diff options
Diffstat (limited to 'arch/x86/kvm')
46 files changed, 1705 insertions, 766 deletions
diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig index 47bdbe705a76..2b1548da00eb 100644 --- a/arch/x86/kvm/Kconfig +++ b/arch/x86/kvm/Kconfig @@ -26,7 +26,9 @@ config KVM select PREEMPT_NOTIFIERS select MMU_NOTIFIER select HAVE_KVM_IRQCHIP + select HAVE_KVM_PFNCACHE select HAVE_KVM_IRQFD + select HAVE_KVM_DIRTY_RING select IRQ_BYPASS_MANAGER select HAVE_KVM_IRQ_BYPASS select HAVE_KVM_IRQ_ROUTING @@ -44,6 +46,7 @@ config KVM select KVM_GENERIC_DIRTYLOG_READ_PROTECT select KVM_VFIO select SRCU + select INTERVAL_TREE select HAVE_KVM_PM_NOTIFIER if PM help Support hosting fully virtualized guest machines using hardware diff --git a/arch/x86/kvm/Makefile b/arch/x86/kvm/Makefile index 75dfd27b6e8a..30f244b64523 100644 --- a/arch/x86/kvm/Makefile +++ b/arch/x86/kvm/Makefile @@ -7,12 +7,7 @@ ifeq ($(CONFIG_FRAME_POINTER),y) OBJECT_FILES_NON_STANDARD_vmenter.o := y endif -KVM := ../../../virt/kvm - -kvm-y += $(KVM)/kvm_main.o $(KVM)/coalesced_mmio.o \ - $(KVM)/eventfd.o $(KVM)/irqchip.o $(KVM)/vfio.o \ - $(KVM)/dirty_ring.o $(KVM)/binary_stats.o -kvm-$(CONFIG_KVM_ASYNC_PF) += $(KVM)/async_pf.o +include $(srctree)/virt/kvm/Makefile.kvm 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 \ diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index 07e9215e911d..c55e57b30e81 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -32,7 +32,7 @@ u32 kvm_cpu_caps[NR_KVM_CPU_CAPS] __read_mostly; EXPORT_SYMBOL_GPL(kvm_cpu_caps); -static u32 xstate_required_size(u64 xstate_bv, bool compacted) +u32 xstate_required_size(u64 xstate_bv, bool compacted) { int feature_bit = 0; u32 ret = XSAVE_HDR_SIZE + XSAVE_HDR_OFFSET; @@ -42,7 +42,11 @@ static u32 xstate_required_size(u64 xstate_bv, bool compacted) if (xstate_bv & 0x1) { u32 eax, ebx, ecx, edx, offset; cpuid_count(0xD, feature_bit, &eax, &ebx, &ecx, &edx); - offset = compacted ? ret : ebx; + /* ECX[1]: 64B alignment in compacted form */ + if (compacted) + offset = (ecx & 0x2) ? ALIGN(ret, 64) : ret; + else + offset = ebx; ret = max(ret, offset + eax); } @@ -80,9 +84,12 @@ static inline struct kvm_cpuid_entry2 *cpuid_entry2_find( return NULL; } -static int kvm_check_cpuid(struct kvm_cpuid_entry2 *entries, int nent) +static int kvm_check_cpuid(struct kvm_vcpu *vcpu, + struct kvm_cpuid_entry2 *entries, + int nent) { struct kvm_cpuid_entry2 *best; + u64 xfeatures; /* * The existing code assumes virtual address is 48-bit or 57-bit in the @@ -96,7 +103,20 @@ static int kvm_check_cpuid(struct kvm_cpuid_entry2 *entries, int nent) return -EINVAL; } - return 0; + /* + * Exposing dynamic xfeatures to the guest requires additional + * enabling in the FPU, e.g. to expand the guest XSAVE state size. + */ + best = cpuid_entry2_find(entries, nent, 0xd, 0); + if (!best) + return 0; + + xfeatures = best->eax | ((u64)best->edx << 32); + xfeatures &= XFEATURE_MASK_USER_DYNAMIC; + if (!xfeatures) + return 0; + + return fpu_enable_guest_xfd_features(&vcpu->arch.guest_fpu, xfeatures); } static void kvm_update_kvm_cpuid_base(struct kvm_vcpu *vcpu) @@ -276,21 +296,21 @@ u64 kvm_vcpu_reserved_gpa_bits_raw(struct kvm_vcpu *vcpu) static int kvm_set_cpuid(struct kvm_vcpu *vcpu, struct kvm_cpuid_entry2 *e2, int nent) { - int r; + int r; - r = kvm_check_cpuid(e2, nent); - if (r) - return r; + r = kvm_check_cpuid(vcpu, e2, nent); + if (r) + return r; - kvfree(vcpu->arch.cpuid_entries); - vcpu->arch.cpuid_entries = e2; - vcpu->arch.cpuid_nent = nent; + kvfree(vcpu->arch.cpuid_entries); + vcpu->arch.cpuid_entries = e2; + vcpu->arch.cpuid_nent = nent; - kvm_update_kvm_cpuid_base(vcpu); - kvm_update_cpuid_runtime(vcpu); - kvm_vcpu_after_set_cpuid(vcpu); + kvm_update_kvm_cpuid_base(vcpu); + kvm_update_cpuid_runtime(vcpu); + kvm_vcpu_after_set_cpuid(vcpu); - return 0; + return 0; } /* when an old userspace process fills a new kernel module */ @@ -422,9 +442,11 @@ void kvm_set_cpu_caps(void) #ifdef CONFIG_X86_64 unsigned int f_gbpages = F(GBPAGES); unsigned int f_lm = F(LM); + unsigned int f_xfd = F(XFD); #else unsigned int f_gbpages = 0; unsigned int f_lm = 0; + unsigned int f_xfd = 0; #endif memset(kvm_cpu_caps, 0, sizeof(kvm_cpu_caps)); @@ -492,7 +514,8 @@ void kvm_set_cpu_caps(void) F(AVX512_4VNNIW) | F(AVX512_4FMAPS) | F(SPEC_CTRL) | F(SPEC_CTRL_SSBD) | F(ARCH_CAPABILITIES) | F(INTEL_STIBP) | F(MD_CLEAR) | F(AVX512_VP2INTERSECT) | F(FSRM) | - F(SERIALIZE) | F(TSXLDTRK) | F(AVX512_FP16) + F(SERIALIZE) | F(TSXLDTRK) | F(AVX512_FP16) | + F(AMX_TILE) | F(AMX_INT8) | F(AMX_BF16) ); /* TSC_ADJUST and ARCH_CAPABILITIES are emulated in software. */ @@ -511,7 +534,7 @@ void kvm_set_cpu_caps(void) ); kvm_cpu_cap_mask(CPUID_D_1_EAX, - F(XSAVEOPT) | F(XSAVEC) | F(XGETBV1) | F(XSAVES) + F(XSAVEOPT) | F(XSAVEC) | F(XGETBV1) | F(XSAVES) | f_xfd ); kvm_cpu_cap_init_scattered(CPUID_12_EAX, @@ -523,7 +546,7 @@ void kvm_set_cpu_caps(void) F(CR8_LEGACY) | F(ABM) | F(SSE4A) | F(MISALIGNSSE) | F(3DNOWPREFETCH) | F(OSVW) | 0 /* IBS */ | F(XOP) | 0 /* SKINIT, WDT, LWP */ | F(FMA4) | F(TBM) | - F(TOPOEXT) | F(PERFCTR_CORE) + F(TOPOEXT) | 0 /* PERFCTR_CORE */ ); kvm_cpu_cap_mask(CPUID_8000_0001_EDX, @@ -637,6 +660,8 @@ static struct kvm_cpuid_entry2 *do_host_cpuid(struct kvm_cpuid_array *array, case 0x14: case 0x17: case 0x18: + case 0x1d: + case 0x1e: case 0x1f: case 0x8000001d: entry->flags |= KVM_CPUID_FLAG_SIGNIFCANT_INDEX; @@ -811,11 +836,13 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function) goto out; } break; - case 0xd: - entry->eax &= supported_xcr0; + case 0xd: { + u64 guest_perm = xstate_get_guest_group_perm(); + + entry->eax &= supported_xcr0 & guest_perm; entry->ebx = xstate_required_size(supported_xcr0, false); entry->ecx = entry->ebx; - entry->edx &= supported_xcr0 >> 32; + entry->edx &= (supported_xcr0 & guest_perm) >> 32; if (!supported_xcr0) break; @@ -862,6 +889,7 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function) entry->edx = 0; } break; + } case 0x12: /* Intel SGX */ if (!kvm_cpu_cap_has(X86_FEATURE_SGX)) { @@ -906,6 +934,24 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function) goto out; } break; + /* Intel AMX TILE */ + case 0x1d: + if (!kvm_cpu_cap_has(X86_FEATURE_AMX_TILE)) { + entry->eax = entry->ebx = entry->ecx = entry->edx = 0; + break; + } + + for (i = 1, max_idx = entry->eax; i <= max_idx; ++i) { + if (!do_host_cpuid(array, function, i)) + goto out; + } + break; + case 0x1e: /* TMUL information */ + if (!kvm_cpu_cap_has(X86_FEATURE_AMX_TILE)) { + entry->eax = entry->ebx = entry->ecx = entry->edx = 0; + break; + } + break; case KVM_CPUID_SIGNATURE: { const u32 *sigptr = (const u32 *)KVM_SIGNATURE; entry->eax = KVM_CPUID_FEATURES; diff --git a/arch/x86/kvm/cpuid.h b/arch/x86/kvm/cpuid.h index c99edfff7f82..8a770b481d9d 100644 --- a/arch/x86/kvm/cpuid.h +++ b/arch/x86/kvm/cpuid.h @@ -30,6 +30,8 @@ int kvm_vcpu_ioctl_get_cpuid2(struct kvm_vcpu *vcpu, bool kvm_cpuid(struct kvm_vcpu *vcpu, u32 *eax, u32 *ebx, u32 *ecx, u32 *edx, bool exact_only); +u32 xstate_required_size(u64 xstate_bv, bool compacted); + int cpuid_query_maxphyaddr(struct kvm_vcpu *vcpu); u64 kvm_vcpu_reserved_gpa_bits_raw(struct kvm_vcpu *vcpu); diff --git a/arch/x86/kvm/debugfs.c b/arch/x86/kvm/debugfs.c index f33c804a922a..9240b3b7f8dd 100644 --- a/arch/x86/kvm/debugfs.c +++ b/arch/x86/kvm/debugfs.c @@ -110,9 +110,10 @@ static int kvm_mmu_rmaps_stat_show(struct seq_file *m, void *v) write_lock(&kvm->mmu_lock); for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) { + int bkt; + slots = __kvm_memslots(kvm, i); - for (j = 0; j < slots->used_slots; j++) { - slot = &slots->memslots[j]; + kvm_for_each_memslot(slot, bkt, slots) for (k = 0; k < KVM_NR_PAGE_SIZES; k++) { rmap = slot->arch.rmap[k]; lpage_size = kvm_mmu_slot_lpages(slot, k + 1); @@ -124,7 +125,6 @@ static int kvm_mmu_rmaps_stat_show(struct seq_file *m, void *v) cur[index]++; } } - } } write_unlock(&kvm->mmu_lock); diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index 1e19a4de441f..5719d8cfdbd9 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -175,6 +175,7 @@ #define No16 ((u64)1 << 53) /* No 16 bit operand */ #define IncSP ((u64)1 << 54) /* SP is incremented before ModRM calc */ #define TwoMemOp ((u64)1 << 55) /* Instruction has two memory operand */ +#define IsBranch ((u64)1 << 56) /* Instruction is considered a branch. */ #define DstXacc (DstAccLo | SrcAccHi | SrcWrite) @@ -191,8 +192,9 @@ #define FASTOP_SIZE 8 struct opcode { - u64 flags : 56; - u64 intercept : 8; + u64 flags; + u8 intercept; + u8 pad[7]; union { int (*execute)(struct x86_emulate_ctxt *ctxt); const struct opcode *group; @@ -4356,10 +4358,10 @@ static const struct opcode group4[] = { static const struct opcode group5[] = { F(DstMem | SrcNone | Lock, em_inc), F(DstMem | SrcNone | Lock, em_dec), - I(SrcMem | NearBranch, em_call_near_abs), - I(SrcMemFAddr | ImplicitOps, em_call_far), - I(SrcMem | NearBranch, em_jmp_abs), - I(SrcMemFAddr | ImplicitOps, em_jmp_far), + I(SrcMem | NearBranch | IsBranch, em_call_near_abs), + I(SrcMemFAddr | ImplicitOps | IsBranch, em_call_far), + I(SrcMem | NearBranch | IsBranch, em_jmp_abs), + I(SrcMemFAddr | ImplicitOps | IsBranch, em_jmp_far), I(SrcMem | Stack | TwoMemOp, em_push), D(Undefined), }; @@ -4569,7 +4571,7 @@ static const struct opcode opcode_table[256] = { I2bvIP(DstDI | SrcDX | Mov | String | Unaligned, em_in, ins, check_perm_in), /* insb, insw/insd */ I2bvIP(SrcSI | DstDX | String, em_out, outs, check_perm_out), /* outsb, outsw/outsd */ /* 0x70 - 0x7F */ - X16(D(SrcImmByte | NearBranch)), + X16(D(SrcImmByte | NearBranch | IsBranch)), /* 0x80 - 0x87 */ G(ByteOp | DstMem | SrcImm, group1), G(DstMem | SrcImm, group1), @@ -4588,7 +4590,7 @@ static const struct opcode opcode_table[256] = { DI(SrcAcc | DstReg, pause), X7(D(SrcAcc | DstReg)), /* 0x98 - 0x9F */ D(DstAcc | SrcNone), I(ImplicitOps | SrcAcc, em_cwd), - I(SrcImmFAddr | No64, em_call_far), N, + I(SrcImmFAddr | No64 | IsBranch, em_call_far), N, II(ImplicitOps | Stack, em_pushf, pushf), II(ImplicitOps | Stack, em_popf, popf), I(ImplicitOps, em_sahf), I(ImplicitOps, em_lahf), @@ -4608,17 +4610,19 @@ static const struct opcode opcode_table[256] = { X8(I(DstReg | SrcImm64 | Mov, em_mov)), /* 0xC0 - 0xC7 */ G(ByteOp | Src2ImmByte, group2), G(Src2ImmByte, group2), - I(ImplicitOps | NearBranch | SrcImmU16, em_ret_near_imm), - I(ImplicitOps | NearBranch, em_ret), + I(ImplicitOps | NearBranch | SrcImmU16 | IsBranch, em_ret_near_imm), + I(ImplicitOps | NearBranch | IsBranch, em_ret), I(DstReg | SrcMemFAddr | ModRM | No64 | Src2ES, em_lseg), I(DstReg | SrcMemFAddr | ModRM | No64 | Src2DS, em_lseg), G(ByteOp, group11), G(0, group11), /* 0xC8 - 0xCF */ - I(Stack | SrcImmU16 | Src2ImmByte, em_enter), I(Stack, em_leave), - I(ImplicitOps | SrcImmU16, em_ret_far_imm), - I(ImplicitOps, em_ret_far), - D(ImplicitOps), DI(SrcImmByte, intn), - D(ImplicitOps | No64), II(ImplicitOps, em_iret, iret), + I(Stack | SrcImmU16 | Src2ImmByte | IsBranch, em_enter), + I(Stack | IsBranch, em_leave), + I(ImplicitOps | SrcImmU16 | IsBranch, em_ret_far_imm), + I(ImplicitOps | IsBranch, em_ret_far), + D(ImplicitOps | IsBranch), DI(SrcImmByte | IsBranch, intn), + D(ImplicitOps | No64 | IsBranch), + II(ImplicitOps | IsBranch, em_iret, iret), /* 0xD0 - 0xD7 */ G(Src2One | ByteOp, group2), G(Src2One, group2), G(Src2CL | ByteOp, group2), G(Src2CL, group2), @@ -4629,14 +4633,15 @@ static const struct opcode opcode_table[256] = { /* 0xD8 - 0xDF */ N, E(0, &escape_d9), N, E(0, &escape_db), N, E(0, &escape_dd), N, N, /* 0xE0 - 0xE7 */ - X3(I(SrcImmByte | NearBranch, em_loop)), - I(SrcImmByte | NearBranch, em_jcxz), + X3(I(SrcImmByte | NearBranch | IsBranch, em_loop)), + I(SrcImmByte | NearBranch | IsBranch, em_jcxz), I2bvIP(SrcImmUByte | DstAcc, em_in, in, check_perm_in), I2bvIP(SrcAcc | DstImmUByte, em_out, out, check_perm_out), /* 0xE8 - 0xEF */ - I(SrcImm | NearBranch, em_call), D(SrcImm | ImplicitOps | NearBranch), - I(SrcImmFAddr | No64, em_jmp_far), - D(SrcImmByte | ImplicitOps | NearBranch), + I(SrcImm | NearBranch | IsBranch, em_call), + D(SrcImm | ImplicitOps | NearBranch | IsBranch), + I(SrcImmFAddr | No64 | IsBranch, em_jmp_far), + D(SrcImmByte | ImplicitOps | NearBranch | IsBranch), I2bvIP(SrcDX | DstAcc, em_in, in, check_perm_in), I2bvIP(SrcAcc | DstDX, em_out, out, check_perm_out), /* 0xF0 - 0xF7 */ @@ -4652,7 +4657,7 @@ static const struct opcode opcode_table[256] = { static const struct opcode twobyte_table[256] = { /* 0x00 - 0x0F */ G(0, group6), GD(0, &group7), N, N, - N, I(ImplicitOps | EmulateOnUD, em_syscall), + N, I(ImplicitOps | EmulateOnUD | IsBranch, em_syscall), II(ImplicitOps | Priv, em_clts, clts), N, DI(ImplicitOps | Priv, invd), DI(ImplicitOps | Priv, wbinvd), N, N, N, D(ImplicitOps | ModRM | SrcMem | NoAccess), N, N, @@ -4683,8 +4688,8 @@ static const struct opcode twobyte_table[256] = { IIP(ImplicitOps, em_rdtsc, rdtsc, check_rdtsc), II(ImplicitOps | Priv, em_rdmsr, rdmsr), IIP(ImplicitOps, em_rdpmc, rdpmc, check_rdpmc), - I(ImplicitOps | EmulateOnUD, em_sysenter), - I(ImplicitOps | Priv | EmulateOnUD, em_sysexit), + I(ImplicitOps | EmulateOnUD | IsBranch, em_sysenter), + I(ImplicitOps | Priv | EmulateOnUD | IsBranch, em_sysexit), N, N, N, N, N, N, N, N, N, N, /* 0x40 - 0x4F */ @@ -4702,7 +4707,7 @@ static const struct opcode twobyte_table[256] = { N, N, N, N, N, N, N, GP(SrcReg | DstMem | ModRM | Mov, &pfx_0f_6f_0f_7f), /* 0x80 - 0x8F */ - X16(D(SrcImm | NearBranch)), + X16(D(SrcImm | NearBranch | IsBranch)), /* 0x90 - 0x9F */ X16(D(ByteOp | DstMem | SrcNone | ModRM| Mov)), /* 0xA0 - 0xA7 */ @@ -5216,6 +5221,8 @@ done_prefixes: ctxt->d |= opcode.flags; } + ctxt->is_branch = opcode.flags & IsBranch; + /* Unrecognised? */ if (ctxt->d == 0) return EMULATION_FAILED; diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c index 8d8c1cc7cb53..6e38a7d22e97 100644 --- a/arch/x86/kvm/hyperv.c +++ b/arch/x86/kvm/hyperv.c @@ -164,7 +164,7 @@ static int synic_set_sint(struct kvm_vcpu_hv_synic *synic, int sint, static struct kvm_vcpu *get_vcpu_by_vpidx(struct kvm *kvm, u32 vpidx) { struct kvm_vcpu *vcpu = NULL; - int i; + unsigned long i; if (vpidx >= KVM_MAX_VCPUS) return NULL; @@ -1716,7 +1716,8 @@ static __always_inline unsigned long *sparse_set_to_vcpu_mask( { struct kvm_hv *hv = to_kvm_hv(kvm); struct kvm_vcpu *vcpu; - int i, bank, sbank = 0; + int bank, sbank = 0; + unsigned long i; memset(vp_bitmap, 0, KVM_HV_MAX_SPARSE_VCPU_SET_BITS * sizeof(*vp_bitmap)); @@ -1863,7 +1864,7 @@ static void kvm_send_ipi_to_many(struct kvm *kvm, u32 vector, .vector = vector }; struct kvm_vcpu *vcpu; - int i; + unsigned long i; kvm_for_each_vcpu(i, vcpu, kvm) { if (vcpu_bitmap && !test_bit(i, vcpu_bitmap)) @@ -2519,6 +2520,8 @@ int kvm_get_hv_cpuid(struct kvm_vcpu *vcpu, struct kvm_cpuid2 *cpuid, case HYPERV_CPUID_NESTED_FEATURES: ent->eax = evmcs_ver; + if (evmcs_ver) + ent->eax |= HV_X64_NESTED_MSR_BITMAP; break; diff --git a/arch/x86/kvm/i8254.c b/arch/x86/kvm/i8254.c index 5a69cce4d72d..0b65a764ed3a 100644 --- a/arch/x86/kvm/i8254.c +++ b/arch/x86/kvm/i8254.c @@ -242,7 +242,7 @@ static void pit_do_work(struct kthread_work *work) struct kvm_pit *pit = container_of(work, struct kvm_pit, expired); struct kvm *kvm = pit->kvm; struct kvm_vcpu *vcpu; - int i; + unsigned long i; struct kvm_kpit_state *ps = &pit->pit_state; if (atomic_read(&ps->reinject) && !atomic_xchg(&ps->irq_ack, 0)) diff --git a/arch/x86/kvm/i8259.c b/arch/x86/kvm/i8259.c index 0b80263d46d8..814064d06016 100644 --- a/arch/x86/kvm/i8259.c +++ b/arch/x86/kvm/i8259.c @@ -50,7 +50,7 @@ static void pic_unlock(struct kvm_pic *s) { bool wakeup = s->wakeup_needed; struct kvm_vcpu *vcpu; - int i; + unsigned long i; s->wakeup_needed = false; @@ -270,7 +270,8 @@ int kvm_pic_read_irq(struct kvm *kvm) static void kvm_pic_reset(struct kvm_kpic_state *s) { - int irq, i; + int irq; + unsigned long i; struct kvm_vcpu *vcpu; u8 edge_irr = s->irr & ~s->elcr; bool found = false; diff --git a/arch/x86/kvm/ioapic.c b/arch/x86/kvm/ioapic.c index 816a82515dcd..decfa36b7891 100644 --- a/arch/x86/kvm/ioapic.c +++ b/arch/x86/kvm/ioapic.c @@ -149,7 +149,7 @@ void kvm_rtc_eoi_tracking_restore_one(struct kvm_vcpu *vcpu) static void kvm_rtc_eoi_tracking_restore_all(struct kvm_ioapic *ioapic) { struct kvm_vcpu *vcpu; - int i; + unsigned long i; if (RTC_GSI >= IOAPIC_NUM_PINS) return; @@ -184,7 +184,7 @@ static bool rtc_irq_check_coalesced(struct kvm_ioapic *ioapic) static void ioapic_lazy_update_eoi(struct kvm_ioapic *ioapic, int irq) { - int i; + unsigned long i; struct kvm_vcpu *vcpu; union kvm_ioapic_redirect_entry *entry = &ioapic->redirtbl[irq]; diff --git a/arch/x86/kvm/irq_comm.c b/arch/x86/kvm/irq_comm.c index d5b72a08e566..6e0dab04320e 100644 --- a/arch/x86/kvm/irq_comm.c +++ b/arch/x86/kvm/irq_comm.c @@ -24,6 +24,7 @@ #include "hyperv.h" #include "x86.h" +#include "xen.h" static int kvm_set_pic_irq(struct kvm_kernel_irq_routing_entry *e, struct kvm *kvm, int irq_source_id, int level, @@ -45,9 +46,9 @@ static int kvm_set_ioapic_irq(struct kvm_kernel_irq_routing_entry *e, int kvm_irq_delivery_to_apic(struct kvm *kvm, struct kvm_lapic *src, struct kvm_lapic_irq *irq, struct dest_map *dest_map) { - int i, r = -1; + int r = -1; struct kvm_vcpu *vcpu, *lowest = NULL; - unsigned long dest_vcpu_bitmap[BITS_TO_LONGS(KVM_MAX_VCPUS)]; + unsigned long i, dest_vcpu_bitmap[BITS_TO_LONGS(KVM_MAX_VCPUS)]; unsigned int dest_vcpus = 0; if (kvm_irq_delivery_to_apic_fast(kvm, src, irq, &r, dest_map)) @@ -175,6 +176,13 @@ int kvm_arch_set_irq_inatomic(struct kvm_kernel_irq_routing_entry *e, return r; break; +#ifdef CONFIG_KVM_XEN + case KVM_IRQ_ROUTING_XEN_EVTCHN: + if (!level) + return -1; + + return kvm_xen_set_evtchn_fast(e, kvm); +#endif default: break; } @@ -310,6 +318,10 @@ int kvm_set_routing_entry(struct kvm *kvm, e->hv_sint.vcpu = ue->u.hv_sint.vcpu; e->hv_sint.sint = ue->u.hv_sint.sint; break; +#ifdef CONFIG_KVM_XEN + case KVM_IRQ_ROUTING_XEN_EVTCHN: + return kvm_xen_setup_evtchn(kvm, e, ue); +#endif default: return -EINVAL; } @@ -320,7 +332,8 @@ int kvm_set_routing_entry(struct kvm *kvm, bool kvm_intr_is_single_vcpu(struct kvm *kvm, struct kvm_lapic_irq *irq, struct kvm_vcpu **dest_vcpu) { - int i, r = 0; + int r = 0; + unsigned long i; struct kvm_vcpu *vcpu; if (kvm_intr_is_single_vcpu_fast(kvm, irq, dest_vcpu)) diff --git a/arch/x86/kvm/kvm_cache_regs.h b/arch/x86/kvm/kvm_cache_regs.h index 90e1ffdc05b7..3febc342360c 100644 --- a/arch/x86/kvm/kvm_cache_regs.h +++ b/arch/x86/kvm/kvm_cache_regs.h @@ -9,6 +9,12 @@ (X86_CR4_PVI | X86_CR4_DE | X86_CR4_PCE | X86_CR4_OSFXSR \ | X86_CR4_OSXMMEXCPT | X86_CR4_PGE | X86_CR4_TSD | X86_CR4_FSGSBASE) +#define X86_CR0_PDPTR_BITS (X86_CR0_CD | X86_CR0_NW | X86_CR0_PG) +#define X86_CR4_TLBFLUSH_BITS (X86_CR4_PGE | X86_CR4_PCIDE | X86_CR4_PAE | X86_CR4_SMEP) +#define X86_CR4_PDPTR_BITS (X86_CR4_PGE | X86_CR4_PSE | X86_CR4_PAE | X86_CR4_SMEP) + +static_assert(!