmx->nested.msrs, 0, sizeof(vmx->nested.msrs)); vmx->nested.posted_intr_nv = -1; vmx->nested.current_vmptr = -1ull; - vmx->msr_ia32_feature_control_valid_bits = FEATURE_CONTROL_LOCKED; + vcpu->arch.microcode_version = 0x100000000ULL; + vmx->msr_ia32_feature_control_valid_bits = FEAT_CTL_LOCKED; /* * Enforce invariant: pi_desc.nv is always either POSTED_INTR_VECTOR @@ -6722,24 +6777,15 @@ static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id) vmx->ept_pointer = INVALID_PAGE; - return &vmx->vcpu; + return 0; free_vmcs: free_loaded_vmcs(vmx->loaded_vmcs); -free_msrs: - kfree(vmx->guest_msrs); free_pml: vmx_destroy_pml_buffer(vmx); -uninit_vcpu: - kvm_vcpu_uninit(&vmx->vcpu); -free_vcpu: +free_vpid: free_vpid(vmx->vpid); - kmem_cache_free(x86_fpu_cache, vmx->vcpu.arch.guest_fpu); -free_user_fpu: - kmem_cache_free(x86_fpu_cache, vmx->vcpu.arch.user_fpu); -free_partial_vcpu: - kmem_cache_free(kvm_vcpu_cache, vmx); - return ERR_PTR(err); + return err; } #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" @@ -6775,6 +6821,7 @@ static int vmx_vm_init(struct kvm *kvm) break; } } + kvm_apicv_init(kvm, enable_apicv); return 0; } @@ -6783,6 +6830,12 @@ static int __init vmx_check_processor_compat(void) struct vmcs_config vmcs_conf; struct vmx_capability vmx_cap; + if (!this_cpu_has(X86_FEATURE_MSR_IA32_FEAT_CTL) || + !this_cpu_has(X86_FEATURE_VMX)) { + pr_err("kvm: VMX is disabled on CPU %d\n", smp_processor_id()); + return -EIO; + } + if (setup_vmcs_config(&vmcs_conf, &vmx_cap) < 0) return -EIO; if (nested) @@ -6885,27 +6938,28 @@ static void nested_vmx_cr_fixed1_bits_update(struct kvm_vcpu *vcpu) } while (0) entry = kvm_find_cpuid_entry(vcpu, 0x1, 0); - cr4_fixed1_update(X86_CR4_VME, edx, bit(X86_FEATURE_VME)); - cr4_fixed1_update(X86_CR4_PVI, edx, bit(X86_FEATURE_VME)); - cr4_fixed1_update(X86_CR4_TSD, edx, bit(X86_FEATURE_TSC)); - cr4_fixed1_update(X86_CR4_DE, edx, bit(X86_FEATURE_DE)); - cr4_fixed1_update(X86_CR4_PSE, edx, bit(X86_FEATURE_PSE)); - cr4_fixed1_update(X86_CR4_PAE, edx, bit(X86_FEATURE_PAE)); - cr4_fixed1_update(X86_CR4_MCE, edx, bit(X86_FEATURE_MCE)); - cr4_fixed1_update(X86_CR4_PGE, edx, bit(X86_FEATURE_PGE)); - cr4_fixed1_update(X86_CR4_OSFXSR, edx, bit(X86_FEATURE_FXSR)); - cr4_fixed1_update(X86_CR4_OSXMMEXCPT, edx, bit(X86_FEATURE_XMM)); - cr4_fixed1_update(X86_CR4_VMXE, ecx, bit(X86_FEATURE_VMX)); - cr4_fixed1_update(X86_CR4_SMXE, ecx, bit(X86_FEATURE_SMX)); - cr4_fixed1_update(X86_CR4_PCIDE, ecx, bit(X86_FEATURE_PCID)); - cr4_fixed1_update(X86_CR4_OSXSAVE, ecx, bit(X86_FEATURE_XSAVE)); + cr4_fixed1_update(X86_CR4_VME, edx, feature_bit(VME)); + cr4_fixed1_update(X86_CR4_PVI, edx, feature_bit(VME)); + cr4_fixed1_update(X86_CR4_TSD, edx, feature_bit(TSC)); + cr4_fixed1_update(X86_CR4_DE, edx, feature_bit(DE)); + cr4_fixed1_update(X86_CR4_PSE, edx, feature_bit(PSE)); + cr4_fixed1_update(X86_CR4_PAE, edx, feature_bit(PAE)); + cr4_fixed1_update(X86_CR4_MCE, edx, feature_bit(MCE)); + cr4_fixed1_update(X86_CR4_PGE, edx, feature_bit(PGE)); + cr4_fixed1_update(X86_CR4_OSFXSR, edx, feature_bit(FXSR)); + cr4_fixed1_update(X86_CR4_OSXMMEXCPT, edx, feature_bit(XMM)); + cr4_fixed1_update(X86_CR4_VMXE, ecx, feature_bit(VMX)); + cr4_fixed1_update(X86_CR4_SMXE, ecx, feature_bit(SMX)); + cr4_fixed1_update(X86_CR4_PCIDE, ecx, feature_bit(PCID)); + cr4_fixed1_update(X86_CR4_OSXSAVE, ecx, feature_bit(XSAVE)); entry = kvm_find_cpuid_entry(vcpu, 0x7, 0); - cr4_fixed1_update(X86_CR4_FSGSBASE, ebx, bit(X86_FEATURE_FSGSBASE)); - cr4_fixed1_update(X86_CR4_SMEP, ebx, bit(X86_FEATURE_SMEP)); - cr4_fixed1_update(X86_CR4_SMAP, ebx, bit(X86_FEATURE_SMAP)); - cr4_fixed1_update(X86_CR4_PKE, ecx, bit(X86_FEATURE_PKU)); - cr4_fixed1_update(X86_CR4_UMIP, ecx, bit(X86_FEATURE_UMIP)); + cr4_fixed1_update(X86_CR4_FSGSBASE, ebx, feature_bit(FSGSBASE)); + cr4_fixed1_update(X86_CR4_SMEP, ebx, feature_bit(SMEP)); + cr4_fixed1_update(X86_CR4_SMAP, ebx, feature_bit(SMAP)); + cr4_fixed1_update(X86_CR4_PKE, ecx, feature_bit(PKU)); + cr4_fixed1_update(X86_CR4_UMIP, ecx, feature_bit(UMIP)); + cr4_fixed1_update(X86_CR4_LA57, ecx, feature_bit(LA57)); #undef cr4_fixed1_update } @@ -7000,6 +7054,9 @@ static void vmx_cpuid_update(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); + /* xsaves_enabled is recomputed in vmx_compute_secondary_exec_control(). */ + vcpu->arch.xsaves_enabled = false; + if (cpu_has_secondary_exec_ctrls()) { vmx_compute_secondary_exec_control(vmx); vmcs_set_secondary_exec_control(vmx); @@ -7007,10 +7064,12 @@ static void vmx_cpuid_update(struct kvm_vcpu *vcpu) if (nested_vmx_allowed(vcpu)) to_vmx(vcpu)->msr_ia32_feature_control_valid_bits |= - FEATURE_CONTROL_VMXON_ENABLED_OUTSIDE_SMX; + FEAT_CTL_VMX_ENABLED_INSIDE_SMX | + FEAT_CTL_VMX_ENABLED_OUTSIDE_SMX; else to_vmx(vcpu)->msr_ia32_feature_control_valid_bits &= - ~FEATURE_CONTROL_VMXON_ENABLED_OUTSIDE_SMX; + ~(FEAT_CTL_VMX_ENABLED_INSIDE_SMX | + FEAT_CTL_VMX_ENABLED_OUTSIDE_SMX); if (nested_vmx_allowed(vcpu)) { nested_vmx_cr_fixed1_bits_update(vcpu); @@ -7020,12 +7079,21 @@ static void vmx_cpuid_update(struct kvm_vcpu *vcpu) if (boot_cpu_has(X86_FEATURE_INTEL_PT) && guest_cpuid_has(vcpu, X86_FEATURE_INTEL_PT)) update_intel_pt_cfg(vcpu); + + if (boot_cpu_has(X86_FEATURE_RTM)) { + struct shared_msr_entry *msr; + msr = find_msr_entry(vmx, MSR_IA32_TSX_CTRL); + if (msr) { + bool enabled = guest_cpuid_has(vcpu, X86_FEATURE_RTM); + vmx_set_guest_msr(vmx, msr, enabled ? 0 : TSX_CTRL_RTM_DISABLE); + } + } } static void vmx_set_supported_cpuid(u32 func, struct kvm_cpuid_entry2 *entry) { if (func == 1 && nested) - entry->ecx |= bit(X86_FEATURE_VMX); + entry->ecx |= feature_bit(VMX); } static void vmx_request_immediate_exit(struct kvm_vcpu *vcpu) @@ -7369,10 +7437,14 @@ static int vmx_update_pi_irte(struct kvm *kvm, unsigned int host_irq, * irqbalance to make the interrupts single-CPU. * * We will support full lowest-priority interrupt later. + * + * In addition, we can only inject generic interrupts using + * the PI mechanism, refuse to route others through it. */ kvm_set_msi_irq(kvm, e, &irq); - if (!kvm_intr_is_single_vcpu(kvm, &irq, &vcpu)) { + if (!kvm_intr_is_single_vcpu(kvm, &irq, &vcpu) || + !kvm_irq_is_postable(&irq)) { /* * Make sure the IRTE is in remapped mode if * we don't handle it in posted mode. @@ -7416,10 +7488,10 @@ static 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 |= - FEATURE_CONTROL_LMCE; + FEAT_CTL_LMCE_ENABLED; else to_vmx(vcpu)->msr_ia32_feature_control_valid_bits &= - ~FEATURE_CONTROL_LMCE; + ~FEAT_CTL_LMCE_ENABLED; } static int vmx_smi_allowed(struct kvm_vcpu *vcpu) @@ -7474,6 +7546,11 @@ static bool vmx_need_emulation_on_page_fault(struct kvm_vcpu *vcpu) return false; } +static bool vmx_apic_init_signal_blocked(struct kvm_vcpu *vcpu) +{ + return to_vmx(vcpu)->nested.vmxon; +} + static __init int hardware_setup(void) { unsigned long host_bndcfgs; @@ -7499,9 +7576,6 @@ static __init int hardware_setup(void) WARN_ONCE(host_bndcfgs, "KVM: BNDCFGS in host will be lost"); } - if (boot_cpu_has(X86_FEATURE_XSAVES)) - rdmsrl(MSR_IA32_XSS, host_xss); - if (!cpu_has_vmx_vpid() || !cpu_has_vmx_invvpid() || !(cpu_has_vmx_invvpid_single() || cpu_has_vmx_invvpid_global())) enable_vpid = 0; @@ -7649,6 +7723,14 @@ static __exit void hardware_unsetup(void) free_kvm_area(); } +static bool vmx_check_apicv_inhibit_reasons(ulong bit) +{ + ulong supported = BIT(APICV_INHIBIT_REASON_DISABLE) | + BIT(APICV_INHIBIT_REASON_HYPERV); + + return supported & BIT(bit); +} + static struct kvm_x86_ops vmx_x86_ops __ro_after_init = { .cpu_has_kvm_support = cpu_has_kvm_support, .disabled_by_bios = vmx_disabled_by_bios, @@ -7682,7 +7764,6 @@ static struct kvm_x86_ops vmx_x86_ops __ro_after_init = { .get_cpl = vmx_get_cpl, .get_cs_db_l_bits = vmx_get_cs_db_l_bits, .decache_cr0_guest_bits = vmx_decache_cr0_guest_bits, - .decache_cr3 = vmx_decache_cr3, .decache_cr4_guest_bits = vmx_decache_cr4_guest_bits, .set_cr0 = vmx_set_cr0, .set_cr3 = vmx_set_cr3, @@ -7722,10 +7803,10 @@ static struct kvm_x86_ops vmx_x86_ops __ro_after_init = { .update_cr8_intercept = update_cr8_intercept, .set_virtual_apic_mode = vmx_set_virtual_apic_mode, .set_apic_access_page_addr = vmx_set_apic_access_page_addr, - .get_enable_apicv = vmx_get_enable_apicv, .refresh_apicv_exec_ctrl = vmx_refresh_apicv_exec_ctrl, .load_eoi_exitmap = vmx_load_eoi_exitmap, .apicv_post_state_restore = vmx_apicv_post_state_restore, + .check_apicv_inhibit_reasons = vmx_check_apicv_inhibit_reasons, .hwapic_irr_update = vmx_hwapic_irr_update, .hwapic_isr_update = vmx_hwapic_isr_update, .guest_apic_has_interrupt = vmx_guest_apic_has_interrupt, @@ -7762,6 +7843,7 @@ static struct kvm_x86_ops vmx_x86_ops __ro_after_init = { .xsaves_supported = vmx_xsaves_supported, .umip_emulated = vmx_umip_emulated, .pt_supported = vmx_pt_supported, + .pku_supported = vmx_pku_supported, .request_immediate_exit = vmx_request_immediate_exit, @@ -7797,7 +7879,9 @@ static struct kvm_x86_ops vmx_x86_ops __ro_after_init = { .set_nested_state = NULL, .get_vmcs12_pages = NULL, .nested_enable_evmcs = NULL, + .nested_get_evmcs_version = NULL, .need_emulation_on_page_fault = vmx_need_emulation_on_page_fault, + .apic_init_signal_blocked = vmx_apic_init_signal_blocked, }; static void vmx_cleanup_l1d_flush(void) @@ -7834,6 +7918,7 @@ static void vmx_exit(void) if (!vp_ap) continue; + vp_ap->nested_control.features.directhypercall = 0; vp_ap->current_nested_vmcs = 0; vp_ap->enlighten_vmentry = 0; } @@ -7873,6 +7958,11 @@ static int __init vmx_init(void) pr_info("KVM: vmx: using Hyper-V Enlightened VMCS\n"); static_branch_enable(&enable_evmcs); } + + if (ms_hyperv.nested_features & HV_X64_NESTED_DIRECT_FLUSH) + vmx_x86_ops.enable_direct_tlbflush + = hv_enable_direct_tlbflush; + } else { enlightened_vmcs = false; } @@ -7890,12 +7980,10 @@ static int __init vmx_init(void) * contain 'auto' which will be turned into the default 'cond' * mitigation mode. */ - if (boot_cpu_has(X86_BUG_L1TF)) { - r = vmx_setup_l1d_flush(vmentry_l1d_flush_param); - if (r) { - vmx_exit(); - return r; - } + r = vmx_setup_l1d_flush(vmentry_l1d_flush_param); + if (r) { + vmx_exit(); + return r; } #ifdef CONFIG_KEXEC_CORE diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h index 82d0bc3a4d52..7f42cf3dcd70 100644 --- a/arch/x86/kvm/vmx/vmx.h +++ b/arch/x86/kvm/vmx/vmx.h @@ -14,17 +14,25 @@ extern const u32 vmx_msr_index[]; extern u64 host_efer; +extern u32 get_umwait_control_msr(void); + #define MSR_TYPE_R 1 #define MSR_TYPE_W 2 #define MSR_TYPE_RW 3 #define X2APIC_MSR(r) (APIC_BASE_MSR + ((r) >> 4)) -#define NR_AUTOLOAD_MSRS 8 +#ifdef CONFIG_X86_64 +#define NR_SHARED_MSRS 7 +#else +#define NR_SHARED_MSRS 4 +#endif + +#define NR_LOADSTORE_MSRS 8 struct vmx_msrs { unsigned int nr; - struct vmx_msr_entry val[NR_AUTOLOAD_MSRS]; + struct vmx_msr_entry val[NR_LOADSTORE_MSRS]; }; struct shared_msr_entry { @@ -165,6 +173,9 @@ struct nested_vmx { u64 vmcs01_debugctl; u64 vmcs01_guest_bndcfgs; + /* to migrate it to L1 if L2 writes to L1's CR8 directly */ + int l1_tpr_threshold; + u16 vpid02; u16 last_vpid; @@ -201,7 +212,7 @@ struct vcpu_vmx { u32 idt_vectoring_info; ulong rflags; - struct shared_msr_entry *guest_msrs; + struct shared_msr_entry guest_msrs[NR_SHARED_MSRS]; int nmsrs; int save_nmsrs; bool guest_msrs_ready; @@ -211,6 +222,7 @@ struct vcpu_vmx { #endif u64 spec_ctrl; + u32 msr_ia32_umwait_control; u32 secondary_exec_control; @@ -227,6 +239,10 @@ struct vcpu_vmx { struct vmx_msrs host; } msr_autoload; + struct msr_autostore { + struct vmx_msrs guest; + } msr_autostore; + struct { int vm86_active; ulong save_rflags; @@ -253,7 +269,7 @@ struct vcpu_vmx { struct nested_vmx nested; /* Dynamic PLE window. */ - int ple_window; + unsigned int ple_window; bool ple_window_dirty; bool req_immediate_exit; @@ -273,7 +289,7 @@ struct vcpu_vmx { /* * Only bits masked by msr_ia32_feature_control_valid_bits can be set in - * msr_ia32_feature_control. FEATURE_CONTROL_LOCKED is always included + * msr_ia32_feature_control. FEAT_CTL_LOCKED is always included * in msr_ia32_feature_control_valid_bits. */ u64 msr_ia32_feature_control; @@ -331,6 +347,7 @@ void vmx_set_virtual_apic_mode(struct kvm_vcpu *vcpu); struct shared_msr_entry *find_msr_entry(struct vcpu_vmx *vmx, u32 msr); void pt_update_intercept_for_msr(struct vcpu_vmx *vmx); void vmx_update_host_rsp(struct vcpu_vmx *vmx, unsigned long host_rsp); +int vmx_find_msr_index(struct vmx_msrs *m, u32 msr); #define POSTED_INTR_ON 0 #define POSTED_INTR_SN 1 @@ -352,6 +369,11 @@ static inline int pi_test_and_set_pir(int vector, struct pi_desc *pi_desc) return test_and_set_bit(vector, (unsigned long *)pi_desc->pir); } +static inline bool pi_is_pir_empty(struct pi_desc *pi_desc) +{ + return bitmap_empty((unsigned long *)pi_desc->pir, NR_VECTORS); +} + static