(KVM_POSSIBLE_CR0_GUEST_BITS & X86_CR0_PDPTR_BITS)); + #define BUILD_KVM_GPR_ACCESSORS(lname, uname) \ static __always_inline unsigned long kvm_##lname##_read(struct kvm_vcpu *vcpu)\ { \ @@ -37,6 +43,13 @@ BUILD_KVM_GPR_ACCESSORS(r14, R14) BUILD_KVM_GPR_ACCESSORS(r15, R15) #endif +/* + * avail dirty + * 0 0 register in VMCS/VMCB + * 0 1 *INVALID* + * 1 0 register in vcpu->arch + * 1 1 register in vcpu->arch, needs to be stored back + */ static inline bool kvm_register_is_available(struct kvm_vcpu *vcpu, enum kvm_reg reg) { @@ -55,13 +68,6 @@ static inline void kvm_register_mark_available(struct kvm_vcpu *vcpu, __set_bit(reg, (unsigned long *)&vcpu->arch.regs_avail); } -static inline void kvm_register_clear_available(struct kvm_vcpu *vcpu, - enum kvm_reg reg) -{ - __clear_bit(reg, (unsigned long *)&vcpu->arch.regs_avail); - __clear_bit(reg, (unsigned long *)&vcpu->arch.regs_dirty); -} - static inline void kvm_register_mark_dirty(struct kvm_vcpu *vcpu, enum kvm_reg reg) { diff --git a/arch/x86/kvm/kvm_emulate.h b/arch/x86/kvm/kvm_emulate.h index 68b420289d7e..39eded2426ff 100644 --- a/arch/x86/kvm/kvm_emulate.h +++ b/arch/x86/kvm/kvm_emulate.h @@ -369,6 +369,7 @@ struct x86_emulate_ctxt { struct fetch_cache fetch; struct read_cache io_read; struct read_cache mem_read; + bool is_branch; }; /* Repeat String Operation Prefix */ diff --git a/arch/x86/kvm/kvm_onhyperv.c b/arch/x86/kvm/kvm_onhyperv.c index c7db2df50a7a..b469f45e3fe4 100644 --- a/arch/x86/kvm/kvm_onhyperv.c +++ b/arch/x86/kvm/kvm_onhyperv.c @@ -33,7 +33,8 @@ int hv_remote_flush_tlb_with_range(struct kvm *kvm, { struct kvm_arch *kvm_arch = &kvm->arch; struct kvm_vcpu *vcpu; - int ret = 0, i, nr_unique_valid_roots; + int ret = 0, nr_unique_valid_roots; + unsigned long i; hpa_t root; spin_lock(&kvm_arch->hv_root_tdp_lock); diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index f206fc35deff..c5028e6b0f96 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -185,7 +185,7 @@ void kvm_recalculate_apic_map(struct kvm *kvm) { struct kvm_apic_map *new, *old = NULL; struct kvm_vcpu *vcpu; - int i; + unsigned long i; u32 max_id = 255; /* enough space for any xAPIC ID */ /* Read kvm->arch.apic_map_dirty before kvm->arch.apic_map. */ @@ -673,35 +673,34 @@ static inline bool pv_eoi_enabled(struct kvm_vcpu *vcpu) return vcpu->arch.pv_eoi.msr_val & KVM_MSR_ENABLED; } -static bool pv_eoi_get_pending(struct kvm_vcpu *vcpu) -{ - u8 val; - if (pv_eoi_get_user(vcpu, &val) < 0) { - printk(KERN_WARNING "Can't read EOI MSR value: 0x%llx\n", - (unsigned long long)vcpu->arch.pv_eoi.msr_val); - return false; - } - return val & KVM_PV_EOI_ENABLED; -} - static void pv_eoi_set_pending(struct kvm_vcpu *vcpu) { - if (pv_eoi_put_user(vcpu, KVM_PV_EOI_ENABLED) < 0) { - printk(KERN_WARNING "Can't set EOI MSR value: 0x%llx\n", - (unsigned long long)vcpu->arch.pv_eoi.msr_val); + if (pv_eoi_put_user(vcpu, KVM_PV_EOI_ENABLED) < 0) return; - } + __set_bit(KVM_APIC_PV_EOI_PENDING, &vcpu->arch.apic_attention); } -static void pv_eoi_clr_pending(struct kvm_vcpu *vcpu) +static bool pv_eoi_test_and_clr_pending(struct kvm_vcpu *vcpu) { - if (pv_eoi_put_user(vcpu, KVM_PV_EOI_DISABLED) < 0) { - printk(KERN_WARNING "Can't clear EOI MSR value: 0x%llx\n", - (unsigned long long)vcpu->arch.pv_eoi.msr_val); - return; - } + u8 val; + + if (pv_eoi_get_user(vcpu, &val) < 0) + return false; + + val &= KVM_PV_EOI_ENABLED; + + if (val && pv_eoi_put_user(vcpu, KVM_PV_EOI_DISABLED) < 0) + return false; + + /* + * Clear pending bit in any case: it will be set again on vmentry. + * While this might not be ideal from performance point of view, + * this makes sure pv eoi is only enabled when we know it's safe. + */ __clear_bit(KVM_APIC_PV_EOI_PENDING, &vcpu->arch.apic_attention); + + return val; } static int apic_has_interrupt_for_ppr(struct kvm_lapic *apic, u32 ppr) @@ -1101,6 +1100,9 @@ static int __apic_accept_irq(struct kvm_lapic *apic, int delivery_mode, kvm_lapic_set_irr(vector, apic); kvm_make_request(KVM_REQ_EVENT, vcpu); kvm_vcpu_kick(vcpu); + } else { + trace_kvm_apicv_accept_irq(vcpu->vcpu_id, delivery_mode, + trig_mode, vector); } break; @@ -1172,8 +1174,8 @@ void kvm_bitmap_or_dest_vcpus(struct kvm *kvm, struct kvm_lapic_irq *irq, struct kvm_lapic *src = NULL; struct kvm_apic_map *map; struct kvm_vcpu *vcpu; - unsigned long bitmap; - int i, vcpu_idx; + unsigned long bitmap, i; + int vcpu_idx; bool ret; rcu_read_lock(); @@ -1931,7 +1933,7 @@ void kvm_lapic_expired_hv_timer(struct kvm_vcpu *vcpu) /* If the preempt notifier has already run, it also called apic_timer_expired */ if (!apic->lapic_timer.hv_timer_in_use) goto out; - WARN_ON(rcuwait_active(&vcpu->wait)); + WARN_ON(kvm_vcpu_is_blocking(vcpu)); apic_timer_expired(apic, false); cancel_hv_timer(apic); @@ -2677,7 +2679,6 @@ void __kvm_migrate_apic_timer(struct kvm_vcpu *vcpu) static void apic_sync_pv_eoi_from_guest(struct kvm_vcpu *vcpu, struct kvm_lapic *apic) { - bool pending; int vector; /* * PV EOI state is derived from KVM_APIC_PV_EOI_PENDING in host @@ -2691,14 +2692,8 @@ static void apic_sync_pv_eoi_from_guest(struct kvm_vcpu *vcpu, * -> host enabled PV EOI, guest executed EOI. */ BUG_ON(!pv_eoi_enabled(vcpu)); - pending = pv_eoi_get_pending(vcpu); - /* - * Clear pending bit in any case: it will be set again on vmentry. - * While this might not be ideal from performance point of view, - * this makes sure pv eoi is only enabled when we know it's safe. - */ - pv_eoi_clr_pending(vcpu); - if (pending) + + if (pv_eoi_test_and_clr_pending(vcpu)) return; vector = apic_set_eoi(apic); trace_kvm_pv_eoi(apic, vector); diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h index 9ae6168d381e..e9fbb2c8bbe2 100644 --- a/arch/x86/kvm/mmu.h +++ b/arch/x86/kvm/mmu.h @@ -71,7 +71,8 @@ void kvm_init_mmu(struct kvm_vcpu *vcpu); void kvm_init_shadow_npt_mmu(struct kvm_vcpu *vcpu, unsigned long cr0, unsigned long cr4, u64 efer, gpa_t nested_cr3); void kvm_init_shadow_ept_mmu(struct kvm_vcpu *vcpu, bool execonly, - bool accessed_dirty, gpa_t new_eptp); + int huge_page_level, bool accessed_dirty, + gpa_t new_eptp); bool kvm_can_do_async_pf(struct kvm_vcpu *vcpu); int kvm_handle_page_fault(struct kvm_vcpu *vcpu, u64 error_code, u64 fault_address, char *insn, int insn_len); @@ -351,4 +352,17 @@ static inline void kvm_update_page_stats(struct kvm *kvm, int level, int count) { atomic64_add(count, &kvm->stat.pages[level - 1]); } + +gpa_t translate_nested_gpa(struct kvm_vcpu *vcpu, gpa_t gpa, u32 access, + struct x86_exception *exception); + +static inline gpa_t kvm_translate_gpa(struct kvm_vcpu *vcpu, + struct kvm_mmu *mmu, + gpa_t gpa, u32 access, + struct x86_exception *exception) +{ + if (mmu != &vcpu->arch.nested_mmu) + return gpa; + return translate_nested_gpa(vcpu, gpa, access, exception); +} #endif diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index fcdf3f8bb59a..1d275e9d76b5 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -335,12 +335,6 @@ static bool check_mmio_spte(struct kvm_vcpu *vcpu, u64 spte) return likely(kvm_gen == spte_gen); } -static gpa_t translate_gpa(struct kvm_vcpu *vcpu, gpa_t gpa, u32 access, - struct x86_exception *exception) -{ - return gpa; -} - static int is_cpuid_PSE36(void) { return 1; @@ -1454,7 +1448,7 @@ static bool kvm_set_pte_rmapp(struct kvm *kvm, struct kvm_rmap_head *rmap_head, { u64 *sptep; struct rmap_iterator iter; - int need_flush = 0; + bool need_flush = false; u64 new_spte; kvm_pfn_t new_pfn; @@ -1466,7 +1460,7 @@ restart: rmap_printk("spte %p %llx gfn %llx (%d)\n", sptep, *sptep, gfn, level); - need_flush = 1; + need_flush = true; if (pte_write(pte)) { pte_list_remove(kvm, rmap_head, sptep); @@ -1482,7 +1476,7 @@ restart: if (need_flush && kvm_available_flush_tlb_with_range()) { kvm_flush_remote_tlbs_with_address(kvm, gfn, 1); - return 0; + return false; } return need_flush; @@ -1623,8 +1617,8 @@ static bool kvm_test_age_rmapp(struct kvm *kvm, struct kvm_rmap_head *rmap_head, for_each_rmap_spte(rmap_head, &iter, sptep) if (is_accessed_spte(*sptep)) - return 1; - return 0; + return true; + return false; } #define RMAP_RECYCLE_THRESHOLD 1000 @@ -2086,10 +2080,8 @@ static struct kvm_mmu_page *kvm_mmu_get_page(struct kvm_vcpu *vcpu, role = vcpu->arch.mmu->mmu_role.base; role.level = level; role.direct = direct; - if (role.direct) - role.gpte_is_8_bytes = true; role.access = access; - if (!direct_mmu && vcpu->arch.mmu->root_level <= PT32_ROOT_LEVEL) { + if (role.has_4_byte_gpte) { quadrant = gaddr >> (PAGE_SHIFT + (PT64_PT_BITS * level)); quadrant &= (1 << ((PT32_PT_BITS - PT64_PT_BITS) * level)) - 1; role.quadrant = quadrant; @@ -2565,10 +2557,10 @@ static int kvm_mmu_unprotect_page_virt(struct kvm_vcpu *vcpu, gva_t gva) return r; } -static void kvm_unsync_page(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp) +static void kvm_unsync_page(struct kvm *kvm, struct kvm_mmu_page *sp) { trace_kvm_mmu_unsync_page(sp); - ++vcpu->kvm->stat.mmu_unsync; + ++kvm->stat.mmu_unsync; sp->unsync = 1; kvm_mmu_mark_parents_unsync(sp); @@ -2580,7 +2572,7 @@ static void kvm_unsync_page(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp) * were marked unsync (or if there is no shadow page), -EPERM if the SPTE must * be write-protected. */ -int mmu_try_to_unsync_pages(struct kvm_vcpu *vcpu, struct kvm_memory_slot *slot, +int mmu_try_to_unsync_pages(struct kvm *kvm, const struct kvm_memory_slot *slot, gfn_t gfn, bool can_unsync, bool prefetch) { struct kvm_mmu_page *sp; @@ -2591,7 +2583,7 @@ int mmu_try_to_unsync_pages(struct kvm_vcpu *vcpu, struct kvm_memory_slot *slot, * track machinery is used to write-protect upper-level shadow pages, * i.e. this guards the role.level == 4K assertion below! */ - if (kvm_slot_page_track_is_active(vcpu, slot, gfn, KVM_PAGE_TRACK_WRITE)) + if (kvm_slot_page_track_is_active(kvm, slot, gfn, KVM_PAGE_TRACK_WRITE)) return -EPERM; /* @@ -2600,7 +2592,7 @@ int mmu_try_to_unsync_pages(struct kvm_vcpu *vcpu, struct kvm_memory_slot *slot, * that case, KVM must complete emulation of the guest TLB flush before * allowing shadow pages to become unsync (writable by the guest). */ - for_each_gfn_indirect_valid_sp(vcpu->kvm, sp, gfn) { + for_each_gfn_indirect_valid_sp(kvm, sp, gfn) { if (!can_unsync) return -EPERM; @@ -2619,7 +2611,7 @@ int mmu_try_to_unsync_pages(struct kvm_vcpu *vcpu, struct kvm_memory_slot *slot, */ if (!locked) { locked = true; - spin_lock(&vcpu->kvm->arch.mmu_unsync_pages_lock); + spin_lock(&kvm->arch.mmu_unsync_pages_lock); /* * Recheck after taking the spinlock, a different vCPU @@ -2634,10 +2626,10 @@ int mmu_try_to_unsync_pages(struct kvm_vcpu *vcpu, struct kvm_memory_slot *slot, } WARN_ON(sp->role.level != PG_LEVEL_4K); - kvm_unsync_page(vcpu, sp); + kvm_unsync_page(kvm, sp); } if (locked) - spin_unlock(&vcpu->kvm->arch.mmu_unsync_pages_lock); + spin_unlock(&kvm->arch.mmu_unsync_pages_lock); /* * We need to ensure that the marking of unsync pages is visible @@ -3409,7 +3401,7 @@ static int mmu_first_shadow_root_alloc(struct kvm *kvm) { struct kvm_memslots *slots; struct kvm_memory_slot *slot; - int r = 0, i; + int r = 0, i, bkt; /* * Check if this is the first shadow root being allocated before @@ -3434,7 +3426,7 @@ static int mmu_first_shadow_root_alloc(struct kvm *kvm) for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) { slots = __kvm_memslots(kvm, i); - kvm_for_each_memslot(slot, slots) { + kvm_for_each_memslot(slot, bkt, slots) { /* * Both of these functions are no-ops if the target is * already allocated, so unconditionally calling both @@ -3734,21 +3726,13 @@ void kvm_mmu_sync_prev_roots(struct kvm_vcpu *vcpu) kvm_mmu_free_roots(vcpu, vcpu->arch.mmu, roots_to_free); } -static gpa_t nonpaging_gva_to_gpa(struct kvm_vcpu *vcpu, gpa_t vaddr, - u32 access, struct x86_exception *exception) +static gpa_t nonpaging_gva_to_gpa(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, + gpa_t vaddr, u32 access, + struct x86_exception *exception) { if (exception) exception->error_code = 0; - return vaddr; -} - -static gpa_t nonpaging_gva_to_gpa_nested(struct kvm_vcpu *vcpu, gpa_t vaddr, - u32 access, - struct x86_exception *exception) -{ - if (exception) - exception->error_code = 0; - return vcpu->arch.nested_mmu.translate_gpa(vcpu, vaddr, access, exception); + return kvm_translate_gpa(vcpu, mmu, vaddr, access, exception); } static bool mmio_info_in_cache(struct kvm_vcpu *vcpu, u64 addr, bool direct) @@ -3888,7 +3872,7 @@ static bool page_fault_handle_page_track(struct kvm_vcpu *vcpu, * guest is writing the page which is write tracked which can * not be fixed by page fault handler. */ - if (kvm_slot_page_track_is_active(vcpu, fault->slot, fault->gfn, KVM_PAGE_TRACK_WRITE)) + if (kvm_slot_page_track_is_active(vcpu->kvm, fault->slot, fault->gfn, KVM_PAGE_TRACK_WRITE)) return true; return false; @@ -4388,22 +4372,28 @@ static void reset_rsvds_bits_mask(struct kvm_vcpu *vcpu, static void __reset_rsvds_bits_mask_ept(struct rsvd_bits_validate *rsvd_check, - u64 pa_bits_rsvd, bool execonly) + u64 pa_bits_rsvd, bool execonly, int huge_page_level) { u64 high_bits_rsvd = pa_bits_rsvd & rsvd_bits(0, 51); + u64 large_1g_rsvd = 0, large_2m_rsvd = 0; u64 bad_mt_xwr; + if (huge_page_level < PG_LEVEL_1G) + large_1g_rsvd = rsvd_bits(7, 7); + if (huge_page_level < PG_LEVEL_2M) + large_2m_rsvd = rsvd_bits(7, 7); + rsvd_check->rsvd_bits_mask[0][4] = high_bits_rsvd | rsvd_bits(3, 7); rsvd_check->rsvd_bits_mask[0][3] = high_bits_rsvd | rsvd_bits(3, 7); - rsvd_check->rsvd_bits_mask[0][2] = high_bits_rsvd | rsvd_bits(3, 6); - rsvd_check->rsvd_bits_mask[0][1] = high_bits_rsvd | rsvd_bits(3, 6); + rsvd_check->rsvd_bits_mask[0][2] = high_bits_rsvd | rsvd_bits(3, 6) | large_1g_rsvd; + rsvd_check->rsvd_bits_mask[0][1] = high_bits_rsvd | rsvd_bits(3, 6) | large_2m_rsvd; rsvd_check->rsvd_bits_mask[0][0] = high_bits_rsvd; /* large page */ rsvd_check->rsvd_bits_mask[1][4] = rsvd_check->rsvd_bits_mask[0][4]; rsvd_check->rsvd_bits_mask[1][3] = rsvd_check->rsvd_bits_mask[0][3]; - rsvd_check->rsvd_bits_mask[1][2] = high_bits_rsvd | rsvd_bits(12, 29); - rsvd_check->rsvd_bits_mask[1][1] = high_bits_rsvd | rsvd_bits(12, 20); + rsvd_check->rsvd_bits_mask[1][2] = high_bits_rsvd | rsvd_bits(12, 29) | large_1g_rsvd; + rsvd_check->rsvd_bits_mask[1][1] = high_bits_rsvd | rsvd_bits(12, 20) | large_2m_rsvd; rsvd_check->rsvd_bits_mask[1][0] = rsvd_check->rsvd_bits_mask[0][0]; bad_mt_xwr = 0xFFull << (2 * 8); /* bits 3..5 must not be 2 */ @@ -4419,10 +4409,11 @@ __reset_rsvds_bits_mask_ept(struct rsvd_bits_validate *rsvd_check, } static void reset_rsvds_bits_mask_ept(struct kvm_vcpu *vcpu, - struct kvm_mmu *context, bool execonly) + struct kvm_mmu *context, bool execonly, int huge_page_level) { __reset_rsvds_bits_mask_ept(&context->guest_rsvd_check, - vcpu->arch.reserved_gpa_bits, execonly); + vcpu->arch.reserved_gpa_bits, execonly, + huge_page_level); } static inline u64 reserved_hpa_bits(void) @@ -4498,7 +4489,8 @@ reset_tdp_shadow_zero_bits_mask(struct kvm_vcpu *vcpu, false, true); else __reset_rsvds_bits_mask_ept(shadow_zero_check, - reserved_hpa_bits(), false); + reserved_hpa_bits(), false, + max_huge_page_level); if (!shadow_me_mask) return; @@ -4518,7 +4510,8 @@ reset_ept_shadow_zero_bits_mask(struct kvm_vcpu *vcpu, struct kvm_mmu *context, bool execonly) { __reset_rsvds_bits_mask_ept(&context->shadow_zero_check, - reserved_hpa_bits(), execonly); + reserved_hpa_bits(), execonly, + max_huge_page_level); } #define BYTE_MASK(access) \ @@ -4767,7 +4760,7 @@ kvm_calc_tdp_mmu_root_page_role(struct kvm_vcpu *vcpu, role.base.ad_disabled = (shadow_accessed_mask == 0); role.base.level = kvm_mmu_get_tdp_level(vcpu); role.base.direct = true; - role.base.gpte_is_8_bytes = true; + role.base.has_4_byte_gpte = false; return role; } @@ -4812,7 +4805,7 @@ kvm_calc_shadow_root_page_role_common(struct kvm_vcpu *vcpu, role.base.smep_andnot_wp = role.ext.cr4_smep && !____is_cr0_wp(regs); role.base.smap_andnot_wp = role.ext.cr4_smap && !____is_cr0_wp(regs); - role.base.gpte_is_8_bytes = ____is_cr0_pg(regs) && ____is_cr4_pae(regs); + role.base.has_4_byte_gpte = ____is_cr0_pg(regs) && !____is_cr4_pae(regs); return role; } @@ -4911,7 +4904,7 @@ kvm_calc_shadow_ept_root_page_role(struct kvm_vcpu *vcpu, bool accessed_dirty, role.base.smm = vcpu->arch.root_mmu.mmu_role.base.smm; role.base.level = level; - role.base.gpte_is_8_bytes = true; + role.base.has_4_byte_gpte = false; role.base.direct = false; role.base.ad_disabled = !accessed_dirty; role.base.guest_mode = true; @@ -4926,7 +4919,8 @@ kvm_calc_shadow_ept_root_page_role(struct kvm_vcpu *vcpu, bool accessed_dirty, } void kvm_init_shadow_ept_mmu(struct kvm_vcpu *vcpu, bool execonly, - bool accessed_dirty, gpa_t new_eptp) + int huge_page_level, bool accessed_dirty, + gpa_t new_eptp) { struct kvm_mmu *context = &vcpu->arch.guest_mmu; u8 level = vmx_eptp_page_walk_level(new_eptp); @@ -4953,7 +4947,7 @@ void kvm_init_shadow_ept_mmu(struct kvm_vcpu *vcpu, bool execonly, update_permission_bitmask(context, true); context->pkru_mask = 0; - reset_rsvds_bits_mask_ept(vcpu, context, execonly); + reset_rsvds_bits_mask_ept(vcpu, context, execonly, huge_page_level); reset_ept_shadow_zero_bits_mask(vcpu, context, execonly); } EXPORT_SYMBOL_GPL(kvm_init_shadow_ept_mmu); @@ -5017,13 +5011,13 @@ static void init_kvm_nested_mmu(struct kvm_vcpu *vcpu) * the gva_to_gpa functions between mmu and nested_mmu are swapped. */ if (!is_paging(vcpu)) - g_context->gva_to_gpa = nonpaging_gva_to_gpa_nested; + g_context->gva_to_gpa = nonpaging_gva_to_gpa; else if (is_long_mode(vcpu)) - g_context->gva_to_gpa = paging64_gva_to_gpa_nested; + g_context->gva_to_gpa = paging64_gva_to_gpa; else if (is_pae(vcpu)) - g_context->gva_to_gpa = paging64_gva_to_gpa_nested; + g_context->gva_to_gpa = paging64_gva_to_gpa; else - g_context->gva_to_gpa = paging32_gva_to_gpa_nested; + g_context->gva_to_gpa = paging32_gva_to_gpa; reset_guest_paging_metadata(vcpu, g_context); } @@ -5188,7 +5182,7 @@ static bool detect_write_misaligned(struct kvm_mmu_page *sp, gpa_t gpa, gpa, bytes, sp->role.word); offset = offset_in_page(gpa); - pte_size = sp->role.gpte_is_8_bytes ? 8 : 4; + pte_size = sp->role.has_4_byte_gpte ? 4 : 8; /* * Sometimes, the OS only writes the last one bytes to update status @@ -5212,7 +5206,7 @@ static u64 *get_written_sptes(struct kvm_mmu_page *sp, gpa_t gpa, int *nspte) page_offset = offset_in_page(gpa); level = sp->role.level; *nspte = 1; - if (!sp->role.gpte_is_8_bytes) { + if (sp->role.has_4_byte_gpte) { page_offset <<= 1; /* 32->64 */ /* * A 32-bit pde maps 4MB while the shadow pdes map @@ -5524,10 +5518,13 @@ static int __kvm_mmu_create(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu) mmu->root_hpa = INVALID_PAGE; mmu->root_pgd = 0; - mmu->translate_gpa = translate_gpa; for (i = 0; i < KVM_MMU_NUM_PREV_ROOTS; i++) mmu->prev_roots[i] = KVM_MMU_ROOT_INFO_INVALID; + /* vcpu->arch.guest_mmu isn't used when !tdp_enabled. */ + if (!tdp_enabled && mmu == &vcpu->arch.guest_mmu) + return 0; + /* * When using PAE paging, the four PDPTEs are treated as 'root' pages, * while the PDP table is a per-vCPU construct that's allocated at MMU @@ -5537,7 +5534,7 @@ static int __kvm_mmu_create(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu) * generally doesn't use PAE paging and can skip allocating the PDP * table. The main exception, handled here, is SVM's 32-bit NPT. The * other exception is for shadowing L1's 32-bit or PAE NPT on 64-bit - * KVM; that horror is handled on-demand by mmu_alloc_shadow_roots(). + * KVM; that horror is handled on-demand by mmu_alloc_special_roots(). */ if (tdp_enabled && kvm_mmu_get_tdp_level(vcpu) > PT32E_ROOT_LEVEL) return 0; @@ -5582,8 +5579,6 @@ int kvm_mmu_create(struct kvm_vcpu *vcpu) vcpu->arch.mmu = &vcpu->arch.root_mmu; vcpu->arch.walk_mmu = &vcpu->arch.root_mmu; - vcpu->arch.nested_mmu.translate_gpa = translate_nested_gpa; - ret = __kvm_mmu_create(vcpu, &vcpu->arch.guest_mmu); if (ret) return ret; @@ -5742,6 +5737,7 @@ static bool __kvm_zap_rmaps(struct kvm *kvm, gfn_t gfn_start, gfn_t gfn_end) { const struct kvm_memory_slot *memslot; struct kvm_memslots *slots; + struct kvm_memslot_iter iter; bool flush = false; gfn_t start, end; int i; @@ -5751,10 +5747,12 @@ static bool __kvm_zap_rmaps(struct kvm *kvm, gfn_t gfn_start, gfn_t gfn_end) for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) { slots = __kvm_memslots(kvm, i); - kvm_for_each_memslot(memslot, slots) { + + kvm_for_each_memslot_in_gfn_range(&iter, slots, gfn_start, gfn_end) { + memslot = iter.slot; start = max(gfn_start, memslot->base_gfn); end = min(gfn_end, memslot->base_gfn + memslot->npages); - if (start >= end) + if (WARN_ON_ONCE(start >= end)) continue; flush = slot_handle_level_range(kvm, memslot, kvm_zap_rmapp, @@ -5775,6 +5773,9 @@ void kvm_zap_gfn_range(struct kvm *kvm, gfn_t gfn_start, gfn_t gfn_end) bool flush; int i; + if (WARN_ON_ONCE(gfn_end <= gfn_start)) + return; + write_lock(&kvm->mmu_lock); kvm_inc_notifier_count(kvm, gfn_start, gfn_end); @@ -6164,30 +6165,6 @@ out: return ret; } -/* - * Calculate mmu pages needed for kvm. - */ -unsigned long kvm_mmu_calculate_default_mmu_pages(struct kvm *kvm) -{ - unsigned long nr_mmu_pages; - unsigned long nr_pages = 0; - struct kvm_memslots *slots; - struct kvm_memory_slot *memslot; - int i; - - for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) { - slots = __kvm_memslots(kvm, i); - - kvm_for_each_memslot(memslot, slots) - nr_pages += memslot->npages; - } - - nr_mmu_pages = nr_pages * KVM_PERMILLE_MMU_PAGES / 1000; - nr_mmu_pages = max(nr_mmu_pages, KVM_MIN_ALLOC_MMU_PAGES); - - return nr_mmu_pages; -} - void kvm_mmu_destroy(struct kvm_vcpu *vcpu) { kvm_mmu_unload(vcpu); diff --git a/arch/x86/kvm/mmu/mmu_internal.h b/arch/x86/kvm/mmu/mmu_internal.h index 52c6527b1a06..da6166b5c377 100644 --- a/arch/x86/kvm/mmu/mmu_internal.h +++ b/arch/x86/kvm/mmu/mmu_internal.h @@ -104,7 +104,7 @@ static inline int kvm_mmu_page_as_id(struct kvm_mmu_page *sp) return kvm_mmu_role_as_id(sp->role); } -static inline bool kvm_vcpu_ad_need_write_protect(struct kvm_vcpu *vcpu) +static inline bool kvm_mmu_page_ad_need_write_protect(struct kvm_mmu_page *sp) { /* * When using the EPT page-modification log, the GPAs in the CPU dirty @@ -112,13 +112,12 @@ static inline bool kvm_vcpu_ad_need_write_protect(struct kvm_vcpu *vcpu) * on write protection to record dirty pages, which bypasses PML, since * writes now result in a vmexit. Note, the check on CPU dirty logging * being enabled is mandatory as the bits used to denote WP-only SPTEs - * are reserved for NPT w/ PAE (32-bit KVM). + * are reserved for PAE paging (32-bit KVM). */ - return vcpu->arch.mmu == &vcpu->arch.guest_mmu && - kvm_x86_ops.cpu_dirty_log_size; + return kvm_x86_ops.cpu_dirty_log_size && sp->role.guest_mode; } -int mmu_try_to_unsync_pages(struct kvm_vcpu *vcpu, struct kvm_memory_slot *slot, +int mmu_try_to_unsync_pages(struct kvm *kvm, const struct kvm_memory_slot *slot, gfn_t gfn, bool can_unsync, bool prefetch); void kvm_mmu_gfn_disallow_lpage(const struct kvm_memory_slot *slot, gfn_t gfn); diff --git a/arch/x86/kvm/mmu/mmutrace.h b/arch/x86/kvm/mmu/mmutrace.h index b8151bbca36a..de5e8e4e1aa7 100644 --- a/arch/x86/kvm/mmu/mmutrace.h +++ b/arch/x86/kvm/mmu/mmutrace.h @@ -35,7 +35,7 @@ " %snxe %sad root %u %s%c", \ __entry->mmu_valid_gen, \ __entry->gfn, role.level, \ - role.gpte_is_8_bytes ? 8 : 4, \ + role.has_4_byte_gpte ? 4 : 8, \ role.quadrant, \ role.direct ? " direct" : "", \ access_str[role.access], \ diff --git a/arch/x86/kvm/mmu/page_track.c b/arch/x86/kvm/mmu/page_track.c index cc4eb5b7fb76..68eb1fb548b6 100644 --- a/arch/x86/kvm/mmu/page_track.c +++ b/arch/x86/kvm/mmu/page_track.c @@ -173,9 +173,9 @@ EXPORT_SYMBOL_GPL(kvm_slot_page_track_remove_page); /* * check if the corresponding access on the specified guest page is tracked. */ -bool kvm_slot_page_track_is_active(struct kvm_vcpu *vcpu, - struct kvm_memory_slot *slot, gfn_t gfn, - enum kvm_page_track_mode mode) +bool kvm_slot_page_track_is_active(struct kvm *kvm, + const struct kvm_memory_slot *slot, + gfn_t gfn, enum kvm_page_track_mode mode) { int index; @@ -186,7 +186,7 @@ bool kvm_slot_page_track_is_active(struct kvm_vcpu *vcpu, return false; if (mode == KVM_PAGE_TRACK_WRITE && - !kvm_page_track_write_tracking_enabled(vcpu->kvm)) + !kvm_page_track_write_tracking_enabled(kvm)) return false; index = gfn_to_index(gfn, slot->base_gfn, PG_LEVEL_4K); diff --git a/arch/x86/kvm/mmu/paging_tmpl.h b/arch/x86/kvm/mmu/paging_tmpl.h index 708a5d297fe1..5b5bdac97c7b 100644 --- a/arch/x86/kvm/mmu/paging_tmpl.h +++ b/arch/x86/kvm/mmu/paging_tmpl.h @@ -403,9 +403,8 @@ retry_walk: walker->table_gfn[walker->level - 1] = table_gfn; walker->pte_gpa[walker->level - 1] = pte_gpa; - real_gpa = mmu->translate_gpa(vcpu, gfn_to_gpa(table_gfn), - nested_access, - &walker->fault); + real_gpa = kvm_translate_gpa(vcpu, mmu, gfn_to_gpa(table_gfn), + nested_access, &walker->fault); /* * FIXME: This can happen if emulation (for of an INS/OUTS @@ -467,7 +466,7 @@ retry_walk: if (PTTYPE == 32 && walker->level > PG_LEVEL_4K && is_cpuid_PSE36()) gfn += pse36_gfn_delta(pte); - real_gpa = mmu->translate_gpa(vcpu, gfn_to_gpa(gfn), access, &walker->fault); + real_gpa = kvm_translate_gpa(vcpu, mmu, gfn_to_gpa(gfn), access, &walker->fault); if (real_gpa == UNMAPPED_GVA) return 0; @@ -547,16 +546,6 @@ static int FNAME(walk_addr)(struct guest_walker *walker, access); } -#if PTTYPE != PTTYPE_EPT -static int FNAME(walk_addr_nested)(struct guest_walker *walker, - struct kvm_vcpu *vcpu, gva_t addr, - u32 access) -{ - return FNAME(walk_addr_generic)(walker, vcpu, &vcpu->arch.nested_mmu, - addr, access); -} -#endif - static bool FNAME(prefetch_gpte)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp, u64 *spte, pt_element_t gpte, bool no_dirty_log) @@ -1000,50 +989,29 @@ static void FNAME(invlpg)(struct kvm_vcpu *vcpu, gva_t gva, hpa_t root_hpa) } /* 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, +static gpa_t FNAME(gva_to_gpa)(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, + 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, addr, access); - - if (r) { - gpa = gfn_to_gpa(walker.gfn); - gpa |= addr & ~PAGE_MASK; - } else if (exception) - *exception = walker.fault; - - return gpa; -} - -#if PTTYPE != PTTYPE_EPT -/* 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) -{ - struct guest_walker walker; - 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); + WARN_ON_ONCE((addr >> 32) && mmu == vcpu->arch.walk_mmu); #endif - r = FNAME(walk_addr_nested)(&walker, vcpu, vaddr, access); + r = FNAME(walk_addr_generic)(&walker, vcpu, mmu, addr, access); if (r) { gpa = gfn_to_gpa(walker.gfn); - gpa |= vaddr & ~PAGE_MASK; + gpa |= addr & ~PAGE_MASK; } else if (exception) *exception = walker.fault; return gpa; } -#endif /* * Using the cached information from sp->gfns is safe because: diff --git a/arch/x86/kvm/mmu/spte.c b/arch/x86/kvm/mmu/spte.c index fad546df0bba..351b04ad62a1 100644 --- a/arch/x86/kvm/mmu/spte.c +++ b/arch/x86/kvm/mmu/spte.c @@ -91,7 +91,7 @@ static bool kvm_is_mmio_pfn(kvm_pfn_t pfn) } bool make_spte(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp, - struct kvm_memory_slot *slot, + const struct kvm_memory_slot *slot, unsigned int pte_access, gfn_t gfn, kvm_pfn_t pfn, u64 old_spte, bool prefetch, bool can_unsync, bool host_writable, u64 *new_spte) @@ -102,7 +102,7 @@ bool make_spte(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp, if (sp->role.ad_disabled) spte |= SPTE_TDP_AD_DISABLED_MASK; - else if (kvm_vcpu_ad_need_write_protect(vcpu)) + else if (kvm_mmu_page_ad_need_write_protect(sp)) spte |= SPTE_TDP_AD_WRPROT_ONLY_MASK; /* @@ -162,7 +162,7 @@ bool make_spte(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp, * e.g. it's write-tracked (upper-level SPs) or has one or more * shadow pages and unsync'ing pages is not allowed. */ - if (mmu_try_to_unsync_pages(vcpu, slot, gfn, can_unsync, prefetch)) { + if (mmu_try_to_unsync_pages(vcpu->kvm, slot, gfn, can_unsync, prefetch)) { pgprintk("%s: found shadow page for %llx, marking ro\n", __func__, gfn); wrprot = true; diff --git a/arch/x86/kvm/mmu/spte.h b/arch/x86/kvm/mmu/spte.h index cc432f9a966b..a4af2a42695c 100644 --- a/arch/x86/kvm/mmu/spte.h +++ b/arch/x86/kvm/mmu/spte.h @@ -330,7 +330,7 @@ static inline u64 get_mmio_spte_generation(u64 spte) } bool make_spte(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp, - struct kvm_memory_slot *slot, + const struct kvm_memory_slot *slot, unsigned int pte_access, gfn_t gfn, kvm_pfn_t pfn, u64 old_spte, bool prefetch, bool can_unsync, bool host_writable, u64 *new_spte); diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c index 1beb4ca90560..7b1bc816b7c3 100644 --- a/arch/x86/kvm/mmu/tdp_mmu.c +++ b/arch/x86/kvm/mmu/tdp_mmu.c @@ -165,7 +165,7 @@ static union kvm_mmu_page_role page_role_for_level(struct kvm_vcpu *vcpu, role = vcpu->arch.mmu->mmu_role.base; role.level = level; role.direct = true; - role.gpte_is_8_bytes = true; + role.has_4_byte_gpte = false; role.access = ACC_ALL; role.ad_disabled = !shadow_accessed_mask; diff --git a/arch/x86/kvm/pmu.c b/arch/x86/kvm/pmu.c index 0c2133eb4cf6..261b39cbef6e 100644 --- a/arch/x86/kvm/pmu.c +++ b/arch/x86/kvm/pmu.c @@ -55,43 +55,41 @@ static void kvm_pmi_trigger_fn(struct irq_work *irq_work) kvm_pmu_deliver_pmi(vcpu); } -static void kvm_perf_overflow(struct perf_event *perf_event, - struct perf_sample_data *data, - struct pt_regs *regs) +static inline void __kvm_perf_overflow(struct kvm_pmc *pmc, bool in_pmi) { - struct kvm_pmc *pmc = perf_event->overflow_handler_context; struct kvm_pmu *pmu = pmc_to_pmu(pmc); - 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); - } + /* Ignore counters that have been reprogrammed already. */ + if (test_and_set_bit(pmc->idx, pmu->reprogram_pmi)) + return; + + __set_bit(pmc->idx, (unsigned long *)&pmu->global_status); + kvm_make_request(KVM_REQ_PMU, pmc->vcpu); + + if (!pmc->intr) + return; + + /* + * Inject PMI. If vcpu was in a guest mode during NMI PMI + * can be ejected on a guest mode re-entry. Otherwise we can't + * be sure that vcpu wasn't executing hlt instruction at the + * time of vmexit and is not going to re-enter guest mode until + * woken up. So we should wake it, but this is impossible from + * NMI context. Do it from irq work instead. + */ + if (in_pmi && !kvm_handling_nmi_from_guest(pmc->vcpu)) + irq_work_queue(&pmc_to_pmu(pmc)->irq_work); + else + kvm_make_request(KVM_REQ_PMI, pmc->vcpu); } -static void kvm_perf_overflow_intr(struct perf_event *perf_event, - struct perf_sample_data *data, - struct pt_regs *regs) +static void kvm_perf_overflow(struct perf_event *perf_event, + struct perf_sample_data *data, + struct pt_regs *regs) { struct kvm_pmc *pmc = perf_event->overflow_handler_context; - struct kvm_pmu *pmu = pmc_to_pmu(pmc); - - 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); - /* - * Inject PMI. If vcpu was in a guest mode during NMI PMI - * can be ejected on a guest mode re-entry. Otherwise we can't - * be sure that vcpu wasn't executing hlt instruction at the - * time of vmexit and is not going to re-enter guest mode until - * woken up. So we should wake it, but this is impossible from - * NMI context. Do it from irq work instead. - */ - if (!kvm_handling_nmi_from_guest(pmc->vcpu)) - irq_work_queue(&pmc_to_pmu(pmc)->irq_work); - else - kvm_make_request(KVM_REQ_PMI, pmc->vcpu); - } + __kvm_perf_overflow(pmc, true); } static void pmc_reprogram_counter(struct kvm_pmc *pmc, u32 type, @@ -126,7 +124,6 @@ static void pmc_reprogram_counter(struct kvm_pmc *pmc, u32 type, } event = perf_event_create_kernel_counter(&attr, -1, current, - intr ? kvm_perf_overflow_intr : kvm_perf_overflow, pmc); if (IS_ERR(event)) { pr_debug_ratelimited("kvm_pmu: event creation failed %ld for pmc->idx = %d\n", @@ -138,6 +135,7 @@ static void pmc_reprogram_counter(struct kvm_pmc *pmc, u32 type, pmc_to_pmu(pmc)->event_count++; clear_bit(pmc->idx, pmc_to_pmu(pmc)->reprogram_pmi); pmc->is_paused = false; + pmc->intr = intr; } static void pmc_pause_counter(struct kvm_pmc *pmc) @@ -174,7 +172,6 @@ static bool pmc_resume_counter(struct kvm_pmc *pmc) void reprogram_gp_counter(struct kvm_pmc *pmc, u64 eventsel) { unsigned config, type = PERF_TYPE_RAW; - u8 event_select, unit_mask; struct kvm *kvm = pmc->vcpu->kvm; struct kvm_pmu_event_filter *filter; int i; @@ -206,17 +203,12 @@ void reprogram_gp_counter(struct kvm_pmc *pmc, u64 eventsel) if (!allow_event) return; - event_select = eventsel & ARCH_PERFMON_EVENTSEL_EVENT; - unit_mask = (eventsel & ARCH_PERFMON_EVENTSEL_UMASK) >> 8; - if (!(eventsel & (ARCH_PERFMON_EVENTSEL_EDGE | ARCH_PERFMON_EVENTSEL_INV | ARCH_PERFMON_EVENTSEL_CMASK | HSW_IN_TX | HSW_IN_TX_CHECKPOINTED))) { - config = kvm_x86_ops.pmu_ops->find_arch_event(pmc_to_pmu(pmc), - event_select, - unit_mask); + config = kvm_x86_ops.pmu_ops->pmc_perf_hw_id(pmc); if (config != PERF_COUNT_HW_MAX) type = PERF_TYPE_HARDWARE; } @@ -268,7 +260,7 @@ void reprogram_fixed_counter(struct kvm_pmc *pmc, u8 ctrl, int idx) pmc->current_config = (u64)ctrl; pmc_reprogram_counter(pmc, PERF_TYPE_HARDWARE, - kvm_x86_ops.pmu_ops->find_fixed_event(idx), + kvm_x86_ops.pmu_ops->pmc_perf_hw_id(pmc), !(en_field & 0x2), /* exclude user */ !(en_field & 0x1), /* exclude kernel */ pmi, false, false); @@ -490,6 +482,66 @@ void kvm_pmu_destroy(struct kvm_vcpu *vcpu) kvm_pmu_reset(vcpu); } +static void kvm_pmu_incr_counter(struct kvm_pmc *pmc) +{ + struct kvm_pmu *pmu = pmc_to_pmu(pmc); + u64 prev_count; + + prev_count = pmc->counter; + pmc->counter = (pmc->counter + 1) & pmc_bitmask(pmc); + + reprogram_counter(pmu, pmc->idx); + if (pmc->counter < prev_count) + __kvm_perf_overflow(pmc, false); +} + +static inline bool eventsel_match_perf_hw_id(struct kvm_pmc *pmc, + unsigned int perf_hw_id) +{ + u64 old_eventsel = pmc->eventsel; + unsigned int config; + + pmc->eventsel &= (ARCH_PERFMON_EVENTSEL_EVENT | ARCH_PERFMON_EVENTSEL_UMASK); + config = kvm_x86_ops.pmu_ops->pmc_perf_hw_id(pmc); + pmc->eventsel = old_eventsel; + return config == perf_hw_id; +} + +static inline bool cpl_is_matched(struct kvm_pmc *pmc) +{ + bool select_os, select_user; + u64 config = pmc->current_config; + + if (pmc_is_gp(pmc)) { + select_os = config & ARCH_PERFMON_EVENTSEL_OS; + select_user = config & ARCH_PERFMON_EVENTSEL_USR; + } else { + select_os = config & 0x1; + select_user = config & 0x2; + } + + return (static_call(kvm_x86_get_cpl)(pmc->vcpu) == 0) ? select_os : select_user; +} + +void kvm_pmu_trigger_event(struct kvm_vcpu *vcpu, u64 perf_hw_id) +{ + struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); + struct kvm_pmc *pmc; + int i; + + for_each_set_bit(i, pmu->all_valid_pmc_idx, X86_PMC_IDX_MAX) { + pmc = kvm_x86_ops.pmu_ops->pmc_idx_to_pmc(pmu, i); + + if (!pmc || !pmc_is_enabled(pmc) || !pmc_speculative_in_use(pmc)) + continue; + + /* Ignore checks for edge detect, pin control, invert and CMASK bits */ + if (eventsel_match_perf_hw_id(pmc, perf_hw_id) && cpl_is_matched(pmc)) + kvm_pmu_incr_counter(pmc); + } +} +EXPORT_SYMBOL_GPL(kvm_pmu_trigger_event); + int kvm_vm_ioctl_set_pmu_event_filter(struct kvm *kvm, void __user *argp) { struct kvm_pmu_event_filter tmp, *filter; diff --git a/arch/x86/kvm/pmu.h b/arch/x86/kvm/pmu.h index 59d6b76203d5..7a7b8d5b775e 100644 --- a/arch/x86/kvm/pmu.h +++ b/arch/x86/kvm/pmu.h @@ -24,9 +24,7 @@ struct kvm_event_hw_type_mapping { }; struct kvm_pmu_ops { - unsigned (*find_arch_event)(struct kvm_pmu *pmu, u8 event_select, - u8 unit_mask); - unsigned (*find_fixed_event)(int idx); + unsigned int (*pmc_perf_hw_id)(struct kvm_pmc *pmc); 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 *(*rdpmc_ecx_to_pmc)(struct kvm_vcpu *vcpu, @@ -159,6 +157,7 @@ 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); +void kvm_pmu_trigger_event(struct kvm_vcpu *vcpu, u64 perf_hw_id); bool is_vmware_backdoor_pmc(u32 pmc_idx); diff --git a/arch/x86/kvm/svm/avic.c b/arch/x86/kvm/svm/avic.c index 8f9af7b7dbbe..0e5b49294086 100644 --- a/arch/x86/kvm/svm/avic.c +++ b/arch/x86/kvm/svm/avic.c @@ -293,7 +293,7 @@ static void avic_kick_target_vcpus(struct kvm *kvm, struct kvm_lapic *source, u32 icrl, u32 icrh) { struct kvm_vcpu *vcpu; - int i; + unsigned long i; kvm_for_each_vcpu(i, vcpu, kvm) { bool m = kvm_apic_match_dest(vcpu, source, @@ -675,10 +675,18 @@ int svm_deliver_avic_intr(struct kvm_vcpu *vcpu, int vec) smp_mb__after_atomic(); if (avic_vcpu_is_running(vcpu)) { - int cpuid = vcpu->cpu; + int cpu = READ_ONCE(vcpu->cpu); - if (cpuid != get_cpu()) - wrmsrl(SVM_AVIC_DOORBELL, kvm_cpu_get_apicid(cpuid)); + /* + * Note, the vCPU could get migrated to a different pCPU at any + * point, which could result in signalling the wrong/previous + * pCPU. But if that happens the vCPU is guaranteed to do a + * VMRUN (after being migrated) and thus will process pending + * interrupts, i.e. a doorbell is not needed (and the spurious + * one is harmless). + */ + if (cpu != get_cpu()) + wrmsrl(SVM_AVIC_DOORBELL, kvm_cpu_get_apicid(cpu)); put_cpu(); } else kvm_vcpu_wake_up(vcpu); diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c index f8b7bc04b3e7..cf206855ebf0 100644 --- a/arch/x86/kvm/svm/nested.c +++ b/arch/x86/kvm/svm/nested.c @@ -58,8 +58,9 @@ static void svm_inject_page_fault_nested(struct kvm_vcpu *vcpu, struct x86_excep struct vcpu_svm *svm = to_svm(vcpu); WARN_ON(!is_guest_mode(vcpu)); - if (vmcb_is_intercept(&svm->nested.ctl, INTERCEPT_EXCEPTION_OFFSET + PF_VECTOR) && - !svm->nested.nested_run_pending) { + if (vmcb12_is_intercept(&svm->nested.ctl, + INTERCEPT_EXCEPTION_OFFSET + PF_VECTOR) && + !svm->nested.nested_run_pending) { svm->vmcb->control.exit_code = SVM_EXIT_EXCP_BASE + PF_VECTOR; svm->vmcb->control.exit_code_hi = 0; svm->vmcb->control.exit_info_1 = fault->error_code; @@ -121,7 +122,8 @@ static void nested_svm_uninit_mmu_context(struct kvm_vcpu *vcpu) void recalc_intercepts(struct vcpu_svm *svm) { - struct vmcb_control_area *c, *h, *g; + struct vmcb_control_area *c, *h; + struct vmcb_ctrl_area_cached *g; unsigned int i; vmcb_mark_dirty(svm->vmcb, VMCB_INTERCEPTS); @@ -163,37 +165,6 @@ void recalc_intercepts(struct vcpu_svm *svm) vmcb_set_intercept(c, INTERCEPT_VMSAVE); } -static void copy_vmcb_control_area(struct vmcb_control_area *dst, - struct vmcb_control_area *from) -{ - unsigned int i; - - for (i = 0; i < MAX_INTERCEPT; i++) - dst->intercepts[i] = from->intercepts[i]; - - dst->iopm_base_pa = from->iopm_base_pa; - dst->msrpm_base_pa = from->msrpm_base_pa; - dst->tsc_offset = from->tsc_offset; - /* asid not copied, it is handled manually for svm->vmcb. */ - dst->tlb_ctl = from->tlb_ctl; - dst->int_ctl = from->int_ctl; - dst->int_vector = from->int_vector; - dst->int_state = from->int_state; - dst->exit_code = from->exit_code; - dst->exit_code_hi = from->exit_code_hi; - dst->exit_info_1 = from->exit_info_1; - dst->exit_info_2 = from->exit_info_2; - dst->exit_int_info = from->exit_int_info; - dst->exit_int_info_err = from->exit_int_info_err; - dst->nested_ctl = from->nested_ctl; - dst->event_inj = from->event_inj; - dst->event_inj_err = from->event_inj_err; - dst->nested_cr3 = from->nested_cr3; - dst->virt_ext = from->virt_ext; - dst->pause_filter_count = from->pause_filter_count; - dst->pause_filter_thresh = from->pause_filter_thresh; -} - static bool nested_svm_vmrun_msrpm(struct vcpu_svm *svm) { /* @@ -203,7 +174,7 @@ static bool nested_svm_vmrun_msrpm(struct vcpu_svm *svm) */ int i; - if (!(vmcb_is_intercept(&svm->nested.ctl, INTERCEPT_MSR_PROT))) + if (!(vmcb12_is_intercept(&svm->nested.ctl, INTERCEPT_MSR_PROT))) return true; for (i = 0; i < MSRPM_OFFSETS; i++) { @@ -250,10 +221,10 @@ static bool nested_svm_check_tlb_ctl(struct kvm_vcpu *vcpu, u8 tlb_ctl) } } -static bool nested_vmcb_check_controls(struct kvm_vcpu *vcpu, - struct vmcb_control_area *control) +static bool __nested_vmcb_check_controls(struct kvm_vcpu *vcpu, + struct vmcb_ctrl_area_cached *control) { - if (CC(!vmcb_is_intercept(control, INTERCEPT_VMRUN))) + if (CC(!vmcb12_is_intercept(control, INTERCEPT_VMRUN))) return false; if (CC(control->asid == 0)) @@ -275,9 +246,20 @@ static bool nested_vmcb_check_controls(struct kvm_vcpu *vcpu, return true; } -static bool nested_vmcb_check_cr3_cr4(struct kvm_vcpu *vcpu, - struct vmcb_save_area *save) +/* Common checks that apply to both L1 and L2 state. */ +static bool __nested_vmcb_check_save(struct kvm_vcpu *vcpu, + struct vmcb_save_area_cached *save) { + if (CC(!(save->efer & EFER_SVME))) + return false; + + if (CC((save->cr0 & X86_CR0_CD) == 0 && (save->cr0 & X86_CR0_NW)) || + CC(save->cr0 & ~0xffffffffULL)) + return false; + + if (CC(!kvm_dr6_valid(save->dr6)) || CC(!kvm_dr7_valid(save->dr7))) + return false; + /* * These checks are also performed by KVM_SET_SREGS, * except that EFER.LMA is not checked by SVM against @@ -293,48 +275,90 @@ static bool nested_vmcb_check_cr3_cr4(struct kvm_vcpu *vcpu, if (CC(!kvm_is_valid_cr4(vcpu, save->cr4))) return false; + if (CC(!kvm_valid_efer(vcpu, save->efer))) + return false; + return true; } -/* Common checks that apply to both L1 and L2 state. */ -static bool nested_vmcb_valid_sregs(struct kvm_vcpu *vcpu, - struct vmcb_save_area *save) +static bool nested_vmcb_check_save(struct kvm_vcpu *vcpu) { - /* - * FIXME: these should be done after copying the fields, - * to avoid TOC/TOU races. For these save area checks - * the possible damage is limited since kvm_set_cr0 and - * kvm_set_cr4 handle failure; EFER_SVME is an exception - * so it is force-set later in nested_prepare_vmcb_save. - */ - if (CC(!