inline void pi_set_sn(struct pi_desc *pi_desc) { set_bit(POSTED_INTR_SN, @@ -370,6 +392,12 @@ static inline void pi_clear_on(struct pi_desc *pi_desc) (unsigned long *)&pi_desc->control); } +static inline void pi_clear_sn(struct pi_desc *pi_desc) +{ + clear_bit(POSTED_INTR_SN, + (unsigned long *)&pi_desc->control); +} + static inline int pi_test_on(struct pi_desc *pi_desc) { return test_bit(POSTED_INTR_ON, @@ -497,6 +525,12 @@ static inline void decache_tsc_multiplier(struct vcpu_vmx *vmx) vmcs_write64(TSC_MULTIPLIER, vmx->current_tsc_ratio); } +static inline bool vmx_has_waitpkg(struct vcpu_vmx *vmx) +{ + return vmx->secondary_exec_control & + SECONDARY_EXEC_ENABLE_USR_WAIT_PAUSE; +} + void dump_vmcs(void); #endif /* __KVM_X86_VMX_H */ diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 93b0bd45ac73..fb5d64ebc35d 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -26,6 +26,7 @@ #include "cpuid.h" #include "pmu.h" #include "hyperv.h" +#include "lapic.h" #include <linux/clocksource.h> #include <linux/interrupt.h> @@ -68,6 +69,7 @@ #include <asm/mshyperv.h> #include <asm/hypervisor.h> #include <asm/intel_pt.h> +#include <asm/emulate_prefix.h> #include <clocksource/hyperv_timer.h> #define CREATE_TRACE_POINTS @@ -92,8 +94,10 @@ u64 __read_mostly efer_reserved_bits = ~((u64)(EFER_SCE | EFER_LME | EFER_LMA)); static u64 __read_mostly efer_reserved_bits = ~((u64)EFER_SCE); #endif -#define VM_STAT(x) offsetof(struct kvm, stat.x), KVM_STAT_VM -#define VCPU_STAT(x) offsetof(struct kvm_vcpu, stat.x), KVM_STAT_VCPU +static u64 __read_mostly cr4_reserved_bits = CR4_RESERVED_BITS; + +#define VM_STAT(x, ...) offsetof(struct kvm, stat.x), KVM_STAT_VM, ## __VA_ARGS__ +#define VCPU_STAT(x, ...) offsetof(struct kvm_vcpu, stat.x), KVM_STAT_VCPU, ## __VA_ARGS__ #define KVM_X2APIC_API_VALID_FLAGS (KVM_X2APIC_API_USE_32BIT_IDS | \ KVM_X2APIC_API_DISABLE_BROADCAST_QUIRK) @@ -176,6 +180,8 @@ struct kvm_shared_msrs { static struct kvm_shared_msrs_global __read_mostly shared_msrs_global; static struct kvm_shared_msrs __percpu *shared_msrs; +static u64 __read_mostly host_xss; + struct kvm_stats_debugfs_item debugfs_entries[] = { { "pf_fixed", VCPU_STAT(pf_fixed) }, { "pf_guest", VCPU_STAT(pf_guest) }, @@ -212,7 +218,8 @@ struct kvm_stats_debugfs_item debugfs_entries[] = { { "mmu_cache_miss", VM_STAT(mmu_cache_miss) }, { "mmu_unsync", VM_STAT(mmu_unsync) }, { "remote_tlb_flush", VM_STAT(remote_tlb_flush) }, - { "largepages", VM_STAT(lpages) }, + { "largepages", VM_STAT(lpages, .mode = 0444) }, + { "nx_largepages_splitted", VM_STAT(nx_lpage_splits, .mode = 0444) }, { "max_mmu_page_hash_collisions", VM_STAT(max_mmu_page_hash_collisions) }, { NULL } @@ -259,23 +266,6 @@ static void kvm_on_user_return(struct user_return_notifier *urn) } } -static void shared_msr_update(unsigned slot, u32 msr) -{ - u64 value; - unsigned int cpu = smp_processor_id(); - struct kvm_shared_msrs *smsr = per_cpu_ptr(shared_msrs, cpu); - - /* only read, and nobody should modify it at this time, - * so don't need lock */ - if (slot >= shared_msrs_global.nr) { - printk(KERN_ERR "kvm: invalid MSR slot!"); - return; - } - rdmsrl_safe(msr, &value); - smsr->values[slot].host = value; - smsr->values[slot].curr = value; -} - void kvm_define_shared_msr(unsigned slot, u32 msr) { BUG_ON(slot >= KVM_NR_SHARED_MSRS); @@ -287,10 +277,16 @@ EXPORT_SYMBOL_GPL(kvm_define_shared_msr); static void kvm_shared_msr_cpu_online(void) { - unsigned i; + unsigned int cpu = smp_processor_id(); + struct kvm_shared_msrs *smsr = per_cpu_ptr(shared_msrs, cpu); + u64 value; + int i; - for (i = 0; i < shared_msrs_global.nr; ++i) - shared_msr_update(i, shared_msrs_global.msrs[i]); + for (i = 0; i < shared_msrs_global.nr; ++i) { + rdmsrl_safe(shared_msrs_global.msrs[i], &value); + smsr->values[i].host = value; + smsr->values[i].curr = value; + } } int kvm_set_shared_msr(unsigned slot, u64 value, u64 mask) @@ -299,13 +295,14 @@ int kvm_set_shared_msr(unsigned slot, u64 value, u64 mask) struct kvm_shared_msrs *smsr = per_cpu_ptr(shared_msrs, cpu); int err; - if (((value ^ smsr->values[slot].curr) & mask) == 0) + value = (value & mask) | (smsr->values[slot].host & ~mask); + if (value == smsr->values[slot].curr) return 0; - smsr->values[slot].curr = value; err = wrmsrl_safe(shared_msrs_global.msrs[slot], value); if (err) return 1; + smsr->values[slot].curr = value; if (!smsr->registered) { smsr->urn.on_user_return = kvm_on_user_return; user_return_notifier_register(&smsr->urn); @@ -360,7 +357,7 @@ EXPORT_SYMBOL_GPL(kvm_set_apic_base); asmlinkage __visible void kvm_spurious_fault(void) { /* Fault while not rebooting. We want the trace. */ - BUG(); + BUG_ON(!kvm_rebooting); } EXPORT_SYMBOL_GPL(kvm_spurious_fault); @@ -441,6 +438,14 @@ void kvm_deliver_exception_payload(struct kvm_vcpu *vcpu) * for #DB exceptions under VMX. */ vcpu->arch.dr6 ^= payload & DR6_RTM; + + /* + * The #DB payload is defined as compatible with the 'pending + * debug exceptions' field under VMX, not DR6. While bit 12 is + * defined in the 'pending debug exceptions' field (enabled + * breakpoint), it is reserved and must be zero in DR6. + */ + vcpu->arch.dr6 &= ~BIT(12); break; case PF_VECTOR: vcpu->arch.cr2 = payload; @@ -493,19 +498,7 @@ static void kvm_multiple_exception(struct kvm_vcpu *vcpu, vcpu->arch.exception.error_code = error_code; vcpu->arch.exception.has_payload = has_payload; vcpu->arch.exception.payload = payload; - /* - * In guest mode, payload delivery should be deferred, - * so that the L1 hypervisor can intercept #PF before - * CR2 is modified (or intercept #DB before DR6 is - * modified under nVMX). However, for ABI - * compatibility with KVM_GET_VCPU_EVENTS and - * KVM_SET_VCPU_EVENTS, we can't delay payload - * delivery unless userspace has enabled this - * functionality via the per-VM capability, - * KVM_CAP_EXCEPTION_PAYLOAD. - */ - if (!vcpu->kvm->arch.exception_payload_enabled || - !is_guest_mode(vcpu)) + if (!is_guest_mode(vcpu)) kvm_deliver_exception_payload(vcpu); return; } @@ -674,8 +667,14 @@ static int kvm_read_nested_guest_page(struct kvm_vcpu *vcpu, gfn_t gfn, data, offset, len, access); } +static inline u64 pdptr_rsvd_bits(struct kvm_vcpu *vcpu) +{ + return rsvd_bits(cpuid_maxphyaddr(vcpu), 63) | rsvd_bits(5, 8) | + rsvd_bits(1, 2); +} + /* - * Load the pae pdptrs. Return true is they are all valid. + * Load the pae pdptrs. Return 1 if they are all valid, 0 otherwise. */ int load_pdptrs(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, unsigned long cr3) { @@ -694,8 +693,7 @@ int load_pdptrs(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, unsigned long cr3) } for (i = 0; i < ARRAY_SIZE(pdpte); ++i) { if ((pdpte[i] & PT_PRESENT_MASK) && - (pdpte[i] & - vcpu->arch.mmu->guest_rsvd_check.rsvd_bits_mask[0][2])) { + (pdpte[i] & pdptr_rsvd_bits(vcpu))) { ret = 0; goto out; } @@ -703,10 +701,8 @@ int load_pdptrs(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, unsigned long cr3) ret = 1; memcpy(mmu->pdptrs, pdpte, sizeof(mmu->pdptrs)); - __set_bit(VCPU_EXREG_PDPTR, - (unsigned long *)&vcpu->arch.regs_avail); - __set_bit(VCPU_EXREG_PDPTR, - (unsigned long *)&vcpu->arch.regs_dirty); + kvm_register_mark_dirty(vcpu, VCPU_EXREG_PDPTR); + out: return ret; @@ -716,7 +712,6 @@ EXPORT_SYMBOL_GPL(load_pdptrs); bool pdptrs_changed(struct kvm_vcpu *vcpu) { u64 pdpte[ARRAY_SIZE(vcpu->arch.walk_mmu->pdptrs)]; - bool changed = true; int offset; gfn_t gfn; int r; @@ -724,8 +719,7 @@ bool pdptrs_changed(struct kvm_vcpu *vcpu) if (!is_pae_paging(vcpu)) return false; - if (!test_bit(VCPU_EXREG_PDPTR, - (unsigned long *)&vcpu->arch.regs_avail)) + if (!kvm_register_is_available(vcpu, VCPU_EXREG_PDPTR)) return true; gfn = (kvm_read_cr3(vcpu) & 0xffffffe0ul) >> PAGE_SHIFT; @@ -733,11 +727,9 @@ bool pdptrs_changed(struct kvm_vcpu *vcpu) r = kvm_read_nested_guest_page(vcpu, gfn, pdpte, offset, sizeof(pdpte), PFERR_USER_MASK | PFERR_WRITE_MASK); if (r < 0) - goto out; - changed = memcmp(pdpte, vcpu->arch.walk_mmu->pdptrs, sizeof(pdpte)) != 0; -out: + return true; - return changed; + return memcmp(pdpte, vcpu->arch.walk_mmu->pdptrs, sizeof(pdpte)) != 0; } EXPORT_SYMBOL_GPL(pdptrs_changed); @@ -806,27 +798,34 @@ void kvm_lmsw(struct kvm_vcpu *vcpu, unsigned long msw) } EXPORT_SYMBOL_GPL(kvm_lmsw); -void kvm_load_guest_xcr0(struct kvm_vcpu *vcpu) +void kvm_load_guest_xsave_state(struct kvm_vcpu *vcpu) { - if (kvm_read_cr4_bits(vcpu, X86_CR4_OSXSAVE) && - !vcpu->guest_xcr0_loaded) { - /* kvm_set_xcr() also depends on this */ + if (kvm_read_cr4_bits(vcpu, X86_CR4_OSXSAVE)) { + if (vcpu->arch.xcr0 != host_xcr0) xsetbv(XCR_XFEATURE_ENABLED_MASK, vcpu->arch.xcr0); - vcpu->guest_xcr0_loaded = 1; + + if (vcpu->arch.xsaves_enabled && + vcpu->arch.ia32_xss != host_xss) + wrmsrl(MSR_IA32_XSS, vcpu->arch.ia32_xss); } } -EXPORT_SYMBOL_GPL(kvm_load_guest_xcr0); +EXPORT_SYMBOL_GPL(kvm_load_guest_xsave_state); -void kvm_put_guest_xcr0(struct kvm_vcpu *vcpu) +void kvm_load_host_xsave_state(struct kvm_vcpu *vcpu) { - if (vcpu->guest_xcr0_loaded) { + if (kvm_read_cr4_bits(vcpu, X86_CR4_OSXSAVE)) { + if (vcpu->arch.xcr0 != host_xcr0) xsetbv(XCR_XFEATURE_ENABLED_MASK, host_xcr0); - vcpu->guest_xcr0_loaded = 0; + + if (vcpu->arch.xsaves_enabled && + vcpu->arch.ia32_xss != host_xss) + wrmsrl(MSR_IA32_XSS, host_xss); } + } -EXPORT_SYMBOL_GPL(kvm_put_guest_xcr0); +EXPORT_SYMBOL_GPL(kvm_load_host_xsave_state); static int __kvm_set_xcr(struct kvm_vcpu *vcpu, u32 index, u64 xcr) { @@ -879,34 +878,58 @@ int kvm_set_xcr(struct kvm_vcpu *vcpu, u32 index, u64 xcr) } EXPORT_SYMBOL_GPL(kvm_set_xcr); -int kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) +#define __cr4_reserved_bits(__cpu_has, __c) \ +({ \ + u64 __reserved_bits = CR4_RESERVED_BITS; \ + \ + if (!__cpu_has(__c, X86_FEATURE_XSAVE)) \ + __reserved_bits |= X86_CR4_OSXSAVE; \ + if (!__cpu_has(__c, X86_FEATURE_SMEP)) \ + __reserved_bits |= X86_CR4_SMEP; \ + if (!__cpu_has(__c, X86_FEATURE_SMAP)) \ + __reserved_bits |= X86_CR4_SMAP; \ + if (!__cpu_has(__c, X86_FEATURE_FSGSBASE)) \ + __reserved_bits |= X86_CR4_FSGSBASE; \ + if (!__cpu_has(__c, X86_FEATURE_PKU)) \ + __reserved_bits |= X86_CR4_PKE; \ + if (!__cpu_has(__c, X86_FEATURE_LA57)) \ + __reserved_bits |= X86_CR4_LA57; \ + if (!__cpu_has(__c, X86_FEATURE_UMIP)) \ + __reserved_bits |= X86_CR4_UMIP; \ + __reserved_bits; \ +}) + +static u64 kvm_host_cr4_reserved_bits(struct cpuinfo_x86 *c) { - unsigned long old_cr4 = kvm_read_cr4(vcpu); - unsigned long pdptr_bits = X86_CR4_PGE | X86_CR4_PSE | X86_CR4_PAE | - X86_CR4_SMEP | X86_CR4_SMAP | X86_CR4_PKE; + u64 reserved_bits = __cr4_reserved_bits(cpu_has, c); - if (cr4 & CR4_RESERVED_BITS) - return 1; + if (cpuid_ecx(0x7) & feature_bit(LA57)) + reserved_bits &= ~X86_CR4_LA57; - if (!guest_cpuid_has(vcpu, X86_FEATURE_XSAVE) && (cr4 & X86_CR4_OSXSAVE)) - return 1; + if (kvm_x86_ops->umip_emulated()) + reserved_bits &= ~X86_CR4_UMIP; - if (!guest_cpuid_has(vcpu, X86_FEATURE_SMEP) && (cr4 & X86_CR4_SMEP)) - return 1; + return reserved_bits; +} - if (!guest_cpuid_has(vcpu, X86_FEATURE_SMAP) && (cr4 & X86_CR4_SMAP)) - return 1; +static int kvm_valid_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) +{ + if (cr4 & cr4_reserved_bits) + return -EINVAL; - if (!guest_cpuid_has(vcpu, X86_FEATURE_FSGSBASE) && (cr4 & X86_CR4_FSGSBASE)) - return 1; + if (cr4 & __cr4_reserved_bits(guest_cpuid_has, vcpu)) + return -EINVAL; - if (!guest_cpuid_has(vcpu, X86_FEATURE_PKU) && (cr4 & X86_CR4_PKE)) - return 1; + return 0; +} - if (!guest_cpuid_has(vcpu, X86_FEATURE_LA57) && (cr4 & X86_CR4_LA57)) - return 1; +int kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) +{ + unsigned long old_cr4 = kvm_read_cr4(vcpu); + unsigned long pdptr_bits = X86_CR4_PGE | X86_CR4_PSE | X86_CR4_PAE | + X86_CR4_SMEP | X86_CR4_SMAP | X86_CR4_PKE; - if (!guest_cpuid_has(vcpu, X86_FEATURE_UMIP) && (cr4 & X86_CR4_UMIP)) + if (kvm_valid_cr4(vcpu, cr4)) return 1; if (is_long_mode(vcpu)) { @@ -970,7 +993,7 @@ int kvm_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3) kvm_mmu_new_cr3(vcpu, cr3, skip_tlb_flush); vcpu->arch.cr3 = cr3; - __set_bit(VCPU_EXREG_CR3, (ulong *)&vcpu->arch.regs_avail); + kvm_register_mark_available(vcpu, VCPU_EXREG_CR3); return 0; } @@ -1039,9 +1062,11 @@ static u64 kvm_dr6_fixed(struct kvm_vcpu *vcpu) static int __kvm_set_dr(struct kvm_vcpu *vcpu, int dr, unsigned long val) { + size_t size = ARRAY_SIZE(vcpu->arch.db); + switch (dr) { case 0 ... 3: - vcpu->arch.db[dr] = val; + vcpu->arch.db[array_index_nospec(dr, size)] = val; if (!(vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP)) vcpu->arch.eff_db[dr] = val; break; @@ -1056,7 +1081,7 @@ static int __kvm_set_dr(struct kvm_vcpu *vcpu, int dr, unsigned long val) case 5: /* fall through */ default: /* 7 */ - if (val & 0xffffffff00000000ULL) + if (!kvm_dr7_valid(val)) return -1; /* #GP */ vcpu->arch.dr7 = (val & DR7_VOLATILE) | DR7_FIXED_1; kvm_update_dr7(vcpu); @@ -1078,9 +1103,11 @@ EXPORT_SYMBOL_GPL(kvm_set_dr); int kvm_get_dr(struct kvm_vcpu *vcpu, int dr, unsigned long *val) { + size_t size = ARRAY_SIZE(vcpu->arch.db); + switch (dr) { case 0 ... 3: - *val = vcpu->arch.db[dr]; + *val = vcpu->arch.db[array_index_nospec(dr, size)]; break; case 4: /* fall through */ @@ -1119,20 +1146,22 @@ EXPORT_SYMBOL_GPL(kvm_rdpmc); * List of msr numbers which we expose to userspace through KVM_GET_MSRS * and KVM_SET_MSRS, and KVM_GET_MSR_INDEX_LIST. * - * This list is modified at module load time to reflect the + * The three MSR lists(msrs_to_save, emulated_msrs, msr_based_features) + * extract the supported MSRs from the related const lists. + * msrs_to_save is selected from the msrs_to_save_all to reflect the * capabilities of the host cpu. This capabilities test skips MSRs that are - * kvm-specific. Those are put in emulated_msrs; filtering of emulated_msrs + * kvm-specific. Those are put in emulated_msrs_all; filtering of emulated_msrs * may depend on host virtualization features rather than host cpu features. */ -static u32 msrs_to_save[] = { +static const u32 msrs_to_save_all[] = { MSR_IA32_SYSENTER_CS, MSR_IA32_SYSENTER_ESP, MSR_IA32_SYSENTER_EIP, MSR_STAR, #ifdef CONFIG_X86_64 MSR_CSTAR, MSR_KERNEL_GS_BASE, MSR_SYSCALL_MASK, MSR_LSTAR, #endif MSR_IA32_TSC, MSR_IA32_CR_PAT, MSR_VM_HSAVE_PA, - MSR_IA32_FEATURE_CONTROL, MSR_IA32_BNDCFGS, MSR_TSC_AUX, + MSR_IA32_FEAT_CTL, MSR_IA32_BNDCFGS, MSR_TSC_AUX, MSR_IA32_SPEC_CTRL, MSR_IA32_RTIT_CTL, MSR_IA32_RTIT_STATUS, MSR_IA32_RTIT_CR3_MATCH, MSR_IA32_RTIT_OUTPUT_BASE, MSR_IA32_RTIT_OUTPUT_MASK, @@ -1140,11 +1169,36 @@ static u32 msrs_to_save[] = { MSR_IA32_RTIT_ADDR1_A, MSR_IA32_RTIT_ADDR1_B, MSR_IA32_RTIT_ADDR2_A, MSR_IA32_RTIT_ADDR2_B, MSR_IA32_RTIT_ADDR3_A, MSR_IA32_RTIT_ADDR3_B, + MSR_IA32_UMWAIT_CONTROL, + + MSR_ARCH_PERFMON_FIXED_CTR0, MSR_ARCH_PERFMON_FIXED_CTR1, + MSR_ARCH_PERFMON_FIXED_CTR0 + 2, MSR_ARCH_PERFMON_FIXED_CTR0 + 3, + MSR_CORE_PERF_FIXED_CTR_CTRL, MSR_CORE_PERF_GLOBAL_STATUS, + MSR_CORE_PERF_GLOBAL_CTRL, MSR_CORE_PERF_GLOBAL_OVF_CTRL, + MSR_ARCH_PERFMON_PERFCTR0, MSR_ARCH_PERFMON_PERFCTR1, + MSR_ARCH_PERFMON_PERFCTR0 + 2, MSR_ARCH_PERFMON_PERFCTR0 + 3, + MSR_ARCH_PERFMON_PERFCTR0 + 4, MSR_ARCH_PERFMON_PERFCTR0 + 5, + MSR_ARCH_PERFMON_PERFCTR0 + 6, MSR_ARCH_PERFMON_PERFCTR0 + 7, + MSR_ARCH_PERFMON_PERFCTR0 + 8, MSR_ARCH_PERFMON_PERFCTR0 + 9, + MSR_ARCH_PERFMON_PERFCTR0 + 10, MSR_ARCH_PERFMON_PERFCTR0 + 11, + MSR_ARCH_PERFMON_PERFCTR0 + 12, MSR_ARCH_PERFMON_PERFCTR0 + 13, + MSR_ARCH_PERFMON_PERFCTR0 + 14, MSR_ARCH_PERFMON_PERFCTR0 + 15, + MSR_ARCH_PERFMON_PERFCTR0 + 16, MSR_ARCH_PERFMON_PERFCTR0 + 17, + MSR_ARCH_PERFMON_EVENTSEL0, MSR_ARCH_PERFMON_EVENTSEL1, + MSR_ARCH_PERFMON_EVENTSEL0 + 2, MSR_ARCH_PERFMON_EVENTSEL0 + 3, + MSR_ARCH_PERFMON_EVENTSEL0 + 4, MSR_ARCH_PERFMON_EVENTSEL0 + 5, + MSR_ARCH_PERFMON_EVENTSEL0 + 6, MSR_ARCH_PERFMON_EVENTSEL0 + 7, + MSR_ARCH_PERFMON_EVENTSEL0 + 8, MSR_ARCH_PERFMON_EVENTSEL0 + 9, + MSR_ARCH_PERFMON_EVENTSEL0 + 10, MSR_ARCH_PERFMON_EVENTSEL0 + 11, + MSR_ARCH_PERFMON_EVENTSEL0 + 12, MSR_ARCH_PERFMON_EVENTSEL0 + 13, + MSR_ARCH_PERFMON_EVENTSEL0 + 14, MSR_ARCH_PERFMON_EVENTSEL0 + 15, + MSR_ARCH_PERFMON_EVENTSEL0 + 16, MSR_ARCH_PERFMON_EVENTSEL0 + 17, }; +static u32 msrs_to_save[ARRAY_SIZE(msrs_to_save_all)]; static unsigned num_msrs_to_save; -static u32 emulated_msrs[] = { +static const u32 emulated_msrs_all[] = { MSR_KVM_SYSTEM_TIME, MSR_KVM_WALL_CLOCK, MSR_KVM_SYSTEM_TIME_NEW, MSR_KVM_WALL_CLOCK_NEW, HV_X64_MSR_GUEST_OS_ID, HV_X64_MSR_HYPERCALL, @@ -1177,13 +1231,14 @@ static u32 emulated_msrs[] = { MSR_MISC_FEATURES_ENABLES, MSR_AMD64_VIRT_SPEC_CTRL, MSR_IA32_POWER_CTL, + MSR_IA32_UCODE_REV, /* * The following list leaves out MSRs whose values are determined * by arch/x86/kvm/vmx/nested.c based on CPUID or other MSRs. * We always support the "true" VMX control MSRs, even if the host * processor does not, so I am putting these registers here rather - * than in msrs_to_save. + * than in msrs_to_save_all. */ MSR_IA32_VMX_BASIC, MSR_IA32_VMX_TRUE_PINBASED_CTLS, @@ -1202,13 +1257,14 @@ static u32 emulated_msrs[] = { MSR_KVM_POLL_CONTROL, }; +static u32 emulated_msrs[ARRAY_SIZE(emulated_msrs_all)]; static unsigned num_emulated_msrs; /* * List of msr numbers which are used to expose MSR-based features that * can be used by a hypervisor to validate requested CPU features. */ -static u32 msr_based_features[] = { +static const u32 msr_based_features_all[] = { MSR_IA32_VMX_BASIC, MSR_IA32_VMX_TRUE_PINBASED_CTLS, MSR_IA32_VMX_PINBASED_CTLS, @@ -1233,6 +1289,7 @@ static u32 msr_based_features[] = { MSR_IA32_ARCH_CAPABILITIES, }; +static u32 msr_based_features[ARRAY_SIZE(msr_based_features_all)]; static unsigned int num_msr_based_features; static u64 kvm_get_arch_capabilities(void) @@ -1243,6 +1300,14 @@ static u64 kvm_get_arch_capabilities(void) rdmsrl(MSR_IA32_ARCH_CAPABILITIES, data); /* + * If nx_huge_pages is enabled, KVM's shadow paging will ensure that + * the nested hypervisor runs with NX huge pages. If it is not, + * L1 is anyway vulnerable to ITLB_MULTIHIT explots from other + * L1 guests, so it need not worry about its own (L2) guests. + */ + data |= ARCH_CAP_PSCHANGE_MC_NO; + + /* * If we're doing cache flushes (either "always" or "cond") * we will do one whenever the guest does a vmlaunch/vmresume. * If an outer hypervisor is doing the cache flush for us @@ -1254,6 +1319,24 @@ static u64 kvm_get_arch_capabilities(void) if (l1tf_vmx_mitigation != VMENTER_L1D_FLUSH_NEVER) data |= ARCH_CAP_SKIP_VMENTRY_L1DFLUSH; + if (!boot_cpu_has_bug(X86_BUG_CPU_MELTDOWN)) + data |= ARCH_CAP_RDCL_NO; + if (!boot_cpu_has_bug(X86_BUG_SPEC_STORE_BYPASS)) + data |= ARCH_CAP_SSB_NO; + if (!boot_cpu_has_bug(X86_BUG_MDS)) + data |= ARCH_CAP_MDS_NO; + + /* + * On TAA affected systems: + * - nothing to do if TSX is disabled on the host. + * - we emulate TSX_CTRL if present on the host. + * This lets the guest use VERW to clear CPU buffers. + */ + if (!boot_cpu_has(X86_FEATURE_RTM)) + data &= ~(ARCH_CAP_TAA_NO | ARCH_CAP_TSX_CTRL_MSR); + else if (!boot_cpu_has_bug(X86_BUG_TAA)) + data |= ARCH_CAP_TAA_NO; + return data; } @@ -1351,19 +1434,23 @@ void kvm_enable_efer_bits(u64 mask) EXPORT_SYMBOL_GPL(kvm_enable_efer_bits); /* - * Writes msr value into into the appropriate "register". + * Write @data into the MSR specified by @index. Select MSR specific fault + * checks are bypassed if @host_initiated is %true. * Returns 0 on success, non-0 otherwise. * Assumes vcpu_load() was already called. */ -int kvm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr) +static int __kvm_set_msr(struct kvm_vcpu *vcpu, u32 index, u64 data, + bool host_initiated) { - switch (msr->index) { + struct msr_data msr; + + switch (index) { case MSR_FS_BASE: case MSR_GS_BASE: case MSR_KERNEL_GS_BASE: case MSR_CSTAR: case MSR_LSTAR: - if (is_noncanonical_address(msr->data, vcpu)) + if (is_noncanonical_address(data, vcpu)) return 1; break; case MSR_IA32_SYSENTER_EIP: @@ -1380,54 +1467,158 @@ int kvm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr) * value, and that something deterministic happens if the guest * invokes 64-bit SYSENTER. */ - msr->data = get_canonical(msr->data, vcpu_virt_addr_bits(vcpu)); + data = get_canonical(data, vcpu_virt_addr_bits(vcpu)); } - return kvm_x86_ops->set_msr(vcpu, msr); + + msr.data = data; + msr.index = index; + msr.host_initiated = host_initiated; + + return kvm_x86_ops->set_msr(vcpu, &msr); } -EXPORT_SYMBOL_GPL(kvm_set_msr); /* - * Adapt set_msr() to msr_io()'s calling convention + * Read the MSR specified by @index into @data. Select MSR specific fault + * checks are bypassed if @host_initiated is %true. + * Returns 0 on success, non-0 otherwise. + * Assumes vcpu_load() was already called. */ -static int do_get_msr(struct kvm_vcpu *vcpu, unsigned index, u64 *data) +int __kvm_get_msr(struct kvm_vcpu *vcpu, u32 index, u64 *data, + bool host_initiated) { struct msr_data msr; - int r; + int ret; msr.index = index; - msr.host_initiated = true; - r = kvm_get_msr(vcpu, &msr); - if (r) - return r; + msr.host_initiated = host_initiated; - *data = msr.data; - return 0; + ret = kvm_x86_ops->get_msr(vcpu, &msr); + if (!ret) + *data = msr.data; + return ret; } -static int do_set_msr(struct kvm_vcpu *vcpu, unsigned index, u64 *data) +int kvm_get_msr(struct kvm_vcpu *vcpu, u32 index, u64 *data) { - struct msr_data msr; + return __kvm_get_msr(vcpu, index, data, false); +} +EXPORT_SYMBOL_GPL(kvm_get_msr); - msr.data = *data; - msr.index = index; - msr.host_initiated = true; - return kvm_set_msr(vcpu, &msr); +int kvm_set_msr(struct kvm_vcpu *vcpu, u32 index, u64 data) +{ + return __kvm_set_msr(vcpu, index, data, false); +} +EXPORT_SYMBOL_GPL(kvm_set_msr); + +int kvm_emulate_rdmsr(struct kvm_vcpu *vcpu) +{ + u32 ecx = kvm_rcx_read(vcpu); + u64 data; + + if (kvm_get_msr(vcpu, ecx, &data)) { + trace_kvm_msr_read_ex(ecx); + kvm_inject_gp(vcpu, 0); + return 1; + } + + trace_kvm_msr_read(ecx, data); + + kvm_rax_write(vcpu, data & -1u); + kvm_rdx_write(vcpu, (data >> 32) & -1u); + return kvm_skip_emulated_instruction(vcpu); +} +EXPORT_SYMBOL_GPL(kvm_emulate_rdmsr); + +int kvm_emulate_wrmsr(struct kvm_vcpu *vcpu) +{ + u32 ecx = kvm_rcx_read(vcpu); + u64 data = kvm_read_edx_eax(vcpu); + + if (kvm_set_msr(vcpu, ecx, data)) { + trace_kvm_msr_write_ex(ecx, data); + kvm_inject_gp(vcpu, 0); + return 1; + } + + trace_kvm_msr_write(ecx, data); + return kvm_skip_emulated_instruction(vcpu); +} +EXPORT_SYMBOL_GPL(kvm_emulate_wrmsr); + +/* + * The fast path for frequent and performance sensitive wrmsr emulation, + * i.e. the sending of IPI, sending IPI early in the VM-Exit flow reduces + * the latency of virtual IPI by avoiding the expensive bits of transitioning + * from guest to host, e.g. reacquiring KVM's SRCU lock. In contrast to the + * other cases which must be called after interrupts are enabled on the host. + */ +static int handle_fastpath_set_x2apic_icr_irqoff(struct kvm_vcpu *vcpu, u64 data) +{ + if (lapic_in_kernel(vcpu) && apic_x2apic_mode(vcpu->arch.apic) && + ((data & APIC_DEST_MASK) == APIC_DEST_PHYSICAL) && + ((data & APIC_MODE_MASK) == APIC_DM_FIXED)) { + + kvm_lapic_set_reg(vcpu->arch.apic, APIC_ICR2, (u32)(data >> 32)); + return kvm_lapic_reg_write(vcpu->arch.apic, APIC_ICR, (u32)data); + } + + return 1; +} + +enum exit_fastpath_completion handle_fastpath_set_msr_irqoff(struct kvm_vcpu *vcpu) +{ + u32 msr = kvm_rcx_read(vcpu); + u64 data = kvm_read_edx_eax(vcpu); + int ret = 0; + + switch (msr) { + case APIC_BASE_MSR + (APIC_ICR >> 4): + ret = handle_fastpath_set_x2apic_icr_irqoff(vcpu, data); + break; + default: + return EXIT_FASTPATH_NONE; + } + + if (!ret) { + trace_kvm_msr_write(msr, data); + return EXIT_FASTPATH_SKIP_EMUL_INS; + } + + return EXIT_FASTPATH_NONE; +} +EXPORT_SYMBOL_GPL(handle_fastpath_set_msr_irqoff); + +/* + * Adapt set_msr() to msr_io()'s calling convention + */ +static int do_get_msr(struct kvm_vcpu *vcpu, unsigned index, u64 *data) +{ + return __kvm_get_msr(vcpu, index, data, true); +} + +static int do_set_msr(struct kvm_vcpu *vcpu, unsigned index, u64 *data) +{ + return __kvm_set_msr(vcpu, index, *data, true); } #ifdef CONFIG_X86_64 +struct pvclock_clock { + int vclock_mode; + u64 cycle_last; + u64 mask; + u32 mult; + u32 shift; + u64 base_cycles; + u64 offset; +}; + struct pvclock_gtod_data { seqcount_t seq; - struct { /* extract of a clocksource struct */ - int vclock_mode; - u64 cycle_last; - u64 mask; - u32 mult; - u32 shift; - } clock; + struct pvclock_clock clock; /* extract of a clocksource struct */ + struct pvclock_clock raw_clock; /* extract of a clocksource struct */ - u64 boot_ns; - u64 nsec_base; + ktime_t offs_boot; u64 wall_time_sec; }; @@ -1436,9 +1627,6 @@ static struct pvclock_gtod_data pvclock_gtod_data; static void update_pvclock_gtod(struct timekeeper *tk) { struct pvclock_gtod_data *vdata = &pvclock_gtod_data; - u64 boot_ns; - - boot_ns = ktime_to_ns(ktime_add(tk->tkr_mono.base, tk->offs_boot)); write_seqcount_begin(&vdata->seq); @@ -1448,14 +1636,35 @@ static void update_pvclock_gtod(struct timekeeper *tk) vdata->clock.mask = tk->tkr_mono.mask; vdata->clock.mult = tk->tkr_mono.mult; vdata->clock.shift = tk->tkr_mono.shift; + vdata->clock.base_cycles = tk->tkr_mono.xtime_nsec; + vdata->clock.offset = tk->tkr_mono.base; - vdata->boot_ns = boot_ns; - vdata->nsec_base = tk->tkr_mono.xtime_nsec; + vdata->raw_clock.vclock_mode = tk->tkr_raw.clock->archdata.vclock_mode; + vdata->raw_clock.cycle_last = tk->tkr_raw.cycle_last; + vdata->raw_clock.mask = tk->tkr_raw.mask; + vdata->raw_clock.mult = tk->tkr_raw.mult; + vdata->raw_clock.shift = tk->tkr_raw.shift; + vdata->raw_clock.base_cycles = tk->tkr_raw.xtime_nsec; + vdata->raw_clock.offset = tk->tkr_raw.base; vdata->wall_time_sec = tk->xtime_sec; + vdata->offs_boot = tk->offs_boot; + write_seqcount_end(&vdata->seq); } + +static s64 get_kvmclock_base_ns(void) +{ + /* Count up from boot time, but with the frequency of the raw clock. */ + return ktime_to_ns(ktime_add(ktime_get_raw(), pvclock_gtod_data.offs_boot)); +} +#else +static s64 get_kvmclock_base_ns(void) +{ + /* Master clock not used, so we can just use CLOCK_BOOTTIME. */ + return ktime_get_boottime_ns(); +} #endif void kvm_set_pending_timer(struct kvm_vcpu *vcpu) @@ -1469,7 +1678,7 @@ static void kvm_write_wall_clock(struct kvm *kvm, gpa_t wall_clock) int version; int r; struct pvclock_wall_clock wc; - struct timespec64 boot; + u64 wall_nsec; if (!wall_clock) return; @@ -1489,17 +1698,12 @@ static void kvm_write_wall_clock(struct kvm *kvm, gpa_t wall_clock) /* * The guest calculates current wall clock time by adding * system time (updated by kvm_guest_time_update below) to the - * wall clock specified here. guest system time equals host - * system time for us, thus we must fill in host boot time here. + * wall clock specified here. We do the reverse here. */ - getboottime64(&boot); + wall_nsec = ktime_get_real_ns() - get_kvmclock_ns(kvm); - if (kvm->arch.kvmclock_offset) { - struct timespec64 ts = ns_to_timespec64(kvm->arch.kvmclock_offset); - boot = timespec64_sub(boot, ts); - } - wc.sec = (u32)boot.tv_sec; /* overflow in 2106 guest time */ - wc.nsec = boot.tv_nsec; + wc.nsec = do_div(wall_nsec, 1000000000); + wc.sec = (u32)wall_nsec; /* overflow in 2106 guest time */ wc.version = version; kvm_write_guest(kvm, wall_clock, &wc, sizeof(wc)); @@ -1747,7 +1951,7 @@ void kvm_write_tsc(struct kvm_vcpu *vcpu, struct msr_data *msr) raw_spin_lock_irqsave(&kvm->arch.tsc_write_lock, flags); offset = kvm_compute_tsc_offset(vcpu, data); - ns = ktime_get_boottime_ns(); + ns = get_kvmclock_base_ns(); elapsed = ns - kvm->arch.last_tsc_nsec; if (vcpu->arch.virtual_tsc_khz) { @@ -1877,21 +2081,21 @@ static u64 read_tsc(void) return last; } -static inline u64 vgettsc(u64 *tsc_timestamp, int *mode) +static inline u64 vgettsc(struct pvclock_clock *clock, u64 *tsc_timestamp, + int *mode) { long v; - struct pvclock_gtod_data *gtod = &pvclock_gtod_data; u64 tsc_pg_val; - switch (gtod->clock.vclock_mode) { + switch (clock->vclock_mode) { case VCLOCK_HVCLOCK: tsc_pg_val = hv_read_tsc_page_tsc(hv_get_tsc_page(), tsc_timestamp); if (tsc_pg_val != U64_MAX) { /* TSC page valid */ *mode = VCLOCK_HVCLOCK; - v = (tsc_pg_val - gtod->clock.cycle_last) & - gtod->clock.mask; + v = (tsc_pg_val - clock->cycle_last) & + clock->mask; } else { /* TSC page invalid */ *mode = VCLOCK_NONE; @@ -1900,8 +2104,8 @@ static inline u64 vgettsc(u64 *tsc_timestamp, int *mode) case VCLOCK_TSC: *mode = VCLOCK_TSC; *tsc_timestamp = read_tsc(); - v = (*tsc_timestamp - gtod->clock.cycle_last) & - gtod->clock.mask; + v = (*tsc_timestamp - clock->cycle_last) & + clock->mask; break; default: *mode = VCLOCK_NONE; @@ -1910,10 +2114,10 @@ static inline u64 vgettsc(u64 *tsc_timestamp, int *mode) if (*mode == VCLOCK_NONE) *tsc_timestamp = v = 0; - return v * gtod->clock.mult; + return v * clock->mult; } -static int do_monotonic_boot(s64 *t, u64 *tsc_timestamp) +static int do_monotonic_raw(s64 *t, u64 *tsc_timestamp) { struct pvclock_gtod_data *gtod = &pvclock_gtod_data; unsigned long seq; @@ -1922,10 +2126,10 @@ static int do_monotonic_boot(s64 *t, u64 *tsc_timestamp) do { seq = read_seqcount_begin(>od->seq); - ns = gtod->nsec_base; - ns += vgettsc(tsc_timestamp, &mode); - ns >>= gtod->clock.shift; - ns += gtod->boot_ns; + ns = gtod->raw_clock.base_cycles; + ns += vgettsc(>od->raw_clock, tsc_timestamp, &mode); + ns >>= gtod->raw_clock.shift; + ns += ktime_to_ns(ktime_add(gtod->raw_clock.offset, gtod->offs_boot)); } while (unlikely(read_seqcount_retry(>od->seq, seq))); *t = ns; @@ -1942,8 +2146,8 @@ static int do_realtime(struct timespec64 *ts, u64 *tsc_timestamp) do { seq = read_seqcount_begin(>od->seq); ts->tv_sec = gtod->wall_time_sec; - ns = gtod->nsec_base; - ns += vgettsc(tsc_timestamp, &mode); + ns = gtod->clock.base_cycles; + ns += vgettsc(>od->clock, tsc_timestamp, &mode); ns >>= gtod->clock.shift; } while (unlikely(read_seqcount_retry(>od->seq, seq))); @@ -1960,7 +2164,7 @@ static bool kvm_get_time_and_clockread(s64 *kernel_ns, u64 *tsc_timestamp) if (!gtod_is_based_on_tsc(pvclock_gtod_data.clock.vclock_mode)) return false; - return gtod_is_based_on_tsc(do_monotonic_boot(kernel_ns, + return gtod_is_based_on_tsc(do_monotonic_raw(kernel_ns, tsc_timestamp)); } @@ -2085,7 +2289,7 @@ u64 get_kvmclock_ns(struct kvm *kvm) spin_lock(&ka->pvclock_gtod_sync_lock); if (!ka->use_master_clock) { spin_unlock(&ka->pvclock_gtod_sync_lock); - return ktime_get_boottime_ns() + ka->kvmclock_offset; + return get_kvmclock_base_ns() + ka->kvmclock_offset; } hv_clock.tsc_timestamp = ka->master_cycle_now; @@ -2101,7 +2305,7 @@ u64 get_kvmclock_ns(struct kvm *kvm) &hv_clock.tsc_to_system_mul); ret = __pvclock_read_cycles(&hv_clock, rdtsc()); } else - ret = ktime_get_boottime_ns() + ka->kvmclock_offset; + ret = get_kvmclock_base_ns() + ka->kvmclock_offset; put_cpu(); @@ -2200,7 +2404,7 @@ static int kvm_guest_time_update(struct kvm_vcpu *v) } if (!use_master_clock) { host_tsc = rdtsc(); - kernel_ns = ktime_get_boottime_ns(); + kernel_ns = get_kvmclock_base_ns(); } tsc_timestamp = kvm_read_l1_tsc(v, host_tsc); @@ -2240,6 +2444,7 @@ static int kvm_guest_time_update(struct kvm_vcpu *v) vcpu->hv_clock.tsc_timestamp = tsc_timestamp; vcpu->hv_clock.system_time = kernel_ns + v->kvm->arch.kvmclock_offset; vcpu->last_guest_tsc = tsc_timestamp; + WARN_ON((s64)vcpu->hv_clock.system_time < 0); /* If the host uses TSC clocksource, then it is stable */ pvclock_flags = 0; @@ -2346,7 +2551,10 @@ static int set_msr_mce(struct kvm_vcpu *vcpu, struct msr_data *msr_info) default: if (msr >= MSR_IA32_MC0_CTL && msr < MSR_IA32_MCx_CTL(bank_num)) { - u32 offset = msr - MSR_IA32_MC0_CTL; + u32 offset = array_index_nospec( + msr - MSR_IA32_MC0_CTL, + MSR_IA32_MCx_CTL(bank_num) - MSR_IA32_MC0_CTL); + /* only 0 or all 1s can be written to IA32_MCi_CTL * some Linux kernels though clear bit 10 in bank 4 to * workaround a BIOS/GART TBL issue on AMD K8s, ignore @@ -2431,6 +2639,7 @@ static int kvm_pv_enable_async_pf(struct kvm_vcpu *vcpu, u64 data) static void kvmclock_reset(struct kvm_vcpu *vcpu) { vcpu->arch.pv_time_enabled = false; + vcpu->arch.time = 0; } static void kvm_vcpu_flush_tlb(struct kvm_vcpu *vcpu, bool invalidate_gpa) @@ -2441,43 +2650,47 @@ static void kvm_vcpu_flush_tlb(struct kvm_vcpu *vcpu, bool invalidate_gpa) static void record_steal_time(struct kvm_vcpu *vcpu) { + struct kvm_host_map map; + struct kvm_steal_time *st; + if (!(vcpu->arch.st.msr_val & KVM_MSR_ENABLED)) return; - if (unlikely(kvm_read_guest_cached(vcpu->kvm, &vcpu->arch.st.stime, - &vcpu->arch.st.steal, sizeof(struct kvm_steal_time)))) + /* -EAGAIN is returned in atomic context so we can just return. */ + if (kvm_map_gfn(vcpu, vcpu->arch.st.msr_val >> PAGE_SHIFT, + &map, &vcpu->arch.st.cache, false)) return; + st = map.hva + + offset_in_page(vcpu->arch.st.msr_val & KVM_STEAL_VALID_BITS); + /* * Doing a TLB flush here, on the guest's behalf, can avoid * expensive IPIs. */ - if (xchg(&vcpu->arch.st.steal.preempted, 0) & KVM_VCPU_FLUSH_TLB) + trace_kvm_pv_tlb_flush(vcpu->vcpu_id, + st->preempted & KVM_VCPU_FLUSH_TLB); + if (xchg(&st->preempted, 0) & KVM_VCPU_FLUSH_TLB) kvm_vcpu_flush_tlb(vcpu, false); - if (vcpu->arch.st.steal.version & 1) - vcpu->arch.st.steal.version += 1; /* first time write, random junk */ + vcpu->arch.st.preempted = 0; - vcpu->arch.st.steal.version += 1; + if (st->version & 1) + st->version += 1; /* first time write, random junk */ - kvm_write_guest_cached(vcpu->kvm, &vcpu->arch.st.stime, - &vcpu->arch.st.steal, sizeof(struct kvm_steal_time)); + st->version += 1; smp_wmb(); - vcpu->arch.st.steal.steal += current->sched_info.run_delay - + st->steal += current->sched_info.run_delay - vcpu->arch.st.last_steal; vcpu->arch.st.last_steal = current->sched_info.run_delay; - kvm_write_guest_cached(vcpu->kvm, &vcpu->arch.st.stime, - &vcpu->arch.st.steal, sizeof(struct kvm_steal_time)); - smp_wmb(); - vcpu->arch.st.steal.version += 1; + st->version += 1; - kvm_write_guest_cached(vcpu->kvm, &vcpu->arch.st.stime, - &vcpu->arch.st.steal, sizeof(struct kvm_steal_time)); + kvm_unmap_gfn(vcpu, &map, &vcpu->arch.st.cache, true, false); } int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) @@ -2580,6 +2793,20 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) case MSR_IA32_TSC: kvm_write_tsc(vcpu, msr_info); break; + case MSR_IA32_XSS: + if (!msr_info->host_initiated && + !guest_cpuid_has(vcpu, X86_FEATURE_XSAVES)) + return 1; + /* + * We do support PT if kvm_x86_ops->pt_supported(), but we do + * not support IA32_XSS[bit 8]. Guests will have to use + * RDMSR/WRMSR rather than XSAVES/XRSTORS to save/restore PT + * MSRs. + */ + if (data != 0) + return 1; + vcpu->arch.ia32_xss = data; + break; case MSR_SMI_COUNT: if (!msr_info->host_initiated) return 1; @@ -2594,8 +2821,6 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) case MSR_KVM_SYSTEM_TIME: { struct kvm_arch *ka = &vcpu->kvm->arch; - kvmclock_reset(vcpu); - if (vcpu->vcpu_id == 0 && !msr_info->host_initiated) { bool tmp = (msr == MSR_KVM_SYSTEM_TIME); @@ -2609,14 +2834,13 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) kvm_make_request(KVM_REQ_GLOBAL_CLOCK_UPDATE, vcpu); /* we verify if the enable bit is set... */ + vcpu->arch.pv_time_enabled = false; if (!(data & 1)) break; - if (kvm_gfn_to_hva_cache_init(vcpu->kvm, + if (!kvm_gfn_to_hva_cache_init(vcpu->kvm, &vcpu->arch.pv_time, data & ~1ULL, sizeof(struct pvclock_vcpu_time_info))) - vcpu->arch.pv_time_enabled = false; - else vcpu->arch.pv_time_enabled = true; break; @@ -2633,11 +2857,6 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) if (data & KVM_STEAL_RESERVED_MASK) return 1; - if (kvm_gfn_to_hva_cache_init(vcpu->kvm, &vcpu->arch.st.stime, - data & KVM_STEAL_VALID_BITS, - sizeof(struct kvm_steal_time))) - return 1; - vcpu->arch.st.msr_val = data; if (!(data & KVM_MSR_ENABLED)) @@ -2748,18 +2967,6 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) } EXPORT_SYMBOL_GPL(kvm_set_msr_common); - -/* - * Reads an msr value (of 'msr_index') into 'pdata'. - * Returns 0 on success, non-0 otherwise. - * Assumes vcpu_load() was already called. - */ -int kvm_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr) -{ - return kvm_x86_ops->get_msr(vcpu, msr); -} -EXPORT_SYMBOL_GPL(kvm_get_msr); - static int get_msr_mce(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata, bool host) { u64 data; @@ -2785,7 +2992,10 @@ static int get_msr_mce(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata, bool host) default: if (msr >= MSR_IA32_MC0_CTL && msr < MSR_IA32_MCx_CTL(bank_num)) { - u32 offset = msr - MSR_IA32_MC0_CTL; + u32 offset = array_index_nospec( + msr - MSR_IA32_MC0_CTL, + MSR_IA32_MCx_CTL(bank_num) - MSR_IA32_MC0_CTL); + data = vcpu->arch.mce_banks[offset]; break; } @@ -2922,6 +3132,12 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) case MSR_IA32_MC0_CTL ... MSR_IA32_MCx_CTL(KVM_MAX_MCE_BANKS) - 1: return get_msr_mce(vcpu, msr_info->index, &msr_info->data, msr_info->host_initiated); + case MSR_IA32_XSS: + if (!msr_info->host_initiated && + !guest_cpuid_has(vcpu, X86_FEATURE_XSAVES)) + return 1; + msr_info->data = vcpu->arch.ia32_xss; + break; case MSR_K7_CLK_CTL: /* * Provide expected ramp-up count for K7. All other @@ -3106,7 +3322,6 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_HYPERV_EVENTFD: case KVM_CAP_HYPERV_TLBFLUSH: case KVM_CAP_HYPERV_SEND_IPI: - case KVM_CAP_HYPERV_ENLIGHTENED_VMCS: case KVM_CAP_HYPERV_CPUID: case KVM_CAP_PCI_SEGMENT: case KVM_CAP_DEBUGREGS: @@ -3183,6 +3398,12 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) r = kvm_x86_ops->get_nested_state ? kvm_x86_ops->get_nested_state(NULL, NULL, 0) : 0; break; + case KVM_CAP_HYPERV_DIRECT_TLBFLUSH: + r = kvm_x86_ops->enable_direct_tlbflush != NULL; + break; + case KVM_CAP_HYPERV_ENLIGHTENED_VMCS: + r = kvm_x86_ops->nested_enable_evmcs != NULL; + break; default: break; } @@ -3306,10 +3527,6 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu) kvm_x86_ops->vcpu_load(vcpu, cpu); - fpregs_assert_state_consistent(); - if (test_thread_flag(TIF_NEED_FPU_LOAD)) - switch_fpu_return(); - /* Apply any externally detected TSC adjustments (due to suspend) */ if (unlikely(vcpu->arch.tsc_offset_adjustment)) { adjust_tsc_offset_host(vcpu, vcpu->arch.tsc_offset_adjustment); @@ -3349,15 +3566,25 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu) static void kvm_steal_time_set_preempted(struct kvm_vcpu *vcpu) { + struct kvm_host_map map; + struct kvm_steal_time *st; + if (!