(save->efer & EFER_SVME))) - return false; + struct vcpu_svm *svm = to_svm(vcpu); + struct vmcb_save_area_cached *save = &svm->nested.save; - if (CC((save->cr0 & X86_CR0_CD) == 0 && (save->cr0 & X86_CR0_NW)) || - CC(save->cr0 & ~0xffffffffULL)) - return false; + return __nested_vmcb_check_save(vcpu, save); +} - if (CC(!kvm_dr6_valid(save->dr6)) || CC(!kvm_dr7_valid(save->dr7))) - return false; +static bool nested_vmcb_check_controls(struct kvm_vcpu *vcpu) +{ + struct vcpu_svm *svm = to_svm(vcpu); + struct vmcb_ctrl_area_cached *ctl = &svm->nested.ctl; - if (!nested_vmcb_check_cr3_cr4(vcpu, save)) - return false; + return __nested_vmcb_check_controls(vcpu, ctl); +} - if (CC(!kvm_valid_efer(vcpu, save->efer))) - return false; +static +void __nested_copy_vmcb_control_to_cache(struct vmcb_ctrl_area_cached *to, + struct vmcb_control_area *from) +{ + unsigned int i; - return true; + for (i = 0; i < MAX_INTERCEPT; i++) + to->intercepts[i] = from->intercepts[i]; + + to->iopm_base_pa = from->iopm_base_pa; + to->msrpm_base_pa = from->msrpm_base_pa; + to->tsc_offset = from->tsc_offset; + to->tlb_ctl = from->tlb_ctl; + to->int_ctl = from->int_ctl; + to->int_vector = from->int_vector; + to->int_state = from->int_state; + to->exit_code = from->exit_code; + to->exit_code_hi = from->exit_code_hi; + to->exit_info_1 = from->exit_info_1; + to->exit_info_2 = from->exit_info_2; + to->exit_int_info = from->exit_int_info; + to->exit_int_info_err = from->exit_int_info_err; + to->nested_ctl = from->nested_ctl; + to->event_inj = from->event_inj; + to->event_inj_err = from->event_inj_err; + to->nested_cr3 = from->nested_cr3; + to->virt_ext = from->virt_ext; + to->pause_filter_count = from->pause_filter_count; + to->pause_filter_thresh = from->pause_filter_thresh; + + /* Copy asid here because nested_vmcb_check_controls will check it. */ + to->asid = from->asid; + to->msrpm_base_pa &= ~0x0fffULL; + to->iopm_base_pa &= ~0x0fffULL; } -void nested_load_control_from_vmcb12(struct vcpu_svm *svm, - struct vmcb_control_area *control) +void nested_copy_vmcb_control_to_cache(struct vcpu_svm *svm, + struct vmcb_control_area *control) { - copy_vmcb_control_area(&svm->nested.ctl, control); + __nested_copy_vmcb_control_to_cache(&svm->nested.ctl, control); +} + +static void __nested_copy_vmcb_save_to_cache(struct vmcb_save_area_cached *to, + struct vmcb_save_area *from) +{ + /* + * Copy only fields that are validated, as we need them + * to avoid TOC/TOU races. + */ + to->efer = from->efer; + to->cr0 = from->cr0; + to->cr3 = from->cr3; + to->cr4 = from->cr4; - /* Copy it here because nested_svm_check_controls will check it. */ - svm->nested.ctl.asid = control->asid; - svm->nested.ctl.msrpm_base_pa &= ~0x0fffULL; - svm->nested.ctl.iopm_base_pa &= ~0x0fffULL; + to->dr6 = from->dr6; + to->dr7 = from->dr7; +} + +void nested_copy_vmcb_save_to_cache(struct vcpu_svm *svm, + struct vmcb_save_area *save) +{ + __nested_copy_vmcb_save_to_cache(&svm->nested.save, save); } /* @@ -437,14 +461,13 @@ static int nested_svm_load_cr3(struct kvm_vcpu *vcpu, unsigned long cr3, return -EINVAL; if (reload_pdptrs && !nested_npt && is_pae_paging(vcpu) && - CC(!load_pdptrs(vcpu, vcpu->arch.walk_mmu, cr3))) + CC(!load_pdptrs(vcpu, cr3))) return -EINVAL; if (!nested_npt) kvm_mmu_new_pgd(vcpu, cr3); vcpu->arch.cr3 = cr3; - kvm_register_mark_available(vcpu, VCPU_EXREG_CR3); /* Re-initialize the MMU, e.g. to pick up CR4 MMU role changes. */ kvm_init_mmu(vcpu); @@ -490,15 +513,10 @@ static void nested_vmcb02_prepare_save(struct vcpu_svm *svm, struct vmcb *vmcb12 kvm_set_rflags(&svm->vcpu, vmcb12->save.rflags | X86_EFLAGS_FIXED); - /* - * Force-set EFER_SVME even though it is checked earlier on the - * VMCB12, because the guest can flip the bit between the check - * and now. Clearing EFER_SVME would call svm_free_nested. - */ - svm_set_efer(&svm->vcpu, vmcb12->save.efer | EFER_SVME); + svm_set_efer(&svm->vcpu, svm->nested.save.efer); - svm_set_cr0(&svm->vcpu, vmcb12->save.cr0); - svm_set_cr4(&svm->vcpu, vmcb12->save.cr4); + svm_set_cr0(&svm->vcpu, svm->nested.save.cr0); + svm_set_cr4(&svm->vcpu, svm->nested.save.cr4); svm->vcpu.arch.cr2 = vmcb12->save.cr2; @@ -513,8 +531,8 @@ static void nested_vmcb02_prepare_save(struct vcpu_svm *svm, struct vmcb *vmcb12 /* These bits will be set properly on the first execution when new_vmc12 is true */ if (unlikely(new_vmcb12 || vmcb_is_dirty(vmcb12, VMCB_DR))) { - svm->vmcb->save.dr7 = vmcb12->save.dr7 | DR7_FIXED_1; - svm->vcpu.arch.dr6 = vmcb12->save.dr6 | DR6_ACTIVE_LOW; + svm->vmcb->save.dr7 = svm->nested.save.dr7 | DR7_FIXED_1; + svm->vcpu.arch.dr6 = svm->nested.save.dr6 | DR6_ACTIVE_LOW; vmcb_mark_dirty(svm->vmcb, VMCB_DR); } } @@ -628,7 +646,7 @@ int enter_svm_guest_mode(struct kvm_vcpu *vcpu, u64 vmcb12_gpa, nested_vmcb02_prepare_control(svm); nested_vmcb02_prepare_save(svm, vmcb12); - ret = nested_svm_load_cr3(&svm->vcpu, vmcb12->save.cr3, + ret = nested_svm_load_cr3(&svm->vcpu, svm->nested.save.cr3, nested_npt_enabled(svm), from_vmrun); if (ret) return ret; @@ -678,10 +696,11 @@ int nested_svm_vmrun(struct kvm_vcpu *vcpu) if (WARN_ON_ONCE(!svm->nested.initialized)) return -EINVAL; - nested_load_control_from_vmcb12(svm, &vmcb12->control); + nested_copy_vmcb_control_to_cache(svm, &vmcb12->control); + nested_copy_vmcb_save_to_cache(svm, &vmcb12->save); - if (!nested_vmcb_valid_sregs(vcpu, &vmcb12->save) || - !nested_vmcb_check_controls(vcpu, &svm->nested.ctl)) { + if (!nested_vmcb_check_save(vcpu) || + !nested_vmcb_check_controls(vcpu)) { vmcb12->control.exit_code = SVM_EXIT_ERR; vmcb12->control.exit_code_hi = 0; vmcb12->control.exit_info_1 = 0; @@ -988,7 +1007,7 @@ static int nested_svm_exit_handled_msr(struct vcpu_svm *svm) u32 offset, msr, value; int write, mask; - if (!(vmcb_is_intercept(&svm->nested.ctl, INTERCEPT_MSR_PROT))) + if (!(vmcb12_is_intercept(&svm->nested.ctl, INTERCEPT_MSR_PROT))) return NESTED_EXIT_HOST; msr = svm->vcpu.arch.regs[VCPU_REGS_RCX]; @@ -1015,7 +1034,7 @@ static int nested_svm_intercept_ioio(struct vcpu_svm *svm) u8 start_bit; u64 gpa; - if (!(vmcb_is_intercept(&svm->nested.ctl, INTERCEPT_IOIO_PROT))) + if (!(vmcb12_is_intercept(&svm->nested.ctl, INTERCEPT_IOIO_PROT))) return NESTED_EXIT_HOST; port = svm->vmcb->control.exit_info_1 >> 16; @@ -1046,12 +1065,12 @@ static int nested_svm_intercept(struct vcpu_svm *svm) vmexit = nested_svm_intercept_ioio(svm); break; case SVM_EXIT_READ_CR0 ... SVM_EXIT_WRITE_CR8: { - if (vmcb_is_intercept(&svm->nested.ctl, exit_code)) + if (vmcb12_is_intercept(&svm->nested.ctl, exit_code)) vmexit = NESTED_EXIT_DONE; break; } case SVM_EXIT_READ_DR0 ... SVM_EXIT_WRITE_DR7: { - if (vmcb_is_intercept(&svm->nested.ctl, exit_code)) + if (vmcb12_is_intercept(&svm->nested.ctl, exit_code)) vmexit = NESTED_EXIT_DONE; break; } @@ -1069,7 +1088,7 @@ static int nested_svm_intercept(struct vcpu_svm *svm) break; } default: { - if (vmcb_is_intercept(&svm->nested.ctl, exit_code)) + if (vmcb12_is_intercept(&svm->nested.ctl, exit_code)) vmexit = NESTED_EXIT_DONE; } } @@ -1147,7 +1166,7 @@ static void nested_svm_inject_exception_vmexit(struct vcpu_svm *svm) static inline bool nested_exit_on_init(struct vcpu_svm *svm) { - return vmcb_is_intercept(&svm->nested.ctl, INTERCEPT_INIT); + return vmcb12_is_intercept(&svm->nested.ctl, INTERCEPT_INIT); } static int svm_check_nested_events(struct kvm_vcpu *vcpu) @@ -1251,11 +1270,47 @@ void nested_svm_update_tsc_ratio_msr(struct kvm_vcpu *vcpu) svm_write_tsc_multiplier(vcpu, vcpu->arch.tsc_scaling_ratio); } +/* Inverse operation of nested_copy_vmcb_control_to_cache(). asid is copied too. */ +static void nested_copy_vmcb_cache_to_control(struct vmcb_control_area *dst, + struct vmcb_ctrl_area_cached *from) +{ + unsigned int i; + + memset(dst, 0, sizeof(struct vmcb_control_area)); + + for (i = 0; i < MAX_INTERCEPT; i++) + dst->intercepts[i] = from->intercepts[i]; + + dst->iopm_base_pa = from->iopm_base_pa; + dst->msrpm_base_pa = from->msrpm_base_pa; + dst->tsc_offset = from->tsc_offset; + dst->asid = from->asid; + dst->tlb_ctl = from->tlb_ctl; + dst->int_ctl = from->int_ctl; + dst->int_vector = from->int_vector; + dst->int_state = from->int_state; + dst->exit_code = from->exit_code; + dst->exit_code_hi = from->exit_code_hi; + dst->exit_info_1 = from->exit_info_1; + dst->exit_info_2 = from->exit_info_2; + dst->exit_int_info = from->exit_int_info; + dst->exit_int_info_err = from->exit_int_info_err; + dst->nested_ctl = from->nested_ctl; + dst->event_inj = from->event_inj; + dst->event_inj_err = from->event_inj_err; + dst->nested_cr3 = from->nested_cr3; + dst->virt_ext = from->virt_ext; + dst->pause_filter_count = from->pause_filter_count; + dst->pause_filter_thresh = from->pause_filter_thresh; +} + static int svm_get_nested_state(struct kvm_vcpu *vcpu, struct kvm_nested_state __user *user_kvm_nested_state, u32 user_data_size) { struct vcpu_svm *svm; + struct vmcb_control_area *ctl; + unsigned long r; struct kvm_nested_state kvm_state = { .flags = 0, .format = KVM_STATE_NESTED_FORMAT_SVM, @@ -1297,9 +1352,18 @@ static int svm_get_nested_state(struct kvm_vcpu *vcpu, */ if (clear_user(user_vmcb, KVM_STATE_NESTED_SVM_VMCB_SIZE)) return -EFAULT; - if (copy_to_user(&user_vmcb->control, &svm->nested.ctl, - sizeof(user_vmcb->control))) + + ctl = kzalloc(sizeof(*ctl), GFP_KERNEL); + if (!ctl) + return -ENOMEM; + + nested_copy_vmcb_cache_to_control(ctl, &svm->nested.ctl); + r = copy_to_user(&user_vmcb->control, ctl, + sizeof(user_vmcb->control)); + kfree(ctl); + if (r) return -EFAULT; + if (copy_to_user(&user_vmcb->save, &svm->vmcb01.ptr->save, sizeof(user_vmcb->save))) return -EFAULT; @@ -1316,6 +1380,8 @@ static int svm_set_nested_state(struct kvm_vcpu *vcpu, &user_kvm_nested_state->data.svm[0]; struct vmcb_control_area *ctl; struct vmcb_save_area *save; + struct vmcb_save_area_cached save_cached; + struct vmcb_ctrl_area_cached ctl_cached; unsigned long cr0; int ret; @@ -1368,7 +1434,8 @@ static int svm_set_nested_state(struct kvm_vcpu *vcpu, goto out_free; ret = -EINVAL; - if (!nested_vmcb_check_controls(vcpu, ctl)) + __nested_copy_vmcb_control_to_cache(&ctl_cached, ctl); + if (!__nested_vmcb_check_controls(vcpu, &ctl_cached)) goto out_free; /* @@ -1383,10 +1450,11 @@ static int svm_set_nested_state(struct kvm_vcpu *vcpu, * Validate host state saved from before VMRUN (see * nested_svm_check_permissions). */ + __nested_copy_vmcb_save_to_cache(&save_cached, save); if (!(save->cr0 & X86_CR0_PG) || !(save->cr0 & X86_CR0_PE) || (save->rflags & X86_EFLAGS_VM) || - !nested_vmcb_valid_sregs(vcpu, save)) + !__nested_vmcb_check_save(vcpu, &save_cached)) goto out_free; /* @@ -1422,7 +1490,7 @@ static int svm_set_nested_state(struct kvm_vcpu *vcpu, svm->nested.vmcb12_gpa = kvm_state->hdr.svm.vmcb_pa; svm_copy_vmrun_state(&svm->vmcb01.ptr->save, save); - nested_load_control_from_vmcb12(svm, ctl); + nested_copy_vmcb_control_to_cache(svm, ctl); svm_switch_vmcb(svm, &svm->nested.vmcb02); nested_vmcb02_prepare_control(svm); @@ -1449,7 +1517,7 @@ static bool svm_get_nested_state_pages(struct kvm_vcpu *vcpu) * the guest CR3 might be restored prior to setting the nested * state which can lead to a load of wrong PDPTRs. */ - if (CC(!load_pdptrs(vcpu, vcpu->arch.walk_mmu, vcpu->arch.cr3))) + if (CC(!load_pdptrs(vcpu, vcpu->arch.cr3))) return false; if (!nested_svm_vmrun_msrpm(svm)) { diff --git a/arch/x86/kvm/svm/pmu.c b/arch/x86/kvm/svm/pmu.c index b4095dfeeee6..12d8b301065a 100644 --- a/arch/x86/kvm/svm/pmu.c +++ b/arch/x86/kvm/svm/pmu.c @@ -16,6 +16,7 @@ #include "cpuid.h" #include "lapic.h" #include "pmu.h" +#include "svm.h" enum pmu_type { PMU_TYPE_COUNTER = 0, @@ -100,6 +101,9 @@ static inline struct kvm_pmc *get_gp_pmc_amd(struct kvm_pmu *pmu, u32 msr, { struct kvm_vcpu *vcpu = pmu_to_vcpu(pmu); + if (!pmu) + return NULL; + switch (msr) { case MSR_F15H_PERF_CTL0: case MSR_F15H_PERF_CTL1: @@ -134,12 +138,16 @@ static inline struct kvm_pmc *get_gp_pmc_amd(struct kvm_pmu *pmu, u32 msr, return &pmu->gp_counters[msr_to_index(msr)]; } -static unsigned amd_find_arch_event(struct kvm_pmu *pmu, - u8 event_select, - u8 unit_mask) +static unsigned int amd_pmc_perf_hw_id(struct kvm_pmc *pmc) { + u8 event_select = pmc->eventsel & ARCH_PERFMON_EVENTSEL_EVENT; + u8 unit_mask = (pmc->eventsel & ARCH_PERFMON_EVENTSEL_UMASK) >> 8; int i; + /* return PERF_COUNT_HW_MAX as AMD doesn't have fixed events */ + if (WARN_ON(pmc_is_fixed(pmc))) + return PERF_COUNT_HW_MAX; + for (i = 0; i < ARRAY_SIZE(amd_event_mapping); i++) if (amd_event_mapping[i].eventsel == event_select && amd_event_mapping[i].unit_mask == unit_mask) @@ -151,12 +159,6 @@ static unsigned amd_find_arch_event(struct kvm_pmu *pmu, return amd_event_mapping[i].event_type; } -/* return PERF_COUNT_HW_MAX as AMD doesn't have fixed events */ -static unsigned amd_find_fixed_event(int idx) -{ - return PERF_COUNT_HW_MAX; -} - /* check if a PMC is enabled by comparing it against global_ctrl bits. Because * AMD CPU doesn't have global_ctrl MSR, all PMCs are enabled (return TRUE). */ @@ -319,8 +321,7 @@ static void amd_pmu_reset(struct kvm_vcpu *vcpu) } struct kvm_pmu_ops amd_pmu_ops = { - .find_arch_event = amd_find_arch_event, - .find_fixed_event = amd_find_fixed_event, + .pmc_perf_hw_id = amd_pmc_perf_hw_id, .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, diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c index be2883141220..6a22798eaaee 100644 --- a/arch/x86/kvm/svm/sev.c +++ b/arch/x86/kvm/svm/sev.c @@ -636,7 +636,8 @@ static int __sev_launch_update_vmsa(struct kvm *kvm, struct kvm_vcpu *vcpu, static int sev_launch_update_vmsa(struct kvm *kvm, struct kvm_sev_cmd *argp) { struct kvm_vcpu *vcpu; - int i, ret; + unsigned long i; + int ret; if (!sev_es_guest(kvm)) return -ENOTTY; @@ -1593,7 +1594,7 @@ static void sev_unlock_two_vms(struct kvm *dst_kvm, struct kvm *src_kvm) static int sev_lock_vcpus_for_migration(struct kvm *kvm) { struct kvm_vcpu *vcpu; - int i, j; + unsigned long i, j; kvm_for_each_vcpu(i, vcpu, kvm) { if (mutex_lock_killable(&vcpu->mutex)) @@ -1615,7 +1616,7 @@ out_unlock: static void sev_unlock_vcpus_for_migration(struct kvm *kvm) { struct kvm_vcpu *vcpu; - int i; + unsigned long i; kvm_for_each_vcpu(i, vcpu, kvm) { mutex_unlock(&vcpu->mutex); @@ -1642,7 +1643,7 @@ static void sev_migrate_from(struct kvm_sev_info *dst, static int sev_es_migrate_from(struct kvm *dst, struct kvm *src) { - int i; + unsigned long i; struct kvm_vcpu *dst_vcpu, *src_vcpu; struct vcpu_svm *dst_svm, *src_svm; diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index 9079d2fdc12e..46bcc706f257 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -192,6 +192,10 @@ module_param(vgif, int, 0444); static int lbrv = true; module_param(lbrv, int, 0444); +/* enable/disable PMU virtualization */ +bool pmu = true; +module_param(pmu, bool, 0444); + static int tsc_scaling = true; module_param(tsc_scaling, int, 0444); @@ -265,7 +269,7 @@ u32 svm_msrpm_offset(u32 msr) #define MAX_INST_SIZE 15 -static int get_max_npt_level(void) +static int get_npt_level(void) { #ifdef CONFIG_X86_64 return pgtable_l5_enabled() ? PT64_ROOT_5LEVEL : PT64_ROOT_4LEVEL; @@ -585,12 +589,10 @@ static int svm_cpu_init(int cpu) if (!sd) return ret; sd->cpu = cpu; - sd->save_area = alloc_page(GFP_KERNEL); + sd->save_area = alloc_page(GFP_KERNEL | __GFP_ZERO); if (!sd->save_area) goto free_cpu_data; - clear_page(page_address(sd->save_area)); - ret = sev_cpu_init(sd); if (ret) goto free_save_area; @@ -954,6 +956,10 @@ static __init void svm_set_cpu_caps(void) boot_cpu_has(X86_FEATURE_AMD_SSBD)) kvm_cpu_cap_set(X86_FEATURE_VIRT_SSBD); + /* AMD PMU PERFCTR_CORE CPUID */ + if (pmu && boot_cpu_has(X86_FEATURE_PERFCTR_CORE)) + kvm_cpu_cap_set(X86_FEATURE_PERFCTR_CORE); + /* CPUID 0x8000001F (SME/SEV features) */ sev_set_cpu_caps(); } @@ -1029,9 +1035,9 @@ static __init int svm_hardware_setup(void) if (!boot_cpu_has(X86_FEATURE_NPT)) npt_enabled = false; - /* Force VM NPT level equal to the host's max NPT level */ - kvm_configure_mmu(npt_enabled, get_max_npt_level(), - get_max_npt_level(), PG_LEVEL_1G); + /* Force VM NPT level equal to the host's paging level */ + kvm_configure_mmu(npt_enabled, get_npt_level(), + get_npt_level(), PG_LEVEL_1G); pr_info("kvm: Nested Paging %sabled\n", npt_enabled ? "en" : "dis"); /* Note, SEV setup consumes npt_enabled. */ @@ -1087,6 +1093,9 @@ static __init int svm_hardware_setup(void) pr_info("LBR virtualization supported\n"); } + if (!pmu) + pr_info("PMU virtualization is disabled\n"); + svm_set_cpu_caps(); /* @@ -1596,10 +1605,16 @@ static bool svm_get_if_flag(struct kvm_vcpu *vcpu) static void svm_cache_reg(struct kvm_vcpu *vcpu, enum kvm_reg reg) { + kvm_register_mark_available(vcpu, reg); + switch (reg) { case VCPU_EXREG_PDPTR: - BUG_ON(!npt_enabled); - load_pdptrs(vcpu, vcpu->arch.walk_mmu, kvm_read_cr3(vcpu)); + /* + * When !npt_enabled, mmu->pdptrs[] is already available since + * it is always updated per SDM when moving to CRs. + */ + if (npt_enabled) + load_pdptrs(vcpu, kvm_read_cr3(vcpu)); break; default: KVM_BUG_ON(1, vcpu->kvm); @@ -1786,6 +1801,24 @@ static void svm_set_gdt(struct kvm_vcpu *vcpu, struct desc_ptr *dt) vmcb_mark_dirty(svm->vmcb, VMCB_DT); } +static void svm_post_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3) +{ + struct vcpu_svm *svm = to_svm(vcpu); + + /* + * For guests that don't set guest_state_protected, the cr3 update is + * handled via kvm_mmu_load() while entering the guest. For guests + * that do (SEV-ES/SEV-SNP), the cr3 update needs to be written to + * VMCB save area now, since the save area will become the initial + * contents of the VMSA, and future VMCB save area updates won't be + * seen. + */ + if (sev_es_guest(vcpu->kvm)) { + svm->vmcb->save.cr3 = cr3; + vmcb_mark_dirty(svm->vmcb, VMCB_CR); + } +} + void svm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0) { struct vcpu_svm *svm = to_svm(vcpu); @@ -2517,7 +2550,7 @@ static bool check_selective_cr0_intercepted(struct kvm_vcpu *vcpu, bool ret = false; if (!is_guest_mode(vcpu) || - (!(vmcb_is_intercept(&svm->nested.ctl, INTERCEPT_SELECTIVE_CR0)))) + (!(vmcb12_is_intercept(&svm->nested.ctl, INTERCEPT_SELECTIVE_CR0)))) return false; cr0 &= ~SVM_CR0_SELECTIVE_MASK; @@ -3931,6 +3964,7 @@ static __no_kcsan fastpath_t svm_vcpu_run(struct kvm_vcpu *vcpu) vcpu->arch.regs[VCPU_REGS_RSP] = svm->vmcb->save.rsp; vcpu->arch.regs[VCPU_REGS_RIP] = svm->vmcb->save.rip; } + vcpu->arch.regs_dirty = 0; if (unlikely(svm->vmcb->control.exit_code == SVM_EXIT_NMI)) kvm_before_interrupt(vcpu, KVM_HANDLING_NMI); @@ -3965,8 +3999,7 @@ static __no_kcsan fastpath_t svm_vcpu_run(struct kvm_vcpu *vcpu) vcpu->arch.apf.host_apf_flags = kvm_read_and_reset_apf_flags(); - if (npt_enabled) - kvm_register_clear_available(vcpu, VCPU_EXREG_PDPTR); + vcpu->arch.regs_avail &= ~SVM_REGS_LAZY_LOAD_SET; /* * We need to handle MC intercepts here before the vcpu has a chance to @@ -3996,9 +4029,6 @@ static void svm_load_mmu_pgd(struct kvm_vcpu *vcpu, hpa_t root_hpa, hv_track_root_tdp(vcpu, root_hpa); - /* Loading L2's CR3 is handled by enter_svm_guest_mode. */ - if (!test_bit(VCPU_EXREG_CR3, (ulong *)&vcpu->arch.regs_avail)) - return; cr3 = vcpu->arch.cr3; } else if (vcpu->arch.mmu->shadow_root_level >= PT64_ROOT_4LEVEL) { cr3 = __sme_set(root_hpa) | kvm_get_active_pcid(vcpu); @@ -4217,7 +4247,7 @@ static int svm_check_intercept(struct kvm_vcpu *vcpu, info->intercept == x86_intercept_clts) break; - if (!(vmcb_is_intercept(&svm->nested.ctl, + if (!(vmcb12_is_intercept(&svm->nested.ctl, INTERCEPT_SELECTIVE_CR0))) break; @@ -4436,7 +4466,8 @@ static int svm_leave_smm(struct kvm_vcpu *vcpu, const char *smstate) */ vmcb12 = map.hva; - nested_load_control_from_vmcb12(svm, &vmcb12->control); + nested_copy_vmcb_control_to_cache(svm, &vmcb12->control); + nested_copy_vmcb_save_to_cache(svm, &vmcb12->save); ret = enter_svm_guest_mode(vcpu, vmcb12_gpa, vmcb12, false); unmap_save: @@ -4611,6 +4642,7 @@ static struct kvm_x86_ops svm_x86_ops __initdata = { .get_cpl = svm_get_cpl, .get_cs_db_l_bits = kvm_get_cs_db_l_bits, .set_cr0 = svm_set_cr0, + .post_set_cr3 = svm_post_set_cr3, .is_valid_cr4 = svm_is_valid_cr4, .set_cr4 = svm_set_cr4, .set_efer = svm_set_efer, diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h index 1c7306c370fa..9f153c59f2c8 100644 --- a/arch/x86/kvm/svm/svm.h +++ b/arch/x86/kvm/svm/svm.h @@ -32,6 +32,7 @@ extern u32 msrpm_offsets[MSRPM_OFFSETS] __read_mostly; extern bool npt_enabled; extern bool intercept_smi; +extern bool pmu; /* * Clean bits in VMCB. @@ -105,6 +106,40 @@ struct kvm_vmcb_info { uint64_t asid_generation; }; +struct vmcb_save_area_cached { + u64 efer; + u64 cr4; + u64 cr3; + u64 cr0; + u64 dr7; + u64 dr6; +}; + +struct vmcb_ctrl_area_cached { + u32 intercepts[MAX_INTERCEPT]; + u16 pause_filter_thresh; + u16 pause_filter_count; + u64 iopm_base_pa; + u64 msrpm_base_pa; + u64 tsc_offset; + u32 asid; + u8 tlb_ctl; + u32 int_ctl; + u32 int_vector; + u32 int_state; + u32 exit_code; + u32 exit_code_hi; + u64 exit_info_1; + u64 exit_info_2; + u32 exit_int_info; + u32 exit_int_info_err; + u64 nested_ctl; + u32 event_inj; + u32 event_inj_err; + u64 nested_cr3; + u64 virt_ext; +}; + struct svm_nested_state { struct kvm_vmcb_info vmcb02; u64 hsave_msr; @@ -120,7 +155,13 @@ struct svm_nested_state { bool nested_run_pending; /* cache for control fields of the guest */ - struct vmcb_control_area ctl; + struct vmcb_ctrl_area_cached ctl; + + /* + * Note: this struct is not kept up-to-date while L2 runs; it is only + * valid within nested_svm_vmrun. + */ + struct vmcb_save_area_cached save; bool initialized; }; @@ -285,6 +326,16 @@ static __always_inline struct vcpu_svm *to_svm(struct kvm_vcpu *vcpu) return container_of(vcpu, struct vcpu_svm, vcpu); } +/* + * Only the PDPTRs are loaded on demand into the shadow MMU. All other + * fields are synchronized in handle_exit, because accessing the VMCB is cheap. + * + * CR3 might be out of date in the VMCB but it is not marked dirty; instead, + * KVM_REQ_LOAD_MMU_PGD is always requested when the cached vcpu->arch.cr3 + * is changed. svm_load_mmu_pgd() then syncs the new CR3 value into the VMCB. + */ +#define SVM_REGS_LAZY_LOAD_SET (1 << VCPU_EXREG_PDPTR) + static inline void vmcb_set_intercept(struct vmcb_control_area *control, u32 bit) { WARN_ON_ONCE(bit >= 32 * MAX_INTERCEPT); @@ -303,6 +354,12 @@ static inline bool vmcb_is_intercept(struct vmcb_control_area *control, u32 bit) return test_bit(bit, (unsigned long *)&control->intercepts); } +static inline bool vmcb12_is_intercept(struct vmcb_ctrl_area_cached *control, u32 bit) +{ + WARN_ON_ONCE(bit >= 32 * MAX_INTERCEPT); + return test_bit(bit, (unsigned long *)&control->intercepts); +} + static inline void set_dr_intercepts(struct vcpu_svm *svm) { struct vmcb *vmcb = svm->vmcb01.ptr; @@ -455,17 +512,17 @@ static inline bool nested_svm_virtualize_tpr(struct kvm_vcpu *vcpu) static inline bool nested_exit_on_smi(struct vcpu_svm *svm) { - return vmcb_is_intercept(&svm->nested.ctl, INTERCEPT_SMI); + return vmcb12_is_intercept(&svm->nested.ctl, INTERCEPT_SMI); } static inline bool nested_exit_on_intr(struct vcpu_svm *svm) { - return vmcb_is_intercept(&svm->nested.ctl, INTERCEPT_INTR); + return vmcb12_is_intercept(&svm->nested.ctl, INTERCEPT_INTR); } static inline bool nested_exit_on_nmi(struct vcpu_svm *svm) { - return vmcb_is_intercept(&svm->nested.ctl, INTERCEPT_NMI); + return vmcb12_is_intercept(&svm->nested.ctl, INTERCEPT_NMI); } int enter_svm_guest_mode(struct kvm_vcpu *vcpu, @@ -494,8 +551,10 @@ int nested_svm_check_exception(struct vcpu_svm *svm, unsigned nr, int nested_svm_exit_special(struct vcpu_svm *svm); void nested_svm_update_tsc_ratio_msr(struct kvm_vcpu *vcpu); void svm_write_tsc_multiplier(struct kvm_vcpu *vcpu, u64 multiplier); -void nested_load_control_from_vmcb12(struct vcpu_svm *svm, - struct vmcb_control_area *control); +void nested_copy_vmcb_control_to_cache(struct vcpu_svm *svm, + struct vmcb_control_area *control); +void nested_copy_vmcb_save_to_cache(struct vcpu_svm *svm, + struct vmcb_save_area *save); void nested_sync_control_from_vmcb02(struct vcpu_svm *svm); void nested_vmcb02_compute_g_pat(struct vcpu_svm *svm); void svm_switch_vmcb(struct vcpu_svm *svm, struct kvm_vmcb_info *target_vmcb); diff --git a/arch/x86/kvm/trace.h b/arch/x86/kvm/trace.h index 953b0fcb21ee..92e6f6702f00 100644 --- a/arch/x86/kvm/trace.h +++ b/arch/x86/kvm/trace.h @@ -1356,6 +1356,30 @@ TRACE_EVENT(kvm_apicv_update_request, __entry->bit) ); +TRACE_EVENT(kvm_apicv_accept_irq, + TP_PROTO(__u32 apicid, __u16 dm, __u16 tm, __u8 vec), + TP_ARGS(apicid, dm, tm, vec), + + TP_STRUCT__entry( + __field( __u32, apicid ) + __field( __u16, dm ) + __field( __u16, tm ) + __field( __u8, vec ) + ), + + TP_fast_assign( + __entry->apicid = apicid; + __entry->dm = dm; + __entry->tm = tm; + __entry->vec = vec; + ), + + TP_printk("apicid %x vec %u (%s|%s)", + __entry->apicid, __entry->vec, + __print_symbolic((__entry->dm >> 8 & 0x7), kvm_deliver_mode), + __entry->tm ? "level" : "edge") +); + /* * Tracepoint for AMD AVIC */ diff --git a/arch/x86/kvm/vmx/capabilities.h b/arch/x86/kvm/vmx/capabilities.h index 4705ad55abb5..c8029b7845b6 100644 --- a/arch/x86/kvm/vmx/capabilities.h +++ b/arch/x86/kvm/vmx/capabilities.h @@ -312,6 +312,15 @@ static inline bool cpu_has_vmx_ept_1g_page(void) return vmx_capability.ept & VMX_EPT_1GB_PAGE_BIT; } +static inline int ept_caps_to_lpage_level(u32 ept_caps) +{ + if (ept_caps & VMX_EPT_1GB_PAGE_BIT) + return PG_LEVEL_1G; + if (ept_caps & VMX_EPT_2MB_PAGE_BIT) + return PG_LEVEL_2M; + return PG_LEVEL_4K; +} + static inline bool cpu_has_vmx_ept_ad_bits(void) { return vmx_capability.ept & VMX_EPT_AD_BIT; diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c index 9c941535f78c..f235f77cbc03 100644 --- a/arch/x86/kvm/vmx/nested.c +++ b/arch/x86/kvm/vmx/nested.c @@ -245,7 +245,8 @@ static void vmx_sync_vmcs_host_state(struct vcpu_vmx *vmx, src = &prev->host_state; dest = &vmx->loaded_vmcs->host_state; - vmx_set_host_fs_gs(dest, src->fs_sel, src->gs_sel, src->fs_base, src->gs_base); + vmx_set_vmcs_host_state(dest, src->cr3, src->fs_sel, src->gs_sel, + src->fs_base, src->gs_base); dest->ldt_sel = src->ldt_sel; #ifdef CONFIG_X86_64 dest->ds_sel = src->ds_sel; @@ -269,7 +270,13 @@ static void vmx_switch_vmcs(struct kvm_vcpu *vcpu, struct loaded_vmcs *vmcs) vmx_sync_vmcs_host_state(vmx, prev); put_cpu(); - vmx_register_cache_reset(vcpu); + vcpu->arch.regs_avail = ~VMX_REGS_LAZY_LOAD_SET; + + /* + * All lazily updated registers will be reloaded from VMCS12 on both + * vmentry and vmexit. + */ + vcpu->arch.regs_dirty = 0; } /* @@ -391,9 +398,11 @@ static void nested_ept_inject_page_fault(struct kvm_vcpu *vcpu, static void nested_ept_new_eptp(struct kvm_vcpu *vcpu) { - kvm_init_shadow_ept_mmu(vcpu, - to_vmx(vcpu)->nested.msrs.ept_caps & - VMX_EPT_EXECUTE_ONLY_BIT, + struct vcpu_vmx *vmx = to_vmx(vcpu); + bool execonly = vmx->nested.msrs.ept_caps & VMX_EPT_EXECUTE_ONLY_BIT; + int ept_lpage_level = ept_caps_to_lpage_level(vmx->nested.msrs.ept_caps); + + kvm_init_shadow_ept_mmu(vcpu, execonly, ept_lpage_level, nested_ept_ad_enabled(vcpu), nested_ept_get_eptp(vcpu)); } @@ -591,6 +600,7 @@ static inline bool nested_vmx_prepare_msr_bitmap(struct kvm_vcpu *vcpu, int msr; unsigned long *msr_bitmap_l1; unsigned long *msr_bitmap_l0 = vmx->nested.vmcs02.msr_bitmap; + struct hv_enlightened_vmcs *evmcs = vmx->nested.hv_evmcs; struct kvm_host_map *map = &vmx->nested.msr_bitmap_map; /* Nothing to do if the MSR bitmap is not in use. */ @@ -598,6 +608,19 @@ static inline bool nested_vmx_prepare_msr_bitmap(struct kvm_vcpu *vcpu, !nested_cpu_has(vmcs12, CPU_BASED_USE_MSR_BITMAPS)) return false; + /* + * MSR bitmap update can be skipped when: + * - MSR bitmap for L1 hasn't changed. + * - Nested hypervisor (L1) is attempting to launch the same L2 as + * before. + * - Nested hypervisor (L1) has enabled 'Enlightened MSR Bitmap' feature + * and tells KVM (L0) there were no changes in MSR bitmap for L2. + */ + if (!vmx->nested.force_msr_bitmap_recalc && evmcs && + evmcs->hv_enlightenments_control.msr_bitmap && + evmcs->hv_clean_fields & HV_VMX_ENLIGHTENED_CLEAN_FIELD_MSR_BITMAP) + return true; + if (kvm_vcpu_map(vcpu, gpa_to_gfn(vmcs12->msr_bitmap), map)) return false; @@ -664,6 +687,8 @@ static inline bool nested_vmx_prepare_msr_bitmap(struct kvm_vcpu *vcpu, kvm_vcpu_unmap(vcpu, &vmx->nested.msr_bitmap_map, false); + vmx->nested.force_msr_bitmap_recalc = false; + return true; } @@ -1095,7 +1120,7 @@ static int nested_vmx_load_cr3(struct kvm_vcpu *vcpu, unsigned long cr3, * must not be dereferenced. */ if (reload_pdptrs && !nested_ept && is_pae_paging(vcpu) && - CC(!load_pdptrs(vcpu, vcpu->arch.walk_mmu, cr3))) { + CC(!load_pdptrs(vcpu, cr3))) { *entry_failure_code = ENTRY_FAIL_PDPTE; return -EINVAL; } @@ -1104,7 +1129,7 @@ static int nested_vmx_load_cr3(struct kvm_vcpu *vcpu, unsigned long cr3, kvm_mmu_new_pgd(vcpu, cr3); vcpu->arch.cr3 = cr3; - kvm_register_mark_available(vcpu, VCPU_EXREG_CR3); + kvm_register_mark_dirty(vcpu, VCPU_EXREG_CR3); /* Re-initialize the MMU, e.g. to pick up CR4 MMU role changes. */ kvm_init_mmu(vcpu); @@ -2021,10 +2046,13 @@ static enum nested_evmptrld_status nested_vmx_handle_enlightened_vmptrld( * 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) + if (from_launch || evmcs_gpa_changed) { vmx->nested.hv_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL; + vmx->nested.force_msr_bitmap_recalc = true; + } + return EVMPTRLD_SUCCEEDED; } @@ -3027,7 +3055,7 @@ static int nested_vmx_check_guest_state(struct kvm_vcpu *vcpu, static int nested_vmx_check_vmentry_hw(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); - unsigned long cr3, cr4; + unsigned long cr4; bool vm_fail; if (!nested_early_check) @@ -3050,12 +3078,6 @@ static int nested_vmx_check_vmentry_hw(struct kvm_vcpu *vcpu) */ vmcs_writel(GUEST_RFLAGS, 0); - cr3 = __get_current_cr3_fast(); - if (unlikely(cr3 != vmx->loaded_vmcs->host_state.cr3)) { - vmcs_writel(HOST_CR3, cr3); - vmx->loaded_vmcs->host_state.cr3 = cr3; - } - cr4 = cr4_read_shadow(); if (unlikely(cr4 != vmx->loaded_vmcs->host_state.cr4)) { vmcs_writel(HOST_CR4, cr4); @@ -3145,7 +3167,7 @@ static bool nested_get_vmcs12_pages(struct kvm_vcpu *vcpu) * the guest CR3 might be restored prior to setting the nested * state which can lead to a load of wrong PDPTRs. */ - if (CC(!load_pdptrs(vcpu, vcpu->arch.walk_mmu, vcpu->arch.cr3))) + if (CC(!load_pdptrs(vcpu, vcpu->arch.cr3))) return false; } @@ -3504,10 +3526,13 @@ static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch) if (evmptrld_status == EVMPTRLD_ERROR) { kvm_queue_exception(vcpu, UD_VECTOR); return 1; - } else if (CC(evmptrld_status == EVMPTRLD_VMFAIL)) { - return nested_vmx_failInvalid(vcpu); } + kvm_pmu_trigger_event(vcpu, PERF_COUNT_HW_BRANCH_INSTRUCTIONS); + + if (CC(evmptrld_status == EVMPTRLD_VMFAIL)) + return nested_vmx_failInvalid(vcpu); + if (CC(!evmptr_is_valid(vmx->nested.hv_evmcs_vmptr) && vmx->nested.current_vmptr == INVALID_GPA)) return nested_vmx_failInvalid(vcpu); @@ -3603,7 +3628,7 @@ static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch) !(nested_cpu_has(vmcs12, CPU_BASED_INTR_WINDOW_EXITING) && (vmcs12->guest_rflags & X86_EFLAGS_IF))) { vmx->nested.nested_run_pending = 0; - return kvm_vcpu_halt(vcpu); + return kvm_emulate_halt_noskip(vcpu); } break; case GUEST_ACTIVITY_WAIT_SIPI: @@ -5258,6 +5283,7 @@ static void set_current_vmptr(struct vcpu_vmx *vmx, gpa_t vmptr) vmx->nested.need_vmcs12_to_shadow_sync = true; } vmx->nested.dirty_vmcs12 = true; + vmx->nested.force_msr_bitmap_recalc = true; } /* Emulate the VMPTRLD instruction */ @@ -6393,6 +6419,7 @@ static int vmx_set_nested_state(struct kvm_vcpu *vcpu, goto error_guest_mode; vmx->nested.dirty_vmcs12 = true; + vmx->nested.force_msr_bitmap_recalc = true; ret = nested_vmx_enter_non_root_mode(vcpu, false); if (ret) goto error_guest_mode; diff --git a/arch/x86/kvm/vmx/pmu_intel.c b/arch/x86/kvm/vmx/pmu_intel.c index 1b7456b2177b..5e0ac57d6d1b 100644 --- a/arch/x86/kvm/vmx/pmu_intel.c +++ b/arch/x86/kvm/vmx/pmu_intel.c @@ -68,16 +68,17 @@ static void global_ctrl_changed(struct kvm_pmu *pmu, u64 data) reprogram_counter(pmu, bit); } -static unsigned intel_find_arch_event(struct kvm_pmu *pmu, - u8 event_select, - u8 unit_mask) +static unsigned int intel_pmc_perf_hw_id(struct kvm_pmc *pmc) { + struct kvm_pmu *pmu = pmc_to_pmu(pmc); + u8 event_select = pmc->eventsel & ARCH_PERFMON_EVENTSEL_EVENT; + u8 unit_mask = (pmc->eventsel & ARCH_PERFMON_EVENTSEL_UMASK) >> 8; int i; for (i = 0; i < ARRAY_SIZE(intel_arch_events); i++) - if (intel_arch_events[i].eventsel == event_select - && intel_arch_events[i].unit_mask == unit_mask - && (pmu->available_event_types & (1 << i))) + if (intel_arch_events[i].eventsel == event_select && + intel_arch_events[i].unit_mask == unit_mask && + (pmc_is_fixed(pmc) || pmu->available_event_types & (1 << i))) break; if (i == ARRAY_SIZE(intel_arch_events)) @@ -86,18 +87,6 @@ static unsigned intel_find_arch_event(struct kvm_pmu *pmu, return intel_arch_events[i].event_type; } -static unsigned intel_find_fixed_event(int idx) -{ - u32 event; - size_t size = ARRAY_SIZE(fixed_pmc_events); - - if (idx >= size) - return PERF_COUNT_HW_MAX; - - 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. */ static bool intel_pmc_is_enabled(struct kvm_pmc *pmc) { @@ -459,6 +448,21 @@ static int intel_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) return 1; } +static void setup_fixed_pmc_eventsel(struct kvm_pmu *pmu) +{ + size_t size = ARRAY_SIZE(fixed_pmc_events); + struct kvm_pmc *pmc; + u32 event; + int i; + + for (i = 0; i < pmu->nr_arch_fixed_counters; i++) { + pmc = &pmu->fixed_counters[i]; + event = fixed_pmc_events[array_index_nospec(i, size)]; + pmc->eventsel = (intel_arch_events[event].unit_mask << 8) | + intel_arch_events[event].eventsel; + } +} + static void intel_pmu_refresh(struct kvm_vcpu *vcpu) { struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); @@ -500,12 +504,14 @@ static void intel_pmu_refresh(struct kvm_vcpu *vcpu) pmu->nr_arch_fixed_counters = 0; } else { pmu->nr_arch_fixed_counters = - min_t(int, edx.split.num_counters_fixed, - x86_pmu.num_counters_fixed); + min3(ARRAY_SIZE(fixed_pmc_events), + (size_t) edx.split.num_counters_fixed, + (size_t) x86_pmu.num_counters_fixed); edx.split.bit_width_fixed = min_t(int, edx.split.bit_width_fixed, x86_pmu.bit_width_fixed); pmu->counter_bitmask[KVM_PMC_FIXED] = ((u64)1 << edx.split.bit_width_fixed) - 1; + setup_fixed_pmc_eventsel(pmu); } pmu->global_ctrl = ((1ull << pmu->nr_arch_gp_counters) - 1) | @@ -703,8 +709,7 @@ static void intel_pmu_cleanup(struct kvm_vcpu *vcpu) } struct kvm_pmu_ops intel_pmu_ops = { - .find_arch_event = intel_find_arch_event, - .find_fixed_event = intel_find_fixed_event, + .pmc_perf_hw_id = intel_pmc_perf_hw_id, .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, diff --git a/arch/x86/kvm/vmx/posted_intr.c b/arch/x86/kvm/vmx/posted_intr.c index 1c94783b5a54..88c53c521094 100644 --- a/arch/x86/kvm/vmx/posted_intr.c +++ b/arch/x86/kvm/vmx/posted_intr.c @@ -11,10 +11,22 @@ #include "vmx.h" /* - * We maintain a per-CPU linked-list of vCPU, so in wakeup_handler() we - * can find which vCPU should be waken up. + * Maintain a per-CPU list of vCPUs that need to be awakened by wakeup_handler() + * when a WAKEUP_VECTOR interrupted is posted. vCPUs are added to the list when + * the vCPU is scheduled out and is blocking (e.g. in HLT) with IRQs enabled. + * The vCPUs posted interrupt descriptor is updated at the same time to set its + * notification vector to WAKEUP_VECTOR, so that posted interrupt from devices + * wake the target vCPUs. vCPUs are removed from the list and the notification + * vector is reset when the vCPU is scheduled in. */ static DEFINE_PER_CPU(struct list_head, blocked_vcpu_on_cpu); +/* + * Protect the per-CPU list with a per-CPU spinlock to handle task migration. + * When a blocking vCPU is awakened _and_ migrated to a different pCPU, the + * ->sched_in() path will need to take the vCPU off the list of the _previous_ + * CPU. IRQs must be disabled when taking this lock, otherwise deadlock will + * occur if a wakeup IRQ arrives and attempts to acquire the lock. + */ static DEFINE_PER_CPU(spinlock_t, blocked_vcpu_on_cpu_lock); static inline struct pi_desc *vcpu_to_pi_desc(struct kvm_vcpu *vcpu) @@ -22,6 +34,20 @@ static inline struct pi_desc *vcpu_to_pi_desc(struct kvm_vcpu *vcpu) return &(to_vmx(vcpu)->pi_desc); } +static int pi_try_set_control(struct pi_desc *pi_desc, u64 old, u64 new) +{ + /* + * PID.ON can be set at any time by a different vCPU or by hardware, + * e.g. a device. PID.control must be written atomically, and the + * update must be retried with a fresh snapshot an ON change causes + * the cmpxchg to fail. + */ + if (cmpxchg64(&pi_desc->control, old, new) != old) + return -EBUSY; + + return 0; +} + void vmx_vcpu_pi_load(struct kvm_vcpu *vcpu, int cpu) { struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu); @@ -29,11 +55,14 @@ void vmx_vcpu_pi_load(struct kvm_vcpu *vcpu, int cpu) unsigned int dest; /* - * In case of hot-plug or hot-unplug, we may have to undo - * vmx_vcpu_pi_put even if there is no assigned device. And we - * always keep PI.NDST up to date for simplicity: it makes the - * code easier, and CPU migration is not a fast path. + * To simplify hot-plug and dynamic toggling of APICv, keep PI.NDST and + * PI.SN up-to-date even if there is no assigned device or if APICv is + * deactivated due to a dynamic inhibit bit, e.g. for Hyper-V's SyncIC. */ + if (!enable_apicv || !lapic_in_kernel(vcpu)) + return; + + /* Nothing to do if PI.SN and PI.NDST both have the desired value. */ if (!pi_test_sn(pi_desc) && vcpu->cpu == cpu) return; @@ -49,20 +78,17 @@ void vmx_vcpu_pi_load(struct kvm_vcpu *vcpu, int cpu) goto after_clear_sn; } - /* The full case. */ - do { - old.control = new.control = pi_desc->control; - - dest = cpu_physical_id(cpu); + /* The full case. Set the new destination and clear SN. */ + dest = cpu_physical_id(cpu); + if (!x2apic_mode) + dest = (dest << 8) & 0xFF00; - if (x2apic_mode) - new.ndst = dest; - else - new.ndst = (dest << 8) & 0xFF00; + do { + old.control = new.control = READ_ONCE(pi_desc->control); + new.ndst = dest; new.sn = 0; - } while (cmpxchg64(&pi_desc->control, old.control, - new.control) != old.control); + } while (pi_try_set_control(pi_desc, old.control, new.control)); after_clear_sn: @@ -103,29 +129,31 @@ static void __pi_post_block(struct kvm_vcpu *vcpu) struct pi_desc old, new; unsigned int dest; - do { - old.control = new.control = pi_desc->control; - WARN(old.nv != POSTED_INTR_WAKEUP_VECTOR, - "Wakeup handler not enabled while the VCPU is blocked\n"); + /* + * Remove the vCPU from the wakeup list of the _previous_ pCPU, which + * will not be the same as the current pCPU if the task was migrated. + */ + spin_lock(&per_cpu(blocked_vcpu_on_cpu_lock, vcpu->pre_pcpu)); + list_del(&vcpu->blocked_vcpu_list); + spin_unlock(&per_cpu(blocked_vcpu_on_cpu_lock, vcpu->pre_pcpu)); - dest = cpu_physical_id(vcpu->cpu); + dest = cpu_physical_id(vcpu->cpu); + if (!x2apic_mode) + dest = (dest << 8) & 0xFF00; - if (x2apic_mode) - new.ndst = dest; - else - new.ndst = (dest << 8) & 0xFF00; + WARN(pi_desc->nv != POSTED_INTR_WAKEUP_VECTOR, + "Wakeup handler not enabled while the vCPU was blocking"); + + do { + old.control = new.control = READ_ONCE(pi_desc->control); + + new.ndst = dest; /* set 'NV' to 'notification vector' */ new.nv = POSTED_INTR_VECTOR; - } while (cmpxchg64(&pi_desc->control, old.control, - new.control) != old.control); - - if (!WARN_ON_ONCE(vcpu->pre_pcpu == -1)) { - spin_lock(&per_cpu(blocked_vcpu_on_cpu_lock, vcpu->pre_pcpu)); - list_del(&vcpu->blocked_vcpu_list); - spin_unlock(&per_cpu(blocked_vcpu_on_cpu_lock, vcpu->pre_pcpu)); - vcpu->pre_pcpu = -1; - } + } while (pi_try_set_control(pi_desc, old.control, new.control)); + + vcpu->pre_pcpu = -1; } /* @@ -134,7 +162,6 @@ static void __pi_post_block(struct kvm_vcpu *vcpu) * - Store the vCPU to the wakeup list, so when interrupts happen * we can find the right vCPU to wake up. * - Change the Posted-interrupt descriptor as below: - * 'NDST' <-- vcpu->pre_pcpu * 'NV' <-- POSTED_INTR_WAKEUP_VECTOR * - If 'ON' is set during this process, which means at least one * interrupt is posted for this vCPU, we cannot block it, in @@ -143,68 +170,50 @@ static void __pi_post_block(struct kvm_vcpu *vcpu) */ int pi_pre_block(struct kvm_vcpu *vcpu) { - unsigned int dest; struct pi_desc old, new; struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu); + unsigned long flags; - if (!vmx_can_use_vtd_pi(vcpu->kvm)) + if (!vmx_can_use_vtd_pi(vcpu->kvm) || + vmx_interrupt_blocked(vcpu)) return 0; - WARN_ON(irqs_disabled()); - local_irq_disable(); - if (!WARN_ON_ONCE(vcpu->pre_pcpu != -1)) { - vcpu->pre_pcpu = vcpu->cpu; - spin_lock(&per_cpu(blocked_vcpu_on_cpu_lock, vcpu->pre_pcpu)); - list_add_tail(&vcpu->blocked_vcpu_list, - &per_cpu(blocked_vcpu_on_cpu, - vcpu->pre_pcpu)); - spin_unlock(&per_cpu(blocked_vcpu_on_cpu_lock, vcpu->pre_pcpu)); - } - - do { - old.control = new.control = pi_desc->control; + local_irq_save(flags); - WARN((pi_desc->sn == 1), - "Warning: SN field of posted-interrupts " - "is set before blocking\n"); + vcpu->pre_pcpu = vcpu->cpu; + spin_lock(&per_cpu(blocked_vcpu_on_cpu_lock, vcpu->cpu)); + list_add_tail(&vcpu->blocked_vcpu_list, + &per_cpu(blocked_vcpu_on_cpu, vcpu->cpu)); + spin_unlock(&per_cpu(blocked_vcpu_on_cpu_lock, vcpu->cpu)); - /* - * Since vCPU can be preempted during this process, - * vcpu->cpu could be different with pre_pcpu, we - * need to set pre_pcpu as the destination of wakeup - * notification event, then we can find the right vCPU - * to wakeup in wakeup handler if interrupts happen - * when the vCPU is in blocked state. - */ - dest = cpu_physical_id(vcpu->pre_pcpu); + WARN(pi_desc->sn == 1, + "Posted Interrupt Suppress Notification set before blocking"); - if (x2apic_mode) - new.ndst = dest; - else - new.ndst = (dest << 8) & 0xFF00; + do { + old.control = new.control = READ_ONCE(pi_desc->control); /* set 'NV' to 'wakeup vector' */ new.nv = POSTED_INTR_WAKEUP_VECTOR; - } while (cmpxchg64(&pi_desc->control, old.control, - new.control) != old.control); + } while (pi_try_set_control(pi_desc, old.control, new.control)); /* We should not block the vCPU if an interrupt is posted for it. */ - if (pi_test_on(pi_desc) == 1) + if (pi_test_on(pi_desc)) __pi_post_block(vcpu); - local_irq_enable(); + local_irq_restore(flags); return (vcpu->pre_pcpu == -1); } void pi_post_block(struct kvm_vcpu *vcpu) { + unsigned long flags; + if (vcpu->pre_pcpu == -1) return; - WARN_ON(irqs_disabled()); - local_irq_disable(); + local_irq_save(flags); __pi_post_block(vcpu); - local_irq_enable(); + local_irq_restore(flags); } /* @@ -220,7 +229,7 @@ void pi_wakeup_handler(void) blocked_vcpu_list) { struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu); - if (pi_test_on(pi_desc) == 1) + if (pi_test_on(pi_desc)) kvm_vcpu_kick(vcpu); } spin_unlock(&per_cpu(blocked_vcpu_on_cpu_lock, cpu)); diff --git a/arch/x86/kvm/vmx/posted_intr.h b/arch/x86/kvm/vmx/posted_intr.h index 7f7b2326caf5..36ae035f14aa 100644 --- a/arch/x86/kvm/vmx/posted_intr.h +++ b/arch/x86/kvm/vmx/posted_intr.h @@ -40,7 +40,7 @@ static inline bool pi_test_and_clear_on(struct pi_desc *pi_desc) (unsigned long *)&pi_desc->control); } -static inline int pi_test_and_set_pir(int vector, struct pi_desc *pi_desc) +static inline bool pi_test_and_set_pir(int vector, struct pi_desc *pi_desc) { return test_and_set_bit(vector, (unsigned long *)pi_desc->pir); } @@ -74,13 +74,13 @@ static inline void pi_clear_sn(struct pi_desc *pi_desc) (unsigned long *)&pi_desc->control); } -static inline int pi_test_on(struct pi_desc *pi_desc) +static inline bool pi_test_on(struct pi_desc *pi_desc) { return test_bit(POSTED_INTR_ON, (unsigned long *)&pi_desc->control); } -static inline int pi_test_sn(struct pi_desc *pi_desc) +static inline bool pi_test_sn(struct pi_desc *pi_desc) { return test_bit(POSTED_INTR_SN, (unsigned long *)&pi_desc->control); diff --git a/arch/x86/kvm/vmx/vmcs.h b/arch/x86/kvm/vmx/vmcs.h index 6e5de2e2b0da..e325c290a816 100644 --- a/arch/x86/kvm/vmx/vmcs.h +++ b/arch/x86/kvm/vmx/vmcs.h @@ -129,6 +129,11 @@ static inline bool is_machine_check(u32 intr_info) return is_exception_n(intr_info, MC_VECTOR); } +static inline bool is_nm_fault(u32 intr_info) +{ + return is_exception_n(intr_info, NM_VECTOR); +} + /* Undocumented: icebp/int1 */ static inline bool is_icebp(u32 intr_info) { diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index 1187cd1e38aa..1b2e9d8c5cc9 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -36,6 +36,7 @@ #include <asm/debugreg.h> #include <asm/desc.h> #include <asm/fpu/api.h> +#include <asm/fpu/xstate.h> #include <asm/idtentry.h> #include <asm/io.h> #include <asm/irq_remapping.h> @@ -161,6 +162,8 @@ static u32 vmx_possible_passthrough_msrs[MAX_POSSIBLE_PASSTHROUGH_MSRS] = { MSR_FS_BASE, MSR_GS_BASE, MSR_KERNEL_GS_BASE, + MSR_IA32_XFD, + MSR_IA32_XFD_ERR, #endif MSR_IA32_SYSENTER_CS, MSR_IA32_SYSENTER_ESP, @@ -602,15 +605,13 @@ static int vmx_set_guest_uret_msr(struct vcpu_vmx *vmx, unsigned int slot = msr - vmx->guest_uret_msrs; int ret = 0; - u64 old_msr_data = msr->data; - msr->data = data; if (msr->load_into_hardware) { preempt_disable(); - ret = kvm_set_user_return_msr(slot, msr->data, msr->mask); + ret = kvm_set_user_return_msr(slot, data, msr->mask); preempt_enable(); - if (ret) - msr->data = old_msr_data; } + if (!ret) + msr->data = data; return ret; } @@ -763,6 +764,14 @@ void vmx_update_exception_bitmap(struct kvm_vcpu *vcpu) vmcs_write32(PAGE_FAULT_ERROR_CODE_MATCH, match); } + /* + * Disabling xfd interception indicates that dynamic xfeatures + * might be used in the guest. Always trap #NM in this case + * to save guest xfd_err timely. + */ + if (vcpu->arch.xfd_no_write_intercept) + eb |= (1u << NM_VECTOR); + vmcs_write32(EXCEPTION_BITMAP, eb); } @@ -1071,9 +1080,14 @@ static void pt_guest_exit(struct vcpu_vmx *vmx) wrmsrl(MSR_IA32_RTIT_CTL, vmx->pt_desc.host.ctl); } -void vmx_set_host_fs_gs(struct vmcs_host_state *host, u16 fs_sel, u16 gs_sel, - unsigned long fs_base, unsigned long gs_base) +void vmx_set_vmcs_host_state(struct vmcs_host_state *host, unsigned long cr3, + u16 fs_sel, u16 gs_sel, + unsigned long fs_base, unsigned long gs_base) { + if (unlikely(cr3 != host->cr3)) { + vmcs_writel(HOST_CR3, cr3); + host->cr3 = cr3; + } if (unlikely(fs_sel != host->fs_sel)) { if (!