(vcpu->arch.st.msr_val & KVM_MSR_ENABLED)) return; - vcpu->arch.st.steal.preempted = KVM_VCPU_PREEMPTED; + if (vcpu->arch.st.preempted) + return; - kvm_write_guest_offset_cached(vcpu->kvm, &vcpu->arch.st.stime, - &vcpu->arch.st.steal.preempted, - offsetof(struct kvm_steal_time, preempted), - sizeof(vcpu->arch.st.steal.preempted)); + if (kvm_map_gfn(vcpu, vcpu->arch.st.msr_val >> PAGE_SHIFT, &map, + &vcpu->arch.st.cache, true)) + return; + + st = map.hva + + offset_in_page(vcpu->arch.st.msr_val & KVM_STEAL_VALID_BITS); + + st->preempted = vcpu->arch.st.preempted = KVM_VCPU_PREEMPTED; + + kvm_unmap_gfn(vcpu, &map, &vcpu->arch.st.cache, true, true); } void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu) @@ -3506,8 +3733,7 @@ static int kvm_vcpu_ioctl_x86_setup_mce(struct kvm_vcpu *vcpu, for (bank = 0; bank < bank_num; bank++) vcpu->arch.mce_banks[bank*4] = ~(u64)0; - if (kvm_x86_ops->setup_mce) - kvm_x86_ops->setup_mce(vcpu); + kvm_x86_ops->setup_mce(vcpu); out: return r; } @@ -3566,6 +3792,21 @@ static void kvm_vcpu_ioctl_x86_get_vcpu_events(struct kvm_vcpu *vcpu, process_nmi(vcpu); /* + * In guest mode, payload delivery should be deferred, + * so that the L1 hypervisor can intercept #PF before + * CR2 is modified (or intercept #DB before DR6 is + * modified under nVMX). Unless the per-VM capability, + * KVM_CAP_EXCEPTION_PAYLOAD, is set, we may not defer the delivery of + * an exception payload and handle after a KVM_GET_VCPU_EVENTS. Since we + * opportunistically defer the exception payload, deliver it if the + * capability hasn't been requested before processing a + * KVM_GET_VCPU_EVENTS. + */ + if (!vcpu->kvm->arch.exception_payload_enabled && + vcpu->arch.exception.pending && vcpu->arch.exception.has_payload) + kvm_deliver_exception_payload(vcpu); + + /* * The API doesn't provide the instruction length for software * exceptions, so don't report them. As long as the guest RIP * isn't advanced, we should expect to encounter the exception @@ -3695,12 +3936,13 @@ static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu, vcpu->arch.hflags |= HF_SMM_INSIDE_NMI_MASK; else vcpu->arch.hflags &= ~HF_SMM_INSIDE_NMI_MASK; - if (lapic_in_kernel(vcpu)) { - if (events->smi.latched_init) - set_bit(KVM_APIC_INIT, &vcpu->arch.apic->pending_events); - else - clear_bit(KVM_APIC_INIT, &vcpu->arch.apic->pending_events); - } + } + + if (lapic_in_kernel(vcpu)) { + if (events->smi.latched_init) + set_bit(KVM_APIC_INIT, &vcpu->arch.apic->pending_events); + else + clear_bit(KVM_APIC_INIT, &vcpu->arch.apic->pending_events); } } @@ -3957,6 +4199,11 @@ static int kvm_vcpu_ioctl_enable_cap(struct kvm_vcpu *vcpu, r = -EFAULT; } return r; + case KVM_CAP_HYPERV_DIRECT_TLBFLUSH: + if (!kvm_x86_ops->enable_direct_tlbflush) + return -ENOTTY; + + return kvm_x86_ops->enable_direct_tlbflush(vcpu); default: return -EINVAL; @@ -4286,6 +4533,7 @@ long kvm_arch_vcpu_ioctl(struct file *filp, case KVM_SET_NESTED_STATE: { struct kvm_nested_state __user *user_kvm_nested_state = argp; struct kvm_nested_state kvm_state; + int idx; r = -EINVAL; if (!kvm_x86_ops->set_nested_state) @@ -4309,7 +4557,9 @@ long kvm_arch_vcpu_ioctl(struct file *filp, && !(kvm_state.flags & KVM_STATE_NESTED_GUEST_MODE)) break; + idx = srcu_read_lock(&vcpu->kvm->srcu); r = kvm_x86_ops->set_nested_state(vcpu, user_kvm_nested_state, &kvm_state); + srcu_read_unlock(&vcpu->kvm->srcu, idx); break; } case KVM_GET_SUPPORTED_HV_CPUID: { @@ -4500,9 +4750,6 @@ static int kvm_vm_ioctl_reinject(struct kvm *kvm, { struct kvm_pit *pit = kvm->arch.vpit; - if (!pit) - return -ENXIO; - /* pit->pit_state.lock was overloaded to prevent userspace from getting * an inconsistent state after running multiple KVM_REINJECT_CONTROL * ioctls in parallel. Use a separate lock if that ioctl isn't rare. @@ -4811,9 +5058,6 @@ set_identity_unlock: if (!irqchip_kernel(kvm)) goto set_irqchip_out; r = kvm_vm_ioctl_set_irqchip(kvm, chip); - if (r) - goto set_irqchip_out; - r = 0; set_irqchip_out: kfree(chip); break; @@ -4872,6 +5116,9 @@ set_identity_unlock: r = -EFAULT; if (copy_from_user(&control, argp, sizeof(control))) goto out; + r = -ENXIO; + if (!kvm->arch.vpit) + goto out; r = kvm_vm_ioctl_reinject(kvm, &control); break; } @@ -4986,18 +5233,28 @@ out: static void kvm_init_msr_list(void) { + struct x86_pmu_capability x86_pmu; u32 dummy[2]; - unsigned i, j; + unsigned i; + + BUILD_BUG_ON_MSG(INTEL_PMC_MAX_FIXED != 4, + "Please update the fixed PMCs in msrs_to_saved_all[]"); + + perf_get_x86_pmu_capability(&x86_pmu); + + num_msrs_to_save = 0; + num_emulated_msrs = 0; + num_msr_based_features = 0; - for (i = j = 0; i < ARRAY_SIZE(msrs_to_save); i++) { - if (rdmsr_safe(msrs_to_save[i], &dummy[0], &dummy[1]) < 0) + for (i = 0; i < ARRAY_SIZE(msrs_to_save_all); i++) { + if (rdmsr_safe(msrs_to_save_all[i], &dummy[0], &dummy[1]) < 0) continue; /* * Even MSRs that are valid in the host may not be exposed * to the guests in some cases. */ - switch (msrs_to_save[i]) { + switch (msrs_to_save_all[i]) { case MSR_IA32_BNDCFGS: if (!kvm_mpx_supported()) continue; @@ -5025,43 +5282,43 @@ static void kvm_init_msr_list(void) break; case MSR_IA32_RTIT_ADDR0_A ... MSR_IA32_RTIT_ADDR3_B: { if (!kvm_x86_ops->pt_supported() || - msrs_to_save[i] - MSR_IA32_RTIT_ADDR0_A >= + msrs_to_save_all[i] - MSR_IA32_RTIT_ADDR0_A >= intel_pt_validate_hw_cap(PT_CAP_num_address_ranges) * 2) continue; break; + case MSR_ARCH_PERFMON_PERFCTR0 ... MSR_ARCH_PERFMON_PERFCTR0 + 17: + if (msrs_to_save_all[i] - MSR_ARCH_PERFMON_PERFCTR0 >= + min(INTEL_PMC_MAX_GENERIC, x86_pmu.num_counters_gp)) + continue; + break; + case MSR_ARCH_PERFMON_EVENTSEL0 ... MSR_ARCH_PERFMON_EVENTSEL0 + 17: + if (msrs_to_save_all[i] - MSR_ARCH_PERFMON_EVENTSEL0 >= + min(INTEL_PMC_MAX_GENERIC, x86_pmu.num_counters_gp)) + continue; } default: break; } - if (j < i) - msrs_to_save[j] = msrs_to_save[i]; - j++; + msrs_to_save[num_msrs_to_save++] = msrs_to_save_all[i]; } - num_msrs_to_save = j; - for (i = j = 0; i < ARRAY_SIZE(emulated_msrs); i++) { - if (!kvm_x86_ops->has_emulated_msr(emulated_msrs[i])) + for (i = 0; i < ARRAY_SIZE(emulated_msrs_all); i++) { + if (!kvm_x86_ops->has_emulated_msr(emulated_msrs_all[i])) continue; - if (j < i) - emulated_msrs[j] = emulated_msrs[i]; - j++; + emulated_msrs[num_emulated_msrs++] = emulated_msrs_all[i]; } - num_emulated_msrs = j; - for (i = j = 0; i < ARRAY_SIZE(msr_based_features); i++) { + for (i = 0; i < ARRAY_SIZE(msr_based_features_all); i++) { struct kvm_msr_entry msr; - msr.index = msr_based_features[i]; + msr.index = msr_based_features_all[i]; if (kvm_get_msr_feature(&msr)) continue; - if (j < i) - msr_based_features[j] = msr_based_features[i]; - j++; + msr_based_features[num_msr_based_features++] = msr_based_features_all[i]; } - num_msr_based_features = j; } static int vcpu_mmio_write(struct kvm_vcpu *vcpu, gpa_t addr, int len, @@ -5312,6 +5569,13 @@ int kvm_write_guest_virt_system(struct kvm_vcpu *vcpu, gva_t addr, void *val, /* kvm_write_guest_virt_system can pull in tons of pages. */ vcpu->arch.l1tf_flush_l1d = true; + /* + * FIXME: this should call handle_emulation_failure if X86EMUL_IO_NEEDED + * is returned, but our callers are not ready for that and they blindly + * call kvm_inject_page_fault. Ensure that they at least do not leak + * uninitialized kernel stack memory into cr2 and error code. + */ + memset(exception, 0, sizeof(*exception)); return kvm_write_guest_virt_helper(addr, val, bytes, vcpu, PFERR_WRITE_MASK, exception); } @@ -5319,25 +5583,20 @@ EXPORT_SYMBOL_GPL(kvm_write_guest_virt_system); int handle_ud(struct kvm_vcpu *vcpu) { + static const char kvm_emulate_prefix[] = { __KVM_EMULATE_PREFIX }; int emul_type = EMULTYPE_TRAP_UD; - enum emulation_result er; char sig[5]; /* ud2; .ascii "kvm" */ struct x86_exception e; if (force_emulation_prefix && kvm_read_guest_virt(vcpu, kvm_get_linear_rip(vcpu), sig, sizeof(sig), &e) == 0 && - memcmp(sig, "\xf\xbkvm", sizeof(sig)) == 0) { + memcmp(sig, kvm_emulate_prefix, sizeof(sig)) == 0) { kvm_rip_write(vcpu, kvm_rip_read(vcpu) + sizeof(sig)); - emul_type = 0; + emul_type = EMULTYPE_TRAP_UD_FORCED; } - er = kvm_emulate_instruction(vcpu, emul_type); - if (er == EMULATE_USER_EXIT) - return 0; - if (er != EMULATE_DONE) - kvm_queue_exception(vcpu, UD_VECTOR); - return 1; + return kvm_emulate_instruction(vcpu, emul_type); } EXPORT_SYMBOL_GPL(handle_ud); @@ -5370,7 +5629,7 @@ static int vcpu_mmio_gva_to_gpa(struct kvm_vcpu *vcpu, unsigned long gva, */ if (vcpu_match_mmio_gva(vcpu, gva) && !permission_fault(vcpu, vcpu->arch.walk_mmu, - vcpu->arch.access, 0, access)) { + vcpu->arch.mmio_access, 0, access)) { *gpa = vcpu->arch.mmio_gfn << PAGE_SHIFT | (gva & (PAGE_SIZE - 1)); trace_vcpu_match_mmio(gva, *gpa, write, false); @@ -5964,28 +6223,13 @@ static void emulator_set_segment(struct x86_emulate_ctxt *ctxt, u16 selector, static int emulator_get_msr(struct x86_emulate_ctxt *ctxt, u32 msr_index, u64 *pdata) { - struct msr_data msr; - int r; - - msr.index = msr_index; - msr.host_initiated = false; - r = kvm_get_msr(emul_to_vcpu(ctxt), &msr); - if (r) - return r; - - *pdata = msr.data; - return 0; + return kvm_get_msr(emul_to_vcpu(ctxt), msr_index, pdata); } static int emulator_set_msr(struct x86_emulate_ctxt *ctxt, u32 msr_index, u64 data) { - struct msr_data msr; - - msr.data = data; - msr.index = msr_index; - msr.host_initiated = false; - return kvm_set_msr(emul_to_vcpu(ctxt), &msr); + return kvm_set_msr(emul_to_vcpu(ctxt), msr_index, data); } static u64 emulator_get_smbase(struct x86_emulate_ctxt *ctxt) @@ -6005,7 +6249,7 @@ static void emulator_set_smbase(struct x86_emulate_ctxt *ctxt, u64 smbase) static int emulator_check_pmc(struct x86_emulate_ctxt *ctxt, u32 pmc) { - return kvm_pmu_is_valid_msr_idx(emul_to_vcpu(ctxt), pmc); + return kvm_pmu_is_valid_rdpmc_ecx(emul_to_vcpu(ctxt), pmc); } static int emulator_read_pmc(struct x86_emulate_ctxt *ctxt, @@ -6032,6 +6276,21 @@ static bool emulator_get_cpuid(struct x86_emulate_ctxt *ctxt, return kvm_cpuid(emul_to_vcpu(ctxt), eax, ebx, ecx, edx, check_limit); } +static bool emulator_guest_has_long_mode(struct x86_emulate_ctxt *ctxt) +{ + return guest_cpuid_has(emul_to_vcpu(ctxt), X86_FEATURE_LM); +} + +static bool emulator_guest_has_movbe(struct x86_emulate_ctxt *ctxt) +{ + return guest_cpuid_has(emul_to_vcpu(ctxt), X86_FEATURE_MOVBE); +} + +static bool emulator_guest_has_fxsr(struct x86_emulate_ctxt *ctxt) +{ + return guest_cpuid_has(emul_to_vcpu(ctxt), X86_FEATURE_FXSR); +} + static ulong emulator_read_gpr(struct x86_emulate_ctxt *ctxt, unsigned reg) { return kvm_register_read(emul_to_vcpu(ctxt), reg); @@ -6068,6 +6327,11 @@ static void emulator_post_leave_smm(struct x86_emulate_ctxt *ctxt) kvm_smm_changed(emul_to_vcpu(ctxt)); } +static int emulator_set_xcr(struct x86_emulate_ctxt *ctxt, u32 index, u64 xcr) +{ + return __kvm_set_xcr(emul_to_vcpu(ctxt), index, xcr); +} + static const struct x86_emulate_ops emulate_ops = { .read_gpr = emulator_read_gpr, .write_gpr = emulator_write_gpr, @@ -6104,11 +6368,15 @@ static const struct x86_emulate_ops emulate_ops = { .fix_hypercall = emulator_fix_hypercall, .intercept = emulator_intercept, .get_cpuid = emulator_get_cpuid, + .guest_has_long_mode = emulator_guest_has_long_mode, + .guest_has_movbe = emulator_guest_has_movbe, + .guest_has_fxsr = emulator_guest_has_fxsr, .set_nmi_mask = emulator_set_nmi_mask, .get_hflags = emulator_get_hflags, .set_hflags = emulator_set_hflags, .pre_leave_smm = emulator_pre_leave_smm, .post_leave_smm = emulator_post_leave_smm, + .set_xcr = emulator_set_xcr, }; static void toggle_interruptibility(struct kvm_vcpu *vcpu, u32 mask) @@ -6168,7 +6436,7 @@ static void init_emulate_ctxt(struct kvm_vcpu *vcpu) vcpu->arch.emulate_regs_need_sync_from_vcpu = false; } -int kvm_inject_realmode_interrupt(struct kvm_vcpu *vcpu, int irq, int inc_eip) +void kvm_inject_realmode_interrupt(struct kvm_vcpu *vcpu, int irq, int inc_eip) { struct x86_emulate_ctxt *ctxt = &vcpu->arch.emulate_ctxt; int ret; @@ -6180,44 +6448,50 @@ int kvm_inject_realmode_interrupt(struct kvm_vcpu *vcpu, int irq, int inc_eip) ctxt->_eip = ctxt->eip + inc_eip; ret = emulate_int_real(ctxt, irq); - if (ret != X86EMUL_CONTINUE) - return EMULATE_FAIL; - - ctxt->eip = ctxt->_eip; - kvm_rip_write(vcpu, ctxt->eip); - kvm_set_rflags(vcpu, ctxt->eflags); - - return EMULATE_DONE; + if (ret != X86EMUL_CONTINUE) { + kvm_make_request(KVM_REQ_TRIPLE_FAULT, vcpu); + } else { + ctxt->eip = ctxt->_eip; + kvm_rip_write(vcpu, ctxt->eip); + kvm_set_rflags(vcpu, ctxt->eflags); + } } EXPORT_SYMBOL_GPL(kvm_inject_realmode_interrupt); static int handle_emulation_failure(struct kvm_vcpu *vcpu, int emulation_type) { - int r = EMULATE_DONE; - ++vcpu->stat.insn_emulation_fail; trace_kvm_emulate_insn_failed(vcpu); - if (emulation_type & EMULTYPE_NO_UD_ON_FAIL) - return EMULATE_FAIL; + if (emulation_type & EMULTYPE_VMWARE_GP) { + kvm_queue_exception_e(vcpu, GP_VECTOR, 0); + return 1; + } - if (!is_guest_mode(vcpu) && kvm_x86_ops->get_cpl(vcpu) == 0) { + if (emulation_type & EMULTYPE_SKIP) { vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR; vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_EMULATION; vcpu->run->internal.ndata = 0; - r = EMULATE_USER_EXIT; + return 0; } kvm_queue_exception(vcpu, UD_VECTOR); - return r; + if (!is_guest_mode(vcpu) && kvm_x86_ops->get_cpl(vcpu) == 0) { + vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR; + vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_EMULATION; + vcpu->run->internal.ndata = 0; + return 0; + } + + return 1; } -static bool reexecute_instruction(struct kvm_vcpu *vcpu, gva_t cr2, +static bool reexecute_instruction(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, bool write_fault_to_shadow_pgtable, int emulation_type) { - gpa_t gpa = cr2; + gpa_t gpa = cr2_or_gpa; kvm_pfn_t pfn; if (!