(fs_sel & 7)) vmcs_write16(HOST_FS_SELECTOR, fs_sel); @@ -1168,7 +1182,9 @@ void vmx_prepare_switch_to_guest(struct kvm_vcpu *vcpu) gs_base = segment_base(gs_sel); #endif - vmx_set_host_fs_gs(host_state, fs_sel, gs_sel, fs_base, gs_base); + vmx_set_vmcs_host_state(host_state, __get_current_cr3_fast(), + fs_sel, gs_sel, fs_base, gs_base); + vmx->guest_state_loaded = true; } @@ -1271,7 +1287,6 @@ void vmx_vcpu_load_vmcs(struct kvm_vcpu *vcpu, int cpu, if (!already_loaded) { void *gdt = get_current_gdt_ro(); - unsigned long sysenter_esp; /* * Flush all EPTP/VPID contexts, the new pCPU may have stale @@ -1287,8 +1302,11 @@ 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 */ - rdmsrl(MSR_IA32_SYSENTER_ESP, sysenter_esp); - vmcs_writel(HOST_IA32_SYSENTER_ESP, sysenter_esp); /* 22.2.3 */ + if (IS_ENABLED(CONFIG_IA32_EMULATION) || IS_ENABLED(CONFIG_X86_32)) { + /* 22.2.3 */ + vmcs_writel(HOST_IA32_SYSENTER_ESP, + (unsigned long)(cpu_entry_stack(cpu) + 1)); + } vmx->loaded_vmcs->cpu = cpu; } @@ -1753,7 +1771,7 @@ static int vmx_get_msr_feature(struct kvm_msr_entry *msr) } /* - * Reads an msr value (of 'msr_index') into 'pdata'. + * Reads an msr value (of 'msr_info->index') into 'msr_info->data'. * Returns 0 on success, non-0 otherwise. * Assumes vcpu_load() was already called. */ @@ -1960,6 +1978,24 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) case MSR_KERNEL_GS_BASE: vmx_write_guest_kernel_gs_base(vmx, data); break; + case MSR_IA32_XFD: + ret = kvm_set_msr_common(vcpu, msr_info); + /* + * Always intercepting WRMSR could incur non-negligible + * overhead given xfd might be changed frequently in + * guest context switch. Disable write interception + * upon the first write with a non-zero value (indicating + * potential usage on dynamic xfeatures). Also update + * exception bitmap to trap #NM for proper virtualization + * of guest xfd_err. + */ + if (!ret && data) { + vmx_disable_intercept_for_msr(vcpu, MSR_IA32_XFD, + MSR_TYPE_RW); + vcpu->arch.xfd_no_write_intercept = true; + vmx_update_exception_bitmap(vcpu); + } + break; #endif case MSR_IA32_SYSENTER_CS: if (is_guest_mode(vcpu)) @@ -2100,9 +2136,6 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) } ret = kvm_set_msr_common(vcpu, msr_info); break; - case MSR_IA32_TSC_ADJUST: - ret = kvm_set_msr_common(vcpu, msr_info); - break; case MSR_IA32_MCG_EXT_CTL: if ((!msr_info->host_initiated && !(to_vmx(vcpu)->msr_ia32_feature_control & @@ -2985,7 +3018,7 @@ void ept_save_pdptrs(struct kvm_vcpu *vcpu) mmu->pdptrs[2] = vmcs_read64(GUEST_PDPTR2); mmu->pdptrs[3] = vmcs_read64(GUEST_PDPTR3); - kvm_register_mark_dirty(vcpu, VCPU_EXREG_PDPTR); + kvm_register_mark_available(vcpu, VCPU_EXREG_PDPTR); } #define CR3_EXITING_BITS (CPU_BASED_CR3_LOAD_EXITING | \ @@ -3067,6 +3100,13 @@ void vmx_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0) /* Note, vmx_set_cr4() consumes the new vcpu->arch.cr0. */ if ((old_cr0_pg ^ cr0) & X86_CR0_PG) vmx_set_cr4(vcpu, kvm_read_cr4(vcpu)); + + /* + * When !CR0_PG -> CR0_PG, vcpu->arch.cr3 becomes active, but + * GUEST_CR3 is still vmx->ept_identity_map_addr if EPT + !URG. + */ + if (!(old_cr0_pg & X86_CR0_PG) && (cr0 & X86_CR0_PG)) + kvm_register_mark_dirty(vcpu, VCPU_EXREG_CR3); } /* depends on vcpu->arch.cr0 to be set to a new value */ @@ -3110,9 +3150,9 @@ static void vmx_load_mmu_pgd(struct kvm_vcpu *vcpu, hpa_t root_hpa, 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)) + else if (kvm_register_is_dirty(vcpu, VCPU_EXREG_CR3)) guest_cr3 = vcpu->arch.cr3; - else /* vmcs01.GUEST_CR3 is already up-to-date. */ + else /* vmcs.GUEST_CR3 is already up-to-date. */ update_guest_cr3 = false; vmx_ept_load_pdptrs(vcpu); } else { @@ -3123,6 +3163,7 @@ static void vmx_load_mmu_pgd(struct kvm_vcpu *vcpu, hpa_t root_hpa, vmcs_writel(GUEST_CR3, guest_cr3); } + static bool vmx_is_valid_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) { /* @@ -3687,6 +3728,19 @@ void free_vpid(int vpid) spin_unlock(&vmx_vpid_lock); } +static void vmx_msr_bitmap_l01_changed(struct vcpu_vmx *vmx) +{ + /* + * When KVM is a nested hypervisor on top of Hyper-V and uses + * 'Enlightened MSR Bitmap' feature L0 needs to know that MSR + * bitmap has changed. + */ + if (static_branch_unlikely(&enable_evmcs)) + evmcs_touch_msr_bitmap(); + + vmx->nested.force_msr_bitmap_recalc = true; +} + void vmx_disable_intercept_for_msr(struct kvm_vcpu *vcpu, u32 msr, int type) { struct vcpu_vmx *vmx = to_vmx(vcpu); @@ -3695,8 +3749,7 @@ void vmx_disable_intercept_for_msr(struct kvm_vcpu *vcpu, u32 msr, int type) if (!cpu_has_vmx_msr_bitmap()) return; - if (static_branch_unlikely(&enable_evmcs)) - evmcs_touch_msr_bitmap(); + vmx_msr_bitmap_l01_changed(vmx); /* * Mark the desired intercept state in shadow bitmap, this is needed @@ -3740,8 +3793,7 @@ void vmx_enable_intercept_for_msr(struct kvm_vcpu *vcpu, u32 msr, int type) if (!cpu_has_vmx_msr_bitmap()) return; - if (static_branch_unlikely(&enable_evmcs)) - evmcs_touch_msr_bitmap(); + vmx_msr_bitmap_l01_changed(vmx); /* * Mark the desired intercept state in shadow bitmap, this is needed @@ -3931,6 +3983,19 @@ static int vmx_deliver_nested_posted_interrupt(struct kvm_vcpu *vcpu, */ vmx->nested.pi_pending = true; kvm_make_request(KVM_REQ_EVENT, vcpu); + + /* + * This pairs with the smp_mb_*() after setting vcpu->mode in + * vcpu_enter_guest() to guarantee the vCPU sees the event + * request if triggering a posted interrupt "fails" because + * vcpu->mode != IN_GUEST_MODE. The extra barrier is needed as + * the smb_wmb() in kvm_make_request() only ensures everything + * done before making the request is visible when the request + * is visible, it doesn't ensure ordering between the store to + * vcpu->requests and the load from vcpu->mode. + */ + smp_mb__after_atomic(); + /* the PIR and ON have been set by L1. */ if (!kvm_vcpu_trigger_posted_interrupt(vcpu, true)) kvm_vcpu_kick(vcpu); @@ -3964,6 +4029,12 @@ static int vmx_deliver_posted_interrupt(struct kvm_vcpu *vcpu, int vector) if (pi_test_and_set_on(&vmx->pi_desc)) return 0; + /* + * The implied barrier in pi_test_and_set_on() pairs with the smp_mb_*() + * after setting vcpu->mode in vcpu_enter_guest(), thus the vCPU is + * guaranteed to see PID.ON=1 and sync the PIR to IRR if triggering a + * posted interrupt "fails" because vcpu->mode != IN_GUEST_MODE. + */ if (!kvm_vcpu_trigger_posted_interrupt(vcpu, false)) kvm_vcpu_kick(vcpu); @@ -4021,6 +4092,12 @@ void vmx_set_constant_host_state(struct vcpu_vmx *vmx) rdmsr(MSR_IA32_SYSENTER_CS, low32, high32); vmcs_write32(HOST_IA32_SYSENTER_CS, low32); + + /* + * If 32-bit syscall is enabled, vmx_vcpu_load_vcms rewrites + * HOST_IA32_SYSENTER_ESP. + */ + vmcs_writel(HOST_IA32_SYSENTER_ESP, 0); rdmsrl(MSR_IA32_SYSENTER_EIP, tmpl); vmcs_writel(HOST_IA32_SYSENTER_EIP, tmpl); /* 22.2.3 */ @@ -4039,8 +4116,10 @@ void set_cr4_guest_host_mask(struct vcpu_vmx *vmx) vcpu->arch.cr4_guest_owned_bits = KVM_POSSIBLE_CR4_GUEST_BITS & ~vcpu->arch.cr4_guest_rsvd_bits; - if (!enable_ept) - vcpu->arch.cr4_guest_owned_bits &= ~X86_CR4_PGE; + if (!enable_ept) { + vcpu->arch.cr4_guest_owned_bits &= ~X86_CR4_TLBFLUSH_BITS; + vcpu->arch.cr4_guest_owned_bits &= ~X86_CR4_PDPTR_BITS; + } if (is_guest_mode(&vmx->vcpu)) vcpu->arch.cr4_guest_owned_bits &= ~get_vmcs12(vcpu)->cr4_guest_host_mask; @@ -4692,7 +4771,7 @@ static int handle_rmode_exception(struct kvm_vcpu *vcpu, if (kvm_emulate_instruction(vcpu, 0)) { if (vcpu->arch.halt_request) { vcpu->arch.halt_request = 0; - return kvm_vcpu_halt(vcpu); + return kvm_emulate_halt_noskip(vcpu); } return 1; } @@ -4748,6 +4827,17 @@ static int handle_exception_nmi(struct kvm_vcpu *vcpu) if (is_machine_check(intr_info) || is_nmi(intr_info)) return 1; /* handled by handle_exception_nmi_irqoff() */ + /* + * Queue the exception here instead of in handle_nm_fault_irqoff(). + * This ensures the nested_vmx check is not skipped so vmexit can + * be reflected to L1 (when it intercepts #NM) before reaching this + * point. + */ + if (is_nm_fault(intr_info)) { + kvm_queue_exception(vcpu, NM_VECTOR); + return 1; + } + if (is_invalid_opcode(intr_info)) return handle_ud(vcpu); @@ -5363,7 +5453,7 @@ static int handle_invalid_guest_state(struct kvm_vcpu *vcpu) if (vcpu->arch.halt_request) { vcpu->arch.halt_request = 0; - return kvm_vcpu_halt(vcpu); + return kvm_emulate_halt_noskip(vcpu); } /* @@ -6351,6 +6441,26 @@ static void handle_interrupt_nmi_irqoff(struct kvm_vcpu *vcpu, kvm_after_interrupt(vcpu); } +static void handle_nm_fault_irqoff(struct kvm_vcpu *vcpu) +{ + /* + * Save xfd_err to guest_fpu before interrupt is enabled, so the + * MSR value is not clobbered by the host activity before the guest + * has chance to consume it. + * + * Do not blindly read xfd_err here, since this exception might + * be caused by L1 interception on a platform which doesn't + * support xfd at all. + * + * Do it conditionally upon guest_fpu::xfd. xfd_err matters + * only when xfd contains a non-zero value. + * + * Queuing exception is done in vmx_handle_exit. See comment there. + */ + if (vcpu->arch.guest_fpu.fpstate->xfd) + rdmsrl(MSR_IA32_XFD_ERR, vcpu->arch.guest_fpu.xfd_err); +} + static void handle_exception_nmi_irqoff(struct vcpu_vmx *vmx) { const unsigned long nmi_entry = (unsigned long)asm_exc_nmi_noist; @@ -6359,6 +6469,9 @@ static void handle_exception_nmi_irqoff(struct vcpu_vmx *vmx) /* if exit due to PF check for async PF */ if (is_page_fault(intr_info)) vmx->vcpu.arch.apf.host_apf_flags = kvm_read_and_reset_apf_flags(); + /* if exit due to NM, handle before interrupts are enabled */ + else if (is_nm_fault(intr_info)) + handle_nm_fault_irqoff(&vmx->vcpu); /* Handle machine checks before interrupts are enabled */ else if (is_machine_check(intr_info)) kvm_machine_check(); @@ -6617,7 +6730,7 @@ static noinstr void vmx_vcpu_enter_exit(struct kvm_vcpu *vcpu, static fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); - unsigned long cr3, cr4; + unsigned long cr4; /* Record the guest's net vcpu time for enforced NMI injections. */ if (unlikely(!enable_vnmi && @@ -6658,12 +6771,7 @@ static fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu) vmcs_writel(GUEST_RSP, vcpu->arch.regs[VCPU_REGS_RSP]); if (kvm_register_is_dirty(vcpu, VCPU_REGS_RIP)) vmcs_writel(GUEST_RIP, vcpu->arch.regs[VCPU_REGS_RIP]); - - cr3 = __get_current_cr3_fast(); - if (unlikely(cr3 != vmx->loaded_vmcs->host_state.cr3)) { - vmcs_writel(HOST_CR3, cr3); - vmx->loaded_vmcs->host_state.cr3 = cr3; - } + vcpu->arch.regs_dirty = 0; cr4 = cr4_read_shadow(); if (unlikely(cr4 != vmx->loaded_vmcs->host_state.cr4)) { @@ -6752,7 +6860,7 @@ static fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu) loadsegment(es, __USER_DS); #endif - vmx_register_cache_reset(vcpu); + vcpu->arch.regs_avail &= ~VMX_REGS_LAZY_LOAD_SET; pt_guest_exit(vmx); @@ -6971,7 +7079,6 @@ static int __init vmx_check_processor_compat(void) static u64 vmx_get_mt_mask(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio) { u8 cache; - u64 ipat = 0; /* We wanted to honor guest CD/MTRR/PAT, but doing so could result in * memory aliases with conflicting memory types and sometimes MCEs. @@ -6991,30 +7098,22 @@ static u64 vmx_get_mt_mask(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio) * EPT memory type is used to emulate guest CD/MTRR. */ - if (is_mmio) { - cache = MTRR_TYPE_UNCACHABLE; - goto exit; - } + if (is_mmio) + return MTRR_TYPE_UNCACHABLE << VMX_EPT_MT_EPTE_SHIFT; - if (!kvm_arch_has_noncoherent_dma(vcpu->kvm)) { - ipat = VMX_EPT_IPAT_BIT; - cache = MTRR_TYPE_WRBACK; - goto exit; - } + if (!kvm_arch_has_noncoherent_dma(vcpu->kvm)) + return (MTRR_TYPE_WRBACK << VMX_EPT_MT_EPTE_SHIFT) | VMX_EPT_IPAT_BIT; if (kvm_read_cr0(vcpu) & X86_CR0_CD) { - ipat = VMX_EPT_IPAT_BIT; if (kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_CD_NW_CLEARED)) cache = MTRR_TYPE_WRBACK; else cache = MTRR_TYPE_UNCACHABLE; - goto exit; - } - cache = kvm_mtrr_get_guest_memory_type(vcpu, gfn); + return (cache << VMX_EPT_MT_EPTE_SHIFT) | VMX_EPT_IPAT_BIT; + } -exit: - return (cache << VMX_EPT_MT_EPTE_SHIFT) | ipat; + return kvm_mtrr_get_guest_memory_type(vcpu, gfn) << VMX_EPT_MT_EPTE_SHIFT; } static void vmcs_set_secondary_exec_control(struct vcpu_vmx *vmx, u32 new_ctl) @@ -7206,6 +7305,11 @@ static void vmx_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu) } } + if (kvm_cpu_cap_has(X86_FEATURE_XFD)) + vmx_set_intercept_for_msr(vcpu, MSR_IA32_XFD_ERR, MSR_TYPE_R, + !guest_cpuid_has(vcpu, X86_FEATURE_XFD)); + + set_cr4_guest_host_mask(vmx); vmx_write_encls_bitmap(vcpu, NULL); @@ -7741,7 +7845,7 @@ static __init int hardware_setup(void) { unsigned long host_bndcfgs; struct desc_ptr dt; - int r, ept_lpage_level; + int r; store_idt(&dt); host_idt_base = dt.address; @@ -7838,16 +7942,8 @@ static __init int hardware_setup(void) kvm_mmu_set_ept_masks(enable_ept_ad_bits, cpu_has_vmx_ept_execute_only()); - if (!enable_ept) - ept_lpage_level = 0; - else if (cpu_has_vmx_ept_1g_page()) - ept_lpage_level = PG_LEVEL_1G; - else if (cpu_has_vmx_ept_2m_page()) - ept_lpage_level = PG_LEVEL_2M; - else - ept_lpage_level = PG_LEVEL_4K; kvm_configure_mmu(enable_ept, 0, vmx_get_max_tdp_level(), - ept_lpage_level); + ept_caps_to_lpage_level(vmx_capability.ept)); /* * Only enable PML when hardware supports PML feature, and both EPT diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h index 4df2ac24ffc1..f8fc7441baea 100644 --- a/arch/x86/kvm/vmx/vmx.h +++ b/arch/x86/kvm/vmx/vmx.h @@ -159,6 +159,15 @@ struct nested_vmx { bool dirty_vmcs12; /* + * Indicates whether MSR bitmap for L2 needs to be rebuilt due to + * changes in MSR bitmap for L1 or switching to a different L2. Note, + * this flag can only be used reliably in conjunction with a paravirt L1 + * which informs L0 whether any changes to MSR bitmap for L2 were done + * on its side. + */ + bool force_msr_bitmap_recalc; + + /* * Indicates lazily loaded guest state has not yet been decached from * vmcs02. */ @@ -340,7 +349,7 @@ struct vcpu_vmx { struct lbr_desc lbr_desc; /* Save desired MSR intercept (read: pass-through) state */ -#define MAX_POSSIBLE_PASSTHROUGH_MSRS 13 +#define MAX_POSSIBLE_PASSTHROUGH_MSRS 15 struct { DECLARE_BITMAP(read, MAX_POSSIBLE_PASSTHROUGH_MSRS); DECLARE_BITMAP(write, MAX_POSSIBLE_PASSTHROUGH_MSRS); @@ -362,8 +371,9 @@ int allocate_vpid(void); void free_vpid(int vpid); void vmx_set_constant_host_state(struct vcpu_vmx *vmx); void vmx_prepare_switch_to_guest(struct kvm_vcpu *vcpu); -void vmx_set_host_fs_gs(struct vmcs_host_state *host, u16 fs_sel, u16 gs_sel, - unsigned long fs_base, unsigned long gs_base); +void vmx_set_vmcs_host_state(struct vmcs_host_state *host, unsigned long cr3, + u16 fs_sel, u16 gs_sel, + unsigned long fs_base, unsigned long gs_base); int vmx_get_cpl(struct kvm_vcpu *vcpu); bool vmx_emulation_required(struct kvm_vcpu *vcpu); unsigned long vmx_get_rflags(struct kvm_vcpu *vcpu); @@ -473,19 +483,21 @@ BUILD_CONTROLS_SHADOW(pin, PIN_BASED_VM_EXEC_CONTROL) BUILD_CONTROLS_SHADOW(exec, CPU_BASED_VM_EXEC_CONTROL) BUILD_CONTROLS_SHADOW(secondary_exec, SECONDARY_VM_EXEC_CONTROL) -static inline void vmx_register_cache_reset(struct kvm_vcpu *vcpu) -{ - vcpu->arch.regs_avail = ~((1 << VCPU_REGS_RIP) | (1 << VCPU_REGS_RSP) - | (1 << VCPU_EXREG_RFLAGS) - | (1 << VCPU_EXREG_PDPTR) - | (1 << VCPU_EXREG_SEGMENTS) - | (1 << VCPU_EXREG_CR0) - | (1 << VCPU_EXREG_CR3) - | (1 << VCPU_EXREG_CR4) - | (1 << VCPU_EXREG_EXIT_INFO_1) - | (1 << VCPU_EXREG_EXIT_INFO_2)); - vcpu->arch.regs_dirty = 0; -} +/* + * VMX_REGS_LAZY_LOAD_SET - The set of registers that will be updated in the + * cache on demand. Other registers not listed here are synced to + * the cache immediately after VM-Exit. + */ +#define VMX_REGS_LAZY_LOAD_SET ((1 << VCPU_REGS_RIP) | \ + (1 << VCPU_REGS_RSP) | \ + (1 << VCPU_EXREG_RFLAGS) | \ + (1 << VCPU_EXREG_PDPTR) | \ + (1 << VCPU_EXREG_SEGMENTS) | \ + (1 << VCPU_EXREG_CR0) | \ + (1 << VCPU_EXREG_CR3) | \ + (1 << VCPU_EXREG_CR4) | \ + (1 << VCPU_EXREG_EXIT_INFO_1) | \ + (1 << VCPU_EXREG_EXIT_INFO_2)) static inline struct kvm_vmx *to_kvm_vmx(struct kvm *kvm) { diff --git a/arch/x86/kvm/vmx/vmx_ops.h b/arch/x86/kvm/vmx/vmx_ops.h index 35d9324c2f2a..5e7f41225780 100644 --- a/arch/x86/kvm/vmx/vmx_ops.h +++ b/arch/x86/kvm/vmx/vmx_ops.h @@ -71,6 +71,31 @@ static __always_inline unsigned long __vmcs_readl(unsigned long field) { unsigned long value; +#ifdef CONFIG_CC_HAS_ASM_GOTO_OUTPUT + + asm_volatile_goto("1: vmread %[field], %[output]\n\t" + "jna %l[do_fail]\n\t" + + _ASM_EXTABLE(1b, %l[do_exception]) + + : [output] "=r" (value) + : [field] "r" (field) + : "cc" + : do_fail, do_exception); + + return value; + +do_fail: + WARN_ONCE(1, "kvm: vmread failed: field=%lx\n", field); + pr_warn_ratelimited("kvm: vmread failed: field=%lx\n", field); + return 0; + +do_exception: + kvm_spurious_fault(); + return 0; + +#else /* !CONFIG_CC_HAS_ASM_GOTO_OUTPUT */ + asm volatile("1: vmread %2, %1\n\t" ".byte 0x3e\n\t" /* branch taken hint */ "ja 3f\n\t" @@ -99,6 +124,8 @@ static __always_inline unsigned long __vmcs_readl(unsigned long field) : ASM_CALL_CONSTRAINT, "=&r"(value) : "r"(field) : "cc"); return value; + +#endif /* CONFIG_CC_HAS_ASM_GOTO_OUTPUT */ } static __always_inline u16 vmcs_read16(unsigned long field) diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 829d03fcb481..76b4803dd3bd 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -118,6 +118,7 @@ static void enter_smm(struct kvm_vcpu *vcpu); static void __kvm_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags); static void store_regs(struct kvm_vcpu *vcpu); static int sync_regs(struct kvm_vcpu *vcpu); +static int kvm_vcpu_do_singlestep(struct kvm_vcpu *vcpu); static int __set_sregs2(struct kvm_vcpu *vcpu, struct kvm_sregs2 *sregs2); static void __get_sregs2(struct kvm_vcpu *vcpu, struct kvm_sregs2 *sregs2); @@ -210,7 +211,7 @@ static struct kvm_user_return_msrs __percpu *user_return_msrs; #define KVM_SUPPORTED_XCR0 (XFEATURE_MASK_FP | XFEATURE_MASK_SSE \ | XFEATURE_MASK_YMM | XFEATURE_MASK_BNDREGS \ | XFEATURE_MASK_BNDCSR | XFEATURE_MASK_AVX512 \ - | XFEATURE_MASK_PKRU) + | XFEATURE_MASK_PKRU | XFEATURE_MASK_XTILE) u64 __read_mostly host_efer; EXPORT_SYMBOL_GPL(host_efer); @@ -710,6 +711,17 @@ int kvm_complete_insn_gp(struct kvm_vcpu *vcpu, int err) } EXPORT_SYMBOL_GPL(kvm_complete_insn_gp); +static int complete_emulated_insn_gp(struct kvm_vcpu *vcpu, int err) +{ + if (err) { + kvm_inject_gp(vcpu, 0); + return 1; + } + + return kvm_emulate_instruction(vcpu, EMULTYPE_NO_DECODE | EMULTYPE_SKIP | + EMULTYPE_COMPLETE_USER_EXIT); +} + void kvm_inject_page_fault(struct kvm_vcpu *vcpu, struct x86_exception *fault) { ++vcpu->stat.pf_guest; @@ -798,8 +810,9 @@ static inline u64 pdptr_rsvd_bits(struct kvm_vcpu *vcpu) /* * 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) +int load_pdptrs(struct kvm_vcpu *vcpu, unsigned long cr3) { + struct kvm_mmu *mmu = vcpu->arch.walk_mmu; gfn_t pdpt_gfn = cr3 >> PAGE_SHIFT; gpa_t real_gpa; int i; @@ -810,8 +823,8 @@ int load_pdptrs(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, unsigned long cr3) * If the MMU is nested, CR3 holds an L2 GPA and needs to be translated * to an L1 GPA. */ - real_gpa = mmu->translate_gpa(vcpu, gfn_to_gpa(pdpt_gfn), - PFERR_USER_MASK | PFERR_WRITE_MASK, NULL); + real_gpa = kvm_translate_gpa(vcpu, mmu, gfn_to_gpa(pdpt_gfn), + PFERR_USER_MASK | PFERR_WRITE_MASK, NULL); if (real_gpa == UNMAPPED_GVA) return 0; @@ -828,8 +841,16 @@ int load_pdptrs(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, unsigned long cr3) } } + /* + * Marking VCPU_EXREG_PDPTR dirty doesn't work for !tdp_enabled. + * Shadow page roots need to be reconstructed instead. + */ + if (!tdp_enabled && memcmp(mmu->pdptrs, pdpte, sizeof(mmu->pdptrs))) + kvm_mmu_free_roots(vcpu, mmu, KVM_MMU_ROOT_CURRENT); + memcpy(mmu->pdptrs, pdpte, sizeof(mmu->pdptrs)); kvm_register_mark_dirty(vcpu, VCPU_EXREG_PDPTR); + kvm_make_request(KVM_REQ_LOAD_MMU_PGD, vcpu); vcpu->arch.pdptrs_from_userspace = false; return 1; @@ -856,7 +877,6 @@ EXPORT_SYMBOL_GPL(kvm_post_set_cr0); int kvm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0) { unsigned long old_cr0 = kvm_read_cr0(vcpu); - unsigned long pdptr_bits = X86_CR0_CD | X86_CR0_NW | X86_CR0_PG; cr0 |= X86_CR0_ET; @@ -886,8 +906,8 @@ int kvm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0) } #endif if (!