(emulation_type & EMULTYPE_ALLOW_RETRY)) @@ -6231,7 +6505,7 @@ static bool reexecute_instruction(struct kvm_vcpu *vcpu, gva_t cr2, * Write permission should be allowed since only * write access need to be emulated. */ - gpa = kvm_mmu_gva_to_gpa_write(vcpu, cr2, NULL); + gpa = kvm_mmu_gva_to_gpa_write(vcpu, cr2_or_gpa, NULL); /* * If the mapping is invalid in guest, let cpu retry @@ -6288,10 +6562,10 @@ static bool reexecute_instruction(struct kvm_vcpu *vcpu, gva_t cr2, } static bool retry_instruction(struct x86_emulate_ctxt *ctxt, - unsigned long cr2, int emulation_type) + gpa_t cr2_or_gpa, int emulation_type) { struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt); - unsigned long last_retry_eip, last_retry_addr, gpa = cr2; + unsigned long last_retry_eip, last_retry_addr, gpa = cr2_or_gpa; last_retry_eip = vcpu->arch.last_retry_eip; last_retry_addr = vcpu->arch.last_retry_addr; @@ -6320,14 +6594,14 @@ static bool retry_instruction(struct x86_emulate_ctxt *ctxt, if (x86_page_table_writing_insn(ctxt)) return false; - if (ctxt->eip == last_retry_eip && last_retry_addr == cr2) + if (ctxt->eip == last_retry_eip && last_retry_addr == cr2_or_gpa) return false; vcpu->arch.last_retry_eip = ctxt->eip; - vcpu->arch.last_retry_addr = cr2; + vcpu->arch.last_retry_addr = cr2_or_gpa; if (!vcpu->arch.mmu->direct_map) - gpa = kvm_mmu_gva_to_gpa_write(vcpu, cr2, NULL); + gpa = kvm_mmu_gva_to_gpa_write(vcpu, cr2_or_gpa, NULL); kvm_mmu_unprotect_page(vcpu->kvm, gpa_to_gfn(gpa)); @@ -6365,7 +6639,7 @@ static int kvm_vcpu_check_hw_bp(unsigned long addr, u32 type, u32 dr7, return dr6; } -static void kvm_vcpu_do_singlestep(struct kvm_vcpu *vcpu, int *r) +static int kvm_vcpu_do_singlestep(struct kvm_vcpu *vcpu) { struct kvm_run *kvm_run = vcpu->run; @@ -6374,18 +6648,20 @@ static void kvm_vcpu_do_singlestep(struct kvm_vcpu *vcpu, int *r) kvm_run->debug.arch.pc = vcpu->arch.singlestep_rip; kvm_run->debug.arch.exception = DB_VECTOR; kvm_run->exit_reason = KVM_EXIT_DEBUG; - *r = EMULATE_USER_EXIT; - } else { - kvm_queue_exception_p(vcpu, DB_VECTOR, DR6_BS); + return 0; } + kvm_queue_exception_p(vcpu, DB_VECTOR, DR6_BS); + return 1; } int kvm_skip_emulated_instruction(struct kvm_vcpu *vcpu) { unsigned long rflags = kvm_x86_ops->get_rflags(vcpu); - int r = EMULATE_DONE; + int r; - kvm_x86_ops->skip_emulated_instruction(vcpu); + r = kvm_x86_ops->skip_emulated_instruction(vcpu); + if (unlikely(!r)) + return 0; /* * rflags is the old, "raw" value of the flags. The new value has @@ -6396,8 +6672,8 @@ int kvm_skip_emulated_instruction(struct kvm_vcpu *vcpu) * that sets the TF flag". */ if (unlikely(rflags & X86_EFLAGS_TF)) - kvm_vcpu_do_singlestep(vcpu, &r); - return r == EMULATE_DONE; + r = kvm_vcpu_do_singlestep(vcpu); + return r; } EXPORT_SYMBOL_GPL(kvm_skip_emulated_instruction); @@ -6416,7 +6692,7 @@ static bool kvm_vcpu_check_breakpoint(struct kvm_vcpu *vcpu, int *r) kvm_run->debug.arch.pc = eip; kvm_run->debug.arch.exception = DB_VECTOR; kvm_run->exit_reason = KVM_EXIT_DEBUG; - *r = EMULATE_USER_EXIT; + *r = 0; return true; } } @@ -6432,7 +6708,7 @@ static bool kvm_vcpu_check_breakpoint(struct kvm_vcpu *vcpu, int *r) vcpu->arch.dr6 &= ~DR_TRAP_BITS; vcpu->arch.dr6 |= dr6 | DR6_RTM; kvm_queue_exception(vcpu, DB_VECTOR); - *r = EMULATE_DONE; + *r = 1; return true; } } @@ -6471,11 +6747,8 @@ static bool is_vmware_backdoor_opcode(struct x86_emulate_ctxt *ctxt) return false; } -int x86_emulate_instruction(struct kvm_vcpu *vcpu, - unsigned long cr2, - int emulation_type, - void *insn, - int insn_len) +int x86_emulate_instruction(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, + int emulation_type, void *insn, int insn_len) { int r; struct x86_emulate_ctxt *ctxt = &vcpu->arch.emulate_ctxt; @@ -6516,32 +6789,49 @@ int x86_emulate_instruction(struct kvm_vcpu *vcpu, trace_kvm_emulate_insn_start(vcpu); ++vcpu->stat.insn_emulation; if (r != EMULATION_OK) { - if (emulation_type & EMULTYPE_TRAP_UD) - return EMULATE_FAIL; - if (reexecute_instruction(vcpu, cr2, write_fault_to_spt, - emulation_type)) - return EMULATE_DONE; - if (ctxt->have_exception && inject_emulated_exception(vcpu)) - return EMULATE_DONE; - if (emulation_type & EMULTYPE_SKIP) - return EMULATE_FAIL; + if ((emulation_type & EMULTYPE_TRAP_UD) || + (emulation_type & EMULTYPE_TRAP_UD_FORCED)) { + kvm_queue_exception(vcpu, UD_VECTOR); + return 1; + } + if (reexecute_instruction(vcpu, cr2_or_gpa, + write_fault_to_spt, + emulation_type)) + return 1; + if (ctxt->have_exception) { + /* + * #UD should result in just EMULATION_FAILED, and trap-like + * exception should not be encountered during decode. + */ + WARN_ON_ONCE(ctxt->exception.vector == UD_VECTOR || + exception_type(ctxt->exception.vector) == EXCPT_TRAP); + inject_emulated_exception(vcpu); + return 1; + } return handle_emulation_failure(vcpu, emulation_type); } } - if ((emulation_type & EMULTYPE_VMWARE) && - !is_vmware_backdoor_opcode(ctxt)) - return EMULATE_FAIL; + if ((emulation_type & EMULTYPE_VMWARE_GP) && + !is_vmware_backdoor_opcode(ctxt)) { + kvm_queue_exception_e(vcpu, GP_VECTOR, 0); + return 1; + } + /* + * Note, EMULTYPE_SKIP is intended for use *only* by vendor callbacks + * for kvm_skip_emulated_instruction(). The caller is responsible for + * updating interruptibility state and injecting single-step #DBs. + */ if (emulation_type & EMULTYPE_SKIP) { kvm_rip_write(vcpu, ctxt->_eip); if (ctxt->eflags & X86_EFLAGS_RF) kvm_set_rflags(vcpu, ctxt->eflags & ~X86_EFLAGS_RF); - return EMULATE_DONE; + return 1; } - if (retry_instruction(ctxt, cr2, emulation_type)) - return EMULATE_DONE; + if (retry_instruction(ctxt, cr2_or_gpa, emulation_type)) + return 1; /* this is needed for vmware backdoor interface to work since it changes registers values during IO operation */ @@ -6552,23 +6842,23 @@ int x86_emulate_instruction(struct kvm_vcpu *vcpu, restart: /* Save the faulting GPA (cr2) in the address field */ - ctxt->exception.address = cr2; + ctxt->exception.address = cr2_or_gpa; r = x86_emulate_insn(ctxt); if (r == EMULATION_INTERCEPTED) - return EMULATE_DONE; + return 1; if (r == EMULATION_FAILED) { - if (reexecute_instruction(vcpu, cr2, write_fault_to_spt, + if (reexecute_instruction(vcpu, cr2_or_gpa, write_fault_to_spt, emulation_type)) - return EMULATE_DONE; + return 1; return handle_emulation_failure(vcpu, emulation_type); } if (ctxt->have_exception) { - r = EMULATE_DONE; + r = 1; if (inject_emulated_exception(vcpu)) return r; } else if (vcpu->arch.pio.count) { @@ -6579,27 +6869,30 @@ restart: writeback = false; vcpu->arch.complete_userspace_io = complete_emulated_pio; } - r = EMULATE_USER_EXIT; + r = 0; } else if (vcpu->mmio_needed) { + ++vcpu->stat.mmio_exits; + if (!vcpu->mmio_is_write) writeback = false; - r = EMULATE_USER_EXIT; + r = 0; vcpu->arch.complete_userspace_io = complete_emulated_mmio; } else if (r == EMULATION_RESTART) goto restart; else - r = EMULATE_DONE; + r = 1; if (writeback) { unsigned long rflags = kvm_x86_ops->get_rflags(vcpu); toggle_interruptibility(vcpu, ctxt->interruptibility); vcpu->arch.emulate_regs_need_sync_to_vcpu = false; - kvm_rip_write(vcpu, ctxt->eip); - if (r == EMULATE_DONE && ctxt->tf) - kvm_vcpu_do_singlestep(vcpu, &r); if (!ctxt->have_exception || - exception_type(ctxt->exception.vector) == EXCPT_TRAP) + exception_type(ctxt->exception.vector) == EXCPT_TRAP) { + kvm_rip_write(vcpu, ctxt->eip); + if (r && ctxt->tf) + r = kvm_vcpu_do_singlestep(vcpu); __kvm_set_rflags(vcpu, ctxt->eflags); + } /* * For STI, interrupts are shadowed; so KVM_REQ_EVENT will @@ -7170,8 +7463,8 @@ static void kvm_pv_kick_cpu_op(struct kvm *kvm, unsigned long flags, int apicid) { struct kvm_lapic_irq lapic_irq; - lapic_irq.shorthand = 0; - lapic_irq.dest_mode = 0; + lapic_irq.shorthand = APIC_DEST_NOSHORT; + lapic_irq.dest_mode = APIC_DEST_PHYSICAL; lapic_irq.level = 0; lapic_irq.dest_id = apicid; lapic_irq.msi_redir_hint = false; @@ -7180,18 +7473,22 @@ static void kvm_pv_kick_cpu_op(struct kvm *kvm, unsigned long flags, int apicid) kvm_irq_delivery_to_apic(kvm, NULL, &lapic_irq, NULL); } -void kvm_vcpu_deactivate_apicv(struct kvm_vcpu *vcpu) +bool kvm_apicv_activated(struct kvm *kvm) { - if (!lapic_in_kernel(vcpu)) { - WARN_ON_ONCE(vcpu->arch.apicv_active); - return; - } - if (!vcpu->arch.apicv_active) - return; + return (READ_ONCE(kvm->arch.apicv_inhibit_reasons) == 0); +} +EXPORT_SYMBOL_GPL(kvm_apicv_activated); - vcpu->arch.apicv_active = false; - kvm_x86_ops->refresh_apicv_exec_ctrl(vcpu); +void kvm_apicv_init(struct kvm *kvm, bool enable) +{ + if (enable) + clear_bit(APICV_INHIBIT_REASON_DISABLE, + &kvm->arch.apicv_inhibit_reasons); + else + set_bit(APICV_INHIBIT_REASON_DISABLE, + &kvm->arch.apicv_inhibit_reasons); } +EXPORT_SYMBOL_GPL(kvm_apicv_init); static void kvm_sched_yield(struct kvm *kvm, unsigned long dest_id) { @@ -7702,11 +7999,65 @@ static void process_smi(struct kvm_vcpu *vcpu) kvm_make_request(KVM_REQ_EVENT, vcpu); } +void kvm_make_scan_ioapic_request_mask(struct kvm *kvm, + unsigned long *vcpu_bitmap) +{ + cpumask_var_t cpus; + + zalloc_cpumask_var(&cpus, GFP_ATOMIC); + + kvm_make_vcpus_request_mask(kvm, KVM_REQ_SCAN_IOAPIC, + vcpu_bitmap, cpus); + + free_cpumask_var(cpus); +} + void kvm_make_scan_ioapic_request(struct kvm *kvm) { kvm_make_all_cpus_request(kvm, KVM_REQ_SCAN_IOAPIC); } +void kvm_vcpu_update_apicv(struct kvm_vcpu *vcpu) +{ + if (!lapic_in_kernel(vcpu)) + return; + + vcpu->arch.apicv_active = kvm_apicv_activated(vcpu->kvm); + kvm_apic_update_apicv(vcpu); + kvm_x86_ops->refresh_apicv_exec_ctrl(vcpu); +} +EXPORT_SYMBOL_GPL(kvm_vcpu_update_apicv); + +/* + * NOTE: Do not hold any lock prior to calling this. + * + * In particular, kvm_request_apicv_update() expects kvm->srcu not to be + * locked, because it calls __x86_set_memory_region() which does + * synchronize_srcu(&kvm->srcu). + */ +void kvm_request_apicv_update(struct kvm *kvm, bool activate, ulong bit) +{ + if (!kvm_x86_ops->check_apicv_inhibit_reasons || + !kvm_x86_ops->check_apicv_inhibit_reasons(bit)) + return; + + if (activate) { + if (!test_and_clear_bit(bit, &kvm->arch.apicv_inhibit_reasons) || + !kvm_apicv_activated(kvm)) + return; + } else { + if (test_and_set_bit(bit, &kvm->arch.apicv_inhibit_reasons) || + kvm_apicv_activated(kvm)) + return; + } + + trace_kvm_apicv_update_request(activate, bit); + if (kvm_x86_ops->pre_update_apicv_exec_ctrl) + kvm_x86_ops->pre_update_apicv_exec_ctrl(kvm, activate); + kvm_make_all_cpus_request(kvm, KVM_REQ_APICV_UPDATE); +} +EXPORT_SYMBOL_GPL(kvm_request_apicv_update); + static void vcpu_scan_ioapic(struct kvm_vcpu *vcpu) { if (!kvm_apic_present(vcpu)) @@ -7779,7 +8130,6 @@ void kvm_vcpu_reload_apic_access_page(struct kvm_vcpu *vcpu) */ put_page(page); } -EXPORT_SYMBOL_GPL(kvm_vcpu_reload_apic_access_page); void __kvm_request_immediate_exit(struct kvm_vcpu *vcpu) { @@ -7798,12 +8148,17 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) bool req_int_win = dm_request_for_irq_injection(vcpu) && kvm_cpu_accept_dm_intr(vcpu); + enum exit_fastpath_completion exit_fastpath = EXIT_FASTPATH_NONE; bool req_immediate_exit = false; if (kvm_request_pending(vcpu)) { - if (kvm_check_request(KVM_REQ_GET_VMCS12_PAGES, vcpu)) - kvm_x86_ops->get_vmcs12_pages(vcpu); + if (kvm_check_request(KVM_REQ_GET_VMCS12_PAGES, vcpu)) { + if (unlikely(!kvm_x86_ops->get_vmcs12_pages(vcpu))) { + r = 0; + goto out; + } + } if (kvm_check_request(KVM_REQ_MMU_RELOAD, vcpu)) kvm_mmu_unload(vcpu); if (kvm_check_request(KVM_REQ_MIGRATE_TIMER, vcpu)) @@ -7893,6 +8248,8 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) */ if (kvm_check_request(KVM_REQ_HV_STIMER, vcpu)) kvm_hv_process_stimers(vcpu); + if (kvm_check_request(KVM_REQ_APICV_UPDATE, vcpu)) + kvm_vcpu_update_apicv(vcpu); } if (kvm_check_request(KVM_REQ_EVENT, vcpu) || req_int_win) { @@ -7995,8 +8352,9 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) trace_kvm_entry(vcpu->vcpu_id); guest_enter_irqoff(); - /* The preempt notifier should have taken care of the FPU already. */ - WARN_ON_ONCE(test_thread_flag(TIF_NEED_FPU_LOAD)); + fpregs_assert_state_consistent(); + if (test_thread_flag(TIF_NEED_FPU_LOAD)) + switch_fpu_return(); if (unlikely(vcpu->arch.switch_db_regs)) { set_debugreg(0, 7); @@ -8040,7 +8398,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) vcpu->mode = OUTSIDE_GUEST_MODE; smp_wmb(); - kvm_x86_ops->handle_exit_irqoff(vcpu); + kvm_x86_ops->handle_exit_irqoff(vcpu, &exit_fastpath); /* * Consume any pending interrupts, including the possible source of @@ -8084,7 +8442,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) kvm_lapic_sync_from_vapic(vcpu); vcpu->arch.gpa_available = false; - r = kvm_x86_ops->handle_exit(vcpu); + r = kvm_x86_ops->handle_exit(vcpu, exit_fastpath); return r; cancel_injection: @@ -8191,12 +8549,11 @@ static int vcpu_run(struct kvm_vcpu *vcpu) static inline int complete_emulated_io(struct kvm_vcpu *vcpu) { int r; + vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu); r = kvm_emulate_instruction(vcpu, EMULTYPE_NO_DECODE); srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx); - if (r != EMULATE_DONE) - return 0; - return 1; + return r; } static int complete_emulated_pio(struct kvm_vcpu *vcpu) @@ -8269,12 +8626,26 @@ static int complete_emulated_mmio(struct kvm_vcpu *vcpu) return 0; } +static void kvm_save_current_fpu(struct fpu *fpu) +{ + /* + * If the target FPU state is not resident in the CPU registers, just + * memcpy() from current, else save CPU state directly to the target. + */ + if (test_thread_flag(TIF_NEED_FPU_LOAD)) + memcpy(&fpu->state, ¤t->thread.fpu.state, + fpu_kernel_xstate_size); + else + copy_fpregs_to_fpstate(fpu); +} + /* Swap (qemu) user FPU context for the guest FPU context. */ static void kvm_load_guest_fpu(struct kvm_vcpu *vcpu) { fpregs_lock(); - copy_fpregs_to_fpstate(vcpu->arch.user_fpu); + kvm_save_current_fpu(vcpu->arch.user_fpu); + /* PKRU is separately restored in kvm_x86_ops->run. */ __copy_kernel_to_fpregs(&vcpu->arch.guest_fpu->state, ~XFEATURE_MASK_PKRU); @@ -8290,7 +8661,8 @@ static void kvm_put_guest_fpu(struct kvm_vcpu *vcpu) { fpregs_lock(); - copy_fpregs_to_fpstate(vcpu->arch.guest_fpu); + kvm_save_current_fpu(vcpu->arch.guest_fpu); + copy_kernel_to_fpregs(&vcpu->arch.user_fpu->state); fpregs_mark_activate(); @@ -8512,6 +8884,8 @@ int kvm_arch_vcpu_ioctl_get_mpstate(struct kvm_vcpu *vcpu, struct kvm_mp_state *mp_state) { vcpu_load(vcpu); + if (kvm_mpx_supported()) + kvm_load_guest_fpu(vcpu); kvm_apic_accept_events(vcpu); if (vcpu->arch.mp_state == KVM_MP_STATE_HALTED && @@ -8520,6 +8894,8 @@ int kvm_arch_vcpu_ioctl_get_mpstate(struct kvm_vcpu *vcpu, else mp_state->mp_state = vcpu->arch.mp_state; + if (kvm_mpx_supported()) + kvm_put_guest_fpu(vcpu); vcpu_put(vcpu); return 0; } @@ -8535,8 +8911,12 @@ int kvm_arch_vcpu_ioctl_set_mpstate(struct kvm_vcpu *vcpu, mp_state->mp_state != KVM_MP_STATE_RUNNABLE) goto out; - /* INITs are latched while in SMM */ - if ((is_smm(vcpu) || vcpu->arch.smi_pending) && + /* + * KVM_MP_STATE_INIT_RECEIVED means the processor is in + * INIT state; latched init should be reported using + * KVM_SET_VCPU_EVENTS, so reject it here. + */ + if ((kvm_vcpu_latch_init(vcpu) || vcpu->arch.smi_pending) && (mp_state->mp_state == KVM_MP_STATE_SIPI_RECEIVED || mp_state->mp_state == KVM_MP_STATE_INIT_RECEIVED)) goto out; @@ -8564,23 +8944,21 @@ int kvm_task_switch(struct kvm_vcpu *vcpu, u16 tss_selector, int idt_index, ret = emulator_task_switch(ctxt, tss_selector, idt_index, reason, has_error_code, error_code); - - if (ret) - return EMULATE_FAIL; + if (ret) { + vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR; + vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_EMULATION; + vcpu->run->internal.ndata = 0; + return 0; + } kvm_rip_write(vcpu, ctxt->eip); kvm_set_rflags(vcpu, ctxt->eflags); - kvm_make_request(KVM_REQ_EVENT, vcpu); - return EMULATE_DONE; + return 1; } EXPORT_SYMBOL_GPL(kvm_task_switch); static int kvm_valid_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs) { - if (!guest_cpuid_has(vcpu, X86_FEATURE_XSAVE) && - (sregs->cr4 & X86_CR4_OSXSAVE)) - return -EINVAL; - if ((sregs->efer & EFER_LME) && (sregs->cr0 & X86_CR0_PG)) { /* * When EFER.LME and CR0.PG are set, the processor is in @@ -8599,7 +8977,7 @@ static int kvm_valid_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs) return -EINVAL; } - return 0; + return kvm_valid_cr4(vcpu, sregs->cr4); } static int __set_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs) @@ -8629,7 +9007,7 @@ static int __set_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs) vcpu->arch.cr2 = sregs->cr2; mmu_reset_needed |= kvm_read_cr3(vcpu) != sregs->cr3; vcpu->arch.cr3 = sregs->cr3; - __set_bit(VCPU_EXREG_CR3, (ulong *)&vcpu->arch.regs_avail); + kvm_register_mark_available(vcpu, VCPU_EXREG_CR3); kvm_set_cr8(vcpu, sregs->cr8); @@ -8877,33 +9255,91 @@ static void fx_init(struct kvm_vcpu *vcpu) vcpu->arch.cr0 |= X86_CR0_ET; } -void kvm_arch_vcpu_free(struct kvm_vcpu *vcpu) +int kvm_arch_vcpu_precreate(struct kvm *kvm, unsigned int id) { - void *wbinvd_dirty_mask = vcpu->arch.wbinvd_dirty_mask; - - kvmclock_reset(vcpu); + if (kvm_check_tsc_unstable() && atomic_read(&kvm->online_vcpus) != 0) + pr_warn_once("kvm: SMP vm created on host with unstable TSC; " + "guest TSC will not be reliable\n"); - kvm_x86_ops->vcpu_free(vcpu); - free_cpumask_var(wbinvd_dirty_mask); + return 0; } -struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm, - unsigned int id) +int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu) { - struct kvm_vcpu *vcpu; + struct page *page; + int r; - if (kvm_check_tsc_unstable() && atomic_read(&kvm->online_vcpus) != 0) - printk_once(KERN_WARNING - "kvm: SMP vm created on host with unstable TSC; " - "guest TSC will not be reliable\n"); + vcpu->arch.emulate_ctxt.ops = &emulate_ops; + if (!irqchip_in_kernel(vcpu->kvm) || kvm_vcpu_is_reset_bsp(vcpu)) + vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE; + else + vcpu->arch.mp_state = KVM_MP_STATE_UNINITIALIZED; - vcpu = kvm_x86_ops->vcpu_create(kvm, id); + kvm_set_tsc_khz(vcpu, max_tsc_khz); - return vcpu; -} + r = kvm_mmu_create(vcpu); + if (r < 0) + return r; + + if (irqchip_in_kernel(vcpu->kvm)) { + r = kvm_create_lapic(vcpu, lapic_timer_advance_ns); + if (r < 0) + goto fail_mmu_destroy; + if (kvm_apicv_activated(vcpu->kvm)) + vcpu->arch.apicv_active = true; + } else + static_key_slow_inc(&kvm_no_apic_vcpu); + + r = -ENOMEM; + + page = alloc_page(GFP_KERNEL | __GFP_ZERO); + if (!page) + goto fail_free_lapic; + vcpu->arch.pio_data = page_address(page); + + vcpu->arch.mce_banks = kzalloc(KVM_MAX_MCE_BANKS * sizeof(u64) * 4, + GFP_KERNEL_ACCOUNT); + if (!vcpu->arch.mce_banks) + goto fail_free_pio_data; + vcpu->arch.mcg_cap = KVM_MAX_MCE_BANKS; + + if (!zalloc_cpumask_var(&vcpu->arch.wbinvd_dirty_mask, + GFP_KERNEL_ACCOUNT)) + goto fail_free_mce_banks; + + vcpu->arch.user_fpu = kmem_cache_zalloc(x86_fpu_cache, + GFP_KERNEL_ACCOUNT); + if (!vcpu->arch.user_fpu) { + pr_err("kvm: failed to allocate userspace's fpu\n"); + goto free_wbinvd_dirty_mask; + } + + vcpu->arch.guest_fpu = kmem_cache_zalloc(x86_fpu_cache, + GFP_KERNEL_ACCOUNT); + if (!vcpu->arch.guest_fpu) { + pr_err("kvm: failed to allocate vcpu's fpu\n"); + goto free_user_fpu; + } + fx_init(vcpu); + + vcpu->arch.guest_xstate_size = XSAVE_HDR_SIZE + XSAVE_HDR_OFFSET; + + vcpu->arch.maxphyaddr = cpuid_query_maxphyaddr(vcpu); + + vcpu->arch.pat = MSR_IA32_CR_PAT_DEFAULT; + + kvm_async_pf_hash_reset(vcpu); + kvm_pmu_init(vcpu); + + vcpu->arch.pending_external_vector = -1; + vcpu->arch.preempted_in_kernel = false; + + kvm_hv_vcpu_init(vcpu); + + r = kvm_x86_ops->vcpu_create(vcpu); + if (r) + goto free_guest_fpu; -int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu) -{ vcpu->arch.arch_capabilities = kvm_get_arch_capabilities(); vcpu->arch.msr_platform_info = MSR_PLATFORM_INFO_CPUID_FAULT; kvm_vcpu_mtrr_init(vcpu); @@ -8912,6 +9348,22 @@ int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu) kvm_init_mmu(vcpu, false); vcpu_put(vcpu); return 0; + +free_guest_fpu: + kmem_cache_free(x86_fpu_cache, vcpu->arch.guest_fpu); +free_user_fpu: + kmem_cache_free(x86_fpu_cache, vcpu->arch.user_fpu); +free_wbinvd_dirty_mask: + free_cpumask_var(vcpu->arch.wbinvd_dirty_mask); +fail_free_mce_banks: + kfree(vcpu->arch.mce_banks); +fail_free_pio_data: + free_page((unsigned long)vcpu->arch.pio_data); +fail_free_lapic: + kvm_free_lapic(vcpu); +fail_mmu_destroy: + kvm_mmu_destroy(vcpu); + return r; } void kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu) @@ -8944,13 +9396,29 @@ void kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu) void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu) { - vcpu->arch.apf.msr_val = 0; + struct gfn_to_pfn_cache *cache = &vcpu->arch.st.cache; + int idx; - vcpu_load(vcpu); - kvm_mmu_unload(vcpu); - vcpu_put(vcpu); + kvm_release_pfn(cache->pfn, cache->dirty, cache); + + kvmclock_reset(vcpu); kvm_x86_ops->vcpu_free(vcpu); + + free_cpumask_var(vcpu->arch.wbinvd_dirty_mask); + kmem_cache_free(x86_fpu_cache, vcpu->arch.user_fpu); + kmem_cache_free(x86_fpu_cache, vcpu->arch.guest_fpu); + + kvm_hv_vcpu_uninit(vcpu); + kvm_pmu_destroy(vcpu); + kfree(vcpu->arch.mce_banks); + kvm_free_lapic(vcpu); + idx = srcu_read_lock(&vcpu->kvm->srcu); + kvm_mmu_destroy(vcpu); + srcu_read_unlock(&vcpu->kvm->srcu, idx); + free_page((unsigned long)vcpu->arch.pio_data); + if (!lapic_in_kernel(vcpu)) + static_key_slow_dec(&kvm_no_apic_vcpu); } void kvm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) @@ -8966,7 +9434,6 @@ void kvm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) vcpu->arch.nmi_injected = false; kvm_clear_interrupt_queue(vcpu); kvm_clear_exception_queue(vcpu); - vcpu->arch.exception.pending = false; memset(vcpu->arch.db, 0, sizeof(vcpu->arch.db)); kvm_update_dr0123(vcpu); @@ -9142,6 +9609,8 @@ int kvm_arch_hardware_setup(void) if (r != 0) return r; + cr4_reserved_bits = kvm_host_cr4_reserved_bits(&boot_cpu_data); + if (kvm_has_tsc_control) { /* * Make sure the user can only configure tsc_khz values that @@ -9156,6 +9625,9 @@ int kvm_arch_hardware_setup(void) kvm_default_tsc_scaling_ratio = 1ULL << kvm_tsc_scaling_ratio_frac_bits; } + if (boot_cpu_has(X86_FEATURE_XSAVES)) + rdmsrl(MSR_IA32_XSS, host_xss); + kvm_init_msr_list(); return 0; } @@ -9167,6 +9639,13 @@ void kvm_arch_hardware_unsetup(void) int kvm_arch_check_processor_compat(void) { + struct cpuinfo_x86 *c = &cpu_data(smp_processor_id()); + + WARN_ON(!irqs_disabled()); + + if (kvm_host_cr4_reserved_bits(c) != cr4_reserved_bits) + return -EIO; + return kvm_x86_ops->check_processor_compatibility(); } @@ -9184,101 +9663,15 @@ bool kvm_vcpu_is_bsp(struct kvm_vcpu *vcpu) struct static_key kvm_no_apic_vcpu __read_mostly; EXPORT_SYMBOL_GPL(kvm_no_apic_vcpu); -int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu) -{ - struct page *page; - int r; - - vcpu->arch.emulate_ctxt.ops = &emulate_ops; - if (!irqchip_in_kernel(vcpu->kvm) || kvm_vcpu_is_reset_bsp(vcpu)) - vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE; - else - vcpu->arch.mp_state = KVM_MP_STATE_UNINITIALIZED; - - page = alloc_page(GFP_KERNEL | __GFP_ZERO); - if (!page) { - r = -ENOMEM; - goto fail; - } - vcpu->arch.pio_data = page_address(page); - - kvm_set_tsc_khz(vcpu, max_tsc_khz); - - r = kvm_mmu_create(vcpu); - if (r < 0) - goto fail_free_pio_data; - - if (irqchip_in_kernel(vcpu->kvm)) { - vcpu->arch.apicv_active = kvm_x86_ops->get_enable_apicv(vcpu); - r = kvm_create_lapic(vcpu, lapic_timer_advance_ns); - if (r < 0) - goto fail_mmu_destroy; - } else - static_key_slow_inc(&kvm_no_apic_vcpu); - - vcpu->arch.mce_banks = kzalloc(KVM_MAX_MCE_BANKS * sizeof(u64) * 4, - GFP_KERNEL_ACCOUNT); - if (!vcpu->arch.mce_banks) { - r = -ENOMEM; - goto fail_free_lapic; - } - vcpu->arch.mcg_cap = KVM_MAX_MCE_BANKS; - - if (!zalloc_cpumask_var(&vcpu->arch.wbinvd_dirty_mask, - GFP_KERNEL_ACCOUNT)) { - r = -ENOMEM; - goto fail_free_mce_banks; - } - - fx_init(vcpu); - - vcpu->arch.guest_xstate_size = XSAVE_HDR_SIZE + XSAVE_HDR_OFFSET; - - vcpu->arch.maxphyaddr = cpuid_query_maxphyaddr(vcpu); - - vcpu->arch.pat = MSR_IA32_CR_PAT_DEFAULT; - - kvm_async_pf_hash_reset(vcpu); - kvm_pmu_init(vcpu); - - vcpu->arch.pending_external_vector = -1; - vcpu->arch.preempted_in_kernel = false; - - kvm_hv_vcpu_init(vcpu); - - return 0; - -fail_free_mce_banks: - kfree(vcpu->arch.mce_banks); -fail_free_lapic: - kvm_free_lapic(vcpu); -fail_mmu_destroy: - kvm_mmu_destroy(vcpu); -fail_free_pio_data: - free_page((unsigned long)vcpu->arch.pio_data); -fail: - return r; -} - -void kvm_arch_vcpu_uninit(struct kvm_vcpu *vcpu) -{ - int idx; - - kvm_hv_vcpu_uninit(vcpu); - kvm_pmu_destroy(vcpu); - kfree(vcpu->arch.mce_banks); - kvm_free_lapic(vcpu); - idx = srcu_read_lock(&vcpu->kvm->srcu); - kvm_mmu_destroy(vcpu); - srcu_read_unlock(&vcpu->kvm->srcu, idx); - free_page((unsigned long)vcpu->arch.pio_data); - if (!lapic_in_kernel(vcpu)) - static_key_slow_dec(&kvm_no_apic_vcpu); -} - void kvm_arch_sched_in(struct kvm_vcpu *vcpu, int cpu) { + struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); + vcpu->arch.l1tf_flush_l1d = true; + if (pmu->version && unlikely(pmu->event_count)) { + pmu->need_cleanup = true; + kvm_make_request(KVM_REQ_PMU, vcpu); + } kvm_x86_ops->sched_in(vcpu, cpu); } @@ -9289,6 +9682,8 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) INIT_HLIST_HEAD(&kvm->arch.mask_notifier_list); INIT_LIST_HEAD(&kvm->arch.active_mmu_pages); + INIT_LIST_HEAD(&kvm->arch.zapped_obsolete_pages); + INIT_LIST_HEAD(&kvm->arch.lpage_disallowed_mmu_pages); INIT_LIST_HEAD(&kvm->arch.assigned_dev_head); atomic_set(&kvm->arch.noncoherent_dma_count, 0); @@ -9302,7 +9697,7 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) mutex_init(&kvm->arch.apic_map_lock); spin_lock_init(&kvm->arch.pvclock_gtod_sync_lock); - kvm->arch.kvmclock_offset = -ktime_get_boottime_ns(); + kvm->arch.kvmclock_offset = -get_kvmclock_base_ns(); pvclock_update_vm_gtod_copy(kvm); kvm->arch.guest_can_read_msr_platform_info = true; @@ -9314,10 +9709,12 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) kvm_page_track_init(kvm); kvm_mmu_init_vm(kvm); - if (kvm_x86_ops->vm_init) - return kvm_x86_ops->vm_init(kvm); + return kvm_x86_ops->vm_init(kvm); +} - return 0; +int kvm_arch_post_init_vm(struct kvm *kvm) +{ + return kvm_mmu_post_init_vm(kvm); } static void kvm_unload_vcpu_mmu(struct kvm_vcpu *vcpu) @@ -9340,7 +9737,7 @@ static void kvm_free_vcpus(struct kvm *kvm) kvm_unload_vcpu_mmu(vcpu); } kvm_for_each_vcpu(i, vcpu, kvm) - kvm_arch_vcpu_free(vcpu); + kvm_vcpu_destroy(vcpu); mutex_lock(&kvm->lock); for (i = 0; i < atomic_read(&kvm->online_vcpus); i++) @@ -9409,17 +9806,10 @@ int __x86_set_memory_region(struct kvm *kvm, int id, gpa_t gpa, u32 size) } EXPORT_SYMBOL_GPL(__x86_set_memory_region); -int x86_set_memory_region(struct kvm *kvm, int id, gpa_t gpa, u32 size) +void kvm_arch_pre_destroy_vm(struct kvm *kvm) { - int r; - - mutex_lock(&kvm->slots_lock); - r = __x86_set_memory_region(kvm, id, gpa, size); - mutex_unlock(&kvm->slots_lock); - - return r; + kvm_mmu_pre_destroy_vm(kvm); } -EXPORT_SYMBOL_GPL(x86_set_memory_region); void kvm_arch_destroy_vm(struct kvm *kvm) { @@ -9429,9 +9819,13 @@ void kvm_arch_destroy_vm(struct kvm *kvm) * unless the the memory map has changed due to process exit * or fd copying. */ - x86_set_memory_region(kvm, APIC_ACCESS_PAGE_PRIVATE_MEMSLOT, 0, 0); - x86_set_memory_region(kvm, IDENTITY_PAGETABLE_PRIVATE_MEMSLOT, 0, 0); - x86_set_memory_region(kvm, TSS_PRIVATE_MEMSLOT, 0, 0); + mutex_lock(&kvm->slots_lock); + __x86_set_memory_region(kvm, APIC_ACCESS_PAGE_PRIVATE_MEMSLOT, + 0, 0); + __x86_set_memory_region(kvm, IDENTITY_PAGETABLE_PRIVATE_MEMSLOT, + 0, 0); + __x86_set_memory_region(kvm, TSS_PRIVATE_MEMSLOT, 0, 0); + mutex_unlock(&kvm->slots_lock); } if (kvm_x86_ops->vm_destroy) kvm_x86_ops->vm_destroy(kvm); @@ -9535,11 +9929,18 @@ out_free: void kvm_arch_memslots_updated(struct kvm *kvm, u64 gen) { + struct kvm_vcpu *vcpu; + int i; + /* * memslots->generation has been incremented. * mmio generation may have reached its maximum value. */ kvm_mmu_invalidate_mmio_sptes(kvm, gen); + + /* Force re-initialization of steal_time cache */ + kvm_for_each_vcpu(i, vcpu, kvm) + kvm_vcpu_kick(vcpu); } int kvm_arch_prepare_memory_region(struct kvm *kvm, @@ -9569,7 +9970,7 @@ static void kvm_mmu_slot_apply_flags(struct kvm *kvm, * * The reason is, in case of PML, we need to set D-bit for any slots * with dirty logging disabled in order to eliminate unnecessary GPA - * logging in PML buffer (and potential PML buffer full VMEXT). This + * logging in PML buffer (and potential PML buffer full VMEXIT). This * guarantees leaving PML enabled during guest's lifetime won't have * any additional overhead from PML when guest is running with dirty * logging disabled for memory slots. @@ -9621,8 +10022,13 @@ void kvm_arch_commit_memory_region(struct kvm *kvm, * Scan sptes if dirty logging has been stopped, dropping those * which can be collapsed into a single large-page spte. Later * page faults will create the large-page sptes. + * + * There is no need to do this in any of the following cases: + * CREATE: No dirty mappings will already exist. + * MOVE/DELETE: The old mappings will already have been cleaned up by + * kvm_arch_flush_shadow_memslot() */ - if ((change != KVM_MR_DELETE) && + if (change == KVM_MR_FLAGS_ONLY && (old->flags & KVM_MEM_LOG_DIRTY_PAGES) && !(new->flags & KVM_MEM_LOG_DIRTY_PAGES)) kvm_mmu_zap_collapsible_sptes(kvm, new); @@ -9786,7 +10192,7 @@ void kvm_arch_async_page_ready(struct kvm_vcpu *vcpu, struct kvm_async_pf *work) work->arch.cr3 != vcpu->arch.mmu->get_cr3(vcpu)) return; - vcpu->arch.mmu->page_fault(vcpu, work->gva, 0, true); + kvm_mmu_do_page_fault(vcpu, work->cr2_or_gpa, 0, true); } static inline u32 kvm_async_pf_hash_fn(gfn_t gfn) @@ -9899,7 +10305,7 @@ void kvm_arch_async_page_not_present(struct kvm_vcpu *vcpu, { struct x86_exception fault; - trace_kvm_async_pf_not_present(work->arch.token, work->gva); + trace_kvm_async_pf_not_present(work->arch.token, work->cr2_or_gpa); kvm_add_async_pf_gfn(vcpu, work->arch.gfn); if (kvm_can_deliver_async_pf(vcpu) && @@ -9934,7 +10340,7 @@ void kvm_arch_async_page_present(struct kvm_vcpu *vcpu, work->arch.token = ~0; /* broadcast wakeup */ else kvm_del_async_pf_gfn(vcpu, work->arch.gfn); - trace_kvm_async_pf_ready(work->arch.token, work->gva); + trace_kvm_async_pf_ready(work->arch.token, work->cr2_or_gpa); if (vcpu->arch.apf.msr_val & KVM_ASYNC_PF_ENABLED && !apf_get_user(vcpu, &val)) { @@ -10009,7 +10415,7 @@ EXPORT_SYMBOL_GPL(kvm_arch_has_noncoherent_dma); bool kvm_arch_has_irq_bypass(void) { - return kvm_x86_ops->update_pi_irte != NULL; + return true; } int kvm_arch_irq_bypass_add_producer(struct irq_bypass_consumer *cons, @@ -10049,9 +10455,6 @@ void kvm_arch_irq_bypass_del_producer(struct irq_bypass_consumer *cons, int kvm_arch_update_irqfd_routing(struct kvm *kvm, unsigned int host_irq, uint32_t guest_irq, bool set) { - if (!kvm_x86_ops->update_pi_irte) - return -EINVAL; - return kvm_x86_ops->update_pi_irte(kvm, host_irq, guest_irq, set); } @@ -10059,7 +10462,6 @@ bool kvm_vector_hashing_enabled(void) { return vector_hashing; } -EXPORT_SYMBOL_GPL(kvm_vector_hashing_enabled); bool kvm_arch_no_poll(struct kvm_vcpu *vcpu) { @@ -10067,6 +10469,28 @@ bool kvm_arch_no_poll(struct kvm_vcpu *vcpu) } EXPORT_SYMBOL_GPL(kvm_arch_no_poll); +u64 kvm_spec_ctrl_valid_bits(struct kvm_vcpu *vcpu) +{ + uint64_t bits = SPEC_CTRL_IBRS | SPEC_CTRL_STIBP | SPEC_CTRL_SSBD; + + /* The STIBP bit doesn't fault even if it's not advertised */ + if (!guest_cpuid_has(vcpu, X86_FEATURE_SPEC_CTRL) && + !guest_cpuid_has(vcpu, X86_FEATURE_AMD_IBRS)) + bits &= ~(SPEC_CTRL_IBRS | SPEC_CTRL_STIBP); + if (!boot_cpu_has(X86_FEATURE_SPEC_CTRL) && + !boot_cpu_has(X86_FEATURE_AMD_IBRS)) + bits &= ~(SPEC_CTRL_IBRS | SPEC_CTRL_STIBP); + + if (!guest_cpuid_has(vcpu, X86_FEATURE_SPEC_CTRL_SSBD) && + !guest_cpuid_has(vcpu, X86_FEATURE_AMD_SSBD)) + bits &= ~SPEC_CTRL_SSBD; + if (!boot_cpu_has(X86_FEATURE_SPEC_CTRL_SSBD) && + !boot_cpu_has(X86_FEATURE_AMD_SSBD)) + bits &= ~SPEC_CTRL_SSBD; + + return bits; +} +EXPORT_SYMBOL_GPL(kvm_spec_ctrl_valid_bits); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_exit); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_fast_mmio); @@ -10078,12 +10502,14 @@ EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_nested_vmrun); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_nested_vmexit); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_nested_vmexit_inject); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_nested_intr_vmexit); +EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_nested_vmenter_failed); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_invlpga); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_skinit); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_nested_intercepts); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_write_tsc_offset); -EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_ple_window); +EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_ple_window_update); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_pml_full); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_pi_irte_update); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_avic_unaccelerated_access); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_avic_incomplete_ipi); +EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_apicv_update_request); diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h index 6594020c0691..3624665acee4 100644 --- a/arch/x86/kvm/x86.h +++ b/arch/x86/kvm/x86.h @@ -144,11 +144,6 @@ static inline bool is_pae_paging(struct kvm_vcpu *vcpu) return !is_long_mode(vcpu) && is_pae(vcpu) && is_paging(vcpu); } -static inline u32 bit(int bitno) -{ - return 1 << (bitno & 31); -} - static inline u8 vcpu_virt_addr_bits(struct kvm_vcpu *vcpu) { return kvm_read_cr4_bits(vcpu, X86_CR4_LA57) ? 57 : 48; @@ -166,21 +161,13 @@ static inline u64 get_canonical(u64 la, u8 vaddr_bits) static inline bool is_noncanonical_address(u64 la, struct kvm_vcpu *vcpu) { -#ifdef CONFIG_X86_64 return get_canonical(la, vcpu_virt_addr_bits(vcpu)) != la; -#else - return false; -#endif } static inline bool emul_is_noncanonical_address(u64 la, struct x86_emulate_ctxt *ctxt) { -#ifdef CONFIG_X86_64 return get_canonical(la, ctxt_virt_addr_bits(ctxt)) != la; -#else - return false; -#endif } static inline void vcpu_cache_mmio_info(struct kvm_vcpu *vcpu, @@ -196,7 +183,7 @@ static inline void vcpu_cache_mmio_info(struct kvm_vcpu *vcpu, * actually a nGPA. */ vcpu->arch.mmio_gva = mmu_is_nested(vcpu) ? 0 : gva & PAGE_MASK; - vcpu->arch.access = access; + vcpu->arch.mmio_access = access; vcpu->arch.mmio_gfn = gfn; vcpu->arch.mmio_gen = gen; } @@ -238,8 +225,7 @@ static inline bool vcpu_match_mmio_gpa(struct kvm_vcpu *vcpu, gpa_t gpa) return false; } -static inline unsigned long kvm_register_readl(struct kvm_vcpu *vcpu, - enum kvm_reg reg) +static inline unsigned long kvm_register_readl(struct kvm_vcpu *vcpu, int reg) { unsigned long val = kvm_register_read(vcpu, reg); @@ -247,8 +233,7 @@ static inline unsigned long kvm_register_readl(struct kvm_vcpu *vcpu, } static inline void kvm_register_writel(struct kvm_vcpu *vcpu, - enum kvm_reg reg, - unsigned long val) + int reg, unsigned long val) { if (!is_64_bit_mode(vcpu)) val = (u32)val; @@ -260,8 +245,13 @@ static inline bool kvm_check_has_quirk(struct kvm *kvm, u64 quirk) return !(kvm->arch.disabled_quirks & quirk); } +static inline bool kvm_vcpu_latch_init(struct kvm_vcpu *vcpu) +{ + return is_smm(vcpu) || kvm_x86_ops->apic_init_signal_blocked(vcpu); +} + void kvm_set_pending_timer(struct kvm_vcpu *vcpu); -int kvm_inject_realmode_interrupt(struct kvm_vcpu *vcpu, int irq, int inc_eip); +void kvm_inject_realmode_interrupt(struct kvm_vcpu *vcpu, int irq, int inc_eip); void kvm_write_tsc(struct kvm_vcpu *vcpu, struct msr_data *msr); u64 get_kvmclock_ns(struct kvm *kvm); @@ -286,8 +276,9 @@ int kvm_mtrr_get_msr(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata); bool kvm_mtrr_check_gfn_range_consistency(struct kvm_vcpu *vcpu, gfn_t gfn, int page_num); bool kvm_vector_hashing_enabled(void); -int x86_emulate_instruction(struct kvm_vcpu *vcpu, unsigned long cr2, +int x86_emulate_instruction(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, int emulation_type, void *insn, int insn_len); +enum exit_fastpath_completion handle_fastpath_set_msr_irqoff(struct kvm_vcpu *vcpu); #define KVM_SUPPORTED_XCR0 (XFEATURE_MASK_FP | XFEATURE_MASK_SSE \ | XFEATURE_MASK_YMM | XFEATURE_MASK_BNDREGS \ @@ -366,7 +357,14 @@ static inline bool kvm_pat_valid(u64 data) return (data | ((data & 0x0202020202020202ull) << 1)) == data; } -void kvm_load_guest_xcr0(struct kvm_vcpu *vcpu); -void kvm_put_guest_xcr0(struct kvm_vcpu *vcpu); +static inline bool kvm_dr7_valid(u64 data) +{ + /* Bits [63:32] are reserved */ + return !(data >> 32); +} + +void kvm_load_guest_xsave_state(struct kvm_vcpu *vcpu); +void kvm_load_host_xsave_state(struct kvm_vcpu *vcpu); +u64 kvm_spec_ctrl_valid_bits(struct kvm_vcpu *vcpu); #endif |