(vcpu->arch.efer & EFER_LME) && (cr0 & X86_CR0_PG) && - is_pae(vcpu) && ((cr0 ^ old_cr0) & pdptr_bits) && - !load_pdptrs(vcpu, vcpu->arch.walk_mmu, kvm_read_cr3(vcpu))) + is_pae(vcpu) && ((cr0 ^ old_cr0) & X86_CR0_PDPTR_BITS) && + !load_pdptrs(vcpu, kvm_read_cr3(vcpu))) return 1; if (!(cr0 & X86_CR0_PG) && @@ -990,6 +1010,11 @@ static int __kvm_set_xcr(struct kvm_vcpu *vcpu, u32 index, u64 xcr) if ((xcr0 & XFEATURE_MASK_AVX512) != XFEATURE_MASK_AVX512) return 1; } + + if ((xcr0 & XFEATURE_MASK_XTILE) && + ((xcr0 & XFEATURE_MASK_XTILE) != XFEATURE_MASK_XTILE)) + return 1; + vcpu->arch.xcr0 = xcr0; if ((xcr0 ^ old_xcr0) & XFEATURE_MASK_EXTEND) @@ -1051,8 +1076,6 @@ EXPORT_SYMBOL_GPL(kvm_post_set_cr4); 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; if (!kvm_is_valid_cr4(vcpu, cr4)) return 1; @@ -1063,9 +1086,8 @@ int kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) if ((cr4 ^ old_cr4) & X86_CR4_LA57) return 1; } else if (is_paging(vcpu) && (cr4 & X86_CR4_PAE) - && ((cr4 ^ old_cr4) & pdptr_bits) - && !load_pdptrs(vcpu, vcpu->arch.walk_mmu, - kvm_read_cr3(vcpu))) + && ((cr4 ^ old_cr4) & X86_CR4_PDPTR_BITS) + && !load_pdptrs(vcpu, kvm_read_cr3(vcpu))) return 1; if ((cr4 & X86_CR4_PCIDE) && !(old_cr4 & X86_CR4_PCIDE)) { @@ -1154,14 +1176,15 @@ int kvm_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3) if (kvm_vcpu_is_illegal_gpa(vcpu, cr3)) return 1; - if (is_pae_paging(vcpu) && !load_pdptrs(vcpu, vcpu->arch.walk_mmu, cr3)) + if (is_pae_paging(vcpu) && !load_pdptrs(vcpu, cr3)) return 1; if (cr3 != kvm_read_cr3(vcpu)) kvm_mmu_new_pgd(vcpu, cr3); vcpu->arch.cr3 = cr3; - kvm_register_mark_available(vcpu, VCPU_EXREG_CR3); + kvm_register_mark_dirty(vcpu, VCPU_EXREG_CR3); + /* Do not call post_set_cr3, we do not get here for confidential guests. */ handle_tlb_flush: /* @@ -1359,6 +1382,7 @@ static const u32 msrs_to_save_all[] = { MSR_F15H_PERF_CTL3, MSR_F15H_PERF_CTL4, MSR_F15H_PERF_CTL5, MSR_F15H_PERF_CTR0, MSR_F15H_PERF_CTR1, MSR_F15H_PERF_CTR2, MSR_F15H_PERF_CTR3, MSR_F15H_PERF_CTR4, MSR_F15H_PERF_CTR5, + MSR_IA32_XFD, MSR_IA32_XFD_ERR, }; static u32 msrs_to_save[ARRAY_SIZE(msrs_to_save_all)]; @@ -1815,22 +1839,36 @@ int kvm_set_msr(struct kvm_vcpu *vcpu, u32 index, u64 data) } EXPORT_SYMBOL_GPL(kvm_set_msr); -static int complete_emulated_rdmsr(struct kvm_vcpu *vcpu) +static void complete_userspace_rdmsr(struct kvm_vcpu *vcpu) { - int err = vcpu->run->msr.error; - if (!err) { + if (!vcpu->run->msr.error) { kvm_rax_write(vcpu, (u32)vcpu->run->msr.data); kvm_rdx_write(vcpu, vcpu->run->msr.data >> 32); } +} - return static_call(kvm_x86_complete_emulated_msr)(vcpu, err); +static int complete_emulated_msr_access(struct kvm_vcpu *vcpu) +{ + return complete_emulated_insn_gp(vcpu, vcpu->run->msr.error); } -static int complete_emulated_wrmsr(struct kvm_vcpu *vcpu) +static int complete_emulated_rdmsr(struct kvm_vcpu *vcpu) +{ + complete_userspace_rdmsr(vcpu); + return complete_emulated_msr_access(vcpu); +} + +static int complete_fast_msr_access(struct kvm_vcpu *vcpu) { return static_call(kvm_x86_complete_emulated_msr)(vcpu, vcpu->run->msr.error); } +static int complete_fast_rdmsr(struct kvm_vcpu *vcpu) +{ + complete_userspace_rdmsr(vcpu); + return complete_fast_msr_access(vcpu); +} + static u64 kvm_msr_reason(int r) { switch (r) { @@ -1865,18 +1903,6 @@ static int kvm_msr_user_space(struct kvm_vcpu *vcpu, u32 index, return 1; } -static int kvm_get_msr_user_space(struct kvm_vcpu *vcpu, u32 index, int r) -{ - return kvm_msr_user_space(vcpu, index, KVM_EXIT_X86_RDMSR, 0, - complete_emulated_rdmsr, r); -} - -static int kvm_set_msr_user_space(struct kvm_vcpu *vcpu, u32 index, u64 data, int r) -{ - return kvm_msr_user_space(vcpu, index, KVM_EXIT_X86_WRMSR, data, - complete_emulated_wrmsr, r); -} - int kvm_emulate_rdmsr(struct kvm_vcpu *vcpu) { u32 ecx = kvm_rcx_read(vcpu); @@ -1885,18 +1911,16 @@ int kvm_emulate_rdmsr(struct kvm_vcpu *vcpu) r = kvm_get_msr(vcpu, ecx, &data); - /* MSR read failed? See if we should ask user space */ - if (r && kvm_get_msr_user_space(vcpu, ecx, r)) { - /* Bounce to user space */ - return 0; - } - if (!r) { trace_kvm_msr_read(ecx, data); kvm_rax_write(vcpu, data & -1u); kvm_rdx_write(vcpu, (data >> 32) & -1u); } else { + /* MSR read failed? See if we should ask user space */ + if (kvm_msr_user_space(vcpu, ecx, KVM_EXIT_X86_RDMSR, 0, + complete_fast_rdmsr, r)) + return 0; trace_kvm_msr_read_ex(ecx); } @@ -1912,19 +1936,18 @@ int kvm_emulate_wrmsr(struct kvm_vcpu *vcpu) r = kvm_set_msr(vcpu, ecx, data); - /* MSR write failed? See if we should ask user space */ - if (r && kvm_set_msr_user_space(vcpu, ecx, data, r)) - /* Bounce to user space */ - return 0; - - /* Signal all other negative errors to userspace */ - if (r < 0) - return r; - - if (!r) + if (!r) { trace_kvm_msr_write(ecx, data); - else + } else { + /* MSR write failed? See if we should ask user space */ + if (kvm_msr_user_space(vcpu, ecx, KVM_EXIT_X86_WRMSR, data, + complete_fast_msr_access, r)) + return 0; + /* Signal all other negative errors to userspace */ + if (r < 0) + return r; trace_kvm_msr_write_ex(ecx, data); + } return static_call(kvm_x86_complete_emulated_msr)(vcpu, r); } @@ -2119,7 +2142,7 @@ static s64 get_kvmclock_base_ns(void) } #endif -void kvm_write_wall_clock(struct kvm *kvm, gpa_t wall_clock, int sec_hi_ofs) +static void kvm_write_wall_clock(struct kvm *kvm, gpa_t wall_clock, int sec_hi_ofs) { int version; int r; @@ -2817,7 +2840,7 @@ static void kvm_end_pvclock_update(struct kvm *kvm) { struct kvm_arch *ka = &kvm->arch; struct kvm_vcpu *vcpu; - int i; + unsigned long i; write_seqcount_end(&ka->pvclock_sc); raw_spin_unlock_irq(&ka->tsc_write_lock); @@ -3066,7 +3089,7 @@ static int kvm_guest_time_update(struct kvm_vcpu *v) static void kvmclock_update_fn(struct work_struct *work) { - int i; + unsigned long i; struct delayed_work *dwork = to_delayed_work(work); struct kvm_arch *ka = container_of(dwork, struct kvm_arch, kvmclock_update_work); @@ -3669,6 +3692,30 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) return 1; vcpu->arch.msr_misc_features_enables = data; break; +#ifdef CONFIG_X86_64 + case MSR_IA32_XFD: + if (!msr_info->host_initiated && + !guest_cpuid_has(vcpu, X86_FEATURE_XFD)) + return 1; + + if (data & ~(XFEATURE_MASK_USER_DYNAMIC & + vcpu->arch.guest_supported_xcr0)) + return 1; + + fpu_update_guest_xfd(&vcpu->arch.guest_fpu, data); + break; + case MSR_IA32_XFD_ERR: + if (!msr_info->host_initiated && + !guest_cpuid_has(vcpu, X86_FEATURE_XFD)) + return 1; + + if (data & ~(XFEATURE_MASK_USER_DYNAMIC & + vcpu->arch.guest_supported_xcr0)) + return 1; + + vcpu->arch.guest_fpu.xfd_err = data; + break; +#endif default: if (kvm_pmu_is_valid_msr(vcpu, msr)) return kvm_pmu_set_msr(vcpu, msr_info); @@ -3989,6 +4036,22 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) case MSR_K7_HWCR: msr_info->data = vcpu->arch.msr_hwcr; break; +#ifdef CONFIG_X86_64 + case MSR_IA32_XFD: + if (!msr_info->host_initiated && + !guest_cpuid_has(vcpu, X86_FEATURE_XFD)) + return 1; + + msr_info->data = vcpu->arch.guest_fpu.fpstate->xfd; + break; + case MSR_IA32_XFD_ERR: + if (!msr_info->host_initiated && + !guest_cpuid_has(vcpu, X86_FEATURE_XFD)) + return 1; + + msr_info->data = vcpu->arch.guest_fpu.xfd_err; + break; +#endif default: if (kvm_pmu_is_valid_msr(vcpu, msr_info->index)) return kvm_pmu_get_msr(vcpu, msr_info); @@ -4172,7 +4235,8 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_XEN_HVM: r = KVM_XEN_HVM_CONFIG_HYPERCALL_MSR | KVM_XEN_HVM_CONFIG_INTERCEPT_HCALL | - KVM_XEN_HVM_CONFIG_SHARED_INFO; + KVM_XEN_HVM_CONFIG_SHARED_INFO | + KVM_XEN_HVM_CONFIG_EVTCHN_2LEVEL; if (sched_info_on()) r |= KVM_XEN_HVM_CONFIG_RUNSTATE; break; @@ -4250,6 +4314,14 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) else r = 0; break; + case KVM_CAP_XSAVE2: { + u64 guest_perm = xstate_get_guest_group_perm(); + + r = xstate_required_size(supported_xcr0 & guest_perm, false); + if (r < sizeof(struct kvm_xsave)) + r = sizeof(struct kvm_xsave); + break; + } default: break; } @@ -4853,6 +4925,16 @@ static void kvm_vcpu_ioctl_x86_get_xsave(struct kvm_vcpu *vcpu, vcpu->arch.pkru); } +static void kvm_vcpu_ioctl_x86_get_xsave2(struct kvm_vcpu *vcpu, + u8 *state, unsigned int size) +{ + if (fpstate_is_confidential(&vcpu->arch.guest_fpu)) + return; + + fpu_copy_guest_fpstate_to_uabi(&vcpu->arch.guest_fpu, + state, size, vcpu->arch.pkru); +} + static int kvm_vcpu_ioctl_x86_set_xsave(struct kvm_vcpu *vcpu, struct kvm_xsave *guest_xsave) { @@ -5306,6 +5388,10 @@ long kvm_arch_vcpu_ioctl(struct file *filp, break; } case KVM_GET_XSAVE: { + r = -EINVAL; + if (vcpu->arch.guest_fpu.uabi_size > sizeof(struct kvm_xsave)) + break; + u.xsave = kzalloc(sizeof(struct kvm_xsave), GFP_KERNEL_ACCOUNT); r = -ENOMEM; if (!u.xsave) @@ -5320,7 +5406,9 @@ long kvm_arch_vcpu_ioctl(struct file *filp, break; } case KVM_SET_XSAVE: { - u.xsave = memdup_user(argp, sizeof(*u.xsave)); + int size = vcpu->arch.guest_fpu.uabi_size; + + u.xsave = memdup_user(argp, size); if (IS_ERR(u.xsave)) { r = PTR_ERR(u.xsave); goto out_nofree; @@ -5329,6 +5417,25 @@ long kvm_arch_vcpu_ioctl(struct file *filp, r = kvm_vcpu_ioctl_x86_set_xsave(vcpu, u.xsave); break; } + + case KVM_GET_XSAVE2: { + int size = vcpu->arch.guest_fpu.uabi_size; + + u.xsave = kzalloc(size, GFP_KERNEL_ACCOUNT); + r = -ENOMEM; + if (!u.xsave) + break; + + kvm_vcpu_ioctl_x86_get_xsave2(vcpu, u.buffer, size); + + r = -EFAULT; + if (copy_to_user(argp, u.xsave, size)) + break; + + r = 0; + break; + } + case KVM_GET_XCRS: { u.xcrs = kzalloc(sizeof(struct kvm_xcrs), GFP_KERNEL_ACCOUNT); r = -ENOMEM; @@ -5693,7 +5800,7 @@ void kvm_arch_sync_dirty_log(struct kvm *kvm, struct kvm_memory_slot *memslot) * VM-Exit. */ struct kvm_vcpu *vcpu; - int i; + unsigned long i; kvm_for_each_vcpu(i, vcpu, kvm) kvm_vcpu_kick(vcpu); @@ -5962,7 +6069,8 @@ static int kvm_vm_ioctl_set_msr_filter(struct kvm *kvm, void __user *argp) static int kvm_arch_suspend_notifier(struct kvm *kvm) { struct kvm_vcpu *vcpu; - int i, ret = 0; + unsigned long i; + int ret = 0; mutex_lock(&kvm->lock); kvm_for_each_vcpu(i, vcpu, kvm) { @@ -6422,6 +6530,11 @@ static void kvm_init_msr_list(void) min(INTEL_PMC_MAX_GENERIC, x86_pmu.num_counters_gp)) continue; break; + case MSR_IA32_XFD: + case MSR_IA32_XFD_ERR: + if (!kvm_cpu_cap_has(X86_FEATURE_XFD)) + continue; + break; default: break; } @@ -6505,13 +6618,14 @@ void kvm_get_segment(struct kvm_vcpu *vcpu, gpa_t translate_nested_gpa(struct kvm_vcpu *vcpu, gpa_t gpa, u32 access, struct x86_exception *exception) { + struct kvm_mmu *mmu = vcpu->arch.mmu; gpa_t t_gpa; BUG_ON(!mmu_is_nested(vcpu)); /* NPT walks are always user-walks */ access |= PFERR_USER_MASK; - t_gpa = vcpu->arch.mmu->gva_to_gpa(vcpu, gpa, access, exception); + t_gpa = mmu->gva_to_gpa(vcpu, mmu, gpa, access, exception); return t_gpa; } @@ -6519,25 +6633,31 @@ gpa_t translate_nested_gpa(struct kvm_vcpu *vcpu, gpa_t gpa, u32 access, gpa_t kvm_mmu_gva_to_gpa_read(struct kvm_vcpu *vcpu, gva_t gva, struct x86_exception *exception) { + struct kvm_mmu *mmu = vcpu->arch.walk_mmu; + u32 access = (static_call(kvm_x86_get_cpl)(vcpu) == 3) ? PFERR_USER_MASK : 0; - return vcpu->arch.walk_mmu->gva_to_gpa(vcpu, gva, access, exception); + return mmu->gva_to_gpa(vcpu, mmu, gva, access, exception); } EXPORT_SYMBOL_GPL(kvm_mmu_gva_to_gpa_read); gpa_t kvm_mmu_gva_to_gpa_fetch(struct kvm_vcpu *vcpu, gva_t gva, struct x86_exception *exception) { + struct kvm_mmu *mmu = vcpu->arch.walk_mmu; + u32 access = (static_call(kvm_x86_get_cpl)(vcpu) == 3) ? PFERR_USER_MASK : 0; access |= PFERR_FETCH_MASK; - return vcpu->arch.walk_mmu->gva_to_gpa(vcpu, gva, access, exception); + return mmu->gva_to_gpa(vcpu, mmu, gva, access, exception); } gpa_t kvm_mmu_gva_to_gpa_write(struct kvm_vcpu *vcpu, gva_t gva, struct x86_exception *exception) { + struct kvm_mmu *mmu = vcpu->arch.walk_mmu; + u32 access = (static_call(kvm_x86_get_cpl)(vcpu) == 3) ? PFERR_USER_MASK : 0; access |= PFERR_WRITE_MASK; - return vcpu->arch.walk_mmu->gva_to_gpa(vcpu, gva, access, exception); + return mmu->gva_to_gpa(vcpu, mmu, gva, access, exception); } EXPORT_SYMBOL_GPL(kvm_mmu_gva_to_gpa_write); @@ -6545,19 +6665,21 @@ EXPORT_SYMBOL_GPL(kvm_mmu_gva_to_gpa_write); gpa_t kvm_mmu_gva_to_gpa_system(struct kvm_vcpu *vcpu, gva_t gva, struct x86_exception *exception) { - return vcpu->arch.walk_mmu->gva_to_gpa(vcpu, gva, 0, exception); + struct kvm_mmu *mmu = vcpu->arch.walk_mmu; + + return mmu->gva_to_gpa(vcpu, mmu, gva, 0, exception); } static int kvm_read_guest_virt_helper(gva_t addr, void *val, unsigned int bytes, struct kvm_vcpu *vcpu, u32 access, struct x86_exception *exception) { + struct kvm_mmu *mmu = vcpu->arch.walk_mmu; void *data = val; int r = X86EMUL_CONTINUE; while (bytes) { - gpa_t gpa = vcpu->arch.walk_mmu->gva_to_gpa(vcpu, addr, access, - exception); + gpa_t gpa = mmu->gva_to_gpa(vcpu, mmu, addr, access, exception); unsigned offset = addr & (PAGE_SIZE-1); unsigned toread = min(bytes, (unsigned)PAGE_SIZE - offset); int ret; @@ -6585,13 +6707,14 @@ static int kvm_fetch_guest_virt(struct x86_emulate_ctxt *ctxt, struct x86_exception *exception) { struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt); + struct kvm_mmu *mmu = vcpu->arch.walk_mmu; u32 access = (static_call(kvm_x86_get_cpl)(vcpu) == 3) ? PFERR_USER_MASK : 0; unsigned offset; int ret; /* Inline kvm_read_guest_virt_helper for speed. */ - gpa_t gpa = vcpu->arch.walk_mmu->gva_to_gpa(vcpu, addr, access|PFERR_FETCH_MASK, - exception); + gpa_t gpa = mmu->gva_to_gpa(vcpu, mmu, addr, access|PFERR_FETCH_MASK, + exception); if (unlikely(gpa == UNMAPPED_GVA)) return X86EMUL_PROPAGATE_FAULT; @@ -6650,13 +6773,12 @@ static int kvm_write_guest_virt_helper(gva_t addr, void *val, unsigned int bytes struct kvm_vcpu *vcpu, u32 access, struct x86_exception *exception) { + struct kvm_mmu *mmu = vcpu->arch.walk_mmu; void *data = val; int r = X86EMUL_CONTINUE; while (bytes) { - gpa_t gpa = vcpu->arch.walk_mmu->gva_to_gpa(vcpu, addr, - access, - exception); + gpa_t gpa = mmu->gva_to_gpa(vcpu, mmu, addr, access, exception); unsigned offset = addr & (PAGE_SIZE-1); unsigned towrite = min(bytes, (unsigned)PAGE_SIZE - offset); int ret; @@ -6743,6 +6865,7 @@ static int vcpu_mmio_gva_to_gpa(struct kvm_vcpu *vcpu, unsigned long gva, gpa_t *gpa, struct x86_exception *exception, bool write) { + struct kvm_mmu *mmu = vcpu->arch.walk_mmu; u32 access = ((static_call(kvm_x86_get_cpl)(vcpu) == 3) ? PFERR_USER_MASK : 0) | (write ? PFERR_WRITE_MASK : 0); @@ -6760,7 +6883,7 @@ static int vcpu_mmio_gva_to_gpa(struct kvm_vcpu *vcpu, unsigned long gva, return 1; } - *gpa = vcpu->arch.walk_mmu->gva_to_gpa(vcpu, gva, access, exception); + *gpa = mmu->gva_to_gpa(vcpu, mmu, gva, access, exception); if (*gpa == UNMAPPED_GVA) return -1; @@ -7394,7 +7517,8 @@ static int emulator_get_msr(struct x86_emulate_ctxt *ctxt, r = kvm_get_msr(vcpu, msr_index, pdata); - if (r && kvm_get_msr_user_space(vcpu, msr_index, r)) { + if (r && kvm_msr_user_space(vcpu, msr_index, KVM_EXIT_X86_RDMSR, 0, + complete_emulated_rdmsr, r)) { /* Bounce to user space */ return X86EMUL_IO_NEEDED; } @@ -7410,7 +7534,8 @@ static int emulator_set_msr(struct x86_emulate_ctxt *ctxt, r = kvm_set_msr(vcpu, msr_index, data); - if (r && kvm_set_msr_user_space(vcpu, msr_index, data, r)) { + if (r && kvm_msr_user_space(vcpu, msr_index, KVM_EXIT_X86_WRMSR, data, + complete_emulated_msr_access, r)) { /* Bounce to user space */ return X86EMUL_IO_NEEDED; } @@ -7961,6 +8086,8 @@ int kvm_skip_emulated_instruction(struct kvm_vcpu *vcpu) if (unlikely(!r)) return 0; + kvm_pmu_trigger_event(vcpu, PERF_COUNT_HW_INSTRUCTIONS); + /* * rflags is the old, "raw" value of the flags. The new value has * not been saved yet. @@ -8128,12 +8255,23 @@ int x86_emulate_instruction(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, } /* - * 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. + * EMULTYPE_SKIP without EMULTYPE_COMPLETE_USER_EXIT 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->mode != X86EMUL_MODE_PROT64) + ctxt->eip = (u32)ctxt->_eip; + else + ctxt->eip = ctxt->_eip; + + if (emulation_type & EMULTYPE_COMPLETE_USER_EXIT) { + r = 1; + goto writeback; + } + + kvm_rip_write(vcpu, ctxt->eip); if (ctxt->eflags & X86_EFLAGS_RF) kvm_set_rflags(vcpu, ctxt->eflags & ~X86_EFLAGS_RF); return 1; @@ -8197,17 +8335,24 @@ restart: writeback = false; r = 0; vcpu->arch.complete_userspace_io = complete_emulated_mmio; + } else if (vcpu->arch.complete_userspace_io) { + writeback = false; + r = 0; } else if (r == EMULATION_RESTART) goto restart; else r = 1; +writeback: if (writeback) { unsigned long rflags = static_call(kvm_x86_get_rflags)(vcpu); toggle_interruptibility(vcpu, ctxt->interruptibility); vcpu->arch.emulate_regs_need_sync_to_vcpu = false; if (!ctxt->have_exception || exception_type(ctxt->exception.vector) == EXCPT_TRAP) { + kvm_pmu_trigger_event(vcpu, PERF_COUNT_HW_INSTRUCTIONS); + if (ctxt->is_branch) + kvm_pmu_trigger_event(vcpu, PERF_COUNT_HW_BRANCH_INSTRUCTIONS); kvm_rip_write(vcpu, ctxt->eip); if (r && (ctxt->tf || (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP))) r = kvm_vcpu_do_singlestep(vcpu); @@ -8394,7 +8539,8 @@ static void __kvmclock_cpufreq_notifier(struct cpufreq_freqs *freq, int cpu) { struct kvm *kvm; struct kvm_vcpu *vcpu; - int i, send_ipi = 0; + int send_ipi = 0; + unsigned long i; /* * We allow guests to temporarily run on slowing clocks, @@ -8523,9 +8669,8 @@ static void kvm_timer_init(void) static void pvclock_gtod_update_fn(struct work_struct *work) { struct kvm *kvm; - struct kvm_vcpu *vcpu; - int i; + unsigned long i; mutex_lock(&kvm_lock); list_for_each_entry(kvm, &vm_list, vm_list) @@ -8683,8 +8828,15 @@ void kvm_arch_exit(void) #endif } -static int __kvm_vcpu_halt(struct kvm_vcpu *vcpu, int state, int reason) +static int __kvm_emulate_halt(struct kvm_vcpu *vcpu, int state, int reason) { + /* + * The vCPU has halted, e.g. executed HLT. Update the run state if the + * local APIC is in-kernel, the run loop will detect the non-runnable + * state and halt the vCPU. Exit to userspace if the local APIC is + * managed by userspace, in which case userspace is responsible for + * handling wake events. + */ ++vcpu->stat.halt_exits; if (lapic_in_kernel(vcpu)) { vcpu->arch.mp_state = state; @@ -8695,11 +8847,11 @@ static int __kvm_vcpu_halt(struct kvm_vcpu *vcpu, int state, int reason) } } -int kvm_vcpu_halt(struct kvm_vcpu *vcpu) +int kvm_emulate_halt_noskip(struct kvm_vcpu *vcpu) { - return __kvm_vcpu_halt(vcpu, KVM_MP_STATE_HALTED, KVM_EXIT_HLT); + return __kvm_emulate_halt(vcpu, KVM_MP_STATE_HALTED, KVM_EXIT_HLT); } -EXPORT_SYMBOL_GPL(kvm_vcpu_halt); +EXPORT_SYMBOL_GPL(kvm_emulate_halt_noskip); int kvm_emulate_halt(struct kvm_vcpu *vcpu) { @@ -8708,7 +8860,7 @@ int kvm_emulate_halt(struct kvm_vcpu *vcpu) * TODO: we might be squashing a GUESTDBG_SINGLESTEP-triggered * KVM_EXIT_DEBUG here. */ - return kvm_vcpu_halt(vcpu) && ret; + return kvm_emulate_halt_noskip(vcpu) && ret; } EXPORT_SYMBOL_GPL(kvm_emulate_halt); @@ -8716,7 +8868,8 @@ int kvm_emulate_ap_reset_hold(struct kvm_vcpu *vcpu) { int ret = kvm_skip_emulated_instruction(vcpu); - return __kvm_vcpu_halt(vcpu, KVM_MP_STATE_AP_RESET_HOLD, KVM_EXIT_AP_RESET_HOLD) && ret; + return __kvm_emulate_halt(vcpu, KVM_MP_STATE_AP_RESET_HOLD, + KVM_EXIT_AP_RESET_HOLD) && ret; } EXPORT_SYMBOL_GPL(kvm_emulate_ap_reset_hold); @@ -9819,6 +9972,9 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) if (test_thread_flag(TIF_NEED_FPU_LOAD)) switch_fpu_return(); + if (vcpu->arch.guest_fpu.xfd_err) + wrmsrl(MSR_IA32_XFD_ERR, vcpu->arch.guest_fpu.xfd_err); + if (unlikely(vcpu->arch.switch_db_regs)) { set_debugreg(0, 7); set_debugreg(vcpu->arch.eff_db[0], 0); @@ -9880,8 +10036,19 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) vcpu->mode = OUTSIDE_GUEST_MODE; smp_wmb(); + /* + * Sync xfd before calling handle_exit_irqoff() which may + * rely on the fact that guest_fpu::xfd is up-to-date (e.g. + * in #NM irqoff handler). + */ + if (vcpu->arch.xfd_no_write_intercept) + fpu_sync_guest_vmexit_xfd_state(); + static_call(kvm_x86_handle_exit_irqoff)(vcpu); + if (vcpu->arch.guest_fpu.xfd_err) + wrmsrl(MSR_IA32_XFD_ERR, 0); + /* * Consume any pending interrupts, including the possible source of * VM-Exit on SVM and any ticks that occur between VM-Exit and now. @@ -9949,7 +10116,10 @@ static inline int vcpu_block(struct kvm *kvm, struct kvm_vcpu *vcpu) if (!kvm_arch_vcpu_runnable(vcpu) && (!kvm_x86_ops.pre_block || static_call(kvm_x86_pre_block)(vcpu) == 0)) { srcu_read_unlock(&kvm->srcu, vcpu->srcu_idx); - kvm_vcpu_block(vcpu); + if (vcpu->arch.mp_state == KVM_MP_STATE_HALTED) + kvm_vcpu_halt(vcpu); + else + kvm_vcpu_block(vcpu); vcpu->srcu_idx = srcu_read_lock(&kvm->srcu); if (kvm_x86_ops.post_block) @@ -10509,7 +10679,8 @@ static int __set_sregs_common(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; - kvm_register_mark_available(vcpu, VCPU_EXREG_CR3); + kvm_register_mark_dirty(vcpu, VCPU_EXREG_CR3); + static_call_cond(kvm_x86_post_set_cr3)(vcpu, sregs->cr3); kvm_set_cr8(vcpu, sregs->cr8); @@ -10526,7 +10697,7 @@ static int __set_sregs_common(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs, if (update_pdptrs) { idx = srcu_read_lock(&vcpu->kvm->srcu); if (is_pae_paging(vcpu)) { - load_pdptrs(vcpu, vcpu->arch.walk_mmu, kvm_read_cr3(vcpu)); + load_pdptrs(vcpu, kvm_read_cr3(vcpu)); *mmu_reset_needed = 1; } srcu_read_unlock(&vcpu->kvm->srcu, idx); @@ -10624,7 +10795,7 @@ static void kvm_arch_vcpu_guestdbg_update_apicv_inhibit(struct kvm *kvm) { bool inhibit = false; struct kvm_vcpu *vcpu; - int i; + unsigned long i; down_write(&kvm->arch.apicv_update_lock); @@ -11112,7 +11283,7 @@ int kvm_arch_hardware_enable(void) { struct kvm *kvm; struct kvm_vcpu *vcpu; - int i; + unsigned long i; int ret; u64 local_tsc; u64 max_tsc = 0; @@ -11369,7 +11540,7 @@ static void kvm_unload_vcpu_mmu(struct kvm_vcpu *vcpu) static void kvm_free_vcpus(struct kvm *kvm) { - unsigned int i; + unsigned long i; struct kvm_vcpu *vcpu; /* @@ -11379,15 +11550,8 @@ static void kvm_free_vcpus(struct kvm *kvm) kvm_clear_async_pf_completion_queue(vcpu); kvm_unload_vcpu_mmu(vcpu); } - kvm_for_each_vcpu(i, vcpu, kvm) - kvm_vcpu_destroy(vcpu); - - mutex_lock(&kvm->lock); - for (i = 0; i < atomic_read(&kvm->online_vcpus); i++) - kvm->vcpus[i] = NULL; - atomic_set(&kvm->online_vcpus, 0); - mutex_unlock(&kvm->lock); + kvm_destroy_vcpus(kvm); } void kvm_arch_sync_events(struct kvm *kvm) @@ -11555,9 +11719,9 @@ int memslot_rmap_alloc(struct kvm_memory_slot *slot, unsigned long npages) } static int kvm_alloc_memslot_metadata(struct kvm *kvm, - struct kvm_memory_slot *slot, - unsigned long npages) + struct kvm_memory_slot *slot) { + unsigned long npages = slot->npages; int i, r; /* @@ -11622,7 +11786,7 @@ out_free: void kvm_arch_memslots_updated(struct kvm *kvm, u64 gen) { struct kvm_vcpu *vcpu; - int i; + unsigned long i; /* * memslots->generation has been incremented. @@ -11636,13 +11800,18 @@ void kvm_arch_memslots_updated(struct kvm *kvm, u64 gen) } int kvm_arch_prepare_memory_region(struct kvm *kvm, - struct kvm_memory_slot *memslot, - const struct kvm_userspace_memory_region *mem, - enum kvm_mr_change change) + const struct kvm_memory_slot *old, + struct kvm_memory_slot *new, + enum kvm_mr_change change) { if (change == KVM_MR_CREATE || change == KVM_MR_MOVE) - return kvm_alloc_memslot_metadata(kvm, memslot, - mem->memory_size >> PAGE_SHIFT); + return kvm_alloc_memslot_metadata(kvm, new); + + if (change == KVM_MR_FLAGS_ONLY) + memcpy(&new->arch, &old->arch, sizeof(old->arch)); + else if (WARN_ON_ONCE(change != KVM_MR_DELETE)) + return -EIO; + return 0; } @@ -11666,13 +11835,15 @@ static void kvm_mmu_slot_apply_flags(struct kvm *kvm, const struct kvm_memory_slot *new, enum kvm_mr_change change) { - bool log_dirty_pages = new->flags & KVM_MEM_LOG_DIRTY_PAGES; + u32 old_flags = old ? old->flags : 0; + u32 new_flags = new ? new->flags : 0; + bool log_dirty_pages = new_flags & KVM_MEM_LOG_DIRTY_PAGES; /* * Update CPU dirty logging if dirty logging is being toggled. This * applies to all operations. */ - if ((old->flags ^ new->flags) & KVM_MEM_LOG_DIRTY_PAGES) + if ((old_flags ^ new_flags) & KVM_MEM_LOG_DIRTY_PAGES) kvm_mmu_update_cpu_dirty_logging(kvm, log_dirty_pages); /* @@ -11690,7 +11861,7 @@ static void kvm_mmu_slot_apply_flags(struct kvm *kvm, * MOVE/DELETE: The old mappings will already have been cleaned up by * kvm_arch_flush_shadow_memslot(). */ - if ((change != KVM_MR_FLAGS_ONLY) || (new->flags & KVM_MEM_READONLY)) + if ((change != KVM_MR_FLAGS_ONLY) || (new_flags & KVM_MEM_READONLY)) return; /* @@ -11698,7 +11869,7 @@ static void kvm_mmu_slot_apply_flags(struct kvm *kvm, * other flag is LOG_DIRTY_PAGES, i.e. something is wrong if dirty * logging isn't being toggled on or off. */ - if (WARN_ON_ONCE(!((old->flags ^ new->flags) & KVM_MEM_LOG_DIRTY_PAGES))) + if (WARN_ON_ONCE(!((old_flags ^ new_flags) & KVM_MEM_LOG_DIRTY_PAGES))) return; if (!log_dirty_pages) { @@ -11734,14 +11905,18 @@ static void kvm_mmu_slot_apply_flags(struct kvm *kvm, } void kvm_arch_commit_memory_region(struct kvm *kvm, - const struct kvm_userspace_memory_region *mem, struct kvm_memory_slot *old, const struct kvm_memory_slot *new, enum kvm_mr_change change) { - if (!kvm->arch.n_requested_mmu_pages) - kvm_mmu_change_mmu_pages(kvm, - kvm_mmu_calculate_default_mmu_pages(kvm)); + if (!kvm->arch.n_requested_mmu_pages && + (change == KVM_MR_CREATE || change == KVM_MR_DELETE)) { + unsigned long nr_mmu_pages; + + nr_mmu_pages = kvm->nr_memslot_pages / KVM_MEMSLOT_PAGES_TO_MMU_PAGES_RATIO; + nr_mmu_pages = max(nr_mmu_pages, KVM_MIN_ALLOC_MMU_PAGES); + kvm_mmu_change_mmu_pages(kvm, nr_mmu_pages); + } kvm_mmu_slot_apply_flags(kvm, old, new, change); @@ -12256,12 +12431,13 @@ EXPORT_SYMBOL_GPL(kvm_spec_ctrl_test_value); void kvm_fixup_and_inject_pf_error(struct kvm_vcpu *vcpu, gva_t gva, u16 error_code) { + struct kvm_mmu *mmu = vcpu->arch.walk_mmu; struct x86_exception fault; u32 access = error_code & (PFERR_WRITE_MASK | PFERR_FETCH_MASK | PFERR_USER_MASK); if (!(error_code & PFERR_PRESENT_MASK) || - vcpu->arch.walk_mmu->gva_to_gpa(vcpu, gva, access, &fault) != UNMAPPED_GVA) { + mmu->gva_to_gpa(vcpu, mmu, gva, access, &fault) != UNMAPPED_GVA) { /* * If vcpu->arch.walk_mmu->gva_to_gpa succeeded, the page * tables probably do not match the TLB. Just proceed @@ -12598,6 +12774,7 @@ EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_avic_unaccelerated_access); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_avic_incomplete_ipi); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_avic_ga_log); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_apicv_update_request); +EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_apicv_accept_irq); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_vmgexit_enter); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_vmgexit_exit); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_vmgexit_msr_protocol_enter); diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h index 6aeca8f1da91..bec8ed090abc 100644 --- a/arch/x86/kvm/x86.h +++ b/arch/x86/kvm/x86.h @@ -301,7 +301,6 @@ static inline bool kvm_vcpu_latch_init(struct kvm_vcpu *vcpu) return is_smm(vcpu) || static_call(kvm_x86_apic_init_signal_blocked)(vcpu); } -void kvm_write_wall_clock(struct kvm *kvm, gpa_t wall_clock, int sec_hi_ofs); void kvm_inject_realmode_interrupt(struct kvm_vcpu *vcpu, int irq, int inc_eip); u64 get_kvmclock_ns(struct kvm *kvm); diff --git a/arch/x86/kvm/xen.c b/arch/x86/kvm/xen.c index dff2bdf9507a..0e3f7d6e9fd7 100644 --- a/arch/x86/kvm/xen.c +++ b/arch/x86/kvm/xen.c @@ -16,6 +16,7 @@ #include <trace/events/kvm.h> #include <xen/interface/xen.h> #include <xen/interface/vcpu.h> +#include <xen/interface/event_channel.h> #include "trace.h" @@ -23,38 +24,77 @@ DEFINE_STATIC_KEY_DEFERRED_FALSE(kvm_xen_enabled, HZ); static int kvm_xen_shared_info_init(struct kvm *kvm, gfn_t gfn) { + struct gfn_to_pfn_cache *gpc = &kvm->arch.xen.shinfo_cache; + struct pvclock_wall_clock *wc; gpa_t gpa = gfn_to_gpa(gfn); - int wc_ofs, sec_hi_ofs; + u32 *wc_sec_hi; + u32 wc_version; + u64 wall_nsec; int ret = 0; int idx = srcu_read_lock(&kvm->srcu); - if (kvm_is_error_hva(gfn_to_hva(kvm, gfn))) { - ret = -EFAULT; + if (gfn == GPA_INVALID) { + kvm_gfn_to_pfn_cache_destroy(kvm, gpc); goto out; } - kvm->arch.xen.shinfo_gfn = gfn; + + do { + ret = kvm_gfn_to_pfn_cache_init(kvm, gpc, NULL, false, true, + gpa, PAGE_SIZE, false); + if (ret) + goto out; + + /* + * This code mirrors kvm_write_wall_clock() except that it writes + * directly through the pfn cache and doesn't mark the page dirty. + */ + wall_nsec = ktime_get_real_ns() - get_kvmclock_ns(kvm); + + /* It could be invalid again already, so we need to check */ + read_lock_irq(&gpc->lock); + + if (gpc->valid) + break; + + read_unlock_irq(&gpc->lock); + } while (1); /* Paranoia checks on the 32-bit struct layout */ BUILD_BUG_ON(offsetof(struct compat_shared_info, wc) != 0x900); BUILD_BUG_ON(offsetof(struct compat_shared_info, arch.wc_sec_hi) != 0x924); BUILD_BUG_ON(offsetof(struct pvclock_vcpu_time_info, version) != 0); - /* 32-bit location by default */ - wc_ofs = offsetof(struct compat_shared_info, wc); - sec_hi_ofs = offsetof(struct compat_shared_info, arch.wc_sec_hi); - #ifdef CONFIG_X86_64 /* Paranoia checks on the 64-bit struct layout */ BUILD_BUG_ON(offsetof(struct shared_info, wc) != 0xc00); BUILD_BUG_ON(offsetof(struct shared_info, wc_sec_hi) != 0xc0c); - if (kvm->arch.xen.long_mode) { - wc_ofs = offsetof(struct shared_info, wc); - sec_hi_ofs = offsetof(struct shared_info, wc_sec_hi); - } + if (IS_ENABLED(CONFIG_64BIT) && kvm->arch.xen.long_mode) { + struct shared_info *shinfo = gpc->khva; + + wc_sec_hi = &shinfo->wc_sec_hi; + wc = &shinfo->wc; + } else #endif + { + struct compat_shared_info *shinfo = gpc->khva; + + wc_sec_hi = &shinfo->arch.wc_sec_hi; + wc = &shinfo->wc; + } + + /* Increment and ensure an odd value */ + wc_version = wc->version = (wc->version + 1) | 1; + smp_wmb(); + + wc->nsec = do_div(wall_nsec, 1000000000); + wc->sec = (u32)wall_nsec; + *wc_sec_hi = wall_nsec >> 32; + smp_wmb(); + + wc->version = wc_version + 1; + read_unlock_irq(&gpc->lock); - kvm_write_wall_clock(kvm, gpa + wc_ofs, sec_hi_ofs - wc_ofs); kvm_make_all_cpus_request(kvm, KVM_REQ_MASTERCLOCK_UPDATE); out: @@ -190,6 +230,8 @@ void kvm_xen_update_runstate_guest(struct kvm_vcpu *v, int state) int __kvm_xen_has_interrupt(struct kvm_vcpu *v) { + unsigned long evtchn_pending_sel = READ_ONCE(v->arch.xen.evtchn_pending_sel); + bool atomic = in_atomic() || !task_is_running(current); int err; u8 rc = 0; @@ -199,6 +241,9 @@ int __kvm_xen_has_interrupt(struct kvm_vcpu *v) */ struct gfn_to_hva_cache *ghc = &v->arch.xen.vcpu_info_cache; struct kvm_memslots *slots = kvm_memslots(v->kvm); + bool ghc_valid = slots->generation == ghc->generation && + !kvm_is_error_hva(ghc->hva) && ghc->memslot; + unsigned int offset = offsetof(struct vcpu_info, evtchn_upcall_pending); /* No need for compat handling here */ @@ -214,8 +259,7 @@ int __kvm_xen_has_interrupt(struct kvm_vcpu *v) * cache in kvm_read_guest_offset_cached(), but just uses * __get_user() instead. And falls back to the slow path. */ - if (likely(slots->generation == ghc->generation && - !kvm_is_error_hva(ghc->hva) && ghc->memslot)) { + if (!evtchn_pending_sel && ghc_valid) { /* Fast path */ pagefault_disable(); err = __get_user(rc, (u8 __user *)ghc->hva + offset); @@ -234,11 +278,82 @@ int __kvm_xen_has_interrupt(struct kvm_vcpu *v) * and we'll end up getting called again from a context where we *can* * fault in the page and wait for it. */ - if (in_atomic() || !task_is_running(current)) + if (atomic) return 1; - kvm_read_guest_offset_cached(v->kvm, ghc, &rc, offset, - sizeof(rc)); + if (!ghc_valid) { + err = kvm_gfn_to_hva_cache_init(v->kvm, ghc, ghc->gpa, ghc->len); + if (err || !ghc->memslot) { + /* + * If this failed, userspace has screwed up the + * vcpu_info mapping. No interrupts for you. + */ + return 0; + } + } + + /* + * Now we have a valid (protected by srcu) userspace HVA in + * ghc->hva which points to the struct vcpu_info. If there + * are any bits in the in-kernel evtchn_pending_sel then + * we need to write those to the guest vcpu_info and set + * its evtchn_upcall_pending flag. If there aren't any bits + * to add, we only want to *check* evtchn_upcall_pending. + */ + if (evtchn_pending_sel) { + bool long_mode = v->kvm->arch.xen.long_mode; + + if (!user_access_begin((void __user *)ghc->hva, sizeof(struct vcpu_info))) + return 0; + + if (IS_ENABLED(CONFIG_64BIT) && long_mode) { + struct vcpu_info __user *vi = (void __user *)ghc->hva; + + /* Attempt to set the evtchn_pending_sel bits in the + * guest, and if that succeeds then clear the same + * bits in the in-kernel version. */ + asm volatile("1:\t" LOCK_PREFIX "orq %0, %1\n" + "\tnotq %0\n" + "\t" LOCK_PREFIX "andq %0, %2\n" + "2:\n" + "\t.section .fixup,\"ax\"\n" + "3:\tjmp\t2b\n" + "\t.previous\n" + _ASM_EXTABLE_UA(1b, 3b) + : "=r" (evtchn_pending_sel), + "+m" (vi->evtchn_pending_sel), + "+m" (v->arch.xen.evtchn_pending_sel) + : "0" (evtchn_pending_sel)); + } else { + struct compat_vcpu_info __user *vi = (void __user *)ghc->hva; + u32 evtchn_pending_sel32 = evtchn_pending_sel; + + /* Attempt to set the evtchn_pending_sel bits in the + * guest, and if that succeeds then clear the same + * bits in the in-kernel version. */ + asm volatile("1:\t" LOCK_PREFIX "orl %0, %1\n" + "\tnotl %0\n" + "\t" LOCK_PREFIX "andl %0, %2\n" + "2:\n" + "\t.section .fixup,\"ax\"\n" + "3:\tjmp\t2b\n" + "\t.previous\n" + _ASM_EXTABLE_UA(1b, 3b) + : "=r" (evtchn_pending_sel32), + "+m" (vi->evtchn_pending_sel), + "+m" (v->arch.xen.evtchn_pending_sel) + : "0" (evtchn_pending_sel32)); + } + rc = 1; + unsafe_put_user(rc, (u8 __user *)ghc->hva + offset, err); + + err: + user_access_end(); + + mark_page_dirty_in_slot(v->kvm, ghc->memslot, ghc->gpa >> PAGE_SHIFT); + } else { + __get_user(rc, (u8 __user *)ghc->hva + offset); + } return rc; } @@ -260,15 +375,9 @@ int kvm_xen_hvm_set_attr(struct kvm *kvm, struct kvm_xen_hvm_attr *data) break; case KVM_XEN_ATTR_TYPE_SHARED_INFO: - if (data->u.shared_info.gfn == GPA_INVALID) { - kvm->arch.xen.shinfo_gfn = GPA_INVALID; - r = 0; - break; - } r = kvm_xen_shared_info_init(kvm, data->u.shared_info.gfn); break; - case KVM_XEN_ATTR_TYPE_UPCALL_VECTOR: if (data->u.vector && data->u.vector < 0x10) r = -EINVAL; @@ -299,7 +408,10 @@ int kvm_xen_hvm_get_attr(struct kvm *kvm, struct kvm_xen_hvm_attr *data) break; case KVM_XEN_ATTR_TYPE_SHARED_INFO: - data->u.shared_info.gfn = kvm->arch.xen.shinfo_gfn; + if (kvm->arch.xen.shinfo_cache.active) + data->u.shared_info.gfn = gpa_to_gfn(kvm->arch.xen.shinfo_cache.gpa); + else + data->u.shared_info.gfn = GPA_INVALID; r = 0; break; @@ -661,11 +773,12 @@ int kvm_xen_hvm_config(struct kvm *kvm, struct kvm_xen_hvm_config *xhc) void kvm_xen_init_vm(struct kvm *kvm) { - kvm->arch.xen.shinfo_gfn = GPA_INVALID; } void kvm_xen_destroy_vm(struct kvm *kvm) { + kvm_gfn_to_pfn_cache_destroy(kvm, &kvm->arch.xen.shinfo_cache); + if (kvm->arch.xen_hvm_config.msr) static_branch_slow_dec_deferred(&kvm_xen_enabled); } @@ -737,3 +850,179 @@ int kvm_xen_hypercall(struct kvm_vcpu *vcpu) return 0; } + +static inline int max_evtchn_port(struct kvm *kvm) +{ + if (IS_ENABLED(CONFIG_64BIT) && kvm->arch.xen.long_mode) + return EVTCHN_2L_NR_CHANNELS; + else + return COMPAT_EVTCHN_2L_NR_CHANNELS; +} + +/* + * This follows the kvm_set_irq() API, so it returns: + * < 0 Interrupt was ignored (masked or not delivered for other reasons) + * = 0 Interrupt was coalesced (previous irq is still pending) + * > 0 Number of CPUs interrupt was delivered to + */ +int kvm_xen_set_evtchn_fast(struct kvm_kernel_irq_routing_entry *e, + struct kvm *kvm) +{ + struct gfn_to_pfn_cache *gpc = &kvm->arch.xen.shinfo_cache; + struct kvm_vcpu *vcpu; + unsigned long *pending_bits, *mask_bits; + unsigned long flags; + int port_word_bit; + bool kick_vcpu = false; + int idx; + int rc; + + vcpu = kvm_get_vcpu_by_id(kvm, e->xen_evtchn.vcpu); + if (!vcpu) + return -1; + + if (!vcpu->arch.xen.vcpu_info_set) + return -1; + + if (e->xen_evtchn.port >= max_evtchn_port(kvm)) + return -1; + + rc = -EWOULDBLOCK; + read_lock_irqsave(&gpc->lock, flags); + + idx = srcu_read_lock(&kvm->srcu); + if (!kvm_gfn_to_pfn_cache_check(kvm, gpc, gpc->gpa, PAGE_SIZE)) + goto out_rcu; + + if (IS_ENABLED(CONFIG_64BIT) && kvm->arch.xen.long_mode) { + struct shared_info *shinfo = gpc->khva; + pending_bits = (unsigned long *)&shinfo->evtchn_pending; + mask_bits = (unsigned long *)&shinfo->evtchn_mask; + port_word_bit = e->xen_evtchn.port / 64; + } else { + struct compat_shared_info *shinfo = gpc->khva; + pending_bits = (unsigned long *)&shinfo->evtchn_pending; + mask_bits = (unsigned long *)&shinfo->evtchn_mask; + port_word_bit = e->xen_evtchn.port / 32; + } + + /* + * If this port wasn't already set, and if it isn't masked, then + * we try to set the corresponding bit in the in-kernel shadow of + * evtchn_pending_sel for the target vCPU. And if *that* wasn't + * already set, then we kick the vCPU in question to write to the + * *real* evtchn_pending_sel in its own guest vcpu_info struct. + */ + if (test_and_set_bit(e->xen_evtchn.port, pending_bits)) { + rc = 0; /* It was already raised */ + } else if (test_bit(e->xen_evtchn.port, mask_bits)) { + rc = -1; /* Masked */ + } else { + rc = 1; /* Delivered. But was the vCPU waking already? */ + if (!test_and_set_bit(port_word_bit, &vcpu->arch.xen.evtchn_pending_sel)) + kick_vcpu = true; + } + + out_rcu: + srcu_read_unlock(&kvm->srcu, idx); + read_unlock_irqrestore(&gpc->lock, flags); + + if (kick_vcpu) { + kvm_make_request(KVM_REQ_EVENT, vcpu); + kvm_vcpu_kick(vcpu); + } + + return rc; +} + +/* This is the version called from kvm_set_irq() as the .set function */ +static int evtchn_set_fn(struct kvm_kernel_irq_routing_entry *e, struct kvm *kvm, + int irq_source_id, int level, bool line_status) +{ + bool mm_borrowed = false; + int rc; + + if (!level) + return -1; + + rc = kvm_xen_set_evtchn_fast(e, kvm); + if (rc != -EWOULDBLOCK) + return rc; + + if (current->mm != kvm->mm) { + /* + * If not on a thread which already belongs to this KVM, + * we'd better be in the irqfd workqueue. + */ + if (WARN_ON_ONCE(current->mm)) + return -EINVAL; + + kthread_use_mm(kvm->mm); + mm_borrowed = true; + } + + /* + * For the irqfd workqueue, using the main kvm->lock mutex is + * fine since this function is invoked from kvm_set_irq() with + * no other lock held, no srcu. In future if it will be called + * directly from a vCPU thread (e.g. on hypercall for an IPI) + * then it may need to switch to using a leaf-node mutex for + * serializing the shared_info mapping. + */ + mutex_lock(&kvm->lock); + + /* + * It is theoretically possible for the page to be unmapped + * and the MMU notifier to invalidate the shared_info before + * we even get to use it. In that case, this looks like an + * infinite loop. It was tempting to do it via the userspace + * HVA instead... but that just *hides* the fact that it's + * an infinite loop, because if a fault occurs and it waits + * for the page to come back, it can *still* immediately + * fault and have to wait again, repeatedly. + * + * Conversely, the page could also have been reinstated by + * another thread before we even obtain the mutex above, so + * check again *first* before remapping it. + */ + do { + struct gfn_to_pfn_cache *gpc = &kvm->arch.xen.shinfo_cache; + int idx; + + rc = kvm_xen_set_evtchn_fast(e, kvm); + if (rc != -EWOULDBLOCK) + break; + + idx = srcu_read_lock(&kvm->srcu); + rc = kvm_gfn_to_pfn_cache_refresh(kvm, gpc, gpc->gpa, + PAGE_SIZE, false); + srcu_read_unlock(&kvm->srcu, idx); + } while(!rc); + + mutex_unlock(&kvm->lock); + + if (mm_borrowed) + kthread_unuse_mm(kvm->mm); + + return rc; +} + +int kvm_xen_setup_evtchn(struct kvm *kvm, + struct kvm_kernel_irq_routing_entry *e, + const struct kvm_irq_routing_entry *ue) + +{ + if (ue->u.xen_evtchn.port >= max_evtchn_port(kvm)) + return -EINVAL; + + /* We only support 2 level event channels for now */ + if (ue->u.xen_evtchn.priority != KVM_IRQ_ROUTING_XEN_EVTCHN_PRIO_2LEVEL) + return -EINVAL; + + e->xen_evtchn.port = ue->u.xen_evtchn.port; + e->xen_evtchn.vcpu = ue->u.xen_evtchn.vcpu; + e->xen_evtchn.priority = ue->u.xen_evtchn.priority; + e->set = evtchn_set_fn; + + return 0; +} diff --git a/arch/x86/kvm/xen.h b/arch/x86/kvm/xen.h index cc0cf5f37450..adbcc9ed59db 100644 --- a/arch/x86/kvm/xen.h +++ b/arch/x86/kvm/xen.h @@ -24,6 +24,12 @@ int kvm_xen_hvm_config(struct kvm *kvm, struct kvm_xen_hvm_config *xhc); void kvm_xen_init_vm(struct kvm *kvm); void kvm_xen_destroy_vm(struct kvm *kvm); +int kvm_xen_set_evtchn_fast(struct kvm_kernel_irq_routing_entry *e, + struct kvm *kvm); +int kvm_xen_setup_evtchn(struct kvm *kvm, + struct kvm_kernel_irq_routing_entry *e, + const struct kvm_irq_routing_entry *ue); + static inline bool kvm_xen_msr_enabled(struct kvm *kvm) { return static_branch_unlikely(&kvm_xen_enabled.key) && @@ -134,6 +140,9 @@ struct compat_shared_info { struct compat_arch_shared_info arch; }; +#define COMPAT_EVTCHN_2L_NR_CHANNELS (8 * \ + sizeof_field(struct compat_shared_info, \ + evtchn_pending)) struct compat_vcpu_runstate_info { int state; uint64_t state_entry_time; |